Merge branch 'perf/vlbr'

5 files changed, 140 insertions, 56 deletions

diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 12c42eba77ec..9933c0e8e97a 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y					+= core.o probe.o
-obj-$(PERF_EVENTS_INTEL_RAPL)		+= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= rapl.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 4103665c6e03..d740c861724c 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -71,10 +71,9 @@ u64 x86_perf_event_update(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int shift = 64 - x86_pmu.cntval_bits;
 	u64 prev_raw_count, new_raw_count;
-	int idx = hwc->idx;
 	u64 delta;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
@@ -1097,22 +1096,31 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 				struct cpu_hw_events *cpuc, int i)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	int idx;
 
-	hwc->idx = cpuc->assign[i];
+	idx = hwc->idx = cpuc->assign[i];
 	hwc->last_cpu = smp_processor_id();
 	hwc->last_tag = ++cpuc->tags[i];
 
-	if (hwc->idx == INTEL_PMC_IDX_FIXED_BTS) {
+	switch (hwc->idx) {
+	case INTEL_PMC_IDX_FIXED_BTS:
+	case INTEL_PMC_IDX_FIXED_VLBR:
 		hwc->config_base = 0;
 		hwc->event_base	= 0;
-	} else if (hwc->idx >= INTEL_PMC_IDX_FIXED) {
+		break;
+
+	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 + (hwc->idx - INTEL_PMC_IDX_FIXED);
-		hwc->event_base_rdpmc = (hwc->idx - INTEL_PMC_IDX_FIXED) | 1<<30;
-	} else {
+		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
+				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) | 1<<30;
+		break;
+
+	default:
 		hwc->config_base = x86_pmu_config_addr(hwc->idx);
 		hwc->event_base  = x86_pmu_event_addr(hwc->idx);
 		hwc->event_base_rdpmc = x86_pmu_rdpmc_index(hwc->idx);
+		break;
 	}
 }
 
@@ -1233,7 +1241,7 @@ int x86_perf_event_set_period(struct perf_event *event)
 	s64 period = hwc->sample_period;
 	int ret = 0, idx = hwc->idx;
 
-	if (idx == INTEL_PMC_IDX_FIXED_BTS)
+	if (unlikely(!hwc->event_base))
 		return 0;
 
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index ca35c8b5ee10..582ddff9a359 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2136,8 +2136,35 @@ static inline void intel_pmu_ack_status(u64 ack)
 	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
 }
 
-static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+	return unlikely(event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
+static inline void intel_set_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (event->attr.exclude_host)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	if (event->attr.exclude_guest)
+		__set_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	if (event_is_checkpointed(event))
+		__set_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static inline void intel_clear_masks(struct perf_event *event, int idx)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_guest_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_ctrl_host_mask);
+	__clear_bit(idx, (unsigned long *)&cpuc->intel_cp_status);
+}
+
+static void intel_pmu_disable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
 	u64 ctrl_val, mask;
 
@@ -2148,30 +2175,22 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 	wrmsrl(hwc->config_base, ctrl_val);
 }
 
-static inline bool event_is_checkpointed(struct perf_event *event)
-{
-	return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
-}
-
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx = hwc->idx;
 
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_clear_masks(event, idx);
+		x86_pmu_disable_event(event);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_clear_masks(event, idx);
+		intel_pmu_disable_fixed(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
 		intel_pmu_disable_bts();
 		intel_pmu_drain_bts_buffer();
-		return;
-	}
-
-	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
-	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
-
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL))
-		intel_pmu_disable_fixed(hwc);
-	else
-		x86_pmu_disable_event(event);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_clear_masks(event, idx);
 
 	/*
 	 * Needs to be called after x86_pmu_disable_event,
@@ -2238,33 +2257,23 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-
-	if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
-		if (!__this_cpu_read(cpu_hw_events.enabled))
-			return;
-
-		intel_pmu_enable_bts(hwc->config);
-		return;
-	}
-
-	if (event->attr.exclude_host)
-		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
-	if (event->attr.exclude_guest)
-		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
-
-	if (unlikely(event_is_checkpointed(event)))
-		cpuc->intel_cp_status |= (1ull << hwc->idx);
+	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
 		intel_pmu_pebs_enable(event);
 
-	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		intel_set_masks(event, idx);
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx < INTEL_PMC_IDX_FIXED_BTS) {
+		intel_set_masks(event, idx);
 		intel_pmu_enable_fixed(event);
-		return;
-	}
-
-	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	} else if (idx == INTEL_PMC_IDX_FIXED_BTS) {
+		if (!__this_cpu_read(cpu_hw_events.enabled))
+			return;
+		intel_pmu_enable_bts(hwc->config);
+	} else if (idx == INTEL_PMC_IDX_FIXED_VLBR)
+		intel_set_masks(event, idx);
 }
 
 static void intel_pmu_add_event(struct perf_event *event)
@@ -2614,6 +2623,20 @@ intel_bts_constraints(struct perf_event *event)
 	return NULL;
 }
 
+/*
+ * Note: matches a fake event, like Fixed2.
+ */
+static struct event_constraint *
+intel_vlbr_constraints(struct perf_event *event)
+{
+	struct event_constraint *c = &vlbr_constraint;
+
+	if (unlikely(constraint_match(c, event->hw.config)))
+		return c;
+
+	return NULL;
+}
+
 static int intel_alt_er(int idx, u64 config)
 {
 	int alt_idx = idx;
@@ -2804,6 +2827,10 @@ __intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
+	c = intel_vlbr_constraints(event);
+	if (c)
+		return c;
+
 	c = intel_bts_constraints(event);
 	if (c)
 		return c;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 65113b16804a..d03de7539957 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -383,6 +383,9 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
+
+	if (cpuc->lbr_select)
+		wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
@@ -415,6 +418,9 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	cpuc->last_task_ctx = task_ctx;
 	cpuc->last_log_id = ++task_ctx->log_id;
+
+	if (cpuc->lbr_select)
+		rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
 }
 
 void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
@@ -485,6 +491,9 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	if (!x86_pmu.lbr_nr)
 		return;
 
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 1;
+
 	cpuc->br_sel = event->hw.branch_reg.reg;
 
 	if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) {
@@ -532,6 +541,9 @@ void intel_pmu_lbr_del(struct perf_event *event)
 		task_ctx->lbr_callstack_users--;
 	}
 
+	if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT)
+		cpuc->lbr_select = 0;
+
 	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
 		cpuc->lbr_pebs_users--;
 	cpuc->lbr_users--;
@@ -540,11 +552,19 @@ void intel_pmu_lbr_del(struct perf_event *event)
 	perf_sched_cb_dec(event->ctx->pmu);
 }
 
+static inline bool vlbr_exclude_host(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	return test_bit(INTEL_PMC_IDX_FIXED_VLBR,
+		(unsigned long *)&cpuc->intel_ctrl_guest_mask);
+}
+
 void intel_pmu_lbr_enable_all(bool pmi)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_enable(pmi);
 }
 
@@ -552,7 +572,7 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users)
+	if (cpuc->lbr_users && !vlbr_exclude_host())
 		__intel_pmu_lbr_disable();
 }
 
@@ -694,7 +714,8 @@ void intel_pmu_lbr_read(void)
 	 * This could be smarter and actually check the event,
 	 * but this simple approach seems to work for now.
 	 */
-	if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
+	if (!cpuc->lbr_users || vlbr_exclude_host() ||
+	    cpuc->lbr_users == cpuc->lbr_pebs_users)
 		return;
 
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
@@ -1343,3 +1364,27 @@ void intel_pmu_lbr_init_knl(void)
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP)
 		x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS;
 }
+
+/**
+ * x86_perf_get_lbr - get the LBR records information
+ *
+ * @lbr: the caller's memory to store the LBR records information
+ *
+ * Returns: 0 indicates the LBR info has been successfully obtained
+ */
+int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+{
+	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
+
+	lbr->nr = x86_pmu.lbr_nr;
+	lbr->from = x86_pmu.lbr_from;
+	lbr->to = x86_pmu.lbr_to;
+	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? MSR_LBR_INFO_0 : 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
+
+struct event_constraint vlbr_constraint =
+	__EVENT_CONSTRAINT(INTEL_FIXED_VLBR_EVENT, (1ULL << INTEL_PMC_IDX_FIXED_VLBR),
+			  FIXED_EVENT_FLAGS, 1, 0, PERF_X86_EVENT_LBR_SELECT);
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e17a3d8a47ed..81475963df99 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -78,6 +78,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
 #define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
 #define PERF_X86_EVENT_PAIR		0x1000 /* Large Increment per Cycle */
+#define PERF_X86_EVENT_LBR_SELECT	0x2000 /* Save/Restore MSR_LBR_SELECT */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -237,6 +238,7 @@ struct cpu_hw_events {
 	u64				br_sel;
 	struct x86_perf_task_context	*last_task_ctx;
 	int				last_log_id;
+	int				lbr_select;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -673,8 +675,8 @@ struct x86_pmu {
 	/*
 	 * Intel LBR
 	 */
-	unsigned long	lbr_tos, lbr_from, lbr_to; /* MSR base regs       */
-	int		lbr_nr;			   /* hardware stack size */
+	unsigned int	lbr_tos, lbr_from, lbr_to,
+			lbr_nr;			   /* LBR base regs and size */
 	u64		lbr_sel_mask;		   /* LBR_SELECT valid bits */
 	const int	*lbr_sel_map;		   /* lbr_select mappings */
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
@@ -722,6 +724,7 @@ struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	u64 lbr_sel;
 	int tos;
 	int valid_lbrs;
 	int lbr_callstack_users;
@@ -990,6 +993,7 @@ void release_ds_buffers(void);
 void reserve_ds_buffers(void);
 
 extern struct event_constraint bts_constraint;
+extern struct event_constraint vlbr_constraint;
 
 void intel_pmu_enable_bts(u64 config);