summaryrefslogtreecommitdiffstats
path: root/fs/ext4/mballoc.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:57 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 17:39:57 +0000
commitdc50eab76b709d68175a358d6e23a5a3890764d3 (patch)
treec754d0390db060af0213ff994f0ac310e4cfd6e9 /fs/ext4/mballoc.c
parentAdding debian version 6.6.15-2. (diff)
downloadlinux-dc50eab76b709d68175a358d6e23a5a3890764d3.tar.xz
linux-dc50eab76b709d68175a358d6e23a5a3890764d3.zip
Merging upstream version 6.7.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/ext4/mballoc.c')
-rw-r--r--fs/ext4/mballoc.c613
1 files changed, 248 insertions, 365 deletions
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9a4b73485d..7497a789d0 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -18,6 +18,7 @@
#include <linux/backing-dev.h>
#include <linux/freezer.h>
#include <trace/events/ext4.h>
+#include <kunit/static_stub.h>
/*
* MUSTDO:
@@ -841,7 +842,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
struct ext4_sb_info *sbi = EXT4_SB(sb);
int new_order;
- if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+ if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0)
return;
new_order = mb_avg_fragment_size_order(sb,
@@ -1232,6 +1233,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
atomic64_add(period, &sbi->s_mb_generation_time);
}
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+ int count;
+ int order = 1;
+ void *buddy;
+
+ while ((buddy = mb_find_buddy(e4b, order++, &count)))
+ mb_set_bits(buddy, 0, count);
+
+ e4b->bd_info->bb_fragments = 0;
+ memset(e4b->bd_info->bb_counters, 0,
+ sizeof(*e4b->bd_info->bb_counters) *
+ (e4b->bd_sb->s_blocksize_bits + 2));
+
+ ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+ e4b->bd_bitmap, e4b->bd_group, e4b->bd_info);
+}
+
/* The buddy information is attached the buddy cache inode
* for convenience. The information regarding each group
* is loaded via ext4_mb_load_buddy. The information involve
@@ -1891,11 +1910,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
mb_check_buddy(e4b);
mb_free_blocks_double(inode, e4b, first, count);
- this_cpu_inc(discard_pa_seq);
- e4b->bd_info->bb_free += count;
- if (first < e4b->bd_info->bb_first_free)
- e4b->bd_info->bb_first_free = first;
-
/* access memory sequentially: check left neighbour,
* clear range and then check right neighbour
*/
@@ -1909,21 +1923,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t blocknr;
+ /*
+ * Fastcommit replay can free already freed blocks which
+ * corrupts allocation info. Regenerate it.
+ */
+ if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+ mb_regenerate_buddy(e4b);
+ goto check;
+ }
+
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += EXT4_C2B(sbi, block);
- if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
- ext4_grp_locked_error(sb, e4b->bd_group,
- inode ? inode->i_ino : 0,
- blocknr,
- "freeing already freed block (bit %u); block bitmap corrupt.",
- block);
- ext4_mark_group_bitmap_corrupted(
- sb, e4b->bd_group,
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ inode ? inode->i_ino : 0, blocknr,
+ "freeing already freed block (bit %u); block bitmap corrupt.",
+ block);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
- }
- goto done;
+ return;
}
+ this_cpu_inc(discard_pa_seq);
+ e4b->bd_info->bb_free += count;
+ if (first < e4b->bd_info->bb_first_free)
+ e4b->bd_info->bb_first_free = first;
+
/* let's maintain fragments counter */
if (left_is_free && right_is_free)
e4b->bd_info->bb_fragments--;
@@ -1948,9 +1972,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
if (first <= last)
mb_buddy_mark_free(e4b, first >> 1, last >> 1);
-done:
mb_set_largest_free_order(sb, e4b->bd_info);
mb_update_avg_fragment_size(sb, e4b->bd_info);
+check:
mb_check_buddy(e4b);
}
@@ -2281,6 +2305,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
return;
ext4_lock_group(ac->ac_sb, group);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ goto out;
+
max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
if (max > 0) {
@@ -2288,6 +2315,7 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
ext4_mb_use_best_found(ac, e4b);
}
+out:
ext4_unlock_group(ac->ac_sb, group);
ext4_mb_unload_buddy(e4b);
}
@@ -2314,12 +2342,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
if (err)
return err;
- if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
- ext4_mb_unload_buddy(e4b);
- return 0;
- }
-
ext4_lock_group(ac->ac_sb, group);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ goto out;
+
max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
ac->ac_g_ex.fe_len, &ex);
ex.fe_logical = 0xDEADFA11; /* debug value */
@@ -2352,6 +2378,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
ac->ac_b_ex = ex;
ext4_mb_use_best_found(ac, e4b);
}
+out:
ext4_unlock_group(ac->ac_sb, group);
ext4_mb_unload_buddy(e4b);
@@ -3629,7 +3656,8 @@ int ext4_mb_init(struct super_block *sb)
spin_lock_init(&sbi->s_md_lock);
sbi->s_mb_free_pending = 0;
- INIT_LIST_HEAD(&sbi->s_freed_data_list);
+ INIT_LIST_HEAD(&sbi->s_freed_data_list[0]);
+ INIT_LIST_HEAD(&sbi->s_freed_data_list[1]);
INIT_LIST_HEAD(&sbi->s_discard_list);
INIT_WORK(&sbi->s_discard_work, ext4_discard_work);
atomic_set(&sbi->s_retry_alloc_pending, 0);
@@ -3881,19 +3909,10 @@ void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid)
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_free_data *entry, *tmp;
LIST_HEAD(freed_data_list);
- struct list_head *cut_pos = NULL;
+ struct list_head *s_freed_head = &sbi->s_freed_data_list[commit_tid & 1];
bool wake;
- spin_lock(&sbi->s_md_lock);
- list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) {
- if (entry->efd_tid != commit_tid)
- break;
- cut_pos = &entry->efd_list;
- }
- if (cut_pos)
- list_cut_position(&freed_data_list, &sbi->s_freed_data_list,
- cut_pos);
- spin_unlock(&sbi->s_md_lock);
+ list_replace_init(s_freed_head, &freed_data_list);
list_for_each_entry(entry, &freed_data_list, efd_list)
ext4_free_data_in_buddy(sb, entry);
@@ -3951,6 +3970,111 @@ void ext4_exit_mballoc(void)
ext4_groupinfo_destroy_slabs();
}
+#define EXT4_MB_BITMAP_MARKED_CHECK 0x0001
+#define EXT4_MB_SYNC_UPDATE 0x0002
+static int
+ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state,
+ ext4_group_t group, ext4_grpblk_t blkoff,
+ ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct buffer_head *bitmap_bh = NULL;
+ struct ext4_group_desc *gdp;
+ struct buffer_head *gdp_bh;
+ int err;
+ unsigned int i, already, changed = len;
+
+ KUNIT_STATIC_STUB_REDIRECT(ext4_mb_mark_context,
+ handle, sb, state, group, blkoff, len,
+ flags, ret_changed);
+
+ if (ret_changed)
+ *ret_changed = 0;
+ bitmap_bh = ext4_read_block_bitmap(sb, group);
+ if (IS_ERR(bitmap_bh))
+ return PTR_ERR(bitmap_bh);
+
+ if (handle) {
+ BUFFER_TRACE(bitmap_bh, "getting write access");
+ err = ext4_journal_get_write_access(handle, sb, bitmap_bh,
+ EXT4_JTR_NONE);
+ if (err)
+ goto out_err;
+ }
+
+ err = -EIO;
+ gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+ if (!gdp)
+ goto out_err;
+
+ if (handle) {
+ BUFFER_TRACE(gdp_bh, "get_write_access");
+ err = ext4_journal_get_write_access(handle, sb, gdp_bh,
+ EXT4_JTR_NONE);
+ if (err)
+ goto out_err;
+ }
+
+ ext4_lock_group(sb, group);
+ 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 (flags & EXT4_MB_BITMAP_MARKED_CHECK) {
+ already = 0;
+ for (i = 0; i < len; i++)
+ if (mb_test_bit(blkoff + i, bitmap_bh->b_data) ==
+ state)
+ already++;
+ changed = len - already;
+ }
+
+ if (state) {
+ mb_set_bits(bitmap_bh->b_data, blkoff, len);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_group_clusters(sb, gdp) - changed);
+ } else {
+ mb_clear_bits(bitmap_bh->b_data, blkoff, len);
+ ext4_free_group_clusters_set(sb, gdp,
+ ext4_free_group_clusters(sb, gdp) + changed);
+ }
+
+ ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
+ ext4_group_desc_csum_set(sb, group, gdp);
+ ext4_unlock_group(sb, group);
+ if (ret_changed)
+ *ret_changed = changed;
+
+ 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(changed, &fg->free_clusters);
+ else
+ atomic64_add(changed, &fg->free_clusters);
+ }
+
+ err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
+ if (err)
+ goto out_err;
+ err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
+ if (err)
+ goto out_err;
+
+ if (flags & EXT4_MB_SYNC_UPDATE) {
+ sync_dirty_buffer(bitmap_bh);
+ sync_dirty_buffer(gdp_bh);
+ }
+
+out_err:
+ brelse(bitmap_bh);
+ return err;
+}
/*
* Check quota and mark chosen space (ac->ac_b_ex) non-free in bitmaps
@@ -3960,13 +4084,13 @@ static noinline_for_stack int
ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
handle_t *handle, unsigned int reserv_clstrs)
{
- struct buffer_head *bitmap_bh = NULL;
struct ext4_group_desc *gdp;
- struct buffer_head *gdp_bh;
struct ext4_sb_info *sbi;
struct super_block *sb;
ext4_fsblk_t block;
int err, len;
+ int flags = 0;
+ ext4_grpblk_t changed;
BUG_ON(ac->ac_status != AC_STATUS_FOUND);
BUG_ON(ac->ac_b_ex.fe_len <= 0);
@@ -3974,32 +4098,13 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
sb = ac->ac_sb;
sbi = EXT4_SB(sb);
- bitmap_bh = ext4_read_block_bitmap(sb, ac->ac_b_ex.fe_group);
- if (IS_ERR(bitmap_bh)) {
- return PTR_ERR(bitmap_bh);
- }
-
- BUFFER_TRACE(bitmap_bh, "getting write access");
- err = ext4_journal_get_write_access(handle, sb, bitmap_bh,
- EXT4_JTR_NONE);
- if (err)
- goto out_err;
-
- err = -EIO;
- gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, &gdp_bh);
+ gdp = ext4_get_group_desc(sb, ac->ac_b_ex.fe_group, NULL);
if (!gdp)
- goto out_err;
-
+ return -EIO;
ext4_debug("using block group %u(%d)\n", ac->ac_b_ex.fe_group,
ext4_free_group_clusters(sb, gdp));
- BUFFER_TRACE(gdp_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, sb, gdp_bh, EXT4_JTR_NONE);
- if (err)
- goto out_err;
-
block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex);
-
len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len);
if (!ext4_inode_block_valid(ac->ac_inode, block, len)) {
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
@@ -4008,41 +4113,29 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
* Fix the bitmap and return EFSCORRUPTED
* We leak some of the blocks here.
*/
- ext4_lock_group(sb, ac->ac_b_ex.fe_group);
- 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);
+ err = ext4_mb_mark_context(handle, sb, true,
+ ac->ac_b_ex.fe_group,
+ ac->ac_b_ex.fe_start,
+ ac->ac_b_ex.fe_len,
+ 0, NULL);
if (!err)
err = -EFSCORRUPTED;
- goto out_err;
+ return err;
}
- ext4_lock_group(sb, ac->ac_b_ex.fe_group);
#ifdef AGGRESSIVE_CHECK
- {
- int i;
- for (i = 0; i < ac->ac_b_ex.fe_len; i++) {
- BUG_ON(mb_test_bit(ac->ac_b_ex.fe_start + i,
- bitmap_bh->b_data));
- }
- }
+ flags |= EXT4_MB_BITMAP_MARKED_CHECK;
#endif
- 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))) {
- gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
- ext4_free_group_clusters_set(sb, gdp,
- ext4_free_clusters_after_init(sb,
- ac->ac_b_ex.fe_group, gdp));
- }
- len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len;
- ext4_free_group_clusters_set(sb, gdp, len);
- ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
- ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp);
+ err = ext4_mb_mark_context(handle, sb, true, ac->ac_b_ex.fe_group,
+ ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len,
+ flags, &changed);
+
+ if (err && changed == 0)
+ return err;
- ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
+#ifdef AGGRESSIVE_CHECK
+ BUG_ON(changed != ac->ac_b_ex.fe_len);
+#endif
percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len);
/*
* Now reduce the dirty block count also. Should not go negative
@@ -4052,21 +4145,6 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
percpu_counter_sub(&sbi->s_dirtyclusters_counter,
reserv_clstrs);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t flex_group = ext4_flex_group(sbi,
- ac->ac_b_ex.fe_group);
- atomic64_sub(ac->ac_b_ex.fe_len,
- &sbi_array_rcu_deref(sbi, s_flex_groups,
- flex_group)->free_clusters);
- }
-
- err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
- if (err)
- goto out_err;
- err = ext4_handle_dirty_metadata(handle, NULL, gdp_bh);
-
-out_err:
- brelse(bitmap_bh);
return err;
}
@@ -4075,17 +4153,13 @@ out_err:
* blocks in bitmaps and update counters.
*/
void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
- int len, int state)
+ int len, bool state)
{
- struct buffer_head *bitmap_bh = NULL;
- struct ext4_group_desc *gdp;
- struct buffer_head *gdp_bh;
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i, err = 0;
- int already;
- unsigned int clen, clen_changed, thisgrp_len;
+ int err = 0;
+ unsigned int clen, thisgrp_len;
while (len > 0) {
ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
@@ -4106,80 +4180,21 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
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);
- bitmap_bh = NULL;
- break;
- }
-
- err = -EIO;
- gdp = ext4_get_group_desc(sb, group, &gdp_bh);
- if (!gdp)
- break;
-
- 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)
- mb_set_bits(bitmap_bh->b_data, blkoff, clen);
- else
- 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);
- 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, 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);
- if (err)
- break;
- sync_dirty_buffer(bitmap_bh);
- err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
- sync_dirty_buffer(gdp_bh);
+ err = ext4_mb_mark_context(NULL, sb, state,
+ group, blkoff, clen,
+ EXT4_MB_BITMAP_MARKED_CHECK |
+ EXT4_MB_SYNC_UPDATE,
+ NULL);
if (err)
break;
block += thisgrp_len;
len -= thisgrp_len;
- brelse(bitmap_bh);
BUG_ON(len < 0);
}
-
- if (err)
- brelse(bitmap_bh);
}
/*
@@ -6107,7 +6122,7 @@ ext4_mb_new_blocks_simple(struct ext4_allocation_request *ar, int *errp)
}
block = ext4_group_first_block_no(sb, group) + EXT4_C2B(sbi, i);
- ext4_mb_mark_bb(sb, block, 1, 1);
+ ext4_mb_mark_bb(sb, block, 1, true);
ar->len = 1;
return block;
@@ -6355,7 +6370,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
}
spin_lock(&sbi->s_md_lock);
- list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list);
+ list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]);
sbi->s_mb_free_pending += clusters;
spin_unlock(&sbi->s_md_lock);
}
@@ -6363,43 +6378,15 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
unsigned long count)
{
- struct buffer_head *bitmap_bh;
struct super_block *sb = inode->i_sb;
- struct ext4_group_desc *gdp;
- struct buffer_head *gdp_bh;
ext4_group_t group;
ext4_grpblk_t blkoff;
- int already_freed = 0, err, i;
ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
- bitmap_bh = ext4_read_block_bitmap(sb, group);
- if (IS_ERR(bitmap_bh)) {
- pr_warn("Failed to read block bitmap\n");
- return;
- }
- gdp = ext4_get_group_desc(sb, group, &gdp_bh);
- if (!gdp)
- goto err_out;
-
- for (i = 0; i < count; i++) {
- if (!mb_test_bit(blkoff + i, bitmap_bh->b_data))
- already_freed++;
- }
- mb_clear_bits(bitmap_bh->b_data, blkoff, count);
- err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
- if (err)
- goto err_out;
- ext4_free_group_clusters_set(
- sb, gdp, ext4_free_group_clusters(sb, gdp) +
- count - already_freed);
- ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
- ext4_group_desc_csum_set(sb, group, gdp);
- ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
- sync_dirty_buffer(bitmap_bh);
- sync_dirty_buffer(gdp_bh);
-
-err_out:
- brelse(bitmap_bh);
+ ext4_mb_mark_context(NULL, sb, false, group, blkoff, count,
+ EXT4_MB_BITMAP_MARKED_CHECK |
+ EXT4_MB_SYNC_UPDATE,
+ NULL);
}
/**
@@ -6415,19 +6402,17 @@ 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;
- struct ext4_group_desc *gdp;
struct ext4_group_info *grp;
unsigned int overflow;
ext4_grpblk_t bit;
- struct buffer_head *gd_bh;
ext4_group_t block_group;
struct ext4_sb_info *sbi;
struct ext4_buddy e4b;
unsigned int count_clusters;
int err = 0;
- int ret;
+ int mark_flags = 0;
+ ext4_grpblk_t changed;
sbi = EXT4_SB(sb);
@@ -6436,7 +6421,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
ext4_error(sb, "Freeing blocks in system zone - "
"Block = %llu, count = %lu", block, count);
/* err = 0. ext4_std_error should be a no op */
- goto error_return;
+ goto error_out;
}
flags |= EXT4_FREE_BLOCKS_VALIDATED;
@@ -6460,55 +6445,35 @@ do_more:
flags &= ~EXT4_FREE_BLOCKS_VALIDATED;
}
count_clusters = EXT4_NUM_B2C(sbi, count);
- bitmap_bh = ext4_read_block_bitmap(sb, block_group);
- if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- bitmap_bh = NULL;
- goto error_return;
- }
- gdp = ext4_get_group_desc(sb, block_group, &gd_bh);
- if (!gdp) {
- err = -EIO;
- goto error_return;
- }
+ trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
+
+ /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
+ err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
+ GFP_NOFS|__GFP_NOFAIL);
+ if (err)
+ goto error_out;
if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
!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 */
- goto error_return;
+ goto error_clean;
}
- BUFFER_TRACE(bitmap_bh, "getting write access");
- err = ext4_journal_get_write_access(handle, sb, bitmap_bh,
- EXT4_JTR_NONE);
- if (err)
- goto error_return;
-
- /*
- * We are about to modify some metadata. Call the journal APIs
- * to unshare ->b_data if a currently-committing transaction is
- * using it
- */
- BUFFER_TRACE(gd_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, sb, gd_bh, EXT4_JTR_NONE);
- if (err)
- goto error_return;
#ifdef AGGRESSIVE_CHECK
- {
- int i;
- for (i = 0; i < count_clusters; i++)
- BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
- }
+ mark_flags |= EXT4_MB_BITMAP_MARKED_CHECK;
#endif
- trace_ext4_mballoc_free(sb, inode, block_group, bit, count_clusters);
+ err = ext4_mb_mark_context(handle, sb, false, block_group, bit,
+ count_clusters, mark_flags, &changed);
- /* __GFP_NOFAIL: retry infinitely, ignore TIF_MEMDIE and memcg limit. */
- err = ext4_mb_load_buddy_gfp(sb, block_group, &e4b,
- GFP_NOFS|__GFP_NOFAIL);
- if (err)
- goto error_return;
+
+ if (err && changed == 0)
+ goto error_clean;
+
+#ifdef AGGRESSIVE_CHECK
+ BUG_ON(changed != count_clusters);
+#endif
/*
* We need to make sure we don't reuse the freed block until after the
@@ -6532,13 +6497,8 @@ do_more:
new_entry->efd_tid = handle->h_transaction->t_tid;
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
ext4_mb_free_metadata(handle, &e4b, new_entry);
} else {
- /* need to update group_info->bb_free and bitmap
- * with group lock held. generate_buddy look at
- * them with group lock_held
- */
if (test_opt(sb, DISCARD)) {
err = ext4_issue_discard(sb, block_group, bit,
count_clusters, NULL);
@@ -6551,23 +6511,11 @@ do_more:
EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
mb_free_blocks(inode, &e4b, bit, count_clusters);
}
- ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
- ext4_free_group_clusters_set(sb, gdp, ret);
- ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
- ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic64_add(count_clusters,
- &sbi_array_rcu_deref(sbi, s_flex_groups,
- flex_group)->free_clusters);
- }
-
/*
* on a bigalloc file system, defer the s_freeclusters_counter
* update to the caller (ext4_remove_space and friends) so they
@@ -6580,28 +6528,18 @@ do_more:
count_clusters);
}
- ext4_mb_unload_buddy(&e4b);
-
- /* We dirtied the bitmap block */
- BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
- err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
-
- /* And the group descriptor block */
- BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
- ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
- if (!err)
- err = ret;
-
if (overflow && !err) {
block += count;
count = overflow;
- put_bh(bitmap_bh);
+ ext4_mb_unload_buddy(&e4b);
/* The range changed so it's no longer validated */
flags &= ~EXT4_FREE_BLOCKS_VALIDATED;
goto do_more;
}
-error_return:
- brelse(bitmap_bh);
+
+error_clean:
+ ext4_mb_unload_buddy(&e4b);
+error_out:
ext4_std_error(sb, err);
}
@@ -6719,23 +6657,19 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count)
{
- struct buffer_head *bitmap_bh = NULL;
- struct buffer_head *gd_bh;
ext4_group_t block_group;
ext4_grpblk_t bit;
- unsigned int i;
- struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_buddy e4b;
- int err = 0, ret, free_clusters_count;
- ext4_grpblk_t clusters_freed;
+ int err = 0;
ext4_fsblk_t first_cluster = EXT4_B2C(sbi, block);
ext4_fsblk_t last_cluster = EXT4_B2C(sbi, block + count - 1);
unsigned long cluster_count = last_cluster - first_cluster + 1;
+ ext4_grpblk_t changed;
ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
- if (count == 0)
+ if (cluster_count == 0)
return 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
@@ -6747,99 +6681,39 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
ext4_warning(sb, "too many blocks added to group %u",
block_group);
err = -EINVAL;
- goto error_return;
+ goto error_out;
}
- bitmap_bh = ext4_read_block_bitmap(sb, block_group);
- if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- bitmap_bh = NULL;
- goto error_return;
- }
-
- desc = ext4_get_group_desc(sb, block_group, &gd_bh);
- if (!desc) {
- err = -EIO;
- goto error_return;
- }
+ err = ext4_mb_load_buddy(sb, block_group, &e4b);
+ if (err)
+ goto error_out;
if (!ext4_sb_block_valid(sb, NULL, block, count)) {
ext4_error(sb, "Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
err = -EINVAL;
- goto error_return;
+ goto error_clean;
}
- BUFFER_TRACE(bitmap_bh, "getting write access");
- err = ext4_journal_get_write_access(handle, sb, bitmap_bh,
- EXT4_JTR_NONE);
- if (err)
- goto error_return;
-
- /*
- * We are about to modify some metadata. Call the journal APIs
- * to unshare ->b_data if a currently-committing transaction is
- * using it
- */
- BUFFER_TRACE(gd_bh, "get_write_access");
- err = ext4_journal_get_write_access(handle, sb, gd_bh, EXT4_JTR_NONE);
- if (err)
- goto error_return;
-
- for (i = 0, clusters_freed = 0; i < cluster_count; i++) {
- BUFFER_TRACE(bitmap_bh, "clear bit");
- if (!mb_test_bit(bit + i, bitmap_bh->b_data)) {
- ext4_error(sb, "bit already cleared for block %llu",
- (ext4_fsblk_t)(block + i));
- BUFFER_TRACE(bitmap_bh, "bit already cleared");
- } else {
- clusters_freed++;
- }
- }
+ err = ext4_mb_mark_context(handle, sb, false, block_group, bit,
+ cluster_count, EXT4_MB_BITMAP_MARKED_CHECK,
+ &changed);
+ if (err && changed == 0)
+ goto error_clean;
- err = ext4_mb_load_buddy(sb, block_group, &e4b);
- if (err)
- goto error_return;
+ if (changed != cluster_count)
+ ext4_error(sb, "bit already cleared in group %u", block_group);
- /*
- * need to update group_info->bb_free and bitmap
- * with group lock held. generate_buddy look at
- * them with group lock_held
- */
ext4_lock_group(sb, block_group);
- mb_clear_bits(bitmap_bh->b_data, bit, cluster_count);
mb_free_blocks(NULL, &e4b, bit, cluster_count);
- free_clusters_count = clusters_freed +
- ext4_free_group_clusters(sb, desc);
- ext4_free_group_clusters_set(sb, desc, free_clusters_count);
- ext4_block_bitmap_csum_set(sb, desc, bitmap_bh);
- ext4_group_desc_csum_set(sb, block_group, desc);
ext4_unlock_group(sb, block_group);
percpu_counter_add(&sbi->s_freeclusters_counter,
- clusters_freed);
-
- if (sbi->s_log_groups_per_flex) {
- ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
- atomic64_add(clusters_freed,
- &sbi_array_rcu_deref(sbi, s_flex_groups,
- flex_group)->free_clusters);
- }
+ changed);
+error_clean:
ext4_mb_unload_buddy(&e4b);
-
- /* We dirtied the bitmap block */
- BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
- err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
-
- /* And the group descriptor block */
- BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
- ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
- if (!err)
- err = ret;
-
-error_return:
- brelse(bitmap_bh);
+error_out:
ext4_std_error(sb, err);
return err;
}
@@ -6910,13 +6784,15 @@ static int ext4_try_to_trim_range(struct super_block *sb,
__acquires(ext4_group_lock_ptr(sb, e4b->bd_group))
__releases(ext4_group_lock_ptr(sb, e4b->bd_group))
{
- ext4_grpblk_t next, count, free_count;
+ ext4_grpblk_t next, count, free_count, last, origin_start;
bool set_trimmed = false;
void *bitmap;
+ last = ext4_last_grp_cluster(sb, e4b->bd_group);
bitmap = e4b->bd_bitmap;
- if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group))
+ if (start == 0 && max >= last)
set_trimmed = true;
+ origin_start = start;
start = max(e4b->bd_info->bb_first_free, start);
count = 0;
free_count = 0;
@@ -6925,7 +6801,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
start = mb_find_next_zero_bit(bitmap, max + 1, start);
if (start > max)
break;
- next = mb_find_next_bit(bitmap, max + 1, start);
+
+ next = mb_find_next_bit(bitmap, last + 1, start);
+ if (origin_start == 0 && next >= last)
+ set_trimmed = true;
if ((next - start) >= minblocks) {
int ret = ext4_trim_extent(sb, start, next - start, e4b);
@@ -7152,3 +7031,7 @@ out_unload:
return error;
}
+
+#ifdef CONFIG_EXT4_KUNIT_TESTS
+#include "mballoc-test.c"
+#endif