[PATCH 01/19] f2fs: fix not to check IS_ERR for null pointer

[PATCH 01/19] f2fs: fix not to check IS_ERR for null pointer

[Jaegeuk Kim]

The acl can have null, error pointer, or valid pointer.
So, we should check its pointer existence too.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/acl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index c8f25f7..851ff98 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -190,7 +190,7 @@ static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type,
 		acl = ERR_PTR(retval);
 	kfree(value);
 
-	if (!IS_ERR(acl))
+	if (!IS_ERR_OR_NULL(acl))
 		set_cached_acl(inode, type, acl);
 
 	return acl;
-- 
2.1.1

[PATCH 02/19] f2fs: add missing version info in superblock

[Jaegeuk Kim]

The mkfs.f2fs remains kernel version in superblock, but f2fs module has not
added that so far.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 include/linux/f2fs_fs.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 591f8c3..8d345c2 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -50,6 +50,8 @@
 #define MAX_ACTIVE_NODE_LOGS	8
 #define MAX_ACTIVE_DATA_LOGS	8
 
+#define VERSION_LEN	256
+
 /*
  * For superblock
  */
@@ -86,6 +88,9 @@ struct f2fs_super_block {
 	__le32 extension_count;		/* # of extensions below */
 	__u8 extension_list[F2FS_MAX_EXTENSION][8];	/* extension array */
 	__le32 cp_payload;
+	__u8 version[VERSION_LEN];	/* the kernel version */
+	__u8 init_version[VERSION_LEN];	/* the initial kernel version */
+	__u8 reserved[892];		/* valid reserved region */
 } __packed;
 
 /*
-- 
2.1.1

[PATCH 03/19] f2fs: move existing definitions into f2fs.h

[Jaegeuk Kim]

This patch moves some inode-related definitions from node.h to f2fs.h to
add new features.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h | 22 ++++++++++++++++++++++
 fs/f2fs/node.h | 22 ----------------------
 2 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 8be6cab..cd9748a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -320,6 +320,13 @@ struct extent_tree {
 #define FADVISE_COLD_BIT	0x01
 #define FADVISE_LOST_PINO_BIT	0x02
 
+#define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
+#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
+#define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
+#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
+#define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
+#define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
+
 #define DEF_DIR_LEVEL		0
 
 struct f2fs_inode_info {
@@ -1391,6 +1398,21 @@ static inline void f2fs_dentry_kunmap(struct inode *dir, struct page *page)
 		kunmap(page);
 }
 
+static inline int is_file(struct inode *inode, int type)
+{
+	return F2FS_I(inode)->i_advise & type;
+}
+
+static inline void set_file(struct inode *inode, int type)
+{
+	F2FS_I(inode)->i_advise |= type;
+}
+
+static inline void clear_file(struct inode *inode, int type)
+{
+	F2FS_I(inode)->i_advise &= ~type;
+}
+
 static inline int f2fs_readonly(struct super_block *sb)
 {
 	return sb->s_flags & MS_RDONLY;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index c56026f..7427e95 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -343,28 +343,6 @@ static inline nid_t get_nid(struct page *p, int off, bool i)
  *  - Mark cold node blocks in their node footer
  *  - Mark cold data pages in page cache
  */
-static inline int is_file(struct inode *inode, int type)
-{
-	return F2FS_I(inode)->i_advise & type;
-}
-
-static inline void set_file(struct inode *inode, int type)
-{
-	F2FS_I(inode)->i_advise |= type;
-}
-
-static inline void clear_file(struct inode *inode, int type)
-{
-	F2FS_I(inode)->i_advise &= ~type;
-}
-
-#define file_is_cold(inode)	is_file(inode, FADVISE_COLD_BIT)
-#define file_wrong_pino(inode)	is_file(inode, FADVISE_LOST_PINO_BIT)
-#define file_set_cold(inode)	set_file(inode, FADVISE_COLD_BIT)
-#define file_lost_pino(inode)	set_file(inode, FADVISE_LOST_PINO_BIT)
-#define file_clear_cold(inode)	clear_file(inode, FADVISE_COLD_BIT)
-#define file_got_pino(inode)	clear_file(inode, FADVISE_LOST_PINO_BIT)
-
 static inline int is_cold_data(struct page *page)
 {
 	return PageChecked(page);
-- 
2.1.1

[PATCH 04/19] f2fs: add feature facility in superblock

[Jaegeuk Kim]

This patch introduces a feature in superblock, which will indicate any new
features for f2fs.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h          | 7 +++++++
 include/linux/f2fs_fs.h | 3 ++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index cd9748a..e1dd986 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -70,6 +70,13 @@ struct f2fs_mount_info {
 	unsigned int	opt;
 };
 
+#define F2FS_HAS_FEATURE(sb, mask)					\
+	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
+#define F2FS_SET_FEATURE(sb, mask)					\
+	F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask)
+#define F2FS_CLEAR_FEATURE(sb, mask)					\
+	F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
+
 #define CRCPOLY_LE 0xedb88320
 
 static inline __u32 f2fs_crc32(void *buf, size_t len)
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 8d345c2..d44e97f 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -90,7 +90,8 @@ struct f2fs_super_block {
 	__le32 cp_payload;
 	__u8 version[VERSION_LEN];	/* the kernel version */
 	__u8 init_version[VERSION_LEN];	/* the initial kernel version */
-	__u8 reserved[892];		/* valid reserved region */
+	__le32 feature;			/* defined features */
+	__u8 reserved[888];		/* valid reserved region */
 } __packed;
 
 /*
-- 
2.1.1

[PATCH 05/19] f2fs: add f2fs_map_blocks

[Jaegeuk Kim]

This patch introduces f2fs_map_blocks structure likewise ext4_map_blocks.
Now, f2fs uses f2fs_map_blocks when handling get_block.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c              | 72 ++++++++++++++++++++++++++-------------------
 fs/f2fs/f2fs.h              | 16 ++++++++++
 include/trace/events/f2fs.h | 28 +++++++++---------
 3 files changed, 71 insertions(+), 45 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 1e1aae6..aa3c079 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -251,19 +251,6 @@ 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 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);
-	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,
 							struct extent_info *ei)
 {
@@ -1208,18 +1195,18 @@ out:
 }
 
 /*
- * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
+ * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
+ * f2fs_map_blocks structure.
  * If original data blocks are allocated, then give them to blockdev.
  * Otherwise,
  *     a. preallocate requested block addresses
  *     b. do not use extent cache for better performance
  *     c. give the block addresses to blockdev
  */
-static int __get_data_block(struct inode *inode, sector_t iblock,
-			struct buffer_head *bh_result, int create, bool fiemap)
+static int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+			int create, bool fiemap)
 {
-	unsigned int blkbits = inode->i_sb->s_blocksize_bits;
-	unsigned maxblocks = bh_result->b_size >> blkbits;
+	unsigned int maxblocks = map->m_len;
 	struct dnode_of_data dn;
 	int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
 	pgoff_t pgofs, end_offset;
@@ -1227,11 +1214,16 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	struct extent_info ei;
 	bool allocated = false;
 
-	/* Get the page offset from the block offset(iblock) */
-	pgofs =	(pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));
+	map->m_len = 0;
+	map->m_flags = 0;
+
+	/* it only supports block size == page size */
+	pgofs =	(pgoff_t)map->m_lblk;
 
 	if (f2fs_lookup_extent_cache(inode, pgofs, &ei)) {
-		f2fs_map_bh(inode->i_sb, pgofs, &ei, bh_result);
+		map->m_pblk = ei.blk + pgofs - ei.fofs;
+		map->m_len = min((pgoff_t)maxblocks, ei.fofs + ei.len - pgofs);
+		map->m_flags = F2FS_MAP_MAPPED;
 		goto out;
 	}
 
@@ -1250,21 +1242,21 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 		goto put_out;
 
 	if (dn.data_blkaddr != NULL_ADDR) {
-		clear_buffer_new(bh_result);
-		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
+		map->m_flags = F2FS_MAP_MAPPED;
+		map->m_pblk = dn.data_blkaddr;
 	} else if (create) {
 		err = __allocate_data_block(&dn);
 		if (err)
 			goto put_out;
 		allocated = true;
-		set_buffer_new(bh_result);
-		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
+		map->m_flags = F2FS_MAP_NEW | F2FS_MAP_MAPPED;
+		map->m_pblk = dn.data_blkaddr;
 	} else {
 		goto put_out;
 	}
 
 	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
-	bh_result->b_size = (((size_t)1) << blkbits);
+	map->m_len = 1;
 	dn.ofs_in_node++;
 	pgofs++;
 
@@ -1288,22 +1280,22 @@ get_next:
 		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
 	}
 
-	if (maxblocks > (bh_result->b_size >> blkbits)) {
+	if (maxblocks > map->m_len) {
 		block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
 		if (blkaddr == NULL_ADDR && create) {
 			err = __allocate_data_block(&dn);
 			if (err)
 				goto sync_out;
 			allocated = true;
-			set_buffer_new(bh_result);
+			map->m_flags |= F2FS_MAP_NEW;
 			blkaddr = dn.data_blkaddr;
 		}
 		/* Give more consecutive addresses for the readahead */
-		if (blkaddr == (bh_result->b_blocknr + ofs)) {
+		if (map->m_pblk != NEW_ADDR && blkaddr == (map->m_pblk + ofs)) {
 			ofs++;
 			dn.ofs_in_node++;
 			pgofs++;
-			bh_result->b_size += (((size_t)1) << blkbits);
+			map->m_len++;
 			goto get_next;
 		}
 	}
@@ -1316,10 +1308,28 @@ unlock_out:
 	if (create)
 		f2fs_unlock_op(F2FS_I_SB(inode));
 out:
-	trace_f2fs_get_data_block(inode, iblock, bh_result, err);
+	trace_f2fs_map_blocks(inode, map, err);
 	return err;
 }
 
+static int __get_data_block(struct inode *inode, sector_t iblock,
+			struct buffer_head *bh, int create, bool fiemap)
+{
+	struct f2fs_map_blocks map;
+	int ret;
+
+	map.m_lblk = iblock;
+	map.m_len = bh->b_size >> inode->i_blkbits;
+
+	ret = f2fs_map_blocks(inode, &map, create, fiemap);
+	if (!ret) {
+		map_bh(bh, inode->i_sb, map.m_pblk);
+		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
+		bh->b_size = map.m_len << inode->i_blkbits;
+	}
+	return ret;
+}
+
 static int get_data_block(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create)
 {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e1dd986..c98454d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -322,6 +322,22 @@ struct extent_tree {
 };
 
 /*
+ * This structure is taken from ext4_map_blocks.
+ *
+ * Note that, however, f2fs uses NEW and MAPPED flags for f2fs_map_blocks().
+ */
+#define F2FS_MAP_NEW		(1 << BH_New)
+#define F2FS_MAP_MAPPED		(1 << BH_Mapped)
+#define F2FS_MAP_FLAGS		(F2FS_MAP_NEW | F2FS_MAP_MAPPED)
+
+struct f2fs_map_blocks {
+	block_t m_pblk;
+	block_t m_lblk;
+	unsigned int m_len;
+	unsigned int m_flags;
+};
+
+/*
  * i_advise uses FADVISE_XXX_BIT. We can add additional hints later.
  */
 #define FADVISE_COLD_BIT	0x01
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 7a61ccc..04856a2 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -117,6 +117,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD);
 		{ CP_DISCARD,	"Discard" })
 
 struct victim_sel_policy;
+struct f2fs_map_blocks;
 
 DECLARE_EVENT_CLASS(f2fs__inode,
 
@@ -481,36 +482,35 @@ TRACE_EVENT(f2fs_truncate_partial_nodes,
 		__entry->err)
 );
 
-TRACE_EVENT(f2fs_get_data_block,
-	TP_PROTO(struct inode *inode, sector_t iblock,
-				struct buffer_head *bh, int ret),
+TRACE_EVENT(f2fs_map_blocks,
+	TP_PROTO(struct inode *inode, struct f2fs_map_blocks *map, int ret),
 
-	TP_ARGS(inode, iblock, bh, ret),
+	TP_ARGS(inode, map, ret),
 
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(ino_t,	ino)
-		__field(sector_t,	iblock)
-		__field(sector_t,	bh_start)
-		__field(size_t,	bh_size)
+		__field(block_t,	m_lblk)
+		__field(block_t,	m_pblk)
+		__field(unsigned int,	m_len)
 		__field(int,	ret)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= inode->i_sb->s_dev;
 		__entry->ino		= inode->i_ino;
-		__entry->iblock		= iblock;
-		__entry->bh_start	= bh->b_blocknr;
-		__entry->bh_size	= bh->b_size;
+		__entry->m_lblk		= map->m_lblk;
+		__entry->m_pblk		= map->m_pblk;
+		__entry->m_len		= map->m_len;
 		__entry->ret		= ret;
 	),
 
 	TP_printk("dev = (%d,%d), ino = %lu, file offset = %llu, "
-		"start blkaddr = 0x%llx, len = 0x%llx bytes, err = %d",
+		"start blkaddr = 0x%llx, len = 0x%llx, err = %d",
 		show_dev_ino(__entry),
-		(unsigned long long)__entry->iblock,
-		(unsigned long long)__entry->bh_start,
-		(unsigned long long)__entry->bh_size,
+		(unsigned long long)__entry->m_lblk,
+		(unsigned long long)__entry->m_pblk,
+		(unsigned long long)__entry->m_len,
 		__entry->ret)
 );
 
-- 
2.1.1

[PATCH 06/19] f2fs: introduce f2fs_commit_super

[Jaegeuk Kim]

This patch introduces f2fs_commit_super to write updated superblock.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h  |  1 +
 fs/f2fs/super.c | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c98454d..7ff3ac7 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1535,6 +1535,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 /*
  * super.c
  */
+int f2fs_commit_super(struct f2fs_sb_info *);
 int f2fs_sync_fs(struct super_block *, int);
 extern __printf(3, 4)
 void f2fs_msg(struct super_block *, const char *, const char *, ...);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b2dd1b0..8584168 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -966,6 +966,30 @@ retry:
 	return 0;
 }
 
+int f2fs_commit_super(struct f2fs_sb_info *sbi)
+{
+	struct buffer_head *sbh = sbi->raw_super_buf;
+	sector_t block = sbh->b_blocknr;
+	int err;
+
+	/* write back-up superblock first */
+	sbh->b_blocknr = block ? 0 : 1;
+	mark_buffer_dirty(sbh);
+	err = sync_dirty_buffer(sbh);
+
+	sbh->b_blocknr = block;
+	if (err)
+		goto out;
+
+	/* write current valid superblock */
+	mark_buffer_dirty(sbh);
+	err = sync_dirty_buffer(sbh);
+out:
+	clear_buffer_write_io_error(sbh);
+	set_buffer_uptodate(sbh);
+	return err;
+}
+
 static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct f2fs_sb_info *sbi;
-- 
2.1.1

[PATCH 07/19] f2fs: expose f2fs_mpage_readpages

[Jaegeuk Kim]

This patch implements f2fs_mpage_readpages for further optimization on
encryption support.

The basic code was taken from fs/mpage.c, and changed to be simple by adjusting
that block_size is equal to page_size in f2fs.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 157 +++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 154 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index aa3c079..2a3a9cd 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -18,6 +18,7 @@
 #include <linux/bio.h>
 #include <linux/prefetch.h>
 #include <linux/uio.h>
+#include <linux/cleancache.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -47,6 +48,30 @@ static void f2fs_read_end_io(struct bio *bio, int err)
 	bio_put(bio);
 }
 
+/*
+ * I/O completion handler for multipage BIOs.
+ * copied from fs/mpage.c
+ */
+static void mpage_end_io(struct bio *bio, int err)
+{
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+
+		if (!err) {
+			SetPageUptodate(page);
+		} else {
+			ClearPageUptodate(page);
+			SetPageError(page);
+		}
+		unlock_page(page);
+	}
+
+	bio_put(bio);
+}
+
 static void f2fs_write_end_io(struct bio *bio, int err)
 {
 	struct f2fs_sb_info *sbi = bio->bi_private;
@@ -1349,6 +1374,133 @@ int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 				start, len, get_data_block_fiemap);
 }
 
+/*
+ * This function was originally taken from fs/mpage.c, and customized for f2fs.
+ * Major change was from block_size == page_size in f2fs by default.
+ */
+static int f2fs_mpage_readpages(struct address_space *mapping,
+			struct list_head *pages, struct page *page,
+			unsigned nr_pages)
+{
+	struct bio *bio = NULL;
+	unsigned page_idx;
+	sector_t last_block_in_bio = 0;
+	struct inode *inode = mapping->host;
+	const unsigned blkbits = inode->i_blkbits;
+	const unsigned blocksize = 1 << blkbits;
+	sector_t block_in_file;
+	sector_t last_block;
+	sector_t last_block_in_file;
+	sector_t block_nr;
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	struct f2fs_map_blocks map;
+
+	map.m_pblk = 0;
+	map.m_lblk = 0;
+	map.m_len = 0;
+	map.m_flags = 0;
+
+	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
+
+		prefetchw(&page->flags);
+		if (pages) {
+			page = list_entry(pages->prev, struct page, lru);
+			list_del(&page->lru);
+			if (add_to_page_cache_lru(page, mapping,
+						  page->index, GFP_KERNEL))
+				goto next_page;
+		}
+
+		block_in_file = (sector_t)page->index;
+		last_block = block_in_file + nr_pages;
+		last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
+								blkbits;
+		if (last_block > last_block_in_file)
+			last_block = last_block_in_file;
+
+		/*
+		 * Map blocks using the previous result first.
+		 */
+		if ((map.m_flags & F2FS_MAP_MAPPED) &&
+				block_in_file > map.m_lblk &&
+				block_in_file < (map.m_lblk + map.m_len))
+			goto got_it;
+
+		/*
+		 * Then do more f2fs_map_blocks() calls until we are
+		 * done with this page.
+		 */
+		map.m_flags = 0;
+
+		if (block_in_file < last_block) {
+			map.m_lblk = block_in_file;
+			map.m_len = last_block - block_in_file;
+
+			if (f2fs_map_blocks(inode, &map, 0, false))
+				goto set_error_page;
+		}
+got_it:
+		if ((map.m_flags & F2FS_MAP_MAPPED)) {
+			block_nr = map.m_pblk + block_in_file - map.m_lblk;
+			SetPageMappedToDisk(page);
+
+			if (!PageUptodate(page) && !cleancache_get_page(page)) {
+				SetPageUptodate(page);
+				goto confused;
+			}
+		} else {
+			zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+			SetPageUptodate(page);
+			unlock_page(page);
+			goto next_page;
+		}
+
+		/*
+		 * This page will go to BIO.  Do we need to send this
+		 * BIO off first?
+		 */
+		if (bio && (last_block_in_bio != block_nr - 1)) {
+submit_and_realloc:
+			submit_bio(READ, bio);
+			bio = NULL;
+		}
+		if (bio == NULL) {
+			bio = bio_alloc(GFP_KERNEL,
+				min_t(int, nr_pages, bio_get_nr_vecs(bdev)));
+			if (!bio)
+				goto set_error_page;
+			bio->bi_bdev = bdev;
+			bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
+			bio->bi_end_io = mpage_end_io;
+			bio->bi_private = NULL;
+		}
+
+		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
+			goto submit_and_realloc;
+
+		last_block_in_bio = block_nr;
+		goto next_page;
+set_error_page:
+		SetPageError(page);
+		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+		unlock_page(page);
+		goto next_page;
+confused:
+		if (bio) {
+			submit_bio(READ, bio);
+			bio = NULL;
+		}
+		unlock_page(page);
+next_page:
+		if (pages)
+			page_cache_release(page);
+	}
+	BUG_ON(pages && !list_empty(pages));
+	if (bio)
+		submit_bio(READ, bio);
+	return 0;
+}
+
 static int f2fs_read_data_page(struct file *file, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
@@ -1360,8 +1512,7 @@ static int f2fs_read_data_page(struct file *file, struct page *page)
 	if (f2fs_has_inline_data(inode))
 		ret = f2fs_read_inline_data(inode, page);
 	if (ret == -EAGAIN)
-		ret = mpage_readpage(page, get_data_block);
-
+		ret = f2fs_mpage_readpages(page->mapping, NULL, page, 1);
 	return ret;
 }
 
@@ -1375,7 +1526,7 @@ static int f2fs_read_data_pages(struct file *file,
 	if (f2fs_has_inline_data(inode))
 		return 0;
 
-	return mpage_readpages(mapping, pages, nr_pages, get_data_block);
+	return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
 }
 
 int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
-- 
2.1.1

[PATCH 08/19] f2fs: clean up f2fs_lookup

[Jaegeuk Kim]

This patch cleans up to avoid deep indentation.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/namei.c | 31 ++++++++++++++++---------------
 1 file changed, 16 insertions(+), 15 deletions(-)

diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 658e807..a311c3c 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -232,31 +232,32 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 	struct inode *inode = NULL;
 	struct f2fs_dir_entry *de;
 	struct page *page;
+	nid_t ino;
 
 	if (dentry->d_name.len > F2FS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
-	if (de) {
-		nid_t ino = le32_to_cpu(de->ino);
-		f2fs_dentry_kunmap(dir, page);
-		f2fs_put_page(page, 0);
+	if (!de)
+		return d_splice_alias(inode, dentry);
 
-		inode = f2fs_iget(dir->i_sb, ino);
-		if (IS_ERR(inode))
-			return ERR_CAST(inode);
+	ino = le32_to_cpu(de->ino);
+	f2fs_dentry_kunmap(dir, page);
+	f2fs_put_page(page, 0);
 
-		if (f2fs_has_inline_dots(inode)) {
-			int err;
+	inode = f2fs_iget(dir->i_sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	if (f2fs_has_inline_dots(inode)) {
+		int err;
 
-			err = __recover_dot_dentries(inode, dir->i_ino);
-			if (err) {
-				iget_failed(inode);
-				return ERR_PTR(err);
-			}
+		err = __recover_dot_dentries(inode, dir->i_ino);
+		if (err) {
+			iget_failed(inode);
+			return ERR_PTR(err);
 		}
 	}
-
 	return d_splice_alias(inode, dentry);
 }
 
-- 
2.1.1

[PATCH 09/19] f2fs: add f2fs_may_inline_{data, dentry}

[Jaegeuk Kim]

This patch adds f2fs_may_inline_data and f2fs_may_inline_dentry.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h   |  3 ++-
 fs/f2fs/file.c   |  2 +-
 fs/f2fs/inline.c | 13 ++++++++++++-
 fs/f2fs/namei.c  |  4 ++--
 4 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 7ff3ac7..2bb9b57 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1839,7 +1839,8 @@ extern struct kmem_cache *inode_entry_slab;
 /*
  * inline.c
  */
-bool f2fs_may_inline(struct inode *);
+bool f2fs_may_inline_data(struct inode *);
+bool f2fs_may_inline_dentry(struct inode *);
 void read_inline_data(struct page *, struct page *);
 bool truncate_inline_inode(struct page *, u64);
 int f2fs_read_inline_data(struct inode *, struct page *);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 3d6de54..ffd9b7e 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -560,7 +560,7 @@ void f2fs_truncate(struct inode *inode)
 	trace_f2fs_truncate(inode);
 
 	/* we should check inline_data size */
-	if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) {
+	if (f2fs_has_inline_data(inode) && !f2fs_may_inline_data(inode)) {
 		if (f2fs_convert_inline_inode(inode))
 			return;
 	}
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 8140e4f..99d5148 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -13,7 +13,7 @@
 
 #include "f2fs.h"
 
-bool f2fs_may_inline(struct inode *inode)
+bool f2fs_may_inline_data(struct inode *inode)
 {
 	if (!test_opt(F2FS_I_SB(inode), INLINE_DATA))
 		return false;
@@ -30,6 +30,17 @@ bool f2fs_may_inline(struct inode *inode)
 	return true;
 }
 
+bool f2fs_may_inline_dentry(struct inode *inode)
+{
+	if (!test_opt(F2FS_I_SB(inode), INLINE_DENTRY))
+		return false;
+
+	if (!S_ISDIR(inode->i_mode))
+		return false;
+
+	return true;
+}
+
 void read_inline_data(struct page *page, struct page *ipage)
 {
 	void *src_addr, *dst_addr;
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index a311c3c..c0ba8e3 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -56,9 +56,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 		goto out;
 	}
 
-	if (f2fs_may_inline(inode))
+	if (f2fs_may_inline_data(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
-	if (test_opt(sbi, INLINE_DENTRY) && S_ISDIR(inode->i_mode))
+	if (f2fs_may_inline_dentry(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
 
 	trace_f2fs_new_inode(inode, 0);
-- 
2.1.1

[PATCH 10/19] f2fs: add sbi and page pointer in f2fs_io_info

[Jaegeuk Kim]

This patch adds f2fs_sb_info and page pointers in f2fs_io_info structure.
With this change, we can reduce a lot of parameters for IO functions.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c |  9 +++++++--
 fs/f2fs/data.c       | 47 +++++++++++++++++++++++++++++------------------
 fs/f2fs/f2fs.h       | 18 ++++++++----------
 fs/f2fs/file.c       |  2 +-
 fs/f2fs/gc.c         |  4 +++-
 fs/f2fs/inline.c     |  4 +++-
 fs/f2fs/node.c       |  8 ++++++--
 fs/f2fs/segment.c    | 38 ++++++++++++++++++++------------------
 fs/f2fs/super.c      |  2 +-
 fs/f2fs/trace.c      |  6 +++---
 fs/f2fs/trace.h      |  2 +-
 11 files changed, 82 insertions(+), 58 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 72f64b3..6dbff2b 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -52,6 +52,7 @@ struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
 	struct address_space *mapping = META_MAPPING(sbi);
 	struct page *page;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO,
 		.blk_addr = index,
@@ -65,7 +66,9 @@ repeat:
 	if (PageUptodate(page))
 		goto out;
 
-	if (f2fs_submit_page_bio(sbi, page, &fio))
+	fio.page = page;
+
+	if (f2fs_submit_page_bio(&fio))
 		goto repeat;
 
 	lock_page(page);
@@ -117,6 +120,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 	struct page *page;
 	block_t blkno = start;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = META,
 		.rw = READ_SYNC | REQ_META | REQ_PRIO
 	};
@@ -160,7 +164,8 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages, int type
 			continue;
 		}
 
-		f2fs_submit_page_mbio(sbi, page, &fio);
+		fio.page = page;
+		f2fs_submit_page_mbio(&fio);
 		f2fs_put_page(page, 0);
 	}
 out:
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 2a3a9cd..81d1fd5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -158,16 +158,16 @@ void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
  * Fill the locked page with data located in the block address.
  * Return unlocked page.
  */
-int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
-					struct f2fs_io_info *fio)
+int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 {
 	struct bio *bio;
+	struct page *page = fio->page;
 
 	trace_f2fs_submit_page_bio(page, fio);
-	f2fs_trace_ios(page, fio, 0);
+	f2fs_trace_ios(fio, 0);
 
 	/* Allocate a new bio */
-	bio = __bio_alloc(sbi, fio->blk_addr, 1, is_read_io(fio->rw));
+	bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw));
 
 	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
 		bio_put(bio);
@@ -179,9 +179,9 @@ int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
 	return 0;
 }
 
-void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
-					struct f2fs_io_info *fio)
+void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 {
+	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
 	struct f2fs_bio_info *io;
 	bool is_read = is_read_io(fio->rw);
@@ -206,17 +206,17 @@ alloc_new:
 		io->fio = *fio;
 	}
 
-	if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) <
+	if (bio_add_page(io->bio, fio->page, PAGE_CACHE_SIZE, 0) <
 							PAGE_CACHE_SIZE) {
 		__submit_merged_bio(io);
 		goto alloc_new;
 	}
 
 	io->last_block_in_bio = fio->blk_addr;
-	f2fs_trace_ios(page, fio, 0);
+	f2fs_trace_ios(fio, 0);
 
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(page, fio);
+	trace_f2fs_submit_page_mbio(fio->page, fio);
 }
 
 /*
@@ -925,6 +925,7 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	struct extent_info ei;
 	int err;
 	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
 		.rw = sync ? READ_SYNC : READA,
 	};
@@ -971,7 +972,8 @@ got_it:
 	}
 
 	fio.blk_addr = dn.data_blkaddr;
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
+	fio.page = page;
+	err = f2fs_submit_page_bio(&fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -998,6 +1000,7 @@ struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
 	struct extent_info ei;
 	int err;
 	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
 		.rw = READ_SYNC,
 	};
@@ -1041,7 +1044,8 @@ got_it:
 	}
 
 	fio.blk_addr = dn.data_blkaddr;
-	err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
+	fio.page = page;
+	err = f2fs_submit_page_bio(&fio);
 	if (err)
 		return ERR_PTR(err);
 
@@ -1092,11 +1096,13 @@ repeat:
 		SetPageUptodate(page);
 	} else {
 		struct f2fs_io_info fio = {
+			.sbi = F2FS_I_SB(inode),
 			.type = DATA,
 			.rw = READ_SYNC,
 			.blk_addr = dn.data_blkaddr,
+			.page = page,
 		};
-		err = f2fs_submit_page_bio(F2FS_I_SB(inode), page, &fio);
+		err = f2fs_submit_page_bio(&fio);
 		if (err)
 			goto put_err;
 
@@ -1529,8 +1535,9 @@ static int f2fs_read_data_pages(struct file *file,
 	return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
 }
 
-int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
+int do_write_data_page(struct f2fs_io_info *fio)
 {
+	struct page *page = fio->page;
 	struct inode *inode = page->mapping->host;
 	struct dnode_of_data dn;
 	int err = 0;
@@ -1557,11 +1564,11 @@ int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
 	if (unlikely(fio->blk_addr != NEW_ADDR &&
 			!is_cold_data(page) &&
 			need_inplace_update(inode))) {
-		rewrite_data_page(page, fio);
+		rewrite_data_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);
+		write_data_page(&dn, fio);
 		set_data_blkaddr(&dn);
 		f2fs_update_extent_cache(&dn);
 		trace_f2fs_do_write_data_page(page, OPU);
@@ -1586,8 +1593,10 @@ static int f2fs_write_data_page(struct page *page,
 	bool need_balance_fs = false;
 	int err = 0;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = DATA,
 		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+		.page = page,
 	};
 
 	trace_f2fs_writepage(page, DATA);
@@ -1617,7 +1626,7 @@ write:
 	if (S_ISDIR(inode->i_mode)) {
 		if (unlikely(f2fs_cp_error(sbi)))
 			goto redirty_out;
-		err = do_write_data_page(page, &fio);
+		err = do_write_data_page(&fio);
 		goto done;
 	}
 
@@ -1637,7 +1646,7 @@ write:
 	if (f2fs_has_inline_data(inode))
 		err = f2fs_write_inline_data(inode, page);
 	if (err == -EAGAIN)
-		err = do_write_data_page(page, &fio);
+		err = do_write_data_page(&fio);
 	f2fs_unlock_op(sbi);
 done:
 	if (err && err != -ENOENT)
@@ -1806,11 +1815,13 @@ put_next:
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 	} else {
 		struct f2fs_io_info fio = {
+			.sbi = sbi,
 			.type = DATA,
 			.rw = READ_SYNC,
 			.blk_addr = dn.data_blkaddr,
+			.page = page,
 		};
-		err = f2fs_submit_page_bio(sbi, page, &fio);
+		err = f2fs_submit_page_bio(&fio);
 		if (err)
 			goto fail;
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2bb9b57..e99a404 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -601,9 +601,11 @@ enum page_type {
 };
 
 struct f2fs_io_info {
+	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
 	int rw;			/* contains R/RS/W/WS with REQ_META/REQ_PRIO */
 	block_t blk_addr;	/* block address to be written */
+	struct page *page;	/* page to be written */
 };
 
 #define is_read_io(rw)	(((rw) & 1) == READ)
@@ -1601,11 +1603,9 @@ void allocate_new_segments(struct f2fs_sb_info *);
 int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
 struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
 void write_meta_page(struct f2fs_sb_info *, struct page *);
-void write_node_page(struct f2fs_sb_info *, struct page *,
-				unsigned int, struct f2fs_io_info *);
-void write_data_page(struct page *, struct dnode_of_data *,
-			struct f2fs_io_info *);
-void rewrite_data_page(struct page *, struct f2fs_io_info *);
+void write_node_page(unsigned int, struct f2fs_io_info *);
+void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
+void rewrite_data_page(struct f2fs_io_info *);
 void recover_data_page(struct f2fs_sb_info *, struct page *,
 				struct f2fs_summary *, block_t, block_t);
 void allocate_data_block(struct f2fs_sb_info *, struct page *,
@@ -1653,10 +1653,8 @@ void destroy_checkpoint_caches(void);
  * data.c
  */
 void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-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 *);
+int f2fs_submit_page_bio(struct f2fs_io_info *);
+void f2fs_submit_page_mbio(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);
@@ -1668,7 +1666,7 @@ 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);
-int do_write_data_page(struct page *, struct f2fs_io_info *);
+int do_write_data_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);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ffd9b7e..0e58f02 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -271,7 +271,7 @@ flush_out:
 	ret = f2fs_issue_flush(sbi);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
-	f2fs_trace_ios(NULL, NULL, 1);
+	f2fs_trace_ios(NULL, 1);
 	return ret;
 }
 
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index ed58211..72667a5 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -521,8 +521,10 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 {
 	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
 		.rw = WRITE_SYNC,
+		.page = page,
 	};
 
 	if (gc_type == BG_GC) {
@@ -536,7 +538,7 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
-		do_write_data_page(page, &fio);
+		do_write_data_page(&fio);
 		clear_cold_data(page);
 	}
 out:
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 99d5148..d9b3033 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -106,8 +106,10 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 {
 	void *src_addr, *dst_addr;
 	struct f2fs_io_info fio = {
+		.sbi = F2FS_I_SB(dn->inode),
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
+		.page = page,
 	};
 	int dirty, err;
 
@@ -141,7 +143,7 @@ no_update:
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
 	fio.blk_addr = dn->data_blkaddr;
-	write_data_page(page, dn, &fio);
+	write_data_page(dn, &fio);
 	set_data_blkaddr(dn);
 	f2fs_update_extent_cache(dn);
 	f2fs_wait_on_page_writeback(page, DATA);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 1676c7a..880d578 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -995,8 +995,10 @@ static int read_node_page(struct page *page, int rw)
 	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 	struct node_info ni;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = NODE,
 		.rw = rw,
+		.page = page,
 	};
 
 	get_node_info(sbi, page->index, &ni);
@@ -1011,7 +1013,7 @@ static int read_node_page(struct page *page, int rw)
 		return LOCKED_PAGE;
 
 	fio.blk_addr = ni.blk_addr;
-	return f2fs_submit_page_bio(sbi, page, &fio);
+	return f2fs_submit_page_bio(&fio);
 }
 
 /*
@@ -1293,8 +1295,10 @@ static int f2fs_write_node_page(struct page *page,
 	nid_t nid;
 	struct node_info ni;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = NODE,
 		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
+		.page = page,
 	};
 
 	trace_f2fs_writepage(page, NODE);
@@ -1329,7 +1333,7 @@ static int f2fs_write_node_page(struct page *page,
 
 	set_page_writeback(page);
 	fio.blk_addr = ni.blk_addr;
-	write_node_page(sbi, page, nid, &fio);
+	write_node_page(nid, &fio);
 	set_node_addr(sbi, &ni, fio.blk_addr, is_fsync_dnode(page));
 	dec_page_count(sbi, F2FS_DIRTY_NODES);
 	up_read(&sbi->node_write);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f939660..df8bce5 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -216,6 +216,7 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 	struct inmem_pages *cur, *tmp;
 	bool submit_bio = false;
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = DATA,
 		.rw = WRITE_SYNC | REQ_PRIO,
 	};
@@ -241,7 +242,8 @@ void commit_inmem_pages(struct inode *inode, bool abort)
 				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);
+				fio.page = cur->page;
+				do_write_data_page(&fio);
 				submit_bio = true;
 			}
 			f2fs_put_page(cur->page, 1);
@@ -1206,56 +1208,56 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
-static void do_write_page(struct f2fs_sb_info *sbi, struct page *page,
-			struct f2fs_summary *sum,
-			struct f2fs_io_info *fio)
+static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
-	int type = __get_segment_type(page, fio->type);
+	int type = __get_segment_type(fio->page, fio->type);
 
-	allocate_data_block(sbi, page, fio->blk_addr, &fio->blk_addr, sum, type);
+	allocate_data_block(fio->sbi, fio->page, fio->blk_addr,
+					&fio->blk_addr, sum, type);
 
 	/* writeout dirty page into bdev */
-	f2fs_submit_page_mbio(sbi, page, fio);
+	f2fs_submit_page_mbio(fio);
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 {
 	struct f2fs_io_info fio = {
+		.sbi = sbi,
 		.type = META,
 		.rw = WRITE_SYNC | REQ_META | REQ_PRIO,
 		.blk_addr = page->index,
+		.page = page,
 	};
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(sbi, page, &fio);
+	f2fs_submit_page_mbio(&fio);
 }
 
-void write_node_page(struct f2fs_sb_info *sbi, struct page *page,
-			unsigned int nid, struct f2fs_io_info *fio)
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
 {
 	struct f2fs_summary sum;
+
 	set_summary(&sum, nid, 0, 0);
-	do_write_page(sbi, page, &sum, fio);
+	do_write_page(&sum, fio);
 }
 
-void write_data_page(struct page *page, struct dnode_of_data *dn,
-				struct f2fs_io_info *fio)
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	struct f2fs_sb_info *sbi = fio->sbi;
 	struct f2fs_summary sum;
 	struct node_info ni;
 
 	f2fs_bug_on(sbi, dn->data_blkaddr == NULL_ADDR);
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
-	do_write_page(sbi, page, &sum, fio);
+	do_write_page(&sum, fio);
 	dn->data_blkaddr = fio->blk_addr;
 }
 
-void rewrite_data_page(struct page *page, struct f2fs_io_info *fio)
+void rewrite_data_page(struct f2fs_io_info *fio)
 {
-	stat_inc_inplace_blocks(F2FS_P_SB(page));
-	f2fs_submit_page_mbio(F2FS_P_SB(page), page, fio);
+	stat_inc_inplace_blocks(fio->sbi);
+	f2fs_submit_page_mbio(fio);
 }
 
 void recover_data_page(struct f2fs_sb_info *sbi,
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 8584168..138fa93 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -520,7 +520,7 @@ int f2fs_sync_fs(struct super_block *sb, int sync)
 	} else {
 		f2fs_balance_fs(sbi);
 	}
-	f2fs_trace_ios(NULL, NULL, 1);
+	f2fs_trace_ios(NULL, 1);
 
 	return 0;
 }
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 875aa81..145fb65 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -80,7 +80,7 @@ out:
 	radix_tree_preload_end();
 }
 
-void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush)
+void f2fs_trace_ios(struct f2fs_io_info *fio, int flush)
 {
 	struct inode *inode;
 	pid_t pid;
@@ -91,8 +91,8 @@ void f2fs_trace_ios(struct page *page, struct f2fs_io_info *fio, int flush)
 		return;
 	}
 
-	inode = page->mapping->host;
-	pid = page_private(page);
+	inode = fio->page->mapping->host;
+	pid = page_private(fio->page);
 
 	major = MAJOR(inode->i_sb->s_dev);
 	minor = MINOR(inode->i_sb->s_dev);
diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h
index 1041dbe..dc5cd26 100644
--- a/fs/f2fs/trace.h
+++ b/fs/f2fs/trace.h
@@ -33,7 +33,7 @@ struct last_io_info {
 };
 
 extern void f2fs_trace_pid(struct page *);
-extern void f2fs_trace_ios(struct page *, struct f2fs_io_info *, int);
+extern void f2fs_trace_ios(struct f2fs_io_info *, int);
 extern void f2fs_build_trace_ios(void);
 extern void f2fs_destroy_trace_ios(void);
 #else
-- 
2.1.1

[PATCH 11/19] f2fs: move get_page for gc victims

[Jaegeuk Kim]

This patch moves getting victim page into move_data_page.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/gc.c | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 72667a5..1bd11f0 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -518,14 +518,13 @@ static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	return 1;
 }
 
-static void move_data_page(struct inode *inode, struct page *page, int gc_type)
+static void move_data_page(struct inode *inode, block_t bidx, int gc_type)
 {
-	struct f2fs_io_info fio = {
-		.sbi = F2FS_I_SB(inode),
-		.type = DATA,
-		.rw = WRITE_SYNC,
-		.page = page,
-	};
+	struct page *page;
+
+	page = get_lock_data_page(inode, bidx);
+	if (IS_ERR(page))
+		return;
 
 	if (gc_type == BG_GC) {
 		if (PageWriteback(page))
@@ -533,6 +532,12 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
 		set_page_dirty(page);
 		set_cold_data(page);
 	} else {
+		struct f2fs_io_info fio = {
+			.sbi = F2FS_I_SB(inode),
+			.type = DATA,
+			.rw = WRITE_SYNC,
+			.page = page,
+		};
 		f2fs_wait_on_page_writeback(page, DATA);
 
 		if (clear_page_dirty_for_io(page))
@@ -618,12 +623,9 @@ next_step:
 		/* phase 3 */
 		inode = find_gc_inode(gc_list, dni.ino);
 		if (inode) {
-			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
-			data_page = get_lock_data_page(inode,
-						start_bidx + ofs_in_node);
-			if (IS_ERR(data_page))
-				continue;
-			move_data_page(inode, data_page, gc_type);
+			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode))
+								+ ofs_in_node;
+			move_data_page(inode, start_bidx, gc_type);
 			stat_inc_data_blk_count(sbi, 1, gc_type);
 		}
 	}
-- 
2.1.1

[PATCH 12/19] f2fs: introduce dot and dotdot name check

[Jaegeuk Kim]

This patch adds an inline function to check dot and dotdot names.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h | 11 +++++++++++
 fs/f2fs/hash.c |  3 +--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e99a404..b8f99fd 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1454,6 +1454,17 @@ static inline void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi)
 	sbi->sb->s_flags |= MS_RDONLY;
 }
 
+static inline bool is_dot_dotdot(const struct qstr *str)
+{
+	if (str->len == 1 && str->name[0] == '.')
+		return true;
+
+	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+		return true;
+
+	return false;
+}
+
 #define get_inode_mode(i) \
 	((is_inode_flag_set(F2FS_I(i), FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index a844fcf..71b7206 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -79,8 +79,7 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
 	const unsigned char *name = name_info->name;
 	size_t len = name_info->len;
 
-	if ((len <= 2) && (name[0] == '.') &&
-		(name[1] == '.' || name[1] == '\0'))
+	if (is_dot_dotdot(name_info))
 		return 0;
 
 	/* Initialize the default seed for the hash checksum functions */
-- 
2.1.1

[PATCH 13/19] f2fs: fix race on allocating and deallocating a dentry block

[Jaegeuk Kim]

There are two threads:
 f2fs_delete_entry()              get_new_data_page()
                                  f2fs_reserve_block()
				  dn.blkaddr = XXX
 lock_page(dentry_block)
 truncate_hole()
 dn.blkaddr = NULL
 unlock_page(dentry_block)
                                  lock_page(dentry_block)
                                  fill the block from XXX address
                                  add new dentries
                                  unlock_page(dentry_block)

Later, f2fs_write_data_page() will truncate the dentry_block, since
its block address is NULL.

The reason for this was due to the wrong lock order.
In this case, we should do f2fs_reserve_block() after locking its dentry block.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 81d1fd5..9ba30b4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1076,20 +1076,22 @@ struct page *get_new_data_page(struct inode *inode,
 	struct page *page;
 	struct dnode_of_data dn;
 	int err;
+repeat:
+	page = grab_cache_page(mapping, index);
+	if (!page)
+		return ERR_PTR(-ENOMEM);
 
 	set_new_dnode(&dn, inode, ipage, NULL, 0);
 	err = f2fs_reserve_block(&dn, index);
-	if (err)
+	if (err) {
+		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
-repeat:
-	page = grab_cache_page(mapping, index);
-	if (!page) {
-		err = -ENOMEM;
-		goto put_err;
 	}
+	if (!ipage)
+		f2fs_put_dnode(&dn);
 
 	if (PageUptodate(page))
-		return page;
+		goto got_it;
 
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
@@ -1104,20 +1106,19 @@ repeat:
 		};
 		err = f2fs_submit_page_bio(&fio);
 		if (err)
-			goto put_err;
+			return ERR_PTR(err);
 
 		lock_page(page);
 		if (unlikely(!PageUptodate(page))) {
 			f2fs_put_page(page, 1);
-			err = -EIO;
-			goto put_err;
+			return ERR_PTR(-EIO);
 		}
 		if (unlikely(page->mapping != mapping)) {
 			f2fs_put_page(page, 1);
 			goto repeat;
 		}
 	}
-
+got_it:
 	if (new_i_size &&
 		i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
 		i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
@@ -1125,10 +1126,6 @@ repeat:
 		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
 	}
 	return page;
-
-put_err:
-	f2fs_put_dnode(&dn);
-	return ERR_PTR(err);
 }
 
 static int __allocate_data_block(struct dnode_of_data *dn)
-- 
2.1.1

[PATCH 14/19] f2fs: add need_dentry_mark

[Jaegeuk Kim]

This patch introduces need_dentry_mark() to clean up and avoid redundant
node locks.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h |  1 +
 fs/f2fs/node.c | 35 +++++++++++++++++------------------
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index b8f99fd..9e43ddc 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1565,6 +1565,7 @@ struct dnode_of_data;
 struct node_info;
 
 bool available_free_memory(struct f2fs_sb_info *, int);
+int need_dentry_mark(struct f2fs_sb_info *, nid_t);
 bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
 bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
 void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 880d578..62982e6 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -195,32 +195,35 @@ static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
 							start, nr);
 }
 
-bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
-	bool is_cp = true;
+	bool need = false;
 
 	down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
-	if (e && !get_nat_flag(e, IS_CHECKPOINTED))
-		is_cp = false;
+	if (e) {
+		if (!get_nat_flag(e, IS_CHECKPOINTED) &&
+				!get_nat_flag(e, HAS_FSYNCED_INODE))
+			need = true;
+	}
 	up_read(&nm_i->nat_tree_lock);
-	return is_cp;
+	return need;
 }
 
-static bool has_fsynced_inode(struct f2fs_sb_info *sbi, nid_t ino)
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct nat_entry *e;
-	bool fsynced = false;
+	bool is_cp = true;
 
 	down_read(&nm_i->nat_tree_lock);
-	e = __lookup_nat_cache(nm_i, ino);
-	if (e && get_nat_flag(e, HAS_FSYNCED_INODE))
-		fsynced = true;
+	e = __lookup_nat_cache(nm_i, nid);
+	if (e && !get_nat_flag(e, IS_CHECKPOINTED))
+		is_cp = false;
 	up_read(&nm_i->nat_tree_lock);
-	return fsynced;
+	return is_cp;
 }
 
 bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
@@ -1206,13 +1209,9 @@ continue_unlock:
 			/* called by fsync() */
 			if (ino && IS_DNODE(page)) {
 				set_fsync_mark(page, 1);
-				if (IS_INODE(page)) {
-					if (!is_checkpointed_node(sbi, ino) &&
-						!has_fsynced_inode(sbi, ino))
-						set_dentry_mark(page, 1);
-					else
-						set_dentry_mark(page, 0);
-				}
+				if (IS_INODE(page))
+					set_dentry_mark(page,
+						need_dentry_mark(sbi, ino));
 				nwritten++;
 			} else {
 				set_fsync_mark(page, 0);
-- 
2.1.1

[PATCH 15/19] f2fs: fix counting the number of inline_data inodes

[Jaegeuk Kim]

This patch fixes to count the missing symlink case.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/namei.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index c0ba8e3..90a9640 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -61,6 +61,9 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	if (f2fs_may_inline_dentry(inode))
 		set_inode_flag(F2FS_I(inode), FI_INLINE_DENTRY);
 
+	stat_inc_inline_inode(inode);
+	stat_inc_inline_dir(inode);
+
 	trace_f2fs_new_inode(inode, 0);
 	mark_inode_dirty(inode);
 	return inode;
@@ -136,7 +139,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	alloc_nid_done(sbi, ino);
 
-	stat_inc_inline_inode(inode);
 	d_instantiate(dentry, inode);
 	unlock_new_inode(inode);
 
@@ -384,7 +386,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out_fail;
 	f2fs_unlock_op(sbi);
 
-	stat_inc_inline_dir(inode);
 	alloc_nid_done(sbi, inode->i_ino);
 
 	d_instantiate(dentry, inode);
@@ -770,7 +771,6 @@ static int f2fs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	alloc_nid_done(sbi, inode->i_ino);
 
-	stat_inc_inline_inode(inode);
 	d_tmpfile(dentry, inode);
 	unlock_new_inode(inode);
 	return 0;
-- 
2.1.1

[PATCH 16/19] f2fs: split find_data_page according to specific purposes

[Jaegeuk Kim]

This patch splits find_data_page as follows.

1. f2fs_gc
 - use get_read_data_page() with read only

2. find_in_level
 - use find_data_page without locked page

3. truncate_partial_page
 - In the case cache_only mode, just drop cached page.
 - Ohterwise, use get_lock_data_page() and guarantee to truncate

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c | 127 ++++++++++++++++++++++-----------------------------------
 fs/f2fs/dir.c  |   2 +-
 fs/f2fs/f2fs.h |   3 +-
 fs/f2fs/file.c |  26 +++++++-----
 fs/f2fs/gc.c   |   5 +--
 5 files changed, 68 insertions(+), 95 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9ba30b4..3b76261 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -917,7 +917,7 @@ void f2fs_update_extent_cache(struct dnode_of_data *dn)
 		sync_inode_page(dn);
 }
 
-struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
+struct page *get_read_data_page(struct inode *inode, pgoff_t index, int rw)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
@@ -927,84 +927,9 @@ struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
-		.rw = sync ? READ_SYNC : READA,
+		.rw = rw,
 	};
 
-	/*
-	 * 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;
-	}
-
-	set_new_dnode(&dn, inode, NULL, NULL, 0);
-	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
-	if (err)
-		return ERR_PTR(err);
-	f2fs_put_dnode(&dn);
-
-	if (dn.data_blkaddr == NULL_ADDR)
-		return ERR_PTR(-ENOENT);
-
-	/* By fallocate(), there is no cached page, but with NEW_ADDR */
-	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);
-
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		return page;
-	}
-
-	fio.blk_addr = dn.data_blkaddr;
-	fio.page = page;
-	err = f2fs_submit_page_bio(&fio);
-	if (err)
-		return ERR_PTR(err);
-
-	if (sync) {
-		wait_on_page_locked(page);
-		if (unlikely(!PageUptodate(page))) {
-			f2fs_put_page(page, 0);
-			return ERR_PTR(-EIO);
-		}
-	}
-	return page;
-}
-
-/*
- * If it tries to access a hole, return an error.
- * Because, the callers, functions in dir.c and GC, should be able to know
- * whether this page exists or not.
- */
-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 = {
-		.sbi = F2FS_I_SB(inode),
-		.type = DATA,
-		.rw = READ_SYNC,
-	};
-repeat:
 	page = grab_cache_page(mapping, index);
 	if (!page)
 		return ERR_PTR(-ENOMEM);
@@ -1026,10 +951,11 @@ repeat:
 		f2fs_put_page(page, 1);
 		return ERR_PTR(-ENOENT);
 	}
-
 got_it:
-	if (PageUptodate(page))
+	if (PageUptodate(page)) {
+		unlock_page(page);
 		return page;
+	}
 
 	/*
 	 * A new dentry page is allocated but not able to be written, since its
@@ -1040,6 +966,7 @@ got_it:
 	if (dn.data_blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
 		SetPageUptodate(page);
+		unlock_page(page);
 		return page;
 	}
 
@@ -1048,7 +975,49 @@ got_it:
 	err = f2fs_submit_page_bio(&fio);
 	if (err)
 		return ERR_PTR(err);
+	return page;
+}
+
+struct page *find_data_page(struct inode *inode, pgoff_t index)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+
+	page = find_get_page(mapping, index);
+	if (page && PageUptodate(page))
+		return page;
+	f2fs_put_page(page, 0);
+
+	page = get_read_data_page(inode, index, READ_SYNC);
+	if (IS_ERR(page))
+		return page;
+
+	if (PageUptodate(page))
+		return page;
+
+	wait_on_page_locked(page);
+	if (unlikely(!PageUptodate(page))) {
+		f2fs_put_page(page, 0);
+		return ERR_PTR(-EIO);
+	}
+	return page;
+}
+
+/*
+ * If it tries to access a hole, return an error.
+ * Because, the callers, functions in dir.c and GC, should be able to know
+ * whether this page exists or not.
+ */
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page;
+repeat:
+	page = get_read_data_page(inode, index, READ_SYNC);
+	if (IS_ERR(page))
+		return page;
 
+	/* wait for read completion */
 	lock_page(page);
 	if (unlikely(!PageUptodate(page))) {
 		f2fs_put_page(page, 1);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 3a3302a..9d558d2 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -177,7 +177,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 
 	for (; bidx < end_block; bidx++) {
 		/* no need to allocate new dentry pages to all the indices */
-		dentry_page = find_data_page(dir, bidx, true);
+		dentry_page = find_data_page(dir, bidx);
 		if (IS_ERR(dentry_page)) {
 			room = true;
 			continue;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9e43ddc..78a4300 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1675,7 +1675,8 @@ 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_read_data_page(struct inode *, pgoff_t, int);
+struct page *find_data_page(struct inode *, pgoff_t);
 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 f2fs_io_info *);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 0e58f02..cb002c0 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -461,28 +461,32 @@ void truncate_data_blocks(struct dnode_of_data *dn)
 }
 
 static int truncate_partial_data_page(struct inode *inode, u64 from,
-								bool force)
+								bool cache_only)
 {
 	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
+	pgoff_t index = from >> PAGE_CACHE_SHIFT;
+	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 
-	if (!offset && !force)
+	if (!offset && !cache_only)
 		return 0;
 
-	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force);
-	if (IS_ERR(page))
+	if (cache_only) {
+		page = grab_cache_page(mapping, index);
+		if (page && PageUptodate(page))
+			goto truncate_out;
+		f2fs_put_page(page, 1);
 		return 0;
+	}
 
-	lock_page(page);
-	if (unlikely(!PageUptodate(page) ||
-			page->mapping != inode->i_mapping))
-		goto out;
-
+	page = get_lock_data_page(inode, index);
+	if (IS_ERR(page))
+		return 0;
+truncate_out:
 	f2fs_wait_on_page_writeback(page, DATA);
 	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
-	if (!force)
+	if (!cache_only)
 		set_page_dirty(page);
-out:
 	f2fs_put_page(page, 1);
 	return 0;
 }
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 1bd11f0..2e2afeb 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -607,9 +607,8 @@ next_step:
 				continue;
 
 			start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
-
-			data_page = find_data_page(inode,
-					start_bidx + ofs_in_node, false);
+			data_page = get_read_data_page(inode,
+					start_bidx + ofs_in_node, READA);
 			if (IS_ERR(data_page)) {
 				iput(inode);
 				continue;
-- 
2.1.1

[PATCH 17/19] f2fs: revmove spin_lock for write_orphan_inodes

[Jaegeuk Kim]

This patch removes spin_lock, since this is covered by f2fs_lock_op already.
And, we should avoid to use page operations inside spin_lock.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 6dbff2b..d076e7e 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -514,7 +514,12 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 		grab_meta_page(sbi, start_blk + index);
 
 	index = 1;
-	spin_lock(&im->ino_lock);
+
+	/*
+	 * we don't need to do spin_lock(&im->ino_lock) here, since all the
+	 * orphan inode operations are covered under f2fs_lock_op().
+	 * And, spin_lock should be avoided due to page operations below.
+	 */
 	head = &im->ino_list;
 
 	/* loop for each orphan inode entry and write them in Jornal block */
@@ -554,8 +559,6 @@ static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
 		set_page_dirty(page);
 		f2fs_put_page(page, 1);
 	}
-
-	spin_unlock(&im->ino_lock);
 }
 
 static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
-- 
2.1.1

[PATCH 18/19] f2fs: introduce discard_map for f2fs_trim_fs

[Jaegeuk Kim]

This patch adds a bitmap for discard issues from f2fs_trim_fs.
There-in rule is to issue discard commands only for invalidated blocks
after mount.
Once mount is done, f2fs_trim_fs trims out whole invalid area.
After ehn, it will not issue and discrads redundantly.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/debug.c   |  2 +-
 fs/f2fs/f2fs.h    | 21 +++++++++++++++++++++
 fs/f2fs/segment.c | 52 +++++++++++++++++++++++++++++++++++++++-------------
 fs/f2fs/segment.h |  1 +
 4 files changed, 62 insertions(+), 14 deletions(-)

diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index f5388f3..f50acbc 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -143,7 +143,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	si->base_mem += sizeof(struct sit_info);
 	si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry);
 	si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi));
-	si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
+	si->base_mem += 3 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi);
 	si->base_mem += SIT_VBLOCK_MAP_SIZE;
 	if (sbi->segs_per_sec > 1)
 		si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 78a4300..98fc719 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -117,6 +117,8 @@ enum {
 #define DEF_BATCHED_TRIM_SECTIONS	32
 #define BATCHED_TRIM_SEGMENTS(sbi)	\
 		(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+#define BATCHED_TRIM_BLOCKS(sbi)	\
+		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
 
 struct cp_control {
 	int reason;
@@ -698,6 +700,7 @@ struct f2fs_sb_info {
 	block_t user_block_count;		/* # of user blocks */
 	block_t total_valid_block_count;	/* # of valid blocks */
 	block_t alloc_valid_block_count;	/* # of allocated blocks */
+	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
 	u32 s_next_generation;			/* for NFS support */
 	atomic_t nr_pages[NR_COUNT_TYPE];	/* # of pages, see count_type */
@@ -1225,6 +1228,24 @@ static inline int f2fs_test_bit(unsigned int nr, char *addr)
 	return mask & *addr;
 }
 
+static inline void f2fs_set_bit(unsigned int nr, char *addr)
+{
+	int mask;
+
+	addr += (nr >> 3);
+	mask = 1 << (7 - (nr & 0x07));
+	*addr |= mask;
+}
+
+static inline void f2fs_clear_bit(unsigned int nr, char *addr)
+{
+	int mask;
+
+	addr += (nr >> 3);
+	mask = 1 << (7 - (nr & 0x07));
+	*addr &= ~mask;
+}
+
 static inline int f2fs_test_and_set_bit(unsigned int nr, char *addr)
 {
 	int mask;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index df8bce5..5a4ec01 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -483,10 +483,12 @@ void discard_next_dnode(struct f2fs_sb_info *sbi, block_t blkaddr)
 }
 
 static void __add_discard_entry(struct f2fs_sb_info *sbi,
-		struct cp_control *cpc, unsigned int start, unsigned int end)
+		struct cp_control *cpc, struct seg_entry *se,
+		unsigned int start, unsigned int end)
 {
 	struct list_head *head = &SM_I(sbi)->discard_list;
 	struct discard_entry *new, *last;
+	unsigned int i;
 
 	if (!list_empty(head)) {
 		last = list_last_entry(head, struct discard_entry, list);
@@ -504,6 +506,10 @@ static void __add_discard_entry(struct f2fs_sb_info *sbi,
 	list_add_tail(&new->list, head);
 done:
 	SM_I(sbi)->nr_discards += end - start;
+	for (i = start; i < end; i++) {
+		f2fs_set_bit(i, se->discard_map);
+		sbi->discard_blks--;
+	}
 	cpc->trimmed += end - start;
 }
 
@@ -514,6 +520,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	struct seg_entry *se = get_seg_entry(sbi, cpc->trim_start);
 	unsigned long *cur_map = (unsigned long *)se->cur_valid_map;
 	unsigned long *ckpt_map = (unsigned long *)se->ckpt_valid_map;
+	unsigned long *discard_map = (unsigned long *)se->discard_map;
 	unsigned long *dmap = SIT_I(sbi)->tmp_map;
 	unsigned int start = 0, end = -1;
 	bool force = (cpc->reason == CP_DISCARD);
@@ -523,8 +530,11 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards))
 		return;
 
-	if (force && !se->valid_blocks) {
+	if (!se->valid_blocks) {
 		struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+
+		if (!force)
+			return;
 		/*
 		 * if this segment is registered in the prefree list, then
 		 * we should skip adding a discard candidate, and let the
@@ -537,18 +547,14 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			return;
 		}
 		mutex_unlock(&dirty_i->seglist_lock);
-
-		__add_discard_entry(sbi, cpc, 0, sbi->blocks_per_seg);
+	} else if (se->valid_blocks == max_blocks) {
+		/* zero block will be discarded through the prefree list */
 		return;
 	}
 
-	/* zero block will be discarded through the prefree list */
-	if (!se->valid_blocks || se->valid_blocks == max_blocks)
-		return;
-
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
 	for (i = 0; i < entries; i++)
-		dmap[i] = force ? ~ckpt_map[i] :
+		dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
 				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
 	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
@@ -561,7 +567,7 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		if (force && end - start < cpc->trim_minlen)
 			continue;
 
-		__add_discard_entry(sbi, cpc, start, end);
+		__add_discard_entry(sbi, cpc, se, start, end);
 	}
 }
 
@@ -675,9 +681,13 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 	if (del > 0) {
 		if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
 			f2fs_bug_on(sbi, 1);
+		if (f2fs_test_and_set_bit(offset, se->discard_map))
+			sbi->discard_blks--;
 	} else {
 		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
 			f2fs_bug_on(sbi, 1);
+		if (f2fs_test_and_clear_bit(offset, se->discard_map))
+			sbi->discard_blks++;
 	}
 	if (!f2fs_test_bit(offset, se->ckpt_valid_map))
 		se->ckpt_valid_blocks += del;
@@ -1080,7 +1090,14 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	/* do checkpoint to issue discard commands safely */
 	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
 		cpc.trim_start = start_segno;
-		cpc.trim_end = min_t(unsigned int, rounddown(start_segno +
+
+		if (sbi->discard_blks == 0)
+			break;
+		else if (sbi->discard_blks < BATCHED_TRIM_BLOCKS(sbi))
+			cpc.trim_end = end_segno;
+		else
+			cpc.trim_end = min_t(unsigned int,
+				rounddown(start_segno +
 				BATCHED_TRIM_SEGMENTS(sbi),
 				sbi->segs_per_sec) - 1, end_segno);
 
@@ -1859,8 +1876,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
 		sit_i->sentries[start].ckpt_valid_map
 			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
-		if (!sit_i->sentries[start].cur_valid_map
-				|| !sit_i->sentries[start].ckpt_valid_map)
+		sit_i->sentries[start].discard_map
+			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+		if (!sit_i->sentries[start].cur_valid_map ||
+				!sit_i->sentries[start].ckpt_valid_map ||
+				!sit_i->sentries[start].discard_map)
 			return -ENOMEM;
 	}
 
@@ -1998,6 +2018,11 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 got_it:
 			check_block_count(sbi, start, &sit);
 			seg_info_from_raw_sit(se, &sit);
+
+			/* build discard map only one time */
+			memcpy(se->discard_map, se->cur_valid_map, SIT_VBLOCK_MAP_SIZE);
+			sbi->discard_blks += sbi->blocks_per_seg - se->valid_blocks;
+
 			if (sbi->segs_per_sec > 1) {
 				struct sec_entry *e = get_sec_entry(sbi, start);
 				e->valid_blocks += se->valid_blocks;
@@ -2247,6 +2272,7 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 		for (start = 0; start < MAIN_SEGS(sbi); start++) {
 			kfree(sit_i->sentries[start].cur_valid_map);
 			kfree(sit_i->sentries[start].ckpt_valid_map);
+			kfree(sit_i->sentries[start].discard_map);
 		}
 	}
 	kfree(sit_i->tmp_map);
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 85d7fa7..8496357 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -163,6 +163,7 @@ struct seg_entry {
 	 */
 	unsigned short ckpt_valid_blocks;
 	unsigned char *ckpt_valid_map;
+	unsigned char *discard_map;
 	unsigned char type;		/* segment type like CURSEG_XXX_TYPE */
 	unsigned long long mtime;	/* modification time of the segment */
 };
-- 
2.1.1

[PATCH 19/19] f2fs: issue discard with finally produced len and minlen

[Jaegeuk Kim]

This patch determines to issue discard commands by comparing given minlen and
the length of produced final candidates.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c |  2 +-
 fs/f2fs/f2fs.h       |  2 +-
 fs/f2fs/segment.c    | 10 ++++++----
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index d076e7e..1da20a6 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1043,7 +1043,7 @@ static void do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	if (unlikely(f2fs_cp_error(sbi)))
 		return;
 
-	clear_prefree_segments(sbi);
+	clear_prefree_segments(sbi, cpc);
 	clear_sbi_flag(sbi, SBI_IS_DIRTY);
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 98fc719..0b8c454 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1628,7 +1628,7 @@ int create_flush_cmd_control(struct f2fs_sb_info *);
 void destroy_flush_cmd_control(struct f2fs_sb_info *);
 void invalidate_blocks(struct f2fs_sb_info *, block_t);
 void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
-void clear_prefree_segments(struct f2fs_sb_info *);
+void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
 void release_discard_addrs(struct f2fs_sb_info *);
 void discard_next_dnode(struct f2fs_sb_info *, block_t);
 int npages_for_summary_flush(struct f2fs_sb_info *, bool);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 5a4ec01..667bbf2 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -597,7 +597,7 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-void clear_prefree_segments(struct f2fs_sb_info *sbi)
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct list_head *head = &(SM_I(sbi)->discard_list);
 	struct discard_entry *entry, *this;
@@ -630,7 +630,10 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi)
 
 	/* send small discards */
 	list_for_each_entry_safe(entry, this, head, list) {
+		if (cpc->reason == CP_DISCARD && entry->len < cpc->trim_minlen)
+			goto skip;
 		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
+skip:
 		list_del(&entry->list);
 		SM_I(sbi)->nr_discards -= entry->len;
 		kmem_cache_free(discard_entry_slab, entry);
@@ -1072,8 +1075,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	unsigned int start_segno, end_segno;
 	struct cp_control cpc;
 
-	if (range->minlen > SEGMENT_SIZE(sbi) || start >= MAX_BLKADDR(sbi) ||
-						range->len < sbi->blocksize)
+	if (start >= MAX_BLKADDR(sbi) || range->len < sbi->blocksize)
 		return -EINVAL;
 
 	cpc.trimmed = 0;
@@ -1085,7 +1087,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 	end_segno = (end >= MAX_BLKADDR(sbi)) ? MAIN_SEGS(sbi) - 1 :
 						GET_SEGNO(sbi, end);
 	cpc.reason = CP_DISCARD;
-	cpc.trim_minlen = F2FS_BYTES_TO_BLK(range->minlen);
+	cpc.trim_minlen = max_t(__u64, 1, F2FS_BYTES_TO_BLK(range->minlen));
 
 	/* do checkpoint to issue discard commands safely */
 	for (; start_segno <= end_segno; start_segno = cpc.trim_end + 1) {
-- 
2.1.1