From: Jan Kara <jack@suse.cz>
To: <linux-fsdevel@vger.kernel.org>
Cc: <linux-block@vger.kernel.org>,
Christian Brauner <brauner@kernel.org>,
Al Viro <viro@ZenIV.linux.org.uk>, <linux-ext4@vger.kernel.org>,
Ted Tso <tytso@mit.edu>,
"Tigran A. Aivazian" <aivazian.tigran@gmail.com>,
David Sterba <dsterba@suse.com>,
OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>,
Muchun Song <muchun.song@linux.dev>,
Oscar Salvador <osalvador@suse.de>,
David Hildenbrand <david@kernel.org>,
linux-mm@kvack.org, linux-aio@kvack.org,
Benjamin LaHaise <bcrl@kvack.org>, Jan Kara <jack@suse.cz>,
Christoph Hellwig <hch@lst.de>
Subject: [PATCH 31/42] fs: Make bhs point to mapping_metadata_bhs
Date: Thu, 26 Mar 2026 10:54:25 +0100 [thread overview]
Message-ID: <20260326095354.16340-73-jack@suse.cz> (raw)
In-Reply-To: <20260326082428.31660-1-jack@suse.cz>
Make buffer heads point to mapping_metadata_bhs instead of struct
address_space. This makes the code more self contained. For the (only)
case of IO error handling where we really need to reach struct
address_space add a pointer to the mapping from mapping_metadata_bhs.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
fs/buffer.c | 34 ++++++++++++++++------------------
fs/inode.c | 1 +
include/linux/buffer_head.h | 4 ++--
include/linux/fs.h | 1 +
4 files changed, 20 insertions(+), 20 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 294f9cd07f42..67b3d4624503 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -497,13 +497,12 @@ static void __remove_assoc_queue(struct mapping_metadata_bhs *mmb,
{
lockdep_assert_held(&mmb->lock);
list_del_init(&bh->b_assoc_buffers);
- WARN_ON(!bh->b_assoc_map);
- bh->b_assoc_map = NULL;
+ WARN_ON(!bh->b_mmb);
+ bh->b_mmb = NULL;
}
static void remove_assoc_queue(struct buffer_head *bh)
{
- struct address_space *mapping;
struct mapping_metadata_bhs *mmb;
/*
@@ -514,13 +513,12 @@ static void remove_assoc_queue(struct buffer_head *bh)
* opportunistically acquire the lock and then recheck the bh
* didn't move under us.
*/
- while (bh->b_assoc_map) {
+ while (bh->b_mmb) {
rcu_read_lock();
- mapping = READ_ONCE(bh->b_assoc_map);
- if (mapping) {
- mmb = &mapping->i_metadata_bhs;
+ mmb = READ_ONCE(bh->b_mmb);
+ if (mmb) {
spin_lock(&mmb->lock);
- if (bh->b_assoc_map == mapping)
+ if (bh->b_mmb == mmb)
__remove_assoc_queue(mmb, bh);
spin_unlock(&mmb->lock);
}
@@ -551,9 +549,9 @@ EXPORT_SYMBOL_GPL(inode_has_buffers);
* Do this in two main stages: first we copy dirty buffers to a
* temporary inode list, queueing the writes as we go. Then we clean
* up, waiting for those writes to complete. mark_buffer_dirty_inode()
- * doesn't touch b_assoc_buffers list if b_assoc_map is not NULL so we
- * are sure the buffer stays on our list until IO completes (at which point
- * it can be reaped).
+ * doesn't touch b_assoc_buffers list if b_mmb is not NULL so we are sure the
+ * buffer stays on our list until IO completes (at which point it can be
+ * reaped).
*/
int sync_mapping_buffers(struct address_space *mapping)
{
@@ -571,14 +569,14 @@ int sync_mapping_buffers(struct address_space *mapping)
spin_lock(&mmb->lock);
while (!list_empty(&mmb->list)) {
bh = BH_ENTRY(mmb->list.next);
- WARN_ON_ONCE(bh->b_assoc_map != mapping);
+ WARN_ON_ONCE(bh->b_mmb != mmb);
__remove_assoc_queue(mmb, bh);
/* Avoid race with mark_buffer_dirty_inode() which does
* a lockless check and we rely on seeing the dirty bit */
smp_mb();
if (buffer_dirty(bh) || buffer_locked(bh)) {
list_add(&bh->b_assoc_buffers, &tmp);
- bh->b_assoc_map = mapping;
+ bh->b_mmb = mmb;
if (buffer_dirty(bh)) {
get_bh(bh);
spin_unlock(&mmb->lock);
@@ -616,7 +614,7 @@ int sync_mapping_buffers(struct address_space *mapping)
smp_mb();
if (buffer_dirty(bh)) {
list_add(&bh->b_assoc_buffers, &mmb->list);
- bh->b_assoc_map = mapping;
+ bh->b_mmb = mmb;
}
spin_unlock(&mmb->lock);
wait_on_buffer(bh);
@@ -724,11 +722,11 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode)
struct address_space *mapping = inode->i_mapping;
mark_buffer_dirty(bh);
- if (!bh->b_assoc_map) {
+ if (!bh->b_mmb) {
spin_lock(&mapping->i_metadata_bhs.lock);
list_move_tail(&bh->b_assoc_buffers,
&mapping->i_metadata_bhs.list);
- bh->b_assoc_map = mapping;
+ bh->b_mmb = &mapping->i_metadata_bhs;
spin_unlock(&mapping->i_metadata_bhs.lock);
}
}
@@ -1124,8 +1122,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh)
/* FIXME: do we need to set this in both places? */
if (bh->b_folio && bh->b_folio->mapping)
mapping_set_error(bh->b_folio->mapping, -EIO);
- if (bh->b_assoc_map)
- mapping_set_error(bh->b_assoc_map, -EIO);
+ if (bh->b_mmb)
+ mapping_set_error(bh->b_mmb->mapping, -EIO);
}
EXPORT_SYMBOL(mark_buffer_write_io_error);
diff --git a/fs/inode.c b/fs/inode.c
index 393f586d050a..3874b933abdb 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -276,6 +276,7 @@ int inode_init_always_gfp(struct super_block *sb, struct inode *inode, gfp_t gfp
mapping->a_ops = &empty_aops;
mapping->host = inode;
+ mapping->i_metadata_bhs.mapping = mapping;
mapping->flags = 0;
mapping->wb_err = 0;
atomic_set(&mapping->i_mmap_writable, 0);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 631bf971efc0..20636599d858 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -73,8 +73,8 @@ struct buffer_head {
bh_end_io_t *b_end_io; /* I/O completion */
void *b_private; /* reserved for b_end_io */
struct list_head b_assoc_buffers; /* associated with another mapping */
- struct address_space *b_assoc_map; /* mapping this buffer is
- associated with */
+ struct mapping_metadata_bhs *b_mmb; /* head of the list of metadata bhs
+ * this buffer is associated with */
atomic_t b_count; /* users using this buffer_head */
spinlock_t b_uptodate_lock; /* Used by the first bh in a page, to
* serialise IO completion of other
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 76360b0040e0..fa2a812bd718 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -447,6 +447,7 @@ extern const struct address_space_operations empty_aops;
/* Structure for tracking metadata buffer heads associated with the mapping */
struct mapping_metadata_bhs {
+ struct address_space *mapping; /* Mapping bhs are associated with */
spinlock_t lock; /* Lock protecting bh list */
struct list_head list; /* The list of bhs (b_assoc_buffers) */
};
--
2.51.0
next prev parent reply other threads:[~2026-03-26 9:57 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-26 9:53 [PATCH v3 0/42] fs: Move metadata bh tracking from address_space Jan Kara
2026-03-26 9:53 ` [PATCH 01/42] ext4: Use inode_has_buffers() Jan Kara
2026-03-26 9:53 ` [PATCH 02/42] gfs2: Don't zero i_private_data Jan Kara
2026-03-26 9:53 ` [PATCH 03/42] ntfs3: Drop pointless sync_mapping_buffers() and invalidate_inode_buffers() calls Jan Kara
2026-03-26 9:53 ` [PATCH 04/42] ocfs2: Drop pointless sync_mapping_buffers() calls Jan Kara
2026-03-26 9:53 ` [PATCH 05/42] bdev: Drop pointless invalidate_inode_buffers() call Jan Kara
2026-03-26 9:54 ` [PATCH 06/42] ufs: Drop pointless invalidate_mapping_buffers() call Jan Kara
2026-03-26 9:54 ` [PATCH 07/42] exfat: Drop pointless invalidate_inode_buffers() call Jan Kara
2026-03-26 9:54 ` [PATCH 08/42] fs: Remove inode lock from __generic_file_fsync() Jan Kara
2026-03-26 9:54 ` [PATCH 09/42] udf: Switch to generic_buffers_fsync() Jan Kara
2026-03-26 9:54 ` [PATCH 10/42] minix: " Jan Kara
2026-03-26 9:54 ` [PATCH 11/42] bfs: " Jan Kara
2026-03-26 9:54 ` [PATCH 12/42] fat: Switch to generic_buffers_fsync_noflush() Jan Kara
2026-03-26 9:54 ` [PATCH 13/42] fs: Drop sync_mapping_buffers() from __generic_file_fsync() Jan Kara
2026-03-26 9:54 ` [PATCH 14/42] fs: Rename generic_file_fsync() to simple_fsync() Jan Kara
2026-03-26 9:54 ` [PATCH 15/42] fat: Sync and invalidate metadata buffers from fat_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 16/42] udf: Sync and invalidate metadata buffers from udf_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 17/42] minix: Sync and invalidate metadata buffers from minix_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 18/42] ext2: Sync and invalidate metadata buffers from ext2_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 19/42] ext4: Sync and invalidate metadata buffers from ext4_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 20/42] bfs: Sync and invalidate metadata buffers from bfs_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 21/42] affs: Sync and invalidate metadata buffers from affs_evict_inode() Jan Kara
2026-03-26 9:54 ` [PATCH 22/42] fs: Ignore inode metadata buffers in inode_lru_isolate() Jan Kara
2026-03-26 9:54 ` [PATCH 23/42] fs: Stop using i_private_data for metadata bh tracking Jan Kara
2026-03-26 9:54 ` [PATCH 24/42] hugetlbfs: Stop using i_private_data Jan Kara
2026-03-26 9:54 ` [PATCH 25/42] aio: Stop using i_private_data and i_private_lock Jan Kara
2026-03-26 9:54 ` [PATCH 26/42] fs: Remove i_private_data Jan Kara
2026-03-26 9:54 ` [PATCH 27/42] kvm: Use private inode list instead of i_private_list Jan Kara
2026-03-26 9:54 ` [PATCH 28/42] fs: Drop osync_buffers_list() Jan Kara
2026-03-26 9:54 ` [PATCH 29/42] fs: Fold fsync_buffers_list() into sync_mapping_buffers() Jan Kara
2026-03-26 9:54 ` [PATCH 30/42] fs: Move metadata bhs tracking to a separate struct Jan Kara
2026-03-26 9:54 ` Jan Kara [this message]
2026-03-26 9:54 ` [PATCH 32/42] fs: Switch inode_has_buffers() to take mapping_metadata_bhs Jan Kara
2026-03-26 9:54 ` [PATCH 33/42] fs: Provide functions for handling mapping_metadata_bhs directly Jan Kara
2026-03-26 9:54 ` [PATCH 34/42] ext2: Track metadata bhs in fs-private inode part Jan Kara
2026-03-26 9:54 ` [PATCH 35/42] affs: " Jan Kara
2026-03-26 9:54 ` [PATCH 36/42] bfs: " Jan Kara
2026-03-26 9:54 ` [PATCH 37/42] fat: " Jan Kara
2026-03-26 9:54 ` [PATCH 38/42] udf: " Jan Kara
2026-03-26 9:54 ` [PATCH 39/42] minix: " Jan Kara
2026-03-26 9:54 ` [PATCH 40/42] ext4: " Jan Kara
2026-03-26 9:54 ` [PATCH 41/42] fs: Drop mapping_metadata_bhs from address space Jan Kara
2026-03-26 9:54 ` [PATCH 42/42] fs: Drop i_private_list from address_space Jan Kara
2026-03-26 14:06 ` [PATCH v3 0/42] fs: Move metadata bh tracking " Christian Brauner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260326095354.16340-73-jack@suse.cz \
--to=jack@suse.cz \
--cc=aivazian.tigran@gmail.com \
--cc=bcrl@kvack.org \
--cc=brauner@kernel.org \
--cc=david@kernel.org \
--cc=dsterba@suse.com \
--cc=hch@lst.de \
--cc=hirofumi@mail.parknet.co.jp \
--cc=linux-aio@kvack.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=muchun.song@linux.dev \
--cc=osalvador@suse.de \
--cc=tytso@mit.edu \
--cc=viro@ZenIV.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox