mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Dapeng Mi <dapeng1.mi@linux.intel.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Eranian Stephane <eranian@google.com>
Cc: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	Dapeng Mi <dapeng1.mi@intel.com>, Zide Chen <zide.chen@intel.com>,
	Falcon Thomas <thomas.falcon@intel.com>,
	Xudong Hao <xudong.hao@intel.com>,
	Dapeng Mi <dapeng1.mi@linux.intel.com>
Subject: [PATCH 14/15] perf/core: Add event_caps dependency flags
Date: Mon, 28 Sep 2026 15:43:08 +0800	[thread overview]
Message-ID: <20260928074309.898043-15-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20260928074309.898043-1-dapeng1.mi@linux.intel.com>

Add two new event capability flags:
- PERF_EV_CAP_RELIED_ON: An event that other group events rely on. Must
  not be set on a group leader.
- PERF_EV_CAP_RELIANT: An event that relies on a group event carrying
  PERF_EV_CAP_RELIED_ON. Must not be combined with PERF_EV_CAP_RELIED_ON.
  If the dependency is on the group leader, use PERF_EV_CAP_SIBLING
  instead of PERF_EV_CAP_RELIANT.

When an event with PERF_EV_CAP_RELIED_ON is detached from the group, all
events in the group carrying PERF_EV_CAP_RELIANT can no longer function
and must be transitioned to the ERROR state.

Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 include/linux/perf_event.h |  8 ++++++
 kernel/events/core.c       | 52 +++++++++++++++++++++++++++++++++-----
 2 files changed, 53 insertions(+), 7 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 7797ce207555..3031fe8dab37 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -706,11 +706,19 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
  * group it is scheduled out and moved into an unrecoverable ERROR state.
  * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the
  * PMU scope where it is active.
+ * PERF_EV_CAP_RELIED_ON: An event on which other group members depend.
+ * This flag must not be set on a group leader.
+ * PERF_EV_CAP_RELIANT: A member that depends on another group event carrying
+ * PERF_EV_CAP_RELIED_ON. It must not be combined with PERF_EV_CAP_RELIED_ON
+ * and must not be set on a group leader. If the dependency is on the group
+ * leader, use PERF_EV_CAP_SIBLING instead.
  */
 #define PERF_EV_CAP_SOFTWARE		BIT(0)
 #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 #define PERF_EV_CAP_SIBLING		BIT(2)
 #define PERF_EV_CAP_READ_SCOPE		BIT(3)
+#define PERF_EV_CAP_RELIED_ON		BIT(4)
+#define PERF_EV_CAP_RELIANT		BIT(5)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index de05df65ab3d..55db0ad8b93a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2349,13 +2349,12 @@ static void perf_promote_sibling_to_leader(struct perf_event *sibling,
 					   int group_caps)
 {
 	/*
-	 * Events that have PERF_EV_CAP_SIBLING require being part of
-	 * a group and cannot exist on their own, schedule them out
-	 * and move them into the ERROR state. Also see
-	 * _perf_event_enable(), it will not be able to recover this
-	 * ERROR state.
+	 * Events with PERF_EV_CAP_SIBLING or PERF_EV_CAP_RELIANT
+	 * must stay in a group or depend on another event in the
+	 * group; otherwise schedule them out and move them to ERROR.
+	 * _perf_event_enable() cannot recover from this state.
 	 */
-	if (sibling->event_caps & PERF_EV_CAP_SIBLING)
+	if (sibling->event_caps & (PERF_EV_CAP_SIBLING | PERF_EV_CAP_RELIANT))
 		__event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
 
 	sibling->group_leader = sibling;
@@ -2371,6 +2370,43 @@ static void perf_promote_sibling_to_leader(struct perf_event *sibling,
 	perf_event__header_size(sibling);
 }
 
+static void perf_group_disable_reliants(struct perf_event *event)
+{
+	struct perf_event *leader = event->group_leader;
+	struct perf_event *sibling, *tmp;
+	struct perf_event_context *ctx = event->ctx;
+	u32 mask = PERF_EV_CAP_RELIED_ON | PERF_EV_CAP_RELIANT;
+
+	if (!(event->event_caps & PERF_EV_CAP_RELIED_ON))
+		return;
+
+	/* Group leader should not carry PERF_EV_CAP_RELIED_ON. */
+	WARN_ON_ONCE(leader->event_caps & PERF_EV_CAP_RELIED_ON);
+	/* Group leader should not carry PERF_EV_CAP_RELIANT. */
+	WARN_ON_ONCE(leader->event_caps & PERF_EV_CAP_RELIANT);
+
+	/*
+	 * Disable all siblings that rely on this event. Without it,
+	 * they cannot function and would otherwise fall into ERROR state.
+	 */
+	list_for_each_entry_safe(sibling, tmp, &leader->sibling_list, sibling_list) {
+		if (!(sibling->event_caps & PERF_EV_CAP_RELIANT))
+			continue;
+
+		/*
+		 * An event must not set both PERF_EV_CAP_RELIED_ON and
+		 * PERF_EV_CAP_RELIANT simultaneously.
+		 */
+		if (WARN_ON_ONCE((sibling->event_caps & mask) == mask))
+			continue;
+
+		list_del_init(&sibling->sibling_list);
+		leader->nr_siblings--;
+		leader->group_generation++;
+		perf_promote_sibling_to_leader(sibling, ctx, leader->group_caps);
+	}
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
@@ -2393,6 +2429,7 @@ static void perf_group_detach(struct perf_event *event)
 	 * If this is a sibling, remove it from its group.
 	 */
 	if (leader != event) {
+		perf_group_disable_reliants(event);
 		list_del_init(&event->sibling_list);
 		leader->nr_siblings--;
 		leader->group_generation++;
@@ -3305,7 +3342,8 @@ static void _perf_event_enable(struct perf_event *event)
 		/*
 		 * Detached SIBLING events cannot leave ERROR state.
 		 */
-		if (event->event_caps & PERF_EV_CAP_SIBLING &&
+		if (event->event_caps &
+		    (PERF_EV_CAP_SIBLING | PERF_EV_CAP_RELIANT) &&
 		    event->group_leader == event)
 			goto out;
 
-- 
2.34.1


  parent reply	other threads:[~2026-09-28  7:51 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-28  7:42 [PATCH 00/15] perf/x86: Fix sampling bugs and relax slots-event grouping Dapeng Mi
2026-09-28  7:42 ` [PATCH 01/15] perf/x86/intel: Guard leader sibling walk on nr_siblings Dapeng Mi
2026-09-28  7:42 ` [PATCH 02/15] perf/x86/intel: Reset active_fixed_ctrl_val on CPU teardown Dapeng Mi
2026-09-28  7:42 ` [PATCH 03/15] perf/x86/intel: Reset active_pebs_data_cfg " Dapeng Mi
2026-09-28  7:42 ` [PATCH 04/15] perf/x86/intel: Reset cached acr_cfg_b[] and cfg_c_val[] " Dapeng Mi
2026-09-28  7:42 ` [PATCH 05/15] perf/x86/intel: Pass correct PEBS counter mask to no-drain update path Dapeng Mi
2026-09-28  7:43 ` [PATCH 06/15] perf/x86/intel: Limit PEBS counter iteration to valid array bounds Dapeng Mi
2026-09-28  7:43 ` [PATCH 07/15] perf/x86/intel: Reject SAMPLE_READ for no-counter-snapshot ACR events Dapeng Mi
2026-09-28  7:43 ` [PATCH 08/15] perf/x86/intel: Fix stale PEBS count without counter-group support Dapeng Mi
2026-09-28  7:43 ` [PATCH 09/15] perf/x86/intel: Refactor intel_pmu_drain_arch_pebs() Dapeng Mi
2026-09-28  7:43 ` [PATCH 10/15] perf/x86/intel: Refactor intel_pmu_drain_pebs_icl() Dapeng Mi
2026-09-28  7:43 ` [PATCH 11/15] perf/x86/intel: Fix invalid PEBS counts with counter-group support Dapeng Mi
2026-09-28  7:43 ` [PATCH 12/15] perf/x86/intel: Make ACR static_call update architectural Dapeng Mi
2026-09-28  7:43 ` [PATCH 13/15] perf/x86: Validate event type before topdown/mem-loads classification Dapeng Mi
2026-09-28  7:43 ` Dapeng Mi [this message]
2026-09-28  7:43 ` [PATCH 15/15] perf/x86/intel: Allow Topdown metrics with a non-leader slots event Dapeng Mi

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=20260928074309.898043-15-dapeng1.mi@linux.intel.com \
    --to=dapeng1.mi@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=dapeng1.mi@intel.com \
    --cc=eranian@google.com \
    --cc=irogers@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=thomas.falcon@intel.com \
    --cc=xudong.hao@intel.com \
    --cc=zide.chen@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

all inboxes | Powered by JetHome®