public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: tglx@linutronix.de, jstultz@google.com, peterz@infradead.org,
	mingo@redhat.com, linux-kernel@vger.kernel.org
Cc: sboyd@kernel.org, eranian@google.com, namhyung@kernel.org,
	ak@linux.intel.com, adrian.hunter@intel.com,
	Kan Liang <kan.liang@linux.intel.com>
Subject: [RFC PATCH V2 2/9] perf: Extend ABI to support post-processing monotonic raw conversion
Date: Mon, 13 Feb 2023 11:07:47 -0800	[thread overview]
Message-ID: <20230213190754.1836051-3-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20230213190754.1836051-1-kan.liang@linux.intel.com>

From: Kan Liang <kan.liang@linux.intel.com>

The monotonic raw clock is not affected by NTP/PTP correction. The
calculation of the monotonic raw clock can be done in the
post-processing, which can reduce the kernel overhead.

Add hw_time in the struct perf_event_attr to tell the kernel dump the
raw HW time to user space. The perf tool will calculate the HW time
in post-processing.
Currently, only supports the monotonic raw conversion.
Only dump the raw HW time with PERF_RECORD_SAMPLE, because the accurate
HW time can only be provided in a sample by HW. For other type of
records, the user requested clock should be returned as usual. Nothing
is changed.

Add perf_event_mmap_page::cap_user_time_mono_raw ABI to dump the
conversion information. The cap_user_time_mono_raw also indicates
whether the monotonic raw conversion information is available.
If yes, the clock monotonic raw can be calculated as
mono_raw = base + ((cyc - last) * mult + nsec) >> shift

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 include/uapi/linux/perf_event.h | 21 ++++++++++++++++++---
 kernel/events/core.c            |  7 +++++++
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ccb7f5dad59b..9d56fe027f6c 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -455,7 +455,8 @@ struct perf_event_attr {
 				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
 				remove_on_exec :  1, /* event is removed from task on exec */
 				sigtrap        :  1, /* send synchronous SIGTRAP on event */
-				__reserved_1   : 26;
+				hw_time        :  1, /* generate raw HW time for samples */
+				__reserved_1   : 25;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -615,7 +616,8 @@ struct perf_event_mmap_page {
 				cap_user_time		: 1, /* The time_{shift,mult,offset} fields are used */
 				cap_user_time_zero	: 1, /* The time_zero field is used */
 				cap_user_time_short	: 1, /* the time_{cycle,mask} fields are used */
-				cap_____res		: 58;
+				cap_user_time_mono_raw  : 1, /* The time_mono_* fields are used */
+				cap_____res		: 57;
 		};
 	};
 
@@ -692,11 +694,24 @@ struct perf_event_mmap_page {
 	__u64	time_cycles;
 	__u64	time_mask;
 
+	/*
+	 * If cap_user_time_mono_raw, the monotonic raw clock can be calculated
+	 * from the hardware clock (e.g. TSC) 'cyc'.
+	 *
+	 * mono_raw = base + ((cyc - last) * mult + nsec) >> shift
+	 *
+	 */
+	__u64	time_mono_last;
+	__u32	time_mono_mult;
+	__u32	time_mono_shift;
+	__u64	time_mono_nsec;
+	__u64	time_mono_base;
+
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u8	__reserved[116*8];	/* align to 1k. */
+	__u8	__reserved[112*8];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 380476a934e8..f062cce2dafc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -12135,6 +12135,13 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (attr->sigtrap && !attr->remove_on_exec)
 		return -EINVAL;
 
+	if (attr->use_clockid) {
+		/*
+		 * Only support post-processing for the monotonic raw clock
+		 */
+		if (attr->hw_time && (attr->clockid != CLOCK_MONOTONIC_RAW))
+			return -EINVAL;
+	}
 out:
 	return ret;
 
-- 
2.35.1


  parent reply	other threads:[~2023-02-13 19:08 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-13 19:07 [RFC PATCH V2 0/9] Convert TSC to monotonic raw clock for PEBS kan.liang
2023-02-13 19:07 ` [RFC PATCH V2 1/9] timekeeping: Expose the conversion information of monotonic raw kan.liang
2023-02-13 19:28   ` John Stultz
2023-02-13 19:07 ` kan.liang [this message]
2023-02-13 19:37   ` [RFC PATCH V2 2/9] perf: Extend ABI to support post-processing monotonic raw conversion John Stultz
2023-02-13 21:40     ` Liang, Kan
2023-02-13 22:22       ` John Stultz
2023-02-14 10:43         ` Peter Zijlstra
2023-02-14 17:46           ` Liang, Kan
2023-02-14 19:37             ` John Stultz
2023-02-14 20:09               ` Liang, Kan
2023-02-14 20:21                 ` John Stultz
2023-03-12 20:50                   ` Andi Kleen
2023-02-14 19:34           ` John Stultz
2023-02-14 14:51         ` Liang, Kan
2023-02-14 17:00           ` Liang, Kan
2023-02-14 20:11             ` John Stultz
2023-02-14 20:38               ` Liang, Kan
2023-02-17 23:11                 ` John Stultz
2023-03-08 18:44                   ` Liang, Kan
2023-03-09  1:17                     ` John Stultz
2023-03-09 16:56                       ` Liang, Kan
2023-03-11  5:55                         ` John Stultz
2023-03-13 21:19                           ` Liang, Kan
2023-03-18  6:02                             ` John Stultz
2023-03-21 15:26                               ` Liang, Kan
2023-02-14 19:52           ` John Stultz
2023-02-13 19:07 ` [RFC PATCH V2 3/9] perf/x86: Factor out x86_pmu_sample_preload() kan.liang
2023-02-13 19:07 ` [RFC PATCH V2 4/9] perf/x86: Enable post-processing monotonic raw conversion kan.liang
2023-02-14 20:02   ` Thomas Gleixner
2023-02-14 20:21     ` Liang, Kan
2023-02-14 20:55       ` Thomas Gleixner
2023-03-21 15:38         ` Liang, Kan
2023-02-13 19:07 ` [RFC PATCH V2 5/9] perf/x86/intel: Enable large PEBS for monotonic raw kan.liang
2023-02-13 19:07 ` [RFC PATCH V2 6/9] tools headers UAPI: Sync linux/perf_event.h with the kernel sources kan.liang
2023-02-13 19:07 ` [RFC PATCH V2 7/9] perf session: Support the monotonic raw clock conversion information kan.liang
2023-02-13 19:07 ` [RFC PATCH V2 8/9] perf evsel, tsc: Support the monotonic raw clock conversion kan.liang
2023-02-13 19:07 ` [RFC PATCH V2 9/9] perf evsel: Enable post-processing monotonic raw conversion by default kan.liang

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=20230213190754.1836051-3-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jstultz@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=sboyd@kernel.org \
    --cc=tglx@linutronix.de \
    /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