| 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
| ||
|
Message-ID: <CABPqkBRBN=Dh07K9++P+0wL-FfDGLw16Mx5qS9fgsJPVdND4qQ@mail.gmail.com>
Date: Wed, 28 Dec 2011 17:55:06 +0000
From: Stephane Eranian <eranian@...gle.com>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: mingo@...e.hu, William Cohen <wcohen@...hat.com>,
linux-kernel@...r.kernel.org, Arun Sharma <asharma@...com>,
Vince Weaver <vince@...ter.net>
Subject: Re: [RFC][PATCH 5/6] perf: Extend the mmap control page with time
(TSC) fields
On Mon, Nov 21, 2011 at 2:51 PM, Peter Zijlstra <a.p.zijlstra@...llo.nl> wrote:
> Extend the mmap control page with fields so that userspace can compute
> time deltas relative to the provided time fields.
>
> Currently only implemented for x86 with constant and nonstop TSC.
>
It is not obvious to me how one would use time_mult, time_shift, time_offset
+ TSC to complement time_enabled/time_running to compute the correct
scaling factor. The patch does not include any example. Woud you mind
describing the method?
Thanks.
> Cc: Stephane Eranian <eranian@...gle.com>
> Cc: Arun Sharma <asharma@...com>
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
> ---
> arch/x86/kernel/cpu/perf_event.c | 14 ++++++++++++++
> include/linux/perf_event.h | 4 +++-
> kernel/events/core.c | 21 ++++++++++++++-------
> 3 files changed, 31 insertions(+), 8 deletions(-)
> Index: linux-2.6/arch/x86/kernel/cpu/perf_event.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/cpu/perf_event.c
> +++ linux-2.6/arch/x86/kernel/cpu/perf_event.c
> @@ -32,6 +32,7 @@
> #include <asm/compat.h>
> #include <asm/smp.h>
> #include <asm/alternative.h>
> +#include <asm/timer.h>
>
> #include "perf_event.h"
>
> @@ -1621,6 +1622,19 @@ static struct pmu pmu = {
> .event_idx = x86_pmu_event_idx,
> };
>
> +void perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
> +{
> + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
> + return;
> +
> + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
> + return;
> +
> + userpg->time_mult = this_cpu_read(cyc2ns);
> + userpg->time_shift = CYC2NS_SCALE_FACTOR;
> + userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
> +}
> +
> /*
> * callchain support
> */
> Index: linux-2.6/include/linux/perf_event.h
> ===================================================================
> --- linux-2.6.orig/include/linux/perf_event.h
> +++ linux-2.6/include/linux/perf_event.h
> @@ -290,12 +290,14 @@ struct perf_event_mmap_page {
> __s64 offset; /* add to hardware event value */
> __u64 time_enabled; /* time event active */
> __u64 time_running; /* time event on cpu */
> + __u32 time_mult, time_shift;
> + __u64 time_offset;
>
> /*
> * Hole for extension of the self monitor capabilities
> */
>
> - __u64 __reserved[123]; /* align to 1k */
> + __u64 __reserved[121]; /* align to 1k */
>
> /*
> * Control data for the mmap() data buffer.
> Index: linux-2.6/kernel/events/core.c
> ===================================================================
> --- linux-2.6.orig/kernel/events/core.c
> +++ linux-2.6/kernel/events/core.c
> @@ -3203,17 +3203,22 @@ static int perf_event_index(struct perf_
> }
>
> static void calc_timer_values(struct perf_event *event,
> + u64 *now,
> u64 *enabled,
> u64 *running)
> {
> - u64 now, ctx_time;
> + u64 ctx_time;
>
> - now = perf_clock();
> - ctx_time = event->shadow_ctx_time + now;
> + *now = perf_clock();
> + ctx_time = event->shadow_ctx_time + *now;
> *enabled = ctx_time - event->tstamp_enabled;
> *running = ctx_time - event->tstamp_running;
> }
>
> +void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
> +{
> +}
> +
> /*
> * Callers need to ensure there can be no nesting of this function, otherwise
> * the seqlock logic goes bad. We can not serialize this because the arch
> @@ -3223,7 +3228,7 @@ void perf_event_update_userpage(struct p
> {
> struct perf_event_mmap_page *userpg;
> struct ring_buffer *rb;
> - u64 enabled, running;
> + u64 enabled, running, now;
>
> rcu_read_lock();
> /*
> @@ -3235,7 +3240,7 @@ void perf_event_update_userpage(struct p
> * because of locking issue as we can be called in
> * NMI context
> */
> - calc_timer_values(event, &enabled, &running);
> + calc_timer_values(event, &now, &enabled, &running);
> rb = rcu_dereference(event->rb);
> if (!rb)
> goto unlock;
> @@ -3260,6 +3265,8 @@ void perf_event_update_userpage(struct p
> userpg->time_running = running +
> atomic64_read(&event->child_total_time_running);
>
> + perf_update_user_clock(userpg, now);
> +
> barrier();
> ++userpg->lock;
> preempt_enable();
> @@ -3692,7 +3699,7 @@ static void perf_output_read_group(struc
> static void perf_output_read(struct perf_output_handle *handle,
> struct perf_event *event)
> {
> - u64 enabled = 0, running = 0;
> + u64 enabled = 0, running = 0, now;
> u64 read_format = event->attr.read_format;
>
> /*
> @@ -3705,7 +3712,7 @@ static void perf_output_read(struct perf
> * NMI context
> */
> if (read_format & PERF_FORMAT_TOTAL_TIMES)
> - calc_timer_values(event, &enabled, &running);
> + calc_timer_values(event, &now, &enabled, &running);
>
> if (event->attr.read_format & PERF_FORMAT_GROUP)
> perf_output_read_group(handle, event, enabled, running);
>
>
--
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