simpe_xattr: use per-sb cache

Move the hash table to the super block to remove excessive overhead in case
of small number of xattrs per inode.

Add linked list to the inode, used for listxattr and eviction.  Listxattr
uses rcu protection to iterate the list of xattrs.

Before being made per-sb, lazy allocation was protected by inode lock.  Now
inode lock no longer provides sufficient exclusion, so use cmpxchg() to
ensure atomicity.

Though I haven't found a description of this pattern, after some research
it seems that cmpxchg_release() and READ_ONCE() should provide the
necessary memory barriers.

Use simple_xattr_free_rcu() in simple_xattrs_free(). This is needed because
the hash table is now shared between inodes and lookup on a different inode
might be running the compare function on the just freed element within the
RCU grace period.

Following stats are based on slabinfo diff, after creating 100k empty
files, then adding a "user.test=foo" xattr to each:

v7.0 (no rhashtable):
  File creation: 993.40 bytes/file
  Xattr addition: 79.99 bytes/file

v7.1-rc2 (per-inode rhashtable):
  File creation: 939.73 bytes/file
  Xattr addition: 1296.08 bytes/file

v7.1-rc2 + this patch (per-sb rhashtable)
  File creation: 946.84 bytes/file
  Xattr addition: 111.86 bytes/file

The overhead of a single xattr is reduced to nearly v7.0 levels.  The per
xattr overhead is slightly larger due to the addition of three pointers to
struct simple_xattr.

Fixes: b32c4a213698 ("xattr: add rhashtable-based simple_xattr infrastructure")
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://patch.msgid.link/20260605135322.2632068-5-mszeredi@redhat.com
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

1 files changed, 7 insertions, 5 deletions

diff --git a/net/socket.c b/net/socket.c
index d3597c858345..a8014f930d9e 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -310,8 +310,10 @@ efault_end:
 
 static struct kmem_cache *sock_inode_cachep __ro_after_init;
 
+static struct simple_xattr_cache sockfs_xa_cache;
+
 struct sockfs_inode {
-	struct simple_xattrs *xattrs;
+	struct list_head xattrs;
 	struct simple_xattr_limits xattr_limits;
 	struct socket_alloc;
 };
@@ -328,7 +330,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	si = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL);
 	if (!si)
 		return NULL;
-	si->xattrs = NULL;
+	INIT_LIST_HEAD_RCU(&si->xattrs);
 	simple_xattr_limits_init(&si->xattr_limits);
 
 	init_waitqueue_head(&si->socket.wq.wait);
@@ -348,7 +350,7 @@ static void sock_evict_inode(struct inode *inode)
 {
 	struct sockfs_inode *si = SOCKFS_I(inode);
 
-	simple_xattrs_free(&si->xattrs, NULL);
+	simple_xattrs_free(&sockfs_xa_cache, &si->xattrs, NULL);
 	clear_inode(inode);
 }
 
@@ -441,7 +443,7 @@ static int sockfs_user_xattr_get(const struct xattr_handler *handler,
 	const char *name = xattr_full_name(handler, suffix);
 	struct sockfs_inode *si = SOCKFS_I(inode);
 
-	return simple_xattr_get(&si->xattrs, name, value, size);
+	return simple_xattr_get(&sockfs_xa_cache, &si->xattrs, name, value, size);
 }
 
 static int sockfs_user_xattr_set(const struct xattr_handler *handler,
@@ -453,7 +455,7 @@ static int sockfs_user_xattr_set(const struct xattr_handler *handler,
 	const char *name = xattr_full_name(handler, suffix);
 	struct sockfs_inode *si = SOCKFS_I(inode);
 
-	return simple_xattr_set_limited(&si->xattrs, &si->xattr_limits,
+	return simple_xattr_set_limited(&sockfs_xa_cache, &si->xattrs, &si->xattr_limits,
 					name, value, size, flags);
 }