From: Christian Brauner <brauner@kernel.org>
To: linux-fsdevel@vger.kernel.org
Cc: Jeff Layton <jlayton@kernel.org>,
Josef Bacik <josef@toxicpanda.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Jan Kara <jack@suse.cz>,
linux-kernel@vger.kernel.org, Hugh Dickins <hughd@google.com>,
linux-mm@kvack.org,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Tejun Heo <tj@kernel.org>, Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Jann Horn <jannh@google.com>,
netdev@vger.kernel.org, Christian Brauner <brauner@kernel.org>
Subject: [PATCH 05/14] pidfs: adapt to rhashtable-based simple_xattrs
Date: Mon, 16 Feb 2026 14:32:01 +0100 [thread overview]
Message-ID: <20260216-work-xattr-socket-v1-5-c2efa4f74cb7@kernel.org> (raw)
In-Reply-To: <20260216-work-xattr-socket-v1-0-c2efa4f74cb7@kernel.org>
Adapt pidfs to use the rhashtable-based xattr path by switching from a
dedicated slab cache to simple_xattrs_alloc().
Previously pidfs used a custom kmem_cache (pidfs_xattr_cachep) that
allocated a struct containing an embedded simple_xattrs plus
simple_xattrs_init(). Replace this with simple_xattrs_alloc() which
combines kzalloc + rhashtable_init, and drop the dedicated slab cache
entirely.
Use simple_xattr_free_rcu() for replaced xattr entries to allow
concurrent RCU readers to finish.
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
fs/pidfs.c | 65 +++++++++++++++++++++++++++++++++++++++-----------------------
1 file changed, 41 insertions(+), 24 deletions(-)
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 1e20e36e0ed5..cb62000681df 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -21,6 +21,7 @@
#include <linux/utsname.h>
#include <net/net_namespace.h>
#include <linux/coredump.h>
+#include <linux/llist.h>
#include <linux/xattr.h>
#include "internal.h"
@@ -29,7 +30,6 @@
#define PIDFS_PID_DEAD ERR_PTR(-ESRCH)
static struct kmem_cache *pidfs_attr_cachep __ro_after_init;
-static struct kmem_cache *pidfs_xattr_cachep __ro_after_init;
static struct path pidfs_root_path = {};
@@ -44,9 +44,8 @@ enum pidfs_attr_mask_bits {
PIDFS_ATTR_BIT_COREDUMP = 1,
};
-struct pidfs_attr {
+struct pidfs_anon_attr {
unsigned long attr_mask;
- struct simple_xattrs *xattrs;
struct /* exit info */ {
__u64 cgroupid;
__s32 exit_code;
@@ -55,6 +54,14 @@ struct pidfs_attr {
__u32 coredump_signal;
};
+struct pidfs_attr {
+ struct simple_xattrs *xattrs;
+ union {
+ struct pidfs_anon_attr;
+ struct llist_node pidfs_llist;
+ };
+};
+
static struct rb_root pidfs_ino_tree = RB_ROOT;
#if BITS_PER_LONG == 32
@@ -147,10 +154,30 @@ void pidfs_remove_pid(struct pid *pid)
write_seqcount_end(&pidmap_lock_seq);
}
+static LLIST_HEAD(pidfs_free_list);
+
+static void pidfs_free_attr_work(struct work_struct *work)
+{
+ struct pidfs_attr *attr, *next;
+ struct llist_node *head;
+
+ head = llist_del_all(&pidfs_free_list);
+ llist_for_each_entry_safe(attr, next, head, pidfs_llist) {
+ struct simple_xattrs *xattrs = attr->xattrs;
+
+ if (xattrs) {
+ simple_xattrs_free(xattrs, NULL);
+ kfree(xattrs);
+ }
+ kfree(attr);
+ }
+}
+
+static DECLARE_WORK(pidfs_free_work, pidfs_free_attr_work);
+
void pidfs_free_pid(struct pid *pid)
{
- struct pidfs_attr *attr __free(kfree) = no_free_ptr(pid->attr);
- struct simple_xattrs *xattrs __free(kfree) = NULL;
+ struct pidfs_attr *attr = pid->attr;
/*
* Any dentry must've been wiped from the pid by now.
@@ -169,9 +196,10 @@ void pidfs_free_pid(struct pid *pid)
if (IS_ERR(attr))
return;
- xattrs = no_free_ptr(attr->xattrs);
- if (xattrs)
- simple_xattrs_free(xattrs, NULL);
+ if (likely(!attr->xattrs))
+ kfree(attr);
+ else if (llist_add(&attr->pidfs_llist, &pidfs_free_list))
+ schedule_work(&pidfs_free_work);
}
#ifdef CONFIG_PROC_FS
@@ -998,7 +1026,7 @@ static int pidfs_xattr_get(const struct xattr_handler *handler,
xattrs = READ_ONCE(attr->xattrs);
if (!xattrs)
- return 0;
+ return -ENODATA;
name = xattr_full_name(handler, suffix);
return simple_xattr_get(xattrs, name, value, size);
@@ -1018,22 +1046,16 @@ static int pidfs_xattr_set(const struct xattr_handler *handler,
/* Ensure we're the only one to set @attr->xattrs. */
WARN_ON_ONCE(!inode_is_locked(inode));
- xattrs = READ_ONCE(attr->xattrs);
- if (!xattrs) {
- xattrs = kmem_cache_zalloc(pidfs_xattr_cachep, GFP_KERNEL);
- if (!xattrs)
- return -ENOMEM;
-
- simple_xattrs_init(xattrs);
- smp_store_release(&pid->attr->xattrs, xattrs);
- }
+ xattrs = simple_xattrs_lazy_alloc(&attr->xattrs, value, flags);
+ if (IS_ERR_OR_NULL(xattrs))
+ return PTR_ERR(xattrs);
name = xattr_full_name(handler, suffix);
old_xattr = simple_xattr_set(xattrs, name, value, size, flags);
if (IS_ERR(old_xattr))
return PTR_ERR(old_xattr);
- simple_xattr_free(old_xattr);
+ simple_xattr_free_rcu(old_xattr);
return 0;
}
@@ -1108,11 +1130,6 @@ void __init pidfs_init(void)
(SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT |
SLAB_ACCOUNT | SLAB_PANIC), NULL);
- pidfs_xattr_cachep = kmem_cache_create("pidfs_xattr_cache",
- sizeof(struct simple_xattrs), 0,
- (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT |
- SLAB_ACCOUNT | SLAB_PANIC), NULL);
-
pidfs_mnt = kern_mount(&pidfs_type);
if (IS_ERR(pidfs_mnt))
panic("Failed to mount pidfs pseudo filesystem");
--
2.47.3
next prev parent reply other threads:[~2026-02-16 13:32 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-16 13:31 [PATCH 00/14] xattr: rework simple xattrs and support user.* xattrs on sockets Christian Brauner
2026-02-16 13:31 ` [PATCH 01/14] xattr: add rcu_head and rhash_head to struct simple_xattr Christian Brauner
2026-02-16 13:31 ` [PATCH 02/14] xattr: add rhashtable-based simple_xattr infrastructure Christian Brauner
2026-02-16 13:31 ` [PATCH 03/14] shmem: adapt to rhashtable-based simple_xattrs with lazy allocation Christian Brauner
2026-02-16 13:32 ` [PATCH 04/14] kernfs: " Christian Brauner
2026-02-16 13:32 ` Christian Brauner [this message]
2026-02-16 13:32 ` [PATCH 06/14] xattr: remove rbtree-based simple_xattr infrastructure Christian Brauner
2026-02-16 13:32 ` [PATCH 07/14] xattr: add xattr_permission_error() Christian Brauner
2026-02-16 13:32 ` [PATCH 08/14] xattr: switch xattr_permission() to switch statement Christian Brauner
2026-02-16 13:32 ` [PATCH 09/14] xattr: move user limits for xattrs to generic infra Christian Brauner
2026-02-21 0:03 ` Darrick J. Wong
2026-02-16 13:32 ` [PATCH 10/14] xattr,net: support limited amount of extended attributes on sockfs sockets Christian Brauner
2026-02-16 13:32 ` [PATCH 11/14] xattr: support extended attributes on sockets Christian Brauner
2026-02-16 13:32 ` [PATCH 12/14] selftests/xattr: path-based AF_UNIX socket xattr tests Christian Brauner
2026-02-16 13:32 ` [PATCH 13/14] selftests/xattr: sockfs " Christian Brauner
2026-02-16 13:32 ` [PATCH 14/14] selftests/xattr: test xattrs on various socket families Christian Brauner
2026-02-20 0:44 ` [PATCH 00/14] xattr: rework simple xattrs and support user.* xattrs on sockets Darrick J. Wong
2026-02-20 9:23 ` Christian Brauner
2026-02-21 0:14 ` Darrick J. Wong
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=20260216-work-xattr-socket-v1-5-c2efa4f74cb7@kernel.org \
--to=brauner@kernel.org \
--cc=edumazet@google.com \
--cc=gregkh@linuxfoundation.org \
--cc=hughd@google.com \
--cc=jack@suse.cz \
--cc=jannh@google.com \
--cc=jlayton@kernel.org \
--cc=josef@toxicpanda.com \
--cc=kuba@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=tj@kernel.org \
--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