ext4: convert sbi->s_mb_free_pending to atomic_t

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 <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Reviewed-by: Zhang Yi <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Theodore Ts'o <[email protected]>

Author: LiBaokun96

fs/ext4/balloc.c

@@ -703,7 +703,7 @@ 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);

fs/ext4/ext4.h

@@ -1602,7 +1602,7 @@ 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;

fs/ext4/mballoc.c

@@ -3687,7 +3687,7 @@ 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);
@@ -3903,10 +3903,7 @@ 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;
@@ -6401,7 +6398,7 @@ 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);
 }