Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 54 insertions, 24 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 985ef3b479..1fc4ce44e7 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -647,7 +647,7 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
-static inline void amd_pmu_set_global_ctl(u64 ctl)
+static __always_inline void amd_pmu_set_global_ctl(u64 ctl)
 {
 	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
 }
@@ -907,6 +907,37 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	return amd_pmu_adjust_nmi_window(handled);
 }
 
+/*
+ * AMD-specific callback invoked through perf_snapshot_branch_stack static
+ * call, defined in include/linux/perf_event.h. See its definition for API
+ * details. It's up to caller to provide enough space in *entries* to fit all
+ * LBR records, otherwise returned result will be truncated to *cnt* entries.
+ */
+static int amd_pmu_v2_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	struct cpu_hw_events *cpuc;
+	unsigned long flags;
+
+	/*
+	 * The sequence of steps to freeze LBR should be completely inlined
+	 * and contain no branches to minimize contamination of LBR snapshot
+	 */
+	local_irq_save(flags);
+	amd_pmu_core_disable_all();
+	__amd_pmu_lbr_disable();
+
+	cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	amd_pmu_lbr_read();
+	cnt = min(cnt, x86_pmu.lbr_nr);
+	memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt);
+
+	amd_pmu_v2_enable_all(0);
+	local_irq_restore(flags);
+
+	return cnt;
+}
+
 static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1443,6 +1474,10 @@ static int __init amd_core_pmu_init(void)
 		static_call_update(amd_pmu_branch_reset, amd_pmu_lbr_reset);
 		static_call_update(amd_pmu_branch_add, amd_pmu_lbr_add);
 		static_call_update(amd_pmu_branch_del, amd_pmu_lbr_del);
+
+		/* Only support branch_stack snapshot on perfmon v2 */
+		if (x86_pmu.handle_irq == amd_pmu_v2_handle_irq)
+			static_call_update(perf_snapshot_branch_stack, amd_pmu_v2_snapshot_branch_stack);
 	} else if (!amd_brs_init()) {
 		/*
 		 * BRS requires special event constraints and flushing on ctxsw.
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 5149830c7c..19c7b76e21 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -310,10 +310,6 @@ int amd_pmu_lbr_hw_config(struct perf_event *event)
 {
 	int ret = 0;
 
-	/* LBR is not recommended in counting mode */
-	if (!is_sampling_event(event))
-		return -EINVAL;
-
 	ret = amd_pmu_lbr_setup_filter(event);
 	if (!ret)
 		event->attach_state |= PERF_ATTACH_SCHED_CB;
@@ -414,18 +410,11 @@ void amd_pmu_lbr_enable_all(void)
 void amd_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	u64 dbg_ctl, dbg_extn_cfg;
 
 	if (!cpuc->lbr_users || !x86_pmu.lbr_nr)
 		return;
 
-	rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
-	wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
-
-	if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
-		rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
-		wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
-	}
+	__amd_pmu_lbr_disable();
 }
 
 __init int amd_pmu_lbr_init(void)
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4ccb8fa483..5a4bfe9aea 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -639,7 +639,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	info.split.aux_data = 0;
 	info.split.num_pmcs = NUM_COUNTERS_NB;
 	info.split.gid = 0;
-	info.split.cid = topology_die_id(cpu);
+	info.split.cid = topology_logical_package_id(cpu);
 
 	if (pmu_version >= 2) {
 		ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
@@ -654,17 +654,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 {
 	struct attribute **df_attr = amd_uncore_df_format_attr;
 	struct amd_uncore_pmu *pmu;
+	int num_counters;
 
 	/* Run just once */
 	if (uncore->init_done)
 		return amd_uncore_ctx_init(uncore, cpu);
 
+	num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	if (!num_counters)
+		goto done;
+
 	/* No grouping, single instance for a system */
 	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
-	if (!uncore->pmus) {
-		uncore->num_pmus = 0;
+	if (!uncore->pmus)
 		goto done;
-	}
 
 	/*
 	 * For Family 17h and above, the Northbridge counters are repurposed
@@ -674,7 +677,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	pmu = &uncore->pmus[0];
 	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
 		sizeof(pmu->name));
-	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	pmu->num_counters = num_counters;
 	pmu->msr_base = MSR_F15H_NB_PERF_CTL;
 	pmu->rdpmc_base = RDPMC_BASE_NB;
 	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -785,17 +788,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 {
 	struct attribute **l3_attr = amd_uncore_l3_format_attr;
 	struct amd_uncore_pmu *pmu;
+	int num_counters;
 
 	/* Run just once */
 	if (uncore->init_done)
 		return amd_uncore_ctx_init(uncore, cpu);
 
+	num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	if (!num_counters)
+		goto done;
+
 	/* No grouping, single instance for a system */
 	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
-	if (!uncore->pmus) {
-		uncore->num_pmus = 0;
+	if (!uncore->pmus)
 		goto done;
-	}
 
 	/*
 	 * For Family 17h and above, L3 cache counters are available instead
@@ -805,7 +811,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	pmu = &uncore->pmus[0];
 	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
 		sizeof(pmu->name));
-	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	pmu->num_counters = num_counters;
 	pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
 	pmu->rdpmc_base = RDPMC_BASE_LLC;
 	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -893,8 +899,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
 	info.split.aux_data = ecx;	/* stash active mask */
 	info.split.num_pmcs = ebx.split.num_umc_pmc;
-	info.split.gid = topology_die_id(cpu);
-	info.split.cid = topology_die_id(cpu);
+	info.split.gid = topology_logical_package_id(cpu);
+	info.split.cid = topology_logical_package_id(cpu);
 	*per_cpu_ptr(uncore->info, cpu) = info;
 }