[tip: perf/core] perf/x86/intel: Convert x86_perf_regs to per-cpu variables

[tip-bot2 for Dapeng Mi]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     bbdf84fcedfa4f1e570e12e7657f7095f6e7d340
Gitweb:        https://git.kernel.org/tip/bbdf84fcedfa4f1e570e12e7657f7095f6e7d340
Author:        Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
AuthorDate:    Mon, 24 Aug 2026 16:27:11 +08:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Wed, 02 Sep 2026 13:10:40 +02:00

perf/x86/intel: Convert x86_perf_regs to per-cpu variables

Currently, the drain_pebs() helpers, e.g., intel_pmu_drain_arch_pebs()
define an on-stack x86_perf_regs. Upcoming patches will add new fields
like *ymm_regs and *zmm_regs to the x86_perf_regs structure to support
sampling for these SIMD registers. This would increase the stack size
consumed by these helpers, potentially triggering the warning:

"the frame size of 1048 bytes is larger than 1024 bytes
 [-Wframe-larger-than=]".

To eliminate this warning, convert x86_perf_regs to per-cpu variables.

Please note drain_pebs() can't be interrupted by other NMIs since
either it's already in NMI context or PMU is already disabled.

Signed-off-by: Dapeng Mi <dapeng1.mi@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://patch.msgid.link/20260824082731.1013973-4-dapeng1.mi@xxxxxxxxxxxxxxx
---
 arch/x86/events/intel/ds.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8940f02..d592a72 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -2917,6 +2917,8 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
 	}
 }
 
+static DEFINE_PER_CPU(struct x86_perf_regs, x86_pebs_regs);
+
 static __always_inline void
 __intel_pmu_pebs_events(struct perf_event *event,
 			struct pt_regs *iregs,
@@ -2926,8 +2928,8 @@ __intel_pmu_pebs_events(struct perf_event *event,
 			setup_fn setup_sample)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct x86_perf_regs perf_regs;
-	struct pt_regs *regs = &perf_regs.regs;
+	struct x86_perf_regs *perf_regs = this_cpu_ptr(&x86_pebs_regs);
+	struct pt_regs *regs = &perf_regs->regs;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
 	int cnt = count;
 
@@ -3175,8 +3177,8 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS];
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
-	struct x86_perf_regs perf_regs;
-	struct pt_regs *regs = &perf_regs.regs;
+	struct x86_perf_regs *perf_regs = this_cpu_ptr(&x86_pebs_regs);
+	struct pt_regs *regs = &perf_regs->regs;
 	struct pebs_basic *basic;
 	void *base, *at, *top;
 	u64 mask;
@@ -3226,8 +3228,8 @@ static void intel_pmu_drain_arch_pebs(struct pt_regs *iregs,
 	void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS];
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	union arch_pebs_index index;
-	struct x86_perf_regs perf_regs;
-	struct pt_regs *regs = &perf_regs.regs;
+	struct x86_perf_regs *perf_regs = this_cpu_ptr(&x86_pebs_regs);
+	struct pt_regs *regs = &perf_regs->regs;
 	void *base, *at, *top;
 	u64 mask;