From 9bffad1ed2a003a355ed1b42424a0ae3575275ed Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Wed, 17 Jun 2009 11:48:11 -0400
Subject: ext4: convert instrumentation from markers to tracepoints

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 69 ++++++++++++---------------------------------------------
 1 file changed, 14 insertions(+), 55 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 875db944b22f..2418ad36eab5 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -37,11 +37,14 @@
 #include <linux/namei.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
+
 #include "ext4_jbd2.h"
 #include "xattr.h"
 #include "acl.h"
 #include "ext4_extents.h"
 
+#include <trace/events/ext4.h>
+
 #define MPAGE_DA_EXTENT_TAIL 0x01
 
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
@@ -1466,10 +1469,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
  	pgoff_t index;
 	unsigned from, to;
 
-	trace_mark(ext4_write_begin,
-		   "dev %s ino %lu pos %llu len %u flags %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, flags);
+	trace_ext4_write_begin(inode, pos, len, flags);
 	/*
 	 * Reserve one block more for addition to orphan list in case
 	 * we allocate blocks but write fails for some reason
@@ -1611,10 +1611,7 @@ static int ext4_ordered_write_end(struct file *file,
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 
-	trace_mark(ext4_ordered_write_end,
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
+	trace_ext4_ordered_write_end(inode, pos, len, copied);
 	ret = ext4_jbd2_file_inode(handle, inode);
 
 	if (ret == 0) {
@@ -1658,10 +1655,7 @@ static int ext4_writeback_write_end(struct file *file,
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
 
-	trace_mark(ext4_writeback_write_end,
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
+	trace_ext4_writeback_write_end(inode, pos, len, copied);
 	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 	copied = ret2;
@@ -1705,10 +1699,7 @@ static int ext4_journalled_write_end(struct file *file,
 	unsigned from, to;
 	loff_t new_i_size;
 
-	trace_mark(ext4_journalled_write_end,
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
+	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
@@ -2554,9 +2545,7 @@ static int ext4_da_writepage(struct page *page,
 	struct buffer_head *page_bufs;
 	struct inode *inode = page->mapping->host;
 
-	trace_mark(ext4_da_writepage,
-		   "dev %s ino %lu page_index %lu",
-		   inode->i_sb->s_id, inode->i_ino, page->index);
+	trace_ext4_da_writepage(inode, page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2667,19 +2656,7 @@ static int ext4_da_writepages(struct address_space *mapping,
 	int needed_blocks, ret = 0, nr_to_writebump = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
 
-	trace_mark(ext4_da_writepages,
-		   "dev %s ino %lu nr_t_write %ld "
-		   "pages_skipped %ld range_start %llu "
-		   "range_end %llu nonblocking %d "
-		   "for_kupdate %d for_reclaim %d "
-		   "for_writepages %d range_cyclic %d",
-		   inode->i_sb->s_id, inode->i_ino,
-		   wbc->nr_to_write, wbc->pages_skipped,
-		   (unsigned long long) wbc->range_start,
-		   (unsigned long long) wbc->range_end,
-		   wbc->nonblocking, wbc->for_kupdate,
-		   wbc->for_reclaim, wbc->for_writepages,
-		   wbc->range_cyclic);
+	trace_ext4_da_writepages(inode, wbc);
 
 	/*
 	 * No pages to write? This is mainly a kludge to avoid starting
@@ -2845,14 +2822,7 @@ out_writepages:
 	if (!no_nrwrite_index_update)
 		wbc->no_nrwrite_index_update = 0;
 	wbc->nr_to_write -= nr_to_writebump;
-	trace_mark(ext4_da_writepage_result,
-		   "dev %s ino %lu ret %d pages_written %d "
-		   "pages_skipped %ld congestion %d "
-		   "more_io %d no_nrwrite_index_update %d",
-		   inode->i_sb->s_id, inode->i_ino, ret,
-		   pages_written, wbc->pages_skipped,
-		   wbc->encountered_congestion, wbc->more_io,
-		   wbc->no_nrwrite_index_update);
+	trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
 	return ret;
 }
 
@@ -2904,11 +2874,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 					len, flags, pagep, fsdata);
 	}
 	*fsdata = (void *)0;
-
-	trace_mark(ext4_da_write_begin,
-		   "dev %s ino %lu pos %llu len %u flags %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, flags);
+	trace_ext4_da_write_begin(inode, pos, len, flags);
 retry:
 	/*
 	 * With delayed allocation, we don't log the i_disksize update
@@ -3001,10 +2967,7 @@ static int ext4_da_write_end(struct file *file,
 		}
 	}
 
-	trace_mark(ext4_da_write_end,
-		   "dev %s ino %lu pos %llu len %u copied %u",
-		   inode->i_sb->s_id, inode->i_ino,
-		   (unsigned long long) pos, len, copied);
+	trace_ext4_da_write_end(inode, pos, len, copied);
 	start = pos & (PAGE_CACHE_SIZE - 1);
 	end = start + copied - 1;
 
@@ -3255,9 +3218,7 @@ static int ext4_normal_writepage(struct page *page,
 	loff_t size = i_size_read(inode);
 	loff_t len;
 
-	trace_mark(ext4_normal_writepage,
-		   "dev %s ino %lu page_index %lu",
-		   inode->i_sb->s_id, inode->i_ino, page->index);
+	trace_ext4_normal_writepage(inode, page);
 	J_ASSERT(PageLocked(page));
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -3343,9 +3304,7 @@ static int ext4_journalled_writepage(struct page *page,
 	loff_t size = i_size_read(inode);
 	loff_t len;
 
-	trace_mark(ext4_journalled_writepage,
-		   "dev %s ino %lu page_index %lu",
-		   inode->i_sb->s_id, inode->i_ino, page->index);
+	trace_ext4_journalled_writepage(inode, page);
 	J_ASSERT(PageLocked(page));
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
-- 
cgit v1.2.3


From 7f4520cc6242780ce720aa440ad4b391f998b558 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Sat, 13 Jun 2009 10:09:41 -0400
Subject: ext4: change s_mount_opt to be an unsigned int

We can only fit 32 options in s_mount_opt because an unsigned long is
32-bits on a x86 machine.  So use an unsigned int to save space on
64-bit platforms.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2418ad36eab5..f8325a2bc897 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -93,7 +93,7 @@ int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 	BUFFER_TRACE(bh, "enter");
 
 	jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
-		  "data mode %lx\n",
+		  "data mode %x\n",
 		  bh, is_metadata, inode->i_mode,
 		  test_opt(inode->i_sb, DATA_FLAGS));
 
-- 
cgit v1.2.3


From 4ab2f15b7f709c3626a7eed075a7225b4c775c7e Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Sat, 13 Jun 2009 10:09:36 -0400
Subject: ext4: move the abort flag from s_mount_opts to s_mount_flags

We're running out of space in the mount options word, and
EXT4_MOUNT_ABORT isn't really a mount option, but a run-time flag.  So
move it to become EXT4_MF_FS_ABORTED in s_mount_flags.

Also remove bogus ext2_fs.h / ext4.h simultaneous #include protection,
which can never happen.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index f8325a2bc897..5f927f6a1289 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2670,13 +2670,13 @@ static int ext4_da_writepages(struct address_space *mapping,
 	 * If the filesystem has aborted, it is read-only, so return
 	 * right away instead of dumping stack traces later on that
 	 * will obscure the real source of the problem.  We test
-	 * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+	 * EXT4_MF_FS_ABORTED instead of sb->s_flag's MS_RDONLY because
 	 * the latter could be true if the filesystem is mounted
 	 * read-only, and in that case, ext4_da_writepages should
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED))
 		return -EROFS;
 
 	/*
-- 
cgit v1.2.3


From de9a55b841132f7ae097f6e31ccebad2d5030cf5 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Sun, 14 Jun 2009 17:45:34 -0400
Subject: ext4: Fix up whitespace issues in fs/ext4/inode.c

This is a pure cleanup patch.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 200 +++++++++++++++++++++++++++++---------------------------
 1 file changed, 103 insertions(+), 97 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5f927f6a1289..8d0908afbd5b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -81,7 +81,7 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
  * If the handle isn't valid we're not journaling so there's nothing to do.
  */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
-			struct buffer_head *bh, ext4_fsblk_t blocknr)
+		struct buffer_head *bh, ext4_fsblk_t blocknr)
 {
 	int err;
 
@@ -332,8 +332,8 @@ static inline void add_chain(Indirect *p, struct buffer_head *bh, __le32 *v)
  */
 
 static int ext4_block_to_path(struct inode *inode,
-			ext4_lblk_t i_block,
-			ext4_lblk_t offsets[4], int *boundary)
+			      ext4_lblk_t i_block,
+			      ext4_lblk_t offsets[4], int *boundary)
 {
 	int ptrs = EXT4_ADDR_PER_BLOCK(inode->i_sb);
 	int ptrs_bits = EXT4_ADDR_PER_BLOCK_BITS(inode->i_sb);
@@ -365,9 +365,9 @@ static int ext4_block_to_path(struct inode *inode,
 		final = ptrs;
 	} else {
 		ext4_warning(inode->i_sb, "ext4_block_to_path",
-				"block %lu > max in inode %lu",
-				i_block + direct_blocks +
-				indirect_blocks + double_blocks, inode->i_ino);
+			     "block %lu > max in inode %lu",
+			     i_block + direct_blocks +
+			     indirect_blocks + double_blocks, inode->i_ino);
 	}
 	if (boundary)
 		*boundary = final - 1 - (i_block & (ptrs - 1));
@@ -382,25 +382,25 @@ static int __ext4_check_blockref(const char *function, struct inode *inode,
 
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
-		if (blk && 
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), 
+		if (blk &&
+		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
 						    blk, 1))) {
 			ext4_error(inode->i_sb, function,
 				   "invalid block reference %u "
 				   "in inode #%lu", blk, inode->i_ino);
- 			return -EIO;
- 		}
- 	}
- 	return 0;
+			return -EIO;
+		}
+	}
+	return 0;
 }
 
 
 #define ext4_check_indirect_blockref(inode, bh)                         \
-        __ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data,  \
+	__ext4_check_blockref(__func__, inode, (__le32 *)(bh)->b_data,  \
 			      EXT4_ADDR_PER_BLOCK((inode)->i_sb))
 
 #define ext4_check_inode_blockref(inode)                                \
-        __ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data,   \
+	__ext4_check_blockref(__func__, inode, EXT4_I(inode)->i_data,   \
 			      EXT4_NDIR_BLOCKS)
 
 /**
@@ -450,7 +450,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 		bh = sb_getblk(sb, le32_to_cpu(p->key));
 		if (unlikely(!bh))
 			goto failure;
-                  
+
 		if (!bh_uptodate_or_lock(bh)) {
 			if (bh_submit_read(bh) < 0) {
 				put_bh(bh);
@@ -462,7 +462,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 				goto failure;
 			}
 		}
-		
+
 		add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets);
 		/* Reader: end */
 		if (!p->key)
@@ -555,7 +555,7 @@ static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind)
  *	returns it.
  */
 static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
-		Indirect *partial)
+				   Indirect *partial)
 {
 	/*
 	 * XXX need to get goal block from mballoc's data structures
@@ -577,7 +577,7 @@ static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
  *	direct and indirect blocks.
  */
 static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
-		int blocks_to_boundary)
+				 int blocks_to_boundary)
 {
 	unsigned int count = 0;
 
@@ -613,9 +613,9 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks,
  *		direct blocks
  */
 static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, ext4_fsblk_t goal,
-				int indirect_blks, int blks,
-				ext4_fsblk_t new_blocks[4], int *err)
+			     ext4_lblk_t iblock, ext4_fsblk_t goal,
+			     int indirect_blks, int blks,
+			     ext4_fsblk_t new_blocks[4], int *err)
 {
 	struct ext4_allocation_request ar;
 	int target, i;
@@ -686,10 +686,10 @@ static int ext4_alloc_blocks(handle_t *handle, struct inode *inode,
 	}
 	if (!*err) {
 		if (target == blks) {
-		/*
-		 * save the new block number
-		 * for the first direct block
-		 */
+			/*
+			 * save the new block number
+			 * for the first direct block
+			 */
 			new_blocks[index] = current_block;
 		}
 		blk_allocated += ar.len;
@@ -731,9 +731,9 @@ failed_out:
  *	as described above and return 0.
  */
 static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
-				ext4_lblk_t iblock, int indirect_blks,
-				int *blks, ext4_fsblk_t goal,
-				ext4_lblk_t *offsets, Indirect *branch)
+			     ext4_lblk_t iblock, int indirect_blks,
+			     int *blks, ext4_fsblk_t goal,
+			     ext4_lblk_t *offsets, Indirect *branch)
 {
 	int blocksize = inode->i_sb->s_blocksize;
 	int i, n = 0;
@@ -780,7 +780,7 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 			 * the chain to point to the new allocated
 			 * data blocks numbers
 			 */
-			for (i=1; i < num; i++)
+			for (i = 1; i < num; i++)
 				*(branch[n].p + i) = cpu_to_le32(++current_block);
 		}
 		BUFFER_TRACE(bh, "marking uptodate");
@@ -823,7 +823,8 @@ failed:
  * chain to new block and return 0.
  */
 static int ext4_splice_branch(handle_t *handle, struct inode *inode,
-			ext4_lblk_t block, Indirect *where, int num, int blks)
+			      ext4_lblk_t block, Indirect *where, int num,
+			      int blks)
 {
 	int i;
 	int err = 0;
@@ -924,9 +925,9 @@ err_out:
  * blocks.
  */
 static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
-				  ext4_lblk_t iblock, unsigned int maxblocks,
-				  struct buffer_head *bh_result,
-				  int flags)
+			       ext4_lblk_t iblock, unsigned int maxblocks,
+			       struct buffer_head *bh_result,
+			       int flags)
 {
 	int err = -EIO;
 	ext4_lblk_t offsets[4];
@@ -942,7 +943,7 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL));
 	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
 	depth = ext4_block_to_path(inode, iblock, offsets,
-					&blocks_to_boundary);
+				   &blocks_to_boundary);
 
 	if (depth == 0)
 		goto out;
@@ -990,8 +991,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	 * Block out ext4_truncate while we alter the tree
 	 */
 	err = ext4_alloc_branch(handle, inode, iblock, indirect_blks,
-					&count, goal,
-					offsets + (partial - chain), partial);
+				&count, goal,
+				offsets + (partial - chain), partial);
 
 	/*
 	 * The ext4_splice_branch call will free and forget any buffers
@@ -1002,8 +1003,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
 	 */
 	if (!err)
 		err = ext4_splice_branch(handle, inode, iblock,
-					partial, indirect_blks, count);
-	else 
+					 partial, indirect_blks, count);
+	else
 		goto cleanup;
 
 	set_buffer_new(bh_result);
@@ -1175,7 +1176,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 	up_read((&EXT4_I(inode)->i_data_sem));
 
 	if (retval > 0 && buffer_mapped(bh)) {
-		int ret = check_block_validity(inode, block, 
+		int ret = check_block_validity(inode, block,
 					       bh->b_blocknr, retval);
 		if (ret != 0)
 			return ret;
@@ -1257,7 +1258,7 @@ int ext4_get_blocks(handle_t *handle, struct inode *inode, sector_t block,
 
 	up_write((&EXT4_I(inode)->i_data_sem));
 	if (retval > 0 && buffer_mapped(bh)) {
-		int ret = check_block_validity(inode, block, 
+		int ret = check_block_validity(inode, block,
 					       bh->b_blocknr, retval);
 		if (ret != 0)
 			return ret;
@@ -1408,8 +1409,7 @@ static int walk_page_buffers(handle_t *handle,
 
 	for (bh = head, block_start = 0;
 	     ret == 0 && (bh != head || !block_start);
-	     block_start = block_end, bh = next)
-	{
+	     block_start = block_end, bh = next) {
 		next = bh->b_this_page;
 		block_end = block_start + blocksize;
 		if (block_end <= from || block_start >= to) {
@@ -1450,7 +1450,7 @@ static int walk_page_buffers(handle_t *handle,
  * write.
  */
 static int do_journal_get_write_access(handle_t *handle,
-					struct buffer_head *bh)
+				       struct buffer_head *bh)
 {
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
@@ -1458,15 +1458,15 @@ static int do_journal_get_write_access(handle_t *handle,
 }
 
 static int ext4_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata)
+			    loff_t pos, unsigned len, unsigned flags,
+			    struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret, needed_blocks;
 	handle_t *handle;
 	int retries = 0;
 	struct page *page;
- 	pgoff_t index;
+	pgoff_t index;
 	unsigned from, to;
 
 	trace_ext4_write_begin(inode, pos, len, flags);
@@ -1475,7 +1475,7 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	 * we allocate blocks but write fails for some reason
 	 */
 	needed_blocks = ext4_writepage_trans_blocks(inode) + 1;
- 	index = pos >> PAGE_CACHE_SHIFT;
+	index = pos >> PAGE_CACHE_SHIFT;
 	from = pos & (PAGE_CACHE_SIZE - 1);
 	to = from + len;
 
@@ -1523,7 +1523,7 @@ retry:
 		ext4_journal_stop(handle);
 		if (pos + len > inode->i_size) {
 			vmtruncate(inode, inode->i_size);
-			/* 
+			/*
 			 * If vmtruncate failed early the inode might
 			 * still be on the orphan list; we need to
 			 * make sure the inode is removed from the
@@ -1550,9 +1550,9 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 }
 
 static int ext4_generic_write_end(struct file *file,
-				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				  struct address_space *mapping,
+				  loff_t pos, unsigned len, unsigned copied,
+				  struct page *page, void *fsdata)
 {
 	int i_size_changed = 0;
 	struct inode *inode = mapping->host;
@@ -1603,9 +1603,9 @@ static int ext4_generic_write_end(struct file *file,
  * buffers are managed internally.
  */
 static int ext4_ordered_write_end(struct file *file,
-				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				  struct address_space *mapping,
+				  loff_t pos, unsigned len, unsigned copied,
+				  struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
@@ -1633,7 +1633,7 @@ static int ext4_ordered_write_end(struct file *file,
 
 	if (pos + len > inode->i_size) {
 		vmtruncate(inode, inode->i_size);
-		/* 
+		/*
 		 * If vmtruncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
@@ -1647,9 +1647,9 @@ static int ext4_ordered_write_end(struct file *file,
 }
 
 static int ext4_writeback_write_end(struct file *file,
-				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				    struct address_space *mapping,
+				    loff_t pos, unsigned len, unsigned copied,
+				    struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
@@ -1675,7 +1675,7 @@ static int ext4_writeback_write_end(struct file *file,
 
 	if (pos + len > inode->i_size) {
 		vmtruncate(inode, inode->i_size);
-		/* 
+		/*
 		 * If vmtruncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
@@ -1688,9 +1688,9 @@ static int ext4_writeback_write_end(struct file *file,
 }
 
 static int ext4_journalled_write_end(struct file *file,
-				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				     struct address_space *mapping,
+				     loff_t pos, unsigned len, unsigned copied,
+				     struct page *page, void *fsdata)
 {
 	handle_t *handle = ext4_journal_current_handle();
 	struct inode *inode = mapping->host;
@@ -1738,7 +1738,7 @@ static int ext4_journalled_write_end(struct file *file,
 		ret = ret2;
 	if (pos + len > inode->i_size) {
 		vmtruncate(inode, inode->i_size);
-		/* 
+		/*
 		 * If vmtruncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
@@ -1845,7 +1845,7 @@ static void ext4_da_release_space(struct inode *inode, int to_free)
 }
 
 static void ext4_da_page_release_reservation(struct page *page,
-						unsigned long offset)
+					     unsigned long offset)
 {
 	int to_release = 0;
 	struct buffer_head *head, *bh;
@@ -2854,8 +2854,8 @@ static int ext4_nonda_switch(struct super_block *sb)
 }
 
 static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata)
+			       loff_t pos, unsigned len, unsigned flags,
+			       struct page **pagep, void **fsdata)
 {
 	int ret, retries = 0;
 	struct page *page;
@@ -2925,7 +2925,7 @@ out:
  * when write to the end of file but not require block allocation
  */
 static int ext4_da_should_update_i_disksize(struct page *page,
-					 unsigned long offset)
+					    unsigned long offset)
 {
 	struct buffer_head *bh;
 	struct inode *inode = page->mapping->host;
@@ -2944,9 +2944,9 @@ static int ext4_da_should_update_i_disksize(struct page *page,
 }
 
 static int ext4_da_write_end(struct file *file,
-				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len, unsigned copied,
+			     struct page *page, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret = 0, ret2;
@@ -3044,7 +3044,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
 	 * not strictly speaking necessary (and for users of
 	 * laptop_mode, not even desirable).  However, to do otherwise
 	 * would require replicating code paths in:
-	 * 
+	 *
 	 * ext4_da_writepages() ->
 	 *    write_cache_pages() ---> (via passed in callback function)
 	 *        __mpage_da_writepage() -->
@@ -3064,7 +3064,7 @@ int ext4_alloc_da_blocks(struct inode *inode)
 	 * write out the pages, but rather only collect contiguous
 	 * logical block extents, call the multi-block allocator, and
 	 * then update the buffer heads with the block allocations.
-	 * 
+	 *
 	 * For now, though, we'll cheat by calling filemap_flush(),
 	 * which will map the blocks, and start the I/O, but not
 	 * actually wait for the I/O to complete.
@@ -3200,7 +3200,7 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
  *
  */
 static int __ext4_normal_writepage(struct page *page,
-				struct writeback_control *wbc)
+				   struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 
@@ -3212,7 +3212,7 @@ static int __ext4_normal_writepage(struct page *page,
 }
 
 static int ext4_normal_writepage(struct page *page,
-				struct writeback_control *wbc)
+				 struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	loff_t size = i_size_read(inode);
@@ -3248,7 +3248,7 @@ static int ext4_normal_writepage(struct page *page,
 }
 
 static int __ext4_journalled_writepage(struct page *page,
-				struct writeback_control *wbc)
+				       struct writeback_control *wbc)
 {
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
@@ -3298,7 +3298,7 @@ out:
 }
 
 static int ext4_journalled_writepage(struct page *page,
-				struct writeback_control *wbc)
+				     struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	loff_t size = i_size_read(inode);
@@ -3401,8 +3401,8 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
  * VFS code falls back into buffered path in that case so we are safe.
  */
 static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
-			const struct iovec *iov, loff_t offset,
-			unsigned long nr_segs)
+			      const struct iovec *iov, loff_t offset,
+			      unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -3722,7 +3722,8 @@ static inline int all_zeroes(__le32 *p, __le32 *q)
  *			(no partially truncated stuff there).  */
 
 static Indirect *ext4_find_shared(struct inode *inode, int depth,
-			ext4_lblk_t offsets[4], Indirect chain[4], __le32 *top)
+				  ext4_lblk_t offsets[4], Indirect chain[4],
+				  __le32 *top)
 {
 	Indirect *partial, *p;
 	int k, err;
@@ -3778,8 +3779,10 @@ no_top:
  * than `count' because there can be holes in there.
  */
 static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
-		struct buffer_head *bh, ext4_fsblk_t block_to_free,
-		unsigned long count, __le32 *first, __le32 *last)
+			      struct buffer_head *bh,
+			      ext4_fsblk_t block_to_free,
+			      unsigned long count, __le32 *first,
+			      __le32 *last)
 {
 	__le32 *p;
 	if (try_to_extend_transaction(handle, inode)) {
@@ -3796,10 +3799,11 @@ static void ext4_clear_blocks(handle_t *handle, struct inode *inode,
 	}
 
 	/*
-	 * Any buffers which are on the journal will be in memory. We find
-	 * them on the hash table so jbd2_journal_revoke() will run jbd2_journal_forget()
-	 * on them.  We've already detached each block from the file, so
-	 * bforget() in jbd2_journal_forget() should be safe.
+	 * Any buffers which are on the journal will be in memory. We
+	 * find them on the hash table so jbd2_journal_revoke() will
+	 * run jbd2_journal_forget() on them.  We've already detached
+	 * each block from the file, so bforget() in
+	 * jbd2_journal_forget() should be safe.
 	 *
 	 * AKPM: turn on bforget in jbd2_journal_forget()!!!
 	 */
@@ -4171,7 +4175,7 @@ void ext4_truncate(struct inode *inode)
 				   (__le32*)partial->bh->b_data+addr_per_block,
 				   (chain+n-1) - partial);
 		BUFFER_TRACE(partial->bh, "call brelse");
-		brelse (partial->bh);
+		brelse(partial->bh);
 		partial--;
 	}
 do_indirects:
@@ -4412,8 +4416,9 @@ void ext4_get_inode_flags(struct ext4_inode_info *ei)
 	if (flags & S_DIRSYNC)
 		ei->i_flags |= EXT4_DIRSYNC_FL;
 }
+
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
-					struct ext4_inode_info *ei)
+				  struct ext4_inode_info *ei)
 {
 	blkcnt_t i_blocks ;
 	struct inode *inode = &(ei->vfs_inode);
@@ -4528,7 +4533,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 					EXT4_GOOD_OLD_INODE_SIZE +
 					ei->i_extra_isize;
 			if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC))
-				 ei->i_state |= EXT4_STATE_XATTR;
+				ei->i_state |= EXT4_STATE_XATTR;
 		}
 	} else
 		ei->i_extra_isize = 0;
@@ -4547,7 +4552,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 
 	ret = 0;
 	if (ei->i_file_acl &&
-	    ((ei->i_file_acl < 
+	    ((ei->i_file_acl <
 	      (le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) +
 	       EXT4_SB(sb)->s_gdb_count)) ||
 	     (ei->i_file_acl >= ext4_blocks_count(EXT4_SB(sb)->s_es)))) {
@@ -4562,15 +4567,15 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		     !ext4_inode_is_fast_symlink(inode)))
 			/* Validate extent which is part of inode */
 			ret = ext4_ext_check_inode(inode);
- 	} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+	} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 		   (S_ISLNK(inode->i_mode) &&
 		    !ext4_inode_is_fast_symlink(inode))) {
-	 	/* Validate block references which are part of inode */
+		/* Validate block references which are part of inode */
 		ret = ext4_check_inode_blockref(inode);
 	}
 	if (ret) {
- 		brelse(bh);
- 		goto bad_inode;
+		brelse(bh);
+		goto bad_inode;
 	}
 
 	if (S_ISREG(inode->i_mode)) {
@@ -4601,7 +4606,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	} else {
 		brelse(bh);
 		ret = -EIO;
-		ext4_error(inode->i_sb, __func__, 
+		ext4_error(inode->i_sb, __func__,
 			   "bogus i_mode (%o) for inode=%lu",
 			   inode->i_mode, inode->i_ino);
 		goto bad_inode;
@@ -4754,8 +4759,9 @@ static int ext4_do_update_inode(handle_t *handle,
 				cpu_to_le32(new_encode_dev(inode->i_rdev));
 			raw_inode->i_block[2] = 0;
 		}
-	} else for (block = 0; block < EXT4_N_BLOCKS; block++)
-		raw_inode->i_block[block] = ei->i_data[block];
+	} else
+		for (block = 0; block < EXT4_N_BLOCKS; block++)
+			raw_inode->i_block[block] = ei->i_data[block];
 
 	raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
 	if (ei->i_extra_isize) {
@@ -5109,7 +5115,7 @@ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks)
  * Give this, we know that the caller already has write access to iloc->bh.
  */
 int ext4_mark_iloc_dirty(handle_t *handle,
-		struct inode *inode, struct ext4_iloc *iloc)
+			 struct inode *inode, struct ext4_iloc *iloc)
 {
 	int err = 0;
 
-- 
cgit v1.2.3


From 4159175058987cb68aefd0e9eec2598b795363b4 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Mon, 15 Jun 2009 03:41:23 -0400
Subject: ext4: Don't update ctime for non-extent-mapped inodes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The VFS handles updating ctime, so we don't need to update the inode's
ctime in ext4_splace_branch() to update the direct or indirect blocks.
This was harmless when we did this in ext3, but in ext4, thanks to
delayed allocation, updating the ctime in ext4_splice_branch() can
cause the ctime to mysteriously jump when the blocks are finally
allocated.

Thanks to Björn Steinbrink for pointing out this problem on the git
mailing list.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8d0908afbd5b..7c17ae275af4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -856,10 +856,6 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	}
 
 	/* We are done with atomic stuff, now do the rest of housekeeping */
-
-	inode->i_ctime = ext4_current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-
 	/* had we spliced it onto indirect block? */
 	if (where->bh) {
 		/*
@@ -878,8 +874,8 @@ static int ext4_splice_branch(handle_t *handle, struct inode *inode,
 	} else {
 		/*
 		 * OK, we spliced it into the inode itself on a direct block.
-		 * Inode was dirtied above.
 		 */
+		ext4_mark_inode_dirty(handle, inode);
 		jbd_debug(5, "splicing direct\n");
 	}
 	return err;
-- 
cgit v1.2.3


From d4bfe2f76d785cc77611a4bda8cedaff358d8c7d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 8 Jun 2009 19:54:26 -0400
Subject: switch ext4 to inode->i_acl

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ext4/inode.c | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7c17ae275af4..60a26f3a6f8b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4453,10 +4453,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		return inode;
 
 	ei = EXT4_I(inode);
-#ifdef CONFIG_EXT4_FS_POSIX_ACL
-	ei->i_acl = EXT4_ACL_NOT_CACHED;
-	ei->i_default_acl = EXT4_ACL_NOT_CACHED;
-#endif
 
 	ret = __ext4_get_inode_loc(inode, &iloc, 0);
 	if (ret < 0)
-- 
cgit v1.2.3


From f4a01017d678fe4baecf480e79d7c4f4b7ebc772 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Sun, 5 Jul 2009 22:08:16 -0400
Subject: ext4: Fix potential reclaim deadlock when truncating partial block

The ext4_block_truncate_page() function previously called
grab_cache_page(), which called find_or_create_page() with the
__GFP_FS flag potentially set.  This could cause a deadlock if the
system is low on memory and it attempts a memory reclaim, which could
potentially call back into ext4.  So we need to call
find_or_create_page() directly, and remove the __GFP_FP flag to avoid
this potential deadlock.

Thanks to Roland Dreier for reporting a lockdep warning which showed
this problem.

[20786.363249] =================================
[20786.363257] [ INFO: inconsistent lock state ]
[20786.363265] 2.6.31-2-generic #14~rbd4gitd960eea9
[20786.363270] ---------------------------------
[20786.363276] inconsistent {IN-RECLAIM_FS-W} -> {RECLAIM_FS-ON-W} usage.
[20786.363285] http/8397 [HC0[0]:SC0[0]:HE1:SE1] takes:
[20786.363291]  (jbd2_handle){+.+.?.}, at: [<ffffffff812008bb>] jbd2_journal_start+0xdb/0x150
[20786.363314] {IN-RECLAIM_FS-W} state was registered at:
[20786.363320]   [<ffffffff8108bef6>] mark_irqflags+0xc6/0x1a0
[20786.363334]   [<ffffffff8108d347>] __lock_acquire+0x287/0x430
[20786.363345]   [<ffffffff8108d595>] lock_acquire+0xa5/0x150
[20786.363355]   [<ffffffff812008da>] jbd2_journal_start+0xfa/0x150
[20786.363365]   [<ffffffff811d98a8>] ext4_journal_start_sb+0x58/0x90
[20786.363377]   [<ffffffff811cce85>] ext4_delete_inode+0xc5/0x2c0
[20786.363389]   [<ffffffff81146fa3>] generic_delete_inode+0xd3/0x1a0
[20786.363401]   [<ffffffff81147095>] generic_drop_inode+0x25/0x30
[20786.363411]   [<ffffffff81145ce2>] iput+0x62/0x70
[20786.363420]   [<ffffffff81142878>] dentry_iput+0x98/0x110
[20786.363429]   [<ffffffff81142a00>] d_kill+0x50/0x80
[20786.363438]   [<ffffffff811444c5>] dput+0x95/0x180
[20786.363447]   [<ffffffff8120de4b>] ecryptfs_d_release+0x2b/0x70
[20786.363459]   [<ffffffff81142978>] d_free+0x28/0x60
[20786.363468]   [<ffffffff81142a18>] d_kill+0x68/0x80
[20786.363477]   [<ffffffff81142ad3>] prune_one_dentry+0xa3/0xc0
[20786.363487]   [<ffffffff81142d61>] __shrink_dcache_sb+0x271/0x290
[20786.363497]   [<ffffffff81142e89>] prune_dcache+0x109/0x1b0
[20786.363506]   [<ffffffff81142f6f>] shrink_dcache_memory+0x3f/0x50
[20786.363516]   [<ffffffff810f6d3d>] shrink_slab+0x12d/0x190
[20786.363527]   [<ffffffff810f97d7>] balance_pgdat+0x4d7/0x640
[20786.363537]   [<ffffffff810f9a57>] kswapd+0x117/0x170
[20786.363546]   [<ffffffff810773ce>] kthread+0x9e/0xb0
[20786.363558]   [<ffffffff8101430a>] child_rip+0xa/0x20
[20786.363569]   [<ffffffffffffffff>] 0xffffffffffffffff
[20786.363598] irq event stamp: 15997
[20786.363603] hardirqs last  enabled at (15997): [<ffffffff81125f9d>] kmem_cache_alloc+0xfd/0x1a0
[20786.363617] hardirqs last disabled at (15996): [<ffffffff81125f01>] kmem_cache_alloc+0x61/0x1a0
[20786.363628] softirqs last  enabled at (15966): [<ffffffff810631ea>] __do_softirq+0x14a/0x220
[20786.363641] softirqs last disabled at (15861): [<ffffffff8101440c>] call_softirq+0x1c/0x30
[20786.363651]
[20786.363653] other info that might help us debug this:
[20786.363660] 3 locks held by http/8397:
[20786.363665]  #0:  (&sb->s_type->i_mutex_key#8){+.+.+.}, at: [<ffffffff8112ed24>] do_truncate+0x64/0x90
[20786.363685]  #1:  (&sb->s_type->i_alloc_sem_key#5){+++++.}, at: [<ffffffff81147f90>] notify_change+0x250/0x350
[20786.363707]  #2:  (jbd2_handle){+.+.?.}, at: [<ffffffff812008bb>] jbd2_journal_start+0xdb/0x150
[20786.363724]
[20786.363726] stack backtrace:
[20786.363734] Pid: 8397, comm: http Tainted: G         C 2.6.31-2-generic #14~rbd4gitd960eea9
[20786.363741] Call Trace:
[20786.363752]  [<ffffffff8108ad7c>] print_usage_bug+0x18c/0x1a0
[20786.363763]  [<ffffffff8108b0c0>] ? check_usage_backwards+0x0/0xb0
[20786.363773]  [<ffffffff8108bad2>] mark_lock_irq+0xf2/0x280
[20786.363783]  [<ffffffff8108bd97>] mark_lock+0x137/0x1d0
[20786.363793]  [<ffffffff8108c03c>] mark_held_locks+0x6c/0xa0
[20786.363803]  [<ffffffff8108c11f>] lockdep_trace_alloc+0xaf/0xe0
[20786.363813]  [<ffffffff810efbac>] __alloc_pages_nodemask+0x7c/0x180
[20786.363824]  [<ffffffff810e9411>] ? find_get_page+0x91/0xf0
[20786.363835]  [<ffffffff8111d3b7>] alloc_pages_current+0x87/0xd0
[20786.363845]  [<ffffffff810e9827>] __page_cache_alloc+0x67/0x70
[20786.363856]  [<ffffffff810eb7df>] find_or_create_page+0x4f/0xb0
[20786.363867]  [<ffffffff811cb3be>] ext4_block_truncate_page+0x3e/0x460
[20786.363876]  [<ffffffff812008da>] ? jbd2_journal_start+0xfa/0x150
[20786.363885]  [<ffffffff812008bb>] ? jbd2_journal_start+0xdb/0x150
[20786.363895]  [<ffffffff811c6415>] ? ext4_meta_trans_blocks+0x75/0xf0
[20786.363905]  [<ffffffff811e8d8b>] ext4_ext_truncate+0x1bb/0x1e0
[20786.363916]  [<ffffffff811072c5>] ? unmap_mapping_range+0x75/0x290
[20786.363926]  [<ffffffff811ccc28>] ext4_truncate+0x498/0x630
[20786.363938]  [<ffffffff8129b4ce>] ? _raw_spin_unlock+0x5e/0xb0
[20786.363947]  [<ffffffff81107306>] ? unmap_mapping_range+0xb6/0x290
[20786.363957]  [<ffffffff8108c3ad>] ? trace_hardirqs_on+0xd/0x10
[20786.363966]  [<ffffffff811ffe58>] ? jbd2_journal_stop+0x1f8/0x2e0
[20786.363976]  [<ffffffff81107690>] vmtruncate+0xb0/0x110
[20786.363986]  [<ffffffff81147c05>] inode_setattr+0x35/0x170
[20786.363995]  [<ffffffff811c9906>] ext4_setattr+0x186/0x370
[20786.364005]  [<ffffffff81147eab>] notify_change+0x16b/0x350
[20786.364014]  [<ffffffff8112ed30>] do_truncate+0x70/0x90
[20786.364021]  [<ffffffff8112f48b>] T.657+0xeb/0x110
[20786.364021]  [<ffffffff8112f4be>] sys_ftruncate+0xe/0x10
[20786.364021]  [<ffffffff81013132>] system_call_fastpath+0x16/0x1b

Reported-by: Roland Dreier <roland@digitalvampire.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 60a26f3a6f8b..9760ba09275e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3583,7 +3583,8 @@ int ext4_block_truncate_page(handle_t *handle,
 	struct page *page;
 	int err = 0;
 
-	page = grab_cache_page(mapping, from >> PAGE_CACHE_SHIFT);
+	page = find_or_create_page(mapping, from >> PAGE_CACHE_SHIFT,
+				   mapping_gfp_mask(mapping) & ~__GFP_FS);
 	if (!page)
 		return -EINVAL;
 
-- 
cgit v1.2.3


From ffacfa7a79d6c00624196b2d13b0a7f72f2b8227 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 13 Jul 2009 16:22:22 -0400
Subject: ext4: Fix truncation of symlinks after failed write

Contents of long symlinks is written via standard write methods. So
when the write fails, we add inode to orphan list. But symlinks don't
have .truncate method defined so nobody properly removes them from the
on disk orphan list.

Fix this by calling ext4_truncate() directly instead of calling
vmtruncate() (which is saner anyway since we don't need anything
vmtruncate() does except from calling .truncate in these paths).  We
also add inode to orphan list only if ext4_can_truncate() is true
(currently, it can be false for symlinks when there are no blocks
allocated) - otherwise orphan list processing will complain and
ext4_truncate() will not remove inode from on-disk orphan list.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9760ba09275e..ff2afc1909b3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1513,14 +1513,14 @@ retry:
 		 * Add inode to orphan list in case we crash before
 		 * truncate finishes
 		 */
-		if (pos + len > inode->i_size)
+		if (pos + len > inode->i_size && ext4_can_truncate(inode))
 			ext4_orphan_add(handle, inode);
 
 		ext4_journal_stop(handle);
 		if (pos + len > inode->i_size) {
-			vmtruncate(inode, inode->i_size);
+			ext4_truncate(inode);
 			/*
-			 * If vmtruncate failed early the inode might
+			 * If truncate failed early the inode might
 			 * still be on the orphan list; we need to
 			 * make sure the inode is removed from the
 			 * orphan list in that case.
@@ -1614,7 +1614,7 @@ static int ext4_ordered_write_end(struct file *file,
 		ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 		copied = ret2;
-		if (pos + len > inode->i_size)
+		if (pos + len > inode->i_size && ext4_can_truncate(inode))
 			/* if we have allocated more blocks and copied
 			 * less. We will have blocks allocated outside
 			 * inode->i_size. So truncate them
@@ -1628,9 +1628,9 @@ static int ext4_ordered_write_end(struct file *file,
 		ret = ret2;
 
 	if (pos + len > inode->i_size) {
-		vmtruncate(inode, inode->i_size);
+		ext4_truncate(inode);
 		/*
-		 * If vmtruncate failed early the inode might still be
+		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
 		 */
@@ -1655,7 +1655,7 @@ static int ext4_writeback_write_end(struct file *file,
 	ret2 = ext4_generic_write_end(file, mapping, pos, len, copied,
 							page, fsdata);
 	copied = ret2;
-	if (pos + len > inode->i_size)
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1670,9 +1670,9 @@ static int ext4_writeback_write_end(struct file *file,
 		ret = ret2;
 
 	if (pos + len > inode->i_size) {
-		vmtruncate(inode, inode->i_size);
+		ext4_truncate(inode);
 		/*
-		 * If vmtruncate failed early the inode might still be
+		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
 		 */
@@ -1722,7 +1722,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 	unlock_page(page);
 	page_cache_release(page);
-	if (pos + len > inode->i_size)
+	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
 		 * inode->i_size. So truncate them
@@ -1733,9 +1733,9 @@ static int ext4_journalled_write_end(struct file *file,
 	if (!ret)
 		ret = ret2;
 	if (pos + len > inode->i_size) {
-		vmtruncate(inode, inode->i_size);
+		ext4_truncate(inode);
 		/*
-		 * If vmtruncate failed early the inode might still be
+		 * If truncate failed early the inode might still be
 		 * on the orphan list; we need to make sure the inode
 		 * is removed from the orphan list in that case.
 		 */
@@ -2907,7 +2907,7 @@ retry:
 		 * i_size_read because we hold i_mutex.
 		 */
 		if (pos + len > inode->i_size)
-			vmtruncate(inode, inode->i_size);
+			ext4_truncate(inode);
 	}
 
 	if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
-- 
cgit v1.2.3


From b767e78a179e5ab30fdbff1686d074ac270471eb Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Thu, 4 Jun 2009 08:06:06 -0400
Subject: ext4: Don't look at buffer_heads outside i_size.

Buffer heads outside i_size will be unmapped. So when we
are doing "walk_page_buffers" limit ourself to i_size.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reviewed-by: Josef Bacik <jbacik@redhat.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
----
---
 fs/ext4/inode.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ff2afc1909b3..b87b68cd3241 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2578,7 +2578,7 @@ static int ext4_da_writepage(struct page *page,
 		 * all are mapped and non delay. We don't want to
 		 * do block allocation here.
 		 */
-		ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
+		ret = block_prepare_write(page, 0, len,
 					  noalloc_get_block_write);
 		if (!ret) {
 			page_bufs = page_buffers(page);
@@ -2600,7 +2600,7 @@ static int ext4_da_writepage(struct page *page,
 			return 0;
 		}
 		/* now mark the buffer_heads as dirty and uptodate */
-		block_commit_write(page, 0, PAGE_CACHE_SIZE);
+		block_commit_write(page, 0, len);
 	}
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
@@ -3246,6 +3246,8 @@ static int ext4_normal_writepage(struct page *page,
 static int __ext4_journalled_writepage(struct page *page,
 				       struct writeback_control *wbc)
 {
+	loff_t size;
+	unsigned int len;
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
 	struct buffer_head *page_bufs;
@@ -3253,14 +3255,17 @@ static int __ext4_journalled_writepage(struct page *page,
 	int ret = 0;
 	int err;
 
-	ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
-				  noalloc_get_block_write);
+	size = i_size_read(inode);
+	if (page->index == size >> PAGE_CACHE_SHIFT)
+		len = size & ~PAGE_CACHE_MASK;
+	else
+		len = PAGE_CACHE_SIZE;
+	ret = block_prepare_write(page, 0, len, noalloc_get_block_write);
 	if (ret != 0)
 		goto out_unlock;
 
 	page_bufs = page_buffers(page);
-	walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL,
-								bget_one);
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
 	/* As soon as we unlock the page, it can go away, but we have
 	 * references to buffers so we are safe */
 	unlock_page(page);
@@ -3271,19 +3276,18 @@ static int __ext4_journalled_writepage(struct page *page,
 		goto out;
 	}
 
-	ret = walk_page_buffers(handle, page_bufs, 0,
-			PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
+	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				do_journal_get_write_access);
 
-	err = walk_page_buffers(handle, page_bufs, 0,
-				PAGE_CACHE_SIZE, NULL, write_end_fn);
+	err = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				write_end_fn);
 	if (ret == 0)
 		ret = err;
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;
 
-	walk_page_buffers(handle, page_bufs, 0,
-				PAGE_CACHE_SIZE, NULL, bput_one);
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
 	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
 	goto out;
 
-- 
cgit v1.2.3


From c364b22c9580a885e0f8c0d0f9710d67dc448958 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sun, 14 Jun 2009 17:57:10 -0400
Subject: ext4: Fix mmap/truncate race when blocksize < pagesize && delayed
 allocation

It is possible to see buffer_heads which are not mapped in the
writepage callback in the following scneario (where the fs blocksize
is 1k and the page size is 4k):

1) truncate(f, 1024)
2) mmap(f, 0, 4096)
3) a[0] = 'a'
4) truncate(f, 4096)
5) writepage(...)

Now if we get a writepage callback immediately after (4) and before an
attempt to write at any other offset via mmap address (which implies we
are yet to get a pagefault and do a get_block) what we would have is the
page which is dirty have first block allocated and the other three
buffer_heads unmapped.

In the above case the writepage should go ahead and try to write the
first blocks and clear the page_dirty flag. Further attempts to write
to the page will again create a fault and result in allocating blocks
and marking page dirty.  If we don't write any other offset via mmap
address we would still have written the first block to the disk and
rest of the space will be considered as a hole.

So to address this, we change all of the places where we look for
delayed, unmapped, or unwritten buffer heads, and only check for
delayed or unwritten buffer heads instead.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 23 ++++++++---------------
 1 file changed, 8 insertions(+), 15 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index b87b68cd3241..1275f34589c7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2305,15 +2305,9 @@ flush_it:
 	return;
 }
 
-static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
+static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
 {
-	/*
-	 * unmapped buffer is possible for holes.
-	 * delay buffer is possible with delayed allocation.
-	 * We also need to consider unwritten buffer as unmapped.
-	 */
-	return (!buffer_mapped(bh) || buffer_delay(bh) ||
-				buffer_unwritten(bh)) && buffer_dirty(bh);
+	return (buffer_delay(bh) || buffer_unwritten(bh)) && buffer_dirty(bh);
 }
 
 /*
@@ -2400,7 +2394,7 @@ static int __mpage_da_writepage(struct page *page,
 			 * Otherwise we won't make progress
 			 * with the page in ext4_da_writepage
 			 */
-			if (ext4_bh_unmapped_or_delay(NULL, bh)) {
+			if (ext4_bh_delay_or_unwritten(NULL, bh)) {
 				mpage_add_bh_to_extent(mpd, logical,
 						       bh->b_size,
 						       bh->b_state);
@@ -2517,7 +2511,6 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 	 * so call get_block_wrap with create = 0
 	 */
 	ret = ext4_get_blocks(NULL, inode, iblock, max_blocks, bh_result, 0);
-	BUG_ON(create && ret == 0);
 	if (ret > 0) {
 		bh_result->b_size = (ret << inode->i_blkbits);
 		ret = 0;
@@ -2533,7 +2526,7 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
  *   - grab_page_cache when doing write_begin (have journal handle)
  */
 static int ext4_da_writepage(struct page *page,
-				struct writeback_control *wbc)
+			     struct writeback_control *wbc)
 {
 	int ret = 0;
 	loff_t size;
@@ -2551,7 +2544,7 @@ static int ext4_da_writepage(struct page *page,
 	if (page_has_buffers(page)) {
 		page_bufs = page_buffers(page);
 		if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
-					ext4_bh_unmapped_or_delay)) {
+					ext4_bh_delay_or_unwritten)) {
 			/*
 			 * We don't want to do  block allocation
 			 * So redirty the page and return
@@ -2584,7 +2577,7 @@ static int ext4_da_writepage(struct page *page,
 			page_bufs = page_buffers(page);
 			/* check whether all are mapped and non delay */
 			if (walk_page_buffers(NULL, page_bufs, 0, len, NULL,
-						ext4_bh_unmapped_or_delay)) {
+						ext4_bh_delay_or_unwritten)) {
 				redirty_page_for_writepage(wbc, page);
 				unlock_page(page);
 				return 0;
@@ -3232,7 +3225,7 @@ static int ext4_normal_writepage(struct page *page,
 		 * happily proceed with mapping them and writing the page.
 		 */
 		BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-					ext4_bh_unmapped_or_delay));
+					ext4_bh_delay_or_unwritten));
 	}
 
 	if (!ext4_journal_current_handle())
@@ -3322,7 +3315,7 @@ static int ext4_journalled_writepage(struct page *page,
 		 * happily proceed with mapping them and writing the page.
 		 */
 		BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-					ext4_bh_unmapped_or_delay));
+					ext4_bh_delay_or_unwritten));
 	}
 
 	if (ext4_journal_current_handle())
-- 
cgit v1.2.3


From 43ce1d23b43330634507a049b55c36e91d27282e Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sun, 14 Jun 2009 17:58:45 -0400
Subject: ext4: Fix mmap/truncate race when blocksize < pagesize && !nodellaoc

This patch fixes the mmap/truncate race that was fixed for delayed
allocation by merging ext4_{journalled,normal,da}_writepage() into
ext4_writepage().

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 234 ++++++++++++++------------------------------------------
 1 file changed, 57 insertions(+), 177 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1275f34589c7..97c48b5b0578 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -47,6 +47,10 @@
 
 #define MPAGE_DA_EXTENT_TAIL 0x01
 
+static int __ext4_journalled_writepage(struct page *page,
+				       struct writeback_control *wbc,
+				       unsigned int len);
+
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
@@ -2392,7 +2396,7 @@ static int __mpage_da_writepage(struct page *page,
 			 * We need to try to allocate
 			 * unmapped blocks in the same page.
 			 * Otherwise we won't make progress
-			 * with the page in ext4_da_writepage
+			 * with the page in ext4_writepage
 			 */
 			if (ext4_bh_delay_or_unwritten(NULL, bh)) {
 				mpage_add_bh_to_extent(mpd, logical,
@@ -2519,13 +2523,47 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 }
 
 /*
+ * Note that we don't need to start a transaction unless we're journaling data
+ * because we should have holes filled from ext4_page_mkwrite(). We even don't
+ * need to file the inode to the transaction's list in ordered mode because if
+ * we are writing back data added by write(), the inode is already there and if
+ * we are writing back data modified via mmap(), noone guarantees in which
+ * transaction the data will hit the disk. In case we are journaling data, we
+ * cannot start transaction directly because transaction start ranks above page
+ * lock so we have to do some magic.
+ *
  * This function can get called via...
  *   - ext4_da_writepages after taking page lock (have journal handle)
  *   - journal_submit_inode_data_buffers (no journal handle)
  *   - shrink_page_list via pdflush (no journal handle)
  *   - grab_page_cache when doing write_begin (have journal handle)
+ *
+ * We don't do any block allocation in this function. If we have page with
+ * multiple blocks we need to write those buffer_heads that are mapped. This
+ * is important for mmaped based write. So if we do with blocksize 1K
+ * truncate(f, 1024);
+ * a = mmap(f, 0, 4096);
+ * a[0] = 'a';
+ * truncate(f, 4096);
+ * we have in the page first buffer_head mapped via page_mkwrite call back
+ * but other bufer_heads would be unmapped but dirty(dirty done via the
+ * do_wp_page). So writepage should write the first block. If we modify
+ * the mmap area beyond 1024 we will again get a page_fault and the
+ * page_mkwrite callback will do the block allocation and mark the
+ * buffer_heads mapped.
+ *
+ * We redirty the page if we have any buffer_heads that is either delay or
+ * unwritten in the page.
+ *
+ * We can get recursively called as show below.
+ *
+ *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
+ *		ext4_writepage()
+ *
+ * But since we don't do any block allocation we should not deadlock.
+ * Page also have the dirty flag cleared so we don't get recurive page_lock.
  */
-static int ext4_da_writepage(struct page *page,
+static int ext4_writepage(struct page *page,
 			     struct writeback_control *wbc)
 {
 	int ret = 0;
@@ -2534,7 +2572,7 @@ static int ext4_da_writepage(struct page *page,
 	struct buffer_head *page_bufs;
 	struct inode *inode = page->mapping->host;
 
-	trace_ext4_da_writepage(inode, page);
+	trace_ext4_writepage(inode, page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_CACHE_SHIFT)
 		len = size & ~PAGE_CACHE_MASK;
@@ -2596,6 +2634,15 @@ static int ext4_da_writepage(struct page *page,
 		block_commit_write(page, 0, len);
 	}
 
+	if (PageChecked(page) && ext4_should_journal_data(inode)) {
+		/*
+		 * It's mmapped pagecache.  Add buffers and journal it.  There
+		 * doesn't seem much point in redirtying the page here.
+		 */
+		ClearPageChecked(page);
+		return __ext4_journalled_writepage(page, wbc, len);
+	}
+
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
 		ret = nobh_writepage(page, noalloc_get_block_write, wbc);
 	else
@@ -3135,112 +3182,10 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
 	return 0;
 }
 
-/*
- * Note that we don't need to start a transaction unless we're journaling data
- * because we should have holes filled from ext4_page_mkwrite(). We even don't
- * need to file the inode to the transaction's list in ordered mode because if
- * we are writing back data added by write(), the inode is already there and if
- * we are writing back data modified via mmap(), noone guarantees in which
- * transaction the data will hit the disk. In case we are journaling data, we
- * cannot start transaction directly because transaction start ranks above page
- * lock so we have to do some magic.
- *
- * In all journaling modes block_write_full_page() will start the I/O.
- *
- * Problem:
- *
- *	ext4_writepage() -> kmalloc() -> __alloc_pages() -> page_launder() ->
- *		ext4_writepage()
- *
- * Similar for:
- *
- *	ext4_file_write() -> generic_file_write() -> __alloc_pages() -> ...
- *
- * Same applies to ext4_get_block().  We will deadlock on various things like
- * lock_journal and i_data_sem
- *
- * Setting PF_MEMALLOC here doesn't work - too many internal memory
- * allocations fail.
- *
- * 16May01: If we're reentered then journal_current_handle() will be
- *	    non-zero. We simply *return*.
- *
- * 1 July 2001: @@@ FIXME:
- *   In journalled data mode, a data buffer may be metadata against the
- *   current transaction.  But the same file is part of a shared mapping
- *   and someone does a writepage() on it.
- *
- *   We will move the buffer onto the async_data list, but *after* it has
- *   been dirtied. So there's a small window where we have dirty data on
- *   BJ_Metadata.
- *
- *   Note that this only applies to the last partial page in the file.  The
- *   bit which block_write_full_page() uses prepare/commit for.  (That's
- *   broken code anyway: it's wrong for msync()).
- *
- *   It's a rare case: affects the final partial page, for journalled data
- *   where the file is subject to bith write() and writepage() in the same
- *   transction.  To fix it we'll need a custom block_write_full_page().
- *   We'll probably need that anyway for journalling writepage() output.
- *
- * We don't honour synchronous mounts for writepage().  That would be
- * disastrous.  Any write() or metadata operation will sync the fs for
- * us.
- *
- */
-static int __ext4_normal_writepage(struct page *page,
-				   struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-
-	if (test_opt(inode->i_sb, NOBH))
-		return nobh_writepage(page, noalloc_get_block_write, wbc);
-	else
-		return block_write_full_page(page, noalloc_get_block_write,
-					     wbc);
-}
-
-static int ext4_normal_writepage(struct page *page,
-				 struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	loff_t size = i_size_read(inode);
-	loff_t len;
-
-	trace_ext4_normal_writepage(inode, page);
-	J_ASSERT(PageLocked(page));
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
-	else
-		len = PAGE_CACHE_SIZE;
-
-	if (page_has_buffers(page)) {
-		/* if page has buffers it should all be mapped
-		 * and allocated. If there are not buffers attached
-		 * to the page we know the page is dirty but it lost
-		 * buffers. That means that at some moment in time
-		 * after write_begin() / write_end() has been called
-		 * all buffers have been clean and thus they must have been
-		 * written at least once. So they are all mapped and we can
-		 * happily proceed with mapping them and writing the page.
-		 */
-		BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-					ext4_bh_delay_or_unwritten));
-	}
-
-	if (!ext4_journal_current_handle())
-		return __ext4_normal_writepage(page, wbc);
-
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-	return 0;
-}
-
 static int __ext4_journalled_writepage(struct page *page,
-				       struct writeback_control *wbc)
+				       struct writeback_control *wbc,
+				       unsigned int len)
 {
-	loff_t size;
-	unsigned int len;
 	struct address_space *mapping = page->mapping;
 	struct inode *inode = mapping->host;
 	struct buffer_head *page_bufs;
@@ -3248,16 +3193,8 @@ static int __ext4_journalled_writepage(struct page *page,
 	int ret = 0;
 	int err;
 
-	size = i_size_read(inode);
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
-	else
-		len = PAGE_CACHE_SIZE;
-	ret = block_prepare_write(page, 0, len, noalloc_get_block_write);
-	if (ret != 0)
-		goto out_unlock;
-
 	page_bufs = page_buffers(page);
+	BUG_ON(!page_bufs);
 	walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
 	/* As soon as we unlock the page, it can go away, but we have
 	 * references to buffers so we are safe */
@@ -3282,67 +3219,10 @@ static int __ext4_journalled_writepage(struct page *page,
 
 	walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
 	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
-	goto out;
-
-out_unlock:
-	unlock_page(page);
 out:
 	return ret;
 }
 
-static int ext4_journalled_writepage(struct page *page,
-				     struct writeback_control *wbc)
-{
-	struct inode *inode = page->mapping->host;
-	loff_t size = i_size_read(inode);
-	loff_t len;
-
-	trace_ext4_journalled_writepage(inode, page);
-	J_ASSERT(PageLocked(page));
-	if (page->index == size >> PAGE_CACHE_SHIFT)
-		len = size & ~PAGE_CACHE_MASK;
-	else
-		len = PAGE_CACHE_SIZE;
-
-	if (page_has_buffers(page)) {
-		/* if page has buffers it should all be mapped
-		 * and allocated. If there are not buffers attached
-		 * to the page we know the page is dirty but it lost
-		 * buffers. That means that at some moment in time
-		 * after write_begin() / write_end() has been called
-		 * all buffers have been clean and thus they must have been
-		 * written at least once. So they are all mapped and we can
-		 * happily proceed with mapping them and writing the page.
-		 */
-		BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
-					ext4_bh_delay_or_unwritten));
-	}
-
-	if (ext4_journal_current_handle())
-		goto no_write;
-
-	if (PageChecked(page)) {
-		/*
-		 * It's mmapped pagecache.  Add buffers and journal it.  There
-		 * doesn't seem much point in redirtying the page here.
-		 */
-		ClearPageChecked(page);
-		return __ext4_journalled_writepage(page, wbc);
-	} else {
-		/*
-		 * It may be a page full of checkpoint-mode buffers.  We don't
-		 * really know unless we go poke around in the buffer_heads.
-		 * But block_write_full_page will do the right thing.
-		 */
-		return block_write_full_page(page, noalloc_get_block_write,
-					     wbc);
-	}
-no_write:
-	redirty_page_for_writepage(wbc, page);
-	unlock_page(page);
-	return 0;
-}
-
 static int ext4_readpage(struct file *file, struct page *page)
 {
 	return mpage_readpage(page, ext4_get_block);
@@ -3489,7 +3369,7 @@ static int ext4_journalled_set_page_dirty(struct page *page)
 static const struct address_space_operations ext4_ordered_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_normal_writepage,
+	.writepage		= ext4_writepage,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_ordered_write_end,
@@ -3504,7 +3384,7 @@ static const struct address_space_operations ext4_ordered_aops = {
 static const struct address_space_operations ext4_writeback_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_normal_writepage,
+	.writepage		= ext4_writepage,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_writeback_write_end,
@@ -3519,7 +3399,7 @@ static const struct address_space_operations ext4_writeback_aops = {
 static const struct address_space_operations ext4_journalled_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_journalled_writepage,
+	.writepage		= ext4_writepage,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_write_begin,
 	.write_end		= ext4_journalled_write_end,
@@ -3533,7 +3413,7 @@ static const struct address_space_operations ext4_journalled_aops = {
 static const struct address_space_operations ext4_da_aops = {
 	.readpage		= ext4_readpage,
 	.readpages		= ext4_readpages,
-	.writepage		= ext4_da_writepage,
+	.writepage		= ext4_writepage,
 	.writepages		= ext4_da_writepages,
 	.sync_page		= block_sync_page,
 	.write_begin		= ext4_da_write_begin,
-- 
cgit v1.2.3


From 62e086be5d2abef8cad854bc5707329ad345f2ec Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sun, 14 Jun 2009 17:59:34 -0400
Subject: ext4: Move __ext4_journalled_writepage() to avoid forward declaration

In addition, fix two unused variable warnings.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 112 +++++++++++++++++++++++++++-----------------------------
 1 file changed, 54 insertions(+), 58 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 97c48b5b0578..c98e3afea30a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -47,10 +47,6 @@
 
 #define MPAGE_DA_EXTENT_TAIL 0x01
 
-static int __ext4_journalled_writepage(struct page *page,
-				       struct writeback_control *wbc,
-				       unsigned int len);
-
 static inline int ext4_begin_ordered_truncate(struct inode *inode,
 					      loff_t new_size)
 {
@@ -2522,6 +2518,59 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
 	return ret;
 }
 
+static int bget_one(handle_t *handle, struct buffer_head *bh)
+{
+	get_bh(bh);
+	return 0;
+}
+
+static int bput_one(handle_t *handle, struct buffer_head *bh)
+{
+	put_bh(bh);
+	return 0;
+}
+
+static int __ext4_journalled_writepage(struct page *page,
+				       struct writeback_control *wbc,
+				       unsigned int len)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+	struct buffer_head *page_bufs;
+	handle_t *handle = NULL;
+	int ret = 0;
+	int err;
+
+	page_bufs = page_buffers(page);
+	BUG_ON(!page_bufs);
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
+	/* As soon as we unlock the page, it can go away, but we have
+	 * references to buffers so we are safe */
+	unlock_page(page);
+
+	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out;
+	}
+
+	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				do_journal_get_write_access);
+
+	err = walk_page_buffers(handle, page_bufs, 0, len, NULL,
+				write_end_fn);
+	if (ret == 0)
+		ret = err;
+	err = ext4_journal_stop(handle);
+	if (!ret)
+		ret = err;
+
+	walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
+	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
+out:
+	return ret;
+}
+
 /*
  * Note that we don't need to start a transaction unless we're journaling data
  * because we should have holes filled from ext4_page_mkwrite(). We even don't
@@ -2564,7 +2613,7 @@ static int noalloc_get_block_write(struct inode *inode, sector_t iblock,
  * Page also have the dirty flag cleared so we don't get recurive page_lock.
  */
 static int ext4_writepage(struct page *page,
-			     struct writeback_control *wbc)
+			  struct writeback_control *wbc)
 {
 	int ret = 0;
 	loff_t size;
@@ -3170,59 +3219,6 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, ext4_get_block);
 }
 
-static int bget_one(handle_t *handle, struct buffer_head *bh)
-{
-	get_bh(bh);
-	return 0;
-}
-
-static int bput_one(handle_t *handle, struct buffer_head *bh)
-{
-	put_bh(bh);
-	return 0;
-}
-
-static int __ext4_journalled_writepage(struct page *page,
-				       struct writeback_control *wbc,
-				       unsigned int len)
-{
-	struct address_space *mapping = page->mapping;
-	struct inode *inode = mapping->host;
-	struct buffer_head *page_bufs;
-	handle_t *handle = NULL;
-	int ret = 0;
-	int err;
-
-	page_bufs = page_buffers(page);
-	BUG_ON(!page_bufs);
-	walk_page_buffers(handle, page_bufs, 0, len, NULL, bget_one);
-	/* As soon as we unlock the page, it can go away, but we have
-	 * references to buffers so we are safe */
-	unlock_page(page);
-
-	handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode));
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		goto out;
-	}
-
-	ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
-				do_journal_get_write_access);
-
-	err = walk_page_buffers(handle, page_bufs, 0, len, NULL,
-				write_end_fn);
-	if (ret == 0)
-		ret = err;
-	err = ext4_journal_stop(handle);
-	if (!ret)
-		ret = err;
-
-	walk_page_buffers(handle, page_bufs, 0, len, NULL, bput_one);
-	EXT4_I(inode)->i_state |= EXT4_STATE_JDATA;
-out:
-	return ret;
-}
-
 static int ext4_readpage(struct file *file, struct page *page)
 {
 	return mpage_readpage(page, ext4_get_block);
-- 
cgit v1.2.3


From e6b5d30104db5f34110678ecab14988f1f1eff63 Mon Sep 17 00:00:00 2001
From: Curt Wohlgemuth <curtw@google.com>
Date: Mon, 13 Jul 2009 09:07:20 -0400
Subject: ext4: Fix buffer head reference leak in no-journal mode

We found a problem with buffer head reference leaks when using an ext4
partition without a journal.  In particular, calls to ext4_forget() would
not to a brelse() on the input buffer head, which will cause pages they
belong to to not be reclaimable.

Further investigation showed that all places where ext4_journal_forget() and
ext4_journal_revoke() are called are subject to the same problem.  The patch
below changes __ext4_journal_forget/__ext4_journal_revoke to do an explicit
release of the buffer head when the journal handle isn't valid.

Signed-off-by: Curt Wohlgemuth <curtw@google.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/inode.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

(limited to 'fs/ext4/inode.c')

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c98e3afea30a..f9c642b22efa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -78,16 +78,14 @@ static int ext4_inode_is_fast_symlink(struct inode *inode)
  * but there may still be a record of it in the journal, and that record
  * still needs to be revoked.
  *
- * If the handle isn't valid we're not journaling so there's nothing to do.
+ * If the handle isn't valid we're not journaling, but we still need to
+ * call into ext4_journal_revoke() to put the buffer head.
  */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 		struct buffer_head *bh, ext4_fsblk_t blocknr)
 {
 	int err;
 
-	if (!ext4_handle_valid(handle))
-		return 0;
-
 	might_sleep();
 
 	BUFFER_TRACE(bh, "enter");
-- 
cgit v1.2.3