Merge tag 'v6.6-rc4' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 28 insertions, 8 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index abadd5f23425..e24976593a29 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu)
 	/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
 	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
 
-	/* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask);
+	/*
+	 * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
+	 * and PerfCntrGLobalStatus.PerfCntrOvfl
+	 */
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+	       GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
 }
 
 static int amd_pmu_cpu_prepare(int cpu)
@@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu)
 	int i, nb_id;
 
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
+	amd_pmu_cpu_reset(cpu);
 
 	if (!x86_pmu.amd_nb_constraints)
 		return;
@@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu)
 
 	cpuc->amd_nb->nb_id = nb_id;
 	cpuc->amd_nb->refcnt++;
-
-	amd_pmu_cpu_reset(cpu);
 }
 
 static void amd_pmu_cpu_dead(int cpu)
@@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu)
 
 	kfree(cpuhw->lbr_sel);
 	cpuhw->lbr_sel = NULL;
+	amd_pmu_cpu_reset(cpu);
 
 	if (!x86_pmu.amd_nb_constraints)
 		return;
@@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
 		cpuhw->amd_nb = NULL;
 	}
-
-	amd_pmu_cpu_reset(cpu);
 }
 
 static inline void amd_pmu_set_global_ctl(u64 ctl)
@@ -884,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	struct hw_perf_event *hwc;
 	struct perf_event *event;
 	int handled = 0, idx;
-	u64 status, mask;
+	u64 reserved, status, mask;
 	bool pmu_enabled;
 
 	/*
@@ -909,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		status &= ~GLOBAL_STATUS_LBRS_FROZEN;
 	}
 
+	reserved = status & ~amd_pmu_global_cntr_mask;
+	if (reserved)
+		pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n",
+			     reserved);
+
+	/* Clear any reserved bits set by buggy microcode */
+	status &= amd_pmu_global_cntr_mask;
+
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 4d349986f76a..8250f0f59c2b 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6474,8 +6474,18 @@ void spr_uncore_cpu_init(void)
 
 	type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA);
 	if (type) {
+		/*
+		 * The value from the discovery table (stored in the type->num_boxes
+		 * of UNCORE_SPR_CHA) is incorrect on some SPR variants because of a
+		 * firmware bug. Using the value from SPR_MSR_UNC_CBO_CONFIG to replace it.
+		 */
 		rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
-		type->num_boxes = num_cbo;
+		/*
+		 * The MSR doesn't work on the EMR XCC, but the firmware bug doesn't impact
+		 * the EMR XCC. Don't let the value from the MSR replace the existing value.
+		 */
+		if (num_cbo)
+			type->num_boxes = num_cbo;
 	}
 	spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO);
 }