mainline inclusion from mainline-v6.17-rc1 commit 0a2326f6ae60e99f5e6e9ca900a19b5c14304a51 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICN2MB Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Previously, s_md_lock was used to protect s_mb_free_pending during modifications, while smp_mb() ensured fresh reads, so s_md_lock just guarantees the atomicity of s_mb_free_pending. Thus we optimized it by converting s_mb_free_pending into an atomic variable, thereby eliminating s_md_lock and minimizing lock contention. This also prepares for future lockless merging of free extents. Following this modification, s_md_lock is exclusively responsible for managing insertions and deletions within s_freed_data_list, along with operations involving list_splice. Performance test data follows: Test: Running will-it-scale/fallocate2 on CPU-bound containers. Observation: Average fallocate operations per container per second. |CPU: Kunpeng 920 | P80 | P1 | |Memory: 512GB |------------------------|-------------------------| |960GB SSD (0.5GB/s)| base | patched | base | patched | |-------------------|-------|----------------|--------|----------------| |mb_optimize_scan=0 | 19628 | 20043 (+2.1%) | 320885 | 314331 (-2.0%) | |mb_optimize_scan=1 | 7129 | 7290 (+2.2%) | 321275 | 324226 (+0.9%) | |CPU: AMD 9654 * 2 | P96 | P1 | |Memory: 1536GB |------------------------|-------------------------| |960GB SSD (1GB/s) | base | patched | base | patched | |-------------------|-------|----------------|--------|----------------| |mb_optimize_scan=0 | 53760 | 54999 (+2.3%) | 213145 | 214380 (+0.5%) | |mb_optimize_scan=1 | 12716 | 13497 (+6.1%) | 215262 | 216276 (+0.4%) | Signed-off-by: Baokun Li <libaokun1@huawei.com> Reviewed-by: Jan Kara <jack@suse.cz> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Link: https://patch.msgid.link/20250714130327.1830534-9-libaokun1@huawei.com Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Baokun Li <libaokun1@huawei.com> --- fs/ext4/balloc.c | 2 +- fs/ext4/ext4.h | 2 +- fs/ext4/mballoc.c | 9 +++------ 3 files changed, 5 insertions(+), 8 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 396474e9e2bf..7e70176e0eae 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -695,7 +695,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries) * possible we just missed a transaction commit that did so */ smp_mb(); - if (sbi->s_mb_free_pending == 0) { + if (atomic_read(&sbi->s_mb_free_pending) == 0) { if (test_opt(sb, DISCARD)) { atomic_inc(&sbi->s_retry_alloc_pending); flush_work(&sbi->s_discard_work); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index ee57bbc9bca5..07e240231fe0 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1584,7 +1584,7 @@ struct ext4_sb_info { unsigned short *s_mb_offsets; unsigned int *s_mb_maxs; unsigned int s_group_info_size; - unsigned int s_mb_free_pending; + atomic_t s_mb_free_pending; struct list_head s_freed_data_list[2]; /* List of blocks to be freed after commit completed */ struct list_head s_discard_list; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 82b3d539be7f..ab05e047c553 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3682,7 +3682,7 @@ int ext4_mb_init(struct super_block *sb) } spin_lock_init(&sbi->s_md_lock); - sbi->s_mb_free_pending = 0; + atomic_set(&sbi->s_mb_free_pending, 0); 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); @@ -3906,10 +3906,7 @@ static void ext4_free_data_in_buddy(struct super_block *sb, /* we expect to find existing buddy because it's pinned */ BUG_ON(err != 0); - spin_lock(&EXT4_SB(sb)->s_md_lock); - EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count; - spin_unlock(&EXT4_SB(sb)->s_md_lock); - + atomic_sub(entry->efd_count, &EXT4_SB(sb)->s_mb_free_pending); db = e4b.bd_info; /* there are blocks to put in buddy to make them really free */ count += entry->efd_count; @@ -6483,7 +6480,7 @@ 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[new_entry->efd_tid & 1]); - sbi->s_mb_free_pending += clusters; + atomic_add(clusters, &sbi->s_mb_free_pending); spin_unlock(&sbi->s_md_lock); } -- 2.46.1