public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>, Ingo Molnar <mingo@redhat.com>
Cc: linux-kernel@vger.kernel.org, vince@deater.net,
	eranian@google.com, Arnaldo Carvalho de Melo <acme@infradead.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>
Subject: [PATCH] perf, pt, bts: Get rid of itrace_started
Date: Thu, 30 Mar 2017 18:39:56 +0300	[thread overview]
Message-ID: <20170330153956.25994-1-alexander.shishkin@linux.intel.com> (raw)

I just noticed that hw.itrace_started and hw.config are aliased to the
same location. Now, the PT driver happens to use both, which works out
fine by sheer luck:

 - STORE(hw.itrace_start) is ordered before STORE(hw.config), in the
 program order, although there are no compiler barriers to ensure that,
 - to the perf_log_itrace_start() hw.itrace_start looks set at the same
 time as when it is intended to be set because both stores happen in the
 same path,
 - hw.config is never reset to zero in the PT driver.

Now, the use of hw.config by the PT driver makes more sense (it being a
HW PMU) than messing around with itrace_started, which is an awkward API
to begin with.

This patch replaces hw.itrace_started with an attach_state bit and an
API call for the PMU drivers to use to communicate the condition.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 arch/x86/events/intel/bts.c | 2 +-
 arch/x86/events/intel/pt.c  | 5 +++--
 include/linux/perf_event.h  | 5 ++---
 kernel/events/core.c        | 7 ++++++-
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8ae8c5ce3a..c036ed56db 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -268,7 +268,7 @@ static void bts_event_start(struct perf_event *event, int flags)
 	bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum;
 	bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold;
 
-	event->hw.itrace_started = 1;
+	perf_event_itrace_started(event);
 	event->hw.state = 0;
 
 	__bts_event_start(event);
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index ae8324d65e..81fd41d5a0 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -471,8 +471,9 @@ static void pt_config(struct perf_event *event)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	u64 reg;
 
-	if (!event->hw.itrace_started) {
-		event->hw.itrace_started = 1;
+	/* First round: clear STATUS, in particular the PSB byte counter. */
+	if (!event->hw.config) {
+		perf_event_itrace_started(event);
 		wrmsrl(MSR_IA32_RTIT_STATUS, 0);
 	}
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 24a635887f..30eacfa4fa 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -147,9 +147,6 @@ struct hw_perf_event {
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
 		};
-		struct { /* itrace */
-			int			itrace_started;
-		};
 		struct { /* amd_power */
 			u64	pwr_acc;
 			u64	ptsc;
@@ -541,6 +538,7 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP	0x02
 #define PERF_ATTACH_TASK	0x04
 #define PERF_ATTACH_TASK_DATA	0x08
+#define PERF_ATTACH_ITRACE	0x10
 
 struct perf_cgroup;
 struct ring_buffer;
@@ -862,6 +860,7 @@ extern int perf_aux_output_skip(struct perf_output_handle *handle,
 				unsigned long size);
 extern void *perf_get_aux(struct perf_output_handle *handle);
 extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags);
+extern void perf_event_itrace_started(struct perf_event *event);
 
 extern int perf_pmu_register(struct pmu *pmu, const char *name, int type);
 extern void perf_pmu_unregister(struct pmu *pmu);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c941..2e23f5373f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7239,6 +7239,11 @@ static void perf_log_throttle(struct perf_event *event, int enable)
 	perf_output_end(&handle);
 }
 
+void perf_event_itrace_started(struct perf_event *event)
+{
+	event->attach_state |= PERF_ATTACH_ITRACE;
+}
+
 static void perf_log_itrace_start(struct perf_event *event)
 {
 	struct perf_output_handle handle;
@@ -7254,7 +7259,7 @@ static void perf_log_itrace_start(struct perf_event *event)
 		event = event->parent;
 
 	if (!(event->pmu->capabilities & PERF_PMU_CAP_ITRACE) ||
-	    event->hw.itrace_started)
+	    event->attach_state & PERF_ATTACH_ITRACE)
 		return;
 
 	rec.header.type	= PERF_RECORD_ITRACE_START;
-- 
2.11.0

             reply	other threads:[~2017-03-30 15:40 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-30 15:39 Alexander Shishkin [this message]
2017-08-29 14:21 ` [tip:perf/core] perf/core, pt, bts: Get rid of itrace_started tip-bot for Alexander Shishkin

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=20170330153956.25994-1-alexander.shishkin@linux.intel.com \
    --to=alexander.shishkin@linux.intel.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@infradead.org \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=vince@deater.net \
    /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