The patch titled
Subject: ucount: use RCU for ucounts lookups
has been added to the -mm mm-nonmm-unstable branch. Its filename is
ucount-use-rcu-for-ucounts-lookups.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/ucount-use-rcu-for-ucounts-lookups.patch
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Subject: ucount: use RCU for ucounts lookups
Date: Mon, 3 Feb 2025 16:05:24 +0100
The ucounts element is looked up under ucounts_lock. This can be
optimized by using RCU for a lockless lookup and return and element if the
reference can be obtained.
Replace hlist_head with hlist_nulls_head which is RCU compatible. Let
find_ucounts() search for the required item within a RCU section and
return the item if a reference could be obtained. This means
alloc_ucounts() will always return an element (unless the memory
allocation failed). Let put_ucounts() RCU free the element if the
reference counter dropped to zero.
Link: https://lkml.kernel.org/r/20250203150525.456525-4-bigeasy@xxxxxxxxxxxxx
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Reviewed-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Cc: Acked-by:Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
Cc: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
Cc: Lai jiangshan <jiangshanlai@xxxxxxxxx>
Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Mengen Sun <mengensun@xxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: "Uladzislau Rezki (Sony)" <urezki@xxxxxxxxx>
Cc: YueHong Wu <yuehongwu@xxxxxxxxxxx>
Cc: Zqiang <qiang.zhang1211@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/user_namespace.h | 4 +
kernel/ucount.c | 75 ++++++++++++++++---------------
2 files changed, 43 insertions(+), 36 deletions(-)
--- a/include/linux/user_namespace.h~ucount-use-rcu-for-ucounts-lookups
+++ a/include/linux/user_namespace.h
@@ -5,6 +5,7 @@
#include <linux/kref.h>
#include <linux/nsproxy.h>
#include <linux/ns_common.h>
+#include <linux/rculist_nulls.h>
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/rwsem.h>
@@ -115,9 +116,10 @@ struct user_namespace {
} __randomize_layout;
struct ucounts {
- struct hlist_node node;
+ struct hlist_nulls_node node;
struct user_namespace *ns;
kuid_t uid;
+ struct rcu_head rcu;
atomic_t count;
atomic_long_t ucount[UCOUNT_COUNTS];
atomic_long_t rlimit[UCOUNT_RLIMIT_COUNTS];
--- a/kernel/ucount.c~ucount-use-rcu-for-ucounts-lookups
+++ a/kernel/ucount.c
@@ -15,7 +15,10 @@ struct ucounts init_ucounts = {
};
#define UCOUNTS_HASHTABLE_BITS 10
-static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)];
+#define UCOUNTS_HASHTABLE_ENTRIES (1 << UCOUNTS_HASHTABLE_BITS)
+static struct hlist_nulls_head ucounts_hashtable[UCOUNTS_HASHTABLE_ENTRIES] = {
+ [0 ... UCOUNTS_HASHTABLE_ENTRIES - 1] = HLIST_NULLS_HEAD_INIT(0)
+};
static DEFINE_SPINLOCK(ucounts_lock);
#define ucounts_hashfn(ns, uid) \
@@ -24,7 +27,6 @@ static DEFINE_SPINLOCK(ucounts_lock);
#define ucounts_hashentry(ns, uid) \
(ucounts_hashtable + ucounts_hashfn(ns, uid))
-
#ifdef CONFIG_SYSCTL
static struct ctl_table_set *
set_lookup(struct ctl_table_root *root)
@@ -127,22 +129,28 @@ void retire_userns_sysctls(struct user_n
#endif
}
-static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent)
+static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid,
+ struct hlist_nulls_head *hashent)
{
struct ucounts *ucounts;
+ struct hlist_nulls_node *pos;
- hlist_for_each_entry(ucounts, hashent, node) {
- if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns))
- return ucounts;
+ guard(rcu)();
+ hlist_nulls_for_each_entry_rcu(ucounts, pos, hashent, node) {
+ if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) {
+ if (atomic_inc_not_zero(&ucounts->count))
+ return ucounts;
+ }
}
return NULL;
}
static void hlist_add_ucounts(struct ucounts *ucounts)
{
- struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid);
+ struct hlist_nulls_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid);
+
spin_lock_irq(&ucounts_lock);
- hlist_add_head(&ucounts->node, hashent);
+ hlist_nulls_add_head_rcu(&ucounts->node, hashent);
spin_unlock_irq(&ucounts_lock);
}
@@ -155,37 +163,33 @@ struct ucounts *get_ucounts(struct ucoun
struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid)
{
- struct hlist_head *hashent = ucounts_hashentry(ns, uid);
- struct ucounts *ucounts, *new = NULL;
+ struct hlist_nulls_head *hashent = ucounts_hashentry(ns, uid);
+ struct ucounts *ucounts, *new;
+
+ ucounts = find_ucounts(ns, uid, hashent);
+ if (ucounts)
+ return ucounts;
+
+ new = kzalloc(sizeof(*new), GFP_KERNEL);
+ if (!new)
+ return NULL;
+
+ new->ns = ns;
+ new->uid = uid;
+ atomic_set(&new->count, 1);
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
- if (!ucounts) {
+ if (ucounts) {
spin_unlock_irq(&ucounts_lock);
-
- new = kzalloc(sizeof(*new), GFP_KERNEL);
- if (!new)
- return NULL;
-
- new->ns = ns;
- new->uid = uid;
- atomic_set(&new->count, 1);
-
- spin_lock_irq(&ucounts_lock);
- ucounts = find_ucounts(ns, uid, hashent);
- if (!ucounts) {
- hlist_add_head(&new->node, hashent);
- get_user_ns(new->ns);
- spin_unlock_irq(&ucounts_lock);
- return new;
- }
+ kfree(new);
+ return ucounts;
}
- if (!atomic_inc_not_zero(&ucounts->count))
- ucounts = NULL;
- spin_unlock_irq(&ucounts_lock);
- kfree(new);
- return ucounts;
+ hlist_nulls_add_head_rcu(&new->node, hashent);
+ get_user_ns(new->ns);
+ spin_unlock_irq(&ucounts_lock);
+ return new;
}
void put_ucounts(struct ucounts *ucounts)
@@ -193,10 +197,11 @@ void put_ucounts(struct ucounts *ucounts
unsigned long flags;
if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) {
- hlist_del_init(&ucounts->node);
+ hlist_nulls_del_rcu(&ucounts->node);
spin_unlock_irqrestore(&ucounts_lock, flags);
+
put_user_ns(ucounts->ns);
- kfree(ucounts);
+ kfree_rcu(ucounts, rcu);
}
}
_
Patches currently in -mm which might be from bigeasy@xxxxxxxxxxxxx are
rcu-provide-a-static-initializer-for-hlist_nulls_head.patch
ucount-replace-get_ucounts_or_wrap-with-atomic_inc_not_zero.patch
ucount-use-rcu-for-ucounts-lookups.patch
ucount-use-rcuref_t-for-reference-counting.patch
