When enable preempt and debug ftrace, and perform the following steps, the
system will hang:
mount -t debugfs nodev /sys/kernel/debug/
cd /sys/kernel/debug/tracing/
echo function_graph > current_tracer
This is because tracing the preempt_disable/enable calls would cause
trace_clock() which would get local timer to go into infinite recursion
when enable the arch timer erratum workaround for some chips, so Prevent
tracing of preempt_disable/enable() in arch_timer_reg_read_stable().
This problem is similar to the fixed by upstream commit 96b3d28bf4
("sched/clock: Prevent tracing recursion in sched_clock_cpu()").
Fixes: 6acc71ccac71 ("arm64: arch_timer: Allows a CPU-specific erratum to only affect a subset of CPUs")
Signed-off-by: Ding Tianhong <[email protected]>
---
arch/arm64/include/asm/arch_timer.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 74d08e4..67bb7a4 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -65,13 +65,13 @@ struct arch_timer_erratum_workaround {
u64 _val; \
if (needs_unstable_timer_counter_workaround()) { \
const struct arch_timer_erratum_workaround *wa; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
wa = __this_cpu_read(timer_unstable_counter_workaround); \
if (wa && wa->read_##reg) \
_val = wa->read_##reg(); \
else \
_val = read_sysreg(reg); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
} else { \
_val = read_sysreg(reg); \
} \
--
1.9.0
On 2017/7/9 16:30, Ding Tianhong wrote:
> When enable preempt and debug ftrace, and perform the following steps, the
> system will hang:
> mount -t debugfs nodev /sys/kernel/debug/
> cd /sys/kernel/debug/tracing/
> echo function_graph > current_tracer
>
> This is because tracing the preempt_disable/enable calls would cause
> trace_clock() which would get local timer to go into infinite recursion
> when enable the arch timer erratum workaround for some chips, so Prevent
> tracing of preempt_disable/enable() in arch_timer_reg_read_stable().
>
> This problem is similar to the fixed by upstream commit 96b3d28bf4
> ("sched/clock: Prevent tracing recursion in sched_clock_cpu()").
>
> Fixes: 6acc71ccac71 ("arm64: arch_timer: Allows a CPU-specific erratum to only affect a subset of CPUs")
> Signed-off-by: Ding Tianhong <[email protected]>
> ---
> arch/arm64/include/asm/arch_timer.h | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
> index 74d08e4..67bb7a4 100644
> --- a/arch/arm64/include/asm/arch_timer.h
> +++ b/arch/arm64/include/asm/arch_timer.h
> @@ -65,13 +65,13 @@ struct arch_timer_erratum_workaround {
> u64 _val; \
> if (needs_unstable_timer_counter_workaround()) { \
> const struct arch_timer_erratum_workaround *wa; \
> - preempt_disable(); \
> + preempt_disable_notrace(); \
> wa = __this_cpu_read(timer_unstable_counter_workaround); \
> if (wa && wa->read_##reg) \
> _val = wa->read_##reg(); \
> else \
> _val = read_sysreg(reg); \
> - preempt_enable(); \
> + preempt_enable_notrace(); \
> } else { \
> _val = read_sysreg(reg); \
> } \
This fixes my system hang issue when I using function tracer with
enabled timer errata on D03,
Tested-by: Hanjun Guo <[email protected]>
Thanks
Hanjun
On Sun, Jul 09, 2017 at 04:30:54PM +0800, Ding Tianhong wrote:
> When enable preempt and debug ftrace, and perform the following steps, the
> system will hang:
> mount -t debugfs nodev /sys/kernel/debug/
> cd /sys/kernel/debug/tracing/
> echo function_graph > current_tracer
>
> This is because tracing the preempt_disable/enable calls would cause
> trace_clock() which would get local timer to go into infinite recursion
> when enable the arch timer erratum workaround for some chips, so Prevent
> tracing of preempt_disable/enable() in arch_timer_reg_read_stable().
>
> This problem is similar to the fixed by upstream commit 96b3d28bf4
> ("sched/clock: Prevent tracing recursion in sched_clock_cpu()").
As I mentioned before, the patch itself looks fine to me, but the commit
message is somewhat difficult to read.
Can we please change this to:
arm64: arch_timer: avoid infinite recursion when ftrace is enabled
On platforms with an arch timer erratum workaround, it's possible for
arch_timer_reg_read_stable() to recurse into itself when certain
tracing options are enabled, leading to stack overflows and related
problems.
For example, when PREEMPT_TRACER and FUNCTION_GRAPH_TRACER are
selected, it's possible to trigger this with:
$ mount -t debugfs nodev /sys/kernel/debug/
$ echo function_graph > /sys/kernel/debug/tracing/current_tracer
The problem is that in such cases, preempt_disable() instrumentation
attempts to acquire a timestamp via trace_clock(), resulting in a call
back to arch_timer_reg_read_stable(), and hence recursion.
This patch changes arch_timer_reg_read_stable() to use
preempt_{disable,enable}_notrace(), which avoids this.
With that commit message:
Acked-by: Mark Rutland <[email protected]>
Daniel, Thomas, would you be happy to fold that in when picking this? Or
would you prefer that I fix this up and resend?
Thanks,
Mark.
> Fixes: 6acc71ccac71 ("arm64: arch_timer: Allows a CPU-specific erratum to only affect a subset of CPUs")
> Signed-off-by: Ding Tianhong <[email protected]>
> ---
> arch/arm64/include/asm/arch_timer.h | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
> index 74d08e4..67bb7a4 100644
> --- a/arch/arm64/include/asm/arch_timer.h
> +++ b/arch/arm64/include/asm/arch_timer.h
> @@ -65,13 +65,13 @@ struct arch_timer_erratum_workaround {
> u64 _val; \
> if (needs_unstable_timer_counter_workaround()) { \
> const struct arch_timer_erratum_workaround *wa; \
> - preempt_disable(); \
> + preempt_disable_notrace(); \
> wa = __this_cpu_read(timer_unstable_counter_workaround); \
> if (wa && wa->read_##reg) \
> _val = wa->read_##reg(); \
> else \
> _val = read_sysreg(reg); \
> - preempt_enable(); \
> + preempt_enable_notrace(); \
> } else { \
> _val = read_sysreg(reg); \
> } \
> --
> 1.9.0
>
>
On 10/07/17 12:22, Mark Rutland wrote:
> On Sun, Jul 09, 2017 at 04:30:54PM +0800, Ding Tianhong wrote:
>> When enable preempt and debug ftrace, and perform the following steps, the
>> system will hang:
>> mount -t debugfs nodev /sys/kernel/debug/
>> cd /sys/kernel/debug/tracing/
>> echo function_graph > current_tracer
>>
>> This is because tracing the preempt_disable/enable calls would cause
>> trace_clock() which would get local timer to go into infinite recursion
>> when enable the arch timer erratum workaround for some chips, so Prevent
>> tracing of preempt_disable/enable() in arch_timer_reg_read_stable().
>>
>> This problem is similar to the fixed by upstream commit 96b3d28bf4
>> ("sched/clock: Prevent tracing recursion in sched_clock_cpu()").
>
> As I mentioned before, the patch itself looks fine to me, but the commit
> message is somewhat difficult to read.
>
> Can we please change this to:
>
> arm64: arch_timer: avoid infinite recursion when ftrace is enabled
>
> On platforms with an arch timer erratum workaround, it's possible for
> arch_timer_reg_read_stable() to recurse into itself when certain
> tracing options are enabled, leading to stack overflows and related
> problems.
>
> For example, when PREEMPT_TRACER and FUNCTION_GRAPH_TRACER are
> selected, it's possible to trigger this with:
>
> $ mount -t debugfs nodev /sys/kernel/debug/
> $ echo function_graph > /sys/kernel/debug/tracing/current_tracer
>
> The problem is that in such cases, preempt_disable() instrumentation
> attempts to acquire a timestamp via trace_clock(), resulting in a call
> back to arch_timer_reg_read_stable(), and hence recursion.
>
> This patch changes arch_timer_reg_read_stable() to use
> preempt_{disable,enable}_notrace(), which avoids this.
>
> With that commit message:
>
> Acked-by: Mark Rutland <[email protected]>
>
> Daniel, Thomas, would you be happy to fold that in when picking this? Or
> would you prefer that I fix this up and resend?
With the proposed changes:
Acked-by: Marc Zyngier <[email protected]>
M.
--
Jazz is not dead. It just smells funny...
On 2017/7/10 19:22, Mark Rutland wrote:
> On Sun, Jul 09, 2017 at 04:30:54PM +0800, Ding Tianhong wrote:
>> When enable preempt and debug ftrace, and perform the following steps, the
>> system will hang:
>> mount -t debugfs nodev /sys/kernel/debug/
>> cd /sys/kernel/debug/tracing/
>> echo function_graph > current_tracer
>>
>> This is because tracing the preempt_disable/enable calls would cause
>> trace_clock() which would get local timer to go into infinite recursion
>> when enable the arch timer erratum workaround for some chips, so Prevent
>> tracing of preempt_disable/enable() in arch_timer_reg_read_stable().
>>
>> This problem is similar to the fixed by upstream commit 96b3d28bf4
>> ("sched/clock: Prevent tracing recursion in sched_clock_cpu()").
>
> As I mentioned before, the patch itself looks fine to me, but the commit
> message is somewhat difficult to read.
>
> Can we please change this to:
>
> arm64: arch_timer: avoid infinite recursion when ftrace is enabled
>
> On platforms with an arch timer erratum workaround, it's possible for
> arch_timer_reg_read_stable() to recurse into itself when certain
> tracing options are enabled, leading to stack overflows and related
> problems.
>
> For example, when PREEMPT_TRACER and FUNCTION_GRAPH_TRACER are
> selected, it's possible to trigger this with:
>
> $ mount -t debugfs nodev /sys/kernel/debug/
> $ echo function_graph > /sys/kernel/debug/tracing/current_tracer
>
> The problem is that in such cases, preempt_disable() instrumentation
> attempts to acquire a timestamp via trace_clock(), resulting in a call
> back to arch_timer_reg_read_stable(), and hence recursion.
>
> This patch changes arch_timer_reg_read_stable() to use
> preempt_{disable,enable}_notrace(), which avoids this.
>
> With that commit message:
>
> Acked-by: Mark Rutland <[email protected]>
>
> Daniel, Thomas, would you be happy to fold that in when picking this? Or
> would you prefer that I fix this up and resend?
>
Hi Danial, Thomas:
It looks didn't merge to the mainline tree yet, should I update the commit and
resend this patch again?
Thanks
Ding
> Thanks,
> Mark.
>
>> Fixes: 6acc71ccac71 ("arm64: arch_timer: Allows a CPU-specific erratum to only affect a subset of CPUs")
>> Signed-off-by: Ding Tianhong <[email protected]>
>> ---
>> arch/arm64/include/asm/arch_timer.h | 4 ++--
>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
>> index 74d08e4..67bb7a4 100644
>> --- a/arch/arm64/include/asm/arch_timer.h
>> +++ b/arch/arm64/include/asm/arch_timer.h
>> @@ -65,13 +65,13 @@ struct arch_timer_erratum_workaround {
>> u64 _val; \
>> if (needs_unstable_timer_counter_workaround()) { \
>> const struct arch_timer_erratum_workaround *wa; \
>> - preempt_disable(); \
>> + preempt_disable_notrace(); \
>> wa = __this_cpu_read(timer_unstable_counter_workaround); \
>> if (wa && wa->read_##reg) \
>> _val = wa->read_##reg(); \
>> else \
>> _val = read_sysreg(reg); \
>> - preempt_enable(); \
>> + preempt_enable_notrace(); \
>> } else { \
>> _val = read_sysreg(reg); \
>> } \
>> --
>> 1.9.0
>>
>>
>
> _______________________________________________
> linux-arm-kernel mailing list
> [email protected]
> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
>
> .
>