Skip to contentSkip to conversation

fat: permit to return phy block number by fibmap in fallocated region

PATCH Superseded Namjae Jeon 2 participants 7 messages Dec 25, 2013 – Feb 4, 2014

Subsystems (2)

v3 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

PATCH v3 5/6 fat: permit to return phy block number by fibmap in fallocated region

From: Namjae Jeon <[email protected]>

Make the fibmap call the return the proper physical block number for any offset request in the fallocated range.

---
 fs/fat/cache.c |   13 ++++++++++---
 fs/fat/fat.h   |    3 +++
 fs/fat/inode.c |    3 +++
 3 files changed, 16 insertions(+), 3 deletions(-)
fs/fat/cache.c +10 -3
index a132666..d22c1a2 100644
@@ -325,19 +325,26 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 
 	last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
 	if (sector >= last_block) {
-		if (!create)
-			return 0;
-
 		/*
 		 * Both ->mmu_private and ->i_disksize can access
 		 * on only allocation path. (caller must hold ->i_mutex)
 		 */
 		last_block = (MSDOS_I(inode)->i_disksize + (blocksize - 1))
 			>> blocksize_bits;
+		if (!create) {
+			/* Map a block in fallocated region */
+			if (atomic_read(&MSDOS_I(inode)->beyond_isize))
+				if (sector < last_block)
+					goto out_map_cluster;
+
+			return 0;
+		}
+
 		if (sector >= last_block)
 			return 0;
 	}
 
+out_map_cluster:
 	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
 	offset  = sector & (sbi->sec_per_clus - 1);
 	cluster = fat_bmap_cluster(inode, cluster);
fs/fat/fat.h +3 -0
index 7b5851f..b884276 100644
@@ -129,6 +129,9 @@ struct msdos_inode_info {
 	struct hlist_node i_dir_hash;	/* hash by i_logstart */
 	struct rw_semaphore truncate_lock; /* protect bmap against truncate */
 	struct inode vfs_inode;
+
+	/* for getting block number beyond file size in case of fallocate */
+	atomic_t beyond_isize;
 };
 
 struct fat_slot_info {
fs/fat/inode.c +3 -0
index 3636617..1c3192b 100644
@@ -256,7 +256,10 @@ static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);
 
 	return blocknr;
Signature · 1 line
1.7.9.5
maintainer
#1 lore raw
Quoted 66 lines · Namjae Jeon

From: Namjae Jeon <[email protected]>

Make the fibmap call the return the proper physical block number for any offset request in the fallocated range.

---
 fs/fat/cache.c |   13 ++++++++++---
 fs/fat/fat.h   |    3 +++
 fs/fat/inode.c |    3 +++
 3 files changed, 16 insertions(+), 3 deletions(-)
fs/fat/cache.c +10 -3
index a132666..d22c1a2 100644
@@ -325,19 +325,26 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 
 	last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
 	if (sector >= last_block) {
-		if (!create)
-			return 0;
-
 		/*
 		 * Both ->mmu_private and ->i_disksize can access
 		 * on only allocation path. (caller must hold ->i_mutex)
 		 */
 		last_block = (MSDOS_I(inode)->i_disksize + (blocksize - 1))
 			>> blocksize_bits;
+		if (!create) {
+			/* Map a block in fallocated region */
+			if (atomic_read(&MSDOS_I(inode)->beyond_isize))
+				if (sector < last_block)
+					goto out_map_cluster;
+
+			return 0;
+		}
+
 		if (sector >= last_block)
 			return 0;
 	}
 
+out_map_cluster:
 	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
 	offset  = sector & (sbi->sec_per_clus - 1);
 	cluster = fat_bmap_cluster(inode, cluster);
fs/fat/fat.h +3 -0
index 7b5851f..b884276 100644
@@ -129,6 +129,9 @@ struct msdos_inode_info {
 	struct hlist_node i_dir_hash;	/* hash by i_logstart */
 	struct rw_semaphore truncate_lock; /* protect bmap against truncate */
 	struct inode vfs_inode;
+
+	/* for getting block number beyond file size in case of fallocate */
+	atomic_t beyond_isize;
 };
 
 struct fat_slot_info {
fs/fat/inode.c +0 -0
index 3636617..1c3192b 100644

fs/fat/inode.c static sector_t _fat_bmap(struct address_space *mapping, sector_t block) · line 263

Quoted 8 lines
fs/fat/inode.c +3 -0
@@ -256,7 +256,10 @@ static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);

This is racy. While user is using bmap, kernel can allocate new blocks. We should use another function for this.

For example, something like

fat_get_block_bmap()

{
        [...]
	fat_get_block2(inode, iblock, &max_blocks, bh_result, create, bmap);
        [...]
}

blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);

Signature · 1 line
OGAWA Hirofumi <[email protected]>
#2 lore raw

2014-02-03, OGAWA Hirofumi <[email protected]>:

Quoted 71 lines
Quoted 69 lines · Namjae Jeon

From: Namjae Jeon <[email protected]>

Make the fibmap call the return the proper physical block number for any offset request in the fallocated range.

---
 fs/fat/cache.c |   13 ++++++++++---
 fs/fat/fat.h   |    3 +++
 fs/fat/inode.c |    3 +++
 3 files changed, 16 insertions(+), 3 deletions(-)
fs/fat/cache.c +10 -3
index a132666..d22c1a2 100644
@@ -325,19 +325,26 @@ int fat_bmap(struct inode *inode, sector_t sector,
 sector_t *phys,
 
 	last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
 	if (sector >= last_block) {
-		if (!create)
-			return 0;
-
 		/*
 		 * Both ->mmu_private and ->i_disksize can access
 		 * on only allocation path. (caller must hold ->i_mutex)
 		 */
 		last_block = (MSDOS_I(inode)->i_disksize + (blocksize - 1))
 			>> blocksize_bits;
+		if (!create) {
+			/* Map a block in fallocated region */
+			if (atomic_read(&MSDOS_I(inode)->beyond_isize))
+				if (sector < last_block)
+					goto out_map_cluster;
+
+			return 0;
+		}
+
 		if (sector >= last_block)
 			return 0;
 	}
 
+out_map_cluster:
 	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
 	offset  = sector & (sbi->sec_per_clus - 1);
fs/fat/cache.c +0 -0
 	cluster = fat_bmap_cluster(inode, cluster);
fs/fat/fat.h +3 -0
index 7b5851f..b884276 100644
@@ -129,6 +129,9 @@ struct msdos_inode_info {
 	struct hlist_node i_dir_hash;	/* hash by i_logstart */
 	struct rw_semaphore truncate_lock; /* protect bmap against truncate */
 	struct inode vfs_inode;
+
+	/* for getting block number beyond file size in case of fallocate */
+	atomic_t beyond_isize;
 };
 
 struct fat_slot_info {
fs/fat/inode.c +0 -0
index 3636617..1c3192b 100644
@@ -256,7 +256,10 @@ static sector_t _fat_bmap(struct address_space
 *mapping, sector_t block)
 
Quoted 10 lines

fs/fat/inode.c static sector_t _fat_bmap(struct address_space *mapping, sector_t block) · line 263

Quoted 7 lines
fs/fat/inode.c +3 -0
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);

This is racy. While user is using bmap, kernel can allocate new blocks. We should use another function for this.

I understand that fat can map fallocated blocks in read case while user is using bmap.
But I can not find the case allocate new blocks.
If I am missing something, Could you please elaborate more ? Is it a case of _bmap request returning the block number for block allocated in parallel write path ?

Thanks.

Quoted 14 lines

For example, something like

fat_get_block_bmap()

{
        [...]
	fat_get_block2(inode, iblock, &max_blocks, bh_result, create, bmap);
        [...]
}

blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); --
OGAWA Hirofumi <[email protected]>

maintainer
#3 lore raw
Quoted 10 lines · Namjae Jeon
Quoted 10 lines

fs/fat/inode.c static sector_t _fat_bmap(struct address_space *mapping, sector_t block) · line 263

Quoted 7 lines
fs/fat/inode.c +3 -0
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);

This is racy. While user is using bmap, kernel can allocate new blocks. We should use another function for this.

Quoted 6 lines

I understand that fat can map fallocated blocks in read case while user is using bmap.
But I can not find the case allocate new blocks.
If I am missing something, Could you please elaborate more ? Is it a case of _bmap request returning the block number for block allocated in parallel write path ?

->beyond_size is global for inode. So, write(2) path on same inode with bmap() also can see 1 set by bmap() while another process is using bmap().

Signature · 1 line
OGAWA Hirofumi <[email protected]>
#4 lore raw

2014-02-04, OGAWA Hirofumi <[email protected]>:

Quoted 20 lines
Quoted 11 lines · Namjae Jeon
Quoted 11 lines

fs/fat/inode.c static sector_t _fat_bmap(struct address_space *mapping, sector_t block) · line 263

Quoted 8 lines

/* fat_get_cluster() assumes the requested blocknr isn't truncated.
*/

fs/fat/inode.c +3 -0
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);

This is racy. While user is using bmap, kernel can allocate new blocks. We should use another function for this.

Quoted 6 lines

I understand that fat can map fallocated blocks in read case while user is using bmap.
But I can not find the case allocate new blocks.
If I am missing something, Could you please elaborate more ? Is it a case of _bmap request returning the block number for block allocated in parallel write path ?

Quoted 2 lines

->beyond_size is global for inode. So, write(2) path on same inode with bmap() also can see 1 set by bmap() while another process is using bmap().

'create' flag will be 1 in write(2) path. ->beyond_isize will only be checked when 'create' flag is 0. Is there any case to be racy by beyond_isize in write(2) path ?

Thanks.

Quoted 3 lines

--
OGAWA Hirofumi <[email protected]>

maintainer
#5 lore raw
Quoted 21 lines · Namjae Jeon

2014-02-04, OGAWA Hirofumi <[email protected]>:

Quoted 20 lines
Quoted 17 lines · Namjae Jeon
Quoted 11 lines

fs/fat/inode.c static sector_t _fat_bmap(struct address_space *mapping, sector_t block) · line 263

Quoted 8 lines

/* fat_get_cluster() assumes the requested blocknr isn't truncated.
*/

fs/fat/inode.c +3 -0
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);

This is racy. While user is using bmap, kernel can allocate new blocks. We should use another function for this.

I understand that fat can map fallocated blocks in read case while user is using bmap.
But I can not find the case allocate new blocks.
If I am missing something, Could you please elaborate more ? Is it a case of _bmap request returning the block number for block allocated in parallel write path ?

Quoted 5 lines
Quoted 2 lines

->beyond_size is global for inode. So, write(2) path on same inode with bmap() also can see 1 set by bmap() while another process is using bmap().

'create' flag will be 1 in write(2) path. ->beyond_isize will only be checked when 'create' flag is 0. Is there any case to be racy by beyond_isize in write(2) path ?

Ah, so instead of write, it will assign physical address to buffers beyond i_size for simple read if race? In this case, it is still wrong.

Signature · 1 line
OGAWA Hirofumi <[email protected]>
#6 lore raw

2014-02-04, OGAWA Hirofumi <[email protected]>:

Quoted 27 lines
Quoted 25 lines · Namjae Jeon

2014-02-04, OGAWA Hirofumi <[email protected]>:

Quoted 24 lines
Quoted 12 lines · Namjae Jeon
Quoted 4 lines
Quoted 4 lines

/* fat_get_cluster() assumes the requested blocknr isn't truncated.
*/

fs/fat/inode.c +1 -0
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
+	/* To get block number beyond file size in fallocated region */
Quoted 8 lines

fs/fat/inode.c static sector_t _fat_bmap(struct address_space *mapping, sector_t block) · line 263

Quoted 4 lines
fs/fat/inode.c +2 -0
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 1);
 	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	atomic_set(&MSDOS_I(mapping->host)->beyond_isize, 0);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);

This is racy. While user is using bmap, kernel can allocate new blocks.
We should use another function for this.

Quoted 6 lines

I understand that fat can map fallocated blocks in read case while user is using bmap.
But I can not find the case allocate new blocks.
If I am missing something, Could you please elaborate more ? Is it a case of _bmap request returning the block number for block allocated in parallel write path ?

->beyond_size is global for inode. So, write(2) path on same inode with bmap() also can see 1 set by bmap() while another process is using bmap().

Quoted 6 lines
Quoted 3 lines

'create' flag will be 1 in write(2) path. ->beyond_isize will only be checked when 'create' flag is 0. Is there any case to be racy by beyond_isize in write(2) path ?

Ah, so instead of write, it will assign physical address to buffers beyond i_size for simple read if race? In this case, it is still wrong.

Right. I will fix this case.
Thanks for review!

Quoted 3 lines

--
OGAWA Hirofumi <[email protected]>