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>,
Kan Liang <kan.liang@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>
Subject: [Patch v2 01/24] perf/x86: Add dynamic constraint
Date: Tue, 18 Feb 2025 15:27:55 +0000 [thread overview]
Message-ID: <20250218152818.158614-2-dapeng1.mi@linux.intel.com> (raw)
In-Reply-To: <20250218152818.158614-1-dapeng1.mi@linux.intel.com>
From: Kan Liang <kan.liang@linux.intel.com>
More and more features require a dynamic event constraint, e.g., branch
counter logging, auto counter reload, Arch PEBS, etc.
Add a generic flag, PMU_FL_DYN_CONSTRAINT, to indicate the case. It
avoids keeping adding the individual flag in intel_cpuc_prepare().
Add a variable dyn_constraint in the struct hw_perf_event to track the
dynamic constraint of the event. Apply it if it's updated.
Apply the generic dynamic constraint for branch counter logging.
Many features on and after V6 require dynamic constraint. So
unconditionally set the flag for V6+.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
arch/x86/events/core.c | 1 +
arch/x86/events/intel/core.c | 21 +++++++++++++++------
arch/x86/events/intel/lbr.c | 2 +-
arch/x86/events/perf_event.h | 1 +
include/linux/perf_event.h | 1 +
5 files changed, 19 insertions(+), 7 deletions(-)
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 7b6430e5a77b..883e0ee893cb 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -675,6 +675,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
event->hw.idx = -1;
event->hw.last_cpu = -1;
event->hw.last_tag = ~0ULL;
+ event->hw.dyn_constraint = ~0ULL;
/* mark unused */
event->hw.extra_reg.idx = EXTRA_REG_NONE;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a9b4f1099a86..5570d97b8f4f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3736,10 +3736,9 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (cpuc->excl_cntrs)
return intel_get_excl_constraints(cpuc, event, idx, c2);
- /* Not all counters support the branch counter feature. */
- if (branch_sample_counters(event)) {
+ if (event->hw.dyn_constraint != ~0ULL) {
c2 = dyn_constraint(cpuc, c2, idx);
- c2->idxmsk64 &= x86_pmu.lbr_counters;
+ c2->idxmsk64 &= event->hw.dyn_constraint;
c2->weight = hweight64(c2->idxmsk64);
}
@@ -4056,15 +4055,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
leader = event->group_leader;
if (branch_sample_call_stack(leader))
return -EINVAL;
- if (branch_sample_counters(leader))
+ if (branch_sample_counters(leader)) {
num++;
+ leader->hw.dyn_constraint &= x86_pmu.lbr_counters;
+ }
leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
for_each_sibling_event(sibling, leader) {
if (branch_sample_call_stack(sibling))
return -EINVAL;
- if (branch_sample_counters(sibling))
+ if (branch_sample_counters(sibling)) {
num++;
+ sibling->hw.dyn_constraint &= x86_pmu.lbr_counters;
+ }
}
if (num > fls(x86_pmu.lbr_counters))
@@ -4864,7 +4867,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
goto err;
}
- if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
+ if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_DYN_CONSTRAINT)) {
size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -6582,6 +6585,12 @@ __init int intel_pmu_init(void)
pr_cont(" AnyThread deprecated, ");
}
+ /*
+ * Many features on and after V6 require dynamic constraint,
+ * e.g., Arch PEBS, ACR.
+ */
+ if (version >= 6)
+ x86_pmu.flags |= PMU_FL_DYN_CONSTRAINT;
/*
* Install the hw-cache-events table:
*/
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index dc641b50814e..743dcc322085 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1609,7 +1609,7 @@ void __init intel_pmu_arch_lbr_init(void)
x86_pmu.lbr_nr = lbr_nr;
if (!!x86_pmu.lbr_counters)
- x86_pmu.flags |= PMU_FL_BR_CNTR;
+ x86_pmu.flags |= PMU_FL_BR_CNTR | PMU_FL_DYN_CONSTRAINT;
if (x86_pmu.lbr_mispred)
static_branch_enable(&x86_lbr_mispred);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a698e6484b3b..f4693409e191 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1066,6 +1066,7 @@ do { \
#define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */
#define PMU_FL_RETIRE_LATENCY 0x200 /* Support Retire Latency in PEBS */
#define PMU_FL_BR_CNTR 0x400 /* Support branch counter logging */
+#define PMU_FL_DYN_CONSTRAINT 0x800 /* Needs dynamic constraint */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2d07bc1193f3..c381ea7135df 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -158,6 +158,7 @@ struct hw_perf_event {
struct { /* hardware */
u64 config;
u64 last_tag;
+ u64 dyn_constraint;
unsigned long config_base;
unsigned long event_base;
int event_base_rdpmc;
--
2.40.1
next prev parent reply other threads:[~2025-02-18 8:13 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-18 15:27 [Patch v2 00/24] Arch-PEBS and PMU supports for Clearwater Forest and Panther Lake Dapeng Mi
2025-02-18 15:27 ` Dapeng Mi [this message]
2025-02-18 15:27 ` [Patch v2 02/24] perf/x86/intel: Add Panther Lake support Dapeng Mi
2025-02-18 15:27 ` [Patch v2 03/24] perf/x86/intel: Add PMU support for Clearwater Forest Dapeng Mi
2025-02-18 15:27 ` [Patch v2 04/24] perf/x86/intel: Parse CPUID archPerfmonExt leaves for non-hybrid CPUs Dapeng Mi
2025-02-18 15:27 ` [Patch v2 05/24] perf/x86/intel: Decouple BTS initialization from PEBS initialization Dapeng Mi
2025-02-18 15:28 ` [Patch v2 06/24] perf/x86/intel: Rename x86_pmu.pebs to x86_pmu.ds_pebs Dapeng Mi
2025-02-18 15:28 ` [Patch v2 07/24] perf/x86/intel: Introduce pairs of PEBS static calls Dapeng Mi
2025-02-18 15:28 ` [Patch v2 08/24] perf/x86/intel: Initialize architectural PEBS Dapeng Mi
2025-02-18 15:28 ` [Patch v2 09/24] perf/x86/intel/ds: Factor out common PEBS processing code to functions Dapeng Mi
2025-02-18 15:28 ` [Patch v2 10/24] perf/x86/intel: Process arch-PEBS records or record fragments Dapeng Mi
2025-02-25 10:39 ` Peter Zijlstra
2025-02-25 11:00 ` Peter Zijlstra
2025-02-26 5:20 ` Mi, Dapeng
2025-02-26 9:35 ` Peter Zijlstra
2025-02-26 15:45 ` Liang, Kan
2025-02-27 2:04 ` Mi, Dapeng
2025-02-25 20:42 ` Andi Kleen
2025-02-26 2:54 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 11/24] perf/x86/intel: Factor out common functions to process PEBS groups Dapeng Mi
2025-02-25 11:02 ` Peter Zijlstra
2025-02-26 5:24 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 12/24] perf/x86/intel: Allocate arch-PEBS buffer and initialize PEBS_BASE MSR Dapeng Mi
2025-02-25 11:18 ` Peter Zijlstra
2025-02-26 5:48 ` Mi, Dapeng
2025-02-26 9:46 ` Peter Zijlstra
2025-02-27 2:05 ` Mi, Dapeng
2025-02-25 11:25 ` Peter Zijlstra
2025-02-26 6:19 ` Mi, Dapeng
2025-02-26 9:48 ` Peter Zijlstra
2025-02-27 2:09 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 13/24] perf/x86/intel: Update dyn_constranit base on PEBS event precise level Dapeng Mi
2025-02-27 14:06 ` Liang, Kan
2025-03-05 1:41 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 14/24] perf/x86/intel: Setup PEBS data configuration and enable legacy groups Dapeng Mi
2025-02-18 15:28 ` [Patch v2 15/24] perf/x86/intel: Add SSP register support for arch-PEBS Dapeng Mi
2025-02-25 11:52 ` Peter Zijlstra
2025-02-26 6:56 ` Mi, Dapeng
2025-02-25 11:54 ` Peter Zijlstra
2025-02-25 20:44 ` Andi Kleen
2025-02-27 6:29 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 16/24] perf/x86/intel: Add counter group " Dapeng Mi
2025-02-18 15:28 ` [Patch v2 17/24] perf/core: Support to capture higher width vector registers Dapeng Mi
2025-02-25 20:32 ` Peter Zijlstra
2025-02-26 7:55 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 18/24] perf/x86/intel: Support arch-PEBS vector registers group capturing Dapeng Mi
2025-02-25 15:32 ` Peter Zijlstra
2025-02-26 8:08 ` Mi, Dapeng
2025-02-27 6:40 ` Mi, Dapeng
2025-03-04 3:08 ` Mi, Dapeng
2025-03-04 16:26 ` Liang, Kan
2025-03-05 1:34 ` Mi, Dapeng
2025-02-18 15:28 ` [Patch v2 19/24] perf tools: Support to show SSP register Dapeng Mi
2025-02-18 15:28 ` [Patch v2 20/24] perf tools: Enhance arch__intr/user_reg_mask() helpers Dapeng Mi
2025-02-18 15:28 ` [Patch v2 21/24] perf tools: Enhance sample_regs_user/intr to capture more registers Dapeng Mi
2025-02-18 15:28 ` [Patch v2 22/24] perf tools: Support to capture more vector registers (x86/Intel) Dapeng Mi
2025-02-18 15:28 ` [Patch v2 23/24] perf tools/tests: Add vector registers PEBS sampling test Dapeng Mi
2025-02-18 15:28 ` [Patch v2 24/24] perf tools: Fix incorrect --user-regs comments 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=20250218152818.158614-2-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=kan.liang@linux.intel.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 \
/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