From 0c872e2dedfc09f41a5604d1c5010f800c0bd8f1 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:46:29 +0800
Subject: f2fs: move ext_lock out of struct extent_info

Move ext_lock out of struct extent_info, then in the following patches we can
use variables with struct extent_info type as a parameter to pass pure data.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 985ed023a750..0811d6509fce 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -258,9 +258,9 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
 		return 0;
 
-	read_lock(&fi->ext.ext_lock);
+	read_lock(&fi->ext_lock);
 	if (fi->ext.len == 0) {
-		read_unlock(&fi->ext.ext_lock);
+		read_unlock(&fi->ext_lock);
 		return 0;
 	}
 
@@ -284,10 +284,10 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 			bh_result->b_size = UINT_MAX;
 
 		stat_inc_read_hit(inode->i_sb);
-		read_unlock(&fi->ext.ext_lock);
+		read_unlock(&fi->ext_lock);
 		return 1;
 	}
-	read_unlock(&fi->ext.ext_lock);
+	read_unlock(&fi->ext_lock);
 	return 0;
 }
 
@@ -309,7 +309,7 @@ void update_extent_cache(struct dnode_of_data *dn)
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
 							dn->ofs_in_node;
 
-	write_lock(&fi->ext.ext_lock);
+	write_lock(&fi->ext_lock);
 
 	start_fofs = fi->ext.fofs;
 	end_fofs = fi->ext.fofs + fi->ext.len - 1;
@@ -366,7 +366,7 @@ void update_extent_cache(struct dnode_of_data *dn)
 		need_update = true;
 	}
 end_update:
-	write_unlock(&fi->ext.ext_lock);
+	write_unlock(&fi->ext_lock);
 	if (need_update)
 		sync_inode_page(dn);
 	return;
-- 
cgit v1.2.3


From 4d0b0bd4385f0ce8d3b430f9667c5e2ca1de10af Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:47:25 +0800
Subject: f2fs: simplfy a field name in struct f2fs_extent,extent_info

Rename a filed name from 'blk_addr' to 'blk' in struct {f2fs_extent,extent_info}
as annotation of this field descripts its meaning well to us.

By this way, we can avoid long statement in code of following patches.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c          | 13 ++++++-------
 fs/f2fs/f2fs.h          |  6 +++---
 include/linux/f2fs_fs.h |  2 +-
 3 files changed, 10 insertions(+), 11 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0811d6509fce..64f9049a9f25 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -268,7 +268,7 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 
 	start_fofs = fi->ext.fofs;
 	end_fofs = fi->ext.fofs + fi->ext.len - 1;
-	start_blkaddr = fi->ext.blk_addr;
+	start_blkaddr = fi->ext.blk;
 
 	if (pgofs >= start_fofs && pgofs <= end_fofs) {
 		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
@@ -313,8 +313,8 @@ void update_extent_cache(struct dnode_of_data *dn)
 
 	start_fofs = fi->ext.fofs;
 	end_fofs = fi->ext.fofs + fi->ext.len - 1;
-	start_blkaddr = fi->ext.blk_addr;
-	end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1;
+	start_blkaddr = fi->ext.blk;
+	end_blkaddr = fi->ext.blk + fi->ext.len - 1;
 
 	/* Drop and initialize the matched extent */
 	if (fi->ext.len == 1 && fofs == start_fofs)
@@ -324,7 +324,7 @@ void update_extent_cache(struct dnode_of_data *dn)
 	if (fi->ext.len == 0) {
 		if (dn->data_blkaddr != NULL_ADDR) {
 			fi->ext.fofs = fofs;
-			fi->ext.blk_addr = dn->data_blkaddr;
+			fi->ext.blk = dn->data_blkaddr;
 			fi->ext.len = 1;
 		}
 		goto end_update;
@@ -333,7 +333,7 @@ void update_extent_cache(struct dnode_of_data *dn)
 	/* Front merge */
 	if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) {
 		fi->ext.fofs--;
-		fi->ext.blk_addr--;
+		fi->ext.blk--;
 		fi->ext.len++;
 		goto end_update;
 	}
@@ -351,8 +351,7 @@ void update_extent_cache(struct dnode_of_data *dn)
 			fi->ext.len = fofs - start_fofs;
 		} else {
 			fi->ext.fofs = fofs + 1;
-			fi->ext.blk_addr = start_blkaddr +
-					fofs - start_fofs + 1;
+			fi->ext.blk = start_blkaddr + fofs - start_fofs + 1;
 			fi->ext.len -= fofs - start_fofs + 1;
 		}
 	} else {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c3caa3cb5beb..5d2e52e31fac 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -278,7 +278,7 @@ enum {
 
 struct extent_info {
 	unsigned int fofs;	/* start offset in a file */
-	u32 blk_addr;		/* start block address of the extent */
+	u32 blk;		/* start block address of the extent */
 	unsigned int len;	/* length of the extent */
 };
 
@@ -320,7 +320,7 @@ static inline void get_extent_info(struct extent_info *ext,
 					struct f2fs_extent i_ext)
 {
 	ext->fofs = le32_to_cpu(i_ext.fofs);
-	ext->blk_addr = le32_to_cpu(i_ext.blk_addr);
+	ext->blk = le32_to_cpu(i_ext.blk);
 	ext->len = le32_to_cpu(i_ext.len);
 }
 
@@ -328,7 +328,7 @@ static inline void set_raw_extent(struct extent_info *ext,
 					struct f2fs_extent *i_ext)
 {
 	i_ext->fofs = cpu_to_le32(ext->fofs);
-	i_ext->blk_addr = cpu_to_le32(ext->blk_addr);
+	i_ext->blk = cpu_to_le32(ext->blk);
 	i_ext->len = cpu_to_le32(ext->len);
 }
 
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index a23556c32703..502f28cfb78e 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -153,7 +153,7 @@ struct f2fs_orphan_block {
  */
 struct f2fs_extent {
 	__le32 fofs;		/* start file offset of the extent */
-	__le32 blk_addr;	/* start block address of the extent */
+	__le32 blk;		/* start block address of the extent */
 	__le32 len;		/* lengh of the extent */
 } __packed;
 
-- 
cgit v1.2.3


From a2e7d1bfebe0bc349a3eb9d01caac026627f095e Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:50:30 +0800
Subject: f2fs: introduce f2fs_map_bh to clean codes of check_extent_cache

This patch introduces f2fs_map_bh to clean codes of check_extent_cache.

v2:
 o cleanup f2fs_map_bh pointed out by Jaegeuk Kim.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 64f9049a9f25..bce0372a90d4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -248,8 +248,23 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
 	return err;
 }
 
+static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs,
+			struct extent_info *ei, struct buffer_head *bh_result)
+{
+	unsigned int blkbits = sb->s_blocksize_bits;
+	size_t count;
+
+	set_buffer_new(bh_result);
+	map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs);
+	count = ei->fofs + ei->len - pgofs;
+	if (count < (UINT_MAX >> blkbits))
+		bh_result->b_size = (count << blkbits);
+	else
+		bh_result->b_size = UINT_MAX;
+}
+
 static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
-					struct buffer_head *bh_result)
+					struct extent_info *ei)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	pgoff_t start_fofs, end_fofs;
@@ -271,18 +286,7 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 	start_blkaddr = fi->ext.blk;
 
 	if (pgofs >= start_fofs && pgofs <= end_fofs) {
-		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
-		size_t count;
-
-		set_buffer_new(bh_result);
-		map_bh(bh_result, inode->i_sb,
-				start_blkaddr + pgofs - start_fofs);
-		count = end_fofs - pgofs + 1;
-		if (count < (UINT_MAX >> blkbits))
-			bh_result->b_size = (count << blkbits);
-		else
-			bh_result->b_size = UINT_MAX;
-
+		*ei = fi->ext;
 		stat_inc_read_hit(inode->i_sb);
 		read_unlock(&fi->ext_lock);
 		return 1;
@@ -658,13 +662,16 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
 	pgoff_t pgofs, end_offset;
 	int err = 0, ofs = 1;
+	struct extent_info ei;
 	bool allocated = false;
 
 	/* Get the page offset from the block offset(iblock) */
 	pgofs =	(pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
 
-	if (check_extent_cache(inode, pgofs, bh_result))
+	if (check_extent_cache(inode, pgofs, &ei)) {
+		f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result);
 		goto out;
+	}
 
 	if (create)
 		f2fs_lock_op(F2FS_I_SB(inode));
-- 
cgit v1.2.3


From 7e4dde79df7cdf8b40282857e030c7572ff04886 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:51:34 +0800
Subject: f2fs: introduce universal lookup/update interface for extent cache

In this patch, we do these jobs:
1. rename {check,update}_extent_cache to {lookup,update}_extent_info;
2. introduce universal lookup/update interface of extent cache:
f2fs_{lookup,update}_extent_cache including above two real functions, then
export them to function callers.

So after above cleanup, we can add new rb-tree based extent cache into exported
interfaces.

v2:
 o remove "f2fs_" for inner function {lookup,update}_extent_info suggested by
   Jaegeuk Kim.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c     | 66 +++++++++++++++++++++++++++++++++---------------------
 fs/f2fs/f2fs.h     |  2 +-
 fs/f2fs/file.c     |  2 +-
 fs/f2fs/inline.c   |  2 +-
 fs/f2fs/recovery.c |  2 +-
 5 files changed, 44 insertions(+), 30 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index bce0372a90d4..3dbaa475fce4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -263,20 +263,20 @@ static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs,
 		bh_result->b_size = UINT_MAX;
 }
 
-static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
-					struct extent_info *ei)
+static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs,
+							struct extent_info *ei)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 	pgoff_t start_fofs, end_fofs;
 	block_t start_blkaddr;
 
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
-		return 0;
+		return false;
 
 	read_lock(&fi->ext_lock);
 	if (fi->ext.len == 0) {
 		read_unlock(&fi->ext_lock);
-		return 0;
+		return false;
 	}
 
 	stat_inc_total_hit(inode->i_sb);
@@ -289,29 +289,22 @@ static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
 		*ei = fi->ext;
 		stat_inc_read_hit(inode->i_sb);
 		read_unlock(&fi->ext_lock);
-		return 1;
+		return true;
 	}
 	read_unlock(&fi->ext_lock);
-	return 0;
+	return false;
 }
 
-void update_extent_cache(struct dnode_of_data *dn)
+static bool update_extent_info(struct inode *inode, pgoff_t fofs,
+								block_t blkaddr)
 {
-	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
-	pgoff_t fofs, start_fofs, end_fofs;
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	pgoff_t start_fofs, end_fofs;
 	block_t start_blkaddr, end_blkaddr;
 	int need_update = true;
 
-	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
-
-	/* Update the page address in the parent node */
-	__set_data_blkaddr(dn);
-
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
-		return;
-
-	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
-							dn->ofs_in_node;
+		return false;
 
 	write_lock(&fi->ext_lock);
 
@@ -326,16 +319,16 @@ void update_extent_cache(struct dnode_of_data *dn)
 
 	/* Initial extent */
 	if (fi->ext.len == 0) {
-		if (dn->data_blkaddr != NULL_ADDR) {
+		if (blkaddr != NULL_ADDR) {
 			fi->ext.fofs = fofs;
-			fi->ext.blk = dn->data_blkaddr;
+			fi->ext.blk = blkaddr;
 			fi->ext.len = 1;
 		}
 		goto end_update;
 	}
 
 	/* Front merge */
-	if (fofs == start_fofs - 1 && dn->data_blkaddr == start_blkaddr - 1) {
+	if (fofs == start_fofs - 1 && blkaddr == start_blkaddr - 1) {
 		fi->ext.fofs--;
 		fi->ext.blk--;
 		fi->ext.len++;
@@ -343,7 +336,7 @@ void update_extent_cache(struct dnode_of_data *dn)
 	}
 
 	/* Back merge */
-	if (fofs == end_fofs + 1 && dn->data_blkaddr == end_blkaddr + 1) {
+	if (fofs == end_fofs + 1 && blkaddr == end_blkaddr + 1) {
 		fi->ext.len++;
 		goto end_update;
 	}
@@ -370,9 +363,30 @@ void update_extent_cache(struct dnode_of_data *dn)
 	}
 end_update:
 	write_unlock(&fi->ext_lock);
-	if (need_update)
+	return need_update;
+}
+
+static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+							struct extent_info *ei)
+{
+	return lookup_extent_info(inode, pgofs, ei);
+}
+
+void f2fs_update_extent_cache(struct dnode_of_data *dn)
+{
+	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
+	pgoff_t fofs;
+
+	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
+
+	/* Update the page address in the parent node */
+	__set_data_blkaddr(dn);
+
+	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+							dn->ofs_in_node;
+
+	if (update_extent_info(dn->inode, fofs, dn->data_blkaddr))
 		sync_inode_page(dn);
-	return;
 }
 
 struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
@@ -668,7 +682,7 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	/* Get the page offset from the block offset(iblock) */
 	pgofs =	(pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
 
-	if (check_extent_cache(inode, pgofs, &ei)) {
+	if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
 		f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result);
 		goto out;
 	}
@@ -835,7 +849,7 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
 	} else {
 		write_data_page(page, &dn, fio);
-		update_extent_cache(&dn);
+		f2fs_update_extent_cache(&dn);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	}
 out_writepage:
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 5d2e52e31fac..f3fbfa91de8e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1513,7 +1513,7 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-void update_extent_cache(struct dnode_of_data *);
+void f2fs_update_extent_cache(struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 98dac27bc3f7..baadaf2afc6c 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -433,7 +433,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 			continue;
 
 		dn->data_blkaddr = NULL_ADDR;
-		update_extent_cache(dn);
+		f2fs_update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
 		nr_free++;
 	}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 82b74415b623..4ba97320d194 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -122,7 +122,7 @@ no_update:
 	set_page_writeback(page);
 	fio.blk_addr = dn->data_blkaddr;
 	write_data_page(page, dn, &fio);
-	update_extent_cache(dn);
+	f2fs_update_extent_cache(dn);
 	f2fs_wait_on_page_writeback(page, DATA);
 	if (dirty)
 		inode_dec_dirty_pages(dn->inode);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 41afb9534bbd..188a03449c5c 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -401,7 +401,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 			/* write dummy data page */
 			recover_data_page(sbi, NULL, &sum, src, dest);
 			dn.data_blkaddr = dest;
-			update_extent_cache(&dn);
+			f2fs_update_extent_cache(&dn);
 			recovered++;
 		}
 		dn.ofs_in_node++;
-- 
cgit v1.2.3


From 429511cdf8b3a9b894b914f282a9293df405a449 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:54:31 +0800
Subject: f2fs: add core functions for rb-tree extent cache

This patch adds core functions including slab cache init function and
init/lookup/update/shrink/destroy function for rb-tree based extent cache.

Thank Jaegeuk Kim and Changman Lee as they gave much suggestion about detail
design and implementation of extent cache.

Todo:
 * register rb-based extent cache shrink with mm shrink interface.

v2:
 o move set_extent_info and __is_{extent,back,front}_mergeable into f2fs.h.
 o introduce __{attach,detach}_extent_node for code readability.
 o add cond_resched() when fail to invoke kmem_cache_alloc/radix_tree_insert.
 o fix some coding style and typo issues.

v3:
 o fix oops due to using an unassigned pointer.
 o use list_del to remove extent node in shrink list.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Changman Lee <cm224.lee@samsung.com>
[Jaegeuk Kim: add static for some funcitons and declare in f2fs.h]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 411 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/f2fs/f2fs.h |  32 +++++
 fs/f2fs/node.c |   9 +-
 3 files changed, 451 insertions(+), 1 deletion(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 3dbaa475fce4..f52745346205 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -25,6 +25,9 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
+static struct kmem_cache *extent_tree_slab;
+static struct kmem_cache *extent_node_slab;
+
 static void f2fs_read_end_io(struct bio *bio, int err)
 {
 	struct bio_vec *bvec;
@@ -366,6 +369,383 @@ end_update:
 	return need_update;
 }
 
+static struct extent_node *__attach_extent_node(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_info *ei,
+				struct rb_node *parent, struct rb_node **p)
+{
+	struct extent_node *en;
+
+	en = kmem_cache_alloc(extent_node_slab, GFP_ATOMIC);
+	if (!en)
+		return NULL;
+
+	en->ei = *ei;
+	INIT_LIST_HEAD(&en->list);
+
+	rb_link_node(&en->rb_node, parent, p);
+	rb_insert_color(&en->rb_node, &et->root);
+	et->count++;
+	atomic_inc(&sbi->total_ext_node);
+	return en;
+}
+
+static void __detach_extent_node(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_node *en)
+{
+	rb_erase(&en->rb_node, &et->root);
+	et->count--;
+	atomic_dec(&sbi->total_ext_node);
+}
+
+static struct extent_node *__lookup_extent_tree(struct extent_tree *et,
+							unsigned int fofs)
+{
+	struct rb_node *node = et->root.rb_node;
+	struct extent_node *en;
+
+	while (node) {
+		en = rb_entry(node, struct extent_node, rb_node);
+
+		if (fofs < en->ei.fofs)
+			node = node->rb_left;
+		else if (fofs >= en->ei.fofs + en->ei.len)
+			node = node->rb_right;
+		else
+			return en;
+	}
+	return NULL;
+}
+
+static struct extent_node *__try_back_merge(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_node *en)
+{
+	struct extent_node *prev;
+	struct rb_node *node;
+
+	node = rb_prev(&en->rb_node);
+	if (!node)
+		return NULL;
+
+	prev = rb_entry(node, struct extent_node, rb_node);
+	if (__is_back_mergeable(&en->ei, &prev->ei)) {
+		en->ei.fofs = prev->ei.fofs;
+		en->ei.blk = prev->ei.blk;
+		en->ei.len += prev->ei.len;
+		__detach_extent_node(sbi, et, prev);
+		return prev;
+	}
+	return NULL;
+}
+
+static struct extent_node *__try_front_merge(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_node *en)
+{
+	struct extent_node *next;
+	struct rb_node *node;
+
+	node = rb_next(&en->rb_node);
+	if (!node)
+		return NULL;
+
+	next = rb_entry(node, struct extent_node, rb_node);
+	if (__is_front_mergeable(&en->ei, &next->ei)) {
+		en->ei.len += next->ei.len;
+		__detach_extent_node(sbi, et, next);
+		return next;
+	}
+	return NULL;
+}
+
+static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
+				struct extent_tree *et, struct extent_info *ei,
+				struct extent_node **den)
+{
+	struct rb_node **p = &et->root.rb_node;
+	struct rb_node *parent = NULL;
+	struct extent_node *en;
+
+	while (*p) {
+		parent = *p;
+		en = rb_entry(parent, struct extent_node, rb_node);
+
+		if (ei->fofs < en->ei.fofs) {
+			if (__is_front_mergeable(ei, &en->ei)) {
+				f2fs_bug_on(sbi, !den);
+				en->ei.fofs = ei->fofs;
+				en->ei.blk = ei->blk;
+				en->ei.len += ei->len;
+				*den = __try_back_merge(sbi, et, en);
+				return en;
+			}
+			p = &(*p)->rb_left;
+		} else if (ei->fofs >= en->ei.fofs + en->ei.len) {
+			if (__is_back_mergeable(ei, &en->ei)) {
+				f2fs_bug_on(sbi, !den);
+				en->ei.len += ei->len;
+				*den = __try_front_merge(sbi, et, en);
+				return en;
+			}
+			p = &(*p)->rb_right;
+		} else {
+			f2fs_bug_on(sbi, 1);
+		}
+	}
+
+	return __attach_extent_node(sbi, et, ei, parent, p);
+}
+
+static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
+					struct extent_tree *et, bool free_all)
+{
+	struct rb_node *node, *next;
+	struct extent_node *en;
+	unsigned int count = et->count;
+
+	node = rb_first(&et->root);
+	while (node) {
+		next = rb_next(node);
+		en = rb_entry(node, struct extent_node, rb_node);
+
+		if (free_all) {
+			spin_lock(&sbi->extent_lock);
+			if (!list_empty(&en->list))
+				list_del_init(&en->list);
+			spin_unlock(&sbi->extent_lock);
+		}
+
+		if (free_all || list_empty(&en->list)) {
+			__detach_extent_node(sbi, et, en);
+			kmem_cache_free(extent_node_slab, en);
+		}
+		node = next;
+	}
+
+	return count - et->count;
+}
+
+static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
+							struct extent_info *ei)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et;
+	struct extent_node *en;
+
+	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+		return false;
+
+	down_read(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
+	if (!et) {
+		up_read(&sbi->extent_tree_lock);
+		return false;
+	}
+	atomic_inc(&et->refcount);
+	up_read(&sbi->extent_tree_lock);
+
+	read_lock(&et->lock);
+	en = __lookup_extent_tree(et, pgofs);
+	if (en) {
+		*ei = en->ei;
+		spin_lock(&sbi->extent_lock);
+		if (!list_empty(&en->list))
+			list_move_tail(&en->list, &sbi->extent_list);
+		spin_unlock(&sbi->extent_lock);
+		stat_inc_read_hit(sbi->sb);
+	}
+	stat_inc_total_hit(sbi->sb);
+	read_unlock(&et->lock);
+
+	atomic_dec(&et->refcount);
+	return en ? true : false;
+}
+
+static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
+							block_t blkaddr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	nid_t ino = inode->i_ino;
+	struct extent_tree *et;
+	struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL;
+	struct extent_node *den = NULL;
+	struct extent_info ei, dei;
+	unsigned int endofs;
+
+	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+		return;
+
+	down_write(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
+	if (!et) {
+		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
+		f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
+		memset(et, 0, sizeof(struct extent_tree));
+		et->ino = ino;
+		et->root = RB_ROOT;
+		rwlock_init(&et->lock);
+		atomic_set(&et->refcount, 0);
+		et->count = 0;
+		sbi->total_ext_tree++;
+	}
+	atomic_inc(&et->refcount);
+	up_write(&sbi->extent_tree_lock);
+
+	write_lock(&et->lock);
+
+	/* 1. lookup and remove existing extent info in cache */
+	en = __lookup_extent_tree(et, fofs);
+	if (!en)
+		goto update_extent;
+
+	dei = en->ei;
+	__detach_extent_node(sbi, et, en);
+
+	/* 2. if extent can be split more, split and insert the left part */
+	if (dei.len > 1) {
+		/*  insert left part of split extent into cache */
+		if (fofs - dei.fofs >= F2FS_MIN_EXTENT_LEN) {
+			set_extent_info(&ei, dei.fofs, dei.blk,
+							fofs - dei.fofs);
+			en1 = __insert_extent_tree(sbi, et, &ei, NULL);
+		}
+
+		/* insert right part of split extent into cache */
+		endofs = dei.fofs + dei.len - 1;
+		if (endofs - fofs >= F2FS_MIN_EXTENT_LEN) {
+			set_extent_info(&ei, fofs + 1,
+				fofs - dei.fofs + dei.blk, endofs - fofs);
+			en2 = __insert_extent_tree(sbi, et, &ei, NULL);
+		}
+	}
+
+update_extent:
+	/* 3. update extent in extent cache */
+	if (blkaddr) {
+		set_extent_info(&ei, fofs, blkaddr, 1);
+		en3 = __insert_extent_tree(sbi, et, &ei, &den);
+	}
+
+	/* 4. update in global extent list */
+	spin_lock(&sbi->extent_lock);
+	if (en && !list_empty(&en->list))
+		list_del(&en->list);
+	/*
+	 * en1 and en2 split from en, they will become more and more smaller
+	 * fragments after splitting several times. So if the length is smaller
+	 * than F2FS_MIN_EXTENT_LEN, we will not add them into extent tree.
+	 */
+	if (en1)
+		list_add_tail(&en1->list, &sbi->extent_list);
+	if (en2)
+		list_add_tail(&en2->list, &sbi->extent_list);
+	if (en3) {
+		if (list_empty(&en3->list))
+			list_add_tail(&en3->list, &sbi->extent_list);
+		else
+			list_move_tail(&en3->list, &sbi->extent_list);
+	}
+	if (den && !list_empty(&den->list))
+		list_del(&den->list);
+	spin_unlock(&sbi->extent_lock);
+
+	/* 5. release extent node */
+	if (en)
+		kmem_cache_free(extent_node_slab, en);
+	if (den)
+		kmem_cache_free(extent_node_slab, den);
+
+	write_unlock(&et->lock);
+	atomic_dec(&et->refcount);
+}
+
+void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
+{
+	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
+	struct extent_node *en, *tmp;
+	unsigned long ino = F2FS_ROOT_INO(sbi);
+	struct radix_tree_iter iter;
+	void **slot;
+	unsigned int found;
+
+	if (available_free_memory(sbi, EXTENT_CACHE))
+		return;
+
+	spin_lock(&sbi->extent_lock);
+	list_for_each_entry_safe(en, tmp, &sbi->extent_list, list) {
+		if (!nr_shrink--)
+			break;
+		list_del_init(&en->list);
+	}
+	spin_unlock(&sbi->extent_lock);
+
+	down_read(&sbi->extent_tree_lock);
+	while ((found = radix_tree_gang_lookup(&sbi->extent_tree_root,
+				(void **)treevec, ino, EXT_TREE_VEC_SIZE))) {
+		unsigned i;
+
+		ino = treevec[found - 1]->ino + 1;
+		for (i = 0; i < found; i++) {
+			struct extent_tree *et = treevec[i];
+
+			atomic_inc(&et->refcount);
+			write_lock(&et->lock);
+			__free_extent_tree(sbi, et, false);
+			write_unlock(&et->lock);
+			atomic_dec(&et->refcount);
+		}
+	}
+	up_read(&sbi->extent_tree_lock);
+
+	down_write(&sbi->extent_tree_lock);
+	radix_tree_for_each_slot(slot, &sbi->extent_tree_root, &iter,
+							F2FS_ROOT_INO(sbi)) {
+		struct extent_tree *et = (struct extent_tree *)*slot;
+
+		if (!atomic_read(&et->refcount) && !et->count) {
+			radix_tree_delete(&sbi->extent_tree_root, et->ino);
+			kmem_cache_free(extent_tree_slab, et);
+			sbi->total_ext_tree--;
+		}
+	}
+	up_write(&sbi->extent_tree_lock);
+}
+
+void f2fs_destroy_extent_tree(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et;
+
+	down_read(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
+	if (!et) {
+		up_read(&sbi->extent_tree_lock);
+		goto out;
+	}
+	atomic_inc(&et->refcount);
+	up_read(&sbi->extent_tree_lock);
+
+	/* free all extent info belong to this extent tree */
+	write_lock(&et->lock);
+	__free_extent_tree(sbi, et, true);
+	write_unlock(&et->lock);
+
+	atomic_dec(&et->refcount);
+
+	/* try to find and delete extent tree entry in radix tree */
+	down_write(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
+	if (!et) {
+		up_write(&sbi->extent_tree_lock);
+		goto out;
+	}
+	f2fs_bug_on(sbi, atomic_read(&et->refcount) || et->count);
+	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
+	kmem_cache_free(extent_tree_slab, et);
+	sbi->total_ext_tree--;
+	up_write(&sbi->extent_tree_lock);
+out:
+	return;
+}
+
 static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
@@ -1256,6 +1636,37 @@ static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, get_data_block);
 }
 
+void init_extent_cache_info(struct f2fs_sb_info *sbi)
+{
+	INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
+	init_rwsem(&sbi->extent_tree_lock);
+	INIT_LIST_HEAD(&sbi->extent_list);
+	spin_lock_init(&sbi->extent_lock);
+	sbi->total_ext_tree = 0;
+	atomic_set(&sbi->total_ext_node, 0);
+}
+
+int __init create_extent_cache(void)
+{
+	extent_tree_slab = f2fs_kmem_cache_create("f2fs_extent_tree",
+			sizeof(struct extent_tree));
+	if (!extent_tree_slab)
+		return -ENOMEM;
+	extent_node_slab = f2fs_kmem_cache_create("f2fs_extent_node",
+			sizeof(struct extent_node));
+	if (!extent_node_slab) {
+		kmem_cache_destroy(extent_tree_slab);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void destroy_extent_cache(void)
+{
+	kmem_cache_destroy(extent_node_slab);
+	kmem_cache_destroy(extent_tree_slab);
+}
+
 const struct address_space_operations f2fs_dblock_aops = {
 	.readpage	= f2fs_read_data_page,
 	.readpages	= f2fs_read_data_pages,
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index a214cce9fe70..a0af10dad871 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -352,6 +352,33 @@ static inline void set_raw_extent(struct extent_info *ext,
 	i_ext->len = cpu_to_le32(ext->len);
 }
 
+static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
+						u32 blk, unsigned int len)
+{
+	ei->fofs = fofs;
+	ei->blk = blk;
+	ei->len = len;
+}
+
+static inline bool __is_extent_mergeable(struct extent_info *back,
+						struct extent_info *front)
+{
+	return (back->fofs + back->len == front->fofs &&
+			back->blk + back->len == front->blk);
+}
+
+static inline bool __is_back_mergeable(struct extent_info *cur,
+						struct extent_info *back)
+{
+	return __is_extent_mergeable(back, cur);
+}
+
+static inline bool __is_front_mergeable(struct extent_info *cur,
+						struct extent_info *front)
+{
+	return __is_extent_mergeable(cur, front);
+}
+
 struct f2fs_nm_info {
 	block_t nat_blkaddr;		/* base disk address of NAT */
 	nid_t max_nid;			/* maximum possible node ids */
@@ -1541,12 +1568,17 @@ void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
+void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
+void f2fs_destroy_extent_tree(struct inode *);
 void f2fs_update_extent_cache(struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
 int do_write_data_page(struct page *, struct f2fs_io_info *);
 int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
+void init_extent_cache_info(struct f2fs_sb_info *);
+int __init create_extent_cache(void);
+void destroy_extent_cache(void);
 void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
 int f2fs_release_page(struct page *, gfp_t);
 
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 97bd9d3db882..28423697e97a 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -41,7 +41,9 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 	/* only uses low memory */
 	avail_ram = val.totalram - val.totalhigh;
 
-	/* give 25%, 25%, 50%, 50% memory for each components respectively */
+	/*
+	 * give 25%, 25%, 50%, 50%, 50% memory for each components respectively
+	 */
 	if (type == FREE_NIDS) {
 		mem_size = (nm_i->fcnt * sizeof(struct free_nid)) >>
 							PAGE_CACHE_SHIFT;
@@ -62,6 +64,11 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 			mem_size += (sbi->im[i].ino_num *
 				sizeof(struct ino_entry)) >> PAGE_CACHE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
+	} else if (type == EXTENT_CACHE) {
+		mem_size = (sbi->total_ext_tree * sizeof(struct extent_tree) +
+				atomic_read(&sbi->total_ext_node) *
+				sizeof(struct extent_node)) >> PAGE_CACHE_SHIFT;
+		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else {
 		if (sbi->sb->s_bdi->dirty_exceeded)
 			return false;
-- 
cgit v1.2.3


From 1dcc336b02bff3d38f173feac55a2b6c25a5fb54 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:57:31 +0800
Subject: f2fs: enable rb-tree extent cache

This patch enables rb-tree based extent cache in f2fs.

When we mount with "-o extent_cache", f2fs will try to add recently accessed
page-block mappings into rb-tree based extent cache as much as possible, instead
of original one extent info cache.

By this way, f2fs can support more effective cache between dnode page cache and
disk. It will supply high hit ratio in the cache with fewer memory when dnode
page cache are reclaimed in environment of low memory.

Storage: Sandisk sd card 64g
1.append write file (offset: 0, size: 128M);
2.override write file (offset: 2M, size: 1M);
3.override write file (offset: 4M, size: 1M);
...
4.override write file (offset: 48M, size: 1M);
...
5.override write file (offset: 112M, size: 1M);
6.sync
7.echo 3 > /proc/sys/vm/drop_caches
8.read file (size:128M, unit: 4k, count: 32768)
(time dd if=/mnt/f2fs/128m bs=4k count=32768)

Extent Hit Ratio:
		before		patched
Hit Ratio	121 / 1071	1071 / 1071

Performance:
		before		patched
real    	0m37.051s	0m35.556s
user    	0m0.040s	0m0.026s
sys     	0m2.990s	0m2.251s

Memory Cost:
		before		patched
Tree Count:	0		1 (size: 24 bytes)
Node Count:	0		45 (size: 1440 bytes)

v3:
 o retest and given more details of test result.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c    | 13 +++++++++++++
 fs/f2fs/inode.c   |  1 +
 fs/f2fs/segment.c |  3 +++
 fs/f2fs/super.c   |  9 ++++++++-
 4 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f52745346205..acdc0767f77c 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -666,6 +666,9 @@ void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	void **slot;
 	unsigned int found;
 
+	if (!test_opt(sbi, EXTENT_CACHE))
+		return;
+
 	if (available_free_memory(sbi, EXTENT_CACHE))
 		return;
 
@@ -714,6 +717,9 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et;
 
+	if (!test_opt(sbi, EXTENT_CACHE))
+		return;
+
 	down_read(&sbi->extent_tree_lock);
 	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
 	if (!et) {
@@ -749,6 +755,9 @@ out:
 static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
+	if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
+		return f2fs_lookup_extent_tree(inode, pgofs, ei);
+
 	return lookup_extent_info(inode, pgofs, ei);
 }
 
@@ -765,6 +774,10 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
 							dn->ofs_in_node;
 
+	if (test_opt(F2FS_I_SB(dn->inode), EXTENT_CACHE))
+		return f2fs_update_extent_tree(dn->inode, fofs,
+							dn->data_blkaddr);
+
 	if (update_extent_info(dn->inode, fofs, dn->data_blkaddr))
 		sync_inode_page(dn);
 }
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 28dd26a50276..b5087443be41 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -335,6 +335,7 @@ void f2fs_evict_inode(struct inode *inode)
 no_delete:
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
+	f2fs_destroy_extent_tree(inode);
 	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index daee4ab913da..29c04edcb843 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -277,6 +277,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi)
 
 void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 {
+	/* try to shrink extent cache when there is no enough memory */
+	f2fs_shrink_extent_tree(sbi, EXTENT_CACHE_SHRINK_NUMBER);
+
 	/* check the # of cached NAT entries and prefree segments */
 	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK) ||
 			excess_prefree_segs(sbi) ||
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3ce4d7c9a29d..e649f21121d2 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1079,6 +1079,8 @@ try_onemore:
 	INIT_LIST_HEAD(&sbi->dir_inode_list);
 	spin_lock_init(&sbi->dir_inode_lock);
 
+	init_extent_cache_info(sbi);
+
 	init_ino_entry_info(sbi);
 
 	/* setup f2fs internal modules */
@@ -1285,10 +1287,13 @@ static int __init init_f2fs_fs(void)
 	err = create_checkpoint_caches();
 	if (err)
 		goto free_segment_manager_caches;
+	err = create_extent_cache();
+	if (err)
+		goto free_checkpoint_caches;
 	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
 	if (!f2fs_kset) {
 		err = -ENOMEM;
-		goto free_checkpoint_caches;
+		goto free_extent_cache;
 	}
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
@@ -1299,6 +1304,8 @@ static int __init init_f2fs_fs(void)
 
 free_kset:
 	kset_unregister(f2fs_kset);
+free_extent_cache:
+	destroy_extent_cache();
 free_checkpoint_caches:
 	destroy_checkpoint_caches();
 free_segment_manager_caches:
-- 
cgit v1.2.3


From 1ec4610c522cc51219cc022ef120a928828fa934 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 17:59:59 +0800
Subject: f2fs: add trace for rb-tree extent cache ops

This patch adds trace for lookup/update/shrink/destroy ops in rb-tree extent cache.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c              |  16 +++++-
 include/trace/events/f2fs.h | 134 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 148 insertions(+), 2 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index acdc0767f77c..d7ff4ca5be18 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -533,6 +533,8 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
 		return false;
 
+	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
+
 	down_read(&sbi->extent_tree_lock);
 	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
 	if (!et) {
@@ -555,6 +557,8 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	stat_inc_total_hit(sbi->sb);
 	read_unlock(&et->lock);
 
+	trace_f2fs_lookup_extent_tree_end(inode, pgofs, en);
+
 	atomic_dec(&et->refcount);
 	return en ? true : false;
 }
@@ -573,6 +577,8 @@ static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
 	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
 		return;
 
+	trace_f2fs_update_extent_tree(inode, fofs, blkaddr);
+
 	down_write(&sbi->extent_tree_lock);
 	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
 	if (!et) {
@@ -665,6 +671,7 @@ void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	struct radix_tree_iter iter;
 	void **slot;
 	unsigned int found;
+	unsigned int node_cnt = 0, tree_cnt = 0;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return;
@@ -691,7 +698,7 @@ void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 
 			atomic_inc(&et->refcount);
 			write_lock(&et->lock);
-			__free_extent_tree(sbi, et, false);
+			node_cnt += __free_extent_tree(sbi, et, false);
 			write_unlock(&et->lock);
 			atomic_dec(&et->refcount);
 		}
@@ -707,15 +714,19 @@ void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 			radix_tree_delete(&sbi->extent_tree_root, et->ino);
 			kmem_cache_free(extent_tree_slab, et);
 			sbi->total_ext_tree--;
+			tree_cnt++;
 		}
 	}
 	up_write(&sbi->extent_tree_lock);
+
+	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
 }
 
 void f2fs_destroy_extent_tree(struct inode *inode)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et;
+	unsigned int node_cnt = 0;
 
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return;
@@ -731,7 +742,7 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 
 	/* free all extent info belong to this extent tree */
 	write_lock(&et->lock);
-	__free_extent_tree(sbi, et, true);
+	node_cnt = __free_extent_tree(sbi, et, true);
 	write_unlock(&et->lock);
 
 	atomic_dec(&et->refcount);
@@ -749,6 +760,7 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	sbi->total_ext_tree--;
 	up_write(&sbi->extent_tree_lock);
 out:
+	trace_f2fs_destroy_extent_tree(inode, node_cnt);
 	return;
 }
 
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 5422dbfaf97d..09a56dc75f8d 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -1011,6 +1011,140 @@ TRACE_EVENT(f2fs_issue_flush,
 		__entry->nobarrier ? "skip (nobarrier)" : "issue",
 		__entry->flush_merge ? " with flush_merge" : "")
 );
+
+TRACE_EVENT(f2fs_lookup_extent_tree_start,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs),
+
+	TP_ARGS(inode, pgofs),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u",
+		show_dev_ino(__entry),
+		__entry->pgofs)
+);
+
+TRACE_EVENT_CONDITION(f2fs_lookup_extent_tree_end,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs,
+						struct extent_node *en),
+
+	TP_ARGS(inode, pgofs, en),
+
+	TP_CONDITION(en),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+		__field(unsigned int, fofs)
+		__field(u32, blk)
+		__field(unsigned int, len)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+		__entry->fofs = en->ei.fofs;
+		__entry->blk = en->ei.blk;
+		__entry->len = en->ei.len;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, "
+		"ext_info(fofs: %u, blk: %u, len: %u)",
+		show_dev_ino(__entry),
+		__entry->pgofs,
+		__entry->fofs,
+		__entry->blk,
+		__entry->len)
+);
+
+TRACE_EVENT(f2fs_update_extent_tree,
+
+	TP_PROTO(struct inode *inode, unsigned int pgofs, block_t blkaddr),
+
+	TP_ARGS(inode, pgofs, blkaddr),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, pgofs)
+		__field(u32, blk)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->pgofs = pgofs;
+		__entry->blk = blkaddr;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, pgofs = %u, blkaddr = %u",
+		show_dev_ino(__entry),
+		__entry->pgofs,
+		__entry->blk)
+);
+
+TRACE_EVENT(f2fs_shrink_extent_tree,
+
+	TP_PROTO(struct f2fs_sb_info *sbi, unsigned int node_cnt,
+						unsigned int tree_cnt),
+
+	TP_ARGS(sbi, node_cnt, tree_cnt),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(unsigned int, node_cnt)
+		__field(unsigned int, tree_cnt)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sbi->sb->s_dev;
+		__entry->node_cnt = node_cnt;
+		__entry->tree_cnt = tree_cnt;
+	),
+
+	TP_printk("dev = (%d,%d), shrunk: node_cnt = %u, tree_cnt = %u",
+		show_dev(__entry),
+		__entry->node_cnt,
+		__entry->tree_cnt)
+);
+
+TRACE_EVENT(f2fs_destroy_extent_tree,
+
+	TP_PROTO(struct inode *inode, unsigned int node_cnt),
+
+	TP_ARGS(inode, node_cnt),
+
+	TP_STRUCT__entry(
+		__field(dev_t,	dev)
+		__field(ino_t,	ino)
+		__field(unsigned int, node_cnt)
+	),
+
+	TP_fast_assign(
+		__entry->dev = inode->i_sb->s_dev;
+		__entry->ino = inode->i_ino;
+		__entry->node_cnt = node_cnt;
+	),
+
+	TP_printk("dev = (%d,%d), ino = %lu, destroyed: node_cnt = %u",
+		show_dev_ino(__entry),
+		__entry->node_cnt)
+);
+
 #endif /* _TRACE_F2FS_H */
 
  /* This part must be outside protection */
-- 
cgit v1.2.3


From 62c8af651b37490c18a42c02586fa6a4fb39320a Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 18:01:39 +0800
Subject: f2fs: support fast lookup in extent cache

This patch adds a fast lookup path for rb-tree extent cache.

In this patch we add a recently accessed extent node pointer 'cached_en' in
extent tree. In lookup path of extent cache, we will firstly lookup the last
accessed extent node which cached_en points, if we do not hit in this node,
we will try to lookup extent node in rb-tree.

By this way we can avoid unnecessary slow lookup in rb-tree sometimes.

Note that, side-effect of this patch is that we will increase memory cost,
because we will store a pointer variable in each struct extent tree
additionally.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 19 ++++++++++++++++---
 fs/f2fs/f2fs.h |  1 +
 2 files changed, 17 insertions(+), 3 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index d7ff4ca5be18..08a71ae3ab8d 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -395,6 +395,9 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 	rb_erase(&en->rb_node, &et->root);
 	et->count--;
 	atomic_dec(&sbi->total_ext_node);
+
+	if (et->cached_en == en)
+		et->cached_en = NULL;
 }
 
 static struct extent_node *__lookup_extent_tree(struct extent_tree *et,
@@ -403,15 +406,24 @@ static struct extent_node *__lookup_extent_tree(struct extent_tree *et,
 	struct rb_node *node = et->root.rb_node;
 	struct extent_node *en;
 
+	if (et->cached_en) {
+		struct extent_info *cei = &et->cached_en->ei;
+
+		if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
+			return et->cached_en;
+	}
+
 	while (node) {
 		en = rb_entry(node, struct extent_node, rb_node);
 
-		if (fofs < en->ei.fofs)
+		if (fofs < en->ei.fofs) {
 			node = node->rb_left;
-		else if (fofs >= en->ei.fofs + en->ei.len)
+		} else if (fofs >= en->ei.fofs + en->ei.len) {
 			node = node->rb_right;
-		else
+		} else {
+			et->cached_en = en;
 			return en;
+		}
 	}
 	return NULL;
 }
@@ -587,6 +599,7 @@ static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
 		memset(et, 0, sizeof(struct extent_tree));
 		et->ino = ino;
 		et->root = RB_ROOT;
+		et->cached_en = NULL;
 		rwlock_init(&et->lock);
 		atomic_set(&et->refcount, 0);
 		et->count = 0;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 85ce9b30b539..08fc7e0d5e4a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -298,6 +298,7 @@ struct extent_node {
 struct extent_tree {
 	nid_t ino;			/* inode number */
 	struct rb_root root;		/* root of extent info rb-tree */
+	struct extent_node *cached_en;	/* recently accessed extent node */
 	rwlock_t lock;			/* protect extent info rb-tree */
 	atomic_t refcount;		/* reference count of rb-tree */
 	unsigned int count;		/* # of extent node in rb-tree*/
-- 
cgit v1.2.3


From 91c5d9bce7fef638add2cd36676e157354784d0f Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 18:02:44 +0800
Subject: f2fs: switch to check FI_NO_EXTENT in
 f2fs_{lookup,update}_extent_cache

This patch switch to check FI_NO_EXTENT in f2fs_{lookup,update}_extent_cache
instead of f2fs_{lookup,update}_extent_tree or {lookup,update}_extent_info.

No functionality modification in this patch.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 08a71ae3ab8d..ad99b7a295b4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -273,9 +273,6 @@ static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs,
 	pgoff_t start_fofs, end_fofs;
 	block_t start_blkaddr;
 
-	if (is_inode_flag_set(fi, FI_NO_EXTENT))
-		return false;
-
 	read_lock(&fi->ext_lock);
 	if (fi->ext.len == 0) {
 		read_unlock(&fi->ext_lock);
@@ -306,9 +303,6 @@ static bool update_extent_info(struct inode *inode, pgoff_t fofs,
 	block_t start_blkaddr, end_blkaddr;
 	int need_update = true;
 
-	if (is_inode_flag_set(fi, FI_NO_EXTENT))
-		return false;
-
 	write_lock(&fi->ext_lock);
 
 	start_fofs = fi->ext.fofs;
@@ -542,9 +536,6 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 	struct extent_tree *et;
 	struct extent_node *en;
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
-		return false;
-
 	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
 
 	down_read(&sbi->extent_tree_lock);
@@ -586,9 +577,6 @@ static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
 	struct extent_info ei, dei;
 	unsigned int endofs;
 
-	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
-		return;
-
 	trace_f2fs_update_extent_tree(inode, fofs, blkaddr);
 
 	down_write(&sbi->extent_tree_lock);
@@ -780,6 +768,9 @@ out:
 static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
+	if (is_inode_flag_set(F2FS_I(inode), FI_NO_EXTENT))
+		return false;
+
 	if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
 		return f2fs_lookup_extent_tree(inode, pgofs, ei);
 
@@ -796,6 +787,9 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
 	/* Update the page address in the parent node */
 	__set_data_blkaddr(dn);
 
+	if (is_inode_flag_set(fi, FI_NO_EXTENT))
+		return;
+
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
 							dn->ofs_in_node;
 
-- 
cgit v1.2.3


From cb3bc9ee06f708f3b615b6ce119b907d6a4c8a5d Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 5 Feb 2015 18:03:40 +0800
Subject: f2fs: use extent cache for dir

We update extent cache for all user inode of f2fs including dir inode, so this
patch gives another chance to try to get physical address of page from extent
cache for dir inode.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ad99b7a295b4..ae5c41444e8f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -806,6 +806,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
 	struct page *page;
+	struct extent_info ei;
 	int err;
 	struct f2fs_io_info fio = {
 		.type = DATA,
@@ -817,6 +818,11 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 		return page;
 	f2fs_put_page(page, 0);
 
+	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+		dn.data_blkaddr = ei.blk + index - ei.fofs;
+		goto got_it;
+	}
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 	if (err)
@@ -830,6 +836,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	if (unlikely(dn.data_blkaddr == NEW_ADDR))
 		return ERR_PTR(-EINVAL);
 
+got_it:
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
@@ -864,6 +871,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
 	struct page *page;
+	struct extent_info ei;
 	int err;
 	struct f2fs_io_info fio = {
 		.type = DATA,
@@ -874,6 +882,11 @@ repeat:
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
+	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
+		dn.data_blkaddr = ei.blk + index - ei.fofs;
+		goto got_it;
+	}
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 	if (err) {
@@ -887,6 +900,7 @@ repeat:
 		return ERR_PTR(-ENOENT);
 	}
 
+got_it:
 	if (PageUptodate(page))
 		return page;
 
-- 
cgit v1.2.3


From e2e40f2c1ed433c5e224525c8c862fd32e5d3df2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 22 Feb 2015 08:58:50 -0800
Subject: fs: move struct kiocb to fs.h

struct kiocb now is a generic I/O container, so move it to fs.h.
Also do a #include diet for aio.h while we're at it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/s390/hypfs/inode.c                      |  2 +-
 drivers/char/mem.c                           |  2 +-
 drivers/char/tile-srom.c                     |  1 -
 drivers/infiniband/hw/ipath/ipath_file_ops.c |  1 -
 drivers/infiniband/hw/qib/qib_file_ops.c     |  1 -
 drivers/misc/mei/amthif.c                    |  1 -
 drivers/misc/mei/main.c                      |  1 -
 drivers/misc/mei/pci-me.c                    |  1 -
 drivers/scsi/sg.c                            |  2 +-
 drivers/staging/unisys/include/timskmod.h    |  1 -
 drivers/usb/gadget/function/f_fs.c           |  1 +
 drivers/usb/gadget/legacy/inode.c            |  1 +
 fs/9p/vfs_addr.c                             |  2 +-
 fs/affs/file.c                               |  2 +-
 fs/afs/write.c                               |  1 -
 fs/bfs/inode.c                               |  1 +
 fs/block_dev.c                               |  1 -
 fs/btrfs/file.c                              |  2 +-
 fs/btrfs/inode.c                             |  2 +-
 fs/ceph/file.c                               |  1 -
 fs/direct-io.c                               |  1 -
 fs/ecryptfs/file.c                           |  1 -
 fs/ext2/inode.c                              |  2 +-
 fs/ext3/inode.c                              |  2 +-
 fs/ext4/file.c                               |  2 +-
 fs/ext4/indirect.c                           |  2 +-
 fs/ext4/inode.c                              |  1 -
 fs/ext4/page-io.c                            |  1 -
 fs/f2fs/data.c                               |  2 +-
 fs/fat/inode.c                               |  1 -
 fs/fuse/cuse.c                               |  2 +-
 fs/fuse/dev.c                                |  1 -
 fs/fuse/file.c                               |  2 +-
 fs/gfs2/aops.c                               |  2 +-
 fs/gfs2/file.c                               |  1 -
 fs/hfs/inode.c                               |  2 +-
 fs/hfsplus/inode.c                           |  2 +-
 fs/jfs/inode.c                               |  2 +-
 fs/nfs/file.c                                |  1 -
 fs/nilfs2/inode.c                            |  2 +-
 fs/ntfs/file.c                               |  1 -
 fs/ntfs/inode.c                              |  1 -
 fs/ocfs2/aops.c                              |  1 +
 fs/ocfs2/aops.h                              |  2 +-
 fs/pipe.c                                    |  1 -
 fs/read_write.c                              |  1 -
 fs/reiserfs/inode.c                          |  2 +-
 fs/splice.c                                  |  1 -
 fs/ubifs/file.c                              |  1 -
 fs/udf/file.c                                |  2 +-
 fs/udf/inode.c                               |  2 +-
 fs/xfs/xfs_aops.c                            |  1 -
 fs/xfs/xfs_file.c                            |  1 -
 include/linux/aio.h                          | 31 +---------------------------
 include/linux/fs.h                           | 22 ++++++++++++++++++++
 include/net/sock.h                           |  1 -
 kernel/printk/printk.c                       |  2 +-
 kernel/sysctl.c                              |  1 +
 mm/filemap.c                                 |  1 -
 mm/page_io.c                                 |  2 +-
 mm/shmem.c                                   |  2 +-
 net/ipv4/raw.c                               |  1 -
 sound/core/pcm_native.c                      |  2 +-
 63 files changed, 55 insertions(+), 86 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 4c8008dd938e..ad66b07f742e 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -21,7 +21,7 @@
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include <asm/ebcdic.h>
 #include "hypfs.h"
 
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 297110c12635..9c4fd7a8e2e5 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -26,7 +26,7 @@
 #include <linux/pfn.h>
 #include <linux/export.h>
 #include <linux/io.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include <linux/uaccess.h>
 
diff --git a/drivers/char/tile-srom.c b/drivers/char/tile-srom.c
index 02e76ac6d282..69f6b4acc377 100644
--- a/drivers/char/tile-srom.c
+++ b/drivers/char/tile-srom.c
@@ -27,7 +27,6 @@
 #include <linux/types.h>	/* size_t */
 #include <linux/proc_fs.h>
 #include <linux/fcntl.h>	/* O_ACCMODE */
-#include <linux/aio.h>
 #include <linux/pagemap.h>
 #include <linux/hugetlb.h>
 #include <linux/uaccess.h>
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index 6d7f453b4d05..aed8afee56da 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -40,7 +40,6 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
-#include <linux/aio.h>
 #include <linux/jiffies.h>
 #include <linux/cpu.h>
 #include <asm/pgtable.h>
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index b15e34eeef68..826c17ee4c7d 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -39,7 +39,6 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
-#include <linux/aio.h>
 #include <linux/jiffies.h>
 #include <asm/pgtable.h>
 #include <linux/delay.h>
diff --git a/drivers/misc/mei/amthif.c b/drivers/misc/mei/amthif.c
index c4cb9a984a5f..40ea639fa413 100644
--- a/drivers/misc/mei/amthif.c
+++ b/drivers/misc/mei/amthif.c
@@ -19,7 +19,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/ioctl.h>
 #include <linux/cdev.h>
 #include <linux/list.h>
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 3c019c0e60eb..47680c84801c 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -22,7 +22,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/poll.h>
 #include <linux/init.h>
 #include <linux/ioctl.h>
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index bd3039ab8f98..af44ee26075d 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -21,7 +21,6 @@
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/pci.h>
 #include <linux/poll.h>
 #include <linux/ioctl.h>
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 0cbc1fb45f10..c78a6f7bbc20 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -33,7 +33,6 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 #include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/mm.h>
-#include <linux/aio.h>
 #include <linux/errno.h>
 #include <linux/mtio.h>
 #include <linux/ioctl.h>
@@ -51,6 +50,7 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 #include <linux/ratelimit.h>
+#include <linux/uio.h>
 
 #include "scsi.h"
 #include <scsi/scsi_dbg.h>
diff --git a/drivers/staging/unisys/include/timskmod.h b/drivers/staging/unisys/include/timskmod.h
index 4019a0d63645..52648d4d9922 100644
--- a/drivers/staging/unisys/include/timskmod.h
+++ b/drivers/staging/unisys/include/timskmod.h
@@ -46,7 +46,6 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 #include <linux/workqueue.h>
 #include <linux/kthread.h>
 #include <linux/seq_file.h>
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index b64538b498dc..a12315a78248 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -23,6 +23,7 @@
 #include <linux/export.h>
 #include <linux/hid.h>
 #include <linux/module.h>
+#include <linux/uio.h>
 #include <asm/unaligned.h>
 
 #include <linux/usb/composite.h>
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index a4a80694f607..662ef2c1c62b 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -26,6 +26,7 @@
 #include <linux/poll.h>
 #include <linux/mmu_context.h>
 #include <linux/aio.h>
+#include <linux/uio.h>
 
 #include <linux/device.h>
 #include <linux/moduleparam.h>
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index eb14e055ea83..ff1a5bac4200 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -33,7 +33,7 @@
 #include <linux/pagemap.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 
diff --git a/fs/affs/file.c b/fs/affs/file.c
index d2468bf95669..33eaa67bb026 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -12,7 +12,7 @@
  *  affs regular file handling primitives
  */
 
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "affs.h"
 
 static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c13cb08964ed..0714abcd7f32 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -14,7 +14,6 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/pagevec.h>
-#include <linux/aio.h>
 #include "internal.h"
 
 static int afs_write_back_from_locked_page(struct afs_writeback *wb,
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 90bc079d9982..fdcb4d69f430 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -15,6 +15,7 @@
 #include <linux/buffer_head.h>
 #include <linux/vfs.h>
 #include <linux/writeback.h>
+#include <linux/uio.h>
 #include <asm/uaccess.h>
 #include "bfs.h"
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 975266be67d3..2e522aed6584 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -27,7 +27,6 @@
 #include <linux/namei.h>
 #include <linux/log2.h>
 #include <linux/cleancache.h>
-#include <linux/aio.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b78bbbac900d..69c9508d2c7e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,7 +24,6 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
-#include <linux/aio.h>
 #include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
@@ -32,6 +31,7 @@
 #include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/btrfs.h>
+#include <linux/uio.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 54bcf639d1cf..b214ab178f3a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -32,7 +32,6 @@
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
-#include <linux/aio.h>
 #include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
@@ -43,6 +42,7 @@
 #include <linux/btrfs.h>
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
+#include <linux/uio.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 081c4e3f9e49..98e257c1b5b1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -7,7 +7,6 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
 #include <linux/falloc.h>
 
 #include "super.h"
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c38b460776e6..6fb00e3f1059 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -37,7 +37,6 @@
 #include <linux/uio.h>
 #include <linux/atomic.h>
 #include <linux/prefetch.h>
-#include <linux/aio.h>
 
 /*
  * How many user pages to map in one call to get_user_pages().  This determines
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index a36da8841e0c..273d36e3f0c0 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -31,7 +31,6 @@
 #include <linux/security.h>
 #include <linux/compat.h>
 #include <linux/fs_stack.h>
-#include <linux/aio.h>
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 6434bc000125..df9d6afbc5d5 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -31,7 +31,7 @@
 #include <linux/mpage.h>
 #include <linux/fiemap.h>
 #include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xattr.h"
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 2c6ccc49ba27..db07ffbe7c85 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -27,7 +27,7 @@
 #include <linux/writeback.h>
 #include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "ext3.h"
 #include "xattr.h"
 #include "acl.h"
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 33a09da16c9c..598abbbe6786 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -23,9 +23,9 @@
 #include <linux/jbd2.h>
 #include <linux/mount.h>
 #include <linux/path.h>
-#include <linux/aio.h>
 #include <linux/quotaops.h>
 #include <linux/pagevec.h>
+#include <linux/uio.h>
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "xattr.h"
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 6b9878a24182..8611640856d3 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -20,9 +20,9 @@
  *	(sct@redhat.com), 1993, 1998
  */
 
-#include <linux/aio.h>
 #include "ext4_jbd2.h"
 #include "truncate.h"
+#include <linux/uio.h>
 
 #include <trace/events/ext4.h>
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 85404f15e53a..6325d2c1a65c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -37,7 +37,6 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
-#include <linux/aio.h>
 #include <linux/bitops.h>
 
 #include "ext4_jbd2.h"
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index b24a2541a9ba..464984261e69 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -18,7 +18,6 @@
 #include <linux/pagevec.h>
 #include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/aio.h>
 #include <linux/uio.h>
 #include <linux/bio.h>
 #include <linux/workqueue.h>
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 985ed023a750..497f8515d205 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -12,12 +12,12 @@
 #include <linux/f2fs_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/mpage.h>
-#include <linux/aio.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/prefetch.h>
+#include <linux/uio.h>
 
 #include "f2fs.h"
 #include "node.h"
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 497c7c5263c7..8521207de229 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -19,7 +19,6 @@
 #include <linux/mpage.h>
 #include <linux/buffer_head.h>
 #include <linux/mount.h>
-#include <linux/aio.h>
 #include <linux/vfs.h>
 #include <linux/parser.h>
 #include <linux/uio.h>
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index 28d0c7abba1c..b3fa05032234 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -38,7 +38,6 @@
 #include <linux/device.h>
 #include <linux/file.h>
 #include <linux/fs.h>
-#include <linux/aio.h>
 #include <linux/kdev_t.h>
 #include <linux/kthread.h>
 #include <linux/list.h>
@@ -48,6 +47,7 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/module.h>
+#include <linux/uio.h>
 
 #include "fuse_i.h"
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ed19a7d622fa..8c92c727ddd6 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -19,7 +19,6 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/swap.h>
 #include <linux/splice.h>
-#include <linux/aio.h>
 
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index a5c5e38b3ff8..ff102cbf16ea 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -15,8 +15,8 @@
 #include <linux/module.h>
 #include <linux/compat.h>
 #include <linux/swap.h>
-#include <linux/aio.h>
 #include <linux/falloc.h>
+#include <linux/uio.h>
 
 static const struct file_operations fuse_direct_io_file_operations;
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 4ad4f94edebe..fe6634d25d1d 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -20,7 +20,7 @@
 #include <linux/swap.h>
 #include <linux/gfs2_ondisk.h>
 #include <linux/backing-dev.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include <trace/events/writeback.h>
 
 #include "gfs2.h"
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 3e32bb8e2d7e..f6fc412b1100 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -25,7 +25,6 @@
 #include <asm/uaccess.h>
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
-#include <linux/aio.h>
 #include <linux/delay.h>
 
 #include "gfs2.h"
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index d0929bc81782..98d4ea45bb70 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -14,7 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "hfs_fs.h"
 #include "btree.h"
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 0cf786f2d046..f541196d4ee9 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -14,7 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index bd3df1ca3c9b..3197aed10614 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -22,8 +22,8 @@
 #include <linux/buffer_head.h>
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
+#include <linux/uio.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
 #include "jfs_incore.h"
 #include "jfs_inode.h"
 #include "jfs_filsys.h"
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 94712fc781fa..5d8b89cb13c0 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -26,7 +26,6 @@
 #include <linux/nfs_mount.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
-#include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 8b5969538f39..ab4987bc637f 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -26,7 +26,7 @@
 #include <linux/mpage.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 #include "nilfs.h"
 #include "btnode.h"
 #include "segment.h"
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 1da9b2d184dc..f16f2d8401fe 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -28,7 +28,6 @@
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/writeback.h>
-#include <linux/aio.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 898b9949d363..1d0c21df0d80 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -28,7 +28,6 @@
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/log2.h>
-#include <linux/aio.h>
 
 #include "aops.h"
 #include "attrib.h"
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 44db1808cdb5..e1bf18c5d25e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -29,6 +29,7 @@
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/uio.h>
 
 #include <cluster/masklog.h>
 
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 6cae155d54df..dd59599b022d 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -22,7 +22,7 @@
 #ifndef OCFS2_AOPS_H
 #define OCFS2_AOPS_H
 
-#include <linux/aio.h>
+#include <linux/fs.h>
 
 handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 struct page *page,
diff --git a/fs/pipe.c b/fs/pipe.c
index 21981e58e2a6..2d084f2d0b83 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -21,7 +21,6 @@
 #include <linux/audit.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
-#include <linux/aio.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
diff --git a/fs/read_write.c b/fs/read_write.c
index 76e324e8ce8d..99a6ef946d01 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -9,7 +9,6 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
-#include <linux/aio.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
 #include <linux/export.h>
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index e72401e1f995..9312b7842e03 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -18,7 +18,7 @@
 #include <linux/writeback.h>
 #include <linux/quotaops.h>
 #include <linux/swap.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
diff --git a/fs/splice.c b/fs/splice.c
index 7968da96bebb..4bbfa95b5bfe 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -32,7 +32,6 @@
 #include <linux/gfp.h>
 #include <linux/socket.h>
 #include <linux/compat.h>
-#include <linux/aio.h>
 #include "internal.h"
 
 /*
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index e627c0acf626..c3d15fe83403 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -50,7 +50,6 @@
  */
 
 #include "ubifs.h"
-#include <linux/aio.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/slab.h>
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 9c0b6da9dbb3..7f885cc8b0b7 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -34,7 +34,7 @@
 #include <linux/errno.h>
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "udf_i.h"
 #include "udf_sb.h"
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index a445d599098d..9c1fbd23913d 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -38,7 +38,7 @@
 #include <linux/slab.h>
 #include <linux/crc-itu-t.h>
 #include <linux/mpage.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 #include "udf_i.h"
 #include "udf_sb.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 3a9b7a1b8704..4f8cdc59bc38 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -31,7 +31,6 @@
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
 #include "xfs_bmap_btree.h"
-#include <linux/aio.h>
 #include <linux/gfp.h>
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1cdba95c78cb..f527618cb42b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -37,7 +37,6 @@
 #include "xfs_log.h"
 #include "xfs_icache.h"
 
-#include <linux/aio.h>
 #include <linux/dcache.h>
 #include <linux/falloc.h>
 #include <linux/pagevec.h>
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 5c40b61285ac..9eb42dbc5582 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -1,52 +1,23 @@
 #ifndef __LINUX__AIO_H
 #define __LINUX__AIO_H
 
-#include <linux/list.h>
-#include <linux/workqueue.h>
 #include <linux/aio_abi.h>
-#include <linux/uio.h>
-#include <linux/rcupdate.h>
-
-#include <linux/atomic.h>
 
 struct kioctx;
 struct kiocb;
+struct mm_struct;
 
 #define KIOCB_KEY		0
 
 typedef int (kiocb_cancel_fn)(struct kiocb *);
 
-#define IOCB_EVENTFD		(1 << 0)
-
-struct kiocb {
-	struct file		*ki_filp;
-	loff_t			ki_pos;
-	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
-	void			*private;
-	int			ki_flags;
-};
-
-static inline bool is_sync_kiocb(struct kiocb *kiocb)
-{
-	return kiocb->ki_complete == NULL;
-}
-
-static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
-{
-	*kiocb = (struct kiocb) {
-			.ki_filp = filp,
-		};
-}
-
 /* prototypes */
 #ifdef CONFIG_AIO
-struct mm_struct;
 extern void exit_aio(struct mm_struct *mm);
 extern long do_io_submit(aio_context_t ctx_id, long nr,
 			 struct iocb __user *__user *iocbpp, bool compat);
 void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel);
 #else
-struct mm_struct;
 static inline void exit_aio(struct mm_struct *mm) { }
 static inline long do_io_submit(aio_context_t ctx_id, long nr,
 				struct iocb __user * __user *iocbpp,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 447932aed1e1..48c1472bde4a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -314,6 +314,28 @@ struct page;
 struct address_space;
 struct writeback_control;
 
+#define IOCB_EVENTFD		(1 << 0)
+
+struct kiocb {
+	struct file		*ki_filp;
+	loff_t			ki_pos;
+	void (*ki_complete)(struct kiocb *iocb, long ret, long ret2);
+	void			*private;
+	int			ki_flags;
+};
+
+static inline bool is_sync_kiocb(struct kiocb *kiocb)
+{
+	return kiocb->ki_complete == NULL;
+}
+
+static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
+{
+	*kiocb = (struct kiocb) {
+		.ki_filp = filp,
+	};
+}
+
 /*
  * "descriptor" for what we're up to with a read.
  * This allows us to use the same read code yet
diff --git a/include/net/sock.h b/include/net/sock.h
index ab186b1d31ff..71c1300025e2 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -57,7 +57,6 @@
 #include <linux/page_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/static_key.h>
-#include <linux/aio.h>
 #include <linux/sched.h>
 
 #include <linux/filter.h>
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 60b2aa2a2da9..40d50cc4c686 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -32,7 +32,6 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
-#include <linux/aio.h>
 #include <linux/syscalls.h>
 #include <linux/kexec.h>
 #include <linux/kdb.h>
@@ -46,6 +45,7 @@
 #include <linux/irq_work.h>
 #include <linux/utsname.h>
 #include <linux/ctype.h>
+#include <linux/uio.h>
 
 #include <asm/uaccess.h>
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 88ea2d6e0031..83d907afb4a6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/aio.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
diff --git a/mm/filemap.c b/mm/filemap.c
index ad7242043bdb..876f4e6f3ed6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -13,7 +13,6 @@
 #include <linux/compiler.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
-#include <linux/aio.h>
 #include <linux/capability.h>
 #include <linux/kernel_stat.h>
 #include <linux/gfp.h>
diff --git a/mm/page_io.c b/mm/page_io.c
index 7ef21577856c..a96c8562d835 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -20,8 +20,8 @@
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/frontswap.h>
-#include <linux/aio.h>
 #include <linux/blkdev.h>
+#include <linux/uio.h>
 #include <asm/pgtable.h>
 
 static struct bio *get_swap_bio(gfp_t gfp_flags,
diff --git a/mm/shmem.c b/mm/shmem.c
index a63031fa3e0c..944b94079bb0 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -31,7 +31,7 @@
 #include <linux/mm.h>
 #include <linux/export.h>
 #include <linux/swap.h>
-#include <linux/aio.h>
+#include <linux/uio.h>
 
 static struct vfsmount *shm_mnt;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index f027a708b7e0..4a356b7c081b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -46,7 +46,6 @@
 #include <linux/stddef.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
-#include <linux/aio.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/spinlock.h>
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index b03a638b420c..9ecff240a39b 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -25,7 +25,6 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/pm_qos.h>
-#include <linux/aio.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
 #include <sound/core.h>
@@ -35,6 +34,7 @@
 #include <sound/pcm_params.h>
 #include <sound/timer.h>
 #include <sound/minors.h>
+#include <linux/uio.h>
 
 /*
  *  Compatibility
-- 
cgit v1.2.3


From 2bca1e2388a8a9e8a3db0daf54fcc124516a3e83 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Wed, 25 Feb 2015 19:25:01 -0800
Subject: f2fs: clear page's up-to-date if block was deallocated

If page's on-disk block was deallocated, let's remove up-to-date flag to avoid
further access with wrong contents.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 6 +++++-
 fs/f2fs/dir.c  | 1 +
 fs/f2fs/node.c | 2 ++
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ae5c41444e8f..62e31b2aa131 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1259,8 +1259,10 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	fio->blk_addr = dn.data_blkaddr;
 
 	/* This page is already truncated */
-	if (fio->blk_addr == NULL_ADDR)
+	if (fio->blk_addr == NULL_ADDR) {
+		ClearPageUptodate(page);
 		goto out_writepage;
+	}
 
 	set_page_writeback(page);
 
@@ -1355,6 +1357,8 @@ done:
 	clear_cold_data(page);
 out:
 	inode_dec_dirty_pages(inode);
+	if (err)
+		ClearPageUptodate(page);
 	unlock_page(page);
 	if (need_balance_fs)
 		f2fs_balance_fs(sbi);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 583896cb5346..590aeef6f85e 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -682,6 +682,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	if (bit_pos == NR_DENTRY_IN_BLOCK) {
 		truncate_hole(dir, page->index, page->index + 1);
 		clear_page_dirty_for_io(page);
+		ClearPagePrivate(page);
 		ClearPageUptodate(page);
 		inode_dec_dirty_pages(dir);
 	}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 28423697e97a..35a911722d59 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1002,6 +1002,7 @@ static int read_node_page(struct page *page, int rw)
 	get_node_info(sbi, page->index, &ni);
 
 	if (unlikely(ni.blk_addr == NULL_ADDR)) {
+		ClearPageUptodate(page);
 		f2fs_put_page(page, 1);
 		return -ENOENT;
 	}
@@ -1313,6 +1314,7 @@ static int f2fs_write_node_page(struct page *page,
 
 	/* This page is already truncated */
 	if (unlikely(ni.blk_addr == NULL_ADDR)) {
+		ClearPageUptodate(page);
 		dec_page_count(sbi, F2FS_DIRTY_NODES);
 		unlock_page(page);
 		return 0;
-- 
cgit v1.2.3


From b7f204cca4b7155f47e64555614b1f534a53737e Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Wed, 25 Feb 2015 19:54:48 -0800
Subject: f2fs: check its block allocation to avoid producing wrong dirty pages

If a page is cached but its block was deallocated, we don't need to make
the page dirty again by gc and truncate_partial_data_page.

In that case, it needs to check its block allocation all the time instead
of giving up-to-date page.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 62e31b2aa131..389fda772e69 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -813,11 +813,19 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 		.rw = sync ? READ_SYNC : READA,
 	};
 
+	/*
+	 * If sync is false, it needs to check its block allocation.
+	 * This is need and triggered by two flows:
+	 *   gc and truncate_partial_data_page.
+	 */
+	if (!sync)
+		goto search;
+
 	page = find_get_page(mapping, index);
 	if (page && PageUptodate(page))
 		return page;
 	f2fs_put_page(page, 0);
-
+search:
 	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
 		dn.data_blkaddr = ei.blk + index - ei.fofs;
 		goto got_it;
-- 
cgit v1.2.3


From d5669f7b9b0344a7f1e874ac86b9403434381ba8 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Fri, 27 Feb 2015 13:37:39 -0800
Subject: f2fs: avoid to trigger writepage during POR

This patch doesn't make any effect on previous behavior, since
f2fs_write_data_page bypasses writing the page during POR.

But, the difference is that this patch avoids holding writepages mutex.
This is to avoid the following false warning, since this can happen only
when mount and shutdown are triggered at the same time.

 ======================================================
 [ INFO: possible circular locking dependency detected ]
 4.0.0-rc1+ #3 Tainted: G           O
 -------------------------------------------------------
 kworker/u8:0/2270 is trying to acquire lock:
  (&sbi->gc_mutex){+.+.+.}, at: [<ffffffffa02bdd33>] f2fs_balance_fs+0x73/0x90 [f2fs]

 but task is already holding lock:
  (&sbi->writepages){+.+...}, at: [<ffffffffa02b261b>] f2fs_write_data_pages+0xcb/0x3a0 [f2fs]

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #2 (&sbi->writepages){+.+...}:
        [<ffffffff810e2b11>] lock_acquire+0xe1/0x2f0
        [<ffffffff8185e1b3>] mutex_lock_nested+0x63/0x530
        [<ffffffffa02b261b>] f2fs_write_data_pages+0xcb/0x3a0 [f2fs]
        [<ffffffff811c38c1>] do_writepages+0x21/0x50
        [<ffffffff8126c5a6>] __writeback_single_inode+0x76/0xbf0
        [<ffffffff8126e23a>] writeback_single_inode+0xea/0x1c0
        [<ffffffff8126e425>] write_inode_now+0x95/0xa0
        [<ffffffff81259dab>] iput+0x20b/0x3f0
        [<ffffffffa02c1c8b>] recover_data.constprop.14+0x26b/0xa80 [f2fs]
        [<ffffffffa02c2776>] recover_fsync_data+0x2b6/0x5e0 [f2fs]
        [<ffffffffa02a9744>] f2fs_fill_super+0xb24/0xb90 [f2fs]
        [<ffffffff8123d7f4>] mount_bdev+0x1a4/0x1e0
        [<ffffffffa02a3c85>] f2fs_mount+0x15/0x20 [f2fs]
        [<ffffffff8123e159>] mount_fs+0x39/0x180
        [<ffffffff8125e51b>] vfs_kern_mount+0x6b/0x160
        [<ffffffff81261554>] do_mount+0x204/0xbe0
        [<ffffffff8126223b>] SyS_mount+0x8b/0xe0
        [<ffffffff81863e6d>] system_call_fastpath+0x16/0x1b

 -> #1 (&sbi->cp_mutex){+.+...}:
        [<ffffffff810e2b11>] lock_acquire+0xe1/0x2f0
        [<ffffffff8185e1b3>] mutex_lock_nested+0x63/0x530
        [<ffffffffa02acbf2>] write_checkpoint+0x42/0x1230 [f2fs]
        [<ffffffffa02a847d>] f2fs_sync_fs+0x9d/0x2a0 [f2fs]
        [<ffffffff81272f82>] sync_filesystem+0x82/0xb0
        [<ffffffff8123c214>] generic_shutdown_super+0x34/0x100
        [<ffffffff8123c5f7>] kill_block_super+0x27/0x70
        [<ffffffffa02a3c60>] kill_f2fs_super+0x20/0x30 [f2fs]
        [<ffffffff8123ca49>] deactivate_locked_super+0x49/0x80
        [<ffffffff8123d05e>] deactivate_super+0x4e/0x70
        [<ffffffff8125df63>] cleanup_mnt+0x43/0x90
        [<ffffffff8125e002>] __cleanup_mnt+0x12/0x20
        [<ffffffff810a82e4>] task_work_run+0xc4/0xf0
        [<ffffffff8101f0bd>] do_notify_resume+0x8d/0xa0
        [<ffffffff81864141>] int_signal+0x12/0x17

 -> #0 (&sbi->gc_mutex){+.+.+.}:
        [<ffffffff810e2866>] __lock_acquire+0x1ac6/0x1c90
        [<ffffffff810e2b11>] lock_acquire+0xe1/0x2f0
        [<ffffffff8185e1b3>] mutex_lock_nested+0x63/0x530
        [<ffffffffa02bdd33>] f2fs_balance_fs+0x73/0x90 [f2fs]
        [<ffffffffa02b5938>] f2fs_write_data_page+0x348/0x5b0 [f2fs]
        [<ffffffffa02af9da>] __f2fs_writepage+0x1a/0x50 [f2fs]
        [<ffffffff811c1b54>] write_cache_pages+0x274/0x6f0
        [<ffffffffa02b2630>] f2fs_write_data_pages+0xe0/0x3a0 [f2fs]
        [<ffffffff811c38c1>] do_writepages+0x21/0x50
        [<ffffffff8126c5a6>] __writeback_single_inode+0x76/0xbf0
        [<ffffffff8126d44a>] writeback_sb_inodes+0x32a/0x710
        [<ffffffff8126d8cf>] __writeback_inodes_wb+0x9f/0xd0
        [<ffffffff8126dcdb>] wb_writeback+0x3db/0x850
        [<ffffffff8126e848>] bdi_writeback_workfn+0x148/0x980
        [<ffffffff810a3782>] process_one_work+0x1e2/0x840
        [<ffffffff810a3f01>] worker_thread+0x121/0x460
        [<ffffffff810a9dc8>] kthread+0xf8/0x110
        [<ffffffff81863dbc>] ret_from_fork+0x7c/0xb0

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 389fda772e69..0057d4baad33 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1408,6 +1408,10 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 			available_free_memory(sbi, DIRTY_DENTS))
 		goto skip_write;
 
+	/* during POR, we don't need to trigger writepage at all. */
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	diff = nr_pages_to_write(sbi, DATA, wbc);
 
 	if (!S_ISDIR(inode->i_mode)) {
-- 
cgit v1.2.3


From d6d4f1cb912d9bcf988a529d0934568d4550f7b5 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 12 Mar 2015 17:04:24 +0800
Subject: f2fs: fix to check current blkaddr in __allocate_data_blocks

In __allocate_data_blocks, we should check current blkaddr which is located at
ofs_in_node of dnode page instead of checking first blkaddr all the time.
Otherwise we can only allocate one blkaddr in each dnode page. Fix it.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0057d4baad33..ba70a78a396f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1066,7 +1066,10 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset,
 		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 
 		while (dn.ofs_in_node < end_offset && len) {
-			if (dn.data_blkaddr == NULL_ADDR) {
+			block_t blkaddr;
+
+			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
+			if (blkaddr == NULL_ADDR) {
 				if (__allocate_data_block(&dn))
 					goto sync_out;
 				allocated = true;
-- 
cgit v1.2.3


From 3402e87cfb5e762f9c95071bf4a2ad65fd9392a2 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Wed, 11 Mar 2015 23:27:25 -0400
Subject: f2fs: set buffer_new when new blocks are allocated

This patch modifies to call set_buffer_new, if new blocks are allocated.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ba70a78a396f..4a416e74bb2a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -257,7 +257,7 @@ static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs,
 	unsigned int blkbits = sb->s_blocksize_bits;
 	size_t count;
 
-	set_buffer_new(bh_result);
+	clear_buffer_new(bh_result);
 	map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs);
 	count = ei->fofs + ei->len - pgofs;
 	if (count < (UINT_MAX >> blkbits))
@@ -1139,7 +1139,7 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
-		set_buffer_new(bh_result);
+		clear_buffer_new(bh_result);
 		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
 	} else if (create) {
 		err = __allocate_data_block(&dn);
@@ -1184,6 +1184,7 @@ get_next:
 			if (err)
 				goto sync_out;
 			allocated = true;
+			set_buffer_new(bh_result);
 			blkaddr = dn.data_blkaddr;
 		}
 		/* Give more consecutive addresses for the readahead */
-- 
cgit v1.2.3


From 78373b7319abdf15050af5b1632c4c8b8b398f33 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Fri, 13 Mar 2015 21:44:36 -0700
Subject: f2fs: enhance multi-threads performance

Previously, f2fs_write_data_pages has a mutex, sbi->writepages, to serialize
data writes to maximize write bandwidth, while sacrificing multi-threads
performance.
Practically, however, multi-threads environment is much more important for
users. So this patch tries to remove the mutex.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c  | 7 -------
 fs/f2fs/f2fs.h  | 1 -
 fs/f2fs/super.c | 1 -
 3 files changed, 9 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 4a416e74bb2a..f0a18a005bda 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1397,7 +1397,6 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	bool locked = false;
 	int ret;
 	long diff;
 
@@ -1418,13 +1417,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 	diff = nr_pages_to_write(sbi, DATA, wbc);
 
-	if (!S_ISDIR(inode->i_mode)) {
-		mutex_lock(&sbi->writepages);
-		locked = true;
-	}
 	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
-	if (locked)
-		mutex_unlock(&sbi->writepages);
 
 	f2fs_submit_merged_bio(sbi, DATA, WRITE);
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 147ef316f0ff..dbe114463a18 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -613,7 +613,6 @@ struct f2fs_sb_info {
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
-	struct mutex writepages;		/* mutex for writepages() */
 	wait_queue_head_t cp_wait;
 
 	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index f9dc543805d9..fc6857f378cc 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1027,7 +1027,6 @@ try_onemore:
 	sbi->raw_super = raw_super;
 	sbi->raw_super_buf = raw_super_buf;
 	mutex_init(&sbi->gc_mutex);
-	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
 	clear_sbi_flag(sbi, SBI_POR_DOING);
-- 
cgit v1.2.3


From 3c6c2bebef79999b1827041696dc1881e637e3af Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Tue, 17 Mar 2015 17:16:35 -0700
Subject: f2fs: avoid punch_hole overhead when releasing volatile data

This patch is to avoid some punch_hole overhead when releasing volatile data.
If volatile data was not written yet, we just can make the first page as zero.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c  |  2 ++
 fs/f2fs/f2fs.h  |  6 ++++++
 fs/f2fs/file.c  |  6 ++++++
 fs/f2fs/inode.c | 10 ++++++++++
 4 files changed, 24 insertions(+)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f0a18a005bda..486113db97b1 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1291,6 +1291,8 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 		write_data_page(page, &dn, fio);
 		f2fs_update_extent_cache(&dn);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
+		if (page->index == 0)
+			set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
 	}
 out_writepage:
 	f2fs_put_dnode(&dn);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index dbe114463a18..9e378179ff93 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1232,6 +1232,7 @@ enum {
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
+	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
 	FI_DROP_CACHE,		/* drop dirty page cache */
 	FI_DATA_EXIST,		/* indicate data exists */
 };
@@ -1340,6 +1341,11 @@ static inline bool f2fs_is_volatile_file(struct inode *inode)
 	return is_inode_flag_set(F2FS_I(inode), FI_VOLATILE_FILE);
 }
 
+static inline bool f2fs_is_first_block_written(struct inode *inode)
+{
+	return is_inode_flag_set(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+}
+
 static inline bool f2fs_is_drop_cache(struct inode *inode)
 {
 	return is_inode_flag_set(F2FS_I(inode), FI_DROP_CACHE);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 36dc7581a28b..39a07a59b134 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -437,6 +437,9 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 		dn->data_blkaddr = NULL_ADDR;
 		f2fs_update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
+		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
+			clear_inode_flag(F2FS_I(dn->inode),
+						FI_FIRST_BLOCK_WRITTEN);
 		nr_free++;
 	}
 	if (nr_free) {
@@ -1005,6 +1008,9 @@ static int f2fs_ioc_release_volatile_write(struct file *filp)
 	if (!f2fs_is_volatile_file(inode))
 		return 0;
 
+	if (!f2fs_is_first_block_written(inode))
+		return truncate_partial_data_page(inode, 0, true);
+
 	punch_hole(inode, 0, F2FS_BLKSIZE);
 	return 0;
 }
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index b5087443be41..bb5800969bcc 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -51,6 +51,13 @@ static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 	}
 }
 
+static bool __written_first_block(struct f2fs_inode *ri)
+{
+	if (ri->i_addr[0] != NEW_ADDR && ri->i_addr[0] != NULL_ADDR)
+		return true;
+	return false;
+}
+
 static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
 {
 	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
@@ -143,6 +150,9 @@ static int do_read_inode(struct inode *inode)
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
 
+	if (__written_first_block(ri))
+		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
+
 	f2fs_put_page(node_page, 1);
 
 	stat_inc_inline_inode(inode);
-- 
cgit v1.2.3


From 8ce67cb07dbf6ba35aea1e07e8ad1ea004ced27b Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Tue, 17 Mar 2015 17:58:08 -0700
Subject: f2fs: add some tracepoints to debug volatile and atomic writes

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c              |  2 ++
 fs/f2fs/f2fs.h              |  4 ++++
 fs/f2fs/segment.c           |  4 ++++
 include/trace/events/f2fs.h | 27 ++++++++++++++++++++++++++-
 4 files changed, 36 insertions(+), 1 deletion(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 486113db97b1..241b98741df9 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1287,9 +1287,11 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 			need_inplace_update(inode))) {
 		rewrite_data_page(page, fio);
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
+		trace_f2fs_do_write_data_page(page, IPU);
 	} else {
 		write_data_page(page, &dn, fio);
 		f2fs_update_extent_cache(&dn);
+		trace_f2fs_do_write_data_page(page, OPU);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 		if (page->index == 0)
 			set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9e378179ff93..c9818193e15e 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -556,6 +556,10 @@ enum page_type {
 	META,
 	NR_PAGE_TYPE,
 	META_FLUSH,
+	INMEM,		/* the below types are used by tracepoints only. */
+	INMEM_DROP,
+	IPU,
+	OPU,
 };
 
 struct f2fs_io_info {
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index eafaf728236b..f939660941bb 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -205,6 +205,8 @@ retry:
 	list_add_tail(&new->list, &fi->inmem_pages);
 	inc_page_count(F2FS_I_SB(inode), F2FS_INMEM_PAGES);
 	mutex_unlock(&fi->inmem_lock);
+
+	trace_f2fs_register_inmem_page(page, INMEM);
 }
 
 void commit_inmem_pages(struct inode *inode, bool abort)
@@ -238,11 +240,13 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 				f2fs_wait_on_page_writeback(cur->page, DATA);
 				if (clear_page_dirty_for_io(cur->page))
 					inode_dec_dirty_pages(inode);
+				trace_f2fs_commit_inmem_page(cur->page, INMEM);
 				do_write_data_page(cur->page, &fio);
 				submit_bio = true;
 			}
 			f2fs_put_page(cur->page, 1);
 		} else {
+			trace_f2fs_commit_inmem_page(cur->page, INMEM_DROP);
 			put_page(cur->page);
 		}
 		radix_tree_delete(&fi->inmem_root, cur->page->index);
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 09a56dc75f8d..75724bd28356 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -14,7 +14,11 @@
 		{ NODE,		"NODE" },				\
 		{ DATA,		"DATA" },				\
 		{ META,		"META" },				\
-		{ META_FLUSH,	"META_FLUSH" })
+		{ META_FLUSH,	"META_FLUSH" },				\
+		{ INMEM,	"INMEM" },				\
+		{ INMEM_DROP,	"INMEM_DROP" },				\
+		{ IPU,		"IN-PLACE" },				\
+		{ OPU,		"OUT-OF-PLACE" })
 
 #define F2FS_BIO_MASK(t)	(t & (READA | WRITE_FLUSH_FUA))
 #define F2FS_BIO_EXTRA_MASK(t)	(t & (REQ_META | REQ_PRIO))
@@ -854,6 +858,13 @@ DEFINE_EVENT(f2fs__page, f2fs_writepage,
 	TP_ARGS(page, type)
 );
 
+DEFINE_EVENT(f2fs__page, f2fs_do_write_data_page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
 DEFINE_EVENT(f2fs__page, f2fs_readpage,
 
 	TP_PROTO(struct page *page, int type),
@@ -875,6 +886,20 @@ DEFINE_EVENT(f2fs__page, f2fs_vm_page_mkwrite,
 	TP_ARGS(page, type)
 );
 
+DEFINE_EVENT(f2fs__page, f2fs_register_inmem_page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
+DEFINE_EVENT(f2fs__page, f2fs_commit_inmem_page,
+
+	TP_PROTO(struct page *page, int type),
+
+	TP_ARGS(page, type)
+);
+
 TRACE_EVENT(f2fs_writepages,
 
 	TP_PROTO(struct inode *inode, struct writeback_control *wbc, int type),
-- 
cgit v1.2.3


From 216a620a7c3d35ae604ba519c99c5cd1ce4dad6e Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 19 Mar 2015 19:23:32 +0800
Subject: f2fs: split set_data_blkaddr from f2fs_update_extent_cache

Split __set_data_blkaddr from f2fs_update_extent_cache for readability.

Additionally rename __set_data_blkaddr to set_data_blkaddr for exporting.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c     | 10 ++++------
 fs/f2fs/f2fs.h     |  1 +
 fs/f2fs/file.c     |  1 +
 fs/f2fs/inline.c   |  1 +
 fs/f2fs/recovery.c |  1 +
 5 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 241b98741df9..6492f88a2cc4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -200,7 +200,7 @@ alloc_new:
  *  ->node_page
  *    update block addresses in the node page
  */
-static void __set_data_blkaddr(struct dnode_of_data *dn)
+void set_data_blkaddr(struct dnode_of_data *dn)
 {
 	struct f2fs_node *rn;
 	__le32 *addr_array;
@@ -229,7 +229,7 @@ int reserve_new_block(struct dnode_of_data *dn)
 	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);
 
 	dn->data_blkaddr = NEW_ADDR;
-	__set_data_blkaddr(dn);
+	set_data_blkaddr(dn);
 	mark_inode_dirty(dn->inode);
 	sync_inode_page(dn);
 	return 0;
@@ -784,9 +784,6 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
 
 	f2fs_bug_on(F2FS_I_SB(dn->inode), dn->data_blkaddr == NEW_ADDR);
 
-	/* Update the page address in the parent node */
-	__set_data_blkaddr(dn);
-
 	if (is_inode_flag_set(fi, FI_NO_EXTENT))
 		return;
 
@@ -1032,7 +1029,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg);
 
 	/* direct IO doesn't use extent cache to maximize the performance */
-	__set_data_blkaddr(dn);
+	set_data_blkaddr(dn);
 
 	/* update i_size */
 	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
@@ -1290,6 +1287,7 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 		trace_f2fs_do_write_data_page(page, IPU);
 	} else {
 		write_data_page(page, &dn, fio);
+		set_data_blkaddr(&dn);
 		f2fs_update_extent_cache(&dn);
 		trace_f2fs_do_write_data_page(page, OPU);
 		set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c9818193e15e..83223d8b32bb 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1591,6 +1591,7 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
 void f2fs_submit_page_mbio(struct f2fs_sb_info *, struct page *,
 						struct f2fs_io_info *);
+void set_data_blkaddr(struct dnode_of_data *);
 int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 39a07a59b134..da1392965424 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -435,6 +435,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
 			continue;
 
 		dn->data_blkaddr = NULL_ADDR;
+		set_data_blkaddr(dn);
 		f2fs_update_extent_cache(dn);
 		invalidate_blocks(sbi, blkaddr);
 		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 375d2c797f4c..8241a87046c3 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -131,6 +131,7 @@ no_update:
 	set_page_writeback(page);
 	fio.blk_addr = dn->data_blkaddr;
 	write_data_page(page, dn, &fio);
+	set_data_blkaddr(dn);
 	f2fs_update_extent_cache(dn);
 	f2fs_wait_on_page_writeback(page, DATA);
 	if (dirty)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 6e40874dfbb9..e60ffaa380f1 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -403,6 +403,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 			/* write dummy data page */
 			recover_data_page(sbi, NULL, &sum, src, dest);
 			dn.data_blkaddr = dest;
+			set_data_blkaddr(&dn);
 			f2fs_update_extent_cache(&dn);
 			recovered++;
 		}
-- 
cgit v1.2.3


From 93dfc52656e9ae1009ccba67e67ff69285b7743f Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 19 Mar 2015 19:24:59 +0800
Subject: f2fs: introduce __{find,grab}_extent_tree

This patch introduces __{find,grab}_extent_tree for reusing by following
patches.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 79 +++++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 48 insertions(+), 31 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 6492f88a2cc4..67b3a99e03d5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -394,6 +394,49 @@ static void __detach_extent_node(struct f2fs_sb_info *sbi,
 		et->cached_en = NULL;
 }
 
+static struct extent_tree *__find_extent_tree(struct f2fs_sb_info *sbi,
+							nid_t ino)
+{
+	struct extent_tree *et;
+
+	down_read(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
+	if (!et) {
+		up_read(&sbi->extent_tree_lock);
+		return NULL;
+	}
+	atomic_inc(&et->refcount);
+	up_read(&sbi->extent_tree_lock);
+
+	return et;
+}
+
+static struct extent_tree *__grab_extent_tree(struct inode *inode)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et;
+	nid_t ino = inode->i_ino;
+
+	down_write(&sbi->extent_tree_lock);
+	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
+	if (!et) {
+		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
+		f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
+		memset(et, 0, sizeof(struct extent_tree));
+		et->ino = ino;
+		et->root = RB_ROOT;
+		et->cached_en = NULL;
+		rwlock_init(&et->lock);
+		atomic_set(&et->refcount, 0);
+		et->count = 0;
+		sbi->total_ext_tree++;
+	}
+	atomic_inc(&et->refcount);
+	up_write(&sbi->extent_tree_lock);
+
+	return et;
+}
+
 static struct extent_node *__lookup_extent_tree(struct extent_tree *et,
 							unsigned int fofs)
 {
@@ -538,14 +581,9 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 
 	trace_f2fs_lookup_extent_tree_start(inode, pgofs);
 
-	down_read(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
-	if (!et) {
-		up_read(&sbi->extent_tree_lock);
+	et = __find_extent_tree(sbi, inode->i_ino);
+	if (!et)
 		return false;
-	}
-	atomic_inc(&et->refcount);
-	up_read(&sbi->extent_tree_lock);
 
 	read_lock(&et->lock);
 	en = __lookup_extent_tree(et, pgofs);
@@ -570,7 +608,6 @@ static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
 							block_t blkaddr)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	nid_t ino = inode->i_ino;
 	struct extent_tree *et;
 	struct extent_node *en = NULL, *en1 = NULL, *en2 = NULL, *en3 = NULL;
 	struct extent_node *den = NULL;
@@ -579,22 +616,7 @@ static void f2fs_update_extent_tree(struct inode *inode, pgoff_t fofs,
 
 	trace_f2fs_update_extent_tree(inode, fofs, blkaddr);
 
-	down_write(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
-	if (!et) {
-		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
-		f2fs_radix_tree_insert(&sbi->extent_tree_root, ino, et);
-		memset(et, 0, sizeof(struct extent_tree));
-		et->ino = ino;
-		et->root = RB_ROOT;
-		et->cached_en = NULL;
-		rwlock_init(&et->lock);
-		atomic_set(&et->refcount, 0);
-		et->count = 0;
-		sbi->total_ext_tree++;
-	}
-	atomic_inc(&et->refcount);
-	up_write(&sbi->extent_tree_lock);
+	et = __grab_extent_tree(inode);
 
 	write_lock(&et->lock);
 
@@ -732,14 +754,9 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	if (!test_opt(sbi, EXTENT_CACHE))
 		return;
 
-	down_read(&sbi->extent_tree_lock);
-	et = radix_tree_lookup(&sbi->extent_tree_root, inode->i_ino);
-	if (!et) {
-		up_read(&sbi->extent_tree_lock);
+	et = __find_extent_tree(sbi, inode->i_ino);
+	if (!et)
 		goto out;
-	}
-	atomic_inc(&et->refcount);
-	up_read(&sbi->extent_tree_lock);
 
 	/* free all extent info belong to this extent tree */
 	write_lock(&et->lock);
-- 
cgit v1.2.3


From 028a41e89383e1208dff1afe3e260b8cb6d3431c Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 19 Mar 2015 19:26:02 +0800
Subject: f2fs: initialize extent tree with on-disk extent info of inode

With normal extent info cache, we records largest extent mapping between logical
block and physical block into extent info, and we persist extent info in on-disk
inode.

When we enable extent tree cache, if extent info of on-disk inode is exist, and
the extent is not a small fragmented mapping extent. We'd better to load the
extent info into extent tree cache when inode is loaded. By this way we can have
more chance to hit extent tree cache rather than taking more time to read dnode
page for block address.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c  | 43 +++++++++++++++++++++++++++++++++++++++++++
 fs/f2fs/f2fs.h  |  1 +
 fs/f2fs/inode.c |  4 +---
 3 files changed, 45 insertions(+), 3 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 67b3a99e03d5..e3be4be3a6d8 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -572,6 +572,39 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
 	return count - et->count;
 }
 
+static void f2fs_init_extent_tree(struct inode *inode,
+						struct f2fs_extent *i_ext)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct extent_tree *et;
+	struct extent_node *en;
+	struct extent_info ei;
+
+	if (le32_to_cpu(i_ext->len) < F2FS_MIN_EXTENT_LEN)
+		return;
+
+	et = __grab_extent_tree(inode);
+
+	write_lock(&et->lock);
+	if (et->count)
+		goto out;
+
+	set_extent_info(&ei, le32_to_cpu(i_ext->fofs),
+		le32_to_cpu(i_ext->blk), le32_to_cpu(i_ext->len));
+
+	en = __insert_extent_tree(sbi, et, &ei, NULL);
+	if (en) {
+		et->cached_en = en;
+
+		spin_lock(&sbi->extent_lock);
+		list_add_tail(&en->list, &sbi->extent_list);
+		spin_unlock(&sbi->extent_lock);
+	}
+out:
+	write_unlock(&et->lock);
+	atomic_dec(&et->refcount);
+}
+
 static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
@@ -782,6 +815,16 @@ out:
 	return;
 }
 
+void f2fs_init_extent_cache(struct inode *inode, struct f2fs_extent *i_ext)
+{
+	if (test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
+		f2fs_init_extent_tree(inode, i_ext);
+
+	write_lock(&F2FS_I(inode)->ext_lock);
+	get_extent_info(&F2FS_I(inode)->ext, *i_ext);
+	write_unlock(&F2FS_I(inode)->ext_lock);
+}
+
 static bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 83223d8b32bb..431b4af693e5 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1596,6 +1596,7 @@ int reserve_new_block(struct dnode_of_data *);
 int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
 void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
 void f2fs_destroy_extent_tree(struct inode *);
+void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *);
 void f2fs_update_extent_cache(struct dnode_of_data *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index bb5800969bcc..9e64d3efb2d2 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -137,9 +137,7 @@ static int do_read_inode(struct inode *inode)
 	fi->i_pino = le32_to_cpu(ri->i_pino);
 	fi->i_dir_level = ri->i_dir_level;
 
-	write_lock(&fi->ext_lock);
-	get_extent_info(&fi->ext, ri->i_ext);
-	write_unlock(&fi->ext_lock);
+	f2fs_init_extent_cache(inode, &ri->i_ext);
 
 	get_inline_info(fi, ri);
 
-- 
cgit v1.2.3


From 0bdee482509fe8c3cf0e66231ed37b8e70954093 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Thu, 19 Mar 2015 19:27:51 +0800
Subject: f2fs: preserve extent info for extent cache

This patch tries to preserve last extent info in extent tree cache into on-disk
inode, so this can help us to reuse the last extent info next time for
performance.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c  | 49 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/f2fs/f2fs.h  |  8 ++++++++
 fs/f2fs/inode.c |  5 +++++
 3 files changed, 62 insertions(+)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e3be4be3a6d8..8a940e518be8 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -719,6 +719,55 @@ update_extent:
 	atomic_dec(&et->refcount);
 }
 
+void f2fs_preserve_extent_tree(struct inode *inode)
+{
+	struct extent_tree *et;
+	struct extent_info *ext = &F2FS_I(inode)->ext;
+	bool sync = false;
+
+	if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE))
+		return;
+
+	et = __find_extent_tree(F2FS_I_SB(inode), inode->i_ino);
+	if (!et) {
+		if (ext->len) {
+			ext->len = 0;
+			update_inode_page(inode);
+		}
+		return;
+	}
+
+	read_lock(&et->lock);
+	if (et->count) {
+		struct extent_node *en;
+
+		if (et->cached_en) {
+			en = et->cached_en;
+		} else {
+			struct rb_node *node = rb_first(&et->root);
+
+			if (!node)
+				node = rb_last(&et->root);
+			en = rb_entry(node, struct extent_node, rb_node);
+		}
+
+		if (__is_extent_same(ext, &en->ei))
+			goto out;
+
+		*ext = en->ei;
+		sync = true;
+	} else if (ext->len) {
+		ext->len = 0;
+		sync = true;
+	}
+out:
+	read_unlock(&et->lock);
+	atomic_dec(&et->refcount);
+
+	if (sync)
+		update_inode_page(inode);
+}
+
 void f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 {
 	struct extent_tree *treevec[EXT_TREE_VEC_SIZE];
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 431b4af693e5..0be198339c3b 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -371,6 +371,13 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
 	ei->len = len;
 }
 
+static inline bool __is_extent_same(struct extent_info *ei1,
+						struct extent_info *ei2)
+{
+	return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk &&
+						ei1->len == ei2->len);
+}
+
 static inline bool __is_extent_mergeable(struct extent_info *back,
 						struct extent_info *front)
 {
@@ -1598,6 +1605,7 @@ void f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
 void f2fs_destroy_extent_tree(struct inode *);
 void f2fs_init_extent_cache(struct inode *, struct f2fs_extent *);
 void f2fs_update_extent_cache(struct dnode_of_data *);
+void f2fs_preserve_extent_tree(struct inode *);
 struct page *find_data_page(struct inode *, pgoff_t, bool);
 struct page *get_lock_data_page(struct inode *, pgoff_t);
 struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 9e64d3efb2d2..07237ac2935e 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -343,7 +343,12 @@ void f2fs_evict_inode(struct inode *inode)
 no_delete:
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
+
+	/* update extent info in inode */
+	if (inode->i_nlink)
+		f2fs_preserve_extent_tree(inode);
 	f2fs_destroy_extent_tree(inode);
+
 	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
-- 
cgit v1.2.3


From df6136ef5533421e68ea7ff9c33d5b2ac9005ff9 Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Mon, 23 Mar 2015 10:33:37 +0800
Subject: f2fs: preallocate fallocated blocks for direct IO

Normally, due to DIO_SKIP_HOLES flag is set by default, blockdev_direct_IO in
f2fs_direct_IO tries to skip DIO in holes when writing inside i_size, this
makes us falling back to buffered IO which shows lower performance.

So in commit 59b802e5a453 ("f2fs: allocate data blocks in advance for
f2fs_direct_IO"), we improve perfromance by allocating data blocks in advance
if we meet holes no matter in i_size or not, since with it we can avoid falling
back to buffered IO.

But we forget to consider for unwritten fallocated block in this commit.
This patch tries to fix it for fallocate case, this helps to improve
performance.

Test result:
Storage info: sandisk ultra 64G micro sd card.

touch /mnt/f2fs/file
truncate -s 67108864 /mnt/f2fs/file
fallocate -o 0 -l 67108864 /mnt/f2fs/file
time dd if=/dev/zero of=/mnt/f2fs/file bs=1M count=64 conv=notrunc oflag=direct

Time before applying the patch:
67108864 bytes (67 MB) copied, 36.16 s, 1.9 MB/s
real    0m36.162s
user    0m0.000s
sys     0m0.180s

Time after applying the patch:
67108864 bytes (67 MB) copied, 27.7776 s, 2.4 MB/s
real    0m27.780s
user    0m0.000s
sys     0m0.036s

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8a940e518be8..614e444e5297 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1126,16 +1126,23 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 
 	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
 		return -EPERM;
+
+	dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
+	if (dn->data_blkaddr == NEW_ADDR)
+		goto alloc;
+
 	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
 		return -ENOSPC;
 
+alloc:
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
 	if (dn->ofs_in_node == 0 && dn->inode_page == dn->node_page)
 		seg = CURSEG_DIRECT_IO;
 
-	allocate_data_block(sbi, NULL, NULL_ADDR, &dn->data_blkaddr, &sum, seg);
+	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
+								&sum, seg);
 
 	/* direct IO doesn't use extent cache to maximize the performance */
 	set_data_blkaddr(dn);
@@ -1175,7 +1182,7 @@ static void __allocate_data_blocks(struct inode *inode, loff_t offset,
 			block_t blkaddr;
 
 			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
-			if (blkaddr == NULL_ADDR) {
+			if (blkaddr == NULL_ADDR || blkaddr == NEW_ADDR) {
 				if (__allocate_data_block(&dn))
 					goto sync_out;
 				allocated = true;
-- 
cgit v1.2.3


From 1b3e27a92ab60452b8fbb35e3ba691ac34f2c0fb Mon Sep 17 00:00:00 2001
From: Chao Yu <chao2.yu@samsung.com>
Date: Tue, 24 Mar 2015 13:08:05 +0800
Subject: f2fs: limit b_size of mapped bh in f2fs_map_bh

Map bh over max size which caller defined is not needed, limit it in
f2fs_map_bh.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 614e444e5297..93aae548cf80 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -255,15 +255,13 @@ static void f2fs_map_bh(struct super_block *sb, pgoff_t pgofs,
 			struct extent_info *ei, struct buffer_head *bh_result)
 {
 	unsigned int blkbits = sb->s_blocksize_bits;
-	size_t count;
+	size_t max_size = bh_result->b_size;
+	size_t mapped_size;
 
 	clear_buffer_new(bh_result);
 	map_bh(bh_result, sb, ei->blk + pgofs - ei->fofs);
-	count = ei->fofs + ei->len - pgofs;
-	if (count < (UINT_MAX >> blkbits))
-		bh_result->b_size = (count << blkbits);
-	else
-		bh_result->b_size = UINT_MAX;
+	mapped_size = (ei->fofs + ei->len - pgofs) << blkbits;
+	bh_result->b_size = min(max_size, mapped_size);
 }
 
 static bool lookup_extent_info(struct inode *inode, pgoff_t pgofs,
-- 
cgit v1.2.3


From 17f8c842d24ac054e4212c82b5bd6ae455a334f3 Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@osandov.com>
Date: Mon, 16 Mar 2015 04:33:50 -0700
Subject: Remove rw from {,__,do_}blockdev_direct_IO()

Most filesystems call through to these at some point, so we'll start
here.

Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/affs/file.c      |  2 +-
 fs/block_dev.c      |  5 ++---
 fs/btrfs/inode.c    |  8 ++++----
 fs/direct-io.c      | 39 ++++++++++++++++++---------------------
 fs/ext2/inode.c     |  2 +-
 fs/ext3/inode.c     |  2 +-
 fs/ext4/indirect.c  | 11 ++++++-----
 fs/ext4/inode.c     |  2 +-
 fs/f2fs/data.c      |  2 +-
 fs/fat/inode.c      |  2 +-
 fs/gfs2/aops.c      |  5 ++---
 fs/hfs/inode.c      |  2 +-
 fs/hfsplus/inode.c  |  3 +--
 fs/jfs/inode.c      |  2 +-
 fs/nilfs2/inode.c   |  3 +--
 fs/ocfs2/aops.c     | 16 +++++++---------
 fs/reiserfs/inode.c |  2 +-
 fs/udf/inode.c      |  2 +-
 fs/xfs/xfs_aops.c   |  9 ++++-----
 include/linux/fs.h  | 22 ++++++++++++----------
 20 files changed, 67 insertions(+), 74 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/affs/file.c b/fs/affs/file.c
index 7c1a3d4c19c2..1edc0d4b40db 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -405,7 +405,7 @@ affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 			return 0;
 	}
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, affs_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block);
 	if (ret < 0 && (rw & WRITE))
 		affs_write_failed(mapping, offset + count);
 	return ret;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b5e87896f517..bc23afd35fdb 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -152,9 +152,8 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
-	return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter,
-				    offset, blkdev_get_block,
-				    NULL, NULL, 0);
+	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
+				    blkdev_get_block, NULL, NULL, 0);
 }
 
 int __sync_blockdev(struct block_device *bdev, int wait)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 686331f22b15..e9a3ff8a85fd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8174,10 +8174,10 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		wakeup = false;
 	}
 
-	ret = __blockdev_direct_IO(rw, iocb, inode,
-			BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
-			iter, offset, btrfs_get_blocks_direct, NULL,
-			btrfs_submit_direct, flags);
+	ret = __blockdev_direct_IO(iocb, inode,
+				   BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
+				   iter, offset, btrfs_get_blocks_direct, NULL,
+				   btrfs_submit_direct, flags);
 	if (rw & WRITE) {
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 6fb00e3f1059..c3b560b24a46 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1093,10 +1093,10 @@ static inline int drop_refcount(struct dio *dio)
  * for the whole file.
  */
 static inline ssize_t
-do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, struct iov_iter *iter, loff_t offset, 
-	get_block_t get_block, dio_iodone_t end_io,
-	dio_submit_t submit_io,	int flags)
+do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
+		      struct block_device *bdev, struct iov_iter *iter,
+		      loff_t offset, get_block_t get_block, dio_iodone_t end_io,
+		      dio_submit_t submit_io, int flags)
 {
 	unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits);
 	unsigned blkbits = i_blkbits;
@@ -1110,9 +1110,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	struct blk_plug plug;
 	unsigned long align = offset | iov_iter_alignment(iter);
 
-	if (rw & WRITE)
-		rw = WRITE_ODIRECT;
-
 	/*
 	 * Avoid references to bdev if not absolutely needed to give
 	 * the early prefetch in the caller enough time.
@@ -1127,7 +1124,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	}
 
 	/* watch out for a 0 len io from a tricksy fs */
-	if (rw == READ && !iov_iter_count(iter))
+	if (iov_iter_rw(iter) == READ && !iov_iter_count(iter))
 		return 0;
 
 	dio = kmem_cache_alloc(dio_cache, GFP_KERNEL);
@@ -1143,7 +1140,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 
 	dio->flags = flags;
 	if (dio->flags & DIO_LOCKING) {
-		if (rw == READ) {
+		if (iov_iter_rw(iter) == READ) {
 			struct address_space *mapping =
 					iocb->ki_filp->f_mapping;
 
@@ -1169,19 +1166,19 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	if (is_sync_kiocb(iocb))
 		dio->is_async = false;
 	else if (!(dio->flags & DIO_ASYNC_EXTEND) &&
-            (rw & WRITE) && end > i_size_read(inode))
+		 iov_iter_rw(iter) == WRITE && end > i_size_read(inode))
 		dio->is_async = false;
 	else
 		dio->is_async = true;
 
 	dio->inode = inode;
-	dio->rw = rw;
+	dio->rw = iov_iter_rw(iter) == WRITE ? WRITE_ODIRECT : READ;
 
 	/*
 	 * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
 	 * so that we can call ->fsync.
 	 */
-	if (dio->is_async && (rw & WRITE) &&
+	if (dio->is_async && iov_iter_rw(iter) == WRITE &&
 	    ((iocb->ki_filp->f_flags & O_DSYNC) ||
 	     IS_SYNC(iocb->ki_filp->f_mapping->host))) {
 		retval = dio_set_defer_completion(dio);
@@ -1274,7 +1271,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	 * we can let i_mutex go now that its achieved its purpose
 	 * of protecting us from looking up uninitialized blocks.
 	 */
-	if (rw == READ && (dio->flags & DIO_LOCKING))
+	if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING))
 		mutex_unlock(&dio->inode->i_mutex);
 
 	/*
@@ -1286,7 +1283,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	 */
 	BUG_ON(retval == -EIOCBQUEUED);
 	if (dio->is_async && retval == 0 && dio->result &&
-	    (rw == READ || dio->result == count))
+	    (iov_iter_rw(iter) == READ || dio->result == count))
 		retval = -EIOCBQUEUED;
 	else
 		dio_await_completion(dio);
@@ -1300,11 +1297,11 @@ out:
 	return retval;
 }
 
-ssize_t
-__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, struct iov_iter *iter, loff_t offset,
-	get_block_t get_block, dio_iodone_t end_io,
-	dio_submit_t submit_io,	int flags)
+ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
+			     struct block_device *bdev, struct iov_iter *iter,
+			     loff_t offset, get_block_t get_block,
+			     dio_iodone_t end_io, dio_submit_t submit_io,
+			     int flags)
 {
 	/*
 	 * The block device state is needed in the end to finally
@@ -1318,8 +1315,8 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
 	prefetch(bdev->bd_queue);
 	prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES);
 
-	return do_blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset,
-				     get_block, end_io, submit_io, flags);
+	return do_blockdev_direct_IO(iocb, inode, bdev, iter, offset, get_block,
+				     end_io, submit_io, flags);
 }
 
 EXPORT_SYMBOL(__blockdev_direct_IO);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index df9d6afbc5d5..3cbeb1b63acf 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -864,7 +864,7 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 		ret = dax_do_io(rw, iocb, inode, iter, offset, ext2_get_block,
 				NULL, DIO_LOCKING);
 	else
-		ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+		ret = blockdev_direct_IO(iocb, inode, iter, offset,
 					 ext2_get_block);
 	if (ret < 0 && (rw & WRITE))
 		ext2_write_failed(mapping, offset + count);
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index db07ffbe7c85..6fb376c8d938 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1856,7 +1856,7 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, ext3_get_block);
 	/*
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 740c7871c117..ae4ffc27abc6 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -693,9 +693,10 @@ retry:
 			ret = dax_do_io(rw, iocb, inode, iter, offset,
 					ext4_get_block, NULL, 0);
 		else
-			ret = __blockdev_direct_IO(rw, iocb, inode,
-					inode->i_sb->s_bdev, iter, offset,
-					ext4_get_block, NULL, NULL, 0);
+			ret = __blockdev_direct_IO(iocb, inode,
+						   inode->i_sb->s_bdev, iter,
+						   offset, ext4_get_block, NULL,
+						   NULL, 0);
 		inode_dio_done(inode);
 	} else {
 locked:
@@ -703,8 +704,8 @@ locked:
 			ret = dax_do_io(rw, iocb, inode, iter, offset,
 					ext4_get_block, NULL, DIO_LOCKING);
 		else
-			ret = blockdev_direct_IO(rw, iocb, inode, iter,
-					offset, ext4_get_block);
+			ret = blockdev_direct_IO(iocb, inode, iter, offset,
+						 ext4_get_block);
 
 		if (unlikely((rw & WRITE) && ret < 0)) {
 			loff_t isize = i_size_read(inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index a3f451370bef..ec049c04b197 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3037,7 +3037,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 		ret = dax_do_io(rw, iocb, inode, iter, offset, get_block_func,
 				ext4_end_io_dio, dio_flags);
 	else
-		ret = __blockdev_direct_IO(rw, iocb, inode,
+		ret = __blockdev_direct_IO(iocb, inode,
 					   inode->i_sb->s_bdev, iter, offset,
 					   get_block_func,
 					   ext4_end_io_dio, NULL, dio_flags);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 497f8515d205..e16adebcb9b6 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1159,7 +1159,7 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 	if (rw & WRITE)
 		__allocate_data_blocks(inode, offset, count);
 
-	err = blockdev_direct_IO(rw, iocb, inode, iter, offset, get_data_block);
+	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block);
 	if (err < 0 && (rw & WRITE))
 		f2fs_write_failed(mapping, offset + count);
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 8521207de229..a1a39f571e78 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -274,7 +274,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	 * FAT need to use the DIO_LOCKING for avoiding the race
 	 * condition of fat_get_block() and ->truncate().
 	 */
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, fat_get_block);
 	if (ret < 0 && (rw & WRITE))
 		fat_write_failed(mapping, offset + count);
 
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index fe6634d25d1d..59983a18cab4 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1095,9 +1095,8 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 			truncate_inode_pages_range(mapping, lstart, end);
 	}
 
-	rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
-				  iter, offset,
-				  gfs2_get_block_direct, NULL, NULL, 0);
+	rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
+				  offset, gfs2_get_block_direct, NULL, NULL, 0);
 out:
 	gfs2_glock_dq(&gh);
 	gfs2_holder_uninit(&gh);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 9337065bcc67..e92d175d1fd7 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -133,7 +133,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, hfs_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, hfs_get_block);
 
 	/*
 	 * In case of error extending write may have instantiated a few
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 5f86cadb0542..2a98dc07c22c 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -131,8 +131,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, 
-				 hfsplus_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, hfsplus_get_block);
 
 	/*
 	 * In case of error extending write may have instantiated a few
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 3197aed10614..c20f7883543f 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -339,7 +339,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, jfs_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block);
 
 	/*
 	 * In case of error extending write may have instantiated a few
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index ab4987bc637f..3727b8caa46e 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -318,8 +318,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 		return 0;
 
 	/* Needs synchronization with the cleaner */
-	size = blockdev_direct_IO(rw, iocb, inode, iter, offset,
-				  nilfs_get_block);
+	size = blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block);
 
 	/*
 	 * In case of error extending write may have instantiated a few
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index e1bf18c5d25e..68cb199fb2b6 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -738,10 +738,9 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
 		di_bh = NULL;
 	}
 
-	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
-			iter, offset,
-			ocfs2_direct_IO_get_blocks,
-			ocfs2_dio_end_io, NULL, 0);
+	written = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
+				       offset, ocfs2_direct_IO_get_blocks,
+				       ocfs2_dio_end_io, NULL, 0);
 	if (unlikely(written < 0)) {
 		loff_t i_size = i_size_read(inode);
 
@@ -844,11 +843,10 @@ static ssize_t ocfs2_direct_IO(int rw,
 		return 0;
 
 	if (rw == READ)
-		return __blockdev_direct_IO(rw, iocb, inode,
-				    inode->i_sb->s_bdev,
-				    iter, offset,
-				    ocfs2_direct_IO_get_blocks,
-				    ocfs2_dio_end_io, NULL, 0);
+		return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+					    iter, offset,
+					    ocfs2_direct_IO_get_blocks,
+					    ocfs2_dio_end_io, NULL, 0);
 	else
 		return ocfs2_direct_IO_write(iocb, iter, offset);
 }
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index 9312b7842e03..a51e9177b056 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3286,7 +3286,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset,
+	ret = blockdev_direct_IO(iocb, inode, iter, offset,
 				 reiserfs_get_blocks_direct_io);
 
 	/*
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 9c1fbd23913d..3adf49c01c19 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -225,7 +225,7 @@ static ssize_t udf_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, udf_get_block);
+	ret = blockdev_direct_IO(iocb, inode, iter, offset, udf_get_block);
 	if (unlikely(ret < 0 && (rw & WRITE)))
 		udf_write_failed(mapping, offset + count);
 	return ret;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4f8cdc59bc38..5ca504c66e85 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1504,14 +1504,13 @@ xfs_vm_direct_IO(
 	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
 
 	if (rw & WRITE) {
-		return __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
-					    offset, xfs_get_blocks_direct,
+		return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
+					    xfs_get_blocks_direct,
 					    xfs_end_io_direct_write, NULL,
 					    DIO_ASYNC_EXTEND);
 	}
-	return __blockdev_direct_IO(rw, iocb, inode, bdev, iter,
-				    offset, xfs_get_blocks_direct,
-				    NULL, NULL, 0);
+	return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
+				    xfs_get_blocks_direct, NULL, NULL, 0);
 }
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f1e3f65255a8..c67b6de8be33 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2634,16 +2634,18 @@ enum {
 
 void dio_end_io(struct bio *bio, int error);
 
-ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
-	struct block_device *bdev, struct iov_iter *iter, loff_t offset,
-	get_block_t get_block, dio_iodone_t end_io,
-	dio_submit_t submit_io,	int flags);
-
-static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
-		struct inode *inode, struct iov_iter *iter, loff_t offset,
-		get_block_t get_block)
-{
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter,
+ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
+			     struct block_device *bdev, struct iov_iter *iter,
+			     loff_t offset, get_block_t get_block,
+			     dio_iodone_t end_io, dio_submit_t submit_io,
+			     int flags);
+
+static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
+					 struct inode *inode,
+					 struct iov_iter *iter, loff_t offset,
+					 get_block_t get_block)
+{
+	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
 				    offset, get_block, NULL, NULL,
 				    DIO_LOCKING | DIO_SKIP_HOLES);
 }
-- 
cgit v1.2.3


From 6f67376318abea58589ebe6d69dffeabb6f6c26a Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@osandov.com>
Date: Mon, 16 Mar 2015 04:33:52 -0700
Subject: direct_IO: use iov_iter_rw() instead of rw everywhere

The rw parameter to direct_IO is redundant with iov_iter->type, and
treated slightly differently just about everywhere it's used: some users
do rw & WRITE, and others do rw == WRITE where they should be doing a
bitwise check. Simplify this with the new iov_iter_rw() helper, which
always returns either READ or WRITE.

Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/staging/lustre/lustre/llite/rw26.c | 18 +++++++++---------
 fs/9p/vfs_addr.c                           |  2 +-
 fs/affs/file.c                             |  4 ++--
 fs/btrfs/inode.c                           | 10 +++++-----
 fs/ext2/inode.c                            |  2 +-
 fs/ext3/inode.c                            |  8 ++++----
 fs/ext4/ext4.h                             |  4 ++--
 fs/ext4/indirect.c                         | 10 +++++-----
 fs/ext4/inode.c                            | 20 ++++++++++----------
 fs/f2fs/data.c                             | 16 ++++++++--------
 fs/fat/inode.c                             |  4 ++--
 fs/fuse/file.c                             | 13 +++++++------
 fs/gfs2/aops.c                             |  7 +++----
 fs/hfs/inode.c                             |  2 +-
 fs/hfsplus/inode.c                         |  2 +-
 fs/jfs/inode.c                             |  2 +-
 fs/nfs/direct.c                            |  2 +-
 fs/nilfs2/inode.c                          |  4 ++--
 fs/ocfs2/aops.c                            |  2 +-
 fs/reiserfs/inode.c                        |  2 +-
 fs/udf/inode.c                             |  2 +-
 fs/xfs/xfs_aops.c                          |  2 +-
 22 files changed, 69 insertions(+), 69 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c
index 2f21304046aa..3aa9de6bcc40 100644
--- a/drivers/staging/lustre/lustre/llite/rw26.c
+++ b/drivers/staging/lustre/lustre/llite/rw26.c
@@ -399,7 +399,7 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 	 *    size changing by concurrent truncates and writes.
 	 * 1. Need inode mutex to operate transient pages.
 	 */
-	if (rw == READ)
+	if (iov_iter_rw(iter) == READ)
 		mutex_lock(&inode->i_mutex);
 
 	LASSERT(obj->cob_transient_pages == 0);
@@ -408,7 +408,7 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 		size_t offs;
 
 		count = min_t(size_t, iov_iter_count(iter), size);
-		if (rw == READ) {
+		if (iov_iter_rw(iter) == READ) {
 			if (file_offset >= i_size_read(inode))
 				break;
 			if (file_offset + count > i_size_read(inode))
@@ -418,11 +418,11 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 		result = iov_iter_get_pages_alloc(iter, &pages, count, &offs);
 		if (likely(result > 0)) {
 			int n = DIV_ROUND_UP(result + offs, PAGE_SIZE);
-			result = ll_direct_IO_26_seg(env, io, rw, inode,
-						     file->f_mapping,
-						     result, file_offset,
-						     pages, n);
-			ll_free_user_pages(pages, n, rw==READ);
+			result = ll_direct_IO_26_seg(env, io, iov_iter_rw(iter),
+						     inode, file->f_mapping,
+						     result, file_offset, pages,
+						     n);
+			ll_free_user_pages(pages, n, iov_iter_rw(iter) == READ);
 		}
 		if (unlikely(result <= 0)) {
 			/* If we can't allocate a large enough buffer
@@ -449,11 +449,11 @@ static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
 	}
 out:
 	LASSERT(obj->cob_transient_pages == 0);
-	if (rw == READ)
+	if (iov_iter_rw(iter) == READ)
 		mutex_unlock(&inode->i_mutex);
 
 	if (tot_bytes > 0) {
-		if (rw == WRITE) {
+		if (iov_iter_rw(iter) == WRITE) {
 			struct lov_stripe_md *lsm;
 
 			lsm = ccc_inode_lsm_get(inode);
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 2e38f9a5b472..dd5543b1d183 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -253,7 +253,7 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 	struct file *file = iocb->ki_filp;
 	ssize_t n;
 	int err = 0;
-	if (rw & WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		n = p9_client_write(file->private_data, pos, iter, &err);
 		if (n) {
 			struct inode *inode = file_inode(file);
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 1edc0d4b40db..7f05a468d594 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -398,7 +398,7 @@ affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		loff_t size = offset + count;
 
 		if (AFFS_I(inode)->mmu_private < size)
@@ -406,7 +406,7 @@ affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	ret = blockdev_direct_IO(iocb, inode, iter, offset, affs_get_block);
-	if (ret < 0 && (rw & WRITE))
+	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		affs_write_failed(mapping, offset + count);
 	return ret;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e9a3ff8a85fd..ca69e83d4f3c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8081,7 +8081,7 @@ free_ordered:
 	bio_endio(dio_bio, ret);
 }
 
-static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb,
+static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb,
 			const struct iov_iter *iter, loff_t offset)
 {
 	int seg;
@@ -8096,7 +8096,7 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io
 		goto out;
 
 	/* If this is a write we don't need to check anymore */
-	if (rw & WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		return 0;
 	/*
 	 * Check to make sure we don't have duplicate iov_base's in this
@@ -8126,7 +8126,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 	bool relock = false;
 	ssize_t ret;
 
-	if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset))
+	if (check_direct_IO(BTRFS_I(inode)->root, iocb, iter, offset))
 		return 0;
 
 	atomic_inc(&inode->i_dio_count);
@@ -8144,7 +8144,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		filemap_fdatawrite_range(inode->i_mapping, offset,
 					 offset + count - 1);
 
-	if (rw & WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		/*
 		 * If the write DIO is beyond the EOF, we need update
 		 * the isize, but it is protected by i_mutex. So we can
@@ -8178,7 +8178,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 				   BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
 				   iter, offset, btrfs_get_blocks_direct, NULL,
 				   btrfs_submit_direct, flags);
-	if (rw & WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED)
 			btrfs_delalloc_release_space(inode, count);
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 14e8d1752685..685e514c57dd 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -866,7 +866,7 @@ ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	else
 		ret = blockdev_direct_IO(iocb, inode, iter, offset,
 					 ext2_get_block);
-	if (ret < 0 && (rw & WRITE))
+	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		ext2_write_failed(mapping, offset + count);
 	return ret;
 }
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 6fb376c8d938..c70839d26ccd 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1832,9 +1832,9 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	int retries = 0;
 
-	trace_ext3_direct_IO_enter(inode, offset, count, rw);
+	trace_ext3_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		loff_t final_size = offset + count;
 
 		if (final_size > inode->i_size) {
@@ -1861,7 +1861,7 @@ retry:
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
-	if (unlikely((rw & WRITE) && ret < 0)) {
+	if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + count;
 
@@ -1908,7 +1908,7 @@ retry:
 			ret = err;
 	}
 out:
-	trace_ext3_direct_IO_exit(inode, offset, count, rw, ret);
+	trace_ext3_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
 	return ret;
 }
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f63c3d5805c4..2031c994024e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2152,8 +2152,8 @@ extern void ext4_da_update_reserve_space(struct inode *inode,
 /* indirect.c */
 extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 				struct ext4_map_blocks *map, int flags);
-extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
-				struct iov_iter *iter, loff_t offset);
+extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+				  loff_t offset);
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index cd81d01da0b0..3580629e42d3 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -642,8 +642,8 @@ out:
  * crashes then stale disk data _may_ be exposed inside the file. But current
  * VFS code falls back into buffered path in that case so we are safe.
  */
-ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
-			   struct iov_iter *iter, loff_t offset)
+ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			   loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -654,7 +654,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	int retries = 0;
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		loff_t final_size = offset + count;
 
 		if (final_size > inode->i_size) {
@@ -676,7 +676,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retry:
-	if (rw == READ && ext4_should_dioread_nolock(inode)) {
+	if (iov_iter_rw(iter) == READ && ext4_should_dioread_nolock(inode)) {
 		/*
 		 * Nolock dioread optimization may be dynamically disabled
 		 * via ext4_inode_block_unlocked_dio(). Check inode's state
@@ -707,7 +707,7 @@ locked:
 			ret = blockdev_direct_IO(iocb, inode, iter, offset,
 						 ext4_get_block);
 
-		if (unlikely((rw & WRITE) && ret < 0)) {
+		if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 			loff_t isize = i_size_read(inode);
 			loff_t end = offset + count;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 76b8cba5d041..cf6ba6536035 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2952,8 +2952,8 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
  * if the machine crashes during the write.
  *
  */
-static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
-			      struct iov_iter *iter, loff_t offset)
+static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+				  loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
@@ -2966,8 +2966,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	ext4_io_end_t *io_end = NULL;
 
 	/* Use the old path for reads and writes beyond i_size. */
-	if (rw != WRITE || final_size > inode->i_size)
-		return ext4_ind_direct_IO(rw, iocb, iter, offset);
+	if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
+		return ext4_ind_direct_IO(iocb, iter, offset);
 
 	BUG_ON(iocb->private == NULL);
 
@@ -2976,7 +2976,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	 * conversion. This also disallows race between truncate() and
 	 * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
 	 */
-	if (rw == WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		atomic_inc(&inode->i_dio_count);
 
 	/* If we do a overwrite dio, i_mutex locking can be released */
@@ -3078,7 +3078,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
 	}
 
 retake_lock:
-	if (rw == WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		inode_dio_done(inode);
 	/* take i_mutex locking again if we do a ovewrite dio */
 	if (overwrite) {
@@ -3107,12 +3107,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
 	if (ext4_has_inline_data(inode))
 		return 0;
 
-	trace_ext4_direct_IO_enter(inode, offset, count, rw);
+	trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		ret = ext4_ext_direct_IO(rw, iocb, iter, offset);
+		ret = ext4_ext_direct_IO(iocb, iter, offset);
 	else
-		ret = ext4_ind_direct_IO(rw, iocb, iter, offset);
-	trace_ext4_direct_IO_exit(inode, offset, count, rw, ret);
+		ret = ext4_ind_direct_IO(iocb, iter, offset);
+	trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
 	return ret;
 }
 
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index e16adebcb9b6..ce25f62edfa7 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1118,12 +1118,12 @@ static int f2fs_write_end(struct file *file,
 	return copied;
 }
 
-static int check_direct_IO(struct inode *inode, int rw,
-		struct iov_iter *iter, loff_t offset)
+static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
+			   loff_t offset)
 {
 	unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
 
-	if (rw == READ)
+	if (iov_iter_rw(iter) == READ)
 		return 0;
 
 	if (offset & blocksize_mask)
@@ -1151,19 +1151,19 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
 			return err;
 	}
 
-	if (check_direct_IO(inode, rw, iter, offset))
+	if (check_direct_IO(inode, iter, offset))
 		return 0;
 
-	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
+	trace_f2fs_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
 
-	if (rw & WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		__allocate_data_blocks(inode, offset, count);
 
 	err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block);
-	if (err < 0 && (rw & WRITE))
+	if (err < 0 && iov_iter_rw(iter) == WRITE)
 		f2fs_write_failed(mapping, offset + count);
 
-	trace_f2fs_direct_IO_exit(inode, offset, count, rw, err);
+	trace_f2fs_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), err);
 
 	return err;
 }
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index a1a39f571e78..342d791b28db 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -255,7 +255,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	size_t count = iov_iter_count(iter);
 	ssize_t ret;
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		/*
 		 * FIXME: blockdev_direct_IO() doesn't use ->write_begin(),
 		 * so we need to update the ->mmu_private to block boundary.
@@ -275,7 +275,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	 * condition of fat_get_block() and ->truncate().
 	 */
 	ret = blockdev_direct_IO(iocb, inode, iter, offset, fat_get_block);
-	if (ret < 0 && (rw & WRITE))
+	if (ret < 0 && iov_iter_rw(iter) == WRITE)
 		fat_write_failed(mapping, offset + count);
 
 	return ret;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index e1afdd7abf90..c1a67da6a8a0 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2800,11 +2800,11 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	inode = file->f_mapping->host;
 	i_size = i_size_read(inode);
 
-	if ((rw == READ) && (offset > i_size))
+	if ((iov_iter_rw(iter) == READ) && (offset > i_size))
 		return 0;
 
 	/* optimization for short read */
-	if (async_dio && rw != WRITE && offset + count > i_size) {
+	if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) {
 		if (offset >= i_size)
 			return 0;
 		count = min_t(loff_t, count, fuse_round_up(i_size - offset));
@@ -2819,7 +2819,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	io->bytes = -1;
 	io->size = 0;
 	io->offset = offset;
-	io->write = (rw == WRITE);
+	io->write = (iov_iter_rw(iter) == WRITE);
 	io->err = 0;
 	io->file = file;
 	/*
@@ -2834,13 +2834,14 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	 * to wait on real async I/O requests, so we must submit this request
 	 * synchronously.
 	 */
-	if (!is_sync_kiocb(iocb) && (offset + count > i_size) && rw == WRITE)
+	if (!is_sync_kiocb(iocb) && (offset + count > i_size) &&
+	    iov_iter_rw(iter) == WRITE)
 		io->async = false;
 
 	if (io->async && is_sync_kiocb(iocb))
 		io->done = &wait;
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		ret = generic_write_checks(file, &pos, &count, 0);
 		if (!ret) {
 			iov_iter_truncate(iter, count);
@@ -2865,7 +2866,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 
 	kfree(io);
 
-	if (rw == WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		if (ret > 0)
 			fuse_write_update_size(inode, pos);
 		else if (ret < 0 && offset + count > i_size)
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 59983a18cab4..e22e6e686a11 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1016,13 +1016,12 @@ out:
 /**
  * gfs2_ok_for_dio - check that dio is valid on this file
  * @ip: The inode
- * @rw: READ or WRITE
  * @offset: The offset at which we are reading or writing
  *
  * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
  *          1 (to accept the i/o request)
  */
-static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset)
+static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset)
 {
 	/*
 	 * Should we return an error here? I can't see that O_DIRECT for
@@ -1061,7 +1060,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 	rv = gfs2_glock_nq(&gh);
 	if (rv)
 		return rv;
-	rv = gfs2_ok_for_dio(ip, rw, offset);
+	rv = gfs2_ok_for_dio(ip, offset);
 	if (rv != 1)
 		goto out; /* dio not valid, fall back to buffered i/o */
 
@@ -1091,7 +1090,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 		rv = filemap_write_and_wait_range(mapping, lstart, end);
 		if (rv)
 			goto out;
-		if (rw == WRITE)
+		if (iov_iter_rw(iter) == WRITE)
 			truncate_inode_pages_range(mapping, lstart, end);
 	}
 
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index e92d175d1fd7..0085d527a55c 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -139,7 +139,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
-	if (unlikely((rw & WRITE) && ret < 0)) {
+	if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + count;
 
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 2a98dc07c22c..afcde36b506b 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -137,7 +137,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
-	if (unlikely((rw & WRITE) && ret < 0)) {
+	if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + count;
 
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index c20f7883543f..e7047b63ffc5 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -345,7 +345,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
-	if (unlikely((rw & WRITE) && ret < 0)) {
+	if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + count;
 
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index c3929fb2ab26..e8482b8f4830 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -267,7 +267,7 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t
 #else
 	VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
 
-	if (rw == READ)
+	if (iov_iter_rw(iter) == READ)
 		return nfs_file_direct_read(iocb, iter, pos);
 	return nfs_file_direct_write(iocb, iter, pos);
 #endif /* CONFIG_NFS_SWAP */
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 3727b8caa46e..4726f1493d5d 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -314,7 +314,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	size_t count = iov_iter_count(iter);
 	ssize_t size;
 
-	if (rw == WRITE)
+	if (iov_iter_rw(iter) == WRITE)
 		return 0;
 
 	/* Needs synchronization with the cleaner */
@@ -324,7 +324,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
-	if (unlikely((rw & WRITE) && size < 0)) {
+	if (unlikely(iov_iter_rw(iter) == WRITE && size < 0)) {
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + count;
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 68cb199fb2b6..0ee9474cca46 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -842,7 +842,7 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	if (rw == READ)
+	if (iov_iter_rw(iter) == READ)
 		return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
 					    iter, offset,
 					    ocfs2_direct_IO_get_blocks,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index a51e9177b056..d61ab13244a8 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3293,7 +3293,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
 	 * In case of error extending write may have instantiated a few
 	 * blocks outside i_size. Trim these off again.
 	 */
-	if (unlikely((rw & WRITE) && ret < 0)) {
+	if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + count;
 
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 3adf49c01c19..a685aea93068 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -226,7 +226,7 @@ static ssize_t udf_direct_IO(int rw, struct kiocb *iocb,
 	ssize_t ret;
 
 	ret = blockdev_direct_IO(iocb, inode, iter, offset, udf_get_block);
-	if (unlikely(ret < 0 && (rw & WRITE)))
+	if (unlikely(ret < 0 && iov_iter_rw(iter) == WRITE))
 		udf_write_failed(mapping, offset + count);
 	return ret;
 }
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 5ca504c66e85..532d5279df2f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1503,7 +1503,7 @@ xfs_vm_direct_IO(
 	struct inode		*inode = iocb->ki_filp->f_mapping->host;
 	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
 
-	if (rw & WRITE) {
+	if (iov_iter_rw(iter) == WRITE) {
 		return __blockdev_direct_IO(iocb, inode, bdev, iter, offset,
 					    xfs_get_blocks_direct,
 					    xfs_end_io_direct_write, NULL,
-- 
cgit v1.2.3


From 22c6186ecea0be9eff1c399298ad36e94a59995f Mon Sep 17 00:00:00 2001
From: Omar Sandoval <osandov@osandov.com>
Date: Mon, 16 Mar 2015 04:33:53 -0700
Subject: direct_IO: remove rw from a_ops->direct_IO()

Now that no one is using rw, remove it completely.

Signed-off-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/Locking          | 2 +-
 Documentation/filesystems/vfs.txt          | 2 +-
 drivers/staging/lustre/lustre/llite/rw26.c | 4 ++--
 fs/9p/vfs_addr.c                           | 3 +--
 fs/affs/file.c                             | 3 +--
 fs/block_dev.c                             | 3 +--
 fs/btrfs/inode.c                           | 4 ++--
 fs/ceph/addr.c                             | 3 +--
 fs/cifs/file.c                             | 3 +--
 fs/exofs/inode.c                           | 4 ++--
 fs/ext2/inode.c                            | 3 +--
 fs/ext3/inode.c                            | 4 ++--
 fs/ext4/inode.c                            | 4 ++--
 fs/f2fs/data.c                             | 4 ++--
 fs/fat/inode.c                             | 3 +--
 fs/fuse/file.c                             | 3 +--
 fs/gfs2/aops.c                             | 4 ++--
 fs/hfs/inode.c                             | 4 ++--
 fs/hfsplus/inode.c                         | 4 ++--
 fs/jfs/inode.c                             | 4 ++--
 fs/nfs/direct.c                            | 3 +--
 fs/nilfs2/inode.c                          | 3 +--
 fs/ocfs2/aops.c                            | 4 +---
 fs/reiserfs/inode.c                        | 4 ++--
 fs/udf/file.c                              | 3 +--
 fs/udf/inode.c                             | 3 +--
 fs/xfs/xfs_aops.c                          | 1 -
 include/linux/fs.h                         | 2 +-
 include/linux/nfs_fs.h                     | 2 +-
 mm/filemap.c                               | 4 ++--
 mm/page_io.c                               | 4 +---
 31 files changed, 42 insertions(+), 59 deletions(-)

(limited to 'fs/f2fs/data.c')

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index c3cd6279e92e..7cdbca44e343 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -196,7 +196,7 @@ prototypes:
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	int (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
+	int (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
 	int (*migratepage)(struct address_space *, struct page *, struct page *);
 	int (*launder_page)(struct page *);
 	int (*is_partially_uptodate)(struct page *, unsigned long, unsigned long);
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 207cdca68bed..5d833b32bbcd 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -590,7 +590,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, int);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
+	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
 	/* migrate the contents of a page to the specified target */
 	int (*migratepage) (struct page *, struct page *);
 	int (*launder_page) (struct page *);
diff --git a/drivers/staging/lustre/lustre/llite/rw26.c b/drivers/staging/lustre/lustre/llite/rw26.c
index 3aa9de6bcc40..0d7ce6b0e23c 100644
--- a/drivers/staging/lustre/lustre/llite/rw26.c
+++ b/drivers/staging/lustre/lustre/llite/rw26.c
@@ -359,8 +359,8 @@ static ssize_t ll_direct_IO_26_seg(const struct lu_env *env, struct cl_io *io,
  * up to 22MB for 128kB kmalloc and up to 682MB for 4MB kmalloc. */
 #define MAX_DIO_SIZE ((MAX_MALLOC / sizeof(struct brw_page) * PAGE_CACHE_SIZE) & \
 		      ~(DT_MAX_BRW_SIZE - 1))
-static ssize_t ll_direct_IO_26(int rw, struct kiocb *iocb,
-			       struct iov_iter *iter, loff_t file_offset)
+static ssize_t ll_direct_IO_26(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t file_offset)
 {
 	struct lu_env *env;
 	struct cl_io *io;
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index dd5543b1d183..be35d05a4d0e 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -230,7 +230,6 @@ static int v9fs_launder_page(struct page *page)
 
 /**
  * v9fs_direct_IO - 9P address space operation for direct I/O
- * @rw: direction (read or write)
  * @iocb: target I/O control block
  * @iov: array of vectors that define I/O buffer
  * @pos: offset in file to begin the operation
@@ -248,7 +247,7 @@ static int v9fs_launder_page(struct page *page)
  *
  */
 static ssize_t
-v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
 	struct file *file = iocb->ki_filp;
 	ssize_t n;
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 7f05a468d594..dcf27951781c 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -389,8 +389,7 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
 }
 
 static ssize_t
-affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
-	       loff_t offset)
+affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index bc23afd35fdb..6e3de63c3055 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -146,8 +146,7 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
 }
 
 static ssize_t
-blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
-			loff_t offset)
+blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ca69e83d4f3c..43192e10cc43 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8114,8 +8114,8 @@ out:
 	return retval;
 }
 
-static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
-			struct iov_iter *iter, loff_t offset)
+static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index fd5599d32362..155ab9c0246b 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1198,8 +1198,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
  * intercept O_DIRECT reads and writes early, this function should
  * never get called.
  */
-static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
-			      struct iov_iter *iter,
+static ssize_t ceph_direct_io(struct kiocb *iocb, struct iov_iter *iter,
 			      loff_t pos)
 {
 	WARN_ON(1);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ca30c391a894..72394c5abd0f 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3877,8 +3877,7 @@ void cifs_oplock_break(struct work_struct *work)
  * Direct IO is not yet supported in the cached mode. 
  */
 static ssize_t
-cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter,
-               loff_t pos)
+cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
         /*
          * FIXME
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index a198e94813fe..35073aaec6e0 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -963,8 +963,8 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset,
 
 
  /* TODO: Should be easy enough to do proprly */
-static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb,
-		struct iov_iter *iter, loff_t offset)
+static ssize_t exofs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			       loff_t offset)
 {
 	return 0;
 }
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 685e514c57dd..e1abf75e994c 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -851,8 +851,7 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block)
 }
 
 static ssize_t
-ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
-			loff_t offset)
+ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index c70839d26ccd..13c0868c7160 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1820,8 +1820,8 @@ static int ext3_releasepage(struct page *page, gfp_t wait)
  * crashes then stale disk data _may_ be exposed inside the file. But current
  * VFS code falls back into buffered path in that case so we are safe.
  */
-static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
-			struct iov_iter *iter, loff_t offset)
+static ssize_t ext3_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			      loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cf6ba6536035..42c942a950e1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3089,8 +3089,8 @@ retake_lock:
 	return ret;
 }
 
-static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb,
-			      struct iov_iter *iter, loff_t offset)
+static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			      loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index ce25f62edfa7..319eda511c4f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1135,8 +1135,8 @@ static int check_direct_IO(struct inode *inode, struct iov_iter *iter,
 	return 0;
 }
 
-static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
-		struct iov_iter *iter, loff_t offset)
+static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			      loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 342d791b28db..41b729933638 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -245,8 +245,7 @@ static int fat_write_end(struct file *file, struct address_space *mapping,
 	return err;
 }
 
-static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
-			     struct iov_iter *iter,
+static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			     loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index c1a67da6a8a0..3d355e946991 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2782,8 +2782,7 @@ static inline loff_t fuse_round_up(loff_t off)
 }
 
 static ssize_t
-fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
-			loff_t offset)
+fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
 	ssize_t ret = 0;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index e22e6e686a11..20dd33da92de 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1038,8 +1038,8 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset)
 
 
 
-static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
-			      struct iov_iter *iter, loff_t offset)
+static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			      loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 0085d527a55c..75fd5d873c19 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -124,8 +124,8 @@ static int hfs_releasepage(struct page *page, gfp_t mask)
 	return res ? try_to_free_buffers(page) : 0;
 }
 
-static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
-		struct iov_iter *iter, loff_t offset)
+static ssize_t hfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			     loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index afcde36b506b..a43811f90935 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -122,8 +122,8 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
 	return res ? try_to_free_buffers(page) : 0;
 }
 
-static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
-		struct iov_iter *iter, loff_t offset)
+static ssize_t hfsplus_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+				 loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index e7047b63ffc5..070dc4b33544 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -330,8 +330,8 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block)
 	return generic_block_bmap(mapping, block, jfs_get_block);
 }
 
-static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
-	struct iov_iter *iter, loff_t offset)
+static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+			     loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index e8482b8f4830..06503bc604e1 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -240,7 +240,6 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
 
 /**
  * nfs_direct_IO - NFS address space operation for direct I/O
- * @rw: direction (read or write)
  * @iocb: target I/O control block
  * @iov: array of vectors that define I/O buffer
  * @pos: offset in file to begin the operation
@@ -251,7 +250,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
  * shunt off direct read and write requests before the VFS gets them,
  * so this method is only ever called for swap.
  */
-ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
 {
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 4726f1493d5d..36f057fa8aa3 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -305,8 +305,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 }
 
 static ssize_t
-nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
-		loff_t offset)
+nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 0ee9474cca46..28b5ad81bbec 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -818,9 +818,7 @@ out:
 	return ret;
 }
 
-static ssize_t ocfs2_direct_IO(int rw,
-			       struct kiocb *iocb,
-			       struct iov_iter *iter,
+static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			       loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index d61ab13244a8..742242b60972 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3278,8 +3278,8 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags)
  * We thank Mingming Cao for helping us understand in great detail what
  * to do in this section of the code.
  */
-static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
-				  struct iov_iter *iter, loff_t offset)
+static ssize_t reiserfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+				  loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
diff --git a/fs/udf/file.c b/fs/udf/file.c
index 74050bff64f4..78d42548b260 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -100,8 +100,7 @@ static int udf_adinicb_write_begin(struct file *file,
 	return 0;
 }
 
-static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb,
-				     struct iov_iter *iter,
+static ssize_t udf_adinicb_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 				     loff_t offset)
 {
 	/* Fallback to buffered I/O. */
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index a685aea93068..4f178c83b04f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -215,8 +215,7 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static ssize_t udf_direct_IO(int rw, struct kiocb *iocb,
-			     struct iov_iter *iter,
+static ssize_t udf_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
 			     loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 532d5279df2f..1d8eef9cf0f5 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1495,7 +1495,6 @@ xfs_end_io_direct_write(
 
 STATIC ssize_t
 xfs_vm_direct_IO(
-	int			rw,
 	struct kiocb		*iocb,
 	struct iov_iter		*iter,
 	loff_t			offset)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 295bc589fe1b..72e3759de8c3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -383,7 +383,7 @@ struct address_space_operations {
 	void (*invalidatepage) (struct page *, unsigned int, unsigned int);
 	int (*releasepage) (struct page *, gfp_t);
 	void (*freepage)(struct page *);
-	ssize_t (*direct_IO)(int, struct kiocb *, struct iov_iter *iter, loff_t offset);
+	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter, loff_t offset);
 	/*
 	 * migrate the contents of a page to the specified target. If
 	 * migrate_mode is MIGRATE_ASYNC, it must not block.
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index b01ccf371fdc..3d1b0d2fe55e 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -447,7 +447,7 @@ static inline struct rpc_cred *nfs_file_cred(struct file *file)
 /*
  * linux/fs/nfs/direct.c
  */
-extern ssize_t nfs_direct_IO(int, struct kiocb *, struct iov_iter *, loff_t);
+extern ssize_t nfs_direct_IO(struct kiocb *, struct iov_iter *, loff_t);
 extern ssize_t nfs_file_direct_read(struct kiocb *iocb,
 			struct iov_iter *iter,
 			loff_t pos);
diff --git a/mm/filemap.c b/mm/filemap.c
index 876f4e6f3ed6..9920db455f05 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1707,7 +1707,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 					pos + count - 1);
 		if (!retval) {
 			struct iov_iter data = *iter;
-			retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos);
+			retval = mapping->a_ops->direct_IO(iocb, &data, pos);
 		}
 
 		if (retval > 0) {
@@ -2395,7 +2395,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos)
 	}
 
 	data = *from;
-	written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos);
+	written = mapping->a_ops->direct_IO(iocb, &data, pos);
 
 	/*
 	 * Finally, try again to invalidate clean pages which might have been
diff --git a/mm/page_io.c b/mm/page_io.c
index a96c8562d835..6424869e275e 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -277,9 +277,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 
 		set_page_writeback(page);
 		unlock_page(page);
-		ret = mapping->a_ops->direct_IO(ITER_BVEC | WRITE,
-						&kiocb, &from,
-						kiocb.ki_pos);
+		ret = mapping->a_ops->direct_IO(&kiocb, &from, kiocb.ki_pos);
 		if (ret == PAGE_SIZE) {
 			count_vm_event(PSWPOUT);
 			ret = 0;
-- 
cgit v1.2.3


From 5463e7c18e51152104aba9614e6abfc039a8b710 Mon Sep 17 00:00:00 2001
From: Jaegeuk Kim <jaegeuk@kernel.org>
Date: Tue, 21 Apr 2015 10:40:54 -0700
Subject: Revert "f2fs: enhance multi-threads performance"

This reports performance regression by Yuanhan Liu.
The basic idea was to reduce one-point mutex, but it turns out this causes
another contention like context swithes.

https://lkml.org/lkml/2015/4/21/11

Until finishing the analysis on this issue, I'd like to revert this for a while.

This reverts commit 78373b7319abdf15050af5b1632c4c8b8b398f33.
---
 fs/f2fs/data.c  | 7 +++++++
 fs/f2fs/f2fs.h  | 1 +
 fs/f2fs/super.c | 1 +
 3 files changed, 9 insertions(+)

(limited to 'fs/f2fs/data.c')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index b91b0e10678e..1e1aae669fa8 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1513,6 +1513,7 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	bool locked = false;
 	int ret;
 	long diff;
 
@@ -1533,7 +1534,13 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 
 	diff = nr_pages_to_write(sbi, DATA, wbc);
 
+	if (!S_ISDIR(inode->i_mode)) {
+		mutex_lock(&sbi->writepages);
+		locked = true;
+	}
 	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
+	if (locked)
+		mutex_unlock(&sbi->writepages);
 
 	f2fs_submit_merged_bio(sbi, DATA, WRITE);
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index d8921cf2ba9a..8de34ab6d5b1 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -625,6 +625,7 @@ struct f2fs_sb_info {
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
+	struct mutex writepages;		/* mutex for writepages() */
 	wait_queue_head_t cp_wait;
 
 	struct inode_management im[MAX_INO_ENTRY];      /* manage inode cache */
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 160b88346b24..b2dd1b01f076 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1035,6 +1035,7 @@ try_onemore:
 	sbi->raw_super = raw_super;
 	sbi->raw_super_buf = raw_super_buf;
 	mutex_init(&sbi->gc_mutex);
+	mutex_init(&sbi->writepages);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
 	clear_sbi_flag(sbi, SBI_POR_DOING);
-- 
cgit v1.2.3