x86: avoid calling arch_trigger_all_cpu_backtrace() at the same time on SMP
PATCH 1/1 x86: avoid calling arch_trigger_all_cpu_backtrace() at the same time on SMP
From: Dongdong Deng <[email protected]>
The spin_lock_debug/rcu_cpu_stall detector uses trigger_all_cpu_backtrace() to dump cpu backtrace. Therefore it is possible that trigger_all_cpu_backtrace() could be called at the same time on different CPUs, which triggers and 'unknown reason NMI' warning. The following case illustrates the problem:
CPU1 CPU2 ... CPU N
trigger_all_cpu_backtrace()
set "backtrace_mask" to cpu mask
|
generate NMI interrupts generate NMI interrupts ...
\ | /
\ | /
The "backtrace_mask" will be cleaned by the first NMI interrupt
at nmi_watchdog_tick(), then the following NMI interrupts generated
by other cpus's arch_trigger_all_cpu_backtrace() will be took as unknown reason NMI interrupts.
This patch uses a lock to avoid the problem, and stop the arch_trigger_all_cpu_backtrace() calling to avoid dumping double cpu backtrace info when there is already a trigger_all_cpu_backtrace() in progress.
--- arch/x86/kernel/apic/hw_nmi.c | 14 ++++++++++++++ arch/x86/kernel/apic/nmi.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+), 0 deletions(-)
arch/x86/kernel/apic/hw_nmi.c +14 -0
@@ -29,6 +29,16 @@ u64 hw_nmi_get_sample_period(void)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; +unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);
@@ -41,6 +51,10 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags); } static int __kprobes
arch/x86/kernel/apic/nmi.c +14 -0
@@ -552,6 +552,16 @@ int do_nmi_callback(struct pt_regs *regs, int cpu)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; +unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);
@@ -564,4 +574,8 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags); }
Signature · 1 line
1.7.2.3
Quoted 44 lines · Don Zickus
From: Dongdong Deng <[email protected]>
The spin_lock_debug/rcu_cpu_stall detector uses
trigger_all_cpu_backtrace()to dump cpu backtrace. Therefore it is possible thattrigger_all_cpu_backtrace()could be called at the same time on different CPUs, which triggers and 'unknown reason NMI' warning. The following case illustrates the problem:CPU1 CPU2 ... CPU N
trigger_all_cpu_backtrace()
set "backtrace_mask" to cpu mask
|
generate NMI interrupts generate NMI interrupts ...
\ | /
\ | /
The "backtrace_mask" will be cleaned by the first NMI interrupt
atnmi_watchdog_tick(), then the following NMI interrupts generated
by other cpus'sarch_trigger_all_cpu_backtrace()will be took as unknown reason NMI interrupts.This patch uses a lock to avoid the problem, and stop the
arch_trigger_all_cpu_backtrace()calling to avoid dumping double cpu backtrace info when there is already atrigger_all_cpu_backtrace()in progress.Signed-off-by Dongdong Deng <[email protected]>Reviewed-by Bruce Ashfield <[email protected]>CC Thomas Gleixner <[email protected]>CC Ingo Molnar <[email protected]>CC "H. Peter Anvin" <[email protected]>Signed-off-by Don Zickus <[email protected]>--- arch/x86/kernel/apic/hw_nmi.c | 14 ++++++++++++++ arch/x86/kernel/apic/nmi.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+), 0 deletions(-)arch/x86/kernel/apic/hw_nmi.c +0
-0
arch/x86/kernel/apic/hw_nmi.c u64 hw_nmi_get_sample_period(void) · line 32
Quoted 4 lines
arch/x86/kernel/apic/hw_nmi.c +1
-0@@ -29,6 +29,16 @@ u64 hw_nmi_get_sample_period(void)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
Please dont put statics into the middle of local variables - put them into file scope in a visible way.
Quoted 45 lines
arch/x86/kernel/apic/hw_nmi.c +13
-0+unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);@@ -41,6 +51,10 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags); } static int __kprobesarch/x86/kernel/apic/nmi.c +10
-0@@ -552,6 +552,16 @@ int do_nmi_callback(struct pt_regs *regs, int cpu)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; +unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);
arch/x86/kernel/apic/nmi.c void arch_trigger_all_cpu_backtrace(void) · line 580
Quoted 7 lines
arch/x86/kernel/apic/nmi.c +4
-0@@ -564,4 +574,8 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags);
This spinlock is never actually used as a spinlock - it's a "in progress" flag. Why not use a flag and test_and_set_bit()?
Also, the irq disabling really needed, will this code ever be called with irqs on?
Thanks,
Ingo
Quoted 41 lines · Ingo Molnar
Quoted 39 lines · Don Zickus
From: Dongdong Deng <[email protected]>
The spin_lock_debug/rcu_cpu_stall detector uses
trigger_all_cpu_backtrace()to dump cpu backtrace. Therefore it is possible thattrigger_all_cpu_backtrace()could be called at the same time on different CPUs, which triggers and 'unknown reason NMI' warning. The following case illustrates the problem:CPU1 CPU2 ... CPU N
trigger_all_cpu_backtrace()
set "backtrace_mask" to cpu mask
|
generate NMI interrupts generate NMI interrupts ...
\ | /
\ | /
The "backtrace_mask" will be cleaned by the first NMI interrupt
atnmi_watchdog_tick(), then the following NMI interrupts generated
by other cpus'sarch_trigger_all_cpu_backtrace()will be took as unknown reason NMI interrupts.This patch uses a lock to avoid the problem, and stop the
arch_trigger_all_cpu_backtrace()calling to avoid dumping double cpu backtrace info when there is already atrigger_all_cpu_backtrace()in progress.Signed-off-by Dongdong Deng <[email protected]>Reviewed-by Bruce Ashfield <[email protected]>CC Thomas Gleixner <[email protected]>CC Ingo Molnar <[email protected]>CC "H. Peter Anvin" <[email protected]>Signed-off-by Don Zickus <[email protected]>--- arch/x86/kernel/apic/hw_nmi.c | 14 ++++++++++++++ arch/x86/kernel/apic/nmi.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+), 0 deletions(-)
Quoted 11 lines
arch/x86/kernel/apic/hw_nmi.c u64 hw_nmi_get_sample_period(void) · line 32
Quoted 9 lines
arch/x86/kernel/apic/hw_nmi.c +1
-0@@ -29,6 +29,16 @@ u64 hw_nmi_get_sample_period(void)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;Please dont put statics into the middle of local variables - put them into file scope in a visible way.
Got it. will change it.
Quoted 45 lines
Quoted 45 lines
arch/x86/kernel/apic/hw_nmi.c +13
-0+unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);@@ -41,6 +51,10 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags); } static int __kprobesarch/x86/kernel/apic/nmi.c +10
-0@@ -552,6 +552,16 @@ int do_nmi_callback(struct pt_regs *regs, int cpu)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; +unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);
Quoted 10 lines
arch/x86/kernel/apic/nmi.c void arch_trigger_all_cpu_backtrace(void) · line 580
Quoted 8 lines
arch/x86/kernel/apic/nmi.c +4
-0@@ -564,4 +574,8 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags);This spinlock is never actually used as a spinlock - it's a "in progress" flag. Why not use a flag and
test_and_set_bit()?
Yep, it's a "in progress" flag, I will change to use a flag to replace the spinlock.
Quoted 1 line
Also, the irq disabling really needed, will this code ever be called with irqs on?
This code could be called with irqs on.
If the arch_trigger_all_cpu_backtrace() was triggered by "spin_lock()"'s spin_lock_debug detector, it is possible that the irq is enabled, thus we have to save and disable it here.
Thanks,
Dongdong
Quoted 5 lines
Thanks,
Ingo
Quoted 109 lines · DDD
Quoted 41 lines · Ingo Molnar
Quoted 39 lines · Don Zickus
From: Dongdong Deng <[email protected]>
The spin_lock_debug/rcu_cpu_stall detector uses
trigger_all_cpu_backtrace()to dump cpu backtrace. Therefore it is possible thattrigger_all_cpu_backtrace()could be called at the same time on different CPUs, which triggers and 'unknown reason NMI' warning. The following case illustrates the problem:CPU1 CPU2 ... CPU N
trigger_all_cpu_backtrace()
set "backtrace_mask" to cpu mask
|
generate NMI interrupts generate NMI interrupts ...
\ | /
\ | /
The "backtrace_mask" will be cleaned by the first NMI interrupt
atnmi_watchdog_tick(), then the following NMI interrupts generated
by other cpus'sarch_trigger_all_cpu_backtrace()will be took as unknown reason NMI interrupts.This patch uses a lock to avoid the problem, and stop the
arch_trigger_all_cpu_backtrace()calling to avoid dumping double cpu backtrace info when there is already atrigger_all_cpu_backtrace()in progress.Signed-off-by Dongdong Deng <[email protected]>Reviewed-by Bruce Ashfield <[email protected]>CC Thomas Gleixner <[email protected]>CC Ingo Molnar <[email protected]>CC "H. Peter Anvin" <[email protected]>Signed-off-by Don Zickus <[email protected]>---
arch/x86/kernel/apic/hw_nmi.c | 14 ++++++++++++++ arch/x86/kernel/apic/nmi.c | 14 ++++++++++++++ 2 files changed, 28 insertions(+), 0 deletions(-)Quoted 12 lines
arch/x86/kernel/apic/hw_nmi.c u64 hw_nmi_get_sample_period(void) · line 32
Quoted 9 lines
arch/x86/kernel/apic/hw_nmi.c +1
-0@@ -29,6 +29,16 @@ u64 hw_nmi_get_sample_period(void)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;Please dont put statics into the middle of local variables - put them into file scope in a visible way.
Got it. will change it.
Quoted 43 lines
Quoted 43 lines
arch/x86/kernel/apic/hw_nmi.c +13
-0+unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);@@ -41,6 +51,10 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 ); } + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags); }static int
__kprobesarch/x86/kernel/apic/nmi.c +10
-0@@ -552,6 +552,16 @@ int do_nmi_callback(struct pt_regs *regs, int cpu)void arch_trigger_all_cpu_backtrace (void ) {int i; +static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED; +unsigned long flags; + +local_irq_save (flags); +if (!arch_spin_trylock (&lock)) +/* +* If there is already a trigger_all_cpu_backtrace() +* in progress, don't output double cpu dump infos. +*/ + goto out_restore_irq;cpumask_copy (to_cpumask (backtrace_mask), cpu_online_mask);@@ -564,4 +574,8 @@ void arch_trigger_all_cpu_backtrace(void)break ;mdelay (1 );Quoted 8 lines
arch/x86/kernel/apic/nmi.c void arch_trigger_all_cpu_backtrace(void) · line 580
Quoted 5 lines
arch/x86/kernel/apic/nmi.c +4
-0} + +arch_spin_unlock (&lock); +out_restore_irq: +local_irq_restore (flags);This spinlock is never actually used as a spinlock - it's a "in progress" flag. Why not use a flag and
test_and_set_bit()?
Quoted 2 lines
Yep, it's a "in progress" flag, I will change to use a flag to replace the spinlock.
Thanks.
Quoted 7 lines
Quoted 1 line
Also, the irq disabling really needed, will this code ever be called with irqs on?
This code could be called with irqs on.
If the
arch_trigger_all_cpu_backtrace()was triggered by "spin_lock()"'sspin_lock_debugdetector, it is possible that the irq is enabled, thus we have to save and disable it here.
Ok - please document that fact in the code.
Thanks,
Ingo