[PATCH v3 8/8] ext4: Convert group-count barrier protocol to acquire/release

[Jinjie Ruan <ruanjinjie@huawei.com>]

During an online resize, reading s_groups_count and s_blockfile_groups
requires strict ordering against subsequent initialized block group
metadata.

Replace the historical smp_wmb()/smp_rmb() pairs with smp_store_release()
and smp_load_acquire(). This formalizes the publish-subscribe pattern
and allows weakly-ordered architectures (e.g., arm64) to utilize native
STLR/LDAR instructions instead of full DMB fences.

Update the documentation in resize.c and ext4.h accordingly.

Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Baokun Li <libaokun@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Cc: "Ritesh Harjani (IBM)" <ritesh.list@gmail.com>
Cc: Zhang Yi <yi.zhang@huawei.com>
Assisted-by: Gemini:Gemini-3.1
Assisted-by: DeepSeek:DeepSeek-V3
Reviewed-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
---
 fs/ext4/ext4.h    | 10 +++-------
 fs/ext4/mballoc.c |  6 ++----
 fs/ext4/resize.c  | 19 +++++++++++--------
 3 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 724a27e8be61..d70b9cb09155 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3542,16 +3542,12 @@ static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
 }
 
 /*
- * Reading s_groups_count requires using smp_rmb() afterwards.  See
- * the locking protocol documented in the comments of ext4_group_add()
- * in resize.c
+ * Reading s_groups_count uses acquire semantics.
  */
 static inline ext4_group_t ext4_get_groups_count(struct super_block *sb)
 {
-	ext4_group_t	ngroups = EXT4_SB(sb)->s_groups_count;
-
-	smp_rmb();
-	return ngroups;
+	/* Pairs with smp_store_release() in ext4_update_super() */
+	return smp_load_acquire(&EXT4_SB(sb)->s_groups_count);
 }
 
 static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 06171a11db12..a15285224cdf 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -899,10 +899,8 @@ static ext4_group_t ext4_get_allocation_groups_count(
 
 	/* non-extent files are limited to low blocks/groups */
 	if (!(ext4_test_inode_flag(ac->ac_inode, EXT4_INODE_EXTENTS)))
-		ngroups = EXT4_SB(ac->ac_sb)->s_blockfile_groups;
-
-	/* Pairs with smp_wmb() in ext4_update_super() */
-	smp_rmb();
+		/* Pairs with smp_store_release() in ext4_update_super() */
+		ngroups = smp_load_acquire(&EXT4_SB(ac->ac_sb)->s_blockfile_groups);
 
 	return ngroups;
 }
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 2c5b851c552a..5e3ad8393cf8 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1462,11 +1462,11 @@ static void ext4_update_super(struct super_block *sb,
 	 *
 	 * The precise rules we use are:
 	 *
-	 * * Writers must perform a smp_wmb() after updating all
-	 *   dependent data and before modifying the groups count
+	 * * Writers must use a release store when updating the groups count
+	 *   after all dependent data has been updated
 	 *
-	 * * Readers must perform an smp_rmb() after reading the groups
-	 *   count and before reading any dependent data.
+	 * * Readers must use an acquire load when reading the groups
+	 *   count before reading any dependent data.
 	 *
 	 * NB. These rules can be relaxed when checking the group count
 	 * while freeing data, as we can only allocate from a block
@@ -1474,12 +1474,15 @@ static void ext4_update_super(struct super_block *sb,
 	 * only then free after serialising in turn against that
 	 * allocation.
 	 */
-	smp_wmb();
 
 	/* Update the global fs size fields */
-	sbi->s_groups_count += flex_gd->count;
-	sbi->s_blockfile_groups = min(sbi->s_groups_count,
-			(EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb)));
+	/* Pairs with smp_load_acquire() in ext4_get_groups_count() */
+	smp_store_release(&sbi->s_groups_count,
+			  sbi->s_groups_count + flex_gd->count);
+	/* Pairs with smp_load_acquire() in ext4_get_allocation_groups_count() */
+	smp_store_release(&sbi->s_blockfile_groups,
+			  min(sbi->s_groups_count,
+			      (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))));
 
 	/* Update the reserved block counts only once the new group is
 	 * active. */
-- 
2.34.1