linux-kernel - [PATCH V4 10/25] perf/x86: Hybrid PMU support for extra

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1617322252-154215-11-git-send-email-kan.liang@linux.intel.com>
Date:   Thu,  1 Apr 2021 17:10:37 -0700
From:   kan.liang@...ux.intel.com
To:     peterz@...radead.org, mingo@...nel.org,
        linux-kernel@...r.kernel.org
Cc:     acme@...nel.org, tglx@...utronix.de, bp@...en8.de,
        namhyung@...nel.org, jolsa@...hat.com, ak@...ux.intel.com,
        yao.jin@...ux.intel.com, alexander.shishkin@...ux.intel.com,
        adrian.hunter@...el.com, Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH V4 10/25] perf/x86: Hybrid PMU support for extra_regs

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

Different hybrid PMU may have different extra registers, e.g. Core PMU
may have offcore registers, frontend register and ldlat register. Atom
core may only have offcore registers and ldlat register. Each hybrid PMU
should use its own extra_regs.

An Intel Hybrid system should always have extra registers.
Unconditionally allocate shared_regs for Intel Hybrid system.

Reviewed-by: Andi Kleen <ak@...ux.intel.com>
Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
 arch/x86/events/core.c       |  5 +++--
 arch/x86/events/intel/core.c | 15 +++++++++------
 arch/x86/events/perf_event.h |  1 +
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index b866867..b79a506 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -153,15 +153,16 @@ u64 x86_perf_event_update(struct perf_event *event)
  */
 static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 {
+	struct extra_reg *extra_regs = hybrid(event->pmu, extra_regs);
 	struct hw_perf_event_extra *reg;
 	struct extra_reg *er;
 
 	reg = &event->hw.extra_reg;
 
-	if (!x86_pmu.extra_regs)
+	if (!extra_regs)
 		return 0;
 
-	for (er = x86_pmu.extra_regs; er->msr; er++) {
+	for (er = extra_regs; er->msr; er++) {
 		if (er->event != (config & er->config_mask))
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d304ba3..b5b7694 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2966,8 +2966,10 @@ intel_vlbr_constraints(struct perf_event *event)
 	return NULL;
 }
 
-static int intel_alt_er(int idx, u64 config)
+static int intel_alt_er(struct cpu_hw_events *cpuc,
+			int idx, u64 config)
 {
+	struct extra_reg *extra_regs = hybrid(cpuc->pmu, extra_regs);
 	int alt_idx = idx;
 
 	if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1))
@@ -2979,7 +2981,7 @@ static int intel_alt_er(int idx, u64 config)
 	if (idx == EXTRA_REG_RSP_1)
 		alt_idx = EXTRA_REG_RSP_0;
 
-	if (config & ~x86_pmu.extra_regs[alt_idx].valid_mask)
+	if (config & ~extra_regs[alt_idx].valid_mask)
 		return idx;
 
 	return alt_idx;
@@ -2987,15 +2989,16 @@ static int intel_alt_er(int idx, u64 config)
 
 static void intel_fixup_er(struct perf_event *event, int idx)
 {
+	struct extra_reg *extra_regs = hybrid(event->pmu, extra_regs);
 	event->hw.extra_reg.idx = idx;
 
 	if (idx == EXTRA_REG_RSP_0) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event;
+		event->hw.config |= extra_regs[EXTRA_REG_RSP_0].event;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
 	} else if (idx == EXTRA_REG_RSP_1) {
 		event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
-		event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event;
+		event->hw.config |= extra_regs[EXTRA_REG_RSP_1].event;
 		event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
 	}
 }
@@ -3071,7 +3074,7 @@ __intel_shared_reg_get_constraints(struct cpu_hw_events *cpuc,
 		 */
 		c = NULL;
 	} else {
-		idx = intel_alt_er(idx, reg->config);
+		idx = intel_alt_er(cpuc, idx, reg->config);
 		if (idx != reg->idx) {
 			raw_spin_unlock_irqrestore(&era->lock, flags);
 			goto again;
@@ -4161,7 +4164,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 {
 	cpuc->pebs_record_size = x86_pmu.pebs_record_size;
 
-	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
+	if (is_hybrid() || x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
 			goto err;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index c32e9dc..5679c12 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -651,6 +651,7 @@ struct x86_hybrid_pmu {
 					[PERF_COUNT_HW_CACHE_RESULT_MAX];
 	struct event_constraint		*event_constraints;
 	struct event_constraint		*pebs_constraints;
+	struct extra_reg		*extra_regs;
 };
 
 static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu)
-- 
2.7.4