| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sun, 4 Apr 2010 16:50:03 +0200
From: Frederic Weisbecker <fweisbec@...il.com>
To: Ingo Molnar <mingo@...e.hu>
Cc: LKML <linux-kernel@...r.kernel.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Steven Rostedt <rostedt@...dmis.org>
Subject: Re: [PATCH v3] lockdep: Make lockstats counting per cpu
On Sun, Mar 28, 2010 at 01:29:57AM +0100, Frederic Weisbecker wrote:
> Locking statistics are implemented using global atomic variables.
> This is usually fine unless some path write them very often.
>
> This is the case for the function and function graph tracers
> that disable irqs for each entry saved (except if the function
> tracer is in preempt disabled only mode).
> And calls to local_irq_save/restore() increment hardirqs_on_events
> and hardirqs_off_events stats (or similar stats for redundant
> versions).
>
> Incrementing these global vars for each function ends up in too
> much cache bouncing if lockstats are enabled.
>
> To solve this, implement the debug_atomic_*() operations using
> per cpu vars.
>
> v2: Use per_cpu() instead of get_cpu_var() to fetch the desired
> cpu vars on debug_atomic_read()
>
> v3: Store the stats in a structure. No need for local_t as we
> are NMI/irq safe.
>
> Suggested-by: Steven Rostedt <rostedt@...dmis.org>
> Signed-off-by: Frederic Weisbecker <fweisbec@...il.com>
> Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
> Cc: Steven Rostedt <rostedt@...dmis.org>
Quick ping.
No problem with this patch?
Thanks.
> ---
> kernel/lockdep.c | 15 +--------
> kernel/lockdep_internals.h | 74 +++++++++++++++++++++++++++++++------------
> 2 files changed, 54 insertions(+), 35 deletions(-)
>
> diff --git a/kernel/lockdep.c b/kernel/lockdep.c
> index 65b5f5b..3434c81 100644
> --- a/kernel/lockdep.c
> +++ b/kernel/lockdep.c
> @@ -430,20 +430,7 @@ static struct stack_trace lockdep_init_trace = {
> /*
> * Various lockdep statistics:
> */
> -atomic_t chain_lookup_hits;
> -atomic_t chain_lookup_misses;
> -atomic_t hardirqs_on_events;
> -atomic_t hardirqs_off_events;
> -atomic_t redundant_hardirqs_on;
> -atomic_t redundant_hardirqs_off;
> -atomic_t softirqs_on_events;
> -atomic_t softirqs_off_events;
> -atomic_t redundant_softirqs_on;
> -atomic_t redundant_softirqs_off;
> -atomic_t nr_unused_locks;
> -atomic_t nr_cyclic_checks;
> -atomic_t nr_find_usage_forwards_checks;
> -atomic_t nr_find_usage_backwards_checks;
> +DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
> #endif
>
> /*
> diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h
> index a2ee95a..ccc18f6 100644
> --- a/kernel/lockdep_internals.h
> +++ b/kernel/lockdep_internals.h
> @@ -110,29 +110,61 @@ lockdep_count_backward_deps(struct lock_class *class)
> #endif
>
> #ifdef CONFIG_DEBUG_LOCKDEP
> +
> +#include <asm/local.h>
> /*
> - * Various lockdep statistics:
> + * Various lockdep statistics.
> + * We want them per cpu as they are often accessed in fast path
> + * and we want to avoid too much cache bouncing.
> */
> -extern atomic_t chain_lookup_hits;
> -extern atomic_t chain_lookup_misses;
> -extern atomic_t hardirqs_on_events;
> -extern atomic_t hardirqs_off_events;
> -extern atomic_t redundant_hardirqs_on;
> -extern atomic_t redundant_hardirqs_off;
> -extern atomic_t softirqs_on_events;
> -extern atomic_t softirqs_off_events;
> -extern atomic_t redundant_softirqs_on;
> -extern atomic_t redundant_softirqs_off;
> -extern atomic_t nr_unused_locks;
> -extern atomic_t nr_cyclic_checks;
> -extern atomic_t nr_cyclic_check_recursions;
> -extern atomic_t nr_find_usage_forwards_checks;
> -extern atomic_t nr_find_usage_forwards_recursions;
> -extern atomic_t nr_find_usage_backwards_checks;
> -extern atomic_t nr_find_usage_backwards_recursions;
> -# define debug_atomic_inc(ptr) atomic_inc(ptr)
> -# define debug_atomic_dec(ptr) atomic_dec(ptr)
> -# define debug_atomic_read(ptr) atomic_read(ptr)
> +struct lockdep_stats {
> + int chain_lookup_hits;
> + int chain_lookup_misses;
> + int hardirqs_on_events;
> + int hardirqs_off_events;
> + int redundant_hardirqs_on;
> + int redundant_hardirqs_off;
> + int softirqs_on_events;
> + int softirqs_off_events;
> + int redundant_softirqs_on;
> + int redundant_softirqs_off;
> + int nr_unused_locks;
> + int nr_cyclic_checks
> + int nr_cyclic_check_recursions;
> + int nr_find_usage_forwards_checks;
> + int nr_find_usage_forwards_recursions;
> + int nr_find_usage_backwards_checks;
> + int nr_find_usage_backwards_recursions;
> +};
> +
> +DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats);
> +
> +#define debug_atomic_inc(ptr) { \
> + struct lockdep_stats *__cpu_lockdep_stats; \
> + \
> + WARN_ON_ONCE(!irq_disabled()); \
> + __cpu_lockdep_stats = &__get_cpu_var(lockdep_stats); \
> + __cpu_lockdep_stats->ptr++; \
> +}
> +
> +#define debug_atomic_dec(ptr) { \
> + struct lockdep_stats *__cpu_lockdep_stats; \
> + \
> + WARN_ON_ONCE(!irq_disabled()); \
> + __cpu_lockdep_stats = &__get_cpu_var(lockdep_stats); \
> + __cpu_lockdep_stats->ptr--; \
> +}
> +
> +#define debug_atomic_read(ptr) ({ \
> + struct lockdep_stats *__cpu_lockdep_stats; \
> + unsigned long long __total = 0; \
> + int __cpu; \
> + for_each_possible_cpu(__cpu) { \
> + __cpu_lockdep_stats = &per_cpu(lockdep_stats, cpu); \
> + __total += __cpu_lockdep_stats->ptr; \
> + } \
> + __total; \
> +})
> #else
> # define debug_atomic_inc(ptr) do { } while (0)
> # define debug_atomic_dec(ptr) do { } while (0)
> --
> 1.6.2.3
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists