From d7eecb483cc29e929bbc5515b8def830d7fc6ad2 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@caiaq.de>
Date: Thu, 28 Jan 2010 16:13:01 +0800
Subject: jfs_dmap.[ch]: trivial typo fix: s/heigth/height/g
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Daniel Mack <daniel@caiaq.de>
Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: Jiri Kosina <trivial@kernel.org>
Cc: André Goddard Rosa <andre.goddard@gmail.com>
Cc: jfs-discussion@lists.sourceforge.net
---
 fs/jfs/jfs_dmap.c | 16 ++++++++--------
 fs/jfs/jfs_dmap.h |  6 +++---
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'fs')

diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index d9b031cf69f..7e19d2fe009 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -195,7 +195,7 @@ int dbMount(struct inode *ipbmap)
 	bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag);
 	bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref);
 	bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel);
-	bmp->db_agheigth = le32_to_cpu(dbmp_le->dn_agheigth);
+	bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight);
 	bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth);
 	bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart);
 	bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size);
@@ -287,7 +287,7 @@ int dbSync(struct inode *ipbmap)
 	dbmp_le->dn_maxag = cpu_to_le32(bmp->db_maxag);
 	dbmp_le->dn_agpref = cpu_to_le32(bmp->db_agpref);
 	dbmp_le->dn_aglevel = cpu_to_le32(bmp->db_aglevel);
-	dbmp_le->dn_agheigth = cpu_to_le32(bmp->db_agheigth);
+	dbmp_le->dn_agheight = cpu_to_le32(bmp->db_agheight);
 	dbmp_le->dn_agwidth = cpu_to_le32(bmp->db_agwidth);
 	dbmp_le->dn_agstart = cpu_to_le32(bmp->db_agstart);
 	dbmp_le->dn_agl2size = cpu_to_le32(bmp->db_agl2size);
@@ -1440,7 +1440,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
 	 * tree index of this allocation group within the control page.
 	 */
 	agperlev =
-	    (1 << (L2LPERCTL - (bmp->db_agheigth << 1))) / bmp->db_agwidth;
+	    (1 << (L2LPERCTL - (bmp->db_agheight << 1))) / bmp->db_agwidth;
 	ti = bmp->db_agstart + bmp->db_agwidth * (agno & (agperlev - 1));
 
 	/* dmap control page trees fan-out by 4 and a single allocation
@@ -1459,7 +1459,7 @@ dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results)
 		 * the subtree to find the leftmost leaf that describes this
 		 * free space.
 		 */
-		for (k = bmp->db_agheigth; k > 0; k--) {
+		for (k = bmp->db_agheight; k > 0; k--) {
 			for (n = 0, m = (ti << 2) + 1; n < 4; n++) {
 				if (l2nb <= dcp->stree[m + n]) {
 					ti = m + n;
@@ -3606,7 +3606,7 @@ void dbFinalizeBmap(struct inode *ipbmap)
 	}
 
 	/*
-	 * compute db_aglevel, db_agheigth, db_width, db_agstart:
+	 * compute db_aglevel, db_agheight, db_width, db_agstart:
 	 * an ag is covered in aglevel dmapctl summary tree,
 	 * at agheight level height (from leaf) with agwidth number of nodes
 	 * each, which starts at agstart index node of the smmary tree node
@@ -3615,9 +3615,9 @@ void dbFinalizeBmap(struct inode *ipbmap)
 	bmp->db_aglevel = BMAPSZTOLEV(bmp->db_agsize);
 	l2nl =
 	    bmp->db_agl2size - (L2BPERDMAP + bmp->db_aglevel * L2LPERCTL);
-	bmp->db_agheigth = l2nl >> 1;
-	bmp->db_agwidth = 1 << (l2nl - (bmp->db_agheigth << 1));
-	for (i = 5 - bmp->db_agheigth, bmp->db_agstart = 0, n = 1; i > 0;
+	bmp->db_agheight = l2nl >> 1;
+	bmp->db_agwidth = 1 << (l2nl - (bmp->db_agheight << 1));
+	for (i = 5 - bmp->db_agheight, bmp->db_agstart = 0, n = 1; i > 0;
 	     i--) {
 		bmp->db_agstart += n;
 		n <<= 2;
diff --git a/fs/jfs/jfs_dmap.h b/fs/jfs/jfs_dmap.h
index 1a6eb41569b..6dcb906c55d 100644
--- a/fs/jfs/jfs_dmap.h
+++ b/fs/jfs/jfs_dmap.h
@@ -210,7 +210,7 @@ struct dbmap_disk {
 	__le32 dn_maxag;	/* 4: max active alloc group number	*/
 	__le32 dn_agpref;	/* 4: preferred alloc group (hint)	*/
 	__le32 dn_aglevel;	/* 4: dmapctl level holding the AG	*/
-	__le32 dn_agheigth;	/* 4: height in dmapctl of the AG	*/
+	__le32 dn_agheight;	/* 4: height in dmapctl of the AG	*/
 	__le32 dn_agwidth;	/* 4: width in dmapctl of the AG	*/
 	__le32 dn_agstart;	/* 4: start tree index at AG height	*/
 	__le32 dn_agl2size;	/* 4: l2 num of blks per alloc group	*/
@@ -229,7 +229,7 @@ struct dbmap {
 	int dn_maxag;		/* max active alloc group number	*/
 	int dn_agpref;		/* preferred alloc group (hint)		*/
 	int dn_aglevel;		/* dmapctl level holding the AG		*/
-	int dn_agheigth;	/* height in dmapctl of the AG		*/
+	int dn_agheight;	/* height in dmapctl of the AG		*/
 	int dn_agwidth;		/* width in dmapctl of the AG		*/
 	int dn_agstart;		/* start tree index at AG height	*/
 	int dn_agl2size;	/* l2 num of blks per alloc group	*/
@@ -255,7 +255,7 @@ struct bmap {
 #define	db_agsize	db_bmap.dn_agsize
 #define	db_agl2size	db_bmap.dn_agl2size
 #define	db_agwidth	db_bmap.dn_agwidth
-#define	db_agheigth	db_bmap.dn_agheigth
+#define	db_agheight	db_bmap.dn_agheight
 #define	db_agstart	db_bmap.dn_agstart
 #define	db_numag	db_bmap.dn_numag
 #define	db_maxlevel	db_bmap.dn_maxlevel
-- 
cgit v1.2.3-18-g5258


From 8bf8c376ab2eefaf0386f4e003e720e1434fa43d Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Wed, 3 Mar 2010 06:28:06 +0300
Subject: blkdev: fix merge_bvec_fn return value checks v2

merge_bvec_fn() returns bvec->bv_len on success. So we have to check
against this value. But in case of fs_optimization merge we compare
with wrong value. This patch must be included in
 b428cd6da7e6559aca69aa2e3a526037d3f20403
But accidentally i've forgot to add this in the initial patch.
To make things straight let's replace all such checks.
In fact this makes code easy to understand.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 fs/bio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/bio.c b/fs/bio.c
index dc17afd672e..d89e0199dc0 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -555,7 +555,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 					.bi_rw = bio->bi_rw,
 				};
 
-				if (q->merge_bvec_fn(q, &bvm, prev) < len) {
+				if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
 					prev->bv_len -= len;
 					return 0;
 				}
@@ -608,7 +608,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
+		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
 			bvec->bv_page = NULL;
 			bvec->bv_len = 0;
 			bvec->bv_offset = 0;
-- 
cgit v1.2.3-18-g5258


From f11c9c5c259cb2c3d698548dc3936f773ab1f5b9 Mon Sep 17 00:00:00 2001
From: Edward Shishkin <edward.shishkin@gmail.com>
Date: Thu, 11 Mar 2010 14:09:47 -0800
Subject: vfs: improve writeback_inodes_wb()

Do not pin/unpin superblock for every inode in writeback_inodes_wb(), pin
it for the whole group of inodes which belong to the same superblock and
call writeback_sb_inodes() handler for them.

Signed-off-by: Edward Shishkin <edward.shishkin@gmail.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 fs/fs-writeback.c | 133 ++++++++++++++++++++++++++++++------------------------
 1 file changed, 73 insertions(+), 60 deletions(-)

(limited to 'fs')

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 76fc4d594ac..6841effa47c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -553,108 +553,85 @@ select_queue:
 	return ret;
 }
 
-static void unpin_sb_for_writeback(struct super_block **psb)
+static void unpin_sb_for_writeback(struct super_block *sb)
 {
-	struct super_block *sb = *psb;
-
-	if (sb) {
-		up_read(&sb->s_umount);
-		put_super(sb);
-		*psb = NULL;
-	}
+	up_read(&sb->s_umount);
+	put_super(sb);
 }
 
+enum sb_pin_state {
+	SB_PINNED,
+	SB_NOT_PINNED,
+	SB_PIN_FAILED
+};
+
 /*
  * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
  * before calling writeback. So make sure that we do pin it, so it doesn't
  * go away while we are writing inodes from it.
- *
- * Returns 0 if the super was successfully pinned (or pinning wasn't needed),
- * 1 if we failed.
  */
-static int pin_sb_for_writeback(struct writeback_control *wbc,
-				struct inode *inode, struct super_block **psb)
+static enum sb_pin_state pin_sb_for_writeback(struct writeback_control *wbc,
+					      struct super_block *sb)
 {
-	struct super_block *sb = inode->i_sb;
-
-	/*
-	 * If this sb is already pinned, nothing more to do. If not and
-	 * *psb is non-NULL, unpin the old one first
-	 */
-	if (sb == *psb)
-		return 0;
-	else if (*psb)
-		unpin_sb_for_writeback(psb);
-
 	/*
 	 * Caller must already hold the ref for this
 	 */
 	if (wbc->sync_mode == WB_SYNC_ALL) {
 		WARN_ON(!rwsem_is_locked(&sb->s_umount));
-		return 0;
+		return SB_NOT_PINNED;
 	}
-
 	spin_lock(&sb_lock);
 	sb->s_count++;
 	if (down_read_trylock(&sb->s_umount)) {
 		if (sb->s_root) {
 			spin_unlock(&sb_lock);
-			goto pinned;
+			return SB_PINNED;
 		}
 		/*
 		 * umounted, drop rwsem again and fall through to failure
 		 */
 		up_read(&sb->s_umount);
 	}
-
 	sb->s_count--;
 	spin_unlock(&sb_lock);
-	return 1;
-pinned:
-	*psb = sb;
-	return 0;
+	return SB_PIN_FAILED;
 }
 
-static void writeback_inodes_wb(struct bdi_writeback *wb,
-				struct writeback_control *wbc)
+/*
+ * Write a portion of b_io inodes which belong to @sb.
+ * If @wbc->sb != NULL, then find and write all such
+ * inodes. Otherwise write only ones which go sequentially
+ * in reverse order.
+ * Return 1, if the caller writeback routine should be
+ * interrupted. Otherwise return 0.
+ */
+static int writeback_sb_inodes(struct super_block *sb,
+			       struct bdi_writeback *wb,
+			       struct writeback_control *wbc)
 {
-	struct super_block *sb = wbc->sb, *pin_sb = NULL;
-	const unsigned long start = jiffies;	/* livelock avoidance */
-
-	spin_lock(&inode_lock);
-
-	if (!wbc->for_kupdate || list_empty(&wb->b_io))
-		queue_io(wb, wbc->older_than_this);
-
 	while (!list_empty(&wb->b_io)) {
-		struct inode *inode = list_entry(wb->b_io.prev,
-						struct inode, i_list);
 		long pages_skipped;
-
-		/*
-		 * super block given and doesn't match, skip this inode
-		 */
-		if (sb && sb != inode->i_sb) {
+		struct inode *inode = list_entry(wb->b_io.prev,
+						 struct inode, i_list);
+		if (wbc->sb && sb != inode->i_sb) {
+			/* super block given and doesn't
+			   match, skip this inode */
 			redirty_tail(inode);
 			continue;
 		}
-
+		if (sb != inode->i_sb)
+			/* finish with this superblock */
+			return 0;
 		if (inode->i_state & (I_NEW | I_WILL_FREE)) {
 			requeue_io(inode);
 			continue;
 		}
-
 		/*
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
 		 */
-		if (inode_dirtied_after(inode, start))
-			break;
-
-		if (pin_sb_for_writeback(wbc, inode, &pin_sb)) {
-			requeue_io(inode);
-			continue;
-		}
+		if (inode_dirtied_after(inode, wbc->wb_start))
+			return 1;
 
 		BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
 		__iget(inode);
@@ -673,14 +650,50 @@ static void writeback_inodes_wb(struct bdi_writeback *wb,
 		spin_lock(&inode_lock);
 		if (wbc->nr_to_write <= 0) {
 			wbc->more_io = 1;
-			break;
+			return 1;
 		}
 		if (!list_empty(&wb->b_more_io))
 			wbc->more_io = 1;
 	}
+	/* b_io is empty */
+	return 1;
+}
+
+static void writeback_inodes_wb(struct bdi_writeback *wb,
+				struct writeback_control *wbc)
+{
+	int ret = 0;
 
-	unpin_sb_for_writeback(&pin_sb);
+	wbc->wb_start = jiffies; /* livelock avoidance */
+	spin_lock(&inode_lock);
+	if (!wbc->for_kupdate || list_empty(&wb->b_io))
+		queue_io(wb, wbc->older_than_this);
+
+	while (!list_empty(&wb->b_io)) {
+		struct inode *inode = list_entry(wb->b_io.prev,
+						 struct inode, i_list);
+		struct super_block *sb = inode->i_sb;
+		enum sb_pin_state state;
+
+		if (wbc->sb && sb != wbc->sb) {
+			/* super block given and doesn't
+			   match, skip this inode */
+			redirty_tail(inode);
+			continue;
+		}
+		state = pin_sb_for_writeback(wbc, sb);
+
+		if (state == SB_PIN_FAILED) {
+			requeue_io(inode);
+			continue;
+		}
+		ret = writeback_sb_inodes(sb, wb, wbc);
 
+		if (state == SB_PINNED)
+			unpin_sb_for_writeback(sb);
+		if (ret)
+			break;
+	}
 	spin_unlock(&inode_lock);
 	/* Leave any unwritten inodes on b_io */
 }
-- 
cgit v1.2.3-18-g5258


From 157f1071354db1aed885816094888e0e257c9d0a Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Thu, 11 Feb 2010 07:10:38 -0600
Subject: eCryptfs: Fix metadata in xattr feature regression

Fixes regression in 8faece5f906725c10e7a1f6caf84452abadbdc7b

When using the ecryptfs_xattr_metadata mount option, eCryptfs stores the
metadata (normally stored at the front of the file) in the user.ecryptfs
xattr.  This causes ecryptfs_crypt_stat.num_header_bytes_at_front to be
0, since there is no header data at the front of the file.  This results
in too much memory being requested and ENOMEM being returned from
ecryptfs_write_metadata().

This patch fixes the problem by using the num_header_bytes_at_front
variable for specifying the max size of the metadata, despite whether it
is stored in the header or xattr.

Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/crypto.c          |  7 ++++---
 fs/ecryptfs/ecryptfs_kernel.h |  8 ++++++++
 fs/ecryptfs/inode.c           |  2 +-
 fs/ecryptfs/mmap.c            | 19 +++++--------------
 4 files changed, 18 insertions(+), 18 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 7cb0a59f4b9..c907f6f4935 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -381,8 +381,8 @@ out:
 static void ecryptfs_lower_offset_for_extent(loff_t *offset, loff_t extent_num,
 					     struct ecryptfs_crypt_stat *crypt_stat)
 {
-	(*offset) = (crypt_stat->num_header_bytes_at_front
-		     + (crypt_stat->extent_size * extent_num));
+	(*offset) = ecryptfs_lower_header_size(crypt_stat)
+		    + (crypt_stat->extent_size * extent_num);
 }
 
 /**
@@ -834,7 +834,8 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat)
 	set_extent_mask_and_shift(crypt_stat);
 	crypt_stat->iv_bytes = ECRYPTFS_DEFAULT_IV_BYTES;
 	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
-		crypt_stat->num_header_bytes_at_front = 0;
+		crypt_stat->num_header_bytes_at_front =
+					ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 	else {
 		if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)
 			crypt_stat->num_header_bytes_at_front =
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 542f625312f..8456f70606a 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -464,6 +464,14 @@ struct ecryptfs_daemon {
 
 extern struct mutex ecryptfs_daemon_hash_mux;
 
+static inline size_t
+ecryptfs_lower_header_size(struct ecryptfs_crypt_stat *crypt_stat)
+{
+	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
+		return 0;
+	return crypt_stat->num_header_bytes_at_front;
+}
+
 static inline struct ecryptfs_file_info *
 ecryptfs_file_to_private(struct file *file)
 {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4a430ab4115..1a739531b0d 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -768,7 +768,7 @@ upper_size_to_lower_size(struct ecryptfs_crypt_stat *crypt_stat,
 {
 	loff_t lower_size;
 
-	lower_size = crypt_stat->num_header_bytes_at_front;
+	lower_size = ecryptfs_lower_header_size(crypt_stat);
 	if (upper_size != 0) {
 		loff_t num_extents;
 
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index df4ce99d059..5a30e01547f 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -97,19 +97,6 @@ out:
  *                        (big-endian)
  *     Octet  26:         Begin RFC 2440 authentication token packet set
  */
-static void set_header_info(char *page_virt,
-			    struct ecryptfs_crypt_stat *crypt_stat)
-{
-	size_t written;
-	size_t save_num_header_bytes_at_front =
-		crypt_stat->num_header_bytes_at_front;
-
-	crypt_stat->num_header_bytes_at_front =
-		ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
-	ecryptfs_write_header_metadata(page_virt + 20, crypt_stat, &written);
-	crypt_stat->num_header_bytes_at_front =
-		save_num_header_bytes_at_front;
-}
 
 /**
  * ecryptfs_copy_up_encrypted_with_header
@@ -146,9 +133,13 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 			memset(page_virt, 0, PAGE_CACHE_SIZE);
 			/* TODO: Support more than one header extent */
 			if (view_extent_num == 0) {
+				size_t written;
+
 				rc = ecryptfs_read_xattr_region(
 					page_virt, page->mapping->host);
-				set_header_info(page_virt, crypt_stat);
+				ecryptfs_write_header_metadata(page_virt + 20,
+							       crypt_stat,
+							       &written);
 			}
 			kunmap_atomic(page_virt, KM_USER0);
 			flush_dcache_page(page);
-- 
cgit v1.2.3-18-g5258


From fa3ef1cb4e6e9958a9bfaa977c107c515907f102 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Thu, 11 Feb 2010 05:09:14 -0600
Subject: eCryptfs: Rename ecryptfs_crypt_stat.num_header_bytes_at_front

This patch renames the num_header_bytes_at_front variable to
metadata_size since it now contains the max size of the metadata.

Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/crypto.c          | 24 ++++++++++--------------
 fs/ecryptfs/ecryptfs_kernel.h |  4 ++--
 fs/ecryptfs/inode.c           |  2 +-
 fs/ecryptfs/mmap.c            |  5 ++---
 4 files changed, 15 insertions(+), 20 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index c907f6f4935..391f558eb4d 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -834,14 +834,13 @@ void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat)
 	set_extent_mask_and_shift(crypt_stat);
 	crypt_stat->iv_bytes = ECRYPTFS_DEFAULT_IV_BYTES;
 	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
-		crypt_stat->num_header_bytes_at_front =
-					ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
+		crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 	else {
 		if (PAGE_CACHE_SIZE <= ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)
-			crypt_stat->num_header_bytes_at_front =
+			crypt_stat->metadata_size =
 				ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 		else
-			crypt_stat->num_header_bytes_at_front =	PAGE_CACHE_SIZE;
+			crypt_stat->metadata_size = PAGE_CACHE_SIZE;
 	}
 }
 
@@ -1238,8 +1237,7 @@ ecryptfs_write_header_metadata(char *virt,
 
 	header_extent_size = (u32)crypt_stat->extent_size;
 	num_header_extents_at_front =
-		(u16)(crypt_stat->num_header_bytes_at_front
-		      / crypt_stat->extent_size);
+		(u16)(crypt_stat->metadata_size / crypt_stat->extent_size);
 	put_unaligned_be32(header_extent_size, virt);
 	virt += 4;
 	put_unaligned_be16(num_header_extents_at_front, virt);
@@ -1382,7 +1380,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
 		rc = -EINVAL;
 		goto out;
 	}
-	virt_len = crypt_stat->num_header_bytes_at_front;
+	virt_len = crypt_stat->metadata_size;
 	order = get_order(virt_len);
 	/* Released in this function */
 	virt = (char *)ecryptfs_get_zeroed_pages(GFP_KERNEL, order);
@@ -1428,16 +1426,15 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat,
 	header_extent_size = get_unaligned_be32(virt);
 	virt += sizeof(__be32);
 	num_header_extents_at_front = get_unaligned_be16(virt);
-	crypt_stat->num_header_bytes_at_front =
-		(((size_t)num_header_extents_at_front
-		  * (size_t)header_extent_size));
+	crypt_stat->metadata_size = (((size_t)num_header_extents_at_front
+				     * (size_t)header_extent_size));
 	(*bytes_read) = (sizeof(__be32) + sizeof(__be16));
 	if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE)
-	    && (crypt_stat->num_header_bytes_at_front
+	    && (crypt_stat->metadata_size
 		< ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) {
 		rc = -EINVAL;
 		printk(KERN_WARNING "Invalid header size: [%zd]\n",
-		       crypt_stat->num_header_bytes_at_front);
+		       crypt_stat->metadata_size);
 	}
 	return rc;
 }
@@ -1452,8 +1449,7 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat,
  */
 static void set_default_header_data(struct ecryptfs_crypt_stat *crypt_stat)
 {
-	crypt_stat->num_header_bytes_at_front =
-		ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
+	crypt_stat->metadata_size = ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE;
 }
 
 /**
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 8456f70606a..d031efd7666 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -273,7 +273,7 @@ struct ecryptfs_crypt_stat {
 	u32 flags;
 	unsigned int file_version;
 	size_t iv_bytes;
-	size_t num_header_bytes_at_front;
+	size_t metadata_size;
 	size_t extent_size; /* Data extent size; default is 4096 */
 	size_t key_size;
 	size_t extent_shift;
@@ -469,7 +469,7 @@ ecryptfs_lower_header_size(struct ecryptfs_crypt_stat *crypt_stat)
 {
 	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
 		return 0;
-	return crypt_stat->num_header_bytes_at_front;
+	return crypt_stat->metadata_size;
 }
 
 static inline struct ecryptfs_file_info *
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 1a739531b0d..a50efb18701 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -335,7 +335,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
 		ecryptfs_dentry->d_sb)->mount_crypt_stat;
 	if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) {
 		if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
-			file_size = (crypt_stat->num_header_bytes_at_front
+			file_size = (crypt_stat->metadata_size
 				     + i_size_read(lower_dentry->d_inode));
 		else
 			file_size = i_size_read(lower_dentry->d_inode);
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 5a30e01547f..270f42ae7c0 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -122,8 +122,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 					   * num_extents_per_page)
 					  + extent_num_in_page);
 		size_t num_header_extents_at_front =
-			(crypt_stat->num_header_bytes_at_front
-			 / crypt_stat->extent_size);
+			(crypt_stat->metadata_size / crypt_stat->extent_size);
 
 		if (view_extent_num < num_header_extents_at_front) {
 			/* This is a header extent */
@@ -152,7 +151,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 			/* This is an encrypted data extent */
 			loff_t lower_offset =
 				((view_extent_num * crypt_stat->extent_size)
-				 - crypt_stat->num_header_bytes_at_front);
+				 - crypt_stat->metadata_size);
 
 			rc = ecryptfs_read_lower_page_segment(
 				page, (lower_offset >> PAGE_CACHE_SHIFT),
-- 
cgit v1.2.3-18-g5258


From 1984c23f9e0cdb432d90a85ecf88b424d36878fc Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Wed, 10 Feb 2010 23:17:44 -0600
Subject: eCryptfs: Clear buffer before reading in metadata xattr

We initially read in the first PAGE_CACHE_SIZE of a file to if the
eCryptfs header marker can be found.  If it isn't found and
ecryptfs_xattr_metadata was given as a mount option, then the
user.ecryptfs xattr is read into the same buffer.  Since the data from
the first page of the file wasn't cleared, it is possible that we think
we've found a second tag 3 or tag 1 packet and then error out after the
packet contents aren't as expected.  This patch clears the buffer before
filling it with metadata from the user.ecryptfs xattr.

Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/crypto.c | 1 +
 fs/ecryptfs/inode.c  | 1 +
 2 files changed, 2 insertions(+)

(limited to 'fs')

diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 391f558eb4d..4d9db0ed88e 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1603,6 +1603,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 						ecryptfs_dentry,
 						ECRYPTFS_VALIDATE_HEADER_SIZE);
 	if (rc) {
+		memset(page_virt, 0, PAGE_CACHE_SIZE);
 		rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_inode);
 		if (rc) {
 			printk(KERN_DEBUG "Valid eCryptfs headers not found in "
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a50efb18701..ddbd096c740 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -323,6 +323,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
 	rc = ecryptfs_read_and_validate_header_region(page_virt,
 						      ecryptfs_dentry->d_inode);
 	if (rc) {
+		memset(page_virt, 0, PAGE_CACHE_SIZE);
 		rc = ecryptfs_read_and_validate_xattr_region(page_virt,
 							     ecryptfs_dentry);
 		if (rc) {
-- 
cgit v1.2.3-18-g5258


From f4e60e6b303bc46cdc477d3174dbf9cb5dd013aa Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Thu, 11 Feb 2010 00:02:32 -0600
Subject: eCryptfs: Strip metadata in xattr flag in encrypted view

The ecryptfs_encrypted_view mount option provides a unified way of
viewing encrypted eCryptfs files.  If the metadata is stored in a xattr,
the metadata is moved to the file header when the file is read inside
the eCryptfs mount.  Because of this, we should strip the
ECRYPTFS_METADATA_IN_XATTR flag from the header's flag section.  This
allows eCryptfs to treat the file as an eCryptfs file with a header
at the front.

Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/crypto.c          |  9 +++++----
 fs/ecryptfs/ecryptfs_kernel.h |  3 +++
 fs/ecryptfs/mmap.c            | 14 ++++++++++++++
 3 files changed, 22 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 4d9db0ed88e..fad5bf6a611 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1107,9 +1107,9 @@ static void write_ecryptfs_marker(char *page_virt, size_t *written)
 	(*written) = MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
 }
 
-static void
-write_ecryptfs_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat,
-		     size_t *written)
+void ecryptfs_write_crypt_stat_flags(char *page_virt,
+				     struct ecryptfs_crypt_stat *crypt_stat,
+				     size_t *written)
 {
 	u32 flags = 0;
 	int i;
@@ -1290,7 +1290,8 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t max,
 	offset = ECRYPTFS_FILE_SIZE_BYTES;
 	write_ecryptfs_marker((page_virt + offset), &written);
 	offset += written;
-	write_ecryptfs_flags((page_virt + offset), crypt_stat, &written);
+	ecryptfs_write_crypt_stat_flags((page_virt + offset), crypt_stat,
+					&written);
 	offset += written;
 	ecryptfs_write_header_metadata((page_virt + offset), crypt_stat,
 				       &written);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index d031efd7666..bc7115403f3 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -659,6 +659,9 @@ int ecryptfs_decrypt_page(struct page *page);
 int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry);
 int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
 int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
+void ecryptfs_write_crypt_stat_flags(char *page_virt,
+				     struct ecryptfs_crypt_stat *crypt_stat,
+				     size_t *written);
 int ecryptfs_read_and_validate_header_region(char *data,
 					     struct inode *ecryptfs_inode);
 int ecryptfs_read_and_validate_xattr_region(char *page_virt,
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 270f42ae7c0..bea998a25af 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -82,6 +82,19 @@ out:
 	return rc;
 }
 
+static void strip_xattr_flag(char *page_virt,
+			     struct ecryptfs_crypt_stat *crypt_stat)
+{
+	if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
+		size_t written;
+
+		crypt_stat->flags &= ~ECRYPTFS_METADATA_IN_XATTR;
+		ecryptfs_write_crypt_stat_flags(page_virt, crypt_stat,
+						&written);
+		crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
+	}
+}
+
 /**
  *   Header Extent:
  *     Octets 0-7:        Unencrypted file size (big-endian)
@@ -136,6 +149,7 @@ ecryptfs_copy_up_encrypted_with_header(struct page *page,
 
 				rc = ecryptfs_read_xattr_region(
 					page_virt, page->mapping->host);
+				strip_xattr_flag(page_virt + 16, crypt_stat);
 				ecryptfs_write_header_metadata(page_virt + 20,
 							       crypt_stat,
 							       &written);
-- 
cgit v1.2.3-18-g5258


From 810627a013163cd294762d57c0ea2ec055ffe4f6 Mon Sep 17 00:00:00 2001
From: Pavel Shilovsky <piastryyy@gmail.com>
Date: Sat, 27 Mar 2010 02:00:49 +0000
Subject: [CIFS] Add mmap for direct, nobrl cifs mount types

without mmap functions in file_ops OpenOffice can't save changes in
existing document. The same situation you can see with gedit. Also, a.out
format of files can't be executed without mmap.

Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
---
 fs/cifs/cifsfs.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs')

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5183bc2a191..ded66be6597 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -808,6 +808,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
 	.release = cifs_close,
 	.fsync = cifs_fsync,
 	.flush = cifs_flush,
+	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 #ifdef CONFIG_CIFS_POSIX
 	.unlocked_ioctl  = cifs_ioctl,
-- 
cgit v1.2.3-18-g5258


From 49137f2efb5cf68724bccaba531ab3d59acd71f9 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Tue, 16 Mar 2010 21:46:15 +0100
Subject: Open segment file before using it

logfs_recover_sb() needs it open.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/super.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index c66beab78de..018728120bb 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -289,6 +289,10 @@ static int logfs_make_writeable(struct super_block *sb)
 {
 	int err;
 
+	err = logfs_open_segfile(sb);
+	if (err)
+		return err;
+
 	/* Repair any broken superblock copies */
 	err = logfs_recover_sb(sb);
 	if (err)
@@ -299,10 +303,6 @@ static int logfs_make_writeable(struct super_block *sb)
 	if (err)
 		return err;
 
-	err = logfs_open_segfile(sb);
-	if (err)
-		return err;
-
 	/* Do one GC pass before any data gets dirtied */
 	logfs_gc_pass(sb);
 
-- 
cgit v1.2.3-18-g5258


From 59fe27c0a8173a74b105debc803b97582028c90b Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Wed, 17 Mar 2010 13:47:45 +0100
Subject: Limit max_pages for insane devices

Intel SSDs have a limit of 0xffff as queue_max_hw_sectors(q).  Such a
limit may make sense from a hardware pov, but it causes bio_alloc() to
return NULL.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/dev_bdev.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 9718c22f186..f99f5dcce54 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -97,8 +97,10 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
 	unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
 	int i;
 
+	if (max_pages > BIO_MAX_PAGES)
+		max_pages = BIO_MAX_PAGES;
 	bio = bio_alloc(GFP_NOFS, max_pages);
-	BUG_ON(!bio); /* FIXME: handle this */
+	BUG_ON(!bio);
 
 	for (i = 0; i < nr_pages; i++) {
 		if (i >= max_pages) {
@@ -191,8 +193,10 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
 	unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
 	int i;
 
+	if (max_pages > BIO_MAX_PAGES)
+		max_pages = BIO_MAX_PAGES;
 	bio = bio_alloc(GFP_NOFS, max_pages);
-	BUG_ON(!bio); /* FIXME: handle this */
+	BUG_ON(!bio);
 
 	for (i = 0; i < nr_pages; i++) {
 		if (i >= max_pages) {
-- 
cgit v1.2.3-18-g5258


From e07bf553f37cd4fa470b499ff34d800956df2d48 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Wed, 17 Mar 2010 15:29:38 +0100
Subject: Plug memory leak in writeseg_end_io

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/dev_bdev.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs')

diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index f99f5dcce54..a5d0c56d3eb 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -80,6 +80,7 @@ static void writeseg_end_io(struct bio *bio, int err)
 			prefetchw(&bvec->bv_page->flags);
 
 		end_page_writeback(page);
+		page_cache_release(page);
 	} while (bvec >= bio->bi_io_vec);
 	bio_put(bio);
 	if (atomic_dec_and_test(&super->s_pending_writes))
-- 
cgit v1.2.3-18-g5258


From e326068806ee044cc617b1dc24be1293fca3fbf6 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Wed, 17 Mar 2010 16:00:07 +0100
Subject: Prevent schedule while atomic in __logfs_readdir

Apparently filldir can sleep, which forbids kmap_atomic.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/dir.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 56a8bfbb012..c76b4b5c7ff 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -303,12 +303,12 @@ static int __logfs_readdir(struct file *file, void *buf, filldir_t filldir)
 				(filler_t *)logfs_readpage, NULL);
 		if (IS_ERR(page))
 			return PTR_ERR(page);
-		dd = kmap_atomic(page, KM_USER0);
+		dd = kmap(page);
 		BUG_ON(dd->namelen == 0);
 
 		full = filldir(buf, (char *)dd->name, be16_to_cpu(dd->namelen),
 				pos, be64_to_cpu(dd->ino), dd->type);
-		kunmap_atomic(dd, KM_USER0);
+		kunmap(page);
 		page_cache_release(page);
 		if (full)
 			break;
-- 
cgit v1.2.3-18-g5258


From faaa27ab919799929732c356a92a160f8657ecc6 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Fri, 26 Mar 2010 10:18:36 +0100
Subject: Write out both superblocks on mismatch

If the first superblock is wrong and the second gets written, there
will still be a mismatch on next mount.  Write both to make sure they
match.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 018728120bb..006670fe9e8 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -277,7 +277,7 @@ static int logfs_recover_sb(struct super_block *sb)
 	}
 	if (valid0 && valid1 && ds_cmp(ds0, ds1)) {
 		printk(KERN_INFO"Superblocks don't match - fixing.\n");
-		return write_one_sb(sb, super->s_devops->find_last_sb);
+		return logfs_write_sb(sb);
 	}
 	/* If neither is valid now, something's wrong.  Didn't we properly
 	 * check them before?!? */
-- 
cgit v1.2.3-18-g5258


From 7db8064c17b92e95aec2e333096c035db9ddd4fe Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Fri, 26 Mar 2010 14:45:55 +0100
Subject: Fix logfs_get_sb_final error path

rootdir was already allocated, so we must iput it again.
Found by Al Viro.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 006670fe9e8..2845c41d70d 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -328,7 +328,7 @@ static int logfs_get_sb_final(struct super_block *sb, struct vfsmount *mnt)
 
 	sb->s_root = d_alloc_root(rootdir);
 	if (!sb->s_root)
-		goto fail;
+		goto fail2;
 
 	super->s_erase_page = alloc_pages(GFP_KERNEL, 0);
 	if (!super->s_erase_page)
-- 
cgit v1.2.3-18-g5258


From 6f2e9e6a950a165a7d2c399ab7557e6745ef2bfd Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Fri, 26 Mar 2010 14:50:08 +0100
Subject: Use deactivate_locked_super

Found by Al Viro.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/super.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 2845c41d70d..9d856c49afc 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -572,8 +572,7 @@ int logfs_get_sb_device(struct file_system_type *type, int flags,
 	return 0;
 
 err1:
-	up_write(&sb->s_umount);
-	deactivate_super(sb);
+	deactivate_locked_super(sb);
 	return err;
 err0:
 	kfree(super);
-- 
cgit v1.2.3-18-g5258


From 193219172691e29813821dc8433317768c6ed1a3 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Sat, 27 Mar 2010 09:56:58 +0100
Subject: Prevent data corruption in logfs_rewrite_block()

The comment was correct, so make the code match the comment.  As the
new comment indicates, we might be able to do a little less work.  But
for the current -rc series let's keep it simple and just fix the bug.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/readwrite.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 7a23b3e7c0a..c3a3a6814b8 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -1594,7 +1594,6 @@ int logfs_delete(struct inode *inode, pgoff_t index,
 	return ret;
 }
 
-/* Rewrite cannot mark the inode dirty but has to write it immediatly. */
 int logfs_rewrite_block(struct inode *inode, u64 bix, u64 ofs,
 		gc_level_t gc_level, long flags)
 {
@@ -1611,6 +1610,18 @@ int logfs_rewrite_block(struct inode *inode, u64 bix, u64 ofs,
 		if (level != 0)
 			alloc_indirect_block(inode, page, 0);
 		err = logfs_write_buf(inode, page, flags);
+		if (!err && shrink_level(gc_level) == 0) {
+			/* Rewrite cannot mark the inode dirty but has to
+			 * write it immediatly.
+			 * Q: Can't we just create an alias for the inode
+			 * instead?  And if not, why not?
+			 */
+			if (inode->i_ino == LOGFS_INO_MASTER)
+				logfs_write_anchor(inode->i_sb);
+			else {
+				err = __logfs_write_inode(inode, flags);
+			}
+		}
 	}
 	logfs_put_write_page(page);
 	return err;
-- 
cgit v1.2.3-18-g5258


From 81def6b9862764924a99ac1b680e73ac8c80ac64 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Sun, 28 Mar 2010 12:47:09 +0200
Subject: Simplify and fix pad_wbuf

A comment in the old code read:
        /* The math in this function can surely use some love */

And indeed it did.  In the case that area->a_used_bytes is exactly
4096 bytes below segment size it fell apart.  pad_wbuf is now split
into two helpers that are significantly less complicated.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/segment.c | 52 ++++++++++++++++++++++++++++++----------------------
 1 file changed, 30 insertions(+), 22 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 1a14f9910d5..ff9d7f3b4d3 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -93,49 +93,57 @@ void __logfs_buf_write(struct logfs_area *area, u64 ofs, void *buf, size_t len,
 	} while (len);
 }
 
-/*
- * bdev_writeseg will write full pages.  Memset the tail to prevent data leaks.
- */
-static void pad_wbuf(struct logfs_area *area, int final)
+static void pad_partial_page(struct logfs_area *area)
 {
 	struct super_block *sb = area->a_sb;
-	struct logfs_super *super = logfs_super(sb);
 	struct page *page;
 	u64 ofs = dev_ofs(sb, area->a_segno, area->a_used_bytes);
 	pgoff_t index = ofs >> PAGE_SHIFT;
 	long offset = ofs & (PAGE_SIZE-1);
 	u32 len = PAGE_SIZE - offset;
 
-	if (len == PAGE_SIZE) {
-		/* The math in this function can surely use some love */
-		len = 0;
-	}
-	if (len) {
-		BUG_ON(area->a_used_bytes >= super->s_segsize);
-
-		page = get_mapping_page(area->a_sb, index, 0);
+	if (len % PAGE_SIZE) {
+		page = get_mapping_page(sb, index, 0);
 		BUG_ON(!page); /* FIXME: reserve a pool */
 		memset(page_address(page) + offset, 0xff, len);
 		SetPagePrivate(page);
 		page_cache_release(page);
 	}
+}
 
-	if (!final)
-		return;
+static void pad_full_pages(struct logfs_area *area)
+{
+	struct super_block *sb = area->a_sb;
+	struct logfs_super *super = logfs_super(sb);
+	u64 ofs = dev_ofs(sb, area->a_segno, area->a_used_bytes);
+	u32 len = super->s_segsize - area->a_used_bytes;
+	pgoff_t index = PAGE_CACHE_ALIGN(ofs) >> PAGE_CACHE_SHIFT;
+	pgoff_t no_indizes = len >> PAGE_CACHE_SHIFT;
+	struct page *page;
 
-	area->a_used_bytes += len;
-	for ( ; area->a_used_bytes < super->s_segsize;
-			area->a_used_bytes += PAGE_SIZE) {
-		/* Memset another page */
-		index++;
-		page = get_mapping_page(area->a_sb, index, 0);
+	while (no_indizes) {
+		page = get_mapping_page(sb, index, 0);
 		BUG_ON(!page); /* FIXME: reserve a pool */
-		memset(page_address(page), 0xff, PAGE_SIZE);
+		SetPageUptodate(page);
+		memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
 		SetPagePrivate(page);
 		page_cache_release(page);
+		index++;
+		no_indizes--;
 	}
 }
 
+/*
+ * bdev_writeseg will write full pages.  Memset the tail to prevent data leaks.
+ * Also make sure we allocate (and memset) all pages for final writeout.
+ */
+static void pad_wbuf(struct logfs_area *area, int final)
+{
+	pad_partial_page(area);
+	if (final)
+		pad_full_pages(area);
+}
+
 /*
  * We have to be careful with the alias tree.  Since lookup is done by bix,
  * it needs to be normalized, so 14, 15, 16, etc. all match when dealing with
-- 
cgit v1.2.3-18-g5258


From 723b2ff40876678b49e61df34fb1d8001e34639d Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Sun, 28 Mar 2010 18:10:07 +0200
Subject: [LogFS] Clear PagePrivate when moving journal

do_logfs_journal_wl_pass() must call freeseg(), thereby clear
PagePrivate on all pages of the current journal segment.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/journal.c | 1 +
 fs/logfs/logfs.h   | 1 +
 fs/logfs/segment.c | 2 +-
 3 files changed, 3 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 6ad30a4c905..15454ac7bd9 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -821,6 +821,7 @@ void do_logfs_journal_wl_pass(struct super_block *sb)
 		logfs_set_segment_reserved(sb, segno);
 	}
 	/* Manually move journal_area */
+	freeseg(sb, area->a_segno);
 	area->a_segno = super->s_journal_seg[0];
 	area->a_is_open = 0;
 	area->a_used_bytes = 0;
diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 12977943137..b84b0eec602 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -587,6 +587,7 @@ void move_page_to_btree(struct page *page);
 int logfs_init_mapping(struct super_block *sb);
 void logfs_sync_area(struct logfs_area *area);
 void logfs_sync_segments(struct super_block *sb);
+void freeseg(struct super_block *sb, u32 segno);
 
 /* area handling */
 int logfs_init_areas(struct super_block *sb);
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index ff9d7f3b4d3..0ecd8f07c11 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -691,7 +691,7 @@ int logfs_segment_delete(struct inode *inode, struct logfs_shadow *shadow)
 	return 0;
 }
 
-static void freeseg(struct super_block *sb, u32 segno)
+void freeseg(struct super_block *sb, u32 segno)
 {
 	struct logfs_super *super = logfs_super(sb);
 	struct address_space *mapping = super->s_mapping_inode->i_mapping;
-- 
cgit v1.2.3-18-g5258


From 0943846ae05603efd98550f2d475e9c98191bde8 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Mon, 29 Mar 2010 21:13:28 +0200
Subject: [LogFS] Move reserved segments with journal

Fixes a GC livelock.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/journal.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'fs')

diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 15454ac7bd9..25b1345c465 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -800,6 +800,7 @@ void do_logfs_journal_wl_pass(struct super_block *sb)
 {
 	struct logfs_super *super = logfs_super(sb);
 	struct logfs_area *area = super->s_journal_area;
+	struct btree_head32 *head = &super->s_reserved_segments;
 	u32 segno, ec;
 	int i, err;
 
@@ -807,6 +808,7 @@ void do_logfs_journal_wl_pass(struct super_block *sb)
 	/* Drop old segments */
 	journal_for_each(i)
 		if (super->s_journal_seg[i]) {
+			btree_remove32(head, super->s_journal_seg[i]);
 			logfs_set_segment_unreserved(sb,
 					super->s_journal_seg[i],
 					super->s_journal_ec[i]);
@@ -819,6 +821,8 @@ void do_logfs_journal_wl_pass(struct super_block *sb)
 		super->s_journal_seg[i] = segno;
 		super->s_journal_ec[i] = ec;
 		logfs_set_segment_reserved(sb, segno);
+		err = btree_insert32(head, segno, (void *)1, GFP_KERNEL);
+		BUG_ON(err); /* mempool should prevent this */
 	}
 	/* Manually move journal_area */
 	freeseg(sb, area->a_segno);
-- 
cgit v1.2.3-18-g5258


From 6be7fa06eb4d721df734bd0946b5e63b27c0589b Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Mon, 29 Mar 2010 21:14:52 +0200
Subject: [LogFS] Erase new journal segments

If the device contains on old logfs image and the journal is moved to
segment that have never been used by the current logfs and not all
journal segments are erased before the next mount, the old content can
confuse mount code.  To prevent this, always erase the new journal
segments.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/journal.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'fs')

diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 25b1345c465..d57c7b07b60 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -823,6 +823,8 @@ void do_logfs_journal_wl_pass(struct super_block *sb)
 		logfs_set_segment_reserved(sb, segno);
 		err = btree_insert32(head, segno, (void *)1, GFP_KERNEL);
 		BUG_ON(err); /* mempool should prevent this */
+		err = logfs_erase_segment(sb, segno, 1);
+		BUG_ON(err); /* FIXME: remount-ro would be nicer */
 	}
 	/* Manually move journal_area */
 	freeseg(sb, area->a_segno);
-- 
cgit v1.2.3-18-g5258


From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 24 Mar 2010 17:04:11 +0900
Subject: include cleanup: Update gfp.h and slab.h includes to prepare for
 breaking implicit slab.h inclusion from percpu.h

percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
---
 fs/9p/cache.c                  | 1 +
 fs/9p/fid.c                    | 1 +
 fs/9p/v9fs.c                   | 1 +
 fs/9p/vfs_dentry.c             | 1 +
 fs/9p/vfs_dir.c                | 1 +
 fs/9p/vfs_inode.c              | 1 +
 fs/9p/vfs_super.c              | 1 +
 fs/adfs/super.c                | 1 +
 fs/affs/bitmap.c               | 1 +
 fs/affs/inode.c                | 1 +
 fs/affs/super.c                | 1 +
 fs/afs/cache.c                 | 1 -
 fs/afs/cmservice.c             | 1 +
 fs/afs/dir.c                   | 1 -
 fs/afs/file.c                  | 2 +-
 fs/afs/fsclient.c              | 1 +
 fs/afs/inode.c                 | 1 -
 fs/afs/mntpt.c                 | 2 +-
 fs/afs/rxrpc.c                 | 1 +
 fs/afs/vlclient.c              | 1 +
 fs/afs/vlocation.c             | 1 +
 fs/afs/vnode.c                 | 1 -
 fs/anon_inodes.c               | 1 -
 fs/autofs/root.c               | 1 +
 fs/autofs4/dev-ioctl.c         | 1 +
 fs/autofs4/root.c              | 1 +
 fs/befs/datastream.c           | 1 -
 fs/binfmt_aout.c               | 2 +-
 fs/binfmt_em86.c               | 1 -
 fs/binfmt_script.c             | 1 -
 fs/bio-integrity.c             | 1 +
 fs/btrfs/acl.c                 | 1 +
 fs/btrfs/async-thread.c        | 1 +
 fs/btrfs/compression.c         | 1 +
 fs/btrfs/ctree.c               | 1 +
 fs/btrfs/ctree.h               | 1 +
 fs/btrfs/delayed-ref.c         | 1 +
 fs/btrfs/disk-io.c             | 1 +
 fs/btrfs/extent-tree.c         | 1 +
 fs/btrfs/extent_io.c           | 1 -
 fs/btrfs/extent_map.c          | 1 -
 fs/btrfs/file-item.c           | 1 +
 fs/btrfs/file.c                | 1 +
 fs/btrfs/free-space-cache.c    | 1 +
 fs/btrfs/inode.c               | 1 +
 fs/btrfs/ioctl.c               | 1 +
 fs/btrfs/locking.c             | 1 -
 fs/btrfs/ordered-data.c        | 1 -
 fs/btrfs/ref-cache.c           | 1 +
 fs/btrfs/relocation.c          | 1 +
 fs/btrfs/super.c               | 1 +
 fs/btrfs/transaction.c         | 1 +
 fs/btrfs/tree-log.c            | 1 +
 fs/btrfs/volumes.c             | 1 +
 fs/cachefiles/interface.c      | 1 +
 fs/cachefiles/namei.c          | 1 +
 fs/cachefiles/rdwr.c           | 1 +
 fs/cachefiles/xattr.c          | 1 +
 fs/ceph/addr.c                 | 1 +
 fs/ceph/auth.c                 | 1 +
 fs/ceph/auth_none.c            | 1 +
 fs/ceph/auth_x.c               | 1 +
 fs/ceph/buffer.c               | 3 +++
 fs/ceph/caps.c                 | 1 +
 fs/ceph/crypto.c               | 1 +
 fs/ceph/debugfs.c              | 1 +
 fs/ceph/dir.c                  | 1 +
 fs/ceph/export.c               | 1 +
 fs/ceph/file.c                 | 1 +
 fs/ceph/mds_client.c           | 1 +
 fs/ceph/messenger.c            | 1 +
 fs/ceph/mon_client.c           | 1 +
 fs/ceph/osdmap.c               | 4 +++-
 fs/ceph/pagelist.c             | 1 +
 fs/ceph/snap.c                 | 1 +
 fs/ceph/super.c                | 1 +
 fs/ceph/super.h                | 1 +
 fs/ceph/xattr.c                | 1 +
 fs/cifs/cifs_dfs_ref.c         | 1 +
 fs/cifs/cifs_spnego.c          | 1 +
 fs/cifs/cifs_unicode.c         | 1 +
 fs/cifs/cifsacl.c              | 1 +
 fs/cifs/cifsencrypt.c          | 1 +
 fs/cifs/cifsglob.h             | 1 +
 fs/cifs/cifssmb.c              | 1 +
 fs/cifs/connect.c              | 1 +
 fs/cifs/dns_resolve.c          | 1 +
 fs/cifs/file.c                 | 1 +
 fs/cifs/inode.c                | 1 +
 fs/cifs/link.c                 | 1 +
 fs/cifs/readdir.c              | 1 +
 fs/cifs/sess.c                 | 1 +
 fs/cifs/smbencrypt.c           | 1 +
 fs/cifs/transport.c            | 1 +
 fs/cifs/xattr.c                | 1 +
 fs/coda/dir.c                  | 1 +
 fs/coda/file.c                 | 1 +
 fs/coda/inode.c                | 1 +
 fs/coda/upcall.c               | 1 +
 fs/compat.c                    | 1 +
 fs/compat_ioctl.c              | 2 +-
 fs/configfs/inode.c            | 1 +
 fs/configfs/mount.c            | 1 +
 fs/configfs/symlink.c          | 1 +
 fs/debugfs/inode.c             | 1 +
 fs/devpts/inode.c              | 1 +
 fs/dlm/config.c                | 1 +
 fs/dlm/debug_fs.c              | 1 +
 fs/dlm/lock.c                  | 1 +
 fs/dlm/lowcomms.c              | 1 +
 fs/dlm/netlink.c               | 1 +
 fs/dlm/plock.c                 | 1 +
 fs/dlm/user.c                  | 1 +
 fs/ecryptfs/crypto.c           | 1 +
 fs/ecryptfs/dentry.c           | 1 +
 fs/ecryptfs/file.c             | 1 +
 fs/ecryptfs/inode.c            | 1 +
 fs/ecryptfs/keystore.c         | 1 +
 fs/ecryptfs/kthread.c          | 1 +
 fs/ecryptfs/main.c             | 1 +
 fs/ecryptfs/messaging.c        | 1 +
 fs/ecryptfs/miscdev.c          | 1 +
 fs/ecryptfs/mmap.c             | 1 +
 fs/ecryptfs/super.c            | 1 +
 fs/eventfd.c                   | 1 +
 fs/exofs/inode.c               | 1 +
 fs/exofs/ios.c                 | 1 +
 fs/exofs/super.c               | 1 +
 fs/ext2/balloc.c               | 1 +
 fs/ext2/xattr_security.c       | 1 +
 fs/ext3/balloc.c               | 1 +
 fs/ext3/xattr_security.c       | 1 +
 fs/ext4/block_validity.c       | 1 +
 fs/ext4/inode.c                | 1 +
 fs/ext4/mballoc.c              | 1 +
 fs/ext4/migrate.c              | 1 +
 fs/ext4/move_extent.c          | 1 +
 fs/ext4/xattr_security.c       | 1 +
 fs/fat/cache.c                 | 1 +
 fs/fifo.c                      | 1 -
 fs/filesystems.c               | 2 +-
 fs/freevxfs/vxfs_subr.c        | 1 -
 fs/fs-writeback.c              | 1 +
 fs/fscache/object-list.c       | 1 +
 fs/fscache/operation.c         | 1 +
 fs/fscache/page.c              | 1 +
 fs/fuse/cuse.c                 | 1 +
 fs/generic_acl.c               | 1 +
 fs/gfs2/bmap.c                 | 1 -
 fs/gfs2/dentry.c               | 1 -
 fs/gfs2/export.c               | 1 -
 fs/gfs2/glops.c                | 1 -
 fs/gfs2/lock_dlm.c             | 1 +
 fs/gfs2/rgrp.h                 | 2 ++
 fs/gfs2/sys.c                  | 1 -
 fs/gfs2/util.c                 | 1 -
 fs/hfs/bnode.c                 | 1 +
 fs/hfs/btree.c                 | 1 +
 fs/hfs/mdb.c                   | 1 +
 fs/hfs/super.c                 | 1 +
 fs/hfsplus/options.c           | 1 +
 fs/hostfs/hostfs_kern.c        | 1 +
 fs/hpfs/buffer.c               | 1 +
 fs/hpfs/dir.c                  | 1 +
 fs/hpfs/inode.c                | 1 +
 fs/hpfs/super.c                | 1 +
 fs/ioprio.c                    | 1 +
 fs/isofs/dir.c                 | 1 +
 fs/isofs/namei.c               | 1 +
 fs/jbd/commit.c                | 1 -
 fs/jbd/recovery.c              | 1 -
 fs/jbd2/recovery.c             | 1 -
 fs/jffs2/compr_lzo.c           | 1 -
 fs/jffs2/compr_zlib.c          | 1 -
 fs/jffs2/debug.c               | 1 +
 fs/jffs2/file.c                | 1 -
 fs/jffs2/nodelist.c            | 1 -
 fs/jffs2/nodemgmt.c            | 1 -
 fs/jffs2/symlink.c             | 1 -
 fs/jffs2/write.c               | 1 -
 fs/jfs/acl.c                   | 1 +
 fs/jfs/jfs_dmap.c              | 1 +
 fs/jfs/jfs_dtree.c             | 1 +
 fs/jfs/jfs_imap.c              | 1 +
 fs/jfs/jfs_logmgr.c            | 1 +
 fs/jfs/jfs_metapage.c          | 1 +
 fs/jfs/jfs_unicode.h           | 1 +
 fs/jfs/super.c                 | 1 +
 fs/jfs/xattr.c                 | 1 +
 fs/libfs.c                     | 1 +
 fs/lockd/clntlock.c            | 1 +
 fs/lockd/clntproc.c            | 1 +
 fs/lockd/mon.c                 | 1 +
 fs/lockd/svc.c                 | 1 -
 fs/lockd/svc4proc.c            | 1 -
 fs/lockd/svclock.c             | 1 +
 fs/lockd/svcproc.c             | 1 -
 fs/lockd/svcsubs.c             | 1 +
 fs/logfs/dev_bdev.c            | 1 +
 fs/logfs/dir.c                 | 2 +-
 fs/logfs/gc.c                  | 1 +
 fs/logfs/inode.c               | 1 +
 fs/logfs/journal.c             | 1 +
 fs/logfs/readwrite.c           | 1 +
 fs/logfs/segment.c             | 1 +
 fs/logfs/super.c               | 1 +
 fs/minix/itree_v1.c            | 1 +
 fs/mpage.c                     | 1 +
 fs/ncpfs/dir.c                 | 1 -
 fs/ncpfs/file.c                | 1 -
 fs/ncpfs/ioctl.c               | 1 +
 fs/ncpfs/mmap.c                | 2 +-
 fs/ncpfs/sock.c                | 1 +
 fs/ncpfs/symlink.c             | 1 +
 fs/nfs/cache_lib.c             | 1 +
 fs/nfs/callback_proc.c         | 1 +
 fs/nfs/callback_xdr.c          | 1 +
 fs/nfs/client.c                | 1 +
 fs/nfs/delegation.c            | 1 +
 fs/nfs/direct.c                | 1 +
 fs/nfs/dns_resolve.c           | 1 +
 fs/nfs/file.c                  | 2 +-
 fs/nfs/fscache.c               | 1 +
 fs/nfs/inode.c                 | 1 +
 fs/nfs/namespace.c             | 1 +
 fs/nfs/nfs2xdr.c               | 1 -
 fs/nfs/nfs3acl.c               | 1 +
 fs/nfs/nfs3proc.c              | 1 +
 fs/nfs/nfs3xdr.c               | 1 -
 fs/nfs/nfs4namespace.c         | 1 +
 fs/nfs/nfs4proc.c              | 1 +
 fs/nfs/nfs4xdr.c               | 1 -
 fs/nfs/proc.c                  | 1 -
 fs/nfs/super.c                 | 1 +
 fs/nfs/symlink.c               | 1 -
 fs/nfs_common/nfsacl.c         | 1 +
 fs/nfsd/export.c               | 1 +
 fs/nfsd/nfs2acl.c              | 1 +
 fs/nfsd/nfs3acl.c              | 1 +
 fs/nfsd/nfs4acl.c              | 1 +
 fs/nfsd/nfs4callback.c         | 1 +
 fs/nfsd/nfs4idmap.c            | 1 +
 fs/nfsd/nfs4proc.c             | 1 +
 fs/nfsd/nfs4recover.c          | 1 +
 fs/nfsd/nfs4state.c            | 1 +
 fs/nfsd/nfs4xdr.c              | 1 +
 fs/nfsd/nfscache.c             | 2 ++
 fs/nfsd/nfsctl.c               | 1 +
 fs/nfsd/vfs.c                  | 1 +
 fs/nilfs2/alloc.c              | 1 +
 fs/nilfs2/btnode.c             | 1 +
 fs/nilfs2/gcinode.c            | 1 +
 fs/nilfs2/inode.c              | 1 +
 fs/nilfs2/ioctl.c              | 1 +
 fs/nilfs2/mdt.c                | 1 +
 fs/nilfs2/page.c               | 1 +
 fs/nilfs2/recovery.c           | 1 +
 fs/nilfs2/segbuf.c             | 1 +
 fs/nilfs2/segment.c            | 1 +
 fs/nilfs2/the_nilfs.h          | 1 +
 fs/notify/fsnotify.c           | 1 +
 fs/notify/inode_mark.c         | 1 -
 fs/ntfs/aops.c                 | 1 +
 fs/ntfs/attrib.c               | 1 +
 fs/ntfs/compress.c             | 1 +
 fs/ntfs/dir.c                  | 1 +
 fs/ntfs/file.c                 | 1 +
 fs/ntfs/index.c                | 2 ++
 fs/ntfs/mft.c                  | 1 +
 fs/ntfs/namei.c                | 1 +
 fs/ocfs2/acl.c                 | 1 +
 fs/ocfs2/buffer_head_io.c      | 1 -
 fs/ocfs2/cluster/heartbeat.c   | 1 +
 fs/ocfs2/cluster/nodemanager.c | 1 +
 fs/ocfs2/cluster/quorum.c      | 1 -
 fs/ocfs2/dlm/dlmast.c          | 1 -
 fs/ocfs2/dlm/dlmconvert.c      | 1 -
 fs/ocfs2/dlm/dlmthread.c       | 1 -
 fs/ocfs2/dlm/dlmunlock.c       | 1 -
 fs/ocfs2/extent_map.c          | 1 +
 fs/ocfs2/heartbeat.c           | 1 -
 fs/ocfs2/inode.c               | 1 -
 fs/ocfs2/mmap.c                | 1 -
 fs/ocfs2/quota_global.c        | 1 +
 fs/ocfs2/quota_local.c         | 1 +
 fs/ocfs2/refcounttree.c        | 1 -
 fs/ocfs2/stack_o2cb.c          | 1 +
 fs/ocfs2/stack_user.c          | 1 +
 fs/ocfs2/sysfile.c             | 1 -
 fs/omfs/inode.c                | 1 +
 fs/open.c                      | 2 +-
 fs/partitions/check.c          | 1 +
 fs/partitions/efi.c            | 1 +
 fs/proc/array.c                | 1 -
 fs/proc/base.c                 | 1 +
 fs/proc/generic.c              | 1 +
 fs/proc/inode.c                | 1 +
 fs/proc/kcore.c                | 1 +
 fs/proc/nommu.c                | 1 -
 fs/proc/proc_devtree.c         | 1 +
 fs/proc/proc_net.c             | 1 +
 fs/proc/stat.c                 | 1 -
 fs/proc/task_mmu.c             | 1 +
 fs/proc/task_nommu.c           | 1 +
 fs/proc/vmcore.c               | 1 +
 fs/quota/netlink.c             | 1 +
 fs/ramfs/file-nommu.c          | 1 +
 fs/ramfs/inode.c               | 1 +
 fs/reiserfs/dir.c              | 1 +
 fs/reiserfs/fix_node.c         | 1 +
 fs/reiserfs/inode.c            | 1 +
 fs/reiserfs/journal.c          | 1 +
 fs/reiserfs/namei.c            | 1 +
 fs/reiserfs/super.c            | 1 +
 fs/reiserfs/xattr.c            | 1 +
 fs/reiserfs/xattr_acl.c        | 1 +
 fs/reiserfs/xattr_security.c   | 1 +
 fs/signalfd.c                  | 1 +
 fs/smbfs/file.c                | 1 -
 fs/smbfs/smbiod.c              | 1 -
 fs/smbfs/symlink.c             | 1 +
 fs/splice.c                    | 1 +
 fs/squashfs/symlink.c          | 1 -
 fs/squashfs/zlib_wrapper.c     | 1 +
 fs/sync.c                      | 1 +
 fs/sysfs/inode.c               | 1 +
 fs/sysfs/mount.c               | 1 +
 fs/sysfs/symlink.c             | 1 +
 fs/timerfd.c                   | 1 +
 fs/ubifs/commit.c              | 1 +
 fs/ubifs/debug.c               | 1 +
 fs/ubifs/file.c                | 1 +
 fs/ubifs/gc.c                  | 1 +
 fs/ubifs/io.c                  | 1 +
 fs/ubifs/lpt.c                 | 1 +
 fs/ubifs/lpt_commit.c          | 1 +
 fs/ubifs/recovery.c            | 1 +
 fs/ubifs/sb.c                  | 1 +
 fs/ubifs/tnc.c                 | 1 +
 fs/ubifs/ubifs.h               | 1 +
 fs/ubifs/xattr.c               | 1 +
 fs/udf/partition.c             | 1 -
 fs/udf/symlink.c               | 1 -
 fs/udf/unicode.c               | 1 +
 fs/xattr_acl.c                 | 2 +-
 fs/xfs/linux-2.6/kmem.c        | 1 +
 fs/xfs/linux-2.6/xfs_acl.c     | 1 +
 fs/xfs/linux-2.6/xfs_aops.c    | 1 +
 fs/xfs/linux-2.6/xfs_buf.c     | 2 +-
 fs/xfs/linux-2.6/xfs_ioctl.c   | 1 +
 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 +
 fs/xfs/linux-2.6/xfs_iops.c    | 1 +
 fs/xfs/linux-2.6/xfs_super.c   | 1 +
 353 files changed, 300 insertions(+), 72 deletions(-)

(limited to 'fs')

diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index e777961939f..0dbe0d139ac 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -22,6 +22,7 @@
 
 #include <linux/jiffies.h>
 #include <linux/file.h>
+#include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 08b2eb15704..82ee460e534 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/idr.h>
 #include <net/9p/9p.h>
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6c7f6a25111..cb57d332618 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -29,6 +29,7 @@
 #include <linux/sched.h>
 #include <linux/parser.h>
 #include <linux/idr.h>
+#include <linux/slab.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index d74325295b1..cbf4e50f393 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -34,6 +34,7 @@
 #include <linux/namei.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index d8a3afe4ff7..909711f57c0 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -32,6 +32,7 @@
 #include <linux/sched.h>
 #include <linux/inet.h>
 #include <linux/idr.h>
+#include <linux/slab.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 5fe45d692c9..63c2b5af268 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -34,6 +34,7 @@
 #include <linux/namei.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 69357c0d989..a271549d9e2 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -37,6 +37,7 @@
 #include <linux/mount.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 6910a98bd73..4a3af7075c1 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -13,6 +13,7 @@
 #include <linux/parser.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/statfs.h>
 #include "adfs.h"
diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c
index 8306d53307e..3e262711ae0 100644
--- a/fs/affs/bitmap.c
+++ b/fs/affs/bitmap.c
@@ -7,6 +7,7 @@
  *  block allocation, deallocation, calculation of free space.
  */
 
+#include <linux/slab.h>
 #include "affs.h"
 
 /* This is, of course, shamelessly stolen from fs/minix */
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index c9744d771d9..f4b2a4ee4f9 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -10,6 +10,7 @@
  *  (C) 1991  Linus Torvalds - minix filesystem
  */
 #include <linux/sched.h>
+#include <linux/gfp.h>
 #include "affs.h"
 
 extern const struct inode_operations affs_symlink_inode_operations;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index d41e9673cd9..16a3e4765f6 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -17,6 +17,7 @@
 #include <linux/magic.h>
 #include <linux/sched.h>
 #include <linux/smp_lock.h>
+#include <linux/slab.h>
 #include "affs.h"
 
 extern struct timezone sys_tz;
diff --git a/fs/afs/cache.c b/fs/afs/cache.c
index e2b1d3f1651..0fb315dd4d2 100644
--- a/fs/afs/cache.c
+++ b/fs/afs/cache.c
@@ -9,7 +9,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/slab.h>
 #include <linux/sched.h>
 #include "internal.h"
 
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index eb765489164..a3bcec75c54 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -11,6 +11,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/ip.h>
 #include "internal.h"
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 88067f36e5e..adc1cb771b5 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/ctype.h>
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 39b301662f2..0df9bc2b724 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -12,10 +12,10 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
+#include <linux/gfp.h>
 #include "internal.h"
 
 static int afs_readpage(struct file *file, struct page *page);
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 023b95b0d9d..4bd0218473a 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/circ_buf.h>
 #include "internal.h"
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index c048f065875..d00b312e311 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -16,7 +16,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/sched.h>
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 5ffb570cd3a..5e813a816ce 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -12,11 +12,11 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/gfp.h>
 #include "internal.h"
 
 
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index bde3f19c099..67cf810e0fd 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/slab.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <rxrpc/packet.h>
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 36c1306e09e..340afd0cd18 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -9,6 +9,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/gfp.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include "internal.h"
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 6e689208def..9ac260d1361 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -11,6 +11,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include "internal.h"
diff --git a/fs/afs/vnode.c b/fs/afs/vnode.c
index 2f05c4fc2a7..25cf4c3f4ff 100644
--- a/fs/afs/vnode.c
+++ b/fs/afs/vnode.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include "internal.h"
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 2de009565d8..e4b75d6eda8 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -12,7 +12,6 @@
 #include <linux/file.h>
 #include <linux/poll.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index 4a1401cea0a..8713c7cfbc7 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -13,6 +13,7 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/stat.h>
+#include <linux/slab.h>
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/smp_lock.h>
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index c8a80dffb45..d29b7f6df86 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -22,6 +22,7 @@
 #include <linux/magic.h>
 #include <linux/dcache.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 
 #include "autofs_i.h"
 
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index a015b49891d..109a6c606d9 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -15,6 +15,7 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/stat.h>
+#include <linux/slab.h>
 #include <linux/param.h>
 #include <linux/time.h>
 #include "autofs_i.h"
diff --git a/fs/befs/datastream.c b/fs/befs/datastream.c
index e3287d0d1a5..59096b5e0fc 100644
--- a/fs/befs/datastream.c
+++ b/fs/befs/datastream.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/string.h>
 
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 9b6aef0f75e..f96eff04e11 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -20,11 +20,11 @@
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
-#include <linux/slab.h>
 #include <linux/binfmts.h>
 #include <linux/personality.h>
 #include <linux/init.h>
 #include <linux/coredump.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index 32fb00b52cd..b8e8b0acf9b 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/stat.h>
-#include <linux/slab.h>
 #include <linux/binfmts.h>
 #include <linux/elf.h>
 #include <linux/init.h>
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 08343505e18..aca9d55afb2 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -8,7 +8,6 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/stat.h>
-#include <linux/slab.h>
 #include <linux/binfmts.h>
 #include <linux/init.h>
 #include <linux/file.h>
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index a16f29e888c..612a5c38d3c 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -24,6 +24,7 @@
 #include <linux/mempool.h>
 #include <linux/bio.h>
 #include <linux/workqueue.h>
+#include <linux/slab.h>
 
 struct integrity_slab {
 	struct kmem_cache *slab;
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 6df6d6ed74f..6ef7b26724e 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -22,6 +22,7 @@
 #include <linux/posix_acl_xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include "ctree.h"
 #include "btrfs_inode.h"
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index c0861e781cd..462859a3014 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/kthread.h>
+#include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 28b92a7218a..629880ec8ac 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -32,6 +32,7 @@
 #include <linux/writeback.h>
 #include <linux/bit_spinlock.h>
 #include <linux/pagevec.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index c4bc570a396..8e29260cd0b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0af2e386857..8a6518a3f04 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -26,6 +26,7 @@
 #include <linux/completion.h>
 #include <linux/backing-dev.h>
 #include <linux/wait.h>
+#include <linux/slab.h>
 #include <asm/kmap_types.h>
 #include "extent_io.h"
 #include "extent_map.h"
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 84e6781413b..902ce507c4e 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/sort.h>
 #include "ctree.h"
 #include "delayed-ref.h"
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 11d0ad30e20..e57ded75d91 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -27,6 +27,7 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/crc32c.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1727b26fb19..fa2907d531a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -22,6 +22,7 @@
 #include <linux/sort.h>
 #include <linux/rcupdate.h>
 #include <linux/kthread.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "hash.h"
 #include "ctree.h"
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c99121ac5d6..0adceb52516 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2,7 +2,6 @@
 #include <linux/slab.h>
 #include <linux/bio.h>
 #include <linux/mm.h>
-#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/page-flags.h>
 #include <linux/module.h>
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 28d87ba60ce..454ca52d645 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1,5 +1,4 @@
 #include <linux/err.h>
-#include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 9b99886562d..54a255065aa 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/bio.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include "ctree.h"
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ee3323c7fc1..29ff749ff4c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -28,6 +28,7 @@
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
+#include <linux/slab.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index dd831ed31ee..f488fac04d9 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -18,6 +18,7 @@
 
 #include <linux/pagemap.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/math64.h>
 #include "ctree.h"
 #include "free-space-cache.h"
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 02bb099845f..2fe494c84e6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -36,6 +36,7 @@
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/falloc.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2845c6ceecd..9b3d73a0fdc 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -39,6 +39,7 @@
 #include <linux/security.h>
 #include <linux/xattr.h>
 #include <linux/vmalloc.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 1c36e5cd8f5..6151f2ea38b 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -16,7 +16,6 @@
  * Boston, MA 021110-1307, USA.
  */
 #include <linux/sched.h>
-#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/spinlock.h>
 #include <linux/page-flags.h>
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index a8ffecd0b49..ecb22ff7d1f 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -16,7 +16,6 @@
  * Boston, MA 021110-1307, USA.
  */
 
-#include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
diff --git a/fs/btrfs/ref-cache.c b/fs/btrfs/ref-cache.c
index d0cc62bccb9..a97314cf6bd 100644
--- a/fs/btrfs/ref-cache.c
+++ b/fs/btrfs/ref-cache.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/sort.h>
 #include "ctree.h"
 #include "ref-cache.h"
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 0b23942cbc0..e558dd941de 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -21,6 +21,7 @@
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
 #include <linux/rbtree.h>
+#include <linux/slab.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9ac612e6ca6..693a664318f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -38,6 +38,7 @@
 #include <linux/namei.h>
 #include <linux/miscdevice.h>
 #include <linux/magic.h>
+#include <linux/slab.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 2d654c1c794..c0d0e3e7bc6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/writeback.h>
 #include <linux/pagemap.h>
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1255fcc8ade..af57dd2b43d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9df8e3f1cca..1692ec9cd7b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -17,6 +17,7 @@
  */
 #include <linux/sched.h>
 #include <linux/bio.h>
+#include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
 #include <linux/random.h>
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 27089311fbe..37fe101a4e0 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -9,6 +9,7 @@
  * 2 of the Licence, or (at your option) any later version.
  */
 
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/buffer_head.h>
 #include "internal.h"
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index eeb4986ea7d..d5db84a1ee0 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -19,6 +19,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/security.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 #define CACHEFILES_KEYBUF_SIZE 512
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 1d833256386..0f0d41fbb03 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -10,6 +10,7 @@
  */
 
 #include <linux/mount.h>
+#include <linux/slab.h>
 #include <linux/file.h>
 #include "internal.h"
 
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index f3e7a0bf068..e18b183b47e 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -16,6 +16,7 @@
 #include <linux/fsnotify.h>
 #include <linux/quotaops.h>
 #include <linux/xattr.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 static const char cachefiles_xattr_cache[] =
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index ce8ef610772..aa3cd7cc3e4 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>	/* generic_writepages */
+#include <linux/slab.h>
 #include <linux/pagevec.h>
 #include <linux/task_io_accounting_ops.h>
 
diff --git a/fs/ceph/auth.c b/fs/ceph/auth.c
index abb204fea6c..f6394b94b86 100644
--- a/fs/ceph/auth.c
+++ b/fs/ceph/auth.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/err.h>
 
 #include "types.h"
diff --git a/fs/ceph/auth_none.c b/fs/ceph/auth_none.c
index b4ef6f0a6c8..8cd9e3af07f 100644
--- a/fs/ceph/auth_none.c
+++ b/fs/ceph/auth_none.c
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 
 #include "auth_none.h"
 #include "auth.h"
diff --git a/fs/ceph/auth_x.c b/fs/ceph/auth_x.c
index 8d8a8496476..d9001a4dc8c 100644
--- a/fs/ceph/auth_x.c
+++ b/fs/ceph/auth_x.c
@@ -4,6 +4,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/slab.h>
 
 #include "auth_x.h"
 #include "auth_x_protocol.h"
diff --git a/fs/ceph/buffer.c b/fs/ceph/buffer.c
index b98086c7aeb..c67535d70aa 100644
--- a/fs/ceph/buffer.c
+++ b/fs/ceph/buffer.c
@@ -1,5 +1,8 @@
 
 #include "ceph_debug.h"
+
+#include <linux/slab.h>
+
 #include "buffer.h"
 #include "decode.h"
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 7d0a0d0adc1..3710e077a85 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 291ac288e79..f704b3b6242 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -3,6 +3,7 @@
 
 #include <linux/err.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <crypto/hash.h>
 
 #include "crypto.h"
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index e159f141511..f7048da92ac 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/device.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8a9116e15b7..7261dc6c2ea 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -3,6 +3,7 @@
 #include <linux/spinlock.h>
 #include <linux/fs_struct.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include "super.h"
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index fc68e39cbad..9d67572fb32 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/exportfs.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 
 #include "super.h"
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 5d2af8464f6..4add3d5da2c 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/namei.h>
 #include <linux/writeback.h>
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 5c7920be642..60a9a4ae47b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/wait.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 
 #include "mds_client.h"
diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index a32f0f896d9..8f1715ffbe4 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -6,6 +6,7 @@
 #include <linux/inet.h>
 #include <linux/kthread.h>
 #include <linux/net.h>
+#include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
 #include <net/tcp.h>
diff --git a/fs/ceph/mon_client.c b/fs/ceph/mon_client.c
index 890597c09d4..8fdc011ca95 100644
--- a/fs/ceph/mon_client.c
+++ b/fs/ceph/mon_client.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/sched.h>
 
diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index d82fe87c2a6..21c6623c4b0 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -1,4 +1,7 @@
 
+#include "ceph_debug.h"
+
+#include <linux/slab.h>
 #include <asm/div64.h>
 
 #include "super.h"
@@ -6,7 +9,6 @@
 #include "crush/hash.h"
 #include "crush/mapper.h"
 #include "decode.h"
-#include "ceph_debug.h"
 
 char *ceph_osdmap_state_str(char *str, int len, int state)
 {
diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
index 370e9369547..5f8dbf7c745 100644
--- a/fs/ceph/pagelist.c
+++ b/fs/ceph/pagelist.c
@@ -1,4 +1,5 @@
 
+#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index df04e210a05..e6f9bc57d47 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1,6 +1,7 @@
 #include "ceph_debug.h"
 
 #include <linux/sort.h>
+#include <linux/slab.h>
 
 #include "super.h"
 #include "decode.h"
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 4290a6e860b..75d02eaa127 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -11,6 +11,7 @@
 #include <linux/rwsem.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include <linux/statfs.h>
 #include <linux/string.h>
 #include <linux/version.h>
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 65d12036b67..ca702c67bc6 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -12,6 +12,7 @@
 #include <linux/pagemap.h>
 #include <linux/wait.h>
 #include <linux/writeback.h>
+#include <linux/slab.h>
 
 #include "types.h"
 #include "messenger.h"
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 37d6ce64569..2845422907f 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -3,6 +3,7 @@
 #include "decode.h"
 
 #include <linux/xattr.h>
+#include <linux/slab.h>
 
 static bool ceph_is_valid_xattr(const char *name)
 {
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index b1d61d0bdfc..78e4d2a3a68 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -15,6 +15,7 @@
 #include <linux/dcache.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 #include <linux/vfs.h>
 #include <linux/fs.h>
 #include "cifsglob.h"
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index 8ec7736ce95..310d12f69a9 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/list.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <keys/user-type.h>
 #include <linux/key-type.h>
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 714a542cbaf..d07676bd76d 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -19,6 +19,7 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include "cifs_unicode.h"
 #include "cifs_uniupr.h"
 #include "cifspdu.h"
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 7dfe0842a6f..9b716d044bb 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsacl.h"
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 7efe1745494..fbe986430d0 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifs_debug.h"
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 63c89d1d70b..ecf0ffbe2b6 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -18,6 +18,7 @@
  */
 #include <linux/in.h>
 #include <linux/in6.h>
+#include <linux/slab.h>
 #include <linux/slow-work.h>
 #include "cifs_fs_sb.h"
 #include "cifsacl.h"
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 7cc7f83e931..3f4fbd67050 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -30,6 +30,7 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/vfs.h>
+#include <linux/slab.h>
 #include <linux/posix_acl_xattr.h>
 #include <asm/uaccess.h>
 #include "cifspdu.h"
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 45eb6cba793..d9566bf8f91 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -23,6 +23,7 @@
 #include <linux/string.h>
 #include <linux/list.h>
 #include <linux/wait.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/ctype.h>
 #include <linux/utsname.h>
diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c
index 87948147d7e..6f8a0e3fb25 100644
--- a/fs/cifs/dns_resolve.c
+++ b/fs/cifs/dns_resolve.c
@@ -23,6 +23,7 @@
  *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
+#include <linux/slab.h>
 #include <keys/user-type.h>
 #include "dns_resolve.h"
 #include "cifsglob.h"
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ca2ba7a0193..058b390d3da 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -31,6 +31,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/delay.h>
 #include <linux/mount.h>
+#include <linux/slab.h>
 #include <asm/div64.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 723daaccbd0..35ec1171621 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -20,6 +20,7 @@
  */
 #include <linux/fs.h>
 #include <linux/stat.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <asm/div64.h>
 #include "cifsfs.h"
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index fc1e0487eae..c1a9d4236a8 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -20,6 +20,7 @@
  */
 #include <linux/fs.h>
 #include <linux/stat.h>
+#include <linux/slab.h>
 #include <linux/namei.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index c343b14ba2d..18e0bc1fb59 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -22,6 +22,7 @@
  */
 #include <linux/fs.h>
 #include <linux/pagemap.h>
+#include <linux/slab.h>
 #include <linux/stat.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index aaa9c1c5a5b..7c3fd7463f4 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -29,6 +29,7 @@
 #include "ntlmssp.h"
 #include "nterr.h"
 #include <linux/utsname.h>
+#include <linux/slab.h>
 #include "cifs_spnego.h"
 
 extern void SMBNTencrypt(unsigned char *passwd, unsigned char *c8,
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 93fb09a99c6..192ea51af20 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -24,6 +24,7 @@
 */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 07b8e71544e..ad081fe7eb1 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -22,6 +22,7 @@
 
 #include <linux/fs.h>
 #include <linux/list.h>
+#include <linux/gfp.h>
 #include <linux/wait.h>
 #include <linux/net.h>
 #include <linux/delay.h>
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 3e2ef0de120..f555ce077d4 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -21,6 +21,7 @@
 
 #include <linux/fs.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/slab.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
 #include "cifsglob.h"
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 4bb9d0a5dec..ccd98b0f2b0 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/time.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/stat.h>
 #include <linux/errno.h>
diff --git a/fs/coda/file.c b/fs/coda/file.c
index ffd42815fda..4c813f2cdc5 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/smp_lock.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 
 #include <linux/coda.h>
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 830f51abb97..a1695dcadd9 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -18,6 +18,7 @@
 #include <linux/smp_lock.h>
 #include <linux/file.h>
 #include <linux/vfs.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index c274d949179..f09c5ed76f6 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -26,6 +26,7 @@
 #include <linux/stat.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/vfs.h>
diff --git a/fs/compat.c b/fs/compat.c
index 030602d453b..4b6ed03cc47 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -49,6 +49,7 @@
 #include <linux/mm.h>
 #include <linux/eventpoll.h>
 #include <linux/fs_struct.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 6d55b61bfa7..c32a1b6a856 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -23,7 +23,6 @@
 #include <linux/ioctl.h>
 #include <linux/if.h>
 #include <linux/if_bridge.h>
-#include <linux/slab.h>
 #include <linux/raid/md_u.h>
 #include <linux/kd.h>
 #include <linux/route.h>
@@ -60,6 +59,7 @@
 #include <linux/i2c.h>
 #include <linux/i2c-dev.h>
 #include <linux/atalk.h>
+#include <linux/gfp.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci.h>
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index a2f746066c5..c8af2d91174 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -34,6 +34,7 @@
 #include <linux/capability.h>
 #include <linux/sched.h>
 #include <linux/lockdep.h>
+#include <linux/slab.h>
 
 #include <linux/configfs.h>
 #include "configfs_internal.h"
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 8421cea7d8c..8c8d64230c2 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -29,6 +29,7 @@
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 
 #include <linux/configfs.h>
 #include "configfs_internal.h"
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 32a5f46b115..0f3eb41d920 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -27,6 +27,7 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 
 #include <linux/configfs.h>
 #include "configfs_internal.h"
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 049d6c36da0..30a87b3dbca 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -27,6 +27,7 @@
 #include <linux/fsnotify.h>
 #include <linux/string.h>
 #include <linux/magic.h>
+#include <linux/slab.h>
 
 static struct vfsmount *debugfs_mount;
 static int debugfs_mount_count;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 8882ecc0f1b..0120247b41c 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -15,6 +15,7 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/tty.h>
 #include <linux/mutex.h>
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 0df24385081..b54bca03d92 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/configfs.h>
+#include <linux/slab.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <net/ipv6.h>
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index 29d6139c35f..c6cf2515874 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/ctype.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 
 #include "dlm_internal.h"
 #include "lock.h"
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 46ffd3eeaaf..17903b49129 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -56,6 +56,7 @@
    L: receive_xxxx_reply()     <-  R: send_xxxx_reply()
 */
 #include <linux/types.h>
+#include <linux/slab.h>
 #include "dlm_internal.h"
 #include <linux/dlm_device.h>
 #include "memory.h"
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 52cab160893..c0d35c62052 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -51,6 +51,7 @@
 #include <linux/file.h>
 #include <linux/mutex.h>
 #include <linux/sctp.h>
+#include <linux/slab.h>
 #include <net/sctp/user.h>
 #include <net/ipv6.h>
 
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index 052095cd592..2c6ad518100 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -9,6 +9,7 @@
 #include <net/genetlink.h>
 #include <linux/dlm.h>
 #include <linux/dlm_netlink.h>
+#include <linux/gfp.h>
 
 #include "dlm_internal.h"
 
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index b5f89aef3b2..d45c02db694 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -11,6 +11,7 @@
 #include <linux/poll.h>
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
+#include <linux/slab.h>
 
 #include "dlm_internal.h"
 #include "lockspace.h"
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index a4bfd31ac45..8b6e73c4743 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/dlm.h>
 #include <linux/dlm_device.h>
+#include <linux/slab.h>
 
 #include "dlm_internal.h"
 #include "lockspace.h"
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 7cb0a59f4b9..efb2b940039 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -33,6 +33,7 @@
 #include <linux/crypto.h>
 #include <linux/file.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 #include "ecryptfs_kernel.h"
 
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 8f006a0d607..906e803f7f7 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -26,6 +26,7 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/fs_stack.h>
+#include <linux/slab.h>
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 678172b61be..e7440a6f5eb 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -25,6 +25,7 @@
 
 #include <linux/file.h>
 #include <linux/poll.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/security.h>
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 4a430ab4115..d3362faf385 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -31,6 +31,7 @@
 #include <linux/mount.h>
 #include <linux/crypto.h>
 #include <linux/fs_stack.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 #include "ecryptfs_kernel.h"
 
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index a0a7847567e..89c5476506e 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -32,6 +32,7 @@
 #include <linux/random.h>
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index e14cf7e588d..d8c3a373aaf 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -22,6 +22,7 @@
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/mount.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index ea2f92101df..af1a8f01eba 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -35,6 +35,7 @@
 #include <linux/key.h>
 #include <linux/parser.h>
 #include <linux/fs_stack.h>
+#include <linux/slab.h>
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c
index f1c17e87c5f..2d8dbce9d48 100644
--- a/fs/ecryptfs/messaging.c
+++ b/fs/ecryptfs/messaging.c
@@ -20,6 +20,7 @@
  * 02111-1307, USA.
  */
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/user_namespace.h>
 #include <linux/nsproxy.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 4ec8f61ccf5..3745f612bcd 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -24,6 +24,7 @@
 #include <linux/random.h>
 #include <linux/miscdevice.h>
 #include <linux/poll.h>
+#include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/module.h>
 #include "ecryptfs_kernel.h"
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index df4ce99d059..d491237c98e 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -32,6 +32,7 @@
 #include <linux/file.h>
 #include <linux/crypto.h>
 #include <linux/scatterlist.h>
+#include <linux/slab.h>
 #include <asm/unaligned.h>
 #include "ecryptfs_kernel.h"
 
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index b15a43a80ab..fcef41c1d2c 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/key.h>
+#include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/smp_lock.h>
 #include <linux/file.h>
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 7758cc382ef..6bd3f76fdf8 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -11,6 +11,7 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/anon_inodes.h>
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index a17e4b733e3..76d2a79ef93 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -31,6 +31,7 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#include <linux/slab.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <scsi/scsi_device.h>
diff --git a/fs/exofs/ios.c b/fs/exofs/ios.c
index 5293bc411d1..4337cad7777 100644
--- a/fs/exofs/ios.c
+++ b/fs/exofs/ios.c
@@ -22,6 +22,7 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#include <linux/slab.h>
 #include <scsi/scsi_device.h>
 #include <asm/div64.h>
 
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 6cf5e4e84d6..18e57ea1e5b 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -37,6 +37,7 @@
 #include <linux/vfs.h>
 #include <linux/random.h>
 #include <linux/exportfs.h>
+#include <linux/slab.h>
 
 #include "exofs.h"
 
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 1d081f0cfec..3cf038c055d 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -13,6 +13,7 @@
 
 #include "ext2.h"
 #include <linux/quotaops.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/buffer_head.h>
 #include <linux/capability.h>
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index c8155845ac0..b118c6383c6 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/ext2_fs.h>
diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 161da2d3f89..a177122a1b2 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -14,6 +14,7 @@
 #include <linux/time.h>
 #include <linux/capability.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/jbd.h>
 #include <linux/ext3_fs.h>
 #include <linux/ext3_jbd.h>
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 474348788dd..3af91f476df 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/ext3_jbd.h>
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 983f0e12749..538c4865508 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -18,6 +18,7 @@
 #include <linux/pagemap.h>
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include "ext4.h"
 
 struct ext4_system_zone {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 11119e07233..5381802d605 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -39,6 +39,7 @@
 #include <linux/bio.h>
 #include <linux/workqueue.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 54df209d2ee..bde9d0b170c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -23,6 +23,7 @@
 
 #include "mballoc.h"
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 #include <trace/events/ext4.h>
 
 /*
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 8b87bd0eac9..34dcfc52ef4 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index aa5fe28d180..d1fc662cc31 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -15,6 +15,7 @@
 
 #include <linux/fs.h>
 #include <linux/quotaops.h>
+#include <linux/slab.h>
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 #include "ext4.h"
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index 983c253999a..8b145e98df0 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -7,6 +7,7 @@
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/security.h>
+#include <linux/slab.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 923990e4f16..113f0a1e565 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include "fat.h"
 
diff --git a/fs/fifo.c b/fs/fifo.c
index f8f97b8b6d4..5d6606ffc2d 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/pipe_fs_i.h>
diff --git a/fs/filesystems.c b/fs/filesystems.c
index a24c58e181d..68ba492d8ee 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -10,10 +10,10 @@
 #include <linux/fs.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 
 /*
diff --git a/fs/freevxfs/vxfs_subr.c b/fs/freevxfs/vxfs_subr.c
index ed8f0b0dd88..1429f3ae1e8 100644
--- a/fs/freevxfs/vxfs_subr.c
+++ b/fs/freevxfs/vxfs_subr.c
@@ -33,7 +33,6 @@
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 
 #include "vxfs_extern.h"
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 76fc4d594ac..781a322ccb4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
+#include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 3221a0c7944..1e1f286dd70 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -12,6 +12,7 @@
 #define FSCACHE_DEBUG_LEVEL COOKIE
 #include <linux/module.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include <linux/key.h>
 #include <keys/user-type.h>
 #include "internal.h"
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 9f6c928d458..f17cecafae4 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -14,6 +14,7 @@
 #define FSCACHE_DEBUG_LEVEL OPERATION
 #include <linux/module.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 atomic_t fscache_op_debug_id;
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 69809024d71..47aefd376e5 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -14,6 +14,7 @@
 #include <linux/fscache-cache.h>
 #include <linux/buffer_head.h>
 #include <linux/pagevec.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 /*
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index de792dcf327..e1f8171278b 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -44,6 +44,7 @@
 #include <linux/magic.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/stat.h>
 
diff --git a/fs/generic_acl.c b/fs/generic_acl.c
index 55458031e50..fe5df545765 100644
--- a/fs/generic_acl.c
+++ b/fs/generic_acl.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/gfp.h>
 #include <linux/fs.h>
 #include <linux/generic_acl.h>
 #include <linux/posix_acl.h>
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 583e823307a..5e411d5f469 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 91beddadd38..bb7907bde3d 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index d15876e9aa2..c22c2117483 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 38e3749d476..49f97d3bb69 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 569b46240f6..0e0470ed34c 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -9,6 +9,7 @@
 
 #include <linux/fs.h>
 #include <linux/dlm.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/gfs2_ondisk.h>
 
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index b4106ddaaa9..f07119d8955 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -10,6 +10,8 @@
 #ifndef __RGRP_DOT_H__
 #define __RGRP_DOT_H__
 
+#include <linux/slab.h>
+
 struct gfs2_rgrpd;
 struct gfs2_sbd;
 struct gfs2_holder;
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 419042f7f0b..54fd9842599 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 226f2bfbf16..53511291fe3 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -7,7 +7,6 @@
  * of the GNU General Public License version 2.
  */
 
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
diff --git a/fs/hfs/bnode.c b/fs/hfs/bnode.c
index 0d200068d0a..cdb41a1f6a6 100644
--- a/fs/hfs/bnode.c
+++ b/fs/hfs/bnode.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 
 #include "btree.h"
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 052f214ea6f..38a0a9917d7 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/pagemap.h>
+#include <linux/slab.h>
 #include <linux/log2.h>
 
 #include "btree.h"
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index 8bbe03c3f6d..86428f5ac99 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -11,6 +11,7 @@
 #include <linux/cdrom.h>
 #include <linux/genhd.h>
 #include <linux/nls.h>
+#include <linux/slab.h>
 
 #include "hfs_fs.h"
 #include "btree.h"
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 5ed7252b7b2..0a81eb7111f 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -19,6 +19,7 @@
 #include <linux/nls.h>
 #include <linux/parser.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/vfs.h>
 
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 3fcbb0e1f6f..572628b4b07 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -15,6 +15,7 @@
 #include <linux/nls.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include "hfsplus_fs.h"
 
 enum {
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 032604e5ef2..3a029d8f4cf 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -11,6 +11,7 @@
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/statfs.h>
+#include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include "hostfs.h"
diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c
index b6fca543544..eac5f96323e 100644
--- a/fs/hpfs/buffer.c
+++ b/fs/hpfs/buffer.c
@@ -6,6 +6,7 @@
  *  general buffer i/o
  */
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include "hpfs_fn.h"
 
 void hpfs_lock_creation(struct super_block *s)
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 26e3964a4b8..2338130cceb 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/smp_lock.h>
+#include <linux/slab.h>
 #include "hpfs_fn.h"
 
 static int hpfs_dir_release(struct inode *inode, struct file *filp)
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index ff90affb94e..1042a9bc97f 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/smp_lock.h>
+#include <linux/slab.h>
 #include "hpfs_fn.h"
 
 void hpfs_init_inode(struct inode *i)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index cadc4ce4865..aa53842c599 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/smp_lock.h>
 #include <linux/bitmap.h>
+#include <linux/slab.h>
 
 /* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */
 
diff --git a/fs/ioprio.c b/fs/ioprio.c
index c7c0b28d7d2..748cfb92dcc 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -19,6 +19,7 @@
  * See also Documentation/block/ioprio.txt
  *
  */
+#include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/ioprio.h>
 #include <linux/blkdev.h>
diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c
index 8ba5441063b..b9ab69b3a48 100644
--- a/fs/isofs/dir.c
+++ b/fs/isofs/dir.c
@@ -11,6 +11,7 @@
  *  isofs directory handling functions
  */
 #include <linux/smp_lock.h>
+#include <linux/gfp.h>
 #include "isofs.h"
 
 int isofs_name_translate(struct iso_directory_record *de, char *new, struct inode *inode)
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index eaa831311c9..ab438beb867 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/smp_lock.h>
+#include <linux/gfp.h>
 #include "isofs.h"
 
 /*
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 2c90e3ef625..ecb44c94ba8 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/jbd.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/bio.h>
diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c
index cb1a49ae605..54c9bc9e1b1 100644
--- a/fs/jbd/recovery.c
+++ b/fs/jbd/recovery.c
@@ -20,7 +20,6 @@
 #include <linux/fs.h>
 #include <linux/jbd.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
 #endif
 
 /*
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 73063285b13..049281b7cb8 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -20,7 +20,6 @@
 #include <linux/fs.h>
 #include <linux/jbd2.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
 #include <linux/crc32.h>
 #endif
 
diff --git a/fs/jffs2/compr_lzo.c b/fs/jffs2/compr_lzo.c
index 90cb60d0978..cd02acafde8 100644
--- a/fs/jffs2/compr_lzo.c
+++ b/fs/jffs2/compr_lzo.c
@@ -11,7 +11,6 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/lzo.h>
diff --git a/fs/jffs2/compr_zlib.c b/fs/jffs2/compr_zlib.c
index cfd301a5edf..b46661a4275 100644
--- a/fs/jffs2/compr_zlib.c
+++ b/fs/jffs2/compr_zlib.c
@@ -14,7 +14,6 @@
 #endif
 
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/zlib.h>
 #include <linux/zutil.h>
 #include "nodelist.h"
diff --git a/fs/jffs2/debug.c b/fs/jffs2/debug.c
index 5544d31c066..ec353841392 100644
--- a/fs/jffs2/debug.c
+++ b/fs/jffs2/debug.c
@@ -15,6 +15,7 @@
 #include <linux/crc32.h>
 #include <linux/jffs2.h>
 #include <linux/mtd/mtd.h>
+#include <linux/slab.h>
 #include "nodelist.h"
 #include "debug.h"
 
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index b7b74e29914..e7291c161a1 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/time.h>
 #include <linux/pagemap.h>
diff --git a/fs/jffs2/nodelist.c b/fs/jffs2/nodelist.c
index 87c6f555e1a..af02bd13846 100644
--- a/fs/jffs2/nodelist.c
+++ b/fs/jffs2/nodelist.c
@@ -15,7 +15,6 @@
 #include <linux/mtd/mtd.h>
 #include <linux/rbtree.h>
 #include <linux/crc32.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include "nodelist.h"
 
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 21a052915aa..191359dde4e 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/mtd/mtd.h>
 #include <linux/compiler.h>
 #include <linux/sched.h> /* For cond_resched() */
diff --git a/fs/jffs2/symlink.c b/fs/jffs2/symlink.c
index 4ec11e8bda8..b955626071c 100644
--- a/fs/jffs2/symlink.c
+++ b/fs/jffs2/symlink.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include "nodelist.h"
diff --git a/fs/jffs2/write.c b/fs/jffs2/write.c
index ca29440e943..c819eb0e982 100644
--- a/fs/jffs2/write.c
+++ b/fs/jffs2/write.c
@@ -12,7 +12,6 @@
 #include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/crc32.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/mtd/mtd.h>
 #include "nodelist.h"
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index 213169780b6..1057a4998e4 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/posix_acl_xattr.h>
 #include "jfs_incore.h"
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index d9b031cf69f..6c4dfcbf3f5 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include "jfs_incore.h"
 #include "jfs_superblock.h"
 #include "jfs_dmap.h"
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 0e4623be70c..9197a1b0d02 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -102,6 +102,7 @@
 
 #include <linux/fs.h>
 #include <linux/quotaops.h>
+#include <linux/slab.h>
 #include "jfs_incore.h"
 #include "jfs_superblock.h"
 #include "jfs_filsys.h"
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index 0fc30407f03..f8332dc8eeb 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -45,6 +45,7 @@
 #include <linux/buffer_head.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
+#include <linux/slab.h>
 
 #include "jfs_incore.h"
 #include "jfs_inode.h"
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 335c4de6552..c51af2a1451 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -70,6 +70,7 @@
 #include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 #include "jfs_incore.h"
 #include "jfs_filsys.h"
 #include "jfs_metapage.h"
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 07b6c5dfb4b..48b44bd8267 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/bio.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/buffer_head.h>
 #include <linux/mempool.h>
diff --git a/fs/jfs/jfs_unicode.h b/fs/jfs/jfs_unicode.h
index 3fbb3a22559..8f0f02cb6ca 100644
--- a/fs/jfs/jfs_unicode.h
+++ b/fs/jfs/jfs_unicode.h
@@ -19,6 +19,7 @@
 #ifndef _H_JFS_UNICODE
 #define _H_JFS_UNICODE
 
+#include <linux/slab.h>
 #include <asm/byteorder.h>
 #include "jfs_types.h"
 
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 266699deb1c..157382fa625 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -30,6 +30,7 @@
 #include <linux/buffer_head.h>
 #include <linux/exportfs.h>
 #include <linux/crc32.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/smp_lock.h>
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 1f594ab2189..fa96bbb2634 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/slab.h>
 #include <linux/quotaops.h>
 #include <linux/security.h>
 #include "jfs_incore.h"
diff --git a/fs/libfs.c b/fs/libfs.c
index 9e50bcf5585..ea9a6cc9b35 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -5,6 +5,7 @@
 
 #include <linux/module.h>
 #include <linux/pagemap.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/vfs.h>
 #include <linux/mutex.h>
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index fc9032dc886..64fd427c993 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -8,6 +8,7 @@
 
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/nfs_fs.h>
 #include <linux/sunrpc/clnt.h>
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index c81249fef11..7932c399fab 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -8,6 +8,7 @@
 
 #include <linux/module.h>
 #include <linux/smp_lock.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index fefa4df3f00..e3015464fba 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -10,6 +10,7 @@
 #include <linux/utsname.h>
 #include <linux/kernel.h>
 #include <linux/ktime.h>
+#include <linux/slab.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprtsock.h>
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 7d150517ddf..f1bacf1a039 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -21,7 +21,6 @@
 #include <linux/errno.h>
 #include <linux/in.h>
 #include <linux/uio.h>
-#include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/smp_lock.h>
 #include <linux/mutex.h>
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index a7966eed3c1..031c6569a13 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -9,7 +9,6 @@
 
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index d1001790fa9..84055d31bfc 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 56c9519d900..0f2ab741ae7 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -9,7 +9,6 @@
 
 #include <linux/types.h>
 #include <linux/time.h>
-#include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index ad478da7ca6..d0ef94cfb3d 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -10,6 +10,7 @@
 #include <linux/string.h>
 #include <linux/time.h>
 #include <linux/in.h>
+#include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 9718c22f186..18e8c144c7f 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -9,6 +9,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
+#include <linux/gfp.h>
 
 #define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
 
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index 56a8bfbb012..e1cb9956610 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -6,7 +6,7 @@
  * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
  */
 #include "logfs.h"
-
+#include <linux/slab.h>
 
 /*
  * Atomic dir operations
diff --git a/fs/logfs/gc.c b/fs/logfs/gc.c
index 92949f95a90..84e36f52fe9 100644
--- a/fs/logfs/gc.c
+++ b/fs/logfs/gc.c
@@ -7,6 +7,7 @@
  */
 #include "logfs.h"
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 /*
  * Wear leveling needs to kick in when the difference between low erase
diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c
index 33ec1aeaeec..14ed27274da 100644
--- a/fs/logfs/inode.c
+++ b/fs/logfs/inode.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
  */
 #include "logfs.h"
+#include <linux/slab.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 
diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 6ad30a4c905..f186043e862 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -6,6 +6,7 @@
  * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
  */
 #include "logfs.h"
+#include <linux/slab.h>
 
 static void logfs_calc_free(struct super_block *sb)
 {
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 7a23b3e7c0a..d5919af2c7a 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -18,6 +18,7 @@
  */
 #include "logfs.h"
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 static u64 adjust_bix(u64 bix, level_t level)
 {
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 1a14f9910d5..614d7a6fda2 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -10,6 +10,7 @@
  * three kinds of objects: inodes, dentries and blocks, both data and indirect.
  */
 #include "logfs.h"
+#include <linux/slab.h>
 
 static int logfs_mark_segment_bad(struct super_block *sb, u32 segno)
 {
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index c66beab78de..46990eafe05 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -11,6 +11,7 @@
  */
 #include "logfs.h"
 #include <linux/bio.h>
+#include <linux/slab.h>
 #include <linux/mtd/mtd.h>
 #include <linux/statfs.h>
 #include <linux/buffer_head.h>
diff --git a/fs/minix/itree_v1.c b/fs/minix/itree_v1.c
index 82d6554b02f..282e15ad8cd 100644
--- a/fs/minix/itree_v1.c
+++ b/fs/minix/itree_v1.c
@@ -1,4 +1,5 @@
 #include <linux/buffer_head.h>
+#include <linux/slab.h>
 #include "minix.h"
 
 enum {DEPTH = 3, DIRECT = 7};	/* Only double indirect */
diff --git a/fs/mpage.c b/fs/mpage.c
index 598d54e200e..fd56ca2ea55 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/kdev_t.h>
+#include <linux/gfp.h>
 #include <linux/bio.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index b8b5b30d53f..7edfcd4d5e5 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -15,7 +15,6 @@
 #include <linux/errno.h>
 #include <linux/stat.h>
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <asm/uaccess.h>
diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c
index 6a7d901f193..1daabb90e0a 100644
--- a/fs/ncpfs/file.c
+++ b/fs/ncpfs/file.c
@@ -15,7 +15,6 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
 #include <linux/smp_lock.h>
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index ec8f45f12e0..60a5e2864ea 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -15,6 +15,7 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/mount.h>
+#include <linux/slab.h>
 #include <linux/highuid.h>
 #include <linux/smp_lock.h>
 #include <linux/vmalloc.h>
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 15458decdb8..56f5b3a0e1e 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -9,12 +9,12 @@
 #include <linux/stat.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
+#include <linux/gfp.h>
 #include <linux/mm.h>
 #include <linux/shm.h>
 #include <linux/errno.h>
 #include <linux/mman.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/fcntl.h>
 #include <linux/ncp_fs.h>
 
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index e37df8d5fe7..c7ff6c700a6 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/netdevice.h>
 #include <linux/signal.h>
+#include <linux/slab.h>
 #include <net/scm.h>
 #include <net/sock.h>
 #include <linux/ipx.h>
diff --git a/fs/ncpfs/symlink.c b/fs/ncpfs/symlink.c
index e3d26c1bd10..c634fd17b33 100644
--- a/fs/ncpfs/symlink.c
+++ b/fs/ncpfs/symlink.c
@@ -27,6 +27,7 @@
 #include <linux/fs.h>
 #include <linux/ncp_fs.h>
 #include <linux/time.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/stat.h>
 #include "ncplib_kernel.h"
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index b4ffd0146ea..84690319e62 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -10,6 +10,7 @@
 #include <linux/moduleparam.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
 
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 84761b5bb8e..a08770a7e85 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -7,6 +7,7 @@
  */
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
+#include <linux/slab.h>
 #include "nfs4_fs.h"
 #include "callback.h"
 #include "delegation.h"
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index a2b8b4df125..05af212f0ed 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -9,6 +9,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
+#include <linux/slab.h>
 #include "nfs4_fs.h"
 #include "callback.h"
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2274f173733..2a3d352c0bf 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -35,6 +35,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
+#include <linux/slab.h>
 #include <net/ipv6.h>
 #include <linux/nfs_xdr.h>
 #include <linux/sunrpc/bc_xprt.h>
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 2563bebc4c6..15671245c6e 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -10,6 +10,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 0d289823e85..ad4cd31d605 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -44,6 +44,7 @@
 #include <linux/file.h>
 #include <linux/pagemap.h>
 #include <linux/kref.h>
+#include <linux/slab.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index 3f0cd4dfdda..76fd235d002 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -9,6 +9,7 @@
 #include <linux/hash.h>
 #include <linux/string.h>
 #include <linux/kmod.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/socket.h>
 #include <linux/seq_file.h>
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index ae0d9273653..8d965bddb87 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -24,9 +24,9 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/aio.h>
+#include <linux/gfp.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 237874f1af2..a6b16ed9322 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -17,6 +17,7 @@
 #include <linux/nfs_fs_sb.h>
 #include <linux/in6.h>
 #include <linux/seq_file.h>
+#include <linux/slab.h>
 
 #include "internal.h"
 #include "iostat.h"
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index e358df75a6a..737128f777f 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -36,6 +36,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/nfs_xdr.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 40c76678289..7888cf36022 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/dcache.h>
+#include <linux/gfp.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/nfs_fs.h>
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 7bc2da8efd4..81cf1425791 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -12,7 +12,6 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index bac60515a4b..d150ae0c5ec 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -1,4 +1,5 @@
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
 #include <linux/nfs_fs.h>
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 24992f0a29f..e701002694e 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/sunrpc/clnt.h>
+#include <linux/slab.h>
 #include <linux/nfs.h>
 #include <linux/nfs3.h>
 #include <linux/nfs_fs.h>
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 5fe5492fbd2..56a86f6ac8b 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -9,7 +9,6 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index fa3408f2011..f071d12c613 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -11,6 +11,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/nfs_fs.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/vfs.h>
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f9254fb0c9d..d79a7b37e56 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -39,6 +39,7 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/slab.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs.h>
 #include <linux/nfs4.h>
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index dd17713413a..38f3b582e7c 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -38,7 +38,6 @@
 #include <linux/param.h>
 #include <linux/time.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/in.h>
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index c752d944fe9..0288be80444 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -29,7 +29,6 @@
 
 #include <linux/types.h>
 #include <linux/param.h>
-#include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/errno.h>
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 6baf9a39346..e01637240ee 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -48,6 +48,7 @@
 #include <linux/vfs.h>
 #include <linux/inet.h>
 #include <linux/in6.h>
+#include <linux/slab.h>
 #include <net/ipv6.h>
 #include <linux/netdevice.h>
 #include <linux/nfs_xdr.h>
diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c
index 2ea9e5c27e5..05c9e02f415 100644
--- a/fs/nfs/symlink.c
+++ b/fs/nfs/symlink.c
@@ -19,7 +19,6 @@
 #include <linux/pagemap.h>
 #include <linux/stat.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/namei.h>
 
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index 04133aacb1e..fc1c52571c0 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -22,6 +22,7 @@
 
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <linux/sunrpc/xdr.h>
 #include <linux/nfsacl.h>
 #include <linux/nfs3.h>
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index a0c4016413f..872a5ef550c 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -12,6 +12,7 @@
  * Copyright (C) 1995, 1996 Olaf Kirch, <okir@monad.swb.de>
  */
 
+#include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/module.h>
 #include <linux/exportfs.h>
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index f20589d2ae2..6aa5590c367 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -7,6 +7,7 @@
 #include "nfsd.h"
 /* FIXME: nfsacl.h is a broken header */
 #include <linux/nfsacl.h>
+#include <linux/gfp.h>
 #include "cache.h"
 #include "xdr3.h"
 #include "vfs.h"
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index e0c4846bad9..a596e9d987e 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -7,6 +7,7 @@
 #include "nfsd.h"
 /* FIXME: nfsacl.h is a broken header */
 #include <linux/nfsacl.h>
+#include <linux/gfp.h>
 #include "cache.h"
 #include "xdr3.h"
 #include "vfs.h"
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 88150685df3..e4805261515 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -34,6 +34,7 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/slab.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs4_acl.h>
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 4bc22c763de..7e32bd394e8 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/sunrpc/clnt.h>
+#include <linux/slab.h>
 #include "nfsd.h"
 #include "state.h"
 
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 6e2983b27f3..c78dbf49342 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -36,6 +36,7 @@
 #include <linux/nfsd_idmap.h>
 #include <linux/seq_file.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 /*
  * Cache entry
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 37514c46984..2ab9e8501bf 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -33,6 +33,7 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 #include <linux/file.h>
+#include <linux/slab.h>
 
 #include "cache.h"
 #include "xdr4.h"
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 98fb98e330b..7a9ae3254a4 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -32,6 +32,7 @@
 */
 
 #include <linux/file.h>
+#include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/crypto.h>
 #include <linux/sched.h>
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c97fddbd17d..6a8fedaa4f5 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -34,6 +34,7 @@
 
 #include <linux/file.h>
 #include <linux/smp_lock.h>
+#include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/swap.h>
 #include <linux/sunrpc/svcauth_gss.h>
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c47b4d7bafa..e1703175ee2 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -40,6 +40,7 @@
  * at the end of nfs4svc_decode_compoundargs.
  */
 
+#include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/statfs.h>
 #include <linux/utsname.h>
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index da08560c481..4666a209678 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -8,6 +8,8 @@
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
  */
 
+#include <linux/slab.h>
+
 #include "nfsd.h"
 #include "cache.h"
 
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 0f0e77f2012..e3591073098 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -4,6 +4,7 @@
  * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
  */
 
+#include <linux/slab.h>
 #include <linux/namei.h>
 #include <linux/ctype.h>
 
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index a11b0e8678e..6dd5f1970e0 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -25,6 +25,7 @@
 #include <linux/xattr.h>
 #include <linux/jhash.h>
 #include <linux/ima.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/exportfs.h>
 #include <linux/writeback.h>
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 3f959f1879d..8d6356a804f 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -26,6 +26,7 @@
 #include <linux/buffer_head.h>
 #include <linux/fs.h>
 #include <linux/bitops.h>
+#include <linux/slab.h>
 #include "mdt.h"
 #include "alloc.h"
 
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 471e269536a..447ce47a330 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -27,6 +27,7 @@
 #include <linux/buffer_head.h>
 #include <linux/mm.h>
 #include <linux/backing-dev.h>
+#include <linux/gfp.h>
 #include "nilfs.h"
 #include "mdt.h"
 #include "dat.h"
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 8880a9e281e..145f03cd7d3 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -45,6 +45,7 @@
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
 #include <linux/hash.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include "nilfs.h"
 #include "page.h"
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7868cc122ac..0957b58f909 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/buffer_head.h>
+#include <linux/gfp.h>
 #include <linux/mpage.h>
 #include <linux/writeback.h>
 #include <linux/uio.h>
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 313d0a21da4..c2ff1b30601 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -23,6 +23,7 @@
 #include <linux/fs.h>
 #include <linux/wait.h>
 #include <linux/smp_lock.h>	/* lock_kernel(), unlock_kernel() */
+#include <linux/slab.h>
 #include <linux/capability.h>	/* capable() */
 #include <linux/uaccess.h>	/* copy_from_user(), copy_to_user() */
 #include <linux/vmalloc.h>
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 06713ffcc7f..024be8c35bb 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -26,6 +26,7 @@
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/swap.h>
+#include <linux/slab.h>
 #include "nilfs.h"
 #include "segment.h"
 #include "page.h"
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index fc246dba112..8de3e1e4813 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -29,6 +29,7 @@
 #include <linux/list.h>
 #include <linux/highmem.h>
 #include <linux/pagevec.h>
+#include <linux/gfp.h>
 #include "nilfs.h"
 #include "page.h"
 #include "mdt.h"
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 017bedc761a..ba43146f3c3 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -23,6 +23,7 @@
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
 #include <linux/swap.h>
+#include <linux/slab.h>
 #include <linux/crc32.h>
 #include "nilfs.h"
 #include "segment.h"
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 6129a431aa3..17851f77f73 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -25,6 +25,7 @@
 #include <linux/writeback.h>
 #include <linux/crc32.h>
 #include <linux/backing-dev.h>
+#include <linux/slab.h>
 #include "page.h"
 #include "segbuf.h"
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index c161d89061b..6a7dbd8451d 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -32,6 +32,7 @@
 #include <linux/kthread.h>
 #include <linux/crc32.h>
 #include <linux/pagevec.h>
+#include <linux/slab.h>
 #include "nilfs.h"
 #include "btnode.h"
 #include "page.h"
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index e9795f1724d..1ab97453369 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -29,6 +29,7 @@
 #include <linux/fs.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/slab.h>
 #include "sb.h"
 
 /* the_nilfs struct */
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 037e878e03f..fcc2f064af8 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -18,6 +18,7 @@
 
 #include <linux/dcache.h>
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/srcu.h>
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index 3165d85aada..0399bcbe09c 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -87,7 +87,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/writeback.h> /* for inode_lock */
 
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index cfce53cb65d..c3c2c7ac902 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -23,6 +23,7 @@
 
 #include <linux/errno.h>
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 50d3b0c258e..f5094ee224c 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -22,6 +22,7 @@
 
 #include <linux/buffer_head.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
 
diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c
index 08f7530e934..6551c7cbad9 100644
--- a/fs/ntfs/compress.c
+++ b/fs/ntfs/compress.c
@@ -25,6 +25,7 @@
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
 #include <linux/vmalloc.h>
+#include <linux/slab.h>
 
 #include "attrib.h"
 #include "inode.h"
diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c
index 9173e82a45d..fe44d3feee4 100644
--- a/fs/ntfs/dir.c
+++ b/fs/ntfs/dir.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/buffer_head.h>
+#include <linux/slab.h>
 
 #include "dir.h"
 #include "aops.h"
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index b681c71d706..8804f093ba7 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -20,6 +20,7 @@
  */
 
 #include <linux/buffer_head.h>
+#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
 #include <linux/sched.h>
diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c
index 2194eff4974..096c135691a 100644
--- a/fs/ntfs/index.c
+++ b/fs/ntfs/index.c
@@ -19,6 +19,8 @@
  * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/slab.h>
+
 #include "aops.h"
 #include "collate.h"
 #include "debug.h"
diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c
index 1caa0ef0b2b..b572b672718 100644
--- a/fs/ntfs/mft.c
+++ b/fs/ntfs/mft.c
@@ -21,6 +21,7 @@
  */
 
 #include <linux/buffer_head.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 
 #include "attrib.h"
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 2ca00153b6e..358273e59ad 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -23,6 +23,7 @@
 #include <linux/dcache.h>
 #include <linux/exportfs.h>
 #include <linux/security.h>
+#include <linux/slab.h>
 
 #include "attrib.h"
 #include "debug.h"
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 8ccf0f8c9cc..e13fc9e8fcd 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -21,6 +21,7 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 
 #define MLOG_MASK_PREFIX ML_INODE
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 21c808f752d..ecebb227679 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -25,7 +25,6 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 
 #include <cluster/masklog.h>
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 5c989000670..41d5f1f92d5 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -34,6 +34,7 @@
 #include <linux/crc32.h>
 #include <linux/time.h>
 #include <linux/debugfs.h>
+#include <linux/slab.h>
 
 #include "heartbeat.h"
 #include "tcp.h"
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index c81142e3ef8..ed0c9f367fe 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -19,6 +19,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/configfs.h>
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 639024033fc..cf3e1669621 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -44,7 +44,6 @@
  * and if they're the last, they fire off the decision.
  */
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
 
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index dccc439fa08..a795eb91f4e 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/sysctl.h>
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index f283bce776b..90803b47cd8 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/sysctl.h>
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 52ec020ea78..11a6d1fd1d3 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/sysctl.h>
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 49e29ecd020..b47c1b92b82 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -28,7 +28,6 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/sysctl.h>
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index c562a7581cf..09e3fdfa6d3 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -24,6 +24,7 @@
 
 #include <linux/fs.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/fiemap.h>
 
diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c
index c6e7213db86..1aa863dd901 100644
--- a/fs/ocfs2/heartbeat.c
+++ b/fs/ocfs2/heartbeat.c
@@ -26,7 +26,6 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 
 #define MLOG_MASK_PREFIX ML_SUPER
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index ab207901d32..07cc8bb68b6 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -25,7 +25,6 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 39737613424..7898bd3a99f 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -25,7 +25,6 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/uio.h>
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 355f41d1d52..ab42a74c753 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -3,6 +3,7 @@
  */
 #include <linux/spinlock.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/quota.h>
 #include <linux/quotaops.h>
 #include <linux/dqblk_qtree.h>
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index a6467f3d262..9ad49305f45 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -3,6 +3,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/quota.h>
 #include <linux/quotaops.h>
 #include <linux/module.h>
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 29405f2ff61..bd96f6c7877 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -37,7 +37,6 @@
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 7020e1253ff..0d3049f696c 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -19,6 +19,7 @@
 
 #include <linux/kernel.h>
 #include <linux/crc32.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 
 /* Needed for AOP_TRUNCATED_PAGE in mlog_errno() */
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 5ae8812b286..2dc57bca068 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/reboot.h>
 #include <asm/uaccess.h>
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index 40e53702948..bfe7190cdbf 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -25,7 +25,6 @@
 
 #include <linux/fs.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 #include <linux/highmem.h>
 
 #define MLOG_MASK_PREFIX ML_INODE
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 75d9b5ba1d4..c82af6acc2e 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -6,6 +6,7 @@
 #include <linux/version.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/parser.h>
diff --git a/fs/open.c b/fs/open.c
index e17f54454b5..74e5cd9f718 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -10,7 +10,6 @@
 #include <linux/fdtable.h>
 #include <linux/fsnotify.h>
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/tty.h>
 #include <linux/namei.h>
 #include <linux/backing-dev.h>
@@ -20,6 +19,7 @@
 #include <linux/mount.h>
 #include <linux/vfs.h>
 #include <linux/fcntl.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <linux/fs.h>
 #include <linux/personality.h>
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index e8865c11777..e238ab23a9e 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/ctype.h>
 #include <linux/genhd.h>
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index 49cfd5f5423..91babdae758 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -95,6 +95,7 @@
  ************************************************************/
 #include <linux/crc32.h>
 #include <linux/math64.h>
+#include <linux/slab.h>
 #include "check.h"
 #include "efi.h"
 
diff --git a/fs/proc/array.c b/fs/proc/array.c
index aa8637b8102..e51f2ec2c5e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -68,7 +68,6 @@
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
-#include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/signal.h>
 #include <linux/highmem.h>
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a7310841c83..9e82adc37b0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -81,6 +81,7 @@
 #include <linux/elf.h>
 #include <linux/pid_namespace.h>
 #include <linux/fs_struct.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 /* NOTE:
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 08f4d71dacd..43c12749060 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -13,6 +13,7 @@
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/init.h>
 #include <linux/idr.h>
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 445a02bcaab..d35b23238fb 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/smp_lock.h>
 #include <linux/sysctl.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index b442dac8f5f..19979a2ce27 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -19,6 +19,7 @@
 #include <linux/highmem.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <linux/list.h>
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 9fe7d7ebe11..b1822dde55c 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -21,7 +21,6 @@
 #include <linux/mmzone.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
-#include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/seq_file.h>
 #include <linux/hugetlb.h>
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index f8650dce74f..ce94801f48c 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/of.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <asm/prom.h>
 #include <asm/uaccess.h>
 #include "internal.h"
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 04d1270f1c3..9020ac15baa 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -14,6 +14,7 @@
 #include <linux/time.h>
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/module.h>
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index b9b7aad2003..bf31b03fc27 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -1,6 +1,5 @@
 #include <linux/cpumask.h>
 #include <linux/fs.h>
-#include <linux/gfp.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 183f8ff5f40..2d45889931f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -4,6 +4,7 @@
 #include <linux/seq_file.h>
 #include <linux/highmem.h>
 #include <linux/ptrace.h>
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
 #include <linux/swap.h>
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 5d9fd64ef81..46d4b5d72bd 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -5,6 +5,7 @@
 #include <linux/fs_struct.h>
 #include <linux/mount.h>
 #include <linux/ptrace.h>
+#include <linux/slab.h>
 #include <linux/seq_file.h>
 #include "internal.h"
 
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 0872afa58d3..9fbc99ec799 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -12,6 +12,7 @@
 #include <linux/user.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
+#include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
diff --git a/fs/quota/netlink.c b/fs/quota/netlink.c
index 2663ed90fb0..d67908b407d 100644
--- a/fs/quota/netlink.c
+++ b/fs/quota/netlink.c
@@ -5,6 +5,7 @@
 #include <linux/kernel.h>
 #include <linux/quotaops.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <net/netlink.h>
 #include <net/genetlink.h>
 
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 1739a4aba25..5ea4ad81a42 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -21,6 +21,7 @@
 #include <linux/pagevec.h>
 #include <linux/mman.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include "internal.h"
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index a6090aa1a7c..c94853473ca 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -35,6 +35,7 @@
 #include <linux/sched.h>
 #include <linux/parser.h>
 #include <linux/magic.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index c094f58c744..f8a6075abf5 100644
--- a/fs/reiserfs/dir.c
+++ b/fs/reiserfs/dir.c
@@ -8,6 +8,7 @@
 #include <linux/reiserfs_fs.h>
 #include <linux/stat.h>
 #include <linux/buffer_head.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 
 extern const struct reiserfs_key MIN_KEY;
diff --git a/fs/reiserfs/fix_node.c b/fs/reiserfs/fix_node.c
index 6591cb21edf..1e4250bc3a6 100644
--- a/fs/reiserfs/fix_node.c
+++ b/fs/reiserfs/fix_node.c
@@ -35,6 +35,7 @@
  **/
 
 #include <linux/time.h>
+#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/reiserfs_fs.h>
 #include <linux/buffer_head.h>
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index d1da94b82d8..dc2c65e0485 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -11,6 +11,7 @@
 #include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include <asm/unaligned.h>
 #include <linux/buffer_head.h>
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index f3de5e8a2ae..19fbc810e8e 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -50,6 +50,7 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/uaccess.h>
+#include <linux/slab.h>
 
 #include <asm/system.h>
 
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 96e4cbbfaa1..d0c43cb99ff 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -13,6 +13,7 @@
 
 #include <linux/time.h>
 #include <linux/bitops.h>
+#include <linux/slab.h>
 #include <linux/reiserfs_fs.h>
 #include <linux/reiserfs_acl.h>
 #include <linux/reiserfs_xattr.h>
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 04bf5d791bd..d8fd90d83ab 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/time.h>
 #include <asm/uaccess.h>
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 37d034ca7d9..4f9586bb763 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -38,6 +38,7 @@
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include <linux/errno.h>
+#include <linux/gfp.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/pagemap.h>
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index dd20a7883f0..9cdb759645a 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
+#include <linux/slab.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/reiserfs_xattr.h>
 #include <linux/reiserfs_acl.h>
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index de1fcffd906..7271a477c04 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
+#include <linux/slab.h>
 #include <linux/reiserfs_xattr.h>
 #include <linux/security.h>
 #include <asm/uaccess.h>
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 1dabe4ee02f..f329849ce3c 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/list.h>
diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c
index 92d5e8ffb63..dbf6548bbf0 100644
--- a/fs/smbfs/file.c
+++ b/fs/smbfs/file.c
@@ -13,7 +13,6 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/mm.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/smp_lock.h>
 #include <linux/net.h>
diff --git a/fs/smbfs/smbiod.c b/fs/smbfs/smbiod.c
index 6bd9b691a46..0e39a924f10 100644
--- a/fs/smbfs/smbiod.c
+++ b/fs/smbfs/smbiod.c
@@ -12,7 +12,6 @@
 #include <linux/string.h>
 #include <linux/stat.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/dcache.h>
diff --git a/fs/smbfs/symlink.c b/fs/smbfs/symlink.c
index 00b2909bd46..54350b59046 100644
--- a/fs/smbfs/symlink.c
+++ b/fs/smbfs/symlink.c
@@ -15,6 +15,7 @@
 #include <linux/pagemap.h>
 #include <linux/net.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
diff --git a/fs/splice.c b/fs/splice.c
index 39208663aaf..9313b6124a2 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -30,6 +30,7 @@
 #include <linux/syscalls.h>
 #include <linux/uio.h>
 #include <linux/security.h>
+#include <linux/gfp.h>
 
 /*
  * Attempt to steal a page from a pipe buffer. This should perhaps go into
diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c
index e80be2022a7..32b911f4ee3 100644
--- a/fs/squashfs/symlink.c
+++ b/fs/squashfs/symlink.c
@@ -33,7 +33,6 @@
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/kernel.h>
-#include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/pagemap.h>
 
diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c
index 4dd70e04333..15a03d0fb9f 100644
--- a/fs/squashfs/zlib_wrapper.c
+++ b/fs/squashfs/zlib_wrapper.c
@@ -24,6 +24,7 @@
 
 #include <linux/mutex.h>
 #include <linux/buffer_head.h>
+#include <linux/slab.h>
 #include <linux/zlib.h>
 
 #include "squashfs_fs.h"
diff --git a/fs/sync.c b/fs/sync.c
index f557d71cb09..fc5c3d75cf3 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -5,6 +5,7 @@
 #include <linux/kernel.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/writeback.h>
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 082daaecac1..a4a0a941971 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -18,6 +18,7 @@
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include "sysfs.h"
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 0cb10884a2f..776137828dc 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/magic.h>
+#include <linux/slab.h>
 
 #include "sysfs.h"
 
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 1b9a3a1e8a1..b93ec51fa7a 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/gfp.h>
 #include <linux/mount.h>
 #include <linux/module.h>
 #include <linux/kobject.h>
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 1bfc95ad5f7..98158de91d2 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/time.h>
diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c
index 4775af40116..37fa7ed062d 100644
--- a/fs/ubifs/commit.c
+++ b/fs/ubifs/commit.c
@@ -45,6 +45,7 @@
 
 #include <linux/freezer.h>
 #include <linux/kthread.h>
+#include <linux/slab.h>
 #include "ubifs.h"
 
 /**
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 90492327b38..c2a68baa782 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -34,6 +34,7 @@
 #include <linux/moduleparam.h>
 #include <linux/debugfs.h>
 #include <linux/math64.h>
+#include <linux/slab.h>
 
 #ifdef CONFIG_UBIFS_FS_DEBUG
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index e26c02ab6cd..5692cf72b80 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -52,6 +52,7 @@
 #include "ubifs.h"
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/slab.h>
 
 static int read_block(struct inode *inode, void *addr, unsigned int block,
 		      struct ubifs_data_node *dn)
diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c
index e5a3d8e96bb..918d1582ca0 100644
--- a/fs/ubifs/gc.c
+++ b/fs/ubifs/gc.c
@@ -53,6 +53,7 @@
  * good, and GC takes extra care when moving them.
  */
 
+#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/list_sort.h>
 #include "ubifs.h"
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index e589fedaf1e..77d5cf4a754 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -51,6 +51,7 @@
  */
 
 #include <linux/crc32.h>
+#include <linux/slab.h>
 #include "ubifs.h"
 
 /**
diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c
index b2792e84d24..ad7f67b827e 100644
--- a/fs/ubifs/lpt.c
+++ b/fs/ubifs/lpt.c
@@ -46,6 +46,7 @@
 #include "ubifs.h"
 #include <linux/crc16.h>
 #include <linux/math64.h>
+#include <linux/slab.h>
 
 /**
  * do_calc_lpt_geom - calculate sizes for the LPT area.
diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c
index 8cbfb824802..13cb7a4237b 100644
--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -26,6 +26,7 @@
  */
 
 #include <linux/crc16.h>
+#include <linux/slab.h>
 #include "ubifs.h"
 
 /**
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 868a55ee080..109c6ea03bb 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/crc32.h>
+#include <linux/slab.h>
 #include "ubifs.h"
 
 /**
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 57085e43320..96cb62c8a9d 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -27,6 +27,7 @@
  */
 
 #include "ubifs.h"
+#include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/math64.h>
 
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index e5b1a7d00fa..2194915220e 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -31,6 +31,7 @@
  */
 
 #include <linux/crc32.h>
+#include <linux/slab.h>
 #include "ubifs.h"
 
 /*
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index b2d976366a4..bd2542dad01 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -28,6 +28,7 @@
 #include <linux/fs.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 195830f4756..c74400f88fe 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -56,6 +56,7 @@
  */
 
 #include "ubifs.h"
+#include <linux/slab.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl_xattr.h>
 
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index 4b540ee632d..745eb209be0 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -24,7 +24,6 @@
 
 #include <linux/fs.h>
 #include <linux/string.h>
-#include <linux/slab.h>
 #include <linux/buffer_head.h>
 
 uint32_t udf_get_pblock(struct super_block *sb, uint32_t block,
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 852e9184568..16064787d2b 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -26,7 +26,6 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/stat.h>
-#include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index cefa8c8913e..d03a90b6ad6 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -24,6 +24,7 @@
 #include <linux/string.h>	/* for memset */
 #include <linux/nls.h>
 #include <linux/crc-itu-t.h>
+#include <linux/slab.h>
 
 #include "udf_sb.h"
 
diff --git a/fs/xattr_acl.c b/fs/xattr_acl.c
index 05ac0fe9c4d..8d5a506c82e 100644
--- a/fs/xattr_acl.c
+++ b/fs/xattr_acl.c
@@ -6,9 +6,9 @@
  */
 
 #include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/gfp.h>
 
 
 /*
diff --git a/fs/xfs/linux-2.6/kmem.c b/fs/xfs/linux-2.6/kmem.c
index bc7405585de..666c9db48eb 100644
--- a/fs/xfs/linux-2.6/kmem.c
+++ b/fs/xfs/linux-2.6/kmem.c
@@ -17,6 +17,7 @@
  */
 #include <linux/mm.h>
 #include <linux/highmem.h>
+#include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index bf85bbe4a9a..a7bc925c4d6 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -22,6 +22,7 @@
 #include "xfs_inode.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include <linux/slab.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl_xattr.h>
 
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 99628508cb1..0f8b9968a80 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -40,6 +40,7 @@
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
 #include "xfs_bmap.h"
+#include <linux/gfp.h>
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index bd111b7e1da..44c2b0ef9a4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -18,7 +18,7 @@
 #include "xfs.h"
 #include <linux/stddef.h>
 #include <linux/errno.h>
-#include <linux/slab.h>
+#include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
 #include <linux/vmalloc.h>
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 4ea1ee18ade..7b26cc2fd28 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -58,6 +58,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/pagemap.h>
+#include <linux/slab.h>
 #include <linux/exportfs.h>
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 0bf6d61f052..593c05b4df8 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -18,6 +18,7 @@
 #include <linux/compat.h>
 #include <linux/ioctl.h>
 #include <linux/mount.h>
+#include <linux/slab.h>
 #include <asm/uaccess.h>
 #include "xfs.h"
 #include "xfs_fs.h"
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 61a99608731..e65a7937f3a 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -56,6 +56,7 @@
 #include <linux/security.h>
 #include <linux/falloc.h>
 #include <linux/fiemap.h>
+#include <linux/slab.h>
 
 /*
  * Bring the timestamps in the XFS inode uptodate.
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 71345a370d9..52e06b487ce 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -61,6 +61,7 @@
 
 #include <linux/namei.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/mount.h>
 #include <linux/mempool.h>
 #include <linux/writeback.h>
-- 
cgit v1.2.3-18-g5258


From e05c378f4973674a16d5b9636f2310cf88aca5f2 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Tue, 30 Mar 2010 18:25:17 +0200
Subject: [LogFS] Remove unused method

All callers are long gone.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/logfs.h     |  1 -
 fs/logfs/readwrite.c | 21 ---------------------
 fs/logfs/segment.c   |  6 ------
 3 files changed, 28 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index b84b0eec602..97195b9e93a 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -305,7 +305,6 @@ typedef int write_alias_t(struct super_block *sb, u64 ino, u64 bix,
 		level_t level, int child_no, __be64 val);
 struct logfs_block_ops {
 	void	(*write_block)(struct logfs_block *block);
-	gc_level_t	(*block_level)(struct logfs_block *block);
 	void	(*free_block)(struct super_block *sb, struct logfs_block*block);
 	int	(*write_alias)(struct super_block *sb,
 			struct logfs_block *block,
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index c3a3a6814b8..3659c37fbd7 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -429,25 +429,6 @@ static void inode_write_block(struct logfs_block *block)
 	}
 }
 
-static gc_level_t inode_block_level(struct logfs_block *block)
-{
-	BUG_ON(block->inode->i_ino == LOGFS_INO_MASTER);
-	return GC_LEVEL(LOGFS_MAX_LEVELS);
-}
-
-static gc_level_t indirect_block_level(struct logfs_block *block)
-{
-	struct page *page;
-	struct inode *inode;
-	u64 bix;
-	level_t level;
-
-	page = block->page;
-	inode = page->mapping->host;
-	logfs_unpack_index(page->index, &bix, &level);
-	return expand_level(inode->i_ino, level);
-}
-
 /*
  * This silences a false, yet annoying gcc warning.  I hate it when my editor
  * jumps into bitops.h each time I recompile this file.
@@ -586,14 +567,12 @@ static void indirect_free_block(struct super_block *sb,
 
 static struct logfs_block_ops inode_block_ops = {
 	.write_block = inode_write_block,
-	.block_level = inode_block_level,
 	.free_block = inode_free_block,
 	.write_alias = inode_write_alias,
 };
 
 struct logfs_block_ops indirect_block_ops = {
 	.write_block = indirect_write_block,
-	.block_level = indirect_block_level,
 	.free_block = indirect_free_block,
 	.write_alias = indirect_write_alias,
 };
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 0ecd8f07c11..02db22ebbf1 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -182,14 +182,8 @@ static int btree_write_alias(struct super_block *sb, struct logfs_block *block,
 	return 0;
 }
 
-static gc_level_t btree_block_level(struct logfs_block *block)
-{
-	return expand_level(block->ino, block->level);
-}
-
 static struct logfs_block_ops btree_block_ops = {
 	.write_block	= btree_write_block,
-	.block_level	= btree_block_level,
 	.free_block	= __free_block,
 	.write_alias	= btree_write_alias,
 };
-- 
cgit v1.2.3-18-g5258


From b7b7fa43103a9fb30dbcc60cbd5161fdfc25f904 Mon Sep 17 00:00:00 2001
From: Jeff Mahoney <jeffm@jeffreymahoney.com>
Date: Mon, 29 Mar 2010 15:12:39 -0400
Subject: reiserfs: Fix locking BUG during mount failure

Commit 8ebc423238341b52912c7295b045a32477b33f09 (reiserfs: kill-the-BKL)
introduced a bug in the mount failure case.

The error label releases the lock before calling journal_release_error,
but it requires that the lock be held. do_journal_release unlocks and
retakes it. When it releases it without it held, we trigger a BUG().

The error_alloc label skips the unlock since the lock isn't held yet
but none of the other conditions that are clean up exist yet either.

This patch returns immediately after the kzalloc failure and moves
the reiserfs_write_unlock after the journal_release_error call.

This was reported in https://bugzilla.novell.com/show_bug.cgi?id=591807

Reported-by:  Thomas Siedentopf <thomas.siedentopf@novell.com>
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Cc: Thomas Siedentopf <thomas.siedentopf@novell.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: 2.6.33.x <stable@kernel.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 fs/reiserfs/super.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 04bf5d791bd..ab190511bc1 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -1618,10 +1618,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	save_mount_options(s, data);
 
 	sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL);
-	if (!sbi) {
-		errval = -ENOMEM;
-		goto error_alloc;
-	}
+	if (!sbi)
+		return -ENOMEM;
 	s->s_fs_info = sbi;
 	/* Set default values for options: non-aggressive tails, RO on errors */
 	REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_SMALLTAIL);
@@ -1878,12 +1876,12 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	return (0);
 
 error:
-	reiserfs_write_unlock(s);
-error_alloc:
 	if (jinit_done) {	/* kill the commit thread, free journal ram */
 		journal_release_error(NULL, s);
 	}
 
+	reiserfs_write_unlock(s);
+
 	reiserfs_free_bitmap_cache(s);
 	if (SB_BUFFER_WITH_SB(s))
 		brelse(SB_BUFFER_WITH_SB(s));
-- 
cgit v1.2.3-18-g5258


From 9358c6d4c0264b1572554c49c4b92673ea9a5c72 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Tue, 30 Mar 2010 13:54:41 -0700
Subject: ceph: fix dentry rehashing on virtual .snap dir

If a lookup fails on the magic .snap directory, we bind it to a magic
snap directory inode in ceph_lookup_finish().  That code assumes the dentry
is unhashed, but a recent server-side change started returning NULL leases
on lookup failure, causing the .snap dentry to be hashed and NULL by
ceph_fill_trace().

This causes dentry hash chain corruption, or a dies when d_rehash()
includes
	BUG_ON(!d_unhashed(entry));

So, avoid processing the NULL dentry lease if it the dentry matches the
snapdir name in ceph_fill_trace().  That allows the lookup completion to
properly bind it to the snapdir inode.  BUG there if dentry is hashed to
be sure.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/dir.c   |  1 +
 fs/ceph/inode.c | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8a9116e15b7..aed8fda3302 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -488,6 +488,7 @@ struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
 		struct inode *inode = ceph_get_snapdir(parent);
 		dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
 		     dentry, dentry->d_name.len, dentry->d_name.name, inode);
+		BUG_ON(!d_unhashed(dentry));
 		d_add(dentry, inode);
 		err = 0;
 	}
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index aca82d55cc5..26f883c275e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -886,6 +886,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 	struct inode *in = NULL;
 	struct ceph_mds_reply_inode *ininfo;
 	struct ceph_vino vino;
+	struct ceph_client *client = ceph_sb_to_client(sb);
 	int i = 0;
 	int err = 0;
 
@@ -949,7 +950,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			return err;
 	}
 
-	if (rinfo->head->is_dentry && !req->r_aborted) {
+	/*
+	 * ignore null lease/binding on snapdir ENOENT, or else we
+	 * will have trouble splicing in the virtual snapdir later
+	 */
+	if (rinfo->head->is_dentry && !req->r_aborted &&
+	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
+					       client->mount_args->snapdir_name,
+					       req->r_dentry->d_name.len))) {
 		/*
 		 * lookup link rename   : null -> possibly existing inode
 		 * mknod symlink mkdir  : null -> new inode
-- 
cgit v1.2.3-18-g5258


From 2f3014fc2ab1e25c36531e19164c48182c168995 Mon Sep 17 00:00:00 2001
From: Andrea Gelmini <andrea.gelmini@gelma.net>
Date: Thu, 25 Mar 2010 17:22:45 +0000
Subject: Btrfs: remove duplicate include in ioctl.c

fs/btrfs/ioctl.c: ctree.h is included more than once.

Signed-off-by: Andrea Gelmini <andrea.gelmini@gelma.net>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ioctl.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'fs')

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2845c6ceecd..5c9f8b30608 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -48,7 +48,6 @@
 #include "print-tree.h"
 #include "volumes.h"
 #include "locking.h"
-#include "ctree.h"
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
-- 
cgit v1.2.3-18-g5258


From 90d2c51dbb4db05c040bc7db264bb7ab35e35455 Mon Sep 17 00:00:00 2001
From: Miao Xie <miaox@cn.fujitsu.com>
Date: Thu, 25 Mar 2010 12:37:12 +0000
Subject: Btrfs: add NULL check for do_walk_down()

btrfs_find_create_tree_block() may return NULL, so we must check the returned
value, or we will access a NULL pointer.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/extent-tree.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1727b26fb19..503a18eaef5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5205,6 +5205,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	next = btrfs_find_tree_block(root, bytenr, blocksize);
 	if (!next) {
 		next = btrfs_find_create_tree_block(root, bytenr, blocksize);
+		if (!next)
+			return -ENOMEM;
 		reada = 1;
 	}
 	btrfs_tree_lock(next);
@@ -5417,7 +5419,8 @@ static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
 		if (ret > 0) {
 			path->slots[level]++;
 			continue;
-		}
+		} else if (ret < 0)
+			return ret;
 		level = wc->level;
 	}
 	return 0;
-- 
cgit v1.2.3-18-g5258


From 471fa17dff556ad38caf26de097c0630530d8cbe Mon Sep 17 00:00:00 2001
From: Zhao Lei <zhaolei@cn.fujitsu.com>
Date: Thu, 25 Mar 2010 12:35:14 +0000
Subject: Btrfs: Remove unnecessary finish_wait() in wait_current_trans()

We only need to call finish_wait() after wait loop.

By the way, this patch makes code of waiting loop similar to
example in wait.h(no functional change)

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/transaction.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 2d654c1c794..43054285f63 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -147,18 +147,13 @@ static void wait_current_trans(struct btrfs_root *root)
 		while (1) {
 			prepare_to_wait(&root->fs_info->transaction_wait, &wait,
 					TASK_UNINTERRUPTIBLE);
-			if (cur_trans->blocked) {
-				mutex_unlock(&root->fs_info->trans_mutex);
-				schedule();
-				mutex_lock(&root->fs_info->trans_mutex);
-				finish_wait(&root->fs_info->transaction_wait,
-					    &wait);
-			} else {
-				finish_wait(&root->fs_info->transaction_wait,
-					    &wait);
+			if (!cur_trans->blocked)
 				break;
-			}
+			mutex_unlock(&root->fs_info->trans_mutex);
+			schedule();
+			mutex_lock(&root->fs_info->trans_mutex);
 		}
+		finish_wait(&root->fs_info->transaction_wait, &wait);
 		put_transaction(cur_trans);
 	}
 }
-- 
cgit v1.2.3-18-g5258


From ab59381ea43f81c977cbd09add26950aaf6cb9fe Mon Sep 17 00:00:00 2001
From: Zhao Lei <zhaolei@cn.fujitsu.com>
Date: Thu, 25 Mar 2010 12:34:49 +0000
Subject: Btrfs: Add error handle for btrfs_search_slot() in
 btrfs_read_chunk_tree()

We need to check return value of btrfs_search_slot() in
btrfs_read_chunk_tree() and do corresponding error handing.

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/volumes.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'fs')

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9df8e3f1cca..c6c80093eac 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3389,6 +3389,8 @@ int btrfs_read_chunk_tree(struct btrfs_root *root)
 	key.type = 0;
 again:
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto error;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
-- 
cgit v1.2.3-18-g5258


From f3eae7e8a5ed124bbc781e18ea10c21856017322 Mon Sep 17 00:00:00 2001
From: Zhao Lei <zhaolei@cn.fujitsu.com>
Date: Thu, 25 Mar 2010 12:32:59 +0000
Subject: Btrfs: Simplify num_stripes's calculation logical for
 __btrfs_alloc_chunk()

We can use this simple method to make source more readable.

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/volumes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c6c80093eac..bf3bec3e413 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2198,9 +2198,9 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		min_stripes = 2;
 	}
 	if (type & (BTRFS_BLOCK_GROUP_RAID1)) {
-		num_stripes = min_t(u64, 2, fs_devices->rw_devices);
-		if (num_stripes < 2)
+		if (fs_devices->rw_devices < 2)
 			return -ENOSPC;
+		num_stripes = 2;
 		min_stripes = 2;
 	}
 	if (type & (BTRFS_BLOCK_GROUP_RAID10)) {
-- 
cgit v1.2.3-18-g5258


From 683be16eb6e19a35aca2473668652259ed074094 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Sat, 20 Mar 2010 11:24:48 +0000
Subject: Btrfs: dereferencing freed memory

The original code dereferenced range on the next line.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ioctl.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs')

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 5c9f8b30608..874d36e5f16 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1374,6 +1374,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 					   sizeof(*range))) {
 				ret = -EFAULT;
 				kfree(range);
+				goto out;
 			}
 			/* compression requires us to start the IO */
 			if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
-- 
cgit v1.2.3-18-g5258


From c2b96929e2ca6914cf4a66cd8fe2a34c4a98277f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Sat, 20 Mar 2010 11:24:15 +0000
Subject: Btrfs: handle kmalloc() failure in inode lookup ioctl

Return -ENOMEM if kmalloc() fails.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ioctl.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'fs')

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 874d36e5f16..74d89133f76 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1211,6 +1211,9 @@ static noinline int btrfs_ioctl_ino_lookup(struct file *file,
 		return -EPERM;
 
 	args = kmalloc(sizeof(*args), GFP_KERNEL);
+	if (!args)
+		return -ENOMEM;
+
 	if (copy_from_user(args, argp, sizeof(*args))) {
 		kfree(args);
 		return -EFAULT;
-- 
cgit v1.2.3-18-g5258


From 6cf8bfbf5e88edfb09a2bf0631a067060f534592 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Sat, 20 Mar 2010 11:22:10 +0000
Subject: Btrfs: check btrfs_get_extent return for IS_ERR()

btrfs_get_extent() never returns NULL, only a valid pointer or ERR_PTR()

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 74d89133f76..2b7dd88fc54 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -510,7 +510,7 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len,
 		em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
 		unlock_extent(io_tree, start, start + len - 1, GFP_NOFS);
 
-		if (!em)
+		if (IS_ERR(em))
 			return 0;
 	}
 
-- 
cgit v1.2.3-18-g5258


From 1b1d1f6625e517a08640ddb4b8f8a0e025243fe3 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@redhat.com>
Date: Fri, 19 Mar 2010 20:49:55 +0000
Subject: Btrfs: fail to mount if we have problems reading the block groups

We don't actually check the return value of btrfs_read_block_groups, so we can
possibly succeed to mount, but then fail to say read the superblock xattr for
selinux which will cause the vfs code to deactivate the super.

This is a problem because in find_free_extent we just assume that we
will find the right space_info for the allocation we want.  But if we
failed to read the block groups, we won't have setup any space_info's,
and we'll hit a NULL pointer deref in find_free_extent.

This patch fixes that problem by checking the return value of
btrfs_read_block_groups, and failing out properly.  I've also added a
check in find_free_extent so if for some reason we don't find an
appropriate space_info, we just return -ENOSPC.

Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/disk-io.c     | 11 ++++++++---
 fs/btrfs/extent-tree.c |  5 ++++-
 2 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 11d0ad30e20..5ae1c0fcfce 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1922,7 +1922,11 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 
 	csum_root->track_dirty = 1;
 
-	btrfs_read_block_groups(extent_root);
+	ret = btrfs_read_block_groups(extent_root);
+	if (ret) {
+		printk(KERN_ERR "Failed to read block groups: %d\n", ret);
+		goto fail_block_groups;
+	}
 
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
@@ -1932,7 +1936,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
-		goto fail_csum_root;
+		goto fail_block_groups;
 
 	fs_info->transaction_kthread = kthread_run(transaction_kthread,
 						   tree_root,
@@ -2020,7 +2024,8 @@ fail_cleaner:
 	filemap_write_and_wait(fs_info->btree_inode->i_mapping);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
-fail_csum_root:
+fail_block_groups:
+	btrfs_free_block_groups(fs_info);
 	free_extent_buffer(csum_root->node);
 	free_extent_buffer(csum_root->commit_root);
 fail_dev_root:
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 503a18eaef5..4c910359c80 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4170,6 +4170,10 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 	ins->offset = 0;
 
 	space_info = __find_space_info(root->fs_info, data);
+	if (!space_info) {
+		printk(KERN_ERR "No space info for %d\n", data);
+		return -ENOSPC;
+	}
 
 	if (orig_root->ref_cows || empty_size)
 		allowed_chunk_alloc = 1;
@@ -7372,7 +7376,6 @@ static int find_first_block_group(struct btrfs_root *root,
 		}
 		path->slots[0]++;
 	}
-	ret = -ENOENT;
 out:
 	return ret;
 }
-- 
cgit v1.2.3-18-g5258


From 287a0ab91d25ca982f895a76402e5893b47ed7a6 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@redhat.com>
Date: Fri, 19 Mar 2010 18:07:23 +0000
Subject: Btrfs: kill max_extent mount option

As Yan pointed out, theres not much reason for all this complicated math to
account for file extents being split up into max_extent chunks, since they are
likely to all end up in the same leaf anyway.  Since there isn't much reason to
use max_extent, just remove the option altogether so we have one less thing we
need to test.

Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ctree.h        |  1 -
 fs/btrfs/disk-io.c      |  1 -
 fs/btrfs/extent-tree.c  |  4 ++--
 fs/btrfs/inode.c        | 59 ++++---------------------------------------------
 fs/btrfs/ordered-data.c |  6 +++--
 fs/btrfs/super.c        | 23 +++----------------
 6 files changed, 13 insertions(+), 81 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 11115847d87..ae8c40922c5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -834,7 +834,6 @@ struct btrfs_fs_info {
 	u64 last_trans_log_full_commit;
 	u64 open_ioctl_trans;
 	unsigned long mount_opt;
-	u64 max_extent;
 	u64 max_inline;
 	u64 alloc_start;
 	struct btrfs_transaction *running_transaction;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 5ae1c0fcfce..6632e5c4c8b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1634,7 +1634,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->async_submit_draining, 0);
 	atomic_set(&fs_info->nr_async_bios, 0);
 	fs_info->sb = sb;
-	fs_info->max_extent = (u64)-1;
 	fs_info->max_inline = 8192 * 1024;
 	fs_info->metadata_ratio = 0;
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4c910359c80..5f6bc283c0c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2846,7 +2846,7 @@ int btrfs_unreserve_metadata_for_delalloc(struct btrfs_root *root,
 	}
 	spin_unlock(&BTRFS_I(inode)->accounting_lock);
 
-	BTRFS_I(inode)->reserved_extents--;
+	BTRFS_I(inode)->reserved_extents -= num_items;
 	BUG_ON(BTRFS_I(inode)->reserved_extents < 0);
 
 	if (meta_sinfo->bytes_delalloc < num_bytes) {
@@ -3111,7 +3111,7 @@ again:
 		return -ENOSPC;
 	}
 
-	BTRFS_I(inode)->reserved_extents++;
+	BTRFS_I(inode)->reserved_extents += num_items;
 	check_force_delalloc(meta_sinfo);
 	spin_unlock(&meta_sinfo->lock);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2a337a09c65..a85b90c86cb 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -796,7 +796,7 @@ static noinline int cow_file_range(struct inode *inode,
 	while (disk_num_bytes > 0) {
 		unsigned long op;
 
-		cur_alloc_size = min(disk_num_bytes, root->fs_info->max_extent);
+		cur_alloc_size = disk_num_bytes;
 		ret = btrfs_reserve_extent(trans, root, cur_alloc_size,
 					   root->sectorsize, 0, alloc_hint,
 					   (u64)-1, &ins, 1);
@@ -1227,30 +1227,9 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 static int btrfs_split_extent_hook(struct inode *inode,
 				    struct extent_state *orig, u64 split)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	u64 size;
-
 	if (!(orig->state & EXTENT_DELALLOC))
 		return 0;
 
-	size = orig->end - orig->start + 1;
-	if (size > root->fs_info->max_extent) {
-		u64 num_extents;
-		u64 new_size;
-
-		new_size = orig->end - split + 1;
-		num_extents = div64_u64(size + root->fs_info->max_extent - 1,
-					root->fs_info->max_extent);
-
-		/*
-		 * if we break a large extent up then leave oustanding_extents
-		 * be, since we've already accounted for the large extent.
-		 */
-		if (div64_u64(new_size + root->fs_info->max_extent - 1,
-			      root->fs_info->max_extent) < num_extents)
-			return 0;
-	}
-
 	spin_lock(&BTRFS_I(inode)->accounting_lock);
 	BTRFS_I(inode)->outstanding_extents++;
 	spin_unlock(&BTRFS_I(inode)->accounting_lock);
@@ -1268,38 +1247,10 @@ static int btrfs_merge_extent_hook(struct inode *inode,
 				   struct extent_state *new,
 				   struct extent_state *other)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	u64 new_size, old_size;
-	u64 num_extents;
-
 	/* not delalloc, ignore it */
 	if (!(other->state & EXTENT_DELALLOC))
 		return 0;
 
-	old_size = other->end - other->start + 1;
-	if (new->start < other->start)
-		new_size = other->end - new->start + 1;
-	else
-		new_size = new->end - other->start + 1;
-
-	/* we're not bigger than the max, unreserve the space and go */
-	if (new_size <= root->fs_info->max_extent) {
-		spin_lock(&BTRFS_I(inode)->accounting_lock);
-		BTRFS_I(inode)->outstanding_extents--;
-		spin_unlock(&BTRFS_I(inode)->accounting_lock);
-		return 0;
-	}
-
-	/*
-	 * If we grew by another max_extent, just return, we want to keep that
-	 * reserved amount.
-	 */
-	num_extents = div64_u64(old_size + root->fs_info->max_extent - 1,
-				root->fs_info->max_extent);
-	if (div64_u64(new_size + root->fs_info->max_extent - 1,
-		      root->fs_info->max_extent) > num_extents)
-		return 0;
-
 	spin_lock(&BTRFS_I(inode)->accounting_lock);
 	BTRFS_I(inode)->outstanding_extents--;
 	spin_unlock(&BTRFS_I(inode)->accounting_lock);
@@ -1328,6 +1279,7 @@ static int btrfs_set_bit_hook(struct inode *inode, u64 start, u64 end,
 		BTRFS_I(inode)->outstanding_extents++;
 		spin_unlock(&BTRFS_I(inode)->accounting_lock);
 		btrfs_delalloc_reserve_space(root, inode, end - start + 1);
+
 		spin_lock(&root->fs_info->delalloc_lock);
 		BTRFS_I(inode)->delalloc_bytes += end - start + 1;
 		root->fs_info->delalloc_bytes += end - start + 1;
@@ -1356,6 +1308,7 @@ static int btrfs_clear_bit_hook(struct inode *inode,
 
 		if (bits & EXTENT_DO_ACCOUNTING) {
 			spin_lock(&BTRFS_I(inode)->accounting_lock);
+			WARN_ON(!BTRFS_I(inode)->outstanding_extents);
 			BTRFS_I(inode)->outstanding_extents--;
 			spin_unlock(&BTRFS_I(inode)->accounting_lock);
 			btrfs_unreserve_metadata_for_delalloc(root, inode, 1);
@@ -5384,7 +5337,6 @@ free:
 void btrfs_drop_inode(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-
 	if (inode->i_nlink > 0 && btrfs_root_refs(&root->root_item) == 0)
 		generic_delete_inode(inode);
 	else
@@ -5788,18 +5740,15 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end,
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key ins;
-	u64 alloc_size;
 	u64 cur_offset = start;
 	u64 num_bytes = end - start;
 	int ret = 0;
 	u64 i_size;
 
 	while (num_bytes > 0) {
-		alloc_size = min(num_bytes, root->fs_info->max_extent);
-
 		trans = btrfs_start_transaction(root, 1);
 
-		ret = btrfs_reserve_extent(trans, root, alloc_size,
+		ret = btrfs_reserve_extent(trans, root, num_bytes,
 					   root->sectorsize, 0, alloc_hint,
 					   (u64)-1, &ins, 1);
 		if (ret) {
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index a8ffecd0b49..5c99882b976 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -303,6 +303,7 @@ static int __btrfs_remove_ordered_extent(struct inode *inode,
 				struct btrfs_ordered_extent *entry)
 {
 	struct btrfs_ordered_inode_tree *tree;
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct rb_node *node;
 
 	tree = &BTRFS_I(inode)->ordered_tree;
@@ -312,12 +313,13 @@ static int __btrfs_remove_ordered_extent(struct inode *inode,
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
 
 	spin_lock(&BTRFS_I(inode)->accounting_lock);
+	WARN_ON(!BTRFS_I(inode)->outstanding_extents);
 	BTRFS_I(inode)->outstanding_extents--;
 	spin_unlock(&BTRFS_I(inode)->accounting_lock);
 	btrfs_unreserve_metadata_for_delalloc(BTRFS_I(inode)->root,
 					      inode, 1);
 
-	spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
+	spin_lock(&root->fs_info->ordered_extent_lock);
 	list_del_init(&entry->root_extent_list);
 
 	/*
@@ -329,7 +331,7 @@ static int __btrfs_remove_ordered_extent(struct inode *inode,
 	    !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
 		list_del_init(&BTRFS_I(inode)->ordered_operations);
 	}
-	spin_unlock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
+	spin_unlock(&root->fs_info->ordered_extent_lock);
 
 	return 0;
 }
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9ac612e6ca6..d11b12fc086 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -64,10 +64,9 @@ static void btrfs_put_super(struct super_block *sb)
 
 enum {
 	Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum,
-	Opt_nodatacow, Opt_max_extent, 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_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_err,
 };
 
@@ -79,7 +78,6 @@ static match_table_t tokens = {
 	{Opt_nodatasum, "nodatasum"},
 	{Opt_nodatacow, "nodatacow"},
 	{Opt_nobarrier, "nobarrier"},
-	{Opt_max_extent, "max_extent=%s"},
 	{Opt_max_inline, "max_inline=%s"},
 	{Opt_alloc_start, "alloc_start=%s"},
 	{Opt_thread_pool, "thread_pool=%d"},
@@ -188,18 +186,6 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 				       info->thread_pool_size);
 			}
 			break;
-		case Opt_max_extent:
-			num = match_strdup(&args[0]);
-			if (num) {
-				info->max_extent = memparse(num, NULL);
-				kfree(num);
-
-				info->max_extent = max_t(u64,
-					info->max_extent, root->sectorsize);
-				printk(KERN_INFO "btrfs: max_extent at %llu\n",
-				       (unsigned long long)info->max_extent);
-			}
-			break;
 		case Opt_max_inline:
 			num = match_strdup(&args[0]);
 			if (num) {
@@ -529,9 +515,6 @@ static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",nodatacow");
 	if (btrfs_test_opt(root, NOBARRIER))
 		seq_puts(seq, ",nobarrier");
-	if (info->max_extent != (u64)-1)
-		seq_printf(seq, ",max_extent=%llu",
-			   (unsigned long long)info->max_extent);
 	if (info->max_inline != 8192 * 1024)
 		seq_printf(seq, ",max_inline=%llu",
 			   (unsigned long long)info->max_inline);
-- 
cgit v1.2.3-18-g5258


From 0cad8a1130f77c7c445e3298c0e3593b3c0ef439 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@redhat.com>
Date: Wed, 17 Mar 2010 20:45:56 +0000
Subject: Btrfs: fix chunk allocate size calculation

If the amount of free space left in a device is less than what we think should
be the minimum size, just ignore the minimum size and use the amount we have.  I
ran into this running tests on a 600mb volume, the chunk allocator wouldn't let
me allocate the last 52mb of the disk for data because we want to have at least
64mb chunks for data.  This patch fixes that problem.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/volumes.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bf3bec3e413..9bf1f581b87 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2244,8 +2244,10 @@ again:
 		do_div(calc_size, stripe_len);
 		calc_size *= stripe_len;
 	}
+
 	/* we don't want tiny stripes */
-	calc_size = max_t(u64, min_stripe_size, calc_size);
+	if (!looped)
+		calc_size = max_t(u64, min_stripe_size, calc_size);
 
 	do_div(calc_size, stripe_len);
 	calc_size *= stripe_len;
-- 
cgit v1.2.3-18-g5258


From 753234007f4ac2c96921cfb19ec1ba535ac29790 Mon Sep 17 00:00:00 2001
From: Li Hong <lihong.hi@gmail.com>
Date: Wed, 31 Mar 2010 15:41:00 +0800
Subject: nilfs2: fix a wrong type conversion in nilfs_ioctl()

(void * __user *) should be (void __user *)

Signed-off-by: Li Hong <lihong.hi@gmail.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
---
 fs/nilfs2/ioctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 313d0a21da4..c446017141d 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -648,7 +648,7 @@ static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
 long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = filp->f_dentry->d_inode;
-	void __user *argp = (void * __user *)arg;
+	void __user *argp = (void __user *)arg;
 
 	switch (cmd) {
 	case NILFS_IOCTL_CHANGE_CPMODE:
-- 
cgit v1.2.3-18-g5258


From 30d1872d9eb3663b4cf7bdebcbf5cd465674cced Mon Sep 17 00:00:00 2001
From: Nikolaus Schulz <microschulz@web.de>
Date: Thu, 1 Apr 2010 02:21:10 +0900
Subject: fat: fix buffer overflow in vfat_create_shortname()

When using the string representation of a random counter as part of the base
name, ensure that it is no longer than 4 bytes.

Since we are repeatedly decrementing the counter in a loop until we have found a
unique base name, the counter may wrap around zero; therefore, it is not enough
to mask its higher bits before entering the loop, this must be done inside the
loop.

[hirofumi@mail.parknet.co.jp: use snprintf()]
Signed-off-by: Nikolaus Schulz <microschulz@web.de>
Cc: stable@kernel.org
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fat/namei_vfat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index c1ef5015486..6fcc7e71fba 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -309,7 +309,7 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
 {
 	struct fat_mount_options *opts = &MSDOS_SB(dir->i_sb)->options;
 	wchar_t *ip, *ext_start, *end, *name_start;
-	unsigned char base[9], ext[4], buf[8], *p;
+	unsigned char base[9], ext[4], buf[5], *p;
 	unsigned char charbuf[NLS_MAX_CHARSET_SIZE];
 	int chl, chi;
 	int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen;
@@ -467,7 +467,7 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
 			return 0;
 	}
 
-	i = jiffies & 0xffff;
+	i = jiffies;
 	sz = (jiffies >> 16) & 0x7;
 	if (baselen > 2) {
 		baselen = numtail2_baselen;
@@ -476,7 +476,7 @@ static int vfat_create_shortname(struct inode *dir, struct nls_table *nls,
 	name_res[baselen + 4] = '~';
 	name_res[baselen + 5] = '1' + sz;
 	while (1) {
-		sprintf(buf, "%04X", i);
+		snprintf(buf, sizeof(buf), "%04X", i & 0xffff);
 		memcpy(&name_res[baselen], buf, 4);
 		if (vfat_find_form(dir, name_res) < 0)
 			break;
-- 
cgit v1.2.3-18-g5258


From b95c35e76b29ba812e5dabdd91592e25ec640e93 Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@redhat.com>
Date: Thu, 1 Apr 2010 15:13:57 +0200
Subject: oom: fix the unsafe usage of badness() in proc_oom_score()

proc_oom_score(task) has a reference to task_struct, but that is all.
If this task was already released before we take tasklist_lock

	- we can't use task->group_leader, it points to nowhere

	- it is not safe to call badness() even if this task is
	  ->group_leader, has_intersects_mems_allowed() assumes
	  it is safe to iterate over ->thread_group list.

	- even worse, badness() can hit ->signal == NULL

Add the pid_alive() check to ensure __unhash_process() was not called.

Also, use "task" instead of task->group_leader. badness() should return
the same result for any sub-thread. Currently this is not true, but
this should be changed anyway.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/base.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/proc/base.c b/fs/proc/base.c
index a7310841c83..b1f6e62773d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -442,12 +442,13 @@ static const struct file_operations proc_lstats_operations = {
 unsigned long badness(struct task_struct *p, unsigned long uptime);
 static int proc_oom_score(struct task_struct *task, char *buffer)
 {
-	unsigned long points;
+	unsigned long points = 0;
 	struct timespec uptime;
 
 	do_posix_clock_monotonic_gettime(&uptime);
 	read_lock(&tasklist_lock);
-	points = badness(task->group_leader, uptime.tv_sec);
+	if (pid_alive(task))
+		points = badness(task, uptime.tv_sec);
 	read_unlock(&tasklist_lock);
 	return sprintf(buffer, "%lu\n", points);
 }
-- 
cgit v1.2.3-18-g5258


From 80e755fedebc8de0599a79efad2c656503df2e62 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Wed, 31 Mar 2010 21:52:10 -0700
Subject: ceph: allow writeback of snapped pages older than 'oldest' snapc

On snap deletion, we don't regenerate ceph_cap_snaps for inodes with dirty
pages because deletion does not affect metadata writeback.  However, we
did run into problems when we went to write back the pages because the
'oldest' snapc is determined by the oldest cap_snap, and that may be the
newer snapc that reflects the deletion.  This caused confusion and an
infinite loop in ceph_update_writeable_page().

Change the snapc checks to allow writeback of any snapc that is equal to
OR older than the 'oldest' snapc.

When there are no cap_snaps, we were also using the realm's latest snapc
for writeback, which complicates ceph_put_wrbufffer_cap_refs().  Instead,
use i_head_snapc, the most snapc used for the most recent ('head') data.
This makes the writeback snapc (ceph_osd_request.r_snapc) _always_ match a
capsnap or i_head_snapc.

Also, in writepags_finish(), drop the snapc referenced by the _page_
and do not assume it matches the request snapc (it may not anymore).

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/addr.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

(limited to 'fs')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index ce8ef610772..a313e9baeed 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -356,8 +356,8 @@ static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
 			break;
 		}
 	}
-	if (!snapc && ci->i_snap_realm) {
-		snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);
+	if (!snapc && ci->i_head_snapc) {
+		snapc = ceph_get_snap_context(ci->i_head_snapc);
 		dout(" head snapc %p has %d dirty pages\n",
 		     snapc, ci->i_wrbuffer_ref_head);
 	}
@@ -412,7 +412,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 		dout("writepage %p page %p not dirty?\n", inode, page);
 		goto out;
 	}
-	if (snapc != get_oldest_context(inode, &snap_size)) {
+	if (snapc->seq > get_oldest_context(inode, &snap_size)->seq) {
 		dout("writepage %p page %p snapc %p not writeable - noop\n",
 		     inode, page, (void *)page->private);
 		/* we should only noop if called by kswapd */
@@ -557,9 +557,9 @@ static void writepages_finish(struct ceph_osd_request *req,
 			dout("inode %p skipping page %p\n", inode, page);
 			wbc->pages_skipped++;
 		}
+		ceph_put_snap_context((void *)page->private);
 		page->private = 0;
 		ClearPagePrivate(page);
-		ceph_put_snap_context(snapc);
 		dout("unlocking %d %p\n", i, page);
 		end_page_writeback(page);
 
@@ -617,7 +617,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	int range_whole = 0;
 	int should_loop = 1;
 	pgoff_t max_pages = 0, max_pages_ever = 0;
-	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL;
+	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
@@ -769,9 +769,10 @@ get_more_pages:
 			}
 
 			/* only if matching snap context */
-			if (snapc != (void *)page->private) {
-				dout("page snapc %p != oldest %p\n",
-				     (void *)page->private, snapc);
+			pgsnapc = (void *)page->private;
+			if (pgsnapc->seq > snapc->seq) {
+				dout("page snapc %p %lld > oldest %p %lld\n",
+				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
 				unlock_page(page);
 				if (!locked_pages)
 					continue; /* keep looking for snap */
@@ -935,8 +936,8 @@ static int ceph_update_writeable_page(struct file *file,
 	int pos_in_page = pos & ~PAGE_CACHE_MASK;
 	int end_in_page = pos_in_page + len;
 	loff_t i_size;
-	struct ceph_snap_context *snapc;
 	int r;
+	struct ceph_snap_context *snapc, *oldest;
 
 retry_locked:
 	/* writepages currently holds page lock, but if we change that later, */
@@ -946,16 +947,16 @@ retry_locked:
 	BUG_ON(!ci->i_snap_realm);
 	down_read(&mdsc->snap_rwsem);
 	BUG_ON(!ci->i_snap_realm->cached_context);
-	if (page->private &&
-	    (void *)page->private != ci->i_snap_realm->cached_context) {
+	snapc = (void *)page->private;
+	if (snapc && snapc != ci->i_head_snapc) {
 		/*
 		 * this page is already dirty in another (older) snap
 		 * context!  is it writeable now?
 		 */
-		snapc = get_oldest_context(inode, NULL);
+		oldest = get_oldest_context(inode, NULL);
 		up_read(&mdsc->snap_rwsem);
 
-		if (snapc != (void *)page->private) {
+		if (snapc->seq > oldest->seq) {
 			dout(" page %p snapc %p not current or oldest\n",
 			     page, (void *)page->private);
 			/*
-- 
cgit v1.2.3-18-g5258


From 6298a33757ba7361bb8f506c106daad77e5ac8cf Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Wed, 31 Mar 2010 22:01:38 -0700
Subject: ceph: fix snap context reference leaks

The get_oldest_context() helper takes a reference to the returned snap
context, but most callers weren't dropping that reference.  Fix them.

Also drop the unused locked __get_oldest_context() variant.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/addr.c | 37 +++++++++++++++++--------------------
 1 file changed, 17 insertions(+), 20 deletions(-)

(limited to 'fs')

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index a313e9baeed..41f1f713b7b 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -336,16 +336,15 @@ out:
 /*
  * Get ref for the oldest snapc for an inode with dirty data... that is, the
  * only snap context we are allowed to write back.
- *
- * Caller holds i_lock.
  */
-static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
-						      u64 *snap_size)
+static struct ceph_snap_context *get_oldest_context(struct inode *inode,
+						    u64 *snap_size)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_snap_context *snapc = NULL;
 	struct ceph_cap_snap *capsnap = NULL;
 
+	spin_lock(&inode->i_lock);
 	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
 		     capsnap->context, capsnap->dirty_pages);
@@ -361,16 +360,6 @@ static struct ceph_snap_context *__get_oldest_context(struct inode *inode,
 		dout(" head snapc %p has %d dirty pages\n",
 		     snapc, ci->i_wrbuffer_ref_head);
 	}
-	return snapc;
-}
-
-static struct ceph_snap_context *get_oldest_context(struct inode *inode,
-						    u64 *snap_size)
-{
-	struct ceph_snap_context *snapc = NULL;
-
-	spin_lock(&inode->i_lock);
-	snapc = __get_oldest_context(inode, snap_size);
 	spin_unlock(&inode->i_lock);
 	return snapc;
 }
@@ -391,7 +380,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	int len = PAGE_CACHE_SIZE;
 	loff_t i_size;
 	int err = 0;
-	struct ceph_snap_context *snapc;
+	struct ceph_snap_context *snapc, *oldest;
 	u64 snap_size = 0;
 	long writeback_stat;
 
@@ -412,13 +401,16 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 		dout("writepage %p page %p not dirty?\n", inode, page);
 		goto out;
 	}
-	if (snapc->seq > get_oldest_context(inode, &snap_size)->seq) {
+	oldest = get_oldest_context(inode, &snap_size);
+	if (snapc->seq > oldest->seq) {
 		dout("writepage %p page %p snapc %p not writeable - noop\n",
 		     inode, page, (void *)page->private);
 		/* we should only noop if called by kswapd */
 		WARN_ON((current->flags & PF_MEMALLOC) == 0);
+		ceph_put_snap_context(oldest);
 		goto out;
 	}
+	ceph_put_snap_context(oldest);
 
 	/* is this a partial page at end of file? */
 	if (snap_size)
@@ -457,7 +449,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	ClearPagePrivate(page);
 	end_page_writeback(page);
 	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
-	ceph_put_snap_context(snapc);
+	ceph_put_snap_context(snapc);  /* page's reference */
 out:
 	return err;
 }
@@ -914,7 +906,10 @@ static int context_is_writeable_or_written(struct inode *inode,
 					   struct ceph_snap_context *snapc)
 {
 	struct ceph_snap_context *oldest = get_oldest_context(inode, NULL);
-	return !oldest || snapc->seq <= oldest->seq;
+	int ret = !oldest || snapc->seq <= oldest->seq;
+
+	ceph_put_snap_context(oldest);
+	return ret;
 }
 
 /*
@@ -957,13 +952,14 @@ retry_locked:
 		up_read(&mdsc->snap_rwsem);
 
 		if (snapc->seq > oldest->seq) {
+			ceph_put_snap_context(oldest);
 			dout(" page %p snapc %p not current or oldest\n",
-			     page, (void *)page->private);
+			     page, snapc);
 			/*
 			 * queue for writeback, and wait for snapc to
 			 * be writeable or written
 			 */
-			snapc = ceph_get_snap_context((void *)page->private);
+			snapc = ceph_get_snap_context(snapc);
 			unlock_page(page);
 			ceph_queue_writeback(inode);
 			r = wait_event_interruptible(ci->i_cap_wq,
@@ -973,6 +969,7 @@ retry_locked:
 				return r;
 			return -EAGAIN;
 		}
+		ceph_put_snap_context(oldest);
 
 		/* yay, writeable, do it now (without dropping page lock) */
 		dout(" page %p snapc %p not current, but oldest\n",
-- 
cgit v1.2.3-18-g5258


From 819ccbfa448403992ceafc05d6d7097aaa74d4c3 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Thu, 1 Apr 2010 09:33:46 -0700
Subject: ceph: fix leaked inode ref due to snap metadata writeback race

We create a ceph_cap_snap if there is dirty cap metadata (for writeback to
mds) OR dirty pages (for writeback to osd).  It is thus possible that the
metadata has been written back to the MDS but the OSD data has not when
the cap_snap is created.  This results in a cap_snap with dirty(caps) == 0.
The problem is that cap writeback to the MDS isn't necessary, and a
FLUSHSNAP cap op gets no ack from the MDS.  This leaves the cap_snap
attached to the inode along with its inode reference.

Fix the problem by dropping the cap_snap if it becomes 'complete' (all
pages written out) and dirty(caps) == 0 in ceph_put_wrbuffer_cap_refs().

Also, BUG() in __ceph_flush_snaps() if we encounter a cap_snap with
dirty(caps) == 0.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/caps.c | 42 ++++++++++++++++++++++++++++++++----------
 fs/ceph/snap.c | 10 ++++++----
 2 files changed, 38 insertions(+), 14 deletions(-)

(limited to 'fs')

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 7d0a0d0adc1..b6fdf010749 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1204,6 +1204,12 @@ retry:
 		if (capsnap->dirty_pages || capsnap->writing)
 			continue;
 
+		/*
+		 * if cap writeback already occurred, we should have dropped
+		 * the capsnap in ceph_put_wrbuffer_cap_refs.
+		 */
+		BUG_ON(capsnap->dirty == 0);
+
 		/* pick mds, take s_mutex */
 		mds = __ceph_get_cap_mds(ci, &mseq);
 		if (session && session->s_mds != mds) {
@@ -2117,8 +2123,8 @@ void ceph_put_cap_refs(struct ceph_inode_info *ci, int had)
 		}
 	spin_unlock(&inode->i_lock);
 
-	dout("put_cap_refs %p had %s %s\n", inode, ceph_cap_string(had),
-	     last ? "last" : "");
+	dout("put_cap_refs %p had %s%s%s\n", inode, ceph_cap_string(had),
+	     last ? " last" : "", put ? " put" : "");
 
 	if (last && !flushsnaps)
 		ceph_check_caps(ci, 0, NULL);
@@ -2142,7 +2148,8 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 {
 	struct inode *inode = &ci->vfs_inode;
 	int last = 0;
-	int last_snap = 0;
+	int complete_capsnap = 0;
+	int drop_capsnap = 0;
 	int found = 0;
 	struct ceph_cap_snap *capsnap = NULL;
 
@@ -2165,19 +2172,32 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 		list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
 			if (capsnap->context == snapc) {
 				found = 1;
-				capsnap->dirty_pages -= nr;
-				last_snap = !capsnap->dirty_pages;
 				break;
 			}
 		}
 		BUG_ON(!found);
+		capsnap->dirty_pages -= nr;
+		if (capsnap->dirty_pages == 0) {
+			complete_capsnap = 1;
+			if (capsnap->dirty == 0)
+				/* cap writeback completed before we created
+				 * the cap_snap; no FLUSHSNAP is needed */
+				drop_capsnap = 1;
+		}
 		dout("put_wrbuffer_cap_refs on %p cap_snap %p "
-		     " snap %lld %d/%d -> %d/%d %s%s\n",
+		     " snap %lld %d/%d -> %d/%d %s%s%s\n",
 		     inode, capsnap, capsnap->context->seq,
 		     ci->i_wrbuffer_ref+nr, capsnap->dirty_pages + nr,
 		     ci->i_wrbuffer_ref, capsnap->dirty_pages,
 		     last ? " (wrbuffer last)" : "",
-		     last_snap ? " (capsnap last)" : "");
+		     complete_capsnap ? " (complete capsnap)" : "",
+		     drop_capsnap ? " (drop capsnap)" : "");
+		if (drop_capsnap) {
+			ceph_put_snap_context(capsnap->context);
+			list_del(&capsnap->ci_item);
+			list_del(&capsnap->flushing_item);
+			ceph_put_cap_snap(capsnap);
+		}
 	}
 
 	spin_unlock(&inode->i_lock);
@@ -2185,10 +2205,12 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 	if (last) {
 		ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
 		iput(inode);
-	} else if (last_snap) {
+	} else if (complete_capsnap) {
 		ceph_flush_snaps(ci);
 		wake_up(&ci->i_cap_wq);
 	}
+	if (drop_capsnap)
+		iput(inode);
 }
 
 /*
@@ -2464,8 +2486,8 @@ static void handle_cap_flushsnap_ack(struct inode *inode, u64 flush_tid,
 				break;
 			}
 			WARN_ON(capsnap->dirty_pages || capsnap->writing);
-			dout(" removing cap_snap %p follows %lld\n",
-			     capsnap, follows);
+			dout(" removing %p cap_snap %p follows %lld\n",
+			     inode, capsnap, follows);
 			ceph_put_snap_context(capsnap->context);
 			list_del(&capsnap->ci_item);
 			list_del(&capsnap->flushing_item);
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index df04e210a05..7e3e5f9edaa 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -521,15 +521,17 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 	capsnap->ctime = inode->i_ctime;
 	capsnap->time_warp_seq = ci->i_time_warp_seq;
 	if (capsnap->dirty_pages) {
-		dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu "
+		dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu "
 		     "still has %d dirty pages\n", inode, capsnap,
 		     capsnap->context, capsnap->context->seq,
-		     capsnap->size, capsnap->dirty_pages);
+		     ceph_cap_string(capsnap->dirty), capsnap->size,
+		     capsnap->dirty_pages);
 		return 0;
 	}
-	dout("finish_cap_snap %p cap_snap %p snapc %p %llu s=%llu clean\n",
+	dout("finish_cap_snap %p cap_snap %p snapc %p %llu %s s=%llu\n",
 	     inode, capsnap, capsnap->context,
-	     capsnap->context->seq, capsnap->size);
+	     capsnap->context->seq, ceph_cap_string(capsnap->dirty),
+	     capsnap->size);
 
 	spin_lock(&mdsc->snap_flush_lock);
 	list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list);
-- 
cgit v1.2.3-18-g5258


From 308f44193f796b1c522b3b87760e43d8d8e316d2 Mon Sep 17 00:00:00 2001
From: Li Hong <lihong.hi@gmail.com>
Date: Fri, 2 Apr 2010 18:40:39 +0800
Subject: nilfs2: Remove an uninitialization warning in
 nilfs_btree_propagate_v()

`make CONFIG_NILFS2_FS=m M=fs/nilfs2/` will give the following warnings:

fs/nilfs2/btree.c: In function 'nilfs_btree_propagate':
fs/nilfs2/btree.c:1882: warning: 'maxlevel' may be used uninitialized in this function
fs/nilfs2/btree.c:1882: note: 'maxlevel' was declared here

Set maxlevel = 0 to fix it.

Signed-off-by: Li Hong <lihong.hi@gmail.com>
Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
---
 fs/nilfs2/btree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 7cdd98b8d51..76c38e3e19d 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1879,7 +1879,7 @@ static int nilfs_btree_propagate_v(struct nilfs_btree *btree,
 				   struct nilfs_btree_path *path,
 				   int level, struct buffer_head *bh)
 {
-	int maxlevel, ret;
+	int maxlevel = 0, ret;
 	struct nilfs_btree_node *parent;
 	struct inode *dat = nilfs_bmap_get_dat(&btree->bt_bmap);
 	__u64 ptr;
-- 
cgit v1.2.3-18-g5258


From 0e0d5e0c4bb0476d53a43bfc87d03a25ec4b5579 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Fri, 2 Apr 2010 16:07:19 -0700
Subject: ceph: fix ack counter reset on connection reset

If in_seq_acked isn't reset along with in_seq, we don't ack received
messages until we reach the old count, consuming gobs memory on the other
end of the connection and introducing a large delay when those messages
are eventually deleted.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/messenger.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs')

diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index a32f0f896d9..f35b4945a9c 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -332,6 +332,7 @@ static void reset_connection(struct ceph_connection *con)
 		con->out_msg = NULL;
 	}
 	con->in_seq = 0;
+	con->in_seq_acked = 0;
 }
 
 /*
-- 
cgit v1.2.3-18-g5258


From a24e2d7d8f512340991ef0a59cb5d08d491b8e98 Mon Sep 17 00:00:00 2001
From: Steve French <sfrench@us.ibm.com>
Date: Sat, 3 Apr 2010 17:20:21 +0000
Subject: [CIFS] initialize nbytes at the beginning of CIFSSMBWrite()

By doing this we always overwrite nbytes value that is being passed on to
CIFSSMBWrite() and need not rely on the callers to initialize. CIFSSMBWrite2 is
doing this already.

CC: Stable <stable@kernel.org>
Reviewed-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Reviewed-by: Jeff Layton <jlayton@samba.org>
Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: Steve French <sfrench@us.ibm.com>
---
 fs/cifs/cifssmb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 7cc7f83e931..e1f90a3a016 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1430,6 +1430,8 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 	__u32 bytes_sent;
 	__u16 byte_count;
 
+	*nbytes = 0;
+
 	/* cFYI(1, ("write at %lld %d bytes", offset, count));*/
 	if (tcon->ses == NULL)
 		return -ECONNABORTED;
@@ -1512,7 +1514,6 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 	cifs_stats_inc(&tcon->num_writes);
 	if (rc) {
 		cFYI(1, ("Send error in write = %d", rc));
-		*nbytes = 0;
 	} else {
 		*nbytes = le16_to_cpu(pSMBr->CountHigh);
 		*nbytes = (*nbytes) << 16;
-- 
cgit v1.2.3-18-g5258


From 6513a81e9325d712f1bfb9a1d7b750134e49ff18 Mon Sep 17 00:00:00 2001
From: Suresh Jayaraman <sjayaraman@suse.de>
Date: Wed, 31 Mar 2010 12:00:03 +0530
Subject: cifs: Fix a kernel BUG with remote OS/2 server (try #3)

While chasing a bug report involving a OS/2 server, I noticed the server sets
pSMBr->CountHigh to a incorrect value even in case of normal writes. This
results in 'nbytes' being computed wrongly and triggers a kernel BUG at
mm/filemap.c.

void iov_iter_advance(struct iov_iter *i, size_t bytes)
{
        BUG_ON(i->count < bytes);    <--- BUG here

Why the server is setting 'CountHigh' is not clear but only does so after
writing 64k bytes. Though this looks like the server bug, the client side
crash may not be acceptable.

The workaround is to mask off high 16 bits if the number of bytes written as
returned by the server is greater than the bytes requested by the client as
suggested by Jeff Layton.

CC: Stable <stable@kernel.org>
Reviewed-by: Jeff Layton <jlayton@samba.org>
Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: Steve French <sfrench@us.ibm.com>
---
 fs/cifs/cifssmb.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'fs')

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index e1f90a3a016..f213b8ae43c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1518,6 +1518,14 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 		*nbytes = le16_to_cpu(pSMBr->CountHigh);
 		*nbytes = (*nbytes) << 16;
 		*nbytes += le16_to_cpu(pSMBr->Count);
+
+		/*
+		 * Mask off high 16 bits when bytes written as returned by the
+		 * server is greater than bytes requested by the client. Some
+		 * OS/2 servers are known to set incorrect CountHigh values.
+		 */
+		if (*nbytes > count)
+			*nbytes &= 0xFFFF;
 	}
 
 	cifs_buf_release(pSMB);
@@ -1606,6 +1614,14 @@ CIFSSMBWrite2(const int xid, struct cifsTconInfo *tcon,
 		*nbytes = le16_to_cpu(pSMBr->CountHigh);
 		*nbytes = (*nbytes) << 16;
 		*nbytes += le16_to_cpu(pSMBr->Count);
+
+		/*
+		 * Mask off high 16 bits when bytes written as returned by the
+		 * server is greater than bytes requested by the client. OS/2
+		 * servers are known to set incorrect CountHigh values.
+		 */
+		if (*nbytes > count)
+			*nbytes &= 0xFFFF;
 	}
 
 /*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
-- 
cgit v1.2.3-18-g5258


From d82ef020cf31504c816803b1def94eb5ff173363 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Fri, 2 Apr 2010 09:11:29 +0900
Subject: proc: pagemap: Hold mmap_sem during page walk

In initial design, walk_page_range() was designed just for walking page
table and it didn't require mmap_sem.  Now, find_vma() etc..  are used
in walk_page_range() and we need mmap_sem around it.

This patch adds mmap_sem around walk_page_range().

Because /proc/<pid>/pagemap's callback routine use put_user(), we have
to get rid of it to do sane fix.

Changelog: 2010/Apr/2
 - fixed start_vaddr and end overflow
Changelog: 2010/Apr/1
 - fixed start_vaddr calculation
 - removed unnecessary cast.
 - removed unnecessary change in smaps.
 - use GFP_TEMPORARY instead of GFP_KERNEL

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Matt Mackall <mpm@selenic.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: San Mehat <san@google.com>
Cc: Brian Swetland <swetland@google.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
[ Fixed kmalloc failure return code as per Matt ]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c | 87 ++++++++++++++++++++++++------------------------------
 1 file changed, 38 insertions(+), 49 deletions(-)

(limited to 'fs')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 183f8ff5f40..096273984c3 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -406,6 +406,7 @@ static int show_smap(struct seq_file *m, void *v)
 
 	memset(&mss, 0, sizeof mss);
 	mss.vma = vma;
+	/* mmap_sem is held in m_start */
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
 
@@ -552,7 +553,8 @@ const struct file_operations proc_clear_refs_operations = {
 };
 
 struct pagemapread {
-	u64 __user *out, *end;
+	int pos, len;
+	u64 *buffer;
 };
 
 #define PM_ENTRY_BYTES      sizeof(u64)
@@ -575,10 +577,8 @@ struct pagemapread {
 static int add_to_pagemap(unsigned long addr, u64 pfn,
 			  struct pagemapread *pm)
 {
-	if (put_user(pfn, pm->out))
-		return -EFAULT;
-	pm->out++;
-	if (pm->out >= pm->end)
+	pm->buffer[pm->pos++] = pfn;
+	if (pm->pos >= pm->len)
 		return PM_END_OF_BUFFER;
 	return 0;
 }
@@ -720,21 +720,20 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long addr,
  * determine which areas of memory are actually mapped and llseek to
  * skip over unmapped regions.
  */
+#define PAGEMAP_WALK_SIZE	(PMD_SIZE)
 static ssize_t pagemap_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
 	struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
-	struct page **pages, *page;
-	unsigned long uaddr, uend;
 	struct mm_struct *mm;
 	struct pagemapread pm;
-	int pagecount;
 	int ret = -ESRCH;
 	struct mm_walk pagemap_walk = {};
 	unsigned long src;
 	unsigned long svpfn;
 	unsigned long start_vaddr;
 	unsigned long end_vaddr;
+	int copied = 0;
 
 	if (!task)
 		goto out;
@@ -757,35 +756,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!mm)
 		goto out_task;
 
-
-	uaddr = (unsigned long)buf & PAGE_MASK;
-	uend = (unsigned long)(buf + count);
-	pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
-	ret = 0;
-	if (pagecount == 0)
-		goto out_mm;
-	pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
+	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;
-	if (!pages)
+	if (!pm.buffer)
 		goto out_mm;
 
-	down_read(&current->mm->mmap_sem);
-	ret = get_user_pages(current, current->mm, uaddr, pagecount,
-			     1, 0, pages, NULL);
-	up_read(&current->mm->mmap_sem);
-
-	if (ret < 0)
-		goto out_free;
-
-	if (ret != pagecount) {
-		pagecount = ret;
-		ret = -EFAULT;
-		goto out_pages;
-	}
-
-	pm.out = (u64 __user *)buf;
-	pm.end = (u64 __user *)(buf + count);
-
 	pagemap_walk.pmd_entry = pagemap_pte_range;
 	pagemap_walk.pte_hole = pagemap_pte_hole;
 	pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
@@ -807,23 +783,36 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	 * user buffer is tracked in "pm", and the walk
 	 * will stop when we hit the end of the buffer.
 	 */
-	ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk);
-	if (ret == PM_END_OF_BUFFER)
-		ret = 0;
-	/* don't need mmap_sem for these, but this looks cleaner */
-	*ppos += (char __user *)pm.out - buf;
-	if (!ret)
-		ret = (char __user *)pm.out - buf;
-
-out_pages:
-	for (; pagecount; pagecount--) {
-		page = pages[pagecount-1];
-		if (!PageReserved(page))
-			SetPageDirty(page);
-		page_cache_release(page);
+	ret = 0;
+	while (count && (start_vaddr < end_vaddr)) {
+		int len;
+		unsigned long end;
+
+		pm.pos = 0;
+		end = start_vaddr + PAGEMAP_WALK_SIZE;
+		/* overflow ? */
+		if (end < start_vaddr || end > end_vaddr)
+			end = end_vaddr;
+		down_read(&mm->mmap_sem);
+		ret = walk_page_range(start_vaddr, end, &pagemap_walk);
+		up_read(&mm->mmap_sem);
+		start_vaddr = end;
+
+		len = min(count, PM_ENTRY_BYTES * pm.pos);
+		if (copy_to_user(buf, pm.buffer, len) < 0) {
+			ret = -EFAULT;
+			goto out_free;
+		}
+		copied += len;
+		buf += len;
+		count -= len;
 	}
+	*ppos += copied;
+	if (!ret || ret == PM_END_OF_BUFFER)
+		ret = copied;
+
 out_free:
-	kfree(pages);
+	kfree(pm.buffer);
 out_mm:
 	mmput(mm);
 out_task:
-- 
cgit v1.2.3-18-g5258


From 476ada0436351672fbf482db54cb94b8ba877709 Mon Sep 17 00:00:00 2001
From: Sripathi Kodi <sripathik@in.ibm.com>
Date: Wed, 17 Mar 2010 17:02:38 +0000
Subject: 9p: Fix setting of protocol flags in v9fs_session_info structure.

This patch fixes a simple bug I left behind in my earlier protocol
negotiation patch.

Thanks,
Sripathi.

Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/v9fs.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 6c7f6a25111..2f814cf0c73 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -241,7 +241,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	list_add(&v9ses->slist, &v9fs_sessionlist);
 	spin_unlock(&v9fs_sessionlist_lock);
 
-	v9ses->flags = V9FS_PROTO_2000U | V9FS_ACCESS_USER;
+	v9ses->flags = V9FS_ACCESS_USER;
 	strcpy(v9ses->uname, V9FS_DEFUSER);
 	strcpy(v9ses->aname, V9FS_DEFANAME);
 	v9ses->uid = ~0;
@@ -262,8 +262,10 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		goto error;
 	}
 
-	if (!p9_is_proto_dotu(v9ses->clnt))
-		v9ses->flags &= ~V9FS_PROTO_2000U;
+	if (p9_is_proto_dotl(v9ses->clnt))
+		v9ses->flags |= V9FS_PROTO_2000L;
+	else if (p9_is_proto_dotu(v9ses->clnt))
+		v9ses->flags |= V9FS_PROTO_2000U;
 
 	v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
 
-- 
cgit v1.2.3-18-g5258


From 5b0fa207d1a6f27c9a2f2d707147dce01af21db7 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Fri, 19 Mar 2010 12:47:26 +0000
Subject: fs/9p: Clunk the fid resulting from partial walk of the name

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/fid.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 08b2eb15704..b0a23c7e736 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -110,7 +110,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 {
 	int i, n, l, clone, any, access;
 	u32 uid;
-	struct p9_fid *fid;
+	struct p9_fid *fid, *old_fid = NULL;
 	struct dentry *d, *ds;
 	struct v9fs_session_info *v9ses;
 	char **wnames, *uname;
@@ -183,10 +183,18 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry)
 		l = min(n - i, P9_MAXWELEM);
 		fid = p9_client_walk(fid, l, &wnames[i], clone);
 		if (IS_ERR(fid)) {
+			if (old_fid) {
+				/*
+				 * If we fail, clunk fid which are mapping
+				 * to path component and not the last component
+				 * of the path.
+				 */
+				p9_client_clunk(old_fid);
+			}
 			kfree(wnames);
 			return fid;
 		}
-
+		old_fid = fid;
 		i += l;
 		clone = 0;
 	}
-- 
cgit v1.2.3-18-g5258


From d994f4058d9f9be7e44529b55fc6be6552901ead Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 29 Mar 2010 18:14:50 -0500
Subject: 9p: drop nlink remove

We need to drop the link count on the inode of a sucessfull remove

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/vfs_inode.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 5fe45d692c9..ae839670770 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -431,6 +431,7 @@ error:
 
 static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir)
 {
+	int retval;
 	struct inode *file_inode;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *v9fid;
@@ -444,7 +445,10 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir)
 	if (IS_ERR(v9fid))
 		return PTR_ERR(v9fid);
 
-	return p9_client_remove(v9fid);
+	retval = p9_client_remove(v9fid);
+	if (!retval)
+		drop_nlink(file_inode);
+	return retval;
 }
 
 static int
-- 
cgit v1.2.3-18-g5258


From 6d96d3ab7aea5f0e75205a0c97f8d1fdf82c5287 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Mon, 29 Mar 2010 18:13:59 -0500
Subject: 9p: Make sure we are able to clunk the cached fid on umount

dcache prune happen on umount. So we cannot mark the client
satus disconnect. That will prevent a 9p call to the server

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/v9fs.c      | 13 +++++++++++++
 fs/9p/v9fs.h      |  1 +
 fs/9p/vfs_super.c |  3 ++-
 3 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 2f814cf0c73..0b78ae8157b 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -342,6 +342,19 @@ void v9fs_session_cancel(struct v9fs_session_info *v9ses) {
 	p9_client_disconnect(v9ses->clnt);
 }
 
+/**
+ * v9fs_session_begin_cancel - Begin terminate of a session
+ * @v9ses: session to terminate
+ *
+ * After this call we don't allow any request other than clunk.
+ */
+
+void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses)
+{
+	P9_DPRINTK(P9_DEBUG_ERROR, "begin cancel session %p\n", v9ses);
+	p9_client_begin_disconnect(v9ses->clnt);
+}
+
 extern int v9fs_error_init(void);
 
 static struct kobject *v9fs_kobj;
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 6b801d1ddf4..a0a8d3dd136 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -108,6 +108,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
 									char *);
 void v9fs_session_close(struct v9fs_session_info *v9ses);
 void v9fs_session_cancel(struct v9fs_session_info *v9ses);
+void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
 
 #define V9FS_MAGIC 0x01021997
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 69357c0d989..d1a3c809a29 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -193,6 +193,7 @@ static void v9fs_kill_super(struct super_block *s)
 
 	kill_anon_super(s);
 
+	v9fs_session_cancel(v9ses);
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
 	s->s_fs_info = NULL;
@@ -205,7 +206,7 @@ v9fs_umount_begin(struct super_block *sb)
 	struct v9fs_session_info *v9ses;
 
 	v9ses = sb->s_fs_info;
-	v9fs_session_cancel(v9ses);
+	v9fs_session_begin_cancel(v9ses);
 }
 
 static const struct super_operations v9fs_super_ops = {
-- 
cgit v1.2.3-18-g5258


From 11e9b49b7fa056bfc00a56de8956d1d5fe8b84ea Mon Sep 17 00:00:00 2001
From: Sripathi Kodi <sripathik@in.ibm.com>
Date: Mon, 29 Mar 2010 18:13:59 -0500
Subject: 9p: Creating files with names too long should fail with ENAMETOOLONG.

Signed-off-by: Sripathi Kodi <sripathik@in.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/vfs_inode.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'fs')

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index ae839670770..905f664b8bc 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -660,6 +660,9 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	P9_DPRINTK(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p nameidata: %p\n",
 		dir, dentry->d_name.name, dentry, nameidata);
 
+	if (dentry->d_name.len > NAME_MAX)
+		return ERR_PTR(-ENAMETOOLONG);
+
 	sb = dir->i_sb;
 	v9ses = v9fs_inode2v9ses(dir);
 	dfid = v9fs_fid_lookup(dentry->d_parent);
-- 
cgit v1.2.3-18-g5258


From 28ecb60906e86e74e9ad4ac7e0218d8631e73a94 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Wed, 17 Mar 2010 13:31:04 +0000
Subject: Btrfs: use add_to_page_cache_lru, use __page_cache_alloc

Pagecache pages should be allocated with __page_cache_alloc, so they
obey pagecache memory policies.

add_to_page_cache_lru is exported, so it should be used. Benefits over
using a private pagevec: neater code, 128 bytes fewer stack used, percpu
lru ordering is preserved, and finally don't need to flush pagevec
before returning so batching may be shared with other LRU insertions.

Signed-off-by: Nick Piggin <npiggin@suse.de>:
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/compression.c | 22 ++++------------------
 fs/btrfs/extent_io.c   | 15 +--------------
 2 files changed, 5 insertions(+), 32 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 28b92a7218a..1d54c5308df 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -31,7 +31,6 @@
 #include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/bit_spinlock.h>
-#include <linux/pagevec.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"
@@ -445,7 +444,6 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 	unsigned long nr_pages = 0;
 	struct extent_map *em;
 	struct address_space *mapping = inode->i_mapping;
-	struct pagevec pvec;
 	struct extent_map_tree *em_tree;
 	struct extent_io_tree *tree;
 	u64 end;
@@ -461,7 +459,6 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 
 	end_index = (i_size_read(inode) - 1) >> PAGE_CACHE_SHIFT;
 
-	pagevec_init(&pvec, 0);
 	while (last_offset < compressed_end) {
 		page_index = last_offset >> PAGE_CACHE_SHIFT;
 
@@ -478,26 +475,17 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 			goto next;
 		}
 
-		page = alloc_page(mapping_gfp_mask(mapping) & ~__GFP_FS);
+		page = __page_cache_alloc(mapping_gfp_mask(mapping) &
+								~__GFP_FS);
 		if (!page)
 			break;
 
-		page->index = page_index;
-		/*
-		 * what we want to do here is call add_to_page_cache_lru,
-		 * but that isn't exported, so we reproduce it here
-		 */
-		if (add_to_page_cache(page, mapping,
-				      page->index, GFP_NOFS)) {
+		if (add_to_page_cache_lru(page, mapping, page_index,
+								GFP_NOFS)) {
 			page_cache_release(page);
 			goto next;
 		}
 
-		/* open coding of lru_cache_add, also not exported */
-		page_cache_get(page);
-		if (!pagevec_add(&pvec, page))
-			__pagevec_lru_add_file(&pvec);
-
 		end = last_offset + PAGE_CACHE_SIZE - 1;
 		/*
 		 * at this point, we have a locked page in the page cache
@@ -551,8 +539,6 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 next:
 		last_offset += PAGE_CACHE_SIZE;
 	}
-	if (pagevec_count(&pvec))
-		__pagevec_lru_add_file(&pvec);
 	return 0;
 }
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c99121ac5d6..fc742e59815 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2679,33 +2679,20 @@ int extent_readpages(struct extent_io_tree *tree,
 {
 	struct bio *bio = NULL;
 	unsigned page_idx;
-	struct pagevec pvec;
 	unsigned long bio_flags = 0;
 
-	pagevec_init(&pvec, 0);
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		struct page *page = list_entry(pages->prev, struct page, lru);
 
 		prefetchw(&page->flags);
 		list_del(&page->lru);
-		/*
-		 * what we want to do here is call add_to_page_cache_lru,
-		 * but that isn't exported, so we reproduce it here
-		 */
-		if (!add_to_page_cache(page, mapping,
+		if (!add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
-
-			/* open coding of lru_cache_add, also not exported */
-			page_cache_get(page);
-			if (!pagevec_add(&pvec, page))
-				__pagevec_lru_add_file(&pvec);
 			__extent_read_full_page(tree, page, get_extent,
 						&bio, 0, &bio_flags);
 		}
 		page_cache_release(page);
 	}
-	if (pagevec_count(&pvec))
-		__pagevec_lru_add_file(&pvec);
 	BUG_ON(!list_empty(pages));
 	if (bio)
 		submit_one_bio(READ, bio, 0, bio_flags);
-- 
cgit v1.2.3-18-g5258


From b5cb160084fad438c513d0952849e597ffe9e3d9 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@redhat.com>
Date: Fri, 12 Mar 2010 19:28:18 +0000
Subject: Btrfs: fix small race with delalloc flushing waitqueue's

Everytime we start a new flushing thread, we init the waitqueue if there isn't a
flushing thread running.  The problem with this is we check
space_info->flushing, which we clear right before doing a wake_up on the
flushing waitqueue, which causes problems if we init the waitqueue in the middle
of clearing the flushing flagh and calling wake_up.  This is hard to hit, but
the code is wrong anyway, so init the flushing/allocating waitqueue when
creating the space info and let it be.  I haven't seen the panic since I've been
using this patch.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/extent-tree.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5f6bc283c0c..101041d4d2b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2676,6 +2676,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 
 	INIT_LIST_HEAD(&found->block_groups);
 	init_rwsem(&found->groups_sem);
+	init_waitqueue_head(&found->flush_wait);
+	init_waitqueue_head(&found->allocate_wait);
 	spin_lock_init(&found->lock);
 	found->flags = flags;
 	found->total_bytes = total_bytes;
@@ -2944,12 +2946,10 @@ static void flush_delalloc(struct btrfs_root *root,
 
 	spin_lock(&info->lock);
 
-	if (!info->flushing) {
+	if (!info->flushing)
 		info->flushing = 1;
-		init_waitqueue_head(&info->flush_wait);
-	} else {
+	else
 		wait = true;
-	}
 
 	spin_unlock(&info->lock);
 
@@ -3011,7 +3011,6 @@ static int maybe_allocate_chunk(struct btrfs_root *root,
 	if (!info->allocating_chunk) {
 		info->force_alloc = 1;
 		info->allocating_chunk = 1;
-		init_waitqueue_head(&info->allocate_wait);
 	} else {
 		wait = true;
 	}
-- 
cgit v1.2.3-18-g5258


From 6bdb72ded1e281cd8844918c39d00cdd0e59f655 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Mon, 15 Mar 2010 17:27:13 +0000
Subject: Btrfs: create snapshot references in same commit as snapshot

This creates the reference to a new snapshot in the same commit as the
snapshot itself.  This avoids the need for a second commit in order for a
snapshot to be persistent, and also avoids the problem of "leaking" a
new snapshot tree root if the host crashes before the second commit takes
place.

It is not at all clear to me why it wasn't always done this way.  If there
is still a reason for the two-stage {create,finish}_pending_snapshots()
approach I'm missing something!  :)

I've been running this for a couple weeks under pretty heavy usage (a few
snapshots per minute) without obvious problems.

Signed-off-by: Sage Weil <sage@newdream.net>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/transaction.c | 97 ++++++++++++++++----------------------------------
 1 file changed, 31 insertions(+), 66 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 43054285f63..01cebd66199 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -755,10 +755,17 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	struct btrfs_root_item *new_root_item;
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_root *root = pending->root;
+	struct btrfs_root *parent_root;
+	struct inode *parent_inode;
 	struct extent_buffer *tmp;
 	struct extent_buffer *old;
 	int ret;
 	u64 objectid;
+	int namelen;
+	u64 index = 0;
+
+	parent_inode = pending->dentry->d_parent->d_inode;
+	parent_root = BTRFS_I(parent_inode)->root;
 
 	new_root_item = kmalloc(sizeof(*new_root_item), GFP_NOFS);
 	if (!new_root_item) {
@@ -769,79 +776,59 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto fail;
 
-	record_root_in_trans(trans, root);
-	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
-	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
-
 	key.objectid = objectid;
 	/* record when the snapshot was created in key.offset */
 	key.offset = trans->transid;
 	btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
 
-	old = btrfs_lock_root_node(root);
-	btrfs_cow_block(trans, root, old, NULL, 0, &old);
-	btrfs_set_lock_blocking(old);
-
-	btrfs_copy_root(trans, root, old, &tmp, objectid);
-	btrfs_tree_unlock(old);
-	free_extent_buffer(old);
-
-	btrfs_set_root_node(new_root_item, tmp);
-	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
-				new_root_item);
-	btrfs_tree_unlock(tmp);
-	free_extent_buffer(tmp);
-	if (ret)
-		goto fail;
-
-	key.offset = (u64)-1;
 	memcpy(&pending->root_key, &key, sizeof(key));
-fail:
-	kfree(new_root_item);
-	return ret;
-}
-
-static noinline int finish_pending_snapshot(struct btrfs_fs_info *fs_info,
-				   struct btrfs_pending_snapshot *pending)
-{
-	int ret;
-	int namelen;
-	u64 index = 0;
-	struct btrfs_trans_handle *trans;
-	struct inode *parent_inode;
-	struct btrfs_root *parent_root;
-
-	parent_inode = pending->dentry->d_parent->d_inode;
-	parent_root = BTRFS_I(parent_inode)->root;
-	trans = btrfs_join_transaction(parent_root, 1);
+	pending->root_key.offset = (u64)-1;
 
+	record_root_in_trans(trans, parent_root);
 	/*
 	 * insert the directory item
 	 */
 	namelen = strlen(pending->name);
 	ret = btrfs_set_inode_index(parent_inode, &index);
+	BUG_ON(ret);
 	ret = btrfs_insert_dir_item(trans, parent_root,
 			    pending->name, namelen,
 			    parent_inode->i_ino,
 			    &pending->root_key, BTRFS_FT_DIR, index);
-
-	if (ret)
-		goto fail;
+	BUG_ON(ret);
 
 	btrfs_i_size_write(parent_inode, parent_inode->i_size + namelen * 2);
 	ret = btrfs_update_inode(trans, parent_root, parent_inode);
 	BUG_ON(ret);
 
+	record_root_in_trans(trans, root);
+	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
+	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
+
+	old = btrfs_lock_root_node(root);
+	btrfs_cow_block(trans, root, old, NULL, 0, &old);
+	btrfs_set_lock_blocking(old);
+
+	btrfs_copy_root(trans, root, old, &tmp, objectid);
+	btrfs_tree_unlock(old);
+	free_extent_buffer(old);
+
+	btrfs_set_root_node(new_root_item, tmp);
+	ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
+				new_root_item);
+	BUG_ON(ret);
+	btrfs_tree_unlock(tmp);
+	free_extent_buffer(tmp);
+
 	ret = btrfs_add_root_ref(trans, parent_root->fs_info->tree_root,
 				 pending->root_key.objectid,
 				 parent_root->root_key.objectid,
 				 parent_inode->i_ino, index, pending->name,
 				 namelen);
-
 	BUG_ON(ret);
 
 fail:
-	btrfs_end_transaction(trans, fs_info->fs_root);
+	kfree(new_root_item);
 	return ret;
 }
 
@@ -862,25 +849,6 @@ static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-static noinline int finish_pending_snapshots(struct btrfs_trans_handle *trans,
-					     struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_pending_snapshot *pending;
-	struct list_head *head = &trans->transaction->pending_snapshots;
-	int ret;
-
-	while (!list_empty(head)) {
-		pending = list_entry(head->next,
-				     struct btrfs_pending_snapshot, list);
-		ret = finish_pending_snapshot(fs_info, pending);
-		BUG_ON(ret);
-		list_del(&pending->list);
-		kfree(pending->name);
-		kfree(pending);
-	}
-	return 0;
-}
-
 static void update_super_roots(struct btrfs_root *root)
 {
 	struct btrfs_root_item *root_item;
@@ -1092,9 +1060,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 	btrfs_finish_extent_commit(trans, root);
 
-	/* do the directory inserts of any pending snapshot creations */
-	finish_pending_snapshots(trans, root->fs_info);
-
 	mutex_lock(&root->fs_info->trans_mutex);
 
 	cur_trans->commit_done = 1;
-- 
cgit v1.2.3-18-g5258


From 109f6aef5fc436f355ad027f4d97bd696df2049a Mon Sep 17 00:00:00 2001
From: Chris Mason <chris.mason@oracle.com>
Date: Fri, 2 Apr 2010 09:20:18 -0400
Subject: Btrfs: add check for changed leaves in setup_leaf_for_split

setup_leaf_for_split needs to drop the path and search again, and has
checks to see if the item we want to split changed size.  But, it misses
the case where the leaf changed and now has enough room for the item
we want to insert.

This adds an extra check to make sure the leaf really needs splitting
before we call btrfs_split_leaf(), which keeps us from trying to split
a leaf with a single item.

btrfs_split_leaf() will blindly split the single item leaf, leaving us
with one good leaf and one empty leaf and then a crash.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/ctree.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'fs')

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index c4bc570a396..babf7fbaec8 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -3040,6 +3040,10 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans,
 	if (ret > 0 || item_size != btrfs_item_size_nr(leaf, path->slots[0]))
 		goto err;
 
+	/* the leaf has  changed, it now has room.  return now */
+	if (btrfs_leaf_free_space(root, path->nodes[0]) >= ins_len)
+		goto err;
+
 	if (key.type == BTRFS_EXTENT_DATA_KEY) {
 		fi = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_file_extent_item);
-- 
cgit v1.2.3-18-g5258


From 85a770a8889035625466a4cfb1393cd7d2ffd165 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Tue, 30 Mar 2010 09:41:25 +0000
Subject: 9p: return on mutex_lock_interruptible()

If "err" is -EINTR here the original code calls mutex_unlock() and then
returns, but it should just return directly.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>

------------------------------------------------------------------------------
Download Intel&#174; Parallel Studio Eval
Try the new software tools for yourself. Speed compiling, find bugs
proactively, and fine-tune applications for parallel performance.
See why Intel Parallel Studio got high marks during beta.
http://p.sf.net/sfu/intel-sw-dev
---
 fs/9p/vfs_dir.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'fs')

diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index d8a3afe4ff7..bbe00cf799f 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -130,6 +130,8 @@ static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	rdir = (struct p9_rdir *) fid->rdir;
 
 	err = mutex_lock_interruptible(&rdir->mutex);
+	if (err)
+		return err;
 	while (err == 0) {
 		if (rdir->tail == rdir->head) {
 			err = v9fs_file_readn(filp, rdir->buf, NULL,
-- 
cgit v1.2.3-18-g5258


From ab6e24103cbd215e922938a4f58c75194761a60e Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@redhat.com>
Date: Fri, 19 Mar 2010 14:38:13 +0000
Subject: Btrfs: fix data enospc check overflow

Because we account for reserved space we get from the allocator before we
actually account for allocating delalloc space, we can have a small window where
the amount of "used" space in a space_info is more than the total amount of
space in the space_info.  This will cause a overflow in our check, so it will
seem like we have _tons_ of free space, and we'll allow reservations to occur
that will end up larger than the amount of space we have.  I've seen users
report ENOSPC panic's in cow_file_range a few times recently, so I tried to
reproduce this problem and found I could reproduce it if I ran one of my tests
in a loop for like 20 minutes.  With this patch my test ran all night without
issues.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/extent-tree.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

(limited to 'fs')

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 101041d4d2b..786899da3eb 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3234,7 +3234,8 @@ int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
 				u64 bytes)
 {
 	struct btrfs_space_info *data_sinfo;
-	int ret = 0, committed = 0;
+	u64 used;
+	int ret = 0, committed = 0, flushed = 0;
 
 	/* make sure bytes are sectorsize aligned */
 	bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
@@ -3246,12 +3247,21 @@ int btrfs_check_data_free_space(struct btrfs_root *root, struct inode *inode,
 again:
 	/* make sure we have enough space to handle the data first */
 	spin_lock(&data_sinfo->lock);
-	if (data_sinfo->total_bytes - data_sinfo->bytes_used -
-	    data_sinfo->bytes_delalloc - data_sinfo->bytes_reserved -
-	    data_sinfo->bytes_pinned - data_sinfo->bytes_readonly -
-	    data_sinfo->bytes_may_use - data_sinfo->bytes_super < bytes) {
+	used = data_sinfo->bytes_used + data_sinfo->bytes_delalloc +
+		data_sinfo->bytes_reserved + data_sinfo->bytes_pinned +
+		data_sinfo->bytes_readonly + data_sinfo->bytes_may_use +
+		data_sinfo->bytes_super;
+
+	if (used + bytes > data_sinfo->total_bytes) {
 		struct btrfs_trans_handle *trans;
 
+		if (!flushed) {
+			spin_unlock(&data_sinfo->lock);
+			flush_delalloc(root, data_sinfo);
+			flushed = 1;
+			goto again;
+		}
+
 		/*
 		 * if we don't have enough free bytes in this space then we need
 		 * to alloc a new chunk.
-- 
cgit v1.2.3-18-g5258


From 9f680ce04ea19dabbbafe01b57b61930a9b70741 Mon Sep 17 00:00:00 2001
From: Chris Mason <chris.mason@oracle.com>
Date: Tue, 6 Apr 2010 09:37:47 -0400
Subject: Btrfs: make sure the chunk allocator doesn't create zero length
 chunks

A recent commit allowed for smaller chunks to be created, but didn't
make sure they were always bigger than a stripe.  After some divides,
this led to zero length stripes.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
---
 fs/btrfs/volumes.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'fs')

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9bf1f581b87..b584e9a2add 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2249,6 +2249,12 @@ again:
 	if (!looped)
 		calc_size = max_t(u64, min_stripe_size, calc_size);
 
+	/*
+	 * we're about to do_div by the stripe_len so lets make sure
+	 * we end up with something bigger than a stripe
+	 */
+	calc_size = max_t(u64, calc_size, stripe_len * 4);
+
 	do_div(calc_size, stripe_len);
 	calc_size *= stripe_len;
 
-- 
cgit v1.2.3-18-g5258


From 309361e09ca9e9670dc8664e5d14125bf82078af Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Tue, 6 Apr 2010 13:45:39 +0300
Subject: proc: copy_to_user() returns unsigned

copy_to_user() returns the number of bytes left to be copied.

This was a typo from: d82ef020cf31 "proc: pagemap: Hold mmap_sem during
page walk".

Signed-off-by: Dan Carpenter <error27@gmail.com>
Acked-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index caf0337dff7..a05a669510a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -800,7 +800,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 		start_vaddr = end;
 
 		len = min(count, PM_ENTRY_BYTES * pm.pos);
-		if (copy_to_user(buf, pm.buffer, len) < 0) {
+		if (copy_to_user(buf, pm.buffer, len)) {
 			ret = -EFAULT;
 			goto out_free;
 		}
-- 
cgit v1.2.3-18-g5258


From f05337c6ac48d19d354e0640a8eb8fc884f82bcc Mon Sep 17 00:00:00 2001
From: Pavel Shilovsky <piastryyy@gmail.com>
Date: Mon, 5 Apr 2010 09:59:14 +0400
Subject: not overwriting file_lock structure after GET_LK

If we have preventing lock, cifs should overwrite file_lock structure
with info about preventing lock. If we haven't preventing lock, cifs
should leave it unchanged except for the lock type (change it to F_UNLCK).

Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Reviewed-by: Jeff Layton <jlayton@samba.org>
Signed-off-by: Steve French <sfrench@us.ibm.com>
---
 fs/cifs/cifssmb.c | 15 ++++++++++++++-
 fs/cifs/file.c    | 28 ++++++++++++++++++++++++++--
 2 files changed, 40 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index f213b8ae43c..184a399749a 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1810,8 +1810,21 @@ CIFSSMBPosixLock(const int xid, struct cifsTconInfo *tcon,
 		}
 		parm_data = (struct cifs_posix_lock *)
 			((char *)&pSMBr->hdr.Protocol + data_offset);
-		if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
+		if (parm_data->lock_type == __constant_cpu_to_le16(CIFS_UNLCK))
 			pLockData->fl_type = F_UNLCK;
+		else {
+			if (parm_data->lock_type ==
+					__constant_cpu_to_le16(CIFS_RDLCK))
+				pLockData->fl_type = F_RDLCK;
+			else if (parm_data->lock_type ==
+					__constant_cpu_to_le16(CIFS_WRLCK))
+				pLockData->fl_type = F_WRLCK;
+
+			pLockData->fl_start = parm_data->start;
+			pLockData->fl_end = parm_data->start +
+						parm_data->length - 1;
+			pLockData->fl_pid = parm_data->pid;
+		}
 	}
 
 plk_err_exit:
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ca2ba7a0193..d9e86504b9d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -838,8 +838,32 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
 
 		} else {
 			/* if rc == ERR_SHARING_VIOLATION ? */
-			rc = 0;	/* do not change lock type to unlock
-				   since range in use */
+			rc = 0;
+
+			if (lockType & LOCKING_ANDX_SHARED_LOCK) {
+				pfLock->fl_type = F_WRLCK;
+			} else {
+				rc = CIFSSMBLock(xid, tcon, netfid, length,
+					pfLock->fl_start, 0, 1,
+					lockType | LOCKING_ANDX_SHARED_LOCK,
+					0 /* wait flag */);
+				if (rc == 0) {
+					rc = CIFSSMBLock(xid, tcon, netfid,
+						length, pfLock->fl_start, 1, 0,
+						lockType |
+						LOCKING_ANDX_SHARED_LOCK,
+						0 /* wait flag */);
+					pfLock->fl_type = F_RDLCK;
+					if (rc != 0)
+						cERROR(1, ("Error unlocking "
+						"previously locked range %d "
+						"during test of lock", rc));
+					rc = 0;
+				} else {
+					pfLock->fl_type = F_WRLCK;
+					rc = 0;
+				}
+			}
 		}
 
 		FreeXid(xid);
-- 
cgit v1.2.3-18-g5258


From 55ab3a1ff843e3f0e24d2da44e71bffa5d853010 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 6 Apr 2010 14:34:58 -0700
Subject: raw: fsync method is now required

Commit 148f948ba877f4d3cdef036b1ff6d9f68986706a (vfs: Introduce new
helpers for syncing after writing to O_SYNC file or IS_SYNC inode) broke
the raw driver.

We now call through generic_file_aio_write -> generic_write_sync ->
vfs_fsync_range.  vfs_fsync_range has:

        if (!fop || !fop->fsync) {
                ret = -EINVAL;
                goto out;
        }

But drivers/char/raw.c doesn't set an fsync method.

We have two options: fix it or remove the raw driver completely.  I'm
happy to do either, the fact this has been broken for so long suggests it
is rarely used.

The patch below adds an fsync method to the raw driver.  My knowledge of
the block layer is pretty sketchy so this could do with a once over.

If we instead decide to remove the raw driver, this patch might still be
useful as a backport to 2.6.33 and 2.6.32.

Signed-off-by: Anton Blanchard <anton@samba.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <jens.axboe@oracle.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Tested-by: Jeff Moyer <jmoyer@redhat.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/block_dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index d11d0289f3d..8db62b2b6df 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -404,7 +404,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
  *	NULL first argument is nfsd_sync_dir() and that's not a directory.
  */
  
-static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
+int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
 	int error;
@@ -418,6 +418,7 @@ static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
 		error = 0;
 	return error;
 }
+EXPORT_SYMBOL(block_fsync);
 
 /*
  * pseudo-fs
-- 
cgit v1.2.3-18-g5258


From b1dd3b2843b3b73b7fc2ee47d96310cd1c051371 Mon Sep 17 00:00:00 2001
From: Andrew Morton <akpm@linux-foundation.org>
Date: Tue, 6 Apr 2010 14:35:00 -0700
Subject: vfs: rename block_fsync() to blkdev_fsync()

Requested by hch, for consistency now it is exported.

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Anton Blanchard <anton@samba.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Jan Kara <jack@suse.cz>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/block_dev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'fs')

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8db62b2b6df..2a6d0193f13 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -404,7 +404,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin)
  *	NULL first argument is nfsd_sync_dir() and that's not a directory.
  */
  
-int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
+int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
 	int error;
@@ -418,7 +418,7 @@ int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
 		error = 0;
 	return error;
 }
-EXPORT_SYMBOL(block_fsync);
+EXPORT_SYMBOL(blkdev_fsync);
 
 /*
  * pseudo-fs
@@ -1482,7 +1482,7 @@ const struct file_operations def_blk_fops = {
   	.aio_read	= generic_file_aio_read,
 	.aio_write	= blkdev_aio_write,
 	.mmap		= generic_file_mmap,
-	.fsync		= block_fsync,
+	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= compat_blkdev_ioctl,
-- 
cgit v1.2.3-18-g5258


From 116354d177ba2da37e91cf884e3d11e67f825efd Mon Sep 17 00:00:00 2001
From: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Date: Tue, 6 Apr 2010 14:35:04 -0700
Subject: pagemap: fix pfn calculation for hugepage

When we look into pagemap using page-types with option -p, the value of
pfn for hugepages looks wrong (see below.) This is because pte was
evaluated only once for one vma although it should be updated for each
hugepage.  This patch fixes it.

  $ page-types -p 3277 -Nl -b huge
  voffset   offset  len     flags
  7f21e8a00 11e400  1       ___U___________H_G________________
  7f21e8a01 11e401  1ff     ________________TG________________
               ^^^
  7f21e8c00 11e400  1       ___U___________H_G________________
  7f21e8c01 11e401  1ff     ________________TG________________
               ^^^

One hugepage contains 1 head page and 511 tail pages in x86_64 and each
two lines represent each hugepage.  Voffset and offset mean virtual
address and physical address in the page unit, respectively.  The
different hugepages should not have the same offset value.

With this patch applied:

  $ page-types -p 3386 -Nl -b huge
  voffset   offset   len    flags
  7fec7a600 112c00   1      ___UD__________H_G________________
  7fec7a601 112c01   1ff    ________________TG________________
               ^^^
  7fec7a800 113200   1      ___UD__________H_G________________
  7fec7a801 113201   1ff    ________________TG________________
               ^^^
               OK

More info:

- This patch modifies walk_page_range()'s hugepage walker.  But the
  change only affects pagemap_read(), which is the only caller of hugepage
  callback.

- Without this patch, hugetlb_entry() callback is called per vma, that
  doesn't match the natural expectation from its name.

- With this patch, hugetlb_entry() is called per hugepte entry and the
  callback can become much simpler.

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Matt Mackall <mpm@selenic.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/proc/task_mmu.c | 27 +++++++--------------------
 1 file changed, 7 insertions(+), 20 deletions(-)

(limited to 'fs')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index a05a669510a..070553427dd 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -662,31 +662,18 @@ static u64 huge_pte_to_pagemap_entry(pte_t pte, int offset)
 	return pme;
 }
 
-static int pagemap_hugetlb_range(pte_t *pte, unsigned long addr,
-				 unsigned long end, struct mm_walk *walk)
+/* This function walks within one hugetlb entry in the single call */
+static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
+				 unsigned long addr, unsigned long end,
+				 struct mm_walk *walk)
 {
-	struct vm_area_struct *vma;
 	struct pagemapread *pm = walk->private;
-	struct hstate *hs = NULL;
 	int err = 0;
+	u64 pfn;
 
-	vma = find_vma(walk->mm, addr);
-	if (vma)
-		hs = hstate_vma(vma);
 	for (; addr != end; addr += PAGE_SIZE) {
-		u64 pfn = PM_NOT_PRESENT;
-
-		if (vma && (addr >= vma->vm_end)) {
-			vma = find_vma(walk->mm, addr);
-			if (vma)
-				hs = hstate_vma(vma);
-		}
-
-		if (vma && (vma->vm_start <= addr) && is_vm_hugetlb_page(vma)) {
-			/* calculate pfn of the "raw" page in the hugepage. */
-			int offset = (addr & ~huge_page_mask(hs)) >> PAGE_SHIFT;
-			pfn = huge_pte_to_pagemap_entry(*pte, offset);
-		}
+		int offset = (addr & ~hmask) >> PAGE_SHIFT;
+		pfn = huge_pte_to_pagemap_entry(*pte, offset);
 		err = add_to_pagemap(addr, pfn, pm);
 		if (err)
 			return err;
-- 
cgit v1.2.3-18-g5258


From cc4fc29e59c386919a7674e203be7822dc968dc0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 6 Apr 2010 14:35:09 -0700
Subject: fs-cache: order the debugfs stats correctly

Order the debugfs statistics correctly.  The values displayed through a
seq_printf() statement should be in the same order as the names in the
format string.

In the 'Lookups' line, objects created ('crt=') and lookups timed out
('tmo=') have their values transposed.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fscache/stats.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 46435f3aae6..4765190d537 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -165,8 +165,8 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_object_lookups),
 		   atomic_read(&fscache_n_object_lookups_negative),
 		   atomic_read(&fscache_n_object_lookups_positive),
-		   atomic_read(&fscache_n_object_lookups_timed_out),
-		   atomic_read(&fscache_n_object_created));
+		   atomic_read(&fscache_n_object_created),
+		   atomic_read(&fscache_n_object_lookups_timed_out));
 
 	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
 		   atomic_read(&fscache_n_updates),
-- 
cgit v1.2.3-18-g5258


From 04287f975e68038051eb9c79896866d36610b8e0 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@ZenIV.linux.org.uk>
Date: Thu, 8 Apr 2010 00:06:07 +0100
Subject: Have nfs ->d_revalidate() report errors properly

	If nfs atomic open implementation ends up doing open request from
->d_revalidate() codepath and gets an error from server, return that error
to caller explicitly and don't bother with lookup_instantiate_filp() at all.
->d_revalidate() can return an error itself just fine...

See
	http://bugzilla.kernel.org/show_bug.cgi?id=15674
	http://marc.info/?l=linux-kernel&m=126988782722711&w=2

for original report.

Reported-by: Daniel J Blueman <daniel.blueman@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/nfs/nfs4proc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d79a7b37e56..fe0cd9eb1d4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2068,8 +2068,7 @@ nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, st
 			case -EDQUOT:
 			case -ENOSPC:
 			case -EROFS:
-				lookup_instantiate_filp(nd, (struct dentry *)state, NULL);
-				return 1;
+				return PTR_ERR(state);
 			default:
 				goto out_drop;
 		}
-- 
cgit v1.2.3-18-g5258


From 69ecbbedac8e353bbd924fad16fed0c7c54e6382 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Mon, 15 Mar 2010 11:21:13 +0300
Subject: udf: potential integer overflow

bloc->logicalBlockNum is unsigned so it's never less than zero.

When I saw that, it made me worry that "bloc->logicalBlockNum + count"
could overflow.  That's why I changed the check for less than zero
to an overflow check.  (The test works because "count" is also
unsigned.)

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/udf/balloc.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 19626e2491c..9a9378b4eb5 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -125,9 +125,8 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
 
 	mutex_lock(&sbi->s_alloc_mutex);
 	partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
-	if (bloc->logicalBlockNum < 0 ||
-	    (bloc->logicalBlockNum + count) >
-		partmap->s_partition_len) {
+	if (bloc->logicalBlockNum + count < count ||
+	    (bloc->logicalBlockNum + count) > partmap->s_partition_len) {
 		udf_debug("%d < %d || %d + %d > %d\n",
 			  bloc->logicalBlockNum, 0, bloc->logicalBlockNum,
 			  count, partmap->s_partition_len);
@@ -393,9 +392,8 @@ static void udf_table_free_blocks(struct super_block *sb,
 
 	mutex_lock(&sbi->s_alloc_mutex);
 	partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
-	if (bloc->logicalBlockNum < 0 ||
-	    (bloc->logicalBlockNum + count) >
-		partmap->s_partition_len) {
+	if (bloc->logicalBlockNum + count < count ||
+	    (bloc->logicalBlockNum + count) > partmap->s_partition_len) {
 		udf_debug("%d < %d || %d + %d > %d\n",
 			  bloc->logicalBlockNum, 0, bloc->logicalBlockNum, count,
 			  partmap->s_partition_len);
-- 
cgit v1.2.3-18-g5258


From c15d0fc0fc399d2639240b35ad7ed93ed5a59412 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Mon, 29 Mar 2010 11:05:21 +0400
Subject: udf: add speciffic ->setattr callback

generic setattr not longer responsible for quota transfer.
use udf_setattr for all udf's inodes.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/udf/file.c    | 2 +-
 fs/udf/inode.c   | 2 +-
 fs/udf/namei.c   | 9 ++++++++-
 fs/udf/udfdecl.h | 3 ++-
 4 files changed, 12 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/udf/file.c b/fs/udf/file.c
index 1eb06774ed9..4b6a46ccbf4 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -218,7 +218,7 @@ const struct file_operations udf_file_operations = {
 	.llseek			= generic_file_llseek,
 };
 
-static int udf_setattr(struct dentry *dentry, struct iattr *iattr)
+int udf_setattr(struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = dentry->d_inode;
 	int error;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index bb863fe579a..8a3fbd177ca 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1314,7 +1314,7 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
 		break;
 	case ICBTAG_FILE_TYPE_SYMLINK:
 		inode->i_data.a_ops = &udf_symlink_aops;
-		inode->i_op = &page_symlink_inode_operations;
+		inode->i_op = &udf_symlink_inode_operations;
 		inode->i_mode = S_IFLNK | S_IRWXUGO;
 		break;
 	case ICBTAG_FILE_TYPE_MAIN:
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index db423ab078b..75816025f95 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -925,7 +925,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 	iinfo = UDF_I(inode);
 	inode->i_mode = S_IFLNK | S_IRWXUGO;
 	inode->i_data.a_ops = &udf_symlink_aops;
-	inode->i_op = &page_symlink_inode_operations;
+	inode->i_op = &udf_symlink_inode_operations;
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
 		struct kernel_lb_addr eloc;
@@ -1393,6 +1393,7 @@ const struct export_operations udf_export_ops = {
 const struct inode_operations udf_dir_inode_operations = {
 	.lookup				= udf_lookup,
 	.create				= udf_create,
+	.setattr			= udf_setattr,
 	.link				= udf_link,
 	.unlink				= udf_unlink,
 	.symlink			= udf_symlink,
@@ -1401,3 +1402,9 @@ const struct inode_operations udf_dir_inode_operations = {
 	.mknod				= udf_mknod,
 	.rename				= udf_rename,
 };
+const struct inode_operations udf_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+	.setattr	= udf_setattr,
+};
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 4223ac855da..702a1148e70 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -76,6 +76,7 @@ extern const struct inode_operations udf_dir_inode_operations;
 extern const struct file_operations udf_dir_operations;
 extern const struct inode_operations udf_file_inode_operations;
 extern const struct file_operations udf_file_operations;
+extern const struct inode_operations udf_symlink_inode_operations;
 extern const struct address_space_operations udf_aops;
 extern const struct address_space_operations udf_adinicb_aops;
 extern const struct address_space_operations udf_symlink_aops;
@@ -131,7 +132,7 @@ extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
 /* file.c */
 extern int udf_ioctl(struct inode *, struct file *, unsigned int,
 		     unsigned long);
-
+extern int udf_setattr(struct dentry *dentry, struct iattr *iattr);
 /* inode.c */
 extern struct inode *udf_iget(struct super_block *, struct kernel_lb_addr *);
 extern int udf_sync_inode(struct inode *);
-- 
cgit v1.2.3-18-g5258


From 2844a76a25a2fc2f5025cf128c95a14d86146d33 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Fri, 9 Apr 2010 15:46:42 -0700
Subject: ceph: decode v5 of osdmap (pool names) [protocol change]

Teach the client to decode an updated format for the osdmap.  The new
format includes pool names, which will be useful shortly.  Get this change
in earlier rather than later.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/osdmap.c | 180 +++++++++++++++++++++++++++++++++----------------------
 fs/ceph/osdmap.h |   1 +
 fs/ceph/rados.h  |   6 +-
 3 files changed, 114 insertions(+), 73 deletions(-)

(limited to 'fs')

diff --git a/fs/ceph/osdmap.c b/fs/ceph/osdmap.c
index d82fe87c2a6..7526d6d3301 100644
--- a/fs/ceph/osdmap.c
+++ b/fs/ceph/osdmap.c
@@ -312,71 +312,6 @@ bad:
 	return ERR_PTR(err);
 }
 
-
-/*
- * osd map
- */
-void ceph_osdmap_destroy(struct ceph_osdmap *map)
-{
-	dout("osdmap_destroy %p\n", map);
-	if (map->crush)
-		crush_destroy(map->crush);
-	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
-		struct ceph_pg_mapping *pg =
-			rb_entry(rb_first(&map->pg_temp),
-				 struct ceph_pg_mapping, node);
-		rb_erase(&pg->node, &map->pg_temp);
-		kfree(pg);
-	}
-	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
-		struct ceph_pg_pool_info *pi =
-			rb_entry(rb_first(&map->pg_pools),
-				 struct ceph_pg_pool_info, node);
-		rb_erase(&pi->node, &map->pg_pools);
-		kfree(pi);
-	}
-	kfree(map->osd_state);
-	kfree(map->osd_weight);
-	kfree(map->osd_addr);
-	kfree(map);
-}
-
-/*
- * adjust max osd value.  reallocate arrays.
- */
-static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
-{
-	u8 *state;
-	struct ceph_entity_addr *addr;
-	u32 *weight;
-
-	state = kcalloc(max, sizeof(*state), GFP_NOFS);
-	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
-	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
-	if (state == NULL || addr == NULL || weight == NULL) {
-		kfree(state);
-		kfree(addr);
-		kfree(weight);
-		return -ENOMEM;
-	}
-
-	/* copy old? */
-	if (map->osd_state) {
-		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
-		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
-		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
-		kfree(map->osd_state);
-		kfree(map->osd_addr);
-		kfree(map->osd_weight);
-	}
-
-	map->osd_state = state;
-	map->osd_weight = weight;
-	map->osd_addr = addr;
-	map->max_osd = max;
-	return 0;
-}
-
 /*
  * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid
  * to a set of osds)
@@ -480,6 +415,13 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
 	return NULL;
 }
 
+static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
+{
+	rb_erase(&pi->node, root);
+	kfree(pi->name);
+	kfree(pi);
+}
+
 void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 {
 	ceph_decode_copy(p, &pi->v, sizeof(pi->v));
@@ -488,6 +430,98 @@ void __decode_pool(void **p, struct ceph_pg_pool_info *pi)
 	*p += le32_to_cpu(pi->v.num_removed_snap_intervals) * sizeof(u64) * 2;
 }
 
+static int __decode_pool_names(void **p, void *end, struct ceph_osdmap *map)
+{
+	struct ceph_pg_pool_info *pi;
+	u32 num, len, pool;
+
+	ceph_decode_32_safe(p, end, num, bad);
+	dout(" %d pool names\n", num);
+	while (num--) {
+		ceph_decode_32_safe(p, end, pool, bad);
+		ceph_decode_32_safe(p, end, len, bad);
+		dout("  pool %d len %d\n", pool, len);
+		pi = __lookup_pg_pool(&map->pg_pools, pool);
+		if (pi) {
+			kfree(pi->name);
+			pi->name = kmalloc(len + 1, GFP_NOFS);
+			if (pi->name) {
+				memcpy(pi->name, *p, len);
+				pi->name[len] = '\0';
+				dout("  name is %s\n", pi->name);
+			}
+		}
+		*p += len;
+	}
+	return 0;
+
+bad:
+	return -EINVAL;
+}
+
+/*
+ * osd map
+ */
+void ceph_osdmap_destroy(struct ceph_osdmap *map)
+{
+	dout("osdmap_destroy %p\n", map);
+	if (map->crush)
+		crush_destroy(map->crush);
+	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
+		struct ceph_pg_mapping *pg =
+			rb_entry(rb_first(&map->pg_temp),
+				 struct ceph_pg_mapping, node);
+		rb_erase(&pg->node, &map->pg_temp);
+		kfree(pg);
+	}
+	while (!RB_EMPTY_ROOT(&map->pg_pools)) {
+		struct ceph_pg_pool_info *pi =
+			rb_entry(rb_first(&map->pg_pools),
+				 struct ceph_pg_pool_info, node);
+		__remove_pg_pool(&map->pg_pools, pi);
+	}
+	kfree(map->osd_state);
+	kfree(map->osd_weight);
+	kfree(map->osd_addr);
+	kfree(map);
+}
+
+/*
+ * adjust max osd value.  reallocate arrays.
+ */
+static int osdmap_set_max_osd(struct ceph_osdmap *map, int max)
+{
+	u8 *state;
+	struct ceph_entity_addr *addr;
+	u32 *weight;
+
+	state = kcalloc(max, sizeof(*state), GFP_NOFS);
+	addr = kcalloc(max, sizeof(*addr), GFP_NOFS);
+	weight = kcalloc(max, sizeof(*weight), GFP_NOFS);
+	if (state == NULL || addr == NULL || weight == NULL) {
+		kfree(state);
+		kfree(addr);
+		kfree(weight);
+		return -ENOMEM;
+	}
+
+	/* copy old? */
+	if (map->osd_state) {
+		memcpy(state, map->osd_state, map->max_osd*sizeof(*state));
+		memcpy(addr, map->osd_addr, map->max_osd*sizeof(*addr));
+		memcpy(weight, map->osd_weight, map->max_osd*sizeof(*weight));
+		kfree(map->osd_state);
+		kfree(map->osd_addr);
+		kfree(map->osd_weight);
+	}
+
+	map->osd_state = state;
+	map->osd_weight = weight;
+	map->osd_addr = addr;
+	map->max_osd = max;
+	return 0;
+}
+
 /*
  * decode a full map.
  */
@@ -524,7 +558,7 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 	ceph_decode_32_safe(p, end, max, bad);
 	while (max--) {
 		ceph_decode_need(p, end, 4 + 1 + sizeof(pi->v), bad);
-		pi = kmalloc(sizeof(*pi), GFP_NOFS);
+		pi = kzalloc(sizeof(*pi), GFP_NOFS);
 		if (!pi)
 			goto bad;
 		pi->id = ceph_decode_32(p);
@@ -537,6 +571,10 @@ struct ceph_osdmap *osdmap_decode(void **p, void *end)
 		__decode_pool(p, pi);
 		__insert_pg_pool(&map->pg_pools, pi);
 	}
+
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
+
 	ceph_decode_32_safe(p, end, map->pool_max, bad);
 
 	ceph_decode_32_safe(p, end, map->flags, bad);
@@ -710,7 +748,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		}
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
 		if (!pi) {
-			pi = kmalloc(sizeof(*pi), GFP_NOFS);
+			pi = kzalloc(sizeof(*pi), GFP_NOFS);
 			if (!pi) {
 				err = -ENOMEM;
 				goto bad;
@@ -720,6 +758,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		}
 		__decode_pool(p, pi);
 	}
+	if (version >= 5 && __decode_pool_names(p, end, map) < 0)
+		goto bad;
 
 	/* old_pool */
 	ceph_decode_32_safe(p, end, len, bad);
@@ -728,10 +768,8 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 
 		ceph_decode_32_safe(p, end, pool, bad);
 		pi = __lookup_pg_pool(&map->pg_pools, pool);
-		if (pi) {
-			rb_erase(&pi->node, &map->pg_pools);
-			kfree(pi);
-		}
+		if (pi)
+			__remove_pg_pool(&map->pg_pools, pi);
 	}
 
 	/* new_up */
diff --git a/fs/ceph/osdmap.h b/fs/ceph/osdmap.h
index 1fb55afb264..8bc9f1e4f56 100644
--- a/fs/ceph/osdmap.h
+++ b/fs/ceph/osdmap.h
@@ -23,6 +23,7 @@ struct ceph_pg_pool_info {
 	int id;
 	struct ceph_pg_pool v;
 	int pg_num_mask, pgp_num_mask, lpg_num_mask, lpgp_num_mask;
+	char *name;
 };
 
 struct ceph_pg_mapping {
diff --git a/fs/ceph/rados.h b/fs/ceph/rados.h
index 26ac8b89a67..a1fc1d017b5 100644
--- a/fs/ceph/rados.h
+++ b/fs/ceph/rados.h
@@ -11,8 +11,10 @@
 /*
  * osdmap encoding versions
  */
-#define CEPH_OSDMAP_INC_VERSION 4
-#define CEPH_OSDMAP_VERSION     4
+#define CEPH_OSDMAP_INC_VERSION     5
+#define CEPH_OSDMAP_INC_VERSION_EXT 5
+#define CEPH_OSDMAP_VERSION         5
+#define CEPH_OSDMAP_VERSION_EXT     5
 
 /*
  * fs id
-- 
cgit v1.2.3-18-g5258


From 80e60639f1b7c121a7fea53920c5a4b94009361a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Thu, 25 Mar 2010 13:51:05 -0400
Subject: NFSv4: Fall back to ordinary lookup if nfs4_atomic_open() returns
 EISDIR

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@kernel.org
---
 fs/nfs/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c6f2750648f..be46f26c9a5 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1025,12 +1025,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 				res = NULL;
 				goto out;
 			/* This turned out not to be a regular file */
+			case -EISDIR:
 			case -ENOTDIR:
 				goto no_open;
 			case -ELOOP:
 				if (!(nd->intent.open.flags & O_NOFOLLOW))
 					goto no_open;
-			/* case -EISDIR: */
 			/* case -EINVAL: */
 			default:
 				goto out;
-- 
cgit v1.2.3-18-g5258


From 1544fa0f7a46241582abc48f07b74f3d846379e4 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Thu, 25 Mar 2010 13:54:49 -0400
Subject: NFS: Fix the mode calculation in nfs_find_open_context

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/inode.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 737128f777f..50a56edca0b 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -623,10 +623,10 @@ struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_c
 	list_for_each_entry(pos, &nfsi->open_files, list) {
 		if (cred != NULL && pos->cred != cred)
 			continue;
-		if ((pos->mode & mode) == mode) {
-			ctx = get_nfs_open_context(pos);
-			break;
-		}
+		if ((pos->mode & (FMODE_READ|FMODE_WRITE)) != mode)
+			continue;
+		ctx = get_nfs_open_context(pos);
+		break;
 	}
 	spin_unlock(&inode->i_lock);
 	return ctx;
-- 
cgit v1.2.3-18-g5258


From b80c3cb628f0ebc241b02e38dd028969fb8026a2 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Fri, 9 Apr 2010 19:07:07 -0400
Subject: NFS: Ensure that writeback_single_inode() calls write_inode() when
 syncing

Since writeback_single_inode() checks the inode->i_state flags _before_ it
flushes out the data, we need to ensure that the I_DIRTY_DATASYNC flag is
already set. Otherwise we risk not seeing a call to write_inode(), which
again means that we break fsync() et al...

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/write.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 53ff70e2399..7f40ea30554 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -421,6 +421,7 @@ static void
 nfs_mark_request_dirty(struct nfs_page *req)
 {
 	__set_page_dirty_nobuffers(req->wb_page);
+	__mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
 }
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
@@ -660,6 +661,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 	req = nfs_setup_write_request(ctx, page, offset, count);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
+	nfs_mark_request_dirty(req);
 	/* Update file length */
 	nfs_grow_file(page, offset, count);
 	nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
@@ -739,8 +741,6 @@ int nfs_updatepage(struct file *file, struct page *page,
 	status = nfs_writepage_setup(ctx, page, offset, count);
 	if (status < 0)
 		nfs_set_pageerror(page);
-	else
-		__set_page_dirty_nobuffers(page);
 
 	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
-- 
cgit v1.2.3-18-g5258


From a6305ddb080fb483ca41ca56cacb6f96089f0c8e Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Fri, 9 Apr 2010 19:07:08 -0400
Subject: NFS: Fix a race with the new commit code

This patch fixes a race which occurs due to the fact that we release the
PG_writeback flag while still holding the nfs_page locked.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/write.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 7f40ea30554..40297c4f1ee 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -201,6 +201,7 @@ static int nfs_set_page_writeback(struct page *page)
 		struct inode *inode = page->mapping->host;
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
+		page_cache_get(page);
 		if (atomic_long_inc_return(&nfss->writeback) >
 				NFS_CONGESTION_ON_THRESH) {
 			set_bdi_congested(&nfss->backing_dev_info,
@@ -216,6 +217,7 @@ static void nfs_end_page_writeback(struct page *page)
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
 	end_page_writeback(page);
+	page_cache_release(page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
 		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
@@ -665,6 +667,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 	/* Update file length */
 	nfs_grow_file(page, offset, count);
 	nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
+	nfs_mark_request_dirty(req);
 	nfs_clear_page_tag_locked(req);
 	return 0;
 }
@@ -749,13 +752,12 @@ int nfs_updatepage(struct file *file, struct page *page,
 
 static void nfs_writepage_release(struct nfs_page *req)
 {
+	struct page *page = req->wb_page;
 
-	if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) {
-		nfs_end_page_writeback(req->wb_page);
+	if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req))
 		nfs_inode_remove_request(req);
-	} else
-		nfs_end_page_writeback(req->wb_page);
 	nfs_clear_page_tag_locked(req);
+	nfs_end_page_writeback(page);
 }
 
 static int flush_task_priority(int how)
@@ -847,9 +849,11 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
  */
 static void nfs_redirty_request(struct nfs_page *req)
 {
+	struct page *page = req->wb_page;
+
 	nfs_mark_request_dirty(req);
-	nfs_end_page_writeback(req->wb_page);
 	nfs_clear_page_tag_locked(req);
+	nfs_end_page_writeback(page);
 }
 
 /*
@@ -1084,16 +1088,15 @@ static void nfs_writeback_release_full(void *calldata)
 		if (nfs_write_need_commit(data)) {
 			memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
 			nfs_mark_request_commit(req);
-			nfs_end_page_writeback(page);
 			dprintk(" marked for commit\n");
 			goto next;
 		}
 		dprintk(" OK\n");
 remove_request:
-		nfs_end_page_writeback(page);
 		nfs_inode_remove_request(req);
 	next:
 		nfs_clear_page_tag_locked(req);
+		nfs_end_page_writeback(page);
 	}
 	nfs_writedata_release(calldata);
 }
-- 
cgit v1.2.3-18-g5258


From 2c61be0a9478258f77b66208a0c4b1f5f8161c3c Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Fri, 9 Apr 2010 19:54:50 -0400
Subject: NFS: Ensure that the WRITE and COMMIT RPC calls are always
 uninterruptible

We always want to ensure that WRITE and COMMIT completes, whether or not
the user presses ^C. Do this by making the call asynchronous, and allowing
the user to do an interruptible wait for rpc_task completion.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/write.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 40297c4f1ee..de38d63aa92 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -781,7 +781,6 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 		int how)
 {
 	struct inode *inode = req->wb_context->path.dentry->d_inode;
-	int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
 	int priority = flush_task_priority(how);
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -796,9 +795,10 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 		.callback_ops = call_ops,
 		.callback_data = data,
 		.workqueue = nfsiod_workqueue,
-		.flags = flags,
+		.flags = RPC_TASK_ASYNC,
 		.priority = priority,
 	};
+	int ret = 0;
 
 	/* Set up the RPC argument and reply structs
 	 * NB: take care not to mess about with data->commit et al. */
@@ -837,10 +837,18 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 		(unsigned long long)data->args.offset);
 
 	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task))
-		return PTR_ERR(task);
+	if (IS_ERR(task)) {
+		ret = PTR_ERR(task);
+		goto out;
+	}
+	if (how & FLUSH_SYNC) {
+		ret = rpc_wait_for_completion_task(task);
+		if (ret == 0)
+			ret = task->tk_status;
+	}
 	rpc_put_task(task);
-	return 0;
+out:
+	return ret;
 }
 
 /* If a nfs_flush_* function fails, it should remove reqs from @head and
@@ -1210,7 +1218,6 @@ static int nfs_commit_rpcsetup(struct list_head *head,
 {
 	struct nfs_page *first = nfs_list_entry(head->next);
 	struct inode *inode = first->wb_context->path.dentry->d_inode;
-	int flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
 	int priority = flush_task_priority(how);
 	struct rpc_task *task;
 	struct rpc_message msg = {
@@ -1225,7 +1232,7 @@ static int nfs_commit_rpcsetup(struct list_head *head,
 		.callback_ops = &nfs_commit_ops,
 		.callback_data = data,
 		.workqueue = nfsiod_workqueue,
-		.flags = flags,
+		.flags = RPC_TASK_ASYNC,
 		.priority = priority,
 	};
 
@@ -1255,6 +1262,8 @@ static int nfs_commit_rpcsetup(struct list_head *head,
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
+	if (how & FLUSH_SYNC)
+		rpc_wait_for_completion_task(task);
 	rpc_put_task(task);
 	return 0;
 }
-- 
cgit v1.2.3-18-g5258


From be3bd2223b89d270853302ab0a5909fa875fd831 Mon Sep 17 00:00:00 2001
From: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Date: Mon, 12 Apr 2010 01:51:03 +0900
Subject: nilfs2: fix typo "numer" -> "number" in alloc.c

Fixes the typo found in a warning message of a persistent object
allocator function.

Signed-off-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
---
 fs/nilfs2/alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 3f959f1879d..c2a13870c60 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -425,7 +425,7 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
 	bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
 	if (!nilfs_clear_bit_atomic(nilfs_mdt_bgl_lock(inode, group),
 				    group_offset, bitmap))
-		printk(KERN_WARNING "%s: entry numer %llu already freed\n",
+		printk(KERN_WARNING "%s: entry number %llu already freed\n",
 		       __func__, (unsigned long long)req->pr_entry_nr);
 
 	nilfs_palloc_group_desc_add_entries(inode, group, desc, 1);
-- 
cgit v1.2.3-18-g5258


From 0df5dd4aae211edeeeb84f7f84f6d093406d7c22 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Sun, 11 Apr 2010 16:48:44 -0400
Subject: NFSv4: fix delegated locking

Arnaud Giersch reports that NFSv4 locking is broken when we hold a
delegation since commit 8e469ebd6dc32cbaf620e134d79f740bf0ebab79 (NFSv4:
Don't allow posix locking against servers that don't support it).

According to Arnaud, the lock succeeds the first time he opens the file
(since we cannot do a delegated open) but then fails after we start using
delegated opens.

The following patch fixes it by ensuring that locking behaviour is
governed by a per-filesystem capability flag that is initially set, but
gets cleared if the server ever returns an OPEN without the
NFS4_OPEN_RESULT_LOCKTYPE_POSIX flag being set.

Reported-by: Arnaud Giersch <arnaud.giersch@iut-bm.univ-fcomte.fr>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: stable@kernel.org
---
 fs/nfs/client.c   | 3 ++-
 fs/nfs/nfs4proc.c | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2a3d352c0bf..a8766c4ef2e 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1294,7 +1294,8 @@ static int nfs4_init_server(struct nfs_server *server,
 
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
-	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|
+		NFS_CAP_POSIX_LOCK;
 	server->options = data->options;
 
 	/* Get a client record */
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index fe0cd9eb1d4..638067007c6 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1523,6 +1523,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 		nfs_post_op_update_inode(dir, o_res->dir_attr);
 	} else
 		nfs_refresh_inode(dir, o_res->dir_attr);
+	if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
+		server->caps &= ~NFS_CAP_POSIX_LOCK;
 	if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
 		status = _nfs4_proc_open_confirm(data);
 		if (status != 0)
@@ -1664,7 +1666,7 @@ static int _nfs4_do_open(struct inode *dir, struct path *path, fmode_t fmode, in
 	status = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto err_opendata_put;
-	if ((opendata->o_res.rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) != 0)
+	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 	nfs4_opendata_put(opendata);
 	nfs4_put_state_owner(sp);
-- 
cgit v1.2.3-18-g5258


From fc7683a3c30c22131b1651271d6bf9ea113b77c5 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Fri, 26 Mar 2010 19:29:54 +0300
Subject: ext2: symlink must be handled via filesystem specific operation

generic setattr implementation is no longer responsible for
quota transfer so synlinks must be handled via ext2_setattr.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext2/symlink.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'fs')

diff --git a/fs/ext2/symlink.c b/fs/ext2/symlink.c
index 4e2426e22bb..565cf817bbf 100644
--- a/fs/ext2/symlink.c
+++ b/fs/ext2/symlink.c
@@ -32,6 +32,7 @@ const struct inode_operations ext2_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
+	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -43,6 +44,7 @@ const struct inode_operations ext2_symlink_inode_operations = {
 const struct inode_operations ext2_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= ext2_follow_link,
+	.setattr	= ext2_setattr,
 #ifdef CONFIG_EXT2_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
-- 
cgit v1.2.3-18-g5258


From 774f03fb2cf89951b5f5f363b7739a2835d5924e Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Fri, 26 Mar 2010 19:29:55 +0300
Subject: ext3: symlink must be handled via filesystem specific operation

generic setattr implementation is no longer responsible for
quota transfer so synlinks must be handled via ext3_setattr.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ext3/symlink.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'fs')

diff --git a/fs/ext3/symlink.c b/fs/ext3/symlink.c
index ff7b4ccd898..7c489820777 100644
--- a/fs/ext3/symlink.c
+++ b/fs/ext3/symlink.c
@@ -34,6 +34,7 @@ const struct inode_operations ext3_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= page_follow_link_light,
 	.put_link	= page_put_link,
+	.setattr	= ext3_setattr,
 #ifdef CONFIG_EXT3_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
@@ -45,6 +46,7 @@ const struct inode_operations ext3_symlink_inode_operations = {
 const struct inode_operations ext3_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= ext3_follow_link,
+	.setattr	= ext3_setattr,
 #ifdef CONFIG_EXT3_FS_XATTR
 	.setxattr	= generic_setxattr,
 	.getxattr	= generic_getxattr,
-- 
cgit v1.2.3-18-g5258


From 4c5e6c0e70fd6ca2fa67184fd36a261b3b7b38d0 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Tue, 6 Apr 2010 18:52:47 +0200
Subject: quota: Hide warnings about writes to the filesystem before quota was
 turned on

For a root filesystem write to the filesystem before quota is turned on happens
regularly and there's no way around it because of writes to syslog, /etc/mtab,
and similar. So the warning is rather pointless for ordinary users. It's
still useful during development so we just hide the warning behind
__DQUOT_PARANOIA config option.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/dquot.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'fs')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index e0b870f4749..f9a37513f24 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -874,14 +874,18 @@ static int dqinit_needed(struct inode *inode, int type)
 static void add_dquot_ref(struct super_block *sb, int type)
 {
 	struct inode *inode, *old_inode = NULL;
+#ifdef __DQUOT_PARANOIA
 	int reserved = 0;
+#endif
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
 			continue;
+#ifdef __DQUOT_PARANOIA
 		if (unlikely(inode_get_rsv_space(inode) > 0))
 			reserved = 1;
+#endif
 		if (!atomic_read(&inode->i_writecount))
 			continue;
 		if (!dqinit_needed(inode, type))
@@ -903,11 +907,13 @@ static void add_dquot_ref(struct super_block *sb, int type)
 	spin_unlock(&inode_lock);
 	iput(old_inode);
 
+#ifdef __DQUOT_PARANOIA
 	if (reserved) {
 		printk(KERN_WARNING "VFS (%s): Writes happened before quota"
 			" was turned on thus quota information is probably "
 			"inconsistent. Please run quotacheck(8).\n", sb->s_id);
 	}
+#endif
 }
 
 /*
-- 
cgit v1.2.3-18-g5258


From 08261673cb6dc638c39f44d69b76fffb57b92a8b Mon Sep 17 00:00:00 2001
From: Andrew Perepechko <andrew.perepechko@sun.com>
Date: Mon, 12 Apr 2010 22:16:50 +0400
Subject: quota: Fix possible dq_flags corruption

dq_flags are modified non-atomically in do_set_dqblk via __set_bit calls and
atomically for example in mark_dquot_dirty or clear_dquot_dirty.  Hence a
change done by an atomic operation can be overwritten by a change done by a
non-atomic one. Fix the problem by using atomic bitops even in do_set_dqblk.

Signed-off-by: Andrew Perepechko <andrew.perepechko@sun.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/dquot.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index f9a37513f24..a0a9405b202 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2328,34 +2328,34 @@ static int do_set_dqblk(struct dquot *dquot, struct if_dqblk *di)
 	if (di->dqb_valid & QIF_SPACE) {
 		dm->dqb_curspace = di->dqb_curspace - dm->dqb_rsvspace;
 		check_blim = 1;
-		__set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
+		set_bit(DQ_LASTSET_B + QIF_SPACE_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_BLIMITS) {
 		dm->dqb_bsoftlimit = qbtos(di->dqb_bsoftlimit);
 		dm->dqb_bhardlimit = qbtos(di->dqb_bhardlimit);
 		check_blim = 1;
-		__set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
+		set_bit(DQ_LASTSET_B + QIF_BLIMITS_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_INODES) {
 		dm->dqb_curinodes = di->dqb_curinodes;
 		check_ilim = 1;
-		__set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
+		set_bit(DQ_LASTSET_B + QIF_INODES_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_ILIMITS) {
 		dm->dqb_isoftlimit = di->dqb_isoftlimit;
 		dm->dqb_ihardlimit = di->dqb_ihardlimit;
 		check_ilim = 1;
-		__set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
+		set_bit(DQ_LASTSET_B + QIF_ILIMITS_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_BTIME) {
 		dm->dqb_btime = di->dqb_btime;
 		check_blim = 1;
-		__set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
+		set_bit(DQ_LASTSET_B + QIF_BTIME_B, &dquot->dq_flags);
 	}
 	if (di->dqb_valid & QIF_ITIME) {
 		dm->dqb_itime = di->dqb_itime;
 		check_ilim = 1;
-		__set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
+		set_bit(DQ_LASTSET_B + QIF_ITIME_B, &dquot->dq_flags);
 	}
 
 	if (check_blim) {
-- 
cgit v1.2.3-18-g5258


From f5b066287c74b624583b993395a65d03a6487b3a Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Mon, 12 Apr 2010 14:24:28 -0700
Subject: ceph: fix dentry reference leak in dcache readdir

When filldir returned an error (e.g. buffer full for a large directory),
we would leak a dentry reference, causing an oops on umount.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/dir.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index aed8fda3302..7505b4f1f59 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -170,11 +170,11 @@ more:
 	spin_lock(&inode->i_lock);
 	spin_lock(&dcache_lock);
 
+	last = dentry;
+
 	if (err < 0)
 		goto out_unlock;
 
-	last = dentry;
-
 	p = p->prev;
 	filp->f_pos++;
 
-- 
cgit v1.2.3-18-g5258


From 032d8f7268444a0f5d4ee02d9513d682d5b8edfc Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Tue, 13 Apr 2010 17:46:37 +0200
Subject: [LogFS] Prevent memory corruption on large deletes

Removing sufficiently large files would create aliases for a large
number of segments.  This in turn results in a large number of journal
entries and an overflow of s_je_array.

Cheap fix is to add a BUG_ON, turning memory corruption into something
annoying, but less dangerous.  Real fix is to count the number of
affected segments and prevent the problem completely.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/gc.c        |  8 ++++++++
 fs/logfs/journal.c   |  3 +++
 fs/logfs/logfs.h     |  8 +++++++-
 fs/logfs/readwrite.c | 14 ++++++++++++++
 fs/logfs/super.c     |  2 ++
 5 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/logfs/gc.c b/fs/logfs/gc.c
index 92949f95a90..e8253e7fb6b 100644
--- a/fs/logfs/gc.c
+++ b/fs/logfs/gc.c
@@ -458,6 +458,14 @@ static void __logfs_gc_pass(struct super_block *sb, int target)
 	struct logfs_block *block;
 	int round, progress, last_progress = 0;
 
+	/*
+	 * Doing too many changes to the segfile at once would result
+	 * in a large number of aliases.  Write the journal before
+	 * things get out of hand.
+	 */
+	if (super->s_shadow_tree.no_shadowed_segments >= MAX_OBJ_ALIASES)
+		logfs_write_anchor(sb);
+
 	if (no_free_segments(sb) >= target &&
 			super->s_no_object_aliases < MAX_OBJ_ALIASES)
 		return;
diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index d57c7b07b60..2c22a4ad532 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -493,6 +493,8 @@ static void account_shadows(struct super_block *sb)
 
 	btree_grim_visitor64(&tree->new, (unsigned long)sb, account_shadow);
 	btree_grim_visitor64(&tree->old, (unsigned long)sb, account_shadow);
+	btree_grim_visitor32(&tree->segment_map, 0, NULL);
+	tree->no_shadowed_segments = 0;
 
 	if (li->li_block) {
 		/*
@@ -660,6 +662,7 @@ static int logfs_write_je_buf(struct super_block *sb, void *buf, u16 type,
 	if (ofs < 0)
 		return ofs;
 	logfs_buf_write(area, ofs, super->s_compressed_je, len);
+	BUG_ON(super->s_no_je >= MAX_JOURNAL_ENTRIES);
 	super->s_je_array[super->s_no_je++] = cpu_to_be64(ofs);
 	return 0;
 }
diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index 97195b9e93a..c9929eed80b 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -257,10 +257,14 @@ struct logfs_shadow {
  * struct shadow_tree
  * @new:			shadows where old_ofs==0, indexed by new_ofs
  * @old:			shadows where old_ofs!=0, indexed by old_ofs
+ * @segment_map:		bitfield of segments containing shadows
+ * @no_shadowed_segment:	number of segments containing shadows
  */
 struct shadow_tree {
 	struct btree_head64 new;
 	struct btree_head64 old;
+	struct btree_head32 segment_map;
+	int no_shadowed_segments;
 };
 
 struct object_alias_item {
@@ -311,6 +315,8 @@ struct logfs_block_ops {
 			write_alias_t *write_one_alias);
 };
 
+#define MAX_JOURNAL_ENTRIES 256
+
 struct logfs_super {
 	struct mtd_info *s_mtd;			/* underlying device */
 	struct block_device *s_bdev;		/* underlying device */
@@ -377,7 +383,7 @@ struct logfs_super {
 	u32	 s_journal_ec[LOGFS_JOURNAL_SEGS]; /* journal erasecounts */
 	u64	 s_last_version;
 	struct logfs_area *s_journal_area;	/* open journal segment */
-	__be64	s_je_array[64];
+	__be64	s_je_array[MAX_JOURNAL_ENTRIES];
 	int	s_no_je;
 
 	int	 s_sum_index;			/* for the 12 summaries */
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 3659c37fbd7..7e0c39c4971 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -1219,6 +1219,18 @@ static void free_shadow(struct inode *inode, struct logfs_shadow *shadow)
 	mempool_free(shadow, super->s_shadow_pool);
 }
 
+static void mark_segment(struct shadow_tree *tree, u32 segno)
+{
+	int err;
+
+	if (!btree_lookup32(&tree->segment_map, segno)) {
+		err = btree_insert32(&tree->segment_map, segno, (void *)1,
+				GFP_NOFS);
+		BUG_ON(err);
+		tree->no_shadowed_segments++;
+	}
+}
+
 /**
  * fill_shadow_tree - Propagate shadow tree changes due to a write
  * @inode:	Inode owning the page
@@ -1266,6 +1278,8 @@ static void fill_shadow_tree(struct inode *inode, struct page *page,
 
 		super->s_dirty_used_bytes += shadow->new_len;
 		super->s_dirty_free_bytes += shadow->old_len;
+		mark_segment(tree, shadow->old_ofs >> super->s_segshift);
+		mark_segment(tree, shadow->new_ofs >> super->s_segshift);
 	}
 }
 
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 9d856c49afc..d6e1f4fc311 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -451,6 +451,8 @@ static int logfs_read_sb(struct super_block *sb, int read_only)
 
 	btree_init_mempool64(&super->s_shadow_tree.new, super->s_btree_pool);
 	btree_init_mempool64(&super->s_shadow_tree.old, super->s_btree_pool);
+	btree_init_mempool32(&super->s_shadow_tree.segment_map,
+			super->s_btree_pool);
 
 	ret = logfs_init_mapping(sb);
 	if (ret)
-- 
cgit v1.2.3-18-g5258


From d3a03f8031000f8297823b80e36db536fd020884 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Tue, 13 Apr 2010 17:54:27 +0200
Subject: [LogFS] Plug 8 byte information leak

Within each journal segment, 8 bytes at offset 24 would remain
uninitialized.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/journal.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 2c22a4ad532..2957bfc2192 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -388,7 +388,10 @@ static void journal_get_erase_count(struct logfs_area *area)
 static int journal_erase_segment(struct logfs_area *area)
 {
 	struct super_block *sb = area->a_sb;
-	struct logfs_segment_header sh;
+	union {
+		struct logfs_segment_header sh;
+		unsigned char c[ALIGN(sizeof(struct logfs_segment_header), 16)];
+	} u;
 	u64 ofs;
 	int err;
 
@@ -396,20 +399,21 @@ static int journal_erase_segment(struct logfs_area *area)
 	if (err)
 		return err;
 
-	sh.pad = 0;
-	sh.type = SEG_JOURNAL;
-	sh.level = 0;
-	sh.segno = cpu_to_be32(area->a_segno);
-	sh.ec = cpu_to_be32(area->a_erase_count);
-	sh.gec = cpu_to_be64(logfs_super(sb)->s_gec);
-	sh.crc = logfs_crc32(&sh, sizeof(sh), 4);
+	memset(&u, 0, sizeof(u));
+	u.sh.pad = 0;
+	u.sh.type = SEG_JOURNAL;
+	u.sh.level = 0;
+	u.sh.segno = cpu_to_be32(area->a_segno);
+	u.sh.ec = cpu_to_be32(area->a_erase_count);
+	u.sh.gec = cpu_to_be64(logfs_super(sb)->s_gec);
+	u.sh.crc = logfs_crc32(&u.sh, sizeof(u.sh), 4);
 
 	/* This causes a bug in segment.c.  Not yet. */
 	//logfs_set_segment_erased(sb, area->a_segno, area->a_erase_count, 0);
 
 	ofs = dev_ofs(sb, area->a_segno, 0);
-	area->a_used_bytes = ALIGN(sizeof(sh), 16);
-	logfs_buf_write(area, ofs, &sh, sizeof(sh));
+	area->a_used_bytes = sizeof(u);
+	logfs_buf_write(area, ofs, &u, sizeof(u));
 	return 0;
 }
 
-- 
cgit v1.2.3-18-g5258


From ead88af5f577fd2b399a0fcdfe52605116fac489 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Tue, 13 Apr 2010 17:57:21 +0200
Subject: [LogFS] Move assertion

The assertion is valid independently of the condition.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/journal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c
index 2957bfc2192..fd44eeea513 100644
--- a/fs/logfs/journal.c
+++ b/fs/logfs/journal.c
@@ -612,9 +612,9 @@ static size_t __logfs_write_je(struct super_block *sb, void *buf, u16 type,
 	if (len == 0)
 		return logfs_write_header(super, header, 0, type);
 
+	BUG_ON(len > sb->s_blocksize);
 	compr_len = logfs_compress(buf, data, len, sb->s_blocksize);
 	if (compr_len < 0 || type == JE_ANCHOR) {
-		BUG_ON(len > sb->s_blocksize);
 		memcpy(data, buf, len);
 		compr_len = len;
 		compr = COMPR_NONE;
-- 
cgit v1.2.3-18-g5258


From fc837c8f0446b73a1661339db406c0238dd1d184 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Tue, 13 Apr 2010 11:41:22 -0700
Subject: ceph: queue_cap_snap should always queue dirty context

This simplifies the calling convention, and fixes a bug where we queue a
capsnap with a context other than i_head_snapc (the one that matches the
dirty pages).  The result was a BUG at fs/ceph/caps.c:2178 on writeback
completion when a capsnap matching the writeback snapc could not be found.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/snap.c  | 16 +++++++---------
 fs/ceph/super.h |  3 +--
 2 files changed, 8 insertions(+), 11 deletions(-)

(limited to 'fs')

diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 7e3e5f9edaa..d197431532c 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -430,8 +430,7 @@ static int dup_array(u64 **dst, __le64 *src, int num)
  * Caller must hold snap_rwsem for read (i.e., the realm topology won't
  * change).
  */
-void ceph_queue_cap_snap(struct ceph_inode_info *ci,
-			 struct ceph_snap_context *snapc)
+void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap_snap *capsnap;
@@ -450,10 +449,11 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		   as no new writes are allowed to start when pending, so any
 		   writes in progress now were started before the previous
 		   cap_snap.  lucky us. */
-		dout("queue_cap_snap %p snapc %p seq %llu used %d"
-		     " already pending\n", inode, snapc, snapc->seq, used);
+		dout("queue_cap_snap %p already pending\n", inode);
 		kfree(capsnap);
 	} else if (ci->i_wrbuffer_ref_head || (used & CEPH_CAP_FILE_WR)) {
+		struct ceph_snap_context *snapc = ci->i_head_snapc;
+
 		igrab(inode);
 
 		atomic_set(&capsnap->nref, 1);
@@ -462,7 +462,6 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		INIT_LIST_HEAD(&capsnap->flushing_item);
 
 		capsnap->follows = snapc->seq - 1;
-		capsnap->context = ceph_get_snap_context(snapc);
 		capsnap->issued = __ceph_caps_issued(ci, NULL);
 		capsnap->dirty = __ceph_caps_dirty(ci);
 
@@ -479,7 +478,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci,
 		   snapshot. */
 		capsnap->dirty_pages = ci->i_wrbuffer_ref_head;
 		ci->i_wrbuffer_ref_head = 0;
-		ceph_put_snap_context(ci->i_head_snapc);
+		capsnap->context = snapc;
 		ci->i_head_snapc = NULL;
 		list_add_tail(&capsnap->ci_item, &ci->i_cap_snaps);
 
@@ -603,7 +602,7 @@ more:
 				if (lastinode)
 					iput(lastinode);
 				lastinode = inode;
-				ceph_queue_cap_snap(ci, realm->cached_context);
+				ceph_queue_cap_snap(ci);
 				spin_lock(&realm->inodes_with_caps_lock);
 			}
 			spin_unlock(&realm->inodes_with_caps_lock);
@@ -825,8 +824,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			spin_unlock(&realm->inodes_with_caps_lock);
 			spin_unlock(&inode->i_lock);
 
-			ceph_queue_cap_snap(ci,
-					    ci->i_snap_realm->cached_context);
+			ceph_queue_cap_snap(ci);
 
 			iput(inode);
 			continue;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 65d12036b67..4c07acaf21e 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -714,8 +714,7 @@ extern int ceph_update_snap_trace(struct ceph_mds_client *m,
 extern void ceph_handle_snap(struct ceph_mds_client *mdsc,
 			     struct ceph_mds_session *session,
 			     struct ceph_msg *msg);
-extern void ceph_queue_cap_snap(struct ceph_inode_info *ci,
-				struct ceph_snap_context *snapc);
+extern void ceph_queue_cap_snap(struct ceph_inode_info *ci);
 extern int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
 				  struct ceph_cap_snap *capsnap);
 extern void ceph_cleanup_empty_realms(struct ceph_mds_client *mdsc);
-- 
cgit v1.2.3-18-g5258


From e1e4dd0caa63e166afa46a1ccc947bebb4f66bcf Mon Sep 17 00:00:00 2001
From: Yehuda Sadeh <yehuda@hq.newdream.net>
Date: Tue, 13 Apr 2010 11:45:56 -0700
Subject: ceph: reserve one more caps space when doing readdir

We were missing space for the directory cap.  The result was a BUG at
fs/ceph/caps.c:2178.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/dir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 7505b4f1f59..159f588ca16 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -311,7 +311,7 @@ more:
 		req->r_readdir_offset = fi->next_offset;
 		req->r_args.readdir.frag = cpu_to_le32(frag);
 		req->r_args.readdir.max_entries = cpu_to_le32(max_entries);
-		req->r_num_caps = max_entries;
+		req->r_num_caps = max_entries + 1;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 		if (err < 0) {
 			ceph_mdsc_put_request(req);
-- 
cgit v1.2.3-18-g5258


From a6a5349d17f2a5c37079826f1a1474c3d08c6b53 Mon Sep 17 00:00:00 2001
From: Sage Weil <sage@newdream.net>
Date: Tue, 13 Apr 2010 14:07:07 -0700
Subject: ceph: use separate class for ceph sockets' sk_lock

Use a separate class for ceph sockets to prevent lockdep confusion.
Because ceph sockets only get passed kernel pointers, there is no
dependency from sk_lock -> mmap_sem.  If we share the same class as other
sockets, lockdep detects a circular dependency from

	mmap_sem (page fault) -> fs mutex -> sk_lock -> mmap_sem

because dependencies are noted from both ceph and user contexts.  Using
a separate class prevents the sk_lock(ceph) -> mmap_sem dependency and
makes lockdep happy.

Signed-off-by: Sage Weil <sage@newdream.net>
---
 fs/ceph/messenger.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'fs')

diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c
index f35b4945a9c..5c75d5d32b2 100644
--- a/fs/ceph/messenger.c
+++ b/fs/ceph/messenger.c
@@ -29,6 +29,10 @@ static char tag_msg = CEPH_MSGR_TAG_MSG;
 static char tag_ack = CEPH_MSGR_TAG_ACK;
 static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
 
+#ifdef CONFIG_LOCKDEP
+static struct lock_class_key socket_class;
+#endif
+
 
 static void queue_con(struct ceph_connection *con);
 static void con_work(struct work_struct *);
@@ -227,6 +231,10 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
 	con->sock = sock;
 	sock->sk->sk_allocation = GFP_NOFS;
 
+#ifdef CONFIG_LOCKDEP
+	lockdep_set_class(&sock->sk->sk_lock, &socket_class);
+#endif
+
 	set_sock_callbacks(sock, con);
 
 	dout("connect %s\n", pr_addr(&con->peer_addr.in_addr));
-- 
cgit v1.2.3-18-g5258


From 1f1b0008e8dd1930d6e89522c70f4a438374302a Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Thu, 15 Apr 2010 08:03:57 +0200
Subject: [LogFS] Prevent mempool_destroy NULL pointer dereference

It would probably be better to just accept NULL pointers in
mempool_destroy().  But for the current -rc series let's keep things
simple.

This patch was lost in the cracks for a while.
Kevin Cernekee <cernekee@gmail.com> had to rediscover the problem and
send a similar patch because of it. :(

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/logfs.h     | 6 ++++++
 fs/logfs/readwrite.c | 6 ++----
 fs/logfs/segment.c   | 2 +-
 fs/logfs/super.c     | 4 ++--
 4 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h
index c9929eed80b..0a3df1a0c93 100644
--- a/fs/logfs/logfs.h
+++ b/fs/logfs/logfs.h
@@ -727,4 +727,10 @@ static inline struct logfs_area *get_area(struct super_block *sb,
 	return logfs_super(sb)->s_area[(__force u8)gc_level];
 }
 
+static inline void logfs_mempool_destroy(mempool_t *pool)
+{
+	if (pool)
+		mempool_destroy(pool);
+}
+
 #endif
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index 7e0c39c4971..aca6c56a107 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -2243,8 +2243,6 @@ void logfs_cleanup_rw(struct super_block *sb)
 	struct logfs_super *super = logfs_super(sb);
 
 	destroy_meta_inode(super->s_segfile_inode);
-	if (super->s_block_pool)
-		mempool_destroy(super->s_block_pool);
-	if (super->s_shadow_pool)
-		mempool_destroy(super->s_shadow_pool);
+	logfs_mempool_destroy(super->s_block_pool);
+	logfs_mempool_destroy(super->s_shadow_pool);
 }
diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c
index 02db22ebbf1..8c82fe05d3e 100644
--- a/fs/logfs/segment.c
+++ b/fs/logfs/segment.c
@@ -912,7 +912,7 @@ err:
 	for (i--; i >= 0; i--)
 		free_area(super->s_area[i]);
 	free_area(super->s_journal_area);
-	mempool_destroy(super->s_alias_pool);
+	logfs_mempool_destroy(super->s_alias_pool);
 	return -ENOMEM;
 }
 
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index d6e1f4fc311..d4531eb46d0 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -517,8 +517,8 @@ static void logfs_kill_sb(struct super_block *sb)
 	if (super->s_erase_page)
 		__free_page(super->s_erase_page);
 	super->s_devops->put_device(sb);
-	mempool_destroy(super->s_btree_pool);
-	mempool_destroy(super->s_alias_pool);
+	logfs_mempool_destroy(super->s_btree_pool);
+	logfs_mempool_destroy(super->s_alias_pool);
 	kfree(super);
 	log_super("LogFS: Finished unmounting\n");
 }
-- 
cgit v1.2.3-18-g5258


From 2b0b39517d1af5294128dbc2fd7ed39c8effa540 Mon Sep 17 00:00:00 2001
From: Bill Pemberton <wfp5p@virginia.edu>
Date: Fri, 16 Apr 2010 08:01:20 -0500
Subject: jfs: fix diAllocExt error in resizing filesystem

Resizing the filesystem would result in an diAllocExt error in some
instances because changes in bmp->db_agsize would not get noticed if
goto extendBmap was called.

Signed-off-by: Bill Pemberton <wfp5p@virginia.edu>
Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: jfs-discussion@lists.sourceforge.net
Cc: linux-kernel@vger.kernel.org
---
 fs/jfs/resize.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c
index 7f24a0bb08c..1aba0039f1c 100644
--- a/fs/jfs/resize.c
+++ b/fs/jfs/resize.c
@@ -81,6 +81,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
 	struct inode *iplist[1];
 	struct jfs_superblock *j_sb, *j_sb2;
 	uint old_agsize;
+	int agsizechanged = 0;
 	struct buffer_head *bh, *bh2;
 
 	/* If the volume hasn't grown, get out now */
@@ -333,6 +334,9 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
 	 */
 	if ((rc = dbExtendFS(ipbmap, XAddress, nblocks)))
 		goto error_out;
+
+	agsizechanged |= (bmp->db_agsize != old_agsize);
+
 	/*
 	 * the map now has extended to cover additional nblocks:
 	 * dn_mapsize = oldMapsize + nblocks;
@@ -432,7 +436,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize)
 	 * will correctly identify the new ag);
 	 */
 	/* if new AG size the same as old AG size, done! */
-	if (bmp->db_agsize != old_agsize) {
+	if (agsizechanged) {
 		if ((rc = diExtendFS(ipimap, ipbmap)))
 			goto error_out;
 
-- 
cgit v1.2.3-18-g5258


From c7f2e1f0ac142a657a1de00d404e1c8345b20598 Mon Sep 17 00:00:00 2001
From: Dmitry Monakhov <dmonakhov@openvz.org>
Date: Fri, 16 Apr 2010 08:05:50 -0500
Subject: jfs: add jfs specific ->setattr call

generic setattr not longer responsible for quota transfer.
use jfs_setattr for all jfs's inodes.

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
---
 fs/jfs/inode.c     |  2 +-
 fs/jfs/jfs_inode.h |  1 +
 fs/jfs/namei.c     |  4 ++--
 fs/jfs/symlink.c   | 14 +++++++++++++-
 4 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index b2ae190a77b..97cd11954d0 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -60,7 +60,7 @@ struct inode *jfs_iget(struct super_block *sb, unsigned long ino)
 			inode->i_op = &page_symlink_inode_operations;
 			inode->i_mapping->a_ops = &jfs_aops;
 		} else {
-			inode->i_op = &jfs_symlink_inode_operations;
+			inode->i_op = &jfs_fast_symlink_inode_operations;
 			/*
 			 * The inline data should be null-terminated, but
 			 * don't let on-disk corruption crash the kernel
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index 1eff7db34d6..f8b56b238bb 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -47,5 +47,6 @@ extern const struct file_operations jfs_dir_operations;
 extern const struct inode_operations jfs_file_inode_operations;
 extern const struct file_operations jfs_file_operations;
 extern const struct inode_operations jfs_symlink_inode_operations;
+extern const struct inode_operations jfs_fast_symlink_inode_operations;
 extern const struct dentry_operations jfs_ci_dentry_operations;
 #endif				/* _H_JFS_INODE */
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index c79a4270f08..114e6007110 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -946,7 +946,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	 */
 
 	if (ssize <= IDATASIZE) {
-		ip->i_op = &jfs_symlink_inode_operations;
+		ip->i_op = &jfs_fast_symlink_inode_operations;
 
 		i_fastsymlink = JFS_IP(ip)->i_inline;
 		memcpy(i_fastsymlink, name, ssize);
@@ -968,7 +968,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	else {
 		jfs_info("jfs_symlink: allocate extent ip:0x%p", ip);
 
-		ip->i_op = &page_symlink_inode_operations;
+		ip->i_op = &jfs_symlink_inode_operations;
 		ip->i_mapping->a_ops = &jfs_aops;
 
 		/*
diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c
index 4af1a05aad0..205b946d8e0 100644
--- a/fs/jfs/symlink.c
+++ b/fs/jfs/symlink.c
@@ -29,9 +29,21 @@ static void *jfs_follow_link(struct dentry *dentry, struct nameidata *nd)
 	return NULL;
 }
 
-const struct inode_operations jfs_symlink_inode_operations = {
+const struct inode_operations jfs_fast_symlink_inode_operations = {
 	.readlink	= generic_readlink,
 	.follow_link	= jfs_follow_link,
+	.setattr	= jfs_setattr,
+	.setxattr	= jfs_setxattr,
+	.getxattr	= jfs_getxattr,
+	.listxattr	= jfs_listxattr,
+	.removexattr	= jfs_removexattr,
+};
+
+const struct inode_operations jfs_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+	.setattr	= jfs_setattr,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
 	.listxattr	= jfs_listxattr,
-- 
cgit v1.2.3-18-g5258


From b6f8dd49dbdbfa60a33bba3d4b766fe341109b4b Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Tue, 13 Apr 2010 15:06:44 +1000
Subject: xfs: ensure that sync updates the log tail correctly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Updates to the VFS layer removed an extra ->sync_fs call into the
filesystem during the sync process (from the quota code).
Unfortunately the sync code was unknowingly relying on this call to
make sure metadata buffers were flushed via a xfs_buftarg_flush()
call to move the tail of the log forward in memory before the final
transactions of the sync process were issued.

As a result, the old code would write a very recent log tail value
to the log by the end of the sync process, and so a subsequent crash
would leave nothing for log recovery to do. Hence in qa test 182,
log recovery only replayed a small handle for inode fsync
transactions in this case.

However, with the removal of the extra ->sync_fs call, the log tail
was now not moved forward with the inode fsync transactions near the
end of the sync procese the first (and only) buftarg flush occurred
after these transactions went to disk. The result is that log
recovery now sees a large number of transactions for metadata that
is already on disk.

This usually isn't a problem, but when the transactions include
inode chunk allocation, the inode create transactions and all
subsequent changes are replayed as we cannt rely on what is on disk
is valid. As a result, if the inode was written and contains
unlogged changes, the unlogged changes are lost, thereby violating
sync semantics.

The fix is to always issue a transaction after the buftarg flush
occurs is the log iѕ not idle or covered. This results in a dummy
transaction being written that contains the up-to-date log tail
value, which will be very recent. Indeed, it will be at least as
recent as the old code would have left on disk, so log recovery
will behave exactly as it used to in this situation.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/xfs_log.c | 38 ++++++++++++++++++++++++++------------
 1 file changed, 26 insertions(+), 12 deletions(-)

(limited to 'fs')

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index e8fba92d7cd..2be01913628 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -745,9 +745,16 @@ xfs_log_move_tail(xfs_mount_t	*mp,
 
 /*
  * Determine if we have a transaction that has gone to disk
- * that needs to be covered. Log activity needs to be idle (no AIL and
- * nothing in the iclogs). And, we need to be in the right state indicating
- * something has gone out.
+ * that needs to be covered. To begin the transition to the idle state
+ * firstly the log needs to be idle (no AIL and nothing in the iclogs).
+ * If we are then in a state where covering is needed, the caller is informed
+ * that dummy transactions are required to move the log into the idle state.
+ *
+ * Because this is called as part of the sync process, we should also indicate
+ * that dummy transactions should be issued in anything but the covered or
+ * idle states. This ensures that the log tail is accurately reflected in
+ * the log at the end of the sync, hence if a crash occurrs avoids replay
+ * of transactions where the metadata is already on disk.
  */
 int
 xfs_log_need_covered(xfs_mount_t *mp)
@@ -759,17 +766,24 @@ xfs_log_need_covered(xfs_mount_t *mp)
 		return 0;
 
 	spin_lock(&log->l_icloglock);
-	if (((log->l_covered_state == XLOG_STATE_COVER_NEED) ||
-		(log->l_covered_state == XLOG_STATE_COVER_NEED2))
-			&& !xfs_trans_ail_tail(log->l_ailp)
-			&& xlog_iclogs_empty(log)) {
-		if (log->l_covered_state == XLOG_STATE_COVER_NEED)
-			log->l_covered_state = XLOG_STATE_COVER_DONE;
-		else {
-			ASSERT(log->l_covered_state == XLOG_STATE_COVER_NEED2);
-			log->l_covered_state = XLOG_STATE_COVER_DONE2;
+	switch (log->l_covered_state) {
+	case XLOG_STATE_COVER_DONE:
+	case XLOG_STATE_COVER_DONE2:
+	case XLOG_STATE_COVER_IDLE:
+		break;
+	case XLOG_STATE_COVER_NEED:
+	case XLOG_STATE_COVER_NEED2:
+		if (!xfs_trans_ail_tail(log->l_ailp) &&
+		    xlog_iclogs_empty(log)) {
+			if (log->l_covered_state == XLOG_STATE_COVER_NEED)
+				log->l_covered_state = XLOG_STATE_COVER_DONE;
+			else
+				log->l_covered_state = XLOG_STATE_COVER_DONE2;
 		}
+		/* FALLTHRU */
+	default:
 		needed = 1;
+		break;
 	}
 	spin_unlock(&log->l_icloglock);
 	return needed;
-- 
cgit v1.2.3-18-g5258


From f1d486a3617a2f620b31224e4ace1496c4627e39 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Tue, 13 Apr 2010 15:06:45 +1000
Subject: xfs: don't warn on EAGAIN in inode reclaim

Any inode reclaim flush that returns EAGAIN will result in the inode
reclaim being attempted again later. There is no need to issue a
warning into the logs about this situation.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Alex Elder <aelder@sgi.com>
Signed-off-by: Alex Elder <aelder@sgi.com>
---
 fs/xfs/linux-2.6/xfs_sync.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 05cd85317f6..fd969821575 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -820,10 +820,10 @@ xfs_reclaim_inode(
 	 * call into reclaim to find it in a clean state instead of waiting for
 	 * it now. We also don't return errors here - if the error is transient
 	 * then the next reclaim pass will flush the inode, and if the error
-	 * is permanent then the next sync reclaim will relcaim the inode and
+	 * is permanent then the next sync reclaim will reclaim the inode and
 	 * pass on the error.
 	 */
-	if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+	if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_fs_cmn_err(CE_WARN, ip->i_mount,
 			"inode 0x%llx background reclaim flush failed with %d",
 			(long long)ip->i_ino, error);
-- 
cgit v1.2.3-18-g5258


From b8639077abf034824046ed09e779b74c4393031f Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Sat, 17 Apr 2010 19:54:27 +0200
Subject: [LogFS] Set s_bdi

Since 32a88aa1 sync() was turned into a NOP for logfs.  Worse, sync()
would not return an error, giving the illusion that writeout had
actually happened.

Afaics jffs2 was broken as well.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/super.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'fs')

diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index d4531eb46d0..dacce3a917a 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -11,6 +11,7 @@
  */
 #include "logfs.h"
 #include <linux/bio.h>
+#include <linux/blkdev.h>
 #include <linux/mtd/mtd.h>
 #include <linux/statfs.h>
 #include <linux/buffer_head.h>
@@ -136,6 +137,10 @@ static int logfs_sb_set(struct super_block *sb, void *_super)
 	sb->s_fs_info = super;
 	sb->s_mtd = super->s_mtd;
 	sb->s_bdev = super->s_bdev;
+	if (sb->s_bdev)
+		sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
+	if (sb->s_mtd)
+		sb->s_bdi = sb->s_mtd->backing_dev_info;
 	return 0;
 }
 
-- 
cgit v1.2.3-18-g5258


From 3a60a1686f0d51c99bd0df8ac93050fb6dfce647 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Mon, 22 Mar 2010 00:41:35 -0500
Subject: eCryptfs: Decrypt symlink target for stat size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create a getattr handler for eCryptfs symlinks that is capable of
reading the lower target and decrypting its path.  Prior to this patch,
a stat's st_size field would represent the strlen of the encrypted path,
while readlink() would return the strlen of the decrypted path.  This
could lead to confusion in some userspace applications, since the two
values should be equal.

https://bugs.launchpad.net/bugs/524919

Reported-by: Loïc Minier <loic.minier@canonical.com>
Cc: stable@kernel.org
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/inode.c | 100 +++++++++++++++++++++++++++-------------------------
 1 file changed, 52 insertions(+), 48 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index ddbd096c740..605f514f3b4 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -648,38 +648,17 @@ out_lock:
 	return rc;
 }
 
-static int
-ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+static int ecryptfs_readlink_lower(struct dentry *dentry, char **buf,
+				   size_t *bufsiz)
 {
+	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	char *lower_buf;
-	size_t lower_bufsiz;
-	struct dentry *lower_dentry;
-	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
-	char *plaintext_name;
-	size_t plaintext_name_size;
+	size_t lower_bufsiz = PATH_MAX;
 	mm_segment_t old_fs;
 	int rc;
 
-	lower_dentry = ecryptfs_dentry_to_lower(dentry);
-	if (!lower_dentry->d_inode->i_op->readlink) {
-		rc = -EINVAL;
-		goto out;
-	}
-	mount_crypt_stat = &ecryptfs_superblock_to_private(
-						dentry->d_sb)->mount_crypt_stat;
-	/*
-	 * If the lower filename is encrypted, it will result in a significantly
-	 * longer name.  If needed, truncate the name after decode and decrypt.
-	 */
-	if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)
-		lower_bufsiz = PATH_MAX;
-	else
-		lower_bufsiz = bufsiz;
-	/* Released in this function */
 	lower_buf = kmalloc(lower_bufsiz, GFP_KERNEL);
-	if (lower_buf == NULL) {
-		printk(KERN_ERR "%s: Out of memory whilst attempting to "
-		       "kmalloc [%zd] bytes\n", __func__, lower_bufsiz);
+	if (!lower_buf) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -689,29 +668,31 @@ ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
 						   (char __user *)lower_buf,
 						   lower_bufsiz);
 	set_fs(old_fs);
-	if (rc >= 0) {
-		rc = ecryptfs_decode_and_decrypt_filename(&plaintext_name,
-							  &plaintext_name_size,
-							  dentry, lower_buf,
-							  rc);
-		if (rc) {
-			printk(KERN_ERR "%s: Error attempting to decode and "
-			       "decrypt filename; rc = [%d]\n", __func__,
-				rc);
-			goto out_free_lower_buf;
-		}
-		/* Check for bufsiz <= 0 done in sys_readlinkat() */
-		rc = copy_to_user(buf, plaintext_name,
-				  min((size_t) bufsiz, plaintext_name_size));
-		if (rc)
-			rc = -EFAULT;
-		else
-			rc = plaintext_name_size;
-		kfree(plaintext_name);
-		fsstack_copy_attr_atime(dentry->d_inode, lower_dentry->d_inode);
-	}
-out_free_lower_buf:
+	if (rc < 0)
+		goto out;
+	lower_bufsiz = rc;
+	rc = ecryptfs_decode_and_decrypt_filename(buf, bufsiz, dentry,
+						  lower_buf, lower_bufsiz);
+out:
 	kfree(lower_buf);
+	return rc;
+}
+
+static int
+ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz)
+{
+	char *kbuf;
+	size_t kbufsiz, copied;
+	int rc;
+
+	rc = ecryptfs_readlink_lower(dentry, &kbuf, &kbufsiz);
+	if (rc)
+		goto out;
+	copied = min_t(size_t, bufsiz, kbufsiz);
+	rc = copy_to_user(buf, kbuf, copied) ? -EFAULT : copied;
+	kfree(kbuf);
+	fsstack_copy_attr_atime(dentry->d_inode,
+				ecryptfs_dentry_to_lower(dentry)->d_inode);
 out:
 	return rc;
 }
@@ -1016,6 +997,28 @@ out:
 	return rc;
 }
 
+int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
+			  struct kstat *stat)
+{
+	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
+	int rc = 0;
+
+	mount_crypt_stat = &ecryptfs_superblock_to_private(
+						dentry->d_sb)->mount_crypt_stat;
+	generic_fillattr(dentry->d_inode, stat);
+	if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
+		char *target;
+		size_t targetsiz;
+
+		rc = ecryptfs_readlink_lower(dentry, &target, &targetsiz);
+		if (!rc) {
+			kfree(target);
+			stat->size = targetsiz;
+		}
+	}
+	return rc;
+}
+
 int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		     struct kstat *stat)
 {
@@ -1133,6 +1136,7 @@ const struct inode_operations ecryptfs_symlink_iops = {
 	.put_link = ecryptfs_put_link,
 	.permission = ecryptfs_permission,
 	.setattr = ecryptfs_setattr,
+	.getattr = ecryptfs_getattr_link,
 	.setxattr = ecryptfs_setxattr,
 	.getxattr = ecryptfs_getxattr,
 	.listxattr = ecryptfs_listxattr,
-- 
cgit v1.2.3-18-g5258


From cfce08c6bdfb20ade979284e55001ca1f100ed51 Mon Sep 17 00:00:00 2001
From: Christian Pulvermacher <pulvermacher@gmx.de>
Date: Tue, 23 Mar 2010 11:51:38 -0500
Subject: ecryptfs: fix error code for missing xattrs in lower fs

If the lower file system driver has extended attributes disabled,
ecryptfs' own access functions return -ENOSYS instead of -EOPNOTSUPP.
This breaks execution of programs in the ecryptfs mount, since the
kernel expects the latter error when checking for security
capabilities in xattrs.

Signed-off-by: Christian Pulvermacher <pulvermacher@gmx.de>
Cc: stable@kernel.org
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/inode.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 605f514f3b4..efd4f47d530 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1043,7 +1043,7 @@ ecryptfs_setxattr(struct dentry *dentry, const char *name, const void *value,
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	if (!lower_dentry->d_inode->i_op->setxattr) {
-		rc = -ENOSYS;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1061,7 +1061,7 @@ ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
 	int rc = 0;
 
 	if (!lower_dentry->d_inode->i_op->getxattr) {
-		rc = -ENOSYS;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1088,7 +1088,7 @@ ecryptfs_listxattr(struct dentry *dentry, char *list, size_t size)
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	if (!lower_dentry->d_inode->i_op->listxattr) {
-		rc = -ENOSYS;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
@@ -1105,7 +1105,7 @@ static int ecryptfs_removexattr(struct dentry *dentry, const char *name)
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	if (!lower_dentry->d_inode->i_op->removexattr) {
-		rc = -ENOSYS;
+		rc = -EOPNOTSUPP;
 		goto out;
 	}
 	mutex_lock(&lower_dentry->d_inode->i_mutex);
-- 
cgit v1.2.3-18-g5258


From 133b8f9d632cc23715c6d72d1c5ac449e054a12a Mon Sep 17 00:00:00 2001
From: Jeff Mahoney <jeffm@jeffreymahoney.com>
Date: Fri, 19 Mar 2010 15:35:46 -0400
Subject: ecryptfs: fix use with tmpfs by removing d_drop from
 ecryptfs_destroy_inode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since tmpfs has no persistent storage, it pins all its dentries in memory
so they have d_count=1 when other file systems would have d_count=0.
->lookup is only used to create new dentries. If the caller doesn't
instantiate it, it's freed immediately at dput(). ->readdir reads
directly from the dcache and depends on the dentries being hashed.

When an ecryptfs mount is mounted, it associates the lower file and dentry
with the ecryptfs files as they're accessed. When it's umounted and
destroys all the in-memory ecryptfs inodes, it fput's the lower_files and
d_drop's the lower_dentries. Commit 4981e081 added this and a d_delete in
2008 and several months later commit caeeeecf removed the d_delete. I
believe the d_drop() needs to be removed as well.

The d_drop effectively hides any file that has been accessed via ecryptfs
from the underlying tmpfs since it depends on it being hashed for it to
be accessible. I've removed the d_drop on my development node and see no
ill effects with basic testing on both tmpfs and persistent storage.

As a side effect, after ecryptfs d_drops the dentries on tmpfs, tmpfs
BUGs on umount. This is due to the dentries being unhashed.
tmpfs->kill_sb is kill_litter_super which calls d_genocide to drop
the reference pinning the dentry. It skips unhashed and negative dentries,
but shrink_dcache_for_umount_subtree doesn't. Since those dentries
still have an elevated d_count, we get a BUG().

This patch removes the d_drop call and fixes both issues.

This issue was reported at:
https://bugzilla.novell.com/show_bug.cgi?id=567887

Reported-by:  Árpád Bíró <biroa@demasz.hu>
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Cc: Dustin Kirkland <kirkland@canonical.com>
Cc: stable@kernel.org
Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/super.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index b15a43a80ab..1a037f77aa5 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -85,7 +85,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
 		if (lower_dentry->d_inode) {
 			fput(inode_info->lower_file);
 			inode_info->lower_file = NULL;
-			d_drop(lower_dentry);
 		}
 	}
 	ecryptfs_destroy_crypt_stat(&inode_info->crypt_stat);
-- 
cgit v1.2.3-18-g5258


From 3a8380c0754a7972668a46f645930910e304095c Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Tue, 23 Mar 2010 18:09:02 -0500
Subject: eCryptfs: Copy lower directory inode times and size on link

The timestamps and size of a lower inode involved in a link() call was
being copied to the upper parent inode.  Instead, we should be
copying lower parent inode's timestamps and size to the upper parent
inode.  I discovered this bug using the POSIX test suite at Tuxera.

Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index efd4f47d530..15b424837c1 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -456,8 +456,8 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
 	rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb, 0);
 	if (rc)
 		goto out_lock;
-	fsstack_copy_attr_times(dir, lower_new_dentry->d_inode);
-	fsstack_copy_inode_size(dir, lower_new_dentry->d_inode);
+	fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
+	fsstack_copy_inode_size(dir, lower_dir_dentry->d_inode);
 	old_dentry->d_inode->i_nlink =
 		ecryptfs_inode_to_lower(old_dentry->d_inode)->i_nlink;
 	i_size_write(new_dentry->d_inode, file_size_save);
-- 
cgit v1.2.3-18-g5258


From 9f37622f897a90ad3c3da5c14d94d8f3ffc62b70 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
Date: Thu, 25 Mar 2010 11:16:56 -0500
Subject: eCryptfs: Turn lower lookup error messages into debug messages

Vaugue warnings about ENAMETOOLONG errors when looking up an encrypted
file name have caused many users to become concerned about their data.
Since this is a rather harmless condition, I'm moving this warning to
only be printed when the ecryptfs_verbosity module param is 1.

Signed-off-by: Tyler Hicks <tyhicks@linux.vnet.ibm.com>
---
 fs/ecryptfs/inode.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'fs')

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 15b424837c1..b980fce984c 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -388,9 +388,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
-		printk(KERN_ERR "%s: lookup_one_len() returned [%d] on "
-		       "lower_dentry = [%s]\n", __func__, rc,
-		       ecryptfs_dentry->d_name.name);
+		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
+				"[%d] on lower_dentry = [%s]\n", __func__, rc,
+				encrypted_and_encoded_name);
 		goto out_d_drop;
 	}
 	if (lower_dentry->d_inode)
@@ -417,9 +417,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 	mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
 	if (IS_ERR(lower_dentry)) {
 		rc = PTR_ERR(lower_dentry);
-		printk(KERN_ERR "%s: lookup_one_len() returned [%d] on "
-		       "lower_dentry = [%s]\n", __func__, rc,
-		       encrypted_and_encoded_name);
+		ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
+				"[%d] on lower_dentry = [%s]\n", __func__, rc,
+				encrypted_and_encoded_name);
 		goto out_d_drop;
 	}
 lookup_and_interpose:
-- 
cgit v1.2.3-18-g5258


From 62af9b520513d78484f22f874916dfacbc889ce0 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Mon, 19 Apr 2010 16:47:20 +0200
Subject: quota: Convert __DQUOT_PARANOIA symbol to standard config option

Make __DQUOT_PARANOIA define from the old days a standard config option
and turn it off by default.

This gets rid of a quota warning about writes before quota is turned on
for systems with ext4 root filesystem. Currently there's no way to legally
solve this because /etc/mtab has to be written before quota is turned on
on most systems.

Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/quota/Kconfig |  8 ++++++++
 fs/quota/dquot.c | 16 +++++++---------
 2 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'fs')

diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig
index dad7fb247dd..3e21b1e2ad3 100644
--- a/fs/quota/Kconfig
+++ b/fs/quota/Kconfig
@@ -33,6 +33,14 @@ config PRINT_QUOTA_WARNING
 	  Note that this behavior is currently deprecated and may go away in
 	  future. Please use notification via netlink socket instead.
 
+config QUOTA_DEBUG
+	bool "Additional quota sanity checks"
+	depends on QUOTA
+	default n
+	help
+	  If you say Y here, quota subsystem will perform some additional
+	  sanity checks of quota internal structures. If unsure, say N.
+
 # Generic support for tree structured quota files. Selected when needed.
 config QUOTA_TREE
 	 tristate
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index a0a9405b202..788b5802a7c 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -80,8 +80,6 @@
 
 #include <asm/uaccess.h>
 
-#define __DQUOT_PARANOIA
-
 /*
  * There are three quota SMP locks. dq_list_lock protects all lists with quotas
  * and quota formats, dqstats structure containing statistics about the lists
@@ -695,7 +693,7 @@ void dqput(struct dquot *dquot)
 
 	if (!dquot)
 		return;
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 	if (!atomic_read(&dquot->dq_count)) {
 		printk("VFS: dqput: trying to free free dquot\n");
 		printk("VFS: device %s, dquot of %s %d\n",
@@ -748,7 +746,7 @@ we_slept:
 		goto we_slept;
 	}
 	atomic_dec(&dquot->dq_count);
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 	/* sanity check */
 	BUG_ON(!list_empty(&dquot->dq_free));
 #endif
@@ -845,7 +843,7 @@ we_slept:
 		dquot = NULL;
 		goto out;
 	}
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 	BUG_ON(!dquot->dq_sb);	/* Has somebody invalidated entry under us? */
 #endif
 out:
@@ -874,7 +872,7 @@ static int dqinit_needed(struct inode *inode, int type)
 static void add_dquot_ref(struct super_block *sb, int type)
 {
 	struct inode *inode, *old_inode = NULL;
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 	int reserved = 0;
 #endif
 
@@ -882,7 +880,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
 			continue;
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 		if (unlikely(inode_get_rsv_space(inode) > 0))
 			reserved = 1;
 #endif
@@ -907,7 +905,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
 	spin_unlock(&inode_lock);
 	iput(old_inode);
 
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 	if (reserved) {
 		printk(KERN_WARNING "VFS (%s): Writes happened before quota"
 			" was turned on thus quota information is probably "
@@ -940,7 +938,7 @@ static int remove_inode_dquot_ref(struct inode *inode, int type,
 	inode->i_dquot[type] = NULL;
 	if (dquot) {
 		if (dqput_blocks(dquot)) {
-#ifdef __DQUOT_PARANOIA
+#ifdef CONFIG_QUOTA_DEBUG
 			if (atomic_read(&dquot->dq_count) != 1)
 				printk(KERN_WARNING "VFS: Adding dquot with dq_count %d to dispose list.\n", atomic_read(&dquot->dq_count));
 #endif
-- 
cgit v1.2.3-18-g5258


From b6349ac89eacb813f6963f7263da05bc3f483351 Mon Sep 17 00:00:00 2001
From: Joern Engel <joern@logfs.org>
Date: Tue, 20 Apr 2010 21:44:10 +0200
Subject: [LogFS] Split large truncated into smaller chunks

Truncate would do an almost limitless amount of work without invoking
the garbage collector in between.  Split it up into more manageable,
though still large, chunks.

Signed-off-by: Joern Engel <joern@logfs.org>
---
 fs/logfs/readwrite.c | 34 ++++++++++++++++++++++++++--------
 1 file changed, 26 insertions(+), 8 deletions(-)

(limited to 'fs')

diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index aca6c56a107..7e3a1e5fd76 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -1837,19 +1837,37 @@ static int __logfs_truncate(struct inode *inode, u64 size)
 	return logfs_truncate_direct(inode, size);
 }
 
-int logfs_truncate(struct inode *inode, u64 size)
+/*
+ * Truncate, by changing the segment file, can consume a fair amount
+ * of resources.  So back off from time to time and do some GC.
+ * 8 or 2048 blocks should be well within safety limits even if
+ * every single block resided in a different segment.
+ */
+#define TRUNCATE_STEP	(8 * 1024 * 1024)
+int logfs_truncate(struct inode *inode, u64 target)
 {
 	struct super_block *sb = inode->i_sb;
-	int err;
+	u64 size = i_size_read(inode);
+	int err = 0;
 
-	logfs_get_wblocks(sb, NULL, 1);
-	err = __logfs_truncate(inode, size);
-	if (!err)
-		err = __logfs_write_inode(inode, 0);
-	logfs_put_wblocks(sb, NULL, 1);
+	size = ALIGN(size, TRUNCATE_STEP);
+	while (size > target) {
+		if (size > TRUNCATE_STEP)
+			size -= TRUNCATE_STEP;
+		else
+			size = 0;
+		if (size < target)
+			size = target;
+
+		logfs_get_wblocks(sb, NULL, 1);
+		err = __logfs_truncate(inode, target);
+		if (!err)
+			err = __logfs_write_inode(inode, 0);
+		logfs_put_wblocks(sb, NULL, 1);
+	}
 
 	if (!err)
-		err = vmtruncate(inode, size);
+		err = vmtruncate(inode, target);
 
 	/* I don't trust error recovery yet. */
 	WARN_ON(err);
-- 
cgit v1.2.3-18-g5258


From d7dfee3f5db5575b1d838744559c3c9bb351f74f Mon Sep 17 00:00:00 2001
From: Jun Sun <jsun@junsun.net>
Date: Thu, 31 Dec 2009 17:28:52 -0800
Subject: uclinux: error message when FLAT reloc symbol is invalid, v2

This patch fixes a cosmetic error in printk. Text segment and data/bss
segment are allocated from two different areas. It is not meaningful to
give the diff between them in the error reporting messages.

Signed-off-by: Jun Sun <jsun@junsun.net>
Signed-off-by: Greg Ungerer <gerg@uclinux.org>
---
 fs/binfmt_flat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs')

diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index e0e769bdca5..49566c1687d 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -355,7 +355,7 @@ calc_reloc(unsigned long r, struct lib_info *p, int curid, int internalp)
 
 	if (!flat_reloc_valid(r, start_brk - start_data + text_len)) {
 		printk("BINFMT_FLAT: reloc outside program 0x%x (0 - 0x%x/0x%x)",
-		       (int) r,(int)(start_brk-start_code),(int)text_len);
+		       (int) r,(int)(start_brk-start_data+text_len),(int)text_len);
 		goto failed;
 	}
 
-- 
cgit v1.2.3-18-g5258


From 083fd8b21a13742b37ab347089c73f895a896672 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 21 Apr 2010 12:01:23 +0100
Subject: AFS: Don't pass error value to page_cache_release() in error handling

In the error handling in afs_mntpt_do_automount(), we pass an error
pointer to page_cache_release() if read_mapping_page() failed.  Instead,
we should extend the gotos around the error handling we don't need.

Reported-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/afs/mntpt.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'fs')

diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 5e813a816ce..b3feddc4f7d 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -138,9 +138,9 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 {
 	struct afs_super_info *super;
 	struct vfsmount *mnt;
-	struct page *page = NULL;
+	struct page *page;
 	size_t size;
-	char *buf, *devname = NULL, *options = NULL;
+	char *buf, *devname, *options;
 	int ret;
 
 	_enter("{%s}", mntpt->d_name.name);
@@ -150,22 +150,22 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 	ret = -EINVAL;
 	size = mntpt->d_inode->i_size;
 	if (size > PAGE_SIZE - 1)
-		goto error;
+		goto error_no_devname;
 
 	ret = -ENOMEM;
 	devname = (char *) get_zeroed_page(GFP_KERNEL);
 	if (!devname)
-		goto error;
+		goto error_no_devname;
 
 	options = (char *) get_zeroed_page(GFP_KERNEL);
 	if (!options)
-		goto error;
+		goto error_no_options;
 
 	/* read the contents of the AFS special symlink */
 	page = read_mapping_page(mntpt->d_inode->i_mapping, 0, NULL);
 	if (IS_ERR(page)) {
 		ret = PTR_ERR(page);
-		goto error;
+		goto error_no_page;
 	}
 
 	ret = -EIO;
@@ -196,12 +196,12 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 	return mnt;
 
 error:
-	if (page)
-		page_cache_release(page);
-	if (devname)
-		free_page((unsigned long) devname);
-	if (options)
-		free_page((unsigned long) options);
+	page_cache_release(page);
+error_no_page:
+	free_page((unsigned long) options);
+error_no_options:
+	free_page((unsigned long) devname);
+error_no_devname:
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
 }
-- 
cgit v1.2.3-18-g5258


From d4cd1871cff68e188dadcf6d1280762522b643eb Mon Sep 17 00:00:00 2001
From: Li Dongyang <lidongyang@novell.com>
Date: Thu, 22 Apr 2010 16:11:19 +0800
Subject: ocfs2: add OCFS2_INODE_SKIP_ORPHAN_DIR flag and honor it in the inode
 wipe code

Currently in the error path of ocfs2_symlink and ocfs2_mknod, we just call
iput with the inode we failed with, but the inode wipe code will complain
because we don't add the inode to orphan dir. One solution would be to lock
the orphan dir during the entire transaction, but that's too heavy for a
rare error path. Instead, we add a flag, OCFS2_INODE_SKIP_ORPHAN_DIR which
tells the inode wipe code that it won't find this inode in the orphan dir.

[ Merge fixes and comment style cleanups -Mark ]

Signed-off-by: Li Dongyang <lidongyang@novell.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/inode.c | 65 +++++++++++++++++++++++++++++++-------------------------
 fs/ocfs2/inode.h |  2 ++
 fs/ocfs2/namei.c |  1 +
 3 files changed, 39 insertions(+), 29 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 07cc8bb68b6..26399202be7 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -639,11 +639,13 @@ static int ocfs2_remove_inode(struct inode *inode,
 		goto bail_unlock;
 	}
 
-	status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
-				  orphan_dir_bh);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail_commit;
+	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
+		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode, inode,
+					  orphan_dir_bh);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail_commit;
+		}
 	}
 
 	/* set the inodes dtime */
@@ -726,34 +728,35 @@ static int ocfs2_wipe_inode(struct inode *inode,
 	struct inode *orphan_dir_inode = NULL;
 	struct buffer_head *orphan_dir_bh = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct ocfs2_dinode *di;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
 
-	di = (struct ocfs2_dinode *) di_bh->b_data;
-	orphaned_slot = le16_to_cpu(di->i_orphaned_slot);
+	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
+		orphaned_slot = le16_to_cpu(di->i_orphaned_slot);
 
-	status = ocfs2_check_orphan_recovery_state(osb, orphaned_slot);
-	if (status)
-		return status;
+		status = ocfs2_check_orphan_recovery_state(osb, orphaned_slot);
+		if (status)
+			return status;
 
-	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
-						       ORPHAN_DIR_SYSTEM_INODE,
-						       orphaned_slot);
-	if (!orphan_dir_inode) {
-		status = -EEXIST;
-		mlog_errno(status);
-		goto bail;
-	}
+		orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+							       ORPHAN_DIR_SYSTEM_INODE,
+							       orphaned_slot);
+		if (!orphan_dir_inode) {
+			status = -EEXIST;
+			mlog_errno(status);
+			goto bail;
+		}
 
-	/* Lock the orphan dir. The lock will be held for the entire
-	 * delete_inode operation. We do this now to avoid races with
-	 * recovery completion on other nodes. */
-	mutex_lock(&orphan_dir_inode->i_mutex);
-	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
-	if (status < 0) {
-		mutex_unlock(&orphan_dir_inode->i_mutex);
+		/* Lock the orphan dir. The lock will be held for the entire
+		 * delete_inode operation. We do this now to avoid races with
+		 * recovery completion on other nodes. */
+		mutex_lock(&orphan_dir_inode->i_mutex);
+		status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+		if (status < 0) {
+			mutex_unlock(&orphan_dir_inode->i_mutex);
 
-		mlog_errno(status);
-		goto bail;
+			mlog_errno(status);
+			goto bail;
+		}
 	}
 
 	/* we do this while holding the orphan dir lock because we
@@ -794,6 +797,9 @@ static int ocfs2_wipe_inode(struct inode *inode,
 		mlog_errno(status);
 
 bail_unlock_dir:
+	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)
+		return status;
+
 	ocfs2_inode_unlock(orphan_dir_inode, 1);
 	mutex_unlock(&orphan_dir_inode->i_mutex);
 	brelse(orphan_dir_bh);
@@ -889,7 +895,8 @@ static int ocfs2_query_inode_wipe(struct inode *inode,
 
 	/* Do some basic inode verification... */
 	di = (struct ocfs2_dinode *) di_bh->b_data;
-	if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL))) {
+	if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL)) &&
+	    !(oi->ip_flags & OCFS2_INODE_SKIP_ORPHAN_DIR)) {
 		/*
 		 * Inodes in the orphan dir must have ORPHANED_FL.  The only
 		 * inodes that come back out of the orphan dir are reflink
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ba4fe07b293..0b28e1921a3 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -100,6 +100,8 @@ struct ocfs2_inode_info
 #define OCFS2_INODE_MAYBE_ORPHANED	0x00000020
 /* Does someone have the file open O_DIRECT */
 #define OCFS2_INODE_OPEN_DIRECT		0x00000040
+/* Tell the inode wipe code it's not in orphan dir */
+#define OCFS2_INODE_SKIP_ORPHAN_DIR     0x00000080
 
 static inline struct ocfs2_inode_info *OCFS2_I(struct inode *inode)
 {
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b1eb50ae409..ae315c9c768 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -1976,6 +1976,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 	}
 
 	le32_add_cpu(&fe->i_flags, OCFS2_ORPHANED_FL);
+	OCFS2_I(inode)->ip_flags &= ~OCFS2_INODE_SKIP_ORPHAN_DIR;
 
 	/* Record which orphan dir our inode now resides
 	 * in. delete_inode will use this to determine which orphan
-- 
cgit v1.2.3-18-g5258


From ab41fdc8fdd9f0942430941c1e2b516fd481371d Mon Sep 17 00:00:00 2001
From: Li Dongyang <lidongyang@novell.com>
Date: Thu, 22 Apr 2010 16:11:25 +0800
Subject: ocfs2: use OCFS2_INODE_SKIP_ORPHAN_DIR in ocfs2_symlink error path

Mark the inode with flag OCFS2_INODE_SKIP_ORPHAN_DIR when we get an error
after allocating one, so that we can kill the inode.

Signed-off-by: Li Dongyang <lidongyang@novell.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/namei.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs')

diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index ae315c9c768..b66e4885582 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -1811,6 +1811,7 @@ bail:
 	if (xattr_ac)
 		ocfs2_free_alloc_context(xattr_ac);
 	if ((status < 0) && inode) {
+		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
 		clear_nlink(inode);
 		iput(inode);
 	}
-- 
cgit v1.2.3-18-g5258


From 062d340384dcf77dfd8de0a082b5da571de3925a Mon Sep 17 00:00:00 2001
From: Li Dongyang <lidongyang@novell.com>
Date: Thu, 22 Apr 2010 16:11:29 +0800
Subject: ocfs2: use OCFS2_INODE_SKIP_ORPHAN_DIR in ocfs2_mknod error path

Mark the inode with flag OCFS2_INODE_SKIP_ORPHAN_DIR in ocfs2_mknod, so we
can kill the inode in case of error.

[ Fixed up comment style -Mark ]

Signed-off-by: Li Dongyang <lidongyang@novell.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/namei.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b66e4885582..8ff035eabfd 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -445,11 +445,6 @@ leave:
 
 	ocfs2_free_dir_lookup_result(&lookup);
 
-	if ((status < 0) && inode) {
-		clear_nlink(inode);
-		iput(inode);
-	}
-
 	if (inode_ac)
 		ocfs2_free_alloc_context(inode_ac);
 
@@ -459,6 +454,17 @@ leave:
 	if (meta_ac)
 		ocfs2_free_alloc_context(meta_ac);
 
+	/*
+	 * We should call iput after the i_mutex of the bitmap been
+	 * unlocked in ocfs2_free_alloc_context, or the
+	 * ocfs2_delete_inode will mutex_lock again.
+	 */
+	if ((status < 0) && inode) {
+		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR;
+		clear_nlink(inode);
+		iput(inode);
+	}
+
 	mlog_exit(status);
 
 	return status;
-- 
cgit v1.2.3-18-g5258


From a9743fcdc0eb43d028b71267438076e1b0112ba0 Mon Sep 17 00:00:00 2001
From: Mark Fasheh <mfasheh@suse.com>
Date: Fri, 23 Apr 2010 11:42:22 -0700
Subject: ocfs2: Add directory entry later in ocfs2_symlink() and ocfs2_mknod()

If we get a failure during creation of an inode we'll allow the orphan code
to remove the inode, which is correct. However, we need to ensure that we
don't get any errors after the call to ocfs2_add_entry(), otherwise we could
leave a dangling directory reference. The solution is simple - in both
cases, all I had to do was move ocfs2_dentry_attach_lock() above the
ocfs2_add_entry() call.

Signed-off-by: Mark Fasheh <mfasheh@suse.com>
---
 fs/ocfs2/namei.c | 40 +++++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

(limited to 'fs')

diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 8ff035eabfd..4cbb18f26c5 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -408,23 +408,28 @@ static int ocfs2_mknod(struct inode *dir,
 		}
 	}
 
-	status = ocfs2_add_entry(handle, dentry, inode,
-				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
-				 &lookup);
-	if (status < 0) {
+	/*
+	 * Do this before adding the entry to the directory. We add
+	 * also set d_op after success so that ->d_iput() will cleanup
+	 * the dentry lock even if ocfs2_add_entry() fails below.
+	 */
+	status = ocfs2_dentry_attach_lock(dentry, inode,
+					  OCFS2_I(dir)->ip_blkno);
+	if (status) {
 		mlog_errno(status);
 		goto leave;
 	}
+	dentry->d_op = &ocfs2_dentry_ops;
 
-	status = ocfs2_dentry_attach_lock(dentry, inode,
-					  OCFS2_I(dir)->ip_blkno);
-	if (status) {
+	status = ocfs2_add_entry(handle, dentry, inode,
+				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
+				 &lookup);
+	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
 	}
 
 	insert_inode_hash(inode);
-	dentry->d_op = &ocfs2_dentry_ops;
 	d_instantiate(dentry, inode);
 	status = 0;
 leave:
@@ -1777,22 +1782,27 @@ static int ocfs2_symlink(struct inode *dir,
 		}
 	}
 
-	status = ocfs2_add_entry(handle, dentry, inode,
-				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
-				 &lookup);
-	if (status < 0) {
+	/*
+	 * Do this before adding the entry to the directory. We add
+	 * also set d_op after success so that ->d_iput() will cleanup
+	 * the dentry lock even if ocfs2_add_entry() fails below.
+	 */
+	status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno);
+	if (status) {
 		mlog_errno(status);
 		goto bail;
 	}
+	dentry->d_op = &ocfs2_dentry_ops;
 
-	status = ocfs2_dentry_attach_lock(dentry, inode, OCFS2_I(dir)->ip_blkno);
-	if (status) {
+	status = ocfs2_add_entry(handle, dentry, inode,
+				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
+				 &lookup);
+	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
 	}
 
 	insert_inode_hash(inode);
-	dentry->d_op = &ocfs2_dentry_ops;
 	d_instantiate(dentry, inode);
 bail:
 	if (status < 0 && did_quota)
-- 
cgit v1.2.3-18-g5258