ext4: fast_commit fixes, stricter block checking & cleanups

ext4_mb_mark_bb() currently wrongly calculates cluster len (clen) and flex_group->free_clusters. This patch fixes that.

Identified based on code review of ext4_mb_mark_bb() function.

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

---
 fs/ext4/mballoc.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

fs/ext4/mballoc.c +12 -7

index c781974df9d0..2f117ce3bb73 100644
@@ -3899,10 +3899,11 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_group_t group;
 	ext4_grpblk_t blkoff;
-	int i, clen, err;
+	int i, err;
 	int already;
+	unsigned int clen, clen_changed;
 
-	clen = EXT4_B2C(sbi, len);
+	clen = EXT4_NUM_B2C(sbi, len);
 
 	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
 	bitmap_bh = ext4_read_block_bitmap(sb, group);

@@ -3923,6 +3924,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
 			already++;
 
+	clen_changed = clen - already;
 	if (state)
 		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
 	else

@@ -3935,9 +3937,9 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 						group, gdp));
 	}
 	if (state)
-		clen = ext4_free_group_clusters(sb, gdp) - clen + already;
+		clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
 	else
-		clen = ext4_free_group_clusters(sb, gdp) + clen - already;
+		clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
 
 	ext4_free_group_clusters_set(sb, gdp, clen);
 	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);

@@ -3947,10 +3949,13 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, group);
+		struct flex_groups *fg = sbi_array_rcu_deref(sbi,
+					   s_flex_groups, flex_group);
 
-		atomic64_sub(len,
-			     &sbi_array_rcu_deref(sbi, s_flex_groups,
-						  flex_group)->free_clusters);
+		if (state)
+			atomic64_sub(clen_changed, &fg->free_clusters);
+		else
+			atomic64_add(clen_changed, &fg->free_clusters);
 	}
 
 	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);

Signature · 1 line

2.31.1

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

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

---
 fs/ext4/mballoc.c | 131 +++++++++++++++++++++++++++-------------------
 1 file changed, 76 insertions(+), 55 deletions(-)

fs/ext4/mballoc.c +63 -47

index 2f117ce3bb73..d0bd51b1e1ad 100644
@@ -3901,72 +3901,93 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	ext4_grpblk_t blkoff;
 	int i, err;
 	int already;
-	unsigned int clen, clen_changed;
+	unsigned int clen, clen_changed, thisgrp_len;
 
-	clen = EXT4_NUM_B2C(sbi, len);
-
-	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
-	bitmap_bh = ext4_read_block_bitmap(sb, group);
-	if (IS_ERR(bitmap_bh)) {
-		err = PTR_ERR(bitmap_bh);
-		bitmap_bh = NULL;
-		goto out_err;
-	}
-
-	err = -EIO;
-	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
-	if (!gdp)
-		goto out_err;
+	while (len > 0) {
+		ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
 
-	ext4_lock_group(sb, group);
-	already = 0;
-	for (i = 0; i < clen; i++)
-		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
-			already++;
-
-	clen_changed = clen - already;
-	if (state)
-		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
-	else
-		mb_test_and_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);
-		ext4_free_group_clusters_set(sb, gdp,
-					     ext4_free_clusters_after_init(sb,
-						group, gdp));
-	}
-	if (state)
-		clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
-	else
-		clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
+		/*
+		 * 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.
+		 */
+		thisgrp_len = min_t(unsigned int, (unsigned int)len,
+			EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
+		clen = EXT4_NUM_B2C(sbi, thisgrp_len);
 
-	ext4_free_group_clusters_set(sb, gdp, clen);
-	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
-	ext4_group_desc_csum_set(sb, group, gdp);
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(bitmap_bh)) {
+			err = PTR_ERR(bitmap_bh);
+			bitmap_bh = NULL;
+			break;
+		}
 
-	ext4_unlock_group(sb, group);
+		err = -EIO;
+		gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+		if (!gdp)
+			break;
 
-	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t flex_group = ext4_flex_group(sbi, group);
-		struct flex_groups *fg = sbi_array_rcu_deref(sbi,
-					   s_flex_groups, flex_group);
+		ext4_lock_group(sb, group);
+		already = 0;
+		for (i = 0; i < clen; i++)
+			if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) ==
+					 !state)
+				already++;
 
+		clen_changed = clen - already;
 		if (state)
-			atomic64_sub(clen_changed, &fg->free_clusters);
+			ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
 		else
-			atomic64_add(clen_changed, &fg->free_clusters);
+			mb_test_and_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);
+			ext4_free_group_clusters_set(sb, gdp,
+			     ext4_free_clusters_after_init(sb, group, gdp));
+		}
+		if (state)
+			clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
+		else
+			clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
+
+		ext4_free_group_clusters_set(sb, gdp, clen);
+		ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+		ext4_group_desc_csum_set(sb, group, gdp);
+
+		ext4_unlock_group(sb, group);
+
+		if (sbi->s_log_groups_per_flex) {
+			ext4_group_t flex_group = ext4_flex_group(sbi, group);
+			struct flex_groups *fg = sbi_array_rcu_deref(sbi,
+						   s_flex_groups, flex_group);
+
+			if (state)
+				atomic64_sub(clen_changed, &fg->free_clusters);
+			else
+				atomic64_add(clen_changed, &fg->free_clusters);
+
+		}
+
+		err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);

Quoted 50 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

Quoted 1 line

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

Just two nits below. Otherwise feel free to add:

Reviewed-by Jan Kara <[email protected]>

Quoted 130 lines

---
 fs/ext4/mballoc.c | 131 +++++++++++++++++++++++++++-------------------
 1 file changed, 76 insertions(+), 55 deletions(-)

fs/ext4/mballoc.c +63 -47

index 2f117ce3bb73..d0bd51b1e1ad 100644
@@ -3901,72 +3901,93 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	ext4_grpblk_t blkoff;
 	int i, err;
 	int already;
-	unsigned int clen, clen_changed;
+	unsigned int clen, clen_changed, thisgrp_len;
 
-	clen = EXT4_NUM_B2C(sbi, len);
-
-	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
-	bitmap_bh = ext4_read_block_bitmap(sb, group);
-	if (IS_ERR(bitmap_bh)) {
-		err = PTR_ERR(bitmap_bh);
-		bitmap_bh = NULL;
-		goto out_err;
-	}
-
-	err = -EIO;
-	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
-	if (!gdp)
-		goto out_err;
+	while (len > 0) {
+		ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
 
-	ext4_lock_group(sb, group);
-	already = 0;
-	for (i = 0; i < clen; i++)
-		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
-			already++;
-
-	clen_changed = clen - already;
-	if (state)
-		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
-	else
-		mb_test_and_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);
-		ext4_free_group_clusters_set(sb, gdp,
-					     ext4_free_clusters_after_init(sb,
-						group, gdp));
-	}
-	if (state)
-		clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
-	else
-		clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
+		/*
+		 * 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.
+		 */
+		thisgrp_len = min_t(unsigned int, (unsigned int)len,
+			EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
+		clen = EXT4_NUM_B2C(sbi, thisgrp_len);
 
-	ext4_free_group_clusters_set(sb, gdp, clen);
-	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
-	ext4_group_desc_csum_set(sb, group, gdp);
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(bitmap_bh)) {
+			err = PTR_ERR(bitmap_bh);
+			bitmap_bh = NULL;
+			break;
+		}
 
-	ext4_unlock_group(sb, group);
+		err = -EIO;
+		gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+		if (!gdp)
+			break;
 
-	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t flex_group = ext4_flex_group(sbi, group);
-		struct flex_groups *fg = sbi_array_rcu_deref(sbi,
-					   s_flex_groups, flex_group);
+		ext4_lock_group(sb, group);
+		already = 0;
+		for (i = 0; i < clen; i++)
+			if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) ==
+					 !state)
+				already++;
 
+		clen_changed = clen - already;
 		if (state)
-			atomic64_sub(clen_changed, &fg->free_clusters);
+			ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
 		else
-			atomic64_add(clen_changed, &fg->free_clusters);
+			mb_test_and_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);
+			ext4_free_group_clusters_set(sb, gdp,
+			     ext4_free_clusters_after_init(sb, group, gdp));
+		}
+		if (state)
+			clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
+		else
+			clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
+
+		ext4_free_group_clusters_set(sb, gdp, clen);
+		ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+		ext4_group_desc_csum_set(sb, group, gdp);
+
+		ext4_unlock_group(sb, group);
+
+		if (sbi->s_log_groups_per_flex) {
+			ext4_group_t flex_group = ext4_flex_group(sbi, group);
+			struct flex_groups *fg = sbi_array_rcu_deref(sbi,
+						   s_flex_groups, flex_group);
+
+			if (state)
+				atomic64_sub(clen_changed, &fg->free_clusters);
+			else
+				atomic64_add(clen_changed, &fg->free_clusters);
+
+		}
+
+		err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);

fs/ext4/mballoc.c void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, · line 3984

Quoted 10 lines

fs/ext4/mballoc.c +10 -0

+		if (err)
+			break;
+		sync_dirty_buffer(bitmap_bh);
+		err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+		sync_dirty_buffer(gdp_bh);
+		if (err)
+			break;
+
+		block += thisgrp_len;
+		len = len - thisgrp_len;

		^^^ Maybe: len -= thisgrp_len;

fs/ext4/mballoc.c void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, · line 3985

Quoted 1 line

fs/ext4/mballoc.c +1 -0

+		put_bh(bitmap_bh);

^^ brelse() would be more usual here...

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

Quoted 199 lines · Jan Kara

Quoted 50 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

Quoted 1 line

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

Just two nits below. Otherwise feel free to add:

Reviewed-by Jan Kara <[email protected]>

Quoted 130 lines

---
 fs/ext4/mballoc.c | 131 +++++++++++++++++++++++++++-------------------
 1 file changed, 76 insertions(+), 55 deletions(-)

fs/ext4/mballoc.c +63 -47

index 2f117ce3bb73..d0bd51b1e1ad 100644
@@ -3901,72 +3901,93 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 	ext4_grpblk_t blkoff;
 	int i, err;
 	int already;
-	unsigned int clen, clen_changed;
+	unsigned int clen, clen_changed, thisgrp_len;
 
-	clen = EXT4_NUM_B2C(sbi, len);
-
-	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
-	bitmap_bh = ext4_read_block_bitmap(sb, group);
-	if (IS_ERR(bitmap_bh)) {
-		err = PTR_ERR(bitmap_bh);
-		bitmap_bh = NULL;
-		goto out_err;
-	}
-
-	err = -EIO;
-	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
-	if (!gdp)
-		goto out_err;
+	while (len > 0) {
+		ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
 
-	ext4_lock_group(sb, group);
-	already = 0;
-	for (i = 0; i < clen; i++)
-		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
-			already++;
-
-	clen_changed = clen - already;
-	if (state)
-		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
-	else
-		mb_test_and_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);
-		ext4_free_group_clusters_set(sb, gdp,
-					     ext4_free_clusters_after_init(sb,
-						group, gdp));
-	}
-	if (state)
-		clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
-	else
-		clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
+		/*
+		 * 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.
+		 */
+		thisgrp_len = min_t(unsigned int, (unsigned int)len,
+			EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
+		clen = EXT4_NUM_B2C(sbi, thisgrp_len);
 
-	ext4_free_group_clusters_set(sb, gdp, clen);
-	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
-	ext4_group_desc_csum_set(sb, group, gdp);
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(bitmap_bh)) {
+			err = PTR_ERR(bitmap_bh);
+			bitmap_bh = NULL;
+			break;
+		}
 
-	ext4_unlock_group(sb, group);
+		err = -EIO;
+		gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+		if (!gdp)
+			break;
 
-	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t flex_group = ext4_flex_group(sbi, group);
-		struct flex_groups *fg = sbi_array_rcu_deref(sbi,
-					   s_flex_groups, flex_group);
+		ext4_lock_group(sb, group);
+		already = 0;
+		for (i = 0; i < clen; i++)
+			if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) ==
+					 !state)
+				already++;
 
+		clen_changed = clen - already;
 		if (state)
-			atomic64_sub(clen_changed, &fg->free_clusters);
+			ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
 		else
-			atomic64_add(clen_changed, &fg->free_clusters);
+			mb_test_and_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);
+			ext4_free_group_clusters_set(sb, gdp,
+			     ext4_free_clusters_after_init(sb, group, gdp));
+		}
+		if (state)
+			clen = ext4_free_group_clusters(sb, gdp) - clen_changed;
+		else
+			clen = ext4_free_group_clusters(sb, gdp) + clen_changed;
+
+		ext4_free_group_clusters_set(sb, gdp, clen);
+		ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+		ext4_group_desc_csum_set(sb, group, gdp);
+
+		ext4_unlock_group(sb, group);
+
+		if (sbi->s_log_groups_per_flex) {
+			ext4_group_t flex_group = ext4_flex_group(sbi, group);
+			struct flex_groups *fg = sbi_array_rcu_deref(sbi,
+						   s_flex_groups, flex_group);
+
+			if (state)
+				atomic64_sub(clen_changed, &fg->free_clusters);
+			else
+				atomic64_add(clen_changed, &fg->free_clusters);
+
+		}
+
+		err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);

fs/ext4/mballoc.c void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, · line 3984

Quoted 10 lines

fs/ext4/mballoc.c +10 -0

+		if (err)
+			break;
+		sync_dirty_buffer(bitmap_bh);
+		err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+		sync_dirty_buffer(gdp_bh);
+		if (err)
+			break;
+
+		block += thisgrp_len;
+		len = len - thisgrp_len;

		^^^ Maybe: len -= thisgrp_len;

Quoted 2 lines

fs/ext4/mballoc.c void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block, · line 3985

Quoted 1 line

fs/ext4/mballoc.c +1 -0

+		put_bh(bitmap_bh);

^^ brelse() would be more usual here...

Sure, will make above two changes.

Btw, any general rules of when should we use put_bh() v/s brelse()?

Assumption about why I used put_bh() above was that in a non-error loop, where we are doing ext4_read_block_bitmap() (which will return bh with b_count elevated), I thought, we could simply do put_bh() in the end.

But when there is a possibility of an error occurred somewhere in between, then it's safe to do brelse().

ext4_set_bits() should actually be mb_set_bits() for uniform API naming convention.
This is via below cmd -

grep -nr "ext4_set_bits" fs/ext4/ | cut -d ":" -f 1 | xargs sed -i 's/ext4_set_bits/mb_set_bits/g'

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

---
 fs/ext4/ext4.h    |  2 +-
 fs/ext4/mballoc.c | 14 +++++++-------
 fs/ext4/resize.c  |  4 ++--
 3 files changed, 10 insertions(+), 10 deletions(-)

fs/ext4/ext4.h +1 -1

index 09d8f60ebf0f..8c1d0e352f47 100644
@@ -1279,7 +1279,7 @@ struct ext4_inode_info {
 #define ext4_find_next_zero_bit		find_next_zero_bit_le
 #define ext4_find_next_bit		find_next_bit_le
 
-extern void ext4_set_bits(void *bm, int cur, int len);
+extern void mb_set_bits(void *bm, int cur, int len);
 
 /*
  * Maximal mount counts between two filesystem checks

fs/ext4/mballoc.c +7 -7

index 91058f81a0c6..f80af108d05e 100644
@@ -1689,7 +1689,7 @@ static int mb_test_and_clear_bits(void *bm, int cur, int len)
 	return zero_bit;
 }
 
-void ext4_set_bits(void *bm, int cur, int len)
+void mb_set_bits(void *bm, int cur, int len)
 {
 	__u32 *addr;
 

@@ -1996,7 +1996,7 @@ static int mb_mark_used(struct ext4_buddy *e4b, struct ext4_free_extent *ex)
 	mb_set_largest_free_order(e4b->bd_sb, e4b->bd_info);
 
 	mb_update_avg_fragment_size(e4b->bd_sb, e4b->bd_info);
-	ext4_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
+	mb_set_bits(e4b->bd_bitmap, ex->fe_start, len0);
 	mb_check_buddy(e4b);
 
 	return ret;

@@ -3825,7 +3825,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		 * We leak some of the blocks here.
 		 */
 		ext4_lock_group(sb, ac->ac_b_ex.fe_group);
-		ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+		mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
 			      ac->ac_b_ex.fe_len);
 		ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
 		err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);

@@ -3844,7 +3844,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 		}
 	}
 #endif
-	ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
+	mb_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
 		      ac->ac_b_ex.fe_len);
 	if (ext4_has_group_desc_csum(sb) &&
 	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {

@@ -3939,7 +3939,7 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 
 		clen_changed = clen - already;
 		if (state)
-			ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
+			mb_set_bits(bitmap_bh->b_data, blkoff, clen);
 		else
 			mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
 		if (ext4_has_group_desc_csum(sb) &&

@@ -4459,7 +4459,7 @@ static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 
 	while (n) {
 		entry = rb_entry(n, struct ext4_free_data, efd_node);
-		ext4_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
+		mb_set_bits(bitmap, entry->efd_start_cluster, entry->efd_count);
 		n = rb_next(n);
 	}
 	return;

@@ -4500,7 +4500,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 		if (unlikely(len == 0))
 			continue;
 		BUG_ON(groupnr != group);
-		ext4_set_bits(bitmap, start, len);
+		mb_set_bits(bitmap, start, len);
 		preallocated += len;
 	}
 	mb_debug(sb, "preallocated %d for group %u\n", preallocated, group);

fs/ext4/resize.c +2 -3

index ee8f02f406cb..f507f34be602 100644
@@ -483,7 +483,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
 		}
 		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n",
 			   first_cluster, first_cluster - start, count2);
-		ext4_set_bits(bh->b_data, first_cluster - start, count2);
+		mb_set_bits(bh->b_data, first_cluster - start, count2);
 
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
 		brelse(bh);

@@ -632,7 +632,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb,
 		if (overhead != 0) {
 			ext4_debug("mark backup superblock %#04llx (+0)\n",
 				   start);
-			ext4_set_bits(bh->b_data, 0,
+			mb_set_bits(bh->b_data, 0,
 				      EXT4_NUM_B2C(sbi, overhead));
 		}
 		ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count),
--

2.31.1

This API will be needed at places where we don't have an inode for e.g. while freeing blocks in ext4_group_add_blocks()

Suggested-by Jan Kara <[email protected]>

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

Quoted 5 lines · Ritesh Harjani

This API will be needed at places where we don't have an inode for e.g. while freeing blocks in ext4_group_add_blocks()

Suggested-by Jan Kara <[email protected]>

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

...

fs/ext4/block_validity.c int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, · line 329

Quoted 8 lines

fs/ext4/block_validity.c +2 -1

@@ -329,7 +324,8 @@ int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
 		else if (start_blk >= (entry->start_blk + entry->count))
 			n = n->rb_right;
 		else {
-			ret = (entry->ino == inode->i_ino);
+			if (inode)
+				ret = (entry->ino == inode->i_ino);
 			break;

In case inode is not passed, we must not overlap any entry in the rbtree. So we should return 0, not 1.

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

Currently ext4_mb_clear_bb() & ext4_group_add_blocks() only checks whether the given block ranges (which is to be freed) belongs to any FS metadata blocks or not, of the block's respective block group. But to detect any FS error early, it is better to add more strict checkings in those functions which checks whether the given blocks belongs to any critical FS metadata or not within system-zone.

Suggested-by Jan Kara <[email protected]>

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

---
 fs/ext4/mballoc.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

fs/ext4/mballoc.c +3 -13

index 23313963bb56..9f2b3a057918 100644
@@ -5930,13 +5930,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
 		goto error_return;
 	}
 
-	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_inode_block_valid(inode, 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 */

@@ -6007,7 +6001,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
 						 NULL);
 			if (err && err != -EOPNOTSUPP)
 				ext4_msg(sb, KERN_WARNING, "discard request in"
-					 " group:%d block:%d count:%lu failed"
+					 " group:%u block:%d count:%lu failed"
 					 " with %d", block_group, bit, count,
 					 err);
 		} else

@@ -6220,11 +6214,7 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 		goto error_return;
 	}
 
-	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_sb_block_valid(sb, NULL, block, count)) {
 		ext4_error(sb, "Adding blocks in system zones - "
 			   "Block = %llu, count = %lu",
 			   block, count);

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.

Suggested-by Jan Kara <[email protected]>

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

---
 fs/ext4/mballoc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

fs/ext4/mballoc.c +8 -0

index 9f2b3a057918..75c20a10529a 100644
@@ -3918,6 +3918,14 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
 			EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
 		clen = EXT4_NUM_B2C(sbi, thisgrp_len);
 
+		if (!ext4_sb_block_valid(sb, NULL, block, thisgrp_len)) {
+			ext4_error(sb, "Marking blocks in system zone - "
+				   "Block = %llu, len = %u",
+				   block, thisgrp_len);
+			bitmap_bh = NULL;
+			break;
+		}
+
 		bitmap_bh = ext4_read_block_bitmap(sb, group);
 		if (IS_ERR(bitmap_bh)) {
 			err = PTR_ERR(bitmap_bh);

Signature · 1 line

2.31.1