summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/compression.c18
-rw-r--r--fs/btrfs/ctree.h1
-rw-r--r--fs/btrfs/disk-io.c9
-rw-r--r--fs/btrfs/extent_io.c8
-rw-r--r--fs/btrfs/inode.c27
-rw-r--r--fs/btrfs/ioctl.c12
-rw-r--r--fs/btrfs/qgroup.c6
-rw-r--r--fs/btrfs/relocation.c2
-rw-r--r--fs/btrfs/send.c2
-rw-r--r--fs/btrfs/tree-log.c12
-rw-r--r--fs/btrfs/volumes.c2
-rw-r--r--fs/direct-io.c49
-rw-r--r--fs/gfs2/glock.c14
-rw-r--r--fs/iomap.c43
-rw-r--r--fs/isofs/inode.c2
-rw-r--r--fs/proc/array.c35
-rw-r--r--fs/quota/dquot.c2
-rw-r--r--fs/quota/quota_v2.c4
-rw-r--r--fs/read_write.c4
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c12
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c17
-rw-r--r--fs/xfs/xfs_aops.c3
-rw-r--r--fs/xfs/xfs_bmap_util.c14
-rw-r--r--fs/xfs/xfs_buf.c2
-rw-r--r--fs/xfs/xfs_error.c2
-rw-r--r--fs/xfs/xfs_file.c39
-rw-r--r--fs/xfs/xfs_inode.c8
-rw-r--r--fs/xfs/xfs_inode_item.c2
-rw-r--r--fs/xfs/xfs_ioctl.c3
-rw-r--r--fs/xfs/xfs_iomap.c7
-rw-r--r--fs/xfs/xfs_iomap.h2
-rw-r--r--fs/xfs/xfs_pnfs.c2
-rw-r--r--fs/xfs/xfs_super.c10
33 files changed, 242 insertions, 133 deletions
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b51d23f5cafa..280384bf34f1 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -107,7 +107,8 @@ 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_status)
cb->errors = 1;
@@ -118,6 +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);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5a8933da39a7..899ddaeeacec 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -709,7 +709,6 @@ 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
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 487bbe4fb3c6..dfdab849037b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3643,7 +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;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3e5bb0cdd3cd..12ab19a4b93e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3471,8 +3471,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
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);
@@ -3718,7 +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;
- unsigned 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);
@@ -4063,9 +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;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 128f3e58634f..d94e3f68b9b1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -135,6 +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);
}
@@ -8357,11 +8369,8 @@ static void btrfs_endio_direct_read(struct bio *bio)
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
blk_status_t err = bio->bi_status;
- if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
+ if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
err = btrfs_subio_endio_read(inode, io_bio, err);
- if (!err)
- bio->bi_status = 0;
- }
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
@@ -8369,7 +8378,7 @@ static void btrfs_endio_direct_read(struct bio *bio)
kfree(dip);
- dio_bio->bi_status = bio->bi_status;
+ dio_bio->bi_status = err;
dio_end_io(dio_bio);
if (io_bio->end_io)
@@ -8387,6 +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))) {
@@ -8398,6 +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,
@@ -8409,6 +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
*/
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d6715c2bcdc4..6c7a49faf4e0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2773,9 +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;
@@ -3032,7 +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)
@@ -4061,6 +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) {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5c8b61c86e61..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;
}
@@ -953,7 +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;
@@ -1307,6 +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,
@@ -2086,8 +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)) {
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3a49a3c2fca4..9841faef08ea 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2400,11 +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);
}
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 32b043ef8ac9..8fd195cfe81b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -2630,7 +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;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index ad7f4bab640b..c800d067fcbf 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4181,6 +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;
@@ -4190,10 +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
@@ -4208,6 +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);
@@ -4216,7 +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
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0e8f16c305df..b39737568c22 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6166,7 +6166,7 @@ blk_status_t 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);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 5fa2211e49ae..62cf812ed0e5 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -229,6 +229,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
{
loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
+ int err;
/*
* AIO submission can race with bio completion to get here while
@@ -258,8 +259,22 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, bool is_async)
if (ret == 0)
ret = transferred;
+ /*
+ * 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 (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->end_io) {
- int err;
// XXX: ki_pos??
err = dio->end_io(dio->iocb, offset, ret, dio->private);
@@ -304,6 +319,7 @@ 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);
@@ -315,7 +331,19 @@ 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);
@@ -1210,10 +1238,19 @@ 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
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 98e845b7841b..11066d8647d2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1945,13 +1945,9 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
{
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 {
@@ -1959,6 +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;
}
@@ -1970,6 +1967,7 @@ 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;
}
@@ -1980,6 +1978,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
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)
@@ -2042,12 +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;
}
@@ -2063,7 +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/iomap.c b/fs/iomap.c
index 269b24a01f32..be61cf742b5e 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -713,8 +713,24 @@ 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);
ssize_t 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...
+ */
+ if (!dio->error &&
+ (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+ ret = invalidate_inode_pages2_range(inode->i_mapping,
+ iocb->ki_pos >> PAGE_SHIFT,
+ (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
+ WARN_ON_ONCE(ret);
+ }
+
if (dio->end_io) {
ret = dio->end_io(iocb,
dio->error ? dio->error : dio->size,
@@ -993,6 +1009,13 @@ 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);
@@ -1015,13 +1038,6 @@ 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;
@@ -1042,19 +1058,6 @@ 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 db692f554158..447a24d77b89 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -514,9 +514,11 @@ static int isofs_show_options(struct seq_file *m, struct dentry *root)
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;
}
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 525157ca25cb..77a8eacbe032 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -119,30 +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)
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 8381db9db6d9..50b0556a124f 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1980,7 +1980,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
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;
}
}
diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c
index c0187cda2c1e..a73e5b34db41 100644
--- a/fs/quota/quota_v2.c
+++ b/fs/quota/quota_v2.c
@@ -328,12 +328,16 @@ static int v2_write_dquot(struct dquot *dquot)
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;
}
diff --git a/fs/read_write.c b/fs/read_write.c
index a2b9a47235c5..f0d4b16873e8 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -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;
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index b008ff3250eb..df3e600835e8 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -156,7 +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.
@@ -216,7 +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_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 459f4b4f08fe..044a363119be 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;
}
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 29172609f2a3..f18e5932aec4 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -343,7 +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);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index cd9a5400ba4f..bc6c6e10a969 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1459,7 +1459,19 @@ 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.
*/
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index da14658da310..2f97c12ca75e 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1258,8 +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;
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index bd786a9ac2c3..eaf86f55b7f2 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -347,7 +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_file.c b/fs/xfs/xfs_file.c
index ebdd0bd2b261..309e26c9dddb 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
@@ -377,8 +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) {
@@ -399,7 +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
@@ -436,7 +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);
@@ -447,6 +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
@@ -461,20 +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;
}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5599dda4727a..4ec5b7f45401 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1624,10 +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);
}
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 6d0f74ec31e8..a705f34b58fa 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -745,7 +745,7 @@ xfs_iflush_done(
*/
iip = INODE_ITEM(blip);
if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
- lip->li_flags & XFS_LI_FAILED)
+ (blip->li_flags & XFS_LI_FAILED))
need_ail++;
blip = next;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 5049e8ab6e30..aa75389be8cf 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1088,6 +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;
@@ -1100,7 +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;
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index a1909bc064e9..f179bdf1644d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -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;
@@ -899,7 +901,8 @@ 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;
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_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_super.c b/fs/xfs/xfs_super.c
index c996f4ae4a5f..584cf2d573ba 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1654,6 +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,
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2025-05-11 18:39:21 +0200