1
0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-01-11 17:10:13 +00:00

Compare commits

...

7 Commits

Author SHA1 Message Date
Linus Torvalds
1af5c1d3a9 Miscellaneous fixes:
- Fix a race in timer->function clearing in timer_shutdown_sync()
 
  - Fix a timekeeper sysfs-setup resource leak in error paths
 
  - Fix the NOHZ report_idle_softirq() syslog rate-limiting
    logic to have no side effects on the return value
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmkivgERHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1i/0g/+ODFR6NF7cNcsZPhKdRt/A9Il72qmjteG
 Fqzacev1rzaQpPSaRpOnEAnqDRmfnFLZ0I4WA36QJxfApHHg9kI8GzEaa7WDvQOc
 kOL317i3vsme+tolI0fwazvMRnwgSipHVvXp76eyaEKXHM97i81XUpJYynxl+j9R
 0le8wpcBQKMUnpvYWN4J7u0AOO0vXCdaKSM2r9bgecXGyaqgzdyLYqGhgPLd0tYC
 Tn3pSrQIffORZQed3hKjXmC4DSs+tsdQr1npphxrzHy3Q8rXbt3eEj96IYyHdz1f
 /3eetSWRcd0jnZYIjuA9xG7xMSBBitkPBzSQMaZMdzV2d03oPU2WVvoKLSPnFNxz
 JQIErExLJH2AOrYNLmx+6DJ0Ql8398KdISJnb6HdX1cZcljRKmqlo9BIaPorQDqf
 WFm8WvhthBXHwEbWx/ecaPkV2aBQpXTTH7AkCebBLF+YTxtHUVGjwlBQ/CltABk3
 a4U93M/Zdyaxys/9YpIeWAsg0y3b54r6aFbReyt8CiMVe+gKqTOnT3Jy4hqFZPnB
 x+AHtooGsN7CIV4q9NIB6EmvJ5J1HFkmGQrWo1y/OHbZp2mDJy/1sQ+rj7NXdBZA
 ibrUHIWzTtZ6WpuR1ABD3wubhb7/BF3Gwh4v27AUtLFKW/cZq7ovMODVrp+Svt6X
 3EOg/YofAy0=
 =JVik
 -----END PGP SIGNATURE-----

Merge tag 'timers-urgent-2025-11-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timer fixes from Ingo Molnar:

 - Fix a race in timer->function clearing in timer_shutdown_sync()

 - Fix a timekeeper sysfs-setup resource leak in error paths

 - Fix the NOHZ report_idle_softirq() syslog rate-limiting
   logic to have no side effects on the return value

* tag 'timers-urgent-2025-11-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  timers: Fix NULL function pointer race in timer_shutdown_sync()
  timekeeping: Fix resource leak in tk_aux_sysfs_init() error paths
  tick/sched: Fix bogus condition in report_idle_softirq()
2025-11-23 08:23:30 -08:00
Linus Torvalds
e624f73775 Fix perf CPU-clock counters, and address a static checker warning.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmkiu0sRHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1h5+xAAsBjDSBSLwCyMb+k9iP482jMgMkl3s3m1
 LjqBvdJgbBZvZF2mfxRFRcgR8KLNyy4uXq05w0Bb5zP4pTvPK0cNuhG6SmlAhppr
 r4OHwnbRThXoKssWYVTc5qILEiCAoRbwSXDYdFjgl29Fd0u+IIv2sQIYRKkna8OJ
 A73TuOjFTWdU58sKPqY/tp7O0duzyFoicFkkap4atAV8lPHlDZJl+r1ayBtmx3pD
 xe9u9kHQXYq6NLPwXKrKIA77RAa3w1nTAe9zh/mIFF36MvifxGhSwNSB4Fr/RKuN
 2lBzCW5KnTrY9Mzs1Ds4k1RBt6RNNn30AZU/c9RB1qdzl1X6Z1xtse72yjHYQPb1
 +VM4YwMhnaJkGEczK6KP62DfNa/scrSjehLHXwqNPCt+FzJY2YRXp5s3v8SK8AXP
 rlRBnL0U8FhImR3VucgHp6LIkZMvuKI/+dDdW/KIO6XkZqbYQ/fORAgCFNGJDNAo
 UQv4mb11qk2Bv/QC0NJGfQqIb2mS+/xmM8q31Ipf9eC0eHzM0sLmVtJW9IX61qfI
 K+rP4qmIKkWJMLMkwGJxpw2G0v3Wfx0LQ6xa9io/Bw9F/9rs8/Qd5C2eafZmCRqW
 Mt/dK+2eYnR/+hKsWN/xN8ayawN2Ra5NSJjQAxL5CfLEXJRQAmrvwpWPNA/Ef3Dg
 0KOqU6yJlNo=
 =kaoD
 -----END PGP SIGNATURE-----

Merge tag 'perf-urgent-2025-11-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Fix perf CPU-clock counters, and address a static checker warning"

* tag 'perf-urgent-2025-11-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf: Fix 0 count issue of cpu-clock
  perf/x86/intel/uncore: Remove superfluous check
2025-11-23 08:20:15 -08:00
Yipeng Zou
20739af073 timers: Fix NULL function pointer race in timer_shutdown_sync()
There is a race condition between timer_shutdown_sync() and timer
expiration that can lead to hitting a WARN_ON in expire_timers().

The issue occurs when timer_shutdown_sync() clears the timer function
to NULL while the timer is still running on another CPU. The race
scenario looks like this:

CPU0					CPU1
					<SOFTIRQ>
					lock_timer_base()
					expire_timers()
					base->running_timer = timer;
					unlock_timer_base()
					[call_timer_fn enter]
					mod_timer()
					...
timer_shutdown_sync()
lock_timer_base()
// For now, will not detach the timer but only clear its function to NULL
if (base->running_timer != timer)
	ret = detach_if_pending(timer, base, true);
if (shutdown)
	timer->function = NULL;
unlock_timer_base()
					[call_timer_fn exit]
					lock_timer_base()
					base->running_timer = NULL;
					unlock_timer_base()
					...
					// Now timer is pending while its function set to NULL.
					// next timer trigger
					<SOFTIRQ>
					expire_timers()
					WARN_ON_ONCE(!fn) // hit
					...
lock_timer_base()
// Now timer will detach
if (base->running_timer != timer)
	ret = detach_if_pending(timer, base, true);
if (shutdown)
	timer->function = NULL;
unlock_timer_base()

The problem is that timer_shutdown_sync() clears the timer function
regardless of whether the timer is currently running. This can leave a
pending timer with a NULL function pointer, which triggers the
WARN_ON_ONCE(!fn) check in expire_timers().

Fix this by only clearing the timer function when actually detaching the
timer. If the timer is running, leave the function pointer intact, which is
safe because the timer will be properly detached when it finishes running.

Fixes: 0cc04e80458a ("timers: Add shutdown mechanism to the internal functions")
Signed-off-by: Yipeng Zou <zouyipeng@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20251122093942.301559-1-zouyipeng@huawei.com
2025-11-22 22:55:26 +01:00
Malaya Kumar Rout
7b5ab04f03 timekeeping: Fix resource leak in tk_aux_sysfs_init() error paths
tk_aux_sysfs_init() returns immediately on error during the auxiliary clock
initialization loop without cleaning up previously allocated kobjects and
sysfs groups.

If kobject_create_and_add() or sysfs_create_group() fails during loop
iteration, the parent kobjects (tko and auxo) and any previously created
child kobjects are leaked.

Fix this by adding proper error handling with goto labels to ensure all
allocated resources are cleaned up on failure. kobject_put() on the
parent kobjects will handle cleanup of their children.

Fixes: 7b95663a3d96 ("timekeeping: Provide interface to control auxiliary clocks")
Signed-off-by: Malaya Kumar Rout <mrout@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://patch.msgid.link/20251120150213.246777-1-mrout@redhat.com
2025-11-20 16:40:48 +01:00
Dapeng Mi
f1f96511b1 perf: Fix 0 count issue of cpu-clock
Currently cpu-clock event always returns 0 count, e.g.,

perf stat -e cpu-clock -- sleep 1

 Performance counter stats for 'sleep 1':
                 0      cpu-clock                        #    0.000 CPUs utilized
       1.002308394 seconds time elapsed

The root cause is the commit 'bc4394e5e79c ("perf: Fix the throttle
 error of some clock events")' adds PERF_EF_UPDATE flag check before
calling cpu_clock_event_update() to update the count, however the
PERF_EF_UPDATE flag is never set when the cpu-clock event is stopped in
counting mode (pmu->dev() -> cpu_clock_event_del() ->
cpu_clock_event_stop()). This leads to the cpu-clock event count is
never updated.

To fix this issue, force to set PERF_EF_UPDATE flag for cpu-clock event
just like what task-clock does.

Fixes: bc4394e5e79c ("perf: Fix the throttle error of some clock events")
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://patch.msgid.link/20251112080526.3971392-1-dapeng1.mi@linux.intel.com
2025-11-20 10:42:12 +01:00
Wen Yang
807e0d187d tick/sched: Fix bogus condition in report_idle_softirq()
In commit 0345691b24c0 ("tick/rcu: Stop allowing RCU_SOFTIRQ in idle") the
new function report_idle_softirq() was created by breaking code out of the
existing can_stop_idle_tick() for kernels v5.18 and newer.

In doing so, the code essentially went from this form:

	if (A) {
		static int ratelimit;
		if (ratelimit < 10 && !C && A&D) {
                       pr_warn("NOHZ tick-stop error: ...");
		       ratelimit++;
		}
		return false;
	}

to a new function:

static bool report_idle_softirq(void)
{
       static int ratelimit;

       if (likely(!A))
               return false;

       if (ratelimit < 10)
               return false;
...
       pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
               pending);
       ratelimit++;

       return true;
}

commit a7e282c77785 ("tick/rcu: Fix bogus ratelimit condition") realized
ratelimit was essentially set to zero instead of ten, and hence *no*
softirq pending messages would ever be issued, but "fixed" it as:

-       if (ratelimit < 10)
+       if (ratelimit >= 10)
                return false;

However, this fix introduced another issue:

When ratelimit is greater than or equal 10, even if A is true, it will
directly return false. While ratelimit in the original code was only used
to control printing and will not affect the return value.

Restore the original logic and restrict ratelimit to control the printk and
not the return value.

Fixes: 0345691b24c0 ("tick/rcu: Stop allowing RCU_SOFTIRQ in idle")
Fixes: a7e282c77785 ("tick/rcu: Fix bogus ratelimit condition")
Signed-off-by: Wen Yang <wen.yang@linux.dev>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://patch.msgid.link/20251119174525.29470-1-wen.yang@linux.dev
2025-11-19 19:30:45 +01:00
Jiri Slaby (SUSE)
a24074ca88 perf/x86/intel/uncore: Remove superfluous check
The 'pmu' pointer cannot be NULL, as it is taken as a pointer to an array.
Remove the superfluous NULL check.

Found by Coverity: CID#1497507.

Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Liang Kan <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20251119091538.825307-1-jirislaby@kernel.org
2025-11-19 10:26:31 +01:00
5 changed files with 22 additions and 21 deletions

View File

@ -1325,8 +1325,6 @@ static void uncore_pci_sub_driver_init(void)
continue;
pmu = &type->pmus[UNCORE_PCI_DEV_IDX(ids->driver_data)];
if (!pmu)
continue;
if (uncore_pci_get_dev_die_info(pci_sub_dev, &die))
continue;

View File

@ -11901,7 +11901,7 @@ static int cpu_clock_event_add(struct perf_event *event, int flags)
static void cpu_clock_event_del(struct perf_event *event, int flags)
{
cpu_clock_event_stop(event, flags);
cpu_clock_event_stop(event, PERF_EF_UPDATE);
}
static void cpu_clock_event_read(struct perf_event *event)

View File

@ -1152,16 +1152,15 @@ static bool report_idle_softirq(void)
return false;
}
if (ratelimit >= 10)
return false;
/* On RT, softirq handling may be waiting on some lock */
if (local_bh_blocked())
return false;
pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
pending);
ratelimit++;
if (ratelimit < 10) {
pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
pending);
ratelimit++;
}
return true;
}

View File

@ -3060,29 +3060,32 @@ static const struct attribute_group aux_clock_enable_attr_group = {
static int __init tk_aux_sysfs_init(void)
{
struct kobject *auxo, *tko = kobject_create_and_add("time", kernel_kobj);
int ret = -ENOMEM;
if (!tko)
return -ENOMEM;
return ret;
auxo = kobject_create_and_add("aux_clocks", tko);
if (!auxo) {
kobject_put(tko);
return -ENOMEM;
}
if (!auxo)
goto err_clean;
for (int i = 0; i < MAX_AUX_CLOCKS; i++) {
char id[2] = { [0] = '0' + i, };
struct kobject *clk = kobject_create_and_add(id, auxo);
if (!clk)
return -ENOMEM;
int ret = sysfs_create_group(clk, &aux_clock_enable_attr_group);
goto err_clean;
ret = sysfs_create_group(clk, &aux_clock_enable_attr_group);
if (ret)
return ret;
goto err_clean;
}
return 0;
err_clean:
kobject_put(auxo);
kobject_put(tko);
return ret;
}
late_initcall(tk_aux_sysfs_init);

View File

@ -1458,10 +1458,11 @@ static int __try_to_del_timer_sync(struct timer_list *timer, bool shutdown)
base = lock_timer_base(timer, &flags);
if (base->running_timer != timer)
if (base->running_timer != timer) {
ret = detach_if_pending(timer, base, true);
if (shutdown)
timer->function = NULL;
if (shutdown)
timer->function = NULL;
}
raw_spin_unlock_irqrestore(&base->lock, flags);