From 261507a02ccba9afda919852263b6bc1581ce1ef Mon Sep 17 00:00:00 2001
From: Li Zefan
Date: Fri, 17 Dec 2010 14:21:50 +0800
Subject: btrfs: Allow to add new compression algorithm

Make the code aware of compression type, instead of always assuming
zlib compression.

Also make the zlib workspace function as common code for all
compression types.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
---
 fs/btrfs/super.c | 47 ++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 36 insertions(+), 11 deletions(-)

(limited to 'fs/btrfs/super.c')

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 61bd79abb805..f348f2b93164 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -69,9 +69,9 @@ enum {
 	Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum,
 	Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd,
 	Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
-	Opt_compress_force, Opt_notreelog, Opt_ratio, Opt_flushoncommit,
-	Opt_discard, Opt_space_cache, Opt_clear_cache, Opt_err,
-	Opt_user_subvol_rm_allowed,
+	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
+	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
+	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -86,7 +86,9 @@ static match_table_t tokens = {
 	{Opt_alloc_start, "alloc_start=%s"},
 	{Opt_thread_pool, "thread_pool=%d"},
 	{Opt_compress, "compress"},
+	{Opt_compress_type, "compress=%s"},
 	{Opt_compress_force, "compress-force"},
+	{Opt_compress_force_type, "compress-force=%s"},
 	{Opt_ssd, "ssd"},
 	{Opt_ssd_spread, "ssd_spread"},
 	{Opt_nossd, "nossd"},
@@ -112,6 +114,8 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	char *p, *num, *orig;
 	int intarg;
 	int ret = 0;
+	char *compress_type;
+	bool compress_force = false;
 
 	if (!options)
 		return 0;
@@ -154,14 +158,29 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			btrfs_set_opt(info->mount_opt, NODATACOW);
 			btrfs_set_opt(info->mount_opt, NODATASUM);
 			break;
-		case Opt_compress:
-			printk(KERN_INFO "btrfs: use compression\n");
-			btrfs_set_opt(info->mount_opt, COMPRESS);
-			break;
 		case Opt_compress_force:
-			printk(KERN_INFO "btrfs: forcing compression\n");
-			btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
+		case Opt_compress_force_type:
+			compress_force = true;
+		case Opt_compress:
+		case Opt_compress_type:
+			if (token == Opt_compress ||
+			    token == Opt_compress_force ||
+			    strcmp(args[0].from, "zlib") == 0) {
+				compress_type = "zlib";
+				info->compress_type = BTRFS_COMPRESS_ZLIB;
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
+
 			btrfs_set_opt(info->mount_opt, COMPRESS);
+			if (compress_force) {
+				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
+				pr_info("btrfs: force %s compression\n",
+					compress_type);
+			} else
+				pr_info("btrfs: use %s compression\n",
+					compress_type);
 			break;
 		case Opt_ssd:
 			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
@@ -898,10 +917,14 @@ static int __init init_btrfs_fs(void)
 	if (err)
 		return err;
 
-	err = btrfs_init_cachep();
+	err = btrfs_init_compress();
 	if (err)
 		goto free_sysfs;
 
+	err = btrfs_init_cachep();
+	if (err)
+		goto free_compress;
+
 	err = extent_io_init();
 	if (err)
 		goto free_cachep;
@@ -929,6 +952,8 @@ free_extent_io:
 	extent_io_exit();
 free_cachep:
 	btrfs_destroy_cachep();
+free_compress:
+	btrfs_exit_compress();
 free_sysfs:
 	btrfs_exit_sysfs();
 	return err;
@@ -943,7 +968,7 @@ static void __exit exit_btrfs_fs(void)
 	unregister_filesystem(&btrfs_fs_type);
 	btrfs_exit_sysfs();
 	btrfs_cleanup_fs_uuids();
-	btrfs_zlib_exit();
+	btrfs_exit_compress();
 }
 
 module_init(init_btrfs_fs)
-- 
cgit v1.2.3-55-g7522


From a6fa6fae40ec336c7df6155255ae64ebef43a8bc Mon Sep 17 00:00:00 2001
From: Li Zefan
Date: Mon, 25 Oct 2010 15:12:26 +0800
Subject: btrfs: Add lzo compression support

Lzo is a much faster compression algorithm than gzib, so would allow
more users to enable transparent compression, and some users can
choose from compression ratio and speed for different applications

Usage:

 # mount -t btrfs -o compress[=<zlib,lzo>] dev /mnt
or
 # mount -t btrfs -o compress-force[=<zlib,lzo>] dev /mnt

"-o compress" without argument is still allowed for compatability.

Compatibility:

If we mount a filesystem with lzo compression, it will not be able be
mounted in old kernels. One reason is, otherwise btrfs will directly
dump compressed data, which sits in inline extent, to user.

Performance:

The test copied a linux source tarball (~400M) from an ext4 partition
to the btrfs partition, and then extracted it.

(time in second)
           lzo        zlib        nocompress
copy:      10.6       21.7        14.9
extract:   70.1       94.4        66.6

(data size in MB)
           lzo        zlib        nocompress
copy:      185.87     108.69      394.49
extract:   193.80     132.36      381.21

Changelog:

v1 -> v2:
- Select LZO_COMPRESS and LZO_DECOMPRESS in btrfs Kconfig.
- Add incompability flag.
- Fix error handling in compress code.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
---
 fs/btrfs/Kconfig       |   2 +
 fs/btrfs/Makefile      |   2 +-
 fs/btrfs/compression.c |   1 +
 fs/btrfs/compression.h |   1 +
 fs/btrfs/ctree.h       |   9 +-
 fs/btrfs/disk-io.c     |   8 +-
 fs/btrfs/lzo.c         | 509 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/super.c       |   3 +
 8 files changed, 527 insertions(+), 8 deletions(-)
 create mode 100644 fs/btrfs/lzo.c

(limited to 'fs/btrfs/super.c')

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index 7bb3c020e570..ecb9fd3be143 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -4,6 +4,8 @@ config BTRFS_FS
 	select LIBCRC32C
 	select ZLIB_INFLATE
 	select ZLIB_DEFLATE
+	select LZO_COMPRESS
+	select LZO_DECOMPRESS
 	help
 	  Btrfs is a new filesystem with extents, writable snapshotting,
 	  support for multiple devices and many more features.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index a35eb36b32fd..31610ea73aec 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -6,5 +6,5 @@ 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 acl.o free-space-cache.o zlib.o \
+	   export.o tree-log.o acl.o free-space-cache.o zlib.o lzo.o \
 	   compression.o delayed-ref.o relocation.o
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 6638c9877720..8faa2df9e719 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -691,6 +691,7 @@ static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES];
 
 struct btrfs_compress_op *btrfs_compress_op[] = {
 	&btrfs_zlib_compress,
+	&btrfs_lzo_compress,
 };
 
 int __init btrfs_init_compress(void)
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 9b5f2f365b79..f7ce217113fa 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -73,5 +73,6 @@ struct btrfs_compress_op {
 };
 
 extern struct btrfs_compress_op btrfs_zlib_compress;
+extern struct btrfs_compress_op btrfs_lzo_compress;
 
 #endif
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e06534438592..53b984623983 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -398,13 +398,15 @@ struct btrfs_super_block {
 #define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF	(1ULL << 0)
 #define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL	(1ULL << 1)
 #define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS	(1ULL << 2)
+#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO	(1ULL << 3)
 
 #define BTRFS_FEATURE_COMPAT_SUPP		0ULL
 #define BTRFS_FEATURE_COMPAT_RO_SUPP		0ULL
 #define BTRFS_FEATURE_INCOMPAT_SUPP			\
 	(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF |		\
 	 BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL |	\
-	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+	 BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS |		\
+	 BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO)
 
 /*
  * A leaf is full of items. offset and size tell us where to find
@@ -553,8 +555,9 @@ struct btrfs_timespec {
 enum btrfs_compression_type {
 	BTRFS_COMPRESS_NONE  = 0,
 	BTRFS_COMPRESS_ZLIB  = 1,
-	BTRFS_COMPRESS_TYPES = 1,
-	BTRFS_COMPRESS_LAST  = 2,
+	BTRFS_COMPRESS_LZO   = 2,
+	BTRFS_COMPRESS_TYPES = 2,
+	BTRFS_COMPRESS_LAST  = 3,
 };
 
 struct btrfs_inode_item {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a5d2249e6da5..f88eb2ce7919 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1744,10 +1744,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	}
 
 	features = btrfs_super_incompat_flags(disk_super);
-	if (!(features & BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF)) {
-		features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
-		btrfs_set_super_incompat_flags(disk_super, features);
-	}
+	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
+	if (tree_root->fs_info->compress_type & BTRFS_COMPRESS_LZO)
+		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
+	btrfs_set_super_incompat_flags(disk_super, features);
 
 	features = btrfs_super_compat_ro_flags(disk_super) &
 		~BTRFS_FEATURE_COMPAT_RO_SUPP;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
new file mode 100644
index 000000000000..523b144e2aec
--- /dev/null
+++ b/fs/btrfs/lzo.c
@@ -0,0 +1,509 @@
+/*
+ * Copyright (C) 2008 Oracle.  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.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.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 "compression.h"
+
+#define LZO_LEN	4
+
+struct workspace {
+	void *mem;
+	void *buf;	/* where compressed data goes */
+	void *cbuf;	/* where decompressed data goes */
+	struct list_head list;
+};
+
+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);
+	kfree(workspace);
+}
+
+static struct list_head *lzo_alloc_workspace(void)
+{
+	struct workspace *workspace;
+
+	workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
+	if (!workspace)
+		return ERR_PTR(-ENOMEM);
+
+	workspace->mem = vmalloc(LZO1X_MEM_COMPRESS);
+	workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE));
+	workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_CACHE_SIZE));
+	if (!workspace->mem || !workspace->buf || !workspace->cbuf)
+		goto fail;
+
+	INIT_LIST_HEAD(&workspace->list);
+
+	return &workspace->list;
+fail:
+	lzo_free_workspace(&workspace->list);
+	return ERR_PTR(-ENOMEM);
+}
+
+static inline void write_compress_length(char *buf, size_t len)
+{
+	__le32 dlen;
+
+	dlen = cpu_to_le32(len);
+	memcpy(buf, &dlen, LZO_LEN);
+}
+
+static inline size_t read_compress_length(char *buf)
+{
+	__le32 dlen;
+
+	memcpy(&dlen, buf, LZO_LEN);
+	return le32_to_cpu(dlen);
+}
+
+static int lzo_compress_pages(struct list_head *ws,
+			      struct address_space *mapping,
+			      u64 start, unsigned long len,
+			      struct page **pages,
+			      unsigned long nr_dest_pages,
+			      unsigned long *out_pages,
+			      unsigned long *total_in,
+			      unsigned long *total_out,
+			      unsigned long max_out)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	int ret = 0;
+	char *data_in;
+	char *cpage_out;
+	int nr_pages = 0;
+	struct page *in_page = NULL;
+	struct page *out_page = NULL;
+	unsigned long bytes_left;
+
+	size_t in_len;
+	size_t out_len;
+	char *buf;
+	unsigned long tot_in = 0;
+	unsigned long tot_out = 0;
+	unsigned long pg_bytes_left;
+	unsigned long out_offset;
+	unsigned long bytes;
+
+	*out_pages = 0;
+	*total_out = 0;
+	*total_in = 0;
+
+	in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+	data_in = kmap(in_page);
+
+	/*
+	 * store the size of all chunks of compressed data in
+	 * the first 4 bytes
+	 */
+	out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+	if (out_page == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	cpage_out = kmap(out_page);
+	out_offset = LZO_LEN;
+	tot_out = LZO_LEN;
+	pages[0] = out_page;
+	nr_pages = 1;
+	pg_bytes_left = PAGE_CACHE_SIZE - LZO_LEN;
+
+	/* compress at most one page of data each time */
+	in_len = min(len, PAGE_CACHE_SIZE);
+	while (tot_in < len) {
+		ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
+				       &out_len, workspace->mem);
+		if (ret != LZO_E_OK) {
+			printk(KERN_DEBUG "btrfs deflate in loop returned %d\n",
+			       ret);
+			ret = -1;
+			goto out;
+		}
+
+		/* store the size of this chunk of compressed data */
+		write_compress_length(cpage_out + out_offset, out_len);
+		tot_out += LZO_LEN;
+		out_offset += LZO_LEN;
+		pg_bytes_left -= LZO_LEN;
+
+		tot_in += in_len;
+		tot_out += out_len;
+
+		/* copy bytes from the working buffer into the pages */
+		buf = workspace->cbuf;
+		while (out_len) {
+			bytes = min_t(unsigned long, pg_bytes_left, out_len);
+
+			memcpy(cpage_out + out_offset, buf, bytes);
+
+			out_len -= bytes;
+			pg_bytes_left -= bytes;
+			buf += bytes;
+			out_offset += bytes;
+
+			/*
+			 * we need another page for writing out.
+			 *
+			 * Note if there's less than 4 bytes left, we just
+			 * skip to a new page.
+			 */
+			if ((out_len == 0 && pg_bytes_left < LZO_LEN) ||
+			    pg_bytes_left == 0) {
+				if (pg_bytes_left) {
+					memset(cpage_out + out_offset, 0,
+					       pg_bytes_left);
+					tot_out += pg_bytes_left;
+				}
+
+				/* we're done, don't allocate new page */
+				if (out_len == 0 && tot_in >= len)
+					break;
+
+				kunmap(out_page);
+				if (nr_pages == nr_dest_pages) {
+					out_page = NULL;
+					ret = -1;
+					goto out;
+				}
+
+				out_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
+				if (out_page == NULL) {
+					ret = -ENOMEM;
+					goto out;
+				}
+				cpage_out = kmap(out_page);
+				pages[nr_pages++] = out_page;
+
+				pg_bytes_left = PAGE_CACHE_SIZE;
+				out_offset = 0;
+			}
+		}
+
+		/* we're making it bigger, give up */
+		if (tot_in > 8192 && tot_in < tot_out)
+			goto out;
+
+		/* we're all done */
+		if (tot_in >= len)
+			break;
+
+		if (tot_out > max_out)
+			break;
+
+		bytes_left = len - tot_in;
+		kunmap(in_page);
+		page_cache_release(in_page);
+
+		start += PAGE_CACHE_SIZE;
+		in_page = find_get_page(mapping, start >> PAGE_CACHE_SHIFT);
+		data_in = kmap(in_page);
+		in_len = min(bytes_left, PAGE_CACHE_SIZE);
+	}
+
+	if (tot_out > tot_in)
+		goto out;
+
+	/* store the size of all chunks of compressed data */
+	cpage_out = kmap(pages[0]);
+	write_compress_length(cpage_out, tot_out);
+
+	kunmap(pages[0]);
+
+	ret = 0;
+	*total_out = tot_out;
+	*total_in = tot_in;
+out:
+	*out_pages = nr_pages;
+	if (out_page)
+		kunmap(out_page);
+
+	if (in_page) {
+		kunmap(in_page);
+		page_cache_release(in_page);
+	}
+
+	return ret;
+}
+
+static int lzo_decompress_biovec(struct list_head *ws,
+				 struct page **pages_in,
+				 u64 disk_start,
+				 struct bio_vec *bvec,
+				 int vcnt,
+				 size_t srclen)
+{
+	struct workspace *workspace = list_entry(ws, struct workspace, list);
+	int ret = 0;
+	char *data_in;
+	unsigned long page_bytes_left;
+	unsigned long page_in_index = 0;
+	unsigned long page_out_index = 0;
+	struct page *page_out;
+	unsigned long total_pages_in = (srclen + PAGE_CACHE_SIZE - 1) /
+					PAGE_CACHE_SIZE;
+	unsigned long buf_start;
+	unsigned long buf_offset = 0;
+	unsigned long bytes;
+	unsigned long working_bytes;
+	unsigned long pg_offset;
+	unsigned long start_byte;
+	unsigned long current_buf_start;
+	char *kaddr;
+
+	size_t in_len;
+	size_t out_len;
+	unsigned long in_offset;
+	unsigned long in_page_bytes_left;
+	unsigned long tot_in;
+	unsigned long tot_out;
+	unsigned long tot_len;
+	char *buf;
+
+	data_in = kmap(pages_in[0]);
+	tot_len = read_compress_length(data_in);
+
+	tot_in = LZO_LEN;
+	in_offset = LZO_LEN;
+	tot_len = min_t(size_t, srclen, tot_len);
+	in_page_bytes_left = PAGE_CACHE_SIZE - LZO_LEN;
+
+	tot_out = 0;
+	page_out = bvec[0].bv_page;
+	page_bytes_left = PAGE_CACHE_SIZE;
+	pg_offset = 0;
+
+	while (tot_in < tot_len) {
+		in_len = read_compress_length(data_in + in_offset);
+		in_page_bytes_left -= LZO_LEN;
+		in_offset += LZO_LEN;
+		tot_in += LZO_LEN;
+
+		tot_in += in_len;
+		working_bytes = in_len;
+
+		/* fast path: avoid using the working buffer */
+		if (in_page_bytes_left >= in_len) {
+			buf = data_in + in_offset;
+			bytes = in_len;
+			goto cont;
+		}
+
+		/* copy bytes from the pages into the working buffer */
+		buf = workspace->cbuf;
+		buf_offset = 0;
+		while (working_bytes) {
+			bytes = min(working_bytes, in_page_bytes_left);
+
+			memcpy(buf + buf_offset, data_in + in_offset, bytes);
+			buf_offset += bytes;
+cont:
+			working_bytes -= bytes;
+			in_page_bytes_left -= bytes;
+			in_offset += bytes;
+
+			/* check if we need to pick another page */
+			if ((working_bytes == 0 && in_page_bytes_left < LZO_LEN)
+			    || in_page_bytes_left == 0) {
+				tot_in += in_page_bytes_left;
+
+				if (working_bytes == 0 && tot_in >= tot_len)
+					break;
+
+				kunmap(pages_in[page_in_index]);
+				page_in_index++;
+				if (page_in_index >= total_pages_in) {
+					ret = -1;
+					data_in = NULL;
+					goto done;
+				}
+				data_in = kmap(pages_in[page_in_index]);
+
+				in_page_bytes_left = PAGE_CACHE_SIZE;
+				in_offset = 0;
+			}
+		}
+
+		out_len = lzo1x_worst_compress(PAGE_CACHE_SIZE);
+		ret = lzo1x_decompress_safe(buf, in_len, workspace->buf,
+					    &out_len);
+		if (ret != LZO_E_OK) {
+			printk(KERN_WARNING "btrfs decompress failed\n");
+			ret = -1;
+			break;
+		}
+
+		/*
+		 * buf start is the byte offset we're of the start of
+		 * our workspace buffer
+		 */
+		buf_start = tot_out;
+
+		/* tot_out is the last byte of the workspace buffer */
+		tot_out += out_len;
+
+		working_bytes = tot_out - buf_start;
+
+		/*
+		 * start_byte is the first byte of the page we're currently
+		 * copying into relative to the start of the compressed data.
+		 */
+		start_byte = page_offset(page_out) - disk_start;
+
+		if (working_bytes == 0) {
+			/* we didn't make progress in this inflate
+			 * call, we're done
+			 */
+			break;
+		}
+
+		/* we haven't yet hit data corresponding to this page */
+		if (tot_out <= start_byte)
+			continue;
+
+		/*
+		 * the start of the data we care about is offset into
+		 * the middle of our working buffer
+		 */
+		if (tot_out > start_byte && buf_start < start_byte) {
+			buf_offset = start_byte - buf_start;
+			working_bytes -= buf_offset;
+		} else {
+			buf_offset = 0;
+		}
+		current_buf_start = buf_start;
+
+		/* copy bytes from the working buffer into the pages */
+		while (working_bytes > 0) {
+			bytes = min(PAGE_CACHE_SIZE - pg_offset,
+				    PAGE_CACHE_SIZE - buf_offset);
+			bytes = min(bytes, working_bytes);
+			kaddr = kmap_atomic(page_out, KM_USER0);
+			memcpy(kaddr + pg_offset, workspace->buf + buf_offset,
+			       bytes);
+			kunmap_atomic(kaddr, KM_USER0);
+			flush_dcache_page(page_out);
+
+			pg_offset += bytes;
+			page_bytes_left -= bytes;
+			buf_offset += bytes;
+			working_bytes -= bytes;
+			current_buf_start += bytes;
+
+			/* check if we need to pick another page */
+			if (page_bytes_left == 0) {
+				page_out_index++;
+				if (page_out_index >= vcnt) {
+					ret = 0;
+					goto done;
+				}
+
+				page_out = bvec[page_out_index].bv_page;
+				pg_offset = 0;
+				page_bytes_left = PAGE_CACHE_SIZE;
+				start_byte = page_offset(page_out) - disk_start;
+
+				/*
+				 * make sure our new page is covered by this
+				 * working buffer
+				 */
+				if (tot_out <= start_byte)
+					break;
+
+				/* the next page in the biovec might not
+				 * be adjacent to the last page, but it
+				 * might still be found inside this working
+				 * buffer.  bump our offset pointer
+				 */
+				if (tot_out > start_byte &&
+				    current_buf_start < start_byte) {
+					buf_offset = start_byte - buf_start;
+					working_bytes = tot_out - start_byte;
+					current_buf_start = buf_start +
+						buf_offset;
+				}
+			}
+		}
+	}
+done:
+	if (data_in)
+		kunmap(pages_in[page_in_index]);
+	return ret;
+}
+
+static int lzo_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);
+	size_t in_len;
+	size_t out_len;
+	size_t tot_len;
+	int ret = 0;
+	char *kaddr;
+	unsigned long bytes;
+
+	BUG_ON(srclen < LZO_LEN);
+
+	tot_len = read_compress_length(data_in);
+	data_in += LZO_LEN;
+
+	in_len = read_compress_length(data_in);
+	data_in += LZO_LEN;
+
+	out_len = PAGE_CACHE_SIZE;
+	ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
+	if (ret != LZO_E_OK) {
+		printk(KERN_WARNING "btrfs decompress failed!\n");
+		ret = -1;
+		goto out;
+	}
+
+	if (out_len < start_byte) {
+		ret = -1;
+		goto out;
+	}
+
+	bytes = min_t(unsigned long, destlen, out_len - start_byte);
+
+	kaddr = kmap_atomic(dest_page, KM_USER0);
+	memcpy(kaddr, workspace->buf + start_byte, bytes);
+	kunmap_atomic(kaddr, KM_USER0);
+out:
+	return ret;
+}
+
+struct btrfs_compress_op btrfs_lzo_compress = {
+	.alloc_workspace	= lzo_alloc_workspace,
+	.free_workspace		= lzo_free_workspace,
+	.compress_pages		= lzo_compress_pages,
+	.decompress_biovec	= lzo_decompress_biovec,
+	.decompress		= lzo_decompress,
+};
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f348f2b93164..a1a76b2a61f9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -168,6 +168,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			    strcmp(args[0].from, "zlib") == 0) {
 				compress_type = "zlib";
 				info->compress_type = BTRFS_COMPRESS_ZLIB;
+			} else if (strcmp(args[0].from, "lzo") == 0) {
+				compress_type = "lzo";
+				info->compress_type = BTRFS_COMPRESS_LZO;
 			} else {
 				ret = -EINVAL;
 				goto out;
-- 
cgit v1.2.3-55-g7522


From 299a08b1c34f9397797946a0fa215c5fd145c5cf Mon Sep 17 00:00:00 2001
From: Miao Xie
Date: Wed, 5 Jan 2011 10:07:15 +0000
Subject: btrfs: fix wrong data space statistics

Josef has implemented mixed data/metadata chunks, we must add those chunks'
space just like data chunks.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Reviewed-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/super.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'fs/btrfs/super.c')

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a1a76b2a61f9..caa5bcc62f16 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -790,11 +790,10 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
-		if (found->flags & (BTRFS_BLOCK_GROUP_METADATA |
-				    BTRFS_BLOCK_GROUP_SYSTEM))
-			total_used_data += found->disk_total;
-		else
+		if (found->flags & BTRFS_BLOCK_GROUP_DATA)
 			total_used_data += found->disk_used;
+		else
+			total_used_data += found->disk_total;
 		total_used += found->disk_used;
 	}
 	rcu_read_unlock();
-- 
cgit v1.2.3-55-g7522


From 6d07bcec969af335d4e35b3921131b7929bd634e Mon Sep 17 00:00:00 2001
From: Miao Xie
Date: Wed, 5 Jan 2011 10:07:31 +0000
Subject: btrfs: fix wrong free space information of btrfs

When we store data by raid profile in btrfs with two or more different size
disks, df command shows there is some free space in the filesystem, but the
user can not write any data in fact, df command shows the wrong free space
information of btrfs.

 # mkfs.btrfs -d raid1 /dev/sda9 /dev/sda10
 # btrfs-show
 Label: none  uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
 	Total devices 2 FS bytes used 28.00KB
 	devid    1 size 5.01GB used 2.03GB path /dev/sda9
 	devid    2 size 10.00GB used 2.01GB path /dev/sda10
 # btrfs device scan /dev/sda9 /dev/sda10
 # mount /dev/sda9 /mnt
 # dd if=/dev/zero of=tmpfile0 bs=4K count=9999999999
   (fill the filesystem)
 # sync
 # df -TH
 Filesystem	Type	Size	Used	Avail	Use%	Mounted on
 /dev/sda9	btrfs	17G	8.6G	5.4G	62%	/mnt
 # btrfs-show
 Label: none  uuid: a95cd49e-6e33-45b8-8741-a36153ce4b64
 	Total devices 2 FS bytes used 3.99GB
 	devid    1 size 5.01GB used 5.01GB path /dev/sda9
 	devid    2 size 10.00GB used 4.99GB path /dev/sda10

It is because btrfs cannot allocate chunks when one of the pairing disks has
no space, the free space on the other disks can not be used for ever, and should
be subtracted from the total space, but btrfs doesn't subtract this space from
the total. It is strange to the user.

This patch fixes it by calcing the free space that can be used to allocate
chunks.

Implementation:
1. get all the devices free space, and align them by stripe length.
2. sort the devices by the free space.
3. check the free space of the devices,
   3.1. if it is not zero, and then check the number of the devices that has
        more free space than this device,
        if the number of the devices is beyond the min stripe number, the free
        space can be used, and add into total free space.
        if the number of the devices is below the min stripe number, we can not
        use the free space, the check ends.
   3.2. if the free space is zero, check the next devices, goto 3.1

This implementation is just likely fake chunk allocation.

After appling this patch, df can show correct space information:
 # df -TH
 Filesystem	Type	Size	Used	Avail	Use%	Mounted on
 /dev/sda9	btrfs	17G	8.6G	0	100%	/mnt

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ctree.h       |   2 +
 fs/btrfs/extent-tree.c |  58 +++++++++++++++++++-
 fs/btrfs/super.c       | 146 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/btrfs/volumes.c     |  84 ++++++++++++++++++++++++++++
 fs/btrfs/volumes.h     |   3 +
 5 files changed, 286 insertions(+), 7 deletions(-)

(limited to 'fs/btrfs/super.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0cb322cc4fc0..0995f4f68d7a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2158,6 +2158,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 group_start);
 u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data);
 void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
@@ -2201,6 +2202,7 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 		     int level, int *slot);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1e1c9a177626..04bfc3a2bd9f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3090,7 +3090,7 @@ static u64 get_alloc_profile(struct btrfs_root *root, u64 flags)
 	return btrfs_reduce_alloc_profile(root, flags);
 }
 
-static u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
+u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
 {
 	u64 flags;
 
@@ -8019,6 +8019,62 @@ out:
 	return ret;
 }
 
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * list. takes mirrors into account.
+ */
+static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list)
+{
+	struct btrfs_block_group_cache *block_group;
+	u64 free_bytes = 0;
+	int factor;
+
+	list_for_each_entry(block_group, groups_list, list) {
+		spin_lock(&block_group->lock);
+
+		if (!block_group->ro) {
+			spin_unlock(&block_group->lock);
+			continue;
+		}
+
+		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
+					  BTRFS_BLOCK_GROUP_RAID10 |
+					  BTRFS_BLOCK_GROUP_DUP))
+			factor = 2;
+		else
+			factor = 1;
+
+		free_bytes += (block_group->key.offset -
+			       btrfs_block_group_used(&block_group->item)) *
+			       factor;
+
+		spin_unlock(&block_group->lock);
+	}
+
+	return free_bytes;
+}
+
+/*
+ * helper to account the unused space of all the readonly block group in the
+ * space_info. takes mirrors into account.
+ */
+u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
+{
+	int i;
+	u64 free_bytes = 0;
+
+	spin_lock(&sinfo->lock);
+
+	for(i = 0; i < BTRFS_NR_RAID_TYPES; i++)
+		if (!list_empty(&sinfo->block_groups[i]))
+			free_bytes += __btrfs_get_ro_block_group_free_space(
+						&sinfo->block_groups[i]);
+
+	spin_unlock(&sinfo->lock);
+
+	return free_bytes;
+}
+
 int btrfs_set_block_group_rw(struct btrfs_root *root,
 			      struct btrfs_block_group_cache *cache)
 {
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index caa5bcc62f16..2963376e77f4 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -777,6 +777,127 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	return 0;
 }
 
+/*
+ * The helper to calc the free space on the devices that can be used to store
+ * file data.
+ */
+static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	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;
+	int i = 0, nr_devices;
+	int ret;
+
+	nr_devices = fs_info->fs_devices->rw_devices;
+	BUG_ON(!nr_devices);
+
+	devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
+			       GFP_NOFS);
+	if (!devices_info)
+		return -ENOMEM;
+
+	/* calc min stripe number for data space alloction */
+	type = btrfs_get_alloc_profile(root, 1);
+	if (type & BTRFS_BLOCK_GROUP_RAID0)
+		min_stripes = 2;
+	else if (type & BTRFS_BLOCK_GROUP_RAID1)
+		min_stripes = 2;
+	else if (type & BTRFS_BLOCK_GROUP_RAID10)
+		min_stripes = 4;
+
+	if (type & BTRFS_BLOCK_GROUP_DUP)
+		min_stripe_size = 2 * BTRFS_STRIPE_LEN;
+	else
+		min_stripe_size = BTRFS_STRIPE_LEN;
+
+	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
+		if (!device->in_fs_metadata)
+			continue;
+
+		avail_space = device->total_bytes - device->bytes_used;
+
+		/* align with stripe_len */
+		do_div(avail_space, BTRFS_STRIPE_LEN);
+		avail_space *= BTRFS_STRIPE_LEN;
+
+		/*
+		 * In order to avoid overwritting the superblock on the drive,
+		 * btrfs starts at an offset of at least 1MB when doing chunk
+		 * allocation.
+		 */
+		skip_space = 1024 * 1024;
+
+		/* user can set the offset in fs_info->alloc_start. */
+		if (fs_info->alloc_start + BTRFS_STRIPE_LEN <=
+		    device->total_bytes)
+			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);
+			return ret;
+		}
+
+		/* 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.
+		 */
+		if (avail_space && avail_space >= skip_space)
+			avail_space -= skip_space;
+		else
+			avail_space = 0;
+
+		if (avail_space < min_stripe_size)
+			continue;
+
+		devices_info[i].dev = device;
+		devices_info[i].max_avail = avail_space;
+
+		i++;
+	}
+
+	nr_devices = i;
+
+	btrfs_descending_sort_devices(devices_info, nr_devices);
+
+	i = nr_devices - 1;
+	avail_space = 0;
+	while (nr_devices >= min_stripes) {
+		if (devices_info[i].max_avail >= min_stripe_size) {
+			int j;
+			u64 alloc_size;
+
+			avail_space += devices_info[i].max_avail * min_stripes;
+			alloc_size = devices_info[i].max_avail;
+			for (j = i + 1 - min_stripes; j <= i; j++)
+				devices_info[j].max_avail -= alloc_size;
+		}
+		i--;
+		nr_devices--;
+	}
+
+	kfree(devices_info);
+	*free_bytes = avail_space;
+	return 0;
+}
+
 static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct btrfs_root *root = btrfs_sb(dentry->d_sb);
@@ -784,16 +905,21 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct list_head *head = &root->fs_info->space_info;
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
-	u64 total_used_data = 0;
+	u64 total_free_data = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
 	__be32 *fsid = (__be32 *)root->fs_info->fsid;
+	int ret;
 
+	/* holding chunk_muext to avoid allocating new chunks */
+	mutex_lock(&root->fs_info->chunk_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
-		if (found->flags & BTRFS_BLOCK_GROUP_DATA)
-			total_used_data += found->disk_used;
-		else
-			total_used_data += found->disk_total;
+		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
+			total_free_data += found->disk_total - found->disk_used;
+			total_free_data -=
+				btrfs_account_ro_block_groups_free_space(found);
+		}
+
 		total_used += found->disk_used;
 	}
 	rcu_read_unlock();
@@ -801,9 +927,17 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_namelen = BTRFS_NAME_LEN;
 	buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits;
 	buf->f_bfree = buf->f_blocks - (total_used >> bits);
-	buf->f_bavail = buf->f_blocks - (total_used_data >> bits);
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_type = BTRFS_SUPER_MAGIC;
+	buf->f_bavail = total_free_data;
+	ret = btrfs_calc_avail_data_space(root, &total_free_data);
+	if (ret) {
+		mutex_unlock(&root->fs_info->chunk_mutex);
+		return ret;
+	}
+	buf->f_bavail += total_free_data;
+	buf->f_bavail = buf->f_bavail >> bits;
+	mutex_unlock(&root->fs_info->chunk_mutex);
 
 	/* We treat it as constant endianness (it doesn't matter _which_)
 	   because we want the fsid to come out the same whether mounted
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c22784b989b7..0c7f478cf645 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -728,6 +728,90 @@ error:
 	return ret;
 }
 
+/* helper to account the used device space in the range */
+int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
+				   u64 end, u64 *length)
+{
+	struct btrfs_key key;
+	struct btrfs_root *root = device->dev_root;
+	struct btrfs_dev_extent *dev_extent;
+	struct btrfs_path *path;
+	u64 extent_end;
+	int ret;
+	int slot;
+	struct extent_buffer *l;
+
+	*length = 0;
+
+	if (start >= device->total_bytes)
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+	path->reada = 2;
+
+	key.objectid = device->devid;
+	key.offset = start;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = btrfs_previous_item(root, path, key.objectid, key.type);
+		if (ret < 0)
+			goto out;
+	}
+
+	while (1) {
+		l = path->nodes[0];
+		slot = path->slots[0];
+		if (slot >= btrfs_header_nritems(l)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret == 0)
+				continue;
+			if (ret < 0)
+				goto out;
+
+			break;
+		}
+		btrfs_item_key_to_cpu(l, &key, slot);
+
+		if (key.objectid < device->devid)
+			goto next;
+
+		if (key.objectid > device->devid)
+			break;
+
+		if (btrfs_key_type(&key) != BTRFS_DEV_EXTENT_KEY)
+			goto next;
+
+		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
+		extent_end = key.offset + btrfs_dev_extent_length(l,
+								  dev_extent);
+		if (key.offset <= start && extent_end > end) {
+			*length = end - start + 1;
+			break;
+		} else if (key.offset <= start && extent_end > start)
+			*length += extent_end - start;
+		else if (key.offset > start && extent_end <= end)
+			*length += extent_end - key.offset;
+		else if (key.offset > start && key.offset <= end) {
+			*length += end - key.offset + 1;
+			break;
+		} else if (key.offset > end)
+			break;
+
+next:
+		path->slots[0]++;
+	}
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 /*
  * find_free_dev_extent - find free space in the specified device
  * @trans:	transaction handler
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index a5cfedf393f9..7af6144a7954 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -161,6 +161,9 @@ static inline void btrfs_descending_sort_devices(
 	     btrfs_cmp_device_free_bytes, NULL);
 }
 
+int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
+				   u64 end, u64 *length);
+
 #define btrfs_multi_bio_size(n) (sizeof(struct btrfs_multi_bio) + \
 			    (sizeof(struct btrfs_bio_stripe) * (n)))
 
-- 
cgit v1.2.3-55-g7522


From acce952b0263825da32cf10489413dec78053347 Mon Sep 17 00:00:00 2001
From: liubo
Date: Thu, 6 Jan 2011 19:30:25 +0800
Subject: Btrfs: forced readonly mounts on errors

This patch comes from "Forced readonly mounts on errors" ideas.

As we know, this is the first step in being more fault tolerant of disk
corruptions instead of just using BUG() statements.

The major content:
- add a framework for generating errors that should result in filesystems
  going readonly.
- keep FS state in disk super block.
- make sure that all of resource will be freed and released at umount time.
- make sure that fter FS is forced readonly on error, there will be no more
  disk change before FS is corrected. For this, we should stop write operation.

After this patch is applied, the conversion from BUG() to such a framework can
happen incrementally.

Signed-off-by: Liu Bo <liubo2009@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ctree.h       |  24 +++
 fs/btrfs/disk-io.c     | 391 ++++++++++++++++++++++++++++++++++++++++++++++++-
 fs/btrfs/disk-io.h     |   1 +
 fs/btrfs/extent-tree.c |  11 ++
 fs/btrfs/file.c        |  11 ++
 fs/btrfs/super.c       |  84 +++++++++++
 fs/btrfs/transaction.c |   3 +
 7 files changed, 523 insertions(+), 2 deletions(-)

(limited to 'fs/btrfs/super.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0995f4f68d7a..72195378bef9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -295,6 +295,14 @@ static inline unsigned long btrfs_chunk_item_size(int num_stripes)
 #define BTRFS_FSID_SIZE 16
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)
 #define BTRFS_HEADER_FLAG_RELOC		(1ULL << 1)
+
+/*
+ * File system states
+ */
+
+/* Errors detected */
+#define BTRFS_SUPER_FLAG_ERROR		(1ULL << 2)
+
 #define BTRFS_SUPER_FLAG_SEEDING	(1ULL << 32)
 #define BTRFS_SUPER_FLAG_METADUMP	(1ULL << 33)
 
@@ -1058,6 +1066,9 @@ struct btrfs_fs_info {
 	unsigned metadata_ratio;
 
 	void *bdev_holder;
+
+	/* filesystem state */
+	u64 fs_state;
 };
 
 /*
@@ -2203,6 +2214,11 @@ int btrfs_set_block_group_rw(struct btrfs_root *root,
 			     struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
+int btrfs_error_unpin_extent_range(struct btrfs_root *root,
+				   u64 start, u64 end);
+int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+			       u64 num_bytes);
+
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 		     int level, int *slot);
@@ -2556,6 +2572,14 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
 /* super.c */
 int btrfs_parse_options(struct btrfs_root *root, char *options);
 int btrfs_sync_fs(struct super_block *sb, int wait);
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		     unsigned int line, int errno);
+
+#define btrfs_std_error(fs_info, errno)				\
+do {								\
+	if ((errno))						\
+		__btrfs_std_error((fs_info), __func__, __LINE__, (errno));\
+} while (0)
 
 /* acl.c */
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9b1dd4138072..1a3af9e8e0c4 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -44,6 +44,20 @@
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
+static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+				    int read_only);
+static int btrfs_destroy_ordered_operations(struct btrfs_root *root);
+static int btrfs_destroy_ordered_extents(struct btrfs_root *root);
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+				      struct btrfs_root *root);
+static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t);
+static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
+static int btrfs_destroy_marked_extents(struct btrfs_root *root,
+					struct extent_io_tree *dirty_pages,
+					int mark);
+static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
+				       struct extent_io_tree *pinned_extents);
+static int btrfs_cleanup_transaction(struct btrfs_root *root);
 
 /*
  * end_io_wq structs are used to do processing in task context when an IO is
@@ -1738,6 +1752,11 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (!btrfs_super_root(disk_super))
 		goto fail_iput;
 
+	/* check FS state, whether FS is broken. */
+	fs_info->fs_state |= btrfs_super_flags(disk_super);
+
+	btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+
 	ret = btrfs_parse_options(tree_root, options);
 	if (ret) {
 		err = ret;
@@ -1968,7 +1987,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		btrfs_set_opt(fs_info->mount_opt, SSD);
 	}
 
-	if (btrfs_super_log_root(disk_super) != 0) {
+	/* do not make disk changes in broken FS */
+	if (btrfs_super_log_root(disk_super) != 0 &&
+	    !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) {
 		u64 bytenr = btrfs_super_log_root(disk_super);
 
 		if (fs_devices->rw_devices == 0) {
@@ -2464,8 +2485,28 @@ int close_ctree(struct btrfs_root *root)
 	smp_mb();
 
 	btrfs_put_block_group_cache(fs_info);
+
+	/*
+	 * Here come 2 situations when btrfs is broken to flip readonly:
+	 *
+	 * 1. when btrfs flips readonly somewhere else before
+	 * btrfs_commit_super, sb->s_flags has MS_RDONLY flag,
+	 * and btrfs will skip to write sb directly to keep
+	 * ERROR state on disk.
+	 *
+	 * 2. when btrfs flips readonly just in btrfs_commit_super,
+	 * and in such case, btrfs cannnot write sb via btrfs_commit_super,
+	 * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag,
+	 * btrfs will cleanup all FS resources first and write sb then.
+	 */
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
-		ret =  btrfs_commit_super(root);
+		ret = btrfs_commit_super(root);
+		if (ret)
+			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
+	}
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		ret = btrfs_error_commit_super(root);
 		if (ret)
 			printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
 	}
@@ -2641,6 +2682,352 @@ out:
 	return 0;
 }
 
+static void btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
+			      int read_only)
+{
+	if (read_only)
+		return;
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		printk(KERN_WARNING "warning: mount fs with errors, "
+		       "running btrfsck is recommended\n");
+}
+
+int btrfs_error_commit_super(struct btrfs_root *root)
+{
+	int ret;
+
+	mutex_lock(&root->fs_info->cleaner_mutex);
+	btrfs_run_delayed_iputs(root);
+	mutex_unlock(&root->fs_info->cleaner_mutex);
+
+	down_write(&root->fs_info->cleanup_work_sem);
+	up_write(&root->fs_info->cleanup_work_sem);
+
+	/* cleanup FS via transaction */
+	btrfs_cleanup_transaction(root);
+
+	ret = write_ctree_super(NULL, root, 0);
+
+	return ret;
+}
+
+static int btrfs_destroy_ordered_operations(struct btrfs_root *root)
+{
+	struct btrfs_inode *btrfs_inode;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	mutex_lock(&root->fs_info->ordered_operations_mutex);
+	spin_lock(&root->fs_info->ordered_extent_lock);
+
+	list_splice_init(&root->fs_info->ordered_operations, &splice);
+	while (!list_empty(&splice)) {
+		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
+					 ordered_operations);
+
+		list_del_init(&btrfs_inode->ordered_operations);
+
+		btrfs_invalidate_inodes(btrfs_inode->root);
+	}
+
+	spin_unlock(&root->fs_info->ordered_extent_lock);
+	mutex_unlock(&root->fs_info->ordered_operations_mutex);
+
+	return 0;
+}
+
+static int btrfs_destroy_ordered_extents(struct btrfs_root *root)
+{
+	struct list_head splice;
+	struct btrfs_ordered_extent *ordered;
+	struct inode *inode;
+
+	INIT_LIST_HEAD(&splice);
+
+	spin_lock(&root->fs_info->ordered_extent_lock);
+
+	list_splice_init(&root->fs_info->ordered_extents, &splice);
+	while (!list_empty(&splice)) {
+		ordered = list_entry(splice.next, struct btrfs_ordered_extent,
+				     root_extent_list);
+
+		list_del_init(&ordered->root_extent_list);
+		atomic_inc(&ordered->refs);
+
+		/* the inode may be getting freed (in sys_unlink path). */
+		inode = igrab(ordered->inode);
+
+		spin_unlock(&root->fs_info->ordered_extent_lock);
+		if (inode)
+			iput(inode);
+
+		atomic_set(&ordered->refs, 1);
+		btrfs_put_ordered_extent(ordered);
+
+		spin_lock(&root->fs_info->ordered_extent_lock);
+	}
+
+	spin_unlock(&root->fs_info->ordered_extent_lock);
+
+	return 0;
+}
+
+static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
+				      struct btrfs_root *root)
+{
+	struct rb_node *node;
+	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_delayed_ref_node *ref;
+	int ret = 0;
+
+	delayed_refs = &trans->delayed_refs;
+
+	spin_lock(&delayed_refs->lock);
+	if (delayed_refs->num_entries == 0) {
+		printk(KERN_INFO "delayed_refs has NO entry\n");
+		return ret;
+	}
+
+	node = rb_first(&delayed_refs->root);
+	while (node) {
+		ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+		node = rb_next(node);
+
+		ref->in_tree = 0;
+		rb_erase(&ref->rb_node, &delayed_refs->root);
+		delayed_refs->num_entries--;
+
+		atomic_set(&ref->refs, 1);
+		if (btrfs_delayed_ref_is_head(ref)) {
+			struct btrfs_delayed_ref_head *head;
+
+			head = btrfs_delayed_node_to_head(ref);
+			mutex_lock(&head->mutex);
+			kfree(head->extent_op);
+			delayed_refs->num_heads--;
+			if (list_empty(&head->cluster))
+				delayed_refs->num_heads_ready--;
+			list_del_init(&head->cluster);
+			mutex_unlock(&head->mutex);
+		}
+
+		spin_unlock(&delayed_refs->lock);
+		btrfs_put_delayed_ref(ref);
+
+		cond_resched();
+		spin_lock(&delayed_refs->lock);
+	}
+
+	spin_unlock(&delayed_refs->lock);
+
+	return ret;
+}
+
+static int btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
+{
+	struct btrfs_pending_snapshot *snapshot;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	list_splice_init(&t->pending_snapshots, &splice);
+
+	while (!list_empty(&splice)) {
+		snapshot = list_entry(splice.next,
+				      struct btrfs_pending_snapshot,
+				      list);
+
+		list_del_init(&snapshot->list);
+
+		kfree(snapshot);
+	}
+
+	return 0;
+}
+
+static int btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
+{
+	struct btrfs_inode *btrfs_inode;
+	struct list_head splice;
+
+	INIT_LIST_HEAD(&splice);
+
+	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+
+	spin_lock(&root->fs_info->delalloc_lock);
+
+	while (!list_empty(&splice)) {
+		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
+				    delalloc_inodes);
+
+		list_del_init(&btrfs_inode->delalloc_inodes);
+
+		btrfs_invalidate_inodes(btrfs_inode->root);
+	}
+
+	spin_unlock(&root->fs_info->delalloc_lock);
+
+	return 0;
+}
+
+static int btrfs_destroy_marked_extents(struct btrfs_root *root,
+					struct extent_io_tree *dirty_pages,
+					int mark)
+{
+	int ret;
+	struct page *page;
+	struct inode *btree_inode = root->fs_info->btree_inode;
+	struct extent_buffer *eb;
+	u64 start = 0;
+	u64 end;
+	u64 offset;
+	unsigned long index;
+
+	while (1) {
+		ret = find_first_extent_bit(dirty_pages, start, &start, &end,
+					    mark);
+		if (ret)
+			break;
+
+		clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+		while (start <= end) {
+			index = start >> PAGE_CACHE_SHIFT;
+			start = (u64)(index + 1) << PAGE_CACHE_SHIFT;
+			page = find_get_page(btree_inode->i_mapping, index);
+			if (!page)
+				continue;
+			offset = page_offset(page);
+
+			spin_lock(&dirty_pages->buffer_lock);
+			eb = radix_tree_lookup(
+			     &(&BTRFS_I(page->mapping->host)->io_tree)->buffer,
+					       offset >> PAGE_CACHE_SHIFT);
+			spin_unlock(&dirty_pages->buffer_lock);
+			if (eb) {
+				ret = test_and_clear_bit(EXTENT_BUFFER_DIRTY,
+							 &eb->bflags);
+				atomic_set(&eb->refs, 1);
+			}
+			if (PageWriteback(page))
+				end_page_writeback(page);
+
+			lock_page(page);
+			if (PageDirty(page)) {
+				clear_page_dirty_for_io(page);
+				spin_lock_irq(&page->mapping->tree_lock);
+				radix_tree_tag_clear(&page->mapping->page_tree,
+							page_index(page),
+							PAGECACHE_TAG_DIRTY);
+				spin_unlock_irq(&page->mapping->tree_lock);
+			}
+
+			page->mapping->a_ops->invalidatepage(page, 0);
+			unlock_page(page);
+		}
+	}
+
+	return ret;
+}
+
+static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
+				       struct extent_io_tree *pinned_extents)
+{
+	struct extent_io_tree *unpin;
+	u64 start;
+	u64 end;
+	int ret;
+
+	unpin = pinned_extents;
+	while (1) {
+		ret = find_first_extent_bit(unpin, 0, &start, &end,
+					    EXTENT_DIRTY);
+		if (ret)
+			break;
+
+		/* opt_discard */
+		ret = btrfs_error_discard_extent(root, start, end + 1 - start);
+
+		clear_extent_dirty(unpin, start, end, GFP_NOFS);
+		btrfs_error_unpin_extent_range(root, start, end);
+		cond_resched();
+	}
+
+	return 0;
+}
+
+static int btrfs_cleanup_transaction(struct btrfs_root *root)
+{
+	struct btrfs_transaction *t;
+	LIST_HEAD(list);
+
+	WARN_ON(1);
+
+	mutex_lock(&root->fs_info->trans_mutex);
+	mutex_lock(&root->fs_info->transaction_kthread_mutex);
+
+	list_splice_init(&root->fs_info->trans_list, &list);
+	while (!list_empty(&list)) {
+		t = list_entry(list.next, struct btrfs_transaction, list);
+		if (!t)
+			break;
+
+		btrfs_destroy_ordered_operations(root);
+
+		btrfs_destroy_ordered_extents(root);
+
+		btrfs_destroy_delayed_refs(t, root);
+
+		btrfs_block_rsv_release(root,
+					&root->fs_info->trans_block_rsv,
+					t->dirty_pages.dirty_bytes);
+
+		/* FIXME: cleanup wait for commit */
+		t->in_commit = 1;
+		t->blocked = 1;
+		if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
+			wake_up(&root->fs_info->transaction_blocked_wait);
+
+		t->blocked = 0;
+		if (waitqueue_active(&root->fs_info->transaction_wait))
+			wake_up(&root->fs_info->transaction_wait);
+		mutex_unlock(&root->fs_info->trans_mutex);
+
+		mutex_lock(&root->fs_info->trans_mutex);
+		t->commit_done = 1;
+		if (waitqueue_active(&t->commit_wait))
+			wake_up(&t->commit_wait);
+		mutex_unlock(&root->fs_info->trans_mutex);
+
+		mutex_lock(&root->fs_info->trans_mutex);
+
+		btrfs_destroy_pending_snapshots(t);
+
+		btrfs_destroy_delalloc_inodes(root);
+
+		spin_lock(&root->fs_info->new_trans_lock);
+		root->fs_info->running_transaction = NULL;
+		spin_unlock(&root->fs_info->new_trans_lock);
+
+		btrfs_destroy_marked_extents(root, &t->dirty_pages,
+					     EXTENT_DIRTY);
+
+		btrfs_destroy_pinned_extent(root,
+					    root->fs_info->pinned_extents);
+
+		t->use_count = 0;
+		list_del_init(&t->list);
+		memset(t, 0, sizeof(*t));
+		kmem_cache_free(btrfs_transaction_cachep, t);
+	}
+
+	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
+	mutex_unlock(&root->fs_info->trans_mutex);
+
+	return 0;
+}
+
 static struct extent_io_ops btree_extent_io_ops = {
 	.write_cache_pages_lock_hook = btree_lock_page_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 88e825a0bf21..07b20dc2fd95 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -52,6 +52,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_commit_super(struct btrfs_root *root);
+int btrfs_error_commit_super(struct btrfs_root *root);
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 					    u64 bytenr, u32 blocksize);
 struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 055b837eab19..bcf303204f7f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8642,3 +8642,14 @@ out:
 	btrfs_free_path(path);
 	return ret;
 }
+
+int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
+{
+	return unpin_extent_range(root, start, end);
+}
+
+int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
+			       u64 num_bytes)
+{
+	return btrfs_discard_extent(root, bytenr, num_bytes);
+}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 05df688c96f4..f903433f5bdf 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -892,6 +892,17 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	if (err)
 		goto out;
 
+	/*
+	 * If BTRFS flips readonly due to some impossible error
+	 * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
+	 * although we have opened a file as writable, we have
+	 * to stop this write operation to ensure FS consistency.
+	 */
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		err = -EROFS;
+		goto out;
+	}
+
 	file_update_time(file);
 	BTRFS_I(inode)->sequence++;
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 2963376e77f4..52e903b0a293 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -54,6 +54,90 @@
 
 static const struct super_operations btrfs_super_ops;
 
+static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
+				      char nbuf[16])
+{
+	char *errstr = NULL;
+
+	switch (errno) {
+	case -EIO:
+		errstr = "IO failure";
+		break;
+	case -ENOMEM:
+		errstr = "Out of memory";
+		break;
+	case -EROFS:
+		errstr = "Readonly filesystem";
+		break;
+	default:
+		if (nbuf) {
+			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
+				errstr = nbuf;
+		}
+		break;
+	}
+
+	return errstr;
+}
+
+static void __save_error_info(struct btrfs_fs_info *fs_info)
+{
+	/*
+	 * today we only save the error info into ram.  Long term we'll
+	 * also send it down to the disk
+	 */
+	fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
+}
+
+/* NOTE:
+ *	We move write_super stuff at umount in order to avoid deadlock
+ *	for umount hold all lock.
+ */
+static void save_error_info(struct btrfs_fs_info *fs_info)
+{
+	__save_error_info(fs_info);
+}
+
+/* btrfs handle error by forcing the filesystem readonly */
+static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
+{
+	struct super_block *sb = fs_info->sb;
+
+	if (sb->s_flags & MS_RDONLY)
+		return;
+
+	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+		sb->s_flags |= MS_RDONLY;
+		printk(KERN_INFO "btrfs is forced readonly\n");
+	}
+}
+
+/*
+ * __btrfs_std_error decodes expected errors from the caller and
+ * invokes the approciate error response.
+ */
+void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+		     unsigned int line, int errno)
+{
+	struct super_block *sb = fs_info->sb;
+	char nbuf[16];
+	const char *errstr;
+
+	/*
+	 * 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))
+		return;
+
+	errstr = btrfs_decode_error(fs_info, errno, nbuf);
+	printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
+		sb->s_id, function, line, errstr);
+	save_error_info(fs_info);
+
+	btrfs_handle_error(fs_info);
+}
+
 static void btrfs_put_super(struct super_block *sb)
 {
 	struct btrfs_root *root = btrfs_sb(sb);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 29e30d832ec9..bae5c7b8bbe2 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -181,6 +181,9 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 	struct btrfs_trans_handle *h;
 	struct btrfs_transaction *cur_trans;
 	int ret;
+
+	if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
+		return ERR_PTR(-EROFS);
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
 	if (!h)
-- 
cgit v1.2.3-55-g7522