ucount: use RCU for ucounts lookups

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@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Lai jiangshan <jiangshanlai@gmail.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mengen Sun <mengensun@tencent.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: YueHong Wu <yuehongwu@tencent.com>
Cc: Zqiang <qiang.zhang1211@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
This commit is contained in:
Sebastian Andrzej Siewior 2025-02-03 16:05:24 +01:00 committed by Andrew Morton
parent 328152e677
commit 5f01a22c5b
2 changed files with 43 additions and 36 deletions

View file

@ -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];

View file

@ -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_namespace *ns)
#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 ucounts *ucounts)
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);
}
}