ext4: Implement ext4_group_block_valid() as common function

In case of flex_bg feature (which is by default enabled), extents for any given inode might span across blocks from two different block group. ext4_mb_mark_bb() only reads the buffer_head of block bitmap once for the starting block group, but it fails to read it again when the extent length boundary overflows to another block group. Then in this below loop it accesses memory beyond the block group bitmap buffer_head and results into a data abort.

	for (i = 0; i < clen; i++)
		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
			already++;

This patch adds this functionality for checking block group boundary in ext4_mb_mark_bb() and update the buffer_head(bitmap_bh) for every different block group.

w/o this patch, I was easily able to hit a data access abort using Power platform.

<...>

[   74.327662] EXT4-fs error (device loop3): ext4_mb_generate_buddy:1141: group 11, block bitmap and bg descriptor inconsistent: 21248 vs 23294 free clusters
[   74.533214] EXT4-fs (loop3): shut down requested (2)
[   74.536705] Aborting journal on device loop3-8.
[   74.702705] BUG: Unable to handle kernel data access on read at 0xc00000005e980000
[   74.703727] Faulting instruction address: 0xc0000000007bffb8
cpu 0xd: Vector: 300 (Data Access) at [c000000015db7060]
    pc: c0000000007bffb8: ext4_mb_mark_bb+0x198/0x5a0
    lr: c0000000007bfeec: ext4_mb_mark_bb+0xcc/0x5a0
    sp: c000000015db7300
   msr: 800000000280b033
   dar: c00000005e980000
 dsisr: 40000000
  current = 0xc000000027af6880
  paca    = 0xc00000003ffd5200   irqmask: 0x03   irq_happened: 0x01
    pid   = 5167, comm = mount

<...>
enter ? for help
[c000000015db7380] c000000000782708 ext4_ext_clear_bb+0x378/0x410 [c000000015db7400] c000000000813f14 ext4_fc_replay+0x1794/0x2000 [c000000015db7580] c000000000833f7c do_one_pass+0xe9c/0x12a0 [c000000015db7710] c000000000834504 jbd2_journal_recover+0x184/0x2d0 [c000000015db77c0] c000000000841398 jbd2_journal_load+0x188/0x4a0 [c000000015db7880] c000000000804de8 ext4_fill_super+0x2638/0x3e10 [c000000015db7a40] c0000000005f8404 get_tree_bdev+0x2b4/0x350 [c000000015db7ae0] c0000000007ef058 ext4_get_tree+0x28/0x40 [c000000015db7b00] c0000000005f6344 vfs_get_tree+0x44/0x100 [c000000015db7b70] c00000000063c408 path_mount+0xdd8/0xe70 [c000000015db7c40] c00000000063c8f0 sys_mount+0x450/0x550 [c000000015db7d50] c000000000035770 system_call_exception+0x4a0/0x4e0 [c000000015db7e10] c00000000000c74c system_call_common+0xec/0x250 --- Exception: c00 (System Call) at 00007ffff7dbfaa4

Fixes 8016e29f4362e28 ("ext4: fast commit recovery path")

Signed-off-by Ritesh Harjani <[email protected]>

---
 fs/ext4/mballoc.c | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

fs/ext4/mballoc.c +0 -0

index c781974df9d0..8d23108cf9d7 100644
@@ -3899,12 +3899,29 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);

fs/ext4/mballoc.c +3 -0

+	overflow = 0;
 	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+
+	/*

fs/ext4/mballoc.c +11 -0

+	}
+
+	clen = EXT4_NUM_B2C(sbi, len);
+
 	bitmap_bh = ext4_read_block_bitmap(sb, group);
 	if (IS_ERR(bitmap_bh)) {
 		err = PTR_ERR(bitmap_bh);

@@ -3960,6 +3977,13 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
 	sync_dirty_buffer(gdp_bh);
 
+	if (overflow && !err) {
+		block += len;
+		len = overflow;
+		put_bh(bitmap_bh);
+		goto again;
+	}
+
 out_err:
 	brelse(bitmap_bh);
 }

Signature · 1 line

2.31.1

This patch implements ext4_group_block_valid() check functionality, and refactors all the callers to use this common function instead.

Signed-off-by Ritesh Harjani <[email protected]>

fs/ext4/mballoc.c +0 -1

index 8d23108cf9d7..60d32d3d8dc4 100644
@@ -6001,13 +6001,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		goto error_return;
 	}
 
-	if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||

Instead of open coding it, use in_range() function instead.

Signed-off-by Ritesh Harjani <[email protected]>

---
 fs/ext4/fast_commit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

fs/ext4/fast_commit.c +2 -2

index 5934c23e153e..bd6a47d18716 100644
@@ -1874,8 +1874,8 @@ bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk)
 		if (state->fc_regions[i].ino == 0 ||
 			state->fc_regions[i].len == 0)
 			continue;
-		if (blk >= state->fc_regions[i].pblk &&
-		    blk < state->fc_regions[i].pblk + state->fc_regions[i].len)
+		if (in_range(blk, state->fc_regions[i].pblk,
+					state->fc_regions[i].len))
 			return true;
 	}
 	return false;

Signature · 1 line

2.31.1

We don't need the return value of mb_test_and_clear_bits() in ext4_mb_mark_bb() So simply use mb_clear_bits() instead.

Signed-off-by Ritesh Harjani <[email protected]>

---
 fs/ext4/mballoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/ext4/mballoc.c +1 -1

index 60d32d3d8dc4..2f931575e6c2 100644
@@ -3943,7 +3943,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	if (state)
 		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
 	else
-		mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
+		mb_clear_bits(bitmap_bh->b_data, blkoff, clen);
 	if (ext4_has_group_desc_csum(sb) &&
 	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);

Signature · 1 line

2.31.1

ext4_free_blocks() function became too long and confusing, this patch just pulls out the ext4_mb_clear_bb() function logic from it which clears the block bitmap and frees it.

No functionality change in this patch

Signed-off-by Ritesh Harjani <[email protected]>

---
 fs/ext4/mballoc.c | 180 ++++++++++++++++++++++++++--------------------
 1 file changed, 102 insertions(+), 78 deletions(-)

fs/ext4/mballoc.c +102 -78

index 2f931575e6c2..5f20e355d08c 100644
@@ -5870,7 +5870,8 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
 }
 
 /**
- * ext4_free_blocks() -- Free given blocks and update quota
+ * ext4_mb_clear_bb() -- helper function for freeing blocks.
+ * 			Used by ext4_free_blocks()
  * @handle:		handle for this transaction
  * @inode:		inode
  * @bh:			optional buffer of the block to be freed

@@ -5878,9 +5879,9 @@ static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
  * @count:		number of blocks to be freed
  * @flags:		flags used by ext4_free_blocks
  */
-void ext4_free_blocks(handle_t *handle, struct inode *inode,
-		      struct buffer_head *bh, ext4_fsblk_t block,
-		      unsigned long count, int flags)
+static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
+			       ext4_fsblk_t block, unsigned long count,
+			       int flags)
 {
 	struct buffer_head *bitmap_bh = NULL;
 	struct super_block *sb = inode->i_sb;

@@ -5897,80 +5898,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 
 	sbi = EXT4_SB(sb);
 
-	if (sbi->s_mount_state & EXT4_FC_REPLAY) {
-		ext4_free_blocks_simple(inode, block, count);
-		return;
-	}
-
-	might_sleep();
-	if (bh) {
-		if (block)
-			BUG_ON(block != bh->b_blocknr);
-		else
-			block = bh->b_blocknr;
-	}
-
-	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
-	    !ext4_inode_block_valid(inode, block, count)) {
-		ext4_error(sb, "Freeing blocks not in datazone - "
-			   "block = %llu, count = %lu", block, count);
-		goto error_return;
-	}
-
-	ext4_debug("freeing block %llu\n", block);
-	trace_ext4_free_blocks(inode, block, count, flags);
-
-	if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
-		BUG_ON(count > 1);
-
-		ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
-			    inode, bh, block);
-	}
-
-	/*
-	 * If the extent to be freed does not begin on a cluster
-	 * boundary, we need to deal with partial clusters at the
-	 * beginning and end of the extent.  Normally we will free
-	 * blocks at the beginning or the end unless we are explicitly
-	 * requested to avoid doing so.
-	 */
-	overflow = EXT4_PBLK_COFF(sbi, block);
-	if (overflow) {
-		if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
-			overflow = sbi->s_cluster_ratio - overflow;
-			block += overflow;
-			if (count > overflow)
-				count -= overflow;
-			else
-				return;
-		} else {
-			block -= overflow;
-			count += overflow;
-		}
-	}
-	overflow = EXT4_LBLK_COFF(sbi, count);
-	if (overflow) {
-		if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
-			if (count > overflow)
-				count -= overflow;
-			else
-				return;
-		} else
-			count += sbi->s_cluster_ratio - overflow;
-	}
-
-	if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
-		int i;
-		int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
-
-		for (i = 0; i < count; i++) {
-			cond_resched();
-			if (is_metadata)
-				bh = sb_find_get_block(inode->i_sb, block + i);
-			ext4_forget(handle, is_metadata, inode, bh, block + i);
-		}
-	}
-
 do_more:
 	overflow = 0;
 	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);

@@ -6132,6 +6059,103 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	return;
 }
 
+/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle:		handle for this transaction
+ * @inode:		inode
+ * @bh:			optional buffer of the block to be freed
+ * @block:		starting physical block to be freed
+ * @count:		number of blocks to be freed
+ * @flags:		flags used by ext4_free_blocks
+ */
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+		      struct buffer_head *bh, ext4_fsblk_t block,
+		      unsigned long count, int flags)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned int overflow;
+	struct ext4_sb_info *sbi;
+
+	sbi = EXT4_SB(sb);
+
+	if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+		ext4_free_blocks_simple(inode, block, count);
+		return;
+	}
+
+	might_sleep();
+	if (bh) {
+		if (block)
+			BUG_ON(block != bh->b_blocknr);
+		else
+			block = bh->b_blocknr;
+	}
+
+	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
+	    !ext4_inode_block_valid(inode, block, count)) {
+		ext4_error(sb, "Freeing blocks not in datazone - "
+			   "block = %llu, count = %lu", block, count);
+		return;
+	}
+
+	ext4_debug("freeing block %llu\n", block);
+	trace_ext4_free_blocks(inode, block, count, flags);
+
+	if (bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
+		BUG_ON(count > 1);
+
+		ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
+			    inode, bh, block);
+	}
+
+	/*
+	 * If the extent to be freed does not begin on a cluster
+	 * boundary, we need to deal with partial clusters at the
+	 * beginning and end of the extent.  Normally we will free
+	 * blocks at the beginning or the end unless we are explicitly
+	 * requested to avoid doing so.
+	 */
+	overflow = EXT4_PBLK_COFF(sbi, block);
+	if (overflow) {
+		if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) {
+			overflow = sbi->s_cluster_ratio - overflow;
+			block += overflow;
+			if (count > overflow)
+				count -= overflow;
+			else
+				return;
+		} else {
+			block -= overflow;
+			count += overflow;
+		}
+	}
+	overflow = EXT4_LBLK_COFF(sbi, count);
+	if (overflow) {
+		if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) {
+			if (count > overflow)
+				count -= overflow;
+			else
+				return;
+		} else
+			count += sbi->s_cluster_ratio - overflow;
+	}
+
+	if (!bh && (flags & EXT4_FREE_BLOCKS_FORGET)) {
+		int i;
+		int is_metadata = flags & EXT4_FREE_BLOCKS_METADATA;
+
+		for (i = 0; i < count; i++) {
+			cond_resched();
+			if (is_metadata)
+				bh = sb_find_get_block(inode->i_sb, block + i);
+			ext4_forget(handle, is_metadata, inode, bh, block + i);
+		}
+	}
+
+	ext4_mb_clear_bb(handle, inode, block, count, flags);
+	return;
+}
+
 /**
  * ext4_group_add_blocks() -- Add given blocks to an existing group
  * @handle:			handle to this transaction

Signature · 1 line

2.31.1

This patch adds an extra checks in ext4_mb_mark_bb() function to make sure we mark & report error if we were to mark/clear any of the critical FS metadata specific bitmaps (&bail out) to prevent from any accidental corruption.

Signed-off-by Ritesh Harjani <[email protected]>

---
 fs/ext4/mballoc.c | 7 +++++++
 1 file changed, 7 insertions(+)

fs/ext4/mballoc.c +7 -0

index 5f20e355d08c..c94888534caa 100644
@@ -3920,6 +3920,13 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 		len -= overflow;
 	}
 
+	if (!ext4_group_block_valid(sb, group, block, len)) {
+		ext4_error(sb, "Marking blocks in system zone - "
+			   "Block = %llu, len = %d", block, len);
+		bitmap_bh = NULL;
+		goto out_err;
+	}
+
 	clen = EXT4_NUM_B2C(sbi, len);
 
 	bitmap_bh = ext4_read_block_bitmap(sb, group);

Signature · 1 line

2.31.1

Quoted 4 lines · Ritesh Harjani

This patch implements ext4_group_block_valid() check functionality, and refactors all the callers to use this common function instead.

Signed-off-by Ritesh Harjani <[email protected]>

...

Quoted 8 lines

fs/ext4/mballoc.c +0 -0

index 8d23108cf9d7..60d32d3d8dc4 100644
@@ -6001,13 +6001,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		goto error_return;
 	}
 

fs/ext4/mballoc.c void ext4_free_blocks(handle_t *handle, struct inode *inode, · line 6007

Quoted 11 lines

fs/ext4/mballoc.c +1 -7

-	if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
-	    in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
-	    in_range(block, ext4_inode_table(sb, gdp),
-		     sbi->s_itb_per_group) ||
-	    in_range(block + count - 1, ext4_inode_table(sb, gdp),
-		     sbi->s_itb_per_group)) {
-
+	if (!ext4_group_block_valid(sb, block_group, block, count)) {
 		ext4_error(sb, "Freeing blocks in system zone - "
 			   "Block = %llu, count = %lu", block, count);
 		/* err = 0. ext4_std_error should be a no op */

When doing this, why not rather directly use ext4_inode_block_valid() here?

Quoted 4 lines

fs/ext4/mballoc.c +0 -0

@@ -6194,11 +6188,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 		goto error_return;
 	}

fs/ext4/mballoc.c int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, · line 6194

Quoted 10 lines

fs/ext4/mballoc.c +1 -5

 
-	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
-	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
-	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
-	    in_range(block + count - 1, ext4_inode_table(sb, desc),
-		     sbi->s_itb_per_group)) {
+	if (!ext4_group_block_valid(sb, block_group, block, count)) {
 		ext4_error(sb, "Adding blocks in system zones - "
 			   "Block = %llu, count = %lu",
 			   block, count);

And here I'd rather refactor ext4_inode_block_valid() a bit to provide a more generic helper not requiring an inode and use it here...

Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR

Quoted 4 lines · Ritesh Harjani

We don't need the return value of mb_test_and_clear_bits() in ext4_mb_mark_bb() So simply use mb_clear_bits() instead.

Signed-off-by Ritesh Harjani <[email protected]>

Looks good. I'm rather confused by ext4_set_bits() vs mb_clear_bits() asymetry but that's not directly related to this patch. Just another cleanup to do. Feel free to add:

Reviewed-by Jan Kara <[email protected]>

Honza

Quoted 18 lines

---
 fs/ext4/mballoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/ext4/mballoc.c +1 -2

index 60d32d3d8dc4..2f931575e6c2 100644
@@ -3943,7 +3943,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	if (state)
 		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
 	else
-		mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
+		mb_clear_bits(bitmap_bh->b_data, blkoff, clen);
 	if (ext4_has_group_desc_csum(sb) &&
 	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
--

Quoted 2 lines

2.31.1

--
Jan Kara <[email protected]>
SUSE Labs, CR

Quoted 6 lines · Ritesh Harjani

This patch adds an extra checks in ext4_mb_mark_bb() function to make sure we mark & report error if we were to mark/clear any of the critical FS metadata specific bitmaps (&bail out) to prevent from any accidental corruption.

Signed-off-by Ritesh Harjani <[email protected]>

Again please rather use ext4_inode_block_valid() here. All the callers of ext4_mb_mark_bb() have the information available.

Honza

Quoted 23 lines

---
 fs/ext4/mballoc.c | 7 +++++++
 1 file changed, 7 insertions(+)

fs/ext4/mballoc.c +7 -1

index 5f20e355d08c..c94888534caa 100644
@@ -3920,6 +3920,13 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 		len -= overflow;
 	}
 
+	if (!ext4_group_block_valid(sb, group, block, len)) {
+		ext4_error(sb, "Marking blocks in system zone - "
+			   "Block = %llu, len = %d", block, len);
+		bitmap_bh = NULL;
+		goto out_err;
+	}
+
 	clen = EXT4_NUM_B2C(sbi, len);
 
 	bitmap_bh = ext4_read_block_bitmap(sb, group);
--

Quoted 2 lines

2.31.1

--
Jan Kara <[email protected]>
SUSE Labs, CR

Quoted 63 lines · Ritesh Harjani

In case of flex_bg feature (which is by default enabled), extents for any given inode might span across blocks from two different block group. ext4_mb_mark_bb() only reads the buffer_head of block bitmap once for the starting block group, but it fails to read it again when the extent length boundary overflows to another block group. Then in this below loop it accesses memory beyond the block group bitmap buffer_head and results into a data abort.

	for (i = 0; i < clen; i++)
		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
			already++;

This patch adds this functionality for checking block group boundary in ext4_mb_mark_bb() and update the buffer_head(bitmap_bh) for every different block group.

w/o this patch, I was easily able to hit a data access abort using Power platform.

<...>

[   74.327662] EXT4-fs error (device loop3): ext4_mb_generate_buddy:1141: group 11, block bitmap and bg descriptor inconsistent: 21248 vs 23294 free clusters
[   74.533214] EXT4-fs (loop3): shut down requested (2)
[   74.536705] Aborting journal on device loop3-8.
[   74.702705] BUG: Unable to handle kernel data access on read at 0xc00000005e980000
[   74.703727] Faulting instruction address: 0xc0000000007bffb8
cpu 0xd: Vector: 300 (Data Access) at [c000000015db7060]
    pc: c0000000007bffb8: ext4_mb_mark_bb+0x198/0x5a0
    lr: c0000000007bfeec: ext4_mb_mark_bb+0xcc/0x5a0
    sp: c000000015db7300
   msr: 800000000280b033
   dar: c00000005e980000
 dsisr: 40000000
  current = 0xc000000027af6880
  paca    = 0xc00000003ffd5200   irqmask: 0x03   irq_happened: 0x01
    pid   = 5167, comm = mount

<...>
enter ? for help
[c000000015db7380] c000000000782708 ext4_ext_clear_bb+0x378/0x410 [c000000015db7400] c000000000813f14 ext4_fc_replay+0x1794/0x2000 [c000000015db7580] c000000000833f7c do_one_pass+0xe9c/0x12a0 [c000000015db7710] c000000000834504 jbd2_journal_recover+0x184/0x2d0 [c000000015db77c0] c000000000841398 jbd2_journal_load+0x188/0x4a0 [c000000015db7880] c000000000804de8 ext4_fill_super+0x2638/0x3e10 [c000000015db7a40] c0000000005f8404 get_tree_bdev+0x2b4/0x350 [c000000015db7ae0] c0000000007ef058 ext4_get_tree+0x28/0x40 [c000000015db7b00] c0000000005f6344 vfs_get_tree+0x44/0x100 [c000000015db7b70] c00000000063c408 path_mount+0xdd8/0xe70 [c000000015db7c40] c00000000063c8f0 sys_mount+0x450/0x550 [c000000015db7d50] c000000000035770 system_call_exception+0x4a0/0x4e0 [c000000015db7e10] c00000000000c74c system_call_common+0xec/0x250 --- Exception: c00 (System Call) at 00007ffff7dbfaa4

Fixes 8016e29f4362e28 ("ext4: fast commit recovery path")

Signed-off-by Ritesh Harjani <[email protected]>

---
 fs/ext4/mballoc.c | 30 +++++++++++++++++++++++++++---
 1 file changed, 27 insertions(+), 3 deletions(-)

fs/ext4/mballoc.c +0 -0

index c781974df9d0..8d23108cf9d7 100644
@@ -3899,12 +3899,29 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);

fs/ext4/mballoc.c void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, · line 3906

Quoted 10 lines

fs/ext4/mballoc.c +3 -3

 	ext4_group_t group;
 	ext4_grpblk_t blkoff;
-	int i, clen, err;
+	int i, err;
 	int already;
+	unsigned int clen, overflow;
 
-	clen = EXT4_B2C(sbi, len);
-
+again:

And maybe structure this as a while loop? Like:

	while (len > 0) {
		...
	}

Quoted 5 lines

fs/ext4/mballoc.c +3 -0

+	overflow = 0;
 	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+
+	/*

fs/ext4/mballoc.c void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, · line 3920

Quoted 10 lines

fs/ext4/mballoc.c +10 -0

+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 * In case of flex_bg, this can happen that (block, len) may span across
+	 * more than one group. In that case we need to get the corresponding
+	 * group metadata to work with. For this we have goto again loop.
+	 */
+	if (EXT4_C2B(sbi, blkoff) + len > EXT4_BLOCKS_PER_GROUP(sb)) {
+		overflow = EXT4_C2B(sbi, blkoff) + len -
+			EXT4_BLOCKS_PER_GROUP(sb);
+		len -= overflow;

Why not just:

	thisgrp_len = min_t(int, len,
			EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
	clen = EXT4_NUM_B2C(sbi, thisgrp_len);

It seems easier to understand to me.

Quoted 15 lines · Jan Kara

Quoted 4 lines · Ritesh Harjani

This patch implements ext4_group_block_valid() check functionality, and refactors all the callers to use this common function instead.

Signed-off-by Ritesh Harjani <[email protected]>

...

Quoted 8 lines

fs/ext4/mballoc.c +0 -0

index 8d23108cf9d7..60d32d3d8dc4 100644
@@ -6001,13 +6001,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		goto error_return;
 	}
 

Quoted 13 lines

fs/ext4/mballoc.c void ext4_free_blocks(handle_t *handle, struct inode *inode, · line 6007

Quoted 11 lines

fs/ext4/mballoc.c +1 -7

-	if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
-	    in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
-	    in_range(block, ext4_inode_table(sb, gdp),
-		     sbi->s_itb_per_group) ||
-	    in_range(block + count - 1, ext4_inode_table(sb, gdp),
-		     sbi->s_itb_per_group)) {
-
+	if (!ext4_group_block_valid(sb, block_group, block, count)) {
 		ext4_error(sb, "Freeing blocks in system zone - "
 			   "Block = %llu, count = %lu", block, count);
 		/* err = 0. ext4_std_error should be a no op */

When doing this, why not rather directly use ext4_inode_block_valid() here?

This is because while freeing these blocks we have their's corresponding block group too. So there is little point in checking FS Metadata of all block groups v/s FS Metadata of just this block group, no?

Also, I am not sure if we changing this to check against system-zone's blocks (which has FS Metadata blocks from all block groups), can add any additional penalty?

Quoted 30 lines · Ritesh Harjani

Quoted 15 lines · Jan Kara

Quoted 4 lines · Ritesh Harjani

This patch implements ext4_group_block_valid() check functionality, and refactors all the callers to use this common function instead.

Signed-off-by Ritesh Harjani <[email protected]>

...

Quoted 8 lines

fs/ext4/mballoc.c +0 -0

index 8d23108cf9d7..60d32d3d8dc4 100644
@@ -6001,13 +6001,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 		goto error_return;
 	}
 

Quoted 13 lines

fs/ext4/mballoc.c void ext4_free_blocks(handle_t *handle, struct inode *inode, · line 6007

Quoted 11 lines

fs/ext4/mballoc.c +1 -7

-	if (in_range(ext4_block_bitmap(sb, gdp), block, count) ||
-	    in_range(ext4_inode_bitmap(sb, gdp), block, count) ||
-	    in_range(block, ext4_inode_table(sb, gdp),
-		     sbi->s_itb_per_group) ||
-	    in_range(block + count - 1, ext4_inode_table(sb, gdp),
-		     sbi->s_itb_per_group)) {
-
+	if (!ext4_group_block_valid(sb, block_group, block, count)) {
 		ext4_error(sb, "Freeing blocks in system zone - "
 			   "Block = %llu, count = %lu", block, count);
 		/* err = 0. ext4_std_error should be a no op */

When doing this, why not rather directly use ext4_inode_block_valid() here?

Quoted 7 lines

This is because while freeing these blocks we have their's corresponding block group too. So there is little point in checking FS Metadata of all block groups v/s FS Metadata of just this block group, no?

Also, I am not sure if we changing this to check against system-zone's blocks (which has FS Metadata blocks from all block groups), can add any additional penalty?

I agree the check will be somewhat more costly (rbtree lookup). OTOH with more complex fs structure (like flexbg which is default for quite some time), this is by far not checking the only metadata blocks, that can overlap the freed range. Also this is not checking for freeing journal blocks. So I'd either got for no check (if we really want performance) or full check (if we care more about detecting fs errors early). Because these half-baked checks do not bring much value these days...