posix-timers: Make signal_struct:: Next_posix_timer_id an atomic_t

The global hash_lock protecting the posix timer hash table can be heavily
contended especially when there is an extensive linear search for a timer
ID.

Timer IDs are handed out by monotonically increasing next_posix_timer_id
and then validating that there is no timer with the same ID in the hash
table. Both operations happen with the global hash lock held.

To reduce the hash lock contention the hash will be reworked to a scaled
hash with per bucket locks, which requires to handle the ID counter
lockless.

Prepare for this by making next_posix_timer_id an atomic_t, which can be
used lockless with atomic_inc_return().

[ tglx: Adopted from Eric's series, massaged change log and simplified it ]

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/all/20250219125522.2535263-2-edumazet@google.com
Link: https://lore.kernel.org/all/20250308155624.151545978@linutronix.de

diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index d5d03d919df811caffff34462e452a2d3d8bf6a6..72649d7fce2a52b3b0a56ef1fe7a3c7cb604ce1c 100644 (file)
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -136,7 +136,7 @@ struct signal_struct {
 #ifdef CONFIG_POSIX_TIMERS
 
        /* POSIX.1b Interval Timers */
-       unsigned int            next_posix_timer_id;
+       atomic_t                next_posix_timer_id;
        struct hlist_head       posix_timers;
        struct hlist_head       ignored_posix_timers;
 

diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 991d12abae45d2a9d0329f25033ab7846520e0b6..f9a70c1373b647b42d29527cc11473f706e13793 100644 (file)
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -119,21 +119,17 @@ static bool posix_timer_hashed(struct hlist_head *head, struct signal_struct *si
 static int posix_timer_add(struct k_itimer *timer)
 {
        struct signal_struct *sig = current->signal;
-       struct hlist_head *head;
-       unsigned int cnt, id;
 
        /*
         * FIXME: Replace this by a per signal struct xarray once there is
         * a plan to handle the resulting CRIU regression gracefully.
         */
-       for (cnt = 0; cnt <= INT_MAX; cnt++) {
-               spin_lock(&hash_lock);
-               id = sig->next_posix_timer_id;
-
-               /* Write the next ID back. Clamp it to the positive space */
-               sig->next_posix_timer_id = (id + 1) & INT_MAX;
+       for (unsigned int cnt = 0; cnt <= INT_MAX; cnt++) {
+               /* Get the next timer ID and clamp it to positive space */
+               unsigned int id = atomic_fetch_inc(&sig->next_posix_timer_id) & INT_MAX;
+               struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)];
 
-               head = &posix_timers_hashtable[hash(sig, id)];
+               spin_lock(&hash_lock);
                if (!posix_timer_hashed(head, sig, id)) {
                        /*
                         * Set the timer ID and the signal pointer to make