From: "Yan, Zheng" <zheng.z.yan@intel.com>
To: a.p.zijlstra@chello.nl, mingo@elte.hu, andi@firstfloor.org,
eranian@google.com, jolsa@redhat.com, ming.m.lin@intel.com,
gregkh@linuxfoundation.org
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 04/10] perf: Introduce perf_pmu_migrate_context
Date: Wed, 16 May 2012 12:59:57 +0800 [thread overview]
Message-ID: <1337144403-30841-5-git-send-email-zheng.z.yan@intel.com> (raw)
In-Reply-To: <1337144403-30841-1-git-send-email-zheng.z.yan@intel.com>
From: "Yan, Zheng" <zheng.z.yan@intel.com>
Originally from Peter Zijlstra. The helper migrates perf events
from one cpu to another cpu.
Signed-off-by: Zheng Yan <zheng.z.yan@intel.com>
---
include/linux/perf_event.h | 2 ++
kernel/events/core.c | 36 ++++++++++++++++++++++++++++++++++++
2 files changed, 38 insertions(+), 0 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8adf70e..c8abdd2 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1104,6 +1104,8 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr,
struct task_struct *task,
perf_overflow_handler_t callback,
void *context);
+extern void perf_pmu_migrate_context(struct pmu *pmu,
+ int src_cpu, int dst_cpu);
extern u64 perf_event_read_value(struct perf_event *event,
u64 *enabled, u64 *running);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6a2d0b9..2857878 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) {
/*
@@ -6382,6 +6384,7 @@ SYSCALL_DEFINE5(perf_event_open,
mutex_lock(&ctx->mutex);
if (move_group) {
+ synchronize_rcu();
perf_install_in_context(ctx, group_leader, event->cpu);
get_ctx(ctx);
list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -6487,6 +6490,39 @@ 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_event_context *src_ctx;
+ struct perf_event_context *dst_ctx;
+ struct perf_event *event, *tmp;
+ LIST_HEAD(events);
+
+ src_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, src_cpu)->ctx;
+ dst_ctx = &per_cpu_ptr(pmu->pmu_cpu_context, dst_cpu)->ctx;
+
+ 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);
+ if (event->state >= PERF_EVENT_STATE_OFF)
+ event->state = PERF_EVENT_STATE_INACTIVE;
+ 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)
{
--
1.7.7.6
next prev parent reply other threads:[~2012-05-16 5:00 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-16 4:59 [PATCH V4 0/10] perf: Intel uncore pmu counting support Yan, Zheng
2012-05-16 4:59 ` [PATCH 01/10] perf: Export perf_assign_events Yan, Zheng
2012-05-16 4:59 ` [PATCH 02/10] perf: Avoid race between cpu hotplug and installing event Yan, Zheng
2012-05-16 4:59 ` [PATCH 03/10] perf: Allow pmu to choose cpu on which to install event Yan, Zheng
2012-05-16 4:59 ` Yan, Zheng [this message]
2012-05-16 4:59 ` [PATCH 05/10] perf: Generic intel uncore support Yan, Zheng
2012-05-16 4:59 ` [PATCH 06/10] perf: Add Nehalem and Sandy Bridge " Yan, Zheng
2012-05-16 5:00 ` [PATCH 07/10] perf: Generic pci uncore device support Yan, Zheng
2012-05-16 5:00 ` [PATCH 08/10] perf: Add Sandy Bridge-EP uncore support Yan, Zheng
2012-05-16 5:00 ` [PATCH 09/10] perf tool: Make the event parser reentrantable Yan, Zheng
2012-05-16 5:00 ` [PATCH 10/10] perf tool: Add pmu event alias support Yan, Zheng
2012-05-21 7:36 ` [RFC 0/5] perf, tool: uncore related changes Jiri Olsa
2012-05-21 7:36 ` [PATCH 1/5] perf, tool: Use data struct for arg passing in event parse function Jiri Olsa
2012-05-21 7:36 ` [PATCH 2/5] perf, tool: Make the event parser reentrantable Jiri Olsa
2012-05-21 7:36 ` [PATCH 3/5] perf, tool: Add support to reuse event grammar to parse out terms Jiri Olsa
2012-05-21 7:36 ` [PATCH 4/5] perf, tool: Add pmu event alias support Jiri Olsa
2012-05-21 7:36 ` [PATCH 5/5] perf, tool: Add automated test for pure terms parsing Jiri Olsa
2012-05-21 8:22 ` [RFC 0/5] perf, tool: uncore related changes Jiri Olsa
2012-05-23 14:53 ` Stephane Eranian
2012-05-23 15:16 ` Jiri Olsa
2012-05-23 15:21 ` Stephane Eranian
2012-05-23 15:28 ` Jiri Olsa
2012-06-04 9:35 ` [PATCH V4 0/10] perf: Intel uncore pmu counting support Anshuman Khandual
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=1337144403-30841-5-git-send-email-zheng.z.yan@intel.com \
--to=zheng.z.yan@intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=andi@firstfloor.org \
--cc=eranian@google.com \
--cc=gregkh@linuxfoundation.org \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=ming.m.lin@intel.com \
--cc=mingo@elte.hu \
/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;
as well as URLs for NNTP newsgroup(s).