From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: "Yan, Zheng" <zheng.z.yan@intel.com>
Cc: mingo@elte.hu, andi@firstfloor.org, eranian@google.com,
linux-kernel@vger.kernel.org, ming.m.lin@intel.com
Subject: Re: [PATCH 2/5] perf: generic intel uncore support
Date: Mon, 16 Apr 2012 14:07:54 +0200 [thread overview]
Message-ID: <1334578074.28150.38.camel@twins> (raw)
In-Reply-To: <4F77C75B.4060105@intel.com>
On Sun, 2012-04-01 at 11:11 +0800, Yan, Zheng wrote:
> Any hints how to do this. I'm afraid it requires big changes to perf core.
Sorry for taking so long..
I think something like the (completely untested) below should suffice..
In your driver, have hotplug notifiers keep track of what cpu is the
active cpu for your node, if it needs to change due to it going offline,
pick a new one and use the below function to migrate the events.
The only missing piece is not doing the normal
perf_event_exit_cpu_context() thing for these PMUs, except of course
once there's no cpus left in your node.
Doing that might want an extra struct pmu method, which if not set
defaults to perf_event_exit_cpu_context, and otherwise does your custom
migrate/exit.
---
kernel/events/core.c | 33 +++++++++++++++++++++++++++++++++
1 files changed, 33 insertions(+), 0 deletions(-)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a6a9ec4..824becf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1641,6 +1641,8 @@ perf_install_in_context(struct perf_event_context *ctx,
lockdep_assert_held(&ctx->mutex);
event->ctx = ctx;
+ if (event->cpu != -1)
+ event->cpu = cpu;
if (!task) {
/*
@@ -6375,6 +6377,8 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_lock(&ctx->mutex);
if (move_group) {
+ synchronize_rcu();
+
perf_install_in_context(ctx, group_leader, cpu);
get_ctx(ctx);
list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -6477,6 +6481,35 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
}
EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
+void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
+{
+ struct perf_cpu_context *src_cpuctx = per_cpu(pmu->pmu_cpu_context, src_cpu);
+ struct perf_cpu_context *dst_cpuctx = per_cpu(pmu->pmu_cpu_context, dst_cpu);
+ struct perf_event_context *src_ctx = &src_cpuctx->ctx;
+ struct perf_event_context *dst_ctx = &dst_cpuctx->ctx;
+ struct perf_event *event, *tmp;
+ LIST_HEAD(events);
+
+ mutex_lock(&src_ctx->mutex);
+ list_for_each_entry_safe(event, tmp, &src_ctx->event_list, event_entry) {
+ perf_remove_from_context(event);
+ put_ctx(src_ctx);
+ list_add(&event->event_entry, &events);
+ }
+ mutex_unlock(&src_ctx->mutex);
+
+ synchronize_rcu();
+
+ mutex_lock(&dst_ctx->mutex);
+ list_for_each_entry_safe(event, tmp, &events, event_entry) {
+ list_del(&event->event_entry);
+ perf_install_in_context(dst_ctx, event, dst_cpu);
+ get_ctx(dst_ctx);
+ }
+ mutex_unlock(&dst_ctx->mutex);
+}
+EXPORT_SYMBOL_GPL(perf_pmu_migrate_context);
+
static void sync_child_event(struct perf_event *child_event,
struct task_struct *child)
{
next prev parent reply other threads:[~2012-04-16 12:08 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-03-28 6:43 [RFC PATCH 0/5] perf: Intel uncore pmu counting support Yan, Zheng
2012-03-28 6:43 ` [PATCH 1/5] perf: Export perf_assign_events Yan, Zheng
2012-03-28 6:43 ` [PATCH 2/5] perf: generic intel uncore support Yan, Zheng
2012-03-28 9:24 ` Andi Kleen
2012-03-28 9:38 ` Peter Zijlstra
2012-03-28 11:24 ` Yan, Zheng
2012-03-31 3:18 ` Peter Zijlstra
2012-04-01 3:11 ` Yan, Zheng
2012-04-02 22:10 ` Peter Zijlstra
2012-04-02 22:11 ` Peter Zijlstra
2012-04-03 8:28 ` Yan, Zheng
2012-04-03 14:29 ` Peter Zijlstra
2012-04-04 1:47 ` Yan, Zheng
2012-04-10 0:48 ` Yan, Zheng
2012-04-16 12:11 ` Peter Zijlstra
2012-04-02 22:16 ` Peter Zijlstra
2012-04-02 22:24 ` Peter Zijlstra
2012-04-16 12:07 ` Peter Zijlstra [this message]
2012-04-17 6:56 ` Yan, Zheng
2012-03-28 6:43 ` [PATCH 3/5] perf: Add Nehalem and Sandy Bridge " Yan, Zheng
2012-03-28 6:43 ` [PATCH 4/5] perf: Generic pci uncore device support Yan, Zheng
2012-03-28 6:43 ` [PATCH 5/5] perf: Add Sandy Bridge-EP uncore support Yan, Zheng
2012-03-28 6:49 ` [RFC PATCH 0/5] perf: Intel uncore pmu counting support Ingo Molnar
2012-03-28 8:49 ` Peter Zijlstra
2012-03-28 9:02 ` Yan, Zheng
2012-03-28 8:57 ` Andi Kleen
2012-03-28 9:30 ` Ingo Molnar
2012-03-28 10:58 ` Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1334578074.28150.38.camel@twins \
--to=a.p.zijlstra@chello.nl \
--cc=andi@firstfloor.org \
--cc=eranian@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.m.lin@intel.com \
--cc=mingo@elte.hu \
--cc=zheng.z.yan@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox