mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Colton Lewis <coltonlewis@google.com>
To: Marc Zyngier <maz@kernel.org>, Oliver Upton <oupton@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	 Mark Rutland <mark.rutland@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	 Ingo Molnar <mingo@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	 Russell King <linux@armlinux.org.uk>,
	Jonathan Corbet <corbet@lwn.net>,
	 Fuad Tabba <fuad.tabba@linux.dev>,
	Joey Gouly <joey.gouly@arm.com>,
	 Suzuki K Poulose <suzuki.poulose@arm.com>,
	Zenghui Yu <yuzenghui@huawei.com>,
	 Shuah Khan <skhan@linuxfoundation.org>,
	James Clark <james.clark@linaro.org>,
	 Alexandru Elisei <alexandru.elisei@arm.com>,
	Mingwei Zhang <mizhang@google.com>,
	 Ganapatrao Kulkarni <gankulkarni@os.amperecomputing.com>,
	kvmarm@lists.linux.dev,  linux-arm-kernel@lists.infradead.org,
	kvm@vger.kernel.org,  linux-perf-users@vger.kernel.org,
	linux-kselftest@vger.kernel.org,  linux-doc@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH v10 20/33] perf/core: Prioritize kernel-owned pinned events when scheduling groups
Date: Thu, 19 Nov 2026 18:52:02 +0000	[thread overview]
Message-ID: <20261119185215.632334-21-coltonlewis@google.com> (raw)
In-Reply-To: <20261119185215.632334-1-coltonlewis@google.com>

When scheduling event groups in visit_groups_merge(), pinned and
flexible groups are ordered by group_index (creation order). Normally,
kernel-owned pinned events such as the hardlockup NMI watchdog are
created at boot with group_index 0 and are scheduled ahead of userspace
events.

However, if the NMI watchdog is disabled and re-enabled at runtime
after a userspace pinned per-CPU event is already active, the
watchdog's group_index is larger than the userspace event's
group_index. When hardware counters are constrained (for example, when
PMU partitioning reserves counters for a guest and leaves only one
general-purpose counter for the host), the userspace pinned event
claims the remaining counter first and merge_sched_in() transitions the
kernel watchdog event into PERF_EVENT_STATE_ERROR.

Order pinned kernel-owned events (is_pinned_kernel_event()) ahead of
userspace pinned events in perf_event_groups_cmp() and
perf_less_group_idx() while leaving flexible groups ordered by
group_index for normal round-robin rotation.

Suggested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Colton Lewis <coltonlewis@google.com>
---
 kernel/events/core.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index dbc42ded5f698..6b82029b8ebc5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -237,11 +237,16 @@ class_perf_ctx_lock_constructor(struct perf_cpu_context *cpuctx,
 
 #define TASK_TOMBSTONE ((void *)-1L)
 
-static bool is_kernel_event(struct perf_event *event)
+static bool is_kernel_event(const struct perf_event *event)
 {
 	return READ_ONCE(event->owner) == TASK_TOMBSTONE;
 }
 
+static bool is_pinned_kernel_event(const struct perf_event *event)
+{
+	return event->attr.pinned && is_kernel_event(event);
+}
+
 static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
 
 struct perf_event_context *perf_cpu_task_ctx(void)
@@ -1781,7 +1786,8 @@ static inline struct cgroup *event_cgroup(const struct perf_event *event)
  */
 static __always_inline int
 perf_event_groups_cmp(const int left_cpu, const struct pmu *left_pmu,
-		      const struct cgroup *left_cgroup, const u64 left_group_index,
+		      const struct cgroup *left_cgroup, const bool left_kernel,
+		      const u64 left_group_index,
 		      const struct perf_event *right)
 {
 	if (left_cpu < right->cpu)
@@ -1824,6 +1830,9 @@ perf_event_groups_cmp(const int left_cpu, const struct pmu *left_pmu,
 	}
 #endif
 
+	if (left_kernel != is_pinned_kernel_event(right))
+		return left_kernel ? -1 : 1;
+
 	if (left_group_index < right->group_index)
 		return -1;
 	if (left_group_index > right->group_index)
@@ -1839,7 +1848,8 @@ static inline bool __group_less(struct rb_node *a, const struct rb_node *b)
 {
 	struct perf_event *e = __node_2_pe(a);
 	return perf_event_groups_cmp(e->cpu, e->pmu_ctx->pmu, event_cgroup(e),
-				     e->group_index, __node_2_pe(b)) < 0;
+				     is_pinned_kernel_event(e), e->group_index,
+				     __node_2_pe(b)) < 0;
 }
 
 struct __group_key {
@@ -1853,8 +1863,9 @@ static inline int __group_cmp(const void *key, const struct rb_node *node)
 	const struct __group_key *a = key;
 	const struct perf_event *b = __node_2_pe(node);
 
-	/* partial/subtree match: @cpu, @pmu, @cgroup; ignore: @group_index */
-	return perf_event_groups_cmp(a->cpu, a->pmu, a->cgroup, b->group_index, b);
+	/* partial/subtree match: @cpu, @pmu, @cgroup; ignore: @kernel, @group_index */
+	return perf_event_groups_cmp(a->cpu, a->pmu, a->cgroup,
+				     is_pinned_kernel_event(b), b->group_index, b);
 }
 
 static inline int
@@ -1863,9 +1874,9 @@ __group_cmp_ignore_cgroup(const void *key, const struct rb_node *node)
 	const struct __group_key *a = key;
 	const struct perf_event *b = __node_2_pe(node);
 
-	/* partial/subtree match: @cpu, @pmu, ignore: @cgroup, @group_index */
+	/* partial/subtree match: @cpu, @pmu, ignore: @cgroup, @kernel, @group_index */
 	return perf_event_groups_cmp(a->cpu, a->pmu, event_cgroup(b),
-				     b->group_index, b);
+				     is_pinned_kernel_event(b), b->group_index, b);
 }
 
 /*
@@ -4024,6 +4035,9 @@ static bool perf_less_group_idx(const void *l, const void *r, void __always_unus
 	const struct perf_event *le = *(const struct perf_event **)l;
 	const struct perf_event *re = *(const struct perf_event **)r;
 
+	if (is_pinned_kernel_event(le) != is_pinned_kernel_event(re))
+		return is_pinned_kernel_event(le);
+
 	return le->group_index < re->group_index;
 }
 
-- 
2.56.1.708.g77570a6a1d-goog


  parent reply	other threads:[~2026-11-19 18:52 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 18:51 [PATCH v10 00/33] ARM64 PMU Partitioning Colton Lewis
2026-11-19 18:51 ` [PATCH v10 01/33] arm64: cpufeature: Add cpucap for HPMN0 Colton Lewis
2026-11-19 18:51 ` [PATCH v10 02/33] KVM: arm64: Reorganize PMU includes Colton Lewis
2026-11-19 18:51 ` [PATCH v10 03/33] KVM: arm64: Reorganize PMU functions Colton Lewis
2026-11-19 18:51 ` [PATCH v10 04/33] KVM: arm64: Use nr_pmu_counters in kvm_pmu_implemented_counter_mask() Colton Lewis
2026-11-19 18:51 ` [PATCH v10 05/33] KVM: arm64: Ignore HPMN for userspace PMU register access Colton Lewis
2026-11-19 18:51 ` [PATCH v10 06/33] perf: arm_pmuv3: Generalize counter bitmasks Colton Lewis
2026-11-19 18:51 ` [PATCH v10 07/33] perf: arm_pmuv3: Move counter allocation mask to per-CPU struct pmu_hw_events Colton Lewis
2026-11-19 18:51 ` [PATCH v10 08/33] perf: arm_pmuv3: Check cntr_mask before using pmccntr Colton Lewis
2026-11-19 18:51 ` [PATCH v10 09/33] perf: arm_pmuv3: Allocate counter indices from high to low Colton Lewis
2026-11-19 18:51 ` [PATCH v10 10/33] perf: arm_pmuv3: Expose number of general-purpose counters in sysfs Colton Lewis
2026-11-19 18:51 ` [PATCH v10 11/33] KVM: arm64: Add initial scaffolding for Partitioned PMU Colton Lewis
2026-11-19 18:51 ` [PATCH v10 12/33] KVM: arm64: Set up FGT " Colton Lewis
2026-11-19 18:51 ` [PATCH v10 13/33] KVM: arm64: Make __vcpu_rmw_sys_reg() atomic Colton Lewis
2026-11-19 18:51 ` [PATCH v10 14/33] KVM: arm64: Add Partitioned PMU register trap handlers Colton Lewis
2026-11-19 18:51 ` [PATCH v10 15/33] KVM: arm64: Construct mdcr_el2 in a local variable in kvm_arm_setup_mdcr_el2() Colton Lewis
2026-11-19 18:51 ` [PATCH v10 16/33] KVM: arm64: Set up MDCR_EL2 to handle a Partitioned PMU Colton Lewis
2026-11-19 18:51 ` [PATCH v10 17/33] KVM: arm64: Context swap Partitioned PMU guest registers Colton Lewis
2026-11-19 18:52 ` [PATCH v10 18/33] KVM: arm64: Enforce PMU event filter at vcpu_load() Colton Lewis
2026-11-19 18:52 ` [PATCH v10 19/33] perf: Add perf_pmu_resched_update() Colton Lewis
2026-11-19 18:52 ` Colton Lewis [this message]
2026-11-19 18:52 ` [PATCH v10 21/33] KVM: arm64: Allow kvm_vcpu_pmu_resync_el0() to resync filters in process context Colton Lewis
2026-11-19 18:52 ` [PATCH v10 22/33] KVM: arm64: Apply dynamic guest counter reservations Colton Lewis
2026-11-19 18:52 ` [PATCH v10 23/33] KVM: arm64: Implement lazy PMU context swaps Colton Lewis
2026-11-19 18:52 ` [PATCH v10 24/33] perf: arm_pmuv3: Handle IRQs for Partitioned PMU guest counters Colton Lewis
2026-11-19 18:52 ` [PATCH v10 25/33] KVM: arm64: Detect overflows for the Partitioned PMU Colton Lewis
2026-11-19 18:52 ` [PATCH v10 26/33] KVM: arm64: Multiplex PMCR_EL0.E and MDCR_EL2.HPME for sub-partitioned L1 Colton Lewis
2026-11-19 18:52 ` [PATCH v10 27/33] KVM: arm64: Emulate mismatched LP and HLP overflow widths " Colton Lewis
2026-11-19 18:52 ` [PATCH v10 28/33] KVM: arm64: Emulate trapped PMSWINC_EL0 writes for Partitioned PMU Colton Lewis
2026-11-19 18:52 ` [PATCH v10 29/33] KVM: arm64: Forward FGT traps for PMXEVTYPER_EL0 and PMXEVCNTR_EL0 Colton Lewis
2026-11-19 18:52 ` [PATCH v10 30/33] KVM: arm64: Support zero event counters on Partitioned PMU without HPMN0 Colton Lewis
2026-11-19 18:52 ` [PATCH v10 31/33] KVM: arm64: Add vCPU device attr to partition the PMU Colton Lewis
2026-11-19 18:52 ` [PATCH v10 32/33] KVM: selftests: Add find_bit to KVM library Colton Lewis
2026-11-19 18:52 ` [PATCH v10 33/33] KVM: arm64: selftests: Add test case for Partitioned PMU Colton Lewis

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=20261119185215.632334-21-coltonlewis@google.com \
    --to=coltonlewis@google.com \
    --cc=alexandru.elisei@arm.com \
    --cc=catalin.marinas@arm.com \
    --cc=corbet@lwn.net \
    --cc=fuad.tabba@linux.dev \
    --cc=gankulkarni@os.amperecomputing.com \
    --cc=james.clark@linaro.org \
    --cc=joey.gouly@arm.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.linux.dev \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=mark.rutland@arm.com \
    --cc=maz@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mizhang@google.com \
    --cc=oupton@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=skhan@linuxfoundation.org \
    --cc=suzuki.poulose@arm.com \
    --cc=will@kernel.org \
    --cc=yuzenghui@huawei.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®