diff options
Diffstat (limited to 'fs')
660 files changed, 26180 insertions, 15050 deletions
diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 103ca5e1267b..64c58eb26159 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -151,34 +151,6 @@ fscache_checkaux v9fs_cache_inode_check_aux(void *cookie_netfs_data, return FSCACHE_CHECKAUX_OKAY; } -static void v9fs_cache_inode_now_uncached(void *cookie_netfs_data) -{ - struct v9fs_inode *v9inode = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - for (;;) { - nr_pages = pagevec_lookup(&pvec, v9inode->vfs_inode.i_mapping, - first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - const struct fscache_cookie_def v9fs_cache_inode_index_def = { .name = "9p.inode", .type = FSCACHE_COOKIE_TYPE_DATAFILE, @@ -186,7 +158,6 @@ const struct fscache_cookie_def v9fs_cache_inode_index_def = { .get_attr = v9fs_cache_inode_get_attr, .get_aux = v9fs_cache_inode_get_aux, .check_aux = v9fs_cache_inode_check_aux, - .now_uncached = v9fs_cache_inode_now_uncached, }; void v9fs_cache_inode_get_cookie(struct inode *inode) diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index c202930086ed..8fb89ddc6cc7 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -33,6 +33,7 @@ #include <linux/parser.h> #include <linux/idr.h> #include <linux/slab.h> +#include <linux/seq_file.h> #include <net/9p/9p.h> #include <net/9p/client.h> #include <net/9p/transport.h> @@ -82,6 +83,13 @@ static const match_table_t tokens = { {Opt_err, NULL} }; +static const char *const v9fs_cache_modes[nr__p9_cache_modes] = { + [CACHE_NONE] = "none", + [CACHE_MMAP] = "mmap", + [CACHE_LOOSE] = "loose", + [CACHE_FSCACHE] = "fscache", +}; + /* Interpret mount options for cache mode */ static int get_cache_mode(char *s) { @@ -104,6 +112,58 @@ static int get_cache_mode(char *s) return version; } +/* + * Display the mount options in /proc/mounts. + */ +int v9fs_show_options(struct seq_file *m, struct dentry *root) +{ + struct v9fs_session_info *v9ses = root->d_sb->s_fs_info; + + if (v9ses->debug) + seq_printf(m, ",debug=%x", v9ses->debug); + if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID)) + seq_printf(m, ",dfltuid=%u", + from_kuid_munged(&init_user_ns, v9ses->dfltuid)); + if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID)) + seq_printf(m, ",dfltgid=%u", + from_kgid_munged(&init_user_ns, v9ses->dfltgid)); + if (v9ses->afid != ~0) + seq_printf(m, ",afid=%u", v9ses->afid); + if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0) + seq_printf(m, ",uname=%s", v9ses->uname); + if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0) + seq_printf(m, ",aname=%s", v9ses->aname); + if (v9ses->nodev) + seq_puts(m, ",nodevmap"); + if (v9ses->cache) + seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]); +#ifdef CONFIG_9P_FSCACHE + if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE) + seq_printf(m, ",cachetag=%s", v9ses->cachetag); +#endif + + switch (v9ses->flags & V9FS_ACCESS_MASK) { + case V9FS_ACCESS_USER: + seq_puts(m, ",access=user"); + break; + case V9FS_ACCESS_ANY: + seq_puts(m, ",access=any"); + break; + case V9FS_ACCESS_CLIENT: + seq_puts(m, ",access=client"); + break; + case V9FS_ACCESS_SINGLE: + seq_printf(m, ",access=%u", + from_kuid_munged(&init_user_ns, v9ses->uid)); + break; + } + + if (v9ses->flags & V9FS_POSIX_ACL) + seq_puts(m, ",posixacl"); + + return p9_show_client_options(m, v9ses->clnt); +} + /** * v9fs_parse_options - parse mount options into session structure * @v9ses: existing v9fs session information @@ -230,6 +290,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) break; case Opt_cachetag: #ifdef CONFIG_9P_FSCACHE + kfree(v9ses->cachetag); v9ses->cachetag = match_strdup(&args[0]); #endif break; diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 76eaf49abd3a..982e017acadb 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -67,6 +67,7 @@ enum p9_cache_modes { CACHE_MMAP, CACHE_LOOSE, CACHE_FSCACHE, + nr__p9_cache_modes }; /** @@ -137,6 +138,8 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode) return container_of(inode, struct v9fs_inode, vfs_inode); } +extern int v9fs_show_options(struct seq_file *m, struct dentry *root); + struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *, char *); extern void v9fs_session_close(struct v9fs_session_info *v9ses); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index adaf6f6dd858..e1cbdfdb7c68 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -310,9 +310,13 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - if (unlikely(copied < len && !PageUptodate(page))) { - copied = 0; - goto out; + if (!PageUptodate(page)) { + if (unlikely(copied < len)) { + copied = 0; + goto out; + } else if (len == PAGE_SIZE) { + SetPageUptodate(page); + } } /* * No need to use i_size_read() here, the i_size diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 3de3b4a89d89..03c9e325bfbc 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -288,7 +288,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) fl->fl_end = OFFSET_MAX; else fl->fl_end = glock.start + glock.length - 1; - fl->fl_pid = glock.proc_id; + fl->fl_pid = -glock.proc_id; } kfree(glock.client_id); return res; @@ -445,7 +445,7 @@ static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end, struct p9_wstat wstat; int retval; - retval = filemap_write_and_wait_range(inode->i_mapping, start, end); + retval = file_write_and_wait_range(filp, start, end); if (retval) return retval; @@ -468,7 +468,7 @@ int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end, struct inode *inode = filp->f_mapping->host; int retval; - retval = filemap_write_and_wait_range(inode->i_mapping, start, end); + retval = file_write_and_wait_range(filp, start, end); if (retval) return retval; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index a0965fb587a5..8b75463cb211 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -33,7 +33,6 @@ #include <linux/string.h> #include <linux/inet.h> #include <linux/pagemap.h> -#include <linux/seq_file.h> #include <linux/mount.h> #include <linux/idr.h> #include <linux/sched.h> @@ -104,7 +103,6 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses, sb->s_flags |= MS_POSIXACL; #endif - save_mount_options(sb, data); return 0; } @@ -349,7 +347,7 @@ static const struct super_operations v9fs_super_ops = { .destroy_inode = v9fs_destroy_inode, .statfs = simple_statfs, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode, }; @@ -360,7 +358,7 @@ static const struct super_operations v9fs_super_ops_dotl = { .statfs = v9fs_statfs, .drop_inode = v9fs_drop_inode, .evict_inode = v9fs_evict_inode, - .show_options = generic_show_options, + .show_options = v9fs_show_options, .umount_begin = v9fs_umount_begin, .write_inode = v9fs_write_inode_dotl, }; diff --git a/fs/Kconfig b/fs/Kconfig index b0e42b6a96b9..7aee6d699fd6 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -80,7 +80,6 @@ config EXPORTFS_BLOCK_OPS config FILE_LOCKING bool "Enable POSIX file locking API" if EXPERT default y - select PERCPU_RWSEM help This option enables standard file locking support, required for filesystems like NFS and for the flock() system diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c index b573c3b9a328..8cf941c3b511 100644 --- a/fs/affs/amigaffs.c +++ b/fs/affs/amigaffs.c @@ -450,7 +450,7 @@ affs_error(struct super_block *sb, const char *function, const char *fmt, ...) vaf.fmt = fmt; vaf.va = &args; pr_crit("error (device %s): %s(): %pV\n", sb->s_id, function, &vaf); - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) pr_warn("Remounting filesystem read-only\n"); sb->s_flags |= MS_RDONLY; va_end(args); diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c index 675148950fed..2b2112475ec2 100644 --- a/fs/affs/bitmap.c +++ b/fs/affs/bitmap.c @@ -19,7 +19,7 @@ affs_count_free_blocks(struct super_block *sb) pr_debug("%s()\n", __func__); - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; mutex_lock(&AFFS_SB(sb)->s_bmlock); diff --git a/fs/affs/file.c b/fs/affs/file.c index 196ee7f6fdc4..00331810f690 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -954,7 +954,7 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) struct inode *inode = filp->f_mapping->host; int ret, err; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(filp, start, end); if (err) return err; diff --git a/fs/affs/super.c b/fs/affs/super.c index c2c27a8f128e..884bedab7266 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -20,9 +20,11 @@ #include <linux/slab.h> #include <linux/writeback.h> #include <linux/blkdev.h> +#include <linux/seq_file.h> #include "affs.h" static int affs_statfs(struct dentry *dentry, struct kstatfs *buf); +static int affs_show_options(struct seq_file *m, struct dentry *root); static int affs_remount (struct super_block *sb, int *flags, char *data); static void @@ -78,7 +80,7 @@ void affs_mark_sb_dirty(struct super_block *sb) struct affs_sb_info *sbi = AFFS_SB(sb); unsigned long delay; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; spin_lock(&sbi->work_lock); @@ -159,7 +161,7 @@ static const struct super_operations affs_sops = { .sync_fs = affs_sync_fs, .statfs = affs_statfs, .remount_fs = affs_remount, - .show_options = generic_show_options, + .show_options = affs_show_options, }; enum { @@ -293,6 +295,40 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved, return 1; } +static int affs_show_options(struct seq_file *m, struct dentry *root) +{ + struct super_block *sb = root->d_sb; + struct affs_sb_info *sbi = AFFS_SB(sb); + + if (sb->s_blocksize) + seq_printf(m, ",bs=%lu", sb->s_blocksize); + if (affs_test_opt(sbi->s_flags, SF_SETMODE)) + seq_printf(m, ",mode=%o", sbi->s_mode); + if (affs_test_opt(sbi->s_flags, SF_MUFS)) + seq_puts(m, ",mufs"); + if (affs_test_opt(sbi->s_flags, SF_NO_TRUNCATE)) + seq_puts(m, ",nofilenametruncate"); + if (affs_test_opt(sbi->s_flags, SF_PREFIX)) + seq_printf(m, ",prefix=%s", sbi->s_prefix); + if (affs_test_opt(sbi->s_flags, SF_IMMUTABLE)) + seq_puts(m, ",protect"); + if (sbi->s_reserved != 2) + seq_printf(m, ",reserved=%u", sbi->s_reserved); + if (sbi->s_root_block != (sbi->s_reserved + sbi->s_partition_size - 1) / 2) + seq_printf(m, ",root=%u", sbi->s_root_block); + if (affs_test_opt(sbi->s_flags, SF_SETGID)) + seq_printf(m, ",setgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + if (affs_test_opt(sbi->s_flags, SF_SETUID)) + seq_printf(m, ",setuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (affs_test_opt(sbi->s_flags, SF_VERBOSE)) + seq_puts(m, ",verbose"); + if (sbi->s_volume[0]) + seq_printf(m, ",volume=%s", sbi->s_volume); + return 0; +} + /* This function definitely needs to be split up. Some fine day I'll * hopefully have the guts to do so. Until then: sorry for the mess. */ @@ -316,8 +352,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) u8 sig[4]; int ret; - save_mount_options(sb, data); - pr_debug("read_super(%s)\n", data ? (const char *)data : "no options"); sb->s_magic = AFFS_SUPER_MAGIC; @@ -430,7 +464,7 @@ got_root: * not recommended. */ if ((chksum == FS_DCFFS || chksum == MUFS_DCFFS || chksum == FS_DCOFS - || chksum == MUFS_DCOFS) && !(sb->s_flags & MS_RDONLY)) { + || chksum == MUFS_DCOFS) && !sb_rdonly(sb)) { pr_notice("Dircache FS - mounting %s read only\n", sb->s_id); sb->s_flags |= MS_RDONLY; } @@ -548,8 +582,6 @@ affs_remount(struct super_block *sb, int *flags, char *data) } flush_delayed_work(&sbi->sb_work); - if (new_opts) - replace_mount_options(sb, new_opts); sbi->s_flags = mount_flags; sbi->s_mode = mode; @@ -564,7 +596,7 @@ affs_remount(struct super_block *sb, int *flags, char *data) memcpy(sbi->s_volume, volume, 32); spin_unlock(&sbi->symlink_lock); - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) return 0; if (*flags & MS_RDONLY) diff --git a/fs/afs/Makefile b/fs/afs/Makefile index 4f64b95d57bd..095c54165dfd 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -27,6 +27,7 @@ kafs-objs := \ vlocation.o \ vnode.o \ volume.o \ - write.o + write.o \ + xattr.o obj-$(CONFIG_AFS_FS) := kafs.o diff --git a/fs/afs/cache.c b/fs/afs/cache.c index 577763c3d88b..1fe855191261 100644 --- a/fs/afs/cache.c +++ b/fs/afs/cache.c @@ -39,7 +39,6 @@ static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data, static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, const void *buffer, uint16_t buflen); -static void afs_vnode_cache_now_uncached(void *cookie_netfs_data); struct fscache_netfs afs_cache_netfs = { .name = "afs", @@ -75,7 +74,6 @@ struct fscache_cookie_def afs_vnode_cache_index_def = { .get_attr = afs_vnode_cache_get_attr, .get_aux = afs_vnode_cache_get_aux, .check_aux = afs_vnode_cache_check_aux, - .now_uncached = afs_vnode_cache_now_uncached, }; /* @@ -359,44 +357,3 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, _leave(" = SUCCESS"); return FSCACHE_CHECKAUX_OKAY; } - -/* - * indication the cookie is no longer uncached - * - this function is called when the backing store currently caching a cookie - * is removed - * - the netfs should use this to clean up any markers indicating cached pages - * - this is mandatory for any object that may have data - */ -static void afs_vnode_cache_now_uncached(void *cookie_netfs_data) -{ - struct afs_vnode *vnode = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - _enter("{%x,%x,%Lx}", - vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version); - - pagevec_init(&pvec, 0); - first = 0; - - for (;;) { - /* grab a bunch of pages to clean */ - nr_pages = pagevec_lookup(&pvec, vnode->vfs_inode.i_mapping, - first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } - - _leave(""); -} diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 3062cceb5c2a..782d4d05a53b 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -350,7 +350,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) { struct sockaddr_rxrpc srx; struct afs_server *server; - struct uuid_v1 *r; + struct afs_uuid *r; unsigned loop; __be32 *b; int ret; @@ -380,7 +380,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL); + call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); if (!call->request) return -ENOMEM; @@ -453,7 +453,7 @@ static int afs_deliver_cb_probe(struct afs_call *call) static void SRXAFSCB_ProbeUuid(struct work_struct *work) { struct afs_call *call = container_of(work, struct afs_call, work); - struct uuid_v1 *r = call->request; + struct afs_uuid *r = call->request; struct { __be32 match; @@ -476,7 +476,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) */ static int afs_deliver_cb_probe_uuid(struct afs_call *call) { - struct uuid_v1 *r; + struct afs_uuid *r; unsigned loop; __be32 *b; int ret; @@ -502,15 +502,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) } _debug("unmarshall UUID"); - call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL); + call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL); if (!call->request) return -ENOMEM; b = call->buffer; r = call->request; - r->time_low = b[0]; - r->time_mid = htons(ntohl(b[1])); - r->time_hi_and_version = htons(ntohl(b[2])); + r->time_low = ntohl(b[0]); + r->time_mid = ntohl(b[1]); + r->time_hi_and_version = ntohl(b[2]); r->clock_seq_hi_and_reserved = ntohl(b[3]); r->clock_seq_low = ntohl(b[4]); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 949f960337f5..613a77058263 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -61,6 +61,7 @@ const struct inode_operations afs_dir_inode_operations = { .permission = afs_permission, .getattr = afs_getattr, .setattr = afs_setattr, + .listxattr = afs_listxattr, }; const struct dentry_operations afs_fs_dentry_operations = { diff --git a/fs/afs/file.c b/fs/afs/file.c index 0d5b8508869b..510cba15fa56 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -46,6 +46,7 @@ const struct inode_operations afs_file_inode_operations = { .getattr = afs_getattr, .setattr = afs_setattr, .permission = afs_permission, + .listxattr = afs_listxattr, }; const struct address_space_operations afs_fs_aops = { diff --git a/fs/afs/inode.c b/fs/afs/inode.c index aae55dd15108..342316a9e3e0 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -28,6 +28,11 @@ struct afs_iget_data { struct afs_volume *volume; /* volume on which resides */ }; +static const struct inode_operations afs_symlink_inode_operations = { + .get_link = page_get_link, + .listxattr = afs_listxattr, +}; + /* * map the AFS file status to the inode member variables */ @@ -67,7 +72,7 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key) inode->i_fop = &afs_mntpt_file_operations; } else { inode->i_mode = S_IFLNK | vnode->status.mode; - inode->i_op = &page_symlink_inode_operations; + inode->i_op = &afs_symlink_inode_operations; } inode_nohighmem(inode); break; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 393672997cc2..82e16556afea 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -410,6 +410,15 @@ struct afs_interface { unsigned mtu; /* MTU of interface */ }; +struct afs_uuid { + __be32 time_low; /* low part of timestamp */ + __be16 time_mid; /* mid part of timestamp */ + __be16 time_hi_and_version; /* high part of timestamp and version */ + __u8 clock_seq_hi_and_reserved; /* clock seq hi and variant */ + __u8 clock_seq_low; /* clock seq low */ + __u8 node[6]; /* spatially unique node ID (MAC addr) */ +}; + /*****************************************************************************/ /* * cache.c @@ -544,7 +553,7 @@ extern int afs_drop_inode(struct inode *); * main.c */ extern struct workqueue_struct *afs_wq; -extern struct uuid_v1 afs_uuid; +extern struct afs_uuid afs_uuid; /* * misc.c @@ -722,6 +731,11 @@ extern int afs_writeback_all(struct afs_vnode *); extern int afs_flush(struct file *, fl_owner_t); extern int afs_fsync(struct file *, loff_t, loff_t, int); +/* + * xattr.c + */ +extern const struct xattr_handler *afs_xattr_handlers[]; +extern ssize_t afs_listxattr(struct dentry *, char *, size_t); /*****************************************************************************/ /* diff --git a/fs/afs/main.c b/fs/afs/main.c index 51d7d17bca57..9944770849da 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -31,7 +31,7 @@ static char *rootcell; module_param(rootcell, charp, 0); MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list"); -struct uuid_v1 afs_uuid; +struct afs_uuid afs_uuid; struct workqueue_struct *afs_wq; /* diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 100b207efc9e..c05f1f1c0d41 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -12,7 +12,6 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/errno.h> -#include <rxrpc/packet.h> #include "internal.h" #include "afs_fs.h" diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index bd3b65cde282..690fea9d84c3 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -35,6 +35,7 @@ const struct inode_operations afs_mntpt_inode_operations = { .lookup = afs_mntpt_lookup, .readlink = page_readlink, .getattr = afs_getattr, + .listxattr = afs_listxattr, }; const struct inode_operations afs_autocell_inode_operations = { diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index d5990eb160bd..0bf191f0dbaf 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -14,7 +14,6 @@ #include <net/sock.h> #include <net/af_rxrpc.h> -#include <rxrpc/packet.h> #include "internal.h" #include "afs_cm.h" @@ -293,6 +292,19 @@ static void afs_load_bvec(struct afs_call *call, struct msghdr *msg, } /* + * Advance the AFS call state when the RxRPC call ends the transmit phase. + */ +static void afs_notify_end_request_tx(struct sock *sock, + struct rxrpc_call *rxcall, + unsigned long call_user_ID) +{ + struct afs_call *call = (struct afs_call *)call_user_ID; + + if (call->state == AFS_CALL_REQUESTING) + call->state = AFS_CALL_AWAIT_REPLY; +} + +/* * attach the data from a bunch of pages on an inode to a call */ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) @@ -311,14 +323,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) bytes = msg->msg_iter.count; nr = msg->msg_iter.nr_segs; - /* Have to change the state *before* sending the last - * packet as RxRPC might give us the reply before it - * returns from sending the request. - */ - if (first + nr - 1 >= last) - call->state = AFS_CALL_AWAIT_REPLY; - ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, - msg, bytes); + ret = rxrpc_kernel_send_data(afs_socket, call->rxcall, msg, + bytes, afs_notify_end_request_tx); for (loop = 0; loop < nr; loop++) put_page(bv[loop].bv_page); if (ret < 0) @@ -341,6 +347,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, struct msghdr msg; struct kvec iov[1]; size_t offset; + s64 tx_total_len; u32 abort_code; int ret; @@ -364,9 +371,20 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, srx.transport.sin.sin_port = call->port; memcpy(&srx.transport.sin.sin_addr, addr, 4); + /* Work out the length we're going to transmit. This is awkward for + * calls such as FS.StoreData where there's an extra injection of data + * after the initial fixed part. + */ + tx_total_len = call->request_size; + if (call->send_pages) { + tx_total_len += call->last_to - call->first_offset; + tx_total_len += (call->last - call->first) * PAGE_SIZE; + } + /* create a call */ rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key, - (unsigned long) call, gfp, + (unsigned long)call, + tx_total_len, gfp, (async ? afs_wake_up_async_call : afs_wake_up_call_waiter)); @@ -398,7 +416,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, if (!call->send_pages) call->state = AFS_CALL_AWAIT_REPLY; ret = rxrpc_kernel_send_data(afs_socket, rxcall, - &msg, call->request_size); + &msg, call->request_size, + afs_notify_end_request_tx); if (ret < 0) goto error_do_abort; @@ -730,6 +749,20 @@ static int afs_deliver_cm_op_id(struct afs_call *call) } /* + * Advance the AFS call state when an RxRPC service call ends the transmit + * phase. + */ +static void afs_notify_end_reply_tx(struct sock *sock, + struct rxrpc_call *rxcall, + unsigned long call_user_ID) +{ + struct afs_call *call = (struct afs_call *)call_user_ID; + + if (call->state == AFS_CALL_REPLYING) + call->state = AFS_CALL_AWAIT_ACK; +} + +/* * send an empty reply */ void afs_send_empty_reply(struct afs_call *call) @@ -738,6 +771,8 @@ void afs_send_empty_reply(struct afs_call *call) _enter(""); + rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, 0); + msg.msg_name = NULL; msg.msg_namelen = 0; iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); @@ -746,7 +781,8 @@ void afs_send_empty_reply(struct afs_call *call) msg.msg_flags = 0; call->state = AFS_CALL_AWAIT_ACK; - switch (rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, 0)) { + switch (rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, 0, + afs_notify_end_reply_tx)) { case 0: _leave(" [replied]"); return; @@ -772,6 +808,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) _enter(""); + rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, len); + iov[0].iov_base = (void *) buf; iov[0].iov_len = len; msg.msg_name = NULL; @@ -782,7 +820,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) msg.msg_flags = 0; call->state = AFS_CALL_AWAIT_ACK; - n = rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, len); + n = rxrpc_kernel_send_data(afs_socket, call->rxcall, &msg, len, + afs_notify_end_reply_tx); if (n >= 0) { /* Success */ _leave(" [replied]"); diff --git a/fs/afs/security.c b/fs/afs/security.c index ecb86a670180..faca66227ecf 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -327,12 +327,11 @@ int afs_permission(struct inode *inode, int mask) if (!(access & AFS_ACE_LOOKUP)) goto permission_denied; } else if (mask & MAY_READ) { - if (!(access & AFS_ACE_READ)) + if (!(access & AFS_ACE_LOOKUP)) goto permission_denied; } else if (mask & MAY_WRITE) { if (!(access & (AFS_ACE_DELETE | /* rmdir, unlink, rename from */ - AFS_ACE_INSERT | /* create, mkdir, symlink, rename to */ - AFS_ACE_WRITE))) /* chmod */ + AFS_ACE_INSERT))) /* create, mkdir, symlink, rename to */ goto permission_denied; } else { BUG(); diff --git a/fs/afs/super.c b/fs/afs/super.c index c79633e5cfd8..689173c0a682 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -37,6 +37,8 @@ static void afs_kill_super(struct super_block *sb); static struct inode *afs_alloc_inode(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); static int afs_statfs(struct dentry *dentry, struct kstatfs *buf); +static int afs_show_devname(struct seq_file *m, struct dentry *root); +static int afs_show_options(struct seq_file *m, struct dentry *root); struct file_system_type afs_fs_type = { .owner = THIS_MODULE, @@ -53,7 +55,8 @@ static const struct super_operations afs_super_ops = { .drop_inode = afs_drop_inode, .destroy_inode = afs_destroy_inode, .evict_inode = afs_evict_inode, - .show_options = generic_show_options, + .show_devname = afs_show_devname, + .show_options = afs_show_options, }; static struct kmem_cache *afs_inode_cachep; @@ -136,6 +139,45 @@ void __exit afs_fs_exit(void) } /* + * Display the mount device name in /proc/mounts. + */ +static int afs_show_devname(struct seq_file *m, struct dentry *root) +{ + struct afs_super_info *as = root->d_sb->s_fs_info; + struct afs_volume *volume = as->volume; + struct afs_cell *cell = volume->cell; + const char *suf = ""; + char pref = '%'; + + switch (volume->type) { + case AFSVL_RWVOL: + break; + case AFSVL_ROVOL: + pref = '#'; + if (volume->type_force) + suf = ".readonly"; + break; + case AFSVL_BACKVOL: + pref = '#'; + suf = ".backup"; + break; + } + + seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->vlocation->vldb.name, suf); + return 0; +} + +/* + * Display the mount options in /proc/mounts. + */ +static int afs_show_options(struct seq_file *m, struct dentry *root) +{ + if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags)) + seq_puts(m, "autocell"); + return 0; +} + +/* * parse the mount options * - this function has been shamelessly adapted from the ext3 fs which * shamelessly adapted it from the msdos fs @@ -319,6 +361,7 @@ static int afs_fill_super(struct super_block *sb, sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = AFS_FS_MAGIC; sb->s_op = &afs_super_ops; + sb->s_xattr = afs_xattr_handlers; ret = super_setup_bdi(sb); if (ret) return ret; @@ -426,7 +469,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type, deactivate_locked_super(sb); goto error; } - save_mount_options(sb, new_opts); sb->s_flags |= MS_ACTIVE; } else { _debug("reuse"); diff --git a/fs/afs/write.c b/fs/afs/write.c index 2d2fccd5044b..106e43db1115 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -714,7 +714,7 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) vnode->fid.vid, vnode->fid.vnode, file, datasync); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); if (ret) return ret; inode_lock(inode); diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c new file mode 100644 index 000000000000..2830e4f48d85 --- /dev/null +++ b/fs/afs/xattr.c @@ -0,0 +1,121 @@ +/* Extended attribute handling for AFS. We use xattrs to get and set metadata + * instead of providing pioctl(). + * + * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/slab.h> +#include <linux/fs.h> +#include <linux/xattr.h> +#include "internal.h" + +static const char afs_xattr_list[] = + "afs.cell\0" + "afs.fid\0" + "afs.volume"; + +/* + * Retrieve a list of the supported xattrs. + */ +ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size) +{ + if (size == 0) + return sizeof(afs_xattr_list); + if (size < sizeof(afs_xattr_list)) + return -ERANGE; + memcpy(buffer, afs_xattr_list, sizeof(afs_xattr_list)); + return sizeof(afs_xattr_list); +} + +/* + * Get the name of the cell on which a file resides. + */ +static int afs_xattr_get_cell(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + void *buffer, size_t size) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + struct afs_cell *cell = vnode->volume->cell; + size_t namelen; + + namelen = strlen(cell->name); + if (size == 0) + return namelen; + if (namelen > size) + return -ERANGE; + memcpy(buffer, cell->name, size); + return namelen; +} + +static const struct xattr_handler afs_xattr_afs_cell_handler = { + .name = "afs.cell", + .get = afs_xattr_get_cell, +}; + +/* + * Get the volume ID, vnode ID and vnode uniquifier of a file as a sequence of + * hex numbers separated by colons. + */ +static int afs_xattr_get_fid(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + void *buffer, size_t size) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + char text[8 + 1 + 8 + 1 + 8 + 1]; + size_t len; + + len = sprintf(text, "%x:%x:%x", + vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); + if (size == 0) + return len; + if (len > size) + return -ERANGE; + memcpy(buffer, text, len); + return len; +} + +static const struct xattr_handler afs_xattr_afs_fid_handler = { + .name = "afs.fid", + .get = afs_xattr_get_fid, +}; + +/* + * Get the name of the volume on which a file resides. + */ +static int afs_xattr_get_volume(const struct xattr_handler *handler, + struct dentry *dentry, + struct inode *inode, const char *name, + void *buffer, size_t size) +{ + struct afs_vnode *vnode = AFS_FS_I(inode); + const char *volname = vnode->volume->vlocation->vldb.name; + size_t namelen; + + namelen = strlen(volname); + if (size == 0) + return namelen; + if (namelen > size) + return -ERANGE; + memcpy(buffer, volname, size); + return namelen; +} + +static const struct xattr_handler afs_xattr_afs_volume_handler = { + .name = "afs.volume", + .get = afs_xattr_get_volume, +}; + +const struct xattr_handler *afs_xattr_handlers[] = { + &afs_xattr_afs_cell_handler, + &afs_xattr_afs_fid_handler, + &afs_xattr_afs_volume_handler, + NULL +}; @@ -373,6 +373,14 @@ static int aio_migratepage(struct address_space *mapping, struct page *new, pgoff_t idx; int rc; + /* + * We cannot support the _NO_COPY case here, because copy needs to + * happen under the ctx->completion_lock. That does not work with the + * migration workflow of MIGRATE_SYNC_NO_COPY. + */ + if (mode == MIGRATE_SYNC_NO_COPY) + return -EINVAL; + rc = 0; /* mapping->private_lock here protects against the kioctx teardown. */ @@ -441,10 +449,9 @@ static const struct address_space_operations aio_ctx_aops = { #endif }; -static int aio_setup_ring(struct kioctx *ctx) +static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) { struct aio_ring *ring; - unsigned nr_events = ctx->max_reqs; struct mm_struct *mm = current->mm; unsigned long size, unused; int nr_pages; @@ -707,6 +714,12 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) int err = -ENOMEM; /* + * Store the original nr_events -- what userspace passed to io_setup(), + * for counting against the global limit -- before it changes. + */ + unsigned int max_reqs = nr_events; + + /* * We keep track of the number of available ringbuffer slots, to prevent * overflow (reqs_available), and we also use percpu counters for this. * @@ -724,14 +737,14 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) return ERR_PTR(-EINVAL); } - if (!nr_events || (unsigned long)nr_events > (aio_max_nr * 2UL)) + if (!nr_events || (unsigned long)max_reqs > aio_max_nr) return ERR_PTR(-EAGAIN); ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); - ctx->max_reqs = nr_events; + ctx->max_reqs = max_reqs; spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); @@ -753,7 +766,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) if (!ctx->cpu) goto err; - err = aio_setup_ring(ctx); + err = aio_setup_ring(ctx, nr_events); if (err < 0) goto err; @@ -764,8 +777,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events) /* limit the number of system wide aios */ spin_lock(&aio_nr_lock); - if (aio_nr + nr_events > (aio_max_nr * 2UL) || - aio_nr + nr_events < aio_nr) { + if (aio_nr + ctx->max_reqs > aio_max_nr || + aio_nr + ctx->max_reqs < aio_nr) { spin_unlock(&aio_nr_lock); err = -EAGAIN; goto err_ctx; @@ -1541,7 +1554,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, ssize_t ret; /* enforce forwards compatibility on users */ - if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) { + if (unlikely(iocb->aio_reserved2)) { pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } @@ -1568,6 +1581,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->common.ki_pos = iocb->aio_offset; req->common.ki_complete = aio_complete; req->common.ki_flags = iocb_flags(req->common.ki_filp); + req->common.ki_hint = file_write_hint(file); if (iocb->aio_flags & IOCB_FLAG_RESFD) { /* @@ -1586,6 +1600,12 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->common.ki_flags |= IOCB_EVENTFD; } + ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags); + if (unlikely(ret)) { + pr_debug("EINVAL: aio_rw_flags\n"); + goto out_put_req; + } + ret = put_user(KIOCB_KEY, &user_iocb->aio_key); if (unlikely(ret)) { pr_debug("EFAULT: aio_key\n"); diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index beef981aa54f..4737615f0eaa 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -11,10 +11,21 @@ #include <linux/auto_fs4.h> #include <linux/auto_dev-ioctl.h> + +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/time.h> +#include <linux/string.h> +#include <linux/wait.h> +#include <linux/sched.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/uaccess.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/completion.h> +#include <asm/current.h> /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY @@ -24,17 +35,6 @@ #define AUTOFS_DEV_IOCTL_IOC_COUNT \ (AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD - AUTOFS_DEV_IOCTL_VERSION_CMD) -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/time.h> -#include <linux/string.h> -#include <linux/wait.h> -#include <linux/sched.h> -#include <linux/mount.h> -#include <linux/namei.h> -#include <asm/current.h> -#include <linux/uaccess.h> - #ifdef pr_fmt #undef pr_fmt #endif diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index dd9f1bebb5a3..b7c816f39404 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -93,17 +93,17 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) * at the end of the struct. */ static struct autofs_dev_ioctl * - copy_dev_ioctl(struct autofs_dev_ioctl __user *in) +copy_dev_ioctl(struct autofs_dev_ioctl __user *in) { struct autofs_dev_ioctl tmp, *res; - if (copy_from_user(&tmp, in, sizeof(tmp))) + if (copy_from_user(&tmp, in, AUTOFS_DEV_IOCTL_SIZE)) return ERR_PTR(-EFAULT); - if (tmp.size < sizeof(tmp)) + if (tmp.size < AUTOFS_DEV_IOCTL_SIZE) return ERR_PTR(-EINVAL); - if (tmp.size > (PATH_MAX + sizeof(tmp))) + if (tmp.size > AUTOFS_DEV_IOCTL_SIZE + PATH_MAX) return ERR_PTR(-ENAMETOOLONG); res = memdup_user(in, tmp.size); @@ -133,8 +133,8 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) goto out; } - if (param->size > sizeof(*param)) { - err = invalid_str(param->path, param->size - sizeof(*param)); + if (param->size > AUTOFS_DEV_IOCTL_SIZE) { + err = invalid_str(param->path, param->size - AUTOFS_DEV_IOCTL_SIZE); if (err) { pr_warn( "path string terminator missing for cmd(0x%08x)\n", @@ -258,11 +258,6 @@ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid) if (err) goto out; - /* - * Find autofs super block that has the device number - * corresponding to the autofs fs we want to open. - */ - filp = dentry_open(&path, O_RDONLY, current_cred()); path_put(&path); if (IS_ERR(filp)) { @@ -451,7 +446,7 @@ static int autofs_dev_ioctl_requester(struct file *fp, dev_t devid; int err = -ENOENT; - if (param->size <= sizeof(*param)) { + if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { err = -EINVAL; goto out; } @@ -539,7 +534,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp, unsigned int devid, magic; int err = -ENOENT; - if (param->size <= sizeof(*param)) { + if (param->size <= AUTOFS_DEV_IOCTL_SIZE) { err = -EINVAL; goto out; } @@ -628,10 +623,6 @@ static int _autofs_dev_ioctl(unsigned int command, ioctl_fn fn = NULL; int err = 0; - /* only root can play with this */ - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - cmd_first = _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST); cmd = _IOC_NR(command); @@ -640,6 +631,14 @@ static int _autofs_dev_ioctl(unsigned int command, return -ENOTTY; } + /* Only root can use ioctls other than AUTOFS_DEV_IOCTL_VERSION_CMD + * and AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD + */ + if (cmd != AUTOFS_DEV_IOCTL_VERSION_CMD && + cmd != AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + /* Copy the parameters into kernel space. */ param = copy_dev_ioctl(user); if (IS_ERR(param)) @@ -706,7 +705,8 @@ out: return err; } -static long autofs_dev_ioctl(struct file *file, uint command, ulong u) +static long autofs_dev_ioctl(struct file *file, unsigned int command, + unsigned long u) { int err; @@ -715,9 +715,10 @@ static long autofs_dev_ioctl(struct file *file, uint command, ulong u) } #ifdef CONFIG_COMPAT -static long autofs_dev_ioctl_compat(struct file *file, uint command, ulong u) +static long autofs_dev_ioctl_compat(struct file *file, unsigned int command, + unsigned long u) { - return (long) autofs_dev_ioctl(file, command, (ulong) compat_ptr(u)); + return autofs_dev_ioctl(file, command, (unsigned long) compat_ptr(u)); } #else #define autofs_dev_ioctl_compat NULL @@ -733,7 +734,8 @@ static const struct file_operations _dev_ioctl_fops = { static struct miscdevice _autofs_dev_ioctl_misc = { .minor = AUTOFS_MINOR, .name = AUTOFS_DEVICE_NAME, - .fops = &_dev_ioctl_fops + .fops = &_dev_ioctl_fops, + .mode = 0644, }; MODULE_ALIAS_MISCDEV(AUTOFS_MINOR); diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 24a58bf9ca72..4ac49d038bf3 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -56,19 +56,14 @@ static int autofs4_write(struct autofs_sb_info *sbi, struct file *file, const void *addr, int bytes) { unsigned long sigpipe, flags; - mm_segment_t fs; const char *data = (const char *)addr; ssize_t wr = 0; sigpipe = sigismember(¤t->pending.signal, SIGPIPE); - /* Save pointer to user space and point back to kernel space */ - fs = get_fs(); - set_fs(KERNEL_DS); - mutex_lock(&sbi->pipe_mutex); while (bytes) { - wr = __vfs_write(file, data, bytes, &file->f_pos); + wr = __kernel_write(file, data, bytes, &file->f_pos); if (wr <= 0) break; data += wr; @@ -76,8 +71,6 @@ static int autofs4_write(struct autofs_sb_info *sbi, } mutex_unlock(&sbi->pipe_mutex); - set_fs(fs); - /* Keep the currently executing process from receiving a * SIGPIPE unless it was already supposed to get one */ diff --git a/fs/befs/btree.c b/fs/befs/btree.c index d509887c580c..1b7e0f7128d6 100644 --- a/fs/befs/btree.c +++ b/fs/befs/btree.c @@ -120,18 +120,15 @@ static int befs_compare_strings(const void *key1, int keylen1, const void *key2, int keylen2); /** - * befs_bt_read_super - read in btree superblock convert to cpu byteorder - * @sb: Filesystem superblock - * @ds: Datastream to read from - * @sup: Buffer in which to place the btree superblock + * befs_bt_read_super() - read in btree superblock convert to cpu byteorder + * @sb: Filesystem superblock + * @ds: Datastream to read from + * @sup: Buffer in which to place the btree superblock * * Calls befs_read_datastream to read in the btree superblock and * makes sure it is in cpu byteorder, byteswapping if necessary. - * - * On success, returns BEFS_OK and *@sup contains the btree superblock, - * in cpu byte order. - * - * On failure, BEFS_ERR is returned. + * Return: BEFS_OK on success and if *@sup contains the btree superblock in cpu + * byte order. Otherwise return BEFS_ERR on error. */ static int befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds, diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 63e7c4760bfb..a92355cc453b 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -20,6 +20,7 @@ #include <linux/sched.h> #include <linux/cred.h> #include <linux/exportfs.h> +#include <linux/seq_file.h> #include "befs.h" #include "btree.h" @@ -53,6 +54,7 @@ static int befs_nls2utf(struct super_block *sb, const char *in, int in_len, static void befs_put_super(struct super_block *); static int befs_remount(struct super_block *, int *, char *); static int befs_statfs(struct dentry *, struct kstatfs *); +static int befs_show_options(struct seq_file *, struct dentry *); static int parse_options(char *, struct befs_mount_options *); static struct dentry *befs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); @@ -66,7 +68,7 @@ static const struct super_operations befs_sops = { .put_super = befs_put_super, /* uninit super */ .statfs = befs_statfs, /* statfs */ .remount_fs = befs_remount, - .show_options = generic_show_options, + .show_options = befs_show_options, }; /* slab cache for befs_inode_info objects */ @@ -771,6 +773,24 @@ parse_options(char *options, struct befs_mount_options *opts) return 1; } +static int befs_show_options(struct seq_file *m, struct dentry *root) +{ + struct befs_sb_info *befs_sb = BEFS_SB(root->d_sb); + struct befs_mount_options *opts = &befs_sb->mount_opts; + + if (!uid_eq(opts->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->uid)); + if (!gid_eq(opts->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->gid)); + if (opts->iocharset) + seq_printf(m, ",charset=%s", opts->iocharset); + if (opts->debug) + seq_puts(m, ",debug"); + return 0; +} + /* This function has the responsibiltiy of getting the * filesystem ready for unmounting. * Basically, we free everything that we allocated in @@ -804,8 +824,6 @@ befs_fill_super(struct super_block *sb, void *data, int silent) const off_t x86_sb_off = 512; int blocksize; - save_mount_options(sb, data); - sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL); if (sb->s_fs_info == NULL) goto unacquire_none; @@ -820,7 +838,7 @@ befs_fill_super(struct super_block *sb, void *data, int silent) befs_debug(sb, "---> %s", __func__); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { befs_warning(sb, "No write support. Marking filesystem read-only"); sb->s_flags |= MS_RDONLY; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 25e312cb6071..9a69392f1fb3 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -419,7 +419,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) if (i_sblock > info->si_blocks || i_eblock > info->si_blocks || i_sblock > i_eblock || - i_eoff > s_size || + (i_eoff != le32_to_cpu(-1) && i_eoff > s_size) || i_sblock * BFS_BSIZE > i_eoff) { printf("Inode 0x%08x corrupted\n", i); diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 9be82c4e14a4..ce1824f47ba6 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -341,11 +341,12 @@ static int load_aout_library(struct file *file) unsigned long error; int retval; struct exec ex; + loff_t pos = 0; inode = file_inode(file); retval = -ENOEXEC; - error = kernel_read(file, 0, (char *) &ex, sizeof(ex)); + error = kernel_read(file, &ex, sizeof(ex), &pos); if (error != sizeof(ex)) goto out; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 5075fd5c62c8..73b01e474fdc 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -163,8 +163,6 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, unsigned long p = bprm->p; int argc = bprm->argc; int envc = bprm->envc; - elf_addr_t __user *argv; - elf_addr_t __user *envp; elf_addr_t __user *sp; elf_addr_t __user *u_platform; elf_addr_t __user *u_base_platform; @@ -254,7 +252,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid)); NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid)); NEW_AUX_ENT(AT_EGID, from_kgid_munged(cred->user_ns, cred->egid)); - NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); + NEW_AUX_ENT(AT_SECURE, bprm->secureexec); NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes); #ifdef ELF_HWCAP2 NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2); @@ -304,38 +302,38 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, /* Now, let's put argc (and argv, envp if appropriate) on the stack */ if (__put_user(argc, sp++)) return -EFAULT; - argv = sp; - envp = argv + argc + 1; - /* Populate argv and envp */ + /* Populate list of argv pointers back to argv strings. */ p = current->mm->arg_end = current->mm->arg_start; while (argc-- > 0) { size_t len; - if (__put_user((elf_addr_t)p, argv++)) + if (__put_user((elf_addr_t)p, sp++)) return -EFAULT; len = strnlen_user((void __user *)p, MAX_ARG_STRLEN); if (!len || len > MAX_ARG_STRLEN) return -EINVAL; p += len; } - if (__put_user(0, argv)) + if (__put_user(0, sp++)) return -EFAULT; - current->mm->arg_end = current->mm->env_start = p; + current->mm->arg_end = p; + + /* Populate list of envp pointers back to envp strings. */ + current->mm->env_end = current->mm->env_start = p; while (envc-- > 0) { size_t len; - if (__put_user((elf_addr_t)p, envp++)) + if (__put_user((elf_addr_t)p, sp++)) return -EFAULT; len = strnlen_user((void __user *)p, MAX_ARG_STRLEN); if (!len || len > MAX_ARG_STRLEN) return -EINVAL; p += len; } - if (__put_user(0, envp)) + if (__put_user(0, sp++)) return -EFAULT; current->mm->env_end = p; /* Put the elf_info on the stack in the right place. */ - sp = (elf_addr_t __user *)envp + 1; if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t))) return -EFAULT; return 0; @@ -411,6 +409,7 @@ static struct elf_phdr *load_elf_phdrs(struct elfhdr *elf_ex, { struct elf_phdr *elf_phdata = NULL; int retval, size, err = -1; + loff_t pos = elf_ex->e_phoff; /* * If the size of this structure has changed, then punt, since @@ -434,8 +433,7 @@ static struct elf_phdr *load_elf_phdrs(struct elfhdr *elf_ex, goto out; /* Read in the program headers */ - retval = kernel_read(elf_file, elf_ex->e_phoff, - (char *)elf_phdata, size); + retval = kernel_read(elf_file, elf_phdata, size, &pos); if (retval != size) { err = (retval < 0) ? retval : -EIO; goto out; @@ -666,8 +664,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) { + if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; @@ -701,6 +698,7 @@ static int load_elf_binary(struct linux_binprm *bprm) struct elfhdr interp_elf_ex; } *loc; struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE; + loff_t pos; loc = kmalloc(sizeof(*loc), GFP_KERNEL); if (!loc) { @@ -753,9 +751,9 @@ static int load_elf_binary(struct linux_binprm *bprm) if (!elf_interpreter) goto out_free_ph; - retval = kernel_read(bprm->file, elf_ppnt->p_offset, - elf_interpreter, - elf_ppnt->p_filesz); + pos = elf_ppnt->p_offset; + retval = kernel_read(bprm->file, elf_interpreter, + elf_ppnt->p_filesz, &pos); if (retval != elf_ppnt->p_filesz) { if (retval >= 0) retval = -EIO; @@ -779,9 +777,9 @@ static int load_elf_binary(struct linux_binprm *bprm) would_dump(bprm, interpreter); /* Get the exec headers */ - retval = kernel_read(interpreter, 0, - (void *)&loc->interp_elf_ex, - sizeof(loc->interp_elf_ex)); + pos = 0; + retval = kernel_read(interpreter, &loc->interp_elf_ex, + sizeof(loc->interp_elf_ex), &pos); if (retval != sizeof(loc->interp_elf_ex)) { if (retval >= 0) retval = -EIO; @@ -927,17 +925,60 @@ static int load_elf_binary(struct linux_binprm *bprm) elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; vaddr = elf_ppnt->p_vaddr; + /* + * If we are loading ET_EXEC or we have already performed + * the ET_DYN load_addr calculations, proceed normally. + */ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) { elf_flags |= MAP_FIXED; } else if (loc->elf_ex.e_type == ET_DYN) { - /* Try and get dynamic programs out of the way of the - * default mmap base, as well as whatever program they - * might try to exec. This is because the brk will - * follow the loader, and is not movable. */ - load_bias = ELF_ET_DYN_BASE - vaddr; - if (current->flags & PF_RANDOMIZE) - load_bias += arch_mmap_rnd(); - load_bias = ELF_PAGESTART(load_bias); + /* + * This logic is run once for the first LOAD Program + * Header for ET_DYN binaries to calculate the + * randomization (load_bias) for all the LOAD + * Program Headers, and to calculate the entire + * size of the ELF mapping (total_size). (Note that + * load_addr_set is set to true later once the + * initial mapping is performed.) + * + * There are effectively two types of ET_DYN + * binaries: programs (i.e. PIE: ET_DYN with INTERP) + * and loaders (ET_DYN without INTERP, since they + * _are_ the ELF interpreter). The loaders must + * be loaded away from programs since the program + * may otherwise collide with the loader (especially + * for ET_EXEC which does not have a randomized + * position). For example to handle invocations of + * "./ld.so someprog" to test out a new version of + * the loader, the subsequent program that the + * loader loads must avoid the loader itself, so + * they cannot share the same load range. Sufficient + * room for the brk must be allocated with the + * loader as well, since brk must be available with + * the loader. + * + * Therefore, programs are loaded offset from + * ELF_ET_DYN_BASE and loaders are loaded into the + * independently randomized mmap region (0 load_bias + * without MAP_FIXED). + */ + if (elf_interpreter) { + load_bias = ELF_ET_DYN_BASE; + if (current->flags & PF_RANDOMIZE) + load_bias += arch_mmap_rnd(); + elf_flags |= MAP_FIXED; + } else + load_bias = 0; + + /* + * Since load_bias is used for all subsequent loading + * calculations, we must lower it by the first vaddr + * so that the remaining calculations based on the + * ELF vaddrs will be correctly offset. The result + * is then page aligned. + */ + load_bias = ELF_PAGESTART(load_bias - vaddr); + total_size = total_mapping_size(elf_phdata, loc->elf_ex.e_phnum); if (!total_size) { @@ -1135,9 +1176,10 @@ static int load_elf_library(struct file *file) unsigned long elf_bss, bss, len; int retval, error, i, j; struct elfhdr elf_ex; + loff_t pos = 0; error = -ENOEXEC; - retval = kernel_read(file, 0, (char *)&elf_ex, sizeof(elf_ex)); + retval = kernel_read(file, &elf_ex, sizeof(elf_ex), &pos); if (retval != sizeof(elf_ex)) goto out; @@ -1161,7 +1203,8 @@ static int load_elf_library(struct file *file) eppnt = elf_phdata; error = -ENOEXEC; - retval = kernel_read(file, elf_ex.e_phoff, (char *)eppnt, j); + pos = elf_ex.e_phoff; + retval = kernel_read(file, eppnt, j, &pos); if (retval != j) goto out_free_ph; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index cf93a4fad012..e70c039ac190 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -145,6 +145,7 @@ static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *params, struct elf32_phdr *phdr; unsigned long size; int retval, loop; + loff_t pos = params->hdr.e_phoff; if (params->hdr.e_phentsize != sizeof(struct elf_phdr)) return -ENOMEM; @@ -156,8 +157,7 @@ static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *params, if (!params->phdrs) return -ENOMEM; - retval = kernel_read(file, params->hdr.e_phoff, - (char *) params->phdrs, size); + retval = kernel_read(file, params->phdrs, size, &pos); if (unlikely(retval != size)) return retval < 0 ? retval : -ENOEXEC; @@ -199,6 +199,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) char *interpreter_name = NULL; int executable_stack; int retval, i; + loff_t pos; kdebug("____ LOAD %d ____", current->pid); @@ -246,10 +247,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) if (!interpreter_name) goto error; - retval = kernel_read(bprm->file, - phdr->p_offset, - interpreter_name, - phdr->p_filesz); + pos = phdr->p_offset; + retval = kernel_read(bprm->file, interpreter_name, + phdr->p_filesz, &pos); if (unlikely(retval != phdr->p_filesz)) { if (retval >= 0) retval = -ENOEXEC; @@ -277,8 +277,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm) */ would_dump(bprm, interpreter); - retval = kernel_read(interpreter, 0, bprm->buf, - BINPRM_BUF_SIZE); + pos = 0; + retval = kernel_read(interpreter, bprm->buf, + BINPRM_BUF_SIZE, &pos); if (unlikely(retval != BINPRM_BUF_SIZE)) { if (retval >= 0) retval = -ENOEXEC; @@ -650,7 +651,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, NEW_AUX_ENT(AT_EUID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid)); NEW_AUX_ENT(AT_GID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->gid)); NEW_AUX_ENT(AT_EGID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid)); - NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); + NEW_AUX_ENT(AT_SECURE, bprm->secureexec); NEW_AUX_ENT(AT_EXECFN, bprm->exec); #ifdef ARCH_DLINFO diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 2edcefc0a294..475d083f8088 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -176,41 +176,32 @@ static int create_flat_tables(struct linux_binprm *bprm, unsigned long arg_start #define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */ #define RESERVED 0xC0 /* bit 6,7: reserved */ -static int decompress_exec( - struct linux_binprm *bprm, - unsigned long offset, - char *dst, - long len, - int fd) +static int decompress_exec(struct linux_binprm *bprm, loff_t fpos, char *dst, + long len, int fd) { unsigned char *buf; z_stream strm; - loff_t fpos; int ret, retval; - pr_debug("decompress_exec(offset=%lx,buf=%p,len=%lx)\n", offset, dst, len); + pr_debug("decompress_exec(offset=%llx,buf=%p,len=%lx)\n", fpos, dst, len); memset(&strm, 0, sizeof(strm)); strm.workspace = kmalloc(zlib_inflate_workspacesize(), GFP_KERNEL); - if (strm.workspace == NULL) { - pr_debug("no memory for decompress workspace\n"); + if (!strm.workspace) return -ENOMEM; - } + buf = kmalloc(LBUFSIZE, GFP_KERNEL); - if (buf == NULL) { - pr_debug("no memory for read buffer\n"); + if (!buf) { retval = -ENOMEM; goto out_free; } /* Read in first chunk of data and parse gzip header. */ - fpos = offset; - ret = kernel_read(bprm->file, offset, buf, LBUFSIZE); + ret = kernel_read(bprm->file, buf, LBUFSIZE, &fpos); strm.next_in = buf; strm.avail_in = ret; strm.total_in = 0; - fpos += ret; retval = -ENOEXEC; @@ -276,7 +267,7 @@ static int decompress_exec( } while ((ret = zlib_inflate(&strm, Z_NO_FLUSH)) == Z_OK) { - ret = kernel_read(bprm->file, fpos, buf, LBUFSIZE); + ret = kernel_read(bprm->file, buf, LBUFSIZE, &fpos); if (ret <= 0) break; len -= ret; @@ -284,7 +275,6 @@ static int decompress_exec( strm.next_in = buf; strm.avail_in = ret; strm.total_in = 0; - fpos += ret; } if (ret < 0) { @@ -422,9 +412,9 @@ static int load_flat_file(struct linux_binprm *bprm, { struct flat_hdr *hdr; unsigned long textpos, datapos, realdatastart; - unsigned long text_len, data_len, bss_len, stack_len, full_data, flags; + u32 text_len, data_len, bss_len, stack_len, full_data, flags; unsigned long len, memp, memp_size, extra, rlim; - unsigned long __user *reloc, *rp; + u32 __user *reloc, *rp; struct inode *inode; int i, rev, relocs; loff_t fpos; @@ -574,7 +564,7 @@ static int load_flat_file(struct linux_binprm *bprm, MAX_SHARED_LIBS * sizeof(unsigned long), FLAT_DATA_ALIGN); - pr_debug("Allocated data+bss+stack (%ld bytes): %lx\n", + pr_debug("Allocated data+bss+stack (%u bytes): %lx\n", data_len + bss_len + stack_len, datapos); fpos = ntohl(hdr->data_start); @@ -596,13 +586,13 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - reloc = (unsigned long __user *) + reloc = (u32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = realdatastart; memp_size = len; } else { - len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); + len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32); len = PAGE_ALIGN(len); textpos = vm_mmap(NULL, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); @@ -618,10 +608,10 @@ static int load_flat_file(struct linux_binprm *bprm, realdatastart = textpos + ntohl(hdr->data_start); datapos = ALIGN(realdatastart + - MAX_SHARED_LIBS * sizeof(unsigned long), + MAX_SHARED_LIBS * sizeof(u32), FLAT_DATA_ALIGN); - reloc = (unsigned long __user *) + reloc = (u32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = textpos; memp_size = len; @@ -694,7 +684,7 @@ static int load_flat_file(struct linux_binprm *bprm, ret = result; pr_err("Unable to read code+data+bss, errno %d\n", ret); vm_munmap(textpos, text_len + data_len + extra + - MAX_SHARED_LIBS * sizeof(unsigned long)); + MAX_SHARED_LIBS * sizeof(u32)); goto err; } } @@ -754,8 +744,8 @@ static int load_flat_file(struct linux_binprm *bprm, * image. */ if (flags & FLAT_FLAG_GOTPIC) { - for (rp = (unsigned long __user *)datapos; ; rp++) { - unsigned long addr, rp_val; + for (rp = (u32 __user *)datapos; ; rp++) { + u32 addr, rp_val; if (get_user(rp_val, rp)) return -EFAULT; if (rp_val == 0xffffffff) @@ -784,9 +774,9 @@ static int load_flat_file(struct linux_binprm *bprm, * __start to address 4 so that is okay). */ if (rev > OLD_FLAT_VERSION) { - unsigned long __maybe_unused persistent = 0; + u32 __maybe_unused persistent = 0; for (i = 0; i < relocs; i++) { - unsigned long addr, relval; + u32 addr, relval; /* * Get the address of the pointer to be @@ -799,15 +789,18 @@ static int load_flat_file(struct linux_binprm *bprm, if (flat_set_persistent(relval, &persistent)) continue; addr = flat_get_relocate_addr(relval); - rp = (unsigned long __user *)calc_reloc(addr, libinfo, id, 1); - if (rp == (unsigned long __user *)RELOC_FAILED) { + rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1); + if (rp == (u32 __user *)RELOC_FAILED) { ret = -ENOEXEC; goto err; } /* Get the pointer's value. */ - addr = flat_get_addr_from_rp(rp, relval, flags, - &persistent); + ret = flat_get_addr_from_rp(rp, relval, flags, + &addr, &persistent); + if (unlikely(ret)) + goto err; + if (addr != 0) { /* * Do the relocation. PIC relocs in the data section are @@ -822,12 +815,14 @@ static int load_flat_file(struct linux_binprm *bprm, } /* Write back the relocated pointer. */ - flat_put_addr_at_rp(rp, addr, relval); + ret = flat_put_addr_at_rp(rp, addr, relval); + if (unlikely(ret)) + goto err; } } } else { for (i = 0; i < relocs; i++) { - unsigned long relval; + u32 relval; if (get_user(relval, reloc + i)) return -EFAULT; relval = ntohl(relval); @@ -885,7 +880,7 @@ static int load_flat_shared_library(int id, struct lib_info *libs) * as we're past the point of no return and are dealing with shared * libraries. */ - bprm.cred_prepared = 1; + bprm.called_set_creds = 1; res = prepare_binprm(&bprm); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index f4718098ac31..a7c5a9861bef 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -54,7 +54,7 @@ typedef struct { int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ - char *interpreter; /* filename of interpreter */ + const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; @@ -131,27 +131,26 @@ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; - char iname[BINPRM_BUF_SIZE]; - const char *iname_addr = iname; int retval; int fd_binary = -1; retval = -ENOEXEC; if (!enabled) - goto ret; + return retval; /* to keep locking time low, we copy the interpreter string */ read_lock(&entries_lock); fmt = check_file(bprm); if (fmt) - strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE); + dget(fmt->dentry); read_unlock(&entries_lock); if (!fmt) - goto ret; + return retval; /* Need to be able to load the file after exec */ + retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; + goto ret; if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) { retval = remove_arg_zero(bprm); @@ -195,22 +194,22 @@ static int load_misc_binary(struct linux_binprm *bprm) bprm->argc++; /* add the interp as argv[0] */ - retval = copy_strings_kernel(1, &iname_addr, bprm); + retval = copy_strings_kernel(1, &fmt->interpreter, bprm); if (retval < 0) goto error; bprm->argc++; /* Update interp in case binfmt_script needs it. */ - retval = bprm_change_interp(iname, bprm); + retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto error; - if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) { + if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = filp_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { - interp_file = open_exec(iname); + interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) @@ -218,12 +217,15 @@ static int load_misc_binary(struct linux_binprm *bprm) bprm->file = interp_file; if (fmt->flags & MISC_FMT_CREDENTIALS) { + loff_t pos = 0; + /* * No need to call prepare_binprm(), it's already been * done. bprm->buf is stale, update from interp_file. */ memset(bprm->buf, 0, BINPRM_BUF_SIZE); - retval = kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE); + retval = kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, + &pos); } else retval = prepare_binprm(bprm); @@ -235,6 +237,7 @@ static int load_misc_binary(struct linux_binprm *bprm) goto error; ret: + dput(fmt->dentry); return retval; error: if (fd_binary > 0) @@ -591,8 +594,13 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_evict_inode(struct inode *inode) { + Node *e = inode->i_private; + + if (e && e->flags & MISC_FMT_OPEN_FILE) + filp_close(e->interp_file, NULL); + clear_inode(inode); - kfree(inode->i_private); + kfree(e); } static void kill_node(Node *e) @@ -600,24 +608,14 @@ static void kill_node(Node *e) struct dentry *dentry; write_lock(&entries_lock); - dentry = e->dentry; - if (dentry) { - list_del_init(&e->list); - e->dentry = NULL; - } + list_del_init(&e->list); write_unlock(&entries_lock); - if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) { - filp_close(e->interp_file, NULL); - e->interp_file = NULL; - } - - if (dentry) { - drop_nlink(d_inode(dentry)); - d_drop(dentry); - dput(dentry); - simple_release_fs(&bm_mnt, &entry_count); - } + dentry = e->dentry; + drop_nlink(d_inode(dentry)); + d_drop(dentry); + dput(dentry); + simple_release_fs(&bm_mnt, &entry_count); } /* /<entry> */ @@ -662,7 +660,8 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, root = file_inode(file)->i_sb->s_root; inode_lock(d_inode(root)); - kill_node(e); + if (!list_empty(&e->list)) + kill_node(e); inode_unlock(d_inode(root)); break; @@ -791,7 +790,7 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, inode_lock(d_inode(root)); while (!list_empty(&entries)) - kill_node(list_entry(entries.next, Node, list)); + kill_node(list_first_entry(&entries, Node, list)); inode_unlock(d_inode(root)); break; diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index afdf4e3cafc2..7cde3f46ad26 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -19,7 +19,6 @@ static int load_script(struct linux_binprm *bprm) const char *i_arg, *i_name; char *cp; struct file *file; - char interp[BINPRM_BUF_SIZE]; int retval; if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) @@ -55,7 +54,7 @@ static int load_script(struct linux_binprm *bprm) break; } for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++); - if (*cp == '\0') + if (*cp == '\0') return -ENOEXEC; /* No interpreter name found */ i_name = cp; i_arg = NULL; @@ -65,7 +64,6 @@ static int load_script(struct linux_binprm *bprm) *cp++ = '\0'; if (*cp) i_arg = cp; - strcpy (interp, i_name); /* * OK, we've parsed out the interpreter name and * (optional) argument. @@ -80,24 +78,27 @@ static int load_script(struct linux_binprm *bprm) if (retval) return retval; retval = copy_strings_kernel(1, &bprm->interp, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; if (i_arg) { retval = copy_strings_kernel(1, &i_arg, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; } retval = copy_strings_kernel(1, &i_name, bprm); - if (retval) return retval; + if (retval) + return retval; bprm->argc++; - retval = bprm_change_interp(interp, bprm); + retval = bprm_change_interp(i_name, bprm); if (retval < 0) return retval; /* * OK, now restart the process with the interpreter's dentry. */ - file = open_exec(interp); + file = open_exec(i_name); if (IS_ERR(file)) return PTR_ERR(file); diff --git a/fs/block_dev.c b/fs/block_dev.c index 0a7404ef9335..789f55e851ae 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -223,8 +223,9 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, } bio_init(&bio, vecs, nr_pages); - bio.bi_bdev = bdev; + bio_set_dev(&bio, bdev); bio.bi_iter.bi_sector = pos >> 9; + bio.bi_write_hint = iocb->ki_hint; bio.bi_private = current; bio.bi_end_io = blkdev_bio_end_io_simple; @@ -262,8 +263,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, if (vecs != inline_vecs) kfree(vecs); - if (unlikely(bio.bi_error)) - ret = bio.bi_error; + if (unlikely(bio.bi_status)) + ret = blk_status_to_errno(bio.bi_status); bio_uninit(&bio); @@ -291,16 +292,18 @@ static void blkdev_bio_end_io(struct bio *bio) bool should_dirty = dio->should_dirty; if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) { - if (bio->bi_error && !dio->bio.bi_error) - dio->bio.bi_error = bio->bi_error; + if (bio->bi_status && !dio->bio.bi_status) + dio->bio.bi_status = bio->bi_status; } else { if (!dio->is_sync) { struct kiocb *iocb = dio->iocb; - ssize_t ret = dio->bio.bi_error; + ssize_t ret; - if (likely(!ret)) { + if (likely(!dio->bio.bi_status)) { ret = dio->size; iocb->ki_pos += ret; + } else { + ret = blk_status_to_errno(dio->bio.bi_status); } dio->iocb->ki_complete(iocb, ret, 0); @@ -337,7 +340,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bool is_read = (iov_iter_rw(iter) == READ), is_sync; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - int ret; + int ret = 0; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) @@ -359,14 +362,15 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) blk_start_plug(&plug); for (;;) { - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; + bio->bi_write_hint = iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = blkdev_bio_end_io; ret = bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) { - bio->bi_error = ret; + bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; } @@ -415,7 +419,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); - ret = dio->bio.bi_error; + if (!ret) + ret = blk_status_to_errno(dio->bio.bi_status); if (likely(!ret)) ret = dio->size; @@ -439,7 +444,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static __init int blkdev_init(void) { - blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio)); + blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS); if (!blkdev_dio_pool) return -ENOMEM; return 0; @@ -627,7 +632,7 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync) struct block_device *bdev = I_BDEV(bd_inode); int error; - error = filemap_write_and_wait_range(filp->f_mapping, start, end); + error = file_write_and_wait_range(filp, start, end); if (error) return error; @@ -711,10 +716,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); - if (result) + if (result) { end_page_writeback(page); - else + } else { + clean_page_buffers(page); unlock_page(page); + } blk_queue_exit(bdev->bd_queue); return result; } @@ -1446,6 +1453,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; + bdev->bd_partno = partno; if (!partno) { ret = -ENXIO; @@ -1734,6 +1742,8 @@ static int blkdev_open(struct inode * inode, struct file * filp) */ filp->f_flags |= O_LARGEFILE; + filp->f_mode |= FMODE_NOWAIT; + if (filp->f_flags & O_NDELAY) filp->f_mode |= FMODE_NDELAY; if (filp->f_flags & O_EXCL) @@ -1746,6 +1756,7 @@ static int blkdev_open(struct inode * inode, struct file * filp) return -ENOMEM; filp->f_mapping = bdev->bd_inode->i_mapping; + filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping); return blkdev_get(bdev, filp->f_mode, filp); } @@ -1885,6 +1896,9 @@ ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos >= size) return -ENOSPC; + if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT) + return -EOPNOTSUPP; + iov_iter_truncate(from, size - iocb->ki_pos); blk_start_plug(&plug); diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 80e9c18ea64f..a26c63b4ad68 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -6,6 +6,8 @@ config BTRFS_FS select ZLIB_DEFLATE select LZO_COMPRESS select LZO_DECOMPRESS + select ZSTD_COMPRESS + select ZSTD_DECOMPRESS select RAID6_PQ select XOR_BLOCKS select SRCU diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index 128ce17a80b0..962a95aefb81 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -6,7 +6,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \ transaction.o inode.o file.o tree-defrag.o \ extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \ extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \ - export.o tree-log.o free-space-cache.o zlib.o lzo.o \ + export.o tree-log.o free-space-cache.o zlib.o lzo.o zstd.o \ compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \ reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \ uuid-tree.o props.o hash.o free-space-tree.o diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 247b8dfaf6e5..1ba49ebe67da 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -78,12 +78,6 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (ret) - return ret; - } - ret = 0; break; case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) @@ -119,7 +113,18 @@ out: int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { - return __btrfs_set_acl(NULL, inode, acl, type); + int ret; + umode_t old_mode = inode->i_mode; + + if (type == ACL_TYPE_ACCESS && acl) { + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) + return ret; + } + ret = __btrfs_set_acl(NULL, inode, acl, type); + if (ret) + inode->i_mode = old_mode; + return ret; } /* diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index ff0b0be92d61..e00c8a9fd5bb 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -75,18 +75,18 @@ void btrfs_##name(struct work_struct *arg) \ } struct btrfs_fs_info * -btrfs_workqueue_owner(struct __btrfs_workqueue *wq) +btrfs_workqueue_owner(const struct __btrfs_workqueue *wq) { return wq->fs_info; } struct btrfs_fs_info * -btrfs_work_owner(struct btrfs_work *work) +btrfs_work_owner(const struct btrfs_work *work) { return work->wq->fs_info; } -bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq) +bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq) { /* * We could compare wq->normal->pending with num_online_cpus() diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h index 1f9597355c9d..fc957e00cef1 100644 --- a/fs/btrfs/async-thread.h +++ b/fs/btrfs/async-thread.h @@ -82,7 +82,7 @@ void btrfs_queue_work(struct btrfs_workqueue *wq, void btrfs_destroy_workqueue(struct btrfs_workqueue *wq); void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max); void btrfs_set_work_high_priority(struct btrfs_work *work); -struct btrfs_fs_info *btrfs_work_owner(struct btrfs_work *work); -struct btrfs_fs_info *btrfs_workqueue_owner(struct __btrfs_workqueue *wq); -bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq); +struct btrfs_fs_info *btrfs_work_owner(const struct btrfs_work *work); +struct btrfs_fs_info *btrfs_workqueue_owner(const struct __btrfs_workqueue *wq); +bool btrfs_workqueue_normal_congested(const struct btrfs_workqueue *wq); #endif diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 24865da63d8f..b517ef1477ea 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -16,8 +16,9 @@ * Boston, MA 021110-1307, USA. */ -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/rbtree.h> +#include <trace/events/btrfs.h> #include "ctree.h" #include "disk-io.h" #include "backref.h" @@ -26,11 +27,6 @@ #include "delayed-ref.h" #include "locking.h" -enum merge_mode { - MERGE_IDENTICAL_KEYS = 1, - MERGE_IDENTICAL_PARENTS, -}; - /* Just an arbitrary number so we can be sure this happened */ #define BACKREF_FOUND_SHARED 6 @@ -40,269 +36,11 @@ struct extent_inode_elem { struct extent_inode_elem *next; }; -/* - * ref_root is used as the root of the ref tree that hold a collection - * of unique references. - */ -struct ref_root { - struct rb_root rb_root; - - /* - * The unique_refs represents the number of ref_nodes with a positive - * count stored in the tree. Even if a ref_node (the count is greater - * than one) is added, the unique_refs will only increase by one. - */ - unsigned int unique_refs; -}; - -/* ref_node is used to store a unique reference to the ref tree. */ -struct ref_node { - struct rb_node rb_node; - - /* For NORMAL_REF, otherwise all these fields should be set to 0 */ - u64 root_id; - u64 object_id; - u64 offset; - - /* For SHARED_REF, otherwise parent field should be set to 0 */ - u64 parent; - - /* Ref to the ref_mod of btrfs_delayed_ref_node */ - int ref_mod; -}; - -/* Dynamically allocate and initialize a ref_root */ -static struct ref_root *ref_root_alloc(void) -{ - struct ref_root *ref_tree; - - ref_tree = kmalloc(sizeof(*ref_tree), GFP_NOFS); - if (!ref_tree) - return NULL; - - ref_tree->rb_root = RB_ROOT; - ref_tree->unique_refs = 0; - - return ref_tree; -} - -/* Free all nodes in the ref tree, and reinit ref_root */ -static void ref_root_fini(struct ref_root *ref_tree) -{ - struct ref_node *node; - struct rb_node *next; - - while ((next = rb_first(&ref_tree->rb_root)) != NULL) { - node = rb_entry(next, struct ref_node, rb_node); - rb_erase(next, &ref_tree->rb_root); - kfree(node); - } - - ref_tree->rb_root = RB_ROOT; - ref_tree->unique_refs = 0; -} - -static void ref_root_free(struct ref_root *ref_tree) -{ - if (!ref_tree) - return; - - ref_root_fini(ref_tree); - kfree(ref_tree); -} - -/* - * Compare ref_node with (root_id, object_id, offset, parent) - * - * The function compares two ref_node a and b. It returns an integer less - * than, equal to, or greater than zero , respectively, to be less than, to - * equal, or be greater than b. - */ -static int ref_node_cmp(struct ref_node *a, struct ref_node *b) -{ - if (a->root_id < b->root_id) - return -1; - else if (a->root_id > b->root_id) - return 1; - - if (a->object_id < b->object_id) - return -1; - else if (a->object_id > b->object_id) - return 1; - - if (a->offset < b->offset) - return -1; - else if (a->offset > b->offset) - return 1; - - if (a->parent < b->parent) - return -1; - else if (a->parent > b->parent) - return 1; - - return 0; -} - -/* - * Search ref_node with (root_id, object_id, offset, parent) in the tree - * - * if found, the pointer of the ref_node will be returned; - * if not found, NULL will be returned and pos will point to the rb_node for - * insert, pos_parent will point to pos'parent for insert; -*/ -static struct ref_node *__ref_tree_search(struct ref_root *ref_tree, - struct rb_node ***pos, - struct rb_node **pos_parent, - u64 root_id, u64 object_id, - u64 offset, u64 parent) -{ - struct ref_node *cur = NULL; - struct ref_node entry; - int ret; - - entry.root_id = root_id; - entry.object_id = object_id; - entry.offset = offset; - entry.parent = parent; - - *pos = &ref_tree->rb_root.rb_node; - - while (**pos) { - *pos_parent = **pos; - cur = rb_entry(*pos_parent, struct ref_node, rb_node); - - ret = ref_node_cmp(cur, &entry); - if (ret > 0) - *pos = &(**pos)->rb_left; - else if (ret < 0) - *pos = &(**pos)->rb_right; - else - return cur; - } - - return NULL; -} - -/* - * Insert a ref_node to the ref tree - * @pos used for specifiy the position to insert - * @pos_parent for specifiy pos's parent - * - * success, return 0; - * ref_node already exists, return -EEXIST; -*/ -static int ref_tree_insert(struct ref_root *ref_tree, struct rb_node **pos, - struct rb_node *pos_parent, struct ref_node *ins) -{ - struct rb_node **p = NULL; - struct rb_node *parent = NULL; - struct ref_node *cur = NULL; - - if (!pos) { - cur = __ref_tree_search(ref_tree, &p, &parent, ins->root_id, - ins->object_id, ins->offset, - ins->parent); - if (cur) - return -EEXIST; - } else { - p = pos; - parent = pos_parent; - } - - rb_link_node(&ins->rb_node, parent, p); - rb_insert_color(&ins->rb_node, &ref_tree->rb_root); - - return 0; -} - -/* Erase and free ref_node, caller should update ref_root->unique_refs */ -static void ref_tree_remove(struct ref_root *ref_tree, struct ref_node *node) -{ - rb_erase(&node->rb_node, &ref_tree->rb_root); - kfree(node); -} - -/* - * Update ref_root->unique_refs - * - * Call __ref_tree_search - * 1. if ref_node doesn't exist, ref_tree_insert this node, and update - * ref_root->unique_refs: - * if ref_node->ref_mod > 0, ref_root->unique_refs++; - * if ref_node->ref_mod < 0, do noting; - * - * 2. if ref_node is found, then get origin ref_node->ref_mod, and update - * ref_node->ref_mod. - * if ref_node->ref_mod is equal to 0,then call ref_tree_remove - * - * according to origin_mod and new_mod, update ref_root->items - * +----------------+--------------+-------------+ - * | |new_count <= 0|new_count > 0| - * +----------------+--------------+-------------+ - * |origin_count < 0| 0 | 1 | - * +----------------+--------------+-------------+ - * |origin_count > 0| -1 | 0 | - * +----------------+--------------+-------------+ - * - * In case of allocation failure, -ENOMEM is returned and the ref_tree stays - * unaltered. - * Success, return 0 - */ -static int ref_tree_add(struct ref_root *ref_tree, u64 root_id, u64 object_id, - u64 offset, u64 parent, int count) -{ - struct ref_node *node = NULL; - struct rb_node **pos = NULL; - struct rb_node *pos_parent = NULL; - int origin_count; - int ret; - - if (!count) - return 0; - - node = __ref_tree_search(ref_tree, &pos, &pos_parent, root_id, - object_id, offset, parent); - if (node == NULL) { - node = kmalloc(sizeof(*node), GFP_NOFS); - if (!node) - return -ENOMEM; - - node->root_id = root_id; - node->object_id = object_id; - node->offset = offset; - node->parent = parent; - node->ref_mod = count; - - ret = ref_tree_insert(ref_tree, pos, pos_parent, node); - ASSERT(!ret); - if (ret) { - kfree(node); - return ret; - } - - ref_tree->unique_refs += node->ref_mod > 0 ? 1 : 0; - - return 0; - } - - origin_count = node->ref_mod; - node->ref_mod += count; - - if (node->ref_mod > 0) - ref_tree->unique_refs += origin_count > 0 ? 0 : 1; - else if (node->ref_mod <= 0) - ref_tree->unique_refs += origin_count > 0 ? -1 : 0; - - if (!node->ref_mod) - ref_tree_remove(ref_tree, node); - - return 0; -} - -static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb, - struct btrfs_file_extent_item *fi, - u64 extent_item_pos, - struct extent_inode_elem **eie) +static int check_extent_in_eb(const struct btrfs_key *key, + const struct extent_buffer *eb, + const struct btrfs_file_extent_item *fi, + u64 extent_item_pos, + struct extent_inode_elem **eie) { u64 offset = 0; struct extent_inode_elem *e; @@ -344,9 +82,9 @@ static void free_inode_elem_list(struct extent_inode_elem *eie) } } -static int find_extent_in_eb(struct extent_buffer *eb, u64 wanted_disk_byte, - u64 extent_item_pos, - struct extent_inode_elem **eie) +static int find_extent_in_eb(const struct extent_buffer *eb, + u64 wanted_disk_byte, u64 extent_item_pos, + struct extent_inode_elem **eie) { u64 disk_byte; struct btrfs_key key; @@ -383,26 +121,44 @@ static int find_extent_in_eb(struct extent_buffer *eb, u64 wanted_disk_byte, return 0; } +struct preftree { + struct rb_root root; + unsigned int count; +}; + +#define PREFTREE_INIT { .root = RB_ROOT, .count = 0 } + +struct preftrees { + struct preftree direct; /* BTRFS_SHARED_[DATA|BLOCK]_REF_KEY */ + struct preftree indirect; /* BTRFS_[TREE_BLOCK|EXTENT_DATA]_REF_KEY */ + struct preftree indirect_missing_keys; +}; + /* - * this structure records all encountered refs on the way up to the root + * Checks for a shared extent during backref search. + * + * The share_count tracks prelim_refs (direct and indirect) having a + * ref->count >0: + * - incremented when a ref->count transitions to >0 + * - decremented when a ref->count transitions to <1 */ -struct __prelim_ref { - struct list_head list; - u64 root_id; - struct btrfs_key key_for_search; - int level; - int count; - struct extent_inode_elem *inode_list; - u64 parent; - u64 wanted_disk_byte; +struct share_check { + u64 root_objectid; + u64 inum; + int share_count; }; +static inline int extent_is_shared(struct share_check *sc) +{ + return (sc && sc->share_count > 1) ? BACKREF_FOUND_SHARED : 0; +} + static struct kmem_cache *btrfs_prelim_ref_cache; int __init btrfs_prelim_ref_init(void) { btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref", - sizeof(struct __prelim_ref), + sizeof(struct prelim_ref), 0, SLAB_MEM_SPREAD, NULL); @@ -416,6 +172,134 @@ void btrfs_prelim_ref_exit(void) kmem_cache_destroy(btrfs_prelim_ref_cache); } +static void free_pref(struct prelim_ref *ref) +{ + kmem_cache_free(btrfs_prelim_ref_cache, ref); +} + +/* + * Return 0 when both refs are for the same block (and can be merged). + * A -1 return indicates ref1 is a 'lower' block than ref2, while 1 + * indicates a 'higher' block. + */ +static int prelim_ref_compare(struct prelim_ref *ref1, + struct prelim_ref *ref2) +{ + if (ref1->level < ref2->level) + return -1; + if (ref1->level > ref2->level) + return 1; + if (ref1->root_id < ref2->root_id) + return -1; + if (ref1->root_id > ref2->root_id) + return 1; + if (ref1->key_for_search.type < ref2->key_for_search.type) + return -1; + if (ref1->key_for_search.type > ref2->key_for_search.type) + return 1; + if (ref1->key_for_search.objectid < ref2->key_for_search.objectid) + return -1; + if (ref1->key_for_search.objectid > ref2->key_for_search.objectid) + return 1; + if (ref1->key_for_search.offset < ref2->key_for_search.offset) + return -1; + if (ref1->key_for_search.offset > ref2->key_for_search.offset) + return 1; + if (ref1->parent < ref2->parent) + return -1; + if (ref1->parent > ref2->parent) + return 1; + + return 0; +} + +void update_share_count(struct share_check *sc, int oldcount, int newcount) +{ + if ((!sc) || (oldcount == 0 && newcount < 1)) + return; + + if (oldcount > 0 && newcount < 1) + sc->share_count--; + else if (oldcount < 1 && newcount > 0) + sc->share_count++; +} + +/* + * Add @newref to the @root rbtree, merging identical refs. + * + * Callers should assume that newref has been freed after calling. + */ +static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, + struct preftree *preftree, + struct prelim_ref *newref, + struct share_check *sc) +{ + struct rb_root *root; + struct rb_node **p; + struct rb_node *parent = NULL; + struct prelim_ref *ref; + int result; + + root = &preftree->root; + p = &root->rb_node; + + while (*p) { + parent = *p; + ref = rb_entry(parent, struct prelim_ref, rbnode); + result = prelim_ref_compare(ref, newref); + if (result < 0) { + p = &(*p)->rb_left; + } else if (result > 0) { + p = &(*p)->rb_right; + } else { + /* Identical refs, merge them and free @newref */ + struct extent_inode_elem *eie = ref->inode_list; + + while (eie && eie->next) + eie = eie->next; + + if (!eie) + ref->inode_list = newref->inode_list; + else + eie->next = newref->inode_list; + trace_btrfs_prelim_ref_merge(fs_info, ref, newref, + preftree->count); + /* + * A delayed ref can have newref->count < 0. + * The ref->count is updated to follow any + * BTRFS_[ADD|DROP]_DELAYED_REF actions. + */ + update_share_count(sc, ref->count, + ref->count + newref->count); + ref->count += newref->count; + free_pref(newref); + return; + } + } + + update_share_count(sc, 0, newref->count); + preftree->count++; + trace_btrfs_prelim_ref_insert(fs_info, newref, NULL, preftree->count); + rb_link_node(&newref->rbnode, parent, p); + rb_insert_color(&newref->rbnode, root); +} + +/* + * Release the entire tree. We don't care about internal consistency so + * just free everything and then reset the tree root. + */ +static void prelim_release(struct preftree *preftree) +{ + struct prelim_ref *ref, *next_ref; + + rbtree_postorder_for_each_entry_safe(ref, next_ref, &preftree->root, + rbnode) + free_pref(ref); + + preftree->root = RB_ROOT; + preftree->count = 0; +} + /* * the rules for all callers of this function are: * - obtaining the parent is the goal @@ -448,19 +332,19 @@ void btrfs_prelim_ref_exit(void) * * - column 1, 3: we've the parent -> done * - column 2: we take the first key from the block to find the parent - * (see __add_missing_keys) + * (see add_missing_keys) * - column 4: we use the key to find the parent * * additional information that's available but not required to find the parent * block might help in merging entries to gain some speed. */ - -static int __add_prelim_ref(struct list_head *head, u64 root_id, - struct btrfs_key *key, int level, - u64 parent, u64 wanted_disk_byte, int count, - gfp_t gfp_mask) +static int add_prelim_ref(const struct btrfs_fs_info *fs_info, + struct preftree *preftree, u64 root_id, + const struct btrfs_key *key, int level, u64 parent, + u64 wanted_disk_byte, int count, + struct share_check *sc, gfp_t gfp_mask) { - struct __prelim_ref *ref; + struct prelim_ref *ref; if (root_id == BTRFS_DATA_RELOC_TREE_OBJECTID) return 0; @@ -503,13 +387,37 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id, ref->count = count; ref->parent = parent; ref->wanted_disk_byte = wanted_disk_byte; - list_add_tail(&ref->list, head); + prelim_ref_insert(fs_info, preftree, ref, sc); + return extent_is_shared(sc); +} - return 0; +/* direct refs use root == 0, key == NULL */ +static int add_direct_ref(const struct btrfs_fs_info *fs_info, + struct preftrees *preftrees, int level, u64 parent, + u64 wanted_disk_byte, int count, + struct share_check *sc, gfp_t gfp_mask) +{ + return add_prelim_ref(fs_info, &preftrees->direct, 0, NULL, level, + parent, wanted_disk_byte, count, sc, gfp_mask); +} + +/* indirect refs use parent == 0 */ +static int add_indirect_ref(const struct btrfs_fs_info *fs_info, + struct preftrees *preftrees, u64 root_id, + const struct btrfs_key *key, int level, + u64 wanted_disk_byte, int count, + struct share_check *sc, gfp_t gfp_mask) +{ + struct preftree *tree = &preftrees->indirect; + + if (!key) + tree = &preftrees->indirect_missing_keys; + return add_prelim_ref(fs_info, tree, root_id, key, level, 0, + wanted_disk_byte, count, sc, gfp_mask); } static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, - struct ulist *parents, struct __prelim_ref *ref, + struct ulist *parents, struct prelim_ref *ref, int level, u64 time_seq, const u64 *extent_item_pos, u64 total_refs) { @@ -599,11 +507,10 @@ next: * resolve an indirect backref in the form (root_id, key, level) * to a logical address */ -static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, u64 time_seq, - struct __prelim_ref *ref, - struct ulist *parents, - const u64 *extent_item_pos, u64 total_refs) +static int resolve_indirect_ref(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, u64 time_seq, + struct prelim_ref *ref, struct ulist *parents, + const u64 *extent_item_pos, u64 total_refs) { struct btrfs_root *root; struct btrfs_key root_key; @@ -681,52 +588,90 @@ out: return ret; } +static struct extent_inode_elem * +unode_aux_to_inode_list(struct ulist_node *node) +{ + if (!node) + return NULL; + return (struct extent_inode_elem *)(uintptr_t)node->aux; +} + /* - * resolve all indirect backrefs from the list + * We maintain three seperate rbtrees: one for direct refs, one for + * indirect refs which have a key, and one for indirect refs which do not + * have a key. Each tree does merge on insertion. + * + * Once all of the references are located, we iterate over the tree of + * indirect refs with missing keys. An appropriate key is located and + * the ref is moved onto the tree for indirect refs. After all missing + * keys are thus located, we iterate over the indirect ref tree, resolve + * each reference, and then insert the resolved reference onto the + * direct tree (merging there too). + * + * New backrefs (i.e., for parent nodes) are added to the appropriate + * rbtree as they are encountered. The new backrefs are subsequently + * resolved as above. */ -static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, u64 time_seq, - struct list_head *head, - const u64 *extent_item_pos, u64 total_refs, - u64 root_objectid) +static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, u64 time_seq, + struct preftrees *preftrees, + const u64 *extent_item_pos, u64 total_refs, + struct share_check *sc) { int err; int ret = 0; - struct __prelim_ref *ref; - struct __prelim_ref *ref_safe; - struct __prelim_ref *new_ref; struct ulist *parents; struct ulist_node *node; struct ulist_iterator uiter; + struct rb_node *rnode; parents = ulist_alloc(GFP_NOFS); if (!parents) return -ENOMEM; /* - * _safe allows us to insert directly after the current item without - * iterating over the newly inserted items. - * we're also allowed to re-assign ref during iteration. + * We could trade memory usage for performance here by iterating + * the tree, allocating new refs for each insertion, and then + * freeing the entire indirect tree when we're done. In some test + * cases, the tree can grow quite large (~200k objects). */ - list_for_each_entry_safe(ref, ref_safe, head, list) { - if (ref->parent) /* already direct */ - continue; - if (ref->count == 0) + while ((rnode = rb_first(&preftrees->indirect.root))) { + struct prelim_ref *ref; + + ref = rb_entry(rnode, struct prelim_ref, rbnode); + if (WARN(ref->parent, + "BUG: direct ref found in indirect tree")) { + ret = -EINVAL; + goto out; + } + + rb_erase(&ref->rbnode, &preftrees->indirect.root); + preftrees->indirect.count--; + + if (ref->count == 0) { + free_pref(ref); continue; - if (root_objectid && ref->root_id != root_objectid) { + } + + if (sc && sc->root_objectid && + ref->root_id != sc->root_objectid) { + free_pref(ref); ret = BACKREF_FOUND_SHARED; goto out; } - err = __resolve_indirect_ref(fs_info, path, time_seq, ref, - parents, extent_item_pos, - total_refs); + err = resolve_indirect_ref(fs_info, path, time_seq, ref, + parents, extent_item_pos, + total_refs); /* * we can only tolerate ENOENT,otherwise,we should catch error * and return directly. */ if (err == -ENOENT) { + prelim_ref_insert(fs_info, &preftrees->direct, ref, + NULL); continue; } else if (err) { + free_pref(ref); ret = err; goto out; } @@ -735,68 +680,65 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, ULIST_ITER_INIT(&uiter); node = ulist_next(parents, &uiter); ref->parent = node ? node->val : 0; - ref->inode_list = node ? - (struct extent_inode_elem *)(uintptr_t)node->aux : NULL; + ref->inode_list = unode_aux_to_inode_list(node); - /* additional parents require new refs being added here */ + /* Add a prelim_ref(s) for any other parent(s). */ while ((node = ulist_next(parents, &uiter))) { + struct prelim_ref *new_ref; + new_ref = kmem_cache_alloc(btrfs_prelim_ref_cache, GFP_NOFS); if (!new_ref) { + free_pref(ref); ret = -ENOMEM; goto out; } memcpy(new_ref, ref, sizeof(*ref)); new_ref->parent = node->val; - new_ref->inode_list = (struct extent_inode_elem *) - (uintptr_t)node->aux; - list_add(&new_ref->list, &ref->list); + new_ref->inode_list = unode_aux_to_inode_list(node); + prelim_ref_insert(fs_info, &preftrees->direct, + new_ref, NULL); } + + /* + * Now it's a direct ref, put it in the the direct tree. We must + * do this last because the ref could be merged/freed here. + */ + prelim_ref_insert(fs_info, &preftrees->direct, ref, NULL); + ulist_reinit(parents); + cond_resched(); } out: ulist_free(parents); return ret; } -static inline int ref_for_same_block(struct __prelim_ref *ref1, - struct __prelim_ref *ref2) -{ - if (ref1->level != ref2->level) - return 0; - if (ref1->root_id != ref2->root_id) - return 0; - if (ref1->key_for_search.type != ref2->key_for_search.type) - return 0; - if (ref1->key_for_search.objectid != ref2->key_for_search.objectid) - return 0; - if (ref1->key_for_search.offset != ref2->key_for_search.offset) - return 0; - if (ref1->parent != ref2->parent) - return 0; - - return 1; -} - /* * read tree blocks and add keys where required. */ -static int __add_missing_keys(struct btrfs_fs_info *fs_info, - struct list_head *head) +static int add_missing_keys(struct btrfs_fs_info *fs_info, + struct preftrees *preftrees) { - struct __prelim_ref *ref; + struct prelim_ref *ref; struct extent_buffer *eb; + struct preftree *tree = &preftrees->indirect_missing_keys; + struct rb_node *node; - list_for_each_entry(ref, head, list) { - if (ref->parent) - continue; - if (ref->key_for_search.type) - continue; + while ((node = rb_first(&tree->root))) { + ref = rb_entry(node, struct prelim_ref, rbnode); + rb_erase(node, &tree->root); + + BUG_ON(ref->parent); /* should not be a direct ref */ + BUG_ON(ref->key_for_search.type); BUG_ON(!ref->wanted_disk_byte); + eb = read_tree_block(fs_info, ref->wanted_disk_byte, 0); if (IS_ERR(eb)) { + free_pref(ref); return PTR_ERR(eb); } else if (!extent_buffer_uptodate(eb)) { + free_pref(ref); free_extent_buffer(eb); return -EIO; } @@ -807,73 +749,33 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info, btrfs_node_key_to_cpu(eb, &ref->key_for_search, 0); btrfs_tree_read_unlock(eb); free_extent_buffer(eb); + prelim_ref_insert(fs_info, &preftrees->indirect, ref, NULL); + cond_resched(); } return 0; } /* - * merge backrefs and adjust counts accordingly - * - * FIXME: For MERGE_IDENTICAL_KEYS, if we add more keys in __add_prelim_ref - * then we can merge more here. Additionally, we could even add a key - * range for the blocks we looked into to merge even more (-> replace - * unresolved refs by those having a parent). - */ -static void __merge_refs(struct list_head *head, enum merge_mode mode) -{ - struct __prelim_ref *pos1; - - list_for_each_entry(pos1, head, list) { - struct __prelim_ref *pos2 = pos1, *tmp; - - list_for_each_entry_safe_continue(pos2, tmp, head, list) { - struct __prelim_ref *ref1 = pos1, *ref2 = pos2; - struct extent_inode_elem *eie; - - if (!ref_for_same_block(ref1, ref2)) - continue; - if (mode == MERGE_IDENTICAL_KEYS) { - if (!ref1->parent && ref2->parent) - swap(ref1, ref2); - } else { - if (ref1->parent != ref2->parent) - continue; - } - - eie = ref1->inode_list; - while (eie && eie->next) - eie = eie->next; - if (eie) - eie->next = ref2->inode_list; - else - ref1->inode_list = ref2->inode_list; - ref1->count += ref2->count; - - list_del(&ref2->list); - kmem_cache_free(btrfs_prelim_ref_cache, ref2); - cond_resched(); - } - - } -} - -/* * add all currently queued delayed refs from this head whose seq nr is * smaller or equal that seq to the list */ -static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, - struct list_head *prefs, u64 *total_refs, - u64 inum) +static int add_delayed_refs(const struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_head *head, u64 seq, + struct preftrees *preftrees, u64 *total_refs, + struct share_check *sc) { struct btrfs_delayed_ref_node *node; struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct btrfs_key key; - struct btrfs_key op_key = {0}; - int sgn; + struct btrfs_key tmp_op_key; + struct btrfs_key *op_key = NULL; + int count; int ret = 0; - if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(&op_key, &extent_op->key); + if (extent_op && extent_op->update_key) { + btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); + op_key = &tmp_op_key; + } spin_lock(&head->lock); list_for_each_entry(node, &head->ref_list, list) { @@ -886,36 +788,40 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, WARN_ON(1); continue; case BTRFS_ADD_DELAYED_REF: - sgn = 1; + count = node->ref_mod; break; case BTRFS_DROP_DELAYED_REF: - sgn = -1; + count = node->ref_mod * -1; break; default: BUG_ON(1); } - *total_refs += (node->ref_mod * sgn); + *total_refs += count; switch (node->type) { case BTRFS_TREE_BLOCK_REF_KEY: { + /* NORMAL INDIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; ref = btrfs_delayed_node_to_tree_ref(node); - ret = __add_prelim_ref(prefs, ref->root, &op_key, - ref->level + 1, 0, node->bytenr, - node->ref_mod * sgn, GFP_ATOMIC); + ret = add_indirect_ref(fs_info, preftrees, ref->root, + &tmp_op_key, ref->level + 1, + node->bytenr, count, sc, + GFP_ATOMIC); break; } case BTRFS_SHARED_BLOCK_REF_KEY: { + /* SHARED DIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; ref = btrfs_delayed_node_to_tree_ref(node); - ret = __add_prelim_ref(prefs, 0, NULL, - ref->level + 1, ref->parent, - node->bytenr, - node->ref_mod * sgn, GFP_ATOMIC); + + ret = add_direct_ref(fs_info, preftrees, ref->level + 1, + ref->parent, node->bytenr, count, + sc, GFP_ATOMIC); break; } case BTRFS_EXTENT_DATA_REF_KEY: { + /* NORMAL INDIRECT DATA backref */ struct btrfs_delayed_data_ref *ref; ref = btrfs_delayed_node_to_data_ref(node); @@ -927,42 +833,53 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, * Found a inum that doesn't match our known inum, we * know it's shared. */ - if (inum && ref->objectid != inum) { + if (sc && sc->inum && ref->objectid != sc->inum) { ret = BACKREF_FOUND_SHARED; - break; + goto out; } - ret = __add_prelim_ref(prefs, ref->root, &key, 0, 0, - node->bytenr, - node->ref_mod * sgn, GFP_ATOMIC); + ret = add_indirect_ref(fs_info, preftrees, ref->root, + &key, 0, node->bytenr, count, sc, + GFP_ATOMIC); break; } case BTRFS_SHARED_DATA_REF_KEY: { + /* SHARED DIRECT FULL backref */ struct btrfs_delayed_data_ref *ref; ref = btrfs_delayed_node_to_data_ref(node); - ret = __add_prelim_ref(prefs, 0, NULL, 0, - ref->parent, node->bytenr, - node->ref_mod * sgn, GFP_ATOMIC); + + ret = add_direct_ref(fs_info, preftrees, 0, ref->parent, + node->bytenr, count, sc, + GFP_ATOMIC); break; } default: WARN_ON(1); } - if (ret) + /* + * We must ignore BACKREF_FOUND_SHARED until all delayed + * refs have been checked. + */ + if (ret && (ret != BACKREF_FOUND_SHARED)) break; } + if (!ret) + ret = extent_is_shared(sc); +out: spin_unlock(&head->lock); return ret; } /* * add all inline backrefs for bytenr to the list + * + * Returns 0 on success, <0 on error, or BACKREF_FOUND_SHARED. */ -static int __add_inline_refs(struct btrfs_path *path, u64 bytenr, - int *info_level, struct list_head *prefs, - struct ref_root *ref_tree, - u64 *total_refs, u64 inum) +static int add_inline_refs(const struct btrfs_fs_info *fs_info, + struct btrfs_path *path, u64 bytenr, + int *info_level, struct preftrees *preftrees, + u64 *total_refs, struct share_check *sc) { int ret = 0; int slot; @@ -1012,14 +929,18 @@ static int __add_inline_refs(struct btrfs_path *path, u64 bytenr, int type; iref = (struct btrfs_extent_inline_ref *)ptr; - type = btrfs_extent_inline_ref_type(leaf, iref); + type = btrfs_get_extent_inline_ref_type(leaf, iref, + BTRFS_REF_TYPE_ANY); + if (type == BTRFS_REF_TYPE_INVALID) + return -EINVAL; + offset = btrfs_extent_inline_ref_offset(leaf, iref); switch (type) { case BTRFS_SHARED_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, 0, NULL, - *info_level + 1, offset, - bytenr, 1, GFP_NOFS); + ret = add_direct_ref(fs_info, preftrees, + *info_level + 1, offset, + bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_SHARED_DATA_REF_KEY: { struct btrfs_shared_data_ref *sdref; @@ -1027,21 +948,15 @@ static int __add_inline_refs(struct btrfs_path *path, u64 bytenr, sdref = (struct btrfs_shared_data_ref *)(iref + 1); count = btrfs_shared_data_ref_count(leaf, sdref); - ret = __add_prelim_ref(prefs, 0, NULL, 0, offset, - bytenr, count, GFP_NOFS); - if (ref_tree) { - if (!ret) - ret = ref_tree_add(ref_tree, 0, 0, 0, - bytenr, count); - if (!ret && ref_tree->unique_refs > 1) - ret = BACKREF_FOUND_SHARED; - } + + ret = add_direct_ref(fs_info, preftrees, 0, offset, + bytenr, count, sc, GFP_NOFS); break; } case BTRFS_TREE_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, offset, NULL, - *info_level + 1, 0, - bytenr, 1, GFP_NOFS); + ret = add_indirect_ref(fs_info, preftrees, offset, + NULL, *info_level + 1, + bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_extent_data_ref *dref; @@ -1055,23 +970,16 @@ static int __add_inline_refs(struct btrfs_path *path, u64 bytenr, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (inum && key.objectid != inum) { + if (sc && sc->inum && key.objectid != sc->inum) { ret = BACKREF_FOUND_SHARED; break; } root = btrfs_extent_data_ref_root(leaf, dref); - ret = __add_prelim_ref(prefs, root, &key, 0, 0, - bytenr, count, GFP_NOFS); - if (ref_tree) { - if (!ret) - ret = ref_tree_add(ref_tree, root, - key.objectid, - key.offset, 0, - count); - if (!ret && ref_tree->unique_refs > 1) - ret = BACKREF_FOUND_SHARED; - } + + ret = add_indirect_ref(fs_info, preftrees, root, + &key, 0, bytenr, count, + sc, GFP_NOFS); break; } default: @@ -1087,11 +995,13 @@ static int __add_inline_refs(struct btrfs_path *path, u64 bytenr, /* * add all non-inline backrefs for bytenr to the list + * + * Returns 0 on success, <0 on error, or BACKREF_FOUND_SHARED. */ -static int __add_keyed_refs(struct btrfs_fs_info *fs_info, - struct btrfs_path *path, u64 bytenr, - int info_level, struct list_head *prefs, - struct ref_root *ref_tree, u64 inum) +static int add_keyed_refs(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, u64 bytenr, + int info_level, struct preftrees *preftrees, + struct share_check *sc) { struct btrfs_root *extent_root = fs_info->extent_root; int ret; @@ -1121,34 +1031,32 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, switch (key.type) { case BTRFS_SHARED_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, 0, NULL, - info_level + 1, key.offset, - bytenr, 1, GFP_NOFS); + /* SHARED DIRECT METADATA backref */ + ret = add_direct_ref(fs_info, preftrees, + info_level + 1, key.offset, + bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_SHARED_DATA_REF_KEY: { + /* SHARED DIRECT FULL backref */ struct btrfs_shared_data_ref *sdref; int count; sdref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); count = btrfs_shared_data_ref_count(leaf, sdref); - ret = __add_prelim_ref(prefs, 0, NULL, 0, key.offset, - bytenr, count, GFP_NOFS); - if (ref_tree) { - if (!ret) - ret = ref_tree_add(ref_tree, 0, 0, 0, - bytenr, count); - if (!ret && ref_tree->unique_refs > 1) - ret = BACKREF_FOUND_SHARED; - } + ret = add_direct_ref(fs_info, preftrees, 0, + key.offset, bytenr, count, + sc, GFP_NOFS); break; } case BTRFS_TREE_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, key.offset, NULL, - info_level + 1, 0, - bytenr, 1, GFP_NOFS); + /* NORMAL INDIRECT METADATA backref */ + ret = add_indirect_ref(fs_info, preftrees, key.offset, + NULL, info_level + 1, bytenr, + 1, NULL, GFP_NOFS); break; case BTRFS_EXTENT_DATA_REF_KEY: { + /* NORMAL INDIRECT DATA backref */ struct btrfs_extent_data_ref *dref; int count; u64 root; @@ -1161,23 +1069,15 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (inum && key.objectid != inum) { + if (sc && sc->inum && key.objectid != sc->inum) { ret = BACKREF_FOUND_SHARED; break; } root = btrfs_extent_data_ref_root(leaf, dref); - ret = __add_prelim_ref(prefs, root, &key, 0, 0, - bytenr, count, GFP_NOFS); - if (ref_tree) { - if (!ret) - ret = ref_tree_add(ref_tree, root, - key.objectid, - key.offset, 0, - count); - if (!ret && ref_tree->unique_refs > 1) - ret = BACKREF_FOUND_SHARED; - } + ret = add_indirect_ref(fs_info, preftrees, root, + &key, 0, bytenr, count, + sc, GFP_NOFS); break; } default: @@ -1197,15 +1097,15 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, * indirect refs to their parent bytenr. * When roots are found, they're added to the roots list * - * NOTE: This can return values > 0 - * * If time_seq is set to SEQ_LAST, it will not search delayed_refs, and behave * much like trans == NULL case, the difference only lies in it will not * commit root. * The special case is for qgroup to search roots in commit_transaction(). * - * If check_shared is set to 1, any extent has more than one ref item, will - * be returned BACKREF_FOUND_SHARED immediately. + * @sc - if !NULL, then immediately return BACKREF_FOUND_SHARED when a + * shared extent is detected. + * + * Otherwise this returns 0 for success and <0 for an error. * * FIXME some caching might speed things up */ @@ -1213,7 +1113,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, u64 time_seq, struct ulist *refs, struct ulist *roots, const u64 *extent_item_pos, - u64 root_objectid, u64 inum, int check_shared) + struct share_check *sc) { struct btrfs_key key; struct btrfs_path *path; @@ -1221,15 +1121,16 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_head *head; int info_level = 0; int ret; - struct list_head prefs_delayed; - struct list_head prefs; - struct __prelim_ref *ref; + struct prelim_ref *ref; + struct rb_node *node; struct extent_inode_elem *eie = NULL; - struct ref_root *ref_tree = NULL; + /* total of both direct AND indirect refs! */ u64 total_refs = 0; - - INIT_LIST_HEAD(&prefs); - INIT_LIST_HEAD(&prefs_delayed); + struct preftrees preftrees = { + .direct = PREFTREE_INIT, + .indirect = PREFTREE_INIT, + .indirect_missing_keys = PREFTREE_INIT + }; key.objectid = bytenr; key.offset = (u64)-1; @@ -1257,18 +1158,6 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans, again: head = NULL; - if (check_shared) { - if (!ref_tree) { - ref_tree = ref_root_alloc(); - if (!ref_tree) { - ret = -ENOMEM; - goto out; - } - } else { - ref_root_fini(ref_tree); - } - } - ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0); if (ret < 0) goto out; @@ -1304,45 +1193,14 @@ again: goto again; } spin_unlock(&delayed_refs->lock); - ret = __add_delayed_refs(head, time_seq, - &prefs_delayed, &total_refs, - inum); + ret = add_delayed_refs(fs_info, head, time_seq, + &preftrees, &total_refs, sc); mutex_unlock(&head->mutex); if (ret) goto out; } else { spin_unlock(&delayed_refs->lock); } - - if (check_shared && !list_empty(&prefs_delayed)) { - /* - * Add all delay_ref to the ref_tree and check if there - * are multiple ref items added. - */ - list_for_each_entry(ref, &prefs_delayed, list) { - if (ref->key_for_search.type) { - ret = ref_tree_add(ref_tree, - ref->root_id, - ref->key_for_search.objectid, - ref->key_for_search.offset, - 0, ref->count); - if (ret) - goto out; - } else { - ret = ref_tree_add(ref_tree, 0, 0, 0, - ref->parent, ref->count); - if (ret) - goto out; - } - - } - - if (ref_tree->unique_refs > 1) { - ret = BACKREF_FOUND_SHARED; - goto out; - } - - } } if (path->slots[0]) { @@ -1356,42 +1214,48 @@ again: if (key.objectid == bytenr && (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY)) { - ret = __add_inline_refs(path, bytenr, - &info_level, &prefs, - ref_tree, &total_refs, - inum); + ret = add_inline_refs(fs_info, path, bytenr, + &info_level, &preftrees, + &total_refs, sc); if (ret) goto out; - ret = __add_keyed_refs(fs_info, path, bytenr, - info_level, &prefs, - ref_tree, inum); + ret = add_keyed_refs(fs_info, path, bytenr, info_level, + &preftrees, sc); if (ret) goto out; } } - btrfs_release_path(path); - list_splice_init(&prefs_delayed, &prefs); + btrfs_release_path(path); - ret = __add_missing_keys(fs_info, &prefs); + ret = add_missing_keys(fs_info, &preftrees); if (ret) goto out; - __merge_refs(&prefs, MERGE_IDENTICAL_KEYS); + WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root)); - ret = __resolve_indirect_refs(fs_info, path, time_seq, &prefs, - extent_item_pos, total_refs, - root_objectid); + ret = resolve_indirect_refs(fs_info, path, time_seq, &preftrees, + extent_item_pos, total_refs, sc); if (ret) goto out; - __merge_refs(&prefs, MERGE_IDENTICAL_PARENTS); + WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect.root)); - while (!list_empty(&prefs)) { - ref = list_first_entry(&prefs, struct __prelim_ref, list); + /* + * This walks the tree of merged and resolved refs. Tree blocks are + * read in as needed. Unique entries are added to the ulist, and + * the list of found roots is updated. + * + * We release the entire tree in one go before returning. + */ + node = rb_first(&preftrees.direct.root); + while (node) { + ref = rb_entry(node, struct prelim_ref, rbnode); + node = rb_next(&ref->rbnode); WARN_ON(ref->count < 0); if (roots && ref->count && ref->root_id && ref->parent == 0) { - if (root_objectid && ref->root_id != root_objectid) { + if (sc && sc->root_objectid && + ref->root_id != sc->root_objectid) { ret = BACKREF_FOUND_SHARED; goto out; } @@ -1442,24 +1306,16 @@ again: } eie = NULL; } - list_del(&ref->list); - kmem_cache_free(btrfs_prelim_ref_cache, ref); + cond_resched(); } out: btrfs_free_path(path); - ref_root_free(ref_tree); - while (!list_empty(&prefs)) { - ref = list_first_entry(&prefs, struct __prelim_ref, list); - list_del(&ref->list); - kmem_cache_free(btrfs_prelim_ref_cache, ref); - } - while (!list_empty(&prefs_delayed)) { - ref = list_first_entry(&prefs_delayed, struct __prelim_ref, - list); - list_del(&ref->list); - kmem_cache_free(btrfs_prelim_ref_cache, ref); - } + + prelim_release(&preftrees.direct); + prelim_release(&preftrees.indirect); + prelim_release(&preftrees.indirect_missing_keys); + if (ret < 0) free_inode_elem_list(eie); return ret; @@ -1475,7 +1331,7 @@ static void free_leaf_list(struct ulist *blocks) while ((node = ulist_next(blocks, &uiter))) { if (!node->aux) continue; - eie = (struct extent_inode_elem *)(uintptr_t)node->aux; + eie = unode_aux_to_inode_list(node); free_inode_elem_list(eie); node->aux = 0; } @@ -1503,7 +1359,7 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, return -ENOMEM; ret = find_parent_nodes(trans, fs_info, bytenr, time_seq, - *leafs, NULL, extent_item_pos, 0, 0, 0); + *leafs, NULL, extent_item_pos, NULL); if (ret < 0 && ret != -ENOENT) { free_leaf_list(*leafs); return ret; @@ -1525,9 +1381,9 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, * * returns 0 on success, < 0 on error. */ -static int __btrfs_find_all_roots(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, - u64 time_seq, struct ulist **roots) +static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, + u64 time_seq, struct ulist **roots) { struct ulist *tmp; struct ulist_node *node = NULL; @@ -1546,7 +1402,7 @@ static int __btrfs_find_all_roots(struct btrfs_trans_handle *trans, ULIST_ITER_INIT(&uiter); while (1) { ret = find_parent_nodes(trans, fs_info, bytenr, time_seq, - tmp, *roots, NULL, 0, 0, 0); + tmp, *roots, NULL, NULL); if (ret < 0 && ret != -ENOENT) { ulist_free(tmp); ulist_free(*roots); @@ -1571,7 +1427,8 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, if (!trans) down_read(&fs_info->commit_root_sem); - ret = __btrfs_find_all_roots(trans, fs_info, bytenr, time_seq, roots); + ret = btrfs_find_all_roots_safe(trans, fs_info, bytenr, + time_seq, roots); if (!trans) up_read(&fs_info->commit_root_sem); return ret; @@ -1580,26 +1437,32 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, /** * btrfs_check_shared - tell us whether an extent is shared * - * @trans: optional trans handle - * * btrfs_check_shared uses the backref walking code but will short * circuit as soon as it finds a root or inode that doesn't match the * one passed in. This provides a significant performance benefit for * callers (such as fiemap) which want to know whether the extent is * shared but do not need a ref count. * + * This attempts to allocate a transaction in order to account for + * delayed refs, but continues on even when the alloc fails. + * * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error. */ -int btrfs_check_shared(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 root_objectid, - u64 inum, u64 bytenr) +int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr) { + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_trans_handle *trans; struct ulist *tmp = NULL; struct ulist *roots = NULL; struct ulist_iterator uiter; struct ulist_node *node; struct seq_list elem = SEQ_LIST_INIT(elem); int ret = 0; + struct share_check shared = { + .root_objectid = root->objectid, + .inum = inum, + .share_count = 0, + }; tmp = ulist_alloc(GFP_NOFS); roots = ulist_alloc(GFP_NOFS); @@ -1609,14 +1472,18 @@ int btrfs_check_shared(struct btrfs_trans_handle *trans, return -ENOMEM; } - if (trans) - btrfs_get_tree_mod_seq(fs_info, &elem); - else + trans = btrfs_join_transaction(root); + if (IS_ERR(trans)) { + trans = NULL; down_read(&fs_info->commit_root_sem); + } else { + btrfs_get_tree_mod_seq(fs_info, &elem); + } + ULIST_ITER_INIT(&uiter); while (1) { ret = find_parent_nodes(trans, fs_info, bytenr, elem.seq, tmp, - roots, NULL, root_objectid, inum, 1); + roots, NULL, &shared); if (ret == BACKREF_FOUND_SHARED) { /* this is the only condition under which we return 1 */ ret = 1; @@ -1631,10 +1498,13 @@ int btrfs_check_shared(struct btrfs_trans_handle *trans, bytenr = node->val; cond_resched(); } - if (trans) + + if (trans) { btrfs_put_tree_mod_seq(fs_info, &elem); - else + btrfs_end_transaction(trans); + } else { up_read(&fs_info->commit_root_sem); + } ulist_free(tmp); ulist_free(roots); return ret; @@ -1649,7 +1519,7 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid, struct btrfs_key key; struct btrfs_key found_key; struct btrfs_inode_extref *extref; - struct extent_buffer *leaf; + const struct extent_buffer *leaf; unsigned long ptr; key.objectid = inode_objectid; @@ -1806,7 +1676,7 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, u64 flags; u64 size = 0; u32 item_size; - struct extent_buffer *eb; + const struct extent_buffer *eb; struct btrfs_extent_item *ei; struct btrfs_key key; @@ -1870,15 +1740,17 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, * helper function to iterate extent inline refs. ptr must point to a 0 value * for the first call and may be modified. it is used to track state. * if more refs exist, 0 is returned and the next call to - * __get_extent_inline_ref must pass the modified ptr parameter to get the + * get_extent_inline_ref must pass the modified ptr parameter to get the * next ref. after the last ref was processed, 1 is returned. * returns <0 on error */ -static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, - struct btrfs_key *key, - struct btrfs_extent_item *ei, u32 item_size, - struct btrfs_extent_inline_ref **out_eiref, - int *out_type) +static int get_extent_inline_ref(unsigned long *ptr, + const struct extent_buffer *eb, + const struct btrfs_key *key, + const struct btrfs_extent_item *ei, + u32 item_size, + struct btrfs_extent_inline_ref **out_eiref, + int *out_type) { unsigned long end; u64 flags; @@ -1908,7 +1780,10 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, end = (unsigned long)ei + item_size; *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr); - *out_type = btrfs_extent_inline_ref_type(eb, *out_eiref); + *out_type = btrfs_get_extent_inline_ref_type(eb, *out_eiref, + BTRFS_REF_TYPE_ANY); + if (*out_type == BTRFS_REF_TYPE_INVALID) + return -EINVAL; *ptr += btrfs_extent_inline_ref_size(*out_type); WARN_ON(*ptr > end); @@ -1921,7 +1796,7 @@ static int __get_extent_inline_ref(unsigned long *ptr, struct extent_buffer *eb, /* * reads the tree block backref for an extent. tree level and root are returned * through out_level and out_root. ptr must point to a 0 value for the first - * call and may be modified (see __get_extent_inline_ref comment). + * call and may be modified (see get_extent_inline_ref comment). * returns 0 if data was provided, 1 if there was no more data to provide or * <0 on error. */ @@ -1937,7 +1812,7 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, return 1; while (1) { - ret = __get_extent_inline_ref(ptr, eb, key, ei, item_size, + ret = get_extent_inline_ref(ptr, eb, key, ei, item_size, &eiref, &type); if (ret < 0) return ret; @@ -2034,8 +1909,8 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, ULIST_ITER_INIT(&ref_uiter); while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) { - ret = __btrfs_find_all_roots(trans, fs_info, ref_node->val, - tree_mod_seq_elem.seq, &roots); + ret = btrfs_find_all_roots_safe(trans, fs_info, ref_node->val, + tree_mod_seq_elem.seq, &roots); if (ret) break; ULIST_ITER_INIT(&root_uiter); @@ -2305,7 +2180,7 @@ struct btrfs_data_container *init_data_container(u32 total_bytes) size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); - data = vmalloc(alloc_bytes); + data = kvmalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); @@ -2339,9 +2214,9 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, if (IS_ERR(fspath)) return (void *)fspath; - ifp = kmalloc(sizeof(*ifp), GFP_NOFS); + ifp = kmalloc(sizeof(*ifp), GFP_KERNEL); if (!ifp) { - vfree(fspath); + kvfree(fspath); return ERR_PTR(-ENOMEM); } @@ -2356,6 +2231,6 @@ void free_ipath(struct inode_fs_paths *ipath) { if (!ipath) return; - vfree(ipath->fspath); + kvfree(ipath->fspath); kfree(ipath); } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 9c41fbac3009..e410335841aa 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -68,10 +68,20 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid, u64 start_off, struct btrfs_path *path, struct btrfs_inode_extref **ret_extref, u64 *found_off); -int btrfs_check_shared(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 root_objectid, - u64 inum, u64 bytenr); +int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr); int __init btrfs_prelim_ref_init(void); void btrfs_prelim_ref_exit(void); + +struct prelim_ref { + struct rb_node rbnode; + u64 root_id; + struct btrfs_key key_for_search; + int level; + int count; + struct extent_inode_elem *inode_list; + u64 parent; + u64 wanted_disk_byte; +}; + #endif diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index b8622e4d1744..eccadb5f62a5 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -179,9 +179,14 @@ struct btrfs_inode { unsigned reserved_extents; /* - * always compress this one file + * Cached values of inode properties */ - unsigned force_compress; + unsigned prop_compress; /* per-file compression algorithm */ + /* + * Force compression on the file using the defrag ioctl, could be + * different from prop_compress and takes precedence if set + */ + unsigned defrag_compress; struct btrfs_delayed_node *delayed_node; @@ -207,7 +212,7 @@ struct btrfs_inode { extern unsigned char btrfs_filetype_table[]; -static inline struct btrfs_inode *BTRFS_I(struct inode *inode) +static inline struct btrfs_inode *BTRFS_I(const struct inode *inode) { return container_of(inode, struct btrfs_inode, vfs_inode); } @@ -231,7 +236,7 @@ static inline void btrfs_insert_inode_hash(struct inode *inode) __insert_inode_hash(inode, h); } -static inline u64 btrfs_ino(struct btrfs_inode *inode) +static inline u64 btrfs_ino(const struct btrfs_inode *inode) { u64 ino = inode->location.objectid; @@ -310,7 +315,8 @@ struct btrfs_dio_private { * The original bio may be split to several sub-bios, this is * done during endio of sub-bios */ - int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int); + blk_status_t (*subio_endio)(struct inode *, struct btrfs_io_bio *, + blk_status_t); }; /* diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index ab14c2e635ca..7d5a9b51f0d7 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -94,7 +94,7 @@ #include <linux/mutex.h> #include <linux/genhd.h> #include <linux/blkdev.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/string.h> #include "ctree.h" #include "disk-io.h" @@ -296,8 +296,7 @@ static void btrfsic_dev_state_hashtable_add( struct btrfsic_dev_state *ds, struct btrfsic_dev_state_hashtable *h); static void btrfsic_dev_state_hashtable_remove(struct btrfsic_dev_state *ds); -static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup( - struct block_device *bdev, +static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(dev_t dev, struct btrfsic_dev_state_hashtable *h); static struct btrfsic_stack_frame *btrfsic_stack_frame_alloc(void); static void btrfsic_stack_frame_free(struct btrfsic_stack_frame *sf); @@ -385,8 +384,7 @@ static int btrfsic_process_superblock_dev_mirror( int superblock_mirror_num, struct btrfsic_dev_state **selected_dev_state, struct btrfs_super_block *selected_super); -static struct btrfsic_dev_state *btrfsic_dev_state_lookup( - struct block_device *bdev); +static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev); static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, u64 bytenr, struct btrfsic_dev_state *dev_state, @@ -626,17 +624,15 @@ static void btrfsic_dev_state_hashtable_remove(struct btrfsic_dev_state *ds) list_del(&ds->collision_resolving_node); } -static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup( - struct block_device *bdev, +static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(dev_t dev, struct btrfsic_dev_state_hashtable *h) { const unsigned int hashval = - (((unsigned int)((uintptr_t)bdev)) & - (BTRFSIC_DEV2STATE_HASHTABLE_SIZE - 1)); + dev & (BTRFSIC_DEV2STATE_HASHTABLE_SIZE - 1); struct btrfsic_dev_state *ds; list_for_each_entry(ds, h->table + hashval, collision_resolving_node) { - if (ds->bdev == bdev) + if (ds->bdev->bd_dev == dev) return ds; } @@ -668,7 +664,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, if (!device->bdev || !device->name) continue; - dev_state = btrfsic_dev_state_lookup(device->bdev); + dev_state = btrfsic_dev_state_lookup(device->bdev->bd_dev); BUG_ON(NULL == dev_state); for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { ret = btrfsic_process_superblock_dev_mirror( @@ -795,12 +791,12 @@ static int btrfsic_process_superblock_dev_mirror( dev_bytenr = btrfs_sb_offset(superblock_mirror_num); if (dev_bytenr + BTRFS_SUPER_INFO_SIZE > device->commit_total_bytes) return -1; - bh = __bread(superblock_bdev, dev_bytenr / 4096, + bh = __bread(superblock_bdev, dev_bytenr / BTRFS_BDEV_BLOCKSIZE, BTRFS_SUPER_INFO_SIZE); if (NULL == bh) return -1; super_tmp = (struct btrfs_super_block *) - (bh->b_data + (dev_bytenr & 4095)); + (bh->b_data + (dev_bytenr & (BTRFS_BDEV_BLOCKSIZE - 1))); if (btrfs_super_bytenr(super_tmp) != dev_bytenr || btrfs_super_magic(super_tmp) != BTRFS_MAGIC || @@ -1556,7 +1552,7 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len, } device = multi->stripes[0].dev; - block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev); + block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev->bd_dev); block_ctx_out->dev_bytenr = multi->stripes[0].physical; block_ctx_out->start = bytenr; block_ctx_out->len = len; @@ -1638,13 +1634,8 @@ static int btrfsic_read_block(struct btrfsic_state *state, struct bio *bio; unsigned int j; - bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i); - if (!bio) { - pr_info("btrfsic: bio_alloc() for %u pages failed!\n", - num_pages - i); - return -1; - } - bio->bi_bdev = block_ctx->dev->bdev; + bio = btrfs_io_bio_alloc(num_pages - i); + bio_set_dev(bio, block_ctx->dev->bdev); bio->bi_iter.bi_sector = dev_bytenr >> 9; bio_set_op_attrs(bio, REQ_OP_READ, 0); @@ -1668,14 +1659,8 @@ static int btrfsic_read_block(struct btrfsic_state *state, dev_bytenr += (j - i) * PAGE_SIZE; i = j; } - for (i = 0; i < num_pages; i++) { + for (i = 0; i < num_pages; i++) block_ctx->datav[i] = kmap(block_ctx->pagev[i]); - if (!block_ctx->datav[i]) { - pr_info("btrfsic: kmap() failed (dev %s)!\n", - block_ctx->dev->name); - return -1; - } - } return block_ctx->len; } @@ -1743,7 +1728,7 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state, num_pages = state->metablock_size >> PAGE_SHIFT; h = (struct btrfs_header *)datav[0]; - if (memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE)) + if (memcmp(h->fsid, fs_info->fsid, BTRFS_FSID_SIZE)) return 1; for (i = 0; i < num_pages; i++) { @@ -2129,7 +2114,7 @@ static void btrfsic_bio_end_io(struct bio *bp) /* mutex is not held! This is not save if IO is not yet completed * on umount */ iodone_w_error = 0; - if (bp->bi_error) + if (bp->bi_status) iodone_w_error = 1; BUG_ON(NULL == block); @@ -2143,7 +2128,7 @@ static void btrfsic_bio_end_io(struct bio *bp) if ((dev_state->state->print_mask & BTRFSIC_PRINT_MASK_END_IO_BIO_BH)) pr_info("bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n", - bp->bi_error, + bp->bi_status, btrfsic_get_block_type(dev_state->state, block), block->logical_bytenr, dev_state->name, block->dev_bytenr, block->mirror_num); @@ -2665,7 +2650,7 @@ static struct btrfsic_block *btrfsic_block_lookup_or_add( pr_info("btrfsic: error, kmalloc failed!\n"); return NULL; } - dev_state = btrfsic_dev_state_lookup(block_ctx->dev->bdev); + dev_state = btrfsic_dev_state_lookup(block_ctx->dev->bdev->bd_dev); if (NULL == dev_state) { pr_info("btrfsic: error, lookup dev_state failed!\n"); btrfsic_block_free(block); @@ -2745,10 +2730,9 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, } } -static struct btrfsic_dev_state *btrfsic_dev_state_lookup( - struct block_device *bdev) +static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev) { - return btrfsic_dev_state_hashtable_lookup(bdev, + return btrfsic_dev_state_hashtable_lookup(dev, &btrfsic_dev_state_hashtable); } @@ -2762,14 +2746,14 @@ int btrfsic_submit_bh(int op, int op_flags, struct buffer_head *bh) mutex_lock(&btrfsic_mutex); /* since btrfsic_submit_bh() might also be called before * btrfsic_mount(), this might return NULL */ - dev_state = btrfsic_dev_state_lookup(bh->b_bdev); + dev_state = btrfsic_dev_state_lookup(bh->b_bdev->bd_dev); /* Only called to write the superblock (incl. FLUSH/FUA) */ if (NULL != dev_state && (op == REQ_OP_WRITE) && bh->b_size > 0) { u64 dev_bytenr; - dev_bytenr = 4096 * bh->b_blocknr; + dev_bytenr = BTRFS_BDEV_BLOCKSIZE * bh->b_blocknr; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) pr_info("submit_bh(op=0x%x,0x%x, blocknr=%llu (bytenr %llu), size=%zu, data=%p, bdev=%p)\n", @@ -2819,53 +2803,56 @@ static void __btrfsic_submit_bio(struct bio *bio) mutex_lock(&btrfsic_mutex); /* since btrfsic_submit_bio() is also called before * btrfsic_mount(), this might return NULL */ - dev_state = btrfsic_dev_state_lookup(bio->bi_bdev); + dev_state = btrfsic_dev_state_lookup(bio_dev(bio)); if (NULL != dev_state && (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) { - unsigned int i; + unsigned int i = 0; u64 dev_bytenr; u64 cur_bytenr; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; int bio_is_patched; char **mapped_datav; + unsigned int segs = bio_segments(bio); dev_bytenr = 512 * bio->bi_iter.bi_sector; bio_is_patched = 0; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n", - bio_op(bio), bio->bi_opf, bio->bi_vcnt, + pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_disk=%p)\n", + bio_op(bio), bio->bi_opf, segs, (unsigned long long)bio->bi_iter.bi_sector, - dev_bytenr, bio->bi_bdev); + dev_bytenr, bio->bi_disk); - mapped_datav = kmalloc_array(bio->bi_vcnt, + mapped_datav = kmalloc_array(segs, sizeof(*mapped_datav), GFP_NOFS); if (!mapped_datav) goto leave; cur_bytenr = dev_bytenr; - bio_for_each_segment_all(bvec, bio, i) { - BUG_ON(bvec->bv_len != PAGE_SIZE); - mapped_datav[i] = kmap(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) { + BUG_ON(bvec.bv_len != PAGE_SIZE); + mapped_datav[i] = kmap(bvec.bv_page); + i++; if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE) pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n", - i, cur_bytenr, bvec->bv_len, bvec->bv_offset); - cur_bytenr += bvec->bv_len; + i, cur_bytenr, bvec.bv_len, bvec.bv_offset); + cur_bytenr += bvec.bv_len; } btrfsic_process_written_block(dev_state, dev_bytenr, - mapped_datav, bio->bi_vcnt, + mapped_datav, segs, bio, &bio_is_patched, NULL, bio->bi_opf); - bio_for_each_segment_all(bvec, bio, i) - kunmap(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) + kunmap(bvec.bv_page); kfree(mapped_datav); } else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) { if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) - pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n", - bio_op(bio), bio->bi_opf, bio->bi_bdev); + pr_info("submit_bio(rw=%d,0x%x FLUSH, disk=%p)\n", + bio_op(bio), bio->bi_opf, bio->bi_disk); if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { if ((dev_state->state->print_mask & (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | @@ -2923,13 +2910,10 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info, fs_info->sectorsize, PAGE_SIZE); return -1; } - state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + state = kvzalloc(sizeof(*state), GFP_KERNEL); if (!state) { - state = vzalloc(sizeof(*state)); - if (!state) { - pr_info("btrfs check-integrity: vzalloc() failed!\n"); - return -1; - } + pr_info("btrfs check-integrity: allocation failed!\n"); + return -1; } if (!btrfsic_is_initialized) { @@ -3009,7 +2993,7 @@ void btrfsic_unmount(struct btrfs_fs_devices *fs_devices) continue; ds = btrfsic_dev_state_hashtable_lookup( - device->bdev, + device->bdev->bd_dev, &btrfsic_dev_state_hashtable); if (NULL != ds) { state = ds->state; diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 10e6b282d09d..280384bf34f1 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -32,6 +32,7 @@ #include <linux/writeback.h> #include <linux/bit_spinlock.h> #include <linux/slab.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -42,48 +43,7 @@ #include "extent_io.h" #include "extent_map.h" -struct compressed_bio { - /* number of bios pending for this compressed extent */ - refcount_t pending_bios; - - /* the pages with the compressed data on them */ - struct page **compressed_pages; - - /* inode that owns this data */ - struct inode *inode; - - /* starting offset in the inode for our pages */ - u64 start; - - /* number of bytes in the inode we're working on */ - unsigned long len; - - /* number of bytes on disk */ - unsigned long compressed_len; - - /* the compression algorithm for this bio */ - int compress_type; - - /* number of compressed pages in the array */ - unsigned long nr_pages; - - /* IO errors */ - int errors; - int mirror_num; - - /* for reads, this is the bio we are copying the data into */ - struct bio *orig_bio; - - /* - * the start of a variable length array of checksums only - * used by reads - */ - u32 sums; -}; - -static int btrfs_decompress_bio(int type, struct page **pages_in, - u64 disk_start, struct bio *orig_bio, - size_t srclen); +static int btrfs_decompress_bio(struct compressed_bio *cb); static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, unsigned long disk_size) @@ -94,12 +54,6 @@ static inline int compressed_bio_size(struct btrfs_fs_info *fs_info, (DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size; } -static struct bio *compressed_bio_alloc(struct block_device *bdev, - u64 first_byte, gfp_t gfp_flags) -{ - return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags); -} - static int check_compressed_csum(struct btrfs_inode *inode, struct compressed_bio *cb, u64 disk_start) @@ -153,9 +107,10 @@ static void end_compressed_bio_read(struct bio *bio) struct inode *inode; struct page *page; unsigned long index; - int ret; + unsigned int mirror = btrfs_io_bio(bio)->mirror_num; + int ret = 0; - if (bio->bi_error) + if (bio->bi_status) cb->errors = 1; /* if there are more bios still pending for this compressed @@ -164,6 +119,21 @@ static void end_compressed_bio_read(struct bio *bio) if (!refcount_dec_and_test(&cb->pending_bios)) goto out; + /* + * Record the correct mirror_num in cb->orig_bio so that + * read-repair can work properly. + */ + ASSERT(btrfs_io_bio(cb->orig_bio)); + btrfs_io_bio(cb->orig_bio)->mirror_num = mirror; + cb->mirror_num = mirror; + + /* + * Some IO in this cb have failed, just skip checksum as there + * is no way it could be correct. + */ + if (cb->errors == 1) + goto csum_failed; + inode = cb->inode; ret = check_compressed_csum(BTRFS_I(inode), cb, (u64)bio->bi_iter.bi_sector << 9); @@ -173,11 +143,8 @@ static void end_compressed_bio_read(struct bio *bio) /* ok, we're the last bio for this extent, lets start * the decompression. */ - ret = btrfs_decompress_bio(cb->compress_type, - cb->compressed_pages, - cb->start, - cb->orig_bio, - cb->compressed_len); + ret = btrfs_decompress_bio(cb); + csum_failed: if (ret) cb->errors = 1; @@ -201,6 +168,7 @@ csum_failed: * we have verified the checksum already, set page * checked so the end_io handlers know about it */ + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, cb->orig_bio, i) SetPageChecked(bvec->bv_page); @@ -268,7 +236,7 @@ static void end_compressed_bio_write(struct bio *bio) struct page *page; unsigned long index; - if (bio->bi_error) + if (bio->bi_status) cb->errors = 1; /* if there are more bios still pending for this compressed @@ -287,7 +255,7 @@ static void end_compressed_bio_write(struct bio *bio) cb->start, cb->start + cb->len - 1, NULL, - bio->bi_error ? 0 : 1); + bio->bi_status ? 0 : 1); cb->compressed_pages[0]->mapping = NULL; end_compressed_writeback(inode, cb); @@ -320,7 +288,7 @@ out: * This also checksums the file bytes and gets things ready for * the end io hooks. */ -int btrfs_submit_compressed_write(struct inode *inode, u64 start, +blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, @@ -335,13 +303,13 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, struct page *page; u64 first_byte = disk_start; struct block_device *bdev; - int ret; + blk_status_t ret; int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; WARN_ON(start & ((u64)PAGE_SIZE - 1)); cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); if (!cb) - return -ENOMEM; + return BLK_STS_RESOURCE; refcount_set(&cb->pending_bios, 0); cb->errors = 0; cb->inode = inode; @@ -355,11 +323,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, bdev = fs_info->fs_devices->latest_bdev; - bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS); - if (!bio) { - kfree(cb); - return -ENOMEM; - } + bio = btrfs_bio_alloc(bdev, first_byte); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; @@ -368,17 +332,17 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, /* create and submit bios for the compressed pages */ bytes_left = compressed_len; for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { + int submit = 0; + page = compressed_pages[pg_index]; page->mapping = inode->i_mapping; if (bio->bi_iter.bi_size) - ret = io_tree->ops->merge_bio_hook(page, 0, + submit = io_tree->ops->merge_bio_hook(page, 0, PAGE_SIZE, bio, 0); - else - ret = 0; page->mapping = NULL; - if (ret || bio_add_page(bio, page, PAGE_SIZE, 0) < + if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_get(bio); @@ -400,14 +364,13 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, ret = btrfs_map_bio(fs_info, bio, 0, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } bio_put(bio); - bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS); - BUG_ON(!bio); + bio = btrfs_bio_alloc(bdev, first_byte); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; @@ -434,7 +397,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start, ret = btrfs_map_bio(fs_info, bio, 0, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } @@ -569,7 +532,7 @@ next: * After the compressed pages are read, we copy the bytes into the * bio we were passed and then call the bio end_io calls */ -int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, +blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -586,7 +549,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, u64 em_len; u64 em_start; struct extent_map *em; - int ret = -ENOMEM; + blk_status_t ret = BLK_STS_RESOURCE; int faili = 0; u32 *sums; @@ -600,7 +563,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, PAGE_SIZE); read_unlock(&em_tree->lock); if (!em) - return -EIO; + return BLK_STS_IOERR; compressed_len = em->block_len; cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); @@ -638,7 +601,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, __GFP_HIGHMEM); if (!cb->compressed_pages[pg_index]) { faili = pg_index - 1; - ret = -ENOMEM; + ret = BLK_STS_RESOURCE; goto fail2; } } @@ -650,28 +613,26 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, /* include any pages we added in add_ra-bio_pages */ cb->len = bio->bi_iter.bi_size; - comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS); - if (!comp_bio) - goto fail2; + comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte); bio_set_op_attrs (comp_bio, REQ_OP_READ, 0); comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; refcount_set(&cb->pending_bios, 1); for (pg_index = 0; pg_index < nr_pages; pg_index++) { + int submit = 0; + page = cb->compressed_pages[pg_index]; page->mapping = inode->i_mapping; page->index = em_start >> PAGE_SHIFT; if (comp_bio->bi_iter.bi_size) - ret = tree->ops->merge_bio_hook(page, 0, + submit = tree->ops->merge_bio_hook(page, 0, PAGE_SIZE, comp_bio, 0); - else - ret = 0; page->mapping = NULL; - if (ret || bio_add_page(comp_bio, page, PAGE_SIZE, 0) < + if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_get(comp_bio); @@ -697,15 +658,13 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0); if (ret) { - comp_bio->bi_error = ret; + comp_bio->bi_status = ret; bio_endio(comp_bio); } bio_put(comp_bio); - comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, - GFP_NOFS); - BUG_ON(!comp_bio); + comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte); bio_set_op_attrs(comp_bio, REQ_OP_READ, 0); comp_bio->bi_private = cb; comp_bio->bi_end_io = end_compressed_bio_read; @@ -726,7 +685,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0); if (ret) { - comp_bio->bi_error = ret; + comp_bio->bi_status = ret; bio_endio(comp_bio); } @@ -761,6 +720,7 @@ static struct { static const struct btrfs_compress_op * const btrfs_compress_op[] = { &btrfs_zlib_compress, &btrfs_lzo_compress, + &btrfs_zstd_compress, }; void __init btrfs_init_compress(void) @@ -801,6 +761,7 @@ static struct list_head *find_workspace(int type) struct list_head *workspace; int cpus = num_online_cpus(); int idx = type - 1; + unsigned nofs_flag; struct list_head *idle_ws = &btrfs_comp_ws[idx].idle_ws; spinlock_t *ws_lock = &btrfs_comp_ws[idx].ws_lock; @@ -830,7 +791,15 @@ again: atomic_inc(total_ws); spin_unlock(ws_lock); + /* + * Allocation helpers call vmalloc that can't use GFP_NOFS, so we have + * to turn it off here because we might get called from the restricted + * context of btrfs_compress_bio/btrfs_compress_pages + */ + nofs_flag = memalloc_nofs_save(); workspace = btrfs_compress_op[idx]->alloc_workspace(); + memalloc_nofs_restore(nofs_flag); + if (IS_ERR(workspace)) { atomic_dec(total_ws); wake_up(ws_wait); @@ -873,7 +842,7 @@ static void free_workspace(int type, struct list_head *workspace) int *free_ws = &btrfs_comp_ws[idx].free_ws; spin_lock(ws_lock); - if (*free_ws < num_online_cpus()) { + if (*free_ws <= num_online_cpus()) { list_add(workspace, idle_ws); (*free_ws)++; spin_unlock(ws_lock); @@ -961,19 +930,16 @@ int btrfs_compress_pages(int type, struct address_space *mapping, * be contiguous. They all correspond to the range of bytes covered by * the compressed extent. */ -static int btrfs_decompress_bio(int type, struct page **pages_in, - u64 disk_start, struct bio *orig_bio, - size_t srclen) +static int btrfs_decompress_bio(struct compressed_bio *cb) { struct list_head *workspace; int ret; + int type = cb->compress_type; workspace = find_workspace(type); - - ret = btrfs_compress_op[type-1]->decompress_bio(workspace, pages_in, - disk_start, orig_bio, - srclen); + ret = btrfs_compress_op[type - 1]->decompress_bio(workspace, cb); free_workspace(type, workspace); + return ret; } @@ -1098,3 +1064,36 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start, return 1; } + +/* + * Compression heuristic. + * + * For now is's a naive and optimistic 'return true', we'll extend the logic to + * quickly (compared to direct compression) detect data characteristics + * (compressible/uncompressible) to avoid wasting CPU time on uncompressible + * data. + * + * The following types of analysis can be performed: + * - detect mostly zero data + * - detect data with low "byte set" size (text, etc) + * - detect data with low/high "core byte" set + * + * Return non-zero if the compression should be done, 0 otherwise. + */ +int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end) +{ + u64 index = start >> PAGE_SHIFT; + u64 end_index = end >> PAGE_SHIFT; + struct page *page; + int ret = 1; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + kmap(page); + kunmap(page); + put_page(page); + index++; + } + + return ret; +} diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h index 39ec43ab8df1..d2781ff8f994 100644 --- a/fs/btrfs/compression.h +++ b/fs/btrfs/compression.h @@ -34,6 +34,45 @@ /* Maximum size of data before compression */ #define BTRFS_MAX_UNCOMPRESSED (SZ_128K) +struct compressed_bio { + /* number of bios pending for this compressed extent */ + refcount_t pending_bios; + + /* the pages with the compressed data on them */ + struct page **compressed_pages; + + /* inode that owns this data */ + struct inode *inode; + + /* starting offset in the inode for our pages */ + u64 start; + + /* number of bytes in the inode we're working on */ + unsigned long len; + + /* number of bytes on disk */ + unsigned long compressed_len; + + /* the compression algorithm for this bio */ + int compress_type; + + /* number of compressed pages in the array */ + unsigned long nr_pages; + + /* IO errors */ + int errors; + int mirror_num; + + /* for reads, this is the bio we are copying the data into */ + struct bio *orig_bio; + + /* + * the start of a variable length array of checksums only + * used by reads + */ + u32 sums; +}; + void btrfs_init_compress(void); void btrfs_exit_compress(void); @@ -48,20 +87,20 @@ int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start, unsigned long total_out, u64 disk_start, struct bio *bio); -int btrfs_submit_compressed_write(struct inode *inode, u64 start, +blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start, unsigned long len, u64 disk_start, unsigned long compressed_len, struct page **compressed_pages, unsigned long nr_pages); -int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, +blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, int mirror_num, unsigned long bio_flags); enum btrfs_compression_type { BTRFS_COMPRESS_NONE = 0, BTRFS_COMPRESS_ZLIB = 1, BTRFS_COMPRESS_LZO = 2, - BTRFS_COMPRESS_TYPES = 2, - BTRFS_COMPRESS_LAST = 3, + BTRFS_COMPRESS_ZSTD = 3, + BTRFS_COMPRESS_TYPES = 3, }; struct btrfs_compress_op { @@ -78,10 +117,7 @@ struct btrfs_compress_op { unsigned long *total_out); int (*decompress_bio)(struct list_head *workspace, - struct page **pages_in, - u64 disk_start, - struct bio *orig_bio, - size_t srclen); + struct compressed_bio *cb); int (*decompress)(struct list_head *workspace, unsigned char *data_in, @@ -92,5 +128,8 @@ struct btrfs_compress_op { extern const struct btrfs_compress_op btrfs_zlib_compress; extern const struct btrfs_compress_op btrfs_lzo_compress; +extern const struct btrfs_compress_op btrfs_zstd_compress; + +int btrfs_compress_heuristic(struct inode *inode, u64 start, u64 end); #endif diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index a3a75f1de002..6d49db7d86be 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -19,7 +19,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/rbtree.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -3667,14 +3667,14 @@ static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info, /* make room in the right data area */ data_end = leaf_data_end(fs_info, right); memmove_extent_buffer(right, - btrfs_leaf_data(right) + data_end - push_space, - btrfs_leaf_data(right) + data_end, + BTRFS_LEAF_DATA_OFFSET + data_end - push_space, + BTRFS_LEAF_DATA_OFFSET + data_end, BTRFS_LEAF_DATA_SIZE(fs_info) - data_end); /* copy from the left data area */ - copy_extent_buffer(right, left, btrfs_leaf_data(right) + + copy_extent_buffer(right, left, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, - btrfs_leaf_data(left) + leaf_data_end(fs_info, left), + BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, left), push_space); memmove_extent_buffer(right, btrfs_item_nr_offset(push_items), @@ -3888,9 +3888,9 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, push_space = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_offset_nr(right, push_items - 1); - copy_extent_buffer(left, right, btrfs_leaf_data(left) + + copy_extent_buffer(left, right, BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, left) - push_space, - btrfs_leaf_data(right) + + BTRFS_LEAF_DATA_OFFSET + btrfs_item_offset_nr(right, push_items - 1), push_space); old_left_nritems = btrfs_header_nritems(left); @@ -3917,9 +3917,9 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info, if (push_items < right_nritems) { push_space = btrfs_item_offset_nr(right, push_items - 1) - leaf_data_end(fs_info, right); - memmove_extent_buffer(right, btrfs_leaf_data(right) + + memmove_extent_buffer(right, BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - push_space, - btrfs_leaf_data(right) + + BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, right), push_space); memmove_extent_buffer(right, btrfs_item_nr_offset(0), @@ -4069,8 +4069,8 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans, nritems * sizeof(struct btrfs_item)); copy_extent_buffer(right, l, - btrfs_leaf_data(right) + BTRFS_LEAF_DATA_SIZE(fs_info) - - data_copy_size, btrfs_leaf_data(l) + + BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) - + data_copy_size, BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, l), data_copy_size); rt_data_off = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_end_nr(l, mid); @@ -4607,8 +4607,8 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, /* shift the data */ if (from_end) { - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end + size_diff, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end + size_diff, BTRFS_LEAF_DATA_OFFSET + data_end, old_data_start + new_size - data_end); } else { struct btrfs_disk_key disk_key; @@ -4634,8 +4634,8 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, } } - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end + size_diff, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end + size_diff, BTRFS_LEAF_DATA_OFFSET + data_end, old_data_start - data_end); offset = btrfs_disk_key_offset(&disk_key); @@ -4650,7 +4650,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info, btrfs_mark_buffer_dirty(leaf); if (btrfs_leaf_free_space(fs_info, leaf) < 0) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); BUG(); } } @@ -4679,7 +4679,7 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, data_end = leaf_data_end(fs_info, leaf); if (btrfs_leaf_free_space(fs_info, leaf) < data_size) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); BUG(); } slot = path->slots[0]; @@ -4687,7 +4687,7 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, BUG_ON(slot < 0); if (slot >= nritems) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); btrfs_crit(fs_info, "slot %d too large, nritems %d", slot, nritems); BUG_ON(1); @@ -4707,8 +4707,8 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, } /* shift the data */ - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end - data_size, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end - data_size, BTRFS_LEAF_DATA_OFFSET + data_end, old_data - data_end); data_end = old_data; @@ -4718,7 +4718,7 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path, btrfs_mark_buffer_dirty(leaf); if (btrfs_leaf_free_space(fs_info, leaf) < 0) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); BUG(); } } @@ -4757,7 +4757,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, data_end = leaf_data_end(fs_info, leaf); if (btrfs_leaf_free_space(fs_info, leaf) < total_size) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); btrfs_crit(fs_info, "not enough freespace need %u have %d", total_size, btrfs_leaf_free_space(fs_info, leaf)); BUG(); @@ -4767,7 +4767,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, unsigned int old_data = btrfs_item_end_nr(leaf, slot); if (old_data < data_end) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); btrfs_crit(fs_info, "slot %d old_data %d data_end %d", slot, old_data, data_end); BUG_ON(1); @@ -4790,8 +4790,8 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, (nritems - slot) * sizeof(struct btrfs_item)); /* shift the data */ - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + - data_end - total_data, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + + data_end - total_data, BTRFS_LEAF_DATA_OFFSET + data_end, old_data - data_end); data_end = old_data; } @@ -4811,7 +4811,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path, btrfs_mark_buffer_dirty(leaf); if (btrfs_leaf_free_space(fs_info, leaf) < 0) { - btrfs_print_leaf(fs_info, leaf); + btrfs_print_leaf(leaf); BUG(); } } @@ -4983,9 +4983,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, if (slot + nr != nritems) { int data_end = leaf_data_end(fs_info, leaf); - memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) + + memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET + data_end + dsize, - btrfs_leaf_data(leaf) + data_end, + BTRFS_LEAF_DATA_OFFSET + data_end, last_off - data_end); for (i = slot + nr; i < nritems; i++) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4f8f75d9e839..8fc690384c58 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -48,7 +48,6 @@ struct btrfs_trans_handle; struct btrfs_transaction; struct btrfs_pending_snapshot; extern struct kmem_cache *btrfs_trans_handle_cachep; -extern struct kmem_cache *btrfs_transaction_cachep; extern struct kmem_cache *btrfs_bit_radix_cachep; extern struct kmem_cache *btrfs_path_cachep; extern struct kmem_cache *btrfs_free_space_cachep; @@ -271,6 +270,7 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS | \ BTRFS_FEATURE_INCOMPAT_BIG_METADATA | \ BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \ + BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD | \ BTRFS_FEATURE_INCOMPAT_RAID56 | \ BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ @@ -471,8 +471,8 @@ struct btrfs_block_rsv { /* * free clusters are used to claim free space in relatively large chunks, - * allowing us to do less seeky writes. They are used for all metadata - * allocations and data allocations in ssd mode. + * allowing us to do less seeky writes. They are used for all metadata + * allocations. In ssd_spread mode they are also used for data allocations. */ struct btrfs_free_cluster { spinlock_t lock; @@ -559,7 +559,6 @@ struct btrfs_block_group_cache { u64 bytes_super; u64 flags; u64 cache_generation; - u32 sectorsize; /* * If the free space extent count exceeds this number, convert the block @@ -710,17 +709,20 @@ struct btrfs_delayed_root; #define BTRFS_FS_OPEN 5 #define BTRFS_FS_QUOTA_ENABLED 6 #define BTRFS_FS_QUOTA_ENABLING 7 -#define BTRFS_FS_QUOTA_DISABLING 8 #define BTRFS_FS_UPDATE_UUID_TREE_GEN 9 #define BTRFS_FS_CREATING_FREE_SPACE_TREE 10 #define BTRFS_FS_BTREE_ERR 11 #define BTRFS_FS_LOG1_ERR 12 #define BTRFS_FS_LOG2_ERR 13 +#define BTRFS_FS_QUOTA_OVERRIDE 14 +/* Used to record internally whether fs has been frozen */ +#define BTRFS_FS_FROZEN 15 + /* * Indicate that a whole-filesystem exclusive operation is running * (device replace, resize, device add/delete, balance) */ -#define BTRFS_FS_EXCL_OP 14 +#define BTRFS_FS_EXCL_OP 16 struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; @@ -748,8 +750,7 @@ struct btrfs_fs_info { struct rb_root block_group_cache_tree; /* keep track of unallocated space */ - spinlock_t free_chunk_lock; - u64 free_chunk_space; + atomic64_t free_chunk_space; struct extent_io_tree freed_extents[2]; struct extent_io_tree *pinned_extents; @@ -797,17 +798,7 @@ struct btrfs_fs_info { * so it is also safe. */ u64 max_inline; - /* - * Protected by ->chunk_mutex and sb->s_umount. - * - * The reason that we use two lock to protect it is because only - * remount and mount operations can change it and these two operations - * are under sb->s_umount, but the read side (chunk allocation) can not - * acquire sb->s_umount or the deadlock would happen. So we use two - * locks to protect it. On the write side, we must acquire two locks, - * and on the read side, we just need acquire one of them. - */ - u64 alloc_start; + struct btrfs_transaction *running_transaction; wait_queue_head_t transaction_throttle; wait_queue_head_t transaction_wait; @@ -976,7 +967,7 @@ struct btrfs_fs_info { struct reloc_control *reloc_ctl; - /* data_alloc_cluster is only used in ssd mode */ + /* data_alloc_cluster is only used in ssd_spread mode */ struct btrfs_free_cluster data_alloc_cluster; /* all metadata allocations go through this cluster */ @@ -1080,8 +1071,6 @@ struct btrfs_fs_info { /* next backup root to be overwritten */ int backup_root_index; - int num_tolerated_disk_barrier_failures; - /* device replace state */ struct btrfs_dev_replace dev_replace; @@ -1107,9 +1096,6 @@ struct btrfs_fs_info { */ struct list_head pinned_chunks; - /* Used to record internally whether fs has been frozen */ - int fs_frozen; - /* Cached block sizes */ u32 nodesize; u32 sectorsize; @@ -1272,26 +1258,30 @@ struct btrfs_root { */ int send_in_progress; struct btrfs_subvolume_writers *subv_writers; - atomic_t will_be_snapshoted; + atomic_t will_be_snapshotted; /* For qgroup metadata space reserve */ atomic64_t qgroup_meta_rsv; }; + +struct btrfs_file_private { + struct btrfs_trans_handle *trans; + void *filldir_buf; +}; + static inline u32 btrfs_inode_sectorsize(const struct inode *inode) { return btrfs_sb(inode->i_sb)->sectorsize; } -static inline u32 __BTRFS_LEAF_DATA_SIZE(u32 blocksize) -{ - return blocksize - sizeof(struct btrfs_header); -} - static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info) { - return __BTRFS_LEAF_DATA_SIZE(info->nodesize); + + return info->nodesize - sizeof(struct btrfs_header); } +#define BTRFS_LEAF_DATA_OFFSET offsetof(struct btrfs_leaf, items) + static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info) { return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item); @@ -1447,7 +1437,7 @@ do { \ #define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31) struct btrfs_map_token { - struct extent_buffer *eb; + const struct extent_buffer *eb; char *kaddr; unsigned long offset; }; @@ -1481,18 +1471,19 @@ static inline void btrfs_init_map_token (struct btrfs_map_token *token) sizeof(((type *)0)->member))) #define DECLARE_BTRFS_SETGET_BITS(bits) \ -u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr, \ - unsigned long off, \ - struct btrfs_map_token *token); \ -void btrfs_set_token_##bits(struct extent_buffer *eb, void *ptr, \ +u##bits btrfs_get_token_##bits(const struct extent_buffer *eb, \ + const void *ptr, unsigned long off, \ + struct btrfs_map_token *token); \ +void btrfs_set_token_##bits(struct extent_buffer *eb, const void *ptr, \ unsigned long off, u##bits val, \ struct btrfs_map_token *token); \ -static inline u##bits btrfs_get_##bits(struct extent_buffer *eb, void *ptr, \ +static inline u##bits btrfs_get_##bits(const struct extent_buffer *eb, \ + const void *ptr, \ unsigned long off) \ { \ return btrfs_get_token_##bits(eb, ptr, off, NULL); \ } \ -static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr, \ +static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr,\ unsigned long off, u##bits val) \ { \ btrfs_set_token_##bits(eb, ptr, off, val, NULL); \ @@ -1504,7 +1495,8 @@ DECLARE_BTRFS_SETGET_BITS(32) DECLARE_BTRFS_SETGET_BITS(64) #define BTRFS_SETGET_FUNCS(name, type, member, bits) \ -static inline u##bits btrfs_##name(struct extent_buffer *eb, type *s) \ +static inline u##bits btrfs_##name(const struct extent_buffer *eb, \ + const type *s) \ { \ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \ return btrfs_get_##bits(eb, s, offsetof(type, member)); \ @@ -1515,7 +1507,8 @@ static inline void btrfs_set_##name(struct extent_buffer *eb, type *s, \ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \ btrfs_set_##bits(eb, s, offsetof(type, member), val); \ } \ -static inline u##bits btrfs_token_##name(struct extent_buffer *eb, type *s, \ +static inline u##bits btrfs_token_##name(const struct extent_buffer *eb,\ + const type *s, \ struct btrfs_map_token *token) \ { \ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \ @@ -1530,9 +1523,9 @@ static inline void btrfs_set_token_##name(struct extent_buffer *eb, \ } #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \ -static inline u##bits btrfs_##name(struct extent_buffer *eb) \ +static inline u##bits btrfs_##name(const struct extent_buffer *eb) \ { \ - type *p = page_address(eb->pages[0]); \ + const type *p = page_address(eb->pages[0]); \ u##bits res = le##bits##_to_cpu(p->member); \ return res; \ } \ @@ -1544,7 +1537,7 @@ static inline void btrfs_set_##name(struct extent_buffer *eb, \ } #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \ -static inline u##bits btrfs_##name(type *s) \ +static inline u##bits btrfs_##name(const type *s) \ { \ return le##bits##_to_cpu(s->member); \ } \ @@ -1553,8 +1546,27 @@ static inline void btrfs_set_##name(type *s, u##bits val) \ s->member = cpu_to_le##bits(val); \ } + +static inline u64 btrfs_device_total_bytes(struct extent_buffer *eb, + struct btrfs_dev_item *s) +{ + BUILD_BUG_ON(sizeof(u64) != + sizeof(((struct btrfs_dev_item *)0))->total_bytes); + return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item, + total_bytes)); +} +static inline void btrfs_set_device_total_bytes(struct extent_buffer *eb, + struct btrfs_dev_item *s, + u64 val) +{ + BUILD_BUG_ON(sizeof(u64) != + sizeof(((struct btrfs_dev_item *)0))->total_bytes); + WARN_ON(!IS_ALIGNED(val, eb->fs_info->sectorsize)); + btrfs_set_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes), val); +} + + BTRFS_SETGET_FUNCS(device_type, struct btrfs_dev_item, type, 64); -BTRFS_SETGET_FUNCS(device_total_bytes, struct btrfs_dev_item, total_bytes, 64); BTRFS_SETGET_FUNCS(device_bytes_used, struct btrfs_dev_item, bytes_used, 64); BTRFS_SETGET_FUNCS(device_io_align, struct btrfs_dev_item, io_align, 32); BTRFS_SETGET_FUNCS(device_io_width, struct btrfs_dev_item, io_width, 32); @@ -1792,7 +1804,6 @@ static inline u32 btrfs_extent_inline_ref_size(int type) if (type == BTRFS_EXTENT_DATA_REF_KEY) return sizeof(struct btrfs_extent_data_ref) + offsetof(struct btrfs_extent_inline_ref, offset); - BUG(); return 0; } @@ -1850,7 +1861,7 @@ static inline unsigned long btrfs_node_key_ptr_offset(int nr) sizeof(struct btrfs_key_ptr) * nr; } -void btrfs_node_key(struct extent_buffer *eb, +void btrfs_node_key(const struct extent_buffer *eb, struct btrfs_disk_key *disk_key, int nr); static inline void btrfs_set_node_key(struct extent_buffer *eb, @@ -1879,28 +1890,28 @@ static inline struct btrfs_item *btrfs_item_nr(int nr) return (struct btrfs_item *)btrfs_item_nr_offset(nr); } -static inline u32 btrfs_item_end(struct extent_buffer *eb, +static inline u32 btrfs_item_end(const struct extent_buffer *eb, struct btrfs_item *item) { return btrfs_item_offset(eb, item) + btrfs_item_size(eb, item); } -static inline u32 btrfs_item_end_nr(struct extent_buffer *eb, int nr) +static inline u32 btrfs_item_end_nr(const struct extent_buffer *eb, int nr) { return btrfs_item_end(eb, btrfs_item_nr(nr)); } -static inline u32 btrfs_item_offset_nr(struct extent_buffer *eb, int nr) +static inline u32 btrfs_item_offset_nr(const struct extent_buffer *eb, int nr) { return btrfs_item_offset(eb, btrfs_item_nr(nr)); } -static inline u32 btrfs_item_size_nr(struct extent_buffer *eb, int nr) +static inline u32 btrfs_item_size_nr(const struct extent_buffer *eb, int nr) { return btrfs_item_size(eb, btrfs_item_nr(nr)); } -static inline void btrfs_item_key(struct extent_buffer *eb, +static inline void btrfs_item_key(const struct extent_buffer *eb, struct btrfs_disk_key *disk_key, int nr) { struct btrfs_item *item = btrfs_item_nr(nr); @@ -1936,8 +1947,8 @@ BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item, BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item, transid, 64); -static inline void btrfs_dir_item_key(struct extent_buffer *eb, - struct btrfs_dir_item *item, +static inline void btrfs_dir_item_key(const struct extent_buffer *eb, + const struct btrfs_dir_item *item, struct btrfs_disk_key *key) { read_eb_member(eb, item, struct btrfs_dir_item, location, key); @@ -1945,7 +1956,7 @@ static inline void btrfs_dir_item_key(struct extent_buffer *eb, static inline void btrfs_set_dir_item_key(struct extent_buffer *eb, struct btrfs_dir_item *item, - struct btrfs_disk_key *key) + const struct btrfs_disk_key *key) { write_eb_member(eb, item, struct btrfs_dir_item, location, key); } @@ -1957,8 +1968,8 @@ BTRFS_SETGET_FUNCS(free_space_bitmaps, struct btrfs_free_space_header, BTRFS_SETGET_FUNCS(free_space_generation, struct btrfs_free_space_header, generation, 64); -static inline void btrfs_free_space_key(struct extent_buffer *eb, - struct btrfs_free_space_header *h, +static inline void btrfs_free_space_key(const struct extent_buffer *eb, + const struct btrfs_free_space_header *h, struct btrfs_disk_key *key) { read_eb_member(eb, h, struct btrfs_free_space_header, location, key); @@ -1966,7 +1977,7 @@ static inline void btrfs_free_space_key(struct extent_buffer *eb, static inline void btrfs_set_free_space_key(struct extent_buffer *eb, struct btrfs_free_space_header *h, - struct btrfs_disk_key *key) + const struct btrfs_disk_key *key) { write_eb_member(eb, h, struct btrfs_free_space_header, location, key); } @@ -1993,25 +2004,25 @@ static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk, disk->objectid = cpu_to_le64(cpu->objectid); } -static inline void btrfs_node_key_to_cpu(struct extent_buffer *eb, - struct btrfs_key *key, int nr) +static inline void btrfs_node_key_to_cpu(const struct extent_buffer *eb, + struct btrfs_key *key, int nr) { struct btrfs_disk_key disk_key; btrfs_node_key(eb, &disk_key, nr); btrfs_disk_key_to_cpu(key, &disk_key); } -static inline void btrfs_item_key_to_cpu(struct extent_buffer *eb, - struct btrfs_key *key, int nr) +static inline void btrfs_item_key_to_cpu(const struct extent_buffer *eb, + struct btrfs_key *key, int nr) { struct btrfs_disk_key disk_key; btrfs_item_key(eb, &disk_key, nr); btrfs_disk_key_to_cpu(key, &disk_key); } -static inline void btrfs_dir_item_key_to_cpu(struct extent_buffer *eb, - struct btrfs_dir_item *item, - struct btrfs_key *key) +static inline void btrfs_dir_item_key_to_cpu(const struct extent_buffer *eb, + const struct btrfs_dir_item *item, + struct btrfs_key *key) { struct btrfs_disk_key disk_key; btrfs_dir_item_key(eb, item, &disk_key); @@ -2043,7 +2054,7 @@ BTRFS_SETGET_STACK_FUNCS(stack_header_nritems, struct btrfs_header, nritems, 32); BTRFS_SETGET_STACK_FUNCS(stack_header_bytenr, struct btrfs_header, bytenr, 64); -static inline int btrfs_header_flag(struct extent_buffer *eb, u64 flag) +static inline int btrfs_header_flag(const struct extent_buffer *eb, u64 flag) { return (btrfs_header_flags(eb) & flag) == flag; } @@ -2062,7 +2073,7 @@ static inline int btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag) return (flags & flag) == flag; } -static inline int btrfs_header_backref_rev(struct extent_buffer *eb) +static inline int btrfs_header_backref_rev(const struct extent_buffer *eb) { u64 flags = btrfs_header_flags(eb); return flags >> BTRFS_BACKREF_REV_SHIFT; @@ -2082,12 +2093,12 @@ static inline unsigned long btrfs_header_fsid(void) return offsetof(struct btrfs_header, fsid); } -static inline unsigned long btrfs_header_chunk_tree_uuid(struct extent_buffer *eb) +static inline unsigned long btrfs_header_chunk_tree_uuid(const struct extent_buffer *eb) { return offsetof(struct btrfs_header, chunk_tree_uuid); } -static inline int btrfs_is_leaf(struct extent_buffer *eb) +static inline int btrfs_is_leaf(const struct extent_buffer *eb) { return btrfs_header_level(eb) == 0; } @@ -2121,12 +2132,12 @@ BTRFS_SETGET_STACK_FUNCS(root_stransid, struct btrfs_root_item, BTRFS_SETGET_STACK_FUNCS(root_rtransid, struct btrfs_root_item, rtransid, 64); -static inline bool btrfs_root_readonly(struct btrfs_root *root) +static inline bool btrfs_root_readonly(const struct btrfs_root *root) { return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_RDONLY)) != 0; } -static inline bool btrfs_root_dead(struct btrfs_root *root) +static inline bool btrfs_root_dead(const struct btrfs_root *root) { return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0; } @@ -2183,51 +2194,51 @@ BTRFS_SETGET_STACK_FUNCS(backup_num_devices, struct btrfs_root_backup, /* struct btrfs_balance_item */ BTRFS_SETGET_FUNCS(balance_flags, struct btrfs_balance_item, flags, 64); -static inline void btrfs_balance_data(struct extent_buffer *eb, - struct btrfs_balance_item *bi, +static inline void btrfs_balance_data(const struct extent_buffer *eb, + const struct btrfs_balance_item *bi, struct btrfs_disk_balance_args *ba) { read_eb_member(eb, bi, struct btrfs_balance_item, data, ba); } static inline void btrfs_set_balance_data(struct extent_buffer *eb, - struct btrfs_balance_item *bi, - struct btrfs_disk_balance_args *ba) + struct btrfs_balance_item *bi, + const struct btrfs_disk_balance_args *ba) { write_eb_member(eb, bi, struct btrfs_balance_item, data, ba); } -static inline void btrfs_balance_meta(struct extent_buffer *eb, - struct btrfs_balance_item *bi, +static inline void btrfs_balance_meta(const struct extent_buffer *eb, + const struct btrfs_balance_item *bi, struct btrfs_disk_balance_args *ba) { read_eb_member(eb, bi, struct btrfs_balance_item, meta, ba); } static inline void btrfs_set_balance_meta(struct extent_buffer *eb, - struct btrfs_balance_item *bi, - struct btrfs_disk_balance_args *ba) + struct btrfs_balance_item *bi, + const struct btrfs_disk_balance_args *ba) { write_eb_member(eb, bi, struct btrfs_balance_item, meta, ba); } -static inline void btrfs_balance_sys(struct extent_buffer *eb, - struct btrfs_balance_item *bi, +static inline void btrfs_balance_sys(const struct extent_buffer *eb, + const struct btrfs_balance_item *bi, struct btrfs_disk_balance_args *ba) { read_eb_member(eb, bi, struct btrfs_balance_item, sys, ba); } static inline void btrfs_set_balance_sys(struct extent_buffer *eb, - struct btrfs_balance_item *bi, - struct btrfs_disk_balance_args *ba) + struct btrfs_balance_item *bi, + const struct btrfs_disk_balance_args *ba) { write_eb_member(eb, bi, struct btrfs_balance_item, sys, ba); } static inline void btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu, - struct btrfs_disk_balance_args *disk) + const struct btrfs_disk_balance_args *disk) { memset(cpu, 0, sizeof(*cpu)); @@ -2247,7 +2258,7 @@ btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu, static inline void btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk, - struct btrfs_balance_args *cpu) + const struct btrfs_balance_args *cpu) { memset(disk, 0, sizeof(*disk)); @@ -2315,7 +2326,7 @@ BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64); BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, uuid_tree_generation, 64); -static inline int btrfs_super_csum_size(struct btrfs_super_block *s) +static inline int btrfs_super_csum_size(const struct btrfs_super_block *s) { u16 t = btrfs_super_csum_type(s); /* @@ -2324,18 +2335,14 @@ static inline int btrfs_super_csum_size(struct btrfs_super_block *s) return btrfs_csum_sizes[t]; } -static inline unsigned long btrfs_leaf_data(struct extent_buffer *l) -{ - return offsetof(struct btrfs_leaf, items); -} /* * The leaf data grows from end-to-front in the node. * this returns the address of the start of the last item, * which is the stop of the leaf data stack */ -static inline unsigned int leaf_data_end(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf) +static inline unsigned int leaf_data_end(const struct btrfs_fs_info *fs_info, + const struct extent_buffer *leaf) { u32 nr = btrfs_header_nritems(leaf); @@ -2360,7 +2367,7 @@ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression, struct btrfs_file_extent_item, compression, 8); static inline unsigned long -btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e) +btrfs_file_extent_inline_start(const struct btrfs_file_extent_item *e) { return (unsigned long)e + BTRFS_FILE_EXTENT_INLINE_DATA_START; } @@ -2394,8 +2401,9 @@ BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item, * size of any extent headers. If a file is compressed on disk, this is * the compressed size */ -static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb, - struct btrfs_item *e) +static inline u32 btrfs_file_extent_inline_item_len( + const struct extent_buffer *eb, + struct btrfs_item *e) { return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START; } @@ -2403,9 +2411,9 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb, /* this returns the number of file bytes represented by the inline item. * If an item is compressed, this is the uncompressed size */ -static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb, - int slot, - struct btrfs_file_extent_item *fi) +static inline u32 btrfs_file_extent_inline_len(const struct extent_buffer *eb, + int slot, + const struct btrfs_file_extent_item *fi) { struct btrfs_map_token token; @@ -2427,8 +2435,8 @@ static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb, /* btrfs_dev_stats_item */ -static inline u64 btrfs_dev_stats_value(struct extent_buffer *eb, - struct btrfs_dev_stats_item *ptr, +static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb, + const struct btrfs_dev_stats_item *ptr, int index) { u64 val; @@ -2538,11 +2546,11 @@ BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cursor_right, /* helper function to cast into the data area of the leaf. */ #define btrfs_item_ptr(leaf, slot, type) \ - ((type *)(btrfs_leaf_data(leaf) + \ + ((type *)(BTRFS_LEAF_DATA_OFFSET + \ btrfs_item_offset_nr(leaf, slot))) #define btrfs_item_ptr_offset(leaf, slot) \ - ((unsigned long)(btrfs_leaf_data(leaf) + \ + ((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \ btrfs_item_offset_nr(leaf, slot))) static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info) @@ -2558,6 +2566,17 @@ static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping) /* extent-tree.c */ +enum btrfs_inline_ref_type { + BTRFS_REF_TYPE_INVALID = 0, + BTRFS_REF_TYPE_BLOCK = 1, + BTRFS_REF_TYPE_DATA = 2, + BTRFS_REF_TYPE_ANY = 3, +}; + +int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, + struct btrfs_extent_inline_ref *iref, + enum btrfs_inline_ref_type is_data); + u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes); static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info, @@ -2667,8 +2686,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info); int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr); int btrfs_make_block_group(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytes_used, - u64 type, u64 chunk_objectid, u64 chunk_offset, - u64 size); + u64 type, u64 chunk_offset, u64 size); struct btrfs_trans_handle *btrfs_start_trans_remove_block_group( struct btrfs_fs_info *fs_info, const u64 chunk_offset); @@ -2680,7 +2698,9 @@ void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache); void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache); void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data); +u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info); +u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info); +u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info); void btrfs_clear_space_info_full(struct btrfs_fs_info *info); enum btrfs_reserve_flush_enum { @@ -2703,9 +2723,13 @@ enum btrfs_flush_state { COMMIT_TRANS = 6, }; -int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len); int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes); -void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len); +int btrfs_check_data_free_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len); +void btrfs_free_reserved_data_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len); +void btrfs_delalloc_release_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len); void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, u64 len); void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, @@ -2722,8 +2746,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes); void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes); -int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len); -void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len); +int btrfs_delalloc_reserve_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len); void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type); struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info, unsigned short type); @@ -2763,8 +2787,8 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info); int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int __get_raid_index(u64 flags); -int btrfs_start_write_no_snapshoting(struct btrfs_root *root); -void btrfs_end_write_no_snapshoting(struct btrfs_root *root); +int btrfs_start_write_no_snapshotting(struct btrfs_root *root); +void btrfs_end_write_no_snapshotting(struct btrfs_root *root); void btrfs_wait_for_snapshot_creation(struct btrfs_root *root); void check_system_chunk(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, const u64 type); @@ -2964,8 +2988,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 root_id, u64 ref_id, u64 dirid, u64 *sequence, const char *name, int name_len); -int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct btrfs_key *key); +int btrfs_del_root(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, const struct btrfs_key *key); int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, const struct btrfs_key *key, struct btrfs_root_item *item); @@ -3031,12 +3055,14 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, const char *name, u16 name_len, int mod); int verify_dir_item(struct btrfs_fs_info *fs_info, - struct extent_buffer *leaf, + struct extent_buffer *leaf, int slot, struct btrfs_dir_item *dir_item); struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info, struct btrfs_path *path, const char *name, int name_len); +bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot, + unsigned long start, u16 name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, @@ -3078,8 +3104,8 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, struct btrfs_dio_private; int btrfs_del_csums(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, u64 len); -int btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst); -int btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst); +blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 logical_offset); int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3094,7 +3120,7 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums); -int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, u64 file_start, int contig); int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, int search_commit); @@ -3124,21 +3150,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, u64 *orig_start, u64 *orig_block_len, u64 *ram_bytes); -/* RHEL and EL kernels have a patch that renames PG_checked to FsMisc */ -#if defined(ClearPageFsMisc) && !defined(ClearPageChecked) -#define ClearPageChecked ClearPageFsMisc -#define SetPageChecked SetPageFsMisc -#define PageChecked PageFsMisc -#endif - -/* This forces readahead on a given range of bytes in an inode */ -static inline void btrfs_force_ra(struct address_space *mapping, - struct file_ra_state *ra, struct file *file, - pgoff_t offset, unsigned long req_size) -{ - page_cache_sync_readahead(mapping, ra, file, offset, req_size); -} - struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry); int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index); int btrfs_unlink_inode(struct btrfs_trans_handle *trans, @@ -3171,6 +3182,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, int btrfs_merge_bio_hook(struct page *page, unsigned long offset, size_t size, struct bio *bio, unsigned long bio_flags); +void btrfs_set_range_writeback(void *private_data, u64 start, u64 end); int btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); @@ -3217,7 +3229,6 @@ long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int btrfs_ioctl_get_supported_features(void __user *arg); void btrfs_update_iflags(struct inode *inode); -void btrfs_inherit_iflags(struct inode *inode, struct inode *dir); int btrfs_is_empty_uuid(u8 *uuid); int btrfs_defrag_file(struct inode *inode, struct file *file, struct btrfs_ioctl_defrag_range_args *range, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 8ae409b5a61d..19e4ad2f3f2e 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1727,6 +1727,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + ctx->pos++; } return 0; } diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index be70d90dfee5..93ffa898df6d 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -470,7 +470,8 @@ add_tail: static noinline void update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_delayed_ref_node *existing, - struct btrfs_delayed_ref_node *update) + struct btrfs_delayed_ref_node *update, + int *old_ref_mod_ret) { struct btrfs_delayed_ref_head *existing_ref; struct btrfs_delayed_ref_head *ref; @@ -523,6 +524,8 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs, * currently, for refs we just added we know we're a-ok. */ old_ref_mod = existing_ref->total_ref_mod; + if (old_ref_mod_ret) + *old_ref_mod_ret = old_ref_mod; existing->ref_mod += update->ref_mod; existing_ref->total_ref_mod += update->ref_mod; @@ -550,7 +553,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_node *ref, struct btrfs_qgroup_extent_record *qrecord, u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved, - int action, int is_data, int *qrecord_inserted_ret) + int action, int is_data, int *qrecord_inserted_ret, + int *old_ref_mod, int *new_ref_mod) { struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; @@ -638,7 +642,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, if (existing) { WARN_ON(ref_root && reserved && existing->qgroup_ref_root && existing->qgroup_reserved); - update_existing_head_ref(delayed_refs, &existing->node, ref); + update_existing_head_ref(delayed_refs, &existing->node, ref, + old_ref_mod); /* * we've updated the existing ref, free the newly * allocated ref @@ -646,6 +651,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref); head_ref = existing; } else { + if (old_ref_mod) + *old_ref_mod = 0; if (is_data && count_mod < 0) delayed_refs->pending_csums += num_bytes; delayed_refs->num_heads++; @@ -655,6 +662,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, } if (qrecord_inserted_ret) *qrecord_inserted_ret = qrecord_inserted; + if (new_ref_mod) + *new_ref_mod = head_ref->total_ref_mod; return head_ref; } @@ -778,7 +787,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op) + struct btrfs_delayed_extent_op *extent_op, + int *old_ref_mod, int *new_ref_mod) { struct btrfs_delayed_tree_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -813,7 +823,8 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, bytenr, num_bytes, 0, 0, action, 0, - &qrecord_inserted); + &qrecord_inserted, old_ref_mod, + new_ref_mod); add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, level, action); @@ -838,7 +849,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action) + u64 owner, u64 offset, u64 reserved, int action, + int *old_ref_mod, int *new_ref_mod) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -878,7 +890,8 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, */ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record, bytenr, num_bytes, ref_root, reserved, - action, 1, &qrecord_inserted); + action, 1, &qrecord_inserted, + old_ref_mod, new_ref_mod); add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, @@ -909,7 +922,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr, num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD, - extent_op->is_data, NULL); + extent_op->is_data, NULL, NULL, NULL); spin_unlock(&delayed_refs->lock); return 0; diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index c0264ff01b53..ce88e4ac5276 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -247,12 +247,14 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op); + struct btrfs_delayed_extent_op *extent_op, + int *old_ref_mod, int *new_ref_mod); int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action); + u64 owner, u64 offset, u64 reserved, int action, + int *old_ref_mod, int *new_ref_mod); int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5fe1ca8abc70..7c655f9a7a50 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -388,7 +388,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, if (ret) btrfs_err(fs_info, "kobj add dev failed %d", ret); - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); /* force writing the updated state information to disk */ trans = btrfs_start_transaction(root, 0); @@ -507,7 +507,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { @@ -639,11 +639,39 @@ static void btrfs_dev_replace_update_device_in_mapping_tree( write_unlock(&em_tree->lock); } +/* + * Read progress of device replace status according to the state and last + * stored position. The value format is the same as for + * btrfs_dev_replace::progress_1000 + */ +static u64 btrfs_dev_replace_progress(struct btrfs_fs_info *fs_info) +{ + struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; + u64 ret = 0; + + switch (dev_replace->replace_state) { + case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: + case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: + ret = 0; + break; + case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: + ret = 1000; + break; + case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: + case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: + ret = div64_u64(dev_replace->cursor_left, + div_u64(btrfs_device_get_total_bytes( + dev_replace->srcdev), 1000)); + break; + } + + return ret; +} + void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; - struct btrfs_device *srcdev; btrfs_dev_replace_lock(dev_replace, 0); /* even if !dev_replace_is_valid, the values are good enough for @@ -656,21 +684,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info, atomic64_read(&dev_replace->num_write_errors); args->status.num_uncorrectable_read_errors = atomic64_read(&dev_replace->num_uncorrectable_read_errors); - switch (dev_replace->replace_state) { - case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: - case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: - args->status.progress_1000 = 0; - break; - case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: - args->status.progress_1000 = 1000; - break; - case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: - case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: - srcdev = dev_replace->srcdev; - args->status.progress_1000 = div64_u64(dev_replace->cursor_left, - div_u64(btrfs_device_get_total_bytes(srcdev), 1000)); - break; - } + args->status.progress_1000 = btrfs_dev_replace_progress(fs_info); btrfs_dev_replace_unlock(dev_replace, 0); } @@ -690,7 +704,7 @@ static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info) u64 result; int ret; - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) return -EROFS; mutex_lock(&dev_replace->lock_finishing_cancel_unmount); @@ -795,25 +809,19 @@ static int btrfs_dev_replace_kthread(void *data) { struct btrfs_fs_info *fs_info = data; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; - struct btrfs_ioctl_dev_replace_args *status_args; u64 progress; - status_args = kzalloc(sizeof(*status_args), GFP_KERNEL); - if (status_args) { - btrfs_dev_replace_status(fs_info, status_args); - progress = status_args->status.progress_1000; - kfree(status_args); - progress = div_u64(progress, 10); - btrfs_info_in_rcu(fs_info, - "continuing dev_replace from %s (devid %llu) to %s @%u%%", - dev_replace->srcdev->missing ? "<missing disk>" : - rcu_str_deref(dev_replace->srcdev->name), - dev_replace->srcdev->devid, - dev_replace->tgtdev ? - rcu_str_deref(dev_replace->tgtdev->name) : - "<missing target disk>", - (unsigned int)progress); - } + progress = btrfs_dev_replace_progress(fs_info); + progress = div_u64(progress, 10); + btrfs_info_in_rcu(fs_info, + "continuing dev_replace from %s (devid %llu) to %s @%u%%", + dev_replace->srcdev->missing ? "<missing disk>" + : rcu_str_deref(dev_replace->srcdev->name), + dev_replace->srcdev->devid, + dev_replace->tgtdev ? rcu_str_deref(dev_replace->tgtdev->name) + : "<missing target disk>", + (unsigned int)progress); + btrfs_dev_replace_continue_on_mount(fs_info); clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags); diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index c24d615e3d7f..41cb9196eaa8 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -395,8 +395,6 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info, leaf = path->nodes[0]; dir_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item); - if (verify_dir_item(fs_info, leaf, dir_item)) - return NULL; total_len = btrfs_item_size_nr(leaf, path->slots[0]); while (cur < total_len) { @@ -405,6 +403,8 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info, btrfs_dir_data_len(leaf, dir_item); name_ptr = (unsigned long)(dir_item + 1); + if (verify_dir_item(fs_info, leaf, path->slots[0], dir_item)) + return NULL; if (btrfs_dir_name_len(leaf, dir_item) == name_len && memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0) return dir_item; @@ -453,9 +453,11 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf, + int slot, struct btrfs_dir_item *dir_item) { u16 namelen = BTRFS_NAME_LEN; + int ret; u8 type = btrfs_dir_type(leaf, dir_item); if (type >= BTRFS_FT_MAX) { @@ -472,6 +474,12 @@ int verify_dir_item(struct btrfs_fs_info *fs_info, return 1; } + namelen = btrfs_dir_name_len(leaf, dir_item); + ret = btrfs_is_name_len_valid(leaf, slot, + (unsigned long)(dir_item + 1), namelen); + if (!ret) + return 1; + /* BTRFS_MAX_XATTR_SIZE is the same for all dir items */ if ((btrfs_dir_data_len(leaf, dir_item) + btrfs_dir_name_len(leaf, dir_item)) > @@ -484,3 +492,67 @@ int verify_dir_item(struct btrfs_fs_info *fs_info, return 0; } + +bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot, + unsigned long start, u16 name_len) +{ + struct btrfs_fs_info *fs_info = leaf->fs_info; + struct btrfs_key key; + u32 read_start; + u32 read_end; + u32 item_start; + u32 item_end; + u32 size; + bool ret = true; + + ASSERT(start > BTRFS_LEAF_DATA_OFFSET); + + read_start = start - BTRFS_LEAF_DATA_OFFSET; + read_end = read_start + name_len; + item_start = btrfs_item_offset_nr(leaf, slot); + item_end = btrfs_item_end_nr(leaf, slot); + + btrfs_item_key_to_cpu(leaf, &key, slot); + + switch (key.type) { + case BTRFS_DIR_ITEM_KEY: + case BTRFS_XATTR_ITEM_KEY: + case BTRFS_DIR_INDEX_KEY: + size = sizeof(struct btrfs_dir_item); + break; + case BTRFS_INODE_REF_KEY: + size = sizeof(struct btrfs_inode_ref); + break; + case BTRFS_INODE_EXTREF_KEY: + size = sizeof(struct btrfs_inode_extref); + break; + case BTRFS_ROOT_REF_KEY: + case BTRFS_ROOT_BACKREF_KEY: + size = sizeof(struct btrfs_root_ref); + break; + default: + ret = false; + goto out; + } + + if (read_start < item_start) { + ret = false; + goto out; + } + if (read_end > item_end) { + ret = false; + goto out; + } + + /* there shall be item(s) before name */ + if (read_start - item_start < size) { + ret = false; + goto out; + } + +out: + if (!ret) + btrfs_crit(fs_info, "invalid dir item name len: %u", + (unsigned int)name_len); + return ret; +} diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5f678dcb20e6..dfdab849037b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -87,9 +87,8 @@ struct btrfs_end_io_wq { bio_end_io_t *end_io; void *private; struct btrfs_fs_info *info; - int error; + blk_status_t status; enum btrfs_wq_endio_type metadata; - struct list_head list; struct btrfs_work work; }; @@ -118,9 +117,9 @@ void btrfs_end_io_wq_exit(void) * just before they are sent down the IO stack. */ struct async_submit_bio { - struct inode *inode; + void *private_data; + struct btrfs_fs_info *fs_info; struct bio *bio; - struct list_head list; extent_submit_bio_hook_t *submit_bio_start; extent_submit_bio_hook_t *submit_bio_done; int mirror_num; @@ -131,7 +130,7 @@ struct async_submit_bio { */ u64 bio_offset; struct btrfs_work work; - int error; + blk_status_t status; }; /* @@ -530,7 +529,7 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) { struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; - u8 fsid[BTRFS_UUID_SIZE]; + u8 fsid[BTRFS_FSID_SIZE]; int ret = 1; read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE); @@ -799,7 +798,7 @@ static void end_workqueue_bio(struct bio *bio) btrfs_work_func_t func; fs_info = end_io_wq->info; - end_io_wq->error = bio->bi_error; + end_io_wq->status = bio->bi_status; if (bio_op(bio) == REQ_OP_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { @@ -836,19 +835,19 @@ static void end_workqueue_bio(struct bio *bio) btrfs_queue_work(wq, &end_io_wq->work); } -int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, +blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata) { struct btrfs_end_io_wq *end_io_wq; end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS); if (!end_io_wq) - return -ENOMEM; + return BLK_STS_RESOURCE; end_io_wq->private = bio->bi_private; end_io_wq->end_io = bio->bi_end_io; end_io_wq->info = info; - end_io_wq->error = 0; + end_io_wq->status = 0; end_io_wq->bio = bio; end_io_wq->metadata = metadata; @@ -868,14 +867,14 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info) static void run_one_async_start(struct btrfs_work *work) { struct async_submit_bio *async; - int ret; + blk_status_t ret; async = container_of(work, struct async_submit_bio, work); - ret = async->submit_bio_start(async->inode, async->bio, + ret = async->submit_bio_start(async->private_data, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); if (ret) - async->error = ret; + async->status = ret; } static void run_one_async_done(struct btrfs_work *work) @@ -885,7 +884,7 @@ static void run_one_async_done(struct btrfs_work *work) int limit; async = container_of(work, struct async_submit_bio, work); - fs_info = BTRFS_I(async->inode)->root->fs_info; + fs_info = async->fs_info; limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; @@ -898,13 +897,13 @@ static void run_one_async_done(struct btrfs_work *work) wake_up(&fs_info->async_submit_wait); /* If an error occurred we just want to clean up the bio and move on */ - if (async->error) { - async->bio->bi_error = async->error; + if (async->status) { + async->bio->bi_status = async->status; bio_endio(async->bio); return; } - async->submit_bio_done(async->inode, async->bio, async->mirror_num, + async->submit_bio_done(async->private_data, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); } @@ -916,20 +915,20 @@ static void run_one_async_free(struct btrfs_work *work) kfree(async); } -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, - struct bio *bio, int mirror_num, - unsigned long bio_flags, - u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done) +blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset, void *private_data, + extent_submit_bio_hook_t *submit_bio_start, + extent_submit_bio_hook_t *submit_bio_done) { struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); if (!async) - return -ENOMEM; + return BLK_STS_RESOURCE; - async->inode = inode; + async->private_data = private_data; + async->fs_info = fs_info; async->bio = bio; async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; @@ -941,7 +940,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, async->bio_flags = bio_flags; async->bio_offset = bio_offset; - async->error = 0; + async->status = 0; atomic_inc(&fs_info->nr_async_submits); @@ -959,12 +958,13 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, return 0; } -static int btree_csum_one_bio(struct bio *bio) +static blk_status_t btree_csum_one_bio(struct bio *bio) { struct bio_vec *bvec; struct btrfs_root *root; int i, ret = 0; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { root = BTRFS_I(bvec->bv_page->mapping->host)->root; ret = csum_dirty_buffer(root->fs_info, bvec->bv_page); @@ -972,12 +972,12 @@ static int btree_csum_one_bio(struct bio *bio) break; } - return ret; + return errno_to_blk_status(ret); } -static int __btree_submit_bio_start(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btree_submit_bio_start(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { /* * when we're called for a write, we're already in the async @@ -986,11 +986,12 @@ static int __btree_submit_bio_start(struct inode *inode, struct bio *bio, return btree_csum_one_bio(bio); } -static int __btree_submit_bio_done(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t __btree_submit_bio_done(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { - int ret; + struct inode *inode = private_data; + blk_status_t ret; /* * when we're called for a write, we're already in the async @@ -998,7 +999,7 @@ static int __btree_submit_bio_done(struct inode *inode, struct bio *bio, */ ret = btrfs_map_bio(btrfs_sb(inode->i_sb), bio, mirror_num, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } return ret; @@ -1015,13 +1016,14 @@ static int check_async_write(unsigned long bio_flags) return 1; } -static int btree_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int async = check_async_write(bio_flags); - int ret; + blk_status_t ret; if (bio_op(bio) != REQ_OP_WRITE) { /* @@ -1043,8 +1045,8 @@ static int btree_submit_bio_hook(struct inode *inode, struct bio *bio, * kthread helpers are used to submit writes so that * checksumming can happen in parallel across all CPUs */ - ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num, 0, - bio_offset, + ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0, + bio_offset, private_data, __btree_submit_bio_start, __btree_submit_bio_done); } @@ -1054,7 +1056,7 @@ static int btree_submit_bio_hook(struct inode *inode, struct bio *bio, return 0; out_w_error: - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); return ret; } @@ -1222,10 +1224,10 @@ int btrfs_write_tree_block(struct extent_buffer *buf) buf->start + buf->len - 1); } -int btrfs_wait_tree_block_writeback(struct extent_buffer *buf) +void btrfs_wait_tree_block_writeback(struct extent_buffer *buf) { - return filemap_fdatawait_range(buf->pages[0]->mapping, - buf->start, buf->start + buf->len - 1); + filemap_fdatawait_range(buf->pages[0]->mapping, + buf->start, buf->start + buf->len - 1); } struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, @@ -1255,9 +1257,9 @@ void clean_tree_block(struct btrfs_fs_info *fs_info, btrfs_assert_tree_locked(buf); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) { - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -buf->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + -buf->len, + fs_info->dirty_metadata_batch); /* ugh, clear_extent_buffer_dirty needs to lock the page */ btrfs_set_lock_blocking(buf); clear_extent_buffer_dirty(buf); @@ -1341,14 +1343,13 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->log_batch, 0); atomic_set(&root->orphan_inodes, 0); refcount_set(&root->refs, 1); - atomic_set(&root->will_be_snapshoted, 0); + atomic_set(&root->will_be_snapshotted, 0); atomic64_set(&root->qgroup_meta_rsv, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; if (!dummy) - extent_io_tree_init(&root->dirty_log_pages, - fs_info->btree_inode->i_mapping); + extent_io_tree_init(&root->dirty_log_pages, NULL); memset(&root->root_key, 0, sizeof(root->root_key)); memset(&root->root_item, 0, sizeof(root->root_item)); @@ -1820,7 +1821,7 @@ static void end_workqueue_fn(struct btrfs_work *work) end_io_wq = container_of(work, struct btrfs_end_io_wq, work); bio = end_io_wq->bio; - bio->bi_error = end_io_wq->error; + bio->bi_status = end_io_wq->status; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); @@ -2309,7 +2310,7 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info) inode->i_mapping->a_ops = &btree_aops; RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node); - extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode->i_mapping); + extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode); BTRFS_I(inode)->io_tree.track_uptodate = 0; extent_map_tree_init(&BTRFS_I(inode)->extent_tree); @@ -2477,7 +2478,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, return ret; } - if (fs_info->sb->s_flags & MS_RDONLY) { + if (sb_rdonly(fs_info->sb)) { ret = btrfs_commit_super(fs_info); if (ret) return ret; @@ -2626,7 +2627,6 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->fs_roots_radix_lock); spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); - spin_lock_init(&fs_info->free_chunk_lock); spin_lock_init(&fs_info->tree_mod_seq_lock); spin_lock_init(&fs_info->super_lock); spin_lock_init(&fs_info->qgroup_op_lock); @@ -2662,12 +2662,11 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic64_set(&fs_info->tree_mod_seq, 0); - fs_info->fs_frozen = 0; fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; - fs_info->free_chunk_space = 0; + atomic64_set(&fs_info->free_chunk_space, 0); fs_info->tree_mod_log = RB_ROOT; fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL; fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */ @@ -2695,8 +2694,8 @@ int open_ctree(struct super_block *sb, btrfs_init_balance(fs_info); btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work); - sb->s_blocksize = 4096; - sb->s_blocksize_bits = blksize_bits(4096); + sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE; + sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE); btrfs_init_btree_inode(fs_info); @@ -2704,10 +2703,8 @@ int open_ctree(struct super_block *sb, fs_info->block_group_cache_tree = RB_ROOT; fs_info->first_logical_byte = (u64)-1; - extent_io_tree_init(&fs_info->freed_extents[0], - fs_info->btree_inode->i_mapping); - extent_io_tree_init(&fs_info->freed_extents[1], - fs_info->btree_inode->i_mapping); + extent_io_tree_init(&fs_info->freed_extents[0], NULL); + extent_io_tree_init(&fs_info->freed_extents[1], NULL); fs_info->pinned_extents = &fs_info->freed_extents[0]; set_bit(BTRFS_FS_BARRIER, &fs_info->flags); @@ -2831,6 +2828,8 @@ int open_ctree(struct super_block *sb, features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; if (fs_info->compress_type == BTRFS_COMPRESS_LZO) features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; + else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD) + features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD; if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA) btrfs_info(fs_info, "has skinny extents"); @@ -2877,7 +2876,7 @@ int open_ctree(struct super_block *sb, features = btrfs_super_compat_ro_flags(disk_super) & ~BTRFS_FEATURE_COMPAT_RO_SUPP; - if (!(sb->s_flags & MS_RDONLY) && features) { + if (!sb_rdonly(sb) && features) { btrfs_err(fs_info, "cannot mount read-write because of unsupported optional features (%llx)", features); @@ -3038,15 +3037,10 @@ retry_root_backup: btrfs_err(fs_info, "failed to read block groups: %d", ret); goto fail_sysfs; } - fs_info->num_tolerated_disk_barrier_failures = - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); - if (fs_info->fs_devices->missing_devices > - fs_info->num_tolerated_disk_barrier_failures && - !(sb->s_flags & MS_RDONLY)) { + + if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info)) { btrfs_warn(fs_info, -"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed", - fs_info->fs_devices->missing_devices, - fs_info->num_tolerated_disk_barrier_failures); + "writeable mount is not allowed due to too many missing devices"); goto fail_sysfs; } @@ -3061,11 +3055,9 @@ retry_root_backup: if (IS_ERR(fs_info->transaction_kthread)) goto fail_cleaner; - if (!btrfs_test_opt(fs_info, SSD) && - !btrfs_test_opt(fs_info, NOSSD) && + if (!btrfs_test_opt(fs_info, NOSSD) && !fs_info->fs_devices->rotating) { - btrfs_info(fs_info, "detected SSD devices, enabling SSD mode"); - btrfs_set_opt(fs_info->mount_opt, SSD); + btrfs_set_and_info(fs_info, SSD, "enabling ssd optimizations"); } /* @@ -3105,7 +3097,7 @@ retry_root_backup: if (ret) goto fail_qgroup; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto fail_qgroup; @@ -3131,7 +3123,7 @@ retry_root_backup: goto fail_qgroup; } - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; if (btrfs_test_opt(fs_info, CLEAR_CACHE) && @@ -3324,7 +3316,7 @@ int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num, if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) return -EINVAL; - bh = __bread(bdev, bytenr / 4096, BTRFS_SUPER_INFO_SIZE); + bh = __bread(bdev, bytenr / BTRFS_BDEV_BLOCKSIZE, BTRFS_SUPER_INFO_SIZE); /* * If we fail to read from the underlying devices, as of now * the best option we have is to mark it EIO. @@ -3381,19 +3373,17 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev) } /* - * this should be called twice, once with wait == 0 and - * once with wait == 1. When wait == 0 is done, all the buffer heads - * we write are pinned. + * Write superblock @sb to the @device. Do not wait for completion, all the + * buffer heads we write are pinned. * - * They are released when wait == 1 is done. - * max_mirrors must be the same for both runs, and it indicates how - * many supers on this one device should be written. + * Write @max_mirrors copies of the superblock, where 0 means default that fit + * the expected device size at commit time. Note that max_mirrors must be + * same for write and wait phases. * - * max_mirrors == 0 means to write them all. + * Return number of errors when buffer head is not found or submission fails. */ static int write_dev_supers(struct btrfs_device *device, - struct btrfs_super_block *sb, - int wait, int max_mirrors) + struct btrfs_super_block *sb, int max_mirrors) { struct buffer_head *bh; int i; @@ -3411,57 +3401,33 @@ static int write_dev_supers(struct btrfs_device *device, device->commit_total_bytes) break; - if (wait) { - bh = __find_get_block(device->bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - if (!bh) { - errors++; - continue; - } - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) - errors++; + btrfs_set_super_bytenr(sb, bytenr); - /* drop our reference */ - brelse(bh); + crc = ~(u32)0; + crc = btrfs_csum_data((const char *)sb + BTRFS_CSUM_SIZE, crc, + BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE); + btrfs_csum_final(crc, sb->csum); - /* drop the reference from the wait == 0 run */ - brelse(bh); + /* One reference for us, and we leave it for the caller */ + bh = __getblk(device->bdev, bytenr / BTRFS_BDEV_BLOCKSIZE, + BTRFS_SUPER_INFO_SIZE); + if (!bh) { + btrfs_err(device->fs_info, + "couldn't get super buffer head for bytenr %llu", + bytenr); + errors++; continue; - } else { - btrfs_set_super_bytenr(sb, bytenr); - - crc = ~(u32)0; - crc = btrfs_csum_data((const char *)sb + - BTRFS_CSUM_SIZE, crc, - BTRFS_SUPER_INFO_SIZE - - BTRFS_CSUM_SIZE); - btrfs_csum_final(crc, sb->csum); - - /* - * one reference for us, and we leave it for the - * caller - */ - bh = __getblk(device->bdev, bytenr / 4096, - BTRFS_SUPER_INFO_SIZE); - if (!bh) { - btrfs_err(device->fs_info, - "couldn't get super buffer head for bytenr %llu", - bytenr); - errors++; - continue; - } + } - memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE); + memcpy(bh->b_data, sb, BTRFS_SUPER_INFO_SIZE); - /* one reference for submit_bh */ - get_bh(bh); + /* one reference for submit_bh */ + get_bh(bh); - set_buffer_uptodate(bh); - lock_buffer(bh); - bh->b_end_io = btrfs_end_buffer_write_sync; - bh->b_private = device; - } + set_buffer_uptodate(bh); + lock_buffer(bh); + bh->b_end_io = btrfs_end_buffer_write_sync; + bh->b_private = device; /* * we fua the first super. The others we allow @@ -3469,9 +3435,10 @@ static int write_dev_supers(struct btrfs_device *device, */ if (i == 0) { ret = btrfsic_submit_bh(REQ_OP_WRITE, - REQ_SYNC | REQ_FUA, bh); + REQ_SYNC | REQ_FUA | REQ_META | REQ_PRIO, bh); } else { - ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh); + ret = btrfsic_submit_bh(REQ_OP_WRITE, + REQ_SYNC | REQ_META | REQ_PRIO, bh); } if (ret) errors++; @@ -3480,71 +3447,101 @@ static int write_dev_supers(struct btrfs_device *device, } /* + * Wait for write completion of superblocks done by write_dev_supers, + * @max_mirrors same for write and wait phases. + * + * Return number of errors when buffer head is not found or not marked up to + * date. + */ +static int wait_dev_supers(struct btrfs_device *device, int max_mirrors) +{ + struct buffer_head *bh; + int i; + int errors = 0; + u64 bytenr; + + if (max_mirrors == 0) + max_mirrors = BTRFS_SUPER_MIRROR_MAX; + + for (i = 0; i < max_mirrors; i++) { + bytenr = btrfs_sb_offset(i); + if (bytenr + BTRFS_SUPER_INFO_SIZE >= + device->commit_total_bytes) + break; + + bh = __find_get_block(device->bdev, + bytenr / BTRFS_BDEV_BLOCKSIZE, + BTRFS_SUPER_INFO_SIZE); + if (!bh) { + errors++; + continue; + } + wait_on_buffer(bh); + if (!buffer_uptodate(bh)) + errors++; + + /* drop our reference */ + brelse(bh); + + /* drop the reference from the writing run */ + brelse(bh); + } + + return errors < i ? 0 : -1; +} + +/* * endio for the write_dev_flush, this will wake anyone waiting * for the barrier when it is done */ static void btrfs_end_empty_barrier(struct bio *bio) { - if (bio->bi_private) - complete(bio->bi_private); - bio_put(bio); + complete(bio->bi_private); } /* - * trigger flushes for one the devices. If you pass wait == 0, the flushes are - * sent down. With wait == 1, it waits for the previous flush. - * - * any device where the flush fails with eopnotsupp are flagged as not-barrier - * capable + * Submit a flush request to the device if it supports it. Error handling is + * done in the waiting counterpart. */ -static int write_dev_flush(struct btrfs_device *device, int wait) +static void write_dev_flush(struct btrfs_device *device) { struct request_queue *q = bdev_get_queue(device->bdev); - struct bio *bio; - int ret = 0; + struct bio *bio = device->flush_bio; if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) - return 0; - - if (wait) { - bio = device->flush_bio; - if (!bio) - return 0; - - wait_for_completion(&device->flush_wait); - - if (bio->bi_error) { - ret = bio->bi_error; - btrfs_dev_stat_inc_and_print(device, - BTRFS_DEV_STAT_FLUSH_ERRS); - } - - /* drop the reference from the wait == 0 run */ - bio_put(bio); - device->flush_bio = NULL; - - return ret; - } - - /* - * one reference for us, and we leave it for the - * caller - */ - device->flush_bio = NULL; - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - return -ENOMEM; + return; + bio_reset(bio); bio->bi_end_io = btrfs_end_empty_barrier; - bio->bi_bdev = device->bdev; + bio_set_dev(bio, device->bdev); bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; - device->flush_bio = bio; - bio_get(bio); btrfsic_submit_bio(bio); + device->flush_bio_sent = 1; +} +/* + * If the flush bio has been submitted by write_dev_flush, wait for it. + */ +static blk_status_t wait_dev_flush(struct btrfs_device *device) +{ + struct bio *bio = device->flush_bio; + + if (!device->flush_bio_sent) + return BLK_STS_OK; + + device->flush_bio_sent = 0; + wait_for_completion_io(&device->flush_wait); + + return bio->bi_status; +} + +static int check_barrier_error(struct btrfs_fs_info *fs_info) +{ + if (!btrfs_check_rw_degradable(fs_info)) + return -EIO; return 0; } @@ -3556,25 +3553,21 @@ static int barrier_all_devices(struct btrfs_fs_info *info) { struct list_head *head; struct btrfs_device *dev; - int errors_send = 0; int errors_wait = 0; - int ret; + blk_status_t ret; /* send down all the barriers */ head = &info->fs_devices->devices; list_for_each_entry_rcu(dev, head, dev_list) { if (dev->missing) continue; - if (!dev->bdev) { - errors_send++; + if (!dev->bdev) continue; - } if (!dev->in_fs_metadata || !dev->writeable) continue; - ret = write_dev_flush(dev, 0); - if (ret) - errors_send++; + write_dev_flush(dev); + dev->last_flush_error = BLK_STS_OK; } /* wait for all the barriers */ @@ -3588,13 +3581,23 @@ static int barrier_all_devices(struct btrfs_fs_info *info) if (!dev->in_fs_metadata || !dev->writeable) continue; - ret = write_dev_flush(dev, 1); - if (ret) + ret = wait_dev_flush(dev); + if (ret) { + dev->last_flush_error = ret; + btrfs_dev_stat_inc_and_print(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); errors_wait++; + } + } + + if (errors_wait) { + /* + * At some point we need the status of all disks + * to arrive at the volume status. So error checking + * is being pushed to a separate loop. + */ + return check_barrier_error(info); } - if (errors_send > info->num_tolerated_disk_barrier_failures || - errors_wait > info->num_tolerated_disk_barrier_failures) - return -EIO; return 0; } @@ -3627,60 +3630,6 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) return min_tolerated; } -int btrfs_calc_num_tolerated_disk_barrier_failures( - struct btrfs_fs_info *fs_info) -{ - struct btrfs_ioctl_space_info space; - struct btrfs_space_info *sinfo; - u64 types[] = {BTRFS_BLOCK_GROUP_DATA, - BTRFS_BLOCK_GROUP_SYSTEM, - BTRFS_BLOCK_GROUP_METADATA, - BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA}; - int i; - int c; - int num_tolerated_disk_barrier_failures = - (int)fs_info->fs_devices->num_devices; - - for (i = 0; i < ARRAY_SIZE(types); i++) { - struct btrfs_space_info *tmp; - - sinfo = NULL; - rcu_read_lock(); - list_for_each_entry_rcu(tmp, &fs_info->space_info, list) { - if (tmp->flags == types[i]) { - sinfo = tmp; - break; - } - } - rcu_read_unlock(); - - if (!sinfo) - continue; - - down_read(&sinfo->groups_sem); - for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { - u64 flags; - - if (list_empty(&sinfo->block_groups[c])) - continue; - - btrfs_get_block_group_info(&sinfo->block_groups[c], - &space); - if (space.total_bytes == 0 || space.used_bytes == 0) - continue; - flags = space.flags; - - num_tolerated_disk_barrier_failures = min( - num_tolerated_disk_barrier_failures, - btrfs_get_num_tolerated_disk_barrier_failures( - flags)); - } - up_read(&sinfo->groups_sem); - } - - return num_tolerated_disk_barrier_failures; -} - int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) { struct list_head *head; @@ -3694,7 +3643,14 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) u64 flags; do_barriers = !btrfs_test_opt(fs_info, NOBARRIER); - backup_super_roots(fs_info); + + /* + * max_mirrors == 0 indicates we're from commit_transaction, + * not from fsync where the tree roots in fs_info have not + * been consistent on disk. + */ + if (max_mirrors == 0) + backup_super_roots(fs_info); sb = fs_info->super_for_commit; dev_item = &sb->dev_item; @@ -3733,12 +3689,12 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) btrfs_set_stack_device_io_width(dev_item, dev->io_width); btrfs_set_stack_device_sector_size(dev_item, dev->sector_size); memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE); - memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_UUID_SIZE); + memcpy(dev_item->fsid, dev->fs_devices->fsid, BTRFS_FSID_SIZE); flags = btrfs_super_flags(sb); btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN); - ret = write_dev_supers(dev, sb, 0, max_mirrors); + ret = write_dev_supers(dev, sb, max_mirrors); if (ret) total_errors++; } @@ -3761,7 +3717,7 @@ int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors) if (!dev->in_fs_metadata || !dev->writeable) continue; - ret = write_dev_supers(dev, sb, 1, max_mirrors); + ret = wait_dev_supers(dev, max_mirrors); if (ret) total_errors++; } @@ -3929,7 +3885,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) cancel_work_sync(&fs_info->async_reclaim_work); - if (!(fs_info->sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(fs_info->sb)) { /* * If the cleaner thread is stopped and there are * block groups queued for removal, the deletion will be @@ -3996,7 +3952,6 @@ void close_ctree(struct btrfs_fs_info *fs_info) __btrfs_free_block_rsv(root->orphan_block_rsv); root->orphan_block_rsv = NULL; - mutex_lock(&fs_info->chunk_mutex); while (!list_empty(&fs_info->pinned_chunks)) { struct extent_map *em; @@ -4005,7 +3960,6 @@ void close_ctree(struct btrfs_fs_info *fs_info) list_del_init(&em->list); free_extent_map(em); } - mutex_unlock(&fs_info->chunk_mutex); } int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, @@ -4049,12 +4003,12 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf) buf->start, transid, fs_info->generation); was_dirty = set_extent_buffer_dirty(buf); if (!was_dirty) - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - buf->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + buf->len, + fs_info->dirty_metadata_batch); #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) { - btrfs_print_leaf(fs_info, buf); + btrfs_print_leaf(buf); ASSERT(0); } #endif @@ -4174,7 +4128,7 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info) ret = -EINVAL; } - if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) { + if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_FSID_SIZE) != 0) { btrfs_err(fs_info, "dev_item UUID does not match fsid: %pU != %pU", fs_info->fsid, sb->dev_item.fsid); @@ -4578,11 +4532,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state =TRANS_STATE_COMPLETED; wake_up(&cur_trans->commit_wait); - - /* - memset(cur_trans, 0, sizeof(*cur_trans)); - kmem_cache_free(btrfs_transaction_cachep, cur_trans); - */ } static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) @@ -4638,6 +4587,12 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info) return 0; } +static struct btrfs_fs_info *btree_fs_info(void *private_data) +{ + struct inode *inode = private_data; + return btrfs_sb(inode->i_sb); +} + static const struct extent_io_ops btree_extent_io_ops = { /* mandatory callbacks */ .submit_bio_hook = btree_submit_bio_hook, @@ -4645,6 +4600,8 @@ static const struct extent_io_ops btree_extent_io_ops = { /* note we're sharing with inode.c for the merge bio hook */ .merge_bio_hook = btrfs_merge_bio_hook, .readpage_io_failed_hook = btree_io_failed_hook, + .set_range_writeback = btrfs_set_range_writeback, + .tree_fs_info = btree_fs_info, /* optional callbacks */ }; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 21f1ceb85b76..7f7c35d6347a 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -25,6 +25,14 @@ #define BTRFS_SUPER_MIRROR_MAX 3 #define BTRFS_SUPER_MIRROR_SHIFT 12 +/* + * Fixed blocksize for all devices, applies to specific ways of reading + * metadata like superblock. Must meet the set_blocksize requirements. + * + * Do not change. + */ +#define BTRFS_BDEV_BLOCKSIZE (4096) + enum btrfs_wq_endio_type { BTRFS_WQ_ENDIO_DATA = 0, BTRFS_WQ_ENDIO_METADATA = 1, @@ -118,16 +126,16 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid); u32 btrfs_csum_data(const char *data, u32 seed, size_t len); void btrfs_csum_final(u32 crc, u8 *result); -int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, +blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode, - struct bio *bio, int mirror_num, - unsigned long bio_flags, u64 bio_offset, +blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset, void *private_data, extent_submit_bio_hook_t *submit_bio_start, extent_submit_bio_hook_t *submit_bio_done); unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info); int btrfs_write_tree_block(struct extent_buffer *buf); -int btrfs_wait_tree_block_writeback(struct extent_buffer *buf); +void btrfs_wait_tree_block_writeback(struct extent_buffer *buf); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, @@ -142,8 +150,6 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); -int btrfs_calc_num_tolerated_disk_barrier_failures( - struct btrfs_fs_info *fs_info); int __init btrfs_end_io_wq_init(void); void btrfs_end_io_wq_exit(void); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 87144c9f9593..fa66980726c9 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -282,6 +282,11 @@ static int btrfs_get_name(struct dentry *parent, char *name, name_len = btrfs_inode_ref_name_len(leaf, iref); } + ret = btrfs_is_name_len_valid(leaf, path->slots[0], name_ptr, name_len); + if (!ret) { + btrfs_free_path(path); + return -EIO; + } read_extent_buffer(leaf, name, name_ptr, name_len); btrfs_free_path(path); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 33d979e9ea2a..e2d7e86b51d1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -97,10 +97,11 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); -static int __reserve_metadata_bytes(struct btrfs_root *root, +static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, - enum btrfs_reserve_flush_enum flush); + enum btrfs_reserve_flush_enum flush, + bool system_chunk); static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes); @@ -766,6 +767,26 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info, return NULL; } +static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes, + u64 owner, u64 root_objectid) +{ + struct btrfs_space_info *space_info; + u64 flags; + + if (owner < BTRFS_FIRST_FREE_OBJECTID) { + if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID) + flags = BTRFS_BLOCK_GROUP_SYSTEM; + else + flags = BTRFS_BLOCK_GROUP_METADATA; + } else { + flags = BTRFS_BLOCK_GROUP_DATA; + } + + space_info = __find_space_info(fs_info, flags); + ASSERT(space_info); + percpu_counter_add(&space_info->total_bytes_pinned, num_bytes); +} + /* * after adding space to the filesystem, we need to clear the full flags * on all the space infos. @@ -1127,6 +1148,64 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans, } #endif +/* + * is_data == BTRFS_REF_TYPE_BLOCK, tree block type is required, + * is_data == BTRFS_REF_TYPE_DATA, data type is requried, + * is_data == BTRFS_REF_TYPE_ANY, either type is OK. + */ +int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb, + struct btrfs_extent_inline_ref *iref, + enum btrfs_inline_ref_type is_data) +{ + int type = btrfs_extent_inline_ref_type(eb, iref); + u64 offset = btrfs_extent_inline_ref_offset(eb, iref); + + if (type == BTRFS_TREE_BLOCK_REF_KEY || + type == BTRFS_SHARED_BLOCK_REF_KEY || + type == BTRFS_SHARED_DATA_REF_KEY || + type == BTRFS_EXTENT_DATA_REF_KEY) { + if (is_data == BTRFS_REF_TYPE_BLOCK) { + if (type == BTRFS_TREE_BLOCK_REF_KEY) + return type; + if (type == BTRFS_SHARED_BLOCK_REF_KEY) { + ASSERT(eb->fs_info); + /* + * Every shared one has parent tree + * block, which must be aligned to + * nodesize. + */ + if (offset && + IS_ALIGNED(offset, eb->fs_info->nodesize)) + return type; + } + } else if (is_data == BTRFS_REF_TYPE_DATA) { + if (type == BTRFS_EXTENT_DATA_REF_KEY) + return type; + if (type == BTRFS_SHARED_DATA_REF_KEY) { + ASSERT(eb->fs_info); + /* + * Every shared one has parent tree + * block, which must be aligned to + * nodesize. + */ + if (offset && + IS_ALIGNED(offset, eb->fs_info->nodesize)) + return type; + } + } else { + ASSERT(is_data == BTRFS_REF_TYPE_ANY); + return type; + } + } + + btrfs_print_leaf((struct extent_buffer *)eb); + btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d", + eb->start, type); + WARN_ON(1); + + return BTRFS_REF_TYPE_INVALID; +} + static u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset) { u32 high_crc = ~(u32)0; @@ -1396,12 +1475,18 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path, struct btrfs_extent_data_ref *ref1; struct btrfs_shared_data_ref *ref2; u32 num_refs = 0; + int type; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (iref) { - if (btrfs_extent_inline_ref_type(leaf, iref) == - BTRFS_EXTENT_DATA_REF_KEY) { + /* + * If type is invalid, we should have bailed out earlier than + * this call. + */ + type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); + ASSERT(type != BTRFS_REF_TYPE_INVALID); + if (type == BTRFS_EXTENT_DATA_REF_KEY) { ref1 = (struct btrfs_extent_data_ref *)(&iref->offset); num_refs = btrfs_extent_data_ref_count(leaf, ref1); } else { @@ -1562,6 +1647,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans, int ret; int err = 0; bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA); + int needed; key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; @@ -1653,6 +1739,11 @@ again: BUG_ON(ptr > end); } + if (owner >= BTRFS_FIRST_FREE_OBJECTID) + needed = BTRFS_REF_TYPE_DATA; + else + needed = BTRFS_REF_TYPE_BLOCK; + err = -ENOENT; while (1) { if (ptr >= end) { @@ -1660,7 +1751,12 @@ again: break; } iref = (struct btrfs_extent_inline_ref *)ptr; - type = btrfs_extent_inline_ref_type(leaf, iref); + type = btrfs_get_extent_inline_ref_type(leaf, iref, needed); + if (type == BTRFS_REF_TYPE_INVALID) { + err = -EINVAL; + goto out; + } + if (want < type) break; if (want > type) { @@ -1852,7 +1948,12 @@ void update_inline_extent_backref(struct btrfs_fs_info *fs_info, if (extent_op) __run_delayed_extent_op(extent_op, leaf, ei); - type = btrfs_extent_inline_ref_type(leaf, iref); + /* + * If type is invalid, we should have bailed out after + * lookup_inline_extent_backref(). + */ + type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_ANY); + ASSERT(type != BTRFS_REF_TYPE_INVALID); if (type == BTRFS_EXTENT_DATA_REF_KEY) { dref = (struct btrfs_extent_data_ref *)(&iref->offset); @@ -2092,6 +2193,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset) { + int old_ref_mod, new_ref_mod; int ret; BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID && @@ -2099,15 +2201,21 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, if (owner < BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL); + num_bytes, parent, + root_objectid, (int)owner, + BTRFS_ADD_DELAYED_REF, NULL, + &old_ref_mod, &new_ref_mod); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, - num_bytes, parent, root_objectid, - owner, offset, 0, - BTRFS_ADD_DELAYED_REF); + num_bytes, parent, + root_objectid, owner, offset, + 0, BTRFS_ADD_DELAYED_REF, + &old_ref_mod, &new_ref_mod); } + + if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) + add_pinned_bytes(fs_info, -num_bytes, owner, root_objectid); + return ret; } @@ -2411,6 +2519,16 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans, head = btrfs_delayed_node_to_head(node); trace_run_delayed_ref_head(fs_info, node, head, node->action); + if (head->total_ref_mod < 0) { + struct btrfs_block_group_cache *cache; + + cache = btrfs_lookup_block_group(fs_info, node->bytenr); + ASSERT(cache); + percpu_counter_add(&cache->space_info->total_bytes_pinned, + -node->num_bytes); + btrfs_put_block_group(cache); + } + if (insert_reserved) { btrfs_pin_extent(fs_info, node->bytenr, node->num_bytes, 1); @@ -3120,6 +3238,7 @@ static noinline int check_committed_ref(struct btrfs_root *root, struct btrfs_extent_item *ei; struct btrfs_key key; u32 item_size; + int type; int ret; key.objectid = bytenr; @@ -3161,8 +3280,9 @@ static noinline int check_committed_ref(struct btrfs_root *root, goto out; iref = (struct btrfs_extent_inline_ref *)(ei + 1); - if (btrfs_extent_inline_ref_type(leaf, iref) != - BTRFS_EXTENT_DATA_REF_KEY) + + type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA); + if (type != BTRFS_EXTENT_DATA_REF_KEY) goto out; ref = (struct btrfs_extent_data_ref *)(&iref->offset); @@ -3364,6 +3484,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group, struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *root = fs_info->tree_root; struct inode *inode = NULL; + struct extent_changeset *data_reserved = NULL; u64 alloc_hint = 0; int dcs = BTRFS_DC_ERROR; u64 num_pages = 0; @@ -3483,7 +3604,7 @@ again: num_pages *= 16; num_pages *= PAGE_SIZE; - ret = btrfs_check_data_free_space(inode, 0, num_pages); + ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages); if (ret) goto out_put; @@ -3514,6 +3635,7 @@ out: block_group->disk_cache_state = dcs; spin_unlock(&block_group->lock); + extent_changeset_free(data_reserved); return ret; } @@ -3924,88 +4046,83 @@ static const char *alloc_name(u64 flags) }; } -static int update_space_info(struct btrfs_fs_info *info, u64 flags, - u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, - struct btrfs_space_info **space_info) +static int create_space_info(struct btrfs_fs_info *info, u64 flags, + struct btrfs_space_info **new) { - struct btrfs_space_info *found; + + struct btrfs_space_info *space_info; int i; - int factor; int ret; - if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID10)) - factor = 2; - else - factor = 1; - - found = __find_space_info(info, flags); - if (found) { - spin_lock(&found->lock); - found->total_bytes += total_bytes; - found->disk_total += total_bytes * factor; - found->bytes_used += bytes_used; - found->disk_used += bytes_used * factor; - found->bytes_readonly += bytes_readonly; - if (total_bytes > 0) - found->full = 0; - space_info_add_new_bytes(info, found, total_bytes - - bytes_used - bytes_readonly); - spin_unlock(&found->lock); - *space_info = found; - return 0; - } - found = kzalloc(sizeof(*found), GFP_NOFS); - if (!found) + space_info = kzalloc(sizeof(*space_info), GFP_NOFS); + if (!space_info) return -ENOMEM; - ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL); + ret = percpu_counter_init(&space_info->total_bytes_pinned, 0, + GFP_KERNEL); if (ret) { - kfree(found); + kfree(space_info); return ret; } for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) - INIT_LIST_HEAD(&found->block_groups[i]); - init_rwsem(&found->groups_sem); - spin_lock_init(&found->lock); - found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; - found->total_bytes = total_bytes; - found->disk_total = total_bytes * factor; - found->bytes_used = bytes_used; - found->disk_used = bytes_used * factor; - found->bytes_pinned = 0; - found->bytes_reserved = 0; - found->bytes_readonly = bytes_readonly; - found->bytes_may_use = 0; - found->full = 0; - found->max_extent_size = 0; - found->force_alloc = CHUNK_ALLOC_NO_FORCE; - found->chunk_alloc = 0; - found->flush = 0; - init_waitqueue_head(&found->wait); - INIT_LIST_HEAD(&found->ro_bgs); - INIT_LIST_HEAD(&found->tickets); - INIT_LIST_HEAD(&found->priority_tickets); - - ret = kobject_init_and_add(&found->kobj, &space_info_ktype, + INIT_LIST_HEAD(&space_info->block_groups[i]); + init_rwsem(&space_info->groups_sem); + spin_lock_init(&space_info->lock); + space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK; + space_info->force_alloc = CHUNK_ALLOC_NO_FORCE; + init_waitqueue_head(&space_info->wait); + INIT_LIST_HEAD(&space_info->ro_bgs); + INIT_LIST_HEAD(&space_info->tickets); + INIT_LIST_HEAD(&space_info->priority_tickets); + + ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype, info->space_info_kobj, "%s", - alloc_name(found->flags)); + alloc_name(space_info->flags)); if (ret) { - percpu_counter_destroy(&found->total_bytes_pinned); - kfree(found); + percpu_counter_destroy(&space_info->total_bytes_pinned); + kfree(space_info); return ret; } - *space_info = found; - list_add_rcu(&found->list, &info->space_info); + *new = space_info; + list_add_rcu(&space_info->list, &info->space_info); if (flags & BTRFS_BLOCK_GROUP_DATA) - info->data_sinfo = found; + info->data_sinfo = space_info; return ret; } +static void update_space_info(struct btrfs_fs_info *info, u64 flags, + u64 total_bytes, u64 bytes_used, + u64 bytes_readonly, + struct btrfs_space_info **space_info) +{ + struct btrfs_space_info *found; + int factor; + + if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID10)) + factor = 2; + else + factor = 1; + + found = __find_space_info(info, flags); + ASSERT(found); + spin_lock(&found->lock); + found->total_bytes += total_bytes; + found->disk_total += total_bytes * factor; + found->bytes_used += bytes_used; + found->disk_used += bytes_used * factor; + found->bytes_readonly += bytes_readonly; + if (total_bytes > 0) + found->full = 0; + space_info_add_new_bytes(info, found, total_bytes - + bytes_used - bytes_readonly); + spin_unlock(&found->lock); + *space_info = found; +} + static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags) { u64 extra_flags = chunk_to_extended(flags) & @@ -4121,7 +4238,7 @@ static u64 get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags) return btrfs_reduce_alloc_profile(fs_info, flags); } -u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) +static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data) { struct btrfs_fs_info *fs_info = root->fs_info; u64 flags; @@ -4138,6 +4255,21 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data) return ret; } +u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info) +{ + return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA); +} + +u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info) +{ + return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA); +} + +u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info) +{ + return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM); +} + static u64 btrfs_space_info_used(struct btrfs_space_info *s_info, bool may_use_included) { @@ -4149,9 +4281,9 @@ static u64 btrfs_space_info_used(struct btrfs_space_info *s_info, int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes) { - struct btrfs_space_info *data_sinfo; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; u64 used; int ret = 0; int need_commit = 2; @@ -4165,10 +4297,6 @@ int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes) ASSERT(current->journal_info); } - data_sinfo = fs_info->data_sinfo; - if (!data_sinfo) - goto alloc; - again: /* make sure we have enough space to handle the data first */ spin_lock(&data_sinfo->lock); @@ -4186,8 +4314,8 @@ again: data_sinfo->force_alloc = CHUNK_ALLOC_FORCE; spin_unlock(&data_sinfo->lock); -alloc: - alloc_target = btrfs_get_alloc_profile(root, 1); + + alloc_target = btrfs_data_alloc_profile(fs_info); /* * It is ugly that we don't call nolock join * transaction for the free space inode case here. @@ -4214,9 +4342,6 @@ alloc: } } - if (!data_sinfo) - data_sinfo = fs_info->data_sinfo; - goto again; } @@ -4238,7 +4363,7 @@ commit_trans: if (need_commit > 0) { btrfs_start_delalloc_roots(fs_info, 0, -1); - btrfs_wait_ordered_roots(fs_info, -1, 0, + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } @@ -4278,12 +4403,8 @@ commit_trans: return ret; } -/* - * New check_data_free_space() with ability for precious data reservation - * Will replace old btrfs_check_data_free_space(), but for patch split, - * add a new function first and then replace it. - */ -int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) +int btrfs_check_data_free_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int ret; @@ -4298,9 +4419,11 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len) return ret; /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ - ret = btrfs_qgroup_reserve_data(inode, start, len); - if (ret) + ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); + if (ret < 0) btrfs_free_reserved_data_space_noquota(inode, start, len); + else + ret = 0; return ret; } @@ -4341,7 +4464,8 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, * This one will handle the per-inode data rsv map for accurate reserved * space framework. */ -void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) +void btrfs_free_reserved_data_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -4351,7 +4475,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len) start = round_down(start, root->fs_info->sectorsize); btrfs_free_reserved_data_space_noquota(inode, start, len); - btrfs_qgroup_free_data(inode, start, len); + btrfs_qgroup_free_data(inode, reserved, start, len); } static void force_metadata_allocation(struct btrfs_fs_info *info) @@ -4376,8 +4500,7 @@ static int should_alloc_chunk(struct btrfs_fs_info *fs_info, struct btrfs_space_info *sinfo, int force) { struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; - u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly; - u64 num_allocated = sinfo->bytes_used + sinfo->bytes_reserved; + u64 bytes_used = btrfs_space_info_used(sinfo, false); u64 thresh; if (force == CHUNK_ALLOC_FORCE) @@ -4389,7 +4512,7 @@ static int should_alloc_chunk(struct btrfs_fs_info *fs_info, * global_rsv, it doesn't change except when the transaction commits. */ if (sinfo->flags & BTRFS_BLOCK_GROUP_METADATA) - num_allocated += calc_global_rsv_need_space(global_rsv); + bytes_used += calc_global_rsv_need_space(global_rsv); /* * in limited mode, we want to have some free space up to @@ -4399,11 +4522,11 @@ static int should_alloc_chunk(struct btrfs_fs_info *fs_info, thresh = btrfs_super_total_bytes(fs_info->super_copy); thresh = max_t(u64, SZ_64M, div_factor_fine(thresh, 1)); - if (num_bytes - num_allocated < thresh) + if (sinfo->total_bytes - bytes_used < thresh) return 1; } - if (num_allocated + SZ_2M < div_factor(num_bytes, 8)) + if (bytes_used + SZ_2M < div_factor(sinfo->total_bytes, 8)) return 0; return 1; } @@ -4463,9 +4586,8 @@ void check_system_chunk(struct btrfs_trans_handle *trans, } if (left < thresh) { - u64 flags; + u64 flags = btrfs_system_alloc_profile(fs_info); - flags = btrfs_get_alloc_profile(fs_info->chunk_root, 0); /* * Ignore failure to create system chunk. We might end up not * needing it, as we might not need to COW all nodes/leafs from @@ -4506,10 +4628,10 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, space_info = __find_space_info(fs_info, flags); if (!space_info) { - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); - BUG_ON(ret); /* -ENOMEM */ + ret = create_space_info(fs_info, flags, &space_info); + if (ret) + return ret; } - BUG_ON(!space_info); /* Logic error */ again: spin_lock(&space_info->lock); @@ -4614,11 +4736,11 @@ out: return ret; } -static int can_overcommit(struct btrfs_root *root, +static int can_overcommit(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 bytes, - enum btrfs_reserve_flush_enum flush) + enum btrfs_reserve_flush_enum flush, + bool system_chunk) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; u64 profile; u64 space_size; @@ -4629,7 +4751,11 @@ static int can_overcommit(struct btrfs_root *root, if (space_info->flags & BTRFS_BLOCK_GROUP_DATA) return 0; - profile = btrfs_get_alloc_profile(root, 0); + if (system_chunk) + profile = btrfs_system_alloc_profile(fs_info); + else + profile = btrfs_metadata_alloc_profile(fs_info); + used = btrfs_space_info_used(space_info, false); /* @@ -4646,9 +4772,7 @@ static int can_overcommit(struct btrfs_root *root, used += space_info->bytes_may_use; - spin_lock(&fs_info->free_chunk_lock); - avail = fs_info->free_chunk_space; - spin_unlock(&fs_info->free_chunk_lock); + avail = atomic64_read(&fs_info->free_chunk_space); /* * If we have dup, raid1 or raid10 then only half of the free @@ -4698,14 +4822,14 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info, } } -static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info, +static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info, u64 to_reclaim) { u64 bytes; - int nr; + u64 nr; bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - nr = (int)div64_u64(to_reclaim, bytes); + nr = div64_u64(to_reclaim, bytes); if (!nr) nr = 1; return nr; @@ -4716,24 +4840,23 @@ static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info, /* * shrink metadata reservation for delalloc */ -static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, - bool wait_ordered) +static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim, + u64 orig, bool wait_ordered) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *block_rsv; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; u64 delalloc_bytes; u64 max_reclaim; + u64 items; long time_left; unsigned long nr_pages; int loops; - int items; enum btrfs_reserve_flush_enum flush; /* Calc the number of the pages we need flush for space reservation */ items = calc_reclaim_items_nr(fs_info, to_reclaim); - to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM; + to_reclaim = items * EXTENT_SIZE_PER_ITEM; trans = (struct btrfs_trans_handle *)current->journal_info; block_rsv = &fs_info->delalloc_block_rsv; @@ -4776,10 +4899,6 @@ skip_async: else flush = BTRFS_RESERVE_NO_FLUSH; spin_lock(&space_info->lock); - if (can_overcommit(root, space_info, orig, flush)) { - spin_unlock(&space_info->lock); - break; - } if (list_empty(&space_info->tickets) && list_empty(&space_info->priority_tickets)) { spin_unlock(&space_info->lock); @@ -4838,7 +4957,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info, spin_lock(&delayed_rsv->lock); if (percpu_counter_compare(&space_info->total_bytes_pinned, - bytes - delayed_rsv->size) >= 0) { + bytes - delayed_rsv->size) < 0) { spin_unlock(&delayed_rsv->lock); return -ENOSPC; } @@ -4859,9 +4978,14 @@ struct reserve_ticket { wait_queue_head_t wait; }; -static int flush_space(struct btrfs_fs_info *fs_info, +/* + * Try to flush some data based on policy set by @state. This is only advisory + * and may fail for various reasons. The caller is supposed to examine the + * state of @space_info to detect the outcome. + */ +static void flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, - u64 orig_bytes, int state) + int state) { struct btrfs_root *root = fs_info->extent_root; struct btrfs_trans_handle *trans; @@ -4886,7 +5010,7 @@ static int flush_space(struct btrfs_fs_info *fs_info, break; case FLUSH_DELALLOC: case FLUSH_DELALLOC_WAIT: - shrink_delalloc(root, num_bytes * 2, orig_bytes, + shrink_delalloc(fs_info, num_bytes * 2, num_bytes, state == FLUSH_DELALLOC_WAIT); break; case ALLOC_CHUNK: @@ -4896,7 +5020,7 @@ static int flush_space(struct btrfs_fs_info *fs_info, break; } ret = do_chunk_alloc(trans, fs_info, - btrfs_get_alloc_profile(root, 0), + btrfs_metadata_alloc_profile(fs_info), CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans); if (ret > 0 || ret == -ENOSPC) @@ -4904,21 +5028,22 @@ static int flush_space(struct btrfs_fs_info *fs_info, break; case COMMIT_TRANS: ret = may_commit_transaction(fs_info, space_info, - orig_bytes, 0); + num_bytes, 0); break; default: ret = -ENOSPC; break; } - trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, - orig_bytes, state, ret); - return ret; + trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state, + ret); + return; } static inline u64 -btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, - struct btrfs_space_info *space_info) +btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, + bool system_chunk) { struct reserve_ticket *ticket; u64 used; @@ -4933,14 +5058,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, return to_reclaim; to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M); - if (can_overcommit(root, space_info, to_reclaim, - BTRFS_RESERVE_FLUSH_ALL)) + if (can_overcommit(fs_info, space_info, to_reclaim, + BTRFS_RESERVE_FLUSH_ALL, system_chunk)) return 0; - used = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - space_info->bytes_may_use; - if (can_overcommit(root, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL)) + used = btrfs_space_info_used(space_info, true); + + if (can_overcommit(fs_info, space_info, SZ_1M, + BTRFS_RESERVE_FLUSH_ALL, system_chunk)) expected = div_factor_fine(space_info->total_bytes, 95); else expected = div_factor_fine(space_info->total_bytes, 90); @@ -4954,17 +5079,18 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root, return to_reclaim; } -static inline int need_do_async_reclaim(struct btrfs_space_info *space_info, - struct btrfs_root *root, u64 used) +static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info, + struct btrfs_space_info *space_info, + u64 used, bool system_chunk) { - struct btrfs_fs_info *fs_info = root->fs_info; u64 thresh = div_factor_fine(space_info->total_bytes, 98); /* If we're just plain full then async reclaim just slows us down. */ if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh) return 0; - if (!btrfs_calc_reclaim_metadata_size(root, space_info)) + if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info, + system_chunk)) return 0; return (used >= thresh && !btrfs_fs_closing(fs_info) && @@ -5001,8 +5127,8 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root, - space_info); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info, + false); if (!to_reclaim) { space_info->flush = 0; spin_unlock(&space_info->lock); @@ -5013,21 +5139,16 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) flush_state = FLUSH_DELAYED_ITEMS_NR; do { - struct reserve_ticket *ticket; - int ret; - - ret = flush_space(fs_info, space_info, to_reclaim, to_reclaim, - flush_state); + flush_space(fs_info, space_info, to_reclaim, flush_state); spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; spin_unlock(&space_info->lock); return; } - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root, - space_info); - ticket = list_first_entry(&space_info->tickets, - struct reserve_ticket, list); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, + space_info, + false); if (last_tickets_id == space_info->tickets_id) { flush_state++; } else { @@ -5063,8 +5184,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, int flush_state = FLUSH_DELAYED_ITEMS_NR; spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root, - space_info); + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info, + false); if (!to_reclaim) { spin_unlock(&space_info->lock); return; @@ -5072,8 +5193,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, spin_unlock(&space_info->lock); do { - flush_space(fs_info, space_info, to_reclaim, to_reclaim, - flush_state); + flush_space(fs_info, space_info, to_reclaim, flush_state); flush_state++; spin_lock(&space_info->lock); if (ticket->bytes == 0) { @@ -5143,12 +5263,12 @@ static int wait_reserve_ticket(struct btrfs_fs_info *fs_info, * regain reservations will be made and this will fail if there is not enough * space already. */ -static int __reserve_metadata_bytes(struct btrfs_root *root, +static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 orig_bytes, - enum btrfs_reserve_flush_enum flush) + enum btrfs_reserve_flush_enum flush, + bool system_chunk) { - struct btrfs_fs_info *fs_info = root->fs_info; struct reserve_ticket ticket; u64 used; int ret = 0; @@ -5170,7 +5290,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, orig_bytes, 1); ret = 0; - } else if (can_overcommit(root, space_info, orig_bytes, flush)) { + } else if (can_overcommit(fs_info, space_info, orig_bytes, flush, + system_chunk)) { space_info->bytes_may_use += orig_bytes; trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, orig_bytes, 1); @@ -5197,7 +5318,7 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, orig_bytes, flush, "enospc"); queue_work(system_unbound_wq, - &root->fs_info->async_reclaim_work); + &fs_info->async_reclaim_work); } } else { list_add_tail(&ticket.list, @@ -5211,7 +5332,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root, * the async reclaim as we will panic. */ if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) && - need_do_async_reclaim(space_info, root, used) && + need_do_async_reclaim(fs_info, space_info, + used, system_chunk) && !work_busy(&fs_info->async_reclaim_work)) { trace_btrfs_trigger_flush(fs_info, space_info->flags, orig_bytes, flush, "preempt"); @@ -5269,9 +5391,10 @@ static int reserve_metadata_bytes(struct btrfs_root *root, struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; int ret; + bool system_chunk = (root == fs_info->chunk_root); - ret = __reserve_metadata_bytes(root, block_rsv->space_info, orig_bytes, - flush); + ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info, + orig_bytes, flush, system_chunk); if (ret == -ENOSPC && unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) { if (block_rsv != global_rsv && @@ -5380,9 +5503,7 @@ static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info, * overcommit, and if we can't then we just need to free up our space * and not satisfy any requests. */ - used = space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - space_info->bytes_may_use; + used = btrfs_space_info_used(space_info, true); if (used - num_bytes >= space_info->total_bytes) check_overcommit = true; again: @@ -5394,8 +5515,7 @@ again: * adding the ticket space would be a double count. */ if (check_overcommit && - !can_overcommit(fs_info->extent_root, space_info, 0, - flush)) + !can_overcommit(fs_info, space_info, 0, flush, false)) break; if (num_bytes >= ticket->bytes) { list_del_init(&ticket->list); @@ -6124,6 +6244,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes) * @inode: inode we're writing to * @start: start range we are writing to * @len: how long the range we are writing to + * @reserved: mandatory parameter, record actually reserved qgroup ranges of + * current reservation. * * This will do the following things * @@ -6141,16 +6263,17 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes) * Return 0 for success * Return <0 for error(-ENOSPC or -EQUOT) */ -int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) +int btrfs_delalloc_reserve_space(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len) { int ret; - ret = btrfs_check_data_free_space(inode, start, len); + ret = btrfs_check_data_free_space(inode, reserved, start, len); if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len); if (ret < 0) - btrfs_free_reserved_data_space(inode, start, len); + btrfs_free_reserved_data_space(inode, *reserved, start, len); return ret; } @@ -6169,10 +6292,11 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len) * list if there are no delalloc bytes left. * Also it will handle the qgroup reserved space. */ -void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len) +void btrfs_delalloc_release_space(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) { btrfs_delalloc_release_metadata(BTRFS_I(inode), len); - btrfs_free_reserved_data_space(inode, start, len); + btrfs_free_reserved_data_space(inode, reserved, start, len); } static int update_block_group(struct btrfs_trans_handle *trans, @@ -6248,6 +6372,8 @@ static int update_block_group(struct btrfs_trans_handle *trans, trace_btrfs_space_reservation(info, "pinned", cache->space_info->flags, num_bytes, 1); + percpu_counter_add(&cache->space_info->total_bytes_pinned, + num_bytes); set_extent_dirty(info->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); @@ -6324,6 +6450,7 @@ static int pin_down_extent(struct btrfs_fs_info *fs_info, trace_btrfs_space_reservation(fs_info, "pinned", cache->space_info->flags, num_bytes, 1); + percpu_counter_add(&cache->space_info->total_bytes_pinned, num_bytes); set_extent_dirty(fs_info->pinned_extents, bytenr, bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL); return 0; @@ -6609,19 +6736,20 @@ fetch_cluster_info(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 *empty_cluster) { struct btrfs_free_cluster *ret = NULL; - bool ssd = btrfs_test_opt(fs_info, SSD); *empty_cluster = 0; if (btrfs_mixed_space_info(space_info)) return ret; - if (ssd) - *empty_cluster = SZ_2M; if (space_info->flags & BTRFS_BLOCK_GROUP_METADATA) { ret = &fs_info->meta_alloc_cluster; - if (!ssd) + if (btrfs_test_opt(fs_info, SSD)) + *empty_cluster = SZ_2M; + else *empty_cluster = SZ_64K; - } else if ((space_info->flags & BTRFS_BLOCK_GROUP_DATA) && ssd) { + } else if ((space_info->flags & BTRFS_BLOCK_GROUP_DATA) && + btrfs_test_opt(fs_info, SSD_SPREAD)) { + *empty_cluster = SZ_2M; ret = &fs_info->data_alloc_cluster; } @@ -6700,7 +6828,7 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, if (!readonly && return_free_space && global_rsv->space_info == space_info) { u64 to_add = len; - WARN_ON(!return_free_space); + spin_lock(&global_rsv->lock); if (!global_rsv->full) { to_add = min(len, global_rsv->size - @@ -6786,7 +6914,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, if (ret) { const char *errstr = btrfs_decode_error(ret); btrfs_warn(fs_info, - "Discard failed while removing blockgroup: errno=%d %s\n", + "discard failed while removing blockgroup: errno=%d %s", ret, errstr); } } @@ -6794,27 +6922,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, return 0; } -static void add_pinned_bytes(struct btrfs_fs_info *fs_info, u64 num_bytes, - u64 owner, u64 root_objectid) -{ - struct btrfs_space_info *space_info; - u64 flags; - - if (owner < BTRFS_FIRST_FREE_OBJECTID) { - if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID) - flags = BTRFS_BLOCK_GROUP_SYSTEM; - else - flags = BTRFS_BLOCK_GROUP_METADATA; - } else { - flags = BTRFS_BLOCK_GROUP_DATA; - } - - space_info = __find_space_info(fs_info, flags); - BUG_ON(!space_info); /* Logic bug */ - percpu_counter_add(&space_info->total_bytes_pinned, num_bytes); -} - - static int __btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *info, struct btrfs_delayed_ref_node *node, u64 parent, @@ -6935,7 +7042,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, "umm, got %d back from search, was looking for %llu", ret, bytenr); if (ret > 0) - btrfs_print_leaf(info, path->nodes[0]); + btrfs_print_leaf(path->nodes[0]); } if (ret < 0) { btrfs_abort_transaction(trans, ret); @@ -6944,7 +7051,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, extent_slot = path->slots[0]; } } else if (WARN_ON(ret == -ENOENT)) { - btrfs_print_leaf(info, path->nodes[0]); + btrfs_print_leaf(path->nodes[0]); btrfs_err(info, "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu", bytenr, parent, root_objectid, owner_objectid, @@ -6981,7 +7088,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_err(info, "umm, got %d back from search, was looking for %llu", ret, bytenr); - btrfs_print_leaf(info, path->nodes[0]); + btrfs_print_leaf(path->nodes[0]); } if (ret < 0) { btrfs_abort_transaction(trans, ret); @@ -7037,8 +7144,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, goto out; } } - add_pinned_bytes(info, -num_bytes, owner_objectid, - root_objectid); } else { if (found_extent) { BUG_ON(is_data && refs_to_drop != @@ -7170,19 +7275,19 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, int ret; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(fs_info, trans, - buf->start, buf->len, - parent, + int old_ref_mod, new_ref_mod; + + ret = btrfs_add_delayed_tree_ref(fs_info, trans, buf->start, + buf->len, parent, root->root_key.objectid, btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL); + BTRFS_DROP_DELAYED_REF, NULL, + &old_ref_mod, &new_ref_mod); BUG_ON(ret); /* -ENOMEM */ + pin = old_ref_mod >= 0 && new_ref_mod < 0; } - if (!last_ref) - return; - - if (btrfs_header_generation(buf) == trans->transid) { + if (last_ref && btrfs_header_generation(buf) == trans->transid) { struct btrfs_block_group_cache *cache; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { @@ -7191,6 +7296,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } + pin = 0; cache = btrfs_lookup_block_group(fs_info, buf->start); if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) { @@ -7206,18 +7312,19 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, btrfs_free_reserved_bytes(cache, buf->len, 0); btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len); - pin = 0; } out: if (pin) add_pinned_bytes(fs_info, buf->len, btrfs_header_level(buf), root->root_key.objectid); - /* - * Deleting the buffer, clear the corrupt flag since it doesn't matter - * anymore. - */ - clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags); + if (last_ref) { + /* + * Deleting the buffer, clear the corrupt flag since it doesn't + * matter anymore. + */ + clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags); + } } /* Can return -ENOMEM */ @@ -7226,12 +7333,12 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset) { + int old_ref_mod, new_ref_mod; int ret; if (btrfs_is_testing(fs_info)) return 0; - add_pinned_bytes(fs_info, num_bytes, owner, root_objectid); /* * tree log blocks never actually go into the extent allocation @@ -7241,19 +7348,25 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, WARN_ON(owner >= BTRFS_FIRST_FREE_OBJECTID); /* unlocks the pinned mutex */ btrfs_pin_extent(fs_info, bytenr, num_bytes, 1); + old_ref_mod = new_ref_mod = 0; ret = 0; } else if (owner < BTRFS_FIRST_FREE_OBJECTID) { ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL); + num_bytes, parent, + root_objectid, (int)owner, + BTRFS_DROP_DELAYED_REF, NULL, + &old_ref_mod, &new_ref_mod); } else { ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, - num_bytes, - parent, root_objectid, owner, - offset, 0, - BTRFS_DROP_DELAYED_REF); + num_bytes, parent, + root_objectid, owner, offset, + 0, BTRFS_DROP_DELAYED_REF, + &old_ref_mod, &new_ref_mod); } + + if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) + add_pinned_bytes(fs_info, num_bytes, owner, root_objectid); + return ret; } @@ -7545,6 +7658,10 @@ search: u64 offset; int cached; + /* If the block group is read-only, we can skip it entirely. */ + if (unlikely(block_group->ro)) + continue; + btrfs_grab_block_group(block_group, delalloc); search_start = block_group->key.objectid; @@ -7580,8 +7697,6 @@ have_block_group: if (unlikely(block_group->cached == BTRFS_CACHE_ERROR)) goto loop; - if (unlikely(block_group->ro)) - goto loop; /* * Ok we want to try and use the cluster allocator, so @@ -7795,6 +7910,7 @@ loop: failed_alloc = false; BUG_ON(index != get_block_group_index(block_group)); btrfs_release_block_group(block_group, delalloc); + cond_resched(); } up_read(&space_info->groups_sem); @@ -7956,7 +8072,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 flags; int ret; - flags = btrfs_get_alloc_profile(root, is_data); + flags = get_alloc_profile_by_root(root, is_data); again: WARN_ON(num_bytes < fs_info->sectorsize); ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size, @@ -8200,9 +8316,9 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID); ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid, - ins->offset, 0, - root_objectid, owner, offset, - ram_bytes, BTRFS_ADD_DELAYED_EXTENT); + ins->offset, 0, root_objectid, owner, + offset, ram_bytes, + BTRFS_ADD_DELAYED_EXTENT, NULL, NULL); return ret; } @@ -8422,11 +8538,11 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, extent_op->is_data = false; extent_op->level = level; - ret = btrfs_add_delayed_tree_ref(fs_info, trans, - ins.objectid, ins.offset, - parent, root_objectid, level, + ret = btrfs_add_delayed_tree_ref(fs_info, trans, ins.objectid, + ins.offset, parent, + root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op); + extent_op, NULL, NULL); if (ret) goto out_free_delayed; } @@ -9150,7 +9266,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, if (err) goto out_end_trans; - ret = btrfs_del_root(trans, tree_root, &root->root_key); + ret = btrfs_del_root(trans, fs_info, &root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); goto out_end_trans; @@ -9909,11 +10025,8 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info, cache->key.offset = size; cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; - cache->sectorsize = fs_info->sectorsize; cache->fs_info = fs_info; - cache->full_stripe_len = btrfs_full_stripe_len(fs_info, - &fs_info->mapping_tree, - start); + cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start); set_free_space_tree_thresholds(cache); atomic_set(&cache->count, 1); @@ -10059,19 +10172,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info) } trace_btrfs_add_block_group(info, cache, 0); - ret = update_space_info(info, cache->flags, found_key.offset, - btrfs_block_group_used(&cache->item), - cache->bytes_super, &space_info); - if (ret) { - btrfs_remove_free_space_cache(cache); - spin_lock(&info->block_group_cache_lock); - rb_erase(&cache->cache_node, - &info->block_group_cache_tree); - RB_CLEAR_NODE(&cache->cache_node); - spin_unlock(&info->block_group_cache_lock); - btrfs_put_block_group(cache); - goto error; - } + update_space_info(info, cache->flags, found_key.offset, + btrfs_block_group_used(&cache->item), + cache->bytes_super, &space_info); cache->space_info = space_info; @@ -10159,8 +10262,7 @@ next: int btrfs_make_block_group(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytes_used, - u64 type, u64 chunk_objectid, u64 chunk_offset, - u64 size) + u64 type, u64 chunk_offset, u64 size) { struct btrfs_block_group_cache *cache; int ret; @@ -10172,7 +10274,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, return -ENOMEM; btrfs_set_block_group_used(&cache->item, bytes_used); - btrfs_set_block_group_chunk_objectid(&cache->item, chunk_objectid); + btrfs_set_block_group_chunk_objectid(&cache->item, + BTRFS_FIRST_CHUNK_TREE_OBJECTID); btrfs_set_block_group_flags(&cache->item, type); cache->flags = type; @@ -10203,16 +10306,19 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, } #endif /* - * Call to ensure the corresponding space_info object is created and - * assigned to our block group, but don't update its counters just yet. - * We want our bg to be added to the rbtree with its ->space_info set. + * Ensure the corresponding space_info object is created and + * assigned to our block group. We want our bg to be added to the rbtree + * with its ->space_info set. */ - ret = update_space_info(fs_info, cache->flags, 0, 0, 0, - &cache->space_info); - if (ret) { - btrfs_remove_free_space_cache(cache); - btrfs_put_block_group(cache); - return ret; + cache->space_info = __find_space_info(fs_info, cache->flags); + if (!cache->space_info) { + ret = create_space_info(fs_info, cache->flags, + &cache->space_info); + if (ret) { + btrfs_remove_free_space_cache(cache); + btrfs_put_block_group(cache); + return ret; + } } ret = btrfs_add_block_group_cache(fs_info, cache); @@ -10227,18 +10333,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, * the rbtree, update the space info's counters. */ trace_btrfs_add_block_group(fs_info, cache, 1); - ret = update_space_info(fs_info, cache->flags, size, bytes_used, + update_space_info(fs_info, cache->flags, size, bytes_used, cache->bytes_super, &cache->space_info); - if (ret) { - btrfs_remove_free_space_cache(cache); - spin_lock(&fs_info->block_group_cache_lock); - rb_erase(&cache->cache_node, - &fs_info->block_group_cache_tree); - RB_CLEAR_NODE(&cache->cache_node); - spin_unlock(&fs_info->block_group_cache_lock); - btrfs_put_block_group(cache); - return ret; - } update_global_block_rsv(fs_info); __link_block_group(cache->space_info, cache); @@ -10786,21 +10882,21 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info) mixed = 1; flags = BTRFS_BLOCK_GROUP_SYSTEM; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); if (ret) goto out; if (mixed) { flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); } else { flags = BTRFS_BLOCK_GROUP_METADATA; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); if (ret) goto out; flags = BTRFS_BLOCK_GROUP_DATA; - ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info); + ret = create_space_info(fs_info, flags, &space_info); } out: return ret; @@ -10975,14 +11071,14 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) } /* - * btrfs_{start,end}_write_no_snapshoting() are similar to + * btrfs_{start,end}_write_no_snapshotting() are similar to * mnt_{want,drop}_write(), they are used to prevent some tasks from writing * data into the page cache through nocow before the subvolume is snapshoted, * but flush the data into disk after the snapshot creation, or to prevent - * operations while snapshoting is ongoing and that cause the snapshot to be + * operations while snapshotting is ongoing and that cause the snapshot to be * inconsistent (writes followed by expanding truncates for example). */ -void btrfs_end_write_no_snapshoting(struct btrfs_root *root) +void btrfs_end_write_no_snapshotting(struct btrfs_root *root) { percpu_counter_dec(&root->subv_writers->counter); /* @@ -10993,9 +11089,9 @@ void btrfs_end_write_no_snapshoting(struct btrfs_root *root) wake_up(&root->subv_writers->wait); } -int btrfs_start_write_no_snapshoting(struct btrfs_root *root) +int btrfs_start_write_no_snapshotting(struct btrfs_root *root) { - if (atomic_read(&root->will_be_snapshoted)) + if (atomic_read(&root->will_be_snapshotted)) return 0; percpu_counter_inc(&root->subv_writers->counter); @@ -11003,14 +11099,14 @@ int btrfs_start_write_no_snapshoting(struct btrfs_root *root) * Make sure counter is updated before we check for snapshot creation. */ smp_mb(); - if (atomic_read(&root->will_be_snapshoted)) { - btrfs_end_write_no_snapshoting(root); + if (atomic_read(&root->will_be_snapshotted)) { + btrfs_end_write_no_snapshotting(root); return 0; } return 1; } -static int wait_snapshoting_atomic_t(atomic_t *a) +static int wait_snapshotting_atomic_t(atomic_t *a) { schedule(); return 0; @@ -11021,11 +11117,11 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root) while (true) { int ret; - ret = btrfs_start_write_no_snapshoting(root); + ret = btrfs_start_write_no_snapshotting(root); if (ret) break; - wait_on_atomic_t(&root->will_be_snapshoted, - wait_snapshoting_atomic_t, + wait_on_atomic_t(&root->will_be_snapshotted, + wait_snapshotting_atomic_t, TASK_UNINTERRUPTIBLE); } } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d3619e010005..970190cd347e 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -20,7 +20,6 @@ #include "locking.h" #include "rcu-string.h" #include "backref.h" -#include "transaction.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -87,19 +86,9 @@ void btrfs_leak_debug_check(void) static inline void __btrfs_debug_check_extent_io_range(const char *caller, struct extent_io_tree *tree, u64 start, u64 end) { - struct inode *inode; - u64 isize; - - if (!tree->mapping) - return; - - inode = tree->mapping->host; - isize = i_size_read(inode); - if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { - btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, - "%s: ino %llu isize %llu odd range [%llu,%llu]", - caller, btrfs_ino(BTRFS_I(inode)), isize, start, end); - } + if (tree->ops && tree->ops->check_extent_io_range) + tree->ops->check_extent_io_range(tree->private_data, caller, + start, end); } #else #define btrfs_leak_debug_add(new, head) do {} while (0) @@ -154,9 +143,9 @@ static noinline void flush_write_bio(void *data); static inline struct btrfs_fs_info * tree_fs_info(struct extent_io_tree *tree) { - if (!tree->mapping) - return NULL; - return btrfs_sb(tree->mapping->host->i_sb); + if (tree->ops) + return tree->ops->tree_fs_info(tree->private_data); + return NULL; } int __init extent_io_init(void) @@ -174,7 +163,8 @@ int __init extent_io_init(void) goto free_state_cache; btrfs_bioset = bioset_create(BIO_POOL_SIZE, - offsetof(struct btrfs_io_bio, bio)); + offsetof(struct btrfs_io_bio, bio), + BIOSET_NEED_BVECS); if (!btrfs_bioset) goto free_buffer_cache; @@ -213,13 +203,13 @@ void extent_io_exit(void) } void extent_io_tree_init(struct extent_io_tree *tree, - struct address_space *mapping) + void *private_data) { tree->state = RB_ROOT; tree->ops = NULL; tree->dirty_bytes = 0; spin_lock_init(&tree->lock); - tree->mapping = mapping; + tree->private_data = private_data; } static struct extent_state *alloc_extent_state(gfp_t mask) @@ -369,8 +359,7 @@ static void merge_cb(struct extent_io_tree *tree, struct extent_state *new, struct extent_state *other) { if (tree->ops && tree->ops->merge_extent_hook) - tree->ops->merge_extent_hook(tree->mapping->host, new, - other); + tree->ops->merge_extent_hook(tree->private_data, new, other); } /* @@ -421,15 +410,14 @@ static void set_state_cb(struct extent_io_tree *tree, struct extent_state *state, unsigned *bits) { if (tree->ops && tree->ops->set_bit_hook) - tree->ops->set_bit_hook(tree->mapping->host, state, bits); + tree->ops->set_bit_hook(tree->private_data, state, bits); } static void clear_state_cb(struct extent_io_tree *tree, struct extent_state *state, unsigned *bits) { if (tree->ops && tree->ops->clear_bit_hook) - tree->ops->clear_bit_hook(BTRFS_I(tree->mapping->host), - state, bits); + tree->ops->clear_bit_hook(tree->private_data, state, bits); } static void set_state_bits(struct extent_io_tree *tree, @@ -478,7 +466,7 @@ static void split_cb(struct extent_io_tree *tree, struct extent_state *orig, u64 split) { if (tree->ops && tree->ops->split_extent_hook) - tree->ops->split_extent_hook(tree->mapping->host, orig, split); + tree->ops->split_extent_hook(tree->private_data, orig, split); } /* @@ -1402,17 +1390,7 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end) */ static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end) { - unsigned long index = start >> PAGE_SHIFT; - unsigned long end_index = end >> PAGE_SHIFT; - struct page *page; - - while (index <= end_index) { - page = find_get_page(tree->mapping, index); - BUG_ON(!page); /* Pages should be in the extent_io_tree */ - set_page_writeback(page); - put_page(page); - index++; - } + tree->ops->set_range_writeback(tree->private_data, start, end); } /* find the first state struct with 'bits' set after 'start', and @@ -1961,11 +1939,12 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page) SetPageUptodate(page); } -int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) +int free_io_failure(struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, + struct io_failure_record *rec) { int ret; int err = 0; - struct extent_io_tree *failure_tree = &inode->io_failure_tree; set_state_failrec(failure_tree, rec->start, NULL); ret = clear_extent_bits(failure_tree, rec->start, @@ -1974,7 +1953,7 @@ int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) if (ret) err = ret; - ret = clear_extent_bits(&inode->io_tree, rec->start, + ret = clear_extent_bits(io_tree, rec->start, rec->start + rec->len - 1, EXTENT_DAMAGED); if (ret && !err) @@ -1994,11 +1973,10 @@ int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec) * currently, there can be no more than two copies of every data bit. thus, * exactly one rewrite is required. */ -int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, - u64 logical, struct page *page, - unsigned int pg_offset, int mirror_num) +int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, + u64 length, u64 logical, struct page *page, + unsigned int pg_offset, int mirror_num) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio; struct btrfs_device *dev; u64 map_length = 0; @@ -2009,9 +1987,7 @@ int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, ASSERT(!(fs_info->sb->s_flags & MS_RDONLY)); BUG_ON(!mirror_num); - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) - return -EIO; + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; map_length = length; @@ -2021,7 +1997,7 @@ int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, * read repair operation. */ btrfs_bio_counter_inc_blocked(fs_info); - if (btrfs_is_parity_mirror(fs_info, logical, length, mirror_num)) { + if (btrfs_is_parity_mirror(fs_info, logical, length)) { /* * Note that we don't use BTRFS_MAP_WRITE because it's supposed * to update all raid stripes, but here we just want to correct @@ -2056,7 +2032,7 @@ int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, bio_put(bio); return -EIO; } - bio->bi_bdev = dev->bdev; + bio_set_dev(bio, dev->bdev); bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; bio_add_page(bio, page, length, pg_offset); @@ -2070,7 +2046,7 @@ int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, btrfs_info_rl_in_rcu(fs_info, "read error corrected: ino %llu off %llu (dev %s sector %llu)", - btrfs_ino(inode), start, + ino, start, rcu_str_deref(dev->name), sector); btrfs_bio_counter_dec(fs_info); bio_put(bio); @@ -2084,14 +2060,13 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info, unsigned long i, num_pages = num_extent_pages(eb->start, eb->len); int ret = 0; - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) return -EROFS; for (i = 0; i < num_pages; i++) { struct page *p = eb->pages[i]; - ret = repair_io_failure(BTRFS_I(fs_info->btree_inode), start, - PAGE_SIZE, start, p, + ret = repair_io_failure(fs_info, 0, start, PAGE_SIZE, start, p, start - page_offset(p), mirror_num); if (ret) break; @@ -2105,24 +2080,24 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info, * each time an IO finishes, we do a fast check in the IO failure tree * to see if we need to process or clean up an io_failure_record */ -int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page, - unsigned int pg_offset) +int clean_io_failure(struct btrfs_fs_info *fs_info, + struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, u64 start, + struct page *page, u64 ino, unsigned int pg_offset) { u64 private; struct io_failure_record *failrec; - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_state *state; int num_copies; int ret; private = 0; - ret = count_range_bits(&inode->io_failure_tree, &private, - (u64)-1, 1, EXTENT_DIRTY, 0); + ret = count_range_bits(failure_tree, &private, (u64)-1, 1, + EXTENT_DIRTY, 0); if (!ret) return 0; - ret = get_state_failrec(&inode->io_failure_tree, start, - &failrec); + ret = get_state_failrec(failure_tree, start, &failrec); if (ret) return 0; @@ -2135,28 +2110,28 @@ int clean_io_failure(struct btrfs_inode *inode, u64 start, struct page *page, failrec->start); goto out; } - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) goto out; - spin_lock(&inode->io_tree.lock); - state = find_first_extent_bit_state(&inode->io_tree, + spin_lock(&io_tree->lock); + state = find_first_extent_bit_state(io_tree, failrec->start, EXTENT_LOCKED); - spin_unlock(&inode->io_tree.lock); + spin_unlock(&io_tree->lock); if (state && state->start <= failrec->start && state->end >= failrec->start + failrec->len - 1) { num_copies = btrfs_num_copies(fs_info, failrec->logical, failrec->len); if (num_copies > 1) { - repair_io_failure(inode, start, failrec->len, - failrec->logical, page, - pg_offset, failrec->failed_mirror); + repair_io_failure(fs_info, ino, start, failrec->len, + failrec->logical, page, pg_offset, + failrec->failed_mirror); } } out: - free_io_failure(inode, failrec); + free_io_failure(failure_tree, io_tree, failrec); return 0; } @@ -2282,7 +2257,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, return 0; } -int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, +bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, int failed_mirror) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -2298,7 +2273,7 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, btrfs_debug(fs_info, "Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d", num_copies, failrec->this_mirror, failed_mirror); - return 0; + return false; } /* @@ -2339,10 +2314,10 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, btrfs_debug(fs_info, "Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d", num_copies, failrec->this_mirror, failed_mirror); - return 0; + return false; } - return 1; + return true; } @@ -2356,13 +2331,10 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct btrfs_io_bio *btrfs_failed_bio; struct btrfs_io_bio *btrfs_bio; - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) - return NULL; - + bio = btrfs_io_bio_alloc(1); bio->bi_end_io = endio_func; bio->bi_iter.bi_sector = failrec->logical >> 9; - bio->bi_bdev = fs_info->fs_devices->latest_bdev; + bio_set_dev(bio, fs_info->fs_devices->latest_bdev); bio->bi_iter.bi_size = 0; bio->bi_private = data; @@ -2397,8 +2369,10 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, struct io_failure_record *failrec; struct inode *inode = page->mapping->host; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; struct bio *bio; int read_mode = 0; + blk_status_t status; int ret; BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); @@ -2407,9 +2381,9 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, if (ret) return ret; - ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror); - if (!ret) { - free_io_failure(BTRFS_I(inode), failrec); + if (!btrfs_check_repairable(inode, failed_bio, failrec, + failed_mirror)) { + free_io_failure(failure_tree, tree, failrec); return -EIO; } @@ -2421,21 +2395,18 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset, start - page_offset(page), (int)phy_offset, failed_bio->bi_end_io, NULL); - if (!bio) { - free_io_failure(BTRFS_I(inode), failrec); - return -EIO; - } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); btrfs_debug(btrfs_sb(inode->i_sb), "Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d", read_mode, failrec->this_mirror, failrec->in_validation); - ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror, + status = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror, failrec->bio_flags, 0); - if (ret) { - free_io_failure(BTRFS_I(inode), failrec); + if (status) { + free_io_failure(failure_tree, tree, failrec); bio_put(bio); + ret = blk_status_to_errno(status); } return ret; @@ -2474,11 +2445,13 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end) */ static void end_bio_extent_writepage(struct bio *bio) { + int error = blk_status_to_errno(bio->bi_status); struct bio_vec *bvec; u64 start; u64 end; int i; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; @@ -2503,7 +2476,7 @@ static void end_bio_extent_writepage(struct bio *bio) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; - end_extent_writepage(page, bio->bi_error, start, end); + end_extent_writepage(page, error, start, end); end_page_writeback(page); } @@ -2536,9 +2509,9 @@ endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len, static void end_bio_extent_readpage(struct bio *bio) { struct bio_vec *bvec; - int uptodate = !bio->bi_error; + int uptodate = !bio->bi_status; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - struct extent_io_tree *tree; + struct extent_io_tree *tree, *failure_tree; u64 offset = 0; u64 start; u64 end; @@ -2549,6 +2522,7 @@ static void end_bio_extent_readpage(struct bio *bio) int ret; int i; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; @@ -2556,9 +2530,10 @@ static void end_bio_extent_readpage(struct bio *bio) btrfs_debug(fs_info, "end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u", - (u64)bio->bi_iter.bi_sector, bio->bi_error, + (u64)bio->bi_iter.bi_sector, bio->bi_status, io_bio->mirror_num); tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; /* We always issue full-page reads, but if some block * in a page fails to read, blk_update_request() will @@ -2588,8 +2563,10 @@ static void end_bio_extent_readpage(struct bio *bio) if (ret) uptodate = 0; else - clean_io_failure(BTRFS_I(inode), start, - page, 0); + clean_io_failure(BTRFS_I(inode)->root->fs_info, + failure_tree, tree, start, + page, + btrfs_ino(BTRFS_I(inode)), 0); } if (likely(uptodate)) @@ -2615,7 +2592,7 @@ static void end_bio_extent_readpage(struct bio *bio) ret = bio_readpage_error(bio, offset, page, start, end, mirror); if (ret == 0) { - uptodate = !bio->bi_error; + uptodate = !bio->bi_status; offset += len; continue; } @@ -2673,77 +2650,80 @@ readpage_ok: endio_readpage_release_extent(tree, extent_start, extent_len, uptodate); if (io_bio->end_io) - io_bio->end_io(io_bio, bio->bi_error); + io_bio->end_io(io_bio, blk_status_to_errno(bio->bi_status)); bio_put(bio); } /* - * this allocates from the btrfs_bioset. We're returning a bio right now - * but you can call btrfs_io_bio for the appropriate container_of magic + * Initialize the members up to but not including 'bio'. Use after allocating a + * new bio by bio_alloc_bioset as it does not initialize the bytes outside of + * 'bio' because use of __GFP_ZERO is not supported. */ -struct bio * -btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, - gfp_t gfp_flags) +static inline void btrfs_io_bio_init(struct btrfs_io_bio *btrfs_bio) { - struct btrfs_io_bio *btrfs_bio; - struct bio *bio; - - bio = bio_alloc_bioset(gfp_flags, nr_vecs, btrfs_bioset); + memset(btrfs_bio, 0, offsetof(struct btrfs_io_bio, bio)); +} - if (bio == NULL && (current->flags & PF_MEMALLOC)) { - while (!bio && (nr_vecs /= 2)) { - bio = bio_alloc_bioset(gfp_flags, - nr_vecs, btrfs_bioset); - } - } +/* + * The following helpers allocate a bio. As it's backed by a bioset, it'll + * never fail. We're returning a bio right now but you can call btrfs_io_bio + * for the appropriate container_of magic + */ +struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte) +{ + struct bio *bio; - if (bio) { - bio->bi_bdev = bdev; - bio->bi_iter.bi_sector = first_sector; - btrfs_bio = btrfs_io_bio(bio); - btrfs_bio->csum = NULL; - btrfs_bio->csum_allocated = NULL; - btrfs_bio->end_io = NULL; - } + bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset); + bio_set_dev(bio, bdev); + bio->bi_iter.bi_sector = first_byte >> 9; + btrfs_io_bio_init(btrfs_io_bio(bio)); return bio; } -struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) +struct bio *btrfs_bio_clone(struct bio *bio) { struct btrfs_io_bio *btrfs_bio; struct bio *new; - new = bio_clone_bioset(bio, gfp_mask, btrfs_bioset); - if (new) { - btrfs_bio = btrfs_io_bio(new); - btrfs_bio->csum = NULL; - btrfs_bio->csum_allocated = NULL; - btrfs_bio->end_io = NULL; - } + /* Bio allocation backed by a bioset does not fail */ + new = bio_clone_fast(bio, GFP_NOFS, btrfs_bioset); + btrfs_bio = btrfs_io_bio(new); + btrfs_io_bio_init(btrfs_bio); + btrfs_bio->iter = bio->bi_iter; return new; } -/* this also allocates from the btrfs_bioset */ -struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) +struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs) { - struct btrfs_io_bio *btrfs_bio; struct bio *bio; - bio = bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset); - if (bio) { - btrfs_bio = btrfs_io_bio(bio); - btrfs_bio->csum = NULL; - btrfs_bio->csum_allocated = NULL; - btrfs_bio->end_io = NULL; - } + /* Bio allocation backed by a bioset does not fail */ + bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, btrfs_bioset); + btrfs_io_bio_init(btrfs_io_bio(bio)); return bio; } +struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size) +{ + struct bio *bio; + struct btrfs_io_bio *btrfs_bio; + + /* this will never fail when it's backed by a bioset */ + bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset); + ASSERT(bio); + + btrfs_bio = btrfs_io_bio(bio); + btrfs_io_bio_init(btrfs_bio); + + bio_trim(bio, offset >> 9, size >> 9); + btrfs_bio->iter = bio->bi_iter; + return bio; +} static int __must_check submit_one_bio(struct bio *bio, int mirror_num, unsigned long bio_flags) { - int ret = 0; + blk_status_t ret = 0; struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; struct page *page = bvec->bv_page; struct extent_io_tree *tree = bio->bi_private; @@ -2755,13 +2735,13 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num, bio_get(bio); if (tree->ops) - ret = tree->ops->submit_bio_hook(page->mapping->host, bio, + ret = tree->ops->submit_bio_hook(tree->private_data, bio, mirror_num, bio_flags, start); else btrfsic_submit_bio(bio); bio_put(bio); - return ret; + return blk_status_to_errno(ret); } static int merge_bio(struct extent_io_tree *tree, struct page *page, @@ -2776,7 +2756,10 @@ static int merge_bio(struct extent_io_tree *tree, struct page *page, } -static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree, +/* + * @opf: bio REQ_OP_* and REQ_* flags as one value + */ +static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree, struct writeback_control *wbc, struct page *page, sector_t sector, size_t size, unsigned long offset, @@ -2818,15 +2801,12 @@ static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree, } } - bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES, - GFP_NOFS | __GFP_HIGH); - if (!bio) - return -ENOMEM; - + bio = btrfs_bio_alloc(bdev, (u64)sector << 9); bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; - bio_set_op_attrs(bio, op, op_flags); + bio->bi_write_hint = page->mapping->host->i_write_hint; + bio->bi_opf = opf; if (wbc) { wbc_init_bio(wbc, bio); wbc_account_io(wbc, page, page_size); @@ -2900,7 +2880,7 @@ static int __do_readpage(struct extent_io_tree *tree, get_extent_t *get_extent, struct extent_map **em_cached, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int read_flags, + unsigned long *bio_flags, unsigned int read_flags, u64 *prev_em_start) { struct inode *inode = page->mapping->host; @@ -3081,7 +3061,7 @@ static int __do_readpage(struct extent_io_tree *tree, continue; } - ret = submit_extent_page(REQ_OP_READ, read_flags, tree, NULL, + ret = submit_extent_page(REQ_OP_READ | read_flags, tree, NULL, page, sector, disk_io_size, pg_offset, bdev, bio, end_bio_extent_readpage, mirror_num, @@ -3186,7 +3166,8 @@ static int __extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, struct bio **bio, int mirror_num, - unsigned long *bio_flags, int read_flags) + unsigned long *bio_flags, + unsigned int read_flags) { struct inode *inode = page->mapping->host; struct btrfs_ordered_extent *ordered; @@ -3333,7 +3314,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, struct extent_page_data *epd, loff_t i_size, unsigned long nr_written, - int write_flags, int *nr_ret) + unsigned int write_flags, int *nr_ret) { struct extent_io_tree *tree = epd->tree; u64 start = page_offset(page); @@ -3449,7 +3430,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, page->index, cur, end); } - ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc, + ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc, page, sector, iosize, pg_offset, bdev, &epd->bio, end_bio_extent_writepage, @@ -3487,11 +3468,10 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc, size_t pg_offset = 0; loff_t i_size = i_size_read(inode); unsigned long end_index = i_size >> PAGE_SHIFT; - int write_flags = 0; + unsigned int write_flags = 0; unsigned long nr_written = 0; - if (wbc->sync_mode == WB_SYNC_ALL) - write_flags = REQ_SYNC; + write_flags = wbc_to_write_flags(wbc); trace___extent_writepage(page, inode, wbc); @@ -3597,9 +3577,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb, set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); spin_unlock(&eb->refs_lock); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); - __percpu_counter_add(&fs_info->dirty_metadata_bytes, - -eb->len, - fs_info->dirty_metadata_batch); + percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, + -eb->len, + fs_info->dirty_metadata_batch); ret = 1; } else { spin_unlock(&eb->refs_lock); @@ -3700,6 +3680,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) struct extent_buffer *eb; int i, done; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; @@ -3707,7 +3688,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio) BUG_ON(!eb); done = atomic_dec_and_test(&eb->io_pages); - if (bio->bi_error || + if (bio->bi_status || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) { ClearPageUptodate(page); set_btree_ioerr(page); @@ -3736,7 +3717,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, unsigned long i, num_pages; unsigned long bio_flags = 0; unsigned long start, end; - int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META; + unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META; int ret = 0; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); @@ -3757,7 +3738,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0 */ start = btrfs_item_nr_offset(nritems); - end = btrfs_leaf_data(eb) + leaf_data_end(fs_info, eb); + end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, eb); memzero_extent_buffer(eb, start, end - start); } @@ -3766,7 +3747,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); - ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc, + ret = submit_extent_page(REQ_OP_WRITE | write_flags, tree, wbc, p, offset >> 9, PAGE_SIZE, 0, bdev, &epd->bio, end_bio_extent_buffer_writepage, @@ -4081,9 +4062,6 @@ static void flush_epd_write_bio(struct extent_page_data *epd) if (epd->bio) { int ret; - bio_set_op_attrs(epd->bio, REQ_OP_WRITE, - epd->sync_io ? REQ_SYNC : 0); - ret = submit_one_bio(epd->bio, 0, epd->bio_flags); BUG_ON(ret < 0); /* -ENOMEM */ epd->bio = NULL; @@ -4463,29 +4441,25 @@ try_submit_last: } /* - * Sanity check for fiemap cache + * Emit last fiemap cache * - * All fiemap cache should be submitted by emit_fiemap_extent() - * Iteration should be terminated either by last fiemap extent or - * fieinfo->fi_extents_max. - * So no cached fiemap should exist. + * The last fiemap cache may still be cached in the following case: + * 0 4k 8k + * |<- Fiemap range ->| + * |<------------ First extent ----------->| + * + * In this case, the first extent range will be cached but not emitted. + * So we must emit it before ending extent_fiemap(). */ -static int check_fiemap_cache(struct btrfs_fs_info *fs_info, - struct fiemap_extent_info *fieinfo, - struct fiemap_cache *cache) +static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info, + struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache) { int ret; if (!cache->cached) return 0; - /* Small and recoverbale problem, only to info developer */ -#ifdef CONFIG_BTRFS_DEBUG - WARN_ON(1); -#endif - btrfs_warn(fs_info, - "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x", - cache->offset, cache->phys, cache->len, cache->flags); ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, cache->len, cache->flags); cache->cached = false; @@ -4631,36 +4605,21 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); } else if (fieinfo->fi_extents_max) { - struct btrfs_trans_handle *trans; - u64 bytenr = em->block_start - (em->start - em->orig_start); disko = em->block_start + offset_in_extent; /* - * We need a trans handle to get delayed refs - */ - trans = btrfs_join_transaction(root); - /* - * It's OK if we can't start a trans we can still check - * from commit_root - */ - if (IS_ERR(trans)) - trans = NULL; - - /* * As btrfs supports shared space, this information * can be exported to userspace tools via * flag FIEMAP_EXTENT_SHARED. If fi_extents_max == 0 * then we're just getting a count and we can skip the * lookup stuff. */ - ret = btrfs_check_shared(trans, root->fs_info, - root->objectid, - btrfs_ino(BTRFS_I(inode)), bytenr); - if (trans) - btrfs_end_transaction(trans); + ret = btrfs_check_shared(root, + btrfs_ino(BTRFS_I(inode)), + bytenr); if (ret < 0) goto out_free; if (ret) @@ -4701,7 +4660,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } out_free: if (!ret) - ret = check_fiemap_cache(root->fs_info, fieinfo, &cache); + ret = emit_last_fiemap_cache(root->fs_info, fieinfo, &cache); free_extent_map(em); out: btrfs_free_path(path); @@ -5430,9 +5389,8 @@ unlock_exit: return ret; } -void read_extent_buffer(struct extent_buffer *eb, void *dstv, - unsigned long start, - unsigned long len) +void read_extent_buffer(const struct extent_buffer *eb, void *dstv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; @@ -5442,8 +5400,12 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv, size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1); unsigned long i = (start_offset + start) >> PAGE_SHIFT; - WARN_ON(start > eb->len); - WARN_ON(start + len > eb->start + eb->len); + if (start + len > eb->len) { + WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n", + eb->start, eb->len, start, len); + memset(dst, 0, len); + return; + } offset = (start_offset + start) & (PAGE_SIZE - 1); @@ -5461,9 +5423,9 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv, } } -int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv, - unsigned long start, - unsigned long len) +int read_extent_buffer_to_user(const struct extent_buffer *eb, + void __user *dstv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; @@ -5503,10 +5465,10 @@ int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv, * return 1 if the item spans two pages. * return -EINVAL otherwise. */ -int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, - unsigned long min_len, char **map, - unsigned long *map_start, - unsigned long *map_len) +int map_private_extent_buffer(const struct extent_buffer *eb, + unsigned long start, unsigned long min_len, + char **map, unsigned long *map_start, + unsigned long *map_len) { size_t offset = start & (PAGE_SIZE - 1); char *kaddr; @@ -5516,6 +5478,12 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, unsigned long end_i = (start_offset + start + min_len - 1) >> PAGE_SHIFT; + if (start + min_len > eb->len) { + WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n", + eb->start, eb->len, start, min_len); + return -EINVAL; + } + if (i != end_i) return 1; @@ -5527,12 +5495,6 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, *map_start = ((u64)i << PAGE_SHIFT) - start_offset; } - if (start + min_len > eb->len) { - WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n", - eb->start, eb->len, start, min_len); - return -EINVAL; - } - p = eb->pages[i]; kaddr = page_address(p); *map = kaddr + offset; @@ -5540,9 +5502,8 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, return 0; } -int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv, - unsigned long start, - unsigned long len) +int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, + unsigned long start, unsigned long len) { size_t cur; size_t offset; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 1eafa2f0ede3..faffa28ba707 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -92,7 +92,7 @@ struct btrfs_inode; struct btrfs_io_bio; struct io_failure_record; -typedef int (extent_submit_bio_hook_t)(struct inode *inode, struct bio *bio, +typedef blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset); struct extent_io_ops { @@ -108,32 +108,36 @@ struct extent_io_ops { size_t size, struct bio *bio, unsigned long bio_flags); int (*readpage_io_failed_hook)(struct page *page, int failed_mirror); + struct btrfs_fs_info *(*tree_fs_info)(void *private_data); + void (*set_range_writeback)(void *private_data, u64 start, u64 end); /* * Optional hooks, called if the pointer is not NULL */ - int (*fill_delalloc)(struct inode *inode, struct page *locked_page, + int (*fill_delalloc)(void *private_data, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written); int (*writepage_start_hook)(struct page *page, u64 start, u64 end); void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); - void (*set_bit_hook)(struct inode *inode, struct extent_state *state, + void (*set_bit_hook)(void *private_data, struct extent_state *state, unsigned *bits); - void (*clear_bit_hook)(struct btrfs_inode *inode, + void (*clear_bit_hook)(void *private_data, struct extent_state *state, unsigned *bits); - void (*merge_extent_hook)(struct inode *inode, + void (*merge_extent_hook)(void *private_data, struct extent_state *new, struct extent_state *other); - void (*split_extent_hook)(struct inode *inode, + void (*split_extent_hook)(void *private_data, struct extent_state *orig, u64 split); + void (*check_extent_io_range)(void *private_data, const char *caller, + u64 start, u64 end); }; struct extent_io_tree { struct rb_root state; - struct address_space *mapping; + void *private_data; u64 dirty_bytes; int track_uptodate; spinlock_t lock; @@ -205,12 +209,46 @@ struct extent_buffer { */ struct extent_changeset { /* How many bytes are set/cleared in this operation */ - u64 bytes_changed; + unsigned int bytes_changed; /* Changed ranges */ struct ulist range_changed; }; +static inline void extent_changeset_init(struct extent_changeset *changeset) +{ + changeset->bytes_changed = 0; + ulist_init(&changeset->range_changed); +} + +static inline struct extent_changeset *extent_changeset_alloc(void) +{ + struct extent_changeset *ret; + + ret = kmalloc(sizeof(*ret), GFP_KERNEL); + if (!ret) + return NULL; + + extent_changeset_init(ret); + return ret; +} + +static inline void extent_changeset_release(struct extent_changeset *changeset) +{ + if (!changeset) + return; + changeset->bytes_changed = 0; + ulist_release(&changeset->range_changed); +} + +static inline void extent_changeset_free(struct extent_changeset *changeset) +{ + if (!changeset) + return; + extent_changeset_release(changeset); + kfree(changeset); +} + static inline void extent_set_compress_type(unsigned long *bio_flags, int compress_type) { @@ -230,8 +268,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, u64 start, u64 len, int create); -void extent_io_tree_init(struct extent_io_tree *tree, - struct address_space *mapping); +void extent_io_tree_init(struct extent_io_tree *tree, void *private_data); int try_release_extent_mapping(struct extent_map_tree *map, struct extent_io_tree *tree, struct page *page, gfp_t mask); @@ -412,14 +449,13 @@ static inline void extent_buffer_get(struct extent_buffer *eb) atomic_inc(&eb->refs); } -int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv, - unsigned long start, - unsigned long len); -void read_extent_buffer(struct extent_buffer *eb, void *dst, +int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, + unsigned long start, unsigned long len); +void read_extent_buffer(const struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); -int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst, - unsigned long start, +int read_extent_buffer_to_user(const struct extent_buffer *eb, + void __user *dst, unsigned long start, unsigned long len); void write_extent_buffer_fsid(struct extent_buffer *eb, const void *src); void write_extent_buffer_chunk_tree_uuid(struct extent_buffer *eb, @@ -449,30 +485,31 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb); void clear_extent_buffer_uptodate(struct extent_buffer *eb); int extent_buffer_uptodate(struct extent_buffer *eb); int extent_buffer_under_io(struct extent_buffer *eb); -int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset, - unsigned long min_len, char **map, - unsigned long *map_start, - unsigned long *map_len); +int map_private_extent_buffer(const struct extent_buffer *eb, + unsigned long offset, unsigned long min_len, + char **map, unsigned long *map_start, + unsigned long *map_len); void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end); void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end); void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, u64 delalloc_end, struct page *locked_page, unsigned bits_to_clear, unsigned long page_ops); -struct bio * -btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs, - gfp_t gfp_flags); -struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs); -struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask); +struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte); +struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs); +struct bio *btrfs_bio_clone(struct bio *bio); +struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size); struct btrfs_fs_info; struct btrfs_inode; -int repair_io_failure(struct btrfs_inode *inode, u64 start, u64 length, - u64 logical, struct page *page, - unsigned int pg_offset, int mirror_num); -int clean_io_failure(struct btrfs_inode *inode, u64 start, - struct page *page, unsigned int pg_offset); +int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start, + u64 length, u64 logical, struct page *page, + unsigned int pg_offset, int mirror_num); +int clean_io_failure(struct btrfs_fs_info *fs_info, + struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, u64 start, + struct page *page, u64 ino, unsigned int pg_offset); void end_extent_writepage(struct page *page, int err, u64 start, u64 end); int repair_eb_io_failure(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, int mirror_num); @@ -501,13 +538,15 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end); int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end, struct io_failure_record **failrec_ret); -int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, - struct io_failure_record *failrec, int fail_mirror); +bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio, + struct io_failure_record *failrec, int fail_mirror); struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio, struct io_failure_record *failrec, struct page *page, int pg_offset, int icsum, bio_end_io_t *endio_func, void *data); -int free_io_failure(struct btrfs_inode *inode, struct io_failure_record *rec); +int free_io_failure(struct extent_io_tree *failure_tree, + struct extent_io_tree *io_tree, + struct io_failure_record *rec); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS noinline u64 find_lock_delalloc_range(struct inode *inode, struct extent_io_tree *tree, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index 64fcb31d7163..fdcb41002623 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -160,11 +160,12 @@ static void btrfs_io_bio_endio_readpage(struct btrfs_io_bio *bio, int err) kfree(bio->csum_allocated); } -static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, +static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u64 logical_offset, u32 *dst, int dio) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio); struct btrfs_csum_item *item = NULL; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; @@ -177,12 +178,12 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u64 page_bytes_left; u32 diff; int nblocks; - int count = 0, i; + int count = 0; u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); path = btrfs_alloc_path(); if (!path) - return -ENOMEM; + return BLK_STS_RESOURCE; nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits; if (!dst) { @@ -191,7 +192,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, csum_size, GFP_NOFS); if (!btrfs_bio->csum_allocated) { btrfs_free_path(path); - return -ENOMEM; + return BLK_STS_RESOURCE; } btrfs_bio->csum = btrfs_bio->csum_allocated; btrfs_bio->end_io = btrfs_io_bio_endio_readpage; @@ -206,8 +207,6 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, if (bio->bi_iter.bi_size > PAGE_SIZE * 8) path->reada = READA_FORWARD; - WARN_ON(bio->bi_vcnt <= 0); - /* * the free space stuff is only read when it hasn't been * updated in the current transaction. So, we can safely @@ -223,13 +222,13 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, if (dio) offset = logical_offset; - bio_for_each_segment_all(bvec, bio, i) { - page_bytes_left = bvec->bv_len; + bio_for_each_segment(bvec, bio, iter) { + page_bytes_left = bvec.bv_len; if (count) goto next; if (!dio) - offset = page_offset(bvec->bv_page) + bvec->bv_offset; + offset = page_offset(bvec.bv_page) + bvec.bv_offset; count = btrfs_find_ordered_sum(inode, offset, disk_bytenr, (u32 *)csum, nblocks); if (count) @@ -303,12 +302,12 @@ next: return 0; } -int btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst) +blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst) { return __btrfs_lookup_bio_sums(inode, bio, 0, dst, 0); } -int btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset) +blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset) { return __btrfs_lookup_bio_sums(inode, bio, offset, NULL, 1); } @@ -433,26 +432,26 @@ fail: return ret; } -int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, +blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio, u64 file_start, int contig) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_ordered_sum *sums; struct btrfs_ordered_extent *ordered = NULL; char *data; - struct bio_vec *bvec; + struct bvec_iter iter; + struct bio_vec bvec; int index; int nr_sectors; - int i, j; unsigned long total_bytes = 0; unsigned long this_sum_bytes = 0; + int i; u64 offset; - WARN_ON(bio->bi_vcnt <= 0); sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), GFP_NOFS); if (!sums) - return -ENOMEM; + return BLK_STS_RESOURCE; sums->len = bio->bi_iter.bi_size; INIT_LIST_HEAD(&sums->list); @@ -465,19 +464,19 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, sums->bytenr = (u64)bio->bi_iter.bi_sector << 9; index = 0; - bio_for_each_segment_all(bvec, bio, j) { + bio_for_each_segment(bvec, bio, iter) { if (!contig) - offset = page_offset(bvec->bv_page) + bvec->bv_offset; + offset = page_offset(bvec.bv_page) + bvec.bv_offset; if (!ordered) { ordered = btrfs_lookup_ordered_extent(inode, offset); BUG_ON(!ordered); /* Logic error */ } - data = kmap_atomic(bvec->bv_page); + data = kmap_atomic(bvec.bv_page); nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, - bvec->bv_len + fs_info->sectorsize + bvec.bv_len + fs_info->sectorsize - 1); for (i = 0; i < nr_sectors; i++) { @@ -504,12 +503,12 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio, + total_bytes; index = 0; - data = kmap_atomic(bvec->bv_page); + data = kmap_atomic(bvec.bv_page); } sums->sums[index] = ~(u32)0; sums->sums[index] - = btrfs_csum_data(data + bvec->bv_offset + = btrfs_csum_data(data + bvec.bv_offset + (i * fs_info->sectorsize), sums->sums[index], fs_info->sectorsize); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index da1096eb1a40..aafcc785f840 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1536,7 +1536,7 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, u64 num_bytes; int ret; - ret = btrfs_start_write_no_snapshoting(root); + ret = btrfs_start_write_no_snapshotting(root); if (!ret) return -ENOSPC; @@ -1561,7 +1561,7 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, NULL, NULL, NULL); if (ret <= 0) { ret = 0; - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); } else { *write_bytes = min_t(size_t, *write_bytes , num_bytes - pos + lockstart); @@ -1581,6 +1581,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, struct btrfs_root *root = BTRFS_I(inode)->root; struct page **pages = NULL; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; u64 release_bytes = 0; u64 lockstart; u64 lockend; @@ -1628,7 +1629,9 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes = round_up(write_bytes + sector_offset, fs_info->sectorsize); - ret = btrfs_check_data_free_space(inode, pos, write_bytes); + extent_changeset_release(data_reserved); + ret = btrfs_check_data_free_space(inode, &data_reserved, pos, + write_bytes); if (ret < 0) { if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && @@ -1657,10 +1660,11 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file, reserve_bytes); if (ret) { if (!only_release_metadata) - btrfs_free_reserved_data_space(inode, pos, - write_bytes); + btrfs_free_reserved_data_space(inode, + data_reserved, pos, + write_bytes); else - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); break; } @@ -1740,8 +1744,9 @@ again: __pos = round_down(pos, fs_info->sectorsize) + (dirty_pages << PAGE_SHIFT); - btrfs_delalloc_release_space(inode, __pos, - release_bytes); + btrfs_delalloc_release_space(inode, + data_reserved, __pos, + release_bytes); } } @@ -1762,7 +1767,7 @@ again: release_bytes = 0; if (only_release_metadata) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); if (only_release_metadata && copied > 0) { lockstart = round_down(pos, @@ -1792,16 +1797,17 @@ again: if (release_bytes) { if (only_release_metadata) { - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); btrfs_delalloc_release_metadata(BTRFS_I(inode), release_bytes); } else { - btrfs_delalloc_release_space(inode, - round_down(pos, fs_info->sectorsize), - release_bytes); + btrfs_delalloc_release_space(inode, data_reserved, + round_down(pos, fs_info->sectorsize), + release_bytes); } } + extent_changeset_free(data_reserved); return num_written ? num_written : ret; } @@ -1876,17 +1882,40 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host); ssize_t err; loff_t pos; - size_t count; + size_t count = iov_iter_count(from); loff_t oldsize; int clean_page = 0; - inode_lock(inode); + if (!(iocb->ki_flags & IOCB_DIRECT) && + (iocb->ki_flags & IOCB_NOWAIT)) + return -EOPNOTSUPP; + + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } + err = generic_write_checks(iocb, from); if (err <= 0) { inode_unlock(inode); return err; } + pos = iocb->ki_pos; + if (iocb->ki_flags & IOCB_NOWAIT) { + /* + * We will allocate space in case nodatacow is not set, + * so bail + */ + if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | + BTRFS_INODE_PREALLOC)) || + check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + inode_unlock(inode); + return -EAGAIN; + } + } + current->backing_dev_info = inode_to_bdi(inode); err = file_remove_privs(file); if (err) { @@ -1914,8 +1943,6 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ update_time_for_write(inode); - pos = iocb->ki_pos; - count = iov_iter_count(from); start_pos = round_down(pos, fs_info->sectorsize); oldsize = i_size_read(inode); if (start_pos > oldsize) { @@ -1967,8 +1994,15 @@ out: int btrfs_release_file(struct inode *inode, struct file *filp) { - if (filp->private_data) + struct btrfs_file_private *private = filp->private_data; + + if (private && private->trans) btrfs_ioctl_trans_end(filp); + if (private && private->filldir_buf) + kfree(private->filldir_buf); + kfree(private); + filp->private_data = NULL; + /* * ordered_data_close is set by settattr when we are about to truncate * a file from a non-zero size to a zero size. This tries to @@ -2011,7 +2045,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; struct btrfs_log_ctx ctx; - int ret = 0; + int ret = 0, err; bool full_sync = 0; u64 len; @@ -2030,7 +2064,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ ret = start_ordered_ops(inode, start, end); if (ret) - return ret; + goto out; inode_lock(inode); atomic_inc(&root->log_batch); @@ -2135,10 +2169,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * An ordered extent might have started before and completed * already with io errors, in which case the inode was not * updated and we end up here. So check the inode's mapping - * flags for any errors that might have happened while doing - * writeback of file data. + * for any errors that might have happened since we last + * checked called fsync. */ - ret = filemap_check_errors(inode->i_mapping); + ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err); inode_unlock(inode); goto out; } @@ -2227,6 +2261,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = btrfs_end_transaction(trans); } out: + err = file_check_and_advance_wb_err(file); + if (!ret) + ret = err; return ret > 0 ? -EIO : ret; } @@ -2390,10 +2427,13 @@ out: */ static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len) { + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct extent_map *em; int ret = 0; - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, *start, *len, 0); + em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, + round_down(*start, fs_info->sectorsize), + round_up(*len, fs_info->sectorsize), 0); if (IS_ERR(em)) return PTR_ERR(em); @@ -2769,6 +2809,7 @@ static long btrfs_fallocate(struct file *file, int mode, { struct inode *inode = file_inode(file); struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; struct falloc_range *range; struct falloc_range *tmp; struct list_head reserve_list; @@ -2898,8 +2939,8 @@ static long btrfs_fallocate(struct file *file, int mode, free_extent_map(em); break; } - ret = btrfs_qgroup_reserve_data(inode, cur_offset, - last_byte - cur_offset); + ret = btrfs_qgroup_reserve_data(inode, &data_reserved, + cur_offset, last_byte - cur_offset); if (ret < 0) { free_extent_map(em); break; @@ -2910,8 +2951,8 @@ static long btrfs_fallocate(struct file *file, int mode, * range, free reserved data space first, otherwise * it'll result in false ENOSPC error. */ - btrfs_free_reserved_data_space(inode, cur_offset, - last_byte - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + cur_offset, last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -2930,8 +2971,9 @@ static long btrfs_fallocate(struct file *file, int mode, range->len, i_blocksize(inode), offset + len, &alloc_hint); else - btrfs_free_reserved_data_space(inode, range->start, - range->len); + btrfs_free_reserved_data_space(inode, + data_reserved, range->start, + range->len); list_del(&range->list); kfree(range); } @@ -2969,8 +3011,9 @@ out: inode_unlock(inode); /* Let go of our reservation. */ if (ret != 0) - btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + alloc_start, alloc_end - cur_offset); + extent_changeset_free(data_reserved); return ret; } @@ -3071,13 +3114,19 @@ out: return offset; } +static int btrfs_file_open(struct inode *inode, struct file *filp) +{ + filp->f_mode |= FMODE_NOWAIT; + return generic_file_open(inode, filp); +} + const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .write_iter = btrfs_file_write_iter, .mmap = btrfs_file_mmap, - .open = generic_file_open, + .open = btrfs_file_open, .release = btrfs_release_file, .fsync = btrfs_sync_file, .fallocate = btrfs_fallocate, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index c5e6180cdb8c..cdc9f4015ec3 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -709,7 +709,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, if (!BTRFS_I(inode)->generation) { btrfs_info(fs_info, - "The free space cache file (%llu) is invalid. skip it\n", + "the free space cache file (%llu) is invalid, skip it", offset); return 0; } diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index fc0bd8406758..684f12247db7 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -17,7 +17,7 @@ */ #include <linux/kernel.h> -#include <linux/vmalloc.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "disk-io.h" #include "locking.h" @@ -153,21 +153,21 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize) static u8 *alloc_bitmap(u32 bitmap_size) { - void *mem; + u8 *ret; + unsigned int nofs_flag; /* - * The allocation size varies, observed numbers were < 4K up to 16K. - * Using vmalloc unconditionally would be too heavy, we'll try - * contiguous allocations first. + * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse + * into the filesystem as the free space bitmap can be modified in the + * critical section of a transaction commit. + * + * TODO: push the memalloc_nofs_{save,restore}() to the caller where we + * know that recursion is unsafe. */ - if (bitmap_size <= PAGE_SIZE) - return kzalloc(bitmap_size, GFP_NOFS); - - mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN); - if (mem) - return mem; - - return __vmalloc(bitmap_size, GFP_NOFS | __GFP_ZERO, PAGE_KERNEL); + nofs_flag = memalloc_nofs_save(); + ret = kvzalloc(bitmap_size, GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); + return ret; } int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, @@ -1188,11 +1188,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); - ret = btrfs_commit_transaction(trans); - if (ret) - return ret; - - return 0; + return btrfs_commit_transaction(trans); abort: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); @@ -1261,7 +1257,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) if (ret) goto abort; - ret = btrfs_del_root(trans, tree_root, &free_space_root->root_key); + ret = btrfs_del_root(trans, fs_info, &free_space_root->root_key); if (ret) goto abort; @@ -1277,11 +1273,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) free_extent_buffer(free_space_root->commit_root); kfree(free_space_root); - ret = btrfs_commit_transaction(trans); - if (ret) - return ret; - - return 0; + return btrfs_commit_transaction(trans); abort: btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/free-space-tree.h b/fs/btrfs/free-space-tree.h index 54ffced3bce8..ba3787df43c3 100644 --- a/fs/btrfs/free-space-tree.h +++ b/fs/btrfs/free-space-tree.h @@ -44,7 +44,7 @@ int remove_from_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 start, u64 size); -/* Exposed for testing. */ +#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct btrfs_free_space_info * search_free_space_info(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, @@ -68,5 +68,6 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, struct btrfs_path *path); int free_space_test_bit(struct btrfs_block_group_cache *block_group, struct btrfs_path *path, u64 offset); +#endif #endif diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 5c6c20ec64d8..d02019747d00 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -400,6 +400,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root, struct btrfs_path *path; struct inode *inode; struct btrfs_block_rsv *rsv; + struct extent_changeset *data_reserved = NULL; u64 num_bytes; u64 alloc_hint = 0; int ret; @@ -492,7 +493,7 @@ again: /* Just to make sure we have enough space */ prealloc += 8 * PAGE_SIZE; - ret = btrfs_delalloc_reserve_space(inode, 0, prealloc); + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc); if (ret) goto out_put; @@ -516,6 +517,7 @@ out: trans->bytes_reserved = num_bytes; btrfs_free_path(path); + extent_changeset_free(data_reserved); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ef3c98c527c1..d94e3f68b9b1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -86,7 +86,6 @@ static const struct extent_io_ops btrfs_extent_io_ops; static struct kmem_cache *btrfs_inode_cachep; struct kmem_cache *btrfs_trans_handle_cachep; -struct kmem_cache *btrfs_transaction_cachep; struct kmem_cache *btrfs_path_cachep; struct kmem_cache *btrfs_free_space_cachep; @@ -136,6 +135,18 @@ static inline void btrfs_cleanup_ordered_extents(struct inode *inode, const u64 offset, const u64 bytes) { + unsigned long index = offset >> PAGE_SHIFT; + unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + index++; + if (!page) + continue; + ClearPagePrivate2(page); + put_page(page); + } return __endio_write_update_ordered(inode, offset + PAGE_SIZE, bytes - PAGE_SIZE, false); } @@ -178,7 +189,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, char *kaddr; unsigned long ptr; struct btrfs_file_extent_item *ei; - int err = 0; int ret; size_t cur_size = size; unsigned long offset; @@ -200,10 +210,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, path->leave_spinning = 1; ret = btrfs_insert_empty_item(trans, root, path, &key, datasize); - if (ret) { - err = ret; + if (ret) goto fail; - } } leaf = path->nodes[0]; ei = btrfs_item_ptr(leaf, path->slots[0], @@ -258,9 +266,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, BTRFS_I(inode)->disk_i_size = inode->i_size; ret = btrfs_update_inode(trans, root, inode); - return ret; fail: - return err; + return ret; } @@ -350,7 +357,7 @@ out: * And at reserve time, it's always aligned to page size, so * just free one page here. */ - btrfs_qgroup_free_data(inode, 0, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE); btrfs_free_path(path); btrfs_end_transaction(trans); return ret; @@ -397,20 +404,23 @@ static noinline int add_async_extent(struct async_cow *cow, return 0; } -static inline int inode_need_compress(struct inode *inode) +static inline int inode_need_compress(struct inode *inode, u64 start, u64 end) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); /* force compress */ if (btrfs_test_opt(fs_info, FORCE_COMPRESS)) return 1; + /* defrag ioctl */ + if (BTRFS_I(inode)->defrag_compress) + return 1; /* bad compression ratios */ if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS) return 0; if (btrfs_test_opt(fs_info, COMPRESS) || BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS || - BTRFS_I(inode)->force_compress) - return 1; + BTRFS_I(inode)->prop_compress) + return btrfs_compress_heuristic(inode, start, end); return 0; } @@ -508,7 +518,7 @@ again: * inode has not been flagged as nocompress. This flag can * change at any time if we discover bad compression ratios. */ - if (inode_need_compress(inode)) { + if (inode_need_compress(inode, start, end)) { WARN_ON(pages); pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!pages) { @@ -516,8 +526,10 @@ again: goto cont; } - if (BTRFS_I(inode)->force_compress) - compress_type = BTRFS_I(inode)->force_compress; + if (BTRFS_I(inode)->defrag_compress) + compress_type = BTRFS_I(inode)->defrag_compress; + else if (BTRFS_I(inode)->prop_compress) + compress_type = BTRFS_I(inode)->prop_compress; /* * we need to call clear_page_dirty_for_io on each @@ -608,12 +620,11 @@ cont: /* * one last check to make sure the compression is really a - * win, compare the page count read with the blocks on disk + * win, compare the page count read with the blocks on disk, + * compression must free at least one sector size */ total_in = ALIGN(total_in, PAGE_SIZE); - if (total_compressed >= total_in) { - will_compress = 0; - } else { + if (total_compressed + blocksize <= total_in) { num_bytes = total_in; *num_added += 1; @@ -651,7 +662,7 @@ cont: /* flag the file so we don't compress in the future */ if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) && - !(BTRFS_I(inode)->force_compress)) { + !(BTRFS_I(inode)->prop_compress)) { BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; } } @@ -842,13 +853,12 @@ retry: NULL, EXTENT_LOCKED | EXTENT_DELALLOC, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK); - ret = btrfs_submit_compressed_write(inode, + if (btrfs_submit_compressed_write(inode, async_extent->start, async_extent->ram_size, ins.objectid, ins.offset, async_extent->pages, - async_extent->nr_pages); - if (ret) { + async_extent->nr_pages)) { struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; struct page *p = async_extent->pages[0]; const u64 start = async_extent->start; @@ -1388,7 +1398,7 @@ next_slot: * we fall into common COW way. */ if (!nolock) { - err = btrfs_start_write_no_snapshoting(root); + err = btrfs_start_write_no_snapshotting(root); if (!err) goto out_check; } @@ -1400,12 +1410,12 @@ next_slot: if (csum_exist_in_range(fs_info, disk_bytenr, num_bytes)) { if (!nolock) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); goto out_check; } if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) { if (!nolock) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); goto out_check; } nocow = 1; @@ -1422,7 +1432,7 @@ out_check: if (extent_end <= start) { path->slots[0]++; if (!nolock && nocow) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); goto next_slot; @@ -1445,7 +1455,7 @@ out_check: NULL); if (ret) { if (!nolock && nocow) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1466,7 +1476,7 @@ out_check: BTRFS_ORDERED_PREALLOC); if (IS_ERR(em)) { if (!nolock && nocow) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1506,7 +1516,7 @@ out_check: PAGE_UNLOCK | PAGE_SET_PRIVATE2); if (!nolock && nocow) - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); cur_offset = extent_end; /* @@ -1569,10 +1579,11 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end) /* * extent_io.c call back to do delayed allocation processing */ -static int run_delalloc_range(struct inode *inode, struct page *locked_page, +static int run_delalloc_range(void *private_data, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written) { + struct inode *inode = private_data; int ret; int force_cow = need_force_cow(inode, start, end); @@ -1582,7 +1593,7 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - } else if (!inode_need_compress(inode)) { + } else if (!inode_need_compress(inode, start, end)) { ret = cow_file_range(inode, locked_page, start, end, end, page_started, nr_written, 1, NULL); } else { @@ -1596,9 +1607,10 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, return ret; } -static void btrfs_split_extent_hook(struct inode *inode, +static void btrfs_split_extent_hook(void *private_data, struct extent_state *orig, u64 split) { + struct inode *inode = private_data; u64 size; /* not delalloc, ignore it */ @@ -1633,10 +1645,11 @@ static void btrfs_split_extent_hook(struct inode *inode, * extents, such as when we are doing sequential writes, so we can properly * account for the metadata space we'll need. */ -static void btrfs_merge_extent_hook(struct inode *inode, +static void btrfs_merge_extent_hook(void *private_data, struct extent_state *new, struct extent_state *other) { + struct inode *inode = private_data; u64 new_size, old_size; u32 num_extents; @@ -1736,9 +1749,10 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root, * bytes in this file, and to maintain the list of inodes that * have pending delalloc work to be done. */ -static void btrfs_set_bit_hook(struct inode *inode, +static void btrfs_set_bit_hook(void *private_data, struct extent_state *state, unsigned *bits) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -1766,8 +1780,8 @@ static void btrfs_set_bit_hook(struct inode *inode, if (btrfs_is_testing(fs_info)) return; - __percpu_counter_add(&fs_info->delalloc_bytes, len, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->delalloc_bytes, len, + fs_info->delalloc_batch); spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->delalloc_bytes += len; if (*bits & EXTENT_DEFRAG) @@ -1790,18 +1804,20 @@ static void btrfs_set_bit_hook(struct inode *inode, /* * extent_io.c clear_bit_hook, see set_bit_hook for why */ -static void btrfs_clear_bit_hook(struct btrfs_inode *inode, +static void btrfs_clear_bit_hook(void *private_data, struct extent_state *state, unsigned *bits) { + struct btrfs_inode *inode = BTRFS_I((struct inode *)private_data); struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); u64 len = state->end + 1 - state->start; u32 num_extents = count_max_extents(len); - spin_lock(&inode->lock); - if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) + if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG)) { + spin_lock(&inode->lock); inode->defrag_bytes -= len; - spin_unlock(&inode->lock); + spin_unlock(&inode->lock); + } /* * set_bit and clear bit hooks normally require _irqsave/restore @@ -1840,8 +1856,8 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode, &inode->vfs_inode, state->start, len); - __percpu_counter_add(&fs_info->delalloc_bytes, -len, - fs_info->delalloc_batch); + percpu_counter_add_batch(&fs_info->delalloc_bytes, -len, + fs_info->delalloc_batch); spin_lock(&inode->lock); inode->delalloc_bytes -= len; if (do_list && inode->delalloc_bytes == 0 && @@ -1901,11 +1917,12 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio, +static blk_status_t __btrfs_submit_bio_start(void *private_data, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset) { - int ret = 0; + struct inode *inode = private_data; + blk_status_t ret = 0; ret = btrfs_csum_one_bio(inode, bio, 0, 0); BUG_ON(ret); /* -ENOMEM */ @@ -1920,16 +1937,17 @@ static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio, * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ -static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio, +static blk_status_t __btrfs_submit_bio_done(void *private_data, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int ret; + blk_status_t ret; ret = btrfs_map_bio(fs_info, bio, mirror_num, 1); if (ret) { - bio->bi_error = ret; + bio->bi_status = ret; bio_endio(bio); } return ret; @@ -1939,14 +1957,15 @@ static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio, * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read */ -static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) +static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA; - int ret = 0; + blk_status_t ret = 0; int skip_sum; int async = !atomic_read(&BTRFS_I(inode)->sync_writers); @@ -1976,8 +1995,8 @@ static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) goto mapit; /* we're doing a write, do the async checksumming */ - ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num, - bio_flags, bio_offset, + ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags, + bio_offset, inode, __btrfs_submit_bio_start, __btrfs_submit_bio_done); goto out; @@ -1991,8 +2010,8 @@ mapit: ret = btrfs_map_bio(fs_info, bio, mirror_num, 0); out: - if (ret < 0) { - bio->bi_error = ret; + if (ret) { + bio->bi_status = ret; bio_endio(bio); } return ret; @@ -2035,6 +2054,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work) struct btrfs_writepage_fixup *fixup; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; struct page *page; struct inode *inode; u64 page_start; @@ -2072,7 +2092,7 @@ again: goto again; } - ret = btrfs_delalloc_reserve_space(inode, page_start, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, PAGE_SIZE); if (ret) { mapping_set_error(page->mapping, ret); @@ -2092,6 +2112,7 @@ out_page: unlock_page(page); put_page(page); kfree(fixup); + extent_changeset_free(data_reserved); } /* @@ -2143,6 +2164,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_key ins; + u64 qg_released; int extent_inserted = 0; int ret; @@ -2198,13 +2220,17 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans, ins.objectid = disk_bytenr; ins.offset = disk_num_bytes; ins.type = BTRFS_EXTENT_ITEM_KEY; - ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid, - btrfs_ino(BTRFS_I(inode)), file_pos, ram_bytes, &ins); + /* * Release the reserved range from inode dirty range map, as it is * already moved into delayed_ref_head */ - btrfs_qgroup_release_data(inode, file_pos, ram_bytes); + ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes); + if (ret < 0) + goto out; + qg_released = ret; + ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid, + btrfs_ino(BTRFS_I(inode)), file_pos, qg_released, &ins); out: btrfs_free_path(path); @@ -2926,7 +2952,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) * space for NOCOW range. * As NOCOW won't cause a new delayed ref, just free the space */ - btrfs_qgroup_free_data(inode, ordered_extent->file_offset, + btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset, ordered_extent->len); btrfs_ordered_update_i_size(inode, 0, ordered_extent); if (nolock) @@ -3151,8 +3177,6 @@ zeroit: memset(kaddr + pgoff, 1, len); flush_dcache_page(page); kunmap_atomic(kaddr); - if (csum_expected == 0) - return 0; return -EIO; } @@ -4762,6 +4786,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; char *kaddr; u32 blocksize = fs_info->sectorsize; pgoff_t index = from >> PAGE_SHIFT; @@ -4776,7 +4801,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, (!len || ((len & (blocksize - 1)) == 0))) goto out; - ret = btrfs_delalloc_reserve_space(inode, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, round_down(from, blocksize), blocksize); if (ret) goto out; @@ -4784,7 +4809,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, again: page = find_or_create_page(mapping, index, mask); if (!page) { - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, data_reserved, round_down(from, blocksize), blocksize); ret = -ENOMEM; @@ -4856,11 +4881,12 @@ again: out_unlock: if (ret) - btrfs_delalloc_release_space(inode, block_start, + btrfs_delalloc_release_space(inode, data_reserved, block_start, blocksize); unlock_page(page); put_page(page); out: + extent_changeset_free(data_reserved); return ret; } @@ -5045,7 +5071,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) if (newsize > oldsize) { /* - * Don't do an expanding truncate while snapshoting is ongoing. + * Don't do an expanding truncate while snapshotting is ongoing. * This is to ensure the snapshot captures a fully consistent * state of this file - if the snapshot captures this expanding * truncation, it must capture all writes that happened before @@ -5054,13 +5080,13 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) btrfs_wait_for_snapshot_creation(root); ret = btrfs_cont_expand(inode, oldsize, newsize); if (ret) { - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); return ret; } trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); return PTR_ERR(trans); } @@ -5068,7 +5094,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL); pagecache_isize_extended(inode, oldsize, newsize); ret = btrfs_update_inode(trans, root, inode); - btrfs_end_write_no_snapshoting(root); + btrfs_end_write_no_snapshotting(root); btrfs_end_transaction(trans); } else { @@ -5255,7 +5281,7 @@ static void evict_inode_truncate_pages(struct inode *inode) * Note, end is the bytenr of last byte, so we need + 1 here. */ if (state->state & EXTENT_DELALLOC) - btrfs_qgroup_free_data(inode, start, end - start + 1); + btrfs_qgroup_free_data(inode, NULL, start, end - start + 1); clear_extent_bit(io_tree, start, end, EXTENT_LOCKED | EXTENT_DIRTY | @@ -5807,7 +5833,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) if (!IS_ERR(inode) && root != sub_root) { down_read(&fs_info->cleanup_work_sem); - if (!(inode->i_sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(inode->i_sb)) ret = btrfs_orphan_cleanup(sub_root); up_read(&fs_info->cleanup_work_sem); if (ret) { @@ -5863,26 +5889,74 @@ unsigned char btrfs_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; +/* + * All this infrastructure exists because dir_emit can fault, and we are holding + * the tree lock when doing readdir. For now just allocate a buffer and copy + * our information into that, and then dir_emit from the buffer. This is + * similar to what NFS does, only we don't keep the buffer around in pagecache + * because I'm afraid I'll mess that up. Long term we need to make filldir do + * copy_to_user_inatomic so we don't have to worry about page faulting under the + * tree lock. + */ +static int btrfs_opendir(struct inode *inode, struct file *file) +{ + struct btrfs_file_private *private; + + private = kzalloc(sizeof(struct btrfs_file_private), GFP_KERNEL); + if (!private) + return -ENOMEM; + private->filldir_buf = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!private->filldir_buf) { + kfree(private); + return -ENOMEM; + } + file->private_data = private; + return 0; +} + +struct dir_entry { + u64 ino; + u64 offset; + unsigned type; + int name_len; +}; + +static int btrfs_filldir(void *addr, int entries, struct dir_context *ctx) +{ + while (entries--) { + struct dir_entry *entry = addr; + char *name = (char *)(entry + 1); + + ctx->pos = entry->offset; + if (!dir_emit(ctx, name, entry->name_len, entry->ino, + entry->type)) + return 1; + addr += sizeof(struct dir_entry) + entry->name_len; + ctx->pos++; + } + return 0; +} + static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) { struct inode *inode = file_inode(file); struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_item *item; + struct btrfs_file_private *private = file->private_data; struct btrfs_dir_item *di; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_path *path; + void *addr; struct list_head ins_list; struct list_head del_list; int ret; struct extent_buffer *leaf; int slot; - unsigned char d_type; - int over = 0; - char tmp_name[32]; char *name_ptr; int name_len; + int entries = 0; + int total_len = 0; bool put = false; struct btrfs_key location; @@ -5893,12 +5967,14 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (!path) return -ENOMEM; + addr = private->filldir_buf; path->reada = READA_FORWARD; INIT_LIST_HEAD(&ins_list); INIT_LIST_HEAD(&del_list); put = btrfs_readdir_get_delayed_items(inode, &ins_list, &del_list); +again: key.type = BTRFS_DIR_INDEX_KEY; key.offset = ctx->pos; key.objectid = btrfs_ino(BTRFS_I(inode)); @@ -5908,6 +5984,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) goto err; while (1) { + struct dir_entry *entry; + leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { @@ -5919,7 +5997,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) continue; } - item = btrfs_item_nr(slot); btrfs_item_key_to_cpu(leaf, &found_key, slot); if (found_key.objectid != key.objectid) @@ -5930,41 +6007,43 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) goto next; if (btrfs_should_delete_dir_index(&del_list, found_key.offset)) goto next; - - ctx->pos = found_key.offset; - di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item); - if (verify_dir_item(fs_info, leaf, di)) + if (verify_dir_item(fs_info, leaf, slot, di)) goto next; name_len = btrfs_dir_name_len(leaf, di); - if (name_len <= sizeof(tmp_name)) { - name_ptr = tmp_name; - } else { - name_ptr = kmalloc(name_len, GFP_KERNEL); - if (!name_ptr) { - ret = -ENOMEM; - goto err; - } + if ((total_len + sizeof(struct dir_entry) + name_len) >= + PAGE_SIZE) { + btrfs_release_path(path); + ret = btrfs_filldir(private->filldir_buf, entries, ctx); + if (ret) + goto nopos; + addr = private->filldir_buf; + entries = 0; + total_len = 0; + goto again; } + + entry = addr; + entry->name_len = name_len; + name_ptr = (char *)(entry + 1); read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1), name_len); - - d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)]; + entry->type = btrfs_filetype_table[btrfs_dir_type(leaf, di)]; btrfs_dir_item_key_to_cpu(leaf, di, &location); - - over = !dir_emit(ctx, name_ptr, name_len, location.objectid, - d_type); - - if (name_ptr != tmp_name) - kfree(name_ptr); - - if (over) - goto nopos; - ctx->pos++; + entry->ino = location.objectid; + entry->offset = found_key.offset; + entries++; + addr += sizeof(struct dir_entry) + name_len; + total_len += sizeof(struct dir_entry) + name_len; next: path->slots[0]++; } + btrfs_release_path(path); + + ret = btrfs_filldir(private->filldir_buf, entries, ctx); + if (ret) + goto nopos; ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); if (ret) @@ -6177,6 +6256,37 @@ static int btrfs_insert_inode_locked(struct inode *inode) btrfs_find_actor, &args); } +/* + * Inherit flags from the parent inode. + * + * Currently only the compression flags and the cow flags are inherited. + */ +static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) +{ + unsigned int flags; + + if (!dir) + return; + + flags = BTRFS_I(dir)->flags; + + if (flags & BTRFS_INODE_NOCOMPRESS) { + BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS; + BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; + } else if (flags & BTRFS_INODE_COMPRESS) { + BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS; + BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS; + } + + if (flags & BTRFS_INODE_NODATACOW) { + BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW; + if (S_ISREG(inode->i_mode)) + BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM; + } + + btrfs_update_iflags(inode); +} + static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *dir, @@ -7480,7 +7590,7 @@ out: bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) { struct radix_tree_root *root = &inode->i_mapping->page_tree; - int found = false; + bool found = false; void **pagep = NULL; struct page *page = NULL; unsigned long start_idx; @@ -7916,11 +8026,12 @@ err: return ret; } -static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio, - int mirror_num) +static inline blk_status_t submit_dio_repair_bio(struct inode *inode, + struct bio *bio, + int mirror_num) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int ret; + blk_status_t ret; BUG_ON(bio_op(bio) == REQ_OP_WRITE); @@ -7972,56 +8083,56 @@ static int btrfs_check_dio_repairable(struct inode *inode, return 1; } -static int dio_read_error(struct inode *inode, struct bio *failed_bio, - struct page *page, unsigned int pgoff, - u64 start, u64 end, int failed_mirror, - bio_end_io_t *repair_endio, void *repair_arg) +static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio, + struct page *page, unsigned int pgoff, + u64 start, u64 end, int failed_mirror, + bio_end_io_t *repair_endio, void *repair_arg) { struct io_failure_record *failrec; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; struct bio *bio; int isector; - int read_mode = 0; + unsigned int read_mode = 0; + int segs; int ret; + blk_status_t status; BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); ret = btrfs_get_io_failure_record(inode, start, end, &failrec); if (ret) - return ret; + return errno_to_blk_status(ret); ret = btrfs_check_dio_repairable(inode, failed_bio, failrec, failed_mirror); if (!ret) { - free_io_failure(BTRFS_I(inode), failrec); - return -EIO; + free_io_failure(failure_tree, io_tree, failrec); + return BLK_STS_IOERR; } - if ((failed_bio->bi_vcnt > 1) - || (failed_bio->bi_io_vec->bv_len - > btrfs_inode_sectorsize(inode))) + segs = bio_segments(failed_bio); + if (segs > 1 || + (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode))) read_mode |= REQ_FAILFAST_DEV; isector = start - btrfs_io_bio(failed_bio)->logical; isector >>= inode->i_sb->s_blocksize_bits; bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page, pgoff, isector, repair_endio, repair_arg); - if (!bio) { - free_io_failure(BTRFS_I(inode), failrec); - return -EIO; - } bio_set_op_attrs(bio, REQ_OP_READ, read_mode); btrfs_debug(BTRFS_I(inode)->root->fs_info, - "Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n", + "repair DIO read error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d", read_mode, failrec->this_mirror, failrec->in_validation); - ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror); - if (ret) { - free_io_failure(BTRFS_I(inode), failrec); + status = submit_dio_repair_bio(inode, bio, failrec->this_mirror); + if (status) { + free_io_failure(failure_tree, io_tree, failrec); bio_put(bio); } - return ret; + return status; } struct btrfs_retry_complete { @@ -8034,66 +8145,77 @@ struct btrfs_retry_complete { static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; + struct inode *inode = done->inode; struct bio_vec *bvec; + struct extent_io_tree *io_tree, *failure_tree; int i; - if (bio->bi_error) + if (bio->bi_status) goto end; ASSERT(bio->bi_vcnt == 1); - ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); + io_tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; + ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode)); done->uptodate = 1; + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) - clean_io_failure(BTRFS_I(done->inode), done->start, - bvec->bv_page, 0); + clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree, + io_tree, done->start, bvec->bv_page, + btrfs_ino(BTRFS_I(inode)), 0); end: complete(&done->done); bio_put(bio); } -static int __btrfs_correct_data_nocsum(struct inode *inode, - struct btrfs_io_bio *io_bio) +static blk_status_t __btrfs_correct_data_nocsum(struct inode *inode, + struct btrfs_io_bio *io_bio) { struct btrfs_fs_info *fs_info; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_retry_complete done; u64 start; unsigned int pgoff; u32 sectorsize; int nr_sectors; - int i; - int ret; + blk_status_t ret; + blk_status_t err = BLK_STS_OK; fs_info = BTRFS_I(inode)->root->fs_info; sectorsize = fs_info->sectorsize; start = io_bio->logical; done.inode = inode; + io_bio->bio.bi_iter = io_bio->iter; - bio_for_each_segment_all(bvec, &io_bio->bio, i) { - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); - pgoff = bvec->bv_offset; + bio_for_each_segment(bvec, &io_bio->bio, iter) { + nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); + pgoff = bvec.bv_offset; next_block_or_try_again: done.uptodate = 0; done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, + ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page, pgoff, start, start + sectorsize - 1, io_bio->mirror_num, btrfs_retry_endio_nocsum, &done); - if (ret) - return ret; + if (ret) { + err = ret; + goto next; + } - wait_for_completion(&done.done); + wait_for_completion_io(&done.done); if (!done.uptodate) { /* We might have another mirror, so try again */ goto next_block_or_try_again; } +next: start += sectorsize; nr_sectors--; @@ -8104,19 +8226,21 @@ next_block_or_try_again: } } - return 0; + return err; } static void btrfs_retry_endio(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); + struct extent_io_tree *io_tree, *failure_tree; + struct inode *inode = done->inode; struct bio_vec *bvec; int uptodate; int ret; int i; - if (bio->bi_error) + if (bio->bi_status) goto end; uptodate = 1; @@ -8124,13 +8248,20 @@ static void btrfs_retry_endio(struct bio *bio) ASSERT(bio->bi_vcnt == 1); ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode)); + io_tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; + + ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_segment_all(bvec, bio, i) { - ret = __readpage_endio_check(done->inode, io_bio, i, - bvec->bv_page, bvec->bv_offset, - done->start, bvec->bv_len); + ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page, + bvec->bv_offset, done->start, + bvec->bv_len); if (!ret) - clean_io_failure(BTRFS_I(done->inode), done->start, - bvec->bv_page, bvec->bv_offset); + clean_io_failure(BTRFS_I(inode)->root->fs_info, + failure_tree, io_tree, done->start, + bvec->bv_page, + btrfs_ino(BTRFS_I(inode)), + bvec->bv_offset); else uptodate = 0; } @@ -8141,11 +8272,12 @@ end: bio_put(bio); } -static int __btrfs_subio_endio_read(struct inode *inode, - struct btrfs_io_bio *io_bio, int err) +static blk_status_t __btrfs_subio_endio_read(struct inode *inode, + struct btrfs_io_bio *io_bio, blk_status_t err) { struct btrfs_fs_info *fs_info; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_retry_complete done; u64 start; u64 offset = 0; @@ -8153,42 +8285,45 @@ static int __btrfs_subio_endio_read(struct inode *inode, int nr_sectors; unsigned int pgoff; int csum_pos; - int i; + bool uptodate = (err == 0); int ret; + blk_status_t status; fs_info = BTRFS_I(inode)->root->fs_info; sectorsize = fs_info->sectorsize; - err = 0; + err = BLK_STS_OK; start = io_bio->logical; done.inode = inode; + io_bio->bio.bi_iter = io_bio->iter; - bio_for_each_segment_all(bvec, &io_bio->bio, i) { - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); + bio_for_each_segment(bvec, &io_bio->bio, iter) { + nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len); - pgoff = bvec->bv_offset; + pgoff = bvec.bv_offset; next_block: - csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset); - ret = __readpage_endio_check(inode, io_bio, csum_pos, - bvec->bv_page, pgoff, start, - sectorsize); - if (likely(!ret)) - goto next; + if (uptodate) { + csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset); + ret = __readpage_endio_check(inode, io_bio, csum_pos, + bvec.bv_page, pgoff, start, sectorsize); + if (likely(!ret)) + goto next; + } try_again: done.uptodate = 0; done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page, - pgoff, start, start + sectorsize - 1, - io_bio->mirror_num, - btrfs_retry_endio, &done); - if (ret) { - err = ret; + status = dio_read_error(inode, &io_bio->bio, bvec.bv_page, + pgoff, start, start + sectorsize - 1, + io_bio->mirror_num, btrfs_retry_endio, + &done); + if (status) { + err = status; goto next; } - wait_for_completion(&done.done); + wait_for_completion_io(&done.done); if (!done.uptodate) { /* We might have another mirror, so try again */ @@ -8211,8 +8346,8 @@ next: return err; } -static int btrfs_subio_endio_read(struct inode *inode, - struct btrfs_io_bio *io_bio, int err) +static blk_status_t btrfs_subio_endio_read(struct inode *inode, + struct btrfs_io_bio *io_bio, blk_status_t err) { bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; @@ -8220,7 +8355,7 @@ static int btrfs_subio_endio_read(struct inode *inode, if (unlikely(err)) return __btrfs_correct_data_nocsum(inode, io_bio); else - return 0; + return BLK_STS_OK; } else { return __btrfs_subio_endio_read(inode, io_bio, err); } @@ -8232,7 +8367,7 @@ static void btrfs_endio_direct_read(struct bio *bio) struct inode *inode = dip->inode; struct bio *dio_bio; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - int err = bio->bi_error; + blk_status_t err = bio->bi_status; if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); @@ -8243,11 +8378,11 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); - dio_bio->bi_error = bio->bi_error; - dio_end_io(dio_bio, bio->bi_error); + dio_bio->bi_status = err; + dio_end_io(dio_bio); if (io_bio->end_io) - io_bio->end_io(io_bio, err); + io_bio->end_io(io_bio, blk_status_to_errno(err)); bio_put(bio); } @@ -8261,6 +8396,7 @@ static void __endio_write_update_ordered(struct inode *inode, btrfs_work_func_t func; u64 ordered_offset = offset; u64 ordered_bytes = bytes; + u64 last_offset; int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { @@ -8272,6 +8408,7 @@ static void __endio_write_update_ordered(struct inode *inode, } again: + last_offset = ordered_offset; ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, ordered_bytes, @@ -8283,6 +8420,12 @@ again: btrfs_queue_work(wq, &ordered->work); out_test: /* + * If btrfs_dec_test_ordered_pending does not find any ordered extent + * in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; + /* * our bio might span multiple ordered extents. If we haven't * completed the accounting for the whole dio, go back and try again */ @@ -8299,20 +8442,21 @@ static void btrfs_endio_direct_write(struct bio *bio) struct bio *dio_bio = dip->dio_bio; __endio_write_update_ordered(dip->inode, dip->logical_offset, - dip->bytes, !bio->bi_error); + dip->bytes, !bio->bi_status); kfree(dip); - dio_bio->bi_error = bio->bi_error; - dio_end_io(dio_bio, bio->bi_error); + dio_bio->bi_status = bio->bi_status; + dio_end_io(dio_bio); bio_put(bio); } -static int __btrfs_submit_bio_start_direct_io(struct inode *inode, +static blk_status_t __btrfs_submit_bio_start_direct_io(void *private_data, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 offset) { - int ret; + struct inode *inode = private_data; + blk_status_t ret; ret = btrfs_csum_one_bio(inode, bio, offset, 1); BUG_ON(ret); /* -ENOMEM */ return 0; @@ -8321,7 +8465,7 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode, static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; - int err = bio->bi_error; + blk_status_t err = bio->bi_status; if (err) btrfs_warn(BTRFS_I(dip->inode)->root->fs_info, @@ -8351,31 +8495,21 @@ static void btrfs_end_dio_bio(struct bio *bio) if (dip->errors) { bio_io_error(dip->orig_bio); } else { - dip->dio_bio->bi_error = 0; + dip->dio_bio->bi_status = 0; bio_endio(dip->orig_bio); } out: bio_put(bio); } -static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, - u64 first_sector, gfp_t gfp_flags) -{ - struct bio *bio; - bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags); - if (bio) - bio_associate_current(bio); - return bio; -} - -static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode, +static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, struct btrfs_dio_private *dip, struct bio *bio, u64 file_offset) { struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio); - int ret; + blk_status_t ret; /* * We load all the csum data we need when we submit @@ -8399,14 +8533,14 @@ static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode, return 0; } -static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, - u64 file_offset, int skip_sum, - int async_submit) +static inline blk_status_t +__btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, u64 file_offset, + int async_submit) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_private *dip = bio->bi_private; bool write = bio_op(bio) == REQ_OP_WRITE; - int ret; + blk_status_t ret; if (async_submit) async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers); @@ -8419,12 +8553,12 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, goto err; } - if (skip_sum) + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) goto map; if (write && async_submit) { - ret = btrfs_wq_submit_bio(fs_info, inode, bio, 0, 0, - file_offset, + ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0, + file_offset, inode, __btrfs_submit_bio_start_direct_io, __btrfs_submit_bio_done); goto err; @@ -8449,113 +8583,92 @@ err: return ret; } -static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, - int skip_sum) +static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip) { struct inode *inode = dip->inode; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_root *root = BTRFS_I(inode)->root; struct bio *bio; struct bio *orig_bio = dip->orig_bio; - struct bio_vec *bvec; u64 start_sector = orig_bio->bi_iter.bi_sector; u64 file_offset = dip->logical_offset; - u64 submit_len = 0; u64 map_length; - u32 blocksize = fs_info->sectorsize; int async_submit = 0; - int nr_sectors; + u64 submit_len; + int clone_offset = 0; + int clone_len; int ret; - int i, j; + blk_status_t status; map_length = orig_bio->bi_iter.bi_size; + submit_len = map_length; ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9, &map_length, NULL, 0); if (ret) return -EIO; - if (map_length >= orig_bio->bi_iter.bi_size) { + if (map_length >= submit_len) { bio = orig_bio; dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED; goto submit; } /* async crcs make it difficult to collect full stripe writes. */ - if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_RAID56_MASK) + if (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK) async_submit = 0; else async_submit = 1; - bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS); - if (!bio) - return -ENOMEM; - - bio->bi_opf = orig_bio->bi_opf; - bio->bi_private = dip; - bio->bi_end_io = btrfs_end_dio_bio; - btrfs_io_bio(bio)->logical = file_offset; + /* bio split */ + ASSERT(map_length <= INT_MAX); atomic_inc(&dip->pending_bios); + do { + clone_len = min_t(int, submit_len, map_length); - bio_for_each_segment_all(bvec, orig_bio, j) { - nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len); - i = 0; -next_block: - if (unlikely(map_length < submit_len + blocksize || - bio_add_page(bio, bvec->bv_page, blocksize, - bvec->bv_offset + (i * blocksize)) < blocksize)) { - /* - * inc the count before we submit the bio so - * we know the end IO handler won't happen before - * we inc the count. Otherwise, the dip might get freed - * before we're done setting it up - */ - atomic_inc(&dip->pending_bios); - ret = __btrfs_submit_dio_bio(bio, inode, - file_offset, skip_sum, - async_submit); - if (ret) { - bio_put(bio); - atomic_dec(&dip->pending_bios); - goto out_err; - } - - start_sector += submit_len >> 9; - file_offset += submit_len; - - submit_len = 0; + /* + * This will never fail as it's passing GPF_NOFS and + * the allocation is backed by btrfs_bioset. + */ + bio = btrfs_bio_clone_partial(orig_bio, clone_offset, + clone_len); + bio->bi_private = dip; + bio->bi_end_io = btrfs_end_dio_bio; + btrfs_io_bio(bio)->logical = file_offset; + + ASSERT(submit_len >= clone_len); + submit_len -= clone_len; + if (submit_len == 0) + break; - bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, - start_sector, GFP_NOFS); - if (!bio) - goto out_err; - bio->bi_opf = orig_bio->bi_opf; - bio->bi_private = dip; - bio->bi_end_io = btrfs_end_dio_bio; - btrfs_io_bio(bio)->logical = file_offset; + /* + * Increase the count before we submit the bio so we know + * the end IO handler won't happen before we increase the + * count. Otherwise, the dip might get freed before we're + * done setting it up. + */ + atomic_inc(&dip->pending_bios); + + status = __btrfs_submit_dio_bio(bio, inode, file_offset, + async_submit); + if (status) { + bio_put(bio); + atomic_dec(&dip->pending_bios); + goto out_err; + } - map_length = orig_bio->bi_iter.bi_size; - ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), - start_sector << 9, - &map_length, NULL, 0); - if (ret) { - bio_put(bio); - goto out_err; - } + clone_offset += clone_len; + start_sector += clone_len >> 9; + file_offset += clone_len; - goto next_block; - } else { - submit_len += blocksize; - if (--nr_sectors) { - i++; - goto next_block; - } - } - } + map_length = submit_len; + ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), + start_sector << 9, &map_length, NULL, 0); + if (ret) + goto out_err; + } while (submit_len > 0); submit: - ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, - async_submit); - if (!ret) + status = __btrfs_submit_dio_bio(bio, inode, file_offset, async_submit); + if (!status) return 0; bio_put(bio); @@ -8577,19 +8690,12 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, loff_t file_offset) { struct btrfs_dio_private *dip = NULL; - struct bio *io_bio = NULL; - struct btrfs_io_bio *btrfs_bio; - int skip_sum; + struct bio *bio = NULL; + struct btrfs_io_bio *io_bio; bool write = (bio_op(dio_bio) == REQ_OP_WRITE); int ret = 0; - skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM; - - io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS); - if (!io_bio) { - ret = -ENOMEM; - goto free_ordered; - } + bio = btrfs_bio_clone(dio_bio); dip = kzalloc(sizeof(*dip), GFP_NOFS); if (!dip) { @@ -8602,17 +8708,17 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, dip->logical_offset = file_offset; dip->bytes = dio_bio->bi_iter.bi_size; dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9; - io_bio->bi_private = dip; - dip->orig_bio = io_bio; + bio->bi_private = dip; + dip->orig_bio = bio; dip->dio_bio = dio_bio; atomic_set(&dip->pending_bios, 0); - btrfs_bio = btrfs_io_bio(io_bio); - btrfs_bio->logical = file_offset; + io_bio = btrfs_io_bio(bio); + io_bio->logical = file_offset; if (write) { - io_bio->bi_end_io = btrfs_endio_direct_write; + bio->bi_end_io = btrfs_endio_direct_write; } else { - io_bio->bi_end_io = btrfs_endio_direct_read; + bio->bi_end_io = btrfs_endio_direct_read; dip->subio_endio = btrfs_subio_endio_read; } @@ -8631,12 +8737,12 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode, dio_data->unsubmitted_oe_range_end; } - ret = btrfs_submit_direct_hook(dip, skip_sum); + ret = btrfs_submit_direct_hook(dip); if (!ret) return; - if (btrfs_bio->end_io) - btrfs_bio->end_io(btrfs_bio, ret); + if (io_bio->end_io) + io_bio->end_io(io_bio, ret); free_ordered: /* @@ -8648,16 +8754,15 @@ free_ordered: * same as btrfs_endio_direct_[write|read] because we can't call these * callbacks - they require an allocated dip and a clone of dio_bio. */ - if (io_bio && dip) { - io_bio->bi_error = -EIO; - bio_endio(io_bio); + if (bio && dip) { + bio_io_error(bio); /* - * The end io callbacks free our dip, do the final put on io_bio + * The end io callbacks free our dip, do the final put on bio * and all the cleanup and final put for dio_bio (through * dio_end_io()). */ dip = NULL; - io_bio = NULL; + bio = NULL; } else { if (write) __endio_write_update_ordered(inode, @@ -8668,15 +8773,15 @@ free_ordered: unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, file_offset + dio_bio->bi_iter.bi_size - 1); - dio_bio->bi_error = -EIO; + dio_bio->bi_status = BLK_STS_IOERR; /* * Releases and cleans up our dio_bio, no need to bio_put() * nor bio_endio()/bio_io_error() against dio_bio. */ - dio_end_io(dio_bio, ret); + dio_end_io(dio_bio); } - if (io_bio) - bio_put(io_bio); + if (bio) + bio_put(bio); kfree(dip); } @@ -8720,6 +8825,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = file->f_mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_data dio_data = { 0 }; + struct extent_changeset *data_reserved = NULL; loff_t offset = iocb->ki_pos; size_t count = 0; int flags = 0; @@ -8731,7 +8837,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return 0; inode_dio_begin(inode); - smp_mb__after_atomic(); /* * The generic stuff only does filemap_write_and_wait_range, which @@ -8755,8 +8860,12 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.overwrite = 1; inode_unlock(inode); relock = true; + } else if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; } - ret = btrfs_delalloc_reserve_space(inode, offset, count); + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, + offset, count); if (ret) goto out; dio_data.outstanding_extents = count_max_extents(count); @@ -8788,8 +8897,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) - btrfs_delalloc_release_space(inode, offset, - dio_data.reserve); + btrfs_delalloc_release_space(inode, data_reserved, + offset, dio_data.reserve); /* * On error we might have left some ordered extents * without submitting corresponding bios for them, so @@ -8804,8 +8913,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.unsubmitted_oe_range_start, false); } else if (ret >= 0 && (size_t)ret < count) - btrfs_delalloc_release_space(inode, offset, - count - (size_t)ret); + btrfs_delalloc_release_space(inode, data_reserved, + offset, count - (size_t)ret); } out: if (wakeup) @@ -8813,6 +8922,7 @@ out: if (relock) inode_lock(inode); + extent_changeset_free(data_reserved); return ret; } @@ -9003,7 +9113,7 @@ again: * free the entire extent. */ if (PageDirty(page)) - btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); + btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | @@ -9045,6 +9155,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_changeset *data_reserved = NULL; char *kaddr; unsigned long zero_start; loff_t size; @@ -9070,7 +9181,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) * end up waiting indefinitely to get a lock on the page currently * being processed by btrfs_page_mkwrite() function. */ - ret = btrfs_delalloc_reserve_space(inode, page_start, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, reserved_space); if (!ret) { ret = file_update_time(vmf->vma->vm_file); @@ -9124,8 +9235,8 @@ again: spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, page_start, - PAGE_SIZE - reserved_space); + btrfs_delalloc_release_space(inode, data_reserved, + page_start, PAGE_SIZE - reserved_space); } } @@ -9176,13 +9287,16 @@ again: out_unlock: if (!ret) { sb_end_pagefault(inode->i_sb); + extent_changeset_free(data_reserved); return VM_FAULT_LOCKED; } unlock_page(page); out: - btrfs_delalloc_release_space(inode, page_start, reserved_space); + btrfs_delalloc_release_space(inode, data_reserved, page_start, + reserved_space); out_noreserve: sb_end_pagefault(inode->i_sb); + extent_changeset_free(data_reserved); return ret; } @@ -9395,7 +9509,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->reserved_extents = 0; ei->runtime_flags = 0; - ei->force_compress = BTRFS_COMPRESS_NONE; + ei->prop_compress = BTRFS_COMPRESS_NONE; + ei->defrag_compress = BTRFS_COMPRESS_NONE; ei->delayed_node = NULL; @@ -9404,8 +9519,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) inode = &ei->vfs_inode; extent_map_tree_init(&ei->extent_tree); - extent_io_tree_init(&ei->io_tree, &inode->i_data); - extent_io_tree_init(&ei->io_failure_tree, &inode->i_data); + extent_io_tree_init(&ei->io_tree, inode); + extent_io_tree_init(&ei->io_failure_tree, inode); ei->io_tree.track_uptodate = 1; ei->io_failure_tree.track_uptodate = 1; atomic_set(&ei->sync_writers, 0); @@ -9514,7 +9629,6 @@ void btrfs_destroy_cachep(void) rcu_barrier(); kmem_cache_destroy(btrfs_inode_cachep); kmem_cache_destroy(btrfs_trans_handle_cachep); - kmem_cache_destroy(btrfs_transaction_cachep); kmem_cache_destroy(btrfs_path_cachep); kmem_cache_destroy(btrfs_free_space_cachep); } @@ -9534,12 +9648,6 @@ int btrfs_init_cachep(void) if (!btrfs_trans_handle_cachep) goto fail; - btrfs_transaction_cachep = kmem_cache_create("btrfs_transaction", - sizeof(struct btrfs_transaction), 0, - SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL); - if (!btrfs_transaction_cachep) - goto fail; - btrfs_path_cachep = kmem_cache_create("btrfs_path", sizeof(struct btrfs_path), 0, SLAB_MEM_SPREAD, NULL); @@ -9564,6 +9672,24 @@ static int btrfs_getattr(const struct path *path, struct kstat *stat, u64 delalloc_bytes; struct inode *inode = d_inode(path->dentry); u32 blocksize = inode->i_sb->s_blocksize; + u32 bi_flags = BTRFS_I(inode)->flags; + + stat->result_mask |= STATX_BTIME; + stat->btime.tv_sec = BTRFS_I(inode)->i_otime.tv_sec; + stat->btime.tv_nsec = BTRFS_I(inode)->i_otime.tv_nsec; + if (bi_flags & BTRFS_INODE_APPEND) + stat->attributes |= STATX_ATTR_APPEND; + if (bi_flags & BTRFS_INODE_COMPRESS) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (bi_flags & BTRFS_INODE_IMMUTABLE) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (bi_flags & BTRFS_INODE_NODUMP) + stat->attributes |= STATX_ATTR_NODUMP; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); generic_fillattr(inode, stat); stat->dev = BTRFS_I(inode)->root->anon_dev; @@ -10538,7 +10664,7 @@ next: btrfs_end_transaction(trans); } if (cur_offset < end) - btrfs_free_reserved_data_space(inode, cur_offset, + btrfs_free_reserved_data_space(inode, NULL, cur_offset, end - cur_offset + 1); return ret; } @@ -10659,6 +10785,42 @@ static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror) return -EAGAIN; } +static struct btrfs_fs_info *iotree_fs_info(void *private_data) +{ + struct inode *inode = private_data; + return btrfs_sb(inode->i_sb); +} + +static void btrfs_check_extent_io_range(void *private_data, const char *caller, + u64 start, u64 end) +{ + struct inode *inode = private_data; + u64 isize; + + isize = i_size_read(inode); + if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) { + btrfs_debug_rl(BTRFS_I(inode)->root->fs_info, + "%s: ino %llu isize %llu odd range [%llu,%llu]", + caller, btrfs_ino(BTRFS_I(inode)), isize, start, end); + } +} + +void btrfs_set_range_writeback(void *private_data, u64 start, u64 end) +{ + struct inode *inode = private_data; + unsigned long index = start >> PAGE_SHIFT; + unsigned long end_index = end >> PAGE_SHIFT; + struct page *page; + + while (index <= end_index) { + page = find_get_page(inode->i_mapping, index); + ASSERT(page); /* Pages should be in the extent_io_tree */ + set_page_writeback(page); + put_page(page); + index++; + } +} + static const struct inode_operations btrfs_dir_inode_operations = { .getattr = btrfs_getattr, .lookup = btrfs_lookup, @@ -10688,6 +10850,7 @@ static const struct file_operations btrfs_dir_file_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .iterate_shared = btrfs_real_readdir, + .open = btrfs_opendir, .unlocked_ioctl = btrfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_compat_ioctl, @@ -10702,6 +10865,8 @@ static const struct extent_io_ops btrfs_extent_io_ops = { .readpage_end_io_hook = btrfs_readpage_end_io_hook, .merge_bio_hook = btrfs_merge_bio_hook, .readpage_io_failed_hook = btrfs_readpage_io_failed_hook, + .tree_fs_info = iotree_fs_info, + .set_range_writeback = btrfs_set_range_writeback, /* optional callbacks */ .fill_delalloc = run_delalloc_range, @@ -10711,6 +10876,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = { .clear_bit_hook = btrfs_clear_bit_hook, .merge_extent_hook = btrfs_merge_extent_hook, .split_extent_hook = btrfs_split_extent_hook, + .check_extent_io_range = btrfs_check_extent_io_range, }; /* diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e176375f374f..6c7a49faf4e0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -37,7 +37,7 @@ #include <linux/bit_spinlock.h> #include <linux/security.h> #include <linux/xattr.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/uuid.h> @@ -156,37 +156,6 @@ void btrfs_update_iflags(struct inode *inode) new_fl); } -/* - * Inherit flags from the parent inode. - * - * Currently only the compression flags and the cow flags are inherited. - */ -void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) -{ - unsigned int flags; - - if (!dir) - return; - - flags = BTRFS_I(dir)->flags; - - if (flags & BTRFS_INODE_NOCOMPRESS) { - BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS; - BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; - } else if (flags & BTRFS_INODE_COMPRESS) { - BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS; - BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS; - } - - if (flags & BTRFS_INODE_NODATACOW) { - BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW; - if (S_ISREG(inode->i_mode)) - BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM; - } - - btrfs_update_iflags(inode); -} - static int btrfs_ioctl_getflags(struct file *file, void __user *arg) { struct btrfs_inode *ip = BTRFS_I(file_inode(file)); @@ -327,8 +296,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (fs_info->compress_type == BTRFS_COMPRESS_LZO) comp = "lzo"; - else + else if (fs_info->compress_type == BTRFS_COMPRESS_ZLIB) comp = "zlib"; + else + comp = "zstd"; ret = btrfs_set_prop(inode, "btrfs.compression", comp, strlen(comp), 0); if (ret) @@ -638,7 +609,7 @@ fail_free: return ret; } -static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root) +static void btrfs_wait_for_no_snapshotting_writes(struct btrfs_root *root) { s64 writers; DEFINE_WAIT(wait); @@ -681,15 +652,15 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } - atomic_inc(&root->will_be_snapshoted); + atomic_inc(&root->will_be_snapshotted); smp_mb__after_atomic(); - btrfs_wait_for_no_snapshoting_writes(root); + btrfs_wait_for_no_snapshotting_writes(root); ret = btrfs_start_delalloc_inodes(root, 0); if (ret) goto dec_and_free; - btrfs_wait_ordered_extents(root, -1, 0, (u64)-1); + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); btrfs_init_block_rsv(&pending_snapshot->block_rsv, BTRFS_BLOCK_RSV_TEMP); @@ -754,8 +725,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, fail: btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); dec_and_free: - if (atomic_dec_and_test(&root->will_be_snapshoted)) - wake_up_atomic_t(&root->will_be_snapshoted); + if (atomic_dec_and_test(&root->will_be_snapshotted)) + wake_up_atomic_t(&root->will_be_snapshotted); free_pending: kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); @@ -1127,6 +1098,7 @@ static int cluster_pages_for_defrag(struct inode *inode, struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; struct extent_io_tree *tree; + struct extent_changeset *data_reserved = NULL; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); file_end = (isize - 1) >> PAGE_SHIFT; @@ -1135,7 +1107,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); - ret = btrfs_delalloc_reserve_space(inode, + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT); if (ret) @@ -1226,7 +1198,7 @@ again: spin_lock(&BTRFS_I(inode)->lock); BTRFS_I(inode)->outstanding_extents++; spin_unlock(&BTRFS_I(inode)->lock); - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, (page_cnt - i_done) << PAGE_SHIFT); } @@ -1247,15 +1219,17 @@ again: unlock_page(pages[i]); put_page(pages[i]); } + extent_changeset_free(data_reserved); return i_done; out: for (i = 0; i < i_done; i++) { unlock_page(pages[i]); put_page(pages[i]); } - btrfs_delalloc_release_space(inode, + btrfs_delalloc_release_space(inode, data_reserved, start_index << PAGE_SHIFT, page_cnt << PAGE_SHIFT); + extent_changeset_free(data_reserved); return ret; } @@ -1283,6 +1257,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, unsigned long cluster = max_cluster; u64 new_align = ~((u64)SZ_128K - 1); struct page **pages = NULL; + bool do_compress = range->flags & BTRFS_DEFRAG_RANGE_COMPRESS; if (isize == 0) return 0; @@ -1290,7 +1265,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (range->start >= isize) return -EINVAL; - if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) { + if (do_compress) { if (range->compress_type > BTRFS_COMPRESS_TYPES) return -EINVAL; if (range->compress_type) @@ -1301,20 +1276,19 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, extent_thresh = SZ_256K; /* - * if we were not given a file, allocate a readahead - * context + * If we were not given a file, allocate a readahead context. As + * readahead is just an optimization, defrag will work without it so + * we don't error out. */ if (!file) { - ra = kzalloc(sizeof(*ra), GFP_NOFS); - if (!ra) - return -ENOMEM; - file_ra_state_init(ra, inode->i_mapping); + ra = kzalloc(sizeof(*ra), GFP_KERNEL); + if (ra) + file_ra_state_init(ra, inode->i_mapping); } else { ra = &file->f_ra; } - pages = kmalloc_array(max_cluster, sizeof(struct page *), - GFP_NOFS); + pages = kmalloc_array(max_cluster, sizeof(struct page *), GFP_KERNEL); if (!pages) { ret = -ENOMEM; goto out_ra; @@ -1370,8 +1344,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT, extent_thresh, &last_len, &skip, - &defrag_end, range->flags & - BTRFS_DEFRAG_RANGE_COMPRESS)) { + &defrag_end, do_compress)){ unsigned long next; /* * the should_defrag function tells us how much to skip @@ -1392,14 +1365,15 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (i + cluster > ra_index) { ra_index = max(i, ra_index); - btrfs_force_ra(inode->i_mapping, ra, file, ra_index, - cluster); + if (ra) + page_cache_sync_readahead(inode->i_mapping, ra, + file, ra_index, cluster); ra_index += cluster; } inode_lock(inode); - if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) - BTRFS_I(inode)->force_compress = compress_type; + if (do_compress) + BTRFS_I(inode)->defrag_compress = compress_type; ret = cluster_pages_for_defrag(inode, pages, i, cluster); if (ret < 0) { inode_unlock(inode); @@ -1446,7 +1420,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, filemap_flush(inode->i_mapping); } - if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) { + if (do_compress) { /* the filemap_flush will queue IO into the worker threads, but * we have to make sure the IO is actually started and that * ordered extents get created before we return @@ -1463,14 +1437,16 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, if (range->compress_type == BTRFS_COMPRESS_LZO) { btrfs_set_fs_incompat(fs_info, COMPRESS_LZO); + } else if (range->compress_type == BTRFS_COMPRESS_ZSTD) { + btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD); } ret = defrag_count; out_ra: - if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) { + if (do_compress) { inode_lock(inode); - BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE; + BTRFS_I(inode)->defrag_compress = BTRFS_COMPRESS_NONE; inode_unlock(inode); } if (!file) @@ -1597,8 +1573,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, goto out_free; } - new_size = div_u64(new_size, fs_info->sectorsize); - new_size *= fs_info->sectorsize; + new_size = round_down(new_size, fs_info->sectorsize); btrfs_info_in_rcu(fs_info, "new size for %s is %llu", rcu_str_deref(device->name), new_size); @@ -2198,9 +2173,6 @@ static noinline int btrfs_ioctl_tree_search_v2(struct file *file, buf_size = args.buf_size; - if (buf_size < sizeof(struct btrfs_ioctl_search_header)) - return -EOVERFLOW; - /* limit result size to 16MB */ if (buf_size > buf_limit) buf_size = buf_limit; @@ -2801,9 +2773,9 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info, } mutex_unlock(&fs_devices->device_list_mutex); - fi_args->nodesize = fs_info->super_copy->nodesize; - fi_args->sectorsize = fs_info->super_copy->sectorsize; - fi_args->clone_alignment = fs_info->super_copy->sectorsize; + fi_args->nodesize = fs_info->nodesize; + fi_args->sectorsize = fs_info->sectorsize; + fi_args->clone_alignment = fs_info->sectorsize; if (copy_to_user(arg, fi_args, sizeof(*fi_args))) ret = -EFAULT; @@ -3060,7 +3032,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, out: if (ret) btrfs_cmp_data_free(cmp); - return 0; + return ret; } static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp) @@ -3995,15 +3967,35 @@ static long btrfs_ioctl_trans_start(struct file *file) struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans; + struct btrfs_file_private *private; int ret; + static bool warned = false; ret = -EPERM; if (!capable(CAP_SYS_ADMIN)) goto out; + if (!warned) { + btrfs_warn(fs_info, + "Userspace transaction mechanism is considered " + "deprecated and slated to be removed in 4.17. " + "If you have a valid use case please " + "speak up on the mailing list"); + WARN_ON(1); + warned = true; + } + ret = -EINPROGRESS; - if (file->private_data) + private = file->private_data; + if (private && private->trans) goto out; + if (!private) { + private = kzalloc(sizeof(struct btrfs_file_private), + GFP_KERNEL); + if (!private) + return -ENOMEM; + file->private_data = private; + } ret = -EROFS; if (btrfs_root_readonly(root)) @@ -4020,7 +4012,7 @@ static long btrfs_ioctl_trans_start(struct file *file) if (IS_ERR(trans)) goto out_drop; - file->private_data = trans; + private->trans = trans; return 0; out_drop: @@ -4069,6 +4061,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } + if (!is_fstree(new_root->objectid)) { + ret = -ENOENT; + goto out; + } path = btrfs_alloc_path(); if (!path) { @@ -4275,14 +4271,13 @@ long btrfs_ioctl_trans_end(struct file *file) { struct inode *inode = file_inode(file); struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_trans_handle *trans; + struct btrfs_file_private *private = file->private_data; - trans = file->private_data; - if (!trans) + if (!private || !private->trans) return -EINVAL; - file->private_data = NULL; - btrfs_end_transaction(trans); + btrfs_end_transaction(private->trans); + private->trans = NULL; atomic_dec(&root->fs_info->open_ioctl_trans); @@ -4435,7 +4430,7 @@ static long btrfs_ioctl_dev_replace(struct btrfs_fs_info *fs_info, switch (p->cmd) { case BTRFS_IOCTL_DEV_REPLACE_CMD_START: - if (fs_info->sb->s_flags & MS_RDONLY) { + if (sb_rdonly(fs_info->sb)) { ret = -EROFS; goto out; } @@ -4588,7 +4583,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info, out: btrfs_free_path(path); - vfree(inodes); + kvfree(inodes); kfree(loi); return ret; @@ -4897,7 +4892,6 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) goto out; } - /* FIXME: check if the IDs really exist */ if (sa->assign) { ret = btrfs_add_qgroup_relation(trans, fs_info, sa->src, sa->dst); @@ -4956,7 +4950,6 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } - /* FIXME: check if the IDs really exist */ if (sa->create) { ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid); } else { @@ -5010,7 +5003,6 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg) qgroupid = root->root_key.objectid; } - /* FIXME: check if the IDs really exist */ ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim); err = btrfs_end_transaction(trans); diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index f48c8c14dc14..d433e75d489a 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -18,13 +18,14 @@ #include <linux/kernel.h> #include <linux/slab.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/init.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/pagemap.h> #include <linux/bio.h> #include <linux/lzo.h> +#include <linux/refcount.h> #include "compression.h" #define LZO_LEN 4 @@ -40,9 +41,9 @@ static void lzo_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); - vfree(workspace->buf); - vfree(workspace->cbuf); - vfree(workspace->mem); + kvfree(workspace->buf); + kvfree(workspace->cbuf); + kvfree(workspace->mem); kfree(workspace); } @@ -50,13 +51,13 @@ static struct list_head *lzo_alloc_workspace(void) { struct workspace *workspace; - workspace = kzalloc(sizeof(*workspace), GFP_NOFS); + workspace = kzalloc(sizeof(*workspace), GFP_KERNEL); if (!workspace) return ERR_PTR(-ENOMEM); - workspace->mem = vmalloc(LZO1X_MEM_COMPRESS); - workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_SIZE)); - workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_SIZE)); + workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); + workspace->buf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL); + workspace->cbuf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL); if (!workspace->mem || !workspace->buf || !workspace->cbuf) goto fail; @@ -141,7 +142,7 @@ static int lzo_compress_pages(struct list_head *ws, ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf, &out_len, workspace->mem); if (ret != LZO_E_OK) { - pr_debug("BTRFS: deflate in loop returned %d\n", + pr_debug("BTRFS: lzo in loop returned %d\n", ret); ret = -EIO; goto out; @@ -229,8 +230,10 @@ static int lzo_compress_pages(struct list_head *ws, in_len = min(bytes_left, PAGE_SIZE); } - if (tot_out > tot_in) + if (tot_out >= tot_in) { + ret = -E2BIG; goto out; + } /* store the size of all chunks of compressed data */ cpage_out = kmap(pages[0]); @@ -254,16 +257,13 @@ out: return ret; } -static int lzo_decompress_bio(struct list_head *ws, - struct page **pages_in, - u64 disk_start, - struct bio *orig_bio, - size_t srclen) +static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0, ret2; char *data_in; unsigned long page_in_index = 0; + size_t srclen = cb->compressed_len; unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; unsigned long buf_offset = 0; @@ -278,6 +278,9 @@ static int lzo_decompress_bio(struct list_head *ws, unsigned long tot_len; char *buf; bool may_late_unmap, need_unmap; + struct page **pages_in = cb->compressed_pages; + u64 disk_start = cb->start; + struct bio *orig_bio = cb->orig_bio; data_in = kmap(pages_in[0]); tot_len = read_compress_length(data_in); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 7b40e2e7292a..a3aca495e33e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -663,7 +663,7 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work) * wait for all the ordered extents in a root. This is done when balancing * space between drives. */ -int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, +u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len) { struct btrfs_fs_info *fs_info = root->fs_info; @@ -671,7 +671,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, LIST_HEAD(skipped); LIST_HEAD(works); struct btrfs_ordered_extent *ordered, *next; - int count = 0; + u64 count = 0; const u64 range_end = range_start + range_len; mutex_lock(&root->ordered_extent_mutex); @@ -701,7 +701,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, cond_resched(); spin_lock(&root->ordered_extent_lock); - if (nr != -1) + if (nr != U64_MAX) nr--; count++; } @@ -720,13 +720,13 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, return count; } -int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, - const u64 range_start, const u64 range_len) +u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, + const u64 range_start, const u64 range_len) { struct btrfs_root *root; struct list_head splice; - int done; - int total_done = 0; + u64 total_done = 0; + u64 done; INIT_LIST_HEAD(&splice); @@ -748,9 +748,8 @@ int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, total_done += done; spin_lock(&fs_info->ordered_root_lock); - if (nr != -1) { + if (nr != U64_MAX) { nr -= done; - WARN_ON(nr < 0); } } list_splice_tail(&splice, &fs_info->ordered_roots); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index e0c1d5b8d859..56c4c0ee6381 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -200,9 +200,9 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct btrfs_ordered_extent *ordered); int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, u32 *sum, int len); -int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr, +u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr, const u64 range_start, const u64 range_len); -int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr, +u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr, const u64 range_start, const u64 range_len); void btrfs_get_logged_extents(struct btrfs_inode *inode, struct list_head *logged_list, diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index cdafbf92ef0c..569205e651c7 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -44,7 +44,7 @@ static void print_dev_item(struct extent_buffer *eb, static void print_extent_data_ref(struct extent_buffer *eb, struct btrfs_extent_data_ref *ref) { - pr_info("\t\textent data backref root %llu objectid %llu offset %llu count %u\n", + pr_cont("extent data backref root %llu objectid %llu offset %llu count %u\n", btrfs_extent_data_ref_root(eb, ref), btrfs_extent_data_ref_objectid(eb, ref), btrfs_extent_data_ref_offset(eb, ref), @@ -63,6 +63,7 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) u32 item_size = btrfs_item_size_nr(eb, slot); u64 flags; u64 offset; + int ref_index = 0; if (item_size < sizeof(*ei)) { #ifdef BTRFS_COMPAT_EXTENT_TREE_V0 @@ -104,12 +105,20 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) iref = (struct btrfs_extent_inline_ref *)ptr; type = btrfs_extent_inline_ref_type(eb, iref); offset = btrfs_extent_inline_ref_offset(eb, iref); + pr_info("\t\tref#%d: ", ref_index++); switch (type) { case BTRFS_TREE_BLOCK_REF_KEY: - pr_info("\t\ttree block backref root %llu\n", offset); + pr_cont("tree block backref root %llu\n", offset); break; case BTRFS_SHARED_BLOCK_REF_KEY: - pr_info("\t\tshared block backref parent %llu\n", offset); + pr_cont("shared block backref parent %llu\n", offset); + /* + * offset is supposed to be a tree block which + * must be aligned to nodesize. + */ + if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n", + offset, (unsigned long long)eb->fs_info->nodesize); break; case BTRFS_EXTENT_DATA_REF_KEY: dref = (struct btrfs_extent_data_ref *)(&iref->offset); @@ -117,11 +126,20 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type) break; case BTRFS_SHARED_DATA_REF_KEY: sref = (struct btrfs_shared_data_ref *)(iref + 1); - pr_info("\t\tshared data backref parent %llu count %u\n", + pr_cont("shared data backref parent %llu count %u\n", offset, btrfs_shared_data_ref_count(eb, sref)); + /* + * offset is supposed to be a tree block which + * must be aligned to nodesize. + */ + if (!IS_ALIGNED(offset, eb->fs_info->nodesize)) + pr_info("\t\t\t(parent %llu is NOT ALIGNED to nodesize %llu)\n", + offset, (unsigned long long)eb->fs_info->nodesize); break; default: - BUG(); + pr_cont("(extent %llu has INVALID ref type %d)\n", + eb->start, type); + return; } ptr += btrfs_extent_inline_ref_size(type); } @@ -161,8 +179,9 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset, } } -void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l) +void btrfs_print_leaf(struct extent_buffer *l) { + struct btrfs_fs_info *fs_info; int i; u32 type, nr; struct btrfs_item *item; @@ -180,6 +199,7 @@ void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l) if (!l) return; + fs_info = l->fs_info; nr = btrfs_header_nritems(l); btrfs_info(fs_info, "leaf %llu total ptrs %d free space %d", @@ -261,8 +281,11 @@ void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l) case BTRFS_BLOCK_GROUP_ITEM_KEY: bi = btrfs_item_ptr(l, i, struct btrfs_block_group_item); - pr_info("\t\tblock group used %llu\n", - btrfs_disk_block_group_used(l, bi)); + pr_info( + "\t\tblock group used %llu chunk_objectid %llu flags %llu\n", + btrfs_disk_block_group_used(l, bi), + btrfs_disk_block_group_chunk_objectid(l, bi), + btrfs_disk_block_group_flags(l, bi)); break; case BTRFS_CHUNK_ITEM_KEY: print_chunk(l, btrfs_item_ptr(l, i, @@ -315,18 +338,20 @@ void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l) } } -void btrfs_print_tree(struct btrfs_fs_info *fs_info, struct extent_buffer *c) +void btrfs_print_tree(struct extent_buffer *c) { + struct btrfs_fs_info *fs_info; int i; u32 nr; struct btrfs_key key; int level; if (!c) return; + fs_info = c->fs_info; nr = btrfs_header_nritems(c); level = btrfs_header_level(c); if (level == 0) { - btrfs_print_leaf(fs_info, c); + btrfs_print_leaf(c); return; } btrfs_info(fs_info, @@ -356,7 +381,7 @@ void btrfs_print_tree(struct btrfs_fs_info *fs_info, struct extent_buffer *c) if (btrfs_header_level(next) != level - 1) BUG(); - btrfs_print_tree(fs_info, next); + btrfs_print_tree(next); free_extent_buffer(next); } } diff --git a/fs/btrfs/print-tree.h b/fs/btrfs/print-tree.h index 4f2e0ea0e95a..3afd508ed8c5 100644 --- a/fs/btrfs/print-tree.h +++ b/fs/btrfs/print-tree.h @@ -18,6 +18,6 @@ #ifndef __PRINT_TREE_ #define __PRINT_TREE_ -void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l); -void btrfs_print_tree(struct btrfs_fs_info *fs_info, struct extent_buffer *c); +void btrfs_print_leaf(struct extent_buffer *l); +void btrfs_print_tree(struct extent_buffer *c); #endif diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index d6cb155ef7a1..f6a05f836629 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -164,6 +164,7 @@ static int iterate_object_props(struct btrfs_root *root, size_t), void *ctx) { + struct btrfs_fs_info *fs_info = root->fs_info; int ret; char *name_buf = NULL; char *value_buf = NULL; @@ -214,6 +215,12 @@ static int iterate_object_props(struct btrfs_root *root, name_ptr = (unsigned long)(di + 1); data_ptr = name_ptr + name_len; + if (verify_dir_item(fs_info, leaf, + path->slots[0], di)) { + ret = -EIO; + goto out; + } + if (name_len <= XATTR_BTRFS_PREFIX_LEN || memcmp_extent_buffer(leaf, XATTR_BTRFS_PREFIX, name_ptr, @@ -383,6 +390,8 @@ static int prop_compression_validate(const char *value, size_t len) return 0; else if (!strncmp("zlib", value, len)) return 0; + else if (!strncmp("zstd", value, len)) + return 0; return -EINVAL; } @@ -396,32 +405,36 @@ static int prop_compression_apply(struct inode *inode, if (len == 0) { BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS; - BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE; + BTRFS_I(inode)->prop_compress = BTRFS_COMPRESS_NONE; return 0; } - if (!strncmp("lzo", value, len)) + if (!strncmp("lzo", value, 3)) type = BTRFS_COMPRESS_LZO; - else if (!strncmp("zlib", value, len)) + else if (!strncmp("zlib", value, 4)) type = BTRFS_COMPRESS_ZLIB; + else if (!strncmp("zstd", value, len)) + type = BTRFS_COMPRESS_ZSTD; else return -EINVAL; BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS; BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS; - BTRFS_I(inode)->force_compress = type; + BTRFS_I(inode)->prop_compress = type; return 0; } static const char *prop_compression_extract(struct inode *inode) { - switch (BTRFS_I(inode)->force_compress) { + switch (BTRFS_I(inode)->prop_compress) { case BTRFS_COMPRESS_ZLIB: return "zlib"; case BTRFS_COMPRESS_LZO: return "lzo"; + case BTRFS_COMPRESS_ZSTD: + return "zstd"; } return NULL; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index deffbeb74a0b..e172d4843eae 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -807,7 +807,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans, } ret = 0; out: - set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags); btrfs_free_path(path); return ret; } @@ -946,7 +945,6 @@ out: int btrfs_quota_disable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { - struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *quota_root; int ret = 0; @@ -954,7 +952,6 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, if (!fs_info->quota_root) goto out; clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -968,7 +965,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, if (ret) goto out; - ret = btrfs_del_root(trans, tree_root, "a_root->root_key); + ret = btrfs_del_root(trans, fs_info, "a_root->root_key); if (ret) goto out; @@ -1308,6 +1305,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, } } ret = del_qgroup_item(trans, quota_root, qgroupid); + if (ret && ret != -ENOENT) + goto out; while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -1406,38 +1405,6 @@ out: return ret; } -int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info) -{ - struct btrfs_qgroup_extent_record *record; - struct btrfs_delayed_ref_root *delayed_refs; - struct rb_node *node; - u64 qgroup_to_skip; - int ret = 0; - - delayed_refs = &trans->transaction->delayed_refs; - qgroup_to_skip = delayed_refs->qgroup_to_skip; - - /* - * No need to do lock, since this function will only be called in - * btrfs_commit_transaction(). - */ - node = rb_first(&delayed_refs->dirty_extent_root); - while (node) { - record = rb_entry(node, struct btrfs_qgroup_extent_record, - node); - if (WARN_ON(!record->old_roots)) - ret = btrfs_find_all_roots(NULL, fs_info, - record->bytenr, 0, &record->old_roots); - if (ret < 0) - break; - if (qgroup_to_skip) - ulist_del(record->old_roots, qgroup_to_skip, 0); - node = rb_next(node); - } - return ret; -} - int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, struct btrfs_qgroup_extent_record *record) @@ -1559,6 +1526,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans, if (ret) return ret; } + cond_resched(); return 0; } @@ -1634,7 +1602,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans, struct extent_buffer *eb = root_eb; struct btrfs_path *path = NULL; - BUG_ON(root_level < 0 || root_level > BTRFS_MAX_LEVEL); + BUG_ON(root_level < 0 || root_level >= BTRFS_MAX_LEVEL); BUG_ON(root_eb == NULL); if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) @@ -1918,6 +1886,35 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, return 0; } +/* + * Check if the @roots potentially is a list of fs tree roots + * + * Return 0 for definitely not a fs/subvol tree roots ulist + * Return 1 for possible fs/subvol tree roots in the list (considering an empty + * one as well) + */ +static int maybe_fs_roots(struct ulist *roots) +{ + struct ulist_node *unode; + struct ulist_iterator uiter; + + /* Empty one, still possible for fs roots */ + if (!roots || roots->nnodes == 0) + return 1; + + ULIST_ITER_INIT(&uiter); + unode = ulist_next(roots, &uiter); + if (!unode) + return 1; + + /* + * If it contains fs tree roots, then it must belong to fs/subvol + * trees. + * If it contains a non-fs tree, it won't be shared with fs/subvol trees. + */ + return is_fstree(unode->val); +} + int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, @@ -1934,10 +1931,20 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) return 0; - if (new_roots) + if (new_roots) { + if (!maybe_fs_roots(new_roots)) + goto out_free; nr_new_roots = new_roots->nnodes; - if (old_roots) + } + if (old_roots) { + if (!maybe_fs_roots(old_roots)) + goto out_free; nr_old_roots = old_roots->nnodes; + } + + /* Quick exit, either not fs tree roots, or won't affect any qgroup */ + if (nr_old_roots == 0 && nr_new_roots == 0) + goto out_free; BUG_ON(!fs_info->quota_root); @@ -2017,6 +2024,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans, if (!ret) { /* + * Old roots should be searched when inserting qgroup + * extent record + */ + if (WARN_ON(!record->old_roots)) { + /* Search commit root to find old_roots */ + ret = btrfs_find_all_roots(NULL, fs_info, + record->bytenr, 0, + &record->old_roots); + if (ret < 0) + goto cleanup; + } + + /* * Use SEQ_LAST as time_seq to do special search, which * doesn't lock tree or delayed_refs and search current * root. It's safe inside commit_transaction(). @@ -2025,8 +2045,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans, record->bytenr, SEQ_LAST, &new_roots); if (ret < 0) goto cleanup; - if (qgroup_to_skip) + if (qgroup_to_skip) { ulist_del(new_roots, qgroup_to_skip, 0); + ulist_del(record->old_roots, qgroup_to_skip, + 0); + } ret = btrfs_qgroup_account_extent(trans, fs_info, record->bytenr, record->num_bytes, record->old_roots, new_roots); @@ -2063,8 +2086,6 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans, if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags)) set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags)) - clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); spin_lock(&fs_info->qgroup_lock); while (!list_empty(&fs_info->dirty_qgroups)) { @@ -2338,6 +2359,11 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce) if (num_bytes == 0) return 0; + + if (test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags) && + capable(CAP_SYS_RESOURCE)) + enforce = false; + retry: spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; @@ -2376,7 +2402,7 @@ retry: ret = btrfs_start_delalloc_inodes(root, 0); if (ret) return ret; - btrfs_wait_ordered_extents(root, -1, 0, (u64)-1); + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); @@ -2617,7 +2643,7 @@ out: if (IS_ERR(trans)) { err = PTR_ERR(trans); btrfs_err(fs_info, - "fail to start transaction for status update: %d\n", + "fail to start transaction for status update: %d", err); goto done; } @@ -2806,55 +2832,130 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info) * Return <0 for error (including -EQUOT) * * NOTE: this function may sleep for memory allocation. + * if btrfs_qgroup_reserve_data() is called multiple times with + * same @reserved, caller must ensure when error happens it's OK + * to free *ALL* reserved space. */ -int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len) +int btrfs_qgroup_reserve_data(struct inode *inode, + struct extent_changeset **reserved_ret, u64 start, + u64 len) { struct btrfs_root *root = BTRFS_I(inode)->root; - struct extent_changeset changeset; struct ulist_node *unode; struct ulist_iterator uiter; + struct extent_changeset *reserved; + u64 orig_reserved; + u64 to_reserve; int ret; if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) || !is_fstree(root->objectid) || len == 0) return 0; - changeset.bytes_changed = 0; - ulist_init(&changeset.range_changed); + /* @reserved parameter is mandatory for qgroup */ + if (WARN_ON(!reserved_ret)) + return -EINVAL; + if (!*reserved_ret) { + *reserved_ret = extent_changeset_alloc(); + if (!*reserved_ret) + return -ENOMEM; + } + reserved = *reserved_ret; + /* Record already reserved space */ + orig_reserved = reserved->bytes_changed; ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start, - start + len -1, EXTENT_QGROUP_RESERVED, &changeset); + start + len -1, EXTENT_QGROUP_RESERVED, reserved); + + /* Newly reserved space */ + to_reserve = reserved->bytes_changed - orig_reserved; trace_btrfs_qgroup_reserve_data(inode, start, len, - changeset.bytes_changed, - QGROUP_RESERVE); + to_reserve, QGROUP_RESERVE); if (ret < 0) goto cleanup; - ret = qgroup_reserve(root, changeset.bytes_changed, true); + ret = qgroup_reserve(root, to_reserve, true); if (ret < 0) goto cleanup; - ulist_release(&changeset.range_changed); return ret; cleanup: - /* cleanup already reserved ranges */ + /* cleanup *ALL* already reserved ranges */ ULIST_ITER_INIT(&uiter); - while ((unode = ulist_next(&changeset.range_changed, &uiter))) + while ((unode = ulist_next(&reserved->range_changed, &uiter))) clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val, unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL, GFP_NOFS); - ulist_release(&changeset.range_changed); + extent_changeset_release(reserved); + return ret; +} + +/* Free ranges specified by @reserved, normally in error path */ +static int qgroup_free_reserved_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + struct ulist_node *unode; + struct ulist_iterator uiter; + struct extent_changeset changeset; + int freed = 0; + int ret; + + extent_changeset_init(&changeset); + len = round_up(start + len, root->fs_info->sectorsize); + start = round_down(start, root->fs_info->sectorsize); + + ULIST_ITER_INIT(&uiter); + while ((unode = ulist_next(&reserved->range_changed, &uiter))) { + u64 range_start = unode->val; + /* unode->aux is the inclusive end */ + u64 range_len = unode->aux - range_start + 1; + u64 free_start; + u64 free_len; + + extent_changeset_release(&changeset); + + /* Only free range in range [start, start + len) */ + if (range_start >= start + len || + range_start + range_len <= start) + continue; + free_start = max(range_start, start); + free_len = min(start + len, range_start + range_len) - + free_start; + /* + * TODO: To also modify reserved->ranges_reserved to reflect + * the modification. + * + * However as long as we free qgroup reserved according to + * EXTENT_QGROUP_RESERVED, we won't double free. + * So not need to rush. + */ + ret = clear_record_extent_bits(&BTRFS_I(inode)->io_failure_tree, + free_start, free_start + free_len - 1, + EXTENT_QGROUP_RESERVED, &changeset); + if (ret < 0) + goto out; + freed += changeset.bytes_changed; + } + btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed); + ret = freed; +out: + extent_changeset_release(&changeset); return ret; } -static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, - int free) +static int __btrfs_qgroup_release_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len, + int free) { struct extent_changeset changeset; int trace_op = QGROUP_RELEASE; int ret; - changeset.bytes_changed = 0; - ulist_init(&changeset.range_changed); + /* In release case, we shouldn't have @reserved */ + WARN_ON(!free && reserved); + if (free && reserved) + return qgroup_free_reserved_data(inode, reserved, start, len); + extent_changeset_init(&changeset); ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len -1, EXTENT_QGROUP_RESERVED, &changeset); if (ret < 0) @@ -2868,8 +2969,9 @@ static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len, btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info, BTRFS_I(inode)->root->objectid, changeset.bytes_changed); + ret = changeset.bytes_changed; out: - ulist_release(&changeset.range_changed); + extent_changeset_release(&changeset); return ret; } @@ -2878,14 +2980,17 @@ out: * * Should be called when a range of pages get invalidated before reaching disk. * Or for error cleanup case. + * if @reserved is given, only reserved range in [@start, @start + @len) will + * be freed. * * For data written to disk, use btrfs_qgroup_release_data(). * * NOTE: This function may sleep for memory allocation. */ -int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len) +int btrfs_qgroup_free_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len) { - return __btrfs_qgroup_release_data(inode, start, len, 1); + return __btrfs_qgroup_release_data(inode, reserved, start, len, 1); } /* @@ -2905,7 +3010,7 @@ int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len) */ int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len) { - return __btrfs_qgroup_release_data(inode, start, len, 0); + return __btrfs_qgroup_release_data(inode, NULL, start, len, 0); } int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, @@ -2969,8 +3074,7 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) struct ulist_iterator iter; int ret; - changeset.bytes_changed = 0; - ulist_init(&changeset.range_changed); + extent_changeset_init(&changeset); ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_QGROUP_RESERVED, &changeset); @@ -2987,5 +3091,5 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode) changeset.bytes_changed); } - ulist_release(&changeset.range_changed); + extent_changeset_release(&changeset); } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index fe04d3f295c6..d9984e87cddf 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -134,8 +134,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info); void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; -int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info); + /* * Inform qgroup to trace one dirty extent, its info is recorded in @record. * So qgroup can account it at transaction committing time. @@ -243,9 +242,11 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid, #endif /* New io_tree based accurate qgroup reserve API */ -int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len); +int btrfs_qgroup_reserve_data(struct inode *inode, + struct extent_changeset **reserved, u64 start, u64 len); int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len); -int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len); +int btrfs_qgroup_free_data(struct inode *inode, + struct extent_changeset *reserved, u64 start, u64 len); int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes, bool enforce); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index d8ea0eb76325..24a62224b24b 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -31,7 +31,7 @@ #include <linux/hash.h> #include <linux/list_sort.h> #include <linux/raid/xor.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <asm/div64.h> #include "ctree.h" #include "extent_map.h" @@ -218,12 +218,9 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info) * of a failing mount. */ table_size = sizeof(*table) + sizeof(*h) * num_entries; - table = kzalloc(table_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); - if (!table) { - table = vzalloc(table_size); - if (!table) - return -ENOMEM; - } + table = kvzalloc(table_size, GFP_KERNEL); + if (!table) + return -ENOMEM; spin_lock_init(&table->cache_lock); INIT_LIST_HEAD(&table->stripe_cache); @@ -871,7 +868,7 @@ static void free_raid_bio(struct btrfs_raid_bio *rbio) * this frees the rbio and runs through all the bios in the * bio_list and calls end_io on them */ -static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) +static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err) { struct bio *cur = bio_list_get(&rbio->bio_list); struct bio *next; @@ -884,7 +881,7 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) while (cur) { next = cur->bi_next; cur->bi_next = NULL; - cur->bi_error = err; + cur->bi_status = err; bio_endio(cur); cur = next; } @@ -897,7 +894,7 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) static void raid_write_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - int err = bio->bi_error; + blk_status_t err = bio->bi_status; int max_errors; if (err) @@ -908,13 +905,13 @@ static void raid_write_end_io(struct bio *bio) if (!atomic_dec_and_test(&rbio->stripes_pending)) return; - err = 0; + err = BLK_STS_OK; /* OK, we have read all the stripes we need to. */ max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ? 0 : rbio->bbio->max_errors; if (atomic_read(&rbio->error) > max_errors) - err = -EIO; + err = BLK_STS_IOERR; rbio_orig_end_io(rbio, err); } @@ -1092,8 +1089,9 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, * devices or if they are not contiguous */ if (last_end == disk_start && stripe->dev->bdev && - !last->bi_error && - last->bi_bdev == stripe->dev->bdev) { + !last->bi_status && + last->bi_disk == stripe->dev->bdev->bd_disk && + last->bi_partno == stripe->dev->bdev->bd_partno) { ret = bio_add_page(last, page, PAGE_SIZE, 0); if (ret == PAGE_SIZE) return 0; @@ -1101,12 +1099,9 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, } /* put a new bio on the list */ - bio = btrfs_io_bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1); - if (!bio) - return -ENOMEM; - + bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1); bio->bi_iter.bi_size = 0; - bio->bi_bdev = stripe->dev->bdev; + bio_set_dev(bio, stripe->dev->bdev); bio->bi_iter.bi_sector = disk_start >> 9; bio_add_page(bio, page, PAGE_SIZE, 0); @@ -1142,20 +1137,27 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio) static void index_rbio_pages(struct btrfs_raid_bio *rbio) { struct bio *bio; - struct bio_vec *bvec; u64 start; unsigned long stripe_offset; unsigned long page_index; - int i; spin_lock_irq(&rbio->bio_list_lock); bio_list_for_each(bio, &rbio->bio_list) { + struct bio_vec bvec; + struct bvec_iter iter; + int i = 0; + start = (u64)bio->bi_iter.bi_sector << 9; stripe_offset = start - rbio->bbio->raid_map[0]; page_index = stripe_offset >> PAGE_SHIFT; - bio_for_each_segment_all(bvec, bio, i) - rbio->bio_pages[page_index + i] = bvec->bv_page; + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_io_bio(bio)->iter; + + bio_for_each_segment(bvec, bio, iter) { + rbio->bio_pages[page_index + i] = bvec.bv_page; + i++; + } } spin_unlock_irq(&rbio->bio_list_lock); } @@ -1323,7 +1325,7 @@ write_data: return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } /* @@ -1346,7 +1348,8 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio, stripe_start = stripe->physical; if (physical >= stripe_start && physical < stripe_start + rbio->stripe_len && - bio->bi_bdev == stripe->dev->bdev) { + bio->bi_disk == stripe->dev->bdev->bd_disk && + bio->bi_partno == stripe->dev->bdev->bd_partno) { return i; } } @@ -1429,11 +1432,14 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio, */ static void set_bio_pages_uptodate(struct bio *bio) { - struct bio_vec *bvec; - int i; + struct bio_vec bvec; + struct bvec_iter iter; + + if (bio_flagged(bio, BIO_CLONED)) + bio->bi_iter = btrfs_io_bio(bio)->iter; - bio_for_each_segment_all(bvec, bio, i) - SetPageUptodate(bvec->bv_page); + bio_for_each_segment(bvec, bio, iter) + SetPageUptodate(bvec.bv_page); } /* @@ -1448,7 +1454,7 @@ static void raid_rmw_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - if (bio->bi_error) + if (bio->bi_status) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -1471,7 +1477,7 @@ static void raid_rmw_end_io(struct bio *bio) cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } static void async_rmw_stripe(struct btrfs_raid_bio *rbio) @@ -1575,7 +1581,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) return 0; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); return -EIO; finish: @@ -1791,12 +1797,12 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) void **pointers; int faila = -1, failb = -1; struct page *page; - int err; + blk_status_t err; int i; pointers = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS); if (!pointers) { - err = -ENOMEM; + err = BLK_STS_RESOURCE; goto cleanup_io; } @@ -1852,7 +1858,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) * a bad data or Q stripe. * TODO, we should redo the xor here. */ - err = -EIO; + err = BLK_STS_IOERR; goto cleanup; } /* @@ -1878,7 +1884,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) if (rbio->bbio->raid_map[failb] == RAID6_Q_STRIPE) { if (rbio->bbio->raid_map[faila] == RAID5_P_STRIPE) { - err = -EIO; + err = BLK_STS_IOERR; goto cleanup; } /* @@ -1950,13 +1956,13 @@ pstripe: } } - err = 0; + err = BLK_STS_OK; cleanup: kfree(pointers); cleanup_io: if (rbio->operation == BTRFS_RBIO_READ_REBUILD) { - if (err == 0) + if (err == BLK_STS_OK) cache_rbio_pages(rbio); else clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); @@ -1964,7 +1970,7 @@ cleanup_io: rbio_orig_end_io(rbio, err); } else if (rbio->operation == BTRFS_RBIO_REBUILD_MISSING) { rbio_orig_end_io(rbio, err); - } else if (err == 0) { + } else if (err == BLK_STS_OK) { rbio->faila = -1; rbio->failb = -1; @@ -1991,7 +1997,7 @@ static void raid_recover_end_io(struct bio *bio) * we only read stripe pages off the disk, set them * up to date if there were no errors */ - if (bio->bi_error) + if (bio->bi_status) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -2001,7 +2007,7 @@ static void raid_recover_end_io(struct bio *bio) return; if (atomic_read(&rbio->error) > rbio->bbio->max_errors) - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); else __raid_recover_end_io(rbio); } @@ -2100,7 +2106,7 @@ out: cleanup: if (rbio->operation == BTRFS_RBIO_READ_REBUILD || rbio->operation == BTRFS_RBIO_REBUILD_MISSING) - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); return -EIO; } @@ -2427,7 +2433,7 @@ submit_write: nr_data = bio_list_size(&bio_list); if (!nr_data) { /* Every parity is right */ - rbio_orig_end_io(rbio, 0); + rbio_orig_end_io(rbio, BLK_STS_OK); return; } @@ -2447,7 +2453,7 @@ submit_write: return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe) @@ -2515,7 +2521,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio) return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } /* @@ -2530,7 +2536,7 @@ static void raid56_parity_scrub_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - if (bio->bi_error) + if (bio->bi_status) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -2629,7 +2635,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); return; finish: diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index a17e775a4a89..ab852b8e3e37 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -66,7 +66,6 @@ struct reada_extctl { struct reada_extent { u64 logical; struct btrfs_key top; - int err; struct list_head extctl; int refcnt; spinlock_t lock; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index d60df51959f7..9841faef08ea 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -32,6 +32,7 @@ #include "free-space-cache.h" #include "inode-map.h" #include "qgroup.h" +#include "print-tree.h" /* * backref_node, mapping_node and tree_block start with this @@ -799,9 +800,17 @@ again: if (ptr < end) { /* update key for inline back ref */ struct btrfs_extent_inline_ref *iref; + int type; iref = (struct btrfs_extent_inline_ref *)ptr; - key.type = btrfs_extent_inline_ref_type(eb, iref); + type = btrfs_get_extent_inline_ref_type(eb, iref, + BTRFS_REF_TYPE_BLOCK); + if (type == BTRFS_REF_TYPE_INVALID) { + err = -EINVAL; + goto out; + } + key.type = type; key.offset = btrfs_extent_inline_ref_offset(eb, iref); + WARN_ON(key.type != BTRFS_TREE_BLOCK_REF_KEY && key.type != BTRFS_SHARED_BLOCK_REF_KEY); } @@ -1308,8 +1317,6 @@ static int __must_check __add_reloc_root(struct btrfs_root *root) btrfs_panic(fs_info, -EEXIST, "Duplicate root found for start=%llu while inserting into relocation tree", node->bytenr); - kfree(node); - return -EEXIST; } list_add_tail(&root->root_list, &rc->reloc_roots); @@ -2393,11 +2400,11 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->node = NULL; reloc_root->commit_root = NULL; - __del_reloc_root(reloc_root); } } @@ -3093,11 +3100,12 @@ int prealloc_file_extent_cluster(struct inode *inode, u64 prealloc_start = cluster->start - offset; u64 prealloc_end = cluster->end - offset; u64 cur_offset; + struct extent_changeset *data_reserved = NULL; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); - ret = btrfs_check_data_free_space(inode, prealloc_start, + ret = btrfs_check_data_free_space(inode, &data_reserved, prealloc_start, prealloc_end + 1 - prealloc_start); if (ret) goto out; @@ -3113,8 +3121,8 @@ int prealloc_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, start, end); num_bytes = end + 1 - start; if (cur_offset < start) - btrfs_free_reserved_data_space(inode, cur_offset, - start - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + cur_offset, start - cur_offset); ret = btrfs_prealloc_file_range(inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); @@ -3125,10 +3133,11 @@ int prealloc_file_extent_cluster(struct inode *inode, nr++; } if (cur_offset < prealloc_end) - btrfs_free_reserved_data_space(inode, cur_offset, - prealloc_end + 1 - cur_offset); + btrfs_free_reserved_data_space(inode, data_reserved, + cur_offset, prealloc_end + 1 - cur_offset); out: inode_unlock(inode); + extent_changeset_free(data_reserved); return ret; } @@ -3475,7 +3484,16 @@ again: goto again; } } - BUG_ON(ret); + if (ret) { + ASSERT(ret == 1); + btrfs_print_leaf(path->nodes[0]); + btrfs_err(fs_info, + "tree block extent item (%llu) is not found in extent tree", + bytenr); + WARN_ON(1); + ret = -EINVAL; + goto out; + } ret = add_tree_block(rc, &key, path, blocks); out: @@ -3753,7 +3771,8 @@ int add_data_references(struct reloc_control *rc, while (ptr < end) { iref = (struct btrfs_extent_inline_ref *)ptr; - key.type = btrfs_extent_inline_ref_type(eb, iref); + key.type = btrfs_get_extent_inline_ref_type(eb, iref, + BTRFS_REF_TYPE_DATA); if (key.type == BTRFS_SHARED_DATA_REF_KEY) { key.offset = btrfs_extent_inline_ref_offset(eb, iref); ret = __add_tree_block(rc, key.offset, blocksize, @@ -3763,7 +3782,10 @@ int add_data_references(struct reloc_control *rc, ret = find_data_references(rc, extent_key, eb, dref, blocks); } else { - BUG(); + ret = -EINVAL; + btrfs_err(rc->extent_root->fs_info, + "extent %llu slot %d has an invalid inline ref type", + eb->start, path->slots[0]); } if (ret) { err = ret; @@ -4269,8 +4291,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info) INIT_LIST_HEAD(&rc->reloc_roots); backref_cache_init(&rc->backref_cache); mapping_tree_init(&rc->reloc_root_tree); - extent_io_tree_init(&rc->processed_blocks, - fs_info->btree_inode->i_mapping); + extent_io_tree_init(&rc->processed_blocks, NULL); return rc; } @@ -4372,7 +4393,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) btrfs_wait_block_group_reservations(rc->block_group); btrfs_wait_nocow_writers(rc->block_group); - btrfs_wait_ordered_roots(fs_info, -1, + btrfs_wait_ordered_roots(fs_info, U64_MAX, rc->block_group->key.objectid, rc->block_group->key.offset); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7d6bc308bf43..95bcc3cce78f 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -151,7 +151,7 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root } if (ret != 0) { - btrfs_print_leaf(fs_info, path->nodes[0]); + btrfs_print_leaf(path->nodes[0]); btrfs_crit(fs_info, "unable to update root key %llu %u %llu", key->objectid, key->type, key->offset); BUG_ON(1); @@ -228,7 +228,7 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info) int ret; bool can_recover = true; - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) can_recover = false; path = btrfs_alloc_path(); @@ -335,10 +335,11 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info) return err; } -/* drop the root item for 'key' from 'root' */ -int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, - const struct btrfs_key *key) +/* drop the root item for 'key' from the tree root */ +int btrfs_del_root(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, const struct btrfs_key *key) { + struct btrfs_root *root = fs_info->tree_root; struct btrfs_path *path; int ret; @@ -390,6 +391,13 @@ again: WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid); WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len); ptr = (unsigned long)(ref + 1); + ret = btrfs_is_name_len_valid(leaf, path->slots[0], ptr, + name_len); + if (!ret) { + err = -EIO; + goto out; + } + WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len)); *sequence = btrfs_root_ref_sequence(leaf, ref); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index c7b45eb2403d..e3f6c49e5c4d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -18,6 +18,7 @@ #include <linux/blkdev.h> #include <linux/ratelimit.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "volumes.h" #include "disk-io.h" @@ -95,7 +96,7 @@ struct scrub_bio { struct scrub_ctx *sctx; struct btrfs_device *dev; struct bio *bio; - int err; + blk_status_t status; u64 logical; u64 physical; #if SCRUB_PAGES_PER_WR_BIO >= SCRUB_PAGES_PER_RD_BIO @@ -161,14 +162,6 @@ struct scrub_parity { unsigned long bitmap[0]; }; -struct scrub_wr_ctx { - struct scrub_bio *wr_curr_bio; - struct btrfs_device *tgtdev; - int pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */ - atomic_t flush_all_writes; - struct mutex wr_lock; -}; - struct scrub_ctx { struct scrub_bio *bios[SCRUB_BIOS_PER_SCTX]; struct btrfs_fs_info *fs_info; @@ -183,11 +176,14 @@ struct scrub_ctx { atomic_t cancel_req; int readonly; int pages_per_rd_bio; - u32 sectorsize; - u32 nodesize; int is_dev_replace; - struct scrub_wr_ctx wr_ctx; + + struct scrub_bio *wr_curr_bio; + struct mutex wr_lock; + int pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */ + struct btrfs_device *wr_tgtdev; + bool flush_all_writes; /* * statistics @@ -289,10 +285,6 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info, u64 *extent_physical, struct btrfs_device **extent_dev, int *extent_mirror_num); -static int scrub_setup_wr_ctx(struct scrub_wr_ctx *wr_ctx, - struct btrfs_device *dev, - int is_dev_replace); -static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx); static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage); static void scrub_wr_submit(struct scrub_ctx *sctx); @@ -643,8 +635,6 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) if (!sctx) return; - scrub_free_wr_ctx(&sctx->wr_ctx); - /* this can happen when scrub is cancelled */ if (sctx->curr != -1) { struct scrub_bio *sbio = sctx->bios[sctx->curr]; @@ -664,6 +654,7 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) kfree(sbio); } + kfree(sctx->wr_curr_bio); scrub_free_csums(sctx); kfree(sctx); } @@ -680,7 +671,6 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) struct scrub_ctx *sctx; int i; struct btrfs_fs_info *fs_info = dev->fs_info; - int ret; sctx = kzalloc(sizeof(*sctx), GFP_KERNEL); if (!sctx) @@ -710,8 +700,6 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) sctx->bios[i]->next_free = -1; } sctx->first_free = 0; - sctx->nodesize = fs_info->nodesize; - sctx->sectorsize = fs_info->sectorsize; atomic_set(&sctx->bios_in_flight, 0); atomic_set(&sctx->workers_pending, 0); atomic_set(&sctx->cancel_req, 0); @@ -722,12 +710,16 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) spin_lock_init(&sctx->stat_lock); init_waitqueue_head(&sctx->list_wait); - ret = scrub_setup_wr_ctx(&sctx->wr_ctx, - fs_info->dev_replace.tgtdev, is_dev_replace); - if (ret) { - scrub_free_ctx(sctx); - return ERR_PTR(ret); + WARN_ON(sctx->wr_curr_bio != NULL); + mutex_init(&sctx->wr_lock); + sctx->wr_curr_bio = NULL; + if (is_dev_replace) { + WARN_ON(!fs_info->dev_replace.tgtdev); + sctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO; + sctx->wr_tgtdev = fs_info->dev_replace.tgtdev; + sctx->flush_all_writes = false; } + return sctx; nomem: @@ -742,6 +734,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, u32 nlink; int ret; int i; + unsigned nofs_flag; struct extent_buffer *eb; struct btrfs_inode_item *inode_item; struct scrub_warning *swarn = warn_ctx; @@ -780,7 +773,14 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, nlink = btrfs_inode_nlink(eb, inode_item); btrfs_release_path(swarn->path); + /* + * init_path might indirectly call vmalloc, or use GFP_KERNEL. Scrub + * uses GFP_NOFS in this context, so we keep it consistent but it does + * not seem to be strictly necessary. + */ + nofs_flag = memalloc_nofs_save(); ipath = init_ipath(4096, local_root, swarn->path); + memalloc_nofs_restore(nofs_flag); if (IS_ERR(ipath)) { ret = PTR_ERR(ipath); ipath = NULL; @@ -954,7 +954,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx) ret = -EIO; goto out; } - ret = repair_io_failure(BTRFS_I(inode), offset, PAGE_SIZE, + ret = repair_io_failure(fs_info, inum, offset, PAGE_SIZE, fixup->logical, page, offset - page_offset(page), fixup->mirror_num); @@ -1668,14 +1668,14 @@ leave_nomem: struct scrub_bio_ret { struct completion event; - int error; + blk_status_t status; }; static void scrub_bio_wait_endio(struct bio *bio) { struct scrub_bio_ret *ret = bio->bi_private; - ret->error = bio->bi_error; + ret->status = bio->bi_status; complete(&ret->event); } @@ -1693,7 +1693,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, int ret; init_completion(&done.event); - done.error = 0; + done.status = 0; bio->bi_iter.bi_sector = page->logical >> 9; bio->bi_private = &done; bio->bi_end_io = scrub_bio_wait_endio; @@ -1704,8 +1704,8 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info, if (ret) return ret; - wait_for_completion(&done.event); - if (done.error) + wait_for_completion_io(&done.event); + if (done.status) return -EIO; return 0; @@ -1737,13 +1737,8 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info, } WARN_ON(!page->page); - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) { - page->io_error = 1; - sblock->no_io_error_seen = 0; - continue; - } - bio->bi_bdev = page->dev->bdev; + bio = btrfs_io_bio_alloc(1); + bio_set_dev(bio, page->dev->bdev); bio_add_page(bio, page->page, PAGE_SIZE, 0); if (!retry_failed_mirror && scrub_is_page_on_raid56(page)) { @@ -1774,7 +1769,7 @@ static inline int scrub_check_fsid(u8 fsid[], struct btrfs_fs_devices *fs_devices = spage->dev->fs_devices; int ret; - ret = memcmp(fsid, fs_devices->fsid, BTRFS_UUID_SIZE); + ret = memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE); return !ret; } @@ -1830,10 +1825,8 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, return -EIO; } - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) - return -EIO; - bio->bi_bdev = page_bad->dev->bdev; + bio = btrfs_io_bio_alloc(1); + bio_set_dev(bio, page_bad->dev->bdev); bio->bi_iter.bi_sector = page_bad->physical >> 9; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -1898,46 +1891,40 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock, static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage) { - struct scrub_wr_ctx *wr_ctx = &sctx->wr_ctx; struct scrub_bio *sbio; int ret; - mutex_lock(&wr_ctx->wr_lock); + mutex_lock(&sctx->wr_lock); again: - if (!wr_ctx->wr_curr_bio) { - wr_ctx->wr_curr_bio = kzalloc(sizeof(*wr_ctx->wr_curr_bio), + if (!sctx->wr_curr_bio) { + sctx->wr_curr_bio = kzalloc(sizeof(*sctx->wr_curr_bio), GFP_KERNEL); - if (!wr_ctx->wr_curr_bio) { - mutex_unlock(&wr_ctx->wr_lock); + if (!sctx->wr_curr_bio) { + mutex_unlock(&sctx->wr_lock); return -ENOMEM; } - wr_ctx->wr_curr_bio->sctx = sctx; - wr_ctx->wr_curr_bio->page_count = 0; + sctx->wr_curr_bio->sctx = sctx; + sctx->wr_curr_bio->page_count = 0; } - sbio = wr_ctx->wr_curr_bio; + sbio = sctx->wr_curr_bio; if (sbio->page_count == 0) { struct bio *bio; sbio->physical = spage->physical_for_dev_replace; sbio->logical = spage->logical; - sbio->dev = wr_ctx->tgtdev; + sbio->dev = sctx->wr_tgtdev; bio = sbio->bio; if (!bio) { - bio = btrfs_io_bio_alloc(GFP_KERNEL, - wr_ctx->pages_per_wr_bio); - if (!bio) { - mutex_unlock(&wr_ctx->wr_lock); - return -ENOMEM; - } + bio = btrfs_io_bio_alloc(sctx->pages_per_wr_bio); sbio->bio = bio; } bio->bi_private = sbio; bio->bi_end_io = scrub_wr_bio_end_io; - bio->bi_bdev = sbio->dev->bdev; + bio_set_dev(bio, sbio->dev->bdev); bio->bi_iter.bi_sector = sbio->physical >> 9; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - sbio->err = 0; + sbio->status = 0; } else if (sbio->physical + sbio->page_count * PAGE_SIZE != spage->physical_for_dev_replace || sbio->logical + sbio->page_count * PAGE_SIZE != @@ -1951,7 +1938,7 @@ again: if (sbio->page_count < 1) { bio_put(sbio->bio); sbio->bio = NULL; - mutex_unlock(&wr_ctx->wr_lock); + mutex_unlock(&sctx->wr_lock); return -EIO; } scrub_wr_submit(sctx); @@ -1961,24 +1948,23 @@ again: sbio->pagev[sbio->page_count] = spage; scrub_page_get(spage); sbio->page_count++; - if (sbio->page_count == wr_ctx->pages_per_wr_bio) + if (sbio->page_count == sctx->pages_per_wr_bio) scrub_wr_submit(sctx); - mutex_unlock(&wr_ctx->wr_lock); + mutex_unlock(&sctx->wr_lock); return 0; } static void scrub_wr_submit(struct scrub_ctx *sctx) { - struct scrub_wr_ctx *wr_ctx = &sctx->wr_ctx; struct scrub_bio *sbio; - if (!wr_ctx->wr_curr_bio) + if (!sctx->wr_curr_bio) return; - sbio = wr_ctx->wr_curr_bio; - wr_ctx->wr_curr_bio = NULL; - WARN_ON(!sbio->bio->bi_bdev); + sbio = sctx->wr_curr_bio; + sctx->wr_curr_bio = NULL; + WARN_ON(!sbio->bio->bi_disk); scrub_pending_bio_inc(sctx); /* process all writes in a single worker thread. Then the block layer * orders the requests before sending them to the driver which @@ -1992,7 +1978,7 @@ static void scrub_wr_bio_end_io(struct bio *bio) struct scrub_bio *sbio = bio->bi_private; struct btrfs_fs_info *fs_info = sbio->dev->fs_info; - sbio->err = bio->bi_error; + sbio->status = bio->bi_status; sbio->bio = bio; btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper, @@ -2007,7 +1993,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work) int i; WARN_ON(sbio->page_count > SCRUB_PAGES_PER_WR_BIO); - if (sbio->err) { + if (sbio->status) { struct btrfs_dev_replace *dev_replace = &sbio->sctx->fs_info->dev_replace; @@ -2081,7 +2067,7 @@ static int scrub_checksum_data(struct scrub_block *sblock) page = sblock->pagev[0]->page; buffer = kmap_atomic(page); - len = sctx->sectorsize; + len = sctx->fs_info->sectorsize; index = 0; for (;;) { u64 l = min_t(u64, len, PAGE_SIZE); @@ -2146,7 +2132,7 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) BTRFS_UUID_SIZE)) sblock->header_error = 1; - len = sctx->nodesize - BTRFS_CSUM_SIZE; + len = sctx->fs_info->nodesize - BTRFS_CSUM_SIZE; mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE; index = 0; @@ -2329,19 +2315,16 @@ again: sbio->dev = spage->dev; bio = sbio->bio; if (!bio) { - bio = btrfs_io_bio_alloc(GFP_KERNEL, - sctx->pages_per_rd_bio); - if (!bio) - return -ENOMEM; + bio = btrfs_io_bio_alloc(sctx->pages_per_rd_bio); sbio->bio = bio; } bio->bi_private = sbio; bio->bi_end_io = scrub_bio_end_io; - bio->bi_bdev = sbio->dev->bdev; + bio_set_dev(bio, sbio->dev->bdev); bio->bi_iter.bi_sector = sbio->physical >> 9; bio_set_op_attrs(bio, REQ_OP_READ, 0); - sbio->err = 0; + sbio->status = 0; } else if (sbio->physical + sbio->page_count * PAGE_SIZE != spage->physical || sbio->logical + sbio->page_count * PAGE_SIZE != @@ -2377,7 +2360,7 @@ static void scrub_missing_raid56_end_io(struct bio *bio) struct scrub_block *sblock = bio->bi_private; struct btrfs_fs_info *fs_info = sblock->sctx->fs_info; - if (bio->bi_error) + if (bio->bi_status) sblock->no_io_error_seen = 0; bio_put(bio); @@ -2419,11 +2402,10 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work) scrub_block_put(sblock); - if (sctx->is_dev_replace && - atomic_read(&sctx->wr_ctx.flush_all_writes)) { - mutex_lock(&sctx->wr_ctx.wr_lock); + if (sctx->is_dev_replace && sctx->flush_all_writes) { + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); } scrub_pending_bio_dec(sctx); @@ -2458,10 +2440,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock) goto bbio_out; } - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - goto bbio_out; - + bio = btrfs_io_bio_alloc(0); bio->bi_iter.bi_sector = logical >> 9; bio->bi_private = sblock; bio->bi_end_io = scrub_missing_raid56_end_io; @@ -2588,7 +2567,7 @@ static void scrub_bio_end_io(struct bio *bio) struct scrub_bio *sbio = bio->bi_private; struct btrfs_fs_info *fs_info = sbio->dev->fs_info; - sbio->err = bio->bi_error; + sbio->status = bio->bi_status; sbio->bio = bio; btrfs_queue_work(fs_info->scrub_workers, &sbio->work); @@ -2601,7 +2580,7 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work) int i; BUG_ON(sbio->page_count > SCRUB_PAGES_PER_RD_BIO); - if (sbio->err) { + if (sbio->status) { for (i = 0; i < sbio->page_count; i++) { struct scrub_page *spage = sbio->pagev[i]; @@ -2627,11 +2606,10 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work) sctx->first_free = sbio->index; spin_unlock(&sctx->list_lock); - if (sctx->is_dev_replace && - atomic_read(&sctx->wr_ctx.flush_all_writes)) { - mutex_lock(&sctx->wr_ctx.wr_lock); + if (sctx->is_dev_replace && sctx->flush_all_writes) { + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); } scrub_pending_bio_dec(sctx); @@ -2642,7 +2620,8 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, u64 start, u64 len) { u64 offset; - int nsectors; + u64 nsectors64; + u32 nsectors; int sectorsize = sparity->sctx->fs_info->sectorsize; if (len >= sparity->stripe_len) { @@ -2653,7 +2632,10 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity, start -= sparity->logic_start; start = div64_u64_rem(start, sparity->stripe_len, &offset); offset = div_u64(offset, sectorsize); - nsectors = (int)len / sectorsize; + nsectors64 = div_u64(len, sectorsize); + + ASSERT(nsectors64 < UINT_MAX); + nsectors = (u32)nsectors64; if (offset + nsectors <= sparity->nsectors) { bitmap_set(bitmap, offset, nsectors); @@ -2726,8 +2708,10 @@ static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum) if (!sum) return 0; - index = ((u32)(logical - sum->bytenr)) / sctx->sectorsize; - num_sectors = sum->len / sctx->sectorsize; + index = div_u64(logical - sum->bytenr, sctx->fs_info->sectorsize); + ASSERT(index < UINT_MAX); + + num_sectors = sum->len / sctx->fs_info->sectorsize; memcpy(csum, sum->sums + index, sctx->csum_size); if (index == num_sectors - 1) { list_del(&sum->list); @@ -2746,19 +2730,19 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len, u32 blocksize; if (flags & BTRFS_EXTENT_FLAG_DATA) { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; spin_lock(&sctx->stat_lock); sctx->stat.data_extents_scrubbed++; sctx->stat.data_bytes_scrubbed += len; spin_unlock(&sctx->stat_lock); } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - blocksize = sctx->nodesize; + blocksize = sctx->fs_info->nodesize; spin_lock(&sctx->stat_lock); sctx->stat.tree_extents_scrubbed++; sctx->stat.tree_bytes_scrubbed += len; spin_unlock(&sctx->stat_lock); } else { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; WARN_ON(1); } @@ -2892,11 +2876,11 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity, } if (flags & BTRFS_EXTENT_FLAG_DATA) { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; } else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { - blocksize = sctx->nodesize; + blocksize = sctx->fs_info->nodesize; } else { - blocksize = sctx->sectorsize; + blocksize = sctx->fs_info->sectorsize; WARN_ON(1); } @@ -3004,7 +2988,7 @@ static void scrub_parity_bio_endio(struct bio *bio) struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private; struct btrfs_fs_info *fs_info = sparity->sctx->fs_info; - if (bio->bi_error) + if (bio->bi_status) bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap, sparity->nsectors); @@ -3037,10 +3021,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity) if (ret || !bbio || !bbio->raid_map) goto bbio_out; - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - goto bbio_out; - + bio = btrfs_io_bio_alloc(0); bio->bi_iter.bi_sector = sparity->logic_start >> 9; bio->bi_private = sparity; bio->bi_end_io = scrub_parity_bio_endio; @@ -3305,9 +3286,9 @@ out: logic_end - logic_start); scrub_parity_put(sparity); scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); btrfs_release_path(path); return ret < 0 ? ret : 0; @@ -3463,14 +3444,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, */ if (atomic_read(&fs_info->scrub_pause_req)) { /* push queued extents */ - atomic_set(&sctx->wr_ctx.flush_all_writes, 1); + sctx->flush_all_writes = true; scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); - atomic_set(&sctx->wr_ctx.flush_all_writes, 0); + sctx->flush_all_writes = false; scrub_blocked_if_needed(fs_info); } @@ -3677,9 +3658,9 @@ skip: out: /* push queued extents */ scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); blk_finish_plug(&plug); btrfs_free_path(path); @@ -3859,7 +3840,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, */ btrfs_wait_block_group_reservations(cache); btrfs_wait_nocow_writers(cache); - ret = btrfs_wait_ordered_roots(fs_info, -1, + ret = btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->key.objectid, cache->key.offset); if (ret > 0) { @@ -3892,8 +3873,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, ro_set = 0; } else { btrfs_warn(fs_info, - "failed setting block group ro, ret=%d\n", - ret); + "failed setting block group ro: %d", ret); btrfs_put_block_group(cache); break; } @@ -3916,11 +3896,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * write requests are really completed when bios_in_flight * changes to 0. */ - atomic_set(&sctx->wr_ctx.flush_all_writes, 1); + sctx->flush_all_writes = true; scrub_submit(sctx); - mutex_lock(&sctx->wr_ctx.wr_lock); + mutex_lock(&sctx->wr_lock); scrub_wr_submit(sctx); - mutex_unlock(&sctx->wr_ctx.wr_lock); + mutex_unlock(&sctx->wr_lock); wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); @@ -3934,7 +3914,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, */ wait_event(sctx->list_wait, atomic_read(&sctx->workers_pending) == 0); - atomic_set(&sctx->wr_ctx.flush_all_writes, 0); + sctx->flush_all_writes = false; scrub_pause_off(fs_info); @@ -4035,14 +4015,8 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info, int max_active = fs_info->thread_pool_size; if (fs_info->scrub_workers_refcnt == 0) { - if (is_dev_replace) - fs_info->scrub_workers = - btrfs_alloc_workqueue(fs_info, "scrub", flags, - 1, 4); - else - fs_info->scrub_workers = - btrfs_alloc_workqueue(fs_info, "scrub", flags, - max_active, 4); + fs_info->scrub_workers = btrfs_alloc_workqueue(fs_info, "scrub", + flags, is_dev_replace ? 1 : max_active, 4); if (!fs_info->scrub_workers) goto fail_scrub_workers; @@ -4337,32 +4311,6 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info, btrfs_put_bbio(bbio); } -static int scrub_setup_wr_ctx(struct scrub_wr_ctx *wr_ctx, - struct btrfs_device *dev, - int is_dev_replace) -{ - WARN_ON(wr_ctx->wr_curr_bio != NULL); - - mutex_init(&wr_ctx->wr_lock); - wr_ctx->wr_curr_bio = NULL; - if (!is_dev_replace) - return 0; - - WARN_ON(!dev->bdev); - wr_ctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO; - wr_ctx->tgtdev = dev; - atomic_set(&wr_ctx->flush_all_writes, 0); - return 0; -} - -static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx) -{ - mutex_lock(&wr_ctx->wr_lock); - kfree(wr_ctx->wr_curr_bio); - wr_ctx->wr_curr_bio = NULL; - mutex_unlock(&wr_ctx->wr_lock); -} - static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, int mirror_num, u64 physical_for_dev_replace) { @@ -4665,7 +4613,7 @@ static int write_page_nocow(struct scrub_ctx *sctx, struct btrfs_device *dev; int ret; - dev = sctx->wr_ctx.tgtdev; + dev = sctx->wr_tgtdev; if (!dev) return -EIO; if (!dev->bdev) { @@ -4673,16 +4621,10 @@ static int write_page_nocow(struct scrub_ctx *sctx, "scrub write_page_nocow(bdev == NULL) is unexpected"); return -EIO; } - bio = btrfs_io_bio_alloc(GFP_NOFS, 1); - if (!bio) { - spin_lock(&sctx->stat_lock); - sctx->stat.malloc_errors++; - spin_unlock(&sctx->stat_lock); - return -ENOMEM; - } + bio = btrfs_io_bio_alloc(1); bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = physical_for_dev_replace >> 9; - bio->bi_bdev = dev->bdev; + bio_set_dev(bio, dev->bdev); bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; ret = bio_add_page(bio, page, PAGE_SIZE, 0); if (ret != PAGE_SIZE) { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index fc496a6f842a..8fd195cfe81b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -539,33 +539,23 @@ static struct btrfs_path *alloc_path_for_send(void) static int write_buf(struct file *filp, const void *buf, u32 len, loff_t *off) { int ret; - mm_segment_t old_fs; u32 pos = 0; - old_fs = get_fs(); - set_fs(KERNEL_DS); - while (pos < len) { - ret = vfs_write(filp, (__force const char __user *)buf + pos, - len - pos, off); + ret = kernel_write(filp, buf + pos, len - pos, off); /* TODO handle that correctly */ /*if (ret == -ERESTARTSYS) { continue; }*/ if (ret < 0) - goto out; + return ret; if (ret == 0) { - ret = -EIO; - goto out; + return -EIO; } pos += ret; } - ret = 0; - -out: - set_fs(old_fs); - return ret; + return 0; } static int tlv_put(struct send_ctx *sctx, u16 attr, const void *data, int len) @@ -1069,6 +1059,12 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path, } } + ret = btrfs_is_name_len_valid(eb, path->slots[0], + (unsigned long)(di + 1), name_len + data_len); + if (!ret) { + ret = -EIO; + goto out; + } if (name_len + data_len > buf_len) { buf_len = name_len + data_len; if (is_vmalloc_addr(buf)) { @@ -1083,7 +1079,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path, buf = tmp; } if (!buf) { - buf = vmalloc(buf_len); + buf = kvmalloc(buf_len, GFP_KERNEL); if (!buf) { ret = -ENOMEM; goto out; @@ -1850,7 +1846,7 @@ out: */ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, const char *name, int name_len, - u64 *who_ino, u64 *who_gen) + u64 *who_ino, u64 *who_gen, u64 *who_mode) { int ret = 0; u64 gen; @@ -1899,7 +1895,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, if (other_inode > sctx->send_progress || is_waiting_for_move(sctx, other_inode)) { ret = get_inode_info(sctx->parent_root, other_inode, NULL, - who_gen, NULL, NULL, NULL, NULL); + who_gen, who_mode, NULL, NULL, NULL); if (ret < 0) goto out; @@ -2634,7 +2630,7 @@ static int send_create_inode(struct send_ctx *sctx, u64 ino) } else { btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o", (int)(mode & S_IFMT)); - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; goto out; } @@ -2769,15 +2765,20 @@ out: struct recorded_ref { struct list_head list; - char *dir_path; char *name; struct fs_path *full_path; u64 dir; u64 dir_gen; - int dir_path_len; int name_len; }; +static void set_ref_path(struct recorded_ref *ref, struct fs_path *path) +{ + ref->full_path = path; + ref->name = (char *)kbasename(ref->full_path->start); + ref->name_len = ref->full_path->end - ref->name; +} + /* * We need to process new refs before deleted refs, but compare_tree gives us * everything mixed. So we first record all refs and later process them. @@ -2794,17 +2795,7 @@ static int __record_ref(struct list_head *head, u64 dir, ref->dir = dir; ref->dir_gen = dir_gen; - ref->full_path = path; - - ref->name = (char *)kbasename(ref->full_path->start); - ref->name_len = ref->full_path->end - ref->name; - ref->dir_path = ref->full_path->start; - if (ref->name == ref->full_path->start) - ref->dir_path_len = 0; - else - ref->dir_path_len = ref->full_path->end - - ref->full_path->start - 1 - ref->name_len; - + set_ref_path(ref, path); list_add_tail(&ref->list, head); return 0; } @@ -3546,9 +3537,17 @@ static int is_ancestor(struct btrfs_root *root, struct fs_path *fs_path) { u64 ino = ino2; + bool free_path = false; + int ret = 0; + + if (!fs_path) { + fs_path = fs_path_alloc(); + if (!fs_path) + return -ENOMEM; + free_path = true; + } while (ino > BTRFS_FIRST_FREE_OBJECTID) { - int ret; u64 parent; u64 parent_gen; @@ -3557,13 +3556,18 @@ static int is_ancestor(struct btrfs_root *root, if (ret < 0) { if (ret == -ENOENT && ino == ino2) ret = 0; - return ret; + goto out; + } + if (parent == ino1) { + ret = parent_gen == ino1_gen ? 1 : 0; + goto out; } - if (parent == ino1) - return parent_gen == ino1_gen ? 1 : 0; ino = parent; } - return 0; + out: + if (free_path) + fs_path_free(fs_path); + return ret; } static int wait_for_parent_move(struct send_ctx *sctx, @@ -3669,6 +3673,36 @@ out: return ret; } +static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref) +{ + int ret; + struct fs_path *new_path; + + /* + * Our reference's name member points to its full_path member string, so + * we use here a new path. + */ + new_path = fs_path_alloc(); + if (!new_path) + return -ENOMEM; + + ret = get_cur_path(sctx, ref->dir, ref->dir_gen, new_path); + if (ret < 0) { + fs_path_free(new_path); + return ret; + } + ret = fs_path_add(new_path, ref->name, ref->name_len); + if (ret < 0) { + fs_path_free(new_path); + return ret; + } + + fs_path_free(ref->full_path); + set_ref_path(ref, new_path); + + return 0; +} + /* * This does all the move/link/unlink/rmdir magic. */ @@ -3682,10 +3716,13 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct fs_path *valid_path = NULL; u64 ow_inode = 0; u64 ow_gen; + u64 ow_mode; int did_overwrite = 0; int is_orphan = 0; u64 last_dir_ino_rm = 0; bool can_rename = true; + bool orphanized_dir = false; + bool orphanized_ancestor = false; btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino); @@ -3783,7 +3820,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) */ ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen, cur->name, cur->name_len, - &ow_inode, &ow_gen); + &ow_inode, &ow_gen, &ow_mode); if (ret < 0) goto out; if (ret) { @@ -3800,6 +3837,8 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) cur->full_path); if (ret < 0) goto out; + if (S_ISDIR(ow_mode)) + orphanized_dir = true; /* * If ow_inode has its rename operation delayed @@ -3837,9 +3876,16 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) * might contain the pre-orphanization name of * ow_inode, which is no longer valid. */ - fs_path_reset(valid_path); - ret = get_cur_path(sctx, sctx->cur_ino, - sctx->cur_inode_gen, valid_path); + ret = is_ancestor(sctx->parent_root, + ow_inode, ow_gen, + sctx->cur_ino, NULL); + if (ret > 0) { + orphanized_ancestor = true; + fs_path_reset(valid_path); + ret = get_cur_path(sctx, sctx->cur_ino, + sctx->cur_inode_gen, + valid_path); + } if (ret < 0) goto out; } else { @@ -3898,6 +3944,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (ret < 0) goto out; } else { + /* + * We might have previously orphanized an inode + * which is an ancestor of our current inode, + * so our reference's full path, which was + * computed before any such orphanizations, must + * be updated. + */ + if (orphanized_dir) { + ret = update_ref_path(sctx, cur); + if (ret < 0) + goto out; + } ret = send_link(sctx, cur->full_path, valid_path); if (ret < 0) @@ -3960,6 +4018,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (ret < 0) goto out; if (!ret) { + /* + * If we orphanized any ancestor before, we need + * to recompute the full path for deleted names, + * since any such path was computed before we + * processed any references and orphanized any + * ancestor inode. + */ + if (orphanized_ancestor) { + ret = update_ref_path(sctx, cur); + if (ret < 0) + goto out; + } ret = send_unlink(sctx, cur->full_path); if (ret < 0) goto out; @@ -4653,7 +4723,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len) /* initial readahead */ memset(&sctx->ra, 0, sizeof(struct file_ra_state)); file_ra_state_init(&sctx->ra, inode->i_mapping); - btrfs_force_ra(inode->i_mapping, &sctx->ra, NULL, index, + page_cache_sync_readahead(inode->i_mapping, &sctx->ra, NULL, index, last_index - index + 1); while (index <= last_index) { @@ -4912,6 +4982,25 @@ static int clone_range(struct send_ctx *sctx, struct btrfs_key key; int ret; + /* + * Prevent cloning from a zero offset with a length matching the sector + * size because in some scenarios this will make the receiver fail. + * + * For example, if in the source filesystem the extent at offset 0 + * has a length of sectorsize and it was written using direct IO, then + * it can never be an inline extent (even if compression is enabled). + * Then this extent can be cloned in the original filesystem to a non + * zero file offset, but it may not be possible to clone in the + * destination filesystem because it can be inlined due to compression + * on the destination filesystem (as the receiver's write operations are + * always done using buffered IO). The same happens when the original + * filesystem does not have compression enabled but the destination + * filesystem has. + */ + if (clone_root->offset == 0 && + len == sctx->send_root->fs_info->sectorsize) + return send_extent_data(sctx, offset, len); + path = alloc_path_for_send(); if (!path) return -ENOMEM; @@ -5190,15 +5279,12 @@ static int is_extent_unchanged(struct send_ctx *sctx, goto out; } - right_disknr = btrfs_file_extent_disk_bytenr(eb, ei); if (right_type == BTRFS_FILE_EXTENT_INLINE) { right_len = btrfs_file_extent_inline_len(eb, slot, ei); right_len = PAGE_ALIGN(right_len); } else { right_len = btrfs_file_extent_num_bytes(eb, ei); } - right_offset = btrfs_file_extent_offset(eb, ei); - right_gen = btrfs_file_extent_generation(eb, ei); /* * Are we at extent 8? If yes, we know the extent is changed. @@ -5223,6 +5309,10 @@ static int is_extent_unchanged(struct send_ctx *sctx, goto out; } + right_disknr = btrfs_file_extent_disk_bytenr(eb, ei); + right_offset = btrfs_file_extent_offset(eb, ei); + right_gen = btrfs_file_extent_generation(eb, ei); + left_offset_fixed = left_offset; if (key.offset < ekey->offset) { /* Fix the right offset for 2a and 7. */ @@ -6397,13 +6487,10 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1); - sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN); + sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL); if (!sctx->clone_roots) { - sctx->clone_roots = vzalloc(alloc_size); - if (!sctx->clone_roots) { - ret = -ENOMEM; - goto out; - } + ret = -ENOMEM; + goto out; } alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources); diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c index 875c757e73e2..5e2b92d83617 100644 --- a/fs/btrfs/struct-funcs.c +++ b/fs/btrfs/struct-funcs.c @@ -50,8 +50,8 @@ static inline void put_unaligned_le8(u8 val, void *p) */ #define DEFINE_BTRFS_SETGET_BITS(bits) \ -u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr, \ - unsigned long off, \ +u##bits btrfs_get_token_##bits(const struct extent_buffer *eb, \ + const void *ptr, unsigned long off, \ struct btrfs_map_token *token) \ { \ unsigned long part_offset = (unsigned long)ptr; \ @@ -90,7 +90,8 @@ u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr, \ return res; \ } \ void btrfs_set_token_##bits(struct extent_buffer *eb, \ - void *ptr, unsigned long off, u##bits val, \ + const void *ptr, unsigned long off, \ + u##bits val, \ struct btrfs_map_token *token) \ { \ unsigned long part_offset = (unsigned long)ptr; \ @@ -133,7 +134,7 @@ DEFINE_BTRFS_SETGET_BITS(16) DEFINE_BTRFS_SETGET_BITS(32) DEFINE_BTRFS_SETGET_BITS(64) -void btrfs_node_key(struct extent_buffer *eb, +void btrfs_node_key(const struct extent_buffer *eb, struct btrfs_disk_key *disk_key, int nr) { unsigned long ptr = btrfs_node_key_ptr_offset(nr); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4f1cdd5058f1..161694b66038 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -61,6 +61,7 @@ #include "tests/btrfs-tests.h" #include "qgroup.h" +#include "backref.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> @@ -102,7 +103,7 @@ static void btrfs_handle_error(struct btrfs_fs_info *fs_info) { struct super_block *sb = fs_info->sb; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { @@ -138,7 +139,7 @@ void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function * Special case: if the error is EROFS, and we're already * under MS_RDONLY, then it is safe here. */ - if (errno == -EROFS && (sb->s_flags & MS_RDONLY)) + if (errno == -EROFS && sb_rdonly(sb)) return; #ifdef CONFIG_PRINTK @@ -425,7 +426,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, * strsep changes the string, duplicate it because parse_options * gets called twice */ - options = kstrdup(options, GFP_NOFS); + options = kstrdup(options, GFP_KERNEL); if (!options) return -ENOMEM; @@ -498,14 +499,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, btrfs_test_opt(info, FORCE_COMPRESS); if (token == Opt_compress || token == Opt_compress_force || - strcmp(args[0].from, "zlib") == 0) { + strncmp(args[0].from, "zlib", 4) == 0) { compress_type = "zlib"; info->compress_type = BTRFS_COMPRESS_ZLIB; btrfs_set_opt(info->mount_opt, COMPRESS); btrfs_clear_opt(info->mount_opt, NODATACOW); btrfs_clear_opt(info->mount_opt, NODATASUM); no_compress = 0; - } else if (strcmp(args[0].from, "lzo") == 0) { + } else if (strncmp(args[0].from, "lzo", 3) == 0) { compress_type = "lzo"; info->compress_type = BTRFS_COMPRESS_LZO; btrfs_set_opt(info->mount_opt, COMPRESS); @@ -513,6 +514,14 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, btrfs_clear_opt(info->mount_opt, NODATASUM); btrfs_set_fs_incompat(info, COMPRESS_LZO); no_compress = 0; + } else if (strcmp(args[0].from, "zstd") == 0) { + compress_type = "zstd"; + info->compress_type = BTRFS_COMPRESS_ZSTD; + btrfs_set_opt(info->mount_opt, COMPRESS); + btrfs_clear_opt(info->mount_opt, NODATACOW); + btrfs_clear_opt(info->mount_opt, NODATASUM); + btrfs_set_fs_incompat(info, COMPRESS_ZSTD); + no_compress = 0; } else if (strncmp(args[0].from, "no", 2) == 0) { compress_type = "no"; btrfs_clear_opt(info->mount_opt, COMPRESS); @@ -548,20 +557,22 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, break; case Opt_ssd: btrfs_set_and_info(info, SSD, - "use ssd allocation scheme"); + "enabling ssd optimizations"); btrfs_clear_opt(info->mount_opt, NOSSD); break; case Opt_ssd_spread: + btrfs_set_and_info(info, SSD, + "enabling ssd optimizations"); btrfs_set_and_info(info, SSD_SPREAD, - "use spread ssd allocation scheme"); - btrfs_set_opt(info->mount_opt, SSD); + "using spread ssd allocation scheme"); btrfs_clear_opt(info->mount_opt, NOSSD); break; case Opt_nossd: - btrfs_set_and_info(info, NOSSD, - "not using ssd allocation scheme"); - btrfs_clear_opt(info->mount_opt, SSD); - btrfs_clear_opt(info->mount_opt, SSD_SPREAD); + btrfs_set_opt(info->mount_opt, NOSSD); + btrfs_clear_and_info(info, SSD, + "not using ssd optimizations"); + btrfs_clear_and_info(info, SSD_SPREAD, + "not using spread ssd allocation scheme"); break; case Opt_barrier: btrfs_clear_and_info(info, NOBARRIER, @@ -601,18 +612,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options, } break; case Opt_alloc_start: - num = match_strdup(&args[0]); - if (num) { - mutex_lock(&info->chunk_mutex); - info->alloc_start = memparse(num, NULL); - mutex_unlock(&info->chunk_mutex); - kfree(num); - btrfs_info(info, "allocations start at %llu", - info->alloc_start); - } else { - ret = -ENOMEM; - goto out; - } + btrfs_info(info, + "option alloc_start is obsolete, ignored"); break; case Opt_acl: #ifdef CONFIG_BTRFS_FS_POSIX_ACL @@ -959,7 +960,7 @@ static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info, } path->leave_spinning = 1; - name = kmalloc(PATH_MAX, GFP_NOFS); + name = kmalloc(PATH_MAX, GFP_KERNEL); if (!name) { ret = -ENOMEM; goto err; @@ -1134,7 +1135,7 @@ static int btrfs_fill_super(struct super_block *sb, #ifdef CONFIG_BTRFS_FS_POSIX_ACL sb->s_flags |= MS_POSIXACL; #endif - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; sb->s_iflags |= SB_I_CGROUPWB; err = super_setup_bdi(sb); @@ -1164,7 +1165,6 @@ static int btrfs_fill_super(struct super_block *sb, goto fail_close; } - save_mount_options(sb, data); cleancache_init_fs(sb); sb->s_flags |= MS_ACTIVE; return 0; @@ -1187,7 +1187,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { @@ -1232,16 +1232,16 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_puts(seq, ",nobarrier"); if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE) seq_printf(seq, ",max_inline=%llu", info->max_inline); - if (info->alloc_start != 0) - seq_printf(seq, ",alloc_start=%llu", info->alloc_start); if (info->thread_pool_size != min_t(unsigned long, num_online_cpus() + 2, 8)) seq_printf(seq, ",thread_pool=%d", info->thread_pool_size); if (btrfs_test_opt(info, COMPRESS)) { if (info->compress_type == BTRFS_COMPRESS_ZLIB) compress_type = "zlib"; - else + else if (info->compress_type == BTRFS_COMPRESS_LZO) compress_type = "lzo"; + else + compress_type = "zstd"; if (btrfs_test_opt(info, FORCE_COMPRESS)) seq_printf(seq, ",compress-force=%s", compress_type); else @@ -1348,10 +1348,11 @@ static char *setup_root_args(char *args) char *buf, *dst, *sep; if (!args) - return kstrdup("subvolid=0", GFP_NOFS); + return kstrdup("subvolid=0", GFP_KERNEL); /* The worst case is that we add ",subvolid=0" to the end. */ - buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1, GFP_NOFS); + buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1, + GFP_KERNEL); if (!buf) return NULL; @@ -1580,7 +1581,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, * it for searching for existing supers, so this lets us do that and * then open_ctree will properly initialize everything later. */ - fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS); + fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_KERNEL); if (!fs_info) { error = -ENOMEM; goto error_sec_opts; @@ -1588,8 +1589,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, fs_info->fs_devices = fs_devices; - fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS); - fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS); + fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); + fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); security_init_mnt_opts(&fs_info->security_opts); if (!fs_info->super_copy || !fs_info->super_for_commit) { error = -ENOMEM; @@ -1700,8 +1701,7 @@ static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info, * close or the filesystem is read only. */ if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) && - (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) || - (fs_info->sb->s_flags & MS_RDONLY))) { + (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) || sb_rdonly(fs_info->sb))) { btrfs_cleanup_defrag_inodes(fs_info); } @@ -1716,7 +1716,6 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) unsigned long old_opts = fs_info->mount_opt; unsigned long old_compress_type = fs_info->compress_type; u64 old_max_inline = fs_info->max_inline; - u64 old_alloc_start = fs_info->alloc_start; int old_thread_pool_size = fs_info->thread_pool_size; unsigned int old_metadata_ratio = fs_info->metadata_ratio; int ret; @@ -1749,7 +1748,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) btrfs_resize_thread_pool(fs_info, fs_info->thread_pool_size, old_thread_pool_size); - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) goto out; if (*flags & MS_RDONLY) { @@ -1794,8 +1793,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } - if (fs_info->fs_devices->missing_devices > - fs_info->num_tolerated_disk_barrier_failures) { + if (!btrfs_check_rw_degradable(fs_info)) { btrfs_warn(fs_info, "too many missing devices, writeable remount is not allowed"); ret = -EACCES; @@ -1828,6 +1826,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } + btrfs_qgroup_rescan_resume(fs_info); + if (!fs_info->uuid_root) { btrfs_info(fs_info, "creating UUID tree"); ret = btrfs_create_uuid_tree(fs_info); @@ -1849,15 +1849,12 @@ out: restore: /* We've hit an error - don't reset MS_RDONLY */ - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) old_flags |= MS_RDONLY; sb->s_flags = old_flags; fs_info->mount_opt = old_opts; fs_info->compress_type = old_compress_type; fs_info->max_inline = old_max_inline; - mutex_lock(&fs_info->chunk_mutex); - fs_info->alloc_start = old_alloc_start; - mutex_unlock(&fs_info->chunk_mutex); btrfs_resize_thread_pool(fs_info, old_thread_pool_size, fs_info->thread_pool_size); fs_info->metadata_ratio = old_metadata_ratio; @@ -1898,18 +1895,15 @@ static inline void btrfs_descending_sort_devices( static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, u64 *free_bytes) { - struct btrfs_root *root = fs_info->tree_root; struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *device; u64 skip_space; u64 type; u64 avail_space; - u64 used_space; u64 min_stripe_size; int min_stripes = 1, num_stripes = 1; int i = 0, nr_devices; - int ret; /* * We aren't under the device list lock, so this is racy-ish, but good @@ -1927,12 +1921,12 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, } devices_info = kmalloc_array(nr_devices, sizeof(*devices_info), - GFP_NOFS); + GFP_KERNEL); if (!devices_info) return -ENOMEM; /* calc min stripe number for data space allocation */ - type = btrfs_get_alloc_profile(root, 1); + type = btrfs_data_alloc_profile(fs_info); if (type & BTRFS_BLOCK_GROUP_RAID0) { min_stripes = 2; num_stripes = nr_devices; @@ -1949,8 +1943,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, else min_stripe_size = BTRFS_STRIPE_LEN; - if (fs_info->alloc_start) - mutex_lock(&fs_devices->device_list_mutex); rcu_read_lock(); list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) { if (!device->in_fs_metadata || !device->bdev || @@ -1973,34 +1965,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, */ skip_space = SZ_1M; - /* user can set the offset in fs_info->alloc_start. */ - if (fs_info->alloc_start && - fs_info->alloc_start + BTRFS_STRIPE_LEN <= - device->total_bytes) { - rcu_read_unlock(); - skip_space = max(fs_info->alloc_start, skip_space); - - /* - * btrfs can not use the free space in - * [0, skip_space - 1], we must subtract it from the - * total. In order to implement it, we account the used - * space in this range first. - */ - ret = btrfs_account_dev_extents_size(device, 0, - skip_space - 1, - &used_space); - if (ret) { - kfree(devices_info); - mutex_unlock(&fs_devices->device_list_mutex); - return ret; - } - - rcu_read_lock(); - - /* calc the free space in [0, skip_space - 1] */ - skip_space -= used_space; - } - /* * we can use the free space in [0, skip_space - 1], subtract * it from the total. @@ -2019,8 +1983,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, i++; } rcu_read_unlock(); - if (fs_info->alloc_start) - mutex_unlock(&fs_devices->device_list_mutex); nr_devices = i; @@ -2057,10 +2019,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, * multiplier to scale the sizes. * * Unused device space usage is based on simulating the chunk allocator - * algorithm that respects the device sizes, order of allocations and the - * 'alloc_start' value, this is a close approximation of the actual use but - * there are other factors that may change the result (like a new metadata - * chunk). + * algorithm that respects the device sizes and order of allocations. This is + * a close approximation of the actual use but there are other factors that may + * change the result (like a new metadata chunk). * * If metadata is exhausted, f_bavail will be 0. */ @@ -2243,7 +2204,7 @@ static int btrfs_freeze(struct super_block *sb) struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root = fs_info->tree_root; - fs_info->fs_frozen = 1; + set_bit(BTRFS_FS_FROZEN, &fs_info->flags); /* * We don't need a barrier here, we'll wait for any transaction that * could be in progress on other threads (and do delayed iputs that @@ -2262,7 +2223,9 @@ static int btrfs_freeze(struct super_block *sb) static int btrfs_unfreeze(struct super_block *sb) { - btrfs_sb(sb)->fs_frozen = 0; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + + clear_bit(BTRFS_FS_FROZEN, &fs_info->flags); return 0; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 1f157fba8940..883881b16c86 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -120,7 +120,7 @@ static ssize_t btrfs_feature_attr_store(struct kobject *kobj, if (!fs_info) return -EPERM; - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) return -EROFS; ret = kstrtoul(skip_spaces(buf), 0, &val); @@ -200,6 +200,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF); BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL); BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS); BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO); +BTRFS_FEAT_ATTR_INCOMPAT(compress_zstd, COMPRESS_ZSTD); BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF); BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56); @@ -212,6 +213,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(default_subvol), BTRFS_FEAT_ATTR_PTR(mixed_groups), BTRFS_FEAT_ATTR_PTR(compress_lzo), + BTRFS_FEAT_ATTR_PTR(compress_zstd), BTRFS_FEAT_ATTR_PTR(big_metadata), BTRFS_FEAT_ATTR_PTR(extended_iref), BTRFS_FEAT_ATTR_PTR(raid56), @@ -388,7 +390,7 @@ static ssize_t btrfs_label_store(struct kobject *kobj, if (!fs_info) return -EPERM; - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) return -EROFS; /* @@ -447,11 +449,52 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, BTRFS_ATTR(clone_alignment, btrfs_clone_alignment_show); +static ssize_t quota_override_show(struct kobject *kobj, + struct kobj_attribute *a, char *buf) +{ + struct btrfs_fs_info *fs_info = to_fs_info(kobj); + int quota_override; + + quota_override = test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); + return snprintf(buf, PAGE_SIZE, "%d\n", quota_override); +} + +static ssize_t quota_override_store(struct kobject *kobj, + struct kobj_attribute *a, + const char *buf, size_t len) +{ + struct btrfs_fs_info *fs_info = to_fs_info(kobj); + unsigned long knob; + int err; + + if (!fs_info) + return -EPERM; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + err = kstrtoul(buf, 10, &knob); + if (err) + return err; + if (knob > 1) + return -EINVAL; + + if (knob) + set_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); + else + clear_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags); + + return len; +} + +BTRFS_ATTR_RW(quota_override, quota_override_show, quota_override_store); + static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(label), BTRFS_ATTR_PTR(nodesize), BTRFS_ATTR_PTR(sectorsize), BTRFS_ATTR_PTR(clone_alignment), + BTRFS_ATTR_PTR(quota_override), NULL, }; diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index b18ab8f327a5..d3f25376a0f8 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -211,7 +211,6 @@ btrfs_alloc_dummy_block_group(struct btrfs_fs_info *fs_info, cache->key.objectid = 0; cache->key.offset = length; cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY; - cache->sectorsize = fs_info->sectorsize; cache->full_stripe_len = fs_info->sectorsize; cache->fs_info = fs_info; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index 133753232a94..d06b1c931d05 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -87,7 +87,7 @@ static int test_find_delalloc(u32 sectorsize) return -ENOMEM; } - extent_io_tree_init(&tmp, &inode->i_data); + extent_io_tree_init(&tmp, inode); /* * First go through and create and mark all of our pages dirty, we pin diff --git a/fs/btrfs/tests/free-space-tree-tests.c b/fs/btrfs/tests/free-space-tree-tests.c index b29954c01673..1458bb0ea124 100644 --- a/fs/btrfs/tests/free-space-tree-tests.c +++ b/fs/btrfs/tests/free-space-tree-tests.c @@ -81,7 +81,7 @@ static int __check_free_space_extents(struct btrfs_trans_handle *trans, i++; } prev_bit = bit; - offset += cache->sectorsize; + offset += fs_info->sectorsize; } } if (prev_bit == 1) { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 2168654c90a1..f615d59b0489 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -93,7 +93,7 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) btrfs_put_block_group_trimming(cache); btrfs_put_block_group(cache); } - kmem_cache_free(btrfs_transaction_cachep, transaction); + kfree(transaction); } } @@ -228,7 +228,7 @@ loop: */ BUG_ON(type == TRANS_JOIN_NOLOCK); - cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS); + cur_trans = kmalloc(sizeof(*cur_trans), GFP_NOFS); if (!cur_trans) return -ENOMEM; @@ -238,11 +238,11 @@ loop: * someone started a transaction after we unlocked. Make sure * to redo the checks above */ - kmem_cache_free(btrfs_transaction_cachep, cur_trans); + kfree(cur_trans); goto loop; } else if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { spin_unlock(&fs_info->trans_lock); - kmem_cache_free(btrfs_transaction_cachep, cur_trans); + kfree(cur_trans); return -EROFS; } @@ -294,7 +294,7 @@ loop: spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, - fs_info->btree_inode->i_mapping); + fs_info->btree_inode); fs_info->generation++; cur_trans->transid = fs_info->generation; fs_info->running_transaction = cur_trans; @@ -1374,9 +1374,6 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans, ret = commit_fs_roots(trans, fs_info); if (ret) goto out; - ret = btrfs_qgroup_prepare_account_extents(trans, fs_info); - if (ret < 0) - goto out; ret = btrfs_qgroup_account_extents(trans, fs_info); if (ret < 0) goto out; @@ -1926,7 +1923,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) - btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); + btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } static inline void @@ -2180,13 +2177,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) goto scrub_continue; } - ret = btrfs_qgroup_prepare_account_extents(trans, fs_info); - if (ret) { - mutex_unlock(&fs_info->tree_log_mutex); - mutex_unlock(&fs_info->reloc_mutex); - goto scrub_continue; - } - /* * Since fs roots are all committed, we can get a quite accurate * new_roots. So let's do quota accounting. @@ -2314,7 +2304,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) * it'll result in deadlock about SB_FREEZE_FS. */ if (current != fs_info->transaction_kthread && - current != fs_info->cleaner_kthread && !fs_info->fs_frozen) + current != fs_info->cleaner_kthread && + !test_bit(BTRFS_FS_FROZEN, &fs_info->flags)) btrfs_run_delayed_iputs(fs_info); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ccfe9fe7754a..c800d067fcbf 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1143,8 +1143,6 @@ again: goto again; } kfree(victim_name); - if (ret) - return ret; next: cur_offset += victim_name_len + sizeof(*extref); } @@ -1175,15 +1173,19 @@ next: return 0; } -static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - u32 *namelen, char **name, u64 *index, - u64 *parent_objectid) +static int extref_get_fields(struct extent_buffer *eb, int slot, + unsigned long ref_ptr, u32 *namelen, char **name, + u64 *index, u64 *parent_objectid) { struct btrfs_inode_extref *extref; extref = (struct btrfs_inode_extref *)ref_ptr; *namelen = btrfs_inode_extref_name_len(eb, extref); + if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)&extref->name, + *namelen)) + return -EIO; + *name = kmalloc(*namelen, GFP_NOFS); if (*name == NULL) return -ENOMEM; @@ -1198,14 +1200,19 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, return 0; } -static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr, - u32 *namelen, char **name, u64 *index) +static int ref_get_fields(struct extent_buffer *eb, int slot, + unsigned long ref_ptr, u32 *namelen, char **name, + u64 *index) { struct btrfs_inode_ref *ref; ref = (struct btrfs_inode_ref *)ref_ptr; *namelen = btrfs_inode_ref_name_len(eb, ref); + if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)(ref + 1), + *namelen)) + return -EIO; + *name = kmalloc(*namelen, GFP_NOFS); if (*name == NULL) return -ENOMEM; @@ -1280,8 +1287,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, while (ref_ptr < ref_end) { if (log_ref_ver) { - ret = extref_get_fields(eb, ref_ptr, &namelen, &name, - &ref_index, &parent_objectid); + ret = extref_get_fields(eb, slot, ref_ptr, &namelen, + &name, &ref_index, &parent_objectid); /* * parent object can change from one array * item to another. @@ -1293,8 +1300,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, goto out; } } else { - ret = ref_get_fields(eb, ref_ptr, &namelen, &name, - &ref_index); + ret = ref_get_fields(eb, slot, ref_ptr, &namelen, + &name, &ref_index); } if (ret) goto out; @@ -1841,7 +1848,7 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans, ptr_end = ptr + item_size; while (ptr < ptr_end) { di = (struct btrfs_dir_item *)ptr; - if (verify_dir_item(fs_info, eb, di)) + if (verify_dir_item(fs_info, eb, slot, di)) return -EIO; name_len = btrfs_dir_name_len(eb, di); ret = replay_one_name(trans, root, path, eb, di, key); @@ -2017,7 +2024,7 @@ again: ptr_end = ptr + item_size; while (ptr < ptr_end) { di = (struct btrfs_dir_item *)ptr; - if (verify_dir_item(fs_info, eb, di)) { + if (verify_dir_item(fs_info, eb, slot, di)) { ret = -EIO; goto out; } @@ -2102,6 +2109,7 @@ static int replay_xattr_deletes(struct btrfs_trans_handle *trans, struct btrfs_path *path, const u64 ino) { + struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key search_key; struct btrfs_path *log_path; int i; @@ -2143,6 +2151,11 @@ process_leaf: u32 this_len = sizeof(*di) + name_len + data_len; char *name; + ret = verify_dir_item(fs_info, path->nodes[0], i, di); + if (ret) { + ret = -EIO; + goto out; + } name = kmalloc(name_len, GFP_NOFS); if (!name) { ret = -ENOMEM; @@ -3675,7 +3688,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans, src_offset = btrfs_item_ptr_offset(src, start_slot + i); - if ((i == (nr - 1))) + if (i == nr - 1) last_key = ins_keys[i]; if (ins_keys[i].type == BTRFS_INODE_ITEM_KEY) { @@ -4168,6 +4181,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct extent_map *em, *n; struct list_head extents; struct extent_map_tree *tree = &inode->extent_tree; + u64 logged_start, logged_end; u64 test_gen; int ret = 0; int num = 0; @@ -4177,10 +4191,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, down_write(&inode->dio_sem); write_lock(&tree->lock); test_gen = root->fs_info->last_trans_committed; + logged_start = start; + logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { list_del_init(&em->list); - /* * Just an arbitrary number, this can be really CPU intensive * once we start getting a lot of extents, and really once we @@ -4195,6 +4210,12 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, if (em->generation <= test_gen) continue; + + if (em->start < logged_start) + logged_start = em->start; + if ((em->start + em->len - 1) > logged_end) + logged_end = em->start + em->len - 1; + /* Need a ref to keep it from getting evicted from cache */ refcount_inc(&em->refs); set_bit(EXTENT_FLAG_LOGGING, &em->flags); @@ -4203,7 +4224,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - btrfs_get_logged_extents(inode, logged_list, start, end); + btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end); /* * Some ordered extents started by fsync might have completed * before we could collect them into the list logged_list, which @@ -4435,7 +4456,10 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, len = btrfs_file_extent_inline_len(leaf, path->slots[0], extent); - ASSERT(len == i_size); + ASSERT(len == i_size || + (len == fs_info->sectorsize && + btrfs_file_extent_compression(leaf, extent) != + BTRFS_COMPRESS_NONE)); return 0; } @@ -4546,6 +4570,12 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, this_len = sizeof(*extref) + this_name_len; } + ret = btrfs_is_name_len_valid(eb, slot, name_ptr, + this_name_len); + if (!ret) { + ret = -EIO; + goto out; + } if (this_name_len > name_len) { char *new_name; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 017b67daa3bb..b39737568c22 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -152,7 +152,15 @@ struct list_head *btrfs_get_fs_uuids(void) return &fs_uuids; } -static struct btrfs_fs_devices *__alloc_fs_devices(void) +/* + * alloc_fs_devices - allocate struct btrfs_fs_devices + * @fsid: if not NULL, copy the uuid to fs_devices::fsid + * + * Return a pointer to a new struct btrfs_fs_devices on success, or ERR_PTR(). + * The returned struct is not linked onto any lists and can be destroyed with + * kfree() right away. + */ +static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid) { struct btrfs_fs_devices *fs_devs; @@ -166,31 +174,8 @@ static struct btrfs_fs_devices *__alloc_fs_devices(void) INIT_LIST_HEAD(&fs_devs->resized_devices); INIT_LIST_HEAD(&fs_devs->alloc_list); INIT_LIST_HEAD(&fs_devs->list); - - return fs_devs; -} - -/** - * alloc_fs_devices - allocate struct btrfs_fs_devices - * @fsid: a pointer to UUID for this FS. If NULL a new UUID is - * generated. - * - * Return: a pointer to a new &struct btrfs_fs_devices on success; - * ERR_PTR() on error. Returned struct is not linked onto any lists and - * can be destroyed with kfree() right away. - */ -static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid) -{ - struct btrfs_fs_devices *fs_devs; - - fs_devs = __alloc_fs_devices(); - if (IS_ERR(fs_devs)) - return fs_devs; - if (fsid) memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE); - else - generate_random_uuid(fs_devs->fsid); return fs_devs; } @@ -242,6 +227,17 @@ static struct btrfs_device *__alloc_device(void) if (!dev) return ERR_PTR(-ENOMEM); + /* + * Preallocate a bio that's always going to be used for flushing device + * barriers and matches the device lifespan + */ + dev->flush_bio = bio_alloc_bioset(GFP_KERNEL, 0, NULL); + if (!dev->flush_bio) { + kfree(dev); + return ERR_PTR(-ENOMEM); + } + bio_get(dev->flush_bio); + INIT_LIST_HEAD(&dev->dev_list); INIT_LIST_HEAD(&dev->dev_alloc_list); INIT_LIST_HEAD(&dev->resized_list); @@ -258,9 +254,17 @@ static struct btrfs_device *__alloc_device(void) return dev; } -static noinline struct btrfs_device *__find_device(struct list_head *head, - u64 devid, u8 *uuid) +/* + * Find a device specified by @devid or @uuid in the list of @fs_devices, or + * return NULL. + * + * If devid and uuid are both specified, the match must be exact, otherwise + * only devid is used. + */ +static struct btrfs_device *find_device(struct btrfs_fs_devices *fs_devices, + u64 devid, const u8 *uuid) { + struct list_head *head = &fs_devices->devices; struct btrfs_device *dev; list_for_each_entry(dev, head, dev_list) { @@ -299,7 +303,7 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder, if (flush) filemap_write_and_wait((*bdev)->bd_inode->i_mapping); - ret = set_blocksize(*bdev, 4096); + ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE); if (ret) { blkdev_put(*bdev, flags); goto error; @@ -625,8 +629,8 @@ static noinline int device_list_add(const char *path, device = NULL; } else { - device = __find_device(&fs_devices->devices, devid, - disk_super->dev_item.uuid); + device = find_device(fs_devices, devid, + disk_super->dev_item.uuid); } if (!device) { @@ -838,6 +842,7 @@ static void __free_device(struct work_struct *work) device = container_of(work, struct btrfs_device, rcu_work); rcu_string_free(device->name); + bio_put(device->flush_bio); kfree(device); } @@ -1353,15 +1358,13 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction, int ret; int slot; struct extent_buffer *l; - u64 min_search_start; /* * We don't want to overwrite the superblock on the drive nor any area * used by the boot loader (grub for example), so we make sure to start * at an offset of at least 1MB. */ - min_search_start = max(fs_info->alloc_start, 1024ull * 1024); - search_start = max(search_start, min_search_start); + search_start = max_t(u64, search_start, SZ_1M); path = btrfs_alloc_path(); if (!path) @@ -1568,7 +1571,6 @@ out: static int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, - u64 chunk_tree, u64 chunk_objectid, u64 chunk_offset, u64 start, u64 num_bytes) { int ret; @@ -1596,12 +1598,12 @@ static int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans, leaf = path->nodes[0]; extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); - btrfs_set_dev_extent_chunk_tree(leaf, extent, chunk_tree); - btrfs_set_dev_extent_chunk_objectid(leaf, extent, chunk_objectid); + btrfs_set_dev_extent_chunk_tree(leaf, extent, + BTRFS_CHUNK_TREE_OBJECTID); + btrfs_set_dev_extent_chunk_objectid(leaf, extent, + BTRFS_FIRST_CHUNK_TREE_OBJECTID); btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset); - write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid); - btrfs_set_dev_extent_length(leaf, extent, num_bytes); btrfs_mark_buffer_dirty(leaf); out: @@ -1716,7 +1718,7 @@ static int btrfs_add_device(struct btrfs_trans_handle *trans, ptr = btrfs_device_uuid(dev_item); write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE); ptr = btrfs_device_fsid(dev_item); - write_extent_buffer(leaf, fs_info->fsid, ptr, BTRFS_UUID_SIZE); + write_extent_buffer(leaf, fs_info->fsid, ptr, BTRFS_FSID_SIZE); btrfs_mark_buffer_dirty(leaf); ret = 0; @@ -1862,7 +1864,6 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, struct btrfs_fs_devices *cur_devices; u64 num_devices; int ret = 0; - bool clear_super = false; mutex_lock(&uuid_mutex); @@ -1898,7 +1899,6 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, list_del_init(&device->dev_alloc_list); device->fs_devices->rw_devices--; mutex_unlock(&fs_info->chunk_mutex); - clear_super = true; } mutex_unlock(&uuid_mutex); @@ -1977,9 +1977,6 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path, free_fs_devices(cur_devices); } - fs_info->num_tolerated_disk_barrier_failures = - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); - out: mutex_unlock(&uuid_mutex); return ret; @@ -2192,7 +2189,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info) if (!fs_devices->seeding) return -EINVAL; - seed_devices = __alloc_fs_devices(); + seed_devices = alloc_fs_devices(NULL); if (IS_ERR(seed_devices)) return PTR_ERR(seed_devices); @@ -2251,7 +2248,7 @@ static int btrfs_finish_sprout(struct btrfs_trans_handle *trans, struct btrfs_dev_item *dev_item; struct btrfs_device *device; struct btrfs_key key; - u8 fs_uuid[BTRFS_UUID_SIZE]; + u8 fs_uuid[BTRFS_FSID_SIZE]; u8 dev_uuid[BTRFS_UUID_SIZE]; u64 devid; int ret; @@ -2294,7 +2291,7 @@ next_slot: read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item), BTRFS_UUID_SIZE); read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item), - BTRFS_UUID_SIZE); + BTRFS_FSID_SIZE); device = btrfs_find_device(fs_info, devid, dev_uuid, fs_uuid); BUG_ON(!device); /* Logic error */ @@ -2327,7 +2324,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path int seeding_dev = 0; int ret = 0; - if ((sb->s_flags & MS_RDONLY) && !fs_info->fs_devices->seeding) + if (sb_rdonly(sb) && !fs_info->fs_devices->seeding) return -EROFS; bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, @@ -2387,7 +2384,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->io_width = fs_info->sectorsize; device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; - device->total_bytes = i_size_read(bdev->bd_inode); + device->total_bytes = round_down(i_size_read(bdev->bd_inode), + fs_info->sectorsize); device->disk_total_bytes = device->total_bytes; device->commit_total_bytes = device->total_bytes; device->fs_info = fs_info; @@ -2396,7 +2394,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->is_tgtdev_for_dev_replace = 0; device->mode = FMODE_EXCL; device->dev_stats_valid = 1; - set_blocksize(device->bdev, 4096); + set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); if (seeding_dev) { sb->s_flags &= ~MS_RDONLY; @@ -2417,16 +2415,14 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path fs_info->fs_devices->total_devices++; fs_info->fs_devices->total_rw_bytes += device->total_bytes; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += device->total_bytes; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(device->total_bytes, &fs_info->free_chunk_space); if (!blk_queue_nonrot(q)) fs_info->fs_devices->rotating = 1; tmp = btrfs_super_total_bytes(fs_info->super_copy); btrfs_set_super_total_bytes(fs_info->super_copy, - tmp + device->total_bytes); + round_down(tmp + device->total_bytes, fs_info->sectorsize)); tmp = btrfs_super_num_devices(fs_info->super_copy); btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1); @@ -2478,8 +2474,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path "sysfs: failed to create fsid for sprout"); } - fs_info->num_tolerated_disk_barrier_failures = - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); ret = btrfs_commit_transaction(trans); if (seeding_dev) { @@ -2574,7 +2568,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, goto error; } - name = rcu_string_strdup(device_path, GFP_NOFS); + name = rcu_string_strdup(device_path, GFP_KERNEL); if (!name) { kfree(device); ret = -ENOMEM; @@ -2603,7 +2597,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, device->is_tgtdev_for_dev_replace = 1; device->mode = FMODE_EXCL; device->dev_stats_valid = 1; - set_blocksize(device->bdev, 4096); + set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE); device->fs_devices = fs_info->fs_devices; list_add(&device->dev_list, &fs_info->fs_devices->devices); fs_info->fs_devices->num_devices++; @@ -2689,9 +2683,11 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, if (!device->writeable) return -EACCES; + new_size = round_down(new_size, fs_info->sectorsize); + mutex_lock(&fs_info->chunk_mutex); old_total = btrfs_super_total_bytes(super_copy); - diff = new_size - device->total_bytes; + diff = round_down(new_size - device->total_bytes, fs_info->sectorsize); if (new_size <= device->total_bytes || device->is_tgtdev_for_dev_replace) { @@ -2701,7 +2697,8 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, fs_devices = fs_info->fs_devices; - btrfs_set_super_total_bytes(super_copy, old_total + diff); + btrfs_set_super_total_bytes(super_copy, + round_down(old_total + diff, fs_info->sectorsize)); device->fs_devices->total_rw_bytes += diff; btrfs_device_set_total_bytes(device, new_size); @@ -2716,8 +2713,7 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans, } static int btrfs_free_chunk(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 chunk_objectid, - u64 chunk_offset) + struct btrfs_fs_info *fs_info, u64 chunk_offset) { struct btrfs_root *root = fs_info->chunk_root; int ret; @@ -2728,7 +2724,7 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, if (!path) return -ENOMEM; - key.objectid = chunk_objectid; + key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; key.offset = chunk_offset; key.type = BTRFS_CHUNK_ITEM_KEY; @@ -2751,8 +2747,7 @@ out: return ret; } -static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, - u64 chunk_objectid, u64 chunk_offset) +static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) { struct btrfs_super_block *super_copy = fs_info->super_copy; struct btrfs_disk_key *disk_key; @@ -2785,7 +2780,7 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info, ret = -EIO; break; } - if (key.objectid == chunk_objectid && + if (key.objectid == BTRFS_FIRST_CHUNK_TREE_OBJECTID && key.offset == chunk_offset) { memmove(ptr, ptr + len, array_size - (cur + len)); array_size -= len; @@ -2834,7 +2829,6 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, struct extent_map *em; struct map_lookup *map; u64 dev_extent_len = 0; - u64 chunk_objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; int i, ret = 0; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2874,9 +2868,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, mutex_lock(&fs_info->chunk_mutex); btrfs_device_set_bytes_used(device, device->bytes_used - dev_extent_len); - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += dev_extent_len; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(dev_extent_len, &fs_info->free_chunk_space); btrfs_clear_space_info_full(fs_info); mutex_unlock(&fs_info->chunk_mutex); } @@ -2892,7 +2884,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, } mutex_unlock(&fs_devices->device_list_mutex); - ret = btrfs_free_chunk(trans, fs_info, chunk_objectid, chunk_offset); + ret = btrfs_free_chunk(trans, fs_info, chunk_offset); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -2901,8 +2893,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, trace_btrfs_chunk_free(fs_info, map, chunk_offset, em->len); if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) { - ret = btrfs_del_sys_chunk(fs_info, chunk_objectid, - chunk_offset); + ret = btrfs_del_sys_chunk(fs_info, chunk_offset); if (ret) { btrfs_abort_transaction(trans, ret); goto out; @@ -3302,7 +3293,6 @@ static int chunk_devid_filter(struct extent_buffer *leaf, /* [pstart, pend) */ static int chunk_drange_filter(struct extent_buffer *leaf, struct btrfs_chunk *chunk, - u64 chunk_offset, struct btrfs_balance_args *bargs) { struct btrfs_stripe *stripe; @@ -3429,7 +3419,7 @@ static int should_balance_chunk(struct btrfs_fs_info *fs_info, /* drange filter, makes sense only with devid filter */ if ((bargs->flags & BTRFS_BALANCE_ARGS_DRANGE) && - chunk_drange_filter(leaf, chunk, chunk_offset, bargs)) { + chunk_drange_filter(leaf, chunk, bargs)) { return 0; } @@ -3888,13 +3878,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl, meta_target, data_target); } - if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) { - fs_info->num_tolerated_disk_barrier_failures = min( - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info), - btrfs_get_num_tolerated_disk_barrier_failures( - bctl->sys.target)); - } - ret = insert_balance_item(fs_info, bctl); if (ret && ret != -EEXIST) goto out; @@ -3917,11 +3900,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl, mutex_lock(&fs_info->balance_mutex); atomic_dec(&fs_info->balance_running); - if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) { - fs_info->num_tolerated_disk_barrier_failures = - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); - } - if (bargs) { memset(bargs, 0, sizeof(*bargs)); update_ioctl_balance_args(fs_info, 0, bargs); @@ -4075,7 +4053,7 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info) int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) { - if (fs_info->sb->s_flags & MS_RDONLY) + if (sb_rdonly(fs_info->sb)) return -EROFS; mutex_lock(&fs_info->balance_mutex); @@ -4117,7 +4095,6 @@ static int btrfs_uuid_scan_kthread(void *data) struct btrfs_fs_info *fs_info = data; struct btrfs_root *root = fs_info->tree_root; struct btrfs_key key; - struct btrfs_key max_key; struct btrfs_path *path = NULL; int ret = 0; struct extent_buffer *eb; @@ -4136,10 +4113,6 @@ static int btrfs_uuid_scan_kthread(void *data) key.type = BTRFS_ROOT_ITEM_KEY; key.offset = 0; - max_key.objectid = (u64)-1; - max_key.type = BTRFS_ROOT_ITEM_KEY; - max_key.offset = (u64)-1; - while (1) { ret = btrfs_search_forward(root, &key, path, 0); if (ret) { @@ -4393,7 +4366,10 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) struct btrfs_super_block *super_copy = fs_info->super_copy; u64 old_total = btrfs_super_total_bytes(super_copy); u64 old_size = btrfs_device_get_total_bytes(device); - u64 diff = old_size - new_size; + u64 diff; + + new_size = round_down(new_size, fs_info->sectorsize); + diff = round_down(old_size - new_size, fs_info->sectorsize); if (device->is_tgtdev_for_dev_replace) return -EINVAL; @@ -4409,9 +4385,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size) btrfs_device_set_total_bytes(device, new_size); if (device->writeable) { device->fs_devices->total_rw_bytes -= diff; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space -= diff; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_sub(diff, &fs_info->free_chunk_space); } mutex_unlock(&fs_info->chunk_mutex); @@ -4522,7 +4496,8 @@ again: &fs_info->fs_devices->resized_devices); WARN_ON(diff > old_total); - btrfs_set_super_total_bytes(super_copy, old_total - diff); + btrfs_set_super_total_bytes(super_copy, + round_down(old_total - diff, fs_info->sectorsize)); mutex_unlock(&fs_info->chunk_mutex); /* Now btrfs_update_device() will change the on-disk size. */ @@ -4535,9 +4510,7 @@ done: btrfs_device_set_total_bytes(device, old_size); if (device->writeable) device->fs_devices->total_rw_bytes += diff; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += diff; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(diff, &fs_info->free_chunk_space); mutex_unlock(&fs_info->chunk_mutex); } return ret; @@ -4591,12 +4564,6 @@ static int btrfs_cmp_device_info(const void *a, const void *b) return 0; } -static u32 find_raid56_stripe_len(u32 data_devices, u32 dev_stripe_target) -{ - /* TODO allow them to set a preferred stripe size */ - return SZ_64K; -} - static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type) { if (!(type & BTRFS_BLOCK_GROUP_RAID56_MASK)) @@ -4619,7 +4586,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *info = trans->fs_info; struct btrfs_fs_devices *fs_devices = info->fs_devices; - struct list_head *cur; + struct btrfs_device *device; struct map_lookup *map = NULL; struct extent_map_tree *em_tree; struct extent_map *em; @@ -4639,7 +4606,6 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 max_chunk_size; u64 stripe_size; u64 num_bytes; - u64 raid_stripe_len = BTRFS_STRIPE_LEN; int ndevs; int i; int j; @@ -4693,22 +4659,15 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, if (!devices_info) return -ENOMEM; - cur = fs_devices->alloc_list.next; - /* * in the first pass through the devices list, we gather information * about the available holes on each device. */ ndevs = 0; - while (cur != &fs_devices->alloc_list) { - struct btrfs_device *device; + list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { u64 max_avail; u64 dev_offset; - device = list_entry(cur, struct btrfs_device, dev_alloc_list); - - cur = cur->next; - if (!device->writeable) { WARN(1, KERN_ERR "BTRFS: read-only device in alloc_list\n"); @@ -4759,15 +4718,15 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, btrfs_cmp_device_info, NULL); /* round down to number of usable stripes */ - ndevs -= ndevs % devs_increment; + ndevs = round_down(ndevs, devs_increment); if (ndevs < devs_increment * sub_stripes || ndevs < devs_min) { ret = -ENOSPC; goto error; } - if (devs_max && ndevs > devs_max) - ndevs = devs_max; + ndevs = min(ndevs, devs_max); + /* * the primary goal is to maximize the number of stripes, so use as many * devices as possible, even if the stripes are not maximum sized. @@ -4781,16 +4740,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, */ data_stripes = num_stripes / ncopies; - if (type & BTRFS_BLOCK_GROUP_RAID5) { - raid_stripe_len = find_raid56_stripe_len(ndevs - 1, - info->stripesize); + if (type & BTRFS_BLOCK_GROUP_RAID5) data_stripes = num_stripes - 1; - } - if (type & BTRFS_BLOCK_GROUP_RAID6) { - raid_stripe_len = find_raid56_stripe_len(ndevs - 2, - info->stripesize); + + if (type & BTRFS_BLOCK_GROUP_RAID6) data_stripes = num_stripes - 2; - } /* * Use the number of data stripes to figure out how big this chunk @@ -4815,8 +4769,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = div_u64(stripe_size, dev_stripes); /* align to BTRFS_STRIPE_LEN */ - stripe_size = div64_u64(stripe_size, raid_stripe_len); - stripe_size *= raid_stripe_len; + stripe_size = round_down(stripe_size, BTRFS_STRIPE_LEN); map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS); if (!map) { @@ -4833,10 +4786,9 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, j * stripe_size; } } - map->sector_size = info->sectorsize; - map->stripe_len = raid_stripe_len; - map->io_align = raid_stripe_len; - map->io_width = raid_stripe_len; + map->stripe_len = BTRFS_STRIPE_LEN; + map->io_align = BTRFS_STRIPE_LEN; + map->io_width = BTRFS_STRIPE_LEN; map->type = type; map->sub_stripes = sub_stripes; @@ -4871,9 +4823,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, goto error; } - ret = btrfs_make_block_group(trans, info, 0, type, - BTRFS_FIRST_CHUNK_TREE_OBJECTID, - start, num_bytes); + ret = btrfs_make_block_group(trans, info, 0, type, start, num_bytes); if (ret) goto error_del_extent; @@ -4882,9 +4832,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes); } - spin_lock(&info->free_chunk_lock); - info->free_chunk_space -= (stripe_size * map->num_stripes); - spin_unlock(&info->free_chunk_lock); + atomic64_sub(stripe_size * map->num_stripes, &info->free_chunk_space); free_extent_map(em); check_raid56_incompat_flag(info, type); @@ -4955,11 +4903,8 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, ret = btrfs_update_device(trans, device); if (ret) break; - ret = btrfs_alloc_dev_extent(trans, device, - chunk_root->root_key.objectid, - BTRFS_FIRST_CHUNK_TREE_OBJECTID, - chunk_offset, dev_offset, - stripe_size); + ret = btrfs_alloc_dev_extent(trans, device, chunk_offset, + dev_offset, stripe_size); if (ret) break; } @@ -5029,20 +4974,19 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info) { - struct btrfs_root *extent_root = fs_info->extent_root; u64 chunk_offset; u64 sys_chunk_offset; u64 alloc_profile; int ret; chunk_offset = find_next_chunk(fs_info); - alloc_profile = btrfs_get_alloc_profile(extent_root, 0); + alloc_profile = btrfs_metadata_alloc_profile(fs_info); ret = __btrfs_alloc_chunk(trans, chunk_offset, alloc_profile); if (ret) return ret; sys_chunk_offset = find_next_chunk(fs_info); - alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0); + alloc_profile = btrfs_system_alloc_profile(fs_info); ret = __btrfs_alloc_chunk(trans, sys_chunk_offset, alloc_profile); return ret; } @@ -5165,7 +5109,6 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len) } unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, - struct btrfs_mapping_tree *map_tree, u64 logical) { struct extent_map *em; @@ -5173,29 +5116,30 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, unsigned long len = fs_info->sectorsize; em = get_chunk_map(fs_info, logical, len); - WARN_ON(IS_ERR(em)); - map = em->map_lookup; - if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) - len = map->stripe_len * nr_data_stripes(map); - free_extent_map(em); + if (!WARN_ON(IS_ERR(em))) { + map = em->map_lookup; + if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) + len = map->stripe_len * nr_data_stripes(map); + free_extent_map(em); + } return len; } -int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, - u64 logical, u64 len, int mirror_num) +int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, u64 logical, u64 len) { struct extent_map *em; struct map_lookup *map; int ret = 0; em = get_chunk_map(fs_info, logical, len); - WARN_ON(IS_ERR(em)); - map = em->map_lookup; - if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) - ret = 1; - free_extent_map(em); + if(!WARN_ON(IS_ERR(em))) { + map = em->map_lookup; + if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) + ret = 1; + free_extent_map(em); + } return ret; } @@ -6042,9 +5986,10 @@ static void btrfs_end_bio(struct bio *bio) struct btrfs_bio *bbio = bio->bi_private; int is_orig_bio = 0; - if (bio->bi_error) { + if (bio->bi_status) { atomic_inc(&bbio->error); - if (bio->bi_error == -EIO || bio->bi_error == -EREMOTEIO) { + if (bio->bi_status == BLK_STS_IOERR || + bio->bi_status == BLK_STS_TARGET) { unsigned int stripe_index = btrfs_io_bio(bio)->stripe_index; struct btrfs_device *dev; @@ -6082,13 +6027,13 @@ static void btrfs_end_bio(struct bio *bio) * beyond the tolerance of the btrfs bio */ if (atomic_read(&bbio->error) > bbio->max_errors) { - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; } else { /* * this bio is actually up to date, we didn't * go over the max number of errors */ - bio->bi_error = 0; + bio->bi_status = 0; } btrfs_end_bbio(bbio, bio); @@ -6180,7 +6125,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio, rcu_read_unlock(); } #endif - bio->bi_bdev = dev->bdev; + bio_set_dev(bio, dev->bdev); btrfs_bio_counter_inc_noblocked(fs_info); @@ -6199,13 +6144,13 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; bio->bi_iter.bi_sector = logical >> 9; - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; btrfs_end_bbio(bbio, bio); } } -int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, int async_submit) +blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, int async_submit) { struct btrfs_device *dev; struct bio *first_bio = bio; @@ -6221,11 +6166,11 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, map_length = length; btrfs_bio_counter_inc_blocked(fs_info); - ret = __btrfs_map_block(fs_info, bio_op(bio), logical, + ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical, &map_length, &bbio, mirror_num, 1); if (ret) { btrfs_bio_counter_dec(fs_info); - return ret; + return errno_to_blk_status(ret); } total_devs = bbio->num_stripes; @@ -6248,7 +6193,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, } btrfs_bio_counter_dec(fs_info); - return ret; + return errno_to_blk_status(ret); } if (map_length < length) { @@ -6266,17 +6211,16 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, continue; } - if (dev_nr < total_devs - 1) { - bio = btrfs_bio_clone(first_bio, GFP_NOFS); - BUG_ON(!bio); /* -ENOMEM */ - } else + if (dev_nr < total_devs - 1) + bio = btrfs_bio_clone(first_bio); + else bio = first_bio; submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical, dev_nr, async_submit); } btrfs_bio_counter_dec(fs_info); - return 0; + return BLK_STS_OK; } struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid, @@ -6288,9 +6232,8 @@ struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid, cur_devices = fs_info->fs_devices; while (cur_devices) { if (!fsid || - !memcmp(cur_devices->fsid, fsid, BTRFS_UUID_SIZE)) { - device = __find_device(&cur_devices->devices, - devid, uuid); + !memcmp(cur_devices->fsid, fsid, BTRFS_FSID_SIZE)) { + device = find_device(cur_devices, devid, uuid); if (device) return device; } @@ -6443,7 +6386,6 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, struct extent_map *em; u64 logical; u64 length; - u64 stripe_len; u64 devid; u8 uuid[BTRFS_UUID_SIZE]; int num_stripes; @@ -6452,7 +6394,6 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, logical = key->offset; length = btrfs_chunk_length(leaf, chunk); - stripe_len = btrfs_chunk_stripe_len(leaf, chunk); num_stripes = btrfs_chunk_num_stripes(leaf, chunk); ret = btrfs_check_chunk_valid(fs_info, leaf, chunk, logical); @@ -6491,7 +6432,6 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, map->num_stripes = num_stripes; map->io_width = btrfs_chunk_io_width(leaf, chunk); map->io_align = btrfs_chunk_io_align(leaf, chunk); - map->sector_size = btrfs_chunk_sector_size(leaf, chunk); map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk); map->type = btrfs_chunk_type(leaf, chunk); map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); @@ -6507,6 +6447,7 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, if (!map->stripes[i].dev && !btrfs_test_opt(fs_info, DEGRADED)) { free_extent_map(em); + btrfs_report_missing_device(fs_info, devid, uuid); return -EIO; } if (!map->stripes[i].dev) { @@ -6517,8 +6458,7 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key, free_extent_map(em); return -EIO; } - btrfs_warn(fs_info, "devid %llu uuid %pU is missing", - devid, uuid); + btrfs_report_missing_device(fs_info, devid, uuid); } map->stripes[i].dev->in_fs_metadata = 1; } @@ -6562,10 +6502,11 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info, int ret; BUG_ON(!mutex_is_locked(&uuid_mutex)); + ASSERT(fsid); fs_devices = fs_info->fs_devices->seed; while (fs_devices) { - if (!memcmp(fs_devices->fsid, fsid, BTRFS_UUID_SIZE)) + if (!memcmp(fs_devices->fsid, fsid, BTRFS_FSID_SIZE)) return fs_devices; fs_devices = fs_devices->seed; @@ -6618,16 +6559,16 @@ static int read_one_dev(struct btrfs_fs_info *fs_info, struct btrfs_device *device; u64 devid; int ret; - u8 fs_uuid[BTRFS_UUID_SIZE]; + u8 fs_uuid[BTRFS_FSID_SIZE]; u8 dev_uuid[BTRFS_UUID_SIZE]; devid = btrfs_device_id(leaf, dev_item); read_extent_buffer(leaf, dev_uuid, btrfs_device_uuid(dev_item), BTRFS_UUID_SIZE); read_extent_buffer(leaf, fs_uuid, btrfs_device_fsid(dev_item), - BTRFS_UUID_SIZE); + BTRFS_FSID_SIZE); - if (memcmp(fs_uuid, fs_info->fsid, BTRFS_UUID_SIZE)) { + if (memcmp(fs_uuid, fs_info->fsid, BTRFS_FSID_SIZE)) { fs_devices = open_seed_devices(fs_info, fs_uuid); if (IS_ERR(fs_devices)) return PTR_ERR(fs_devices); @@ -6635,17 +6576,21 @@ static int read_one_dev(struct btrfs_fs_info *fs_info, device = btrfs_find_device(fs_info, devid, dev_uuid, fs_uuid); if (!device) { - if (!btrfs_test_opt(fs_info, DEGRADED)) + if (!btrfs_test_opt(fs_info, DEGRADED)) { + btrfs_report_missing_device(fs_info, devid, dev_uuid); return -EIO; + } device = add_missing_dev(fs_devices, devid, dev_uuid); if (!device) return -ENOMEM; - btrfs_warn(fs_info, "devid %llu uuid %pU missing", - devid, dev_uuid); + btrfs_report_missing_device(fs_info, devid, dev_uuid); } else { - if (!device->bdev && !btrfs_test_opt(fs_info, DEGRADED)) - return -EIO; + if (!device->bdev) { + btrfs_report_missing_device(fs_info, devid, dev_uuid); + if (!btrfs_test_opt(fs_info, DEGRADED)) + return -EIO; + } if(!device->bdev && !device->missing) { /* @@ -6684,10 +6629,8 @@ static int read_one_dev(struct btrfs_fs_info *fs_info, device->in_fs_metadata = 1; if (device->writeable && !device->is_tgtdev_for_dev_replace) { device->fs_devices->total_rw_bytes += device->total_bytes; - spin_lock(&fs_info->free_chunk_lock); - fs_info->free_chunk_space += device->total_bytes - - device->bytes_used; - spin_unlock(&fs_info->free_chunk_lock); + atomic64_add(device->total_bytes - device->bytes_used, + &fs_info->free_chunk_space); } ret = 0; return ret; @@ -6813,6 +6756,70 @@ out_short_read: return -EIO; } +void btrfs_report_missing_device(struct btrfs_fs_info *fs_info, u64 devid, + u8 *uuid) +{ + btrfs_warn_rl(fs_info, "devid %llu uuid %pU is missing", devid, uuid); +} + +/* + * Check if all chunks in the fs are OK for read-write degraded mount + * + * Return true if all chunks meet the minimal RW mount requirements. + * Return false if any chunk doesn't meet the minimal RW mount requirements. + */ +bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info) +{ + struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree; + struct extent_map *em; + u64 next_start = 0; + bool ret = true; + + read_lock(&map_tree->map_tree.lock); + em = lookup_extent_mapping(&map_tree->map_tree, 0, (u64)-1); + read_unlock(&map_tree->map_tree.lock); + /* No chunk at all? Return false anyway */ + if (!em) { + ret = false; + goto out; + } + while (em) { + struct map_lookup *map; + int missing = 0; + int max_tolerated; + int i; + + map = em->map_lookup; + max_tolerated = + btrfs_get_num_tolerated_disk_barrier_failures( + map->type); + for (i = 0; i < map->num_stripes; i++) { + struct btrfs_device *dev = map->stripes[i].dev; + + if (!dev || !dev->bdev || dev->missing || + dev->last_flush_error) + missing++; + } + if (missing > max_tolerated) { + btrfs_warn(fs_info, + "chunk %llu missing %d devices, max tolerance is %d for writeable mount", + em->start, missing, max_tolerated); + free_extent_map(em); + ret = false; + goto out; + } + next_start = extent_map_end(em); + free_extent_map(em); + + read_lock(&map_tree->map_tree.lock); + em = lookup_extent_mapping(&map_tree->map_tree, next_start, + (u64)(-1) - next_start); + read_unlock(&map_tree->map_tree.lock); + } +out: + return ret; +} + int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) { struct btrfs_root *root = fs_info->chunk_root; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index c7d0fbc915ca..6108fdfec67f 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -74,6 +74,8 @@ struct btrfs_device { int missing; int can_discard; int is_tgtdev_for_dev_replace; + blk_status_t last_flush_error; + int flush_bio_sent; #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED seqcount_t data_seqcount; @@ -279,6 +281,11 @@ struct btrfs_io_bio { u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE]; u8 *csum_allocated; btrfs_io_bio_end_io_t *end_io; + struct bvec_iter iter; + /* + * This member must come last, bio_alloc_bioset will allocate enough + * bytes for entire btrfs_io_bio but relies on bio being last. + */ struct bio bio; }; @@ -346,7 +353,6 @@ struct map_lookup { int io_align; int io_width; u64 stripe_len; - int sector_size; int num_stripes; int sub_stripes; struct btrfs_bio_stripe stripes[]; @@ -409,8 +415,8 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 type); void btrfs_mapping_init(struct btrfs_mapping_tree *tree); void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree); -int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, int async_submit); +blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, int async_submit); int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fmode_t flags, void *holder); int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, @@ -474,9 +480,8 @@ void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info, struct btrfs_device *tgtdev); void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path); int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info, - u64 logical, u64 len, int mirror_num); + u64 logical, u64 len); unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info, - struct btrfs_mapping_tree *map_tree, u64 logical); int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, @@ -536,4 +541,8 @@ struct list_head *btrfs_get_fs_uuids(void); void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info); void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info); +bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info); +void btrfs_report_missing_device(struct btrfs_fs_info *fs_info, u64 devid, + u8 *uuid); + #endif diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index b3cbf80c5acf..2c7e53f9ff1b 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -336,7 +336,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size) u32 this_len = sizeof(*di) + name_len + data_len; unsigned long name_ptr = (unsigned long)(di + 1); - if (verify_dir_item(fs_info, leaf, di)) { + if (verify_dir_item(fs_info, leaf, slot, di)) { ret = -EIO; goto err; } diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 135b10823c6d..c248f9286366 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -24,12 +24,13 @@ #include <linux/slab.h> #include <linux/zlib.h> #include <linux/zutil.h> -#include <linux/vmalloc.h> +#include <linux/mm.h> #include <linux/init.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/pagemap.h> #include <linux/bio.h> +#include <linux/refcount.h> #include "compression.h" struct workspace { @@ -42,7 +43,7 @@ static void zlib_free_workspace(struct list_head *ws) { struct workspace *workspace = list_entry(ws, struct workspace, list); - vfree(workspace->strm.workspace); + kvfree(workspace->strm.workspace); kfree(workspace->buf); kfree(workspace); } @@ -52,14 +53,14 @@ static struct list_head *zlib_alloc_workspace(void) struct workspace *workspace; int workspacesize; - workspace = kzalloc(sizeof(*workspace), GFP_NOFS); + workspace = kzalloc(sizeof(*workspace), GFP_KERNEL); if (!workspace) return ERR_PTR(-ENOMEM); workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = vmalloc(workspacesize); - workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS); + workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL); + workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!workspace->strm.workspace || !workspace->buf) goto fail; @@ -211,10 +212,7 @@ out: return ret; } -static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in, - u64 disk_start, - struct bio *orig_bio, - size_t srclen) +static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb) { struct workspace *workspace = list_entry(ws, struct workspace, list); int ret = 0, ret2; @@ -222,8 +220,12 @@ static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in, char *data_in; size_t total_out = 0; unsigned long page_in_index = 0; + size_t srclen = cb->compressed_len; unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; + struct page **pages_in = cb->compressed_pages; + u64 disk_start = cb->start; + struct bio *orig_bio = cb->orig_bio; data_in = kmap(pages_in[page_in_index]); workspace->strm.next_in = data_in; diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c new file mode 100644 index 000000000000..607ce47b483a --- /dev/null +++ b/fs/btrfs/zstd.c @@ -0,0 +1,432 @@ +/* + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#include <linux/bio.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/refcount.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/zstd.h> +#include "compression.h" + +#define ZSTD_BTRFS_MAX_WINDOWLOG 17 +#define ZSTD_BTRFS_MAX_INPUT (1 << ZSTD_BTRFS_MAX_WINDOWLOG) +#define ZSTD_BTRFS_DEFAULT_LEVEL 3 + +static ZSTD_parameters zstd_get_btrfs_parameters(size_t src_len) +{ + ZSTD_parameters params = ZSTD_getParams(ZSTD_BTRFS_DEFAULT_LEVEL, + src_len, 0); + + if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG) + params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG; + WARN_ON(src_len > ZSTD_BTRFS_MAX_INPUT); + return params; +} + +struct workspace { + void *mem; + size_t size; + char *buf; + struct list_head list; +}; + +static void zstd_free_workspace(struct list_head *ws) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + + kvfree(workspace->mem); + kfree(workspace->buf); + kfree(workspace); +} + +static struct list_head *zstd_alloc_workspace(void) +{ + ZSTD_parameters params = + zstd_get_btrfs_parameters(ZSTD_BTRFS_MAX_INPUT); + struct workspace *workspace; + + workspace = kzalloc(sizeof(*workspace), GFP_KERNEL); + if (!workspace) + return ERR_PTR(-ENOMEM); + + workspace->size = max_t(size_t, + ZSTD_CStreamWorkspaceBound(params.cParams), + ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT)); + workspace->mem = kvmalloc(workspace->size, GFP_KERNEL); + workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!workspace->mem || !workspace->buf) + goto fail; + + INIT_LIST_HEAD(&workspace->list); + + return &workspace->list; +fail: + zstd_free_workspace(&workspace->list); + return ERR_PTR(-ENOMEM); +} + +static int zstd_compress_pages(struct list_head *ws, + struct address_space *mapping, + u64 start, + struct page **pages, + unsigned long *out_pages, + unsigned long *total_in, + unsigned long *total_out) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + ZSTD_CStream *stream; + int ret = 0; + int nr_pages = 0; + struct page *in_page = NULL; /* The current page to read */ + struct page *out_page = NULL; /* The current page to write to */ + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + unsigned long tot_in = 0; + unsigned long tot_out = 0; + unsigned long len = *total_out; + const unsigned long nr_dest_pages = *out_pages; + unsigned long max_out = nr_dest_pages * PAGE_SIZE; + ZSTD_parameters params = zstd_get_btrfs_parameters(len); + + *out_pages = 0; + *total_out = 0; + *total_in = 0; + + /* Initialize the stream */ + stream = ZSTD_initCStream(params, len, workspace->mem, + workspace->size); + if (!stream) { + pr_warn("BTRFS: ZSTD_initCStream failed\n"); + ret = -EIO; + goto out; + } + + /* map in the first page of input data */ + in_page = find_get_page(mapping, start >> PAGE_SHIFT); + in_buf.src = kmap(in_page); + in_buf.pos = 0; + in_buf.size = min_t(size_t, len, PAGE_SIZE); + + + /* Allocate and map in the output buffer */ + out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (out_page == NULL) { + ret = -ENOMEM; + goto out; + } + pages[nr_pages++] = out_page; + out_buf.dst = kmap(out_page); + out_buf.pos = 0; + out_buf.size = min_t(size_t, max_out, PAGE_SIZE); + + while (1) { + size_t ret2; + + ret2 = ZSTD_compressStream(stream, &out_buf, &in_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_compressStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto out; + } + + /* Check to see if we are making it bigger */ + if (tot_in + in_buf.pos > 8192 && + tot_in + in_buf.pos < + tot_out + out_buf.pos) { + ret = -E2BIG; + goto out; + } + + /* We've reached the end of our output range */ + if (out_buf.pos >= max_out) { + tot_out += out_buf.pos; + ret = -E2BIG; + goto out; + } + + /* Check if we need more output space */ + if (out_buf.pos == out_buf.size) { + tot_out += PAGE_SIZE; + max_out -= PAGE_SIZE; + kunmap(out_page); + if (nr_pages == nr_dest_pages) { + out_page = NULL; + ret = -E2BIG; + goto out; + } + out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (out_page == NULL) { + ret = -ENOMEM; + goto out; + } + pages[nr_pages++] = out_page; + out_buf.dst = kmap(out_page); + out_buf.pos = 0; + out_buf.size = min_t(size_t, max_out, PAGE_SIZE); + } + + /* We've reached the end of the input */ + if (in_buf.pos >= len) { + tot_in += in_buf.pos; + break; + } + + /* Check if we need more input */ + if (in_buf.pos == in_buf.size) { + tot_in += PAGE_SIZE; + kunmap(in_page); + put_page(in_page); + + start += PAGE_SIZE; + len -= PAGE_SIZE; + in_page = find_get_page(mapping, start >> PAGE_SHIFT); + in_buf.src = kmap(in_page); + in_buf.pos = 0; + in_buf.size = min_t(size_t, len, PAGE_SIZE); + } + } + while (1) { + size_t ret2; + + ret2 = ZSTD_endStream(stream, &out_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_endStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto out; + } + if (ret2 == 0) { + tot_out += out_buf.pos; + break; + } + if (out_buf.pos >= max_out) { + tot_out += out_buf.pos; + ret = -E2BIG; + goto out; + } + + tot_out += PAGE_SIZE; + max_out -= PAGE_SIZE; + kunmap(out_page); + if (nr_pages == nr_dest_pages) { + out_page = NULL; + ret = -E2BIG; + goto out; + } + out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM); + if (out_page == NULL) { + ret = -ENOMEM; + goto out; + } + pages[nr_pages++] = out_page; + out_buf.dst = kmap(out_page); + out_buf.pos = 0; + out_buf.size = min_t(size_t, max_out, PAGE_SIZE); + } + + if (tot_out >= tot_in) { + ret = -E2BIG; + goto out; + } + + ret = 0; + *total_in = tot_in; + *total_out = tot_out; +out: + *out_pages = nr_pages; + /* Cleanup */ + if (in_page) { + kunmap(in_page); + put_page(in_page); + } + if (out_page) + kunmap(out_page); + return ret; +} + +static int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + struct page **pages_in = cb->compressed_pages; + u64 disk_start = cb->start; + struct bio *orig_bio = cb->orig_bio; + size_t srclen = cb->compressed_len; + ZSTD_DStream *stream; + int ret = 0; + unsigned long page_in_index = 0; + unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); + unsigned long buf_start; + unsigned long total_out = 0; + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + + stream = ZSTD_initDStream( + ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); + if (!stream) { + pr_debug("BTRFS: ZSTD_initDStream failed\n"); + ret = -EIO; + goto done; + } + + in_buf.src = kmap(pages_in[page_in_index]); + in_buf.pos = 0; + in_buf.size = min_t(size_t, srclen, PAGE_SIZE); + + out_buf.dst = workspace->buf; + out_buf.pos = 0; + out_buf.size = PAGE_SIZE; + + while (1) { + size_t ret2; + + ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto done; + } + buf_start = total_out; + total_out += out_buf.pos; + out_buf.pos = 0; + + ret = btrfs_decompress_buf2page(out_buf.dst, buf_start, + total_out, disk_start, orig_bio); + if (ret == 0) + break; + + if (in_buf.pos >= srclen) + break; + + /* Check if we've hit the end of a frame */ + if (ret2 == 0) + break; + + if (in_buf.pos == in_buf.size) { + kunmap(pages_in[page_in_index++]); + if (page_in_index >= total_pages_in) { + in_buf.src = NULL; + ret = -EIO; + goto done; + } + srclen -= PAGE_SIZE; + in_buf.src = kmap(pages_in[page_in_index]); + in_buf.pos = 0; + in_buf.size = min_t(size_t, srclen, PAGE_SIZE); + } + } + ret = 0; + zero_fill_bio(orig_bio); +done: + if (in_buf.src) + kunmap(pages_in[page_in_index]); + return ret; +} + +static int zstd_decompress(struct list_head *ws, unsigned char *data_in, + struct page *dest_page, + unsigned long start_byte, + size_t srclen, size_t destlen) +{ + struct workspace *workspace = list_entry(ws, struct workspace, list); + ZSTD_DStream *stream; + int ret = 0; + size_t ret2; + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + unsigned long total_out = 0; + unsigned long pg_offset = 0; + char *kaddr; + + stream = ZSTD_initDStream( + ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); + if (!stream) { + pr_warn("BTRFS: ZSTD_initDStream failed\n"); + ret = -EIO; + goto finish; + } + + destlen = min_t(size_t, destlen, PAGE_SIZE); + + in_buf.src = data_in; + in_buf.pos = 0; + in_buf.size = srclen; + + out_buf.dst = workspace->buf; + out_buf.pos = 0; + out_buf.size = PAGE_SIZE; + + ret2 = 1; + while (pg_offset < destlen && in_buf.pos < in_buf.size) { + unsigned long buf_start; + unsigned long buf_offset; + unsigned long bytes; + + /* Check if the frame is over and we still need more input */ + if (ret2 == 0) { + pr_debug("BTRFS: ZSTD_decompressStream ended early\n"); + ret = -EIO; + goto finish; + } + ret2 = ZSTD_decompressStream(stream, &out_buf, &in_buf); + if (ZSTD_isError(ret2)) { + pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", + ZSTD_getErrorCode(ret2)); + ret = -EIO; + goto finish; + } + + buf_start = total_out; + total_out += out_buf.pos; + out_buf.pos = 0; + + if (total_out <= start_byte) + continue; + + if (total_out > start_byte && buf_start < start_byte) + buf_offset = start_byte - buf_start; + else + buf_offset = 0; + + bytes = min_t(unsigned long, destlen - pg_offset, + out_buf.size - buf_offset); + + kaddr = kmap_atomic(dest_page); + memcpy(kaddr + pg_offset, out_buf.dst + buf_offset, bytes); + kunmap_atomic(kaddr); + + pg_offset += bytes; + } + ret = 0; +finish: + if (pg_offset < destlen) { + kaddr = kmap_atomic(dest_page); + memset(kaddr + pg_offset, 0, destlen - pg_offset); + kunmap_atomic(kaddr); + } + return ret; +} + +const struct btrfs_compress_op btrfs_zstd_compress = { + .alloc_workspace = zstd_alloc_workspace, + .free_workspace = zstd_free_workspace, + .compress_pages = zstd_compress_pages, + .decompress_bio = zstd_decompress_bio, + .decompress = zstd_decompress, +}; diff --git a/fs/buffer.c b/fs/buffer.c index 161be58c5cb0..170df856bdb9 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -49,7 +49,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, - struct writeback_control *wbc); + enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) @@ -178,7 +178,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); @@ -352,8 +352,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); - mapping_set_error(page->mapping, -EIO); - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } @@ -481,8 +480,6 @@ static void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_assoc_map); - if (buffer_write_io_error(bh)) - set_bit(AS_EIO, &bh->b_assoc_map->flags); bh->b_assoc_map = NULL; } @@ -1181,6 +1178,17 @@ void mark_buffer_dirty(struct buffer_head *bh) } EXPORT_SYMBOL(mark_buffer_dirty); +void mark_buffer_write_io_error(struct buffer_head *bh) +{ + set_buffer_write_io_error(bh); + /* FIXME: do we need to set this in both places? */ + if (bh->b_page && bh->b_page->mapping) + mapping_set_error(bh->b_page->mapping, -EIO); + if (bh->b_assoc_map) + mapping_set_error(bh->b_assoc_map, -EIO); +} +EXPORT_SYMBOL(mark_buffer_write_io_error); + /* * Decrement a buffer_head's reference count. If all buffers against a page * have zero reference count, are clean and unlocked, and if the page is clean @@ -1273,44 +1281,31 @@ static inline void check_irqs_on(void) } /* - * The LRU management algorithm is dopey-but-simple. Sorry. + * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is + * inserted at the front, and the buffer_head at the back if any is evicted. + * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { - struct buffer_head *evictee = NULL; + struct buffer_head *evictee = bh; + struct bh_lru *b; + int i; check_irqs_on(); bh_lru_lock(); - if (__this_cpu_read(bh_lrus.bhs[0]) != bh) { - struct buffer_head *bhs[BH_LRU_SIZE]; - int in; - int out = 0; - get_bh(bh); - bhs[out++] = bh; - for (in = 0; in < BH_LRU_SIZE; in++) { - struct buffer_head *bh2 = - __this_cpu_read(bh_lrus.bhs[in]); - - if (bh2 == bh) { - __brelse(bh2); - } else { - if (out >= BH_LRU_SIZE) { - BUG_ON(evictee != NULL); - evictee = bh2; - } else { - bhs[out++] = bh2; - } - } + b = this_cpu_ptr(&bh_lrus); + for (i = 0; i < BH_LRU_SIZE; i++) { + swap(evictee, b->bhs[i]); + if (evictee == bh) { + bh_lru_unlock(); + return; } - while (out < BH_LRU_SIZE) - bhs[out++] = NULL; - memcpy(this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs)); } - bh_lru_unlock(); - if (evictee) - __brelse(evictee); + get_bh(bh); + bh_lru_unlock(); + brelse(evictee); } /* @@ -1632,20 +1627,17 @@ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) struct pagevec pvec; pgoff_t index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); pgoff_t end; - int i; + int i, count; struct buffer_head *bh; struct buffer_head *head; end = (block + len - 1) >> (PAGE_SHIFT - bd_inode->i_blkbits); pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, bd_mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { - for (i = 0; i < pagevec_count(&pvec); i++) { + while (pagevec_lookup_range(&pvec, bd_mapping, &index, end)) { + count = pagevec_count(&pvec); + for (i = 0; i < count; i++) { struct page *page = pvec.pages[i]; - index = page->index; - if (index > end) - break; if (!page_has_buffers(page)) continue; /* @@ -1675,7 +1667,9 @@ unlock_page: } pagevec_release(&pvec); cond_resched(); - index++; + /* End of range already reached? */ + if (index > end || !index) + break; } } EXPORT_SYMBOL(clean_bdev_aliases); @@ -1829,7 +1823,8 @@ int __block_write_full_page(struct inode *inode, struct page *page, do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { - submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc); + submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, + inode->i_write_hint, wbc); nr_underway++; } bh = next; @@ -1883,7 +1878,8 @@ recover: struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); - submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, wbc); + submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, + inode->i_write_hint, wbc); nr_underway++; } bh = next; @@ -3021,11 +3017,11 @@ EXPORT_SYMBOL(block_write_full_page); sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { - struct buffer_head tmp; struct inode *inode = mapping->host; - tmp.b_state = 0; - tmp.b_blocknr = 0; - tmp.b_size = i_blocksize(inode); + struct buffer_head tmp = { + .b_size = i_blocksize(inode), + }; + get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } @@ -3038,7 +3034,7 @@ static void end_bio_bh_io_sync(struct bio *bio) if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); - bh->b_end_io(bh, !bio->bi_error); + bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } @@ -3060,7 +3056,7 @@ void guard_bio_eod(int op, struct bio *bio) struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1]; unsigned truncated_bytes; - maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9; + maxsector = get_capacity(bio->bi_disk); if (!maxsector) return; @@ -3091,7 +3087,7 @@ void guard_bio_eod(int op, struct bio *bio) } static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, - struct writeback_control *wbc) + enum rw_hint write_hint, struct writeback_control *wbc) { struct bio *bio; @@ -3119,7 +3115,8 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, } bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_bdev = bh->b_bdev; + bio_set_dev(bio, bh->b_bdev); + bio->bi_write_hint = write_hint; bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); BUG_ON(bio->bi_iter.bi_size != bh->b_size); @@ -3142,7 +3139,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, int submit_bh(int op, int op_flags, struct buffer_head *bh) { - return submit_bh_wbc(op, op_flags, bh, NULL); + return submit_bh_wbc(op, op_flags, bh, 0, NULL); } EXPORT_SYMBOL(submit_bh); @@ -3279,8 +3276,6 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) bh = head; do { - if (buffer_write_io_error(bh) && page->mapping) - mapping_set_error(page->mapping, -EIO); if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; @@ -3492,6 +3487,120 @@ int bh_submit_read(struct buffer_head *bh) } EXPORT_SYMBOL(bh_submit_read); +/* + * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff. + * + * Returns the offset within the file on success, and -ENOENT otherwise. + */ +static loff_t +page_seek_hole_data(struct page *page, loff_t lastoff, int whence) +{ + loff_t offset = page_offset(page); + struct buffer_head *bh, *head; + bool seek_data = whence == SEEK_DATA; + + if (lastoff < offset) + lastoff = offset; + + bh = head = page_buffers(page); + do { + offset += bh->b_size; + if (lastoff >= offset) + continue; + + /* + * Unwritten extents that have data in the page cache covering + * them can be identified by the BH_Unwritten state flag. + * Pages with multiple buffers might have a mix of holes, data + * and unwritten extents - any buffer with valid data in it + * should have BH_Uptodate flag set on it. + */ + + if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data) + return lastoff; + + lastoff = offset; + } while ((bh = bh->b_this_page) != head); + return -ENOENT; +} + +/* + * Seek for SEEK_DATA / SEEK_HOLE in the page cache. + * + * Within unwritten extents, the page cache determines which parts are holes + * and which are data: unwritten and uptodate buffer heads count as data; + * everything else counts as a hole. + * + * Returns the resulting offset on successs, and -ENOENT otherwise. + */ +loff_t +page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length, + int whence) +{ + pgoff_t index = offset >> PAGE_SHIFT; + pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE); + loff_t lastoff = offset; + struct pagevec pvec; + + if (length <= 0) + return -ENOENT; + + pagevec_init(&pvec, 0); + + do { + unsigned nr_pages, i; + + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index, + end - 1); + if (nr_pages == 0) + break; + + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + /* + * At this point, the page may be truncated or + * invalidated (changing page->mapping to NULL), or + * even swizzled back from swapper_space to tmpfs file + * mapping. However, page->index will not change + * because we have a reference on the page. + * + * If current page offset is beyond where we've ended, + * we've found a hole. + */ + if (whence == SEEK_HOLE && + lastoff < page_offset(page)) + goto check_range; + + lock_page(page); + if (likely(page->mapping == inode->i_mapping) && + page_has_buffers(page)) { + lastoff = page_seek_hole_data(page, lastoff, whence); + if (lastoff >= 0) { + unlock_page(page); + goto check_range; + } + } + unlock_page(page); + lastoff = page_offset(page) + PAGE_SIZE; + } + pagevec_release(&pvec); + } while (index < end); + + /* When no page at lastoff and we are not done, we found a hole. */ + if (whence != SEEK_HOLE) + goto not_found; + +check_range: + if (lastoff < offset + length) + goto out; +not_found: + lastoff = -ENOENT; +out: + pagevec_release(&pvec); + return lastoff; +} + void __init buffer_init(void) { unsigned long nrpages; diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index 3ff867f87d73..d9f001078e08 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -133,7 +133,7 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) goto error_unsupported; ret = -EROFS; - if (root->d_sb->s_flags & MS_RDONLY) + if (sb_rdonly(root->d_sb)) goto error_unsupported; /* determine the security of the on-disk cache as this governs diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 9bf90bcc56ac..bb3a02ca9da4 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -18,7 +18,7 @@ #include <linux/fscache-cache.h> #include <linux/timer.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/cred.h> #include <linux/workqueue.h> #include <linux/security.h> @@ -97,7 +97,7 @@ struct cachefiles_cache { * backing file read tracking */ struct cachefiles_one_read { - wait_queue_t monitor; /* link into monitored waitqueue */ + wait_queue_entry_t monitor; /* link into monitored waitqueue */ struct page *back_page; /* backing file page we're waiting for */ struct page *netfs_page; /* netfs page we're going to fill */ struct fscache_retrieval *op; /* retrieval op covering this */ diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 41df8a27d7eb..3978b324cbca 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -204,7 +204,7 @@ wait_for_old_object: wait_queue_head_t *wq; signed long timeout = 60 * HZ; - wait_queue_t wait; + wait_queue_entry_t wait; bool requeue; /* if the object we're waiting for is queued for processing, diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index afbdc418966d..18d7aa61ef0f 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -21,7 +21,7 @@ * - we use this to detect read completion of backing pages * - the caller holds the waitqueue lock */ -static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, +static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, int sync, void *_key) { struct cachefiles_one_read *monitor = @@ -48,7 +48,7 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, } /* remove from the waitqueue */ - list_del(&wait->task_list); + list_del(&wait->entry); /* move onto the action list and queue for FS-Cache thread pool */ ASSERT(monitor->op); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 1e71e6ca5ddf..b3e3edc09d80 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -152,17 +152,10 @@ static void ceph_invalidatepage(struct page *page, unsigned int offset, ceph_invalidate_fscache_page(inode, page); + WARN_ON(!PageLocked(page)); if (!PagePrivate(page)) return; - /* - * We can get non-dirty pages here due to races between - * set_page_dirty and truncate_complete_page; just spit out a - * warning, in case we end up with accounting problems later. - */ - if (!PageDirty(page)) - pr_err("%p invalidatepage %p page not dirty\n", inode, page); - ClearPageChecked(page); dout("%p invalidatepage %p idx %lu full dirty page\n", @@ -189,7 +182,7 @@ static int ceph_releasepage(struct page *page, gfp_t g) /* * read a single page, without unlocking it. */ -static int readpage_nounlock(struct file *filp, struct page *page) +static int ceph_do_readpage(struct file *filp, struct page *page) { struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); @@ -219,7 +212,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) err = ceph_readpage_from_fscache(inode, page); if (err == 0) - goto out; + return -EINPROGRESS; dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); @@ -249,8 +242,11 @@ out: static int ceph_readpage(struct file *filp, struct page *page) { - int r = readpage_nounlock(filp, page); - unlock_page(page); + int r = ceph_do_readpage(filp, page); + if (r != -EINPROGRESS) + unlock_page(page); + else + r = 0; return r; } @@ -452,13 +448,9 @@ static int ceph_readpages(struct file *file, struct address_space *mapping, if (rc == 0) goto out; - if (fsc->mount_options->rsize >= PAGE_SIZE) - max = (fsc->mount_options->rsize + PAGE_SIZE - 1) - >> PAGE_SHIFT; - - dout("readpages %p file %p nr_pages %d max %d\n", inode, - file, nr_pages, - max); + max = fsc->mount_options->rsize >> PAGE_SHIFT; + dout("readpages %p file %p nr_pages %d max %d\n", + inode, file, nr_pages, max); while (!list_empty(page_list)) { rc = start_read(inode, page_list, max); if (rc < 0) @@ -471,14 +463,22 @@ out: return rc; } +struct ceph_writeback_ctl +{ + loff_t i_size; + u64 truncate_size; + u32 truncate_seq; + bool size_stable; + bool head_snapc; +}; + /* * Get ref for the oldest snapc for an inode with dirty data... that is, the * only snap context we are allowed to write back. */ -static struct ceph_snap_context *get_oldest_context(struct inode *inode, - loff_t *snap_size, - u64 *truncate_size, - u32 *truncate_seq) +static struct ceph_snap_context * +get_oldest_context(struct inode *inode, struct ceph_writeback_ctl *ctl, + struct ceph_snap_context *page_snapc) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc = NULL; @@ -488,30 +488,78 @@ static struct ceph_snap_context *get_oldest_context(struct inode *inode, list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) { dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap, capsnap->context, capsnap->dirty_pages); - if (capsnap->dirty_pages) { - snapc = ceph_get_snap_context(capsnap->context); - if (snap_size) - *snap_size = capsnap->size; - if (truncate_size) - *truncate_size = capsnap->truncate_size; - if (truncate_seq) - *truncate_seq = capsnap->truncate_seq; - break; + if (!capsnap->dirty_pages) + continue; + + /* get i_size, truncate_{seq,size} for page_snapc? */ + if (snapc && capsnap->context != page_snapc) + continue; + + if (ctl) { + if (capsnap->writing) { + ctl->i_size = i_size_read(inode); + ctl->size_stable = false; + } else { + ctl->i_size = capsnap->size; + ctl->size_stable = true; + } + ctl->truncate_size = capsnap->truncate_size; + ctl->truncate_seq = capsnap->truncate_seq; + ctl->head_snapc = false; } + + if (snapc) + break; + + snapc = ceph_get_snap_context(capsnap->context); + if (!page_snapc || + page_snapc == snapc || + page_snapc->seq > snapc->seq) + break; } if (!snapc && ci->i_wrbuffer_ref_head) { snapc = ceph_get_snap_context(ci->i_head_snapc); dout(" head snapc %p has %d dirty pages\n", snapc, ci->i_wrbuffer_ref_head); - if (truncate_size) - *truncate_size = ci->i_truncate_size; - if (truncate_seq) - *truncate_seq = ci->i_truncate_seq; + if (ctl) { + ctl->i_size = i_size_read(inode); + ctl->truncate_size = ci->i_truncate_size; + ctl->truncate_seq = ci->i_truncate_seq; + ctl->size_stable = false; + ctl->head_snapc = true; + } } spin_unlock(&ci->i_ceph_lock); return snapc; } +static u64 get_writepages_data_length(struct inode *inode, + struct page *page, u64 start) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_snap_context *snapc = page_snap_context(page); + struct ceph_cap_snap *capsnap = NULL; + u64 end = i_size_read(inode); + + if (snapc != ci->i_head_snapc) { + bool found = false; + spin_lock(&ci->i_ceph_lock); + list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) { + if (capsnap->context == snapc) { + if (!capsnap->writing) + end = capsnap->size; + found = true; + break; + } + } + spin_unlock(&ci->i_ceph_lock); + WARN_ON(!found); + } + if (end > page_offset(page) + PAGE_SIZE) + end = page_offset(page) + PAGE_SIZE; + return end > start ? end - start : 0; +} + /* * Write a single page, but leave the page locked. * @@ -523,57 +571,48 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) struct inode *inode; struct ceph_inode_info *ci; struct ceph_fs_client *fsc; - struct ceph_osd_client *osdc; struct ceph_snap_context *snapc, *oldest; loff_t page_off = page_offset(page); - loff_t snap_size = -1; long writeback_stat; - u64 truncate_size; - u32 truncate_seq; - int err = 0, len = PAGE_SIZE; + int err, len = PAGE_SIZE; + struct ceph_writeback_ctl ceph_wbc; dout("writepage %p idx %lu\n", page, page->index); - if (!page->mapping || !page->mapping->host) { - dout("writepage %p - no mapping\n", page); - return -EFAULT; - } inode = page->mapping->host; ci = ceph_inode(inode); fsc = ceph_inode_to_client(inode); - osdc = &fsc->client->osdc; /* verify this is a writeable snap context */ snapc = page_snap_context(page); - if (snapc == NULL) { + if (!snapc) { dout("writepage %p page %p not dirty?\n", inode, page); - goto out; + return 0; } - oldest = get_oldest_context(inode, &snap_size, - &truncate_size, &truncate_seq); + oldest = get_oldest_context(inode, &ceph_wbc, snapc); if (snapc->seq > oldest->seq) { dout("writepage %p page %p snapc %p not writeable - noop\n", inode, page, snapc); /* we should only noop if called by kswapd */ - WARN_ON((current->flags & PF_MEMALLOC) == 0); + WARN_ON(!(current->flags & PF_MEMALLOC)); ceph_put_snap_context(oldest); - goto out; + redirty_page_for_writepage(wbc, page); + return 0; } ceph_put_snap_context(oldest); - if (snap_size == -1) - snap_size = i_size_read(inode); - /* is this a partial page at end of file? */ - if (page_off >= snap_size) { - dout("%p page eof %llu\n", page, snap_size); - goto out; + if (page_off >= ceph_wbc.i_size) { + dout("%p page eof %llu\n", page, ceph_wbc.i_size); + page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); + return 0; } - if (snap_size < page_off + len) - len = snap_size - page_off; - dout("writepage %p page %p index %lu on %llu~%u snapc %p\n", - inode, page, page->index, page_off, len, snapc); + if (ceph_wbc.i_size < page_off + len) + len = ceph_wbc.i_size - page_off; + + dout("writepage %p page %p index %lu on %llu~%u snapc %p seq %lld\n", + inode, page, page->index, page_off, len, snapc, snapc->seq); writeback_stat = atomic_long_inc_return(&fsc->writeback_count); if (writeback_stat > @@ -581,10 +620,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); set_page_writeback(page); - err = ceph_osdc_writepages(osdc, ceph_vino(inode), - &ci->i_layout, snapc, - page_off, len, - truncate_seq, truncate_size, + err = ceph_osdc_writepages(&fsc->client->osdc, ceph_vino(inode), + &ci->i_layout, snapc, page_off, len, + ceph_wbc.truncate_seq, + ceph_wbc.truncate_size, &inode->i_mtime, &page, 1); if (err < 0) { struct writeback_control tmp_wbc; @@ -595,7 +634,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage interrupted page %p\n", page); redirty_page_for_writepage(wbc, page); end_page_writeback(page); - goto out; + return err; } dout("writepage setting page/mapping error %d %p\n", err, page); @@ -611,7 +650,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) end_page_writeback(page); ceph_put_wrbuffer_cap_refs(ci, 1, snapc); ceph_put_snap_context(snapc); /* page's reference */ -out: return err; } @@ -746,31 +784,17 @@ static int ceph_writepages_start(struct address_space *mapping, struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_vino vino = ceph_vino(inode); - pgoff_t index, start, end; - int range_whole = 0; - int should_loop = 1; - pgoff_t max_pages = 0, max_pages_ever = 0; + pgoff_t index, start_index, end = -1; struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc; struct pagevec pvec; - int done = 0; int rc = 0; unsigned int wsize = i_blocksize(inode); struct ceph_osd_request *req = NULL; - int do_sync = 0; - loff_t snap_size, i_size; - u64 truncate_size; - u32 truncate_seq; + struct ceph_writeback_ctl ceph_wbc; + bool should_loop, range_whole = false; + bool stop, done = false; - /* - * Include a 'sync' in the OSD request if this is a data - * integrity write (e.g., O_SYNC write or fsync()), or if our - * cap is being revoked. - */ - if ((wbc->sync_mode == WB_SYNC_ALL) || - ceph_caps_revoking(ci, CEPH_CAP_FILE_BUFFER)) - do_sync = 1; - dout("writepages_start %p dosync=%d (mode=%s)\n", - inode, do_sync, + dout("writepages_start %p (mode=%s)\n", inode, wbc->sync_mode == WB_SYNC_NONE ? "NONE" : (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD")); @@ -783,35 +807,17 @@ static int ceph_writepages_start(struct address_space *mapping, mapping_set_error(mapping, -EIO); return -EIO; /* we're in a forced umount, don't write! */ } - if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize) + if (fsc->mount_options->wsize < wsize) wsize = fsc->mount_options->wsize; - if (wsize < PAGE_SIZE) - wsize = PAGE_SIZE; - max_pages_ever = wsize >> PAGE_SHIFT; pagevec_init(&pvec, 0); - /* where to start/end? */ - if (wbc->range_cyclic) { - start = mapping->writeback_index; /* Start from prev offset */ - end = -1; - dout(" cyclic, start at %lu\n", start); - } else { - start = wbc->range_start >> PAGE_SHIFT; - end = wbc->range_end >> PAGE_SHIFT; - if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) - range_whole = 1; - should_loop = 0; - dout(" not cyclic, %lu to %lu\n", start, end); - } - index = start; + start_index = wbc->range_cyclic ? mapping->writeback_index : 0; + index = start_index; retry: /* find oldest snap context with dirty data */ - ceph_put_snap_context(snapc); - snap_size = -1; - snapc = get_oldest_context(inode, &snap_size, - &truncate_size, &truncate_seq); + snapc = get_oldest_context(inode, &ceph_wbc, NULL); if (!snapc) { /* hmm, why does writepages get called when there is no dirty data? */ @@ -821,40 +827,56 @@ retry: dout(" oldest snapc is %p seq %lld (%d snaps)\n", snapc, snapc->seq, snapc->num_snaps); - i_size = i_size_read(inode); - - if (last_snapc && snapc != last_snapc) { - /* if we switched to a newer snapc, restart our scan at the - * start of the original file range. */ - dout(" snapc differs from last pass, restarting at %lu\n", - index); - index = start; + should_loop = false; + if (ceph_wbc.head_snapc && snapc != last_snapc) { + /* where to start/end? */ + if (wbc->range_cyclic) { + index = start_index; + end = -1; + if (index > 0) + should_loop = true; + dout(" cyclic, start at %lu\n", index); + } else { + index = wbc->range_start >> PAGE_SHIFT; + end = wbc->range_end >> PAGE_SHIFT; + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = true; + dout(" not cyclic, %lu to %lu\n", index, end); + } + } else if (!ceph_wbc.head_snapc) { + /* Do not respect wbc->range_{start,end}. Dirty pages + * in that range can be associated with newer snapc. + * They are not writeable until we write all dirty pages + * associated with 'snapc' get written */ + if (index > 0 || wbc->sync_mode != WB_SYNC_NONE) + should_loop = true; + dout(" non-head snapc, range whole\n"); } + + ceph_put_snap_context(last_snapc); last_snapc = snapc; - while (!done && index <= end) { - unsigned i; - int first; - pgoff_t strip_unit_end = 0; + stop = false; + while (!stop && index <= end) { int num_ops = 0, op_idx; - int pvec_pages, locked_pages = 0; + unsigned i, pvec_pages, max_pages, locked_pages = 0; struct page **pages = NULL, **data_pages; mempool_t *pool = NULL; /* Becomes non-null if mempool used */ struct page *page; - int want; + pgoff_t strip_unit_end = 0; u64 offset = 0, len = 0; - max_pages = max_pages_ever; + max_pages = wsize >> PAGE_SHIFT; get_more_pages: - first = -1; - want = min(end - index, - min((pgoff_t)PAGEVEC_SIZE, - max_pages - (pgoff_t)locked_pages) - 1) - + 1; + pvec_pages = min_t(unsigned, PAGEVEC_SIZE, + max_pages - locked_pages); + if (end - index < (u64)(pvec_pages - 1)) + pvec_pages = (unsigned)(end - index) + 1; + pvec_pages = pagevec_lookup_tag(&pvec, mapping, &index, PAGECACHE_TAG_DIRTY, - want); + pvec_pages); dout("pagevec_lookup_tag got %d\n", pvec_pages); if (!pvec_pages && !locked_pages) break; @@ -871,11 +893,15 @@ get_more_pages: unlikely(page->mapping != mapping)) { dout("!dirty or !mapping %p\n", page); unlock_page(page); - break; + continue; } - if (!wbc->range_cyclic && page->index > end) { + if (page->index > end) { dout("end of range %p\n", page); - done = 1; + /* can't be range_cyclic (1st pass) because + * end == -1 in that case. */ + stop = true; + if (ceph_wbc.head_snapc) + done = true; unlock_page(page); break; } @@ -884,39 +910,37 @@ get_more_pages: unlock_page(page); break; } - if (wbc->sync_mode != WB_SYNC_NONE) { - dout("waiting on writeback %p\n", page); - wait_on_page_writeback(page); - } - if (page_offset(page) >= - (snap_size == -1 ? i_size : snap_size)) { - dout("%p page eof %llu\n", page, - (snap_size == -1 ? i_size : snap_size)); - done = 1; + if (page_offset(page) >= ceph_wbc.i_size) { + dout("%p page eof %llu\n", + page, ceph_wbc.i_size); + /* not done if range_cyclic */ + stop = true; unlock_page(page); break; } if (PageWriteback(page)) { - dout("%p under writeback\n", page); - unlock_page(page); - break; + if (wbc->sync_mode == WB_SYNC_NONE) { + dout("%p under writeback\n", page); + unlock_page(page); + continue; + } + dout("waiting on writeback %p\n", page); + wait_on_page_writeback(page); } /* only if matching snap context */ pgsnapc = page_snap_context(page); - if (pgsnapc->seq > snapc->seq) { - dout("page snapc %p %lld > oldest %p %lld\n", + if (pgsnapc != snapc) { + dout("page snapc %p %lld != oldest %p %lld\n", pgsnapc, pgsnapc->seq, snapc, snapc->seq); unlock_page(page); - if (!locked_pages) - continue; /* keep looking for snap */ - break; + continue; } if (!clear_page_dirty_for_io(page)) { dout("%p !clear_page_dirty_for_io\n", page); unlock_page(page); - break; + continue; } /* @@ -942,7 +966,7 @@ get_more_pages: break; } - num_ops = 1 + do_sync; + num_ops = 1; strip_unit_end = page->index + ((len - 1) >> PAGE_SHIFT); @@ -972,8 +996,6 @@ get_more_pages: } /* note position of first page in pvec */ - if (first < 0) - first = i; dout("%p will write page %p idx %lu\n", inode, page, page->index); @@ -984,8 +1006,10 @@ get_more_pages: BLK_RW_ASYNC); } - pages[locked_pages] = page; - locked_pages++; + + pages[locked_pages++] = page; + pvec.pages[i] = NULL; + len += PAGE_SIZE; } @@ -993,23 +1017,23 @@ get_more_pages: if (!locked_pages) goto release_pvec_pages; if (i) { - int j; - BUG_ON(!locked_pages || first < 0); + unsigned j, n = 0; + /* shift unused page to beginning of pvec */ + for (j = 0; j < pvec_pages; j++) { + if (!pvec.pages[j]) + continue; + if (n < j) + pvec.pages[n] = pvec.pages[j]; + n++; + } + pvec.nr = n; if (pvec_pages && i == pvec_pages && locked_pages < max_pages) { dout("reached end pvec, trying for more\n"); - pagevec_reinit(&pvec); + pagevec_release(&pvec); goto get_more_pages; } - - /* shift unused pages over in the pvec... we - * will need to release them below. */ - for (j = i; j < pvec_pages; j++) { - dout(" pvec leftover page %p\n", pvec.pages[j]); - pvec.pages[j-i+first] = pvec.pages[j]; - } - pvec.nr -= i-first; } new_request: @@ -1019,10 +1043,9 @@ new_request: req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, offset, &len, 0, num_ops, - CEPH_OSD_OP_WRITE, - CEPH_OSD_FLAG_WRITE, - snapc, truncate_seq, - truncate_size, false); + CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, + snapc, ceph_wbc.truncate_seq, + ceph_wbc.truncate_size, false); if (IS_ERR(req)) { req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, @@ -1031,8 +1054,8 @@ new_request: CEPH_OSD_SLAB_OPS), CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, - snapc, truncate_seq, - truncate_size, true); + snapc, ceph_wbc.truncate_seq, + ceph_wbc.truncate_size, true); BUG_ON(IS_ERR(req)); } BUG_ON(len < page_offset(pages[locked_pages - 1]) + @@ -1048,7 +1071,7 @@ new_request: for (i = 0; i < locked_pages; i++) { u64 cur_offset = page_offset(pages[i]); if (offset + len != cur_offset) { - if (op_idx + do_sync + 1 == req->r_num_ops) + if (op_idx + 1 == req->r_num_ops) break; osd_req_op_extent_dup_last(req, op_idx, cur_offset - offset); @@ -1069,14 +1092,15 @@ new_request: len += PAGE_SIZE; } - if (snap_size != -1) { - len = min(len, snap_size - offset); + if (ceph_wbc.size_stable) { + len = min(len, ceph_wbc.i_size - offset); } else if (i == locked_pages) { /* writepages_finish() clears writeback pages * according to the data length, so make sure * data length covers all locked pages */ u64 min_len = len + 1 - PAGE_SIZE; - len = min(len, (u64)i_size_read(inode) - offset); + len = get_writepages_data_length(inode, pages[i - 1], + offset); len = max(len, min_len); } dout("writepages got pages at %llu~%llu\n", offset, len); @@ -1085,17 +1109,12 @@ new_request: 0, !!pool, false); osd_req_op_extent_update(req, op_idx, len); - if (do_sync) { - op_idx++; - osd_req_op_init(req, op_idx, CEPH_OSD_OP_STARTSYNC, 0); - } BUG_ON(op_idx + 1 != req->r_num_ops); pool = NULL; if (i < locked_pages) { BUG_ON(num_ops <= req->r_num_ops); num_ops -= req->r_num_ops; - num_ops += do_sync; locked_pages -= i; /* allocate new pages array for next request */ @@ -1127,22 +1146,50 @@ new_request: if (pages) goto new_request; - if (wbc->nr_to_write <= 0) - done = 1; + /* + * We stop writing back only if we are not doing + * integrity sync. In case of integrity sync we have to + * keep going until we have written all the pages + * we tagged for writeback prior to entering this loop. + */ + if (wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) + done = stop = true; release_pvec_pages: dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr, pvec.nr ? pvec.pages[0] : NULL); pagevec_release(&pvec); - - if (locked_pages && !done) - goto retry; } if (should_loop && !done) { /* more to do; loop back to beginning of file */ dout("writepages looping back to beginning of file\n"); - should_loop = 0; + end = start_index - 1; /* OK even when start_index == 0 */ + + /* to write dirty pages associated with next snapc, + * we need to wait until current writes complete */ + if (wbc->sync_mode != WB_SYNC_NONE && + start_index == 0 && /* all dirty pages were checked */ + !ceph_wbc.head_snapc) { + struct page *page; + unsigned i, nr; + index = 0; + while ((index <= end) && + (nr = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_WRITEBACK, + PAGEVEC_SIZE))) { + for (i = 0; i < nr; i++) { + page = pvec.pages[i]; + if (page_snap_context(page) != snapc) + continue; + wait_on_page_writeback(page); + } + pagevec_release(&pvec); + cond_resched(); + } + } + + start_index = 0; index = 0; goto retry; } @@ -1152,8 +1199,8 @@ release_pvec_pages: out: ceph_osdc_put_request(req); - ceph_put_snap_context(snapc); - dout("writepages done, rc = %d\n", rc); + ceph_put_snap_context(last_snapc); + dout("writepages dend - startone, rc = %d\n", rc); return rc; } @@ -1165,8 +1212,7 @@ out: static int context_is_writeable_or_written(struct inode *inode, struct ceph_snap_context *snapc) { - struct ceph_snap_context *oldest = get_oldest_context(inode, NULL, - NULL, NULL); + struct ceph_snap_context *oldest = get_oldest_context(inode, NULL, NULL); int ret = !oldest || snapc->seq <= oldest->seq; ceph_put_snap_context(oldest); @@ -1211,8 +1257,7 @@ retry_locked: * this page is already dirty in another (older) snap * context! is it writeable now? */ - oldest = get_oldest_context(inode, NULL, NULL, NULL); - + oldest = get_oldest_context(inode, NULL, NULL); if (snapc->seq > oldest->seq) { ceph_put_snap_context(oldest); dout(" page %p snapc %p not current or oldest\n", @@ -1240,7 +1285,7 @@ retry_locked: goto retry_locked; r = writepage_nounlock(page, NULL); if (r < 0) - goto fail_nosnap; + goto fail_unlock; goto retry_locked; } @@ -1268,11 +1313,14 @@ retry_locked: } /* we need to read it. */ - r = readpage_nounlock(file, page); - if (r < 0) - goto fail_nosnap; + r = ceph_do_readpage(file, page); + if (r < 0) { + if (r == -EINPROGRESS) + return -EAGAIN; + goto fail_unlock; + } goto retry_locked; -fail_nosnap: +fail_unlock: unlock_page(page); return r; } @@ -1318,7 +1366,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { struct inode *inode = file_inode(file); - int check_cap = 0; + bool check_cap = false; dout("write_end file %p inode %p page %p %d~%d (%d)\n", file, inode, page, (int)pos, (int)copied, (int)len); diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 4e7421caf380..a3ab265d3215 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -35,18 +35,34 @@ struct fscache_netfs ceph_cache_netfs = { .version = 0, }; +static DEFINE_MUTEX(ceph_fscache_lock); +static LIST_HEAD(ceph_fscache_list); + +struct ceph_fscache_entry { + struct list_head list; + struct fscache_cookie *fscache; + struct ceph_fsid fsid; + size_t uniq_len; + char uniquifier[0]; +}; + static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data, void *buffer, uint16_t maxbuf) { const struct ceph_fs_client* fsc = cookie_netfs_data; - uint16_t klen; + const char *fscache_uniq = fsc->mount_options->fscache_uniq; + uint16_t fsid_len, uniq_len; - klen = sizeof(fsc->client->fsid); - if (klen > maxbuf) + fsid_len = sizeof(fsc->client->fsid); + uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0; + if (fsid_len + uniq_len > maxbuf) return 0; - memcpy(buffer, &fsc->client->fsid, klen); - return klen; + memcpy(buffer, &fsc->client->fsid, fsid_len); + if (uniq_len) + memcpy(buffer + fsid_len, fscache_uniq, uniq_len); + + return fsid_len + uniq_len; } static const struct fscache_cookie_def ceph_fscache_fsid_object_def = { @@ -67,13 +83,54 @@ void ceph_fscache_unregister(void) int ceph_fscache_register_fs(struct ceph_fs_client* fsc) { + const struct ceph_fsid *fsid = &fsc->client->fsid; + const char *fscache_uniq = fsc->mount_options->fscache_uniq; + size_t uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0; + struct ceph_fscache_entry *ent; + int err = 0; + + mutex_lock(&ceph_fscache_lock); + list_for_each_entry(ent, &ceph_fscache_list, list) { + if (memcmp(&ent->fsid, fsid, sizeof(*fsid))) + continue; + if (ent->uniq_len != uniq_len) + continue; + if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len)) + continue; + + pr_err("fscache cookie already registered for fsid %pU\n", fsid); + pr_err(" use fsc=%%s mount option to specify a uniquifier\n"); + err = -EBUSY; + goto out_unlock; + } + + ent = kzalloc(sizeof(*ent) + uniq_len, GFP_KERNEL); + if (!ent) { + err = -ENOMEM; + goto out_unlock; + } + fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index, &ceph_fscache_fsid_object_def, fsc, true); - if (!fsc->fscache) - pr_err("Unable to register fsid: %p fscache cookie\n", fsc); - return 0; + if (fsc->fscache) { + memcpy(&ent->fsid, fsid, sizeof(*fsid)); + if (uniq_len > 0) { + memcpy(&ent->uniquifier, fscache_uniq, uniq_len); + ent->uniq_len = uniq_len; + } + ent->fscache = fsc->fscache; + list_add_tail(&ent->list, &ceph_fscache_list); + } else { + kfree(ent); + pr_err("unable to register fscache cookie for fsid %pU\n", + fsid); + /* all other fs ignore this error */ + } +out_unlock: + mutex_unlock(&ceph_fscache_lock); + return err; } static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data, @@ -137,36 +194,6 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux( return FSCACHE_CHECKAUX_OKAY; } -static void ceph_fscache_inode_now_uncached(void* cookie_netfs_data) -{ - struct ceph_inode_info* ci = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - dout("ceph inode 0x%p now uncached", ci); - - while (1) { - nr_pages = pagevec_lookup(&pvec, ci->vfs_inode.i_mapping, first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - static const struct fscache_cookie_def ceph_fscache_inode_object_def = { .name = "CEPH.inode", .type = FSCACHE_COOKIE_TYPE_DATAFILE, @@ -174,7 +201,6 @@ static const struct fscache_cookie_def ceph_fscache_inode_object_def = { .get_attr = ceph_fscache_inode_get_attr, .get_aux = ceph_fscache_inode_get_aux, .check_aux = ceph_fscache_inode_check_aux, - .now_uncached = ceph_fscache_inode_now_uncached, }; void ceph_fscache_register_inode_cookie(struct inode *inode) @@ -183,7 +209,7 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) struct ceph_fs_client *fsc = ceph_inode_to_client(inode); /* No caching for filesystem */ - if (fsc->fscache == NULL) + if (!fsc->fscache) return; /* Only cache for regular files that are read only */ @@ -240,13 +266,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp) } } -static void ceph_vfs_readpage_complete(struct page *page, void *data, int error) -{ - if (!error) - SetPageUptodate(page); -} - -static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error) +static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error) { if (!error) SetPageUptodate(page); @@ -274,7 +294,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page) return -ENOBUFS; ret = fscache_read_or_alloc_page(ci->fscache, page, - ceph_vfs_readpage_complete, NULL, + ceph_readpage_from_fscache_complete, NULL, GFP_KERNEL); switch (ret) { @@ -303,7 +323,7 @@ int ceph_readpages_from_fscache(struct inode *inode, return -ENOBUFS; ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages, - ceph_vfs_readpage_complete_unlock, + ceph_readpage_from_fscache_complete, NULL, mapping_gfp_mask(mapping)); switch (ret) { @@ -349,7 +369,24 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page) void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc) { - fscache_relinquish_cookie(fsc->fscache, 0); + if (fscache_cookie_valid(fsc->fscache)) { + struct ceph_fscache_entry *ent; + bool found = false; + + mutex_lock(&ceph_fscache_lock); + list_for_each_entry(ent, &ceph_fscache_list, list) { + if (ent->fscache == fsc->fscache) { + list_del(&ent->list); + kfree(ent); + found = true; + break; + } + } + WARN_ON_ONCE(!found); + mutex_unlock(&ceph_fscache_lock); + + __fscache_relinquish_cookie(fsc->fscache, 0); + } fsc->fscache = NULL; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index a3ebb632294e..157fe59fbabe 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -490,13 +490,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, } /* - * if we are newly issued FILE_SHARED, mark dir not complete; we - * don't know what happened to this directory while we didn't - * have the cap. + * If FILE_SHARED is newly issued, mark dir not complete. We don't + * know what happened to this directory while we didn't have the cap. + * If FILE_SHARED is being revoked, also mark dir not complete. It + * stops on-going cached readdir. */ - if ((issued & CEPH_CAP_FILE_SHARED) && - (had & CEPH_CAP_FILE_SHARED) == 0) { - ci->i_shared_gen++; + if ((issued & CEPH_CAP_FILE_SHARED) != (had & CEPH_CAP_FILE_SHARED)) { + if (issued & CEPH_CAP_FILE_SHARED) + ci->i_shared_gen++; if (S_ISDIR(ci->vfs_inode.i_mode)) { dout(" marking %p NOT complete\n", &ci->vfs_inode); __ceph_dir_clear_complete(ci); @@ -611,7 +612,7 @@ void ceph_add_cap(struct inode *inode, } if (flags & CEPH_CAP_FLAG_AUTH) { - if (ci->i_auth_cap == NULL || + if (!ci->i_auth_cap || ceph_seq_cmp(ci->i_auth_cap->mseq, mseq) < 0) { ci->i_auth_cap = cap; cap->mds_wanted = wanted; @@ -728,7 +729,7 @@ static void __touch_cap(struct ceph_cap *cap) struct ceph_mds_session *s = cap->session; spin_lock(&s->s_cap_lock); - if (s->s_cap_iterator == NULL) { + if (!s->s_cap_iterator) { dout("__touch_cap %p cap %p mds%d\n", &cap->ci->vfs_inode, cap, s->s_mds); list_move_tail(&cap->session_caps, &s->s_caps); @@ -1248,7 +1249,10 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, arg.mode = inode->i_mode; arg.inline_data = ci->i_inline_version != CEPH_INLINE_NONE; - arg.flags = 0; + if (list_empty(&ci->i_cap_snaps)) + arg.flags = CEPH_CLIENT_CAPS_NO_CAPSNAP; + else + arg.flags = CEPH_CLIENT_CAPS_PENDING_CAPSNAP; if (sync) arg.flags |= CEPH_CLIENT_CAPS_SYNC; @@ -1454,13 +1458,19 @@ retry: goto retry; } + // make sure flushsnap messages are sent in proper order. + if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) { + __kick_flushing_caps(mdsc, session, ci, 0); + ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH; + } + __ceph_flush_snaps(ci, session); out: spin_unlock(&ci->i_ceph_lock); if (psession) { *psession = session; - } else { + } else if (session) { mutex_unlock(&session->s_mutex); ceph_put_mds_session(session); } @@ -1653,6 +1663,21 @@ static int try_nonblocking_invalidate(struct inode *inode) return -1; } +bool __ceph_should_report_size(struct ceph_inode_info *ci) +{ + loff_t size = ci->vfs_inode.i_size; + /* mds will adjust max size according to the reported size */ + if (ci->i_flushing_caps & CEPH_CAP_FILE_WR) + return false; + if (size >= ci->i_max_size) + return true; + /* half of previous max_size increment has been used */ + if (ci->i_max_size > ci->i_reported_size && + (size << 1) >= ci->i_max_size + ci->i_reported_size) + return true; + return false; +} + /* * Swiss army knife function to examine currently used and wanted * versus held caps. Release, flush, ack revoked caps to mds as @@ -1806,8 +1831,7 @@ retry_locked: } /* approaching file_max? */ - if ((inode->i_size << 1) >= ci->i_max_size && - (ci->i_reported_size << 1) < ci->i_max_size) { + if (__ceph_should_report_size(ci)) { dout("i_size approaching max_size\n"); goto ack; } @@ -1887,11 +1911,7 @@ ack: (ci->i_ceph_flags & (CEPH_I_KICK_FLUSH | CEPH_I_FLUSH_SNAPS))) { if (ci->i_ceph_flags & CEPH_I_KICK_FLUSH) { - spin_lock(&mdsc->cap_dirty_lock); - oldest_flush_tid = __get_oldest_flush_tid(mdsc); - spin_unlock(&mdsc->cap_dirty_lock); - __kick_flushing_caps(mdsc, session, ci, - oldest_flush_tid); + __kick_flushing_caps(mdsc, session, ci, 0); ci->i_ceph_flags &= ~CEPH_I_KICK_FLUSH; } if (ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS) @@ -2096,7 +2116,7 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) dout("fsync %p%s\n", inode, datasync ? " datasync" : ""); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); if (ret < 0) goto out; @@ -3027,8 +3047,10 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, le32_to_cpu(grant->truncate_seq), le64_to_cpu(grant->truncate_size), size); - /* max size increase? */ - if (ci->i_auth_cap == cap && max_size != ci->i_max_size) { + } + + if (ci->i_auth_cap == cap && (newcaps & CEPH_CAP_ANY_FILE_WR)) { + if (max_size != ci->i_max_size) { dout("max_size %lld -> %llu\n", ci->i_max_size, max_size); ci->i_max_size = max_size; @@ -3037,6 +3059,10 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc, ci->i_requested_max_size = 0; } wake = true; + } else if (ci->i_wanted_max_size > ci->i_max_size && + ci->i_wanted_max_size > ci->i_requested_max_size) { + /* CEPH_CAP_OP_IMPORT */ + wake = true; } } @@ -3402,7 +3428,7 @@ retry: tcap = __get_cap_for_mds(ci, target); if (tcap) { /* already have caps from the target */ - if (tcap->cap_id != t_cap_id || + if (tcap->cap_id == t_cap_id && ceph_seq_cmp(tcap->seq, t_seq) < 0) { dout(" updating import cap %p mds%d\n", tcap, target); tcap->cap_id = t_cap_id; @@ -3554,7 +3580,6 @@ retry: } /* make sure we re-request max_size, if necessary */ - ci->i_wanted_max_size = 0; ci->i_requested_max_size = 0; *old_issued = issued; @@ -3790,6 +3815,7 @@ bad: */ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) { + struct inode *inode; struct ceph_inode_info *ci; int flags = CHECK_CAPS_NODELAY; @@ -3805,9 +3831,15 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) time_before(jiffies, ci->i_hold_caps_max)) break; list_del_init(&ci->i_cap_delay_list); + + inode = igrab(&ci->vfs_inode); spin_unlock(&mdsc->cap_delay_lock); - dout("check_delayed_caps on %p\n", &ci->vfs_inode); - ceph_check_caps(ci, flags, NULL); + + if (inode) { + dout("check_delayed_caps on %p\n", inode); + ceph_check_caps(ci, flags, NULL); + iput(inode); + } } spin_unlock(&mdsc->cap_delay_lock); } diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 4e2d112c982f..d635496ea189 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -24,7 +24,7 @@ static int mdsmap_show(struct seq_file *s, void *p) struct ceph_fs_client *fsc = s->private; struct ceph_mdsmap *mdsmap; - if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL) + if (!fsc->mdsc || !fsc->mdsc->mdsmap) return 0; mdsmap = fsc->mdsc->mdsmap; seq_printf(s, "epoch %d\n", mdsmap->m_epoch); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index e071d23f6148..019c2036d36f 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -271,6 +271,11 @@ out: if (ret < 0) err = ret; dput(last); + /* last_name no longer match cache index */ + if (fi->readdir_cache_idx >= 0) { + fi->readdir_cache_idx = -1; + fi->dir_release_count = 0; + } } return err; } @@ -372,8 +377,10 @@ more: } /* hints to request -> mds selection code */ req->r_direct_mode = USE_AUTH_MDS; - req->r_direct_hash = ceph_frag_value(frag); - __set_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags); + if (op == CEPH_MDS_OP_READDIR) { + req->r_direct_hash = ceph_frag_value(frag); + __set_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags); + } if (fi->last_name) { req->r_path2 = kstrdup(fi->last_name, GFP_KERNEL); if (!req->r_path2) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 29308a80d66f..65a6fa12c857 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -175,7 +175,7 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode) dout("init_file %p %p 0%o (regular)\n", inode, file, inode->i_mode); cf = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL); - if (cf == NULL) { + if (!cf) { ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */ return -ENOMEM; } @@ -562,8 +562,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ssize_t ret; size_t len = iov_iter_count(to); - dout("sync_read on file %p %llu~%u %s\n", file, off, - (unsigned)len, + dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); if (!len) @@ -788,7 +787,7 @@ static void ceph_aio_retry_work(struct work_struct *work) goto out; } - req->r_flags = CEPH_OSD_FLAG_ORDERSNAP | CEPH_OSD_FLAG_WRITE; + req->r_flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE; ceph_oloc_copy(&req->r_base_oloc, &orig_req->r_base_oloc); ceph_oid_copy(&req->r_base_oid, &orig_req->r_base_oid); @@ -800,7 +799,6 @@ static void ceph_aio_retry_work(struct work_struct *work) } req->r_ops[0] = orig_req->r_ops[0]; - osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0); req->r_mtime = aio_req->mtime; req->r_data_offset = req->r_ops[0].extent.offset; @@ -847,8 +845,9 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP) return -EROFS; - dout("sync_direct_read_write (%s) on file %p %lld~%u\n", - (write ? "write" : "read"), file, pos, (unsigned)count); + dout("sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n", + (write ? "write" : "read"), file, pos, (unsigned)count, + snapc, snapc->seq); ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count); if (ret < 0) @@ -861,7 +860,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (ret2 < 0) dout("invalidate_inode_pages2_range returned %d\n", ret2); - flags = CEPH_OSD_FLAG_ORDERSNAP | CEPH_OSD_FLAG_WRITE; + flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE; } else { flags = CEPH_OSD_FLAG_READ; } @@ -874,8 +873,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, vino = ceph_vino(inode); req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, pos, &size, 0, - /*include a 'startsync' command*/ - write ? 2 : 1, + 1, write ? CEPH_OSD_OP_WRITE : CEPH_OSD_OP_READ, flags, snapc, @@ -887,6 +885,11 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } + if (write) + size = min_t(u64, size, fsc->mount_options->wsize); + else + size = min_t(u64, size, fsc->mount_options->rsize); + len = size; pages = dio_get_pages_alloc(iter, len, &start, &num_pages); if (IS_ERR(pages)) { @@ -922,7 +925,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, truncate_inode_pages_range(inode->i_mapping, pos, (pos+len) | (PAGE_SIZE - 1)); - osd_req_op_init(req, 1, CEPH_OSD_OP_STARTSYNC, 0); req->r_mtime = mtime; } @@ -1040,15 +1042,16 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, int num_pages; int written = 0; int flags; - int check_caps = 0; int ret; + bool check_caps = false; struct timespec mtime = current_time(inode); size_t count = iov_iter_count(from); if (ceph_snap(file_inode(file)) != CEPH_NOSNAP) return -EROFS; - dout("sync_write on file %p %lld~%u\n", file, pos, (unsigned)count); + dout("sync_write on file %p %lld~%u snapc %p seq %lld\n", + file, pos, (unsigned)count, snapc, snapc->seq); ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count); if (ret < 0) @@ -1060,7 +1063,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, if (ret < 0) dout("invalidate_inode_pages2_range returned %d\n", ret); - flags = CEPH_OSD_FLAG_ORDERSNAP | CEPH_OSD_FLAG_WRITE; + flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE; while ((len = iov_iter_count(from)) > 0) { size_t left; @@ -1307,6 +1310,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) if (!prealloc_cf) return -ENOMEM; +retry_snap: inode_lock(inode); /* We can write back this queue in page reclaim */ @@ -1338,7 +1342,6 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; } -retry_snap: /* FIXME: not complete since it doesn't account for being at quota */ if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) { err = -ENOSPC; @@ -1387,14 +1390,6 @@ retry_snap: &prealloc_cf); else written = ceph_sync_write(iocb, &data, pos, snapc); - if (written == -EOLDSNAPC) { - dout("aio_write %p %llx.%llx %llu~%u" - "got EOLDSNAPC, retrying\n", - inode, ceph_vinop(inode), - pos, (unsigned)count); - inode_lock(inode); - goto retry_snap; - } if (written > 0) iov_iter_advance(from, written); ceph_put_snap_context(snapc); @@ -1428,10 +1423,15 @@ retry_snap: ceph_cap_string(got)); ceph_put_cap_refs(ci, got); + if (written == -EOLDSNAPC) { + dout("aio_write %p %llx.%llx %llu~%u" "got EOLDSNAPC, retrying\n", + inode, ceph_vinop(inode), pos, (unsigned)count); + goto retry_snap; + } + if (written >= 0) { if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_NEARFULL)) iocb->ki_flags |= IOCB_DSYNC; - written = generic_write_sync(iocb, written); } @@ -1481,13 +1481,13 @@ static loff_t ceph_llseek(struct file *file, loff_t offset, int whence) offset += file->f_pos; break; case SEEK_DATA: - if (offset >= i_size) { + if (offset < 0 || offset >= i_size) { ret = -ENXIO; goto out; } break; case SEEK_HOLE: - if (offset >= i_size) { + if (offset < 0 || offset >= i_size) { ret = -ENXIO; goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 4de6cdddf059..373dab5173ca 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -52,7 +52,7 @@ struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino) ino_t t = ceph_vino_to_ino(vino); inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino); - if (inode == NULL) + if (!inode) return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { dout("get_inode created new inode %p %llx.%llx ino %llx\n", @@ -133,12 +133,9 @@ static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci, } frag = kmalloc(sizeof(*frag), GFP_NOFS); - if (!frag) { - pr_err("__get_or_create_frag ENOMEM on %p %llx.%llx " - "frag %x\n", &ci->vfs_inode, - ceph_vinop(&ci->vfs_inode), f); + if (!frag) return ERR_PTR(-ENOMEM); - } + frag->frag = f; frag->split_by = 0; frag->mds = -1; @@ -1016,6 +1013,7 @@ static void update_dentry_lease(struct dentry *dentry, long unsigned ttl = from_time + (duration * HZ) / 1000; long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000; struct inode *dir; + struct ceph_mds_session *old_lease_session = NULL; /* * Make sure dentry's inode matches tgt_vino. NULL tgt_vino means that @@ -1051,8 +1049,10 @@ static void update_dentry_lease(struct dentry *dentry, time_before(ttl, di->time)) goto out_unlock; /* we already have a newer lease. */ - if (di->lease_session && di->lease_session != session) - goto out_unlock; + if (di->lease_session && di->lease_session != session) { + old_lease_session = di->lease_session; + di->lease_session = NULL; + } ceph_dentry_lru_touch(dentry); @@ -1065,7 +1065,8 @@ static void update_dentry_lease(struct dentry *dentry, di->time = ttl; out_unlock: spin_unlock(&dentry->d_lock); - return; + if (old_lease_session) + ceph_put_mds_session(old_lease_session); } /* @@ -1172,7 +1173,7 @@ retry_lookup: dn = d_alloc(parent, &dname); dout("d_alloc %p '%.*s' = %p\n", parent, dname.len, dname.name, dn); - if (dn == NULL) { + if (!dn) { dput(parent); err = -ENOMEM; goto done; @@ -1472,7 +1473,6 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct dentry *dn; struct inode *in; int err = 0, skipped = 0, ret, i; - struct inode *snapdir = NULL; struct ceph_mds_request_head *rhead = req->r_request->front.iov_base; u32 frag = le32_to_cpu(rhead->args.readdir.frag); u32 last_hash = 0; @@ -1505,8 +1505,6 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, } if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) { - snapdir = ceph_get_snapdir(d_inode(parent)); - parent = d_find_alias(snapdir); dout("readdir_prepopulate %d items under SNAPDIR dn %p\n", rinfo->dir_nr, parent); } else { @@ -1514,15 +1512,18 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, rinfo->dir_nr, parent); if (rinfo->dir_dir) ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir); - } - if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 && - !(rinfo->hash_order && last_hash)) { - /* note dir version at start of readdir so we can tell - * if any dentries get dropped */ - req->r_dir_release_cnt = atomic64_read(&ci->i_release_count); - req->r_dir_ordered_cnt = atomic64_read(&ci->i_ordered_count); - req->r_readdir_cache_idx = 0; + if (ceph_frag_is_leftmost(frag) && + req->r_readdir_offset == 2 && + !(rinfo->hash_order && last_hash)) { + /* note dir version at start of readdir so we can + * tell if any dentries get dropped */ + req->r_dir_release_cnt = + atomic64_read(&ci->i_release_count); + req->r_dir_ordered_cnt = + atomic64_read(&ci->i_ordered_count); + req->r_readdir_cache_idx = 0; + } } cache_ctl.index = req->r_readdir_cache_idx; @@ -1561,7 +1562,7 @@ retry_lookup: dn = d_alloc(parent, &dname); dout("d_alloc %p '%.*s' = %p\n", parent, dname.len, dname.name, dn); - if (dn == NULL) { + if (!dn) { dout("d_alloc badness\n"); err = -ENOMEM; goto out; @@ -1645,28 +1646,21 @@ out: req->r_readdir_cache_idx = cache_ctl.index; } ceph_readdir_cache_release(&cache_ctl); - if (snapdir) { - iput(snapdir); - dput(parent); - } dout("readdir_prepopulate done\n"); return err; } -int ceph_inode_set_size(struct inode *inode, loff_t size) +bool ceph_inode_set_size(struct inode *inode, loff_t size) { struct ceph_inode_info *ci = ceph_inode(inode); - int ret = 0; + bool ret; spin_lock(&ci->i_ceph_lock); dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size); i_size_write(inode, size); inode->i_blocks = calc_inode_blocks(size); - /* tell the MDS if we are approaching max_size */ - if ((size << 1) >= ci->i_max_size && - (ci->i_reported_size << 1) < ci->i_max_size) - ret = 1; + ret = __ceph_should_report_size(ci); spin_unlock(&ci->i_ceph_lock); return ret; @@ -1839,9 +1833,20 @@ retry: * possibly truncate them.. so write AND block! */ if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) { + struct ceph_cap_snap *capsnap; + to = ci->i_truncate_size; + list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) { + // MDS should have revoked Frw caps + WARN_ON_ONCE(capsnap->writing); + if (capsnap->dirty_pages && capsnap->size > to) + to = capsnap->size; + } + spin_unlock(&ci->i_ceph_lock); dout("__do_pending_vmtruncate %p flushing snaps first\n", inode); - spin_unlock(&ci->i_ceph_lock); + + truncate_pagecache(inode, to); + filemap_write_and_wait_range(&inode->i_data, 0, inode->i_sb->s_maxbytes); goto retry; diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 6806dbeaee19..8cd63e8123d8 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -79,7 +79,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file, err = ceph_mdsc_do_request(mdsc, inode, req); if (operation == CEPH_MDS_OP_GETFILELOCK) { - fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid); + fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid); if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type) fl->fl_type = F_RDLCK; else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type) @@ -127,6 +127,29 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, dout("ceph_lock_wait_for_completion: request %llu was interrupted\n", req->r_tid); + mutex_lock(&mdsc->mutex); + if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) { + err = 0; + } else { + /* + * ensure we aren't running concurrently with + * ceph_fill_trace or ceph_readdir_prepopulate, which + * rely on locks (dir mutex) held by our caller. + */ + mutex_lock(&req->r_fill_mutex); + req->r_err = err; + set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags); + mutex_unlock(&req->r_fill_mutex); + + if (!req->r_session) { + // haven't sent the request + err = 0; + } + } + mutex_unlock(&mdsc->mutex); + if (!err) + return 0; + intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK, USE_AUTH_MDS); if (IS_ERR(intr_req)) @@ -146,7 +169,7 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, if (err && err != -ERESTARTSYS) return err; - wait_for_completion(&req->r_completion); + wait_for_completion_killable(&req->r_safe_completion); return 0; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 0c05df44cc6c..f23c820daaed 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -7,7 +7,6 @@ #include <linux/sched.h> #include <linux/debugfs.h> #include <linux/seq_file.h> -#include <linux/utsname.h> #include <linux/ratelimit.h> #include "super.h" @@ -408,7 +407,7 @@ struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc, { struct ceph_mds_session *session; - if (mds >= mdsc->max_sessions || mdsc->sessions[mds] == NULL) + if (mds >= mdsc->max_sessions || !mdsc->sessions[mds]) return NULL; session = mdsc->sessions[mds]; dout("lookup_mds_session %p %d\n", session, @@ -483,7 +482,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, dout("register_session realloc to %d\n", newmax); sa = kcalloc(newmax, sizeof(void *), GFP_NOFS); - if (sa == NULL) + if (!sa) goto fail_realloc; if (mdsc->sessions) { memcpy(sa, mdsc->sessions, @@ -731,8 +730,16 @@ static int __choose_mds(struct ceph_mds_client *mdsc, inode = NULL; if (req->r_inode) { - inode = req->r_inode; - ihold(inode); + if (ceph_snap(req->r_inode) != CEPH_SNAPDIR) { + inode = req->r_inode; + ihold(inode); + } else { + /* req->r_dentry is non-null for LSSNAP request */ + rcu_read_lock(); + inode = get_nonsnap_parent(req->r_dentry); + rcu_read_unlock(); + dout("__choose_mds using snapdir's parent %p\n", inode); + } } else if (req->r_dentry) { /* ignore race with rename; old or new d_parent is okay */ struct dentry *parent; @@ -877,8 +884,8 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 void *p; const char* metadata[][2] = { - {"hostname", utsname()->nodename}, - {"kernel_version", utsname()->release}, + {"hostname", mdsc->nodename}, + {"kernel_version", init_utsname()->release}, {"entity_id", opt->name ? : ""}, {"root", fsopt->server_path ? : "/"}, {NULL, NULL} @@ -886,7 +893,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 /* Calculate serialized length of metadata */ metadata_bytes = 4; /* map length */ - for (i = 0; metadata[i][0] != NULL; ++i) { + for (i = 0; metadata[i][0]; ++i) { metadata_bytes += 8 + strlen(metadata[i][0]) + strlen(metadata[i][1]); metadata_key_count++; @@ -919,7 +926,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6 ceph_encode_32(&p, metadata_key_count); /* Two length-prefixed strings for each entry in the map */ - for (i = 0; metadata[i][0] != NULL; ++i) { + for (i = 0; metadata[i][0]; ++i) { size_t const key_len = strlen(metadata[i][0]); size_t const val_len = strlen(metadata[i][1]); @@ -1122,7 +1129,7 @@ static int iterate_session_caps(struct ceph_mds_session *session, spin_lock(&session->s_cap_lock); p = p->next; - if (cap->ci == NULL) { + if (!cap->ci) { dout("iterate_session_caps finishing cap %p removal\n", cap); BUG_ON(cap->session != session); @@ -1748,7 +1755,7 @@ char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, int len, pos; unsigned seq; - if (dentry == NULL) + if (!dentry) return ERR_PTR(-EINVAL); retry: @@ -1771,7 +1778,7 @@ retry: len--; /* no leading '/' */ path = kmalloc(len+1, GFP_NOFS); - if (path == NULL) + if (!path) return ERR_PTR(-ENOMEM); pos = len; path[pos] = 0; /* trailing null */ @@ -2875,7 +2882,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, } if (list_empty(&ci->i_cap_snaps)) { - snap_follows = 0; + snap_follows = ci->i_head_snapc ? ci->i_head_snapc->seq : 0; } else { struct ceph_cap_snap *capsnap = list_first_entry(&ci->i_cap_snaps, @@ -3133,7 +3140,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, newmap->m_epoch, oldmap->m_epoch); for (i = 0; i < oldmap->m_num_mds && i < mdsc->max_sessions; i++) { - if (mdsc->sessions[i] == NULL) + if (!mdsc->sessions[i]) continue; s = mdsc->sessions[i]; oldstate = ceph_mdsmap_get_state(oldmap, i); @@ -3280,7 +3287,7 @@ static void handle_lease(struct ceph_mds_client *mdsc, mutex_lock(&session->s_mutex); session->s_seq++; - if (inode == NULL) { + if (!inode) { dout("handle_lease no inode %llx\n", vino.ino); goto release; } @@ -3438,7 +3445,7 @@ static void delayed_work(struct work_struct *work) for (i = 0; i < mdsc->max_sessions; i++) { struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i); - if (s == NULL) + if (!s) continue; if (s->s_state == CEPH_MDS_SESSION_CLOSING) { dout("resending session close request for mds%d\n", @@ -3490,7 +3497,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) fsc->mdsc = mdsc; mutex_init(&mdsc->mutex); mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS); - if (mdsc->mdsmap == NULL) { + if (!mdsc->mdsmap) { kfree(mdsc); return -ENOMEM; } @@ -3532,6 +3539,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) init_rwsem(&mdsc->pool_perm_rwsem); mdsc->pool_perm_tree = RB_ROOT; + strncpy(mdsc->nodename, utsname()->nodename, + sizeof(mdsc->nodename) - 1); return 0; } @@ -3769,13 +3778,13 @@ static void ceph_mdsc_stop(struct ceph_mds_client *mdsc) void ceph_mdsc_destroy(struct ceph_fs_client *fsc) { struct ceph_mds_client *mdsc = fsc->mdsc; - dout("mdsc_destroy %p\n", mdsc); - ceph_mdsc_stop(mdsc); /* flush out any connection work with references to us */ ceph_msgr_flush(); + ceph_mdsc_stop(mdsc); + fsc->mdsc = NULL; kfree(mdsc); dout("mdsc_destroy %p done\n", mdsc); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index db57ae98ed34..636d6b2ec49c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -8,6 +8,7 @@ #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/refcount.h> +#include <linux/utsname.h> #include <linux/ceph/types.h> #include <linux/ceph/messenger.h> @@ -368,6 +369,8 @@ struct ceph_mds_client { struct rw_semaphore pool_perm_rwsem; struct rb_root pool_perm_tree; + + char nodename[__NEW_UTS_LEN + 1]; }; extern const char *ceph_mds_op_name(int op); diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 1a748cf88535..33ced4c22732 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -112,7 +112,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) u16 mdsmap_ev; m = kzalloc(sizeof(*m), GFP_NOFS); - if (m == NULL) + if (!m) return ERR_PTR(-ENOMEM); ceph_decode_need(p, end, 1 + 1, bad); @@ -138,7 +138,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) m->m_num_mds = m->m_max_mds; m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS); - if (m->m_info == NULL) + if (!m->m_info) goto nomem; /* pick out active nodes from mds_info (state > 0) */ @@ -232,7 +232,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) if (num_export_targets) { info->export_targets = kcalloc(num_export_targets, sizeof(u32), GFP_NOFS); - if (info->export_targets == NULL) + if (!info->export_targets) goto nomem; for (j = 0; j < num_export_targets; j++) info->export_targets[j] = diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index dab5d6732345..7fc0b850c352 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -299,7 +299,8 @@ static int cmpu64_rev(const void *a, const void *b) /* * build the snap context for a given realm. */ -static int build_snap_context(struct ceph_snap_realm *realm) +static int build_snap_context(struct ceph_snap_realm *realm, + struct list_head* dirty_realms) { struct ceph_snap_realm *parent = realm->parent; struct ceph_snap_context *snapc; @@ -313,7 +314,7 @@ static int build_snap_context(struct ceph_snap_realm *realm) */ if (parent) { if (!parent->cached_context) { - err = build_snap_context(parent); + err = build_snap_context(parent, dirty_realms); if (err) goto fail; } @@ -332,7 +333,7 @@ static int build_snap_context(struct ceph_snap_realm *realm) " (unchanged)\n", realm->ino, realm, realm->cached_context, realm->cached_context->seq, - (unsigned int) realm->cached_context->num_snaps); + (unsigned int)realm->cached_context->num_snaps); return 0; } @@ -375,6 +376,8 @@ static int build_snap_context(struct ceph_snap_realm *realm) ceph_put_snap_context(realm->cached_context); realm->cached_context = snapc; + /* queue realm for cap_snap creation */ + list_add_tail(&realm->dirty_item, dirty_realms); return 0; fail: @@ -394,15 +397,16 @@ fail: /* * rebuild snap context for the given realm and all of its children. */ -static void rebuild_snap_realms(struct ceph_snap_realm *realm) +static void rebuild_snap_realms(struct ceph_snap_realm *realm, + struct list_head *dirty_realms) { struct ceph_snap_realm *child; dout("rebuild_snap_realms %llx %p\n", realm->ino, realm); - build_snap_context(realm); + build_snap_context(realm, dirty_realms); list_for_each_entry(child, &realm->children, child_item) - rebuild_snap_realms(child); + rebuild_snap_realms(child, dirty_realms); } @@ -624,13 +628,11 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm) { struct ceph_inode_info *ci; struct inode *lastinode = NULL; - struct ceph_snap_realm *child; dout("queue_realm_cap_snaps %p %llx inodes\n", realm, realm->ino); spin_lock(&realm->inodes_with_caps_lock); - list_for_each_entry(ci, &realm->inodes_with_caps, - i_snap_realm_item) { + list_for_each_entry(ci, &realm->inodes_with_caps, i_snap_realm_item) { struct inode *inode = igrab(&ci->vfs_inode); if (!inode) continue; @@ -643,14 +645,6 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm) spin_unlock(&realm->inodes_with_caps_lock); iput(lastinode); - list_for_each_entry(child, &realm->children, child_item) { - dout("queue_realm_cap_snaps %p %llx queue child %p %llx\n", - realm, realm->ino, child, child->ino); - list_del_init(&child->dirty_item); - list_add(&child->dirty_item, &realm->dirty_item); - } - - list_del_init(&realm->dirty_item); dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino); } @@ -721,8 +715,6 @@ more: if (err < 0) goto fail; - /* queue realm for cap_snap creation */ - list_add(&realm->dirty_item, &dirty_realms); if (realm->seq > mdsc->last_snap_seq) mdsc->last_snap_seq = realm->seq; @@ -741,7 +733,7 @@ more: /* invalidate when we reach the _end_ (root) of the trace */ if (invalidate && p >= e) - rebuild_snap_realms(realm); + rebuild_snap_realms(realm, &dirty_realms); if (!first_realm) first_realm = realm; @@ -758,6 +750,7 @@ more: while (!list_empty(&dirty_realms)) { realm = list_first_entry(&dirty_realms, struct ceph_snap_realm, dirty_item); + list_del_init(&realm->dirty_item); queue_realm_cap_snaps(realm); } diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 8d7918ce694a..e4082afedcb1 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -49,9 +49,16 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf) struct ceph_statfs st; u64 fsid; int err; + u64 data_pool; + + if (fsc->mdsc->mdsmap->m_num_data_pg_pools == 1) { + data_pool = fsc->mdsc->mdsmap->m_data_pg_pools[0]; + } else { + data_pool = CEPH_NOPOOL; + } dout("statfs\n"); - err = ceph_monc_do_statfs(&fsc->client->monc, &st); + err = ceph_monc_do_statfs(&fsc->client->monc, data_pool, &st); if (err < 0) return err; @@ -113,7 +120,6 @@ enum { Opt_rasize, Opt_caps_wanted_delay_min, Opt_caps_wanted_delay_max, - Opt_cap_release_safety, Opt_readdir_max_entries, Opt_readdir_max_bytes, Opt_congestion_kb, @@ -121,6 +127,7 @@ enum { /* int args above */ Opt_snapdirname, Opt_mds_namespace, + Opt_fscache_uniq, Opt_last_string, /* string args above */ Opt_dirstat, @@ -151,13 +158,13 @@ static match_table_t fsopt_tokens = { {Opt_rasize, "rasize=%d"}, {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"}, {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"}, - {Opt_cap_release_safety, "cap_release_safety=%d"}, {Opt_readdir_max_entries, "readdir_max_entries=%d"}, {Opt_readdir_max_bytes, "readdir_max_bytes=%d"}, {Opt_congestion_kb, "write_congestion_kb=%d"}, /* int args above */ {Opt_snapdirname, "snapdirname=%s"}, {Opt_mds_namespace, "mds_namespace=%s"}, + {Opt_fscache_uniq, "fsc=%s"}, /* string args above */ {Opt_dirstat, "dirstat"}, {Opt_nodirstat, "nodirstat"}, @@ -223,29 +230,53 @@ static int parse_fsopt_token(char *c, void *private) if (!fsopt->mds_namespace) return -ENOMEM; break; + case Opt_fscache_uniq: + fsopt->fscache_uniq = kstrndup(argstr[0].from, + argstr[0].to-argstr[0].from, + GFP_KERNEL); + if (!fsopt->fscache_uniq) + return -ENOMEM; + fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE; + break; /* misc */ case Opt_wsize: - fsopt->wsize = intval; + if (intval < PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE) + return -EINVAL; + fsopt->wsize = ALIGN(intval, PAGE_SIZE); break; case Opt_rsize: - fsopt->rsize = intval; + if (intval < PAGE_SIZE || intval > CEPH_MAX_READ_SIZE) + return -EINVAL; + fsopt->rsize = ALIGN(intval, PAGE_SIZE); break; case Opt_rasize: - fsopt->rasize = intval; + if (intval < 0) + return -EINVAL; + fsopt->rasize = ALIGN(intval + PAGE_SIZE - 1, PAGE_SIZE); break; case Opt_caps_wanted_delay_min: + if (intval < 1) + return -EINVAL; fsopt->caps_wanted_delay_min = intval; break; case Opt_caps_wanted_delay_max: + if (intval < 1) + return -EINVAL; fsopt->caps_wanted_delay_max = intval; break; case Opt_readdir_max_entries: + if (intval < 1) + return -EINVAL; fsopt->max_readdir = intval; break; case Opt_readdir_max_bytes: + if (intval < PAGE_SIZE && intval != 0) + return -EINVAL; fsopt->max_readdir_bytes = intval; break; case Opt_congestion_kb: + if (intval < 1024) /* at least 1M */ + return -EINVAL; fsopt->congestion_kb = intval; break; case Opt_dirstat: @@ -317,6 +348,7 @@ static void destroy_mount_options(struct ceph_mount_options *args) kfree(args->snapdir_name); kfree(args->mds_namespace); kfree(args->server_path); + kfree(args->fscache_uniq); kfree(args); } @@ -350,10 +382,12 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt, ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace); if (ret) return ret; - ret = strcmp_null(fsopt1->server_path, fsopt2->server_path); if (ret) return ret; + ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq); + if (ret) + return ret; return ceph_compare_options(new_opt, fsc->client); } @@ -379,7 +413,8 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, fsopt->sb_flags = flags; fsopt->flags = CEPH_MOUNT_OPT_DEFAULT; - fsopt->rsize = CEPH_RSIZE_DEFAULT; + fsopt->wsize = CEPH_MAX_WRITE_SIZE; + fsopt->rsize = CEPH_MAX_READ_SIZE; fsopt->rasize = CEPH_RASIZE_DEFAULT; fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL); if (!fsopt->snapdir_name) { @@ -389,7 +424,6 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, fsopt->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT; fsopt->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT; - fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT; fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT; fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; fsopt->congestion_kb = default_congestion_kb(); @@ -475,8 +509,12 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",noasyncreaddir"); if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0) seq_puts(m, ",nodcache"); - if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) - seq_puts(m, ",fsc"); + if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) { + if (fsopt->fscache_uniq) + seq_printf(m, ",fsc=%s", fsopt->fscache_uniq); + else + seq_puts(m, ",fsc"); + } if (fsopt->flags & CEPH_MOUNT_OPT_NOPOOLPERM) seq_puts(m, ",nopoolperm"); @@ -491,7 +529,7 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_printf(m, ",mds_namespace=%s", fsopt->mds_namespace); if (fsopt->wsize) seq_printf(m, ",wsize=%d", fsopt->wsize); - if (fsopt->rsize != CEPH_RSIZE_DEFAULT) + if (fsopt->rsize != CEPH_MAX_READ_SIZE) seq_printf(m, ",rsize=%d", fsopt->rsize); if (fsopt->rasize != CEPH_RASIZE_DEFAULT) seq_printf(m, ",rasize=%d", fsopt->rasize); @@ -503,9 +541,6 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT) seq_printf(m, ",caps_wanted_delay_max=%d", fsopt->caps_wanted_delay_max); - if (fsopt->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT) - seq_printf(m, ",cap_release_safety=%d", - fsopt->cap_release_safety); if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT) seq_printf(m, ",readdir_max_entries=%d", fsopt->max_readdir); if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT) @@ -559,7 +594,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, } fsc->client->extra_mon_dispatch = extra_mon_dispatch; - if (fsopt->mds_namespace == NULL) { + if (!fsopt->mds_namespace) { ceph_monc_want_map(&fsc->client->monc, CEPH_SUB_MDSMAP, 0, true); } else { @@ -580,13 +615,13 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, * to be processed in parallel, limit concurrency. */ fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1); - if (fsc->wb_wq == NULL) + if (!fsc->wb_wq) goto fail_client; fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1); - if (fsc->pg_inv_wq == NULL) + if (!fsc->pg_inv_wq) goto fail_wb_wq; fsc->trunc_wq = alloc_workqueue("ceph-trunc", 0, 1); - if (fsc->trunc_wq == NULL) + if (!fsc->trunc_wq) goto fail_pg_inv_wq; /* set up mempools */ @@ -597,18 +632,11 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, if (!fsc->wb_pagevec_pool) goto fail_trunc_wq; - /* setup fscache */ - if ((fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) && - (ceph_fscache_register_fs(fsc) != 0)) - goto fail_fscache; - /* caps */ fsc->min_caps = fsopt->max_readdir; return fsc; -fail_fscache: - ceph_fscache_unregister_fs(fsc); fail_trunc_wq: destroy_workqueue(fsc->trunc_wq); fail_pg_inv_wq: @@ -626,8 +654,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) { dout("destroy_fs_client %p\n", fsc); - ceph_fscache_unregister_fs(fsc); - destroy_workqueue(fsc->wb_wq); destroy_workqueue(fsc->pg_inv_wq); destroy_workqueue(fsc->trunc_wq); @@ -636,8 +662,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) destroy_mount_options(fsc->mount_options); - ceph_fs_debugfs_cleanup(fsc); - ceph_destroy_client(fsc->client); kfree(fsc); @@ -668,26 +692,26 @@ static int __init init_caches(void) __alignof__(struct ceph_inode_info), SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD| SLAB_ACCOUNT, ceph_inode_init_once); - if (ceph_inode_cachep == NULL) + if (!ceph_inode_cachep) return -ENOMEM; ceph_cap_cachep = KMEM_CACHE(ceph_cap, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); - if (ceph_cap_cachep == NULL) + if (!ceph_cap_cachep) goto bad_cap; ceph_cap_flush_cachep = KMEM_CACHE(ceph_cap_flush, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); - if (ceph_cap_flush_cachep == NULL) + if (!ceph_cap_flush_cachep) goto bad_cap_flush; ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD); - if (ceph_dentry_cachep == NULL) + if (!ceph_dentry_cachep) goto bad_dentry; ceph_file_cachep = KMEM_CACHE(ceph_file_info, SLAB_MEM_SPREAD); - if (ceph_file_cachep == NULL) + if (!ceph_file_cachep) goto bad_file; if ((error = ceph_fscache_register())) @@ -822,6 +846,13 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) if (err < 0) goto out; + /* setup fscache */ + if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) { + err = ceph_fscache_register_fs(fsc); + if (err < 0) + goto out; + } + if (!fsc->mount_options->server_path) { path = ""; dout("mount opening path \\t\n"); @@ -934,20 +965,10 @@ static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc) return err; /* set ra_pages based on rasize mount option? */ - if (fsc->mount_options->rasize >= PAGE_SIZE) - sb->s_bdi->ra_pages = - (fsc->mount_options->rasize + PAGE_SIZE - 1) - >> PAGE_SHIFT; - else - sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE; + sb->s_bdi->ra_pages = fsc->mount_options->rasize >> PAGE_SHIFT; - if (fsc->mount_options->rsize > fsc->mount_options->rasize && - fsc->mount_options->rsize >= PAGE_SIZE) - sb->s_bdi->io_pages = - (fsc->mount_options->rsize + PAGE_SIZE - 1) - >> PAGE_SHIFT; - else if (fsc->mount_options->rsize == 0) - sb->s_bdi->io_pages = ULONG_MAX; + /* set io_pages based on max osd read size */ + sb->s_bdi->io_pages = fsc->mount_options->rsize >> PAGE_SHIFT; return 0; } @@ -1040,6 +1061,12 @@ static void ceph_kill_sb(struct super_block *s) ceph_mdsc_pre_umount(fsc->mdsc); generic_shutdown_super(s); + + fsc->client->extra_mon_dispatch = NULL; + ceph_fs_debugfs_cleanup(fsc); + + ceph_fscache_unregister_fs(fsc); + ceph_mdsc_destroy(fsc); destroy_fs_client(fsc); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index a973acd8beaf..279a2f401cf5 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -46,12 +46,25 @@ #define ceph_test_mount_opt(fsc, opt) \ (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt)) -#define CEPH_RSIZE_DEFAULT (64*1024*1024) /* max read size */ +/* max size of osd read request, limited by libceph */ +#define CEPH_MAX_READ_SIZE CEPH_MSG_MAX_DATA_LEN +/* osd has a configurable limitaion of max write size. + * CEPH_MSG_MAX_DATA_LEN should be small enough. */ +#define CEPH_MAX_WRITE_SIZE CEPH_MSG_MAX_DATA_LEN #define CEPH_RASIZE_DEFAULT (8192*1024) /* max readahead */ #define CEPH_MAX_READDIR_DEFAULT 1024 #define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024) #define CEPH_SNAPDIRNAME_DEFAULT ".snap" +/* + * Delay telling the MDS we no longer want caps, in case we reopen + * the file. Delay a minimum amount of time, even if we send a cap + * message for some other reason. Otherwise, take the oppotunity to + * update the mds to avoid sending another message later. + */ +#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT 5 /* cap release delay */ +#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT 60 /* cap release delay */ + struct ceph_mount_options { int flags; int sb_flags; @@ -61,7 +74,6 @@ struct ceph_mount_options { int rasize; /* max readahead */ int congestion_kb; /* max writeback in flight */ int caps_wanted_delay_min, caps_wanted_delay_max; - int cap_release_safety; int max_readdir; /* max readdir result (entires) */ int max_readdir_bytes; /* max readdir result (bytes) */ @@ -73,6 +85,7 @@ struct ceph_mount_options { char *snapdir_name; /* default ".snap" */ char *mds_namespace; /* default NULL */ char *server_path; /* default "/" */ + char *fscache_uniq; /* default NULL */ }; struct ceph_fs_client { @@ -793,7 +806,7 @@ extern int ceph_readdir_prepopulate(struct ceph_mds_request *req, extern int ceph_inode_holds_cap(struct inode *inode, int mask); -extern int ceph_inode_set_size(struct inode *inode, loff_t size); +extern bool ceph_inode_set_size(struct inode *inode, loff_t size); extern void __ceph_do_pending_vmtruncate(struct inode *inode); extern void ceph_queue_vmtruncate(struct inode *inode); @@ -918,6 +931,7 @@ extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, struct ceph_snap_context *snapc); extern void ceph_flush_snaps(struct ceph_inode_info *ci, struct ceph_mds_session **psession); +extern bool __ceph_should_report_size(struct ceph_inode_info *ci); extern void ceph_check_caps(struct ceph_inode_info *ci, int flags, struct ceph_mds_session *session); extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc); diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 75267cdd5dfd..3542b2c364cf 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -756,6 +756,9 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, /* let's see if a virtual xattr was requested */ vxattr = ceph_match_vxattr(inode, name); if (vxattr) { + err = ceph_do_getattr(inode, 0, true); + if (err) + return err; err = -ENODATA; if (!(vxattr->exists_cb && !vxattr->exists_cb(ci))) err = vxattr->getxattr_cb(ci, value, size); @@ -774,7 +777,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, spin_unlock(&ci->i_ceph_lock); /* security module gets xattr while filling trace */ - if (current->journal_info != NULL) { + if (current->journal_info) { pr_warn_ratelimited("sync getxattr %p " "during filling trace\n", inode); return -EBUSY; @@ -806,7 +809,7 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value, memcpy(value, xattr->val, xattr->val_len); - if (current->journal_info != NULL && + if (current->journal_info && !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) ci->i_ceph_flags |= CEPH_I_SEC_INITED; out: @@ -1055,7 +1058,7 @@ do_sync_unlocked: up_read(&mdsc->snap_rwsem); /* security module set xattr while filling trace */ - if (current->journal_info != NULL) { + if (current->journal_info) { pr_warn_ratelimited("sync setxattr %p " "during filling trace\n", inode); err = -EBUSY; @@ -1105,7 +1108,7 @@ bool ceph_security_xattr_deadlock(struct inode *in) { struct ceph_inode_info *ci; bool ret; - if (in->i_security == NULL) + if (!in->i_security) return false; ci = ceph_inode(in); spin_lock(&ci->i_ceph_lock); diff --git a/fs/char_dev.c b/fs/char_dev.c index fb8507f521b2..ebcc8fb3fa66 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -28,6 +28,8 @@ static struct kobj_map *cdev_map; static DEFINE_MUTEX(chrdevs_lock); +#define CHRDEV_MAJOR_HASH_SIZE 255 + static struct char_device_struct { struct char_device_struct *next; unsigned int major; @@ -49,16 +51,39 @@ void chrdev_show(struct seq_file *f, off_t offset) { struct char_device_struct *cd; - if (offset < CHRDEV_MAJOR_HASH_SIZE) { - mutex_lock(&chrdevs_lock); - for (cd = chrdevs[offset]; cd; cd = cd->next) + mutex_lock(&chrdevs_lock); + for (cd = chrdevs[major_to_index(offset)]; cd; cd = cd->next) { + if (cd->major == offset) seq_printf(f, "%3d %s\n", cd->major, cd->name); - mutex_unlock(&chrdevs_lock); } + mutex_unlock(&chrdevs_lock); } #endif /* CONFIG_PROC_FS */ +static int find_dynamic_major(void) +{ + int i; + struct char_device_struct *cd; + + for (i = ARRAY_SIZE(chrdevs)-1; i > CHRDEV_MAJOR_DYN_END; i--) { + if (chrdevs[i] == NULL) + return i; + } + + for (i = CHRDEV_MAJOR_DYN_EXT_START; + i > CHRDEV_MAJOR_DYN_EXT_END; i--) { + for (cd = chrdevs[major_to_index(i)]; cd; cd = cd->next) + if (cd->major == i) + break; + + if (cd == NULL || cd->major != i) + return i; + } + + return -EBUSY; +} + /* * Register a single major with a specified minor range. * @@ -84,22 +109,21 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, mutex_lock(&chrdevs_lock); - /* temporary */ if (major == 0) { - for (i = ARRAY_SIZE(chrdevs)-1; i > 0; i--) { - if (chrdevs[i] == NULL) - break; - } - - if (i < CHRDEV_MAJOR_DYN_END) - pr_warn("CHRDEV \"%s\" major number %d goes below the dynamic allocation range\n", - name, i); - - if (i == 0) { - ret = -EBUSY; + ret = find_dynamic_major(); + if (ret < 0) { + pr_err("CHRDEV \"%s\" dynamic allocation region is full\n", + name); goto out; } - major = i; + major = ret; + } + + if (major >= CHRDEV_MAJOR_MAX) { + pr_err("CHRDEV \"%s\" major requested (%d) is greater than the maximum (%d)\n", + name, major, CHRDEV_MAJOR_MAX); + ret = -EINVAL; + goto out; } cd->major = major; diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 034f00f21390..f7243617316c 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -1,5 +1,5 @@ config CIFS - tristate "CIFS support (advanced network filesystem, SMBFS successor)" + tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET select NLS select CRYPTO @@ -10,28 +10,35 @@ config CIFS select CRYPTO_ECB select CRYPTO_DES help - This is the client VFS module for the Common Internet File System - (CIFS) protocol which is the successor to the Server Message Block - (SMB) protocol, the native file sharing mechanism for most early - PC operating systems. The CIFS protocol is fully supported by - file servers such as Windows 2000 (including Windows 2003, Windows 2008, - NT 4 and Windows XP) as well by Samba (which provides excellent CIFS + This is the client VFS module for the SMB3 family of NAS protocols, + as well as for earlier dialects such as SMB2.1, SMB2 and the + Common Internet File System (CIFS) protocol. CIFS was the successor + to the original dialect, the Server Message Block (SMB) protocol, the + native file sharing mechanism for most early PC operating systems. + + The SMB3 protocol is supported by most modern operating systems and + NAS appliances (e.g. Samba, Windows 8, Windows 2012, MacOS). + The older CIFS protocol was included in Windows NT4, 2000 and XP (and + later) as well by Samba (which provides excellent CIFS and SMB3 server support for Linux and many other operating systems). Limited - support for OS/2 and Windows ME and similar servers is provided as - well. + support for OS/2 and Windows ME and similar very old servers is + provided as well. - The module also provides optional support for the followon - protocols for CIFS including SMB3, which enables - useful performance and security features (see the description - of CONFIG_CIFS_SMB2). - - The cifs module provides an advanced network file system - client for mounting to CIFS compliant servers. It includes + The cifs module provides an advanced network file system client + for mounting to SMB3 (and CIFS) compliant servers. It includes support for DFS (hierarchical name space), secure per-user session establishment via Kerberos or NTLM or NTLMv2, safe distributed caching (oplock), optional packet signing, Unicode and other internationalization improvements. - If you need to mount to Samba or Windows from this machine, say Y. + + In general, the default dialects, SMB3 and later, enable better + performance, security and features, than would be possible with CIFS. + Note that when mounting to Samba, due to the CIFS POSIX extensions, + CIFS mounts can provide slightly better POSIX compatibility + than SMB3 mounts. SMB2/SMB3 mount options are also + slightly simpler (compared to CIFS) due to protocol improvements. + + If you need to mount to Samba, Macs or Windows from this machine, say Y. config CIFS_STATS bool "CIFS statistics" @@ -89,7 +96,7 @@ config CIFS_UPCALL Enables an upcall mechanism for CIFS which accesses userspace helper utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets which are needed to mount to certain secure servers (for which more - secure Kerberos authentication is required). If unsure, say N. + secure Kerberos authentication is required). If unsure, say Y. config CIFS_XATTR bool "CIFS extended attributes" @@ -105,7 +112,7 @@ config CIFS_XATTR (used by some filesystems to store ACLs) is not supported at this time. - If unsure, say N. + If unsure, say Y. config CIFS_POSIX bool "CIFS POSIX Extensions" @@ -125,7 +132,7 @@ config CIFS_ACL help Allows fetching CIFS/NTFS ACL from the server. The DACL blob is handed over to the application/caller. See the man - page for getcifsacl for more information. + page for getcifsacl for more information. If unsure, say Y. config CIFS_DEBUG bool "Enable CIFS debugging routines" @@ -146,6 +153,16 @@ config CIFS_DEBUG2 option can be turned off unless you are debugging cifs problems. If unsure, say N. +config CIFS_DEBUG_DUMP_KEYS + bool "Dump encryption keys for offline decryption (Unsafe)" + depends on CIFS_DEBUG + help + Enabling this will dump the encryption and decryption keys + used to communicate on an encrypted share connection on the + console. This allows Wireshark to decrypt and dissect + encrypted network captures. Enable this carefully. + If unsure, say N. + config CIFS_DFS_UPCALL bool "DFS feature support" depends on CIFS && KEYS @@ -157,7 +174,7 @@ config CIFS_DFS_UPCALL an upcall mechanism for CIFS which contacts userspace helper utilities to provide server name resolution (host names to IP addresses) which is needed for implicit mounts of DFS junction - points. If unsure, say N. + points. If unsure, say Y. config CIFS_NFSD_EXPORT bool "Allow nfsd to export CIFS file system" @@ -165,38 +182,9 @@ config CIFS_NFSD_EXPORT help Allows NFS server to export a CIFS mounted share (nfsd over cifs) -config CIFS_SMB2 - bool "SMB2 and SMB3 network file system support" - depends on CIFS - select KEYS - select FSCACHE - select DNS_RESOLVER - select CRYPTO_AES - select CRYPTO_SHA256 - select CRYPTO_CMAC - select CRYPTO_AEAD2 - select CRYPTO_CCM - - help - This enables support for the Server Message Block version 2 - family of protocols, including SMB3. SMB3 support is - enabled on mount by specifying "vers=3.0" in the mount - options. These protocols are the successors to the popular - CIFS and SMB network file sharing protocols. SMB3 is the - native file sharing mechanism for the more recent - versions of Windows (Windows 8 and Windows 2012 and - later) and Samba server and many others support SMB3 well. - In general SMB3 enables better performance, security - and features, than would be possible with CIFS (Note that - when mounting to Samba, due to the CIFS POSIX extensions, - CIFS mounts can provide slightly better POSIX compatibility - than SMB3 mounts do though). Note that SMB2/SMB3 mount - options are also slightly simpler (compared to CIFS) due - to protocol improvements. - config CIFS_SMB311 bool "SMB3.1.1 network file system support (Experimental)" - depends on CIFS_SMB2 + depends on CIFS help This enables experimental support for the newest, SMB3.1.1, dialect. diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index eed7eb09f46f..5e853a395b92 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -6,7 +6,9 @@ obj-$(CONFIG_CIFS) += cifs.o cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \ link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \ cifs_unicode.o nterr.o cifsencrypt.o \ - readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o + readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o \ + smb2ops.o smb2maperror.o smb2transport.o \ + smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifs-$(CONFIG_CIFS_XATTR) += xattr.o cifs-$(CONFIG_CIFS_ACL) += cifsacl.o @@ -16,6 +18,3 @@ cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o - -cifs-$(CONFIG_CIFS_SMB2) += smb2ops.o smb2maperror.o smb2transport.o \ - smb2misc.o smb2pdu.o smb2inode.o smb2file.o diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index 6c665bf4a27c..2c14020e5e1d 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -292,36 +292,6 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data, return FSCACHE_CHECKAUX_OKAY; } -static void cifs_fscache_inode_now_uncached(void *cookie_netfs_data) -{ - struct cifsInodeInfo *cifsi = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - cifs_dbg(FYI, "%s: cifs inode 0x%p now uncached\n", __func__, cifsi); - - for (;;) { - nr_pages = pagevec_lookup(&pvec, - cifsi->vfs_inode.i_mapping, first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - const struct fscache_cookie_def cifs_fscache_inode_object_def = { .name = "CIFS.uniqueid", .type = FSCACHE_COOKIE_TYPE_DATAFILE, @@ -329,5 +299,4 @@ const struct fscache_cookie_def cifs_fscache_inode_object_def = { .get_attr = cifs_fscache_inode_get_attr, .get_aux = cifs_fscache_inode_get_aux, .check_aux = cifs_fscache_inode_check_aux, - .now_uncached = cifs_fscache_inode_now_uncached, }; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 9727e1dcacd5..cbb9534b89b4 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -160,8 +160,13 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v) if ((ses->serverDomain == NULL) || (ses->serverOS == NULL) || (ses->serverNOS == NULL)) { - seq_printf(m, "\n%d) entry for %s not fully " - "displayed\n\t", i, ses->serverName); + seq_printf(m, "\n%d) Name: %s Uses: %d Capability: 0x%x\tSession Status: %d\t", + i, ses->serverName, ses->ses_count, + ses->capabilities, ses->status); + if (ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) + seq_printf(m, "Guest\t"); + else if (ses->session_flags & SMB2_SESSION_FLAG_IS_NULL) + seq_printf(m, "Anonymous\t"); } else { seq_printf(m, "\n%d) Name: %s Domain: %s Uses: %d OS:" diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index a0b3e7d1be48..b380e0871372 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -79,6 +79,10 @@ convert_sfu_char(const __u16 src_char, char *target) static bool convert_sfm_char(const __u16 src_char, char *target) { + if (src_char >= 0xF001 && src_char <= 0xF01F) { + *target = src_char - 0xF000; + return true; + } switch (src_char) { case SFM_COLON: *target = ':'; @@ -417,6 +421,10 @@ static __le16 convert_to_sfm_char(char src_char, bool end_of_string) { __le16 dest_char; + if (src_char >= 0x01 && src_char <= 0x1F) { + dest_char = cpu_to_le16(src_char + 0xF000); + return dest_char; + } switch (src_char) { case ':': dest_char = cpu_to_le16(SFM_COLON); @@ -580,7 +588,6 @@ ctoUTF16_out: return j; } -#ifdef CONFIG_CIFS_SMB2 /* * cifs_local_to_utf16_bytes - how long will a string be after conversion? * @from - pointer to input string @@ -639,4 +646,3 @@ cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len, *utf16_len = len; return dst; } -#endif /* CONFIG_CIFS_SMB2 */ diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index 8a79a34e66b8..8360b74530a9 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -116,11 +116,9 @@ char *cifs_strndup_from_utf16(const char *src, const int maxlen, extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen, const struct nls_table *cp, int mapChars); extern int cifs_remap(struct cifs_sb_info *cifs_sb); -#ifdef CONFIG_CIFS_SMB2 extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len, const struct nls_table *cp, int remap); -#endif /* CONFIG_CIFS_SMB2 */ #endif wchar_t cifs_toupper(wchar_t in); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 9a1667e0e8d6..8c8b75d33f31 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -51,9 +51,7 @@ #include <linux/key-type.h> #include "cifs_spnego.h" #include "fscache.h" -#ifdef CONFIG_CIFS_SMB2 #include "smb2pdu.h" -#endif int cifsFYI = 0; bool traceSMB; @@ -277,9 +275,8 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->uniqueid = 0; cifs_inode->createtime = 0; cifs_inode->epoch = 0; -#ifdef CONFIG_CIFS_SMB2 generate_random_uuid(cifs_inode->lease_key); -#endif + /* * Can not set i_flags here - they get immediately overwritten to zero * by the VFS. @@ -464,6 +461,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",nocase"); if (tcon->retry) seq_puts(s, ",hard"); + else + seq_puts(s, ",soft"); if (tcon->use_persistent) seq_puts(s, ",persistenthandles"); else if (tcon->use_resilient) @@ -1213,14 +1212,12 @@ cifs_destroy_inodecache(void) static int cifs_init_request_bufs(void) { - size_t max_hdr_size = MAX_CIFS_HDR_SIZE; -#ifdef CONFIG_CIFS_SMB2 /* * SMB2 maximum header size is bigger than CIFS one - no problems to * allocate some more bytes for CIFS. */ - max_hdr_size = MAX_SMB2_HDR_SIZE; -#endif + size_t max_hdr_size = MAX_SMB2_HDR_SIZE; + if (CIFSMaxBufSize < 8192) { /* Buffer size can not be smaller than 2 * PATH_MAX since maximum Unicode path name has to fit in any SMB/CIFS path based frames */ @@ -1359,7 +1356,7 @@ init_cifs(void) spin_lock_init(&cifs_tcp_ses_lock); spin_lock_init(&GlobalMid_Lock); - get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret)); + cifs_lock_secret = get_random_u32(); if (cifs_max_pending < 2) { cifs_max_pending = 2; @@ -1452,7 +1449,7 @@ exit_cifs(void) exit_cifs_idmap(); #endif #ifdef CONFIG_CIFS_UPCALL - unregister_key_type(&cifs_spnego_key_type); + exit_cifs_spnego(); #endif cifs_destroy_request_bufs(); cifs_destroy_mids(); @@ -1476,12 +1473,10 @@ MODULE_SOFTDEP("pre: hmac"); MODULE_SOFTDEP("pre: md4"); MODULE_SOFTDEP("pre: md5"); MODULE_SOFTDEP("pre: nls"); -#ifdef CONFIG_CIFS_SMB2 MODULE_SOFTDEP("pre: aes"); MODULE_SOFTDEP("pre: cmac"); MODULE_SOFTDEP("pre: sha256"); MODULE_SOFTDEP("pre: aead2"); MODULE_SOFTDEP("pre: ccm"); -#endif /* CONFIG_CIFS_SMB2 */ module_init(init_cifs) module_exit(exit_cifs) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 30bf89b1fd9a..5a10e566f0e6 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -149,5 +149,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.09" +#define CIFS_VERSION "2.10" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index bcc7d9acad64..de5b2e1fcce5 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -29,9 +29,7 @@ #include <crypto/internal/hash.h> #include <linux/scatterlist.h> #include <uapi/linux/cifs/cifs_mount.h> -#ifdef CONFIG_CIFS_SMB2 #include "smb2pdu.h" -#endif #define CIFS_MAGIC_NUMBER 0xFF534D42 /* the first four bytes of SMB PDUs */ @@ -190,6 +188,8 @@ enum smb_version { #ifdef CONFIG_CIFS_SMB311 Smb_311, #endif /* SMB311 */ + Smb_3any, + Smb_default, Smb_version_err }; @@ -367,6 +367,8 @@ struct smb_version_operations { unsigned int (*calc_smb_size)(void *); /* check for STATUS_PENDING and process it in a positive case */ bool (*is_status_pending)(char *, struct TCP_Server_Info *, int); + /* check for STATUS_NETWORK_SESSION_EXPIRED */ + bool (*is_session_expired)(char *); /* send oplock break response */ int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, struct cifsInodeInfo *); @@ -421,7 +423,7 @@ struct smb_version_operations { size_t, struct cifs_sb_info *); int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *, const char *, const void *, const __u16, - const struct nls_table *, int); + const struct nls_table *, struct cifs_sb_info *); struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *, const char *, u32 *); struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *, @@ -610,12 +612,10 @@ struct TCP_Server_Info { __u16 sec_mode; bool sign; /* is signing enabled on this connection? */ bool session_estab; /* mark when very first sess is established */ -#ifdef CONFIG_CIFS_SMB2 int echo_credits; /* echo reserved slots */ int oplock_credits; /* oplock break reserved slots */ bool echoes:1; /* enable echoes */ __u8 client_guid[SMB2_CLIENT_GUID_SIZE]; /* Client GUID */ -#endif u16 dialect; /* dialect index that server chose */ bool oplocks:1; /* enable oplocks */ unsigned int maxReq; /* Clients should submit no more */ @@ -659,13 +659,11 @@ struct TCP_Server_Info { atomic_t in_send; /* requests trying to send */ atomic_t num_waiters; /* blocked waiting to get in sendrecv */ #endif -#ifdef CONFIG_CIFS_SMB2 unsigned int max_read; unsigned int max_write; __u8 preauth_hash[512]; struct delayed_work reconnect; /* reconnect workqueue job */ struct mutex reconnect_mutex; /* prevent simultaneous reconnects */ -#endif /* CONFIG_CIFS_SMB2 */ unsigned long echo_interval; }; @@ -847,13 +845,11 @@ struct cifs_ses { bool sign; /* is signing required? */ bool need_reconnect:1; /* connection reset, uid now invalid */ bool domainAuto:1; -#ifdef CONFIG_CIFS_SMB2 __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; __u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE]; __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE]; __u8 preauth_hash[512]; -#endif /* CONFIG_CIFS_SMB2 */ }; static inline bool @@ -905,12 +901,10 @@ struct cifs_tcon { atomic_t num_acl_get; atomic_t num_acl_set; } cifs_stats; -#ifdef CONFIG_CIFS_SMB2 struct { atomic_t smb2_com_sent[NUMBER_OF_SMB2_COMMANDS]; atomic_t smb2_com_failed[NUMBER_OF_SMB2_COMMANDS]; } smb2_stats; -#endif /* CONFIG_CIFS_SMB2 */ } stats; #ifdef CONFIG_CIFS_STATS2 unsigned long long time_writes; @@ -946,7 +940,6 @@ struct cifs_tcon { bool need_reopen_files:1; /* need to reopen tcon file handles */ bool use_resilient:1; /* use resilient instead of durable handles */ bool use_persistent:1; /* use persistent instead of durable handles */ -#ifdef CONFIG_CIFS_SMB2 bool print:1; /* set if connection to printer share */ __le32 capabilities; __u32 share_flags; @@ -959,7 +952,6 @@ struct cifs_tcon { __u32 max_chunks; __u32 max_bytes_chunk; __u32 max_bytes_copy; -#endif /* CONFIG_CIFS_SMB2 */ #ifdef CONFIG_CIFS_FSCACHE u64 resource_id; /* server resource id */ struct fscache_cookie *fscache; /* cookie for share */ @@ -1062,12 +1054,10 @@ struct cifs_open_parms { struct cifs_fid { __u16 netfid; -#ifdef CONFIG_CIFS_SMB2 __u64 persistent_fid; /* persist file id for smb2 */ __u64 volatile_fid; /* volatile file id for smb2 */ __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for smb2 */ __u8 create_guid[16]; -#endif struct cifs_pending_open *pending_open; unsigned int epoch; bool purge_cache; @@ -1105,10 +1095,8 @@ struct cifsFileInfo { struct cifs_io_parms { __u16 netfid; -#ifdef CONFIG_CIFS_SMB2 __u64 persistent_fid; /* persist file id for smb2 */ __u64 volatile_fid; /* volatile file id for smb2 */ -#endif __u32 pid; __u64 offset; unsigned int length; @@ -1234,9 +1222,7 @@ struct cifsInodeInfo { u64 server_eof; /* current file size on server -- protected by i_lock */ u64 uniqueid; /* server inode number */ u64 createtime; /* creation time on server */ -#ifdef CONFIG_CIFS_SMB2 __u8 lease_key[SMB2_LEASE_KEY_SIZE]; /* lease key for this inode */ -#endif #ifdef CONFIG_CIFS_FSCACHE struct fscache_cookie *fscache; #endif @@ -1717,6 +1703,10 @@ extern struct smb_version_values smb20_values; #define SMB21_VERSION_STRING "2.1" extern struct smb_version_operations smb21_operations; extern struct smb_version_values smb21_values; +#define SMBDEFAULT_VERSION_STRING "default" +extern struct smb_version_values smbdefault_values; +#define SMB3ANY_VERSION_STRING "3" +extern struct smb_version_values smb3any_values; #define SMB30_VERSION_STRING "3.0" extern struct smb_version_operations smb30_operations; extern struct smb_version_values smb30_values; diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 6eb3147132e3..4143c9dec463 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -484,7 +484,8 @@ extern ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon, extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, const char *fileName, const char *ea_name, const void *ea_value, const __u16 ea_value_len, - const struct nls_table *nls_codepage, int remap_special_chars); + const struct nls_table *nls_codepage, + struct cifs_sb_info *cifs_sb); extern int CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, struct cifs_ntsd **acl_inf, __u32 *buflen); extern int CIFSSMBSetCIFSACL(const unsigned int, struct cifs_tcon *, __u16, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index fbb0d4cbda41..35dc5bf01ee2 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -178,6 +178,18 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) * reconnect the same SMB session */ mutex_lock(&ses->session_mutex); + + /* + * Recheck after acquire mutex. If another thread is negotiating + * and the server never sends an answer the socket will be closed + * and tcpStatus set to reconnect. + */ + if (server->tcpStatus == CifsNeedReconnect) { + rc = -EHOSTDOWN; + mutex_unlock(&ses->session_mutex); + goto out; + } + rc = cifs_negotiate_protocol(0, ses); if (rc == 0 && ses->need_reconnect) rc = cifs_setup_session(0, ses, nls_codepage); @@ -1460,6 +1472,13 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_session_expired && + server->ops->is_session_expired(buf)) { + cifs_reconnect(server); + wake_up(&server->response_q); + return -1; + } + if (server->ops->is_status_pending && server->ops->is_status_pending(buf, server, 0)) { cifs_discard_remaining_data(server); @@ -2515,7 +2534,7 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon, pLockData->fl_start = le64_to_cpu(parm_data->start); pLockData->fl_end = pLockData->fl_start + le64_to_cpu(parm_data->length) - 1; - pLockData->fl_pid = le32_to_cpu(parm_data->pid); + pLockData->fl_pid = -le32_to_cpu(parm_data->pid); } } @@ -6257,7 +6276,7 @@ int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, const char *fileName, const char *ea_name, const void *ea_value, const __u16 ea_value_len, const struct nls_table *nls_codepage, - int remap) + struct cifs_sb_info *cifs_sb) { struct smb_com_transaction2_spi_req *pSMB = NULL; struct smb_com_transaction2_spi_rsp *pSMBr = NULL; @@ -6266,6 +6285,7 @@ CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int bytes_returned = 0; __u16 params, param_offset, byte_count, offset, count; + int remap = cifs_remap(cifs_sb); cifs_dbg(FYI, "In SetEA\n"); SetEARetry: diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 9365c0cf77ad..0bfc2280436d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -55,9 +55,7 @@ #include "nterr.h" #include "rfc1002pdu.h" #include "fscache.h" -#ifdef CONFIG_CIFS_SMB2 #include "smb2proto.h" -#endif #define CIFS_PORT 445 #define RFC1001_PORT 139 @@ -303,6 +301,8 @@ static const match_table_t cifs_smb_version_tokens = { { Smb_311, SMB311_VERSION_STRING }, { Smb_311, ALT_SMB311_VERSION_STRING }, #endif /* SMB311 */ + { Smb_3any, SMB3ANY_VERSION_STRING }, + { Smb_default, SMBDEFAULT_VERSION_STRING }, { Smb_version_err, NULL } }; @@ -341,9 +341,7 @@ cifs_reconnect(struct TCP_Server_Info *server) server->tcpStatus = CifsNeedReconnect; spin_unlock(&GlobalMid_Lock); server->maxBuf = 0; -#ifdef CONFIG_CIFS_SMB2 server->max_read = 0; -#endif cifs_dbg(FYI, "Reconnecting tcp session\n"); @@ -513,7 +511,8 @@ server_unresponsive(struct TCP_Server_Info *server) * 65s kernel_recvmsg times out, and we see that we haven't gotten * a response in >60s. */ - if (server->tcpStatus == CifsGood && + if ((server->tcpStatus == CifsGood || + server->tcpStatus == CifsNeedNegotiate) && time_after(jiffies, server->lstrp + 2 * server->echo_interval)) { cifs_dbg(VFS, "Server %s has not responded in %lu seconds. Reconnecting...\n", server->hostname, (2 * server->echo_interval) / HZ); @@ -812,6 +811,13 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid) cifs_dump_mem("Bad SMB: ", buf, min_t(unsigned int, server->total_read, 48)); + if (server->ops->is_session_expired && + server->ops->is_session_expired(buf)) { + cifs_reconnect(server); + wake_up(&server->response_q); + return -1; + } + if (server->ops->is_status_pending && server->ops->is_status_pending(buf, server, length)) return -1; @@ -1122,7 +1128,6 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol) vol->ops = &smb1_operations; vol->vals = &smb1_values; break; -#ifdef CONFIG_CIFS_SMB2 case Smb_20: vol->ops = &smb20_operations; vol->vals = &smb20_values; @@ -1145,7 +1150,14 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol) vol->vals = &smb311_values; break; #endif /* SMB311 */ -#endif + case Smb_3any: + vol->ops = &smb30_operations; /* currently identical with 3.0 */ + vol->vals = &smb3any_values; + break; + case Smb_default: + vol->ops = &smb30_operations; /* currently identical with 3.0 */ + vol->vals = &smbdefault_values; + break; default: cifs_dbg(VFS, "Unknown vers= option specified: %s\n", value); return 1; @@ -1222,6 +1234,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, char *tmp_end, *value; char delim; bool got_ip = false; + bool got_version = false; unsigned short port = 0; struct sockaddr *dstaddr = (struct sockaddr *)&vol->dstaddr; @@ -1271,9 +1284,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->actimeo = CIFS_DEF_ACTIMEO; - /* FIXME: add autonegotiation -- for now, SMB1 is default */ - vol->ops = &smb1_operations; - vol->vals = &smb1_values; + /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */ + vol->ops = &smb30_operations; + vol->vals = &smbdefault_values; vol->echo_interval = SMB_ECHO_INTERVAL_DEFAULT; @@ -1873,24 +1886,35 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, pr_warn("CIFS: server netbiosname longer than 15 truncated.\n"); break; case Opt_ver: + /* version of mount userspace tools, not dialect */ string = match_strdup(args); if (string == NULL) goto out_nomem; + /* If interface changes in mount.cifs bump to new ver */ if (strncasecmp(string, "1", 1) == 0) { + if (strlen(string) > 1) { + pr_warn("Bad mount helper ver=%s. Did " + "you want SMB1 (CIFS) dialect " + "and mean to type vers=1.0 " + "instead?\n", string); + goto cifs_parse_mount_err; + } /* This is the default */ break; } /* For all other value, error */ - pr_warn("CIFS: Invalid version specified\n"); + pr_warn("CIFS: Invalid mount helper version specified\n"); goto cifs_parse_mount_err; case Opt_vers: + /* protocol version (dialect) */ string = match_strdup(args); if (string == NULL) goto out_nomem; if (cifs_parse_smb_version(string, vol) != 0) goto cifs_parse_mount_err; + got_version = true; break; case Opt_sec: string = match_strdup(args); @@ -1972,6 +1996,13 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, else if (override_gid == 1) pr_notice("CIFS: ignoring forcegid mount option specified with no gid= option.\n"); + if (got_version == false) + pr_warn("No dialect specified on mount. Default has changed to " + "a more secure dialect, SMB2.1 or later (e.g. SMB3), from CIFS " + "(SMB1). To use the less secure SMB1 dialect to access " + "old servers which do not support SMB3 (or SMB2.1) specify vers=1.0" + " on mount.\n"); + kfree(mountdata_copy); return 0; @@ -2111,6 +2142,7 @@ static int match_server(struct TCP_Server_Info *server, struct smb_vol *vol) if (vol->nosharesock) return 0; + /* BB update this for smb3any and default case */ if ((server->vals != vol->vals) || (server->ops != vol->ops)) return 0; @@ -2170,7 +2202,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) cancel_delayed_work_sync(&server->echo); -#ifdef CONFIG_CIFS_SMB2 if (from_reconnect) /* * Avoid deadlock here: reconnect work calls @@ -2181,7 +2212,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) cancel_delayed_work(&server->reconnect); else cancel_delayed_work_sync(&server->reconnect); -#endif spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; @@ -2247,17 +2277,13 @@ cifs_get_tcp_session(struct smb_vol *volume_info) INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); -#ifdef CONFIG_CIFS_SMB2 INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server); mutex_init(&tcp_ses->reconnect_mutex); -#endif memcpy(&tcp_ses->srcaddr, &volume_info->srcaddr, sizeof(tcp_ses->srcaddr)); memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr, sizeof(tcp_ses->dstaddr)); -#ifdef CONFIG_CIFS_SMB2 generate_random_uuid(tcp_ses->client_guid); -#endif /* * at this point we are the only ones with the pointer * to the struct since the kernel thread not created yet @@ -2655,10 +2681,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info) return 0; if (tcon->seal != volume_info->seal) return 0; -#ifdef CONFIG_CIFS_SMB2 if (tcon->snapshot_time != volume_info->snapshot_time) return 0; -#endif /* CONFIG_CIFS_SMB2 */ return 1; } @@ -2733,7 +2757,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) } if (volume_info->snapshot_time) { -#ifdef CONFIG_CIFS_SMB2 if (ses->server->vals->protocol_id == 0) { cifs_dbg(VFS, "Use SMB2 or later for snapshot mount option\n"); @@ -2741,11 +2764,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) goto out_fail; } else tcon->snapshot_time = volume_info->snapshot_time; -#else - cifs_dbg(VFS, "Snapshot mount option requires SMB2 support\n"); - rc = -EOPNOTSUPP; - goto out_fail; -#endif /* CONFIG_CIFS_SMB2 */ } tcon->ses = ses; @@ -2781,7 +2799,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) "SMB3 or later required for persistent handles\n"); rc = -EOPNOTSUPP; goto out_fail; -#ifdef CONFIG_CIFS_SMB2 } else if (ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) tcon->use_persistent = true; @@ -2790,15 +2807,12 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) "Persistent handles not supported on share\n"); rc = -EOPNOTSUPP; goto out_fail; -#endif /* CONFIG_CIFS_SMB2 */ } -#ifdef CONFIG_CIFS_SMB2 } else if ((tcon->capabilities & SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY) && (ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) && (volume_info->nopersistent == false)) { cifs_dbg(FYI, "enabling persistent handles\n"); tcon->use_persistent = true; -#endif /* CONFIG_CIFS_SMB2 */ } else if (volume_info->resilient) { if (ses->server->vals->protocol_id == 0) { cifs_dbg(VFS, @@ -2815,7 +2829,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) "SMB3 or later required for encryption\n"); rc = -EOPNOTSUPP; goto out_fail; -#ifdef CONFIG_CIFS_SMB2 } else if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) tcon->seal = true; @@ -2823,7 +2836,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) cifs_dbg(VFS, "Encryption is not supported on share\n"); rc = -EOPNOTSUPP; goto out_fail; -#endif /* CONFIG_CIFS_SMB2 */ } } @@ -3738,14 +3750,12 @@ try_mount_again: goto mount_fail_check; } -#ifdef CONFIG_CIFS_SMB2 if ((volume_info->persistent == true) && ((ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) == 0)) { cifs_dbg(VFS, "persistent handles not supported by server\n"); rc = -EOPNOTSUPP; goto mount_fail_check; } -#endif /* CONFIG_CIFS_SMB2*/ /* search for existing tcon to this server share */ tcon = cifs_get_tcon(ses, volume_info); @@ -4144,6 +4154,14 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n", server->sec_mode, server->capabilities, server->timeAdj); + if (ses->auth_key.response) { + cifs_dbg(VFS, "Free previous auth_key.response = %p\n", + ses->auth_key.response); + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + ses->auth_key.len = 0; + } + if (server->ops->sess_setup) rc = server->ops->sess_setup(xid, ses, nls_info); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 56366e984076..e702d48bd023 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -194,15 +194,20 @@ cifs_bp_rename_retry: } /* + * Don't allow path components longer than the server max. * Don't allow the separator character in a path component. * The VFS will not allow "/", but "\" is allowed by posix. */ static int -check_name(struct dentry *direntry) +check_name(struct dentry *direntry, struct cifs_tcon *tcon) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); int i; + if (unlikely(direntry->d_name.len > + le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength))) + return -ENAMETOOLONG; + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { for (i = 0; i < direntry->d_name.len; i++) { if (direntry->d_name.name[i] == '\\') { @@ -500,10 +505,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, return finish_no_open(file, res); } - rc = check_name(direntry); - if (rc) - return rc; - xid = get_xid(); cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n", @@ -516,6 +517,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, } tcon = tlink_tcon(tlink); + + rc = check_name(direntry, tcon); + if (rc) + goto out_free_xid; + server = tcon->ses->server; if (server->ops->new_lease_key) @@ -776,7 +782,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } pTcon = tlink_tcon(tlink); - rc = check_name(direntry); + rc = check_name(direntry, pTcon); if (rc) goto lookup_out; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fcef70602b27..92fdf9c35de2 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -224,6 +224,13 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, if (backup_cred(cifs_sb)) create_options |= CREATE_OPEN_BACKUP_INTENT; + /* O_SYNC also has bit for O_DSYNC so following check picks up either */ + if (f_flags & O_SYNC) + create_options |= CREATE_WRITE_THROUGH; + + if (f_flags & O_DIRECT) + create_options |= CREATE_NO_BUFFER; + oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = desired_access; @@ -1102,8 +1109,10 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) struct cifs_tcon *tcon; unsigned int num, max_num, max_buf; LOCKING_ANDX_RANGE *buf, *cur; - int types[] = {LOCKING_ANDX_LARGE_FILES, - LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; + static const int types[] = { + LOCKING_ANDX_LARGE_FILES, + LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES + }; int i; xid = get_xid(); @@ -1434,8 +1443,10 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, unsigned int xid) { int rc = 0, stored_rc; - int types[] = {LOCKING_ANDX_LARGE_FILES, - LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; + static const int types[] = { + LOCKING_ANDX_LARGE_FILES, + LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES + }; unsigned int i; unsigned int max_num, num, max_buf; LOCKING_ANDX_RANGE *buf, *cur; @@ -2234,14 +2245,16 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc) set_page_writeback(page); retry_write: rc = cifs_partialpagewrite(page, 0, PAGE_SIZE); - if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL) - goto retry_write; - else if (rc == -EAGAIN) + if (rc == -EAGAIN) { + if (wbc->sync_mode == WB_SYNC_ALL) + goto retry_write; redirty_page_for_writepage(wbc, page); - else if (rc != 0) + } else if (rc != 0) { SetPageError(page); - else + mapping_set_error(page->mapping, rc); + } else { SetPageUptodate(page); + } end_page_writeback(page); put_page(page); free_xid(xid); @@ -2327,7 +2340,7 @@ int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, struct inode *inode = file_inode(file); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); - rc = filemap_write_and_wait_range(inode->i_mapping, start, end); + rc = file_write_and_wait_range(file, start, end); if (rc) return rc; inode_lock(inode); @@ -2369,7 +2382,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); struct inode *inode = file->f_mapping->host; - rc = filemap_write_and_wait_range(inode->i_mapping, start, end); + rc = file_write_and_wait_range(file, start, end); if (rc) return rc; inode_lock(inode); @@ -2810,12 +2823,12 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; ssize_t rc; + inode_lock(inode); /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents writing. */ down_read(&cinode->lock_sem); - inode_lock(inode); rc = generic_write_checks(iocb, from); if (rc <= 0) @@ -2828,11 +2841,11 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) else rc = -EACCES; out: + up_read(&cinode->lock_sem); inode_unlock(inode); if (rc > 0) rc = generic_write_sync(iocb, rc); - up_read(&cinode->lock_sem); return rc; } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 4d1fcd76d022..7c732cb44164 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -24,6 +24,7 @@ #include <linux/pagemap.h> #include <linux/freezer.h> #include <linux/sched/signal.h> +#include <linux/wait_bit.h> #include <asm/div64.h> #include "cifsfs.h" @@ -233,6 +234,8 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime); fattr->cf_mtime = cifs_NTtimeToUnix(info->LastModificationTime); fattr->cf_ctime = cifs_NTtimeToUnix(info->LastStatusChange); + /* old POSIX extensions don't get create time */ + fattr->cf_mode = le64_to_cpu(info->Permissions); /* @@ -2023,6 +2026,19 @@ int cifs_getattr(const struct path *path, struct kstat *stat, stat->blksize = CIFS_MAX_MSGSIZE; stat->ino = CIFS_I(inode)->uniqueid; + /* old CIFS Unix Extensions doesn't return create time */ + if (CIFS_I(inode)->createtime) { + stat->result_mask |= STATX_BTIME; + stat->btime = + cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime)); + } + + stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED); + if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_COMPRESSED) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_ENCRYPTED) + stat->attributes |= STATX_ATTR_ENCRYPTED; + /* * If on a multiuser mount without unix extensions or cifsacl being * enabled, and the admin hasn't overridden them, set the ownership diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 76fb0917dc8c..54f32f9143a9 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -101,7 +101,6 @@ static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon, fsinf->fs_attributes = le32_to_cpu(tcon->fsAttrInfo.Attributes); fsinf->max_path_component = le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength); -#ifdef CONFIG_CIFS_SMB2 fsinf->vol_serial_number = tcon->vol_serial_number; fsinf->vol_create_time = le64_to_cpu(tcon->vol_create_time); fsinf->share_flags = tcon->share_flags; @@ -110,7 +109,6 @@ static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon, fsinf->optimal_sector_size = tcon->perf_sector_size; fsinf->max_bytes_chunk = tcon->max_bytes_chunk; fsinf->maximal_access = tcon->maximal_access; -#endif /* SMB2 */ fsinf->cifs_posix_caps = le64_to_cpu(tcon->fsUnixInfo.Capability); if (copy_to_user(arg, fsinf, sizeof(struct smb_mnt_fs_info))) diff --git a/fs/cifs/link.c b/fs/cifs/link.c index c4d996f78e1c..60b5a11ee11b 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -29,9 +29,7 @@ #include "cifs_debug.h" #include "cifs_fs_sb.h" #include "cifs_unicode.h" -#ifdef CONFIG_CIFS_SMB2 #include "smb2proto.h" -#endif /* * M-F Symlink Functions - Begin @@ -402,7 +400,6 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, /* * SMB 2.1/SMB3 Protocol specific functions */ -#ifdef CONFIG_CIFS_SMB2 int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, @@ -525,7 +522,6 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, kfree(utf16_path); return rc; } -#endif /* CONFIG_CIFS_SMB2 */ /* * M-F Symlink Functions - End diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 3b147dc6af63..eea93ac15ef0 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -30,9 +30,7 @@ #include "smberr.h" #include "nterr.h" #include "cifs_unicode.h" -#ifdef CONFIG_CIFS_SMB2 #include "smb2pdu.h" -#endif extern mempool_t *cifs_sm_req_poolp; extern mempool_t *cifs_req_poolp; @@ -149,15 +147,12 @@ struct smb_hdr * cifs_buf_get(void) { struct smb_hdr *ret_buf = NULL; - size_t buf_size = sizeof(struct smb_hdr); - -#ifdef CONFIG_CIFS_SMB2 /* * SMB2 header is bigger than CIFS one - no problems to clean some * more bytes for CIFS. */ - buf_size = sizeof(struct smb2_hdr); -#endif + size_t buf_size = sizeof(struct smb2_hdr); + /* * We could use negotiated size instead of max_msgsize - * but it may be more efficient to always alloc same size @@ -620,9 +615,7 @@ void cifs_add_pending_open_locked(struct cifs_fid *fid, struct tcon_link *tlink, struct cifs_pending_open *open) { -#ifdef CONFIG_CIFS_SMB2 memcpy(open->lease_key, fid->lease_key, SMB2_LEASE_KEY_SIZE); -#endif open->oplock = CIFS_OPLOCK_NO_CHANGE; open->tlink = tlink; fid->pending_open = open; diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 3030a9dfb0dd..7ca9808a0daa 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -2475,8 +2475,8 @@ map_smb2_to_linux_error(char *buf, bool log_err) /* on error mapping not found - return EIO */ - cifs_dbg(FYI, "Mapping SMB2 status code %d to POSIX err %d\n", - smb2err, rc); + cifs_dbg(FYI, "Mapping SMB2 status code 0x%08x to POSIX err %d\n", + __le32_to_cpu(smb2err), rc); return rc; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 7e48561abd29..0dafdbae1f8c 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -426,6 +426,196 @@ smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, return rc; } +#ifdef CONFIG_CIFS_XATTR +static ssize_t +move_smb2_ea_to_cifs(char *dst, size_t dst_size, + struct smb2_file_full_ea_info *src, size_t src_size, + const unsigned char *ea_name) +{ + int rc = 0; + unsigned int ea_name_len = ea_name ? strlen(ea_name) : 0; + char *name, *value; + size_t name_len, value_len, user_name_len; + + while (src_size > 0) { + name = &src->ea_data[0]; + name_len = (size_t)src->ea_name_length; + value = &src->ea_data[src->ea_name_length + 1]; + value_len = (size_t)le16_to_cpu(src->ea_value_length); + + if (name_len == 0) { + break; + } + + if (src_size < 8 + name_len + 1 + value_len) { + cifs_dbg(FYI, "EA entry goes beyond length of list\n"); + rc = -EIO; + goto out; + } + + if (ea_name) { + if (ea_name_len == name_len && + memcmp(ea_name, name, name_len) == 0) { + rc = value_len; + if (dst_size == 0) + goto out; + if (dst_size < value_len) { + rc = -ERANGE; + goto out; + } + memcpy(dst, value, value_len); + goto out; + } + } else { + /* 'user.' plus a terminating null */ + user_name_len = 5 + 1 + name_len; + + rc += user_name_len; + + if (dst_size >= user_name_len) { + dst_size -= user_name_len; + memcpy(dst, "user.", 5); + dst += 5; + memcpy(dst, src->ea_data, name_len); + dst += name_len; + *dst = 0; + ++dst; + } else if (dst_size == 0) { + /* skip copy - calc size only */ + } else { + /* stop before overrun buffer */ + rc = -ERANGE; + break; + } + } + + if (!src->next_entry_offset) + break; + + if (src_size < le32_to_cpu(src->next_entry_offset)) { + /* stop before overrun buffer */ + rc = -ERANGE; + break; + } + src_size -= le32_to_cpu(src->next_entry_offset); + src = (void *)((char *)src + + le32_to_cpu(src->next_entry_offset)); + } + + /* didn't find the named attribute */ + if (ea_name) + rc = -ENODATA; + +out: + return (ssize_t)rc; +} + +static ssize_t +smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, + const unsigned char *path, const unsigned char *ea_name, + char *ea_data, size_t buf_size, + struct cifs_sb_info *cifs_sb) +{ + int rc; + __le16 *utf16_path; + __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_open_parms oparms; + struct cifs_fid fid; + struct smb2_file_full_ea_info *smb2_data; + + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return -ENOMEM; + + oparms.tcon = tcon; + oparms.desired_access = FILE_READ_EA; + oparms.disposition = FILE_OPEN; + oparms.create_options = 0; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + kfree(utf16_path); + if (rc) { + cifs_dbg(FYI, "open failed rc=%d\n", rc); + return rc; + } + + smb2_data = kzalloc(SMB2_MAX_EA_BUF, GFP_KERNEL); + if (smb2_data == NULL) { + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + return -ENOMEM; + } + + rc = SMB2_query_eas(xid, tcon, fid.persistent_fid, fid.volatile_fid, + smb2_data); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + + if (!rc) + rc = move_smb2_ea_to_cifs(ea_data, buf_size, smb2_data, + SMB2_MAX_EA_BUF, ea_name); + + kfree(smb2_data); + return rc; +} + + +static int +smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, + const char *path, const char *ea_name, const void *ea_value, + const __u16 ea_value_len, const struct nls_table *nls_codepage, + struct cifs_sb_info *cifs_sb) +{ + int rc; + __le16 *utf16_path; + __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_open_parms oparms; + struct cifs_fid fid; + struct smb2_file_full_ea_info *ea; + int ea_name_len = strlen(ea_name); + int len; + + if (ea_name_len > 255) + return -EINVAL; + + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return -ENOMEM; + + oparms.tcon = tcon; + oparms.desired_access = FILE_WRITE_EA; + oparms.disposition = FILE_OPEN; + oparms.create_options = 0; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + kfree(utf16_path); + if (rc) { + cifs_dbg(FYI, "open failed rc=%d\n", rc); + return rc; + } + + len = sizeof(ea) + ea_name_len + ea_value_len + 1; + ea = kzalloc(len, GFP_KERNEL); + if (ea == NULL) { + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + return -ENOMEM; + } + + ea->ea_name_length = ea_name_len; + ea->ea_value_length = cpu_to_le16(ea_value_len); + memcpy(ea->ea_data, ea_name, ea_name_len + 1); + memcpy(ea->ea_data + ea_name_len + 1, ea_value, ea_value_len); + + rc = SMB2_set_ea(xid, tcon, fid.persistent_fid, fid.volatile_fid, ea, + len); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + + return rc; +} +#endif + static bool smb2_can_echo(struct TCP_Server_Info *server) { @@ -1036,6 +1226,18 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length) return true; } +static bool +smb2_is_session_expired(char *buf) +{ + struct smb2_sync_hdr *shdr = get_sync_hdr(buf); + + if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED) + return false; + + cifs_dbg(FYI, "Session expired\n"); + return true; +} + static int smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, struct cifsInodeInfo *cinode) @@ -1288,6 +1490,165 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, return rc; } +#ifdef CONFIG_CIFS_ACL +static struct cifs_ntsd * +get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb, + const struct cifs_fid *cifsfid, u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + unsigned int xid; + int rc = -EOPNOTSUPP; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + + if (IS_ERR(tlink)) + return ERR_CAST(tlink); + + xid = get_xid(); + cifs_dbg(FYI, "trying to get acl\n"); + + rc = SMB2_query_acl(xid, tlink_tcon(tlink), cifsfid->persistent_fid, + cifsfid->volatile_fid, (void **)&pntsd, pacllen); + free_xid(xid); + + cifs_put_tlink(tlink); + + cifs_dbg(FYI, "%s: rc = %d ACL len %d\n", __func__, rc, *pacllen); + if (rc) + return ERR_PTR(rc); + return pntsd; + +} + +static struct cifs_ntsd * +get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, + const char *path, u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + unsigned int xid; + int rc; + struct cifs_tcon *tcon; + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_fid fid; + struct cifs_open_parms oparms; + __le16 *utf16_path; + + cifs_dbg(FYI, "get smb3 acl for path %s\n", path); + if (IS_ERR(tlink)) + return ERR_CAST(tlink); + + tcon = tlink_tcon(tlink); + xid = get_xid(); + + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; + + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return ERR_PTR(-ENOMEM); + + oparms.tcon = tcon; + oparms.desired_access = READ_CONTROL; + oparms.disposition = FILE_OPEN; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + kfree(utf16_path); + if (!rc) { + rc = SMB2_query_acl(xid, tlink_tcon(tlink), fid.persistent_fid, + fid.volatile_fid, (void **)&pntsd, pacllen); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + } + + cifs_put_tlink(tlink); + free_xid(xid); + + cifs_dbg(FYI, "%s: rc = %d ACL len %d\n", __func__, rc, *pacllen); + if (rc) + return ERR_PTR(rc); + return pntsd; +} + +#ifdef CONFIG_CIFS_ACL +static int +set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen, + struct inode *inode, const char *path, int aclflag) +{ + u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + unsigned int xid; + int rc, access_flags = 0; + struct cifs_tcon *tcon; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); + struct cifs_fid fid; + struct cifs_open_parms oparms; + __le16 *utf16_path; + + cifs_dbg(FYI, "set smb3 acl for path %s\n", path); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + + tcon = tlink_tcon(tlink); + xid = get_xid(); + + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; + + if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP) + access_flags = WRITE_OWNER; + else + access_flags = WRITE_DAC; + + utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); + if (!utf16_path) + return -ENOMEM; + + oparms.tcon = tcon; + oparms.desired_access = access_flags; + oparms.disposition = FILE_OPEN; + oparms.path = path; + oparms.fid = &fid; + oparms.reconnect = false; + + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + kfree(utf16_path); + if (!rc) { + rc = SMB2_set_acl(xid, tlink_tcon(tlink), fid.persistent_fid, + fid.volatile_fid, pnntsd, acllen, aclflag); + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + } + + cifs_put_tlink(tlink); + free_xid(xid); + return rc; +} +#endif /* CIFS_ACL */ + +/* Retrieve an ACL from the server */ +static struct cifs_ntsd * +get_smb2_acl(struct cifs_sb_info *cifs_sb, + struct inode *inode, const char *path, + u32 *pacllen) +{ + struct cifs_ntsd *pntsd = NULL; + struct cifsFileInfo *open_file = NULL; + + if (inode) + open_file = find_readable_file(CIFS_I(inode), true); + if (!open_file) + return get_smb2_acl_by_path(cifs_sb, path, pacllen); + + pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen); + cifsFileInfo_put(open_file); + return pntsd; +} +#endif + static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, loff_t offset, loff_t len, bool keep_size) { @@ -2058,6 +2419,13 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, return -ENOTSUPP; } + if (server->ops->is_session_expired && + server->ops->is_session_expired(buf)) { + cifs_reconnect(server); + wake_up(&server->response_q); + return -1; + } + if (server->ops->is_status_pending && server->ops->is_status_pending(buf, server, 0)) return -1; @@ -2375,6 +2743,7 @@ struct smb_version_operations smb20_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -2393,6 +2762,15 @@ struct smb_version_operations smb20_operations = { .dir_needs_close = smb2_dir_needs_close, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_XATTR + .query_all_EAs = smb2_query_eas, + .set_EA = smb2_set_ea, +#endif /* CIFS_XATTR */ +#ifdef CONFIG_CIFS_ACL + .get_acl = get_smb2_acl, + .get_acl_by_fid = get_smb2_acl_by_fid, + .set_acl = set_smb2_acl, +#endif /* CIFS_ACL */ }; struct smb_version_operations smb21_operations = { @@ -2458,6 +2836,7 @@ struct smb_version_operations smb21_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -2477,6 +2856,15 @@ struct smb_version_operations smb21_operations = { .enum_snapshots = smb3_enum_snapshots, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_XATTR + .query_all_EAs = smb2_query_eas, + .set_EA = smb2_set_ea, +#endif /* CIFS_XATTR */ +#ifdef CONFIG_CIFS_ACL + .get_acl = get_smb2_acl, + .get_acl_by_fid = get_smb2_acl_by_fid, + .set_acl = set_smb2_acl, +#endif /* CIFS_ACL */ }; struct smb_version_operations smb30_operations = { @@ -2543,6 +2931,7 @@ struct smb_version_operations smb30_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -2571,6 +2960,15 @@ struct smb_version_operations smb30_operations = { .receive_transform = smb3_receive_transform, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_XATTR + .query_all_EAs = smb2_query_eas, + .set_EA = smb2_set_ea, +#endif /* CIFS_XATTR */ +#ifdef CONFIG_CIFS_ACL + .get_acl = get_smb2_acl, + .get_acl_by_fid = get_smb2_acl_by_fid, + .set_acl = set_smb2_acl, +#endif /* CIFS_ACL */ }; #ifdef CONFIG_CIFS_SMB311 @@ -2638,6 +3036,7 @@ struct smb_version_operations smb311_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -2666,6 +3065,10 @@ struct smb_version_operations smb311_operations = { .receive_transform = smb3_receive_transform, .get_dfs_refer = smb2_get_dfs_refer, .select_sectype = smb2_select_sectype, +#ifdef CONFIG_CIFS_XATTR + .query_all_EAs = smb2_query_eas, + .set_EA = smb2_set_ea, +#endif /* CIFS_XATTR */ }; #endif /* CIFS_SMB311 */ @@ -2709,6 +3112,46 @@ struct smb_version_values smb21_values = { .create_lease_size = sizeof(struct create_lease), }; +struct smb_version_values smb3any_values = { + .version_string = SMB3ANY_VERSION_STRING, + .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .large_lock_type = 0, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, + .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, + .header_size = sizeof(struct smb2_hdr), + .max_header_size = MAX_SMB2_HDR_SIZE, + .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .lock_cmd = SMB2_LOCK, + .cap_unix = 0, + .cap_nt_find = SMB2_NT_FIND, + .cap_large_files = SMB2_LARGE_FILES, + .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED, + .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED, + .create_lease_size = sizeof(struct create_lease_v2), +}; + +struct smb_version_values smbdefault_values = { + .version_string = SMBDEFAULT_VERSION_STRING, + .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .large_lock_type = 0, + .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, + .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, + .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK, + .header_size = sizeof(struct smb2_hdr), + .max_header_size = MAX_SMB2_HDR_SIZE, + .read_rsp_size = sizeof(struct smb2_read_rsp) - 1, + .lock_cmd = SMB2_LOCK, + .cap_unix = 0, + .cap_nt_find = SMB2_NT_FIND, + .cap_large_files = SMB2_LARGE_FILES, + .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED, + .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED, + .create_lease_size = sizeof(struct create_lease_v2), +}; + struct smb_version_values smb30_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, @@ -2753,7 +3196,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index e4afdaae743f..6f0e6343c15e 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -238,6 +238,18 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) * the same SMB session */ mutex_lock(&tcon->ses->session_mutex); + + /* + * Recheck after acquire mutex. If another thread is negotiating + * and the server never sends an answer the socket will be closed + * and tcpStatus set to reconnect. + */ + if (server->tcpStatus == CifsNeedReconnect) { + rc = -EHOSTDOWN; + mutex_unlock(&tcon->ses->session_mutex); + goto out; + } + rc = cifs_negotiate_protocol(0, tcon->ses); if (!rc && tcon->ses->need_reconnect) rc = cifs_setup_session(0, tcon->ses, nls_codepage); @@ -427,7 +439,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req) build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt); req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT); req->NegotiateContextCount = cpu_to_le16(2); - inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + 2 + inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + sizeof(struct smb2_encryption_neg_context)); /* calculate hash */ } #else @@ -479,10 +491,25 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) req->hdr.sync_hdr.SessionId = 0; - req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id); - - req->DialectCount = cpu_to_le16(1); /* One vers= at a time for now */ - inc_rfc1001_len(req, 2); + if (strcmp(ses->server->vals->version_string, + SMB3ANY_VERSION_STRING) == 0) { + req->Dialects[0] = cpu_to_le16(SMB30_PROT_ID); + req->Dialects[1] = cpu_to_le16(SMB302_PROT_ID); + req->DialectCount = cpu_to_le16(2); + inc_rfc1001_len(req, 4); + } else if (strcmp(ses->server->vals->version_string, + SMBDEFAULT_VERSION_STRING) == 0) { + req->Dialects[0] = cpu_to_le16(SMB21_PROT_ID); + req->Dialects[1] = cpu_to_le16(SMB30_PROT_ID); + req->Dialects[2] = cpu_to_le16(SMB302_PROT_ID); + req->DialectCount = cpu_to_le16(3); + inc_rfc1001_len(req, 6); + } else { + /* otherwise send specific dialect */ + req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id); + req->DialectCount = cpu_to_le16(1); + inc_rfc1001_len(req, 2); + } /* only one of SMB2 signing flags may be set in SMB2 request */ if (ses->sign) @@ -514,13 +541,45 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) * No tcon so can't do * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]); */ - if (rc != 0) + if (rc == -EOPNOTSUPP) { + cifs_dbg(VFS, "Dialect not supported by server. Consider " + "specifying vers=1.0 or vers=2.0 on mount for accessing" + " older servers\n"); goto neg_exit; + } else if (rc != 0) + goto neg_exit; + + if (strcmp(ses->server->vals->version_string, + SMB3ANY_VERSION_STRING) == 0) { + if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) { + cifs_dbg(VFS, + "SMB2 dialect returned but not requested\n"); + return -EIO; + } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { + cifs_dbg(VFS, + "SMB2.1 dialect returned but not requested\n"); + return -EIO; + } + } else if (strcmp(ses->server->vals->version_string, + SMBDEFAULT_VERSION_STRING) == 0) { + if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) { + cifs_dbg(VFS, + "SMB2 dialect returned but not requested\n"); + return -EIO; + } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) { + /* ops set to 3.0 by default for default so update */ + ses->server->ops = &smb21_operations; + } + } else if (le16_to_cpu(rsp->DialectRevision) != + ses->server->vals->protocol_id) { + /* if requested single dialect ensure returned dialect matched */ + cifs_dbg(VFS, "Illegal 0x%x dialect returned: not requested\n", + le16_to_cpu(rsp->DialectRevision)); + return -EIO; + } cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode); - /* BB we may eventually want to match the negotiated vs. requested - dialect, even though we are only requesting one at a time */ if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) cifs_dbg(FYI, "negotiated smb2.0 dialect\n"); else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) @@ -541,6 +600,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) } server->dialect = le16_to_cpu(rsp->DialectRevision); + /* BB: add check that dialect was valid given dialect(s) we asked for */ + /* SMB2 only has an extended negflavor */ server->negflavor = CIFS_NEGFLAVOR_EXTENDED; /* set it to the maximum buffer size value we can send with 1 credit */ @@ -589,20 +650,28 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) struct validate_negotiate_info_req vneg_inbuf; struct validate_negotiate_info_rsp *pneg_rsp; u32 rsplen; + u32 inbuflen; /* max of 4 dialects */ cifs_dbg(FYI, "validate negotiate\n"); /* * validation ioctl must be signed, so no point sending this if we - * can not sign it. We could eventually change this to selectively + * can not sign it (ie are not known user). Even if signing is not + * required (enabled but not negotiated), in those cases we selectively * sign just this, the first and only signed request on a connection. - * This is good enough for now since a user who wants better security - * would also enable signing on the mount. Having validation of - * negotiate info for signed connections helps reduce attack vectors + * Having validation of negotiate info helps reduce attack vectors. */ - if (tcon->ses->server->sign == false) + if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) return 0; /* validation requires signing */ + if (tcon->ses->user_name == NULL) { + cifs_dbg(FYI, "Can't validate negotiate: null user mount\n"); + return 0; /* validation requires signing */ + } + + if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL) + cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n"); + vneg_inbuf.Capabilities = cpu_to_le32(tcon->ses->server->vals->req_capabilities); memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid, @@ -617,9 +686,30 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) else vneg_inbuf.SecurityMode = 0; - vneg_inbuf.DialectCount = cpu_to_le16(1); - vneg_inbuf.Dialects[0] = - cpu_to_le16(tcon->ses->server->vals->protocol_id); + + if (strcmp(tcon->ses->server->vals->version_string, + SMB3ANY_VERSION_STRING) == 0) { + vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID); + vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID); + vneg_inbuf.DialectCount = cpu_to_le16(2); + /* structure is big enough for 3 dialects, sending only 2 */ + inbuflen = sizeof(struct validate_negotiate_info_req) - 2; + } else if (strcmp(tcon->ses->server->vals->version_string, + SMBDEFAULT_VERSION_STRING) == 0) { + vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID); + vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID); + vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID); + vneg_inbuf.DialectCount = cpu_to_le16(3); + /* structure is big enough for 3 dialects */ + inbuflen = sizeof(struct validate_negotiate_info_req); + } else { + /* otherwise specific dialect was requested */ + vneg_inbuf.Dialects[0] = + cpu_to_le16(tcon->ses->server->vals->protocol_id); + vneg_inbuf.DialectCount = cpu_to_le16(1); + /* structure is big enough for 3 dialects, sending only 1 */ + inbuflen = sizeof(struct validate_negotiate_info_req) - 4; + } rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, @@ -1093,6 +1183,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, while (sess_data->func) sess_data->func(sess_data); + if ((ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) && (ses->sign)) + cifs_dbg(VFS, "signing requested but authenticated as guest\n"); rc = sess_data->result; out: kfree(sess_data); @@ -1167,15 +1259,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, int rc = 0; int resp_buftype; int unc_path_len; - struct TCP_Server_Info *server; __le16 *unc_path = NULL; int flags = 0; cifs_dbg(FYI, "TCON\n"); - if ((ses->server) && tree) - server = ses->server; - else + if (!(ses->server) || !tree) return -EIO; unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL); @@ -1294,15 +1383,12 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon) { struct smb2_tree_disconnect_req *req; /* response is trivial */ int rc = 0; - struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; int flags = 0; cifs_dbg(FYI, "Tree Disconnect\n"); - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !(ses->server)) return -EIO; if ((tcon->need_reconnect) || (tcon->ses->need_reconnect)) @@ -1623,7 +1709,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, struct cifs_tcon *tcon = oparms->tcon; struct cifs_ses *ses = tcon->ses; struct kvec iov[4]; - struct kvec rsp_iov; + struct kvec rsp_iov = {NULL, 0}; int resp_buftype; int uni_path_len; __le16 *copy_path = NULL; @@ -1752,7 +1838,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, if (rc != 0) { cifs_stats_fail_inc(tcon, SMB2_CREATE_HE); - if (err_buf) + if (err_buf && rsp) *err_buf = kmemdup(rsp, get_rfc1002_length(rsp) + 4, GFP_KERNEL); goto creat_exit; @@ -1794,7 +1880,6 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, struct smb2_ioctl_req *req; struct smb2_ioctl_rsp *rsp; struct smb2_sync_hdr *shdr; - struct TCP_Server_Info *server; struct cifs_ses *ses; struct kvec iov[2]; struct kvec rsp_iov; @@ -1817,9 +1902,7 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, else return -EIO; - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !(ses->server)) return -EIO; rc = small_smb2_init(SMB2_IOCTL, tcon, (void **) &req); @@ -1977,7 +2060,6 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, { struct smb2_close_req *req; struct smb2_close_rsp *rsp; - struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; struct kvec iov[1]; struct kvec rsp_iov; @@ -1987,9 +2069,7 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, cifs_dbg(FYI, "Close\n"); - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !(ses->server)) return -EIO; rc = small_smb2_init(SMB2_CLOSE, tcon, (void **) &req); @@ -2081,8 +2161,9 @@ validate_and_copy_buf(unsigned int offset, unsigned int buffer_length, static int query_info(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, u8 info_class, - size_t output_len, size_t min_len, void *data) + u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type, + u32 additional_info, size_t output_len, size_t min_len, void **data, + u32 *dlen) { struct smb2_query_info_req *req; struct smb2_query_info_rsp *rsp = NULL; @@ -2090,15 +2171,12 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, struct kvec rsp_iov; int rc = 0; int resp_buftype; - struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; int flags = 0; cifs_dbg(FYI, "Query Info\n"); - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !(ses->server)) return -EIO; rc = small_smb2_init(SMB2_QUERY_INFO, tcon, (void **) &req); @@ -2108,10 +2186,11 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, if (encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; - req->InfoType = SMB2_O_INFO_FILE; + req->InfoType = info_type; req->FileInfoClass = info_class; req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; + req->AdditionalInformation = cpu_to_le32(additional_info); /* 4 for rfc1002 length field and 1 for Buffer */ req->InputBufferOffset = cpu_to_le16(sizeof(struct smb2_query_info_req) - 1 - 4); @@ -2130,24 +2209,63 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon, goto qinf_exit; } + if (dlen) { + *dlen = le32_to_cpu(rsp->OutputBufferLength); + if (!*data) { + *data = kmalloc(*dlen, GFP_KERNEL); + if (!*data) { + cifs_dbg(VFS, + "Error %d allocating memory for acl\n", + rc); + *dlen = 0; + goto qinf_exit; + } + } + } + rc = validate_and_copy_buf(le16_to_cpu(rsp->OutputBufferOffset), le32_to_cpu(rsp->OutputBufferLength), - &rsp->hdr, min_len, data); + &rsp->hdr, min_len, *data); qinf_exit: free_rsp_buf(resp_buftype, rsp); return rc; } +int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, + struct smb2_file_full_ea_info *data) +{ + return query_info(xid, tcon, persistent_fid, volatile_fid, + FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0, + SMB2_MAX_EA_BUF, + sizeof(struct smb2_file_full_ea_info), + (void **)&data, + NULL); +} + +int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, struct smb2_file_all_info *data) +{ + return query_info(xid, tcon, persistent_fid, volatile_fid, + FILE_ALL_INFORMATION, SMB2_O_INFO_FILE, 0, + sizeof(struct smb2_file_all_info) + PATH_MAX * 2, + sizeof(struct smb2_file_all_info), (void **)&data, + NULL); +} + int -SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, +SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, - struct smb2_file_all_info *data) + void **data, u32 *plen) { + __u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO; + *plen = 0; + return query_info(xid, tcon, persistent_fid, volatile_fid, - FILE_ALL_INFORMATION, - sizeof(struct smb2_file_all_info) + PATH_MAX * 2, - sizeof(struct smb2_file_all_info), data); + 0, SMB2_O_INFO_SECURITY, additional_info, + SMB2_MAX_BUFFER_SIZE, + sizeof(struct smb2_file_all_info), data, plen); } int @@ -2155,9 +2273,10 @@ SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid) { return query_info(xid, tcon, persistent_fid, volatile_fid, - FILE_INTERNAL_INFORMATION, + FILE_INTERNAL_INFORMATION, SMB2_O_INFO_FILE, 0, sizeof(struct smb2_file_internal_info), - sizeof(struct smb2_file_internal_info), uniqueid); + sizeof(struct smb2_file_internal_info), + (void **)&uniqueid, NULL); } /* @@ -2281,7 +2400,6 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid) { struct smb2_flush_req *req; - struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; struct kvec iov[1]; struct kvec rsp_iov; @@ -2291,9 +2409,7 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, cifs_dbg(FYI, "Flush\n"); - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !(ses->server)) return -EIO; rc = small_smb2_init(SMB2_FLUSH, tcon, (void **) &req); @@ -2970,8 +3086,9 @@ qdir_exit: static int send_set_info(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, u32 pid, int info_class, - unsigned int num, void **data, unsigned int *size) + u64 persistent_fid, u64 volatile_fid, u32 pid, u8 info_class, + u8 info_type, u32 additional_info, unsigned int num, + void **data, unsigned int *size) { struct smb2_set_info_req *req; struct smb2_set_info_rsp *rsp = NULL; @@ -2980,13 +3097,10 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, int rc = 0; int resp_buftype; unsigned int i; - struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; int flags = 0; - if (ses && (ses->server)) - server = ses->server; - else + if (!ses || !(ses->server)) return -EIO; if (!num) @@ -3007,10 +3121,11 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon, req->hdr.sync_hdr.ProcessId = cpu_to_le32(pid); - req->InfoType = SMB2_O_INFO_FILE; + req->InfoType = info_type; req->FileInfoClass = info_class; req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; + req->AdditionalInformation = cpu_to_le32(additional_info); /* 4 for RFC1001 length and 1 for Buffer */ req->BufferOffset = @@ -3070,8 +3185,8 @@ SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon, size[1] = len + 2 /* null */; rc = send_set_info(xid, tcon, persistent_fid, volatile_fid, - current->tgid, FILE_RENAME_INFORMATION, 2, data, - size); + current->tgid, FILE_RENAME_INFORMATION, SMB2_O_INFO_FILE, + 0, 2, data, size); kfree(data); return rc; } @@ -3088,8 +3203,8 @@ SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, size = 1; /* sizeof __u8 */ return send_set_info(xid, tcon, persistent_fid, volatile_fid, - current->tgid, FILE_DISPOSITION_INFORMATION, 1, &data, - &size); + current->tgid, FILE_DISPOSITION_INFORMATION, SMB2_O_INFO_FILE, + 0, 1, &data, &size); } int @@ -3118,7 +3233,8 @@ SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon, size[1] = len + 2 /* null */; rc = send_set_info(xid, tcon, persistent_fid, volatile_fid, - current->tgid, FILE_LINK_INFORMATION, 2, data, size); + current->tgid, FILE_LINK_INFORMATION, SMB2_O_INFO_FILE, + 0, 2, data, size); kfree(data); return rc; } @@ -3138,10 +3254,12 @@ SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, if (is_falloc) return send_set_info(xid, tcon, persistent_fid, volatile_fid, - pid, FILE_ALLOCATION_INFORMATION, 1, &data, &size); + pid, FILE_ALLOCATION_INFORMATION, SMB2_O_INFO_FILE, + 0, 1, &data, &size); else return send_set_info(xid, tcon, persistent_fid, volatile_fid, - pid, FILE_END_OF_FILE_INFORMATION, 1, &data, &size); + pid, FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE, + 0, 1, &data, &size); } int @@ -3151,8 +3269,28 @@ SMB2_set_info(const unsigned int xid, struct cifs_tcon *tcon, unsigned int size; size = sizeof(FILE_BASIC_INFO); return send_set_info(xid, tcon, persistent_fid, volatile_fid, - current->tgid, FILE_BASIC_INFORMATION, 1, - (void **)&buf, &size); + current->tgid, FILE_BASIC_INFORMATION, SMB2_O_INFO_FILE, + 0, 1, (void **)&buf, &size); +} + +int +SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, + struct cifs_ntsd *pnntsd, int pacllen, int aclflag) +{ + return send_set_info(xid, tcon, persistent_fid, volatile_fid, + current->tgid, 0, SMB2_O_INFO_SECURITY, aclflag, + 1, (void **)&pnntsd, &pacllen); +} + +int +SMB2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, + struct smb2_file_full_ea_info *buf, int len) +{ + return send_set_info(xid, tcon, persistent_fid, volatile_fid, + current->tgid, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, + 0, 1, (void **)&buf, &len); } int @@ -3195,8 +3333,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf, kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) * le32_to_cpu(pfs_inf->SectorsPerAllocationUnit); kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits); - kst->f_bfree = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits); - kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits); + kst->f_bfree = kst->f_bavail = + le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits); return; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 18700fd25a0b..6c9653a130c8 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* BB FIXME - analyze following length BB */ -#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ +/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ +#define MAX_SMB2_HDR_SIZE 0x00b0 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) @@ -716,7 +716,7 @@ struct validate_negotiate_info_req { __u8 Guid[SMB2_CLIENT_GUID_SIZE]; __le16 SecurityMode; __le16 DialectCount; - __le16 Dialects[1]; /* dialect (someday maybe list) client asked for */ + __le16 Dialects[3]; /* BB expand this if autonegotiate > 3 dialects */ } __packed; struct validate_negotiate_info_rsp { @@ -1178,6 +1178,16 @@ struct smb2_file_link_info { /* encoding of request for level 11 */ char FileName[0]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ +#define SMB2_MAX_EA_BUF 2048 + +struct smb2_file_full_ea_info { /* encoding of response for level 15 */ + __le32 next_entry_offset; + __u8 flags; + __u8 ea_name_length; + __le16 ea_value_length; + char ea_data[0]; /* \0 terminated name plus value */ +} __packed; /* level 15 Set */ + /* * This level 18, although with struct with same name is different from cifs * level 0x107. Level 0x107 has an extra u64 between AccessFlags and diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 6853454fc871..003217099ef3 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -132,9 +132,15 @@ extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); +extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_file_id, u64 volatile_file_id, + struct smb2_file_full_ea_info *data); extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct smb2_file_all_info *data); +extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_file_id, u64 volatile_file_id, + void **data, unsigned int *plen); extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid); @@ -163,6 +169,12 @@ extern int SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, extern int SMB2_set_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, FILE_BASIC_INFO *buf); +extern int SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, + struct cifs_ntsd *pnntsd, int pacllen, int aclflag); +extern int SMB2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, + u64 persistent_fid, u64 volatile_fid, + struct smb2_file_full_ea_info *buf, int len); extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid); extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index c69ec96e92ac..67367cf1f8cd 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -335,9 +335,31 @@ generate_smb3signingkey(struct cifs_ses *ses, if (rc) return rc; - return generate_key(ses, ptriplet->decryption.label, - ptriplet->decryption.context, - ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE); + rc = generate_key(ses, ptriplet->decryption.label, + ptriplet->decryption.context, + ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE); + + if (rc) + return rc; + +#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS + cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__); + /* + * The session id is opaque in terms of endianness, so we can't + * print it as a long long. we dump it as we got it on the wire + */ + cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid), + &ses->Suid); + cifs_dbg(VFS, "Session Key %*ph\n", + SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); + cifs_dbg(VFS, "Signing Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); + cifs_dbg(VFS, "ServerIn Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey); + cifs_dbg(VFS, "ServerOut Key %*ph\n", + SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey); +#endif + return rc; } int diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 47a125ece11e..7efbab013957 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -536,11 +536,14 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst, list_add_tail(&mid->qhead, &server->pending_mid_q); spin_unlock(&GlobalMid_Lock); - + /* + * Need to store the time in mid before calling I/O. For call_async, + * I/O response may come back and free the mid entry on another thread. + */ + cifs_save_when_sent(mid); cifs_in_send_inc(server); rc = smb_send_rqst(server, rqst, flags); cifs_in_send_dec(server); - cifs_save_when_sent(mid); if (rc < 0) { server->sequence_number -= 2; diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index de50e749ff05..52f975d848a0 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -84,7 +84,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler, if (pTcon->ses->server->ops->set_EA) rc = pTcon->ses->server->ops->set_EA(xid, pTcon, full_path, name, value, (__u16)size, - cifs_sb->local_nls, cifs_remap(cifs_sb)); + cifs_sb->local_nls, cifs_sb); break; case XATTR_CIFS_ACL: { diff --git a/fs/coda/dir.c b/fs/coda/dir.c index c0474ac6cbf2..274ab5586dd0 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -368,9 +368,10 @@ static int coda_venus_readdir(struct file *coda_file, struct dir_context *ctx) goto out; while (1) { + loff_t pos = ctx->pos - 2; + /* read entries from the directory file */ - ret = kernel_read(host_file, ctx->pos - 2, (char *)vdir, - sizeof(*vdir)); + ret = kernel_read(host_file, vdir, sizeof(*vdir), &pos); if (ret < 0) { pr_err("%s: read dir %s failed %d\n", __func__, coda_f2s(&cii->c_fid), ret); diff --git a/fs/coda/file.c b/fs/coda/file.c index 9d956cd6d46f..363402fcb3ed 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -34,7 +34,7 @@ coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to) BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); - return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos); + return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos, 0); } static ssize_t @@ -51,7 +51,7 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to) host_file = cfi->cfi_container; file_start_write(host_file); inode_lock(coda_inode); - ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos); + ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0); coda_inode->i_size = file_inode(host_file)->i_size; coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9; coda_inode->i_mtime = coda_inode->i_ctime = current_time(coda_inode); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 6116d5275a3e..d27b326d96f4 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -739,23 +739,22 @@ static int do_i2c_smbus_ioctl(struct file *file, unsigned int cmd, struct i2c_smbus_ioctl_data32 __user *udata) { struct i2c_smbus_ioctl_data __user *tdata; - compat_caddr_t datap; + union { + /* beginnings of those have identical layouts */ + struct i2c_smbus_ioctl_data32 data32; + struct i2c_smbus_ioctl_data data; + } v; tdata = compat_alloc_user_space(sizeof(*tdata)); if (tdata == NULL) return -ENOMEM; - if (!access_ok(VERIFY_WRITE, tdata, sizeof(*tdata))) - return -EFAULT; - if (!access_ok(VERIFY_READ, udata, sizeof(*udata))) + memset(&v, 0, sizeof(v)); + if (copy_from_user(&v.data32, udata, sizeof(v.data32))) return -EFAULT; + v.data.data = compat_ptr(v.data32.data); - if (__copy_in_user(&tdata->read_write, &udata->read_write, 2 * sizeof(u8))) - return -EFAULT; - if (__copy_in_user(&tdata->size, &udata->size, 2 * sizeof(u32))) - return -EFAULT; - if (__get_user(datap, &udata->data) || - __put_user(compat_ptr(datap), &tdata->data)) + if (copy_to_user(tdata, &v.data, sizeof(v.data))) return -EFAULT; return do_ioctl(file, cmd, (unsigned long)tdata); @@ -866,8 +865,6 @@ COMPATIBLE_IOCTL(TIOCGDEV) COMPATIBLE_IOCTL(TIOCCBRK) COMPATIBLE_IOCTL(TIOCGSID) COMPATIBLE_IOCTL(TIOCGICOUNT) -COMPATIBLE_IOCTL(TIOCGPKT) -COMPATIBLE_IOCTL(TIOCGPTLCK) COMPATIBLE_IOCTL(TIOCGEXCL) /* Little t */ COMPATIBLE_IOCTL(TIOCGETD) @@ -883,16 +880,12 @@ COMPATIBLE_IOCTL(TIOCMGET) COMPATIBLE_IOCTL(TIOCMBIC) COMPATIBLE_IOCTL(TIOCMBIS) COMPATIBLE_IOCTL(TIOCMSET) -COMPATIBLE_IOCTL(TIOCPKT) COMPATIBLE_IOCTL(TIOCNOTTY) COMPATIBLE_IOCTL(TIOCSTI) COMPATIBLE_IOCTL(TIOCOUTQ) COMPATIBLE_IOCTL(TIOCSPGRP) COMPATIBLE_IOCTL(TIOCGPGRP) -COMPATIBLE_IOCTL(TIOCGPTN) -COMPATIBLE_IOCTL(TIOCSPTLCK) COMPATIBLE_IOCTL(TIOCSERGETLSR) -COMPATIBLE_IOCTL(TIOCSIG) #ifdef TIOCSRS485 COMPATIBLE_IOCTL(TIOCSRS485) #endif @@ -1338,8 +1331,6 @@ COMPATIBLE_IOCTL(DMX_SET_FILTER) COMPATIBLE_IOCTL(DMX_SET_PES_FILTER) COMPATIBLE_IOCTL(DMX_SET_BUFFER_SIZE) COMPATIBLE_IOCTL(DMX_GET_PES_PIDS) -COMPATIBLE_IOCTL(DMX_GET_CAPS) -COMPATIBLE_IOCTL(DMX_SET_SOURCE) COMPATIBLE_IOCTL(DMX_GET_STC) COMPATIBLE_IOCTL(FE_GET_INFO) COMPATIBLE_IOCTL(FE_DISEQC_RESET_OVERLOAD) diff --git a/fs/coredump.c b/fs/coredump.c index 592683711c64..0eec03696707 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -161,7 +161,7 @@ static int cn_print_exe_file(struct core_name *cn) if (!exe_file) return cn_esc_printf(cn, "%s (path unknown)", current->comm); - pathbuf = kmalloc(PATH_MAX, GFP_TEMPORARY); + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf) { ret = -ENOMEM; goto put_exe_file; diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig index 08b46e6e3995..02b7d91c9231 100644 --- a/fs/crypto/Kconfig +++ b/fs/crypto/Kconfig @@ -7,6 +7,7 @@ config FS_ENCRYPTION select CRYPTO_XTS select CRYPTO_CTS select CRYPTO_CTR + select CRYPTO_SHA256 select KEYS help Enable encryption of files and directories. This diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index a409a84f1bca..483784d5eb73 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -115,7 +115,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, err = -ENOMEM; goto errout; } - bio->bi_bdev = inode->i_sb->s_bdev; + bio_set_dev(bio, inode->i_sb->s_bdev); bio->bi_iter.bi_sector = pblk << (inode->i_sb->s_blocksize_bits - 9); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -129,7 +129,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, goto errout; } err = submit_bio_wait(bio); - if ((err == 0) && bio->bi_error) + if (err == 0 && bio->bi_status) err = -EIO; bio_put(bio); if (err) diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 6d6eca394d4d..c7835df7e7b8 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -26,6 +26,7 @@ #include <linux/ratelimit.h> #include <linux/dcache.h> #include <linux/namei.h> +#include <crypto/aes.h> #include "fscrypt_private.h" static unsigned int num_prealloc_crypto_pages = 32; @@ -147,8 +148,8 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, { struct { __le64 index; - u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)]; - } xts_tweak; + u8 padding[FS_IV_SIZE - sizeof(__le64)]; + } iv; struct skcipher_request *req = NULL; DECLARE_FS_COMPLETION_RESULT(ecr); struct scatterlist dst, src; @@ -158,6 +159,16 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, BUG_ON(len == 0); + BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE); + BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE); + iv.index = cpu_to_le64(lblk_num); + memset(iv.padding, 0, sizeof(iv.padding)); + + if (ci->ci_essiv_tfm != NULL) { + crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv, + (u8 *)&iv); + } + req = skcipher_request_alloc(tfm, gfp_flags); if (!req) { printk_ratelimited(KERN_ERR @@ -170,15 +181,11 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, page_crypt_complete, &ecr); - BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE); - xts_tweak.index = cpu_to_le64(lblk_num); - memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding)); - sg_init_table(&dst, 1); sg_set_page(&dst, dest_page, len, offs); sg_init_table(&src, 1); sg_set_page(&src, src_page, len, offs); - skcipher_request_set_crypt(req, &src, &dst, len, &xts_tweak); + skcipher_request_set_crypt(req, &src, &dst, len, &iv); if (rw == FS_DECRYPT) res = crypto_skcipher_decrypt(req); else @@ -477,6 +484,8 @@ static void __exit fscrypt_exit(void) destroy_workqueue(fscrypt_read_workqueue); kmem_cache_destroy(fscrypt_ctx_cachep); kmem_cache_destroy(fscrypt_info_cachep); + + fscrypt_essiv_cleanup(); } module_exit(fscrypt_exit); diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index d1bb02b1ee58..ad9f814fdead 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -453,12 +453,3 @@ errout: return ret; } EXPORT_SYMBOL(fscrypt_setup_filename); - -void fscrypt_free_filename(struct fscrypt_name *fname) -{ - kfree(fname->crypto_buf.name); - fname->crypto_buf.name = NULL; - fname->usr_fname = NULL; - fname->disk_name.name = NULL; -} -EXPORT_SYMBOL(fscrypt_free_filename); diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 1e1f8a361b75..a1d5021c31ef 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -12,10 +12,13 @@ #define _FSCRYPT_PRIVATE_H #include <linux/fscrypt_supp.h> +#include <crypto/hash.h> /* Encryption parameters */ -#define FS_XTS_TWEAK_SIZE 16 +#define FS_IV_SIZE 16 #define FS_AES_128_ECB_KEY_SIZE 16 +#define FS_AES_128_CBC_KEY_SIZE 16 +#define FS_AES_128_CTS_KEY_SIZE 16 #define FS_AES_256_GCM_KEY_SIZE 32 #define FS_AES_256_CBC_KEY_SIZE 32 #define FS_AES_256_CTS_KEY_SIZE 32 @@ -54,6 +57,7 @@ struct fscrypt_info { u8 ci_filename_mode; u8 ci_flags; struct crypto_skcipher *ci_ctfm; + struct crypto_cipher *ci_essiv_tfm; u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; }; @@ -87,4 +91,7 @@ extern int fscrypt_do_page_crypto(const struct inode *inode, extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags); +/* keyinfo.c */ +extern void __exit fscrypt_essiv_cleanup(void); + #endif /* _FSCRYPT_PRIVATE_H */ diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 179e578b875b..8e704d12a1cf 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -10,8 +10,13 @@ #include <keys/user-type.h> #include <linux/scatterlist.h> +#include <linux/ratelimit.h> +#include <crypto/aes.h> +#include <crypto/sha.h> #include "fscrypt_private.h" +static struct crypto_shash *essiv_hash_tfm; + static void derive_crypt_complete(struct crypto_async_request *req, int rc) { struct fscrypt_completion_result *ecr = req->data; @@ -27,13 +32,13 @@ static void derive_crypt_complete(struct crypto_async_request *req, int rc) * derive_key_aes() - Derive a key using AES-128-ECB * @deriving_key: Encryption key used for derivation. * @source_key: Source key to which to apply derivation. - * @derived_key: Derived key. + * @derived_raw_key: Derived raw key. * * Return: Zero on success; non-zero otherwise. */ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], - u8 source_key[FS_AES_256_XTS_KEY_SIZE], - u8 derived_key[FS_AES_256_XTS_KEY_SIZE]) + const struct fscrypt_key *source_key, + u8 derived_raw_key[FS_MAX_KEY_SIZE]) { int res = 0; struct skcipher_request *req = NULL; @@ -60,10 +65,10 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE], if (res < 0) goto out; - sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE); - sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, - FS_AES_256_XTS_KEY_SIZE, NULL); + sg_init_one(&src_sg, source_key->raw, source_key->size); + sg_init_one(&dst_sg, derived_raw_key, source_key->size); + skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size, + NULL); res = crypto_skcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { wait_for_completion(&ecr.completion); @@ -77,7 +82,7 @@ out: static int validate_user_key(struct fscrypt_info *crypt_info, struct fscrypt_context *ctx, u8 *raw_key, - const char *prefix) + const char *prefix, int min_keysize) { char *description; struct key *keyring_key; @@ -104,6 +109,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info, goto out; } ukp = user_key_payload_locked(keyring_key); + if (!ukp) { + /* key was revoked before we acquired its semaphore */ + res = -EKEYREVOKED; + goto out; + } if (ukp->datalen != sizeof(struct fscrypt_key)) { res = -EINVAL; goto out; @@ -111,50 +121,60 @@ static int validate_user_key(struct fscrypt_info *crypt_info, master_key = (struct fscrypt_key *)ukp->data; BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE); - if (master_key->size != FS_AES_256_XTS_KEY_SIZE) { + if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE + || master_key->size % AES_BLOCK_SIZE != 0) { printk_once(KERN_WARNING "%s: key size incorrect: %d\n", __func__, master_key->size); res = -ENOKEY; goto out; } - res = derive_key_aes(ctx->nonce, master_key->raw, raw_key); + res = derive_key_aes(ctx->nonce, master_key, raw_key); out: up_read(&keyring_key->sem); key_put(keyring_key); return res; } +static const struct { + const char *cipher_str; + int keysize; +} available_modes[] = { + [FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)", + FS_AES_256_XTS_KEY_SIZE }, + [FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))", + FS_AES_256_CTS_KEY_SIZE }, + [FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)", + FS_AES_128_CBC_KEY_SIZE }, + [FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))", + FS_AES_128_CTS_KEY_SIZE }, +}; + static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode, const char **cipher_str_ret, int *keysize_ret) { - if (S_ISREG(inode->i_mode)) { - if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) { - *cipher_str_ret = "xts(aes)"; - *keysize_ret = FS_AES_256_XTS_KEY_SIZE; - return 0; - } - pr_warn_once("fscrypto: unsupported contents encryption mode " - "%d for inode %lu\n", - ci->ci_data_mode, inode->i_ino); - return -ENOKEY; + u32 mode; + + if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) { + pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n", + inode->i_ino, + ci->ci_data_mode, ci->ci_filename_mode); + return -EINVAL; } - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) { - if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) { - *cipher_str_ret = "cts(cbc(aes))"; - *keysize_ret = FS_AES_256_CTS_KEY_SIZE; - return 0; - } - pr_warn_once("fscrypto: unsupported filenames encryption mode " - "%d for inode %lu\n", - ci->ci_filename_mode, inode->i_ino); - return -ENOKEY; + if (S_ISREG(inode->i_mode)) { + mode = ci->ci_data_mode; + } else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) { + mode = ci->ci_filename_mode; + } else { + WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n", + inode->i_ino, (inode->i_mode & S_IFMT)); + return -EINVAL; } - pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n", - (inode->i_mode & S_IFMT), inode->i_ino); - return -ENOKEY; + *cipher_str_ret = available_modes[mode].cipher_str; + *keysize_ret = available_modes[mode].keysize; + return 0; } static void put_crypt_info(struct fscrypt_info *ci) @@ -163,9 +183,76 @@ static void put_crypt_info(struct fscrypt_info *ci) return; crypto_free_skcipher(ci->ci_ctfm); + crypto_free_cipher(ci->ci_essiv_tfm); kmem_cache_free(fscrypt_info_cachep, ci); } +static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt) +{ + struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm); + + /* init hash transform on demand */ + if (unlikely(!tfm)) { + struct crypto_shash *prev_tfm; + + tfm = crypto_alloc_shash("sha256", 0, 0); + if (IS_ERR(tfm)) { + pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n", + PTR_ERR(tfm)); + return PTR_ERR(tfm); + } + prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm); + if (prev_tfm) { + crypto_free_shash(tfm); + tfm = prev_tfm; + } + } + + { + SHASH_DESC_ON_STACK(desc, tfm); + desc->tfm = tfm; + desc->flags = 0; + + return crypto_shash_digest(desc, key, keysize, salt); + } +} + +static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key, + int keysize) +{ + int err; + struct crypto_cipher *essiv_tfm; + u8 salt[SHA256_DIGEST_SIZE]; + + essiv_tfm = crypto_alloc_cipher("aes", 0, 0); + if (IS_ERR(essiv_tfm)) + return PTR_ERR(essiv_tfm); + + ci->ci_essiv_tfm = essiv_tfm; + + err = derive_essiv_salt(raw_key, keysize, salt); + if (err) + goto out; + + /* + * Using SHA256 to derive the salt/key will result in AES-256 being + * used for IV generation. File contents encryption will still use the + * configured keysize (AES-128) nevertheless. + */ + err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt)); + if (err) + goto out; + +out: + memzero_explicit(salt, sizeof(salt)); + return err; +} + +void __exit fscrypt_essiv_cleanup(void) +{ + crypto_free_shash(essiv_hash_tfm); +} + int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; @@ -212,6 +299,7 @@ int fscrypt_get_encryption_info(struct inode *inode) crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; crypt_info->ci_ctfm = NULL; + crypt_info->ci_essiv_tfm = NULL; memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, sizeof(crypt_info->ci_master_key)); @@ -228,10 +316,12 @@ int fscrypt_get_encryption_info(struct inode *inode) if (!raw_key) goto out; - res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX); + res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX, + keysize); if (res && inode->i_sb->s_cop->key_prefix) { int res2 = validate_user_key(crypt_info, &ctx, raw_key, - inode->i_sb->s_cop->key_prefix); + inode->i_sb->s_cop->key_prefix, + keysize); if (res2) { if (res2 == -ENOKEY) res = -ENOKEY; @@ -243,18 +333,30 @@ int fscrypt_get_encryption_info(struct inode *inode) ctfm = crypto_alloc_skcipher(cipher_str, 0, 0); if (!ctfm || IS_ERR(ctfm)) { res = ctfm ? PTR_ERR(ctfm) : -ENOMEM; - printk(KERN_DEBUG - "%s: error %d (inode %u) allocating crypto tfm\n", - __func__, res, (unsigned) inode->i_ino); + pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n", + __func__, res, inode->i_ino); goto out; } crypt_info->ci_ctfm = ctfm; crypto_skcipher_clear_flags(ctfm, ~0); crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY); + /* + * if the provided key is longer than keysize, we use the first + * keysize bytes of the derived key only + */ res = crypto_skcipher_setkey(ctfm, raw_key, keysize); if (res) goto out; + if (S_ISREG(inode->i_mode) && + crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) { + res = init_essiv_generator(crypt_info, raw_key, keysize); + if (res) { + pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n", + __func__, res, inode->i_ino); + goto out; + } + } if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) crypt_info = NULL; out: diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 210976e7a269..ce07a86200f3 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -38,12 +38,8 @@ static int create_encryption_context_from_policy(struct inode *inode, memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, FS_KEY_DESCRIPTOR_SIZE); - if (!fscrypt_valid_contents_enc_mode( - policy->contents_encryption_mode)) - return -EINVAL; - - if (!fscrypt_valid_filenames_enc_mode( - policy->filenames_encryption_mode)) + if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode, + policy->filenames_encryption_mode)) return -EINVAL; if (policy->flags & ~FS_POLICY_FLAGS_VALID) @@ -260,6 +256,7 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child, memcpy(ctx.master_key_descriptor, ci->ci_master_key, FS_KEY_DESCRIPTOR_SIZE); get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE); + BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE); res = parent->i_sb->s_cop->set_context(child, &ctx, sizeof(ctx), fs_data); if (res) @@ -25,7 +25,6 @@ #include <linux/mm.h> #include <linux/mutex.h> #include <linux/pagevec.h> -#include <linux/pmem.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/uio.h> @@ -43,6 +42,9 @@ #define DAX_WAIT_TABLE_BITS 12 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS) +/* The 'colour' (ie low bits) within a PMD of a page offset. */ +#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) + static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES]; static int __init init_dax_wait_table(void) @@ -55,6 +57,40 @@ static int __init init_dax_wait_table(void) } fs_initcall(init_dax_wait_table); +/* + * We use lowest available bit in exceptional entry for locking, one bit for + * the entry size (PMD) and two more to tell us if the entry is a zero page or + * an empty entry that is just used for locking. In total four special bits. + * + * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE + * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem + * block allocation. + */ +#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) +#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) +#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) +#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) +#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) + +static unsigned long dax_radix_sector(void *entry) +{ + return (unsigned long)entry >> RADIX_DAX_SHIFT; +} + +static void *dax_radix_locked_entry(sector_t sector, unsigned long flags) +{ + return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | + ((unsigned long)sector << RADIX_DAX_SHIFT) | + RADIX_DAX_ENTRY_LOCK); +} + +static unsigned int dax_radix_order(void *entry) +{ + if ((unsigned long)entry & RADIX_DAX_PMD) + return PMD_SHIFT - PAGE_SHIFT; + return 0; +} + static int dax_is_pmd_entry(void *entry) { return (unsigned long)entry & RADIX_DAX_PMD; @@ -67,7 +103,7 @@ static int dax_is_pte_entry(void *entry) static int dax_is_zero_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_HZP; + return (unsigned long)entry & RADIX_DAX_ZERO_PAGE; } static int dax_is_empty_entry(void *entry) @@ -84,7 +120,7 @@ struct exceptional_entry_key { }; struct wait_exceptional_entry_queue { - wait_queue_t wait; + wait_queue_entry_t wait; struct exceptional_entry_key key; }; @@ -99,7 +135,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, * the range covered by the PMD map to the same bit lock. */ if (dax_is_pmd_entry(entry)) - index &= ~((1UL << (PMD_SHIFT - PAGE_SHIFT)) - 1); + index &= ~PG_PMD_COLOUR; key->mapping = mapping; key->entry_start = index; @@ -108,7 +144,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, return wait_table + hash; } -static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode, +static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mode, int sync, void *keyp) { struct exceptional_entry_key *key = keyp; @@ -122,6 +158,31 @@ static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode, } /* + * We do not necessarily hold the mapping->tree_lock when we call this + * function so it is possible that 'entry' is no longer a valid item in the + * radix tree. This is okay because all we really need to do is to find the + * correct waitqueue where tasks might be waiting for that old 'entry' and + * wake them. + */ +static void dax_wake_mapping_entry_waiter(struct address_space *mapping, + pgoff_t index, void *entry, bool wake_all) +{ + struct exceptional_entry_key key; + wait_queue_head_t *wq; + + wq = dax_entry_waitqueue(mapping, index, entry, &key); + + /* + * Checking for locked entry and prepare_to_wait_exclusive() happens + * under mapping->tree_lock, ditto for entry handling in our callers. + * So at this point all tasks that could have seen our entry locked + * must be in the waitqueue and the following check will see them. + */ + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); +} + +/* * Check whether the given slot is locked. The function must be called with * mapping->tree_lock held */ @@ -182,7 +243,8 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping, for (;;) { entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); - if (!entry || !radix_tree_exceptional_entry(entry) || + if (!entry || + WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) || !slot_locked(mapping, slot)) { if (slotp) *slotp = slot; @@ -217,14 +279,9 @@ static void dax_unlock_mapping_entry(struct address_space *mapping, } static void put_locked_mapping_entry(struct address_space *mapping, - pgoff_t index, void *entry) + pgoff_t index) { - if (!radix_tree_exceptional_entry(entry)) { - unlock_page(entry); - put_page(entry); - } else { - dax_unlock_mapping_entry(mapping, index); - } + dax_unlock_mapping_entry(mapping, index); } /* @@ -234,7 +291,7 @@ static void put_locked_mapping_entry(struct address_space *mapping, static void put_unlocked_mapping_entry(struct address_space *mapping, pgoff_t index, void *entry) { - if (!radix_tree_exceptional_entry(entry)) + if (!entry) return; /* We have to wake up next waiter for the radix tree entry lock */ @@ -242,15 +299,15 @@ static void put_unlocked_mapping_entry(struct address_space *mapping, } /* - * Find radix tree entry at given index. If it points to a page, return with - * the page locked. If it points to the exceptional entry, return with the - * radix tree entry locked. If the radix tree doesn't contain given index, - * create empty exceptional entry for the index and return with it locked. + * Find radix tree entry at given index. If it points to an exceptional entry, + * return it with the radix tree entry locked. If the radix tree doesn't + * contain given index, create an empty exceptional entry for the index and + * return with it locked. * * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will * either return that locked entry or will return an error. This error will - * happen if there are any 4k entries (either zero pages or DAX entries) - * within the 2MiB range that we are requesting. + * happen if there are any 4k entries within the 2MiB range that we are + * requesting. * * We always favor 4k entries over 2MiB entries. There isn't a flow where we * evict 4k entries in order to 'upgrade' them to a 2MiB entry. A 2MiB @@ -277,18 +334,21 @@ restart: spin_lock_irq(&mapping->tree_lock); entry = get_unlocked_mapping_entry(mapping, index, &slot); + if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) { + entry = ERR_PTR(-EIO); + goto out_unlock; + } + if (entry) { if (size_flag & RADIX_DAX_PMD) { - if (!radix_tree_exceptional_entry(entry) || - dax_is_pte_entry(entry)) { + if (dax_is_pte_entry(entry)) { put_unlocked_mapping_entry(mapping, index, entry); entry = ERR_PTR(-EEXIST); goto out_unlock; } } else { /* trying to grab a PTE entry */ - if (radix_tree_exceptional_entry(entry) && - dax_is_pmd_entry(entry) && + if (dax_is_pmd_entry(entry) && (dax_is_zero_entry(entry) || dax_is_empty_entry(entry))) { pmd_downgrade = true; @@ -322,7 +382,7 @@ restart: mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM); if (err) { if (pmd_downgrade) - put_locked_mapping_entry(mapping, index, entry); + put_locked_mapping_entry(mapping, index); return ERR_PTR(err); } spin_lock_irq(&mapping->tree_lock); @@ -372,52 +432,12 @@ restart: spin_unlock_irq(&mapping->tree_lock); return entry; } - /* Normal page in radix tree? */ - if (!radix_tree_exceptional_entry(entry)) { - struct page *page = entry; - - get_page(page); - spin_unlock_irq(&mapping->tree_lock); - lock_page(page); - /* Page got truncated? Retry... */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); - goto restart; - } - return page; - } entry = lock_slot(mapping, slot); out_unlock: spin_unlock_irq(&mapping->tree_lock); return entry; } -/* - * We do not necessarily hold the mapping->tree_lock when we call this - * function so it is possible that 'entry' is no longer a valid item in the - * radix tree. This is okay because all we really need to do is to find the - * correct waitqueue where tasks might be waiting for that old 'entry' and - * wake them. - */ -void dax_wake_mapping_entry_waiter(struct address_space *mapping, - pgoff_t index, void *entry, bool wake_all) -{ - struct exceptional_entry_key key; - wait_queue_head_t *wq; - - wq = dax_entry_waitqueue(mapping, index, entry, &key); - - /* - * Checking for locked entry and prepare_to_wait_exclusive() happens - * under mapping->tree_lock, ditto for entry handling in our callers. - * So at this point all tasks that could have seen our entry locked - * must be in the waitqueue and the following check will see them. - */ - if (waitqueue_active(wq)) - __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); -} - static int __dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index, bool trunc) { @@ -427,7 +447,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping, spin_lock_irq(&mapping->tree_lock); entry = get_unlocked_mapping_entry(mapping, index, NULL); - if (!entry || !radix_tree_exceptional_entry(entry)) + if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry))) goto out; if (!trunc && (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) || @@ -469,50 +489,6 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_mapping_entry(mapping, index, false); } -/* - * The user has performed a load from a hole in the file. Allocating - * a new page in the file would cause excessive storage usage for - * workloads with sparse files. We allocate a page cache page instead. - * We'll kick it out of the page cache if it's ever written to, - * otherwise it will simply fall out of the page cache under memory - * pressure without ever having been dirtied. - */ -static int dax_load_hole(struct address_space *mapping, void **entry, - struct vm_fault *vmf) -{ - struct inode *inode = mapping->host; - struct page *page; - int ret; - - /* Hole page already exists? Return it... */ - if (!radix_tree_exceptional_entry(*entry)) { - page = *entry; - goto finish_fault; - } - - /* This will replace locked radix tree entry with a hole page */ - page = find_or_create_page(mapping, vmf->pgoff, - vmf->gfp_mask | __GFP_ZERO); - if (!page) { - ret = VM_FAULT_OOM; - goto out; - } - -finish_fault: - vmf->page = page; - ret = finish_fault(vmf); - vmf->page = NULL; - *entry = page; - if (!ret) { - /* Grab reference for PTE that is now referencing the page */ - get_page(page); - ret = VM_FAULT_NOPAGE; - } -out: - trace_dax_load_hole(inode, vmf, ret); - return ret; -} - static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev, sector_t sector, size_t size, struct page *to, unsigned long vaddr) @@ -553,47 +529,27 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, unsigned long flags) { struct radix_tree_root *page_tree = &mapping->page_tree; - int error = 0; - bool hole_fill = false; void *new_entry; pgoff_t index = vmf->pgoff; if (vmf->flags & FAULT_FLAG_WRITE) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - /* Replacing hole page with block mapping? */ - if (!radix_tree_exceptional_entry(entry)) { - hole_fill = true; - /* - * Unmap the page now before we remove it from page cache below. - * The page is locked so it cannot be faulted in again. - */ - unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT, - PAGE_SIZE, 0); - error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM); - if (error) - return ERR_PTR(error); - } else if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_HZP)) { - /* replacing huge zero page with PMD block mapping */ - unmap_mapping_range(mapping, - (vmf->pgoff << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0); + if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) { + /* we are replacing a zero page with block mapping */ + if (dax_is_pmd_entry(entry)) + unmap_mapping_range(mapping, + (vmf->pgoff << PAGE_SHIFT) & PMD_MASK, + PMD_SIZE, 0); + else /* pte entry */ + unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT, + PAGE_SIZE, 0); } spin_lock_irq(&mapping->tree_lock); new_entry = dax_radix_locked_entry(sector, flags); - if (hole_fill) { - __delete_from_page_cache(entry, NULL); - /* Drop pagecache reference */ - put_page(entry); - error = __radix_tree_insert(page_tree, index, - dax_radix_order(new_entry), new_entry); - if (error) { - new_entry = ERR_PTR(error); - goto unlock; - } - mapping->nrexceptional++; - } else if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { /* * Only swap our new entry into the radix tree if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -610,23 +566,14 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, WARN_ON_ONCE(ret != entry); __radix_tree_replace(page_tree, node, slot, new_entry, NULL, NULL); + entry = new_entry; } + if (vmf->flags & FAULT_FLAG_WRITE) radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY); - unlock: + spin_unlock_irq(&mapping->tree_lock); - if (hole_fill) { - radix_tree_preload_end(); - /* - * We don't need hole page anymore, it has been replaced with - * locked radix tree entry now. - */ - if (mapping->a_ops->freepage) - mapping->a_ops->freepage(entry); - unlock_page(entry); - put_page(entry); - } - return new_entry; + return entry; } static inline unsigned long @@ -647,11 +594,10 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, pte_t pte, *ptep = NULL; pmd_t *pmdp = NULL; spinlock_t *ptl; - bool changed; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) { - unsigned long address; + unsigned long address, start, end; cond_resched(); @@ -659,8 +605,13 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, continue; address = pgoff_address(index, vma); - changed = false; - if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl)) + + /* + * Note because we provide start/end to follow_pte_pmd it will + * call mmu_notifier_invalidate_range_start() on our behalf + * before taking any lock. + */ + if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl)) continue; if (pmdp) { @@ -677,7 +628,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, pmd = pmd_wrprotect(pmd); pmd = pmd_mkclean(pmd); set_pmd_at(vma->vm_mm, address, pmdp, pmd); - changed = true; + mmu_notifier_invalidate_range(vma->vm_mm, start, end); unlock_pmd: spin_unlock(ptl); #endif @@ -692,13 +643,12 @@ unlock_pmd: pte = pte_wrprotect(pte); pte = pte_mkclean(pte); set_pte_at(vma->vm_mm, address, ptep, pte); - changed = true; + mmu_notifier_invalidate_range(vma->vm_mm, start, end); unlock_pte: pte_unmap_unlock(ptep, ptl); } - if (changed) - mmu_notifier_invalidate_page(vma->vm_mm, address); + mmu_notifier_invalidate_range_end(vma->vm_mm, start, end); } i_mmap_unlock_read(mapping); } @@ -725,7 +675,7 @@ static int dax_writeback_one(struct block_device *bdev, spin_lock_irq(&mapping->tree_lock); entry2 = get_unlocked_mapping_entry(mapping, index, &slot); /* Entry got punched out / reallocated? */ - if (!entry2 || !radix_tree_exceptional_entry(entry2)) + if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2))) goto put_unlocked; /* * Entry got reallocated elsewhere? No need to writeback. We have to @@ -784,7 +734,7 @@ static int dax_writeback_one(struct block_device *bdev, } dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(pfn)); - wb_cache_pmem(kaddr, size); + dax_flush(dax_dev, kaddr, size); /* * After we have flushed the cache, we can clear the dirty tag. There * cannot be new dirty data in the pfn after the flush has completed as @@ -797,7 +747,7 @@ static int dax_writeback_one(struct block_device *bdev, trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT); dax_unlock: dax_read_unlock(id); - put_locked_mapping_entry(mapping, index, entry); + put_locked_mapping_entry(mapping, index); return ret; put_unlocked: @@ -856,8 +806,10 @@ int dax_writeback_mapping_range(struct address_space *mapping, ret = dax_writeback_one(bdev, dax_dev, mapping, indices[i], pvec.pages[i]); - if (ret < 0) + if (ret < 0) { + mapping_set_error(mapping, ret); goto out; + } } start_index = indices[pvec.nr - 1] + 1; } @@ -870,11 +822,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); static int dax_insert_mapping(struct address_space *mapping, struct block_device *bdev, struct dax_device *dax_dev, - sector_t sector, size_t size, void **entryp, + sector_t sector, size_t size, void *entry, struct vm_area_struct *vma, struct vm_fault *vmf) { unsigned long vaddr = vmf->address; - void *entry = *entryp; void *ret, *kaddr; pgoff_t pgoff; int id, rc; @@ -895,47 +846,48 @@ static int dax_insert_mapping(struct address_space *mapping, ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, 0); if (IS_ERR(ret)) return PTR_ERR(ret); - *entryp = ret; trace_dax_insert_mapping(mapping->host, vmf, ret); - return vm_insert_mixed(vma, vaddr, pfn); + if (vmf->flags & FAULT_FLAG_WRITE) + return vm_insert_mixed_mkwrite(vma, vaddr, pfn); + else + return vm_insert_mixed(vma, vaddr, pfn); } -/** - * dax_pfn_mkwrite - handle first write to DAX page - * @vmf: The description of the fault +/* + * The user has performed a load from a hole in the file. Allocating a new + * page in the file would cause excessive storage usage for workloads with + * sparse files. Instead we insert a read-only mapping of the 4k zero page. + * If this page is ever written to we will re-fault and change the mapping to + * point to real DAX storage instead. */ -int dax_pfn_mkwrite(struct vm_fault *vmf) +static int dax_load_hole(struct address_space *mapping, void *entry, + struct vm_fault *vmf) { - struct file *file = vmf->vma->vm_file; - struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - void *entry, **slot; - pgoff_t index = vmf->pgoff; + unsigned long vaddr = vmf->address; + int ret = VM_FAULT_NOPAGE; + struct page *zero_page; + void *entry2; - spin_lock_irq(&mapping->tree_lock); - entry = get_unlocked_mapping_entry(mapping, index, &slot); - if (!entry || !radix_tree_exceptional_entry(entry)) { - if (entry) - put_unlocked_mapping_entry(mapping, index, entry); - spin_unlock_irq(&mapping->tree_lock); - trace_dax_pfn_mkwrite_no_entry(inode, vmf, VM_FAULT_NOPAGE); - return VM_FAULT_NOPAGE; + zero_page = ZERO_PAGE(0); + if (unlikely(!zero_page)) { + ret = VM_FAULT_OOM; + goto out; } - radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY); - entry = lock_slot(mapping, slot); - spin_unlock_irq(&mapping->tree_lock); - /* - * If we race with somebody updating the PTE and finish_mkwrite_fault() - * fails, we don't care. We need to return VM_FAULT_NOPAGE and retry - * the fault in either case. - */ - finish_mkwrite_fault(vmf); - put_locked_mapping_entry(mapping, index, entry); - trace_dax_pfn_mkwrite(inode, vmf, VM_FAULT_NOPAGE); - return VM_FAULT_NOPAGE; + + entry2 = dax_insert_mapping_entry(mapping, vmf, entry, 0, + RADIX_DAX_ZERO_PAGE); + if (IS_ERR(entry2)) { + ret = VM_FAULT_SIGBUS; + goto out; + } + + vm_insert_mixed(vmf->vma, vaddr, page_to_pfn_t(zero_page)); +out: + trace_dax_load_hole(inode, vmf, ret); + return ret; } -EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); static bool dax_range_is_aligned(struct block_device *bdev, unsigned int offset, unsigned int length) @@ -976,7 +928,8 @@ int __dax_zero_page_range(struct block_device *bdev, dax_read_unlock(id); return rc; } - clear_pmem(kaddr + offset, size); + memset(kaddr + offset, 0, size); + dax_flush(dax_dev, kaddr + offset, size); dax_read_unlock(id); } return 0; @@ -1054,8 +1007,14 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (map_len > end - pos) map_len = end - pos; + /* + * The userspace address for the memory copy has already been + * validated via access_ok() in either vfs_read() or + * vfs_write(), depending on which operation we are doing. + */ if (iov_iter_rw(iter) == WRITE) - map_len = copy_from_iter_pmem(kaddr, map_len, iter); + map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr, + map_len, iter); else map_len = copy_to_iter(kaddr, map_len, iter); if (map_len <= 0) { @@ -1213,11 +1172,11 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, case IOMAP_MAPPED: if (iomap.flags & IOMAP_F_NEW) { count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); + count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); major = VM_FAULT_MAJOR; } error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev, - sector, PAGE_SIZE, &entry, vmf->vma, vmf); + sector, PAGE_SIZE, entry, vmf->vma, vmf); /* -EBUSY is fine, somebody else faulted on the same PTE */ if (error == -EBUSY) error = 0; @@ -1225,7 +1184,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (!(vmf->flags & FAULT_FLAG_WRITE)) { - vmf_ret = dax_load_hole(mapping, &entry, vmf); + vmf_ret = dax_load_hole(mapping, entry, vmf); goto finish_iomap; } /*FALLTHRU*/ @@ -1252,21 +1211,15 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap); } unlock_entry: - put_locked_mapping_entry(mapping, vmf->pgoff, entry); + put_locked_mapping_entry(mapping, vmf->pgoff); out: trace_dax_pte_fault_done(inode, vmf, vmf_ret); return vmf_ret; } #ifdef CONFIG_FS_DAX_PMD -/* - * The 'colour' (ie low bits) within a PMD of a page offset. This comes up - * more often than one might expect in the below functions. - */ -#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) - static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, - loff_t pos, void **entryp) + loff_t pos, void *entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; const sector_t sector = dax_iomap_sector(iomap, pos); @@ -1277,7 +1230,7 @@ static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, void *ret = NULL, *kaddr; long length = 0; pgoff_t pgoff; - pfn_t pfn; + pfn_t pfn = {}; int id; if (bdev_dax_pgoff(bdev, sector, size, &pgoff) != 0) @@ -1297,11 +1250,10 @@ static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap, goto unlock_fallback; dax_read_unlock(id); - ret = dax_insert_mapping_entry(mapping, vmf, *entryp, sector, + ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, RADIX_DAX_PMD); if (IS_ERR(ret)) goto fallback; - *entryp = ret; trace_dax_pmd_insert_mapping(inode, vmf, length, pfn, ret); return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, @@ -1315,7 +1267,7 @@ fallback: } static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, - void **entryp) + void *entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; unsigned long pmd_addr = vmf->address & PMD_MASK; @@ -1330,11 +1282,10 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, if (unlikely(!zero_page)) goto fallback; - ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0, - RADIX_DAX_PMD | RADIX_DAX_HZP); + ret = dax_insert_mapping_entry(mapping, vmf, entry, 0, + RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE); if (IS_ERR(ret)) goto fallback; - *entryp = ret; ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { @@ -1380,6 +1331,16 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, trace_dax_pmd_fault(inode, vmf, max_pgoff, 0); + /* + * Make sure that the faulting address's PMD offset (color) matches + * the PMD offset from the start of the file. This is necessary so + * that a PMD range in the page table overlaps exactly with a PMD + * range in the radix tree. + */ + if ((vmf->pgoff & PG_PMD_COLOUR) != + ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR)) + goto fallback; + /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) goto fallback; @@ -1400,10 +1361,10 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, goto fallback; /* - * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX - * PMD or a HZP entry. If it can't (because a 4k page is already in - * the tree, for instance), it will return -EEXIST and we just fall - * back to 4k entries. + * grab_mapping_entry() will make sure we get a 2MiB empty entry, a + * 2MiB zero page entry or a DAX PMD. If it can't (because a 4k page + * is already in the tree, for instance), it will return -EEXIST and + * we just fall back to 4k entries. */ entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD); if (IS_ERR(entry)) @@ -1436,13 +1397,13 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, switch (iomap.type) { case IOMAP_MAPPED: - result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry); + result = dax_pmd_insert_mapping(vmf, &iomap, pos, entry); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (WARN_ON_ONCE(write)) break; - result = dax_pmd_load_hole(vmf, &iomap, &entry); + result = dax_pmd_load_hole(vmf, &iomap, entry); break; default: WARN_ON_ONCE(1); @@ -1465,7 +1426,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, &iomap); } unlock_entry: - put_locked_mapping_entry(mapping, pgoff, entry); + put_locked_mapping_entry(mapping, pgoff); fallback: if (result == VM_FAULT_FALLBACK) { split_huge_pmd(vma, vmf->pmd, vmf->address); diff --git a/fs/dcache.c b/fs/dcache.c index a9f995f6859e..f90141387f01 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -90,6 +90,11 @@ EXPORT_SYMBOL(rename_lock); static struct kmem_cache *dentry_cache __read_mostly; +const struct qstr empty_name = QSTR_INIT("", 0); +EXPORT_SYMBOL(empty_name); +const struct qstr slash_name = QSTR_INIT("/", 1); +EXPORT_SYMBOL(slash_name); + /* * This is the single most critical data structure when it comes * to the dcache: the hashtable for lookups. Somebody should try @@ -277,6 +282,33 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } +void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + if (unlikely(dname_external(dentry))) { + struct external_name *p = external_name(dentry); + atomic_inc(&p->u.count); + spin_unlock(&dentry->d_lock); + name->name = p->name; + } else { + memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN); + spin_unlock(&dentry->d_lock); + name->name = name->inline_name; + } +} +EXPORT_SYMBOL(take_dentry_name_snapshot); + +void release_dentry_name_snapshot(struct name_snapshot *name) +{ + if (unlikely(name->name != name->inline_name)) { + struct external_name *p; + p = container_of(name->name, struct external_name, name[0]); + if (unlikely(atomic_dec_and_test(&p->u.count))) + kfree_rcu(p, u.head); + } +} +EXPORT_SYMBOL(release_dentry_name_snapshot); + static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -1133,11 +1165,12 @@ void shrink_dcache_sb(struct super_block *sb) LIST_HEAD(dispose); freed = list_lru_walk(&sb->s_dentry_lru, - dentry_lru_isolate_shrink, &dispose, UINT_MAX); + dentry_lru_isolate_shrink, &dispose, 1024); this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); - } while (freed > 0); + cond_resched(); + } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); @@ -1578,8 +1611,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) */ dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { - static const struct qstr anon = QSTR_INIT("/", 1); - name = &anon; + name = &slash_name; dname = dentry->d_iname; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); @@ -3546,8 +3578,6 @@ __setup("dhash_entries=", set_dhash_entries); static void __init dcache_init_early(void) { - unsigned int loop; - /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ @@ -3559,24 +3589,19 @@ static void __init dcache_init_early(void) sizeof(struct hlist_bl_head), dhash_entries, 13, - HASH_EARLY, + HASH_EARLY | HASH_ZERO, &d_hash_shift, &d_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << d_hash_shift); loop++) - INIT_HLIST_BL_HEAD(dentry_hashtable + loop); } static void __init dcache_init(void) { - unsigned int loop; - - /* + /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature - * of the dcache. + * of the dcache. */ dentry_cache = KMEM_CACHE(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT); @@ -3590,14 +3615,11 @@ static void __init dcache_init(void) sizeof(struct hlist_bl_head), dhash_entries, 13, - 0, + HASH_ZERO, &d_hash_shift, &d_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << d_hash_shift); loop++) - INIT_HLIST_BL_HEAD(dentry_hashtable + loop); } /* SLAB cache for __getname() consumers */ @@ -3608,6 +3630,11 @@ EXPORT_SYMBOL(d_genocide); void __init vfs_caches_init_early(void) { + int i; + + for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++) + INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]); + dcache_init_early(); inode_init_early(); } diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 354e2ab62031..6dabc4a10396 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/filesystems for more details. + * See Documentation/filesystems/ for more details. * */ diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index e892ae7d89f8..c59f015f386e 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -9,7 +9,7 @@ * 2 as published by the Free Software Foundation. * * debugfs is for people to use instead of /proc or /sys. - * See Documentation/DocBook/kernel-api for more details. + * See ./Documentation/core-api/kernel-api.rst for more details. * */ @@ -203,8 +203,6 @@ static int debug_fill_super(struct super_block *sb, void *data, int silent) struct debugfs_fs_info *fsi; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) { @@ -766,7 +764,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, { int error; struct dentry *dentry = NULL, *trap; - const char *old_name; + struct name_snapshot old_name; trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ @@ -781,19 +779,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) goto exit; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir), dentry, 0); if (error) { - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); goto exit; } d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name, + fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name, d_is_dir(old_dentry), NULL, old_dentry); - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); unlock_rename(new_dir, old_dir); dput(dentry); return old_dentry; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 108df2e3602c..7eae33ffa3fc 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -133,6 +133,50 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb) return sb->s_fs_info; } +static int devpts_ptmx_path(struct path *path) +{ + struct super_block *sb; + int err; + + /* Has the devpts filesystem already been found? */ + if (path->mnt->mnt_sb->s_magic == DEVPTS_SUPER_MAGIC) + return 0; + + /* Is a devpts filesystem at "pts" in the same directory? */ + err = path_pts(path); + if (err) + return err; + + /* Is the path the root of a devpts filesystem? */ + sb = path->mnt->mnt_sb; + if ((sb->s_magic != DEVPTS_SUPER_MAGIC) || + (path->mnt->mnt_root != sb->s_root)) + return -ENODEV; + + return 0; +} + +struct vfsmount *devpts_mntget(struct file *filp, struct pts_fs_info *fsi) +{ + struct path path; + int err; + + path = filp->f_path; + path_get(&path); + + err = devpts_ptmx_path(&path); + dput(path.dentry); + if (err) { + mntput(path.mnt); + path.mnt = ERR_PTR(err); + } + if (DEVPTS_SB(path.mnt->mnt_sb) != fsi) { + mntput(path.mnt); + path.mnt = ERR_PTR(-ENODEV); + } + return path.mnt; +} + struct pts_fs_info *devpts_acquire(struct file *filp) { struct pts_fs_info *result; @@ -143,27 +187,16 @@ struct pts_fs_info *devpts_acquire(struct file *filp) path = filp->f_path; path_get(&path); - /* Has the devpts filesystem already been found? */ - sb = path.mnt->mnt_sb; - if (sb->s_magic != DEVPTS_SUPER_MAGIC) { - /* Is a devpts filesystem at "pts" in the same directory? */ - err = path_pts(&path); - if (err) { - result = ERR_PTR(err); - goto out; - } - - /* Is the path the root of a devpts filesystem? */ - result = ERR_PTR(-ENODEV); - sb = path.mnt->mnt_sb; - if ((sb->s_magic != DEVPTS_SUPER_MAGIC) || - (path.mnt->mnt_root != sb->s_root)) - goto out; + err = devpts_ptmx_path(&path); + if (err) { + result = ERR_PTR(err); + goto out; } /* * pty code needs to hold extra references in case of last /dev/tty close */ + sb = path.mnt->mnt_sb; atomic_inc(&sb->s_active); result = DEVPTS_SB(sb); diff --git a/fs/direct-io.c b/fs/direct-io.c index a04ebea77de8..b53e66d9abd7 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -45,6 +45,12 @@ #define DIO_PAGES 64 /* + * Flags for dio_complete() + */ +#define DIO_COMPLETE_ASYNC 0x01 /* This is async IO */ +#define DIO_COMPLETE_INVALIDATE 0x02 /* Can invalidate pages */ + +/* * This code generally works in units of "dio_blocks". A dio_block is * somewhere between the hard sector size and the filesystem block size. it * is determined on a per-invocation basis. When talking to the filesystem @@ -111,7 +117,7 @@ struct dio { int op; int op_flags; blk_qc_t bio_cookie; - struct block_device *bio_bdev; + struct gendisk *bio_disk; struct inode *inode; loff_t i_size; /* i_size when submitted */ dio_iodone_t *end_io; /* IO completion function */ @@ -225,10 +231,11 @@ static inline struct page *dio_get_page(struct dio *dio, * filesystems can use it to hold additional state between get_block calls and * dio_complete. */ -static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) +static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) { loff_t offset = dio->iocb->ki_pos; ssize_t transferred = 0; + int err; /* * AIO submission can race with bio completion to get here while @@ -259,18 +266,37 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async) ret = transferred; if (dio->end_io) { - int err; - // XXX: ki_pos?? err = dio->end_io(dio->iocb, offset, ret, dio->private); if (err) ret = err; } + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + * + * And this page cache invalidation has to be after dio->end_io(), as + * some filesystems convert unwritten extents to real allocations in + * end_io() when necessary, otherwise a racing buffer read would cache + * zeros from unwritten extents. + */ + if (flags & DIO_COMPLETE_INVALIDATE && + ret > 0 && dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages) { + err = invalidate_inode_pages2_range(dio->inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + ret - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + if (!(dio->flags & DIO_SKIP_DIO_COUNT)) inode_dio_end(dio->inode); - if (is_async) { + if (flags & DIO_COMPLETE_ASYNC) { /* * generic_write_sync expects ki_pos to have been updated * already, but the submission path only does this for @@ -291,10 +317,10 @@ static void dio_aio_complete_work(struct work_struct *work) { struct dio *dio = container_of(work, struct dio, complete_work); - dio_complete(dio, 0, true); + dio_complete(dio, 0, DIO_COMPLETE_ASYNC | DIO_COMPLETE_INVALIDATE); } -static int dio_bio_complete(struct dio *dio, struct bio *bio); +static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. @@ -304,6 +330,7 @@ static void dio_bio_end_aio(struct bio *bio) struct dio *dio = bio->bi_private; unsigned long remaining; unsigned long flags; + bool defer_completion = false; /* cleanup the bio */ dio_bio_complete(dio, bio); @@ -315,12 +342,24 @@ static void dio_bio_end_aio(struct bio *bio) spin_unlock_irqrestore(&dio->bio_lock, flags); if (remaining == 0) { - if (dio->result && dio->defer_completion) { + /* + * Defer completion when defer_completion is set or + * when the inode has pages mapped and this is AIO write. + * We need to invalidate those pages because there is a + * chance they contain stale data in the case buffered IO + * went in between AIO submission and completion into the + * same region. + */ + if (dio->result) + defer_completion = dio->defer_completion || + (dio->op == REQ_OP_WRITE && + dio->inode->i_mapping->nrpages); + if (defer_completion) { INIT_WORK(&dio->complete_work, dio_aio_complete_work); queue_work(dio->inode->i_sb->s_dio_done_wq, &dio->complete_work); } else { - dio_complete(dio, 0, true); + dio_complete(dio, 0, DIO_COMPLETE_ASYNC); } } } @@ -348,13 +387,12 @@ static void dio_bio_end_io(struct bio *bio) /** * dio_end_io - handle the end io action for the given bio * @bio: The direct io bio thats being completed - * @error: Error if there was one * * This is meant to be called by any filesystem that uses their own dio_submit_t * so that the DIO specific endio actions are dealt with after the filesystem * has done it's completion work. */ -void dio_end_io(struct bio *bio, int error) +void dio_end_io(struct bio *bio) { struct dio *dio = bio->bi_private; @@ -378,7 +416,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, */ bio = bio_alloc(GFP_KERNEL, nr_vecs); - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = first_sector; bio_set_op_attrs(bio, dio->op, dio->op_flags); if (dio->is_async) @@ -386,6 +424,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio, else bio->bi_end_io = dio_bio_end_io; + bio->bi_write_hint = dio->iocb->ki_hint; + sdio->bio = bio; sdio->logical_offset_in_bio = sdio->cur_page_fs_offset; } @@ -411,7 +451,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) bio_set_pages_dirty(bio); - dio->bio_bdev = bio->bi_bdev; + dio->bio_disk = bio->bi_disk; if (sdio->submit_io) { sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio); @@ -457,7 +497,7 @@ static struct bio *dio_await_one(struct dio *dio) dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); if (!(dio->iocb->ki_flags & IOCB_HIPRI) || - !blk_mq_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) + !blk_mq_poll(dio->bio_disk->queue, dio->bio_cookie)) io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); @@ -474,17 +514,20 @@ static struct bio *dio_await_one(struct dio *dio) /* * Process one completed BIO. No locks are held. */ -static int dio_bio_complete(struct dio *dio, struct bio *bio) +static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) { struct bio_vec *bvec; unsigned i; - int err; + blk_status_t err = bio->bi_status; - if (bio->bi_error) - dio->io_error = -EIO; + if (err) { + if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT)) + dio->io_error = -EAGAIN; + else + dio->io_error = -EIO; + } if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) { - err = bio->bi_error; bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_for_each_segment_all(bvec, bio, i) { @@ -495,7 +538,6 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) set_page_dirty_lock(page); put_page(page); } - err = bio->bi_error; bio_put(bio); } return err; @@ -539,7 +581,7 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio) bio = dio->bio_list; dio->bio_list = bio->bi_private; spin_unlock_irqrestore(&dio->bio_lock, flags); - ret2 = dio_bio_complete(dio, bio); + ret2 = blk_status_to_errno(dio_bio_complete(dio, bio)); if (ret == 0) ret = ret2; } @@ -835,7 +877,8 @@ out: */ if (sdio->boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); - dio_bio_submit(dio, sdio); + if (sdio->bio) + dio_bio_submit(dio, sdio); put_page(sdio->cur_page); sdio->cur_page = NULL; } @@ -1197,6 +1240,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, if (iov_iter_rw(iter) == WRITE) { dio->op = REQ_OP_WRITE; dio->op_flags = REQ_SYNC | REQ_IDLE; + if (iocb->ki_flags & IOCB_NOWAIT) + dio->op_flags |= REQ_NOWAIT; } else { dio->op = REQ_OP_READ; } @@ -1205,10 +1250,19 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * For AIO O_(D)SYNC writes we need to defer completions to a workqueue * so that we can call ->fsync. */ - if (dio->is_async && iov_iter_rw(iter) == WRITE && - ((iocb->ki_filp->f_flags & O_DSYNC) || - IS_SYNC(iocb->ki_filp->f_mapping->host))) { - retval = dio_set_defer_completion(dio); + if (dio->is_async && iov_iter_rw(iter) == WRITE) { + retval = 0; + if ((iocb->ki_filp->f_flags & O_DSYNC) || + IS_SYNC(iocb->ki_filp->f_mapping->host)) + retval = dio_set_defer_completion(dio); + else if (!dio->inode->i_sb->s_dio_done_wq) { + /* + * In case of AIO write racing with buffered read we + * need to defer completion. We can't decide this now, + * however the workqueue needs to be initialized here. + */ + retval = sb_init_dio_done_wq(dio->inode->i_sb); + } if (retval) { /* * We grab i_mutex only for reads so we don't have @@ -1317,7 +1371,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, dio_await_completion(dio); if (drop_refcount(dio) == 0) { - retval = dio_complete(dio, retval, false); + retval = dio_complete(dio, retval, DIO_COMPLETE_INVALIDATE); } else BUG_ON(retval != -EIOCBQUEUED); diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index ca7089aeadab..fa08448e35dd 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -68,7 +68,7 @@ static void print_format1_lock(struct seq_file *s, struct dlm_lkb *lkb, if (lkb->lkb_wait_type) seq_printf(s, " wait_type: %d", lkb->lkb_wait_type); - seq_puts(s, "\n"); + seq_putc(s, '\n'); } static void print_format1(struct dlm_rsb *res, struct seq_file *s) @@ -111,7 +111,7 @@ static void print_format1(struct dlm_rsb *res, struct seq_file *s) } if (rsb_flag(res, RSB_VALNOTVALID)) seq_puts(s, " (INVALID)"); - seq_puts(s, "\n"); + seq_putc(s, '\n'); if (seq_has_overflowed(s)) goto out; } @@ -156,7 +156,7 @@ static void print_format1(struct dlm_rsb *res, struct seq_file *s) lkb->lkb_id, print_lockmode(lkb->lkb_rqmode)); if (lkb->lkb_wait_type) seq_printf(s, " wait_type: %d", lkb->lkb_wait_type); - seq_puts(s, "\n"); + seq_putc(s, '\n'); if (seq_has_overflowed(s)) goto out; } @@ -287,7 +287,7 @@ static void print_format3(struct dlm_rsb *r, struct seq_file *s) else seq_printf(s, " %02x", (unsigned char)r->res_name[i]); } - seq_puts(s, "\n"); + seq_putc(s, '\n'); if (seq_has_overflowed(s)) goto out; @@ -298,7 +298,7 @@ static void print_format3(struct dlm_rsb *r, struct seq_file *s) for (i = 0; i < lvblen; i++) seq_printf(s, " %02x", (unsigned char)r->res_lvbptr[i]); - seq_puts(s, "\n"); + seq_putc(s, '\n'); if (seq_has_overflowed(s)) goto out; @@ -361,8 +361,7 @@ static void print_format4(struct dlm_rsb *r, struct seq_file *s) else seq_printf(s, " %02x", (unsigned char)r->res_name[i]); } - seq_puts(s, "\n"); - + seq_putc(s, '\n'); unlock_rsb(r); } @@ -436,7 +435,7 @@ static void *table_seq_start(struct seq_file *seq, loff_t *pos) if (bucket >= ls->ls_rsbtbl_size) return NULL; - ri = kzalloc(sizeof(struct rsbtbl_iter), GFP_NOFS); + ri = kzalloc(sizeof(*ri), GFP_NOFS); if (!ri) return NULL; if (n == 0) @@ -742,7 +741,7 @@ void dlm_delete_debug_file(struct dlm_ls *ls) int dlm_create_debug_file(struct dlm_ls *ls) { - char name[DLM_LOCKSPACE_LEN+8]; + char name[DLM_LOCKSPACE_LEN + 8]; /* format 1 */ @@ -757,7 +756,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) /* format 2 */ memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_locks", ls->ls_name); + snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_locks", ls->ls_name); ls->ls_debug_locks_dentry = debugfs_create_file(name, S_IFREG | S_IRUGO, @@ -770,7 +769,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) /* format 3 */ memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_all", ls->ls_name); + snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_all", ls->ls_name); ls->ls_debug_all_dentry = debugfs_create_file(name, S_IFREG | S_IRUGO, @@ -783,7 +782,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) /* format 4 */ memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_toss", ls->ls_name); + snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_toss", ls->ls_name); ls->ls_debug_toss_dentry = debugfs_create_file(name, S_IFREG | S_IRUGO, @@ -794,7 +793,7 @@ int dlm_create_debug_file(struct dlm_ls *ls) goto fail; memset(name, 0, sizeof(name)); - snprintf(name, DLM_LOCKSPACE_LEN+8, "%s_waiters", ls->ls_name); + snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_waiters", ls->ls_name); ls->ls_debug_waiters_dentry = debugfs_create_file(name, S_IFREG | S_IRUGO, diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 6df332296c66..d4aaddec1b16 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1426,7 +1426,7 @@ void dlm_scan_waiters(struct dlm_ls *ls) if (!num_nodes) { num_nodes = ls->ls_num_nodes; - warned = kzalloc(num_nodes * sizeof(int), GFP_KERNEL); + warned = kcalloc(num_nodes, sizeof(int), GFP_KERNEL); } if (!warned) continue; @@ -5119,11 +5119,9 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) int wait_type, stub_unlock_result, stub_cancel_result; int dir_nodeid; - ms_stub = kmalloc(sizeof(struct dlm_message), GFP_KERNEL); - if (!ms_stub) { - log_error(ls, "dlm_recover_waiters_pre no mem"); + ms_stub = kmalloc(sizeof(*ms_stub), GFP_KERNEL); + if (!ms_stub) return; - } mutex_lock(&ls->ls_waiters_mutex); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 91592b75c309..78a7c855b06b 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -235,7 +235,7 @@ static int dlm_uevent(struct kset *kset, struct kobject *kobj, return 0; } -static struct kset_uevent_ops dlm_uevent_ops = { +static const struct kset_uevent_ops dlm_uevent_ops = { .uevent = dlm_uevent, }; @@ -453,9 +453,14 @@ static int new_lockspace(const char *name, const char *cluster, *ops_result = 0; } + if (!cluster) + log_print("dlm cluster name '%s' is being used without an application provided cluster name", + dlm_config.ci_cluster_name); + if (dlm_config.ci_recover_callbacks && cluster && strncmp(cluster, dlm_config.ci_cluster_name, DLM_LOCKSPACE_LEN)) { - log_print("dlm cluster name %s mismatch %s", + log_print("dlm cluster name '%s' does not match " + "the application cluster name '%s'", dlm_config.ci_cluster_name, cluster); error = -EBADR; goto out; diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 9382db998ec9..4813d0e0cd9b 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -729,7 +729,7 @@ static int tcp_accept_from_sock(struct connection *con) mutex_unlock(&connections_lock); memset(&peeraddr, 0, sizeof(peeraddr)); - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_lite(dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_TCP, &newsock); if (result < 0) return -ENOMEM; diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 9c47f1c14a8b..3fda3832cf6a 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -217,8 +217,7 @@ int dlm_slots_assign(struct dlm_ls *ls, int *num_slots, int *slots_size, } array_size = max + need; - - array = kzalloc(array_size * sizeof(struct dlm_slot), GFP_NOFS); + array = kcalloc(array_size, sizeof(*array), GFP_NOFS); if (!array) return -ENOMEM; @@ -319,7 +318,7 @@ static int dlm_add_member(struct dlm_ls *ls, struct dlm_config_node *node) struct dlm_member *memb; int error; - memb = kzalloc(sizeof(struct dlm_member), GFP_NOFS); + memb = kzalloc(sizeof(*memb), GFP_NOFS); if (!memb) return -ENOMEM; @@ -405,8 +404,7 @@ static void make_member_array(struct dlm_ls *ls) } ls->ls_total_weight = total; - - array = kmalloc(sizeof(int) * total, GFP_NOFS); + array = kmalloc_array(total, sizeof(*array), GFP_NOFS); if (!array) return; @@ -492,8 +490,7 @@ void dlm_lsop_recover_done(struct dlm_ls *ls) return; num = ls->ls_num_nodes; - - slots = kzalloc(num * sizeof(struct dlm_slot), GFP_KERNEL); + slots = kcalloc(num, sizeof(*slots), GFP_KERNEL); if (!slots) return; @@ -673,11 +670,11 @@ int dlm_ls_stop(struct dlm_ls *ls) int dlm_ls_start(struct dlm_ls *ls) { - struct dlm_recover *rv = NULL, *rv_old; + struct dlm_recover *rv, *rv_old; struct dlm_config_node *nodes; int error, count; - rv = kzalloc(sizeof(struct dlm_recover), GFP_NOFS); + rv = kzalloc(sizeof(*rv), GFP_NOFS); if (!rv) return -ENOMEM; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index d401425f602a..e631b1689228 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -367,7 +367,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file, locks_init_lock(fl); fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK; fl->fl_flags = FL_POSIX; - fl->fl_pid = op->info.pid; + fl->fl_pid = -op->info.pid; fl->fl_start = op->info.start; fl->fl_end = op->info.end; rv = 0; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 23488f559cf9..d18e7a539f11 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -123,6 +123,8 @@ static void compat_input(struct dlm_write_request *kb, static void compat_output(struct dlm_lock_result *res, struct dlm_lock_result32 *res32) { + memset(res32, 0, sizeof(*res32)); + res32->version[0] = res->version[0]; res32->version[1] = res->version[1]; res32->version[2] = res->version[2]; @@ -355,6 +357,10 @@ static int dlm_device_register(struct dlm_ls *ls, char *name) error = misc_register(&ls->ls_device); if (error) { kfree(ls->ls_device.name); + /* this has to be set to NULL + * to avoid a double-free in dlm_device_deregister + */ + ls->ls_device.name = NULL; } fail: return error; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 9c351bf757b2..3fbc0ff79699 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -84,11 +84,16 @@ struct ecryptfs_page_crypt_context { static inline struct ecryptfs_auth_tok * ecryptfs_get_encrypted_key_payload_data(struct key *key) { - if (key->type == &key_type_encrypted) - return (struct ecryptfs_auth_tok *) - (&((struct encrypted_key_payload *)key->payload.data[0])->payload_data); - else + struct encrypted_key_payload *payload; + + if (key->type != &key_type_encrypted) return NULL; + + payload = key->payload.data[0]; + if (!payload) + return ERR_PTR(-EKEYREVOKED); + + return (struct ecryptfs_auth_tok *)payload->payload_data; } static inline struct key *ecryptfs_get_encrypted_key(char *sig) @@ -114,12 +119,17 @@ static inline struct ecryptfs_auth_tok * ecryptfs_get_key_payload_data(struct key *key) { struct ecryptfs_auth_tok *auth_tok; + struct user_key_payload *ukp; auth_tok = ecryptfs_get_encrypted_key_payload_data(key); - if (!auth_tok) - return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data; - else + if (auth_tok) return auth_tok; + + ukp = user_key_payload_locked(key); + if (!ukp) + return ERR_PTR(-EKEYREVOKED); + + return (struct ecryptfs_auth_tok *)ukp->data; } #define ECRYPTFS_MAX_KEYSET_SIZE 1024 diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index ca4e83750214..c74ed3ca3372 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -328,7 +328,7 @@ ecryptfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) { int rc; - rc = filemap_write_and_wait(file->f_mapping); + rc = file_write_and_wait(file); if (rc) return rc; diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 3cf1546dca82..fa218cd64f74 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -459,7 +459,8 @@ out: * @auth_tok_key: key containing the authentication token * @auth_tok: authentication token * - * Returns zero on valid auth tok; -EINVAL otherwise + * Returns zero on valid auth tok; -EINVAL if the payload is invalid; or + * -EKEYREVOKED if the key was revoked before we acquired its semaphore. */ static int ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key, @@ -468,6 +469,12 @@ ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key, int rc = 0; (*auth_tok) = ecryptfs_get_key_payload_data(auth_tok_key); + if (IS_ERR(*auth_tok)) { + rc = PTR_ERR(*auth_tok); + *auth_tok = NULL; + goto out; + } + if (ecryptfs_verify_version((*auth_tok)->version)) { printk(KERN_ERR "Data structure version mismatch. Userspace " "tools must match eCryptfs kernel module with major " diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 9014479d0160..6b801186baa5 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -568,8 +568,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags * 1) The lower mount is ro * 2) The ecryptfs_encrypted_view mount option is specified */ - if (path.dentry->d_sb->s_flags & MS_RDONLY || - mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) + if (sb_rdonly(path.dentry->d_sb) || mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) s->s_flags |= MS_RDONLY; s->s_maxbytes = path.dentry->d_sb->s_maxbytes; diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c index 039e627194a9..c596e7c03424 100644 --- a/fs/ecryptfs/read_write.c +++ b/fs/ecryptfs/read_write.c @@ -47,7 +47,7 @@ int ecryptfs_write_lower(struct inode *ecryptfs_inode, char *data, lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file; if (!lower_file) return -EIO; - rc = kernel_write(lower_file, data, size, offset); + rc = kernel_write(lower_file, data, size, &offset); mark_inode_dirty_sync(ecryptfs_inode); return rc; } @@ -237,7 +237,7 @@ int ecryptfs_read_lower(char *data, loff_t offset, size_t size, lower_file = ecryptfs_inode_to_private(ecryptfs_inode)->lower_file; if (!lower_file) return -EIO; - return kernel_read(lower_file, offset, data, size); + return kernel_read(lower_file, data, size, &offset); } /** diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index d7a7c53803c1..5b68e4294faa 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -29,7 +29,6 @@ static const struct super_operations efivarfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .evict_inode = efivarfs_evict_inode, - .show_options = generic_show_options, }; static struct super_block *efivarfs_sb; diff --git a/fs/efs/super.c b/fs/efs/super.c index 368f7dd21c61..5c42f1e34a2f 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -306,7 +306,7 @@ static int efs_fill_super(struct super_block *s, void *d, int silent) } brelse(bh); - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { #ifdef DEBUG pr_info("forcing read-only mode\n"); #endif diff --git a/fs/eventfd.c b/fs/eventfd.c index 68b9fffcb2c8..2fb4eadaa118 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -191,7 +191,7 @@ static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt) * This is used to atomically remove a wait queue entry from the eventfd wait * queue head, and read/reset the counter value. */ -int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait, +int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt) { unsigned long flags; @@ -215,8 +215,8 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue); * * Returns %0 if successful, or the following error codes: * - * -EAGAIN : The operation would have blocked but @no_wait was non-zero. - * -ERESTARTSYS : A signal interrupted the wait operation. + * - -EAGAIN : The operation would have blocked but @no_wait was non-zero. + * - -ERESTARTSYS : A signal interrupted the wait operation. * * If @no_wait is zero, the function might sleep until the eventfd internal * counter becomes greater than zero. diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 5420767c9b68..2fabd19cdeea 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -205,7 +205,7 @@ struct eventpoll { struct list_head rdllist; /* RB tree root used to store monitored fd structs */ - struct rb_root rbr; + struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that @@ -244,7 +244,7 @@ struct eppoll_entry { * Wait queue item that will be linked to the target file wait * queue head. */ - wait_queue_t wait; + wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; @@ -347,13 +347,13 @@ static inline int ep_is_linked(struct list_head *p) return !list_empty(p); } -static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p) +static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ -static inline struct epitem *ep_item_from_wait(wait_queue_t *p) +static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } @@ -600,8 +600,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq) wait_queue_head_t *whead; rcu_read_lock(); - /* If it is cleared by POLLFREE, it should be rcu-safe */ - whead = rcu_dereference(pwq->whead); + /* + * If it is cleared by POLLFREE, it should be rcu-safe. + * If we read NULL we need a barrier paired with + * smp_store_release() in ep_poll_callback(), otherwise + * we rely on whead->lock. + */ + whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); @@ -791,7 +796,7 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) list_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); - rb_erase(&epi->rbn, &ep->rbr); + rb_erase_cached(&epi->rbn, &ep->rbr); spin_lock_irqsave(&ep->lock, flags); if (ep_is_linked(&epi->rdllink)) @@ -835,7 +840,7 @@ static void ep_free(struct eventpoll *ep) /* * Walks through the whole tree by unregistering poll callbacks. */ - for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); @@ -851,7 +856,7 @@ static void ep_free(struct eventpoll *ep) * a lockdep warning. */ mutex_lock(&ep->mtx); - while ((rbp = rb_first(&ep->rbr)) != NULL) { + while ((rbp = rb_first_cached(&ep->rbr)) != NULL) { epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); cond_resched(); @@ -958,12 +963,16 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f) struct rb_node *rbp; mutex_lock(&ep->mtx); - for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); + struct inode *inode = file_inode(epi->ffd.file); - seq_printf(m, "tfd: %8d events: %8x data: %16llx\n", + seq_printf(m, "tfd: %8d events: %8x data: %16llx " + " pos:%lli ino:%lx sdev:%x\n", epi->ffd.fd, epi->event.events, - (long long)epi->event.data); + (long long)epi->event.data, + (long long)epi->ffd.file->f_pos, + inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } @@ -1031,7 +1040,7 @@ static int ep_alloc(struct eventpoll **pep) init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); - ep->rbr = RB_ROOT; + ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; ep->user = user; @@ -1057,7 +1066,7 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) struct epoll_filefd ffd; ep_set_ffd(&ffd, file, fd); - for (rbp = ep->rbr.rb_node; rbp; ) { + for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(&ffd, &epi->ffd); if (kcmp > 0) @@ -1073,12 +1082,56 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd) return epir; } +#ifdef CONFIG_CHECKPOINT_RESTORE +static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) +{ + struct rb_node *rbp; + struct epitem *epi; + + for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { + epi = rb_entry(rbp, struct epitem, rbn); + if (epi->ffd.fd == tfd) { + if (toff == 0) + return epi; + else + toff--; + } + cond_resched(); + } + + return NULL; +} + +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, + unsigned long toff) +{ + struct file *file_raw; + struct eventpoll *ep; + struct epitem *epi; + + if (!is_file_epoll(file)) + return ERR_PTR(-EINVAL); + + ep = file->private_data; + + mutex_lock(&ep->mtx); + epi = ep_find_tfd(ep, tfd, toff); + if (epi) + file_raw = epi->ffd.file; + else + file_raw = ERR_PTR(-ENOENT); + mutex_unlock(&ep->mtx); + + return file_raw; +} +#endif /* CONFIG_CHECKPOINT_RESTORE */ + /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. */ -static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; unsigned long flags; @@ -1086,17 +1139,6 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k struct eventpoll *ep = epi->ep; int ewake = 0; - if ((unsigned long)key & POLLFREE) { - ep_pwq_from_wait(wait)->whead = NULL; - /* - * whead = NULL above can race with ep_remove_wait_queue() - * which can do another remove_wait_queue() after us, so we - * can't use __remove_wait_queue(). whead->lock is held by - * the caller. - */ - list_del_init(&wait->task_list); - } - spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); @@ -1180,10 +1222,26 @@ out_unlock: if (pwake) ep_poll_safewake(&ep->poll_wait); - if (epi->event.events & EPOLLEXCLUSIVE) - return ewake; + if (!(epi->event.events & EPOLLEXCLUSIVE)) + ewake = 1; + + if ((unsigned long)key & POLLFREE) { + /* + * If we race with ep_remove_wait_queue() it can miss + * ->whead = NULL and do another remove_wait_queue() after + * us, so we can't use __remove_wait_queue(). + */ + list_del_init(&wait->entry); + /* + * ->whead != NULL protects us from the race with ep_free() + * or ep_remove(), ep_remove_wait_queue() takes whead->lock + * held by the caller. Once we nullify it, nothing protects + * ep/epi or even wait. + */ + smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); + } - return 1; + return ewake; } /* @@ -1215,20 +1273,22 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; - struct rb_node **p = &ep->rbr.rb_node, *parent = NULL; + struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; + bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); - if (kcmp > 0) + if (kcmp > 0) { p = &parent->rb_right; - else + leftmost = false; + } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); - rb_insert_color(&epi->rbn, &ep->rbr); + rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } @@ -1472,7 +1532,7 @@ error_remove_epi: list_del_rcu(&epi->fllink); spin_unlock(&tfile->f_lock); - rb_erase(&epi->rbn, &ep->rbr); + rb_erase_cached(&epi->rbn, &ep->rbr); error_unregister: ep_unregister_pollwait(ep, epi); @@ -1699,7 +1759,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int res = 0, eavail, timed_out = 0; unsigned long flags; u64 slack = 0; - wait_queue_t wait; + wait_queue_entry_t wait; ktime_t expires, *to = NULL; if (timeout > 0) { @@ -1748,6 +1808,16 @@ fetch_events: * to TASK_INTERRUPTIBLE before doing the checks. */ set_current_state(TASK_INTERRUPTIBLE); + /* + * Always short-circuit for fatal signals to allow + * threads to make a timely exit without the chance of + * finding more events available and fetching + * repeatedly. + */ + if (fatal_signal_pending(current)) { + res = -EINTR; + break; + } if (ep_events_available(ep) || timed_out) break; if (signal_pending(current)) { @@ -1810,7 +1880,7 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) mutex_lock_nested(&ep->mtx, call_nests + 1); ep->visited = 1; list_add(&ep->visited_list_link, &visited_list); - for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) { + for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { ep_tovisit = epi->ffd.file->private_data; diff --git a/fs/exec.c b/fs/exec.c index 904199086490..3e14ba25f678 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -220,8 +220,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, if (write) { unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; - unsigned long ptr_size; - struct rlimit *rlim; + unsigned long ptr_size, limit; /* * Since the stack will hold pointers to the strings, we @@ -250,14 +249,16 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, return page; /* - * Limit to 1/4-th the stack size for the argv+env strings. + * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM + * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ - rlim = current->signal->rlim; - if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) + limit = _STK_LIM / 4 * 3; + limit = min(limit, rlimit(RLIMIT_STACK) / 4); + if (size > limit) goto fail; } @@ -884,23 +885,6 @@ struct file *open_exec(const char *name) } EXPORT_SYMBOL(open_exec); -int kernel_read(struct file *file, loff_t offset, - char *addr, unsigned long count) -{ - mm_segment_t old_fs; - loff_t pos = offset; - int result; - - old_fs = get_fs(); - set_fs(get_ds()); - /* The cast to a user pointer is valid due to the set_fs() */ - result = vfs_read(file, (void __user *)addr, count, &pos); - set_fs(old_fs); - return result; -} - -EXPORT_SYMBOL(kernel_read); - int kernel_read_file(struct file *file, void **buf, loff_t *size, loff_t max_size, enum kernel_read_file_id id) { @@ -938,8 +922,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, pos = 0; while (pos < i_size) { - bytes = kernel_read(file, pos, (char *)(*buf) + pos, - i_size - pos); + bytes = kernel_read(file, *buf + pos, i_size - pos, &pos); if (bytes < 0) { ret = bytes; goto out; @@ -947,7 +930,6 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, if (bytes == 0) break; - pos += bytes; } if (pos != i_size) { @@ -973,7 +955,7 @@ out: } EXPORT_SYMBOL_GPL(kernel_read_file); -int kernel_read_file_from_path(char *path, void **buf, loff_t *size, +int kernel_read_file_from_path(const char *path, void **buf, loff_t *size, loff_t max_size, enum kernel_read_file_id id) { struct file *file; @@ -1258,6 +1240,12 @@ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) perf_event_comm(tsk, exec); } +/* + * Calling this is the point of no return. None of the failures will be + * seen by userspace since either the process is already taking a fatal + * signal (via de_thread() or coredump), or will have SEGV raised + * (after exec_mmap()) by search_binary_handlers (see below). + */ int flush_old_exec(struct linux_binprm * bprm) { int retval; @@ -1285,7 +1273,13 @@ int flush_old_exec(struct linux_binprm * bprm) if (retval) goto out; - bprm->mm = NULL; /* We're using it now */ + /* + * After clearing bprm->mm (to mark that current is using the + * prepared mm now), we have nothing left of the original + * process. If anything from here on returns an error, the check + * in search_binary_handler() will SEGV current. + */ + bprm->mm = NULL; set_fs(USER_DS); current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | @@ -1330,15 +1324,38 @@ EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { + /* + * Once here, prepare_binrpm() will not be called any more, so + * the final state of setuid/setgid/fscaps can be merged into the + * secureexec flag. + */ + bprm->secureexec |= bprm->cap_elevated; + + if (bprm->secureexec) { + /* Make sure parent cannot signal privileged process. */ + current->pdeath_signal = 0; + + /* + * For secureexec, reset the stack limit to sane default to + * avoid bad behavior from the prior rlimits. This has to + * happen before arch_pick_mmap_layout(), which examines + * RLIMIT_STACK, but after the point of no return to avoid + * needing to clean up the change on failure. + */ + if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM) + current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM; + } + arch_pick_mmap_layout(current->mm); - /* This is the point of no return */ current->sas_ss_sp = current->sas_ss_size = 0; - if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) - set_dumpable(current->mm, SUID_DUMP_USER); - else + /* Figure out dumpability. */ + if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || + bprm->secureexec) set_dumpable(current->mm, suid_dumpable); + else + set_dumpable(current->mm, SUID_DUMP_USER); arch_setup_new_exec(); perf_event_exec(); @@ -1350,15 +1367,6 @@ void setup_new_exec(struct linux_binprm * bprm) */ current->mm->task_size = TASK_SIZE; - /* install the new credentials */ - if (!uid_eq(bprm->cred->uid, current_euid()) || - !gid_eq(bprm->cred->gid, current_egid())) { - current->pdeath_signal = 0; - } else { - if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP) - set_dumpable(current->mm, suid_dumpable); - } - /* An exec changes our domain. We are no longer part of the thread group */ current->self_exec_id++; @@ -1402,7 +1410,7 @@ static void free_bprm(struct linux_binprm *bprm) kfree(bprm); } -int bprm_change_interp(char *interp, struct linux_binprm *bprm) +int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) @@ -1540,6 +1548,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm) int prepare_binprm(struct linux_binprm *bprm) { int retval; + loff_t pos = 0; bprm_fill_uid(bprm); @@ -1547,10 +1556,10 @@ int prepare_binprm(struct linux_binprm *bprm) retval = security_bprm_set_creds(bprm); if (retval) return retval; - bprm->cred_prepared = 1; + bprm->called_set_creds = 1; memset(bprm->buf, 0, BINPRM_BUF_SIZE); - return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE); + return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos); } EXPORT_SYMBOL(prepare_binprm); @@ -1736,9 +1745,9 @@ static int do_execveat_common(int fd, struct filename *filename, bprm->filename = filename->name; } else { if (filename->name[0] == '\0') - pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d", fd); + pathbuf = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); else - pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d/%s", + pathbuf = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); if (!pathbuf) { retval = -ENOMEM; @@ -1793,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename, /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; + membarrier_execve(current); acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index 8eeb694332fe..98233a97b7b8 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -72,7 +72,7 @@ static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len) set_page_dirty(page); if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 28645f0640f7..a94594ea2aa3 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -48,7 +48,7 @@ static int exofs_file_fsync(struct file *filp, loff_t start, loff_t end, struct inode *inode = filp->f_mapping->host; int ret; - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(filp, start, end); if (ret) return ret; diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 8bb72807e70d..3c6a9c156b7a 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -869,7 +869,7 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) goto out; } - bio->bi_bdev = NULL; + bio->bi_disk = NULL; bio->bi_next = NULL; per_dev->offset = master_dev->offset; per_dev->length = master_dev->length; diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 79dafa71effd..51f0aea70cb4 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -175,11 +175,8 @@ ext2_get_acl(struct inode *inode, int type) return acl; } -/* - * inode->i_mutex: down - */ -int -ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +static int +__ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) { int name_index; void *value = NULL; @@ -189,13 +186,6 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch(type) { case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - inode->i_ctime = current_time(inode); - mark_inode_dirty(inode); - } break; case ACL_TYPE_DEFAULT: @@ -222,6 +212,31 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) } /* + * inode->i_mutex: down + */ +int +ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int error; + int update_mode = 0; + umode_t mode = inode->i_mode; + + if (type == ACL_TYPE_ACCESS && acl) { + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + return error; + update_mode = 1; + } + error = __ext2_set_acl(inode, acl, type); + if (!error && update_mode) { + inode->i_mode = mode; + inode->i_ctime = current_time(inode); + mark_inode_dirty(inode); + } + return error; +} + +/* * Initialize the ACLs of a new inode. Called from ext2_new_inode. * * dir->i_mutex: down @@ -238,12 +253,12 @@ ext2_init_acl(struct inode *inode, struct inode *dir) return error; if (default_acl) { - error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!error) - error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); } return error; diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c index d9650c9508e4..e2709695b177 100644 --- a/fs/ext2/dir.c +++ b/fs/ext2/dir.c @@ -100,7 +100,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len) } if (IS_DIRSYNC(dir)) { - err = write_one_page(page, 1); + err = write_one_page(page); if (!err) err = sync_inode_metadata(dir, 1); } else { diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 03f5ce1d3dbe..28de3edd4f4d 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -113,7 +113,8 @@ struct ext2_sb_info { * of the mount options. */ spinlock_t s_lock; - struct mb_cache *s_mb_cache; + struct mb_cache *s_ea_block_cache; + struct dax_device *s_daxdev; }; static inline spinlock_t * diff --git a/fs/ext2/file.c b/fs/ext2/file.c index b21891a6bfca..ff3a3636a5ca 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -107,29 +107,6 @@ static int ext2_dax_fault(struct vm_fault *vmf) return ret; } -static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vmf->vma->vm_file); - struct ext2_inode_info *ei = EXT2_I(inode); - loff_t size; - int ret; - - sb_start_pagefault(inode->i_sb); - file_update_time(vmf->vma->vm_file); - down_read(&ei->dax_sem); - - /* check that the faulting page hasn't raced with truncate */ - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (vmf->pgoff >= size) - ret = VM_FAULT_SIGBUS; - else - ret = dax_pfn_mkwrite(vmf); - - up_read(&ei->dax_sem); - sb_end_pagefault(inode->i_sb); - return ret; -} - static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, /* @@ -138,7 +115,7 @@ static const struct vm_operations_struct ext2_dax_vm_ops = { * will always fail and fail back to regular faults. */ .page_mkwrite = ext2_dax_fault, - .pfn_mkwrite = ext2_dax_pfn_mkwrite, + .pfn_mkwrite = ext2_dax_fault, }; static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -174,15 +151,12 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) { int ret; struct super_block *sb = file->f_mapping->host->i_sb; - struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; ret = generic_file_fsync(file, start, end, datasync); - if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) { + if (ret == -EIO) /* We don't really know where the IO error happened... */ ext2_error(sb, __func__, "detected IO error when writing metadata buffers"); - ret = -EIO; - } return ret; } diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 2dcbd5698884..4dca6f348714 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -659,6 +659,7 @@ static int ext2_get_blocks(struct inode *inode, */ err = -EAGAIN; count = 0; + partial = chain + depth - 1; break; } blk = le32_to_cpu(*(chain[depth-1].p + count)); @@ -799,10 +800,10 @@ int ext2_get_block(struct inode *inode, sector_t iblock, static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap) { - struct block_device *bdev; unsigned int blkbits = inode->i_blkbits; unsigned long first_block = offset >> blkbits; unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits; + struct ext2_sb_info *sbi = EXT2_SB(inode->i_sb); bool new = false, boundary = false; u32 bno; int ret; @@ -813,13 +814,9 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, return ret; iomap->flags = 0; - bdev = inode->i_sb->s_bdev; - iomap->bdev = bdev; + iomap->bdev = inode->i_sb->s_bdev; iomap->offset = (u64)first_block << blkbits; - if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); - else - iomap->dax_dev = NULL; + iomap->dax_dev = sbi->s_daxdev; if (ret == 0) { iomap->type = IOMAP_HOLE; @@ -841,7 +838,6 @@ static int ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { - fs_put_dax(iomap->dax_dev); if (iomap->type == IOMAP_MAPPED && written < length && (flags & IOMAP_WRITE)) diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 9c2028b50e5c..1458706bd2ec 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -52,7 +52,7 @@ void ext2_error(struct super_block *sb, const char *function, struct ext2_sb_info *sbi = EXT2_SB(sb); struct ext2_super_block *es = sbi->s_es; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { spin_lock(&sbi->s_lock); sbi->s_mount_state |= EXT2_ERROR_FS; es->s_state |= cpu_to_le16(EXT2_ERROR_FS); @@ -147,11 +147,11 @@ static void ext2_put_super (struct super_block * sb) ext2_quota_off_umount(sb); - if (sbi->s_mb_cache) { - ext2_xattr_destroy_cache(sbi->s_mb_cache); - sbi->s_mb_cache = NULL; + if (sbi->s_ea_block_cache) { + ext2_xattr_destroy_cache(sbi->s_ea_block_cache); + sbi->s_ea_block_cache = NULL; } - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { struct ext2_super_block *es = sbi->s_es; spin_lock(&sbi->s_lock); @@ -171,6 +171,7 @@ static void ext2_put_super (struct super_block * sb) brelse (sbi->s_sbh); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); + fs_put_dax(sbi->s_daxdev); kfree(sbi); } @@ -813,6 +814,7 @@ static unsigned long descriptor_loc(struct super_block *sb, static int ext2_fill_super(struct super_block *sb, void *data, int silent) { + struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); struct buffer_head * bh; struct ext2_sb_info * sbi; struct ext2_super_block * es; @@ -842,6 +844,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; + sbi->s_daxdev = dax_dev; spin_lock_init(&sbi->s_lock); @@ -940,8 +943,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) le32_to_cpu(features)); goto failed_mount; } - if (!(sb->s_flags & MS_RDONLY) && - (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){ + if (!sb_rdonly(sb) && (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){ ext2_msg(sb, KERN_ERR, "error: couldn't mount RDWR because of " "unsupported optional features (%x)", le32_to_cpu(features)); @@ -1131,9 +1133,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } #ifdef CONFIG_EXT2_FS_XATTR - sbi->s_mb_cache = ext2_xattr_create_cache(); - if (!sbi->s_mb_cache) { - ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache"); + sbi->s_ea_block_cache = ext2_xattr_create_cache(); + if (!sbi->s_ea_block_cache) { + ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache"); goto failed_mount3; } #endif @@ -1170,7 +1172,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) ext2_msg(sb, KERN_WARNING, "warning: mounting ext3 filesystem as ext2"); - if (ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY)) + if (ext2_setup_super (sb, es, sb_rdonly(sb))) sb->s_flags |= MS_RDONLY; ext2_write_super(sb); return 0; @@ -1182,8 +1184,8 @@ cantfind_ext2: sb->s_id); goto failed_mount; failed_mount3: - if (sbi->s_mb_cache) - ext2_xattr_destroy_cache(sbi->s_mb_cache); + if (sbi->s_ea_block_cache) + ext2_xattr_destroy_cache(sbi->s_ea_block_cache); percpu_counter_destroy(&sbi->s_freeblocks_counter); percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); @@ -1200,6 +1202,7 @@ failed_sbi: kfree(sbi->s_blockgroup_lock); kfree(sbi); failed: + fs_put_dax(dax_dev); return ret; } @@ -1301,7 +1304,7 @@ static int ext2_unfreeze(struct super_block *sb) static void ext2_write_super(struct super_block *sb) { - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) ext2_sync_fs(sb, 1); } @@ -1339,7 +1342,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data) "dax flag with busy inodes while remounting"); sbi->s_mount_opt ^= EXT2_MOUNT_DAX; } - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) { spin_unlock(&sbi->s_lock); return 0; } diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index fbdb8f171893..1b9b1268d418 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -121,6 +121,8 @@ const struct xattr_handler *ext2_xattr_handlers[] = { NULL }; +#define EA_BLOCK_CACHE(inode) (EXT2_SB(inode->i_sb)->s_ea_block_cache) + static inline const struct xattr_handler * ext2_xattr_handler(int name_index) { @@ -150,7 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name, size_t name_len, size; char *end; int error; - struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -195,7 +197,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get", goto found; entry = next; } - if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) + if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); error = -ENODATA; goto cleanup; @@ -208,7 +210,7 @@ found: le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize) goto bad_block; - if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) + if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); if (buffer) { error = -ERANGE; @@ -246,7 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) char *end; size_t rest = buffer_size; int error; - struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -281,7 +283,7 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", goto bad_block; entry = next; } - if (ext2_xattr_cache_insert(ext2_mb_cache, bh)) + if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); /* list the attribute names */ @@ -493,8 +495,8 @@ bad_block: ext2_error(sb, "ext2_xattr_set", * This must happen under buffer lock for * ext2_xattr_set2() to reliably detect modified block */ - mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache, - hash, bh->b_blocknr); + mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash, + bh->b_blocknr); /* keep the buffer locked while modifying it. */ } else { @@ -627,7 +629,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; int error; - struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (header) { new_bh = ext2_xattr_cache_find(inode, header); @@ -655,7 +657,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, don't need to change the reference count. */ new_bh = old_bh; get_bh(new_bh); - ext2_xattr_cache_insert(ext2_mb_cache, new_bh); + ext2_xattr_cache_insert(ea_block_cache, new_bh); } else { /* We need to allocate a new block */ ext2_fsblk_t goal = ext2_group_first_block_no(sb, @@ -676,7 +678,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, memcpy(new_bh->b_data, header, new_bh->b_size); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext2_xattr_cache_insert(ext2_mb_cache, new_bh); + ext2_xattr_cache_insert(ea_block_cache, new_bh); ext2_xattr_update_super_block(sb); } @@ -721,8 +723,8 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, * This must happen under buffer lock for * ext2_xattr_set2() to reliably detect freed block */ - mb_cache_entry_delete_block(ext2_mb_cache, - hash, old_bh->b_blocknr); + mb_cache_entry_delete(ea_block_cache, hash, + old_bh->b_blocknr); /* Free the old block. */ ea_bdebug(old_bh, "freeing"); ext2_free_blocks(inode, old_bh->b_blocknr, 1); @@ -795,8 +797,8 @@ ext2_xattr_delete_inode(struct inode *inode) * This must happen under buffer lock for ext2_xattr_set2() to * reliably detect freed block */ - mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache, - hash, bh->b_blocknr); + mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash, + bh->b_blocknr); ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1); get_bh(bh); bforget(bh); @@ -897,21 +899,21 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; - struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache; + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); again: - ce = mb_cache_entry_find_first(ext2_mb_cache, hash); + ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; - bh = sb_bread(inode->i_sb, ce->e_block); + bh = sb_bread(inode->i_sb, ce->e_value); if (!bh) { ext2_error(inode->i_sb, "ext2_xattr_cache_find", "inode %ld: block %ld read error", - inode->i_ino, (unsigned long) ce->e_block); + inode->i_ino, (unsigned long) ce->e_value); } else { lock_buffer(bh); /* @@ -924,27 +926,27 @@ again: * entry is still hashed is reliable. */ if (hlist_bl_unhashed(&ce->e_hash_list)) { - mb_cache_entry_put(ext2_mb_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); unlock_buffer(bh); brelse(bh); goto again; } else if (le32_to_cpu(HDR(bh)->h_refcount) > EXT2_XATTR_REFCOUNT_MAX) { ea_idebug(inode, "block %ld refcount %d>%d", - (unsigned long) ce->e_block, + (unsigned long) ce->e_value, le32_to_cpu(HDR(bh)->h_refcount), EXT2_XATTR_REFCOUNT_MAX); } else if (!ext2_xattr_cmp(header, HDR(bh))) { ea_bdebug(bh, "b_count=%d", atomic_read(&(bh->b_count))); - mb_cache_entry_touch(ext2_mb_cache, ce); - mb_cache_entry_put(ext2_mb_cache, ce); + mb_cache_entry_touch(ea_block_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); return bh; } unlock_buffer(bh); brelse(bh); } - ce = mb_cache_entry_find_next(ext2_mb_cache, ce); + ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 3ec0e46de95f..46ff2229ff5e 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type) */ static int __ext4_set_acl(handle_t *handle, struct inode *inode, int type, - struct posix_acl *acl) + struct posix_acl *acl, int xattr_flags) { int name_index; void *value = NULL; @@ -193,13 +193,6 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - inode->i_ctime = current_time(inode); - ext4_mark_inode_dirty(handle, inode); - } break; case ACL_TYPE_DEFAULT: @@ -218,11 +211,12 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, } error = ext4_xattr_set_handle(handle, inode, name_index, "", - value, size, 0); + value, size, xattr_flags); kfree(value); - if (!error) + if (!error) { set_cached_acl(inode, type, acl); + } return error; } @@ -231,18 +225,38 @@ int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type) { handle_t *handle; - int error, retries = 0; + int error, credits, retries = 0; + size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0; + umode_t mode = inode->i_mode; + int update_mode = 0; error = dquot_initialize(inode); if (error) return error; retry: - handle = ext4_journal_start(inode, EXT4_HT_XATTR, - ext4_jbd2_credits_xattr(inode)); + error = ext4_xattr_set_credits(inode, acl_size, false /* is_create */, + &credits); + if (error) + return error; + + handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) return PTR_ERR(handle); - error = __ext4_set_acl(handle, inode, type, acl); + if ((type == ACL_TYPE_ACCESS) && acl) { + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + goto out_stop; + update_mode = 1; + } + + error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */); + if (!error && update_mode) { + inode->i_mode = mode; + inode->i_ctime = current_time(inode); + ext4_mark_inode_dirty(handle, inode); + } +out_stop: ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; @@ -267,13 +281,13 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) if (default_acl) { error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT, - default_acl); + default_acl, XATTR_CREATE); posix_acl_release(default_acl); } if (acl) { if (!error) error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS, - acl); + acl, XATTR_CREATE); posix_acl_release(acl); } return error; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index e8b365000d73..b04e882179c6 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -411,7 +411,7 @@ static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp, { struct dir_private_info *p; - p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL); + p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return NULL; p->curr_hash = pos2maj_hash(filp, pos); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 32191548abed..e2abe01c8c6b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -838,13 +838,11 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) { if (unlikely(sizeof(time->tv_sec) > 4 && (extra & cpu_to_le32(EXT4_EPOCH_MASK)))) { -#if LINUX_VERSION_CODE < KERNEL_VERSION(4,20,0) + +#if 1 /* Handle legacy encoding of pre-1970 dates with epoch - * bits 1,1. We assume that by kernel version 4.20, - * everyone will have run fsck over the affected - * filesystems to correct the problem. (This - * backwards compatibility may be removed before this - * time, at the discretion of the ext4 developers.) + * bits 1,1. (This backwards compatibility may be removed + * at the discretion of the ext4 developers.) */ u64 extra_bits = le32_to_cpu(extra) & EXT4_EPOCH_MASK; if (extra_bits == 3 && ((time->tv_sec) & 0x80000000) != 0) @@ -961,7 +959,7 @@ struct ext4_inode_info { /* * i_block_group is the number of the block group which contains * this file's inode. Constant across the lifetime of the inode, - * it is ued for making block allocation decisions - we try to + * it is used for making block allocation decisions - we try to * place a file's data blocks near its inode block, and new inodes * near to their parent directory's inode. */ @@ -1049,10 +1047,8 @@ struct ext4_inode_info { ext4_group_t i_last_alloc_group; /* allocation reservation info for delalloc */ - /* In case of bigalloc, these refer to clusters rather than blocks */ + /* In case of bigalloc, this refer to clusters rather than blocks */ unsigned int i_reserved_data_blocks; - unsigned int i_reserved_meta_blocks; - unsigned int i_allocated_meta_blocks; ext4_lblk_t i_da_metadata_calc_last_lblock; int i_da_metadata_calc_len; @@ -1114,6 +1110,7 @@ struct ext4_inode_info { /* * Mount flags set via mount options or defaults */ +#define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ @@ -1444,6 +1441,8 @@ struct ext4_sb_info { unsigned int *s_mb_maxs; unsigned int s_group_info_size; unsigned int s_mb_free_pending; + struct list_head s_freed_data_list; /* List of blocks to be freed + after commit completed */ /* tunables */ unsigned long s_stripe; @@ -1516,7 +1515,8 @@ struct ext4_sb_info { struct list_head s_es_list; /* List of inodes with reclaimable extents */ long s_es_nr_inode; struct ext4_es_stats s_es_stats; - struct mb_cache *s_mb_cache; + struct mb_cache *s_ea_block_cache; + struct mb_cache *s_ea_inode_cache; spinlock_t s_es_lock ____cacheline_aligned_in_smp; /* Ratelimit ext4 messages. */ @@ -1526,6 +1526,7 @@ struct ext4_sb_info { /* Barrier between changing inodes' journal flags and writepages ops. */ struct percpu_rw_semaphore s_journal_flag_rwsem; + struct dax_device *s_daxdev; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1565,6 +1566,7 @@ enum { nolocking */ EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */ EXT4_STATE_EXT_PRECACHED, /* extents have been precached */ + EXT4_STATE_LUSTRE_EA_INODE, /* Lustre-style ea_inode */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1797,10 +1799,12 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt, ENCRYPT) EXT4_FEATURE_INCOMPAT_EXTENTS| \ EXT4_FEATURE_INCOMPAT_64BIT| \ EXT4_FEATURE_INCOMPAT_FLEX_BG| \ + EXT4_FEATURE_INCOMPAT_EA_INODE| \ EXT4_FEATURE_INCOMPAT_MMP | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ EXT4_FEATURE_INCOMPAT_ENCRYPT | \ - EXT4_FEATURE_INCOMPAT_CSUM_SEED) + EXT4_FEATURE_INCOMPAT_CSUM_SEED | \ + EXT4_FEATURE_INCOMPAT_LARGEDIR) #define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \ EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \ EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \ @@ -2016,7 +2020,8 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) #define is_dx(dir) (ext4_has_feature_dir_index((dir)->i_sb) && \ ext4_test_inode_flag((dir), EXT4_INODE_INDEX)) -#define EXT4_DIR_LINK_MAX(dir) (!is_dx(dir) && (dir)->i_nlink >= EXT4_LINK_MAX) +#define EXT4_DIR_LINK_MAX(dir) unlikely((dir)->i_nlink >= EXT4_LINK_MAX && \ + !(ext4_has_feature_dir_nlink((dir)->i_sb) && is_dx(dir))) #define EXT4_DIR_LINK_EMPTY(dir) ((dir)->i_nlink == 2 || (dir)->i_nlink == 1) /* Legal values for the dx_root hash_version field: */ @@ -2098,6 +2103,12 @@ static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc) return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset); } +static inline bool ext4_is_quota_file(struct inode *inode) +{ + return IS_NOQUOTA(inode) && + !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL); +} + /* * This structure is stuffed into the struct file's private_data field * for directories. It is where we put information so that we can do @@ -2126,6 +2137,16 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no) */ #define ERR_BAD_DX_DIR (-(MAX_ERRNO - 1)) +/* htree levels for ext4 */ +#define EXT4_HTREE_LEVEL_COMPAT 2 +#define EXT4_HTREE_LEVEL 3 + +static inline int ext4_dir_htree_level(struct super_block *sb) +{ + return ext4_has_feature_largedir(sb) ? + EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT; +} + /* * Timeout and state flag for lazy initialization inode thread. */ @@ -2389,16 +2410,17 @@ extern int ext4fs_dirhash(const char *name, int len, struct /* ialloc.c */ extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t, const struct qstr *qstr, __u32 goal, - uid_t *owner, int handle_type, - unsigned int line_no, int nblocks); + uid_t *owner, __u32 i_flags, + int handle_type, unsigned int line_no, + int nblocks); -#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \ +#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \ __ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \ - 0, 0, 0) + i_flags, 0, 0, 0) #define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \ type, nblocks) \ __ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \ - (type), __LINE__, (nblocks)) + 0, (type), __LINE__, (nblocks)) extern void ext4_free_inode(handle_t *, struct inode *); @@ -2433,11 +2455,14 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb, extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, ext4_fsblk_t block, unsigned long count); extern int ext4_trim_fs(struct super_block *, struct fstrim_range *); +extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid); /* inode.c */ int ext4_inode_is_fast_symlink(struct inode *inode); struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int); struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int); +int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, + bool wait, struct buffer_head **bhs); int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); int ext4_get_block(struct inode *inode, sector_t iblock, @@ -2704,19 +2729,20 @@ extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group, extern int ext4_register_li_request(struct super_block *sb, ext4_group_t first_not_zeroed); -static inline int ext4_has_group_desc_csum(struct super_block *sb) -{ - return ext4_has_feature_gdt_csum(sb) || - EXT4_SB(sb)->s_chksum_driver != NULL; -} - static inline int ext4_has_metadata_csum(struct super_block *sb) { WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) && !EXT4_SB(sb)->s_chksum_driver); - return (EXT4_SB(sb)->s_chksum_driver != NULL); + return ext4_has_feature_metadata_csum(sb) && + (EXT4_SB(sb)->s_chksum_driver != NULL); } + +static inline int ext4_has_group_desc_csum(struct super_block *sb) +{ + return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb); +} + static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) | @@ -2756,13 +2782,15 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es, es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32); } -static inline loff_t ext4_isize(struct ext4_inode *raw_inode) +static inline loff_t ext4_isize(struct super_block *sb, + struct ext4_inode *raw_inode) { - if (S_ISREG(le16_to_cpu(raw_inode->i_mode))) + if (ext4_has_feature_largedir(sb) || + S_ISREG(le16_to_cpu(raw_inode->i_mode))) return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) | le32_to_cpu(raw_inode->i_size_lo); - else - return (loff_t) le32_to_cpu(raw_inode->i_size_lo); + + return (loff_t) le32_to_cpu(raw_inode->i_size_lo); } static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size) @@ -3047,7 +3075,7 @@ extern int ext4_handle_dirty_dirent_node(handle_t *handle, struct inode *inode, struct buffer_head *bh); #define S_SHIFT 12 -static const unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = { +static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { [S_IFREG >> S_SHIFT] = EXT4_FT_REG_FILE, [S_IFDIR >> S_SHIFT] = EXT4_FT_DIR, [S_IFCHR >> S_SHIFT] = EXT4_FT_CHRDEV, diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index dd106b1d5d89..5b342ac67d2e 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -47,7 +47,7 @@ static int ext4_journal_check_start(struct super_block *sb) if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) return -EIO; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index f97611171023..48143e32411c 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -77,7 +77,14 @@ #define EXT4_RESERVE_TRANS_BLOCKS 12U -#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 8 +/* + * Number of credits needed if we need to insert an entry into a + * directory. For each new index block, we need 4 blocks (old index + * block, new index block, bitmap block, bg summary). For normal + * htree directories there are 2 levels; if the largedir feature + * enabled it's 3 levels. + */ +#define EXT4_INDEX_EXTRA_TRANS_BLOCKS 12U #ifdef CONFIG_QUOTA /* Amount of blocks needed for quota update - we know that the structure was @@ -104,20 +111,6 @@ #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb)) #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb)) -static inline int ext4_jbd2_credits_xattr(struct inode *inode) -{ - int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb); - - /* - * In case of inline data, we may push out the data to a block, - * so we need to reserve credits for this eventuality - */ - if (ext4_has_inline_data(inode)) - credits += ext4_writepage_trans_blocks(inode) + 1; - return credits; -} - - /* * Ext4 handle operation types -- for logging purposes */ @@ -234,6 +227,9 @@ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode); +int ext4_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc *iloc); /* * Wrapper functions with which ext4 calls into JBD. */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 3e36508610b7..97f0fd06728d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2488,7 +2488,8 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int extents) static inline int get_default_free_blocks_flags(struct inode *inode) { - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || + ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; else if (ext4_should_journal_data(inode)) return EXT4_FREE_BLOCKS_FORGET; @@ -4651,7 +4652,7 @@ retry: static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, ext4_lblk_t len, loff_t new_size, - int flags, int mode) + int flags) { struct inode *inode = file_inode(file); handle_t *handle; @@ -4814,7 +4815,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, round_down(offset, 1 << blkbits) >> blkbits, (round_up((offset + len), 1 << blkbits) - round_down(offset, 1 << blkbits)) >> blkbits, - new_size, flags, mode); + new_size, flags); if (ret) goto out_dio; @@ -4840,7 +4841,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, inode->i_mtime = inode->i_ctime = current_time(inode); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, - flags, mode); + flags); up_write(&EXT4_I(inode)->i_mmap_sem); if (ret) goto out_dio; @@ -4975,8 +4976,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) ext4_inode_block_unlocked_dio(inode); inode_dio_wait(inode); - ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, - flags, mode); + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); ext4_inode_resume_unlocked_dio(inode); if (ret) goto out; @@ -5836,7 +5836,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, if (e1_blk > lblk1) next1 = e1_blk; if (e2_blk > lblk2) - next2 = e1_blk; + next2 = e2_blk; /* Do we have something to swap */ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS) goto finish; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 02ce7e7bbdf5..b1da660ac3bc 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -37,7 +37,11 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; - inode_lock_shared(inode); + if (!inode_trylock_shared(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock_shared(inode); + } /* * Recheck under inode lock - at this point we are sure it cannot * change anymore @@ -179,7 +183,11 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file_inode(iocb->ki_filp); ssize_t ret; - inode_lock(inode); + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; @@ -215,8 +223,15 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (IS_DAX(inode)) return ext4_dax_write_iter(iocb, from); #endif + if (!o_direct && (iocb->ki_flags & IOCB_NOWAIT)) + return -EOPNOTSUPP; + + if (!inode_trylock(inode)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + inode_lock(inode); + } - inode_lock(inode); ret = ext4_write_checks(iocb, from); if (ret <= 0) goto out; @@ -235,9 +250,15 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) iocb->private = &overwrite; /* Check whether we do a DIO overwrite or not */ - if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio && - ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) - overwrite = 1; + if (o_direct && !unaligned_aio) { + if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) { + if (ext4_should_dioread_nolock(inode)) + overwrite = 1; + } else if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } + } ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); @@ -260,7 +281,20 @@ static int ext4_dax_huge_fault(struct vm_fault *vmf, handle_t *handle = NULL; struct inode *inode = file_inode(vmf->vma->vm_file); struct super_block *sb = inode->i_sb; - bool write = vmf->flags & FAULT_FLAG_WRITE; + + /* + * We have to distinguish real writes from writes which will result in a + * COW page; COW writes should *not* poke the journal (the file will not + * be changed). Doing so would cause unintended failures when mounted + * read-only. + * + * We check for VM_SHARED rather than vmf->cow_page since the latter is + * unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for + * other sizes, dax_iomap_fault will handle splitting / fallback so that + * we eventually come back with a COW page. + */ + bool write = (vmf->flags & FAULT_FLAG_WRITE) && + (vmf->vma->vm_flags & VM_SHARED); if (write) { sb_start_pagefault(sb); @@ -292,41 +326,11 @@ static int ext4_dax_fault(struct vm_fault *vmf) return ext4_dax_huge_fault(vmf, PE_SIZE_PTE); } -/* - * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault() - * handler we check for races agaist truncate. Note that since we cycle through - * i_mmap_sem, we are sure that also any hole punching that began before we - * were called is finished by now and so if it included part of the file we - * are working on, our pte will get unmapped and the check for pte_same() in - * wp_pfn_shared() fails. Thus fault gets retried and things work out as - * desired. - */ -static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vmf->vma->vm_file); - struct super_block *sb = inode->i_sb; - loff_t size; - int ret; - - sb_start_pagefault(sb); - file_update_time(vmf->vma->vm_file); - down_read(&EXT4_I(inode)->i_mmap_sem); - size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; - if (vmf->pgoff >= size) - ret = VM_FAULT_SIGBUS; - else - ret = dax_pfn_mkwrite(vmf); - up_read(&EXT4_I(inode)->i_mmap_sem); - sb_end_pagefault(sb); - - return ret; -} - static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .huge_fault = ext4_dax_huge_fault, .page_mkwrite = ext4_dax_fault, - .pfn_mkwrite = ext4_dax_pfn_mkwrite, + .pfn_mkwrite = ext4_dax_fault, }; #else #define ext4_dax_vm_ops ext4_file_vm_ops @@ -345,13 +349,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; - if (ext4_encrypted_inode(inode)) { - int err = fscrypt_get_encryption_info(inode); - if (err) - return 0; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; @@ -376,7 +373,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp) return -EIO; if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) && - !(sb->s_flags & MS_RDONLY))) { + !sb_rdonly(sb))) { sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; /* * Sample where the filesystem has been mounted and @@ -435,6 +432,8 @@ static int ext4_file_open(struct inode * inode, struct file * filp) if (ret < 0) return ret; } + + filp->f_mode |= FMODE_NOWAIT; return dquot_file_open(inode, filp); } @@ -478,12 +477,11 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, pagevec_init(&pvec, 0); do { - int i, num; + int i; unsigned long nr_pages; - num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, - (pgoff_t)num); + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, + &index, end); if (nr_pages == 0) break; @@ -502,9 +500,6 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, goto out; } - if (page->index > end) - goto out; - lock_page(page); if (unlikely(page->mapping != inode->i_mapping)) { @@ -521,6 +516,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, lastoff = page_offset(page); bh = head = page_buffers(page); do { + if (lastoff + bh->b_size <= startoff) + goto next; if (buffer_uptodate(bh) || buffer_unwritten(bh)) { if (whence == SEEK_DATA) @@ -535,6 +532,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); goto out; } +next: lastoff += bh->b_size; bh = bh->b_this_page; } while (bh != head); @@ -544,14 +542,10 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); } - /* The no. of pages is less than our desired, we are done. */ - if (nr_pages < num) - break; - - index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + /* There are no pages upto endoff - that would be a hole in there. */ if (whence == SEEK_HOLE && lastoff < endoff) { found = 1; *offset = lastoff; @@ -576,7 +570,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize) inode_lock(inode); isize = i_size_read(inode); - if (offset >= isize) { + if (offset < 0 || offset >= isize) { inode_unlock(inode); return -ENXIO; } @@ -639,7 +633,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize) inode_lock(inode); isize = i_size_read(inode); - if (offset >= isize) { + if (offset < 0 || offset >= isize) { inode_unlock(inode); return -ENXIO; } diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index b19436098837..7ec340898598 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -480,6 +480,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start_fsb; ext4_fsblk_t end_fsb; + ext4_fsblk_t bofs; ext4_fsblk_t eofs; ext4_group_t start_ag; ext4_group_t end_ag; @@ -487,9 +488,12 @@ static int ext4_getfsmap_datadev(struct super_block *sb, ext4_grpblk_t last_cluster; int error = 0; + bofs = le32_to_cpu(sbi->s_es->s_first_data_block); eofs = ext4_blocks_count(sbi->s_es); if (keys[0].fmr_physical >= eofs) return 0; + else if (keys[0].fmr_physical < bofs) + keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; start_fsb = keys[0].fmr_physical; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 9d549608fd30..f9230580a84b 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -107,7 +107,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) trace_ext4_sync_file_enter(file, datasync); - if (inode->i_sb->s_flags & MS_RDONLY) { + if (sb_rdonly(inode->i_sb)) { /* Make sure that we read updated s_mount_flags value */ smp_rmb(); if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED) @@ -124,7 +124,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); if (ret) return ret; /* diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 38b8a96eb97c..00c6dd29e621 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -148,8 +148,6 @@ static void str2hashbuf_signed(const char *msg, int len, __u32 *buf, int num) if (len > num*4) len = num * 4; for (i = 0; i < len; i++) { - if ((i % 4) == 0) - val = pad; val = ((int) scp[i]) + (val << 8); if ((i % 4) == 3) { *buf++ = val; @@ -176,8 +174,6 @@ static void str2hashbuf_unsigned(const char *msg, int len, __u32 *buf, int num) if (len > num*4) len = num * 4; for (i = 0; i < len; i++) { - if ((i % 4) == 0) - val = pad; val = ((int) ucp[i]) + (val << 8); if ((i % 4) == 3) { *buf++ = val; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 98ac2f1f23b3..ee823022aa34 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -294,7 +294,6 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) * as writing the quota to disk may need the lock as well. */ dquot_initialize(inode); - ext4_xattr_delete_inode(handle, inode); dquot_free_inode(inode); dquot_drop(inode); @@ -693,24 +692,25 @@ static int find_group_other(struct super_block *sb, struct inode *parent, * somewhat arbitrary...) */ #define RECENTCY_MIN 5 -#define RECENTCY_DIRTY 30 +#define RECENTCY_DIRTY 300 static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) { struct ext4_group_desc *gdp; struct ext4_inode *raw_inode; struct buffer_head *bh; - unsigned long dtime, now; - int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; - int offset, ret = 0, recentcy = RECENTCY_MIN; + int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; + int offset, ret = 0; + int recentcy = RECENTCY_MIN; + u32 dtime, now; gdp = ext4_get_group_desc(sb, group, NULL); if (unlikely(!gdp)) return 0; - bh = sb_getblk(sb, ext4_inode_table(sb, gdp) + + bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) + (ino / inodes_per_block)); - if (unlikely(!bh) || !buffer_uptodate(bh)) + if (!bh || !buffer_uptodate(bh)) /* * If the block is not in the buffer cache, then it * must have been written out. @@ -719,18 +719,45 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb); raw_inode = (struct ext4_inode *) (bh->b_data + offset); + + /* i_dtime is only 32 bits on disk, but we only care about relative + * times in the range of a few minutes (i.e. long enough to sync a + * recently-deleted inode to disk), so using the low 32 bits of the + * clock (a 68 year range) is enough, see time_before32() */ dtime = le32_to_cpu(raw_inode->i_dtime); - now = get_seconds(); + now = ktime_get_real_seconds(); if (buffer_dirty(bh)) recentcy += RECENTCY_DIRTY; - if (dtime && (dtime < now) && (now < dtime + recentcy)) + if (dtime && time_before32(dtime, now) && + time_before32(now, dtime + recentcy)) ret = 1; out: brelse(bh); return ret; } +static int find_inode_bit(struct super_block *sb, ext4_group_t group, + struct buffer_head *bitmap, unsigned long *ino) +{ +next: + *ino = ext4_find_next_zero_bit((unsigned long *) + bitmap->b_data, + EXT4_INODES_PER_GROUP(sb), *ino); + if (*ino >= EXT4_INODES_PER_GROUP(sb)) + return 0; + + if ((EXT4_SB(sb)->s_journal == NULL) && + recently_deleted(sb, group, *ino)) { + *ino = *ino + 1; + if (*ino < EXT4_INODES_PER_GROUP(sb)) + goto next; + return 0; + } + + return 1; +} + /* * There are two policies for allocating an inode. If the new inode is * a directory, then a forward search is made for a block group with both @@ -743,8 +770,9 @@ out: */ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, umode_t mode, const struct qstr *qstr, - __u32 goal, uid_t *owner, int handle_type, - unsigned int line_no, int nblocks) + __u32 goal, uid_t *owner, __u32 i_flags, + int handle_type, unsigned int line_no, + int nblocks) { struct super_block *sb; struct buffer_head *inode_bitmap_bh = NULL; @@ -766,30 +794,69 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, if (!dir || !dir->i_nlink) return ERR_PTR(-EPERM); - if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) + sb = dir->i_sb; + sbi = EXT4_SB(sb); + + if (unlikely(ext4_forced_shutdown(sbi))) return ERR_PTR(-EIO); - if ((ext4_encrypted_inode(dir) || - DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) && - (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) { + if ((ext4_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) && + !(i_flags & EXT4_EA_INODE_FL)) { err = fscrypt_get_encryption_info(dir); if (err) return ERR_PTR(err); if (!fscrypt_has_encryption_key(dir)) return ERR_PTR(-ENOKEY); - if (!handle) - nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb); encrypt = 1; } - sb = dir->i_sb; + if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) { +#ifdef CONFIG_EXT4_FS_POSIX_ACL + struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT); + + if (p) { + int acl_size = p->a_count * sizeof(ext4_acl_entry); + + nblocks += (S_ISDIR(mode) ? 2 : 1) * + __ext4_xattr_set_credits(sb, NULL /* inode */, + NULL /* block_bh */, acl_size, + true /* is_create */); + posix_acl_release(p); + } +#endif + +#ifdef CONFIG_SECURITY + { + int num_security_xattrs = 1; + +#ifdef CONFIG_INTEGRITY + num_security_xattrs++; +#endif + /* + * We assume that security xattrs are never + * more than 1k. In practice they are under + * 128 bytes. + */ + nblocks += num_security_xattrs * + __ext4_xattr_set_credits(sb, NULL /* inode */, + NULL /* block_bh */, 1024, + true /* is_create */); + } +#endif + if (encrypt) + nblocks += __ext4_xattr_set_credits(sb, + NULL /* inode */, NULL /* block_bh */, + FSCRYPT_SET_CONTEXT_MAX_SIZE, + true /* is_create */); + } + ngroups = ext4_get_groups_count(sb); trace_ext4_request_inode(dir, mode); inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOMEM); ei = EXT4_I(inode); - sbi = EXT4_SB(sb); /* * Initialize owners and quota early so that we don't have to account @@ -853,19 +920,13 @@ got_group: /* * Check free inodes count before loading bitmap. */ - if (ext4_free_inodes_count(sb, gdp) == 0) { - if (++group == ngroups) - group = 0; - continue; - } + if (ext4_free_inodes_count(sb, gdp) == 0) + goto next_group; grp = ext4_get_group_info(sb, group); /* Skip groups with already-known suspicious inode tables */ - if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { - if (++group == ngroups) - group = 0; - continue; - } + if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) + goto next_group; brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); @@ -873,27 +934,20 @@ got_group: if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || IS_ERR(inode_bitmap_bh)) { inode_bitmap_bh = NULL; - if (++group == ngroups) - group = 0; - continue; + goto next_group; } repeat_in_this_group: - ino = ext4_find_next_zero_bit((unsigned long *) - inode_bitmap_bh->b_data, - EXT4_INODES_PER_GROUP(sb), ino); - if (ino >= EXT4_INODES_PER_GROUP(sb)) + ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino); + if (!ret2) goto next_group; - if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) { + + if (group == 0 && (ino + 1) < EXT4_FIRST_INO(sb)) { ext4_error(sb, "reserved inode found cleared - " "inode=%lu", ino + 1); - continue; - } - if ((EXT4_SB(sb)->s_journal == NULL) && - recently_deleted(sb, group, ino)) { - ino++; - goto next_inode; + goto next_group; } + if (!handle) { BUG_ON(nblocks <= 0); handle = __ext4_journal_start_sb(dir->i_sb, line_no, @@ -913,11 +967,23 @@ repeat_in_this_group: } ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); + if (ret2) { + /* Someone already took the bit. Repeat the search + * with lock held. + */ + ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino); + if (ret2) { + ext4_set_bit(ino, inode_bitmap_bh->b_data); + ret2 = 0; + } else { + ret2 = 1; /* we didn't grab the inode */ + } + } ext4_unlock_group(sb, group); ino++; /* the inode bitmap is zero-based */ if (!ret2) goto got; /* we grabbed the inode! */ -next_inode: + if (ino < EXT4_INODES_PER_GROUP(sb)) goto repeat_in_this_group; next_group: @@ -1053,6 +1119,7 @@ got: /* Don't inherit extent flag from directory, amongst others. */ ei->i_flags = ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED); + ei->i_flags |= i_flags; ei->i_file_acl = 0; ei->i_dtime = 0; ei->i_block_group = group; @@ -1109,13 +1176,15 @@ got: goto fail_free_drop; } - err = ext4_init_acl(handle, inode, dir); - if (err) - goto fail_free_drop; + if (!(ei->i_flags & EXT4_EA_INODE_FL)) { + err = ext4_init_acl(handle, inode, dir); + if (err) + goto fail_free_drop; - err = ext4_init_security(handle, inode, dir, qstr); - if (err) - goto fail_free_drop; + err = ext4_init_security(handle, inode, dir, qstr); + if (err) + goto fail_free_drop; + } if (ext4_has_feature_extents(sb)) { /* set extent flag only for directory, file and normal symlink*/ @@ -1313,7 +1382,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, int num, ret = 0, used_blks = 0; /* This should not happen, but just to be sure check this */ - if (sb->s_flags & MS_RDONLY) { + if (sb_rdonly(sb)) { ret = 1; goto out; } diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index bc15c2c17633..7ffa290cbb8e 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -829,7 +829,8 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, int flags = EXT4_FREE_BLOCKS_VALIDATED; int err; - if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) + if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || + ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA; else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 8d141c0c8ff9..28c5c3abddb3 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -61,7 +61,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode, /* Compute min_offs. */ for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { - if (!entry->e_value_block && entry->e_value_size) { + if (!entry->e_value_inum && entry->e_value_size) { size_t offs = le16_to_cpu(entry->e_value_offs); if (offs < min_offs) min_offs = offs; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5cf82d03968c..31db875bc7a1 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -144,16 +144,12 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, /* * Test whether an inode is a fast symlink. + * A fast symlink has its symlink data stored in ext4_inode_info->i_data. */ int ext4_inode_is_fast_symlink(struct inode *inode) { - int ea_blocks = EXT4_I(inode)->i_file_acl ? - EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; - - if (ext4_has_inline_data(inode)) - return 0; - - return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); + return S_ISLNK(inode->i_mode) && inode->i_size && + (inode->i_size < EXT4_N_BLOCKS * 4); } /* @@ -189,6 +185,8 @@ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; + int extra_credits = 3; + struct ext4_xattr_inode_array *ea_inode_array = NULL; trace_ext4_evict_inode(inode); @@ -213,7 +211,8 @@ void ext4_evict_inode(struct inode *inode) */ if (inode->i_ino != EXT4_JOURNAL_INO && ext4_should_journal_data(inode) && - (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) { + (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) && + inode->i_data.nrpages) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid = EXT4_I(inode)->i_datasync_tid; @@ -238,8 +237,12 @@ void ext4_evict_inode(struct inode *inode) * protection against it */ sb_start_intwrite(inode->i_sb); + + if (!IS_NOQUOTA(inode)) + extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); + handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, - ext4_blocks_for_truncate(inode)+3); + ext4_blocks_for_truncate(inode)+extra_credits); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* @@ -254,6 +257,16 @@ void ext4_evict_inode(struct inode *inode) if (IS_SYNC(inode)) ext4_handle_sync(handle); + + /* + * Set inode->i_size to 0 before calling ext4_truncate(). We need + * special handling of symlinks here because i_size is used to + * determine whether ext4_inode_info->i_data contains symlink data or + * block mappings. Setting i_size to 0 will remove its fast symlink + * status. Erase i_data so that it becomes a valid empty block map. + */ + if (ext4_inode_is_fast_symlink(inode)) + memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data)); inode->i_size = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) { @@ -271,25 +284,17 @@ void ext4_evict_inode(struct inode *inode) } } - /* - * ext4_ext_truncate() doesn't reserve any slop when it - * restarts journal transactions; therefore there may not be - * enough credits left in the handle to remove the inode from - * the orphan list and set the dtime field. - */ - if (!ext4_handle_has_enough_credits(handle, 3)) { - err = ext4_journal_extend(handle, 3); - if (err > 0) - err = ext4_journal_restart(handle, 3); - if (err != 0) { - ext4_warning(inode->i_sb, - "couldn't extend journal (err %d)", err); - stop_handle: - ext4_journal_stop(handle); - ext4_orphan_del(NULL, inode); - sb_end_intwrite(inode->i_sb); - goto no_delete; - } + /* Remove xattr references. */ + err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array, + extra_credits); + if (err) { + ext4_warning(inode->i_sb, "xattr delete (err %d)", err); +stop_handle: + ext4_journal_stop(handle); + ext4_orphan_del(NULL, inode); + sb_end_intwrite(inode->i_sb); + ext4_xattr_inode_array_free(ea_inode_array); + goto no_delete; } /* @@ -317,6 +322,7 @@ void ext4_evict_inode(struct inode *inode) ext4_free_inode(handle, inode); ext4_journal_stop(handle); sb_end_intwrite(inode->i_sb); + ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ @@ -710,7 +716,7 @@ out_sem: if (map->m_flags & EXT4_MAP_NEW && !(map->m_flags & EXT4_MAP_UNWRITTEN) && !(flags & EXT4_GET_BLOCKS_ZERO) && - !IS_NOQUOTA(inode) && + !ext4_is_quota_file(inode) && ext4_should_order_data(inode)) { if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) ret = ext4_jbd2_inode_add_wait(handle, inode); @@ -886,7 +892,7 @@ static int ext4_dio_get_block_unwritten_async(struct inode *inode, /* * Get block function for non-AIO DIO writes when we create unwritten extent if * blocks are not allocated yet. The extent will be converted to written - * after IO is complete from ext4_ext_direct_IO() function. + * after IO is complete by ext4_direct_IO_write(). */ static int ext4_dio_get_block_unwritten_sync(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) @@ -901,7 +907,7 @@ static int ext4_dio_get_block_unwritten_sync(struct inode *inode, /* * Mark inode as having pending DIO writes to unwritten extents. - * ext4_ext_direct_IO() checks this flag and converts extents to + * ext4_direct_IO_write() checks this flag and converts extents to * written. */ if (!ret && buffer_unwritten(bh_result)) @@ -1009,6 +1015,50 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return ERR_PTR(-EIO); } +/* Read a contiguous batch of blocks. */ +int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, + bool wait, struct buffer_head **bhs) +{ + int i, err; + + for (i = 0; i < bh_count; i++) { + bhs[i] = ext4_getblk(NULL, inode, block + i, 0 /* map_flags */); + if (IS_ERR(bhs[i])) { + err = PTR_ERR(bhs[i]); + bh_count = i; + goto out_brelse; + } + } + + for (i = 0; i < bh_count; i++) + /* Note that NULL bhs[i] is valid because of holes. */ + if (bhs[i] && !buffer_uptodate(bhs[i])) + ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, + &bhs[i]); + + if (!wait) + return 0; + + for (i = 0; i < bh_count; i++) + if (bhs[i]) + wait_on_buffer(bhs[i]); + + for (i = 0; i < bh_count; i++) { + if (bhs[i] && !buffer_uptodate(bhs[i])) { + err = -EIO; + goto out_brelse; + } + } + return 0; + +out_brelse: + for (i = 0; i < bh_count; i++) { + brelse(bhs[i]); + bhs[i] = NULL; + } + return err; +} + int ext4_walk_page_buffers(handle_t *handle, struct buffer_head *head, unsigned from, @@ -1670,13 +1720,12 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, pagevec_init(&pvec, 0); while (index <= end) { - nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); + nr_pages = pagevec_lookup_range(&pvec, mapping, &index, end); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (page->index > end) - break; + BUG_ON(!PageLocked(page)); BUG_ON(PageWriteback(page)); if (invalidate) { @@ -1687,7 +1736,6 @@ static void mpage_release_unused_pages(struct mpage_da_data *mpd, } unlock_page(page); } - index = pvec.pages[nr_pages - 1]->index + 1; pagevec_release(&pvec); } } @@ -2298,17 +2346,13 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) pagevec_init(&pvec, 0); while (start <= end) { - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, start, - PAGEVEC_SIZE); + nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, + &start, end); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; - if (page->index > end) - break; - /* Up to 'end' pages must be contiguous */ - BUG_ON(page->index != start); bh = head = page_buffers(page); do { if (lblk < mpd->map.m_lblk) @@ -2353,7 +2397,6 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) pagevec_release(&pvec); return err; } - start++; } pagevec_release(&pvec); } @@ -3354,7 +3397,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait) static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap) { - struct block_device *bdev; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int blkbits = inode->i_blkbits; unsigned long first_block = offset >> blkbits; unsigned long last_block = (offset + length - 1) >> blkbits; @@ -3423,12 +3466,8 @@ retry: } iomap->flags = 0; - bdev = inode->i_sb->s_bdev; - iomap->bdev = bdev; - if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); - else - iomap->dax_dev = NULL; + iomap->bdev = inode->i_sb->s_bdev; + iomap->dax_dev = sbi->s_daxdev; iomap->offset = first_block << blkbits; if (ret == 0) { @@ -3461,7 +3500,6 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, int blkbits = inode->i_blkbits; bool truncate = false; - fs_put_dax(iomap->dax_dev); if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT)) return 0; @@ -4712,7 +4750,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (ext4_has_feature_64bit(sb)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; - inode->i_size = ext4_isize(raw_inode); + inode->i_size = ext4_isize(sb, raw_inode); if ((size = i_size_read(inode)) < 0) { EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size); ret = -EFSCORRUPTED; @@ -4846,6 +4884,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } brelse(iloc.bh); ext4_set_inode_flags(inode); + unlock_new_inode(inode); return inode; @@ -5037,7 +5076,7 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - if (ei->i_disksize != ext4_isize(raw_inode)) { + if (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) { ext4_isize_set(raw_inode, ei->i_disksize); need_datasync = 1; } @@ -5287,7 +5326,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) error = PTR_ERR(handle); goto err_out; } + + /* dquot_transfer() calls back ext4_get_inode_usage() which + * counts xattr inode references. + */ + down_read(&EXT4_I(inode)->xattr_sem); error = dquot_transfer(inode, attr); + up_read(&EXT4_I(inode)->xattr_sem); + if (error) { ext4_journal_stop(handle); return error; @@ -5307,6 +5353,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) loff_t oldsize = inode->i_size; int shrink = (attr->ia_size <= inode->i_size); + if (ext4_encrypted_inode(inode)) { + error = fscrypt_get_encryption_info(inode); + if (error) + return error; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -5628,22 +5682,16 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode, return err; } -/* - * Expand an inode by new_extra_isize bytes. - * Returns 0 on success or negative error number on failure. - */ -static int ext4_expand_extra_isize(struct inode *inode, - unsigned int new_extra_isize, - struct ext4_iloc iloc, - handle_t *handle) +static int __ext4_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc *iloc, + handle_t *handle, int *no_expand) { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; + int error; - if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) - return 0; - - raw_inode = ext4_raw_inode(&iloc); + raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); @@ -5658,8 +5706,98 @@ static int ext4_expand_extra_isize(struct inode *inode, } /* try to expand with EAs present */ - return ext4_expand_extra_isize_ea(inode, new_extra_isize, - raw_inode, handle); + error = ext4_expand_extra_isize_ea(inode, new_extra_isize, + raw_inode, handle); + if (error) { + /* + * Inode size expansion failed; don't try again + */ + *no_expand = 1; + } + + return error; +} + +/* + * Expand an inode by new_extra_isize bytes. + * Returns 0 on success or negative error number on failure. + */ +static int ext4_try_to_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc iloc, + handle_t *handle) +{ + int no_expand; + int error; + + if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) + return -EOVERFLOW; + + /* + * In nojournal mode, we can immediately attempt to expand + * the inode. When journaled, we first need to obtain extra + * buffer credits since we may write into the EA block + * with this same handle. If journal_extend fails, then it will + * only result in a minor loss of functionality for that inode. + * If this is felt to be critical, then e2fsck should be run to + * force a large enough s_min_extra_isize. + */ + if (ext4_handle_valid(handle) && + jbd2_journal_extend(handle, + EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) != 0) + return -ENOSPC; + + if (ext4_write_trylock_xattr(inode, &no_expand) == 0) + return -EBUSY; + + error = __ext4_expand_extra_isize(inode, new_extra_isize, &iloc, + handle, &no_expand); + ext4_write_unlock_xattr(inode, &no_expand); + + return error; +} + +int ext4_expand_extra_isize(struct inode *inode, + unsigned int new_extra_isize, + struct ext4_iloc *iloc) +{ + handle_t *handle; + int no_expand; + int error, rc; + + if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { + brelse(iloc->bh); + return -EOVERFLOW; + } + + handle = ext4_journal_start(inode, EXT4_HT_INODE, + EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); + if (IS_ERR(handle)) { + error = PTR_ERR(handle); + brelse(iloc->bh); + return error; + } + + ext4_write_lock_xattr(inode, &no_expand); + + BUFFER_TRACE(iloc.bh, "get_write_access"); + error = ext4_journal_get_write_access(handle, iloc->bh); + if (error) { + brelse(iloc->bh); + goto out_stop; + } + + error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc, + handle, &no_expand); + + rc = ext4_mark_iloc_dirty(handle, inode, iloc); + if (!error) + error = rc; + + ext4_write_unlock_xattr(inode, &no_expand); +out_stop: + ext4_journal_stop(handle); + return error; } /* @@ -5679,44 +5817,18 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { struct ext4_iloc iloc; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); - static unsigned int mnt_count; - int err, ret; + int err; might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) return err; - if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize && - !ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { - /* - * In nojournal mode, we can immediately attempt to expand - * the inode. When journaled, we first need to obtain extra - * buffer credits since we may write into the EA block - * with this same handle. If journal_extend fails, then it will - * only result in a minor loss of functionality for that inode. - * If this is felt to be critical, then e2fsck should be run to - * force a large enough s_min_extra_isize. - */ - if (!ext4_handle_valid(handle) || - jbd2_journal_extend(handle, - EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) == 0) { - ret = ext4_expand_extra_isize(inode, - sbi->s_want_extra_isize, - iloc, handle); - if (ret) { - if (mnt_count != - le16_to_cpu(sbi->s_es->s_mnt_count)) { - ext4_warning(inode->i_sb, - "Unable to expand inode %lu. Delete" - " some EAs or run e2fsck.", - inode->i_ino); - mnt_count = - le16_to_cpu(sbi->s_es->s_mnt_count); - } - } - } - } + + if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize) + ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize, + iloc, handle); + return ext4_mark_iloc_dirty(handle, inode, &iloc); } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0c21e22acd74..afb66d4ab5cf 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -64,18 +64,16 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2) ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); - memswap(&inode1->i_flags, &inode2->i_flags, sizeof(inode1->i_flags)); - memswap(&inode1->i_version, &inode2->i_version, - sizeof(inode1->i_version)); - memswap(&inode1->i_blocks, &inode2->i_blocks, - sizeof(inode1->i_blocks)); - memswap(&inode1->i_bytes, &inode2->i_bytes, sizeof(inode1->i_bytes)); - memswap(&inode1->i_atime, &inode2->i_atime, sizeof(inode1->i_atime)); - memswap(&inode1->i_mtime, &inode2->i_mtime, sizeof(inode1->i_mtime)); + swap(inode1->i_flags, inode2->i_flags); + swap(inode1->i_version, inode2->i_version); + swap(inode1->i_blocks, inode2->i_blocks); + swap(inode1->i_bytes, inode2->i_bytes); + swap(inode1->i_atime, inode2->i_atime); + swap(inode1->i_mtime, inode2->i_mtime); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); - memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags)); - memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize)); + swap(ei1->i_flags, ei2->i_flags); + swap(ei1->i_disksize, ei2->i_disksize); ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS); ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS); @@ -218,7 +216,7 @@ static int ext4_ioctl_setflags(struct inode *inode, unsigned int jflag; /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) + if (ext4_is_quota_file(inode)) goto flags_out; oldflags = ei->i_flags; @@ -342,7 +340,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) err = -EPERM; inode_lock(inode); /* Is it quota file? Do not allow user to mess with it */ - if (IS_NOQUOTA(inode)) + if (ext4_is_quota_file(inode)) goto out_unlock; err = ext4_get_inode_loc(inode, &iloc); @@ -351,11 +349,14 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) raw_inode = ext4_raw_inode(&iloc); if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) { - err = -EOVERFLOW; + err = ext4_expand_extra_isize(inode, + EXT4_SB(sb)->s_want_extra_isize, + &iloc); + if (err) + goto out_unlock; + } else { brelse(iloc.bh); - goto out_unlock; } - brelse(iloc.bh); dquot_initialize(inode); @@ -373,7 +374,13 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { + + /* __dquot_transfer() calls back ext4_get_inode_usage() which + * counts xattr inode references. + */ + down_read(&EXT4_I(inode)->xattr_sem); err = __dquot_transfer(inode, transfer_to); + up_read(&EXT4_I(inode)->xattr_sem); dqput(transfer_to[PRJQUOTA]); if (err) goto out_dirty; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index b7928cddd539..701085620cd8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -367,8 +367,6 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_group_t group); static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap, ext4_group_t group); -static void ext4_free_data_callback(struct super_block *sb, - struct ext4_journal_cb_entry *jce, int rc); static inline void *mb_correct_addr_and_bit(int *bit, void *addr) { @@ -2297,6 +2295,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) int err, buddy_loaded = 0; struct ext4_buddy e4b; struct ext4_group_info *grinfo; + unsigned char blocksize_bits = min_t(unsigned char, + sb->s_blocksize_bits, + EXT4_MAX_BLOCK_LOG_SIZE); struct sg { struct ext4_group_info info; ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; @@ -2308,8 +2309,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); - i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + + i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); + grinfo = ext4_get_group_info(sb, group); /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { @@ -2329,7 +2331,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free, sg.info.bb_fragments, sg.info.bb_first_free); for (i = 0; i <= 13; i++) - seq_printf(seq, " %-5u", i <= sb->s_blocksize_bits + 1 ? + seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); seq_printf(seq, " ]\n"); @@ -2639,6 +2641,7 @@ int ext4_mb_init(struct super_block *sb) spin_lock_init(&sbi->s_md_lock); spin_lock_init(&sbi->s_bal_lock); sbi->s_mb_free_pending = 0; + INIT_LIST_HEAD(&sbi->s_freed_data_list); sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN; sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN; @@ -2782,7 +2785,8 @@ int ext4_mb_release(struct super_block *sb) } static inline int ext4_issue_discard(struct super_block *sb, - ext4_group_t block_group, ext4_grpblk_t cluster, int count) + ext4_group_t block_group, ext4_grpblk_t cluster, int count, + struct bio **biop) { ext4_fsblk_t discard_block; @@ -2791,18 +2795,18 @@ static inline int ext4_issue_discard(struct super_block *sb, count = EXT4_C2B(EXT4_SB(sb), count); trace_ext4_discard_blocks(sb, (unsigned long long) discard_block, count); - return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); + if (biop) { + return __blkdev_issue_discard(sb->s_bdev, + (sector_t)discard_block << (sb->s_blocksize_bits - 9), + (sector_t)count << (sb->s_blocksize_bits - 9), + GFP_NOFS, 0, biop); + } else + return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0); } -/* - * This function is called by the jbd2 layer once the commit has finished, - * so we know we can free the blocks that were released with that commit. - */ -static void ext4_free_data_callback(struct super_block *sb, - struct ext4_journal_cb_entry *jce, - int rc) +static void ext4_free_data_in_buddy(struct super_block *sb, + struct ext4_free_data *entry) { - struct ext4_free_data *entry = (struct ext4_free_data *)jce; struct ext4_buddy e4b; struct ext4_group_info *db; int err, count = 0, count2 = 0; @@ -2810,18 +2814,6 @@ static void ext4_free_data_callback(struct super_block *sb, mb_debug(1, "gonna free %u blocks in group %u (0x%p):", entry->efd_count, entry->efd_group, entry); - if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, entry->efd_group, - entry->efd_start_cluster, - entry->efd_count); - if (err && err != -EOPNOTSUPP) - ext4_msg(sb, KERN_WARNING, "discard request in" - " group:%d block:%d count:%d failed" - " with %d", entry->efd_group, - entry->efd_start_cluster, - entry->efd_count, err); - } - err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b); /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); @@ -2862,6 +2854,58 @@ static void ext4_free_data_callback(struct super_block *sb, mb_debug(1, "freed %u blocks in %u structures\n", count, count2); } +/* + * This function is called by the jbd2 layer once the commit has finished, + * so we know we can free the blocks that were released with that commit. + */ +void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_free_data *entry, *tmp; + struct bio *discard_bio = NULL; + struct list_head freed_data_list; + struct list_head *cut_pos = NULL; + int err; + + INIT_LIST_HEAD(&freed_data_list); + + spin_lock(&sbi->s_md_lock); + list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) { + if (entry->efd_tid != commit_tid) + break; + cut_pos = &entry->efd_list; + } + if (cut_pos) + list_cut_position(&freed_data_list, &sbi->s_freed_data_list, + cut_pos); + spin_unlock(&sbi->s_md_lock); + + if (test_opt(sb, DISCARD)) { + list_for_each_entry(entry, &freed_data_list, efd_list) { + err = ext4_issue_discard(sb, entry->efd_group, + entry->efd_start_cluster, + entry->efd_count, + &discard_bio); + if (err && err != -EOPNOTSUPP) { + ext4_msg(sb, KERN_WARNING, "discard request in" + " group:%d block:%d count:%d failed" + " with %d", entry->efd_group, + entry->efd_start_cluster, + entry->efd_count, err); + } else if (err == -EOPNOTSUPP) + break; + } + + if (discard_bio) { + submit_bio_wait(discard_bio); + bio_put(discard_bio); + } + } + + list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list) + ext4_free_data_in_buddy(sb, entry); +} + int __init ext4_init_mballoc(void) { ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space, @@ -3529,7 +3573,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, ext4_set_bits(bitmap, start, len); preallocated += len; } - mb_debug(1, "prellocated %u for group %u\n", preallocated, group); + mb_debug(1, "preallocated %u for group %u\n", preallocated, group); } static void ext4_mb_pa_callback(struct rcu_head *head) @@ -4464,7 +4508,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, trace_ext4_request_blocks(ar); /* Allow to use superuser reservation for quota file */ - if (IS_NOQUOTA(ar->inode)) + if (ext4_is_quota_file(ar->inode)) ar->flags |= EXT4_MB_USE_ROOT_BLOCKS; if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) { @@ -4583,14 +4627,28 @@ out: * are contiguous, AND the extents were freed by the same transaction, * AND the blocks are associated with the same group. */ -static int can_merge(struct ext4_free_data *entry1, - struct ext4_free_data *entry2) +static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi, + struct ext4_free_data *entry, + struct ext4_free_data *new_entry, + struct rb_root *entry_rb_root) { - if ((entry1->efd_tid == entry2->efd_tid) && - (entry1->efd_group == entry2->efd_group) && - ((entry1->efd_start_cluster + entry1->efd_count) == entry2->efd_start_cluster)) - return 1; - return 0; + if ((entry->efd_tid != new_entry->efd_tid) || + (entry->efd_group != new_entry->efd_group)) + return; + if (entry->efd_start_cluster + entry->efd_count == + new_entry->efd_start_cluster) { + new_entry->efd_start_cluster = entry->efd_start_cluster; + new_entry->efd_count += entry->efd_count; + } else if (new_entry->efd_start_cluster + new_entry->efd_count == + entry->efd_start_cluster) { + new_entry->efd_count += entry->efd_count; + } else + return; + spin_lock(&sbi->s_md_lock); + list_del(&entry->efd_list); + spin_unlock(&sbi->s_md_lock); + rb_erase(&entry->efd_node, entry_rb_root); + kmem_cache_free(ext4_free_data_cachep, entry); } static noinline_for_stack int @@ -4646,29 +4704,19 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, node = rb_prev(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(entry, new_entry) && - ext4_journal_callback_try_del(handle, &entry->efd_jce)) { - new_entry->efd_start_cluster = entry->efd_start_cluster; - new_entry->efd_count += entry->efd_count; - rb_erase(node, &(db->bb_free_root)); - kmem_cache_free(ext4_free_data_cachep, entry); - } + ext4_try_merge_freed_extent(sbi, entry, new_entry, + &(db->bb_free_root)); } node = rb_next(new_node); if (node) { entry = rb_entry(node, struct ext4_free_data, efd_node); - if (can_merge(new_entry, entry) && - ext4_journal_callback_try_del(handle, &entry->efd_jce)) { - new_entry->efd_count += entry->efd_count; - rb_erase(node, &(db->bb_free_root)); - kmem_cache_free(ext4_free_data_cachep, entry); - } + ext4_try_merge_freed_extent(sbi, entry, new_entry, + &(db->bb_free_root)); } - /* Add the extent to transaction's private list */ - new_entry->efd_jce.jce_func = ext4_free_data_callback; + spin_lock(&sbi->s_md_lock); - _ext4_journal_callback_add(handle, &new_entry->efd_jce); + list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list); sbi->s_mb_free_pending += clusters; spin_unlock(&sbi->s_md_lock); return 0; @@ -4871,7 +4919,8 @@ do_more: * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count); + err = ext4_issue_discard(sb, block_group, bit, count, + NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%d block:%d count:%lu failed" @@ -5094,7 +5143,7 @@ __acquires(bitlock) */ mb_mark_used(e4b, &ex); ext4_unlock_group(sb, group); - ret = ext4_issue_discard(sb, group, start, count); + ret = ext4_issue_discard(sb, group, start, count, NULL); ext4_lock_group(sb, group); mb_free_blocks(NULL, e4b, start, ex.fe_len); return ret; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 2bed62084a8c..009300ee1561 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -78,10 +78,8 @@ do { \ struct ext4_free_data { - /* MUST be the first member */ - struct ext4_journal_cb_entry efd_jce; - - /* ext4_free_data private data starts from here */ + /* this links the free block information from sb_info */ + struct list_head efd_list; /* this links the free block information from group_info */ struct rb_node efd_node; diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 364ea4d4a943..cf5181b62df1 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -475,7 +475,7 @@ int ext4_ext_migrate(struct inode *inode) owner[0] = i_uid_read(inode); owner[1] = i_gid_read(inode); tmp_inode = ext4_new_inode(handle, d_inode(inode->i_sb->s_root), - S_IFREG, NULL, goal, owner); + S_IFREG, NULL, goal, owner, 0); if (IS_ERR(tmp_inode)) { retval = PTR_ERR(tmp_inode); ext4_journal_stop(handle); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index eb9835638680..84c54f15f1dd 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -185,7 +185,7 @@ static int kmmpd(void *data) goto exit_thread; } - if (sb->s_flags & MS_RDONLY) { + if (sb_rdonly(sb)) { ext4_warning(sb, "kmmpd being stopped since filesystem " "has been remounted as readonly."); goto exit_thread; @@ -367,7 +367,7 @@ skip: goto failed; } - mmpd_data = kmalloc(sizeof(struct mmpd_data), GFP_KERNEL); + mmpd_data = kmalloc(sizeof(*mmpd_data), GFP_KERNEL); if (!mmpd_data) { ext4_warning(sb, "not enough memory for mmpd_data"); goto failed; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index c992ef2c2f94..9bb36909ec92 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -484,7 +484,7 @@ mext_check_arguments(struct inode *orig_inode, return -EBUSY; } - if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) { + if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) { ext4_debug("ext4 move extent: The argument files should " "not be quota files [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 404256caf9cf..c1cf020d1889 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -513,7 +513,7 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize) static inline ext4_lblk_t dx_get_block(struct dx_entry *entry) { - return le32_to_cpu(entry->block) & 0x00ffffff; + return le32_to_cpu(entry->block) & 0x0fffffff; } static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value) @@ -739,6 +739,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR); u32 hash; + memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0])); frame->bh = ext4_read_dirblock(dir, 0, INDEX); if (IS_ERR(frame->bh)) return (struct dx_frame *) frame->bh; @@ -768,9 +769,15 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } indirect = root->info.indirect_levels; - if (indirect > 1) { - ext4_warning_inode(dir, "Unimplemented hash depth: %#06x", - root->info.indirect_levels); + if (indirect >= ext4_dir_htree_level(dir->i_sb)) { + ext4_warning(dir->i_sb, + "Directory (ino: %lu) htree depth %#06x exceed" + "supported value", dir->i_ino, + ext4_dir_htree_level(dir->i_sb)); + if (ext4_dir_htree_level(dir->i_sb) < EXT4_HTREE_LEVEL) { + ext4_warning(dir->i_sb, "Enable large directory " + "feature to access it"); + } goto fail; } @@ -859,12 +866,19 @@ fail: static void dx_release(struct dx_frame *frames) { + struct dx_root_info *info; + int i; + if (frames[0].bh == NULL) return; - if (((struct dx_root *)frames[0].bh->b_data)->info.indirect_levels) - brelse(frames[1].bh); - brelse(frames[0].bh); + info = &((struct dx_root *)frames[0].bh->b_data)->info; + for (i = 0; i <= info->indirect_levels; i++) { + if (frames[i].bh == NULL) + break; + brelse(frames[i].bh); + frames[i].bh = NULL; + } } /* @@ -1050,7 +1064,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, { struct dx_hash_info hinfo; struct ext4_dir_entry_2 *de; - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct inode *dir; ext4_lblk_t block; int count = 0; @@ -1328,13 +1342,12 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, struct super_block *sb; struct buffer_head *bh_use[NAMEI_RA_SIZE]; struct buffer_head *bh, *ret = NULL; - ext4_lblk_t start, block, b; + ext4_lblk_t start, block; const u8 *name = d_name->name; - int ra_max = 0; /* Number of bh's in the readahead + size_t ra_max = 0; /* Number of bh's in the readahead buffer, bh_use[] */ - int ra_ptr = 0; /* Current index into readahead + size_t ra_ptr = 0; /* Current index into readahead buffer */ - int num = 0; ext4_lblk_t nblocks; int i, namelen, retval; struct ext4_filename fname; @@ -1397,42 +1410,28 @@ restart: if (ra_ptr >= ra_max) { /* Refill the readahead buffer */ ra_ptr = 0; - b = block; - for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) { - /* - * Terminate if we reach the end of the - * directory and must wrap, or if our - * search has finished at this block. - */ - if (b >= nblocks || (num && block == start)) { - bh_use[ra_max] = NULL; - break; - } - num++; - bh = ext4_getblk(NULL, dir, b++, 0); - if (IS_ERR(bh)) { - if (ra_max == 0) { - ret = bh; - goto cleanup_and_exit; - } - break; - } - bh_use[ra_max] = bh; - if (bh) - ll_rw_block(REQ_OP_READ, - REQ_META | REQ_PRIO, - 1, &bh); + if (block < start) + ra_max = start - block; + else + ra_max = nblocks - block; + ra_max = min(ra_max, ARRAY_SIZE(bh_use)); + retval = ext4_bread_batch(dir, block, ra_max, + false /* wait */, bh_use); + if (retval) { + ret = ERR_PTR(retval); + ra_max = 0; + goto cleanup_and_exit; } } if ((bh = bh_use[ra_ptr++]) == NULL) goto next; wait_on_buffer(bh); if (!buffer_uptodate(bh)) { - /* read error, skip block & hope for the best */ EXT4_ERROR_INODE(dir, "reading directory lblock %lu", (unsigned long) block); brelse(bh); - goto next; + ret = ERR_PTR(-EIO); + goto cleanup_and_exit; } if (!buffer_verified(bh) && !is_dx_internal_node(dir, block, @@ -1442,7 +1441,8 @@ restart: EXT4_ERROR_INODE(dir, "checksumming directory " "block %lu", (unsigned long)block); brelse(bh); - goto next; + ret = ERR_PTR(-EFSBADCRC); + goto cleanup_and_exit; } set_buffer_verified(bh); i = search_dirblock(bh, dir, &fname, @@ -1485,7 +1485,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, struct ext4_dir_entry_2 **res_dir) { struct super_block * sb = dir->i_sb; - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct buffer_head *bh; ext4_lblk_t block; int retval; @@ -1889,7 +1889,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, */ dir->i_mtime = dir->i_ctime = current_time(dir); ext4_update_dx_flag(dir); - dir->i_version++; + inode_inc_iversion(dir); ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_dirent_node(handle, dir, bh); @@ -1908,7 +1908,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, { struct buffer_head *bh2; struct dx_root *root; - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries; struct ext4_dir_entry_2 *de, *de2; struct ext4_dir_entry_tail *t; @@ -2127,13 +2127,16 @@ out: static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode) { - struct dx_frame frames[2], *frame; + struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries, *at; struct buffer_head *bh; struct super_block *sb = dir->i_sb; struct ext4_dir_entry_2 *de; + int restart; int err; +again: + restart = 0; frame = dx_probe(fname, dir, NULL, frames); if (IS_ERR(frame)) return PTR_ERR(frame); @@ -2155,24 +2158,44 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, if (err != -ENOSPC) goto cleanup; + err = 0; /* Block full, should compress but for now just split */ dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n", dx_get_count(entries), dx_get_limit(entries))); /* Need to split index? */ if (dx_get_count(entries) == dx_get_limit(entries)) { ext4_lblk_t newblock; - unsigned icount = dx_get_count(entries); - int levels = frame - frames; + int levels = frame - frames + 1; + unsigned int icount; + int add_level = 1; struct dx_entry *entries2; struct dx_node *node2; struct buffer_head *bh2; - if (levels && (dx_get_count(frames->entries) == - dx_get_limit(frames->entries))) { - ext4_warning_inode(dir, "Directory index full!"); + while (frame > frames) { + if (dx_get_count((frame - 1)->entries) < + dx_get_limit((frame - 1)->entries)) { + add_level = 0; + break; + } + frame--; /* split higher index block */ + at = frame->at; + entries = frame->entries; + restart = 1; + } + if (add_level && levels == ext4_dir_htree_level(sb)) { + ext4_warning(sb, "Directory (ino: %lu) index full, " + "reach max htree level :%d", + dir->i_ino, levels); + if (ext4_dir_htree_level(sb) < EXT4_HTREE_LEVEL) { + ext4_warning(sb, "Large directory feature is " + "not enabled on this " + "filesystem"); + } err = -ENOSPC; goto cleanup; } + icount = dx_get_count(entries); bh2 = ext4_append(handle, dir, &newblock); if (IS_ERR(bh2)) { err = PTR_ERR(bh2); @@ -2187,7 +2210,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, err = ext4_journal_get_write_access(handle, frame->bh); if (err) goto journal_error; - if (levels) { + if (!add_level) { unsigned icount1 = icount/2, icount2 = icount - icount1; unsigned hash2 = dx_get_hash(entries + icount1); dxtrace(printk(KERN_DEBUG "Split index %i/%i\n", @@ -2195,7 +2218,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */ err = ext4_journal_get_write_access(handle, - frames[0].bh); + (frame - 1)->bh); if (err) goto journal_error; @@ -2211,17 +2234,25 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, frame->entries = entries = entries2; swap(frame->bh, bh2); } - dx_insert_block(frames + 0, hash2, newblock); - dxtrace(dx_show_index("node", frames[1].entries)); + dx_insert_block((frame - 1), hash2, newblock); + dxtrace(dx_show_index("node", frame->entries)); dxtrace(dx_show_index("node", ((struct dx_node *) bh2->b_data)->entries)); err = ext4_handle_dirty_dx_node(handle, dir, bh2); if (err) goto journal_error; brelse (bh2); + err = ext4_handle_dirty_dx_node(handle, dir, + (frame - 1)->bh); + if (err) + goto journal_error; + if (restart) { + err = ext4_handle_dirty_dx_node(handle, dir, + frame->bh); + goto journal_error; + } } else { - dxtrace(printk(KERN_DEBUG - "Creating second level index...\n")); + struct dx_root *dxroot; memcpy((char *) entries2, (char *) entries, icount * sizeof(struct dx_entry)); dx_set_limit(entries2, dx_node_limit(dir)); @@ -2229,22 +2260,18 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, /* Set up root */ dx_set_count(entries, 1); dx_set_block(entries + 0, newblock); - ((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1; - - /* Add new access path frame */ - frame = frames + 1; - frame->at = at = at - entries + entries2; - frame->entries = entries = entries2; - frame->bh = bh2; - err = ext4_journal_get_write_access(handle, - frame->bh); + dxroot = (struct dx_root *)frames[0].bh->b_data; + dxroot->info.indirect_levels += 1; + dxtrace(printk(KERN_DEBUG + "Creating %d level index...\n", + info->indirect_levels)); + err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (err) goto journal_error; - } - err = ext4_handle_dirty_dx_node(handle, dir, frames[0].bh); - if (err) { - ext4_std_error(inode->i_sb, err); - goto cleanup; + err = ext4_handle_dirty_dx_node(handle, dir, bh2); + brelse(bh2); + restart = 1; + goto journal_error; } } de = do_split(handle, dir, &bh, frame, &fname->hinfo); @@ -2256,10 +2283,15 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, goto cleanup; journal_error: - ext4_std_error(dir->i_sb, err); + ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */ cleanup: brelse(bh); dx_release(frames); + /* @restart is true means htree-path has been changed, we need to + * repeat dx_probe() to find out valid htree-path + */ + if (restart && err == 0) + goto again; return err; } @@ -2296,7 +2328,7 @@ int ext4_generic_delete_entry(handle_t *handle, blocksize); else de->inode = 0; - dir->i_version++; + inode_inc_iversion(dir); return 0; } i += ext4_rec_len_from_disk(de->rec_len, blocksize); @@ -2348,19 +2380,22 @@ out: } /* - * DIR_NLINK feature is set if 1) nlinks > EXT4_LINK_MAX or 2) nlinks == 2, - * since this indicates that nlinks count was previously 1. + * Set directory link count to 1 if nlinks > EXT4_LINK_MAX, or if nlinks == 2 + * since this indicates that nlinks count was previously 1 to avoid overflowing + * the 16-bit i_links_count field on disk. Directories with i_nlink == 1 mean + * that subdirectory link counts are not being maintained accurately. + * + * The caller has already checked for i_nlink overflow in case the DIR_LINK + * feature is not enabled and returned -EMLINK. The is_dx() check is a proxy + * for checking S_ISDIR(inode) (since the INODE_INDEX feature will not be set + * on regular files) and to avoid creating huge/slow non-HTREE directories. */ static void ext4_inc_count(handle_t *handle, struct inode *inode) { inc_nlink(inode); - if (is_dx(inode) && inode->i_nlink > 1) { - /* limit is 16-bit i_links_count */ - if (inode->i_nlink >= EXT4_LINK_MAX || inode->i_nlink == 2) { - set_nlink(inode, 1); - ext4_set_feature_dir_nlink(inode->i_sb); - } - } + if (is_dx(inode) && + (inode->i_nlink > EXT4_LINK_MAX || inode->i_nlink == 2)) + set_nlink(inode, 1); } /* diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 1a82138ba739..55ad7dd149d0 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -85,7 +85,7 @@ static void ext4_finish_bio(struct bio *bio) } #endif - if (bio->bi_error) { + if (bio->bi_status) { SetPageError(page); mapping_set_error(page->mapping, -EIO); } @@ -104,7 +104,7 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_error) + if (bio->bi_status) buffer_io_error(bh); } while ((bh = bh->b_this_page) != head); bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); @@ -300,27 +300,28 @@ static void ext4_end_bio(struct bio *bio) char b[BDEVNAME_SIZE]; if (WARN_ONCE(!io_end, "io_end is NULL: %s: sector %Lu len %u err %d\n", - bdevname(bio->bi_bdev, b), + bio_devname(bio, b), (long long) bio->bi_iter.bi_sector, (unsigned) bio_sectors(bio), - bio->bi_error)) { + bio->bi_status)) { ext4_finish_bio(bio); bio_put(bio); return; } bio->bi_end_io = NULL; - if (bio->bi_error) { + if (bio->bi_status) { struct inode *inode = io_end->inode; ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu " "(offset %llu size %ld starting block %llu)", - bio->bi_error, inode->i_ino, + bio->bi_status, inode->i_ino, (unsigned long long) io_end->offset, (long) io_end->size, (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); - mapping_set_error(inode->i_mapping, bio->bi_error); + mapping_set_error(inode->i_mapping, + blk_status_to_errno(bio->bi_status)); } if (io_end->flag & EXT4_IO_END_UNWRITTEN) { @@ -349,6 +350,7 @@ void ext4_io_submit(struct ext4_io_submit *io) if (bio) { int io_op_flags = io->io_wbc->sync_mode == WB_SYNC_ALL ? REQ_SYNC : 0; + io->io_bio->bi_write_hint = io->io_end->inode->i_write_hint; bio_set_op_attrs(io->io_bio, REQ_OP_WRITE, io_op_flags); submit_bio(io->io_bio); } @@ -373,7 +375,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io, return -ENOMEM; wbc_init_bio(io->io_wbc, bio); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_bdev = bh->b_bdev; + bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); io->io_bio = bio; @@ -396,6 +398,7 @@ submit_and_retry: ret = io_submit_init_bio(io, bh); if (ret) return ret; + io->io_bio->bi_write_hint = inode->i_write_hint; } ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh)); if (ret != bh->b_size) diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index a81b829d56de..04c90643af7a 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -73,7 +73,7 @@ static void mpage_end_io(struct bio *bio) int i; if (ext4_bio_encrypted(bio)) { - if (bio->bi_error) { + if (bio->bi_status) { fscrypt_release_ctx(bio->bi_private); } else { fscrypt_decrypt_bio_pages(bio->bi_private, bio); @@ -83,7 +83,7 @@ static void mpage_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - if (!bio->bi_error) { + if (!bio->bi_status) { SetPageUptodate(page); } else { ClearPageUptodate(page); @@ -254,7 +254,7 @@ int ext4_mpage_readpages(struct address_space *mapping, fscrypt_release_ctx(ctx); goto set_error_page; } - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9); bio->bi_end_io = mpage_end_io; bio->bi_private = ctx; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index c3ed9021b781..035cd3f4785e 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1927,7 +1927,8 @@ retry: n_desc_blocks = o_desc_blocks + le16_to_cpu(es->s_reserved_gdt_blocks); n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); - n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb); + n_blocks_count = (ext4_fsblk_t)n_group * + EXT4_BLOCKS_PER_GROUP(sb); n_group--; /* set to last group number */ } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d37c81f327e7..b0915b734a38 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -373,6 +373,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) struct ext4_journal_cb_entry *jce; BUG_ON(txn->t_state == T_FINISHED); + + ext4_process_freed_data(sb, txn->t_tid); + spin_lock(&sbi->s_md_lock); while (!list_empty(&txn->t_private_list)) { jce = list_entry(txn->t_private_list.next, @@ -402,7 +405,7 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn) static void ext4_handle_error(struct super_block *sb) { - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; if (!test_opt(sb, ERRORS_CONT)) { @@ -584,8 +587,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, /* Special case: if the error is EROFS, and we're not already * inside a transaction, then there's really no point in logging * an error. */ - if (errno == -EROFS && journal_current_handle() == NULL && - (sb->s_flags & MS_RDONLY)) + if (errno == -EROFS && journal_current_handle() == NULL && sb_rdonly(sb)) return; if (ext4_error_ratelimit(sb)) { @@ -625,7 +627,7 @@ void __ext4_abort(struct super_block *sb, const char *function, sb->s_id, function, line, &vaf); va_end(args); - if ((sb->s_flags & MS_RDONLY) == 0) { + if (sb_rdonly(sb) == 0) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; /* @@ -886,11 +888,11 @@ static void ext4_put_super(struct super_block *sb) ext4_mb_release(sb); ext4_ext_release(sb); - if (!(sb->s_flags & MS_RDONLY) && !aborted) { + if (!sb_rdonly(sb) && !aborted) { ext4_clear_feature_journal_needs_recovery(sb); es->s_state = cpu_to_le16(sbi->s_mount_state); } - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) ext4_commit_super(sb, 1); for (i = 0; i < sbi->s_gdb_count; i++) @@ -927,9 +929,13 @@ static void ext4_put_super(struct super_block *sb) invalidate_bdev(sbi->journal_bdev); ext4_blkdev_remove(sbi); } - if (sbi->s_mb_cache) { - ext4_xattr_destroy_cache(sbi->s_mb_cache); - sbi->s_mb_cache = NULL; + if (sbi->s_ea_inode_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); + sbi->s_ea_inode_cache = NULL; + } + if (sbi->s_ea_block_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_block_cache); + sbi->s_ea_block_cache = NULL; } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); @@ -944,6 +950,7 @@ static void ext4_put_super(struct super_block *sb) if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); + fs_put_dax(sbi->s_daxdev); kfree(sbi); } @@ -971,8 +978,6 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_es_shk_nr = 0; ei->i_es_shrink_lblk = 0; ei->i_reserved_data_blocks = 0; - ei->i_reserved_meta_blocks = 0; - ei->i_allocated_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); @@ -1143,7 +1148,16 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { handle_t *handle = fs_data; - int res, res2, retries = 0; + int res, res2, credits, retries = 0; + + /* + * Encrypting the root directory is not allowed because e2fsck expects + * lost+found to exist and be unencrypted, and encrypting the root + * directory would imply encrypting the lost+found directory as well as + * the filename "lost+found" itself. + */ + if (inode->i_ino == EXT4_ROOT_INO) + return -EPERM; res = ext4_convert_inline_data(inode); if (res) @@ -1178,8 +1192,12 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, if (res) return res; retry: - handle = ext4_journal_start(inode, EXT4_HT_MISC, - ext4_jbd2_credits_xattr(inode)); + res = ext4_xattr_set_credits(inode, len, false /* is_create */, + &credits); + if (res) + return res; + + handle = ext4_journal_start(inode, EXT4_HT_MISC, credits); if (IS_ERR(handle)) return PTR_ERR(handle); @@ -1203,7 +1221,7 @@ retry: return res; } -static int ext4_dummy_context(struct inode *inode) +static bool ext4_dummy_context(struct inode *inode) { return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb)); } @@ -1256,16 +1274,17 @@ static struct dquot **ext4_get_dquots(struct inode *inode) } static const struct dquot_operations ext4_quota_operations = { - .get_reserved_space = ext4_get_reserved_space, - .write_dquot = ext4_write_dquot, - .acquire_dquot = ext4_acquire_dquot, - .release_dquot = ext4_release_dquot, - .mark_dirty = ext4_mark_dquot_dirty, - .write_info = ext4_write_info, - .alloc_dquot = dquot_alloc, - .destroy_dquot = dquot_destroy, - .get_projid = ext4_get_projid, - .get_next_id = ext4_get_next_id, + .get_reserved_space = ext4_get_reserved_space, + .write_dquot = ext4_write_dquot, + .acquire_dquot = ext4_acquire_dquot, + .release_dquot = ext4_release_dquot, + .mark_dirty = ext4_mark_dquot_dirty, + .write_info = ext4_write_info, + .alloc_dquot = dquot_alloc, + .destroy_dquot = dquot_destroy, + .get_projid = ext4_get_projid, + .get_inode_usage = ext4_get_inode_usage, + .get_next_id = ext4_get_next_id, }; static const struct quotactl_ops ext4_qctl_operations = { @@ -1328,7 +1347,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, - Opt_max_dir_size_kb, Opt_nojournal_checksum, + Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, }; static const match_table_t tokens = { @@ -1411,6 +1430,8 @@ static const match_table_t tokens = { {Opt_noinit_itable, "noinit_itable"}, {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_nombcache, "nombcache"}, + {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1618,6 +1639,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_test_dummy_encryption, 0, MOPT_GTE0}, + {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_err, 0, 0} }; @@ -1655,7 +1677,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; return 1; case Opt_i_version: - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; return 1; case Opt_lazytime: sb->s_flags |= MS_LAZYTIME; @@ -2038,7 +2060,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("min_batch_time=%u", sbi->s_min_batch_time); if (nodefs || sbi->s_max_batch_time != EXT4_DEF_MAX_BATCH_TIME) SEQ_OPTS_PRINT("max_batch_time=%u", sbi->s_max_batch_time); - if (sb->s_flags & MS_I_VERSION) + if (sb->s_flags & SB_I_VERSION) SEQ_OPTS_PUTS("i_version"); if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); @@ -2077,7 +2099,7 @@ int ext4_seq_options_show(struct seq_file *seq, void *offset) struct super_block *sb = seq->private; int rc; - seq_puts(seq, (sb->s_flags & MS_RDONLY) ? "ro" : "rw"); + seq_puts(seq, sb_rdonly(sb) ? "ro" : "rw"); rc = _ext4_show_options(seq, sb, 1); seq_puts(seq, "\n"); return rc; @@ -2345,7 +2367,7 @@ static int ext4_check_descriptors(struct super_block *sb, "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sb, i, gdp)), le16_to_cpu(gdp->bg_checksum)); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { ext4_unlock_group(sb, i); return 0; } @@ -2382,6 +2404,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, unsigned int s_flags = sb->s_flags; int ret, nr_orphans = 0, nr_truncates = 0; #ifdef CONFIG_QUOTA + int quota_update = 0; int i; #endif if (!es->s_last_orphan) { @@ -2420,14 +2443,32 @@ static void ext4_orphan_cleanup(struct super_block *sb, #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ sb->s_flags |= MS_ACTIVE; - /* Turn on quotas so that they are updated correctly */ + + /* + * Turn on quotas which were not enabled for read-only mounts if + * filesystem has quota feature, so that they are updated correctly. + */ + if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) { + int ret = ext4_enable_quotas(sb); + + if (!ret) + quota_update = 1; + else + ext4_msg(sb, KERN_ERR, + "Cannot turn on quotas: error %d", ret); + } + + /* Turn on journaled quotas used for old sytle */ for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); - if (ret < 0) + + if (!ret) + quota_update = 1; + else ext4_msg(sb, KERN_ERR, "Cannot turn on journaled " - "quota: error %d", ret); + "quota: type %d: error %d", i, ret); } } #endif @@ -2488,10 +2529,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up", PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA - /* Turn quotas off */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) { - if (sb_dqopt(sb)->files[i]) - dquot_quota_off(sb, i); + /* Turn off quotas if they were enabled for orphan cleanup */ + if (quota_update) { + for (i = 0; i < EXT4_MAXQUOTAS; i++) { + if (sb_dqopt(sb)->files[i]) + dquot_quota_off(sb, i); + } } #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -3092,8 +3135,7 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (first_not_zeroed == ngroups || - (sb->s_flags & MS_RDONLY) || + if (first_not_zeroed == ngroups || sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) goto out; @@ -3355,6 +3397,7 @@ static void ext4_set_resv_clusters(struct super_block *sb) static int ext4_fill_super(struct super_block *sb, void *data, int silent) { + struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev); char *orig_data = kstrdup(data, GFP_KERNEL); struct buffer_head *bh; struct ext4_super_block *es = NULL; @@ -3380,6 +3423,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if ((data && !orig_data) || !sbi) goto out_free_base; + sbi->s_daxdev = dax_dev; sbi->s_blockgroup_lock = kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL); if (!sbi->s_blockgroup_lock) @@ -3445,7 +3489,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } /* Load the checksum driver */ - if (ext4_has_feature_metadata_csum(sb)) { + if (ext4_has_feature_metadata_csum(sb) || + ext4_has_feature_ea_inode(sb)) { sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(sbi->s_chksum_driver)) { ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); @@ -3467,7 +3512,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) /* Precompute checksum seed for all metadata */ if (ext4_has_feature_csum_seed(sb)) sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed); - else if (ext4_has_metadata_csum(sb)) + else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb)) sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, sizeof(es->s_uuid)); @@ -3597,6 +3642,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "The Hurd can't support 64-bit file systems"); goto failed_mount; } + + /* + * ea_inode feature uses l_i_version field which is not + * available in HURD_COMPAT mode. + */ + if (ext4_has_feature_ea_inode(sb)) { + ext4_msg(sb, KERN_ERR, + "ea_inode feature is not supported for Hurd"); + goto failed_mount; + } } if (IS_EXT2_SB(sb)) { @@ -3626,7 +3681,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * previously didn't change the revision level when setting the flags, * so there is a chance incompat flags are set on a rev 0 filesystem. */ - if (!ext4_feature_set_ok(sb, (sb->s_flags & MS_RDONLY))) + if (!ext4_feature_set_ok(sb, (sb_rdonly(sb)))) goto failed_mount; blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size); @@ -3755,12 +3810,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_hash_unsigned = 3; else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) { #ifdef __CHAR_UNSIGNED__ - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH); sbi->s_hash_unsigned = 3; #else - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH); #endif @@ -3950,7 +4005,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sb->s_qcop = &ext4_qctl_operations; sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; #endif - memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); + memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid)); INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); @@ -3960,7 +4015,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) needs_recovery = (es->s_last_orphan != 0 || ext4_has_feature_journal_needs_recovery(sb)); - if (ext4_has_feature_mmp(sb) && !(sb->s_flags & MS_RDONLY)) + if (ext4_has_feature_mmp(sb) && !sb_rdonly(sb)) if (ext4_multi_mount_protect(sb, le64_to_cpu(es->s_mmp_block))) goto failed_mount3a; @@ -3972,7 +4027,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) err = ext4_load_journal(sb, es, journal_devnum); if (err) goto failed_mount3a; - } else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) && + } else if (test_opt(sb, NOLOAD) && !sb_rdonly(sb) && ext4_has_feature_journal_needs_recovery(sb)) { ext4_msg(sb, KERN_ERR, "required journal recovery " "suppressed and not mounted read-only"); @@ -4061,10 +4116,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_journal->j_commit_callback = ext4_journal_commit_callback; no_journal: - sbi->s_mb_cache = ext4_xattr_create_cache(); - if (!sbi->s_mb_cache) { - ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache"); - goto failed_mount_wq; + if (!test_opt(sb, NO_MBCACHE)) { + sbi->s_ea_block_cache = ext4_xattr_create_cache(); + if (!sbi->s_ea_block_cache) { + ext4_msg(sb, KERN_ERR, + "Failed to create ea_block_cache"); + goto failed_mount_wq; + } + + if (ext4_has_feature_ea_inode(sb)) { + sbi->s_ea_inode_cache = ext4_xattr_create_cache(); + if (!sbi->s_ea_inode_cache) { + ext4_msg(sb, KERN_ERR, + "Failed to create ea_inode_cache"); + goto failed_mount_wq; + } + } } if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) && @@ -4074,7 +4141,7 @@ no_journal: goto failed_mount_wq; } - if (DUMMY_ENCRYPTION_ENABLED(sbi) && !(sb->s_flags & MS_RDONLY) && + if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) && !ext4_has_feature_encrypt(sb)) { ext4_set_feature_encrypt(sb); ext4_commit_super(sb, 1); @@ -4128,7 +4195,7 @@ no_journal: goto failed_mount4; } - if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY)) + if (ext4_setup_super(sb, es, sb_rdonly(sb))) sb->s_flags |= MS_RDONLY; /* determine the minimum size of new large inodes, if present */ @@ -4216,7 +4283,7 @@ no_journal: #ifdef CONFIG_QUOTA /* Enable quota usage during mount. */ - if (ext4_has_feature_quota(sb) && !(sb->s_flags & MS_RDONLY)) { + if (ext4_has_feature_quota(sb) && !sb_rdonly(sb)) { err = ext4_enable_quotas(sb); if (err) goto failed_mount8; @@ -4296,9 +4363,13 @@ failed_mount4: if (EXT4_SB(sb)->rsv_conversion_wq) destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); failed_mount_wq: - if (sbi->s_mb_cache) { - ext4_xattr_destroy_cache(sbi->s_mb_cache); - sbi->s_mb_cache = NULL; + if (sbi->s_ea_inode_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_inode_cache); + sbi->s_ea_inode_cache = NULL; + } + if (sbi->s_ea_block_cache) { + ext4_xattr_destroy_cache(sbi->s_ea_block_cache); + sbi->s_ea_block_cache = NULL; } if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -4329,6 +4400,7 @@ out_fail: out_free_base: kfree(sbi); kfree(orig_data); + fs_put_dax(dax_dev); return err ? err : ret; } @@ -4535,7 +4607,7 @@ static int ext4_load_journal(struct super_block *sb, * can get read-write access to the device. */ if (ext4_has_feature_journal_needs_recovery(sb)) { - if (sb->s_flags & MS_RDONLY) { + if (sb_rdonly(sb)) { ext4_msg(sb, KERN_INFO, "INFO: recovery " "required on readonly filesystem"); if (really_read_only) { @@ -4690,8 +4762,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb, if (jbd2_journal_flush(journal) < 0) goto out; - if (ext4_has_feature_journal_needs_recovery(sb) && - sb->s_flags & MS_RDONLY) { + if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); } @@ -4747,7 +4818,7 @@ int ext4_force_commit(struct super_block *sb) { journal_t *journal; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; journal = EXT4_SB(sb)->s_journal; @@ -4812,7 +4883,7 @@ static int ext4_freeze(struct super_block *sb) int error = 0; journal_t *journal; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; journal = EXT4_SB(sb)->s_journal; @@ -4847,7 +4918,7 @@ out: */ static int ext4_unfreeze(struct super_block *sb) { - if ((sb->s_flags & MS_RDONLY) || ext4_forced_shutdown(EXT4_SB(sb))) + if (sb_rdonly(sb) || ext4_forced_shutdown(EXT4_SB(sb))) return 0; if (EXT4_SB(sb)->s_journal) { @@ -4957,6 +5028,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) { + ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount"); + err = -EINVAL; + goto restore_opts; + } + if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) { ext4_msg(sb, KERN_WARNING, "warning: refusing change of " "dax flag with busy inodes while remounting"); @@ -4979,7 +5056,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (*flags & MS_LAZYTIME) sb->s_flags |= MS_LAZYTIME; - if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) { + if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) { if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; goto restore_opts; @@ -5074,7 +5151,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) * Reinitialize lazy itable initialization thread based on * current settings */ - if ((sb->s_flags & MS_RDONLY) || !test_opt(sb, INIT_INODE_TABLE)) + if (sb_rdonly(sb) || !test_opt(sb, INIT_INODE_TABLE)) ext4_unregister_li_request(sb); else { ext4_group_t first_not_zeroed; @@ -5139,7 +5216,7 @@ static int ext4_statfs_project(struct super_block *sb, dquot = dqget(sb, qid); if (IS_ERR(dquot)) return PTR_ERR(dquot); - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); limit = (dquot->dq_dqb.dqb_bsoftlimit ? dquot->dq_dqb.dqb_bsoftlimit : @@ -5162,7 +5239,7 @@ static int ext4_statfs_project(struct super_block *sb, (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; } - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); dqput(dquot); return 0; } @@ -5208,18 +5285,13 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } -/* Helper function for writing quotas on sync - we need to start transaction - * before quota file is locked for write. Otherwise the are possible deadlocks: - * Process 1 Process 2 - * ext4_create() quota_sync() - * jbd2_journal_start() write_dquot() - * dquot_initialize() down(dqio_mutex) - * down(dqio_mutex) jbd2_journal_start() - * - */ #ifdef CONFIG_QUOTA +/* + * Helper functions so that transaction is started before we acquire dqio_sem + * to keep correct lock ordering of transaction > dqio_sem + */ static inline struct inode *dquot_to_inode(struct dquot *dquot) { return sb_dqopt(dquot->dq_sb)->files[dquot->dq_id.type]; @@ -5354,6 +5426,13 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id, ext4_msg(sb, KERN_WARNING, "Quota file not on filesystem root. " "Journaled quota will not work"); + sb_dqopt(sb)->flags |= DQUOT_NOLIST_DIRTY; + } else { + /* + * Clear the flag just in case mount options changed since + * last time. + */ + sb_dqopt(sb)->flags &= ~DQUOT_NOLIST_DIRTY; } /* @@ -5450,13 +5529,16 @@ static int ext4_enable_quotas(struct super_block *sb) test_opt(sb, PRJQUOTA), }; - sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY; for (type = 0; type < EXT4_MAXQUOTAS; type++) { if (qf_inums[type]) { err = ext4_quota_enable(sb, type, QFMT_VFS_V1, DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { + for (type--; type >= 0; type--) + dquot_quota_off(sb, type); + ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d). Please run " @@ -5646,7 +5728,7 @@ static inline int ext2_feature_set_ok(struct super_block *sb) { if (ext4_has_unknown_ext2_incompat_features(sb)) return 0; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext2_ro_compat_features(sb)) return 0; @@ -5677,7 +5759,7 @@ static inline int ext3_feature_set_ok(struct super_block *sb) return 0; if (!ext4_has_feature_journal(sb)) return 0; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 1; if (ext4_has_unknown_ext3_ro_compat_features(sb)) return 0; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index d74dc5f81a04..48c7a7d55ed3 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a, int ret; ret = kstrtoull(skip_spaces(buf), 0, &val); - if (!ret || val >= clusters) + if (ret || val >= clusters) return -EINVAL; atomic64_set(&sbi->s_resv_clusters, val); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 5d3c2536641c..3b69330a4250 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -72,12 +72,14 @@ # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif -static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *); -static struct buffer_head *ext4_xattr_cache_find(struct inode *, - struct ext4_xattr_header *, - struct mb_cache_entry **); -static void ext4_xattr_rehash(struct ext4_xattr_header *, - struct ext4_xattr_entry *); +static void ext4_xattr_block_cache_insert(struct mb_cache *, + struct buffer_head *); +static struct buffer_head * +ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, + struct mb_cache_entry **); +static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, + size_t value_count); +static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, @@ -104,8 +106,22 @@ const struct xattr_handler *ext4_xattr_handlers[] = { NULL }; -#define EXT4_GET_MB_CACHE(inode) (((struct ext4_sb_info *) \ - inode->i_sb->s_fs_info)->s_mb_cache) +#define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \ + inode->i_sb->s_fs_info)->s_ea_block_cache) + +#define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \ + inode->i_sb->s_fs_info)->s_ea_inode_cache) + +static int +ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, + struct inode *inode); + +#ifdef CONFIG_LOCKDEP +void ext4_xattr_inode_set_class(struct inode *ea_inode) +{ + lockdep_set_subclass(&ea_inode->i_rwsem, 1); +} +#endif static __le32 ext4_xattr_block_csum(struct inode *inode, sector_t block_nr, @@ -177,9 +193,8 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end, /* Check the values */ while (!IS_LAST_ENTRY(entry)) { - if (entry->e_value_block != 0) - return -EFSCORRUPTED; - if (entry->e_value_size != 0) { + if (entry->e_value_size != 0 && + entry->e_value_inum == 0) { u16 offs = le16_to_cpu(entry->e_value_offs); u32 size = le32_to_cpu(entry->e_value_size); void *value; @@ -269,6 +284,208 @@ ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index, return cmp ? -ENODATA : 0; } +static u32 +ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) +{ + return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size); +} + +static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) +{ + return ((u64)ea_inode->i_ctime.tv_sec << 32) | + ((u32)ea_inode->i_version); +} + +static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) +{ + ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32); + ea_inode->i_version = (u32)ref_count; +} + +static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) +{ + return (u32)ea_inode->i_atime.tv_sec; +} + +static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) +{ + ea_inode->i_atime.tv_sec = hash; +} + +/* + * Read the EA value from an inode. + */ +static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size) +{ + int blocksize = 1 << ea_inode->i_blkbits; + int bh_count = (size + blocksize - 1) >> ea_inode->i_blkbits; + int tail_size = (size % blocksize) ?: blocksize; + struct buffer_head *bhs_inline[8]; + struct buffer_head **bhs = bhs_inline; + int i, ret; + + if (bh_count > ARRAY_SIZE(bhs_inline)) { + bhs = kmalloc_array(bh_count, sizeof(*bhs), GFP_NOFS); + if (!bhs) + return -ENOMEM; + } + + ret = ext4_bread_batch(ea_inode, 0 /* block */, bh_count, + true /* wait */, bhs); + if (ret) + goto free_bhs; + + for (i = 0; i < bh_count; i++) { + /* There shouldn't be any holes in ea_inode. */ + if (!bhs[i]) { + ret = -EFSCORRUPTED; + goto put_bhs; + } + memcpy((char *)buf + blocksize * i, bhs[i]->b_data, + i < bh_count - 1 ? blocksize : tail_size); + } + ret = 0; +put_bhs: + for (i = 0; i < bh_count; i++) + brelse(bhs[i]); +free_bhs: + if (bhs != bhs_inline) + kfree(bhs); + return ret; +} + +#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec) + +static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, + u32 ea_inode_hash, struct inode **ea_inode) +{ + struct inode *inode; + int err; + + inode = ext4_iget(parent->i_sb, ea_ino); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + ext4_error(parent->i_sb, + "error while reading EA inode %lu err=%d", ea_ino, + err); + return err; + } + + if (is_bad_inode(inode)) { + ext4_error(parent->i_sb, + "error while reading EA inode %lu is_bad_inode", + ea_ino); + err = -EIO; + goto error; + } + + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + ext4_error(parent->i_sb, + "EA inode %lu does not have EXT4_EA_INODE_FL flag", + ea_ino); + err = -EINVAL; + goto error; + } + + ext4_xattr_inode_set_class(inode); + + /* + * Check whether this is an old Lustre-style xattr inode. Lustre + * implementation does not have hash validation, rather it has a + * backpointer from ea_inode to the parent inode. + */ + if (ea_inode_hash != ext4_xattr_inode_get_hash(inode) && + EXT4_XATTR_INODE_GET_PARENT(inode) == parent->i_ino && + inode->i_generation == parent->i_generation) { + ext4_set_inode_state(inode, EXT4_STATE_LUSTRE_EA_INODE); + ext4_xattr_inode_set_ref(inode, 1); + } else { + inode_lock(inode); + inode->i_flags |= S_NOQUOTA; + inode_unlock(inode); + } + + *ea_inode = inode; + return 0; +error: + iput(inode); + return err; +} + +static int +ext4_xattr_inode_verify_hashes(struct inode *ea_inode, + struct ext4_xattr_entry *entry, void *buffer, + size_t size) +{ + u32 hash; + + /* Verify stored hash matches calculated hash. */ + hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size); + if (hash != ext4_xattr_inode_get_hash(ea_inode)) + return -EFSCORRUPTED; + + if (entry) { + __le32 e_hash, tmp_data; + + /* Verify entry hash. */ + tmp_data = cpu_to_le32(hash); + e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, + &tmp_data, 1); + if (e_hash != entry->e_hash) + return -EFSCORRUPTED; + } + return 0; +} + +/* + * Read xattr value from the EA inode. + */ +static int +ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry, + void *buffer, size_t size) +{ + struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); + struct inode *ea_inode; + int err; + + err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), + le32_to_cpu(entry->e_hash), &ea_inode); + if (err) { + ea_inode = NULL; + goto out; + } + + if (i_size_read(ea_inode) != size) { + ext4_warning_inode(ea_inode, + "ea_inode file size=%llu entry size=%zu", + i_size_read(ea_inode), size); + err = -EFSCORRUPTED; + goto out; + } + + err = ext4_xattr_inode_read(ea_inode, buffer, size); + if (err) + goto out; + + if (!ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) { + err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, + size); + if (err) { + ext4_warning_inode(ea_inode, + "EA inode hash validation failed"); + goto out; + } + + if (ea_inode_cache) + mb_cache_entry_create(ea_inode_cache, GFP_NOFS, + ext4_xattr_inode_get_hash(ea_inode), + ea_inode->i_ino, true /* reusable */); + } +out: + iput(ea_inode); + return err; +} + static int ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) @@ -277,7 +494,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, struct ext4_xattr_entry *entry; size_t size; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); @@ -298,7 +515,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, error = -EFSCORRUPTED; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_block_cache_insert(ea_block_cache, bh); entry = BFIRST(bh); error = ext4_xattr_find_entry(&entry, name_index, name, 1); if (error) @@ -308,8 +525,15 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, error = -ERANGE; if (size > buffer_size) goto cleanup; - memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs), - size); + if (entry->e_value_inum) { + error = ext4_xattr_inode_get(inode, entry, buffer, + size); + if (error) + goto cleanup; + } else { + memcpy(buffer, bh->b_data + + le16_to_cpu(entry->e_value_offs), size); + } } error = size; @@ -350,8 +574,15 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, error = -ERANGE; if (size > buffer_size) goto cleanup; - memcpy(buffer, (void *)IFIRST(header) + - le16_to_cpu(entry->e_value_offs), size); + if (entry->e_value_inum) { + error = ext4_xattr_inode_get(inode, entry, buffer, + size); + if (error) + goto cleanup; + } else { + memcpy(buffer, (void *)IFIRST(header) + + le16_to_cpu(entry->e_value_offs), size); + } } error = size; @@ -428,7 +659,6 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); @@ -450,7 +680,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) error = -EFSCORRUPTED; goto cleanup; } - ext4_xattr_cache_insert(ext4_mb_cache, bh); + ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: @@ -539,15 +769,456 @@ static void ext4_xattr_update_super_block(handle_t *handle, } } +int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) +{ + struct ext4_iloc iloc = { .bh = NULL }; + struct buffer_head *bh = NULL; + struct ext4_inode *raw_inode; + struct ext4_xattr_ibody_header *header; + struct ext4_xattr_entry *entry; + qsize_t ea_inode_refs = 0; + void *end; + int ret; + + lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem); + + if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { + ret = ext4_get_inode_loc(inode, &iloc); + if (ret) + goto out; + raw_inode = ext4_raw_inode(&iloc); + header = IHDR(inode, raw_inode); + end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; + ret = xattr_check_inode(inode, header, end); + if (ret) + goto out; + + for (entry = IFIRST(header); !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + ea_inode_refs++; + } + + if (EXT4_I(inode)->i_file_acl) { + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) { + ret = -EIO; + goto out; + } + + if (ext4_xattr_check_block(inode, bh)) { + ret = -EFSCORRUPTED; + goto out; + } + + for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + ea_inode_refs++; + } + *usage = ea_inode_refs + 1; + ret = 0; +out: + brelse(iloc.bh); + brelse(bh); + return ret; +} + +static inline size_t round_up_cluster(struct inode *inode, size_t length) +{ + struct super_block *sb = inode->i_sb; + size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits + + inode->i_blkbits); + size_t mask = ~(cluster_size - 1); + + return (length + cluster_size - 1) & mask; +} + +static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len) +{ + int err; + + err = dquot_alloc_inode(inode); + if (err) + return err; + err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len)); + if (err) + dquot_free_inode(inode); + return err; +} + +static void ext4_xattr_inode_free_quota(struct inode *parent, + struct inode *ea_inode, + size_t len) +{ + if (ea_inode && + ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) + return; + dquot_free_space_nodirty(parent, round_up_cluster(parent, len)); + dquot_free_inode(parent); +} + +int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, + struct buffer_head *block_bh, size_t value_len, + bool is_create) +{ + int credits; + int blocks; + + /* + * 1) Owner inode update + * 2) Ref count update on old xattr block + * 3) new xattr block + * 4) block bitmap update for new xattr block + * 5) group descriptor for new xattr block + * 6) block bitmap update for old xattr block + * 7) group descriptor for old block + * + * 6 & 7 can happen if we have two racing threads T_a and T_b + * which are each trying to set an xattr on inodes I_a and I_b + * which were both initially sharing an xattr block. + */ + credits = 7; + + /* Quota updates. */ + credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb); + + /* + * In case of inline data, we may push out the data to a block, + * so we need to reserve credits for this eventuality + */ + if (inode && ext4_has_inline_data(inode)) + credits += ext4_writepage_trans_blocks(inode) + 1; + + /* We are done if ea_inode feature is not enabled. */ + if (!ext4_has_feature_ea_inode(sb)) + return credits; + + /* New ea_inode, inode map, block bitmap, group descriptor. */ + credits += 4; + + /* Data blocks. */ + blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits; + + /* Indirection block or one level of extent tree. */ + blocks += 1; + + /* Block bitmap and group descriptor updates for each block. */ + credits += blocks * 2; + + /* Blocks themselves. */ + credits += blocks; + + if (!is_create) { + /* Dereference ea_inode holding old xattr value. + * Old ea_inode, inode map, block bitmap, group descriptor. + */ + credits += 4; + + /* Data blocks for old ea_inode. */ + blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits; + + /* Indirection block or one level of extent tree for old + * ea_inode. + */ + blocks += 1; + + /* Block bitmap and group descriptor updates for each block. */ + credits += blocks * 2; + } + + /* We may need to clone the existing xattr block in which case we need + * to increment ref counts for existing ea_inodes referenced by it. + */ + if (block_bh) { + struct ext4_xattr_entry *entry = BFIRST(block_bh); + + for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) + if (entry->e_value_inum) + /* Ref count update on ea_inode. */ + credits += 1; + } + return credits; +} + +static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode, + int credits, struct buffer_head *bh, + bool dirty, bool block_csum) +{ + int error; + + if (!ext4_handle_valid(handle)) + return 0; + + if (handle->h_buffer_credits >= credits) + return 0; + + error = ext4_journal_extend(handle, credits - handle->h_buffer_credits); + if (!error) + return 0; + if (error < 0) { + ext4_warning(inode->i_sb, "Extend journal (error %d)", error); + return error; + } + + if (bh && dirty) { + if (block_csum) + ext4_xattr_block_csum_set(inode, bh); + error = ext4_handle_dirty_metadata(handle, NULL, bh); + if (error) { + ext4_warning(inode->i_sb, "Handle metadata (error %d)", + error); + return error; + } + } + + error = ext4_journal_restart(handle, credits); + if (error) { + ext4_warning(inode->i_sb, "Restart journal (error %d)", error); + return error; + } + + if (bh) { + error = ext4_journal_get_write_access(handle, bh); + if (error) { + ext4_warning(inode->i_sb, + "Get write access failed (error %d)", + error); + return error; + } + } + return 0; +} + +static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, + int ref_change) +{ + struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode); + struct ext4_iloc iloc; + s64 ref_count; + u32 hash; + int ret; + + inode_lock(ea_inode); + + ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); + if (ret) { + iloc.bh = NULL; + goto out; + } + + ref_count = ext4_xattr_inode_get_ref(ea_inode); + ref_count += ref_change; + ext4_xattr_inode_set_ref(ea_inode, ref_count); + + if (ref_change > 0) { + WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld", + ea_inode->i_ino, ref_count); + + if (ref_count == 1) { + WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u", + ea_inode->i_ino, ea_inode->i_nlink); + + set_nlink(ea_inode, 1); + ext4_orphan_del(handle, ea_inode); + + if (ea_inode_cache) { + hash = ext4_xattr_inode_get_hash(ea_inode); + mb_cache_entry_create(ea_inode_cache, + GFP_NOFS, hash, + ea_inode->i_ino, + true /* reusable */); + } + } + } else { + WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld", + ea_inode->i_ino, ref_count); + + if (ref_count == 0) { + WARN_ONCE(ea_inode->i_nlink != 1, + "EA inode %lu i_nlink=%u", + ea_inode->i_ino, ea_inode->i_nlink); + + clear_nlink(ea_inode); + ext4_orphan_add(handle, ea_inode); + + if (ea_inode_cache) { + hash = ext4_xattr_inode_get_hash(ea_inode); + mb_cache_entry_delete(ea_inode_cache, hash, + ea_inode->i_ino); + } + } + } + + ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); + iloc.bh = NULL; + if (ret) + ext4_warning_inode(ea_inode, + "ext4_mark_iloc_dirty() failed ret=%d", ret); +out: + brelse(iloc.bh); + inode_unlock(ea_inode); + return ret; +} + +static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode) +{ + return ext4_xattr_inode_update_ref(handle, ea_inode, 1); +} + +static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode) +{ + return ext4_xattr_inode_update_ref(handle, ea_inode, -1); +} + +static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent, + struct ext4_xattr_entry *first) +{ + struct inode *ea_inode; + struct ext4_xattr_entry *entry; + struct ext4_xattr_entry *failed_entry; + unsigned int ea_ino; + int err, saved_err; + + for (entry = first; !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + ea_ino = le32_to_cpu(entry->e_value_inum); + err = ext4_xattr_inode_iget(parent, ea_ino, + le32_to_cpu(entry->e_hash), + &ea_inode); + if (err) + goto cleanup; + err = ext4_xattr_inode_inc_ref(handle, ea_inode); + if (err) { + ext4_warning_inode(ea_inode, "inc ref error %d", err); + iput(ea_inode); + goto cleanup; + } + iput(ea_inode); + } + return 0; + +cleanup: + saved_err = err; + failed_entry = entry; + + for (entry = first; entry != failed_entry; + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + ea_ino = le32_to_cpu(entry->e_value_inum); + err = ext4_xattr_inode_iget(parent, ea_ino, + le32_to_cpu(entry->e_hash), + &ea_inode); + if (err) { + ext4_warning(parent->i_sb, + "cleanup ea_ino %u iget error %d", ea_ino, + err); + continue; + } + err = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (err) + ext4_warning_inode(ea_inode, "cleanup dec ref error %d", + err); + iput(ea_inode); + } + return saved_err; +} + +static void +ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, + struct buffer_head *bh, + struct ext4_xattr_entry *first, bool block_csum, + struct ext4_xattr_inode_array **ea_inode_array, + int extra_credits, bool skip_quota) +{ + struct inode *ea_inode; + struct ext4_xattr_entry *entry; + bool dirty = false; + unsigned int ea_ino; + int err; + int credits; + + /* One credit for dec ref on ea_inode, one for orphan list addition, */ + credits = 2 + extra_credits; + + for (entry = first; !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + ea_ino = le32_to_cpu(entry->e_value_inum); + err = ext4_xattr_inode_iget(parent, ea_ino, + le32_to_cpu(entry->e_hash), + &ea_inode); + if (err) + continue; + + err = ext4_expand_inode_array(ea_inode_array, ea_inode); + if (err) { + ext4_warning_inode(ea_inode, + "Expand inode array err=%d", err); + iput(ea_inode); + continue; + } + + err = ext4_xattr_ensure_credits(handle, parent, credits, bh, + dirty, block_csum); + if (err) { + ext4_warning_inode(ea_inode, "Ensure credits err=%d", + err); + continue; + } + + err = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (err) { + ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d", + err); + continue; + } + + if (!skip_quota) + ext4_xattr_inode_free_quota(parent, ea_inode, + le32_to_cpu(entry->e_value_size)); + + /* + * Forget about ea_inode within the same transaction that + * decrements the ref count. This avoids duplicate decrements in + * case the rest of the work spills over to subsequent + * transactions. + */ + entry->e_value_inum = 0; + entry->e_value_size = 0; + + dirty = true; + } + + if (dirty) { + /* + * Note that we are deliberately skipping csum calculation for + * the final update because we do not expect any journal + * restarts until xattr block is freed. + */ + + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + ext4_warning_inode(parent, + "handle dirty metadata err=%d", err); + } +} + /* * Release the xattr block BH: If the reference count is > 1, decrement it; * otherwise free the block. */ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, - struct buffer_head *bh) + struct buffer_head *bh, + struct ext4_xattr_inode_array **ea_inode_array, + int extra_credits) { - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); u32 hash, ref; int error = 0; @@ -565,9 +1236,19 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ - mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr); + if (ea_block_cache) + mb_cache_entry_delete(ea_block_cache, hash, + bh->b_blocknr); get_bh(bh); unlock_buffer(bh); + + if (ext4_has_feature_ea_inode(inode->i_sb)) + ext4_xattr_inode_dec_ref_all(handle, inode, bh, + BFIRST(bh), + true /* block_csum */, + ea_inode_array, + extra_credits, + true /* skip_quota */); ext4_free_blocks(handle, inode, bh, 0, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); @@ -577,11 +1258,13 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) { struct mb_cache_entry *ce; - ce = mb_cache_entry_get(ext4_mb_cache, hash, - bh->b_blocknr); - if (ce) { - ce->e_reusable = 1; - mb_cache_entry_put(ext4_mb_cache, ce); + if (ea_block_cache) { + ce = mb_cache_entry_get(ea_block_cache, hash, + bh->b_blocknr); + if (ce) { + ce->e_reusable = 1; + mb_cache_entry_put(ea_block_cache, ce); + } } } @@ -620,7 +1303,7 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, size_t *min_offs, void *base, int *total) { for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - if (last->e_value_size) { + if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < *min_offs) *min_offs = offs; @@ -631,113 +1314,457 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, return (*min_offs - ((void *)last - base) - sizeof(__u32)); } -static int -ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) +/* + * Write the value of the EA in an inode. + */ +static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, + const void *buf, int bufsize) +{ + struct buffer_head *bh = NULL; + unsigned long block = 0; + int blocksize = ea_inode->i_sb->s_blocksize; + int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits; + int csize, wsize = 0; + int ret = 0; + int retries = 0; + +retry: + while (ret >= 0 && ret < max_blocks) { + struct ext4_map_blocks map; + map.m_lblk = block += ret; + map.m_len = max_blocks -= ret; + + ret = ext4_map_blocks(handle, ea_inode, &map, + EXT4_GET_BLOCKS_CREATE); + if (ret <= 0) { + ext4_mark_inode_dirty(handle, ea_inode); + if (ret == -ENOSPC && + ext4_should_retry_alloc(ea_inode->i_sb, &retries)) { + ret = 0; + goto retry; + } + break; + } + } + + if (ret < 0) + return ret; + + block = 0; + while (wsize < bufsize) { + if (bh != NULL) + brelse(bh); + csize = (bufsize - wsize) > blocksize ? blocksize : + bufsize - wsize; + bh = ext4_getblk(handle, ea_inode, block, 0); + if (IS_ERR(bh)) + return PTR_ERR(bh); + ret = ext4_journal_get_write_access(handle, bh); + if (ret) + goto out; + + memcpy(bh->b_data, buf, csize); + set_buffer_uptodate(bh); + ext4_handle_dirty_metadata(handle, ea_inode, bh); + + buf += csize; + wsize += csize; + block += 1; + } + + inode_lock(ea_inode); + i_size_write(ea_inode, wsize); + ext4_update_i_disksize(ea_inode, wsize); + inode_unlock(ea_inode); + + ext4_mark_inode_dirty(handle, ea_inode); + +out: + brelse(bh); + + return ret; +} + +/* + * Create an inode to store the value of a large EA. + */ +static struct inode *ext4_xattr_inode_create(handle_t *handle, + struct inode *inode, u32 hash) +{ + struct inode *ea_inode = NULL; + uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; + int err; + + /* + * Let the next inode be the goal, so we try and allocate the EA inode + * in the same group, or nearby one. + */ + ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, + S_IFREG | 0600, NULL, inode->i_ino + 1, owner, + EXT4_EA_INODE_FL); + if (!IS_ERR(ea_inode)) { + ea_inode->i_op = &ext4_file_inode_operations; + ea_inode->i_fop = &ext4_file_operations; + ext4_set_aops(ea_inode); + ext4_xattr_inode_set_class(ea_inode); + unlock_new_inode(ea_inode); + ext4_xattr_inode_set_ref(ea_inode, 1); + ext4_xattr_inode_set_hash(ea_inode, hash); + err = ext4_mark_inode_dirty(handle, ea_inode); + if (!err) + err = ext4_inode_attach_jinode(ea_inode); + if (err) { + iput(ea_inode); + return ERR_PTR(err); + } + + /* + * Xattr inodes are shared therefore quota charging is performed + * at a higher level. + */ + dquot_free_inode(ea_inode); + dquot_drop(ea_inode); + inode_lock(ea_inode); + ea_inode->i_flags |= S_NOQUOTA; + inode_unlock(ea_inode); + } + + return ea_inode; +} + +static struct inode * +ext4_xattr_inode_cache_find(struct inode *inode, const void *value, + size_t value_len, u32 hash) +{ + struct inode *ea_inode; + struct mb_cache_entry *ce; + struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); + void *ea_data; + + if (!ea_inode_cache) + return NULL; + + ce = mb_cache_entry_find_first(ea_inode_cache, hash); + if (!ce) + return NULL; + + ea_data = ext4_kvmalloc(value_len, GFP_NOFS); + if (!ea_data) { + mb_cache_entry_put(ea_inode_cache, ce); + return NULL; + } + + while (ce) { + ea_inode = ext4_iget(inode->i_sb, ce->e_value); + if (!IS_ERR(ea_inode) && + !is_bad_inode(ea_inode) && + (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) && + i_size_read(ea_inode) == value_len && + !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && + !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, + value_len) && + !memcmp(value, ea_data, value_len)) { + mb_cache_entry_touch(ea_inode_cache, ce); + mb_cache_entry_put(ea_inode_cache, ce); + kvfree(ea_data); + return ea_inode; + } + + if (!IS_ERR(ea_inode)) + iput(ea_inode); + ce = mb_cache_entry_find_next(ea_inode_cache, ce); + } + kvfree(ea_data); + return NULL; +} + +/* + * Add value of the EA in an inode. + */ +static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, + const void *value, size_t value_len, + struct inode **ret_inode) +{ + struct inode *ea_inode; + u32 hash; + int err; + + hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len); + ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash); + if (ea_inode) { + err = ext4_xattr_inode_inc_ref(handle, ea_inode); + if (err) { + iput(ea_inode); + return err; + } + + *ret_inode = ea_inode; + return 0; + } + + /* Create an inode for the EA value */ + ea_inode = ext4_xattr_inode_create(handle, inode, hash); + if (IS_ERR(ea_inode)) + return PTR_ERR(ea_inode); + + err = ext4_xattr_inode_write(handle, ea_inode, value, value_len); + if (err) { + ext4_xattr_inode_dec_ref(handle, ea_inode); + iput(ea_inode); + return err; + } + + if (EA_INODE_CACHE(inode)) + mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash, + ea_inode->i_ino, true /* reusable */); + + *ret_inode = ea_inode; + return 0; +} + +/* + * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode + * feature is enabled. + */ +#define EXT4_XATTR_BLOCK_RESERVE(inode) min(i_blocksize(inode)/8, 1024U) + +static int ext4_xattr_set_entry(struct ext4_xattr_info *i, + struct ext4_xattr_search *s, + handle_t *handle, struct inode *inode, + bool is_block) { struct ext4_xattr_entry *last; - size_t free, min_offs = s->end - s->base, name_len = strlen(i->name); + struct ext4_xattr_entry *here = s->here; + size_t min_offs = s->end - s->base, name_len = strlen(i->name); + int in_inode = i->in_inode; + struct inode *old_ea_inode = NULL; + struct inode *new_ea_inode = NULL; + size_t old_size, new_size; + int ret; + + /* Space used by old and new values. */ + old_size = (!s->not_found && !here->e_value_inum) ? + EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0; + new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0; + + /* + * Optimization for the simple case when old and new values have the + * same padded sizes. Not applicable if external inodes are involved. + */ + if (new_size && new_size == old_size) { + size_t offs = le16_to_cpu(here->e_value_offs); + void *val = s->base + offs; + + here->e_value_size = cpu_to_le32(i->value_len); + if (i->value == EXT4_ZERO_XATTR_VALUE) { + memset(val, 0, new_size); + } else { + memcpy(val, i->value, i->value_len); + /* Clear padding bytes. */ + memset(val + i->value_len, 0, new_size - i->value_len); + } + goto update_hash; + } /* Compute min_offs and last. */ last = s->first; for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - if (last->e_value_size) { + if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) min_offs = offs; } } - free = min_offs - ((void *)last - s->base) - sizeof(__u32); - if (!s->not_found) { - if (s->here->e_value_size) { - size_t size = le32_to_cpu(s->here->e_value_size); - free += EXT4_XATTR_SIZE(size); - } - free += EXT4_XATTR_LEN(name_len); - } + + /* Check whether we have enough space. */ if (i->value) { - if (free < EXT4_XATTR_LEN(name_len) + - EXT4_XATTR_SIZE(i->value_len)) - return -ENOSPC; + size_t free; + + free = min_offs - ((void *)last - s->base) - sizeof(__u32); + if (!s->not_found) + free += EXT4_XATTR_LEN(name_len) + old_size; + + if (free < EXT4_XATTR_LEN(name_len) + new_size) { + ret = -ENOSPC; + goto out; + } + + /* + * If storing the value in an external inode is an option, + * reserve space for xattr entries/names in the external + * attribute block so that a long value does not occupy the + * whole space and prevent futher entries being added. + */ + if (ext4_has_feature_ea_inode(inode->i_sb) && + new_size && is_block && + (min_offs + old_size - new_size) < + EXT4_XATTR_BLOCK_RESERVE(inode)) { + ret = -ENOSPC; + goto out; + } } - if (i->value && s->not_found) { - /* Insert the new name. */ - size_t size = EXT4_XATTR_LEN(name_len); - size_t rest = (void *)last - (void *)s->here + sizeof(__u32); - memmove((void *)s->here + size, s->here, rest); - memset(s->here, 0, size); - s->here->e_name_index = i->name_index; - s->here->e_name_len = name_len; - memcpy(s->here->e_name, i->name, name_len); - } else { - if (s->here->e_value_size) { - void *first_val = s->base + min_offs; - size_t offs = le16_to_cpu(s->here->e_value_offs); - void *val = s->base + offs; - size_t size = EXT4_XATTR_SIZE( - le32_to_cpu(s->here->e_value_size)); - - if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) { - /* The old and the new value have the same - size. Just replace. */ - s->here->e_value_size = - cpu_to_le32(i->value_len); - if (i->value == EXT4_ZERO_XATTR_VALUE) { - memset(val, 0, size); - } else { - /* Clear pad bytes first. */ - memset(val + size - EXT4_XATTR_PAD, 0, - EXT4_XATTR_PAD); - memcpy(val, i->value, i->value_len); - } - return 0; - } + /* + * Getting access to old and new ea inodes is subject to failures. + * Finish that work before doing any modifications to the xattr data. + */ + if (!s->not_found && here->e_value_inum) { + ret = ext4_xattr_inode_iget(inode, + le32_to_cpu(here->e_value_inum), + le32_to_cpu(here->e_hash), + &old_ea_inode); + if (ret) { + old_ea_inode = NULL; + goto out; + } + } + if (i->value && in_inode) { + WARN_ON_ONCE(!i->value_len); + + ret = ext4_xattr_inode_alloc_quota(inode, i->value_len); + if (ret) + goto out; + + ret = ext4_xattr_inode_lookup_create(handle, inode, i->value, + i->value_len, + &new_ea_inode); + if (ret) { + new_ea_inode = NULL; + ext4_xattr_inode_free_quota(inode, NULL, i->value_len); + goto out; + } + } - /* Remove the old value. */ - memmove(first_val + size, first_val, val - first_val); - memset(first_val, 0, size); - s->here->e_value_size = 0; - s->here->e_value_offs = 0; - min_offs += size; - - /* Adjust all value offsets. */ - last = s->first; - while (!IS_LAST_ENTRY(last)) { - size_t o = le16_to_cpu(last->e_value_offs); - if (last->e_value_size && o < offs) - last->e_value_offs = - cpu_to_le16(o + size); - last = EXT4_XATTR_NEXT(last); + if (old_ea_inode) { + /* We are ready to release ref count on the old_ea_inode. */ + ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode); + if (ret) { + /* Release newly required ref count on new_ea_inode. */ + if (new_ea_inode) { + int err; + + err = ext4_xattr_inode_dec_ref(handle, + new_ea_inode); + if (err) + ext4_warning_inode(new_ea_inode, + "dec ref new_ea_inode err=%d", + err); + ext4_xattr_inode_free_quota(inode, new_ea_inode, + i->value_len); } + goto out; } - if (!i->value) { - /* Remove the old name. */ - size_t size = EXT4_XATTR_LEN(name_len); - last = ENTRY((void *)last - size); - memmove(s->here, (void *)s->here + size, - (void *)last - (void *)s->here + sizeof(__u32)); - memset(last, 0, size); + + ext4_xattr_inode_free_quota(inode, old_ea_inode, + le32_to_cpu(here->e_value_size)); + } + + /* No failures allowed past this point. */ + + if (!s->not_found && here->e_value_offs) { + /* Remove the old value. */ + void *first_val = s->base + min_offs; + size_t offs = le16_to_cpu(here->e_value_offs); + void *val = s->base + offs; + + memmove(first_val + old_size, first_val, val - first_val); + memset(first_val, 0, old_size); + min_offs += old_size; + + /* Adjust all value offsets. */ + last = s->first; + while (!IS_LAST_ENTRY(last)) { + size_t o = le16_to_cpu(last->e_value_offs); + + if (!last->e_value_inum && + last->e_value_size && o < offs) + last->e_value_offs = cpu_to_le16(o + old_size); + last = EXT4_XATTR_NEXT(last); } } + if (!i->value) { + /* Remove old name. */ + size_t size = EXT4_XATTR_LEN(name_len); + + last = ENTRY((void *)last - size); + memmove(here, (void *)here + size, + (void *)last - (void *)here + sizeof(__u32)); + memset(last, 0, size); + } else if (s->not_found) { + /* Insert new name. */ + size_t size = EXT4_XATTR_LEN(name_len); + size_t rest = (void *)last - (void *)here + sizeof(__u32); + + memmove((void *)here + size, here, rest); + memset(here, 0, size); + here->e_name_index = i->name_index; + here->e_name_len = name_len; + memcpy(here->e_name, i->name, name_len); + } else { + /* This is an update, reset value info. */ + here->e_value_inum = 0; + here->e_value_offs = 0; + here->e_value_size = 0; + } + if (i->value) { - /* Insert the new value. */ - s->here->e_value_size = cpu_to_le32(i->value_len); - if (i->value_len) { - size_t size = EXT4_XATTR_SIZE(i->value_len); - void *val = s->base + min_offs - size; - s->here->e_value_offs = cpu_to_le16(min_offs - size); + /* Insert new value. */ + if (in_inode) { + here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino); + } else if (i->value_len) { + void *val = s->base + min_offs - new_size; + + here->e_value_offs = cpu_to_le16(min_offs - new_size); if (i->value == EXT4_ZERO_XATTR_VALUE) { - memset(val, 0, size); + memset(val, 0, new_size); } else { - /* Clear the pad bytes first. */ - memset(val + size - EXT4_XATTR_PAD, 0, - EXT4_XATTR_PAD); memcpy(val, i->value, i->value_len); + /* Clear padding bytes. */ + memset(val + i->value_len, 0, + new_size - i->value_len); } } + here->e_value_size = cpu_to_le32(i->value_len); } - return 0; + +update_hash: + if (i->value) { + __le32 hash = 0; + + /* Entry hash calculation. */ + if (in_inode) { + __le32 crc32c_hash; + + /* + * Feed crc32c hash instead of the raw value for entry + * hash calculation. This is to avoid walking + * potentially long value buffer again. + */ + crc32c_hash = cpu_to_le32( + ext4_xattr_inode_get_hash(new_ea_inode)); + hash = ext4_xattr_hash_entry(here->e_name, + here->e_name_len, + &crc32c_hash, 1); + } else if (is_block) { + __le32 *value = s->base + le16_to_cpu( + here->e_value_offs); + + hash = ext4_xattr_hash_entry(here->e_name, + here->e_name_len, value, + new_size >> 2); + } + here->e_hash = hash; + } + + if (is_block) + ext4_xattr_rehash((struct ext4_xattr_header *)s->base); + + ret = 0; +out: + iput(old_ea_inode); + iput(new_ea_inode); + return ret; } struct ext4_xattr_block_find { @@ -794,15 +1821,18 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, { struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; - struct ext4_xattr_search *s = &bs->s; + struct ext4_xattr_search s_copy = bs->s; + struct ext4_xattr_search *s = &s_copy; struct mb_cache_entry *ce = NULL; int error = 0; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); + struct inode *ea_inode = NULL, *tmp_inode; + size_t old_ea_inode_quota = 0; + unsigned int ea_ino; + #define header(x) ((struct ext4_xattr_header *)(x)) - if (i->value && i->value_len > sb->s_blocksize) - return -ENOSPC; if (s->base) { BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, bs->bh); @@ -818,17 +1848,12 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, * ext4_xattr_block_set() to reliably detect modified * block */ - mb_cache_entry_delete_block(ext4_mb_cache, hash, - bs->bh->b_blocknr); + if (ea_block_cache) + mb_cache_entry_delete(ea_block_cache, hash, + bs->bh->b_blocknr); ea_bdebug(bs->bh, "modifying in-place"); - error = ext4_xattr_set_entry(i, s); - if (!error) { - if (!IS_LAST_ENTRY(s->first)) - ext4_xattr_rehash(header(s->base), - s->here); - ext4_xattr_cache_insert(ext4_mb_cache, - bs->bh); - } + error = ext4_xattr_set_entry(i, s, handle, inode, + true /* is_block */); ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) @@ -854,6 +1879,36 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, header(s->base)->h_refcount = cpu_to_le32(1); s->here = ENTRY(s->base + offset); s->end = s->base + bs->bh->b_size; + + /* + * If existing entry points to an xattr inode, we need + * to prevent ext4_xattr_set_entry() from decrementing + * ref count on it because the reference belongs to the + * original block. In this case, make the entry look + * like it has an empty value. + */ + if (!s->not_found && s->here->e_value_inum) { + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &tmp_inode); + if (error) + goto cleanup; + + if (!ext4_test_inode_state(tmp_inode, + EXT4_STATE_LUSTRE_EA_INODE)) { + /* + * Defer quota free call for previous + * inode until success is guaranteed. + */ + old_ea_inode_quota = le32_to_cpu( + s->here->e_value_size); + } + iput(tmp_inode); + + s->here->e_value_inum = 0; + s->here->e_value_size = 0; + } } } else { /* Allocate a buffer where we construct the new block. */ @@ -870,17 +1925,33 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, s->end = s->base + sb->s_blocksize; } - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */); if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; - if (!IS_LAST_ENTRY(s->first)) - ext4_xattr_rehash(header(s->base), s->here); + + if (i->value && s->here->e_value_inum) { + /* + * A ref count on ea_inode has been taken as part of the call to + * ext4_xattr_set_entry() above. We would like to drop this + * extra ref but we have to wait until the xattr block is + * initialized and has its own ref count on the ea_inode. + */ + ea_ino = le32_to_cpu(s->here->e_value_inum); + error = ext4_xattr_inode_iget(inode, ea_ino, + le32_to_cpu(s->here->e_hash), + &ea_inode); + if (error) { + ea_inode = NULL; + goto cleanup; + } + } inserted: if (!IS_LAST_ENTRY(s->first)) { - new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce); + new_bh = ext4_xattr_block_cache_find(inode, header(s->base), + &ce); if (new_bh) { /* We found an identical block in the cache. */ if (new_bh == bs->bh) @@ -925,7 +1996,7 @@ inserted: EXT4_C2B(EXT4_SB(sb), 1)); brelse(new_bh); - mb_cache_entry_put(ext4_mb_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); ce = NULL; new_bh = NULL; goto inserted; @@ -944,12 +2015,13 @@ inserted: if (error) goto cleanup_dquot; } - mb_cache_entry_touch(ext4_mb_cache, ce); - mb_cache_entry_put(ext4_mb_cache, ce); + mb_cache_entry_touch(ea_block_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ ea_bdebug(bs->bh, "keeping this block"); + ext4_xattr_block_cache_insert(ea_block_cache, bs->bh); new_bh = bs->bh; get_bh(new_bh); } else { @@ -984,6 +2056,22 @@ getblk_failed: EXT4_FREE_BLOCKS_METADATA); goto cleanup; } + error = ext4_xattr_inode_inc_ref_all(handle, inode, + ENTRY(header(s->base)+1)); + if (error) + goto getblk_failed; + if (ea_inode) { + /* Drop the extra ref on ea_inode. */ + error = ext4_xattr_inode_dec_ref(handle, + ea_inode); + if (error) + ext4_warning_inode(ea_inode, + "dec ref error=%d", + error); + iput(ea_inode); + ea_inode = NULL; + } + lock_buffer(new_bh); error = ext4_journal_get_create_access(handle, new_bh); if (error) { @@ -995,7 +2083,7 @@ getblk_failed: ext4_xattr_block_csum_set(inode, new_bh); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); - ext4_xattr_cache_insert(ext4_mb_cache, new_bh); + ext4_xattr_block_cache_insert(ea_block_cache, new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) @@ -1003,17 +2091,40 @@ getblk_failed: } } + if (old_ea_inode_quota) + ext4_xattr_inode_free_quota(inode, NULL, old_ea_inode_quota); + /* Update the inode. */ EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; /* Drop the previous xattr block. */ - if (bs->bh && bs->bh != new_bh) - ext4_xattr_release_block(handle, inode, bs->bh); + if (bs->bh && bs->bh != new_bh) { + struct ext4_xattr_inode_array *ea_inode_array = NULL; + + ext4_xattr_release_block(handle, inode, bs->bh, + &ea_inode_array, + 0 /* extra_credits */); + ext4_xattr_inode_array_free(ea_inode_array); + } error = 0; cleanup: + if (ea_inode) { + int error2; + + error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); + if (error2) + ext4_warning_inode(ea_inode, "dec ref error=%d", + error2); + + /* If there was an error, revert the quota charge. */ + if (error) + ext4_xattr_inode_free_quota(inode, ea_inode, + i_size_read(ea_inode)); + iput(ea_inode); + } if (ce) - mb_cache_entry_put(ext4_mb_cache, ce); + mb_cache_entry_put(ea_block_cache, ce); brelse(new_bh); if (!(bs->bh && s->base == bs->bh->b_data)) kfree(s->base); @@ -1070,7 +2181,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) { if (error == -ENOSPC && ext4_has_inline_data(inode)) { @@ -1082,7 +2193,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, error = ext4_xattr_ibody_find(inode, i, is); if (error) return error; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, + false /* is_block */); } if (error) return error; @@ -1098,7 +2210,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, return 0; } -static int ext4_xattr_ibody_set(struct inode *inode, +static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { @@ -1108,7 +2220,7 @@ static int ext4_xattr_ibody_set(struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */); if (error) return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); @@ -1127,12 +2239,31 @@ static int ext4_xattr_value_same(struct ext4_xattr_search *s, { void *value; + /* When e_value_inum is set the value is stored externally. */ + if (s->here->e_value_inum) + return 0; if (le32_to_cpu(s->here->e_value_size) != i->value_len) return 0; value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs); return !memcmp(value, i->value, i->value_len); } +static struct buffer_head *ext4_xattr_get_block(struct inode *inode) +{ + struct buffer_head *bh; + int error; + + if (!EXT4_I(inode)->i_file_acl) + return NULL; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) + return ERR_PTR(-EIO); + error = ext4_xattr_check_block(inode, bh); + if (error) + return ERR_PTR(error); + return bh; +} + /* * ext4_xattr_set_handle() * @@ -1155,7 +2286,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, .name = name, .value = value, .value_len = value_len, - + .in_inode = 0, }; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, @@ -1173,6 +2304,28 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, ext4_write_lock_xattr(inode, &no_expand); + /* Check journal credits under write lock. */ + if (ext4_handle_valid(handle)) { + struct buffer_head *bh; + int credits; + + bh = ext4_xattr_get_block(inode); + if (IS_ERR(bh)) { + error = PTR_ERR(bh); + goto cleanup; + } + + credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, + value_len, + flags & XATTR_CREATE); + brelse(bh); + + if (!ext4_handle_has_enough_credits(handle, credits)) { + error = -ENOSPC; + goto cleanup; + } + } + error = ext4_reserve_inode_write(handle, inode, &is.iloc); if (error) goto cleanup; @@ -1202,9 +2355,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, if (flags & XATTR_CREATE) goto cleanup; } + if (!value) { if (!is.s.not_found) - error = ext4_xattr_ibody_set(inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, &is); else if (!bs.s.not_found) error = ext4_xattr_block_set(handle, inode, &i, &bs); } else { @@ -1215,7 +2369,12 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i)) goto cleanup; - error = ext4_xattr_ibody_set(inode, &i, &is); + if (ext4_has_feature_ea_inode(inode->i_sb) && + (EXT4_XATTR_SIZE(i.value_len) > + EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize))) + i.in_inode = 1; +retry_inode: + error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (!error && !bs.s.not_found) { i.value = NULL; error = ext4_xattr_block_set(handle, inode, &i, &bs); @@ -1226,11 +2385,20 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, goto cleanup; } error = ext4_xattr_block_set(handle, inode, &i, &bs); - if (error) - goto cleanup; - if (!is.s.not_found) { + if (!error && !is.s.not_found) { i.value = NULL; - error = ext4_xattr_ibody_set(inode, &i, &is); + error = ext4_xattr_ibody_set(handle, inode, &i, + &is); + } else if (error == -ENOSPC) { + /* + * Xattr does not fit in the block, store at + * external inode if possible. + */ + if (ext4_has_feature_ea_inode(inode->i_sb) && + !i.in_inode) { + i.in_inode = 1; + goto retry_inode; + } } } } @@ -1256,6 +2424,33 @@ cleanup: return error; } +int ext4_xattr_set_credits(struct inode *inode, size_t value_len, + bool is_create, int *credits) +{ + struct buffer_head *bh; + int err; + + *credits = 0; + + if (!EXT4_SB(inode->i_sb)->s_journal) + return 0; + + down_read(&EXT4_I(inode)->xattr_sem); + + bh = ext4_xattr_get_block(inode); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + } else { + *credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, + value_len, is_create); + brelse(bh); + err = 0; + } + + up_read(&EXT4_I(inode)->xattr_sem); + return err; +} + /* * ext4_xattr_set() * @@ -1269,13 +2464,20 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { handle_t *handle; + struct super_block *sb = inode->i_sb; int error, retries = 0; - int credits = ext4_jbd2_credits_xattr(inode); + int credits; error = dquot_initialize(inode); if (error) return error; + retry: + error = ext4_xattr_set_credits(inode, value_len, flags & XATTR_CREATE, + &credits); + if (error) + return error; + handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) { error = PTR_ERR(handle); @@ -1286,7 +2488,7 @@ retry: value, value_len, flags); error2 = ext4_journal_stop(handle); if (error == -ENOSPC && - ext4_should_retry_alloc(inode->i_sb, &retries)) + ext4_should_retry_alloc(sb, &retries)) goto retry; if (error == 0) error = error2; @@ -1311,7 +2513,7 @@ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry, /* Adjust the value offsets of the entries */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - if (last->e_value_size) { + if (!last->e_value_inum && last->e_value_size) { new_offs = le16_to_cpu(last->e_value_offs) + value_offs_shift; last->e_value_offs = cpu_to_le16(new_offs); @@ -1331,18 +2533,16 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, struct ext4_xattr_ibody_find *is = NULL; struct ext4_xattr_block_find *bs = NULL; char *buffer = NULL, *b_entry_name = NULL; - size_t value_offs, value_size; + size_t value_size = le32_to_cpu(entry->e_value_size); struct ext4_xattr_info i = { .value = NULL, .value_len = 0, .name_index = entry->e_name_index, + .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); int error; - value_offs = le16_to_cpu(entry->e_value_offs); - value_size = le32_to_cpu(entry->e_value_size); - is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS); bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS); buffer = kmalloc(value_size, GFP_NOFS); @@ -1358,7 +2558,15 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, bs->bh = NULL; /* Save the entry name and the entry value */ - memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + if (entry->e_value_inum) { + error = ext4_xattr_inode_get(inode, entry, buffer, value_size); + if (error) + goto out; + } else { + size_t value_offs = le16_to_cpu(entry->e_value_offs); + memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size); + } + memcpy(b_entry_name, entry->e_name, entry->e_name_len); b_entry_name[entry->e_name_len] = '\0'; i.name = b_entry_name; @@ -1372,11 +2580,10 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, goto out; /* Remove the chosen entry from the inode */ - error = ext4_xattr_ibody_set(inode, &i, is); + error = ext4_xattr_ibody_set(handle, inode, &i, is); if (error) goto out; - i.name = b_entry_name; i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); @@ -1420,9 +2627,10 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, last = IFIRST(header); /* Find the entry best suited to be pushed into EA block */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { - total_size = - EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) + - EXT4_XATTR_LEN(last->e_name_len); + total_size = EXT4_XATTR_LEN(last->e_name_len); + if (!last->e_value_inum) + total_size += EXT4_XATTR_SIZE( + le32_to_cpu(last->e_value_size)); if (total_size <= bfree && total_size < min_total_size) { if (total_size + ifree < isize_diff) { @@ -1441,8 +2649,10 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, } entry_size = EXT4_XATTR_LEN(entry->e_name_len); - total_size = entry_size + - EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)); + total_size = entry_size; + if (!entry->e_value_inum) + total_size += EXT4_XATTR_SIZE( + le32_to_cpu(entry->e_value_size)); error = ext4_xattr_move_to_block(handle, inode, raw_inode, entry); if (error) @@ -1464,23 +2674,21 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; - struct buffer_head *bh = NULL; + struct buffer_head *bh; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + static unsigned int mnt_count; size_t min_offs; size_t ifree, bfree; int total_ino; void *base, *end; int error = 0, tried_min_extra_isize = 0; - int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize); + int s_min_extra_isize = le16_to_cpu(sbi->s_es->s_min_extra_isize); int isize_diff; /* How much do we need to grow i_extra_isize */ - int no_expand; - - if (ext4_write_trylock_xattr(inode, &no_expand) == 0) - return 0; retry: isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) - goto out; + return 0; header = IHDR(inode, raw_inode); @@ -1515,6 +2723,7 @@ retry: EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); error = -EFSCORRUPTED; + brelse(bh); goto cleanup; } base = BHDR(bh); @@ -1522,11 +2731,11 @@ retry: min_offs = end - base; bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base, NULL); + brelse(bh); if (bfree + ifree < isize_diff) { if (!tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; - brelse(bh); goto retry; } error = -ENOSPC; @@ -1544,7 +2753,6 @@ retry: s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; - brelse(bh); goto retry; } goto cleanup; @@ -1556,66 +2764,192 @@ shift: EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize, (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; - brelse(bh); -out: - ext4_write_unlock_xattr(inode, &no_expand); - return 0; cleanup: - brelse(bh); - /* - * Inode size expansion failed; don't try again - */ - no_expand = 1; - ext4_write_unlock_xattr(inode, &no_expand); + if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { + ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.", + inode->i_ino); + mnt_count = le16_to_cpu(sbi->s_es->s_mnt_count); + } return error; } +#define EIA_INCR 16 /* must be 2^n */ +#define EIA_MASK (EIA_INCR - 1) +/* Add the large xattr @inode into @ea_inode_array for deferred iput(). + * If @ea_inode_array is new or full it will be grown and the old + * contents copied over. + */ +static int +ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, + struct inode *inode) +{ + if (*ea_inode_array == NULL) { + /* + * Start with 15 inodes, so it fits into a power-of-two size. + * If *ea_inode_array is NULL, this is essentially offsetof() + */ + (*ea_inode_array) = + kmalloc(offsetof(struct ext4_xattr_inode_array, + inodes[EIA_MASK]), + GFP_NOFS); + if (*ea_inode_array == NULL) + return -ENOMEM; + (*ea_inode_array)->count = 0; + } else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) { + /* expand the array once all 15 + n * 16 slots are full */ + struct ext4_xattr_inode_array *new_array = NULL; + int count = (*ea_inode_array)->count; + + /* if new_array is NULL, this is essentially offsetof() */ + new_array = kmalloc( + offsetof(struct ext4_xattr_inode_array, + inodes[count + EIA_INCR]), + GFP_NOFS); + if (new_array == NULL) + return -ENOMEM; + memcpy(new_array, *ea_inode_array, + offsetof(struct ext4_xattr_inode_array, inodes[count])); + kfree(*ea_inode_array); + *ea_inode_array = new_array; + } + (*ea_inode_array)->inodes[(*ea_inode_array)->count++] = inode; + return 0; +} /* * ext4_xattr_delete_inode() * - * Free extended attribute resources associated with this inode. This - * is called immediately before an inode is freed. We have exclusive - * access to the inode. + * Free extended attribute resources associated with this inode. Traverse + * all entries and decrement reference on any xattr inodes associated with this + * inode. This is called immediately before an inode is freed. We have exclusive + * access to the inode. If an orphan inode is deleted it will also release its + * references on xattr block and xattr inodes. */ -void -ext4_xattr_delete_inode(handle_t *handle, struct inode *inode) +int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, + struct ext4_xattr_inode_array **ea_inode_array, + int extra_credits) { struct buffer_head *bh = NULL; + struct ext4_xattr_ibody_header *header; + struct ext4_iloc iloc = { .bh = NULL }; + struct ext4_xattr_entry *entry; + struct inode *ea_inode; + int error; - if (!EXT4_I(inode)->i_file_acl) - goto cleanup; - bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); - if (!bh) { - EXT4_ERROR_INODE(inode, "block %llu read error", - EXT4_I(inode)->i_file_acl); + error = ext4_xattr_ensure_credits(handle, inode, extra_credits, + NULL /* bh */, + false /* dirty */, + false /* block_csum */); + if (error) { + EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error); goto cleanup; } - if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || - BHDR(bh)->h_blocks != cpu_to_le32(1)) { - EXT4_ERROR_INODE(inode, "bad block %llu", - EXT4_I(inode)->i_file_acl); - goto cleanup; + + if (ext4_has_feature_ea_inode(inode->i_sb) && + ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { + + error = ext4_get_inode_loc(inode, &iloc); + if (error) { + EXT4_ERROR_INODE(inode, "inode loc (error %d)", error); + goto cleanup; + } + + error = ext4_journal_get_write_access(handle, iloc.bh); + if (error) { + EXT4_ERROR_INODE(inode, "write access (error %d)", + error); + goto cleanup; + } + + header = IHDR(inode, ext4_raw_inode(&iloc)); + if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC)) + ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh, + IFIRST(header), + false /* block_csum */, + ea_inode_array, + extra_credits, + false /* skip_quota */); } - ext4_xattr_release_block(handle, inode, bh); - EXT4_I(inode)->i_file_acl = 0; + if (EXT4_I(inode)->i_file_acl) { + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); + if (!bh) { + EXT4_ERROR_INODE(inode, "block %llu read error", + EXT4_I(inode)->i_file_acl); + error = -EIO; + goto cleanup; + } + error = ext4_xattr_check_block(inode, bh); + if (error) { + EXT4_ERROR_INODE(inode, "bad block %llu (error %d)", + EXT4_I(inode)->i_file_acl, error); + goto cleanup; + } + + if (ext4_has_feature_ea_inode(inode->i_sb)) { + for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); + entry = EXT4_XATTR_NEXT(entry)) { + if (!entry->e_value_inum) + continue; + error = ext4_xattr_inode_iget(inode, + le32_to_cpu(entry->e_value_inum), + le32_to_cpu(entry->e_hash), + &ea_inode); + if (error) + continue; + ext4_xattr_inode_free_quota(inode, ea_inode, + le32_to_cpu(entry->e_value_size)); + iput(ea_inode); + } + + } + + ext4_xattr_release_block(handle, inode, bh, ea_inode_array, + extra_credits); + /* + * Update i_file_acl value in the same transaction that releases + * block. + */ + EXT4_I(inode)->i_file_acl = 0; + error = ext4_mark_inode_dirty(handle, inode); + if (error) { + EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)", + error); + goto cleanup; + } + } + error = 0; cleanup: + brelse(iloc.bh); brelse(bh); + return error; +} + +void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array) +{ + int idx; + + if (ea_inode_array == NULL) + return; + + for (idx = 0; idx < ea_inode_array->count; ++idx) + iput(ea_inode_array->inodes[idx]); + kfree(ea_inode_array); } /* - * ext4_xattr_cache_insert() + * ext4_xattr_block_cache_insert() * - * Create a new entry in the extended attribute cache, and insert + * Create a new entry in the extended attribute block cache, and insert * it unless such an entry is already in the cache. * * Returns 0, or a negative error number on failure. */ static void -ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) +ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache, + struct buffer_head *bh) { struct ext4_xattr_header *header = BHDR(bh); __u32 hash = le32_to_cpu(header->h_hash); @@ -1623,7 +2957,9 @@ ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh) EXT4_XATTR_REFCOUNT_MAX; int error; - error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash, + if (!ea_block_cache) + return; + error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash, bh->b_blocknr, reusable); if (error) { if (error == -EBUSY) @@ -1655,11 +2991,11 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, entry1->e_name_index != entry2->e_name_index || entry1->e_name_len != entry2->e_name_len || entry1->e_value_size != entry2->e_value_size || + entry1->e_value_inum != entry2->e_value_inum || memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) return 1; - if (entry1->e_value_block != 0 || entry2->e_value_block != 0) - return -EFSCORRUPTED; - if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), + if (!entry1->e_value_inum && + memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), (char *)header2 + le16_to_cpu(entry2->e_value_offs), le32_to_cpu(entry1->e_value_size))) return 1; @@ -1673,7 +3009,7 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, } /* - * ext4_xattr_cache_find() + * ext4_xattr_block_cache_find() * * Find an identical extended attribute block. * @@ -1681,30 +3017,33 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1, * not found or an error occurred. */ static struct buffer_head * -ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, - struct mb_cache_entry **pce) +ext4_xattr_block_cache_find(struct inode *inode, + struct ext4_xattr_header *header, + struct mb_cache_entry **pce) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; - struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode); + struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); + if (!ea_block_cache) + return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); - ce = mb_cache_entry_find_first(ext4_mb_cache, hash); + ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; - bh = sb_bread(inode->i_sb, ce->e_block); + bh = sb_bread(inode->i_sb, ce->e_value); if (!bh) { EXT4_ERROR_INODE(inode, "block %lu read error", - (unsigned long) ce->e_block); + (unsigned long)ce->e_value); } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { *pce = ce; return bh; } brelse(bh); - ce = mb_cache_entry_find_next(ext4_mb_cache, ce); + ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } @@ -1717,30 +3056,22 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header, * * Compute the hash of an extended attribute. */ -static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header, - struct ext4_xattr_entry *entry) +static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, + size_t value_count) { __u32 hash = 0; - char *name = entry->e_name; - int n; - for (n = 0; n < entry->e_name_len; n++) { + while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ *name++; } - - if (entry->e_value_size != 0) { - __le32 *value = (__le32 *)((char *)header + - le16_to_cpu(entry->e_value_offs)); - for (n = (le32_to_cpu(entry->e_value_size) + - EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) { - hash = (hash << VALUE_HASH_SHIFT) ^ - (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ - le32_to_cpu(*value++); - } + while (value_count--) { + hash = (hash << VALUE_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ + le32_to_cpu(*value++); } - entry->e_hash = cpu_to_le32(hash); + return cpu_to_le32(hash); } #undef NAME_HASH_SHIFT @@ -1753,13 +3084,11 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header, * * Re-compute the extended attribute hash value after an entry has changed. */ -static void ext4_xattr_rehash(struct ext4_xattr_header *header, - struct ext4_xattr_entry *entry) +static void ext4_xattr_rehash(struct ext4_xattr_header *header) { struct ext4_xattr_entry *here; __u32 hash = 0; - ext4_xattr_hash_entry(header, entry); here = ENTRY(header+1); while (!IS_LAST_ENTRY(here)) { if (!here->e_hash) { diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 099c8b670ef5..0d2dde1fa87a 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -44,7 +44,7 @@ struct ext4_xattr_entry { __u8 e_name_len; /* length of name */ __u8 e_name_index; /* attribute name index */ __le16 e_value_offs; /* offset in disk block of value */ - __le32 e_value_block; /* disk block attribute is stored on (n/i) */ + __le32 e_value_inum; /* inode in which the value is stored */ __le32 e_value_size; /* size of attribute value */ __le32 e_hash; /* hash value of name and value */ char e_name[0]; /* attribute name */ @@ -69,6 +69,13 @@ struct ext4_xattr_entry { EXT4_I(inode)->i_extra_isize)) #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1)) +/* + * The minimum size of EA value when you start storing it in an external inode + * size of block - size of header - size of 1 entry - 4 null bytes +*/ +#define EXT4_XATTR_MIN_LARGE_EA_SIZE(b) \ + ((b) - EXT4_XATTR_LEN(3) - sizeof(struct ext4_xattr_header) - 4) + #define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data)) #define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr)) #define BFIRST(bh) ENTRY(BHDR(bh)+1) @@ -77,10 +84,11 @@ struct ext4_xattr_entry { #define EXT4_ZERO_XATTR_VALUE ((void *)-1) struct ext4_xattr_info { - int name_index; const char *name; const void *value; size_t value_len; + int name_index; + int in_inode; }; struct ext4_xattr_search { @@ -96,6 +104,11 @@ struct ext4_xattr_ibody_find { struct ext4_iloc iloc; }; +struct ext4_xattr_inode_array { + unsigned int count; /* # of used items in the array */ + struct inode *inodes[0]; +}; + extern const struct xattr_handler ext4_xattr_user_handler; extern const struct xattr_handler ext4_xattr_trusted_handler; extern const struct xattr_handler ext4_xattr_security_handler; @@ -139,8 +152,16 @@ extern ssize_t ext4_listxattr(struct dentry *, char *, size_t); extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t); extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int); extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int); +extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len, + bool is_create, int *credits); +extern int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, + struct buffer_head *block_bh, size_t value_len, + bool is_create); -extern void ext4_xattr_delete_inode(handle_t *, struct inode *); +extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, + struct ext4_xattr_inode_array **array, + int extra_credits); +extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array); extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle); @@ -169,3 +190,11 @@ static inline int ext4_init_security(handle_t *handle, struct inode *inode, return 0; } #endif + +#ifdef CONFIG_LOCKDEP +extern void ext4_xattr_inode_set_class(struct inode *ea_inode); +#else +static inline void ext4_xattr_inode_set_class(struct inode *ea_inode) { } +#endif + +extern int ext4_get_inode_usage(struct inode *inode, qsize_t *usage); diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile index ca949ea7c02f..a0dc559b1b47 100644 --- a/fs/f2fs/Makefile +++ b/fs/f2fs/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o f2fs-y := dir.o file.o inode.o namei.o hash.o super.o inline.o f2fs-y += checkpoint.o gc.o data.o node.o segment.o recovery.o -f2fs-y += shrinker.o extent_cache.o +f2fs-y += shrinker.o extent_cache.o sysfs.o f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 8f487692c21f..436b3a1464d9 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -207,15 +207,16 @@ static int __f2fs_set_acl(struct inode *inode, int type, void *value = NULL; size_t size = 0; int error; + umode_t mode = inode->i_mode; switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (acl && !ipage) { + error = posix_acl_update_mode(inode, &mode, &acl); if (error) return error; - set_acl_inode(inode, inode->i_mode); + set_acl_inode(inode, mode); } break; @@ -233,7 +234,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size); if (IS_ERR(value)) { clear_inode_flag(inode, FI_ACL_MODE); - return (int)PTR_ERR(value); + return PTR_ERR(value); } } diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index ea9c317b5916..04fe1df052b2 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -31,7 +31,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io) set_ckpt_flags(sbi, CP_ERROR_FLAG); sbi->sb->s_flags |= MS_RDONLY; if (!end_io) - f2fs_flush_merged_bios(sbi); + f2fs_flush_merged_writes(sbi); } /* @@ -162,6 +162,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, .op = REQ_OP_READ, .op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD, .encrypted_page = NULL, + .in_list = false, }; struct blk_plug plug; @@ -207,12 +208,10 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, } fio.page = page; - fio.old_blkaddr = fio.new_blkaddr; - f2fs_submit_page_mbio(&fio); + f2fs_submit_page_bio(&fio); f2fs_put_page(page, 0); } out: - f2fs_submit_merged_bio(sbi, META, READ); blk_finish_plug(&plug); return blkno - start; } @@ -231,8 +230,9 @@ void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); } -static int f2fs_write_meta_page(struct page *page, - struct writeback_control *wbc) +static int __f2fs_write_meta_page(struct page *page, + struct writeback_control *wbc, + enum iostat_type io_type) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); @@ -245,17 +245,17 @@ static int f2fs_write_meta_page(struct page *page, if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; - write_meta_page(sbi, page); + write_meta_page(sbi, page, io_type); dec_page_count(sbi, F2FS_DIRTY_META); if (wbc->for_reclaim) - f2fs_submit_merged_bio_cond(sbi, page->mapping->host, - 0, page->index, META, WRITE); + f2fs_submit_merged_write_cond(sbi, page->mapping->host, + 0, page->index, META); unlock_page(page); if (unlikely(f2fs_cp_error(sbi))) - f2fs_submit_merged_bio(sbi, META, WRITE); + f2fs_submit_merged_write(sbi, META); return 0; @@ -264,12 +264,21 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } +static int f2fs_write_meta_page(struct page *page, + struct writeback_control *wbc) +{ + return __f2fs_write_meta_page(page, wbc, FS_META_IO); +} + static int f2fs_write_meta_pages(struct address_space *mapping, struct writeback_control *wbc) { struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); long diff, written; + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; + /* collect a number of dirty meta pages and write together */ if (wbc->for_kupdate || get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META)) @@ -281,7 +290,7 @@ static int f2fs_write_meta_pages(struct address_space *mapping, trace_f2fs_writepages(mapping->host, wbc, META); diff = nr_pages_to_write(sbi, META, wbc); - written = sync_meta_pages(sbi, META, wbc->nr_to_write); + written = sync_meta_pages(sbi, META, wbc->nr_to_write, FS_META_IO); mutex_unlock(&sbi->cp_mutex); wbc->nr_to_write = max((long)0, wbc->nr_to_write - written - diff); return 0; @@ -293,7 +302,7 @@ skip_write: } long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, - long nr_to_write) + long nr_to_write, enum iostat_type io_type) { struct address_space *mapping = META_MAPPING(sbi); pgoff_t index = 0, end = ULONG_MAX, prev = ULONG_MAX; @@ -344,7 +353,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - if (mapping->a_ops->writepage(page, &wbc)) { + if (__f2fs_write_meta_page(page, &wbc, io_type)) { unlock_page(page); break; } @@ -358,7 +367,7 @@ continue_unlock: } stop: if (nwritten) - f2fs_submit_merged_bio(sbi, type, WRITE); + f2fs_submit_merged_write(sbi, type); blk_finish_plug(&plug); @@ -579,11 +588,24 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino) int recover_orphan_inodes(struct f2fs_sb_info *sbi) { block_t start_blk, orphan_blocks, i, j; - int err; + unsigned int s_flags = sbi->sb->s_flags; + int err = 0; if (!is_set_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG)) return 0; + if (s_flags & MS_RDONLY) { + f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); + sbi->sb->s_flags &= ~MS_RDONLY; + } + +#ifdef CONFIG_QUOTA + /* Needed for iput() to work correctly and not trash data */ + sbi->sb->s_flags |= MS_ACTIVE; + /* Turn on quotas so that they are updated correctly */ + f2fs_enable_quota_files(sbi); +#endif + start_blk = __start_cp_addr(sbi) + 1 + __cp_payload(sbi); orphan_blocks = __start_sum_addr(sbi) - 1 - __cp_payload(sbi); @@ -599,14 +621,21 @@ int recover_orphan_inodes(struct f2fs_sb_info *sbi) err = recover_orphan_inode(sbi, ino); if (err) { f2fs_put_page(page, 1); - return err; + goto out; } } f2fs_put_page(page, 1); } /* clear Orphan Flag */ clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG); - return 0; +out: +#ifdef CONFIG_QUOTA + /* Turn quotas off */ + f2fs_quota_off_umount(sbi->sb); +#endif + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + + return err; } static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk) @@ -877,6 +906,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type) struct inode *inode; struct f2fs_inode_info *fi; bool is_dir = (type == DIR_INODE); + unsigned long ino = 0; trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir, get_pages(sbi, is_dir ? @@ -899,14 +929,30 @@ retry: inode = igrab(&fi->vfs_inode); spin_unlock(&sbi->inode_lock[type]); if (inode) { + unsigned long cur_ino = inode->i_ino; + + if (is_dir) + F2FS_I(inode)->cp_task = current; + filemap_fdatawrite(inode->i_mapping); + + if (is_dir) + F2FS_I(inode)->cp_task = NULL; + iput(inode); + /* We need to give cpu to another writers. */ + if (ino == cur_ino) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + } else { + ino = cur_ino; + } } else { /* * We should submit bio, since it exists several * wribacking dentry pages in the freeing inode. */ - f2fs_submit_merged_bio(sbi, DATA, WRITE); + f2fs_submit_merged_write(sbi, DATA); cond_resched(); } goto retry; @@ -1005,7 +1051,7 @@ retry_flush_nodes: if (get_pages(sbi, F2FS_DIRTY_NODES)) { up_write(&sbi->node_write); - err = sync_node_pages(sbi, &wbc); + err = sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO); if (err) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1051,8 +1097,9 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) { unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned long flags; - spin_lock(&sbi->cp_lock); + spin_lock_irqsave(&sbi->cp_lock, flags); if ((cpc->reason & CP_UMOUNT) && le32_to_cpu(ckpt->cp_pack_total_block_count) > @@ -1083,14 +1130,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* set this flag to activate crc|cp_ver for recovery */ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); - spin_unlock(&sbi->cp_lock); + spin_unlock_irqrestore(&sbi->cp_lock, flags); } static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct f2fs_nm_info *nm_i = NM_I(sbi); - unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num; + unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags; block_t start_blk; unsigned int data_sum_blocks, orphan_blocks; __u32 crc32 = 0; @@ -1102,7 +1149,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* Flush all the NAT/SIT pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX); + sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); if (unlikely(f2fs_cp_error(sbi))) return -EIO; } @@ -1132,12 +1179,12 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* 2 cp + n data seg summary + orphan inode blocks */ data_sum_blocks = npages_for_summary_flush(sbi, false); - spin_lock(&sbi->cp_lock); + spin_lock_irqsave(&sbi->cp_lock, flags); if (data_sum_blocks < NR_CURSEG_DATA_TYPE) __set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); else __clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG); - spin_unlock(&sbi->cp_lock); + spin_unlock_irqrestore(&sbi->cp_lock, flags); orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num); ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks + @@ -1181,7 +1228,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) /* Flush all the NAT BITS pages */ while (get_pages(sbi, F2FS_DIRTY_META)) { - sync_meta_pages(sbi, META, LONG_MAX); + sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO); if (unlikely(f2fs_cp_error(sbi))) return -EIO; } @@ -1236,7 +1283,7 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) percpu_counter_set(&sbi->alloc_valid_block_count, 0); /* Here, we only have one bio having CP pack */ - sync_meta_pages(sbi, META_FLUSH, LONG_MAX); + sync_meta_pages(sbi, META_FLUSH, LONG_MAX, FS_CP_META_IO); /* wait for previous submitted meta pages writeback */ wait_on_all_pages_writeback(sbi); @@ -1295,7 +1342,7 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops"); - f2fs_flush_merged_bios(sbi); + f2fs_flush_merged_writes(sbi); /* this is the case of multiple fstrims without any changes */ if (cpc->reason & CP_DISCARD) { diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7c0f6bdf817d..36b535207c88 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -58,12 +58,12 @@ static void f2fs_read_end_io(struct bio *bio) #ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) { f2fs_show_injection_info(FAULT_IO); - bio->bi_error = -EIO; + bio->bi_status = BLK_STS_IOERR; } #endif if (f2fs_bio_encrypted(bio)) { - if (bio->bi_error) { + if (bio->bi_status) { fscrypt_release_ctx(bio->bi_private); } else { fscrypt_decrypt_bio_pages(bio->bi_private, bio); @@ -74,7 +74,7 @@ static void f2fs_read_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (!bio->bi_error) { + if (!bio->bi_status) { if (!PageUptodate(page)) SetPageUptodate(page); } else { @@ -102,14 +102,14 @@ static void f2fs_write_end_io(struct bio *bio) unlock_page(page); mempool_free(page, sbi->write_io_dummy); - if (unlikely(bio->bi_error)) + if (unlikely(bio->bi_status)) f2fs_stop_checkpoint(sbi, true); continue; } fscrypt_pullback_bio_page(&page, true); - if (unlikely(bio->bi_error)) { + if (unlikely(bio->bi_status)) { mapping_set_error(page->mapping, -EIO); f2fs_stop_checkpoint(sbi, true); } @@ -142,7 +142,7 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, } } if (bio) { - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr); } return bdev; @@ -161,7 +161,8 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr) static bool __same_bdev(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio) { - return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev; + struct block_device *b = f2fs_target_device(sbi, blk_addr, NULL); + return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno; } /* @@ -282,29 +283,32 @@ static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, nid_t ino, pgoff_t idx, enum page_type type) { enum page_type btype = PAGE_TYPE_OF_BIO(type); - struct f2fs_bio_info *io = &sbi->write_io[btype]; - bool ret; + enum temp_type temp; + struct f2fs_bio_info *io; + bool ret = false; + + for (temp = HOT; temp < NR_TEMP_TYPE; temp++) { + io = sbi->write_io[btype] + temp; + + down_read(&io->io_rwsem); + ret = __has_merged_page(io, inode, ino, idx); + up_read(&io->io_rwsem); - down_read(&io->io_rwsem); - ret = __has_merged_page(io, inode, ino, idx); - up_read(&io->io_rwsem); + /* TODO: use HOT temp only for meta pages now. */ + if (ret || btype == META) + break; + } return ret; } -static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type, int rw) +static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi, + enum page_type type, enum temp_type temp) { enum page_type btype = PAGE_TYPE_OF_BIO(type); - struct f2fs_bio_info *io; - - io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype]; + struct f2fs_bio_info *io = sbi->write_io[btype] + temp; down_write(&io->io_rwsem); - if (!__has_merged_page(io, inode, ino, idx)) - goto out; - /* change META to META_FLUSH in the checkpoint procedure */ if (type >= META_FLUSH) { io->fio.type = META_FLUSH; @@ -314,29 +318,45 @@ static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA; } __submit_merged_bio(io); -out: up_write(&io->io_rwsem); } -void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type, - int rw) +static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, + struct inode *inode, nid_t ino, pgoff_t idx, + enum page_type type, bool force) { - __f2fs_submit_merged_bio(sbi, NULL, 0, 0, type, rw); + enum temp_type temp; + + if (!force && !has_merged_page(sbi, inode, ino, idx, type)) + return; + + for (temp = HOT; temp < NR_TEMP_TYPE; temp++) { + + __f2fs_submit_merged_write(sbi, type, temp); + + /* TODO: use HOT temp only for meta pages now. */ + if (type >= META) + break; + } } -void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi, +void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) +{ + __submit_merged_write_cond(sbi, NULL, 0, 0, type, true); +} + +void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type, int rw) + enum page_type type) { - if (has_merged_page(sbi, inode, ino, idx, type)) - __f2fs_submit_merged_bio(sbi, inode, ino, idx, type, rw); + __submit_merged_write_cond(sbi, inode, ino, idx, type, false); } -void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi) +void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) { - f2fs_submit_merged_bio(sbi, DATA, WRITE); - f2fs_submit_merged_bio(sbi, NODE, WRITE); - f2fs_submit_merged_bio(sbi, META, WRITE); + f2fs_submit_merged_write(sbi, DATA); + f2fs_submit_merged_write(sbi, NODE); + f2fs_submit_merged_write(sbi, META); } /* @@ -368,16 +388,29 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) return 0; } -int f2fs_submit_page_mbio(struct f2fs_io_info *fio) +int f2fs_submit_page_write(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); - struct f2fs_bio_info *io; - bool is_read = is_read_io(fio->op); + struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; int err = 0; - io = is_read ? &sbi->read_io : &sbi->write_io[btype]; + f2fs_bug_on(sbi, is_read_io(fio->op)); + + down_write(&io->io_rwsem); +next: + if (fio->in_list) { + spin_lock(&io->io_lock); + if (list_empty(&io->io_list)) { + spin_unlock(&io->io_lock); + goto out_fail; + } + fio = list_first_entry(&io->io_list, + struct f2fs_io_info, list); + list_del(&fio->list); + spin_unlock(&io->io_lock); + } if (fio->old_blkaddr != NEW_ADDR) verify_block_addr(sbi, fio->old_blkaddr); @@ -388,10 +421,7 @@ int f2fs_submit_page_mbio(struct f2fs_io_info *fio) /* set submitted = 1 as a return value */ fio->submitted = 1; - if (!is_read) - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); - - down_write(&io->io_rwsem); + inc_page_count(sbi, WB_DATA_TYPE(bio_page)); if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 || (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) || @@ -402,37 +432,90 @@ alloc_new: if ((fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { err = -EAGAIN; - if (!is_read) - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); + dec_page_count(sbi, WB_DATA_TYPE(bio_page)); goto out_fail; } io->bio = __bio_alloc(sbi, fio->new_blkaddr, - BIO_MAX_PAGES, is_read); + BIO_MAX_PAGES, false); io->fio = *fio; } - if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < - PAGE_SIZE) { + if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) { __submit_merged_bio(io); goto alloc_new; } io->last_block_in_bio = fio->new_blkaddr; f2fs_trace_ios(fio, 0); + + trace_f2fs_submit_page_write(fio->page, fio); + + if (fio->in_list) + goto next; out_fail: up_write(&io->io_rwsem); - trace_f2fs_submit_page_mbio(fio->page, fio); return err; } +static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, + unsigned nr_pages) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct fscrypt_ctx *ctx = NULL; + struct bio *bio; + + if (f2fs_encrypted_file(inode)) { + ctx = fscrypt_get_ctx(inode, GFP_NOFS); + if (IS_ERR(ctx)) + return ERR_CAST(ctx); + + /* wait the page to be moved by cleaning */ + f2fs_wait_on_block_writeback(sbi, blkaddr); + } + + bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES)); + if (!bio) { + if (ctx) + fscrypt_release_ctx(ctx); + return ERR_PTR(-ENOMEM); + } + f2fs_target_device(sbi, blkaddr, bio); + bio->bi_end_io = f2fs_read_end_io; + bio->bi_private = ctx; + bio_set_op_attrs(bio, REQ_OP_READ, 0); + + return bio; +} + +/* This can handle encryption stuffs */ +static int f2fs_submit_page_read(struct inode *inode, struct page *page, + block_t blkaddr) +{ + struct bio *bio = f2fs_grab_read_bio(inode, blkaddr, 1); + + if (IS_ERR(bio)) + return PTR_ERR(bio); + + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { + bio_put(bio); + return -EFAULT; + } + __submit_bio(F2FS_I_SB(inode), bio, DATA); + return 0; +} + static void __set_data_blkaddr(struct dnode_of_data *dn) { struct f2fs_node *rn = F2FS_NODE(dn->node_page); __le32 *addr_array; + int base = 0; + + if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) + base = get_extra_isize(dn->inode); /* Get physical address of data block */ addr_array = blkaddr_in_node(rn); - addr_array[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); + addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); } /* @@ -460,14 +543,15 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); + int err; if (!count) return 0; if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count))) - return -ENOSPC; + if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + return err; trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, dn->ofs_in_node, count); @@ -475,8 +559,8 @@ int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) f2fs_wait_on_page_writeback(dn->node_page, NODE, true); for (; count > 0; dn->ofs_in_node++) { - block_t blkaddr = - datablock_addr(dn->node_page, dn->ofs_in_node); + block_t blkaddr = datablock_addr(dn->inode, + dn->node_page, dn->ofs_in_node); if (blkaddr == NULL_ADDR) { dn->data_blkaddr = NEW_ADDR; __set_data_blkaddr(dn); @@ -537,16 +621,6 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index, struct page *page; struct extent_info ei = {0,0,0}; int err; - struct f2fs_io_info fio = { - .sbi = F2FS_I_SB(inode), - .type = DATA, - .op = REQ_OP_READ, - .op_flags = op_flags, - .encrypted_page = NULL, - }; - - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - return read_mapping_page(mapping, index, NULL); page = f2fs_grab_cache_page(mapping, index, for_write); if (!page) @@ -587,9 +661,7 @@ got_it: return page; } - fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; - fio.page = page; - err = f2fs_submit_page_bio(&fio); + err = f2fs_submit_page_read(inode, page, dn.data_blkaddr); if (err) goto put_err; return page; @@ -718,23 +790,25 @@ static int __allocate_data_block(struct dnode_of_data *dn) struct node_info ni; pgoff_t fofs; blkcnt_t count = 1; + int err; if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = datablock_addr(dn->inode, + dn->node_page, dn->ofs_in_node); if (dn->data_blkaddr == NEW_ADDR) goto alloc; - if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count))) - return -ENOSPC; + if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + return err; alloc: get_node_info(sbi, dn->nid, &ni); set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr, - &sum, CURSEG_WARM_DATA); + &sum, CURSEG_WARM_DATA, NULL, false); set_data_blkaddr(dn); /* update i_size */ @@ -748,7 +822,7 @@ alloc: static inline bool __force_buffered_io(struct inode *inode, int rw) { - return ((f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) || + return (f2fs_encrypted_file(inode) || (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || F2FS_I_SB(inode)->s_ndevs); } @@ -780,7 +854,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO); } - if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA) { + if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) { err = f2fs_convert_inline_inode(inode); if (err) return err; @@ -869,7 +943,7 @@ next_dnode: end_offset = ADDRS_PER_PAGE(dn.node_page, inode); next_block: - blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); if (blkaddr == NEW_ADDR || blkaddr == NULL_ADDR) { if (create) { @@ -1006,7 +1080,7 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DIO, NULL); + F2FS_GET_BLOCK_DEFAULT, NULL); } static int get_data_block_bmap(struct inode *inode, sector_t iblock, @@ -1112,35 +1186,6 @@ out: return ret; } -static struct bio *f2fs_grab_bio(struct inode *inode, block_t blkaddr, - unsigned nr_pages) -{ - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct fscrypt_ctx *ctx = NULL; - struct bio *bio; - - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { - ctx = fscrypt_get_ctx(inode, GFP_NOFS); - if (IS_ERR(ctx)) - return ERR_CAST(ctx); - - /* wait the page to be moved by cleaning */ - f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr); - } - - bio = bio_alloc(GFP_KERNEL, min_t(int, nr_pages, BIO_MAX_PAGES)); - if (!bio) { - if (ctx) - fscrypt_release_ctx(ctx); - return ERR_PTR(-ENOMEM); - } - f2fs_target_device(sbi, blkaddr, bio); - bio->bi_end_io = f2fs_read_end_io; - bio->bi_private = ctx; - - return bio; -} - /* * This function was originally taken from fs/mpage.c, and customized for f2fs. * Major change was from block_size == page_size in f2fs by default. @@ -1206,7 +1251,7 @@ static int f2fs_mpage_readpages(struct address_space *mapping, map.m_len = last_block - block_in_file; if (f2fs_map_blocks(inode, &map, 0, - F2FS_GET_BLOCK_READ)) + F2FS_GET_BLOCK_DEFAULT)) goto set_error_page; } got_it: @@ -1237,12 +1282,11 @@ submit_and_realloc: bio = NULL; } if (bio == NULL) { - bio = f2fs_grab_bio(inode, block_nr, nr_pages); + bio = f2fs_grab_read_bio(inode, block_nr, nr_pages); if (IS_ERR(bio)) { bio = NULL; goto set_error_page; } - bio_set_op_attrs(bio, REQ_OP_READ, 0); } if (bio_add_page(bio, page, blocksize, 0) < blocksize) @@ -1307,11 +1351,11 @@ static int encrypt_one_page(struct f2fs_io_info *fio) struct inode *inode = fio->page->mapping->host; gfp_t gfp_flags = GFP_NOFS; - if (!f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode)) + if (!f2fs_encrypted_file(inode)) return 0; /* wait for GCed encrypted page writeback */ - f2fs_wait_on_encrypted_page_writeback(fio->sbi, fio->old_blkaddr); + f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr); retry_encrypt: fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page, @@ -1321,7 +1365,7 @@ retry_encrypt: /* flush pending IOs and wait for a while in the ENOMEM case */ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { - f2fs_flush_merged_bios(fio->sbi); + f2fs_flush_merged_writes(fio->sbi); congestion_wait(BLK_RW_ASYNC, HZ/50); gfp_flags |= __GFP_NOFAIL; goto retry_encrypt; @@ -1368,13 +1412,14 @@ int do_write_data_page(struct f2fs_io_info *fio) if (valid_ipu_blkaddr(fio)) { ipu_force = true; - fio->need_lock = false; + fio->need_lock = LOCK_DONE; goto got_it; } } - if (fio->need_lock) - f2fs_lock_op(fio->sbi); + /* Deadlock due to between page->lock and f2fs_lock_op */ + if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi)) + return -EAGAIN; err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); if (err) @@ -1388,19 +1433,18 @@ int do_write_data_page(struct f2fs_io_info *fio) goto out_writepage; } got_it: - err = encrypt_one_page(fio); - if (err) - goto out_writepage; - - set_page_writeback(page); - /* * If current allocation needs SSR, * it had better in-place writes for updated data. */ if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) { + err = encrypt_one_page(fio); + if (err) + goto out_writepage; + + set_page_writeback(page); f2fs_put_dnode(&dn); - if (fio->need_lock) + if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); err = rewrite_data_page(fio); trace_f2fs_do_write_data_page(fio->page, IPU); @@ -1408,6 +1452,20 @@ got_it: return err; } + if (fio->need_lock == LOCK_RETRY) { + if (!f2fs_trylock_op(fio->sbi)) { + err = -EAGAIN; + goto out_writepage; + } + fio->need_lock = LOCK_REQ; + } + + err = encrypt_one_page(fio); + if (err) + goto out_writepage; + + set_page_writeback(page); + /* LFS mode write path */ write_data_page(&dn, fio); trace_f2fs_do_write_data_page(page, OPU); @@ -1417,13 +1475,14 @@ got_it: out_writepage: f2fs_put_dnode(&dn); out: - if (fio->need_lock) + if (fio->need_lock == LOCK_REQ) f2fs_unlock_op(fio->sbi); return err; } static int __write_data_page(struct page *page, bool *submitted, - struct writeback_control *wbc) + struct writeback_control *wbc, + enum iostat_type io_type) { struct inode *inode = page->mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -1443,11 +1502,15 @@ static int __write_data_page(struct page *page, bool *submitted, .page = page, .encrypted_page = NULL, .submitted = false, - .need_lock = true, + .need_lock = LOCK_RETRY, + .io_type = io_type, }; trace_f2fs_writepage(page, DATA); + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto redirty_out; + if (page->index < end_index) goto write; @@ -1461,8 +1524,6 @@ static int __write_data_page(struct page *page, bool *submitted, zero_user_segment(page, offset, PAGE_SIZE); write: - if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) - goto redirty_out; if (f2fs_is_drop_cache(inode)) goto out; /* we should not write 0'th page having journal header */ @@ -1479,7 +1540,7 @@ write: /* Dentry blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode)) { - fio.need_lock = false; + fio.need_lock = LOCK_DONE; err = do_write_data_page(&fio); goto done; } @@ -1498,8 +1559,13 @@ write: goto out; } - if (err == -EAGAIN) + if (err == -EAGAIN) { err = do_write_data_page(&fio); + if (err == -EAGAIN) { + fio.need_lock = LOCK_REQ; + err = do_write_data_page(&fio); + } + } if (F2FS_I(inode)->last_disk_size < psize) F2FS_I(inode)->last_disk_size = psize; @@ -1513,8 +1579,7 @@ out: ClearPageUptodate(page); if (wbc->for_reclaim) { - f2fs_submit_merged_bio_cond(sbi, inode, 0, page->index, - DATA, WRITE); + f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA); clear_inode_flag(inode, FI_HOT_DATA); remove_dirty_inode(inode); submitted = NULL; @@ -1525,7 +1590,7 @@ out: f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { - f2fs_submit_merged_bio(sbi, DATA, WRITE); + f2fs_submit_merged_write(sbi, DATA); submitted = NULL; } @@ -1545,7 +1610,7 @@ redirty_out: static int f2fs_write_data_page(struct page *page, struct writeback_control *wbc) { - return __write_data_page(page, NULL, wbc); + return __write_data_page(page, NULL, wbc, FS_DATA_IO); } /* @@ -1554,7 +1619,8 @@ static int f2fs_write_data_page(struct page *page, * warm/hot data page. */ static int f2fs_write_cache_pages(struct address_space *mapping, - struct writeback_control *wbc) + struct writeback_control *wbc, + enum iostat_type io_type) { int ret = 0; int done = 0; @@ -1618,7 +1684,7 @@ retry: } done_index = page->index; - +retry_write: lock_page(page); if (unlikely(page->mapping != mapping)) { @@ -1644,7 +1710,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - ret = __write_data_page(page, &submitted, wbc); + ret = __write_data_page(page, &submitted, wbc, io_type); if (unlikely(ret)) { /* * keep nr_to_write, since vfs uses this to @@ -1654,6 +1720,15 @@ continue_unlock: unlock_page(page); ret = 0; continue; + } else if (ret == -EAGAIN) { + ret = 0; + if (wbc->sync_mode == WB_SYNC_ALL) { + cond_resched(); + congestion_wait(BLK_RW_ASYNC, + HZ/50); + goto retry_write; + } + continue; } done_index = page->index + 1; done = 1; @@ -1684,14 +1759,15 @@ continue_unlock: mapping->writeback_index = done_index; if (last_idx != ULONG_MAX) - f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host, - 0, last_idx, DATA, WRITE); + f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host, + 0, last_idx, DATA); return ret; } -static int f2fs_write_data_pages(struct address_space *mapping, - struct writeback_control *wbc) +int __f2fs_write_data_pages(struct address_space *mapping, + struct writeback_control *wbc, + enum iostat_type io_type) { struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -1706,6 +1782,10 @@ static int f2fs_write_data_pages(struct address_space *mapping, if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE) return 0; + /* during POR, we don't need to trigger writepage at all. */ + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; + if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && available_free_memory(sbi, DIRTY_DENTS)) @@ -1715,10 +1795,6 @@ static int f2fs_write_data_pages(struct address_space *mapping, if (is_inode_flag_set(inode, FI_DO_DEFRAG)) goto skip_write; - /* during POR, we don't need to trigger writepage at all. */ - if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) - goto skip_write; - trace_f2fs_writepages(mapping->host, wbc, DATA); /* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */ @@ -1728,7 +1804,7 @@ static int f2fs_write_data_pages(struct address_space *mapping, goto skip_write; blk_start_plug(&plug); - ret = f2fs_write_cache_pages(mapping, wbc); + ret = f2fs_write_cache_pages(mapping, wbc, io_type); blk_finish_plug(&plug); if (wbc->sync_mode == WB_SYNC_ALL) @@ -1747,14 +1823,26 @@ skip_write: return 0; } +static int f2fs_write_data_pages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct inode *inode = mapping->host; + + return __f2fs_write_data_pages(mapping, wbc, + F2FS_I(inode)->cp_task == current ? + FS_CP_DATA_IO : FS_DATA_IO); +} + static void f2fs_write_failed(struct address_space *mapping, loff_t to) { struct inode *inode = mapping->host; loff_t i_size = i_size_read(inode); if (to > i_size) { + down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); truncate_blocks(inode, i_size, true); + up_write(&F2FS_I(inode)->i_mmap_sem); } } @@ -1794,7 +1882,7 @@ restart: set_new_dnode(&dn, inode, ipage, ipage, 0); if (f2fs_has_inline_data(inode)) { - if (pos + len <= MAX_INLINE_DATA) { + if (pos + len <= MAX_INLINE_DATA(inode)) { read_inline_data(page, ipage); set_inode_flag(inode, FI_DATA_EXIST); if (inode->i_nlink) @@ -1892,8 +1980,8 @@ repeat: f2fs_wait_on_page_writeback(page, DATA, false); /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - f2fs_wait_on_encrypted_page_writeback(sbi, blkaddr); + if (f2fs_encrypted_file(inode)) + f2fs_wait_on_block_writeback(sbi, blkaddr); if (len == PAGE_SIZE || PageUptodate(page)) return 0; @@ -1907,21 +1995,9 @@ repeat: zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); } else { - struct bio *bio; - - bio = f2fs_grab_bio(inode, blkaddr, 1); - if (IS_ERR(bio)) { - err = PTR_ERR(bio); - goto fail; - } - bio->bi_opf = REQ_OP_READ; - if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { - bio_put(bio); - err = -EFAULT; + err = f2fs_submit_page_read(inode, page, blkaddr); + if (err) goto fail; - } - - __submit_bio(sbi, bio, DATA); lock_page(page); if (unlikely(page->mapping != mapping)) { @@ -2011,10 +2087,13 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) up_read(&F2FS_I(inode)->dio_rwsem[rw]); if (rw == WRITE) { - if (err > 0) + if (err > 0) { + f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO, + err); set_inode_flag(inode, FI_UPDATE_WRITE); - else if (err < 0) + } else if (err < 0) { f2fs_write_failed(mapping, offset + count); + } } trace_f2fs_direct_IO_exit(inode, offset, count, rw, err); @@ -2152,8 +2231,12 @@ int f2fs_migrate_page(struct address_space *mapping, BUG_ON(PageWriteback(page)); /* migrating an atomic written page is safe with the inmem_lock hold */ - if (atomic_written && !mutex_trylock(&fi->inmem_lock)) - return -EAGAIN; + if (atomic_written) { + if (mode != MIGRATE_SYNC) + return -EBUSY; + if (!mutex_trylock(&fi->inmem_lock)) + return -EAGAIN; + } /* * A reference is expected if PagePrivate set when move mapping, @@ -2185,7 +2268,10 @@ int f2fs_migrate_page(struct address_space *mapping, SetPagePrivate(newpage); set_page_private(newpage, page_private(page)); - migrate_page_copy(newpage, page); + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); return MIGRATEPAGE_SUCCESS; } diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 94756f55a97e..c0c933ad43c8 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -415,7 +415,8 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir, * We lost i_pino from now on. */ if (is_inode_flag_set(inode, FI_INC_LINK)) { - file_lost_pino(inode); + if (!S_ISDIR(inode->i_mode)) + file_lost_pino(inode); /* * If link the tmpfile to alias through linkat path, * we should remove this inode from orphan list. @@ -704,6 +705,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct f2fs_dentry_block *dentry_blk; unsigned int bit_pos; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); + struct address_space *mapping = page_mapping(page); + unsigned long flags; int i; f2fs_update_time(F2FS_I_SB(dir), REQ_TIME); @@ -734,6 +737,11 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, if (bit_pos == NR_DENTRY_IN_BLOCK && !truncate_hole(dir, page->index, page->index + 1)) { + spin_lock_irqsave(&mapping->tree_lock, flags); + radix_tree_tag_clear(&mapping->page_tree, page_index(page), + PAGECACHE_TAG_DIRTY); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 2f98d7039701..ff2352a0ed15 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -320,7 +320,7 @@ static void __drop_largest_extent(struct inode *inode, } /* return true, if inode page is changed */ -bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et; @@ -358,6 +358,16 @@ out: return false; } +bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext) +{ + bool ret = __f2fs_init_extent_tree(inode, i_ext); + + if (!F2FS_I(inode)->extent_tree) + set_inode_flag(inode, FI_NO_EXTENT); + + return ret; +} + static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs, struct extent_info *ei) { diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index fd2e651bad6d..4b4a72f392be 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -22,6 +22,7 @@ #include <linux/vmalloc.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/quotaops.h> #ifdef CONFIG_F2FS_FS_ENCRYPTION #include <linux/fscrypt_supp.h> #else @@ -88,6 +89,10 @@ extern char *fault_name[FAULT_MAX]; #define F2FS_MOUNT_FAULT_INJECTION 0x00010000 #define F2FS_MOUNT_ADAPTIVE 0x00020000 #define F2FS_MOUNT_LFS 0x00040000 +#define F2FS_MOUNT_USRQUOTA 0x00080000 +#define F2FS_MOUNT_GRPQUOTA 0x00100000 +#define F2FS_MOUNT_PRJQUOTA 0x00200000 +#define F2FS_MOUNT_QUOTA 0x00400000 #define clear_opt(sbi, option) ((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option) #define set_opt(sbi, option) ((sbi)->mount_opt.opt |= F2FS_MOUNT_##option) @@ -107,8 +112,12 @@ struct f2fs_mount_info { unsigned int opt; }; -#define F2FS_FEATURE_ENCRYPT 0x0001 -#define F2FS_FEATURE_BLKZONED 0x0002 +#define F2FS_FEATURE_ENCRYPT 0x0001 +#define F2FS_FEATURE_BLKZONED 0x0002 +#define F2FS_FEATURE_ATOMIC_WRITE 0x0004 +#define F2FS_FEATURE_EXTRA_ATTR 0x0008 +#define F2FS_FEATURE_PRJQUOTA 0x0010 +#define F2FS_FEATURE_INODE_CHKSUM 0x0020 #define F2FS_HAS_FEATURE(sb, mask) \ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) @@ -139,6 +148,8 @@ enum { (BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg) #define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) #define DISCARD_ISSUE_RATE 8 +#define DEF_MIN_DISCARD_ISSUE_TIME 50 /* 50 ms, if exists */ +#define DEF_MAX_DISCARD_ISSUE_TIME 60000 /* 60 s, if no candidates */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ @@ -187,11 +198,18 @@ struct discard_entry { unsigned char discard_map[SIT_VBLOCK_MAP_SIZE]; /* segment discard bitmap */ }; +/* default discard granularity of inner discard thread, unit: block count */ +#define DEFAULT_DISCARD_GRANULARITY 16 + /* max discard pend list number */ #define MAX_PLIST_NUM 512 #define plist_idx(blk_num) ((blk_num) >= MAX_PLIST_NUM ? \ (MAX_PLIST_NUM - 1) : (blk_num - 1)) +#define P_ACTIVE 0x01 +#define P_TRIM 0x02 +#define plist_issue(tag) (((tag) & P_ACTIVE) || ((tag) & P_TRIM)) + enum { D_PREP, D_SUBMIT, @@ -227,11 +245,14 @@ struct discard_cmd_control { struct task_struct *f2fs_issue_discard; /* discard thread */ struct list_head entry_list; /* 4KB discard entry list */ struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */ + unsigned char pend_list_tag[MAX_PLIST_NUM];/* tag for pending entries */ struct list_head wait_list; /* store on-flushing entries */ wait_queue_head_t discard_wait_queue; /* waiting queue for wake-up */ + unsigned int discard_wake; /* to wake up discard thread */ struct mutex cmd_lock; unsigned int nr_discards; /* # of discards in the list */ unsigned int max_discards; /* max. discards to be issued */ + unsigned int discard_granularity; /* discard granularity */ unsigned int undiscard_blks; /* # of undiscard blocks */ atomic_t issued_discard; /* # of issued discard */ atomic_t issing_discard; /* # of issing discard */ @@ -303,6 +324,9 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, struct f2fs_move_range) #define F2FS_IOC_FLUSH_DEVICE _IOW(F2FS_IOCTL_MAGIC, 10, \ struct f2fs_flush_device) +#define F2FS_IOC_GARBAGE_COLLECT_RANGE _IOW(F2FS_IOCTL_MAGIC, 11, \ + struct f2fs_gc_range) +#define F2FS_IOC_GET_FEATURES _IOR(F2FS_IOCTL_MAGIC, 12, __u32) #define F2FS_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY #define F2FS_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY @@ -327,6 +351,15 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal, #define F2FS_IOC32_GETVERSION FS_IOC32_GETVERSION #endif +#define F2FS_IOC_FSGETXATTR FS_IOC_FSGETXATTR +#define F2FS_IOC_FSSETXATTR FS_IOC_FSSETXATTR + +struct f2fs_gc_range { + u32 sync; + u64 start; + u64 len; +}; + struct f2fs_defragment { u64 start; u64 len; @@ -344,16 +377,36 @@ struct f2fs_flush_device { u32 segments; /* # of segments to flush */ }; +/* for inline stuff */ +#define DEF_INLINE_RESERVED_SIZE 1 +static inline int get_extra_isize(struct inode *inode); +#define MAX_INLINE_DATA(inode) (sizeof(__le32) * \ + (CUR_ADDRS_PER_INODE(inode) - \ + DEF_INLINE_RESERVED_SIZE - \ + F2FS_INLINE_XATTR_ADDRS)) + +/* for inline dir */ +#define NR_INLINE_DENTRY(inode) (MAX_INLINE_DATA(inode) * BITS_PER_BYTE / \ + ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ + BITS_PER_BYTE + 1)) +#define INLINE_DENTRY_BITMAP_SIZE(inode) ((NR_INLINE_DENTRY(inode) + \ + BITS_PER_BYTE - 1) / BITS_PER_BYTE) +#define INLINE_RESERVED_SIZE(inode) (MAX_INLINE_DATA(inode) - \ + ((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * \ + NR_INLINE_DENTRY(inode) + \ + INLINE_DENTRY_BITMAP_SIZE(inode))) + /* * For INODE and NODE manager */ /* for directory operations */ struct f2fs_dentry_ptr { struct inode *inode; - const void *bitmap; + void *bitmap; struct f2fs_dir_entry *dentry; __u8 (*filename)[F2FS_SLOT_LEN]; int max; + int nr_bitmap; }; static inline void make_dentry_ptr_block(struct inode *inode, @@ -361,19 +414,26 @@ static inline void make_dentry_ptr_block(struct inode *inode, { d->inode = inode; d->max = NR_DENTRY_IN_BLOCK; + d->nr_bitmap = SIZE_OF_DENTRY_BITMAP; d->bitmap = &t->dentry_bitmap; d->dentry = t->dentry; d->filename = t->filename; } static inline void make_dentry_ptr_inline(struct inode *inode, - struct f2fs_dentry_ptr *d, struct f2fs_inline_dentry *t) + struct f2fs_dentry_ptr *d, void *t) { + int entry_cnt = NR_INLINE_DENTRY(inode); + int bitmap_size = INLINE_DENTRY_BITMAP_SIZE(inode); + int reserved_size = INLINE_RESERVED_SIZE(inode); + d->inode = inode; - d->max = NR_INLINE_DENTRY; - d->bitmap = &t->dentry_bitmap; - d->dentry = t->dentry; - d->filename = t->filename; + d->max = entry_cnt; + d->nr_bitmap = bitmap_size; + d->bitmap = t; + d->dentry = t + bitmap_size + reserved_size; + d->filename = t + bitmap_size + reserved_size + + SIZE_OF_DIR_ENTRY * entry_cnt; } /* @@ -462,12 +522,13 @@ struct f2fs_map_blocks { }; /* for flag in get_data_block */ -#define F2FS_GET_BLOCK_READ 0 -#define F2FS_GET_BLOCK_DIO 1 -#define F2FS_GET_BLOCK_FIEMAP 2 -#define F2FS_GET_BLOCK_BMAP 3 -#define F2FS_GET_BLOCK_PRE_DIO 4 -#define F2FS_GET_BLOCK_PRE_AIO 5 +enum { + F2FS_GET_BLOCK_DEFAULT, + F2FS_GET_BLOCK_FIEMAP, + F2FS_GET_BLOCK_BMAP, + F2FS_GET_BLOCK_PRE_DIO, + F2FS_GET_BLOCK_PRE_AIO, +}; /* * i_advise uses FADVISE_XXX_BIT. We can add additional hints later. @@ -510,15 +571,28 @@ struct f2fs_inode_info { f2fs_hash_t chash; /* hash value of given file name */ unsigned int clevel; /* maximum level of given file name */ struct task_struct *task; /* lookup and create consistency */ + struct task_struct *cp_task; /* separate cp/wb IO stats*/ nid_t i_xattr_nid; /* node id that contains xattrs */ loff_t last_disk_size; /* lastly written file size */ +#ifdef CONFIG_QUOTA + struct dquot *i_dquot[MAXQUOTAS]; + + /* quota space reservation, managed internally by quota code */ + qsize_t i_reserved_quota; +#endif struct list_head dirty_list; /* dirty list for dirs and files */ struct list_head gdirty_list; /* linked in global dirty list */ struct list_head inmem_pages; /* inmemory pages managed by f2fs */ + struct task_struct *inmem_task; /* store inmemory task */ struct mutex inmem_lock; /* lock for inmemory pages */ struct extent_tree *extent_tree; /* cached extent_tree entry */ struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */ + struct rw_semaphore i_mmap_sem; + struct rw_semaphore i_xattr_sem; /* avoid racing between reading and changing EAs */ + + int i_extra_isize; /* size of extra space located in i_addr */ + kprojid_t i_projid; /* id for project quota */ }; static inline void get_extent_info(struct extent_info *ext, @@ -792,17 +866,51 @@ enum page_type { OPU, }; +enum temp_type { + HOT = 0, /* must be zero for meta bio */ + WARM, + COLD, + NR_TEMP_TYPE, +}; + +enum need_lock_type { + LOCK_REQ = 0, + LOCK_DONE, + LOCK_RETRY, +}; + +enum iostat_type { + APP_DIRECT_IO, /* app direct IOs */ + APP_BUFFERED_IO, /* app buffered IOs */ + APP_WRITE_IO, /* app write IOs */ + APP_MAPPED_IO, /* app mapped IOs */ + FS_DATA_IO, /* data IOs from kworker/fsync/reclaimer */ + FS_NODE_IO, /* node IOs from kworker/fsync/reclaimer */ + FS_META_IO, /* meta IOs from kworker/reclaimer */ + FS_GC_DATA_IO, /* data IOs from forground gc */ + FS_GC_NODE_IO, /* node IOs from forground gc */ + FS_CP_DATA_IO, /* data IOs from checkpoint */ + FS_CP_NODE_IO, /* node IOs from checkpoint */ + FS_CP_META_IO, /* meta IOs from checkpoint */ + FS_DISCARD, /* discard */ + NR_IO_TYPE, +}; + struct f2fs_io_info { struct f2fs_sb_info *sbi; /* f2fs_sb_info pointer */ enum page_type type; /* contains DATA/NODE/META/META_FLUSH */ + enum temp_type temp; /* contains HOT/WARM/COLD */ int op; /* contains REQ_OP_ */ int op_flags; /* req_flag_bits */ block_t new_blkaddr; /* new block address to be written */ block_t old_blkaddr; /* old block address before Cow */ struct page *page; /* page to be written */ struct page *encrypted_page; /* encrypted page */ + struct list_head list; /* serialize IOs */ bool submitted; /* indicate IO submission */ - bool need_lock; /* indicate we need to lock cp_rwsem */ + int need_lock; /* indicate we need to lock cp_rwsem */ + bool in_list; /* indicate fio is in io_list */ + enum iostat_type io_type; /* io type */ }; #define is_read_io(rw) ((rw) == READ) @@ -812,6 +920,8 @@ struct f2fs_bio_info { sector_t last_block_in_bio; /* last block number */ struct f2fs_io_info fio; /* store buffered io info. */ struct rw_semaphore io_rwsem; /* blocking op for bio */ + spinlock_t io_lock; /* serialize DATA/NODE IOs */ + struct list_head io_list; /* track fios */ }; #define FDEV(i) (sbi->devs[i]) @@ -879,9 +989,9 @@ struct f2fs_sb_info { struct f2fs_sm_info *sm_info; /* segment manager */ /* for bio operations */ - struct f2fs_bio_info read_io; /* for read bios */ - struct f2fs_bio_info write_io[NR_PAGE_TYPE]; /* for write bios */ - struct mutex wio_mutex[NODE + 1]; /* bio ordering for NODE/DATA */ + struct f2fs_bio_info *write_io[NR_PAGE_TYPE]; /* for write bios */ + struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE]; + /* bio ordering for NODE/DATA */ int write_io_size_bits; /* Write IO size bits */ mempool_t *write_io_dummy; /* Dummy pages */ @@ -939,6 +1049,8 @@ struct f2fs_sb_info { block_t total_valid_block_count; /* # of valid blocks */ block_t discard_blks; /* discard command candidats */ block_t last_valid_block_count; /* for recovery */ + block_t reserved_blocks; /* configurable reserved blocks */ + u32 s_next_generation; /* for NFS support */ /* # of pages, see count_type */ @@ -990,6 +1102,11 @@ struct f2fs_sb_info { #endif spinlock_t stat_lock; /* lock for stat operations */ + /* For app/fs IO statistics */ + spinlock_t iostat_lock; + unsigned long long write_iostat[NR_IO_TYPE]; + bool iostat_enable; + /* For sysfs suppport */ struct kobject s_kobj; struct completion s_kobj_unregister; @@ -1008,10 +1125,19 @@ struct f2fs_sb_info { /* Reference to checksum algorithm driver via cryptoapi */ struct crypto_shash *s_chksum_driver; + /* Precomputed FS UUID checksum for seeding other checksums */ + __u32 s_chksum_seed; + /* For fault injection */ #ifdef CONFIG_F2FS_FAULT_INJECTION struct f2fs_fault_info fault_info; #endif + +#ifdef CONFIG_QUOTA + /* Names of quota files with journalled quota */ + char *s_qf_names[MAXQUOTAS]; + int s_jquota_fmt; /* Format of quota to use */ +#endif }; #ifdef CONFIG_F2FS_FAULT_INJECTION @@ -1099,6 +1225,27 @@ static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, return f2fs_crc32(sbi, buf, buf_size) == blk_crc; } +static inline u32 f2fs_chksum(struct f2fs_sb_info *sbi, u32 crc, + const void *address, unsigned int length) +{ + struct { + struct shash_desc shash; + char ctx[4]; + } desc; + int err; + + BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx)); + + desc.shash.tfm = sbi->s_chksum_driver; + desc.shash.flags = 0; + *(u32 *)desc.ctx = crc; + + err = crypto_shash_update(&desc.shash, address, length); + BUG_ON(err); + + return *(u32 *)desc.ctx; +} + static inline struct f2fs_inode_info *F2FS_I(struct inode *inode) { return container_of(inode, struct f2fs_inode_info, vfs_inode); @@ -1228,9 +1375,11 @@ static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { - spin_lock(&sbi->cp_lock); + unsigned long flags; + + spin_lock_irqsave(&sbi->cp_lock, flags); __set_ckpt_flags(F2FS_CKPT(sbi), f); - spin_unlock(&sbi->cp_lock); + spin_unlock_irqrestore(&sbi->cp_lock, flags); } static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) @@ -1244,22 +1393,26 @@ static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f) { - spin_lock(&sbi->cp_lock); + unsigned long flags; + + spin_lock_irqsave(&sbi->cp_lock, flags); __clear_ckpt_flags(F2FS_CKPT(sbi), f); - spin_unlock(&sbi->cp_lock); + spin_unlock_irqrestore(&sbi->cp_lock, flags); } static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock) { + unsigned long flags; + set_sbi_flag(sbi, SBI_NEED_FSCK); if (lock) - spin_lock(&sbi->cp_lock); + spin_lock_irqsave(&sbi->cp_lock, flags); __clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG); kfree(NM_I(sbi)->nat_bits); NM_I(sbi)->nat_bits = NULL; if (lock) - spin_unlock(&sbi->cp_lock); + spin_unlock_irqrestore(&sbi->cp_lock, flags); } static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi, @@ -1275,6 +1428,11 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) down_read(&sbi->cp_rwsem); } +static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi) +{ + return down_read_trylock(&sbi->cp_rwsem); +} + static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) { up_read(&sbi->cp_rwsem); @@ -1324,17 +1482,14 @@ static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) return 0; } -#define F2FS_DEFAULT_ALLOCATED_BLOCKS 1 - /* * Check whether the inode has blocks or not */ static inline int F2FS_HAS_BLOCKS(struct inode *inode) { - if (F2FS_I(inode)->i_xattr_nid) - return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1; - else - return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS; + block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0; + + return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block; } static inline bool f2fs_has_xattr_block(unsigned int ofs) @@ -1342,16 +1497,23 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs) return ofs == XATTR_NODE_OFFSET; } -static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool); -static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi, +static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); +static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, blkcnt_t *count) { - blkcnt_t diff; + blkcnt_t diff = 0, release = 0; + block_t avail_user_block_count; + int ret; + + ret = dquot_reserve_block(inode, *count); + if (ret) + return ret; #ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_BLOCK)) { f2fs_show_injection_info(FAULT_BLOCK); - return false; + release = *count; + goto enospc; } #endif /* @@ -1362,32 +1524,42 @@ static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi, spin_lock(&sbi->stat_lock); sbi->total_valid_block_count += (block_t)(*count); - if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) { - diff = sbi->total_valid_block_count - sbi->user_block_count; + avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks; + if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { + diff = sbi->total_valid_block_count - avail_user_block_count; *count -= diff; - sbi->total_valid_block_count = sbi->user_block_count; + release = diff; + sbi->total_valid_block_count = avail_user_block_count; if (!*count) { spin_unlock(&sbi->stat_lock); percpu_counter_sub(&sbi->alloc_valid_block_count, diff); - return false; + goto enospc; } } spin_unlock(&sbi->stat_lock); - f2fs_i_blocks_write(inode, *count, true); - return true; + if (release) + dquot_release_reservation_block(inode, release); + f2fs_i_blocks_write(inode, *count, true, true); + return 0; + +enospc: + dquot_release_reservation_block(inode, release); + return -ENOSPC; } static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, struct inode *inode, - blkcnt_t count) + block_t count) { + blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK; + spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count); - f2fs_bug_on(sbi, inode->i_blocks < count); + f2fs_bug_on(sbi, inode->i_blocks < sectors); sbi->total_valid_block_count -= (block_t)count; spin_unlock(&sbi->stat_lock); - f2fs_i_blocks_write(inode, count, false); + f2fs_i_blocks_write(inode, count, false, true); } static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) @@ -1516,51 +1688,70 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi) return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum); } -static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi, - struct inode *inode) +static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, + struct inode *inode, bool is_inode) { block_t valid_block_count; unsigned int valid_node_count; + bool quota = inode && !is_inode; + + if (quota) { + int ret = dquot_reserve_block(inode, 1); + if (ret) + return ret; + } spin_lock(&sbi->stat_lock); valid_block_count = sbi->total_valid_block_count + 1; - if (unlikely(valid_block_count > sbi->user_block_count)) { + if (unlikely(valid_block_count + sbi->reserved_blocks > + sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); - return false; + goto enospc; } valid_node_count = sbi->total_valid_node_count + 1; if (unlikely(valid_node_count > sbi->total_node_count)) { spin_unlock(&sbi->stat_lock); - return false; + goto enospc; } - if (inode) - f2fs_i_blocks_write(inode, 1, true); - sbi->total_valid_node_count++; sbi->total_valid_block_count++; spin_unlock(&sbi->stat_lock); + if (inode) { + if (is_inode) + f2fs_mark_inode_dirty_sync(inode, true); + else + f2fs_i_blocks_write(inode, 1, true, true); + } + percpu_counter_inc(&sbi->alloc_valid_block_count); - return true; + return 0; + +enospc: + if (quota) + dquot_release_reservation_block(inode, 1); + return -ENOSPC; } static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, - struct inode *inode) + struct inode *inode, bool is_inode) { spin_lock(&sbi->stat_lock); f2fs_bug_on(sbi, !sbi->total_valid_block_count); f2fs_bug_on(sbi, !sbi->total_valid_node_count); - f2fs_bug_on(sbi, !inode->i_blocks); + f2fs_bug_on(sbi, !is_inode && !inode->i_blocks); - f2fs_i_blocks_write(inode, 1, false); sbi->total_valid_node_count--; sbi->total_valid_block_count--; spin_unlock(&sbi->stat_lock); + + if (!is_inode) + f2fs_i_blocks_write(inode, 1, false, true); } static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi) @@ -1678,20 +1869,38 @@ static inline bool IS_INODE(struct page *page) return RAW_IS_INODE(p); } +static inline int offset_in_addr(struct f2fs_inode *i) +{ + return (i->i_inline & F2FS_EXTRA_ATTR) ? + (le16_to_cpu(i->i_extra_isize) / sizeof(__le32)) : 0; +} + static inline __le32 *blkaddr_in_node(struct f2fs_node *node) { return RAW_IS_INODE(node) ? node->i.i_addr : node->dn.addr; } -static inline block_t datablock_addr(struct page *node_page, - unsigned int offset) +static inline int f2fs_has_extra_attr(struct inode *inode); +static inline block_t datablock_addr(struct inode *inode, + struct page *node_page, unsigned int offset) { struct f2fs_node *raw_node; __le32 *addr_array; + int base = 0; + bool is_inode = IS_INODE(node_page); raw_node = F2FS_NODE(node_page); + + /* from GC path only */ + if (!inode) { + if (is_inode) + base = offset_in_addr(&raw_node->i); + } else if (f2fs_has_extra_attr(inode) && is_inode) { + base = get_extra_isize(inode); + } + addr_array = blkaddr_in_node(raw_node); - return le32_to_cpu(addr_array[offset]); + return le32_to_cpu(addr_array[base + offset]); } static inline int f2fs_test_bit(unsigned int nr, char *addr) @@ -1754,6 +1963,20 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) *addr ^= mask; } +#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) +#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) +#define F2FS_FL_INHERITED (FS_PROJINHERIT_FL) + +static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & F2FS_REG_FLMASK; + else + return flags & F2FS_OTHER_FLMASK; +} + /* used for f2fs_inode_info->flags */ enum { FI_NEW_INODE, /* indicate newly allocated inode */ @@ -1782,6 +2005,8 @@ enum { FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */ FI_NO_PREALLOC, /* indicate skipped preallocated blocks */ FI_HOT_DATA, /* indicate file is hot */ + FI_EXTRA_ATTR, /* indicate file has extra attribute */ + FI_PROJ_INHERIT, /* indicate file inherits projectid */ }; static inline void __mark_inode_dirty_flag(struct inode *inode, @@ -1835,13 +2060,21 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc) } static inline void f2fs_i_blocks_write(struct inode *inode, - blkcnt_t diff, bool add) + block_t diff, bool add, bool claim) { bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE); bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER); - inode->i_blocks = add ? inode->i_blocks + diff : - inode->i_blocks - diff; + /* add = 1, claim = 1 should be dquot_reserve_block in pair */ + if (add) { + if (claim) + dquot_claim_block(inode, diff); + else + dquot_alloc_block_nofail(inode, diff); + } else { + dquot_free_block(inode, diff); + } + f2fs_mark_inode_dirty_sync(inode, true); if (clean || recover) set_inode_flag(inode, FI_AUTO_RECOVER); @@ -1893,6 +2126,8 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri) set_bit(FI_DATA_EXIST, &fi->flags); if (ri->i_inline & F2FS_INLINE_DOTS) set_bit(FI_INLINE_DOTS, &fi->flags); + if (ri->i_inline & F2FS_EXTRA_ATTR) + set_bit(FI_EXTRA_ATTR, &fi->flags); } static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) @@ -1909,6 +2144,13 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri) ri->i_inline |= F2FS_DATA_EXIST; if (is_inode_flag_set(inode, FI_INLINE_DOTS)) ri->i_inline |= F2FS_INLINE_DOTS; + if (is_inode_flag_set(inode, FI_EXTRA_ATTR)) + ri->i_inline |= F2FS_EXTRA_ATTR; +} + +static inline int f2fs_has_extra_attr(struct inode *inode) +{ + return is_inode_flag_set(inode, FI_EXTRA_ATTR); } static inline int f2fs_has_inline_xattr(struct inode *inode) @@ -1919,8 +2161,8 @@ static inline int f2fs_has_inline_xattr(struct inode *inode) static inline unsigned int addrs_per_inode(struct inode *inode) { if (f2fs_has_inline_xattr(inode)) - return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS; - return DEF_ADDRS_PER_INODE; + return CUR_ADDRS_PER_INODE(inode) - F2FS_INLINE_XATTR_ADDRS; + return CUR_ADDRS_PER_INODE(inode); } static inline void *inline_xattr_addr(struct page *page) @@ -1979,11 +2221,12 @@ static inline bool f2fs_is_drop_cache(struct inode *inode) return is_inode_flag_set(inode, FI_DROP_CACHE); } -static inline void *inline_data_addr(struct page *page) +static inline void *inline_data_addr(struct inode *inode, struct page *page) { struct f2fs_inode *ri = F2FS_INODE(page); + int extra_size = get_extra_isize(inode); - return (void *)&(ri->i_addr[1]); + return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]); } static inline int f2fs_has_inline_dentry(struct inode *inode) @@ -2074,10 +2317,50 @@ static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi, return kmalloc(size, flags); } +static inline int get_extra_isize(struct inode *inode) +{ + return F2FS_I(inode)->i_extra_isize / sizeof(__le32); +} + #define get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) +#define F2FS_TOTAL_EXTRA_ATTR_SIZE \ + (offsetof(struct f2fs_inode, i_extra_end) - \ + offsetof(struct f2fs_inode, i_extra_isize)) \ + +#define F2FS_OLD_ATTRIBUTE_SIZE (offsetof(struct f2fs_inode, i_addr)) +#define F2FS_FITS_IN_INODE(f2fs_inode, extra_isize, field) \ + ((offsetof(typeof(*f2fs_inode), field) + \ + sizeof((f2fs_inode)->field)) \ + <= (F2FS_OLD_ATTRIBUTE_SIZE + extra_isize)) \ + +static inline void f2fs_reset_iostat(struct f2fs_sb_info *sbi) +{ + int i; + + spin_lock(&sbi->iostat_lock); + for (i = 0; i < NR_IO_TYPE; i++) + sbi->write_iostat[i] = 0; + spin_unlock(&sbi->iostat_lock); +} + +static inline void f2fs_update_iostat(struct f2fs_sb_info *sbi, + enum iostat_type type, unsigned long long io_bytes) +{ + if (!sbi->iostat_enable) + return; + spin_lock(&sbi->iostat_lock); + sbi->write_iostat[type] += io_bytes; + + if (type == APP_WRITE_IO || type == APP_DIRECT_IO) + sbi->write_iostat[APP_BUFFERED_IO] = + sbi->write_iostat[APP_WRITE_IO] - + sbi->write_iostat[APP_DIRECT_IO]; + spin_unlock(&sbi->iostat_lock); +} + /* * file.c */ @@ -2097,6 +2380,8 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); * inode.c */ void f2fs_set_inode_flags(struct inode *inode); +bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page); +void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page); struct inode *f2fs_iget(struct super_block *sb, unsigned long ino); struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino); int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink); @@ -2165,6 +2450,8 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) */ int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); +void f2fs_enable_quota_files(struct f2fs_sb_info *sbi); +void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); extern __printf(3, 4) @@ -2195,15 +2482,15 @@ int truncate_xattr_node(struct inode *inode, struct page *page); int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino); int remove_inode_page(struct inode *inode); struct page *new_inode_page(struct inode *inode); -struct page *new_node_page(struct dnode_of_data *dn, - unsigned int ofs, struct page *ipage); +struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs); void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); struct page *get_node_page_ra(struct page *parent, int start); void move_node_page(struct page *node_page, int gc_type); int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic); -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc); +int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, + bool do_balance, enum iostat_type io_type); void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount); bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid); void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid); @@ -2224,6 +2511,7 @@ void destroy_node_manager_caches(void); /* * segment.c */ +bool need_SSR(struct f2fs_sb_info *sbi); void register_inmem_page(struct inode *inode, struct page *page); void drop_inmem_pages(struct inode *inode); void drop_inmem_page(struct inode *inode, struct page *page); @@ -2236,7 +2524,8 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free); void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr); bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr); void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new); -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); +void stop_discard_thread(struct f2fs_sb_info *sbi); +void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount); void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); void release_discard_addrs(struct f2fs_sb_info *sbi); int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); @@ -2245,7 +2534,8 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range); bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc); struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno); void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr); -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page); +void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, + enum iostat_type io_type); void write_node_page(unsigned int nid, struct f2fs_io_info *fio); void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio); int rewrite_data_page(struct f2fs_io_info *fio); @@ -2258,11 +2548,11 @@ void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn, bool recover_newaddr); void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, - struct f2fs_summary *sum, int type); + struct f2fs_summary *sum, int type, + struct f2fs_io_info *fio, bool add_list); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered); -void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi, - block_t blkaddr); +void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr); void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); int lookup_journal_in_cursum(struct f2fs_journal *journal, int type, @@ -2285,7 +2575,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type, bool sync); void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index); long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type, - long nr_to_write); + long nr_to_write, enum iostat_type io_type); void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type); void release_ino_entry(struct f2fs_sb_info *sbi, bool all); @@ -2308,14 +2598,13 @@ void destroy_checkpoint_caches(void); /* * data.c */ -void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type, - int rw); -void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi, +void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); +void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type, int rw); -void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi); + enum page_type type); +void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); -int f2fs_submit_page_mbio(struct f2fs_io_info *fio); +int f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, struct bio *bio); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); @@ -2339,6 +2628,9 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len); void f2fs_set_page_dirty_nobuffers(struct page *page); +int __f2fs_write_data_pages(struct address_space *mapping, + struct writeback_control *wbc, + enum iostat_type io_type); void f2fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length); int f2fs_release_page(struct page *page, gfp_t wait); @@ -2633,6 +2925,14 @@ int __init create_extent_cache(void); void destroy_extent_cache(void); /* + * sysfs.c + */ +int __init f2fs_init_sysfs(void); +void f2fs_exit_sysfs(void); +int f2fs_register_sysfs(struct f2fs_sb_info *sbi); +void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi); + +/* * crypto support */ static inline bool f2fs_encrypted_inode(struct inode *inode) @@ -2640,6 +2940,11 @@ static inline bool f2fs_encrypted_inode(struct inode *inode) return file_is_encrypt(inode); } +static inline bool f2fs_encrypted_file(struct inode *inode) +{ + return f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode); +} + static inline void f2fs_set_encrypted_inode(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION @@ -2662,6 +2967,21 @@ static inline int f2fs_sb_mounted_blkzoned(struct super_block *sb) return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_BLKZONED); } +static inline int f2fs_sb_has_extra_attr(struct super_block *sb) +{ + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_EXTRA_ATTR); +} + +static inline int f2fs_sb_has_project_quota(struct super_block *sb) +{ + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_PRJQUOTA); +} + +static inline int f2fs_sb_has_inode_chksum(struct super_block *sb) +{ + return F2FS_HAS_FEATURE(sb, F2FS_FEATURE_INODE_CHKSUM); +} + #ifdef CONFIG_BLK_DEV_ZONED static inline int get_blkz_type(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkaddr) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 61af721329fa..517e112c8a9a 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -33,6 +33,18 @@ #include "trace.h" #include <trace/events/f2fs.h> +static int f2fs_filemap_fault(struct vm_fault *vmf) +{ + struct inode *inode = file_inode(vmf->vma->vm_file); + int err; + + down_read(&F2FS_I(inode)->i_mmap_sem); + err = filemap_fault(vmf); + up_read(&F2FS_I(inode)->i_mmap_sem); + + return err; +} + static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; @@ -59,13 +71,14 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) f2fs_balance_fs(sbi, dn.node_changed); file_update_time(vmf->vma->vm_file); + down_read(&F2FS_I(inode)->i_mmap_sem); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || page_offset(page) > i_size_read(inode) || !PageUptodate(page))) { unlock_page(page); err = -EFAULT; - goto out; + goto out_sem; } /* @@ -85,15 +98,19 @@ static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) if (!PageUptodate(page)) SetPageUptodate(page); + f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE); + trace_f2fs_vm_page_mkwrite(page, DATA); mapped: /* fill the page */ f2fs_wait_on_page_writeback(page, DATA, false); /* wait for GCed encrypted page writeback */ - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr); + if (f2fs_encrypted_file(inode)) + f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr); +out_sem: + up_read(&F2FS_I(inode)->i_mmap_sem); out: sb_end_pagefault(inode->i_sb); f2fs_update_time(sbi, REQ_TIME); @@ -101,7 +118,7 @@ out: } static const struct vm_operations_struct f2fs_file_vm_ops = { - .fault = filemap_fault, + .fault = f2fs_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = f2fs_vm_page_mkwrite, }; @@ -191,7 +208,7 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, /* if fdatasync is triggered, let's do in-place-update */ if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) set_inode_flag(inode, FI_NEED_IPU); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); clear_inode_flag(inode, FI_NEED_IPU); if (ret) { @@ -259,9 +276,19 @@ sync_nodes: goto sync_nodes; } - ret = wait_on_node_pages_writeback(sbi, ino); - if (ret) - goto out; + /* + * If it's atomic_write, it's just fine to keep write ordering. So + * here we don't need to wait for node write completion, since we use + * node chain which serializes node blocks. If one of node writes are + * reordered, we can see simply broken chain, resulting in stopping + * roll-forward recovery. It means we'll recover all or none node blocks + * given fsync mark. + */ + if (!atomic) { + ret = wait_on_node_pages_writeback(sbi, ino); + if (ret) + goto out; + } /* once recovery info is written, don't need to tack this */ remove_ino_entry(sbi, ino, APPEND_INO); @@ -367,7 +394,8 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) dn.ofs_in_node++, pgofs++, data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; - blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + blkaddr = datablock_addr(dn.inode, + dn.node_page, dn.ofs_in_node); if (__found_offset(blkaddr, dirty, pgofs, whence)) { f2fs_put_dnode(&dn); @@ -415,14 +443,6 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) struct inode *inode = file_inode(file); int err; - if (f2fs_encrypted_inode(inode)) { - err = fscrypt_get_encryption_info(inode); - if (err) - return 0; - if (!f2fs_encrypted_inode(inode)) - return -ENOKEY; - } - /* we don't need to use inline_data strictly */ err = f2fs_convert_inline_inode(inode); if (err) @@ -435,11 +455,10 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) static int f2fs_file_open(struct inode *inode, struct file *filp) { - int ret = generic_file_open(inode, filp); struct dentry *dir; - if (!ret && f2fs_encrypted_inode(inode)) { - ret = fscrypt_get_encryption_info(inode); + if (f2fs_encrypted_inode(inode)) { + int ret = fscrypt_get_encryption_info(inode); if (ret) return -EACCES; if (!fscrypt_has_encryption_key(inode)) @@ -452,7 +471,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) return -EPERM; } dput(dir); - return ret; + return dquot_file_open(inode, filp); } int truncate_data_blocks_range(struct dnode_of_data *dn, int count) @@ -461,9 +480,13 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count) struct f2fs_node *raw_node; int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; + int base = 0; + + if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) + base = get_extra_isize(dn->inode); raw_node = F2FS_NODE(dn->node_page); - addr = blkaddr_in_node(raw_node) + ofs; + addr = blkaddr_in_node(raw_node) + base + ofs; for (; count > 0; count--, addr++, dn->ofs_in_node++) { block_t blkaddr = le32_to_cpu(*addr); @@ -527,8 +550,10 @@ static int truncate_partial_data_page(struct inode *inode, u64 from, truncate_out: f2fs_wait_on_page_writeback(page, DATA, true); zero_user(page, offset, PAGE_SIZE - offset); - if (!cache_only || !f2fs_encrypted_inode(inode) || - !S_ISREG(inode->i_mode)) + + /* An encrypted inode should have a key and truncate the last page. */ + f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode)); + if (!cache_only) set_page_dirty(page); f2fs_put_page(page, 1); return 0; @@ -633,11 +658,31 @@ int f2fs_truncate(struct inode *inode) } int f2fs_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int flags) + u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int flags; + + flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); + if (flags & FS_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (flags & FS_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (f2fs_encrypted_inode(inode)) + stat->attributes |= STATX_ATTR_ENCRYPTED; + if (flags & FS_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + if (flags & FS_NODUMP_FL) + stat->attributes |= STATX_ATTR_NODUMP; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE | + STATX_ATTR_NODUMP); + generic_fillattr(inode, stat); - stat->blocks <<= 3; return 0; } @@ -681,14 +726,34 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) if (err) return err; + if (is_quota_modification(inode, attr)) { + err = dquot_initialize(inode); + if (err) + return err; + } + if ((attr->ia_valid & ATTR_UID && + !uid_eq(attr->ia_uid, inode->i_uid)) || + (attr->ia_valid & ATTR_GID && + !gid_eq(attr->ia_gid, inode->i_gid))) { + err = dquot_transfer(inode, attr); + if (err) + return err; + } + if (attr->ia_valid & ATTR_SIZE) { - if (f2fs_encrypted_inode(inode) && - fscrypt_get_encryption_info(inode)) - return -EACCES; + if (f2fs_encrypted_inode(inode)) { + err = fscrypt_get_encryption_info(inode); + if (err) + return err; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } if (attr->ia_size <= i_size_read(inode)) { + down_write(&F2FS_I(inode)->i_mmap_sem); truncate_setsize(inode, attr->ia_size); err = f2fs_truncate(inode); + up_write(&F2FS_I(inode)->i_mmap_sem); if (err) return err; } else { @@ -696,7 +761,9 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) * do not trim all blocks after i_size if target size is * larger than i_size. */ + down_write(&F2FS_I(inode)->i_mmap_sem); truncate_setsize(inode, attr->ia_size); + up_write(&F2FS_I(inode)->i_mmap_sem); /* should convert inline inode here */ if (!f2fs_may_inline_data(inode)) { @@ -839,12 +906,14 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len) blk_start = (loff_t)pg_start << PAGE_SHIFT; blk_end = (loff_t)pg_end << PAGE_SHIFT; + down_write(&F2FS_I(inode)->i_mmap_sem); truncate_inode_pages_range(mapping, blk_start, blk_end - 1); f2fs_lock_op(sbi); ret = truncate_hole(inode, pg_start, pg_end); f2fs_unlock_op(sbi); + up_write(&F2FS_I(inode)->i_mmap_sem); } } @@ -875,7 +944,8 @@ next_dnode: done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) - dn.ofs_in_node, len); for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { - *blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node); + *blkaddr = datablock_addr(dn.inode, + dn.node_page, dn.ofs_in_node); if (!is_checkpointed_data(sbi, *blkaddr)) { if (test_opt(sbi, LFS)) { @@ -951,15 +1021,15 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, ADDRS_PER_PAGE(dn.node_page, dst_inode) - dn.ofs_in_node, len - i); do { - dn.data_blkaddr = datablock_addr(dn.node_page, - dn.ofs_in_node); + dn.data_blkaddr = datablock_addr(dn.inode, + dn.node_page, dn.ofs_in_node); truncate_data_blocks_range(&dn, 1); if (do_replace[i]) { f2fs_i_blocks_write(src_inode, - 1, false); + 1, false, false); f2fs_i_blocks_write(dst_inode, - 1, true); + 1, true, false); f2fs_replace_block(sbi, &dn, dn.data_blkaddr, blkaddr[i], ni.version, true, false); @@ -1083,16 +1153,17 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) pg_start = offset >> PAGE_SHIFT; pg_end = (offset + len) >> PAGE_SHIFT; + down_write(&F2FS_I(inode)->i_mmap_sem); /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) - return ret; + goto out; truncate_pagecache(inode, offset); ret = f2fs_do_collapse(inode, pg_start, pg_end); if (ret) - return ret; + goto out; /* write out all moved pages, if possible */ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); @@ -1105,6 +1176,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) if (!ret) f2fs_i_size_write(inode, new_size); +out: + up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } @@ -1118,7 +1191,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, int ret; for (; index < end; index++, dn->ofs_in_node++) { - if (datablock_addr(dn->node_page, dn->ofs_in_node) == NULL_ADDR) + if (datablock_addr(dn->inode, dn->node_page, + dn->ofs_in_node) == NULL_ADDR) count++; } @@ -1129,8 +1203,8 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, dn->ofs_in_node = ofs_in_node; for (index = start; index < end; index++, dn->ofs_in_node++) { - dn->data_blkaddr = - datablock_addr(dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = datablock_addr(dn->inode, + dn->node_page, dn->ofs_in_node); /* * reserve_new_blocks will not guarantee entire block * allocation. @@ -1169,9 +1243,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, if (ret) return ret; + down_write(&F2FS_I(inode)->i_mmap_sem); ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); if (ret) - return ret; + goto out_sem; truncate_pagecache_range(inode, offset, offset + len - 1); @@ -1185,7 +1260,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = fill_zero(inode, pg_start, off_start, off_end - off_start); if (ret) - return ret; + goto out_sem; new_size = max_t(loff_t, new_size, offset + len); } else { @@ -1193,7 +1268,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, ret = fill_zero(inode, pg_start++, off_start, PAGE_SIZE - off_start); if (ret) - return ret; + goto out_sem; new_size = max_t(loff_t, new_size, (loff_t)pg_start << PAGE_SHIFT); @@ -1242,6 +1317,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, out: if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) f2fs_i_size_write(inode, new_size); +out_sem: + up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } @@ -1271,14 +1348,15 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); + down_write(&F2FS_I(inode)->i_mmap_sem); ret = truncate_blocks(inode, i_size_read(inode), true); if (ret) - return ret; + goto out; /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) - return ret; + goto out; truncate_pagecache(inode, offset); @@ -1307,6 +1385,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) if (!ret) f2fs_i_size_write(inode, new_size); +out: + up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } @@ -1434,33 +1514,67 @@ static int f2fs_release_file(struct inode *inode, struct file *filp) return 0; } -#define F2FS_REG_FLMASK (~(FS_DIRSYNC_FL | FS_TOPDIR_FL)) -#define F2FS_OTHER_FLMASK (FS_NODUMP_FL | FS_NOATIME_FL) - -static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags) +static int f2fs_file_flush(struct file *file, fl_owner_t id) { - if (S_ISDIR(mode)) - return flags; - else if (S_ISREG(mode)) - return flags & F2FS_REG_FLMASK; - else - return flags & F2FS_OTHER_FLMASK; + struct inode *inode = file_inode(file); + + /* + * If the process doing a transaction is crashed, we should do + * roll-back. Otherwise, other reader/write can see corrupted database + * until all the writers close its file. Since this should be done + * before dropping file lock, it needs to do in ->flush. + */ + if (f2fs_is_atomic_file(inode) && + F2FS_I(inode)->inmem_task == current) + drop_inmem_pages(inode); + return 0; } static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); - unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE; + unsigned int flags = fi->i_flags & + (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); return put_user(flags, (int __user *)arg); } +static int __f2fs_ioc_setflags(struct inode *inode, unsigned int flags) +{ + struct f2fs_inode_info *fi = F2FS_I(inode); + unsigned int oldflags; + + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + return -EPERM; + + flags = f2fs_mask_flags(inode->i_mode, flags); + + oldflags = fi->i_flags; + + if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + flags = flags & (FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); + flags |= oldflags & ~(FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); + fi->i_flags = flags; + + if (fi->i_flags & FS_PROJINHERIT_FL) + set_inode_flag(inode, FI_PROJ_INHERIT); + else + clear_inode_flag(inode, FI_PROJ_INHERIT); + + inode->i_ctime = current_time(inode); + f2fs_set_inode_flags(inode); + f2fs_mark_inode_dirty_sync(inode, false); + return 0; +} + static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); - struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int flags; - unsigned int oldflags; int ret; if (!inode_owner_or_capable(inode)) @@ -1475,27 +1589,9 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) inode_lock(inode); - flags = f2fs_mask_flags(inode->i_mode, flags); - - oldflags = fi->i_flags; - - if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - inode_unlock(inode); - ret = -EPERM; - goto out; - } - } - - flags = flags & FS_FL_USER_MODIFIABLE; - flags |= oldflags & ~FS_FL_USER_MODIFIABLE; - fi->i_flags = flags; - - inode->i_ctime = current_time(inode); - f2fs_set_inode_flags(inode); + ret = __f2fs_ioc_setflags(inode, flags); inode_unlock(inode); -out: mnt_drop_write_file(filp); return ret; } @@ -1544,10 +1640,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) { clear_inode_flag(inode, FI_ATOMIC_FILE); + clear_inode_flag(inode, FI_HOT_DATA); goto out; } inc_stat: + F2FS_I(inode)->inmem_task = current; stat_inc_atomic_write(inode); stat_update_max_atomic_write(inode); out: @@ -1581,10 +1679,11 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); if (!ret) { clear_inode_flag(inode, FI_ATOMIC_FILE); + clear_inode_flag(inode, FI_HOT_DATA); stat_dec_atomic_write(inode); } } else { - ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); + ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } err_out: inode_unlock(inode); @@ -1720,7 +1819,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) f2fs_stop_checkpoint(sbi, false); break; case F2FS_GOING_DOWN_METAFLUSH: - sync_meta_pages(sbi, META, LONG_MAX); + sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); f2fs_stop_checkpoint(sbi, false); break; default: @@ -1862,6 +1961,50 @@ out: return ret; } +static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_gc_range range; + u64 end; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg, + sizeof(range))) + return -EFAULT; + + if (f2fs_readonly(sbi->sb)) + return -EROFS; + + ret = mnt_want_write_file(filp); + if (ret) + return ret; + + end = range.start + range.len; + if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) + return -EINVAL; +do_more: + if (!range.sync) { + if (!mutex_trylock(&sbi->gc_mutex)) { + ret = -EBUSY; + goto out; + } + } else { + mutex_lock(&sbi->gc_mutex); + } + + ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start)); + range.start += sbi->blocks_per_seg; + if (range.start <= end) + goto do_more; +out: + mnt_drop_write_file(filp); + return ret; +} + static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1933,7 +2076,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, */ while (map.m_lblk < pg_end) { map.m_len = pg_end - map.m_lblk; - err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT); if (err) goto out; @@ -1975,7 +2118,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, do_map: map.m_len = pg_end - map.m_lblk; - err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_READ); + err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT); if (err) goto clear_out; @@ -2274,6 +2417,210 @@ out: return ret; } +static int f2fs_ioc_get_features(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature); + + /* Must validate to set it with SQLite behavior in Android. */ + sb_feature |= F2FS_FEATURE_ATOMIC_WRITE; + + return put_user(sb_feature, (u32 __user *)arg); +} + +#ifdef CONFIG_QUOTA +static int f2fs_ioc_setproject(struct file *filp, __u32 projid) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct super_block *sb = sbi->sb; + struct dquot *transfer_to[MAXQUOTAS] = {}; + struct page *ipage; + kprojid_t kprojid; + int err; + + if (!f2fs_sb_has_project_quota(sb)) { + if (projid != F2FS_DEF_PROJID) + return -EOPNOTSUPP; + else + return 0; + } + + if (!f2fs_has_extra_attr(inode)) + return -EOPNOTSUPP; + + kprojid = make_kprojid(&init_user_ns, (projid_t)projid); + + if (projid_eq(kprojid, F2FS_I(inode)->i_projid)) + return 0; + + err = mnt_want_write_file(filp); + if (err) + return err; + + err = -EPERM; + inode_lock(inode); + + /* Is it quota file? Do not allow user to mess with it */ + if (IS_NOQUOTA(inode)) + goto out_unlock; + + ipage = get_node_page(sbi, inode->i_ino); + if (IS_ERR(ipage)) { + err = PTR_ERR(ipage); + goto out_unlock; + } + + if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize, + i_projid)) { + err = -EOVERFLOW; + f2fs_put_page(ipage, 1); + goto out_unlock; + } + f2fs_put_page(ipage, 1); + + dquot_initialize(inode); + + transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); + if (!IS_ERR(transfer_to[PRJQUOTA])) { + err = __dquot_transfer(inode, transfer_to); + dqput(transfer_to[PRJQUOTA]); + if (err) + goto out_dirty; + } + + F2FS_I(inode)->i_projid = kprojid; + inode->i_ctime = current_time(inode); +out_dirty: + f2fs_mark_inode_dirty_sync(inode, true); +out_unlock: + inode_unlock(inode); + mnt_drop_write_file(filp); + return err; +} +#else +static int f2fs_ioc_setproject(struct file *filp, __u32 projid) +{ + if (projid != F2FS_DEF_PROJID) + return -EOPNOTSUPP; + return 0; +} +#endif + +/* Transfer internal flags to xflags */ +static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags) +{ + __u32 xflags = 0; + + if (iflags & FS_SYNC_FL) + xflags |= FS_XFLAG_SYNC; + if (iflags & FS_IMMUTABLE_FL) + xflags |= FS_XFLAG_IMMUTABLE; + if (iflags & FS_APPEND_FL) + xflags |= FS_XFLAG_APPEND; + if (iflags & FS_NODUMP_FL) + xflags |= FS_XFLAG_NODUMP; + if (iflags & FS_NOATIME_FL) + xflags |= FS_XFLAG_NOATIME; + if (iflags & FS_PROJINHERIT_FL) + xflags |= FS_XFLAG_PROJINHERIT; + return xflags; +} + +#define F2FS_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \ + FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \ + FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT) + +/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ +#define F2FS_FL_XFLAG_VISIBLE (FS_SYNC_FL | \ + FS_IMMUTABLE_FL | \ + FS_APPEND_FL | \ + FS_NODUMP_FL | \ + FS_NOATIME_FL | \ + FS_PROJINHERIT_FL) + +/* Transfer xflags flags to internal */ +static inline unsigned long f2fs_xflags_to_iflags(__u32 xflags) +{ + unsigned long iflags = 0; + + if (xflags & FS_XFLAG_SYNC) + iflags |= FS_SYNC_FL; + if (xflags & FS_XFLAG_IMMUTABLE) + iflags |= FS_IMMUTABLE_FL; + if (xflags & FS_XFLAG_APPEND) + iflags |= FS_APPEND_FL; + if (xflags & FS_XFLAG_NODUMP) + iflags |= FS_NODUMP_FL; + if (xflags & FS_XFLAG_NOATIME) + iflags |= FS_NOATIME_FL; + if (xflags & FS_XFLAG_PROJINHERIT) + iflags |= FS_PROJINHERIT_FL; + + return iflags; +} + +static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct fsxattr fa; + + memset(&fa, 0, sizeof(struct fsxattr)); + fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags & + (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL)); + + if (f2fs_sb_has_project_quota(inode->i_sb)) + fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, + fi->i_projid); + + if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) + return -EFAULT; + return 0; +} + +static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct f2fs_inode_info *fi = F2FS_I(inode); + struct fsxattr fa; + unsigned int flags; + int err; + + if (copy_from_user(&fa, (struct fsxattr __user *)arg, sizeof(fa))) + return -EFAULT; + + /* Make sure caller has proper permission */ + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (fa.fsx_xflags & ~F2FS_SUPPORTED_FS_XFLAGS) + return -EOPNOTSUPP; + + flags = f2fs_xflags_to_iflags(fa.fsx_xflags); + if (f2fs_mask_flags(inode->i_mode, flags) != flags) + return -EOPNOTSUPP; + + err = mnt_want_write_file(filp); + if (err) + return err; + + inode_lock(inode); + flags = (fi->i_flags & ~F2FS_FL_XFLAG_VISIBLE) | + (flags & F2FS_FL_XFLAG_VISIBLE); + err = __f2fs_ioc_setflags(inode, flags); + inode_unlock(inode); + mnt_drop_write_file(filp); + if (err) + return err; + + err = f2fs_ioc_setproject(filp, fa.fsx_projid); + if (err) + return err; + + return 0; +} long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { @@ -2306,6 +2653,8 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_get_encryption_pwsalt(filp, arg); case F2FS_IOC_GARBAGE_COLLECT: return f2fs_ioc_gc(filp, arg); + case F2FS_IOC_GARBAGE_COLLECT_RANGE: + return f2fs_ioc_gc_range(filp, arg); case F2FS_IOC_WRITE_CHECKPOINT: return f2fs_ioc_write_checkpoint(filp, arg); case F2FS_IOC_DEFRAGMENT: @@ -2314,6 +2663,12 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return f2fs_ioc_move_range(filp, arg); case F2FS_IOC_FLUSH_DEVICE: return f2fs_ioc_flush_device(filp, arg); + case F2FS_IOC_GET_FEATURES: + return f2fs_ioc_get_features(filp, arg); + case F2FS_IOC_FSGETXATTR: + return f2fs_ioc_fsgetxattr(filp, arg); + case F2FS_IOC_FSSETXATTR: + return f2fs_ioc_fssetxattr(filp, arg); default: return -ENOTTY; } @@ -2326,11 +2681,6 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct blk_plug plug; ssize_t ret; - if (f2fs_encrypted_inode(inode) && - !fscrypt_has_encryption_key(inode) && - fscrypt_get_encryption_info(inode)) - return -EACCES; - inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) { @@ -2348,6 +2698,9 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) ret = __generic_file_write_iter(iocb, from); blk_finish_plug(&plug); clear_inode_flag(inode, FI_NO_PREALLOC); + + if (ret > 0) + f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); } inode_unlock(inode); @@ -2379,10 +2732,14 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case F2FS_IOC_GET_ENCRYPTION_PWSALT: case F2FS_IOC_GET_ENCRYPTION_POLICY: case F2FS_IOC_GARBAGE_COLLECT: + case F2FS_IOC_GARBAGE_COLLECT_RANGE: case F2FS_IOC_WRITE_CHECKPOINT: case F2FS_IOC_DEFRAGMENT: case F2FS_IOC_MOVE_RANGE: case F2FS_IOC_FLUSH_DEVICE: + case F2FS_IOC_GET_FEATURES: + case F2FS_IOC_FSGETXATTR: + case F2FS_IOC_FSSETXATTR: break; default: return -ENOIOCTLCMD; @@ -2398,6 +2755,7 @@ const struct file_operations f2fs_file_operations = { .open = f2fs_file_open, .release = f2fs_release_file, .mmap = f2fs_file_mmap, + .flush = f2fs_file_flush, .fsync = f2fs_sync_file, .fallocate = f2fs_fallocate, .unlocked_ioctl = f2fs_ioctl, diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 026522107ca3..bfe6a8ccc3a0 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -28,17 +28,23 @@ static int gc_thread_func(void *data) struct f2fs_sb_info *sbi = data; struct f2fs_gc_kthread *gc_th = sbi->gc_thread; wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; - long wait_ms; + unsigned int wait_ms; wait_ms = gc_th->min_sleep_time; + set_freezable(); do { + wait_event_interruptible_timeout(*wq, + kthread_should_stop() || freezing(current) || + gc_th->gc_wake, + msecs_to_jiffies(wait_ms)); + + /* give it a try one time */ + if (gc_th->gc_wake) + gc_th->gc_wake = 0; + if (try_to_freeze()) continue; - else - wait_event_interruptible_timeout(*wq, - kthread_should_stop(), - msecs_to_jiffies(wait_ms)); if (kthread_should_stop()) break; @@ -54,6 +60,9 @@ static int gc_thread_func(void *data) } #endif + if (!sb_start_write_trylock(sbi->sb)) + continue; + /* * [GC triggering condition] * 0. GC is not conducted currently. @@ -68,19 +77,24 @@ static int gc_thread_func(void *data) * So, I'd like to wait some time to collect dirty segments. */ if (!mutex_trylock(&sbi->gc_mutex)) - continue; + goto next; + + if (gc_th->gc_urgent) { + wait_ms = gc_th->urgent_sleep_time; + goto do_gc; + } if (!is_idle(sbi)) { increase_sleep_time(gc_th, &wait_ms); mutex_unlock(&sbi->gc_mutex); - continue; + goto next; } if (has_enough_invalid_blocks(sbi)) decrease_sleep_time(gc_th, &wait_ms); else increase_sleep_time(gc_th, &wait_ms); - +do_gc: stat_inc_bggc_count(sbi); /* if return value is not zero, no victim was selected */ @@ -92,6 +106,8 @@ static int gc_thread_func(void *data) /* balancing f2fs's metadata periodically */ f2fs_balance_fs_bg(sbi); +next: + sb_end_write(sbi->sb); } while (!kthread_should_stop()); return 0; @@ -109,11 +125,14 @@ int start_gc_thread(struct f2fs_sb_info *sbi) goto out; } + gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME; gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME; gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME; gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME; gc_th->gc_idle = 0; + gc_th->gc_urgent = 0; + gc_th->gc_wake= 0; sbi->gc_thread = gc_th; init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head); @@ -572,7 +591,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, } *nofs = ofs_of_node(node_page); - source_blkaddr = datablock_addr(node_page, ofs_in_node); + source_blkaddr = datablock_addr(NULL, node_page, ofs_in_node); f2fs_put_page(node_page, 1); if (source_blkaddr != blkaddr) @@ -580,15 +599,21 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, return true; } -static void move_encrypted_block(struct inode *inode, block_t bidx, - unsigned int segno, int off) +/* + * Move data block via META_MAPPING while keeping locked data page. + * This can be used to move blocks, aka LBAs, directly on disk. + */ +static void move_data_block(struct inode *inode, block_t bidx, + unsigned int segno, int off) { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .type = DATA, + .temp = COLD, .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, + .in_list = false, }; struct dnode_of_data dn; struct f2fs_summary sum; @@ -632,7 +657,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx, fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, - &sum, CURSEG_COLD_DATA); + &sum, CURSEG_COLD_DATA, NULL, false); fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); @@ -670,7 +695,9 @@ static void move_encrypted_block(struct inode *inode, block_t bidx, fio.op = REQ_OP_WRITE; fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; - f2fs_submit_page_mbio(&fio); + f2fs_submit_page_write(&fio); + + f2fs_update_iostat(fio.sbi, FS_GC_DATA_IO, F2FS_BLKSIZE); f2fs_update_data_blkaddr(&dn, newaddr); set_inode_flag(inode, FI_APPEND_WRITE); @@ -712,12 +739,14 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type, struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .type = DATA, + .temp = COLD, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC, .old_blkaddr = NULL_ADDR, .page = page, .encrypted_page = NULL, - .need_lock = true, + .need_lock = LOCK_REQ, + .io_type = FS_GC_DATA_IO, }; bool is_dirty = PageDirty(page); int err; @@ -806,8 +835,7 @@ next_step: continue; /* if encrypted inode, let's go phase 3 */ - if (f2fs_encrypted_inode(inode) && - S_ISREG(inode->i_mode)) { + if (f2fs_encrypted_file(inode)) { add_gc_inode(gc_list, inode); continue; } @@ -841,14 +869,18 @@ next_step: continue; } locked = true; + + /* wait for all inflight aio data */ + inode_dio_wait(inode); } start_bidx = start_bidx_of_node(nofs, inode) + ofs_in_node; - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) - move_encrypted_block(inode, start_bidx, segno, off); + if (f2fs_encrypted_file(inode)) + move_data_block(inode, start_bidx, segno, off); else - move_data_page(inode, start_bidx, gc_type, segno, off); + move_data_page(inode, start_bidx, gc_type, + segno, off); if (locked) { up_write(&fi->dio_rwsem[WRITE]); @@ -885,7 +917,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, struct blk_plug plug; unsigned int segno = start_segno; unsigned int end_segno = start_segno + sbi->segs_per_sec; - int sec_freed = 0; + int seg_freed = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; @@ -931,31 +963,31 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, gc_type); stat_inc_seg_count(sbi, type, gc_type); + + if (gc_type == FG_GC && + get_valid_blocks(sbi, segno, false) == 0) + seg_freed++; next: f2fs_put_page(sum_page, 0); } if (gc_type == FG_GC) - f2fs_submit_merged_bio(sbi, - (type == SUM_TYPE_NODE) ? NODE : DATA, WRITE); + f2fs_submit_merged_write(sbi, + (type == SUM_TYPE_NODE) ? NODE : DATA); blk_finish_plug(&plug); - if (gc_type == FG_GC && - get_valid_blocks(sbi, start_segno, true) == 0) - sec_freed = 1; - stat_inc_call_count(sbi->stat_info); - return sec_freed; + return seg_freed; } int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background, unsigned int segno) { int gc_type = sync ? FG_GC : BG_GC; - int sec_freed = 0; - int ret = -EINVAL; + int sec_freed = 0, seg_freed = 0, total_freed = 0; + int ret = 0; struct cp_control cpc; unsigned int init_segno = segno; struct gc_inode_list gc_list = { @@ -963,10 +995,21 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, .iroot = RADIX_TREE_INIT(GFP_NOFS), }; + trace_f2fs_gc_begin(sbi->sb, sync, background, + get_pages(sbi, F2FS_DIRTY_NODES), + get_pages(sbi, F2FS_DIRTY_DENTS), + get_pages(sbi, F2FS_DIRTY_IMETA), + free_sections(sbi), + free_segments(sbi), + reserved_segments(sbi), + prefree_segments(sbi)); + cpc.reason = __get_cp_reason(sbi); gc_more: - if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) + if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) { + ret = -EINVAL; goto stop; + } if (unlikely(f2fs_cp_error(sbi))) { ret = -EIO; goto stop; @@ -988,15 +1031,19 @@ gc_more: } /* f2fs_balance_fs doesn't need to do BG_GC in critical path. */ - if (gc_type == BG_GC && !background) + if (gc_type == BG_GC && !background) { + ret = -EINVAL; goto stop; - if (!__get_victim(sbi, &segno, gc_type)) + } + if (!__get_victim(sbi, &segno, gc_type)) { + ret = -ENODATA; goto stop; - ret = 0; + } - if (do_garbage_collect(sbi, segno, &gc_list, gc_type) && - gc_type == FG_GC) + seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type); + if (gc_type == FG_GC && seg_freed == sbi->segs_per_sec) sec_freed++; + total_freed += seg_freed; if (gc_type == FG_GC) sbi->cur_victim_sec = NULL_SEGNO; @@ -1013,6 +1060,16 @@ gc_more: stop: SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0; SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno; + + trace_f2fs_gc_end(sbi->sb, ret, total_freed, sec_freed, + get_pages(sbi, F2FS_DIRTY_NODES), + get_pages(sbi, F2FS_DIRTY_DENTS), + get_pages(sbi, F2FS_DIRTY_IMETA), + free_sections(sbi), + free_segments(sbi), + reserved_segments(sbi), + prefree_segments(sbi)); + mutex_unlock(&sbi->gc_mutex); put_gc_inode(&gc_list); diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index a993967dcdb9..9325191fab2d 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -13,6 +13,7 @@ * whether IO subsystem is idle * or not */ +#define DEF_GC_THREAD_URGENT_SLEEP_TIME 500 /* 500 ms */ #define DEF_GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */ #define DEF_GC_THREAD_MAX_SLEEP_TIME 60000 #define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */ @@ -27,12 +28,15 @@ struct f2fs_gc_kthread { wait_queue_head_t gc_wait_queue_head; /* for gc sleep time */ + unsigned int urgent_sleep_time; unsigned int min_sleep_time; unsigned int max_sleep_time; unsigned int no_gc_sleep_time; /* for changing gc mode */ unsigned int gc_idle; + unsigned int gc_urgent; + unsigned int gc_wake; }; struct gc_inode_list { @@ -65,25 +69,32 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi) } static inline void increase_sleep_time(struct f2fs_gc_kthread *gc_th, - long *wait) + unsigned int *wait) { + unsigned int min_time = gc_th->min_sleep_time; + unsigned int max_time = gc_th->max_sleep_time; + if (*wait == gc_th->no_gc_sleep_time) return; - *wait += gc_th->min_sleep_time; - if (*wait > gc_th->max_sleep_time) - *wait = gc_th->max_sleep_time; + if ((long long)*wait + (long long)min_time > (long long)max_time) + *wait = max_time; + else + *wait += min_time; } static inline void decrease_sleep_time(struct f2fs_gc_kthread *gc_th, - long *wait) + unsigned int *wait) { + unsigned int min_time = gc_th->min_sleep_time; + if (*wait == gc_th->no_gc_sleep_time) *wait = gc_th->max_sleep_time; - *wait -= gc_th->min_sleep_time; - if (*wait <= gc_th->min_sleep_time) - *wait = gc_th->min_sleep_time; + if ((long long)*wait - (long long)min_time < (long long)min_time) + *wait = min_time; + else + *wait -= min_time; } static inline bool has_enough_invalid_blocks(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index e4c527c4e7d0..8322e4e7bb3f 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -22,10 +22,10 @@ bool f2fs_may_inline_data(struct inode *inode) if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode)) return false; - if (i_size_read(inode) > MAX_INLINE_DATA) + if (i_size_read(inode) > MAX_INLINE_DATA(inode)) return false; - if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + if (f2fs_encrypted_file(inode)) return false; return true; @@ -44,6 +44,7 @@ bool f2fs_may_inline_dentry(struct inode *inode) void read_inline_data(struct page *page, struct page *ipage) { + struct inode *inode = page->mapping->host; void *src_addr, *dst_addr; if (PageUptodate(page)) @@ -51,12 +52,12 @@ void read_inline_data(struct page *page, struct page *ipage) f2fs_bug_on(F2FS_P_SB(page), page->index); - zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE); + zero_user_segment(page, MAX_INLINE_DATA(inode), PAGE_SIZE); /* Copy the whole inline data block */ - src_addr = inline_data_addr(ipage); + src_addr = inline_data_addr(inode, ipage); dst_addr = kmap_atomic(page); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); flush_dcache_page(page); kunmap_atomic(dst_addr); if (!PageUptodate(page)) @@ -67,13 +68,13 @@ void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from) { void *addr; - if (from >= MAX_INLINE_DATA) + if (from >= MAX_INLINE_DATA(inode)) return; - addr = inline_data_addr(ipage); + addr = inline_data_addr(inode, ipage); f2fs_wait_on_page_writeback(ipage, NODE, true); - memset(addr + from, 0, MAX_INLINE_DATA - from); + memset(addr + from, 0, MAX_INLINE_DATA(inode) - from); set_page_dirty(ipage); if (from == 0) @@ -116,6 +117,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) .op_flags = REQ_SYNC | REQ_PRIO, .page = page, .encrypted_page = NULL, + .io_type = FS_DATA_IO, }; int dirty, err; @@ -200,6 +202,8 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; struct dnode_of_data dn; + struct address_space *mapping = page_mapping(page); + unsigned long flags; int err; set_new_dnode(&dn, inode, NULL, NULL, 0); @@ -216,11 +220,16 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) f2fs_wait_on_page_writeback(dn.inode_page, NODE, true); src_addr = kmap_atomic(page); - dst_addr = inline_data_addr(dn.inode_page); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + dst_addr = inline_data_addr(inode, dn.inode_page); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); kunmap_atomic(src_addr); set_page_dirty(dn.inode_page); + spin_lock_irqsave(&mapping->tree_lock, flags); + radix_tree_tag_clear(&mapping->page_tree, page_index(page), + PAGECACHE_TAG_DIRTY); + spin_unlock_irqrestore(&mapping->tree_lock, flags); + set_inode_flag(inode, FI_APPEND_WRITE); set_inode_flag(inode, FI_DATA_EXIST); @@ -255,9 +264,9 @@ process_inline: f2fs_wait_on_page_writeback(ipage, NODE, true); - src_addr = inline_data_addr(npage); - dst_addr = inline_data_addr(ipage); - memcpy(dst_addr, src_addr, MAX_INLINE_DATA); + src_addr = inline_data_addr(inode, npage); + dst_addr = inline_data_addr(inode, ipage); + memcpy(dst_addr, src_addr, MAX_INLINE_DATA(inode)); set_inode_flag(inode, FI_INLINE_DATA); set_inode_flag(inode, FI_DATA_EXIST); @@ -285,11 +294,11 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, struct fscrypt_name *fname, struct page **res_page) { struct f2fs_sb_info *sbi = F2FS_SB(dir->i_sb); - struct f2fs_inline_dentry *inline_dentry; struct qstr name = FSTR_TO_QSTR(&fname->disk_name); struct f2fs_dir_entry *de; struct f2fs_dentry_ptr d; struct page *ipage; + void *inline_dentry; f2fs_hash_t namehash; ipage = get_node_page(sbi, dir->i_ino); @@ -300,9 +309,9 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, namehash = f2fs_dentry_hash(&name, fname); - inline_dentry = inline_data_addr(ipage); + inline_dentry = inline_data_addr(dir, ipage); - make_dentry_ptr_inline(NULL, &d, inline_dentry); + make_dentry_ptr_inline(dir, &d, inline_dentry); de = find_target_dentry(fname, namehash, NULL, &d); unlock_page(ipage); if (de) @@ -316,19 +325,19 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir, int make_empty_inline_dir(struct inode *inode, struct inode *parent, struct page *ipage) { - struct f2fs_inline_dentry *dentry_blk; struct f2fs_dentry_ptr d; + void *inline_dentry; - dentry_blk = inline_data_addr(ipage); + inline_dentry = inline_data_addr(inode, ipage); - make_dentry_ptr_inline(NULL, &d, dentry_blk); + make_dentry_ptr_inline(inode, &d, inline_dentry); do_make_empty_dir(inode, parent, &d); set_page_dirty(ipage); /* update i_size to MAX_INLINE_DATA */ - if (i_size_read(inode) < MAX_INLINE_DATA) - f2fs_i_size_write(inode, MAX_INLINE_DATA); + if (i_size_read(inode) < MAX_INLINE_DATA(inode)) + f2fs_i_size_write(inode, MAX_INLINE_DATA(inode)); return 0; } @@ -337,11 +346,12 @@ int make_empty_inline_dir(struct inode *inode, struct inode *parent, * release ipage in this function. */ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, - struct f2fs_inline_dentry *inline_dentry) + void *inline_dentry) { struct page *page; struct dnode_of_data dn; struct f2fs_dentry_block *dentry_blk; + struct f2fs_dentry_ptr src, dst; int err; page = f2fs_grab_cache_page(dir->i_mapping, 0, false); @@ -356,25 +366,24 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage, goto out; f2fs_wait_on_page_writeback(page, DATA, true); - zero_user_segment(page, MAX_INLINE_DATA, PAGE_SIZE); + zero_user_segment(page, MAX_INLINE_DATA(dir), PAGE_SIZE); dentry_blk = kmap_atomic(page); + make_dentry_ptr_inline(dir, &src, inline_dentry); + make_dentry_ptr_block(dir, &dst, dentry_blk); + /* copy data from inline dentry block to new dentry block */ - memcpy(dentry_blk->dentry_bitmap, inline_dentry->dentry_bitmap, - INLINE_DENTRY_BITMAP_SIZE); - memset(dentry_blk->dentry_bitmap + INLINE_DENTRY_BITMAP_SIZE, 0, - SIZE_OF_DENTRY_BITMAP - INLINE_DENTRY_BITMAP_SIZE); + memcpy(dst.bitmap, src.bitmap, src.nr_bitmap); + memset(dst.bitmap + src.nr_bitmap, 0, dst.nr_bitmap - src.nr_bitmap); /* * we do not need to zero out remainder part of dentry and filename * field, since we have used bitmap for marking the usage status of * them, besides, we can also ignore copying/zeroing reserved space * of dentry block, because them haven't been used so far. */ - memcpy(dentry_blk->dentry, inline_dentry->dentry, - sizeof(struct f2fs_dir_entry) * NR_INLINE_DENTRY); - memcpy(dentry_blk->filename, inline_dentry->filename, - NR_INLINE_DENTRY * F2FS_SLOT_LEN); + memcpy(dst.dentry, src.dentry, SIZE_OF_DIR_ENTRY * src.max); + memcpy(dst.filename, src.filename, src.max * F2FS_SLOT_LEN); kunmap_atomic(dentry_blk); if (!PageUptodate(page)) @@ -395,14 +404,13 @@ out: return err; } -static int f2fs_add_inline_entries(struct inode *dir, - struct f2fs_inline_dentry *inline_dentry) +static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) { struct f2fs_dentry_ptr d; unsigned long bit_pos = 0; int err = 0; - make_dentry_ptr_inline(NULL, &d, inline_dentry); + make_dentry_ptr_inline(dir, &d, inline_dentry); while (bit_pos < d.max) { struct f2fs_dir_entry *de; @@ -444,19 +452,19 @@ punch_dentry_pages: } static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, - struct f2fs_inline_dentry *inline_dentry) + void *inline_dentry) { - struct f2fs_inline_dentry *backup_dentry; + void *backup_dentry; int err; backup_dentry = f2fs_kmalloc(F2FS_I_SB(dir), - sizeof(struct f2fs_inline_dentry), GFP_F2FS_ZERO); + MAX_INLINE_DATA(dir), GFP_F2FS_ZERO); if (!backup_dentry) { f2fs_put_page(ipage, 1); return -ENOMEM; } - memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA); + memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA(dir)); truncate_inline_inode(dir, ipage, 0); unlock_page(ipage); @@ -473,9 +481,9 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage, return 0; recover: lock_page(ipage); - memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA); + memcpy(inline_dentry, backup_dentry, MAX_INLINE_DATA(dir)); f2fs_i_depth_write(dir, 0); - f2fs_i_size_write(dir, MAX_INLINE_DATA); + f2fs_i_size_write(dir, MAX_INLINE_DATA(dir)); set_page_dirty(ipage); f2fs_put_page(ipage, 1); @@ -484,7 +492,7 @@ recover: } static int f2fs_convert_inline_dir(struct inode *dir, struct page *ipage, - struct f2fs_inline_dentry *inline_dentry) + void *inline_dentry) { if (!F2FS_I(dir)->i_dir_level) return f2fs_move_inline_dirents(dir, ipage, inline_dentry); @@ -500,7 +508,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, struct page *ipage; unsigned int bit_pos; f2fs_hash_t name_hash; - struct f2fs_inline_dentry *dentry_blk = NULL; + void *inline_dentry = NULL; struct f2fs_dentry_ptr d; int slots = GET_DENTRY_SLOTS(new_name->len); struct page *page = NULL; @@ -510,11 +518,12 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, if (IS_ERR(ipage)) return PTR_ERR(ipage); - dentry_blk = inline_data_addr(ipage); - bit_pos = room_for_filename(&dentry_blk->dentry_bitmap, - slots, NR_INLINE_DENTRY); - if (bit_pos >= NR_INLINE_DENTRY) { - err = f2fs_convert_inline_dir(dir, ipage, dentry_blk); + inline_dentry = inline_data_addr(dir, ipage); + make_dentry_ptr_inline(dir, &d, inline_dentry); + + bit_pos = room_for_filename(d.bitmap, slots, d.max); + if (bit_pos >= d.max) { + err = f2fs_convert_inline_dir(dir, ipage, inline_dentry); if (err) return err; err = -EAGAIN; @@ -534,7 +543,6 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name, f2fs_wait_on_page_writeback(ipage, NODE, true); name_hash = f2fs_dentry_hash(new_name, NULL); - make_dentry_ptr_inline(NULL, &d, dentry_blk); f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos); set_page_dirty(ipage); @@ -557,7 +565,8 @@ out: void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode) { - struct f2fs_inline_dentry *inline_dentry; + struct f2fs_dentry_ptr d; + void *inline_dentry; int slots = GET_DENTRY_SLOTS(le16_to_cpu(dentry->name_len)); unsigned int bit_pos; int i; @@ -565,11 +574,12 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page, lock_page(page); f2fs_wait_on_page_writeback(page, NODE, true); - inline_dentry = inline_data_addr(page); - bit_pos = dentry - inline_dentry->dentry; + inline_dentry = inline_data_addr(dir, page); + make_dentry_ptr_inline(dir, &d, inline_dentry); + + bit_pos = dentry - d.dentry; for (i = 0; i < slots; i++) - __clear_bit_le(bit_pos + i, - &inline_dentry->dentry_bitmap); + __clear_bit_le(bit_pos + i, d.bitmap); set_page_dirty(page); f2fs_put_page(page, 1); @@ -586,20 +596,21 @@ bool f2fs_empty_inline_dir(struct inode *dir) struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct page *ipage; unsigned int bit_pos = 2; - struct f2fs_inline_dentry *dentry_blk; + void *inline_dentry; + struct f2fs_dentry_ptr d; ipage = get_node_page(sbi, dir->i_ino); if (IS_ERR(ipage)) return false; - dentry_blk = inline_data_addr(ipage); - bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap, - NR_INLINE_DENTRY, - bit_pos); + inline_dentry = inline_data_addr(dir, ipage); + make_dentry_ptr_inline(dir, &d, inline_dentry); + + bit_pos = find_next_bit_le(d.bitmap, d.max, bit_pos); f2fs_put_page(ipage, 1); - if (bit_pos < NR_INLINE_DENTRY) + if (bit_pos < d.max) return false; return true; @@ -609,25 +620,27 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx, struct fscrypt_str *fstr) { struct inode *inode = file_inode(file); - struct f2fs_inline_dentry *inline_dentry = NULL; struct page *ipage = NULL; struct f2fs_dentry_ptr d; + void *inline_dentry = NULL; int err; - if (ctx->pos == NR_INLINE_DENTRY) + make_dentry_ptr_inline(inode, &d, inline_dentry); + + if (ctx->pos == d.max) return 0; ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); if (IS_ERR(ipage)) return PTR_ERR(ipage); - inline_dentry = inline_data_addr(ipage); + inline_dentry = inline_data_addr(inode, ipage); make_dentry_ptr_inline(inode, &d, inline_dentry); err = f2fs_fill_dentries(ctx, &d, 0, fstr); if (!err) - ctx->pos = NR_INLINE_DENTRY; + ctx->pos = d.max; f2fs_put_page(ipage, 1); return err < 0 ? err : 0; @@ -652,7 +665,7 @@ int f2fs_inline_data_fiemap(struct inode *inode, goto out; } - ilen = min_t(size_t, MAX_INLINE_DATA, i_size_read(inode)); + ilen = min_t(size_t, MAX_INLINE_DATA(inode), i_size_read(inode)); if (start >= ilen) goto out; if (start + len < ilen) @@ -661,7 +674,8 @@ int f2fs_inline_data_fiemap(struct inode *inode, get_node_info(F2FS_I_SB(inode), inode->i_ino, &ni); byteaddr = (__u64)ni.blk_addr << inode->i_sb->s_blocksize_bits; - byteaddr += (char *)inline_data_addr(ipage) - (char *)F2FS_INODE(ipage); + byteaddr += (char *)inline_data_addr(inode, ipage) - + (char *)F2FS_INODE(ipage); err = fiemap_fill_next_extent(fieinfo, start, byteaddr, ilen, flags); out: f2fs_put_page(ipage, 1); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 518f49643092..50c88e37ed66 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -16,6 +16,7 @@ #include "f2fs.h" #include "node.h" +#include "segment.h" #include <trace/events/f2fs.h> @@ -44,25 +45,26 @@ void f2fs_set_inode_flags(struct inode *inode) new_fl |= S_DIRSYNC; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); - f2fs_mark_inode_dirty_sync(inode, false); } static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) { + int extra_size = get_extra_isize(inode); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { - if (ri->i_addr[0]) - inode->i_rdev = - old_decode_dev(le32_to_cpu(ri->i_addr[0])); + if (ri->i_addr[extra_size]) + inode->i_rdev = old_decode_dev( + le32_to_cpu(ri->i_addr[extra_size])); else - inode->i_rdev = - new_decode_dev(le32_to_cpu(ri->i_addr[1])); + inode->i_rdev = new_decode_dev( + le32_to_cpu(ri->i_addr[extra_size + 1])); } } static bool __written_first_block(struct f2fs_inode *ri) { - block_t addr = le32_to_cpu(ri->i_addr[0]); + block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]); if (addr != NEW_ADDR && addr != NULL_ADDR) return true; @@ -71,25 +73,27 @@ static bool __written_first_block(struct f2fs_inode *ri) static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) { + int extra_size = get_extra_isize(inode); + if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { - ri->i_addr[0] = + ri->i_addr[extra_size] = cpu_to_le32(old_encode_dev(inode->i_rdev)); - ri->i_addr[1] = 0; + ri->i_addr[extra_size + 1] = 0; } else { - ri->i_addr[0] = 0; - ri->i_addr[1] = + ri->i_addr[extra_size] = 0; + ri->i_addr[extra_size + 1] = cpu_to_le32(new_encode_dev(inode->i_rdev)); - ri->i_addr[2] = 0; + ri->i_addr[extra_size + 2] = 0; } } } static void __recover_inline_status(struct inode *inode, struct page *ipage) { - void *inline_data = inline_data_addr(ipage); + void *inline_data = inline_data_addr(inode, ipage); __le32 *start = inline_data; - __le32 *end = start + MAX_INLINE_DATA / sizeof(__le32); + __le32 *end = start + MAX_INLINE_DATA(inode) / sizeof(__le32); while (start < end) { if (*start++) { @@ -104,12 +108,84 @@ static void __recover_inline_status(struct inode *inode, struct page *ipage) return; } +static bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_inode *ri = &F2FS_NODE(page)->i; + int extra_isize = le32_to_cpu(ri->i_extra_isize); + + if (!f2fs_sb_has_inode_chksum(sbi->sb)) + return false; + + if (!RAW_IS_INODE(F2FS_NODE(page)) || !(ri->i_inline & F2FS_EXTRA_ATTR)) + return false; + + if (!F2FS_FITS_IN_INODE(ri, extra_isize, i_inode_checksum)) + return false; + + return true; +} + +static __u32 f2fs_inode_chksum(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_node *node = F2FS_NODE(page); + struct f2fs_inode *ri = &node->i; + __le32 ino = node->footer.ino; + __le32 gen = ri->i_generation; + __u32 chksum, chksum_seed; + __u32 dummy_cs = 0; + unsigned int offset = offsetof(struct f2fs_inode, i_inode_checksum); + unsigned int cs_size = sizeof(dummy_cs); + + chksum = f2fs_chksum(sbi, sbi->s_chksum_seed, (__u8 *)&ino, + sizeof(ino)); + chksum_seed = f2fs_chksum(sbi, chksum, (__u8 *)&gen, sizeof(gen)); + + chksum = f2fs_chksum(sbi, chksum_seed, (__u8 *)ri, offset); + chksum = f2fs_chksum(sbi, chksum, (__u8 *)&dummy_cs, cs_size); + offset += cs_size; + chksum = f2fs_chksum(sbi, chksum, (__u8 *)ri + offset, + F2FS_BLKSIZE - offset); + return chksum; +} + +bool f2fs_inode_chksum_verify(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_inode *ri; + __u32 provided, calculated; + + if (!f2fs_enable_inode_chksum(sbi, page) || + PageDirty(page) || PageWriteback(page)) + return true; + + ri = &F2FS_NODE(page)->i; + provided = le32_to_cpu(ri->i_inode_checksum); + calculated = f2fs_inode_chksum(sbi, page); + + if (provided != calculated) + f2fs_msg(sbi->sb, KERN_WARNING, + "checksum invalid, ino = %x, %x vs. %x", + ino_of_node(page), provided, calculated); + + return provided == calculated; +} + +void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page) +{ + struct f2fs_inode *ri = &F2FS_NODE(page)->i; + + if (!f2fs_enable_inode_chksum(sbi, page)) + return; + + ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page)); +} + static int do_read_inode(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct page *node_page; struct f2fs_inode *ri; + projid_t i_projid; /* Check if ino is within scope */ if (check_nid_range(sbi, inode->i_ino)) { @@ -130,7 +206,7 @@ static int do_read_inode(struct inode *inode) i_gid_write(inode, le32_to_cpu(ri->i_gid)); set_nlink(inode, le32_to_cpu(ri->i_links)); inode->i_size = le64_to_cpu(ri->i_size); - inode->i_blocks = le64_to_cpu(ri->i_blocks); + inode->i_blocks = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1); inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime); inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime); @@ -153,6 +229,9 @@ static int do_read_inode(struct inode *inode) get_inline_info(inode, ri); + fi->i_extra_isize = f2fs_has_extra_attr(inode) ? + le16_to_cpu(ri->i_extra_isize) : 0; + /* check data exist */ if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) __recover_inline_status(inode, node_page); @@ -166,6 +245,16 @@ static int do_read_inode(struct inode *inode) if (!need_inode_block_update(sbi, inode->i_ino)) fi->last_disk_size = inode->i_size; + if (fi->i_flags & FS_PROJINHERIT_FL) + set_inode_flag(inode, FI_PROJ_INHERIT); + + if (f2fs_has_extra_attr(inode) && f2fs_sb_has_project_quota(sbi->sb) && + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, i_projid)) + i_projid = (projid_t)le32_to_cpu(ri->i_projid); + else + i_projid = F2FS_DEF_PROJID; + fi->i_projid = make_kprojid(&init_user_ns, i_projid); + f2fs_put_page(node_page, 1); stat_inc_inline_xattr(inode); @@ -226,6 +315,7 @@ make_now: ret = -EIO; goto bad_inode; } + f2fs_set_inode_flags(inode); unlock_new_inode(inode); trace_f2fs_iget(inode); return inode; @@ -267,7 +357,7 @@ int update_inode(struct inode *inode, struct page *node_page) ri->i_gid = cpu_to_le32(i_gid_read(inode)); ri->i_links = cpu_to_le32(inode->i_nlink); ri->i_size = cpu_to_le64(i_size_read(inode)); - ri->i_blocks = cpu_to_le64(inode->i_blocks); + ri->i_blocks = cpu_to_le64(SECTOR_TO_BLOCK(inode->i_blocks) + 1); if (et) { read_lock(&et->lock); @@ -291,6 +381,20 @@ int update_inode(struct inode *inode, struct page *node_page) ri->i_generation = cpu_to_le32(inode->i_generation); ri->i_dir_level = F2FS_I(inode)->i_dir_level; + if (f2fs_has_extra_attr(inode)) { + ri->i_extra_isize = cpu_to_le16(F2FS_I(inode)->i_extra_isize); + + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) && + F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, + i_projid)) { + projid_t i_projid; + + i_projid = from_kprojid(&init_user_ns, + F2FS_I(inode)->i_projid); + ri->i_projid = cpu_to_le32(i_projid); + } + } + __set_inode_rdev(inode, ri); set_cold_node(inode, node_page); @@ -372,6 +476,8 @@ void f2fs_evict_inode(struct inode *inode) if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; + dquot_initialize(inode); + remove_ino_entry(sbi, inode->i_ino, APPEND_INO); remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); @@ -404,12 +510,18 @@ retry: if (err) update_inode_page(inode); + dquot_free_inode(inode); sb_end_intwrite(inode->i_sb); no_delete: + dquot_drop(inode); + stat_dec_inline_xattr(inode); stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); + if (!is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) + f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); + /* ino == 0, if f2fs_new_inode() was failed t*/ if (inode->i_ino) invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, @@ -425,9 +537,10 @@ no_delete: if (is_inode_flag_set(inode, FI_FREE_NID)) { alloc_nid_failed(sbi, inode->i_ino); clear_inode_flag(inode, FI_FREE_NID); + } else { + f2fs_bug_on(sbi, err && + !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)); } - f2fs_bug_on(sbi, err && - !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)); out_clear: fscrypt_put_encryption_info(inode, NULL); clear_inode(inode); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index c31b40e5f9cf..a4dab98c4b7b 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -15,6 +15,7 @@ #include <linux/ctype.h> #include <linux/dcache.h> #include <linux/namei.h> +#include <linux/quotaops.h> #include "f2fs.h" #include "node.h" @@ -42,6 +43,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) } f2fs_unlock_op(sbi); + nid_free = true; + inode_init_owner(inode, dir, mode); inode->i_ino = ino; @@ -52,16 +55,35 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) err = insert_inode_locked(inode); if (err) { err = -EINVAL; - nid_free = true; goto fail; } + if (f2fs_sb_has_project_quota(sbi->sb) && + (F2FS_I(dir)->i_flags & FS_PROJINHERIT_FL)) + F2FS_I(inode)->i_projid = F2FS_I(dir)->i_projid; + else + F2FS_I(inode)->i_projid = make_kprojid(&init_user_ns, + F2FS_DEF_PROJID); + + err = dquot_initialize(inode); + if (err) + goto fail_drop; + + err = dquot_alloc_inode(inode); + if (err) + goto fail_drop; + /* If the directory encrypted, then we should encrypt the inode. */ if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode)) f2fs_set_encrypted_inode(inode); set_inode_flag(inode, FI_NEW_INODE); + if (f2fs_sb_has_extra_attr(sbi->sb)) { + set_inode_flag(inode, FI_EXTRA_ATTR); + F2FS_I(inode)->i_extra_isize = F2FS_TOTAL_EXTRA_ATTR_SIZE; + } + if (test_opt(sbi, INLINE_XATTR)) set_inode_flag(inode, FI_INLINE_XATTR); if (test_opt(sbi, INLINE_DATA) && f2fs_may_inline_data(inode)) @@ -75,6 +97,15 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) stat_inc_inline_inode(inode); stat_inc_inline_dir(inode); + F2FS_I(inode)->i_flags = + f2fs_mask_flags(mode, F2FS_I(dir)->i_flags & F2FS_FL_INHERITED); + + if (S_ISDIR(inode->i_mode)) + F2FS_I(inode)->i_flags |= FS_INDEX_FL; + + if (F2FS_I(inode)->i_flags & FS_PROJINHERIT_FL) + set_inode_flag(inode, FI_PROJ_INHERIT); + trace_f2fs_new_inode(inode, 0); return inode; @@ -85,6 +116,16 @@ fail: set_inode_flag(inode, FI_FREE_NID); iput(inode); return ERR_PTR(err); +fail_drop: + trace_f2fs_new_inode(inode, err); + dquot_drop(inode); + inode->i_flags |= S_NOQUOTA; + if (nid_free) + set_inode_flag(inode, FI_FREE_NID); + clear_nlink(inode); + unlock_new_inode(inode); + iput(inode); + return ERR_PTR(err); } static int is_multimedia_file(const unsigned char *s, const char *sub) @@ -136,6 +177,10 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, nid_t ino = 0; int err; + err = dquot_initialize(dir); + if (err) + return err; + inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -180,6 +225,15 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, !fscrypt_has_permitted_context(dir, inode)) return -EPERM; + if (is_inode_flag_set(dir, FI_PROJ_INHERIT) && + (!projid_eq(F2FS_I(dir)->i_projid, + F2FS_I(old_dentry->d_inode)->i_projid))) + return -EXDEV; + + err = dquot_initialize(dir); + if (err) + return err; + f2fs_balance_fs(sbi, true); inode->i_ctime = current_time(inode); @@ -233,6 +287,10 @@ static int __recover_dot_dentries(struct inode *dir, nid_t pino) return 0; } + err = dquot_initialize(dir); + if (err) + return err; + f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); @@ -347,6 +405,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) trace_f2fs_unlink_enter(dir, dentry); + err = dquot_initialize(dir); + if (err) + return err; + de = f2fs_find_entry(dir, &dentry->d_name, &page); if (!de) { if (IS_ERR(page)) @@ -413,6 +475,10 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (disk_link.len > dir->i_sb->s_blocksize) return -ENAMETOOLONG; + err = dquot_initialize(dir); + if (err) + return err; + inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -500,6 +566,10 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct inode *inode; int err; + err = dquot_initialize(dir); + if (err) + return err; + inode = f2fs_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -548,6 +618,10 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, struct inode *inode; int err = 0; + err = dquot_initialize(dir); + if (err) + return err; + inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -583,6 +657,10 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry, struct inode *inode; int err; + err = dquot_initialize(dir); + if (err) + return err; + inode = f2fs_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); @@ -676,6 +754,19 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } + if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && + (!projid_eq(F2FS_I(new_dir)->i_projid, + F2FS_I(old_dentry->d_inode)->i_projid))) + return -EXDEV; + + err = dquot_initialize(old_dir); + if (err) + goto out; + + err = dquot_initialize(new_dir); + if (err) + goto out; + old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -772,7 +863,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } down_write(&F2FS_I(old_inode)->i_sem); - file_lost_pino(old_inode); + if (!old_dir_entry || whiteout) + file_lost_pino(old_inode); + else + F2FS_I(old_inode)->i_pino = new_dir->i_ino; up_write(&F2FS_I(old_inode)->i_sem); old_inode->i_ctime = current_time(old_inode); @@ -853,6 +947,22 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, !fscrypt_has_permitted_context(old_dir, new_inode))) return -EPERM; + if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && + !projid_eq(F2FS_I(new_dir)->i_projid, + F2FS_I(old_dentry->d_inode)->i_projid)) || + (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && + !projid_eq(F2FS_I(old_dir)->i_projid, + F2FS_I(new_dentry->d_inode)->i_projid))) + return -EXDEV; + + err = dquot_initialize(old_dir); + if (err) + goto out; + + err = dquot_initialize(new_dir); + if (err) + goto out; + old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 4547c5c5cd98..fca87835a1da 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -19,6 +19,7 @@ #include "f2fs.h" #include "node.h" #include "segment.h" +#include "xattr.h" #include "trace.h" #include <trace/events/f2fs.h> @@ -158,9 +159,6 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); struct nat_entry_set *head; - if (get_nat_flag(ne, IS_DIRTY)) - return; - head = radix_tree_lookup(&nm_i->nat_set_root, set); if (!head) { head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS); @@ -171,10 +169,18 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, head->entry_cnt = 0; f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } - list_move_tail(&ne->list, &head->entry_list); + + if (get_nat_flag(ne, IS_DIRTY)) + goto refresh_list; + nm_i->dirty_nat_cnt++; head->entry_cnt++; set_nat_flag(ne, IS_DIRTY, true); +refresh_list: + if (nat_get_blkaddr(ne) == NEW_ADDR) + list_del_init(&ne->list); + else + list_move_tail(&ne->list, &head->entry_list); } static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, @@ -549,7 +555,7 @@ static int get_node_path(struct inode *inode, long block, level = 3; goto got; } else { - BUG(); + return -E2BIG; } got: return level; @@ -573,6 +579,8 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) int err = 0; level = get_node_path(dn->inode, index, offset, noffset); + if (level < 0) + return level; nids[0] = dn->inode->i_ino; npage[0] = dn->inode_page; @@ -608,7 +616,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) } dn->nid = nids[i]; - npage[i] = new_node_page(dn, noffset[i], NULL); + npage[i] = new_node_page(dn, noffset[i]); if (IS_ERR(npage[i])) { alloc_nid_failed(sbi, nids[i]); err = PTR_ERR(npage[i]); @@ -649,7 +657,8 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) dn->nid = nids[level]; dn->ofs_in_node = offset[level]; dn->node_page = npage[level]; - dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node); + dn->data_blkaddr = datablock_addr(dn->inode, + dn->node_page, dn->ofs_in_node); return 0; release_pages: @@ -673,15 +682,11 @@ static void truncate_node(struct dnode_of_data *dn) struct node_info ni; get_node_info(sbi, dn->nid, &ni); - if (dn->inode->i_blocks == 0) { - f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR); - goto invalidate; - } f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); /* Deallocate node address */ invalidate_blocks(sbi, ni.blk_addr); - dec_valid_node_count(sbi, dn->inode); + dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); set_node_addr(sbi, &ni, NULL_ADDR, false); if (dn->nid == dn->inode->i_ino) { @@ -689,7 +694,7 @@ static void truncate_node(struct dnode_of_data *dn) dec_valid_inode_count(sbi); f2fs_inode_synced(dn->inode); } -invalidate: + clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); @@ -875,6 +880,8 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from) trace_f2fs_truncate_inode_blocks_enter(inode, from); level = get_node_path(inode, from, offset, noffset); + if (level < 0) + return level; page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { @@ -1006,7 +1013,7 @@ int remove_inode_page(struct inode *inode) /* 0 is possible, after f2fs_new_inode() has failed */ f2fs_bug_on(F2FS_I_SB(inode), - inode->i_blocks != 0 && inode->i_blocks != 1); + inode->i_blocks != 0 && inode->i_blocks != 8); /* will put inode & node pages */ truncate_node(&dn); @@ -1021,11 +1028,10 @@ struct page *new_inode_page(struct inode *inode) set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); /* caller should f2fs_put_page(page, 1); */ - return new_node_page(&dn, 0, NULL); + return new_node_page(&dn, 0); } -struct page *new_node_page(struct dnode_of_data *dn, - unsigned int ofs, struct page *ipage) +struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info new_ni; @@ -1039,10 +1045,9 @@ struct page *new_node_page(struct dnode_of_data *dn, if (!page) return ERR_PTR(-ENOMEM); - if (unlikely(!inc_valid_node_count(sbi, dn->inode))) { - err = -ENOSPC; + if (unlikely((err = inc_valid_node_count(sbi, dn->inode, !ofs)))) goto fail; - } + #ifdef CONFIG_F2FS_CHECK_FS get_node_info(sbi, dn->nid, &new_ni); f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); @@ -1152,6 +1157,7 @@ repeat: f2fs_put_page(page, 1); return ERR_PTR(err); } else if (err == LOCKED_PAGE) { + err = 0; goto page_hit; } @@ -1165,15 +1171,27 @@ repeat: goto repeat; } - if (unlikely(!PageUptodate(page))) + if (unlikely(!PageUptodate(page))) { + err = -EIO; goto out_err; + } + + if (!f2fs_inode_chksum_verify(sbi, page)) { + err = -EBADMSG; + goto out_err; + } page_hit: if(unlikely(nid != nid_of_node(page))) { - f2fs_bug_on(sbi, 1); - ClearPageUptodate(page); + f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, " + "nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", + nid, nid_of_node(page), ino_of_node(page), + ofs_of_node(page), cpver_of_node(page), + next_blkaddr_of_node(page)); + err = -EINVAL; out_err: + ClearPageUptodate(page); f2fs_put_page(page, 1); - return ERR_PTR(-EIO); + return ERR_PTR(err); } return page; } @@ -1318,7 +1336,8 @@ continue_unlock: } static int __write_node_page(struct page *page, bool atomic, bool *submitted, - struct writeback_control *wbc) + struct writeback_control *wbc, bool do_balance, + enum iostat_type io_type) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); nid_t nid; @@ -1331,6 +1350,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, .page = page, .encrypted_page = NULL, .submitted = false, + .io_type = io_type, }; trace_f2fs_writepage(page, NODE); @@ -1373,20 +1393,22 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, up_read(&sbi->node_write); if (wbc->for_reclaim) { - f2fs_submit_merged_bio_cond(sbi, page->mapping->host, 0, - page->index, NODE, WRITE); + f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0, + page->index, NODE); submitted = NULL; } unlock_page(page); if (unlikely(f2fs_cp_error(sbi))) { - f2fs_submit_merged_bio(sbi, NODE, WRITE); + f2fs_submit_merged_write(sbi, NODE); submitted = NULL; } if (submitted) *submitted = fio.submitted; + if (do_balance) + f2fs_balance_fs(sbi, false); return 0; redirty_out: @@ -1397,7 +1419,7 @@ redirty_out: static int f2fs_write_node_page(struct page *page, struct writeback_control *wbc) { - return __write_node_page(page, false, NULL, wbc); + return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO); } int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, @@ -1485,7 +1507,8 @@ continue_unlock: ret = __write_node_page(page, atomic && page == last_page, - &submitted, wbc); + &submitted, wbc, true, + FS_NODE_IO); if (ret) { unlock_page(page); f2fs_put_page(last_page, 0); @@ -1518,12 +1541,12 @@ continue_unlock: } out: if (last_idx != ULONG_MAX) - f2fs_submit_merged_bio_cond(sbi, NULL, ino, last_idx, - NODE, WRITE); + f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); return ret ? -EIO: 0; } -int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc) +int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, + bool do_balance, enum iostat_type io_type) { pgoff_t index, end; struct pagevec pvec; @@ -1601,7 +1624,8 @@ continue_unlock: set_fsync_mark(page, 0); set_dentry_mark(page, 0); - ret = __write_node_page(page, false, &submitted, wbc); + ret = __write_node_page(page, false, &submitted, + wbc, do_balance, io_type); if (ret) unlock_page(page); else if (submitted) @@ -1625,7 +1649,7 @@ continue_unlock: } out: if (nwritten) - f2fs_submit_merged_bio(sbi, NODE, WRITE); + f2fs_submit_merged_write(sbi, NODE); return ret; } @@ -1675,6 +1699,9 @@ static int f2fs_write_node_pages(struct address_space *mapping, struct blk_plug plug; long diff; + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + goto skip_write; + /* balancing f2fs's metadata in background */ f2fs_balance_fs_bg(sbi); @@ -1687,7 +1714,7 @@ static int f2fs_write_node_pages(struct address_space *mapping, diff = nr_pages_to_write(sbi, NODE, wbc); wbc->sync_mode = WB_SYNC_NONE; blk_start_plug(&plug); - sync_node_pages(sbi, wbc); + sync_node_pages(sbi, wbc, true, FS_NODE_IO); blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); return 0; @@ -2181,7 +2208,8 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid; - nid_t new_xnid = nid_of_node(page); + nid_t new_xnid; + struct dnode_of_data dn; struct node_info ni; struct page *xpage; @@ -2192,27 +2220,27 @@ int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) get_node_info(sbi, prev_xnid, &ni); f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); invalidate_blocks(sbi, ni.blk_addr); - dec_valid_node_count(sbi, inode); + dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: /* 2: update xattr nid in inode */ - remove_free_nid(sbi, new_xnid); - f2fs_i_xnid_write(inode, new_xnid); - if (unlikely(!inc_valid_node_count(sbi, inode))) - f2fs_bug_on(sbi, 1); + if (!alloc_nid(sbi, &new_xnid)) + return -ENOSPC; + + set_new_dnode(&dn, inode, NULL, NULL, new_xnid); + xpage = new_node_page(&dn, XATTR_NODE_OFFSET); + if (IS_ERR(xpage)) { + alloc_nid_failed(sbi, new_xnid); + return PTR_ERR(xpage); + } + + alloc_nid_done(sbi, new_xnid); update_inode_page(inode); /* 3: update and set xattr node page dirty */ - xpage = grab_cache_page(NODE_MAPPING(sbi), new_xnid); - if (!xpage) - return -ENOMEM; + memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); - memcpy(F2FS_NODE(xpage), F2FS_NODE(page), PAGE_SIZE); - - get_node_info(sbi, new_xnid, &ni); - ni.ino = inode->i_ino; - set_node_addr(sbi, &ni, NEW_ADDR, false); set_page_dirty(xpage); f2fs_put_page(xpage, 1); @@ -2252,12 +2280,19 @@ retry: dst->i_blocks = cpu_to_le64(1); dst->i_links = cpu_to_le32(1); dst->i_xattr_nid = 0; - dst->i_inline = src->i_inline & F2FS_INLINE_XATTR; + dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR); + if (dst->i_inline & F2FS_EXTRA_ATTR) { + dst->i_extra_isize = src->i_extra_isize; + if (f2fs_sb_has_project_quota(sbi->sb) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_projid)) + dst->i_projid = src->i_projid; + } new_ni = old_ni; new_ni.ino = ino; - if (unlikely(!inc_valid_node_count(sbi, NULL))) + if (unlikely(inc_valid_node_count(sbi, NULL, true))) WARN_ON(1); set_node_addr(sbi, &new_ni, NEW_ADDR, false); inc_valid_inode_count(sbi); @@ -2424,8 +2459,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, nid_t nid = nat_get_nid(ne); int offset; - if (nat_get_blkaddr(ne) == NEW_ADDR) - continue; + f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { offset = lookup_journal_in_cursum(journal, @@ -2553,7 +2587,7 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) return 0; } -inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) +static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int i = 0; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 558048e33cf9..bb53e9955ff2 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -224,11 +224,7 @@ static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi, struct f2fs_nm_info *nm_i = NM_I(sbi); block_addr -= nm_i->nat_blkaddr; - if ((block_addr >> sbi->log_blocks_per_seg) % 2) - block_addr -= sbi->blocks_per_seg; - else - block_addr += sbi->blocks_per_seg; - + block_addr ^= 1 << sbi->log_blocks_per_seg; return block_addr + nm_i->nat_blkaddr; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 907d6b7dde6a..9626758bc762 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -69,20 +69,34 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head, } static struct fsync_inode_entry *add_fsync_inode(struct f2fs_sb_info *sbi, - struct list_head *head, nid_t ino) + struct list_head *head, nid_t ino, bool quota_inode) { struct inode *inode; struct fsync_inode_entry *entry; + int err; inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) return ERR_CAST(inode); + err = dquot_initialize(inode); + if (err) + goto err_out; + + if (quota_inode) { + err = dquot_alloc_inode(inode); + if (err) + goto err_out; + } + entry = f2fs_kmem_cache_alloc(fsync_entry_slab, GFP_F2FS_ZERO); entry->inode = inode; list_add_tail(&entry->list, head); return entry; +err_out: + iput(inode); + return ERR_PTR(err); } static void del_fsync_inode(struct fsync_inode_entry *entry) @@ -107,7 +121,8 @@ static int recover_dentry(struct inode *inode, struct page *ipage, entry = get_fsync_inode(dir_list, pino); if (!entry) { - entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, pino); + entry = add_fsync_inode(F2FS_I_SB(inode), dir_list, + pino, false); if (IS_ERR(entry)) { dir = ERR_CAST(entry); err = PTR_ERR(entry); @@ -140,6 +155,13 @@ retry: err = -EEXIST; goto out_unmap_put; } + + err = dquot_initialize(einode); + if (err) { + iput(einode); + goto out_unmap_put; + } + err = acquire_orphan_inode(F2FS_I_SB(inode)); if (err) { iput(einode); @@ -226,18 +248,22 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, entry = get_fsync_inode(head, ino_of_node(page)); if (!entry) { + bool quota_inode = false; + if (!check_only && IS_INODE(page) && is_dent_dnode(page)) { err = recover_inode_page(sbi, page); if (err) break; + quota_inode = true; } /* * CP | dnode(F) | inode(DF) * For this case, we should not give up now. */ - entry = add_fsync_inode(sbi, head, ino_of_node(page)); + entry = add_fsync_inode(sbi, head, ino_of_node(page), + quota_inode); if (IS_ERR(entry)) { err = PTR_ERR(entry); if (err == -ENOENT) { @@ -291,7 +317,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, return 0; /* Get the previous summary */ - for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) { + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { struct curseg_info *curseg = CURSEG_I(sbi, i); if (curseg->segno == segno) { sum = curseg->sum_blk->entries[blkoff]; @@ -328,10 +354,18 @@ got_it: f2fs_put_page(node_page, 1); if (ino != dn->inode->i_ino) { + int ret; + /* Deallocate previous index in the node page */ inode = f2fs_iget_retry(sbi->sb, ino); if (IS_ERR(inode)) return PTR_ERR(inode); + + ret = dquot_initialize(inode); + if (ret) { + iput(inode); + return ret; + } } else { inode = dn->inode; } @@ -361,7 +395,8 @@ out: return 0; truncate_out: - if (datablock_addr(tdn.node_page, tdn.ofs_in_node) == blkaddr) + if (datablock_addr(tdn.inode, tdn.node_page, + tdn.ofs_in_node) == blkaddr) truncate_data_blocks_range(&tdn, 1); if (dn->inode->i_ino == nid && !dn->inode_page_locked) unlock_page(dn->inode_page); @@ -414,8 +449,8 @@ retry_dn: for (; start < end; start++, dn.ofs_in_node++) { block_t src, dest; - src = datablock_addr(dn.node_page, dn.ofs_in_node); - dest = datablock_addr(page, dn.ofs_in_node); + src = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); + dest = datablock_addr(dn.inode, page, dn.ofs_in_node); /* skip recovering if dest is the same as src */ if (src == dest) @@ -557,12 +592,27 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) struct list_head dir_list; int err; int ret = 0; + unsigned long s_flags = sbi->sb->s_flags; bool need_writecp = false; + if (s_flags & MS_RDONLY) { + f2fs_msg(sbi->sb, KERN_INFO, "orphan cleanup on readonly fs"); + sbi->sb->s_flags &= ~MS_RDONLY; + } + +#ifdef CONFIG_QUOTA + /* Needed for iput() to work correctly and not trash data */ + sbi->sb->s_flags |= MS_ACTIVE; + /* Turn on quotas so that they are updated correctly */ + f2fs_enable_quota_files(sbi); +#endif + fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry", sizeof(struct fsync_inode_entry)); - if (!fsync_entry_slab) - return -ENOMEM; + if (!fsync_entry_slab) { + err = -ENOMEM; + goto out; + } INIT_LIST_HEAD(&inode_list); INIT_LIST_HEAD(&dir_list); @@ -573,11 +623,11 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) /* step #1: find fsynced inode numbers */ err = find_fsync_dnodes(sbi, &inode_list, check_only); if (err || list_empty(&inode_list)) - goto out; + goto skip; if (check_only) { ret = 1; - goto out; + goto skip; } need_writecp = true; @@ -586,7 +636,7 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) err = recover_data(sbi, &inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); -out: +skip: destroy_fsync_dnodes(&inode_list); /* truncate meta pages to be used by the recovery */ @@ -599,8 +649,6 @@ out: } clear_sbi_flag(sbi, SBI_POR_DOING); - if (err) - set_ckpt_flags(sbi, CP_ERROR_FLAG); mutex_unlock(&sbi->cp_mutex); /* let's drop all the directory inodes for clean checkpoint */ @@ -614,5 +662,12 @@ out: } kmem_cache_destroy(fsync_entry_slab); +out: +#ifdef CONFIG_QUOTA + /* Turn quotas off */ + f2fs_quota_off_umount(sbi->sb); +#endif + sbi->sb->s_flags = s_flags; /* Restore MS_RDONLY status */ + return ret ? ret: err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 96845854e7ee..c695ff462ee6 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -16,10 +16,13 @@ #include <linux/kthread.h> #include <linux/swap.h> #include <linux/timer.h> +#include <linux/freezer.h> +#include <linux/sched/signal.h> #include "f2fs.h" #include "segment.h" #include "node.h" +#include "gc.h" #include "trace.h" #include <trace/events/f2fs.h> @@ -166,6 +169,21 @@ found: return result - size + __reverse_ffz(tmp); } +bool need_SSR(struct f2fs_sb_info *sbi) +{ + int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); + int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); + int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); + + if (test_opt(sbi, LFS)) + return false; + if (sbi->gc_thread && sbi->gc_thread->gc_urgent) + return true; + + return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + + 2 * reserved_sections(sbi)); +} + void register_inmem_page(struct inode *inode, struct page *page) { struct f2fs_inode_info *fi = F2FS_I(inode); @@ -212,9 +230,15 @@ static int __revoke_inmem_pages(struct inode *inode, struct node_info ni; trace_f2fs_commit_inmem_page(page, INMEM_REVOKE); - +retry: set_new_dnode(&dn, inode, NULL, NULL, 0); - if (get_dnode_of_data(&dn, page->index, LOOKUP_NODE)) { + err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE); + if (err) { + if (err == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + goto retry; + } err = -EAGAIN; goto next; } @@ -247,6 +271,7 @@ void drop_inmem_pages(struct inode *inode) mutex_unlock(&fi->inmem_lock); clear_inode_flag(inode, FI_ATOMIC_FILE); + clear_inode_flag(inode, FI_HOT_DATA); stat_dec_atomic_write(inode); } @@ -291,6 +316,7 @@ static int __commit_inmem_pages(struct inode *inode, .type = DATA, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC | REQ_PRIO, + .io_type = FS_DATA_IO, }; pgoff_t last_idx = ULONG_MAX; int err = 0; @@ -308,17 +334,21 @@ static int __commit_inmem_pages(struct inode *inode, inode_dec_dirty_pages(inode); remove_dirty_inode(inode); } - +retry: fio.page = page; fio.old_blkaddr = NULL_ADDR; fio.encrypted_page = NULL; - fio.need_lock = false, + fio.need_lock = LOCK_DONE; err = do_write_data_page(&fio); if (err) { + if (err == -ENOMEM) { + congestion_wait(BLK_RW_ASYNC, HZ/50); + cond_resched(); + goto retry; + } unlock_page(page); break; } - /* record old blkaddr for revoking */ cur->old_addr = fio.old_blkaddr; last_idx = page->index; @@ -328,8 +358,7 @@ static int __commit_inmem_pages(struct inode *inode, } if (last_idx != ULONG_MAX) - f2fs_submit_merged_bio_cond(sbi, inode, 0, last_idx, - DATA, WRITE); + f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA); if (!err) __revoke_inmem_pages(inode, revoke_list, false, false); @@ -447,7 +476,7 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi, int ret; bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); ret = submit_bio_wait(bio); bio_put(bio); @@ -481,6 +510,8 @@ repeat: if (kthread_should_stop()) return 0; + sb_start_intwrite(sbi->sb); + if (!llist_empty(&fcc->issue_list)) { struct flush_cmd *cmd, *next; int ret; @@ -499,6 +530,8 @@ repeat: fcc->dispatch_list = NULL; } + sb_end_intwrite(sbi->sb); + wait_event_interruptible(*q, kthread_should_stop() || !llist_empty(&fcc->issue_list)); goto repeat; @@ -519,8 +552,7 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) return ret; } - if (!atomic_read(&fcc->issing_flush)) { - atomic_inc(&fcc->issing_flush); + if (atomic_inc_return(&fcc->issing_flush) == 1) { ret = submit_flush_wait(sbi); atomic_dec(&fcc->issing_flush); @@ -530,18 +562,39 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi) init_completion(&cmd.wait); - atomic_inc(&fcc->issing_flush); llist_add(&cmd.llnode, &fcc->issue_list); - if (!fcc->dispatch_list) + /* update issue_list before we wake up issue_flush thread */ + smp_mb(); + + if (waitqueue_active(&fcc->flush_wait_queue)) wake_up(&fcc->flush_wait_queue); if (fcc->f2fs_issue_flush) { wait_for_completion(&cmd.wait); atomic_dec(&fcc->issing_flush); } else { - llist_del_all(&fcc->issue_list); - atomic_set(&fcc->issing_flush, 0); + struct llist_node *list; + + list = llist_del_all(&fcc->issue_list); + if (!list) { + wait_for_completion(&cmd.wait); + atomic_dec(&fcc->issing_flush); + } else { + struct flush_cmd *tmp, *next; + + ret = submit_flush_wait(sbi); + + llist_for_each_entry_safe(tmp, next, list, llnode) { + if (tmp == &cmd) { + cmd.ret = ret; + atomic_dec(&fcc->issing_flush); + continue; + } + tmp->ret = ret; + complete(&tmp->wait); + } + } } return cmd.ret; @@ -555,6 +608,8 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) if (SM_I(sbi)->fcc_info) { fcc = SM_I(sbi)->fcc_info; + if (fcc->f2fs_issue_flush) + return err; goto init_thread; } @@ -566,6 +621,9 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) init_waitqueue_head(&fcc->flush_wait_queue); init_llist_head(&fcc->issue_list); SM_I(sbi)->fcc_info = fcc; + if (!test_opt(sbi, FLUSH_MERGE)) + return err; + init_thread: fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi, "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); @@ -736,12 +794,15 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + f2fs_bug_on(sbi, dc->ref); + if (dc->error == -EOPNOTSUPP) dc->error = 0; if (dc->error) f2fs_msg(sbi->sb, KERN_INFO, - "Issue discard failed, ret: %d", dc->error); + "Issue discard(%u, %u, %u) failed, ret: %d", + dc->lstart, dc->start, dc->len, dc->error); __detach_discard_cmd(dcc, dc); } @@ -749,12 +810,39 @@ static void f2fs_submit_discard_endio(struct bio *bio) { struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private; - dc->error = bio->bi_error; + dc->error = blk_status_to_errno(bio->bi_status); dc->state = D_DONE; - complete(&dc->wait); + complete_all(&dc->wait); bio_put(bio); } +void __check_sit_bitmap(struct f2fs_sb_info *sbi, + block_t start, block_t end) +{ +#ifdef CONFIG_F2FS_CHECK_FS + struct seg_entry *sentry; + unsigned int segno; + block_t blk = start; + unsigned long offset, size, max_blocks = sbi->blocks_per_seg; + unsigned long *map; + + while (blk < end) { + segno = GET_SEGNO(sbi, blk); + sentry = get_seg_entry(sbi, segno); + offset = GET_BLKOFF_FROM_SEG0(sbi, blk); + + if (end < START_BLOCK(sbi, segno + 1)) + size = GET_BLKOFF_FROM_SEG0(sbi, end); + else + size = max_blocks; + map = (unsigned long *)(sentry->cur_valid_map); + offset = __find_rev_next_bit(map, size, offset); + f2fs_bug_on(sbi, offset != size); + blk = START_BLOCK(sbi, segno + 1); + } +#endif +} + /* this function is copied from blkdev_issue_discard from block/blk-lib.c */ static void __submit_discard_cmd(struct f2fs_sb_info *sbi, struct discard_cmd *dc) @@ -782,6 +870,9 @@ static void __submit_discard_cmd(struct f2fs_sb_info *sbi, bio->bi_opf |= REQ_SYNC; submit_bio(bio); list_move_tail(&dc->list, &dcc->wait_list); + __check_sit_bitmap(sbi, dc->start, dc->start + dc->len); + + f2fs_update_iostat(sbi, FS_DISCARD, 1); } } else { __remove_discard_cmd(sbi, dc); @@ -838,7 +929,6 @@ static void __punch_discard_cmd(struct f2fs_sb_info *sbi, dc->len = blkaddr - dc->lstart; dcc->undiscard_blks += dc->len; __relocate_discard_cmd(dcc, dc); - f2fs_bug_on(sbi, !__check_rb_tree_consistence(sbi, &dcc->root)); modified = true; } @@ -848,16 +938,12 @@ static void __punch_discard_cmd(struct f2fs_sb_info *sbi, di.start + blkaddr + 1 - di.lstart, di.lstart + di.len - 1 - blkaddr, NULL, NULL); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); } else { dc->lstart++; dc->len--; dc->start++; dcc->undiscard_blks += dc->len; __relocate_discard_cmd(dcc, dc); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); } } } @@ -918,8 +1004,6 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, prev_dc->di.len += di.len; dcc->undiscard_blks += di.len; __relocate_discard_cmd(dcc, prev_dc); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); di = prev_dc->di; tdc = prev_dc; merged = true; @@ -935,16 +1019,12 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, __relocate_discard_cmd(dcc, next_dc); if (tdc) __remove_discard_cmd(sbi, tdc); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); merged = true; } if (!merged) { __insert_discard_tree(sbi, bdev, di.lstart, di.start, di.len, NULL, NULL); - f2fs_bug_on(sbi, - !__check_rb_tree_consistence(sbi, &dcc->root)); } next: prev_dc = next_dc; @@ -974,30 +1054,95 @@ static int __queue_discard_cmd(struct f2fs_sb_info *sbi, return 0; } -static void __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond) +static int __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond) { struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *pend_list; struct discard_cmd *dc, *tmp; struct blk_plug plug; - int i, iter = 0; + int iter = 0, issued = 0; + int i; + bool io_interrupted = false; mutex_lock(&dcc->cmd_lock); + f2fs_bug_on(sbi, + !__check_rb_tree_consistence(sbi, &dcc->root)); blk_start_plug(&plug); - for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + for (i = MAX_PLIST_NUM - 1; + i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) { pend_list = &dcc->pend_list[i]; list_for_each_entry_safe(dc, tmp, pend_list, list) { f2fs_bug_on(sbi, dc->state != D_PREP); - if (!issue_cond || is_idle(sbi)) + /* Hurry up to finish fstrim */ + if (dcc->pend_list_tag[i] & P_TRIM) { __submit_discard_cmd(sbi, dc); - if (issue_cond && iter++ > DISCARD_ISSUE_RATE) + issued++; + + if (fatal_signal_pending(current)) + break; + continue; + } + + if (!issue_cond) { + __submit_discard_cmd(sbi, dc); + issued++; + continue; + } + + if (is_idle(sbi)) { + __submit_discard_cmd(sbi, dc); + issued++; + } else { + io_interrupted = true; + } + + if (++iter >= DISCARD_ISSUE_RATE) goto out; } + if (list_empty(pend_list) && dcc->pend_list_tag[i] & P_TRIM) + dcc->pend_list_tag[i] &= (~P_TRIM); } out: blk_finish_plug(&plug); mutex_unlock(&dcc->cmd_lock); + + if (!issued && io_interrupted) + issued = -1; + + return issued; +} + +static void __drop_discard_cmd(struct f2fs_sb_info *sbi) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct list_head *pend_list; + struct discard_cmd *dc, *tmp; + int i; + + mutex_lock(&dcc->cmd_lock); + for (i = MAX_PLIST_NUM - 1; i >= 0; i--) { + pend_list = &dcc->pend_list[i]; + list_for_each_entry_safe(dc, tmp, pend_list, list) { + f2fs_bug_on(sbi, dc->state != D_PREP); + __remove_discard_cmd(sbi, dc); + } + } + mutex_unlock(&dcc->cmd_lock); +} + +static void __wait_one_discard_bio(struct f2fs_sb_info *sbi, + struct discard_cmd *dc) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + + wait_for_completion_io(&dc->wait); + mutex_lock(&dcc->cmd_lock); + f2fs_bug_on(sbi, dc->state != D_DONE); + dc->ref--; + if (!dc->ref) + __remove_discard_cmd(sbi, dc); + mutex_unlock(&dcc->cmd_lock); } static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond) @@ -1005,17 +1150,28 @@ static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond) struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; struct list_head *wait_list = &(dcc->wait_list); struct discard_cmd *dc, *tmp; + bool need_wait; + +next: + need_wait = false; mutex_lock(&dcc->cmd_lock); list_for_each_entry_safe(dc, tmp, wait_list, list) { - if (!wait_cond || dc->state == D_DONE) { - if (dc->ref) - continue; + if (!wait_cond || (dc->state == D_DONE && !dc->ref)) { wait_for_completion_io(&dc->wait); __remove_discard_cmd(sbi, dc); + } else { + dc->ref++; + need_wait = true; + break; } } mutex_unlock(&dcc->cmd_lock); + + if (need_wait) { + __wait_one_discard_bio(sbi, dc); + goto next; + } } /* This should be covered by global mutex, &sit_i->sentry_lock */ @@ -1037,22 +1193,39 @@ void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) } mutex_unlock(&dcc->cmd_lock); - if (need_wait) { - wait_for_completion_io(&dc->wait); - mutex_lock(&dcc->cmd_lock); - f2fs_bug_on(sbi, dc->state != D_DONE); - dc->ref--; - if (!dc->ref) - __remove_discard_cmd(sbi, dc); - mutex_unlock(&dcc->cmd_lock); + if (need_wait) + __wait_one_discard_bio(sbi, dc); +} + +void stop_discard_thread(struct f2fs_sb_info *sbi) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + + if (dcc && dcc->f2fs_issue_discard) { + struct task_struct *discard_thread = dcc->f2fs_issue_discard; + + dcc->f2fs_issue_discard = NULL; + kthread_stop(discard_thread); } } -/* This comes from f2fs_put_super */ -void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi) +/* This comes from f2fs_put_super and f2fs_trim_fs */ +void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi, bool umount) { __issue_discard_cmd(sbi, false); - __wait_discard_cmd(sbi, false); + __drop_discard_cmd(sbi); + __wait_discard_cmd(sbi, !umount); +} + +static void mark_discard_range_all(struct f2fs_sb_info *sbi) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + int i; + + mutex_lock(&dcc->cmd_lock); + for (i = 0; i < MAX_PLIST_NUM; i++) + dcc->pend_list_tag[i] |= P_TRIM; + mutex_unlock(&dcc->cmd_lock); } static int issue_discard_thread(void *data) @@ -1060,18 +1233,41 @@ static int issue_discard_thread(void *data) struct f2fs_sb_info *sbi = data; struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; wait_queue_head_t *q = &dcc->discard_wait_queue; -repeat: - if (kthread_should_stop()) - return 0; + unsigned int wait_ms = DEF_MIN_DISCARD_ISSUE_TIME; + int issued; - __issue_discard_cmd(sbi, true); - __wait_discard_cmd(sbi, true); + set_freezable(); - congestion_wait(BLK_RW_SYNC, HZ/50); + do { + wait_event_interruptible_timeout(*q, + kthread_should_stop() || freezing(current) || + dcc->discard_wake, + msecs_to_jiffies(wait_ms)); + if (try_to_freeze()) + continue; + if (kthread_should_stop()) + return 0; - wait_event_interruptible(*q, kthread_should_stop() || - atomic_read(&dcc->discard_cmd_cnt)); - goto repeat; + if (dcc->discard_wake) { + dcc->discard_wake = 0; + if (sbi->gc_thread && sbi->gc_thread->gc_urgent) + mark_discard_range_all(sbi); + } + + sb_start_intwrite(sbi->sb); + + issued = __issue_discard_cmd(sbi, true); + if (issued) { + __wait_discard_cmd(sbi, true); + wait_ms = DEF_MIN_DISCARD_ISSUE_TIME; + } else { + wait_ms = DEF_MAX_DISCARD_ISSUE_TIME; + } + + sb_end_intwrite(sbi->sb); + + } while (!kthread_should_stop()); + return 0; } #ifdef CONFIG_BLK_DEV_ZONED @@ -1260,7 +1456,8 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi) void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc) { - struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list); + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct list_head *head = &dcc->entry_list; struct discard_entry *entry, *this; struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned long *prefree_map = dirty_i->dirty_segmap[PRE]; @@ -1322,7 +1519,8 @@ find_next: sbi->blocks_per_seg, cur_pos); len = next_pos - cur_pos; - if (force && len < cpc->trim_minlen) + if (f2fs_sb_mounted_blkzoned(sbi->sb) || + (force && len < cpc->trim_minlen)) goto skip; f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos, @@ -1341,11 +1539,11 @@ skip: goto find_next; list_del(&entry->list); - SM_I(sbi)->dcc_info->nr_discards -= total_len; + dcc->nr_discards -= total_len; kmem_cache_free(discard_entry_slab, entry); } - wake_up(&SM_I(sbi)->dcc_info->discard_wait_queue); + wake_up_discard_thread(sbi, false); } static int create_discard_cmd_control(struct f2fs_sb_info *sbi) @@ -1363,9 +1561,13 @@ static int create_discard_cmd_control(struct f2fs_sb_info *sbi) if (!dcc) return -ENOMEM; + dcc->discard_granularity = DEFAULT_DISCARD_GRANULARITY; INIT_LIST_HEAD(&dcc->entry_list); - for (i = 0; i < MAX_PLIST_NUM; i++) + for (i = 0; i < MAX_PLIST_NUM; i++) { INIT_LIST_HEAD(&dcc->pend_list[i]); + if (i >= dcc->discard_granularity - 1) + dcc->pend_list_tag[i] |= P_ACTIVE; + } INIT_LIST_HEAD(&dcc->wait_list); mutex_init(&dcc->cmd_lock); atomic_set(&dcc->issued_discard, 0); @@ -1398,12 +1600,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi) if (!dcc) return; - if (dcc->f2fs_issue_discard) { - struct task_struct *discard_thread = dcc->f2fs_issue_discard; - - dcc->f2fs_issue_discard = NULL; - kthread_stop(discard_thread); - } + stop_discard_thread(sbi); kfree(dcc); SM_I(sbi)->dcc_info = NULL; @@ -1435,6 +1632,10 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) struct seg_entry *se; unsigned int segno, offset; long int new_vblocks; + bool exist; +#ifdef CONFIG_F2FS_CHECK_FS + bool mir_exist; +#endif segno = GET_SEGNO(sbi, blkaddr); @@ -1451,17 +1652,25 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) /* Update valid block bitmap */ if (del > 0) { - if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) { + exist = f2fs_test_and_set_bit(offset, se->cur_valid_map); #ifdef CONFIG_F2FS_CHECK_FS - if (f2fs_test_and_set_bit(offset, - se->cur_valid_map_mir)) - f2fs_bug_on(sbi, 1); - else - WARN_ON(1); -#else + mir_exist = f2fs_test_and_set_bit(offset, + se->cur_valid_map_mir); + if (unlikely(exist != mir_exist)) { + f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " + "when setting bitmap, blk:%u, old bit:%d", + blkaddr, exist); f2fs_bug_on(sbi, 1); + } #endif + if (unlikely(exist)) { + f2fs_msg(sbi->sb, KERN_ERR, + "Bitmap was wrongly set, blk:%u", blkaddr); + f2fs_bug_on(sbi, 1); + se->valid_blocks--; + del = 0; } + if (f2fs_discard_en(sbi) && !f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; @@ -1472,17 +1681,25 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) se->ckpt_valid_blocks++; } } else { - if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) { + exist = f2fs_test_and_clear_bit(offset, se->cur_valid_map); #ifdef CONFIG_F2FS_CHECK_FS - if (!f2fs_test_and_clear_bit(offset, - se->cur_valid_map_mir)) - f2fs_bug_on(sbi, 1); - else - WARN_ON(1); -#else + mir_exist = f2fs_test_and_clear_bit(offset, + se->cur_valid_map_mir); + if (unlikely(exist != mir_exist)) { + f2fs_msg(sbi->sb, KERN_ERR, "Inconsistent error " + "when clearing bitmap, blk:%u, old bit:%d", + blkaddr, exist); f2fs_bug_on(sbi, 1); + } #endif + if (unlikely(!exist)) { + f2fs_msg(sbi->sb, KERN_ERR, + "Bitmap was wrongly cleared, blk:%u", blkaddr); + f2fs_bug_on(sbi, 1); + se->valid_blocks++; + del = 0; } + if (f2fs_discard_en(sbi) && f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; @@ -1844,7 +2061,7 @@ static void __refresh_next_blkoff(struct f2fs_sb_info *sbi, * This function always allocates a used segment(from dirty seglist) by SSR * manner, so it should recover the existing segment information of valid blocks */ -static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse) +static void change_curseg(struct f2fs_sb_info *sbi, int type) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -1865,12 +2082,10 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type, bool reuse) curseg->alloc_type = SSR; __next_free_blkoff(sbi, curseg, 0); - if (reuse) { - sum_page = get_sum_page(sbi, new_segno); - sum_node = (struct f2fs_summary_block *)page_address(sum_page); - memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); - f2fs_put_page(sum_page, 1); - } + sum_page = get_sum_page(sbi, new_segno); + sum_node = (struct f2fs_summary_block *)page_address(sum_page); + memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); + f2fs_put_page(sum_page, 1); } static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) @@ -1934,7 +2149,7 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) new_curseg(sbi, type, false); else if (need_SSR(sbi) && get_ssr_segment(sbi, type)) - change_curseg(sbi, type, true); + change_curseg(sbi, type); else new_curseg(sbi, type, false); @@ -2027,6 +2242,9 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) schedule(); } + /* It's time to issue all the filed discards */ + mark_discard_range_all(sbi); + f2fs_wait_discard_bios(sbi, false); out: range->len = F2FS_BLK_TO_BYTES(cpc.trimmed); return err; @@ -2040,66 +2258,80 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type) return false; } -static int __get_segment_type_2(struct page *page, enum page_type p_type) +static int __get_segment_type_2(struct f2fs_io_info *fio) { - if (p_type == DATA) + if (fio->type == DATA) return CURSEG_HOT_DATA; else return CURSEG_HOT_NODE; } -static int __get_segment_type_4(struct page *page, enum page_type p_type) +static int __get_segment_type_4(struct f2fs_io_info *fio) { - if (p_type == DATA) { - struct inode *inode = page->mapping->host; + if (fio->type == DATA) { + struct inode *inode = fio->page->mapping->host; if (S_ISDIR(inode->i_mode)) return CURSEG_HOT_DATA; else return CURSEG_COLD_DATA; } else { - if (IS_DNODE(page) && is_cold_node(page)) + if (IS_DNODE(fio->page) && is_cold_node(fio->page)) return CURSEG_WARM_NODE; else return CURSEG_COLD_NODE; } } -static int __get_segment_type_6(struct page *page, enum page_type p_type) +static int __get_segment_type_6(struct f2fs_io_info *fio) { - if (p_type == DATA) { - struct inode *inode = page->mapping->host; + if (fio->type == DATA) { + struct inode *inode = fio->page->mapping->host; - if (is_cold_data(page) || file_is_cold(inode)) + if (is_cold_data(fio->page) || file_is_cold(inode)) return CURSEG_COLD_DATA; if (is_inode_flag_set(inode, FI_HOT_DATA)) return CURSEG_HOT_DATA; return CURSEG_WARM_DATA; } else { - if (IS_DNODE(page)) - return is_cold_node(page) ? CURSEG_WARM_NODE : + if (IS_DNODE(fio->page)) + return is_cold_node(fio->page) ? CURSEG_WARM_NODE : CURSEG_HOT_NODE; return CURSEG_COLD_NODE; } } -static int __get_segment_type(struct page *page, enum page_type p_type) +static int __get_segment_type(struct f2fs_io_info *fio) { - switch (F2FS_P_SB(page)->active_logs) { + int type = 0; + + switch (fio->sbi->active_logs) { case 2: - return __get_segment_type_2(page, p_type); + type = __get_segment_type_2(fio); + break; case 4: - return __get_segment_type_4(page, p_type); + type = __get_segment_type_4(fio); + break; + case 6: + type = __get_segment_type_6(fio); + break; + default: + f2fs_bug_on(fio->sbi, true); } - /* NR_CURSEG_TYPE(6) logs by default */ - f2fs_bug_on(F2FS_P_SB(page), - F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE); - return __get_segment_type_6(page, p_type); + + if (IS_HOT(type)) + fio->temp = HOT; + else if (IS_WARM(type)) + fio->temp = WARM; + else + fio->temp = COLD; + return type; } void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, block_t old_blkaddr, block_t *new_blkaddr, - struct f2fs_summary *sum, int type) + struct f2fs_summary *sum, int type, + struct f2fs_io_info *fio, bool add_list) { struct sit_info *sit_i = SIT_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, type); @@ -2132,35 +2364,45 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, mutex_unlock(&sit_i->sentry_lock); - if (page && IS_NODESEG(type)) + if (page && IS_NODESEG(type)) { fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); + f2fs_inode_chksum_set(sbi, page); + } + + if (add_list) { + struct f2fs_bio_info *io; + + INIT_LIST_HEAD(&fio->list); + fio->in_list = true; + io = sbi->write_io[fio->type] + fio->temp; + spin_lock(&io->io_lock); + list_add_tail(&fio->list, &io->io_list); + spin_unlock(&io->io_lock); + } + mutex_unlock(&curseg->curseg_mutex); } static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) { - int type = __get_segment_type(fio->page, fio->type); + int type = __get_segment_type(fio); int err; - if (fio->type == NODE || fio->type == DATA) - mutex_lock(&fio->sbi->wio_mutex[fio->type]); reallocate: allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, - &fio->new_blkaddr, sum, type); + &fio->new_blkaddr, sum, type, fio, true); /* writeout dirty page into bdev */ - err = f2fs_submit_page_mbio(fio); + err = f2fs_submit_page_write(fio); if (err == -EAGAIN) { fio->old_blkaddr = fio->new_blkaddr; goto reallocate; } - - if (fio->type == NODE || fio->type == DATA) - mutex_unlock(&fio->sbi->wio_mutex[fio->type]); } -void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) +void write_meta_page(struct f2fs_sb_info *sbi, struct page *page, + enum iostat_type io_type) { struct f2fs_io_info fio = { .sbi = sbi, @@ -2171,13 +2413,16 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page) .new_blkaddr = page->index, .page = page, .encrypted_page = NULL, + .in_list = false, }; if (unlikely(page->index >= MAIN_BLKADDR(sbi))) fio.op_flags &= ~REQ_META; set_page_writeback(page); - f2fs_submit_page_mbio(&fio); + f2fs_submit_page_write(&fio); + + f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE); } void write_node_page(unsigned int nid, struct f2fs_io_info *fio) @@ -2186,6 +2431,8 @@ void write_node_page(unsigned int nid, struct f2fs_io_info *fio) set_summary(&sum, nid, 0, 0); do_write_page(&sum, fio); + + f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); } void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) @@ -2199,13 +2446,22 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio) set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version); do_write_page(&sum, fio); f2fs_update_data_blkaddr(dn, fio->new_blkaddr); + + f2fs_update_iostat(sbi, fio->io_type, F2FS_BLKSIZE); } int rewrite_data_page(struct f2fs_io_info *fio) { + int err; + fio->new_blkaddr = fio->old_blkaddr; stat_inc_inplace_blocks(fio->sbi); - return f2fs_submit_page_bio(fio); + + err = f2fs_submit_page_bio(fio); + + f2fs_update_iostat(fio->sbi, fio->io_type, F2FS_BLKSIZE); + + return err; } void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, @@ -2247,7 +2503,7 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, /* change the current segment */ if (segno != curseg->segno) { curseg->next_segno = segno; - change_curseg(sbi, type, true); + change_curseg(sbi, type); } curseg->next_blkoff = GET_BLKOFF_FROM_SEG0(sbi, new_blkaddr); @@ -2266,7 +2522,7 @@ void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, if (recover_curseg) { if (old_cursegno != curseg->segno) { curseg->next_segno = old_cursegno; - change_curseg(sbi, type, true); + change_curseg(sbi, type); } curseg->next_blkoff = old_blkoff; } @@ -2296,8 +2552,8 @@ void f2fs_wait_on_page_writeback(struct page *page, if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); - f2fs_submit_merged_bio_cond(sbi, page->mapping->host, - 0, page->index, type, WRITE); + f2fs_submit_merged_write_cond(sbi, page->mapping->host, + 0, page->index, type); if (ordered) wait_on_page_writeback(page); else @@ -2305,8 +2561,7 @@ void f2fs_wait_on_page_writeback(struct page *page, } } -void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi, - block_t blkaddr) +void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) { struct page *cpage; @@ -2455,6 +2710,8 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) static int restore_curseg_summaries(struct f2fs_sb_info *sbi) { + struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal; + struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal; int type = CURSEG_HOT_DATA; int err; @@ -2481,6 +2738,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) return err; } + /* sanity check for summary blocks */ + if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES || + sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) + return -EINVAL; + return 0; } @@ -3203,7 +3465,7 @@ int build_segment_manager(struct f2fs_sb_info *sbi) INIT_LIST_HEAD(&sm_info->sit_entry_set); - if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) { + if (!f2fs_readonly(sbi->sb)) { err = create_flush_cmd_control(sbi); if (err) return err; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 010f336a7573..e0a6cc23ace3 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -27,6 +27,10 @@ #define IS_DATASEG(t) ((t) <= CURSEG_COLD_DATA) #define IS_NODESEG(t) ((t) >= CURSEG_HOT_NODE) +#define IS_HOT(t) ((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA) +#define IS_WARM(t) ((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA) +#define IS_COLD(t) ((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA) + #define IS_CURSEG(sbi, seg) \ (((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) || \ ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) || \ @@ -488,29 +492,11 @@ static inline int overprovision_segments(struct f2fs_sb_info *sbi) return SM_I(sbi)->ovp_segments; } -static inline int overprovision_sections(struct f2fs_sb_info *sbi) -{ - return GET_SEC_FROM_SEG(sbi, (unsigned int)overprovision_segments(sbi)); -} - static inline int reserved_sections(struct f2fs_sb_info *sbi) { return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi)); } -static inline bool need_SSR(struct f2fs_sb_info *sbi) -{ - int node_secs = get_blocktype_secs(sbi, F2FS_DIRTY_NODES); - int dent_secs = get_blocktype_secs(sbi, F2FS_DIRTY_DENTS); - int imeta_secs = get_blocktype_secs(sbi, F2FS_DIRTY_IMETA); - - if (test_opt(sbi, LFS)) - return false; - - return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + - 2 * reserved_sections(sbi)); -} - static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed, int needed) { @@ -573,6 +559,10 @@ static inline bool need_inplace_update_policy(struct inode *inode, if (test_opt(sbi, LFS)) return false; + /* if this is cold file, we should overwrite to avoid fragmentation */ + if (file_is_cold(inode)) + return true; + if (policy & (0x1 << F2FS_IPU_FORCE)) return true; if (policy & (0x1 << F2FS_IPU_SSR) && need_SSR(sbi)) @@ -795,3 +785,28 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type, wbc->nr_to_write = desired; return desired - nr_to_write; } + +static inline void wake_up_discard_thread(struct f2fs_sb_info *sbi, bool force) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + bool wakeup = false; + int i; + + if (force) + goto wake_up; + + mutex_lock(&dcc->cmd_lock); + for (i = MAX_PLIST_NUM - 1; + i >= 0 && plist_issue(dcc->pend_list_tag[i]); i--) { + if (!list_empty(&dcc->pend_list[i])) { + wakeup = true; + break; + } + } + mutex_unlock(&dcc->cmd_lock); + if (!wakeup) + return; +wake_up: + dcc->discard_wake = 1; + wake_up_interruptible_all(&dcc->discard_wait_queue); +} diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 83355ec4a92c..933c3d529e65 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -22,8 +22,10 @@ #include <linux/random.h> #include <linux/exportfs.h> #include <linux/blkdev.h> +#include <linux/quotaops.h> #include <linux/f2fs_fs.h> #include <linux/sysfs.h> +#include <linux/quota.h> #include "f2fs.h" #include "node.h" @@ -35,9 +37,7 @@ #define CREATE_TRACE_POINTS #include <trace/events/f2fs.h> -static struct proc_dir_entry *f2fs_proc_root; static struct kmem_cache *f2fs_inode_cachep; -static struct kset *f2fs_kset; #ifdef CONFIG_F2FS_FAULT_INJECTION @@ -108,6 +108,20 @@ enum { Opt_fault_injection, Opt_lazytime, Opt_nolazytime, + Opt_quota, + Opt_noquota, + Opt_usrquota, + Opt_grpquota, + Opt_prjquota, + Opt_usrjquota, + Opt_grpjquota, + Opt_prjjquota, + Opt_offusrjquota, + Opt_offgrpjquota, + Opt_offprjjquota, + Opt_jqfmt_vfsold, + Opt_jqfmt_vfsv0, + Opt_jqfmt_vfsv1, Opt_err, }; @@ -143,230 +157,139 @@ static match_table_t f2fs_tokens = { {Opt_fault_injection, "fault_injection=%u"}, {Opt_lazytime, "lazytime"}, {Opt_nolazytime, "nolazytime"}, + {Opt_quota, "quota"}, + {Opt_noquota, "noquota"}, + {Opt_usrquota, "usrquota"}, + {Opt_grpquota, "grpquota"}, + {Opt_prjquota, "prjquota"}, + {Opt_usrjquota, "usrjquota=%s"}, + {Opt_grpjquota, "grpjquota=%s"}, + {Opt_prjjquota, "prjjquota=%s"}, + {Opt_offusrjquota, "usrjquota="}, + {Opt_offgrpjquota, "grpjquota="}, + {Opt_offprjjquota, "prjjquota="}, + {Opt_jqfmt_vfsold, "jqfmt=vfsold"}, + {Opt_jqfmt_vfsv0, "jqfmt=vfsv0"}, + {Opt_jqfmt_vfsv1, "jqfmt=vfsv1"}, {Opt_err, NULL}, }; -/* Sysfs support for f2fs */ -enum { - GC_THREAD, /* struct f2fs_gc_thread */ - SM_INFO, /* struct f2fs_sm_info */ - DCC_INFO, /* struct discard_cmd_control */ - NM_INFO, /* struct f2fs_nm_info */ - F2FS_SBI, /* struct f2fs_sb_info */ -#ifdef CONFIG_F2FS_FAULT_INJECTION - FAULT_INFO_RATE, /* struct f2fs_fault_info */ - FAULT_INFO_TYPE, /* struct f2fs_fault_info */ -#endif -}; - -struct f2fs_attr { - struct attribute attr; - ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *); - ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *, - const char *, size_t); - int struct_type; - int offset; -}; - -static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) -{ - if (struct_type == GC_THREAD) - return (unsigned char *)sbi->gc_thread; - else if (struct_type == SM_INFO) - return (unsigned char *)SM_I(sbi); - else if (struct_type == DCC_INFO) - return (unsigned char *)SM_I(sbi)->dcc_info; - else if (struct_type == NM_INFO) - return (unsigned char *)NM_I(sbi); - else if (struct_type == F2FS_SBI) - return (unsigned char *)sbi; -#ifdef CONFIG_F2FS_FAULT_INJECTION - else if (struct_type == FAULT_INFO_RATE || - struct_type == FAULT_INFO_TYPE) - return (unsigned char *)&sbi->fault_info; -#endif - return NULL; -} - -static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, - struct f2fs_sb_info *sbi, char *buf) +void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) { - struct super_block *sb = sbi->sb; - - if (!sb->s_bdev->bd_part) - return snprintf(buf, PAGE_SIZE, "0\n"); + struct va_format vaf; + va_list args; - return snprintf(buf, PAGE_SIZE, "%llu\n", - (unsigned long long)(sbi->kbytes_written + - BD_PART_WRITTEN(sbi))); + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk_ratelimited("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); + va_end(args); } -static ssize_t f2fs_sbi_show(struct f2fs_attr *a, - struct f2fs_sb_info *sbi, char *buf) +static void init_once(void *foo) { - unsigned char *ptr = NULL; - unsigned int *ui; - - ptr = __struct_ptr(sbi, a->struct_type); - if (!ptr) - return -EINVAL; - - ui = (unsigned int *)(ptr + a->offset); + struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; - return snprintf(buf, PAGE_SIZE, "%u\n", *ui); + inode_init_once(&fi->vfs_inode); } -static ssize_t f2fs_sbi_store(struct f2fs_attr *a, - struct f2fs_sb_info *sbi, - const char *buf, size_t count) +#ifdef CONFIG_QUOTA +static const char * const quotatypes[] = INITQFNAMES; +#define QTYPE2NAME(t) (quotatypes[t]) +static int f2fs_set_qf_name(struct super_block *sb, int qtype, + substring_t *args) { - unsigned char *ptr; - unsigned long t; - unsigned int *ui; - ssize_t ret; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + char *qname; + int ret = -EINVAL; - ptr = __struct_ptr(sbi, a->struct_type); - if (!ptr) + if (sb_any_quota_loaded(sb) && !sbi->s_qf_names[qtype]) { + f2fs_msg(sb, KERN_ERR, + "Cannot change journaled " + "quota options when quota turned on"); return -EINVAL; - - ui = (unsigned int *)(ptr + a->offset); - - ret = kstrtoul(skip_spaces(buf), 0, &t); - if (ret < 0) - return ret; -#ifdef CONFIG_F2FS_FAULT_INJECTION - if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) + } + qname = match_strdup(args); + if (!qname) { + f2fs_msg(sb, KERN_ERR, + "Not enough memory for storing quotafile name"); return -EINVAL; -#endif - *ui = t; - return count; -} - -static ssize_t f2fs_attr_show(struct kobject *kobj, - struct attribute *attr, char *buf) -{ - struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, - s_kobj); - struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); - - return a->show ? a->show(a, sbi, buf) : 0; + } + if (sbi->s_qf_names[qtype]) { + if (strcmp(sbi->s_qf_names[qtype], qname) == 0) + ret = 0; + else + f2fs_msg(sb, KERN_ERR, + "%s quota file already specified", + QTYPE2NAME(qtype)); + goto errout; + } + if (strchr(qname, '/')) { + f2fs_msg(sb, KERN_ERR, + "quotafile must be on filesystem root"); + goto errout; + } + sbi->s_qf_names[qtype] = qname; + set_opt(sbi, QUOTA); + return 0; +errout: + kfree(qname); + return ret; } -static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t len) +static int f2fs_clear_qf_name(struct super_block *sb, int qtype) { - struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, - s_kobj); - struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + struct f2fs_sb_info *sbi = F2FS_SB(sb); - return a->store ? a->store(a, sbi, buf, len) : 0; + if (sb_any_quota_loaded(sb) && sbi->s_qf_names[qtype]) { + f2fs_msg(sb, KERN_ERR, "Cannot change journaled quota options" + " when quota turned on"); + return -EINVAL; + } + kfree(sbi->s_qf_names[qtype]); + sbi->s_qf_names[qtype] = NULL; + return 0; } -static void f2fs_sb_release(struct kobject *kobj) +static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) { - struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, - s_kobj); - complete(&sbi->s_kobj_unregister); -} + /* + * We do the test below only for project quotas. 'usrquota' and + * 'grpquota' mount options are allowed even without quota feature + * to support legacy quotas in quota files. + */ + if (test_opt(sbi, PRJQUOTA) && !f2fs_sb_has_project_quota(sbi->sb)) { + f2fs_msg(sbi->sb, KERN_ERR, "Project quota feature not enabled. " + "Cannot enable project quota enforcement."); + return -1; + } + if (sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA] || + sbi->s_qf_names[PRJQUOTA]) { + if (test_opt(sbi, USRQUOTA) && sbi->s_qf_names[USRQUOTA]) + clear_opt(sbi, USRQUOTA); + + if (test_opt(sbi, GRPQUOTA) && sbi->s_qf_names[GRPQUOTA]) + clear_opt(sbi, GRPQUOTA); + + if (test_opt(sbi, PRJQUOTA) && sbi->s_qf_names[PRJQUOTA]) + clear_opt(sbi, PRJQUOTA); + + if (test_opt(sbi, GRPQUOTA) || test_opt(sbi, USRQUOTA) || + test_opt(sbi, PRJQUOTA)) { + f2fs_msg(sbi->sb, KERN_ERR, "old and new quota " + "format mixing"); + return -1; + } -#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \ -static struct f2fs_attr f2fs_attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = _mode }, \ - .show = _show, \ - .store = _store, \ - .struct_type = _struct_type, \ - .offset = _offset \ + if (!sbi->s_jquota_fmt) { + f2fs_msg(sbi->sb, KERN_ERR, "journaled quota format " + "not specified"); + return -1; + } + } + return 0; } - -#define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \ - F2FS_ATTR_OFFSET(struct_type, name, 0644, \ - f2fs_sbi_show, f2fs_sbi_store, \ - offsetof(struct struct_name, elname)) - -#define F2FS_GENERAL_RO_ATTR(name) \ -static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL) - -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); -#ifdef CONFIG_F2FS_FAULT_INJECTION -F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate); -F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); -#endif -F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); - -#define ATTR_LIST(name) (&f2fs_attr_##name.attr) -static struct attribute *f2fs_attrs[] = { - ATTR_LIST(gc_min_sleep_time), - ATTR_LIST(gc_max_sleep_time), - ATTR_LIST(gc_no_gc_sleep_time), - ATTR_LIST(gc_idle), - ATTR_LIST(reclaim_segments), - ATTR_LIST(max_small_discards), - ATTR_LIST(batched_trim_sections), - ATTR_LIST(ipu_policy), - ATTR_LIST(min_ipu_util), - ATTR_LIST(min_fsync_blocks), - ATTR_LIST(min_hot_blocks), - ATTR_LIST(max_victim_search), - ATTR_LIST(dir_level), - ATTR_LIST(ram_thresh), - ATTR_LIST(ra_nid_pages), - ATTR_LIST(dirty_nats_ratio), - ATTR_LIST(cp_interval), - ATTR_LIST(idle_interval), -#ifdef CONFIG_F2FS_FAULT_INJECTION - ATTR_LIST(inject_rate), - ATTR_LIST(inject_type), #endif - ATTR_LIST(lifetime_write_kbytes), - NULL, -}; - -static const struct sysfs_ops f2fs_attr_ops = { - .show = f2fs_attr_show, - .store = f2fs_attr_store, -}; - -static struct kobj_type f2fs_ktype = { - .default_attrs = f2fs_attrs, - .sysfs_ops = &f2fs_attr_ops, - .release = f2fs_sb_release, -}; - -void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - vaf.fmt = fmt; - vaf.va = &args; - printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); - va_end(args); -} - -static void init_once(void *foo) -{ - struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo; - - inode_init_once(&fi->vfs_inode); -} static int parse_options(struct super_block *sb, char *options) { @@ -375,6 +298,9 @@ static int parse_options(struct super_block *sb, char *options) substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; +#ifdef CONFIG_QUOTA + int ret; +#endif if (!options) return 0; @@ -585,6 +511,81 @@ static int parse_options(struct super_block *sb, char *options) case Opt_nolazytime: sb->s_flags &= ~MS_LAZYTIME; break; +#ifdef CONFIG_QUOTA + case Opt_quota: + case Opt_usrquota: + set_opt(sbi, USRQUOTA); + break; + case Opt_grpquota: + set_opt(sbi, GRPQUOTA); + break; + case Opt_prjquota: + set_opt(sbi, PRJQUOTA); + break; + case Opt_usrjquota: + ret = f2fs_set_qf_name(sb, USRQUOTA, &args[0]); + if (ret) + return ret; + break; + case Opt_grpjquota: + ret = f2fs_set_qf_name(sb, GRPQUOTA, &args[0]); + if (ret) + return ret; + break; + case Opt_prjjquota: + ret = f2fs_set_qf_name(sb, PRJQUOTA, &args[0]); + if (ret) + return ret; + break; + case Opt_offusrjquota: + ret = f2fs_clear_qf_name(sb, USRQUOTA); + if (ret) + return ret; + break; + case Opt_offgrpjquota: + ret = f2fs_clear_qf_name(sb, GRPQUOTA); + if (ret) + return ret; + break; + case Opt_offprjjquota: + ret = f2fs_clear_qf_name(sb, PRJQUOTA); + if (ret) + return ret; + break; + case Opt_jqfmt_vfsold: + sbi->s_jquota_fmt = QFMT_VFS_OLD; + break; + case Opt_jqfmt_vfsv0: + sbi->s_jquota_fmt = QFMT_VFS_V0; + break; + case Opt_jqfmt_vfsv1: + sbi->s_jquota_fmt = QFMT_VFS_V1; + break; + case Opt_noquota: + clear_opt(sbi, QUOTA); + clear_opt(sbi, USRQUOTA); + clear_opt(sbi, GRPQUOTA); + clear_opt(sbi, PRJQUOTA); + break; +#else + case Opt_quota: + case Opt_usrquota: + case Opt_grpquota: + case Opt_prjquota: + case Opt_usrjquota: + case Opt_grpjquota: + case Opt_prjjquota: + case Opt_offusrjquota: + case Opt_offgrpjquota: + case Opt_offprjjquota: + case Opt_jqfmt_vfsold: + case Opt_jqfmt_vfsv0: + case Opt_jqfmt_vfsv1: + case Opt_noquota: + f2fs_msg(sb, KERN_INFO, + "quota operations not supported"); + break; +#endif default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -592,6 +593,10 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; } } +#ifdef CONFIG_QUOTA + if (f2fs_check_quota_options(sbi)) + return -EINVAL; +#endif if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) { f2fs_msg(sb, KERN_ERR, @@ -624,9 +629,16 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb) mutex_init(&fi->inmem_lock); init_rwsem(&fi->dio_rwsem[READ]); init_rwsem(&fi->dio_rwsem[WRITE]); + init_rwsem(&fi->i_mmap_sem); + init_rwsem(&fi->i_xattr_sem); +#ifdef CONFIG_QUOTA + memset(&fi->i_dquot, 0, sizeof(fi->i_dquot)); + fi->i_reserved_quota = 0; +#endif /* Will be used by directory only */ fi->i_dir_level = F2FS_SB(sb)->dir_level; + return &fi->vfs_inode; } @@ -768,15 +780,9 @@ static void destroy_device_list(struct f2fs_sb_info *sbi) static void f2fs_put_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); + int i; - if (sbi->s_proc) { - remove_proc_entry("segment_info", sbi->s_proc); - remove_proc_entry("segment_bits", sbi->s_proc); - remove_proc_entry(sb->s_id, f2fs_proc_root); - } - kobject_del(&sbi->s_kobj); - - stop_gc_thread(sbi); + f2fs_quota_off_umount(sb); /* prevent remaining shrinker jobs */ mutex_lock(&sbi->umount_mutex); @@ -795,9 +801,9 @@ static void f2fs_put_super(struct super_block *sb) } /* be sure to wait for any on-going discard commands */ - f2fs_wait_discard_bios(sbi); + f2fs_wait_discard_bios(sbi, true); - if (!sbi->discard_blks) { + if (f2fs_discard_en(sbi) && !sbi->discard_blks) { struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; @@ -817,7 +823,7 @@ static void f2fs_put_super(struct super_block *sb) mutex_unlock(&sbi->umount_mutex); /* our cp_error case, we can wait for any writeback page */ - f2fs_flush_merged_bios(sbi); + f2fs_flush_merged_writes(sbi); iput(sbi->node_inode); iput(sbi->meta_inode); @@ -827,8 +833,8 @@ static void f2fs_put_super(struct super_block *sb) destroy_segment_manager(sbi); kfree(sbi->ckpt); - kobject_put(&sbi->s_kobj); - wait_for_completion(&sbi->s_kobj_unregister); + + f2fs_unregister_sysfs(sbi); sb->s_fs_info = NULL; if (sbi->s_chksum_driver) @@ -837,7 +843,13 @@ static void f2fs_put_super(struct super_block *sb) destroy_device_list(sbi); mempool_destroy(sbi->write_io_dummy); +#ifdef CONFIG_QUOTA + for (i = 0; i < MAXQUOTAS; i++) + kfree(sbi->s_qf_names[i]); +#endif destroy_percpu_info(sbi); + for (i = 0; i < NR_PAGE_TYPE; i++) + kfree(sbi->write_io[i]); kfree(sbi); } @@ -848,6 +860,9 @@ int f2fs_sync_fs(struct super_block *sb, int sync) trace_f2fs_sync_fs(sb, sync); + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) + return -EAGAIN; + if (sync) { struct cp_control cpc; @@ -882,12 +897,55 @@ static int f2fs_unfreeze(struct super_block *sb) return 0; } +#ifdef CONFIG_QUOTA +static int f2fs_statfs_project(struct super_block *sb, + kprojid_t projid, struct kstatfs *buf) +{ + struct kqid qid; + struct dquot *dquot; + u64 limit; + u64 curblock; + + qid = make_kqid_projid(projid); + dquot = dqget(sb, qid); + if (IS_ERR(dquot)) + return PTR_ERR(dquot); + spin_lock(&dq_data_lock); + + limit = (dquot->dq_dqb.dqb_bsoftlimit ? + dquot->dq_dqb.dqb_bsoftlimit : + dquot->dq_dqb.dqb_bhardlimit) >> sb->s_blocksize_bits; + if (limit && buf->f_blocks > limit) { + curblock = dquot->dq_dqb.dqb_curspace >> sb->s_blocksize_bits; + buf->f_blocks = limit; + buf->f_bfree = buf->f_bavail = + (buf->f_blocks > curblock) ? + (buf->f_blocks - curblock) : 0; + } + + limit = dquot->dq_dqb.dqb_isoftlimit ? + dquot->dq_dqb.dqb_isoftlimit : + dquot->dq_dqb.dqb_ihardlimit; + if (limit && buf->f_files > limit) { + buf->f_files = limit; + buf->f_ffree = + (buf->f_files > dquot->dq_dqb.dqb_curinodes) ? + (buf->f_files - dquot->dq_dqb.dqb_curinodes) : 0; + } + + spin_unlock(&dq_data_lock); + dqput(dquot); + return 0; +} +#endif + static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct f2fs_sb_info *sbi = F2FS_SB(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); block_t total_count, user_block_count, start_count, ovp_count; + u64 avail_node_count; total_count = le64_to_cpu(sbi->raw_super->block_count); user_block_count = sbi->user_block_count; @@ -898,19 +956,67 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = total_count - start_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count; - buf->f_bavail = user_block_count - valid_user_blocks(sbi); + buf->f_bavail = user_block_count - valid_user_blocks(sbi) - + sbi->reserved_blocks; - buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; - buf->f_ffree = min(buf->f_files - valid_node_count(sbi), - buf->f_bavail); + avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM; + + if (avail_node_count > user_block_count) { + buf->f_files = user_block_count; + buf->f_ffree = buf->f_bavail; + } else { + buf->f_files = avail_node_count; + buf->f_ffree = min(avail_node_count - valid_node_count(sbi), + buf->f_bavail); + } buf->f_namelen = F2FS_NAME_LEN; buf->f_fsid.val[0] = (u32)id; buf->f_fsid.val[1] = (u32)(id >> 32); +#ifdef CONFIG_QUOTA + if (is_inode_flag_set(dentry->d_inode, FI_PROJ_INHERIT) && + sb_has_quota_limits_enabled(sb, PRJQUOTA)) { + f2fs_statfs_project(sb, F2FS_I(dentry->d_inode)->i_projid, buf); + } +#endif return 0; } +static inline void f2fs_show_quota_options(struct seq_file *seq, + struct super_block *sb) +{ +#ifdef CONFIG_QUOTA + struct f2fs_sb_info *sbi = F2FS_SB(sb); + + if (sbi->s_jquota_fmt) { + char *fmtname = ""; + + switch (sbi->s_jquota_fmt) { + case QFMT_VFS_OLD: + fmtname = "vfsold"; + break; + case QFMT_VFS_V0: + fmtname = "vfsv0"; + break; + case QFMT_VFS_V1: + fmtname = "vfsv1"; + break; + } + seq_printf(seq, ",jqfmt=%s", fmtname); + } + + if (sbi->s_qf_names[USRQUOTA]) + seq_show_option(seq, "usrjquota", sbi->s_qf_names[USRQUOTA]); + + if (sbi->s_qf_names[GRPQUOTA]) + seq_show_option(seq, "grpjquota", sbi->s_qf_names[GRPQUOTA]); + + if (sbi->s_qf_names[PRJQUOTA]) + seq_show_option(seq, "prjjquota", sbi->s_qf_names[PRJQUOTA]); +#endif +} + static int f2fs_show_options(struct seq_file *seq, struct dentry *root) { struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb); @@ -980,79 +1086,24 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi)); #ifdef CONFIG_F2FS_FAULT_INJECTION if (test_opt(sbi, FAULT_INJECTION)) - seq_puts(seq, ",fault_injection"); + seq_printf(seq, ",fault_injection=%u", + sbi->fault_info.inject_rate); #endif +#ifdef CONFIG_QUOTA + if (test_opt(sbi, QUOTA)) + seq_puts(seq, ",quota"); + if (test_opt(sbi, USRQUOTA)) + seq_puts(seq, ",usrquota"); + if (test_opt(sbi, GRPQUOTA)) + seq_puts(seq, ",grpquota"); + if (test_opt(sbi, PRJQUOTA)) + seq_puts(seq, ",prjquota"); +#endif + f2fs_show_quota_options(seq, sbi->sb); return 0; } -static int segment_info_seq_show(struct seq_file *seq, void *offset) -{ - struct super_block *sb = seq->private; - struct f2fs_sb_info *sbi = F2FS_SB(sb); - unsigned int total_segs = - le32_to_cpu(sbi->raw_super->segment_count_main); - int i; - - seq_puts(seq, "format: segment_type|valid_blocks\n" - "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); - - for (i = 0; i < total_segs; i++) { - struct seg_entry *se = get_seg_entry(sbi, i); - - if ((i % 10) == 0) - seq_printf(seq, "%-10d", i); - seq_printf(seq, "%d|%-3u", se->type, - get_valid_blocks(sbi, i, false)); - if ((i % 10) == 9 || i == (total_segs - 1)) - seq_putc(seq, '\n'); - else - seq_putc(seq, ' '); - } - - return 0; -} - -static int segment_bits_seq_show(struct seq_file *seq, void *offset) -{ - struct super_block *sb = seq->private; - struct f2fs_sb_info *sbi = F2FS_SB(sb); - unsigned int total_segs = - le32_to_cpu(sbi->raw_super->segment_count_main); - int i, j; - - seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n" - "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); - - for (i = 0; i < total_segs; i++) { - struct seg_entry *se = get_seg_entry(sbi, i); - - seq_printf(seq, "%-10d", i); - seq_printf(seq, "%d|%-3u|", se->type, - get_valid_blocks(sbi, i, false)); - for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++) - seq_printf(seq, " %.2x", se->cur_valid_map[j]); - seq_putc(seq, '\n'); - } - return 0; -} - -#define F2FS_PROC_FILE_DEF(_name) \ -static int _name##_open_fs(struct inode *inode, struct file *file) \ -{ \ - return single_open(file, _name##_seq_show, PDE_DATA(inode)); \ -} \ - \ -static const struct file_operations f2fs_seq_##_name##_fops = { \ - .open = _name##_open_fs, \ - .read = seq_read, \ - .llseek = seq_lseek, \ - .release = single_release, \ -}; - -F2FS_PROC_FILE_DEF(segment_info); -F2FS_PROC_FILE_DEF(segment_bits); - static void default_options(struct f2fs_sb_info *sbi) { /* init some FS parameters */ @@ -1089,6 +1140,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); struct f2fs_mount_info org_mount_opt; + unsigned long old_sb_flags; int err, active_logs; bool need_restart_gc = false; bool need_stop_gc = false; @@ -1096,14 +1148,37 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) #ifdef CONFIG_F2FS_FAULT_INJECTION struct f2fs_fault_info ffi = sbi->fault_info; #endif +#ifdef CONFIG_QUOTA + int s_jquota_fmt; + char *s_qf_names[MAXQUOTAS]; + int i, j; +#endif /* * Save the old mount options in case we * need to restore them. */ org_mount_opt = sbi->mount_opt; + old_sb_flags = sb->s_flags; active_logs = sbi->active_logs; +#ifdef CONFIG_QUOTA + s_jquota_fmt = sbi->s_jquota_fmt; + for (i = 0; i < MAXQUOTAS; i++) { + if (sbi->s_qf_names[i]) { + s_qf_names[i] = kstrdup(sbi->s_qf_names[i], + GFP_KERNEL); + if (!s_qf_names[i]) { + for (j = 0; j < i; j++) + kfree(s_qf_names[j]); + return -ENOMEM; + } + } else { + s_qf_names[i] = NULL; + } + } +#endif + /* recover superblocks we couldn't write due to previous RO mount */ if (!(*flags & MS_RDONLY) && is_sbi_flag_set(sbi, SBI_NEED_SB_WRITE)) { err = f2fs_commit_super(sbi, false); @@ -1113,7 +1188,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } - sbi->mount_opt.opt = 0; default_options(sbi); /* parse mount options */ @@ -1128,6 +1202,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) if (f2fs_readonly(sb) && (*flags & MS_RDONLY)) goto skip; + if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) { + err = dquot_suspend(sb, -1); + if (err < 0) + goto restore_opts; + } else { + /* dquot_resume needs RW */ + sb->s_flags &= ~MS_RDONLY; + dquot_resume(sb, -1); + } + /* disallow enable/disable extent_cache dynamically */ if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) { err = -EINVAL; @@ -1176,6 +1260,11 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_gc; } skip: +#ifdef CONFIG_QUOTA + /* Release old quota file names */ + for (i = 0; i < MAXQUOTAS; i++) + kfree(s_qf_names[i]); +#endif /* Update the POSIXACL Flag */ sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); @@ -1190,21 +1279,286 @@ restore_gc: stop_gc_thread(sbi); } restore_opts: +#ifdef CONFIG_QUOTA + sbi->s_jquota_fmt = s_jquota_fmt; + for (i = 0; i < MAXQUOTAS; i++) { + kfree(sbi->s_qf_names[i]); + sbi->s_qf_names[i] = s_qf_names[i]; + } +#endif sbi->mount_opt = org_mount_opt; sbi->active_logs = active_logs; + sb->s_flags = old_sb_flags; #ifdef CONFIG_F2FS_FAULT_INJECTION sbi->fault_info = ffi; #endif return err; } -static struct super_operations f2fs_sops = { +#ifdef CONFIG_QUOTA +/* Read data from quotafile */ +static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data, + size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + struct address_space *mapping = inode->i_mapping; + block_t blkidx = F2FS_BYTES_TO_BLK(off); + int offset = off & (sb->s_blocksize - 1); + int tocopy; + size_t toread; + loff_t i_size = i_size_read(inode); + struct page *page; + char *kaddr; + + if (off > i_size) + return 0; + + if (off + len > i_size) + len = i_size - off; + toread = len; + while (toread > 0) { + tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread); +repeat: + page = read_mapping_page(mapping, blkidx, NULL); + if (IS_ERR(page)) + return PTR_ERR(page); + + lock_page(page); + + if (unlikely(page->mapping != mapping)) { + f2fs_put_page(page, 1); + goto repeat; + } + if (unlikely(!PageUptodate(page))) { + f2fs_put_page(page, 1); + return -EIO; + } + + kaddr = kmap_atomic(page); + memcpy(data, kaddr + offset, tocopy); + kunmap_atomic(kaddr); + f2fs_put_page(page, 1); + + offset = 0; + toread -= tocopy; + data += tocopy; + blkidx++; + } + return len; +} + +/* Write to quotafile */ +static ssize_t f2fs_quota_write(struct super_block *sb, int type, + const char *data, size_t len, loff_t off) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + struct address_space *mapping = inode->i_mapping; + const struct address_space_operations *a_ops = mapping->a_ops; + int offset = off & (sb->s_blocksize - 1); + size_t towrite = len; + struct page *page; + char *kaddr; + int err = 0; + int tocopy; + + while (towrite > 0) { + tocopy = min_t(unsigned long, sb->s_blocksize - offset, + towrite); + + err = a_ops->write_begin(NULL, mapping, off, tocopy, 0, + &page, NULL); + if (unlikely(err)) + break; + + kaddr = kmap_atomic(page); + memcpy(kaddr + offset, data, tocopy); + kunmap_atomic(kaddr); + flush_dcache_page(page); + + a_ops->write_end(NULL, mapping, off, tocopy, tocopy, + page, NULL); + offset = 0; + towrite -= tocopy; + off += tocopy; + data += tocopy; + cond_resched(); + } + + if (len == towrite) + return 0; + inode->i_version++; + inode->i_mtime = inode->i_ctime = current_time(inode); + f2fs_mark_inode_dirty_sync(inode, false); + return len - towrite; +} + +static struct dquot **f2fs_get_dquots(struct inode *inode) +{ + return F2FS_I(inode)->i_dquot; +} + +static qsize_t *f2fs_get_reserved_space(struct inode *inode) +{ + return &F2FS_I(inode)->i_reserved_quota; +} + +static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) +{ + return dquot_quota_on_mount(sbi->sb, sbi->s_qf_names[type], + sbi->s_jquota_fmt, type); +} + +void f2fs_enable_quota_files(struct f2fs_sb_info *sbi) +{ + int i, ret; + + for (i = 0; i < MAXQUOTAS; i++) { + if (sbi->s_qf_names[i]) { + ret = f2fs_quota_on_mount(sbi, i); + if (ret < 0) + f2fs_msg(sbi->sb, KERN_ERR, + "Cannot turn on journaled " + "quota: error %d", ret); + } + } +} + +static int f2fs_quota_sync(struct super_block *sb, int type) +{ + struct quota_info *dqopt = sb_dqopt(sb); + int cnt; + int ret; + + ret = dquot_writeback_dquots(sb, type); + if (ret) + return ret; + + /* + * Now when everything is written we can discard the pagecache so + * that userspace sees the changes. + */ + for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + if (type != -1 && cnt != type) + continue; + if (!sb_has_quota_active(sb, cnt)) + continue; + + ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping); + if (ret) + return ret; + + inode_lock(dqopt->files[cnt]); + truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); + inode_unlock(dqopt->files[cnt]); + } + return 0; +} + +static int f2fs_quota_on(struct super_block *sb, int type, int format_id, + const struct path *path) +{ + struct inode *inode; + int err; + + err = f2fs_quota_sync(sb, type); + if (err) + return err; + + err = dquot_quota_on(sb, type, format_id, path); + if (err) + return err; + + inode = d_inode(path->dentry); + + inode_lock(inode); + F2FS_I(inode)->i_flags |= FS_NOATIME_FL | FS_IMMUTABLE_FL; + inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, + S_NOATIME | S_IMMUTABLE); + inode_unlock(inode); + f2fs_mark_inode_dirty_sync(inode, false); + + return 0; +} + +static int f2fs_quota_off(struct super_block *sb, int type) +{ + struct inode *inode = sb_dqopt(sb)->files[type]; + int err; + + if (!inode || !igrab(inode)) + return dquot_quota_off(sb, type); + + f2fs_quota_sync(sb, type); + + err = dquot_quota_off(sb, type); + if (err) + goto out_put; + + inode_lock(inode); + F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL); + inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); + inode_unlock(inode); + f2fs_mark_inode_dirty_sync(inode, false); +out_put: + iput(inode); + return err; +} + +void f2fs_quota_off_umount(struct super_block *sb) +{ + int type; + + for (type = 0; type < MAXQUOTAS; type++) + f2fs_quota_off(sb, type); +} + +int f2fs_get_projid(struct inode *inode, kprojid_t *projid) +{ + *projid = F2FS_I(inode)->i_projid; + return 0; +} + +static const struct dquot_operations f2fs_quota_operations = { + .get_reserved_space = f2fs_get_reserved_space, + .write_dquot = dquot_commit, + .acquire_dquot = dquot_acquire, + .release_dquot = dquot_release, + .mark_dirty = dquot_mark_dquot_dirty, + .write_info = dquot_commit_info, + .alloc_dquot = dquot_alloc, + .destroy_dquot = dquot_destroy, + .get_projid = f2fs_get_projid, + .get_next_id = dquot_get_next_id, +}; + +static const struct quotactl_ops f2fs_quotactl_ops = { + .quota_on = f2fs_quota_on, + .quota_off = f2fs_quota_off, + .quota_sync = f2fs_quota_sync, + .get_state = dquot_get_state, + .set_info = dquot_set_dqinfo, + .get_dqblk = dquot_get_dqblk, + .set_dqblk = dquot_set_dqblk, + .get_nextdqblk = dquot_get_next_dqblk, +}; +#else +void f2fs_quota_off_umount(struct super_block *sb) +{ +} +#endif + +static const struct super_operations f2fs_sops = { .alloc_inode = f2fs_alloc_inode, .drop_inode = f2fs_drop_inode, .destroy_inode = f2fs_destroy_inode, .write_inode = f2fs_write_inode, .dirty_inode = f2fs_dirty_inode, .show_options = f2fs_show_options, +#ifdef CONFIG_QUOTA + .quota_read = f2fs_quota_read, + .quota_write = f2fs_quota_write, + .get_dquots = f2fs_get_dquots, +#endif .evict_inode = f2fs_evict_inode, .put_super = f2fs_put_super, .sync_fs = f2fs_sync_fs, @@ -1297,9 +1651,16 @@ static const struct export_operations f2fs_export_ops = { static loff_t max_file_blocks(void) { - loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS); + loff_t result = 0; loff_t leaf_count = ADDRS_PER_BLOCK; + /* + * note: previously, result is equal to (DEF_ADDRS_PER_INODE - + * F2FS_INLINE_XATTR_ADDRS), but now f2fs try to reserve more + * space in inode.i_addr, it will be more safe to reassign + * result as zero. + */ + /* two direct node blocks */ result += (leaf_count * 2); @@ -1521,6 +1882,8 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); unsigned int ovp_segments, reserved_segments; + unsigned int main_segs, blocks_per_seg; + int i; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -1542,6 +1905,20 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) return 1; } + main_segs = le32_to_cpu(raw_super->segment_count_main); + blocks_per_seg = sbi->blocks_per_seg; + + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || + le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) + return 1; + } + for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || + le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) + return 1; + } + if (unlikely(f2fs_cp_error(sbi))) { f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck"); return 1; @@ -1552,7 +1929,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) static void init_sb_info(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = sbi->raw_super; - int i; + int i, j; sbi->log_sectors_per_block = le32_to_cpu(raw_super->log_sectors_per_block); @@ -1584,8 +1961,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi) INIT_LIST_HEAD(&sbi->s_list); mutex_init(&sbi->umount_mutex); - mutex_init(&sbi->wio_mutex[NODE]); - mutex_init(&sbi->wio_mutex[DATA]); + for (i = 0; i < NR_PAGE_TYPE - 1; i++) + for (j = HOT; j < NR_TEMP_TYPE; j++) + mutex_init(&sbi->wio_mutex[i][j]); spin_lock_init(&sbi->cp_lock); } @@ -1899,6 +2277,11 @@ try_onemore: sb->s_fs_info = sbi; sbi->raw_super = raw_super; + /* precompute checksum seed for metadata */ + if (f2fs_sb_has_inode_chksum(sb)) + sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid, + sizeof(raw_super->uuid)); + /* * The BLKZONED feature indicates that the drive was formatted with * zone alignment optimization. This is optional for host-aware @@ -1908,6 +2291,7 @@ try_onemore: if (f2fs_sb_mounted_blkzoned(sb)) { f2fs_msg(sb, KERN_ERR, "Zoned block device support is not enabled\n"); + err = -EOPNOTSUPP; goto free_sb_buf; } #endif @@ -1929,6 +2313,12 @@ try_onemore: sb->s_max_links = F2FS_LINK_MAX; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); +#ifdef CONFIG_QUOTA + sb->dq_op = &f2fs_quota_operations; + sb->s_qcop = &f2fs_quotactl_ops; + sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ; +#endif + sb->s_op = &f2fs_sops; sb->s_cop = &f2fs_cryptops; sb->s_xattr = f2fs_xattr_handlers; @@ -1937,7 +2327,7 @@ try_onemore: sb->s_time_gran = 1; sb->s_flags = (sb->s_flags & ~MS_POSIXACL) | (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); - memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); + memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid)); /* init f2fs-specific super block info */ sbi->valid_super_block = valid_super_block; @@ -1950,13 +2340,28 @@ try_onemore: set_sbi_flag(sbi, SBI_POR_DOING); spin_lock_init(&sbi->stat_lock); - init_rwsem(&sbi->read_io.io_rwsem); - sbi->read_io.sbi = sbi; - sbi->read_io.bio = NULL; + /* init iostat info */ + spin_lock_init(&sbi->iostat_lock); + sbi->iostat_enable = false; + for (i = 0; i < NR_PAGE_TYPE; i++) { - init_rwsem(&sbi->write_io[i].io_rwsem); - sbi->write_io[i].sbi = sbi; - sbi->write_io[i].bio = NULL; + int n = (i == META) ? 1: NR_TEMP_TYPE; + int j; + + sbi->write_io[i] = kmalloc(n * sizeof(struct f2fs_bio_info), + GFP_KERNEL); + if (!sbi->write_io[i]) { + err = -ENOMEM; + goto free_options; + } + + for (j = HOT; j < n; j++) { + init_rwsem(&sbi->write_io[i][j].io_rwsem); + sbi->write_io[i][j].sbi = sbi; + sbi->write_io[i][j].bio = NULL; + spin_lock_init(&sbi->write_io[i][j].io_lock); + INIT_LIST_HEAD(&sbi->write_io[i][j].io_list); + } } init_rwsem(&sbi->cp_rwsem); @@ -1970,8 +2375,10 @@ try_onemore: if (F2FS_IO_SIZE(sbi) > 1) { sbi->write_io_dummy = mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0); - if (!sbi->write_io_dummy) + if (!sbi->write_io_dummy) { + err = -ENOMEM; goto free_options; + } } /* get an inode for meta space */ @@ -2003,6 +2410,7 @@ try_onemore: sbi->total_valid_block_count = le64_to_cpu(sbi->ckpt->valid_block_count); sbi->last_valid_block_count = sbi->total_valid_block_count; + sbi->reserved_blocks = 0; for (i = 0; i < NR_INODE_TYPE; i++) { INIT_LIST_HEAD(&sbi->inode_list[i]); @@ -2054,11 +2462,6 @@ try_onemore: if (err) goto free_nm; - /* if there are nt orphan nodes free them */ - err = recover_orphan_inodes(sbi); - if (err) - goto free_node_inode; - /* read root inode and dentry */ root = f2fs_iget(sb, F2FS_ROOT_INO(sbi)); if (IS_ERR(root)) { @@ -2078,22 +2481,14 @@ try_onemore: goto free_root_inode; } - if (f2fs_proc_root) - sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); - - if (sbi->s_proc) { - proc_create_data("segment_info", S_IRUGO, sbi->s_proc, - &f2fs_seq_segment_info_fops, sb); - proc_create_data("segment_bits", S_IRUGO, sbi->s_proc, - &f2fs_seq_segment_bits_fops, sb); - } + err = f2fs_register_sysfs(sbi); + if (err) + goto free_root_inode; - sbi->s_kobj.kset = f2fs_kset; - init_completion(&sbi->s_kobj_unregister); - err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL, - "%s", sb->s_id); + /* if there are nt orphan nodes free them */ + err = recover_orphan_inodes(sbi); if (err) - goto free_proc; + goto free_sysfs; /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { @@ -2104,7 +2499,7 @@ try_onemore: if (bdev_read_only(sb->s_bdev) && !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { err = -EROFS; - goto free_kobj; + goto free_meta; } if (need_fsck) @@ -2118,7 +2513,7 @@ try_onemore: need_fsck = true; f2fs_msg(sb, KERN_ERR, "Cannot recover all fsync data errno=%d", err); - goto free_kobj; + goto free_meta; } } else { err = recover_fsync_data(sbi, true); @@ -2127,7 +2522,7 @@ try_onemore: err = -EINVAL; f2fs_msg(sb, KERN_ERR, "Need to recover fsync data"); - goto free_kobj; + goto free_sysfs; } } skip_recovery: @@ -2142,7 +2537,7 @@ skip_recovery: /* After POR, we can run background GC thread.*/ err = start_gc_thread(sbi); if (err) - goto free_kobj; + goto free_meta; } kfree(options); @@ -2160,17 +2555,17 @@ skip_recovery: f2fs_update_time(sbi, REQ_TIME); return 0; -free_kobj: +free_meta: f2fs_sync_inode_meta(sbi); - kobject_del(&sbi->s_kobj); - kobject_put(&sbi->s_kobj); - wait_for_completion(&sbi->s_kobj_unregister); -free_proc: - if (sbi->s_proc) { - remove_proc_entry("segment_info", sbi->s_proc); - remove_proc_entry("segment_bits", sbi->s_proc); - remove_proc_entry(sb->s_id, f2fs_proc_root); - } + /* + * Some dirty meta pages can be produced by recover_orphan_inodes() + * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() + * followed by write_checkpoint() through f2fs_write_node_pages(), which + * falls into an infinite loop in sync_meta_pages(). + */ + truncate_inode_pages_final(META_MAPPING(sbi)); +free_sysfs: + f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); sb->s_root = NULL; @@ -2179,13 +2574,6 @@ free_node_inode: mutex_lock(&sbi->umount_mutex); release_ino_entry(sbi, true); f2fs_leave_shrinker(sbi); - /* - * Some dirty meta pages can be produced by recover_orphan_inodes() - * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() - * followed by write_checkpoint() through f2fs_write_node_pages(), which - * falls into an infinite loop in sync_meta_pages(). - */ - truncate_inode_pages_final(META_MAPPING(sbi)); iput(sbi->node_inode); mutex_unlock(&sbi->umount_mutex); f2fs_destroy_stats(sbi); @@ -2202,7 +2590,13 @@ free_meta_inode: free_io_dummy: mempool_destroy(sbi->write_io_dummy); free_options: + for (i = 0; i < NR_PAGE_TYPE; i++) + kfree(sbi->write_io[i]); destroy_percpu_info(sbi); +#ifdef CONFIG_QUOTA + for (i = 0; i < MAXQUOTAS; i++) + kfree(sbi->s_qf_names[i]); +#endif kfree(options); free_sb_buf: kfree(raw_super); @@ -2228,8 +2622,11 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags, static void kill_f2fs_super(struct super_block *sb) { - if (sb->s_root) + if (sb->s_root) { set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE); + stop_gc_thread(F2FS_SB(sb)); + stop_discard_thread(F2FS_SB(sb)); + } kill_block_super(sb); } @@ -2283,30 +2680,26 @@ static int __init init_f2fs_fs(void) err = create_extent_cache(); if (err) goto free_checkpoint_caches; - f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj); - if (!f2fs_kset) { - err = -ENOMEM; + err = f2fs_init_sysfs(); + if (err) goto free_extent_cache; - } err = register_shrinker(&f2fs_shrinker_info); if (err) - goto free_kset; - + goto free_sysfs; err = register_filesystem(&f2fs_fs_type); if (err) goto free_shrinker; err = f2fs_create_root_stats(); if (err) goto free_filesystem; - f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); return 0; free_filesystem: unregister_filesystem(&f2fs_fs_type); free_shrinker: unregister_shrinker(&f2fs_shrinker_info); -free_kset: - kset_unregister(f2fs_kset); +free_sysfs: + f2fs_exit_sysfs(); free_extent_cache: destroy_extent_cache(); free_checkpoint_caches: @@ -2323,11 +2716,10 @@ fail: static void __exit exit_f2fs_fs(void) { - remove_proc_entry("fs/f2fs", NULL); f2fs_destroy_root_stats(); unregister_filesystem(&f2fs_fs_type); unregister_shrinker(&f2fs_shrinker_info); - kset_unregister(f2fs_kset); + f2fs_exit_sysfs(); destroy_extent_cache(); destroy_checkpoint_caches(); destroy_segment_manager_caches(); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c new file mode 100644 index 000000000000..e2c258f717cd --- /dev/null +++ b/fs/f2fs/sysfs.c @@ -0,0 +1,556 @@ +/* + * f2fs sysfs interface + * + * Copyright (c) 2012 Samsung Electronics Co., Ltd. + * http://www.samsung.com/ + * Copyright (c) 2017 Chao Yu <chao@kernel.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/proc_fs.h> +#include <linux/f2fs_fs.h> +#include <linux/seq_file.h> + +#include "f2fs.h" +#include "segment.h" +#include "gc.h" + +static struct proc_dir_entry *f2fs_proc_root; + +/* Sysfs support for f2fs */ +enum { + GC_THREAD, /* struct f2fs_gc_thread */ + SM_INFO, /* struct f2fs_sm_info */ + DCC_INFO, /* struct discard_cmd_control */ + NM_INFO, /* struct f2fs_nm_info */ + F2FS_SBI, /* struct f2fs_sb_info */ +#ifdef CONFIG_F2FS_FAULT_INJECTION + FAULT_INFO_RATE, /* struct f2fs_fault_info */ + FAULT_INFO_TYPE, /* struct f2fs_fault_info */ +#endif + RESERVED_BLOCKS, +}; + +struct f2fs_attr { + struct attribute attr; + ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *); + ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *, + const char *, size_t); + int struct_type; + int offset; + int id; +}; + +static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type) +{ + if (struct_type == GC_THREAD) + return (unsigned char *)sbi->gc_thread; + else if (struct_type == SM_INFO) + return (unsigned char *)SM_I(sbi); + else if (struct_type == DCC_INFO) + return (unsigned char *)SM_I(sbi)->dcc_info; + else if (struct_type == NM_INFO) + return (unsigned char *)NM_I(sbi); + else if (struct_type == F2FS_SBI || struct_type == RESERVED_BLOCKS) + return (unsigned char *)sbi; +#ifdef CONFIG_F2FS_FAULT_INJECTION + else if (struct_type == FAULT_INFO_RATE || + struct_type == FAULT_INFO_TYPE) + return (unsigned char *)&sbi->fault_info; +#endif + return NULL; +} + +static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->sb; + + if (!sb->s_bdev->bd_part) + return snprintf(buf, PAGE_SIZE, "0\n"); + + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long)(sbi->kbytes_written + + BD_PART_WRITTEN(sbi))); +} + +static ssize_t features_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + struct super_block *sb = sbi->sb; + int len = 0; + + if (!sb->s_bdev->bd_part) + return snprintf(buf, PAGE_SIZE, "0\n"); + + if (f2fs_sb_has_crypto(sb)) + len += snprintf(buf, PAGE_SIZE - len, "%s", + "encryption"); + if (f2fs_sb_mounted_blkzoned(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "blkzoned"); + if (f2fs_sb_has_extra_attr(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "extra_attr"); + if (f2fs_sb_has_project_quota(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "projquota"); + if (f2fs_sb_has_inode_chksum(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "inode_checksum"); + len += snprintf(buf + len, PAGE_SIZE - len, "\n"); + return len; +} + +static ssize_t f2fs_sbi_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + unsigned char *ptr = NULL; + unsigned int *ui; + + ptr = __struct_ptr(sbi, a->struct_type); + if (!ptr) + return -EINVAL; + + ui = (unsigned int *)(ptr + a->offset); + + return snprintf(buf, PAGE_SIZE, "%u\n", *ui); +} + +static ssize_t f2fs_sbi_store(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, + const char *buf, size_t count) +{ + unsigned char *ptr; + unsigned long t; + unsigned int *ui; + ssize_t ret; + + ptr = __struct_ptr(sbi, a->struct_type); + if (!ptr) + return -EINVAL; + + ui = (unsigned int *)(ptr + a->offset); + + ret = kstrtoul(skip_spaces(buf), 0, &t); + if (ret < 0) + return ret; +#ifdef CONFIG_F2FS_FAULT_INJECTION + if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX)) + return -EINVAL; +#endif + if (a->struct_type == RESERVED_BLOCKS) { + spin_lock(&sbi->stat_lock); + if ((unsigned long)sbi->total_valid_block_count + t > + (unsigned long)sbi->user_block_count) { + spin_unlock(&sbi->stat_lock); + return -EINVAL; + } + *ui = t; + spin_unlock(&sbi->stat_lock); + return count; + } + + if (!strcmp(a->attr.name, "discard_granularity")) { + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + int i; + + if (t == 0 || t > MAX_PLIST_NUM) + return -EINVAL; + if (t == *ui) + return count; + + mutex_lock(&dcc->cmd_lock); + for (i = 0; i < MAX_PLIST_NUM; i++) { + if (i >= t - 1) + dcc->pend_list_tag[i] |= P_ACTIVE; + else + dcc->pend_list_tag[i] &= (~P_ACTIVE); + } + mutex_unlock(&dcc->cmd_lock); + + *ui = t; + return count; + } + + *ui = t; + + if (!strcmp(a->attr.name, "iostat_enable") && *ui == 0) + f2fs_reset_iostat(sbi); + if (!strcmp(a->attr.name, "gc_urgent") && t == 1 && sbi->gc_thread) { + sbi->gc_thread->gc_wake = 1; + wake_up_interruptible_all(&sbi->gc_thread->gc_wait_queue_head); + wake_up_discard_thread(sbi, true); + } + + return count; +} + +static ssize_t f2fs_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->show ? a->show(a, sbi, buf) : 0; +} + +static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr); + + return a->store ? a->store(a, sbi, buf, len) : 0; +} + +static void f2fs_sb_release(struct kobject *kobj) +{ + struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info, + s_kobj); + complete(&sbi->s_kobj_unregister); +} + +enum feat_id { + FEAT_CRYPTO = 0, + FEAT_BLKZONED, + FEAT_ATOMIC_WRITE, + FEAT_EXTRA_ATTR, + FEAT_PROJECT_QUOTA, + FEAT_INODE_CHECKSUM, +}; + +static ssize_t f2fs_feature_show(struct f2fs_attr *a, + struct f2fs_sb_info *sbi, char *buf) +{ + switch (a->id) { + case FEAT_CRYPTO: + case FEAT_BLKZONED: + case FEAT_ATOMIC_WRITE: + case FEAT_EXTRA_ATTR: + case FEAT_PROJECT_QUOTA: + case FEAT_INODE_CHECKSUM: + return snprintf(buf, PAGE_SIZE, "supported\n"); + } + return 0; +} + +#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \ +static struct f2fs_attr f2fs_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = _mode }, \ + .show = _show, \ + .store = _store, \ + .struct_type = _struct_type, \ + .offset = _offset \ +} + +#define F2FS_RW_ATTR(struct_type, struct_name, name, elname) \ + F2FS_ATTR_OFFSET(struct_type, name, 0644, \ + f2fs_sbi_show, f2fs_sbi_store, \ + offsetof(struct struct_name, elname)) + +#define F2FS_GENERAL_RO_ATTR(name) \ +static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL) + +#define F2FS_FEATURE_RO_ATTR(_name, _id) \ +static struct f2fs_attr f2fs_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = 0444 }, \ + .show = f2fs_feature_show, \ + .id = _id, \ +} + +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time, + urgent_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle); +F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent, gc_urgent); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); +F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards); +F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity); +F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); +F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); +F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); +#ifdef CONFIG_F2FS_FAULT_INJECTION +F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate); +F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); +#endif +F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes); +F2FS_GENERAL_RO_ATTR(features); + +#ifdef CONFIG_F2FS_FS_ENCRYPTION +F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); +#endif +#ifdef CONFIG_BLK_DEV_ZONED +F2FS_FEATURE_RO_ATTR(block_zoned, FEAT_BLKZONED); +#endif +F2FS_FEATURE_RO_ATTR(atomic_write, FEAT_ATOMIC_WRITE); +F2FS_FEATURE_RO_ATTR(extra_attr, FEAT_EXTRA_ATTR); +F2FS_FEATURE_RO_ATTR(project_quota, FEAT_PROJECT_QUOTA); +F2FS_FEATURE_RO_ATTR(inode_checksum, FEAT_INODE_CHECKSUM); + +#define ATTR_LIST(name) (&f2fs_attr_##name.attr) +static struct attribute *f2fs_attrs[] = { + ATTR_LIST(gc_urgent_sleep_time), + ATTR_LIST(gc_min_sleep_time), + ATTR_LIST(gc_max_sleep_time), + ATTR_LIST(gc_no_gc_sleep_time), + ATTR_LIST(gc_idle), + ATTR_LIST(gc_urgent), + ATTR_LIST(reclaim_segments), + ATTR_LIST(max_small_discards), + ATTR_LIST(discard_granularity), + ATTR_LIST(batched_trim_sections), + ATTR_LIST(ipu_policy), + ATTR_LIST(min_ipu_util), + ATTR_LIST(min_fsync_blocks), + ATTR_LIST(min_hot_blocks), + ATTR_LIST(max_victim_search), + ATTR_LIST(dir_level), + ATTR_LIST(ram_thresh), + ATTR_LIST(ra_nid_pages), + ATTR_LIST(dirty_nats_ratio), + ATTR_LIST(cp_interval), + ATTR_LIST(idle_interval), + ATTR_LIST(iostat_enable), +#ifdef CONFIG_F2FS_FAULT_INJECTION + ATTR_LIST(inject_rate), + ATTR_LIST(inject_type), +#endif + ATTR_LIST(lifetime_write_kbytes), + ATTR_LIST(features), + ATTR_LIST(reserved_blocks), + NULL, +}; + +static struct attribute *f2fs_feat_attrs[] = { +#ifdef CONFIG_F2FS_FS_ENCRYPTION + ATTR_LIST(encryption), +#endif +#ifdef CONFIG_BLK_DEV_ZONED + ATTR_LIST(block_zoned), +#endif + ATTR_LIST(atomic_write), + ATTR_LIST(extra_attr), + ATTR_LIST(project_quota), + ATTR_LIST(inode_checksum), + NULL, +}; + +static const struct sysfs_ops f2fs_attr_ops = { + .show = f2fs_attr_show, + .store = f2fs_attr_store, +}; + +static struct kobj_type f2fs_sb_ktype = { + .default_attrs = f2fs_attrs, + .sysfs_ops = &f2fs_attr_ops, + .release = f2fs_sb_release, +}; + +static struct kobj_type f2fs_ktype = { + .sysfs_ops = &f2fs_attr_ops, +}; + +static struct kset f2fs_kset = { + .kobj = {.ktype = &f2fs_ktype}, +}; + +static struct kobj_type f2fs_feat_ktype = { + .default_attrs = f2fs_feat_attrs, + .sysfs_ops = &f2fs_attr_ops, +}; + +static struct kobject f2fs_feat = { + .kset = &f2fs_kset, +}; + +static int segment_info_seq_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + unsigned int total_segs = + le32_to_cpu(sbi->raw_super->segment_count_main); + int i; + + seq_puts(seq, "format: segment_type|valid_blocks\n" + "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); + + for (i = 0; i < total_segs; i++) { + struct seg_entry *se = get_seg_entry(sbi, i); + + if ((i % 10) == 0) + seq_printf(seq, "%-10d", i); + seq_printf(seq, "%d|%-3u", se->type, + get_valid_blocks(sbi, i, false)); + if ((i % 10) == 9 || i == (total_segs - 1)) + seq_putc(seq, '\n'); + else + seq_putc(seq, ' '); + } + + return 0; +} + +static int segment_bits_seq_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + unsigned int total_segs = + le32_to_cpu(sbi->raw_super->segment_count_main); + int i, j; + + seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n" + "segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n"); + + for (i = 0; i < total_segs; i++) { + struct seg_entry *se = get_seg_entry(sbi, i); + + seq_printf(seq, "%-10d", i); + seq_printf(seq, "%d|%-3u|", se->type, + get_valid_blocks(sbi, i, false)); + for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++) + seq_printf(seq, " %.2x", se->cur_valid_map[j]); + seq_putc(seq, '\n'); + } + return 0; +} + +static int iostat_info_seq_show(struct seq_file *seq, void *offset) +{ + struct super_block *sb = seq->private; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + time64_t now = ktime_get_real_seconds(); + + if (!sbi->iostat_enable) + return 0; + + seq_printf(seq, "time: %-16llu\n", now); + + /* print app IOs */ + seq_printf(seq, "app buffered: %-16llu\n", + sbi->write_iostat[APP_BUFFERED_IO]); + seq_printf(seq, "app direct: %-16llu\n", + sbi->write_iostat[APP_DIRECT_IO]); + seq_printf(seq, "app mapped: %-16llu\n", + sbi->write_iostat[APP_MAPPED_IO]); + + /* print fs IOs */ + seq_printf(seq, "fs data: %-16llu\n", + sbi->write_iostat[FS_DATA_IO]); + seq_printf(seq, "fs node: %-16llu\n", + sbi->write_iostat[FS_NODE_IO]); + seq_printf(seq, "fs meta: %-16llu\n", + sbi->write_iostat[FS_META_IO]); + seq_printf(seq, "fs gc data: %-16llu\n", + sbi->write_iostat[FS_GC_DATA_IO]); + seq_printf(seq, "fs gc node: %-16llu\n", + sbi->write_iostat[FS_GC_NODE_IO]); + seq_printf(seq, "fs cp data: %-16llu\n", + sbi->write_iostat[FS_CP_DATA_IO]); + seq_printf(seq, "fs cp node: %-16llu\n", + sbi->write_iostat[FS_CP_NODE_IO]); + seq_printf(seq, "fs cp meta: %-16llu\n", + sbi->write_iostat[FS_CP_META_IO]); + seq_printf(seq, "fs discard: %-16llu\n", + sbi->write_iostat[FS_DISCARD]); + + return 0; +} + +#define F2FS_PROC_FILE_DEF(_name) \ +static int _name##_open_fs(struct inode *inode, struct file *file) \ +{ \ + return single_open(file, _name##_seq_show, PDE_DATA(inode)); \ +} \ + \ +static const struct file_operations f2fs_seq_##_name##_fops = { \ + .open = _name##_open_fs, \ + .read = seq_read, \ + .llseek = seq_lseek, \ + .release = single_release, \ +}; + +F2FS_PROC_FILE_DEF(segment_info); +F2FS_PROC_FILE_DEF(segment_bits); +F2FS_PROC_FILE_DEF(iostat_info); + +int __init f2fs_init_sysfs(void) +{ + int ret; + + kobject_set_name(&f2fs_kset.kobj, "f2fs"); + f2fs_kset.kobj.parent = fs_kobj; + ret = kset_register(&f2fs_kset); + if (ret) + return ret; + + ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype, + NULL, "features"); + if (ret) + kset_unregister(&f2fs_kset); + else + f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); + return ret; +} + +void f2fs_exit_sysfs(void) +{ + kobject_put(&f2fs_feat); + kset_unregister(&f2fs_kset); + remove_proc_entry("fs/f2fs", NULL); + f2fs_proc_root = NULL; +} + +int f2fs_register_sysfs(struct f2fs_sb_info *sbi) +{ + struct super_block *sb = sbi->sb; + int err; + + sbi->s_kobj.kset = &f2fs_kset; + init_completion(&sbi->s_kobj_unregister); + err = kobject_init_and_add(&sbi->s_kobj, &f2fs_sb_ktype, NULL, + "%s", sb->s_id); + if (err) + return err; + + if (f2fs_proc_root) + sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); + + if (sbi->s_proc) { + proc_create_data("segment_info", S_IRUGO, sbi->s_proc, + &f2fs_seq_segment_info_fops, sb); + proc_create_data("segment_bits", S_IRUGO, sbi->s_proc, + &f2fs_seq_segment_bits_fops, sb); + proc_create_data("iostat_info", S_IRUGO, sbi->s_proc, + &f2fs_seq_iostat_info_fops, sb); + } + return 0; +} + +void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) +{ + if (sbi->s_proc) { + remove_proc_entry("iostat_info", sbi->s_proc); + remove_proc_entry("segment_info", sbi->s_proc); + remove_proc_entry("segment_bits", sbi->s_proc); + remove_proc_entry(sbi->sb->s_id, f2fs_proc_root); + } + kobject_del(&sbi->s_kobj); +} diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 832c5110abab..7c65540148f8 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -442,7 +442,7 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize, } else { struct dnode_of_data dn; set_new_dnode(&dn, inode, NULL, NULL, new_nid); - xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage); + xpage = new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { alloc_nid_failed(sbi, new_nid); return PTR_ERR(xpage); @@ -473,8 +473,10 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, if (len > F2FS_NAME_LEN) return -ERANGE; + down_read(&F2FS_I(inode)->i_xattr_sem); error = lookup_all_xattrs(inode, ipage, index, len, name, &entry, &base_addr); + up_read(&F2FS_I(inode)->i_xattr_sem); if (error) return error; @@ -503,7 +505,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) int error = 0; size_t rest = buffer_size; + down_read(&F2FS_I(inode)->i_xattr_sem); error = read_all_xattrs(inode, NULL, &base_addr); + up_read(&F2FS_I(inode)->i_xattr_sem); if (error) return error; @@ -686,7 +690,9 @@ int f2fs_setxattr(struct inode *inode, int index, const char *name, f2fs_lock_op(sbi); /* protect xattr_ver */ down_write(&F2FS_I(inode)->i_sem); + down_write(&F2FS_I(inode)->i_xattr_sem); err = __f2fs_setxattr(inode, index, name, value, size, ipage, flags); + up_write(&F2FS_I(inode)->i_xattr_sem); up_write(&F2FS_I(inode)->i_sem); f2fs_unlock_op(sbi); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 1d9a8c4e9de0..48b2336692f9 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -309,7 +309,7 @@ static void mark_fsinfo_dirty(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); - if (sb->s_flags & MS_RDONLY || sbi->fat_bits != 32) + if (sb_rdonly(sb) || sbi->fat_bits != 32) return; __mark_inode_dirty(sbi->fsinfo_inode, I_DIRTY_SYNC); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index a2c05f2ada6d..30c52394a7ad 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -657,7 +657,7 @@ static void fat_set_state(struct super_block *sb, struct msdos_sb_info *sbi = MSDOS_SB(sb); /* do not change any thing if mounted read only */ - if ((sb->s_flags & MS_RDONLY) && !force) + if (sb_rdonly(sb) && !force) return; /* do not change state if fs was dirty */ @@ -787,7 +787,7 @@ static int fat_remount(struct super_block *sb, int *flags, char *data) /* make sure we update state on remount. */ new_rdonly = *flags & MS_RDONLY; - if (new_rdonly != (sb->s_flags & MS_RDONLY)) { + if (new_rdonly != sb_rdonly(sb)) { if (new_rdonly) fat_set_state(sb, 0, 0); else diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 8a8698119ff7..acc3aa30ee54 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -32,7 +32,7 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) if (opts->errors == FAT_ERRORS_PANIC) panic("FAT-fs (%s): fs panic from previous error\n", sb->s_id); - else if (opts->errors == FAT_ERRORS_RO && !(sb->s_flags & MS_RDONLY)) { + else if (opts->errors == FAT_ERRORS_RO && !sb_rdonly(sb)) { sb->s_flags |= MS_RDONLY; fat_msg(sb, KERN_ERR, "Filesystem has been set read-only"); } diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 6a7152d0c250..02c066663a3a 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -19,6 +19,8 @@ #include <linux/ctype.h> #include <linux/slab.h> #include <linux/namei.h> +#include <linux/kernel.h> + #include "fat.h" static inline unsigned long vfat_d_version(struct dentry *dentry) @@ -510,10 +512,8 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, struct nls_table *nls) { const unsigned char *ip; - unsigned char nc; unsigned char *op; - unsigned int ec; - int i, k, fill; + int i, fill; int charlen; if (utf8) { @@ -530,33 +530,22 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, i < len && *outlen < FAT_LFN_LEN; *outlen += 1) { if (escape && (*ip == ':')) { + u8 uc[2]; + if (i > len - 5) return -EINVAL; - ec = 0; - for (k = 1; k < 5; k++) { - nc = ip[k]; - ec <<= 4; - if (nc >= '0' && nc <= '9') { - ec |= nc - '0'; - continue; - } - if (nc >= 'a' && nc <= 'f') { - ec |= nc - ('a' - 10); - continue; - } - if (nc >= 'A' && nc <= 'F') { - ec |= nc - ('A' - 10); - continue; - } + + if (hex2bin(uc, ip + 1, 2) < 0) return -EINVAL; - } - *op++ = ec & 0xFF; - *op++ = ec >> 8; + + *(wchar_t *)op = uc[0] << 8 | uc[1]; + + op += 2; ip += 5; i += 5; } else { charlen = nls->char2uni(ip, len - i, - (wchar_t *)op); + (wchar_t *)op); if (charlen < 0) return -EINVAL; ip += charlen; diff --git a/fs/fcntl.c b/fs/fcntl.c index f4e7267d117f..448a1119f0be 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -109,20 +109,34 @@ void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, } EXPORT_SYMBOL(__f_setown); -void f_setown(struct file *filp, unsigned long arg, int force) +int f_setown(struct file *filp, unsigned long arg, int force) { enum pid_type type; - struct pid *pid; - int who = arg; + struct pid *pid = NULL; + int who = arg, ret = 0; + type = PIDTYPE_PID; if (who < 0) { + /* avoid overflow below */ + if (who == INT_MIN) + return -EINVAL; + type = PIDTYPE_PGID; who = -who; } + rcu_read_lock(); - pid = find_vpid(who); - __f_setown(filp, pid, type, force); + if (who) { + pid = find_vpid(who); + if (!pid) + ret = -ESRCH; + } + + if (!ret) + __f_setown(filp, pid, type, force); rcu_read_unlock(); + + return ret; } EXPORT_SYMBOL(f_setown); @@ -243,9 +257,72 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) } #endif +static bool rw_hint_valid(enum rw_hint hint) +{ + switch (hint) { + case RWF_WRITE_LIFE_NOT_SET: + case RWH_WRITE_LIFE_NONE: + case RWH_WRITE_LIFE_SHORT: + case RWH_WRITE_LIFE_MEDIUM: + case RWH_WRITE_LIFE_LONG: + case RWH_WRITE_LIFE_EXTREME: + return true; + default: + return false; + } +} + +static long fcntl_rw_hint(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct inode *inode = file_inode(file); + u64 *argp = (u64 __user *)arg; + enum rw_hint hint; + u64 h; + + switch (cmd) { + case F_GET_FILE_RW_HINT: + h = file_write_hint(file); + if (copy_to_user(argp, &h, sizeof(*argp))) + return -EFAULT; + return 0; + case F_SET_FILE_RW_HINT: + if (copy_from_user(&h, argp, sizeof(h))) + return -EFAULT; + hint = (enum rw_hint) h; + if (!rw_hint_valid(hint)) + return -EINVAL; + + spin_lock(&file->f_lock); + file->f_write_hint = hint; + spin_unlock(&file->f_lock); + return 0; + case F_GET_RW_HINT: + h = inode->i_write_hint; + if (copy_to_user(argp, &h, sizeof(*argp))) + return -EFAULT; + return 0; + case F_SET_RW_HINT: + if (copy_from_user(&h, argp, sizeof(h))) + return -EFAULT; + hint = (enum rw_hint) h; + if (!rw_hint_valid(hint)) + return -EINVAL; + + inode_lock(inode); + inode->i_write_hint = hint; + inode_unlock(inode); + return 0; + default: + return -EINVAL; + } +} + static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { + void __user *argp = (void __user *)arg; + struct flock flock; long err = -EINVAL; switch (cmd) { @@ -273,7 +350,11 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_OFD_GETLK: #endif case F_GETLK: - err = fcntl_getlk(filp, cmd, (struct flock __user *) arg); + if (copy_from_user(&flock, argp, sizeof(flock))) + return -EFAULT; + err = fcntl_getlk(filp, cmd, &flock); + if (!err && copy_to_user(argp, &flock, sizeof(flock))) + return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ @@ -283,7 +364,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, /* Fallthrough */ case F_SETLK: case F_SETLKW: - err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg); + if (copy_from_user(&flock, argp, sizeof(flock))) + return -EFAULT; + err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* @@ -297,8 +380,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, force_successful_syscall_return(); break; case F_SETOWN: - f_setown(filp, arg, 1); - err = 0; + err = f_setown(filp, arg, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); @@ -337,6 +419,12 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_GET_SEALS: err = shmem_fcntl(filp, cmd, arg); break; + case F_GET_RW_HINT: + case F_SET_RW_HINT: + case F_GET_FILE_RW_HINT: + case F_SET_FILE_RW_HINT: + err = fcntl_rw_hint(filp, cmd, arg); + break; default: break; } @@ -383,7 +471,9 @@ out: SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { + void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); + struct flock64 flock; long err = -EBADF; if (!f.file) @@ -401,14 +491,21 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, switch (cmd) { case F_GETLK64: case F_OFD_GETLK: - err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg); + err = -EFAULT; + if (copy_from_user(&flock, argp, sizeof(flock))) + break; + err = fcntl_getlk64(f.file, cmd, &flock); + if (!err && copy_to_user(argp, &flock, sizeof(flock))) + err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: - err = fcntl_setlk64(fd, f.file, cmd, - (struct flock64 __user *) arg); + err = -EFAULT; + if (copy_from_user(&flock, argp, sizeof(flock))) + break; + err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); @@ -422,57 +519,56 @@ out: #endif #ifdef CONFIG_COMPAT -static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) -{ - if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || - __get_user(kfl->l_type, &ufl->l_type) || - __get_user(kfl->l_whence, &ufl->l_whence) || - __get_user(kfl->l_start, &ufl->l_start) || - __get_user(kfl->l_len, &ufl->l_len) || - __get_user(kfl->l_pid, &ufl->l_pid)) +/* careful - don't use anywhere else */ +#define copy_flock_fields(dst, src) \ + (dst)->l_type = (src)->l_type; \ + (dst)->l_whence = (src)->l_whence; \ + (dst)->l_start = (src)->l_start; \ + (dst)->l_len = (src)->l_len; \ + (dst)->l_pid = (src)->l_pid; + +static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) +{ + struct compat_flock fl; + + if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; + copy_flock_fields(kfl, &fl); return 0; } -static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) +static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { - if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || - __put_user(kfl->l_type, &ufl->l_type) || - __put_user(kfl->l_whence, &ufl->l_whence) || - __put_user(kfl->l_start, &ufl->l_start) || - __put_user(kfl->l_len, &ufl->l_len) || - __put_user(kfl->l_pid, &ufl->l_pid)) + struct compat_flock64 fl; + + if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; + copy_flock_fields(kfl, &fl); return 0; } -#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64 -static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) +static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { - if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || - __get_user(kfl->l_type, &ufl->l_type) || - __get_user(kfl->l_whence, &ufl->l_whence) || - __get_user(kfl->l_start, &ufl->l_start) || - __get_user(kfl->l_len, &ufl->l_len) || - __get_user(kfl->l_pid, &ufl->l_pid)) + struct compat_flock fl; + + memset(&fl, 0, sizeof(struct compat_flock)); + copy_flock_fields(&fl, kfl); + if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } -#endif -#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64 -static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl) +static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { - if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) || - __put_user(kfl->l_type, &ufl->l_type) || - __put_user(kfl->l_whence, &ufl->l_whence) || - __put_user(kfl->l_start, &ufl->l_start) || - __put_user(kfl->l_len, &ufl->l_len) || - __put_user(kfl->l_pid, &ufl->l_pid)) + struct compat_flock64 fl; + + memset(&fl, 0, sizeof(struct compat_flock64)); + copy_flock_fields(&fl, kfl); + if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } -#endif +#undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) @@ -489,76 +585,92 @@ convert_fcntl_cmd(unsigned int cmd) return cmd; } +/* + * GETLK was successful and we need to return the data, but it needs to fit in + * the compat structure. + * l_start shouldn't be too big, unless the original start + end is greater than + * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return + * -EOVERFLOW in that case. l_len could be too big, in which case we just + * truncate it, and only allow the app to see that part of the conflicting lock + * that might make sense to it anyway + */ +static int fixup_compat_flock(struct flock *flock) +{ + if (flock->l_start > COMPAT_OFF_T_MAX) + return -EOVERFLOW; + if (flock->l_len > COMPAT_OFF_T_MAX) + flock->l_len = COMPAT_OFF_T_MAX; + return 0; +} + COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { - mm_segment_t old_fs; - struct flock f; - long ret; - unsigned int conv_cmd; + struct fd f = fdget_raw(fd); + struct flock flock; + long err = -EBADF; + + if (!f.file) + return err; + + if (unlikely(f.file->f_mode & FMODE_PATH)) { + if (!check_fcntl_cmd(cmd)) + goto out_put; + } + + err = security_file_fcntl(f.file, cmd, arg); + if (err) + goto out_put; switch (cmd) { case F_GETLK: + err = get_compat_flock(&flock, compat_ptr(arg)); + if (err) + break; + err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); + if (err) + break; + err = fixup_compat_flock(&flock); + if (err) + return err; + err = put_compat_flock(&flock, compat_ptr(arg)); + break; + case F_GETLK64: + case F_OFD_GETLK: + err = get_compat_flock64(&flock, compat_ptr(arg)); + if (err) + break; + err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); + if (err) + break; + err = fixup_compat_flock(&flock); + if (err) + return err; + err = put_compat_flock64(&flock, compat_ptr(arg)); + break; case F_SETLK: case F_SETLKW: - ret = get_compat_flock(&f, compat_ptr(arg)); - if (ret != 0) + err = get_compat_flock(&flock, compat_ptr(arg)); + if (err) break; - old_fs = get_fs(); - set_fs(KERNEL_DS); - ret = sys_fcntl(fd, cmd, (unsigned long)&f); - set_fs(old_fs); - if (cmd == F_GETLK && ret == 0) { - /* GETLK was successful and we need to return the data... - * but it needs to fit in the compat structure. - * l_start shouldn't be too big, unless the original - * start + end is greater than COMPAT_OFF_T_MAX, in which - * case the app was asking for trouble, so we return - * -EOVERFLOW in that case. - * l_len could be too big, in which case we just truncate it, - * and only allow the app to see that part of the conflicting - * lock that might make sense to it anyway - */ - - if (f.l_start > COMPAT_OFF_T_MAX) - ret = -EOVERFLOW; - if (f.l_len > COMPAT_OFF_T_MAX) - f.l_len = COMPAT_OFF_T_MAX; - if (ret == 0) - ret = put_compat_flock(&f, compat_ptr(arg)); - } + err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; - - case F_GETLK64: case F_SETLK64: case F_SETLKW64: - case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: - ret = get_compat_flock64(&f, compat_ptr(arg)); - if (ret != 0) + err = get_compat_flock64(&flock, compat_ptr(arg)); + if (err) break; - old_fs = get_fs(); - set_fs(KERNEL_DS); - conv_cmd = convert_fcntl_cmd(cmd); - ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); - set_fs(old_fs); - if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) { - /* need to return lock information - see above for commentary */ - if (f.l_start > COMPAT_LOFF_T_MAX) - ret = -EOVERFLOW; - if (f.l_len > COMPAT_LOFF_T_MAX) - f.l_len = COMPAT_LOFF_T_MAX; - if (ret == 0) - ret = put_compat_flock64(&f, compat_ptr(arg)); - } + err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; - default: - ret = sys_fcntl(fd, cmd, arg); + err = do_fcntl(fd, cmd, arg, f.file); break; } - return ret; +out_put: + fdput(f); + return err; } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, @@ -629,10 +741,21 @@ static void send_sigio_to_task(struct task_struct *p, si.si_signo = signum; si.si_errno = 0; si.si_code = reason; + /* + * Posix definies POLL_IN and friends to be signal + * specific si_codes for SIG_POLL. Linux extended + * these si_codes to other signals in a way that is + * ambiguous if other signals also have signal + * specific si_codes. In that case use SI_SIGIO instead + * to remove the ambiguity. + */ + if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) + si.si_code = SI_SIGIO; + /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ - BUG_ON((reason & __SI_MASK) != __SI_POLL); + BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else diff --git a/fs/file.c b/fs/file.c index 1c2972e3a405..1fc7fbbb4510 100644 --- a/fs/file.c +++ b/fs/file.c @@ -30,21 +30,6 @@ unsigned int sysctl_nr_open_min = BITS_PER_LONG; unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; -static void *alloc_fdmem(size_t size) -{ - /* - * Very large allocations can stress page reclaim, so fall back to - * vmalloc() if the allocation size will be considered "large" by the VM. - */ - if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { - void *data = kmalloc(size, GFP_KERNEL_ACCOUNT | - __GFP_NOWARN | __GFP_NORETRY); - if (data != NULL) - return data; - } - return __vmalloc(size, GFP_KERNEL_ACCOUNT, PAGE_KERNEL); -} - static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); @@ -131,13 +116,14 @@ static struct fdtable * alloc_fdtable(unsigned int nr) if (!fdt) goto out; fdt->max_fds = nr; - data = alloc_fdmem(nr * sizeof(struct file *)); + data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; - data = alloc_fdmem(max_t(size_t, - 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES)); + data = kvmalloc(max_t(size_t, + 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), + GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; diff --git a/fs/file_table.c b/fs/file_table.c index 954d510b765a..61517f57f8ef 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -168,6 +168,7 @@ struct file *alloc_file(const struct path *path, fmode_t mode, file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; + file->f_wb_err = filemap_sample_wb_err(file->f_mapping); if ((mode & FMODE_READ) && likely(fop->read || fop->read_iter)) mode |= FMODE_CAN_READ; @@ -232,12 +233,10 @@ static LLIST_HEAD(delayed_fput_list); static void delayed_fput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_fput_list); - struct llist_node *next; + struct file *f, *t; - for (; node; node = next) { - next = llist_next(node); - __fput(llist_entry(node, struct file, f_u.fu_llist)); - } + llist_for_each_entry_safe(f, t, node, f_u.fu_llist) + __fput(f); } static void ____fput(struct callback_head *work) @@ -311,7 +310,7 @@ void put_filp(struct file *file) } void __init files_init(void) -{ +{ filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); percpu_counter_init(&nr_files, 0, GFP_KERNEL); @@ -330,4 +329,4 @@ void __init files_maxfiles_init(void) n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); -} +} diff --git a/fs/filesystems.c b/fs/filesystems.c index cac75547d35c..a920ad2629ac 100644 --- a/fs/filesystems.c +++ b/fs/filesystems.c @@ -33,9 +33,10 @@ static struct file_system_type *file_systems; static DEFINE_RWLOCK(file_systems_lock); /* WARNING: This can be used only if we _already_ own a reference */ -void get_filesystem(struct file_system_type *fs) +struct file_system_type *get_filesystem(struct file_system_type *fs) { __module_get(fs->owner); + return fs; } void put_filesystem(struct file_system_type *fs) @@ -275,8 +276,10 @@ struct file_system_type *get_fs_type(const char *name) int len = dot ? dot - name : strlen(name); fs = __get_fs_type(name, len); - if (!fs && (request_module("fs-%.*s", len, name) == 0)) + if (!fs && (request_module("fs-%.*s", len, name) == 0)) { fs = __get_fs_type(name, len); + WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name); + } if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) { put_filesystem(fs); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 63ee2940775c..245c430a2e41 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -380,8 +380,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct page *page = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (likely(page) && PageDirty(page)) { - __dec_wb_stat(old_wb, WB_RECLAIMABLE); - __inc_wb_stat(new_wb, WB_RECLAIMABLE); + dec_wb_stat(old_wb, WB_RECLAIMABLE); + inc_wb_stat(new_wb, WB_RECLAIMABLE); } } @@ -391,8 +391,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) &mapping->tree_lock); if (likely(page)) { WARN_ON_ONCE(!PageWriteback(page)); - __dec_wb_stat(old_wb, WB_WRITEBACK); - __inc_wb_stat(new_wb, WB_WRITEBACK); + dec_wb_stat(old_wb, WB_WRITEBACK); + inc_wb_stat(new_wb, WB_WRITEBACK); } } @@ -2052,11 +2052,13 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode) } /** - * __mark_inode_dirty - internal function - * @inode: inode to mark - * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) - * Mark an inode as dirty. Callers should use mark_inode_dirty or - * mark_inode_dirty_sync. + * __mark_inode_dirty - internal function + * + * @inode: inode to mark + * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) + * + * Mark an inode as dirty. Callers should use mark_inode_dirty or + * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * diff --git a/fs/fs_pin.c b/fs/fs_pin.c index 611b5408f6ec..e747b3d720ee 100644 --- a/fs/fs_pin.c +++ b/fs/fs_pin.c @@ -34,7 +34,7 @@ void pin_insert(struct fs_pin *pin, struct vfsmount *m) void pin_kill(struct fs_pin *p) { - wait_queue_t wait; + wait_queue_entry_t wait; if (!p) { rcu_read_unlock(); @@ -61,7 +61,7 @@ void pin_kill(struct fs_pin *p) rcu_read_unlock(); schedule(); rcu_read_lock(); - if (likely(list_empty(&wait.task_list))) + if (likely(list_empty(&wait.entry))) break; /* OK, we know p couldn't have been freed yet */ spin_lock_irq(&p->wait.lock); diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 67f940892ef8..0438d4cd91ef 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -262,7 +262,8 @@ static int fscache_objlist_show(struct seq_file *m, void *v) type = "DT"; break; default: - sprintf(_type, "%02u", cookie->def->type); + snprintf(_type, sizeof(_type), "%02u", + cookie->def->type); type = _type; break; } @@ -330,6 +331,13 @@ static void fscache_objlist_config(struct fscache_objlist_data *data) rcu_read_lock(); confkey = user_key_payload_rcu(key); + if (!confkey) { + /* key was revoked */ + rcu_read_unlock(); + key_put(key); + goto no_config; + } + buf = confkey->data; for (len = confkey->datalen - 1; len >= 0; len--) { diff --git a/fs/fscache/page.c b/fs/fscache/page.c index c8c4f79c7ce1..0ad3fd3ad0b4 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -1178,11 +1178,10 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, pagevec_init(&pvec, 0); next = 0; do { - if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) + if (!pagevec_lookup(&pvec, mapping, &next)) break; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; - next = page->index; if (PageFsCache(page)) { __fscache_wait_on_page_write(cookie, page); __fscache_uncache_page(cookie, page); @@ -1190,7 +1189,7 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, } pagevec_release(&pvec); cond_resched(); - } while (++next); + } while (next); _leave(""); } diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index c5b6b7165489..e9e97803442a 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -90,7 +90,7 @@ static struct list_head *cuse_conntbl_head(dev_t devt) static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to) { - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp); + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb); loff_t pos = 0; return fuse_direct_io(&io, to, &pos, FUSE_DIO_CUSE); @@ -98,7 +98,7 @@ static ssize_t cuse_read_iter(struct kiocb *kiocb, struct iov_iter *to) static ssize_t cuse_write_iter(struct kiocb *kiocb, struct iov_iter *from) { - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb->ki_filp); + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(kiocb); loff_t pos = 0; /* * No locking or generic_write_checks(), the server is diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c16d00e53264..13c65dd2d37d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1222,9 +1222,6 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, struct fuse_in *in; unsigned reqsize; - if (task_active_pid_ns(current) != fc->pid_ns) - return -EIO; - restart: spin_lock(&fiq->waitq.lock); err = -EAGAIN; @@ -1262,6 +1259,13 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, in = &req->in; reqsize = in->h.len; + + if (task_active_pid_ns(current) != fc->pid_ns) { + rcu_read_lock(); + in->h.pid = pid_vnr(find_pid_ns(in->h.pid, fc->pid_ns)); + rcu_read_unlock(); + } + /* If request is too large, reply with an error and restart the read */ if (nbytes < reqsize) { req->out.h.error = -EIO; @@ -1823,9 +1827,6 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, struct fuse_req *req; struct fuse_out_header oh; - if (task_active_pid_ns(current) != fc->pid_ns) - return -EIO; - if (nbytes < sizeof(struct fuse_out_header)) return -EINVAL; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 00800c07ba1c..622081b97426 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -923,33 +923,29 @@ static int fuse_do_getattr(struct inode *inode, struct kstat *stat, return err; } -int fuse_update_attributes(struct inode *inode, struct kstat *stat, - struct file *file, bool *refreshed) +static int fuse_update_get_attr(struct inode *inode, struct file *file, + struct kstat *stat) { struct fuse_inode *fi = get_fuse_inode(inode); - int err; - bool r; + int err = 0; if (time_before64(fi->i_time, get_jiffies_64())) { - r = true; forget_all_cached_acls(inode); err = fuse_do_getattr(inode, stat, file); - } else { - r = false; - err = 0; - if (stat) { - generic_fillattr(inode, stat); - stat->mode = fi->orig_i_mode; - stat->ino = fi->orig_ino; - } + } else if (stat) { + generic_fillattr(inode, stat); + stat->mode = fi->orig_i_mode; + stat->ino = fi->orig_ino; } - if (refreshed != NULL) - *refreshed = r; - return err; } +int fuse_update_attributes(struct inode *inode, struct file *file) +{ + return fuse_update_get_attr(inode, file, NULL); +} + int fuse_reverse_inval_entry(struct super_block *sb, u64 parent_nodeid, u64 child_nodeid, struct qstr *name) { @@ -1786,7 +1782,7 @@ static int fuse_getattr(const struct path *path, struct kstat *stat, if (!fuse_allow_current_process(fc)) return -EACCES; - return fuse_update_attributes(inode, stat, NULL, NULL); + return fuse_update_get_attr(inode, NULL, stat); } static const struct inode_operations fuse_dir_inode_operations = { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 3ee4fdc3da9e..cb7dff5c45d7 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc) { struct fuse_file *ff; - ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL); + ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL); if (unlikely(!ff)) return NULL; @@ -457,7 +457,7 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, * wait for all outstanding writes, before sending the FSYNC * request. */ - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(file, start, end); if (err) goto out; @@ -465,10 +465,10 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, /* * Due to implementation of fuse writeback - * filemap_write_and_wait_range() does not catch errors. + * file_write_and_wait_range() does not catch errors. * We have to do this directly after fuse_sync_writes() */ - err = filemap_check_errors(file->f_mapping); + err = file_check_and_advance_wb_err(file); if (err) goto out; @@ -609,7 +609,7 @@ static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req) struct fuse_io_priv *io = req->io; ssize_t pos = -1; - fuse_release_user_pages(req, !io->write); + fuse_release_user_pages(req, io->should_dirty); if (io->write) { if (req->misc.write.in.size != req->misc.write.out.size) @@ -645,7 +645,7 @@ static size_t fuse_async_req_send(struct fuse_conn *fc, struct fuse_req *req, static size_t fuse_send_read(struct fuse_req *req, struct fuse_io_priv *io, loff_t pos, size_t count, fl_owner_t owner) { - struct file *file = io->file; + struct file *file = io->iocb->ki_filp; struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fc; @@ -707,7 +707,8 @@ static void fuse_short_read(struct fuse_req *req, struct inode *inode, static int fuse_do_readpage(struct file *file, struct page *page) { - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file); + struct kiocb iocb; + struct fuse_io_priv io; struct inode *inode = page->mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_req *req; @@ -735,6 +736,8 @@ static int fuse_do_readpage(struct file *file, struct page *page) req->num_pages = 1; req->pages[0] = page; req->page_descs[0].length = count; + init_sync_kiocb(&iocb, file); + io = (struct fuse_io_priv) FUSE_IO_PRIV_SYNC(&iocb); num_read = fuse_send_read(req, &io, pos, count, NULL); err = req->out.h.error; @@ -923,7 +926,7 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (fc->auto_inval_data || (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) { int err; - err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL); + err = fuse_update_attributes(inode, iocb->ki_filp); if (err) return err; } @@ -957,13 +960,18 @@ static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff, static size_t fuse_send_write(struct fuse_req *req, struct fuse_io_priv *io, loff_t pos, size_t count, fl_owner_t owner) { - struct file *file = io->file; + struct kiocb *iocb = io->iocb; + struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fc; struct fuse_write_in *inarg = &req->misc.write.in; fuse_write_fill(req, ff, pos, count); inarg->flags = file->f_flags; + if (iocb->ki_flags & IOCB_DSYNC) + inarg->flags |= O_DSYNC; + if (iocb->ki_flags & IOCB_SYNC) + inarg->flags |= O_SYNC; if (owner != NULL) { inarg->write_flags |= FUSE_WRITE_LOCKOWNER; inarg->lock_owner = fuse_lock_owner_id(fc, owner); @@ -993,14 +1001,14 @@ bool fuse_write_update_size(struct inode *inode, loff_t pos) return ret; } -static size_t fuse_send_write_pages(struct fuse_req *req, struct file *file, +static size_t fuse_send_write_pages(struct fuse_req *req, struct kiocb *iocb, struct inode *inode, loff_t pos, size_t count) { size_t res; unsigned offset; unsigned i; - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file); + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); for (i = 0; i < req->num_pages; i++) fuse_wait_on_page_writeback(inode, req->pages[i]->index); @@ -1100,7 +1108,7 @@ static inline unsigned fuse_wr_pages(loff_t pos, size_t len) FUSE_MAX_PAGES_PER_REQ); } -static ssize_t fuse_perform_write(struct file *file, +static ssize_t fuse_perform_write(struct kiocb *iocb, struct address_space *mapping, struct iov_iter *ii, loff_t pos) { @@ -1133,7 +1141,7 @@ static ssize_t fuse_perform_write(struct file *file, } else { size_t num_written; - num_written = fuse_send_write_pages(req, file, inode, + num_written = fuse_send_write_pages(req, iocb, inode, pos, count); err = req->out.h.error; if (!err) { @@ -1169,7 +1177,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (get_fuse_conn(inode)->writeback_cache) { /* Update size (EOF optimization) and mode (SUID clearing) */ - err = fuse_update_attributes(mapping->host, NULL, file, NULL); + err = fuse_update_attributes(mapping->host, file); if (err) return err; @@ -1201,7 +1209,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) pos += written; - written_buffered = fuse_perform_write(file, mapping, from, pos); + written_buffered = fuse_perform_write(iocb, mapping, from, pos); if (written_buffered < 0) { err = written_buffered; goto out; @@ -1220,13 +1228,15 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) written += written_buffered; iocb->ki_pos = pos + written_buffered; } else { - written = fuse_perform_write(file, mapping, from, iocb->ki_pos); + written = fuse_perform_write(iocb, mapping, from, iocb->ki_pos); if (written >= 0) iocb->ki_pos += written; } out: current->backing_dev_info = NULL; inode_unlock(inode); + if (written > 0) + written = generic_write_sync(iocb, written); return written ? written : err; } @@ -1316,9 +1326,8 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; - bool should_dirty = !write && iter_is_iovec(iter); int cuse = flags & FUSE_DIO_CUSE; - struct file *file = io->file; + struct file *file = io->iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct fuse_file *ff = file->private_data; struct fuse_conn *fc = ff->fc; @@ -1346,6 +1355,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, inode_unlock(inode); } + io->should_dirty = !write && iter_is_iovec(iter); while (count) { size_t nres; fl_owner_t owner = current->files; @@ -1360,7 +1370,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, nres = fuse_send_read(req, io, pos, nbytes, owner); if (!io->async) - fuse_release_user_pages(req, should_dirty); + fuse_release_user_pages(req, io->should_dirty); if (req->out.h.error) { err = req->out.h.error; break; @@ -1399,8 +1409,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io, loff_t *ppos) { ssize_t res; - struct file *file = io->file; - struct inode *inode = file_inode(file); + struct inode *inode = file_inode(io->iocb->ki_filp); if (is_bad_inode(inode)) return -EIO; @@ -1414,15 +1423,14 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io, static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) { - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb->ki_filp); + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); return __fuse_direct_read(&io, to, &iocb->ki_pos); } static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) { - struct file *file = iocb->ki_filp; - struct inode *inode = file_inode(file); - struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(file); + struct inode *inode = file_inode(iocb->ki_filp); + struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); ssize_t res; if (is_bad_inode(inode)) @@ -1669,6 +1677,7 @@ err_nofile: err_free: fuse_request_free(req); err: + mapping_set_error(page->mapping, error); end_page_writeback(page); return error; } @@ -2101,11 +2110,11 @@ static int convert_fuse_file_lock(struct fuse_conn *fc, fl->fl_end = ffl->end; /* - * Convert pid into the caller's pid namespace. If the pid - * does not map into the namespace fl_pid will get set to 0. + * Convert pid into init's pid namespace. The locks API will + * translate it into the caller's pid namespace. */ rcu_read_lock(); - fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns)); + fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns); rcu_read_unlock(); break; @@ -2180,9 +2189,6 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock) if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX) return 0; - if (pid && pid_nr == 0) - return -EOVERFLOW; - fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg); err = fuse_simple_request(fc, &args); @@ -2302,7 +2308,7 @@ static loff_t fuse_lseek(struct file *file, loff_t offset, int whence) return vfs_setpos(file, outarg.offset, inode->i_sb->s_maxbytes); fallback: - err = fuse_update_attributes(inode, NULL, file, NULL); + err = fuse_update_attributes(inode, file); if (!err) return generic_file_llseek(file, offset, whence); else @@ -2322,7 +2328,7 @@ static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence) break; case SEEK_END: inode_lock(inode); - retval = fuse_update_attributes(inode, NULL, file, NULL); + retval = fuse_update_attributes(inode, file); if (!retval) retval = generic_file_llseek(file, offset, whence); inode_unlock(inode); @@ -2873,7 +2879,6 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) io->offset = offset; io->write = (iov_iter_rw(iter) == WRITE); io->err = 0; - io->file = file; /* * By default, we want to optimize all I/Os with async request * submission to the client filesystem if supported. diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1bd7ffdad593..d5773ca67ad2 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -249,18 +249,18 @@ struct fuse_io_priv { size_t size; __u64 offset; bool write; + bool should_dirty; int err; struct kiocb *iocb; - struct file *file; struct completion *done; bool blocking; }; -#define FUSE_IO_PRIV_SYNC(f) \ +#define FUSE_IO_PRIV_SYNC(i) \ { \ .refcnt = KREF_INIT(1), \ .async = 0, \ - .file = f, \ + .iocb = i, \ } /** @@ -904,8 +904,7 @@ u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id); void fuse_update_ctime(struct inode *inode); -int fuse_update_attributes(struct inode *inode, struct kstat *stat, - struct file *file, bool *refreshed); +int fuse_update_attributes(struct inode *inode, struct file *file); void fuse_flush_writepages(struct inode *inode); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 65c88379a3a1..94a745acaef8 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1059,7 +1059,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_flags & MS_MANDLOCK) goto err; - sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION); + sb->s_flags &= ~(MS_NOSEC | SB_I_VERSION); if (!parse_fuse_opt(data, &d, is_bdev)) goto err; diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 2524807ee070..9d5eecb123de 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -86,19 +86,6 @@ int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) char *data; const char *name = gfs2_acl_name(type); - if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) - return -E2BIG; - - if (type == ACL_TYPE_ACCESS) { - umode_t mode = inode->i_mode; - - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - if (mode != inode->i_mode) - mark_inode_dirty(inode); - } - if (acl) { len = posix_acl_to_xattr(&init_user_ns, acl, NULL, 0); if (len == 0) @@ -129,6 +116,10 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) struct gfs2_holder gh; bool need_unlock = false; int ret; + umode_t mode; + + if (acl && acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode))) + return -E2BIG; ret = gfs2_rsqa_alloc(ip); if (ret) @@ -140,7 +131,20 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type) return ret; need_unlock = true; } + + mode = inode->i_mode; + if (type == ACL_TYPE_ACCESS && acl) { + ret = posix_acl_update_mode(inode, &mode, &acl); + if (ret) + goto unlock; + } + ret = __gfs2_set_acl(inode, acl, type); + if (!ret && mode != inode->i_mode) { + inode->i_mode = mode; + mark_inode_dirty(inode); + } +unlock: if (need_unlock) gfs2_glock_dq_uninit(&gh); return ret; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index ed7a2e252ad8..68ed06962537 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -234,7 +234,19 @@ out: static int gfs2_writepages(struct address_space *mapping, struct writeback_control *wbc) { - return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc); + struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); + int ret = mpage_writepages(mapping, wbc, gfs2_get_block_noalloc); + + /* + * Even if we didn't write any pages here, we might still be holding + * dirty pages in the ail. We forcibly flush the ail because we don't + * want balance_dirty_pages() to loop indefinitely trying to write out + * pages held in the ail that it can't find. + */ + if (ret == 0) + set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags); + + return ret; } /** diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 4d810be532dd..3dd0cceefa43 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -291,8 +291,9 @@ static void gfs2_metapath_ra(struct gfs2_glock *gl, if (trylock_buffer(rabh)) { if (!buffer_uptodate(rabh)) { rabh->b_end_io = end_buffer_read_sync; - submit_bh(REQ_OP_READ, REQ_RAHEAD | REQ_META, - rabh); + submit_bh(REQ_OP_READ, + REQ_RAHEAD | REQ_META | REQ_PRIO, + rabh); continue; } unlock_buffer(rabh); @@ -970,7 +971,7 @@ more_rgrps: continue; bn = be64_to_cpu(*p); if (gfs2_holder_initialized(rd_gh)) { - rgd = (struct gfs2_rgrpd *)rd_gh->gh_gl->gl_object; + rgd = gfs2_glock2rgrp(rd_gh->gh_gl); gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(rd_gh->gh_gl)); } else { @@ -1103,8 +1104,15 @@ static bool find_nonnull_ptr(struct gfs2_sbd *sdp, struct metapath *mp, while (true) { ptr = metapointer(h, mp); - if (*ptr) /* if we have a non-null pointer */ + if (*ptr) { /* if we have a non-null pointer */ + /* Now zero the metapath after the current height. */ + h++; + if (h < GFS2_MAX_META_HEIGHT) + memset(&mp->mp_list[h], 0, + (GFS2_MAX_META_HEIGHT - h) * + sizeof(mp->mp_list[0])); return true; + } if (mp->mp_list[h] < ptrs) mp->mp_list[h]++; @@ -1120,6 +1128,13 @@ enum dealloc_states { DEALLOC_DONE = 3, /* process complete */ }; +static bool mp_eq_to_hgt(struct metapath *mp, __u16 *nbof, unsigned int h) +{ + if (memcmp(mp->mp_list, nbof, h * sizeof(mp->mp_list[0]))) + return false; + return true; +} + /** * trunc_dealloc - truncate a file down to a desired size * @ip: inode to truncate @@ -1197,8 +1212,7 @@ static int trunc_dealloc(struct gfs2_inode *ip, u64 newsize) /* If we're truncating to a non-zero size and the mp is at the beginning of file for the strip height, we need to preserve the first metadata pointer. */ - preserve1 = (newsize && - (mp.mp_list[mp_h] == nbof[mp_h])); + preserve1 = (newsize && mp_eq_to_hgt(&mp, nbof, mp_h)); bh = mp.mp_bh[mp_h]; gfs2_assert_withdraw(sdp, bh); if (gfs2_assert_withdraw(sdp, diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index 79113219be5f..06a0d1947c77 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -872,7 +872,6 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; - struct qstr name = { .name = "" }; struct timespec tv = current_time(inode); error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); @@ -896,7 +895,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, leaf->lf_sec = cpu_to_be64(tv.tv_sec); memset(leaf->lf_reserved2, 0, sizeof(leaf->lf_reserved2)); dent = (struct gfs2_dirent *)(leaf+1); - gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent); + gfs2_qstr2dirent(&empty_name, bh->b_size - sizeof(struct gfs2_leaf), dent); *pbh = bh; return leaf; } @@ -1444,7 +1443,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx, "g.offset (%u)\n", (unsigned long long)bh->b_blocknr, entries2, g.offset); - + gfs2_consist_inode(ip); error = -EIO; goto out_free; } @@ -1514,7 +1513,9 @@ static void gfs2_dir_readahead(struct inode *inode, unsigned hsize, u32 index, continue; } bh->b_end_io = end_buffer_read_sync; - submit_bh(REQ_OP_READ, REQ_RAHEAD | REQ_META, bh); + submit_bh(REQ_OP_READ, + REQ_RAHEAD | REQ_META | REQ_PRIO, + bh); continue; } brelse(bh); @@ -1612,6 +1613,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx, (unsigned long long)dip->i_no_addr, dip->i_entries, g.offset); + gfs2_consist_inode(dip); error = -EIO; goto out; } @@ -2031,8 +2033,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { - struct gfs2_rgrpd *rgd; - rgd = rlist.rl_ghs[x].gh_gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); + rg_blocks += rgd->rd_length; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index c2062a108d19..33a0cb5701a3 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -668,12 +668,14 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, if (ret) return ret; if (gfs2_is_jdata(ip)) - filemap_write_and_wait(mapping); + ret = file_write_and_wait(file); + if (ret) + return ret; gfs2_ail_flush(ip->i_gl, 1); } if (mapping->nrpages) - ret = filemap_fdatawait_range(mapping, start, end); + ret = file_fdatawait_range(file, start, end); return ret ? ret : ret1; } @@ -1030,8 +1032,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) mutex_lock(&fp->f_fl_mutex); - gl = fl_gh->gh_gl; - if (gl) { + if (gfs2_holder_initialized(fl_gh)) { if (fl_gh->gh_state == state) goto out; locks_lock_file_wait(file, diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 959a19ced4d5..11066d8647d2 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -15,6 +15,7 @@ #include <linux/buffer_head.h> #include <linux/delay.h> #include <linux/sort.h> +#include <linux/hash.h> #include <linux/jhash.h> #include <linux/kallsyms.h> #include <linux/gfs2_ondisk.h> @@ -71,7 +72,7 @@ static DEFINE_SPINLOCK(lru_lock); #define GFS2_GL_HASH_SHIFT 15 #define GFS2_GL_HASH_SIZE BIT(GFS2_GL_HASH_SHIFT) -static struct rhashtable_params ht_parms = { +static const struct rhashtable_params ht_parms = { .nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4, .key_len = offsetofend(struct lm_lockname, ln_type), .key_offset = offsetof(struct gfs2_glock, gl_name), @@ -80,9 +81,52 @@ static struct rhashtable_params ht_parms = { static struct rhashtable gl_hash_table; -void gfs2_glock_free(struct gfs2_glock *gl) +#define GLOCK_WAIT_TABLE_BITS 12 +#define GLOCK_WAIT_TABLE_SIZE (1 << GLOCK_WAIT_TABLE_BITS) +static wait_queue_head_t glock_wait_table[GLOCK_WAIT_TABLE_SIZE] __cacheline_aligned; + +struct wait_glock_queue { + struct lm_lockname *name; + wait_queue_entry_t wait; +}; + +static int glock_wake_function(wait_queue_entry_t *wait, unsigned int mode, + int sync, void *key) { - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct wait_glock_queue *wait_glock = + container_of(wait, struct wait_glock_queue, wait); + struct lm_lockname *wait_name = wait_glock->name; + struct lm_lockname *wake_name = key; + + if (wake_name->ln_sbd != wait_name->ln_sbd || + wake_name->ln_number != wait_name->ln_number || + wake_name->ln_type != wait_name->ln_type) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + +static wait_queue_head_t *glock_waitqueue(struct lm_lockname *name) +{ + u32 hash = jhash2((u32 *)name, sizeof(*name) / 4, 0); + + return glock_wait_table + hash_32(hash, GLOCK_WAIT_TABLE_BITS); +} + +/** + * wake_up_glock - Wake up waiters on a glock + * @gl: the glock + */ +static void wake_up_glock(struct gfs2_glock *gl) +{ + wait_queue_head_t *wq = glock_waitqueue(&gl->gl_name); + + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &gl->gl_name); +} + +static void gfs2_glock_dealloc(struct rcu_head *rcu) +{ + struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu); if (gl->gl_ops->go_flags & GLOF_ASPACE) { kmem_cache_free(gfs2_glock_aspace_cachep, gl); @@ -90,6 +134,16 @@ void gfs2_glock_free(struct gfs2_glock *gl) kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(gfs2_glock_cachep, gl); } +} + +void gfs2_glock_free(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); + smp_mb(); + wake_up_glock(gl); + call_rcu(&gl->gl_rcu, gfs2_glock_dealloc); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_glock_wait); } @@ -100,7 +154,7 @@ void gfs2_glock_free(struct gfs2_glock *gl) * */ -static void gfs2_glock_hold(struct gfs2_glock *gl) +void gfs2_glock_hold(struct gfs2_glock *gl) { GLOCK_BUG_ON(gl, __lockref_is_dead(&gl->gl_lockref)); lockref_get(&gl->gl_lockref); @@ -143,6 +197,9 @@ void gfs2_glock_add_to_lru(struct gfs2_glock *gl) static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) { + if (!(gl->gl_ops->go_flags & GLOF_LRU)) + return; + spin_lock(&lru_lock); if (!list_empty(&gl->gl_lru)) { list_del_init(&gl->gl_lru); @@ -152,31 +209,66 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl) spin_unlock(&lru_lock); } -/** - * gfs2_glock_put() - Decrement reference count on glock - * @gl: The glock to put - * +/* + * Enqueue the glock on the work queue. Passes one glock reference on to the + * work queue. */ +static void __gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) { + if (!queue_delayed_work(glock_workqueue, &gl->gl_work, delay)) { + /* + * We are holding the lockref spinlock, and the work was still + * queued above. The queued work (glock_work_func) takes that + * spinlock before dropping its glock reference(s), so it + * cannot have dropped them in the meantime. + */ + GLOCK_BUG_ON(gl, gl->gl_lockref.count < 2); + gl->gl_lockref.count--; + } +} -void gfs2_glock_put(struct gfs2_glock *gl) +static void gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) { + spin_lock(&gl->gl_lockref.lock); + __gfs2_glock_queue_work(gl, delay); + spin_unlock(&gl->gl_lockref.lock); +} + +static void __gfs2_glock_put(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *mapping = gfs2_glock2aspace(gl); - if (lockref_put_or_lock(&gl->gl_lockref)) - return; - lockref_mark_dead(&gl->gl_lockref); gfs2_glock_remove_from_lru(gl); spin_unlock(&gl->gl_lockref.lock); - rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders)); GLOCK_BUG_ON(gl, mapping && mapping->nrpages); trace_gfs2_glock_put(gl); sdp->sd_lockstruct.ls_ops->lm_put_lock(gl); } +/* + * Cause the glock to be put in work queue context. + */ +void gfs2_glock_queue_put(struct gfs2_glock *gl) +{ + gfs2_glock_queue_work(gl, 0); +} + +/** + * gfs2_glock_put() - Decrement reference count on glock + * @gl: The glock to put + * + */ + +void gfs2_glock_put(struct gfs2_glock *gl) +{ + if (lockref_put_or_lock(&gl->gl_lockref)) + return; + + __gfs2_glock_put(gl); +} + /** * may_grant - check if its ok to grant a new lock * @gl: The glock @@ -482,8 +574,7 @@ __acquires(&gl->gl_lockref.lock) target == LM_ST_UNLOCKED && test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) { finish_xmote(gl, target); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); + gfs2_glock_queue_work(gl, 0); } else if (ret) { pr_err("lm_lock ret %d\n", ret); @@ -492,8 +583,7 @@ __acquires(&gl->gl_lockref.lock) } } else { /* lock_nolock */ finish_xmote(gl, target); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); + gfs2_glock_queue_work(gl, 0); } spin_lock(&gl->gl_lockref.lock); @@ -565,8 +655,7 @@ out_sched: clear_bit(GLF_LOCK, &gl->gl_flags); smp_mb__after_atomic(); gl->gl_lockref.count++; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gl->gl_lockref.count--; + __gfs2_glock_queue_work(gl, 0); return; out_unlock: @@ -601,11 +690,11 @@ static void glock_work_func(struct work_struct *work) { unsigned long delay = 0; struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work); - int drop_ref = 0; + unsigned int drop_refs = 1; if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) { finish_xmote(gl, gl->gl_reply); - drop_ref = 1; + drop_refs++; } spin_lock(&gl->gl_lockref.lock); if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && @@ -623,17 +712,59 @@ static void glock_work_func(struct work_struct *work) } } run_queue(gl, 0); - spin_unlock(&gl->gl_lockref.lock); - if (!delay) - gfs2_glock_put(gl); - else { + if (delay) { + /* Keep one glock reference for the work we requeue. */ + drop_refs--; if (gl->gl_name.ln_type != LM_TYPE_INODE) delay = 0; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) - gfs2_glock_put(gl); + __gfs2_glock_queue_work(gl, delay); } - if (drop_ref) - gfs2_glock_put(gl); + + /* + * Drop the remaining glock references manually here. (Mind that + * __gfs2_glock_queue_work depends on the lockref spinlock begin held + * here as well.) + */ + gl->gl_lockref.count -= drop_refs; + if (!gl->gl_lockref.count) { + __gfs2_glock_put(gl); + return; + } + spin_unlock(&gl->gl_lockref.lock); +} + +static struct gfs2_glock *find_insert_glock(struct lm_lockname *name, + struct gfs2_glock *new) +{ + struct wait_glock_queue wait; + wait_queue_head_t *wq = glock_waitqueue(name); + struct gfs2_glock *gl; + + wait.name = name; + init_wait(&wait.wait); + wait.wait.func = glock_wake_function; + +again: + prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + rcu_read_lock(); + if (new) { + gl = rhashtable_lookup_get_insert_fast(&gl_hash_table, + &new->gl_node, ht_parms); + if (IS_ERR(gl)) + goto out; + } else { + gl = rhashtable_lookup_fast(&gl_hash_table, + name, ht_parms); + } + if (gl && !lockref_get_not_dead(&gl->gl_lockref)) { + rcu_read_unlock(); + schedule(); + goto again; + } +out: + rcu_read_unlock(); + finish_wait(wq, &wait.wait); + return gl; } /** @@ -662,15 +793,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, struct kmem_cache *cachep; int ret = 0; - rcu_read_lock(); - gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms); - if (gl && !lockref_get_not_dead(&gl->gl_lockref)) - gl = NULL; - rcu_read_unlock(); - - *glp = gl; - if (gl) + gl = find_insert_glock(&name, NULL); + if (gl) { + *glp = gl; return 0; + } if (!create) return -ENOENT; @@ -724,10 +851,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, mapping->writeback_index = 0; } -again: - rcu_read_lock(); - tmp = rhashtable_lookup_get_insert_fast(&gl_hash_table, &gl->gl_node, - ht_parms); + tmp = find_insert_glock(&name, gl); if (!tmp) { *glp = gl; goto out; @@ -736,13 +860,7 @@ again: ret = PTR_ERR(tmp); goto out_free; } - if (lockref_get_not_dead(&tmp->gl_lockref)) { - *glp = tmp; - goto out_free; - } - rcu_read_unlock(); - cond_resched(); - goto again; + *glp = tmp; out_free: kfree(gl->gl_lksb.sb_lvbptr); @@ -750,7 +868,6 @@ out_free: atomic_dec(&sdp->sd_glock_disposal); out: - rcu_read_unlock(); return ret; } @@ -986,8 +1103,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) { set_bit(GLF_REPLY_PENDING, &gl->gl_flags); gl->gl_lockref.count++; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gl->gl_lockref.count--; + __gfs2_glock_queue_work(gl, 0); } run_queue(gl, 1); spin_unlock(&gl->gl_lockref.lock); @@ -1047,17 +1163,15 @@ void gfs2_glock_dq(struct gfs2_holder *gh) gfs2_glock_add_to_lru(gl); trace_gfs2_glock_queue(gh, 0); + if (unlikely(!fast_path)) { + gl->gl_lockref.count++; + if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && + !test_bit(GLF_DEMOTE, &gl->gl_flags) && + gl->gl_name.ln_type == LM_TYPE_INODE) + delay = gl->gl_hold_time; + __gfs2_glock_queue_work(gl, delay); + } spin_unlock(&gl->gl_lockref.lock); - if (likely(fast_path)) - return; - - gfs2_glock_hold(gl); - if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) && - !test_bit(GLF_DEMOTE, &gl->gl_flags) && - gl->gl_name.ln_type == LM_TYPE_INODE) - delay = gl->gl_hold_time; - if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) - gfs2_glock_put(gl); } void gfs2_glock_dq_wait(struct gfs2_holder *gh) @@ -1233,9 +1347,8 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) spin_lock(&gl->gl_lockref.lock); handle_callback(gl, state, delay, true); + __gfs2_glock_queue_work(gl, delay); spin_unlock(&gl->gl_lockref.lock); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0) - gfs2_glock_put(gl); } /** @@ -1294,10 +1407,8 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret) gl->gl_lockref.count++; set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + __gfs2_glock_queue_work(gl, 0); spin_unlock(&gl->gl_lockref.lock); - - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); } static int glock_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1355,8 +1466,7 @@ add_back_to_lru: if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags)); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gl->gl_lockref.count--; + __gfs2_glock_queue_work(gl, 0); spin_unlock(&gl->gl_lockref.lock); cond_resched_lock(&lru_lock); } @@ -1440,14 +1550,15 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) do { gl = ERR_PTR(rhashtable_walk_start(&iter)); - if (gl) - continue; + if (IS_ERR(gl)) + goto walk_stop; while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl)) - if ((gl->gl_name.ln_sbd == sdp) && + if (gl->gl_name.ln_sbd == sdp && lockref_get_not_dead(&gl->gl_lockref)) examiner(gl); +walk_stop: rhashtable_walk_stop(&iter); } while (cond_resched(), gl == ERR_PTR(-EAGAIN)); @@ -1462,13 +1573,12 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp) static void thaw_glock(struct gfs2_glock *gl) { - if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) - goto out; - set_bit(GLF_REPLY_PENDING, &gl->gl_flags); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) { -out: + if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) { gfs2_glock_put(gl); + return; } + set_bit(GLF_REPLY_PENDING, &gl->gl_flags); + gfs2_glock_queue_work(gl, 0); } /** @@ -1484,9 +1594,8 @@ static void clear_glock(struct gfs2_glock *gl) spin_lock(&gl->gl_lockref.lock); if (gl->gl_state != LM_ST_UNLOCKED) handle_callback(gl, LM_ST_UNLOCKED, 0, false); + __gfs2_glock_queue_work(gl, 0); spin_unlock(&gl->gl_lockref.lock); - if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) - gfs2_glock_put(gl); } /** @@ -1772,7 +1881,7 @@ static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr) int __init gfs2_glock_init(void) { - int ret; + int i, ret; ret = rhashtable_init(&gl_hash_table, &ht_parms); if (ret < 0) @@ -1801,6 +1910,9 @@ int __init gfs2_glock_init(void) return ret; } + for (i = 0; i < GLOCK_WAIT_TABLE_SIZE; i++) + init_waitqueue_head(glock_wait_table + i); + return 0; } @@ -1829,16 +1941,13 @@ static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi) } static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) { struct gfs2_glock_iter *gi = seq->private; loff_t n = *pos; - int ret; - if (gi->last_pos <= *pos) - n = (*pos - gi->last_pos); - - ret = rhashtable_walk_start(&gi->hti); - if (ret) + rhashtable_walk_enter(&gl_hash_table, &gi->hti); + if (rhashtable_walk_start(&gi->hti) != 0) return NULL; do { @@ -1846,6 +1955,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) } while (gi->gl && n--); gi->last_pos = *pos; + return gi->gl; } @@ -1857,15 +1967,18 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr, (*pos)++; gi->last_pos = *pos; gfs2_glock_iter_next(gi); + return gi->gl; } static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) + __releases(RCU) { struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; rhashtable_walk_stop(&gi->hti); + rhashtable_walk_exit(&gi->hti); } static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) @@ -1928,12 +2041,10 @@ static int __gfs2_glocks_open(struct inode *inode, struct file *file, struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - rhashtable_walk_enter(&gl_hash_table, &gi->hti); } return ret; } @@ -1949,7 +2060,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; - rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index ab1ef322f7a5..5e12220cc0c2 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/parser.h> #include "incore.h" +#include "util.h" /* Options for hostdata parser */ @@ -181,7 +182,9 @@ static inline struct address_space *gfs2_glock2aspace(struct gfs2_glock *gl) extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, int create, struct gfs2_glock **glp); +extern void gfs2_glock_hold(struct gfs2_glock *gl); extern void gfs2_glock_put(struct gfs2_glock *gl); +extern void gfs2_glock_queue_put(struct gfs2_glock *gl); extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags, struct gfs2_holder *gh); extern void gfs2_holder_reinit(unsigned int state, u16 flags, @@ -257,4 +260,44 @@ static inline bool gfs2_holder_initialized(struct gfs2_holder *gh) return gh->gh_gl; } +/** + * glock_set_object - set the gl_object field of a glock + * @gl: the glock + * @object: the object + */ +static inline void glock_set_object(struct gfs2_glock *gl, void *object) +{ + spin_lock(&gl->gl_lockref.lock); + if (gfs2_assert_warn(gl->gl_name.ln_sbd, gl->gl_object == NULL)) + gfs2_dump_glock(NULL, gl); + gl->gl_object = object; + spin_unlock(&gl->gl_lockref.lock); +} + +/** + * glock_clear_object - clear the gl_object field of a glock + * @gl: the glock + * @object: the object + * + * I'd love to similarly add this: + * else if (gfs2_assert_warn(gl->gl_sbd, gl->gl_object == object)) + * gfs2_dump_glock(NULL, gl); + * Unfortunately, that's not possible because as soon as gfs2_delete_inode + * frees the block in the rgrp, another process can reassign it for an I_NEW + * inode in gfs2_create_inode because that calls new_inode, not gfs2_iget. + * That means gfs2_delete_inode may subsequently try to call this function + * for a glock that's already pointing to a brand new inode. If we clear the + * new inode's gl_object, we'll introduce metadata corruption. Function + * gfs2_delete_inode calls clear_inode which calls gfs2_clear_inode which also + * tries to clear gl_object, so it's more than just gfs2_delete_inode. + * + */ +static inline void glock_clear_object(struct gfs2_glock *gl, void *object) +{ + spin_lock(&gl->gl_lockref.lock); + if (gl->gl_object == object) + gl->gl_object = NULL; + spin_unlock(&gl->gl_lockref.lock); +} + #endif /* __GLOCK_DOT_H__ */ diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 5db59d444838..cdd1c5f06f45 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -137,7 +137,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) * * Called when demoting or unlocking an EX glock. We must flush * to disk all dirty buffers/pages relating to this glock, and must not - * not return to caller to demote/unlock the glock until I/O is complete. + * return to caller to demote/unlock the glock until I/O is complete. */ static void rgrp_go_sync(struct gfs2_glock *gl) @@ -184,7 +184,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *mapping = &sdp->sd_aspace; - struct gfs2_rgrpd *rgd = gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); if (rgd) gfs2_rgrp_brelse(rgd); @@ -197,6 +197,38 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) rgd->rd_flags &= ~GFS2_RDF_UPTODATE; } +static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl) +{ + struct gfs2_inode *ip; + + spin_lock(&gl->gl_lockref.lock); + ip = gl->gl_object; + if (ip) + set_bit(GIF_GLOP_PENDING, &ip->i_flags); + spin_unlock(&gl->gl_lockref.lock); + return ip; +} + +struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl) +{ + struct gfs2_rgrpd *rgd; + + spin_lock(&gl->gl_lockref.lock); + rgd = gl->gl_object; + spin_unlock(&gl->gl_lockref.lock); + + return rgd; +} + +static void gfs2_clear_glop_pending(struct gfs2_inode *ip) +{ + if (!ip) + return; + + clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags); + wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING); +} + /** * inode_go_sync - Sync the dirty data and/or metadata for an inode glock * @gl: the glock protecting the inode @@ -205,25 +237,24 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) static void inode_go_sync(struct gfs2_glock *gl) { - struct gfs2_inode *ip = gl->gl_object; + struct gfs2_inode *ip = gfs2_glock2inode(gl); + int isreg = ip && S_ISREG(ip->i_inode.i_mode); struct address_space *metamapping = gfs2_glock2aspace(gl); int error; - if (ip && !S_ISREG(ip->i_inode.i_mode)) - ip = NULL; - if (ip) { + if (isreg) { if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); inode_dio_wait(&ip->i_inode); } if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) - return; + goto out; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); gfs2_log_flush(gl->gl_name.ln_sbd, gl, NORMAL_FLUSH); filemap_fdatawrite(metamapping); - if (ip) { + if (isreg) { struct address_space *mapping = ip->i_inode.i_mapping; filemap_fdatawrite(mapping); error = filemap_fdatawait(mapping); @@ -238,6 +269,9 @@ static void inode_go_sync(struct gfs2_glock *gl) */ smp_mb__before_atomic(); clear_bit(GLF_DIRTY, &gl->gl_flags); + +out: + gfs2_clear_glop_pending(ip); } /** @@ -253,7 +287,7 @@ static void inode_go_sync(struct gfs2_glock *gl) static void inode_go_inval(struct gfs2_glock *gl, int flags) { - struct gfs2_inode *ip = gl->gl_object; + struct gfs2_inode *ip = gfs2_glock2inode(gl); gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count)); @@ -274,6 +308,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags) } if (ip && S_ISREG(ip->i_inode.i_mode)) truncate_inode_pages(ip->i_inode.i_mapping, 0); + + gfs2_clear_glop_pending(ip); } /** @@ -293,32 +329,6 @@ static int inode_go_demote_ok(const struct gfs2_glock *gl) return 1; } -/** - * gfs2_set_nlink - Set the inode's link count based on on-disk info - * @inode: The inode in question - * @nlink: The link count - * - * If the link count has hit zero, it must never be raised, whatever the - * on-disk inode might say. When new struct inodes are created the link - * count is set to 1, so that we can safely use this test even when reading - * in on disk information for the first time. - */ - -static void gfs2_set_nlink(struct inode *inode, u32 nlink) -{ - /* - * We will need to review setting the nlink count here in the - * light of the forthcoming ro bind mount work. This is a reminder - * to do that. - */ - if ((inode->i_nlink != nlink) && (inode->i_nlink != 0)) { - if (nlink == 0) - clear_nlink(inode); - else - set_nlink(inode, nlink); - } -} - static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { const struct gfs2_dinode *str = buf; @@ -340,7 +350,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) i_uid_write(&ip->i_inode, be32_to_cpu(str->di_uid)); i_gid_write(&ip->i_inode, be32_to_cpu(str->di_gid)); - gfs2_set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink)); + set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink)); i_size_write(&ip->i_inode, be64_to_cpu(str->di_size)); gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks)); atime.tv_sec = be64_to_cpu(str->di_atime); @@ -434,7 +444,7 @@ static int inode_go_lock(struct gfs2_holder *gh) (gh->gh_state == LM_ST_EXCLUSIVE)) { spin_lock(&sdp->sd_trunc_lock); if (list_empty(&ip->i_trunc_list)) - list_add(&sdp->sd_trunc_list, &ip->i_trunc_list); + list_add(&ip->i_trunc_list, &sdp->sd_trunc_list); spin_unlock(&sdp->sd_trunc_lock); wake_up(&sdp->sd_quota_wait); return 1; @@ -541,10 +551,10 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl) */ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) { - struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object; + struct gfs2_inode *ip = gl->gl_object; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY)) + if (!remote || sb_rdonly(sdp->sd_vfs)) return; if (gl->gl_demote_state == LM_ST_UNLOCKED && diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index b7cf65d13561..6e18e9793ec4 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -336,7 +336,6 @@ enum { }; struct gfs2_glock { - struct hlist_bl_node gl_list; unsigned long gl_flags; /* GLF_... */ struct lm_lockname gl_name; @@ -374,6 +373,7 @@ struct gfs2_glock { loff_t end; } gl_vm; }; + struct rcu_head gl_rcu; struct rhash_head gl_node; }; @@ -386,6 +386,7 @@ enum { GIF_SW_PAGED = 3, GIF_ORDERED = 4, GIF_FREE_VFS_INODE = 5, + GIF_GLOP_PENDING = 6, }; struct gfs2_inode { @@ -605,6 +606,7 @@ enum { SDF_NOJOURNALID = 6, SDF_RORECOVERY = 7, /* read only recovery */ SDF_SKIP_DLM_UNLOCK = 8, + SDF_FORCE_AIL_FLUSH = 9, }; enum gfs2_freeze_state { @@ -821,7 +823,6 @@ struct gfs2_sbd { wait_queue_head_t sd_reserving_log_wait; unsigned int sd_log_flush_head; - u64 sd_log_flush_wrapped; spinlock_t sd_ail_lock; struct list_head sd_ail1_list; @@ -832,7 +833,7 @@ struct gfs2_sbd { atomic_t sd_freeze_state; struct mutex sd_freeze_mutex; - char sd_fsname[GFS2_FSNAME_LEN]; + char sd_fsname[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; char sd_table_name[GFS2_FSNAME_LEN]; char sd_proto_name[GFS2_FSNAME_LEN]; @@ -858,5 +859,7 @@ static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which) preempt_enable(); } +extern struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl); + #endif /* __INCORE_DOT_H__ */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 9f605ea4810c..863749e29bf9 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -109,7 +109,7 @@ static void gfs2_set_iop(struct inode *inode) * @no_addr: The inode number * @no_formal_ino: The inode generation number * @blktype: Requested block type (GFS2_BLKST_DINODE or GFS2_BLKST_UNLINKED; - * GFS2_BLKST_FREE do indicate not to verify) + * GFS2_BLKST_FREE to indicate not to verify) * * If @type is DT_UNKNOWN, the inode type is fetched from disk. * @@ -144,7 +144,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) goto fail; - ip->i_gl->gl_object = ip; + flush_delayed_work(&ip->i_gl->gl_work); error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) @@ -169,12 +169,12 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, } } + glock_set_object(ip->i_gl, ip); set_bit(GIF_INVALID, &ip->i_flags); error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail_put; - - ip->i_iopen_gh.gh_gl->gl_object = ip; + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); io_gl = NULL; @@ -201,14 +201,14 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, fail_refresh: ip->i_iopen_gh.gh_flags |= GL_NOCACHE; - ip->i_iopen_gh.gh_gl->gl_object = NULL; + glock_clear_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_put: if (io_gl) gfs2_glock_put(io_gl); + glock_clear_object(ip->i_gl, ip); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); - ip->i_gl->gl_object = NULL; fail: iget_failed(inode); return ERR_PTR(error); @@ -607,6 +607,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs); if (error) goto fail; + gfs2_holder_mark_uninitialized(ghs + 1); error = create_ok(dip, name, mode); if (error) @@ -704,8 +705,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (error) goto fail_free_inode; + flush_delayed_work(&ip->i_gl->gl_work); + glock_set_object(ip->i_gl, ip); - ip->i_gl->gl_object = ip; error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); if (error) goto fail_free_inode; @@ -731,7 +733,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock2; - ip->i_iopen_gh.gh_gl->gl_object = ip; + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -773,15 +775,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, return error; fail_gunlock3: + glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); gfs2_glock_put(io_gl); fail_gunlock2: if (io_gl) clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); - gfs2_glock_dq_uninit(ghs + 1); fail_free_inode: - if (ip->i_gl) + if (ip->i_gl) { + glock_clear_object(ip->i_gl, ip); gfs2_glock_put(ip->i_gl); + } gfs2_rsqa_delete(ip, NULL); fail_free_acls: if (default_acl) @@ -799,6 +803,8 @@ fail_gunlock: &GFS2_I(inode)->i_flags); iput(inode); } + if (gfs2_holder_initialized(ghs + 1)) + gfs2_glock_dq_uninit(ghs + 1); fail: return error; } diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 0515f0a68637..65f33a0ac190 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -23,8 +23,6 @@ #include "sys.h" #include "trace_gfs2.h" -extern struct workqueue_struct *gfs2_control_wq; - /** * gfs2_update_stats - Update time based stats * @mv: Pointer to mean/variance structure to update @@ -1059,6 +1057,7 @@ static void free_recover_size(struct lm_lockstruct *ls) ls->ls_recover_submit = NULL; ls->ls_recover_result = NULL; ls->ls_recover_size = 0; + ls->ls_lvb_bits = NULL; } /* dlm calls before it does lock recovery */ @@ -1175,7 +1174,7 @@ static void gdlm_recovery_result(struct gfs2_sbd *sdp, unsigned int jid, spin_unlock(&ls->ls_recover_spin); } -const struct dlm_lockspace_ops gdlm_lockspace_ops = { +static const struct dlm_lockspace_ops gdlm_lockspace_ops = { .recover_prep = gdlm_recover_prep, .recover_slot = gdlm_recover_slot, .recover_done = gdlm_recover_done, diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index d2955daf17a4..f72c44231406 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -722,7 +722,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); sdp->sd_log_flush_head = sdp->sd_log_head; - sdp->sd_log_flush_wrapped = 0; tr = sdp->sd_log_tr; if (tr) { sdp->sd_log_tr = NULL; @@ -775,7 +774,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, } atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */ trace_gfs2_log_blocks(sdp, -1); - sdp->sd_log_flush_wrapped = 0; log_write_header(sdp, 0); sdp->sd_log_head = sdp->sd_log_flush_head; } @@ -880,7 +878,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list)); sdp->sd_log_flush_head = sdp->sd_log_head; - sdp->sd_log_flush_wrapped = 0; log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT); @@ -901,6 +898,10 @@ static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp) static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp) { unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free); + + if (test_and_clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags)) + return 1; + return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >= atomic_read(&sdp->sd_log_thresh2); } @@ -922,6 +923,15 @@ int gfs2_logd(void *data) while (!kthread_should_stop()) { + /* Check for errors writing to the journal */ + if (sdp->sd_log_error) { + gfs2_lm_withdraw(sdp, + "GFS2: fsid=%s: error %d: " + "withdrawing the file system to " + "prevent further damage.\n", + sdp->sd_fsname, sdp->sd_log_error); + } + did_flush = false; if (gfs2_jrnl_flush_reqd(sdp) || t == 0) { gfs2_ail1_empty(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index b1f9144b42c7..c8ff7b7954f0 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -71,7 +71,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd) { struct gfs2_glock *gl = bd->bd_gl; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - struct gfs2_rgrpd *rgd = gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number; struct gfs2_bitmap *bi = rgd->rd_bits + index; @@ -134,10 +134,8 @@ static void gfs2_log_incr_head(struct gfs2_sbd *sdp) BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) && (sdp->sd_log_flush_head != sdp->sd_log_head)); - if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { + if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) sdp->sd_log_flush_head = 0; - sdp->sd_log_flush_wrapped = 1; - } } static u64 gfs2_log_bmap(struct gfs2_sbd *sdp) @@ -170,7 +168,7 @@ static u64 gfs2_log_bmap(struct gfs2_sbd *sdp) */ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, - int error) + blk_status_t error) { struct buffer_head *bh, *next; struct page *page = bvec->bv_page; @@ -182,7 +180,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, bh = bh->b_this_page; do { if (error) - set_buffer_write_io_error(bh); + mark_buffer_write_io_error(bh); unlock_buffer(bh); next = bh->b_this_page; size -= bh->b_size; @@ -209,15 +207,16 @@ static void gfs2_end_log_write(struct bio *bio) struct page *page; int i; - if (bio->bi_error) { - sdp->sd_log_error = bio->bi_error; - fs_err(sdp, "Error %d writing to log\n", bio->bi_error); + if (bio->bi_status) { + fs_err(sdp, "Error %d writing to journal, jid=%u\n", + bio->bi_status, sdp->sd_jdesc->jd_jid); + wake_up(&sdp->sd_logd_waitq); } bio_for_each_segment_all(bvec, bio, i) { page = bvec->bv_page; if (page_has_buffers(page)) - gfs2_end_log_write_bh(sdp, bvec, bio->bi_error); + gfs2_end_log_write_bh(sdp, bvec, bio->bi_status); else mempool_free(page, gfs2_page_pool); } @@ -269,7 +268,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno) bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9); - bio->bi_bdev = sb->s_bdev; + bio_set_dev(bio, sb->s_bdev); bio->bi_end_io = gfs2_end_log_write; bio->bi_private = sdp; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 67d1fc4668f7..0a89e6f7a314 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -52,7 +52,6 @@ static void gfs2_init_glock_once(void *foo) { struct gfs2_glock *gl = foo; - INIT_HLIST_BL_NODE(&gl->gl_list); spin_lock_init(&gl->gl_lockref.lock); INIT_LIST_HEAD(&gl->gl_holders); INIT_LIST_HEAD(&gl->gl_lru); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 663ffc135ef3..52de1036d9f9 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -201,7 +201,7 @@ static void gfs2_meta_read_endio(struct bio *bio) do { struct buffer_head *next = bh->b_this_page; len -= bh->b_size; - bh->b_end_io(bh, !bio->bi_error); + bh->b_end_io(bh, !bio->bi_status); bh = next; } while (bh && len); } @@ -221,7 +221,7 @@ static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[], bio = bio_alloc(GFP_NOIO, num); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_bdev = bh->b_bdev; + bio_set_dev(bio, bh->b_bdev); while (num > 0) { bh = *bhs; if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) { @@ -419,8 +419,9 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { brelse(bh); ret = -EIO; + } else { + *bhp = bh; } - *bhp = bh; return ret; } @@ -452,7 +453,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) if (buffer_uptodate(first_bh)) goto out; if (!buffer_locked(first_bh)) - ll_rw_block(REQ_OP_READ, REQ_META, 1, &first_bh); + ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &first_bh); dblock++; extlen--; @@ -461,7 +462,9 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) bh = gfs2_getbuf(gl, dblock, CREATE); if (!buffer_uptodate(bh) && !buffer_locked(bh)) - ll_rw_block(REQ_OP_READ, REQ_RAHEAD | REQ_META, 1, &bh); + ll_rw_block(REQ_OP_READ, + REQ_RAHEAD | REQ_META | REQ_PRIO, + 1, &bh); brelse(bh); dblock++; extlen--; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index ed67548b286c..a3711f543405 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -176,10 +176,10 @@ static void end_bio_io_page(struct bio *bio) { struct page *page = bio->bi_private; - if (!bio->bi_error) + if (!bio->bi_status) SetPageUptodate(page); else - pr_warn("error %d reading superblock\n", bio->bi_error); + pr_warn("error %d reading superblock\n", bio->bi_status); unlock_page(page); } @@ -203,7 +203,7 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf) memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN); memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN); - memcpy(s->s_uuid, str->sb_uuid, 16); + memcpy(&s->s_uuid, str->sb_uuid, 16); } /** @@ -242,7 +242,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent) bio = bio_alloc(GFP_NOFS, 1); bio->bi_iter.bi_sector = sector * (sb->s_blocksize >> 9); - bio->bi_bdev = sb->s_bdev; + bio_set_dev(bio, sb->s_bdev); bio_add_page(bio, page, PAGE_SIZE, 0); bio->bi_end_io = end_bio_io_page; @@ -1037,7 +1037,7 @@ void gfs2_online_uevent(struct gfs2_sbd *sdp) char ro[20]; char spectator[20]; char *envp[] = { ro, spectator, NULL }; - sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0); + sprintf(ro, "RDONLY=%d", sb_rdonly(sb)); sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0); kobject_uevent_env(&sdp->sd_kobj, KOBJ_ONLINE, envp); } @@ -1113,7 +1113,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent return error; } - snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s", sdp->sd_table_name); + snprintf(sdp->sd_fsname, sizeof(sdp->sd_fsname), "%s", sdp->sd_table_name); error = gfs2_sys_fs_add(sdp); /* @@ -1159,10 +1159,10 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent } if (sdp->sd_args.ar_spectator) - snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.s", + snprintf(sdp->sd_fsname, sizeof(sdp->sd_fsname), "%s.s", sdp->sd_table_name); else - snprintf(sdp->sd_fsname, GFS2_FSNAME_LEN, "%s.%u", + snprintf(sdp->sd_fsname, sizeof(sdp->sd_fsname), "%s.%u", sdp->sd_table_name, sdp->sd_lockstruct.ls_jid); error = init_inodes(sdp, DO); @@ -1179,7 +1179,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent goto fail_per_node; } - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { error = gfs2_make_fs_rw(sdp); if (error) { fs_err(sdp, "can't make FS RW: %d\n", error); @@ -1388,7 +1388,6 @@ static void gfs2_kill_sb(struct super_block *sb) sdp->sd_root_dir = NULL; sdp->sd_master_dir = NULL; shrink_dcache_sb(sb); - gfs2_delete_debugfs_file(sdp); free_percpu(sdp->sd_lkstats); kill_block_super(sb); } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index c2ca9566b764..e700fb162664 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -452,7 +452,7 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) *qdp = NULL; - if (sdp->sd_vfs->s_flags & MS_RDONLY) + if (sb_rdonly(sdp->sd_vfs)) return 0; spin_lock(&qd_lock); @@ -730,7 +730,7 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index, if (PageUptodate(page)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh)) { - ll_rw_block(REQ_OP_READ, REQ_META, 1, &bh); + ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) goto unlock_out; @@ -1474,8 +1474,11 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) { if (error == 0 || error == -EROFS) return; - if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) { fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error); + sdp->sd_log_error = error; + wake_up(&sdp->sd_logd_waitq); + } } static void quotad_check_timeo(struct gfs2_sbd *sdp, const char *msg, diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 113b6095a58d..9395a3db1a60 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -522,7 +522,7 @@ void gfs2_recover_func(struct work_struct *work) if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) ro = 1; } else { - if (sdp->sd_vfs->s_flags & MS_RDONLY) { + if (sb_rdonly(sdp->sd_vfs)) { /* check if device itself is read-only */ ro = bdev_read_only(sdp->sd_vfs->s_bdev); if (!ro) { diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 83c9909ff14a..95b2a57ded33 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -705,10 +705,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) rb_erase(n, &sdp->sd_rindex_tree); if (gl) { - spin_lock(&gl->gl_lockref.lock); - gl->gl_object = NULL; - spin_unlock(&gl->gl_lockref.lock); - gfs2_glock_add_to_lru(gl); + glock_clear_object(gl, rgd); gfs2_glock_put(gl); } @@ -917,7 +914,7 @@ static int read_rindex_entry(struct gfs2_inode *ip) error = rgd_insert(rgd); spin_unlock(&sdp->sd_rindex_spin); if (!error) { - rgd->rd_gl->gl_object = rgd; + glock_set_object(rgd->rd_gl, rgd); rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK; rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 29b0473f6e74..8e54f2e3a304 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -893,7 +893,7 @@ restart: } spin_unlock(&sdp->sd_jindex_spin); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { error = gfs2_make_fs_ro(sdp); if (error) gfs2_io_error(sdp); @@ -924,6 +924,7 @@ restart: gfs2_jindex_free(sdp); /* Take apart glock structures and buffer lists */ gfs2_gl_hash_clear(sdp); + gfs2_delete_debugfs_file(sdp); /* Unmount the locking protocol */ gfs2_lm_unmount(sdp); @@ -943,9 +944,9 @@ static int gfs2_sync_fs(struct super_block *sb, int wait) struct gfs2_sbd *sdp = sb->s_fs_info; gfs2_quota_sync(sb, -1); - if (wait && sdp) + if (wait) gfs2_log_flush(sdp, NULL, NORMAL_FLUSH); - return 0; + return sdp->sd_log_error; } void gfs2_freeze_func(struct work_struct *work) @@ -1105,9 +1106,12 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host gfs2_holder_uninit(gh); error = err; } else { - if (!error) - error = statfs_slow_fill( - gh->gh_gl->gl_object, sc); + if (!error) { + struct gfs2_rgrpd *rgd = + gfs2_glock2rgrp(gh->gh_gl); + + error = statfs_slow_fill(rgd, sc); + } gfs2_glock_dq_uninit(gh); } } @@ -1292,7 +1296,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) * gfs2_drop_inode - Drop an inode (test for remote unlink) * @inode: The inode to drop * - * If we've received a callback on an iopen lock then its because a + * If we've received a callback on an iopen lock then it's because a * remote node tried to deallocate the inode but failed due to this node * still having the inode open. Here we mark the link count zero * since we know that it must have reached zero if the GLF_DEMOTE flag @@ -1314,6 +1318,23 @@ static int gfs2_drop_inode(struct inode *inode) if (test_bit(GLF_DEMOTE, &gl->gl_flags)) clear_nlink(inode); } + + /* + * When under memory pressure when an inode's link count has dropped to + * zero, defer deleting the inode to the delete workqueue. This avoids + * calling into DLM under memory pressure, which can deadlock. + */ + if (!inode->i_nlink && + unlikely(current->flags & PF_MEMALLOC) && + gfs2_holder_initialized(&ip->i_iopen_gh)) { + struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; + + gfs2_glock_hold(gl); + if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0) + gfs2_glock_queue_put(gl); + return false; + } + return generic_drop_inode(inode); } @@ -1498,6 +1519,22 @@ out_qs: } /** + * gfs2_glock_put_eventually + * @gl: The glock to put + * + * When under memory pressure, trigger a deferred glock put to make sure we + * won't call into DLM and deadlock. Otherwise, put the glock directly. + */ + +static void gfs2_glock_put_eventually(struct gfs2_glock *gl) +{ + if (current->flags & PF_MEMALLOC) + gfs2_glock_queue_put(gl); + else + gfs2_glock_put(gl); +} + +/** * gfs2_evict_inode - Remove an inode from cache * @inode: The inode to evict * @@ -1532,22 +1569,31 @@ static void gfs2_evict_inode(struct inode *inode) return; } - if (inode->i_nlink || (sb->s_flags & MS_RDONLY)) + if (inode->i_nlink || sb_rdonly(sb)) + goto out; + + if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) { + BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl)); + gfs2_holder_mark_uninitialized(&gh); + goto alloc_failed; + } + + /* Deletes should never happen under memory pressure anymore. */ + if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) goto out; /* Must not read inode block until block type has been verified */ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh); if (unlikely(error)) { + glock_clear_object(ip->i_iopen_gh.gh_gl, ip); ip->i_iopen_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&ip->i_iopen_gh); goto out; } - if (!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) { - error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED); - if (error) - goto out_truncate; - } + error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED); + if (error) + goto out_truncate; if (test_bit(GIF_INVALID, &ip->i_flags)) { error = gfs2_inode_refresh(ip); @@ -1555,6 +1601,13 @@ static void gfs2_evict_inode(struct inode *inode) goto out_truncate; } + /* + * The inode may have been recreated in the meantime. + */ + if (inode->i_nlink) + goto out_truncate; + +alloc_failed: if (gfs2_holder_initialized(&ip->i_iopen_gh) && test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; @@ -1587,6 +1640,11 @@ static void gfs2_evict_inode(struct inode *inode) goto out_unlock; } + /* We're about to clear the bitmap for the dinode, but as soon as we + do, gfs2_create_inode can create another inode at the same block + location and try to set gl_object again. We clear gl_object here so + that subsequent inode creates don't see an old gl_object. */ + glock_clear_object(ip->i_gl, ip); error = gfs2_dinode_dealloc(ip); goto out_unlock; @@ -1615,13 +1673,17 @@ out_unlock: gfs2_rs_deltree(&ip->i_res); if (gfs2_holder_initialized(&ip->i_iopen_gh)) { + glock_clear_object(ip->i_iopen_gh.gh_gl, ip); if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) { ip->i_iopen_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq(&ip->i_iopen_gh); } gfs2_holder_uninit(&ip->i_iopen_gh); } - gfs2_glock_dq_uninit(&gh); + if (gfs2_holder_initialized(&gh)) { + glock_clear_object(ip->i_gl, ip); + gfs2_glock_dq_uninit(&gh); + } if (error && error != GLR_TRYFAILED && error != -EROFS) fs_warn(sdp, "gfs2_evict_inode: %d\n", error); out: @@ -1631,15 +1693,19 @@ out: gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); - ip->i_gl->gl_object = NULL; - flush_delayed_work(&ip->i_gl->gl_work); + glock_clear_object(ip->i_gl, ip); + wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); gfs2_glock_add_to_lru(ip->i_gl); - gfs2_glock_put(ip->i_gl); + gfs2_glock_put_eventually(ip->i_gl); ip->i_gl = NULL; if (gfs2_holder_initialized(&ip->i_iopen_gh)) { - ip->i_iopen_gh.gh_gl->gl_object = NULL; + struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; + + glock_clear_object(gl, ip); ip->i_iopen_gh.gh_flags |= GL_NOCACHE; + gfs2_glock_hold(gl); gfs2_glock_dq_uninit(&ip->i_iopen_gh); + gfs2_glock_put_eventually(gl); } } diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 7a515345610c..9eb9d0a1abd9 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -71,25 +71,14 @@ static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf) return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname); } -static int gfs2_uuid_valid(const u8 *uuid) -{ - int i; - - for (i = 0; i < 16; i++) { - if (uuid[i]) - return 1; - } - return 0; -} - static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf) { struct super_block *s = sdp->sd_vfs; - const u8 *uuid = s->s_uuid; + buf[0] = '\0'; - if (!gfs2_uuid_valid(uuid)) + if (uuid_is_null(&s->s_uuid)) return 0; - return snprintf(buf, PAGE_SIZE, "%pUB\n", uuid); + return snprintf(buf, PAGE_SIZE, "%pUB\n", &s->s_uuid); } static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf) @@ -637,12 +626,12 @@ static struct attribute *tune_attrs[] = { NULL, }; -static struct attribute_group tune_group = { +static const struct attribute_group tune_group = { .name = "tune", .attrs = tune_attrs, }; -static struct attribute_group lock_module_group = { +static const struct attribute_group lock_module_group = { .name = "lock_module", .attrs = lock_module_attrs, }; @@ -656,7 +645,7 @@ int gfs2_sys_fs_add(struct gfs2_sbd *sdp) char *envp[] = { ro, spectator, NULL }; int sysfs_frees_sdp = 0; - sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0); + sprintf(ro, "RDONLY=%d", sb_rdonly(sb)); sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0); sdp->sd_kobj.kset = gfs2_kset; @@ -712,14 +701,13 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj, { struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); struct super_block *s = sdp->sd_vfs; - const u8 *uuid = s->s_uuid; add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name); add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name); if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags)) add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid); - if (gfs2_uuid_valid(uuid)) - add_uevent_var(env, "UUID=%pUB", uuid); + if (!uuid_is_null(&s->s_uuid)) + add_uevent_var(env, "UUID=%pUB", &s->s_uuid); return 0; } diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index c81295f407f6..3926f95a6eb7 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -151,6 +151,7 @@ extern struct kmem_cache *gfs2_rgrpd_cachep; extern struct kmem_cache *gfs2_quotad_cachep; extern struct kmem_cache *gfs2_qadata_cachep; extern mempool_t *gfs2_page_pool; +extern struct workqueue_struct *gfs2_control_wq; static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt, unsigned int *p) diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index d87721aeb575..ea09e41dbb49 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -25,6 +25,7 @@ #include "meta_io.h" #include "quota.h" #include "rgrp.h" +#include "super.h" #include "trans.h" #include "util.h" @@ -1209,8 +1210,12 @@ int __gfs2_xattr_set(struct inode *inode, const char *name, if (namel > GFS2_EA_MAX_NAME_LEN) return -ERANGE; - if (value == NULL) - return gfs2_xattr_remove(ip, type, name); + if (value == NULL) { + error = gfs2_xattr_remove(ip, type, name); + if (error == -ENODATA && !(flags & XATTR_REPLACE)) + error = 0; + return error; + } if (ea_check_size(sdp, namel, size)) return -ERANGE; @@ -1327,8 +1332,8 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip) gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE); for (x = 0; x < rlist.rl_rgrps; x++) { - struct gfs2_rgrpd *rgd; - rgd = rlist.rl_ghs[x].gh_gl->gl_object; + struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl); + rg_blocks += rgd->rd_length; } diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index bfbba799430f..2538b49cc349 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -656,7 +656,7 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end, struct super_block * sb; int ret, err; - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(filp, start, end); if (ret) return ret; inode_lock(inode); diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 482081bcdf70..894994d2c885 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -210,7 +210,7 @@ int hfs_mdb_get(struct super_block *sb) pr_warn("filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { /* Mark the volume uncleanly unmounted in case we crash */ attrib &= cpu_to_be16(~HFS_SB_ATTRIB_UNMNT); attrib |= cpu_to_be16(HFS_SB_ATTRIB_INCNSTNT); @@ -259,7 +259,7 @@ void hfs_mdb_commit(struct super_block *sb) { struct hfs_mdb *mdb = HFS_SB(sb)->mdb; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; lock_buffer(HFS_SB(sb)->mdb_bh); @@ -334,7 +334,7 @@ void hfs_mdb_commit(struct super_block *sb) void hfs_mdb_close(struct super_block *sb) { /* update volume attributes */ - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; HFS_SB(sb)->mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); HFS_SB(sb)->mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); diff --git a/fs/hfs/super.c b/fs/hfs/super.c index bf6304a350a6..7e0d65e9586c 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -71,7 +71,7 @@ void hfs_mark_mdb_dirty(struct super_block *sb) struct hfs_sb_info *sbi = HFS_SB(sb); unsigned long delay; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; spin_lock(&sbi->work_lock); @@ -115,7 +115,7 @@ static int hfs_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); *flags |= MS_NODIRATIME; - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) return 0; if (!(*flags & MS_RDONLY)) { if (!(HFS_SB(sb)->mdb->drAtrb & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index e8638d528195..4f26b6877130 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -283,7 +283,7 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end, struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); int error = 0, error2; - error = filemap_write_and_wait_range(inode->i_mapping, start, end); + error = file_write_and_wait_range(file, start, end); if (error) return error; inode_lock(inode); diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index 9b92058a1240..6bb5d7c42888 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -51,8 +51,8 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) return acl; } -int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, - int type) +static int __hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, + int type) { int err; char *xattr_name; @@ -64,12 +64,6 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, switch (type) { case ACL_TYPE_ACCESS: xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - err = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (err) - return err; - } - err = 0; break; case ACL_TYPE_DEFAULT: @@ -105,6 +99,18 @@ end_set_acl: return err; } +int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int err; + + if (type == ACL_TYPE_ACCESS && acl) { + err = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (err) + return err; + } + return __hfsplus_set_posix_acl(inode, acl, type); +} + int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) { int err = 0; @@ -122,15 +128,15 @@ int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) return err; if (default_acl) { - err = hfsplus_set_posix_acl(inode, default_acl, - ACL_TYPE_DEFAULT); + err = __hfsplus_set_posix_acl(inode, default_acl, + ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!err) - err = hfsplus_set_posix_acl(inode, acl, - ACL_TYPE_ACCESS); + err = __hfsplus_set_posix_acl(inode, acl, + ACL_TYPE_ACCESS); posix_acl_release(acl); } return err; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 67aedf4c2e7c..e5bb2de2262a 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -264,7 +264,7 @@ void hfsplus_mark_mdb_dirty(struct super_block *sb) struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); unsigned long delay; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; spin_lock(&sbi->work_lock); @@ -284,7 +284,7 @@ static void hfsplus_put_super(struct super_block *sb) cancel_delayed_work_sync(&sbi->sync_work); - if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) { + if (!sb_rdonly(sb) && sbi->s_vhdr) { struct hfsplus_vh *vhdr = sbi->s_vhdr; vhdr->modify_date = hfsp_now2mt(); @@ -329,7 +329,7 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf) static int hfsplus_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) return 0; if (!(*flags & MS_RDONLY)) { struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr; @@ -462,7 +462,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) pr_warn("Filesystem is marked locked, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } else if ((vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_JOURNALED)) && - !(sb->s_flags & MS_RDONLY)) { + !sb_rdonly(sb)) { pr_warn("write access to a journaled filesystem is not supported, use the force option at your own risk, mounting read-only.\n"); sb->s_flags |= MS_RDONLY; } @@ -535,7 +535,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) } else hfs_find_exit(&fd); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { /* * H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused * all three are registered with Apple for our use diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index e254fa0f0697..10032b919a85 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -65,7 +65,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, bio = bio_alloc(GFP_NOIO, 1); bio->bi_iter.bi_sector = sector; - bio->bi_bdev = sb->s_bdev; + bio_set_dev(bio, sb->s_bdev); bio_set_op_attrs(bio, op, op_flags); if (op != WRITE && data) diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index e61261a7417e..c148e7f4f451 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -374,7 +374,7 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end, struct inode *inode = file->f_mapping->host; int ret; - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); if (ret) return ret; diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c index d6a4b55d2ab0..098bf0f4f386 100644 --- a/fs/hpfs/alloc.c +++ b/fs/hpfs/alloc.c @@ -538,7 +538,7 @@ int hpfs_trim_fs(struct super_block *s, u64 start, u64 end, u64 minlen, unsigned return 0; if (start < sbi->sb_dirband_start + sbi->sb_dirband_size && end > sbi->sb_dirband_start) { hpfs_lock(s); - if (s->s_flags & MS_RDONLY) { + if (sb_rdonly(s)) { err = -EROFS; goto unlock_1; } @@ -559,7 +559,7 @@ unlock_1: end_bmp = (end + 0x3fff) >> 14; while (start_bmp < end_bmp && !err) { hpfs_lock(s); - if (s->s_flags & MS_RDONLY) { + if (sb_rdonly(s)) { err = -EROFS; goto unlock_2; } diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index 7b9150c2e75c..fa6bbb4f509f 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -264,7 +264,7 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in hpfs_result = hpfs_i(result); if (!de->directory) hpfs_result->i_parent_dir = dir->i_ino; - if (de->has_acl || de->has_xtd_perm) if (!(dir->i_sb->s_flags & MS_RDONLY)) { + if (de->has_acl || de->has_xtd_perm) if (!sb_rdonly(dir->i_sb)) { hpfs_error(result->i_sb, "ACLs or XPERM found. This is probably HPFS386. This driver doesn't support it now. Send me some info on these structures"); goto bail1; } diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index b3be1b5a62e2..f26138425b16 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -24,7 +24,7 @@ int hpfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file->f_mapping->host; int ret; - ret = filemap_write_and_wait_range(file->f_mapping, start, end); + ret = file_write_and_wait_range(file, start, end); if (ret) return ret; return sync_blockdev(inode->i_sb->s_bdev); diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 82067ca22f2b..1516fb4e28f4 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -21,7 +21,7 @@ static void mark_dirty(struct super_block *s, int remount) { - if (hpfs_sb(s)->sb_chkdsk && (remount || !(s->s_flags & MS_RDONLY))) { + if (hpfs_sb(s)->sb_chkdsk && (remount || !sb_rdonly(s))) { struct buffer_head *bh; struct hpfs_spare_block *sb; if ((sb = hpfs_map_sector(s, 17, &bh, 0))) { @@ -41,7 +41,7 @@ static void unmark_dirty(struct super_block *s) { struct buffer_head *bh; struct hpfs_spare_block *sb; - if (s->s_flags & MS_RDONLY) return; + if (sb_rdonly(s)) return; sync_blockdev(s->s_bdev); if ((sb = hpfs_map_sector(s, 17, &bh, 0))) { sb->dirty = hpfs_sb(s)->sb_chkdsk > 1 - hpfs_sb(s)->sb_was_error; @@ -73,14 +73,14 @@ void hpfs_error(struct super_block *s, const char *fmt, ...) mark_dirty(s, 0); panic("HPFS panic"); } else if (hpfs_sb(s)->sb_err == 1) { - if (s->s_flags & MS_RDONLY) + if (sb_rdonly(s)) pr_cont("; already mounted read-only\n"); else { pr_cont("; remounting read-only\n"); mark_dirty(s, 0); s->s_flags |= MS_RDONLY; } - } else if (s->s_flags & MS_RDONLY) + } else if (sb_rdonly(s)) pr_cont("; going on - but anything won't be destroyed because it's read-only\n"); else pr_cont("; corrupted filesystem mounted read/write - your computer will explode within 20 seconds ... but you wanted it so!\n"); @@ -607,8 +607,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) } /* Check version */ - if (!(s->s_flags & MS_RDONLY) && - superblock->funcversion != 2 && superblock->funcversion != 3) { + if (!sb_rdonly(s) && superblock->funcversion != 2 && superblock->funcversion != 3) { pr_err("Bad version %d,%d. Mount readonly to go around\n", (int)superblock->version, (int)superblock->funcversion); pr_err("please try recent version of HPFS driver at http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi and if it still can't understand this format, contact author - mikulas@artax.karlin.mff.cuni.cz\n"); @@ -666,7 +665,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) hpfs_error(s, "improperly stopped"); } - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { spareblock->dirty = 1; spareblock->old_wrote = 0; mark_buffer_dirty(bh2); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d44f5456eb9b..59073e9f01a4 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -46,13 +46,13 @@ static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; struct hugetlbfs_config { - kuid_t uid; - kgid_t gid; - umode_t mode; - long max_hpages; - long nr_inodes; - struct hstate *hstate; - long min_hpages; + struct hstate *hstate; + long max_hpages; + long nr_inodes; + long min_hpages; + kuid_t uid; + kgid_t gid; + umode_t mode; }; struct hugetlbfs_inode_info { @@ -334,7 +334,7 @@ static void remove_huge_page(struct page *page) } static void -hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end) +hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) { struct vm_area_struct *vma; @@ -401,9 +401,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, const pgoff_t end = lend >> huge_page_shift(h); struct vm_area_struct pseudo_vma; struct pagevec pvec; - pgoff_t next; + pgoff_t next, index; int i, freed = 0; - long lookup_nr = PAGEVEC_SIZE; bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); @@ -412,33 +411,19 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Don't grab more pages than the number left in the range. - */ - if (end - next < lookup_nr) - lookup_nr = end - next; - - /* * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + if (!pagevec_lookup_range(&pvec, mapping, &next, end - 1)) break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; - /* - * The page (index) could be beyond end. This is - * only possible in the punch hole case as end is - * max page offset in the truncate case. - */ - next = page->index; - if (next >= end) - break; - + index = page->index; hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, - mapping, next, 0); + mapping, index, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -455,8 +440,8 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, i_mmap_lock_write(mapping); hugetlb_vmdelete_list(&mapping->i_mmap, - next * pages_per_huge_page(h), - (next + 1) * pages_per_huge_page(h)); + index * pages_per_huge_page(h), + (index + 1) * pages_per_huge_page(h)); i_mmap_unlock_write(mapping); } @@ -475,14 +460,13 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, freed++; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, - next, next + 1, 1))) + index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); } unlock_page(page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); } - ++next; huge_pagevec_release(&pvec); cond_resched(); } @@ -514,7 +498,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_size_write(inode, offset); i_mmap_lock_write(mapping); - if (!RB_EMPTY_ROOT(&mapping->i_mmap)) + if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); @@ -539,7 +523,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) inode_lock(inode); i_mmap_lock_write(mapping); - if (!RB_EMPTY_ROOT(&mapping->i_mmap)) + if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT); @@ -846,11 +830,64 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; - migrate_page_copy(newpage, page); + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); return MIGRATEPAGE_SUCCESS; } +static int hugetlbfs_error_remove_page(struct address_space *mapping, + struct page *page) +{ + struct inode *inode = mapping->host; + + remove_huge_page(page); + hugetlb_fix_reserve_counts(inode); + return 0; +} + +/* + * Display the mount options in /proc/mounts. + */ +static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); + struct hugepage_subpool *spool = sbinfo->spool; + unsigned long hpage_size = huge_page_size(sbinfo->hstate); + unsigned hpage_shift = huge_page_shift(sbinfo->hstate); + char mod; + + if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbinfo->uid)); + if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbinfo->gid)); + if (sbinfo->mode != 0755) + seq_printf(m, ",mode=%o", sbinfo->mode); + if (sbinfo->max_inodes != -1) + seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); + + hpage_size /= 1024; + mod = 'K'; + if (hpage_size >= 1024) { + hpage_size /= 1024; + mod = 'M'; + } + seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); + if (spool) { + if (spool->max_hpages != -1) + seq_printf(m, ",size=%llu", + (unsigned long long)spool->max_hpages << hpage_shift); + if (spool->min_hpages != -1) + seq_printf(m, ",min_size=%llu", + (unsigned long long)spool->min_hpages << hpage_shift); + } + return 0; +} + static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); @@ -966,6 +1003,7 @@ static const struct address_space_operations hugetlbfs_aops = { .write_end = hugetlbfs_write_end, .set_page_dirty = hugetlbfs_set_page_dirty, .migratepage = hugetlbfs_migrate_page, + .error_remove_page = hugetlbfs_error_remove_page, }; @@ -1008,19 +1046,19 @@ static const struct super_operations hugetlbfs_ops = { .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, - .show_options = generic_show_options, + .show_options = hugetlbfs_show_options, }; -enum { NO_SIZE, SIZE_STD, SIZE_PERCENT }; +enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ -static long long +static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, - int val_type) + enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; @@ -1042,7 +1080,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig) substring_t args[MAX_OPT_ARGS]; int option; unsigned long long max_size_opt = 0, min_size_opt = 0; - int max_val_type = NO_SIZE, min_val_type = NO_SIZE; + enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE; if (!options) return 0; @@ -1156,8 +1194,6 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) struct hugetlbfs_config config; struct hugetlbfs_sb_info *sbinfo; - save_mount_options(sb, data); - config.max_hpages = -1; /* No limit on size by default */ config.nr_inodes = -1; /* No limit on number of inodes by default */ config.uid = current_fsuid(); @@ -1178,6 +1214,10 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) sbinfo->max_inodes = config.nr_inodes; sbinfo->free_inodes = config.nr_inodes; sbinfo->spool = NULL; + sbinfo->uid = config.uid; + sbinfo->gid = config.gid; + sbinfo->mode = config.mode; + /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimim size) are taken diff --git a/fs/inode.c b/fs/inode.c index db5914783a71..d1e35b53bb23 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -146,6 +146,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; + inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; @@ -352,7 +353,7 @@ void address_space_init_once(struct address_space *mapping) init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); - mapping->i_mmap = RB_ROOT; + mapping->i_mmap = RB_ROOT_CACHED; } EXPORT_SYMBOL(address_space_init_once); @@ -636,6 +637,7 @@ again: dispose_list(&dispose); } +EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock @@ -1568,11 +1570,24 @@ EXPORT_SYMBOL(bmap); static void update_ovl_inode_times(struct dentry *dentry, struct inode *inode, bool rcu) { - if (!rcu) { - struct inode *realinode = d_real_inode(dentry); + struct dentry *upperdentry; - if (unlikely(inode != realinode) && - (!timespec_equal(&inode->i_mtime, &realinode->i_mtime) || + /* + * Nothing to do if in rcu or if non-overlayfs + */ + if (rcu || likely(!(dentry->d_flags & DCACHE_OP_REAL))) + return; + + upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER); + + /* + * If file is on lower then we can't update atime, so no worries about + * stale mtime/ctime. + */ + if (upperdentry) { + struct inode *realinode = d_inode(upperdentry); + + if ((!timespec_equal(&inode->i_mtime, &realinode->i_mtime) || !timespec_equal(&inode->i_ctime, &realinode->i_ctime))) { inode->i_mtime = realinode->i_mtime; inode->i_ctime = realinode->i_ctime; @@ -1891,11 +1906,11 @@ static void __wait_on_freeing_inode(struct inode *inode) wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); schedule(); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); spin_lock(&inode_hash_lock); } @@ -1914,8 +1929,6 @@ __setup("ihash_entries=", set_ihash_entries); */ void __init inode_init_early(void) { - unsigned int loop; - /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ @@ -1927,20 +1940,15 @@ void __init inode_init_early(void) sizeof(struct hlist_head), ihash_entries, 14, - HASH_EARLY, + HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << i_hash_shift); loop++) - INIT_HLIST_HEAD(&inode_hashtable[loop]); } void __init inode_init(void) { - unsigned int loop; - /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), @@ -1958,14 +1966,11 @@ void __init inode_init(void) sizeof(struct hlist_head), ihash_entries, 14, - 0, + HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); - - for (loop = 0; loop < (1U << i_hash_shift); loop++) - INIT_HLIST_HEAD(&inode_hashtable[loop]); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) @@ -2023,7 +2028,7 @@ bool inode_owner_or_capable(const struct inode *inode) return true; ns = current_user_ns(); - if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid)) + if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } @@ -2038,11 +2043,11 @@ static void __inode_dio_wait(struct inode *inode) DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { - prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); - finish_wait(wq, &q.wait); + finish_wait(wq, &q.wq_entry); } /** diff --git a/fs/internal.h b/fs/internal.h index 9676fe11c093..48cee21b4f14 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -71,8 +71,10 @@ extern void __init mnt_init(void); extern int __mnt_want_write(struct vfsmount *); extern int __mnt_want_write_file(struct file *); +extern int mnt_want_write_file_path(struct file *); extern void __mnt_drop_write(struct vfsmount *); extern void __mnt_drop_write_file(struct file *); +extern void mnt_drop_write_file_path(struct file *); /* * fs_struct.c @@ -132,7 +134,6 @@ static inline bool atime_needs_update_rcu(const struct path *path, extern void inode_io_list_del(struct inode *inode); extern long get_nr_dirty_inodes(void); -extern void evict_inodes(struct super_block *); extern int invalidate_inodes(struct super_block *, bool); /* diff --git a/fs/iomap.c b/fs/iomap.c index 4b10892967a5..d4801f8dd4fd 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -278,7 +278,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, unsigned long bytes; /* Bytes to write to page */ offset = (pos & (PAGE_SIZE - 1)); - bytes = min_t(unsigned long, PAGE_SIZE - offset, length); + bytes = min_t(loff_t, PAGE_SIZE - offset, length); rpage = __iomap_read_page(inode, pos); if (IS_ERR(rpage)) @@ -373,7 +373,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, unsigned offset, bytes; offset = pos & (PAGE_SIZE - 1); /* Within page */ - bytes = min_t(unsigned, PAGE_SIZE - offset, count); + bytes = min_t(loff_t, PAGE_SIZE - offset, count); if (IS_DAX(inode)) status = iomap_dax_zero(pos, offset, bytes, iomap); @@ -477,10 +477,10 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops) set_page_dirty(page); wait_for_stable_page(page); - return 0; + return VM_FAULT_LOCKED; out_unlock: unlock_page(page); - return ret; + return block_page_mkwrite_return(ret); } EXPORT_SYMBOL_GPL(iomap_page_mkwrite); @@ -584,6 +584,100 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, } EXPORT_SYMBOL_GPL(iomap_fiemap); +static loff_t +iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length, + void *data, struct iomap *iomap) +{ + switch (iomap->type) { + case IOMAP_UNWRITTEN: + offset = page_cache_seek_hole_data(inode, offset, length, + SEEK_HOLE); + if (offset < 0) + return length; + /* fall through */ + case IOMAP_HOLE: + *(loff_t *)data = offset; + return 0; + default: + return length; + } +} + +loff_t +iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops) +{ + loff_t size = i_size_read(inode); + loff_t length = size - offset; + loff_t ret; + + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) + return -ENXIO; + + while (length > 0) { + ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, + &offset, iomap_seek_hole_actor); + if (ret < 0) + return ret; + if (ret == 0) + break; + + offset += ret; + length -= ret; + } + + return offset; +} +EXPORT_SYMBOL_GPL(iomap_seek_hole); + +static loff_t +iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length, + void *data, struct iomap *iomap) +{ + switch (iomap->type) { + case IOMAP_HOLE: + return length; + case IOMAP_UNWRITTEN: + offset = page_cache_seek_hole_data(inode, offset, length, + SEEK_DATA); + if (offset < 0) + return length; + /*FALLTHRU*/ + default: + *(loff_t *)data = offset; + return 0; + } +} + +loff_t +iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops) +{ + loff_t size = i_size_read(inode); + loff_t length = size - offset; + loff_t ret; + + /* Nothing to be found before or beyond the end of the file. */ + if (offset < 0 || offset >= size) + return -ENXIO; + + while (length > 0) { + ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops, + &offset, iomap_seek_data_actor); + if (ret < 0) + return ret; + if (ret == 0) + break; + + offset += ret; + length -= ret; + } + + if (length <= 0) + return -ENXIO; + return offset; +} +EXPORT_SYMBOL_GPL(iomap_seek_data); + /* * Private flags for iomap_dio, must not overlap with the public ones in * iomap.h: @@ -619,6 +713,8 @@ struct iomap_dio { static ssize_t iomap_dio_complete(struct iomap_dio *dio) { struct kiocb *iocb = dio->iocb; + struct inode *inode = file_inode(iocb->ki_filp); + loff_t offset = iocb->ki_pos; ssize_t ret; if (dio->end_io) { @@ -632,12 +728,33 @@ static ssize_t iomap_dio_complete(struct iomap_dio *dio) if (likely(!ret)) { ret = dio->size; /* check for short read */ - if (iocb->ki_pos + ret > dio->i_size && + if (offset + ret > dio->i_size && !(dio->flags & IOMAP_DIO_WRITE)) - ret = dio->i_size - iocb->ki_pos; + ret = dio->i_size - offset; iocb->ki_pos += ret; } + /* + * Try again to invalidate clean pages which might have been cached by + * non-direct readahead, or faulted in by get_user_pages() if the source + * of the write was an mmap'ed region of the file we're writing. Either + * one is a pretty crazy thing to do, so we don't support it 100%. If + * this invalidation fails, tough, the write still worked... + * + * And this page cache invalidation has to be after dio->end_io(), as + * some filesystems convert unwritten extents to real allocations in + * end_io() when necessary, otherwise a racing buffer read would cache + * zeros from unwritten extents. + */ + if (!dio->error && + (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) { + int err; + err = invalidate_inode_pages2_range(inode->i_mapping, + offset >> PAGE_SHIFT, + (offset + dio->size - 1) >> PAGE_SHIFT); + WARN_ON_ONCE(err); + } + inode_dio_end(file_inode(iocb->ki_filp)); kfree(dio); @@ -672,8 +789,8 @@ static void iomap_dio_bio_end_io(struct bio *bio) struct iomap_dio *dio = bio->bi_private; bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY); - if (bio->bi_error) - iomap_dio_set_error(dio, bio->bi_error); + if (bio->bi_status) + iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status)); if (atomic_dec_and_test(&dio->ref)) { if (is_sync_kiocb(dio->iocb)) { @@ -711,7 +828,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, struct bio *bio; bio = bio_alloc(GFP_KERNEL, 1); - bio->bi_bdev = iomap->bdev; + bio_set_dev(bio, iomap->bdev); bio->bi_iter.bi_sector = iomap->blkno + ((pos - iomap->offset) >> 9); bio->bi_private = dio; @@ -790,9 +907,10 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, return 0; bio = bio_alloc(GFP_KERNEL, nr_pages); - bio->bi_bdev = iomap->bdev; + bio_set_dev(bio, iomap->bdev); bio->bi_iter.bi_sector = iomap->blkno + ((pos - iomap->offset) >> 9); + bio->bi_write_hint = dio->iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; @@ -881,6 +999,14 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, flags |= IOMAP_WRITE; } + if (iocb->ki_flags & IOCB_NOWAIT) { + if (filemap_range_has_page(mapping, start, end)) { + ret = -EAGAIN; + goto out_free_dio; + } + flags |= IOMAP_NOWAIT; + } + ret = filemap_write_and_wait_range(mapping, start, end); if (ret) goto out_free_dio; @@ -890,6 +1016,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, WARN_ON_ONCE(ret); ret = 0; + if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && + !inode->i_sb->s_dio_done_wq) { + ret = sb_init_dio_done_wq(inode->i_sb); + if (ret < 0) + goto out_free_dio; + } + inode_dio_begin(inode); blk_start_plug(&plug); @@ -912,13 +1045,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret < 0) iomap_dio_set_error(dio, ret); - if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) && - !inode->i_sb->s_dio_done_wq) { - ret = sb_init_dio_done_wq(inode->i_sb); - if (ret < 0) - iomap_dio_set_error(dio, ret); - } - if (!atomic_dec_and_test(&dio->ref)) { if (!is_sync_kiocb(iocb)) return -EIOCBQUEUED; @@ -939,19 +1065,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, ret = iomap_dio_complete(dio); - /* - * Try again to invalidate clean pages which might have been cached by - * non-direct readahead, or faulted in by get_user_pages() if the source - * of the write was an mmap'ed region of the file we're writing. Either - * one is a pretty crazy thing to do, so we don't support it 100%. If - * this invalidation fails, tough, the write still worked... - */ - if (iov_iter_rw(iter) == WRITE) { - int err = invalidate_inode_pages2_range(mapping, - start >> PAGE_SHIFT, end >> PAGE_SHIFT); - WARN_ON_ONCE(err); - } - return ret; out_free_dio: diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 020ba0936146..447a24d77b89 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -23,6 +23,7 @@ #include <linux/parser.h> #include <linux/mpage.h> #include <linux/user_namespace.h> +#include <linux/seq_file.h> #include "isofs.h" #include "zisofs.h" @@ -57,6 +58,7 @@ static void isofs_put_super(struct super_block *sb) static int isofs_read_inode(struct inode *, int relocated); static int isofs_statfs (struct dentry *, struct kstatfs *); +static int isofs_show_options(struct seq_file *, struct dentry *); static struct kmem_cache *isofs_inode_cachep; @@ -94,7 +96,7 @@ static int __init init_inodecache(void) 0, (SLAB_RECLAIM_ACCOUNT| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); - if (isofs_inode_cachep == NULL) + if (!isofs_inode_cachep) return -ENOMEM; return 0; } @@ -123,7 +125,7 @@ static const struct super_operations isofs_sops = { .put_super = isofs_put_super, .statfs = isofs_statfs, .remount_fs = isofs_remount, - .show_options = generic_show_options, + .show_options = isofs_show_options, }; @@ -408,7 +410,11 @@ static int parse_options(char *options, struct iso9660_options *popt) if (match_int(&args[0], &option)) return 0; n = option; - if (n > 99) + /* + * Track numbers are supposed to be in range 1-99, the + * mount option starts indexing at 0. + */ + if (n >= 99) return 0; popt->session = n + 1; break; @@ -473,6 +479,50 @@ static int parse_options(char *options, struct iso9660_options *popt) } /* + * Display the mount options in /proc/mounts. + */ +static int isofs_show_options(struct seq_file *m, struct dentry *root) +{ + struct isofs_sb_info *sbi = ISOFS_SB(root->d_sb); + + if (!sbi->s_rock) seq_puts(m, ",norock"); + else if (!sbi->s_joliet_level) seq_puts(m, ",nojoliet"); + if (sbi->s_cruft) seq_puts(m, ",cruft"); + if (sbi->s_hide) seq_puts(m, ",hide"); + if (sbi->s_nocompress) seq_puts(m, ",nocompress"); + if (sbi->s_overriderockperm) seq_puts(m, ",overriderockperm"); + if (sbi->s_showassoc) seq_puts(m, ",showassoc"); + if (sbi->s_utf8) seq_puts(m, ",utf8"); + + if (sbi->s_check) seq_printf(m, ",check=%c", sbi->s_check); + if (sbi->s_mapping) seq_printf(m, ",map=%c", sbi->s_mapping); + if (sbi->s_session != 255) seq_printf(m, ",session=%u", sbi->s_session - 1); + if (sbi->s_sbsector != -1) seq_printf(m, ",sbsector=%u", sbi->s_sbsector); + + if (root->d_sb->s_blocksize != 1024) + seq_printf(m, ",blocksize=%lu", root->d_sb->s_blocksize); + + if (sbi->s_uid_set) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (sbi->s_gid_set) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + + if (sbi->s_dmode != ISOFS_INVALID_MODE) + seq_printf(m, ",dmode=%o", sbi->s_dmode); + if (sbi->s_fmode != ISOFS_INVALID_MODE) + seq_printf(m, ",fmode=%o", sbi->s_fmode); + +#ifdef CONFIG_JOLIET + if (sbi->s_nls_iocharset && + strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0) + seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset); +#endif + return 0; +} + +/* * look if the driver can tell the multi session redirection value * * don't change this if you don't know what you do, please! @@ -499,7 +549,7 @@ static unsigned int isofs_get_last_session(struct super_block *sb, s32 session) vol_desc_start=0; ms_info.addr_format=CDROM_LBA; - if(session >= 0 && session <= 99) { + if (session > 0) { struct cdrom_tocentry Te; Te.cdte_track=session; Te.cdte_format=CDROM_LBA; @@ -583,8 +633,6 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) int table, error = -EINVAL; unsigned int vol_desc_start; - save_mount_options(s, data); - sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; @@ -605,6 +653,8 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) opt.blocksize = sb_min_blocksize(s, opt.blocksize); sbi->s_high_sierra = 0; /* default is iso9660 */ + sbi->s_session = opt.session; + sbi->s_sbsector = opt.sbsector; vol_desc_start = (opt.sbsector != -1) ? opt.sbsector : isofs_get_last_session(s,opt.session); @@ -630,7 +680,7 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) if (isonum_711(vdp->type) == ISO_VD_END) break; if (isonum_711(vdp->type) == ISO_VD_PRIMARY) { - if (pri == NULL) { + if (!pri) { pri = (struct iso_primary_descriptor *)vdp; /* Save the buffer in case we need it ... */ pri_bh = bh; @@ -689,12 +739,12 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) root_found: /* We don't support read-write mounts */ - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { error = -EACCES; goto out_freebh; } - if (joliet_level && (pri == NULL || !opt.rock)) { + if (joliet_level && (!pri || !opt.rock)) { /* This is the case of Joliet with the norock mount flag. * A disc with both Joliet and Rock Ridge is handled later */ @@ -911,6 +961,7 @@ root_found: table += 2; if (opt.check == 'r') table++; + sbi->s_check = opt.check; if (table) s->s_d_op = &isofs_dentry_ops[table - 1]; @@ -1249,7 +1300,7 @@ static int isofs_read_inode(struct inode *inode, int relocated) unsigned long bufsize = ISOFS_BUFFER_SIZE(inode); unsigned long block; int high_sierra = sbi->s_high_sierra; - struct buffer_head *bh = NULL; + struct buffer_head *bh; struct iso_directory_record *de; struct iso_directory_record *tmpde = NULL; unsigned int de_len; @@ -1271,8 +1322,7 @@ static int isofs_read_inode(struct inode *inode, int relocated) int frag1 = bufsize - offset; tmpde = kmalloc(de_len, GFP_KERNEL); - if (tmpde == NULL) { - printk(KERN_INFO "%s: out of memory\n", __func__); + if (!tmpde) { ret = -ENOMEM; goto fail; } diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h index 0ac4c1f73fbd..133a456b0425 100644 --- a/fs/isofs/isofs.h +++ b/fs/isofs/isofs.h @@ -36,8 +36,11 @@ struct isofs_sb_info { unsigned long s_max_size; int s_rock_offset; /* offset of SUSP fields within SU area */ + s32 s_sbsector; unsigned char s_joliet_level; unsigned char s_mapping; + unsigned char s_check; + unsigned char s_session; unsigned int s_high_sierra:1; unsigned int s_rock:2; unsigned int s_utf8:1; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index b6b194ec1b4f..3c1c31321d9b 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -263,18 +263,10 @@ static int journal_finish_inode_data_buffers(journal_t *journal, continue; jinode->i_flags |= JI_COMMIT_RUNNING; spin_unlock(&journal->j_list_lock); - err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping); - if (err) { - /* - * Because AS_EIO is cleared by - * filemap_fdatawait_range(), set it again so - * that user process can get -EIO from fsync(). - */ - mapping_set_error(jinode->i_vfs_inode->i_mapping, -EIO); - - if (!ret) - ret = err; - } + err = filemap_fdatawait_keep_errors( + jinode->i_vfs_inode->i_mapping); + if (!ret) + ret = err; spin_lock(&journal->j_list_lock); jinode->i_flags &= ~JI_COMMIT_RUNNING; smp_mb(); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index ebad34266bcf..7d5ef3bf3f3e 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -2579,10 +2579,10 @@ restart: wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&journal->j_list_lock); schedule(); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); goto restart; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 2d30a6da7013..8b08044b3120 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -409,25 +409,6 @@ static handle_t *new_handle(int nblocks) return handle; } -/** - * handle_t *jbd2_journal_start() - Obtain a new handle. - * @journal: Journal to start transaction on. - * @nblocks: number of block buffer we might modify - * - * We make sure that the transaction can guarantee at least nblocks of - * modified buffers in the log. We block until the log can guarantee - * that much space. Additionally, if rsv_blocks > 0, we also create another - * handle with rsv_blocks reserved blocks in the journal. This handle is - * is stored in h_rsv_handle. It is not attached to any particular transaction - * and thus doesn't block transaction commit. If the caller uses this reserved - * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() - * on the parent handle will dispose the reserved one. Reserved handle has to - * be converted to a normal handle using jbd2_journal_start_reserved() before - * it can be used. - * - * Return a pointer to a newly allocated handle, or an ERR_PTR() value - * on failure. - */ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, gfp_t gfp_mask, unsigned int type, unsigned int line_no) @@ -478,6 +459,25 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks, EXPORT_SYMBOL(jbd2__journal_start); +/** + * handle_t *jbd2_journal_start() - Obtain a new handle. + * @journal: Journal to start transaction on. + * @nblocks: number of block buffer we might modify + * + * We make sure that the transaction can guarantee at least nblocks of + * modified buffers in the log. We block until the log can guarantee + * that much space. Additionally, if rsv_blocks > 0, we also create another + * handle with rsv_blocks reserved blocks in the journal. This handle is + * is stored in h_rsv_handle. It is not attached to any particular transaction + * and thus doesn't block transaction commit. If the caller uses this reserved + * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop() + * on the parent handle will dispose the reserved one. Reserved handle has to + * be converted to a normal handle using jbd2_journal_start_reserved() before + * it can be used. + * + * Return a pointer to a newly allocated handle, or an ERR_PTR() value + * on failure. + */ handle_t *jbd2_journal_start(journal_t *journal, int nblocks) { return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0); @@ -1072,10 +1072,10 @@ out: * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * - * Returns an error code or 0 on success. + * Returns: error code or 0 on success. * * In full data journalling mode the buffer may be of type BJ_AsyncData, - * because we're write()ing a buffer which is also part of a shared mapping. + * because we're ``write()ing`` a buffer which is also part of a shared mapping. */ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index c12476e309c6..bd0428bebe9b 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -35,7 +35,7 @@ int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync) struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); int ret; - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + ret = file_write_and_wait_range(filp, start, end); if (ret) return ret; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 76fa814df3d1..e96c6b05e43e 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -395,14 +395,14 @@ int jffs2_do_remount_fs(struct super_block *sb, int *flags, char *data) { struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); - if (c->flags & JFFS2_SB_FLAG_RO && !(sb->s_flags & MS_RDONLY)) + if (c->flags & JFFS2_SB_FLAG_RO && !sb_rdonly(sb)) return -EROFS; /* We stop if it was running, then restart if it needs to. This also catches the case where it was stopped and this is just a remount to restart it. Flush the writebuffer, if neccecary, else we loose it */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { jffs2_stop_garbage_collect_thread(c); mutex_lock(&c->alloc_sem); jffs2_flush_wbuf_pad(c); @@ -590,7 +590,7 @@ int jffs2_do_fill_super(struct super_block *sb, void *data, int silent) sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = JFFS2_SUPER_MAGIC; - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) jffs2_start_garbage_collect_thread(c); return 0; diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 5ef21f4c4c77..153f1c6eb169 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -342,7 +342,7 @@ static void jffs2_put_super (struct super_block *sb) static void jffs2_kill_sb(struct super_block *sb) { struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) jffs2_stop_garbage_collect_thread(c); kill_mtd_super(sb); kfree(c); diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index b25d28a21212..2cfe487708e0 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -17,7 +17,7 @@ #include <linux/slab.h> #include <linux/mtd/mtd.h> #include <linux/crc32.h> -#include <linux/mtd/nand.h> +#include <linux/mtd/rawnand.h> #include <linux/jiffies.h> #include <linux/sched.h> #include <linux/writeback.h> @@ -1162,7 +1162,7 @@ static void delayed_wbuf_sync(struct work_struct *work) struct jffs2_sb_info *c = work_to_sb(work); struct super_block *sb = OFNI_BS_2SFFJ(c); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { jffs2_dbg(1, "%s()\n", __func__); jffs2_flush_wbuf_gc(c, 0); } @@ -1173,7 +1173,7 @@ void jffs2_dirty_trigger(struct jffs2_sb_info *c) struct super_block *sb = OFNI_BS_2SFFJ(c); unsigned long delay; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; delay = msecs_to_jiffies(dirty_writeback_interval * 10); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 7bc186f4ed4d..2e71b6e7e646 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -77,13 +77,6 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: ea_name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - rc = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (rc) - return rc; - inode->i_ctime = current_time(inode); - mark_inode_dirty(inode); - } break; case ACL_TYPE_DEFAULT: ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; @@ -115,12 +108,27 @@ int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { int rc; tid_t tid; + int update_mode = 0; + umode_t mode = inode->i_mode; tid = txBegin(inode->i_sb, 0); mutex_lock(&JFS_IP(inode)->commit_mutex); + if (type == ACL_TYPE_ACCESS && acl) { + rc = posix_acl_update_mode(inode, &mode, &acl); + if (rc) + goto end_tx; + update_mode = 1; + } rc = __jfs_set_acl(tid, inode, type, acl); - if (!rc) + if (!rc) { + if (update_mode) { + inode->i_mode = mode; + inode->i_ctime = current_time(inode); + mark_inode_dirty(inode); + } rc = txCommit(tid, 1, &inode, 0); + } +end_tx: txEnd(tid); mutex_unlock(&JFS_IP(inode)->commit_mutex); return rc; diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 739492c7a3fd..36665fd37095 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -34,7 +34,7 @@ int jfs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file->f_mapping->host; int rc = 0; - rc = filemap_write_and_wait_range(inode->i_mapping, start, end); + rc = file_write_and_wait_range(file, start, end); if (rc) return rc; diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index bb1da1feafeb..0e5d412c0b01 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1995,7 +1995,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bio = bio_alloc(GFP_NOFS, 1); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); - bio->bi_bdev = log->bdev; + bio_set_dev(bio, log->bdev); bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); @@ -2139,7 +2139,7 @@ static void lbmStartIO(struct lbuf * bp) bio = bio_alloc(GFP_NOFS, 1); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); - bio->bi_bdev = log->bdev; + bio_set_dev(bio, log->bdev); bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); @@ -2205,7 +2205,7 @@ static void lbmIODone(struct bio *bio) bp->l_flag |= lbmDONE; - if (bio->bi_error) { + if (bio->bi_status) { bp->l_flag |= lbmERROR; jfs_err("lbmIODone: I/O error in JFS log"); diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 489aaa1403e5..1c4b9ad4d7ab 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -280,7 +280,7 @@ static void metapage_read_end_io(struct bio *bio) { struct page *page = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_status) { printk(KERN_ERR "metapage_read_end_io: I/O error\n"); SetPageError(page); } @@ -337,7 +337,7 @@ static void metapage_write_end_io(struct bio *bio) BUG_ON(!PagePrivate(page)); - if (bio->bi_error) { + if (bio->bi_status) { printk(KERN_ERR "metapage_write_end_io: I/O error\n"); SetPageError(page); } @@ -430,7 +430,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc) len = min(xlen, (int)JFS_SBI(inode->i_sb)->nbperpage); bio = bio_alloc(GFP_NOFS, 1); - bio->bi_bdev = inode->i_sb->s_bdev; + bio_set_dev(bio, inode->i_sb->s_bdev); bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9); bio->bi_end_io = metapage_write_end_io; bio->bi_private = page; @@ -510,7 +510,7 @@ static int metapage_readpage(struct file *fp, struct page *page) submit_bio(bio); bio = bio_alloc(GFP_NOFS, 1); - bio->bi_bdev = inode->i_sb->s_bdev; + bio_set_dev(bio, inode->i_sb->s_bdev); bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9); bio->bi_end_io = metapage_read_end_io; @@ -664,6 +664,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock, INCREMENT(mpStat.pagealloc); mp = alloc_metapage(GFP_NOFS); mp->page = page; + mp->sb = inode->i_sb; mp->flag = 0; mp->xflag = COMMIT_PAGE; mp->count = 1; @@ -711,7 +712,8 @@ void force_metapage(struct metapage *mp) get_page(page); lock_page(page); set_page_dirty(page); - write_one_page(page, 1); + if (write_one_page(page)) + jfs_error(mp->sb, "write_one_page() failed\n"); clear_bit(META_forcewrite, &mp->flag); put_page(page); } @@ -756,7 +758,8 @@ void release_metapage(struct metapage * mp) set_page_dirty(page); if (test_bit(META_sync, &mp->flag)) { clear_bit(META_sync, &mp->flag); - write_one_page(page, 1); + if (write_one_page(page)) + jfs_error(mp->sb, "write_one_page() failed\n"); lock_page(page); /* write_one_page unlocks the page */ } } else if (mp->lsn) /* discard_metapage doesn't remove it */ diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index a869fb4a20d6..8b0ee514eb84 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -38,6 +38,7 @@ struct metapage { /* implementation */ struct page *page; + struct super_block *sb; unsigned int logical_size; /* Journal management */ diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 9895595fd2f2..d8658607bf46 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -362,7 +362,7 @@ static int chkSuper(struct super_block *sb) /* validate fs state */ if (j_sb->s_state != cpu_to_le32(FM_CLEAN) && - !(sb->s_flags & MS_RDONLY)) { + !sb_rdonly(sb)) { jfs_err("jfs_mount: Mount Failure: File System Dirty."); rc = -EINVAL; goto out; diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index bd9b641ada2c..7ddcb445a3d9 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -98,7 +98,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) goto out; } - VolumeSize = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits; + VolumeSize = i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits; if (VolumeSize) { if (newLVSize > VolumeSize) { @@ -211,7 +211,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) txQuiesce(sb); /* Reset size of direct inode */ - sbi->direct_inode->i_size = sb->s_bdev->bd_inode->i_size; + sbi->direct_inode->i_size = i_size_read(sb->s_bdev->bd_inode); if (sbi->mntflag & JFS_INLINELOG) { /* diff --git a/fs/jfs/super.c b/fs/jfs/super.c index e8aad7d87b8c..2f14677169c3 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -76,7 +76,7 @@ static void jfs_handle_error(struct super_block *sb) { struct jfs_sb_info *sbi = JFS_SBI(sb); - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; updateSuper(sb, FM_DIRTY); @@ -313,7 +313,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, } case Opt_resize_nosize: { - *newLVSize = sb->s_bdev->bd_inode->i_size >> + *newLVSize = i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits; if (*newLVSize == 0) pr_err("JFS: Cannot determine volume size\n"); @@ -468,7 +468,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) return -EINVAL; if (newLVSize) { - if (sb->s_flags & MS_RDONLY) { + if (sb_rdonly(sb)) { pr_err("JFS: resize requires volume to be mounted read-write\n"); return -EROFS; } @@ -477,7 +477,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) return rc; } - if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) { + if (sb_rdonly(sb) && !(*flags & MS_RDONLY)) { /* * Invalidate any previously read metadata. fsck may have * changed the on-disk data since we mounted r/o @@ -493,7 +493,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) dquot_resume(sb, -1); return ret; } - if ((!(sb->s_flags & MS_RDONLY)) && (*flags & MS_RDONLY)) { + if (!sb_rdonly(sb) && (*flags & MS_RDONLY)) { rc = dquot_suspend(sb, -1); if (rc < 0) return rc; @@ -502,7 +502,7 @@ static int jfs_remount(struct super_block *sb, int *flags, char *data) return rc; } if ((JFS_SBI(sb)->flag & JFS_NOINTEGRITY) != (flag & JFS_NOINTEGRITY)) - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { rc = jfs_umount_rw(sb); if (rc) return rc; @@ -579,7 +579,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) goto out_unload; } inode->i_ino = 0; - inode->i_size = sb->s_bdev->bd_inode->i_size; + inode->i_size = i_size_read(sb->s_bdev->bd_inode); inode->i_mapping->a_ops = &jfs_metapage_aops; hlist_add_fake(&inode->i_hash); mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); @@ -592,7 +592,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) jfs_err("jfs_mount failed w/return code = %d", rc); goto out_mount_failed; } - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) sbi->log = NULL; else { rc = jfs_mount_rw(sb, 0); @@ -619,16 +619,10 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) if (!sb->s_root) goto out_no_root; - /* logical blocks are represented by 40 bits in pxd_t, etc. */ - sb->s_maxbytes = ((u64) sb->s_blocksize) << 40; -#if BITS_PER_LONG == 32 - /* - * Page cache is indexed by long. - * I would use MAX_LFS_FILESIZE, but it's only half as big + /* logical blocks are represented by 40 bits in pxd_t, etc. + * and page cache is indexed by long */ - sb->s_maxbytes = min(((u64) PAGE_SIZE << 32) - 1, - (u64)sb->s_maxbytes); -#endif + sb->s_maxbytes = min(((loff_t)sb->s_blocksize) << 40, MAX_LFS_FILESIZE); sb->s_time_gran = 1; return 0; @@ -658,7 +652,7 @@ static int jfs_freeze(struct super_block *sb) struct jfs_log *log = sbi->log; int rc = 0; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { txQuiesce(sb); rc = lmLogShutdown(log); if (rc) { @@ -688,7 +682,7 @@ static int jfs_unfreeze(struct super_block *sb) struct jfs_log *log = sbi->log; int rc = 0; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { rc = updateSuper(sb, FM_MOUNT); if (rc) { jfs_error(sb, "updateSuper failed\n"); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index db5900aaa55a..89d1dc19340b 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -21,6 +21,7 @@ DEFINE_MUTEX(kernfs_mutex); static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by rename_lock */ +static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) @@ -507,6 +508,10 @@ void kernfs_put(struct kernfs_node *kn) struct kernfs_node *parent; struct kernfs_root *root; + /* + * kernfs_node is freed with ->count 0, kernfs_find_and_get_node_by_ino + * depends on this to filter reused stale node + */ if (!kn || !atomic_dec_and_test(&kn->count)) return; root = kernfs_root(kn); @@ -533,7 +538,9 @@ void kernfs_put(struct kernfs_node *kn) simple_xattrs_free(&kn->iattr->xattrs); } kfree(kn->iattr); - ida_simple_remove(&root->ino_ida, kn->ino); + spin_lock(&kernfs_idr_lock); + idr_remove(&root->ino_idr, kn->id.ino); + spin_unlock(&kernfs_idr_lock); kmem_cache_free(kernfs_node_cache, kn); kn = parent; @@ -542,7 +549,7 @@ void kernfs_put(struct kernfs_node *kn) goto repeat; } else { /* just released the root kn, free @root too */ - ida_destroy(&root->ino_ida); + idr_destroy(&root->ino_idr); kfree(root); } } @@ -559,7 +566,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) if (d_really_is_negative(dentry)) goto out_bad_unlocked; - kn = dentry->d_fsdata; + kn = kernfs_dentry_node(dentry); mutex_lock(&kernfs_mutex); /* The kernfs node has been deactivated */ @@ -567,7 +574,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) goto out_bad; /* The kernfs node has been moved? */ - if (dentry->d_parent->d_fsdata != kn->parent) + if (kernfs_dentry_node(dentry->d_parent) != kn->parent) goto out_bad; /* The kernfs node has been renamed */ @@ -587,14 +594,8 @@ out_bad_unlocked: return 0; } -static void kernfs_dop_release(struct dentry *dentry) -{ - kernfs_put(dentry->d_fsdata); -} - const struct dentry_operations kernfs_dops = { .d_revalidate = kernfs_dop_revalidate, - .d_release = kernfs_dop_release, }; /** @@ -610,8 +611,9 @@ const struct dentry_operations kernfs_dops = { */ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { - if (dentry->d_sb->s_op == &kernfs_sops) - return dentry->d_fsdata; + if (dentry->d_sb->s_op == &kernfs_sops && + !d_really_is_negative(dentry)) + return kernfs_dentry_node(dentry); return NULL; } @@ -620,6 +622,8 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, unsigned flags) { struct kernfs_node *kn; + u32 gen; + int cursor; int ret; name = kstrdup_const(name, GFP_KERNEL); @@ -630,11 +634,25 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, if (!kn) goto err_out1; - ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL); + idr_preload(GFP_KERNEL); + spin_lock(&kernfs_idr_lock); + cursor = idr_get_cursor(&root->ino_idr); + ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); + if (ret >= 0 && ret < cursor) + root->next_generation++; + gen = root->next_generation; + spin_unlock(&kernfs_idr_lock); + idr_preload_end(); if (ret < 0) goto err_out2; - kn->ino = ret; + kn->id.ino = ret; + kn->id.generation = gen; + /* + * set ino first. This barrier is paired with atomic_inc_not_zero in + * kernfs_find_and_get_node_by_ino + */ + smp_mb__before_atomic(); atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); @@ -666,6 +684,54 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, return kn; } +/* + * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number + * @root: the kernfs root + * @ino: inode number + * + * RETURNS: + * NULL on failure. Return a kernfs node with reference counter incremented + */ +struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root, + unsigned int ino) +{ + struct kernfs_node *kn; + + rcu_read_lock(); + kn = idr_find(&root->ino_idr, ino); + if (!kn) + goto out; + + /* + * Since kernfs_node is freed in RCU, it's possible an old node for ino + * is freed, but reused before RCU grace period. But a freed node (see + * kernfs_put) or an incompletedly initialized node (see + * __kernfs_new_node) should have 'count' 0. We can use this fact to + * filter out such node. + */ + if (!atomic_inc_not_zero(&kn->count)) { + kn = NULL; + goto out; + } + + /* + * The node could be a new node or a reused node. If it's a new node, + * we are ok. If it's reused because of RCU (because of + * SLAB_TYPESAFE_BY_RCU), the __kernfs_new_node always sets its 'ino' + * before 'count'. So if 'count' is uptodate, 'ino' should be uptodate, + * hence we can use 'ino' to filter stale node. + */ + if (kn->id.ino != ino) + goto out; + rcu_read_unlock(); + + return kn; +out: + rcu_read_unlock(); + kernfs_put(kn); + return NULL; +} + /** * kernfs_add_one - add kernfs_node to parent without warning * @kn: kernfs_node to be added @@ -875,13 +941,14 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, if (!root) return ERR_PTR(-ENOMEM); - ida_init(&root->ino_ida); + idr_init(&root->ino_idr); INIT_LIST_HEAD(&root->supers); + root->next_generation = 1; kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO, KERNFS_DIR); if (!kn) { - ida_destroy(&root->ino_ida); + idr_destroy(&root->ino_idr); kfree(root); return ERR_PTR(-ENOMEM); } @@ -984,7 +1051,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, unsigned int flags) { struct dentry *ret; - struct kernfs_node *parent = dentry->d_parent->d_fsdata; + struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; struct inode *inode; const void *ns = NULL; @@ -1001,8 +1068,6 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, ret = NULL; goto out_unlock; } - kernfs_get(kn); - dentry->d_fsdata = kn; /* attach dentry and inode */ inode = kernfs_get_inode(dir->i_sb, kn); @@ -1039,7 +1104,7 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry, static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) { - struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; @@ -1059,7 +1124,7 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { - struct kernfs_node *kn = old_dentry->d_fsdata; + struct kernfs_node *kn = kernfs_dentry_node(old_dentry); struct kernfs_node *new_parent = new_dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; @@ -1572,7 +1637,7 @@ static struct kernfs_node *kernfs_dir_next_pos(const void *ns, static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; - struct kernfs_node *parent = dentry->d_fsdata; + struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; const void *ns = NULL; @@ -1589,7 +1654,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) const char *name = pos->name; unsigned int type = dt_type(pos); int len = strlen(name); - ino_t ino = pos->ino; + ino_t ino = pos->id.ino; ctx->pos = pos->hash; file->private_data = pos; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index ac2dfe0c5a9c..9698e51656b1 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -616,7 +616,7 @@ static void kernfs_put_open_node(struct kernfs_node *kn, static int kernfs_fop_open(struct inode *inode, struct file *file) { - struct kernfs_node *kn = file->f_path.dentry->d_fsdata; + struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; @@ -768,7 +768,7 @@ static void kernfs_release_file(struct kernfs_node *kn, static int kernfs_fop_release(struct inode *inode, struct file *filp) { - struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; + struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { @@ -835,7 +835,7 @@ void kernfs_drain_open_files(struct kernfs_node *kn) static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); - struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; + struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); struct kernfs_open_node *on = kn->attr.open; if (!kernfs_get_active(kn)) @@ -895,7 +895,7 @@ repeat: * have the matching @file available. Look up the inodes * and generate the events manually. */ - inode = ilookup(info->sb, kn->ino); + inode = ilookup(info->sb, kn->id.ino); if (!inode) continue; @@ -903,7 +903,7 @@ repeat: if (parent) { struct inode *p_inode; - p_inode = ilookup(info->sb, parent->ino); + p_inode = ilookup(info->sb, parent->id.ino); if (p_inode) { fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, kn->name, 0); @@ -997,7 +997,7 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { - lockdep_init_map(&kn->dep_map, "s_active", key, 0); + lockdep_init_map(&kn->dep_map, "kn->count", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index fb4b4a79a0d6..a34303981deb 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -112,7 +112,7 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr) { struct inode *inode = d_inode(dentry); - struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_node *kn = inode->i_private; int error; if (!kn) @@ -154,7 +154,7 @@ static int kernfs_node_setsecdata(struct kernfs_iattrs *attrs, void **secdata, ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) { - struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_iattrs *attrs; attrs = kernfs_iattrs(kn); @@ -203,8 +203,8 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) int kernfs_iop_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { - struct kernfs_node *kn = path->dentry->d_fsdata; struct inode *inode = d_inode(path->dentry); + struct kernfs_node *kn = inode->i_private; mutex_lock(&kernfs_mutex); kernfs_refresh_inode(kn, inode); @@ -220,6 +220,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode) inode->i_private = kn; inode->i_mapping->a_ops = &kernfs_aops; inode->i_op = &kernfs_iops; + inode->i_generation = kn->id.generation; set_default_inode_attr(inode, kn->mode); kernfs_refresh_inode(kn, inode); @@ -265,7 +266,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) { struct inode *inode; - inode = iget_locked(sb, kn->ino); + inode = iget_locked(sb, kn->id.ino); if (inode && (inode->i_state & I_NEW)) kernfs_init_inode(kn, inode); diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 2d5144ab4251..0f260dcca177 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -70,6 +70,13 @@ struct kernfs_super_info { }; #define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info)) +static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry) +{ + if (d_really_is_negative(dentry)) + return NULL; + return d_inode(dentry)->i_private; +} + extern const struct super_operations kernfs_sops; extern struct kmem_cache *kernfs_node_cache; @@ -98,6 +105,8 @@ int kernfs_add_one(struct kernfs_node *kn); struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, unsigned flags); +struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root, + unsigned int ino); /* * file.c diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index d5b149a45be1..95a7c88baed9 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -16,6 +16,7 @@ #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/seq_file.h> +#include <linux/exportfs.h> #include "kernfs-internal.h" @@ -33,7 +34,7 @@ static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data) static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) { - struct kernfs_root *root = kernfs_root(dentry->d_fsdata); + struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry)); struct kernfs_syscall_ops *scops = root->syscall_ops; if (scops && scops->show_options) @@ -43,7 +44,7 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry) static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry) { - struct kernfs_node *node = dentry->d_fsdata; + struct kernfs_node *node = kernfs_dentry_node(dentry); struct kernfs_root *root = kernfs_root(node); struct kernfs_syscall_ops *scops = root->syscall_ops; @@ -64,6 +65,78 @@ const struct super_operations kernfs_sops = { .show_path = kernfs_sop_show_path, }; +/* + * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode + * number and generation + */ +struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, + const union kernfs_node_id *id) +{ + struct kernfs_node *kn; + + kn = kernfs_find_and_get_node_by_ino(root, id->ino); + if (!kn) + return NULL; + if (kn->id.generation != id->generation) { + kernfs_put(kn); + return NULL; + } + return kn; +} + +static struct inode *kernfs_fh_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + struct kernfs_super_info *info = kernfs_info(sb); + struct inode *inode; + struct kernfs_node *kn; + + if (ino == 0) + return ERR_PTR(-ESTALE); + + kn = kernfs_find_and_get_node_by_ino(info->root, ino); + if (!kn) + return ERR_PTR(-ESTALE); + inode = kernfs_get_inode(sb, kn); + kernfs_put(kn); + if (!inode) + return ERR_PTR(-ESTALE); + + if (generation && inode->i_generation != generation) { + /* we didn't find the right inode.. */ + iput(inode); + return ERR_PTR(-ESTALE); + } + return inode; +} + +static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_dentry(sb, fid, fh_len, fh_type, + kernfs_fh_get_inode); +} + +static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + return generic_fh_to_parent(sb, fid, fh_len, fh_type, + kernfs_fh_get_inode); +} + +static struct dentry *kernfs_get_parent_dentry(struct dentry *child) +{ + struct kernfs_node *kn = kernfs_dentry_node(child); + + return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent)); +} + +static const struct export_operations kernfs_export_ops = { + .fh_to_dentry = kernfs_fh_to_dentry, + .fh_to_parent = kernfs_fh_to_parent, + .get_parent = kernfs_get_parent_dentry, +}; + /** * kernfs_root_from_sb - determine kernfs_root associated with a super_block * @sb: the super_block in question @@ -159,6 +232,8 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic) sb->s_magic = magic; sb->s_op = &kernfs_sops; sb->s_xattr = kernfs_xattr_handlers; + if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP) + sb->s_export_op = &kernfs_export_ops; sb->s_time_gran = 1; /* get root inode, initialize and unlock it */ @@ -176,8 +251,6 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic) pr_debug("%s: could not get root dentry!\n", __func__); return -ENOMEM; } - kernfs_get(info->root->kn); - root->d_fsdata = info->root->kn; sb->s_root = root; sb->s_d_op = &kernfs_dops; return 0; @@ -283,7 +356,6 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, void kernfs_kill_sb(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); - struct kernfs_node *root_kn = sb->s_root->d_fsdata; mutex_lock(&kernfs_mutex); list_del(&info->node); @@ -295,7 +367,6 @@ void kernfs_kill_sb(struct super_block *sb) */ kill_anon_super(sb); kfree(info); - kernfs_put(root_kn); } /** @@ -330,7 +401,16 @@ struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns) void __init kernfs_init(void) { + + /* + * the slab is freed in RCU context, so kernfs_find_and_get_node_by_ino + * can access the slab lock free. This could introduce stale nodes, + * please see how kernfs_find_and_get_node_by_ino filters out stale + * nodes. + */ kernfs_node_cache = kmem_cache_create("kernfs_node_cache", sizeof(struct kernfs_node), - 0, SLAB_PANIC, NULL); + 0, + SLAB_PANIC | SLAB_TYPESAFE_BY_RCU, + NULL); } diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 1684af4a8b9b..08ccabd7047f 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -98,9 +98,9 @@ static int kernfs_get_target_path(struct kernfs_node *parent, return 0; } -static int kernfs_getlink(struct dentry *dentry, char *path) +static int kernfs_getlink(struct inode *inode, char *path) { - struct kernfs_node *kn = dentry->d_fsdata; + struct kernfs_node *kn = inode->i_private; struct kernfs_node *parent = kn->parent; struct kernfs_node *target = kn->symlink.target_kn; int error; @@ -124,7 +124,7 @@ static const char *kernfs_iop_get_link(struct dentry *dentry, body = kzalloc(PAGE_SIZE, GFP_KERNEL); if (!body) return ERR_PTR(-ENOMEM); - error = kernfs_getlink(dentry, body); + error = kernfs_getlink(inode, body); if (unlikely(error < 0)) { kfree(body); return ERR_PTR(error); diff --git a/fs/libfs.c b/fs/libfs.c index a04395334bb1..3aabe553fc45 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -974,7 +974,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, int err; int ret; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(file, start, end); if (err) return err; @@ -991,6 +991,10 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end, out: inode_unlock(inode); + /* check and advance again to catch errors after syncing out buffers */ + err = file_check_and_advance_wb_err(file); + if (ret == 0) + ret = err; return ret; } EXPORT_SYMBOL(__generic_file_fsync); diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index d3e40db28930..c349fc0f9b80 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -381,8 +381,9 @@ static void encode_nlm4_lock(struct xdr_stream *xdr, */ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -402,8 +403,9 @@ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -424,8 +426,9 @@ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -442,8 +445,9 @@ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -458,8 +462,10 @@ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req, */ static void nlm4_xdr_enc_res(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm4_stat(xdr, result->status); } @@ -479,8 +485,10 @@ static void nlm4_xdr_enc_res(struct rpc_rqst *req, */ static void nlm4_xdr_enc_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm4_stat(xdr, result->status); if (result->status == nlm_lck_denied) @@ -525,8 +533,9 @@ out: static int nlm4_xdr_dec_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -545,8 +554,9 @@ out: */ static int nlm4_xdr_dec_res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -566,15 +576,15 @@ out: #define PROC(proc, argtype, restype) \ [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ - .p_encode = (kxdreproc_t)nlm4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nlm4_xdr_dec_##restype, \ + .p_encode = nlm4_xdr_enc_##argtype, \ + .p_decode = nlm4_xdr_dec_##restype, \ .p_arglen = NLM4_##argtype##_sz, \ .p_replen = NLM4_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ .p_name = #proc, \ } -static struct rpc_procinfo nlm4_procedures[] = { +static const struct rpc_procinfo nlm4_procedures[] = { PROC(TEST, testargs, testres), PROC(LOCK, lockargs, res), PROC(CANCEL, cancargs, res), @@ -592,8 +602,10 @@ static struct rpc_procinfo nlm4_procedures[] = { PROC(GRANTED_RES, res, norep), }; +static unsigned int nlm_version4_counts[ARRAY_SIZE(nlm4_procedures)]; const struct rpc_version nlm_version4 = { .number = 4, .nrprocs = ARRAY_SIZE(nlm4_procedures), .procs = nlm4_procedures, + .counts = nlm_version4_counts, }; diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 27d577dbe51a..96c1d14c18f1 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -235,12 +235,8 @@ reclaimer(void *ptr) struct net *net = host->net; req = kmalloc(sizeof(*req), GFP_KERNEL); - if (!req) { - printk(KERN_ERR "lockd: reclaimer unable to alloc memory." - " Locks for %s won't be reclaimed!\n", - host->h_name); + if (!req) return 0; - } allow_signal(SIGKILL); diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 3e9f7874b975..3b4724a6c4ee 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -374,8 +374,9 @@ static void encode_nlm_lock(struct xdr_stream *xdr, */ static void nlm_xdr_enc_testargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -395,8 +396,9 @@ static void nlm_xdr_enc_testargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -417,8 +419,9 @@ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -435,8 +438,9 @@ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_args *args) + const void *data) { + const struct nlm_args *args = data; const struct nlm_lock *lock = &args->lock; encode_cookie(xdr, &args->cookie); @@ -451,8 +455,10 @@ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req, */ static void nlm_xdr_enc_res(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm_stat(xdr, result->status); } @@ -479,8 +485,10 @@ static void encode_nlm_testrply(struct xdr_stream *xdr, static void nlm_xdr_enc_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nlm_res *result) + const void *data) { + const struct nlm_res *result = data; + encode_cookie(xdr, &result->cookie); encode_nlm_stat(xdr, result->status); encode_nlm_testrply(xdr, result); @@ -523,8 +531,9 @@ out: static int nlm_xdr_dec_testres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -543,8 +552,9 @@ out: */ static int nlm_xdr_dec_res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nlm_res *result) + void *data) { + struct nlm_res *result = data; int error; error = decode_cookie(xdr, &result->cookie); @@ -564,15 +574,15 @@ out: #define PROC(proc, argtype, restype) \ [NLMPROC_##proc] = { \ .p_proc = NLMPROC_##proc, \ - .p_encode = (kxdreproc_t)nlm_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nlm_xdr_dec_##restype, \ + .p_encode = nlm_xdr_enc_##argtype, \ + .p_decode = nlm_xdr_dec_##restype, \ .p_arglen = NLM_##argtype##_sz, \ .p_replen = NLM_##restype##_sz, \ .p_statidx = NLMPROC_##proc, \ .p_name = #proc, \ } -static struct rpc_procinfo nlm_procedures[] = { +static const struct rpc_procinfo nlm_procedures[] = { PROC(TEST, testargs, testres), PROC(LOCK, lockargs, res), PROC(CANCEL, cancargs, res), @@ -590,16 +600,20 @@ static struct rpc_procinfo nlm_procedures[] = { PROC(GRANTED_RES, res, norep), }; +static unsigned int nlm_version1_counts[ARRAY_SIZE(nlm_procedures)]; static const struct rpc_version nlm_version1 = { - .number = 1, - .nrprocs = ARRAY_SIZE(nlm_procedures), - .procs = nlm_procedures, + .number = 1, + .nrprocs = ARRAY_SIZE(nlm_procedures), + .procs = nlm_procedures, + .counts = nlm_version1_counts, }; +static unsigned int nlm_version3_counts[ARRAY_SIZE(nlm_procedures)]; static const struct rpc_version nlm_version3 = { - .number = 3, - .nrprocs = ARRAY_SIZE(nlm_procedures), - .procs = nlm_procedures, + .number = 3, + .nrprocs = ARRAY_SIZE(nlm_procedures), + .procs = nlm_procedures, + .counts = nlm_version3_counts, }; static const struct rpc_version *nlm_versions[] = { @@ -613,9 +627,9 @@ static const struct rpc_version *nlm_versions[] = { static struct rpc_stat nlm_rpc_stats; const struct rpc_program nlm_program = { - .name = "lockd", - .number = NLM_PROGRAM, - .nrvers = ARRAY_SIZE(nlm_versions), - .version = nlm_versions, - .stats = &nlm_rpc_stats, + .name = "lockd", + .number = NLM_PROGRAM, + .nrvers = ARRAY_SIZE(nlm_versions), + .version = nlm_versions, + .stats = &nlm_rpc_stats, }; diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index 19166d4a8d31..9d8166c39c54 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -476,22 +476,23 @@ static void encode_priv(struct xdr_stream *xdr, const struct nsm_args *argp) } static void nsm_xdr_enc_mon(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nsm_args *argp) + const void *argp) { encode_mon_id(xdr, argp); encode_priv(xdr, argp); } static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nsm_args *argp) + const void *argp) { encode_mon_id(xdr, argp); } static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nsm_res *resp) + void *data) { + struct nsm_res *resp = data; __be32 *p; p = xdr_inline_decode(xdr, 4 + 4); @@ -507,8 +508,9 @@ static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp, static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nsm_res *resp) + void *data) { + struct nsm_res *resp = data; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -529,11 +531,11 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp, #define SM_monres_sz 2 #define SM_unmonres_sz 1 -static struct rpc_procinfo nsm_procedures[] = { +static const struct rpc_procinfo nsm_procedures[] = { [NSMPROC_MON] = { .p_proc = NSMPROC_MON, - .p_encode = (kxdreproc_t)nsm_xdr_enc_mon, - .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat_res, + .p_encode = nsm_xdr_enc_mon, + .p_decode = nsm_xdr_dec_stat_res, .p_arglen = SM_mon_sz, .p_replen = SM_monres_sz, .p_statidx = NSMPROC_MON, @@ -541,8 +543,8 @@ static struct rpc_procinfo nsm_procedures[] = { }, [NSMPROC_UNMON] = { .p_proc = NSMPROC_UNMON, - .p_encode = (kxdreproc_t)nsm_xdr_enc_unmon, - .p_decode = (kxdrdproc_t)nsm_xdr_dec_stat, + .p_encode = nsm_xdr_enc_unmon, + .p_decode = nsm_xdr_dec_stat, .p_arglen = SM_mon_id_sz, .p_replen = SM_unmonres_sz, .p_statidx = NSMPROC_UNMON, @@ -550,10 +552,12 @@ static struct rpc_procinfo nsm_procedures[] = { }, }; +static unsigned int nsm_version1_counts[ARRAY_SIZE(nsm_procedures)]; static const struct rpc_version nsm_version1 = { - .number = 1, - .nrprocs = ARRAY_SIZE(nsm_procedures), - .procs = nsm_procedures + .number = 1, + .nrprocs = ARRAY_SIZE(nsm_procedures), + .procs = nsm_procedures, + .counts = nsm_version1_counts, }; static const struct rpc_version *nsm_version[] = { @@ -563,9 +567,9 @@ static const struct rpc_version *nsm_version[] = { static struct rpc_stat nsm_stats; static const struct rpc_program nsm_program = { - .name = "statd", - .number = NSM_PROGRAM, - .nrvers = ARRAY_SIZE(nsm_version), - .version = nsm_version, - .stats = &nsm_stats + .name = "statd", + .number = NSM_PROGRAM, + .nrvers = ARRAY_SIZE(nsm_version), + .version = nsm_version, + .stats = &nsm_stats }; diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 5d481e8a1b5d..b995bdc13976 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -396,7 +396,7 @@ out_rqst: return error; } -static struct svc_serv_ops lockd_sv_ops = { +static const struct svc_serv_ops lockd_sv_ops = { .svo_shutdown = svc_rpcb_cleanup, .svo_enqueue_xprt = svc_xprt_do_enqueue, }; @@ -739,27 +739,33 @@ module_exit(exit_nlm); /* * Define NLM program and procedures */ -static struct svc_version nlmsvc_version1 = { - .vs_vers = 1, - .vs_nproc = 17, - .vs_proc = nlmsvc_procedures, - .vs_xdrsize = NLMSVC_XDRSIZE, +static unsigned int nlmsvc_version1_count[17]; +static const struct svc_version nlmsvc_version1 = { + .vs_vers = 1, + .vs_nproc = 17, + .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version1_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; -static struct svc_version nlmsvc_version3 = { - .vs_vers = 3, - .vs_nproc = 24, - .vs_proc = nlmsvc_procedures, - .vs_xdrsize = NLMSVC_XDRSIZE, +static unsigned int nlmsvc_version3_count[24]; +static const struct svc_version nlmsvc_version3 = { + .vs_vers = 3, + .vs_nproc = 24, + .vs_proc = nlmsvc_procedures, + .vs_count = nlmsvc_version3_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; #ifdef CONFIG_LOCKD_V4 -static struct svc_version nlmsvc_version4 = { - .vs_vers = 4, - .vs_nproc = 24, - .vs_proc = nlmsvc_procedures4, - .vs_xdrsize = NLMSVC_XDRSIZE, +static unsigned int nlmsvc_version4_count[24]; +static const struct svc_version nlmsvc_version4 = { + .vs_vers = 4, + .vs_nproc = 24, + .vs_proc = nlmsvc_procedures4, + .vs_count = nlmsvc_version4_count, + .vs_xdrsize = NLMSVC_XDRSIZE, }; #endif -static struct svc_version * nlmsvc_version[] = { +static const struct svc_version *nlmsvc_version[] = { [1] = &nlmsvc_version1, [3] = &nlmsvc_version3, #ifdef CONFIG_LOCKD_V4 diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 09c576f26c7b..82925f17ec45 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -62,7 +62,7 @@ no_locks: * NULL: Test for presence of service */ static __be32 -nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nlm4svc_proc_null(struct svc_rqst *rqstp) { dprintk("lockd: NULL called\n"); return rpc_success; @@ -72,9 +72,9 @@ nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * TEST: Check for conflicting lock */ static __be32 -nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -99,9 +99,15 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_test(struct svc_rqst *rqstp) { + return __nlm4svc_proc_test(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) +{ + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -141,9 +147,15 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_lock(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_lock(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; @@ -170,13 +182,19 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_cancel(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_cancel(rqstp, rqstp->rq_resp); +} + /* * UNLOCK: release a lock */ static __be32 -nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; @@ -203,14 +221,21 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_unlock(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_unlock(rqstp, rqstp->rq_resp); +} + /* * GRANTED: A server calls us to tell that a process' lock request * was granted */ static __be32 -nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; + resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); @@ -219,6 +244,12 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlm4svc_proc_granted(struct svc_rqst *rqstp) +{ + return __nlm4svc_proc_granted(rqstp, rqstp->rq_resp); +} + /* * This is the generic lockd callback for async RPC calls */ @@ -243,9 +274,10 @@ static const struct rpc_call_ops nlm4svc_callback_ops = { * because we send the callback before the reply proper. I hope this * doesn't break any clients. */ -static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp, - __be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res *)) +static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, + __be32 (*func)(struct svc_rqst *, struct nlm_res *)) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_rqst *call; __be32 stat; @@ -261,7 +293,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args if (call == NULL) return rpc_system_err; - stat = func(rqstp, argp, &call->a_res); + stat = func(rqstp, &call->a_res); if (stat != 0) { nlmsvc_release_call(call); return stat; @@ -273,48 +305,44 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_success; } -static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp) { dprintk("lockd: TEST_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, argp, nlm4svc_proc_test); + return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, __nlm4svc_proc_test); } -static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp) { dprintk("lockd: LOCK_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlm4svc_proc_lock); + return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, __nlm4svc_proc_lock); } -static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp) { dprintk("lockd: CANCEL_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlm4svc_proc_cancel); + return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, __nlm4svc_proc_cancel); } -static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp) { dprintk("lockd: UNLOCK_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlm4svc_proc_unlock); + return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlm4svc_proc_unlock); } -static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp) { dprintk("lockd: GRANTED_MSG called\n"); - return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlm4svc_proc_granted); + return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, __nlm4svc_proc_granted); } /* * SHARE: create a DOS share or alter existing share. */ static __be32 -nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_share(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -345,9 +373,10 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, * UNSHARE: Release a DOS share. */ static __be32 -nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_unshare(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -378,22 +407,23 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, * NM_LOCK: Create an unmonitored lock */ static __be32 -nlm4svc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlm4svc_proc_nm_lock(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + dprintk("lockd: NM_LOCK called\n"); argp->monitor = 0; /* just clean the monitor flag */ - return nlm4svc_proc_lock(rqstp, argp, resp); + return nlm4svc_proc_lock(rqstp); } /* * FREE_ALL: Release all locks and shares held by client */ static __be32 -nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlm4svc_proc_free_all(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; /* Obtain client */ @@ -409,9 +439,10 @@ nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, * SM_NOTIFY: private callback from statd (not part of official NLM proto) */ static __be32 -nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, - void *resp) +nlm4svc_proc_sm_notify(struct svc_rqst *rqstp) { + struct nlm_reboot *argp = rqstp->rq_argp; + dprintk("lockd: SM_NOTIFY called\n"); if (!nlm_privileged_requester(rqstp)) { @@ -429,9 +460,10 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, * client sent a GRANTED_RES, let's remove the associated block */ static __be32 -nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, - void *resp) +nlm4svc_proc_granted_res(struct svc_rqst *rqstp) { + struct nlm_res *argp = rqstp->rq_argp; + if (!nlmsvc_ops) return rpc_success; @@ -463,9 +495,9 @@ nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ - { .pc_func = (svc_procfunc) nlm4svc_proc_##name, \ - .pc_decode = (kxdrproc_t) nlm4svc_decode_##xargt, \ - .pc_encode = (kxdrproc_t) nlm4svc_encode_##xrest, \ + { .pc_func = nlm4svc_proc_##name, \ + .pc_decode = nlm4svc_decode_##xargt, \ + .pc_encode = nlm4svc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ .pc_ressize = sizeof(struct nlm_##rest), \ @@ -475,7 +507,7 @@ struct nlm_void { int dummy; }; #define No (1+1024/4) /* netobj */ #define St 1 /* status */ #define Rg 4 /* range (offset + length) */ -struct svc_procedure nlmsvc_procedures4[] = { +const struct svc_procedure nlmsvc_procedures4[] = { PROC(null, void, void, void, void, 1), PROC(test, testargs, testres, args, res, Ck+St+2+No+Rg), PROC(lock, lockargs, res, args, res, Ck+St), diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index fb26b9f522e7..07915162581d 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -92,7 +92,7 @@ no_locks: * NULL: Test for presence of service */ static __be32 -nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nlmsvc_proc_null(struct svc_rqst *rqstp) { dprintk("lockd: NULL called\n"); return rpc_success; @@ -102,9 +102,9 @@ nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * TEST: Check for conflicting lock */ static __be32 -nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -130,9 +130,15 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_test(struct svc_rqst *rqstp) { + return __nlmsvc_proc_test(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) +{ + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; __be32 rc = rpc_success; @@ -172,9 +178,15 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp, } static __be32 -nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_lock(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_lock(rqstp, rqstp->rq_resp); +} + +static __be32 +__nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; struct net *net = SVC_NET(rqstp); @@ -202,13 +214,19 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_cancel(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_cancel(rqstp, rqstp->rq_resp); +} + /* * UNLOCK: release a lock */ static __be32 -nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; struct net *net = SVC_NET(rqstp); @@ -236,14 +254,21 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_unlock(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_unlock(rqstp, rqstp->rq_resp); +} + /* * GRANTED: A server calls us to tell that a process' lock request * was granted */ static __be32 -nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +__nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp) { + struct nlm_args *argp = rqstp->rq_argp; + resp->cookie = argp->cookie; dprintk("lockd: GRANTED called\n"); @@ -252,6 +277,12 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp, return rpc_success; } +static __be32 +nlmsvc_proc_granted(struct svc_rqst *rqstp) +{ + return __nlmsvc_proc_granted(rqstp, rqstp->rq_resp); +} + /* * This is the generic lockd callback for async RPC calls */ @@ -284,9 +315,10 @@ static const struct rpc_call_ops nlmsvc_callback_ops = { * because we send the callback before the reply proper. I hope this * doesn't break any clients. */ -static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp, - __be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res *)) +static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, + __be32 (*func)(struct svc_rqst *, struct nlm_res *)) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_rqst *call; __be32 stat; @@ -302,7 +334,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args if (call == NULL) return rpc_system_err; - stat = func(rqstp, argp, &call->a_res); + stat = func(rqstp, &call->a_res); if (stat != 0) { nlmsvc_release_call(call); return stat; @@ -314,50 +346,46 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args return rpc_success; } -static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp) { dprintk("lockd: TEST_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, argp, nlmsvc_proc_test); + return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, __nlmsvc_proc_test); } -static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp) { dprintk("lockd: LOCK_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlmsvc_proc_lock); + return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, __nlmsvc_proc_lock); } -static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp) { dprintk("lockd: CANCEL_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlmsvc_proc_cancel); + return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, __nlmsvc_proc_cancel); } static __be32 -nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp) { dprintk("lockd: UNLOCK_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlmsvc_proc_unlock); + return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlmsvc_proc_unlock); } static __be32 -nlmsvc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_granted_msg(struct svc_rqst *rqstp) { dprintk("lockd: GRANTED_MSG called\n"); - return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlmsvc_proc_granted); + return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, __nlmsvc_proc_granted); } /* * SHARE: create a DOS share or alter existing share. */ static __be32 -nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_share(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -388,9 +416,10 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp, * UNSHARE: Release a DOS share. */ static __be32 -nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_unshare(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + struct nlm_res *resp = rqstp->rq_resp; struct nlm_host *host; struct nlm_file *file; @@ -421,22 +450,23 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp, * NM_LOCK: Create an unmonitored lock */ static __be32 -nlmsvc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp, - struct nlm_res *resp) +nlmsvc_proc_nm_lock(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; + dprintk("lockd: NM_LOCK called\n"); argp->monitor = 0; /* just clean the monitor flag */ - return nlmsvc_proc_lock(rqstp, argp, resp); + return nlmsvc_proc_lock(rqstp); } /* * FREE_ALL: Release all locks and shares held by client */ static __be32 -nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, - void *resp) +nlmsvc_proc_free_all(struct svc_rqst *rqstp) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; /* Obtain client */ @@ -452,9 +482,10 @@ nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp, * SM_NOTIFY: private callback from statd (not part of official NLM proto) */ static __be32 -nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, - void *resp) +nlmsvc_proc_sm_notify(struct svc_rqst *rqstp) { + struct nlm_reboot *argp = rqstp->rq_argp; + dprintk("lockd: SM_NOTIFY called\n"); if (!nlm_privileged_requester(rqstp)) { @@ -472,9 +503,10 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp, * client sent a GRANTED_RES, let's remove the associated block */ static __be32 -nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, - void *resp) +nlmsvc_proc_granted_res(struct svc_rqst *rqstp) { + struct nlm_res *argp = rqstp->rq_argp; + if (!nlmsvc_ops) return rpc_success; @@ -505,9 +537,9 @@ nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res *argp, struct nlm_void { int dummy; }; #define PROC(name, xargt, xrest, argt, rest, respsize) \ - { .pc_func = (svc_procfunc) nlmsvc_proc_##name, \ - .pc_decode = (kxdrproc_t) nlmsvc_decode_##xargt, \ - .pc_encode = (kxdrproc_t) nlmsvc_encode_##xrest, \ + { .pc_func = nlmsvc_proc_##name, \ + .pc_decode = nlmsvc_decode_##xargt, \ + .pc_encode = nlmsvc_encode_##xrest, \ .pc_release = NULL, \ .pc_argsize = sizeof(struct nlm_##argt), \ .pc_ressize = sizeof(struct nlm_##rest), \ @@ -519,7 +551,7 @@ struct nlm_void { int dummy; }; #define No (1+1024/4) /* Net Obj */ #define Rg 2 /* range - offset + size */ -struct svc_procedure nlmsvc_procedures[] = { +const struct svc_procedure nlmsvc_procedures[] = { PROC(null, void, void, void, void, 1), PROC(test, testargs, testres, args, res, Ck+St+2+No+Rg), PROC(lock, lockargs, res, args, res, Ck+St), diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 5b651daad518..442bbd0b0b29 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -182,8 +182,9 @@ nlm_encode_testres(__be32 *p, struct nlm_res *resp) * First, the server side XDR functions */ int -nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -199,16 +200,19 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_testres(p, resp))) return 0; return xdr_ressize_check(rqstp, p); } int -nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -227,8 +231,9 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm_decode_cookie(p, &argp->cookie))) @@ -243,8 +248,10 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; + if (!(p = nlm_decode_cookie(p, &argp->cookie)) || !(p = nlm_decode_lock(p, &argp->lock))) return 0; @@ -253,8 +260,9 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; memset(lock, 0, sizeof(*lock)); @@ -274,8 +282,10 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -284,8 +294,10 @@ nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -293,8 +305,9 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) +nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!(p = xdr_decode_string_inplace(p, &lock->caller, @@ -305,8 +318,10 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) } int -nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) +nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_reboot *argp = rqstp->rq_argp; + if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN))) return 0; argp->state = ntohl(*p++); @@ -316,8 +331,10 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) } int -nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_argp; + if (!(p = nlm_decode_cookie(p, &resp->cookie))) return 0; resp->status = *p++; @@ -325,13 +342,13 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } int -nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index dfa4789cd460..2a0cd5679c49 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -179,8 +179,9 @@ nlm4_encode_testres(__be32 *p, struct nlm_res *resp) * First, the server side XDR functions */ int -nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -196,16 +197,19 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_testres(p, resp))) return 0; return xdr_ressize_check(rqstp, p); } int -nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -224,8 +228,9 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!(p = nlm4_decode_cookie(p, &argp->cookie))) @@ -240,8 +245,10 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; + if (!(p = nlm4_decode_cookie(p, &argp->cookie)) || !(p = nlm4_decode_lock(p, &argp->lock))) return 0; @@ -250,8 +257,9 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) +nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; memset(lock, 0, sizeof(*lock)); @@ -271,8 +279,10 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp) } int -nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -281,8 +291,10 @@ nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_resp; + if (!(p = nlm4_encode_cookie(p, &resp->cookie))) return 0; *p++ = resp->status; @@ -290,8 +302,9 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) +nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!(p = xdr_decode_string_inplace(p, &lock->caller, @@ -302,8 +315,10 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp) } int -nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp) +nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_reboot *argp = rqstp->rq_argp; + if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN))) return 0; argp->state = ntohl(*p++); @@ -313,8 +328,10 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp } int -nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) +nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) { + struct nlm_res *resp = rqstp->rq_argp; + if (!(p = nlm4_decode_cookie(p, &resp->cookie))) return 0; resp->status = *p++; @@ -322,13 +339,13 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp) } int -nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } int -nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } diff --git a/fs/locks.c b/fs/locks.c index af2031a1fcff..1bd71c4d663a 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -137,6 +137,7 @@ #define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK) #define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) #define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) +#define IS_REMOTELCK(fl) (fl->fl_pid <= 0) static inline bool is_remote_lock(struct file *filp) { @@ -270,6 +271,22 @@ locks_check_ctx_lists(struct inode *inode) } } +static void +locks_check_ctx_file_list(struct file *filp, struct list_head *list, + char *list_type) +{ + struct file_lock *fl; + struct inode *inode = locks_inode(filp); + + list_for_each_entry(fl, list, fl_list) + if (fl->fl_file == filp) + pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " + " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", + list_type, MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), inode->i_ino, + fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); +} + void locks_free_lock_context(struct inode *inode) { @@ -733,7 +750,6 @@ static void locks_wake_up_blocks(struct file_lock *blocker) static void locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) { - fl->fl_nspid = get_pid(task_tgid(current)); list_add_tail(&fl->fl_list, before); locks_insert_global_locks(fl); } @@ -743,10 +759,6 @@ locks_unlink_lock_ctx(struct file_lock *fl) { locks_delete_global_locks(fl); list_del_init(&fl->fl_list); - if (fl->fl_nspid) { - put_pid(fl->fl_nspid); - fl->fl_nspid = NULL; - } locks_wake_up_blocks(fl); } @@ -823,8 +835,6 @@ posix_test_lock(struct file *filp, struct file_lock *fl) list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { if (posix_locks_conflict(fl, cfl)) { locks_copy_conflock(fl, cfl); - if (cfl->fl_nspid) - fl->fl_pid = pid_vnr(cfl->fl_nspid); goto out; } } @@ -1858,8 +1868,8 @@ EXPORT_SYMBOL(generic_setlease); * * Call this to establish a lease on the file. The "lease" argument is not * used for F_UNLCK requests and may be NULL. For commands that set or alter - * an existing lease, the (*lease)->fl_lmops->lm_break operation must be set; - * if not, this function will return -ENOLCK (and generate a scary-looking + * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be + * set; if not, this function will return -ENOLCK (and generate a scary-looking * stack trace). * * The "priv" pointer is passed directly to the lm_setup function as-is. It @@ -1972,15 +1982,13 @@ EXPORT_SYMBOL(locks_lock_inode_wait); * @cmd: the type of lock to apply. * * Apply a %FL_FLOCK style lock to an open file descriptor. - * The @cmd can be one of + * The @cmd can be one of: * - * %LOCK_SH -- a shared lock. - * - * %LOCK_EX -- an exclusive lock. - * - * %LOCK_UN -- remove an existing lock. - * - * %LOCK_MAND -- a `mandatory' flock. This exists to emulate Windows Share Modes. + * - %LOCK_SH -- a shared lock. + * - %LOCK_EX -- an exclusive lock. + * - %LOCK_UN -- remove an existing lock. + * - %LOCK_MAND -- a 'mandatory' flock. + * This exists to emulate Windows Share Modes. * * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other * processes read and write access respectively. @@ -2050,9 +2058,33 @@ int vfs_test_lock(struct file *filp, struct file_lock *fl) } EXPORT_SYMBOL_GPL(vfs_test_lock); +/** + * locks_translate_pid - translate a file_lock's fl_pid number into a namespace + * @fl: The file_lock who's fl_pid should be translated + * @ns: The namespace into which the pid should be translated + * + * Used to tranlate a fl_pid into a namespace virtual pid number + */ +static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns) +{ + pid_t vnr; + struct pid *pid; + + if (IS_OFDLCK(fl)) + return -1; + if (IS_REMOTELCK(fl)) + return fl->fl_pid; + + rcu_read_lock(); + pid = find_pid_ns(fl->fl_pid, &init_pid_ns); + vnr = pid_nr_ns(pid, ns); + rcu_read_unlock(); + return vnr; +} + static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { - flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid; + flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via @@ -2074,7 +2106,7 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { - flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid; + flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; @@ -2086,49 +2118,44 @@ static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ -int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l) +int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) { - struct file_lock file_lock; - struct flock flock; + struct file_lock *fl; int error; - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; + fl = locks_alloc_lock(); + if (fl == NULL) + return -ENOMEM; error = -EINVAL; - if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK)) + if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; - error = flock_to_posix_lock(filp, &file_lock, &flock); + error = flock_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_GETLK; - file_lock.fl_flags |= FL_OFDLCK; - file_lock.fl_owner = filp; + fl->fl_flags |= FL_OFDLCK; + fl->fl_owner = filp; } - error = vfs_test_lock(filp, &file_lock); + error = vfs_test_lock(filp, fl); if (error) goto out; - flock.l_type = file_lock.fl_type; - if (file_lock.fl_type != F_UNLCK) { - error = posix_lock_to_flock(&flock, &file_lock); + flock->l_type = fl->fl_type; + if (fl->fl_type != F_UNLCK) { + error = posix_lock_to_flock(flock, fl); if (error) - goto rel_priv; + goto out; } - error = -EFAULT; - if (!copy_to_user(l, &flock, sizeof(flock))) - error = 0; -rel_priv: - locks_release_private(&file_lock); out: + locks_free_lock(fl); return error; } @@ -2218,26 +2245,16 @@ check_fmode_for_setlk(struct file_lock *fl) * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, - struct flock __user *l) + struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct flock flock; - struct inode *inode; + struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - inode = locks_inode(filp); - - /* - * This might block, so we do it before checking the inode. - */ - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; - /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ @@ -2246,7 +2263,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } - error = flock_to_posix_lock(filp, file_lock, &flock); + error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2261,7 +2278,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, switch (cmd) { case F_OFD_SETLK: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLK; @@ -2270,7 +2287,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, break; case F_OFD_SETLKW: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLKW; @@ -2315,47 +2332,43 @@ out: /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ -int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l) +int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) { - struct file_lock file_lock; - struct flock64 flock; + struct file_lock *fl; int error; - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; + fl = locks_alloc_lock(); + if (fl == NULL) + return -ENOMEM; + error = -EINVAL; - if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK)) + if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) goto out; - error = flock64_to_posix_lock(filp, &file_lock, &flock); + error = flock64_to_posix_lock(filp, fl, flock); if (error) goto out; if (cmd == F_OFD_GETLK) { error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_GETLK64; - file_lock.fl_flags |= FL_OFDLCK; - file_lock.fl_owner = filp; + fl->fl_flags |= FL_OFDLCK; + fl->fl_owner = filp; } - error = vfs_test_lock(filp, &file_lock); + error = vfs_test_lock(filp, fl); if (error) goto out; - flock.l_type = file_lock.fl_type; - if (file_lock.fl_type != F_UNLCK) - posix_lock_to_flock64(&flock, &file_lock); - - error = -EFAULT; - if (!copy_to_user(l, &flock, sizeof(flock))) - error = 0; + flock->l_type = fl->fl_type; + if (fl->fl_type != F_UNLCK) + posix_lock_to_flock64(flock, fl); - locks_release_private(&file_lock); out: + locks_free_lock(fl); return error; } @@ -2363,26 +2376,16 @@ out: * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, - struct flock64 __user *l) + struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct flock64 flock; - struct inode *inode; + struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - /* - * This might block, so we do it before checking the inode. - */ - error = -EFAULT; - if (copy_from_user(&flock, l, sizeof(flock))) - goto out; - - inode = locks_inode(filp); - /* Don't allow mandatory locks on files that may be memory mapped * and shared. */ @@ -2391,7 +2394,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; } - error = flock64_to_posix_lock(filp, file_lock, &flock); + error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2406,7 +2409,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, switch (cmd) { case F_OFD_SETLK: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLK64; @@ -2415,7 +2418,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, break; case F_OFD_SETLKW: error = -EINVAL; - if (flock.l_pid != 0) + if (flock->l_pid != 0) goto out; cmd = F_SETLKW64; @@ -2562,6 +2565,12 @@ void locks_remove_file(struct file *filp) /* remove any leases */ locks_remove_lease(filp, ctx); + + spin_lock(&ctx->flc_lock); + locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX"); + locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK"); + locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE"); + spin_unlock(&ctx->flc_lock); } /** @@ -2615,22 +2624,16 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, { struct inode *inode = NULL; unsigned int fl_pid; + struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; - if (fl->fl_nspid) { - struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; - - /* Don't let fl_pid change based on who is reading the file */ - fl_pid = pid_nr_ns(fl->fl_nspid, proc_pidns); - - /* - * If there isn't a fl_pid don't display who is waiting on - * the lock if we are called from locks_show, or if we are - * called from __show_fd_info - skip lock entirely - */ - if (fl_pid == 0) - return; - } else - fl_pid = fl->fl_pid; + fl_pid = locks_translate_pid(fl, proc_pidns); + /* + * If there isn't a fl_pid don't display who is waiting on + * the lock if we are called from locks_show, or if we are + * called from __show_fd_info - skip lock entirely + */ + if (fl_pid == 0) + return; if (fl->fl_file != NULL) inode = locks_inode(fl->fl_file); @@ -2705,7 +2708,7 @@ static int locks_show(struct seq_file *f, void *v) fl = hlist_entry(v, struct file_lock, fl_link); - if (fl->fl_nspid && !pid_nr_ns(fl->fl_nspid, proc_pidns)) + if (locks_translate_pid(fl, proc_pidns) == 0) return 0; lock_get_status(f, fl, iter->li_pos, ""); diff --git a/fs/mbcache.c b/fs/mbcache.c index b19be429d655..d818fd236787 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -10,13 +10,14 @@ /* * Mbcache is a simple key-value store. Keys need not be unique, however * key-value pairs are expected to be unique (we use this fact in - * mb_cache_entry_delete_block()). + * mb_cache_entry_delete()). * * Ext2 and ext4 use this cache for deduplication of extended attribute blocks. - * They use hash of a block contents as a key and block number as a value. - * That's why keys need not be unique (different xattr blocks may end up having - * the same hash). However block number always uniquely identifies a cache - * entry. + * Ext4 also uses it for deduplication of xattr values stored in inodes. + * They use hash of data as a key and provide a value that may represent a + * block or inode number. That's why keys need not be unique (hash of different + * data may be the same). However user provided value always uniquely + * identifies a cache entry. * * We provide functions for creation and removal of entries, search by key, * and a special "delete entry with given key-value pair" operation. Fixed @@ -62,15 +63,15 @@ static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache, * @cache - cache where the entry should be created * @mask - gfp mask with which the entry should be allocated * @key - key of the entry - * @block - block that contains data - * @reusable - is the block reusable by other inodes? + * @value - value of the entry + * @reusable - is the entry reusable by others? * - * Creates entry in @cache with key @key and records that data is stored in - * block @block. The function returns -EBUSY if entry with the same key - * and for the same block already exists in cache. Otherwise 0 is returned. + * Creates entry in @cache with key @key and value @value. The function returns + * -EBUSY if entry with the same key and value already exists in cache. + * Otherwise 0 is returned. */ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, - sector_t block, bool reusable) + u64 value, bool reusable) { struct mb_cache_entry *entry, *dup; struct hlist_bl_node *dup_node; @@ -91,12 +92,12 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, /* One ref for hash, one ref returned */ atomic_set(&entry->e_refcnt, 1); entry->e_key = key; - entry->e_block = block; + entry->e_value = value; entry->e_reusable = reusable; head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) { - if (dup->e_key == key && dup->e_block == block) { + if (dup->e_key == key && dup->e_value == value) { hlist_bl_unlock(head); kmem_cache_free(mb_entry_cache, entry); return -EBUSY; @@ -187,13 +188,13 @@ struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, EXPORT_SYMBOL(mb_cache_entry_find_next); /* - * mb_cache_entry_get - get a cache entry by block number (and key) + * mb_cache_entry_get - get a cache entry by value (and key) * @cache - cache we work with - * @key - key of block number @block - * @block - block number + * @key - key + * @value - value */ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, - sector_t block) + u64 value) { struct hlist_bl_node *node; struct hlist_bl_head *head; @@ -202,7 +203,7 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_block == block) { + if (entry->e_key == key && entry->e_value == value) { atomic_inc(&entry->e_refcnt); goto out; } @@ -214,15 +215,14 @@ out: } EXPORT_SYMBOL(mb_cache_entry_get); -/* mb_cache_entry_delete_block - remove information about block from cache +/* mb_cache_entry_delete - remove a cache entry * @cache - cache we work with - * @key - key of block @block - * @block - block number + * @key - key + * @value - value * - * Remove entry from cache @cache with key @key with data stored in @block. + * Remove entry from cache @cache with key @key and value @value. */ -void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, - sector_t block) +void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value) { struct hlist_bl_node *node; struct hlist_bl_head *head; @@ -231,7 +231,7 @@ void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, head = mb_cache_entry_head(cache, key); hlist_bl_lock(head); hlist_bl_for_each_entry(entry, node, head, e_hash_list) { - if (entry->e_key == key && entry->e_block == block) { + if (entry->e_key == key && entry->e_value == value) { /* We keep hash list reference to keep entry alive */ hlist_bl_del_init(&entry->e_hash_list); hlist_bl_unlock(head); @@ -248,7 +248,7 @@ void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key, } hlist_bl_unlock(head); } -EXPORT_SYMBOL(mb_cache_entry_delete_block); +EXPORT_SYMBOL(mb_cache_entry_delete); /* mb_cache_entry_touch - cache entry got used * @cache - cache the entry belongs to diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 7edc9b395700..baa9721f1299 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -57,7 +57,7 @@ static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); return err; diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 6ac76b0434e9..b6829d679643 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -42,7 +42,7 @@ static void minix_put_super(struct super_block *sb) int i; struct minix_sb_info *sbi = minix_sb(sb); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */ sbi->s_ms->s_state = sbi->s_mount_state; mark_buffer_dirty(sbi->s_sbh); @@ -125,7 +125,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data) sync_filesystem(sb); ms = sbi->s_ms; - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) return 0; if (*flags & MS_RDONLY) { if (ms->s_state & MINIX_VALID_FS || @@ -293,7 +293,7 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) if (!s->s_root) goto out_no_root; - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */ ms->s_state &= ~MINIX_VALID_FS; mark_buffer_dirty(bh); diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c index 4c57c9af6946..2d1ca08870f7 100644 --- a/fs/minix/itree_common.c +++ b/fs/minix/itree_common.c @@ -142,7 +142,7 @@ changed: return -EAGAIN; } -static inline int get_block(struct inode * inode, sector_t block, +static int get_block(struct inode * inode, sector_t block, struct buffer_head *bh, int create) { int err = -EIO; diff --git a/fs/mount.h b/fs/mount.h index bf1fda6eed8f..6790767d1883 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -16,7 +16,7 @@ struct mnt_namespace { u64 event; unsigned int mounts; /* # of mounts in the namespace */ unsigned int pending_mounts; -}; +} __randomize_layout; struct mnt_pcp { int mnt_count; @@ -58,6 +58,7 @@ struct mount { struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ + struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; @@ -68,7 +69,7 @@ struct mount { struct hlist_head mnt_pins; struct fs_pin mnt_umount; struct dentry *mnt_ex_mountpoint; -}; +} __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ diff --git a/fs/mpage.c b/fs/mpage.c index baff8f820c29..c991faec70b9 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -50,7 +50,8 @@ static void mpage_end_io(struct bio *bio) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - page_endio(page, op_is_write(bio_op(bio)), bio->bi_error); + page_endio(page, op_is_write(bio_op(bio)), + blk_status_to_errno(bio->bi_status)); } bio_put(bio); @@ -82,7 +83,7 @@ mpage_alloc(struct block_device *bdev, } if (bio) { - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = first_sector; } return bio; @@ -344,6 +345,7 @@ confused: * * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be * submitted in the following order: + * * 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16 * * because the indirect block has to be read to get the mappings of blocks @@ -466,6 +468,16 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) try_to_free_buffers(page); } +/* + * For situations where we want to clean all buffers attached to a page. + * We don't need to calculate how many buffers are attached to the page, + * we just need to specify a number larger than the maximum number of buffers. + */ +void clean_page_buffers(struct page *page) +{ + clean_buffers(page, ~0U); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -603,10 +615,8 @@ alloc_new: if (bio == NULL) { if (first_unmapped == blocks_per_page) { if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), - page, wbc)) { - clean_buffers(page, first_unmapped); + page, wbc)) goto out; - } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); @@ -614,6 +624,7 @@ alloc_new: goto confused; wbc_init_bio(wbc, bio); + bio->bi_write_hint = inode->i_write_hint; } /* diff --git a/fs/namei.c b/fs/namei.c index 6571a5f5112e..c75ea03ca147 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -447,8 +447,7 @@ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) umode_t mode = inode->i_mode; /* Nobody gets write access to a read-only fs. */ - if ((sb->s_flags & MS_RDONLY) && - (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) + if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) return -EROFS; } return 0; @@ -524,7 +523,7 @@ struct nameidata { struct inode *link_inode; unsigned root_seq; int dfd; -}; +} __randomize_layout; static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) { @@ -1008,7 +1007,7 @@ static int may_linkat(struct path *link) /* Source inode owner (or CAP_FOWNER) can hardlink all they like, * otherwise, it must be a safe source. */ - if (inode_owner_or_capable(inode) || safe_hardlink_source(inode)) + if (safe_hardlink_source(inode) || inode_owner_or_capable(inode)) return 0; audit_log_link_denied("linkat", link); @@ -1129,9 +1128,18 @@ static int follow_automount(struct path *path, struct nameidata *nd, * of the daemon to instantiate them before they can be used. */ if (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY | - LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) && - path->dentry->d_inode) - return -EISDIR; + LOOKUP_OPEN | LOOKUP_CREATE | + LOOKUP_AUTOMOUNT))) { + /* Positive dentry that isn't meant to trigger an + * automount, EISDIR will allow it to be used, + * otherwise there's no mount here "now" so return + * ENOENT. + */ + if (path->dentry->d_inode) + return -EISDIR; + else + return -ENOENT; + } if (path->dentry->d_sb->s_user_ns != &init_user_ns) return -EACCES; @@ -3400,7 +3408,6 @@ out: struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) { - static const struct qstr name = QSTR_INIT("/", 1); struct dentry *child = NULL; struct inode *dir = dentry->d_inode; struct inode *inode; @@ -3414,7 +3421,7 @@ struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag) if (!dir->i_op->tmpfile) goto out_err; error = -ENOMEM; - child = d_alloc(dentry, &name); + child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; error = dir->i_op->tmpfile(dir, child, mode); @@ -4332,6 +4339,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: + * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4 screws up. Current fix: serialization on @@ -4362,11 +4370,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, { int error; bool is_dir = d_is_dir(old_dentry); - const unsigned char *old_name; struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; + struct name_snapshot old_name; if (source == target) return 0; @@ -4413,7 +4421,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (error) return error; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); if (!is_dir || (flags & RENAME_EXCHANGE)) lock_two_nondirectories(source, target); @@ -4468,14 +4476,14 @@ out: inode_unlock(target); dput(new_dentry); if (!error) { - fsnotify_move(old_dir, new_dir, old_name, is_dir, + fsnotify_move(old_dir, new_dir, old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, old_dentry->d_name.name, new_is_dir, NULL, new_dentry); } } - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); return error; } diff --git a/fs/namespace.c b/fs/namespace.c index 5a4438445bf7..d18deb4c410b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -236,6 +236,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); + INIT_LIST_HEAD(&mnt->mnt_umounting); init_fs_pin(&mnt->mnt_umount, drop_mountpoint); } return mnt; @@ -274,7 +275,7 @@ int __mnt_is_readonly(struct vfsmount *mnt) { if (mnt->mnt_flags & MNT_READONLY) return 1; - if (mnt->mnt_sb->s_flags & MS_RDONLY) + if (sb_rdonly(mnt->mnt_sb)) return 1; return 0; } @@ -430,13 +431,18 @@ int __mnt_want_write_file(struct file *file) } /** - * mnt_want_write_file - get write access to a file's mount + * mnt_want_write_file_path - get write access to a file's mount * @file: the file who's mount on which to take a write * * This is like mnt_want_write, but it takes a file and can * do some optimisations if the file is open for write already + * + * Called by the vfs for cases when we have an open file at hand, but will do an + * inode operation on it (important distinction for files opened on overlayfs, + * since the file operations will come from the real underlying file, while + * inode operations come from the overlay). */ -int mnt_want_write_file(struct file *file) +int mnt_want_write_file_path(struct file *file) { int ret; @@ -446,6 +452,55 @@ int mnt_want_write_file(struct file *file) sb_end_write(file->f_path.mnt->mnt_sb); return ret; } + +static inline int may_write_real(struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; + struct dentry *upperdentry; + + /* Writable file? */ + if (file->f_mode & FMODE_WRITER) + return 0; + + /* Not overlayfs? */ + if (likely(!(dentry->d_flags & DCACHE_OP_REAL))) + return 0; + + /* File refers to upper, writable layer? */ + upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER); + if (upperdentry && + (file_inode(file) == d_inode(upperdentry) || + file_inode(file) == d_inode(dentry))) + return 0; + + /* Lower layer: can't write to real file, sorry... */ + return -EPERM; +} + +/** + * mnt_want_write_file - get write access to a file's mount + * @file: the file who's mount on which to take a write + * + * This is like mnt_want_write, but it takes a file and can + * do some optimisations if the file is open for write already + * + * Mostly called by filesystems from their ioctl operation before performing + * modification. On overlayfs this needs to check if the file is on a read-only + * lower layer and deny access in that case. + */ +int mnt_want_write_file(struct file *file) +{ + int ret; + + ret = may_write_real(file); + if (!ret) { + sb_start_write(file_inode(file)->i_sb); + ret = __mnt_want_write_file(file); + if (ret) + sb_end_write(file_inode(file)->i_sb); + } + return ret; +} EXPORT_SYMBOL_GPL(mnt_want_write_file); /** @@ -483,10 +538,16 @@ void __mnt_drop_write_file(struct file *file) __mnt_drop_write(file->f_path.mnt); } -void mnt_drop_write_file(struct file *file) +void mnt_drop_write_file_path(struct file *file) { mnt_drop_write(file->f_path.mnt); } + +void mnt_drop_write_file(struct file *file) +{ + __mnt_drop_write(file->f_path.mnt); + sb_end_write(file_inode(file)->i_sb); +} EXPORT_SYMBOL(mnt_drop_write_file); static int mnt_make_readonly(struct mount *mnt) @@ -970,7 +1031,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void if (!mnt) return ERR_PTR(-ENOMEM); - if (flags & MS_KERNMOUNT) + if (flags & SB_KERNMOUNT) mnt->mnt.mnt_flags = MNT_INTERNAL; root = mount_fs(type, flags, name, data); @@ -1002,7 +1063,7 @@ vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, if (mountpoint->d_sb->s_user_ns != &init_user_ns) return ERR_PTR(-EPERM); - return vfs_kern_mount(type, MS_SUBMOUNT, name, data); + return vfs_kern_mount(type, SB_SUBMOUNT, name, data); } EXPORT_SYMBOL_GPL(vfs_submount); @@ -1123,12 +1184,10 @@ static LLIST_HEAD(delayed_mntput_list); static void delayed_mntput(struct work_struct *unused) { struct llist_node *node = llist_del_all(&delayed_mntput_list); - struct llist_node *next; + struct mount *m, *t; - for (; node; node = next) { - next = llist_next(node); - cleanup_mnt(llist_entry(node, struct mount, mnt_llist)); - } + llist_for_each_entry_safe(m, t, node, mnt_llist) + cleanup_mnt(m); } static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); @@ -1237,65 +1296,6 @@ struct vfsmount *mnt_clone_internal(const struct path *path) return &p->mnt; } -static inline void mangle(struct seq_file *m, const char *s) -{ - seq_escape(m, s, " \t\n\\"); -} - -/* - * Simple .show_options callback for filesystems which don't want to - * implement more complex mount option showing. - * - * See also save_mount_options(). - */ -int generic_show_options(struct seq_file *m, struct dentry *root) -{ - const char *options; - - rcu_read_lock(); - options = rcu_dereference(root->d_sb->s_options); - - if (options != NULL && options[0]) { - seq_putc(m, ','); - mangle(m, options); - } - rcu_read_unlock(); - - return 0; -} -EXPORT_SYMBOL(generic_show_options); - -/* - * If filesystem uses generic_show_options(), this function should be - * called from the fill_super() callback. - * - * The .remount_fs callback usually needs to be handled in a special - * way, to make sure, that previous options are not overwritten if the - * remount fails. - * - * Also note, that if the filesystem's .remount_fs function doesn't - * reset all options to their default value, but changes only newly - * given options, then the displayed options will not reflect reality - * any more. - */ -void save_mount_options(struct super_block *sb, char *options) -{ - BUG_ON(sb->s_options); - rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL)); -} -EXPORT_SYMBOL(save_mount_options); - -void replace_mount_options(struct super_block *sb, char *options) -{ - char *old = sb->s_options; - rcu_assign_pointer(sb->s_options, options); - if (old) { - synchronize_rcu(); - kfree(old); - } -} -EXPORT_SYMBOL(replace_mount_options); - #ifdef CONFIG_PROC_FS /* iterator; we want it to have access to namespace_sem, thus here... */ static void *m_start(struct seq_file *m, loff_t *pos) @@ -1592,8 +1592,8 @@ static int do_umount(struct mount *mnt, int flags) if (!capable(CAP_SYS_ADMIN)) return -EPERM; down_write(&sb->s_umount); - if (!(sb->s_flags & MS_RDONLY)) - retval = do_remount_sb(sb, MS_RDONLY, NULL, 0); + if (!sb_rdonly(sb)) + retval = do_remount_sb(sb, SB_RDONLY, NULL, 0); up_write(&sb->s_umount); return retval; } @@ -1656,7 +1656,7 @@ out_unlock: namespace_unlock(); } -/* +/* * Is the caller allowed to modify his namespace? */ static inline bool may_mount(void) @@ -2117,7 +2117,7 @@ static void unlock_mount(struct mountpoint *where) static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) { - if (mnt->mnt.mnt_sb->s_flags & MS_NOUSER) + if (mnt->mnt.mnt_sb->s_flags & SB_NOUSER) return -EINVAL; if (d_is_dir(mp->m_dentry) != @@ -2131,9 +2131,9 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) * Sanity check the flags to change_mnt_propagation. */ -static int flags_to_propagation_type(int flags) +static int flags_to_propagation_type(int ms_flags) { - int type = flags & ~(MS_REC | MS_SILENT); + int type = ms_flags & ~(MS_REC | MS_SILENT); /* Fail if any non-propagation flags are set */ if (type & ~(MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) @@ -2147,18 +2147,18 @@ static int flags_to_propagation_type(int flags) /* * recursively change the type of the mountpoint. */ -static int do_change_type(struct path *path, int flag) +static int do_change_type(struct path *path, int ms_flags) { struct mount *m; struct mount *mnt = real_mount(path->mnt); - int recurse = flag & MS_REC; + int recurse = ms_flags & MS_REC; int type; int err = 0; if (path->dentry != path->mnt->mnt_root) return -EINVAL; - type = flags_to_propagation_type(flag); + type = flags_to_propagation_type(ms_flags); if (!type) return -EINVAL; @@ -2210,7 +2210,7 @@ static int do_loopback(struct path *path, const char *old_name, err = -EINVAL; if (mnt_ns_loop(old_path.dentry)) - goto out; + goto out; mp = lock_mount(path); err = PTR_ERR(mp); @@ -2280,8 +2280,8 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags) * If you've mounted a non-root directory somewhere and want to do remount * on it - tough luck. */ -static int do_remount(struct path *path, int flags, int mnt_flags, - void *data) +static int do_remount(struct path *path, int ms_flags, int sb_flags, + int mnt_flags, void *data) { int err; struct super_block *sb = path->mnt->mnt_sb; @@ -2325,12 +2325,12 @@ static int do_remount(struct path *path, int flags, int mnt_flags, return err; down_write(&sb->s_umount); - if (flags & MS_BIND) - err = change_mount_flags(path->mnt, flags); + if (ms_flags & MS_BIND) + err = change_mount_flags(path->mnt, ms_flags); else if (!capable(CAP_SYS_ADMIN)) err = -EPERM; else - err = do_remount_sb(sb, flags, data, 0); + err = do_remount_sb(sb, sb_flags, data, 0); if (!err) { lock_mount_hash(); mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK; @@ -2495,7 +2495,7 @@ static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags); * create a new mount for userspace and request it to be added into the * namespace's tree */ -static int do_new_mount(struct path *path, const char *fstype, int flags, +static int do_new_mount(struct path *path, const char *fstype, int sb_flags, int mnt_flags, const char *name, void *data) { struct file_system_type *type; @@ -2509,7 +2509,7 @@ static int do_new_mount(struct path *path, const char *fstype, int flags, if (!type) return -ENODEV; - mnt = vfs_kern_mount(type, flags, name, data); + mnt = vfs_kern_mount(type, sb_flags, name, data); if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) && !mnt->mnt_sb->s_subtype) mnt = fs_set_subtype(mnt, fstype); @@ -2764,8 +2764,8 @@ long do_mount(const char *dev_name, const char __user *dir_name, const char *type_page, unsigned long flags, void *data_page) { struct path path; + unsigned int mnt_flags = 0, sb_flags; int retval = 0; - int mnt_flags = 0; /* Discard magic */ if ((flags & MS_MGC_MSK) == MS_MGC_VAL) @@ -2775,6 +2775,9 @@ long do_mount(const char *dev_name, const char __user *dir_name, if (data_page) ((char *)data_page)[PAGE_SIZE - 1] = 0; + if (flags & MS_NOUSER) + return -EINVAL; + /* ... and get the mountpoint */ retval = user_path(dir_name, &path); if (retval) @@ -2784,7 +2787,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, type_page, flags, data_page); if (!retval && !may_mount()) retval = -EPERM; - if (!retval && (flags & MS_MANDLOCK) && !may_mandlock()) + if (!retval && (flags & SB_MANDLOCK) && !may_mandlock()) retval = -EPERM; if (retval) goto dput_out; @@ -2806,7 +2809,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, mnt_flags |= MNT_NODIRATIME; if (flags & MS_STRICTATIME) mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); - if (flags & MS_RDONLY) + if (flags & SB_RDONLY) mnt_flags |= MNT_READONLY; /* The default atime for remount is preservation */ @@ -2817,12 +2820,16 @@ long do_mount(const char *dev_name, const char __user *dir_name, mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK; } - flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | - MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | - MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT); + sb_flags = flags & (SB_RDONLY | + SB_SYNCHRONOUS | + SB_MANDLOCK | + SB_DIRSYNC | + SB_SILENT | + SB_POSIXACL | + SB_I_VERSION); if (flags & MS_REMOUNT) - retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags, + retval = do_remount(&path, flags, sb_flags, mnt_flags, data_page); else if (flags & MS_BIND) retval = do_loopback(&path, dev_name, flags & MS_REC); @@ -2831,7 +2838,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, else if (flags & MS_MOVE) retval = do_move_mount(&path, dev_name); else - retval = do_new_mount(&path, type_page, flags, mnt_flags, + retval = do_new_mount(&path, type_page, sb_flags, mnt_flags, dev_name, data_page); dput_out: path_put(&path); @@ -3238,7 +3245,6 @@ static void __init init_mount_tree(void) void __init mnt_init(void) { - unsigned u; int err; mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount), @@ -3247,22 +3253,17 @@ void __init mnt_init(void) mount_hashtable = alloc_large_system_hash("Mount-cache", sizeof(struct hlist_head), mhash_entries, 19, - 0, + HASH_ZERO, &m_hash_shift, &m_hash_mask, 0, 0); mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache", sizeof(struct hlist_head), mphash_entries, 19, - 0, + HASH_ZERO, &mp_hash_shift, &mp_hash_mask, 0, 0); if (!mount_hashtable || !mountpoint_hashtable) panic("Failed to allocate mount hash table\n"); - for (u = 0; u <= m_hash_mask; u++) - INIT_HLIST_HEAD(&mount_hashtable[u]); - for (u = 0; u <= mp_hash_mask; u++) - INIT_HLIST_HEAD(&mountpoint_hashtable[u]); - kernfs_init(); err = sysfs_init(); @@ -3287,7 +3288,7 @@ void put_mnt_ns(struct mnt_namespace *ns) struct vfsmount *kern_mount_data(struct file_system_type *type, void *data) { struct vfsmount *mnt; - mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, data); + mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, data); if (!IS_ERR(mnt)) { /* * it is a longterm mount, don't release mnt until @@ -3364,7 +3365,7 @@ static bool mnt_already_visible(struct mnt_namespace *ns, struct vfsmount *new, mnt_flags = mnt->mnt.mnt_flags; /* Don't miss readonly hidden in the superblock flags */ - if (mnt->mnt.mnt_sb->s_flags & MS_RDONLY) + if (sb_rdonly(mnt->mnt.mnt_sb)) mnt_flags |= MNT_LOCK_READONLY; /* Verify the mount flags are equal to or more permissive diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index 76965e772264..a06c07619ee6 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -23,7 +23,7 @@ static int ncp_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - return filemap_write_and_wait_range(file->f_mapping, start, end); + return file_write_and_wait_range(file, start, end); } /* diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c index 0c3905e0542e..6719c0be674d 100644 --- a/fs/ncpfs/mmap.c +++ b/fs/ncpfs/mmap.c @@ -89,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_fault *vmf) * -- nyc */ count_vm_event(PGMAJFAULT); - mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT); + count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); return VM_FAULT_MAJOR; } diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 69d02cf8cf37..5f93cfacb3d1 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT config PNFS_BLOCK tristate depends on NFS_V4_1 && BLK_DEV_DM + depends on 64BIT || LBDAF default NFS_V4 config PNFS_FLEXFILE_LAYOUT diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 98f4e5728a67..1fb118902d57 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_NFS_FS) += nfs.o CFLAGS_nfstrace.o += -I$(src) nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ io.o direct.o pagelist.o read.o symlink.o unlink.o \ - write.o namespace.o mount_clnt.o nfstrace.o + write.o namespace.o mount_clnt.o nfstrace.o export.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 0ca370d23ddb..995d707537da 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -130,7 +130,7 @@ bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, if (bio) { bio->bi_iter.bi_sector = disk_sector; - bio->bi_bdev = bdev; + bio_set_dev(bio, bdev); bio->bi_end_io = end_io; bio->bi_private = par; } @@ -188,7 +188,7 @@ static void bl_end_io_read(struct bio *bio) { struct parallel_io *par = bio->bi_private; - if (bio->bi_error) { + if (bio->bi_status) { struct nfs_pgio_header *header = par->data; if (!header->pnfs_error) @@ -319,7 +319,7 @@ static void bl_end_io_write(struct bio *bio) struct parallel_io *par = bio->bi_private; struct nfs_pgio_header *header = par->data; - if (bio->bi_error) { + if (bio->bi_status) { if (!header->pnfs_error) header->pnfs_error = -EIO; pnfs_set_lo_fail(header->lseg); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 73a1f928226c..2cddf7f437e6 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -226,26 +226,26 @@ err_bind: return ret; } -static struct svc_serv_ops nfs40_cb_sv_ops = { +static const struct svc_serv_ops nfs40_cb_sv_ops = { .svo_function = nfs4_callback_svc, .svo_enqueue_xprt = svc_xprt_do_enqueue, .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; #if defined(CONFIG_NFS_V4_1) -static struct svc_serv_ops nfs41_cb_sv_ops = { +static const struct svc_serv_ops nfs41_cb_sv_ops = { .svo_function = nfs41_callback_svc, .svo_enqueue_xprt = svc_xprt_do_enqueue, .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; -static struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static const struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = &nfs41_cb_sv_ops, }; #else -static struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static const struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = NULL, }; @@ -254,8 +254,8 @@ static struct svc_serv_ops *nfs4_cb_sv_ops[] = { static struct svc_serv *nfs_callback_create_svc(int minorversion) { struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion]; + const struct svc_serv_ops *sv_ops; struct svc_serv *serv; - struct svc_serv_ops *sv_ops; /* * Check whether we're already up and running. @@ -439,7 +439,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp) /* * Define NFS4 callback program */ -static struct svc_version *nfs4_callback_version[] = { +static const struct svc_version *nfs4_callback_version[] = { [1] = &nfs4_callback_version1, [4] = &nfs4_callback_version4, }; diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index c701c308fac5..3dc54d7cb19c 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -114,8 +114,7 @@ struct cb_sequenceres { uint32_t csr_target_highestslotid; }; -extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, - struct cb_sequenceres *res, +extern __be32 nfs4_callback_sequence(void *argp, void *resp, struct cb_process_state *cps); #define RCA4_TYPE_MASK_RDATA_DLG 0 @@ -134,15 +133,13 @@ struct cb_recallanyargs { uint32_t craa_type_mask; }; -extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, - void *dummy, +extern __be32 nfs4_callback_recallany(void *argp, void *resp, struct cb_process_state *cps); struct cb_recallslotargs { uint32_t crsa_target_highest_slotid; }; -extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, - void *dummy, +extern __be32 nfs4_callback_recallslot(void *argp, void *resp, struct cb_process_state *cps); struct cb_layoutrecallargs { @@ -159,9 +156,8 @@ struct cb_layoutrecallargs { }; }; -extern __be32 nfs4_callback_layoutrecall( - struct cb_layoutrecallargs *args, - void *dummy, struct cb_process_state *cps); +extern __be32 nfs4_callback_layoutrecall(void *argp, void *resp, + struct cb_process_state *cps); struct cb_devicenotifyitem { uint32_t cbd_notify_type; @@ -175,9 +171,8 @@ struct cb_devicenotifyargs { struct cb_devicenotifyitem *devs; }; -extern __be32 nfs4_callback_devicenotify( - struct cb_devicenotifyargs *args, - void *dummy, struct cb_process_state *cps); +extern __be32 nfs4_callback_devicenotify(void *argp, void *resp, + struct cb_process_state *cps); struct cb_notify_lock_args { struct nfs_fh cbnl_fh; @@ -185,15 +180,13 @@ struct cb_notify_lock_args { bool cbnl_valid; }; -extern __be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, - void *dummy, +extern __be32 nfs4_callback_notify_lock(void *argp, void *resp, struct cb_process_state *cps); #endif /* CONFIG_NFS_V4_1 */ extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *); -extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, - struct cb_getattrres *res, +extern __be32 nfs4_callback_getattr(void *argp, void *resp, struct cb_process_state *cps); -extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, +extern __be32 nfs4_callback_recall(void *argp, void *resp, struct cb_process_state *cps); #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 52479f180ea1..14358de173fb 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -19,10 +19,11 @@ #define NFSDBG_FACILITY NFSDBG_CALLBACK -__be32 nfs4_callback_getattr(struct cb_getattrargs *args, - struct cb_getattrres *res, +__be32 nfs4_callback_getattr(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_getattrargs *args = argp; + struct cb_getattrres *res = resp; struct nfs_delegation *delegation; struct nfs_inode *nfsi; struct inode *inode; @@ -50,7 +51,7 @@ __be32 nfs4_callback_getattr(struct cb_getattrargs *args, goto out_iput; res->size = i_size_read(inode); res->change_attr = delegation->change_attr; - if (nfsi->nrequests != 0) + if (nfs_have_writebacks(inode)) res->change_attr++; res->ctime = inode->i_ctime; res->mtime = inode->i_mtime; @@ -68,9 +69,10 @@ out: return res->status; } -__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, +__be32 nfs4_callback_recall(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallargs *args = argp; struct inode *inode; __be32 res; @@ -324,9 +326,10 @@ static u32 do_callback_layoutrecall(struct nfs_client *clp, return initiate_bulk_draining(clp, args); } -__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args, - void *dummy, struct cb_process_state *cps) +__be32 nfs4_callback_layoutrecall(void *argp, void *resp, + struct cb_process_state *cps) { + struct cb_layoutrecallargs *args = argp; u32 res = NFS4ERR_OP_NOT_IN_SESSION; if (cps->clp) @@ -345,9 +348,10 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp) do_callback_layoutrecall(clp, &args); } -__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args, - void *dummy, struct cb_process_state *cps) +__be32 nfs4_callback_devicenotify(void *argp, void *resp, + struct cb_process_state *cps) { + struct cb_devicenotifyargs *args = argp; int i; __be32 res = 0; struct nfs_client *clp = cps->clp; @@ -469,10 +473,11 @@ out: return status; } -__be32 nfs4_callback_sequence(struct cb_sequenceargs *args, - struct cb_sequenceres *res, +__be32 nfs4_callback_sequence(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_sequenceargs *args = argp; + struct cb_sequenceres *res = resp; struct nfs4_slot_table *tbl; struct nfs4_slot *slot; struct nfs_client *clp; @@ -571,9 +576,10 @@ validate_bitmap_values(unsigned long mask) return (mask & ~RCA4_TYPE_MASK_ALL) == 0; } -__be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy, +__be32 nfs4_callback_recallany(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallanyargs *args = argp; __be32 status; fmode_t flags = 0; @@ -606,9 +612,10 @@ out: } /* Reduce the fore channel's max_slots to the target value */ -__be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy, +__be32 nfs4_callback_recallslot(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_recallslotargs *args = argp; struct nfs4_slot_table *fc_tbl; __be32 status; @@ -631,9 +638,11 @@ out: return status; } -__be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, void *dummy, +__be32 nfs4_callback_notify_lock(void *argp, void *resp, struct cb_process_state *cps) { + struct cb_notify_lock_args *args = argp; + if (!cps->clp) /* set in cb_sequence */ return htonl(NFS4ERR_OP_NOT_IN_SESSION); diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 390ac9c39c59..681dd642f119 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -43,32 +43,27 @@ /* Internal error code */ #define NFS4ERR_RESOURCE_HDR 11050 -typedef __be32 (*callback_process_op_t)(void *, void *, - struct cb_process_state *); -typedef __be32 (*callback_decode_arg_t)(struct svc_rqst *, struct xdr_stream *, void *); -typedef __be32 (*callback_encode_res_t)(struct svc_rqst *, struct xdr_stream *, void *); - - struct callback_op { - callback_process_op_t process_op; - callback_decode_arg_t decode_args; - callback_encode_res_t encode_res; + __be32 (*process_op)(void *, void *, struct cb_process_state *); + __be32 (*decode_args)(struct svc_rqst *, struct xdr_stream *, void *); + __be32 (*encode_res)(struct svc_rqst *, struct xdr_stream *, + const void *); long res_maxsize; }; static struct callback_op callback_ops[]; -static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp) +static __be32 nfs4_callback_null(struct svc_rqst *rqstp) { return htonl(NFS4_OK); } -static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } -static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } @@ -184,8 +179,10 @@ static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op) return 0; } -static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_getattrargs *args) +static __be32 decode_getattr_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_getattrargs *args = argp; __be32 status; status = decode_fh(xdr, &args->fh); @@ -194,8 +191,10 @@ static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr return decode_bitmap(xdr, args->bitmap); } -static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallargs *args) +static __be32 decode_recall_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_recallargs *args = argp; __be32 *p; __be32 status; @@ -217,9 +216,9 @@ static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *statei } static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, - struct xdr_stream *xdr, - struct cb_layoutrecallargs *args) + struct xdr_stream *xdr, void *argp) { + struct cb_layoutrecallargs *args = argp; __be32 *p; __be32 status = 0; uint32_t iomode; @@ -262,8 +261,9 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp, static __be32 decode_devicenotify_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_devicenotifyargs *args) + void *argp) { + struct cb_devicenotifyargs *args = argp; __be32 *p; __be32 status = 0; u32 tmp; @@ -403,8 +403,9 @@ out: static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_sequenceargs *args) + void *argp) { + struct cb_sequenceargs *args = argp; __be32 *p; int i; __be32 status; @@ -450,8 +451,9 @@ out_free: static __be32 decode_recallany_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_recallanyargs *args) + void *argp) { + struct cb_recallanyargs *args = argp; uint32_t bitmap[2]; __be32 *p, status; @@ -469,8 +471,9 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp, static __be32 decode_recallslot_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, - struct cb_recallslotargs *args) + void *argp) { + struct cb_recallslotargs *args = argp; __be32 *p; p = read_buf(xdr, 4); @@ -510,8 +513,10 @@ static __be32 decode_lockowner(struct xdr_stream *xdr, struct cb_notify_lock_arg return 0; } -static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_notify_lock_args *args) +static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, + struct xdr_stream *xdr, void *argp) { + struct cb_notify_lock_args *args = argp; __be32 status; status = decode_fh(xdr, &args->cbnl_fh); @@ -641,8 +646,10 @@ static __be32 encode_op_hdr(struct xdr_stream *xdr, uint32_t op, __be32 res) return 0; } -static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, const struct cb_getattrres *res) +static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, + const void *resp) { + const struct cb_getattrres *res = resp; __be32 *savep = NULL; __be32 status = res->status; @@ -683,8 +690,9 @@ static __be32 encode_sessionid(struct xdr_stream *xdr, static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, - const struct cb_sequenceres *res) + const void *resp) { + const struct cb_sequenceres *res = resp; __be32 *p; __be32 status = res->csr_status; @@ -871,7 +879,7 @@ encode_hdr: /* * Decode, process and encode a COMPOUND */ -static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp) +static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) { struct cb_compound_hdr_arg hdr_arg = { 0 }; struct cb_compound_hdr_res hdr_res = { NULL }; @@ -907,7 +915,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r while (status == 0 && nops != hdr_arg.nops) { status = process_op(nops, rqstp, &xdr_in, - argp, &xdr_out, resp, &cps); + rqstp->rq_argp, &xdr_out, rqstp->rq_resp, + &cps); nops++; } @@ -937,48 +946,46 @@ static struct callback_op callback_ops[] = { .res_maxsize = CB_OP_HDR_RES_MAXSZ, }, [OP_CB_GETATTR] = { - .process_op = (callback_process_op_t)nfs4_callback_getattr, - .decode_args = (callback_decode_arg_t)decode_getattr_args, - .encode_res = (callback_encode_res_t)encode_getattr_res, + .process_op = nfs4_callback_getattr, + .decode_args = decode_getattr_args, + .encode_res = encode_getattr_res, .res_maxsize = CB_OP_GETATTR_RES_MAXSZ, }, [OP_CB_RECALL] = { - .process_op = (callback_process_op_t)nfs4_callback_recall, - .decode_args = (callback_decode_arg_t)decode_recall_args, + .process_op = nfs4_callback_recall, + .decode_args = decode_recall_args, .res_maxsize = CB_OP_RECALL_RES_MAXSZ, }, #if defined(CONFIG_NFS_V4_1) [OP_CB_LAYOUTRECALL] = { - .process_op = (callback_process_op_t)nfs4_callback_layoutrecall, - .decode_args = - (callback_decode_arg_t)decode_layoutrecall_args, + .process_op = nfs4_callback_layoutrecall, + .decode_args = decode_layoutrecall_args, .res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ, }, [OP_CB_NOTIFY_DEVICEID] = { - .process_op = (callback_process_op_t)nfs4_callback_devicenotify, - .decode_args = - (callback_decode_arg_t)decode_devicenotify_args, + .process_op = nfs4_callback_devicenotify, + .decode_args = decode_devicenotify_args, .res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ, }, [OP_CB_SEQUENCE] = { - .process_op = (callback_process_op_t)nfs4_callback_sequence, - .decode_args = (callback_decode_arg_t)decode_cb_sequence_args, - .encode_res = (callback_encode_res_t)encode_cb_sequence_res, + .process_op = nfs4_callback_sequence, + .decode_args = decode_cb_sequence_args, + .encode_res = encode_cb_sequence_res, .res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ, }, [OP_CB_RECALL_ANY] = { - .process_op = (callback_process_op_t)nfs4_callback_recallany, - .decode_args = (callback_decode_arg_t)decode_recallany_args, + .process_op = nfs4_callback_recallany, + .decode_args = decode_recallany_args, .res_maxsize = CB_OP_RECALLANY_RES_MAXSZ, }, [OP_CB_RECALL_SLOT] = { - .process_op = (callback_process_op_t)nfs4_callback_recallslot, - .decode_args = (callback_decode_arg_t)decode_recallslot_args, + .process_op = nfs4_callback_recallslot, + .decode_args = decode_recallslot_args, .res_maxsize = CB_OP_RECALLSLOT_RES_MAXSZ, }, [OP_CB_NOTIFY_LOCK] = { - .process_op = (callback_process_op_t)nfs4_callback_notify_lock, - .decode_args = (callback_decode_arg_t)decode_notify_lock_args, + .process_op = nfs4_callback_notify_lock, + .decode_args = decode_notify_lock_args, .res_maxsize = CB_OP_NOTIFY_LOCK_RES_MAXSZ, }, #endif /* CONFIG_NFS_V4_1 */ @@ -987,36 +994,40 @@ static struct callback_op callback_ops[] = { /* * Define NFS4 callback procedures */ -static struct svc_procedure nfs4_callback_procedures1[] = { +static const struct svc_procedure nfs4_callback_procedures1[] = { [CB_NULL] = { .pc_func = nfs4_callback_null, - .pc_decode = (kxdrproc_t)nfs4_decode_void, - .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_decode = nfs4_decode_void, + .pc_encode = nfs4_encode_void, .pc_xdrressize = 1, }, [CB_COMPOUND] = { .pc_func = nfs4_callback_compound, - .pc_encode = (kxdrproc_t)nfs4_encode_void, + .pc_encode = nfs4_encode_void, .pc_argsize = 256, .pc_ressize = 256, .pc_xdrressize = NFS4_CALLBACK_BUFSIZE, } }; -struct svc_version nfs4_callback_version1 = { +static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)]; +const struct svc_version nfs4_callback_version1 = { .vs_vers = 1, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, + .vs_count = nfs4_callback_count1, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, .vs_hidden = true, .vs_need_cong_ctrl = true, }; -struct svc_version nfs4_callback_version4 = { +static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)]; +const struct svc_version nfs4_callback_version4 = { .vs_vers = 4, .vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1), .vs_proc = nfs4_callback_procedures1, + .vs_count = nfs4_callback_count4, .vs_xdrsize = NFS4_CALLBACK_XDRSIZE, .vs_dispatch = NULL, .vs_hidden = true, diff --git a/fs/nfs/client.c b/fs/nfs/client.c index ee5ddbd36088..22880ef6d8dd 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -218,7 +218,6 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) static void pnfs_init_server(struct nfs_server *server) { rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); - rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); } #else @@ -820,6 +819,7 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour target->caps = source->caps; target->options = source->options; target->auth_info = source->auth_info; + target->port = source->port; } EXPORT_SYMBOL_GPL(nfs_server_copy_userdata); @@ -887,6 +887,7 @@ struct nfs_server *nfs_alloc_server(void) ida_init(&server->openowner_id); ida_init(&server->lockowner_id); pnfs_init_server(server); + rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC"); return server; } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index d7df5e67b0c1..606dd3871f66 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -1089,7 +1089,7 @@ bool nfs4_delegation_flush_on_close(const struct inode *inode) delegation = rcu_dereference(nfsi->delegation); if (delegation == NULL || !(delegation->type & FMODE_WRITE)) goto out; - if (nfsi->nrequests < delegation->pagemod_limit) + if (atomic_long_read(&nfsi->nrequests) < delegation->pagemod_limit) ret = false; out: rcu_read_unlock(); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 2ac00bf4ecf1..5ceaeb1f6fb6 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -151,7 +151,7 @@ struct nfs_cache_array { struct nfs_cache_array_entry array[0]; }; -typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int); +typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool); typedef struct { struct file *file; struct page *page; @@ -165,8 +165,8 @@ typedef struct { unsigned long timestamp; unsigned long gencount; unsigned int cache_entry_index; - unsigned int plus:1; - unsigned int eof:1; + bool plus; + bool eof; } nfs_readdir_descriptor_t; /* @@ -355,7 +355,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, if (error == -ENOTSUPP && desc->plus) { NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); - desc->plus = 0; + desc->plus = false; goto again; } goto error; @@ -557,7 +557,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en count++; - if (desc->plus != 0) + if (desc->plus) nfs_prime_dcache(file_dentry(desc->file), entry); status = nfs_readdir_add_to_array(entry, page); @@ -860,7 +860,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->ctx = ctx; desc->dir_cookie = &dir_ctx->dir_cookie; desc->decode = NFS_PROTO(inode)->decode_dirent; - desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0; + desc->plus = nfs_use_readdirplus(inode, ctx); if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) res = nfs_revalidate_mapping(inode, file->f_mapping); @@ -885,8 +885,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); nfs_zap_caches(inode); desc->page_index = 0; - desc->plus = 0; - desc->eof = 0; + desc->plus = false; + desc->eof = false; continue; } if (res < 0) @@ -1115,11 +1115,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) /* Force a full look up iff the parent directory has changed */ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { - - if (nfs_lookup_verify_inode(inode, flags)) { + error = nfs_lookup_verify_inode(inode, flags); + if (error) { if (flags & LOOKUP_RCU) return -ECHILD; - goto out_zap_parent; + if (error == -ESTALE) + goto out_zap_parent; + goto out_error; } nfs_advise_use_readdirplus(dir); goto out_valid; @@ -1144,8 +1146,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) trace_nfs_lookup_revalidate_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - if (error) + if (error == -ESTALE || error == -ENOENT) goto out_bad; + if (error) + goto out_error; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out_bad; if ((error = nfs_refresh_inode(inode, fattr)) != 0) @@ -1427,8 +1431,10 @@ static int nfs_finish_open(struct nfs_open_context *ctx, err = finish_open(file, dentry, do_open, opened); if (err) goto out; - nfs_file_set_open_context(file, ctx); - + if (S_ISREG(file->f_path.dentry->d_inode->i_mode)) + nfs_file_set_open_context(file, ctx); + else + err = -ESTALE; out: return err; } @@ -1512,7 +1518,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, d_drop(dentry); switch (err) { case -ENOENT: - d_add(dentry, NULL); + d_splice_alias(NULL, dentry); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case -EISDIR: @@ -2035,7 +2041,11 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, } error = rpc_wait_for_completion_task(task); - if (error == 0) + if (error != 0) { + ((struct nfs_renamedata *)task->tk_calldata)->cancelled = 1; + /* Paired with the atomic_dec_and_test() barrier in rpc_do_put_task() */ + smp_wmb(); + } else error = task->tk_status; rpc_put_task(task); nfs_mark_for_revalidate(old_inode); @@ -2250,7 +2260,6 @@ static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, str spin_lock(&inode->i_lock); retry = false; } - res->jiffies = cache->jiffies; res->cred = cache->cred; res->mask = cache->mask; list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); @@ -2286,7 +2295,6 @@ static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred, goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; - res->jiffies = cache->jiffies; res->cred = cache->cred; res->mask = cache->mask; err = 0; @@ -2334,7 +2342,6 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->jiffies = set->jiffies; cache->cred = get_rpccred(set->cred); cache->mask = set->mask; @@ -2362,16 +2369,40 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) } EXPORT_SYMBOL_GPL(nfs_access_add_cache); +#define NFS_MAY_READ (NFS4_ACCESS_READ) +#define NFS_MAY_WRITE (NFS4_ACCESS_MODIFY | \ + NFS4_ACCESS_EXTEND | \ + NFS4_ACCESS_DELETE) +#define NFS_FILE_MAY_WRITE (NFS4_ACCESS_MODIFY | \ + NFS4_ACCESS_EXTEND) +#define NFS_DIR_MAY_WRITE NFS_MAY_WRITE +#define NFS_MAY_LOOKUP (NFS4_ACCESS_LOOKUP) +#define NFS_MAY_EXECUTE (NFS4_ACCESS_EXECUTE) +static int +nfs_access_calc_mask(u32 access_result, umode_t umode) +{ + int mask = 0; + + if (access_result & NFS_MAY_READ) + mask |= MAY_READ; + if (S_ISDIR(umode)) { + if ((access_result & NFS_DIR_MAY_WRITE) == NFS_DIR_MAY_WRITE) + mask |= MAY_WRITE; + if ((access_result & NFS_MAY_LOOKUP) == NFS_MAY_LOOKUP) + mask |= MAY_EXEC; + } else if (S_ISREG(umode)) { + if ((access_result & NFS_FILE_MAY_WRITE) == NFS_FILE_MAY_WRITE) + mask |= MAY_WRITE; + if ((access_result & NFS_MAY_EXECUTE) == NFS_MAY_EXECUTE) + mask |= MAY_EXEC; + } else if (access_result & NFS_MAY_WRITE) + mask |= MAY_WRITE; + return mask; +} + void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result) { - entry->mask = 0; - if (access_result & NFS4_ACCESS_READ) - entry->mask |= MAY_READ; - if (access_result & - (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE)) - entry->mask |= MAY_WRITE; - if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE)) - entry->mask |= MAY_EXEC; + entry->mask = access_result; } EXPORT_SYMBOL_GPL(nfs_access_set_mask); @@ -2379,6 +2410,7 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) { struct nfs_access_entry cache; bool may_block = (mask & MAY_NOT_BLOCK) == 0; + int cache_mask; int status; trace_nfs_access_enter(inode); @@ -2394,9 +2426,9 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) goto out; /* Be clever: ask server to check for all possible rights */ - cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ; + cache.mask = NFS_MAY_LOOKUP | NFS_MAY_EXECUTE + | NFS_MAY_WRITE | NFS_MAY_READ; cache.cred = cred; - cache.jiffies = jiffies; status = NFS_PROTO(inode)->access(inode, &cache); if (status != 0) { if (status == -ESTALE) { @@ -2408,7 +2440,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) } nfs_access_add_cache(inode, &cache); out_cached: - if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) + cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode); + if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) status = -EACCES; out: trace_nfs_access_exit(inode, status); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 6fb9fad2d1e6..d2972d537469 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -616,13 +616,13 @@ nfs_direct_write_scan_commit_list(struct inode *inode, struct list_head *list, struct nfs_commit_info *cinfo) { - spin_lock(&cinfo->inode->i_lock); + mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); #ifdef CONFIG_NFS_V4_1 if (cinfo->ds != NULL && cinfo->ds->nwritten != 0) NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo); #endif nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0); - spin_unlock(&cinfo->inode->i_lock); + mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); } static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) diff --git a/fs/nfs/export.c b/fs/nfs/export.c new file mode 100644 index 000000000000..249cb96cc5b5 --- /dev/null +++ b/fs/nfs/export.c @@ -0,0 +1,177 @@ +/* + * Copyright (c) 2015, Primary Data, Inc. All rights reserved. + * + * Tao Peng <bergwolf@primarydata.com> + */ +#include <linux/dcache.h> +#include <linux/exportfs.h> +#include <linux/nfs.h> +#include <linux/nfs_fs.h> + +#include "internal.h" +#include "nfstrace.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +enum { + FILEID_HIGH_OFF = 0, /* inode fileid high */ + FILEID_LOW_OFF, /* inode fileid low */ + FILE_I_TYPE_OFF, /* inode type */ + EMBED_FH_OFF /* embeded server fh */ +}; + + +static struct nfs_fh *nfs_exp_embedfh(__u32 *p) +{ + return (struct nfs_fh *)(p + EMBED_FH_OFF); +} + +/* + * Let's break subtree checking for now... otherwise we'll have to embed parent fh + * but there might not be enough space. + */ +static int +nfs_encode_fh(struct inode *inode, __u32 *p, int *max_len, struct inode *parent) +{ + struct nfs_fh *server_fh = NFS_FH(inode); + struct nfs_fh *clnt_fh = nfs_exp_embedfh(p); + size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; + int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size); + + dprintk("%s: max fh len %d inode %p parent %p", + __func__, *max_len, inode, parent); + + if (*max_len < len || IS_AUTOMOUNT(inode)) { + dprintk("%s: fh len %d too small, required %d\n", + __func__, *max_len, len); + *max_len = len; + return FILEID_INVALID; + } + if (IS_AUTOMOUNT(inode)) { + *max_len = FILEID_INVALID; + goto out; + } + + p[FILEID_HIGH_OFF] = NFS_FILEID(inode) >> 32; + p[FILEID_LOW_OFF] = NFS_FILEID(inode); + p[FILE_I_TYPE_OFF] = inode->i_mode & S_IFMT; + p[len - 1] = 0; /* Padding */ + nfs_copy_fh(clnt_fh, server_fh); + *max_len = len; +out: + dprintk("%s: result fh fileid %llu mode %u size %d\n", + __func__, NFS_FILEID(inode), inode->i_mode, *max_len); + return *max_len; +} + +static struct dentry * +nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, + int fh_len, int fh_type) +{ + struct nfs4_label *label = NULL; + struct nfs_fattr *fattr = NULL; + struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw); + size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; + const struct nfs_rpc_ops *rpc_ops; + struct dentry *dentry; + struct inode *inode; + int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size); + u32 *p = fid->raw; + int ret; + + /* NULL translates to ESTALE */ + if (fh_len < len || fh_type != len) + return NULL; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) { + dentry = ERR_PTR(-ENOMEM); + goto out; + } + + fattr->fileid = ((u64)p[FILEID_HIGH_OFF] << 32) + p[FILEID_LOW_OFF]; + fattr->mode = p[FILE_I_TYPE_OFF]; + fattr->valid |= NFS_ATTR_FATTR_FILEID | NFS_ATTR_FATTR_TYPE; + + dprintk("%s: fileid %llu mode %d\n", __func__, fattr->fileid, fattr->mode); + + inode = nfs_ilookup(sb, fattr, server_fh); + if (inode) + goto out_found; + + label = nfs4_label_alloc(NFS_SB(sb), GFP_KERNEL); + if (IS_ERR(label)) { + dentry = ERR_CAST(label); + goto out_free_fattr; + } + + rpc_ops = NFS_SB(sb)->nfs_client->rpc_ops; + ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label); + if (ret) { + dprintk("%s: getattr failed %d\n", __func__, ret); + dentry = ERR_PTR(ret); + goto out_free_label; + } + + inode = nfs_fhget(sb, server_fh, fattr, label); + +out_found: + dentry = d_obtain_alias(inode); + +out_free_label: + nfs4_label_free(label); +out_free_fattr: + nfs_free_fattr(fattr); +out: + return dentry; +} + +static struct dentry * +nfs_get_parent(struct dentry *dentry) +{ + int ret; + struct inode *inode = d_inode(dentry), *pinode; + struct super_block *sb = inode->i_sb; + struct nfs_server *server = NFS_SB(sb); + struct nfs_fattr *fattr = NULL; + struct nfs4_label *label = NULL; + struct dentry *parent; + struct nfs_rpc_ops const *ops = server->nfs_client->rpc_ops; + struct nfs_fh fh; + + if (!ops->lookupp) + return ERR_PTR(-EACCES); + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) { + parent = ERR_PTR(-ENOMEM); + goto out; + } + + label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(label)) { + parent = ERR_CAST(label); + goto out_free_fattr; + } + + ret = ops->lookupp(inode, &fh, fattr, label); + if (ret) { + parent = ERR_PTR(ret); + goto out_free_label; + } + + pinode = nfs_fhget(sb, &fh, fattr, label); + parent = d_obtain_alias(pinode); +out_free_label: + nfs4_label_free(label); +out_free_fattr: + nfs_free_fattr(fattr); +out: + return parent; +} + +const struct export_operations nfs_export_ops = { + .encode_fh = nfs_encode_fh, + .fh_to_dentry = nfs_fh_to_dentry, + .get_parent = nfs_get_parent, +}; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 5713eb32a45e..0214dd1e1060 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -208,21 +208,19 @@ EXPORT_SYMBOL_GPL(nfs_file_mmap); * fall back to doing a synchronous write. */ static int -nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync) +nfs_file_fsync_commit(struct file *file, int datasync) { struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = file_inode(file); - int have_error, do_resend, status; + int do_resend, status; int ret = 0; dprintk("NFS: fsync file(%pD2) datasync %d\n", file, datasync); nfs_inc_stats(inode, NFSIOS_VFSFSYNC); do_resend = test_and_clear_bit(NFS_CONTEXT_RESEND_WRITES, &ctx->flags); - have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); status = nfs_commit_inode(inode, FLUSH_SYNC); - have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); - if (have_error) { + if (test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) { ret = xchg(&ctx->error, 0); if (ret) goto out; @@ -247,10 +245,16 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) trace_nfs_fsync_enter(inode); do { + struct nfs_open_context *ctx = nfs_file_open_context(file); ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags)) { + int ret2 = xchg(&ctx->error, 0); + if (ret2) + ret = ret2; + } if (ret != 0) break; - ret = nfs_file_fsync_commit(file, start, end, datasync); + ret = nfs_file_fsync_commit(file, datasync); if (!ret) ret = pnfs_sync_inode(inode, !!datasync); /* @@ -617,6 +621,8 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (result) goto out; } + if (iocb->ki_pos > i_size_read(inode)) + nfs_revalidate_mapping(inode, file->f_mapping); nfs_start_io_write(inode); result = generic_write_checks(iocb, from); @@ -629,11 +635,11 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (result <= 0) goto out; - result = generic_write_sync(iocb, result); - if (result < 0) - goto out; written = result; iocb->ki_pos += written; + result = generic_write_sync(iocb, written); + if (result < 0) + goto out; /* Return error values */ if (nfs_need_check_write(file, inode)) { @@ -742,15 +748,18 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) goto out; /* - * Revalidate the cache if the server has time stamps granular - * enough to detect subsecond changes. Otherwise, clear the - * cache to prevent missing any changes. + * Invalidate cache to prevent missing any changes. If + * the file is mapped, clear the page cache as well so + * those mappings will be loaded. * * This makes locking act as a cache coherency point. */ nfs_sync_mapping(filp->f_mapping); - if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) - nfs_zap_mapping(inode, filp->f_mapping); + if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) { + nfs_zap_caches(inode); + if (mapping_mapped(filp->f_mapping)) + nfs_revalidate_mapping(inode, filp->f_mapping); + } out: return status; } diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 1cf85d65b748..508126eb49f9 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -126,32 +126,13 @@ static int filelayout_async_handle_error(struct rpc_task *task, { struct pnfs_layout_hdr *lo = lseg->pls_layout; struct inode *inode = lo->plh_inode; - struct nfs_server *mds_server = NFS_SERVER(inode); struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); - struct nfs_client *mds_client = mds_server->nfs_client; struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; if (task->tk_status >= 0) return 0; switch (task->tk_status) { - /* MDS state errors */ - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - case -NFS4ERR_OPENMODE: - if (state == NULL) - break; - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - goto wait_on_recovery; - case -NFS4ERR_EXPIRED: - if (state != NULL) { - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - } - nfs4_schedule_lease_recovery(mds_client); - goto wait_on_recovery; /* DS session errors */ case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: @@ -172,6 +153,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -NFS4ERR_RETRY_UNCACHED_REP: break; /* Invalidate Layout errors */ + case -NFS4ERR_ACCESS: case -NFS4ERR_PNFS_NO_LAYOUT: case -ESTALE: /* mapped NFS4ERR_STALE */ case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ @@ -202,26 +184,17 @@ static int filelayout_async_handle_error(struct rpc_task *task, task->tk_status); nfs4_mark_deviceid_unavailable(devid); pnfs_error_mark_layout_for_return(inode, lseg); + pnfs_set_lo_fail(lseg); rpc_wake_up(&tbl->slot_tbl_waitq); /* fall through */ default: - pnfs_set_lo_fail(lseg); reset: dprintk("%s Retry through MDS. Error %d\n", __func__, task->tk_status); return -NFS4ERR_RESET_TO_MDS; } -out: task->tk_status = 0; return -EAGAIN; -out_bad_stateid: - task->tk_status = -EIO; - return 0; -wait_on_recovery: - rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); - if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) - rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); - goto out; } /* NFS_PROTO call done callback routines */ @@ -569,6 +542,10 @@ filelayout_check_deviceid(struct pnfs_layout_hdr *lo, struct nfs4_file_layout_dsaddr *dsaddr; int status = -EINVAL; + /* Is the deviceid already set? If so, we're good. */ + if (fl->dsaddr != NULL) + return 0; + /* find and reference the deviceid */ d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid, lo->plh_lc_cred, gfp_flags); @@ -580,8 +557,6 @@ filelayout_check_deviceid(struct pnfs_layout_hdr *lo, if (filelayout_test_devid_unavailable(&dsaddr->id_node)) goto out_put; - fl->dsaddr = dsaddr; - if (fl->first_stripe_index >= dsaddr->stripe_count) { dprintk("%s Bad first_stripe_index %u\n", __func__, fl->first_stripe_index); @@ -597,6 +572,13 @@ filelayout_check_deviceid(struct pnfs_layout_hdr *lo, goto out_put; } status = 0; + + /* + * Atomic compare and xchange to ensure we don't scribble + * over a non-NULL pointer. + */ + if (cmpxchg(&fl->dsaddr, NULL, dsaddr) != NULL) + goto out_put; out: return status; out_put: @@ -763,7 +745,8 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); dprintk("--> %s\n", __func__); - nfs4_fl_put_deviceid(fl->dsaddr); + if (fl->dsaddr != NULL) + nfs4_fl_put_deviceid(fl->dsaddr); /* This assumes a single RW lseg */ if (lseg->pls_range.iomode == IOMODE_RW) { struct nfs4_filelayout *flo; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 23542dc44a25..b0fa83a60754 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1050,34 +1050,10 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, { struct pnfs_layout_hdr *lo = lseg->pls_layout; struct inode *inode = lo->plh_inode; - struct nfs_server *mds_server = NFS_SERVER(inode); - struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); - struct nfs_client *mds_client = mds_server->nfs_client; struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; switch (task->tk_status) { - /* MDS state errors */ - case -NFS4ERR_DELEG_REVOKED: - case -NFS4ERR_ADMIN_REVOKED: - case -NFS4ERR_BAD_STATEID: - if (state == NULL) - break; - nfs_remove_bad_delegation(state->inode, NULL); - case -NFS4ERR_OPENMODE: - if (state == NULL) - break; - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - goto wait_on_recovery; - case -NFS4ERR_EXPIRED: - if (state != NULL) { - if (nfs4_schedule_stateid_recovery(mds_server, state) < 0) - goto out_bad_stateid; - } - nfs4_schedule_lease_recovery(mds_client); - goto wait_on_recovery; - /* DS session errors */ case -NFS4ERR_BADSESSION: case -NFS4ERR_BADSLOT: case -NFS4ERR_BAD_HIGH_SLOT: @@ -1137,17 +1113,8 @@ reset: task->tk_status); return -NFS4ERR_RESET_TO_MDS; } -out: task->tk_status = 0; return -EAGAIN; -out_bad_stateid: - task->tk_status = -EIO; - return 0; -wait_on_recovery: - rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL); - if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0) - rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task); - goto out; } /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ @@ -1875,6 +1842,10 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) int vers, ret; struct nfs_fh *fh; + if (!lseg || !(pnfs_is_valid_lseg(lseg) || + test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))) + goto out_err; + idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); ds = nfs4_ff_layout_prepare_ds(lseg, idx, true); if (!ds) diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 6df7a0cf5660..f32c58bbe556 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -32,6 +32,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) { nfs4_print_deviceid(&mirror_ds->id_node.deviceid); nfs4_pnfs_ds_put(mirror_ds->ds); + kfree(mirror_ds->ds_versions); kfree_rcu(mirror_ds, id_node.rcu); } diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c index 777b055063f6..3025fe8584a0 100644 --- a/fs/nfs/fscache-index.c +++ b/fs/nfs/fscache-index.c @@ -252,45 +252,6 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, } /* - * Indication from FS-Cache that the cookie is no longer cached - * - This function is called when the backing store currently caching a cookie - * is removed - * - The netfs should use this to clean up any markers indicating cached pages - * - This is mandatory for any object that may have data - */ -static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data) -{ - struct nfs_inode *nfsi = cookie_netfs_data; - struct pagevec pvec; - pgoff_t first; - int loop, nr_pages; - - pagevec_init(&pvec, 0); - first = 0; - - dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi); - - for (;;) { - /* grab a bunch of pages to unmark */ - nr_pages = pagevec_lookup(&pvec, - nfsi->vfs_inode.i_mapping, - first, - PAGEVEC_SIZE - pagevec_count(&pvec)); - if (!nr_pages) - break; - - for (loop = 0; loop < nr_pages; loop++) - ClearPageFsCache(pvec.pages[loop]); - - first = pvec.pages[nr_pages - 1]->index + 1; - - pvec.nr = nr_pages; - pagevec_release(&pvec); - cond_resched(); - } -} - -/* * Get an extra reference on a read context. * - This function can be absent if the completion function doesn't require a * context. @@ -330,7 +291,6 @@ const struct fscache_cookie_def nfs_fscache_inode_object_def = { .get_attr = nfs_fscache_inode_get_attr, .get_aux = nfs_fscache_inode_get_aux, .check_aux = nfs_fscache_inode_check_aux, - .now_uncached = nfs_fscache_inode_now_uncached, .get_context = nfs_fh_get_context, .put_context = nfs_fh_put_context, }; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 1de93ba78dc9..134d9f560240 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -386,6 +386,28 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, #endif EXPORT_SYMBOL_GPL(nfs_setsecurity); +/* Search for inode identified by fh, fileid and i_mode in inode cache. */ +struct inode * +nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) +{ + struct nfs_find_desc desc = { + .fh = fh, + .fattr = fattr, + }; + struct inode *inode; + unsigned long hash; + + if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) || + !(fattr->valid & NFS_ATTR_FATTR_TYPE)) + return NULL; + + hash = nfs_fattr_to_ino_t(fattr); + inode = ilookup5(sb, hash, nfs_find_actor, &desc); + + dprintk("%s: returning %p\n", __func__, inode); + return inode; +} + /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. @@ -525,8 +547,14 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_fscache_init_inode(inode); unlock_new_inode(inode); - } else - nfs_refresh_inode(inode, fattr); + } else { + int err = nfs_refresh_inode(inode, fattr); + if (err < 0) { + iput(inode); + inode = ERR_PTR(err); + goto out_no_inode; + } + } dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), @@ -1257,7 +1285,6 @@ static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { - struct nfs_inode *nfsi = NFS_I(inode); unsigned long ret = 0; if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) @@ -1287,7 +1314,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) && (fattr->valid & NFS_ATTR_FATTR_SIZE) && i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) - && nfsi->nrequests == 0) { + && !nfs_have_writebacks(inode)) { i_size_write(inode, nfs_size_to_loff_t(fattr->size)); ret |= NFS_INO_INVALID_ATTR; } @@ -1315,9 +1342,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat return 0; /* Has the inode gone and changed behind our back? */ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) - return -EIO; + return -ESTALE; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) - return -EIO; + return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ @@ -1795,7 +1822,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (new_isize != cur_isize) { /* Do we perhaps have any outstanding writes, or has * the file grown beyond our last write? */ - if (nfsi->nrequests == 0 || new_isize > cur_isize) { + if (!nfs_have_writebacks(inode) || new_isize > cur_isize) { i_size_write(inode, new_isize); if (!have_writers) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; @@ -1984,10 +2011,11 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); INIT_LIST_HEAD(&nfsi->commit_info.list); - nfsi->nrequests = 0; - nfsi->commit_info.ncommit = 0; + atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->commit_info.ncommit, 0); atomic_set(&nfsi->commit_info.rpcs_out, 0); init_rwsem(&nfsi->rmdir_sem); + mutex_init(&nfsi->commit_mutex); nfs4_init_once(nfsi); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 3e24392f2caa..5bdf952f414b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -7,9 +7,12 @@ #include <linux/security.h> #include <linux/crc32.h> #include <linux/nfs_page.h> +#include <linux/wait_bit.h> #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS) +extern const struct export_operations nfs_export_ops; + struct nfs_string; /* Maximum number of readahead requests @@ -225,8 +228,8 @@ static inline void nfs_fs_proc_exit(void) #endif /* callback_xdr.c */ -extern struct svc_version nfs4_callback_version1; -extern struct svc_version nfs4_callback_version4; +extern const struct svc_version nfs4_callback_version1; +extern const struct svc_version nfs4_callback_version4; struct nfs_pageio_descriptor; /* pagelist.c */ @@ -248,7 +251,6 @@ int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); -void nfs_pgio_data_destroy(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, @@ -270,19 +272,19 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, } /* nfs2xdr.c */ -extern struct rpc_procinfo nfs_procedures[]; +extern const struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, - struct nfs_entry *, int); + struct nfs_entry *, bool); /* nfs3xdr.c */ -extern struct rpc_procinfo nfs3_procedures[]; +extern const struct rpc_procinfo nfs3_procedures[]; extern int nfs3_decode_dirent(struct xdr_stream *, - struct nfs_entry *, int); + struct nfs_entry *, bool); /* nfs4xdr.c */ #if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, - struct nfs_entry *, int); + struct nfs_entry *, bool); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; @@ -292,7 +294,7 @@ extern const u32 nfs41_maxgetdevinfo_overhead; /* nfs4proc.c */ #if IS_ENABLED(CONFIG_NFS_V4) -extern struct rpc_procinfo nfs4_procedures[]; +extern const struct rpc_procinfo nfs4_procedures[]; #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL @@ -766,3 +768,10 @@ static inline bool nfs_error_is_fatal(int err) return false; } } + +static inline void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) +{ + ctx->error = error; + smp_wmb(); + set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); +} diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 09b190015df4..60bad882c123 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -304,7 +304,7 @@ static void encode_mntdirpath(struct xdr_stream *xdr, const char *pathname) } static void mnt_xdr_enc_dirpath(struct rpc_rqst *req, struct xdr_stream *xdr, - const char *dirpath) + const void *dirpath) { encode_mntdirpath(xdr, dirpath); } @@ -357,8 +357,9 @@ static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res) static int mnt_xdr_dec_mountres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct mountres *res) + void *data) { + struct mountres *res = data; int status; status = decode_status(xdr, res); @@ -449,8 +450,9 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res) static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, struct xdr_stream *xdr, - struct mountres *res) + void *data) { + struct mountres *res = data; int status; status = decode_fhs_status(xdr, res); @@ -464,11 +466,11 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req, return decode_auth_flavors(xdr, res); } -static struct rpc_procinfo mnt_procedures[] = { +static const struct rpc_procinfo mnt_procedures[] = { [MOUNTPROC_MNT] = { .p_proc = MOUNTPROC_MNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, - .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres, + .p_encode = mnt_xdr_enc_dirpath, + .p_decode = mnt_xdr_dec_mountres, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres_sz, .p_statidx = MOUNTPROC_MNT, @@ -476,18 +478,18 @@ static struct rpc_procinfo mnt_procedures[] = { }, [MOUNTPROC_UMNT] = { .p_proc = MOUNTPROC_UMNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_arglen = MNT_enc_dirpath_sz, .p_statidx = MOUNTPROC_UMNT, .p_name = "UMOUNT", }, }; -static struct rpc_procinfo mnt3_procedures[] = { +static const struct rpc_procinfo mnt3_procedures[] = { [MOUNTPROC3_MNT] = { .p_proc = MOUNTPROC3_MNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, - .p_decode = (kxdrdproc_t)mnt_xdr_dec_mountres3, + .p_encode = mnt_xdr_enc_dirpath, + .p_decode = mnt_xdr_dec_mountres3, .p_arglen = MNT_enc_dirpath_sz, .p_replen = MNT_dec_mountres3_sz, .p_statidx = MOUNTPROC3_MNT, @@ -495,24 +497,27 @@ static struct rpc_procinfo mnt3_procedures[] = { }, [MOUNTPROC3_UMNT] = { .p_proc = MOUNTPROC3_UMNT, - .p_encode = (kxdreproc_t)mnt_xdr_enc_dirpath, + .p_encode = mnt_xdr_enc_dirpath, .p_arglen = MNT_enc_dirpath_sz, .p_statidx = MOUNTPROC3_UMNT, .p_name = "UMOUNT", }, }; - +static unsigned int mnt_counts[ARRAY_SIZE(mnt_procedures)]; static const struct rpc_version mnt_version1 = { .number = 1, .nrprocs = ARRAY_SIZE(mnt_procedures), .procs = mnt_procedures, + .counts = mnt_counts, }; +static unsigned int mnt3_counts[ARRAY_SIZE(mnt3_procedures)]; static const struct rpc_version mnt_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(mnt3_procedures), .procs = mnt3_procedures, + .counts = mnt3_counts, }; static const struct rpc_version *mnt_version[] = { diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index b4e03ed8599d..fe68dabfbde6 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -568,8 +568,10 @@ out_default: static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_fh *fh) + const void *data) { + const struct nfs_fh *fh = data; + encode_fhandle(xdr, fh); } @@ -583,23 +585,29 @@ static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req, */ static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_sattrargs *args) + const void *data) { + const struct nfs_sattrargs *args = data; + encode_fhandle(xdr, args->fh); encode_sattr(xdr, args->sattr); } static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_diropargs *args) + const void *data) { + const struct nfs_diropargs *args = data; + encode_diropargs(xdr, args->fh, args->name, args->len); } static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readlinkargs *args) + const void *data) { + const struct nfs_readlinkargs *args = data; + encode_fhandle(xdr, args->fh); prepare_reply_buffer(req, args->pages, args->pgbase, args->pglen, NFS_readlinkres_sz); @@ -632,8 +640,10 @@ static void encode_readargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_readargs(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, args->count, NFS_readres_sz); @@ -672,8 +682,10 @@ static void encode_writeargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_writeargs(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; } @@ -688,16 +700,20 @@ static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_createargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_createargs *args) + const void *data) { + const struct nfs_createargs *args = data; + encode_diropargs(xdr, args->fh, args->name, args->len); encode_sattr(xdr, args->sattr); } static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; + encode_diropargs(xdr, args->fh, args->name.name, args->name.len); } @@ -711,8 +727,9 @@ static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; const struct qstr *old = args->old_name; const struct qstr *new = args->new_name; @@ -730,8 +747,10 @@ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_linkargs *args) + const void *data) { + const struct nfs_linkargs *args = data; + encode_fhandle(xdr, args->fromfh); encode_diropargs(xdr, args->tofh, args->toname, args->tolen); } @@ -747,8 +766,10 @@ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req, */ static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_symlinkargs *args) + const void *data) { + const struct nfs_symlinkargs *args = data; + encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen); encode_path(xdr, args->pages, args->pathlen); encode_sattr(xdr, args->sattr); @@ -777,8 +798,10 @@ static void encode_readdirargs(struct xdr_stream *xdr, static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_readdirargs *args) + const void *data) { + const struct nfs_readdirargs *args = data; + encode_readdirargs(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS_readdirres_sz); @@ -809,13 +832,13 @@ out_default: } static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { return decode_attrstat(xdr, result, NULL); } static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_diropok *result) + void *result) { return decode_diropres(xdr, result); } @@ -860,8 +883,9 @@ out_default: * }; */ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -882,8 +906,10 @@ out_default: } static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; + /* All NFSv2 writes are "file sync" writes */ result->verf->committed = NFS_FILE_SYNC; return decode_attrstat(xdr, result->fattr, &result->op_status); @@ -913,7 +939,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr, * }; */ int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, - int plus) + bool plus) { __be32 *p; int error; @@ -1034,7 +1060,7 @@ out_overflow: } static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs2_fsstat *result) + void *result) { enum nfs_stat status; int error; @@ -1118,15 +1144,15 @@ static int nfs_stat_to_errno(enum nfs_stat status) #define PROC(proc, argtype, restype, timer) \ [NFSPROC_##proc] = { \ .p_proc = NFSPROC_##proc, \ - .p_encode = (kxdreproc_t)nfs2_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs2_xdr_dec_##restype, \ + .p_encode = nfs2_xdr_enc_##argtype, \ + .p_decode = nfs2_xdr_dec_##restype, \ .p_arglen = NFS_##argtype##_sz, \ .p_replen = NFS_##restype##_sz, \ .p_timer = timer, \ .p_statidx = NFSPROC_##proc, \ .p_name = #proc, \ } -struct rpc_procinfo nfs_procedures[] = { +const struct rpc_procinfo nfs_procedures[] = { PROC(GETATTR, fhandle, attrstat, 1), PROC(SETATTR, sattrargs, attrstat, 0), PROC(LOOKUP, diropargs, diropres, 2), @@ -1144,8 +1170,10 @@ struct rpc_procinfo nfs_procedures[] = { PROC(STATFS, fhandle, statfsres, 0), }; +static unsigned int nfs_version2_counts[ARRAY_SIZE(nfs_procedures)]; const struct rpc_version nfs_version2 = { .number = 2, .nrprocs = ARRAY_SIZE(nfs_procedures), - .procs = nfs_procedures + .procs = nfs_procedures, + .counts = nfs_version2_counts, }; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 0c07b567118d..d1e87ec0df84 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -220,15 +220,8 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); nfs_refresh_inode(inode, res.fattr); - if (status == 0) { - entry->mask = 0; - if (res.access & NFS3_ACCESS_READ) - entry->mask |= MAY_READ; - if (res.access & (NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE)) - entry->mask |= MAY_WRITE; - if (res.access & (NFS3_ACCESS_LOOKUP|NFS3_ACCESS_EXECUTE)) - entry->mask |= MAY_EXEC; - } + if (status == 0) + nfs_access_set_mask(entry, res.access); nfs_free_fattr(res.fattr); out: dprintk("NFS reply access: %d\n", status); @@ -621,7 +614,7 @@ out: */ static int nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); __be32 *verf = NFS_I(dir)->cookieverf; diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 267126d32ec0..e82c9e553224 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -846,8 +846,10 @@ static void encode_diropargs3(struct xdr_stream *xdr, const struct nfs_fh *fh, */ static void nfs3_xdr_enc_getattr3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_fh *fh) + const void *data) { + const struct nfs_fh *fh = data; + encode_nfs_fh3(xdr, fh); } @@ -884,8 +886,9 @@ static void encode_sattrguard3(struct xdr_stream *xdr, static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_sattrargs *args) + const void *data) { + const struct nfs3_sattrargs *args = data; encode_nfs_fh3(xdr, args->fh); encode_sattr3(xdr, args->sattr); encode_sattrguard3(xdr, args); @@ -900,8 +903,10 @@ static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_lookup3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_diropargs *args) + const void *data) { + const struct nfs3_diropargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); } @@ -922,8 +927,10 @@ static void encode_access3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_accessargs *args) + const void *data) { + const struct nfs3_accessargs *args = data; + encode_access3args(xdr, args); } @@ -936,8 +943,10 @@ static void nfs3_xdr_enc_access3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readlinkargs *args) + const void *data) { + const struct nfs3_readlinkargs *args = data; + encode_nfs_fh3(xdr, args->fh); prepare_reply_buffer(req, args->pages, args->pgbase, args->pglen, NFS3_readlinkres_sz); @@ -966,8 +975,10 @@ static void encode_read3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_read3args(xdr, args); prepare_reply_buffer(req, args->pages, args->pgbase, args->count, NFS3_readres_sz); @@ -1008,8 +1019,10 @@ static void encode_write3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_write3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; + encode_write3args(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; } @@ -1055,8 +1068,10 @@ static void encode_createhow3(struct xdr_stream *xdr, static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_createargs *args) + const void *data) { + const struct nfs3_createargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_createhow3(xdr, args); } @@ -1071,8 +1086,10 @@ static void nfs3_xdr_enc_create3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_mkdirargs *args) + const void *data) { + const struct nfs3_mkdirargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_sattr3(xdr, args->sattr); } @@ -1091,16 +1108,20 @@ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req, * }; */ static void encode_symlinkdata3(struct xdr_stream *xdr, - const struct nfs3_symlinkargs *args) + const void *data) { + const struct nfs3_symlinkargs *args = data; + encode_sattr3(xdr, args->sattr); encode_nfspath3(xdr, args->pages, args->pathlen); } static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_symlinkargs *args) + const void *data) { + const struct nfs3_symlinkargs *args = data; + encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen); encode_symlinkdata3(xdr, args); xdr->buf->flags |= XDRBUF_WRITE; @@ -1160,8 +1181,10 @@ static void encode_mknoddata3(struct xdr_stream *xdr, static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_mknodargs *args) + const void *data) { + const struct nfs3_mknodargs *args = data; + encode_diropargs3(xdr, args->fh, args->name, args->len); encode_mknoddata3(xdr, args); } @@ -1175,8 +1198,10 @@ static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; + encode_diropargs3(xdr, args->fh, args->name.name, args->name.len); } @@ -1190,8 +1215,9 @@ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; const struct qstr *old = args->old_name; const struct qstr *new = args->new_name; @@ -1209,8 +1235,10 @@ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req, */ static void nfs3_xdr_enc_link3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_linkargs *args) + const void *data) { + const struct nfs3_linkargs *args = data; + encode_nfs_fh3(xdr, args->fromfh); encode_diropargs3(xdr, args->tofh, args->toname, args->tolen); } @@ -1240,8 +1268,10 @@ static void encode_readdir3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readdirargs *args) + const void *data) { + const struct nfs3_readdirargs *args = data; + encode_readdir3args(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS3_readdirres_sz); @@ -1280,8 +1310,10 @@ static void encode_readdirplus3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_readdirargs *args) + const void *data) { + const struct nfs3_readdirargs *args = data; + encode_readdirplus3args(xdr, args); prepare_reply_buffer(req, args->pages, 0, args->count, NFS3_readdirres_sz); @@ -1310,8 +1342,10 @@ static void encode_commit3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_commitargs *args) + const void *data) { + const struct nfs_commitargs *args = data; + encode_commit3args(xdr, args); } @@ -1319,8 +1353,10 @@ static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_getaclargs *args) + const void *data) { + const struct nfs3_getaclargs *args = data; + encode_nfs_fh3(xdr, args->fh); encode_uint32(xdr, args->mask); if (args->mask & (NFS_ACL | NFS_DFACL)) @@ -1331,8 +1367,9 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs3_setaclargs *args) + const void *data) { + const struct nfs3_setaclargs *args = data; unsigned int base; int error; @@ -1382,7 +1419,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req, */ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1419,7 +1456,7 @@ out_default: */ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1460,8 +1497,9 @@ out_status: */ static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_diropres *result) + void *data) { + struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1507,8 +1545,9 @@ out_default: */ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_accessres *result) + void *data) { + struct nfs3_accessres *result = data; enum nfs_stat status; int error; @@ -1548,7 +1587,7 @@ out_default: */ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -1626,8 +1665,9 @@ out_overflow: } static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -1699,8 +1739,9 @@ out_eio: } static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_res *result) + void *data) { + struct nfs_pgio_res *result = data; enum nfs_stat status; int error; @@ -1764,8 +1805,9 @@ out: static int nfs3_xdr_dec_create3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_diropres *result) + void *data) { + struct nfs3_diropres *result = data; enum nfs_stat status; int error; @@ -1804,8 +1846,9 @@ out_default: */ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_removeres *result) + void *data) { + struct nfs_removeres *result = data; enum nfs_stat status; int error; @@ -1845,8 +1888,9 @@ out_status: */ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_renameres *result) + void *data) { + struct nfs_renameres *result = data; enum nfs_stat status; int error; @@ -1888,8 +1932,9 @@ out_status: * }; */ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_linkres *result) + void *data) { + struct nfs3_linkres *result = data; enum nfs_stat status; int error; @@ -1946,7 +1991,7 @@ out_status: * }; */ int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, - int plus) + bool plus) { struct nfs_entry old = *entry; __be32 *p; @@ -2072,8 +2117,9 @@ out: static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_readdirres *result) + void *data) { + struct nfs3_readdirres *result = data; enum nfs_stat status; int error; @@ -2140,8 +2186,9 @@ out_overflow: static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fsstat *result) + void *data) { + struct nfs_fsstat *result = data; enum nfs_stat status; int error; @@ -2216,8 +2263,9 @@ out_overflow: static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fsinfo *result) + void *data) { + struct nfs_fsinfo *result = data; enum nfs_stat status; int error; @@ -2279,8 +2327,9 @@ out_overflow: static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pathconf *result) + void *data) { + struct nfs_pathconf *result = data; enum nfs_stat status; int error; @@ -2320,8 +2369,9 @@ out_status: */ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_commitres *result) + void *data) { + struct nfs_commitres *result = data; enum nfs_stat status; int error; @@ -2389,7 +2439,7 @@ out: static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs3_getaclres *result) + void *result) { enum nfs_stat status; int error; @@ -2408,7 +2458,7 @@ out_default: static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_fattr *result) + void *result) { enum nfs_stat status; int error; @@ -2495,8 +2545,8 @@ static int nfs3_stat_to_errno(enum nfs_stat status) #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ - .p_encode = (kxdreproc_t)nfs3_xdr_enc_##argtype##3args, \ - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res, \ + .p_encode = nfs3_xdr_enc_##argtype##3args, \ + .p_decode = nfs3_xdr_dec_##restype##3res, \ .p_arglen = NFS3_##argtype##args_sz, \ .p_replen = NFS3_##restype##res_sz, \ .p_timer = timer, \ @@ -2504,7 +2554,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status) .p_name = #proc, \ } -struct rpc_procinfo nfs3_procedures[] = { +const struct rpc_procinfo nfs3_procedures[] = { PROC(GETATTR, getattr, getattr, 1), PROC(SETATTR, setattr, setattr, 0), PROC(LOOKUP, lookup, lookup, 2), @@ -2528,18 +2578,20 @@ struct rpc_procinfo nfs3_procedures[] = { PROC(COMMIT, commit, commit, 5), }; +static unsigned int nfs_version3_counts[ARRAY_SIZE(nfs3_procedures)]; const struct rpc_version nfs_version3 = { .number = 3, .nrprocs = ARRAY_SIZE(nfs3_procedures), - .procs = nfs3_procedures + .procs = nfs3_procedures, + .counts = nfs_version3_counts, }; #ifdef CONFIG_NFS_V3_ACL -static struct rpc_procinfo nfs3_acl_procedures[] = { +static const struct rpc_procinfo nfs3_acl_procedures[] = { [ACLPROC3_GETACL] = { .p_proc = ACLPROC3_GETACL, - .p_encode = (kxdreproc_t)nfs3_xdr_enc_getacl3args, - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res, + .p_encode = nfs3_xdr_enc_getacl3args, + .p_decode = nfs3_xdr_dec_getacl3res, .p_arglen = ACL3_getaclargs_sz, .p_replen = ACL3_getaclres_sz, .p_timer = 1, @@ -2547,8 +2599,8 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { }, [ACLPROC3_SETACL] = { .p_proc = ACLPROC3_SETACL, - .p_encode = (kxdreproc_t)nfs3_xdr_enc_setacl3args, - .p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res, + .p_encode = nfs3_xdr_enc_setacl3args, + .p_decode = nfs3_xdr_dec_setacl3res, .p_arglen = ACL3_setaclargs_sz, .p_replen = ACL3_setaclres_sz, .p_timer = 0, @@ -2556,10 +2608,11 @@ static struct rpc_procinfo nfs3_acl_procedures[] = { }, }; +static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)]; const struct rpc_version nfsacl_version3 = { .number = 3, - .nrprocs = sizeof(nfs3_acl_procedures)/ - sizeof(nfs3_acl_procedures[0]), + .nrprocs = ARRAY_SIZE(nfs3_acl_procedures), .procs = nfs3_acl_procedures, + .counts = nfs3_acl_counts, }; #endif /* CONFIG_NFS_V3_ACL */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 319a47db218d..6c2db51e67a7 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -146,7 +146,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; size_t count = args->count; - int status; + ssize_t status; status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context, src_lock, FMODE_READ); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 528362f69cc1..5ee1b0f0d904 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -112,7 +112,7 @@ decode_getattr_maxsz) static void encode_fallocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const struct nfs42_falloc_args *args) { encode_nfs4_stateid(xdr, &args->falloc_stateid); encode_uint64(xdr, args->falloc_offset); @@ -120,7 +120,7 @@ static void encode_fallocate(struct xdr_stream *xdr, } static void encode_allocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args, + const struct nfs42_falloc_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr); @@ -128,7 +128,7 @@ static void encode_allocate(struct xdr_stream *xdr, } static void encode_copy(struct xdr_stream *xdr, - struct nfs42_copy_args *args, + const struct nfs42_copy_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr); @@ -145,7 +145,7 @@ static void encode_copy(struct xdr_stream *xdr, } static void encode_deallocate(struct xdr_stream *xdr, - struct nfs42_falloc_args *args, + const struct nfs42_falloc_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr); @@ -153,7 +153,7 @@ static void encode_deallocate(struct xdr_stream *xdr, } static void encode_seek(struct xdr_stream *xdr, - struct nfs42_seek_args *args, + const struct nfs42_seek_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr); @@ -163,7 +163,7 @@ static void encode_seek(struct xdr_stream *xdr, } static void encode_layoutstats(struct xdr_stream *xdr, - struct nfs42_layoutstat_args *args, + const struct nfs42_layoutstat_args *args, struct nfs42_layoutstat_devinfo *devinfo, struct compound_hdr *hdr) { @@ -191,7 +191,7 @@ static void encode_layoutstats(struct xdr_stream *xdr, } static void encode_clone(struct xdr_stream *xdr, - struct nfs42_clone_args *args, + const struct nfs42_clone_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -210,8 +210,9 @@ static void encode_clone(struct xdr_stream *xdr, */ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const void *data) { + const struct nfs42_falloc_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -225,7 +226,7 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req, } static void encode_copy_commit(struct xdr_stream *xdr, - struct nfs42_copy_args *args, + const struct nfs42_copy_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -241,8 +242,9 @@ static void encode_copy_commit(struct xdr_stream *xdr, */ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_copy_args *args) + const void *data) { + const struct nfs42_copy_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -262,8 +264,9 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req, */ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_falloc_args *args) + const void *data) { + const struct nfs42_falloc_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -281,8 +284,9 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req, */ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_seek_args *args) + const void *data) { + const struct nfs42_seek_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -299,8 +303,9 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_layoutstat_args *args) + const void *data) { + const struct nfs42_layoutstat_args *args = data; int i; struct compound_hdr hdr = { @@ -321,8 +326,9 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req, */ static void nfs4_xdr_enc_clone(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs42_clone_args *args) + const void *data) { + const struct nfs42_clone_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -448,8 +454,9 @@ static int decode_clone(struct xdr_stream *xdr) */ static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_falloc_res *res) + void *data) { + struct nfs42_falloc_res *res = data; struct compound_hdr hdr; int status; @@ -475,8 +482,9 @@ out: */ static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_copy_res *res) + void *data) { + struct nfs42_copy_res *res = data; struct compound_hdr hdr; int status; @@ -508,8 +516,9 @@ out: */ static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_falloc_res *res) + void *data) { + struct nfs42_falloc_res *res = data; struct compound_hdr hdr; int status; @@ -535,8 +544,9 @@ out: */ static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_seek_res *res) + void *data) { + struct nfs42_seek_res *res = data; struct compound_hdr hdr; int status; @@ -559,8 +569,9 @@ out: */ static int nfs4_xdr_dec_layoutstats(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_layoutstat_res *res) + void *data) { + struct nfs42_layoutstat_res *res = data; struct compound_hdr hdr; int status, i; @@ -589,8 +600,9 @@ out: */ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs42_clone_res *res) + void *data) { + struct nfs42_clone_res *res = data; struct compound_hdr hdr; int status; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index af285cc27ccf..ac4f10b7f6c1 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -303,6 +303,17 @@ _nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, struct rpc_cred *newcred = NULL; rpc_authflavor_t flavor; + if (sp4_mode == NFS_SP4_MACH_CRED_CLEANUP || + sp4_mode == NFS_SP4_MACH_CRED_PNFS_CLEANUP) { + /* Using machine creds for cleanup operations + * is only relevent if the client credentials + * might expire. So don't bother for + * RPC_AUTH_UNIX. If file was only exported to + * sec=sys, the PUTFH would fail anyway. + */ + if ((*clntp)->cl_auth->au_flavor == RPC_AUTH_UNIX) + return false; + } if (test_bit(sp4_mode, &clp->cl_sp4_flags)) { spin_lock(&clp->cl_lock); if (clp->cl_machine_cred != NULL) @@ -493,13 +504,13 @@ static inline void nfs4_unregister_sysctl(void) #endif /* nfs4xdr.c */ -extern struct rpc_procinfo nfs4_procedures[]; +extern const struct rpc_procinfo nfs4_procedures[]; struct nfs4_mount_data; /* callback_xdr.c */ -extern struct svc_version nfs4_callback_version1; -extern struct svc_version nfs4_callback_version4; +extern const struct svc_version nfs4_callback_version1; +extern const struct svc_version nfs4_callback_version4; static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src) { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 66776f022111..e9bea90dc017 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -414,6 +414,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (clp != old) clp->cl_preserve_clid = true; nfs_put_client(clp); + clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); return old; error: @@ -659,9 +660,6 @@ int nfs4_detect_session_trunking(struct nfs_client *clp, if (!nfs4_check_server_scope(clp->cl_serverscope, res->server_scope)) goto out_err; - /* Session trunking passed, add the xprt */ - rpc_clnt_xprt_switch_add_xprt(clp->cl_rpcclient, xprt); - pr_info("NFS: %s: Session trunking succeeded for %s\n", clp->cl_hostname, xprt->address_strings[RPC_DISPLAY_ADDR]); @@ -852,6 +850,8 @@ static int nfs4_set_client(struct nfs_server *server, set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); if (server->options & NFS_OPTION_MIGRATION) set_bit(NFS_CS_MIGRATION, &cl_init.init_flags); + if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status)) + set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags); /* Allocate or find a client reference we can use */ clp = nfs_get_client(&cl_init); @@ -1212,9 +1212,11 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname, return -EAFNOSUPPORT; nfs_server_remove_lists(server); + set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); error = nfs4_set_client(server, hostname, sap, salen, buf, clp->cl_proto, clnt->cl_timeout, clp->cl_minorversion, net); + clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status); nfs_put_client(clp); if (error != 0) { nfs_server_insert_lists(server); diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 835c163f61af..30426c1a1bbd 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -274,7 +274,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen, ssize_t ret; ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); - if (ret <= 0) + if (ret < 0) return ERR_PTR(ret); rkey = request_key(&key_type_id_resolver, desc, ""); @@ -364,7 +364,8 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ ret = -EINVAL; } else { ret = kstrtol(id_str, 10, &id_long); - *id = (__u32)id_long; + if (!ret) + *id = (__u32)id_long; } return ret; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index dbfa18900e25..f90090e8c959 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -275,6 +275,7 @@ const u32 nfs4_fs_locations_bitmap[3] = { static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry, struct nfs4_readdir_arg *readdir) { + unsigned int attrs = FATTR4_WORD0_FILEID | FATTR4_WORD0_TYPE; __be32 *start, *p; if (cookie > 2) { @@ -305,8 +306,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent memcpy(p, ".\0\0\0", 4); /* entry */ p++; *p++ = xdr_one; /* bitmap length */ - *p++ = htonl(FATTR4_WORD0_FILEID); /* bitmap */ - *p++ = htonl(8); /* attribute buffer length */ + *p++ = htonl(attrs); /* bitmap */ + *p++ = htonl(12); /* attribute buffer length */ + *p++ = htonl(NF4DIR); p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry))); } @@ -317,8 +319,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent memcpy(p, "..\0\0", 4); /* entry */ p++; *p++ = xdr_one; /* bitmap length */ - *p++ = htonl(FATTR4_WORD0_FILEID); /* bitmap */ - *p++ = htonl(8); /* attribute buffer length */ + *p++ = htonl(attrs); /* bitmap */ + *p++ = htonl(12); /* attribute buffer length */ + *p++ = htonl(NF4DIR); p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry->d_parent))); readdir->pgbase = (char *)p - (char *)start; @@ -1034,11 +1037,11 @@ struct nfs4_opendata { struct nfs4_state *state; struct iattr attrs; unsigned long timestamp; - unsigned int rpc_done : 1; - unsigned int file_created : 1; - unsigned int is_recover : 1; + bool rpc_done; + bool file_created; + bool is_recover; + bool cancelled; int rpc_status; - int cancelled; }; static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server, @@ -1656,12 +1659,52 @@ update: return state; } +static struct inode * +nfs4_opendata_get_inode(struct nfs4_opendata *data) +{ + struct inode *inode; + + switch (data->o_arg.claim) { + case NFS4_OPEN_CLAIM_NULL: + case NFS4_OPEN_CLAIM_DELEGATE_CUR: + case NFS4_OPEN_CLAIM_DELEGATE_PREV: + if (!(data->f_attr.valid & NFS_ATTR_FATTR)) + return ERR_PTR(-EAGAIN); + inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, + &data->f_attr, data->f_label); + break; + default: + inode = d_inode(data->dentry); + ihold(inode); + nfs_refresh_inode(inode, &data->f_attr); + } + return inode; +} + static struct nfs4_state * -_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) +nfs4_opendata_find_nfs4_state(struct nfs4_opendata *data) { + struct nfs4_state *state; struct inode *inode; - struct nfs4_state *state = NULL; - int ret; + + inode = nfs4_opendata_get_inode(data); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (data->state != NULL && data->state->inode == inode) { + state = data->state; + atomic_inc(&state->count); + } else + state = nfs4_get_open_state(inode, data->owner); + iput(inode); + if (state == NULL) + state = ERR_PTR(-ENOMEM); + return state; +} + +static struct nfs4_state * +_nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) +{ + struct nfs4_state *state; if (!data->rpc_done) { state = nfs4_try_open_cached(data); @@ -1669,29 +1712,17 @@ _nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data) goto out; } - ret = -EAGAIN; - if (!(data->f_attr.valid & NFS_ATTR_FATTR)) - goto err; - inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, &data->f_attr, data->f_label); - ret = PTR_ERR(inode); - if (IS_ERR(inode)) - goto err; - ret = -ENOMEM; - state = nfs4_get_open_state(inode, data->owner); - if (state == NULL) - goto err_put_inode; + state = nfs4_opendata_find_nfs4_state(data); + if (IS_ERR(state)) + goto out; + if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); update_open_stateid(state, &data->o_res.stateid, NULL, data->o_arg.fmode); - iput(inode); out: nfs_release_seqid(data->o_arg.seqid); return state; -err_put_inode: - iput(inode); -err: - return ERR_PTR(ret); } static struct nfs4_state * @@ -1962,7 +1993,7 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata) nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid); nfs_confirm_seqid(&data->owner->so_seqid, 0); renew_lease(data->o_res.server, data->timestamp); - data->rpc_done = 1; + data->rpc_done = true; } } @@ -1972,7 +2003,7 @@ static void nfs4_open_confirm_release(void *calldata) struct nfs4_state *state = NULL; /* If this request hasn't been cancelled, do nothing */ - if (data->cancelled == 0) + if (!data->cancelled) goto out_free; /* In case of error, no cleanup! */ if (!data->rpc_done) @@ -2015,7 +2046,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1); kref_get(&data->kref); - data->rpc_done = 0; + data->rpc_done = false; data->rpc_status = 0; data->timestamp = jiffies; if (data->is_recover) @@ -2025,7 +2056,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data) return PTR_ERR(task); status = rpc_wait_for_completion_task(task); if (status != 0) { - data->cancelled = 1; + data->cancelled = true; smp_wmb(); } else status = data->rpc_status; @@ -2068,7 +2099,6 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0]; case NFS4_OPEN_CLAIM_FH: task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; - nfs_copy_fh(&data->o_res.fh, data->o_arg.fh); } data->timestamp = jiffies; if (nfs4_setup_sequence(data->o_arg.server->nfs_client, @@ -2124,7 +2154,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata) if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM)) nfs_confirm_seqid(&data->owner->so_seqid, 0); } - data->rpc_done = 1; + data->rpc_done = true; } static void nfs4_open_release(void *calldata) @@ -2133,7 +2163,7 @@ static void nfs4_open_release(void *calldata) struct nfs4_state *state = NULL; /* If this request hasn't been cancelled, do nothing */ - if (data->cancelled == 0) + if (!data->cancelled) goto out_free; /* In case of error, no cleanup! */ if (data->rpc_status != 0 || !data->rpc_done) @@ -2179,20 +2209,20 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover) nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1); kref_get(&data->kref); - data->rpc_done = 0; + data->rpc_done = false; data->rpc_status = 0; - data->cancelled = 0; - data->is_recover = 0; + data->cancelled = false; + data->is_recover = false; if (isrecover) { nfs4_set_sequence_privileged(&o_arg->seq_args); - data->is_recover = 1; + data->is_recover = true; } task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) return PTR_ERR(task); status = rpc_wait_for_completion_task(task); if (status != 0) { - data->cancelled = 1; + data->cancelled = true; smp_wmb(); } else status = data->rpc_status; @@ -2233,7 +2263,7 @@ static int nfs4_opendata_access(struct rpc_cred *cred, int openflags) { struct nfs_access_entry cache; - u32 mask; + u32 mask, flags; /* access call failed or for some reason the server doesn't * support any access modes -- defer access call until later */ @@ -2247,16 +2277,19 @@ static int nfs4_opendata_access(struct rpc_cred *cred, */ if (openflags & __FMODE_EXEC) { /* ONLY check for exec rights */ - mask = MAY_EXEC; + if (S_ISDIR(state->inode->i_mode)) + mask = NFS4_ACCESS_LOOKUP; + else + mask = NFS4_ACCESS_EXECUTE; } else if ((fmode & FMODE_READ) && !opendata->file_created) - mask = MAY_READ; + mask = NFS4_ACCESS_READ; cache.cred = cred; - cache.jiffies = jiffies; nfs_access_set_mask(&cache, opendata->o_res.access_result); nfs_access_add_cache(state->inode, &cache); - if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0) + flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP; + if ((mask & ~cache.mask & flags) == 0) return 0; return -EACCES; @@ -2287,9 +2320,9 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) if (o_arg->open_flags & O_CREAT) { if (o_arg->open_flags & O_EXCL) - data->file_created = 1; + data->file_created = true; else if (o_res->cinfo.before != o_res->cinfo.after) - data->file_created = 1; + data->file_created = true; if (data->file_created || dir->i_version != o_res->cinfo.after) update_changeattr(dir, &o_res->cinfo, o_res->f_attr->time_start); @@ -2546,9 +2579,8 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) clear_bit(NFS_O_RDWR_STATE, &state->flags); clear_bit(NFS_OPEN_STATE, &state->flags); stateid->type = NFS4_INVALID_STATEID_TYPE; - } - if (status != NFS_OK) return status; + } if (nfs_open_stateid_recover_openmode(state)) return -NFS4ERR_OPENMODE; return NFS_OK; @@ -3803,6 +3835,54 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, const struct qstr *name, return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; } +static int _nfs4_proc_lookupp(struct inode *inode, + struct nfs_fh *fhandle, struct nfs_fattr *fattr, + struct nfs4_label *label) +{ + struct rpc_clnt *clnt = NFS_CLIENT(inode); + struct nfs_server *server = NFS_SERVER(inode); + int status; + struct nfs4_lookupp_arg args = { + .bitmask = server->attr_bitmask, + .fh = NFS_FH(inode), + }; + struct nfs4_lookupp_res res = { + .server = server, + .fattr = fattr, + .label = label, + .fh = fhandle, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUPP], + .rpc_argp = &args, + .rpc_resp = &res, + }; + + args.bitmask = nfs4_bitmask(server, label); + + nfs_fattr_init(fattr); + + dprintk("NFS call lookupp ino=0x%lx\n", inode->i_ino); + status = nfs4_call_sync(clnt, server, &msg, &args.seq_args, + &res.seq_res, 0); + dprintk("NFS reply lookupp: %d\n", status); + return status; +} + +static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct nfs4_label *label) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = _nfs4_proc_lookupp(inode, fhandle, fattr, label); + trace_nfs4_lookupp(inode, err); + err = nfs4_handle_exception(NFS_SERVER(inode), err, + &exception); + } while (exception.retry); + return err; +} + static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) { struct nfs_server *server = NFS_SERVER(inode); @@ -4273,7 +4353,7 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, } static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); struct nfs4_readdir_arg args = { @@ -4311,7 +4391,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, } static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct nfs4_exception exception = { }; int err; @@ -6135,7 +6215,7 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: begin!\n", __func__); nfs_free_seqid(data->arg.open_seqid); - if (data->cancelled != 0) { + if (data->cancelled) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, data->arg.lock_seqid); @@ -6218,7 +6298,7 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f nfs4_handle_setlk_error(data->server, data->lsp, data->arg.new_lock_owner, ret); } else - data->cancelled = 1; + data->cancelled = true; rpc_put_task(task); dprintk("%s: done, ret = %d!\n", __func__, ret); trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret); @@ -6373,7 +6453,7 @@ struct nfs4_lock_waiter { }; static int -nfs4_wake_lock_waiter(wait_queue_t *wait, unsigned int mode, int flags, void *key) +nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, void *key) { int ret; struct cb_notify_lock_args *cbnl = key; @@ -6416,7 +6496,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) .inode = state->inode, .owner = &owner, .notified = false }; - wait_queue_t wait; + wait_queue_entry_t wait; /* Don't bother with waitqueue if we don't expect a callback */ if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags)) @@ -6441,7 +6521,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irqrestore(&q->lock, flags); - freezable_schedule_timeout_interruptible(NFS4_LOCK_MAXTIMEOUT); + freezable_schedule_timeout(NFS4_LOCK_MAXTIMEOUT); } finish_wait(q, &wait); @@ -7264,7 +7344,9 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, 1 << (OP_DESTROY_SESSION - 32) | 1 << (OP_DESTROY_CLIENTID - 32) }; + unsigned long flags = 0; unsigned int i; + int ret = 0; if (sp->how == SP4_MACH_CRED) { /* Print state protect result */ @@ -7280,7 +7362,8 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, for (i = 0; i < NFS4_OP_MAP_NUM_WORDS; i++) { if (sp->enforce.u.words[i] & ~supported_enforce[i]) { dfprintk(MOUNT, "sp4_mach_cred: disabled\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } } @@ -7299,10 +7382,11 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, test_bit(OP_DESTROY_CLIENTID, sp->enforce.u.longs)) { dfprintk(MOUNT, "sp4_mach_cred:\n"); dfprintk(MOUNT, " minimal mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_MINIMAL, &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_MINIMAL, &flags); } else { dfprintk(MOUNT, "sp4_mach_cred: disabled\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } if (test_bit(OP_CLOSE, sp->allow.u.longs) && @@ -7310,120 +7394,51 @@ static int nfs4_sp4_select_mode(struct nfs_client *clp, test_bit(OP_DELEGRETURN, sp->allow.u.longs) && test_bit(OP_LOCKU, sp->allow.u.longs)) { dfprintk(MOUNT, " cleanup mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_CLEANUP, &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_CLEANUP, &flags); } if (test_bit(OP_LAYOUTRETURN, sp->allow.u.longs)) { dfprintk(MOUNT, " pnfs cleanup mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP, - &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_PNFS_CLEANUP, &flags); } if (test_bit(OP_SECINFO, sp->allow.u.longs) && test_bit(OP_SECINFO_NO_NAME, sp->allow.u.longs)) { dfprintk(MOUNT, " secinfo mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_SECINFO, &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_SECINFO, &flags); } if (test_bit(OP_TEST_STATEID, sp->allow.u.longs) && test_bit(OP_FREE_STATEID, sp->allow.u.longs)) { dfprintk(MOUNT, " stateid mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_STATEID, &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_STATEID, &flags); } if (test_bit(OP_WRITE, sp->allow.u.longs)) { dfprintk(MOUNT, " write mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_WRITE, &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_WRITE, &flags); } if (test_bit(OP_COMMIT, sp->allow.u.longs)) { dfprintk(MOUNT, " commit mode enabled\n"); - set_bit(NFS_SP4_MACH_CRED_COMMIT, &clp->cl_sp4_flags); + __set_bit(NFS_SP4_MACH_CRED_COMMIT, &flags); } } - +out: + clp->cl_sp4_flags = flags; return 0; } struct nfs41_exchange_id_data { struct nfs41_exchange_id_res res; struct nfs41_exchange_id_args args; - struct rpc_xprt *xprt; - int rpc_status; }; -static void nfs4_exchange_id_done(struct rpc_task *task, void *data) -{ - struct nfs41_exchange_id_data *cdata = - (struct nfs41_exchange_id_data *)data; - struct nfs_client *clp = cdata->args.client; - int status = task->tk_status; - - trace_nfs4_exchange_id(clp, status); - - if (status == 0) - status = nfs4_check_cl_exchange_flags(cdata->res.flags); - - if (cdata->xprt && status == 0) { - status = nfs4_detect_session_trunking(clp, &cdata->res, - cdata->xprt); - goto out; - } - - if (status == 0) - status = nfs4_sp4_select_mode(clp, &cdata->res.state_protect); - - if (status == 0) { - clp->cl_clientid = cdata->res.clientid; - clp->cl_exchange_flags = cdata->res.flags; - /* Client ID is not confirmed */ - if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R)) { - clear_bit(NFS4_SESSION_ESTABLISHED, - &clp->cl_session->session_state); - clp->cl_seqid = cdata->res.seqid; - } - - kfree(clp->cl_serverowner); - clp->cl_serverowner = cdata->res.server_owner; - cdata->res.server_owner = NULL; - - /* use the most recent implementation id */ - kfree(clp->cl_implid); - clp->cl_implid = cdata->res.impl_id; - cdata->res.impl_id = NULL; - - if (clp->cl_serverscope != NULL && - !nfs41_same_server_scope(clp->cl_serverscope, - cdata->res.server_scope)) { - dprintk("%s: server_scope mismatch detected\n", - __func__); - set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state); - kfree(clp->cl_serverscope); - clp->cl_serverscope = NULL; - } - - if (clp->cl_serverscope == NULL) { - clp->cl_serverscope = cdata->res.server_scope; - cdata->res.server_scope = NULL; - } - /* Save the EXCHANGE_ID verifier session trunk tests */ - memcpy(clp->cl_confirm.data, cdata->args.verifier->data, - sizeof(clp->cl_confirm.data)); - } -out: - cdata->rpc_status = status; - return; -} - static void nfs4_exchange_id_release(void *data) { struct nfs41_exchange_id_data *cdata = (struct nfs41_exchange_id_data *)data; - if (cdata->xprt) { - xprt_put(cdata->xprt); - rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient); - } nfs_put_client(cdata->args.client); kfree(cdata->res.impl_id); kfree(cdata->res.server_scope); @@ -7432,7 +7447,6 @@ static void nfs4_exchange_id_release(void *data) } static const struct rpc_call_ops nfs4_exchange_id_call_ops = { - .rpc_call_done = nfs4_exchange_id_done, .rpc_release = nfs4_exchange_id_release, }; @@ -7441,10 +7455,10 @@ static const struct rpc_call_ops nfs4_exchange_id_call_ops = { * * Wrapper for EXCHANGE_ID operation. */ -static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, +static struct rpc_task * +nfs4_run_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, u32 sp4_how, struct rpc_xprt *xprt) { - nfs4_verifier verifier; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_EXCHANGE_ID], .rpc_cred = cred, @@ -7453,23 +7467,20 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, .rpc_client = clp->cl_rpcclient, .callback_ops = &nfs4_exchange_id_call_ops, .rpc_message = &msg, - .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT, + .flags = RPC_TASK_TIMEOUT, }; struct nfs41_exchange_id_data *calldata; - struct rpc_task *task; int status; if (!atomic_inc_not_zero(&clp->cl_count)) - return -EIO; + return ERR_PTR(-EIO); + status = -ENOMEM; calldata = kzalloc(sizeof(*calldata), GFP_NOFS); - if (!calldata) { - nfs_put_client(clp); - return -ENOMEM; - } + if (!calldata) + goto out; - if (!xprt) - nfs4_init_boot_verifier(clp, &verifier); + nfs4_init_boot_verifier(clp, &calldata->args.verifier); status = nfs4_init_uniform_client_string(clp); if (status) @@ -7506,41 +7517,22 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, goto out_impl_id; } if (xprt) { - calldata->xprt = xprt; task_setup_data.rpc_xprt = xprt; - task_setup_data.flags = - RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC; - calldata->args.verifier = &clp->cl_confirm; - } else { - calldata->args.verifier = &verifier; + task_setup_data.flags |= RPC_TASK_SOFTCONN; + memcpy(calldata->args.verifier.data, clp->cl_confirm.data, + sizeof(calldata->args.verifier.data)); } calldata->args.client = clp; -#ifdef CONFIG_NFS_V4_1_MIGRATION - calldata->args.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | - EXCHGID4_FLAG_BIND_PRINC_STATEID | - EXCHGID4_FLAG_SUPP_MOVED_MIGR, -#else calldata->args.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER | - EXCHGID4_FLAG_BIND_PRINC_STATEID, + EXCHGID4_FLAG_BIND_PRINC_STATEID; +#ifdef CONFIG_NFS_V4_1_MIGRATION + calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR; #endif msg.rpc_argp = &calldata->args; msg.rpc_resp = &calldata->res; task_setup_data.callback_data = calldata; - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - return PTR_ERR(task); - - if (!xprt) { - status = rpc_wait_for_completion_task(task); - if (!status) - status = calldata->rpc_status; - } else /* session trunking test */ - status = calldata->rpc_status; - - rpc_put_task(task); -out: - return status; + return rpc_run_task(&task_setup_data); out_impl_id: kfree(calldata->res.impl_id); @@ -7550,8 +7542,69 @@ out_server_owner: kfree(calldata->res.server_owner); out_calldata: kfree(calldata); +out: nfs_put_client(clp); - goto out; + return ERR_PTR(status); +} + +/* + * _nfs4_proc_exchange_id() + * + * Wrapper for EXCHANGE_ID operation. + */ +static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, + u32 sp4_how) +{ + struct rpc_task *task; + struct nfs41_exchange_id_args *argp; + struct nfs41_exchange_id_res *resp; + int status; + + task = nfs4_run_exchange_id(clp, cred, sp4_how, NULL); + if (IS_ERR(task)) + return PTR_ERR(task); + + argp = task->tk_msg.rpc_argp; + resp = task->tk_msg.rpc_resp; + status = task->tk_status; + if (status != 0) + goto out; + + status = nfs4_check_cl_exchange_flags(resp->flags); + if (status != 0) + goto out; + + status = nfs4_sp4_select_mode(clp, &resp->state_protect); + if (status != 0) + goto out; + + clp->cl_clientid = resp->clientid; + clp->cl_exchange_flags = resp->flags; + clp->cl_seqid = resp->seqid; + /* Client ID is not confirmed */ + if (!(resp->flags & EXCHGID4_FLAG_CONFIRMED_R)) + clear_bit(NFS4_SESSION_ESTABLISHED, + &clp->cl_session->session_state); + + if (clp->cl_serverscope != NULL && + !nfs41_same_server_scope(clp->cl_serverscope, + resp->server_scope)) { + dprintk("%s: server_scope mismatch detected\n", + __func__); + set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state); + } + + swap(clp->cl_serverowner, resp->server_owner); + swap(clp->cl_serverscope, resp->server_scope); + swap(clp->cl_implid, resp->impl_id); + + /* Save the EXCHANGE_ID verifier session trunk tests */ + memcpy(clp->cl_confirm.data, argp->verifier.data, + sizeof(clp->cl_confirm.data)); +out: + trace_nfs4_exchange_id(clp, status); + rpc_put_task(task); + return status; } /* @@ -7574,13 +7627,13 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) /* try SP4_MACH_CRED if krb5i/p */ if (authflavor == RPC_AUTH_GSS_KRB5I || authflavor == RPC_AUTH_GSS_KRB5P) { - status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED, NULL); + status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED); if (!status) return 0; } /* try SP4_NONE */ - return _nfs4_proc_exchange_id(clp, cred, SP4_NONE, NULL); + return _nfs4_proc_exchange_id(clp, cred, SP4_NONE); } /** @@ -7602,6 +7655,9 @@ int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data) { struct nfs4_add_xprt_data *adata = (struct nfs4_add_xprt_data *)data; + struct rpc_task *task; + int status; + u32 sp4_how; dprintk("--> %s try %s\n", __func__, @@ -7610,7 +7666,17 @@ int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, sp4_how = (adata->clp->cl_sp4_flags == 0 ? SP4_NONE : SP4_MACH_CRED); /* Test connection for session trunking. Async exchange_id call */ - return _nfs4_proc_exchange_id(adata->clp, adata->cred, sp4_how, xprt); + task = nfs4_run_exchange_id(adata->clp, adata->cred, sp4_how, xprt); + if (IS_ERR(task)) + return PTR_ERR(task); + + status = task->tk_status; + if (status == 0) + status = nfs4_detect_session_trunking(adata->clp, + task->tk_msg.rpc_resp, xprt); + + rpc_put_task(task); + return status; } EXPORT_SYMBOL_GPL(nfs4_test_session_trunk); @@ -8333,8 +8399,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task, lo = NFS_I(inode)->layout; /* If the open stateid was bad, then recover it. */ if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) || - nfs4_stateid_match_other(&lgp->args.stateid, - &lgp->args.ctx->state->stateid)) { + !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) { spin_unlock(&inode->i_lock); exception->state = lgp->args.ctx->state; exception->stateid = &lgp->args.stateid; @@ -9313,6 +9378,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, + .lookupp = nfs4_proc_lookupp, .access = nfs4_proc_access, .readlink = nfs4_proc_readlink, .create = nfs4_proc_create, diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index cbf82b0d4467..0378e2257ca7 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -352,11 +352,17 @@ int nfs41_discover_server_trunking(struct nfs_client *clp, if (clp != *result) return 0; - /* Purge state if the client id was established in a prior instance */ - if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) - set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); - else - set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + /* + * Purge state if the client id was established in a prior + * instance and the client id could not have arrived on the + * server via Transparent State Migration. + */ + if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) { + if (!test_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags)) + set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + else + set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + } nfs4_schedule_state_manager(clp); status = nfs_wait_client_init_complete(clp); if (status < 0) diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 845d0eadefc9..be1da19c65d6 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -891,6 +891,35 @@ DEFINE_NFS4_LOOKUP_EVENT(nfs4_remove); DEFINE_NFS4_LOOKUP_EVENT(nfs4_get_fs_locations); DEFINE_NFS4_LOOKUP_EVENT(nfs4_secinfo); +TRACE_EVENT(nfs4_lookupp, + TP_PROTO( + const struct inode *inode, + int error + ), + + TP_ARGS(inode, error), + + TP_STRUCT__entry( + __field(dev_t, dev) + __field(u64, ino) + __field(int, error) + ), + + TP_fast_assign( + __entry->dev = inode->i_sb->s_dev; + __entry->ino = NFS_FILEID(inode); + __entry->error = error; + ), + + TP_printk( + "error=%d (%s) inode=%02x:%02x:%llu", + __entry->error, + show_nfsv4_errors(__entry->error), + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->ino + ) +); + TRACE_EVENT(nfs4_rename, TP_PROTO( const struct inode *olddir, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 3aebfdc82b30..14ed9791ec9c 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -159,6 +159,8 @@ static int nfs4_stat_to_errno(int); (op_decode_hdr_maxsz) #define encode_lookup_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) #define decode_lookup_maxsz (op_decode_hdr_maxsz) +#define encode_lookupp_maxsz (op_encode_hdr_maxsz) +#define decode_lookupp_maxsz (op_decode_hdr_maxsz) #define encode_share_access_maxsz \ (2) #define encode_createmode_maxsz (1 + encode_attrs_maxsz + encode_verifier_maxsz) @@ -618,6 +620,18 @@ static int nfs4_stat_to_errno(int); decode_lookup_maxsz + \ decode_getattr_maxsz + \ decode_getfh_maxsz) +#define NFS4_enc_lookupp_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_lookupp_maxsz + \ + encode_getattr_maxsz + \ + encode_getfh_maxsz) +#define NFS4_dec_lookupp_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_lookupp_maxsz + \ + decode_getattr_maxsz + \ + decode_getfh_maxsz) #define NFS4_enc_lookup_root_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putrootfh_maxsz + \ @@ -1368,6 +1382,11 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc encode_string(xdr, name->len, name->name); } +static void encode_lookupp(struct xdr_stream *xdr, struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_LOOKUPP, decode_lookupp_maxsz, hdr); +} + static void encode_share_access(struct xdr_stream *xdr, u32 share_access) { __be32 *p; @@ -1651,7 +1670,8 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr) } static void -encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compound_hdr *hdr) +encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg, + struct compound_hdr *hdr) { __be32 *p; @@ -1735,7 +1755,7 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ static void encode_bind_conn_to_session(struct xdr_stream *xdr, - struct nfs41_bind_conn_to_session_args *args, + const struct nfs41_bind_conn_to_session_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1748,7 +1768,7 @@ static void encode_bind_conn_to_session(struct xdr_stream *xdr, *p = (args->use_conn_in_rdma_mode) ? cpu_to_be32(1) : cpu_to_be32(0); } -static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) +static void encode_op_map(struct xdr_stream *xdr, const struct nfs4_op_map *op_map) { unsigned int i; encode_uint32(xdr, NFS4_OP_MAP_NUM_WORDS); @@ -1757,7 +1777,7 @@ static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map) } static void encode_exchange_id(struct xdr_stream *xdr, - struct nfs41_exchange_id_args *args, + const struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1765,7 +1785,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, int len = 0; encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr); - encode_nfs4_verifier(xdr, args->verifier); + encode_nfs4_verifier(xdr, &args->verifier); encode_string(xdr, strlen(args->client->cl_owner_id), args->client->cl_owner_id); @@ -1809,7 +1829,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, } static void encode_create_session(struct xdr_stream *xdr, - struct nfs41_create_session_args *args, + const struct nfs41_create_session_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -1822,8 +1842,8 @@ static void encode_create_session(struct xdr_stream *xdr, * Assumes OPEN is the biggest non-idempotent compound. * 2 is the verifier. */ - max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + - RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT; + max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2) + * XDR_UNIT + RPC_MAX_AUTH_SIZE; encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr); p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12); @@ -1862,7 +1882,7 @@ static void encode_create_session(struct xdr_stream *xdr, } static void encode_destroy_session(struct xdr_stream *xdr, - struct nfs4_session *session, + const struct nfs4_session *session, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr); @@ -1878,7 +1898,7 @@ static void encode_destroy_clientid(struct xdr_stream *xdr, } static void encode_reclaim_complete(struct xdr_stream *xdr, - struct nfs41_reclaim_complete_args *args, + const struct nfs41_reclaim_complete_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr); @@ -1974,7 +1994,7 @@ encode_layoutget(struct xdr_stream *xdr, static int encode_layoutcommit(struct xdr_stream *xdr, struct inode *inode, - struct nfs4_layoutcommit_args *args, + const struct nfs4_layoutcommit_args *args, struct compound_hdr *hdr) { __be32 *p; @@ -2044,7 +2064,7 @@ encode_secinfo_no_name(struct xdr_stream *xdr, } static void encode_test_stateid(struct xdr_stream *xdr, - struct nfs41_test_stateid_args *args, + const struct nfs41_test_stateid_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr); @@ -2053,7 +2073,7 @@ static void encode_test_stateid(struct xdr_stream *xdr, } static void encode_free_stateid(struct xdr_stream *xdr, - struct nfs41_free_stateid_args *args, + const struct nfs41_free_stateid_args *args, struct compound_hdr *hdr) { encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr); @@ -2086,8 +2106,9 @@ static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args) * Encode an ACCESS request */ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_accessargs *args) + const void *data) { + const struct nfs4_accessargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2104,8 +2125,9 @@ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode LOOKUP request */ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_lookup_arg *args) + const void *data) { + const struct nfs4_lookup_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2120,12 +2142,33 @@ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr, } /* + * Encode LOOKUPP request + */ +static void nfs4_xdr_enc_lookupp(struct rpc_rqst *req, struct xdr_stream *xdr, + const void *data) +{ + const struct nfs4_lookupp_arg *args = data; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_sequence(xdr, &args->seq_args, &hdr); + encode_putfh(xdr, args->fh, &hdr); + encode_lookupp(xdr, &hdr); + encode_getfh(xdr, &hdr); + encode_getfattr(xdr, args->bitmask, &hdr); + encode_nops(&hdr); +} + +/* * Encode LOOKUP_ROOT request */ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_lookup_root_arg *args) + const void *data) { + const struct nfs4_lookup_root_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2142,8 +2185,9 @@ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req, * Encode REMOVE request */ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_removeargs *args) + const void *data) { + const struct nfs_removeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2159,8 +2203,9 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode RENAME request */ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_renameargs *args) + const void *data) { + const struct nfs_renameargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2178,8 +2223,9 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode LINK request */ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_link_arg *args) + const void *data) { + const struct nfs4_link_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2199,8 +2245,9 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode CREATE request */ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_create_arg *args) + const void *data) { + const struct nfs4_create_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2218,8 +2265,10 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode SYMLINK request */ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_create_arg *args) + const void *data) { + const struct nfs4_create_arg *args = data; + nfs4_xdr_enc_create(req, xdr, args); } @@ -2227,8 +2276,9 @@ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode GETATTR request */ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_getattr_arg *args) + const void *data) { + const struct nfs4_getattr_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2244,8 +2294,9 @@ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a CLOSE request */ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_closeargs *args) + const void *data) { + const struct nfs_closeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2265,8 +2316,9 @@ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode an OPEN request */ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_openargs *args) + const void *data) { + const struct nfs_openargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2287,8 +2339,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_open_confirmargs *args) + const void *data) { + const struct nfs_open_confirmargs *args = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2304,8 +2357,9 @@ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req, */ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_openargs *args) + const void *data) { + const struct nfs_openargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2325,8 +2379,9 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, */ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_closeargs *args) + const void *data) { + const struct nfs_closeargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2344,8 +2399,9 @@ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req, * Encode a LOCK request */ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_lock_args *args) + const void *data) { + const struct nfs_lock_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2361,8 +2417,9 @@ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a LOCKT request */ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_lockt_args *args) + const void *data) { + const struct nfs_lockt_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2378,8 +2435,9 @@ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a LOCKU request */ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_locku_args *args) + const void *data) { + const struct nfs_locku_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2393,8 +2451,9 @@ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr, static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_release_lockowner_args *args) + const void *data) { + const struct nfs_release_lockowner_args *args = data; struct compound_hdr hdr = { .minorversion = 0, }; @@ -2408,8 +2467,9 @@ static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req, * Encode a READLINK request */ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_readlink *args) + const void *data) { + const struct nfs4_readlink *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2428,8 +2488,9 @@ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READDIR request */ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_readdir_arg *args) + const void *data) { + const struct nfs4_readdir_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2451,8 +2512,9 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a READ request */ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2472,8 +2534,9 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode an SETATTR request */ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_setattrargs *args) + const void *data) { + const struct nfs_setattrargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2490,8 +2553,9 @@ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a GETACL request */ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_getaclargs *args) + const void *data) { + const struct nfs_getaclargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2513,8 +2577,9 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, * Encode a WRITE request */ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_pgio_args *args) + const void *data) { + const struct nfs_pgio_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2533,8 +2598,9 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, * a COMMIT request */ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_commitargs *args) + const void *data) { + const struct nfs_commitargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2550,8 +2616,9 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, * FSINFO request */ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsinfo_arg *args) + const void *data) { + const struct nfs4_fsinfo_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2567,8 +2634,9 @@ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, * a PATHCONF request */ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_pathconf_arg *args) + const void *data) { + const struct nfs4_pathconf_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2585,8 +2653,9 @@ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, * a STATFS request */ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_statfs_arg *args) + const void *data) { + const struct nfs4_statfs_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2604,8 +2673,9 @@ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_server_caps_arg *args) + const void *data) { + const struct nfs4_server_caps_arg *args = data; const u32 *bitmask = args->bitmask; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), @@ -2622,8 +2692,10 @@ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req, * a RENEW request */ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_client *clp) + const void *data) + { + const struct nfs_client *clp = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2638,8 +2710,9 @@ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid *sc) + const void *data) { + const struct nfs4_setclientid *sc = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2654,8 +2727,9 @@ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req, */ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid_res *arg) + const void *data) { + const struct nfs4_setclientid_res *arg = data; struct compound_hdr hdr = { .nops = 0, }; @@ -2670,8 +2744,9 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req, */ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs4_delegreturnargs *args) + const void *data) { + const struct nfs4_delegreturnargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2692,8 +2767,9 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, */ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fs_locations_arg *args) + const void *data) { + const struct nfs4_fs_locations_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2715,8 +2791,8 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } /* Set up reply kvec to capture returned fs_locations array. */ - xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page, - 0, PAGE_SIZE); + xdr_inline_pages(&req->rq_rcv_buf, replen << 2, + (struct page **)&args->page, 0, PAGE_SIZE); encode_nops(&hdr); } @@ -2725,8 +2801,9 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, */ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_secinfo_arg *args) + const void *data) { + const struct nfs4_secinfo_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2743,8 +2820,9 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, */ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsid_present_arg *args) + const void *data) { + const struct nfs4_fsid_present_arg *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2764,8 +2842,9 @@ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req, */ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_bind_conn_to_session_args *args) + const void *data) { + const struct nfs41_bind_conn_to_session_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2780,8 +2859,9 @@ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_exchange_id_args *args) + const void *data) { + const struct nfs41_exchange_id_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2796,8 +2876,9 @@ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, */ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_create_session_args *args) + const void *data) { + const struct nfs41_create_session_args *args = data; struct compound_hdr hdr = { .minorversion = args->client->cl_mvops->minor_version, }; @@ -2812,8 +2893,9 @@ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_session *session) + const void *data) { + const struct nfs4_session *session = data; struct compound_hdr hdr = { .minorversion = session->clp->cl_mvops->minor_version, }; @@ -2828,8 +2910,9 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, */ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_client *clp) + const void *data) { + const struct nfs_client *clp = data; struct compound_hdr hdr = { .minorversion = clp->cl_mvops->minor_version, }; @@ -2843,8 +2926,9 @@ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, * a SEQUENCE request */ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_sequence_args *args) + const void *data) { + const struct nfs4_sequence_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(args), }; @@ -2859,8 +2943,9 @@ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, */ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_get_lease_time_args *args) + const void *data) { + const struct nfs4_get_lease_time_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->la_seq_args), }; @@ -2878,8 +2963,9 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req, */ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_reclaim_complete_args *args) + const void *data) { + const struct nfs41_reclaim_complete_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args) }; @@ -2895,8 +2981,9 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, */ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_getdeviceinfo_args *args) + const void *data) { + const struct nfs4_getdeviceinfo_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2919,8 +3006,9 @@ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutget_args *args) + const void *data) { + const struct nfs4_layoutget_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2941,8 +3029,9 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutcommit_args *args) + const void *priv) { + const struct nfs4_layoutcommit_args *args = priv; struct nfs4_layoutcommit_data *data = container_of(args, struct nfs4_layoutcommit_data, args); struct compound_hdr hdr = { @@ -2962,8 +3051,9 @@ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req, */ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_layoutreturn_args *args) + const void *data) { + const struct nfs4_layoutreturn_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2978,10 +3068,11 @@ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req, /* * Encode SECINFO_NO_NAME request */ -static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, +static void nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_secinfo_no_name_args *args) + const void *data) { + const struct nfs41_secinfo_no_name_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -2991,7 +3082,6 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, encode_putrootfh(xdr, &hdr); encode_secinfo_no_name(xdr, args, &hdr); encode_nops(&hdr); - return 0; } /* @@ -2999,8 +3089,9 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req, */ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_test_stateid_args *args) + const void *data) { + const struct nfs41_test_stateid_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -3016,8 +3107,9 @@ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req, */ static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs41_free_stateid_args *args) + const void *data) { + const struct nfs41_free_stateid_args *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -5005,6 +5097,11 @@ static int decode_lookup(struct xdr_stream *xdr) return decode_op_hdr(xdr, OP_LOOKUP); } +static int decode_lookupp(struct xdr_stream *xdr) +{ + return decode_op_hdr(xdr, OP_LOOKUPP); +} + /* This is too sick! */ static int decode_space_limit(struct xdr_stream *xdr, unsigned long *pagemod_limit) @@ -6101,8 +6198,9 @@ int decode_layoutreturn(struct xdr_stream *xdr, */ static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_closeres *res) + void *data) { + struct nfs_closeres *res = data; struct compound_hdr hdr; int status; @@ -6130,8 +6228,9 @@ out: * Decode ACCESS response */ static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_accessres *res) + void *data) { + struct nfs4_accessres *res = data; struct compound_hdr hdr; int status; @@ -6156,8 +6255,9 @@ out: * Decode LOOKUP response */ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_lookup_res *res) + void *data) { + struct nfs4_lookup_res *res = data; struct compound_hdr hdr; int status; @@ -6182,12 +6282,43 @@ out: } /* + * Decode LOOKUPP response + */ +static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *data) +{ + struct nfs4_lookupp_res *res = data; + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (status) + goto out; + status = decode_sequence(xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(xdr); + if (status) + goto out; + status = decode_lookupp(xdr); + if (status) + goto out; + status = decode_getfh(xdr, res->fh); + if (status) + goto out; + status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); +out: + return status; +} + +/* * Decode LOOKUP_ROOT response */ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_lookup_res *res) + void *data) { + struct nfs4_lookup_res *res = data; struct compound_hdr hdr; int status; @@ -6212,8 +6343,9 @@ out: * Decode REMOVE response */ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_removeres *res) + void *data) { + struct nfs_removeres *res = data; struct compound_hdr hdr; int status; @@ -6235,8 +6367,9 @@ out: * Decode RENAME response */ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_renameres *res) + void *data) { + struct nfs_renameres *res = data; struct compound_hdr hdr; int status; @@ -6264,8 +6397,9 @@ out: * Decode LINK response */ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_link_res *res) + void *data) { + struct nfs4_link_res *res = data; struct compound_hdr hdr; int status; @@ -6303,8 +6437,9 @@ out: * Decode CREATE response */ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_create_res *res) + void *data) { + struct nfs4_create_res *res = data; struct compound_hdr hdr; int status; @@ -6332,7 +6467,7 @@ out: * Decode SYMLINK response */ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_create_res *res) + void *res) { return nfs4_xdr_dec_create(rqstp, xdr, res); } @@ -6341,8 +6476,9 @@ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, * Decode GETATTR response */ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_getattr_res *res) + void *data) { + struct nfs4_getattr_res *res = data; struct compound_hdr hdr; int status; @@ -6364,8 +6500,9 @@ out: * Encode an SETACL request */ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_setaclargs *args) + const void *data) { + const struct nfs_setaclargs *args = data; struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), }; @@ -6382,8 +6519,9 @@ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_setaclres *res) + void *data) { + struct nfs_setaclres *res = data; struct compound_hdr hdr; int status; @@ -6406,8 +6544,9 @@ out: */ static int nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_getaclres *res) + void *data) { + struct nfs_getaclres *res = data; struct compound_hdr hdr; int status; @@ -6434,8 +6573,9 @@ out: * Decode CLOSE response */ static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_closeres *res) + void *data) { + struct nfs_closeres *res = data; struct compound_hdr hdr; int status; @@ -6468,8 +6608,9 @@ out: * Decode OPEN response */ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_openres *res) + void *data) { + struct nfs_openres *res = data; struct compound_hdr hdr; int status; @@ -6500,8 +6641,9 @@ out: */ static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_open_confirmres *res) + void *data) { + struct nfs_open_confirmres *res = data; struct compound_hdr hdr; int status; @@ -6521,8 +6663,9 @@ out: */ static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_openres *res) + void *data) { + struct nfs_openres *res = data; struct compound_hdr hdr; int status; @@ -6550,8 +6693,9 @@ out: */ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_setattrres *res) + void *data) { + struct nfs_setattrres *res = data; struct compound_hdr hdr; int status; @@ -6576,8 +6720,9 @@ out: * Decode LOCK response */ static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_lock_res *res) + void *data) { + struct nfs_lock_res *res = data; struct compound_hdr hdr; int status; @@ -6599,8 +6744,9 @@ out: * Decode LOCKT response */ static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_lockt_res *res) + void *data) { + struct nfs_lockt_res *res = data; struct compound_hdr hdr; int status; @@ -6622,8 +6768,9 @@ out: * Decode LOCKU response */ static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_locku_res *res) + void *data) { + struct nfs_locku_res *res = data; struct compound_hdr hdr; int status; @@ -6658,8 +6805,9 @@ static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_readlink_res *res) + void *data) { + struct nfs4_readlink_res *res = data; struct compound_hdr hdr; int status; @@ -6681,8 +6829,9 @@ out: * Decode READDIR response */ static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_readdir_res *res) + void *data) { + struct nfs4_readdir_res *res = data; struct compound_hdr hdr; int status; @@ -6704,8 +6853,9 @@ out: * Decode Read response */ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_pgio_res *res) + void *data) { + struct nfs_pgio_res *res = data; struct compound_hdr hdr; int status; @@ -6730,8 +6880,9 @@ out: * Decode WRITE response */ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_pgio_res *res) + void *data) { + struct nfs_pgio_res *res = data; struct compound_hdr hdr; int status; @@ -6760,8 +6911,9 @@ out: * Decode COMMIT response */ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_commitres *res) + void *data) { + struct nfs_commitres *res = data; struct compound_hdr hdr; int status; @@ -6784,8 +6936,9 @@ out: * Decode FSINFO response */ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fsinfo_res *res) + void *data) { + struct nfs4_fsinfo_res *res = data; struct compound_hdr hdr; int status; @@ -6803,8 +6956,9 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr, * Decode PATHCONF response */ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_pathconf_res *res) + void *data) { + struct nfs4_pathconf_res *res = data; struct compound_hdr hdr; int status; @@ -6822,8 +6976,9 @@ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr, * Decode STATFS response */ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_statfs_res *res) + void *data) { + struct nfs4_statfs_res *res = data; struct compound_hdr hdr; int status; @@ -6842,8 +6997,9 @@ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_server_caps_res *res) + void *data) { + struct nfs4_server_caps_res *res = data; struct compound_hdr hdr; int status; @@ -6881,8 +7037,9 @@ static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_setclientid_res *res) + void *data) { + struct nfs4_setclientid_res *res = data; struct compound_hdr hdr; int status; @@ -6896,7 +7053,8 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req, * Decode SETCLIENTID_CONFIRM response */ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, - struct xdr_stream *xdr) + struct xdr_stream *xdr, + void *data) { struct compound_hdr hdr; int status; @@ -6912,8 +7070,9 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req, */ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_delegreturnres *res) + void *data) { + struct nfs4_delegreturnres *res = data; struct compound_hdr hdr; int status; @@ -6947,8 +7106,9 @@ out: */ static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs4_fs_locations_res *res) + void *data) { + struct nfs4_fs_locations_res *res = data; struct compound_hdr hdr; int status; @@ -6990,8 +7150,9 @@ out: */ static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_secinfo_res *res) + void *data) { + struct nfs4_secinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7014,8 +7175,9 @@ out: */ static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_fsid_present_res *res) + void *data) { + struct nfs4_fsid_present_res *res = data; struct compound_hdr hdr; int status; @@ -7075,7 +7237,7 @@ static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_create_session_res *res) + void *res) { struct compound_hdr hdr; int status; @@ -7123,7 +7285,7 @@ static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_sequence_res *res) + void *res) { struct compound_hdr hdr; int status; @@ -7139,8 +7301,9 @@ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_get_lease_time_res *res) + void *data) { + struct nfs4_get_lease_time_res *res = data; struct compound_hdr hdr; int status; @@ -7159,8 +7322,9 @@ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_reclaim_complete_res *res) + void *data) { + struct nfs41_reclaim_complete_res *res = data; struct compound_hdr hdr; int status; @@ -7177,8 +7341,9 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, */ static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_getdeviceinfo_res *res) + void *data) { + struct nfs4_getdeviceinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7198,8 +7363,9 @@ out: */ static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutget_res *res) + void *data) { + struct nfs4_layoutget_res *res = data; struct compound_hdr hdr; int status; @@ -7222,8 +7388,9 @@ out: */ static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutreturn_res *res) + void *data) { + struct nfs4_layoutreturn_res *res = data; struct compound_hdr hdr; int status; @@ -7246,8 +7413,9 @@ out: */ static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_layoutcommit_res *res) + void *data) { + struct nfs4_layoutcommit_res *res = data; struct compound_hdr hdr; int status; @@ -7273,8 +7441,9 @@ out: */ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs4_secinfo_res *res) + void *data) { + struct nfs4_secinfo_res *res = data; struct compound_hdr hdr; int status; @@ -7297,8 +7466,9 @@ out: */ static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_test_stateid_res *res) + void *data) { + struct nfs41_test_stateid_res *res = data; struct compound_hdr hdr; int status; @@ -7318,8 +7488,9 @@ out: */ static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs41_free_stateid_res *res) + void *data) { + struct nfs41_free_stateid_res *res = data; struct compound_hdr hdr; int status; @@ -7350,7 +7521,7 @@ out: * on a directory already in our cache. */ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, - int plus) + bool plus) { unsigned int savep; uint32_t bitmap[3] = {0}; @@ -7484,8 +7655,8 @@ nfs4_stat_to_errno(int stat) #define PROC(proc, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_COMPOUND, \ - .p_encode = (kxdreproc_t)nfs4_xdr_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_##restype, \ + .p_encode = nfs4_xdr_##argtype, \ + .p_decode = nfs4_xdr_##restype, \ .p_arglen = NFS4_##argtype##_sz, \ .p_replen = NFS4_##restype##_sz, \ .p_statidx = NFSPROC4_CLNT_##proc, \ @@ -7497,7 +7668,7 @@ nfs4_stat_to_errno(int stat) .p_name = #proc, \ } -struct rpc_procinfo nfs4_procedures[] = { +const struct rpc_procinfo nfs4_procedures[] = { PROC(READ, enc_read, dec_read), PROC(WRITE, enc_write, dec_write), PROC(COMMIT, enc_commit, dec_commit), @@ -7517,6 +7688,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(ACCESS, enc_access, dec_access), PROC(GETATTR, enc_getattr, dec_getattr), PROC(LOOKUP, enc_lookup, dec_lookup), + PROC(LOOKUPP, enc_lookupp, dec_lookupp), PROC(LOOKUP_ROOT, enc_lookup_root, dec_lookup_root), PROC(REMOVE, enc_remove, dec_remove), PROC(RENAME, enc_rename, dec_rename), @@ -7564,10 +7736,12 @@ struct rpc_procinfo nfs4_procedures[] = { #endif /* CONFIG_NFS_V4_2 */ }; +static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)]; const struct rpc_version nfs_version4 = { .number = 4, .nrprocs = ARRAY_SIZE(nfs4_procedures), - .procs = nfs4_procedures + .procs = nfs4_procedures, + .counts = nfs_version4_counts, }; /* diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 2ca9167bc97d..551711042ba4 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -719,6 +719,254 @@ TRACE_EVENT(nfs_sillyrename_unlink, __get_str(name) ) ); + +TRACE_EVENT(nfs_initiate_read, + TP_PROTO( + const struct inode *inode, + loff_t offset, unsigned long count + ), + + TP_ARGS(inode, offset, count), + + TP_STRUCT__entry( + __field(loff_t, offset) + __field(unsigned long, count) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->offset = offset; + __entry->count = count; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->count + ) +); + +TRACE_EVENT(nfs_readpage_done, + TP_PROTO( + const struct inode *inode, + int status, loff_t offset, bool eof + ), + + TP_ARGS(inode, status, offset, eof), + + TP_STRUCT__entry( + __field(int, status) + __field(loff_t, offset) + __field(bool, eof) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->status = status; + __entry->offset = offset; + __entry->eof = eof; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld status=%d%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->status, + __entry->eof ? " eof" : "" + ) +); + +/* + * XXX: I tried using NFS_UNSTABLE and friends in this table, but they + * all evaluate to 0 for some reason, even if I include linux/nfs.h. + */ +#define nfs_show_stable(stable) \ + __print_symbolic(stable, \ + { 0, " (UNSTABLE)" }, \ + { 1, " (DATA_SYNC)" }, \ + { 2, " (FILE_SYNC)" }) + +TRACE_EVENT(nfs_initiate_write, + TP_PROTO( + const struct inode *inode, + loff_t offset, unsigned long count, + enum nfs3_stable_how stable + ), + + TP_ARGS(inode, offset, count, stable), + + TP_STRUCT__entry( + __field(loff_t, offset) + __field(unsigned long, count) + __field(enum nfs3_stable_how, stable) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->offset = offset; + __entry->count = count; + __entry->stable = stable; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%lu stable=%d%s", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->count, + __entry->stable, nfs_show_stable(__entry->stable) + ) +); + +TRACE_EVENT(nfs_writeback_done, + TP_PROTO( + const struct inode *inode, + int status, + loff_t offset, + struct nfs_writeverf *writeverf + ), + + TP_ARGS(inode, status, offset, writeverf), + + TP_STRUCT__entry( + __field(int, status) + __field(loff_t, offset) + __field(enum nfs3_stable_how, stable) + __field(unsigned long long, verifier) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->status = status; + __entry->offset = offset; + __entry->stable = writeverf->committed; + memcpy(&__entry->verifier, &writeverf->verifier, + sizeof(__entry->verifier)); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld status=%d stable=%d%s " + "verifier 0x%016llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->status, + __entry->stable, nfs_show_stable(__entry->stable), + __entry->verifier + ) +); + +TRACE_EVENT(nfs_initiate_commit, + TP_PROTO( + const struct nfs_commit_data *data + ), + + TP_ARGS(data), + + TP_STRUCT__entry( + __field(loff_t, offset) + __field(unsigned long, count) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct inode *inode = data->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->offset = data->args.offset; + __entry->count = data->args.count; + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld count=%lu", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->count + ) +); + +TRACE_EVENT(nfs_commit_done, + TP_PROTO( + const struct nfs_commit_data *data + ), + + TP_ARGS(data), + + TP_STRUCT__entry( + __field(int, status) + __field(loff_t, offset) + __field(unsigned long long, verifier) + __field(dev_t, dev) + __field(u32, fhandle) + __field(u64, fileid) + ), + + TP_fast_assign( + const struct inode *inode = data->inode; + const struct nfs_inode *nfsi = NFS_I(inode); + + __entry->status = data->res.op_status; + __entry->offset = data->args.offset; + memcpy(&__entry->verifier, &data->verf.verifier, + sizeof(__entry->verifier)); + __entry->dev = inode->i_sb->s_dev; + __entry->fileid = nfsi->fileid; + __entry->fhandle = nfs_fhandle_hash(&nfsi->fh); + ), + + TP_printk( + "fileid=%02x:%02x:%llu fhandle=0x%08x " + "offset=%lld status=%d verifier 0x%016llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + (unsigned long long)__entry->fileid, + __entry->fhandle, + __entry->offset, __entry->status, + __entry->verifier + ) +); + #endif /* _TRACE_NFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index ad92b401326c..d0543e19098a 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -50,8 +50,8 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->cred = hdr->req->wb_context->cred; hdr->io_start = req_offset(hdr->req); hdr->good_bytes = mirror->pg_count; + hdr->io_completion = desc->pg_io_completion; hdr->dreq = desc->pg_dreq; - hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) @@ -134,19 +134,14 @@ EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait); /* * nfs_page_group_lock - lock the head of the page group * @req - request in group that is to be locked - * @nonblock - if true don't block waiting for lock * - * this lock must be held if modifying the page group list + * this lock must be held when traversing or modifying the page + * group list * - * return 0 on success, < 0 on error: -EDELAY if nonblocking or the - * result from wait_on_bit_lock - * - * NOTE: calling with nonblock=false should always have set the - * lock bit (see fs/buffer.c and other uses of wait_on_bit_lock - * with TASK_UNINTERRUPTIBLE), so there is no need to check the result. + * return 0 on success, < 0 on error */ int -nfs_page_group_lock(struct nfs_page *req, bool nonblock) +nfs_page_group_lock(struct nfs_page *req) { struct nfs_page *head = req->wb_head; @@ -155,28 +150,10 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock) if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags)) return 0; - if (!nonblock) - return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, + set_bit(PG_CONTENDED1, &head->wb_flags); + smp_mb__after_atomic(); + return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, TASK_UNINTERRUPTIBLE); - - return -EAGAIN; -} - -/* - * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it - * @req - a request in the group - * - * This is a blocking call to wait for the group lock to be cleared. - */ -void -nfs_page_group_lock_wait(struct nfs_page *req) -{ - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - - wait_on_bit(&head->wb_flags, PG_HEADLOCK, - TASK_UNINTERRUPTIBLE); } /* @@ -193,6 +170,8 @@ nfs_page_group_unlock(struct nfs_page *req) smp_mb__before_atomic(); clear_bit(PG_HEADLOCK, &head->wb_flags); smp_mb__after_atomic(); + if (!test_bit(PG_CONTENDED1, &head->wb_flags)) + return; wake_up_bit(&head->wb_flags, PG_HEADLOCK); } @@ -237,7 +216,7 @@ bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit) { bool ret; - nfs_page_group_lock(req, false); + nfs_page_group_lock(req); ret = nfs_page_group_sync_on_bit_locked(req, bit); nfs_page_group_unlock(req); @@ -279,9 +258,7 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) inode = page_file_mapping(req->wb_page)->host; set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); - spin_lock(&inode->i_lock); - NFS_I(inode)->nrequests++; - spin_unlock(&inode->i_lock); + atomic_long_inc(&NFS_I(inode)->nrequests); } } } @@ -297,14 +274,11 @@ static void nfs_page_group_destroy(struct kref *kref) { struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); + struct nfs_page *head = req->wb_head; struct nfs_page *tmp, *next; - /* subrequests must release the ref on the head request */ - if (req->wb_head != req) - nfs_release_request(req->wb_head); - if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN)) - return; + goto out; tmp = req; do { @@ -315,6 +289,10 @@ nfs_page_group_destroy(struct kref *kref) nfs_free_request(tmp); tmp = next; } while (tmp != req); +out: + /* subrequests must release the ref on the head request */ + if (head != req) + nfs_release_request(head); } /** @@ -383,6 +361,8 @@ void nfs_unlock_request(struct nfs_page *req) smp_mb__before_atomic(); clear_bit(PG_BUSY, &req->wb_flags); smp_mb__after_atomic(); + if (!test_bit(PG_CONTENDED2, &req->wb_flags)) + return; wake_up_bit(&req->wb_flags, PG_BUSY); } @@ -454,6 +434,7 @@ void nfs_release_request(struct nfs_page *req) { kref_put(&req->wb_kref, nfs_page_group_destroy); } +EXPORT_SYMBOL_GPL(nfs_release_request); /** * nfs_wait_on_request - Wait for a request to complete. @@ -465,9 +446,14 @@ void nfs_release_request(struct nfs_page *req) int nfs_wait_on_request(struct nfs_page *req) { + if (!test_bit(PG_BUSY, &req->wb_flags)) + return 0; + set_bit(PG_CONTENDED2, &req->wb_flags); + smp_mb__after_atomic(); return wait_on_bit_io(&req->wb_flags, PG_BUSY, TASK_UNINTERRUPTIBLE); } +EXPORT_SYMBOL_GPL(nfs_wait_on_request); /* * nfs_generic_pg_test - determine if requests can be coalesced @@ -515,16 +501,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops) } EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc); -/* - * nfs_pgio_header_free - Free a read or write header - * @hdr: The header to free - */ -void nfs_pgio_header_free(struct nfs_pgio_header *hdr) -{ - hdr->rw_ops->rw_free_header(hdr); -} -EXPORT_SYMBOL_GPL(nfs_pgio_header_free); - /** * nfs_pgio_data_destroy - make @hdr suitable for reuse * @@ -533,14 +509,24 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free); * * @hdr: A header that has had nfs_generic_pgio called */ -void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr) +static void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr) { if (hdr->args.context) put_nfs_open_context(hdr->args.context); if (hdr->page_array.pagevec != hdr->page_array.page_array) kfree(hdr->page_array.pagevec); } -EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy); + +/* + * nfs_pgio_header_free - Free a read or write header + * @hdr: The header to free + */ +void nfs_pgio_header_free(struct nfs_pgio_header *hdr) +{ + nfs_pgio_data_destroy(hdr); + hdr->rw_ops->rw_free_header(hdr); +} +EXPORT_SYMBOL_GPL(nfs_pgio_header_free); /** * nfs_pgio_rpcsetup - Set up arguments for a pageio call @@ -654,7 +640,6 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); static void nfs_pgio_error(struct nfs_pgio_header *hdr) { set_bit(NFS_IOHDR_REDO, &hdr->flags); - nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); } @@ -665,7 +650,6 @@ static void nfs_pgio_error(struct nfs_pgio_header *hdr) static void nfs_pgio_release(void *calldata) { struct nfs_pgio_header *hdr = calldata; - nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); } @@ -696,12 +680,8 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, const struct nfs_pgio_completion_ops *compl_ops, const struct nfs_rw_ops *rw_ops, size_t bsize, - int io_flags, - gfp_t gfp_flags) + int io_flags) { - struct nfs_pgio_mirror *new; - int i; - desc->pg_moreio = 0; desc->pg_inode = inode; desc->pg_ops = pg_ops; @@ -710,30 +690,17 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; + desc->pg_io_completion = NULL; desc->pg_dreq = NULL; - desc->pg_layout_private = NULL; desc->pg_bsize = bsize; desc->pg_mirror_count = 1; desc->pg_mirror_idx = 0; - if (pg_ops->pg_get_mirror_count) { - /* until we have a request, we don't have an lseg and no - * idea how many mirrors there will be */ - new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX, - sizeof(struct nfs_pgio_mirror), gfp_flags); - desc->pg_mirrors_dynamic = new; - desc->pg_mirrors = new; - - for (i = 0; i < NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX; i++) - nfs_pageio_mirror_init(&desc->pg_mirrors[i], bsize); - } else { - desc->pg_mirrors_dynamic = NULL; - desc->pg_mirrors = desc->pg_mirrors_static; - nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize); - } + desc->pg_mirrors_dynamic = NULL; + desc->pg_mirrors = desc->pg_mirrors_static; + nfs_pageio_mirror_init(&desc->pg_mirrors[0], bsize); } -EXPORT_SYMBOL_GPL(nfs_pageio_init); /** * nfs_pgio_result - Basic pageio error handling @@ -779,6 +746,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, gfp_t gfp_flags = GFP_KERNEL; pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count); + pg_array->npages = pagecount; if (pagecount <= ARRAY_SIZE(pg_array->page_array)) pg_array->pagevec = pg_array->page_array; @@ -849,32 +817,52 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) return ret; } +static struct nfs_pgio_mirror * +nfs_pageio_alloc_mirrors(struct nfs_pageio_descriptor *desc, + unsigned int mirror_count) +{ + struct nfs_pgio_mirror *ret; + unsigned int i; + + kfree(desc->pg_mirrors_dynamic); + desc->pg_mirrors_dynamic = NULL; + if (mirror_count == 1) + return desc->pg_mirrors_static; + ret = kmalloc_array(mirror_count, sizeof(*ret), GFP_NOFS); + if (ret != NULL) { + for (i = 0; i < mirror_count; i++) + nfs_pageio_mirror_init(&ret[i], desc->pg_bsize); + desc->pg_mirrors_dynamic = ret; + } + return ret; +} + /* * nfs_pageio_setup_mirroring - determine if mirroring is to be used * by calling the pg_get_mirror_count op */ -static int nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, +static void nfs_pageio_setup_mirroring(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { - int mirror_count = 1; - - if (!pgio->pg_ops->pg_get_mirror_count) - return 0; + unsigned int mirror_count = 1; - mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); - - if (pgio->pg_error < 0) - return pgio->pg_error; - - if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) - return -EINVAL; + if (pgio->pg_ops->pg_get_mirror_count) + mirror_count = pgio->pg_ops->pg_get_mirror_count(pgio, req); + if (mirror_count == pgio->pg_mirror_count || pgio->pg_error < 0) + return; - if (WARN_ON_ONCE(!pgio->pg_mirrors_dynamic)) - return -EINVAL; + if (!mirror_count || mirror_count > NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX) { + pgio->pg_error = -EINVAL; + return; + } + pgio->pg_mirrors = nfs_pageio_alloc_mirrors(pgio, mirror_count); + if (pgio->pg_mirrors == NULL) { + pgio->pg_error = -ENOMEM; + pgio->pg_mirrors = pgio->pg_mirrors_static; + mirror_count = 1; + } pgio->pg_mirror_count = mirror_count; - - return 0; } /* @@ -1020,7 +1008,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, unsigned int bytes_left = 0; unsigned int offset, pgbase; - nfs_page_group_lock(req, false); + nfs_page_group_lock(req); subreq = req; bytes_left = subreq->wb_bytes; @@ -1042,7 +1030,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (mirror->pg_recoalesce) return 0; /* retry add_request for this subreq */ - nfs_page_group_lock(req, false); + nfs_page_group_lock(req); continue; } @@ -1139,7 +1127,7 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, for (midx = 0; midx < desc->pg_mirror_count; midx++) { if (midx) { - nfs_page_group_lock(req, false); + nfs_page_group_lock(req); /* find the last request */ for (lastreq = req->wb_head; @@ -1182,8 +1170,8 @@ out_failed: /* remember fatal errors */ if (nfs_error_is_fatal(desc->pg_error)) - mapping_set_error(desc->pg_inode->i_mapping, - desc->pg_error); + nfs_context_set_write_error(req->wb_context, + desc->pg_error); func = desc->pg_completion_ops->error_cleanup; for (midx = 0; midx < desc->pg_mirror_count; midx++) { @@ -1233,6 +1221,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, { LIST_HEAD(failed); + desc->pg_io_completion = hdr->io_completion; desc->pg_dreq = hdr->dreq; while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index c383d0913b54..3bcd669a3152 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -529,47 +529,6 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) } EXPORT_SYMBOL_GPL(pnfs_put_lseg); -static void pnfs_free_lseg_async_work(struct work_struct *work) -{ - struct pnfs_layout_segment *lseg; - struct pnfs_layout_hdr *lo; - - lseg = container_of(work, struct pnfs_layout_segment, pls_work); - lo = lseg->pls_layout; - - pnfs_free_lseg(lseg); - pnfs_put_layout_hdr(lo); -} - -static void pnfs_free_lseg_async(struct pnfs_layout_segment *lseg) -{ - INIT_WORK(&lseg->pls_work, pnfs_free_lseg_async_work); - schedule_work(&lseg->pls_work); -} - -void -pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg) -{ - if (!lseg) - return; - - assert_spin_locked(&lseg->pls_layout->plh_inode->i_lock); - - dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg, - atomic_read(&lseg->pls_refcount), - test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); - if (atomic_dec_and_test(&lseg->pls_refcount)) { - struct pnfs_layout_hdr *lo = lseg->pls_layout; - if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) - return; - pnfs_layout_remove_lseg(lo, lseg); - if (!pnfs_cache_lseg_for_layoutreturn(lo, lseg)) { - pnfs_get_layout_hdr(lo); - pnfs_free_lseg_async(lseg); - } - } -} - /* * is l2 fully contained in l1? * start1 end1 @@ -1705,7 +1664,7 @@ pnfs_update_layout(struct inode *ino, .offset = pos, .length = count, }; - unsigned pg_offset, seq; + unsigned pg_offset; struct nfs_server *server = NFS_SERVER(ino); struct nfs_client *clp = server->nfs_client; struct pnfs_layout_hdr *lo = NULL; @@ -1795,10 +1754,14 @@ lookup_again: } first = true; - do { - seq = read_seqbegin(&ctx->state->seqlock); - nfs4_stateid_copy(&stateid, &ctx->state->stateid); - } while (read_seqretry(&ctx->state->seqlock, seq)); + if (nfs4_select_rw_stateid(ctx->state, + iomode == IOMODE_RW ? FMODE_WRITE : FMODE_READ, + NULL, &stateid, NULL) != 0) { + trace_pnfs_update_layout(ino, pos, count, + iomode, lo, lseg, + PNFS_UPDATE_LAYOUT_INVALID_OPEN); + goto out_unlock; + } } else { nfs4_stateid_copy(&stateid, &lo->plh_stateid); } @@ -2274,7 +2237,6 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, nfs_pageio_reset_write_mds(desc); mirror->pg_recoalesce = 1; } - nfs_pgio_data_destroy(hdr); hdr->release(hdr); } @@ -2398,7 +2360,6 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, nfs_pageio_reset_read_mds(desc); mirror->pg_recoalesce = 1; } - nfs_pgio_data_destroy(hdr); hdr->release(hdr); } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 99731e3e332f..87f144f14d1e 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -67,7 +67,6 @@ struct pnfs_layout_segment { u32 pls_seq; unsigned long pls_flags; struct pnfs_layout_hdr *pls_layout; - struct work_struct pls_work; }; enum pnfs_try_status { @@ -230,7 +229,6 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync); /* pnfs.c */ void pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo); void pnfs_put_lseg(struct pnfs_layout_segment *lseg); -void pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg); void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, struct nfs_fsinfo *); void unset_pnfs_layoutdriver(struct nfs_server *); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index d40755a0984b..60da59be83b6 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -83,34 +83,11 @@ pnfs_generic_clear_request_commit(struct nfs_page *req, } out: nfs_request_remove_commit_list(req, cinfo); - pnfs_put_lseg_locked(freeme); + pnfs_put_lseg(freeme); } EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit); static int -pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst, - struct nfs_commit_info *cinfo, int max) -{ - struct nfs_page *req, *tmp; - int ret = 0; - - list_for_each_entry_safe(req, tmp, src, wb_list) { - if (!nfs_lock_request(req)) - continue; - kref_get(&req->wb_kref); - if (cond_resched_lock(&cinfo->inode->i_lock)) - list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req, cinfo); - clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); - nfs_list_add_request(req, dst); - ret++; - if ((ret == max) && !cinfo->dreq) - break; - } - return ret; -} - -static int pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, struct nfs_commit_info *cinfo, int max) @@ -119,15 +96,15 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, struct list_head *dst = &bucket->committing; int ret; - lockdep_assert_held(&cinfo->inode->i_lock); - ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max); + lockdep_assert_held(&NFS_I(cinfo->inode)->commit_mutex); + ret = nfs_scan_commit_list(src, dst, cinfo, max); if (ret) { cinfo->ds->nwritten -= ret; cinfo->ds->ncommitting += ret; if (bucket->clseg == NULL) bucket->clseg = pnfs_get_lseg(bucket->wlseg); if (list_empty(src)) { - pnfs_put_lseg_locked(bucket->wlseg); + pnfs_put_lseg(bucket->wlseg); bucket->wlseg = NULL; } } @@ -142,7 +119,7 @@ int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, { int i, rv = 0, cnt; - lockdep_assert_held(&cinfo->inode->i_lock); + lockdep_assert_held(&NFS_I(cinfo->inode)->commit_mutex); for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i], cinfo, max); @@ -159,13 +136,17 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst, { struct pnfs_commit_bucket *b; struct pnfs_layout_segment *freeme; + int nwritten; int i; - lockdep_assert_held(&cinfo->inode->i_lock); + lockdep_assert_held(&NFS_I(cinfo->inode)->commit_mutex); restart: for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { - if (pnfs_generic_transfer_commit_list(&b->written, dst, - cinfo, 0)) { + nwritten = nfs_scan_commit_list(&b->written, dst, cinfo, 0); + if (!nwritten) + continue; + cinfo->ds->nwritten -= nwritten; + if (list_empty(&b->written)) { freeme = b->wlseg; b->wlseg = NULL; spin_unlock(&cinfo->inode->i_lock); @@ -174,7 +155,6 @@ restart: goto restart; } } - cinfo->ds->nwritten = 0; } EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs); @@ -183,6 +163,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx) struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds; struct pnfs_commit_bucket *bucket; struct pnfs_layout_segment *freeme; + struct list_head *pos; LIST_HEAD(pages); int i; @@ -193,6 +174,8 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx) continue; freeme = bucket->clseg; bucket->clseg = NULL; + list_for_each(pos, &bucket->committing) + cinfo->ds->ncommitting--; list_splice_init(&bucket->committing, &pages); spin_unlock(&cinfo->inode->i_lock); nfs_retry_commit(&pages, freeme, cinfo, i); @@ -217,13 +200,6 @@ pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo, for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { if (list_empty(&bucket->committing)) continue; - /* - * If the layout segment is invalid, then let - * pnfs_generic_retry_commit() clean up the bucket. - */ - if (bucket->clseg && !pnfs_is_valid_lseg(bucket->clseg) && - !test_bit(NFS_LSEG_LAYOUTRETURN, &bucket->clseg->pls_flags)) - break; data = nfs_commitdata_alloc(false); if (!data) break; @@ -243,9 +219,12 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages, struct nfs_commit_info *cinfo) { struct pnfs_commit_bucket *bucket; + struct list_head *pos; bucket = &cinfo->ds->buckets[data->ds_commit_index]; spin_lock(&cinfo->inode->i_lock); + list_for_each(pos, &bucket->committing) + cinfo->ds->ncommitting--; list_splice_init(&bucket->committing, pages); data->lseg = bucket->clseg; bucket->clseg = NULL; @@ -330,7 +309,6 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, } } out: - cinfo->ds->ncommitting = 0; return PNFS_ATTEMPTED; } EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist); @@ -951,12 +929,12 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, struct list_head *list; struct pnfs_commit_bucket *buckets; - spin_lock(&cinfo->inode->i_lock); + mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); buckets = cinfo->ds->buckets; list = &buckets[ds_commit_idx].written; if (list_empty(list)) { if (!pnfs_is_valid_lseg(lseg)) { - spin_unlock(&cinfo->inode->i_lock); + mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); cinfo->completion_ops->resched_write(cinfo, req); return; } @@ -973,7 +951,7 @@ pnfs_layout_mark_request_commit(struct nfs_page *req, cinfo->ds->nwritten++; nfs_request_add_commit_list_locked(req, list, cinfo); - spin_unlock(&cinfo->inode->i_lock); + mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); nfs_mark_page_unstable(req->wb_page, cinfo); } EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 9872cf676a50..7962e49097c3 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -485,7 +485,7 @@ nfs_proc_rmdir(struct inode *dir, const struct qstr *name) */ static int nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page **pages, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); struct nfs_readdirargs arg = { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index a8421d9dab6a..48d7277c60a9 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -25,6 +25,7 @@ #include "iostat.h" #include "fscache.h" #include "pnfs.h" +#include "nfstrace.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -68,7 +69,7 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, pg_ops = server->pnfs_curr_ld->pg_read_ops; #endif nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops, - server->rsize, 0, GFP_KERNEL); + server->rsize, 0); } EXPORT_SYMBOL_GPL(nfs_pageio_init_read); @@ -200,6 +201,7 @@ static void nfs_initiate_read(struct nfs_pgio_header *hdr, task_setup_data->flags |= swap_flags; rpc_ops->read_setup(hdr, msg); + trace_nfs_initiate_read(inode, hdr->io_start, hdr->good_bytes); } static void @@ -232,6 +234,8 @@ static int nfs_readpage_done(struct rpc_task *task, return status; nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, hdr->res.count); + trace_nfs_readpage_done(inode, task->tk_status, + hdr->args.offset, hdr->res.eof); if (task->tk_status == -ESTALE) { set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index eceb4eabb064..c9d24bae3025 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -812,7 +812,7 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) * Display all mount option settings */ seq_printf(m, "\n\topts:\t"); - seq_puts(m, root->d_sb->s_flags & MS_RDONLY ? "ro" : "rw"); + seq_puts(m, sb_rdonly(root->d_sb) ? "ro" : "rw"); seq_puts(m, root->d_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : ""); seq_puts(m, root->d_sb->s_flags & MS_NOATIME ? ",noatime" : ""); seq_puts(m, root->d_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : ""); @@ -879,7 +879,7 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root) if (nfss->options & NFS_OPTION_FSCACHE) { seq_printf(m, "\n\tfsc:\t"); for (i = 0; i < __NFSIOS_FSCACHEMAX; i++) - seq_printf(m, "%Lu ", totals.bytes[i]); + seq_printf(m, "%Lu ", totals.fscache[i]); } #endif seq_printf(m, "\n"); @@ -1691,8 +1691,8 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, rpc_authflavor_t *server_authlist, unsigned int count) { rpc_authflavor_t flavor = RPC_AUTH_MAXFLAVOR; + bool found_auth_null = false; unsigned int i; - int use_auth_null = false; /* * If the sec= mount option is used, the specified flavor or AUTH_NULL @@ -1701,6 +1701,10 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, * AUTH_NULL has a special meaning when it's in the server list - it * means that the server will ignore the rpc creds, so any flavor * can be used but still use the sec= that was specified. + * + * Note also that the MNT procedure in MNTv1 does not return a list + * of supported security flavors. In this case, nfs_mount() fabricates + * a security flavor list containing just AUTH_NULL. */ for (i = 0; i < count; i++) { flavor = server_authlist[i]; @@ -1709,11 +1713,11 @@ static int nfs_verify_authflavors(struct nfs_parsed_mount_data *args, goto out; if (flavor == RPC_AUTH_NULL) - use_auth_null = true; + found_auth_null = true; } - if (use_auth_null) { - flavor = RPC_AUTH_NULL; + if (found_auth_null) { + flavor = args->auth_info.flavors[0]; goto out; } @@ -2339,6 +2343,7 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) */ sb->s_flags |= MS_POSIXACL; sb->s_time_gran = 1; + sb->s_export_op = &nfs_export_ops; } nfs_initialise_sb(sb); @@ -2360,6 +2365,7 @@ static void nfs_clone_super(struct super_block *sb, sb->s_xattr = old_sb->s_xattr; sb->s_op = old_sb->s_op; sb->s_time_gran = 1; + sb->s_export_op = old_sb->s_export_op; if (server->nfs_client->rpc_ops->version != 2) { /* The VFS shouldn't apply the umask to mode bits. We will do @@ -2545,10 +2551,25 @@ EXPORT_SYMBOL_GPL(nfs_set_sb_security); int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, struct nfs_mount_info *mount_info) { + int error; + unsigned long kflags = 0, kflags_out = 0; + /* clone any lsm security options from the parent to the new sb */ if (d_inode(mntroot)->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) return -ESTALE; - return security_sb_clone_mnt_opts(mount_info->cloned->sb, s); + + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL) + kflags |= SECURITY_LSM_NATIVE_LABELS; + + error = security_sb_clone_mnt_opts(mount_info->cloned->sb, s, kflags, + &kflags_out); + if (error) + return error; + + if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL && + !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) + NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL; + return 0; } EXPORT_SYMBOL_GPL(nfs_clone_sb_security); diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 191aa577dd1f..e3949d93085c 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -288,6 +288,19 @@ static void nfs_async_rename_release(void *calldata) if (d_really_is_positive(data->old_dentry)) nfs_mark_for_revalidate(d_inode(data->old_dentry)); + /* The result of the rename is unknown. Play it safe by + * forcing a new lookup */ + if (data->cancelled) { + spin_lock(&data->old_dir->i_lock); + nfs_force_lookup_revalidate(data->old_dir); + spin_unlock(&data->old_dir->i_lock); + if (data->new_dir != data->old_dir) { + spin_lock(&data->new_dir->i_lock); + nfs_force_lookup_revalidate(data->new_dir); + spin_unlock(&data->new_dir->i_lock); + } + } + dput(data->old_dentry); dput(data->new_dentry); iput(data->old_dir); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index db7ba542559e..babebbccae2a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -40,6 +40,12 @@ #define MIN_POOL_WRITE (32) #define MIN_POOL_COMMIT (4) +struct nfs_io_completion { + void (*complete)(void *data); + void *data; + struct kref refcount; +}; + /* * Local function declarations */ @@ -96,10 +102,8 @@ static struct nfs_pgio_header *nfs_writehdr_alloc(void) { struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO); - if (p) { - memset(p, 0, sizeof(*p)); - p->rw_mode = FMODE_WRITE; - } + memset(p, 0, sizeof(*p)); + p->rw_mode = FMODE_WRITE; return p; } @@ -108,11 +112,45 @@ static void nfs_writehdr_free(struct nfs_pgio_header *hdr) mempool_free(hdr, nfs_wdata_mempool); } -static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) +static struct nfs_io_completion *nfs_io_completion_alloc(gfp_t gfp_flags) +{ + return kmalloc(sizeof(struct nfs_io_completion), gfp_flags); +} + +static void nfs_io_completion_init(struct nfs_io_completion *ioc, + void (*complete)(void *), void *data) +{ + ioc->complete = complete; + ioc->data = data; + kref_init(&ioc->refcount); +} + +static void nfs_io_completion_release(struct kref *kref) +{ + struct nfs_io_completion *ioc = container_of(kref, + struct nfs_io_completion, refcount); + ioc->complete(ioc->data); + kfree(ioc); +} + +static void nfs_io_completion_get(struct nfs_io_completion *ioc) +{ + if (ioc != NULL) + kref_get(&ioc->refcount); +} + +static void nfs_io_completion_put(struct nfs_io_completion *ioc) +{ + if (ioc != NULL) + kref_put(&ioc->refcount, nfs_io_completion_release); +} + +static struct nfs_page * +nfs_page_private_request(struct page *page) { - ctx->error = error; - smp_wmb(); - set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); + if (!PagePrivate(page)) + return NULL; + return (struct nfs_page *)page_private(page); } /* @@ -123,21 +161,41 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) * returns matching head request with reference held, or NULL if not found. */ static struct nfs_page * -nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page) +nfs_page_find_private_request(struct page *page) { - struct nfs_page *req = NULL; - - if (PagePrivate(page)) - req = (struct nfs_page *)page_private(page); - else if (unlikely(PageSwapCache(page))) - req = nfs_page_search_commits_for_head_request_locked(nfsi, - page); + struct address_space *mapping = page_file_mapping(page); + struct nfs_page *req; + if (!PagePrivate(page)) + return NULL; + spin_lock(&mapping->private_lock); + req = nfs_page_private_request(page); if (req) { WARN_ON_ONCE(req->wb_head != req); kref_get(&req->wb_kref); } + spin_unlock(&mapping->private_lock); + return req; +} +static struct nfs_page * +nfs_page_find_swap_request(struct page *page) +{ + struct inode *inode = page_file_mapping(page)->host; + struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_page *req = NULL; + if (!PageSwapCache(page)) + return NULL; + mutex_lock(&nfsi->commit_mutex); + if (PageSwapCache(page)) { + req = nfs_page_search_commits_for_head_request_locked(nfsi, + page); + if (req) { + WARN_ON_ONCE(req->wb_head != req); + kref_get(&req->wb_kref); + } + } + mutex_unlock(&nfsi->commit_mutex); return req; } @@ -148,12 +206,11 @@ nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page) */ static struct nfs_page *nfs_page_find_head_request(struct page *page) { - struct inode *inode = page_file_mapping(page)->host; - struct nfs_page *req = NULL; + struct nfs_page *req; - spin_lock(&inode->i_lock); - req = nfs_page_find_head_request_locked(NFS_I(inode), page); - spin_unlock(&inode->i_lock); + req = nfs_page_find_private_request(page); + if (!req) + req = nfs_page_find_swap_request(page); return req; } @@ -202,9 +259,6 @@ nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) { struct nfs_page *req; - WARN_ON_ONCE(head != head->wb_head); - WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &head->wb_head->wb_flags)); - req = head; do { if (page_offset >= req->wb_pgbase && @@ -230,20 +284,17 @@ static bool nfs_page_group_covers_page(struct nfs_page *req) unsigned int pos = 0; unsigned int len = nfs_page_length(req->wb_page); - nfs_page_group_lock(req, false); + nfs_page_group_lock(req); - do { + for (;;) { tmp = nfs_page_group_search_locked(req->wb_head, pos); - if (tmp) { - /* no way this should happen */ - WARN_ON_ONCE(tmp->wb_pgbase != pos); - pos += tmp->wb_bytes - (pos - tmp->wb_pgbase); - } - } while (tmp && pos < len); + if (!tmp) + break; + pos = tmp->wb_pgbase + tmp->wb_bytes; + } nfs_page_group_unlock(req); - WARN_ON_ONCE(pos > len); - return pos == len; + return pos >= len; } /* We can set the PG_uptodate flag if we see that a write request @@ -294,8 +345,11 @@ static void nfs_end_page_writeback(struct nfs_page *req) { struct inode *inode = page_file_mapping(req->wb_page)->host; struct nfs_server *nfss = NFS_SERVER(inode); + bool is_done; - if (!nfs_page_group_sync_on_bit(req, PG_WB_END)) + is_done = nfs_page_group_sync_on_bit(req, PG_WB_END); + nfs_unlock_request(req); + if (!is_done) return; end_page_writeback(req->wb_page); @@ -303,22 +357,6 @@ static void nfs_end_page_writeback(struct nfs_page *req) clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); } - -/* nfs_page_group_clear_bits - * @req - an nfs request - * clears all page group related bits from @req - */ -static void -nfs_page_group_clear_bits(struct nfs_page *req) -{ - clear_bit(PG_TEARDOWN, &req->wb_flags); - clear_bit(PG_UNLOCKPAGE, &req->wb_flags); - clear_bit(PG_UPTODATE, &req->wb_flags); - clear_bit(PG_WB_END, &req->wb_flags); - clear_bit(PG_REMOVE, &req->wb_flags); -} - - /* * nfs_unroll_locks_and_wait - unlock all newly locked reqs and wait on @req * @@ -327,43 +365,24 @@ nfs_page_group_clear_bits(struct nfs_page *req) * @inode - inode associated with request page group, must be holding inode lock * @head - head request of page group, must be holding head lock * @req - request that couldn't lock and needs to wait on the req bit lock - * @nonblock - if true, don't actually wait * - * NOTE: this must be called holding page_group bit lock and inode spin lock - * and BOTH will be released before returning. + * NOTE: this must be called holding page_group bit lock + * which will be released before returning. * * returns 0 on success, < 0 on error. */ -static int -nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head, - struct nfs_page *req, bool nonblock) - __releases(&inode->i_lock) +static void +nfs_unroll_locks(struct inode *inode, struct nfs_page *head, + struct nfs_page *req) { struct nfs_page *tmp; - int ret; /* relinquish all the locks successfully grabbed this run */ - for (tmp = head ; tmp != req; tmp = tmp->wb_this_page) - nfs_unlock_request(tmp); - - WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags)); - - /* grab a ref on the request that will be waited on */ - kref_get(&req->wb_kref); - - nfs_page_group_unlock(head); - spin_unlock(&inode->i_lock); - - /* release ref from nfs_page_find_head_request_locked */ - nfs_release_request(head); - - if (!nonblock) - ret = nfs_wait_on_request(req); - else - ret = -EAGAIN; - nfs_release_request(req); - - return ret; + for (tmp = head->wb_this_page ; tmp != req; tmp = tmp->wb_this_page) { + if (!kref_read(&tmp->wb_kref)) + continue; + nfs_unlock_and_release_request(tmp); + } } /* @@ -378,7 +397,8 @@ nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head, */ static void nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, - struct nfs_page *old_head) + struct nfs_page *old_head, + struct inode *inode) { while (destroy_list) { struct nfs_page *subreq = destroy_list; @@ -389,33 +409,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, WARN_ON_ONCE(old_head != subreq->wb_head); /* make sure old group is not used */ - subreq->wb_head = subreq; subreq->wb_this_page = subreq; - /* subreq is now totally disconnected from page group or any - * write / commit lists. last chance to wake any waiters */ - nfs_unlock_request(subreq); + clear_bit(PG_REMOVE, &subreq->wb_flags); - if (!test_bit(PG_TEARDOWN, &subreq->wb_flags)) { - /* release ref on old head request */ - nfs_release_request(old_head); + /* Note: races with nfs_page_group_destroy() */ + if (!kref_read(&subreq->wb_kref)) { + /* Check if we raced with nfs_page_group_destroy() */ + if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) + nfs_free_request(subreq); + continue; + } - nfs_page_group_clear_bits(subreq); + subreq->wb_head = subreq; - /* release the PG_INODE_REF reference */ - if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) - nfs_release_request(subreq); - else - WARN_ON_ONCE(1); - } else { - WARN_ON_ONCE(test_bit(PG_CLEAN, &subreq->wb_flags)); - /* zombie requests have already released the last - * reference and were waiting on the rest of the - * group to complete. Since it's no longer part of a - * group, simply free the request */ - nfs_page_group_clear_bits(subreq); - nfs_free_request(subreq); + if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) { + nfs_release_request(subreq); + atomic_long_dec(&NFS_I(inode)->nrequests); } + + /* subreq is now totally disconnected from page group or any + * write / commit lists. last chance to wake any waiters */ + nfs_unlock_and_release_request(subreq); } } @@ -425,7 +440,6 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, * operations for this page. * * @page - the page used to lookup the "page group" of nfs_page structures - * @nonblock - if true, don't block waiting for request locks * * This function joins all sub requests to the head request by first * locking all requests in the group, cancelling any pending operations @@ -439,7 +453,7 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, * error was encountered. */ static struct nfs_page * -nfs_lock_and_join_requests(struct page *page, bool nonblock) +nfs_lock_and_join_requests(struct page *page) { struct inode *inode = page_file_mapping(page)->host; struct nfs_page *head, *subreq; @@ -448,43 +462,63 @@ nfs_lock_and_join_requests(struct page *page, bool nonblock) int ret; try_again: - total_bytes = 0; - - WARN_ON_ONCE(destroy_list); - - spin_lock(&inode->i_lock); - /* * A reference is taken only on the head request which acts as a * reference to the whole page group - the group will not be destroyed * until the head reference is released. */ - head = nfs_page_find_head_request_locked(NFS_I(inode), page); - - if (!head) { - spin_unlock(&inode->i_lock); + head = nfs_page_find_head_request(page); + if (!head) return NULL; - } - /* holding inode lock, so always make a non-blocking call to try the - * page group lock */ - ret = nfs_page_group_lock(head, true); - if (ret < 0) { - spin_unlock(&inode->i_lock); + /* lock the page head first in order to avoid an ABBA inefficiency */ + if (!nfs_lock_request(head)) { + ret = nfs_wait_on_request(head); + nfs_release_request(head); + if (ret < 0) + return ERR_PTR(ret); + goto try_again; + } - if (!nonblock && ret == -EAGAIN) { - nfs_page_group_lock_wait(head); - nfs_release_request(head); - goto try_again; - } + /* Ensure that nobody removed the request before we locked it */ + if (head != nfs_page_private_request(page) && !PageSwapCache(page)) { + nfs_unlock_and_release_request(head); + goto try_again; + } - nfs_release_request(head); + ret = nfs_page_group_lock(head); + if (ret < 0) { + nfs_unlock_and_release_request(head); return ERR_PTR(ret); } /* lock each request in the page group */ - subreq = head; - do { + total_bytes = head->wb_bytes; + for (subreq = head->wb_this_page; subreq != head; + subreq = subreq->wb_this_page) { + + if (!kref_get_unless_zero(&subreq->wb_kref)) { + if (subreq->wb_offset == head->wb_offset + total_bytes) + total_bytes += subreq->wb_bytes; + continue; + } + + while (!nfs_lock_request(subreq)) { + /* + * Unlock page to allow nfs_page_group_sync_on_bit() + * to succeed + */ + nfs_page_group_unlock(head); + ret = nfs_wait_on_request(subreq); + if (!ret) + ret = nfs_page_group_lock(head); + if (ret < 0) { + nfs_unroll_locks(inode, head, subreq); + nfs_release_request(subreq); + nfs_unlock_and_release_request(head); + return ERR_PTR(ret); + } + } /* * Subrequests are always contiguous, non overlapping * and in order - but may be repeated (mirrored writes). @@ -496,24 +530,12 @@ try_again: ((subreq->wb_offset + subreq->wb_bytes) > (head->wb_offset + total_bytes)))) { nfs_page_group_unlock(head); - spin_unlock(&inode->i_lock); + nfs_unroll_locks(inode, head, subreq); + nfs_unlock_and_release_request(subreq); + nfs_unlock_and_release_request(head); return ERR_PTR(-EIO); } - - if (!nfs_lock_request(subreq)) { - /* releases page group bit lock and - * inode spin lock and all references */ - ret = nfs_unroll_locks_and_wait(inode, head, - subreq, nonblock); - - if (ret == 0) - goto try_again; - - return ERR_PTR(ret); - } - - subreq = subreq->wb_this_page; - } while (subreq != head); + } /* Now that all requests are locked, make sure they aren't on any list. * Commit list removal accounting is done after locks are dropped */ @@ -534,34 +556,30 @@ try_again: head->wb_bytes = total_bytes; } - /* - * prepare head request to be added to new pgio descriptor - */ - nfs_page_group_clear_bits(head); - - /* - * some part of the group was still on the inode list - otherwise - * the group wouldn't be involved in async write. - * grab a reference for the head request, iff it needs one. - */ - if (!test_and_set_bit(PG_INODE_REF, &head->wb_flags)) + /* Postpone destruction of this request */ + if (test_and_clear_bit(PG_REMOVE, &head->wb_flags)) { + set_bit(PG_INODE_REF, &head->wb_flags); kref_get(&head->wb_kref); + atomic_long_inc(&NFS_I(inode)->nrequests); + } nfs_page_group_unlock(head); - /* drop lock to clean uprequests on destroy list */ - spin_unlock(&inode->i_lock); + nfs_destroy_unlinked_subrequests(destroy_list, head, inode); - nfs_destroy_unlinked_subrequests(destroy_list, head); + /* Did we lose a race with nfs_inode_remove_request()? */ + if (!(PagePrivate(page) || PageSwapCache(page))) { + nfs_unlock_and_release_request(head); + return NULL; + } - /* still holds ref on head from nfs_page_find_head_request_locked + /* still holds ref on head from nfs_page_find_head_request * and still has lock on head from lock loop */ return head; } static void nfs_write_error_remove_page(struct nfs_page *req) { - nfs_unlock_request(req); nfs_end_page_writeback(req); generic_error_remove_page(page_file_mapping(req->wb_page), req->wb_page); @@ -585,12 +603,12 @@ nfs_error_is_fatal_on_server(int err) * May return an error if the user signalled nfs_wait_on_request(). */ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, - struct page *page, bool nonblock) + struct page *page) { struct nfs_page *req; int ret = 0; - req = nfs_lock_and_join_requests(page, nonblock); + req = nfs_lock_and_join_requests(page); if (!req) goto out; ret = PTR_ERR(req); @@ -633,7 +651,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, int ret; nfs_pageio_cond_complete(pgio, page_index(page)); - ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); + ret = nfs_page_async_flush(pgio, page); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; @@ -681,18 +699,29 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control * return ret; } +static void nfs_io_completion_commit(void *inode) +{ + nfs_commit_inode(inode, 0); +} + int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct nfs_pageio_descriptor pgio; + struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS); int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); + if (ioc) + nfs_io_completion_init(ioc, nfs_io_completion_commit, inode); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false, &nfs_async_write_completion_ops); + pgio.pg_io_completion = ioc; err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); + nfs_io_completion_put(ioc); if (err < 0) goto out_err; @@ -709,6 +738,7 @@ out_err: */ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) { + struct address_space *mapping = page_file_mapping(req->wb_page); struct nfs_inode *nfsi = NFS_I(inode); WARN_ON_ONCE(req->wb_this_page != req); @@ -716,27 +746,30 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) /* Lock the request! */ nfs_lock_request(req); - spin_lock(&inode->i_lock); - if (!nfsi->nrequests && - NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) - inode->i_version++; /* * Swap-space should not get truncated. Hence no need to plug the race * with invalidate/truncate. */ + spin_lock(&mapping->private_lock); + if (!nfs_have_writebacks(inode) && + NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) { + spin_lock(&inode->i_lock); + inode->i_version++; + spin_unlock(&inode->i_lock); + } if (likely(!PageSwapCache(req->wb_page))) { set_bit(PG_MAPPED, &req->wb_flags); SetPagePrivate(req->wb_page); set_page_private(req->wb_page, (unsigned long)req); } - nfsi->nrequests++; + spin_unlock(&mapping->private_lock); + atomic_long_inc(&nfsi->nrequests); /* this a head request for a page group - mark it as having an * extra reference so sub groups can follow suit. * This flag also informs pgio layer when to bump nrequests when * adding subrequests. */ WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); kref_get(&req->wb_kref); - spin_unlock(&inode->i_lock); } /* @@ -744,25 +777,22 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) */ static void nfs_inode_remove_request(struct nfs_page *req) { - struct inode *inode = d_inode(req->wb_context->dentry); + struct address_space *mapping = page_file_mapping(req->wb_page); + struct inode *inode = mapping->host; struct nfs_inode *nfsi = NFS_I(inode); struct nfs_page *head; + atomic_long_dec(&nfsi->nrequests); if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { head = req->wb_head; - spin_lock(&inode->i_lock); + spin_lock(&mapping->private_lock); if (likely(head->wb_page && !PageSwapCache(head->wb_page))) { set_page_private(head->wb_page, 0); ClearPagePrivate(head->wb_page); clear_bit(PG_MAPPED, &head->wb_flags); } - nfsi->nrequests--; - spin_unlock(&inode->i_lock); - } else { - spin_lock(&inode->i_lock); - nfsi->nrequests--; - spin_unlock(&inode->i_lock); + spin_unlock(&mapping->private_lock); } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) @@ -818,7 +848,8 @@ nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, * number of outstanding requests requiring a commit as well as * the MM page stats. * - * The caller must hold cinfo->inode->i_lock, and the nfs_page lock. + * The caller must hold NFS_I(cinfo->inode)->commit_mutex, and the + * nfs_page lock. */ void nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, @@ -826,7 +857,7 @@ nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, { set_bit(PG_CLEAN, &req->wb_flags); nfs_list_add_request(req, dst); - cinfo->mds->ncommit++; + atomic_long_inc(&cinfo->mds->ncommit); } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked); @@ -846,9 +877,9 @@ EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked); void nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo) { - spin_lock(&cinfo->inode->i_lock); + mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo); - spin_unlock(&cinfo->inode->i_lock); + mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); if (req->wb_page) nfs_mark_page_unstable(req->wb_page, cinfo); } @@ -872,7 +903,7 @@ nfs_request_remove_commit_list(struct nfs_page *req, if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) return; nfs_list_remove_request(req); - cinfo->mds->ncommit--; + atomic_long_dec(&cinfo->mds->ncommit); } EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list); @@ -917,7 +948,7 @@ nfs_clear_page_commit(struct page *page) WB_RECLAIMABLE); } -/* Called holding inode (/cinfo) lock */ +/* Called holding the request lock on @req */ static void nfs_clear_request_commit(struct nfs_page *req) { @@ -926,9 +957,11 @@ nfs_clear_request_commit(struct nfs_page *req) struct nfs_commit_info cinfo; nfs_init_cinfo_from_inode(&cinfo, inode); + mutex_lock(&NFS_I(inode)->commit_mutex); if (!pnfs_clear_request_commit(req, &cinfo)) { nfs_request_remove_commit_list(req, &cinfo); } + mutex_unlock(&NFS_I(inode)->commit_mutex); nfs_clear_page_commit(req->wb_page); } } @@ -940,6 +973,11 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr) return hdr->verf.committed != NFS_FILE_SYNC; } +static void nfs_async_write_init(struct nfs_pgio_header *hdr) +{ + nfs_io_completion_get(hdr->io_completion); +} + static void nfs_write_completion(struct nfs_pgio_header *hdr) { struct nfs_commit_info cinfo; @@ -968,21 +1006,21 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) remove_req: nfs_inode_remove_request(req); next: - nfs_unlock_request(req); nfs_end_page_writeback(req); nfs_release_request(req); } out: + nfs_io_completion_put(hdr->io_completion); hdr->release(hdr); } unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { - return cinfo->mds->ncommit; + return atomic_long_read(&cinfo->mds->ncommit); } -/* cinfo->inode->i_lock held by caller */ +/* NFS_I(cinfo->inode)->commit_mutex held by caller */ int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_commit_info *cinfo, int max) @@ -990,20 +1028,37 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, struct nfs_page *req, *tmp; int ret = 0; +restart: list_for_each_entry_safe(req, tmp, src, wb_list) { - if (!nfs_lock_request(req)) - continue; kref_get(&req->wb_kref); - if (cond_resched_lock(&cinfo->inode->i_lock)) - list_safe_reset_next(req, tmp, wb_list); + if (!nfs_lock_request(req)) { + int status; + + /* Prevent deadlock with nfs_lock_and_join_requests */ + if (!list_empty(dst)) { + nfs_release_request(req); + continue; + } + /* Ensure we make progress to prevent livelock */ + mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); + status = nfs_wait_on_request(req); + nfs_release_request(req); + mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); + if (status < 0) + break; + goto restart; + } nfs_request_remove_commit_list(req, cinfo); + clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); nfs_list_add_request(req, dst); ret++; if ((ret == max) && !cinfo->dreq) break; + cond_resched(); } return ret; } +EXPORT_SYMBOL_GPL(nfs_scan_commit_list); /* * nfs_scan_commit - Scan an inode for commit requests @@ -1020,15 +1075,17 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, { int ret = 0; - spin_lock(&cinfo->inode->i_lock); - if (cinfo->mds->ncommit > 0) { + if (!atomic_long_read(&cinfo->mds->ncommit)) + return 0; + mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); + if (atomic_long_read(&cinfo->mds->ncommit) > 0) { const int max = INT_MAX; ret = nfs_scan_commit_list(&cinfo->mds->list, dst, cinfo, max); ret += pnfs_scan_commit_lists(inode, cinfo, max - ret); } - spin_unlock(&cinfo->inode->i_lock); + mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); return ret; } @@ -1049,43 +1106,21 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, unsigned int end; int error; - if (!PagePrivate(page)) - return NULL; - end = offset + bytes; - spin_lock(&inode->i_lock); - - for (;;) { - req = nfs_page_find_head_request_locked(NFS_I(inode), page); - if (req == NULL) - goto out_unlock; - - /* should be handled by nfs_flush_incompatible */ - WARN_ON_ONCE(req->wb_head != req); - WARN_ON_ONCE(req->wb_this_page != req); - - rqend = req->wb_offset + req->wb_bytes; - /* - * Tell the caller to flush out the request if - * the offsets are non-contiguous. - * Note: nfs_flush_incompatible() will already - * have flushed out requests having wrong owners. - */ - if (offset > rqend - || end < req->wb_offset) - goto out_flushme; - if (nfs_lock_request(req)) - break; + req = nfs_lock_and_join_requests(page); + if (IS_ERR_OR_NULL(req)) + return req; - /* The request is locked, so wait and then retry */ - spin_unlock(&inode->i_lock); - error = nfs_wait_on_request(req); - nfs_release_request(req); - if (error != 0) - goto out_err; - spin_lock(&inode->i_lock); - } + rqend = req->wb_offset + req->wb_bytes; + /* + * Tell the caller to flush out the request if + * the offsets are non-contiguous. + * Note: nfs_flush_incompatible() will already + * have flushed out requests having wrong owners. + */ + if (offset > rqend || end < req->wb_offset) + goto out_flushme; /* Okay, the request matches. Update the region */ if (offset < req->wb_offset) { @@ -1096,17 +1131,17 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, req->wb_bytes = end - req->wb_offset; else req->wb_bytes = rqend - req->wb_offset; -out_unlock: - if (req) - nfs_clear_request_commit(req); - spin_unlock(&inode->i_lock); return req; out_flushme: - spin_unlock(&inode->i_lock); - nfs_release_request(req); + /* + * Note: we mark the request dirty here because + * nfs_lock_and_join_requests() cannot preserve + * commit flags, so we have to replay the write. + */ + nfs_mark_request_dirty(req); + nfs_unlock_and_release_request(req); error = nfs_wb_page(inode, page); -out_err: - return ERR_PTR(error); + return (error < 0) ? ERR_PTR(error) : NULL; } /* @@ -1171,8 +1206,6 @@ int nfs_flush_incompatible(struct file *file, struct page *page) l_ctx = req->wb_lock_context; do_flush = req->wb_page != page || !nfs_match_open_context(req->wb_context, ctx); - /* for now, flush if more than 1 request in page_group */ - do_flush |= req->wb_this_page != req; if (l_ctx && flctx && !(list_empty_careful(&flctx->flc_posix) && list_empty_careful(&flctx->flc_flock))) { @@ -1343,6 +1376,8 @@ static void nfs_initiate_write(struct nfs_pgio_header *hdr, task_setup_data->priority = priority; rpc_ops->write_setup(hdr, msg); + trace_nfs_initiate_write(hdr->inode, hdr->io_start, hdr->good_bytes, + hdr->args.stable); nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client, &task_setup_data->rpc_client, msg, hdr); @@ -1356,7 +1391,6 @@ static void nfs_redirty_request(struct nfs_page *req) { nfs_mark_request_dirty(req); set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags); - nfs_unlock_request(req); nfs_end_page_writeback(req); nfs_release_request(req); } @@ -1378,6 +1412,7 @@ static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) } static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { + .init_hdr = nfs_async_write_init, .error_cleanup = nfs_async_write_error, .completion = nfs_write_completion, .reschedule_io = nfs_async_write_reschedule_io, @@ -1395,7 +1430,7 @@ void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, pg_ops = server->pnfs_curr_ld->pg_write_ops; #endif nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops, - server->wsize, ioflags, GFP_NOIO); + server->wsize, ioflags); } EXPORT_SYMBOL_GPL(nfs_pageio_init_write); @@ -1500,7 +1535,10 @@ static int nfs_writeback_done(struct rpc_task *task, status = NFS_PROTO(inode)->write_done(task, hdr); if (status != 0) return status; + nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); + trace_nfs_writeback_done(inode, task->tk_status, + hdr->args.offset, hdr->res.verf); if (hdr->res.verf->committed < hdr->args.stable && task->tk_status >= 0) { @@ -1629,6 +1667,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, }; /* Set up the initial task struct. */ nfs_ops->commit_setup(data, &msg); + trace_nfs_initiate_commit(data); dprintk("NFS: initiated commit call\n"); @@ -1753,6 +1792,7 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) /* Call the NFS version-specific code */ NFS_PROTO(data->inode)->commit_done(task, data); + trace_nfs_commit_done(data); } static void nfs_commit_release_pages(struct nfs_commit_data *data) @@ -1877,14 +1917,14 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) int ret = 0; /* no commits means nothing needs to be done */ - if (!nfsi->commit_info.ncommit) + if (!atomic_long_read(&nfsi->commit_info.ncommit)) return ret; if (wbc->sync_mode == WB_SYNC_NONE) { /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1)) + if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)) goto out_mark_dirty; /* don't wait for the COMMIT response */ @@ -1958,7 +1998,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) /* blocking call to cancel all requests and join to a single (head) * request */ - req = nfs_lock_and_join_requests(page, false); + req = nfs_lock_and_join_requests(page); if (IS_ERR(req)) { ret = PTR_ERR(req); diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index fb5213afc854..c862c2489df0 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -219,6 +219,9 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, u8 *buf, *d, type, assoc; int error; + if (WARN_ON_ONCE(!blk_queue_scsi_passthrough(q))) + return -EINVAL; + buf = kzalloc(bufflen, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -229,7 +232,6 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev, goto out_free_buf; } req = scsi_req(rq); - scsi_req_init(rq); error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL); if (error) diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h index 4123551208d8..34075cee573a 100644 --- a/fs/nfsd/current_stateid.h +++ b/fs/nfsd/current_stateid.h @@ -8,21 +8,33 @@ extern void clear_current_stateid(struct nfsd4_compound_state *cstate); /* * functions to set current state id */ -extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *); -extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *); -extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *); -extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *); +extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); /* * functions to consume current state id */ -extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *); -extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *); -extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *); -extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *); -extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *); -extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *); -extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *); -extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *); +extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); +extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, + union nfsd4_op_u *); #endif /* _NFSD4_CURRENT_STATE_H */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index e71f11b1a180..3bc08c394a3f 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -486,7 +486,7 @@ secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; } #endif static inline int -uuid_parse(char **mesg, char *buf, unsigned char **puuid) +nfsd_uuid_parse(char **mesg, char *buf, unsigned char **puuid) { int len; @@ -586,7 +586,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) if (strcmp(buf, "fsloc") == 0) err = fsloc_parse(&mesg, buf, &exp.ex_fslocs); else if (strcmp(buf, "uuid") == 0) - err = uuid_parse(&mesg, buf, &exp.ex_uuid); + err = nfsd_uuid_parse(&mesg, buf, &exp.ex_uuid); else if (strcmp(buf, "secinfo") == 0) err = secinfo_parse(&mesg, buf, &exp); else diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 838f90f3f890..6276ec8608b0 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -19,7 +19,7 @@ * NULL call. */ static __be32 -nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsacld_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -27,9 +27,10 @@ nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) /* * Get the Access and/or Default ACL of a file. */ -static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp, - struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp) +static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct posix_acl *acl; struct inode *inode; svc_fh *fh; @@ -87,10 +88,10 @@ fail: /* * Set the Access and/or Default ACL of a file. */ -static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp, - struct nfsd3_setaclargs *argp, - struct nfsd_attrstat *resp) +static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; struct inode *inode; svc_fh *fh; __be32 nfserr = 0; @@ -141,9 +142,10 @@ out_errno: /* * Check file attributes */ -static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, - struct nfsd_fhandle *argp, struct nfsd_attrstat *resp) +static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); @@ -158,9 +160,10 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp, /* * Check file access */ -static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, - struct nfsd3_accessres *resp) +static __be32 nfsacld_proc_access(struct svc_rqst *rqstp) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct nfsd3_accessres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: ACCESS(2acl) %s 0x%x\n", @@ -179,9 +182,10 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg /* * XDR decode functions */ -static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclargs *argp) +static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; @@ -191,9 +195,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, } -static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_setaclargs *argp) +static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; unsigned int base; int n; @@ -217,18 +221,20 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, return (n > 0); } -static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_fhandle *argp) +static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; return xdr_argsize_check(rqstp, p); } -static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessargs *argp) +static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + p = nfs2svc_decode_fh(p, &argp->fh); if (!p) return 0; @@ -245,15 +251,15 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, * There must be an encoding function for void results so svc_process * will work properly. */ -static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } /* GETACL */ -static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct inode *inode; struct kvec *head = rqstp->rq_res.head; @@ -296,17 +302,19 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, return (n > 0); } -static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } /* ACCESS */ -static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessres *resp = rqstp->rq_resp; + p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat); *p++ = htonl(resp->access); return xdr_ressize_check(rqstp, p); @@ -315,27 +323,27 @@ static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; + fh_put(&resp->fh); posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); - return 1; } -static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } -static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +static void nfsaclsvc_release_access(struct svc_rqst *rqstp) { - fh_put(&resp->fh); - return 1; + struct nfsd3_accessres *resp = rqstp->rq_resp; + + fh_put(&resp->fh); } #define nfsaclsvc_decode_voidargs NULL @@ -345,24 +353,24 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsacld_proc_##name, \ - (kxdrproc_t) nfsaclsvc_decode_##argt##args, \ - (kxdrproc_t) nfsaclsvc_encode_##rest##res, \ - (kxdrproc_t) nfsaclsvc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } +#define PROC(name, argt, rest, relt, cache, respsize) \ +{ \ + .pc_func = nfsacld_proc_##name, \ + .pc_decode = nfsaclsvc_decode_##argt##args, \ + .pc_encode = nfsaclsvc_encode_##rest##res, \ + .pc_release = nfsaclsvc_release_##relt, \ + .pc_argsize = sizeof(struct nfsd3_##argt##args), \ + .pc_ressize = sizeof(struct nfsd3_##rest##res), \ + .pc_cachetype = cache, \ + .pc_xdrressize = respsize, \ +} #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ #define ACL (1+NFS_ACL_MAX_ENTRIES*3) /* Access Control List */ -static struct svc_procedure nfsd_acl_procedures2[] = { +static const struct svc_procedure nfsd_acl_procedures2[] = { PROC(null, void, void, void, RC_NOCACHE, ST), PROC(getacl, getacl, getacl, getacl, RC_NOCACHE, ST+1+2*(1+ACL)), PROC(setacl, setacl, attrstat, attrstat, RC_NOCACHE, ST+AT), @@ -370,10 +378,12 @@ static struct svc_procedure nfsd_acl_procedures2[] = { PROC(access, access, access, access, RC_NOCACHE, ST+AT+1), }; -struct svc_version nfsd_acl_version2 = { - .vs_vers = 2, - .vs_nproc = 5, - .vs_proc = nfsd_acl_procedures2, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; +const struct svc_version nfsd_acl_version2 = { + .vs_vers = 2, + .vs_nproc = 5, + .vs_proc = nfsd_acl_procedures2, + .vs_count = nfsd_acl_count2, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index dcb5f79076c0..01976529f042 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -18,7 +18,7 @@ * NULL call. */ static __be32 -nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd3_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -26,9 +26,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) /* * Get the Access and/or Default ACL of a file. */ -static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp, - struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp) +static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclargs *argp = rqstp->rq_argp; + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct posix_acl *acl; struct inode *inode; svc_fh *fh; @@ -80,10 +81,10 @@ fail: /* * Set the Access and/or Default ACL of a file. */ -static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp, - struct nfsd3_setaclargs *argp, - struct nfsd3_attrstat *resp) +static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) { + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; struct inode *inode; svc_fh *fh; __be32 nfserr = 0; @@ -123,9 +124,10 @@ out: /* * XDR decode functions */ -static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclargs *args) +static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclargs *args = rqstp->rq_argp; + p = nfs3svc_decode_fh(p, &args->fh); if (!p) return 0; @@ -135,9 +137,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p, } -static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_setaclargs *args) +static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_setaclargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; unsigned int base; int n; @@ -166,9 +168,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p, */ /* GETACL */ -static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh); @@ -211,9 +213,10 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p, } /* SETACL */ -static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh); return xdr_ressize_check(rqstp, p); @@ -222,13 +225,13 @@ static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_getaclres *resp) +static void nfs3svc_release_getacl(struct svc_rqst *rqstp) { + struct nfsd3_getaclres *resp = rqstp->rq_resp; + fh_put(&resp->fh); posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); - return 1; } #define nfs3svc_decode_voidargs NULL @@ -237,34 +240,36 @@ static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsd3_proc_##name, \ - (kxdrproc_t) nfs3svc_decode_##argt##args, \ - (kxdrproc_t) nfs3svc_encode_##rest##res, \ - (kxdrproc_t) nfs3svc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } +#define PROC(name, argt, rest, relt, cache, respsize) \ +{ \ + .pc_func = nfsd3_proc_##name, \ + .pc_decode = nfs3svc_decode_##argt##args, \ + .pc_encode = nfs3svc_encode_##rest##res, \ + .pc_release = nfs3svc_release_##relt, \ + .pc_argsize = sizeof(struct nfsd3_##argt##args), \ + .pc_ressize = sizeof(struct nfsd3_##rest##res), \ + .pc_cachetype = cache, \ + .pc_xdrressize = respsize, \ +} #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ #define ACL (1+NFS_ACL_MAX_ENTRIES*3) /* Access Control List */ -static struct svc_procedure nfsd_acl_procedures3[] = { +static const struct svc_procedure nfsd_acl_procedures3[] = { PROC(null, void, void, void, RC_NOCACHE, ST), PROC(getacl, getacl, getacl, getacl, RC_NOCACHE, ST+1+2*(1+ACL)), PROC(setacl, setacl, setacl, fhandle, RC_NOCACHE, ST+pAT), }; -struct svc_version nfsd_acl_version3 = { - .vs_vers = 3, - .vs_nproc = 3, - .vs_proc = nfsd_acl_procedures3, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; +const struct svc_version nfsd_acl_version3 = { + .vs_vers = 3, + .vs_nproc = 3, + .vs_proc = nfsd_acl_procedures3, + .vs_count = nfsd_acl_count3, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 045c9081eabe..2cb56a0d6625 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -31,7 +31,7 @@ static int nfs3_ftypes[] = { * NULL call. */ static __be32 -nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd3_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -40,9 +40,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) * Get a file's attributes */ static __be32 -nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR(3) %s\n", @@ -63,9 +64,10 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, * Set a file's attributes */ static __be32 -nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_setattr(struct svc_rqst *rqstp) { + struct nfsd3_sattrargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: SETATTR(3) %s\n", @@ -81,9 +83,10 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp, * Look up a path name component */ static __be32 -nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_lookup(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LOOKUP(3) %s %.*s\n", @@ -105,9 +108,10 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, * Check file access */ static __be32 -nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, - struct nfsd3_accessres *resp) +nfsd3_proc_access(struct svc_rqst *rqstp) { + struct nfsd3_accessargs *argp = rqstp->rq_argp; + struct nfsd3_accessres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: ACCESS(3) %s 0x%x\n", @@ -124,9 +128,10 @@ nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp, * Read a symlink. */ static __be32 -nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp, - struct nfsd3_readlinkres *resp) +nfsd3_proc_readlink(struct svc_rqst *rqstp) { + struct nfsd3_readlinkargs *argp = rqstp->rq_argp; + struct nfsd3_readlinkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh)); @@ -142,9 +147,10 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp, * Read a portion of a file. */ static __be32 -nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp, - struct nfsd3_readres *resp) +nfsd3_proc_read(struct svc_rqst *rqstp) { + struct nfsd3_readargs *argp = rqstp->rq_argp; + struct nfsd3_readres *resp = rqstp->rq_resp; __be32 nfserr; u32 max_blocksize = svc_max_payload(rqstp); unsigned long cnt = min(argp->count, max_blocksize); @@ -179,9 +185,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp, * Write data to a file */ static __be32 -nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, - struct nfsd3_writeres *resp) +nfsd3_proc_write(struct svc_rqst *rqstp) { + struct nfsd3_writeargs *argp = rqstp->rq_argp; + struct nfsd3_writeres *resp = rqstp->rq_resp; __be32 nfserr; unsigned long cnt = argp->len; @@ -206,9 +213,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp, * first reports about SunOS compatibility problems start to pour in... */ static __be32 -nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_create(struct svc_rqst *rqstp) { + struct nfsd3_createargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp, *newfhp = NULL; struct iattr *attr; __be32 nfserr; @@ -243,9 +251,10 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, * Make directory. This operation is not idempotent. */ static __be32 -nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_mkdir(struct svc_rqst *rqstp) { + struct nfsd3_createargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: MKDIR(3) %s %.*s\n", @@ -263,9 +272,10 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp, } static __be32 -nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_symlink(struct svc_rqst *rqstp) { + struct nfsd3_symlinkargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: SYMLINK(3) %s %.*s -> %.*s\n", @@ -284,9 +294,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp, * Make socket/fifo/device. */ static __be32 -nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp, - struct nfsd3_diropres *resp) +nfsd3_proc_mknod(struct svc_rqst *rqstp) { + struct nfsd3_mknodargs *argp = rqstp->rq_argp; + struct nfsd3_diropres *resp = rqstp->rq_resp; __be32 nfserr; int type; dev_t rdev = 0; @@ -321,9 +332,10 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp, * Remove file/fifo/socket etc. */ static __be32 -nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_remove(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: REMOVE(3) %s %.*s\n", @@ -342,9 +354,10 @@ nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, * Remove a directory */ static __be32 -nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, - struct nfsd3_attrstat *resp) +nfsd3_proc_rmdir(struct svc_rqst *rqstp) { + struct nfsd3_diropargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: RMDIR(3) %s %.*s\n", @@ -359,9 +372,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp, } static __be32 -nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp, - struct nfsd3_renameres *resp) +nfsd3_proc_rename(struct svc_rqst *rqstp) { + struct nfsd3_renameargs *argp = rqstp->rq_argp; + struct nfsd3_renameres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: RENAME(3) %s %.*s ->\n", @@ -381,9 +395,10 @@ nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp, } static __be32 -nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp, - struct nfsd3_linkres *resp) +nfsd3_proc_link(struct svc_rqst *rqstp) { + struct nfsd3_linkargs *argp = rqstp->rq_argp; + struct nfsd3_linkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LINK(3) %s ->\n", @@ -404,9 +419,10 @@ nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp, * Read a portion of a directory. */ static __be32 -nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, - struct nfsd3_readdirres *resp) +nfsd3_proc_readdir(struct svc_rqst *rqstp) { + struct nfsd3_readdirargs *argp = rqstp->rq_argp; + struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; int count; @@ -440,9 +456,10 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, * For now, we choose to ignore the dircount parameter. */ static __be32 -nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, - struct nfsd3_readdirres *resp) +nfsd3_proc_readdirplus(struct svc_rqst *rqstp) { + struct nfsd3_readdirargs *argp = rqstp->rq_argp; + struct nfsd3_readdirres *resp = rqstp->rq_resp; __be32 nfserr; int count = 0; loff_t offset; @@ -507,9 +524,10 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, * Get file system stats */ static __be32 -nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_fsstatres *resp) +nfsd3_proc_fsstat(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_fsstatres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: FSSTAT(3) %s\n", @@ -524,9 +542,10 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Get file system info */ static __be32 -nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_fsinfores *resp) +nfsd3_proc_fsinfo(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_fsinfores *resp = rqstp->rq_resp; __be32 nfserr; u32 max_blocksize = svc_max_payload(rqstp); @@ -567,9 +586,10 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Get pathconf info for the specified file */ static __be32 -nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd3_pathconfres *resp) +nfsd3_proc_pathconf(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd3_pathconfres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: PATHCONF(3) %s\n", @@ -610,9 +630,10 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, * Commit a file (range) to stable storage. */ static __be32 -nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp, - struct nfsd3_commitres *resp) +nfsd3_proc_commit(struct svc_rqst *rqstp) { + struct nfsd3_commitargs *argp = rqstp->rq_argp; + struct nfsd3_commitres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: COMMIT(3) %s %u@%Lu\n", @@ -647,233 +668,221 @@ nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp, #define nfsd3_voidres nfsd3_voidargs struct nfsd3_voidargs { int dummy; }; -#define PROC(name, argt, rest, relt, cache, respsize) \ - { (svc_procfunc) nfsd3_proc_##name, \ - (kxdrproc_t) nfs3svc_decode_##argt##args, \ - (kxdrproc_t) nfs3svc_encode_##rest##res, \ - (kxdrproc_t) nfs3svc_release_##relt, \ - sizeof(struct nfsd3_##argt##args), \ - sizeof(struct nfsd3_##rest##res), \ - 0, \ - cache, \ - respsize, \ - } - #define ST 1 /* status*/ #define FH 17 /* filehandle with length */ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ #define WC (7+pAT) /* WCC attributes */ -static struct svc_procedure nfsd_procedures3[22] = { +static const struct svc_procedure nfsd_procedures3[22] = { [NFS3PROC_NULL] = { - .pc_func = (svc_procfunc) nfsd3_proc_null, - .pc_encode = (kxdrproc_t) nfs3svc_encode_voidres, + .pc_func = nfsd3_proc_null, + .pc_encode = nfs3svc_encode_voidres, .pc_argsize = sizeof(struct nfsd3_voidargs), .pc_ressize = sizeof(struct nfsd3_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, }, [NFS3PROC_GETATTR] = { - .pc_func = (svc_procfunc) nfsd3_proc_getattr, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_getattr, + .pc_decode = nfs3svc_decode_fhandleargs, + .pc_encode = nfs3svc_encode_attrstatres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_attrstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, }, [NFS3PROC_SETATTR] = { - .pc_func = (svc_procfunc) nfsd3_proc_setattr, - .pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_setattr, + .pc_decode = nfs3svc_decode_sattrargs, + .pc_encode = nfs3svc_encode_wccstatres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_sattrargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, }, [NFS3PROC_LOOKUP] = { - .pc_func = (svc_procfunc) nfsd3_proc_lookup, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_diropres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_lookup, + .pc_decode = nfs3svc_decode_diropargs, + .pc_encode = nfs3svc_encode_diropres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+pAT+pAT, }, [NFS3PROC_ACCESS] = { - .pc_func = (svc_procfunc) nfsd3_proc_access, - .pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_accessres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_access, + .pc_decode = nfs3svc_decode_accessargs, + .pc_encode = nfs3svc_encode_accessres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_accessargs), .pc_ressize = sizeof(struct nfsd3_accessres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1, }, [NFS3PROC_READLINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_readlink, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_readlink, + .pc_decode = nfs3svc_decode_readlinkargs, + .pc_encode = nfs3svc_encode_readlinkres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readlinkargs), .pc_ressize = sizeof(struct nfsd3_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4, }, [NFS3PROC_READ] = { - .pc_func = (svc_procfunc) nfsd3_proc_read, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_read, + .pc_decode = nfs3svc_decode_readargs, + .pc_encode = nfs3svc_encode_readres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readargs), .pc_ressize = sizeof(struct nfsd3_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4, }, [NFS3PROC_WRITE] = { - .pc_func = (svc_procfunc) nfsd3_proc_write, - .pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_writeres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_write, + .pc_decode = nfs3svc_decode_writeargs, + .pc_encode = nfs3svc_encode_writeres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_writeargs), .pc_ressize = sizeof(struct nfsd3_writeres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+4, }, [NFS3PROC_CREATE] = { - .pc_func = (svc_procfunc) nfsd3_proc_create, - .pc_decode = (kxdrproc_t) nfs3svc_decode_createargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_create, + .pc_decode = nfs3svc_decode_createargs, + .pc_encode = nfs3svc_encode_createres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_createargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_MKDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_mkdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_mkdir, + .pc_decode = nfs3svc_decode_mkdirargs, + .pc_encode = nfs3svc_encode_createres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mkdirargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_SYMLINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_symlink, - .pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_symlink, + .pc_decode = nfs3svc_decode_symlinkargs, + .pc_encode = nfs3svc_encode_createres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_symlinkargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_MKNOD] = { - .pc_func = (svc_procfunc) nfsd3_proc_mknod, - .pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_createres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_mknod, + .pc_decode = nfs3svc_decode_mknodargs, + .pc_encode = nfs3svc_encode_createres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_mknodargs), .pc_ressize = sizeof(struct nfsd3_createres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+(1+FH+pAT)+WC, }, [NFS3PROC_REMOVE] = { - .pc_func = (svc_procfunc) nfsd3_proc_remove, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_remove, + .pc_decode = nfs3svc_decode_diropargs, + .pc_encode = nfs3svc_encode_wccstatres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, }, [NFS3PROC_RMDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_rmdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_rmdir, + .pc_decode = nfs3svc_decode_diropargs, + .pc_encode = nfs3svc_encode_wccstatres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_diropargs), .pc_ressize = sizeof(struct nfsd3_wccstatres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC, }, [NFS3PROC_RENAME] = { - .pc_func = (svc_procfunc) nfsd3_proc_rename, - .pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_renameres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_rename, + .pc_decode = nfs3svc_decode_renameargs, + .pc_encode = nfs3svc_encode_renameres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_renameargs), .pc_ressize = sizeof(struct nfsd3_renameres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+WC+WC, }, [NFS3PROC_LINK] = { - .pc_func = (svc_procfunc) nfsd3_proc_link, - .pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_linkres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle2, + .pc_func = nfsd3_proc_link, + .pc_decode = nfs3svc_decode_linkargs, + .pc_encode = nfs3svc_encode_linkres, + .pc_release = nfs3svc_release_fhandle2, .pc_argsize = sizeof(struct nfsd3_linkargs), .pc_ressize = sizeof(struct nfsd3_linkres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+pAT+WC, }, [NFS3PROC_READDIR] = { - .pc_func = (svc_procfunc) nfsd3_proc_readdir, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_readdir, + .pc_decode = nfs3svc_decode_readdirargs, + .pc_encode = nfs3svc_encode_readdirres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, }, [NFS3PROC_READDIRPLUS] = { - .pc_func = (svc_procfunc) nfsd3_proc_readdirplus, - .pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_readdirplus, + .pc_decode = nfs3svc_decode_readdirplusargs, + .pc_encode = nfs3svc_encode_readdirres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_readdirplusargs), .pc_ressize = sizeof(struct nfsd3_readdirres), .pc_cachetype = RC_NOCACHE, }, [NFS3PROC_FSSTAT] = { - .pc_func = (svc_procfunc) nfsd3_proc_fsstat, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres, + .pc_func = nfsd3_proc_fsstat, + .pc_decode = nfs3svc_decode_fhandleargs, + .pc_encode = nfs3svc_encode_fsstatres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsstatres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+2*6+1, }, [NFS3PROC_FSINFO] = { - .pc_func = (svc_procfunc) nfsd3_proc_fsinfo, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores, + .pc_func = nfsd3_proc_fsinfo, + .pc_decode = nfs3svc_decode_fhandleargs, + .pc_encode = nfs3svc_encode_fsinfores, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_fsinfores), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+12, }, [NFS3PROC_PATHCONF] = { - .pc_func = (svc_procfunc) nfsd3_proc_pathconf, - .pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres, + .pc_func = nfsd3_proc_pathconf, + .pc_decode = nfs3svc_decode_fhandleargs, + .pc_encode = nfs3svc_encode_pathconfres, .pc_argsize = sizeof(struct nfsd3_fhandleargs), .pc_ressize = sizeof(struct nfsd3_pathconfres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+pAT+6, }, [NFS3PROC_COMMIT] = { - .pc_func = (svc_procfunc) nfsd3_proc_commit, - .pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs, - .pc_encode = (kxdrproc_t) nfs3svc_encode_commitres, - .pc_release = (kxdrproc_t) nfs3svc_release_fhandle, + .pc_func = nfsd3_proc_commit, + .pc_decode = nfs3svc_decode_commitargs, + .pc_encode = nfs3svc_encode_commitres, + .pc_release = nfs3svc_release_fhandle, .pc_argsize = sizeof(struct nfsd3_commitargs), .pc_ressize = sizeof(struct nfsd3_commitres), .pc_cachetype = RC_NOCACHE, @@ -881,10 +890,12 @@ static struct svc_procedure nfsd_procedures3[22] = { }, }; -struct svc_version nfsd_version3 = { - .vs_vers = 3, - .vs_nproc = 22, - .vs_proc = nfsd_procedures3, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS3_SVC_XDRSIZE, +static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; +const struct svc_version nfsd_version3 = { + .vs_vers = 3, + .vs_nproc = 22, + .vs_proc = nfsd_procedures3, + .vs_dispatch = nfsd_dispatch, + .vs_count = nfsd_count3, + .vs_xdrsize = NFS3_SVC_XDRSIZE, }; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 452334694a5d..bf444b664011 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -260,7 +260,7 @@ void fill_post_wcc(struct svc_fh *fhp) printk("nfsd: inode locked twice during operation.\n"); err = fh_getattr(fhp, &fhp->fh_post_attr); - fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version; + fhp->fh_post_change = nfsd4_change_attribute(d_inode(fhp->fh_dentry)); if (err) { fhp->fh_post_saved = false; /* Grab the ctime anyway - set_change_info might use it */ @@ -273,8 +273,10 @@ void fill_post_wcc(struct svc_fh *fhp) * XDR decode functions */ int -nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) +nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -282,9 +284,10 @@ nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *a } int -nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_sattrargs *args) +nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_sattrargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -300,9 +303,10 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropargs *args) +nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -311,9 +315,10 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessargs *args) +nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -323,9 +328,9 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readargs *args) +nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readargs *args = rqstp->rq_argp; unsigned int len; int v; u32 max_blocksize = svc_max_payload(rqstp); @@ -353,9 +358,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_writeargs *args) +nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_writeargs *args = rqstp->rq_argp; unsigned int len, v, hdr, dlen; u32 max_blocksize = svc_max_payload(rqstp); struct kvec *head = rqstp->rq_arg.head; @@ -413,9 +418,10 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_createargs *args) +nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_createargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -435,10 +441,12 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, return xdr_argsize_check(rqstp, p); } + int -nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_createargs *args) +nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_createargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -448,9 +456,9 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_symlinkargs *args) +nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_symlinkargs *args = rqstp->rq_argp; unsigned int len, avail; char *old, *new; struct kvec *vec; @@ -500,9 +508,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_mknodargs *args) +nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_mknodargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -522,9 +531,10 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_renameargs *args) +nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_renameargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_fh(p, &args->tfh)) @@ -535,9 +545,10 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readlinkargs *args) +nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readlinkargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -547,9 +558,10 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_linkargs *args) +nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_linkargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_fh(p, &args->tfh)) || !(p = decode_filename(p, &args->tname, &args->tlen))) @@ -559,9 +571,9 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirargs *args) +nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirargs *args = rqstp->rq_argp; p = decode_fh(p, &args->fh); if (!p) return 0; @@ -576,9 +588,9 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirargs *args) +nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirargs *args = rqstp->rq_argp; int len; u32 max_blocksize = svc_max_payload(rqstp); @@ -602,9 +614,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, } int -nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_commitargs *args) +nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_commitargs *args = rqstp->rq_argp; p = decode_fh(p, &args->fh); if (!p) return 0; @@ -622,16 +634,17 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p, * will work properly. */ int -nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } /* GETATTR */ int -nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + if (resp->status == 0) { lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime); @@ -642,18 +655,20 @@ nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, /* SETATTR, REMOVE, RMDIR */ int -nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + p = encode_wcc_data(rqstp, p, &resp->fh); return xdr_ressize_check(rqstp, p); } /* LOOKUP */ int -nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropres *resp) +nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropres *resp = rqstp->rq_resp; + if (resp->status == 0) { p = encode_fh(p, &resp->fh); p = encode_post_op_attr(rqstp, p, &resp->fh); @@ -664,9 +679,10 @@ nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, /* ACCESS */ int -nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_accessres *resp) +nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_accessres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) *p++ = htonl(resp->access); @@ -675,9 +691,10 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p, /* READLINK */ int -nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readlinkres *resp) +nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readlinkres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->len); @@ -696,9 +713,10 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, /* READ */ int -nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readres *resp) +nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { *p++ = htonl(resp->count); @@ -720,9 +738,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p, /* WRITE */ int -nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_writeres *resp) +nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_writeres *resp = rqstp->rq_resp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); p = encode_wcc_data(rqstp, p, &resp->fh); @@ -737,9 +755,10 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p, /* CREATE, MKDIR, SYMLINK, MKNOD */ int -nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_diropres *resp) +nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_diropres *resp = rqstp->rq_resp; + if (resp->status == 0) { *p++ = xdr_one; p = encode_fh(p, &resp->fh); @@ -751,9 +770,10 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p, /* RENAME */ int -nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_renameres *resp) +nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_renameres *resp = rqstp->rq_resp; + p = encode_wcc_data(rqstp, p, &resp->ffh); p = encode_wcc_data(rqstp, p, &resp->tfh); return xdr_ressize_check(rqstp, p); @@ -761,9 +781,10 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p, /* LINK */ int -nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_linkres *resp) +nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_linkres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); p = encode_wcc_data(rqstp, p, &resp->tfh); return xdr_ressize_check(rqstp, p); @@ -771,9 +792,10 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p, /* READDIR */ int -nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_readdirres *resp) +nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_readdirres *resp = rqstp->rq_resp; + p = encode_post_op_attr(rqstp, p, &resp->fh); if (resp->status == 0) { @@ -1021,9 +1043,9 @@ nfs3svc_encode_entry_plus(void *cd, const char *name, /* FSSTAT */ int -nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fsstatres *resp) +nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_fsstatres *resp = rqstp->rq_resp; struct kstatfs *s = &resp->stats; u64 bs = s->f_bsize; @@ -1043,9 +1065,10 @@ nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p, /* FSINFO */ int -nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fsinfores *resp) +nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_fsinfores *resp = rqstp->rq_resp; + *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { @@ -1067,9 +1090,10 @@ nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p, /* PATHCONF */ int -nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_pathconfres *resp) +nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_pathconfres *resp = rqstp->rq_resp; + *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { @@ -1086,9 +1110,9 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p, /* COMMIT */ int -nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_commitres *resp) +nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd3_commitres *resp = rqstp->rq_resp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); p = encode_wcc_data(rqstp, p, &resp->fh); @@ -1103,19 +1127,19 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p, /* * XDR release functions */ -int -nfs3svc_release_fhandle(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_attrstat *resp) +void +nfs3svc_release_fhandle(struct svc_rqst *rqstp) { + struct nfsd3_attrstat *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } -int -nfs3svc_release_fhandle2(struct svc_rqst *rqstp, __be32 *p, - struct nfsd3_fhandle_pair *resp) +void +nfs3svc_release_fhandle2(struct svc_rqst *rqstp) { + struct nfsd3_fhandle_pair *resp = rqstp->rq_resp; + fh_put(&resp->fh1); fh_put(&resp->fh2); - return 1; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 0274db6e65d0..49b0a9e7ff18 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -468,7 +468,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr, * NB: Without this zero space reservation, callbacks over krb5p fail */ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, - void *__unused) + const void *__unused) { xdr_reserve_space(xdr, 0); } @@ -477,8 +477,9 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, * 20.2. Operation 4: CB_RECALL - Recall a Delegation */ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfs4_delegation *dp = cb_to_delegation(cb); struct nfs4_cb_compound_hdr hdr = { .ident = cb->cb_clp->cl_cb_ident, @@ -512,8 +513,9 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr, */ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -585,8 +587,9 @@ static void encode_cb_layout4args(struct xdr_stream *xdr, static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfs4_layout_stateid *ls = container_of(cb, struct nfs4_layout_stateid, ls_recall); struct nfs4_cb_compound_hdr hdr = { @@ -602,8 +605,9 @@ static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req, static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -631,8 +635,9 @@ static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfsd4_callback *cb) + const void *data) { + const struct nfsd4_callback *cb = data; const struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner; @@ -659,8 +664,9 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req, static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfsd4_callback *cb) + void *data) { + struct nfsd4_callback *cb = data; struct nfs4_cb_compound_hdr hdr; int status; @@ -682,15 +688,15 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp, #define PROC(proc, call, argtype, restype) \ [NFSPROC4_CLNT_##proc] = { \ .p_proc = NFSPROC4_CB_##call, \ - .p_encode = (kxdreproc_t)nfs4_xdr_enc_##argtype, \ - .p_decode = (kxdrdproc_t)nfs4_xdr_dec_##restype, \ + .p_encode = nfs4_xdr_enc_##argtype, \ + .p_decode = nfs4_xdr_dec_##restype, \ .p_arglen = NFS4_enc_##argtype##_sz, \ .p_replen = NFS4_dec_##restype##_sz, \ .p_statidx = NFSPROC4_CB_##call, \ .p_name = #proc, \ } -static struct rpc_procinfo nfs4_cb_procedures[] = { +static const struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NULL, NULL, cb_null, cb_null), PROC(CB_RECALL, COMPOUND, cb_recall, cb_recall), #ifdef CONFIG_NFSD_PNFS @@ -699,7 +705,8 @@ static struct rpc_procinfo nfs4_cb_procedures[] = { PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), }; -static struct rpc_version nfs_cb_version4 = { +static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; +static const struct rpc_version nfs_cb_version4 = { /* * Note on the callback rpc program version number: despite language in rfc * 5661 section 18.36.3 requiring servers to use 4 in this field, the @@ -709,11 +716,12 @@ static struct rpc_version nfs_cb_version4 = { */ .number = 1, .nrprocs = ARRAY_SIZE(nfs4_cb_procedures), - .procs = nfs4_cb_procedures + .procs = nfs4_cb_procedures, + .counts = nfs4_cb_counts, }; -static const struct rpc_version *nfs_cb_version[] = { - &nfs_cb_version4, +static const struct rpc_version *nfs_cb_version[2] = { + [1] = &nfs_cb_version4, }; static const struct rpc_program cb_program; @@ -787,7 +795,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .saddress = (struct sockaddr *) &conn->cb_saddr, .timeout = &timeparms, .program = &cb_program, - .version = 0, + .version = 1, .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), }; struct rpc_clnt *client; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index dadb3bf305b2..8487486ec496 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -344,8 +344,9 @@ copy_clientid(clientid_t *clid, struct nfsd4_session *session) static __be32 nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_open *open) + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; struct svc_fh *resfh = NULL; struct net *net = SVC_NET(rqstp); @@ -467,14 +468,14 @@ out: */ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_op *op) { - struct nfsd4_open *open = (struct nfsd4_open *)&op->u; + struct nfsd4_open *open = &op->u.open; if (!seqid_mutating_err(ntohl(op->status))) return op->status; if (nfsd4_has_session(cstate)) return op->status; open->op_xdr_error = op->status; - return nfsd4_open(rqstp, cstate, open); + return nfsd4_open(rqstp, cstate, &op->u); } /* @@ -482,19 +483,21 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat */ static __be32 nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct svc_fh **getfh) + union nfsd4_op_u *u) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; - *getfh = &cstate->current_fh; + u->getfh = &cstate->current_fh; return nfs_ok; } static __be32 nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_putfh *putfh) + union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; + fh_put(&cstate->current_fh); cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen; memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval, @@ -504,7 +507,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { __be32 status; @@ -515,7 +518,7 @@ nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { if (!cstate->save_fh.fh_dentry) return nfserr_restorefh; @@ -530,7 +533,7 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; @@ -548,8 +551,10 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, */ static __be32 nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; + if (access->ac_req_access & ~NFS3_ACCESS_FULL) return nfserr_inval; @@ -574,8 +579,10 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net) static __be32 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_commit *commit) + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; + gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp)); return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset, commit->co_count); @@ -583,8 +590,9 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_create *create) + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct svc_fh resfh; __be32 status; dev_t rdev; @@ -670,8 +678,9 @@ out: static __be32 nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_getattr *getattr) + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; __be32 status; status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP); @@ -691,8 +700,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_link *link) + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; __be32 status = nfserr_nofilehandle; if (!cstate->save_fh.fh_dentry) @@ -723,24 +733,25 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh) static __be32 nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - void *arg) + union nfsd4_op_u *u) { return nfsd4_do_lookupp(rqstp, &cstate->current_fh); } static __be32 nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lookup *lookup) + union nfsd4_op_u *u) { return nfsd_lookup(rqstp, &cstate->current_fh, - lookup->lo_name, lookup->lo_len, + u->lookup.lo_name, u->lookup.lo_len, &cstate->current_fh); } static __be32 nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status; read->rd_filp = NULL; @@ -773,10 +784,19 @@ out: return status; } + +static void +nfsd4_read_release(union nfsd4_op_u *u) +{ + if (u->read.rd_filp) + fput(u->read.rd_filp); +} + static __be32 nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_readdir *readdir) + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; u64 cookie = readdir->rd_cookie; static const nfs4_verifier zeroverf; @@ -800,17 +820,18 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_readlink *readlink) + union nfsd4_op_u *u) { - readlink->rl_rqstp = rqstp; - readlink->rl_fhp = &cstate->current_fh; + u->readlink.rl_rqstp = rqstp; + u->readlink.rl_fhp = &cstate->current_fh; return nfs_ok; } static __be32 nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_remove *remove) + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; __be32 status; if (opens_in_grace(SVC_NET(rqstp))) @@ -826,8 +847,9 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_rename *rename) + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status = nfserr_nofilehandle; if (!cstate->save_fh.fh_dentry) @@ -847,8 +869,9 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct svc_export *exp; struct dentry *dentry; __be32 err; @@ -876,11 +899,11 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { __be32 err; - switch (sin->sin_style) { + switch (u->secinfo_no_name.sin_style) { case NFS4_SECINFO_STYLE4_CURRENT_FH: break; case NFS4_SECINFO_STYLE4_PARENT: @@ -892,15 +915,30 @@ nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstat return nfserr_inval; } - sin->sin_exp = exp_get(cstate->current_fh.fh_export); + u->secinfo_no_name.sin_exp = exp_get(cstate->current_fh.fh_export); fh_put(&cstate->current_fh); return nfs_ok; } +static void +nfsd4_secinfo_release(union nfsd4_op_u *u) +{ + if (u->secinfo.si_exp) + exp_put(u->secinfo.si_exp); +} + +static void +nfsd4_secinfo_no_name_release(union nfsd4_op_u *u) +{ + if (u->secinfo_no_name.sin_exp) + exp_put(u->secinfo_no_name.sin_exp); +} + static __be32 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_setattr *setattr) + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status = nfs_ok; int err; @@ -960,8 +998,9 @@ static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write) static __be32 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_write *write) + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; stateid_t *stateid = &write->wr_stateid; struct file *filp = NULL; __be32 status = nfs_ok; @@ -1034,8 +1073,9 @@ out_put_src: static __be32 nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_clone *clone) + union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; struct file *src, *dst; __be32 status; @@ -1055,8 +1095,9 @@ out: static __be32 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; struct file *src, *dst; __be32 status; ssize_t bytes; @@ -1111,23 +1152,24 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static __be32 nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { - return nfsd4_fallocate(rqstp, cstate, fallocate, 0); + return nfsd4_fallocate(rqstp, cstate, &u->allocate, 0); } static __be32 nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { - return nfsd4_fallocate(rqstp, cstate, fallocate, + return nfsd4_fallocate(rqstp, cstate, &u->deallocate, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE); } static __be32 nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; int whence; __be32 status; struct file *file; @@ -1232,21 +1274,21 @@ out_kfree: static __be32 nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_verify *verify) + union nfsd4_op_u *u) { __be32 status; - status = _nfsd4_verify(rqstp, cstate, verify); + status = _nfsd4_verify(rqstp, cstate, &u->verify); return status == nfserr_not_same ? nfs_ok : status; } static __be32 nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_verify *verify) + union nfsd4_op_u *u) { __be32 status; - status = _nfsd4_verify(rqstp, cstate, verify); + status = _nfsd4_verify(rqstp, cstate, &u->nverify); return status == nfserr_same ? nfs_ok : status; } @@ -1271,9 +1313,9 @@ nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type) static __be32 nfsd4_getdeviceinfo(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_getdeviceinfo *gdp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdp = &u->getdeviceinfo; const struct nfsd4_layout_ops *ops; struct nfsd4_deviceid_map *map; struct svc_export *exp; @@ -1315,11 +1357,17 @@ out: return nfserr; } +static void +nfsd4_getdeviceinfo_release(union nfsd4_op_u *u) +{ + kfree(u->getdeviceinfo.gd_device); +} + static __be32 nfsd4_layoutget(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutget *lgp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; struct nfs4_layout_stateid *ls; @@ -1395,11 +1443,17 @@ out: return nfserr; } +static void +nfsd4_layoutget_release(union nfsd4_op_u *u) +{ + kfree(u->layoutget.lg_content); +} + static __be32 nfsd4_layoutcommit(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutcommit *lcp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; const struct nfsd4_layout_seg *seg = &lcp->lc_seg; struct svc_fh *current_fh = &cstate->current_fh; const struct nfsd4_layout_ops *ops; @@ -1461,9 +1515,9 @@ out: static __be32 nfsd4_layoutreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_layoutreturn *lrp) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct svc_fh *current_fh = &cstate->current_fh; __be32 nfserr; @@ -1510,7 +1564,7 @@ out: * NULL call. */ static __be32 -nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd4_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -1521,53 +1575,7 @@ static inline void nfsd4_increment_op_stats(u32 opnum) nfsdstats.nfs4_opcount[opnum]++; } -typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *, - void *); -typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op); -typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *); -typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *); - -enum nfsd4_op_flags { - ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ - ALLOWED_ON_ABSENT_FS = 1 << 1, /* ops processed on absent fs */ - ALLOWED_AS_FIRST_OP = 1 << 2, /* ops reqired first in compound */ - /* For rfc 5661 section 2.6.3.1.1: */ - OP_HANDLES_WRONGSEC = 1 << 3, - OP_IS_PUTFH_LIKE = 1 << 4, - /* - * These are the ops whose result size we estimate before - * encoding, to avoid performing an op then not being able to - * respond or cache a response. This includes writes and setattrs - * as well as the operations usually called "nonidempotent": - */ - OP_MODIFIES_SOMETHING = 1 << 5, - /* - * Cache compounds containing these ops in the xid-based drc: - * We use the DRC for compounds containing non-idempotent - * operations, *except* those that are 4.1-specific (since - * sessions provide their own EOS), and except for stateful - * operations other than setclientid and setclientid_confirm - * (since sequence numbers provide EOS for open, lock, etc in - * the v4.0 case). - */ - OP_CACHEME = 1 << 6, - /* - * These are ops which clear current state id. - */ - OP_CLEAR_STATEID = 1 << 7, -}; - -struct nfsd4_operation { - nfsd4op_func op_func; - u32 op_flags; - char *op_name; - /* Try to get response size before operation */ - nfsd4op_rsize op_rsize_bop; - stateid_getter op_get_currentstateid; - stateid_setter op_set_currentstateid; -}; - -static struct nfsd4_operation nfsd4_ops[]; +static const struct nfsd4_operation nfsd4_ops[]; static const char *nfsd4_op_name(unsigned opnum); @@ -1604,7 +1612,7 @@ static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args) return nfs_ok; } -static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op) +const struct nfsd4_operation *OPDESC(struct nfsd4_op *op) { return &nfsd4_ops[op->opnum]; } @@ -1622,10 +1630,9 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp) struct nfsd4_compoundargs *argp = rqstp->rq_argp; struct nfsd4_op *this = &argp->ops[resp->opcnt - 1]; struct nfsd4_op *next = &argp->ops[resp->opcnt]; - struct nfsd4_operation *thisd; - struct nfsd4_operation *nextd; + const struct nfsd4_operation *thisd = OPDESC(this); + const struct nfsd4_operation *nextd; - thisd = OPDESC(this); /* * Most ops check wronsec on our own; only the putfh-like ops * have special rules. @@ -1673,12 +1680,11 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp, * COMPOUND call. */ static __be32 -nfsd4_proc_compound(struct svc_rqst *rqstp, - struct nfsd4_compoundargs *args, - struct nfsd4_compoundres *resp) +nfsd4_proc_compound(struct svc_rqst *rqstp) { + struct nfsd4_compoundargs *args = rqstp->rq_argp; + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfsd4_op *op; - struct nfsd4_operation *opdesc; struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; @@ -1731,15 +1737,13 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, goto encode_op; } - opdesc = OPDESC(op); - if (!current_fh->fh_dentry) { - if (!(opdesc->op_flags & ALLOWED_WITHOUT_FH)) { + if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { op->status = nfserr_nofilehandle; goto encode_op; } } else if (current_fh->fh_export->ex_fslocs.migrated && - !(opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) { + !(op->opdesc->op_flags & ALLOWED_ON_ABSENT_FS)) { op->status = nfserr_moved; goto encode_op; } @@ -1747,12 +1751,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, fh_clear_wcc(current_fh); /* If op is non-idempotent */ - if (opdesc->op_flags & OP_MODIFIES_SOMETHING) { + if (op->opdesc->op_flags & OP_MODIFIES_SOMETHING) { /* * Don't execute this op if we couldn't encode a * succesful reply: */ - u32 plen = opdesc->op_rsize_bop(rqstp, op); + u32 plen = op->opdesc->op_rsize_bop(rqstp, op); /* * Plus if there's another operation, make sure * we'll have space to at least encode an error: @@ -1765,9 +1769,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, if (op->status) goto encode_op; - if (opdesc->op_get_currentstateid) - opdesc->op_get_currentstateid(cstate, &op->u); - op->status = opdesc->op_func(rqstp, cstate, &op->u); + if (op->opdesc->op_get_currentstateid) + op->opdesc->op_get_currentstateid(cstate, &op->u); + op->status = op->opdesc->op_func(rqstp, cstate, &op->u); /* Only from SEQUENCE */ if (cstate->status == nfserr_replay_cache) { @@ -1776,10 +1780,10 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, goto out; } if (!op->status) { - if (opdesc->op_set_currentstateid) - opdesc->op_set_currentstateid(cstate, &op->u); + if (op->opdesc->op_set_currentstateid) + op->opdesc->op_set_currentstateid(cstate, &op->u); - if (opdesc->op_flags & OP_CLEAR_STATEID) + if (op->opdesc->op_flags & OP_CLEAR_STATEID) clear_current_stateid(cstate); if (need_wrongsec_check(rqstp)) @@ -2091,360 +2095,369 @@ static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op) return (op_encode_hdr_size + 3) * sizeof(__be32); } -static struct nfsd4_operation nfsd4_ops[] = { +static const struct nfsd4_operation nfsd4_ops[] = { [OP_ACCESS] = { - .op_func = (nfsd4op_func)nfsd4_access, + .op_func = nfsd4_access, .op_name = "OP_ACCESS", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_access_rsize, + .op_rsize_bop = nfsd4_access_rsize, }, [OP_CLOSE] = { - .op_func = (nfsd4op_func)nfsd4_close, + .op_func = nfsd4_close, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLOSE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid, - .op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid, + .op_rsize_bop = nfsd4_status_stateid_rsize, + .op_get_currentstateid = nfsd4_get_closestateid, + .op_set_currentstateid = nfsd4_set_closestateid, }, [OP_COMMIT] = { - .op_func = (nfsd4op_func)nfsd4_commit, + .op_func = nfsd4_commit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_COMMIT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_commit_rsize, + .op_rsize_bop = nfsd4_commit_rsize, }, [OP_CREATE] = { - .op_func = (nfsd4op_func)nfsd4_create, + .op_func = nfsd4_create, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID, .op_name = "OP_CREATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize, + .op_rsize_bop = nfsd4_create_rsize, }, [OP_DELEGRETURN] = { - .op_func = (nfsd4op_func)nfsd4_delegreturn, + .op_func = nfsd4_delegreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_DELEGRETURN", .op_rsize_bop = nfsd4_only_status_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid, + .op_get_currentstateid = nfsd4_get_delegreturnstateid, }, [OP_GETATTR] = { - .op_func = (nfsd4op_func)nfsd4_getattr, + .op_func = nfsd4_getattr, .op_flags = ALLOWED_ON_ABSENT_FS, .op_rsize_bop = nfsd4_getattr_rsize, .op_name = "OP_GETATTR", }, [OP_GETFH] = { - .op_func = (nfsd4op_func)nfsd4_getfh, + .op_func = nfsd4_getfh, .op_name = "OP_GETFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_getfh_rsize, + .op_rsize_bop = nfsd4_getfh_rsize, }, [OP_LINK] = { - .op_func = (nfsd4op_func)nfsd4_link, + .op_func = nfsd4_link, .op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_LINK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_link_rsize, + .op_rsize_bop = nfsd4_link_rsize, }, [OP_LOCK] = { - .op_func = (nfsd4op_func)nfsd4_lock, - .op_flags = OP_MODIFIES_SOMETHING, + .op_func = nfsd4_lock, + .op_flags = OP_MODIFIES_SOMETHING | + OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_LOCK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, - .op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid, + .op_rsize_bop = nfsd4_lock_rsize, + .op_set_currentstateid = nfsd4_set_lockstateid, }, [OP_LOCKT] = { - .op_func = (nfsd4op_func)nfsd4_lockt, + .op_func = nfsd4_lockt, + .op_flags = OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_LOCKT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize, + .op_rsize_bop = nfsd4_lock_rsize, }, [OP_LOCKU] = { - .op_func = (nfsd4op_func)nfsd4_locku, + .op_func = nfsd4_locku, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LOCKU", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid, + .op_rsize_bop = nfsd4_status_stateid_rsize, + .op_get_currentstateid = nfsd4_get_lockustateid, }, [OP_LOOKUP] = { - .op_func = (nfsd4op_func)nfsd4_lookup, + .op_func = nfsd4_lookup, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUP", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_LOOKUPP] = { - .op_func = (nfsd4op_func)nfsd4_lookupp, + .op_func = nfsd4_lookupp, .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID, .op_name = "OP_LOOKUPP", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_NVERIFY] = { - .op_func = (nfsd4op_func)nfsd4_nverify, + .op_func = nfsd4_nverify, .op_name = "OP_NVERIFY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_OPEN] = { - .op_func = (nfsd4op_func)nfsd4_open, + .op_func = nfsd4_open, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize, - .op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid, + .op_rsize_bop = nfsd4_open_rsize, + .op_set_currentstateid = nfsd4_set_openstateid, }, [OP_OPEN_CONFIRM] = { - .op_func = (nfsd4op_func)nfsd4_open_confirm, + .op_func = nfsd4_open_confirm, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_CONFIRM", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, + .op_rsize_bop = nfsd4_status_stateid_rsize, }, [OP_OPEN_DOWNGRADE] = { - .op_func = (nfsd4op_func)nfsd4_open_downgrade, + .op_func = nfsd4_open_downgrade, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN_DOWNGRADE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid, - .op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid, + .op_rsize_bop = nfsd4_status_stateid_rsize, + .op_get_currentstateid = nfsd4_get_opendowngradestateid, + .op_set_currentstateid = nfsd4_set_opendowngradestateid, }, [OP_PUTFH] = { - .op_func = (nfsd4op_func)nfsd4_putfh, + .op_func = nfsd4_putfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTPUBFH] = { - .op_func = (nfsd4op_func)nfsd4_putrootfh, + .op_func = nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTPUBFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_PUTROOTFH] = { - .op_func = (nfsd4op_func)nfsd4_putrootfh, + .op_func = nfsd4_putrootfh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID, .op_name = "OP_PUTROOTFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_READ] = { - .op_func = (nfsd4op_func)nfsd4_read, + .op_func = nfsd4_read, + .op_release = nfsd4_read_release, .op_name = "OP_READ", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid, + .op_rsize_bop = nfsd4_read_rsize, + .op_get_currentstateid = nfsd4_get_readstateid, }, [OP_READDIR] = { - .op_func = (nfsd4op_func)nfsd4_readdir, + .op_func = nfsd4_readdir, .op_name = "OP_READDIR", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize, + .op_rsize_bop = nfsd4_readdir_rsize, }, [OP_READLINK] = { - .op_func = (nfsd4op_func)nfsd4_readlink, + .op_func = nfsd4_readlink, .op_name = "OP_READLINK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_readlink_rsize, + .op_rsize_bop = nfsd4_readlink_rsize, }, [OP_REMOVE] = { - .op_func = (nfsd4op_func)nfsd4_remove, + .op_func = nfsd4_remove, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_REMOVE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_remove_rsize, + .op_rsize_bop = nfsd4_remove_rsize, }, [OP_RENAME] = { - .op_func = (nfsd4op_func)nfsd4_rename, + .op_func = nfsd4_rename, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_RENAME", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_rename_rsize, + .op_rsize_bop = nfsd4_rename_rsize, }, [OP_RENEW] = { - .op_func = (nfsd4op_func)nfsd4_renew, + .op_func = nfsd4_renew, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RENEW", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RESTOREFH] = { - .op_func = (nfsd4op_func)nfsd4_restorefh, + .op_func = nfsd4_restorefh, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING, .op_name = "OP_RESTOREFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SAVEFH] = { - .op_func = (nfsd4op_func)nfsd4_savefh, + .op_func = nfsd4_savefh, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_SAVEFH", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO] = { - .op_func = (nfsd4op_func)nfsd4_secinfo, + .op_func = nfsd4_secinfo, + .op_release = nfsd4_secinfo_release, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_secinfo_rsize, + .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_SETATTR] = { - .op_func = (nfsd4op_func)nfsd4_setattr, + .op_func = nfsd4_setattr, .op_name = "OP_SETATTR", - .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, - .op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid, + .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME + | OP_NONTRIVIAL_ERROR_ENCODE, + .op_rsize_bop = nfsd4_setattr_rsize, + .op_get_currentstateid = nfsd4_get_setattrstateid, }, [OP_SETCLIENTID] = { - .op_func = (nfsd4op_func)nfsd4_setclientid, + .op_func = nfsd4_setclientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS - | OP_MODIFIES_SOMETHING | OP_CACHEME, + | OP_MODIFIES_SOMETHING | OP_CACHEME + | OP_NONTRIVIAL_ERROR_ENCODE, .op_name = "OP_SETCLIENTID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_setclientid_rsize, + .op_rsize_bop = nfsd4_setclientid_rsize, }, [OP_SETCLIENTID_CONFIRM] = { - .op_func = (nfsd4op_func)nfsd4_setclientid_confirm, + .op_func = nfsd4_setclientid_confirm, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_SETCLIENTID_CONFIRM", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_VERIFY] = { - .op_func = (nfsd4op_func)nfsd4_verify, + .op_func = nfsd4_verify, .op_name = "OP_VERIFY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_WRITE] = { - .op_func = (nfsd4op_func)nfsd4_write, + .op_func = nfsd4_write, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_WRITE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize, - .op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid, + .op_rsize_bop = nfsd4_write_rsize, + .op_get_currentstateid = nfsd4_get_writestateid, }, [OP_RELEASE_LOCKOWNER] = { - .op_func = (nfsd4op_func)nfsd4_release_lockowner, + .op_func = nfsd4_release_lockowner, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING, .op_name = "OP_RELEASE_LOCKOWNER", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, /* NFSv4.1 operations */ [OP_EXCHANGE_ID] = { - .op_func = (nfsd4op_func)nfsd4_exchange_id, + .op_func = nfsd4_exchange_id, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_EXCHANGE_ID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize, + .op_rsize_bop = nfsd4_exchange_id_rsize, }, [OP_BACKCHANNEL_CTL] = { - .op_func = (nfsd4op_func)nfsd4_backchannel_ctl, + .op_func = nfsd4_backchannel_ctl, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_BACKCHANNEL_CTL", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_BIND_CONN_TO_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_bind_conn_to_session, + .op_func = nfsd4_bind_conn_to_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_BIND_CONN_TO_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_bind_conn_to_session_rsize, + .op_rsize_bop = nfsd4_bind_conn_to_session_rsize, }, [OP_CREATE_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_create_session, + .op_func = nfsd4_create_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_CREATE_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_create_session_rsize, + .op_rsize_bop = nfsd4_create_session_rsize, }, [OP_DESTROY_SESSION] = { - .op_func = (nfsd4op_func)nfsd4_destroy_session, + .op_func = nfsd4_destroy_session, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_SESSION", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SEQUENCE] = { - .op_func = (nfsd4op_func)nfsd4_sequence, + .op_func = nfsd4_sequence, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP, .op_name = "OP_SEQUENCE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_sequence_rsize, + .op_rsize_bop = nfsd4_sequence_rsize, }, [OP_DESTROY_CLIENTID] = { - .op_func = (nfsd4op_func)nfsd4_destroy_clientid, + .op_func = nfsd4_destroy_clientid, .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP | OP_MODIFIES_SOMETHING, .op_name = "OP_DESTROY_CLIENTID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_RECLAIM_COMPLETE] = { - .op_func = (nfsd4op_func)nfsd4_reclaim_complete, + .op_func = nfsd4_reclaim_complete, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_RECLAIM_COMPLETE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_SECINFO_NO_NAME] = { - .op_func = (nfsd4op_func)nfsd4_secinfo_no_name, + .op_func = nfsd4_secinfo_no_name, + .op_release = nfsd4_secinfo_no_name_release, .op_flags = OP_HANDLES_WRONGSEC, .op_name = "OP_SECINFO_NO_NAME", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_secinfo_rsize, + .op_rsize_bop = nfsd4_secinfo_rsize, }, [OP_TEST_STATEID] = { - .op_func = (nfsd4op_func)nfsd4_test_stateid, + .op_func = nfsd4_test_stateid, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_TEST_STATEID", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_test_stateid_rsize, + .op_rsize_bop = nfsd4_test_stateid_rsize, }, [OP_FREE_STATEID] = { - .op_func = (nfsd4op_func)nfsd4_free_stateid, + .op_func = nfsd4_free_stateid, .op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING, .op_name = "OP_FREE_STATEID", - .op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid, - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_get_currentstateid = nfsd4_get_freestateid, + .op_rsize_bop = nfsd4_only_status_rsize, }, #ifdef CONFIG_NFSD_PNFS [OP_GETDEVICEINFO] = { - .op_func = (nfsd4op_func)nfsd4_getdeviceinfo, + .op_func = nfsd4_getdeviceinfo, + .op_release = nfsd4_getdeviceinfo_release, .op_flags = ALLOWED_WITHOUT_FH, .op_name = "OP_GETDEVICEINFO", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_getdeviceinfo_rsize, + .op_rsize_bop = nfsd4_getdeviceinfo_rsize, }, [OP_LAYOUTGET] = { - .op_func = (nfsd4op_func)nfsd4_layoutget, + .op_func = nfsd4_layoutget, + .op_release = nfsd4_layoutget_release, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTGET", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize, + .op_rsize_bop = nfsd4_layoutget_rsize, }, [OP_LAYOUTCOMMIT] = { - .op_func = (nfsd4op_func)nfsd4_layoutcommit, + .op_func = nfsd4_layoutcommit, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTCOMMIT", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize, + .op_rsize_bop = nfsd4_layoutcommit_rsize, }, [OP_LAYOUTRETURN] = { - .op_func = (nfsd4op_func)nfsd4_layoutreturn, + .op_func = nfsd4_layoutreturn, .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_LAYOUTRETURN", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize, + .op_rsize_bop = nfsd4_layoutreturn_rsize, }, #endif /* CONFIG_NFSD_PNFS */ /* NFSv4.2 operations */ [OP_ALLOCATE] = { - .op_func = (nfsd4op_func)nfsd4_allocate, + .op_func = nfsd4_allocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_ALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { - .op_func = (nfsd4op_func)nfsd4_deallocate, + .op_func = nfsd4_deallocate, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_DEALLOCATE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_CLONE] = { - .op_func = (nfsd4op_func)nfsd4_clone, + .op_func = nfsd4_clone, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_CLONE", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize, + .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_COPY] = { - .op_func = (nfsd4op_func)nfsd4_copy, + .op_func = nfsd4_copy, .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, .op_name = "OP_COPY", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_copy_rsize, + .op_rsize_bop = nfsd4_copy_rsize, }, [OP_SEEK] = { - .op_func = (nfsd4op_func)nfsd4_seek, + .op_func = nfsd4_seek, .op_name = "OP_SEEK", - .op_rsize_bop = (nfsd4op_rsize)nfsd4_seek_rsize, + .op_rsize_bop = nfsd4_seek_rsize, }, }; @@ -2515,19 +2528,19 @@ static const char *nfsd4_op_name(unsigned opnum) #define nfsd4_voidres nfsd4_voidargs struct nfsd4_voidargs { int dummy; }; -static struct svc_procedure nfsd_procedures4[2] = { +static const struct svc_procedure nfsd_procedures4[2] = { [NFSPROC4_NULL] = { - .pc_func = (svc_procfunc) nfsd4_proc_null, - .pc_encode = (kxdrproc_t) nfs4svc_encode_voidres, + .pc_func = nfsd4_proc_null, + .pc_encode = nfs4svc_encode_voidres, .pc_argsize = sizeof(struct nfsd4_voidargs), .pc_ressize = sizeof(struct nfsd4_voidres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = 1, }, [NFSPROC4_COMPOUND] = { - .pc_func = (svc_procfunc) nfsd4_proc_compound, - .pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs, - .pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres, + .pc_func = nfsd4_proc_compound, + .pc_decode = nfs4svc_decode_compoundargs, + .pc_encode = nfs4svc_encode_compoundres, .pc_argsize = sizeof(struct nfsd4_compoundargs), .pc_ressize = sizeof(struct nfsd4_compoundres), .pc_release = nfsd4_release_compoundargs, @@ -2536,10 +2549,12 @@ static struct svc_procedure nfsd_procedures4[2] = { }, }; -struct svc_version nfsd_version4 = { +static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; +const struct svc_version nfsd_version4 = { .vs_vers = 4, .vs_nproc = 2, .vs_proc = nfsd_procedures4, + .vs_count = nfsd_count3, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, .vs_rpcb_optnl = true, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 22002fb75a18..0c04f81aa63b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2402,10 +2402,10 @@ static bool client_has_state(struct nfs4_client *clp) } __be32 -nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_exchange_id *exid) +nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; @@ -2698,9 +2698,9 @@ static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs) __be32 nfsd4_create_session(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_create_session *cr_ses) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; @@ -2824,8 +2824,11 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir) return nfserr_inval; } -__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_backchannel_ctl *bc) +__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; struct nfsd4_session *session = cstate->session; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; @@ -2845,8 +2848,9 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_bind_conn_to_session *bcts) + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; __be32 status; struct nfsd4_conn *conn; struct nfsd4_session *session; @@ -2886,10 +2890,10 @@ static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4 } __be32 -nfsd4_destroy_session(struct svc_rqst *r, - struct nfsd4_compound_state *cstate, - struct nfsd4_destroy_session *sessionid) +nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *sessionid = &u->destroy_session; struct nfsd4_session *ses; __be32 status; int ref_held_by_me = 0; @@ -2983,10 +2987,10 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp, } __be32 -nfsd4_sequence(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_sequence *seq) +nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_stream *xdr = &resp->xdr; struct nfsd4_session *session; @@ -3120,8 +3124,11 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp) } __be32 -nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc) +nfsd4_destroy_clientid(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; struct nfs4_client *conf, *unconf; struct nfs4_client *clp = NULL; __be32 status = 0; @@ -3161,8 +3168,10 @@ out: } __be32 -nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc) +nfsd4_reclaim_complete(struct svc_rqst *rqstp, + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; __be32 status = 0; if (rc->rca_one_fs) { @@ -3199,8 +3208,9 @@ out: __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_setclientid *setclid) + union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclid = &u->setclientid; struct xdr_netobj clname = setclid->se_name; nfs4_verifier clverifier = setclid->se_verf; struct nfs4_client *conf, *new; @@ -3257,9 +3267,11 @@ out: __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_setclientid_confirm *setclientid_confirm) + struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *setclientid_confirm = + &u->setclientid_confirm; struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; nfs4_verifier confirm = setclientid_confirm->sc_confirm; @@ -4506,8 +4518,9 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - clientid_t *clid) + union nfsd4_op_u *u) { + clientid_t *clid = &u->renew; struct nfs4_client *clp; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -4993,8 +5006,9 @@ out: */ __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; struct nfs4_client *cl = cstate->session->se_client; @@ -5033,8 +5047,9 @@ out: __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; @@ -5162,8 +5177,9 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_open_confirm *oc) + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; @@ -5230,9 +5246,9 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *cstate, - struct nfsd4_open_downgrade *od) + struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; __be32 status; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -5300,8 +5316,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) */ __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_close *close) + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; __be32 status; struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); @@ -5330,8 +5347,9 @@ out: __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_delegreturn *dr) + union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; struct nfs4_delegation *dp; stateid_t *stateid = &dr->dr_stateid; struct nfs4_stid *s; @@ -5706,8 +5724,9 @@ out: */ __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lock *lock) + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct nfs4_openowner *open_sop = NULL; struct nfs4_lockowner *lock_sop = NULL; struct nfs4_ol_stateid *lock_stp = NULL; @@ -5939,8 +5958,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct */ __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_lockt *lockt) + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct file_lock *file_lock = NULL; struct nfs4_lockowner *lo = NULL; __be32 status; @@ -6012,8 +6032,9 @@ out: __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_locku *locku) + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct nfs4_ol_stateid *stp; struct file *filp = NULL; struct file_lock *file_lock = NULL; @@ -6119,8 +6140,9 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_release_lockowner *rlockowner) + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; clientid_t *clid = &rlockowner->rl_clientid; struct nfs4_stateowner *sop; struct nfs4_lockowner *lo = NULL; @@ -7103,27 +7125,31 @@ clear_current_stateid(struct nfsd4_compound_state *cstate) * functions to set current state id */ void -nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp) +nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &odp->od_stateid); + put_stateid(cstate, &u->open_downgrade.od_stateid); } void -nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) +nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &open->op_stateid); + put_stateid(cstate, &u->open.op_stateid); } void -nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close) +nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &close->cl_stateid); + put_stateid(cstate, &u->close.cl_stateid); } void -nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock) +nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - put_stateid(cstate, &lock->lk_resp_stateid); + put_stateid(cstate, &u->lock.lk_resp_stateid); } /* @@ -7131,49 +7157,57 @@ nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lo */ void -nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp) +nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &odp->od_stateid); + get_stateid(cstate, &u->open_downgrade.od_stateid); } void -nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp) +nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &drp->dr_stateid); + get_stateid(cstate, &u->delegreturn.dr_stateid); } void -nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp) +nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &fsp->fr_stateid); + get_stateid(cstate, &u->free_stateid.fr_stateid); } void -nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr) +nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &setattr->sa_stateid); + get_stateid(cstate, &u->setattr.sa_stateid); } void -nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close) +nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &close->cl_stateid); + get_stateid(cstate, &u->close.cl_stateid); } void -nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku) +nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &locku->lu_stateid); + get_stateid(cstate, &u->locku.lu_stateid); } void -nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read) +nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &read->rd_stateid); + get_stateid(cstate, &u->read.rd_stateid); } void -nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write) +nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, + union nfsd4_op_u *u) { - get_stateid(cstate, &write->wr_stateid); + get_stateid(cstate, &u->write.wr_stateid); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 26780d53a6f9..2c61c6b8ae09 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -144,7 +144,7 @@ static void next_decode_page(struct nfsd4_compoundargs *argp) argp->p = page_address(argp->pagelist[0]); argp->pagelist++; if (argp->pagelen < PAGE_SIZE) { - argp->end = argp->p + (argp->pagelen>>2); + argp->end = argp->p + XDR_QUADLEN(argp->pagelen); argp->pagelen = 0; } else { argp->end = argp->p + (PAGE_SIZE>>2); @@ -159,6 +159,25 @@ static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes) */ unsigned int avail = (char *)argp->end - (char *)argp->p; __be32 *p; + + if (argp->pagelen == 0) { + struct kvec *vec = &argp->rqstp->rq_arg.tail[0]; + + if (!argp->tail) { + argp->tail = true; + avail = vec->iov_len; + argp->p = vec->iov_base; + argp->end = vec->iov_base + avail; + } + + if (avail < nbytes) + return NULL; + + p = argp->p; + argp->p += XDR_QUADLEN(nbytes); + return p; + } + if (avail + argp->pagelen < nbytes) return NULL; if (avail + PAGE_SIZE < nbytes) /* need more than a page !! */ @@ -1279,9 +1298,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) argp->pagelen -= pages * PAGE_SIZE; len -= pages * PAGE_SIZE; - argp->p = (__be32 *)page_address(argp->pagelist[0]); - argp->pagelist++; - argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE); + next_decode_page(argp); } argp->p += XDR_QUADLEN(len); @@ -1780,7 +1797,7 @@ nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); -static nfsd4_dec nfsd4_dec_ops[] = { +static const nfsd4_dec nfsd4_dec_ops[] = { [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, @@ -1929,6 +1946,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } + op->opdesc = OPDESC(op); /* * We'll try to cache the result in the DRC if any one * op in the compound wants to be cached: @@ -1973,7 +1991,7 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, *p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time)); *p++ = 0; } else if (IS_I_VERSION(inode)) { - p = xdr_encode_hyper(p, inode->i_version); + p = xdr_encode_hyper(p, nfsd4_change_attribute(inode)); } else { *p++ = cpu_to_be32(stat->ctime.tv_sec); *p++ = cpu_to_be32(stat->ctime.tv_nsec); @@ -3104,14 +3122,12 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, 8); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(access->ac_supported); - *p++ = cpu_to_be32(access->ac_resp_access); - } - return nfserr; + p = xdr_reserve_space(xdr, 8); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(access->ac_supported); + *p++ = cpu_to_be32(access->ac_resp_access); + return 0; } static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) @@ -3119,17 +3135,15 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, bcts->sessionid.data, - NFS4_MAX_SESSIONID_LEN); - *p++ = cpu_to_be32(bcts->dir); - /* Upshifting from TCP to RDMA is not supported */ - *p++ = cpu_to_be32(0); - } - return nfserr; + p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, bcts->sessionid.data, + NFS4_MAX_SESSIONID_LEN); + *p++ = cpu_to_be32(bcts->dir); + /* Upshifting from TCP to RDMA is not supported */ + *p++ = cpu_to_be32(0); + return 0; } static __be32 @@ -3137,10 +3151,7 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c { struct xdr_stream *xdr = &resp->xdr; - if (!nfserr) - nfserr = nfsd4_encode_stateid(xdr, &close->cl_stateid); - - return nfserr; + return nfsd4_encode_stateid(xdr, &close->cl_stateid); } @@ -3150,14 +3161,12 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque_fixed(p, commit->co_verf.data, + p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque_fixed(p, commit->co_verf.data, NFS4_VERIFIER_SIZE); - } - return nfserr; + return 0; } static __be32 @@ -3166,15 +3175,13 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - encode_cinfo(p, &create->cr_cinfo); - nfserr = nfsd4_encode_bitmap(xdr, create->cr_bmval[0], - create->cr_bmval[1], create->cr_bmval[2]); - } - return nfserr; + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + encode_cinfo(p, &create->cr_cinfo); + nfserr = nfsd4_encode_bitmap(xdr, create->cr_bmval[0], + create->cr_bmval[1], create->cr_bmval[2]); + return 0; } static __be32 @@ -3183,13 +3190,8 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = &resp->xdr; - if (nfserr) - return nfserr; - - nfserr = nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry, - getattr->ga_bmval, - resp->rqstp, 0); - return nfserr; + return nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry, + getattr->ga_bmval, resp->rqstp, 0); } static __be32 @@ -3200,14 +3202,12 @@ nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh unsigned int len; __be32 *p; - if (!nfserr) { - len = fhp->fh_handle.fh_size; - p = xdr_reserve_space(xdr, len + 4); - if (!p) - return nfserr_resource; - p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len); - } - return nfserr; + len = fhp->fh_handle.fh_size; + p = xdr_reserve_space(xdr, len + 4); + if (!p) + return nfserr_resource; + p = xdr_encode_opaque(p, &fhp->fh_handle.fh_base, len); + return 0; } /* @@ -3277,10 +3277,7 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l { struct xdr_stream *xdr = &resp->xdr; - if (!nfserr) - nfserr = nfsd4_encode_stateid(xdr, &locku->lu_stateid); - - return nfserr; + return nfsd4_encode_stateid(xdr, &locku->lu_stateid); } @@ -3290,13 +3287,11 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &link->li_cinfo); - } - return nfserr; + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &link->li_cinfo); + return 0; } @@ -3306,12 +3301,9 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (nfserr) - goto out; - nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid); if (nfserr) - goto out; + return nfserr; p = xdr_reserve_space(xdr, 24); if (!p) return nfserr_resource; @@ -3321,7 +3313,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op nfserr = nfsd4_encode_bitmap(xdr, open->op_bmval[0], open->op_bmval[1], open->op_bmval[2]); if (nfserr) - goto out; + return nfserr; p = xdr_reserve_space(xdr, 4); if (!p) @@ -3394,8 +3386,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op BUG(); } /* XXX save filehandle here */ -out: - return nfserr; + return 0; } static __be32 @@ -3403,10 +3394,7 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct { struct xdr_stream *xdr = &resp->xdr; - if (!nfserr) - nfserr = nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); - - return nfserr; + return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); } static __be32 @@ -3414,10 +3402,7 @@ nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struc { struct xdr_stream *xdr = &resp->xdr; - if (!nfserr) - nfserr = nfsd4_encode_stateid(xdr, &od->od_stateid); - - return nfserr; + return nfsd4_encode_stateid(xdr, &od->od_stateid); } static __be32 nfsd4_encode_splice_read( @@ -3554,20 +3539,15 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, struct raparms *ra = NULL; __be32 *p; - if (nfserr) - goto out; - p = xdr_reserve_space(xdr, 8); /* eof flag and byte count */ if (!p) { WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)); - nfserr = nfserr_resource; - goto out; + return nfserr_resource; } if (resp->xdr.buf->page_len && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) { WARN_ON_ONCE(1); - nfserr = nfserr_resource; - goto out; + return nfserr_resource; } xdr_commit_encode(xdr); @@ -3591,9 +3571,6 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, if (nfserr) xdr_truncate_encode(xdr, starting_len); -out: - if (file) - fput(file); return nfserr; } @@ -3607,9 +3584,6 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd int length_offset = xdr->buf->len; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 4); if (!p) return nfserr_resource; @@ -3653,9 +3627,6 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 int starting_len = xdr->buf->len; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE); if (!p) return nfserr_resource; @@ -3741,13 +3712,11 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, 20); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &remove->rm_cinfo); - } - return nfserr; + p = xdr_reserve_space(xdr, 20); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &remove->rm_cinfo); + return 0; } static __be32 @@ -3756,19 +3725,16 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, 40); - if (!p) - return nfserr_resource; - p = encode_cinfo(p, &rename->rn_sinfo); - p = encode_cinfo(p, &rename->rn_tinfo); - } - return nfserr; + p = xdr_reserve_space(xdr, 40); + if (!p) + return nfserr_resource; + p = encode_cinfo(p, &rename->rn_sinfo); + p = encode_cinfo(p, &rename->rn_tinfo); + return 0; } static __be32 -nfsd4_do_encode_secinfo(struct xdr_stream *xdr, - __be32 nfserr, struct svc_export *exp) +nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) { u32 i, nflavs, supported; struct exp_flavor_info *flavs; @@ -3776,9 +3742,6 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, __be32 *p, *flavorsp; static bool report = true; - if (nfserr) - goto out; - nfserr = nfserr_resource; if (exp->ex_nflavors) { flavs = exp->ex_flavors; nflavs = exp->ex_nflavors; @@ -3802,7 +3765,7 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, supported = 0; p = xdr_reserve_space(xdr, 4); if (!p) - goto out; + return nfserr_resource; flavorsp = p++; /* to be backfilled later */ for (i = 0; i < nflavs; i++) { @@ -3814,7 +3777,7 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, p = xdr_reserve_space(xdr, 4 + 4 + XDR_LEN(info.oid.len) + 4 + 4); if (!p) - goto out; + return nfserr_resource; *p++ = cpu_to_be32(RPC_AUTH_GSS); p = xdr_encode_opaque(p, info.oid.data, info.oid.len); *p++ = cpu_to_be32(info.qop); @@ -3823,7 +3786,7 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, supported++; p = xdr_reserve_space(xdr, 4); if (!p) - goto out; + return nfserr_resource; *p++ = cpu_to_be32(pf); } else { if (report) @@ -3835,11 +3798,7 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, if (nflavs != supported) report = false; *flavorsp = htonl(supported); - nfserr = 0; -out: - if (exp) - exp_put(exp); - return nfserr; + return 0; } static __be32 @@ -3848,7 +3807,7 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, { struct xdr_stream *xdr = &resp->xdr; - return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->si_exp); + return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); } static __be32 @@ -3857,7 +3816,7 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, { struct xdr_stream *xdr = &resp->xdr; - return nfsd4_do_encode_secinfo(xdr, nfserr, secinfo->sin_exp); + return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); } /* @@ -3918,16 +3877,14 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (!nfserr) { - p = xdr_reserve_space(xdr, 16); - if (!p) - return nfserr_resource; - *p++ = cpu_to_be32(write->wr_bytes_written); - *p++ = cpu_to_be32(write->wr_how_written); - p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, - NFS4_VERIFIER_SIZE); - } - return nfserr; + p = xdr_reserve_space(xdr, 16); + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(write->wr_bytes_written); + *p++ = cpu_to_be32(write->wr_how_written); + p = xdr_encode_opaque_fixed(p, write->wr_verifier.data, + NFS4_VERIFIER_SIZE); + return 0; } static __be32 @@ -3940,12 +3897,8 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, char *server_scope; int major_id_sz; int server_scope_sz; - int status = 0; uint64_t minor_id = 0; - if (nfserr) - return nfserr; - major_id = utsname()->nodename; major_id_sz = strlen(major_id); server_scope = utsname()->nodename; @@ -3970,19 +3923,19 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, break; case SP4_MACH_CRED: /* spo_must_enforce bitmap: */ - status = nfsd4_encode_bitmap(xdr, + nfserr = nfsd4_encode_bitmap(xdr, exid->spo_must_enforce[0], exid->spo_must_enforce[1], exid->spo_must_enforce[2]); - if (status) - goto out; + if (nfserr) + return nfserr; /* spo_must_allow bitmap: */ - status = nfsd4_encode_bitmap(xdr, + nfserr = nfsd4_encode_bitmap(xdr, exid->spo_must_allow[0], exid->spo_must_allow[1], exid->spo_must_allow[2]); - if (status) - goto out; + if (nfserr) + return nfserr; break; default: WARN_ON_ONCE(1); @@ -4009,8 +3962,6 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, /* Implementation id */ *p++ = cpu_to_be32(0); /* zero length nfs_impl_id4 array */ return 0; -out: - return status; } static __be32 @@ -4020,9 +3971,6 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 24); if (!p) return nfserr_resource; @@ -4076,9 +4024,6 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20); if (!p) return nfserr_resource; @@ -4103,9 +4048,6 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 4 + (4 * test_stateid->ts_num_ids)); if (!p) return nfserr_resource; @@ -4115,7 +4057,7 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = stateid->ts_id_status; } - return nfserr; + return 0; } #ifdef CONFIG_NFSD_PNFS @@ -4128,14 +4070,9 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, u32 starting_len = xdr->buf->len, needed_len; __be32 *p; - dprintk("%s: err %d\n", __func__, be32_to_cpu(nfserr)); - if (nfserr) - goto out; - - nfserr = nfserr_resource; p = xdr_reserve_space(xdr, 4); if (!p) - goto out; + return nfserr_resource; *p++ = cpu_to_be32(gdev->gd_layout_type); @@ -4151,42 +4088,33 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, */ if (xdr->buf->len + 4 > gdev->gd_maxcount) goto toosmall; - goto out; + return nfserr; } } - nfserr = nfserr_resource; if (gdev->gd_notify_types) { p = xdr_reserve_space(xdr, 4 + 4); if (!p) - goto out; + return nfserr_resource; *p++ = cpu_to_be32(1); /* bitmap length */ *p++ = cpu_to_be32(gdev->gd_notify_types); } else { p = xdr_reserve_space(xdr, 4); if (!p) - goto out; + return nfserr_resource; *p++ = 0; } - nfserr = 0; -out: - kfree(gdev->gd_device); - dprintk("%s: done: %d\n", __func__, be32_to_cpu(nfserr)); - return nfserr; - + return 0; toosmall: dprintk("%s: maxcount too small\n", __func__); needed_len = xdr->buf->len + 4 /* notifications */; xdr_truncate_encode(xdr, starting_len); p = xdr_reserve_space(xdr, 4); - if (!p) { - nfserr = nfserr_resource; - } else { - *p++ = cpu_to_be32(needed_len); - nfserr = nfserr_toosmall; - } - goto out; + if (!p) + return nfserr_resource; + *p++ = cpu_to_be32(needed_len); + return nfserr_toosmall; } static __be32 @@ -4197,14 +4125,9 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, const struct nfsd4_layout_ops *ops; __be32 *p; - dprintk("%s: err %d\n", __func__, nfserr); - if (nfserr) - goto out; - - nfserr = nfserr_resource; p = xdr_reserve_space(xdr, 36 + sizeof(stateid_opaque_t)); if (!p) - goto out; + return nfserr_resource; *p++ = cpu_to_be32(1); /* we always set return-on-close */ *p++ = cpu_to_be32(lgp->lg_sid.si_generation); @@ -4218,10 +4141,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, *p++ = cpu_to_be32(lgp->lg_layout_type); ops = nfsd4_layout_ops[lgp->lg_layout_type]; - nfserr = ops->encode_layoutget(xdr, lgp); -out: - kfree(lgp->lg_content); - return nfserr; + return ops->encode_layoutget(xdr, lgp); } static __be32 @@ -4231,9 +4151,6 @@ nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 4); if (!p) return nfserr_resource; @@ -4245,7 +4162,7 @@ nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, p = xdr_encode_hyper(p, lcp->lc_newsize); } - return nfs_ok; + return 0; } static __be32 @@ -4255,16 +4172,13 @@ nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, struct xdr_stream *xdr = &resp->xdr; __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(xdr, 4); if (!p) return nfserr_resource; *p++ = cpu_to_be32(lrp->lrs_present); if (lrp->lrs_present) return nfsd4_encode_stateid(xdr, &lrp->lr_sid); - return nfs_ok; + return 0; } #endif /* CONFIG_NFSD_PNFS */ @@ -4291,16 +4205,14 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, { __be32 *p; - if (!nfserr) { - nfserr = nfsd42_encode_write_res(resp, ©->cp_res); - if (nfserr) - return nfserr; + nfserr = nfsd42_encode_write_res(resp, ©->cp_res); + if (nfserr) + return nfserr; - p = xdr_reserve_space(&resp->xdr, 4 + 4); - *p++ = cpu_to_be32(copy->cp_consecutive); - *p++ = cpu_to_be32(copy->cp_synchronous); - } - return nfserr; + p = xdr_reserve_space(&resp->xdr, 4 + 4); + *p++ = cpu_to_be32(copy->cp_consecutive); + *p++ = cpu_to_be32(copy->cp_synchronous); + return 0; } static __be32 @@ -4309,14 +4221,11 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, { __be32 *p; - if (nfserr) - return nfserr; - p = xdr_reserve_space(&resp->xdr, 4 + 8); *p++ = cpu_to_be32(seek->seek_eof); p = xdr_encode_hyper(p, seek->seek_pos); - return nfserr; + return 0; } static __be32 @@ -4332,7 +4241,7 @@ typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); * since we don't need to filter out obsolete ops as this is * done in the decoding phase. */ -static nfsd4_enc nfsd4_enc_ops[] = { +static const nfsd4_enc nfsd4_enc_ops[] = { [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, @@ -4451,6 +4360,7 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) struct xdr_stream *xdr = &resp->xdr; struct nfs4_stateowner *so = resp->cstate.replay_owner; struct svc_rqst *rqstp = resp->rqstp; + const struct nfsd4_operation *opdesc = op->opdesc; int post_err_offset; nfsd4_enc encoder; __be32 *p; @@ -4465,10 +4375,15 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) if (op->opnum == OP_ILLEGAL) goto status; + if (op->status && opdesc && + !(opdesc->op_flags & OP_NONTRIVIAL_ERROR_ENCODE)) + goto status; BUG_ON(op->opnum < 0 || op->opnum >= ARRAY_SIZE(nfsd4_enc_ops) || !nfsd4_enc_ops[op->opnum]); encoder = nfsd4_enc_ops[op->opnum]; op->status = encoder(resp, op->status, &op->u); + if (opdesc && opdesc->op_release) + opdesc->op_release(&op->u); xdr_commit_encode(xdr); /* nfsd4_check_resp_size guarantees enough room for error status */ @@ -4538,14 +4453,13 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op) } int -nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } -int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) +void nfsd4_release_compoundargs(struct svc_rqst *rqstp) { - struct svc_rqst *rqstp = rq; struct nfsd4_compoundargs *args = rqstp->rq_argp; if (args->ops != args->iops) { @@ -4559,12 +4473,13 @@ int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp) args->to_free = tb->next; kfree(tb); } - return 1; } int -nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args) +nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd4_compoundargs *args = rqstp->rq_argp; + if (rqstp->rq_arg.head[0].iov_len % 4) { /* client is nuts */ dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)", @@ -4575,6 +4490,7 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_comp args->end = rqstp->rq_arg.head[0].iov_base + rqstp->rq_arg.head[0].iov_len; args->pagelist = rqstp->rq_arg.pages; args->pagelen = rqstp->rq_arg.page_len; + args->tail = false; args->tmpp = NULL; args->to_free = NULL; args->ops = args->iops; @@ -4584,11 +4500,12 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_comp } int -nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp) +nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) { /* * All that remains is to write the tag and operation count... */ + struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_buf *buf = resp->xdr.buf; WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index d96606801d47..b9c538ab7a59 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -60,7 +60,7 @@ struct readdir_cd { extern struct svc_program nfsd_program; -extern struct svc_version nfsd_version2, nfsd_version3, +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; @@ -86,12 +86,12 @@ void nfsd_destroy(struct net *net); #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL -extern struct svc_version nfsd_acl_version2; +extern const struct svc_version nfsd_acl_version2; #else #define nfsd_acl_version2 NULL #endif #ifdef CONFIG_NFSD_V3_ACL -extern struct svc_version nfsd_acl_version3; +extern const struct svc_version nfsd_acl_version3; #else #define nfsd_acl_version3 NULL #endif diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index f84fe6bf9aee..e47cf6c2ac28 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -241,6 +241,28 @@ fh_clear_wcc(struct svc_fh *fhp) } /* + * We could use i_version alone as the change attribute. However, + * i_version can go backwards after a reboot. On its own that doesn't + * necessarily cause a problem, but if i_version goes backwards and then + * is incremented again it could reuse a value that was previously used + * before boot, and a client who queried the two values might + * incorrectly assume nothing changed. + * + * By using both ctime and the i_version counter we guarantee that as + * long as time doesn't go backwards we never reuse an old value. + */ +static inline u64 nfsd4_change_attribute(struct inode *inode) +{ + u64 chattr; + + chattr = inode->i_ctime.tv_sec; + chattr <<= 30; + chattr += inode->i_ctime.tv_nsec; + chattr += inode->i_version; + return chattr; +} + +/* * Fill in the pre_op attr for the wcc data */ static inline void @@ -253,7 +275,7 @@ fill_pre_wcc(struct svc_fh *fhp) fhp->fh_pre_mtime = inode->i_mtime; fhp->fh_pre_ctime = inode->i_ctime; fhp->fh_pre_size = inode->i_size; - fhp->fh_pre_change = inode->i_version; + fhp->fh_pre_change = nfsd4_change_attribute(inode); fhp->fh_pre_saved = true; } } diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 03a7e9da4da0..5076ae2b8258 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -17,7 +17,7 @@ typedef struct svc_buf svc_buf; static __be32 -nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp) +nfsd_proc_null(struct svc_rqst *rqstp) { return nfs_ok; } @@ -39,9 +39,10 @@ nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp) * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, - struct nfsd_attrstat *resp) +nfsd_proc_getattr(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); @@ -56,9 +57,10 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp, - struct nfsd_attrstat *resp) +nfsd_proc_setattr(struct svc_rqst *rqstp) { + struct nfsd_sattrargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; struct iattr *iap = &argp->attrs; struct svc_fh *fhp; __be32 nfserr; @@ -122,9 +124,10 @@ done: * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_lookup(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: LOOKUP %s %.*s\n", @@ -142,9 +145,10 @@ nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, * Read a symlink. */ static __be32 -nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp, - struct nfsd_readlinkres *resp) +nfsd_proc_readlink(struct svc_rqst *rqstp) { + struct nfsd_readlinkargs *argp = rqstp->rq_argp; + struct nfsd_readlinkres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh)); @@ -162,9 +166,10 @@ nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp, - struct nfsd_readres *resp) +nfsd_proc_read(struct svc_rqst *rqstp) { + struct nfsd_readargs *argp = rqstp->rq_argp; + struct nfsd_readres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: READ %s %d bytes at %d\n", @@ -200,9 +205,10 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, - struct nfsd_attrstat *resp) +nfsd_proc_write(struct svc_rqst *rqstp) { + struct nfsd_writeargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; __be32 nfserr; unsigned long cnt = argp->len; @@ -222,9 +228,10 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp, * N.B. After this call _both_ argp->fh and resp->fh need an fh_put */ static __be32 -nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_create(struct svc_rqst *rqstp) { + struct nfsd_createargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; svc_fh *dirfhp = &argp->fh; svc_fh *newfhp = &resp->fh; struct iattr *attr = &argp->attrs; @@ -377,9 +384,9 @@ done: } static __be32 -nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - void *resp) +nfsd_proc_remove(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: REMOVE %s %.*s\n", SVCFH_fmt(&argp->fh), @@ -392,9 +399,9 @@ nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, } static __be32 -nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp, - void *resp) +nfsd_proc_rename(struct svc_rqst *rqstp) { + struct nfsd_renameargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: RENAME %s %.*s -> \n", @@ -410,9 +417,9 @@ nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp, } static __be32 -nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp, - void *resp) +nfsd_proc_link(struct svc_rqst *rqstp) { + struct nfsd_linkargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: LINK %s ->\n", @@ -430,9 +437,9 @@ nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp, } static __be32 -nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp, - void *resp) +nfsd_proc_symlink(struct svc_rqst *rqstp) { + struct nfsd_symlinkargs *argp = rqstp->rq_argp; struct svc_fh newfh; __be32 nfserr; @@ -460,9 +467,10 @@ nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp, * N.B. After this call resp->fh needs an fh_put */ static __be32 -nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp, - struct nfsd_diropres *resp) +nfsd_proc_mkdir(struct svc_rqst *rqstp) { + struct nfsd_createargs *argp = rqstp->rq_argp; + struct nfsd_diropres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: MKDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -484,9 +492,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp, * Remove a directory */ static __be32 -nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, - void *resp) +nfsd_proc_rmdir(struct svc_rqst *rqstp) { + struct nfsd_diropargs *argp = rqstp->rq_argp; __be32 nfserr; dprintk("nfsd: RMDIR %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name); @@ -500,9 +508,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp, * Read a portion of a directory. */ static __be32 -nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp, - struct nfsd_readdirres *resp) +nfsd_proc_readdir(struct svc_rqst *rqstp) { + struct nfsd_readdirargs *argp = rqstp->rq_argp; + struct nfsd_readdirres *resp = rqstp->rq_resp; int count; __be32 nfserr; loff_t offset; @@ -540,9 +549,10 @@ nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp, * Get file system info */ static __be32 -nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, - struct nfsd_statfsres *resp) +nfsd_proc_statfs(struct svc_rqst *rqstp) { + struct nfsd_fhandle *argp = rqstp->rq_argp; + struct nfsd_statfsres *resp = rqstp->rq_resp; __be32 nfserr; dprintk("nfsd: STATFS %s\n", SVCFH_fmt(&argp->fh)); @@ -563,168 +573,168 @@ struct nfsd_void { int dummy; }; #define FH 8 /* filehandle */ #define AT 18 /* attributes */ -static struct svc_procedure nfsd_procedures2[18] = { +static const struct svc_procedure nfsd_procedures2[18] = { [NFSPROC_NULL] = { - .pc_func = (svc_procfunc) nfsd_proc_null, - .pc_decode = (kxdrproc_t) nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_func = nfsd_proc_null, + .pc_decode = nfssvc_decode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, }, [NFSPROC_GETATTR] = { - .pc_func = (svc_procfunc) nfsd_proc_getattr, - .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_getattr, + .pc_decode = nfssvc_decode_fhandle, + .pc_encode = nfssvc_encode_attrstat, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT, }, [NFSPROC_SETATTR] = { - .pc_func = (svc_procfunc) nfsd_proc_setattr, - .pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_setattr, + .pc_decode = nfssvc_decode_sattrargs, + .pc_encode = nfssvc_encode_attrstat, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_sattrargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, }, [NFSPROC_ROOT] = { - .pc_decode = (kxdrproc_t) nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_decode = nfssvc_decode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, }, [NFSPROC_LOOKUP] = { - .pc_func = (svc_procfunc) nfsd_proc_lookup, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_lookup, + .pc_decode = nfssvc_decode_diropargs, + .pc_encode = nfssvc_encode_diropres, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+FH+AT, }, [NFSPROC_READLINK] = { - .pc_func = (svc_procfunc) nfsd_proc_readlink, - .pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres, + .pc_func = nfsd_proc_readlink, + .pc_decode = nfssvc_decode_readlinkargs, + .pc_encode = nfssvc_encode_readlinkres, .pc_argsize = sizeof(struct nfsd_readlinkargs), .pc_ressize = sizeof(struct nfsd_readlinkres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+1+NFS_MAXPATHLEN/4, }, [NFSPROC_READ] = { - .pc_func = (svc_procfunc) nfsd_proc_read, - .pc_decode = (kxdrproc_t) nfssvc_decode_readargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_read, + .pc_decode = nfssvc_decode_readargs, + .pc_encode = nfssvc_encode_readres, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_readargs), .pc_ressize = sizeof(struct nfsd_readres), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4, }, [NFSPROC_WRITECACHE] = { - .pc_decode = (kxdrproc_t) nfssvc_decode_void, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_decode = nfssvc_decode_void, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_void), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_NOCACHE, .pc_xdrressize = ST, }, [NFSPROC_WRITE] = { - .pc_func = (svc_procfunc) nfsd_proc_write, - .pc_decode = (kxdrproc_t) nfssvc_decode_writeargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_attrstat, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_write, + .pc_decode = nfssvc_decode_writeargs, + .pc_encode = nfssvc_encode_attrstat, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_writeargs), .pc_ressize = sizeof(struct nfsd_attrstat), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+AT, }, [NFSPROC_CREATE] = { - .pc_func = (svc_procfunc) nfsd_proc_create, - .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_create, + .pc_decode = nfssvc_decode_createargs, + .pc_encode = nfssvc_encode_diropres, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, }, [NFSPROC_REMOVE] = { - .pc_func = (svc_procfunc) nfsd_proc_remove, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_func = nfsd_proc_remove, + .pc_decode = nfssvc_decode_diropargs, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, }, [NFSPROC_RENAME] = { - .pc_func = (svc_procfunc) nfsd_proc_rename, - .pc_decode = (kxdrproc_t) nfssvc_decode_renameargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_func = nfsd_proc_rename, + .pc_decode = nfssvc_decode_renameargs, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_renameargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, }, [NFSPROC_LINK] = { - .pc_func = (svc_procfunc) nfsd_proc_link, - .pc_decode = (kxdrproc_t) nfssvc_decode_linkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_func = nfsd_proc_link, + .pc_decode = nfssvc_decode_linkargs, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_linkargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, }, [NFSPROC_SYMLINK] = { - .pc_func = (svc_procfunc) nfsd_proc_symlink, - .pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_func = nfsd_proc_symlink, + .pc_decode = nfssvc_decode_symlinkargs, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_symlinkargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, }, [NFSPROC_MKDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_mkdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_createargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_diropres, - .pc_release = (kxdrproc_t) nfssvc_release_fhandle, + .pc_func = nfsd_proc_mkdir, + .pc_decode = nfssvc_decode_createargs, + .pc_encode = nfssvc_encode_diropres, + .pc_release = nfssvc_release_fhandle, .pc_argsize = sizeof(struct nfsd_createargs), .pc_ressize = sizeof(struct nfsd_diropres), .pc_cachetype = RC_REPLBUFF, .pc_xdrressize = ST+FH+AT, }, [NFSPROC_RMDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_rmdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_diropargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_void, + .pc_func = nfsd_proc_rmdir, + .pc_decode = nfssvc_decode_diropargs, + .pc_encode = nfssvc_encode_void, .pc_argsize = sizeof(struct nfsd_diropargs), .pc_ressize = sizeof(struct nfsd_void), .pc_cachetype = RC_REPLSTAT, .pc_xdrressize = ST, }, [NFSPROC_READDIR] = { - .pc_func = (svc_procfunc) nfsd_proc_readdir, - .pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs, - .pc_encode = (kxdrproc_t) nfssvc_encode_readdirres, + .pc_func = nfsd_proc_readdir, + .pc_decode = nfssvc_decode_readdirargs, + .pc_encode = nfssvc_encode_readdirres, .pc_argsize = sizeof(struct nfsd_readdirargs), .pc_ressize = sizeof(struct nfsd_readdirres), .pc_cachetype = RC_NOCACHE, }, [NFSPROC_STATFS] = { - .pc_func = (svc_procfunc) nfsd_proc_statfs, - .pc_decode = (kxdrproc_t) nfssvc_decode_fhandle, - .pc_encode = (kxdrproc_t) nfssvc_encode_statfsres, + .pc_func = nfsd_proc_statfs, + .pc_decode = nfssvc_decode_fhandle, + .pc_encode = nfssvc_encode_statfsres, .pc_argsize = sizeof(struct nfsd_fhandle), .pc_ressize = sizeof(struct nfsd_statfsres), .pc_cachetype = RC_NOCACHE, @@ -733,12 +743,14 @@ static struct svc_procedure nfsd_procedures2[18] = { }; -struct svc_version nfsd_version2 = { - .vs_vers = 2, - .vs_nproc = 18, - .vs_proc = nfsd_procedures2, - .vs_dispatch = nfsd_dispatch, - .vs_xdrsize = NFS2_SVC_XDRSIZE, +static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; +const struct svc_version nfsd_version2 = { + .vs_vers = 2, + .vs_nproc = 18, + .vs_proc = nfsd_procedures2, + .vs_count = nfsd_count2, + .vs_dispatch = nfsd_dispatch, + .vs_xdrsize = NFS2_SVC_XDRSIZE, }; /* diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 59979f0bbd4b..7e3af3ef0917 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -68,14 +68,14 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; -static struct svc_version * nfsd_acl_version[] = { +static const struct svc_version *nfsd_acl_version[] = { [2] = &nfsd_acl_version2, [3] = &nfsd_acl_version3, }; #define NFSD_ACL_MINVERS 2 #define NFSD_ACL_NRVERS ARRAY_SIZE(nfsd_acl_version) -static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; +static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS]; static struct svc_program nfsd_acl_program = { .pg_prog = NFS_ACL_PROGRAM, @@ -92,7 +92,7 @@ static struct svc_stat nfsd_acl_svcstats = { }; #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ -static struct svc_version * nfsd_version[] = { +static const struct svc_version *nfsd_version[] = { [2] = &nfsd_version2, #if defined(CONFIG_NFSD_V3) [3] = &nfsd_version3, @@ -104,7 +104,7 @@ static struct svc_version * nfsd_version[] = { #define NFSD_MINVERS 2 #define NFSD_NRVERS ARRAY_SIZE(nfsd_version) -static struct svc_version *nfsd_versions[NFSD_NRVERS]; +static const struct svc_version *nfsd_versions[NFSD_NRVERS]; struct svc_program nfsd_program = { #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) @@ -475,7 +475,7 @@ static int nfsd_get_default_max_blksize(void) return ret; } -static struct svc_serv_ops nfsd_thread_sv_ops = { +static const struct svc_serv_ops nfsd_thread_sv_ops = { .svo_shutdown = nfsd_last_thread, .svo_function = nfsd, .svo_enqueue_xprt = svc_xprt_do_enqueue, @@ -756,7 +756,7 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr) * problem, we enforce these assumptions here: */ static bool nfs_request_too_big(struct svc_rqst *rqstp, - struct svc_procedure *proc) + const struct svc_procedure *proc) { /* * The ACL code has more careful bounds-checking and is not @@ -781,8 +781,7 @@ static bool nfs_request_too_big(struct svc_rqst *rqstp, int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { - struct svc_procedure *proc; - kxdrproc_t xdr; + const struct svc_procedure *proc; __be32 nfserr; __be32 *nfserrp; @@ -801,9 +800,8 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) */ rqstp->rq_cachetype = proc->pc_cachetype; /* Decode arguments */ - xdr = proc->pc_decode; - if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base, - rqstp->rq_argp)) { + if (proc->pc_decode && + !proc->pc_decode(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base)) { dprintk("nfsd: failed to decode arguments!\n"); *statp = rpc_garbage_args; return 1; @@ -827,7 +825,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_res.head[0].iov_len += sizeof(__be32); /* Now call the procedure handler, and encode NFS status. */ - nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); + nfserr = proc->pc_func(rqstp); nfserr = map_new_errors(rqstp->rq_vers, nfserr); if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) { dprintk("nfsd: Dropping request; may be revisited later\n"); @@ -842,9 +840,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) * For NFSv2, additional info is never returned in case of an error. */ if (!(nfserr && rqstp->rq_vers == 2)) { - xdr = proc->pc_encode; - if (xdr && !xdr(rqstp, nfserrp, - rqstp->rq_resp)) { + if (proc->pc_encode && !proc->pc_encode(rqstp, nfserrp)) { /* Failed to encode result. Release cache entry */ dprintk("nfsd: failed to encode result!\n"); nfsd_cache_update(rqstp, RC_NOCACHE, NULL); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index de07ff625777..e4da2717982d 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -206,14 +206,16 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f * XDR decode functions */ int -nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_argsize_check(rqstp, p); } int -nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args) +nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_fhandle *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -221,9 +223,10 @@ nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *ar } int -nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_sattrargs *args) +nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_sattrargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -233,9 +236,10 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_diropargs *args) +nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_diropargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -244,9 +248,9 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readargs *args) +nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readargs *args = rqstp->rq_argp; unsigned int len; int v; p = decode_fh(p, &args->fh); @@ -276,9 +280,9 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_writeargs *args) +nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_writeargs *args = rqstp->rq_argp; unsigned int len, hdr, dlen; struct kvec *head = rqstp->rq_arg.head; int v; @@ -332,9 +336,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_createargs *args) +nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_createargs *args = rqstp->rq_argp; + if ( !(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; @@ -344,9 +349,10 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_renameargs *args) +nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_renameargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_fh(p, &args->tfh)) @@ -357,8 +363,10 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args) +nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readlinkargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -368,9 +376,10 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli } int -nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_linkargs *args) +nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_linkargs *args = rqstp->rq_argp; + if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_fh(p, &args->tfh)) || !(p = decode_filename(p, &args->tname, &args->tlen))) @@ -380,9 +389,10 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_symlinkargs *args) +nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_symlinkargs *args = rqstp->rq_argp; + if ( !(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen)) || !(p = decode_pathname(p, &args->tname, &args->tlen))) @@ -393,9 +403,10 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readdirargs *args) +nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readdirargs *args = rqstp->rq_argp; + p = decode_fh(p, &args->fh); if (!p) return 0; @@ -411,32 +422,35 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, * XDR encode functions */ int -nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy) +nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p) { return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_attrstat *resp) +nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_attrstat *resp = rqstp->rq_resp; + p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_diropres *resp) +nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_diropres *resp = rqstp->rq_resp; + p = encode_fh(p, &resp->fh); p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); return xdr_ressize_check(rqstp, p); } int -nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readlinkres *resp) +nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readlinkres *resp = rqstp->rq_resp; + *p++ = htonl(resp->len); xdr_ressize_check(rqstp, p); rqstp->rq_res.page_len = resp->len; @@ -450,9 +464,10 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readres *resp) +nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readres *resp = rqstp->rq_resp; + p = encode_fattr(rqstp, p, &resp->fh, &resp->stat); *p++ = htonl(resp->count); xdr_ressize_check(rqstp, p); @@ -469,9 +484,10 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_readdirres *resp) +nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_readdirres *resp = rqstp->rq_resp; + xdr_ressize_check(rqstp, p); p = resp->buffer; *p++ = 0; /* no more entries */ @@ -482,9 +498,9 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_statfsres *resp) +nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) { + struct nfsd_statfsres *resp = rqstp->rq_resp; struct kstatfs *stat = &resp->stats; *p++ = htonl(NFSSVC_MAXBLKSIZE_V2); /* max transfer size */ @@ -543,10 +559,10 @@ nfssvc_encode_entry(void *ccdv, const char *name, /* * XDR release functions */ -int -nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p, - struct nfsd_fhandle *resp) +void +nfssvc_release_fhandle(struct svc_rqst *rqstp) { + struct nfsd_fhandle *resp = rqstp->rq_resp; + fh_put(&resp->fh); - return 1; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 2be32955d7f2..bc69d40c4e8b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -911,24 +911,13 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp, __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, unsigned long *count) { - mm_segment_t oldfs; + struct iov_iter iter; int host_err; - oldfs = get_fs(); - set_fs(KERNEL_DS); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0); - set_fs(oldfs); - return nfsd_finish_read(file, count, host_err); -} + iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count); + host_err = vfs_iter_read(file, &iter, &offset, 0); -static __be32 -nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file, - loff_t offset, struct kvec *vec, int vlen, unsigned long *count) -{ - if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) - return nfsd_splice_read(rqstp, file, offset, count); - else - return nfsd_readv(file, offset, vec, vlen, count); + return nfsd_finish_read(file, count, host_err); } /* @@ -974,13 +963,13 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, unsigned long *cnt, int stable) { struct svc_export *exp; - mm_segment_t oldfs; + struct iov_iter iter; __be32 err = 0; int host_err; int use_wgather; loff_t pos = offset; unsigned int pflags = current->flags; - int flags = 0; + rwf_t flags = 0; if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) /* @@ -1000,10 +989,8 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (stable && !use_wgather) flags |= RWF_SYNC; - /* Write the data. */ - oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, flags); - set_fs(oldfs); + iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt); + host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) goto out_nfserr; *cnt = host_err; @@ -1044,7 +1031,12 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, ra = nfsd_init_raparms(file); trace_read_opened(rqstp, fhp, offset, vlen); - err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count); + + if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags)) + err = nfsd_splice_read(rqstp, file, offset, count); + else + err = nfsd_readv(file, offset, vec, vlen, count); + trace_read_io_done(rqstp, fhp, offset, vlen); if (ra) @@ -1464,41 +1456,34 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp) { - mm_segment_t oldfs; __be32 err; - int host_err; + const char *link; struct path path; + DEFINE_DELAYED_CALL(done); + int len; err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP); - if (err) - goto out; + if (unlikely(err)) + return err; path.mnt = fhp->fh_export->ex_path.mnt; path.dentry = fhp->fh_dentry; - err = nfserr_inval; - if (!d_is_symlink(path.dentry)) - goto out; + if (unlikely(!d_is_symlink(path.dentry))) + return nfserr_inval; touch_atime(&path); - /* N.B. Why does this call need a get_fs()?? - * Remove the set_fs and watch the fireworks:-) --okir - */ - oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_readlink(path.dentry, (char __user *)buf, *lenp); - set_fs(oldfs); - - if (host_err < 0) - goto out_nfserr; - *lenp = host_err; - err = 0; -out: - return err; + link = vfs_get_link(path.dentry, &done); + if (IS_ERR(link)) + return nfserrno(PTR_ERR(link)); -out_nfserr: - err = nfserrno(host_err); - goto out; + len = strlen(link); + if (len < *lenp) + *lenp = len; + memcpy(buf, link, *lenp); + do_delayed_call(&done); + return 0; } /* diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 4f0481d63804..457ce45e5084 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -131,40 +131,30 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd_sattrargs *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd_diropargs *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd_readargs *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd_writeargs *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd_createargs *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd_renameargs *); -int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_readlinkargs *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd_linkargs *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd_symlinkargs *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd_readdirargs *); -int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *); +int nfssvc_decode_void(struct svc_rqst *, __be32 *); +int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); +int nfssvc_encode_void(struct svc_rqst *, __be32 *); +int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *); +int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readres(struct svc_rqst *, __be32 *); +int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *); +int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *); int nfssvc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); -int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); +void nfssvc_release_fhandle(struct svc_rqst *); /* Helper functions for NFSv2 ACL code */ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 335e04aaf7db..80d7da620e91 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -269,71 +269,41 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *, - struct nfsd3_sattrargs *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *, - struct nfsd3_diropargs *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *, - struct nfsd3_accessargs *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *, - struct nfsd3_readargs *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *, - struct nfsd3_writeargs *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_createargs *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *, - struct nfsd3_mknodargs *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *, - struct nfsd3_renameargs *); -int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkargs *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *, - struct nfsd3_linkargs *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *, - struct nfsd3_symlinkargs *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *, - struct nfsd3_readdirargs *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *, - struct nfsd3_commitargs *); -int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *, - struct nfsd3_accessres *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *, - struct nfsd3_readlinkres *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *, - struct nfsd3_diropres *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *, - struct nfsd3_renameres *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *, - struct nfsd3_linkres *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *, - struct nfsd3_readdirres *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *, - struct nfsd3_fsstatres *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *, - struct nfsd3_fsinfores *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *, - struct nfsd3_pathconfres *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *, - struct nfsd3_commitres *); - -int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *, - struct nfsd3_attrstat *); -int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *, - struct nfsd3_fhandle_pair *); +int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *); +int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); +int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *); +int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); +int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_createres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *); +int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *); + +void nfs3svc_release_fhandle(struct svc_rqst *); +void nfs3svc_release_fhandle2(struct svc_rqst *); int nfs3svc_encode_entry(void *, const char *name, int namlen, loff_t offset, u64 ino, unsigned int); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 8fda4abdf3b1..1e4edbf70052 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -538,8 +538,9 @@ struct nfsd4_seek { struct nfsd4_op { int opnum; + const struct nfsd4_operation * opdesc; __be32 status; - union { + union nfsd4_op_u { struct nfsd4_access access; struct nfsd4_close close; struct nfsd4_commit commit; @@ -577,6 +578,7 @@ struct nfsd4_op { struct nfsd4_bind_conn_to_session bind_conn_to_session; struct nfsd4_create_session create_session; struct nfsd4_destroy_session destroy_session; + struct nfsd4_destroy_clientid destroy_clientid; struct nfsd4_sequence sequence; struct nfsd4_reclaim_complete reclaim_complete; struct nfsd4_test_stateid test_stateid; @@ -585,6 +587,7 @@ struct nfsd4_op { struct nfsd4_layoutget layoutget; struct nfsd4_layoutcommit layoutcommit; struct nfsd4_layoutreturn layoutreturn; + struct nfsd4_secinfo_no_name secinfo_no_name; /* NFSv4.2 */ struct nfsd4_fallocate allocate; @@ -612,6 +615,7 @@ struct nfsd4_compoundargs { __be32 * end; struct page ** pagelist; int pagelen; + bool tail; __be32 tmp[8]; __be32 * tmpp; struct svcxdr_tmpbuf *to_free; @@ -659,6 +663,7 @@ static inline bool nfsd4_last_compound_op(struct svc_rqst *rqstp) return argp->opcnt == resp->opcnt; } +const struct nfsd4_operation *OPDESC(struct nfsd4_op *op); int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op); void warn_on_nonidempotent_op(struct nfsd4_op *op); @@ -682,11 +687,9 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, - struct nfsd4_compoundargs *); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, - struct nfsd4_compoundres *); +int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *); +int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); +int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); @@ -695,27 +698,26 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words, struct dentry *dentry, u32 *bmval, struct svc_rqst *, int ignore_crossmnt); extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid *setclid); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_setclientid_confirm *setclientid_confirm); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_exchange_id *); -extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *); -extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_create_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_create_session *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_sequence(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_sequence *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern void nfsd4_sequence_done(struct nfsd4_compoundres *resp); extern __be32 nfsd4_destroy_session(struct svc_rqst *, - struct nfsd4_compound_state *, - struct nfsd4_destroy_session *); -extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *); -__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *u); +__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *, struct nfsd4_open *open, struct nfsd_net *nn); extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp, @@ -724,36 +726,78 @@ extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate); extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open); extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc); -extern __be32 nfsd4_close(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_close *close); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_open_downgrade *od); + struct nfsd4_compound_state *, union nfsd4_op_u *u); extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *, - struct nfsd4_lock *lock); -extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_lockt *lockt); -extern __be32 nfsd4_locku(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_locku *locku); + union nfsd4_op_u *u); +extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); +extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, - struct nfsd4_release_lockowner *rlockowner); -extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp); extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr); -extern __be32 nfsd4_renew(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, clientid_t *clid); + struct nfsd4_compound_state *, union nfsd4_op_u *u); +extern __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *, + union nfsd4_op_u *u); extern __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_test_stateid *test_stateid); + struct nfsd4_compound_state *, union nfsd4_op_u *); extern __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, - struct nfsd4_compound_state *, struct nfsd4_free_stateid *free_stateid); + struct nfsd4_compound_state *, union nfsd4_op_u *); extern void nfsd4_bump_seqid(struct nfsd4_compound_state *, __be32 nfserr); +enum nfsd4_op_flags { + ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */ + ALLOWED_ON_ABSENT_FS = 1 << 1, /* ops processed on absent fs */ + ALLOWED_AS_FIRST_OP = 1 << 2, /* ops reqired first in compound */ + /* For rfc 5661 section 2.6.3.1.1: */ + OP_HANDLES_WRONGSEC = 1 << 3, + OP_IS_PUTFH_LIKE = 1 << 4, + /* + * These are the ops whose result size we estimate before + * encoding, to avoid performing an op then not being able to + * respond or cache a response. This includes writes and setattrs + * as well as the operations usually called "nonidempotent": + */ + OP_MODIFIES_SOMETHING = 1 << 5, + /* + * Cache compounds containing these ops in the xid-based drc: + * We use the DRC for compounds containing non-idempotent + * operations, *except* those that are 4.1-specific (since + * sessions provide their own EOS), and except for stateful + * operations other than setclientid and setclientid_confirm + * (since sequence numbers provide EOS for open, lock, etc in + * the v4.0 case). + */ + OP_CACHEME = 1 << 6, + /* + * These are ops which clear current state id. + */ + OP_CLEAR_STATEID = 1 << 7, + /* Most ops return only an error on failure; some may do more: */ + OP_NONTRIVIAL_ERROR_ENCODE = 1 << 8, +}; + +struct nfsd4_operation { + __be32 (*op_func)(struct svc_rqst *, struct nfsd4_compound_state *, + union nfsd4_op_u *); + void (*op_release)(union nfsd4_op_u *); + u32 op_flags; + char *op_name; + /* Try to get response size before operation */ + u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *); + void (*op_get_currentstateid)(struct nfsd4_compound_state *, + union nfsd4_op_u *); + void (*op_set_currentstateid)(struct nfsd4_compound_state *, + union nfsd4_op_u *); +}; + + #endif /* diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7ffe71a8dfb9..6a612d832e7d 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -174,7 +174,7 @@ static int nilfs_writepages(struct address_space *mapping, struct inode *inode = mapping->host; int err = 0; - if (inode->i_sb->s_flags & MS_RDONLY) { + if (sb_rdonly(inode->i_sb)) { nilfs_clear_dirty_pages(mapping, false); return -EROFS; } @@ -191,7 +191,7 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) struct inode *inode = page->mapping->host; int err; - if (inode->i_sb->s_flags & MS_RDONLY) { + if (sb_rdonly(inode->i_sb)) { /* * It means that filesystem was remounted in read-only * mode because of error or metadata corruption. But we diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index 98835ed6bef4..c6bc1033e7d2 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -413,7 +413,7 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) struct super_block *sb; int err = 0; - if (inode && (inode->i_sb->s_flags & MS_RDONLY)) { + if (inode && sb_rdonly(inode->i_sb)) { /* * It means that filesystem was remounted in read-only * mode because of error or metadata corruption. But we diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index f11a3ad2df0c..8616c46d33da 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -312,10 +312,9 @@ void nilfs_copy_back_pages(struct address_space *dmap, pagevec_init(&pvec, 0); repeat: - n = pagevec_lookup(&pvec, smap, index, PAGEVEC_SIZE); + n = pagevec_lookup(&pvec, smap, &index); if (!n) return; - index = pvec.pages[n - 1]->index + 1; for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i], *dpage; diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 6f87b2ac1aeb..6c5009cc4e6f 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -338,7 +338,7 @@ static void nilfs_end_bio_write(struct bio *bio) { struct nilfs_segment_buffer *segbuf = bio->bi_private; - if (bio->bi_error) + if (bio->bi_status) atomic_inc(&segbuf->sb_err); bio_put(bio); @@ -400,7 +400,7 @@ static struct bio *nilfs_alloc_seg_bio(struct the_nilfs *nilfs, sector_t start, bio = bio_alloc(GFP_NOIO, nr_vecs); } if (likely(bio)) { - bio->bi_bdev = nilfs->ns_bdev; + bio_set_dev(bio, nilfs->ns_bdev); bio->bi_iter.bi_sector = start << (nilfs->ns_blocksize_bits - 9); } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index febed1217b3f..70ded52dc1dd 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2161,7 +2161,7 @@ void nilfs_flush_segment(struct super_block *sb, ino_t ino) } struct nilfs_segctor_wait_request { - wait_queue_t wq; + wait_queue_entry_t wq; __u32 seq; int err; atomic_t done; @@ -2206,8 +2206,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) unsigned long flags; spin_lock_irqsave(&sci->sc_wait_request.lock, flags); - list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.task_list, - wq.task_list) { + list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) { if (!atomic_read(&wrq->done) && nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) { wrq->err = err; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 926682981d61..4fc018dfcfae 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -136,7 +136,7 @@ void __nilfs_error(struct super_block *sb, const char *function, va_end(args); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { nilfs_set_error(sb); if (nilfs_test_opt(nilfs, ERRORS_RO)) { @@ -478,7 +478,7 @@ static void nilfs_put_super(struct super_block *sb) nilfs_detach_log_writer(sb); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { down_write(&nilfs->ns_sem); nilfs_cleanup_super(sb); up_write(&nilfs->ns_sem); @@ -578,7 +578,7 @@ static int nilfs_freeze(struct super_block *sb) struct the_nilfs *nilfs = sb->s_fs_info; int err; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; /* Mark super block clean */ @@ -592,7 +592,7 @@ static int nilfs_unfreeze(struct super_block *sb) { struct the_nilfs *nilfs = sb->s_fs_info; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; down_write(&nilfs->ns_sem); @@ -898,7 +898,7 @@ int nilfs_check_feature_compatibility(struct super_block *sb, } features = le64_to_cpu(sbp->s_feature_compat_ro) & ~NILFS_FEATURE_COMPAT_RO_SUPP; - if (!(sb->s_flags & MS_RDONLY) && features) { + if (!sb_rdonly(sb) && features) { nilfs_msg(sb, KERN_ERR, "couldn't mount RDWR because of unsupported optional features (%llx)", (unsigned long long)features); @@ -1083,7 +1083,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) goto failed_unload; } - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { err = nilfs_attach_log_writer(sb, fsroot); if (err) goto failed_checkpoint; @@ -1095,7 +1095,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { down_write(&nilfs->ns_sem); nilfs_setup_super(sb, true); up_write(&nilfs->ns_sem); @@ -1144,7 +1144,7 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) goto out; if (*flags & MS_RDONLY) { /* Shutting down log writer */ @@ -1338,8 +1338,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags, if ((flags ^ s->s_flags) & MS_RDONLY) { nilfs_msg(s, KERN_ERR, "the device already has a %s mount.", - (s->s_flags & MS_RDONLY) ? - "read-only" : "read/write"); + sb_rdonly(s) ? "read-only" : "read/write"); err = -EBUSY; goto failed_super; } diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 2430a0415995..cba328315929 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -133,7 +133,7 @@ static void dnotify_free_mark(struct fsnotify_mark *fsn_mark) kmem_cache_free(dnotify_mark_cache, dn_mark); } -static struct fsnotify_ops dnotify_fsnotify_ops = { +static const struct fsnotify_ops dnotify_fsnotify_ops = { .handle_event = dnotify_handle_event, .free_mark = dnotify_free_mark, }; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 01a9f0f007d4..0c4583b61717 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -161,16 +161,20 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask if (unlikely(!fsnotify_inode_watches_children(p_inode))) __fsnotify_update_child_dentry_flags(p_inode); else if (p_inode->i_fsnotify_mask & mask) { + struct name_snapshot name; + /* we are notifying a parent so come up with the new mask which * specifies these are events which came from a child. */ mask |= FS_EVENT_ON_CHILD; + take_dentry_name_snapshot(&name, dentry); if (path) ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, - dentry->d_name.name, 0); + name.name, 0); else ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, - dentry->d_name.name, 0); + name.name, 0); + release_dentry_name_snapshot(&name); } dput(parent); diff --git a/fs/nsfs.c b/fs/nsfs.c index f3db56e83dd2..08127a2b8559 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -53,7 +53,6 @@ static void nsfs_evict(struct inode *inode) static void *__ns_get_path(struct path *path, struct ns_common *ns) { struct vfsmount *mnt = nsfs_mnt; - struct qstr qname = { .name = "", }; struct dentry *dentry; struct inode *inode; unsigned long d; @@ -85,7 +84,7 @@ slow: inode->i_fop = &ns_file_operations; inode->i_private = ns; - dentry = d_alloc_pseudo(mnt->mnt_sb, &qname); + dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name); if (!dentry) { iput(inode); return ERR_PTR(-ENOMEM); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 0ee19ecc982d..1a24be9e8405 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1506,7 +1506,7 @@ static int ntfs_dir_fsync(struct file *filp, loff_t start, loff_t end, ntfs_debug("Entering for inode 0x%lx.", vi->i_ino); - err = filemap_write_and_wait_range(vi->i_mapping, start, end); + err = file_write_and_wait_range(filp, start, end); if (err) return err; inode_lock(vi); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index c4f68c338735..331910fa8442 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1989,7 +1989,7 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, ntfs_debug("Entering for inode 0x%lx.", vi->i_ino); - err = filemap_write_and_wait_range(vi->i_mapping, start, end); + err = file_write_and_wait_range(filp, start, end); if (err) return err; inode_lock(vi); diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index ecb49870a680..3f70f041dbe9 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -487,7 +487,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) * When remounting read-only, mark the volume clean if no volume errors * have occurred. */ - if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) { + if (sb_rdonly(sb) && !(*flags & MS_RDONLY)) { static const char *es = ". Cannot remount read-write."; /* Remounting read-write. */ @@ -548,7 +548,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) NVolSetErrors(vol); return -EROFS; } - } else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) { + } else if (!sb_rdonly(sb) && (*flags & MS_RDONLY)) { /* Remounting read-only. */ if (!NVolErrors(vol)) { if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) @@ -732,7 +732,7 @@ hotfix_primary_boot_sector: * on a large sector device contains the whole boot loader or * just the first 512 bytes). */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { ntfs_warning(sb, "Hot-fix: Recovering invalid primary " "boot sector from backup copy."); memcpy(bh_primary->b_data, bh_backup->b_data, @@ -1789,7 +1789,7 @@ static bool load_system_files(ntfs_volume *vol) static const char *es3 = ". Run ntfsfix and/or chkdsk."; /* If a read-write mount, convert it to a read-only mount. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" @@ -1928,7 +1928,7 @@ get_ctx_vol_failed: (unsigned)le16_to_cpu(vol->vol_flags)); } /* If a read-write mount, convert it to a read-only mount. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" @@ -1961,7 +1961,7 @@ get_ctx_vol_failed: es1 = !vol->logfile_ino ? es1a : es1b; /* If a read-write mount, convert it to a read-only mount. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" @@ -2010,7 +2010,7 @@ get_ctx_vol_failed: es1 = err < 0 ? es1a : es1b; /* If a read-write mount, convert it to a read-only mount. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" @@ -2028,8 +2028,7 @@ get_ctx_vol_failed: NVolSetErrors(vol); } /* If (still) a read-write mount, mark the volume dirty. */ - if (!(sb->s_flags & MS_RDONLY) && - ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) { + if (!sb_rdonly(sb) && ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) { static const char *es1 = "Failed to set dirty bit in volume " "information flags"; static const char *es2 = ". Run chkdsk."; @@ -2075,8 +2074,7 @@ get_ctx_vol_failed: } #endif /* If (still) a read-write mount, empty the logfile. */ - if (!(sb->s_flags & MS_RDONLY) && - !ntfs_empty_logfile(vol->logfile_ino)) { + if (!sb_rdonly(sb) && !ntfs_empty_logfile(vol->logfile_ino)) { static const char *es1 = "Failed to empty $LogFile"; static const char *es2 = ". Mount in Windows."; @@ -2121,7 +2119,7 @@ get_ctx_vol_failed: static const char *es2 = ". Run chkdsk."; /* If a read-write mount, convert it to a read-only mount. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" @@ -2139,8 +2137,7 @@ get_ctx_vol_failed: NVolSetErrors(vol); } /* If (still) a read-write mount, mark the quotas out of date. */ - if (!(sb->s_flags & MS_RDONLY) && - !ntfs_mark_quotas_out_of_date(vol)) { + if (!sb_rdonly(sb) && !ntfs_mark_quotas_out_of_date(vol)) { static const char *es1 = "Failed to mark quotas out of date"; static const char *es2 = ". Run chkdsk."; @@ -2165,7 +2162,7 @@ get_ctx_vol_failed: static const char *es2 = ". Run chkdsk."; /* If a read-write mount, convert it to a read-only mount. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" @@ -2183,7 +2180,7 @@ get_ctx_vol_failed: NVolSetErrors(vol); } /* If (still) a read-write mount, stamp the transaction log. */ - if (!(sb->s_flags & MS_RDONLY) && !ntfs_stamp_usnjrnl(vol)) { + if (!sb_rdonly(sb) && !ntfs_stamp_usnjrnl(vol)) { static const char *es1 = "Failed to stamp transaction log " "($UsnJrnl)"; static const char *es2 = ". Run chkdsk."; @@ -2314,7 +2311,7 @@ static void ntfs_put_super(struct super_block *sb) * If a read-write mount and no volume errors have occurred, mark the * volume clean. Also, re-commit all affected inodes. */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!NVolErrors(vol)) { if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) ntfs_warning(sb, "Failed to clear dirty bit " diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index dc22ba8c710f..40b5cc97f7b0 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -221,7 +221,7 @@ out: /* * Set the access or default ACL of an inode. */ -int ocfs2_set_acl(handle_t *handle, +static int ocfs2_set_acl(handle_t *handle, struct inode *inode, struct buffer_head *di_bh, int type, @@ -240,18 +240,6 @@ int ocfs2_set_acl(handle_t *handle, switch (type) { case ACL_TYPE_ACCESS: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - umode_t mode; - - ret = posix_acl_update_mode(inode, &mode, &acl); - if (ret) - return ret; - - ret = ocfs2_acl_set_mode(inode, di_bh, - handle, mode); - if (ret) - return ret; - } break; case ACL_TYPE_DEFAULT: name_index = OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT; @@ -289,7 +277,19 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh); if (had_lock < 0) return had_lock; + if (type == ACL_TYPE_ACCESS && acl) { + umode_t mode; + + status = posix_acl_update_mode(inode, &mode, &acl); + if (status) + goto unlock; + + status = ocfs2_acl_set_mode(inode, bh, NULL, mode); + if (status) + goto unlock; + } status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL); +unlock: ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); brelse(bh); return status; diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 2783a75b3999..7be0bb756286 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -28,13 +28,6 @@ struct ocfs2_acl_entry { struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type); int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type); -int ocfs2_set_acl(handle_t *handle, - struct inode *inode, - struct buffer_head *di_bh, - int type, - struct posix_acl *acl, - struct ocfs2_alloc_context *meta_ac, - struct ocfs2_alloc_context *data_ac); extern int ocfs2_acl_chmod(struct inode *, struct buffer_head *); extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *, struct buffer_head *, struct buffer_head *, diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index fb15a96df0b6..a177eae3aa1a 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -955,8 +955,7 @@ int ocfs2_read_extent_block(struct ocfs2_caching_info *ci, u64 eb_blkno, /* * How many free extents have we got before we need more meta data? */ -int ocfs2_num_free_extents(struct ocfs2_super *osb, - struct ocfs2_extent_tree *et) +int ocfs2_num_free_extents(struct ocfs2_extent_tree *et) { int retval; struct ocfs2_extent_list *el = NULL; @@ -1933,14 +1932,12 @@ out: * the new changes. * * left_rec: the record on the left. - * left_child_el: is the child list pointed to by left_rec * right_rec: the record to the right of left_rec * right_child_el: is the child list pointed to by right_rec * * By definition, this only works on interior nodes. */ static void ocfs2_adjust_adjacent_records(struct ocfs2_extent_rec *left_rec, - struct ocfs2_extent_list *left_child_el, struct ocfs2_extent_rec *right_rec, struct ocfs2_extent_list *right_child_el) { @@ -2003,7 +2000,7 @@ static void ocfs2_adjust_root_records(struct ocfs2_extent_list *root_el, */ BUG_ON(i >= (le16_to_cpu(root_el->l_next_free_rec) - 1)); - ocfs2_adjust_adjacent_records(&root_el->l_recs[i], left_el, + ocfs2_adjust_adjacent_records(&root_el->l_recs[i], &root_el->l_recs[i + 1], right_el); } @@ -2060,8 +2057,7 @@ static void ocfs2_complete_edge_insert(handle_t *handle, el = right_path->p_node[i].el; right_rec = &el->l_recs[0]; - ocfs2_adjust_adjacent_records(left_rec, left_el, right_rec, - right_el); + ocfs2_adjust_adjacent_records(left_rec, right_rec, right_el); ocfs2_journal_dirty(handle, left_path->p_node[i].bh); ocfs2_journal_dirty(handle, right_path->p_node[i].bh); @@ -2509,7 +2505,7 @@ out_ret_path: static int ocfs2_update_edge_lengths(handle_t *handle, struct ocfs2_extent_tree *et, - int subtree_index, struct ocfs2_path *path) + struct ocfs2_path *path) { int i, idx, ret; struct ocfs2_extent_rec *rec; @@ -2755,8 +2751,7 @@ static int ocfs2_rotate_subtree_left(handle_t *handle, if (del_right_subtree) { ocfs2_unlink_subtree(handle, et, left_path, right_path, subtree_index, dealloc); - ret = ocfs2_update_edge_lengths(handle, et, subtree_index, - left_path); + ret = ocfs2_update_edge_lengths(handle, et, left_path); if (ret) { mlog_errno(ret); goto out; @@ -3060,8 +3055,7 @@ static int ocfs2_remove_rightmost_path(handle_t *handle, ocfs2_unlink_subtree(handle, et, left_path, path, subtree_index, dealloc); - ret = ocfs2_update_edge_lengths(handle, et, subtree_index, - left_path); + ret = ocfs2_update_edge_lengths(handle, et, left_path); if (ret) { mlog_errno(ret); goto out; @@ -4790,7 +4784,7 @@ int ocfs2_add_clusters_in_btree(handle_t *handle, if (mark_unwritten) flags = OCFS2_EXT_UNWRITTEN; - free_extents = ocfs2_num_free_extents(osb, et); + free_extents = ocfs2_num_free_extents(et); if (free_extents < 0) { status = free_extents; mlog_errno(status); @@ -5668,7 +5662,7 @@ static int ocfs2_reserve_blocks_for_rec_trunc(struct inode *inode, *ac = NULL; - num_free_extents = ocfs2_num_free_extents(osb, et); + num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index 4a5152ec88a3..27b75cf32cfa 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -144,8 +144,7 @@ int ocfs2_remove_btree_range(struct inode *inode, struct ocfs2_cached_dealloc_ctxt *dealloc, u64 refcount_loc, bool refcount_tree_locked); -int ocfs2_num_free_extents(struct ocfs2_super *osb, - struct ocfs2_extent_tree *et); +int ocfs2_num_free_extents(struct ocfs2_extent_tree *et); /* * how many new metadata chunks would an allocation need at maximum? diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 0da0332725aa..d0206042d068 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -505,8 +505,7 @@ static inline void o2hb_bio_wait_dec(struct o2hb_bio_wait_ctxt *wc, } } -static void o2hb_wait_on_io(struct o2hb_region *reg, - struct o2hb_bio_wait_ctxt *wc) +static void o2hb_wait_on_io(struct o2hb_bio_wait_ctxt *wc) { o2hb_bio_wait_dec(wc, 1); wait_for_completion(&wc->wc_io_complete); @@ -516,9 +515,9 @@ static void o2hb_bio_end_io(struct bio *bio) { struct o2hb_bio_wait_ctxt *wc = bio->bi_private; - if (bio->bi_error) { - mlog(ML_ERROR, "IO Error %d\n", bio->bi_error); - wc->wc_error = bio->bi_error; + if (bio->bi_status) { + mlog(ML_ERROR, "IO Error %d\n", bio->bi_status); + wc->wc_error = blk_status_to_errno(bio->bi_status); } o2hb_bio_wait_dec(wc, 1); @@ -554,7 +553,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, /* Must put everything in 512 byte sectors for the bio... */ bio->bi_iter.bi_sector = (reg->hr_start_block + cs) << (bits - 9); - bio->bi_bdev = reg->hr_bdev; + bio_set_dev(bio, reg->hr_bdev); bio->bi_private = wc; bio->bi_end_io = o2hb_bio_end_io; bio_set_op_attrs(bio, op, op_flags); @@ -608,7 +607,7 @@ static int o2hb_read_slots(struct o2hb_region *reg, status = 0; bail_and_wait: - o2hb_wait_on_io(reg, &wc); + o2hb_wait_on_io(&wc); if (wc.wc_error && !status) status = wc.wc_error; @@ -1162,7 +1161,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg) * before we can go to steady state. This ensures that * people we find in our steady state have seen us. */ - o2hb_wait_on_io(reg, &write_wc); + o2hb_wait_on_io(&write_wc); if (write_wc.wc_error) { /* Do not re-arm the write timeout on I/O error - we * can't be sure that the new block ever made it to @@ -1275,7 +1274,7 @@ static int o2hb_thread(void *data) o2hb_prepare_block(reg, 0); ret = o2hb_issue_node_write(reg, &write_wc); if (ret == 0) - o2hb_wait_on_io(reg, &write_wc); + o2hb_wait_on_io(&write_wc); else mlog_errno(ret); } @@ -2576,22 +2575,6 @@ void o2hb_unregister_callback(const char *region_uuid, } EXPORT_SYMBOL_GPL(o2hb_unregister_callback); -int o2hb_check_node_heartbeating(u8 node_num) -{ - unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; - - o2hb_fill_node_map(testing_map, sizeof(testing_map)); - if (!test_bit(node_num, testing_map)) { - mlog(ML_HEARTBEAT, - "node (%u) does not have heartbeating enabled.\n", - node_num); - return 0; - } - - return 1; -} -EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating); - int o2hb_check_node_heartbeating_no_sem(u8 node_num) { unsigned long testing_map[BITS_TO_LONGS(O2NM_MAX_NODES)]; @@ -2626,23 +2609,6 @@ int o2hb_check_node_heartbeating_from_callback(u8 node_num) } EXPORT_SYMBOL_GPL(o2hb_check_node_heartbeating_from_callback); -/* Makes sure our local node is configured with a node number, and is - * heartbeating. */ -int o2hb_check_local_node_heartbeating(void) -{ - u8 node_num; - - /* if this node was set then we have networking */ - node_num = o2nm_this_node(); - if (node_num == O2NM_MAX_NODES) { - mlog(ML_HEARTBEAT, "this node has not been configured.\n"); - return 0; - } - - return o2hb_check_node_heartbeating(node_num); -} -EXPORT_SYMBOL_GPL(o2hb_check_local_node_heartbeating); - /* * this is just a hack until we get the plumbing which flips file systems * read only and drops the hb ref instead of killing the node dead. diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index 564c504d6efd..74a21f6695c8 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -426,6 +426,7 @@ static int sc_fop_release(struct inode *inode, struct file *file) struct o2net_sock_container *dummy_sc = sd->dbg_sock; o2net_debug_del_sc(dummy_sc); + kfree(dummy_sc); return seq_release_private(inode, file); } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 3ecb9f337b7d..febe6312ceff 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3249,7 +3249,7 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb, spin_unlock(&OCFS2_I(dir)->ip_lock); ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(dir), parent_fe_bh); - num_free_extents = ocfs2_num_free_extents(osb, &et); + num_free_extents = ocfs2_num_free_extents(&et); if (num_free_extents < 0) { status = num_free_extents; mlog_errno(status); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index bfeb647459d9..6e41fc8fabbe 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -196,7 +196,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return -EROFS; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(file, start, end); if (err) return err; @@ -713,13 +713,6 @@ leave: return status; } -int ocfs2_extend_allocation(struct inode *inode, u32 logical_start, - u32 clusters_to_add, int mark_unwritten) -{ - return __ocfs2_extend_allocation(inode, logical_start, - clusters_to_add, mark_unwritten); -} - /* * While a write will already be ordering the data, a truncate will not. * Thus, we need to explicitly order the zeroed pages. diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 382401d3e88f..1a1e0078ab38 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -136,7 +136,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno) struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags, int sysfile_type) { - int rc = 0; + int rc = -ESTALE; struct inode *inode = NULL; struct super_block *sb = osb->sb; struct ocfs2_find_inode_args args; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index d5e5fa7f0743..36304434eacf 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1348,7 +1348,6 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb) ocfs2_schedule_truncate_log_flush(osb, 0); osb->local_alloc_copy = NULL; - osb->dirty = 0; /* queue to recover orphan slots for all offline slots */ ocfs2_replay_map_set_state(osb, REPLAY_NEEDED); diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index e52a2852d50d..7eb3b0a6347e 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -175,7 +175,7 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - num_free_extents = ocfs2_num_free_extents(osb, et); + num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 0c39d71c67a1..9a50f222ac97 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -320,7 +320,6 @@ struct ocfs2_super u64 system_dir_blkno; u64 bitmap_blkno; u32 bitmap_cpg; - u8 *uuid; char *uuid_str; u32 uuid_hash; u8 *vol_label; @@ -388,9 +387,8 @@ struct ocfs2_super unsigned int osb_resv_level; unsigned int osb_dir_resv_level; - /* Next three fields are for local node slot recovery during + /* Next two fields are for local node slot recovery during * mount. */ - int dirty; struct ocfs2_dinode *local_alloc_copy; struct ocfs2_quota_recovery *quota_rec; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 44d178b8d1aa..5bb4a89f9045 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -25,6 +25,8 @@ #ifndef _OCFS2_FS_H #define _OCFS2_FS_H +#include <linux/magic.h> + /* Version */ #define OCFS2_MAJOR_REV_LEVEL 0 #define OCFS2_MINOR_REV_LEVEL 90 @@ -56,9 +58,6 @@ #define OCFS2_MIN_BLOCKSIZE 512 #define OCFS2_MAX_BLOCKSIZE OCFS2_MIN_CLUSTERSIZE -/* Filesystem magic number */ -#define OCFS2_SUPER_MAGIC 0x7461636f - /* Object signatures */ #define OCFS2_SUPER_BLOCK_SIGNATURE "OCFSV2" #define OCFS2_INODE_SIGNATURE "INODE01" diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index cec495a921e3..c94b6baaa551 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -33,7 +33,7 @@ * Locking of quotas with OCFS2 is rather complex. Here are rules that * should be obeyed by all the functions: * - any write of quota structure (either to local or global file) is protected - * by dqio_mutex or dquot->dq_lock. + * by dqio_sem or dquot->dq_lock. * - any modification of global quota file holds inode cluster lock, i_mutex, * and ip_alloc_sem of the global quota file (achieved by * ocfs2_lock_global_qf). It also has to hold qinfo_lock. @@ -42,9 +42,9 @@ * * A rough sketch of locking dependencies (lf = local file, gf = global file): * Normal filesystem operation: - * start_trans -> dqio_mutex -> write to lf + * start_trans -> dqio_sem -> write to lf * Syncing of local and global file: - * ocfs2_lock_global_qf -> start_trans -> dqio_mutex -> qinfo_lock -> + * ocfs2_lock_global_qf -> start_trans -> dqio_sem -> qinfo_lock -> * write to gf * -> write to lf * Acquire dquot for the first time: @@ -60,7 +60,7 @@ * Recovery: * inode cluster lock of recovered lf * -> read bitmaps -> ip_alloc_sem of lf - * -> ocfs2_lock_global_qf -> start_trans -> dqio_mutex -> qinfo_lock -> + * -> ocfs2_lock_global_qf -> start_trans -> dqio_sem -> qinfo_lock -> * write to gf */ @@ -443,13 +443,17 @@ static int __ocfs2_global_write_info(struct super_block *sb, int type) int ocfs2_global_write_info(struct super_block *sb, int type) { int err; - struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv; + struct quota_info *dqopt = sb_dqopt(sb); + struct ocfs2_mem_dqinfo *info = dqopt->info[type].dqi_priv; + down_write(&dqopt->dqio_sem); err = ocfs2_qinfo_lock(info, 1); if (err < 0) - return err; + goto out_sem; err = __ocfs2_global_write_info(sb, type); ocfs2_qinfo_unlock(info, 1); +out_sem: + up_write(&dqopt->dqio_sem); return err; } @@ -500,7 +504,7 @@ int __ocfs2_sync_dquot(struct dquot *dquot, int freeing) /* Update space and inode usage. Get also other information from * global quota file so that we don't overwrite any changes there. * We are */ - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); spacechange = dquot->dq_dqb.dqb_curspace - OCFS2_DQUOT(dquot)->dq_origspace; inodechange = dquot->dq_dqb.dqb_curinodes - @@ -556,7 +560,7 @@ int __ocfs2_sync_dquot(struct dquot *dquot, int freeing) __clear_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags); OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace; OCFS2_DQUOT(dquot)->dq_originodes = dquot->dq_dqb.dqb_curinodes; - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); err = ocfs2_qinfo_lock(info, freeing); if (err < 0) { mlog(ML_ERROR, "Failed to lock quota info, losing quota write" @@ -611,7 +615,7 @@ static int ocfs2_sync_dquot_helper(struct dquot *dquot, unsigned long type) mlog_errno(status); goto out_ilock; } - mutex_lock(&sb_dqopt(sb)->dqio_mutex); + down_write(&sb_dqopt(sb)->dqio_sem); status = ocfs2_sync_dquot(dquot); if (status < 0) mlog_errno(status); @@ -619,7 +623,7 @@ static int ocfs2_sync_dquot_helper(struct dquot *dquot, unsigned long type) status = ocfs2_local_write_dquot(dquot); if (status < 0) mlog_errno(status); - mutex_unlock(&sb_dqopt(sb)->dqio_mutex); + up_write(&sb_dqopt(sb)->dqio_sem); ocfs2_commit_trans(osb, handle); out_ilock: ocfs2_unlock_global_qf(oinfo, 1); @@ -666,9 +670,9 @@ static int ocfs2_write_dquot(struct dquot *dquot) mlog_errno(status); goto out; } - mutex_lock(&sb_dqopt(dquot->dq_sb)->dqio_mutex); + down_write(&sb_dqopt(dquot->dq_sb)->dqio_sem); status = ocfs2_local_write_dquot(dquot); - mutex_unlock(&sb_dqopt(dquot->dq_sb)->dqio_mutex); + up_write(&sb_dqopt(dquot->dq_sb)->dqio_sem); ocfs2_commit_trans(osb, handle); out: return status; @@ -920,10 +924,10 @@ static int ocfs2_mark_dquot_dirty(struct dquot *dquot) /* In case user set some limits, sync dquot immediately to global * quota file so that information propagates quicker */ - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); if (dquot->dq_flags & mask) sync = 1; - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); /* This is a slight hack but we can't afford getting global quota * lock if we already have a transaction started. */ if (!sync || journal_current_handle()) { @@ -939,7 +943,7 @@ static int ocfs2_mark_dquot_dirty(struct dquot *dquot) mlog_errno(status); goto out_ilock; } - mutex_lock(&sb_dqopt(sb)->dqio_mutex); + down_write(&sb_dqopt(sb)->dqio_sem); status = ocfs2_sync_dquot(dquot); if (status < 0) { mlog_errno(status); @@ -948,7 +952,7 @@ static int ocfs2_mark_dquot_dirty(struct dquot *dquot) /* Now write updated local dquot structure */ status = ocfs2_local_write_dquot(dquot); out_dlock: - mutex_unlock(&sb_dqopt(sb)->dqio_mutex); + up_write(&sb_dqopt(sb)->dqio_sem); ocfs2_commit_trans(osb, handle); out_ilock: ocfs2_unlock_global_qf(oinfo, 1); diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 32c5a40c1257..aa700fd10610 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -520,8 +520,8 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode, mlog_errno(status); goto out_drop_lock; } - mutex_lock(&sb_dqopt(sb)->dqio_mutex); - spin_lock(&dq_data_lock); + down_write(&sb_dqopt(sb)->dqio_sem); + spin_lock(&dquot->dq_dqb_lock); /* Add usage from quota entry into quota changes * of our node. Auxiliary variables are important * due to signedness */ @@ -529,7 +529,7 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode, inodechange = le64_to_cpu(dqblk->dqb_inodemod); dquot->dq_dqb.dqb_curspace += spacechange; dquot->dq_dqb.dqb_curinodes += inodechange; - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); /* We want to drop reference held by the crashed * node. Since we have our own reference we know * global structure actually won't be freed. */ @@ -553,7 +553,7 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode, unlock_buffer(qbh); ocfs2_journal_dirty(handle, qbh); out_commit: - mutex_unlock(&sb_dqopt(sb)->dqio_mutex); + up_write(&sb_dqopt(sb)->dqio_sem); ocfs2_commit_trans(OCFS2_SB(sb), handle); out_drop_lock: ocfs2_unlock_global_qf(oinfo, 1); @@ -691,9 +691,6 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) struct ocfs2_quota_recovery *rec; int locked = 0; - /* We don't need the lock and we have to acquire quota file locks - * which will later depend on this lock */ - mutex_unlock(&sb_dqopt(sb)->dqio_mutex); info->dqi_max_spc_limit = 0x7fffffffffffffffLL; info->dqi_max_ino_limit = 0x7fffffffffffffffLL; oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS); @@ -772,7 +769,6 @@ static int ocfs2_local_read_info(struct super_block *sb, int type) goto out_err; } - mutex_lock(&sb_dqopt(sb)->dqio_mutex); return 0; out_err: if (oinfo) { @@ -786,7 +782,6 @@ out_err: kfree(oinfo); } brelse(bh); - mutex_lock(&sb_dqopt(sb)->dqio_mutex); return -1; } @@ -882,12 +877,12 @@ static void olq_set_dquot(struct buffer_head *bh, void *private) dqblk->dqb_id = cpu_to_le64(from_kqid(&init_user_ns, od->dq_dquot.dq_id)); - spin_lock(&dq_data_lock); + spin_lock(&od->dq_dquot.dq_dqb_lock); dqblk->dqb_spacemod = cpu_to_le64(od->dq_dquot.dq_dqb.dqb_curspace - od->dq_origspace); dqblk->dqb_inodemod = cpu_to_le64(od->dq_dquot.dq_dqb.dqb_curinodes - od->dq_originodes); - spin_unlock(&dq_data_lock); + spin_unlock(&od->dq_dquot.dq_dqb_lock); trace_olq_set_dquot( (unsigned long long)le64_to_cpu(dqblk->dqb_spacemod), (unsigned long long)le64_to_cpu(dqblk->dqb_inodemod), diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index f8933cb53d68..ab156e35ec00 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2851,7 +2851,7 @@ static int ocfs2_lock_refcount_allocators(struct super_block *sb, int *credits) { int ret = 0, meta_add = 0; - int num_free_extents = ocfs2_num_free_extents(OCFS2_SB(sb), et); + int num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 820359096c7a..d6c350ba25b9 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -631,7 +631,7 @@ static struct attribute *ocfs2_attrs[] = { NULL, }; -static struct attribute_group ocfs2_attr_group = { +static const struct attribute_group ocfs2_attr_group = { .attrs = ocfs2_attrs, }; diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 6ad3533940ba..71f22c8fbffd 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2700,7 +2700,7 @@ int ocfs2_lock_allocators(struct inode *inode, BUG_ON(clusters_to_add != 0 && data_ac == NULL); - num_free_extents = ocfs2_num_free_extents(osb, et); + num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index ca1646fbcaef..80733496b22a 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -675,7 +675,7 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data) } /* We're going to/from readonly mode. */ - if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) { + if ((bool)(*flags & MS_RDONLY) != sb_rdonly(sb)) { /* Disable quota accounting before remounting RO */ if (*flags & MS_RDONLY) { ret = ocfs2_susp_quotas(osb, 0); @@ -1063,7 +1063,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) /* Hard readonly mode only if: bdev_read_only, MS_RDONLY, * heartbeat=none */ if (bdev_read_only(sb->s_bdev)) { - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { status = -EACCES; mlog(ML_ERROR, "Readonly device detected but readonly " "mount was not specified.\n"); @@ -1098,7 +1098,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) } if (!ocfs2_is_hard_readonly(osb)) { - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) ocfs2_set_ro_flag(osb, 0); } @@ -1179,7 +1179,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) /* Now we can initialize quotas because we can afford to wait * for cluster locks recovery now. That also means that truncation * log recovery can happen but that waits for proper quota setup */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { status = ocfs2_enable_quotas(osb); if (status < 0) { /* We have to err-out specially here because @@ -2062,7 +2062,7 @@ static int ocfs2_initialize_super(struct super_block *sb, cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits); bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits); sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits); - memcpy(sb->s_uuid, di->id2.i_super.s_uuid, + memcpy(&sb->s_uuid, di->id2.i_super.s_uuid, sizeof(di->id2.i_super.s_uuid)); osb->osb_dx_mask = (1 << (cbits - bbits)) - 1; @@ -2180,8 +2180,7 @@ static int ocfs2_initialize_super(struct super_block *sb, status = -EINVAL; goto bail; } - if (!(osb->sb->s_flags & MS_RDONLY) && - (i = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP))) { + if (!sb_rdonly(osb->sb) && (i = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP))) { mlog(ML_ERROR, "couldn't mount RDWR because of " "unsupported optional features (%x).\n", i); status = -EINVAL; @@ -2486,7 +2485,6 @@ static int ocfs2_check_volume(struct ocfs2_super *osb) if (dirty) { /* Recovery will be completed after we've mounted the * rest of the volume. */ - osb->dirty = 1; osb->local_alloc_copy = local_alloc; local_alloc = NULL; } @@ -2568,9 +2566,7 @@ static int ocfs2_handle_error(struct super_block *sb) rv = -EIO; } else { /* default option */ rv = -EROFS; - if (sb->s_flags & MS_RDONLY && - (ocfs2_is_soft_readonly(osb) || - ocfs2_is_hard_readonly(osb))) + if (sb_rdonly(sb) && (ocfs2_is_soft_readonly(osb) || ocfs2_is_hard_readonly(osb))) return rv; pr_crit("OCFS2: File system is now read-only.\n"); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index f70c3778d600..5fdf269ba82e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -6800,7 +6800,7 @@ static int ocfs2_lock_reflink_xattr_rec_allocators( *credits += 1; /* count in the xattr tree change. */ - num_free_extents = ocfs2_num_free_extents(osb, xt_et); + num_free_extents = ocfs2_num_free_extents(xt_et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index 8c9034ee7383..ee14af9e26f2 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -13,6 +13,7 @@ #include <linux/buffer_head.h> #include <linux/vmalloc.h> #include <linux/writeback.h> +#include <linux/seq_file.h> #include <linux/crc-itu-t.h> #include "omfs.h" @@ -290,12 +291,40 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf) return 0; } +/* + * Display the mount options in /proc/mounts. + */ +static int omfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct omfs_sb_info *sbi = OMFS_SB(root->d_sb); + umode_t cur_umask = current_umask(); + + if (!uid_eq(sbi->s_uid, current_uid())) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, sbi->s_uid)); + if (!gid_eq(sbi->s_gid, current_gid())) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, sbi->s_gid)); + + if (sbi->s_dmask == sbi->s_fmask) { + if (sbi->s_fmask != cur_umask) + seq_printf(m, ",umask=%o", sbi->s_fmask); + } else { + if (sbi->s_dmask != cur_umask) + seq_printf(m, ",dmask=%o", sbi->s_dmask); + if (sbi->s_fmask != cur_umask) + seq_printf(m, ",fmask=%o", sbi->s_fmask); + } + + return 0; +} + static const struct super_operations omfs_sops = { .write_inode = omfs_write_inode, .evict_inode = omfs_evict_inode, .put_super = omfs_put_super, .statfs = omfs_statfs, - .show_options = generic_show_options, + .show_options = omfs_show_options, }; /* @@ -434,8 +463,6 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *root; int ret = -EINVAL; - save_mount_options(sb, (char *) data); - sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; diff --git a/fs/open.c b/fs/open.c index cd0c5be8d012..7ea118471dce 100644 --- a/fs/open.c +++ b/fs/open.c @@ -96,7 +96,7 @@ long vfs_truncate(const struct path *path, loff_t length) * write access on the upper inode, not on the overlay inode. For * non-overlay filesystems d_real() is an identity function. */ - upperdentry = d_real(path->dentry, NULL, O_WRONLY); + upperdentry = d_real(path->dentry, NULL, O_WRONLY, 0); error = PTR_ERR(upperdentry); if (IS_ERR(upperdentry)) goto mnt_drop_write_and_out; @@ -670,12 +670,12 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) if (!f.file) goto out; - error = mnt_want_write_file(f.file); + error = mnt_want_write_file_path(f.file); if (error) goto out_fput; audit_file(f.file); error = chown_common(&f.file->f_path, user, group); - mnt_drop_write_file(f.file); + mnt_drop_write_file_path(f.file); out_fput: fdput(f); out: @@ -707,6 +707,9 @@ static int do_dentry_open(struct file *f, f->f_inode = inode; f->f_mapping = inode->i_mapping; + /* Ensure that we skip any errors that predate opening of the file */ + f->f_wb_err = filemap_sample_wb_err(f->f_mapping); + if (unlikely(f->f_flags & O_PATH)) { f->f_mode = FMODE_PATH; f->f_op = &empty_fops; @@ -759,6 +762,7 @@ static int do_dentry_open(struct file *f, likely(f->f_op->write || f->f_op->write_iter)) f->f_mode |= FMODE_CAN_WRITE; + f->f_write_hint = WRITE_LIFE_NOT_SET; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); @@ -853,7 +857,7 @@ EXPORT_SYMBOL(file_path); int vfs_open(const struct path *path, struct file *file, const struct cred *cred) { - struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags); + struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index 7a3754488312..9108ef433e6d 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -35,7 +35,7 @@ struct posix_acl *orangefs_get_acl(struct inode *inode, int type) * I don't do that for now. */ value = kmalloc(ORANGEFS_MAX_XATTR_VALUELEN, GFP_KERNEL); - if (value == NULL) + if (!value) return ERR_PTR(-ENOMEM); gossip_debug(GOSSIP_ACL_DEBUG, @@ -61,9 +61,9 @@ struct posix_acl *orangefs_get_acl(struct inode *inode, int type) return acl; } -int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +static int __orangefs_set_acl(struct inode *inode, struct posix_acl *acl, + int type) { - struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); int error = 0; void *value = NULL; size_t size = 0; @@ -72,22 +72,6 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - umode_t mode; - - error = posix_acl_update_mode(inode, &mode, &acl); - if (error) { - gossip_err("%s: posix_acl_update_mode err: %d\n", - __func__, - error); - return error; - } - - if (inode->i_mode != mode) - SetModeFlag(orangefs_inode); - inode->i_mode = mode; - mark_inode_dirty_sync(inode); - } break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; @@ -132,6 +116,42 @@ out: return error; } +int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int error; + struct iattr iattr; + int rc; + + if (type == ACL_TYPE_ACCESS && acl) { + /* + * posix_acl_update_mode checks to see if the permissions + * described by the ACL can be encoded into the + * object's mode. If so, it sets "acl" to NULL + * and "mode" to the new desired value. It is up to + * us to propagate the new mode back to the server... + */ + error = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); + if (error) { + gossip_err("%s: posix_acl_update_mode err: %d\n", + __func__, + error); + return error; + } + + if (acl) { + rc = __orangefs_set_acl(inode, acl, type); + } else { + iattr.ia_valid = ATTR_MODE; + rc = orangefs_inode_setattr(inode, &iattr); + } + + return rc; + + } else { + return -EINVAL; + } +} + int orangefs_init_acl(struct inode *inode, struct inode *dir) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); @@ -146,13 +166,14 @@ int orangefs_init_acl(struct inode *inode, struct inode *dir) return error; if (default_acl) { - error = orangefs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __orangefs_set_acl(inode, default_acl, + ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!error) - error = orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); } diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index c19f0787c9c6..2826859bdc2c 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -461,13 +461,10 @@ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb, if (op->downcall.type != ORANGEFS_VFS_OP_READDIR) goto wakeup; - op->downcall.trailer_buf = - vmalloc(op->downcall.trailer_size); - if (op->downcall.trailer_buf == NULL) { - gossip_err("%s: failed trailer vmalloc.\n", - __func__); + op->downcall.trailer_buf = vmalloc(op->downcall.trailer_size); + if (!op->downcall.trailer_buf) goto Enomem; - } + memset(op->downcall.trailer_buf, 0, op->downcall.trailer_size); if (!copy_from_iter_full(op->downcall.trailer_buf, op->downcall.trailer_size, iter)) { diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index 28f38d813ad2..336ecbf8c268 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -646,14 +646,11 @@ static int orangefs_fsync(struct file *file, loff_t end, int datasync) { - int ret = -EINVAL; + int ret; struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(file_inode(file)); struct orangefs_kernel_op_s *new_op = NULL; - /* required call */ - filemap_write_and_wait_range(file->f_mapping, start, end); - new_op = op_alloc(ORANGEFS_VFS_OP_FSYNC); if (!new_op) return -ENOMEM; diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c index 83b506020718..7ef473f3d642 100644 --- a/fs/orangefs/orangefs-bufmap.c +++ b/fs/orangefs/orangefs-bufmap.c @@ -46,8 +46,8 @@ static void run_down(struct slot_map *m) spin_lock(&m->q.lock); if (m->c != -1) { for (;;) { - if (likely(list_empty(&wait.task_list))) - __add_wait_queue_tail(&m->q, &wait); + if (likely(list_empty(&wait.entry))) + __add_wait_queue_entry_tail(&m->q, &wait); set_current_state(TASK_UNINTERRUPTIBLE); if (m->c == -1) @@ -84,8 +84,8 @@ static int wait_for_free(struct slot_map *m) do { long n = left, t; - if (likely(list_empty(&wait.task_list))) - __add_wait_queue_tail_exclusive(&m->q, &wait); + if (likely(list_empty(&wait.entry))) + __add_wait_queue_entry_tail_exclusive(&m->q, &wait); set_current_state(TASK_INTERRUPTIBLE); if (m->c > 0) @@ -108,8 +108,8 @@ static int wait_for_free(struct slot_map *m) left = -EINTR; } while (left > 0); - if (!list_empty(&wait.task_list)) - list_del(&wait.task_list); + if (!list_empty(&wait.entry)) + list_del(&wait.entry); else if (left <= 0 && waitqueue_active(&m->q)) __wake_up_locked_key(&m->q, TASK_INTERRUPTIBLE, NULL); __set_current_state(TASK_RUNNING); @@ -244,20 +244,14 @@ orangefs_bufmap_alloc(struct ORANGEFS_dev_map_desc *user_desc) bufmap->buffer_index_array = kzalloc(DIV_ROUND_UP(bufmap->desc_count, BITS_PER_LONG), GFP_KERNEL); - if (!bufmap->buffer_index_array) { - gossip_err("orangefs: could not allocate %d buffer indices\n", - bufmap->desc_count); + if (!bufmap->buffer_index_array) goto out_free_bufmap; - } bufmap->desc_array = kcalloc(bufmap->desc_count, sizeof(struct orangefs_bufmap_desc), GFP_KERNEL); - if (!bufmap->desc_array) { - gossip_err("orangefs: could not allocate %d descriptors\n", - bufmap->desc_count); + if (!bufmap->desc_array) goto out_free_index_array; - } bufmap->page_count = bufmap->total_size / PAGE_SIZE; diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 716ed337f166..5f59917fd631 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -571,11 +571,8 @@ static int orangefs_prepare_cdm_array(char *debug_array_string) goto out; } - cdm_array = - kzalloc(cdm_element_count * sizeof(struct client_debug_mask), - GFP_KERNEL); + cdm_array = kcalloc(cdm_element_count, sizeof(*cdm_array), GFP_KERNEL); if (!cdm_array) { - pr_info("malloc failed for cdm_array!\n"); rc = -ENOMEM; goto out; } diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index c1b5174cb5a9..85ef87245a87 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -98,7 +98,6 @@ static int __init orangefs_init(void) orangefs_htable_ops_in_progress = kcalloc(hash_table_size, sizeof(struct list_head), GFP_KERNEL); if (!orangefs_htable_ops_in_progress) { - gossip_err("Failed to initialize op hashtable"); ret = -ENOMEM; goto cleanup_inode; } diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 5c7c273e17ec..47f3fb9cbec4 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -35,6 +35,19 @@ static const match_table_t tokens = { uint64_t orangefs_features; +static int orangefs_show_options(struct seq_file *m, struct dentry *root) +{ + struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(root->d_sb); + + if (root->d_sb->s_flags & MS_POSIXACL) + seq_puts(m, ",acl"); + if (orangefs_sb->flags & ORANGEFS_OPT_INTR) + seq_puts(m, ",intr"); + if (orangefs_sb->flags & ORANGEFS_OPT_LOCAL_LOCK) + seq_puts(m, ",local_lock"); + return 0; +} + static int parse_mount_options(struct super_block *sb, char *options, int silent) { @@ -94,10 +107,8 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb) struct orangefs_inode_s *orangefs_inode; orangefs_inode = kmem_cache_alloc(orangefs_inode_cache, GFP_KERNEL); - if (orangefs_inode == NULL) { - gossip_err("Failed to allocate orangefs_inode\n"); + if (!orangefs_inode) return NULL; - } /* * We want to clear everything except for rw_semaphore and the @@ -305,7 +316,7 @@ static const struct super_operations orangefs_s_ops = { .drop_inode = generic_delete_inode, .statfs = orangefs_statfs, .remount_fs = orangefs_remount_fs, - .show_options = generic_show_options, + .show_options = orangefs_show_options, }; static struct dentry *orangefs_fh_to_dentry(struct super_block *sb, diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 237c9c04dc3b..81ac88bb91ff 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -76,7 +76,7 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name, if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; - if (strlen(name) > ORANGEFS_MAX_XATTR_NAMELEN) + if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) return -EINVAL; fsuid = from_kuid(&init_user_ns, current_fsuid()); @@ -169,7 +169,7 @@ static int orangefs_inode_removexattr(struct inode *inode, const char *name, struct orangefs_kernel_op_s *new_op = NULL; int ret = -ENOMEM; - if (strlen(name) > ORANGEFS_MAX_XATTR_NAMELEN) + if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) return -EINVAL; down_write(&orangefs_inode->xattr_sem); @@ -233,13 +233,13 @@ int orangefs_inode_setxattr(struct inode *inode, const char *name, if (size > ORANGEFS_MAX_XATTR_VALUELEN) return -EINVAL; - if (strlen(name) > ORANGEFS_MAX_XATTR_NAMELEN) + if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) return -EINVAL; internal_flag = convert_to_internal_xattr_flags(flags); /* This is equivalent to a removexattr */ - if (size == 0 && value == NULL) { + if (size == 0 && !value) { gossip_debug(GOSSIP_XATTR_DEBUG, "removing xattr (%s)\n", name); @@ -311,7 +311,7 @@ ssize_t orangefs_listxattr(struct dentry *dentry, char *buffer, size_t size) int i = 0; int returned_count = 0; - if (size > 0 && buffer == NULL) { + if (size > 0 && !buffer) { gossip_err("%s: bogus NULL pointers\n", __func__); return -EINVAL; } @@ -442,7 +442,7 @@ static int orangefs_xattr_get_default(const struct xattr_handler *handler, } -static struct xattr_handler orangefs_xattr_default_handler = { +static const struct xattr_handler orangefs_xattr_default_handler = { .prefix = "", /* match any name => handlers called with full name */ .get = orangefs_xattr_get_default, .set = orangefs_xattr_set_default, diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index c0c9683934b7..cbfc196e5dc5 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -23,3 +23,23 @@ config OVERLAY_FS_REDIRECT_DIR Note, that redirects are not backward compatible. That is, mounting an overlay which has redirects on a kernel that doesn't support this feature will have unexpected results. + +config OVERLAY_FS_INDEX + bool "Overlayfs: turn on inodes index feature by default" + depends on OVERLAY_FS + help + If this config option is enabled then overlay filesystems will use + the inodes index dir to map lower inodes to upper inodes by default. + In this case it is still possible to turn off index globally with the + "index=off" module option or on a filesystem instance basis with the + "index=off" mount option. + + The inodes index feature prevents breaking of lower hardlinks on copy + up. + + Note, that the inodes index feature is read-only backward compatible. + That is, mounting an overlay which has an index dir on a kernel that + doesn't support this feature read-only, will not have any negative + outcomes. However, mounting the same overlay with an old kernel + read-write and then mounting it again with a new kernel, will have + unexpected results. diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index a2a65120c9d0..c441f9387a1b 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -233,14 +233,15 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat) return err; } -static struct ovl_fh *ovl_encode_fh(struct dentry *lower, uuid_be *uuid) +struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper) { struct ovl_fh *fh; int fh_type, fh_len, dwords; void *buf; int buflen = MAX_HANDLE_SZ; + uuid_t *uuid = &lower->d_sb->s_uuid; - buf = kmalloc(buflen, GFP_TEMPORARY); + buf = kmalloc(buflen, GFP_KERNEL); if (!buf) return ERR_PTR(-ENOMEM); @@ -271,6 +272,14 @@ static struct ovl_fh *ovl_encode_fh(struct dentry *lower, uuid_be *uuid) fh->magic = OVL_FH_MAGIC; fh->type = fh_type; fh->flags = OVL_FH_FLAG_CPU_ENDIAN; + /* + * When we will want to decode an overlay dentry from this handle + * and all layers are on the same fs, if we get a disconncted real + * dentry when we decode fid, the only way to tell if we should assign + * it to upperdentry or to lowerstack is by checking this flag. + */ + if (is_upper) + fh->flags |= OVL_FH_FLAG_PATH_UPPER; fh->len = fh_len; fh->uuid = *uuid; memcpy(fh->fid, buf, buflen); @@ -283,8 +292,6 @@ out: static int ovl_set_origin(struct dentry *dentry, struct dentry *lower, struct dentry *upper) { - struct super_block *sb = lower->d_sb; - uuid_be *uuid = (uuid_be *) &sb->s_uuid; const struct ovl_fh *fh = NULL; int err; @@ -293,9 +300,8 @@ static int ovl_set_origin(struct dentry *dentry, struct dentry *lower, * so we can use the overlay.origin xattr to distignuish between a copy * up and a pure upper inode. */ - if (sb->s_export_op && sb->s_export_op->fh_to_dentry && - uuid_be_cmp(*uuid, NULL_UUID_BE)) { - fh = ovl_encode_fh(lower, uuid); + if (ovl_can_decode_fh(lower->d_sb)) { + fh = ovl_encode_fh(lower, false); if (IS_ERR(fh)) return PTR_ERR(fh); } @@ -310,84 +316,156 @@ static int ovl_set_origin(struct dentry *dentry, struct dentry *lower, return err; } -static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, - struct dentry *dentry, struct path *lowerpath, - struct kstat *stat, const char *link, - struct kstat *pstat, bool tmpfile) +struct ovl_copy_up_ctx { + struct dentry *parent; + struct dentry *dentry; + struct path lowerpath; + struct kstat stat; + struct kstat pstat; + const char *link; + struct dentry *destdir; + struct qstr destname; + struct dentry *workdir; + bool tmpfile; + bool origin; +}; + +static int ovl_link_up(struct ovl_copy_up_ctx *c) +{ + int err; + struct dentry *upper; + struct dentry *upperdir = ovl_dentry_upper(c->parent); + struct inode *udir = d_inode(upperdir); + + /* Mark parent "impure" because it may now contain non-pure upper */ + err = ovl_set_impure(c->parent, upperdir); + if (err) + return err; + + err = ovl_set_nlink_lower(c->dentry); + if (err) + return err; + + inode_lock_nested(udir, I_MUTEX_PARENT); + upper = lookup_one_len(c->dentry->d_name.name, upperdir, + c->dentry->d_name.len); + err = PTR_ERR(upper); + if (!IS_ERR(upper)) { + err = ovl_do_link(ovl_dentry_upper(c->dentry), udir, upper, + true); + dput(upper); + + if (!err) { + /* Restore timestamps on parent (best effort) */ + ovl_set_timestamps(upperdir, &c->pstat); + ovl_dentry_set_upper_alias(c->dentry); + } + } + inode_unlock(udir); + ovl_set_nlink_upper(c->dentry); + + return err; +} + +static int ovl_install_temp(struct ovl_copy_up_ctx *c, struct dentry *temp, + struct dentry **newdentry) +{ + int err; + struct dentry *upper; + struct inode *udir = d_inode(c->destdir); + + upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len); + if (IS_ERR(upper)) + return PTR_ERR(upper); + + if (c->tmpfile) + err = ovl_do_link(temp, udir, upper, true); + else + err = ovl_do_rename(d_inode(c->workdir), temp, udir, upper, 0); + + if (!err) + *newdentry = dget(c->tmpfile ? upper : temp); + dput(upper); + + return err; +} + +static int ovl_get_tmpfile(struct ovl_copy_up_ctx *c, struct dentry **tempp) { - struct inode *wdir = workdir->d_inode; - struct inode *udir = upperdir->d_inode; - struct dentry *newdentry = NULL; - struct dentry *upper = NULL; - struct dentry *temp = NULL; int err; + struct dentry *temp; const struct cred *old_creds = NULL; struct cred *new_creds = NULL; struct cattr cattr = { /* Can't properly set mode on creation because of the umask */ - .mode = stat->mode & S_IFMT, - .rdev = stat->rdev, - .link = link + .mode = c->stat.mode & S_IFMT, + .rdev = c->stat.rdev, + .link = c->link }; - err = security_inode_copy_up(dentry, &new_creds); + err = security_inode_copy_up(c->dentry, &new_creds); if (err < 0) goto out; if (new_creds) old_creds = override_creds(new_creds); - if (tmpfile) - temp = ovl_do_tmpfile(upperdir, stat->mode); - else - temp = ovl_lookup_temp(workdir); - err = 0; - if (IS_ERR(temp)) { - err = PTR_ERR(temp); - temp = NULL; + if (c->tmpfile) { + temp = ovl_do_tmpfile(c->workdir, c->stat.mode); + if (IS_ERR(temp)) + goto temp_err; + } else { + temp = ovl_lookup_temp(c->workdir); + if (IS_ERR(temp)) + goto temp_err; + + err = ovl_create_real(d_inode(c->workdir), temp, &cattr, + NULL, true); + if (err) { + dput(temp); + goto out; + } } - - if (!err && !tmpfile) - err = ovl_create_real(wdir, temp, &cattr, NULL, true); - + err = 0; + *tempp = temp; +out: if (new_creds) { revert_creds(old_creds); put_cred(new_creds); } - if (err) - goto out; + return err; - if (S_ISREG(stat->mode)) { +temp_err: + err = PTR_ERR(temp); + goto out; +} + +static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp) +{ + int err; + + if (S_ISREG(c->stat.mode)) { struct path upperpath; - ovl_path_upper(dentry, &upperpath); + ovl_path_upper(c->dentry, &upperpath); BUG_ON(upperpath.dentry != NULL); upperpath.dentry = temp; - if (tmpfile) { - inode_unlock(udir); - err = ovl_copy_up_data(lowerpath, &upperpath, - stat->size); - inode_lock_nested(udir, I_MUTEX_PARENT); - } else { - err = ovl_copy_up_data(lowerpath, &upperpath, - stat->size); - } - + err = ovl_copy_up_data(&c->lowerpath, &upperpath, c->stat.size); if (err) - goto out_cleanup; + return err; } - err = ovl_copy_xattr(lowerpath->dentry, temp); + err = ovl_copy_xattr(c->lowerpath.dentry, temp); if (err) - goto out_cleanup; + return err; inode_lock(temp->d_inode); - err = ovl_set_attr(temp, stat); + err = ovl_set_attr(temp, &c->stat); inode_unlock(temp->d_inode); if (err) - goto out_cleanup; + return err; /* * Store identifier of lower inode in upper inode xattr to @@ -396,41 +474,48 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, * Don't set origin when we are breaking the association with a lower * hard link. */ - if (S_ISDIR(stat->mode) || stat->nlink == 1) { - err = ovl_set_origin(dentry, lowerpath->dentry, temp); + if (c->origin) { + err = ovl_set_origin(c->dentry, c->lowerpath.dentry, temp); if (err) - goto out_cleanup; + return err; } - upper = lookup_one_len(dentry->d_name.name, upperdir, - dentry->d_name.len); - if (IS_ERR(upper)) { - err = PTR_ERR(upper); - upper = NULL; - goto out_cleanup; - } + return 0; +} - if (tmpfile) - err = ovl_do_link(temp, udir, upper, true); - else - err = ovl_do_rename(wdir, temp, udir, upper, 0); +static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c) +{ + struct inode *udir = c->destdir->d_inode; + struct dentry *newdentry = NULL; + struct dentry *temp = NULL; + int err; + + err = ovl_get_tmpfile(c, &temp); + if (err) + goto out; + + err = ovl_copy_up_inode(c, temp); if (err) goto out_cleanup; - newdentry = dget(tmpfile ? upper : temp); - ovl_dentry_update(dentry, newdentry); - ovl_inode_update(d_inode(dentry), d_inode(newdentry)); + if (c->tmpfile) { + inode_lock_nested(udir, I_MUTEX_PARENT); + err = ovl_install_temp(c, temp, &newdentry); + inode_unlock(udir); + } else { + err = ovl_install_temp(c, temp, &newdentry); + } + if (err) + goto out_cleanup; - /* Restore timestamps on parent (best effort) */ - ovl_set_timestamps(upperdir, pstat); + ovl_inode_update(d_inode(c->dentry), newdentry); out: dput(temp); - dput(upper); return err; out_cleanup: - if (!tmpfile) - ovl_cleanup(wdir, temp); + if (!c->tmpfile) + ovl_cleanup(d_inode(c->workdir), temp); goto out; } @@ -443,78 +528,117 @@ out_cleanup: * is possible that the copy up will lock the old parent. At that point * the file will have already been copied up anyway. */ +static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) +{ + int err; + struct ovl_fs *ofs = c->dentry->d_sb->s_fs_info; + bool indexed = false; + + if (ovl_indexdir(c->dentry->d_sb) && !S_ISDIR(c->stat.mode) && + c->stat.nlink > 1) + indexed = true; + + if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || indexed) + c->origin = true; + + if (indexed) { + c->destdir = ovl_indexdir(c->dentry->d_sb); + err = ovl_get_index_name(c->lowerpath.dentry, &c->destname); + if (err) + return err; + } else { + /* + * Mark parent "impure" because it may now contain non-pure + * upper + */ + err = ovl_set_impure(c->parent, c->destdir); + if (err) + return err; + } + + /* Should we copyup with O_TMPFILE or with workdir? */ + if (S_ISREG(c->stat.mode) && ofs->tmpfile) { + c->tmpfile = true; + err = ovl_copy_up_locked(c); + } else { + err = ovl_lock_rename_workdir(c->workdir, c->destdir); + if (!err) { + err = ovl_copy_up_locked(c); + unlock_rename(c->workdir, c->destdir); + } + } + + if (indexed) { + if (!err) + ovl_set_flag(OVL_INDEX, d_inode(c->dentry)); + kfree(c->destname.name); + } else if (!err) { + struct inode *udir = d_inode(c->destdir); + + /* Restore timestamps on parent (best effort) */ + inode_lock(udir); + ovl_set_timestamps(c->destdir, &c->pstat); + inode_unlock(udir); + + ovl_dentry_set_upper_alias(c->dentry); + } + + return err; +} + static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, - struct path *lowerpath, struct kstat *stat) + int flags) { - DEFINE_DELAYED_CALL(done); - struct dentry *workdir = ovl_workdir(dentry); int err; - struct kstat pstat; + DEFINE_DELAYED_CALL(done); struct path parentpath; - struct dentry *lowerdentry = lowerpath->dentry; - struct dentry *upperdir; - const char *link = NULL; - struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct ovl_copy_up_ctx ctx = { + .parent = parent, + .dentry = dentry, + .workdir = ovl_workdir(dentry), + }; - if (WARN_ON(!workdir)) + if (WARN_ON(!ctx.workdir)) return -EROFS; - ovl_do_check_copy_up(lowerdentry); - - ovl_path_upper(parent, &parentpath); - upperdir = parentpath.dentry; - - /* Mark parent "impure" because it may now contain non-pure upper */ - err = ovl_set_impure(parent, upperdir); + ovl_path_lower(dentry, &ctx.lowerpath); + err = vfs_getattr(&ctx.lowerpath, &ctx.stat, + STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (err) return err; - err = vfs_getattr(&parentpath, &pstat, + ovl_path_upper(parent, &parentpath); + ctx.destdir = parentpath.dentry; + ctx.destname = dentry->d_name; + + err = vfs_getattr(&parentpath, &ctx.pstat, STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT); if (err) return err; - if (S_ISLNK(stat->mode)) { - link = vfs_get_link(lowerdentry, &done); - if (IS_ERR(link)) - return PTR_ERR(link); - } - - /* Should we copyup with O_TMPFILE or with workdir? */ - if (S_ISREG(stat->mode) && ofs->tmpfile) { - err = ovl_copy_up_start(dentry); - /* err < 0: interrupted, err > 0: raced with another copy-up */ - if (unlikely(err)) { - pr_debug("ovl_copy_up_start(%pd2) = %i\n", dentry, err); - if (err > 0) - err = 0; - goto out_done; - } - - inode_lock_nested(upperdir->d_inode, I_MUTEX_PARENT); - err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, - stat, link, &pstat, true); - inode_unlock(upperdir->d_inode); - ovl_copy_up_end(dentry); - goto out_done; - } + /* maybe truncate regular file. this has no effect on dirs */ + if (flags & O_TRUNC) + ctx.stat.size = 0; - err = -EIO; - if (lock_rename(workdir, upperdir) != NULL) { - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - goto out_unlock; + if (S_ISLNK(ctx.stat.mode)) { + ctx.link = vfs_get_link(ctx.lowerpath.dentry, &done); + if (IS_ERR(ctx.link)) + return PTR_ERR(ctx.link); } - if (ovl_dentry_upper(dentry)) { - /* Raced with another copy-up? Nothing to do, then... */ - err = 0; - goto out_unlock; + ovl_do_check_copy_up(ctx.lowerpath.dentry); + + err = ovl_copy_up_start(dentry); + /* err < 0: interrupted, err > 0: raced with another copy-up */ + if (unlikely(err)) { + if (err > 0) + err = 0; + } else { + if (!ovl_dentry_upper(dentry)) + err = ovl_do_copy_up(&ctx); + if (!err && !ovl_dentry_has_upper_alias(dentry)) + err = ovl_link_up(&ctx); + ovl_copy_up_end(dentry); } - - err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath, - stat, link, &pstat, false); -out_unlock: - unlock_rename(workdir, upperdir); -out_done: do_delayed_call(&done); return err; @@ -528,11 +652,22 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags) while (!err) { struct dentry *next; struct dentry *parent; - struct path lowerpath; - struct kstat stat; - enum ovl_path_type type = ovl_path_type(dentry); - if (OVL_TYPE_UPPER(type)) + /* + * Check if copy-up has happened as well as for upper alias (in + * case of hard links) is there. + * + * Both checks are lockless: + * - false negatives: will recheck under oi->lock + * - false positives: + * + ovl_dentry_upper() uses memory barriers to ensure the + * upper dentry is up-to-date + * + ovl_dentry_has_upper_alias() relies on locking of + * upper parent i_rwsem to prevent reordering copy-up + * with rename. + */ + if (ovl_dentry_upper(dentry) && + ovl_dentry_has_upper_alias(dentry)) break; next = dget(dentry); @@ -540,22 +675,14 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags) for (;;) { parent = dget_parent(next); - type = ovl_path_type(parent); - if (OVL_TYPE_UPPER(type)) + if (ovl_dentry_upper(parent)) break; dput(next); next = parent; } - ovl_path_lower(next, &lowerpath); - err = vfs_getattr(&lowerpath, &stat, - STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); - /* maybe truncate regular file. this has no effect on dirs */ - if (flags & O_TRUNC) - stat.size = 0; - if (!err) - err = ovl_copy_up_one(parent, next, &lowerpath, &stat); + err = ovl_copy_up_one(parent, next, flags); dput(parent); dput(next); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index a63a71656e9b..cc961a3bd3bd 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -24,7 +24,7 @@ module_param_named(redirect_max, ovl_redirect_max, ushort, 0644); MODULE_PARM_DESC(ovl_redirect_max, "Maximum length of absolute redirect xattr value"); -void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) +int ovl_cleanup(struct inode *wdir, struct dentry *wdentry) { int err; @@ -39,6 +39,8 @@ void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n", wdentry, err); } + + return err; } struct dentry *ovl_lookup_temp(struct dentry *workdir) @@ -153,13 +155,14 @@ static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry) static void ovl_instantiate(struct dentry *dentry, struct inode *inode, struct dentry *newdentry, bool hardlink) { - ovl_dentry_version_inc(dentry->d_parent); - ovl_dentry_update(dentry, newdentry); + ovl_dentry_version_inc(dentry->d_parent, false); + ovl_dentry_set_upper_alias(dentry); if (!hardlink) { - ovl_inode_update(inode, d_inode(newdentry)); + ovl_inode_update(inode, newdentry); ovl_copyattr(newdentry->d_inode, inode); } else { - WARN_ON(ovl_inode_real(inode, NULL) != d_inode(newdentry)); + WARN_ON(ovl_inode_real(inode) != d_inode(newdentry)); + dput(newdentry); inc_nlink(inode); } d_instantiate(dentry, inode); @@ -213,26 +216,6 @@ out_unlock: return err; } -static int ovl_lock_rename_workdir(struct dentry *workdir, - struct dentry *upperdir) -{ - /* Workdir should not be the same as upperdir */ - if (workdir == upperdir) - goto err; - - /* Workdir should not be subdir of upperdir and vice versa */ - if (lock_rename(workdir, upperdir) != NULL) - goto err_unlock; - - return 0; - -err_unlock: - unlock_rename(workdir, upperdir); -err: - pr_err("overlayfs: failed to lock workdir+upperdir\n"); - return -EIO; -} - static struct dentry *ovl_clear_empty(struct dentry *dentry, struct list_head *list) { @@ -478,17 +461,30 @@ out_cleanup: } static int ovl_create_or_link(struct dentry *dentry, struct inode *inode, - struct cattr *attr, struct dentry *hardlink) + struct cattr *attr, struct dentry *hardlink, + bool origin) { int err; const struct cred *old_cred; struct cred *override_cred; + struct dentry *parent = dentry->d_parent; - err = ovl_copy_up(dentry->d_parent); + err = ovl_copy_up(parent); if (err) return err; old_cred = ovl_override_creds(dentry->d_sb); + + /* + * When linking a file with copy up origin into a new parent, mark the + * new parent dir "impure". + */ + if (origin) { + err = ovl_set_impure(parent, ovl_dentry_upper(parent)); + if (err) + goto out_revert_creds; + } + err = -ENOMEM; override_cred = prepare_creds(); if (override_cred) { @@ -547,7 +543,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev, inode_init_owner(inode, dentry->d_parent->d_inode, mode); attr.mode = inode->i_mode; - err = ovl_create_or_link(dentry, inode, &attr, NULL); + err = ovl_create_or_link(dentry, inode, &attr, NULL, false); if (err) iput(inode); @@ -588,6 +584,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir, struct dentry *new) { int err; + bool locked = false; struct inode *inode; err = ovl_want_write(old); @@ -598,19 +595,30 @@ static int ovl_link(struct dentry *old, struct inode *newdir, if (err) goto out_drop_write; + err = ovl_nlink_start(old, &locked); + if (err) + goto out_drop_write; + inode = d_inode(old); ihold(inode); - err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old)); + err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old), + ovl_type_origin(old)); if (err) iput(inode); + ovl_nlink_end(old, locked); out_drop_write: ovl_drop_write(old); out: return err; } +static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper) +{ + return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper); +} + static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) { struct dentry *workdir = ovl_workdir(dentry); @@ -646,7 +654,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) err = -ESTALE; if ((opaquedir && upper != opaquedir) || (!opaquedir && ovl_dentry_upper(dentry) && - upper != ovl_dentry_upper(dentry))) { + !ovl_matches_upper(dentry, upper))) { goto out_dput_upper; } @@ -664,7 +672,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir) if (flags) ovl_cleanup(wdir, upper); - ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_version_inc(dentry->d_parent, true); out_d_drop: d_drop(dentry); dput(whiteout); @@ -707,14 +715,14 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir) err = -ESTALE; if ((opaquedir && upper != opaquedir) || - (!opaquedir && upper != ovl_dentry_upper(dentry))) + (!opaquedir && !ovl_matches_upper(dentry, upper))) goto out_dput_upper; if (is_dir) err = vfs_rmdir(dir, upper); else err = vfs_unlink(dir, upper, NULL); - ovl_dentry_version_inc(dentry->d_parent); + ovl_dentry_version_inc(dentry->d_parent, ovl_type_origin(dentry)); /* * Keeping this dentry hashed would mean having to release @@ -735,8 +743,8 @@ out: static int ovl_do_remove(struct dentry *dentry, bool is_dir) { - enum ovl_path_type type; int err; + bool locked = false; const struct cred *old_cred; err = ovl_want_write(dentry); @@ -747,7 +755,9 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) if (err) goto out_drop_write; - type = ovl_path_type(dentry); + err = ovl_nlink_start(dentry, &locked); + if (err) + goto out_drop_write; old_cred = ovl_override_creds(dentry->d_sb); if (!ovl_lower_positive(dentry)) @@ -761,6 +771,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) else drop_nlink(dentry->d_inode); } + ovl_nlink_end(dentry, locked); out_drop_write: ovl_drop_write(dentry); out: @@ -802,7 +813,7 @@ static char *ovl_get_redirect(struct dentry *dentry, bool samedir) goto out; } - buf = ret = kmalloc(buflen, GFP_TEMPORARY); + buf = ret = kmalloc(buflen, GFP_KERNEL); if (!buf) goto out; @@ -883,6 +894,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, unsigned int flags) { int err; + bool locked = false; struct dentry *old_upperdir; struct dentry *new_upperdir; struct dentry *olddentry; @@ -926,6 +938,10 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, err = ovl_copy_up(new); if (err) goto out_drop_write; + } else { + err = ovl_nlink_start(new, &locked); + if (err) + goto out_drop_write; } old_cred = ovl_override_creds(old->d_sb); @@ -985,7 +1001,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, goto out_unlock; err = -ESTALE; - if (olddentry != ovl_dentry_upper(old)) + if (!ovl_matches_upper(old, olddentry)) goto out_dput_old; newdentry = lookup_one_len(new->d_name.name, new_upperdir, @@ -998,12 +1014,12 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, new_opaque = ovl_dentry_is_opaque(new); err = -ESTALE; - if (ovl_dentry_upper(new)) { + if (d_inode(new) && ovl_dentry_upper(new)) { if (opaquedir) { if (newdentry != opaquedir) goto out_dput; } else { - if (newdentry != ovl_dentry_upper(new)) + if (!ovl_matches_upper(new, newdentry)) goto out_dput; } } else { @@ -1046,8 +1062,16 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, if (cleanup_whiteout) ovl_cleanup(old_upperdir->d_inode, newdentry); - ovl_dentry_version_inc(old->d_parent); - ovl_dentry_version_inc(new->d_parent); + if (overwrite && d_inode(new)) { + if (new_is_dir) + clear_nlink(d_inode(new)); + else + drop_nlink(d_inode(new)); + } + + ovl_dentry_version_inc(old->d_parent, + !overwrite && ovl_type_origin(new)); + ovl_dentry_version_inc(new->d_parent, ovl_type_origin(old)); out_dput: dput(newdentry); @@ -1057,6 +1081,7 @@ out_unlock: unlock_rename(new_upperdir, old_upperdir); out_revert_creds: revert_creds(old_cred); + ovl_nlink_end(new, locked); out_drop_write: ovl_drop_write(old); out: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d613e2c41242..a619addecafc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -12,6 +12,7 @@ #include <linux/cred.h> #include <linux/xattr.h> #include <linux/posix_acl.h> +#include <linux/ratelimit.h> #include "overlayfs.h" int ovl_setattr(struct dentry *dentry, struct iattr *attr) @@ -96,11 +97,15 @@ int ovl_getattr(const struct path *path, struct kstat *stat, WARN_ON_ONCE(stat->dev != lowerstat.dev); /* - * Lower hardlinks are broken on copy up to different + * Lower hardlinks may be broken on copy up to different * upper files, so we cannot use the lower origin st_ino * for those different files, even for the same fs case. + * With inodes index enabled, it is safe to use st_ino + * of an indexed hardlinked origin. The index validates + * that the upper hardlink is not broken. */ - if (is_dir || lowerstat.nlink == 1) + if (is_dir || lowerstat.nlink == 1 || + ovl_test_flag(OVL_INDEX, d_inode(dentry))) stat->ino = lowerstat.ino; } stat->dev = dentry->d_sb->s_dev; @@ -126,6 +131,15 @@ int ovl_getattr(const struct path *path, struct kstat *stat, if (is_dir && OVL_TYPE_MERGE(type)) stat->nlink = 1; + /* + * Return the overlay inode nlinks for indexed upper inodes. + * Overlay inode nlink counts the union of the upper hardlinks + * and non-covered lower hardlinks. It does not include the upper + * index hardlink. + */ + if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry))) + stat->nlink = dentry->d_inode->i_nlink; + out: revert_creds(old_cred); @@ -134,8 +148,8 @@ out: int ovl_permission(struct inode *inode, int mask) { - bool is_upper; - struct inode *realinode = ovl_inode_real(inode, &is_upper); + struct inode *upperinode = ovl_inode_upper(inode); + struct inode *realinode = upperinode ?: ovl_inode_lower(inode); const struct cred *old_cred; int err; @@ -154,7 +168,8 @@ int ovl_permission(struct inode *inode, int mask) return err; old_cred = ovl_override_creds(inode->i_sb); - if (!is_upper && !special_file(realinode->i_mode) && mask & MAY_WRITE) { + if (!upperinode && + !special_file(realinode->i_mode) && mask & MAY_WRITE) { mask &= ~(MAY_WRITE | MAY_APPEND); /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; @@ -187,37 +202,38 @@ bool ovl_is_private_xattr(const char *name) sizeof(OVL_XATTR_PREFIX) - 1) == 0; } -int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) +int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, + const void *value, size_t size, int flags) { int err; - struct path realpath; - enum ovl_path_type type = ovl_path_real(dentry, &realpath); + struct dentry *upperdentry = ovl_i_dentry_upper(inode); + struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry); const struct cred *old_cred; err = ovl_want_write(dentry); if (err) goto out; - if (!value && !OVL_TYPE_UPPER(type)) { - err = vfs_getxattr(realpath.dentry, name, NULL, 0); + if (!value && !upperdentry) { + err = vfs_getxattr(realdentry, name, NULL, 0); if (err < 0) goto out_drop_write; } - err = ovl_copy_up(dentry); - if (err) - goto out_drop_write; + if (!upperdentry) { + err = ovl_copy_up(dentry); + if (err) + goto out_drop_write; - if (!OVL_TYPE_UPPER(type)) - ovl_path_upper(dentry, &realpath); + realdentry = ovl_dentry_upper(dentry); + } old_cred = ovl_override_creds(dentry->d_sb); if (value) - err = vfs_setxattr(realpath.dentry, name, value, size, flags); + err = vfs_setxattr(realdentry, name, value, size, flags); else { WARN_ON(flags != XATTR_REPLACE); - err = vfs_removexattr(realpath.dentry, name); + err = vfs_removexattr(realdentry, name); } revert_creds(old_cred); @@ -227,12 +243,13 @@ out: return err; } -int ovl_xattr_get(struct dentry *dentry, const char *name, +int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size) { - struct dentry *realdentry = ovl_dentry_real(dentry); ssize_t res; const struct cred *old_cred; + struct dentry *realdentry = + ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry); old_cred = ovl_override_creds(dentry->d_sb); res = vfs_getxattr(realdentry, name, value, size); @@ -286,7 +303,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) struct posix_acl *ovl_get_acl(struct inode *inode, int type) { - struct inode *realinode = ovl_inode_real(inode, NULL); + struct inode *realinode = ovl_inode_real(inode); const struct cred *old_cred; struct posix_acl *acl; @@ -300,13 +317,13 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type) return acl; } -static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, - struct dentry *realdentry) +static bool ovl_open_need_copy_up(struct dentry *dentry, int flags) { - if (OVL_TYPE_UPPER(type)) + if (ovl_dentry_upper(dentry) && + ovl_dentry_has_upper_alias(dentry)) return false; - if (special_file(realdentry->d_inode->i_mode)) + if (special_file(d_inode(dentry)->i_mode)) return false; if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC)) @@ -318,11 +335,8 @@ static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type, int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags) { int err = 0; - struct path realpath; - enum ovl_path_type type; - type = ovl_path_real(dentry, &realpath); - if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) { + if (ovl_open_need_copy_up(dentry, file_flags)) { err = ovl_want_write(dentry); if (!err) { err = ovl_copy_up_flags(dentry, file_flags); @@ -440,6 +454,106 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev) } } +/* + * With inodes index enabled, an overlay inode nlink counts the union of upper + * hardlinks and non-covered lower hardlinks. During the lifetime of a non-pure + * upper inode, the following nlink modifying operations can happen: + * + * 1. Lower hardlink copy up + * 2. Upper hardlink created, unlinked or renamed over + * 3. Lower hardlink whiteout or renamed over + * + * For the first, copy up case, the union nlink does not change, whether the + * operation succeeds or fails, but the upper inode nlink may change. + * Therefore, before copy up, we store the union nlink value relative to the + * lower inode nlink in the index inode xattr trusted.overlay.nlink. + * + * For the second, upper hardlink case, the union nlink should be incremented + * or decremented IFF the operation succeeds, aligned with nlink change of the + * upper inode. Therefore, before link/unlink/rename, we store the union nlink + * value relative to the upper inode nlink in the index inode. + * + * For the last, lower cover up case, we simplify things by preceding the + * whiteout or cover up with copy up. This makes sure that there is an index + * upper inode where the nlink xattr can be stored before the copied up upper + * entry is unlink. + */ +#define OVL_NLINK_ADD_UPPER (1 << 0) + +/* + * On-disk format for indexed nlink: + * + * nlink relative to the upper inode - "U[+-]NUM" + * nlink relative to the lower inode - "L[+-]NUM" + */ + +static int ovl_set_nlink_common(struct dentry *dentry, + struct dentry *realdentry, const char *format) +{ + struct inode *inode = d_inode(dentry); + struct inode *realinode = d_inode(realdentry); + char buf[13]; + int len; + + len = snprintf(buf, sizeof(buf), format, + (int) (inode->i_nlink - realinode->i_nlink)); + + if (WARN_ON(len >= sizeof(buf))) + return -EIO; + + return ovl_do_setxattr(ovl_dentry_upper(dentry), + OVL_XATTR_NLINK, buf, len, 0); +} + +int ovl_set_nlink_upper(struct dentry *dentry) +{ + return ovl_set_nlink_common(dentry, ovl_dentry_upper(dentry), "U%+i"); +} + +int ovl_set_nlink_lower(struct dentry *dentry) +{ + return ovl_set_nlink_common(dentry, ovl_dentry_lower(dentry), "L%+i"); +} + +unsigned int ovl_get_nlink(struct dentry *lowerdentry, + struct dentry *upperdentry, + unsigned int fallback) +{ + int nlink_diff; + int nlink; + char buf[13]; + int err; + + if (!lowerdentry || !upperdentry || d_inode(lowerdentry)->i_nlink == 1) + return fallback; + + err = vfs_getxattr(upperdentry, OVL_XATTR_NLINK, &buf, sizeof(buf) - 1); + if (err < 0) + goto fail; + + buf[err] = '\0'; + if ((buf[0] != 'L' && buf[0] != 'U') || + (buf[1] != '+' && buf[1] != '-')) + goto fail; + + err = kstrtoint(buf + 1, 10, &nlink_diff); + if (err < 0) + goto fail; + + nlink = d_inode(buf[0] == 'L' ? lowerdentry : upperdentry)->i_nlink; + nlink += nlink_diff; + + if (nlink <= 0) + goto fail; + + return nlink; + +fail: + pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n", + upperdentry, err); + return fallback; +} + struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev) { struct inode *inode; @@ -453,27 +567,90 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev) static int ovl_inode_test(struct inode *inode, void *data) { - return ovl_inode_real(inode, NULL) == data; + return inode->i_private == data; } static int ovl_inode_set(struct inode *inode, void *data) { - inode->i_private = (void *) (((unsigned long) data) | OVL_ISUPPER_MASK); + inode->i_private = data; return 0; } -struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode) +static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry, + struct dentry *upperdentry) +{ + /* + * Allow non-NULL lower inode in ovl_inode even if lowerdentry is NULL. + * This happens when finding a copied up overlay inode for a renamed + * or hardlinked overlay dentry and lower dentry cannot be followed + * by origin because lower fs does not support file handles. + */ + if (lowerdentry && ovl_inode_lower(inode) != d_inode(lowerdentry)) + return false; + /* + * Allow non-NULL __upperdentry in inode even if upperdentry is NULL. + * This happens when finding a lower alias for a copied up hard link. + */ + if (upperdentry && ovl_inode_upper(inode) != d_inode(upperdentry)) + return false; + + return true; +} + +struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry) { + struct dentry *lowerdentry = ovl_dentry_lower(dentry); + struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL; struct inode *inode; - inode = iget5_locked(sb, (unsigned long) realinode, - ovl_inode_test, ovl_inode_set, realinode); - if (inode && inode->i_state & I_NEW) { - ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev); - set_nlink(inode, realinode->i_nlink); - unlock_new_inode(inode); + if (!realinode) + realinode = d_inode(lowerdentry); + + if (!S_ISDIR(realinode->i_mode) && + (upperdentry || (lowerdentry && ovl_indexdir(dentry->d_sb)))) { + struct inode *key = d_inode(lowerdentry ?: upperdentry); + unsigned int nlink; + + inode = iget5_locked(dentry->d_sb, (unsigned long) key, + ovl_inode_test, ovl_inode_set, key); + if (!inode) + goto out_nomem; + if (!(inode->i_state & I_NEW)) { + /* + * Verify that the underlying files stored in the inode + * match those in the dentry. + */ + if (!ovl_verify_inode(inode, lowerdentry, upperdentry)) { + iput(inode); + inode = ERR_PTR(-ESTALE); + goto out; + } + + dput(upperdentry); + goto out; + } + + nlink = ovl_get_nlink(lowerdentry, upperdentry, + realinode->i_nlink); + set_nlink(inode, nlink); + } else { + inode = new_inode(dentry->d_sb); + if (!inode) + goto out_nomem; } + ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev); + ovl_inode_init(inode, upperdentry, lowerdentry); + if (upperdentry && ovl_is_impuredir(upperdentry)) + ovl_set_flag(OVL_IMPURE, inode); + + if (inode->i_state & I_NEW) + unlock_new_inode(inode); +out: return inode; + +out_nomem: + inode = ERR_PTR(-ENOMEM); + goto out; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index f3136c31e72a..654bea1a5ac9 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -38,7 +38,7 @@ static int ovl_check_redirect(struct dentry *dentry, struct ovl_lookup_data *d, return 0; goto fail; } - buf = kzalloc(prelen + res + strlen(post) + 1, GFP_TEMPORARY); + buf = kzalloc(prelen + res + strlen(post) + 1, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -88,13 +88,10 @@ static int ovl_acceptable(void *ctx, struct dentry *dentry) return 1; } -static struct dentry *ovl_get_origin(struct dentry *dentry, - struct vfsmount *mnt) +static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry) { int res; struct ovl_fh *fh = NULL; - struct dentry *origin = NULL; - int bytes; res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0); if (res < 0) { @@ -106,7 +103,7 @@ static struct dentry *ovl_get_origin(struct dentry *dentry, if (res == 0) return NULL; - fh = kzalloc(res, GFP_TEMPORARY); + fh = kzalloc(res, GFP_KERNEL); if (!fh) return ERR_PTR(-ENOMEM); @@ -129,15 +126,38 @@ static struct dentry *ovl_get_origin(struct dentry *dentry, (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN) goto out; - bytes = (fh->len - offsetof(struct ovl_fh, fid)); + return fh; + +out: + kfree(fh); + return NULL; + +fail: + pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res); + goto out; +invalid: + pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh); + goto out; +} + +static struct dentry *ovl_get_origin(struct dentry *dentry, + struct vfsmount *mnt) +{ + struct dentry *origin = NULL; + struct ovl_fh *fh = ovl_get_origin_fh(dentry); + int bytes; + + if (IS_ERR_OR_NULL(fh)) + return (struct dentry *)fh; /* * Make sure that the stored uuid matches the uuid of the lower * layer where file handle will be decoded. */ - if (uuid_be_cmp(fh->uuid, *(uuid_be *) &mnt->mnt_sb->s_uuid)) + if (!uuid_equal(&fh->uuid, &mnt->mnt_sb->s_uuid)) goto out; + bytes = (fh->len - offsetof(struct ovl_fh, fid)); origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid, bytes >> 2, (int)fh->type, ovl_acceptable, NULL); @@ -149,21 +169,17 @@ static struct dentry *ovl_get_origin(struct dentry *dentry, } if (ovl_dentry_weird(origin) || - ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT)) { - dput(origin); - origin = NULL; + ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT)) goto invalid; - } out: kfree(fh); return origin; -fail: - pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res); - goto out; invalid: - pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh); + pr_warn_ratelimited("overlayfs: invalid origin (%pd2)\n", origin); + dput(origin); + origin = NULL; goto out; } @@ -269,34 +285,31 @@ static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d, } -static int ovl_check_origin(struct dentry *dentry, struct dentry *upperdentry, +static int ovl_check_origin(struct dentry *upperdentry, + struct path *lowerstack, unsigned int numlower, struct path **stackp, unsigned int *ctrp) { - struct super_block *same_sb = ovl_same_sb(dentry->d_sb); - struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata; struct vfsmount *mnt; - struct dentry *origin; + struct dentry *origin = NULL; + int i; + + + for (i = 0; i < numlower; i++) { + mnt = lowerstack[i].mnt; + origin = ovl_get_origin(upperdentry, mnt); + if (IS_ERR(origin)) + return PTR_ERR(origin); - if (!same_sb || !roe->numlower) + if (origin) + break; + } + + if (!origin) return 0; - /* - * Since all layers are on the same fs, we use the first layer for - * decoding the file handle. We may get a disconnected dentry, - * which is fine, because we only need to hold the origin inode in - * cache and use its inode number. We may even get a connected dentry, - * that is not under the first layer's root. That is also fine for - * using it's inode number - it's the same as if we held a reference - * to a dentry in first layer that was moved under us. - */ - mnt = roe->lowerstack[0].mnt; - - origin = ovl_get_origin(upperdentry, mnt); - if (IS_ERR_OR_NULL(origin)) - return PTR_ERR(origin); - - BUG_ON(*stackp || *ctrp); - *stackp = kmalloc(sizeof(struct path), GFP_TEMPORARY); + BUG_ON(*ctrp); + if (!*stackp) + *stackp = kmalloc(sizeof(struct path), GFP_KERNEL); if (!*stackp) { dput(origin); return -ENOMEM; @@ -308,6 +321,239 @@ static int ovl_check_origin(struct dentry *dentry, struct dentry *upperdentry, } /* + * Verify that @fh matches the origin file handle stored in OVL_XATTR_ORIGIN. + * Return 0 on match, -ESTALE on mismatch, < 0 on error. + */ +static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh) +{ + struct ovl_fh *ofh = ovl_get_origin_fh(dentry); + int err = 0; + + if (!ofh) + return -ENODATA; + + if (IS_ERR(ofh)) + return PTR_ERR(ofh); + + if (fh->len != ofh->len || memcmp(fh, ofh, fh->len)) + err = -ESTALE; + + kfree(ofh); + return err; +} + +/* + * Verify that an inode matches the origin file handle stored in upper inode. + * + * If @set is true and there is no stored file handle, encode and store origin + * file handle in OVL_XATTR_ORIGIN. + * + * Return 0 on match, -ESTALE on mismatch, < 0 on error. + */ +int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt, + struct dentry *origin, bool is_upper, bool set) +{ + struct inode *inode; + struct ovl_fh *fh; + int err; + + fh = ovl_encode_fh(origin, is_upper); + err = PTR_ERR(fh); + if (IS_ERR(fh)) + goto fail; + + err = ovl_verify_origin_fh(dentry, fh); + if (set && err == -ENODATA) + err = ovl_do_setxattr(dentry, OVL_XATTR_ORIGIN, fh, fh->len, 0); + if (err) + goto fail; + +out: + kfree(fh); + return err; + +fail: + inode = d_inode(origin); + pr_warn_ratelimited("overlayfs: failed to verify origin (%pd2, ino=%lu, err=%i)\n", + origin, inode ? inode->i_ino : 0, err); + goto out; +} + +/* + * Verify that an index entry name matches the origin file handle stored in + * OVL_XATTR_ORIGIN and that origin file handle can be decoded to lower path. + * Return 0 on match, -ESTALE on mismatch or stale origin, < 0 on error. + */ +int ovl_verify_index(struct dentry *index, struct path *lowerstack, + unsigned int numlower) +{ + struct ovl_fh *fh = NULL; + size_t len; + struct path origin = { }; + struct path *stack = &origin; + unsigned int ctr = 0; + int err; + + if (!d_inode(index)) + return 0; + + /* + * Directory index entries are going to be used for looking up + * redirected upper dirs by lower dir fh when decoding an overlay + * file handle of a merge dir. Whiteout index entries are going to be + * used as an indication that an exported overlay file handle should + * be treated as stale (i.e. after unlink of the overlay inode). + * We don't know the verification rules for directory and whiteout + * index entries, because they have not been implemented yet, so return + * EROFS if those entries are found to avoid corrupting an index that + * was created by a newer kernel. + */ + err = -EROFS; + if (d_is_dir(index) || ovl_is_whiteout(index)) + goto fail; + + err = -EINVAL; + if (index->d_name.len < sizeof(struct ovl_fh)*2) + goto fail; + + err = -ENOMEM; + len = index->d_name.len / 2; + fh = kzalloc(len, GFP_KERNEL); + if (!fh) + goto fail; + + err = -EINVAL; + if (hex2bin((u8 *)fh, index->d_name.name, len) || len != fh->len) + goto fail; + + err = ovl_verify_origin_fh(index, fh); + if (err) + goto fail; + + err = ovl_check_origin(index, lowerstack, numlower, &stack, &ctr); + if (!err && !ctr) + err = -ESTALE; + if (err) + goto fail; + + /* Check if index is orphan and don't warn before cleaning it */ + if (d_inode(index)->i_nlink == 1 && + ovl_get_nlink(index, origin.dentry, 0) == 0) + err = -ENOENT; + + dput(origin.dentry); +out: + kfree(fh); + return err; + +fail: + pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n", + index, d_inode(index)->i_mode & S_IFMT, err); + goto out; +} + +/* + * Lookup in indexdir for the index entry of a lower real inode or a copy up + * origin inode. The index entry name is the hex representation of the lower + * inode file handle. + * + * If the index dentry in negative, then either no lower aliases have been + * copied up yet, or aliases have been copied up in older kernels and are + * not indexed. + * + * If the index dentry for a copy up origin inode is positive, but points + * to an inode different than the upper inode, then either the upper inode + * has been copied up and not indexed or it was indexed, but since then + * index dir was cleared. Either way, that index cannot be used to indentify + * the overlay inode. + */ +int ovl_get_index_name(struct dentry *origin, struct qstr *name) +{ + int err; + struct ovl_fh *fh; + char *n, *s; + + fh = ovl_encode_fh(origin, false); + if (IS_ERR(fh)) + return PTR_ERR(fh); + + err = -ENOMEM; + n = kzalloc(fh->len * 2, GFP_KERNEL); + if (n) { + s = bin2hex(n, fh, fh->len); + *name = (struct qstr) QSTR_INIT(n, s - n); + err = 0; + } + kfree(fh); + + return err; + +} + +static struct dentry *ovl_lookup_index(struct dentry *dentry, + struct dentry *upper, + struct dentry *origin) +{ + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + struct dentry *index; + struct inode *inode; + struct qstr name; + int err; + + err = ovl_get_index_name(origin, &name); + if (err) + return ERR_PTR(err); + + index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len); + if (IS_ERR(index)) { + err = PTR_ERR(index); + pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n" + "overlayfs: mount with '-o index=off' to disable inodes index.\n", + d_inode(origin)->i_ino, name.len, name.name, + err); + goto out; + } + + inode = d_inode(index); + if (d_is_negative(index)) { + if (upper && d_inode(origin)->i_nlink > 1) { + pr_warn_ratelimited("overlayfs: hard link with origin but no index (ino=%lu).\n", + d_inode(origin)->i_ino); + goto fail; + } + + dput(index); + index = NULL; + } else if (upper && d_inode(upper) != inode) { + pr_warn_ratelimited("overlayfs: wrong index found (index=%pd2, ino=%lu, upper ino=%lu).\n", + index, inode->i_ino, d_inode(upper)->i_ino); + goto fail; + } else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) || + ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) { + /* + * Index should always be of the same file type as origin + * except for the case of a whiteout index. A whiteout + * index should only exist if all lower aliases have been + * unlinked, which means that finding a lower origin on lookup + * whose index is a whiteout should be treated as an error. + */ + pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n", + index, d_inode(index)->i_mode & S_IFMT, + d_inode(origin)->i_mode & S_IFMT); + goto fail; + } + +out: + kfree(name.name); + return index; + +fail: + dput(index); + index = ERR_PTR(-EIO); + goto out; +} + +/* * Returns next layer in stack starting from top. * Returns -1 if this is the last layer. */ @@ -338,10 +584,10 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata; struct path *stack = NULL; struct dentry *upperdir, *upperdentry = NULL; + struct dentry *index = NULL; unsigned int ctr = 0; struct inode *inode = NULL; bool upperopaque = false; - bool upperimpure = false; char *upperredirect = NULL; struct dentry *this; unsigned int i; @@ -359,7 +605,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, return ERR_PTR(-ENAMETOOLONG); old_cred = ovl_override_creds(dentry->d_sb); - upperdir = ovl_upperdentry_dereference(poe); + upperdir = ovl_dentry_upper(dentry->d_parent); if (upperdir) { err = ovl_lookup_layer(upperdir, &d, &upperdentry); if (err) @@ -372,8 +618,18 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } if (upperdentry && !d.is_dir) { BUG_ON(!d.stop || d.redirect); - err = ovl_check_origin(dentry, upperdentry, - &stack, &ctr); + /* + * Lookup copy up origin by decoding origin file handle. + * We may get a disconnected dentry, which is fine, + * because we only need to hold the origin inode in + * cache and use its inode number. We may even get a + * connected dentry, that is not under any of the lower + * layers root. That is also fine for using it's inode + * number - it's the same as if we held a reference + * to a dentry in lower layer that was moved under us. + */ + err = ovl_check_origin(upperdentry, roe->lowerstack, + roe->numlower, &stack, &ctr); if (err) goto out; } @@ -386,14 +642,12 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, poe = roe; } upperopaque = d.opaque; - if (upperdentry && d.is_dir) - upperimpure = ovl_is_impuredir(upperdentry); } if (!d.stop && poe->numlower) { err = -ENOMEM; stack = kcalloc(ofs->numlower, sizeof(struct path), - GFP_TEMPORARY); + GFP_KERNEL); if (!stack) goto out_put_upper; } @@ -428,48 +682,56 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, } } + /* Lookup index by lower inode and verify it matches upper inode */ + if (ctr && !d.is_dir && ovl_indexdir(dentry->d_sb)) { + struct dentry *origin = stack[0].dentry; + + index = ovl_lookup_index(dentry, upperdentry, origin); + if (IS_ERR(index)) { + err = PTR_ERR(index); + index = NULL; + goto out_put; + } + } + oe = ovl_alloc_entry(ctr); err = -ENOMEM; if (!oe) goto out_put; - if (upperdentry || ctr) { - struct dentry *realdentry; - struct inode *realinode; + oe->opaque = upperopaque; + memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr); + dentry->d_fsdata = oe; - realdentry = upperdentry ? upperdentry : stack[0].dentry; - realinode = d_inode(realdentry); + if (upperdentry) + ovl_dentry_set_upper_alias(dentry); + else if (index) + upperdentry = dget(index); - err = -ENOMEM; - if (upperdentry && !d_is_dir(upperdentry)) { - inode = ovl_get_inode(dentry->d_sb, realinode); - } else { - inode = ovl_new_inode(dentry->d_sb, realinode->i_mode, - realinode->i_rdev); - if (inode) - ovl_inode_init(inode, realinode, !!upperdentry); - } - if (!inode) + if (upperdentry || ctr) { + inode = ovl_get_inode(dentry, upperdentry); + err = PTR_ERR(inode); + if (IS_ERR(inode)) goto out_free_oe; - ovl_copyattr(realdentry->d_inode, inode); + + OVL_I(inode)->redirect = upperredirect; + if (index) + ovl_set_flag(OVL_INDEX, inode); } revert_creds(old_cred); - oe->opaque = upperopaque; - oe->impure = upperimpure; - oe->redirect = upperredirect; - oe->__upperdentry = upperdentry; - memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr); + dput(index); kfree(stack); kfree(d.redirect); - dentry->d_fsdata = oe; d_add(dentry, inode); return NULL; out_free_oe: + dentry->d_fsdata = NULL; kfree(oe); out_put: + dput(index); for (i = 0; i < ctr; i++) dput(stack[i].dentry); kfree(stack); @@ -499,7 +761,7 @@ bool ovl_lower_positive(struct dentry *dentry) return oe->opaque; /* Negative upper -> positive lower */ - if (!oe->__upperdentry) + if (!ovl_dentry_upper(dentry)) return true; /* Positive upper -> have to look up lower to see whether it exists */ diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 0623cebeefff..c706a6f99928 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -25,6 +25,12 @@ enum ovl_path_type { #define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect" #define OVL_XATTR_ORIGIN OVL_XATTR_PREFIX "origin" #define OVL_XATTR_IMPURE OVL_XATTR_PREFIX "impure" +#define OVL_XATTR_NLINK OVL_XATTR_PREFIX "nlink" + +enum ovl_flag { + OVL_IMPURE, + OVL_INDEX, +}; /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, @@ -38,8 +44,11 @@ enum ovl_path_type { /* CPU byte order required for fid decoding: */ #define OVL_FH_FLAG_BIG_ENDIAN (1 << 0) #define OVL_FH_FLAG_ANY_ENDIAN (1 << 1) +/* Is the real inode encoded in fid an upper inode? */ +#define OVL_FH_FLAG_PATH_UPPER (1 << 2) -#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN) +#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN | \ + OVL_FH_FLAG_PATH_UPPER) #if defined(__LITTLE_ENDIAN) #define OVL_FH_FLAG_CPU_ENDIAN 0 @@ -56,12 +65,10 @@ struct ovl_fh { u8 len; /* size of this header + size of fid */ u8 flags; /* OVL_FH_FLAG_* */ u8 type; /* fid_type of fid */ - uuid_be uuid; /* uuid of filesystem */ + uuid_t uuid; /* uuid of filesystem */ u8 fid[0]; /* file identifier */ } __packed; -#define OVL_ISUPPER_MASK 1UL - static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry) { int err = vfs_rmdir(dir, dentry); @@ -175,22 +182,14 @@ static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode) return ret; } -static inline struct inode *ovl_inode_real(struct inode *inode, bool *is_upper) -{ - unsigned long x = (unsigned long) READ_ONCE(inode->i_private); - - if (is_upper) - *is_upper = x & OVL_ISUPPER_MASK; - - return (struct inode *) (x & ~OVL_ISUPPER_MASK); -} - /* util.c */ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); struct super_block *ovl_same_sb(struct super_block *sb); +bool ovl_can_decode_fh(struct super_block *sb); +struct dentry *ovl_indexdir(struct super_block *sb); struct ovl_entry *ovl_alloc_entry(unsigned int numlower); bool ovl_dentry_remote(struct dentry *dentry); bool ovl_dentry_weird(struct dentry *dentry); @@ -201,20 +200,24 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path); struct dentry *ovl_dentry_upper(struct dentry *dentry); struct dentry *ovl_dentry_lower(struct dentry *dentry); struct dentry *ovl_dentry_real(struct dentry *dentry); -struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry); -void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache); +struct dentry *ovl_i_dentry_upper(struct inode *inode); +struct inode *ovl_inode_upper(struct inode *inode); +struct inode *ovl_inode_lower(struct inode *inode); +struct inode *ovl_inode_real(struct inode *inode); +struct ovl_dir_cache *ovl_dir_cache(struct inode *inode); +void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache); bool ovl_dentry_is_opaque(struct dentry *dentry); -bool ovl_dentry_is_impure(struct dentry *dentry); bool ovl_dentry_is_whiteout(struct dentry *dentry); void ovl_dentry_set_opaque(struct dentry *dentry); +bool ovl_dentry_has_upper_alias(struct dentry *dentry); +void ovl_dentry_set_upper_alias(struct dentry *dentry); bool ovl_redirect_dir(struct super_block *sb); const char *ovl_dentry_get_redirect(struct dentry *dentry); void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect); -void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry); -void ovl_inode_init(struct inode *inode, struct inode *realinode, - bool is_upper); -void ovl_inode_update(struct inode *inode, struct inode *upperinode); -void ovl_dentry_version_inc(struct dentry *dentry); +void ovl_inode_init(struct inode *inode, struct dentry *upperdentry, + struct dentry *lowerdentry); +void ovl_inode_update(struct inode *inode, struct dentry *upperdentry); +void ovl_dentry_version_inc(struct dentry *dentry, bool impurity); u64 ovl_dentry_version_get(struct dentry *dentry); bool ovl_is_whiteout(struct dentry *dentry); struct file *ovl_path_open(struct path *path, int flags); @@ -225,6 +228,14 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry, const char *name, const void *value, size_t size, int xerr); int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry); +void ovl_set_flag(unsigned long flag, struct inode *inode); +void ovl_clear_flag(unsigned long flag, struct inode *inode); +bool ovl_test_flag(unsigned long flag, struct inode *inode); +bool ovl_inuse_trylock(struct dentry *dentry); +void ovl_inuse_unlock(struct dentry *dentry); +int ovl_nlink_start(struct dentry *dentry, bool *locked); +void ovl_nlink_end(struct dentry *dentry, bool locked); +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir); static inline bool ovl_is_impuredir(struct dentry *dentry) { @@ -233,6 +244,11 @@ static inline bool ovl_is_impuredir(struct dentry *dentry) /* namei.c */ +int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt, + struct dentry *origin, bool is_upper, bool set); +int ovl_verify_index(struct dentry *index, struct path *lowerstack, + unsigned int numlower); +int ovl_get_index_name(struct dentry *origin, struct qstr *name); int ovl_path_next(int idx, struct dentry *dentry, struct path *path); struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); bool ovl_lower_positive(struct dentry *dentry); @@ -242,18 +258,26 @@ extern const struct file_operations ovl_dir_operations; int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list); void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list); void ovl_cache_free(struct list_head *list); +void ovl_dir_cache_free(struct inode *inode); int ovl_check_d_type_supported(struct path *realpath); void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt, struct dentry *dentry, int level); +int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, + struct path *lowerstack, unsigned int numlower); /* inode.c */ +int ovl_set_nlink_upper(struct dentry *dentry); +int ovl_set_nlink_lower(struct dentry *dentry); +unsigned int ovl_get_nlink(struct dentry *lowerdentry, + struct dentry *upperdentry, + unsigned int fallback); int ovl_setattr(struct dentry *dentry, struct iattr *attr); int ovl_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); int ovl_permission(struct inode *inode, int mask); -int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags); -int ovl_xattr_get(struct dentry *dentry, const char *name, +int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, + const void *value, size_t size, int flags); +int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); struct posix_acl *ovl_get_acl(struct inode *inode, int type); @@ -262,7 +286,7 @@ int ovl_update_time(struct inode *inode, struct timespec *ts, int flags); bool ovl_is_private_xattr(const char *name); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); -struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode); +struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry); static inline void ovl_copyattr(struct inode *from, struct inode *to) { to->i_uid = from->i_uid; @@ -284,10 +308,11 @@ struct cattr { int ovl_create_real(struct inode *dir, struct dentry *newdentry, struct cattr *attr, struct dentry *hardlink, bool debug); -void ovl_cleanup(struct inode *dir, struct dentry *dentry); +int ovl_cleanup(struct inode *dir, struct dentry *dentry); /* copy_up.c */ int ovl_copy_up(struct dentry *dentry); int ovl_copy_up_flags(struct dentry *dentry, int flags); int ovl_copy_xattr(struct dentry *old, struct dentry *new); int ovl_set_attr(struct dentry *upper, struct kstat *stat); +struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper); diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 34bc4a9f5c61..25d9b5adcd42 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -14,6 +14,7 @@ struct ovl_config { char *workdir; bool default_permissions; bool redirect_dir; + bool index; }; /* private information held for overlayfs's superblock */ @@ -21,7 +22,12 @@ struct ovl_fs { struct vfsmount *upper_mnt; unsigned numlower; struct vfsmount **lower_mnt; + /* workbasedir is the path at workdir= mount option */ + struct dentry *workbasedir; + /* workdir is the 'work' directory under workbasedir */ struct dentry *workdir; + /* index directory listing overlay inodes by origin file handle */ + struct dentry *indexdir; long namelen; /* pathnames of lower and upper dirs, for show_options */ struct ovl_config config; @@ -29,22 +35,19 @@ struct ovl_fs { const struct cred *creator_cred; bool tmpfile; bool noxattr; - wait_queue_head_t copyup_wq; /* sb common to all layers */ struct super_block *same_sb; + /* Did we take the inuse lock? */ + bool upperdir_locked; + bool workdir_locked; }; /* private information held for every overlayfs dentry */ struct ovl_entry { - struct dentry *__upperdentry; - struct ovl_dir_cache *cache; union { struct { - u64 version; - const char *redirect; + unsigned long has_upper; bool opaque; - bool impure; - bool copying; }; struct rcu_head rcu; }; @@ -54,7 +57,25 @@ struct ovl_entry { struct ovl_entry *ovl_alloc_entry(unsigned int numlower); -static inline struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe) +struct ovl_inode { + struct ovl_dir_cache *cache; + const char *redirect; + u64 version; + unsigned long flags; + struct inode vfs_inode; + struct dentry *__upperdentry; + struct inode *lower; + + /* synchronize copy up and more */ + struct mutex lock; +}; + +static inline struct ovl_inode *OVL_I(struct inode *inode) +{ + return container_of(inode, struct ovl_inode, vfs_inode); +} + +static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi) { - return lockless_dereference(oe->__upperdentry); + return lockless_dereference(oi->__upperdentry); } diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index f241b4ee3d8a..0f85ee9c3268 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -15,11 +15,13 @@ #include <linux/rbtree.h> #include <linux/security.h> #include <linux/cred.h> +#include <linux/ratelimit.h> #include "overlayfs.h" struct ovl_cache_entry { unsigned int len; unsigned int type; + u64 real_ino; u64 ino; struct list_head l_node; struct rb_node node; @@ -32,18 +34,20 @@ struct ovl_dir_cache { long refcount; u64 version; struct list_head entries; + struct rb_root root; }; struct ovl_readdir_data { struct dir_context ctx; struct dentry *dentry; bool is_lowest; - struct rb_root root; + struct rb_root *root; struct list_head *list; struct list_head middle; struct ovl_cache_entry *first_maybe_whiteout; int count; int err; + bool is_upper; bool d_type_supported; }; @@ -58,7 +62,33 @@ struct ovl_dir_file { static struct ovl_cache_entry *ovl_cache_entry_from_node(struct rb_node *n) { - return container_of(n, struct ovl_cache_entry, node); + return rb_entry(n, struct ovl_cache_entry, node); +} + +static bool ovl_cache_entry_find_link(const char *name, int len, + struct rb_node ***link, + struct rb_node **parent) +{ + bool found = false; + struct rb_node **newp = *link; + + while (!found && *newp) { + int cmp; + struct ovl_cache_entry *tmp; + + *parent = *newp; + tmp = ovl_cache_entry_from_node(*newp); + cmp = strncmp(name, tmp->name, len); + if (cmp > 0) + newp = &tmp->node.rb_right; + else if (cmp < 0 || len < tmp->len) + newp = &tmp->node.rb_left; + else + found = true; + } + *link = newp; + + return found; } static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, @@ -82,6 +112,32 @@ static struct ovl_cache_entry *ovl_cache_entry_find(struct rb_root *root, return NULL; } +static bool ovl_calc_d_ino(struct ovl_readdir_data *rdd, + struct ovl_cache_entry *p) +{ + /* Don't care if not doing ovl_iter() */ + if (!rdd->dentry) + return false; + + /* Always recalc d_ino for parent */ + if (strcmp(p->name, "..") == 0) + return true; + + /* If this is lower, then native d_ino will do */ + if (!rdd->is_upper) + return false; + + /* + * Recalc d_ino for '.' and for all entries if dir is impure (contains + * copied up entries) + */ + if ((p->name[0] == '.' && p->len == 1) || + ovl_test_flag(OVL_IMPURE, d_inode(rdd->dentry))) + return true; + + return false; +} + static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd, const char *name, int len, u64 ino, unsigned int d_type) @@ -97,7 +153,11 @@ static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd, p->name[len] = '\0'; p->len = len; p->type = d_type; + p->real_ino = ino; p->ino = ino; + /* Defer setting d_ino for upper entry to ovl_iterate() */ + if (ovl_calc_d_ino(rdd, p)) + p->ino = 0; p->is_whiteout = false; if (d_type == DT_CHR) { @@ -111,32 +171,22 @@ static int ovl_cache_entry_add_rb(struct ovl_readdir_data *rdd, const char *name, int len, u64 ino, unsigned int d_type) { - struct rb_node **newp = &rdd->root.rb_node; + struct rb_node **newp = &rdd->root->rb_node; struct rb_node *parent = NULL; struct ovl_cache_entry *p; - while (*newp) { - int cmp; - struct ovl_cache_entry *tmp; - - parent = *newp; - tmp = ovl_cache_entry_from_node(*newp); - cmp = strncmp(name, tmp->name, len); - if (cmp > 0) - newp = &tmp->node.rb_right; - else if (cmp < 0 || len < tmp->len) - newp = &tmp->node.rb_left; - else - return 0; - } + if (ovl_cache_entry_find_link(name, len, &newp, &parent)) + return 0; p = ovl_cache_entry_new(rdd, name, len, ino, d_type); - if (p == NULL) + if (p == NULL) { + rdd->err = -ENOMEM; return -ENOMEM; + } list_add_tail(&p->l_node, rdd->list); rb_link_node(&p->node, parent, newp); - rb_insert_color(&p->node, &rdd->root); + rb_insert_color(&p->node, rdd->root); return 0; } @@ -147,7 +197,7 @@ static int ovl_fill_lowest(struct ovl_readdir_data *rdd, { struct ovl_cache_entry *p; - p = ovl_cache_entry_find(&rdd->root, name, namelen); + p = ovl_cache_entry_find(rdd->root, name, namelen); if (p) { list_move_tail(&p->l_node, &rdd->middle); } else { @@ -172,6 +222,16 @@ void ovl_cache_free(struct list_head *list) INIT_LIST_HEAD(list); } +void ovl_dir_cache_free(struct inode *inode) +{ + struct ovl_dir_cache *cache = ovl_dir_cache(inode); + + if (cache) { + ovl_cache_free(&cache->entries); + kfree(cache); + } +} + static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) { struct ovl_dir_cache *cache = od->cache; @@ -179,8 +239,8 @@ static void ovl_cache_put(struct ovl_dir_file *od, struct dentry *dentry) WARN_ON(cache->refcount <= 0); cache->refcount--; if (!cache->refcount) { - if (ovl_dir_cache(dentry) == cache) - ovl_set_dir_cache(dentry, NULL); + if (ovl_dir_cache(d_inode(dentry)) == cache) + ovl_set_dir_cache(d_inode(dentry), NULL); ovl_cache_free(&cache->entries); kfree(cache); @@ -273,7 +333,8 @@ static void ovl_dir_reset(struct file *file) od->is_real = false; } -static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list) +static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list, + struct rb_root *root) { int err; struct path realpath; @@ -281,13 +342,14 @@ static int ovl_dir_read_merged(struct dentry *dentry, struct list_head *list) .ctx.actor = ovl_fill_merge, .dentry = dentry, .list = list, - .root = RB_ROOT, + .root = root, .is_lowest = false, }; int idx, next; for (idx = 0; idx != -1; idx = next) { next = ovl_path_next(idx, dentry, &realpath); + rdd.is_upper = ovl_dentry_upper(dentry) == realpath.dentry; if (next != -1) { err = ovl_dir_read(&realpath, &rdd); @@ -326,12 +388,13 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) int res; struct ovl_dir_cache *cache; - cache = ovl_dir_cache(dentry); + cache = ovl_dir_cache(d_inode(dentry)); if (cache && ovl_dentry_version_get(dentry) == cache->version) { + WARN_ON(!cache->refcount); cache->refcount++; return cache; } - ovl_set_dir_cache(dentry, NULL); + ovl_set_dir_cache(d_inode(dentry), NULL); cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); if (!cache) @@ -339,31 +402,276 @@ static struct ovl_dir_cache *ovl_cache_get(struct dentry *dentry) cache->refcount = 1; INIT_LIST_HEAD(&cache->entries); + cache->root = RB_ROOT; + + res = ovl_dir_read_merged(dentry, &cache->entries, &cache->root); + if (res) { + ovl_cache_free(&cache->entries); + kfree(cache); + return ERR_PTR(res); + } + + cache->version = ovl_dentry_version_get(dentry); + ovl_set_dir_cache(d_inode(dentry), cache); + + return cache; +} + +/* + * Set d_ino for upper entries. Non-upper entries should always report + * the uppermost real inode ino and should not call this function. + * + * When not all layer are on same fs, report real ino also for upper. + * + * When all layers are on the same fs, and upper has a reference to + * copy up origin, call vfs_getattr() on the overlay entry to make + * sure that d_ino will be consistent with st_ino from stat(2). + */ +static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p) + +{ + struct dentry *dir = path->dentry; + struct dentry *this = NULL; + enum ovl_path_type type; + u64 ino = p->real_ino; + int err = 0; + + if (!ovl_same_sb(dir->d_sb)) + goto out; + + if (p->name[0] == '.') { + if (p->len == 1) { + this = dget(dir); + goto get; + } + if (p->len == 2 && p->name[1] == '.') { + /* we shall not be moved */ + this = dget(dir->d_parent); + goto get; + } + } + this = lookup_one_len(p->name, dir, p->len); + if (IS_ERR_OR_NULL(this) || !this->d_inode) { + if (IS_ERR(this)) { + err = PTR_ERR(this); + this = NULL; + goto fail; + } + goto out; + } + +get: + type = ovl_path_type(this); + if (OVL_TYPE_ORIGIN(type)) { + struct kstat stat; + struct path statpath = *path; + + statpath.dentry = this; + err = vfs_getattr(&statpath, &stat, STATX_INO, 0); + if (err) + goto fail; + + WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev); + ino = stat.ino; + } + +out: + p->ino = ino; + dput(this); + return err; + +fail: + pr_warn_ratelimited("overlay: failed to look up (%s) for ino (%i)\n", + p->name, err); + goto out; +} + +static int ovl_fill_plain(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) +{ + struct ovl_cache_entry *p; + struct ovl_readdir_data *rdd = + container_of(ctx, struct ovl_readdir_data, ctx); + + rdd->count++; + p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type); + if (p == NULL) { + rdd->err = -ENOMEM; + return -ENOMEM; + } + list_add_tail(&p->l_node, rdd->list); + + return 0; +} + +static int ovl_dir_read_impure(struct path *path, struct list_head *list, + struct rb_root *root) +{ + int err; + struct path realpath; + struct ovl_cache_entry *p, *n; + struct ovl_readdir_data rdd = { + .ctx.actor = ovl_fill_plain, + .list = list, + .root = root, + }; + + INIT_LIST_HEAD(list); + *root = RB_ROOT; + ovl_path_upper(path->dentry, &realpath); + + err = ovl_dir_read(&realpath, &rdd); + if (err) + return err; + + list_for_each_entry_safe(p, n, list, l_node) { + if (strcmp(p->name, ".") != 0 && + strcmp(p->name, "..") != 0) { + err = ovl_cache_update_ino(path, p); + if (err) + return err; + } + if (p->ino == p->real_ino) { + list_del(&p->l_node); + kfree(p); + } else { + struct rb_node **newp = &root->rb_node; + struct rb_node *parent = NULL; - res = ovl_dir_read_merged(dentry, &cache->entries); + if (WARN_ON(ovl_cache_entry_find_link(p->name, p->len, + &newp, &parent))) + return -EIO; + + rb_link_node(&p->node, parent, newp); + rb_insert_color(&p->node, root); + } + } + return 0; +} + +static struct ovl_dir_cache *ovl_cache_get_impure(struct path *path) +{ + int res; + struct dentry *dentry = path->dentry; + struct ovl_dir_cache *cache; + + cache = ovl_dir_cache(d_inode(dentry)); + if (cache && ovl_dentry_version_get(dentry) == cache->version) + return cache; + + /* Impure cache is not refcounted, free it here */ + ovl_dir_cache_free(d_inode(dentry)); + ovl_set_dir_cache(d_inode(dentry), NULL); + + cache = kzalloc(sizeof(struct ovl_dir_cache), GFP_KERNEL); + if (!cache) + return ERR_PTR(-ENOMEM); + + res = ovl_dir_read_impure(path, &cache->entries, &cache->root); if (res) { ovl_cache_free(&cache->entries); kfree(cache); return ERR_PTR(res); } + if (list_empty(&cache->entries)) { + /* Good oportunity to get rid of an unnecessary "impure" flag */ + ovl_do_removexattr(ovl_dentry_upper(dentry), OVL_XATTR_IMPURE); + ovl_clear_flag(OVL_IMPURE, d_inode(dentry)); + kfree(cache); + return NULL; + } cache->version = ovl_dentry_version_get(dentry); - ovl_set_dir_cache(dentry, cache); + ovl_set_dir_cache(d_inode(dentry), cache); return cache; } +struct ovl_readdir_translate { + struct dir_context *orig_ctx; + struct ovl_dir_cache *cache; + struct dir_context ctx; + u64 parent_ino; +}; + +static int ovl_fill_real(struct dir_context *ctx, const char *name, + int namelen, loff_t offset, u64 ino, + unsigned int d_type) +{ + struct ovl_readdir_translate *rdt = + container_of(ctx, struct ovl_readdir_translate, ctx); + struct dir_context *orig_ctx = rdt->orig_ctx; + + if (rdt->parent_ino && strcmp(name, "..") == 0) + ino = rdt->parent_ino; + else if (rdt->cache) { + struct ovl_cache_entry *p; + + p = ovl_cache_entry_find(&rdt->cache->root, name, namelen); + if (p) + ino = p->ino; + } + + return orig_ctx->actor(orig_ctx, name, namelen, offset, ino, d_type); +} + +static int ovl_iterate_real(struct file *file, struct dir_context *ctx) +{ + int err; + struct ovl_dir_file *od = file->private_data; + struct dentry *dir = file->f_path.dentry; + struct ovl_readdir_translate rdt = { + .ctx.actor = ovl_fill_real, + .orig_ctx = ctx, + }; + + if (OVL_TYPE_MERGE(ovl_path_type(dir->d_parent))) { + struct kstat stat; + struct path statpath = file->f_path; + + statpath.dentry = dir->d_parent; + err = vfs_getattr(&statpath, &stat, STATX_INO, 0); + if (err) + return err; + + WARN_ON_ONCE(dir->d_sb->s_dev != stat.dev); + rdt.parent_ino = stat.ino; + } + + if (ovl_test_flag(OVL_IMPURE, d_inode(dir))) { + rdt.cache = ovl_cache_get_impure(&file->f_path); + if (IS_ERR(rdt.cache)) + return PTR_ERR(rdt.cache); + } + + return iterate_dir(od->realfile, &rdt.ctx); +} + + static int ovl_iterate(struct file *file, struct dir_context *ctx) { struct ovl_dir_file *od = file->private_data; struct dentry *dentry = file->f_path.dentry; struct ovl_cache_entry *p; + int err; if (!ctx->pos) ovl_dir_reset(file); - if (od->is_real) + if (od->is_real) { + /* + * If parent is merge, then need to adjust d_ino for '..', if + * dir is impure then need to adjust d_ino for copied up + * entries. + */ + if (ovl_same_sb(dentry->d_sb) && + (ovl_test_flag(OVL_IMPURE, d_inode(dentry)) || + OVL_TYPE_MERGE(ovl_path_type(dentry->d_parent)))) { + return ovl_iterate_real(file, ctx); + } return iterate_dir(od->realfile, ctx); + } if (!od->cache) { struct ovl_dir_cache *cache; @@ -378,9 +686,15 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx) while (od->cursor != &od->cache->entries) { p = list_entry(od->cursor, struct ovl_cache_entry, l_node); - if (!p->is_whiteout) + if (!p->is_whiteout) { + if (!p->ino) { + err = ovl_cache_update_ino(&file->f_path, p); + if (err) + return err; + } if (!dir_emit(ctx, p->name, p->len, p->ino, p->type)) break; + } od->cursor = p->l_node.next; ctx->pos++; } @@ -446,14 +760,14 @@ static int ovl_dir_fsync(struct file *file, loff_t start, loff_t end, ovl_path_upper(dentry, &upperpath); realfile = ovl_path_open(&upperpath, O_RDONLY); - smp_mb__before_spinlock(); + inode_lock(inode); if (!od->upperfile) { if (IS_ERR(realfile)) { inode_unlock(inode); return PTR_ERR(realfile); } - od->upperfile = realfile; + smp_store_release(&od->upperfile, realfile); } else { /* somebody has beaten us to it */ if (!IS_ERR(realfile)) @@ -522,8 +836,9 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list) { int err; struct ovl_cache_entry *p; + struct rb_root root = RB_ROOT; - err = ovl_dir_read_merged(dentry, list); + err = ovl_dir_read_merged(dentry, list, &root); if (err) return err; @@ -612,12 +927,13 @@ static void ovl_workdir_cleanup_recurse(struct path *path, int level) int err; struct inode *dir = path->dentry->d_inode; LIST_HEAD(list); + struct rb_root root = RB_ROOT; struct ovl_cache_entry *p; struct ovl_readdir_data rdd = { .ctx.actor = ovl_fill_merge, .dentry = NULL, .list = &list, - .root = RB_ROOT, + .root = &root, .is_lowest = false, }; @@ -667,3 +983,59 @@ void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt, ovl_cleanup(dir, dentry); } } + +int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt, + struct path *lowerstack, unsigned int numlower) +{ + int err; + struct dentry *index = NULL; + struct inode *dir = dentry->d_inode; + struct path path = { .mnt = mnt, .dentry = dentry }; + LIST_HEAD(list); + struct rb_root root = RB_ROOT; + struct ovl_cache_entry *p; + struct ovl_readdir_data rdd = { + .ctx.actor = ovl_fill_merge, + .dentry = NULL, + .list = &list, + .root = &root, + .is_lowest = false, + }; + + err = ovl_dir_read(&path, &rdd); + if (err) + goto out; + + inode_lock_nested(dir, I_MUTEX_PARENT); + list_for_each_entry(p, &list, l_node) { + if (p->name[0] == '.') { + if (p->len == 1) + continue; + if (p->len == 2 && p->name[1] == '.') + continue; + } + index = lookup_one_len(p->name, dentry, p->len); + if (IS_ERR(index)) { + err = PTR_ERR(index); + index = NULL; + break; + } + err = ovl_verify_index(index, lowerstack, numlower); + if (err) { + if (err == -EROFS) + break; + err = ovl_cleanup(dir, index); + if (err) + break; + } + dput(index); + index = NULL; + } + dput(index); + inode_unlock(dir); +out: + ovl_cache_free(&list); + if (err) + pr_err("overlayfs: failed index dir cleanup (%i)\n", err); + return err; +} diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 4882ffb37bae..092d150643c1 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -34,6 +34,11 @@ module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); MODULE_PARM_DESC(ovl_redirect_dir_def, "Default to on or off for the redirect_dir feature"); +static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); +module_param_named(index, ovl_index_def, bool, 0644); +MODULE_PARM_DESC(ovl_index_def, + "Default to on or off for the inodes index feature"); + static void ovl_dentry_release(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; @@ -41,8 +46,6 @@ static void ovl_dentry_release(struct dentry *dentry) if (oe) { unsigned int i; - dput(oe->__upperdentry); - kfree(oe->redirect); for (i = 0; i < oe->numlower; i++) dput(oe->lowerstack[i].dentry); kfree_rcu(oe, rcu); @@ -67,20 +70,20 @@ static int ovl_check_append_only(struct inode *inode, int flag) static struct dentry *ovl_d_real(struct dentry *dentry, const struct inode *inode, - unsigned int open_flags) + unsigned int open_flags, unsigned int flags) { struct dentry *real; int err; + if (flags & D_REAL_UPPER) + return ovl_dentry_upper(dentry); + if (!d_is_reg(dentry)) { if (!inode || inode == d_inode(dentry)) return dentry; goto bug; } - if (d_is_negative(dentry)) - return dentry; - if (open_flags) { err = ovl_open_maybe_copy_up(dentry, open_flags); if (err) @@ -102,7 +105,7 @@ static struct dentry *ovl_d_real(struct dentry *dentry, goto bug; /* Handle recursion */ - real = d_real(real, inode, open_flags); + real = d_real(real, inode, open_flags, 0); if (!inode || inode == d_inode(real)) return real; @@ -165,12 +168,54 @@ static const struct dentry_operations ovl_reval_dentry_operations = { .d_weak_revalidate = ovl_dentry_weak_revalidate, }; +static struct kmem_cache *ovl_inode_cachep; + +static struct inode *ovl_alloc_inode(struct super_block *sb) +{ + struct ovl_inode *oi = kmem_cache_alloc(ovl_inode_cachep, GFP_KERNEL); + + oi->cache = NULL; + oi->redirect = NULL; + oi->version = 0; + oi->flags = 0; + oi->__upperdentry = NULL; + oi->lower = NULL; + mutex_init(&oi->lock); + + return &oi->vfs_inode; +} + +static void ovl_i_callback(struct rcu_head *head) +{ + struct inode *inode = container_of(head, struct inode, i_rcu); + + kmem_cache_free(ovl_inode_cachep, OVL_I(inode)); +} + +static void ovl_destroy_inode(struct inode *inode) +{ + struct ovl_inode *oi = OVL_I(inode); + + dput(oi->__upperdentry); + kfree(oi->redirect); + ovl_dir_cache_free(inode); + mutex_destroy(&oi->lock); + + call_rcu(&inode->i_rcu, ovl_i_callback); +} + static void ovl_put_super(struct super_block *sb) { struct ovl_fs *ufs = sb->s_fs_info; unsigned i; + dput(ufs->indexdir); dput(ufs->workdir); + if (ufs->workdir_locked) + ovl_inuse_unlock(ufs->workbasedir); + dput(ufs->workbasedir); + if (ufs->upper_mnt && ufs->upperdir_locked) + ovl_inuse_unlock(ufs->upper_mnt->mnt_root); mntput(ufs->upper_mnt); for (i = 0; i < ufs->numlower; i++) mntput(ufs->lower_mnt[i]); @@ -228,6 +273,12 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) return err; } +/* Will this overlay be forced to mount/remount ro? */ +static bool ovl_force_readonly(struct ovl_fs *ufs) +{ + return (!ufs->upper_mnt || !ufs->workdir); +} + /** * ovl_show_options * @@ -249,6 +300,9 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) if (ufs->config.redirect_dir != ovl_redirect_dir_def) seq_printf(m, ",redirect_dir=%s", ufs->config.redirect_dir ? "on" : "off"); + if (ufs->config.index != ovl_index_def) + seq_printf(m, ",index=%s", + ufs->config.index ? "on" : "off"); return 0; } @@ -256,19 +310,21 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data) { struct ovl_fs *ufs = sb->s_fs_info; - if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir)) + if (!(*flags & MS_RDONLY) && ovl_force_readonly(ufs)) return -EROFS; return 0; } static const struct super_operations ovl_super_operations = { + .alloc_inode = ovl_alloc_inode, + .destroy_inode = ovl_destroy_inode, + .drop_inode = generic_delete_inode, .put_super = ovl_put_super, .sync_fs = ovl_sync_fs, .statfs = ovl_statfs, .show_options = ovl_show_options, .remount_fs = ovl_remount, - .drop_inode = generic_delete_inode, }; enum { @@ -278,6 +334,8 @@ enum { OPT_DEFAULT_PERMISSIONS, OPT_REDIRECT_DIR_ON, OPT_REDIRECT_DIR_OFF, + OPT_INDEX_ON, + OPT_INDEX_OFF, OPT_ERR, }; @@ -288,6 +346,8 @@ static const match_table_t ovl_tokens = { {OPT_DEFAULT_PERMISSIONS, "default_permissions"}, {OPT_REDIRECT_DIR_ON, "redirect_dir=on"}, {OPT_REDIRECT_DIR_OFF, "redirect_dir=off"}, + {OPT_INDEX_ON, "index=on"}, + {OPT_INDEX_OFF, "index=off"}, {OPT_ERR, NULL} }; @@ -360,6 +420,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->redirect_dir = false; break; + case OPT_INDEX_ON: + config->index = true; + break; + + case OPT_INDEX_OFF: + config->index = false; + break; + default: pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p); return -EINVAL; @@ -378,23 +446,29 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) } #define OVL_WORKDIR_NAME "work" +#define OVL_INDEXDIR_NAME "index" -static struct dentry *ovl_workdir_create(struct vfsmount *mnt, - struct dentry *dentry) +static struct dentry *ovl_workdir_create(struct super_block *sb, + struct ovl_fs *ufs, + struct dentry *dentry, + const char *name, bool persist) { struct inode *dir = dentry->d_inode; + struct vfsmount *mnt = ufs->upper_mnt; struct dentry *work; int err; bool retried = false; + bool locked = false; err = mnt_want_write(mnt); if (err) - return ERR_PTR(err); + goto out_err; inode_lock_nested(dir, I_MUTEX_PARENT); + locked = true; + retry: - work = lookup_one_len(OVL_WORKDIR_NAME, dentry, - strlen(OVL_WORKDIR_NAME)); + work = lookup_one_len(name, dentry, strlen(name)); if (!IS_ERR(work)) { struct iattr attr = { @@ -407,6 +481,9 @@ retry: if (retried) goto out_dput; + if (persist) + goto out_unlock; + retried = true; ovl_workdir_cleanup(dir, mnt, work, 0); dput(work); @@ -446,16 +523,24 @@ retry: inode_unlock(work->d_inode); if (err) goto out_dput; + } else { + err = PTR_ERR(work); + goto out_err; } out_unlock: - inode_unlock(dir); mnt_drop_write(mnt); + if (locked) + inode_unlock(dir); return work; out_dput: dput(work); - work = ERR_PTR(err); +out_err: + pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n", + ufs->config.workdir, name, -err); + sb->s_flags |= MS_RDONLY; + work = NULL; goto out_unlock; } @@ -555,6 +640,15 @@ static int ovl_lower_dir(const char *name, struct path *path, if (ovl_dentry_remote(path->dentry)) *remote = true; + /* + * The inodes index feature needs to encode and decode file + * handles, so it requires that all layers support them. + */ + if (ofs->config.index && !ovl_can_decode_fh(path->dentry->d_sb)) { + ofs->config.index = false; + pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off.\n", name); + } + return 0; out_put: @@ -600,7 +694,7 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size) { - return ovl_xattr_get(dentry, handler->name, buffer, size); + return ovl_xattr_get(dentry, inode, handler->name, buffer, size); } static int __maybe_unused @@ -610,7 +704,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, size_t size, int flags) { struct dentry *workdir = ovl_workdir(dentry); - struct inode *realinode = ovl_inode_real(inode, NULL); + struct inode *realinode = ovl_inode_real(inode); struct posix_acl *acl = NULL; int err; @@ -650,9 +744,9 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, return err; } - err = ovl_xattr_set(dentry, handler->name, value, size, flags); + err = ovl_xattr_set(dentry, inode, handler->name, value, size, flags); if (!err) - ovl_copyattr(ovl_inode_real(inode, NULL), inode); + ovl_copyattr(ovl_inode_real(inode), inode); return err; @@ -680,7 +774,7 @@ static int ovl_other_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *name, void *buffer, size_t size) { - return ovl_xattr_get(dentry, name, buffer, size); + return ovl_xattr_get(dentry, inode, name, buffer, size); } static int ovl_other_xattr_set(const struct xattr_handler *handler, @@ -688,7 +782,7 @@ static int ovl_other_xattr_set(const struct xattr_handler *handler, const char *name, const void *value, size_t size, int flags) { - return ovl_xattr_set(dentry, name, value, size, flags); + return ovl_xattr_set(dentry, inode, name, value, size, flags); } static const struct xattr_handler __maybe_unused @@ -734,7 +828,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) struct path upperpath = { }; struct path workpath = { }; struct dentry *root_dentry; - struct inode *realinode; struct ovl_entry *oe; struct ovl_fs *ufs; struct path *stack = NULL; @@ -752,8 +845,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!ufs) goto out; - init_waitqueue_head(&ufs->copyup_wq); ufs->config.redirect_dir = ovl_redirect_dir_def; + ufs->config.index = ovl_index_def; err = ovl_parse_opt((char *) data, &ufs->config); if (err) goto out_free_config; @@ -778,7 +871,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) goto out_free_config; /* Upper fs should not be r/o */ - if (upperpath.mnt->mnt_sb->s_flags & MS_RDONLY) { + if (sb_rdonly(upperpath.mnt->mnt_sb)) { pr_err("overlayfs: upper fs is r/o, try multi-lower layers mount\n"); err = -EINVAL; goto out_put_upperpath; @@ -788,9 +881,19 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (err) goto out_put_upperpath; + err = -EBUSY; + if (ovl_inuse_trylock(upperpath.dentry)) { + ufs->upperdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); + goto out_put_upperpath; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); + } + err = ovl_mount_dir(ufs->config.workdir, &workpath); if (err) - goto out_put_upperpath; + goto out_unlock_upperdentry; err = -EINVAL; if (upperpath.mnt != workpath.mnt) { @@ -801,12 +904,24 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) pr_err("overlayfs: workdir and upperdir must be separate subtrees\n"); goto out_put_workpath; } + + err = -EBUSY; + if (ovl_inuse_trylock(workpath.dentry)) { + ufs->workdir_locked = true; + } else if (ufs->config.index) { + pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); + goto out_put_workpath; + } else { + pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); + } + + ufs->workbasedir = workpath.dentry; sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth; } err = -ENOMEM; lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL); if (!lowertmp) - goto out_put_workpath; + goto out_unlock_workdentry; err = -EINVAL; stacklen = ovl_split_lowerdirs(lowertmp); @@ -849,20 +964,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) pr_err("overlayfs: failed to clone upperpath\n"); goto out_put_lowerpath; } + /* Don't inherit atime flags */ ufs->upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME); sb->s_time_gran = ufs->upper_mnt->mnt_sb->s_time_gran; - ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry); - err = PTR_ERR(ufs->workdir); - if (IS_ERR(ufs->workdir)) { - pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n", - ufs->config.workdir, OVL_WORKDIR_NAME, -err); - sb->s_flags |= MS_RDONLY; - ufs->workdir = NULL; - } - + ufs->workdir = ovl_workdir_create(sb, ufs, workpath.dentry, + OVL_WORKDIR_NAME, false); /* * Upper should support d_type, else whiteouts are visible. * Given workdir and upper are on same fs, we can do @@ -904,6 +1013,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } else { vfs_removexattr(ufs->workdir, OVL_XATTR_OPAQUE); } + + /* Check if upper/work fs supports file handles */ + if (ufs->config.index && + !ovl_can_decode_fh(ufs->workdir->d_sb)) { + ufs->config.index = false; + pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n"); + } } } @@ -941,14 +1057,49 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) else if (ufs->upper_mnt->mnt_sb != ufs->same_sb) ufs->same_sb = NULL; + if (!(ovl_force_readonly(ufs)) && ufs->config.index) { + /* Verify lower root is upper root origin */ + err = ovl_verify_origin(upperpath.dentry, ufs->lower_mnt[0], + stack[0].dentry, false, true); + if (err) { + pr_err("overlayfs: failed to verify upper root origin\n"); + goto out_put_lower_mnt; + } + + ufs->indexdir = ovl_workdir_create(sb, ufs, workpath.dentry, + OVL_INDEXDIR_NAME, true); + if (ufs->indexdir) { + /* Verify upper root is index dir origin */ + err = ovl_verify_origin(ufs->indexdir, ufs->upper_mnt, + upperpath.dentry, true, true); + if (err) + pr_err("overlayfs: failed to verify index dir origin\n"); + + /* Cleanup bad/stale/orphan index entries */ + if (!err) + err = ovl_indexdir_cleanup(ufs->indexdir, + ufs->upper_mnt, + stack, numlower); + } + if (err || !ufs->indexdir) + pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n"); + if (err) + goto out_put_indexdir; + } + + /* Show index=off/on in /proc/mounts for any of the reasons above */ + if (!ufs->indexdir) + ufs->config.index = false; + if (remote) sb->s_d_op = &ovl_reval_dentry_operations; else sb->s_d_op = &ovl_dentry_operations; + err = -ENOMEM; ufs->creator_cred = cred = prepare_creds(); if (!cred) - goto out_put_lower_mnt; + goto out_put_indexdir; /* Never override disk quota limits or use reserved space */ cap_lower(cred->cap_effective, CAP_SYS_RESOURCE); @@ -971,12 +1122,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) mntput(upperpath.mnt); for (i = 0; i < numlower; i++) mntput(stack[i].mnt); - path_put(&workpath); + mntput(workpath.mnt); kfree(lowertmp); if (upperpath.dentry) { - oe->__upperdentry = upperpath.dentry; - oe->impure = ovl_is_impuredir(upperpath.dentry); + oe->has_upper = true; + if (ovl_is_impuredir(upperpath.dentry)) + ovl_set_flag(OVL_IMPURE, d_inode(root_dentry)); } for (i = 0; i < numlower; i++) { oe->lowerstack[i].dentry = stack[i].dentry; @@ -986,9 +1138,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) root_dentry->d_fsdata = oe; - realinode = d_inode(ovl_dentry_real(root_dentry)); - ovl_inode_init(d_inode(root_dentry), realinode, !!upperpath.dentry); - ovl_copyattr(realinode, d_inode(root_dentry)); + ovl_inode_init(d_inode(root_dentry), upperpath.dentry, + ovl_dentry_lower(root_dentry)); sb->s_root = root_dentry; @@ -998,6 +1149,8 @@ out_free_oe: kfree(oe); out_put_cred: put_cred(ufs->creator_cred); +out_put_indexdir: + dput(ufs->indexdir); out_put_lower_mnt: for (i = 0; i < ufs->numlower; i++) mntput(ufs->lower_mnt[i]); @@ -1011,8 +1164,14 @@ out_put_lowerpath: kfree(stack); out_free_lowertmp: kfree(lowertmp); +out_unlock_workdentry: + if (ufs->workdir_locked) + ovl_inuse_unlock(workpath.dentry); out_put_workpath: path_put(&workpath); +out_unlock_upperdentry: + if (ufs->upperdir_locked) + ovl_inuse_unlock(upperpath.dentry); out_put_upperpath: path_put(&upperpath); out_free_config: @@ -1038,14 +1197,43 @@ static struct file_system_type ovl_fs_type = { }; MODULE_ALIAS_FS("overlay"); +static void ovl_inode_init_once(void *foo) +{ + struct ovl_inode *oi = foo; + + inode_init_once(&oi->vfs_inode); +} + static int __init ovl_init(void) { - return register_filesystem(&ovl_fs_type); + int err; + + ovl_inode_cachep = kmem_cache_create("ovl_inode", + sizeof(struct ovl_inode), 0, + (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD|SLAB_ACCOUNT), + ovl_inode_init_once); + if (ovl_inode_cachep == NULL) + return -ENOMEM; + + err = register_filesystem(&ovl_fs_type); + if (err) + kmem_cache_destroy(ovl_inode_cachep); + + return err; } static void __exit ovl_exit(void) { unregister_filesystem(&ovl_fs_type); + + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(ovl_inode_cachep); + } module_init(ovl_init); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 809048913889..b9b239fa5cfd 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -12,6 +12,10 @@ #include <linux/slab.h> #include <linux/cred.h> #include <linux/xattr.h> +#include <linux/exportfs.h> +#include <linux/uuid.h> +#include <linux/namei.h> +#include <linux/ratelimit.h> #include "overlayfs.h" #include "ovl_entry.h" @@ -47,6 +51,19 @@ struct super_block *ovl_same_sb(struct super_block *sb) return ofs->same_sb; } +bool ovl_can_decode_fh(struct super_block *sb) +{ + return (sb->s_export_op && sb->s_export_op->fh_to_dentry && + !uuid_is_null(&sb->s_uuid)); +} + +struct dentry *ovl_indexdir(struct super_block *sb) +{ + struct ovl_fs *ofs = sb->s_fs_info; + + return ofs->indexdir; +} + struct ovl_entry *ovl_alloc_entry(unsigned int numlower) { size_t size = offsetof(struct ovl_entry, lowerstack[numlower]); @@ -78,7 +95,7 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) struct ovl_entry *oe = dentry->d_fsdata; enum ovl_path_type type = 0; - if (oe->__upperdentry) { + if (ovl_dentry_upper(dentry)) { type = __OVL_PATH_UPPER; /* @@ -99,10 +116,9 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry) void ovl_path_upper(struct dentry *dentry, struct path *path) { struct ovl_fs *ofs = dentry->d_sb->s_fs_info; - struct ovl_entry *oe = dentry->d_fsdata; path->mnt = ofs->upper_mnt; - path->dentry = ovl_upperdentry_dereference(oe); + path->dentry = ovl_dentry_upper(dentry); } void ovl_path_lower(struct dentry *dentry, struct path *path) @@ -126,47 +142,52 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path) struct dentry *ovl_dentry_upper(struct dentry *dentry) { - struct ovl_entry *oe = dentry->d_fsdata; - - return ovl_upperdentry_dereference(oe); -} - -static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe) -{ - return oe->numlower ? oe->lowerstack[0].dentry : NULL; + return ovl_upperdentry_dereference(OVL_I(d_inode(dentry))); } struct dentry *ovl_dentry_lower(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; - return __ovl_dentry_lower(oe); + return oe->numlower ? oe->lowerstack[0].dentry : NULL; } struct dentry *ovl_dentry_real(struct dentry *dentry) { - struct ovl_entry *oe = dentry->d_fsdata; - struct dentry *realdentry; + return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry); +} - realdentry = ovl_upperdentry_dereference(oe); - if (!realdentry) - realdentry = __ovl_dentry_lower(oe); +struct dentry *ovl_i_dentry_upper(struct inode *inode) +{ + return ovl_upperdentry_dereference(OVL_I(inode)); +} - return realdentry; +struct inode *ovl_inode_upper(struct inode *inode) +{ + struct dentry *upperdentry = ovl_i_dentry_upper(inode); + + return upperdentry ? d_inode(upperdentry) : NULL; } -struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry) +struct inode *ovl_inode_lower(struct inode *inode) { - struct ovl_entry *oe = dentry->d_fsdata; + return OVL_I(inode)->lower; +} - return oe->cache; +struct inode *ovl_inode_real(struct inode *inode) +{ + return ovl_inode_upper(inode) ?: ovl_inode_lower(inode); } -void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache) + +struct ovl_dir_cache *ovl_dir_cache(struct inode *inode) { - struct ovl_entry *oe = dentry->d_fsdata; + return OVL_I(inode)->cache; +} - oe->cache = cache; +void ovl_set_dir_cache(struct inode *inode, struct ovl_dir_cache *cache) +{ + OVL_I(inode)->cache = cache; } bool ovl_dentry_is_opaque(struct dentry *dentry) @@ -175,23 +196,35 @@ bool ovl_dentry_is_opaque(struct dentry *dentry) return oe->opaque; } -bool ovl_dentry_is_impure(struct dentry *dentry) +bool ovl_dentry_is_whiteout(struct dentry *dentry) +{ + return !dentry->d_inode && ovl_dentry_is_opaque(dentry); +} + +void ovl_dentry_set_opaque(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; - return oe->impure; + oe->opaque = true; } -bool ovl_dentry_is_whiteout(struct dentry *dentry) +/* + * For hard links it's possible for ovl_dentry_upper() to return positive, while + * there's no actual upper alias for the inode. Copy up code needs to know + * about the existence of the upper alias, so it can't use ovl_dentry_upper(). + */ +bool ovl_dentry_has_upper_alias(struct dentry *dentry) { - return !dentry->d_inode && ovl_dentry_is_opaque(dentry); + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->has_upper; } -void ovl_dentry_set_opaque(struct dentry *dentry) +void ovl_dentry_set_upper_alias(struct dentry *dentry) { struct ovl_entry *oe = dentry->d_fsdata; - oe->opaque = true; + oe->has_upper = true; } bool ovl_redirect_dir(struct super_block *sb) @@ -203,63 +236,66 @@ bool ovl_redirect_dir(struct super_block *sb) const char *ovl_dentry_get_redirect(struct dentry *dentry) { - struct ovl_entry *oe = dentry->d_fsdata; - - return oe->redirect; + return OVL_I(d_inode(dentry))->redirect; } void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect) { - struct ovl_entry *oe = dentry->d_fsdata; + struct ovl_inode *oi = OVL_I(d_inode(dentry)); - kfree(oe->redirect); - oe->redirect = redirect; + kfree(oi->redirect); + oi->redirect = redirect; } -void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry) +void ovl_inode_init(struct inode *inode, struct dentry *upperdentry, + struct dentry *lowerdentry) { - struct ovl_entry *oe = dentry->d_fsdata; + if (upperdentry) + OVL_I(inode)->__upperdentry = upperdentry; + if (lowerdentry) + OVL_I(inode)->lower = d_inode(lowerdentry); - WARN_ON(!inode_is_locked(upperdentry->d_parent->d_inode)); - WARN_ON(oe->__upperdentry); - /* - * Make sure upperdentry is consistent before making it visible to - * ovl_upperdentry_dereference(). - */ - smp_wmb(); - oe->__upperdentry = upperdentry; + ovl_copyattr(d_inode(upperdentry ?: lowerdentry), inode); } -void ovl_inode_init(struct inode *inode, struct inode *realinode, bool is_upper) +void ovl_inode_update(struct inode *inode, struct dentry *upperdentry) { - WRITE_ONCE(inode->i_private, (unsigned long) realinode | - (is_upper ? OVL_ISUPPER_MASK : 0)); -} + struct inode *upperinode = d_inode(upperdentry); -void ovl_inode_update(struct inode *inode, struct inode *upperinode) -{ - WARN_ON(!upperinode); - WARN_ON(!inode_unhashed(inode)); - WRITE_ONCE(inode->i_private, - (unsigned long) upperinode | OVL_ISUPPER_MASK); - if (!S_ISDIR(upperinode->i_mode)) + WARN_ON(OVL_I(inode)->__upperdentry); + + /* + * Make sure upperdentry is consistent before making it visible + */ + smp_wmb(); + OVL_I(inode)->__upperdentry = upperdentry; + if (!S_ISDIR(upperinode->i_mode) && inode_unhashed(inode)) { + inode->i_private = upperinode; __insert_inode_hash(inode, (unsigned long) upperinode); + } } -void ovl_dentry_version_inc(struct dentry *dentry) +void ovl_dentry_version_inc(struct dentry *dentry, bool impurity) { - struct ovl_entry *oe = dentry->d_fsdata; + struct inode *inode = d_inode(dentry); - WARN_ON(!inode_is_locked(dentry->d_inode)); - oe->version++; + WARN_ON(!inode_is_locked(inode)); + /* + * Version is used by readdir code to keep cache consistent. For merge + * dirs all changes need to be noted. For non-merge dirs, cache only + * contains impure (ones which have been copied up and have origins) + * entries, so only need to note changes to impure entries. + */ + if (OVL_TYPE_MERGE(ovl_path_type(dentry)) || impurity) + OVL_I(inode)->version++; } u64 ovl_dentry_version_get(struct dentry *dentry) { - struct ovl_entry *oe = dentry->d_fsdata; + struct inode *inode = d_inode(dentry); - WARN_ON(!inode_is_locked(dentry->d_inode)); - return oe->version; + WARN_ON(!inode_is_locked(inode)); + return OVL_I(inode)->version; } bool ovl_is_whiteout(struct dentry *dentry) @@ -276,32 +312,21 @@ struct file *ovl_path_open(struct path *path, int flags) int ovl_copy_up_start(struct dentry *dentry) { - struct ovl_fs *ofs = dentry->d_sb->s_fs_info; - struct ovl_entry *oe = dentry->d_fsdata; + struct ovl_inode *oi = OVL_I(d_inode(dentry)); int err; - spin_lock(&ofs->copyup_wq.lock); - err = wait_event_interruptible_locked(ofs->copyup_wq, !oe->copying); - if (!err) { - if (oe->__upperdentry) - err = 1; /* Already copied up */ - else - oe->copying = true; + err = mutex_lock_interruptible(&oi->lock); + if (!err && ovl_dentry_has_upper_alias(dentry)) { + err = 1; /* Already copied up */ + mutex_unlock(&oi->lock); } - spin_unlock(&ofs->copyup_wq.lock); return err; } void ovl_copy_up_end(struct dentry *dentry) { - struct ovl_fs *ofs = dentry->d_sb->s_fs_info; - struct ovl_entry *oe = dentry->d_fsdata; - - spin_lock(&ofs->copyup_wq.lock); - oe->copying = false; - wake_up_locked(&ofs->copyup_wq); - spin_unlock(&ofs->copyup_wq.lock); + mutex_unlock(&OVL_I(d_inode(dentry))->lock); } bool ovl_check_dir_xattr(struct dentry *dentry, const char *name) @@ -343,9 +368,8 @@ int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry, int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry) { int err; - struct ovl_entry *oe = dentry->d_fsdata; - if (oe->impure) + if (ovl_test_flag(OVL_IMPURE, d_inode(dentry))) return 0; /* @@ -355,7 +379,203 @@ int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry) err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE, "y", 1, 0); if (!err) - oe->impure = true; + ovl_set_flag(OVL_IMPURE, d_inode(dentry)); return err; } + +void ovl_set_flag(unsigned long flag, struct inode *inode) +{ + set_bit(flag, &OVL_I(inode)->flags); +} + +void ovl_clear_flag(unsigned long flag, struct inode *inode) +{ + clear_bit(flag, &OVL_I(inode)->flags); +} + +bool ovl_test_flag(unsigned long flag, struct inode *inode) +{ + return test_bit(flag, &OVL_I(inode)->flags); +} + +/** + * Caller must hold a reference to inode to prevent it from being freed while + * it is marked inuse. + */ +bool ovl_inuse_trylock(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + bool locked = false; + + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_OVL_INUSE)) { + inode->i_state |= I_OVL_INUSE; + locked = true; + } + spin_unlock(&inode->i_lock); + + return locked; +} + +void ovl_inuse_unlock(struct dentry *dentry) +{ + if (dentry) { + struct inode *inode = d_inode(dentry); + + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_OVL_INUSE)); + inode->i_state &= ~I_OVL_INUSE; + spin_unlock(&inode->i_lock); + } +} + +/* Caller must hold OVL_I(inode)->lock */ +static void ovl_cleanup_index(struct dentry *dentry) +{ + struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode; + struct dentry *lowerdentry = ovl_dentry_lower(dentry); + struct dentry *upperdentry = ovl_dentry_upper(dentry); + struct dentry *index = NULL; + struct inode *inode; + struct qstr name; + int err; + + err = ovl_get_index_name(lowerdentry, &name); + if (err) + goto fail; + + inode = d_inode(upperdentry); + if (inode->i_nlink != 1) { + pr_warn_ratelimited("overlayfs: cleanup linked index (%pd2, ino=%lu, nlink=%u)\n", + upperdentry, inode->i_ino, inode->i_nlink); + /* + * We either have a bug with persistent union nlink or a lower + * hardlink was added while overlay is mounted. Adding a lower + * hardlink and then unlinking all overlay hardlinks would drop + * overlay nlink to zero before all upper inodes are unlinked. + * As a safety measure, when that situation is detected, set + * the overlay nlink to the index inode nlink minus one for the + * index entry itself. + */ + set_nlink(d_inode(dentry), inode->i_nlink - 1); + ovl_set_nlink_upper(dentry); + goto out; + } + + inode_lock_nested(dir, I_MUTEX_PARENT); + /* TODO: whiteout instead of cleanup to block future open by handle */ + index = lookup_one_len(name.name, ovl_indexdir(dentry->d_sb), name.len); + err = PTR_ERR(index); + if (!IS_ERR(index)) + err = ovl_cleanup(dir, index); + else + index = NULL; + + inode_unlock(dir); + if (err) + goto fail; + +out: + dput(index); + return; + +fail: + pr_err("overlayfs: cleanup index of '%pd2' failed (%i)\n", dentry, err); + goto out; +} + +/* + * Operations that change overlay inode and upper inode nlink need to be + * synchronized with copy up for persistent nlink accounting. + */ +int ovl_nlink_start(struct dentry *dentry, bool *locked) +{ + struct ovl_inode *oi = OVL_I(d_inode(dentry)); + const struct cred *old_cred; + int err; + + if (!d_inode(dentry) || d_is_dir(dentry)) + return 0; + + /* + * With inodes index is enabled, we store the union overlay nlink + * in an xattr on the index inode. When whiting out lower hardlinks + * we need to decrement the overlay persistent nlink, but before the + * first copy up, we have no upper index inode to store the xattr. + * + * As a workaround, before whiteout/rename over of a lower hardlink, + * copy up to create the upper index. Creating the upper index will + * initialize the overlay nlink, so it could be dropped if unlink + * or rename succeeds. + * + * TODO: implement metadata only index copy up when called with + * ovl_copy_up_flags(dentry, O_PATH). + */ + if (ovl_indexdir(dentry->d_sb) && !ovl_dentry_has_upper_alias(dentry) && + d_inode(ovl_dentry_lower(dentry))->i_nlink > 1) { + err = ovl_copy_up(dentry); + if (err) + return err; + } + + err = mutex_lock_interruptible(&oi->lock); + if (err) + return err; + + if (!ovl_test_flag(OVL_INDEX, d_inode(dentry))) + goto out; + + old_cred = ovl_override_creds(dentry->d_sb); + /* + * The overlay inode nlink should be incremented/decremented IFF the + * upper operation succeeds, along with nlink change of upper inode. + * Therefore, before link/unlink/rename, we store the union nlink + * value relative to the upper inode nlink in an upper inode xattr. + */ + err = ovl_set_nlink_upper(dentry); + revert_creds(old_cred); + +out: + if (err) + mutex_unlock(&oi->lock); + else + *locked = true; + + return err; +} + +void ovl_nlink_end(struct dentry *dentry, bool locked) +{ + if (locked) { + if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) && + d_inode(dentry)->i_nlink == 0) { + const struct cred *old_cred; + + old_cred = ovl_override_creds(dentry->d_sb); + ovl_cleanup_index(dentry); + revert_creds(old_cred); + } + + mutex_unlock(&OVL_I(d_inode(dentry))->lock); + } +} + +int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) +{ + /* Workdir should not be the same as upperdir */ + if (workdir == upperdir) + goto err; + + /* Workdir should not be subdir of upperdir and vice versa */ + if (lock_rename(workdir, upperdir) != NULL) + goto err_unlock; + + return 0; + +err_unlock: + unlock_rename(workdir, upperdir); +err: + pr_err("overlayfs: failed to lock workdir+upperdir\n"); + return -EIO; +} diff --git a/fs/pipe.c b/fs/pipe.c index 73b84baf58f8..97e5be897753 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -739,13 +739,12 @@ int create_pipe_files(struct file **res, int flags) struct inode *inode = get_pipe_inode(); struct file *f; struct path path; - static struct qstr name = { .name = "" }; if (!inode) return -ENFILE; err = -ENOMEM; - path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name); + path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name); if (!path.dentry) goto err_inode; path.mnt = mntget(pipe_mnt); diff --git a/fs/pnode.c b/fs/pnode.c index 5bc7896d122a..53d411a371ce 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p) return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave); } +static inline struct mount *last_slave(struct mount *p) +{ + return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave); +} + static inline struct mount *next_slave(struct mount *p) { return list_entry(p->mnt_slave.next, struct mount, mnt_slave); @@ -162,6 +167,19 @@ static struct mount *propagation_next(struct mount *m, } } +static struct mount *skip_propagation_subtree(struct mount *m, + struct mount *origin) +{ + /* + * Advance m such that propagation_next will not return + * the slaves of m. + */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + m = last_slave(m); + + return m; +} + static struct mount *next_group(struct mount *m, struct mount *origin) { while (1) { @@ -413,65 +431,104 @@ void propagate_mount_unlock(struct mount *mnt) } } -/* - * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted. - */ -static void mark_umount_candidates(struct mount *mnt) +static void umount_one(struct mount *mnt, struct list_head *to_umount) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; - - BUG_ON(parent == mnt); - - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt(&m->mnt, - mnt->mnt_mountpoint); - if (!child || (child->mnt.mnt_flags & MNT_UMOUNT)) - continue; - if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) { - SET_MNT_MARK(child); - } - } + CLEAR_MNT_MARK(mnt); + mnt->mnt.mnt_flags |= MNT_UMOUNT; + list_del_init(&mnt->mnt_child); + list_del_init(&mnt->mnt_umounting); + list_move_tail(&mnt->mnt_list, to_umount); } /* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */ -static void __propagate_umount(struct mount *mnt) +static bool __propagate_umount(struct mount *mnt, + struct list_head *to_umount, + struct list_head *to_restore) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; + bool progress = false; + struct mount *child; - BUG_ON(parent == mnt); + /* + * The state of the parent won't change if this mount is + * already unmounted or marked as without children. + */ + if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED)) + goto out; - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *topper; - struct mount *child = __lookup_mnt(&m->mnt, - mnt->mnt_mountpoint); - /* - * umount the child only if the child has no children - * and the child is marked safe to unmount. - */ - if (!child || !IS_MNT_MARKED(child)) + /* Verify topper is the only grandchild that has not been + * speculatively unmounted. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (child->mnt_mountpoint == mnt->mnt.mnt_root) continue; - CLEAR_MNT_MARK(child); + if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child)) + continue; + /* Found a mounted child */ + goto children; + } - /* If there is exactly one mount covering all of child - * replace child with that mount. - */ - topper = find_topper(child); - if (topper) - mnt_change_mountpoint(child->mnt_parent, child->mnt_mp, - topper); + /* Mark mounts that can be unmounted if not locked */ + SET_MNT_MARK(mnt); + progress = true; + + /* If a mount is without children and not locked umount it. */ + if (!IS_MNT_LOCKED(mnt)) { + umount_one(mnt, to_umount); + } else { +children: + list_move_tail(&mnt->mnt_umounting, to_restore); + } +out: + return progress; +} + +static void umount_list(struct list_head *to_umount, + struct list_head *to_restore) +{ + struct mount *mnt, *child, *tmp; + list_for_each_entry(mnt, to_umount, mnt_list) { + list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) { + /* topper? */ + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + list_move_tail(&child->mnt_umounting, to_restore); + else + umount_one(child, to_umount); + } + } +} - if (list_empty(&child->mnt_mounts)) { - list_del_init(&child->mnt_child); - child->mnt.mnt_flags |= MNT_UMOUNT; - list_move_tail(&child->mnt_list, &mnt->mnt_list); +static void restore_mounts(struct list_head *to_restore) +{ + /* Restore mounts to a clean working state */ + while (!list_empty(to_restore)) { + struct mount *mnt, *parent; + struct mountpoint *mp; + + mnt = list_first_entry(to_restore, struct mount, mnt_umounting); + CLEAR_MNT_MARK(mnt); + list_del_init(&mnt->mnt_umounting); + + /* Should this mount be reparented? */ + mp = mnt->mnt_mp; + parent = mnt->mnt_parent; + while (parent->mnt.mnt_flags & MNT_UMOUNT) { + mp = parent->mnt_mp; + parent = parent->mnt_parent; } + if (parent != mnt->mnt_parent) + mnt_change_mountpoint(parent, mp, mnt); + } +} + +static void cleanup_umount_visitations(struct list_head *visited) +{ + while (!list_empty(visited)) { + struct mount *mnt = + list_first_entry(visited, struct mount, mnt_umounting); + list_del_init(&mnt->mnt_umounting); } } @@ -485,11 +542,68 @@ static void __propagate_umount(struct mount *mnt) int propagate_umount(struct list_head *list) { struct mount *mnt; + LIST_HEAD(to_restore); + LIST_HEAD(to_umount); + LIST_HEAD(visited); + + /* Find candidates for unmounting */ + list_for_each_entry_reverse(mnt, list, mnt_list) { + struct mount *parent = mnt->mnt_parent; + struct mount *m; + + /* + * If this mount has already been visited it is known that it's + * entire peer group and all of their slaves in the propagation + * tree for the mountpoint has already been visited and there is + * no need to visit them again. + */ + if (!list_empty(&mnt->mnt_umounting)) + continue; + + list_add_tail(&mnt->mnt_umounting, &visited); + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + struct mount *child = __lookup_mnt(&m->mnt, + mnt->mnt_mountpoint); + if (!child) + continue; + + if (!list_empty(&child->mnt_umounting)) { + /* + * If the child has already been visited it is + * know that it's entire peer group and all of + * their slaves in the propgation tree for the + * mountpoint has already been visited and there + * is no need to visit this subtree again. + */ + m = skip_propagation_subtree(m, parent); + continue; + } else if (child->mnt.mnt_flags & MNT_UMOUNT) { + /* + * We have come accross an partially unmounted + * mount in list that has not been visited yet. + * Remember it has been visited and continue + * about our merry way. + */ + list_add_tail(&child->mnt_umounting, &visited); + continue; + } + + /* Check the child and parents while progress is made */ + while (__propagate_umount(child, + &to_umount, &to_restore)) { + /* Is the parent a umount candidate? */ + child = child->mnt_parent; + if (list_empty(&child->mnt_umounting)) + break; + } + } + } - list_for_each_entry_reverse(mnt, list, mnt_list) - mark_umount_candidates(mnt); + umount_list(&to_umount, &to_restore); + restore_mounts(&to_restore); + cleanup_umount_visitations(&visited); + list_splice_tail(&to_umount, list); - list_for_each_entry(mnt, list, mnt_list) - __propagate_umount(mnt); return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 88c355574aa0..77a8eacbe032 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -62,6 +62,7 @@ #include <linux/mman.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> +#include <linux/sched/task_stack.h> #include <linux/sched/task.h> #include <linux/sched/cputime.h> #include <linux/proc_fs.h> @@ -118,30 +119,25 @@ static inline void task_name(struct seq_file *m, struct task_struct *p) * simple bit tests. */ static const char * const task_state_array[] = { - "R (running)", /* 0 */ - "S (sleeping)", /* 1 */ - "D (disk sleep)", /* 2 */ - "T (stopped)", /* 4 */ - "t (tracing stop)", /* 8 */ - "X (dead)", /* 16 */ - "Z (zombie)", /* 32 */ + + /* states in TASK_REPORT: */ + "R (running)", /* 0x00 */ + "S (sleeping)", /* 0x01 */ + "D (disk sleep)", /* 0x02 */ + "T (stopped)", /* 0x04 */ + "t (tracing stop)", /* 0x08 */ + "X (dead)", /* 0x10 */ + "Z (zombie)", /* 0x20 */ + "P (parked)", /* 0x40 */ + + /* states beyond TASK_REPORT: */ + "I (idle)", /* 0x80 */ }; static inline const char *get_task_state(struct task_struct *tsk) { - unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT; - - /* - * Parked tasks do not run; they sit in __kthread_parkme(). - * Without this check, we would report them as running, which is - * clearly wrong, so we report them as sleeping instead. - */ - if (tsk->state == TASK_PARKED) - state = TASK_INTERRUPTIBLE; - - BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1); - - return task_state_array[fls(state)]; + BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array)); + return task_state_array[__get_task_state(tsk)]; } static inline int get_task_umask(struct task_struct *tsk) @@ -421,7 +417,15 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * esp and eip are intentionally zeroed out. There is no * non-racy way to read them without freezing the task. * Programs that need reliable values can use ptrace(2). + * + * The only exception is if the task is core dumping because + * a program is not able to use ptrace(2) in that case. It is + * safe because the task has stopped executing permanently. */ + if (permitted && (task->flags & PF_DUMPCORE)) { + eip = KSTK_EIP(task); + esp = KSTK_ESP(task); + } } get_task_comm(tcomm, task); diff --git a/fs/proc/base.c b/fs/proc/base.c index f1e1927ccd48..ad3b0762cc3e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -232,7 +232,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, goto out_mmput; } - page = (char *)__get_free_page(GFP_TEMPORARY); + page = (char *)__get_free_page(GFP_KERNEL); if (!page) { rv = -ENOMEM; goto out_mmput; @@ -813,7 +813,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, if (!mm) return 0; - page = (char *)__get_free_page(GFP_TEMPORARY); + page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; @@ -918,7 +918,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, if (!mm || !mm->env_end) return 0; - page = (char *)__get_free_page(GFP_TEMPORARY); + page = (char *)__get_free_page(GFP_KERNEL); if (!page) return -ENOMEM; @@ -1355,6 +1355,49 @@ static const struct file_operations proc_fault_inject_operations = { .write = proc_fault_inject_write, .llseek = generic_file_llseek, }; + +static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + int err; + unsigned int n; + + err = kstrtouint_from_user(buf, count, 0, &n); + if (err) + return err; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + WRITE_ONCE(task->fail_nth, n); + put_task_struct(task); + + return count; +} + +static ssize_t proc_fail_nth_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char numbuf[PROC_NUMBUF]; + ssize_t len; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + len = snprintf(numbuf, sizeof(numbuf), "%u\n", + READ_ONCE(task->fail_nth)); + len = simple_read_from_buffer(buf, count, ppos, numbuf, len); + put_task_struct(task); + + return len; +} + +static const struct file_operations proc_fail_nth_operations = { + .read = proc_fail_nth_read, + .write = proc_fail_nth_write, +}; #endif @@ -1365,12 +1408,13 @@ static const struct file_operations proc_fault_inject_operations = { static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; + struct pid_namespace *ns = inode->i_sb->s_fs_info; struct task_struct *p; p = get_proc_task(inode); if (!p) return -ESRCH; - proc_sched_show_task(p, m); + proc_sched_show_task(p, ns, m); put_task_struct(p); @@ -1586,7 +1630,7 @@ out: static int do_proc_readlink(struct path *path, char __user *buffer, int buflen) { - char *tmp = (char*)__get_free_page(GFP_TEMPORARY); + char *tmp = (char *)__get_free_page(GFP_KERNEL); char *pathname; int len; @@ -2887,6 +2931,7 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_pid_smaps_operations), + REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY @@ -2919,6 +2964,7 @@ static const struct pid_entry tgid_base_stuff[] = { #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), + REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_ELF_CORE REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), @@ -3279,6 +3325,7 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_PROC_PAGE_MONITOR REG("clear_refs", S_IWUSR, proc_clear_refs_operations), REG("smaps", S_IRUGO, proc_tid_smaps_operations), + REG("smaps_rollup", S_IRUGO, proc_pid_smaps_rollup_operations), REG("pagemap", S_IRUSR, proc_pagemap_operations), #endif #ifdef CONFIG_SECURITY @@ -3311,6 +3358,7 @@ static const struct pid_entry tid_base_stuff[] = { #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), + REG("fail-nth", 0644, proc_fail_nth_operations), #endif #ifdef CONFIG_TASK_IO_ACCOUNTING ONE("io", S_IRUSR, proc_tid_io_accounting), diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 50493edc30e5..e5709343feb7 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -7,14 +7,14 @@ static int devinfo_show(struct seq_file *f, void *v) { int i = *(loff_t *) v; - if (i < CHRDEV_MAJOR_HASH_SIZE) { + if (i < CHRDEV_MAJOR_MAX) { if (i == 0) seq_puts(f, "Character devices:\n"); chrdev_show(f, i); } #ifdef CONFIG_BLOCK else { - i -= CHRDEV_MAJOR_HASH_SIZE; + i -= CHRDEV_MAJOR_MAX; if (i == 0) seq_puts(f, "\nBlock devices:\n"); blkdev_show(f, i); @@ -25,7 +25,7 @@ static int devinfo_show(struct seq_file *f, void *v) static void *devinfo_start(struct seq_file *f, loff_t *pos) { - if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + if (*pos < (BLKDEV_MAJOR_MAX + CHRDEV_MAJOR_MAX)) return pos; return NULL; } @@ -33,7 +33,7 @@ static void *devinfo_start(struct seq_file *f, loff_t *pos) static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos) { (*pos)++; - if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE)) + if (*pos >= (BLKDEV_MAJOR_MAX + CHRDEV_MAJOR_MAX)) return NULL; return pos; } diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 9425c0d97262..793a67574668 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -40,8 +40,8 @@ static int proc_match(unsigned int len, const char *name, struct proc_dir_entry static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir) { - return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry, - subdir_node); + return rb_entry_safe(rb_first_cached(&dir->subdir), + struct proc_dir_entry, subdir_node); } static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir) @@ -54,7 +54,7 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, const char *name, unsigned int len) { - struct rb_node *node = dir->subdir.rb_node; + struct rb_node *node = dir->subdir.rb_root.rb_node; while (node) { struct proc_dir_entry *de = rb_entry(node, @@ -75,8 +75,9 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *de) { - struct rb_root *root = &dir->subdir; - struct rb_node **new = &root->rb_node, *parent = NULL; + struct rb_root_cached *root = &dir->subdir; + struct rb_node **new = &root->rb_root.rb_node, *parent = NULL; + bool leftmost = true; /* Figure out where to put new node */ while (*new) { @@ -88,15 +89,16 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, parent = *new; if (result < 0) new = &(*new)->rb_left; - else if (result > 0) + else if (result > 0) { new = &(*new)->rb_right; - else + leftmost = false; + } else return false; } /* Add new node and rebalance tree. */ rb_link_node(&de->subdir_node, parent, new); - rb_insert_color(&de->subdir_node, root); + rb_insert_color_cached(&de->subdir_node, root, leftmost); return true; } @@ -180,7 +182,6 @@ static int xlate_proc_name(const char *name, struct proc_dir_entry **ret, } static DEFINE_IDA(proc_inum_ida); -static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */ #define PROC_DYNAMIC_FIRST 0xF0000000U @@ -190,37 +191,20 @@ static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */ */ int proc_alloc_inum(unsigned int *inum) { - unsigned int i; - int error; + int i; -retry: - if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL)) - return -ENOMEM; + i = ida_simple_get(&proc_inum_ida, 0, UINT_MAX - PROC_DYNAMIC_FIRST + 1, + GFP_KERNEL); + if (i < 0) + return i; - spin_lock_irq(&proc_inum_lock); - error = ida_get_new(&proc_inum_ida, &i); - spin_unlock_irq(&proc_inum_lock); - if (error == -EAGAIN) - goto retry; - else if (error) - return error; - - if (i > UINT_MAX - PROC_DYNAMIC_FIRST) { - spin_lock_irq(&proc_inum_lock); - ida_remove(&proc_inum_ida, i); - spin_unlock_irq(&proc_inum_lock); - return -ENOSPC; - } - *inum = PROC_DYNAMIC_FIRST + i; + *inum = PROC_DYNAMIC_FIRST + (unsigned int)i; return 0; } void proc_free_inum(unsigned int inum) { - unsigned long flags; - spin_lock_irqsave(&proc_inum_lock, flags); - ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); - spin_unlock_irqrestore(&proc_inum_lock, flags); + ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } /* @@ -387,7 +371,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; - ent->subdir = RB_ROOT; + ent->subdir = RB_ROOT_CACHED; atomic_set(&ent->count, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); @@ -517,6 +501,14 @@ out: } EXPORT_SYMBOL(proc_create_data); +struct proc_dir_entry *proc_create(const char *name, umode_t mode, + struct proc_dir_entry *parent, + const struct file_operations *proc_fops) +{ + return proc_create_data(name, mode, parent, proc_fops, NULL); +} +EXPORT_SYMBOL(proc_create); + void proc_set_size(struct proc_dir_entry *de, loff_t size) { de->size = size; @@ -563,7 +555,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) de = pde_subdir_find(parent, fn, len); if (de) - rb_erase(&de->subdir_node, &parent->subdir); + rb_erase_cached(&de->subdir_node, &parent->subdir); write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); @@ -600,13 +592,13 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) write_unlock(&proc_subdir_lock); return -ENOENT; } - rb_erase(&root->subdir_node, &parent->subdir); + rb_erase_cached(&root->subdir_node, &parent->subdir); de = root; while (1) { next = pde_subdir_first(de); if (next) { - rb_erase(&next->subdir_node, &de->subdir); + rb_erase_cached(&next->subdir_node, &de->subdir); de = next; continue; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index c5ae09b6c726..a34195e92b20 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -40,7 +40,7 @@ struct proc_dir_entry { const struct inode_operations *proc_iops; const struct file_operations *proc_fops; struct proc_dir_entry *parent; - struct rb_root subdir; + struct rb_root_cached subdir; struct rb_node subdir_node; void *data; atomic_t count; /* use count */ @@ -51,7 +51,7 @@ struct proc_dir_entry { spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */ u8 namelen; char name[]; -}; +} __randomize_layout; union proc_op { int (*proc_get_link)(struct dentry *, struct path *); @@ -67,10 +67,10 @@ struct proc_inode { struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; - struct list_head sysctl_inodes; + struct hlist_node sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; -}; +} __randomize_layout; /* * General functions @@ -269,17 +269,19 @@ extern int proc_remount(struct super_block *, int *, char *); /* * task_[no]mmu.c */ +struct mem_size_stats; struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; + struct mem_size_stats *rollup; #ifdef CONFIG_MMU struct vm_area_struct *tail_vma; #endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif -}; +} __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); @@ -288,6 +290,7 @@ extern const struct file_operations proc_tid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; extern const struct file_operations proc_tid_numa_maps_operations; extern const struct file_operations proc_pid_smaps_operations; +extern const struct file_operations proc_pid_smaps_rollup_operations; extern const struct file_operations proc_tid_smaps_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 4ee55274f155..45629f4b5402 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -504,7 +504,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) if (&m->list == &kclist_head) { if (clear_user(buffer, tsz)) return -EFAULT; - } else if (is_vmalloc_or_module_addr((void *)start)) { + } else if (m->type == KCORE_VMALLOC) { vread(buf, (char *)start, tsz); /* we have to zero-fill user buffer even if no read */ if (copy_to_user(buffer, buf, tsz)) diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 8a428498d6b2..cdd979724c74 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -80,7 +80,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "Active(file): ", pages[LRU_ACTIVE_FILE]); show_val_kb(m, "Inactive(file): ", pages[LRU_INACTIVE_FILE]); show_val_kb(m, "Unevictable: ", pages[LRU_UNEVICTABLE]); - show_val_kb(m, "Mlocked: ", global_page_state(NR_MLOCK)); + show_val_kb(m, "Mlocked: ", global_zone_page_state(NR_MLOCK)); #ifdef CONFIG_HIGHMEM show_val_kb(m, "HighTotal: ", i.totalhigh); @@ -106,17 +106,17 @@ static int meminfo_proc_show(struct seq_file *m, void *v) global_node_page_state(NR_FILE_MAPPED)); show_val_kb(m, "Shmem: ", i.sharedram); show_val_kb(m, "Slab: ", - global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)); + global_node_page_state(NR_SLAB_RECLAIMABLE) + + global_node_page_state(NR_SLAB_UNRECLAIMABLE)); show_val_kb(m, "SReclaimable: ", - global_page_state(NR_SLAB_RECLAIMABLE)); + global_node_page_state(NR_SLAB_RECLAIMABLE)); show_val_kb(m, "SUnreclaim: ", - global_page_state(NR_SLAB_UNRECLAIMABLE)); + global_node_page_state(NR_SLAB_UNRECLAIMABLE)); seq_printf(m, "KernelStack: %8lu kB\n", - global_page_state(NR_KERNEL_STACK_KB)); + global_zone_page_state(NR_KERNEL_STACK_KB)); show_val_kb(m, "PageTables: ", - global_page_state(NR_PAGETABLE)); + global_zone_page_state(NR_PAGETABLE)); #ifdef CONFIG_QUICKLIST show_val_kb(m, "Quicklists: ", quicklist_total_size()); #endif @@ -124,7 +124,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "NFS_Unstable: ", global_node_page_state(NR_UNSTABLE_NFS)); show_val_kb(m, "Bounce: ", - global_page_state(NR_BOUNCE)); + global_zone_page_state(NR_BOUNCE)); show_val_kb(m, "WritebackTmp: ", global_node_page_state(NR_WRITEBACK_TEMP)); show_val_kb(m, "CommitLimit: ", vm_commit_limit()); @@ -151,7 +151,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #ifdef CONFIG_CMA show_val_kb(m, "CmaTotal: ", totalcma_pages); show_val_kb(m, "CmaFree: ", - global_page_state(NR_FREE_CMA_PAGES)); + global_zone_page_state(NR_FREE_CMA_PAGES)); #endif hugetlb_report_meminfo(m); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index d72fc40241d9..a2bf369c923d 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -196,7 +196,7 @@ static __net_init int proc_net_ns_init(struct net *net) if (!netd) goto out; - netd->subdir = RB_ROOT; + netd->subdir = RB_ROOT_CACHED; netd->data = net; netd->nlink = 2; netd->namelen = 3; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 67985a7233c2..8f479229b349 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -191,7 +191,7 @@ static void init_header(struct ctl_table_header *head, head->set = set; head->parent = NULL; head->node = node; - INIT_LIST_HEAD(&head->inodes); + INIT_HLIST_HEAD(&head->inodes); if (node) { struct ctl_table *entry; for (entry = table; entry->procname; entry++, node++) @@ -261,25 +261,42 @@ static void unuse_table(struct ctl_table_header *p) complete(p->unregistering); } -/* called under sysctl_lock */ static void proc_sys_prune_dcache(struct ctl_table_header *head) { - struct inode *inode, *prev = NULL; + struct inode *inode; struct proc_inode *ei; + struct hlist_node *node; + struct super_block *sb; rcu_read_lock(); - list_for_each_entry_rcu(ei, &head->inodes, sysctl_inodes) { - inode = igrab(&ei->vfs_inode); - if (inode) { - rcu_read_unlock(); - iput(prev); - prev = inode; - d_prune_aliases(inode); + for (;;) { + node = hlist_first_rcu(&head->inodes); + if (!node) + break; + ei = hlist_entry(node, struct proc_inode, sysctl_inodes); + spin_lock(&sysctl_lock); + hlist_del_init_rcu(&ei->sysctl_inodes); + spin_unlock(&sysctl_lock); + + inode = &ei->vfs_inode; + sb = inode->i_sb; + if (!atomic_inc_not_zero(&sb->s_active)) + continue; + inode = igrab(inode); + rcu_read_unlock(); + if (unlikely(!inode)) { + deactivate_super(sb); rcu_read_lock(); + continue; } + + d_prune_aliases(inode); + iput(inode); + deactivate_super(sb); + + rcu_read_lock(); } rcu_read_unlock(); - iput(prev); } /* called under sysctl_lock, will reacquire if has to wait */ @@ -461,7 +478,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, } ei->sysctl = head; ei->sysctl_entry = table; - list_add_rcu(&ei->sysctl_inodes, &head->inodes); + hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes); head->count++; spin_unlock(&sysctl_lock); @@ -489,7 +506,7 @@ out: void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { spin_lock(&sysctl_lock); - list_del_rcu(&PROC_I(inode)->sysctl_inodes); + hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes); if (!--head->count) kfree_rcu(head, rcu); spin_unlock(&sysctl_lock); @@ -1061,16 +1078,30 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...) return -EINVAL; } +static int sysctl_check_table_array(const char *path, struct ctl_table *table) +{ + int err = 0; + + if ((table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax)) { + if (table->maxlen != sizeof(unsigned int)) + err |= sysctl_err(path, table, "array now allowed"); + } + + return err; +} + static int sysctl_check_table(const char *path, struct ctl_table *table) { int err = 0; for (; table->procname; table++) { if (table->child) - err = sysctl_err(path, table, "Not a file"); + err |= sysctl_err(path, table, "Not a file"); if ((table->proc_handler == proc_dostring) || (table->proc_handler == proc_dointvec) || (table->proc_handler == proc_douintvec) || + (table->proc_handler == proc_douintvec_minmax) || (table->proc_handler == proc_dointvec_minmax) || (table->proc_handler == proc_dointvec_jiffies) || (table->proc_handler == proc_dointvec_userhz_jiffies) || @@ -1078,15 +1109,17 @@ static int sysctl_check_table(const char *path, struct ctl_table *table) (table->proc_handler == proc_doulongvec_minmax) || (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) { if (!table->data) - err = sysctl_err(path, table, "No data"); + err |= sysctl_err(path, table, "No data"); if (!table->maxlen) - err = sysctl_err(path, table, "No maxlen"); + err |= sysctl_err(path, table, "No maxlen"); + else + err |= sysctl_check_table_array(path, table); } if (!table->proc_handler) - err = sysctl_err(path, table, "No proc_handler"); + err |= sysctl_err(path, table, "No proc_handler"); if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode) - err = sysctl_err(path, table, "bogus .mode 0%o", + err |= sysctl_err(path, table, "bogus .mode 0%o", table->mode); } return err; diff --git a/fs/proc/root.c b/fs/proc/root.c index deecb397daa3..926fb27f4ca2 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -210,7 +210,7 @@ struct proc_dir_entry proc_root = { .proc_iops = &proc_root_inode_operations, .proc_fops = &proc_root_operations, .parent = &proc_root, - .subdir = RB_ROOT, + .subdir = RB_ROOT_CACHED, .name = "/proc", }; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 520802da059c..5589b4bd4b85 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -16,9 +16,10 @@ #include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> +#include <linux/uaccess.h> #include <asm/elf.h> -#include <linux/uaccess.h> +#include <asm/tlb.h> #include <asm/tlbflush.h> #include "internal.h" @@ -252,6 +253,7 @@ static int proc_map_release(struct inode *inode, struct file *file) if (priv->mm) mmdrop(priv->mm); + kfree(priv->rollup); return seq_release_private(inode, file); } @@ -266,8 +268,7 @@ static int do_maps_open(struct inode *inode, struct file *file, * Indicate if the VMA is a stack for the given task; for * /proc/PID/maps that is the stack of the main task. */ -static int is_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma) +static int is_stack(struct vm_area_struct *vma) { /* * We make no effort to guess what a given thread considers to be @@ -278,12 +279,28 @@ static int is_stack(struct proc_maps_private *priv, vma->vm_end >= vma->vm_mm->start_stack; } +static void show_vma_header_prefix(struct seq_file *m, + unsigned long start, unsigned long end, + vm_flags_t flags, unsigned long long pgoff, + dev_t dev, unsigned long ino) +{ + seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); + seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", + start, + end, + flags & VM_READ ? 'r' : '-', + flags & VM_WRITE ? 'w' : '-', + flags & VM_EXEC ? 'x' : '-', + flags & VM_MAYSHARE ? 's' : 'p', + pgoff, + MAJOR(dev), MINOR(dev), ino); +} + static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) { struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; - struct proc_maps_private *priv = m->private; vm_flags_t flags = vma->vm_flags; unsigned long ino = 0; unsigned long long pgoff = 0; @@ -298,20 +315,9 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT; } - /* We don't show the stack guard page in /proc/maps */ start = vma->vm_start; end = vma->vm_end; - - seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); - seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", - start, - end, - flags & VM_READ ? 'r' : '-', - flags & VM_WRITE ? 'w' : '-', - flags & VM_EXEC ? 'x' : '-', - flags & VM_MAYSHARE ? 's' : 'p', - pgoff, - MAJOR(dev), MINOR(dev), ino); + show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino); /* * Print the dentry name for named mappings, and a @@ -342,7 +348,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - if (is_stack(priv, vma)) + if (is_stack(vma)) name = "[stack]"; } @@ -430,6 +436,7 @@ const struct file_operations proc_tid_maps_operations = { #ifdef CONFIG_PROC_PAGE_MONITOR struct mem_size_stats { + bool first; unsigned long resident; unsigned long shared_clean; unsigned long shared_dirty; @@ -443,7 +450,9 @@ struct mem_size_stats { unsigned long swap; unsigned long shared_hugetlb; unsigned long private_hugetlb; + unsigned long first_vma_start; u64 pss; + u64 pss_locked; u64 swap_pss; bool check_shmem_swap; }; @@ -538,6 +547,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } } else if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); + else if (is_device_private_entry(swpent)) + page = device_private_entry_to_page(swpent); } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap && pte_none(*pte))) { page = find_get_entry(vma->vm_file->f_mapping, @@ -597,13 +608,14 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { - smaps_pmd_entry(pmd, addr, walk); + if (pmd_present(*pmd)) + smaps_pmd_entry(pmd, addr, walk); spin_unlock(ptl); - return 0; + goto out; } if (pmd_trans_unstable(pmd)) - return 0; + goto out; /* * The mmap_sem held all the way back in m_start() is what * keeps khugepaged out of here and from collapsing things @@ -613,6 +625,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, for (; addr != end; pte++, addr += PAGE_SIZE) smaps_pte_entry(pte, addr, walk); pte_unmap_unlock(pte - 1, ptl); +out: cond_resched(); return 0; } @@ -652,6 +665,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_NORESERVE)] = "nr", [ilog2(VM_HUGETLB)] = "ht", [ilog2(VM_ARCH_1)] = "ar", + [ilog2(VM_WIPEONFORK)] = "wf", [ilog2(VM_DONTDUMP)] = "dd", #ifdef CONFIG_MEM_SOFT_DIRTY [ilog2(VM_SOFTDIRTY)] = "sd", @@ -700,6 +714,8 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, if (is_migration_entry(swpent)) page = migration_entry_to_page(swpent); + else if (is_device_private_entry(swpent)) + page = device_private_entry_to_page(swpent); } if (page) { int mapcount = page_mapcount(page); @@ -719,18 +735,36 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) static int show_smap(struct seq_file *m, void *v, int is_pid) { + struct proc_maps_private *priv = m->private; struct vm_area_struct *vma = v; - struct mem_size_stats mss; + struct mem_size_stats mss_stack; + struct mem_size_stats *mss; struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range, #ifdef CONFIG_HUGETLB_PAGE .hugetlb_entry = smaps_hugetlb_range, #endif .mm = vma->vm_mm, - .private = &mss, }; + int ret = 0; + bool rollup_mode; + bool last_vma; + + if (priv->rollup) { + rollup_mode = true; + mss = priv->rollup; + if (mss->first) { + mss->first_vma_start = vma->vm_start; + mss->first = false; + } + last_vma = !m_next_vma(priv, vma); + } else { + rollup_mode = false; + memset(&mss_stack, 0, sizeof(mss_stack)); + mss = &mss_stack; + } - memset(&mss, 0, sizeof mss); + smaps_walk.private = mss; #ifdef CONFIG_SHMEM if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) { @@ -748,9 +782,9 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) if (!shmem_swapped || (vma->vm_flags & VM_SHARED) || !(vma->vm_flags & VM_WRITE)) { - mss.swap = shmem_swapped; + mss->swap = shmem_swapped; } else { - mss.check_shmem_swap = true; + mss->check_shmem_swap = true; smaps_walk.pte_hole = smaps_pte_hole; } } @@ -758,54 +792,71 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); + if (vma->vm_flags & VM_LOCKED) + mss->pss_locked += mss->pss; + + if (!rollup_mode) { + show_map_vma(m, vma, is_pid); + } else if (last_vma) { + show_vma_header_prefix( + m, mss->first_vma_start, vma->vm_end, 0, 0, 0, 0); + seq_pad(m, ' '); + seq_puts(m, "[rollup]\n"); + } else { + ret = SEQ_SKIP; + } - show_map_vma(m, vma, is_pid); - - seq_printf(m, - "Size: %8lu kB\n" - "Rss: %8lu kB\n" - "Pss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n" - "Referenced: %8lu kB\n" - "Anonymous: %8lu kB\n" - "LazyFree: %8lu kB\n" - "AnonHugePages: %8lu kB\n" - "ShmemPmdMapped: %8lu kB\n" - "Shared_Hugetlb: %8lu kB\n" - "Private_Hugetlb: %7lu kB\n" - "Swap: %8lu kB\n" - "SwapPss: %8lu kB\n" - "KernelPageSize: %8lu kB\n" - "MMUPageSize: %8lu kB\n" - "Locked: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - mss.resident >> 10, - (unsigned long)(mss.pss >> (10 + PSS_SHIFT)), - mss.shared_clean >> 10, - mss.shared_dirty >> 10, - mss.private_clean >> 10, - mss.private_dirty >> 10, - mss.referenced >> 10, - mss.anonymous >> 10, - mss.lazyfree >> 10, - mss.anonymous_thp >> 10, - mss.shmem_thp >> 10, - mss.shared_hugetlb >> 10, - mss.private_hugetlb >> 10, - mss.swap >> 10, - (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)), - vma_kernel_pagesize(vma) >> 10, - vma_mmu_pagesize(vma) >> 10, - (vma->vm_flags & VM_LOCKED) ? - (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); - - arch_show_smap(m, vma); - show_smap_vma_flags(m, vma); + if (!rollup_mode) + seq_printf(m, + "Size: %8lu kB\n" + "KernelPageSize: %8lu kB\n" + "MMUPageSize: %8lu kB\n", + (vma->vm_end - vma->vm_start) >> 10, + vma_kernel_pagesize(vma) >> 10, + vma_mmu_pagesize(vma) >> 10); + + + if (!rollup_mode || last_vma) + seq_printf(m, + "Rss: %8lu kB\n" + "Pss: %8lu kB\n" + "Shared_Clean: %8lu kB\n" + "Shared_Dirty: %8lu kB\n" + "Private_Clean: %8lu kB\n" + "Private_Dirty: %8lu kB\n" + "Referenced: %8lu kB\n" + "Anonymous: %8lu kB\n" + "LazyFree: %8lu kB\n" + "AnonHugePages: %8lu kB\n" + "ShmemPmdMapped: %8lu kB\n" + "Shared_Hugetlb: %8lu kB\n" + "Private_Hugetlb: %7lu kB\n" + "Swap: %8lu kB\n" + "SwapPss: %8lu kB\n" + "Locked: %8lu kB\n", + mss->resident >> 10, + (unsigned long)(mss->pss >> (10 + PSS_SHIFT)), + mss->shared_clean >> 10, + mss->shared_dirty >> 10, + mss->private_clean >> 10, + mss->private_dirty >> 10, + mss->referenced >> 10, + mss->anonymous >> 10, + mss->lazyfree >> 10, + mss->anonymous_thp >> 10, + mss->shmem_thp >> 10, + mss->shared_hugetlb >> 10, + mss->private_hugetlb >> 10, + mss->swap >> 10, + (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)), + (unsigned long)(mss->pss >> (10 + PSS_SHIFT))); + + if (!rollup_mode) { + arch_show_smap(m, vma); + show_smap_vma_flags(m, vma); + } m_cache_vma(m, vma); - return 0; + return ret; } static int show_pid_smap(struct seq_file *m, void *v) @@ -837,6 +888,25 @@ static int pid_smaps_open(struct inode *inode, struct file *file) return do_maps_open(inode, file, &proc_pid_smaps_op); } +static int pid_smaps_rollup_open(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + struct proc_maps_private *priv; + int ret = do_maps_open(inode, file, &proc_pid_smaps_op); + + if (ret < 0) + return ret; + seq = file->private_data; + priv = seq->private; + priv->rollup = kzalloc(sizeof(*priv->rollup), GFP_KERNEL); + if (!priv->rollup) { + proc_map_release(inode, file); + return -ENOMEM; + } + priv->rollup->first = true; + return 0; +} + static int tid_smaps_open(struct inode *inode, struct file *file) { return do_maps_open(inode, file, &proc_tid_smaps_op); @@ -849,6 +919,13 @@ const struct file_operations proc_pid_smaps_operations = { .release = proc_map_release, }; +const struct file_operations proc_pid_smaps_rollup_operations = { + .open = pid_smaps_rollup_open, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_map_release, +}; + const struct file_operations proc_tid_smaps_operations = { .open = tid_smaps_open, .read = seq_read, @@ -904,17 +981,22 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, { pmd_t pmd = *pmdp; - /* See comment in change_huge_pmd() */ - pmdp_invalidate(vma, addr, pmdp); - if (pmd_dirty(*pmdp)) - pmd = pmd_mkdirty(pmd); - if (pmd_young(*pmdp)) - pmd = pmd_mkyoung(pmd); - - pmd = pmd_wrprotect(pmd); - pmd = pmd_clear_soft_dirty(pmd); - - set_pmd_at(vma->vm_mm, addr, pmdp, pmd); + if (pmd_present(pmd)) { + /* See comment in change_huge_pmd() */ + pmdp_invalidate(vma, addr, pmdp); + if (pmd_dirty(*pmdp)) + pmd = pmd_mkdirty(pmd); + if (pmd_young(*pmdp)) + pmd = pmd_mkyoung(pmd); + + pmd = pmd_wrprotect(pmd); + pmd = pmd_clear_soft_dirty(pmd); + + set_pmd_at(vma->vm_mm, addr, pmdp, pmd); + } else if (is_migration_entry(pmd_to_swp_entry(pmd))) { + pmd = pmd_swp_clear_soft_dirty(pmd); + set_pmd_at(vma->vm_mm, addr, pmdp, pmd); + } } #else static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, @@ -939,6 +1021,9 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, goto out; } + if (!pmd_present(*pmd)) + goto out; + page = pmd_page(*pmd); /* Clear accessed and referenced bits. */ @@ -1009,6 +1094,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, struct mm_struct *mm; struct vm_area_struct *vma; enum clear_refs_types type; + struct mmu_gather tlb; int itype; int rv; @@ -1055,6 +1141,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, } down_read(&mm->mmap_sem); + tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!(vma->vm_flags & VM_SOFTDIRTY)) @@ -1076,7 +1163,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, walk_page_range(0, mm->highest_vm_end, &clear_refs_walk); if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(mm, 0, -1); - flush_tlb_mm(mm); + tlb_finish_mmu(&tlb, 0, -1); up_read(&mm->mmap_sem); out_mm: mmput(mm); @@ -1179,7 +1266,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (pm->show_pfn) frame = pte_pfn(pte); flags |= PM_PRESENT; - page = vm_normal_page(vma, addr, pte); + page = _vm_normal_page(vma, addr, pte, true); if (pte_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; } else if (is_swap_pte(pte)) { @@ -1192,6 +1279,9 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, flags |= PM_SWAP; if (is_migration_entry(entry)) page = migration_entry_to_page(entry); + + if (is_device_private_entry(entry)) + page = device_private_entry_to_page(entry); } if (page && !PageAnon(page)) @@ -1218,27 +1308,33 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, if (ptl) { u64 flags = 0, frame = 0; pmd_t pmd = *pmdp; + struct page *page = NULL; if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; - /* - * Currently pmd for thp is always present because thp - * can not be swapped-out, migrated, or HWPOISONed - * (split in such cases instead.) - * This if-check is just to prepare for future implementation. - */ if (pmd_present(pmd)) { - struct page *page = pmd_page(pmd); - - if (page_mapcount(page) == 1) - flags |= PM_MMAP_EXCLUSIVE; + page = pmd_page(pmd); flags |= PM_PRESENT; if (pm->show_pfn) frame = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); } +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION + else if (is_swap_pmd(pmd)) { + swp_entry_t entry = pmd_to_swp_entry(pmd); + + frame = swp_type(entry) | + (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + flags |= PM_SWAP; + VM_BUG_ON(!is_pmd_migration_entry(pmd)); + page = migration_entry_to_page(entry); + } +#endif + + if (page && page_mapcount(page) == 1) + flags |= PM_MMAP_EXCLUSIVE; for (; addr != end; addr += PAGE_SIZE) { pagemap_entry_t pme = make_pme(frame, flags); @@ -1378,7 +1474,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, pm.show_pfn = file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN); pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); - pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY); + pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_KERNEL); ret = -ENOMEM; if (!pm.buffer) goto out_mm; @@ -1671,7 +1767,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else if (is_stack(proc_priv, vma)) { + } else if (is_stack(vma)) { seq_puts(m, " stack"); } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 23266694db11..b00b766098fa 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -125,8 +125,7 @@ unsigned long task_statm(struct mm_struct *mm, return size; } -static int is_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma) +static int is_stack(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; @@ -146,7 +145,6 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, int is_pid) { struct mm_struct *mm = vma->vm_mm; - struct proc_maps_private *priv = m->private; unsigned long ino = 0; struct file *file; dev_t dev = 0; @@ -178,7 +176,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm && is_stack(priv, vma)) { + } else if (mm && is_stack(vma)) { seq_pad(m, ' '); seq_printf(m, "[stack]"); } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index b5713fefb4c1..99dff222fe67 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -178,7 +178,7 @@ static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt) } else { mangle(m, r->mnt_devname ? r->mnt_devname : "none"); } - seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw"); + seq_puts(m, sb_rdonly(sb) ? " ro" : " rw"); err = show_sb_opts(m, sb); if (err) goto out; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 792a4e5f9226..d814723fb27d 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -36,7 +36,6 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/uaccess.h> -#include <linux/syslog.h> #include "internal.h" @@ -132,18 +131,6 @@ static const struct seq_operations pstore_ftrace_seq_ops = { .show = pstore_ftrace_seq_show, }; -static int pstore_check_syslog_permissions(struct pstore_private *ps) -{ - switch (ps->record->type) { - case PSTORE_TYPE_DMESG: - case PSTORE_TYPE_CONSOLE: - return check_syslog_permissions(SYSLOG_ACTION_READ_ALL, - SYSLOG_FROM_READER); - default: - return 0; - } -} - static ssize_t pstore_file_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -163,10 +150,6 @@ static int pstore_file_open(struct inode *inode, struct file *file) int err; const struct seq_operations *sops = NULL; - err = pstore_check_syslog_permissions(ps); - if (err) - return err; - if (ps->record->type == PSTORE_TYPE_FTRACE) sops = &pstore_ftrace_seq_ops; @@ -204,11 +187,6 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = d_inode(dentry)->i_private; struct pstore_record *record = p->record; - int err; - - err = pstore_check_syslog_permissions(p); - if (err) - return err; if (!record->psi->erase) return -EPERM; @@ -283,6 +261,16 @@ static void parse_options(char *options) } } +/* + * Display the mount options in /proc/mounts. + */ +static int pstore_show_options(struct seq_file *m, struct dentry *root) +{ + if (kmsg_bytes != PSTORE_DEFAULT_KMSG_BYTES) + seq_printf(m, ",kmsg_bytes=%lu", kmsg_bytes); + return 0; +} + static int pstore_remount(struct super_block *sb, int *flags, char *data) { sync_filesystem(sb); @@ -296,7 +284,7 @@ static const struct super_operations pstore_ops = { .drop_inode = generic_delete_inode, .evict_inode = pstore_evict_inode, .remount_fs = pstore_remount, - .show_options = generic_show_options, + .show_options = pstore_show_options, }; static struct super_block *pstore_sb; @@ -349,48 +337,48 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) switch (record->type) { case PSTORE_TYPE_DMESG: - scnprintf(name, sizeof(name), "dmesg-%s-%lld%s", + scnprintf(name, sizeof(name), "dmesg-%s-%llu%s", record->psi->name, record->id, record->compressed ? ".enc.z" : ""); break; case PSTORE_TYPE_CONSOLE: - scnprintf(name, sizeof(name), "console-%s-%lld", + scnprintf(name, sizeof(name), "console-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_FTRACE: - scnprintf(name, sizeof(name), "ftrace-%s-%lld", + scnprintf(name, sizeof(name), "ftrace-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_MCE: - scnprintf(name, sizeof(name), "mce-%s-%lld", + scnprintf(name, sizeof(name), "mce-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_RTAS: - scnprintf(name, sizeof(name), "rtas-%s-%lld", + scnprintf(name, sizeof(name), "rtas-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_OF: - scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld", + scnprintf(name, sizeof(name), "powerpc-ofw-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_COMMON: - scnprintf(name, sizeof(name), "powerpc-common-%s-%lld", + scnprintf(name, sizeof(name), "powerpc-common-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PMSG: - scnprintf(name, sizeof(name), "pmsg-%s-%lld", + scnprintf(name, sizeof(name), "pmsg-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_PPC_OPAL: - scnprintf(name, sizeof(name), "powerpc-opal-%s-%lld", + scnprintf(name, sizeof(name), "powerpc-opal-%s-%llu", record->psi->name, record->id); break; case PSTORE_TYPE_UNKNOWN: - scnprintf(name, sizeof(name), "unknown-%s-%lld", + scnprintf(name, sizeof(name), "unknown-%s-%llu", record->psi->name, record->id); break; default: - scnprintf(name, sizeof(name), "type%d-%s-%lld", + scnprintf(name, sizeof(name), "type%d-%s-%llu", record->type, record->psi->name, record->id); break; } @@ -448,8 +436,6 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - save_mount_options(sb, data); - pstore_sb = sb; sb->s_maxbytes = MAX_LFS_FILESIZE; @@ -463,7 +449,7 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) inode = pstore_get_inode(sb); if (inode) { - inode->i_mode = S_IFDIR | 0755; + inode->i_mode = S_IFDIR | 0750; inode->i_op = &pstore_dir_inode_operations; inode->i_fop = &simple_dir_operations; inc_nlink(inode); diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index c416e653dc4f..7f4e48c8d188 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -5,6 +5,9 @@ #include <linux/time.h> #include <linux/pstore.h> +#define PSTORE_DEFAULT_KMSG_BYTES 10240 +extern unsigned long kmsg_bytes; + #ifdef CONFIG_PSTORE_FTRACE extern void pstore_register_ftrace(void); extern void pstore_unregister_ftrace(void); @@ -30,5 +33,7 @@ extern void pstore_get_backend_records(struct pstore_info *psi, extern int pstore_mkfile(struct dentry *root, struct pstore_record *record); extern bool pstore_is_mounted(void); +extern void pstore_record_init(struct pstore_record *record, + struct pstore_info *psi); #endif diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index d468eec9b8a6..2b21d180157c 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -99,7 +99,7 @@ static char *big_oops_buf; static size_t big_oops_buf_sz; /* How much of the console log to snapshot */ -static unsigned long kmsg_bytes = 10240; +unsigned long kmsg_bytes = PSTORE_DEFAULT_KMSG_BYTES; void pstore_set_kmsg_bytes(int bytes) { @@ -474,6 +474,20 @@ static size_t copy_kmsg_to_buffer(int hsize, size_t len) return total_len; } +void pstore_record_init(struct pstore_record *record, + struct pstore_info *psinfo) +{ + memset(record, 0, sizeof(*record)); + + record->psi = psinfo; + + /* Report zeroed timestamp if called before timekeeping has resumed. */ + if (__getnstimeofday(&record->time)) { + record->time.tv_sec = 0; + record->time.tv_nsec = 0; + } +} + /* * callback from kmsg_dump. (s2,l2) has the most recently * written bytes, older bytes are in (s1,l1). Save as much @@ -509,15 +523,14 @@ static void pstore_dump(struct kmsg_dumper *dumper, int header_size; int zipped_len = -1; size_t dump_size; - struct pstore_record record = { - .type = PSTORE_TYPE_DMESG, - .count = oopscount, - .reason = reason, - .part = part, - .compressed = false, - .buf = psinfo->buf, - .psi = psinfo, - }; + struct pstore_record record; + + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_DMESG; + record.count = oopscount; + record.reason = reason; + record.part = part; + record.buf = psinfo->buf; if (big_oops_buf && is_locked) { dst = big_oops_buf; @@ -587,12 +600,12 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) const char *e = s + c; while (s < e) { - struct pstore_record record = { - .type = PSTORE_TYPE_CONSOLE, - .psi = psinfo, - }; + struct pstore_record record; unsigned long flags; + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_CONSOLE; + if (c > psinfo->bufsize) c = psinfo->bufsize; @@ -640,19 +653,16 @@ static int pstore_write_user_compat(struct pstore_record *record, if (record->buf) return -EINVAL; - record->buf = kmalloc(record->size, GFP_KERNEL); - if (!record->buf) - return -ENOMEM; - - if (unlikely(copy_from_user(record->buf, buf, record->size))) { - ret = -EFAULT; + record->buf = memdup_user(buf, record->size); + if (unlikely(IS_ERR(record->buf))) { + ret = PTR_ERR(record->buf); goto out; } ret = record->psi->write(record); -out: kfree(record->buf); +out: record->buf = NULL; return unlikely(ret < 0) ? ret : record->size; @@ -770,8 +780,11 @@ static void decompress_record(struct pstore_record *record) int unzipped_len; char *decompressed; + if (!record->compressed) + return; + /* Only PSTORE_TYPE_DMESG support compression. */ - if (!record->compressed || record->type != PSTORE_TYPE_DMESG) { + if (record->type != PSTORE_TYPE_DMESG) { pr_warn("ignored compressed record type %d\n", record->type); return; } @@ -819,6 +832,7 @@ void pstore_get_backend_records(struct pstore_info *psi, struct dentry *root, int quiet) { int failed = 0; + unsigned int stop_loop = 65536; if (!psi || !root) return; @@ -832,7 +846,7 @@ void pstore_get_backend_records(struct pstore_info *psi, * may reallocate record.buf. On success, pstore_mkfile() will keep * the record.buf, so free it only on failure. */ - for (;;) { + for (; stop_loop; stop_loop--) { struct pstore_record *record; int rc; @@ -841,13 +855,15 @@ void pstore_get_backend_records(struct pstore_info *psi, pr_err("out of memory creating record\n"); break; } - record->psi = psi; + pstore_record_init(record, psi); record->size = psi->read(record); /* No more records left in backend? */ - if (record->size <= 0) + if (record->size <= 0) { + kfree(record); break; + } decompress_record(record); rc = pstore_mkfile(root, record); @@ -865,8 +881,11 @@ out: mutex_unlock(&psi->read_mutex); if (failed) - pr_warn("failed to load %d record(s) from '%s'\n", + pr_warn("failed to create %d record(s) from '%s'\n", failed, psi->name); + if (!stop_loop) + pr_err("looping? Too many records seen from '%s'\n", + psi->name); } static void pstore_dowork(struct work_struct *work) diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 209755e0d7c8..24db02de1787 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -22,16 +22,16 @@ static DEFINE_MUTEX(pmsg_lock); static ssize_t write_pmsg(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct pstore_record record = { - .type = PSTORE_TYPE_PMSG, - .size = count, - .psi = psinfo, - }; + struct pstore_record record; int ret; if (!count) return 0; + pstore_record_init(&record, psinfo); + record.type = PSTORE_TYPE_PMSG; + record.size = count; + /* check outside lock, page in any data. write_user also checks */ if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 5cb022c8cd33..7125b398d312 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -27,7 +27,6 @@ #include <linux/module.h> #include <linux/version.h> #include <linux/pstore.h> -#include <linux/time.h> #include <linux/io.h> #include <linux/ioport.h> #include <linux/platform_device.h> @@ -356,20 +355,15 @@ out: } static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz, - bool compressed) + struct pstore_record *record) { char *hdr; - struct timespec timestamp; size_t len; - /* Report zeroed timestamp if called before timekeeping has resumed. */ - if (__getnstimeofday(×tamp)) { - timestamp.tv_sec = 0; - timestamp.tv_nsec = 0; - } hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n", - (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000), - compressed ? 'C' : 'D'); + record->time.tv_sec, + record->time.tv_nsec / 1000, + record->compressed ? 'C' : 'D'); WARN_ON_ONCE(!hdr); len = hdr ? strlen(hdr) : 0; persistent_ram_write(prz, hdr, len); @@ -440,7 +434,7 @@ static int notrace ramoops_pstore_write(struct pstore_record *record) prz = cxt->dprzs[cxt->dump_write_cnt]; /* Build header and append record contents. */ - hlen = ramoops_write_kmsg_hdr(prz, record->compressed); + hlen = ramoops_write_kmsg_hdr(prz, record); size = record->size; if (size + hlen > prz->buffer_size) size = prz->buffer_size - hlen; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 48813aeaab80..52ad15192e72 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -82,16 +82,19 @@ #include <linux/uaccess.h> /* - * There are three quota SMP locks. dq_list_lock protects all lists with quotas - * and quota formats. - * dq_data_lock protects data from dq_dqb and also mem_dqinfo structures and - * also guards consistency of dquot->dq_dqb with inode->i_blocks, i_bytes. - * i_blocks and i_bytes updates itself are guarded by i_lock acquired directly - * in inode_add_bytes() and inode_sub_bytes(). dq_state_lock protects - * modifications of quota state (on quotaon and quotaoff) and readers who care - * about latest values take it as well. + * There are five quota SMP locks: + * * dq_list_lock protects all lists with quotas and quota formats. + * * dquot->dq_dqb_lock protects data from dq_dqb + * * inode->i_lock protects inode->i_blocks, i_bytes and also guards + * consistency of dquot->dq_dqb with inode->i_blocks, i_bytes so that + * dquot_transfer() can stabilize amount it transfers + * * dq_data_lock protects mem_dqinfo structures and modifications of dquot + * pointers in the inode + * * dq_state_lock protects modifications of quota state (on quotaon and + * quotaoff) and readers who care about latest values take it as well. * - * The spinlock ordering is hence: dq_data_lock > dq_list_lock > i_lock, + * The spinlock ordering is hence: + * dq_data_lock > dq_list_lock > i_lock > dquot->dq_dqb_lock, * dq_list_lock > dq_state_lock * * Note that some things (eg. sb pointer, type, id) doesn't change during @@ -110,17 +113,14 @@ * sure they cannot race with quotaon which first sets S_NOQUOTA flag and * then drops all pointers to dquots from an inode. * - * Each dquot has its dq_lock mutex. Locked dquots might not be referenced - * from inodes (dquot_alloc_space() and such don't check the dq_lock). - * Currently dquot is locked only when it is being read to memory (or space for - * it is being allocated) on the first dqget() and when it is being released on - * the last dqput(). The allocation and release oparations are serialized by - * the dq_lock and by checking the use count in dquot_release(). Write - * operations on dquots don't hold dq_lock as they copy data under dq_data_lock - * spinlock to internal buffers before writing. + * Each dquot has its dq_lock mutex. Dquot is locked when it is being read to + * memory (or space for it is being allocated) on the first dqget(), when it is + * being written out, and when it is being released on the last dqput(). The + * allocation and release operations are serialized by the dq_lock and by + * checking the use count in dquot_release(). * * Lock ordering (including related VFS locks) is the following: - * s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_mutex + * s_umount > i_mutex > journal_lock > dquot->dq_lock > dqio_sem */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock); @@ -129,6 +129,8 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_data_lock); EXPORT_SYMBOL(dq_data_lock); DEFINE_STATIC_SRCU(dquot_srcu); +static DECLARE_WAIT_QUEUE_HEAD(dquot_ref_wq); + void __quota_error(struct super_block *sb, const char *func, const char *fmt, ...) { @@ -247,6 +249,7 @@ struct dqstats dqstats; EXPORT_SYMBOL(dqstats); static qsize_t inode_get_rsv_space(struct inode *inode); +static qsize_t __inode_get_rsv_space(struct inode *inode); static int __dquot_initialize(struct inode *inode, int type); static inline unsigned int @@ -342,6 +345,12 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) { int ret = 1; + if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) + return 0; + + if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) + return test_and_set_bit(DQ_MOD_B, &dquot->dq_flags); + /* If quota is dirty already, we don't have to acquire dq_list_lock */ if (test_bit(DQ_MOD_B, &dquot->dq_flags)) return 1; @@ -381,18 +390,26 @@ static inline void dqput_all(struct dquot **dquot) dqput(dquot[cnt]); } -/* This function needs dq_list_lock */ static inline int clear_dquot_dirty(struct dquot *dquot) { - if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags)) + if (sb_dqopt(dquot->dq_sb)->flags & DQUOT_NOLIST_DIRTY) + return test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags); + + spin_lock(&dq_list_lock); + if (!test_and_clear_bit(DQ_MOD_B, &dquot->dq_flags)) { + spin_unlock(&dq_list_lock); return 0; + } list_del_init(&dquot->dq_dirty); + spin_unlock(&dq_list_lock); return 1; } void mark_info_dirty(struct super_block *sb, int type) { - set_bit(DQF_INFO_DIRTY_B, &sb_dqopt(sb)->info[type].dqi_flags); + spin_lock(&dq_data_lock); + sb_dqopt(sb)->info[type].dqi_flags |= DQF_INFO_DIRTY; + spin_unlock(&dq_data_lock); } EXPORT_SYMBOL(mark_info_dirty); @@ -406,7 +423,6 @@ int dquot_acquire(struct dquot *dquot) struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); mutex_lock(&dquot->dq_lock); - mutex_lock(&dqopt->dqio_mutex); if (!test_bit(DQ_READ_B, &dquot->dq_flags)) ret = dqopt->ops[dquot->dq_id.type]->read_dqblk(dquot); if (ret < 0) @@ -436,7 +452,6 @@ int dquot_acquire(struct dquot *dquot) smp_mb__before_atomic(); set_bit(DQ_ACTIVE_B, &dquot->dq_flags); out_iolock: - mutex_unlock(&dqopt->dqio_mutex); mutex_unlock(&dquot->dq_lock); return ret; } @@ -450,21 +465,17 @@ int dquot_commit(struct dquot *dquot) int ret = 0; struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); - mutex_lock(&dqopt->dqio_mutex); - spin_lock(&dq_list_lock); - if (!clear_dquot_dirty(dquot)) { - spin_unlock(&dq_list_lock); - goto out_sem; - } - spin_unlock(&dq_list_lock); + mutex_lock(&dquot->dq_lock); + if (!clear_dquot_dirty(dquot)) + goto out_lock; /* Inactive dquot can be only if there was error during read/init * => we have better not writing it */ if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) ret = dqopt->ops[dquot->dq_id.type]->commit_dqblk(dquot); else ret = -EIO; -out_sem: - mutex_unlock(&dqopt->dqio_mutex); +out_lock: + mutex_unlock(&dquot->dq_lock); return ret; } EXPORT_SYMBOL(dquot_commit); @@ -481,7 +492,6 @@ int dquot_release(struct dquot *dquot) /* Check whether we are not racing with some other dqget() */ if (atomic_read(&dquot->dq_count) > 1) goto out_dqlock; - mutex_lock(&dqopt->dqio_mutex); if (dqopt->ops[dquot->dq_id.type]->release_dqblk) { ret = dqopt->ops[dquot->dq_id.type]->release_dqblk(dquot); /* Write the info */ @@ -493,7 +503,6 @@ int dquot_release(struct dquot *dquot) ret = ret2; } clear_bit(DQ_ACTIVE_B, &dquot->dq_flags); - mutex_unlock(&dqopt->dqio_mutex); out_dqlock: mutex_unlock(&dquot->dq_lock); return ret; @@ -530,22 +539,18 @@ restart: continue; /* Wait for dquot users */ if (atomic_read(&dquot->dq_count)) { - DEFINE_WAIT(wait); - dqgrab(dquot); - prepare_to_wait(&dquot->dq_wait_unused, &wait, - TASK_UNINTERRUPTIBLE); spin_unlock(&dq_list_lock); - /* Once dqput() wakes us up, we know it's time to free + /* + * Once dqput() wakes us up, we know it's time to free * the dquot. * IMPORTANT: we rely on the fact that there is always * at most one process waiting for dquot to free. * Otherwise dq_count would be > 1 and we would never * wake up. */ - if (atomic_read(&dquot->dq_count) > 1) - schedule(); - finish_wait(&dquot->dq_wait_unused, &wait); + wait_event(dquot_ref_wq, + atomic_read(&dquot->dq_count) == 1); dqput(dquot); /* At this moment dquot() need not exist (it could be * reclaimed by prune_dqcache(). Hence we must @@ -629,11 +634,9 @@ int dquot_writeback_dquots(struct super_block *sb, int type) while (!list_empty(dirty)) { dquot = list_first_entry(dirty, struct dquot, dq_dirty); - /* Dirty and inactive can be only bad dquot... */ - if (!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { - clear_dquot_dirty(dquot); - continue; - } + + WARN_ON(!test_bit(DQ_ACTIVE_B, &dquot->dq_flags)); + /* Now we have active dquot from which someone is * holding reference so we can safely just increase * use count */ @@ -759,12 +762,12 @@ we_slept: /* Releasing dquot during quotaoff phase? */ if (!sb_has_quota_active(dquot->dq_sb, dquot->dq_id.type) && atomic_read(&dquot->dq_count) == 1) - wake_up(&dquot->dq_wait_unused); + wake_up(&dquot_ref_wq); spin_unlock(&dq_list_lock); return; } /* Need to release dquot? */ - if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags) && dquot_dirty(dquot)) { + if (dquot_dirty(dquot)) { spin_unlock(&dq_list_lock); /* Commit dquot before releasing */ ret = dquot->dq_sb->dq_op->write_dquot(dquot); @@ -776,14 +779,10 @@ we_slept: * We clear dirty bit anyway, so that we avoid * infinite loop here */ - spin_lock(&dq_list_lock); clear_dquot_dirty(dquot); - spin_unlock(&dq_list_lock); } goto we_slept; } - /* Clear flag in case dquot was inactive (something bad happened) */ - clear_dquot_dirty(dquot); if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) { spin_unlock(&dq_list_lock); dquot->dq_sb->dq_op->release_dquot(dquot); @@ -818,10 +817,10 @@ static struct dquot *get_empty_dquot(struct super_block *sb, int type) INIT_LIST_HEAD(&dquot->dq_inuse); INIT_HLIST_NODE(&dquot->dq_hash); INIT_LIST_HEAD(&dquot->dq_dirty); - init_waitqueue_head(&dquot->dq_wait_unused); dquot->dq_sb = sb; dquot->dq_id = make_kqid_invalid(type); atomic_set(&dquot->dq_count, 1); + spin_lock_init(&dquot->dq_dqb_lock); return dquot; } @@ -1079,42 +1078,6 @@ static void drop_dquot_ref(struct super_block *sb, int type) } } -static inline void dquot_incr_inodes(struct dquot *dquot, qsize_t number) -{ - dquot->dq_dqb.dqb_curinodes += number; -} - -static inline void dquot_incr_space(struct dquot *dquot, qsize_t number) -{ - dquot->dq_dqb.dqb_curspace += number; -} - -static inline void dquot_resv_space(struct dquot *dquot, qsize_t number) -{ - dquot->dq_dqb.dqb_rsvspace += number; -} - -/* - * Claim reserved quota space - */ -static void dquot_claim_reserved_space(struct dquot *dquot, qsize_t number) -{ - if (dquot->dq_dqb.dqb_rsvspace < number) { - WARN_ON_ONCE(1); - number = dquot->dq_dqb.dqb_rsvspace; - } - dquot->dq_dqb.dqb_curspace += number; - dquot->dq_dqb.dqb_rsvspace -= number; -} - -static void dquot_reclaim_reserved_space(struct dquot *dquot, qsize_t number) -{ - if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) - number = dquot->dq_dqb.dqb_curspace; - dquot->dq_dqb.dqb_rsvspace += number; - dquot->dq_dqb.dqb_curspace -= number; -} - static inline void dquot_free_reserved_space(struct dquot *dquot, qsize_t number) { @@ -1124,6 +1087,10 @@ void dquot_free_reserved_space(struct dquot *dquot, qsize_t number) WARN_ON_ONCE(1); dquot->dq_dqb.dqb_rsvspace = 0; } + if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= + dquot->dq_dqb.dqb_bsoftlimit) + dquot->dq_dqb.dqb_btime = (time64_t) 0; + clear_bit(DQ_BLKS_B, &dquot->dq_flags); } static void dquot_decr_inodes(struct dquot *dquot, qsize_t number) @@ -1145,7 +1112,8 @@ static void dquot_decr_space(struct dquot *dquot, qsize_t number) dquot->dq_dqb.dqb_curspace -= number; else dquot->dq_dqb.dqb_curspace = 0; - if (dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit) + if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= + dquot->dq_dqb.dqb_bsoftlimit) dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } @@ -1273,21 +1241,24 @@ static int ignore_hardlimit(struct dquot *dquot) !(info->dqi_flags & DQF_ROOT_SQUASH)); } -/* needs dq_data_lock */ -static int check_idq(struct dquot *dquot, qsize_t inodes, - struct dquot_warn *warn) +static int dquot_add_inodes(struct dquot *dquot, qsize_t inodes, + struct dquot_warn *warn) { - qsize_t newinodes = dquot->dq_dqb.dqb_curinodes + inodes; + qsize_t newinodes; + int ret = 0; + spin_lock(&dquot->dq_dqb_lock); + newinodes = dquot->dq_dqb.dqb_curinodes + inodes; if (!sb_has_quota_limits_enabled(dquot->dq_sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) - return 0; + goto add; if (dquot->dq_dqb.dqb_ihardlimit && newinodes > dquot->dq_dqb.dqb_ihardlimit && !ignore_hardlimit(dquot)) { prepare_warning(warn, dquot, QUOTA_NL_IHARDWARN); - return -EDQUOT; + ret = -EDQUOT; + goto out; } if (dquot->dq_dqb.dqb_isoftlimit && @@ -1296,7 +1267,8 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, ktime_get_real_seconds() >= dquot->dq_dqb.dqb_itime && !ignore_hardlimit(dquot)) { prepare_warning(warn, dquot, QUOTA_NL_ISOFTLONGWARN); - return -EDQUOT; + ret = -EDQUOT; + goto out; } if (dquot->dq_dqb.dqb_isoftlimit && @@ -1306,30 +1278,37 @@ static int check_idq(struct dquot *dquot, qsize_t inodes, dquot->dq_dqb.dqb_itime = ktime_get_real_seconds() + sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type].dqi_igrace; } +add: + dquot->dq_dqb.dqb_curinodes = newinodes; - return 0; +out: + spin_unlock(&dquot->dq_dqb_lock); + return ret; } -/* needs dq_data_lock */ -static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, - struct dquot_warn *warn) +static int dquot_add_space(struct dquot *dquot, qsize_t space, + qsize_t rsv_space, unsigned int flags, + struct dquot_warn *warn) { qsize_t tspace; struct super_block *sb = dquot->dq_sb; + int ret = 0; + spin_lock(&dquot->dq_dqb_lock); if (!sb_has_quota_limits_enabled(sb, dquot->dq_id.type) || test_bit(DQ_FAKE_B, &dquot->dq_flags)) - return 0; + goto finish; tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace - + space; + + space + rsv_space; if (dquot->dq_dqb.dqb_bhardlimit && tspace > dquot->dq_dqb.dqb_bhardlimit && !ignore_hardlimit(dquot)) { - if (!prealloc) + if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BHARDWARN); - return -EDQUOT; + ret = -EDQUOT; + goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && @@ -1337,28 +1316,42 @@ static int check_bdq(struct dquot *dquot, qsize_t space, int prealloc, dquot->dq_dqb.dqb_btime && ktime_get_real_seconds() >= dquot->dq_dqb.dqb_btime && !ignore_hardlimit(dquot)) { - if (!prealloc) + if (flags & DQUOT_SPACE_WARN) prepare_warning(warn, dquot, QUOTA_NL_BSOFTLONGWARN); - return -EDQUOT; + ret = -EDQUOT; + goto finish; } if (dquot->dq_dqb.dqb_bsoftlimit && tspace > dquot->dq_dqb.dqb_bsoftlimit && dquot->dq_dqb.dqb_btime == 0) { - if (!prealloc) { + if (flags & DQUOT_SPACE_WARN) { prepare_warning(warn, dquot, QUOTA_NL_BSOFTWARN); dquot->dq_dqb.dqb_btime = ktime_get_real_seconds() + sb_dqopt(sb)->info[dquot->dq_id.type].dqi_bgrace; - } - else + } else { /* * We don't allow preallocation to exceed softlimit so exceeding will * be always printed */ - return -EDQUOT; + ret = -EDQUOT; + goto finish; + } } - - return 0; +finish: + /* + * We have to be careful and go through warning generation & grace time + * setting even if DQUOT_SPACE_NOFAIL is set. That's why we check it + * only here... + */ + if (flags & DQUOT_SPACE_NOFAIL) + ret = 0; + if (!ret) { + dquot->dq_dqb.dqb_rsvspace += rsv_space; + dquot->dq_dqb.dqb_curspace += space; + } + spin_unlock(&dquot->dq_dqb_lock); + return ret; } static int info_idq_free(struct dquot *dquot, qsize_t inodes) @@ -1381,14 +1374,18 @@ static int info_idq_free(struct dquot *dquot, qsize_t inodes) static int info_bdq_free(struct dquot *dquot, qsize_t space) { + qsize_t tspace; + + tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace; + if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || - dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit) + tspace <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_NOWARN; - if (dquot->dq_dqb.dqb_curspace - space <= dquot->dq_dqb.dqb_bsoftlimit) + if (tspace - space <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_BSOFTBELOW; - if (dquot->dq_dqb.dqb_curspace >= dquot->dq_dqb.dqb_bhardlimit && - dquot->dq_dqb.dqb_curspace - space < dquot->dq_dqb.dqb_bhardlimit) + if (tspace >= dquot->dq_dqb.dqb_bhardlimit && + tspace - space < dquot->dq_dqb.dqb_bhardlimit) return QUOTA_NL_BHARDBELOW; return QUOTA_NL_NOWARN; } @@ -1493,8 +1490,15 @@ static int __dquot_initialize(struct inode *inode, int type) * did a write before quota was turned on */ rsv = inode_get_rsv_space(inode); - if (unlikely(rsv)) - dquot_resv_space(dquots[cnt], rsv); + if (unlikely(rsv)) { + spin_lock(&inode->i_lock); + /* Get reservation again under proper lock */ + rsv = __inode_get_rsv_space(inode); + spin_lock(&dquots[cnt]->dq_dqb_lock); + dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_unlock(&inode->i_lock); + } } } out_lock: @@ -1589,39 +1593,12 @@ static qsize_t *inode_reserved_space(struct inode * inode) return inode->i_sb->dq_op->get_reserved_space(inode); } -void inode_add_rsv_space(struct inode *inode, qsize_t number) +static qsize_t __inode_get_rsv_space(struct inode *inode) { - spin_lock(&inode->i_lock); - *inode_reserved_space(inode) += number; - spin_unlock(&inode->i_lock); -} -EXPORT_SYMBOL(inode_add_rsv_space); - -void inode_claim_rsv_space(struct inode *inode, qsize_t number) -{ - spin_lock(&inode->i_lock); - *inode_reserved_space(inode) -= number; - __inode_add_bytes(inode, number); - spin_unlock(&inode->i_lock); -} -EXPORT_SYMBOL(inode_claim_rsv_space); - -void inode_reclaim_rsv_space(struct inode *inode, qsize_t number) -{ - spin_lock(&inode->i_lock); - *inode_reserved_space(inode) += number; - __inode_sub_bytes(inode, number); - spin_unlock(&inode->i_lock); -} -EXPORT_SYMBOL(inode_reclaim_rsv_space); - -void inode_sub_rsv_space(struct inode *inode, qsize_t number) -{ - spin_lock(&inode->i_lock); - *inode_reserved_space(inode) -= number; - spin_unlock(&inode->i_lock); + if (!inode->i_sb->dq_op->get_reserved_space) + return 0; + return *inode_reserved_space(inode); } -EXPORT_SYMBOL(inode_sub_rsv_space); static qsize_t inode_get_rsv_space(struct inode *inode) { @@ -1630,28 +1607,11 @@ static qsize_t inode_get_rsv_space(struct inode *inode) if (!inode->i_sb->dq_op->get_reserved_space) return 0; spin_lock(&inode->i_lock); - ret = *inode_reserved_space(inode); + ret = __inode_get_rsv_space(inode); spin_unlock(&inode->i_lock); return ret; } -static void inode_incr_space(struct inode *inode, qsize_t number, - int reserve) -{ - if (reserve) - inode_add_rsv_space(inode, number); - else - inode_add_bytes(inode, number); -} - -static void inode_decr_space(struct inode *inode, qsize_t number, int reserve) -{ - if (reserve) - inode_sub_rsv_space(inode, number); - else - inode_sub_bytes(inode, number); -} - /* * This functions updates i_blocks+i_bytes fields and quota information * (together with appropriate checks). @@ -1673,7 +1633,13 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) struct dquot **dquots; if (!dquot_active(inode)) { - inode_incr_space(inode, number, reserve); + if (reserve) { + spin_lock(&inode->i_lock); + *inode_reserved_space(inode) += number; + spin_unlock(&inode->i_lock); + } else { + inode_add_bytes(inode, number); + } goto out; } @@ -1682,27 +1648,41 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); - spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!dquots[cnt]) continue; - ret = check_bdq(dquots[cnt], number, - !(flags & DQUOT_SPACE_WARN), &warn[cnt]); - if (ret && !(flags & DQUOT_SPACE_NOFAIL)) { - spin_unlock(&dq_data_lock); + if (flags & DQUOT_SPACE_RESERVE) { + ret = dquot_add_space(dquots[cnt], 0, number, flags, + &warn[cnt]); + } else { + ret = dquot_add_space(dquots[cnt], number, 0, flags, + &warn[cnt]); + } + if (ret) { + /* Back out changes we already did */ + for (cnt--; cnt >= 0; cnt--) { + if (!dquots[cnt]) + continue; + spin_lock(&dquots[cnt]->dq_dqb_lock); + if (flags & DQUOT_SPACE_RESERVE) { + dquots[cnt]->dq_dqb.dqb_rsvspace -= + number; + } else { + dquots[cnt]->dq_dqb.dqb_curspace -= + number; + } + spin_unlock(&dquots[cnt]->dq_dqb_lock); + } + spin_unlock(&inode->i_lock); goto out_flush_warn; } } - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) - continue; - if (reserve) - dquot_resv_space(dquots[cnt], number); - else - dquot_incr_space(dquots[cnt], number); - } - inode_incr_space(inode, number, reserve); - spin_unlock(&dq_data_lock); + if (reserve) + *inode_reserved_space(inode) += number; + else + __inode_add_bytes(inode, number); + spin_unlock(&inode->i_lock); if (reserve) goto out_flush_warn; @@ -1731,23 +1711,26 @@ int dquot_alloc_inode(struct inode *inode) dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); - spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!dquots[cnt]) continue; - ret = check_idq(dquots[cnt], 1, &warn[cnt]); - if (ret) + ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + if (ret) { + for (cnt--; cnt >= 0; cnt--) { + if (!dquots[cnt]) + continue; + /* Back out changes we already did */ + spin_lock(&dquots[cnt]->dq_dqb_lock); + dquots[cnt]->dq_dqb.dqb_curinodes--; + spin_unlock(&dquots[cnt]->dq_dqb_lock); + } goto warn_put_all; - } - - for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) - continue; - dquot_incr_inodes(dquots[cnt], 1); + } } warn_put_all: - spin_unlock(&dq_data_lock); + spin_unlock(&inode->i_lock); if (ret == 0) mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); @@ -1765,21 +1748,33 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) int cnt, index; if (!dquot_active(inode)) { - inode_claim_rsv_space(inode, number); + spin_lock(&inode->i_lock); + *inode_reserved_space(inode) -= number; + __inode_add_bytes(inode, number); + spin_unlock(&inode->i_lock); return 0; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); - spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) - dquot_claim_reserved_space(dquots[cnt], number); + if (dquots[cnt]) { + struct dquot *dquot = dquots[cnt]; + + spin_lock(&dquot->dq_dqb_lock); + if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) + number = dquot->dq_dqb.dqb_rsvspace; + dquot->dq_dqb.dqb_curspace += number; + dquot->dq_dqb.dqb_rsvspace -= number; + spin_unlock(&dquot->dq_dqb_lock); + } } /* Update inode bytes */ - inode_claim_rsv_space(inode, number); - spin_unlock(&dq_data_lock); + *inode_reserved_space(inode) -= number; + __inode_add_bytes(inode, number); + spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); return 0; @@ -1795,21 +1790,33 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) int cnt, index; if (!dquot_active(inode)) { - inode_reclaim_rsv_space(inode, number); + spin_lock(&inode->i_lock); + *inode_reserved_space(inode) += number; + __inode_sub_bytes(inode, number); + spin_unlock(&inode->i_lock); return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); - spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) - dquot_reclaim_reserved_space(dquots[cnt], number); + if (dquots[cnt]) { + struct dquot *dquot = dquots[cnt]; + + spin_lock(&dquot->dq_dqb_lock); + if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) + number = dquot->dq_dqb.dqb_curspace; + dquot->dq_dqb.dqb_rsvspace += number; + dquot->dq_dqb.dqb_curspace -= number; + spin_unlock(&dquot->dq_dqb_lock); + } } /* Update inode bytes */ - inode_reclaim_rsv_space(inode, number); - spin_unlock(&dq_data_lock); + *inode_reserved_space(inode) += number; + __inode_sub_bytes(inode, number); + spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); return; @@ -1827,19 +1834,26 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!dquot_active(inode)) { - inode_decr_space(inode, number, reserve); + if (reserve) { + spin_lock(&inode->i_lock); + *inode_reserved_space(inode) -= number; + spin_unlock(&inode->i_lock); + } else { + inode_sub_bytes(inode, number); + } return; } dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); - spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; if (!dquots[cnt]) continue; + spin_lock(&dquots[cnt]->dq_dqb_lock); wtype = info_bdq_free(dquots[cnt], number); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn[cnt], dquots[cnt], wtype); @@ -1847,9 +1861,13 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) dquot_free_reserved_space(dquots[cnt], number); else dquot_decr_space(dquots[cnt], number); + spin_unlock(&dquots[cnt]->dq_dqb_lock); } - inode_decr_space(inode, number, reserve); - spin_unlock(&dq_data_lock); + if (reserve) + *inode_reserved_space(inode) -= number; + else + __inode_sub_bytes(inode, number); + spin_unlock(&inode->i_lock); if (reserve) goto out_unlock; @@ -1875,19 +1893,21 @@ void dquot_free_inode(struct inode *inode) dquots = i_dquot(inode); index = srcu_read_lock(&dquot_srcu); - spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; if (!dquots[cnt]) continue; + spin_lock(&dquots[cnt]->dq_dqb_lock); wtype = info_idq_free(dquots[cnt], 1); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn[cnt], dquots[cnt], wtype); dquot_decr_inodes(dquots[cnt], 1); + spin_unlock(&dquots[cnt]->dq_dqb_lock); } - spin_unlock(&dq_data_lock); + spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); srcu_read_unlock(&dquot_srcu, index); flush_warnings(warn); @@ -1908,8 +1928,9 @@ EXPORT_SYMBOL(dquot_free_inode); */ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) { - qsize_t space, cur_space; + qsize_t cur_space; qsize_t rsv_space = 0; + qsize_t inode_usage = 1; struct dquot *transfer_from[MAXQUOTAS] = {}; int cnt, ret = 0; char is_valid[MAXQUOTAS] = {}; @@ -1919,6 +1940,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (IS_NOQUOTA(inode)) return 0; + + if (inode->i_sb->dq_op->get_inode_usage) { + ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage); + if (ret) + return ret; + } + /* Initialize the arrays */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { warn_to[cnt].w_type = QUOTA_NL_NOWARN; @@ -1927,14 +1955,18 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } spin_lock(&dq_data_lock); + spin_lock(&inode->i_lock); if (IS_NOQUOTA(inode)) { /* File without quota accounting? */ + spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); return 0; } - cur_space = inode_get_bytes(inode); - rsv_space = inode_get_rsv_space(inode); - space = cur_space + rsv_space; - /* Build the transfer_from list and check the limits */ + cur_space = __inode_get_bytes(inode); + rsv_space = __inode_get_rsv_space(inode); + /* + * Build the transfer_from list, check limits, and update usage in + * the target structures. + */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { /* * Skip changes for same uid or gid or for turned off quota-type. @@ -1946,43 +1978,47 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) continue; is_valid[cnt] = 1; transfer_from[cnt] = i_dquot(inode)[cnt]; - ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]); + ret = dquot_add_inodes(transfer_to[cnt], inode_usage, + &warn_to[cnt]); if (ret) goto over_quota; - ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]); - if (ret) + ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0, + &warn_to[cnt]); + if (ret) { + spin_lock(&transfer_to[cnt]->dq_dqb_lock); + dquot_decr_inodes(transfer_to[cnt], inode_usage); + spin_unlock(&transfer_to[cnt]->dq_dqb_lock); goto over_quota; + } } - /* - * Finally perform the needed transfer from transfer_from to transfer_to - */ + /* Decrease usage for source structures and update quota pointers */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!is_valid[cnt]) continue; /* Due to IO error we might not have transfer_from[] structure */ if (transfer_from[cnt]) { int wtype; - wtype = info_idq_free(transfer_from[cnt], 1); + + spin_lock(&transfer_from[cnt]->dq_dqb_lock); + wtype = info_idq_free(transfer_from[cnt], inode_usage); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_inodes[cnt], transfer_from[cnt], wtype); - wtype = info_bdq_free(transfer_from[cnt], space); + wtype = info_bdq_free(transfer_from[cnt], + cur_space + rsv_space); if (wtype != QUOTA_NL_NOWARN) prepare_warning(&warn_from_space[cnt], transfer_from[cnt], wtype); - dquot_decr_inodes(transfer_from[cnt], 1); + dquot_decr_inodes(transfer_from[cnt], inode_usage); dquot_decr_space(transfer_from[cnt], cur_space); dquot_free_reserved_space(transfer_from[cnt], rsv_space); + spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - - dquot_incr_inodes(transfer_to[cnt], 1); - dquot_incr_space(transfer_to[cnt], cur_space); - dquot_resv_space(transfer_to[cnt], rsv_space); - i_dquot(inode)[cnt] = transfer_to[cnt]; } + spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); mark_all_dquot_dirty(transfer_from); @@ -1996,6 +2032,17 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) transfer_to[cnt] = transfer_from[cnt]; return 0; over_quota: + /* Back out changes we already did */ + for (cnt--; cnt >= 0; cnt--) { + if (!is_valid[cnt]) + continue; + spin_lock(&transfer_to[cnt]->dq_dqb_lock); + dquot_decr_inodes(transfer_to[cnt], inode_usage); + dquot_decr_space(transfer_to[cnt], cur_space); + dquot_free_reserved_space(transfer_to[cnt], rsv_space); + spin_unlock(&transfer_to[cnt]->dq_dqb_lock); + } + spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); flush_warnings(warn_to); return ret; @@ -2049,29 +2096,21 @@ EXPORT_SYMBOL(dquot_transfer); */ int dquot_commit_info(struct super_block *sb, int type) { - int ret; struct quota_info *dqopt = sb_dqopt(sb); - mutex_lock(&dqopt->dqio_mutex); - ret = dqopt->ops[type]->write_file_info(sb, type); - mutex_unlock(&dqopt->dqio_mutex); - return ret; + return dqopt->ops[type]->write_file_info(sb, type); } EXPORT_SYMBOL(dquot_commit_info); int dquot_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); - int err; if (!sb_has_quota_active(sb, qid->type)) return -ESRCH; if (!dqopt->ops[qid->type]->get_next_id) return -ENOSYS; - mutex_lock(&dqopt->dqio_mutex); - err = dqopt->ops[qid->type]->get_next_id(sb, qid); - mutex_unlock(&dqopt->dqio_mutex); - return err; + return dqopt->ops[qid->type]->get_next_id(sb, qid); } EXPORT_SYMBOL(dquot_get_next_id); @@ -2320,15 +2359,14 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, dqopt->info[type].dqi_format = fmt; dqopt->info[type].dqi_fmt_id = format_id; INIT_LIST_HEAD(&dqopt->info[type].dqi_dirty_list); - mutex_lock(&dqopt->dqio_mutex); error = dqopt->ops[type]->read_file_info(sb, type); - if (error < 0) { - mutex_unlock(&dqopt->dqio_mutex); + if (error < 0) goto out_file_init; - } - if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) + if (dqopt->flags & DQUOT_QUOTA_SYS_FILE) { + spin_lock(&dq_data_lock); dqopt->info[type].dqi_flags |= DQF_SYS_FILE; - mutex_unlock(&dqopt->dqio_mutex); + spin_unlock(&dq_data_lock); + } spin_lock(&dq_state_lock); dqopt->flags |= dquot_state_flag(flags, type); spin_unlock(&dq_state_lock); @@ -2555,7 +2593,7 @@ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) struct mem_dqblk *dm = &dquot->dq_dqb; memset(di, 0, sizeof(*di)); - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); di->d_spc_hardlimit = dm->dqb_bhardlimit; di->d_spc_softlimit = dm->dqb_bsoftlimit; di->d_ino_hardlimit = dm->dqb_ihardlimit; @@ -2564,7 +2602,7 @@ static void do_get_dqblk(struct dquot *dquot, struct qc_dqblk *di) di->d_ino_count = dm->dqb_curinodes; di->d_spc_timer = dm->dqb_btime; di->d_ino_timer = dm->dqb_itime; - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); } int dquot_get_dqblk(struct super_block *sb, struct kqid qid, @@ -2628,7 +2666,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) (di->d_ino_hardlimit > dqi->dqi_max_ino_limit))) return -ERANGE; - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); if (di->d_fieldmask & QC_SPACE) { dm->dqb_curspace = di->d_space - dm->dqb_rsvspace; check_blim = 1; @@ -2673,7 +2711,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) if (check_blim) { if (!dm->dqb_bsoftlimit || - dm->dqb_curspace < dm->dqb_bsoftlimit) { + dm->dqb_curspace + dm->dqb_rsvspace < dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } else if (!(di->d_fieldmask & QC_SPC_TIMER)) @@ -2694,7 +2732,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) clear_bit(DQ_FAKE_B, &dquot->dq_flags); else set_bit(DQ_FAKE_B, &dquot->dq_flags); - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); mark_dquot_dirty(dquot); return 0; diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 07e08c7d05ca..a9c5dfe6b83e 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -753,7 +753,7 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_XGETNEXTQUOTA: return quota_getnextxquota(sb, type, id, addr); case Q_XQUOTASYNC: - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; /* XFS quotas are fully coherent now, making this call a noop */ return 0; diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index 0738972e8d3f..bb3f59bcfcf5 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -379,7 +379,7 @@ int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) if (!ddquot) return -ENOMEM; - /* dq_off is guarded by dqio_mutex */ + /* dq_off is guarded by dqio_sem */ if (!dquot->dq_off) { ret = dq_insert_tree(info, dquot); if (ret < 0) { @@ -389,9 +389,9 @@ int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) return ret; } } - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); info->dqi_ops->mem2disk_dqblk(ddquot, dquot); - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); ret = sb->s_op->quota_write(sb, type, ddquot, info->dqi_entry_size, dquot->dq_off); if (ret != info->dqi_entry_size) { @@ -649,14 +649,14 @@ int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot) kfree(ddquot); goto out; } - spin_lock(&dq_data_lock); + spin_lock(&dquot->dq_dqb_lock); info->dqi_ops->disk2mem_dqblk(dquot, ddquot); if (!dquot->dq_dqb.dqb_bhardlimit && !dquot->dq_dqb.dqb_bsoftlimit && !dquot->dq_dqb.dqb_ihardlimit && !dquot->dq_dqb.dqb_isoftlimit) set_bit(DQ_FAKE_B, &dquot->dq_flags); - spin_unlock(&dq_data_lock); + spin_unlock(&dquot->dq_dqb_lock); kfree(ddquot); out: dqstats_inc(DQST_READS); diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 8fe79beced5c..7ac5298aba70 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -56,8 +56,9 @@ static int v1_read_dqblk(struct dquot *dquot) { int type = dquot->dq_id.type; struct v1_disk_dqblk dqblk; + struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); - if (!sb_dqopt(dquot->dq_sb)->files[type]) + if (!dqopt->files[type]) return -EINVAL; /* Set structure to 0s in case read fails/is after end of file */ @@ -160,6 +161,7 @@ static int v1_read_file_info(struct super_block *sb, int type) struct v1_disk_dqblk dqblk; int ret; + down_read(&dqopt->dqio_sem); ret = sb->s_op->quota_read(sb, type, (char *)&dqblk, sizeof(struct v1_disk_dqblk), v1_dqoff(0)); if (ret != sizeof(struct v1_disk_dqblk)) { @@ -176,6 +178,7 @@ static int v1_read_file_info(struct super_block *sb, int type) dqopt->info[type].dqi_bgrace = dqblk.dqb_btime ? dqblk.dqb_btime : MAX_DQ_TIME; out: + up_read(&dqopt->dqio_sem); return ret; } @@ -185,7 +188,7 @@ static int v1_write_file_info(struct super_block *sb, int type) struct v1_disk_dqblk dqblk; int ret; - dqopt->info[type].dqi_flags &= ~DQF_INFO_DIRTY; + down_write(&dqopt->dqio_sem); ret = sb->s_op->quota_read(sb, type, (char *)&dqblk, sizeof(struct v1_disk_dqblk), v1_dqoff(0)); if (ret != sizeof(struct v1_disk_dqblk)) { @@ -193,8 +196,11 @@ static int v1_write_file_info(struct super_block *sb, int type) ret = -EIO; goto out; } + spin_lock(&dq_data_lock); + dqopt->info[type].dqi_flags &= ~DQF_INFO_DIRTY; dqblk.dqb_itime = dqopt->info[type].dqi_igrace; dqblk.dqb_btime = dqopt->info[type].dqi_bgrace; + spin_unlock(&dq_data_lock); ret = sb->s_op->quota_write(sb, type, (char *)&dqblk, sizeof(struct v1_disk_dqblk), v1_dqoff(0)); if (ret == sizeof(struct v1_disk_dqblk)) @@ -202,6 +208,7 @@ static int v1_write_file_info(struct super_block *sb, int type) else if (ret > 0) ret = -EIO; out: + up_write(&dqopt->dqio_sem); return ret; } diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index ca71bf881ad1..a73e5b34db41 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -65,9 +65,11 @@ static int v2_read_header(struct super_block *sb, int type, if (size != sizeof(struct v2_disk_dqheader)) { quota_error(sb, "Failed header read: expected=%zd got=%zd", sizeof(struct v2_disk_dqheader), size); - return 0; + if (size < 0) + return size; + return -EIO; } - return 1; + return 0; } /* Check whether given file is really vfsv0 quotafile */ @@ -77,7 +79,7 @@ static int v2_check_quota_file(struct super_block *sb, int type) static const uint quota_magics[] = V2_INITQMAGICS; static const uint quota_versions[] = V2_INITQVERSIONS; - if (!v2_read_header(sb, type, &dqhead)) + if (v2_read_header(sb, type, &dqhead)) return 0; if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] || le32_to_cpu(dqhead.dqh_version) > quota_versions[type]) @@ -90,29 +92,38 @@ static int v2_read_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct v2_disk_dqheader dqhead; - struct mem_dqinfo *info = sb_dqinfo(sb, type); + struct quota_info *dqopt = sb_dqopt(sb); + struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo; ssize_t size; unsigned int version; + int ret; - if (!v2_read_header(sb, type, &dqhead)) - return -1; + down_read(&dqopt->dqio_sem); + ret = v2_read_header(sb, type, &dqhead); + if (ret < 0) + goto out; version = le32_to_cpu(dqhead.dqh_version); if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) || - (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) - return -1; + (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) { + ret = -EINVAL; + goto out; + } size = sb->s_op->quota_read(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't read info structure"); - return -1; + if (size < 0) + ret = size; + else + ret = -EIO; + goto out; } info->dqi_priv = kmalloc(sizeof(struct qtree_mem_dqinfo), GFP_NOFS); if (!info->dqi_priv) { - printk(KERN_WARNING - "Not enough memory for quota information structure.\n"); - return -ENOMEM; + ret = -ENOMEM; + goto out; } qinfo = info->dqi_priv; if (version == 0) { @@ -147,17 +158,22 @@ static int v2_read_file_info(struct super_block *sb, int type) qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk); qinfo->dqi_ops = &v2r1_qtree_ops; } - return 0; + ret = 0; +out: + up_read(&dqopt->dqio_sem); + return ret; } /* Write information header to quota file */ static int v2_write_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; - struct mem_dqinfo *info = sb_dqinfo(sb, type); + struct quota_info *dqopt = sb_dqopt(sb); + struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo = info->dqi_priv; ssize_t size; + down_write(&dqopt->dqio_sem); spin_lock(&dq_data_lock); info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); @@ -170,6 +186,7 @@ static int v2_write_file_info(struct super_block *sb, int type) dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry); size = sb->s_op->quota_write(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); + up_write(&dqopt->dqio_sem); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't write info structure"); return -1; @@ -285,17 +302,55 @@ static int v2r1_is_id(void *dp, struct dquot *dquot) static int v2_read_dquot(struct dquot *dquot) { - return qtree_read_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); + struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); + int ret; + + down_read(&dqopt->dqio_sem); + ret = qtree_read_dquot( + sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, + dquot); + up_read(&dqopt->dqio_sem); + return ret; } static int v2_write_dquot(struct dquot *dquot) { - return qtree_write_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); + struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); + int ret; + bool alloc = false; + + /* + * If space for dquot is already allocated, we don't need any + * protection as we'll only overwrite the place of dquot. We are + * still protected by concurrent writes of the same dquot by + * dquot->dq_lock. + */ + if (!dquot->dq_off) { + alloc = true; + down_write(&dqopt->dqio_sem); + } else { + down_read(&dqopt->dqio_sem); + } + ret = qtree_write_dquot( + sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, + dquot); + if (alloc) + up_write(&dqopt->dqio_sem); + else + up_read(&dqopt->dqio_sem); + return ret; } static int v2_release_dquot(struct dquot *dquot) { - return qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); + struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); + int ret; + + down_write(&dqopt->dqio_sem); + ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); + up_write(&dqopt->dqio_sem); + + return ret; } static int v2_free_file_info(struct super_block *sb, int type) @@ -306,7 +361,13 @@ static int v2_free_file_info(struct super_block *sb, int type) static int v2_get_next_id(struct super_block *sb, struct kqid *qid) { - return qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid); + struct quota_info *dqopt = sb_dqopt(sb); + int ret; + + down_read(&dqopt->dqio_sem); + ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid); + up_read(&dqopt->dqio_sem); + return ret; } static const struct quota_format_ops v2_format_ops = { diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 2ef7ce75c062..3ac1f2387083 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -228,7 +228,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file, if (!pages) goto out_free; - nr = find_get_pages(inode->i_mapping, pgoff, lpages, pages); + nr = find_get_pages(inode->i_mapping, &pgoff, lpages, pages); if (nr != lpages) goto out_free_pages; /* leave if some pages were missing */ diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 26e45863e499..11201b2d06b9 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -38,6 +38,14 @@ #include <linux/uaccess.h> #include "internal.h" +struct ramfs_mount_opts { + umode_t mode; +}; + +struct ramfs_fs_info { + struct ramfs_mount_opts mount_opts; +}; + #define RAMFS_DEFAULT_MODE 0755 static const struct super_operations ramfs_ops; @@ -149,14 +157,22 @@ static const struct inode_operations ramfs_dir_inode_operations = { .rename = simple_rename, }; +/* + * Display the mount options in /proc/mounts. + */ +static int ramfs_show_options(struct seq_file *m, struct dentry *root) +{ + struct ramfs_fs_info *fsi = root->d_sb->s_fs_info; + + if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE) + seq_printf(m, ",mode=%o", fsi->mount_opts.mode); + return 0; +} + static const struct super_operations ramfs_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, - .show_options = generic_show_options, -}; - -struct ramfs_mount_opts { - umode_t mode; + .show_options = ramfs_show_options, }; enum { @@ -169,10 +185,6 @@ static const match_table_t tokens = { {Opt_err, NULL} }; -struct ramfs_fs_info { - struct ramfs_mount_opts mount_opts; -}; - static int ramfs_parse_options(char *data, struct ramfs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -211,8 +223,6 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) diff --git a/fs/read_write.c b/fs/read_write.c index 19d4d88fa285..f0d4b16873e8 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -33,7 +33,7 @@ const struct file_operations generic_ro_fops = { EXPORT_SYMBOL(generic_ro_fops); -static inline int unsigned_offsets(struct file *file) +static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } @@ -112,7 +112,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -120,7 +120,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; @@ -356,46 +356,6 @@ out_putf: } #endif -ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - if (!file->f_op->read_iter) - return -EINVAL; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - iter->type |= READ; - ret = call_read_iter(file, &kiocb, iter); - BUG_ON(ret == -EIOCBQUEUED); - if (ret > 0) - *ppos = kiocb.ki_pos; - return ret; -} -EXPORT_SYMBOL(vfs_iter_read); - -ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - if (!file->f_op->write_iter) - return -EINVAL; - - init_sync_kiocb(&kiocb, file); - kiocb.ki_pos = *ppos; - - iter->type |= WRITE; - ret = call_write_iter(file, &kiocb, iter); - BUG_ON(ret == -EIOCBQUEUED); - if (ret > 0) - *ppos = kiocb.ki_pos; - return ret; -} -EXPORT_SYMBOL(vfs_iter_write); - int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { struct inode *inode; @@ -453,7 +413,20 @@ ssize_t __vfs_read(struct file *file, char __user *buf, size_t count, else return -EINVAL; } -EXPORT_SYMBOL(__vfs_read); + +ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) +{ + mm_segment_t old_fs; + ssize_t result; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + result = vfs_read(file, (void __user *)buf, count, pos); + set_fs(old_fs); + return result; +} +EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -481,8 +454,6 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) return ret; } -EXPORT_SYMBOL(vfs_read); - static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; @@ -511,9 +482,8 @@ ssize_t __vfs_write(struct file *file, const char __user *p, size_t count, else return -EINVAL; } -EXPORT_SYMBOL(__vfs_write); -ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) +ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { mm_segment_t old_fs; const char __user *p; @@ -536,9 +506,24 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t inc_syscw(current); return ret; } - EXPORT_SYMBOL(__kernel_write); +ssize_t kernel_write(struct file *file, const void *buf, size_t count, + loff_t *pos) +{ + mm_segment_t old_fs; + ssize_t res; + + old_fs = get_fs(); + set_fs(get_ds()); + /* The cast to a user pointer is valid due to the set_fs() */ + res = vfs_write(file, (__force const char __user *)buf, count, pos); + set_fs(old_fs); + + return res; +} +EXPORT_SYMBOL(kernel_write); + ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; @@ -567,8 +552,6 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ return ret; } -EXPORT_SYMBOL(vfs_write); - static inline loff_t file_pos_read(struct file *file) { return file->f_pos; @@ -673,21 +656,15 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_SYMBOL(iov_shorten); static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, int type, int flags) + loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; - if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC)) - return -EOPNOTSUPP; - init_sync_kiocb(&kiocb, filp); - if (flags & RWF_HIPRI) - kiocb.ki_flags |= IOCB_HIPRI; - if (flags & RWF_DSYNC) - kiocb.ki_flags |= IOCB_DSYNC; - if (flags & RWF_SYNC) - kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + ret = kiocb_set_rw_flags(&kiocb, flags); + if (ret) + return ret; kiocb.ki_pos = *ppos; if (type == READ) @@ -701,7 +678,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, int type, int flags) + loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; @@ -916,90 +893,116 @@ out: } #endif -static ssize_t __do_readv_writev(int type, struct file *file, - struct iov_iter *iter, loff_t *pos, int flags) +static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, + loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; + if (!(file->f_mode & FMODE_READ)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_READ)) + return -EINVAL; + tot_len = iov_iter_count(iter); if (!tot_len) goto out; - ret = rw_verify_area(type, file, pos, tot_len); + ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) - goto out; - - if (type != READ) - file_start_write(file); + return ret; - if ((type == READ && file->f_op->read_iter) || - (type == WRITE && file->f_op->write_iter)) - ret = do_iter_readv_writev(file, iter, pos, type, flags); + if (file->f_op->read_iter) + ret = do_iter_readv_writev(file, iter, pos, READ, flags); else - ret = do_loop_readv_writev(file, iter, pos, type, flags); - - if (type != READ) - file_end_write(file); - + ret = do_loop_readv_writev(file, iter, pos, READ, flags); out: - if ((ret + (type == READ)) > 0) { - if (type == READ) - fsnotify_access(file); - else - fsnotify_modify(file); - } + if (ret >= 0) + fsnotify_access(file); return ret; } -static ssize_t do_readv_writev(int type, struct file *file, - const struct iovec __user *uvector, - unsigned long nr_segs, loff_t *pos, - int flags) +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags) { - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; - ssize_t ret; + if (!file->f_op->read_iter) + return -EINVAL; + return do_iter_read(file, iter, ppos, flags); +} +EXPORT_SYMBOL(vfs_iter_read); + +static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, + loff_t *pos, rwf_t flags) +{ + size_t tot_len; + ssize_t ret = 0; - ret = import_iovec(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), &iov, &iter); + if (!(file->f_mode & FMODE_WRITE)) + return -EBADF; + if (!(file->f_mode & FMODE_CAN_WRITE)) + return -EINVAL; + + tot_len = iov_iter_count(iter); + if (!tot_len) + return 0; + ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) return ret; - ret = __do_readv_writev(type, file, &iter, pos, flags); - kfree(iov); - + if (file->f_op->write_iter) + ret = do_iter_readv_writev(file, iter, pos, WRITE, flags); + else + ret = do_loop_readv_writev(file, iter, pos, WRITE, flags); + if (ret > 0) + fsnotify_modify(file); return ret; } -ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags) { - if (!(file->f_mode & FMODE_READ)) - return -EBADF; - if (!(file->f_mode & FMODE_CAN_READ)) + if (!file->f_op->write_iter) return -EINVAL; - - return do_readv_writev(READ, file, vec, vlen, pos, flags); + return do_iter_write(file, iter, ppos, flags); } +EXPORT_SYMBOL(vfs_iter_write); -EXPORT_SYMBOL(vfs_readv); - -ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) +ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, + unsigned long vlen, loff_t *pos, rwf_t flags) { - if (!(file->f_mode & FMODE_WRITE)) - return -EBADF; - if (!(file->f_mode & FMODE_CAN_WRITE)) - return -EINVAL; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; + + ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret >= 0) { + ret = do_iter_read(file, &iter, pos, flags); + kfree(iov); + } - return do_readv_writev(WRITE, file, vec, vlen, pos, flags); + return ret; } -EXPORT_SYMBOL(vfs_writev); +static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, + unsigned long vlen, loff_t *pos, rwf_t flags) +{ + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; + + ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); + if (ret >= 0) { + file_start_write(file); + ret = do_iter_write(file, &iter, pos, flags); + file_end_write(file); + kfree(iov); + } + return ret; +} static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, int flags) + unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -1019,7 +1022,7 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, int flags) + unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -1045,7 +1048,7 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; @@ -1068,7 +1071,7 @@ static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; @@ -1112,7 +1115,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, - int, flags) + rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); @@ -1132,7 +1135,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, - int, flags) + rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); @@ -1143,44 +1146,20 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, } #ifdef CONFIG_COMPAT - -static ssize_t compat_do_readv_writev(int type, struct file *file, - const struct compat_iovec __user *uvector, - unsigned long nr_segs, loff_t *pos, - int flags) +static size_t compat_readv(struct file *file, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; ssize_t ret; - ret = compat_import_iovec(type, uvector, nr_segs, - UIO_FASTIOV, &iov, &iter); - if (ret < 0) - return ret; - - ret = __do_readv_writev(type, file, &iter, pos, flags); - kfree(iov); - - return ret; -} - -static size_t compat_readv(struct file *file, - const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) -{ - ssize_t ret = -EBADF; - - if (!(file->f_mode & FMODE_READ)) - goto out; - - ret = -EINVAL; - if (!(file->f_mode & FMODE_CAN_READ)) - goto out; - - ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags); - -out: + ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter); + if (ret >= 0) { + ret = do_iter_read(file, &iter, pos, flags); + kfree(iov); + } if (ret > 0) add_rchar(current, ret); inc_syscr(current); @@ -1189,7 +1168,7 @@ out: static size_t do_compat_readv(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, int flags) + compat_ulong_t vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1215,7 +1194,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, static long do_compat_preadv64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret; @@ -1253,7 +1232,7 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos, int, flags) + unsigned long, vlen, loff_t, pos, rwf_t, flags) { return do_compat_preadv64(fd, vec, vlen, pos, flags); } @@ -1262,7 +1241,7 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, - int, flags) + rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; @@ -1274,20 +1253,20 @@ COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { - ssize_t ret = -EBADF; - - if (!(file->f_mode & FMODE_WRITE)) - goto out; - - ret = -EINVAL; - if (!(file->f_mode & FMODE_CAN_WRITE)) - goto out; - - ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, flags); + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov = iovstack; + struct iov_iter iter; + ssize_t ret; -out: + ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter); + if (ret >= 0) { + file_start_write(file); + ret = do_iter_write(file, &iter, pos, flags); + file_end_write(file); + kfree(iov); + } if (ret > 0) add_wchar(current, ret); inc_syscw(current); @@ -1296,7 +1275,7 @@ out: static size_t do_compat_writev(compat_ulong_t fd, const struct compat_iovec __user* vec, - compat_ulong_t vlen, int flags) + compat_ulong_t vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1321,7 +1300,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, static long do_compat_pwritev64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret; @@ -1359,7 +1338,7 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos, int, flags) + unsigned long, vlen, loff_t, pos, rwf_t, flags) { return do_compat_pwritev64(fd, vec, vlen, pos, flags); } @@ -1367,7 +1346,7 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, - compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags) + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index dc198bc64c61..edc8ef78b63f 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -513,9 +513,17 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th, "inode has negative prealloc blocks count."); #endif while (ei->i_prealloc_count > 0) { - reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block); - ei->i_prealloc_block++; + b_blocknr_t block_to_free; + + /* + * reiserfs_free_prealloc_block can drop the write lock, + * which could allow another caller to free the same block. + * We can protect against it by modifying the prealloc + * state before calling it. + */ + block_to_free = ei->i_prealloc_block++; ei->i_prealloc_count--; + reiserfs_free_prealloc_block(th, inode, block_to_free); dirty = 1; } if (dirty) @@ -1128,7 +1136,7 @@ static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint) hint->prealloc_size = 0; if (!hint->formatted_node && hint->preallocate) { - if (S_ISREG(hint->inode->i_mode) + if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode) && hint->inode->i_size >= REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocmin * hint->inode->i_sb->s_blocksize) diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 45aa05e2232f..5b50689d8539 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -34,7 +34,7 @@ static int reiserfs_dir_fsync(struct file *filp, loff_t start, loff_t end, struct inode *inode = filp->f_mapping->host; int err; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(filp, start, end); if (err) return err; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index b396eb09f288..843aadcc123c 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -154,7 +154,7 @@ static int reiserfs_sync_file(struct file *filp, loff_t start, loff_t end, int err; int barrier_done; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(filp, start, end); if (err) return err; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 873fc04e9403..11a48affa882 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1776,7 +1776,7 @@ int reiserfs_write_inode(struct inode *inode, struct writeback_control *wbc) struct reiserfs_transaction_handle th; int jbegin_count = 1; - if (inode->i_sb->s_flags & MS_RDONLY) + if (sb_rdonly(inode->i_sb)) return -EROFS; /* * memory pressure can sometimes initiate write_inode calls with diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index 39bb1e838d8d..f59c667df15b 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1481,7 +1481,7 @@ static int flush_journal_list(struct super_block *s, if ((!was_jwait) && !buffer_locked(saved_bh)) { reiserfs_warning(s, "journal-813", "BAD! buffer %llu %cdirty %cjwait, " - "not in a newer tranasction", + "not in a newer transaction", (unsigned long long)saved_bh-> b_blocknr, was_dirty ? ' ' : '!', was_jwait ? ' ' : '!'); @@ -1918,7 +1918,7 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, * we only want to flush out transactions if we were * called with error == 0 */ - if (!error && !(sb->s_flags & MS_RDONLY)) { + if (!error && !sb_rdonly(sb)) { /* end the current trans */ BUG_ON(!th->t_trans_id); do_journal_end(th, FLUSH_ALL); @@ -2956,7 +2956,7 @@ void reiserfs_wait_on_write_block(struct super_block *s) static void queue_log_writer(struct super_block *s) { - wait_queue_t wait; + wait_queue_entry_t wait; struct reiserfs_journal *journal = SB_JOURNAL(s); set_bit(J_WRITERS_QUEUED, &journal->j_state); diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c index 4f3f928076f3..64f49cafbc5b 100644 --- a/fs/reiserfs/prints.c +++ b/fs/reiserfs/prints.c @@ -386,7 +386,7 @@ void __reiserfs_error(struct super_block *sb, const char *id, printk(KERN_CRIT "REISERFS error (device %s): %s: %s\n", sb->s_id, function, error_buf); - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return; reiserfs_info(sb, "Remounting filesystem read-only\n"); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 685f1e056998..5464ec517702 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -121,7 +121,7 @@ void reiserfs_schedule_old_flush(struct super_block *s) * Avoid scheduling flush when sb is being shut down. It can race * with journal shutdown and free still queued delayed work. */ - if (s->s_flags & MS_RDONLY || !(s->s_flags & MS_ACTIVE)) + if (sb_rdonly(s) || !(s->s_flags & MS_ACTIVE)) return; spin_lock(&sbi->old_work_lock); @@ -151,7 +151,7 @@ static int reiserfs_freeze(struct super_block *s) reiserfs_cancel_old_flush(s); reiserfs_write_lock(s); - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { int err = journal_begin(&th, s, 1); if (err) { reiserfs_block_writes(&th); @@ -599,7 +599,7 @@ static void reiserfs_put_super(struct super_block *s) * change file system state to current state if it was mounted * with read-write permissions */ - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { if (!journal_begin(&th, s, 10)) { reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -700,7 +700,7 @@ static void reiserfs_dirty_inode(struct inode *inode, int flags) int err = 0; - if (inode->i_sb->s_flags & MS_RDONLY) { + if (sb_rdonly(inode->i_sb)) { reiserfs_warning(inode->i_sb, "clm-6006", "writing inode %lu on readonly FS", inode->i_ino); @@ -1525,7 +1525,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) reiserfs_write_unlock(s); reiserfs_xattr_init(s, *mount_flags); /* remount read-only */ - if (s->s_flags & MS_RDONLY) + if (sb_rdonly(s)) /* it is read-only already */ goto out_ok_unlocked; @@ -1551,7 +1551,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) journal_mark_dirty(&th, SB_BUFFER_WITH_SB(s)); } else { /* remount read-write */ - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { reiserfs_write_unlock(s); reiserfs_xattr_init(s, *mount_flags); goto out_ok_unlocked; /* We are read-write already */ @@ -1599,8 +1599,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) } out_ok_unlocked: - if (new_opts) - replace_mount_options(s, new_opts); return 0; out_err_unlock: @@ -1857,7 +1855,7 @@ static int what_hash(struct super_block *s) * the super */ if (code != UNSET_HASH && - !(s->s_flags & MS_RDONLY) && + !sb_rdonly(s) && code != sb_hash_function_code(SB_DISK_SUPER_BLOCK(s))) { set_sb_hash_function_code(SB_DISK_SUPER_BLOCK(s), code); } @@ -1916,8 +1914,6 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) char *qf_names[REISERFS_MAXQUOTAS] = {}; unsigned int qfmt = 0; - save_mount_options(s, data); - sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; @@ -2056,7 +2052,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) if (replay_only(s)) goto error_unlocked; - if (bdev_read_only(s->s_bdev) && !(s->s_flags & MS_RDONLY)) { + if (bdev_read_only(s->s_bdev) && !sb_rdonly(s)) { SWARN(silent, s, "clm-7000", "Detected readonly device, marking FS readonly"); s->s_flags |= MS_RDONLY; @@ -2105,7 +2101,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) else set_bit(REISERFS_3_6, &sbi->s_properties); - if (!(s->s_flags & MS_RDONLY)) { + if (!sb_rdonly(s)) { errval = journal_begin(&th, s, 1); if (errval) { diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 3d2256a425ee..54415f0e3d18 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -23,7 +23,8 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) struct reiserfs_transaction_handle th; size_t jcreate_blocks; int size = acl ? posix_acl_xattr_size(acl->a_count) : 0; - + int update_mode = 0; + umode_t mode = inode->i_mode; /* * Pessimism: We can't assume that anything from the xattr root up @@ -37,7 +38,16 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) error = journal_begin(&th, inode->i_sb, jcreate_blocks); reiserfs_write_unlock(inode->i_sb); if (error == 0) { + if (type == ACL_TYPE_ACCESS && acl) { + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + goto unlock; + update_mode = 1; + } error = __reiserfs_set_acl(&th, inode, type, acl); + if (!error && update_mode) + inode->i_mode = mode; +unlock: reiserfs_write_lock(inode->i_sb); error2 = journal_end(&th); reiserfs_write_unlock(inode->i_sb); @@ -241,11 +251,6 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - } break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; diff --git a/fs/select.c b/fs/select.c index d6c652a31e99..c6362e38ae92 100644 --- a/fs/select.c +++ b/fs/select.c @@ -180,7 +180,7 @@ static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p) return table->entry++; } -static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_wqueues *pwq = wait->private; DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task); @@ -206,7 +206,7 @@ static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) return default_wake_function(&dummy_wait, mode, sync, key); } -static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key) +static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct poll_table_entry *entry; @@ -1161,59 +1161,21 @@ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { - nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); if (ufdset) { - unsigned long odd; - - if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t))) - return -EFAULT; - - odd = nr & 1UL; - nr &= ~1UL; - while (nr) { - unsigned long h, l; - if (__get_user(l, ufdset) || __get_user(h, ufdset+1)) - return -EFAULT; - ufdset += 2; - *fdset++ = h << 32 | l; - nr -= 2; - } - if (odd && __get_user(*fdset, ufdset)) - return -EFAULT; + return compat_get_bitmap(fdset, ufdset, nr); } else { - /* Tricky, must clear full unsigned long in the - * kernel fdset at the end, this makes sure that - * actually happens. - */ - memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t)); + zero_fd_set(nr, fdset); + return 0; } - return 0; } static int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { - unsigned long odd; - nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); - if (!ufdset) return 0; - - odd = nr & 1UL; - nr &= ~1UL; - while (nr) { - unsigned long h, l; - l = *fdset++; - h = l >> 32; - if (__put_user(l, ufdset) || __put_user(h, ufdset+1)) - return -EFAULT; - ufdset += 2; - nr -= 2; - } - if (odd && __put_user(*fdset, ufdset)) - return -EFAULT; - return 0; + return compat_put_bitmap(ufdset, fdset, nr); } diff --git a/fs/signalfd.c b/fs/signalfd.c index 7e3d71109f51..d2c434112f42 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -43,7 +43,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) if (likely(!waitqueue_active(wqh))) return; - /* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */ + /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ wake_up_poll(wqh, POLLHUP | POLLFREE); } @@ -95,23 +95,23 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, */ err |= __put_user(kinfo->si_signo, &uinfo->ssi_signo); err |= __put_user(kinfo->si_errno, &uinfo->ssi_errno); - err |= __put_user((short) kinfo->si_code, &uinfo->ssi_code); - switch (kinfo->si_code & __SI_MASK) { - case __SI_KILL: + err |= __put_user(kinfo->si_code, &uinfo->ssi_code); + switch (siginfo_layout(kinfo->si_signo, kinfo->si_code)) { + case SIL_KILL: err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid); err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid); break; - case __SI_TIMER: + case SIL_TIMER: err |= __put_user(kinfo->si_tid, &uinfo->ssi_tid); err |= __put_user(kinfo->si_overrun, &uinfo->ssi_overrun); err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr); err |= __put_user(kinfo->si_int, &uinfo->ssi_int); break; - case __SI_POLL: + case SIL_POLL: err |= __put_user(kinfo->si_band, &uinfo->ssi_band); err |= __put_user(kinfo->si_fd, &uinfo->ssi_fd); break; - case __SI_FAULT: + case SIL_FAULT: err |= __put_user((long) kinfo->si_addr, &uinfo->ssi_addr); #ifdef __ARCH_SI_TRAPNO err |= __put_user(kinfo->si_trapno, &uinfo->ssi_trapno); @@ -128,20 +128,14 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, &uinfo->ssi_addr_lsb); #endif break; - case __SI_CHLD: + case SIL_CHLD: err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid); err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid); err |= __put_user(kinfo->si_status, &uinfo->ssi_status); err |= __put_user(kinfo->si_utime, &uinfo->ssi_utime); err |= __put_user(kinfo->si_stime, &uinfo->ssi_stime); break; - case __SI_RT: /* This is not generated by the kernel as of now. */ - case __SI_MESGQ: /* But this is */ - err |= __put_user(kinfo->si_pid, &uinfo->ssi_pid); - err |= __put_user(kinfo->si_uid, &uinfo->ssi_uid); - err |= __put_user((long) kinfo->si_ptr, &uinfo->ssi_ptr); - err |= __put_user(kinfo->si_int, &uinfo->ssi_int); - break; + case SIL_RT: default: /* * This case catches also the signals queued by sigqueue(). diff --git a/fs/splice.c b/fs/splice.c index 540c4a44756c..f3084cce0ea6 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -364,22 +364,6 @@ static ssize_t kernel_readv(struct file *file, const struct kvec *vec, return res; } -ssize_t kernel_write(struct file *file, const char *buf, size_t count, - loff_t pos) -{ - mm_segment_t old_fs; - ssize_t res; - - old_fs = get_fs(); - set_fs(get_ds()); - /* The cast to a user pointer is valid due to the set_fs() */ - res = vfs_write(file, (__force const char __user *)buf, count, &pos); - set_fs(old_fs); - - return res; -} -EXPORT_SYMBOL(kernel_write); - static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) @@ -762,7 +746,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n, sd.total_len - left); - ret = vfs_iter_write(out, &from, &sd.pos); + ret = vfs_iter_write(out, &from, &sd.pos, 0); if (ret <= 0) break; diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig index ffb093e72b6c..1adb3346b9d6 100644 --- a/fs/squashfs/Kconfig +++ b/fs/squashfs/Kconfig @@ -165,6 +165,20 @@ config SQUASHFS_XZ If unsure, say N. +config SQUASHFS_ZSTD + bool "Include support for ZSTD compressed file systems" + depends on SQUASHFS + select ZSTD_DECOMPRESS + help + Saying Y here includes support for reading Squashfs file systems + compressed with ZSTD compression. ZSTD gives better compression than + the default ZLIB compression, while using less CPU. + + ZSTD is not the standard compression used in Squashfs and so most + file systems will be readable without selecting this option. + + If unsure, say N. + config SQUASHFS_4K_DEVBLK_SIZE bool "Use 4K device block size?" depends on SQUASHFS diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile index 246a6f329d89..6655631c53ae 100644 --- a/fs/squashfs/Makefile +++ b/fs/squashfs/Makefile @@ -15,3 +15,4 @@ squashfs-$(CONFIG_SQUASHFS_LZ4) += lz4_wrapper.o squashfs-$(CONFIG_SQUASHFS_LZO) += lzo_wrapper.o squashfs-$(CONFIG_SQUASHFS_XZ) += xz_wrapper.o squashfs-$(CONFIG_SQUASHFS_ZLIB) += zlib_wrapper.o +squashfs-$(CONFIG_SQUASHFS_ZSTD) += zstd_wrapper.o diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c index d2bc13636f79..836639810ea0 100644 --- a/fs/squashfs/decompressor.c +++ b/fs/squashfs/decompressor.c @@ -65,6 +65,12 @@ static const struct squashfs_decompressor squashfs_zlib_comp_ops = { }; #endif +#ifndef CONFIG_SQUASHFS_ZSTD +static const struct squashfs_decompressor squashfs_zstd_comp_ops = { + NULL, NULL, NULL, NULL, ZSTD_COMPRESSION, "zstd", 0 +}; +#endif + static const struct squashfs_decompressor squashfs_unknown_comp_ops = { NULL, NULL, NULL, NULL, 0, "unknown", 0 }; @@ -75,6 +81,7 @@ static const struct squashfs_decompressor *decompressor[] = { &squashfs_lzo_comp_ops, &squashfs_xz_comp_ops, &squashfs_lzma_unsupported_comp_ops, + &squashfs_zstd_comp_ops, &squashfs_unknown_comp_ops }; diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h index a25713c031a5..0f5a8e4e58da 100644 --- a/fs/squashfs/decompressor.h +++ b/fs/squashfs/decompressor.h @@ -58,4 +58,8 @@ extern const struct squashfs_decompressor squashfs_lzo_comp_ops; extern const struct squashfs_decompressor squashfs_zlib_comp_ops; #endif +#ifdef CONFIG_SQUASHFS_ZSTD +extern const struct squashfs_decompressor squashfs_zstd_comp_ops; +#endif + #endif diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 506f4ba5b983..24d12fd14177 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -241,6 +241,7 @@ struct meta_index { #define LZO_COMPRESSION 3 #define XZ_COMPRESSION 4 #define LZ4_COMPRESSION 5 +#define ZSTD_COMPRESSION 6 struct squashfs_super_block { __le32 s_magic; diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c new file mode 100644 index 000000000000..eeaabf881159 --- /dev/null +++ b/fs/squashfs/zstd_wrapper.c @@ -0,0 +1,151 @@ +/* + * Squashfs - a compressed read only filesystem for Linux + * + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2, + * or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * zstd_wrapper.c + */ + +#include <linux/mutex.h> +#include <linux/buffer_head.h> +#include <linux/slab.h> +#include <linux/zstd.h> +#include <linux/vmalloc.h> + +#include "squashfs_fs.h" +#include "squashfs_fs_sb.h" +#include "squashfs.h" +#include "decompressor.h" +#include "page_actor.h" + +struct workspace { + void *mem; + size_t mem_size; + size_t window_size; +}; + +static void *zstd_init(struct squashfs_sb_info *msblk, void *buff) +{ + struct workspace *wksp = kmalloc(sizeof(*wksp), GFP_KERNEL); + + if (wksp == NULL) + goto failed; + wksp->window_size = max_t(size_t, + msblk->block_size, SQUASHFS_METADATA_SIZE); + wksp->mem_size = ZSTD_DStreamWorkspaceBound(wksp->window_size); + wksp->mem = vmalloc(wksp->mem_size); + if (wksp->mem == NULL) + goto failed; + + return wksp; + +failed: + ERROR("Failed to allocate zstd workspace\n"); + kfree(wksp); + return ERR_PTR(-ENOMEM); +} + + +static void zstd_free(void *strm) +{ + struct workspace *wksp = strm; + + if (wksp) + vfree(wksp->mem); + kfree(wksp); +} + + +static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, + struct buffer_head **bh, int b, int offset, int length, + struct squashfs_page_actor *output) +{ + struct workspace *wksp = strm; + ZSTD_DStream *stream; + size_t total_out = 0; + size_t zstd_err; + int k = 0; + ZSTD_inBuffer in_buf = { NULL, 0, 0 }; + ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + + stream = ZSTD_initDStream(wksp->window_size, wksp->mem, wksp->mem_size); + + if (!stream) { + ERROR("Failed to initialize zstd decompressor\n"); + goto out; + } + + out_buf.size = PAGE_SIZE; + out_buf.dst = squashfs_first_page(output); + + do { + if (in_buf.pos == in_buf.size && k < b) { + int avail = min(length, msblk->devblksize - offset); + + length -= avail; + in_buf.src = bh[k]->b_data + offset; + in_buf.size = avail; + in_buf.pos = 0; + offset = 0; + } + + if (out_buf.pos == out_buf.size) { + out_buf.dst = squashfs_next_page(output); + if (out_buf.dst == NULL) { + /* Shouldn't run out of pages + * before stream is done. + */ + squashfs_finish_page(output); + goto out; + } + out_buf.pos = 0; + out_buf.size = PAGE_SIZE; + } + + total_out -= out_buf.pos; + zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf); + total_out += out_buf.pos; /* add the additional data produced */ + + if (in_buf.pos == in_buf.size && k < b) + put_bh(bh[k++]); + } while (zstd_err != 0 && !ZSTD_isError(zstd_err)); + + squashfs_finish_page(output); + + if (ZSTD_isError(zstd_err)) { + ERROR("zstd decompression error: %d\n", + (int)ZSTD_getErrorCode(zstd_err)); + goto out; + } + + if (k < b) + goto out; + + return (int)total_out; + +out: + for (; k < b; k++) + put_bh(bh[k]); + + return -EIO; +} + +const struct squashfs_decompressor squashfs_zstd_comp_ops = { + .init = zstd_init, + .free = zstd_free, + .decompress = zstd_uncompress, + .id = ZSTD_COMPRESSION, + .name = "zstd", + .supported = 1 +}; diff --git a/fs/stat.c b/fs/stat.c index c35610845ab1..8a6aa8caf891 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -710,7 +710,7 @@ loff_t inode_get_bytes(struct inode *inode) loff_t ret; spin_lock(&inode->i_lock); - ret = (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; + ret = __inode_get_bytes(inode); spin_unlock(&inode->i_lock); return ret; } diff --git a/fs/statfs.c b/fs/statfs.c index 4e4623c7a126..fab9b6a3c116 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -38,6 +38,8 @@ static int flags_by_sb(int s_flags) flags |= ST_SYNCHRONOUS; if (s_flags & MS_MANDLOCK) flags |= ST_MANDLOCK; + if (s_flags & MS_RDONLY) + flags |= ST_RDONLY; return flags; } @@ -244,6 +246,7 @@ SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf) #ifdef CONFIG_COMPAT static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf) { + struct compat_statfs buf; if (sizeof ubuf->f_blocks == 4) { if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) @@ -257,20 +260,20 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * && (kbuf->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || - __put_user(kbuf->f_type, &ubuf->f_type) || - __put_user(kbuf->f_bsize, &ubuf->f_bsize) || - __put_user(kbuf->f_blocks, &ubuf->f_blocks) || - __put_user(kbuf->f_bfree, &ubuf->f_bfree) || - __put_user(kbuf->f_bavail, &ubuf->f_bavail) || - __put_user(kbuf->f_files, &ubuf->f_files) || - __put_user(kbuf->f_ffree, &ubuf->f_ffree) || - __put_user(kbuf->f_namelen, &ubuf->f_namelen) || - __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || - __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(kbuf->f_flags, &ubuf->f_flags) || - __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) + memset(&buf, 0, sizeof(struct compat_statfs)); + buf.f_type = kbuf->f_type; + buf.f_bsize = kbuf->f_bsize; + buf.f_blocks = kbuf->f_blocks; + buf.f_bfree = kbuf->f_bfree; + buf.f_bavail = kbuf->f_bavail; + buf.f_files = kbuf->f_files; + buf.f_ffree = kbuf->f_ffree; + buf.f_namelen = kbuf->f_namelen; + buf.f_fsid.val[0] = kbuf->f_fsid.val[0]; + buf.f_fsid.val[1] = kbuf->f_fsid.val[1]; + buf.f_frsize = kbuf->f_frsize; + buf.f_flags = kbuf->f_flags; + if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs))) return -EFAULT; return 0; } @@ -299,6 +302,7 @@ COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) { + struct compat_statfs64 buf; if (sizeof(ubuf->f_bsize) == 4) { if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen | kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL) @@ -312,20 +316,20 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat && (kbuf->f_ffree & 0xffffffff00000000ULL)) return -EOVERFLOW; } - if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) || - __put_user(kbuf->f_type, &ubuf->f_type) || - __put_user(kbuf->f_bsize, &ubuf->f_bsize) || - __put_user(kbuf->f_blocks, &ubuf->f_blocks) || - __put_user(kbuf->f_bfree, &ubuf->f_bfree) || - __put_user(kbuf->f_bavail, &ubuf->f_bavail) || - __put_user(kbuf->f_files, &ubuf->f_files) || - __put_user(kbuf->f_ffree, &ubuf->f_ffree) || - __put_user(kbuf->f_namelen, &ubuf->f_namelen) || - __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || - __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(kbuf->f_flags, &ubuf->f_flags) || - __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) + memset(&buf, 0, sizeof(struct compat_statfs64)); + buf.f_type = kbuf->f_type; + buf.f_bsize = kbuf->f_bsize; + buf.f_blocks = kbuf->f_blocks; + buf.f_bfree = kbuf->f_bfree; + buf.f_bavail = kbuf->f_bavail; + buf.f_files = kbuf->f_files; + buf.f_ffree = kbuf->f_ffree; + buf.f_namelen = kbuf->f_namelen; + buf.f_fsid.val[0] = kbuf->f_fsid.val[0]; + buf.f_fsid.val[1] = kbuf->f_fsid.val[1]; + buf.f_frsize = kbuf->f_frsize; + buf.f_flags = kbuf->f_flags; + if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs64))) return -EFAULT; return 0; } diff --git a/fs/super.c b/fs/super.c index adb0c0de428c..166c4ee0d0ed 100644 --- a/fs/super.c +++ b/fs/super.c @@ -168,7 +168,6 @@ static void destroy_super(struct super_block *s) WARN_ON(!list_empty(&s->s_mounts)); put_user_ns(s->s_user_ns); kfree(s->s_subtype); - kfree(s->s_options); call_rcu(&s->rcu, destroy_super_rcu); } @@ -243,7 +242,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key); - mutex_init(&s->s_dquot.dqio_mutex); + init_rwsem(&s->s_dquot.dqio_sem); s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; @@ -361,7 +360,7 @@ static int grab_super(struct super_block *s) __releases(sb_lock) s->s_count++; spin_unlock(&sb_lock); down_write(&s->s_umount); - if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) { + if ((s->s_flags & SB_BORN) && atomic_inc_not_zero(&s->s_active)) { put_super(s); return 1; } @@ -391,7 +390,7 @@ bool trylock_super(struct super_block *sb) { if (down_read_trylock(&sb->s_umount)) { if (!hlist_unhashed(&sb->s_instances) && - sb->s_root && (sb->s_flags & MS_BORN)) + sb->s_root && (sb->s_flags & SB_BORN)) return true; up_read(&sb->s_umount); } @@ -420,7 +419,7 @@ void generic_shutdown_super(struct super_block *sb) if (sb->s_root) { shrink_dcache_for_umount(sb); sync_filesystem(sb); - sb->s_flags &= ~MS_ACTIVE; + sb->s_flags &= ~SB_ACTIVE; fsnotify_unmount_inodes(sb); cgroup_writeback_umount(); @@ -473,7 +472,7 @@ struct super_block *sget_userns(struct file_system_type *type, struct super_block *old; int err; - if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && + if (!(flags & (SB_KERNMOUNT|SB_SUBMOUNT)) && !(type->fs_flags & FS_USERNS_MOUNT) && !capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -503,12 +502,12 @@ retry: } if (!s) { spin_unlock(&sb_lock); - s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns); + s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } - + err = set(s, data); if (err) { spin_unlock(&sb_lock); @@ -548,11 +547,11 @@ struct super_block *sget(struct file_system_type *type, * mount through to here so always use &init_user_ns * until that changes. */ - if (flags & MS_SUBMOUNT) + if (flags & SB_SUBMOUNT) user_ns = &init_user_ns; /* Ensure the requestor has permissions over the target filesystem */ - if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN)) + if (!(flags & (SB_KERNMOUNT|SB_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); return sget_userns(type, test, set, flags, user_ns, data); @@ -595,7 +594,7 @@ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) spin_unlock(&sb_lock); down_read(&sb->s_umount); - if (sb->s_root && (sb->s_flags & MS_BORN)) + if (sb->s_root && (sb->s_flags & SB_BORN)) f(sb, arg); up_read(&sb->s_umount); @@ -629,7 +628,7 @@ void iterate_supers_type(struct file_system_type *type, spin_unlock(&sb_lock); down_read(&sb->s_umount); - if (sb->s_root && (sb->s_flags & MS_BORN)) + if (sb->s_root && (sb->s_flags & SB_BORN)) f(sb, arg); up_read(&sb->s_umount); @@ -665,7 +664,7 @@ rescan: else down_write(&sb->s_umount); /* still alive? */ - if (sb->s_root && (sb->s_flags & MS_BORN)) + if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; if (!excl) up_read(&sb->s_umount); @@ -771,7 +770,7 @@ restart: spin_unlock(&sb_lock); return NULL; } - + struct super_block *user_get_super(dev_t dev) { struct super_block *sb; @@ -786,7 +785,7 @@ rescan: spin_unlock(&sb_lock); down_read(&sb->s_umount); /* still alive? */ - if (sb->s_root && (sb->s_flags & MS_BORN)) + if (sb->s_root && (sb->s_flags & SB_BORN)) return sb; up_read(&sb->s_umount); /* nope, got unmounted */ @@ -802,13 +801,13 @@ rescan: /** * do_remount_sb - asks filesystem to change mount options. * @sb: superblock in question - * @flags: numeric part of options + * @sb_flags: revised superblock flags * @data: the rest of options * @force: whether or not to force the change * * Alters the mount options of a mounted file system. */ -int do_remount_sb(struct super_block *sb, int flags, void *data, int force) +int do_remount_sb(struct super_block *sb, int sb_flags, void *data, int force) { int retval; int remount_ro; @@ -817,11 +816,11 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) return -EBUSY; #ifdef CONFIG_BLOCK - if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev)) + if (!(sb_flags & SB_RDONLY) && bdev_read_only(sb->s_bdev)) return -EACCES; #endif - remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY); + remount_ro = (sb_flags & SB_RDONLY) && !sb_rdonly(sb); if (remount_ro) { if (!hlist_empty(&sb->s_pins)) { @@ -832,7 +831,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) return 0; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; - remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY); + remount_ro = (sb_flags & SB_RDONLY) && !sb_rdonly(sb); } } shrink_dcache_sb(sb); @@ -851,7 +850,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) } if (sb->s_op->remount_fs) { - retval = sb->s_op->remount_fs(sb, &flags, data); + retval = sb->s_op->remount_fs(sb, &sb_flags, data); if (retval) { if (!force) goto cancel_readonly; @@ -860,7 +859,7 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force) sb->s_type->name, retval); } } - sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK); + sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (sb_flags & MS_RMT_MASK); /* Needs to be ordered wrt mnt_is_readonly() */ smp_wmb(); sb->s_readonly_remount = 0; @@ -893,12 +892,12 @@ static void do_emergency_remount(struct work_struct *work) sb->s_count++; spin_unlock(&sb_lock); down_write(&sb->s_umount); - if (sb->s_root && sb->s_bdev && (sb->s_flags & MS_BORN) && - !(sb->s_flags & MS_RDONLY)) { + if (sb->s_root && sb->s_bdev && (sb->s_flags & SB_BORN) && + !sb_rdonly(sb)) { /* * What lock protects sb->s_flags?? */ - do_remount_sb(sb, MS_RDONLY, NULL, 1); + do_remount_sb(sb, SB_RDONLY, NULL, 1); } up_write(&sb->s_umount); spin_lock(&sb_lock); @@ -1024,7 +1023,7 @@ struct dentry *mount_ns(struct file_system_type *fs_type, /* Don't allow mounting unless the caller has CAP_SYS_ADMIN * over the namespace. */ - if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN)) + if (!(flags & SB_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); sb = sget_userns(fs_type, ns_test_super, ns_set_super, flags, @@ -1034,13 +1033,13 @@ struct dentry *mount_ns(struct file_system_type *fs_type, if (!sb->s_root) { int err; - err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0); + err = fill_super(sb, data, flags & SB_SILENT ? 1 : 0); if (err) { deactivate_locked_super(sb); return ERR_PTR(err); } - sb->s_flags |= MS_ACTIVE; + sb->s_flags |= SB_ACTIVE; } return dget(sb->s_root); @@ -1072,7 +1071,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, fmode_t mode = FMODE_READ | FMODE_EXCL; int error = 0; - if (!(flags & MS_RDONLY)) + if (!(flags & SB_RDONLY)) mode |= FMODE_WRITE; bdev = blkdev_get_by_path(dev_name, mode, fs_type); @@ -1090,14 +1089,14 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, error = -EBUSY; goto error_bdev; } - s = sget(fs_type, test_bdev_super, set_bdev_super, flags | MS_NOSEC, + s = sget(fs_type, test_bdev_super, set_bdev_super, flags | SB_NOSEC, bdev); mutex_unlock(&bdev->bd_fsfreeze_mutex); if (IS_ERR(s)) goto error_s; if (s->s_root) { - if ((flags ^ s->s_flags) & MS_RDONLY) { + if ((flags ^ s->s_flags) & SB_RDONLY) { deactivate_locked_super(s); error = -EBUSY; goto error_bdev; @@ -1117,13 +1116,13 @@ struct dentry *mount_bdev(struct file_system_type *fs_type, s->s_mode = mode; snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev); sb_set_blocksize(s, block_size(bdev)); - error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); + error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); goto error; } - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; bdev->bd_super = s; } @@ -1163,12 +1162,12 @@ struct dentry *mount_nodev(struct file_system_type *fs_type, if (IS_ERR(s)) return ERR_CAST(s); - error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); + error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); return ERR_PTR(error); } - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; return dget(s->s_root); } EXPORT_SYMBOL(mount_nodev); @@ -1189,12 +1188,12 @@ struct dentry *mount_single(struct file_system_type *fs_type, if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { - error = fill_super(s, data, flags & MS_SILENT ? 1 : 0); + error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); return ERR_PTR(error); } - s->s_flags |= MS_ACTIVE; + s->s_flags |= SB_ACTIVE; } else { do_remount_sb(s, flags, data, 0); } @@ -1228,7 +1227,7 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) sb = root->d_sb; BUG_ON(!sb); WARN_ON(!sb->s_bdi); - sb->s_flags |= MS_BORN; + sb->s_flags |= SB_BORN; error = security_sb_kern_mount(sb, flags, secdata); if (error) @@ -1435,12 +1434,12 @@ int freeze_super(struct super_block *sb) return -EBUSY; } - if (!(sb->s_flags & MS_BORN)) { + if (!(sb->s_flags & SB_BORN)) { up_write(&sb->s_umount); return 0; /* sic - it's "nothing to do" */ } - if (sb->s_flags & MS_RDONLY) { + if (sb_rdonly(sb)) { /* Nothing to do really... */ sb->s_writers.frozen = SB_FREEZE_COMPLETE; up_write(&sb->s_umount); @@ -1503,7 +1502,7 @@ int thaw_super(struct super_block *sb) return -EINVAL; } - if (sb->s_flags & MS_RDONLY) { + if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; goto out; } diff --git a/fs/sync.c b/fs/sync.c index 11ba023434b1..a576aa2e6b09 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -57,7 +57,7 @@ int sync_filesystem(struct super_block *sb) /* * No point in syncing out anything if the filesystem is read-only. */ - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return 0; ret = __sync_filesystem(sb, 0); @@ -69,13 +69,13 @@ EXPORT_SYMBOL(sync_filesystem); static void sync_inodes_one_sb(struct super_block *sb, void *arg) { - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) sync_inodes_sb(sb); } static void sync_fs_one_sb(struct super_block *sb, void *arg) { - if (!(sb->s_flags & MS_RDONLY) && sb->s_op->sync_fs) + if (!sb_rdonly(sb) && sb->s_op->sync_fs) sb->s_op->sync_fs(sb, *(int *)arg); } @@ -192,7 +192,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) spin_unlock(&inode->i_lock); mark_inode_dirty_sync(inode); } - return call_fsync(file, start, end, datasync); + return file->f_op->fsync(file, start, end, datasync); } EXPORT_SYMBOL(vfs_fsync_range); @@ -335,14 +335,9 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, goto out_put; mapping = f.file->f_mapping; - if (!mapping) { - ret = -EINVAL; - goto out_put; - } - ret = 0; if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) { - ret = filemap_fdatawait_range(mapping, offset, endbyte); + ret = file_fdatawait_range(f.file, offset, endbyte); if (ret < 0) goto out_put; } @@ -355,7 +350,7 @@ SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, } if (flags & SYNC_FILE_RANGE_WAIT_AFTER) - ret = filemap_fdatawait_range(mapping, offset, endbyte); + ret = file_fdatawait_range(f.file, offset, endbyte); out_put: fdput(f); diff --git a/fs/sysv/balloc.c b/fs/sysv/balloc.c index 921c053fc052..862c1f74a583 100644 --- a/fs/sysv/balloc.c +++ b/fs/sysv/balloc.c @@ -231,7 +231,7 @@ trust_sb: Ecount: printk("sysv_count_free_blocks: free block count was %d, " "correcting to %d\n", sb_count, count); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { *sbi->s_free_blocks = cpu_to_fs32(sbi, count); dirty_sb(sb); } diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 5bdae85ceef7..f5191cb2c947 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -45,7 +45,7 @@ static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); return err; diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 53f1b78996dd..eb963fbb7903 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -220,7 +220,7 @@ Einval: printk("sysv_count_free_inodes: " "free inode count was %d, correcting to %d\n", sb_count, count); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { *sbi->s_sb_total_free_inodes = cpu_to_fs16(SYSV_SB(sb), count); dirty_sb(sb); } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 858fb72f9e0f..1c8bf9453a71 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -70,7 +70,7 @@ static void sysv_put_super(struct super_block *sb) { struct sysv_sb_info *sbi = SYSV_SB(sb); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { /* XXX ext2 also updates the state here */ mark_buffer_dirty(sbi->s_bh1); if (sbi->s_bh1 != sbi->s_bh2) diff --git a/fs/sysv/super.c b/fs/sysv/super.c index eda10959714f..0d56e486b392 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -216,7 +216,7 @@ static int detect_sysv(struct sysv_sb_info *sbi, struct buffer_head *bh) if (fs16_to_cpu(sbi, sbd->s_nfree) == 0xffff) { sbi->s_type = FSTYPE_AFS; sbi->s_forced_ro = 1; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { printk("SysV FS: SCO EAFS on %s detected, " "forcing read-only mode.\n", sb->s_id); diff --git a/fs/timerfd.c b/fs/timerfd.c index c543cdb5f8ed..ece0c02d7e63 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -169,7 +169,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) } static int timerfd_setup(struct timerfd_ctx *ctx, int flags, - const struct itimerspec *ktmr) + const struct itimerspec64 *ktmr) { enum hrtimer_mode htmode; ktime_t texp; @@ -178,10 +178,10 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags, htmode = (flags & TFD_TIMER_ABSTIME) ? HRTIMER_MODE_ABS: HRTIMER_MODE_REL; - texp = timespec_to_ktime(ktmr->it_value); + texp = timespec64_to_ktime(ktmr->it_value); ctx->expired = 0; ctx->ticks = 0; - ctx->tintv = timespec_to_ktime(ktmr->it_interval); + ctx->tintv = timespec64_to_ktime(ktmr->it_interval); if (isalarm(ctx)) { alarm_init(&ctx->t.alarm, @@ -432,16 +432,15 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags) } static int do_timerfd_settime(int ufd, int flags, - const struct itimerspec *new, - struct itimerspec *old) + const struct itimerspec64 *new, + struct itimerspec64 *old) { struct fd f; struct timerfd_ctx *ctx; int ret; if ((flags & ~TFD_SETTIME_FLAGS) || - !timespec_valid(&new->it_value) || - !timespec_valid(&new->it_interval)) + !itimerspec64_valid(new)) return -EINVAL; ret = timerfd_fget(ufd, &f); @@ -487,8 +486,8 @@ static int do_timerfd_settime(int ufd, int flags, hrtimer_forward_now(&ctx->t.tmr, ctx->tintv); } - old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); - old->it_interval = ktime_to_timespec(ctx->tintv); + old->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx)); + old->it_interval = ktime_to_timespec64(ctx->tintv); /* * Re-program the timer to the new value ... @@ -500,7 +499,7 @@ static int do_timerfd_settime(int ufd, int flags, return ret; } -static int do_timerfd_gettime(int ufd, struct itimerspec *t) +static int do_timerfd_gettime(int ufd, struct itimerspec64 *t) { struct fd f; struct timerfd_ctx *ctx; @@ -525,8 +524,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec *t) hrtimer_restart(&ctx->t.tmr); } } - t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx)); - t->it_interval = ktime_to_timespec(ctx->tintv); + t->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx)); + t->it_interval = ktime_to_timespec64(ctx->tintv); spin_unlock_irq(&ctx->wqh.lock); fdput(f); return 0; @@ -536,15 +535,15 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct itimerspec __user *, utmr, struct itimerspec __user *, otmr) { - struct itimerspec new, old; + struct itimerspec64 new, old; int ret; - if (copy_from_user(&new, utmr, sizeof(new))) + if (get_itimerspec64(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; - if (otmr && copy_to_user(otmr, &old, sizeof(old))) + if (otmr && put_itimerspec64(&old, otmr)) return -EFAULT; return ret; @@ -552,11 +551,11 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr) { - struct itimerspec kotmr; + struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; - return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0; + return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } #ifdef CONFIG_COMPAT @@ -564,15 +563,15 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, const struct compat_itimerspec __user *, utmr, struct compat_itimerspec __user *, otmr) { - struct itimerspec new, old; + struct itimerspec64 new, old; int ret; - if (get_compat_itimerspec(&new, utmr)) + if (get_compat_itimerspec64(&new, utmr)) return -EFAULT; ret = do_timerfd_settime(ufd, flags, &new, &old); if (ret) return ret; - if (otmr && put_compat_itimerspec(otmr, &old)) + if (otmr && put_compat_itimerspec64(&old, otmr)) return -EFAULT; return ret; } @@ -580,10 +579,10 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags, COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct compat_itimerspec __user *, otmr) { - struct itimerspec kotmr; + struct itimerspec64 kotmr; int ret = do_timerfd_gettime(ufd, &kotmr); if (ret) return ret; - return put_compat_itimerspec(otmr, &kotmr) ? -EFAULT: 0; + return put_compat_itimerspec64(&kotmr, otmr) ? -EFAULT : 0; } #endif diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 328e89c2cf83..bea8ad876bf9 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -270,8 +270,6 @@ static int trace_fill_super(struct super_block *sb, void *data, int silent) struct tracefs_fs_info *fsi; int err; - save_mount_options(sb, data); - fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL); sb->s_fs_info = fsi; if (!fsi) { diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index 382ed428cfd2..114ba455bac3 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -9,8 +9,13 @@ static int ubifs_crypt_get_context(struct inode *inode, void *ctx, size_t len) static int ubifs_crypt_set_context(struct inode *inode, const void *ctx, size_t len, void *fs_data) { + /* + * Creating an encryption context is done unlocked since we + * operate on a new inode which is not visible to other users + * at this point. So, no need to check whether inode is locked. + */ return ubifs_xattr_set(inode, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); + ctx, len, 0, false); } static bool ubifs_crypt_empty_dir(struct inode *inode) diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 566079d9b402..417fe0b29f23 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -143,6 +143,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir, case S_IFBLK: case S_IFCHR: inode->i_op = &ubifs_file_inode_operations; + encrypted = false; break; default: BUG(); @@ -1061,7 +1062,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, int sz_change; int err, devlen = 0; struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1, - .new_ino_d = ALIGN(devlen, 8), .dirtied_ino = 1 }; struct fscrypt_name nm; @@ -1079,6 +1079,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry, devlen = ubifs_encode_dev(dev, rdev); } + req.new_ino_d = ALIGN(devlen, 8); err = ubifs_budget_space(c, &req); if (err) { kfree(dev); @@ -1396,17 +1397,14 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS); if (!dev) { - ubifs_release_budget(c, &req); - ubifs_release_budget(c, &ino_req); - return -ENOMEM; + err = -ENOMEM; + goto out_release; } err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout); if (err) { - ubifs_release_budget(c, &req); - ubifs_release_budget(c, &ino_req); kfree(dev); - return err; + goto out_release; } whiteout->i_state |= I_LINKABLE; @@ -1494,12 +1492,10 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, err = ubifs_budget_space(c, &wht_req); if (err) { - ubifs_release_budget(c, &req); - ubifs_release_budget(c, &ino_req); kfree(whiteout_ui->data); whiteout_ui->data_len = 0; iput(whiteout); - return err; + goto out_release; } inc_nlink(whiteout); @@ -1554,6 +1550,7 @@ out_cancel: iput(whiteout); } unlock_4_inodes(old_dir, new_dir, new_inode, whiteout); +out_release: ubifs_release_budget(c, &ino_req); ubifs_release_budget(c, &req); fscrypt_free_filename(&old_nm); @@ -1647,6 +1644,21 @@ int ubifs_getattr(const struct path *path, struct kstat *stat, struct ubifs_inode *ui = ubifs_inode(inode); mutex_lock(&ui->ui_mutex); + + if (ui->flags & UBIFS_APPEND_FL) + stat->attributes |= STATX_ATTR_APPEND; + if (ui->flags & UBIFS_COMPR_FL) + stat->attributes |= STATX_ATTR_COMPRESSED; + if (ui->flags & UBIFS_CRYPT_FL) + stat->attributes |= STATX_ATTR_ENCRYPTED; + if (ui->flags & UBIFS_IMMUTABLE_FL) + stat->attributes |= STATX_ATTR_IMMUTABLE; + + stat->attributes_mask |= (STATX_ATTR_APPEND | + STATX_ATTR_COMPRESSED | + STATX_ATTR_ENCRYPTED | + STATX_ATTR_IMMUTABLE); + generic_fillattr(inode, stat); stat->blksize = UBIFS_BLOCK_SIZE; stat->size = ui->ui_size; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2cda3d67e2d0..a02aa59d1e24 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -735,6 +735,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, int err, page_idx, page_cnt, ret = 0, n = 0; int allocate = bu->buf ? 0 : 1; loff_t isize; + gfp_t ra_gfp_mask = readahead_gfp_mask(mapping) & ~__GFP_FS; err = ubifs_tnc_get_bu_keys(c, bu); if (err) @@ -796,8 +797,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu, if (page_offset > end_index) break; - page = find_or_create_page(mapping, page_offset, - GFP_NOFS | __GFP_COLD); + page = find_or_create_page(mapping, page_offset, ra_gfp_mask); if (!page) break; if (!PageUptodate(page)) @@ -1284,6 +1284,14 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr) if (err) return err; + if (ubifs_crypt_is_encrypted(inode) && (attr->ia_valid & ATTR_SIZE)) { + err = fscrypt_get_encryption_info(inode); + if (err) + return err; + if (!fscrypt_has_encryption_key(inode)) + return -ENOKEY; + } + if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size < inode->i_size) /* Truncation to a smaller size */ err = do_truncation(c, inode, attr); @@ -1329,7 +1337,7 @@ int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ return 0; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); + err = file_write_and_wait_range(file, start, end); if (err) return err; inode_lock(inode); @@ -1482,7 +1490,10 @@ static int ubifs_migrate_page(struct address_space *mapping, SetPagePrivate(newpage); } - migrate_page_copy(newpage, page); + if (mode != MIGRATE_SYNC_NO_COPY) + migrate_page_copy(newpage, page); + else + migrate_page_states(newpage, page); return MIGRATEPAGE_SUCCESS; } #endif @@ -1607,15 +1618,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = { static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) { int err; - struct inode *inode = file->f_mapping->host; - - if (ubifs_crypt_is_encrypted(inode)) { - err = fscrypt_get_encryption_info(inode); - if (err) - return -EACCES; - if (!fscrypt_has_encryption_key(inode)) - return -ENOKEY; - } err = generic_file_mmap(file, vma); if (err) @@ -1698,12 +1700,6 @@ static const char *ubifs_get_link(struct dentry *dentry, pstr.name[pstr.len] = '\0'; - // XXX this probably won't happen anymore... - if (pstr.name[0] == '\0') { - fscrypt_fname_free_buffer(&pstr); - return ERR_PTR(-ENOENT); - } - set_delayed_call(done, kfree_link, pstr.name); return pstr.name; } diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 294519b98874..04c4ec6483e5 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -549,8 +549,6 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, struct ubifs_ino_node *ino; union ubifs_key dent_key, ino_key; - //dbg_jnl("ino %lu, dent '%.*s', data len %d in dir ino %lu", - // inode->i_ino, nm->len, nm->name, ui->data_len, dir->i_ino); ubifs_assert(mutex_is_locked(&host_ui->ui_mutex)); dlen = UBIFS_DENT_NODE_SZ + fname_len(nm) + 1; @@ -574,7 +572,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, /* Make sure to also account for extended attributes */ len += host_ui->data_len; - dent = kmalloc(len, GFP_NOFS); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -585,7 +583,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, if (!xent) { dent->ch.node_type = UBIFS_DENT_NODE; - dent_key_init(c, &dent_key, dir->i_ino, nm); + if (nm->hash) + dent_key_init_hash(c, &dent_key, dir->i_ino, nm->hash); + else + dent_key_init(c, &dent_key, dir->i_ino, nm); } else { dent->ch.node_type = UBIFS_XENT_NODE; xent_key_init(c, &dent_key, dir->i_ino, nm); @@ -629,7 +630,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, kfree(dent); if (deletion) { - err = ubifs_tnc_remove_nm(c, &dent_key, nm); + if (nm->hash) + err = ubifs_tnc_remove_dh(c, &dent_key, nm->minor_hash); + else + err = ubifs_tnc_remove_nm(c, &dent_key, nm); if (err) goto out_ro; err = ubifs_add_dirt(c, lnum, dlen); @@ -950,9 +954,6 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, int twoparents = (fst_dir != snd_dir); void *p; - //dbg_jnl("dent '%pd' in dir ino %lu between dent '%pd' in dir ino %lu", - // fst_dentry, fst_dir->i_ino, snd_dentry, snd_dir->i_ino); - ubifs_assert(ubifs_inode(fst_dir)->data_len == 0); ubifs_assert(ubifs_inode(snd_dir)->data_len == 0); ubifs_assert(mutex_is_locked(&ubifs_inode(fst_dir)->ui_mutex)); @@ -967,7 +968,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, if (twoparents) len += plen; - dent1 = kmalloc(len, GFP_NOFS); + dent1 = kzalloc(len, GFP_NOFS); if (!dent1) return -ENOMEM; @@ -984,6 +985,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, dent1->nlen = cpu_to_le16(fname_len(snd_nm)); memcpy(dent1->name, fname_name(snd_nm), fname_len(snd_nm)); dent1->name[fname_len(snd_nm)] = '\0'; + set_dent_cookie(c, dent1); zero_dent_node_unused(dent1); ubifs_prep_grp_node(c, dent1, dlen1, 0); @@ -996,6 +998,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, dent2->nlen = cpu_to_le16(fname_len(fst_nm)); memcpy(dent2->name, fname_name(fst_nm), fname_len(fst_nm)); dent2->name[fname_len(fst_nm)] = '\0'; + set_dent_cookie(c, dent2); zero_dent_node_unused(dent2); ubifs_prep_grp_node(c, dent2, dlen2, 0); @@ -1094,8 +1097,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, int move = (old_dir != new_dir); struct ubifs_inode *uninitialized_var(new_ui); - //dbg_jnl("dent '%pd' in dir ino %lu to dent '%pd' in dir ino %lu", - // old_dentry, old_dir->i_ino, new_dentry, new_dir->i_ino); ubifs_assert(ubifs_inode(old_dir)->data_len == 0); ubifs_assert(ubifs_inode(new_dir)->data_len == 0); ubifs_assert(mutex_is_locked(&ubifs_inode(old_dir)->ui_mutex)); @@ -1117,7 +1118,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8); if (move) len += plen; - dent = kmalloc(len, GFP_NOFS); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -1298,7 +1299,9 @@ static int truncate_data_node(const struct ubifs_info *c, const struct inode *in goto out; } - if (compr_type != UBIFS_COMPR_NONE) { + if (compr_type == UBIFS_COMPR_NONE) { + out_len = *new_len; + } else { err = ubifs_decompress(c, &dn->data, dlen, buf, &out_len, compr_type); if (err) goto out; @@ -1485,9 +1488,6 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, int sync = IS_DIRSYNC(host); struct ubifs_inode *host_ui = ubifs_inode(host); - //dbg_jnl("host %lu, xattr ino %lu, name '%s', data len %d", - // host->i_ino, inode->i_ino, nm->name, - // ubifs_inode(inode)->data_len); ubifs_assert(inode->i_nlink == 0); ubifs_assert(mutex_is_locked(&host_ui->ui_mutex)); @@ -1500,7 +1500,7 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, hlen = host_ui->data_len + UBIFS_INO_NODE_SZ; len = aligned_xlen + UBIFS_INO_NODE_SZ + ALIGN(hlen, 8); - xent = kmalloc(len, GFP_NOFS); + xent = kzalloc(len, GFP_NOFS); if (!xent) return -ENOMEM; @@ -1607,7 +1607,7 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, aligned_len1 = ALIGN(len1, 8); aligned_len = aligned_len1 + ALIGN(len2, 8); - ino = kmalloc(aligned_len, GFP_NOFS); + ino = kzalloc(aligned_len, GFP_NOFS); if (!ino) return -ENOMEM; diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 7547be512db2..b1f7c0caa3ac 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -162,6 +162,7 @@ static inline void dent_key_init(const struct ubifs_info *c, uint32_t hash = c->key_hash(fname_name(nm), fname_len(nm)); ubifs_assert(!(hash & ~UBIFS_S_KEY_HASH_MASK)); + ubifs_assert(!nm->hash && !nm->minor_hash); key->u32[0] = inum; key->u32[1] = hash | (UBIFS_DENT_KEY << UBIFS_S_KEY_HASH_BITS); } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index cf4cc99b75b5..5496b17b959c 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -45,7 +45,7 @@ #define UBIFS_KMALLOC_OK (128*1024) /* Slab cache for UBIFS inodes */ -struct kmem_cache *ubifs_inode_slab; +static struct kmem_cache *ubifs_inode_slab; /* UBIFS TNC shrinker description */ static struct shrinker ubifs_shrinker_info = { @@ -446,6 +446,8 @@ static int ubifs_show_options(struct seq_file *s, struct dentry *root) ubifs_compr_name(c->mount_opts.compr_type)); } + seq_printf(s, ",ubi=%d,vol=%d", c->vi.ubi_num, c->vi.vol_id); + return 0; } @@ -931,6 +933,7 @@ enum { Opt_chk_data_crc, Opt_no_chk_data_crc, Opt_override_compr, + Opt_ignore, Opt_err, }; @@ -942,6 +945,8 @@ static const match_table_t tokens = { {Opt_chk_data_crc, "chk_data_crc"}, {Opt_no_chk_data_crc, "no_chk_data_crc"}, {Opt_override_compr, "compr=%s"}, + {Opt_ignore, "ubi=%s"}, + {Opt_ignore, "vol=%s"}, {Opt_err, NULL}, }; @@ -1042,6 +1047,8 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, c->default_compr = c->mount_opts.compr_type; break; } + case Opt_ignore: + break; default: { unsigned long flag; @@ -1152,7 +1159,7 @@ static int mount_ubifs(struct ubifs_info *c) long long x, y; size_t sz; - c->ro_mount = !!(c->vfs_sb->s_flags & MS_RDONLY); + c->ro_mount = !!sb_rdonly(c->vfs_sb); /* Suppress error messages while probing if MS_SILENT is set */ c->probing = !!(c->vfs_sb->s_flags & MS_SILENT); @@ -1869,8 +1876,10 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data) bu_init(c); else { dbg_gen("disable bulk-read"); + mutex_lock(&c->bu_mutex); kfree(c->bu.buf); c->bu.buf = NULL; + mutex_unlock(&c->bu_mutex); } ubifs_assert(c->lst.taken_empty_lebs > 0); diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 709aa098dd46..0a213dcba2a1 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1812,7 +1812,7 @@ static int do_lookup_nm(struct ubifs_info *c, const union ubifs_key *key, int found, n, err; struct ubifs_znode *znode; - //dbg_tnck(key, "name '%.*s' key ", nm->len, nm->name); + dbg_tnck(key, "key "); mutex_lock(&c->tnc_mutex); found = ubifs_lookup_level0(c, key, &znode, &n); if (!found) { @@ -1880,48 +1880,65 @@ int ubifs_tnc_lookup_nm(struct ubifs_info *c, const union ubifs_key *key, return do_lookup_nm(c, key, node, nm); } -static int do_lookup_dh(struct ubifs_info *c, const union ubifs_key *key, - struct ubifs_dent_node *dent, uint32_t cookie) +static int search_dh_cookie(struct ubifs_info *c, const union ubifs_key *key, + struct ubifs_dent_node *dent, uint32_t cookie, + struct ubifs_znode **zn, int *n) { - int n, err, type = key_type(c, key); - struct ubifs_znode *znode; + int err; + struct ubifs_znode *znode = *zn; struct ubifs_zbranch *zbr; - union ubifs_key *dkey, start_key; - - ubifs_assert(is_hash_key(c, key)); - - lowest_dent_key(c, &start_key, key_inum(c, key)); - - mutex_lock(&c->tnc_mutex); - err = ubifs_lookup_level0(c, &start_key, &znode, &n); - if (unlikely(err < 0)) - goto out_unlock; + union ubifs_key *dkey; for (;;) { if (!err) { - err = tnc_next(c, &znode, &n); + err = tnc_next(c, &znode, n); if (err) - goto out_unlock; + goto out; } - zbr = &znode->zbranch[n]; + zbr = &znode->zbranch[*n]; dkey = &zbr->key; if (key_inum(c, dkey) != key_inum(c, key) || - key_type(c, dkey) != type) { + key_type(c, dkey) != key_type(c, key)) { err = -ENOENT; - goto out_unlock; + goto out; } err = tnc_read_hashed_node(c, zbr, dent); if (err) - goto out_unlock; + goto out; if (key_hash(c, key) == key_hash(c, dkey) && - le32_to_cpu(dent->cookie) == cookie) - goto out_unlock; + le32_to_cpu(dent->cookie) == cookie) { + *zn = znode; + goto out; + } } +out: + + return err; +} + +static int do_lookup_dh(struct ubifs_info *c, const union ubifs_key *key, + struct ubifs_dent_node *dent, uint32_t cookie) +{ + int n, err; + struct ubifs_znode *znode; + union ubifs_key start_key; + + ubifs_assert(is_hash_key(c, key)); + + lowest_dent_key(c, &start_key, key_inum(c, key)); + + mutex_lock(&c->tnc_mutex); + err = ubifs_lookup_level0(c, &start_key, &znode, &n); + if (unlikely(err < 0)) + goto out_unlock; + + err = search_dh_cookie(c, key, dent, cookie, &znode, &n); + out_unlock: mutex_unlock(&c->tnc_mutex); return err; @@ -2393,8 +2410,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, struct ubifs_znode *znode; mutex_lock(&c->tnc_mutex); - //dbg_tnck(key, "LEB %d:%d, name '%.*s', key ", - // lnum, offs, nm->len, nm->name); + dbg_tnck(key, "LEB %d:%d, key ", lnum, offs); found = lookup_level0_dirty(c, key, &znode, &n); if (found < 0) { err = found; @@ -2628,7 +2644,7 @@ int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key, struct ubifs_znode *znode; mutex_lock(&c->tnc_mutex); - //dbg_tnck(key, "%.*s, key ", nm->len, nm->name); + dbg_tnck(key, "key "); err = lookup_level0_dirty(c, key, &znode, &n); if (err < 0) goto out_unlock; @@ -2663,6 +2679,74 @@ out_unlock: } /** + * ubifs_tnc_remove_dh - remove an index entry for a "double hashed" node. + * @c: UBIFS file-system description object + * @key: key of node + * @cookie: node cookie for collision resolution + * + * Returns %0 on success or negative error code on failure. + */ +int ubifs_tnc_remove_dh(struct ubifs_info *c, const union ubifs_key *key, + uint32_t cookie) +{ + int n, err; + struct ubifs_znode *znode; + struct ubifs_dent_node *dent; + struct ubifs_zbranch *zbr; + + if (!c->double_hash) + return -EOPNOTSUPP; + + mutex_lock(&c->tnc_mutex); + err = lookup_level0_dirty(c, key, &znode, &n); + if (err <= 0) + goto out_unlock; + + zbr = &znode->zbranch[n]; + dent = kmalloc(UBIFS_MAX_DENT_NODE_SZ, GFP_NOFS); + if (!dent) { + err = -ENOMEM; + goto out_unlock; + } + + err = tnc_read_hashed_node(c, zbr, dent); + if (err) + goto out_free; + + /* If the cookie does not match, we're facing a hash collision. */ + if (le32_to_cpu(dent->cookie) != cookie) { + union ubifs_key start_key; + + lowest_dent_key(c, &start_key, key_inum(c, key)); + + err = ubifs_lookup_level0(c, &start_key, &znode, &n); + if (unlikely(err < 0)) + goto out_free; + + err = search_dh_cookie(c, key, dent, cookie, &znode, &n); + if (err) + goto out_free; + } + + if (znode->cnext || !ubifs_zn_dirty(znode)) { + znode = dirty_cow_bottom_up(c, znode); + if (IS_ERR(znode)) { + err = PTR_ERR(znode); + goto out_free; + } + } + err = tnc_delete(c, znode, n); + +out_free: + kfree(dent); +out_unlock: + if (!err) + err = dbg_check_tnc(c, 0); + mutex_unlock(&c->tnc_mutex); + return err; +} + +/** * key_in_range - determine if a key falls within a range of keys. * @c: UBIFS file-system description object * @key: key to check @@ -2802,6 +2886,8 @@ int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum) dbg_tnc("xent '%s', ino %lu", xent->name, (unsigned long)xattr_inum); + ubifs_evict_xattr_inode(c, xattr_inum); + fname_name(&nm) = xent->name; fname_len(&nm) = le16_to_cpu(xent->nlen); err = ubifs_tnc_remove_nm(c, &key1, &nm); @@ -2863,7 +2949,7 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c, struct ubifs_zbranch *zbr; union ubifs_key *dkey; - //dbg_tnck(key, "%s ", nm->name ? (char *)nm->name : "(lowest)"); + dbg_tnck(key, "key "); ubifs_assert(is_hash_key(c, key)); mutex_lock(&c->tnc_mutex); diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index 51157da3f76e..aa31f60220ef 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -57,6 +57,8 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, ubifs_dump_znode(c, znode); if (zbr->znode) ubifs_dump_znode(c, zbr->znode); + + return -EINVAL; } } ubifs_prepare_node(c, idx, len, 0); @@ -859,6 +861,8 @@ static int write_index(struct ubifs_info *c) ubifs_dump_znode(c, znode); if (zbr->znode) ubifs_dump_znode(c, zbr->znode); + + return -EINVAL; } } len = ubifs_idx_node_sz(c, znode->child_cnt); diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 298b4d89eee9..cd43651f1731 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1451,7 +1451,6 @@ struct ubifs_info { extern struct list_head ubifs_infos; extern spinlock_t ubifs_infos_lock; extern atomic_long_t ubifs_clean_zn_cnt; -extern struct kmem_cache *ubifs_inode_slab; extern const struct super_operations ubifs_super_operations; extern const struct address_space_operations ubifs_file_address_operations; extern const struct file_operations ubifs_file_operations; @@ -1590,6 +1589,8 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, int ubifs_tnc_remove(struct ubifs_info *c, const union ubifs_key *key); int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key, const struct fscrypt_name *nm); +int ubifs_tnc_remove_dh(struct ubifs_info *c, const union ubifs_key *key, + uint32_t cookie); int ubifs_tnc_remove_range(struct ubifs_info *c, union ubifs_key *from_key, union ubifs_key *to_key); int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum); @@ -1754,9 +1755,10 @@ int ubifs_check_dir_empty(struct inode *dir); extern const struct xattr_handler *ubifs_xattr_handlers[]; ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size); int ubifs_xattr_set(struct inode *host, const char *name, const void *value, - size_t size, int flags); + size_t size, int flags, bool check_lock); ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, size_t size); +void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum); #ifdef CONFIG_UBIFS_FS_SECURITY extern int ubifs_init_security(struct inode *dentry, struct inode *inode, diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 6c9e62c2ef55..c13eae819cbc 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -280,7 +280,7 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum) } int ubifs_xattr_set(struct inode *host, const char *name, const void *value, - size_t size, int flags) + size_t size, int flags, bool check_lock) { struct inode *inode; struct ubifs_info *c = host->i_sb->s_fs_info; @@ -289,12 +289,7 @@ int ubifs_xattr_set(struct inode *host, const char *name, const void *value, union ubifs_key key; int err; - /* - * Creating an encryption context is done unlocked since we - * operate on a new inode which is not visible to other users - * at this point. - */ - if (strcmp(name, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT) != 0) + if (check_lock) ubifs_assert(inode_is_locked(host)); if (size > UBIFS_MAX_INO_DATA) @@ -513,6 +508,28 @@ out_cancel: return err; } +/** + * ubifs_evict_xattr_inode - Evict an xattr inode. + * @c: UBIFS file-system description object + * @xattr_inum: xattr inode number + * + * When an inode that hosts xattrs is being removed we have to make sure + * that cached inodes of the xattrs also get removed from the inode cache + * otherwise we'd waste memory. This function looks up an inode from the + * inode cache and clears the link counter such that iput() will evict + * the inode. + */ +void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum) +{ + struct inode *inode; + + inode = ilookup(c->vfs_sb, xattr_inum); + if (inode) { + clear_nlink(inode); + iput(inode); + } +} + static int ubifs_xattr_remove(struct inode *host, const char *name) { struct inode *inode; @@ -576,8 +593,12 @@ static int init_xattrs(struct inode *inode, const struct xattr *xattr_array, } strcpy(name, XATTR_SECURITY_PREFIX); strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name); + /* + * creating a new inode without holding the inode rwsem, + * no need to check whether inode is locked. + */ err = ubifs_xattr_set(inode, name, xattr->value, - xattr->value_len, 0); + xattr->value_len, 0, false); kfree(name); if (err < 0) break; @@ -624,7 +645,7 @@ static int xattr_set(const struct xattr_handler *handler, name = xattr_full_name(handler, name); if (value) - return ubifs_xattr_set(inode, name, value, size, flags); + return ubifs_xattr_set(inode, name, value, size, flags, true); else return ubifs_xattr_remove(inode, name); } diff --git a/fs/udf/file.c b/fs/udf/file.c index f5eb2d5b3bac..356c2bf148a5 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -43,10 +43,15 @@ static void __udf_adinicb_readpage(struct page *page) struct inode *inode = page->mapping->host; char *kaddr; struct udf_inode_info *iinfo = UDF_I(inode); + loff_t isize = i_size_read(inode); + /* + * We have to be careful here as truncate can change i_size under us. + * So just sample it once and use the same value everywhere. + */ kaddr = kmap_atomic(page); - memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, inode->i_size); - memset(kaddr + inode->i_size, 0, PAGE_SIZE - inode->i_size); + memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, isize); + memset(kaddr + isize, 0, PAGE_SIZE - isize); flush_dcache_page(page); SetPageUptodate(page); kunmap_atomic(kaddr); @@ -71,7 +76,8 @@ static int udf_adinicb_writepage(struct page *page, BUG_ON(!PageLocked(page)); kaddr = kmap_atomic(page); - memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, inode->i_size); + memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, + i_size_read(inode)); SetPageUptodate(page); kunmap_atomic(kaddr); mark_inode_dirty(inode); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 98c510e17203..8dacf4f57414 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -114,7 +114,7 @@ static void udf_update_extent_cache(struct inode *inode, loff_t estart, __udf_clear_extent_cache(inode); if (pos->bh) get_bh(pos->bh); - memcpy(&iinfo->cached_extent.epos, pos, sizeof(struct extent_position)); + memcpy(&iinfo->cached_extent.epos, pos, sizeof(*pos)); iinfo->cached_extent.lstart = estart; switch (iinfo->i_alloc_type) { case ICBTAG_FLAG_AD_SHORT: @@ -1222,8 +1222,8 @@ int udf_setsize(struct inode *inode, loff_t newsize) return err; } set_size: - truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); + truncate_setsize(inode, newsize); } else { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); @@ -1240,9 +1240,9 @@ set_size: udf_get_block); if (err) return err; + truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - truncate_setsize(inode, newsize); udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); } @@ -1572,13 +1572,8 @@ static int udf_alloc_i_data(struct inode *inode, size_t size) { struct udf_inode_info *iinfo = UDF_I(inode); iinfo->i_ext.i_data = kmalloc(size, GFP_KERNEL); - - if (!iinfo->i_ext.i_data) { - udf_err(inode->i_sb, "(ino %ld) no free memory\n", - inode->i_ino); + if (!iinfo->i_ext.i_data) return -ENOMEM; - } - return 0; } @@ -1703,7 +1698,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) dsea->impUseLength = cpu_to_le32(sizeof(struct regid)); } eid = (struct regid *)dsea->impUse; - memset(eid, 0, sizeof(struct regid)); + memset(eid, 0, sizeof(*eid)); strcpy(eid->ident, UDF_ID_DEVELOPER); eid->identSuffix[0] = UDF_OS_CLASS_UNIX; eid->identSuffix[1] = UDF_OS_ID_LINUX; @@ -1754,7 +1749,7 @@ static int udf_update_inode(struct inode *inode, int do_sync) udf_time_to_disk_stamp(&efe->createTime, iinfo->i_crtime); udf_time_to_disk_stamp(&efe->attrTime, inode->i_ctime); - memset(&(efe->impIdent), 0, sizeof(struct regid)); + memset(&(efe->impIdent), 0, sizeof(efe->impIdent)); strcpy(efe->impIdent.ident, UDF_ID_DEVELOPER); efe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; efe->impIdent.identSuffix[1] = UDF_OS_ID_LINUX; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 385ee89d5824..885198dfd9f8 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1184,7 +1184,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry, */ ncfi.fileVersionNum = ocfi.fileVersionNum; ncfi.fileCharacteristics = ocfi.fileCharacteristics; - memcpy(&(ncfi.icb), &(ocfi.icb), sizeof(struct long_ad)); + memcpy(&(ncfi.icb), &(ocfi.icb), sizeof(ocfi.icb)); udf_write_fi(new_dir, &ncfi, nfi, &nfibh, NULL, NULL); /* The old fid may have moved - find it again */ diff --git a/fs/udf/super.c b/fs/udf/super.c index 14b4bc1f6801..99cb81d0077f 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -73,8 +73,6 @@ #define VDS_POS_TERMINATING_DESC 6 #define VDS_POS_LENGTH 7 -#define UDF_DEFAULT_BLOCKSIZE 2048 - #define VSD_FIRST_SECTOR_OFFSET 32768 #define VSD_MAX_SECTOR_OFFSET 0x800000 @@ -268,11 +266,8 @@ static int udf_sb_alloc_partition_maps(struct super_block *sb, u32 count) { struct udf_sb_info *sbi = UDF_SB(sb); - sbi->s_partmaps = kcalloc(count, sizeof(struct udf_part_map), - GFP_KERNEL); + sbi->s_partmaps = kcalloc(count, sizeof(*sbi->s_partmaps), GFP_KERNEL); if (!sbi->s_partmaps) { - udf_err(sb, "Unable to allocate space for %d partition maps\n", - count); sbi->s_partitions = 0; return -ENOMEM; } @@ -326,7 +321,8 @@ static void udf_sb_free_partitions(struct super_block *sb) { struct udf_sb_info *sbi = UDF_SB(sb); int i; - if (sbi->s_partmaps == NULL) + + if (!sbi->s_partmaps) return; for (i = 0; i < sbi->s_partitions; i++) udf_free_partition(&sbi->s_partmaps[i]); @@ -677,7 +673,7 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options) sbi->s_dmode = uopt.dmode; write_unlock(&sbi->s_cred_lock); - if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) + if ((bool)(*flags & MS_RDONLY) == sb_rdonly(sb)) goto out_unlock; if (*flags & MS_RDONLY) @@ -1021,7 +1017,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition, fe = udf_iget_special(sb, &addr); if (IS_ERR(fe)) { - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) udf_warn(sb, "bitmap inode efe not found but it's ok since the disc is mounted read-only\n"); else { udf_err(sb, "bitmap inode efe not found and attempted read-write mount\n"); @@ -1073,7 +1069,7 @@ static struct udf_bitmap *udf_sb_alloc_bitmap(struct super_block *sb, u32 index) else bitmap = vzalloc(size); /* TODO: get rid of vzalloc */ - if (bitmap == NULL) + if (!bitmap) return NULL; bitmap->s_nr_groups = nr_groups; @@ -1345,7 +1341,7 @@ static int udf_load_partdesc(struct super_block *sb, sector_t block) * writing to it (we overwrite blocks instead of relocating * them). */ - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { ret = -EACCES; goto out_bh; } @@ -2101,7 +2097,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) uopt.fmode = UDF_INVALID_MODE; uopt.dmode = UDF_INVALID_MODE; - sbi = kzalloc(sizeof(struct udf_sb_info), GFP_KERNEL); + sbi = kzalloc(sizeof(*sbi), GFP_KERNEL); if (!sbi) return -ENOMEM; @@ -2209,7 +2205,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) ret = -EINVAL; goto error_out; } else if (minUDFWriteRev > UDF_MAX_WRITE_VERSION && - !(sb->s_flags & MS_RDONLY)) { + !sb_rdonly(sb)) { ret = -EACCES; goto error_out; } @@ -2230,7 +2226,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (sbi->s_partmaps[sbi->s_partition].s_partition_flags & UDF_PART_FLAG_READ_ONLY && - !(sb->s_flags & MS_RDONLY)) { + !sb_rdonly(sb)) { ret = -EACCES; goto error_out; } @@ -2249,7 +2245,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) le16_to_cpu(ts.year), ts.month, ts.day, ts.hour, ts.minute, le16_to_cpu(ts.typeAndTimezone)); } - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { udf_open_lvid(sb); lvid_open = true; } @@ -2336,7 +2332,7 @@ static void udf_put_super(struct super_block *sb) if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) unload_nls(sbi->s_nls_map); #endif - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) udf_close_lvid(sb); brelse(sbi->s_lvid_bh); udf_sb_free_partitions(sb); diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c index 77c331f1a770..14626b34d13e 100644 --- a/fs/udf/udftime.c +++ b/fs/udf/udftime.c @@ -38,56 +38,11 @@ #include <linux/types.h> #include <linux/kernel.h> - -#define EPOCH_YEAR 1970 - -#ifndef __isleap -/* Nonzero if YEAR is a leap year (every 4 years, - except every 100th isn't, and every 400th is). */ -#define __isleap(year) \ - ((year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0)) -#endif - -/* How many days come before each month (0-12). */ -static const unsigned short int __mon_yday[2][13] = { - /* Normal years. */ - {0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365}, - /* Leap years. */ - {0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366} -}; - -#define MAX_YEAR_SECONDS 69 -#define SPD 0x15180 /*3600*24 */ -#define SPY(y, l, s) (SPD * (365 * y + l) + s) - -static time_t year_seconds[MAX_YEAR_SECONDS] = { -/*1970*/ SPY(0, 0, 0), SPY(1, 0, 0), SPY(2, 0, 0), SPY(3, 1, 0), -/*1974*/ SPY(4, 1, 0), SPY(5, 1, 0), SPY(6, 1, 0), SPY(7, 2, 0), -/*1978*/ SPY(8, 2, 0), SPY(9, 2, 0), SPY(10, 2, 0), SPY(11, 3, 0), -/*1982*/ SPY(12, 3, 0), SPY(13, 3, 0), SPY(14, 3, 0), SPY(15, 4, 0), -/*1986*/ SPY(16, 4, 0), SPY(17, 4, 0), SPY(18, 4, 0), SPY(19, 5, 0), -/*1990*/ SPY(20, 5, 0), SPY(21, 5, 0), SPY(22, 5, 0), SPY(23, 6, 0), -/*1994*/ SPY(24, 6, 0), SPY(25, 6, 0), SPY(26, 6, 0), SPY(27, 7, 0), -/*1998*/ SPY(28, 7, 0), SPY(29, 7, 0), SPY(30, 7, 0), SPY(31, 8, 0), -/*2002*/ SPY(32, 8, 0), SPY(33, 8, 0), SPY(34, 8, 0), SPY(35, 9, 0), -/*2006*/ SPY(36, 9, 0), SPY(37, 9, 0), SPY(38, 9, 0), SPY(39, 10, 0), -/*2010*/ SPY(40, 10, 0), SPY(41, 10, 0), SPY(42, 10, 0), SPY(43, 11, 0), -/*2014*/ SPY(44, 11, 0), SPY(45, 11, 0), SPY(46, 11, 0), SPY(47, 12, 0), -/*2018*/ SPY(48, 12, 0), SPY(49, 12, 0), SPY(50, 12, 0), SPY(51, 13, 0), -/*2022*/ SPY(52, 13, 0), SPY(53, 13, 0), SPY(54, 13, 0), SPY(55, 14, 0), -/*2026*/ SPY(56, 14, 0), SPY(57, 14, 0), SPY(58, 14, 0), SPY(59, 15, 0), -/*2030*/ SPY(60, 15, 0), SPY(61, 15, 0), SPY(62, 15, 0), SPY(63, 16, 0), -/*2034*/ SPY(64, 16, 0), SPY(65, 16, 0), SPY(66, 16, 0), SPY(67, 17, 0), -/*2038*/ SPY(68, 17, 0) -}; - -#define SECS_PER_HOUR (60 * 60) -#define SECS_PER_DAY (SECS_PER_HOUR * 24) +#include <linux/time.h> struct timespec * udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) { - int yday; u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone); u16 year = le16_to_cpu(src.year); uint8_t type = typeAndTimezone >> 12; @@ -102,15 +57,9 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) } else offset = 0; - if ((year < EPOCH_YEAR) || - (year >= EPOCH_YEAR + MAX_YEAR_SECONDS)) { - return NULL; - } - dest->tv_sec = year_seconds[year - EPOCH_YEAR]; + dest->tv_sec = mktime64(year, src.month, src.day, src.hour, src.minute, + src.second); dest->tv_sec -= offset * 60; - - yday = ((__mon_yday[__isleap(year)][src.month - 1]) + src.day - 1); - dest->tv_sec += (((yday * 24) + src.hour) * 60 + src.minute) * 60 + src.second; dest->tv_nsec = 1000 * (src.centiseconds * 10000 + src.hundredsOfMicroseconds * 100 + src.microseconds); return dest; @@ -119,9 +68,9 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src) struct timestamp * udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts) { - long int days, rem, y; - const unsigned short int *ip; + long seconds; int16_t offset; + struct tm tm; offset = -sys_tz.tz_minuteswest; @@ -130,35 +79,14 @@ udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts) dest->typeAndTimezone = cpu_to_le16(0x1000 | (offset & 0x0FFF)); - ts.tv_sec += offset * 60; - days = ts.tv_sec / SECS_PER_DAY; - rem = ts.tv_sec % SECS_PER_DAY; - dest->hour = rem / SECS_PER_HOUR; - rem %= SECS_PER_HOUR; - dest->minute = rem / 60; - dest->second = rem % 60; - y = 1970; - -#define DIV(a, b) ((a) / (b) - ((a) % (b) < 0)) -#define LEAPS_THRU_END_OF(y) (DIV (y, 4) - DIV (y, 100) + DIV (y, 400)) - - while (days < 0 || days >= (__isleap(y) ? 366 : 365)) { - long int yg = y + days / 365 - (days % 365 < 0); - - /* Adjust DAYS and Y to match the guessed year. */ - days -= ((yg - y) * 365 - + LEAPS_THRU_END_OF(yg - 1) - - LEAPS_THRU_END_OF(y - 1)); - y = yg; - } - dest->year = cpu_to_le16(y); - ip = __mon_yday[__isleap(y)]; - for (y = 11; days < (long int)ip[y]; --y) - continue; - days -= ip[y]; - dest->month = y + 1; - dest->day = days + 1; - + seconds = ts.tv_sec + offset * 60; + time64_to_tm(seconds, 0, &tm); + dest->year = cpu_to_le16(tm.tm_year + 1900); + dest->month = tm.tm_mon + 1; + dest->day = tm.tm_mday; + dest->hour = tm.tm_hour; + dest->minute = tm.tm_min; + dest->second = tm.tm_sec; dest->centiseconds = ts.tv_nsec / 10000000; dest->hundredsOfMicroseconds = (ts.tv_nsec / 1000 - dest->centiseconds * 10000) / 100; diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index de01b8f2aa78..48609f1d9580 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -53,7 +53,7 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) mark_inode_dirty(dir); } if (IS_DIRSYNC(dir)) - err = write_one_page(page, 1); + err = write_one_page(page); else unlock_page(page); return err; diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 0a4f58a5073c..6440003f8ddc 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -278,7 +278,7 @@ void ufs_error (struct super_block * sb, const char * function, uspi = UFS_SB(sb)->s_uspi; usb1 = ubh_get_usb_first(uspi); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); ufs_mark_sb_dirty(sb); @@ -312,7 +312,7 @@ void ufs_panic (struct super_block * sb, const char * function, uspi = UFS_SB(sb)->s_uspi; usb1 = ubh_get_usb_first(uspi); - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { usb1->fs_clean = UFS_FSBAD; ubh_mark_buffer_dirty(USPI_UBH(uspi)); ufs_mark_sb_dirty(sb); @@ -742,7 +742,7 @@ static void ufs_put_super(struct super_block *sb) UFSD("ENTER\n"); - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) ufs_put_super_internal(sb); cancel_delayed_work_sync(&sbi->sync_work); @@ -793,7 +793,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) UFSD("ENTER\n"); #ifndef CONFIG_UFS_FS_WRITE - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n"); return -EROFS; } @@ -805,7 +805,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = sbi; sbi->sb = sb; - UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY)); + UFSD("flag %u\n", (int)(sb_rdonly(sb))); mutex_init(&sbi->s_lock); spin_lock_init(&sbi->work_lock); @@ -902,7 +902,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) uspi->s_sbsize = super_block_size = 2048; uspi->s_sbbase = 0; flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=old is supported read-only\n"); sb->s_flags |= MS_RDONLY; @@ -918,7 +918,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) uspi->s_sbbase = 0; uspi->s_dirblksize = 1024; flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=nextstep is supported read-only\n"); sb->s_flags |= MS_RDONLY; @@ -934,7 +934,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) uspi->s_sbbase = 0; uspi->s_dirblksize = 1024; flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=nextstep-cd is supported read-only\n"); sb->s_flags |= MS_RDONLY; @@ -950,7 +950,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) uspi->s_sbbase = 0; uspi->s_dirblksize = 1024; flags |= UFS_DE_44BSD | UFS_UID_44BSD | UFS_ST_44BSD | UFS_CG_44BSD; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=openstep is supported read-only\n"); sb->s_flags |= MS_RDONLY; @@ -965,7 +965,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) uspi->s_sbsize = super_block_size = 2048; uspi->s_sbbase = 0; flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD; - if (!(sb->s_flags & MS_RDONLY)) { + if (!sb_rdonly(sb)) { if (!silent) pr_info("ufstype=hp is supported read-only\n"); sb->s_flags |= MS_RDONLY; @@ -1273,7 +1273,7 @@ magic_found: /* * Read cylinder group structures */ - if (!(sb->s_flags & MS_RDONLY)) + if (!sb_rdonly(sb)) if (!ufs_read_cylinder_structures(sb)) goto failed; @@ -1328,7 +1328,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) return -EINVAL; } - if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) { + if ((bool)(*mount_flags & MS_RDONLY) == sb_rdonly(sb)) { UFS_SB(sb)->s_mount_opt = new_mount_opt; mutex_unlock(&UFS_SB(sb)->s_lock); return 0; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 1d622f276e3a..1c713fd5b3e6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -81,7 +81,7 @@ struct userfaultfd_unmap_ctx { struct userfaultfd_wait_queue { struct uffd_msg msg; - wait_queue_t wq; + wait_queue_entry_t wq; struct userfaultfd_ctx *ctx; bool waken; }; @@ -91,7 +91,7 @@ struct userfaultfd_wake_range { unsigned long len; }; -static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode, +static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { struct userfaultfd_wake_range *range = key; @@ -109,27 +109,24 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode, goto out; WRITE_ONCE(uwq->waken, true); /* - * The implicit smp_mb__before_spinlock in try_to_wake_up() - * renders uwq->waken visible to other CPUs before the task is - * waken. + * The Program-Order guarantees provided by the scheduler + * ensure uwq->waken is visible before the task is woken. */ ret = wake_up_state(wq->private, mode); - if (ret) + if (ret) { /* * Wake only once, autoremove behavior. * - * After the effect of list_del_init is visible to the - * other CPUs, the waitqueue may disappear from under - * us, see the !list_empty_careful() in - * handle_userfault(). try_to_wake_up() has an - * implicit smp_mb__before_spinlock, and the - * wq->private is read before calling the extern - * function "wake_up_state" (which in turns calls - * try_to_wake_up). While the spin_lock;spin_unlock; - * wouldn't be enough, the smp_mb__before_spinlock is - * enough to avoid an explicit smp_mb() here. + * After the effect of list_del_init is visible to the other + * CPUs, the waitqueue may disappear from under us, see the + * !list_empty_careful() in handle_userfault(). + * + * try_to_wake_up() has an implicit smp_mb(), and the + * wq->private is read before calling the extern function + * "wake_up_state" (which in turns calls try_to_wake_up). */ - list_del_init(&wq->task_list); + list_del_init(&wq->entry); + } out: return ret; } @@ -181,7 +178,8 @@ static inline void msg_init(struct uffd_msg *msg) static inline struct uffd_msg userfault_msg(unsigned long address, unsigned int flags, - unsigned long reason) + unsigned long reason, + unsigned int features) { struct uffd_msg msg; msg_init(&msg); @@ -205,6 +203,8 @@ static inline struct uffd_msg userfault_msg(unsigned long address, * write protect fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; + if (features & UFFD_FEATURE_THREAD_ID) + msg.arg.pagefault.feat.ptid = task_pid_vnr(current); return msg; } @@ -214,6 +214,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address, * hugepmd ranges. */ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) @@ -224,7 +225,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); - pte = huge_pte_offset(mm, address); + pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); if (!pte) goto out; @@ -243,6 +244,7 @@ out: } #else static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, + struct vm_area_struct *vma, unsigned long address, unsigned long flags, unsigned long reason) @@ -371,13 +373,34 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); + if (ctx->features & UFFD_FEATURE_SIGBUS) + goto out; + /* * If it's already released don't get it. This avoids to loop * in __get_user_pages if userfaultfd_release waits on the * caller of handle_userfault to release the mmap_sem. */ - if (unlikely(ACCESS_ONCE(ctx->released))) + if (unlikely(ACCESS_ONCE(ctx->released))) { + /* + * Don't return VM_FAULT_SIGBUS in this case, so a non + * cooperative manager can close the uffd after the + * last UFFDIO_COPY, without risking to trigger an + * involuntary SIGBUS if the process was starting the + * userfaultfd while the userfaultfd was still armed + * (but after the last UFFDIO_COPY). If the uffd + * wasn't already closed when the userfault reached + * this point, that would normally be solved by + * userfaultfd_must_wait returning 'false'. + * + * If we were to return VM_FAULT_SIGBUS here, the non + * cooperative manager would be instead forced to + * always call UFFDIO_UNREGISTER before it can safely + * close the uffd. + */ + ret = VM_FAULT_NOPAGE; goto out; + } /* * Check that we can return VM_FAULT_RETRY. @@ -420,7 +443,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; - uwq.msg = userfault_msg(vmf->address, vmf->flags, reason); + uwq.msg = userfault_msg(vmf->address, vmf->flags, reason, + ctx->features); uwq.ctx = ctx; uwq.waken = false; @@ -448,7 +472,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, reason); else - must_wait = userfaultfd_huge_must_wait(ctx, vmf->address, + must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, + vmf->address, vmf->flags, reason); up_read(&mm->mmap_sem); @@ -522,13 +547,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason) * and it's fine not to block on the spinlock. The uwq on this * kernel stack can be released after the list_del_init. */ - if (!list_empty_careful(&uwq.wq.task_list)) { + if (!list_empty_careful(&uwq.wq.entry)) { spin_lock(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ - list_del(&uwq.wq.task_list); + list_del(&uwq.wq.entry); spin_unlock(&ctx->fault_pending_wqh.lock); } @@ -563,6 +588,12 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; if (ACCESS_ONCE(ctx->released) || fatal_signal_pending(current)) { + /* + * &ewq->wq may be queued in fork_event, but + * __remove_wait_queue ignores the head + * parameter. It would be a problem if it + * didn't. + */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; @@ -851,6 +882,9 @@ wakeup: __wake_up_locked_key(&ctx->fault_wqh, TASK_NORMAL, &range); spin_unlock(&ctx->fault_pending_wqh.lock); + /* Flush pending events that may still wait on event_wqh */ + wake_up_all(&ctx->event_wqh); + wake_up_poll(&ctx->fd_wqh, POLLHUP); userfaultfd_ctx_put(ctx); return 0; @@ -860,7 +894,7 @@ wakeup: static inline struct userfaultfd_wait_queue *find_userfault_in( wait_queue_head_t *wqh) { - wait_queue_t *wq; + wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; VM_BUG_ON(!spin_is_locked(&wqh->lock)); @@ -869,7 +903,7 @@ static inline struct userfaultfd_wait_queue *find_userfault_in( if (!waitqueue_active(wqh)) goto out; /* walk in reverse to provide FIFO behavior to read userfaults */ - wq = list_last_entry(&wqh->task_list, typeof(*wq), task_list); + wq = list_last_entry(&wqh->head, typeof(*wq), entry); uwq = container_of(wq, struct userfaultfd_wait_queue, wq); out: return uwq; @@ -1003,14 +1037,14 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, * changes __remove_wait_queue() to use * list_del_init() in turn breaking the * !list_empty_careful() check in - * handle_userfault(). The uwq->wq.task_list + * handle_userfault(). The uwq->wq.head list * must never be empty at any time during the * refile, or the waitqueue could disappear * from under us. The "wait_queue_head_t" * parameter of __remove_wait_queue() is unused * anyway. */ - list_del(&uwq->wq.task_list); + list_del(&uwq->wq.entry); __add_wait_queue(&ctx->fault_wqh, &uwq->wq); write_seqcount_end(&ctx->refile_seq); @@ -1032,7 +1066,13 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, fork_nctx = (struct userfaultfd_ctx *) (unsigned long) uwq->msg.arg.reserved.reserved1; - list_move(&uwq->wq.task_list, &fork_event); + list_move(&uwq->wq.entry, &fork_event); + /* + * fork_nctx can be freed as soon as + * we drop the lock, unless we take a + * reference on it. + */ + userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; @@ -1063,19 +1103,53 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(ctx, fork_nctx, msg); + spin_lock(&ctx->event_wqh.lock); + if (!list_empty(&fork_event)) { + /* + * The fork thread didn't abort, so we can + * drop the temporary refcount. + */ + userfaultfd_ctx_put(fork_nctx); - if (!ret) { - spin_lock(&ctx->event_wqh.lock); - if (!list_empty(&fork_event)) { - uwq = list_first_entry(&fork_event, - typeof(*uwq), - wq.task_list); - list_del(&uwq->wq.task_list); - __add_wait_queue(&ctx->event_wqh, &uwq->wq); + uwq = list_first_entry(&fork_event, + typeof(*uwq), + wq.entry); + /* + * If fork_event list wasn't empty and in turn + * the event wasn't already released by fork + * (the event is allocated on fork kernel + * stack), put the event back to its place in + * the event_wq. fork_event head will be freed + * as soon as we return so the event cannot + * stay queued there no matter the current + * "ret" value. + */ + list_del(&uwq->wq.entry); + __add_wait_queue(&ctx->event_wqh, &uwq->wq); + + /* + * Leave the event in the waitqueue and report + * error to userland if we failed to resolve + * the userfault fork. + */ + if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); - } - spin_unlock(&ctx->event_wqh.lock); + } else { + /* + * Here the fork thread aborted and the + * refcount from the fork thread on fork_nctx + * has already been released. We still hold + * the reference we took before releasing the + * lock above. If resolve_userfault_fork + * failed we've to drop it because the + * fork_nctx has to be freed in such case. If + * it succeeded we'll hold it because the new + * uffd references it. + */ + if (ret) + userfaultfd_ctx_put(fork_nctx); } + spin_unlock(&ctx->event_wqh.lock); } return ret; @@ -1114,11 +1188,6 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf, static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { - unsigned long start, end; - - start = range->start; - end = range->start + range->len; - spin_lock(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) @@ -1196,7 +1265,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, struct uffdio_register __user *user_uffdio_register; unsigned long vm_flags, new_flags; bool found; - bool non_anon_pages; + bool basic_ioctls; unsigned long start, end, vma_end; user_uffdio_register = (struct uffdio_register __user *) arg; @@ -1262,7 +1331,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, * Search for not compatible vmas. */ found = false; - non_anon_pages = false; + basic_ioctls = false; for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) { cond_resched(); @@ -1301,8 +1370,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, /* * Note vmas containing huge pages */ - if (is_vm_hugetlb_page(cur) || vma_is_shmem(cur)) - non_anon_pages = true; + if (is_vm_hugetlb_page(cur)) + basic_ioctls = true; found = true; } @@ -1373,7 +1442,7 @@ out_unlock: * userland which ioctls methods are guaranteed to * succeed on this range. */ - if (put_user(non_anon_pages ? UFFD_API_RANGE_IOCTLS_BASIC : + if (put_user(basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC : UFFD_API_RANGE_IOCTLS, &user_uffdio_register->ioctls)) ret = -EFAULT; @@ -1599,7 +1668,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, uffdio_copy.len); mmput(ctx->mm); } else { - return -ENOSPC; + return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_copy->copy))) return -EFAULT; @@ -1645,6 +1714,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, uffdio_zeropage.range.len); mmput(ctx->mm); + } else { + return -ESRCH; } if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) return -EFAULT; @@ -1747,17 +1818,17 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd, static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) { struct userfaultfd_ctx *ctx = f->private_data; - wait_queue_t *wq; + wait_queue_entry_t *wq; struct userfaultfd_wait_queue *uwq; unsigned long pending = 0, total = 0; spin_lock(&ctx->fault_pending_wqh.lock); - list_for_each_entry(wq, &ctx->fault_pending_wqh.task_list, task_list) { + list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { uwq = container_of(wq, struct userfaultfd_wait_queue, wq); pending++; total++; } - list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) { + list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { uwq = container_of(wq, struct userfaultfd_wait_queue, wq); total++; } diff --git a/fs/utimes.c b/fs/utimes.c index 6571d8c848a0..51edb9f9507c 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -22,7 +22,7 @@ */ SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) { - struct timespec tv[2]; + struct timespec64 tv[2]; if (times) { if (get_user(tv[0].tv_sec, ×->actime) || @@ -44,7 +44,7 @@ static bool nsec_valid(long nsec) return nsec >= 0 && nsec <= 999999999; } -static int utimes_common(const struct path *path, struct timespec *times) +static int utimes_common(const struct path *path, struct timespec64 *times) { int error; struct iattr newattrs; @@ -115,7 +115,7 @@ out: * must be owner or have write permission. * Else, update from *times, must be owner or super user. */ -long do_utimes(int dfd, const char __user *filename, struct timespec *times, +long do_utimes(int dfd, const char __user *filename, struct timespec64 *times, int flags) { int error = -EINVAL; @@ -167,10 +167,11 @@ out: SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename, struct timespec __user *, utimes, int, flags) { - struct timespec tstimes[2]; + struct timespec64 tstimes[2]; if (utimes) { - if (copy_from_user(&tstimes, utimes, sizeof(tstimes))) + if ((get_timespec64(&tstimes[0], &utimes[0]) || + get_timespec64(&tstimes[1], &utimes[1]))) return -EFAULT; /* Nothing to do, we must not even check the path. */ @@ -186,7 +187,7 @@ SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename, struct timeval __user *, utimes) { struct timeval times[2]; - struct timespec tstimes[2]; + struct timespec64 tstimes[2]; if (utimes) { if (copy_from_user(×, utimes, sizeof(times))) @@ -224,7 +225,7 @@ SYSCALL_DEFINE2(utimes, char __user *, filename, COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, struct compat_utimbuf __user *, t) { - struct timespec tv[2]; + struct timespec64 tv[2]; if (t) { if (get_user(tv[0].tv_sec, &t->actime) || @@ -238,11 +239,11 @@ COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename, COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags) { - struct timespec tv[2]; + struct timespec64 tv[2]; if (t) { - if (compat_get_timespec(&tv[0], &t[0]) || - compat_get_timespec(&tv[1], &t[1])) + if (compat_get_timespec64(&tv[0], &t[0]) || + compat_get_timespec64(&tv[1], &t[1])) return -EFAULT; if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) @@ -253,7 +254,7 @@ COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filena COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t) { - struct timespec tv[2]; + struct timespec64 tv[2]; if (t) { if (get_user(tv[0].tv_sec, &t[0].tv_sec) || diff --git a/fs/xattr.c b/fs/xattr.c index 464c94bf65f9..61cd28ba25f3 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -23,6 +23,7 @@ #include <linux/posix_acl_xattr.h> #include <linux/uaccess.h> +#include "internal.h" static const char * strcmp_prefix(const char *a, const char *a_prefix) @@ -249,7 +250,7 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value, } memcpy(value, buffer, len); out: - security_release_secctx(buffer, len); + kfree(buffer); out_noalloc: return len; } @@ -441,6 +442,12 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); + else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { + error = cap_convert_nscap(d, &kvalue, size); + if (error < 0) + goto out; + size = error; + } } error = vfs_setxattr(d, kname, kvalue, size, flags); @@ -496,10 +503,10 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, if (!f.file) return error; audit_file(f.file); - error = mnt_want_write_file(f.file); + error = mnt_want_write_file_path(f.file); if (!error) { error = setxattr(f.file->f_path.dentry, name, value, size, flags); - mnt_drop_write_file(f.file); + mnt_drop_write_file_path(f.file); } fdput(f); return error; @@ -728,10 +735,10 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) if (!f.file) return error; audit_file(f.file); - error = mnt_want_write_file(f.file); + error = mnt_want_write_file_path(f.file); if (!error) { error = removexattr(f.file->f_path.dentry, name); - mnt_drop_write_file(f.file); + mnt_drop_write_file_path(f.file); } fdput(f); return error; diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 35faf128f36d..1b98cfa342ab 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -96,3 +96,16 @@ config XFS_DEBUG not useful unless you are debugging a particular problem. Say N unless you are an XFS developer, or you play one on TV. + +config XFS_ASSERT_FATAL + bool "XFS fatal asserts" + default y + depends on XFS_FS && XFS_DEBUG + help + Set the default DEBUG mode ASSERT failure behavior. + + Say Y here to cause DEBUG mode ASSERT failures to result in fatal + errors that BUG() the kernel by default. If you say N, ASSERT failures + result in warnings. + + This behavior can be modified at runtime via sysfs. diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 5c90f82b8f6b..a6e955bfead8 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -98,8 +98,7 @@ xfs-y += xfs_aops.o \ xfs_sysfs.o \ xfs_trans.o \ xfs_xattr.o \ - kmem.o \ - uuid.o + kmem.o # low-level transaction/log code xfs-y += xfs_log.o \ diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index d6ea520162b2..4d85992d75b2 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -54,6 +54,16 @@ kmem_flags_convert(xfs_km_flags_t flags) lflags &= ~__GFP_FS; } + /* + * Default page/slab allocator behavior is to retry for ever + * for small allocations. We can override this behavior by using + * __GFP_RETRY_MAYFAIL which will tell the allocator to retry as long + * as it is feasible but rather fail than retry forever for all + * request sizes. + */ + if (flags & KM_MAYFAIL) + lflags |= __GFP_RETRY_MAYFAIL; + if (flags & KM_ZERO) lflags |= __GFP_ZERO; diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index 33db69be4832..df3e600835e8 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -111,8 +111,7 @@ xfs_ag_resv_critical( /* Critically low if less than 10% or max btree height remains. */ return XFS_TEST_ERROR(avail < orig / 10 || avail < XFS_BTREE_MAXLEVELS, - pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL, - XFS_RANDOM_AG_RESV_CRITICAL); + pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL); } /* @@ -157,7 +156,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -217,7 +217,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * counter, we only make the adjustment for AG 0. This assumes that + * there aren't any AGs hungrier for per-AG reservation than AG 0. + */ + if (pag->pag_agno == 0) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 7486401ccbd3..f965ce832bc0 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -606,7 +606,7 @@ const struct xfs_buf_ops xfs_agfl_buf_ops = { /* * Read in the allocation group free block array. */ -STATIC int /* error */ +int /* error */ xfs_alloc_read_agfl( xfs_mount_t *mp, /* mount point structure */ xfs_trans_t *tp, /* transaction pointer */ @@ -1584,6 +1584,10 @@ xfs_alloc_ag_vextent_small( bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto error0; + } xfs_trans_binval(args->tp, bp); } args->len = 1; @@ -2141,6 +2145,10 @@ xfs_alloc_fix_freelist( if (error) goto out_agbp_relse; bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto out_agbp_relse; + } xfs_trans_binval(tp, bp); } @@ -2454,8 +2462,7 @@ xfs_agf_read_verify( !xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF)) xfs_buf_ioerror(bp, -EFSBADCRC); else if (XFS_TEST_ERROR(!xfs_agf_verify(mp, bp), mp, - XFS_ERRTAG_ALLOC_READ_AGF, - XFS_RANDOM_ALLOC_READ_AGF)) + XFS_ERRTAG_ALLOC_READ_AGF)) xfs_buf_ioerror(bp, -EFSCORRUPTED); if (bp->b_error) @@ -2842,8 +2849,7 @@ xfs_free_extent( ASSERT(type != XFS_AG_RESV_AGFL); if (XFS_TEST_ERROR(false, mp, - XFS_ERRTAG_FREE_EXTENT, - XFS_RANDOM_FREE_EXTENT)) + XFS_ERRTAG_FREE_EXTENT)) return -EIO; error = xfs_free_extent_fix_freelist(tp, agno, &agbp); diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 77d9c27330ab..ef26edc2e938 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -213,6 +213,8 @@ xfs_alloc_get_rec( int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, int flags, struct xfs_buf **bpp); +int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_agnumber_t agno, struct xfs_buf **bpp); int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags); int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **agbp); diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index e1fcfe7f0a9a..cfde0a0f9706 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -253,7 +253,7 @@ xfs_allocbt_init_ptr_from_cur( ptr->s = agf->agf_roots[cur->bc_btnum]; } -STATIC __int64_t +STATIC int64_t xfs_bnobt_key_diff( struct xfs_btree_cur *cur, union xfs_btree_key *key) @@ -261,42 +261,42 @@ xfs_bnobt_key_diff( xfs_alloc_rec_incore_t *rec = &cur->bc_rec.a; xfs_alloc_key_t *kp = &key->alloc; - return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; + return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; } -STATIC __int64_t +STATIC int64_t xfs_cntbt_key_diff( struct xfs_btree_cur *cur, union xfs_btree_key *key) { xfs_alloc_rec_incore_t *rec = &cur->bc_rec.a; xfs_alloc_key_t *kp = &key->alloc; - __int64_t diff; + int64_t diff; - diff = (__int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount; + diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount; if (diff) return diff; - return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; + return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock; } -STATIC __int64_t +STATIC int64_t xfs_bnobt_diff_two_keys( struct xfs_btree_cur *cur, union xfs_btree_key *k1, union xfs_btree_key *k2) { - return (__int64_t)be32_to_cpu(k1->alloc.ar_startblock) - + return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) - be32_to_cpu(k2->alloc.ar_startblock); } -STATIC __int64_t +STATIC int64_t xfs_cntbt_diff_two_keys( struct xfs_btree_cur *cur, union xfs_btree_key *k1, union xfs_btree_key *k2) { - __int64_t diff; + int64_t diff; diff = be32_to_cpu(k1->alloc.ar_blockcount) - be32_to_cpu(k2->alloc.ar_blockcount); @@ -395,7 +395,6 @@ const struct xfs_buf_ops xfs_allocbt_buf_ops = { }; -#if defined(DEBUG) || defined(XFS_WARN) STATIC int xfs_bnobt_keys_inorder( struct xfs_btree_cur *cur, @@ -442,7 +441,6 @@ xfs_cntbt_recs_inorder( be32_to_cpu(r1->alloc.ar_startblock) < be32_to_cpu(r2->alloc.ar_startblock)); } -#endif /* DEBUG */ static const struct xfs_btree_ops xfs_bnobt_ops = { .rec_len = sizeof(xfs_alloc_rec_t), @@ -462,10 +460,8 @@ static const struct xfs_btree_ops xfs_bnobt_ops = { .key_diff = xfs_bnobt_key_diff, .buf_ops = &xfs_allocbt_buf_ops, .diff_two_keys = xfs_bnobt_diff_two_keys, -#if defined(DEBUG) || defined(XFS_WARN) .keys_inorder = xfs_bnobt_keys_inorder, .recs_inorder = xfs_bnobt_recs_inorder, -#endif }; static const struct xfs_btree_ops xfs_cntbt_ops = { @@ -486,10 +482,8 @@ static const struct xfs_btree_ops xfs_cntbt_ops = { .key_diff = xfs_cntbt_key_diff, .buf_ops = &xfs_allocbt_buf_ops, .diff_two_keys = xfs_cntbt_diff_two_keys, -#if defined(DEBUG) || defined(XFS_WARN) .keys_inorder = xfs_cntbt_keys_inorder, .recs_inorder = xfs_cntbt_recs_inorder, -#endif }; /* diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 6622d46ddec3..6249c92671de 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -114,6 +114,25 @@ xfs_inode_hasattr( * Overall external interface routines. *========================================================================*/ +/* Retrieve an extended attribute and its value. Must have ilock. */ +int +xfs_attr_get_ilocked( + struct xfs_inode *ip, + struct xfs_da_args *args) +{ + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + + if (!xfs_inode_hasattr(ip)) + return -ENOATTR; + else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) + return xfs_attr_shortform_getvalue(args); + else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) + return xfs_attr_leaf_get(args); + else + return xfs_attr_node_get(args); +} + +/* Retrieve an extended attribute by name, and its value. */ int xfs_attr_get( struct xfs_inode *ip, @@ -141,14 +160,7 @@ xfs_attr_get( args.op_flags = XFS_DA_OP_OKNOENT; lock_mode = xfs_ilock_attr_map_shared(ip); - if (!xfs_inode_hasattr(ip)) - error = -ENOATTR; - else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) - error = xfs_attr_shortform_getvalue(&args); - else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK)) - error = xfs_attr_leaf_get(&args); - else - error = xfs_attr_node_get(&args); + error = xfs_attr_get_ilocked(ip, &args); xfs_iunlock(ip, lock_mode); *valuelenp = args.valuelen; @@ -316,20 +328,19 @@ xfs_attr_set( */ xfs_defer_init(args.dfops, args.firstblock); error = xfs_attr_shortform_to_leaf(&args); - if (!error) - error = xfs_defer_finish(&args.trans, args.dfops, dp); - if (error) { - args.trans = NULL; - xfs_defer_cancel(&dfops); - goto out; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args.dfops, dp); + error = xfs_defer_finish(&args.trans, args.dfops); + if (error) + goto out_defer_cancel; /* * Commit the leaf transformation. We'll need another (linked) * transaction to add the new attribute to the leaf. */ - error = xfs_trans_roll(&args.trans, dp); + error = xfs_trans_roll_inode(&args.trans, dp); if (error) goto out; @@ -361,6 +372,9 @@ xfs_attr_set( return error; +out_defer_cancel: + xfs_defer_cancel(&dfops); + args.trans = NULL; out: if (args.trans) xfs_trans_cancel(args.trans); @@ -581,19 +595,18 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) */ xfs_defer_init(args->dfops, args->firstblock); error = xfs_attr3_leaf_to_node(args); - if (!error) - error = xfs_defer_finish(&args->trans, args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - return error; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; /* * Commit the current trans (including the inode) and start * a new one. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) return error; @@ -608,7 +621,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) * Commit the transaction that added the attr name so that * later routines can manage their own transactions. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) return error; @@ -672,20 +685,18 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) xfs_defer_init(args->dfops, args->firstblock); error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ - if (!error) - error = xfs_defer_finish(&args->trans, - args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - return error; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; } /* * Commit the remove and start the next trans in series. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); } else if (args->rmtblkno > 0) { /* @@ -694,6 +705,10 @@ xfs_attr_leaf_addname(xfs_da_args_t *args) error = xfs_attr3_leaf_clearflag(args); } return error; +out_defer_cancel: + xfs_defer_cancel(args->dfops); + args->trans = NULL; + return error; } /* @@ -735,15 +750,18 @@ xfs_attr_leaf_removename(xfs_da_args_t *args) xfs_defer_init(args->dfops, args->firstblock); error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ - if (!error) - error = xfs_defer_finish(&args->trans, args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - return error; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; } return 0; +out_defer_cancel: + xfs_defer_cancel(args->dfops); + args->trans = NULL; + return error; } /* @@ -860,20 +878,18 @@ restart: state = NULL; xfs_defer_init(args->dfops, args->firstblock); error = xfs_attr3_leaf_to_node(args); - if (!error) - error = xfs_defer_finish(&args->trans, - args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - goto out; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; /* * Commit the node conversion and start the next * trans in the chain. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) goto out; @@ -888,13 +904,12 @@ restart: */ xfs_defer_init(args->dfops, args->firstblock); error = xfs_da3_split(state); - if (!error) - error = xfs_defer_finish(&args->trans, args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - goto out; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; } else { /* * Addition succeeded, update Btree hashvals. @@ -913,7 +928,7 @@ restart: * Commit the leaf addition or btree split and start the next * trans in the chain. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) goto out; @@ -987,20 +1002,18 @@ restart: if (retval && (state->path.active > 1)) { xfs_defer_init(args->dfops, args->firstblock); error = xfs_da3_join(state); - if (!error) - error = xfs_defer_finish(&args->trans, - args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - goto out; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; } /* * Commit and start the next trans in the chain. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) goto out; @@ -1020,6 +1033,10 @@ out: if (error) return error; return retval; +out_defer_cancel: + xfs_defer_cancel(args->dfops); + args->trans = NULL; + goto out; } /* @@ -1110,17 +1127,16 @@ xfs_attr_node_removename(xfs_da_args_t *args) if (retval && (state->path.active > 1)) { xfs_defer_init(args->dfops, args->firstblock); error = xfs_da3_join(state); - if (!error) - error = xfs_defer_finish(&args->trans, args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - goto out; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; /* * Commit the Btree join operation and start a new trans. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) goto out; } @@ -1144,14 +1160,12 @@ xfs_attr_node_removename(xfs_da_args_t *args) xfs_defer_init(args->dfops, args->firstblock); error = xfs_attr3_leaf_to_shortform(bp, args, forkoff); /* bp is gone due to xfs_da_shrink_inode */ - if (!error) - error = xfs_defer_finish(&args->trans, - args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - goto out; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; } else xfs_trans_brelse(args->trans, bp); } @@ -1160,6 +1174,10 @@ xfs_attr_node_removename(xfs_da_args_t *args) out: xfs_da_state_free(state); return error; +out_defer_cancel: + xfs_defer_cancel(args->dfops); + args->trans = NULL; + goto out; } /* diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 2852521fc8ec..5c16db86b38f 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -351,7 +351,7 @@ xfs_attr3_leaf_read( err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp, XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF); return err; } @@ -2608,7 +2608,7 @@ xfs_attr3_leaf_clearflag( /* * Commit the flag value change and start the next trans in series. */ - return xfs_trans_roll(&args->trans, args->dp); + return xfs_trans_roll_inode(&args->trans, args->dp); } /* @@ -2659,7 +2659,7 @@ xfs_attr3_leaf_setflag( /* * Commit the flag value change and start the next trans in series. */ - return xfs_trans_roll(&args->trans, args->dp); + return xfs_trans_roll_inode(&args->trans, args->dp); } /* @@ -2777,7 +2777,7 @@ xfs_attr3_leaf_flipflags( /* * Commit the flag value change and start the next trans in series. */ - error = xfs_trans_roll(&args->trans, args->dp); + error = xfs_trans_roll_inode(&args->trans, args->dp); return error; } diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index d52f525f5b2d..d56caf037ca0 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -253,7 +253,7 @@ xfs_attr_rmtval_copyout( xfs_ino_t ino, int *offset, int *valuelen, - __uint8_t **dst) + uint8_t **dst) { char *src = bp->b_addr; xfs_daddr_t bno = bp->b_bn; @@ -301,7 +301,7 @@ xfs_attr_rmtval_copyin( xfs_ino_t ino, int *offset, int *valuelen, - __uint8_t **src) + uint8_t **src) { char *dst = bp->b_addr; xfs_daddr_t bno = bp->b_bn; @@ -355,7 +355,7 @@ xfs_attr_rmtval_get( struct xfs_mount *mp = args->dp->i_mount; struct xfs_buf *bp; xfs_dablk_t lblkno = args->rmtblkno; - __uint8_t *dst = args->value; + uint8_t *dst = args->value; int valuelen; int nmap; int error; @@ -386,7 +386,8 @@ xfs_attr_rmtval_get( (map[i].br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock); dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); - error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, + error = xfs_trans_read_buf(mp, args->trans, + mp->m_ddev_targp, dblkno, dblkcnt, 0, &bp, &xfs_attr3_rmt_buf_ops); if (error) @@ -395,7 +396,7 @@ xfs_attr_rmtval_get( error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino, &offset, &valuelen, &dst); - xfs_buf_relse(bp); + xfs_trans_brelse(args->trans, bp); if (error) return error; @@ -421,7 +422,7 @@ xfs_attr_rmtval_set( struct xfs_bmbt_irec map; xfs_dablk_t lblkno; xfs_fileoff_t lfileoff = 0; - __uint8_t *src = args->value; + uint8_t *src = args->value; int blkcnt; int valuelen; int nmap; @@ -466,13 +467,12 @@ xfs_attr_rmtval_set( error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno, blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock, args->total, &map, &nmap, args->dfops); - if (!error) - error = xfs_defer_finish(&args->trans, args->dfops, dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - return error; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; ASSERT(nmap == 1); ASSERT((map.br_startblock != DELAYSTARTBLOCK) && @@ -483,7 +483,7 @@ xfs_attr_rmtval_set( /* * Start the next trans in the chain. */ - error = xfs_trans_roll(&args->trans, dp); + error = xfs_trans_roll_inode(&args->trans, dp); if (error) return error; } @@ -538,6 +538,10 @@ xfs_attr_rmtval_set( } ASSERT(valuelen == 0); return 0; +out_defer_cancel: + xfs_defer_cancel(args->dfops); + args->trans = NULL; + return error; } /* @@ -608,21 +612,23 @@ xfs_attr_rmtval_remove( error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt, XFS_BMAPI_ATTRFORK, 1, args->firstblock, args->dfops, &done); - if (!error) - error = xfs_defer_finish(&args->trans, args->dfops, - args->dp); - if (error) { - args->trans = NULL; - xfs_defer_cancel(args->dfops); - return error; - } + if (error) + goto out_defer_cancel; + xfs_defer_ijoin(args->dfops, args->dp); + error = xfs_defer_finish(&args->trans, args->dfops); + if (error) + goto out_defer_cancel; /* * Close out trans and start the next one in the chain. */ - error = xfs_trans_roll(&args->trans, args->dp); + error = xfs_trans_roll_inode(&args->trans, args->dp); if (error) return error; } return 0; +out_defer_cancel: + xfs_defer_cancel(args->dfops); + args->trans = NULL; + return error; } diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h index 90928bbe693c..afd684ae3136 100644 --- a/fs/xfs/libxfs/xfs_attr_sf.h +++ b/fs/xfs/libxfs/xfs_attr_sf.h @@ -31,10 +31,10 @@ typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t; * We generate this then sort it, attr_list() must return things in hash-order. */ typedef struct xfs_attr_sf_sort { - __uint8_t entno; /* entry number in original list */ - __uint8_t namelen; /* length of name value (no null) */ - __uint8_t valuelen; /* length of value */ - __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ + uint8_t entno; /* entry number in original list */ + uint8_t namelen; /* length of name value (no null) */ + uint8_t valuelen; /* length of value */ + uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ xfs_dahash_t hash; /* this entry's hash value */ unsigned char *name; /* name value, pointer into buffer */ } xfs_attr_sf_sort_t; @@ -42,7 +42,7 @@ typedef struct xfs_attr_sf_sort { #define XFS_ATTR_SF_ENTSIZE_BYNAME(nlen,vlen) /* space name/value uses */ \ (((int)sizeof(xfs_attr_sf_entry_t)-1 + (nlen)+(vlen))) #define XFS_ATTR_SF_ENTSIZE_MAX /* max space for name&value */ \ - ((1 << (NBBY*(int)sizeof(__uint8_t))) - 1) + ((1 << (NBBY*(int)sizeof(uint8_t))) - 1) #define XFS_ATTR_SF_ENTSIZE(sfep) /* space an entry uses */ \ ((int)sizeof(xfs_attr_sf_entry_t)-1 + (sfep)->namelen+(sfep)->valuelen) #define XFS_ATTR_SF_NEXTENTRY(sfep) /* next entry in struct */ \ diff --git a/fs/xfs/libxfs/xfs_bit.h b/fs/xfs/libxfs/xfs_bit.h index e1649c0d3e02..61c6b2025d0c 100644 --- a/fs/xfs/libxfs/xfs_bit.h +++ b/fs/xfs/libxfs/xfs_bit.h @@ -25,47 +25,47 @@ /* * masks with n high/low bits set, 64-bit values */ -static inline __uint64_t xfs_mask64hi(int n) +static inline uint64_t xfs_mask64hi(int n) { - return (__uint64_t)-1 << (64 - (n)); + return (uint64_t)-1 << (64 - (n)); } -static inline __uint32_t xfs_mask32lo(int n) +static inline uint32_t xfs_mask32lo(int n) { - return ((__uint32_t)1 << (n)) - 1; + return ((uint32_t)1 << (n)) - 1; } -static inline __uint64_t xfs_mask64lo(int n) +static inline uint64_t xfs_mask64lo(int n) { - return ((__uint64_t)1 << (n)) - 1; + return ((uint64_t)1 << (n)) - 1; } /* Get high bit set out of 32-bit argument, -1 if none set */ -static inline int xfs_highbit32(__uint32_t v) +static inline int xfs_highbit32(uint32_t v) { return fls(v) - 1; } /* Get high bit set out of 64-bit argument, -1 if none set */ -static inline int xfs_highbit64(__uint64_t v) +static inline int xfs_highbit64(uint64_t v) { return fls64(v) - 1; } /* Get low bit set out of 32-bit argument, -1 if none set */ -static inline int xfs_lowbit32(__uint32_t v) +static inline int xfs_lowbit32(uint32_t v) { return ffs(v) - 1; } /* Get low bit set out of 64-bit argument, -1 if none set */ -static inline int xfs_lowbit64(__uint64_t v) +static inline int xfs_lowbit64(uint64_t v) { - __uint32_t w = (__uint32_t)v; + uint32_t w = (uint32_t)v; int n = 0; if (w) { /* lower bits */ n = ffs(w); } else { /* upper bits */ - w = (__uint32_t)(v >> 32); + w = (uint32_t)(v >> 32); if (w) { n = ffs(w); if (n) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index a7048eafa8e6..89263797cf32 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -49,7 +49,6 @@ #include "xfs_rmap.h" #include "xfs_ag_resv.h" #include "xfs_refcount.h" -#include "xfs_rmap_btree.h" #include "xfs_icache.h" @@ -192,12 +191,8 @@ xfs_bmap_worst_indlen( int maxrecs; /* maximum record count at this level */ xfs_mount_t *mp; /* mount structure */ xfs_filblks_t rval; /* return value */ - xfs_filblks_t orig_len; mp = ip->i_mount; - - /* Calculate the worst-case size of the bmbt. */ - orig_len = len; maxrecs = mp->m_bmap_dmxr[0]; for (level = 0, rval = 0; level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK); @@ -205,20 +200,12 @@ xfs_bmap_worst_indlen( len += maxrecs - 1; do_div(len, maxrecs); rval += len; - if (len == 1) { - rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - + if (len == 1) + return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) - level - 1; - break; - } if (level == 0) maxrecs = mp->m_bmap_dmxr[1]; } - - /* Calculate the worst-case size of the rmapbt. */ - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) - rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) + - mp->m_rmap_maxlevels; - return rval; } @@ -579,7 +566,7 @@ xfs_bmap_validate_ret( #else #define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0) -#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) +#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) do { } while (0) #endif /* DEBUG */ /* @@ -880,7 +867,7 @@ xfs_bmap_local_to_extents( xfs_ifork_t *ifp; /* inode fork pointer */ xfs_alloc_arg_t args; /* allocation arguments */ xfs_buf_t *bp; /* buffer for extent block */ - xfs_bmbt_rec_host_t *ep; /* extent record pointer */ + struct xfs_bmbt_irec rec; /* * We don't want to deal with the case of keeping inode data inline yet. @@ -943,9 +930,12 @@ xfs_bmap_local_to_extents( xfs_bmap_local_to_extents_empty(ip, whichfork); flags |= XFS_ILOG_CORE; - xfs_iext_add(ifp, 0, 1); - ep = xfs_iext_get_ext(ifp, 0); - xfs_bmbt_set_allf(ep, 0, args.fsbno, 1, XFS_EXT_NORM); + rec.br_startoff = 0; + rec.br_startblock = args.fsbno; + rec.br_blockcount = 1; + rec.br_state = XFS_EXT_NORM; + xfs_iext_insert(ip, 0, 1, &rec, 0); + trace_xfs_bmap_post_update(ip, 0, whichfork == XFS_ATTR_FORK ? BMAP_ATTRFORK : 0, _THIS_IP_); @@ -1196,7 +1186,7 @@ xfs_bmap_add_attrfork( xfs_log_sb(tp); } - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto bmap_cancel; error = xfs_trans_commit(tp); @@ -1356,7 +1346,6 @@ xfs_bmap_first_unused( xfs_fileoff_t lastaddr; /* last block number seen */ xfs_fileoff_t lowest; /* lowest useful block */ xfs_fileoff_t max; /* starting useful block */ - xfs_fileoff_t off; /* offset for this block */ xfs_extnum_t nextents; /* number of extent entries */ ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE || @@ -1373,16 +1362,19 @@ xfs_bmap_first_unused( lowest = *first_unused; nextents = xfs_iext_count(ifp); for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) { - xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx); - off = xfs_bmbt_get_startoff(ep); + struct xfs_bmbt_irec got; + + xfs_iext_get_extent(ifp, idx, &got); + /* * See if the hole before this extent will work. */ - if (off >= lowest + len && off - max >= len) { + if (got.br_startoff >= lowest + len && + got.br_startoff - max >= len) { *first_unused = max; return 0; } - lastaddr = off + xfs_bmbt_get_blockcount(ep); + lastaddr = got.br_startoff + got.br_blockcount; max = XFS_FILEOFF_MAX(lastaddr, lowest); } *first_unused = max; @@ -1485,14 +1477,14 @@ xfs_bmap_isaeof( int is_empty; int error; - bma->aeof = 0; + bma->aeof = false; error = xfs_bmap_last_extent(NULL, bma->ip, whichfork, &rec, &is_empty); if (error) return error; if (is_empty) { - bma->aeof = 1; + bma->aeof = true; return 0; } @@ -3860,6 +3852,17 @@ xfs_trim_extent( } } +/* trim extent to within eof */ +void +xfs_trim_extent_eof( + struct xfs_bmbt_irec *irec, + struct xfs_inode *ip) + +{ + xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount, + i_size_read(VFS_I(ip)))); +} + /* * Trim the returned map to the required bounds */ @@ -3992,7 +3995,7 @@ xfs_bmapi_read( if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + mp, XFS_ERRTAG_BMAPIFORMAT))) { XFS_ERROR_REPORT("xfs_bmapi_read", XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; } @@ -4473,7 +4476,7 @@ xfs_bmapi_write( if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + mp, XFS_ERRTAG_BMAPIFORMAT))) { XFS_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; } @@ -4694,7 +4697,7 @@ xfs_bmapi_remap( if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + mp, XFS_ERRTAG_BMAPIFORMAT))) { XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; } @@ -4918,7 +4921,7 @@ xfs_bmap_del_extent_delay( da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, got->br_blockcount), da_old); got->br_startblock = nullstartblock((int)da_new); - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + xfs_iext_update_extent(ifp, *idx, got); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); break; case BMAP_RIGHT_CONTIG: @@ -4930,7 +4933,7 @@ xfs_bmap_del_extent_delay( da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, got->br_blockcount), da_old); got->br_startblock = nullstartblock((int)da_new); - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + xfs_iext_update_extent(ifp, *idx, got); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); break; case 0: @@ -4956,7 +4959,7 @@ xfs_bmap_del_extent_delay( del->br_blockcount); got->br_startblock = nullstartblock((int)got_indlen); - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + xfs_iext_update_extent(ifp, *idx, got); trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_); new.br_startoff = del_endoff; @@ -5026,7 +5029,7 @@ xfs_bmap_del_extent_cow( got->br_startoff = del_endoff; got->br_blockcount -= del->br_blockcount; got->br_startblock = del->br_startblock + del->br_blockcount; - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + xfs_iext_update_extent(ifp, *idx, got); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); break; case BMAP_RIGHT_CONTIG: @@ -5035,7 +5038,7 @@ xfs_bmap_del_extent_cow( */ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_blockcount -= del->br_blockcount; - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + xfs_iext_update_extent(ifp, *idx, got); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); break; case 0: @@ -5044,7 +5047,7 @@ xfs_bmap_del_extent_cow( */ trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); got->br_blockcount = del->br_startoff - got->br_startoff; - xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + xfs_iext_update_extent(ifp, *idx, got); trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); new.br_startoff = del_endoff; @@ -5434,6 +5437,8 @@ __xfs_bunmapi( int whichfork; /* data or attribute fork */ xfs_fsblock_t sum; xfs_filblks_t len = *rlen; /* length to unmap in file */ + xfs_fileoff_t max_len; + xfs_agnumber_t prev_agno = NULLAGNUMBER, agno; trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_); @@ -5455,6 +5460,16 @@ __xfs_bunmapi( ASSERT(len > 0); ASSERT(nexts >= 0); + /* + * Guesstimate how many blocks we can unmap without running the risk of + * blowing out the transaction with a mix of EFIs and reflink + * adjustments. + */ + if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) + max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); + else + max_len = len; + if (!(ifp->if_flags & XFS_IFEXTENTS) && (error = xfs_iread_extents(tp, ip, whichfork))) return error; @@ -5499,7 +5514,7 @@ __xfs_bunmapi( extno = 0; while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 && - (nexts == 0 || extno < nexts)) { + (nexts == 0 || extno < nexts) && max_len > 0) { /* * Is the found extent after a hole in which bno lives? * Just back up to the previous extent, if so. @@ -5523,6 +5538,17 @@ __xfs_bunmapi( */ del = got; wasdel = isnullstartblock(del.br_startblock); + + /* + * Make sure we don't touch multiple AGF headers out of order + * in a single transaction, as that could cause AB-BA deadlocks. + */ + if (!wasdel) { + agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); + if (prev_agno != NULLAGNUMBER && prev_agno > agno) + break; + prev_agno = agno; + } if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; @@ -5531,6 +5557,15 @@ __xfs_bunmapi( } if (del.br_startoff + del.br_blockcount > bno + 1) del.br_blockcount = bno + 1 - del.br_startoff; + + /* How much can we safely unmap? */ + if (max_len < del.br_blockcount) { + del.br_startoff += del.br_blockcount - max_len; + if (!wasdel) + del.br_startblock += del.br_blockcount - max_len; + del.br_blockcount = max_len; + } + sum = del.br_startblock + del.br_blockcount; if (isrt && (mod = do_mod(sum, mp->m_sb.sb_rextsize))) { @@ -5707,6 +5742,7 @@ __xfs_bunmapi( if (!isrt && wasdel) xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false); + max_len -= del.br_blockcount; bno = del.br_startoff - 1; nodelete: /* @@ -5843,32 +5879,26 @@ xfs_bmse_merge( int whichfork, xfs_fileoff_t shift, /* shift fsb */ int current_ext, /* idx of gotp */ - struct xfs_bmbt_rec_host *gotp, /* extent to shift */ - struct xfs_bmbt_rec_host *leftp, /* preceding extent */ + struct xfs_bmbt_irec *got, /* extent to shift */ + struct xfs_bmbt_irec *left, /* preceding extent */ struct xfs_btree_cur *cur, - int *logflags) /* output */ + int *logflags, /* output */ + struct xfs_defer_ops *dfops) { - struct xfs_bmbt_irec got; - struct xfs_bmbt_irec left; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_bmbt_irec new; xfs_filblks_t blockcount; int error, i; struct xfs_mount *mp = ip->i_mount; - xfs_bmbt_get_all(gotp, &got); - xfs_bmbt_get_all(leftp, &left); - blockcount = left.br_blockcount + got.br_blockcount; + blockcount = left->br_blockcount + got->br_blockcount; ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - ASSERT(xfs_bmse_can_merge(&left, &got, shift)); + ASSERT(xfs_bmse_can_merge(left, got, shift)); - /* - * Merge the in-core extents. Note that the host record pointers and - * current_ext index are invalid once the extent has been removed via - * xfs_iext_remove(). - */ - xfs_bmbt_set_blockcount(leftp, blockcount); - xfs_iext_remove(ip, current_ext, 1, 0); + new = *left; + new.br_blockcount = blockcount; /* * Update the on-disk extent count, the btree if necessary and log the @@ -5879,12 +5909,12 @@ xfs_bmse_merge( *logflags |= XFS_ILOG_CORE; if (!cur) { *logflags |= XFS_ILOG_DEXT; - return 0; + goto done; } /* lookup and remove the extent to merge */ - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(cur, got->br_startoff, got->br_startblock, + got->br_blockcount, &i); if (error) return error; XFS_WANT_CORRUPTED_RETURN(mp, i == 1); @@ -5895,16 +5925,28 @@ xfs_bmse_merge( XFS_WANT_CORRUPTED_RETURN(mp, i == 1); /* lookup and update size of the previous extent */ - error = xfs_bmbt_lookup_eq(cur, left.br_startoff, left.br_startblock, - left.br_blockcount, &i); + error = xfs_bmbt_lookup_eq(cur, left->br_startoff, left->br_startblock, + left->br_blockcount, &i); if (error) return error; XFS_WANT_CORRUPTED_RETURN(mp, i == 1); - left.br_blockcount = blockcount; + error = xfs_bmbt_update(cur, new.br_startoff, new.br_startblock, + new.br_blockcount, new.br_state); + if (error) + return error; + +done: + xfs_iext_update_extent(ifp, current_ext - 1, &new); + xfs_iext_remove(ip, current_ext, 1, 0); - return xfs_bmbt_update(cur, left.br_startoff, left.br_startblock, - left.br_blockcount, left.br_state); + /* update reverse mapping. rmap functions merge the rmaps for us */ + error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, got); + if (error) + return error; + memcpy(&new, got, sizeof(new)); + new.br_startoff = left->br_startoff + left->br_blockcount; + return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &new); } /* @@ -5916,7 +5958,7 @@ xfs_bmse_shift_one( int whichfork, xfs_fileoff_t offset_shift_fsb, int *current_ext, - struct xfs_bmbt_rec_host *gotp, + struct xfs_bmbt_irec *got, struct xfs_btree_cur *cur, int *logflags, enum shift_direction direction, @@ -5925,9 +5967,7 @@ xfs_bmse_shift_one( struct xfs_ifork *ifp; struct xfs_mount *mp; xfs_fileoff_t startoff; - struct xfs_bmbt_rec_host *adj_irecp; - struct xfs_bmbt_irec got; - struct xfs_bmbt_irec adj_irec; + struct xfs_bmbt_irec adj_irec, new; int error; int i; int total_extents; @@ -5936,13 +5976,11 @@ xfs_bmse_shift_one( ifp = XFS_IFORK_PTR(ip, whichfork); total_extents = xfs_iext_count(ifp); - xfs_bmbt_get_all(gotp, &got); - /* delalloc extents should be prevented by caller */ - XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got.br_startblock)); + XFS_WANT_CORRUPTED_RETURN(mp, !isnullstartblock(got->br_startblock)); if (direction == SHIFT_LEFT) { - startoff = got.br_startoff - offset_shift_fsb; + startoff = got->br_startoff - offset_shift_fsb; /* * Check for merge if we've got an extent to the left, @@ -5950,46 +5988,39 @@ xfs_bmse_shift_one( * of the file for the shift. */ if (!*current_ext) { - if (got.br_startoff < offset_shift_fsb) + if (got->br_startoff < offset_shift_fsb) return -EINVAL; goto update_current_ext; } + /* - * grab the left extent and check for a large - * enough hole. + * grab the left extent and check for a large enough hole. */ - adj_irecp = xfs_iext_get_ext(ifp, *current_ext - 1); - xfs_bmbt_get_all(adj_irecp, &adj_irec); - - if (startoff < - adj_irec.br_startoff + adj_irec.br_blockcount) + xfs_iext_get_extent(ifp, *current_ext - 1, &adj_irec); + if (startoff < adj_irec.br_startoff + adj_irec.br_blockcount) return -EINVAL; /* check whether to merge the extent or shift it down */ - if (xfs_bmse_can_merge(&adj_irec, &got, - offset_shift_fsb)) { - error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb, - *current_ext, gotp, adj_irecp, - cur, logflags); - if (error) - return error; - adj_irec = got; - goto update_rmap; + if (xfs_bmse_can_merge(&adj_irec, got, offset_shift_fsb)) { + return xfs_bmse_merge(ip, whichfork, offset_shift_fsb, + *current_ext, got, &adj_irec, + cur, logflags, dfops); } } else { - startoff = got.br_startoff + offset_shift_fsb; + startoff = got->br_startoff + offset_shift_fsb; /* nothing to move if this is the last extent */ if (*current_ext >= (total_extents - 1)) goto update_current_ext; + /* * If this is not the last extent in the file, make sure there * is enough room between current extent and next extent for * accommodating the shift. */ - adj_irecp = xfs_iext_get_ext(ifp, *current_ext + 1); - xfs_bmbt_get_all(adj_irecp, &adj_irec); - if (startoff + got.br_blockcount > adj_irec.br_startoff) + xfs_iext_get_extent(ifp, *current_ext + 1, &adj_irec); + if (startoff + got->br_blockcount > adj_irec.br_startoff) return -EINVAL; + /* * Unlike a left shift (which involves a hole punch), * a right shift does not modify extent neighbors @@ -5997,45 +6028,48 @@ xfs_bmse_shift_one( * in this scenario. Check anyways and warn if we * encounter two extents that could be one. */ - if (xfs_bmse_can_merge(&got, &adj_irec, offset_shift_fsb)) + if (xfs_bmse_can_merge(got, &adj_irec, offset_shift_fsb)) WARN_ON_ONCE(1); } + /* * Increment the extent index for the next iteration, update the start * offset of the in-core extent and update the btree if applicable. */ update_current_ext: - if (direction == SHIFT_LEFT) - (*current_ext)++; - else - (*current_ext)--; - xfs_bmbt_set_startoff(gotp, startoff); *logflags |= XFS_ILOG_CORE; - adj_irec = got; - if (!cur) { + + new = *got; + new.br_startoff = startoff; + + if (cur) { + error = xfs_bmbt_lookup_eq(cur, got->br_startoff, + got->br_startblock, got->br_blockcount, &i); + if (error) + return error; + XFS_WANT_CORRUPTED_RETURN(mp, i == 1); + + error = xfs_bmbt_update(cur, new.br_startoff, + new.br_startblock, new.br_blockcount, + new.br_state); + if (error) + return error; + } else { *logflags |= XFS_ILOG_DEXT; - goto update_rmap; } - error = xfs_bmbt_lookup_eq(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, &i); - if (error) - return error; - XFS_WANT_CORRUPTED_RETURN(mp, i == 1); + xfs_iext_update_extent(ifp, *current_ext, &new); - got.br_startoff = startoff; - error = xfs_bmbt_update(cur, got.br_startoff, got.br_startblock, - got.br_blockcount, got.br_state); - if (error) - return error; + if (direction == SHIFT_LEFT) + (*current_ext)++; + else + (*current_ext)--; -update_rmap: /* update reverse mapping */ - error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, &adj_irec); + error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, got); if (error) return error; - adj_irec.br_startoff = startoff; - return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &adj_irec); + return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &new); } /* @@ -6062,7 +6096,6 @@ xfs_bmap_shift_extents( int num_exts) { struct xfs_btree_cur *cur = NULL; - struct xfs_bmbt_rec_host *gotp; struct xfs_bmbt_irec got; struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp; @@ -6077,7 +6110,7 @@ xfs_bmap_shift_extents( if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + mp, XFS_ERRTAG_BMAPIFORMAT))) { XFS_ERROR_REPORT("xfs_bmap_shift_extents", XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; @@ -6089,7 +6122,6 @@ xfs_bmap_shift_extents( ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT); - ASSERT(*next_fsb != NULLFSBLOCK || direction == SHIFT_RIGHT); ifp = XFS_IFORK_PTR(ip, whichfork); if (!(ifp->if_flags & XFS_IFEXTENTS)) { @@ -6121,10 +6153,26 @@ xfs_bmap_shift_extents( * In case of first right shift, we need to initialize next_fsb */ if (*next_fsb == NULLFSBLOCK) { - gotp = xfs_iext_get_ext(ifp, total_extents - 1); - xfs_bmbt_get_all(gotp, &got); + ASSERT(direction == SHIFT_RIGHT); + + current_ext = total_extents - 1; + xfs_iext_get_extent(ifp, current_ext, &got); + if (stop_fsb > got.br_startoff) { + *done = 1; + goto del_cursor; + } *next_fsb = got.br_startoff; - if (stop_fsb > *next_fsb) { + } else { + /* + * Look up the extent index for the fsb where we start shifting. We can + * henceforth iterate with current_ext as extent list changes are locked + * out via ilock. + * + * If next_fsb lies in a hole beyond which there are no extents we are + * done. + */ + if (!xfs_iext_lookup_extent(ip, ifp, *next_fsb, ¤t_ext, + &got)) { *done = 1; goto del_cursor; } @@ -6132,37 +6180,26 @@ xfs_bmap_shift_extents( /* Lookup the extent index at which we have to stop */ if (direction == SHIFT_RIGHT) { - gotp = xfs_iext_bno_to_ext(ifp, stop_fsb, &stop_extent); + struct xfs_bmbt_irec s; + + xfs_iext_lookup_extent(ip, ifp, stop_fsb, &stop_extent, &s); /* Make stop_extent exclusive of shift range */ stop_extent--; - } else + if (current_ext <= stop_extent) { + error = -EIO; + goto del_cursor; + } + } else { stop_extent = total_extents; - - /* - * Look up the extent index for the fsb where we start shifting. We can - * henceforth iterate with current_ext as extent list changes are locked - * out via ilock. - * - * gotp can be null in 2 cases: 1) if there are no extents or 2) - * *next_fsb lies in a hole beyond which there are no extents. Either - * way, we are done. - */ - gotp = xfs_iext_bno_to_ext(ifp, *next_fsb, ¤t_ext); - if (!gotp) { - *done = 1; - goto del_cursor; - } - - /* some sanity checking before we finally start shifting extents */ - if ((direction == SHIFT_LEFT && current_ext >= stop_extent) || - (direction == SHIFT_RIGHT && current_ext <= stop_extent)) { - error = -EIO; - goto del_cursor; + if (current_ext >= stop_extent) { + error = -EIO; + goto del_cursor; + } } while (nexts++ < num_exts) { error = xfs_bmse_shift_one(ip, whichfork, offset_shift_fsb, - ¤t_ext, gotp, cur, &logflags, + ¤t_ext, &got, cur, &logflags, direction, dfops); if (error) goto del_cursor; @@ -6180,13 +6217,11 @@ xfs_bmap_shift_extents( *next_fsb = NULLFSBLOCK; break; } - gotp = xfs_iext_get_ext(ifp, current_ext); + xfs_iext_get_extent(ifp, current_ext, &got); } - if (!*done) { - xfs_bmbt_get_all(gotp, &got); + if (!*done) *next_fsb = got.br_startoff; - } del_cursor: if (cur) @@ -6215,7 +6250,6 @@ xfs_bmap_split_extent_at( { int whichfork = XFS_DATA_FORK; struct xfs_btree_cur *cur = NULL; - struct xfs_bmbt_rec_host *gotp; struct xfs_bmbt_irec got; struct xfs_bmbt_irec new; /* split extent */ struct xfs_mount *mp = ip->i_mount; @@ -6229,7 +6263,7 @@ xfs_bmap_split_extent_at( if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + mp, XFS_ERRTAG_BMAPIFORMAT))) { XFS_ERROR_REPORT("xfs_bmap_split_extent_at", XFS_ERRLEVEL_LOW, mp); return -EFSCORRUPTED; @@ -6247,21 +6281,10 @@ xfs_bmap_split_extent_at( } /* - * gotp can be null in 2 cases: 1) if there are no extents - * or 2) split_fsb lies in a hole beyond which there are - * no extents. Either way, we are done. + * If there are not extents, or split_fsb lies in a hole we are done. */ - gotp = xfs_iext_bno_to_ext(ifp, split_fsb, ¤t_ext); - if (!gotp) - return 0; - - xfs_bmbt_get_all(gotp, &got); - - /* - * Check split_fsb lies in a hole or the start boundary offset - * of the extent. - */ - if (got.br_startoff >= split_fsb) + if (!xfs_iext_lookup_extent(ip, ifp, split_fsb, ¤t_ext, &got) || + got.br_startoff >= split_fsb) return 0; gotblkcnt = split_fsb - got.br_startoff; @@ -6284,8 +6307,8 @@ xfs_bmap_split_extent_at( XFS_WANT_CORRUPTED_GOTO(mp, i == 1, del_cursor); } - xfs_bmbt_set_blockcount(gotp, gotblkcnt); got.br_blockcount = gotblkcnt; + xfs_iext_update_extent(ifp, current_ext, &got); logflags = XFS_ILOG_CORE; if (cur) { @@ -6369,7 +6392,7 @@ xfs_bmap_split_extent( if (error) goto out; - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out; @@ -6419,7 +6442,7 @@ __xfs_bmap_add( bi->bi_whichfork = whichfork; bi->bi_bmap = *bmap; - error = xfs_defer_join(dfops, bi->bi_owner); + error = xfs_defer_ijoin(dfops, bi->bi_owner); if (error) { kmem_free(bi); return error; @@ -6472,33 +6495,42 @@ xfs_bmap_finish_one( int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, + xfs_filblks_t *blockcount, xfs_exntst_t state) { - int error = 0, done; + xfs_fsblock_t firstfsb; + int error = 0; + + /* + * firstfsb is tied to the transaction lifetime and is used to + * ensure correct AG locking order and schedule work item + * continuations. XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us + * to only making one bmap call per transaction, so it should + * be safe to have it as a local variable here. + */ + firstfsb = NULLFSBLOCK; trace_xfs_bmap_deferred(tp->t_mountp, XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), - ip->i_ino, whichfork, startoff, blockcount, state); + ip->i_ino, whichfork, startoff, *blockcount, state); if (WARN_ON_ONCE(whichfork != XFS_DATA_FORK)) return -EFSCORRUPTED; if (XFS_TEST_ERROR(false, tp->t_mountp, - XFS_ERRTAG_BMAP_FINISH_ONE, - XFS_RANDOM_BMAP_FINISH_ONE)) + XFS_ERRTAG_BMAP_FINISH_ONE)) return -EIO; switch (type) { case XFS_BMAP_MAP: - error = xfs_bmapi_remap(tp, ip, startoff, blockcount, + error = xfs_bmapi_remap(tp, ip, startoff, *blockcount, startblock, dfops); + *blockcount = 0; break; case XFS_BMAP_UNMAP: - error = xfs_bunmapi(tp, ip, startoff, blockcount, - XFS_BMAPI_REMAP, 1, &startblock, dfops, &done); - ASSERT(done); + error = __xfs_bunmapi(tp, ip, startoff, blockcount, + XFS_BMAPI_REMAP, 1, &firstfsb, dfops); break; default: ASSERT(0); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index c35a14fa1527..502e0d8fb4ff 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -208,6 +208,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); +void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, @@ -271,7 +272,7 @@ struct xfs_bmap_intent { int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops, struct xfs_inode *ip, enum xfs_bmap_intent_type type, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, xfs_exntst_t state); + xfs_filblks_t *blockcount, xfs_exntst_t state); int xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, struct xfs_inode *ip, struct xfs_bmbt_irec *imap); int xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 6cba69aff077..a6331ffa51e3 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -94,8 +94,8 @@ xfs_bmdr_to_bmbt( */ STATIC void __xfs_bmbt_get_all( - __uint64_t l0, - __uint64_t l1, + uint64_t l0, + uint64_t l1, xfs_bmbt_irec_t *s) { int ext_flag; @@ -573,6 +573,16 @@ xfs_bmbt_init_key_from_rec( } STATIC void +xfs_bmbt_init_high_key_from_rec( + union xfs_btree_key *key, + union xfs_btree_rec *rec) +{ + key->bmbt.br_startoff = cpu_to_be64( + xfs_bmbt_disk_get_startoff(&rec->bmbt) + + xfs_bmbt_disk_get_blockcount(&rec->bmbt) - 1); +} + +STATIC void xfs_bmbt_init_rec_from_cur( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) @@ -588,15 +598,25 @@ xfs_bmbt_init_ptr_from_cur( ptr->l = 0; } -STATIC __int64_t +STATIC int64_t xfs_bmbt_key_diff( struct xfs_btree_cur *cur, union xfs_btree_key *key) { - return (__int64_t)be64_to_cpu(key->bmbt.br_startoff) - + return (int64_t)be64_to_cpu(key->bmbt.br_startoff) - cur->bc_rec.b.br_startoff; } +STATIC int64_t +xfs_bmbt_diff_two_keys( + struct xfs_btree_cur *cur, + union xfs_btree_key *k1, + union xfs_btree_key *k2) +{ + return (int64_t)be64_to_cpu(k1->bmbt.br_startoff) - + be64_to_cpu(k2->bmbt.br_startoff); +} + static bool xfs_bmbt_verify( struct xfs_buf *bp) @@ -687,7 +707,6 @@ const struct xfs_buf_ops xfs_bmbt_buf_ops = { }; -#if defined(DEBUG) || defined(XFS_WARN) STATIC int xfs_bmbt_keys_inorder( struct xfs_btree_cur *cur, @@ -708,7 +727,6 @@ xfs_bmbt_recs_inorder( xfs_bmbt_disk_get_blockcount(&r1->bmbt) <= xfs_bmbt_disk_get_startoff(&r2->bmbt); } -#endif /* DEBUG */ static const struct xfs_btree_ops xfs_bmbt_ops = { .rec_len = sizeof(xfs_bmbt_rec_t), @@ -722,14 +740,14 @@ static const struct xfs_btree_ops xfs_bmbt_ops = { .get_minrecs = xfs_bmbt_get_minrecs, .get_dmaxrecs = xfs_bmbt_get_dmaxrecs, .init_key_from_rec = xfs_bmbt_init_key_from_rec, + .init_high_key_from_rec = xfs_bmbt_init_high_key_from_rec, .init_rec_from_cur = xfs_bmbt_init_rec_from_cur, .init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur, .key_diff = xfs_bmbt_key_diff, + .diff_two_keys = xfs_bmbt_diff_two_keys, .buf_ops = &xfs_bmbt_buf_ops, -#if defined(DEBUG) || defined(XFS_WARN) .keys_inorder = xfs_bmbt_keys_inorder, .recs_inorder = xfs_bmbt_recs_inorder, -#endif }; /* @@ -840,6 +858,7 @@ xfs_bmbt_change_owner( cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork); if (!cur) return -ENOMEM; + cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER; error = xfs_btree_change_owner(cur, new_owner, buffer_list); xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 3a673ba201aa..5bfb88261c7e 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -43,7 +43,7 @@ kmem_zone_t *xfs_btree_cur_zone; /* * Btree magic numbers. */ -static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = { +static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = { { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC, XFS_FIBT_MAGIC, 0 }, { XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC, @@ -51,12 +51,12 @@ static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = { XFS_REFC_CRC_MAGIC } }; -__uint32_t +uint32_t xfs_btree_magic( int crc, xfs_btnum_t btnum) { - __uint32_t magic = xfs_magics[crc][btnum]; + uint32_t magic = xfs_magics[crc][btnum]; /* Ensure we asked for crc for crc-only magics. */ ASSERT(magic != 0); @@ -101,8 +101,7 @@ xfs_btree_check_lblock( be64_to_cpu(block->bb_u.l.bb_rightsib))); if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp, - XFS_ERRTAG_BTREE_CHECK_LBLOCK, - XFS_RANDOM_BTREE_CHECK_LBLOCK))) { + XFS_ERRTAG_BTREE_CHECK_LBLOCK))) { if (bp) trace_xfs_btree_corrupt(bp, _RET_IP_); XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); @@ -153,8 +152,7 @@ xfs_btree_check_sblock( block->bb_u.s.bb_rightsib; if (unlikely(XFS_TEST_ERROR(!sblock_ok, mp, - XFS_ERRTAG_BTREE_CHECK_SBLOCK, - XFS_RANDOM_BTREE_CHECK_SBLOCK))) { + XFS_ERRTAG_BTREE_CHECK_SBLOCK))) { if (bp) trace_xfs_btree_corrupt(bp, _RET_IP_); XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); @@ -568,7 +566,7 @@ xfs_btree_ptr_offset( /* * Return a pointer to the n-th record in the btree block. */ -STATIC union xfs_btree_rec * +union xfs_btree_rec * xfs_btree_rec_addr( struct xfs_btree_cur *cur, int n, @@ -581,7 +579,7 @@ xfs_btree_rec_addr( /* * Return a pointer to the n-th key in the btree block. */ -STATIC union xfs_btree_key * +union xfs_btree_key * xfs_btree_key_addr( struct xfs_btree_cur *cur, int n, @@ -594,7 +592,7 @@ xfs_btree_key_addr( /* * Return a pointer to the n-th high key in the btree block. */ -STATIC union xfs_btree_key * +union xfs_btree_key * xfs_btree_high_key_addr( struct xfs_btree_cur *cur, int n, @@ -607,7 +605,7 @@ xfs_btree_high_key_addr( /* * Return a pointer to the n-th block pointer in the btree block. */ -STATIC union xfs_btree_ptr * +union xfs_btree_ptr * xfs_btree_ptr_addr( struct xfs_btree_cur *cur, int n, @@ -641,7 +639,7 @@ xfs_btree_get_iroot( * Retrieve the block pointer from the cursor at the given level. * This may be an inode btree root or from a buffer. */ -STATIC struct xfs_btree_block * /* generic btree block pointer */ +struct xfs_btree_block * /* generic btree block pointer */ xfs_btree_get_block( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* level in btree */ @@ -730,7 +728,8 @@ xfs_btree_firstrec( * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); - xfs_btree_check_block(cur, block, level, bp); + if (xfs_btree_check_block(cur, block, level, bp)) + return 0; /* * It's empty, there is no such record. */ @@ -759,7 +758,8 @@ xfs_btree_lastrec( * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); - xfs_btree_check_block(cur, block, level, bp); + if (xfs_btree_check_block(cur, block, level, bp)) + return 0; /* * It's empty, there is no such record. */ @@ -778,14 +778,14 @@ xfs_btree_lastrec( */ void xfs_btree_offsets( - __int64_t fields, /* bitmask of fields */ + int64_t fields, /* bitmask of fields */ const short *offsets, /* table of field offsets */ int nbits, /* number of bits to inspect */ int *first, /* output: first byte offset */ int *last) /* output: last byte offset */ { int i; /* current bit number */ - __int64_t imask; /* mask for current bit number */ + int64_t imask; /* mask for current bit number */ ASSERT(fields != 0); /* @@ -1756,7 +1756,7 @@ error0: return error; } -STATIC int +int xfs_btree_lookup_get_block( struct xfs_btree_cur *cur, /* btree cursor */ int level, /* level in the btree */ @@ -1791,6 +1791,7 @@ xfs_btree_lookup_get_block( /* Check the inode owner since the verifiers don't. */ if (xfs_sb_version_hascrc(&cur->bc_mp->m_sb) && + !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_INVALID_OWNER) && (cur->bc_flags & XFS_BTREE_LONG_PTRS) && be64_to_cpu((*blkp)->bb_u.l.bb_owner) != cur->bc_private.b.ip->i_ino) @@ -1846,7 +1847,7 @@ xfs_btree_lookup( int *stat) /* success/failure */ { struct xfs_btree_block *block; /* current btree block */ - __int64_t diff; /* difference for the current key */ + int64_t diff; /* difference for the current key */ int error; /* error return value */ int keyno; /* current key number */ int level; /* level in the btree */ @@ -4435,7 +4436,7 @@ xfs_btree_visit_blocks( * recovery completion writes the changes to disk. */ struct xfs_btree_block_change_owner_info { - __uint64_t new_owner; + uint64_t new_owner; struct list_head *buffer_list; }; @@ -4451,10 +4452,15 @@ xfs_btree_block_change_owner( /* modify the owner */ block = xfs_btree_get_block(cur, level, &bp); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { + if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner)) + return 0; block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner); - else + } else { + if (block->bb_u.s.bb_owner == cpu_to_be32(bbcoi->new_owner)) + return 0; block->bb_u.s.bb_owner = cpu_to_be32(bbcoi->new_owner); + } /* * If the block is a root block hosted in an inode, we might not have a @@ -4463,16 +4469,19 @@ xfs_btree_block_change_owner( * block is formatted into the on-disk inode fork. We still change it, * though, so everything is consistent in memory. */ - if (bp) { - if (cur->bc_tp) { - xfs_trans_ordered_buf(cur->bc_tp, bp); + if (!bp) { + ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(level == cur->bc_nlevels - 1); + return 0; + } + + if (cur->bc_tp) { + if (!xfs_trans_ordered_buf(cur->bc_tp, bp)) { xfs_btree_log_block(cur, bp, XFS_BB_OWNER); - } else { - xfs_buf_delwri_queue(bp, bbcoi->buffer_list); + return -EAGAIN; } } else { - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); - ASSERT(level == cur->bc_nlevels - 1); + xfs_buf_delwri_queue(bp, bbcoi->buffer_list); } return 0; @@ -4481,7 +4490,7 @@ xfs_btree_block_change_owner( int xfs_btree_change_owner( struct xfs_btree_cur *cur, - __uint64_t new_owner, + uint64_t new_owner, struct list_head *buffer_list) { struct xfs_btree_block_change_owner_info bbcoi; @@ -4585,7 +4594,7 @@ xfs_btree_simple_query_range( { union xfs_btree_rec *recp; union xfs_btree_key rec_key; - __int64_t diff; + int64_t diff; int stat; bool firstrec = true; int error; @@ -4682,8 +4691,8 @@ xfs_btree_overlapped_query_range( union xfs_btree_key *hkp; union xfs_btree_rec *recp; struct xfs_btree_block *block; - __int64_t ldiff; - __int64_t hdiff; + int64_t ldiff; + int64_t hdiff; int level; struct xfs_buf *bp; int i; @@ -4849,12 +4858,14 @@ xfs_btree_query_all( xfs_btree_query_range_fn fn, void *priv) { - union xfs_btree_irec low_rec; - union xfs_btree_irec high_rec; + union xfs_btree_key low_key; + union xfs_btree_key high_key; + + memset(&cur->bc_rec, 0, sizeof(cur->bc_rec)); + memset(&low_key, 0, sizeof(low_key)); + memset(&high_key, 0xFF, sizeof(high_key)); - memset(&low_rec, 0, sizeof(low_rec)); - memset(&high_rec, 0xFF, sizeof(high_rec)); - return xfs_btree_query_range(cur, &low_rec, &high_rec, fn, priv); + return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv); } /* diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 27bed08261c5..f2a88c3b1159 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -76,7 +76,7 @@ union xfs_btree_rec { #define XFS_BTNUM_RMAP ((xfs_btnum_t)XFS_BTNUM_RMAPi) #define XFS_BTNUM_REFC ((xfs_btnum_t)XFS_BTNUM_REFCi) -__uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); +uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum); /* * For logging record fields. @@ -150,20 +150,19 @@ struct xfs_btree_ops { union xfs_btree_rec *rec); /* difference between key value and cursor value */ - __int64_t (*key_diff)(struct xfs_btree_cur *cur, + int64_t (*key_diff)(struct xfs_btree_cur *cur, union xfs_btree_key *key); /* * Difference between key2 and key1 -- positive if key1 > key2, * negative if key1 < key2, and zero if equal. */ - __int64_t (*diff_two_keys)(struct xfs_btree_cur *cur, + int64_t (*diff_two_keys)(struct xfs_btree_cur *cur, union xfs_btree_key *key1, union xfs_btree_key *key2); const struct xfs_buf_ops *buf_ops; -#if defined(DEBUG) || defined(XFS_WARN) /* check that k1 is lower than k2 */ int (*keys_inorder)(struct xfs_btree_cur *cur, union xfs_btree_key *k1, @@ -173,7 +172,6 @@ struct xfs_btree_ops { int (*recs_inorder)(struct xfs_btree_cur *cur, union xfs_btree_rec *r1, union xfs_btree_rec *r2); -#endif }; /* @@ -213,11 +211,11 @@ typedef struct xfs_btree_cur union xfs_btree_irec bc_rec; /* current insert/search record value */ struct xfs_buf *bc_bufs[XFS_BTREE_MAXLEVELS]; /* buf ptr per level */ int bc_ptrs[XFS_BTREE_MAXLEVELS]; /* key/record # */ - __uint8_t bc_ra[XFS_BTREE_MAXLEVELS]; /* readahead bits */ + uint8_t bc_ra[XFS_BTREE_MAXLEVELS]; /* readahead bits */ #define XFS_BTCUR_LEFTRA 1 /* left sibling has been read-ahead */ #define XFS_BTCUR_RIGHTRA 2 /* right sibling has been read-ahead */ - __uint8_t bc_nlevels; /* number of levels in the tree */ - __uint8_t bc_blocklog; /* log2(blocksize) of btree blocks */ + uint8_t bc_nlevels; /* number of levels in the tree */ + uint8_t bc_blocklog; /* log2(blocksize) of btree blocks */ xfs_btnum_t bc_btnum; /* identifies which btree type */ int bc_statoff; /* offset of btre stats array */ union { @@ -235,7 +233,8 @@ typedef struct xfs_btree_cur short forksize; /* fork's inode space */ char whichfork; /* data or attr fork */ char flags; /* flags */ -#define XFS_BTCUR_BPRV_WASDEL 1 /* was delayed */ +#define XFS_BTCUR_BPRV_WASDEL (1<<0) /* was delayed */ +#define XFS_BTCUR_BPRV_INVALID_OWNER (1<<1) /* for ext swap */ } b; } bc_private; /* per-btree type data */ } xfs_btree_cur_t; @@ -330,7 +329,7 @@ xfs_btree_islastblock( */ void xfs_btree_offsets( - __int64_t fields, /* bitmask of fields */ + int64_t fields, /* bitmask of fields */ const short *offsets,/* table of field offsets */ int nbits, /* number of bits to inspect */ int *first, /* output: first byte offset */ @@ -408,7 +407,7 @@ int xfs_btree_new_iroot(struct xfs_btree_cur *, int *, int *); int xfs_btree_insert(struct xfs_btree_cur *, int *); int xfs_btree_delete(struct xfs_btree_cur *, int *); int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *); -int xfs_btree_change_owner(struct xfs_btree_cur *cur, __uint64_t new_owner, +int xfs_btree_change_owner(struct xfs_btree_cur *cur, uint64_t new_owner, struct list_head *buffer_list); /* @@ -434,7 +433,7 @@ static inline int xfs_btree_get_numrecs(struct xfs_btree_block *block) } static inline void xfs_btree_set_numrecs(struct xfs_btree_block *block, - __uint16_t numrecs) + uint16_t numrecs) { block->bb_numrecs = cpu_to_be16(numrecs); } @@ -506,4 +505,17 @@ int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, + struct xfs_btree_block *block); +union xfs_btree_key *xfs_btree_key_addr(struct xfs_btree_cur *cur, int n, + struct xfs_btree_block *block); +union xfs_btree_key *xfs_btree_high_key_addr(struct xfs_btree_cur *cur, int n, + struct xfs_btree_block *block); +union xfs_btree_ptr *xfs_btree_ptr_addr(struct xfs_btree_cur *cur, int n, + struct xfs_btree_block *block); +int xfs_btree_lookup_get_block(struct xfs_btree_cur *cur, int level, + union xfs_btree_ptr *pp, struct xfs_btree_block **blkp); +struct xfs_btree_block *xfs_btree_get_block(struct xfs_btree_cur *cur, + int level, struct xfs_buf **bpp); + #endif /* __XFS_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_cksum.h b/fs/xfs/libxfs/xfs_cksum.h index a416c7cb23ea..8211f48b98e6 100644 --- a/fs/xfs/libxfs/xfs_cksum.h +++ b/fs/xfs/libxfs/xfs_cksum.h @@ -1,7 +1,7 @@ #ifndef _XFS_CKSUM_H #define _XFS_CKSUM_H 1 -#define XFS_CRC_SEED (~(__uint32_t)0) +#define XFS_CRC_SEED (~(uint32_t)0) /* * Calculate the intermediate checksum for a buffer that has the CRC field @@ -9,11 +9,11 @@ * cksum_offset parameter. We do not modify the buffer during verification, * hence we have to split the CRC calculation across the cksum_offset. */ -static inline __uint32_t +static inline uint32_t xfs_start_cksum_safe(char *buffer, size_t length, unsigned long cksum_offset) { - __uint32_t zero = 0; - __uint32_t crc; + uint32_t zero = 0; + uint32_t crc; /* Calculate CRC up to the checksum. */ crc = crc32c(XFS_CRC_SEED, buffer, cksum_offset); @@ -30,7 +30,7 @@ xfs_start_cksum_safe(char *buffer, size_t length, unsigned long cksum_offset) * Fast CRC method where the buffer is modified. Callers must have exclusive * access to the buffer while the calculation takes place. */ -static inline __uint32_t +static inline uint32_t xfs_start_cksum_update(char *buffer, size_t length, unsigned long cksum_offset) { /* zero the CRC field */ @@ -48,7 +48,7 @@ xfs_start_cksum_update(char *buffer, size_t length, unsigned long cksum_offset) * so that it is consistent on disk. */ static inline __le32 -xfs_end_cksum(__uint32_t crc) +xfs_end_cksum(uint32_t crc) { return ~cpu_to_le32(crc); } @@ -62,7 +62,7 @@ xfs_end_cksum(__uint32_t crc) static inline void xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset) { - __uint32_t crc = xfs_start_cksum_update(buffer, length, cksum_offset); + uint32_t crc = xfs_start_cksum_update(buffer, length, cksum_offset); *(__le32 *)(buffer + cksum_offset) = xfs_end_cksum(crc); } @@ -73,7 +73,7 @@ xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset) static inline int xfs_verify_cksum(char *buffer, size_t length, unsigned long cksum_offset) { - __uint32_t crc = xfs_start_cksum_safe(buffer, length, cksum_offset); + uint32_t crc = xfs_start_cksum_safe(buffer, length, cksum_offset); return *(__le32 *)(buffer + cksum_offset) == xfs_end_cksum(crc); } diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 1bdf2888295b..6d4335815c3f 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -263,7 +263,7 @@ xfs_da3_node_read( err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp, which_fork, &xfs_da3_node_buf_ops); - if (!err && tp) { + if (!err && tp && *bpp) { struct xfs_da_blkinfo *info = (*bpp)->b_addr; int type; @@ -1282,7 +1282,7 @@ xfs_da3_fixhashpath( return; break; case XFS_DIR2_LEAFN_MAGIC: - lasthash = xfs_dir2_leafn_lasthash(dp, blk->bp, &count); + lasthash = xfs_dir2_leaf_lasthash(dp, blk->bp, &count); if (count == 0) return; break; @@ -1502,8 +1502,8 @@ xfs_da3_node_lookup_int( if (blk->magic == XFS_DIR2_LEAFN_MAGIC || blk->magic == XFS_DIR3_LEAFN_MAGIC) { blk->magic = XFS_DIR2_LEAFN_MAGIC; - blk->hashval = xfs_dir2_leafn_lasthash(args->dp, - blk->bp, NULL); + blk->hashval = xfs_dir2_leaf_lasthash(args->dp, + blk->bp, NULL); break; } @@ -1929,8 +1929,8 @@ xfs_da3_path_shift( blk->magic = XFS_DIR2_LEAFN_MAGIC; ASSERT(level == path->active-1); blk->index = 0; - blk->hashval = xfs_dir2_leafn_lasthash(args->dp, - blk->bp, NULL); + blk->hashval = xfs_dir2_leaf_lasthash(args->dp, + blk->bp, NULL); break; default: ASSERT(0); @@ -1952,7 +1952,7 @@ xfs_da3_path_shift( * This is implemented with some source-level loop unrolling. */ xfs_dahash_t -xfs_da_hashname(const __uint8_t *name, int namelen) +xfs_da_hashname(const uint8_t *name, int namelen) { xfs_dahash_t hash; diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index 4e29cb6a3627..ae6de17467f2 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -60,10 +60,10 @@ enum xfs_dacmp { */ typedef struct xfs_da_args { struct xfs_da_geometry *geo; /* da block geometry */ - const __uint8_t *name; /* string (maybe not NULL terminated) */ + const uint8_t *name; /* string (maybe not NULL terminated) */ int namelen; /* length of string (maybe no NULL) */ - __uint8_t filetype; /* filetype of inode for directories */ - __uint8_t *value; /* set of bytes (maybe contain NULLs) */ + uint8_t filetype; /* filetype of inode for directories */ + uint8_t *value; /* set of bytes (maybe contain NULLs) */ int valuelen; /* length of value */ int flags; /* argument flags (eg: ATTR_NOCREATE) */ xfs_dahash_t hashval; /* hash value of name */ @@ -207,7 +207,7 @@ int xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno, int xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno, struct xfs_buf *dead_buf); -uint xfs_da_hashname(const __uint8_t *name_string, int name_length); +uint xfs_da_hashname(const uint8_t *name_string, int name_length); enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args, const unsigned char *name, int len); diff --git a/fs/xfs/libxfs/xfs_da_format.c b/fs/xfs/libxfs/xfs_da_format.c index f1e8d4dbb600..6d77d1a8498a 100644 --- a/fs/xfs/libxfs/xfs_da_format.c +++ b/fs/xfs/libxfs/xfs_da_format.c @@ -49,7 +49,7 @@ xfs_dir3_sf_entsize( struct xfs_dir2_sf_hdr *hdr, int len) { - return xfs_dir2_sf_entsize(hdr, len) + sizeof(__uint8_t); + return xfs_dir2_sf_entsize(hdr, len) + sizeof(uint8_t); } static struct xfs_dir2_sf_entry * @@ -77,7 +77,7 @@ xfs_dir3_sf_nextentry( * not necessary. For non-filetype enable directories, the type is always * unknown and we never store the value. */ -static __uint8_t +static uint8_t xfs_dir2_sfe_get_ftype( struct xfs_dir2_sf_entry *sfep) { @@ -87,16 +87,16 @@ xfs_dir2_sfe_get_ftype( static void xfs_dir2_sfe_put_ftype( struct xfs_dir2_sf_entry *sfep, - __uint8_t ftype) + uint8_t ftype) { ASSERT(ftype < XFS_DIR3_FT_MAX); } -static __uint8_t +static uint8_t xfs_dir3_sfe_get_ftype( struct xfs_dir2_sf_entry *sfep) { - __uint8_t ftype; + uint8_t ftype; ftype = sfep->name[sfep->namelen]; if (ftype >= XFS_DIR3_FT_MAX) @@ -107,7 +107,7 @@ xfs_dir3_sfe_get_ftype( static void xfs_dir3_sfe_put_ftype( struct xfs_dir2_sf_entry *sfep, - __uint8_t ftype) + uint8_t ftype) { ASSERT(ftype < XFS_DIR3_FT_MAX); @@ -124,7 +124,7 @@ xfs_dir3_sfe_put_ftype( static xfs_ino_t xfs_dir2_sf_get_ino( struct xfs_dir2_sf_hdr *hdr, - __uint8_t *from) + uint8_t *from) { if (hdr->i8count) return get_unaligned_be64(from) & 0x00ffffffffffffffULL; @@ -135,7 +135,7 @@ xfs_dir2_sf_get_ino( static void xfs_dir2_sf_put_ino( struct xfs_dir2_sf_hdr *hdr, - __uint8_t *to, + uint8_t *to, xfs_ino_t ino) { ASSERT((ino & 0xff00000000000000ULL) == 0); @@ -225,7 +225,7 @@ xfs_dir3_sfe_put_ino( #define XFS_DIR3_DATA_ENTSIZE(n) \ round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) + \ - sizeof(xfs_dir2_data_off_t) + sizeof(__uint8_t)), \ + sizeof(xfs_dir2_data_off_t) + sizeof(uint8_t)), \ XFS_DIR2_DATA_ALIGN) static int @@ -242,7 +242,7 @@ xfs_dir3_data_entsize( return XFS_DIR3_DATA_ENTSIZE(n); } -static __uint8_t +static uint8_t xfs_dir2_data_get_ftype( struct xfs_dir2_data_entry *dep) { @@ -252,16 +252,16 @@ xfs_dir2_data_get_ftype( static void xfs_dir2_data_put_ftype( struct xfs_dir2_data_entry *dep, - __uint8_t ftype) + uint8_t ftype) { ASSERT(ftype < XFS_DIR3_FT_MAX); } -static __uint8_t +static uint8_t xfs_dir3_data_get_ftype( struct xfs_dir2_data_entry *dep) { - __uint8_t ftype = dep->name[dep->namelen]; + uint8_t ftype = dep->name[dep->namelen]; if (ftype >= XFS_DIR3_FT_MAX) return XFS_DIR3_FT_UNKNOWN; @@ -271,7 +271,7 @@ xfs_dir3_data_get_ftype( static void xfs_dir3_data_put_ftype( struct xfs_dir2_data_entry *dep, - __uint8_t type) + uint8_t type) { ASSERT(type < XFS_DIR3_FT_MAX); ASSERT(dep->namelen != 0); diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h index 9a492a9e19bd..3771edcb301d 100644 --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -111,11 +111,11 @@ struct xfs_da3_intnode { * appropriate. */ struct xfs_da3_icnode_hdr { - __uint32_t forw; - __uint32_t back; - __uint16_t magic; - __uint16_t count; - __uint16_t level; + uint32_t forw; + uint32_t back; + uint16_t magic; + uint16_t count; + uint16_t level; }; /* @@ -187,14 +187,14 @@ struct xfs_da3_icnode_hdr { /* * Byte offset in data block and shortform entry. */ -typedef __uint16_t xfs_dir2_data_off_t; +typedef uint16_t xfs_dir2_data_off_t; #define NULLDATAOFF 0xffffU typedef uint xfs_dir2_data_aoff_t; /* argument form */ /* * Offset in data space of a data entry. */ -typedef __uint32_t xfs_dir2_dataptr_t; +typedef uint32_t xfs_dir2_dataptr_t; #define XFS_DIR2_MAX_DATAPTR ((xfs_dir2_dataptr_t)0xffffffff) #define XFS_DIR2_NULL_DATAPTR ((xfs_dir2_dataptr_t)0) @@ -206,7 +206,7 @@ typedef xfs_off_t xfs_dir2_off_t; /* * Directory block number (logical dirblk in file) */ -typedef __uint32_t xfs_dir2_db_t; +typedef uint32_t xfs_dir2_db_t; #define XFS_INO32_SIZE 4 #define XFS_INO64_SIZE 8 @@ -226,9 +226,9 @@ typedef __uint32_t xfs_dir2_db_t; * over them. */ typedef struct xfs_dir2_sf_hdr { - __uint8_t count; /* count of entries */ - __uint8_t i8count; /* count of 8-byte inode #s */ - __uint8_t parent[8]; /* parent dir inode number */ + uint8_t count; /* count of entries */ + uint8_t i8count; /* count of 8-byte inode #s */ + uint8_t parent[8]; /* parent dir inode number */ } __packed xfs_dir2_sf_hdr_t; typedef struct xfs_dir2_sf_entry { @@ -447,11 +447,11 @@ struct xfs_dir3_leaf_hdr { }; struct xfs_dir3_icleaf_hdr { - __uint32_t forw; - __uint32_t back; - __uint16_t magic; - __uint16_t count; - __uint16_t stale; + uint32_t forw; + uint32_t back; + uint16_t magic; + uint16_t count; + uint16_t stale; }; /* @@ -538,10 +538,10 @@ struct xfs_dir3_free { * xfs_dir3_free_hdr_from_disk/xfs_dir3_free_hdr_to_disk. */ struct xfs_dir3_icfree_hdr { - __uint32_t magic; - __uint32_t firstdb; - __uint32_t nvalid; - __uint32_t nused; + uint32_t magic; + uint32_t firstdb; + uint32_t nvalid; + uint32_t nused; }; @@ -632,10 +632,10 @@ typedef struct xfs_attr_shortform { __u8 padding; } hdr; struct xfs_attr_sf_entry { - __uint8_t namelen; /* actual length of name (no NULL) */ - __uint8_t valuelen; /* actual length of value (no NULL) */ - __uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ - __uint8_t nameval[1]; /* name & value bytes concatenated */ + uint8_t namelen; /* actual length of name (no NULL) */ + uint8_t valuelen; /* actual length of value (no NULL) */ + uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ + uint8_t nameval[1]; /* name & value bytes concatenated */ } list[1]; /* variable sized array */ } xfs_attr_shortform_t; @@ -725,22 +725,22 @@ struct xfs_attr3_leafblock { * incore, neutral version of the attribute leaf header */ struct xfs_attr3_icleaf_hdr { - __uint32_t forw; - __uint32_t back; - __uint16_t magic; - __uint16_t count; - __uint16_t usedbytes; + uint32_t forw; + uint32_t back; + uint16_t magic; + uint16_t count; + uint16_t usedbytes; /* * firstused is 32-bit here instead of 16-bit like the on-disk variant * to support maximum fsb size of 64k without overflow issues throughout * the attr code. Instead, the overflow condition is handled on * conversion to/from disk. */ - __uint32_t firstused; + uint32_t firstused; __u8 holes; struct { - __uint16_t base; - __uint16_t size; + uint16_t base; + uint16_t size; } freemap[XFS_ATTR_LEAF_MAPSIZE]; }; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 5c2929f94bd3..072ebfe1d6ae 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -240,23 +240,19 @@ xfs_defer_trans_abort( STATIC int xfs_defer_trans_roll( struct xfs_trans **tp, - struct xfs_defer_ops *dop, - struct xfs_inode *ip) + struct xfs_defer_ops *dop) { int i; int error; - /* Log all the joined inodes except the one we passed in. */ - for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) { - if (dop->dop_inodes[i] == ip) - continue; + /* Log all the joined inodes. */ + for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE); - } trace_xfs_defer_trans_roll((*tp)->t_mountp, dop); /* Roll the transaction. */ - error = xfs_trans_roll(tp, ip); + error = xfs_trans_roll(tp); if (error) { trace_xfs_defer_trans_roll_error((*tp)->t_mountp, dop, error); xfs_defer_trans_abort(*tp, dop, error); @@ -264,12 +260,9 @@ xfs_defer_trans_roll( } dop->dop_committed = true; - /* Rejoin the joined inodes except the one we passed in. */ - for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) { - if (dop->dop_inodes[i] == ip) - continue; + /* Rejoin the joined inodes. */ + for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0); - } return error; } @@ -284,11 +277,10 @@ xfs_defer_has_unfinished_work( /* * Add this inode to the deferred op. Each joined inode is relogged - * each time we roll the transaction, in addition to any inode passed - * to xfs_defer_finish(). + * each time we roll the transaction. */ int -xfs_defer_join( +xfs_defer_ijoin( struct xfs_defer_ops *dop, struct xfs_inode *ip) { @@ -317,8 +309,7 @@ xfs_defer_join( int xfs_defer_finish( struct xfs_trans **tp, - struct xfs_defer_ops *dop, - struct xfs_inode *ip) + struct xfs_defer_ops *dop) { struct xfs_defer_pending *dfp; struct list_head *li; @@ -337,7 +328,7 @@ xfs_defer_finish( xfs_defer_intake_work(*tp, dop); /* Roll the transaction. */ - error = xfs_defer_trans_roll(tp, dop, ip); + error = xfs_defer_trans_roll(tp, dop); if (error) goto out; diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index f6e93ef0bffe..d4f046dd44bd 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -72,12 +72,11 @@ struct xfs_defer_ops { void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type, struct list_head *h); -int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop, - struct xfs_inode *ip); +int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop); void xfs_defer_cancel(struct xfs_defer_ops *dop); void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp); bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop); -int xfs_defer_join(struct xfs_defer_ops *dop, struct xfs_inode *ip); +int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip); /* Description of a deferred type. */ struct xfs_defer_op_type { diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 2f389d366e93..ccf9783fd3f0 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -218,8 +218,7 @@ xfs_dir_ino_validate( agblkno != 0 && ioff < (1 << mp->m_sb.sb_inopblog) && XFS_AGINO_TO_INO(mp, agno, agino) == ino; - if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE, - XFS_RANDOM_DIR_INO_VALIDATE))) { + if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE))) { xfs_warn(mp, "Invalid inode number 0x%Lx", (unsigned long long) ino); XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp); diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h index d6e6d9d16f6c..21c8f8bf94d5 100644 --- a/fs/xfs/libxfs/xfs_dir2.h +++ b/fs/xfs/libxfs/xfs_dir2.h @@ -47,9 +47,9 @@ struct xfs_dir_ops { struct xfs_dir2_sf_entry * (*sf_nextentry)(struct xfs_dir2_sf_hdr *hdr, struct xfs_dir2_sf_entry *sfep); - __uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep); + uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep); void (*sf_put_ftype)(struct xfs_dir2_sf_entry *sfep, - __uint8_t ftype); + uint8_t ftype); xfs_ino_t (*sf_get_ino)(struct xfs_dir2_sf_hdr *hdr, struct xfs_dir2_sf_entry *sfep); void (*sf_put_ino)(struct xfs_dir2_sf_hdr *hdr, @@ -60,9 +60,9 @@ struct xfs_dir_ops { xfs_ino_t ino); int (*data_entsize)(int len); - __uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep); + uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep); void (*data_put_ftype)(struct xfs_dir2_data_entry *dep, - __uint8_t ftype); + uint8_t ftype); __be16 * (*data_entry_tag_p)(struct xfs_dir2_data_entry *dep); struct xfs_dir2_data_free * (*data_bestfree_p)(struct xfs_dir2_data_hdr *hdr); diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index aa17cb788946..43c902f7a68d 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -139,7 +139,7 @@ xfs_dir3_block_read( err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp, XFS_DATA_FORK, &xfs_dir3_block_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index d478065b9544..8727a43115ef 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -136,6 +136,8 @@ __xfs_dir3_data_check( */ if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { XFS_WANT_CORRUPTED_RETURN(mp, lastfree == 0); + XFS_WANT_CORRUPTED_RETURN(mp, endp >= + p + be16_to_cpu(dup->length)); XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) == (char *)dup - (char *)hdr); @@ -164,6 +166,8 @@ __xfs_dir3_data_check( XFS_WANT_CORRUPTED_RETURN(mp, dep->namelen != 0); XFS_WANT_CORRUPTED_RETURN(mp, !xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber))); + XFS_WANT_CORRUPTED_RETURN(mp, endp >= + p + ops->data_entsize(dep->namelen)); XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(*ops->data_entry_tag_p(dep)) == (char *)dep - (char *)hdr); diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index b887fb2a2bcf..27297a689d9c 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -145,7 +145,7 @@ xfs_dir3_leaf_check_int( static bool xfs_dir3_leaf_verify( struct xfs_buf *bp, - __uint16_t magic) + uint16_t magic) { struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_dir2_leaf *leaf = bp->b_addr; @@ -154,7 +154,7 @@ xfs_dir3_leaf_verify( if (xfs_sb_version_hascrc(&mp->m_sb)) { struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr; - __uint16_t magic3; + uint16_t magic3; magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC : XFS_DIR3_LEAFN_MAGIC; @@ -178,7 +178,7 @@ xfs_dir3_leaf_verify( static void __read_verify( struct xfs_buf *bp, - __uint16_t magic) + uint16_t magic) { struct xfs_mount *mp = bp->b_target->bt_mount; @@ -195,7 +195,7 @@ __read_verify( static void __write_verify( struct xfs_buf *bp, - __uint16_t magic) + uint16_t magic) { struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_buf_log_item *bip = bp->b_fspriv; @@ -256,7 +256,7 @@ const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = { .verify_write = xfs_dir3_leafn_write_verify, }; -static int +int xfs_dir3_leaf_read( struct xfs_trans *tp, struct xfs_inode *dp, @@ -268,7 +268,7 @@ xfs_dir3_leaf_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF); return err; } @@ -285,7 +285,7 @@ xfs_dir3_leafn_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF); return err; } @@ -299,7 +299,7 @@ xfs_dir3_leaf_init( struct xfs_trans *tp, struct xfs_buf *bp, xfs_ino_t owner, - __uint16_t type) + uint16_t type) { struct xfs_dir2_leaf *leaf = bp->b_addr; @@ -343,7 +343,7 @@ xfs_dir3_leaf_get_buf( xfs_da_args_t *args, xfs_dir2_db_t bno, struct xfs_buf **bpp, - __uint16_t magic) + uint16_t magic) { struct xfs_inode *dp = args->dp; struct xfs_trans *tp = args->trans; diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index bbd1238852b3..682e2bf370c7 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -528,7 +528,7 @@ xfs_dir2_free_hdr_check( * Stale entries are ok. */ xfs_dahash_t /* hash value */ -xfs_dir2_leafn_lasthash( +xfs_dir2_leaf_lasthash( struct xfs_inode *dp, struct xfs_buf *bp, /* leaf buffer */ int *count) /* count of entries in leaf */ @@ -540,7 +540,9 @@ xfs_dir2_leafn_lasthash( dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf); ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC || - leafhdr.magic == XFS_DIR3_LEAFN_MAGIC); + leafhdr.magic == XFS_DIR3_LEAFN_MAGIC || + leafhdr.magic == XFS_DIR2_LEAF1_MAGIC || + leafhdr.magic == XFS_DIR3_LEAF1_MAGIC); if (count) *count = leafhdr.count; @@ -1405,8 +1407,8 @@ xfs_dir2_leafn_split( /* * Update last hashval in each block since we added the name. */ - oldblk->hashval = xfs_dir2_leafn_lasthash(dp, oldblk->bp, NULL); - newblk->hashval = xfs_dir2_leafn_lasthash(dp, newblk->bp, NULL); + oldblk->hashval = xfs_dir2_leaf_lasthash(dp, oldblk->bp, NULL); + newblk->hashval = xfs_dir2_leaf_lasthash(dp, newblk->bp, NULL); xfs_dir3_leaf_check(dp, oldblk->bp); xfs_dir3_leaf_check(dp, newblk->bp); return error; diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h index 39f8604f764e..4badd26c47e6 100644 --- a/fs/xfs/libxfs/xfs_dir2_priv.h +++ b/fs/xfs/libxfs/xfs_dir2_priv.h @@ -58,6 +58,8 @@ extern int xfs_dir3_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno, struct xfs_buf **bpp); /* xfs_dir2_leaf.c */ +extern int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp, + xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp); extern int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp, xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp); extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args, @@ -69,7 +71,7 @@ extern void xfs_dir3_leaf_compact_x1(struct xfs_dir3_icleaf_hdr *leafhdr, struct xfs_dir2_leaf_entry *ents, int *indexp, int *lowstalep, int *highstalep, int *lowlogp, int *highlogp); extern int xfs_dir3_leaf_get_buf(struct xfs_da_args *args, xfs_dir2_db_t bno, - struct xfs_buf **bpp, __uint16_t magic); + struct xfs_buf **bpp, uint16_t magic); extern void xfs_dir3_leaf_log_ents(struct xfs_da_args *args, struct xfs_buf *bp, int first, int last); extern void xfs_dir3_leaf_log_header(struct xfs_da_args *args, @@ -93,7 +95,7 @@ extern bool xfs_dir3_leaf_check_int(struct xfs_mount *mp, struct xfs_inode *dp, /* xfs_dir2_node.c */ extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args, struct xfs_buf *lbp); -extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_inode *dp, +extern xfs_dahash_t xfs_dir2_leaf_lasthash(struct xfs_inode *dp, struct xfs_buf *bp, int *count); extern int xfs_dir2_leafn_lookup_int(struct xfs_buf *bp, struct xfs_da_args *args, int *indexp, @@ -128,7 +130,7 @@ extern int xfs_dir2_sf_replace(struct xfs_da_args *args); extern int xfs_dir2_sf_verify(struct xfs_inode *ip); /* xfs_dir2_readdir.c */ -extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx, - size_t bufsize); +extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp, + struct dir_context *ctx, size_t bufsize); #endif /* __XFS_DIR2_PRIV_H__ */ diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index e84af093b2ab..be8b9755f66a 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -647,7 +647,7 @@ xfs_dir2_sf_verify( int offset; int size; int error; - __uint8_t filetype; + uint8_t filetype; ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL); /* diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index a1dccd8d96bc..23229f0c5b15 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -103,8 +103,8 @@ struct xfs_ifork; * Must be padded to 64 bit alignment. */ typedef struct xfs_sb { - __uint32_t sb_magicnum; /* magic number == XFS_SB_MAGIC */ - __uint32_t sb_blocksize; /* logical block size, bytes */ + uint32_t sb_magicnum; /* magic number == XFS_SB_MAGIC */ + uint32_t sb_blocksize; /* logical block size, bytes */ xfs_rfsblock_t sb_dblocks; /* number of data blocks */ xfs_rfsblock_t sb_rblocks; /* number of realtime blocks */ xfs_rtblock_t sb_rextents; /* number of realtime extents */ @@ -118,45 +118,45 @@ typedef struct xfs_sb { xfs_agnumber_t sb_agcount; /* number of allocation groups */ xfs_extlen_t sb_rbmblocks; /* number of rt bitmap blocks */ xfs_extlen_t sb_logblocks; /* number of log blocks */ - __uint16_t sb_versionnum; /* header version == XFS_SB_VERSION */ - __uint16_t sb_sectsize; /* volume sector size, bytes */ - __uint16_t sb_inodesize; /* inode size, bytes */ - __uint16_t sb_inopblock; /* inodes per block */ + uint16_t sb_versionnum; /* header version == XFS_SB_VERSION */ + uint16_t sb_sectsize; /* volume sector size, bytes */ + uint16_t sb_inodesize; /* inode size, bytes */ + uint16_t sb_inopblock; /* inodes per block */ char sb_fname[12]; /* file system name */ - __uint8_t sb_blocklog; /* log2 of sb_blocksize */ - __uint8_t sb_sectlog; /* log2 of sb_sectsize */ - __uint8_t sb_inodelog; /* log2 of sb_inodesize */ - __uint8_t sb_inopblog; /* log2 of sb_inopblock */ - __uint8_t sb_agblklog; /* log2 of sb_agblocks (rounded up) */ - __uint8_t sb_rextslog; /* log2 of sb_rextents */ - __uint8_t sb_inprogress; /* mkfs is in progress, don't mount */ - __uint8_t sb_imax_pct; /* max % of fs for inode space */ + uint8_t sb_blocklog; /* log2 of sb_blocksize */ + uint8_t sb_sectlog; /* log2 of sb_sectsize */ + uint8_t sb_inodelog; /* log2 of sb_inodesize */ + uint8_t sb_inopblog; /* log2 of sb_inopblock */ + uint8_t sb_agblklog; /* log2 of sb_agblocks (rounded up) */ + uint8_t sb_rextslog; /* log2 of sb_rextents */ + uint8_t sb_inprogress; /* mkfs is in progress, don't mount */ + uint8_t sb_imax_pct; /* max % of fs for inode space */ /* statistics */ /* * These fields must remain contiguous. If you really * want to change their layout, make sure you fix the * code in xfs_trans_apply_sb_deltas(). */ - __uint64_t sb_icount; /* allocated inodes */ - __uint64_t sb_ifree; /* free inodes */ - __uint64_t sb_fdblocks; /* free data blocks */ - __uint64_t sb_frextents; /* free realtime extents */ + uint64_t sb_icount; /* allocated inodes */ + uint64_t sb_ifree; /* free inodes */ + uint64_t sb_fdblocks; /* free data blocks */ + uint64_t sb_frextents; /* free realtime extents */ /* * End contiguous fields. */ xfs_ino_t sb_uquotino; /* user quota inode */ xfs_ino_t sb_gquotino; /* group quota inode */ - __uint16_t sb_qflags; /* quota flags */ - __uint8_t sb_flags; /* misc. flags */ - __uint8_t sb_shared_vn; /* shared version number */ + uint16_t sb_qflags; /* quota flags */ + uint8_t sb_flags; /* misc. flags */ + uint8_t sb_shared_vn; /* shared version number */ xfs_extlen_t sb_inoalignmt; /* inode chunk alignment, fsblocks */ - __uint32_t sb_unit; /* stripe or raid unit */ - __uint32_t sb_width; /* stripe or raid width */ - __uint8_t sb_dirblklog; /* log2 of dir block size (fsbs) */ - __uint8_t sb_logsectlog; /* log2 of the log sector size */ - __uint16_t sb_logsectsize; /* sector size for the log, bytes */ - __uint32_t sb_logsunit; /* stripe unit size for the log */ - __uint32_t sb_features2; /* additional feature bits */ + uint32_t sb_unit; /* stripe or raid unit */ + uint32_t sb_width; /* stripe or raid width */ + uint8_t sb_dirblklog; /* log2 of dir block size (fsbs) */ + uint8_t sb_logsectlog; /* log2 of the log sector size */ + uint16_t sb_logsectsize; /* sector size for the log, bytes */ + uint32_t sb_logsunit; /* stripe unit size for the log */ + uint32_t sb_features2; /* additional feature bits */ /* * bad features2 field as a result of failing to pad the sb structure to @@ -167,17 +167,17 @@ typedef struct xfs_sb { * the value in sb_features2 when formatting the incore superblock to * the disk buffer. */ - __uint32_t sb_bad_features2; + uint32_t sb_bad_features2; /* version 5 superblock fields start here */ /* feature masks */ - __uint32_t sb_features_compat; - __uint32_t sb_features_ro_compat; - __uint32_t sb_features_incompat; - __uint32_t sb_features_log_incompat; + uint32_t sb_features_compat; + uint32_t sb_features_ro_compat; + uint32_t sb_features_incompat; + uint32_t sb_features_log_incompat; - __uint32_t sb_crc; /* superblock crc */ + uint32_t sb_crc; /* superblock crc */ xfs_extlen_t sb_spino_align; /* sparse inode chunk alignment */ xfs_ino_t sb_pquotino; /* project quota inode */ @@ -449,7 +449,7 @@ static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp) static inline bool xfs_sb_has_compat_feature( struct xfs_sb *sbp, - __uint32_t feature) + uint32_t feature) { return (sbp->sb_features_compat & feature) != 0; } @@ -465,7 +465,7 @@ xfs_sb_has_compat_feature( static inline bool xfs_sb_has_ro_compat_feature( struct xfs_sb *sbp, - __uint32_t feature) + uint32_t feature) { return (sbp->sb_features_ro_compat & feature) != 0; } @@ -482,7 +482,7 @@ xfs_sb_has_ro_compat_feature( static inline bool xfs_sb_has_incompat_feature( struct xfs_sb *sbp, - __uint32_t feature) + uint32_t feature) { return (sbp->sb_features_incompat & feature) != 0; } @@ -492,7 +492,7 @@ xfs_sb_has_incompat_feature( static inline bool xfs_sb_has_incompat_log_feature( struct xfs_sb *sbp, - __uint32_t feature) + uint32_t feature) { return (sbp->sb_features_log_incompat & feature) != 0; } @@ -594,8 +594,8 @@ xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino) */ #define XFS_FSB_TO_B(mp,fsbno) ((xfs_fsize_t)(fsbno) << (mp)->m_sb.sb_blocklog) #define XFS_B_TO_FSB(mp,b) \ - ((((__uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog) -#define XFS_B_TO_FSBT(mp,b) (((__uint64_t)(b)) >> (mp)->m_sb.sb_blocklog) + ((((uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog) +#define XFS_B_TO_FSBT(mp,b) (((uint64_t)(b)) >> (mp)->m_sb.sb_blocklog) #define XFS_B_FSB_OFFSET(mp,b) ((b) & (mp)->m_blockmask) /* @@ -1072,7 +1072,7 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) * next agno_log bits - ag number * high agno_log-agblklog-inopblog bits - 0 */ -#define XFS_INO_MASK(k) (__uint32_t)((1ULL << (k)) - 1) +#define XFS_INO_MASK(k) (uint32_t)((1ULL << (k)) - 1) #define XFS_INO_OFFSET_BITS(mp) (mp)->m_sb.sb_inopblog #define XFS_INO_AGBNO_BITS(mp) (mp)->m_sb.sb_agblklog #define XFS_INO_AGINO_BITS(mp) (mp)->m_agino_log @@ -1211,6 +1211,7 @@ struct xfs_dsymlink_hdr { #define XFS_SYMLINK_CRC_OFF offsetof(struct xfs_dsymlink_hdr, sl_crc) +#define XFS_SYMLINK_MAXLEN 1024 /* * The maximum pathlen is 1024 bytes. Since the minimum file system * blocksize is 512 bytes, we can get a max of 3 extents back from @@ -1269,16 +1270,16 @@ typedef __be32 xfs_alloc_ptr_t; #define XFS_FIBT_MAGIC 0x46494254 /* 'FIBT' */ #define XFS_FIBT_CRC_MAGIC 0x46494233 /* 'FIB3' */ -typedef __uint64_t xfs_inofree_t; +typedef uint64_t xfs_inofree_t; #define XFS_INODES_PER_CHUNK (NBBY * sizeof(xfs_inofree_t)) #define XFS_INODES_PER_CHUNK_LOG (XFS_NBBYLOG + 3) #define XFS_INOBT_ALL_FREE ((xfs_inofree_t)-1) #define XFS_INOBT_MASK(i) ((xfs_inofree_t)1 << (i)) #define XFS_INOBT_HOLEMASK_FULL 0 /* holemask for full chunk */ -#define XFS_INOBT_HOLEMASK_BITS (NBBY * sizeof(__uint16_t)) +#define XFS_INOBT_HOLEMASK_BITS (NBBY * sizeof(uint16_t)) #define XFS_INODES_PER_HOLEMASK_BIT \ - (XFS_INODES_PER_CHUNK / (NBBY * sizeof(__uint16_t))) + (XFS_INODES_PER_CHUNK / (NBBY * sizeof(uint16_t))) static inline xfs_inofree_t xfs_inobt_maskn(int i, int n) { @@ -1312,9 +1313,9 @@ typedef struct xfs_inobt_rec { typedef struct xfs_inobt_rec_incore { xfs_agino_t ir_startino; /* starting inode number */ - __uint16_t ir_holemask; /* hole mask for sparse chunks */ - __uint8_t ir_count; /* total inode count */ - __uint8_t ir_freecount; /* count of free inodes (set bits) */ + uint16_t ir_holemask; /* hole mask for sparse chunks */ + uint8_t ir_count; /* total inode count */ + uint8_t ir_freecount; /* count of free inodes (set bits) */ xfs_inofree_t ir_free; /* free inode mask */ } xfs_inobt_rec_incore_t; @@ -1397,15 +1398,15 @@ struct xfs_rmap_rec { * rm_offset:54-60 aren't used and should be zero * rm_offset:0-53 is the block offset within the inode */ -#define XFS_RMAP_OFF_ATTR_FORK ((__uint64_t)1ULL << 63) -#define XFS_RMAP_OFF_BMBT_BLOCK ((__uint64_t)1ULL << 62) -#define XFS_RMAP_OFF_UNWRITTEN ((__uint64_t)1ULL << 61) +#define XFS_RMAP_OFF_ATTR_FORK ((uint64_t)1ULL << 63) +#define XFS_RMAP_OFF_BMBT_BLOCK ((uint64_t)1ULL << 62) +#define XFS_RMAP_OFF_UNWRITTEN ((uint64_t)1ULL << 61) -#define XFS_RMAP_LEN_MAX ((__uint32_t)~0U) +#define XFS_RMAP_LEN_MAX ((uint32_t)~0U) #define XFS_RMAP_OFF_FLAGS (XFS_RMAP_OFF_ATTR_FORK | \ XFS_RMAP_OFF_BMBT_BLOCK | \ XFS_RMAP_OFF_UNWRITTEN) -#define XFS_RMAP_OFF_MASK ((__uint64_t)0x3FFFFFFFFFFFFFULL) +#define XFS_RMAP_OFF_MASK ((uint64_t)0x3FFFFFFFFFFFFFULL) #define XFS_RMAP_OFF(off) ((off) & XFS_RMAP_OFF_MASK) @@ -1431,8 +1432,8 @@ struct xfs_rmap_rec { struct xfs_rmap_irec { xfs_agblock_t rm_startblock; /* extent start block */ xfs_extlen_t rm_blockcount; /* extent length */ - __uint64_t rm_owner; /* extent owner */ - __uint64_t rm_offset; /* offset within the owner */ + uint64_t rm_owner; /* extent owner */ + uint64_t rm_offset; /* offset within the owner */ unsigned int rm_flags; /* state flags */ }; @@ -1544,11 +1545,11 @@ typedef struct xfs_bmbt_rec { __be64 l0, l1; } xfs_bmbt_rec_t; -typedef __uint64_t xfs_bmbt_rec_base_t; /* use this for casts */ +typedef uint64_t xfs_bmbt_rec_base_t; /* use this for casts */ typedef xfs_bmbt_rec_t xfs_bmdr_rec_t; typedef struct xfs_bmbt_rec_host { - __uint64_t l0, l1; + uint64_t l0, l1; } xfs_bmbt_rec_host_t; /* diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 095bdf049a3f..8c61f21535d4 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -302,10 +302,10 @@ typedef struct xfs_bstat { * and using two 16bit values to hold new 32bit projid was choosen * to retain compatibility with "old" filesystems). */ -static inline __uint32_t +static inline uint32_t bstat_get_projid(struct xfs_bstat *bs) { - return (__uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo; + return (uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo; } /* @@ -446,19 +446,15 @@ typedef struct xfs_handle { } xfs_handle_t; #define ha_fsid ha_u._ha_fsid -#define XFS_HSIZE(handle) (((char *) &(handle).ha_fid.fid_pad \ - - (char *) &(handle)) \ - + (handle).ha_fid.fid_len) - /* * Structure passed to XFS_IOC_SWAPEXT */ typedef struct xfs_swapext { - __int64_t sx_version; /* version */ + int64_t sx_version; /* version */ #define XFS_SX_VERSION 0 - __int64_t sx_fdtarget; /* fd of target file */ - __int64_t sx_fdtmp; /* fd of tmp file */ + int64_t sx_fdtarget; /* fd of target file */ + int64_t sx_fdtmp; /* fd of tmp file */ xfs_off_t sx_offset; /* offset into file */ xfs_off_t sx_length; /* leng from offset */ char sx_pad[16]; /* pad space, unused */ @@ -546,7 +542,7 @@ typedef struct xfs_swapext #define XFS_IOC_ATTRLIST_BY_HANDLE _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq) #define XFS_IOC_ATTRMULTI_BY_HANDLE _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq) #define XFS_IOC_FSGEOMETRY _IOR ('X', 124, struct xfs_fsop_geom) -#define XFS_IOC_GOINGDOWN _IOR ('X', 125, __uint32_t) +#define XFS_IOC_GOINGDOWN _IOR ('X', 125, uint32_t) /* XFS_IOC_GETFSUUID ---------- deprecated 140 */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d41ade5d293e..dfd643909f85 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -46,7 +46,7 @@ /* * Allocation group level functions. */ -static inline int +int xfs_ialloc_cluster_alignment( struct xfs_mount *mp) { @@ -98,24 +98,15 @@ xfs_inobt_update( return xfs_btree_update(cur, &rec); } -/* - * Get the data from the pointed-to record. - */ -int /* error */ -xfs_inobt_get_rec( - struct xfs_btree_cur *cur, /* btree cursor */ - xfs_inobt_rec_incore_t *irec, /* btree record */ - int *stat) /* output: success/failure */ +/* Convert on-disk btree record to incore inobt record. */ +void +xfs_inobt_btrec_to_irec( + struct xfs_mount *mp, + union xfs_btree_rec *rec, + struct xfs_inobt_rec_incore *irec) { - union xfs_btree_rec *rec; - int error; - - error = xfs_btree_get_rec(cur, &rec, stat); - if (error || *stat == 0) - return error; - irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino); - if (xfs_sb_version_hassparseinodes(&cur->bc_mp->m_sb)) { + if (xfs_sb_version_hassparseinodes(&mp->m_sb)) { irec->ir_holemask = be16_to_cpu(rec->inobt.ir_u.sp.ir_holemask); irec->ir_count = rec->inobt.ir_u.sp.ir_count; irec->ir_freecount = rec->inobt.ir_u.sp.ir_freecount; @@ -130,6 +121,25 @@ xfs_inobt_get_rec( be32_to_cpu(rec->inobt.ir_u.f.ir_freecount); } irec->ir_free = be64_to_cpu(rec->inobt.ir_free); +} + +/* + * Get the data from the pointed-to record. + */ +int +xfs_inobt_get_rec( + struct xfs_btree_cur *cur, + struct xfs_inobt_rec_incore *irec, + int *stat) +{ + union xfs_btree_rec *rec; + int error; + + error = xfs_btree_get_rec(cur, &rec, stat); + if (error || *stat == 0) + return error; + + xfs_inobt_btrec_to_irec(cur->bc_mp, rec, irec); return 0; } @@ -140,9 +150,9 @@ xfs_inobt_get_rec( STATIC int xfs_inobt_insert_rec( struct xfs_btree_cur *cur, - __uint16_t holemask, - __uint8_t count, - __int32_t freecount, + uint16_t holemask, + uint8_t count, + int32_t freecount, xfs_inofree_t free, int *stat) { @@ -368,8 +378,6 @@ xfs_ialloc_inode_init( * transaction and pin the log appropriately. */ xfs_trans_ordered_buf(tp, fbuf); - xfs_trans_log_buf(tp, fbuf, 0, - BBTOB(fbuf->b_length) - 1); } } else { fbuf->b_flags |= XBF_DONE; @@ -1123,6 +1131,7 @@ xfs_dialloc_ag_inobt( int error; int offset; int i, j; + int searchdistance = 10; pag = xfs_perag_get(mp, agno); @@ -1149,7 +1158,6 @@ xfs_dialloc_ag_inobt( if (pagno == agno) { int doneleft; /* done, to the left */ int doneright; /* done, to the right */ - int searchdistance = 10; error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i); if (error) @@ -1210,21 +1218,9 @@ xfs_dialloc_ag_inobt( /* * Loop until we find an inode chunk with a free inode. */ - while (!doneleft || !doneright) { + while (--searchdistance > 0 && (!doneleft || !doneright)) { int useleft; /* using left inode chunk this time */ - if (!--searchdistance) { - /* - * Not in range - save last search - * location and allocate a new inode - */ - xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); - pag->pagl_leftrec = trec.ir_startino; - pag->pagl_rightrec = rec.ir_startino; - pag->pagl_pagino = pagino; - goto newino; - } - /* figure out the closer block if both are valid. */ if (!doneleft && !doneright) { useleft = pagino - @@ -1236,13 +1232,13 @@ xfs_dialloc_ag_inobt( /* free inodes to the left? */ if (useleft && trec.ir_freecount) { - rec = trec; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); cur = tcur; pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; + rec = trec; goto alloc_inode; } @@ -1268,26 +1264,37 @@ xfs_dialloc_ag_inobt( goto error1; } - /* - * We've reached the end of the btree. because - * we are only searching a small chunk of the - * btree each search, there is obviously free - * inodes closer to the parent inode than we - * are now. restart the search again. - */ - pag->pagl_pagino = NULLAGINO; - pag->pagl_leftrec = NULLAGINO; - pag->pagl_rightrec = NULLAGINO; - xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); - xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); - goto restart_pagno; + if (searchdistance <= 0) { + /* + * Not in range - save last search + * location and allocate a new inode + */ + xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); + pag->pagl_leftrec = trec.ir_startino; + pag->pagl_rightrec = rec.ir_startino; + pag->pagl_pagino = pagino; + + } else { + /* + * We've reached the end of the btree. because + * we are only searching a small chunk of the + * btree each search, there is obviously free + * inodes closer to the parent inode than we + * are now. restart the search again. + */ + pag->pagl_pagino = NULLAGINO; + pag->pagl_leftrec = NULLAGINO; + pag->pagl_rightrec = NULLAGINO; + xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + goto restart_pagno; + } } /* * In a different AG from the parent. * See if the most recently allocated block has any free. */ -newino: if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), XFS_LOOKUP_EQ, &i); @@ -1955,7 +1962,7 @@ xfs_difree_inobt( if (!(mp->m_flags & XFS_MOUNT_IKEEP) && rec.ir_free == XFS_INOBT_ALL_FREE && mp->m_sb.sb_inopblock <= XFS_INODES_PER_CHUNK) { - xic->deleted = 1; + xic->deleted = true; xic->first_ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino); xic->alloc = xfs_inobt_irec_to_allocmask(&rec); @@ -1982,7 +1989,7 @@ xfs_difree_inobt( xfs_difree_inode_chunk(mp, agno, &rec, dfops); } else { - xic->deleted = 0; + xic->deleted = false; error = xfs_inobt_update(cur, &rec); if (error) { @@ -2542,8 +2549,7 @@ xfs_agi_read_verify( !xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF)) xfs_buf_ioerror(bp, -EFSBADCRC); else if (XFS_TEST_ERROR(!xfs_agi_verify(bp), mp, - XFS_ERRTAG_IALLOC_READ_AGI, - XFS_RANDOM_IALLOC_READ_AGI)) + XFS_ERRTAG_IALLOC_READ_AGI)) xfs_buf_ioerror(bp, -EFSCORRUPTED); if (bp->b_error) diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index 0bb89669fc07..b32cfb5aeb5b 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -168,5 +168,10 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp, int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, struct xfs_buf **bpp); +union xfs_btree_rec; +void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, union xfs_btree_rec *rec, + struct xfs_inobt_rec_incore *irec); + +int xfs_ialloc_cluster_alignment(struct xfs_mount *mp); #endif /* __XFS_IALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 7c471881c9a6..317caba9faa6 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -175,6 +175,18 @@ xfs_inobt_init_key_from_rec( } STATIC void +xfs_inobt_init_high_key_from_rec( + union xfs_btree_key *key, + union xfs_btree_rec *rec) +{ + __u32 x; + + x = be32_to_cpu(rec->inobt.ir_startino); + x += XFS_INODES_PER_CHUNK - 1; + key->inobt.ir_startino = cpu_to_be32(x); +} + +STATIC void xfs_inobt_init_rec_from_cur( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) @@ -219,15 +231,25 @@ xfs_finobt_init_ptr_from_cur( ptr->s = agi->agi_free_root; } -STATIC __int64_t +STATIC int64_t xfs_inobt_key_diff( struct xfs_btree_cur *cur, union xfs_btree_key *key) { - return (__int64_t)be32_to_cpu(key->inobt.ir_startino) - + return (int64_t)be32_to_cpu(key->inobt.ir_startino) - cur->bc_rec.i.ir_startino; } +STATIC int64_t +xfs_inobt_diff_two_keys( + struct xfs_btree_cur *cur, + union xfs_btree_key *k1, + union xfs_btree_key *k2) +{ + return (int64_t)be32_to_cpu(k1->inobt.ir_startino) - + be32_to_cpu(k2->inobt.ir_startino); +} + static int xfs_inobt_verify( struct xfs_buf *bp) @@ -302,7 +324,6 @@ const struct xfs_buf_ops xfs_inobt_buf_ops = { .verify_write = xfs_inobt_write_verify, }; -#if defined(DEBUG) || defined(XFS_WARN) STATIC int xfs_inobt_keys_inorder( struct xfs_btree_cur *cur, @@ -322,7 +343,6 @@ xfs_inobt_recs_inorder( return be32_to_cpu(r1->inobt.ir_startino) + XFS_INODES_PER_CHUNK <= be32_to_cpu(r2->inobt.ir_startino); } -#endif /* DEBUG */ static const struct xfs_btree_ops xfs_inobt_ops = { .rec_len = sizeof(xfs_inobt_rec_t), @@ -335,14 +355,14 @@ static const struct xfs_btree_ops xfs_inobt_ops = { .get_minrecs = xfs_inobt_get_minrecs, .get_maxrecs = xfs_inobt_get_maxrecs, .init_key_from_rec = xfs_inobt_init_key_from_rec, + .init_high_key_from_rec = xfs_inobt_init_high_key_from_rec, .init_rec_from_cur = xfs_inobt_init_rec_from_cur, .init_ptr_from_cur = xfs_inobt_init_ptr_from_cur, .key_diff = xfs_inobt_key_diff, .buf_ops = &xfs_inobt_buf_ops, -#if defined(DEBUG) || defined(XFS_WARN) + .diff_two_keys = xfs_inobt_diff_two_keys, .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, -#endif }; static const struct xfs_btree_ops xfs_finobt_ops = { @@ -356,14 +376,14 @@ static const struct xfs_btree_ops xfs_finobt_ops = { .get_minrecs = xfs_inobt_get_minrecs, .get_maxrecs = xfs_inobt_get_maxrecs, .init_key_from_rec = xfs_inobt_init_key_from_rec, + .init_high_key_from_rec = xfs_inobt_init_high_key_from_rec, .init_rec_from_cur = xfs_inobt_init_rec_from_cur, .init_ptr_from_cur = xfs_finobt_init_ptr_from_cur, .key_diff = xfs_inobt_key_diff, .buf_ops = &xfs_inobt_buf_ops, -#if defined(DEBUG) || defined(XFS_WARN) + .diff_two_keys = xfs_inobt_diff_two_keys, .keys_inorder = xfs_inobt_keys_inorder, .recs_inorder = xfs_inobt_recs_inorder, -#endif }; /* diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 09c3d1aecef2..378f8fbc91a7 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -105,8 +105,7 @@ xfs_inode_buf_verify( di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) && xfs_dinode_good_version(mp, dip->di_version); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, - XFS_ERRTAG_ITOBP_INOTOBP, - XFS_RANDOM_ITOBP_INOTOBP))) { + XFS_ERRTAG_ITOBP_INOTOBP))) { if (readahead) { bp->b_flags &= ~XBF_DONE; xfs_buf_ioerror(bp, -EIO); @@ -381,7 +380,7 @@ xfs_log_dinode_to_disk( } } -static bool +bool xfs_dinode_verify( struct xfs_mount *mp, xfs_ino_t ino, @@ -444,7 +443,7 @@ xfs_dinode_calc_crc( struct xfs_mount *mp, struct xfs_dinode *dip) { - __uint32_t crc; + uint32_t crc; if (dip->di_version < 3) return; diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 6848a0afbce7..a9c97a356c30 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -28,26 +28,26 @@ struct xfs_dinode; * format specific structures at the appropriate time. */ struct xfs_icdinode { - __int8_t di_version; /* inode version */ - __int8_t di_format; /* format of di_c data */ - __uint16_t di_flushiter; /* incremented on flush */ - __uint32_t di_uid; /* owner's user id */ - __uint32_t di_gid; /* owner's group id */ - __uint16_t di_projid_lo; /* lower part of owner's project id */ - __uint16_t di_projid_hi; /* higher part of owner's project id */ + int8_t di_version; /* inode version */ + int8_t di_format; /* format of di_c data */ + uint16_t di_flushiter; /* incremented on flush */ + uint32_t di_uid; /* owner's user id */ + uint32_t di_gid; /* owner's group id */ + uint16_t di_projid_lo; /* lower part of owner's project id */ + uint16_t di_projid_hi; /* higher part of owner's project id */ xfs_fsize_t di_size; /* number of bytes in file */ xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */ xfs_extlen_t di_extsize; /* basic/minimum extent size for file */ xfs_extnum_t di_nextents; /* number of extents in data fork */ xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/ - __uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */ - __int8_t di_aformat; /* format of attr fork's data */ - __uint32_t di_dmevmask; /* DMIG event mask */ - __uint16_t di_dmstate; /* DMIG state info */ - __uint16_t di_flags; /* random flags, XFS_DIFLAG_... */ + uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */ + int8_t di_aformat; /* format of attr fork's data */ + uint32_t di_dmevmask; /* DMIG event mask */ + uint16_t di_dmstate; /* DMIG state info */ + uint16_t di_flags; /* random flags, XFS_DIFLAG_... */ - __uint64_t di_flags2; /* more random flags */ - __uint32_t di_cowextsize; /* basic cow extent size for file */ + uint64_t di_flags2; /* more random flags */ + uint32_t di_cowextsize; /* basic cow extent size for file */ xfs_ictimestamp_t di_crtime; /* time created */ }; @@ -82,4 +82,7 @@ void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); #define xfs_inobp_check(mp, bp) #endif /* DEBUG */ +bool xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino, + struct xfs_dinode *dip); + #endif /* __XFS_INODE_BUF_H__ */ diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 0e80f34fe97c..31840ca24018 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -1499,14 +1499,11 @@ xfs_iext_realloc_indirect( xfs_ifork_t *ifp, /* inode fork pointer */ int new_size) /* new indirection array size */ { - int nlists; /* number of irec's (ex lists) */ - int size; /* current indirection array size */ - ASSERT(ifp->if_flags & XFS_IFEXTIREC); - nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; - size = nlists * sizeof(xfs_ext_irec_t); ASSERT(ifp->if_real_bytes); - ASSERT((new_size >= 0) && (new_size != size)); + ASSERT((new_size >= 0) && + (new_size != ((ifp->if_real_bytes / XFS_IEXT_BUFSZ) * + sizeof(xfs_ext_irec_t)))); if (new_size == 0) { xfs_iext_destroy(ifp); } else { @@ -2023,3 +2020,15 @@ xfs_iext_get_extent( xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), gotp); return true; } + +void +xfs_iext_update_extent( + struct xfs_ifork *ifp, + xfs_extnum_t idx, + struct xfs_bmbt_irec *gotp) +{ + ASSERT(idx >= 0); + ASSERT(idx < xfs_iext_count(ifp)); + + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, idx), gotp); +} diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index 7fb8365326d1..11af705219f6 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -187,6 +187,8 @@ bool xfs_iext_lookup_extent(struct xfs_inode *ip, xfs_extnum_t *idxp, struct xfs_bmbt_irec *gotp); bool xfs_iext_get_extent(struct xfs_ifork *ifp, xfs_extnum_t idx, struct xfs_bmbt_irec *gotp); +void xfs_iext_update_extent(struct xfs_ifork *ifp, xfs_extnum_t idx, + struct xfs_bmbt_irec *gotp); extern struct kmem_zone *xfs_ifork_zone; diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 7ae571f8e34a..71de185735e0 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -31,7 +31,7 @@ struct xfs_trans_res; * through all the log items definitions and everything they encode into the * log. */ -typedef __uint32_t xlog_tid_t; +typedef uint32_t xlog_tid_t; #define XLOG_MIN_ICLOGS 2 #define XLOG_MAX_ICLOGS 8 @@ -211,7 +211,7 @@ typedef struct xfs_log_iovec { typedef struct xfs_trans_header { uint th_magic; /* magic number */ uint th_type; /* transaction type */ - __int32_t th_tid; /* transaction id (unused) */ + int32_t th_tid; /* transaction id (unused) */ uint th_num_items; /* num items logged by trans */ } xfs_trans_header_t; @@ -265,53 +265,42 @@ typedef struct xfs_trans_header { * must be added on to the end. */ typedef struct xfs_inode_log_format { - __uint16_t ilf_type; /* inode log item type */ - __uint16_t ilf_size; /* size of this item */ - __uint32_t ilf_fields; /* flags for fields logged */ - __uint16_t ilf_asize; /* size of attr d/ext/root */ - __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint64_t ilf_ino; /* inode number */ + uint16_t ilf_type; /* inode log item type */ + uint16_t ilf_size; /* size of this item */ + uint32_t ilf_fields; /* flags for fields logged */ + uint16_t ilf_asize; /* size of attr d/ext/root */ + uint16_t ilf_dsize; /* size of data/ext/root */ + uint32_t ilf_pad; /* pad for 64 bit boundary */ + uint64_t ilf_ino; /* inode number */ union { - __uint32_t ilfu_rdev; /* rdev value for dev inode*/ + uint32_t ilfu_rdev; /* rdev value for dev inode*/ uuid_t ilfu_uuid; /* mount point value */ } ilf_u; - __int64_t ilf_blkno; /* blkno of inode buffer */ - __int32_t ilf_len; /* len of inode buffer */ - __int32_t ilf_boffset; /* off of inode in buffer */ + int64_t ilf_blkno; /* blkno of inode buffer */ + int32_t ilf_len; /* len of inode buffer */ + int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_t; -typedef struct xfs_inode_log_format_32 { - __uint16_t ilf_type; /* inode log item type */ - __uint16_t ilf_size; /* size of this item */ - __uint32_t ilf_fields; /* flags for fields logged */ - __uint16_t ilf_asize; /* size of attr d/ext/root */ - __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint64_t ilf_ino; /* inode number */ - union { - __uint32_t ilfu_rdev; /* rdev value for dev inode*/ - uuid_t ilfu_uuid; /* mount point value */ - } ilf_u; - __int64_t ilf_blkno; /* blkno of inode buffer */ - __int32_t ilf_len; /* len of inode buffer */ - __int32_t ilf_boffset; /* off of inode in buffer */ -} __attribute__((packed)) xfs_inode_log_format_32_t; - -typedef struct xfs_inode_log_format_64 { - __uint16_t ilf_type; /* inode log item type */ - __uint16_t ilf_size; /* size of this item */ - __uint32_t ilf_fields; /* flags for fields logged */ - __uint16_t ilf_asize; /* size of attr d/ext/root */ - __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint32_t ilf_pad; /* pad for 64 bit boundary */ - __uint64_t ilf_ino; /* inode number */ +/* + * Old 32 bit systems will log in this format without the 64 bit + * alignment padding. Recovery will detect this and convert it to the + * correct format. + */ +struct xfs_inode_log_format_32 { + uint16_t ilf_type; /* inode log item type */ + uint16_t ilf_size; /* size of this item */ + uint32_t ilf_fields; /* flags for fields logged */ + uint16_t ilf_asize; /* size of attr d/ext/root */ + uint16_t ilf_dsize; /* size of data/ext/root */ + uint64_t ilf_ino; /* inode number */ union { - __uint32_t ilfu_rdev; /* rdev value for dev inode*/ + uint32_t ilfu_rdev; /* rdev value for dev inode*/ uuid_t ilfu_uuid; /* mount point value */ } ilf_u; - __int64_t ilf_blkno; /* blkno of inode buffer */ - __int32_t ilf_len; /* len of inode buffer */ - __int32_t ilf_boffset; /* off of inode in buffer */ -} xfs_inode_log_format_64_t; + int64_t ilf_blkno; /* blkno of inode buffer */ + int32_t ilf_len; /* len of inode buffer */ + int32_t ilf_boffset; /* off of inode in buffer */ +} __attribute__((packed)); /* @@ -379,8 +368,8 @@ static inline int xfs_ilog_fdata(int w) * information. */ typedef struct xfs_ictimestamp { - __int32_t t_sec; /* timestamp seconds */ - __int32_t t_nsec; /* timestamp nanoseconds */ + int32_t t_sec; /* timestamp seconds */ + int32_t t_nsec; /* timestamp nanoseconds */ } xfs_ictimestamp_t; /* @@ -388,18 +377,18 @@ typedef struct xfs_ictimestamp { * kept identical to struct xfs_dinode except for the endianness annotations. */ struct xfs_log_dinode { - __uint16_t di_magic; /* inode magic # = XFS_DINODE_MAGIC */ - __uint16_t di_mode; /* mode and type of file */ - __int8_t di_version; /* inode version */ - __int8_t di_format; /* format of di_c data */ - __uint8_t di_pad3[2]; /* unused in v2/3 inodes */ - __uint32_t di_uid; /* owner's user id */ - __uint32_t di_gid; /* owner's group id */ - __uint32_t di_nlink; /* number of links to file */ - __uint16_t di_projid_lo; /* lower part of owner's project id */ - __uint16_t di_projid_hi; /* higher part of owner's project id */ - __uint8_t di_pad[6]; /* unused, zeroed space */ - __uint16_t di_flushiter; /* incremented on flush */ + uint16_t di_magic; /* inode magic # = XFS_DINODE_MAGIC */ + uint16_t di_mode; /* mode and type of file */ + int8_t di_version; /* inode version */ + int8_t di_format; /* format of di_c data */ + uint8_t di_pad3[2]; /* unused in v2/3 inodes */ + uint32_t di_uid; /* owner's user id */ + uint32_t di_gid; /* owner's group id */ + uint32_t di_nlink; /* number of links to file */ + uint16_t di_projid_lo; /* lower part of owner's project id */ + uint16_t di_projid_hi; /* higher part of owner's project id */ + uint8_t di_pad[6]; /* unused, zeroed space */ + uint16_t di_flushiter; /* incremented on flush */ xfs_ictimestamp_t di_atime; /* time last accessed */ xfs_ictimestamp_t di_mtime; /* time last modified */ xfs_ictimestamp_t di_ctime; /* time created/inode modified */ @@ -408,23 +397,23 @@ struct xfs_log_dinode { xfs_extlen_t di_extsize; /* basic/minimum extent size for file */ xfs_extnum_t di_nextents; /* number of extents in data fork */ xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/ - __uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */ - __int8_t di_aformat; /* format of attr fork's data */ - __uint32_t di_dmevmask; /* DMIG event mask */ - __uint16_t di_dmstate; /* DMIG state info */ - __uint16_t di_flags; /* random flags, XFS_DIFLAG_... */ - __uint32_t di_gen; /* generation number */ + uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */ + int8_t di_aformat; /* format of attr fork's data */ + uint32_t di_dmevmask; /* DMIG event mask */ + uint16_t di_dmstate; /* DMIG state info */ + uint16_t di_flags; /* random flags, XFS_DIFLAG_... */ + uint32_t di_gen; /* generation number */ /* di_next_unlinked is the only non-core field in the old dinode */ xfs_agino_t di_next_unlinked;/* agi unlinked list ptr */ /* start of the extended dinode, writable fields */ - __uint32_t di_crc; /* CRC of the inode */ - __uint64_t di_changecount; /* number of attribute changes */ + uint32_t di_crc; /* CRC of the inode */ + uint64_t di_changecount; /* number of attribute changes */ xfs_lsn_t di_lsn; /* flush sequence */ - __uint64_t di_flags2; /* more random flags */ - __uint32_t di_cowextsize; /* basic cow extent size for file */ - __uint8_t di_pad2[12]; /* more padding for future expansion */ + uint64_t di_flags2; /* more random flags */ + uint32_t di_cowextsize; /* basic cow extent size for file */ + uint8_t di_pad2[12]; /* more padding for future expansion */ /* fields only written to during inode creation */ xfs_ictimestamp_t di_crtime; /* time created */ @@ -483,7 +472,7 @@ typedef struct xfs_buf_log_format { unsigned short blf_size; /* size of this item */ unsigned short blf_flags; /* misc state */ unsigned short blf_len; /* number of blocks in this buf */ - __int64_t blf_blkno; /* starting blkno of this buf */ + int64_t blf_blkno; /* starting blkno of this buf */ unsigned int blf_map_size; /* used size of data bitmap in words */ unsigned int blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */ } xfs_buf_log_format_t; @@ -533,7 +522,7 @@ xfs_blft_to_flags(struct xfs_buf_log_format *blf, enum xfs_blft type) blf->blf_flags |= ((type << XFS_BLFT_SHIFT) & XFS_BLFT_MASK); } -static inline __uint16_t +static inline uint16_t xfs_blft_from_flags(struct xfs_buf_log_format *blf) { return (blf->blf_flags & XFS_BLFT_MASK) >> XFS_BLFT_SHIFT; @@ -554,14 +543,14 @@ typedef struct xfs_extent { * conversion routine. */ typedef struct xfs_extent_32 { - __uint64_t ext_start; - __uint32_t ext_len; + uint64_t ext_start; + uint32_t ext_len; } __attribute__((packed)) xfs_extent_32_t; typedef struct xfs_extent_64 { - __uint64_t ext_start; - __uint32_t ext_len; - __uint32_t ext_pad; + uint64_t ext_start; + uint32_t ext_len; + uint32_t ext_pad; } xfs_extent_64_t; /* @@ -570,26 +559,26 @@ typedef struct xfs_extent_64 { * size is given by efi_nextents. */ typedef struct xfs_efi_log_format { - __uint16_t efi_type; /* efi log item type */ - __uint16_t efi_size; /* size of this item */ - __uint32_t efi_nextents; /* # extents to free */ - __uint64_t efi_id; /* efi identifier */ + uint16_t efi_type; /* efi log item type */ + uint16_t efi_size; /* size of this item */ + uint32_t efi_nextents; /* # extents to free */ + uint64_t efi_id; /* efi identifier */ xfs_extent_t efi_extents[1]; /* array of extents to free */ } xfs_efi_log_format_t; typedef struct xfs_efi_log_format_32 { - __uint16_t efi_type; /* efi log item type */ - __uint16_t efi_size; /* size of this item */ - __uint32_t efi_nextents; /* # extents to free */ - __uint64_t efi_id; /* efi identifier */ + uint16_t efi_type; /* efi log item type */ + uint16_t efi_size; /* size of this item */ + uint32_t efi_nextents; /* # extents to free */ + uint64_t efi_id; /* efi identifier */ xfs_extent_32_t efi_extents[1]; /* array of extents to free */ } __attribute__((packed)) xfs_efi_log_format_32_t; typedef struct xfs_efi_log_format_64 { - __uint16_t efi_type; /* efi log item type */ - __uint16_t efi_size; /* size of this item */ - __uint32_t efi_nextents; /* # extents to free */ - __uint64_t efi_id; /* efi identifier */ + uint16_t efi_type; /* efi log item type */ + uint16_t efi_size; /* size of this item */ + uint32_t efi_nextents; /* # extents to free */ + uint64_t efi_id; /* efi identifier */ xfs_extent_64_t efi_extents[1]; /* array of extents to free */ } xfs_efi_log_format_64_t; @@ -599,26 +588,26 @@ typedef struct xfs_efi_log_format_64 { * size is given by efd_nextents; */ typedef struct xfs_efd_log_format { - __uint16_t efd_type; /* efd log item type */ - __uint16_t efd_size; /* size of this item */ - __uint32_t efd_nextents; /* # of extents freed */ - __uint64_t efd_efi_id; /* id of corresponding efi */ + uint16_t efd_type; /* efd log item type */ + uint16_t efd_size; /* size of this item */ + uint32_t efd_nextents; /* # of extents freed */ + uint64_t efd_efi_id; /* id of corresponding efi */ xfs_extent_t efd_extents[1]; /* array of extents freed */ } xfs_efd_log_format_t; typedef struct xfs_efd_log_format_32 { - __uint16_t efd_type; /* efd log item type */ - __uint16_t efd_size; /* size of this item */ - __uint32_t efd_nextents; /* # of extents freed */ - __uint64_t efd_efi_id; /* id of corresponding efi */ + uint16_t efd_type; /* efd log item type */ + uint16_t efd_size; /* size of this item */ + uint32_t efd_nextents; /* # of extents freed */ + uint64_t efd_efi_id; /* id of corresponding efi */ xfs_extent_32_t efd_extents[1]; /* array of extents freed */ } __attribute__((packed)) xfs_efd_log_format_32_t; typedef struct xfs_efd_log_format_64 { - __uint16_t efd_type; /* efd log item type */ - __uint16_t efd_size; /* size of this item */ - __uint32_t efd_nextents; /* # of extents freed */ - __uint64_t efd_efi_id; /* id of corresponding efi */ + uint16_t efd_type; /* efd log item type */ + uint16_t efd_size; /* size of this item */ + uint32_t efd_nextents; /* # of extents freed */ + uint64_t efd_efi_id; /* id of corresponding efi */ xfs_extent_64_t efd_extents[1]; /* array of extents freed */ } xfs_efd_log_format_64_t; @@ -626,11 +615,11 @@ typedef struct xfs_efd_log_format_64 { * RUI/RUD (reverse mapping) log format definitions */ struct xfs_map_extent { - __uint64_t me_owner; - __uint64_t me_startblock; - __uint64_t me_startoff; - __uint32_t me_len; - __uint32_t me_flags; + uint64_t me_owner; + uint64_t me_startblock; + uint64_t me_startoff; + uint32_t me_len; + uint32_t me_flags; }; /* rmap me_flags: upper bits are flags, lower byte is type code */ @@ -659,10 +648,10 @@ struct xfs_map_extent { * size is given by rui_nextents. */ struct xfs_rui_log_format { - __uint16_t rui_type; /* rui log item type */ - __uint16_t rui_size; /* size of this item */ - __uint32_t rui_nextents; /* # extents to free */ - __uint64_t rui_id; /* rui identifier */ + uint16_t rui_type; /* rui log item type */ + uint16_t rui_size; /* size of this item */ + uint32_t rui_nextents; /* # extents to free */ + uint64_t rui_id; /* rui identifier */ struct xfs_map_extent rui_extents[]; /* array of extents to rmap */ }; @@ -680,19 +669,19 @@ xfs_rui_log_format_sizeof( * size is given by rud_nextents; */ struct xfs_rud_log_format { - __uint16_t rud_type; /* rud log item type */ - __uint16_t rud_size; /* size of this item */ - __uint32_t __pad; - __uint64_t rud_rui_id; /* id of corresponding rui */ + uint16_t rud_type; /* rud log item type */ + uint16_t rud_size; /* size of this item */ + uint32_t __pad; + uint64_t rud_rui_id; /* id of corresponding rui */ }; /* * CUI/CUD (refcount update) log format definitions */ struct xfs_phys_extent { - __uint64_t pe_startblock; - __uint32_t pe_len; - __uint32_t pe_flags; + uint64_t pe_startblock; + uint32_t pe_len; + uint32_t pe_flags; }; /* refcount pe_flags: upper bits are flags, lower byte is type code */ @@ -707,10 +696,10 @@ struct xfs_phys_extent { * size is given by cui_nextents. */ struct xfs_cui_log_format { - __uint16_t cui_type; /* cui log item type */ - __uint16_t cui_size; /* size of this item */ - __uint32_t cui_nextents; /* # extents to free */ - __uint64_t cui_id; /* cui identifier */ + uint16_t cui_type; /* cui log item type */ + uint16_t cui_size; /* size of this item */ + uint32_t cui_nextents; /* # extents to free */ + uint64_t cui_id; /* cui identifier */ struct xfs_phys_extent cui_extents[]; /* array of extents */ }; @@ -728,10 +717,10 @@ xfs_cui_log_format_sizeof( * size is given by cud_nextents; */ struct xfs_cud_log_format { - __uint16_t cud_type; /* cud log item type */ - __uint16_t cud_size; /* size of this item */ - __uint32_t __pad; - __uint64_t cud_cui_id; /* id of corresponding cui */ + uint16_t cud_type; /* cud log item type */ + uint16_t cud_size; /* size of this item */ + uint32_t __pad; + uint64_t cud_cui_id; /* id of corresponding cui */ }; /* @@ -755,10 +744,10 @@ struct xfs_cud_log_format { * size is given by bui_nextents. */ struct xfs_bui_log_format { - __uint16_t bui_type; /* bui log item type */ - __uint16_t bui_size; /* size of this item */ - __uint32_t bui_nextents; /* # extents to free */ - __uint64_t bui_id; /* bui identifier */ + uint16_t bui_type; /* bui log item type */ + uint16_t bui_size; /* size of this item */ + uint32_t bui_nextents; /* # extents to free */ + uint64_t bui_id; /* bui identifier */ struct xfs_map_extent bui_extents[]; /* array of extents to bmap */ }; @@ -776,10 +765,10 @@ xfs_bui_log_format_sizeof( * size is given by bud_nextents; */ struct xfs_bud_log_format { - __uint16_t bud_type; /* bud log item type */ - __uint16_t bud_size; /* size of this item */ - __uint32_t __pad; - __uint64_t bud_bui_id; /* id of corresponding bui */ + uint16_t bud_type; /* bud log item type */ + uint16_t bud_size; /* size of this item */ + uint32_t __pad; + uint64_t bud_bui_id; /* id of corresponding bui */ }; /* @@ -789,12 +778,12 @@ struct xfs_bud_log_format { * 32 bits : log_recovery code assumes that. */ typedef struct xfs_dq_logformat { - __uint16_t qlf_type; /* dquot log item type */ - __uint16_t qlf_size; /* size of this item */ + uint16_t qlf_type; /* dquot log item type */ + uint16_t qlf_size; /* size of this item */ xfs_dqid_t qlf_id; /* usr/grp/proj id : 32 bits */ - __int64_t qlf_blkno; /* blkno of dquot buffer */ - __int32_t qlf_len; /* len of dquot buffer */ - __uint32_t qlf_boffset; /* off of dquot in buffer */ + int64_t qlf_blkno; /* blkno of dquot buffer */ + int32_t qlf_len; /* len of dquot buffer */ + uint32_t qlf_boffset; /* off of dquot in buffer */ } xfs_dq_logformat_t; /* @@ -853,8 +842,8 @@ typedef struct xfs_qoff_logformat { * decoding can be done correctly. */ struct xfs_icreate_log { - __uint16_t icl_type; /* type of log format structure */ - __uint16_t icl_size; /* size of log format structure */ + uint16_t icl_type; /* type of log format structure */ + uint16_t icl_size; /* size of log format structure */ __be32 icl_ag; /* ag being allocated in */ __be32 icl_agbno; /* start block of inode range */ __be32 icl_count; /* number of inodes to initialise */ diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h index 29a01ec89dd0..66948a9fd486 100644 --- a/fs/xfs/libxfs/xfs_log_recover.h +++ b/fs/xfs/libxfs/xfs_log_recover.h @@ -26,7 +26,7 @@ #define XLOG_RHASH_SIZE 16 #define XLOG_RHASH_SHIFT 2 #define XLOG_RHASH(tid) \ - ((((__uint32_t)tid)>>XLOG_RHASH_SHIFT) & (XLOG_RHASH_SIZE-1)) + ((((uint32_t)tid)>>XLOG_RHASH_SHIFT) & (XLOG_RHASH_SIZE-1)) #define XLOG_MAX_REGIONS_IN_ITEM (XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK / 2 + 1) diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h index 8eed51275bb3..d69c772271cb 100644 --- a/fs/xfs/libxfs/xfs_quota_defs.h +++ b/fs/xfs/libxfs/xfs_quota_defs.h @@ -27,8 +27,8 @@ * they may need 64-bit accounting. Hence, 64-bit quota-counters, * and quota-limits. This is a waste in the common case, but hey ... */ -typedef __uint64_t xfs_qcnt_t; -typedef __uint16_t xfs_qwarncnt_t; +typedef uint64_t xfs_qcnt_t; +typedef uint16_t xfs_qwarncnt_t; /* * flags for q_flags field in the dquot. diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 82a38d86ebad..9d5406b4f663 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -784,14 +784,6 @@ xfs_refcount_merge_extents( } /* - * While we're adjusting the refcounts records of an extent, we have - * to keep an eye on the number of extents we're dirtying -- run too - * many in a single transaction and we'll exceed the transaction's - * reservation and crash the fs. Each record adds 12 bytes to the - * log (plus any key updates) so we'll conservatively assume 24 bytes - * per record. We must also leave space for btree splits on both ends - * of the range and space for the CUD and a new CUI. - * * XXX: This is a pretty hand-wavy estimate. The penalty for guessing * true incorrectly is a shutdown FS; the penalty for guessing false * incorrectly is more transaction rolls than might be necessary. @@ -813,8 +805,7 @@ xfs_refcount_still_have_space( */ if (cur->bc_private.a.priv.refc.nr_ops > 2 && XFS_TEST_ERROR(false, cur->bc_mp, - XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE, - XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE)) + XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE)) return false; if (cur->bc_private.a.priv.refc.nr_ops == 0) @@ -822,7 +813,7 @@ xfs_refcount_still_have_space( else if (overhead > cur->bc_tp->t_log_res) return false; return cur->bc_tp->t_log_res - overhead > - cur->bc_private.a.priv.refc.nr_ops * 32; + cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } /* @@ -1076,8 +1067,7 @@ xfs_refcount_finish_one( blockcount); if (XFS_TEST_ERROR(false, mp, - XFS_ERRTAG_REFCOUNT_FINISH_ONE, - XFS_RANDOM_REFCOUNT_FINISH_ONE)) + XFS_ERRTAG_REFCOUNT_FINISH_ONE)) return -EIO; /* @@ -1648,6 +1638,10 @@ xfs_refcount_recover_cow_leftovers( error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (error) goto out_trans; + if (!agbp) { + error = -ENOMEM; + goto out_trans; + } cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL); /* Find all the leftover CoW staging extents. */ @@ -1685,7 +1679,7 @@ xfs_refcount_recover_cow_leftovers( xfs_bmap_add_free(mp, &dfops, fsb, rr->rr_rrec.rc_blockcount, NULL); - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_defer; diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 098dc668ab2c..eafb9d1f3b37 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp, extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, xfs_agnumber_t agno); +/* + * While we're adjusting the refcounts records of an extent, we have + * to keep an eye on the number of extents we're dirtying -- run too + * many in a single transaction and we'll exceed the transaction's + * reservation and crash the fs. Each record adds 12 bytes to the + * log (plus any key updates) so we'll conservatively assume 32 bytes + * per record. We must also leave space for btree splits on both ends + * of the range and space for the CUD and a new CUI. + */ +#define XFS_REFCOUNT_ITEM_OVERHEAD 32 + +static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res) +{ + return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD; +} + #endif /* __XFS_REFCOUNT_H__ */ diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 50add5272807..3c59dd3d58d7 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -202,7 +202,7 @@ xfs_refcountbt_init_ptr_from_cur( ptr->s = agf->agf_refcount_root; } -STATIC __int64_t +STATIC int64_t xfs_refcountbt_key_diff( struct xfs_btree_cur *cur, union xfs_btree_key *key) @@ -210,16 +210,16 @@ xfs_refcountbt_key_diff( struct xfs_refcount_irec *rec = &cur->bc_rec.rc; struct xfs_refcount_key *kp = &key->refc; - return (__int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock; + return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock; } -STATIC __int64_t +STATIC int64_t xfs_refcountbt_diff_two_keys( struct xfs_btree_cur *cur, union xfs_btree_key *k1, union xfs_btree_key *k2) { - return (__int64_t)be32_to_cpu(k1->refc.rc_startblock) - + return (int64_t)be32_to_cpu(k1->refc.rc_startblock) - be32_to_cpu(k2->refc.rc_startblock); } @@ -285,7 +285,6 @@ const struct xfs_buf_ops xfs_refcountbt_buf_ops = { .verify_write = xfs_refcountbt_write_verify, }; -#if defined(DEBUG) || defined(XFS_WARN) STATIC int xfs_refcountbt_keys_inorder( struct xfs_btree_cur *cur, @@ -306,7 +305,6 @@ xfs_refcountbt_recs_inorder( be32_to_cpu(r1->refc.rc_blockcount) <= be32_to_cpu(r2->refc.rc_startblock); } -#endif static const struct xfs_btree_ops xfs_refcountbt_ops = { .rec_len = sizeof(struct xfs_refcount_rec), @@ -325,10 +323,8 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = { .key_diff = xfs_refcountbt_key_diff, .buf_ops = &xfs_refcountbt_buf_ops, .diff_two_keys = xfs_refcountbt_diff_two_keys, -#if defined(DEBUG) || defined(XFS_WARN) .keys_inorder = xfs_refcountbt_keys_inorder, .recs_inorder = xfs_refcountbt_recs_inorder, -#endif }; /* diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 06cfb93c2ef9..55c88a732690 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -179,7 +179,8 @@ done: return error; } -static int +/* Convert an internal btree record to an rmap record. */ +int xfs_rmap_btrec_to_irec( union xfs_btree_rec *rec, struct xfs_rmap_irec *irec) @@ -2061,7 +2062,7 @@ int xfs_rmap_finish_one( struct xfs_trans *tp, enum xfs_rmap_intent_type type, - __uint64_t owner, + uint64_t owner, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, @@ -2086,8 +2087,7 @@ xfs_rmap_finish_one( startoff, blockcount, state); if (XFS_TEST_ERROR(false, mp, - XFS_ERRTAG_RMAP_FINISH_ONE, - XFS_RANDOM_RMAP_FINISH_ONE)) + XFS_ERRTAG_RMAP_FINISH_ONE)) return -EIO; /* @@ -2182,7 +2182,7 @@ __xfs_rmap_add( struct xfs_mount *mp, struct xfs_defer_ops *dfops, enum xfs_rmap_intent_type type, - __uint64_t owner, + uint64_t owner, int whichfork, struct xfs_bmbt_irec *bmap) { @@ -2266,7 +2266,7 @@ xfs_rmap_alloc_extent( xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len, - __uint64_t owner) + uint64_t owner) { struct xfs_bmbt_irec bmap; @@ -2290,7 +2290,7 @@ xfs_rmap_free_extent( xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len, - __uint64_t owner) + uint64_t owner) { struct xfs_bmbt_irec bmap; diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 98f908fea103..466ede637080 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -179,7 +179,7 @@ enum xfs_rmap_intent_type { struct xfs_rmap_intent { struct list_head ri_list; enum xfs_rmap_intent_type ri_type; - __uint64_t ri_owner; + uint64_t ri_owner; int ri_whichfork; struct xfs_bmbt_irec ri_bmap; }; @@ -196,15 +196,15 @@ int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *imap); int xfs_rmap_alloc_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len, - __uint64_t owner); + uint64_t owner); int xfs_rmap_free_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len, - __uint64_t owner); + uint64_t owner); void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp, struct xfs_btree_cur *rcur, int error); int xfs_rmap_finish_one(struct xfs_trans *tp, enum xfs_rmap_intent_type type, - __uint64_t owner, int whichfork, xfs_fileoff_t startoff, + uint64_t owner, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, xfs_filblks_t blockcount, xfs_exntst_t state, struct xfs_btree_cur **pcur); @@ -216,5 +216,8 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno, struct xfs_rmap_irec *irec, int *stat); int xfs_rmap_compare(const struct xfs_rmap_irec *a, const struct xfs_rmap_irec *b); +union xfs_btree_rec; +int xfs_rmap_btrec_to_irec(union xfs_btree_rec *rec, + struct xfs_rmap_irec *irec); #endif /* __XFS_RMAP_H__ */ diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 74e5a54bc428..9d9c9192584c 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -199,7 +199,7 @@ xfs_rmapbt_init_high_key_from_rec( union xfs_btree_key *key, union xfs_btree_rec *rec) { - __uint64_t off; + uint64_t off; int adj; adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1; @@ -241,7 +241,7 @@ xfs_rmapbt_init_ptr_from_cur( ptr->s = agf->agf_roots[cur->bc_btnum]; } -STATIC __int64_t +STATIC int64_t xfs_rmapbt_key_diff( struct xfs_btree_cur *cur, union xfs_btree_key *key) @@ -249,9 +249,9 @@ xfs_rmapbt_key_diff( struct xfs_rmap_irec *rec = &cur->bc_rec.r; struct xfs_rmap_key *kp = &key->rmap; __u64 x, y; - __int64_t d; + int64_t d; - d = (__int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; + d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock; if (d) return d; @@ -271,7 +271,7 @@ xfs_rmapbt_key_diff( return 0; } -STATIC __int64_t +STATIC int64_t xfs_rmapbt_diff_two_keys( struct xfs_btree_cur *cur, union xfs_btree_key *k1, @@ -279,10 +279,10 @@ xfs_rmapbt_diff_two_keys( { struct xfs_rmap_key *kp1 = &k1->rmap; struct xfs_rmap_key *kp2 = &k2->rmap; - __int64_t d; + int64_t d; __u64 x, y; - d = (__int64_t)be32_to_cpu(kp1->rm_startblock) - + d = (int64_t)be32_to_cpu(kp1->rm_startblock) - be32_to_cpu(kp2->rm_startblock); if (d) return d; @@ -377,17 +377,16 @@ const struct xfs_buf_ops xfs_rmapbt_buf_ops = { .verify_write = xfs_rmapbt_write_verify, }; -#if defined(DEBUG) || defined(XFS_WARN) STATIC int xfs_rmapbt_keys_inorder( struct xfs_btree_cur *cur, union xfs_btree_key *k1, union xfs_btree_key *k2) { - __uint32_t x; - __uint32_t y; - __uint64_t a; - __uint64_t b; + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; x = be32_to_cpu(k1->rmap.rm_startblock); y = be32_to_cpu(k2->rmap.rm_startblock); @@ -414,10 +413,10 @@ xfs_rmapbt_recs_inorder( union xfs_btree_rec *r1, union xfs_btree_rec *r2) { - __uint32_t x; - __uint32_t y; - __uint64_t a; - __uint64_t b; + uint32_t x; + uint32_t y; + uint64_t a; + uint64_t b; x = be32_to_cpu(r1->rmap.rm_startblock); y = be32_to_cpu(r2->rmap.rm_startblock); @@ -437,7 +436,6 @@ xfs_rmapbt_recs_inorder( return 1; return 0; } -#endif /* DEBUG */ static const struct xfs_btree_ops xfs_rmapbt_ops = { .rec_len = sizeof(struct xfs_rmap_rec), @@ -456,10 +454,8 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = { .key_diff = xfs_rmapbt_key_diff, .buf_ops = &xfs_rmapbt_buf_ops, .diff_two_keys = xfs_rmapbt_diff_two_keys, -#if defined(DEBUG) || defined(XFS_WARN) .keys_inorder = xfs_rmapbt_keys_inorder, .recs_inorder = xfs_rmapbt_recs_inorder, -#endif }; /* diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index e47b99e59f60..5d4e43ef4eea 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -70,7 +70,7 @@ const struct xfs_buf_ops xfs_rtbuf_ops = { * Get a buffer for the bitmap or summary file block specified. * The buffer is returned read and locked. */ -static int +int xfs_rtbuf_get( xfs_mount_t *mp, /* file system mount structure */ xfs_trans_t *tp, /* transaction pointer */ @@ -1011,7 +1011,7 @@ xfs_rtfree_extent( mp->m_sb.sb_rextents) { if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM; - *(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0; + *(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0; xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); } return 0; diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 584ec896a533..9b5aae2bcc0b 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -448,7 +448,7 @@ xfs_sb_quota_to_disk( struct xfs_dsb *to, struct xfs_sb *from) { - __uint16_t qflags = from->sb_qflags; + uint16_t qflags = from->sb_qflags; to->sb_uquotino = cpu_to_be64(from->sb_uquotino); if (xfs_sb_version_has_pquotino(from)) { @@ -756,7 +756,7 @@ xfs_sb_mount_common( mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; mp->m_bsize = XFS_FSB_TO_BB(mp, 1); - mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK, + mp->m_ialloc_inos = (int)MAX((uint16_t)XFS_INODES_PER_CHUNK, sbp->sb_inopblock); mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog; diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index 2e2c6716b623..c484877129a0 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -114,7 +114,7 @@ xfs_symlink_verify( if (bp->b_bn != be64_to_cpu(dsl->sl_blkno)) return false; if (be32_to_cpu(dsl->sl_offset) + - be32_to_cpu(dsl->sl_bytes) >= MAXPATHLEN) + be32_to_cpu(dsl->sl_bytes) >= XFS_SYMLINK_MAXLEN) return false; if (dsl->sl_owner == 0) return false; diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index b456cca1bfb2..6bd916bd35e2 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -477,14 +477,14 @@ xfs_calc_mkdir_reservation( /* * Making a new symplink is the same as creating a new file, but * with the added blocks for remote symlink data which can be up to 1kB in - * length (MAXPATHLEN). + * length (XFS_SYMLINK_MAXLEN). */ STATIC uint xfs_calc_symlink_reservation( struct xfs_mount *mp) { return xfs_calc_create_reservation(mp) + - xfs_calc_buf_res(1, MAXPATHLEN); + xfs_calc_buf_res(1, XFS_SYMLINK_MAXLEN); } /* diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index 717909f2f7b7..0220159bd463 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -18,34 +18,34 @@ #ifndef __XFS_TYPES_H__ #define __XFS_TYPES_H__ -typedef __uint32_t prid_t; /* project ID */ +typedef uint32_t prid_t; /* project ID */ -typedef __uint32_t xfs_agblock_t; /* blockno in alloc. group */ -typedef __uint32_t xfs_agino_t; /* inode # within allocation grp */ -typedef __uint32_t xfs_extlen_t; /* extent length in blocks */ -typedef __uint32_t xfs_agnumber_t; /* allocation group number */ -typedef __int32_t xfs_extnum_t; /* # of extents in a file */ -typedef __int16_t xfs_aextnum_t; /* # extents in an attribute fork */ -typedef __int64_t xfs_fsize_t; /* bytes in a file */ -typedef __uint64_t xfs_ufsize_t; /* unsigned bytes in a file */ +typedef uint32_t xfs_agblock_t; /* blockno in alloc. group */ +typedef uint32_t xfs_agino_t; /* inode # within allocation grp */ +typedef uint32_t xfs_extlen_t; /* extent length in blocks */ +typedef uint32_t xfs_agnumber_t; /* allocation group number */ +typedef int32_t xfs_extnum_t; /* # of extents in a file */ +typedef int16_t xfs_aextnum_t; /* # extents in an attribute fork */ +typedef int64_t xfs_fsize_t; /* bytes in a file */ +typedef uint64_t xfs_ufsize_t; /* unsigned bytes in a file */ -typedef __int32_t xfs_suminfo_t; /* type of bitmap summary info */ -typedef __int32_t xfs_rtword_t; /* word type for bitmap manipulations */ +typedef int32_t xfs_suminfo_t; /* type of bitmap summary info */ +typedef int32_t xfs_rtword_t; /* word type for bitmap manipulations */ -typedef __int64_t xfs_lsn_t; /* log sequence number */ -typedef __int32_t xfs_tid_t; /* transaction identifier */ +typedef int64_t xfs_lsn_t; /* log sequence number */ +typedef int32_t xfs_tid_t; /* transaction identifier */ -typedef __uint32_t xfs_dablk_t; /* dir/attr block number (in file) */ -typedef __uint32_t xfs_dahash_t; /* dir/attr hash value */ +typedef uint32_t xfs_dablk_t; /* dir/attr block number (in file) */ +typedef uint32_t xfs_dahash_t; /* dir/attr hash value */ -typedef __uint64_t xfs_fsblock_t; /* blockno in filesystem (agno|agbno) */ -typedef __uint64_t xfs_rfsblock_t; /* blockno in filesystem (raw) */ -typedef __uint64_t xfs_rtblock_t; /* extent (block) in realtime area */ -typedef __uint64_t xfs_fileoff_t; /* block number in a file */ -typedef __uint64_t xfs_filblks_t; /* number of blocks in a file */ +typedef uint64_t xfs_fsblock_t; /* blockno in filesystem (agno|agbno) */ +typedef uint64_t xfs_rfsblock_t; /* blockno in filesystem (raw) */ +typedef uint64_t xfs_rtblock_t; /* extent (block) in realtime area */ +typedef uint64_t xfs_fileoff_t; /* block number in a file */ +typedef uint64_t xfs_filblks_t; /* number of blocks in a file */ -typedef __int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */ -typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ +typedef int64_t xfs_srtblock_t; /* signed version of xfs_rtblock_t */ +typedef int64_t xfs_sfiloff_t; /* signed block number in a file */ /* * Null values for the types. @@ -125,7 +125,7 @@ struct xfs_name { * uid_t and gid_t are hard-coded to 32 bits in the inode. * Hence, an 'id' in a dquot is 32 bits.. */ -typedef __uint32_t xfs_dqid_t; +typedef uint32_t xfs_dqid_t; /* * Constants for bit manipulations. diff --git a/fs/xfs/uuid.c b/fs/xfs/uuid.c deleted file mode 100644 index b83f76b6d410..000000000000 --- a/fs/xfs/uuid.c +++ /dev/null @@ -1,63 +0,0 @@ -/* - * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#include <xfs.h> - -/* IRIX interpretation of an uuid_t */ -typedef struct { - __be32 uu_timelow; - __be16 uu_timemid; - __be16 uu_timehi; - __be16 uu_clockseq; - __be16 uu_node[3]; -} xfs_uu_t; - -/* - * uuid_getnodeuniq - obtain the node unique fields of a UUID. - * - * This is not in any way a standard or condoned UUID function; - * it just something that's needed for user-level file handles. - */ -void -uuid_getnodeuniq(uuid_t *uuid, int fsid [2]) -{ - xfs_uu_t *uup = (xfs_uu_t *)uuid; - - fsid[0] = (be16_to_cpu(uup->uu_clockseq) << 16) | - be16_to_cpu(uup->uu_timemid); - fsid[1] = be32_to_cpu(uup->uu_timelow); -} - -int -uuid_is_nil(uuid_t *uuid) -{ - int i; - char *cp = (char *)uuid; - - if (uuid == NULL) - return 0; - /* implied check of version number here... */ - for (i = 0; i < sizeof *uuid; i++) - if (*cp++) return 0; /* not nil */ - return 1; /* is nil */ -} - -int -uuid_equal(uuid_t *uuid1, uuid_t *uuid2) -{ - return memcmp(uuid1, uuid2, sizeof(uuid_t)) ? 0 : 1; -} diff --git a/fs/xfs/uuid.h b/fs/xfs/uuid.h deleted file mode 100644 index 104db0f3bed6..000000000000 --- a/fs/xfs/uuid.h +++ /dev/null @@ -1,35 +0,0 @@ -/* - * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_SUPPORT_UUID_H__ -#define __XFS_SUPPORT_UUID_H__ - -typedef struct { - unsigned char __u_bits[16]; -} uuid_t; - -extern int uuid_is_nil(uuid_t *uuid); -extern int uuid_equal(uuid_t *uuid1, uuid_t *uuid2); -extern void uuid_getnodeuniq(uuid_t *uuid, int fsid [2]); - -static inline void -uuid_copy(uuid_t *dst, uuid_t *src) -{ - memcpy(dst, src, sizeof(uuid_t)); -} - -#endif /* __XFS_SUPPORT_UUID_H__ */ diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h index a742c47f7d5a..80cd0fd86783 100644 --- a/fs/xfs/xfs.h +++ b/fs/xfs/xfs.h @@ -24,6 +24,10 @@ #define XFS_BUF_LOCK_TRACKING 1 #endif +#ifdef CONFIG_XFS_ASSERT_FATAL +#define XFS_ASSERT_FATAL 1 +#endif + #ifdef CONFIG_XFS_WARN #define XFS_WARN 1 #endif diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index b468e041f207..3354140de07e 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -170,8 +170,8 @@ xfs_get_acl(struct inode *inode, int type) return acl; } -STATIC int -__xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) +int +__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct xfs_inode *ip = XFS_I(inode); unsigned char *ea_name; @@ -247,6 +247,8 @@ xfs_set_mode(struct inode *inode, umode_t mode) int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + umode_t mode; + bool set_mode = false; int error = 0; if (!acl) @@ -257,16 +259,24 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode; - error = posix_acl_update_mode(inode, &mode, &acl); if (error) return error; - error = xfs_set_mode(inode, mode); - if (error) - return error; + set_mode = true; } set_acl: - return __xfs_set_acl(inode, type, acl); + error = __xfs_set_acl(inode, acl, type); + if (error) + return error; + + /* + * We set the mode after successfully updating the ACL xattr because the + * xattr update can fail at ENOSPC and we don't want to change the mode + * if the ACL update hasn't been applied. + */ + if (set_mode) + error = xfs_set_mode(inode, mode); + + return error; } diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 286fa89217f5..04327318ef67 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -24,6 +24,7 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); #else static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) { diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3b91faacc1ba..a3eeaba156c5 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -80,16 +80,29 @@ xfs_find_bdev_for_inode( return mp->m_ddev_targp->bt_bdev; } +struct dax_device * +xfs_find_daxdev_for_inode( + struct inode *inode) +{ + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + + if (XFS_IS_REALTIME_INODE(ip)) + return mp->m_rtdev_targp->bt_daxdev; + else + return mp->m_ddev_targp->bt_daxdev; +} + /* * We're now finished for good with this page. Update the page state via the * associated buffer_heads, paying attention to the start and end offsets that * we need to process on the page. * - * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last - * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or - * the page at all, as we may be racing with memory reclaim and it can free both - * the bufferhead chain and the page as it will see the page as clean and - * unused. + * Note that we open code the action in end_buffer_async_write here so that we + * only have to iterate over the buffers attached to the page once. This is not + * only more efficient, but also ensures that we only calls end_page_writeback + * at the end of the iteration, and thus avoids the pitfall of having the page + * and buffers potentially freed after every call to end_buffer_async_write. */ static void xfs_finish_page_writeback( @@ -97,29 +110,44 @@ xfs_finish_page_writeback( struct bio_vec *bvec, int error) { - unsigned int end = bvec->bv_offset + bvec->bv_len - 1; - struct buffer_head *head, *bh, *next; + struct buffer_head *head = page_buffers(bvec->bv_page), *bh = head; + bool busy = false; unsigned int off = 0; - unsigned int bsize; + unsigned long flags; ASSERT(bvec->bv_offset < PAGE_SIZE); ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0); - ASSERT(end < PAGE_SIZE); + ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE); ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); - bh = head = page_buffers(bvec->bv_page); - - bsize = bh->b_size; + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &head->b_state); do { - if (off > end) - break; - next = bh->b_this_page; - if (off < bvec->bv_offset) - goto next_bh; - bh->b_end_io(bh, !error); -next_bh: - off += bsize; - } while ((bh = next) != head); + if (off >= bvec->bv_offset && + off < bvec->bv_offset + bvec->bv_len) { + ASSERT(buffer_async_write(bh)); + ASSERT(bh->b_end_io == NULL); + + if (error) { + mark_buffer_write_io_error(bh); + clear_buffer_uptodate(bh); + SetPageError(bvec->bv_page); + } else { + set_buffer_uptodate(bh); + } + clear_buffer_async_write(bh); + unlock_buffer(bh); + } else if (buffer_async_write(bh)) { + ASSERT(buffer_locked(bh)); + busy = true; + } + off += bh->b_size; + } while ((bh = bh->b_this_page) != head); + bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); + local_irq_restore(flags); + + if (!busy) + end_page_writeback(bvec->bv_page); } /* @@ -133,8 +161,10 @@ xfs_destroy_ioend( int error) { struct inode *inode = ioend->io_inode; - struct bio *last = ioend->io_bio; - struct bio *bio, *next; + struct bio *bio = &ioend->io_inline_bio; + struct bio *last = ioend->io_bio, *next; + u64 start = bio->bi_iter.bi_sector; + bool quiet = bio_flagged(bio, BIO_QUIET); for (bio = &ioend->io_inline_bio; bio; bio = next) { struct bio_vec *bvec; @@ -155,6 +185,11 @@ xfs_destroy_ioend( bio_put(bio); } + + if (unlikely(error && !quiet)) { + xfs_err_ratelimited(XFS_I(inode)->i_mount, + "writeback error on sector %llu", start); + } } /* @@ -276,7 +311,7 @@ xfs_end_io( struct xfs_inode *ip = XFS_I(ioend->io_inode); xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; - int error = ioend->io_bio->bi_error; + int error; /* * Just clean up the in-memory strutures if the fs has been shut down. @@ -289,6 +324,7 @@ xfs_end_io( /* * Clean up any COW blocks on an I/O error. */ + error = blk_status_to_errno(ioend->io_bio->bi_status); if (unlikely(error)) { switch (ioend->io_type) { case XFS_IO_COW: @@ -307,7 +343,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); @@ -332,7 +369,7 @@ xfs_end_bio( else if (ioend->io_append_trans) queue_work(mp->m_data_workqueue, &ioend->io_work); else - xfs_destroy_ioend(ioend, bio->bi_error); + xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status)); } STATIC int @@ -409,6 +446,19 @@ xfs_imap_valid( { offset >>= inode->i_blkbits; + /* + * We have to make sure the cached mapping is within EOF to protect + * against eofblocks trimming on file release leaving us with a stale + * mapping. Otherwise, a page for a subsequent file extending buffered + * write could get picked up by this writeback cycle and written to the + * wrong blocks. + * + * Note that what we really want here is a generic mapping invalidation + * mechanism to protect us from arbitrary extent modifying contexts, not + * just eofblocks. + */ + xfs_trim_extent_eof(imap, XFS_I(inode)); + return offset >= imap->br_startoff && offset < imap->br_startoff + imap->br_blockcount; } @@ -422,7 +472,8 @@ xfs_start_buffer_writeback( ASSERT(!buffer_delay(bh)); ASSERT(!buffer_unwritten(bh)); - mark_buffer_async_write(bh); + bh->b_end_io = NULL; + set_buffer_async_write(bh); set_buffer_uptodate(bh); clear_buffer_dirty(bh); } @@ -500,11 +551,12 @@ xfs_submit_ioend( * time. */ if (status) { - ioend->io_bio->bi_error = status; + ioend->io_bio->bi_status = errno_to_blk_status(status); bio_endio(ioend->io_bio); return status; } + ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint; submit_bio(ioend->io_bio); return 0; } @@ -515,7 +567,7 @@ xfs_init_bio_from_bh( struct buffer_head *bh) { bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); - bio->bi_bdev = bh->b_bdev; + bio_set_dev(bio, bh->b_bdev); } static struct xfs_ioend * @@ -564,6 +616,7 @@ xfs_chain_bio( bio_chain(ioend->io_bio, new); bio_get(ioend->io_bio); /* for xfs_destroy_ioend */ ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); + ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint; submit_bio(ioend->io_bio); ioend->io_bio = new; } @@ -695,6 +748,14 @@ xfs_vm_invalidatepage( { trace_xfs_invalidatepage(page->mapping->host, page, offset, length); + + /* + * If we are invalidating the entire page, clear the dirty state from it + * so that we can check for attempts to release dirty cached pages in + * xfs_vm_releasepage(). + */ + if (offset == 0 && length >= PAGE_SIZE) + cancel_dirty_page(page); block_invalidatepage(page, offset, length); } @@ -836,7 +897,7 @@ xfs_writepage_map( struct inode *inode, struct page *page, loff_t offset, - __uint64_t end_offset) + uint64_t end_offset) { LIST_HEAD(submit_list); struct xfs_ioend *ioend, *next; @@ -991,7 +1052,7 @@ xfs_do_writepage( struct xfs_writepage_ctx *wpc = data; struct inode *inode = page->mapping->host; loff_t offset; - __uint64_t end_offset; + uint64_t end_offset; pgoff_t end_index; trace_xfs_writepage(inode, page, 0, 0); @@ -1150,25 +1211,27 @@ xfs_vm_releasepage( * mm accommodates an old ext3 case where clean pages might not have had * the dirty bit cleared. Thus, it can send actual dirty pages to * ->releasepage() via shrink_active_list(). Conversely, - * block_invalidatepage() can send pages that are still marked dirty - * but otherwise have invalidated buffers. + * block_invalidatepage() can send pages that are still marked dirty but + * otherwise have invalidated buffers. * * We want to release the latter to avoid unnecessary buildup of the - * LRU, skip the former and warn if we've left any lingering - * delalloc/unwritten buffers on clean pages. Skip pages with delalloc - * or unwritten buffers and warn if the page is not dirty. Otherwise - * try to release the buffers. + * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages + * that are entirely invalidated and need to be released. Hence the + * only time we should get dirty pages here is through + * shrink_active_list() and so we can simply skip those now. + * + * warn if we've left any lingering delalloc/unwritten buffers on clean + * or invalidated pages we are about to release. */ + if (PageDirty(page)) + return 0; + xfs_count_page_state(page, &delalloc, &unwritten); - if (delalloc) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(delalloc)) return 0; - } - if (unwritten) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(unwritten)) return 0; - } return try_to_free_buffers(page); } diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index cc174ec6c2fd..88c85ea63da0 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -59,5 +59,6 @@ int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); extern void xfs_count_page_state(struct page *, int *, int *); extern struct block_device *xfs_find_bdev_for_inode(struct inode *); +extern struct dax_device *xfs_find_daxdev_for_inode(struct inode *); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h index d14691aa02b4..5d5a5e277f35 100644 --- a/fs/xfs/xfs_attr.h +++ b/fs/xfs/xfs_attr.h @@ -117,6 +117,7 @@ typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int, unsigned char *, int, int); typedef struct xfs_attr_list_context { + struct xfs_trans *tp; struct xfs_inode *dp; /* inode */ struct attrlist_cursor_kern *cursor; /* position in list */ char *alist; /* output buffer */ @@ -140,8 +141,10 @@ typedef struct xfs_attr_list_context { * Overall external interface routines. */ int xfs_attr_inactive(struct xfs_inode *dp); +int xfs_attr_list_int_ilocked(struct xfs_attr_list_context *); int xfs_attr_list_int(struct xfs_attr_list_context *); int xfs_inode_hasattr(struct xfs_inode *ip); +int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args); int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name, unsigned char *value, int *valuelenp, int flags); int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name, diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index be0b79d8900f..e3a950ed35a8 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -97,7 +97,7 @@ xfs_attr3_leaf_freextent( /* * Roll to next transaction. */ - error = xfs_trans_roll(trans, dp); + error = xfs_trans_roll_inode(trans, dp); if (error) return error; } @@ -302,13 +302,15 @@ xfs_attr3_node_inactive( &bp, XFS_ATTR_FORK); if (error) return error; + node = bp->b_addr; + btree = dp->d_ops->node_tree_p(node); child_fsb = be32_to_cpu(btree[i + 1].before); xfs_trans_brelse(*trans, bp); } /* * Atomically commit the whole invalidate stuff. */ - error = xfs_trans_roll(trans, dp); + error = xfs_trans_roll_inode(trans, dp); if (error) return error; } @@ -375,7 +377,7 @@ xfs_attr3_root_inactive( /* * Commit the invalidate and start the next transaction. */ - error = xfs_trans_roll(trans, dp); + error = xfs_trans_roll_inode(trans, dp); return error; } diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 97c45b6eb91e..7740c8a5e736 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -230,7 +230,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) */ bp = NULL; if (cursor->blkno > 0) { - error = xfs_da3_node_read(NULL, dp, cursor->blkno, -1, + error = xfs_da3_node_read(context->tp, dp, cursor->blkno, -1, &bp, XFS_ATTR_FORK); if ((error != 0) && (error != -EFSCORRUPTED)) return error; @@ -242,7 +242,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) case XFS_DA_NODE_MAGIC: case XFS_DA3_NODE_MAGIC: trace_xfs_attr_list_wrong_blk(context); - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); bp = NULL; break; case XFS_ATTR_LEAF_MAGIC: @@ -254,18 +254,18 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) if (cursor->hashval > be32_to_cpu( entries[leafhdr.count - 1].hashval)) { trace_xfs_attr_list_wrong_blk(context); - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); bp = NULL; } else if (cursor->hashval <= be32_to_cpu( entries[0].hashval)) { trace_xfs_attr_list_wrong_blk(context); - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); bp = NULL; } break; default: trace_xfs_attr_list_wrong_blk(context); - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); bp = NULL; } } @@ -279,9 +279,9 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) if (bp == NULL) { cursor->blkno = 0; for (;;) { - __uint16_t magic; + uint16_t magic; - error = xfs_da3_node_read(NULL, dp, + error = xfs_da3_node_read(context->tp, dp, cursor->blkno, -1, &bp, XFS_ATTR_FORK); if (error) @@ -297,7 +297,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) XFS_ERRLEVEL_LOW, context->dp->i_mount, node); - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); return -EFSCORRUPTED; } @@ -313,10 +313,10 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) } } if (i == nodehdr.count) { - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); return 0; } - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); } } ASSERT(bp != NULL); @@ -333,12 +333,12 @@ xfs_attr_node_list(xfs_attr_list_context_t *context) if (context->seen_enough || leafhdr.forw == 0) break; cursor->blkno = leafhdr.forw; - xfs_trans_brelse(NULL, bp); - error = xfs_attr3_leaf_read(NULL, dp, cursor->blkno, -1, &bp); + xfs_trans_brelse(context->tp, bp); + error = xfs_attr3_leaf_read(context->tp, dp, cursor->blkno, -1, &bp); if (error) return error; } - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); return 0; } @@ -448,16 +448,36 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context) trace_xfs_attr_leaf_list(context); context->cursor->blkno = 0; - error = xfs_attr3_leaf_read(NULL, context->dp, 0, -1, &bp); + error = xfs_attr3_leaf_read(context->tp, context->dp, 0, -1, &bp); if (error) return error; xfs_attr3_leaf_list_int(bp, context); - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(context->tp, bp); return 0; } int +xfs_attr_list_int_ilocked( + struct xfs_attr_list_context *context) +{ + struct xfs_inode *dp = context->dp; + + ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + + /* + * Decide on what work routines to call based on the inode size. + */ + if (!xfs_inode_hasattr(dp)) + return 0; + else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) + return xfs_attr_shortform_list(context); + else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) + return xfs_attr_leaf_list(context); + return xfs_attr_node_list(context); +} + +int xfs_attr_list_int( xfs_attr_list_context_t *context) { @@ -470,19 +490,8 @@ xfs_attr_list_int( if (XFS_FORCED_SHUTDOWN(dp->i_mount)) return -EIO; - /* - * Decide on what work routines to call based on the inode size. - */ lock_mode = xfs_ilock_attr_map_shared(dp); - if (!xfs_inode_hasattr(dp)) { - error = 0; - } else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) { - error = xfs_attr_shortform_list(context); - } else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) { - error = xfs_attr_leaf_list(context); - } else { - error = xfs_attr_node_list(context); - } + error = xfs_attr_list_int_ilocked(context); xfs_iunlock(dp, lock_mode); return error; } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index d419d23fa214..dd136f7275e4 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -396,6 +396,7 @@ xfs_bui_recover( struct xfs_map_extent *bmap; xfs_fsblock_t startblock_fsb; xfs_fsblock_t inode_fsb; + xfs_filblks_t count; bool op_ok; struct xfs_bud_log_item *budp; enum xfs_bmap_intent_type type; @@ -404,6 +405,7 @@ xfs_bui_recover( struct xfs_trans *tp; struct xfs_inode *ip = NULL; struct xfs_defer_ops dfops; + struct xfs_bmbt_irec irec; xfs_fsblock_t firstfsb; ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags)); @@ -481,15 +483,26 @@ xfs_bui_recover( } xfs_trans_ijoin(tp, ip, 0); + count = bmap->me_len; error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type, ip, whichfork, bmap->me_startoff, - bmap->me_startblock, bmap->me_len, - state); + bmap->me_startblock, &count, state); if (error) goto err_dfops; + if (count > 0) { + ASSERT(type == XFS_BMAP_UNMAP); + irec.br_startblock = bmap->me_startblock; + irec.br_blockcount = count; + irec.br_startoff = bmap->me_startoff; + irec.br_state = state; + error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec); + if (error) + goto err_dfops; + } + /* Finish transaction, free inodes. */ - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto err_dfops; diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 9e3cc2146d5b..6503cfa44262 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -84,6 +84,7 @@ xfs_zero_extent( GFP_NOFS, 0); } +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ @@ -190,6 +191,7 @@ xfs_bmap_rtalloc( } return 0; } +#endif /* CONFIG_XFS_RT */ /* * Check if the endoff is outside the last extent. If so the caller will grow @@ -219,21 +221,24 @@ xfs_bmap_eof( */ /* - * Count leaf blocks given a range of extent records. + * Count leaf blocks given a range of extent records. Delayed allocation + * extents are not counted towards the totals. */ -STATIC void +xfs_extnum_t xfs_bmap_count_leaves( - xfs_ifork_t *ifp, - xfs_extnum_t idx, - int numrecs, - int *count) + struct xfs_ifork *ifp, + xfs_filblks_t *count) { - int b; + struct xfs_bmbt_irec got; + xfs_extnum_t numrecs = 0, i = 0; - for (b = 0; b < numrecs; b++) { - xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b); - *count += xfs_bmbt_get_blockcount(frp); + while (xfs_iext_get_extent(ifp, i++, &got)) { + if (!isnullstartblock(got.br_startblock)) { + *count += got.br_blockcount; + numrecs++; + } } + return numrecs; } /* @@ -245,7 +250,7 @@ xfs_bmap_disk_count_leaves( struct xfs_mount *mp, struct xfs_btree_block *block, int numrecs, - int *count) + xfs_filblks_t *count) { int b; xfs_bmbt_rec_t *frp; @@ -260,17 +265,18 @@ xfs_bmap_disk_count_leaves( * Recursively walks each level of a btree * to count total fsblocks in use. */ -STATIC int /* error */ +STATIC int xfs_bmap_count_tree( - xfs_mount_t *mp, /* file system mount point */ - xfs_trans_t *tp, /* transaction pointer */ - xfs_ifork_t *ifp, /* inode fork pointer */ - xfs_fsblock_t blockno, /* file system block number */ - int levelin, /* level in btree */ - int *count) /* Count of blocks */ + struct xfs_mount *mp, + struct xfs_trans *tp, + struct xfs_ifork *ifp, + xfs_fsblock_t blockno, + int levelin, + xfs_extnum_t *nextents, + xfs_filblks_t *count) { int error; - xfs_buf_t *bp, *nbp; + struct xfs_buf *bp, *nbp; int level = levelin; __be64 *pp; xfs_fsblock_t bno = blockno; @@ -303,8 +309,9 @@ xfs_bmap_count_tree( /* Dive to the next level */ pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]); bno = be64_to_cpu(*pp); - if (unlikely((error = - xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) { + error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, nextents, + count); + if (error) { xfs_trans_brelse(tp, bp); XFS_ERROR_REPORT("xfs_bmap_count_tree(1)", XFS_ERRLEVEL_LOW, mp); @@ -316,6 +323,7 @@ xfs_bmap_count_tree( for (;;) { nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib); numrecs = be16_to_cpu(block->bb_numrecs); + (*nextents) += numrecs; xfs_bmap_disk_count_leaves(mp, block, numrecs, count); xfs_trans_brelse(tp, bp); if (nextbno == NULLFSBLOCK) @@ -334,46 +342,64 @@ xfs_bmap_count_tree( } /* - * Count fsblocks of the given fork. + * Count fsblocks of the given fork. Delayed allocation extents are + * not counted towards the totals. */ -static int /* error */ +int xfs_bmap_count_blocks( - xfs_trans_t *tp, /* transaction pointer */ - xfs_inode_t *ip, /* incore inode */ - int whichfork, /* data or attr fork */ - int *count) /* out: count of blocks */ + struct xfs_trans *tp, + struct xfs_inode *ip, + int whichfork, + xfs_extnum_t *nextents, + xfs_filblks_t *count) { + struct xfs_mount *mp; /* file system mount structure */ + __be64 *pp; /* pointer to block address */ struct xfs_btree_block *block; /* current btree block */ + struct xfs_ifork *ifp; /* fork structure */ xfs_fsblock_t bno; /* block # of "block" */ - xfs_ifork_t *ifp; /* fork structure */ int level; /* btree level, for checking */ - xfs_mount_t *mp; /* file system mount structure */ - __be64 *pp; /* pointer to block address */ + int error; bno = NULLFSBLOCK; mp = ip->i_mount; + *nextents = 0; + *count = 0; ifp = XFS_IFORK_PTR(ip, whichfork); - if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) { - xfs_bmap_count_leaves(ifp, 0, xfs_iext_count(ifp), count); + if (!ifp) return 0; - } - /* - * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. - */ - block = ifp->if_broot; - level = be16_to_cpu(block->bb_level); - ASSERT(level > 0); - pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); - bno = be64_to_cpu(*pp); - ASSERT(bno != NULLFSBLOCK); - ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount); - ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks); - - if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) { - XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW, - mp); - return -EFSCORRUPTED; + switch (XFS_IFORK_FORMAT(ip, whichfork)) { + case XFS_DINODE_FMT_EXTENTS: + *nextents = xfs_bmap_count_leaves(ifp, count); + return 0; + case XFS_DINODE_FMT_BTREE: + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(tp, ip, whichfork); + if (error) + return error; + } + + /* + * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out. + */ + block = ifp->if_broot; + level = be16_to_cpu(block->bb_level); + ASSERT(level > 0); + pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes); + bno = be64_to_cpu(*pp); + ASSERT(bno != NULLFSBLOCK); + ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount); + ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks); + + error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, + nextents, count); + if (error) { + XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", + XFS_ERRLEVEL_LOW, mp); + return -EFSCORRUPTED; + } + return 0; } return 0; @@ -389,11 +415,11 @@ xfs_getbmapx_fix_eof_hole( struct getbmapx *out, /* output structure */ int prealloced, /* this is a file with * preallocated data space */ - __int64_t end, /* last block requested */ + int64_t end, /* last block requested */ xfs_fsblock_t startblock, bool moretocome) { - __int64_t fixlen; + int64_t fixlen; xfs_mount_t *mp; /* file system mount point */ xfs_ifork_t *ifp; /* inode fork pointer */ xfs_extnum_t lastx; /* last extent pointer */ @@ -455,8 +481,8 @@ xfs_getbmap_adjust_shared( agno = XFS_FSB_TO_AGNO(mp, map->br_startblock); agbno = XFS_FSB_TO_AGBNO(mp, map->br_startblock); - error = xfs_reflink_find_shared(mp, agno, agbno, map->br_blockcount, - &ebno, &elen, true); + error = xfs_reflink_find_shared(mp, NULL, agno, agbno, + map->br_blockcount, &ebno, &elen, true); if (error) return error; @@ -514,9 +540,9 @@ xfs_getbmap( xfs_bmap_format_t formatter, /* format to user */ void *arg) /* formatter arg */ { - __int64_t bmvend; /* last block requested */ + int64_t bmvend; /* last block requested */ int error = 0; /* return value */ - __int64_t fixlen; /* length for -1 case */ + int64_t fixlen; /* length for -1 case */ int i; /* extent number */ int lock; /* lock state */ xfs_bmbt_irec_t *map; /* buffer for user's data */ @@ -605,7 +631,7 @@ xfs_getbmap( if (bmv->bmv_length == -1) { fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen)); bmv->bmv_length = - max_t(__int64_t, fixlen - bmv->bmv_offset, 0); + max_t(int64_t, fixlen - bmv->bmv_offset, 0); } else if (bmv->bmv_length == 0) { bmv->bmv_entries = 0; return 0; @@ -742,7 +768,7 @@ xfs_getbmap( out[cur_ext].bmv_offset + out[cur_ext].bmv_length; bmv->bmv_length = - max_t(__int64_t, 0, bmvend - bmv->bmv_offset); + max_t(int64_t, 0, bmvend - bmv->bmv_offset); /* * In case we don't want to return the hole, @@ -1111,7 +1137,7 @@ xfs_alloc_file_space( /* * Complete the transaction */ - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto error0; @@ -1177,7 +1203,8 @@ xfs_unmap_extent( if (error) goto out_bmap_cancel; - error = xfs_defer_finish(&tp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -1434,7 +1461,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ @@ -1471,7 +1510,7 @@ xfs_shift_file_space( if (error) goto out_bmap_cancel; - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -1617,7 +1656,7 @@ xfs_swap_extents_check_format( * extent format... */ if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) { - if (XFS_IFORK_BOFF(ip) && + if (XFS_IFORK_Q(ip) && XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip)) return -EINVAL; if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <= @@ -1627,7 +1666,7 @@ xfs_swap_extents_check_format( /* Reciprocal target->temp btree format checks */ if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) { - if (XFS_IFORK_BOFF(tip) && + if (XFS_IFORK_Q(tip) && XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip)) return -EINVAL; if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <= @@ -1676,7 +1715,7 @@ xfs_swap_extent_rmap( xfs_filblks_t ilen; xfs_filblks_t rlen; int nimaps; - __uint64_t tip_flags2; + uint64_t tip_flags2; /* * If the source file has shared blocks, we must flag the donor @@ -1752,7 +1791,8 @@ xfs_swap_extent_rmap( if (error) goto out_defer; - error = xfs_defer_finish(tpp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(tpp, &dfops); if (error) goto out_defer; @@ -1789,10 +1829,11 @@ xfs_swap_extent_forks( int *target_log_flags) { struct xfs_ifork tempifp, *ifp, *tifp; - int aforkblks = 0; - int taforkblks = 0; + xfs_filblks_t aforkblks = 0; + xfs_filblks_t taforkblks = 0; + xfs_extnum_t junk; xfs_extnum_t nextents; - __uint64_t tmp; + uint64_t tmp; int error; /* @@ -1800,43 +1841,32 @@ xfs_swap_extent_forks( */ if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) && (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) { - error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, + error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk, &aforkblks); if (error) return error; } if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) && (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) { - error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, + error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk, &taforkblks); if (error) return error; } /* - * Before we've swapped the forks, lets set the owners of the forks - * appropriately. We have to do this as we are demand paging the btree - * buffers, and so the validation done on read will expect the owner - * field to be correctly set. Once we change the owners, we can swap the - * inode forks. + * Btree format (v3) inodes have the inode number stamped in the bmbt + * block headers. We can't start changing the bmbt blocks until the + * inode owner change is logged so recovery does the right thing in the + * event of a crash. Set the owner change log flags now and leave the + * bmbt scan as the last step. */ if (ip->i_d.di_version == 3 && - ip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + ip->i_d.di_format == XFS_DINODE_FMT_BTREE) (*target_log_flags) |= XFS_ILOG_DOWNER; - error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, - tip->i_ino, NULL); - if (error) - return error; - } - if (tip->i_d.di_version == 3 && - tip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + tip->i_d.di_format == XFS_DINODE_FMT_BTREE) (*src_log_flags) |= XFS_ILOG_DOWNER; - error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK, - ip->i_ino, NULL); - if (error) - return error; - } /* * Swap the data forks of the inodes @@ -1850,15 +1880,15 @@ xfs_swap_extent_forks( /* * Fix the on-disk inode values */ - tmp = (__uint64_t)ip->i_d.di_nblocks; + tmp = (uint64_t)ip->i_d.di_nblocks; ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks; tip->i_d.di_nblocks = tmp + taforkblks - aforkblks; - tmp = (__uint64_t) ip->i_d.di_nextents; + tmp = (uint64_t) ip->i_d.di_nextents; ip->i_d.di_nextents = tip->i_d.di_nextents; tip->i_d.di_nextents = tmp; - tmp = (__uint64_t) ip->i_d.di_format; + tmp = (uint64_t) ip->i_d.di_format; ip->i_d.di_format = tip->i_d.di_format; tip->i_d.di_format = tmp; @@ -1914,6 +1944,48 @@ xfs_swap_extent_forks( return 0; } +/* + * Fix up the owners of the bmbt blocks to refer to the current inode. The + * change owner scan attempts to order all modified buffers in the current + * transaction. In the event of ordered buffer failure, the offending buffer is + * physically logged as a fallback and the scan returns -EAGAIN. We must roll + * the transaction in this case to replenish the fallback log reservation and + * restart the scan. This process repeats until the scan completes. + */ +static int +xfs_swap_change_owner( + struct xfs_trans **tpp, + struct xfs_inode *ip, + struct xfs_inode *tmpip) +{ + int error; + struct xfs_trans *tp = *tpp; + + do { + error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino, + NULL); + /* success or fatal error */ + if (error != -EAGAIN) + break; + + error = xfs_trans_roll(tpp); + if (error) + break; + tp = *tpp; + + /* + * Redirty both inodes so they can relog and keep the log tail + * moving forward. + */ + xfs_trans_ijoin(tp, ip, 0); + xfs_trans_ijoin(tp, tmpip, 0); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE); + } while (true); + + return error; +} + int xfs_swap_extents( struct xfs_inode *ip, /* target inode */ @@ -1927,8 +1999,8 @@ xfs_swap_extents( int error = 0; int lock_flags; struct xfs_ifork *cowfp; - __uint64_t f; - int resblks; + uint64_t f; + int resblks = 0; /* * Lock the inodes against other IO, page faults and truncate to @@ -1976,11 +2048,8 @@ xfs_swap_extents( XFS_SWAP_RMAP_SPACE_RES(mp, XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK), XFS_DATA_FORK); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, - 0, 0, &tp); - } else - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, - 0, 0, &tp); + } + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); if (error) goto out_unlock; @@ -2055,17 +2124,54 @@ xfs_swap_extents( ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK; + } + + /* Swap the cow forks. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + xfs_extnum_t extnum; + + ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS); + ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS); + + extnum = ip->i_cnextents; + ip->i_cnextents = tip->i_cnextents; + tip->i_cnextents = extnum; + cowfp = ip->i_cowfp; ip->i_cowfp = tip->i_cowfp; tip->i_cowfp = cowfp; - xfs_inode_set_cowblocks_tag(ip); - xfs_inode_set_cowblocks_tag(tip); + + if (ip->i_cowfp && ip->i_cnextents) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); + if (tip->i_cowfp && tip->i_cnextents) + xfs_inode_set_cowblocks_tag(tip); + else + xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); xfs_trans_log_inode(tp, tip, target_log_flags); /* + * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems + * have inode number owner values in the bmbt blocks that still refer to + * the old inode. Scan each bmbt to fix up the owner values with the + * inode number of the current inode. + */ + if (src_log_flags & XFS_ILOG_DOWNER) { + error = xfs_swap_change_owner(&tp, ip, tip); + if (error) + goto out_trans_cancel; + } + if (target_log_flags & XFS_ILOG_DOWNER) { + error = xfs_swap_change_owner(&tp, tip, ip); + if (error) + goto out_trans_cancel; + } + + /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. */ diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 135d8267e284..7d330b3c77c3 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -28,7 +28,20 @@ struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); +#else /* !CONFIG_XFS_RT */ +/* + * Attempts to allocate RT extents when RT is disable indicates corruption and + * should trigger a shutdown. + */ +static inline int +xfs_bmap_rtalloc(struct xfs_bmalloca *ap) +{ + return -EFSCORRUPTED; +} +#endif /* CONFIG_XFS_RT */ + int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, @@ -70,4 +83,9 @@ int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip, xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb); +xfs_extnum_t xfs_bmap_count_leaves(struct xfs_ifork *ifp, xfs_filblks_t *count); +int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, + int whichfork, xfs_extnum_t *nextents, + xfs_filblks_t *count); + #endif /* __XFS_BMAP_UTIL_H__ */ diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 16d6a578fc16..2f97c12ca75e 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1194,7 +1194,7 @@ xfs_buf_ioerror_alert( { xfs_alert(bp->b_target->bt_mount, "metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d", - (__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length); + (uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length); } int @@ -1227,8 +1227,11 @@ xfs_buf_bio_end_io( * don't overwrite existing errors - otherwise we can lose errors on * buffers that require multiple bios to complete. */ - if (bio->bi_error) - cmpxchg(&bp->b_io_error, 0, bio->bi_error); + if (bio->bi_status) { + int error = blk_status_to_errno(bio->bi_status); + + cmpxchg(&bp->b_io_error, 0, error); + } if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); @@ -1255,8 +1258,6 @@ xfs_buf_ioapply_map( int size; int offset; - total_nr_pages = bp->b_page_count; - /* skip the pages in the buffer before the start offset */ page_index = 0; offset = *buf_offset; @@ -1278,7 +1279,7 @@ next_chunk: nr_pages = min(total_nr_pages, BIO_MAX_PAGES); bio = bio_alloc(GFP_NOIO, nr_pages); - bio->bi_bdev = bp->b_target->bt_bdev; + bio_set_dev(bio, bp->b_target->bt_bdev); bio->bi_iter.bi_sector = sector; bio->bi_end_io = xfs_buf_bio_end_io; bio->bi_private = bp; @@ -1799,7 +1800,8 @@ xfs_setsize_buftarg_early( xfs_buftarg_t * xfs_alloc_buftarg( struct xfs_mount *mp, - struct block_device *bdev) + struct block_device *bdev, + struct dax_device *dax_dev) { xfs_buftarg_t *btp; @@ -1808,6 +1810,7 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; + btp->bt_daxdev = dax_dev; if (xfs_setsize_buftarg_early(btp, bdev)) goto error; @@ -2047,6 +2050,66 @@ xfs_buf_delwri_submit( return error; } +/* + * Push a single buffer on a delwri queue. + * + * The purpose of this function is to submit a single buffer of a delwri queue + * and return with the buffer still on the original queue. The waiting delwri + * buffer submission infrastructure guarantees transfer of the delwri queue + * buffer reference to a temporary wait list. We reuse this infrastructure to + * transfer the buffer back to the original queue. + * + * Note the buffer transitions from the queued state, to the submitted and wait + * listed state and back to the queued state during this call. The buffer + * locking and queue management logic between _delwri_pushbuf() and + * _delwri_queue() guarantee that the buffer cannot be queued to another list + * before returning. + */ +int +xfs_buf_delwri_pushbuf( + struct xfs_buf *bp, + struct list_head *buffer_list) +{ + LIST_HEAD (submit_list); + int error; + + ASSERT(bp->b_flags & _XBF_DELWRI_Q); + + trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); + + /* + * Isolate the buffer to a new local list so we can submit it for I/O + * independently from the rest of the original list. + */ + xfs_buf_lock(bp); + list_move(&bp->b_list, &submit_list); + xfs_buf_unlock(bp); + + /* + * Delwri submission clears the DELWRI_Q buffer flag and returns with + * the buffer on the wait list with an associated reference. Rather than + * bounce the buffer from a local wait list back to the original list + * after I/O completion, reuse the original list as the wait list. + */ + xfs_buf_delwri_submit_buffers(&submit_list, buffer_list); + + /* + * The buffer is now under I/O and wait listed as during typical delwri + * submission. Lock the buffer to wait for I/O completion. Rather than + * remove the buffer from the wait list and release the reference, we + * want to return with the buffer queued to the original list. The + * buffer already sits on the original list with a wait list reference, + * however. If we let the queue inherit that wait list reference, all we + * need to do is reset the DELWRI_Q flag. + */ + xfs_buf_lock(bp); + error = bp->b_error; + bp->b_flags |= _XBF_DELWRI_Q; + xfs_buf_unlock(bp); + + return error; +} + int __init xfs_buf_init(void) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 1508121f29f2..bf71507ddb16 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -108,6 +108,7 @@ typedef unsigned int xfs_buf_flags_t; typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; + struct dax_device *bt_daxdev; struct xfs_mount *bt_mount; unsigned int bt_meta_sectorsize; size_t bt_meta_sectormask; @@ -332,6 +333,7 @@ extern void xfs_buf_delwri_cancel(struct list_head *); extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); +extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); /* Buffer Daemon Setup Routines */ extern int xfs_buf_init(void); @@ -384,7 +386,7 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset) * Handling of buftargs. */ extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *, - struct block_device *); + struct block_device *, struct dax_device *); extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *); extern void xfs_wait_buftarg(xfs_buftarg_t *); extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 0306168af332..e0a0af0946f2 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -29,6 +29,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_log.h" +#include "xfs_inode.h" kmem_zone_t *xfs_buf_item_zone; @@ -322,6 +323,8 @@ xfs_buf_item_format( ASSERT((bip->bli_flags & XFS_BLI_STALE) || (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED) || + (bip->bli_flags & XFS_BLI_STALE)); /* @@ -346,16 +349,6 @@ xfs_buf_item_format( bip->bli_flags &= ~XFS_BLI_INODE_BUF; } - if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) == - XFS_BLI_ORDERED) { - /* - * The buffer has been logged just to order it. It is not being - * included in the transaction commit, so don't format it. - */ - trace_xfs_buf_item_format_ordered(bip); - return; - } - for (i = 0; i < bip->bli_format_count; i++) { xfs_buf_item_format_segment(bip, lv, &vecp, offset, &bip->bli_formats[i]); @@ -574,26 +567,20 @@ xfs_buf_item_unlock( { struct xfs_buf_log_item *bip = BUF_ITEM(lip); struct xfs_buf *bp = bip->bli_buf; - bool clean; - bool aborted; - int flags; + bool aborted = !!(lip->li_flags & XFS_LI_ABORTED); + bool hold = !!(bip->bli_flags & XFS_BLI_HOLD); + bool dirty = !!(bip->bli_flags & XFS_BLI_DIRTY); +#if defined(DEBUG) || defined(XFS_WARN) + bool ordered = !!(bip->bli_flags & XFS_BLI_ORDERED); +#endif /* Clear the buffer's association with this transaction. */ bp->b_transp = NULL; /* - * If this is a transaction abort, don't return early. Instead, allow - * the brelse to happen. Normally it would be done for stale - * (cancelled) buffers at unpin time, but we'll never go through the - * pin/unpin cycle if we abort inside commit. - */ - aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false; - /* - * Before possibly freeing the buf item, copy the per-transaction state - * so we can reference it safely later after clearing it from the - * buffer log item. + * The per-transaction state has been copied above so clear it from the + * bli. */ - flags = bip->bli_flags; bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED); /* @@ -601,7 +588,7 @@ xfs_buf_item_unlock( * unlock the buffer and free the buf item when the buffer is unpinned * for the last time. */ - if (flags & XFS_BLI_STALE) { + if (bip->bli_flags & XFS_BLI_STALE) { trace_xfs_buf_item_unlock_stale(bip); ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); if (!aborted) { @@ -619,40 +606,34 @@ xfs_buf_item_unlock( * regardless of whether it is dirty or not. A dirty abort implies a * shutdown, anyway. * - * Ordered buffers are dirty but may have no recorded changes, so ensure - * we only release clean items here. + * The bli dirty state should match whether the blf has logged segments + * except for ordered buffers, where only the bli should be dirty. */ - clean = (flags & XFS_BLI_DIRTY) ? false : true; - if (clean) { - int i; - for (i = 0; i < bip->bli_format_count; i++) { - if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map, - bip->bli_formats[i].blf_map_size)) { - clean = false; - break; - } - } - } + ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) || + (ordered && dirty && !xfs_buf_item_dirty_format(bip))); /* * Clean buffers, by definition, cannot be in the AIL. However, aborted - * buffers may be dirty and hence in the AIL. Therefore if we are - * aborting a buffer and we've just taken the last refernce away, we - * have to check if it is in the AIL before freeing it. We need to free - * it in this case, because an aborted transaction has already shut the - * filesystem down and this is the last chance we will have to do so. + * buffers may be in the AIL regardless of dirty state. An aborted + * transaction that invalidates a buffer already in the AIL may have + * marked it stale and cleared the dirty state, for example. + * + * Therefore if we are aborting a buffer and we've just taken the last + * reference away, we have to check if it is in the AIL before freeing + * it. We need to free it in this case, because an aborted transaction + * has already shut the filesystem down and this is the last chance we + * will have to do so. */ if (atomic_dec_and_test(&bip->bli_refcount)) { - if (clean) - xfs_buf_item_relse(bp); - else if (aborted) { + if (aborted) { ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR); xfs_buf_item_relse(bp); - } + } else if (!dirty) + xfs_buf_item_relse(bp); } - if (!(flags & XFS_BLI_HOLD)) + if (!hold) xfs_buf_relse(bp); } @@ -942,14 +923,22 @@ xfs_buf_item_log( /* - * Return 1 if the buffer has been logged or ordered in a transaction (at any - * point, not just the current transaction) and 0 if not. + * Return true if the buffer has any ranges logged/dirtied by a transaction, + * false otherwise. */ -uint -xfs_buf_item_dirty( - xfs_buf_log_item_t *bip) +bool +xfs_buf_item_dirty_format( + struct xfs_buf_log_item *bip) { - return (bip->bli_flags & XFS_BLI_DIRTY); + int i; + + for (i = 0; i < bip->bli_format_count; i++) { + if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map, + bip->bli_formats[i].blf_map_size)) + return true; + } + + return false; } STATIC void @@ -1051,6 +1040,31 @@ xfs_buf_do_callbacks( } } +/* + * Invoke the error state callback for each log item affected by the failed I/O. + * + * If a metadata buffer write fails with a non-permanent error, the buffer is + * eventually resubmitted and so the completion callbacks are not run. The error + * state may need to be propagated to the log items attached to the buffer, + * however, so the next AIL push of the item knows hot to handle it correctly. + */ +STATIC void +xfs_buf_do_callbacks_fail( + struct xfs_buf *bp) +{ + struct xfs_log_item *next; + struct xfs_log_item *lip = bp->b_fspriv; + struct xfs_ail *ailp = lip->li_ailp; + + spin_lock(&ailp->xa_lock); + for (; lip; lip = next) { + next = lip->li_bio_list; + if (lip->li_ops->iop_error) + lip->li_ops->iop_error(lip, bp); + } + spin_unlock(&ailp->xa_lock); +} + static bool xfs_buf_iodone_callback_error( struct xfs_buf *bp) @@ -1120,7 +1134,11 @@ xfs_buf_iodone_callback_error( if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount) goto permanent_error; - /* still a transient error, higher layers will retry */ + /* + * Still a transient error, run IO completion failure callbacks and let + * the higher layers retry the buffer. + */ + xfs_buf_do_callbacks_fail(bp); xfs_buf_ioerror(bp, 0); xfs_buf_relse(bp); return true; @@ -1201,3 +1219,31 @@ xfs_buf_iodone( xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE); xfs_buf_item_free(BUF_ITEM(lip)); } + +/* + * Requeue a failed buffer for writeback + * + * Return true if the buffer has been re-queued properly, false otherwise + */ +bool +xfs_buf_resubmit_failed_buffers( + struct xfs_buf *bp, + struct xfs_log_item *lip, + struct list_head *buffer_list) +{ + struct xfs_log_item *next; + + /* + * Clear XFS_LI_FAILED flag from all items before resubmit + * + * XFS_LI_FAILED set/clear is protected by xa_lock, caller this + * function already have it acquired + */ + for (; lip; lip = next) { + next = lip->li_bio_list; + xfs_clear_li_failed(lip); + } + + /* Add this buffer back to the delayed write list */ + return xfs_buf_delwri_queue(bp, buffer_list); +} diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index f7eba99d19dd..9690ce62c9a7 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -64,12 +64,15 @@ typedef struct xfs_buf_log_item { int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *); void xfs_buf_item_relse(struct xfs_buf *); void xfs_buf_item_log(xfs_buf_log_item_t *, uint, uint); -uint xfs_buf_item_dirty(xfs_buf_log_item_t *); +bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_attach_iodone(struct xfs_buf *, void(*)(struct xfs_buf *, xfs_log_item_t *), xfs_log_item_t *); void xfs_buf_iodone_callbacks(struct xfs_buf *); void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *); +bool xfs_buf_resubmit_failed_buffers(struct xfs_buf *, + struct xfs_log_item *, + struct list_head *); extern kmem_zone_t *xfs_buf_item_zone; diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 20b7a5c6eb2f..ba2638d37031 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -44,7 +44,7 @@ static unsigned char xfs_dir3_filetype_table[] = { static unsigned char xfs_dir3_get_dtype( struct xfs_mount *mp, - __uint8_t filetype) + uint8_t filetype) { if (!xfs_sb_version_hasftype(&mp->m_sb)) return DT_UNKNOWN; @@ -117,7 +117,7 @@ xfs_dir2_sf_getdents( */ sfep = xfs_dir2_sf_firstentry(sfp); for (i = 0; i < sfp->count; i++) { - __uint8_t filetype; + uint8_t filetype; off = xfs_dir2_db_off_to_dataptr(geo, geo->datablk, xfs_dir2_sf_get_offset(sfep)); @@ -170,7 +170,7 @@ xfs_dir2_block_getdents( return 0; lock_mode = xfs_ilock_data_map_shared(dp); - error = xfs_dir3_block_read(NULL, dp, &bp); + error = xfs_dir3_block_read(args->trans, dp, &bp); xfs_iunlock(dp, lock_mode); if (error) return error; @@ -194,7 +194,7 @@ xfs_dir2_block_getdents( * Each object is a real entry (dep) or an unused one (dup). */ while (ptr < endptr) { - __uint8_t filetype; + uint8_t filetype; dup = (xfs_dir2_data_unused_t *)ptr; /* @@ -228,7 +228,7 @@ xfs_dir2_block_getdents( if (!dir_emit(ctx, (char *)dep->name, dep->namelen, be64_to_cpu(dep->inumber), xfs_dir3_get_dtype(dp->i_mount, filetype))) { - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(args->trans, bp); return 0; } } @@ -239,218 +239,104 @@ xfs_dir2_block_getdents( */ ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) & 0x7fffffff; - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(args->trans, bp); return 0; } -struct xfs_dir2_leaf_map_info { - xfs_extlen_t map_blocks; /* number of fsbs in map */ - xfs_dablk_t map_off; /* last mapped file offset */ - int map_size; /* total entries in *map */ - int map_valid; /* valid entries in *map */ - int nmap; /* mappings to ask xfs_bmapi */ - xfs_dir2_db_t curdb; /* db for current block */ - int ra_current; /* number of read-ahead blks */ - int ra_index; /* *map index for read-ahead */ - int ra_offset; /* map entry offset for ra */ - int ra_want; /* readahead count wanted */ - struct xfs_bmbt_irec map[]; /* map vector for blocks */ -}; - +/* + * Read a directory block and initiate readahead for blocks beyond that. + * We maintain a sliding readahead window of the remaining space in the + * buffer rounded up to the nearest block. + */ STATIC int xfs_dir2_leaf_readbuf( struct xfs_da_args *args, size_t bufsize, - struct xfs_dir2_leaf_map_info *mip, - xfs_dir2_off_t *curoff, - struct xfs_buf **bpp, - bool trim_map) + xfs_dir2_off_t *cur_off, + xfs_dablk_t *ra_blk, + struct xfs_buf **bpp) { struct xfs_inode *dp = args->dp; struct xfs_buf *bp = NULL; - struct xfs_bmbt_irec *map = mip->map; + struct xfs_da_geometry *geo = args->geo; + struct xfs_ifork *ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK); + struct xfs_bmbt_irec map; struct blk_plug plug; + xfs_dir2_off_t new_off; + xfs_dablk_t next_ra; + xfs_dablk_t map_off; + xfs_dablk_t last_da; + xfs_extnum_t idx; + int ra_want; int error = 0; - int length; - int i; - int j; - struct xfs_da_geometry *geo = args->geo; - - /* - * If the caller just finished processing a buffer, it will tell us - * we need to trim that block out of the mapping now it is done. - */ - if (trim_map) { - mip->map_blocks -= geo->fsbcount; - /* - * Loop to get rid of the extents for the - * directory block. - */ - for (i = geo->fsbcount; i > 0; ) { - j = min_t(int, map->br_blockcount, i); - map->br_blockcount -= j; - map->br_startblock += j; - map->br_startoff += j; - /* - * If mapping is done, pitch it from - * the table. - */ - if (!map->br_blockcount && --mip->map_valid) - memmove(&map[0], &map[1], - sizeof(map[0]) * mip->map_valid); - i -= j; - } - } - /* - * Recalculate the readahead blocks wanted. - */ - mip->ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)) - 1; - ASSERT(mip->ra_want >= 0); - - /* - * If we don't have as many as we want, and we haven't - * run out of data blocks, get some more mappings. - */ - if (1 + mip->ra_want > mip->map_blocks && - mip->map_off < xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET)) { - /* - * Get more bmaps, fill in after the ones - * we already have in the table. - */ - mip->nmap = mip->map_size - mip->map_valid; - error = xfs_bmapi_read(dp, mip->map_off, - xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET) - - mip->map_off, - &map[mip->map_valid], &mip->nmap, 0); - - /* - * Don't know if we should ignore this or try to return an - * error. The trouble with returning errors is that readdir - * will just stop without actually passing the error through. - */ + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK); if (error) - goto out; /* XXX */ - - /* - * If we got all the mappings we asked for, set the final map - * offset based on the last bmap value received. Otherwise, - * we've reached the end. - */ - if (mip->nmap == mip->map_size - mip->map_valid) { - i = mip->map_valid + mip->nmap - 1; - mip->map_off = map[i].br_startoff + map[i].br_blockcount; - } else - mip->map_off = xfs_dir2_byte_to_da(geo, - XFS_DIR2_LEAF_OFFSET); - - /* - * Look for holes in the mapping, and eliminate them. Count up - * the valid blocks. - */ - for (i = mip->map_valid; i < mip->map_valid + mip->nmap; ) { - if (map[i].br_startblock == HOLESTARTBLOCK) { - mip->nmap--; - length = mip->map_valid + mip->nmap - i; - if (length) - memmove(&map[i], &map[i + 1], - sizeof(map[i]) * length); - } else { - mip->map_blocks += map[i].br_blockcount; - i++; - } - } - mip->map_valid += mip->nmap; + goto out; } /* - * No valid mappings, so no more data blocks. + * Look for mapped directory blocks at or above the current offset. + * Truncate down to the nearest directory block to start the scanning + * operation. */ - if (!mip->map_valid) { - *curoff = xfs_dir2_da_to_byte(geo, mip->map_off); + last_da = xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET); + map_off = xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, *cur_off)); + if (!xfs_iext_lookup_extent(dp, ifp, map_off, &idx, &map)) goto out; - } + if (map.br_startoff >= last_da) + goto out; + xfs_trim_extent(&map, map_off, last_da - map_off); - /* - * Read the directory block starting at the first mapping. - */ - mip->curdb = xfs_dir2_da_to_db(geo, map->br_startoff); - error = xfs_dir3_data_read(NULL, dp, map->br_startoff, - map->br_blockcount >= geo->fsbcount ? - XFS_FSB_TO_DADDR(dp->i_mount, map->br_startblock) : - -1, &bp); - /* - * Should just skip over the data block instead of giving up. - */ + /* Read the directory block of that first mapping. */ + new_off = xfs_dir2_da_to_byte(geo, map.br_startoff); + if (new_off > *cur_off) + *cur_off = new_off; + error = xfs_dir3_data_read(args->trans, dp, map.br_startoff, -1, &bp); if (error) - goto out; /* XXX */ - - /* - * Adjust the current amount of read-ahead: we just read a block that - * was previously ra. - */ - if (mip->ra_current) - mip->ra_current -= geo->fsbcount; + goto out; /* - * Do we need more readahead? - * Each loop tries to process 1 full dir blk; last may be partial. + * Start readahead for the next bufsize's worth of dir data blocks. + * We may have already issued readahead for some of that range; + * ra_blk tracks the last block we tried to read(ahead). */ + ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)); + if (*ra_blk >= last_da) + goto out; + else if (*ra_blk == 0) + *ra_blk = map.br_startoff; + next_ra = map.br_startoff + geo->fsbcount; + if (next_ra >= last_da) + goto out_no_ra; + if (map.br_blockcount < geo->fsbcount && + !xfs_iext_get_extent(ifp, ++idx, &map)) + goto out_no_ra; + if (map.br_startoff >= last_da) + goto out_no_ra; + xfs_trim_extent(&map, next_ra, last_da - next_ra); + + /* Start ra for each dir (not fs) block that has a mapping. */ blk_start_plug(&plug); - for (mip->ra_index = mip->ra_offset = i = 0; - mip->ra_want > mip->ra_current && i < mip->map_blocks; - i += geo->fsbcount) { - ASSERT(mip->ra_index < mip->map_valid); - /* - * Read-ahead a contiguous directory block. - */ - if (i > mip->ra_current && - (map[mip->ra_index].br_blockcount - mip->ra_offset) >= - geo->fsbcount) { - xfs_dir3_data_readahead(dp, - map[mip->ra_index].br_startoff + mip->ra_offset, - XFS_FSB_TO_DADDR(dp->i_mount, - map[mip->ra_index].br_startblock + - mip->ra_offset)); - mip->ra_current = i; - } - - /* - * Read-ahead a non-contiguous directory block. This doesn't - * use our mapping, but this is a very rare case. - */ - else if (i > mip->ra_current) { - xfs_dir3_data_readahead(dp, - map[mip->ra_index].br_startoff + - mip->ra_offset, -1); - mip->ra_current = i; - } - - /* - * Advance offset through the mapping table, processing a full - * dir block even if it is fragmented into several extents. - * But stop if we have consumed all valid mappings, even if - * it's not yet a full directory block. - */ - for (j = 0; - j < geo->fsbcount && mip->ra_index < mip->map_valid; - j += length ) { - /* - * The rest of this extent but not more than a dir - * block. - */ - length = min_t(int, geo->fsbcount - j, - map[mip->ra_index].br_blockcount - - mip->ra_offset); - mip->ra_offset += length; - - /* - * Advance to the next mapping if this one is used up. - */ - if (mip->ra_offset == map[mip->ra_index].br_blockcount) { - mip->ra_offset = 0; - mip->ra_index++; + while (ra_want > 0) { + next_ra = roundup((xfs_dablk_t)map.br_startoff, geo->fsbcount); + while (ra_want > 0 && + next_ra < map.br_startoff + map.br_blockcount) { + if (next_ra >= last_da) { + *ra_blk = last_da; + break; } + if (next_ra > *ra_blk) { + xfs_dir3_data_readahead(dp, next_ra, -2); + *ra_blk = next_ra; + } + ra_want -= geo->fsbcount; + next_ra += geo->fsbcount; + } + if (!xfs_iext_get_extent(ifp, ++idx, &map)) { + *ra_blk = last_da; + break; } } blk_finish_plug(&plug); @@ -458,6 +344,9 @@ xfs_dir2_leaf_readbuf( out: *bpp = bp; return error; +out_no_ra: + *ra_blk = last_da; + goto out; } /* @@ -475,14 +364,14 @@ xfs_dir2_leaf_getdents( xfs_dir2_data_hdr_t *hdr; /* data block header */ xfs_dir2_data_entry_t *dep; /* data entry */ xfs_dir2_data_unused_t *dup; /* unused entry */ - int error = 0; /* error return value */ - int length; /* temporary length value */ - int byteoff; /* offset in current block */ - xfs_dir2_off_t curoff; /* current overall offset */ - xfs_dir2_off_t newoff; /* new curoff after new blk */ char *ptr = NULL; /* pointer to current data */ - struct xfs_dir2_leaf_map_info *map_info; struct xfs_da_geometry *geo = args->geo; + xfs_dablk_t rablk = 0; /* current readahead block */ + xfs_dir2_off_t curoff; /* current overall offset */ + int length; /* temporary length value */ + int byteoff; /* offset in current block */ + int lock_mode; + int error = 0; /* error return value */ /* * If the offset is at or past the largest allowed value, @@ -492,73 +381,35 @@ xfs_dir2_leaf_getdents( return 0; /* - * Set up to bmap a number of blocks based on the caller's - * buffer size, the directory block size, and the filesystem - * block size. - */ - length = howmany(bufsize + geo->blksize, (1 << geo->fsblog)); - map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) + - (length * sizeof(struct xfs_bmbt_irec)), - KM_SLEEP | KM_NOFS); - map_info->map_size = length; - - /* * Inside the loop we keep the main offset value as a byte offset * in the directory file. */ curoff = xfs_dir2_dataptr_to_byte(ctx->pos); /* - * Force this conversion through db so we truncate the offset - * down to get the start of the data block. - */ - map_info->map_off = xfs_dir2_db_to_da(geo, - xfs_dir2_byte_to_db(geo, curoff)); - - /* * Loop over directory entries until we reach the end offset. * Get more blocks and readahead as necessary. */ while (curoff < XFS_DIR2_LEAF_OFFSET) { - __uint8_t filetype; + uint8_t filetype; /* * If we have no buffer, or we're off the end of the * current buffer, need to get another one. */ if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) { - int lock_mode; - bool trim_map = false; - if (bp) { - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(args->trans, bp); bp = NULL; - trim_map = true; } lock_mode = xfs_ilock_data_map_shared(dp); - error = xfs_dir2_leaf_readbuf(args, bufsize, map_info, - &curoff, &bp, trim_map); + error = xfs_dir2_leaf_readbuf(args, bufsize, &curoff, + &rablk, &bp); xfs_iunlock(dp, lock_mode); - if (error || !map_info->map_valid) + if (error || !bp) break; - /* - * Having done a read, we need to set a new offset. - */ - newoff = xfs_dir2_db_off_to_byte(geo, - map_info->curdb, 0); - /* - * Start of the current block. - */ - if (curoff < newoff) - curoff = newoff; - /* - * Make sure we're in the right block. - */ - else if (curoff > newoff) - ASSERT(xfs_dir2_byte_to_db(geo, curoff) == - map_info->curdb); hdr = bp->b_addr; xfs_dir3_data_check(dp, bp); /* @@ -643,17 +494,22 @@ xfs_dir2_leaf_getdents( ctx->pos = XFS_DIR2_MAX_DATAPTR & 0x7fffffff; else ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff; - kmem_free(map_info); if (bp) - xfs_trans_brelse(NULL, bp); + xfs_trans_brelse(args->trans, bp); return error; } /* * Read a directory. + * + * If supplied, the transaction collects locked dir buffers to avoid + * nested buffer deadlocks. This function does not dirty the + * transaction. The caller should ensure that the inode is locked + * before calling this function. */ int xfs_readdir( + struct xfs_trans *tp, struct xfs_inode *dp, struct dir_context *ctx, size_t bufsize) @@ -672,6 +528,7 @@ xfs_readdir( args.dp = dp; args.geo = dp->i_mount->m_dir_geo; + args.trans = tp; if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) rval = xfs_dir2_sf_getdents(&args, ctx); diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 6a05d278da64..b2cde5426182 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -39,7 +39,7 @@ xfs_trim_extents( xfs_daddr_t start, xfs_daddr_t end, xfs_daddr_t minlen, - __uint64_t *blocks_trimmed) + uint64_t *blocks_trimmed) { struct block_device *bdev = mp->m_ddev_targp->bt_bdev; struct xfs_btree_cur *cur; @@ -166,7 +166,7 @@ xfs_ioc_trim( struct fstrim_range range; xfs_daddr_t start, end, minlen; xfs_agnumber_t start_agno, end_agno, agno; - __uint64_t blocks_trimmed = 0; + uint64_t blocks_trimmed = 0; int error, last_error = 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 9d06cc30e875..cd82429d8df7 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -276,7 +276,7 @@ xfs_qm_init_dquot_blk( void xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp) { - __uint64_t space; + uint64_t space; dqp->q_prealloc_hi_wmark = be64_to_cpu(dqp->q_core.d_blk_hardlimit); dqp->q_prealloc_lo_wmark = be64_to_cpu(dqp->q_core.d_blk_softlimit); @@ -383,7 +383,7 @@ xfs_qm_dqalloc( xfs_trans_bhold(tp, bp); - error = xfs_defer_finish(tpp, &dfops, NULL); + error = xfs_defer_finish(tpp, &dfops); if (error) goto error1; @@ -695,21 +695,18 @@ error0: */ static int xfs_dq_get_next_id( - xfs_mount_t *mp, + struct xfs_mount *mp, uint type, - xfs_dqid_t *id, - loff_t eof) + xfs_dqid_t *id) { - struct xfs_inode *quotip; + struct xfs_inode *quotip = xfs_quota_inode(mp, type); + xfs_dqid_t next_id = *id + 1; /* simple advance */ + uint lock_flags; + struct xfs_bmbt_irec got; + xfs_extnum_t idx; xfs_fsblock_t start; - loff_t offset; - uint lock; - xfs_dqid_t next_id; int error = 0; - /* Simple advance */ - next_id = *id + 1; - /* If we'd wrap past the max ID, stop */ if (next_id < *id) return -ENOENT; @@ -723,23 +720,25 @@ xfs_dq_get_next_id( /* Nope, next_id is now past the current chunk, so find the next one */ start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk; - quotip = xfs_quota_inode(mp, type); - lock = xfs_ilock_data_map_shared(quotip); - - offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start), - eof, SEEK_DATA); - if (offset < 0) - error = offset; + lock_flags = xfs_ilock_data_map_shared(quotip); + if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK); + if (error) + return error; + } - xfs_iunlock(quotip, lock); + if (xfs_iext_lookup_extent(quotip, "ip->i_df, start, &idx, &got)) { + /* contiguous chunk, bump startoff for the id calculation */ + if (got.br_startoff < start) + got.br_startoff = start; + *id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk; + } else { + error = -ENOENT; + } - /* -ENXIO is essentially "no more data" */ - if (error) - return (error == -ENXIO ? -ENOENT: error); + xfs_iunlock(quotip, lock_flags); - /* Convert next data offset back to a quota id */ - *id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk; - return 0; + return error; } /* @@ -762,7 +761,6 @@ xfs_qm_dqget( struct xfs_quotainfo *qi = mp->m_quotainfo; struct radix_tree_root *tree = xfs_dquot_tree(qi, type); struct xfs_dquot *dqp; - loff_t eof = 0; int error; ASSERT(XFS_IS_QUOTA_RUNNING(mp)); @@ -790,21 +788,6 @@ xfs_qm_dqget( } #endif - /* Get the end of the quota file if we need it */ - if (flags & XFS_QMOPT_DQNEXT) { - struct xfs_inode *quotip; - xfs_fileoff_t last; - uint lock_mode; - - quotip = xfs_quota_inode(mp, type); - lock_mode = xfs_ilock_data_map_shared(quotip); - error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK); - xfs_iunlock(quotip, lock_mode); - if (error) - return error; - eof = XFS_FSB_TO_B(mp, last); - } - restart: mutex_lock(&qi->qi_tree_lock); dqp = radix_tree_lookup(tree, id); @@ -823,7 +806,7 @@ restart: if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { xfs_dqunlock(dqp); mutex_unlock(&qi->qi_tree_lock); - error = xfs_dq_get_next_id(mp, type, &id, eof); + error = xfs_dq_get_next_id(mp, type, &id); if (error) return error; goto restart; @@ -858,7 +841,7 @@ restart: /* If we are asked to find next active id, keep looking */ if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) { - error = xfs_dq_get_next_id(mp, type, &id, eof); + error = xfs_dq_get_next_id(mp, type, &id); if (!error) goto restart; } @@ -917,7 +900,7 @@ restart: if (flags & XFS_QMOPT_DQNEXT) { if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) { xfs_qm_dqput(dqp); - error = xfs_dq_get_next_id(mp, type, &id, eof); + error = xfs_dq_get_next_id(mp, type, &id); if (error) return error; goto restart; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index ed7ee4e8af73..eaf86f55b7f2 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -22,103 +22,283 @@ #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_error.h" +#include "xfs_sysfs.h" #ifdef DEBUG -int xfs_etest[XFS_NUM_INJECT_ERROR]; -int64_t xfs_etest_fsid[XFS_NUM_INJECT_ERROR]; -char * xfs_etest_fsname[XFS_NUM_INJECT_ERROR]; -int xfs_error_test_active; +static unsigned int xfs_errortag_random_default[] = { + XFS_RANDOM_DEFAULT, + XFS_RANDOM_IFLUSH_1, + XFS_RANDOM_IFLUSH_2, + XFS_RANDOM_IFLUSH_3, + XFS_RANDOM_IFLUSH_4, + XFS_RANDOM_IFLUSH_5, + XFS_RANDOM_IFLUSH_6, + XFS_RANDOM_DA_READ_BUF, + XFS_RANDOM_BTREE_CHECK_LBLOCK, + XFS_RANDOM_BTREE_CHECK_SBLOCK, + XFS_RANDOM_ALLOC_READ_AGF, + XFS_RANDOM_IALLOC_READ_AGI, + XFS_RANDOM_ITOBP_INOTOBP, + XFS_RANDOM_IUNLINK, + XFS_RANDOM_IUNLINK_REMOVE, + XFS_RANDOM_DIR_INO_VALIDATE, + XFS_RANDOM_BULKSTAT_READ_CHUNK, + XFS_RANDOM_IODONE_IOERR, + XFS_RANDOM_STRATREAD_IOERR, + XFS_RANDOM_STRATCMPL_IOERR, + XFS_RANDOM_DIOWRITE_IOERR, + XFS_RANDOM_BMAPIFORMAT, + XFS_RANDOM_FREE_EXTENT, + XFS_RANDOM_RMAP_FINISH_ONE, + XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE, + XFS_RANDOM_REFCOUNT_FINISH_ONE, + XFS_RANDOM_BMAP_FINISH_ONE, + XFS_RANDOM_AG_RESV_CRITICAL, + XFS_RANDOM_DROP_WRITES, + XFS_RANDOM_LOG_BAD_CRC, + XFS_RANDOM_LOG_ITEM_PIN, +}; -int -xfs_error_test(int error_tag, int *fsidp, char *expression, - int line, char *file, unsigned long randfactor) +struct xfs_errortag_attr { + struct attribute attr; + unsigned int tag; +}; + +static inline struct xfs_errortag_attr * +to_attr(struct attribute *attr) { - int i; - int64_t fsid; + return container_of(attr, struct xfs_errortag_attr, attr); +} - if (prandom_u32() % randfactor) - return 0; +static inline struct xfs_mount * +to_mp(struct kobject *kobject) +{ + struct xfs_kobj *kobj = to_kobj(kobject); - memcpy(&fsid, fsidp, sizeof(xfs_fsid_t)); + return container_of(kobj, struct xfs_mount, m_errortag_kobj); +} + +STATIC ssize_t +xfs_errortag_attr_store( + struct kobject *kobject, + struct attribute *attr, + const char *buf, + size_t count) +{ + struct xfs_mount *mp = to_mp(kobject); + struct xfs_errortag_attr *xfs_attr = to_attr(attr); + int ret; + unsigned int val; - for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) { - if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) { - xfs_warn(NULL, - "Injecting error (%s) at file %s, line %d, on filesystem \"%s\"", - expression, file, line, xfs_etest_fsname[i]); - return 1; - } + if (strcmp(buf, "default") == 0) { + val = xfs_errortag_random_default[xfs_attr->tag]; + } else { + ret = kstrtouint(buf, 0, &val); + if (ret) + return ret; } - return 0; + ret = xfs_errortag_set(mp, xfs_attr->tag, val); + if (ret) + return ret; + return count; } +STATIC ssize_t +xfs_errortag_attr_show( + struct kobject *kobject, + struct attribute *attr, + char *buf) +{ + struct xfs_mount *mp = to_mp(kobject); + struct xfs_errortag_attr *xfs_attr = to_attr(attr); + + return snprintf(buf, PAGE_SIZE, "%u\n", + xfs_errortag_get(mp, xfs_attr->tag)); +} + +static const struct sysfs_ops xfs_errortag_sysfs_ops = { + .show = xfs_errortag_attr_show, + .store = xfs_errortag_attr_store, +}; + +#define XFS_ERRORTAG_ATTR_RW(_name, _tag) \ +static struct xfs_errortag_attr xfs_errortag_attr_##_name = { \ + .attr = {.name = __stringify(_name), \ + .mode = VERIFY_OCTAL_PERMISSIONS(S_IWUSR | S_IRUGO) }, \ + .tag = (_tag), \ +} + +#define XFS_ERRORTAG_ATTR_LIST(_name) &xfs_errortag_attr_##_name.attr + +XFS_ERRORTAG_ATTR_RW(noerror, XFS_ERRTAG_NOERROR); +XFS_ERRORTAG_ATTR_RW(iflush1, XFS_ERRTAG_IFLUSH_1); +XFS_ERRORTAG_ATTR_RW(iflush2, XFS_ERRTAG_IFLUSH_2); +XFS_ERRORTAG_ATTR_RW(iflush3, XFS_ERRTAG_IFLUSH_3); +XFS_ERRORTAG_ATTR_RW(iflush4, XFS_ERRTAG_IFLUSH_4); +XFS_ERRORTAG_ATTR_RW(iflush5, XFS_ERRTAG_IFLUSH_5); +XFS_ERRORTAG_ATTR_RW(iflush6, XFS_ERRTAG_IFLUSH_6); +XFS_ERRORTAG_ATTR_RW(dareadbuf, XFS_ERRTAG_DA_READ_BUF); +XFS_ERRORTAG_ATTR_RW(btree_chk_lblk, XFS_ERRTAG_BTREE_CHECK_LBLOCK); +XFS_ERRORTAG_ATTR_RW(btree_chk_sblk, XFS_ERRTAG_BTREE_CHECK_SBLOCK); +XFS_ERRORTAG_ATTR_RW(readagf, XFS_ERRTAG_ALLOC_READ_AGF); +XFS_ERRORTAG_ATTR_RW(readagi, XFS_ERRTAG_IALLOC_READ_AGI); +XFS_ERRORTAG_ATTR_RW(itobp, XFS_ERRTAG_ITOBP_INOTOBP); +XFS_ERRORTAG_ATTR_RW(iunlink, XFS_ERRTAG_IUNLINK); +XFS_ERRORTAG_ATTR_RW(iunlinkrm, XFS_ERRTAG_IUNLINK_REMOVE); +XFS_ERRORTAG_ATTR_RW(dirinovalid, XFS_ERRTAG_DIR_INO_VALIDATE); +XFS_ERRORTAG_ATTR_RW(bulkstat, XFS_ERRTAG_BULKSTAT_READ_CHUNK); +XFS_ERRORTAG_ATTR_RW(logiodone, XFS_ERRTAG_IODONE_IOERR); +XFS_ERRORTAG_ATTR_RW(stratread, XFS_ERRTAG_STRATREAD_IOERR); +XFS_ERRORTAG_ATTR_RW(stratcmpl, XFS_ERRTAG_STRATCMPL_IOERR); +XFS_ERRORTAG_ATTR_RW(diowrite, XFS_ERRTAG_DIOWRITE_IOERR); +XFS_ERRORTAG_ATTR_RW(bmapifmt, XFS_ERRTAG_BMAPIFORMAT); +XFS_ERRORTAG_ATTR_RW(free_extent, XFS_ERRTAG_FREE_EXTENT); +XFS_ERRORTAG_ATTR_RW(rmap_finish_one, XFS_ERRTAG_RMAP_FINISH_ONE); +XFS_ERRORTAG_ATTR_RW(refcount_continue_update, XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE); +XFS_ERRORTAG_ATTR_RW(refcount_finish_one, XFS_ERRTAG_REFCOUNT_FINISH_ONE); +XFS_ERRORTAG_ATTR_RW(bmap_finish_one, XFS_ERRTAG_BMAP_FINISH_ONE); +XFS_ERRORTAG_ATTR_RW(ag_resv_critical, XFS_ERRTAG_AG_RESV_CRITICAL); +XFS_ERRORTAG_ATTR_RW(drop_writes, XFS_ERRTAG_DROP_WRITES); +XFS_ERRORTAG_ATTR_RW(log_bad_crc, XFS_ERRTAG_LOG_BAD_CRC); +XFS_ERRORTAG_ATTR_RW(log_item_pin, XFS_ERRTAG_LOG_ITEM_PIN); + +static struct attribute *xfs_errortag_attrs[] = { + XFS_ERRORTAG_ATTR_LIST(noerror), + XFS_ERRORTAG_ATTR_LIST(iflush1), + XFS_ERRORTAG_ATTR_LIST(iflush2), + XFS_ERRORTAG_ATTR_LIST(iflush3), + XFS_ERRORTAG_ATTR_LIST(iflush4), + XFS_ERRORTAG_ATTR_LIST(iflush5), + XFS_ERRORTAG_ATTR_LIST(iflush6), + XFS_ERRORTAG_ATTR_LIST(dareadbuf), + XFS_ERRORTAG_ATTR_LIST(btree_chk_lblk), + XFS_ERRORTAG_ATTR_LIST(btree_chk_sblk), + XFS_ERRORTAG_ATTR_LIST(readagf), + XFS_ERRORTAG_ATTR_LIST(readagi), + XFS_ERRORTAG_ATTR_LIST(itobp), + XFS_ERRORTAG_ATTR_LIST(iunlink), + XFS_ERRORTAG_ATTR_LIST(iunlinkrm), + XFS_ERRORTAG_ATTR_LIST(dirinovalid), + XFS_ERRORTAG_ATTR_LIST(bulkstat), + XFS_ERRORTAG_ATTR_LIST(logiodone), + XFS_ERRORTAG_ATTR_LIST(stratread), + XFS_ERRORTAG_ATTR_LIST(stratcmpl), + XFS_ERRORTAG_ATTR_LIST(diowrite), + XFS_ERRORTAG_ATTR_LIST(bmapifmt), + XFS_ERRORTAG_ATTR_LIST(free_extent), + XFS_ERRORTAG_ATTR_LIST(rmap_finish_one), + XFS_ERRORTAG_ATTR_LIST(refcount_continue_update), + XFS_ERRORTAG_ATTR_LIST(refcount_finish_one), + XFS_ERRORTAG_ATTR_LIST(bmap_finish_one), + XFS_ERRORTAG_ATTR_LIST(ag_resv_critical), + XFS_ERRORTAG_ATTR_LIST(drop_writes), + XFS_ERRORTAG_ATTR_LIST(log_bad_crc), + XFS_ERRORTAG_ATTR_LIST(log_item_pin), + NULL, +}; + +struct kobj_type xfs_errortag_ktype = { + .release = xfs_sysfs_release, + .sysfs_ops = &xfs_errortag_sysfs_ops, + .default_attrs = xfs_errortag_attrs, +}; + int -xfs_errortag_add(unsigned int error_tag, xfs_mount_t *mp) +xfs_errortag_init( + struct xfs_mount *mp) { - int i; - int len; - int64_t fsid; + mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX, + KM_SLEEP | KM_MAYFAIL); + if (!mp->m_errortag) + return -ENOMEM; - if (error_tag >= XFS_ERRTAG_MAX) - return -EINVAL; + return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype, + &mp->m_kobj, "errortag"); +} - memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t)); +void +xfs_errortag_del( + struct xfs_mount *mp) +{ + xfs_sysfs_del(&mp->m_errortag_kobj); + kmem_free(mp->m_errortag); +} - for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) { - if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) { - xfs_warn(mp, "error tag #%d on", error_tag); - return 0; - } - } +bool +xfs_errortag_test( + struct xfs_mount *mp, + const char *expression, + const char *file, + int line, + unsigned int error_tag) +{ + unsigned int randfactor; - for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) { - if (xfs_etest[i] == 0) { - xfs_warn(mp, "Turned on XFS error tag #%d", - error_tag); - xfs_etest[i] = error_tag; - xfs_etest_fsid[i] = fsid; - len = strlen(mp->m_fsname); - xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP); - strcpy(xfs_etest_fsname[i], mp->m_fsname); - xfs_error_test_active++; - return 0; - } - } + /* + * To be able to use error injection anywhere, we need to ensure error + * injection mechanism is already initialized. + * + * Code paths like I/O completion can be called before the + * initialization is complete, but be able to inject errors in such + * places is still useful. + */ + if (!mp->m_errortag) + return false; - xfs_warn(mp, "error tag overflow, too many turned on"); + ASSERT(error_tag < XFS_ERRTAG_MAX); + randfactor = mp->m_errortag[error_tag]; + if (!randfactor || prandom_u32() % randfactor) + return false; - return 1; + xfs_warn_ratelimited(mp, +"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"", + expression, file, line, mp->m_fsname); + return true; } int -xfs_errortag_clearall(xfs_mount_t *mp, int loud) +xfs_errortag_get( + struct xfs_mount *mp, + unsigned int error_tag) { - int64_t fsid; - int cleared = 0; - int i; - - memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t)); - - - for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) { - if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) && - xfs_etest[i] != 0) { - cleared = 1; - xfs_warn(mp, "Clearing XFS error tag #%d", - xfs_etest[i]); - xfs_etest[i] = 0; - xfs_etest_fsid[i] = 0LL; - kmem_free(xfs_etest_fsname[i]); - xfs_etest_fsname[i] = NULL; - xfs_error_test_active--; - } - } + if (error_tag >= XFS_ERRTAG_MAX) + return -EINVAL; + + return mp->m_errortag[error_tag]; +} + +int +xfs_errortag_set( + struct xfs_mount *mp, + unsigned int error_tag, + unsigned int tag_value) +{ + if (error_tag >= XFS_ERRTAG_MAX) + return -EINVAL; - if (loud || cleared) - xfs_warn(mp, "Cleared all XFS error tags for filesystem"); + mp->m_errortag[error_tag] = tag_value; + return 0; +} +int +xfs_errortag_add( + struct xfs_mount *mp, + unsigned int error_tag) +{ + if (error_tag >= XFS_ERRTAG_MAX) + return -EINVAL; + + return xfs_errortag_set(mp, error_tag, + xfs_errortag_random_default[error_tag]); +} + +int +xfs_errortag_clearall( + struct xfs_mount *mp) +{ + memset(mp->m_errortag, 0, sizeof(unsigned int) * XFS_ERRTAG_MAX); return 0; } #endif /* DEBUG */ @@ -167,7 +347,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h index 05f8666733a0..7c4bef3bddb7 100644 --- a/fs/xfs/xfs_error.h +++ b/fs/xfs/xfs_error.h @@ -96,7 +96,18 @@ extern void xfs_verifier_error(struct xfs_buf *bp); #define XFS_ERRTAG_REFCOUNT_FINISH_ONE 25 #define XFS_ERRTAG_BMAP_FINISH_ONE 26 #define XFS_ERRTAG_AG_RESV_CRITICAL 27 -#define XFS_ERRTAG_MAX 28 +/* + * DEBUG mode instrumentation to test and/or trigger delayed allocation + * block killing in the event of failed writes. When enabled, all + * buffered writes are silenty dropped and handled as if they failed. + * All delalloc blocks in the range of the write (including pre-existing + * delalloc blocks!) are tossed as part of the write failure error + * handling sequence. + */ +#define XFS_ERRTAG_DROP_WRITES 28 +#define XFS_ERRTAG_LOG_BAD_CRC 29 +#define XFS_ERRTAG_LOG_ITEM_PIN 30 +#define XFS_ERRTAG_MAX 31 /* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -129,23 +140,30 @@ extern void xfs_verifier_error(struct xfs_buf *bp); #define XFS_RANDOM_REFCOUNT_FINISH_ONE 1 #define XFS_RANDOM_BMAP_FINISH_ONE 1 #define XFS_RANDOM_AG_RESV_CRITICAL 4 +#define XFS_RANDOM_DROP_WRITES 1 +#define XFS_RANDOM_LOG_BAD_CRC 1 +#define XFS_RANDOM_LOG_ITEM_PIN 1 #ifdef DEBUG -extern int xfs_error_test_active; -extern int xfs_error_test(int, int *, char *, int, char *, unsigned long); - -#define XFS_NUM_INJECT_ERROR 10 -#define XFS_TEST_ERROR(expr, mp, tag, rf) \ - ((expr) || (xfs_error_test_active && \ - xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \ - (rf)))) +extern int xfs_errortag_init(struct xfs_mount *mp); +extern void xfs_errortag_del(struct xfs_mount *mp); +extern bool xfs_errortag_test(struct xfs_mount *mp, const char *expression, + const char *file, int line, unsigned int error_tag); +#define XFS_TEST_ERROR(expr, mp, tag) \ + ((expr) || xfs_errortag_test((mp), #expr, __FILE__, __LINE__, (tag))) -extern int xfs_errortag_add(unsigned int error_tag, struct xfs_mount *mp); -extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud); +extern int xfs_errortag_get(struct xfs_mount *mp, unsigned int error_tag); +extern int xfs_errortag_set(struct xfs_mount *mp, unsigned int error_tag, + unsigned int tag_value); +extern int xfs_errortag_add(struct xfs_mount *mp, unsigned int error_tag); +extern int xfs_errortag_clearall(struct xfs_mount *mp); #else -#define XFS_TEST_ERROR(expr, mp, tag, rf) (expr) -#define xfs_errortag_add(tag, mp) (ENOSYS) -#define xfs_errortag_clearall(mp, loud) (ENOSYS) +#define xfs_errortag_init(mp) (0) +#define xfs_errortag_del(mp) +#define XFS_TEST_ERROR(expr, mp, tag) (expr) +#define xfs_errortag_set(mp, tag, val) (ENOSYS) +#define xfs_errortag_add(mp, tag) (ENOSYS) +#define xfs_errortag_clearall(mp) (ENOSYS) #endif /* DEBUG */ /* diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 5fb5a0958a14..56d0e526870c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -58,7 +58,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int @@ -140,7 +140,7 @@ xfs_file_fsync( trace_xfs_file_fsync(ip); - error = filemap_write_and_wait_range(inode->i_mapping, start, end); + error = file_write_and_wait_range(file, start, end); if (error) return error; @@ -237,7 +237,11 @@ xfs_file_dax_read( if (!count) return 0; /* skip atime */ - xfs_ilock(ip, XFS_IOLOCK_SHARED); + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, XFS_IOLOCK_SHARED); + } ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -255,7 +259,11 @@ xfs_file_buffered_aio_read( trace_xfs_file_buffered_read(ip, iov_iter_count(to), iocb->ki_pos); - xfs_ilock(ip, XFS_IOLOCK_SHARED); + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, XFS_IOLOCK_SHARED); + } ret = generic_file_read_iter(iocb, to); xfs_iunlock(ip, XFS_IOLOCK_SHARED); @@ -369,8 +377,6 @@ restart: */ spin_lock(&ip->i_flags_lock); if (iocb->ki_pos > i_size_read(inode)) { - bool zero = false; - spin_unlock(&ip->i_flags_lock); if (!drained_dio) { if (*iolock == XFS_IOLOCK_SHARED) { @@ -391,7 +397,7 @@ restart: drained_dio = true; goto restart; } - error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero); + error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL); if (error) return error; } else @@ -428,7 +434,6 @@ xfs_dio_write_end_io( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); loff_t offset = iocb->ki_pos; - bool update_size = false; int error = 0; trace_xfs_end_io_direct_write(ip, offset, size); @@ -439,6 +444,21 @@ xfs_dio_write_end_io( if (size <= 0) return size; + if (flags & IOMAP_DIO_COW) { + error = xfs_reflink_end_cow(ip, offset, size); + if (error) + return error; + } + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & IOMAP_DIO_UNWRITTEN) + return xfs_iomap_write_unwritten(ip, offset, size, true); + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -453,20 +473,11 @@ xfs_dio_write_end_io( spin_lock(&ip->i_flags_lock); if (offset + size > i_size_read(inode)) { i_size_write(inode, offset + size); - update_size = true; - } - spin_unlock(&ip->i_flags_lock); - - if (flags & IOMAP_DIO_COW) { - error = xfs_reflink_end_cow(ip, offset, size); - if (error) - return error; - } - - if (flags & IOMAP_DIO_UNWRITTEN) - error = xfs_iomap_write_unwritten(ip, offset, size); - else if (update_size) + spin_unlock(&ip->i_flags_lock); error = xfs_setfilesize(ip, offset, size); + } else { + spin_unlock(&ip->i_flags_lock); + } return error; } @@ -541,7 +552,11 @@ xfs_file_dio_aio_write( iolock = XFS_IOLOCK_SHARED; } - xfs_ilock(ip, iolock); + if (!xfs_ilock_nowait(ip, iolock)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, iolock); + } ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) @@ -553,9 +568,15 @@ xfs_file_dio_aio_write( * otherwise demote the lock if we had to take the exclusive lock * for other reasons in xfs_file_aio_write_checks. */ - if (unaligned_io) - inode_dio_wait(inode); - else if (iolock == XFS_IOLOCK_EXCL) { + if (unaligned_io) { + /* If we are going to wait for other DIO to finish, bail */ + if (iocb->ki_flags & IOCB_NOWAIT) { + if (atomic_read(&inode->i_dio_count)) + return -EAGAIN; + } else { + inode_dio_wait(inode); + } + } else if (iolock == XFS_IOLOCK_EXCL) { xfs_ilock_demote(ip, XFS_IOLOCK_EXCL); iolock = XFS_IOLOCK_SHARED; } @@ -585,7 +606,12 @@ xfs_file_dax_write( size_t count; loff_t pos; - xfs_ilock(ip, iolock); + if (!xfs_ilock_nowait(ip, iolock)) { + if (iocb->ki_flags & IOCB_NOWAIT) + return -EAGAIN; + xfs_ilock(ip, iolock); + } + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; @@ -617,6 +643,9 @@ xfs_file_buffered_aio_write( int enospc = 0; int iolock; + if (iocb->ki_flags & IOCB_NOWAIT) + return -EOPNOTSUPP; + write_retry: iolock = XFS_IOLOCK_EXCL; xfs_ilock(ip, iolock); @@ -660,6 +689,7 @@ write_retry: xfs_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; xfs_icache_free_eofblocks(ip->i_mount, &eofb); + xfs_icache_free_cowblocks(ip->i_mount, &eofb); goto write_retry; } @@ -734,7 +764,7 @@ xfs_file_fallocate( enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL; loff_t new_size = 0; - bool do_file_insert = 0; + bool do_file_insert = false; if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -795,7 +825,7 @@ xfs_file_fallocate( error = -EINVAL; goto out_unlock; } - do_file_insert = 1; + do_file_insert = true; } else { flags |= XFS_PREALLOC_SET; @@ -892,6 +922,7 @@ xfs_file_open( return -EFBIG; if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb))) return -EIO; + file->f_mode |= FMODE_NOWAIT; return 0; } @@ -950,362 +981,7 @@ xfs_file_readdir( */ bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size); - return xfs_readdir(ip, ctx, bufsize); -} - -/* - * This type is designed to indicate the type of offset we would like - * to search from page cache for xfs_seek_hole_data(). - */ -enum { - HOLE_OFF = 0, - DATA_OFF, -}; - -/* - * Lookup the desired type of offset from the given page. - * - * On success, return true and the offset argument will point to the - * start of the region that was found. Otherwise this function will - * return false and keep the offset argument unchanged. - */ -STATIC bool -xfs_lookup_buffer_offset( - struct page *page, - loff_t *offset, - unsigned int type) -{ - loff_t lastoff = page_offset(page); - bool found = false; - struct buffer_head *bh, *head; - - bh = head = page_buffers(page); - do { - /* - * Unwritten extents that have data in the page - * cache covering them can be identified by the - * BH_Unwritten state flag. Pages with multiple - * buffers might have a mix of holes, data and - * unwritten extents - any buffer with valid - * data in it should have BH_Uptodate flag set - * on it. - */ - if (buffer_unwritten(bh) || - buffer_uptodate(bh)) { - if (type == DATA_OFF) - found = true; - } else { - if (type == HOLE_OFF) - found = true; - } - - if (found) { - *offset = lastoff; - break; - } - lastoff += bh->b_size; - } while ((bh = bh->b_this_page) != head); - - return found; -} - -/* - * This routine is called to find out and return a data or hole offset - * from the page cache for unwritten extents according to the desired - * type for xfs_seek_hole_data(). - * - * The argument offset is used to tell where we start to search from the - * page cache. Map is used to figure out the end points of the range to - * lookup pages. - * - * Return true if the desired type of offset was found, and the argument - * offset is filled with that address. Otherwise, return false and keep - * offset unchanged. - */ -STATIC bool -xfs_find_get_desired_pgoff( - struct inode *inode, - struct xfs_bmbt_irec *map, - unsigned int type, - loff_t *offset) -{ - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - struct pagevec pvec; - pgoff_t index; - pgoff_t end; - loff_t endoff; - loff_t startoff = *offset; - loff_t lastoff = startoff; - bool found = false; - - pagevec_init(&pvec, 0); - - index = startoff >> PAGE_SHIFT; - endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount); - end = (endoff - 1) >> PAGE_SHIFT; - do { - int want; - unsigned nr_pages; - unsigned int i; - - want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; - nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, - want); - if (nr_pages == 0) - break; - - for (i = 0; i < nr_pages; i++) { - struct page *page = pvec.pages[i]; - loff_t b_offset; - - /* - * At this point, the page may be truncated or - * invalidated (changing page->mapping to NULL), - * or even swizzled back from swapper_space to tmpfs - * file mapping. However, page->index will not change - * because we have a reference on the page. - * - * If current page offset is beyond where we've ended, - * we've found a hole. - */ - if (type == HOLE_OFF && lastoff < endoff && - lastoff < page_offset(pvec.pages[i])) { - found = true; - *offset = lastoff; - goto out; - } - /* Searching done if the page index is out of range. */ - if (page->index > end) - goto out; - - lock_page(page); - /* - * Page truncated or invalidated(page->mapping == NULL). - * We can freely skip it and proceed to check the next - * page. - */ - if (unlikely(page->mapping != inode->i_mapping)) { - unlock_page(page); - continue; - } - - if (!page_has_buffers(page)) { - unlock_page(page); - continue; - } - - found = xfs_lookup_buffer_offset(page, &b_offset, type); - if (found) { - /* - * The found offset may be less than the start - * point to search if this is the first time to - * come here. - */ - *offset = max_t(loff_t, startoff, b_offset); - unlock_page(page); - goto out; - } - - /* - * We either searching data but nothing was found, or - * searching hole but found a data buffer. In either - * case, probably the next page contains the desired - * things, update the last offset to it so. - */ - lastoff = page_offset(page) + PAGE_SIZE; - unlock_page(page); - } - - /* - * The number of returned pages less than our desired, search - * done. - */ - if (nr_pages < want) - break; - - index = pvec.pages[i - 1]->index + 1; - pagevec_release(&pvec); - } while (index <= end); - - /* No page at lastoff and we are not done - we found a hole. */ - if (type == HOLE_OFF && lastoff < endoff) { - *offset = lastoff; - found = true; - } -out: - pagevec_release(&pvec); - return found; -} - -/* - * caller must lock inode with xfs_ilock_data_map_shared, - * can we craft an appropriate ASSERT? - * - * end is because the VFS-level lseek interface is defined such that any - * offset past i_size shall return -ENXIO, but we use this for quota code - * which does not maintain i_size, and we want to SEEK_DATA past i_size. - */ -loff_t -__xfs_seek_hole_data( - struct inode *inode, - loff_t start, - loff_t end, - int whence) -{ - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - loff_t uninitialized_var(offset); - xfs_fileoff_t fsbno; - xfs_filblks_t lastbno; - int error; - - if (start >= end) { - error = -ENXIO; - goto out_error; - } - - /* - * Try to read extents from the first block indicated - * by fsbno to the end block of the file. - */ - fsbno = XFS_B_TO_FSBT(mp, start); - lastbno = XFS_B_TO_FSB(mp, end); - - for (;;) { - struct xfs_bmbt_irec map[2]; - int nmap = 2; - unsigned int i; - - error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap, - XFS_BMAPI_ENTIRE); - if (error) - goto out_error; - - /* No extents at given offset, must be beyond EOF */ - if (nmap == 0) { - error = -ENXIO; - goto out_error; - } - - for (i = 0; i < nmap; i++) { - offset = max_t(loff_t, start, - XFS_FSB_TO_B(mp, map[i].br_startoff)); - - /* Landed in the hole we wanted? */ - if (whence == SEEK_HOLE && - map[i].br_startblock == HOLESTARTBLOCK) - goto out; - - /* Landed in the data extent we wanted? */ - if (whence == SEEK_DATA && - (map[i].br_startblock == DELAYSTARTBLOCK || - (map[i].br_state == XFS_EXT_NORM && - !isnullstartblock(map[i].br_startblock)))) - goto out; - - /* - * Landed in an unwritten extent, try to search - * for hole or data from page cache. - */ - if (map[i].br_state == XFS_EXT_UNWRITTEN) { - if (xfs_find_get_desired_pgoff(inode, &map[i], - whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF, - &offset)) - goto out; - } - } - - /* - * We only received one extent out of the two requested. This - * means we've hit EOF and didn't find what we are looking for. - */ - if (nmap == 1) { - /* - * If we were looking for a hole, set offset to - * the end of the file (i.e., there is an implicit - * hole at the end of any file). - */ - if (whence == SEEK_HOLE) { - offset = end; - break; - } - /* - * If we were looking for data, it's nowhere to be found - */ - ASSERT(whence == SEEK_DATA); - error = -ENXIO; - goto out_error; - } - - ASSERT(i > 1); - - /* - * Nothing was found, proceed to the next round of search - * if the next reading offset is not at or beyond EOF. - */ - fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount; - start = XFS_FSB_TO_B(mp, fsbno); - if (start >= end) { - if (whence == SEEK_HOLE) { - offset = end; - break; - } - ASSERT(whence == SEEK_DATA); - error = -ENXIO; - goto out_error; - } - } - -out: - /* - * If at this point we have found the hole we wanted, the returned - * offset may be bigger than the file size as it may be aligned to - * page boundary for unwritten extents. We need to deal with this - * situation in particular. - */ - if (whence == SEEK_HOLE) - offset = min_t(loff_t, offset, end); - - return offset; - -out_error: - return error; -} - -STATIC loff_t -xfs_seek_hole_data( - struct file *file, - loff_t start, - int whence) -{ - struct inode *inode = file->f_mapping->host; - struct xfs_inode *ip = XFS_I(inode); - struct xfs_mount *mp = ip->i_mount; - uint lock; - loff_t offset, end; - int error = 0; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - lock = xfs_ilock_data_map_shared(ip); - - end = i_size_read(inode); - offset = __xfs_seek_hole_data(inode, start, end, whence); - if (offset < 0) { - error = offset; - goto out_unlock; - } - - offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes); - -out_unlock: - xfs_iunlock(ip, lock); - - if (error) - return error; - return offset; + return xfs_readdir(NULL, ip, ctx, bufsize); } STATIC loff_t @@ -1314,17 +990,25 @@ xfs_file_llseek( loff_t offset, int whence) { + struct inode *inode = file->f_mapping->host; + + if (XFS_FORCED_SHUTDOWN(XFS_I(inode)->i_mount)) + return -EIO; + switch (whence) { - case SEEK_END: - case SEEK_CUR: - case SEEK_SET: + default: return generic_file_llseek(file, offset, whence); case SEEK_HOLE: + offset = iomap_seek_hole(inode, offset, &xfs_iomap_ops); + break; case SEEK_DATA: - return xfs_seek_hole_data(file, offset, whence); - default: - return -EINVAL; + offset = iomap_seek_data(inode, offset, &xfs_iomap_ops); + break; } + + if (offset < 0) + return offset; + return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); } /* @@ -1337,96 +1021,67 @@ xfs_file_llseek( * page_lock (MM) * i_lock (XFS - extent map serialisation) */ - -/* - * mmap()d file has taken write protection fault and is being made writable. We - * can set the page state up correctly for a writable page, which means we can - * do correct delalloc accounting (ENOSPC checking!) and unwritten extent - * mapping. - */ -STATIC int -xfs_filemap_page_mkwrite( - struct vm_fault *vmf) +static int +__xfs_filemap_fault( + struct vm_fault *vmf, + enum page_entry_size pe_size, + bool write_fault) { struct inode *inode = file_inode(vmf->vma->vm_file); + struct xfs_inode *ip = XFS_I(inode); int ret; - trace_xfs_filemap_page_mkwrite(XFS_I(inode)); + trace_xfs_filemap_fault(ip, pe_size, write_fault); - sb_start_pagefault(inode->i_sb); - file_update_time(vmf->vma->vm_file); - xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + if (write_fault) { + sb_start_pagefault(inode->i_sb); + file_update_time(vmf->vma->vm_file); + } + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); if (IS_DAX(inode)) { - ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops); + ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops); } else { - ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops); - ret = block_page_mkwrite_return(ret); + if (write_fault) + ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops); + else + ret = filemap_fault(vmf); } - xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - sb_end_pagefault(inode->i_sb); + if (write_fault) + sb_end_pagefault(inode->i_sb); return ret; } -STATIC int +static int xfs_filemap_fault( struct vm_fault *vmf) { - struct inode *inode = file_inode(vmf->vma->vm_file); - int ret; - - trace_xfs_filemap_fault(XFS_I(inode)); - /* DAX can shortcut the normal fault path on write faults! */ - if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode)) - return xfs_filemap_page_mkwrite(vmf); - - xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - if (IS_DAX(inode)) - ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops); - else - ret = filemap_fault(vmf); - xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - - return ret; + return __xfs_filemap_fault(vmf, PE_SIZE_PTE, + IS_DAX(file_inode(vmf->vma->vm_file)) && + (vmf->flags & FAULT_FLAG_WRITE)); } -/* - * Similar to xfs_filemap_fault(), the DAX fault path can call into here on - * both read and write faults. Hence we need to handle both cases. There is no - * ->huge_mkwrite callout for huge pages, so we have a single function here to - * handle both cases here. @flags carries the information on the type of fault - * occuring. - */ -STATIC int +static int xfs_filemap_huge_fault( struct vm_fault *vmf, enum page_entry_size pe_size) { - struct inode *inode = file_inode(vmf->vma->vm_file); - struct xfs_inode *ip = XFS_I(inode); - int ret; - - if (!IS_DAX(inode)) + if (!IS_DAX(file_inode(vmf->vma->vm_file))) return VM_FAULT_FALLBACK; - trace_xfs_filemap_huge_fault(ip); - - if (vmf->flags & FAULT_FLAG_WRITE) { - sb_start_pagefault(inode->i_sb); - file_update_time(vmf->vma->vm_file); - } - - xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops); - xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); - - if (vmf->flags & FAULT_FLAG_WRITE) - sb_end_pagefault(inode->i_sb); + /* DAX can shortcut the normal fault path on write faults! */ + return __xfs_filemap_fault(vmf, pe_size, + (vmf->flags & FAULT_FLAG_WRITE)); +} - return ret; +static int +xfs_filemap_page_mkwrite( + struct vm_fault *vmf) +{ + return __xfs_filemap_fault(vmf, PE_SIZE_PTE, true); } /* @@ -1456,7 +1111,7 @@ xfs_filemap_pfn_mkwrite( if (vmf->pgoff >= size) ret = VM_FAULT_SIGBUS; else if (IS_DAX(inode)) - ret = dax_pfn_mkwrite(vmf); + ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops); xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); sb_end_pagefault(inode->i_sb); return ret; diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 814ed729881d..43cfc07996a4 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -367,29 +367,6 @@ xfs_getfsmap_datadev_helper( return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr); } -/* Transform a rtbitmap "record" into a fsmap */ -STATIC int -xfs_getfsmap_rtdev_rtbitmap_helper( - struct xfs_trans *tp, - struct xfs_rtalloc_rec *rec, - void *priv) -{ - struct xfs_mount *mp = tp->t_mountp; - struct xfs_getfsmap_info *info = priv; - struct xfs_rmap_irec irec; - xfs_daddr_t rec_daddr; - - rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock); - - irec.rm_startblock = rec->ar_startblock; - irec.rm_blockcount = rec->ar_blockcount; - irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */ - irec.rm_offset = 0; - irec.rm_flags = 0; - - return xfs_getfsmap_helper(tp, info, &irec, rec_daddr); -} - /* Transform a bnobt irec into a fsmap */ STATIC int xfs_getfsmap_datadev_bnobt_helper( @@ -475,6 +452,30 @@ xfs_getfsmap_logdev( return xfs_getfsmap_helper(tp, info, &rmap, 0); } +#ifdef CONFIG_XFS_RT +/* Transform a rtbitmap "record" into a fsmap */ +STATIC int +xfs_getfsmap_rtdev_rtbitmap_helper( + struct xfs_trans *tp, + struct xfs_rtalloc_rec *rec, + void *priv) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_getfsmap_info *info = priv; + struct xfs_rmap_irec irec; + xfs_daddr_t rec_daddr; + + rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock); + + irec.rm_startblock = rec->ar_startblock; + irec.rm_blockcount = rec->ar_blockcount; + irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */ + irec.rm_offset = 0; + irec.rm_flags = 0; + + return xfs_getfsmap_helper(tp, info, &irec, rec_daddr); +} + /* Execute a getfsmap query against the realtime device. */ STATIC int __xfs_getfsmap_rtdev( @@ -561,6 +562,7 @@ xfs_getfsmap_rtdev_rtbitmap( return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query, info); } +#endif /* CONFIG_XFS_RT */ /* Execute a getfsmap query against the regular data device. */ STATIC int @@ -795,7 +797,15 @@ xfs_getfsmap_check_keys( return false; } +/* + * There are only two devices if we didn't configure RT devices at build time. + */ +#ifdef CONFIG_XFS_RT #define XFS_GETFSMAP_DEVS 3 +#else +#define XFS_GETFSMAP_DEVS 2 +#endif /* CONFIG_XFS_RT */ + /* * Get filesystem's extents as described in head, and format for * output. Calls formatter to fill the user's buffer until all @@ -853,10 +863,12 @@ xfs_getfsmap( handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev); handlers[1].fn = xfs_getfsmap_logdev; } +#ifdef CONFIG_XFS_RT if (mp->m_rtdev_targp) { handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev); handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap; } +#endif /* CONFIG_XFS_RT */ xfs_sort(handlers, XFS_GETFSMAP_DEVS, sizeof(struct xfs_getfsmap_dev), xfs_getfsmap_dev_compare); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 6ccaae9eb0ee..8f22fc579dbb 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -602,7 +602,7 @@ xfs_growfs_data_private( if (nagimax) mp->m_maxagi = nagimax; if (mp->m_sb.sb_imax_pct) { - __uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct; + uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct; do_div(icount, 100); mp->m_maxicount = icount << mp->m_sb.sb_inopblog; } else @@ -793,17 +793,17 @@ xfs_fs_counts( int xfs_reserve_blocks( xfs_mount_t *mp, - __uint64_t *inval, + uint64_t *inval, xfs_fsop_resblks_t *outval) { - __int64_t lcounter, delta; - __int64_t fdblks_delta = 0; - __uint64_t request; - __int64_t free; + int64_t lcounter, delta; + int64_t fdblks_delta = 0; + uint64_t request; + int64_t free; int error = 0; /* If inval is null, report current values and return */ - if (inval == (__uint64_t *)NULL) { + if (inval == (uint64_t *)NULL) { if (!outval) return -EINVAL; outval->resblks = mp->m_resblks; @@ -904,7 +904,7 @@ out: int xfs_fs_goingdown( xfs_mount_t *mp, - __uint32_t inflags) + uint32_t inflags) { switch (inflags) { case XFS_FSOP_GOING_FLAGS_DEFAULT: { diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h index f34915898fea..2954c13a3acd 100644 --- a/fs/xfs/xfs_fsops.h +++ b/fs/xfs/xfs_fsops.h @@ -22,9 +22,9 @@ extern int xfs_fs_geometry(xfs_mount_t *mp, xfs_fsop_geom_t *geo, int nversion); extern int xfs_growfs_data(xfs_mount_t *mp, xfs_growfs_data_t *in); extern int xfs_growfs_log(xfs_mount_t *mp, xfs_growfs_log_t *in); extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt); -extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval, +extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval, xfs_fsop_resblks_t *outval); -extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags); +extern int xfs_fs_goingdown(xfs_mount_t *mp, uint32_t inflags); extern int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp); extern int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c index 687a4b01fc53..3e1cc3001bcb 100644 --- a/fs/xfs/xfs_globals.c +++ b/fs/xfs/xfs_globals.c @@ -47,4 +47,9 @@ xfs_param_t xfs_params = { struct xfs_globals xfs_globals = { .log_recovery_delay = 0, /* no delay by default */ +#ifdef XFS_ASSERT_FATAL + .bug_on_assert = true, /* assert failures BUG() */ +#else + .bug_on_assert = false, /* assert failures WARN() */ +#endif }; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 990210fcb9c3..34227115a5d6 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -269,12 +269,12 @@ xfs_inew_wait( DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT); do { - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (!xfs_iflags_test(ip, XFS_INEW)) break; schedule(); } while (true); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); } /* @@ -368,6 +368,11 @@ xfs_iget_cache_hit( if (ip->i_flags & XFS_IRECLAIMABLE) { trace_xfs_iget_reclaim(ip); + if (flags & XFS_IGET_INCORE) { + error = -EAGAIN; + goto out_error; + } + /* * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode * from stomping over us while we recycle the inode. We can't @@ -432,7 +437,8 @@ xfs_iget_cache_hit( if (lock_flags != 0) xfs_ilock(ip, lock_flags); - xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE); + if (!(flags & XFS_IGET_INCORE)) + xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE); XFS_STATS_INC(mp, xs_ig_found); return 0; @@ -603,6 +609,10 @@ again: goto out_error_or_again; } else { rcu_read_unlock(); + if (flags & XFS_IGET_INCORE) { + error = -ENOENT; + goto out_error_or_again; + } XFS_STATS_INC(mp, xs_ig_missed); error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, @@ -623,7 +633,7 @@ again: return 0; out_error_or_again: - if (error == -EAGAIN) { + if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) { delay(1); goto again; } @@ -632,6 +642,44 @@ out_error_or_again: } /* + * "Is this a cached inode that's also allocated?" + * + * Look up an inode by number in the given file system. If the inode is + * in cache and isn't in purgatory, return 1 if the inode is allocated + * and 0 if it is not. For all other cases (not in cache, being torn + * down, etc.), return a negative error code. + * + * The caller has to prevent inode allocation and freeing activity, + * presumably by locking the AGI buffer. This is to ensure that an + * inode cannot transition from allocated to freed until the caller is + * ready to allow that. If the inode is in an intermediate state (new, + * reclaimable, or being reclaimed), -EAGAIN will be returned; if the + * inode is not in the cache, -ENOENT will be returned. The caller must + * deal with these scenarios appropriately. + * + * This is a specialized use case for the online scrubber; if you're + * reading this, you probably want xfs_iget. + */ +int +xfs_icache_inode_is_allocated( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_ino_t ino, + bool *inuse) +{ + struct xfs_inode *ip; + int error; + + error = xfs_iget(mp, tp, ino, XFS_IGET_INCORE, 0, &ip); + if (error) + return error; + + *inuse = !!(VFS_I(ip)->i_mode); + IRELE(ip); + return 0; +} + +/* * The inode lookup is done in batches to keep the amount of lock traffic and * radix tree lookups to a minimum. The batch size is a trade off between * lookup reduction and stack usage. This is in the reclaim path, so we can't @@ -1076,11 +1124,11 @@ reclaim: * Because we use RCU freeing we need to ensure the inode always appears * to be reclaimed with an invalid inode number when in the free state. * We do this as early as possible under the ILOCK so that - * xfs_iflush_cluster() can be guaranteed to detect races with us here. - * By doing this, we guarantee that once xfs_iflush_cluster has locked - * XFS_ILOCK that it will see either a valid, flushable inode that will - * serialise correctly, or it will see a clean (and invalid) inode that - * it can skip. + * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to + * detect races with us here. By doing this, we guarantee that once + * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that + * it will see either a valid inode that will serialise correctly, or it + * will see an invalid inode that it can skip. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index 9183f77958ef..bff4d85e5498 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -47,6 +47,7 @@ struct xfs_eofblocks { #define XFS_IGET_CREATE 0x1 #define XFS_IGET_UNTRUSTED 0x2 #define XFS_IGET_DONTCACHE 0x4 +#define XFS_IGET_INCORE 0x8 /* don't read from disk or reinit */ /* * flags for AG inode iterator @@ -126,4 +127,7 @@ xfs_fs_eofblocks_from_user( return 0; } +int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_ino_t ino, bool *inuse); + #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index ec9826c56500..4ec5b7f45401 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -622,17 +622,17 @@ __xfs_iflock( DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT); do { - prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (xfs_isiflocked(ip)) io_schedule(); } while (!xfs_iflock_nowait(ip)); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); } STATIC uint _xfs_dic2xflags( - __uint16_t di_flags, + uint16_t di_flags, uint64_t di_flags2, bool has_attr) { @@ -855,8 +855,8 @@ xfs_ialloc( inode->i_version = 1; ip->i_d.di_flags2 = 0; ip->i_d.di_cowextsize = 0; - ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec; - ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec; + ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec; + ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec; } @@ -874,7 +874,6 @@ xfs_ialloc( case S_IFREG: case S_IFDIR: if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) { - uint64_t di_flags2 = 0; uint di_flags = 0; if (S_ISDIR(mode)) { @@ -911,20 +910,23 @@ xfs_ialloc( di_flags |= XFS_DIFLAG_NODEFRAG; if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; - if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; ip->i_d.di_flags |= di_flags; - ip->i_d.di_flags2 |= di_flags2; } if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) && pip->i_d.di_version == 3 && ip->i_d.di_version == 3) { + uint64_t di_flags2 = 0; + if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) { - ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_d.di_cowextsize = pip->i_d.di_cowextsize; } + if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + + ip->i_d.di_flags2 |= di_flags2; } /* FALLTHROUGH */ case S_IFLNK: @@ -1053,7 +1055,7 @@ xfs_dir_ialloc( tp->t_flags &= ~(XFS_TRANS_DQ_DIRTY); } - code = xfs_trans_roll(&tp, NULL); + code = xfs_trans_roll(&tp); if (committed != NULL) *committed = 1; @@ -1283,7 +1285,7 @@ xfs_create( */ xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp); - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -1511,7 +1513,7 @@ xfs_link( if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) xfs_trans_set_sync(tp); - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) { xfs_defer_cancel(&dfops); goto error_return; @@ -1605,11 +1607,12 @@ xfs_itruncate_extents( * Duplicate the transaction that has the permanent * reservation and commit the old transaction. */ - error = xfs_defer_finish(&tp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; - error = xfs_trans_roll(&tp, ip); + error = xfs_trans_roll_inode(&tp, ip); if (error) goto out; } @@ -1621,10 +1624,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } @@ -1853,7 +1858,7 @@ xfs_inactive_ifree( * Just ignore errors at this point. There is nothing we can do except * to try to keep going. Make sure it's not a silent error. */ - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) { xfs_notice(mp, "%s: xfs_defer_finish returned error %d", __func__, error); @@ -2357,11 +2362,24 @@ retry: * already marked stale. If we can't lock it, back off * and retry. */ - if (ip != free_ip && - !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { - rcu_read_unlock(); - delay(1); - goto retry; + if (ip != free_ip) { + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { + rcu_read_unlock(); + delay(1); + goto retry; + } + + /* + * Check the inode number again in case we're + * racing with freeing in xfs_reclaim_inode(). + * See the comments in that function for more + * information as to why the initial check is + * not sufficient. + */ + if (ip->i_ino != inum + i) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); + continue; + } } rcu_read_unlock(); @@ -2486,11 +2504,11 @@ __xfs_iunpin_wait( xfs_iunpin(ip); do { - prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); if (xfs_ipincount(ip)) io_schedule(); } while (xfs_ipincount(ip)); - finish_wait(wq, &wait.wait); + finish_wait(wq, &wait.wq_entry); } void @@ -2635,7 +2653,7 @@ xfs_remove( if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) xfs_trans_set_sync(tp); - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -2721,7 +2739,7 @@ xfs_finish_rename( if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) xfs_trans_set_sync(tp); - error = xfs_defer_finish(&tp, dfops, NULL); + error = xfs_defer_finish(&tp, dfops); if (error) { xfs_defer_cancel(dfops); xfs_trans_cancel(tp); @@ -3489,7 +3507,7 @@ xfs_iflush_int( dip = xfs_buf_offset(bp, ip->i_imap.im_boffset); if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC), - mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) { + mp, XFS_ERRTAG_IFLUSH_1)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad inode %Lu magic number 0x%x, ptr 0x%p", __func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip); @@ -3499,7 +3517,7 @@ xfs_iflush_int( if (XFS_TEST_ERROR( (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) && (ip->i_d.di_format != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_IFLUSH_3, XFS_RANDOM_IFLUSH_3)) { + mp, XFS_ERRTAG_IFLUSH_3)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad regular inode %Lu, ptr 0x%p", __func__, ip->i_ino, ip); @@ -3510,7 +3528,7 @@ xfs_iflush_int( (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) && (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) && (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL), - mp, XFS_ERRTAG_IFLUSH_4, XFS_RANDOM_IFLUSH_4)) { + mp, XFS_ERRTAG_IFLUSH_4)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: Bad directory inode %Lu, ptr 0x%p", __func__, ip->i_ino, ip); @@ -3518,8 +3536,7 @@ xfs_iflush_int( } } if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents > - ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5, - XFS_RANDOM_IFLUSH_5)) { + ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: detected corrupt incore inode %Lu, " "total extents = %d, nblocks = %Ld, ptr 0x%p", @@ -3529,7 +3546,7 @@ xfs_iflush_int( goto corrupt_out; } if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize, - mp, XFS_ERRTAG_IFLUSH_6, XFS_RANDOM_IFLUSH_6)) { + mp, XFS_ERRTAG_IFLUSH_6)) { xfs_alert_tag(mp, XFS_PTAG_IFLUSH, "%s: bad inode %Lu, forkoff 0x%x, ptr 0x%p", __func__, ip->i_ino, ip->i_d.di_forkoff, ip); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 10e89fcb49d7..0ee453de239a 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -192,8 +192,8 @@ static inline void xfs_set_projid(struct xfs_inode *ip, prid_t projid) { - ip->i_d.di_projid_hi = (__uint16_t) (projid >> 16); - ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff); + ip->i_d.di_projid_hi = (uint16_t) (projid >> 16); + ip->i_d.di_projid_lo = (uint16_t) (projid & 0xffff); } static inline prid_t @@ -445,9 +445,6 @@ int xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset, xfs_fsize_t isize, bool *did_zeroing); int xfs_zero_range(struct xfs_inode *ip, xfs_off_t pos, xfs_off_t count, bool *did_zero); -loff_t __xfs_seek_hole_data(struct inode *inode, loff_t start, - loff_t eof, int whence); - /* from xfs_iops.c */ extern void xfs_setup_inode(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 08cb7d1a4a3a..9bbc2d7cc8cb 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -27,6 +27,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans_priv.h" +#include "xfs_buf_item.h" #include "xfs_log.h" @@ -363,6 +364,9 @@ xfs_inode_to_log_dinode( to->di_dmstate = from->di_dmstate; to->di_flags = from->di_flags; + /* log a dummy value to ensure log structure is fully initialised */ + to->di_next_unlinked = NULLAGINO; + if (from->di_version == 3) { to->di_changecount = inode->i_version; to->di_crtime.t_sec = from->di_crtime.t_sec; @@ -403,6 +407,11 @@ xfs_inode_item_format_core( * the second with the on-disk inode structure, and a possible third and/or * fourth with the inode data/extents/b-tree root and inode attributes * data/extents/b-tree root. + * + * Note: Always use the 64 bit inode log format structure so we don't + * leave an uninitialised hole in the format item on 64 bit systems. Log + * recovery on 32 bit systems handles this just fine, so there's no reason + * for not using an initialising the properly padded structure all the time. */ STATIC void xfs_inode_item_format( @@ -411,8 +420,8 @@ xfs_inode_item_format( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_inode_log_format *ilf; struct xfs_log_iovec *vecp = NULL; + struct xfs_inode_log_format *ilf; ASSERT(ip->i_d.di_version > 1); @@ -424,7 +433,17 @@ xfs_inode_item_format( ilf->ilf_boffset = ip->i_imap.im_boffset; ilf->ilf_fields = XFS_ILOG_CORE; ilf->ilf_size = 2; /* format + core */ - xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); + + /* + * make sure we don't leak uninitialised data into the log in the case + * when we don't log every field in the inode. + */ + ilf->ilf_dsize = 0; + ilf->ilf_asize = 0; + ilf->ilf_pad = 0; + uuid_copy(&ilf->ilf_u.ilfu_uuid, &uuid_null); + + xlog_finish_iovec(lv, vecp, sizeof(*ilf)); xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); @@ -475,6 +494,23 @@ xfs_inode_item_unpin( wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } +/* + * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer + * have been failed during writeback + * + * This informs the AIL that the inode is already flush locked on the next push, + * and acquires a hold on the buffer to ensure that it isn't reclaimed before + * dirty data makes it to disk. + */ +STATIC void +xfs_inode_item_error( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode)); + xfs_set_li_failed(lip, bp); +} + STATIC uint xfs_inode_item_push( struct xfs_log_item *lip, @@ -484,13 +520,28 @@ xfs_inode_item_push( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_buf *bp = NULL; + struct xfs_buf *bp = lip->li_buf; uint rval = XFS_ITEM_SUCCESS; int error; if (xfs_ipincount(ip) > 0) return XFS_ITEM_PINNED; + /* + * The buffer containing this item failed to be written back + * previously. Resubmit the buffer for IO. + */ + if (lip->li_flags & XFS_LI_FAILED) { + if (!xfs_buf_trylock(bp)) + return XFS_ITEM_LOCKED; + + if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list)) + rval = XFS_ITEM_FLUSHING; + + xfs_buf_unlock(bp); + return rval; + } + if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) return XFS_ITEM_LOCKED; @@ -622,7 +673,8 @@ static const struct xfs_item_ops xfs_inode_item_ops = { .iop_unlock = xfs_inode_item_unlock, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_committing = xfs_inode_item_committing + .iop_committing = xfs_inode_item_committing, + .iop_error = xfs_inode_item_error }; @@ -710,7 +762,8 @@ xfs_iflush_done( * the AIL lock. */ iip = INODE_ITEM(blip); - if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) + if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; @@ -718,7 +771,8 @@ xfs_iflush_done( /* make sure we capture the state of the initial inode. */ iip = INODE_ITEM(lip); - if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) + if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) || + lip->li_flags & XFS_LI_FAILED) need_ail++; /* @@ -739,6 +793,9 @@ xfs_iflush_done( if (INODE_ITEM(blip)->ili_logged && blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) mlip_changed |= xfs_ail_delete_one(ailp, blip); + else { + xfs_clear_li_failed(blip); + } } if (mlip_changed) { @@ -816,48 +873,29 @@ xfs_istale_done( } /* - * convert an xfs_inode_log_format struct from either 32 or 64 bit versions - * (which can have different field alignments) to the native version + * convert an xfs_inode_log_format struct from the old 32 bit version + * (which can have different field alignments) to the native 64 bit version */ int xfs_inode_item_format_convert( - xfs_log_iovec_t *buf, - xfs_inode_log_format_t *in_f) + struct xfs_log_iovec *buf, + struct xfs_inode_log_format *in_f) { - if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) { - xfs_inode_log_format_32_t *in_f32 = buf->i_addr; - - in_f->ilf_type = in_f32->ilf_type; - in_f->ilf_size = in_f32->ilf_size; - in_f->ilf_fields = in_f32->ilf_fields; - in_f->ilf_asize = in_f32->ilf_asize; - in_f->ilf_dsize = in_f32->ilf_dsize; - in_f->ilf_ino = in_f32->ilf_ino; - /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f32->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); - in_f->ilf_blkno = in_f32->ilf_blkno; - in_f->ilf_len = in_f32->ilf_len; - in_f->ilf_boffset = in_f32->ilf_boffset; - return 0; - } else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){ - xfs_inode_log_format_64_t *in_f64 = buf->i_addr; - - in_f->ilf_type = in_f64->ilf_type; - in_f->ilf_size = in_f64->ilf_size; - in_f->ilf_fields = in_f64->ilf_fields; - in_f->ilf_asize = in_f64->ilf_asize; - in_f->ilf_dsize = in_f64->ilf_dsize; - in_f->ilf_ino = in_f64->ilf_ino; - /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f64->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); - in_f->ilf_blkno = in_f64->ilf_blkno; - in_f->ilf_len = in_f64->ilf_len; - in_f->ilf_boffset = in_f64->ilf_boffset; - return 0; - } - return -EFSCORRUPTED; + struct xfs_inode_log_format_32 *in_f32 = buf->i_addr; + + if (buf->i_len != sizeof(*in_f32)) + return -EFSCORRUPTED; + + in_f->ilf_type = in_f32->ilf_type; + in_f->ilf_size = in_f32->ilf_size; + in_f->ilf_fields = in_f32->ilf_fields; + in_f->ilf_asize = in_f32->ilf_asize; + in_f->ilf_dsize = in_f32->ilf_dsize; + in_f->ilf_ino = in_f32->ilf_ino; + /* copy biggest field of ilf_u */ + uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid); + in_f->ilf_blkno = in_f32->ilf_blkno; + in_f->ilf_len = in_f32->ilf_len; + in_f->ilf_boffset = in_f32->ilf_boffset; + return 0; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6190697603c9..aa75389be8cf 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -120,8 +120,7 @@ xfs_find_handle( handle.ha_fid.fid_pad = 0; handle.ha_fid.fid_gen = inode->i_generation; handle.ha_fid.fid_ino = ip->i_ino; - - hsize = XFS_HSIZE(handle); + hsize = sizeof(xfs_handle_t); } error = -EFAULT; @@ -444,8 +443,8 @@ xfs_attrmulti_attr_get( struct inode *inode, unsigned char *name, unsigned char __user *ubuf, - __uint32_t *len, - __uint32_t flags) + uint32_t *len, + uint32_t flags) { unsigned char *kbuf; int error = -EFAULT; @@ -473,8 +472,8 @@ xfs_attrmulti_attr_set( struct inode *inode, unsigned char *name, const unsigned char __user *ubuf, - __uint32_t len, - __uint32_t flags) + uint32_t len, + uint32_t flags) { unsigned char *kbuf; int error; @@ -499,7 +498,7 @@ int xfs_attrmulti_attr_remove( struct inode *inode, unsigned char *name, - __uint32_t flags) + uint32_t flags) { int error; @@ -877,7 +876,7 @@ xfs_merge_ioc_xflags( STATIC unsigned int xfs_di2lxflags( - __uint16_t di_flags) + uint16_t di_flags) { unsigned int flags = 0; @@ -932,16 +931,15 @@ xfs_ioc_fsgetxattr( return 0; } -STATIC void -xfs_set_diflags( +STATIC uint16_t +xfs_flags2diflags( struct xfs_inode *ip, unsigned int xflags) { - unsigned int di_flags; - uint64_t di_flags2; - /* can't set PREALLOC this way, just preserve it */ - di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); + uint16_t di_flags = + (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); + if (xflags & FS_XFLAG_IMMUTABLE) di_flags |= XFS_DIFLAG_IMMUTABLE; if (xflags & FS_XFLAG_APPEND) @@ -971,19 +969,24 @@ xfs_set_diflags( if (xflags & FS_XFLAG_EXTSIZE) di_flags |= XFS_DIFLAG_EXTSIZE; } - ip->i_d.di_flags = di_flags; - /* diflags2 only valid for v3 inodes. */ - if (ip->i_d.di_version < 3) - return; + return di_flags; +} + +STATIC uint64_t +xfs_flags2diflags2( + struct xfs_inode *ip, + unsigned int xflags) +{ + uint64_t di_flags2 = + (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK); - di_flags2 = (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK); if (xflags & FS_XFLAG_DAX) di_flags2 |= XFS_DIFLAG2_DAX; if (xflags & FS_XFLAG_COWEXTSIZE) di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; - ip->i_d.di_flags2 = di_flags2; + return di_flags2; } STATIC void @@ -1009,11 +1012,12 @@ xfs_diflags_to_linux( inode->i_flags |= S_NOATIME; else inode->i_flags &= ~S_NOATIME; +#if 0 /* disabled until the flag switching races are sorted out */ if (xflags & FS_XFLAG_DAX) inode->i_flags |= S_DAX; else inode->i_flags &= ~S_DAX; - +#endif } static int @@ -1023,6 +1027,7 @@ xfs_ioctl_setattr_xflags( struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; + uint64_t di_flags2; /* Can't change realtime flag if any extents are allocated. */ if ((ip->i_d.di_nextents || ip->i_delayed_blks) && @@ -1053,7 +1058,14 @@ xfs_ioctl_setattr_xflags( !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; - xfs_set_diflags(ip, fa->fsx_xflags); + /* diflags2 only valid for v3 inodes. */ + di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); + if (di_flags2 && ip->i_d.di_version < 3) + return -EINVAL; + + ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags); + ip->i_d.di_flags2 = di_flags2; + xfs_diflags_to_linux(ip); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); @@ -1076,6 +1088,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1088,7 +1101,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } @@ -1288,7 +1301,7 @@ xfs_ioctl_setattr_check_projid( struct fsxattr *fa) { /* Disallow 32bit project ids if projid32bit feature is not enabled. */ - if (fa->fsx_projid > (__uint16_t)-1 && + if (fa->fsx_projid > (uint16_t)-1 && !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) return -EINVAL; @@ -1932,7 +1945,7 @@ xfs_file_ioctl( case XFS_IOC_SET_RESBLKS: { xfs_fsop_resblks_t inout; - __uint64_t in; + uint64_t in; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2018,12 +2031,12 @@ xfs_file_ioctl( } case XFS_IOC_GOINGDOWN: { - __uint32_t in; + uint32_t in; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (get_user(in, (__uint32_t __user *)arg)) + if (get_user(in, (uint32_t __user *)arg)) return -EFAULT; return xfs_fs_goingdown(mp, in); @@ -2038,14 +2051,14 @@ xfs_file_ioctl( if (copy_from_user(&in, arg, sizeof(in))) return -EFAULT; - return xfs_errortag_add(in.errtag, mp); + return xfs_errortag_add(mp, in.errtag); } case XFS_IOC_ERROR_CLEARALL: if (!capable(CAP_SYS_ADMIN)) return -EPERM; - return xfs_errortag_clearall(mp, 1); + return xfs_errortag_clearall(mp); case XFS_IOC_FREE_EOFBLOCKS: { struct xfs_fs_eofblocks eofb; diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h index 8b52881bfd90..e86c3ea137d2 100644 --- a/fs/xfs/xfs_ioctl.h +++ b/fs/xfs/xfs_ioctl.h @@ -48,22 +48,22 @@ xfs_attrmulti_attr_get( struct inode *inode, unsigned char *name, unsigned char __user *ubuf, - __uint32_t *len, - __uint32_t flags); + uint32_t *len, + uint32_t flags); extern int xfs_attrmulti_attr_set( struct inode *inode, unsigned char *name, const unsigned char __user *ubuf, - __uint32_t len, - __uint32_t flags); + uint32_t len, + uint32_t flags); extern int xfs_attrmulti_attr_remove( struct inode *inode, unsigned char *name, - __uint32_t flags); + uint32_t flags); extern struct dentry * xfs_handle_to_dentry( diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h index b1bb45444df8..5492bcf6f442 100644 --- a/fs/xfs/xfs_ioctl32.h +++ b/fs/xfs/xfs_ioctl32.h @@ -112,9 +112,9 @@ typedef struct compat_xfs_fsop_handlereq { /* The bstat field in the swapext struct needs translation */ typedef struct compat_xfs_swapext { - __int64_t sx_version; /* version */ - __int64_t sx_fdtarget; /* fd of target file */ - __int64_t sx_fdtmp; /* fd of tmp file */ + int64_t sx_version; /* version */ + int64_t sx_fdtarget; /* fd of target file */ + int64_t sx_fdtmp; /* fd of tmp file */ xfs_off_t sx_offset; /* offset into file */ xfs_off_t sx_length; /* leng from offset */ char sx_pad[16]; /* pad space, unused */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 94e5bdf7304c..f179bdf1644d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -69,6 +69,7 @@ xfs_bmbt_to_iomap( iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff); iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount); iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip)); + iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip)); } xfs_extlen_t @@ -274,7 +275,7 @@ xfs_iomap_write_direct( /* * Complete the transaction */ - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -520,7 +521,6 @@ xfs_file_iomap_begin_delay( struct inode *inode, loff_t offset, loff_t count, - unsigned flags, struct iomap *iomap) { struct xfs_inode *ip = XFS_I(inode); @@ -543,7 +543,7 @@ xfs_file_iomap_begin_delay( if (unlikely(XFS_TEST_ERROR( (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS && XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE), - mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) { + mp, XFS_ERRTAG_BMAPIFORMAT))) { XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto out_unlock; @@ -784,7 +784,7 @@ xfs_iomap_write_allocate( if (error) goto trans_cancel; - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto trans_cancel; @@ -829,7 +829,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -840,6 +841,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -899,14 +901,15 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); } - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto error_on_bmapi_transaction; @@ -976,7 +979,6 @@ xfs_file_iomap_begin( int nimaps = 1, error = 0; bool shared = false, trimmed = false; unsigned lockmode; - struct block_device *bdev; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; @@ -984,8 +986,7 @@ xfs_file_iomap_begin( if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) && !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ - return xfs_file_iomap_begin_delay(inode, offset, length, flags, - iomap); + return xfs_file_iomap_begin_delay(inode, offset, length, iomap); } if (need_excl_ilock(ip, flags)) { @@ -995,6 +996,11 @@ xfs_file_iomap_begin( lockmode = xfs_ilock_data_map_shared(ip); } + if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) { + error = -EAGAIN; + goto out_unlock; + } + ASSERT(offset <= mp->m_super->s_maxbytes); if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes) length = mp->m_super->s_maxbytes - offset; @@ -1016,6 +1022,15 @@ xfs_file_iomap_begin( if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { if (flags & IOMAP_DIRECT) { + /* + * A reflinked inode will result in CoW alloc. + * FIXME: It could still overwrite on unshared extents + * and not need allocation. + */ + if (flags & IOMAP_NOWAIT) { + error = -EAGAIN; + goto out_unlock; + } /* may drop and re-acquire the ilock */ error = xfs_reflink_allocate_cow(ip, &imap, &shared, &lockmode); @@ -1033,6 +1048,14 @@ xfs_file_iomap_begin( if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) { /* + * If nowait is set bail since we are going to make + * allocations. + */ + if (flags & IOMAP_NOWAIT) { + error = -EAGAIN; + goto out_unlock; + } + /* * We cap the maximum length we map here to MAX_WRITEBACK_PAGES * pages to keep the chunks of work done where somewhat symmetric * with the work writeback does. This is a completely arbitrary @@ -1065,13 +1088,6 @@ xfs_file_iomap_begin( xfs_bmbt_to_iomap(ip, iomap, &imap); - /* optionally associate a dax device with the iomap bdev */ - bdev = iomap->bdev; - if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); - else - iomap->dax_dev = NULL; - if (shared) iomap->flags |= IOMAP_F_SHARED; return 0; @@ -1097,7 +1113,7 @@ xfs_file_iomap_end_delalloc( * Behave as if the write failed if drop writes is enabled. Set the NEW * flag to force delalloc cleanup. */ - if (xfs_mp_drop_writes(mp)) { + if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) { iomap->flags |= IOMAP_F_NEW; written = 0; } @@ -1149,7 +1165,6 @@ xfs_file_iomap_end( unsigned flags, struct iomap *iomap) { - fs_put_dax(iomap->dax_dev); if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC) return xfs_file_iomap_end_delalloc(XFS_I(inode), offset, length, written, iomap); diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 00db3ecea084..ee535065c5d0 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index ebfc13350f9a..17081c77ef86 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -190,12 +190,12 @@ xfs_generic_create( #ifdef CONFIG_XFS_POSIX_ACL if (default_acl) { - error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); if (error) goto out_cleanup_inode; } if (acl) { - error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); if (error) goto out_cleanup_inode; } @@ -460,7 +460,7 @@ xfs_vn_get_link( if (!dentry) return ERR_PTR(-ECHILD); - link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); + link = kmalloc(XFS_SYMLINK_MAXLEN+1, GFP_KERNEL); if (!link) goto out_err; @@ -817,7 +817,7 @@ xfs_vn_setattr_nonsize( * Caution: The caller of this function is responsible for calling * setattr_prepare() or otherwise verifying the change is fine. */ -int +STATIC int xfs_setattr_size( struct xfs_inode *ip, struct iattr *iattr) diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 26d67ce3c18d..c393a2f6d8c3 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -31,7 +31,7 @@ #include "xfs_trace.h" #include "xfs_icache.h" -STATIC int +int xfs_internal_inum( xfs_mount_t *mp, xfs_ino_t ino) diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h index 6ea8b3912fa4..17e86e0541af 100644 --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -96,4 +96,6 @@ xfs_inumbers( void __user *buffer, /* buffer with inode info */ inumbers_fmt_pf formatter); +int xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino); + #endif /* __XFS_ITABLE_H__ */ diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 044fb0e15390..dcd1292664b3 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -19,18 +19,11 @@ #define __XFS_LINUX__ #include <linux/types.h> +#include <linux/uuid.h> /* * Kernel specific type declarations for XFS */ -typedef signed char __int8_t; -typedef unsigned char __uint8_t; -typedef signed short int __int16_t; -typedef unsigned short int __uint16_t; -typedef signed int __int32_t; -typedef unsigned int __uint32_t; -typedef signed long long int __int64_t; -typedef unsigned long long int __uint64_t; typedef __s64 xfs_off_t; /* <file offset> type */ typedef unsigned long long xfs_ino_t; /* <inode> type */ @@ -42,7 +35,6 @@ typedef __u32 xfs_nlink_t; #include "kmem.h" #include "mrlock.h" -#include "uuid.h" #include <linux/semaphore.h> #include <linux/mm.h> @@ -151,7 +143,6 @@ typedef __u32 xfs_nlink_t; #define __return_address __builtin_return_address(0) #define XFS_PROJID_DEFAULT 0 -#define MAXPATHLEN 1024 #define MIN(a,b) (min(a,b)) #define MAX(a,b) (max(a,b)) @@ -186,22 +177,22 @@ extern struct xstats xfsstats; * are converting to the init_user_ns. The uid is later mapped to a particular * user namespace value when crossing the kernel/user boundary. */ -static inline __uint32_t xfs_kuid_to_uid(kuid_t uid) +static inline uint32_t xfs_kuid_to_uid(kuid_t uid) { return from_kuid(&init_user_ns, uid); } -static inline kuid_t xfs_uid_to_kuid(__uint32_t uid) +static inline kuid_t xfs_uid_to_kuid(uint32_t uid) { return make_kuid(&init_user_ns, uid); } -static inline __uint32_t xfs_kgid_to_gid(kgid_t gid) +static inline uint32_t xfs_kgid_to_gid(kgid_t gid) { return from_kgid(&init_user_ns, gid); } -static inline kgid_t xfs_gid_to_kgid(__uint32_t gid) +static inline kgid_t xfs_gid_to_kgid(uint32_t gid) { return make_kgid(&init_user_ns, gid); } @@ -231,14 +222,14 @@ static inline __u32 xfs_do_mod(void *a, __u32 b, int n) #define do_mod(a, b) xfs_do_mod(&(a), (b), sizeof(a)) -static inline __uint64_t roundup_64(__uint64_t x, __uint32_t y) +static inline uint64_t roundup_64(uint64_t x, uint32_t y) { x += y - 1; do_div(x, y); return x * y; } -static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y) +static inline uint64_t howmany_64(uint64_t x, uint32_t y) { x += y - 1; do_div(x, y); @@ -279,7 +270,14 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y) #endif /* DEBUG */ #ifdef CONFIG_XFS_RT -#define XFS_IS_REALTIME_INODE(ip) ((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) + +/* + * make sure we ignore the inode flag if the filesystem doesn't have a + * configured realtime device. + */ +#define XFS_IS_REALTIME_INODE(ip) \ + (((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) && \ + (ip)->i_mount->m_rtdev_targp) #else #define XFS_IS_REALTIME_INODE(ip) (0) #endif diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 3731f13f63e9..dc95a49d62e7 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -434,7 +434,7 @@ xfs_log_reserve( int unit_bytes, int cnt, struct xlog_ticket **ticp, - __uint8_t client, + uint8_t client, bool permanent) { struct xlog *log = mp->m_log; @@ -743,15 +743,45 @@ xfs_log_mount_finish( struct xfs_mount *mp) { int error = 0; + bool readonly = (mp->m_flags & XFS_MOUNT_RDONLY); if (mp->m_flags & XFS_MOUNT_NORECOVERY) { ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; + } else if (readonly) { + /* Allow unlinked processing to proceed */ + mp->m_flags &= ~XFS_MOUNT_RDONLY; } + /* + * During the second phase of log recovery, we need iget and + * iput to behave like they do for an active filesystem. + * xfs_fs_drop_inode needs to be able to prevent the deletion + * of inodes before we're done replaying log items on those + * inodes. Turn it off immediately after recovery finishes + * so that we don't leak the quota inodes if subsequent mount + * activities fail. + * + * We let all inodes involved in redo item processing end up on + * the LRU instead of being evicted immediately so that if we do + * something to an unlinked inode, the irele won't cause + * premature truncation and freeing of the inode, which results + * in log recovery failure. We have to evict the unreferenced + * lru inodes after clearing MS_ACTIVE because we don't + * otherwise clean up the lru if there's a subsequent failure in + * xfs_mountfs, which leads to us leaking the inodes if nothing + * else (e.g. quotacheck) references the inodes before the + * mount failure occurs. + */ + mp->m_super->s_flags |= MS_ACTIVE; error = xlog_recover_finish(mp->m_log); if (!error) xfs_log_work_queue(mp); + mp->m_super->s_flags &= ~MS_ACTIVE; + evict_inodes(mp->m_super); + + if (readonly) + mp->m_flags |= XFS_MOUNT_RDONLY; return error; } @@ -801,11 +831,14 @@ xfs_log_unmount_write(xfs_mount_t *mp) int error; /* - * Don't write out unmount record on read-only mounts. + * Don't write out unmount record on norecovery mounts or ro devices. * Or, if we are doing a forced umount (typically because of IO errors). */ - if (mp->m_flags & XFS_MOUNT_RDONLY) + if (mp->m_flags & XFS_MOUNT_NORECOVERY || + xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) { + ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; + } error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL); ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log))); @@ -825,9 +858,9 @@ xfs_log_unmount_write(xfs_mount_t *mp) if (!error) { /* the data section must be 32 bit size aligned */ struct { - __uint16_t magic; - __uint16_t pad1; - __uint32_t pad2; /* may as well make it 64 bits */ + uint16_t magic; + uint16_t pad1; + uint32_t pad2; /* may as well make it 64 bits */ } magic = { .magic = XLOG_UNMOUNT_TYPE, }; @@ -1189,8 +1222,7 @@ xlog_iodone(xfs_buf_t *bp) * IOABORT state. The IOABORT state is only set in DEBUG mode to inject * CRC errors into log recovery. */ - if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR, - XFS_RANDOM_IODONE_IOERR) || + if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR) || iclog->ic_state & XLOG_STATE_IOABORT) { if (iclog->ic_state & XLOG_STATE_IOABORT) iclog->ic_state &= ~XLOG_STATE_IOABORT; @@ -1665,7 +1697,7 @@ xlog_cksum( char *dp, int size) { - __uint32_t crc; + uint32_t crc; /* first generate the crc for the record header ... */ crc = xfs_start_cksum_update((char *)rhead, @@ -1828,7 +1860,7 @@ xlog_sync( */ dptr = (char *)&iclog->ic_header + count; for (i = 0; i < split; i += BBSIZE) { - __uint32_t cycle = be32_to_cpu(*(__be32 *)dptr); + uint32_t cycle = be32_to_cpu(*(__be32 *)dptr); if (++cycle == XLOG_HEADER_MAGIC_NUM) cycle++; *(__be32 *)dptr = cpu_to_be32(cycle); @@ -1842,7 +1874,6 @@ xlog_sync( /* calculcate the checksum */ iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header, iclog->ic_datap, size); -#ifdef DEBUG /* * Intentionally corrupt the log record CRC based on the error injection * frequency, if defined. This facilitates testing log recovery in the @@ -1850,15 +1881,13 @@ xlog_sync( * write on I/O completion and shutdown the fs. The subsequent mount * detects the bad CRC and attempts to recover. */ - if (log->l_badcrc_factor && - (prandom_u32() % log->l_badcrc_factor == 0)) { + if (XFS_TEST_ERROR(false, log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) { iclog->ic_header.h_crc &= cpu_to_le32(0xAAAAAAAA); iclog->ic_state |= XLOG_STATE_IOABORT; xfs_warn(log->l_mp, "Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.", be64_to_cpu(iclog->ic_header.h_lsn)); } -#endif bp->b_io_length = BTOBB(count); bp->b_fspriv = iclog; @@ -2024,7 +2053,7 @@ xlog_print_tic_res( }; #undef REG_TYPE_STR - xfs_warn(mp, "xlog_write: reservation summary:"); + xfs_warn(mp, "ticket reservation summary:"); xfs_warn(mp, " unit res = %d bytes", ticket->t_unit_res); xfs_warn(mp, " current res = %d bytes", @@ -2045,10 +2074,55 @@ xlog_print_tic_res( "bad-rtype" : res_type_str[r_type]), ticket->t_res_arr[i].r_len); } +} + +/* + * Print a summary of the transaction. + */ +void +xlog_print_trans( + struct xfs_trans *tp) +{ + struct xfs_mount *mp = tp->t_mountp; + struct xfs_log_item_desc *lidp; + + /* dump core transaction and ticket info */ + xfs_warn(mp, "transaction summary:"); + xfs_warn(mp, " flags = 0x%x", tp->t_flags); + + xlog_print_tic_res(mp, tp->t_ticket); + + /* dump each log item */ + list_for_each_entry(lidp, &tp->t_items, lid_trans) { + struct xfs_log_item *lip = lidp->lid_item; + struct xfs_log_vec *lv = lip->li_lv; + struct xfs_log_iovec *vec; + int i; + + xfs_warn(mp, "log item: "); + xfs_warn(mp, " type = 0x%x", lip->li_type); + xfs_warn(mp, " flags = 0x%x", lip->li_flags); + if (!lv) + continue; + xfs_warn(mp, " niovecs = %d", lv->lv_niovecs); + xfs_warn(mp, " size = %d", lv->lv_size); + xfs_warn(mp, " bytes = %d", lv->lv_bytes); + xfs_warn(mp, " buf len = %d", lv->lv_buf_len); + + /* dump each iovec for the log item */ + vec = lv->lv_iovecp; + for (i = 0; i < lv->lv_niovecs; i++) { + int dumplen = min(vec->i_len, 32); - xfs_alert_tag(mp, XFS_PTAG_LOGRES, - "xlog_write: reservation ran out. Need to up reservation"); - xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR); + xfs_warn(mp, " iovec[%d]", i); + xfs_warn(mp, " type = 0x%x", vec->i_type); + xfs_warn(mp, " len = %d", vec->i_len); + xfs_warn(mp, " first %d bytes of iovec[%d]:", dumplen, i); + xfs_hex_dump(vec->i_addr, dumplen); + + vec++; + } + } } /* @@ -2321,8 +2395,12 @@ xlog_write( if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS)) ticket->t_curr_res -= sizeof(xlog_op_header_t); - if (ticket->t_curr_res < 0) + if (ticket->t_curr_res < 0) { + xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, + "ctx ticket reservation ran out. Need to up reservation"); xlog_print_tic_res(log->l_mp, ticket); + xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); + } index = 0; lv = log_vector; @@ -2363,8 +2441,8 @@ xlog_write( } reg = &vecp[index]; - ASSERT(reg->i_len % sizeof(__int32_t) == 0); - ASSERT((unsigned long)ptr % sizeof(__int32_t) == 0); + ASSERT(reg->i_len % sizeof(int32_t) == 0); + ASSERT((unsigned long)ptr % sizeof(int32_t) == 0); start_rec_copy = xlog_write_start_rec(ptr, ticket); if (start_rec_copy) { @@ -2437,7 +2515,7 @@ next_lv: if (lv) vecp = lv->lv_iovecp; } - if (record_cnt == 0 && ordered == false) { + if (record_cnt == 0 && !ordered) { if (!lv) return 0; break; @@ -3143,7 +3221,7 @@ xlog_state_switch_iclogs( /* Round up to next log-sunit */ if (xfs_sb_version_haslogv2(&log->l_mp->m_sb) && log->l_mp->m_sb.sb_logsunit > 1) { - __uint32_t sunit_bb = BTOBB(log->l_mp->m_sb.sb_logsunit); + uint32_t sunit_bb = BTOBB(log->l_mp->m_sb.sb_logsunit); log->l_curr_block = roundup(log->l_curr_block, sunit_bb); } @@ -3297,8 +3375,6 @@ maybe_sleep: */ if (iclog->ic_state & XLOG_STATE_IOERROR) return -EIO; - if (log_flushed) - *log_flushed = 1; } else { no_sleep: @@ -3402,8 +3478,6 @@ try_again: xlog_wait(&iclog->ic_prev->ic_write_wait, &log->l_icloglock); - if (log_flushed) - *log_flushed = 1; already_slept = 1; goto try_again; } @@ -3437,9 +3511,6 @@ try_again: */ if (iclog->ic_state & XLOG_STATE_IOERROR) return -EIO; - - if (log_flushed) - *log_flushed = 1; } else { /* just return */ spin_unlock(&log->l_icloglock); } @@ -3771,7 +3842,7 @@ xlog_verify_iclog( xlog_in_core_2_t *xhdr; void *base_ptr, *ptr, *p; ptrdiff_t field_offset; - __uint8_t clientid; + uint8_t clientid; int len, i, j, k, op_len; int idx; diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index cc5a9f1574e7..bf212772595c 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -159,7 +159,7 @@ int xfs_log_reserve(struct xfs_mount *mp, int length, int count, struct xlog_ticket **ticket, - __uint8_t clientid, + uint8_t clientid, bool permanent); int xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic); void xfs_log_unmount(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 82f1cbcc4de1..43aa42a3a5d3 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -410,6 +410,7 @@ xlog_cil_insert_items( int len = 0; int diff_iovecs = 0; int iclog_space; + int iovhdr_res = 0, split_res = 0, ctx_res = 0; ASSERT(tp); @@ -419,30 +420,11 @@ xlog_cil_insert_items( */ xlog_cil_insert_format_items(log, tp, &len, &diff_iovecs); - /* - * Now (re-)position everything modified at the tail of the CIL. - * We do this here so we only need to take the CIL lock once during - * the transaction commit. - */ spin_lock(&cil->xc_cil_lock); - list_for_each_entry(lidp, &tp->t_items, lid_trans) { - struct xfs_log_item *lip = lidp->lid_item; - - /* Skip items which aren't dirty in this transaction. */ - if (!(lidp->lid_flags & XFS_LID_DIRTY)) - continue; - - /* - * Only move the item if it isn't already at the tail. This is - * to prevent a transient list_empty() state when reinserting - * an item that is already the only item in the CIL. - */ - if (!list_is_last(&lip->li_cil, &cil->xc_cil)) - list_move_tail(&lip->li_cil, &cil->xc_cil); - } /* account for space used by new iovec headers */ - len += diff_iovecs * sizeof(xlog_op_header_t); + iovhdr_res = diff_iovecs * sizeof(xlog_op_header_t); + len += iovhdr_res; ctx->nvecs += diff_iovecs; /* attach the transaction to the CIL if it has any busy extents */ @@ -457,28 +439,66 @@ xlog_cil_insert_items( * during the transaction commit. */ if (ctx->ticket->t_curr_res == 0) { - ctx->ticket->t_curr_res = ctx->ticket->t_unit_res; - tp->t_ticket->t_curr_res -= ctx->ticket->t_unit_res; + ctx_res = ctx->ticket->t_unit_res; + ctx->ticket->t_curr_res = ctx_res; + tp->t_ticket->t_curr_res -= ctx_res; } /* do we need space for more log record headers? */ iclog_space = log->l_iclog_size - log->l_iclog_hsize; if (len > 0 && (ctx->space_used / iclog_space != (ctx->space_used + len) / iclog_space)) { - int hdrs; - - hdrs = (len + iclog_space - 1) / iclog_space; + split_res = (len + iclog_space - 1) / iclog_space; /* need to take into account split region headers, too */ - hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header); - ctx->ticket->t_unit_res += hdrs; - ctx->ticket->t_curr_res += hdrs; - tp->t_ticket->t_curr_res -= hdrs; + split_res *= log->l_iclog_hsize + sizeof(struct xlog_op_header); + ctx->ticket->t_unit_res += split_res; + ctx->ticket->t_curr_res += split_res; + tp->t_ticket->t_curr_res -= split_res; ASSERT(tp->t_ticket->t_curr_res >= len); } tp->t_ticket->t_curr_res -= len; ctx->space_used += len; + /* + * If we've overrun the reservation, dump the tx details before we move + * the log items. Shutdown is imminent... + */ + if (WARN_ON(tp->t_ticket->t_curr_res < 0)) { + xfs_warn(log->l_mp, "Transaction log reservation overrun:"); + xfs_warn(log->l_mp, + " log items: %d bytes (iov hdrs: %d bytes)", + len, iovhdr_res); + xfs_warn(log->l_mp, " split region headers: %d bytes", + split_res); + xfs_warn(log->l_mp, " ctx ticket: %d bytes", ctx_res); + xlog_print_trans(tp); + } + + /* + * Now (re-)position everything modified at the tail of the CIL. + * We do this here so we only need to take the CIL lock once during + * the transaction commit. + */ + list_for_each_entry(lidp, &tp->t_items, lid_trans) { + struct xfs_log_item *lip = lidp->lid_item; + + /* Skip items which aren't dirty in this transaction. */ + if (!(lidp->lid_flags & XFS_LID_DIRTY)) + continue; + + /* + * Only move the item if it isn't already at the tail. This is + * to prevent a transient list_empty() state when reinserting + * an item that is already the only item in the CIL. + */ + if (!list_is_last(&lip->li_cil, &cil->xc_cil)) + list_move_tail(&lip->li_cil, &cil->xc_cil); + } + spin_unlock(&cil->xc_cil_lock); + + if (tp->t_ticket->t_curr_res < 0) + xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); } static void @@ -519,6 +539,7 @@ xlog_discard_endio( INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work); queue_work(xfs_discard_wq, &ctx->discard_endio_work); + bio_put(bio); } static void @@ -973,6 +994,7 @@ xfs_log_commit_cil( { struct xlog *log = mp->m_log; struct xfs_cil *cil = log->l_cilp; + xfs_lsn_t xc_commit_lsn; /* * Do all necessary memory allocation before we lock the CIL. @@ -986,13 +1008,9 @@ xfs_log_commit_cil( xlog_cil_insert_items(log, tp); - /* check we didn't blow the reservation */ - if (tp->t_ticket->t_curr_res < 0) - xlog_print_tic_res(mp, tp->t_ticket); - - tp->t_commit_lsn = cil->xc_ctx->sequence; + xc_commit_lsn = cil->xc_ctx->sequence; if (commit_lsn) - *commit_lsn = tp->t_commit_lsn; + *commit_lsn = xc_commit_lsn; xfs_log_done(mp, tp->t_ticket, NULL, regrant); xfs_trans_unreserve_and_mod_sb(tp); @@ -1008,7 +1026,7 @@ xfs_log_commit_cil( * the log items. This affects (at least) processing of stale buffers, * inodes and EFIs. */ - xfs_trans_free_items(tp, tp->t_commit_lsn, false); + xfs_trans_free_items(tp, xc_commit_lsn, false); xlog_cil_push_background(log); diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index c2604a5366f2..51bf7b827387 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -419,7 +419,7 @@ struct xlog { }; #define XLOG_BUF_CANCEL_BUCKET(log, blkno) \ - ((log)->l_buf_cancel_table + ((__uint64_t)blkno % XLOG_BC_TABLE_SIZE)) + ((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE)) #define XLOG_FORCED_SHUTDOWN(log) ((log)->l_flags & XLOG_IO_ERROR) @@ -456,6 +456,7 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes) } void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket); +void xlog_print_trans(struct xfs_trans *); int xlog_write( struct xlog *log, diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index cd0b077deb35..ee34899396b2 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -352,13 +352,13 @@ xlog_header_check_mount( { ASSERT(head->h_magicno == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)); - if (uuid_is_nil(&head->h_fs_uuid)) { + if (uuid_is_null(&head->h_fs_uuid)) { /* * IRIX doesn't write the h_fs_uuid or h_fmt fields. If - * h_fs_uuid is nil, we assume this log was last mounted + * h_fs_uuid is null, we assume this log was last mounted * by IRIX and continue. */ - xfs_warn(mp, "nil uuid in log - IRIX style log"); + xfs_warn(mp, "null uuid in log - IRIX style log"); } else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) { xfs_warn(mp, "log has mismatched uuid - can't recover"); xlog_header_check_dump(mp, head); @@ -1029,61 +1029,106 @@ out_error: } /* - * Check the log tail for torn writes. This is required when torn writes are - * detected at the head and the head had to be walked back to a previous record. - * The tail of the previous record must now be verified to ensure the torn - * writes didn't corrupt the previous tail. + * Calculate distance from head to tail (i.e., unused space in the log). + */ +static inline int +xlog_tail_distance( + struct xlog *log, + xfs_daddr_t head_blk, + xfs_daddr_t tail_blk) +{ + if (head_blk < tail_blk) + return tail_blk - head_blk; + + return tail_blk + (log->l_logBBsize - head_blk); +} + +/* + * Verify the log tail. This is particularly important when torn or incomplete + * writes have been detected near the front of the log and the head has been + * walked back accordingly. * - * Return an error if CRC verification fails as recovery cannot proceed. + * We also have to handle the case where the tail was pinned and the head + * blocked behind the tail right before a crash. If the tail had been pushed + * immediately prior to the crash and the subsequent checkpoint was only + * partially written, it's possible it overwrote the last referenced tail in the + * log with garbage. This is not a coherency problem because the tail must have + * been pushed before it can be overwritten, but appears as log corruption to + * recovery because we have no way to know the tail was updated if the + * subsequent checkpoint didn't write successfully. + * + * Therefore, CRC check the log from tail to head. If a failure occurs and the + * offending record is within max iclog bufs from the head, walk the tail + * forward and retry until a valid tail is found or corruption is detected out + * of the range of a possible overwrite. */ STATIC int xlog_verify_tail( struct xlog *log, xfs_daddr_t head_blk, - xfs_daddr_t tail_blk) + xfs_daddr_t *tail_blk, + int hsize) { struct xlog_rec_header *thead; struct xfs_buf *bp; xfs_daddr_t first_bad; - int count; int error = 0; bool wrapped; - xfs_daddr_t tmp_head; + xfs_daddr_t tmp_tail; + xfs_daddr_t orig_tail = *tail_blk; bp = xlog_get_bp(log, 1); if (!bp) return -ENOMEM; /* - * Seek XLOG_MAX_ICLOGS + 1 records past the current tail record to get - * a temporary head block that points after the last possible - * concurrently written record of the tail. + * Make sure the tail points to a record (returns positive count on + * success). */ - count = xlog_seek_logrec_hdr(log, head_blk, tail_blk, - XLOG_MAX_ICLOGS + 1, bp, &tmp_head, &thead, - &wrapped); - if (count < 0) { - error = count; + error = xlog_seek_logrec_hdr(log, head_blk, *tail_blk, 1, bp, + &tmp_tail, &thead, &wrapped); + if (error < 0) goto out; - } - - /* - * If the call above didn't find XLOG_MAX_ICLOGS + 1 records, we ran - * into the actual log head. tmp_head points to the start of the record - * so update it to the actual head block. - */ - if (count < XLOG_MAX_ICLOGS + 1) - tmp_head = head_blk; + if (*tail_blk != tmp_tail) + *tail_blk = tmp_tail; /* - * We now have a tail and temporary head block that covers at least - * XLOG_MAX_ICLOGS records from the tail. We need to verify that these - * records were completely written. Run a CRC verification pass from - * tail to head and return the result. + * Run a CRC check from the tail to the head. We can't just check + * MAX_ICLOGS records past the tail because the tail may point to stale + * blocks cleared during the search for the head/tail. These blocks are + * overwritten with zero-length records and thus record count is not a + * reliable indicator of the iclog state before a crash. */ - error = xlog_do_recovery_pass(log, tmp_head, tail_blk, + first_bad = 0; + error = xlog_do_recovery_pass(log, head_blk, *tail_blk, XLOG_RECOVER_CRCPASS, &first_bad); + while ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) { + int tail_distance; + + /* + * Is corruption within range of the head? If so, retry from + * the next record. Otherwise return an error. + */ + tail_distance = xlog_tail_distance(log, head_blk, first_bad); + if (tail_distance > BTOBB(XLOG_MAX_ICLOGS * hsize)) + break; + + /* skip to the next record; returns positive count on success */ + error = xlog_seek_logrec_hdr(log, head_blk, first_bad, 2, bp, + &tmp_tail, &thead, &wrapped); + if (error < 0) + goto out; + + *tail_blk = tmp_tail; + first_bad = 0; + error = xlog_do_recovery_pass(log, head_blk, *tail_blk, + XLOG_RECOVER_CRCPASS, &first_bad); + } + if (!error && *tail_blk != orig_tail) + xfs_warn(log->l_mp, + "Tail block (0x%llx) overwrite detected. Updated to 0x%llx", + orig_tail, *tail_blk); out: xlog_put_bp(bp); return error; @@ -1143,7 +1188,7 @@ xlog_verify_head( */ error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk, XLOG_RECOVER_CRCPASS, &first_bad); - if (error == -EFSBADCRC) { + if ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) { /* * We've hit a potential torn write. Reset the error and warn * about it. @@ -1183,31 +1228,12 @@ xlog_verify_head( ASSERT(0); return 0; } - - /* - * Now verify the tail based on the updated head. This is - * required because the torn writes trimmed from the head could - * have been written over the tail of a previous record. Return - * any errors since recovery cannot proceed if the tail is - * corrupt. - * - * XXX: This leaves a gap in truly robust protection from torn - * writes in the log. If the head is behind the tail, the tail - * pushes forward to create some space and then a crash occurs - * causing the writes into the previous record's tail region to - * tear, log recovery isn't able to recover. - * - * How likely is this to occur? If possible, can we do something - * more intelligent here? Is it safe to push the tail forward if - * we can determine that the tail is within the range of the - * torn write (e.g., the kernel can only overwrite the tail if - * it has actually been pushed forward)? Alternatively, could we - * somehow prevent this condition at runtime? - */ - error = xlog_verify_tail(log, *head_blk, *tail_blk); } + if (error) + return error; - return error; + return xlog_verify_tail(log, *head_blk, tail_blk, + be32_to_cpu((*rhead)->h_size)); } /* @@ -2230,9 +2256,9 @@ xlog_recover_get_buf_lsn( struct xfs_mount *mp, struct xfs_buf *bp) { - __uint32_t magic32; - __uint16_t magic16; - __uint16_t magicda; + uint32_t magic32; + uint16_t magic16; + uint16_t magicda; void *blk = bp->b_addr; uuid_t *uuid; xfs_lsn_t lsn = -1; @@ -2381,9 +2407,9 @@ xlog_recover_validate_buf_type( xfs_lsn_t current_lsn) { struct xfs_da_blkinfo *info = bp->b_addr; - __uint32_t magic32; - __uint16_t magic16; - __uint16_t magicda; + uint32_t magic32; + uint16_t magic16; + uint16_t magicda; char *warnmsg = NULL; /* @@ -2852,7 +2878,7 @@ xlog_recover_buffer_pass2( if (XFS_DINODE_MAGIC == be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) && (BBTOB(bp->b_io_length) != MAX(log->l_mp->m_sb.sb_blocksize, - (__uint32_t)log->l_mp->m_inode_cluster_size))) { + (uint32_t)log->l_mp->m_inode_cluster_size))) { xfs_buf_stale(bp); error = xfs_bwrite(bp); } else { @@ -3423,7 +3449,7 @@ xlog_recover_efd_pass2( xfs_efd_log_format_t *efd_formatp; xfs_efi_log_item_t *efip = NULL; xfs_log_item_t *lip; - __uint64_t efi_id; + uint64_t efi_id; struct xfs_ail_cursor cur; struct xfs_ail *ailp = log->l_ailp; @@ -3519,7 +3545,7 @@ xlog_recover_rud_pass2( struct xfs_rud_log_format *rud_formatp; struct xfs_rui_log_item *ruip = NULL; struct xfs_log_item *lip; - __uint64_t rui_id; + uint64_t rui_id; struct xfs_ail_cursor cur; struct xfs_ail *ailp = log->l_ailp; @@ -3635,7 +3661,7 @@ xlog_recover_cud_pass2( struct xfs_cud_log_format *cud_formatp; struct xfs_cui_log_item *cuip = NULL; struct xfs_log_item *lip; - __uint64_t cui_id; + uint64_t cui_id; struct xfs_ail_cursor cur; struct xfs_ail *ailp = log->l_ailp; @@ -3754,7 +3780,7 @@ xlog_recover_bud_pass2( struct xfs_bud_log_format *bud_formatp; struct xfs_bui_log_item *buip = NULL; struct xfs_log_item *lip; - __uint64_t bui_id; + uint64_t bui_id; struct xfs_ail_cursor cur; struct xfs_ail *ailp = log->l_ailp; @@ -4152,7 +4178,7 @@ xlog_recover_commit_trans( #define XLOG_RECOVER_COMMIT_QUEUE_MAX 100 - hlist_del(&trans->r_list); + hlist_del_init(&trans->r_list); error = xlog_recover_reorder_trans(log, trans, pass); if (error) @@ -4354,6 +4380,8 @@ xlog_recover_free_trans( xlog_recover_item_t *item, *n; int i; + hlist_del_init(&trans->r_list); + list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) { /* Free the regions in the item. */ list_del(&item->ri_list); @@ -4799,12 +4827,16 @@ xlog_recover_process_intents( int error = 0; struct xfs_ail_cursor cur; struct xfs_ail *ailp; +#if defined(DEBUG) || defined(XFS_WARN) xfs_lsn_t last_lsn; +#endif ailp = log->l_ailp; spin_lock(&ailp->xa_lock); lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); +#if defined(DEBUG) || defined(XFS_WARN) last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block); +#endif while (lip != NULL) { /* * We're done when we see something other than an intent. @@ -5216,7 +5248,7 @@ xlog_do_recovery_pass( xfs_daddr_t *first_bad) /* out: first bad log rec */ { xlog_rec_header_t *rhead; - xfs_daddr_t blk_no; + xfs_daddr_t blk_no, rblk_no; xfs_daddr_t rhead_blk; char *offset; xfs_buf_t *hbp, *dbp; @@ -5224,11 +5256,15 @@ xlog_do_recovery_pass( int error2 = 0; int bblks, split_bblks; int hblks, split_hblks, wrapped_hblks; + int i; struct hlist_head rhash[XLOG_RHASH_SIZE]; LIST_HEAD (buffer_list); ASSERT(head_blk != tail_blk); - rhead_blk = 0; + blk_no = rhead_blk = tail_blk; + + for (i = 0; i < XLOG_RHASH_SIZE; i++) + INIT_HLIST_HEAD(&rhash[i]); /* * Read the header of the tail block and get the iclog buffer size from @@ -5303,7 +5339,6 @@ xlog_do_recovery_pass( } memset(rhash, 0, sizeof(rhash)); - blk_no = rhead_blk = tail_blk; if (tail_blk > head_blk) { /* * Perform recovery around the end of the physical log. @@ -5365,9 +5400,19 @@ xlog_do_recovery_pass( bblks = (int)BTOBB(be32_to_cpu(rhead->h_len)); blk_no += hblks; - /* Read in data for log record */ - if (blk_no + bblks <= log->l_logBBsize) { - error = xlog_bread(log, blk_no, bblks, dbp, + /* + * Read the log record data in multiple reads if it + * wraps around the end of the log. Note that if the + * header already wrapped, blk_no could point past the + * end of the log. The record data is contiguous in + * that case. + */ + if (blk_no + bblks <= log->l_logBBsize || + blk_no >= log->l_logBBsize) { + /* mod blk_no in case the header wrapped and + * pushed it beyond the end of the log */ + rblk_no = do_mod(blk_no, log->l_logBBsize); + error = xlog_bread(log, rblk_no, bblks, dbp, &offset); if (error) goto bread_err2; @@ -5466,6 +5511,19 @@ xlog_do_recovery_pass( if (error && first_bad) *first_bad = rhead_blk; + /* + * Transactions are freed at commit time but transactions without commit + * records on disk are never committed. Free any that may be left in the + * hash table. + */ + for (i = 0; i < XLOG_RHASH_SIZE; i++) { + struct hlist_node *tmp; + struct xlog_recover *trans; + + hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list) + xlog_recover_free_trans(trans); + } + return error ? error : error2; } @@ -5544,6 +5602,8 @@ xlog_do_recover( xfs_buf_t *bp; xfs_sb_t *sbp; + trace_xfs_log_recover(log, head_blk, tail_blk); + /* * First replay the images in the log. */ @@ -5772,9 +5832,9 @@ xlog_recover_check_summary( xfs_buf_t *agfbp; xfs_buf_t *agibp; xfs_agnumber_t agno; - __uint64_t freeblks; - __uint64_t itotal; - __uint64_t ifree; + uint64_t freeblks; + uint64_t itotal; + uint64_t ifree; int error; mp = log->l_mp; diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 11792d888e4e..e68bd1050eab 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -110,7 +110,10 @@ assfail(char *expr, char *file, int line) { xfs_emerg(NULL, "Assertion failed: %s, file: %s, line: %d", expr, file, line); - BUG(); + if (xfs_globals.bug_on_assert) + BUG(); + else + WARN_ON(1); } void diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 2eaf81859166..e9727d0a541a 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -74,20 +74,19 @@ xfs_uuid_mount( int hole, i; /* Publish UUID in struct super_block */ - BUILD_BUG_ON(sizeof(mp->m_super->s_uuid) != sizeof(uuid_t)); - memcpy(&mp->m_super->s_uuid, uuid, sizeof(uuid_t)); + uuid_copy(&mp->m_super->s_uuid, uuid); if (mp->m_flags & XFS_MOUNT_NOUUID) return 0; - if (uuid_is_nil(uuid)) { - xfs_warn(mp, "Filesystem has nil UUID - can't mount"); + if (uuid_is_null(uuid)) { + xfs_warn(mp, "Filesystem has null UUID - can't mount"); return -EINVAL; } mutex_lock(&xfs_uuid_table_mutex); for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) { - if (uuid_is_nil(&xfs_uuid_table[i])) { + if (uuid_is_null(&xfs_uuid_table[i])) { hole = i; continue; } @@ -124,7 +123,7 @@ xfs_uuid_unmount( mutex_lock(&xfs_uuid_table_mutex); for (i = 0; i < xfs_uuid_table_size; i++) { - if (uuid_is_nil(&xfs_uuid_table[i])) + if (uuid_is_null(&xfs_uuid_table[i])) continue; if (!uuid_equal(uuid, &xfs_uuid_table[i])) continue; @@ -174,7 +173,7 @@ xfs_free_perag( int xfs_sb_validate_fsb_count( xfs_sb_t *sbp, - __uint64_t nblocks) + uint64_t nblocks) { ASSERT(PAGE_SHIFT >= sbp->sb_blocklog); ASSERT(sbp->sb_blocklog >= BBSHIFT); @@ -436,7 +435,7 @@ STATIC void xfs_set_maxicount(xfs_mount_t *mp) { xfs_sb_t *sbp = &(mp->m_sb); - __uint64_t icount; + uint64_t icount; if (sbp->sb_imax_pct) { /* @@ -502,7 +501,7 @@ xfs_set_low_space_thresholds( int i; for (i = 0; i < XFS_LOWSP_MAX; i++) { - __uint64_t space = mp->m_sb.sb_dblocks; + uint64_t space = mp->m_sb.sb_dblocks; do_div(space, 100); mp->m_low_space[i] = space * (i + 1); @@ -598,10 +597,10 @@ xfs_mount_reset_sbqflags( return xfs_sync_sb(mp, false); } -__uint64_t +uint64_t xfs_default_resblks(xfs_mount_t *mp) { - __uint64_t resblks; + uint64_t resblks; /* * We default to 5% or 8192 fsbs of space reserved, whichever is @@ -612,7 +611,7 @@ xfs_default_resblks(xfs_mount_t *mp) */ resblks = mp->m_sb.sb_dblocks; do_div(resblks, 20); - resblks = min_t(__uint64_t, resblks, 8192); + resblks = min_t(uint64_t, resblks, 8192); return resblks; } @@ -632,7 +631,7 @@ xfs_mountfs( { struct xfs_sb *sbp = &(mp->m_sb); struct xfs_inode *rip; - __uint64_t resblks; + uint64_t resblks; uint quotamount = 0; uint quotaflags = 0; int error = 0; @@ -705,7 +704,7 @@ xfs_mountfs( xfs_set_maxicount(mp); /* enable fail_at_unmount as default */ - mp->m_fail_unmount = 1; + mp->m_fail_unmount = true; error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname); if (error) @@ -720,10 +719,13 @@ xfs_mountfs( if (error) goto out_del_stats; + error = xfs_errortag_init(mp); + if (error) + goto out_remove_error_sysfs; error = xfs_uuid_mount(mp); if (error) - goto out_remove_error_sysfs; + goto out_remove_errortag; /* * Set the minimum read and write sizes @@ -793,7 +795,10 @@ xfs_mountfs( * Copies the low order bits of the timestamp and the randomly * set "sequence" number out of a UUID. */ - uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid); + mp->m_fixedfsid[0] = + (get_unaligned_be16(&sbp->sb_uuid.b[8]) << 16) | + get_unaligned_be16(&sbp->sb_uuid.b[4]); + mp->m_fixedfsid[1] = get_unaligned_be32(&sbp->sb_uuid.b[0]); mp->m_dmevmask = 0; /* not persistent; set after each mount */ @@ -940,15 +945,6 @@ xfs_mountfs( } /* - * During the second phase of log recovery, we need iget and - * iput to behave like they do for an active filesystem. - * xfs_fs_drop_inode needs to be able to prevent the deletion - * of inodes before we're done replaying log items on those - * inodes. - */ - mp->m_super->s_flags |= MS_ACTIVE; - - /* * Finish recovering the file system. This part needed to be delayed * until after the root and real-time bitmap inodes were consistently * read in. @@ -1023,12 +1019,13 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: - mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); + /* Clean out dquots that might be in memory after quotacheck. */ + xfs_qm_unmount(mp); out_log_dealloc: mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); @@ -1042,6 +1039,8 @@ xfs_mountfs( xfs_da_unmount(mp); out_remove_uuid: xfs_uuid_unmount(mp); + out_remove_errortag: + xfs_errortag_del(mp); out_remove_error_sysfs: xfs_error_sysfs_del(mp); out_del_stats: @@ -1060,7 +1059,7 @@ void xfs_unmountfs( struct xfs_mount *mp) { - __uint64_t resblks; + uint64_t resblks; int error; cancel_delayed_work_sync(&mp->m_eofblocks_work); @@ -1145,10 +1144,11 @@ xfs_unmountfs( xfs_uuid_unmount(mp); #if defined(DEBUG) - xfs_errortag_clearall(mp, 0); + xfs_errortag_clearall(mp); #endif xfs_free_perag(mp); + xfs_errortag_del(mp); xfs_error_sysfs_del(mp); xfs_sysfs_del(&mp->m_stats.xs_kobj); xfs_sysfs_del(&mp->m_kobj); @@ -1209,7 +1209,7 @@ xfs_mod_icount( struct xfs_mount *mp, int64_t delta) { - __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH); + percpu_counter_add_batch(&mp->m_icount, delta, XFS_ICOUNT_BATCH); if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) { ASSERT(0); percpu_counter_add(&mp->m_icount, -delta); @@ -1288,7 +1288,7 @@ xfs_mod_fdblocks( else batch = XFS_FDBLOCKS_BATCH; - __percpu_counter_add(&mp->m_fdblocks, delta, batch); + percpu_counter_add_batch(&mp->m_fdblocks, delta, batch); if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside, XFS_FDBLOCKS_BATCH) >= 0) { /* we had space! */ diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 9fa312a41c93..e0792d036be2 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -108,10 +108,10 @@ typedef struct xfs_mount { xfs_buftarg_t *m_ddev_targp; /* saves taking the address */ xfs_buftarg_t *m_logdev_targp;/* ptr to log device */ xfs_buftarg_t *m_rtdev_targp; /* ptr to rt device */ - __uint8_t m_blkbit_log; /* blocklog + NBBY */ - __uint8_t m_blkbb_log; /* blocklog - BBSHIFT */ - __uint8_t m_agno_log; /* log #ag's */ - __uint8_t m_agino_log; /* #bits for agino in inum */ + uint8_t m_blkbit_log; /* blocklog + NBBY */ + uint8_t m_blkbb_log; /* blocklog - BBSHIFT */ + uint8_t m_agno_log; /* log #ag's */ + uint8_t m_agino_log; /* #bits for agino in inum */ uint m_inode_cluster_size;/* min inode buf size */ uint m_blockmask; /* sb_blocksize-1 */ uint m_blockwsize; /* sb_blocksize in words */ @@ -139,7 +139,7 @@ typedef struct xfs_mount { struct mutex m_growlock; /* growfs mutex */ int m_fixedfsid[2]; /* unchanged for life of FS */ uint m_dmevmask; /* DMI events for this FS */ - __uint64_t m_flags; /* global mount flags */ + uint64_t m_flags; /* global mount flags */ bool m_inotbt_nores; /* no per-AG finobt resv. */ int m_ialloc_inos; /* inodes in inode allocation */ int m_ialloc_blks; /* blocks in inode allocation */ @@ -148,14 +148,14 @@ typedef struct xfs_mount { int m_inoalign_mask;/* mask sb_inoalignmt if used */ uint m_qflags; /* quota status flags */ struct xfs_trans_resv m_resv; /* precomputed res values */ - __uint64_t m_maxicount; /* maximum inode count */ - __uint64_t m_resblks; /* total reserved blocks */ - __uint64_t m_resblks_avail;/* available reserved blocks */ - __uint64_t m_resblks_save; /* reserved blks @ remount,ro */ + uint64_t m_maxicount; /* maximum inode count */ + uint64_t m_resblks; /* total reserved blocks */ + uint64_t m_resblks_avail;/* available reserved blocks */ + uint64_t m_resblks_save; /* reserved blks @ remount,ro */ int m_dalign; /* stripe unit */ int m_swidth; /* stripe width */ int m_sinoalign; /* stripe unit inode alignment */ - __uint8_t m_sectbb_log; /* sectlog - BBSHIFT */ + uint8_t m_sectbb_log; /* sectlog - BBSHIFT */ const struct xfs_nameops *m_dirnameops; /* vector of dir name ops */ const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */ const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */ @@ -194,19 +194,17 @@ typedef struct xfs_mount { * ever support shrinks it would have to be persisted in addition * to various other kinds of pain inflicted on the pNFS server. */ - __uint32_t m_generation; + uint32_t m_generation; bool m_fail_unmount; #ifdef DEBUG /* - * DEBUG mode instrumentation to test and/or trigger delayed allocation - * block killing in the event of failed writes. When enabled, all - * buffered writes are silenty dropped and handled as if they failed. - * All delalloc blocks in the range of the write (including pre-existing - * delalloc blocks!) are tossed as part of the write failure error - * handling sequence. + * Frequency with which errors are injected. Replaces xfs_etest; the + * value stored in here is the inverse of the frequency with which the + * error triggers. 1 = always, 2 = half the time, etc. */ - bool m_drop_writes; + unsigned int *m_errortag; + struct xfs_kobj m_errortag_kobj; #endif } xfs_mount_t; @@ -325,20 +323,6 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d) return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks); } -#ifdef DEBUG -static inline bool -xfs_mp_drop_writes(struct xfs_mount *mp) -{ - return mp->m_drop_writes; -} -#else -static inline bool -xfs_mp_drop_writes(struct xfs_mount *mp) -{ - return 0; -} -#endif - /* per-AG block reservation data structures*/ enum xfs_ag_resv_type { XFS_AG_RESV_NONE = 0, @@ -367,12 +351,12 @@ typedef struct xfs_perag { char pagi_init; /* this agi's entry is initialized */ char pagf_metadata; /* the agf is preferred to be metadata */ char pagi_inodeok; /* The agi is ok for inodes */ - __uint8_t pagf_levels[XFS_BTNUM_AGF]; + uint8_t pagf_levels[XFS_BTNUM_AGF]; /* # of levels in bno & cnt btree */ - __uint32_t pagf_flcount; /* count of blocks in freelist */ + uint32_t pagf_flcount; /* count of blocks in freelist */ xfs_extlen_t pagf_freeblks; /* total free blocks */ xfs_extlen_t pagf_longest; /* longest free space */ - __uint32_t pagf_btreeblks; /* # of blocks held in AGF btrees */ + uint32_t pagf_btreeblks; /* # of blocks held in AGF btrees */ xfs_agino_t pagi_freecount; /* number of free inodes */ xfs_agino_t pagi_count; /* number of allocated inodes */ @@ -411,7 +395,7 @@ typedef struct xfs_perag { struct xfs_ag_resv pag_agfl_resv; /* reference count */ - __uint8_t pagf_refcount_level; + uint8_t pagf_refcount_level; } xfs_perag_t; static inline struct xfs_ag_resv * @@ -434,7 +418,7 @@ void xfs_buf_hash_destroy(xfs_perag_t *pag); extern void xfs_uuid_table_free(void); extern int xfs_log_sbcount(xfs_mount_t *); -extern __uint64_t xfs_default_resblks(xfs_mount_t *mp); +extern uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern int xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount, xfs_agnumber_t *maxagi); @@ -450,7 +434,7 @@ extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); extern bool xfs_fs_writable(struct xfs_mount *mp, int level); -extern int xfs_sb_validate_fsb_count(struct xfs_sb *, __uint64_t); +extern int xfs_sb_validate_fsb_count(struct xfs_sb *, uint64_t); extern int xfs_dev_is_read_only(struct xfs_mount *, char *); diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 0c381d71b242..0492436a053f 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -134,7 +134,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28); XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52); - XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20); XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); } diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 2f2dc3c09ad0..4246876df7b7 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -274,7 +274,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 5fe6e70b88ef..010a13a201aa 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -31,6 +31,7 @@ #include "xfs_error.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" +#include "xfs_bmap_util.h" #include "xfs_trans.h" #include "xfs_trans_space.h" #include "xfs_qm.h" @@ -111,6 +112,9 @@ restart: skipped = 0; break; } + /* we're done if id overflows back to zero */ + if (!next_index) + break; } if (skipped) { @@ -1117,31 +1121,6 @@ xfs_qm_quotacheck_dqadjust( return 0; } -STATIC int -xfs_qm_get_rtblks( - xfs_inode_t *ip, - xfs_qcnt_t *O_rtblks) -{ - xfs_filblks_t rtblks; /* total rt blks */ - xfs_extnum_t idx; /* extent record index */ - xfs_ifork_t *ifp; /* inode fork pointer */ - xfs_extnum_t nextents; /* number of extent entries */ - int error; - - ASSERT(XFS_IS_REALTIME_INODE(ip)); - ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); - if (!(ifp->if_flags & XFS_IFEXTENTS)) { - if ((error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK))) - return error; - } - rtblks = 0; - nextents = xfs_iext_count(ifp); - for (idx = 0; idx < nextents; idx++) - rtblks += xfs_bmbt_get_blockcount(xfs_iext_get_ext(ifp, idx)); - *O_rtblks = (xfs_qcnt_t)rtblks; - return 0; -} - /* * callback routine supplied to bulkstat(). Given an inumber, find its * dquots and update them to account for resources taken by that inode. @@ -1157,7 +1136,8 @@ xfs_qm_dqusage_adjust( int *res) /* result code value */ { xfs_inode_t *ip; - xfs_qcnt_t nblks, rtblks = 0; + xfs_qcnt_t nblks; + xfs_filblks_t rtblks = 0; /* total rt blks */ int error; ASSERT(XFS_IS_QUOTA_RUNNING(mp)); @@ -1187,12 +1167,15 @@ xfs_qm_dqusage_adjust( ASSERT(ip->i_delayed_blks == 0); if (XFS_IS_REALTIME_INODE(ip)) { - /* - * Walk thru the extent list and count the realtime blocks. - */ - error = xfs_qm_get_rtblks(ip, &rtblks); - if (error) - goto error0; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); + if (error) + goto error0; + } + + xfs_bmap_count_leaves(ifp, &rtblks); } nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks; @@ -1247,6 +1230,7 @@ xfs_qm_flush_one( struct xfs_dquot *dqp, void *data) { + struct xfs_mount *mp = dqp->q_mount; struct list_head *buffer_list = data; struct xfs_buf *bp = NULL; int error = 0; @@ -1257,7 +1241,32 @@ xfs_qm_flush_one( if (!XFS_DQ_IS_DIRTY(dqp)) goto out_unlock; - xfs_dqflock(dqp); + /* + * The only way the dquot is already flush locked by the time quotacheck + * gets here is if reclaim flushed it before the dqadjust walk dirtied + * it for the final time. Quotacheck collects all dquot bufs in the + * local delwri queue before dquots are dirtied, so reclaim can't have + * possibly queued it for I/O. The only way out is to push the buffer to + * cycle the flush lock. + */ + if (!xfs_dqflock_nowait(dqp)) { + /* buf is pinned in-core by delwri list */ + DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen); + bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL); + if (!bp) { + error = -EINVAL; + goto out_unlock; + } + xfs_buf_unlock(bp); + + xfs_buf_delwri_pushbuf(bp, buffer_list); + xfs_buf_rele(bp); + + error = -EAGAIN; + goto out_unlock; + } + error = xfs_qm_dqflush(dqp, &bp); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 3e52d5de7ae1..2be6d2735ca9 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -33,7 +33,7 @@ xfs_fill_statvfs_from_dquot( struct kstatfs *statp, struct xfs_dquot *dqp) { - __uint64_t limit; + uint64_t limit; limit = dqp->q_core.d_blk_softlimit ? be64_to_cpu(dqp->q_core.d_blk_softlimit) : diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index f82d79a8c694..a65108594a07 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -125,7 +125,7 @@ xfs_fs_set_info( struct xfs_mount *mp = XFS_M(sb); struct qc_dqblk newlim; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; @@ -175,7 +175,7 @@ xfs_quota_enable( { struct xfs_mount *mp = XFS_M(sb); - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; @@ -190,7 +190,7 @@ xfs_quota_disable( { struct xfs_mount *mp = XFS_M(sb); - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; @@ -208,7 +208,7 @@ xfs_fs_rm_xquota( struct xfs_mount *mp = XFS_M(sb); unsigned int flags = 0; - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; if (XFS_IS_QUOTA_ON(mp)) @@ -269,7 +269,6 @@ xfs_fs_get_nextdqblk( /* ID may be different, so convert back what we got */ *qid = make_kqid(current_user_ns(), qid->type, id); return 0; - } STATIC int @@ -280,7 +279,7 @@ xfs_fs_set_dqblk( { struct xfs_mount *mp = XFS_M(sb); - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) return -EROFS; if (!XFS_IS_QUOTA_RUNNING(mp)) return -ENOSYS; diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 96fe209b5eb6..8f2e2fac4255 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -525,7 +525,7 @@ xfs_cui_recover( } xfs_refcount_finish_one_cleanup(tp, rcur, error); - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto abort_defer; set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index ffe6fe7a7eb5..37e603bf1591 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -155,6 +155,7 @@ int xfs_reflink_find_shared( struct xfs_mount *mp, + struct xfs_trans *tp, xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen, @@ -166,18 +167,20 @@ xfs_reflink_find_shared( struct xfs_btree_cur *cur; int error; - error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); + error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (error) return error; + if (!agbp) + return -ENOMEM; - cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL); + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL); error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen, find_end_of_shared); xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); - xfs_buf_relse(agbp); + xfs_trans_brelse(tp, agbp); return error; } @@ -217,7 +220,7 @@ xfs_reflink_trim_around_shared( agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock); aglen = irec->br_blockcount; - error = xfs_reflink_find_shared(ip->i_mount, agno, agbno, + error = xfs_reflink_find_shared(ip->i_mount, NULL, agno, agbno, aglen, &fbno, &flen, true); if (error) return error; @@ -328,7 +331,7 @@ xfs_reflink_convert_cow_extent( xfs_filblks_t count_fsb, struct xfs_defer_ops *dfops) { - xfs_fsblock_t first_block; + xfs_fsblock_t first_block = NULLFSBLOCK; int nimaps = 1; if (imap->br_state == XFS_EXT_NORM) @@ -461,7 +464,7 @@ retry: goto out_bmap_cancel; /* Finish up. */ - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -599,7 +602,8 @@ xfs_reflink_cancel_cow_blocks( -(long)del.br_blockcount); /* Roll the transaction */ - error = xfs_defer_finish(tpp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(tpp, &dfops); if (error) { xfs_defer_cancel(&dfops); break; @@ -732,7 +736,13 @@ xfs_reflink_end_cow( /* If there is a hole at end_fsb - 1 go to the previous extent */ if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) || got.br_startoff > end_fsb) { - ASSERT(idx > 0); + /* + * In case of racing, overlapping AIO writes no COW extents + * might be left by the time I/O completes for the loser of + * the race. In that case we are done. + */ + if (idx <= 0) + goto out_cancel; xfs_iext_get_extent(ifp, --idx, &got); } @@ -788,7 +798,8 @@ xfs_reflink_end_cow( /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &idx, &got, &del); - error = xfs_defer_finish(&tp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_defer; next_extent: @@ -804,6 +815,7 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); +out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: @@ -1149,7 +1161,8 @@ xfs_reflink_remap_extent( next_extent: /* Process all the deferred stuff. */ - error = xfs_defer_finish(&tp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_defer; } @@ -1373,8 +1386,8 @@ xfs_reflink_dirty_extents( agbno = XFS_FSB_TO_AGBNO(mp, map[1].br_startblock); aglen = map[1].br_blockcount; - error = xfs_reflink_find_shared(mp, agno, agbno, aglen, - &rbno, &rlen, true); + error = xfs_reflink_find_shared(mp, NULL, agno, agbno, + aglen, &rbno, &rlen, true); if (error) goto out; if (rbno == NULLAGBLOCK) @@ -1405,57 +1418,73 @@ out: return error; } -/* Clear the inode reflink flag if there are no shared extents. */ +/* Does this inode need the reflink flag? */ int -xfs_reflink_clear_inode_flag( - struct xfs_inode *ip, - struct xfs_trans **tpp) +xfs_reflink_inode_has_shared_extents( + struct xfs_trans *tp, + struct xfs_inode *ip, + bool *has_shared) { - struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t fbno; - xfs_filblks_t end; - xfs_agnumber_t agno; - xfs_agblock_t agbno; - xfs_extlen_t aglen; - xfs_agblock_t rbno; - xfs_extlen_t rlen; - struct xfs_bmbt_irec map; - int nmaps; - int error = 0; - - ASSERT(xfs_is_reflink_inode(ip)); + struct xfs_bmbt_irec got; + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp; + xfs_agnumber_t agno; + xfs_agblock_t agbno; + xfs_extlen_t aglen; + xfs_agblock_t rbno; + xfs_extlen_t rlen; + xfs_extnum_t idx; + bool found; + int error; - fbno = 0; - end = XFS_B_TO_FSB(mp, i_size_read(VFS_I(ip))); - while (end - fbno > 0) { - nmaps = 1; - /* - * Look for extents in the file. Skip holes, delalloc, or - * unwritten extents; they can't be reflinked. - */ - error = xfs_bmapi_read(ip, fbno, end - fbno, &map, &nmaps, 0); + ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + if (!(ifp->if_flags & XFS_IFEXTENTS)) { + error = xfs_iread_extents(tp, ip, XFS_DATA_FORK); if (error) return error; - if (nmaps == 0) - break; - if (!xfs_bmap_is_real_extent(&map)) - goto next; + } - agno = XFS_FSB_TO_AGNO(mp, map.br_startblock); - agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock); - aglen = map.br_blockcount; + *has_shared = false; + found = xfs_iext_lookup_extent(ip, ifp, 0, &idx, &got); + while (found) { + if (isnullstartblock(got.br_startblock) || + got.br_state != XFS_EXT_NORM) + goto next; + agno = XFS_FSB_TO_AGNO(mp, got.br_startblock); + agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock); + aglen = got.br_blockcount; - error = xfs_reflink_find_shared(mp, agno, agbno, aglen, + error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen, &rbno, &rlen, false); if (error) return error; /* Is there still a shared block here? */ - if (rbno != NULLAGBLOCK) + if (rbno != NULLAGBLOCK) { + *has_shared = true; return 0; + } next: - fbno = map.br_startoff + map.br_blockcount; + found = xfs_iext_get_extent(ifp, ++idx, &got); } + return 0; +} + +/* Clear the inode reflink flag if there are no shared extents. */ +int +xfs_reflink_clear_inode_flag( + struct xfs_inode *ip, + struct xfs_trans **tpp) +{ + bool needs_flag; + int error = 0; + + ASSERT(xfs_is_reflink_inode(ip)); + + error = xfs_reflink_inode_has_shared_extents(*tpp, ip, &needs_flag); + if (error || needs_flag) + return error; + /* * We didn't find any shared blocks so turn off the reflink flag. * First, get rid of any leftover CoW mappings. diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index d29a7967f029..701487bab468 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -20,9 +20,9 @@ #ifndef __XFS_REFLINK_H #define __XFS_REFLINK_H 1 -extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno, - xfs_extlen_t *flen, bool find_maximal); +extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen, + xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal); extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed); @@ -47,6 +47,8 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, extern int xfs_reflink_recover_cow(struct xfs_mount *mp); extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe); +extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp, + struct xfs_inode *ip, bool *has_shared); extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, struct xfs_trans **tpp); extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset, diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index c57aa7f18087..488719d43ca8 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -810,7 +810,7 @@ xfs_growfs_rt_alloc( /* * Free any blocks freed up in the transaction, then commit. */ - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; error = xfs_trans_commit(tp); @@ -1256,13 +1256,13 @@ xfs_rtpick_extent( { xfs_rtblock_t b; /* result block */ int log2; /* log of sequence number */ - __uint64_t resid; /* residual after log removed */ - __uint64_t seq; /* sequence number of file creation */ - __uint64_t *seqp; /* pointer to seqno in inode */ + uint64_t resid; /* residual after log removed */ + uint64_t seq; /* sequence number of file creation */ + uint64_t *seqp; /* pointer to seqno in inode */ ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL)); - seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime; + seqp = (uint64_t *)&VFS_I(mp->m_rbmip)->i_atime; if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) { mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM; *seqp = 0; diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h index f13133e6f19f..79defa722bf1 100644 --- a/fs/xfs/xfs_rtalloc.h +++ b/fs/xfs/xfs_rtalloc.h @@ -107,6 +107,8 @@ xfs_growfs_rt( /* * From xfs_rtbitmap.c */ +int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_rtblock_t block, int issum, struct xfs_buf **bpp); int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp, xfs_rtblock_t start, xfs_extlen_t len, int val, xfs_rtblock_t *new, int *stat); @@ -143,6 +145,7 @@ int xfs_rtalloc_query_all(struct xfs_trans *tp, # define xfs_growfs_rt(mp,in) (ENOSYS) # define xfs_rtalloc_query_range(t,l,h,f,p) (ENOSYS) # define xfs_rtalloc_query_all(t,f,p) (ENOSYS) +# define xfs_rtbuf_get(m,t,b,i,p) (ENOSYS) static inline int /* error */ xfs_rtmount_init( xfs_mount_t *mp) /* file system mount structure */ diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index f11282c96887..056e12b421eb 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -33,9 +33,9 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { int i, j; int len = 0; - __uint64_t xs_xstrat_bytes = 0; - __uint64_t xs_write_bytes = 0; - __uint64_t xs_read_bytes = 0; + uint64_t xs_xstrat_bytes = 0; + uint64_t xs_write_bytes = 0; + uint64_t xs_read_bytes = 0; static const struct xstats_entry { char *desc; @@ -100,7 +100,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) void xfs_stats_clearall(struct xfsstats __percpu *stats) { int c; - __uint32_t vn_active; + uint32_t vn_active; xfs_notice(NULL, "Clearing xfsstats"); for_each_possible_cpu(c) { diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index 375840f5a99a..f64d0ae345c4 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -54,125 +54,125 @@ enum { */ struct __xfsstats { # define XFSSTAT_END_EXTENT_ALLOC 4 - __uint32_t xs_allocx; - __uint32_t xs_allocb; - __uint32_t xs_freex; - __uint32_t xs_freeb; + uint32_t xs_allocx; + uint32_t xs_allocb; + uint32_t xs_freex; + uint32_t xs_freeb; # define XFSSTAT_END_ALLOC_BTREE (XFSSTAT_END_EXTENT_ALLOC+4) - __uint32_t xs_abt_lookup; - __uint32_t xs_abt_compare; - __uint32_t xs_abt_insrec; - __uint32_t xs_abt_delrec; + uint32_t xs_abt_lookup; + uint32_t xs_abt_compare; + uint32_t xs_abt_insrec; + uint32_t xs_abt_delrec; # define XFSSTAT_END_BLOCK_MAPPING (XFSSTAT_END_ALLOC_BTREE+7) - __uint32_t xs_blk_mapr; - __uint32_t xs_blk_mapw; - __uint32_t xs_blk_unmap; - __uint32_t xs_add_exlist; - __uint32_t xs_del_exlist; - __uint32_t xs_look_exlist; - __uint32_t xs_cmp_exlist; + uint32_t xs_blk_mapr; + uint32_t xs_blk_mapw; + uint32_t xs_blk_unmap; + uint32_t xs_add_exlist; + uint32_t xs_del_exlist; + uint32_t xs_look_exlist; + uint32_t xs_cmp_exlist; # define XFSSTAT_END_BLOCK_MAP_BTREE (XFSSTAT_END_BLOCK_MAPPING+4) - __uint32_t xs_bmbt_lookup; - __uint32_t xs_bmbt_compare; - __uint32_t xs_bmbt_insrec; - __uint32_t xs_bmbt_delrec; + uint32_t xs_bmbt_lookup; + uint32_t xs_bmbt_compare; + uint32_t xs_bmbt_insrec; + uint32_t xs_bmbt_delrec; # define XFSSTAT_END_DIRECTORY_OPS (XFSSTAT_END_BLOCK_MAP_BTREE+4) - __uint32_t xs_dir_lookup; - __uint32_t xs_dir_create; - __uint32_t xs_dir_remove; - __uint32_t xs_dir_getdents; + uint32_t xs_dir_lookup; + uint32_t xs_dir_create; + uint32_t xs_dir_remove; + uint32_t xs_dir_getdents; # define XFSSTAT_END_TRANSACTIONS (XFSSTAT_END_DIRECTORY_OPS+3) - __uint32_t xs_trans_sync; - __uint32_t xs_trans_async; - __uint32_t xs_trans_empty; + uint32_t xs_trans_sync; + uint32_t xs_trans_async; + uint32_t xs_trans_empty; # define XFSSTAT_END_INODE_OPS (XFSSTAT_END_TRANSACTIONS+7) - __uint32_t xs_ig_attempts; - __uint32_t xs_ig_found; - __uint32_t xs_ig_frecycle; - __uint32_t xs_ig_missed; - __uint32_t xs_ig_dup; - __uint32_t xs_ig_reclaims; - __uint32_t xs_ig_attrchg; + uint32_t xs_ig_attempts; + uint32_t xs_ig_found; + uint32_t xs_ig_frecycle; + uint32_t xs_ig_missed; + uint32_t xs_ig_dup; + uint32_t xs_ig_reclaims; + uint32_t xs_ig_attrchg; # define XFSSTAT_END_LOG_OPS (XFSSTAT_END_INODE_OPS+5) - __uint32_t xs_log_writes; - __uint32_t xs_log_blocks; - __uint32_t xs_log_noiclogs; - __uint32_t xs_log_force; - __uint32_t xs_log_force_sleep; + uint32_t xs_log_writes; + uint32_t xs_log_blocks; + uint32_t xs_log_noiclogs; + uint32_t xs_log_force; + uint32_t xs_log_force_sleep; # define XFSSTAT_END_TAIL_PUSHING (XFSSTAT_END_LOG_OPS+10) - __uint32_t xs_try_logspace; - __uint32_t xs_sleep_logspace; - __uint32_t xs_push_ail; - __uint32_t xs_push_ail_success; - __uint32_t xs_push_ail_pushbuf; - __uint32_t xs_push_ail_pinned; - __uint32_t xs_push_ail_locked; - __uint32_t xs_push_ail_flushing; - __uint32_t xs_push_ail_restarts; - __uint32_t xs_push_ail_flush; + uint32_t xs_try_logspace; + uint32_t xs_sleep_logspace; + uint32_t xs_push_ail; + uint32_t xs_push_ail_success; + uint32_t xs_push_ail_pushbuf; + uint32_t xs_push_ail_pinned; + uint32_t xs_push_ail_locked; + uint32_t xs_push_ail_flushing; + uint32_t xs_push_ail_restarts; + uint32_t xs_push_ail_flush; # define XFSSTAT_END_WRITE_CONVERT (XFSSTAT_END_TAIL_PUSHING+2) - __uint32_t xs_xstrat_quick; - __uint32_t xs_xstrat_split; + uint32_t xs_xstrat_quick; + uint32_t xs_xstrat_split; # define XFSSTAT_END_READ_WRITE_OPS (XFSSTAT_END_WRITE_CONVERT+2) - __uint32_t xs_write_calls; - __uint32_t xs_read_calls; + uint32_t xs_write_calls; + uint32_t xs_read_calls; # define XFSSTAT_END_ATTRIBUTE_OPS (XFSSTAT_END_READ_WRITE_OPS+4) - __uint32_t xs_attr_get; - __uint32_t xs_attr_set; - __uint32_t xs_attr_remove; - __uint32_t xs_attr_list; + uint32_t xs_attr_get; + uint32_t xs_attr_set; + uint32_t xs_attr_remove; + uint32_t xs_attr_list; # define XFSSTAT_END_INODE_CLUSTER (XFSSTAT_END_ATTRIBUTE_OPS+3) - __uint32_t xs_iflush_count; - __uint32_t xs_icluster_flushcnt; - __uint32_t xs_icluster_flushinode; + uint32_t xs_iflush_count; + uint32_t xs_icluster_flushcnt; + uint32_t xs_icluster_flushinode; # define XFSSTAT_END_VNODE_OPS (XFSSTAT_END_INODE_CLUSTER+8) - __uint32_t vn_active; /* # vnodes not on free lists */ - __uint32_t vn_alloc; /* # times vn_alloc called */ - __uint32_t vn_get; /* # times vn_get called */ - __uint32_t vn_hold; /* # times vn_hold called */ - __uint32_t vn_rele; /* # times vn_rele called */ - __uint32_t vn_reclaim; /* # times vn_reclaim called */ - __uint32_t vn_remove; /* # times vn_remove called */ - __uint32_t vn_free; /* # times vn_free called */ + uint32_t vn_active; /* # vnodes not on free lists */ + uint32_t vn_alloc; /* # times vn_alloc called */ + uint32_t vn_get; /* # times vn_get called */ + uint32_t vn_hold; /* # times vn_hold called */ + uint32_t vn_rele; /* # times vn_rele called */ + uint32_t vn_reclaim; /* # times vn_reclaim called */ + uint32_t vn_remove; /* # times vn_remove called */ + uint32_t vn_free; /* # times vn_free called */ #define XFSSTAT_END_BUF (XFSSTAT_END_VNODE_OPS+9) - __uint32_t xb_get; - __uint32_t xb_create; - __uint32_t xb_get_locked; - __uint32_t xb_get_locked_waited; - __uint32_t xb_busy_locked; - __uint32_t xb_miss_locked; - __uint32_t xb_page_retries; - __uint32_t xb_page_found; - __uint32_t xb_get_read; + uint32_t xb_get; + uint32_t xb_create; + uint32_t xb_get_locked; + uint32_t xb_get_locked_waited; + uint32_t xb_busy_locked; + uint32_t xb_miss_locked; + uint32_t xb_page_retries; + uint32_t xb_page_found; + uint32_t xb_get_read; /* Version 2 btree counters */ #define XFSSTAT_END_ABTB_V2 (XFSSTAT_END_BUF + __XBTS_MAX) - __uint32_t xs_abtb_2[__XBTS_MAX]; + uint32_t xs_abtb_2[__XBTS_MAX]; #define XFSSTAT_END_ABTC_V2 (XFSSTAT_END_ABTB_V2 + __XBTS_MAX) - __uint32_t xs_abtc_2[__XBTS_MAX]; + uint32_t xs_abtc_2[__XBTS_MAX]; #define XFSSTAT_END_BMBT_V2 (XFSSTAT_END_ABTC_V2 + __XBTS_MAX) - __uint32_t xs_bmbt_2[__XBTS_MAX]; + uint32_t xs_bmbt_2[__XBTS_MAX]; #define XFSSTAT_END_IBT_V2 (XFSSTAT_END_BMBT_V2 + __XBTS_MAX) - __uint32_t xs_ibt_2[__XBTS_MAX]; + uint32_t xs_ibt_2[__XBTS_MAX]; #define XFSSTAT_END_FIBT_V2 (XFSSTAT_END_IBT_V2 + __XBTS_MAX) - __uint32_t xs_fibt_2[__XBTS_MAX]; + uint32_t xs_fibt_2[__XBTS_MAX]; #define XFSSTAT_END_RMAP_V2 (XFSSTAT_END_FIBT_V2 + __XBTS_MAX) - __uint32_t xs_rmap_2[__XBTS_MAX]; + uint32_t xs_rmap_2[__XBTS_MAX]; #define XFSSTAT_END_REFCOUNT (XFSSTAT_END_RMAP_V2 + __XBTS_MAX) - __uint32_t xs_refcbt_2[__XBTS_MAX]; + uint32_t xs_refcbt_2[__XBTS_MAX]; #define XFSSTAT_END_XQMSTAT (XFSSTAT_END_REFCOUNT + 6) - __uint32_t xs_qm_dqreclaims; - __uint32_t xs_qm_dqreclaim_misses; - __uint32_t xs_qm_dquot_dups; - __uint32_t xs_qm_dqcachemisses; - __uint32_t xs_qm_dqcachehits; - __uint32_t xs_qm_dqwants; + uint32_t xs_qm_dqreclaims; + uint32_t xs_qm_dqreclaim_misses; + uint32_t xs_qm_dquot_dups; + uint32_t xs_qm_dqcachemisses; + uint32_t xs_qm_dqcachehits; + uint32_t xs_qm_dqwants; #define XFSSTAT_END_QM (XFSSTAT_END_XQMSTAT+2) - __uint32_t xs_qm_dquot; - __uint32_t xs_qm_dquot_unused; + uint32_t xs_qm_dquot; + uint32_t xs_qm_dquot_unused; /* Extra precision counters */ - __uint64_t xs_xstrat_bytes; - __uint64_t xs_write_bytes; - __uint64_t xs_read_bytes; + uint64_t xs_xstrat_bytes; + uint64_t xs_write_bytes; + uint64_t xs_read_bytes; }; struct xfsstats { @@ -186,7 +186,7 @@ struct xfsstats { * simple wrapper for getting the array index of s struct member offset */ #define XFS_STATS_CALC_INDEX(member) \ - (offsetof(struct __xfsstats, member) / (int)sizeof(__uint32_t)) + (offsetof(struct __xfsstats, member) / (int)sizeof(uint32_t)) int xfs_stats_format(struct xfsstats __percpu *stats, char *buf); diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 455a575f101d..f663022353c0 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -196,7 +196,7 @@ xfs_parseargs( int dsunit = 0; int dswidth = 0; int iosize = 0; - __uint8_t iosizelog = 0; + uint8_t iosizelog = 0; /* * set up the mount name first so all the errors will refer to the @@ -210,7 +210,7 @@ xfs_parseargs( /* * Copy binary VFS mount flags we are interested in. */ - if (sb->s_flags & MS_RDONLY) + if (sb_rdonly(sb)) mp->m_flags |= XFS_MOUNT_RDONLY; if (sb->s_flags & MS_DIRSYNC) mp->m_flags |= XFS_MOUNT_DIRSYNC; @@ -556,7 +556,7 @@ xfs_showargs( return 0; } -static __uint64_t +static uint64_t xfs_max_file_offset( unsigned int blockshift) { @@ -587,7 +587,7 @@ xfs_max_file_offset( # endif #endif - return (((__uint64_t)pagefactor) << bitshift) - 1; + return (((uint64_t)pagefactor) << bitshift) - 1; } /* @@ -622,7 +622,7 @@ xfs_set_inode_alloc( * the max inode percentage. Used only for inode32. */ if (mp->m_maxicount) { - __uint64_t icount; + uint64_t icount; icount = sbp->sb_dblocks * sbp->sb_imax_pct; do_div(icount, 100); @@ -714,17 +714,26 @@ STATIC void xfs_close_devices( struct xfs_mount *mp) { + struct dax_device *dax_ddev = mp->m_ddev_targp->bt_daxdev; + if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) { struct block_device *logdev = mp->m_logdev_targp->bt_bdev; + struct dax_device *dax_logdev = mp->m_logdev_targp->bt_daxdev; + xfs_free_buftarg(mp, mp->m_logdev_targp); xfs_blkdev_put(logdev); + fs_put_dax(dax_logdev); } if (mp->m_rtdev_targp) { struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev; + struct dax_device *dax_rtdev = mp->m_rtdev_targp->bt_daxdev; + xfs_free_buftarg(mp, mp->m_rtdev_targp); xfs_blkdev_put(rtdev); + fs_put_dax(dax_rtdev); } xfs_free_buftarg(mp, mp->m_ddev_targp); + fs_put_dax(dax_ddev); } /* @@ -742,6 +751,8 @@ xfs_open_devices( struct xfs_mount *mp) { struct block_device *ddev = mp->m_super->s_bdev; + struct dax_device *dax_ddev = fs_dax_get_by_bdev(ddev); + struct dax_device *dax_logdev = NULL, *dax_rtdev = NULL; struct block_device *logdev = NULL, *rtdev = NULL; int error; @@ -752,6 +763,7 @@ xfs_open_devices( error = xfs_blkdev_get(mp, mp->m_logname, &logdev); if (error) goto out; + dax_logdev = fs_dax_get_by_bdev(logdev); } if (mp->m_rtname) { @@ -765,24 +777,25 @@ xfs_open_devices( error = -EINVAL; goto out_close_rtdev; } + dax_rtdev = fs_dax_get_by_bdev(rtdev); } /* * Setup xfs_mount buffer target pointers */ error = -ENOMEM; - mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev); + mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, dax_ddev); if (!mp->m_ddev_targp) goto out_close_rtdev; if (rtdev) { - mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev); + mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, dax_rtdev); if (!mp->m_rtdev_targp) goto out_free_ddev_targ; } if (logdev && logdev != ddev) { - mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev); + mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, dax_logdev); if (!mp->m_logdev_targp) goto out_free_rtdev_targ; } else { @@ -798,10 +811,14 @@ xfs_open_devices( xfs_free_buftarg(mp, mp->m_ddev_targp); out_close_rtdev: xfs_blkdev_put(rtdev); + fs_put_dax(dax_rtdev); out_close_logdev: - if (logdev && logdev != ddev) + if (logdev && logdev != ddev) { xfs_blkdev_put(logdev); + fs_put_dax(dax_logdev); + } out: + fs_put_dax(dax_ddev); return error; } @@ -1088,12 +1105,12 @@ xfs_fs_statfs( struct xfs_mount *mp = XFS_M(dentry->d_sb); xfs_sb_t *sbp = &mp->m_sb; struct xfs_inode *ip = XFS_I(d_inode(dentry)); - __uint64_t fakeinos, id; - __uint64_t icount; - __uint64_t ifree; - __uint64_t fdblocks; + uint64_t fakeinos, id; + uint64_t icount; + uint64_t ifree; + uint64_t fdblocks; xfs_extlen_t lsize; - __int64_t ffree; + int64_t ffree; statp->f_type = XFS_SB_MAGIC; statp->f_namelen = MAXNAMELEN - 1; @@ -1116,7 +1133,7 @@ xfs_fs_statfs( statp->f_bavail = statp->f_bfree; fakeinos = statp->f_bfree << sbp->sb_inopblog; - statp->f_files = MIN(icount + fakeinos, (__uint64_t)XFS_MAXINUMBER); + statp->f_files = MIN(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); if (mp->m_maxicount) statp->f_files = min_t(typeof(statp->f_files), statp->f_files, @@ -1129,7 +1146,7 @@ xfs_fs_statfs( /* make sure statp->f_ffree does not underflow */ ffree = statp->f_files - (icount - ifree); - statp->f_ffree = max_t(__int64_t, ffree, 0); + statp->f_ffree = max_t(int64_t, ffree, 0); if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && @@ -1142,7 +1159,7 @@ xfs_fs_statfs( STATIC void xfs_save_resvblks(struct xfs_mount *mp) { - __uint64_t resblks = 0; + uint64_t resblks = 0; mp->m_resblks_save = mp->m_resblks; xfs_reserve_blocks(mp, &resblks, NULL); @@ -1151,7 +1168,7 @@ xfs_save_resvblks(struct xfs_mount *mp) STATIC void xfs_restore_resvblks(struct xfs_mount *mp) { - __uint64_t resblks; + uint64_t resblks; if (mp->m_resblks_save) { resblks = mp->m_resblks_save; @@ -1220,7 +1237,7 @@ xfs_test_remount_options( tmp_mp->m_super = sb; error = xfs_parseargs(tmp_mp, options); xfs_free_fsname(tmp_mp); - kfree(tmp_mp); + kmem_free(tmp_mp); return error; } @@ -1620,7 +1637,7 @@ xfs_fs_fill_super( /* version 5 superblocks support inode version counters. */ if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5) - sb->s_flags |= MS_I_VERSION; + sb->s_flags |= SB_I_VERSION; if (mp->m_flags & XFS_MOUNT_DAX) { xfs_warn(mp, @@ -1637,6 +1654,16 @@ xfs_fs_fill_super( "DAX and reflink have not been tested together!"); } + if (mp->m_flags & XFS_MOUNT_DISCARD) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + + if (!blk_queue_discard(q)) { + xfs_warn(mp, "mounting with \"discard\" option, but " + "the device does not support discard"); + mp->m_flags &= ~XFS_MOUNT_DISCARD; + } + } + if (xfs_sb_version_hasrmapbt(&mp->m_sb)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp, @@ -1766,7 +1793,8 @@ STATIC int __init xfs_init_zones(void) { xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE, - offsetof(struct xfs_ioend, io_inline_bio)); + offsetof(struct xfs_ioend, io_inline_bio), + BIOSET_NEED_BVECS); if (!xfs_ioend_bioset) goto out; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index f2cb45ed1d54..68d3ca2c4968 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -43,8 +43,8 @@ #include "xfs_log.h" /* ----- Kernel only functions below ----- */ -STATIC int -xfs_readlink_bmap( +int +xfs_readlink_bmap_ilocked( struct xfs_inode *ip, char *link) { @@ -61,6 +61,8 @@ xfs_readlink_bmap( int fsblocks = 0; int offset; + ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)); + fsblocks = xfs_symlink_blocks(mp, pathlen); error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0); if (error) @@ -143,7 +145,7 @@ xfs_readlink( if (!pathlen) goto out; - if (pathlen < 0 || pathlen > MAXPATHLEN) { + if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) { xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)", __func__, (unsigned long long) ip->i_ino, (long long) pathlen); @@ -153,7 +155,7 @@ xfs_readlink( } - error = xfs_readlink_bmap(ip, link); + error = xfs_readlink_bmap_ilocked(ip, link); out: xfs_iunlock(ip, XFS_ILOCK_SHARED); @@ -202,7 +204,7 @@ xfs_symlink( * Check component lengths of the target path name. */ pathlen = strlen(target_path); - if (pathlen >= MAXPATHLEN) /* total string too long */ + if (pathlen >= XFS_SYMLINK_MAXLEN) /* total string too long */ return -ENAMETOOLONG; udqp = gdqp = NULL; @@ -376,7 +378,7 @@ xfs_symlink( xfs_trans_set_sync(tp); } - error = xfs_defer_finish(&tp, &dfops, NULL); + error = xfs_defer_finish(&tp, &dfops); if (error) goto out_bmap_cancel; @@ -495,7 +497,8 @@ xfs_inactive_symlink_rmt( /* * Commit the first transaction. This logs the EFI and the inode. */ - error = xfs_defer_finish(&tp, &dfops, ip); + xfs_defer_ijoin(&dfops, ip); + error = xfs_defer_finish(&tp, &dfops); if (error) goto error_bmap_cancel; /* @@ -559,7 +562,7 @@ xfs_inactive_symlink( return 0; } - if (pathlen < 0 || pathlen > MAXPATHLEN) { + if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) { xfs_alert(mp, "%s: inode (0x%llx) bad symlink length (%d)", __func__, (unsigned long long)ip->i_ino, pathlen); xfs_iunlock(ip, XFS_ILOCK_EXCL); diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h index e75245d09116..aeaee8923617 100644 --- a/fs/xfs/xfs_symlink.h +++ b/fs/xfs/xfs_symlink.h @@ -21,6 +21,7 @@ int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name, const char *target_path, umode_t mode, struct xfs_inode **ipp); +int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link); int xfs_readlink(struct xfs_inode *ip, char *link); int xfs_inactive_symlink(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h index 984a3499cfe3..82afee005140 100644 --- a/fs/xfs/xfs_sysctl.h +++ b/fs/xfs/xfs_sysctl.h @@ -95,6 +95,7 @@ extern xfs_param_t xfs_params; struct xfs_globals { int log_recovery_delay; /* log recovery delay (secs) */ + bool bug_on_assert; /* BUG() the kernel on assert failure */ }; extern struct xfs_globals xfs_globals; diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 80ac15fb9638..8b2ccc234f36 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -90,15 +90,25 @@ to_mp(struct kobject *kobject) return container_of(kobj, struct xfs_mount, m_kobj); } +static struct attribute *xfs_mp_attrs[] = { + NULL, +}; + +struct kobj_type xfs_mp_ktype = { + .release = xfs_sysfs_release, + .sysfs_ops = &xfs_sysfs_ops, + .default_attrs = xfs_mp_attrs, +}; + #ifdef DEBUG +/* debug */ STATIC ssize_t -drop_writes_store( +bug_on_assert_store( struct kobject *kobject, const char *buf, size_t count) { - struct xfs_mount *mp = to_mp(kobject); int ret; int val; @@ -107,9 +117,9 @@ drop_writes_store( return ret; if (val == 1) - mp->m_drop_writes = true; + xfs_globals.bug_on_assert = true; else if (val == 0) - mp->m_drop_writes = false; + xfs_globals.bug_on_assert = false; else return -EINVAL; @@ -117,33 +127,13 @@ drop_writes_store( } STATIC ssize_t -drop_writes_show( +bug_on_assert_show( struct kobject *kobject, char *buf) { - struct xfs_mount *mp = to_mp(kobject); - - return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_drop_writes ? 1 : 0); + return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bug_on_assert ? 1 : 0); } -XFS_SYSFS_ATTR_RW(drop_writes); - -#endif /* DEBUG */ - -static struct attribute *xfs_mp_attrs[] = { -#ifdef DEBUG - ATTR_LIST(drop_writes), -#endif - NULL, -}; - -struct kobj_type xfs_mp_ktype = { - .release = xfs_sysfs_release, - .sysfs_ops = &xfs_sysfs_ops, - .default_attrs = xfs_mp_attrs, -}; - -#ifdef DEBUG -/* debug */ +XFS_SYSFS_ATTR_RW(bug_on_assert); STATIC ssize_t log_recovery_delay_store( @@ -176,6 +166,7 @@ log_recovery_delay_show( XFS_SYSFS_ATTR_RW(log_recovery_delay); static struct attribute *xfs_dbg_attrs[] = { + ATTR_LIST(bug_on_assert), ATTR_LIST(log_recovery_delay), NULL, }; @@ -314,47 +305,11 @@ write_grant_head_show( } XFS_SYSFS_ATTR_RO(write_grant_head); -#ifdef DEBUG -STATIC ssize_t -log_badcrc_factor_store( - struct kobject *kobject, - const char *buf, - size_t count) -{ - struct xlog *log = to_xlog(kobject); - int ret; - uint32_t val; - - ret = kstrtouint(buf, 0, &val); - if (ret) - return ret; - - log->l_badcrc_factor = val; - - return count; -} - -STATIC ssize_t -log_badcrc_factor_show( - struct kobject *kobject, - char *buf) -{ - struct xlog *log = to_xlog(kobject); - - return snprintf(buf, PAGE_SIZE, "%d\n", log->l_badcrc_factor); -} - -XFS_SYSFS_ATTR_RW(log_badcrc_factor); -#endif /* DEBUG */ - static struct attribute *xfs_log_attrs[] = { ATTR_LIST(log_head_lsn), ATTR_LIST(log_tail_lsn), ATTR_LIST(reserve_grant_head), ATTR_LIST(write_grant_head), -#ifdef DEBUG - ATTR_LIST(log_badcrc_factor), -#endif NULL, }; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 7c5a16528d8b..bb5514688d47 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -251,7 +251,7 @@ TRACE_EVENT(xfs_iext_insert, __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), (long)__entry->idx, __entry->startoff, - (__int64_t)__entry->startblock, + (int64_t)__entry->startblock, __entry->blockcount, __entry->state, (char *)__entry->caller_ip) @@ -295,7 +295,7 @@ DECLARE_EVENT_CLASS(xfs_bmap_class, __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), (long)__entry->idx, __entry->startoff, - (__int64_t)__entry->startblock, + (int64_t)__entry->startblock, __entry->blockcount, __entry->state, (char *)__entry->caller_ip) @@ -367,6 +367,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); DEFINE_BUF_EVENT(xfs_buf_delwri_queued); DEFINE_BUF_EVENT(xfs_buf_delwri_split); +DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf); DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_item_iodone_async); @@ -516,7 +517,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); @@ -688,11 +688,34 @@ DEFINE_INODE_EVENT(xfs_inode_set_cowblocks_tag); DEFINE_INODE_EVENT(xfs_inode_clear_cowblocks_tag); DEFINE_INODE_EVENT(xfs_inode_free_cowblocks_invalid); -DEFINE_INODE_EVENT(xfs_filemap_fault); -DEFINE_INODE_EVENT(xfs_filemap_huge_fault); -DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite); DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite); +TRACE_EVENT(xfs_filemap_fault, + TP_PROTO(struct xfs_inode *ip, enum page_entry_size pe_size, + bool write_fault), + TP_ARGS(ip, pe_size, write_fault), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_ino_t, ino) + __field(enum page_entry_size, pe_size) + __field(bool, write_fault) + ), + TP_fast_assign( + __entry->dev = VFS_I(ip)->i_sb->s_dev; + __entry->ino = ip->i_ino; + __entry->pe_size = pe_size; + __entry->write_fault = write_fault; + ), + TP_printk("dev %d:%d ino 0x%llx %s write_fault %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->ino, + __print_symbolic(__entry->pe_size, + { PE_SIZE_PTE, "PTE" }, + { PE_SIZE_PMD, "PMD" }, + { PE_SIZE_PUD, "PUD" }), + __entry->write_fault) +) + DECLARE_EVENT_CLASS(xfs_iref_class, TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), TP_ARGS(ip, caller_ip), @@ -1280,7 +1303,7 @@ DECLARE_EVENT_CLASS(xfs_imap_class, __entry->count, __print_symbolic(__entry->type, XFS_IO_TYPES), __entry->startoff, - (__int64_t)__entry->startblock, + (int64_t)__entry->startblock, __entry->blockcount) ) @@ -1490,25 +1513,6 @@ TRACE_EVENT(xfs_extent_busy_trim, __entry->tlen) ); -TRACE_EVENT(xfs_trans_commit_lsn, - TP_PROTO(struct xfs_trans *trans), - TP_ARGS(trans), - TP_STRUCT__entry( - __field(dev_t, dev) - __field(struct xfs_trans *, tp) - __field(xfs_lsn_t, lsn) - ), - TP_fast_assign( - __entry->dev = trans->t_mountp->m_super->s_dev; - __entry->tp = trans; - __entry->lsn = trans->t_commit_lsn; - ), - TP_printk("dev %d:%d trans 0x%p commit_lsn 0x%llx", - MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->tp, - __entry->lsn) -); - TRACE_EVENT(xfs_agf, TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, unsigned long caller_ip), @@ -1981,6 +1985,24 @@ DEFINE_EVENT(xfs_swap_extent_class, name, \ DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); +TRACE_EVENT(xfs_log_recover, + TP_PROTO(struct xlog *log, xfs_daddr_t headblk, xfs_daddr_t tailblk), + TP_ARGS(log, headblk, tailblk), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_daddr_t, headblk) + __field(xfs_daddr_t, tailblk) + ), + TP_fast_assign( + __entry->dev = log->l_mp->m_super->s_dev; + __entry->headblk = headblk; + __entry->tailblk = tailblk; + ), + TP_printk("dev %d:%d headblk 0x%llx tailblk 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->headblk, + __entry->tailblk) +) + TRACE_EVENT(xfs_log_recover_record, TP_PROTO(struct xlog *log, struct xlog_rec_header *rhead, int pass), TP_ARGS(log, rhead, pass), @@ -2057,7 +2079,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, TP_ARGS(log, buf_f), TP_STRUCT__entry( __field(dev_t, dev) - __field(__int64_t, blkno) + __field(int64_t, blkno) __field(unsigned short, len) __field(unsigned short, flags) __field(unsigned short, size) @@ -2106,7 +2128,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, __field(int, fields) __field(unsigned short, asize) __field(unsigned short, dsize) - __field(__int64_t, blkno) + __field(int64_t, blkno) __field(int, len) __field(int, boffset) ), @@ -3256,8 +3278,8 @@ DECLARE_EVENT_CLASS(xfs_fsmap_class, __field(xfs_agnumber_t, agno) __field(xfs_fsblock_t, bno) __field(xfs_filblks_t, len) - __field(__uint64_t, owner) - __field(__uint64_t, offset) + __field(uint64_t, owner) + __field(uint64_t, offset) __field(unsigned int, flags) ), TP_fast_assign( @@ -3297,9 +3319,9 @@ DECLARE_EVENT_CLASS(xfs_getfsmap_class, __field(dev_t, keydev) __field(xfs_daddr_t, block) __field(xfs_daddr_t, len) - __field(__uint64_t, owner) - __field(__uint64_t, offset) - __field(__uint64_t, flags) + __field(uint64_t, owner) + __field(uint64_t, offset) + __field(uint64_t, flags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 2011620008de..a87f657f59c9 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -1035,25 +1035,18 @@ xfs_trans_cancel( */ int xfs_trans_roll( - struct xfs_trans **tpp, - struct xfs_inode *dp) + struct xfs_trans **tpp) { - struct xfs_trans *trans; + struct xfs_trans *trans = *tpp; struct xfs_trans_res tres; int error; /* - * Ensure that the inode is always logged. - */ - trans = *tpp; - if (dp) - xfs_trans_log_inode(trans, dp, XFS_ILOG_CORE); - - /* * Copy the critical parameters from one trans to the next. */ tres.tr_logres = trans->t_log_res; tres.tr_logcount = trans->t_log_count; + *tpp = xfs_trans_dup(trans); /* @@ -1067,10 +1060,8 @@ xfs_trans_roll( if (error) return error; - trans = *tpp; - /* - * Reserve space in the log for th next transaction. + * Reserve space in the log for the next transaction. * This also pushes items in the "AIL", the list of logged items, * out to disk if they are taking up space at the tail of the log * that we want to use. This requires that either nothing be locked @@ -1078,14 +1069,5 @@ xfs_trans_roll( * the prior and the next transactions. */ tres.tr_logflags = XFS_TRANS_PERM_LOG_RES; - error = xfs_trans_reserve(trans, &tres, 0, 0); - /* - * Ensure that the inode is in the new transaction and locked. - */ - if (error) - return error; - - if (dp) - xfs_trans_ijoin(trans, dp, 0); - return 0; + return xfs_trans_reserve(*tpp, &tres, 0, 0); } diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index a07acbf0bd8a..815b53d20e26 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -49,6 +49,7 @@ typedef struct xfs_log_item { struct xfs_ail *li_ailp; /* ptr to AIL */ uint li_type; /* item type */ uint li_flags; /* misc flags */ + struct xfs_buf *li_buf; /* real buffer pointer */ struct xfs_log_item *li_bio_list; /* buffer item list */ void (*li_cb)(struct xfs_buf *, struct xfs_log_item *); @@ -64,11 +65,13 @@ typedef struct xfs_log_item { } xfs_log_item_t; #define XFS_LI_IN_AIL 0x1 -#define XFS_LI_ABORTED 0x2 +#define XFS_LI_ABORTED 0x2 +#define XFS_LI_FAILED 0x4 #define XFS_LI_FLAGS \ { XFS_LI_IN_AIL, "IN_AIL" }, \ - { XFS_LI_ABORTED, "ABORTED" } + { XFS_LI_ABORTED, "ABORTED" }, \ + { XFS_LI_FAILED, "FAILED" } struct xfs_item_ops { void (*iop_size)(xfs_log_item_t *, int *, int *); @@ -79,6 +82,7 @@ struct xfs_item_ops { void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); + void (*iop_error)(xfs_log_item_t *, xfs_buf_t *); }; void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, @@ -105,10 +109,6 @@ typedef struct xfs_trans { unsigned int t_rtx_res; /* # of rt extents resvd */ unsigned int t_rtx_res_used; /* # of resvd rt extents used */ struct xlog_ticket *t_ticket; /* log mgr ticket */ - xfs_lsn_t t_lsn; /* log seq num of start of - * transaction. */ - xfs_lsn_t t_commit_lsn; /* log seq num of end of - * transaction. */ struct xfs_mount *t_mountp; /* ptr to fs mount struct */ struct xfs_dquot_acct *t_dqinfo; /* acctg info for dquots */ unsigned int t_flags; /* misc flags */ @@ -212,12 +212,14 @@ void xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *); void xfs_trans_binval(xfs_trans_t *, struct xfs_buf *); void xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *); -void xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); +bool xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint); void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int); void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint); -void xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint); +void xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint, + uint); +void xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *); void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint); void xfs_extent_free_init_defer_op(void); @@ -228,7 +230,8 @@ int xfs_trans_free_extent(struct xfs_trans *, struct xfs_efd_log_item *, xfs_fsblock_t, xfs_extlen_t, struct xfs_owner_info *); int xfs_trans_commit(struct xfs_trans *); -int xfs_trans_roll(struct xfs_trans **, struct xfs_inode *); +int xfs_trans_roll(struct xfs_trans **); +int xfs_trans_roll_inode(struct xfs_trans **, struct xfs_inode *); void xfs_trans_cancel(xfs_trans_t *); int xfs_trans_ail_init(struct xfs_mount *); void xfs_trans_ail_destroy(struct xfs_mount *); @@ -249,7 +252,7 @@ struct xfs_rud_log_item *xfs_trans_get_rud(struct xfs_trans *tp, struct xfs_rui_log_item *ruip); int xfs_trans_log_finish_rmap_update(struct xfs_trans *tp, struct xfs_rud_log_item *rudp, enum xfs_rmap_intent_type type, - __uint64_t owner, int whichfork, xfs_fileoff_t startoff, + uint64_t owner, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, xfs_filblks_t blockcount, xfs_exntst_t state, struct xfs_btree_cur **pcur); @@ -275,6 +278,6 @@ int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp, struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops, enum xfs_bmap_intent_type type, struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, xfs_exntst_t state); + xfs_filblks_t *blockcount, xfs_exntst_t state); #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 9056c0f34a3c..354368a906e5 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -325,6 +325,21 @@ xfs_ail_delete( xfs_trans_ail_cursor_clear(ailp, lip); } +static inline uint +xfsaild_push_item( + struct xfs_ail *ailp, + struct xfs_log_item *lip) +{ + /* + * If log item pinning is enabled, skip the push and track the item as + * pinned. This can help induce head-behind-tail conditions. + */ + if (XFS_TEST_ERROR(false, ailp->xa_mount, XFS_ERRTAG_LOG_ITEM_PIN)) + return XFS_ITEM_PINNED; + + return lip->li_ops->iop_push(lip, &ailp->xa_buf_list); +} + static long xfsaild_push( struct xfs_ail *ailp) @@ -382,7 +397,7 @@ xfsaild_push( * rely on the AIL cursor implementation to be able to deal with * the dropped lock. */ - lock_result = lip->li_ops->iop_push(lip, &ailp->xa_buf_list); + lock_result = xfsaild_push_item(ailp, lip); switch (lock_result) { case XFS_ITEM_SUCCESS: XFS_STATS_INC(mp, xs_push_ail_success); @@ -687,12 +702,13 @@ xfs_trans_ail_update_bulk( bool xfs_ail_delete_one( struct xfs_ail *ailp, - struct xfs_log_item *lip) + struct xfs_log_item *lip) { struct xfs_log_item *mlip = xfs_ail_min(ailp); trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); xfs_ail_delete(ailp, lip); + xfs_clear_li_failed(lip); lip->li_flags &= ~XFS_LI_IN_AIL; lip->li_lsn = 0; diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c index 6408e7d7c08c..14543d93cd4b 100644 --- a/fs/xfs/xfs_trans_bmap.c +++ b/fs/xfs/xfs_trans_bmap.c @@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update( int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, + xfs_filblks_t *blockcount, xfs_exntst_t state) { int error; @@ -196,16 +196,23 @@ xfs_bmap_update_finish_item( void **state) { struct xfs_bmap_intent *bmap; + xfs_filblks_t count; int error; bmap = container_of(item, struct xfs_bmap_intent, bi_list); + count = bmap->bi_bmap.br_blockcount; error = xfs_trans_log_finish_bmap_update(tp, done_item, dop, bmap->bi_type, bmap->bi_owner, bmap->bi_whichfork, bmap->bi_bmap.br_startoff, bmap->bi_bmap.br_startblock, - bmap->bi_bmap.br_blockcount, + &count, bmap->bi_bmap.br_state); + if (!error && count > 0) { + ASSERT(bmap->bi_type == XFS_BMAP_UNMAP); + bmap->bi_bmap.br_blockcount = count; + return -EAGAIN; + } kmem_free(bmap); return error; } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 8ee29ca132dc..3ba7a96a8abd 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t *tp, xfs_buf_t *bp) { xfs_buf_log_item_t *bip; + int freed; /* * Default to a normal brelse() call if the tp is NULL. @@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t *tp, /* * Drop our reference to the buf log item. */ - atomic_dec(&bip->bli_refcount); + freed = atomic_dec_and_test(&bip->bli_refcount); /* - * If the buf item is not tracking data in the log, then - * we must free it before releasing the buffer back to the - * free pool. Before releasing the buffer to the free pool, - * clear the transaction pointer in b_fsprivate2 to dissolve - * its relation to this transaction. + * If the buf item is not tracking data in the log, then we must free it + * before releasing the buffer back to the free pool. + * + * If the fs has shutdown and we dropped the last reference, it may fall + * on us to release a (possibly dirty) bli if it never made it to the + * AIL (e.g., the aborted unpin already happened and didn't release it + * due to our reference). Since we're already shutdown and need xa_lock, + * just force remove from the AIL and release the bli here. */ - if (!xfs_buf_item_dirty(bip)) { + if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) { + xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR); + xfs_buf_item_relse(bp); + } else if (!(bip->bli_flags & XFS_BLI_DIRTY)) { /*** ASSERT(bp->b_pincount == 0); ***/ @@ -486,25 +493,17 @@ xfs_trans_bhold_release(xfs_trans_t *tp, } /* - * This is called to mark bytes first through last inclusive of the given - * buffer as needing to be logged when the transaction is committed. - * The buffer must already be associated with the given transaction. - * - * First and last are numbers relative to the beginning of this buffer, - * so the first byte in the buffer is numbered 0 regardless of the - * value of b_blkno. + * Mark a buffer dirty in the transaction. */ void -xfs_trans_log_buf(xfs_trans_t *tp, - xfs_buf_t *bp, - uint first, - uint last) +xfs_trans_dirty_buf( + struct xfs_trans *tp, + struct xfs_buf *bp) { - xfs_buf_log_item_t *bip = bp->b_fspriv; + struct xfs_buf_log_item *bip = bp->b_fspriv; ASSERT(bp->b_transp == tp); ASSERT(bip != NULL); - ASSERT(first <= last && last < BBTOB(bp->b_length)); ASSERT(bp->b_iodone == NULL || bp->b_iodone == xfs_buf_iodone_callbacks); @@ -524,8 +523,6 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_iodone = xfs_buf_iodone_callbacks; bip->bli_item.li_cb = xfs_buf_iodone; - trace_xfs_trans_log_buf(bip); - /* * If we invalidated the buffer within this transaction, then * cancel the invalidation now that we're dirtying the buffer @@ -538,17 +535,37 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_flags &= ~XBF_STALE; bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL; } + bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED; tp->t_flags |= XFS_TRANS_DIRTY; bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY; +} - /* - * If we have an ordered buffer we are not logging any dirty range but - * it still needs to be marked dirty and that it has been logged. - */ - bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED; - if (!(bip->bli_flags & XFS_BLI_ORDERED)) - xfs_buf_item_log(bip, first, last); +/* + * This is called to mark bytes first through last inclusive of the given + * buffer as needing to be logged when the transaction is committed. + * The buffer must already be associated with the given transaction. + * + * First and last are numbers relative to the beginning of this buffer, + * so the first byte in the buffer is numbered 0 regardless of the + * value of b_blkno. + */ +void +xfs_trans_log_buf( + struct xfs_trans *tp, + struct xfs_buf *bp, + uint first, + uint last) +{ + struct xfs_buf_log_item *bip = bp->b_fspriv; + + ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); + + xfs_trans_dirty_buf(tp, bp); + + trace_xfs_trans_log_buf(bip); + xfs_buf_item_log(bip, first, last); } @@ -701,14 +718,13 @@ xfs_trans_inode_alloc_buf( } /* - * Mark the buffer as ordered for this transaction. This means - * that the contents of the buffer are not recorded in the transaction - * but it is tracked in the AIL as though it was. This allows us - * to record logical changes in transactions rather than the physical - * changes we make to the buffer without changing writeback ordering - * constraints of metadata buffers. + * Mark the buffer as ordered for this transaction. This means that the contents + * of the buffer are not recorded in the transaction but it is tracked in the + * AIL as though it was. This allows us to record logical changes in + * transactions rather than the physical changes we make to the buffer without + * changing writeback ordering constraints of metadata buffers. */ -void +bool xfs_trans_ordered_buf( struct xfs_trans *tp, struct xfs_buf *bp) @@ -719,8 +735,18 @@ xfs_trans_ordered_buf( ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); + if (xfs_buf_item_dirty_format(bip)) + return false; + bip->bli_flags |= XFS_BLI_ORDERED; trace_xfs_buf_item_ordered(bip); + + /* + * We don't log a dirty range of an ordered buffer but it still needs + * to be marked dirty and that it has been logged. + */ + xfs_trans_dirty_buf(tp, bp); + return true; } /* diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index dab8daa676f9..daa7615497f9 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -134,3 +134,17 @@ xfs_trans_log_inode( flags |= ip->i_itemp->ili_last_fields; ip->i_itemp->ili_fields |= flags; } + +int +xfs_trans_roll_inode( + struct xfs_trans **tpp, + struct xfs_inode *ip) +{ + int error; + + xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE); + error = xfs_trans_roll(tpp); + if (!error) + xfs_trans_ijoin(*tpp, ip, 0); + return error; +} diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index d91706c56c63..b317a3644c00 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -164,4 +164,35 @@ xfs_trans_ail_copy_lsn( *dst = *src; } #endif + +static inline void +xfs_clear_li_failed( + struct xfs_log_item *lip) +{ + struct xfs_buf *bp = lip->li_buf; + + ASSERT(lip->li_flags & XFS_LI_IN_AIL); + lockdep_assert_held(&lip->li_ailp->xa_lock); + + if (lip->li_flags & XFS_LI_FAILED) { + lip->li_flags &= ~XFS_LI_FAILED; + lip->li_buf = NULL; + xfs_buf_rele(bp); + } +} + +static inline void +xfs_set_li_failed( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + lockdep_assert_held(&lip->li_ailp->xa_lock); + + if (!(lip->li_flags & XFS_LI_FAILED)) { + xfs_buf_hold(bp); + lip->li_flags |= XFS_LI_FAILED; + lip->li_buf = bp; + } +} + #endif /* __XFS_TRANS_PRIV_H__ */ diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c index 9ead064b5e90..9b577beb43d7 100644 --- a/fs/xfs/xfs_trans_rmap.c +++ b/fs/xfs/xfs_trans_rmap.c @@ -96,7 +96,7 @@ xfs_trans_log_finish_rmap_update( struct xfs_trans *tp, struct xfs_rud_log_item *rudp, enum xfs_rmap_intent_type type, - __uint64_t owner, + uint64_t owner, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, |