1 files changed, 227 insertions, 85 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 40e12cfc87f6..35102ecdfc8d 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -18,6 +18,7 @@
 #include <asm/hardirq.h>
 #include <asm/intel-family.h>
 #include <asm/apic.h>
+#include <asm/cpu_device_id.h>
 
 #include "../perf_event.h"
 
@@ -1999,6 +2000,39 @@ static void intel_pmu_nhm_enable_all(int added)
 	intel_pmu_enable_all(added);
 }
 
+static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on)
+{
+	u64 val = on ? MSR_TFA_RTM_FORCE_ABORT : 0;
+
+	if (cpuc->tfa_shadow != val) {
+		cpuc->tfa_shadow = val;
+		wrmsrl(MSR_TSX_FORCE_ABORT, val);
+	}
+}
+
+static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+	/*
+	 * We're going to use PMC3, make sure TFA is set before we touch it.
+	 */
+	if (cntr == 3 && !cpuc->is_fake)
+		intel_set_tfa(cpuc, true);
+}
+
+static void intel_tfa_pmu_enable_all(int added)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/*
+	 * If we find PMC3 is no longer used when we enable the PMU, we can
+	 * clear TFA.
+	 */
+	if (!test_bit(3, cpuc->active_mask))
+		intel_set_tfa(cpuc, false);
+
+	intel_pmu_enable_all(added);
+}
+
 static void enable_counter_freeze(void)
 {
 	update_debugctlmsr(get_debugctlmsr() |
@@ -2769,6 +2803,35 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
 }
 
 static struct event_constraint *
+dyn_constraint(struct cpu_hw_events *cpuc, struct event_constraint *c, int idx)
+{
+	WARN_ON_ONCE(!cpuc->constraint_list);
+
+	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
+		struct event_constraint *cx;
+
+		/*
+		 * grab pre-allocated constraint entry
+		 */
+		cx = &cpuc->constraint_list[idx];
+
+		/*
+		 * initialize dynamic constraint
+		 * with static constraint
+		 */
+		*cx = *c;
+
+		/*
+		 * mark constraint as dynamic
+		 */
+		cx->flags |= PERF_X86_EVENT_DYNAMIC;
+		c = cx;
+	}
+
+	return c;
+}
+
+static struct event_constraint *
 intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 			   int idx, struct event_constraint *c)
 {
@@ -2798,27 +2861,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * only needed when constraint has not yet
 	 * been cloned (marked dynamic)
 	 */
-	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-		struct event_constraint *cx;
-
-		/*
-		 * grab pre-allocated constraint entry
-		 */
-		cx = &cpuc->constraint_list[idx];
-
-		/*
-		 * initialize dynamic constraint
-		 * with static constraint
-		 */
-		*cx = *c;
-
-		/*
-		 * mark constraint as dynamic, so we
-		 * can free it later on
-		 */
-		cx->flags |= PERF_X86_EVENT_DYNAMIC;
-		c = cx;
-	}
+	c = dyn_constraint(cpuc, c, idx);
 
 	/*
 	 * From here on, the constraint is dynamic.
@@ -3206,16 +3249,27 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
 	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
 	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
 	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
-	/*
-	 * If PMU counter has PEBS enabled it is not enough to disable counter
-	 * on a guest entry since PEBS memory write can overshoot guest entry
-	 * and corrupt guest memory. Disabling PEBS solves the problem.
-	 */
-	arr[1].msr = MSR_IA32_PEBS_ENABLE;
-	arr[1].host = cpuc->pebs_enabled;
-	arr[1].guest = 0;
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		arr[0].guest &= ~cpuc->pebs_enabled;
+	else
+		arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	*nr = 1;
+
+	if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
+		/*
+		 * If PMU counter has PEBS enabled it is not enough to
+		 * disable counter on a guest entry since PEBS memory
+		 * write can overshoot guest entry and corrupt guest
+		 * memory. Disabling PEBS solves the problem.
+		 *
+		 * Don't do this if the CPU already enforces it.
+		 */
+		arr[1].msr = MSR_IA32_PEBS_ENABLE;
+		arr[1].host = cpuc->pebs_enabled;
+		arr[1].guest = 0;
+		*nr = 2;
+	}
 
-	*nr = 2;
 	return arr;
 }
 
@@ -3345,6 +3399,26 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return c;
 }
 
+static bool allow_tsx_force_abort = true;
+
+static struct event_constraint *
+tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c = hsw_get_event_constraints(cpuc, idx, event);
+
+	/*
+	 * Without TFA we must not use PMC3.
+	 */
+	if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
+		c = dyn_constraint(cpuc, c, idx);
+		c->idxmsk64 &= ~(1ULL << 3);
+		c->weight--;
+	}
+
+	return c;
+}
+
 /*
  * Broadwell:
  *
@@ -3398,7 +3472,7 @@ ssize_t intel_event_sysfs_show(char *page, u64 config)
 	return x86_event_sysfs_show(page, config, event);
 }
 
-struct intel_shared_regs *allocate_shared_regs(int cpu)
+static struct intel_shared_regs *allocate_shared_regs(int cpu)
 {
 	struct intel_shared_regs *regs;
 	int i;
@@ -3430,23 +3504,24 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 	return c;
 }
 
-static int intel_pmu_cpu_prepare(int cpu)
-{
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
+int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
+{
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
 			goto err;
 	}
 
-	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
+	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
-		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
+		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
 		if (!cpuc->constraint_list)
 			goto err_shared_regs;
+	}
 
+	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
 		cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
 		if (!cpuc->excl_cntrs)
 			goto err_constraint_list;
@@ -3468,6 +3543,11 @@ err:
 	return -ENOMEM;
 }
 
+static int intel_pmu_cpu_prepare(int cpu)
+{
+	return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu);
+}
+
 static void flip_smm_bit(void *data)
 {
 	unsigned long set = *(unsigned long *)data;
@@ -3542,9 +3622,8 @@ static void intel_pmu_cpu_starting(int cpu)
 	}
 }
 
-static void free_excl_cntrs(int cpu)
+static void free_excl_cntrs(struct cpu_hw_events *cpuc)
 {
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	struct intel_excl_cntrs *c;
 
 	c = cpuc->excl_cntrs;
@@ -3552,14 +3631,22 @@ static void free_excl_cntrs(int cpu)
 		if (c->core_id == -1 || --c->refcnt == 0)
 			kfree(c);
 		cpuc->excl_cntrs = NULL;
-		kfree(cpuc->constraint_list);
-		cpuc->constraint_list = NULL;
 	}
+
+	kfree(cpuc->constraint_list);
+	cpuc->constraint_list = NULL;
 }
 
 static void intel_pmu_cpu_dying(int cpu)
 {
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	fini_debug_store_on_cpu(cpu);
+
+	if (x86_pmu.counter_freezing)
+		disable_counter_freeze();
+}
+
+void intel_cpuc_finish(struct cpu_hw_events *cpuc)
+{
 	struct intel_shared_regs *pc;
 
 	pc = cpuc->shared_regs;
@@ -3569,12 +3656,12 @@ static void intel_pmu_cpu_dying(int cpu)
 		cpuc->shared_regs = NULL;
 	}
 
-	free_excl_cntrs(cpu);
-
-	fini_debug_store_on_cpu(cpu);
+	free_excl_cntrs(cpuc);
+}
 
-	if (x86_pmu.counter_freezing)
-		disable_counter_freeze();
+static void intel_pmu_cpu_dead(int cpu)
+{
+	intel_cpuc_finish(&per_cpu(cpu_hw_events, cpu));
 }
 
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3584,6 +3671,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3663,6 +3755,9 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3703,8 +3798,12 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -3733,36 +3832,62 @@ static __init void intel_clovertown_quirk(void)
 	x86_pmu.pebs_constraints = NULL;
 }
 
-static int intel_snb_pebs_broken(int cpu)
+static const struct x86_cpu_desc isolation_ucodes[] = {
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_CORE,		 3, 0x0000001f),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_ULT,		 1, 0x0000001e),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_GT3E,		 1, 0x00000015),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X,		 2, 0x00000037),
+	INTEL_CPU_DESC(INTEL_FAM6_HASWELL_X,		 4, 0x0000000a),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_CORE,	 4, 0x00000023),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_GT3E,	 1, 0x00000014),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 2, 0x00000010),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 3, 0x07000009),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 4, 0x0f000009),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_XEON_D,	 5, 0x0e000002),
+	INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X,		 2, 0x0b000014),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 3, 0x00000021),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X,		 4, 0x00000000),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_MOBILE,	 3, 0x0000007c),
+	INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_DESKTOP,	 3, 0x0000007c),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	 9, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	 9, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	10, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	11, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_MOBILE,	12, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	10, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	11, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	12, 0x0000004e),
+	INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE_DESKTOP,	13, 0x0000004e),
+	{}
+};
+
+static void intel_check_pebs_isolation(void)
 {
-	u32 rev = UINT_MAX; /* default to broken for unknown models */
+	x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes);
+}
 
-	switch (cpu_data(cpu).x86_model) {
-	case INTEL_FAM6_SANDYBRIDGE:
-		rev = 0x28;
-		break;
+static __init void intel_pebs_isolation_quirk(void)
+{
+	WARN_ON_ONCE(x86_pmu.check_microcode);
+	x86_pmu.check_microcode = intel_check_pebs_isolation;
+	intel_check_pebs_isolation();
+}
 
-	case INTEL_FAM6_SANDYBRIDGE_X:
-		switch (cpu_data(cpu).x86_stepping) {
-		case 6: rev = 0x618; break;
-		case 7: rev = 0x70c; break;
-		}
-	}
+static const struct x86_cpu_desc pebs_ucodes[] = {
+	INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE,		7, 0x00000028),
+	INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X,	6, 0x00000618),
+	INTEL_CPU_DESC(INTEL_FAM6_SANDYBRIDGE_X,	7, 0x0000070c),
+	{}
+};
 
-	return (cpu_data(cpu).microcode < rev);
+static bool intel_snb_pebs_broken(void)
+{
+	return !x86_cpu_has_min_microcode_rev(pebs_ucodes);
 }
 
 static void intel_snb_check_microcode(void)
 {
-	int pebs_broken = 0;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if ((pebs_broken = intel_snb_pebs_broken(cpu)))
-			break;
-	}
-
-	if (pebs_broken == x86_pmu.pebs_broken)
+	if (intel_snb_pebs_broken() == x86_pmu.pebs_broken)
 		return;
 
 	/*
@@ -3879,23 +4004,22 @@ static __init void intel_nehalem_quirk(void)
 	}
 }
 
-static bool intel_glp_counter_freezing_broken(int cpu)
-{
-	u32 rev = UINT_MAX; /* default to broken for unknown stepping */
-
-	switch (cpu_data(cpu).x86_stepping) {
-	case 1:
-		rev = 0x28;
-		break;
-	case 8:
-		rev = 0x6;
-		break;
-	}
+static const struct x86_cpu_desc counter_freezing_ucodes[] = {
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT,	 2, 0x0000000e),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT,	 9, 0x0000002e),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT,	10, 0x00000008),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_X,	 1, 0x00000028),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	 1, 0x00000028),
+	INTEL_CPU_DESC(INTEL_FAM6_ATOM_GOLDMONT_PLUS,	 8, 0x00000006),
+	{}
+};
 
-	return (cpu_data(cpu).microcode < rev);
+static bool intel_counter_freezing_broken(void)
+{
+	return !x86_cpu_has_min_microcode_rev(counter_freezing_ucodes);
 }
 
-static __init void intel_glp_counter_freezing_quirk(void)
+static __init void intel_counter_freezing_quirk(void)
 {
 	/* Check if it's already disabled */
 	if (disable_counter_freezing)
@@ -3905,7 +4029,7 @@ static __init void intel_glp_counter_freezing_quirk(void)
 	 * If the system starts with the wrong ucode, leave the
 	 * counter-freezing feature permanently disabled.
 	 */
-	if (intel_glp_counter_freezing_broken(raw_smp_processor_id())) {
+	if (intel_counter_freezing_broken()) {
 		pr_info("PMU counter freezing disabled due to CPU errata,"
 			"please upgrade microcode\n");
 		x86_pmu.counter_freezing = false;
@@ -4055,8 +4179,11 @@ static struct attribute *intel_pmu_caps_attrs[] = {
        NULL
 };
 
+DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort);
+
 static struct attribute *intel_pmu_attrs[] = {
 	&dev_attr_freeze_on_smi.attr,
+	NULL, /* &dev_attr_allow_tsx_force_abort.attr.attr */
 	NULL,
 };
 
@@ -4168,6 +4295,8 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_CORE2_MEROM:
 		x86_add_quirk(intel_clovertown_quirk);
+		/* fall through */
+
 	case INTEL_FAM6_CORE2_MEROM_L:
 	case INTEL_FAM6_CORE2_PENRYN:
 	case INTEL_FAM6_CORE2_DUNNINGTON:
@@ -4256,6 +4385,7 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ATOM_GOLDMONT:
 	case INTEL_FAM6_ATOM_GOLDMONT_X:
+		x86_add_quirk(intel_counter_freezing_quirk);
 		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -4282,7 +4412,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
-		x86_add_quirk(intel_glp_counter_freezing_quirk);
+		x86_add_quirk(intel_counter_freezing_quirk);
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -4425,6 +4555,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_HASWELL_ULT:
 	case INTEL_FAM6_HASWELL_GT3E:
 		x86_add_quirk(intel_ht_bug);
+		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4456,6 +4587,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_BROADWELL_XEON_D:
 	case INTEL_FAM6_BROADWELL_GT3E:
 	case INTEL_FAM6_BROADWELL_X:
+		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4518,6 +4650,7 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
+		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -4549,6 +4682,15 @@ __init int intel_pmu_init(void)
 		tsx_attr = hsw_tsx_events_attrs;
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
+
+		if (boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
+			x86_pmu.flags |= PMU_FL_TFA;
+			x86_pmu.get_event_constraints = tfa_get_event_constraints;
+			x86_pmu.enable_all = intel_tfa_pmu_enable_all;
+			x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
+			intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr;
+		}
+
 		pr_cont("Skylake events, ");
 		name = "skylake";
 		break;
@@ -4700,7 +4842,7 @@ static __init int fixup_ht_bug(void)
 	hardlockup_detector_perf_restart();
 
 	for_each_online_cpu(c)
-		free_excl_cntrs(c);
+		free_excl_cntrs(&per_cpu(cpu_hw_events, c));
 
 	cpus_read_unlock();
 	pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n");