projects/linux·commit fc825e51

Merge tag 'vfs-7.1-rc1.bh.metadata' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

fc825e51 · Linus Torvalds <[email protected]> · 2026-04-13 12:46:42 -07:00

Pull vfs buffer_head updates from Christian Brauner:
 "This cleans up the mess that has accumulated over the years in
  metadata buffer_head tracking for inodes.

  It moves the tracking into dedicated structure in filesystem-private
  part of the inode (so that we don't use private_list, private_data,
  and private_lock in struct address_space), and also moves couple other
  users of private_data and private_list so these are removed from
  struct address_space saving 3 longs in struct inode for 99% of inodes"

* tag 'vfs-7.1-rc1.bh.metadata' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (42 commits)
  fs: Drop i_private_list from address_space
  fs: Drop mapping_metadata_bhs from address space
  ext4: Track metadata bhs in fs-private inode part
  minix: Track metadata bhs in fs-private inode part
  udf: Track metadata bhs in fs-private inode part
  fat: Track metadata bhs in fs-private inode part
  bfs: Track metadata bhs in fs-private inode part
  affs: Track metadata bhs in fs-private inode part
  ext2: Track metadata bhs in fs-private inode part
  fs: Provide functions for handling mapping_metadata_bhs directly
  fs: Switch inode_has_buffers() to take mapping_metadata_bhs
  fs: Make bhs point to mapping_metadata_bhs
  fs: Move metadata bhs tracking to a separate struct
  fs: Fold fsync_buffers_list() into sync_mapping_buffers()
  fs: Drop osync_buffers_list()
  kvm: Use private inode list instead of i_private_list
  fs: Remove i_private_data
  aio: Stop using i_private_data and i_private_lock
  hugetlbfs: Stop using i_private_data
  fs: Stop using i_private_data for metadata bh tracking
  ...
Commit
fc825e513cd494cfcbeb47acf5738fe64f3a9051
Parents
2802f940 · 6e227269

Merge commit. Changes below are compared with the first parent: 2802f940.

Changes

65 files changed · +474 −492

FileStatusAddDelContent
block/bdev.cmodified+0−8View file
fs/adfs/dir.cmodified+1−1View file
fs/adfs/file.cmodified+1−1View file
fs/affs/affs.hmodified+2−0View file
fs/affs/amigaffs.cmodified+6−6View file
fs/affs/file.cmodified+14−11View file
fs/affs/inode.cmodified+8−6View file
fs/affs/namei.cmodified+5−4View file
fs/affs/super.cmodified+1−0View file
fs/aio.cmodified+66−12View file
fs/bfs/bfs.hmodified+1−0View file
fs/bfs/dir.cmodified+12−4View file
fs/bfs/inode.cmodified+5−1View file
fs/buffer.cmodified+173−281View file
fs/exfat/file.cmodified+1−1View file
fs/exfat/inode.cmodified+0−1View file
fs/ext2/ext2.hmodified+1−0View file
fs/ext2/file.cmodified+4−2View file
fs/ext2/inode.cmodified+10−7View file
fs/ext2/super.cmodified+1−0View file
fs/ext4/ext4.hmodified+1−0View file
fs/ext4/ext4_jbd2.cmodified+2−1View file
fs/ext4/fsync.cmodified+3−2View file
fs/ext4/inode.cmodified+4−5View file
fs/ext4/super.cmodified+3−1View file
fs/fat/dir.cmodified+10−7View file
fs/fat/fat.hmodified+1−0View file
fs/fat/fatent.cmodified+10−5View file
fs/fat/file.cmodified+5−3View file
fs/fat/inode.cmodified+5−2View file
fs/fat/namei_msdos.cmodified+4−2View file
fs/fat/namei_vfat.cmodified+1−1View file
fs/gfs2/glock.cmodified+0−1View file
fs/hugetlbfs/inode.cmodified+3−8View file
fs/inode.cmodified+9−15View file
fs/libfs.cmodified+14−23View file
fs/minix/dir.cmodified+1−1View file
fs/minix/file.cmodified+9−1View file
fs/minix/inode.cmodified+5−1View file
fs/minix/itree_common.cmodified+7−4View file
fs/minix/minix.hmodified+3−0View file
fs/ntfs3/file.cmodified+0−3View file
fs/ntfs3/inode.cmodified+0−1View file
fs/ocfs2/dlmglue.cmodified+0−1View file
fs/ocfs2/namei.cmodified+0−3View file
fs/omfs/file.cmodified+1−1View file
fs/qnx4/dir.cmodified+1−1View file
fs/qnx6/dir.cmodified+1−1View file
fs/udf/dir.cmodified+1−1View file
fs/udf/directory.cmodified+3−2View file
fs/udf/file.cmodified+8−1View file
fs/udf/inode.cmodified+9−7View file
fs/udf/namei.cmodified+1−1View file
fs/udf/super.cmodified+1−0View file
fs/udf/truncate.cmodified+1−1View file
fs/udf/udf_i.hmodified+1−0View file
fs/udf/udfdecl.hmodified+1−0View file
fs/ufs/dir.cmodified+1−1View file
fs/ufs/file.cmodified+1−1View file
fs/ufs/inode.cmodified+0−1View file
include/linux/buffer_head.hmodified+13−16View file
include/linux/fs.hmodified+9−6View file
include/linux/hugetlb.hmodified+1−0View file
mm/hugetlb.cmodified+1−9View file
virt/kvm/guest_memfd.cmodified+7−5View file

Only the first 600 diff lines are shown. Download the complete patch.

block/bdev.c

View file
diff --git a/block/bdev.c b/block/bdev.c
index ed022f8..bb0ffa3 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -417,19 +417,11 @@ static void init_once(void *data)
inode_init_once(&ei->vfs_inode);
}
-static void bdev_evict_inode(struct inode *inode)
-{
- truncate_inode_pages_final(&inode->i_data);
- invalidate_inode_buffers(inode); /* is it needed here? */
- clear_inode(inode);
-}
-
static const struct super_operations bdev_sops = {
.statfs = simple_statfs,
.alloc_inode = bdev_alloc_inode,
.free_inode = bdev_free_inode,
.drop_inode = inode_just_drop,
- .evict_inode = bdev_evict_inode,
};
static int bd_init_fs_context(struct fs_context *fc)

fs/adfs/dir.c

View file
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 493500f..b8e23e8 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -389,7 +389,7 @@ const struct file_operations adfs_dir_operations = {
.read = generic_read_dir,
.llseek = generic_file_llseek,
.iterate_shared = adfs_iterate,
- .fsync = generic_file_fsync,
+ .fsync = simple_fsync,
};
static int

fs/adfs/file.c

View file
diff --git a/fs/adfs/file.c b/fs/adfs/file.c
index cd13165..4a1828b 100644
--- a/fs/adfs/file.c
+++ b/fs/adfs/file.c
@@ -26,7 +26,7 @@ const struct file_operations adfs_file_operations = {
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.mmap_prepare = generic_file_mmap_prepare,
- .fsync = generic_file_fsync,
+ .fsync = simple_fsync,
.write_iter = generic_file_write_iter,
.splice_read = filemap_splice_read,
};

fs/affs/affs.h

View file
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index ac4e9a0..a1eb400 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -44,6 +44,7 @@ struct affs_inode_info {
struct mutex i_link_lock; /* Protects internal inode access. */
struct mutex i_ext_lock; /* Protects internal inode access. */
#define i_hash_lock i_ext_lock
+ struct mapping_metadata_bhs i_metadata_bhs;
u32 i_blkcnt; /* block count */
u32 i_extcnt; /* extended block count */
u32 *i_lc; /* linear cache of extended blocks */
@@ -151,6 +152,7 @@ extern bool affs_nofilenametruncate(const struct dentry *dentry);
extern int affs_check_name(const unsigned char *name, int len,
bool notruncate);
extern int affs_copy_name(unsigned char *bstr, struct dentry *dentry);
+struct mapping_metadata_bhs *affs_get_metadata_bhs(struct inode *inode);
/* bitmap. c */

fs/affs/amigaffs.c

View file
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index d8a96d8..ee512ba 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -57,7 +57,7 @@ affs_insert_hash(struct inode *dir, struct buffer_head *bh)
AFFS_TAIL(sb, dir_bh)->hash_chain = cpu_to_be32(ino);
affs_adjust_checksum(dir_bh, ino);
- mark_buffer_dirty_inode(dir_bh, dir);
+ mmb_mark_buffer_dirty(dir_bh, &AFFS_I(dir)->i_metadata_bhs);
affs_brelse(dir_bh);
inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
@@ -100,7 +100,7 @@ affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh)
else
AFFS_TAIL(sb, bh)->hash_chain = ino;
affs_adjust_checksum(bh, be32_to_cpu(ino) - hash_ino);
- mark_buffer_dirty_inode(bh, dir);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(dir)->i_metadata_bhs);
AFFS_TAIL(sb, rem_bh)->parent = 0;
retval = 0;
break;
@@ -180,7 +180,7 @@ affs_remove_link(struct dentry *dentry)
affs_unlock_dir(dir);
goto done;
}
- mark_buffer_dirty_inode(link_bh, inode);
+ mmb_mark_buffer_dirty(link_bh, &AFFS_I(inode)->i_metadata_bhs);
memcpy(AFFS_TAIL(sb, bh)->name, AFFS_TAIL(sb, link_bh)->name, 32);
retval = affs_insert_hash(dir, bh);
@@ -188,7 +188,7 @@ affs_remove_link(struct dentry *dentry)
affs_unlock_dir(dir);
goto done;
}
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
affs_unlock_dir(dir);
iput(dir);
@@ -203,7 +203,7 @@ affs_remove_link(struct dentry *dentry)
__be32 ino2 = AFFS_TAIL(sb, link_bh)->link_chain;
AFFS_TAIL(sb, bh)->link_chain = ino2;
affs_adjust_checksum(bh, be32_to_cpu(ino2) - link_ino);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
retval = 0;
/* Fix the link count, if bh is a normal header block without links */
switch (be32_to_cpu(AFFS_TAIL(sb, bh)->stype)) {
@@ -306,7 +306,7 @@ affs_remove_header(struct dentry *dentry)
retval = affs_remove_hash(dir, bh);
if (retval)
goto done_unlock;
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
affs_unlock_dir(dir);

fs/affs/file.c

View file
diff --git a/fs/affs/file.c b/fs/affs/file.c
index a51dee9..2e93491 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -140,14 +140,14 @@ affs_alloc_extblock(struct inode *inode, struct buffer_head *bh, u32 ext)
AFFS_TAIL(sb, new_bh)->parent = cpu_to_be32(inode->i_ino);
affs_fix_checksum(sb, new_bh);
- mark_buffer_dirty_inode(new_bh, inode);
+ mmb_mark_buffer_dirty(new_bh, &AFFS_I(inode)->i_metadata_bhs);
tmp = be32_to_cpu(AFFS_TAIL(sb, bh)->extension);
if (tmp)
affs_warning(sb, "alloc_ext", "previous extension set (%x)", tmp);
AFFS_TAIL(sb, bh)->extension = cpu_to_be32(blocknr);
affs_adjust_checksum(bh, blocknr - tmp);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
AFFS_I(inode)->i_extcnt++;
mark_inode_dirty(inode);
@@ -581,7 +581,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
memset(AFFS_DATA(bh) + boff, 0, tmp);
be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp);
affs_fix_checksum(sb, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
size += tmp;
bidx++;
} else if (bidx) {
@@ -603,7 +603,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
affs_fix_checksum(sb, bh);
bh->b_state &= ~(1UL << BH_New);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
if (prev_bh) {
u32 tmp_next = be32_to_cpu(AFFS_DATA_HEAD(prev_bh)->next);
@@ -613,7 +613,8 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
bidx, tmp_next);
AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
- mark_buffer_dirty_inode(prev_bh, inode);
+ mmb_mark_buffer_dirty(prev_bh,
+ &AFFS_I(inode)->i_metadata_bhs);
affs_brelse(prev_bh);
}
size += bsize;
@@ -732,7 +733,7 @@ static int affs_write_end_ofs(const struct kiocb *iocb,
AFFS_DATA_HEAD(bh)->size = cpu_to_be32(
max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size)));
affs_fix_checksum(sb, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
written += tmp;
from += tmp;
bidx++;
@@ -765,12 +766,13 @@ static int affs_write_end_ofs(const struct kiocb *iocb,
bidx, tmp_next);
AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
- mark_buffer_dirty_inode(prev_bh, inode);
+ mmb_mark_buffer_dirty(prev_bh,
+ &AFFS_I(inode)->i_metadata_bhs);
}
}
affs_brelse(prev_bh);
affs_fix_checksum(sb, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
written += bsize;
from += bsize;
bidx++;
@@ -799,13 +801,14 @@ static int affs_write_end_ofs(const struct kiocb *iocb,
bidx, tmp_next);
AFFS_DATA_HEAD(prev_bh)->next = cpu_to_be32(bh->b_blocknr);
affs_adjust_checksum(prev_bh, bh->b_blocknr - tmp_next);
- mark_buffer_dirty_inode(prev_bh, inode);
+ mmb_mark_buffer_dirty(prev_bh,
+ &AFFS_I(inode)->i_metadata_bhs);
}
} else if (be32_to_cpu(AFFS_DATA_HEAD(bh)->size) < tmp)
AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
affs_brelse(prev_bh);
affs_fix_checksum(sb, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
written += tmp;
from += tmp;
bidx++;
@@ -942,7 +945,7 @@ affs_truncate(struct inode *inode)
}
AFFS_TAIL(sb, ext_bh)->extension = 0;
affs_fix_checksum(sb, ext_bh);
- mark_buffer_dirty_inode(ext_bh, inode);
+ mmb_mark_buffer_dirty(ext_bh, &AFFS_I(inode)->i_metadata_bhs);
affs_brelse(ext_bh);
if (inode->i_size) {

fs/affs/inode.c

View file
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 561fc01..e03e9f1 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -206,7 +206,7 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
}
}
affs_fix_checksum(sb, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
affs_brelse(bh);
affs_free_prealloc(inode);
return 0;
@@ -267,9 +267,11 @@ affs_evict_inode(struct inode *inode)
if (!inode->i_nlink) {
inode->i_size = 0;
affs_truncate(inode);
+ } else {
+ mmb_sync(&AFFS_I(inode)->i_metadata_bhs);
}
- invalidate_inode_buffers(inode);
+ mmb_invalidate(&AFFS_I(inode)->i_metadata_bhs);
clear_inode(inode);
affs_free_prealloc(inode);
cache_page = (unsigned long)AFFS_I(inode)->i_lc;
@@ -304,7 +306,7 @@ affs_new_inode(struct inode *dir)
bh = affs_getzeroblk(sb, block);
if (!bh)
goto err_bh;
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
affs_brelse(bh);
inode->i_uid = current_fsuid();
@@ -392,17 +394,17 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
AFFS_TAIL(sb, bh)->link_chain = chain;
AFFS_TAIL(sb, inode_bh)->link_chain = cpu_to_be32(block);
affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain));
- mark_buffer_dirty_inode(inode_bh, inode);
+ mmb_mark_buffer_dirty(inode_bh, &AFFS_I(inode)->i_metadata_bhs);
set_nlink(inode, 2);
ihold(inode);
}
affs_fix_checksum(sb, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
dentry->d_fsdata = (void *)(long)bh->b_blocknr;
affs_lock_dir(dir);
retval = affs_insert_hash(dir, bh);
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
affs_unlock_dir(dir);
affs_unlock_link(inode);

fs/affs/namei.c

View file
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 8705321..c3c6532 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -373,7 +373,7 @@ affs_symlink(struct mnt_idmap *idmap, struct inode *dir,
}
*p = 0;
inode->i_size = i + 1;
- mark_buffer_dirty_inode(bh, inode);
+ mmb_mark_buffer_dirty(bh, &AFFS_I(inode)->i_metadata_bhs);
affs_brelse(bh);
mark_inode_dirty(inode);
@@ -443,7 +443,8 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
/* TODO: move it back to old_dir, if error? */
done:
- mark_buffer_dirty_inode(bh, retval ? old_dir : new_dir);
+ mmb_mark_buffer_dirty(bh,
+ &AFFS_I(retval ? old_dir : new_dir)->i_metadata_bhs);
affs_brelse(bh);
return retval;
}
@@ -496,8 +497,8 @@ affs_xrename(struct inode *old_dir, struct dentry *old_dentry,
retval = affs_insert_hash(old_dir, bh_new);
affs_unlock_dir(old_dir);
done:
- mark_buffer_dirty_inode(bh_old, new_dir);
- mark_buffer_dirty_inode(bh_new, old_dir);
+ mmb_mark_buffer_dirty(bh_old, &AFFS_I(new_dir)->i_metadata_bhs);
+ mmb_mark_buffer_dirty(bh_new, &AFFS_I(old_dir)->i_metadata_bhs);
affs_brelse(bh_old);
affs_brelse(bh_new);
return retval;

fs/affs/super.c

View file
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 8451647..079f36e 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -108,6 +108,7 @@ static struct inode *affs_alloc_inode(struct super_block *sb)
i->i_lc = NULL;
i->i_ext_bh = NULL;
i->i_pa_cnt = 0;
+ mmb_init(&i->i_metadata_bhs, &i->vfs_inode.i_data);
return &i->vfs_inode;
}

fs/aio.c

View file
diff --git a/fs/aio.c b/fs/aio.c
index a07bdd1..ba9b9fa 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -218,6 +218,17 @@ struct aio_kiocb {
struct eventfd_ctx *ki_eventfd;
};
+struct aio_inode_info {
+ struct inode vfs_inode;
+ spinlock_t migrate_lock;
+ struct kioctx *ctx;
+};
+
+static inline struct aio_inode_info *AIO_I(struct inode *inode)
+{
+ return container_of(inode, struct aio_inode_info, vfs_inode);
+}
+
/*------ sysctl variables----*/
static DEFINE_SPINLOCK(aio_nr_lock);
static unsigned long aio_nr; /* current system wide number of aio requests */
@@ -251,6 +262,7 @@ static void __init aio_sysctl_init(void)
static struct kmem_cache *kiocb_cachep;
static struct kmem_cache *kioctx_cachep;
+static struct kmem_cache *aio_inode_cachep;
static struct vfsmount *aio_mnt;
@@ -261,11 +273,12 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
{
struct file *file;
struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
+
if (IS_ERR(inode))
return ERR_CAST(inode);
inode->i_mapping->a_ops = &aio_ctx_aops;
- inode->i_mapping->i_private_data = ctx;
+ AIO_I(inode)->ctx = ctx;
inode->i_size = PAGE_SIZE * nr_pages;
file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
@@ -275,14 +288,49 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
return file;
}
+static struct inode *aio_alloc_inode(struct super_block *sb)
+{
+ struct aio_inode_info *ai;
+
+ ai = alloc_inode_sb(sb, aio_inode_cachep, GFP_KERNEL);
+ if (!ai)
+ return NULL;
+ ai->ctx = NULL;
+
+ return &ai->vfs_inode;
+}
+
+static void aio_free_inode(struct inode *inode)
+{
+ kmem_cache_free(aio_inode_cachep, AIO_I(inode));
+}
+
+static const struct super_operations aio_super_operations = {
+ .alloc_inode = aio_alloc_inode,
+ .free_inode = aio_free_inode,
+ .statfs = simple_statfs,
+};
+
static int aio_init_fs_context(struct fs_context *fc)
{
- if (!init_pseudo(fc, AIO_RING_MAGIC))
+ struct pseudo_fs_context *pfc;
+
+ pfc = init_pseudo(fc, AIO_RING_MAGIC);
+ if (!pfc)
return -ENOMEM;
fc->s_iflags |= SB_I_NOEXEC;
+ pfc->ops = &aio_super_operations;
return 0;
}
+static void init_once(void *obj)
+{
+ struct aio_inode_info *ai = obj;
+
+ inode_init_once(&ai->vfs_inode);
+ spin_lock_init(&ai->migrate_lock);
+}
+
/* aio_setup
* Creates the slab caches used by the aio routines, panic on
* failure as this is done early during the boot sequence.
@@ -294,6 +342,11 @@ static int __init aio_setup(void)
.init_fs_context = aio_init_fs_context,
.kill_sb = kill_anon_super,
};
+
+ aio_inode_cachep = kmem_cache_create("aio_inode_cache",
+ sizeof(struct aio_inode_info), 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT),
+ init_once);
aio_mnt = kern_mount(&aio_fs);
if (IS_ERR(aio_mnt))
panic("Failed to create aio fs mount.");
@@ -308,17 +361,17 @@ __initcall(aio_setup);
static void put_aio_ring_file(struct kioctx *ctx)
{
struct file *aio_ring_file = ctx->aio_ring_file;
- struct address_space *i_mapping;
if (aio_ring_file) {
- truncate_setsize(file_inode(aio_ring_file), 0);
+ struct inode *inode = file_inode(aio_ring_file);
+
+ truncate_setsize(inode, 0);
/* Prevent further access to the kioctx from migratepages */
- i_mapping = aio_ring_file->f_mapping;
- spin_lock(&i_mapping->i_private_lock);
- i_mapping->i_private_data = NULL;
+ spin_lock(&AIO_I(inode)->migrate_lock);
+ AIO_I(inode)->ctx = NULL;
ctx->aio_ring_file = NULL;
- spin_unlock(&i_mapping->i_private_lock);
+ spin_unlock(&AIO_I(inode)->migrate_lock);
fput(aio_ring_file);
}
@@ -408,13 +461,14 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
struct folio *src, enum migrate_mode mode)
{
struct kioctx *ctx;
+ struct aio_inode_info *ai = AIO_I(mapping->host);
unsigned long flags;
pgoff_t idx;
int rc = 0;
- /* mapping->i_private_lock here protects against the kioctx teardown. */
- spin_lock(&mapping->i_private_lock);
- ctx = mapping->i_private_data;
+ /* ai->migrate_lock here protects against the kioctx teardown. */
+ spin_lock(&ai->migrate_lock);
+ ctx = ai->ctx;
if (!ctx) {
rc = -EINVAL;
goto out;
@@ -467,7 +521,7 @@ static int aio_migrate_folio(struct address_space *mapping, struct folio *dst,
out_unlock:
mutex_unlock(&ctx->ring_lock);
out:
- spin_unlock(&mapping->i_private_lock);
+ spin_unlock(&ai->migrate_lock);
return rc;
}
#else

fs/bfs/bfs.h

View file
diff --git a/fs/bfs/bfs.h b/fs/bfs/bfs.h
index 606f937..b08afe7 100644
--- a/fs/bfs/bfs.h
+++ b/fs/bfs/bfs.h
@@ -35,6 +35,7 @@ struct bfs_inode_info {
unsigned long i_dsk_ino; /* inode number from the disk, can be 0 */
unsigned long i_sblock;
unsigned long i_eblock;
+ struct mapping_metadata_bhs i_metadata_bhs;
struct inode vfs_inode;
};

fs/bfs/dir.c

View file
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 481514d..5b40ab0 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -68,10 +68,17 @@ static int bfs_readdir(struct file *f, struct dir_context *ctx)
return 0;
}
+static int bfs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
+{
+ return mmb_fsync(file,
+ &BFS_I(file->f_mapping->host)->i_metadata_bhs,
+ start, end, datasync);
+}
+
const struct file_operations bfs_dir_operations = {
.read = generic_read_dir,
.iterate_shared = bfs_readdir,
- .fsync = generic_file_fsync,
+ .fsync = bfs_fsync,
.llseek = generic_file_llseek,
};
@@ -186,7 +193,7 @@ static int bfs_unlink(struct inode *dir, struct dentry *dentry)
set_nlink(inode, 1);
}
de->ino = 0;
- mark_buffer_dirty_inode(bh, dir);
+ mmb_mark_buffer_dirty(bh, &BFS_I(dir)->i_metadata_bhs);
inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
mark_inode_dirty(dir);
inode_set_ctime_to_ts(inode, inode_get_ctime(dir));
@@ -246,7 +253,7 @@ static int bfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
inode_set_ctime_current(new_inode);
inode_dec_link_count(new_inode);
}
- mark_buffer_dirty_inode(old_bh, old_dir);
+ mmb_mark_buffer_dirty(old_bh, &BFS_I(old_dir)->i_metadata_bhs);
error = 0;
end_rename:
@@ -296,7 +303,8 @@ static int bfs_add_entry(struct inode *dir, const struct qstr *child, int ino)
for (i = 0; i < BFS_NAMELEN; i++)
de->name[i] =
(i < namelen) ? name[i] : 0;
- mark_buffer_dirty_inode(bh, dir);
+ mmb_mark_buffer_dirty(bh,
+ &BFS_I(dir)->i_metadata_bhs);
brelse(bh);
return 0;
}

fs/bfs/inode.c

View file
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 9da02f5..19e49c8 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -187,7 +187,9 @@ static void bfs_evict_inode(struct inode *inode)
dprintf("ino=%08lx\n", ino);
truncate_inode_pages_final(&inode->i_data);
- invalidate_inode_buffers(inode);
+ if (inode->i_nlink)
+ mmb_sync(&BFS_I(inode)->i_metadata_bhs);
+ mmb_invalidate(&BFS_I(inode)->i_metadata_bhs);
clear_inode(inode);
if (inode->i_nlink)
@@ -257,6 +259,8 @@ static struct inode *bfs_alloc_inode(struct super_block *sb)
bi = alloc_inode_sb(sb, bfs_inode_cachep, GFP_KERNEL);
if (!bi)
return NULL;
+ mmb_init(&bi->i_metadata_bhs, &bi->vfs_inode.i_data);
+
return &bi->vfs_inode;
}

fs/buffer.c

View file
diff --git a/fs/buffer.c b/fs/buffer.c
index 22b4364..cbed175 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -54,7 +54,6 @@
#include "internal.h"
-static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
enum rw_hint hint, struct writeback_control *wbc);
@@ -468,146 +467,187 @@ EXPORT_SYMBOL(mark_buffer_async_write);
* a successful fsync(). For example, ext2 indirect blocks need to be
* written back and waited upon before fsync() returns.
*
- * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(),
- * inode_has_buffers() and invalidate_inode_buffers() are provided for the
- * management of a list of dependent buffers at ->i_mapping->i_private_list.
- *
- * Locking is a little subtle: try_to_free_buffers() will remove buffers
- * from their controlling inode's queue when they are being freed. But
- * try_to_free_buffers() will be operating against the *blockdev* mapping
- * at the time, not against the S_ISREG file which depends on those buffers.
- * So the locking for i_private_list is via the i_private_lock in the address_space

This diff is incomplete. Download the complete patch.

fs/exfat/file.c

View file

This diff is incomplete. Download the complete patch.

fs/exfat/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/ext2/ext2.h

View file

This diff is incomplete. Download the complete patch.

fs/ext2/file.c

View file

This diff is incomplete. Download the complete patch.

fs/ext2/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/ext2/super.c

View file

This diff is incomplete. Download the complete patch.

fs/ext4/ext4.h

View file

This diff is incomplete. Download the complete patch.

fs/ext4/ext4_jbd2.c

View file

This diff is incomplete. Download the complete patch.

fs/ext4/fsync.c

View file

This diff is incomplete. Download the complete patch.

fs/ext4/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/ext4/super.c

View file

This diff is incomplete. Download the complete patch.

fs/fat/dir.c

View file

This diff is incomplete. Download the complete patch.

fs/fat/fat.h

View file

This diff is incomplete. Download the complete patch.

fs/fat/fatent.c

View file

This diff is incomplete. Download the complete patch.

fs/fat/file.c

View file

This diff is incomplete. Download the complete patch.

fs/fat/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/fat/namei_msdos.c

View file

This diff is incomplete. Download the complete patch.

fs/fat/namei_vfat.c

View file

This diff is incomplete. Download the complete patch.

fs/gfs2/glock.c

View file

This diff is incomplete. Download the complete patch.

fs/hugetlbfs/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/libfs.c

View file

This diff is incomplete. Download the complete patch.

fs/minix/dir.c

View file

This diff is incomplete. Download the complete patch.

fs/minix/file.c

View file

This diff is incomplete. Download the complete patch.

fs/minix/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/minix/itree_common.c

View file

This diff is incomplete. Download the complete patch.

fs/minix/minix.h

View file

This diff is incomplete. Download the complete patch.

fs/ntfs3/file.c

View file

This diff is incomplete. Download the complete patch.

fs/ntfs3/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/ocfs2/dlmglue.c

View file

This diff is incomplete. Download the complete patch.

fs/ocfs2/namei.c

View file

This diff is incomplete. Download the complete patch.

fs/omfs/file.c

View file

This diff is incomplete. Download the complete patch.

fs/qnx4/dir.c

View file

This diff is incomplete. Download the complete patch.

fs/qnx6/dir.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/dir.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/directory.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/file.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/inode.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/namei.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/super.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/truncate.c

View file

This diff is incomplete. Download the complete patch.

fs/udf/udf_i.h

View file

This diff is incomplete. Download the complete patch.

fs/udf/udfdecl.h

View file

This diff is incomplete. Download the complete patch.

fs/ufs/dir.c

View file

This diff is incomplete. Download the complete patch.

fs/ufs/file.c

View file

This diff is incomplete. Download the complete patch.

fs/ufs/inode.c

View file

This diff is incomplete. Download the complete patch.

include/linux/buffer_head.h

View file

This diff is incomplete. Download the complete patch.

include/linux/fs.h

View file

This diff is incomplete. Download the complete patch.

include/linux/hugetlb.h

View file

This diff is incomplete. Download the complete patch.

mm/hugetlb.c

View file

This diff is incomplete. Download the complete patch.

virt/kvm/guest_memfd.c

View file

This diff is incomplete. Download the complete patch.