1 files changed, 130 insertions, 64 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5b0dd07b1ef1..65ab6460aed4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -41,6 +41,8 @@
 #include <asm/desc.h>
 #include <asm/ldt.h>
 #include <asm/unwind.h>
+#include <asm/uprobes.h>
+#include <asm/ibt.h>
 
 #include "perf_event.h"
 
@@ -189,29 +191,31 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-static inline int get_possible_num_counters(void)
+static inline u64 get_possible_counter_mask(void)
 {
-	int i, num_counters = x86_pmu.num_counters;
+	u64 cntr_mask = x86_pmu.cntr_mask64;
+	int i;
 
 	if (!is_hybrid())
-		return num_counters;
+		return cntr_mask;
 
 	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++)
-		num_counters = max_t(int, num_counters, x86_pmu.hybrid_pmu[i].num_counters);
+		cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64;
 
-	return num_counters;
+	return cntr_mask;
 }
 
 static bool reserve_pmc_hardware(void)
 {
-	int i, num_counters = get_possible_num_counters();
+	u64 cntr_mask = get_possible_counter_mask();
+	int i, end;
 
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
 		if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
 			goto perfctr_fail;
 	}
 
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
 		if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
 			goto eventsel_fail;
 	}
@@ -219,13 +223,14 @@ static bool reserve_pmc_hardware(void)
 	return true;
 
 eventsel_fail:
-	for (i--; i >= 0; i--)
+	end = i;
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
 		release_evntsel_nmi(x86_pmu_config_addr(i));
-
-	i = num_counters;
+	i = X86_PMC_IDX_MAX;
 
 perfctr_fail:
-	for (i--; i >= 0; i--)
+	end = i;
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
 		release_perfctr_nmi(x86_pmu_event_addr(i));
 
 	return false;
@@ -233,9 +238,10 @@ perfctr_fail:
 
 static void release_pmc_hardware(void)
 {
-	int i, num_counters = get_possible_num_counters();
+	u64 cntr_mask = get_possible_counter_mask();
+	int i;
 
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
 		release_perfctr_nmi(x86_pmu_event_addr(i));
 		release_evntsel_nmi(x86_pmu_config_addr(i));
 	}
@@ -248,7 +254,8 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
-bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+		     unsigned long *fixed_cntr_mask)
 {
 	u64 val, val_fail = -1, val_new= ~0;
 	int i, reg, reg_fail = -1, ret = 0;
@@ -259,7 +266,7 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
 	 * Check to see if the BIOS enabled any of the counters, if so
 	 * complain and bail.
 	 */
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
@@ -273,12 +280,12 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
 		}
 	}
 
-	if (num_counters_fixed) {
+	if (*(u64 *)fixed_cntr_mask) {
 		reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
-		for (i = 0; i < num_counters_fixed; i++) {
+		for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
 			if (fixed_counter_disabled(i, pmu))
 				continue;
 			if (val & (0x03ULL << i*4)) {
@@ -619,7 +626,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 		event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
 
 	if (event->attr.type == event->pmu->type)
-		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
+		event->hw.config |= x86_pmu_get_event_config(event);
 
 	if (event->attr.sample_period && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
@@ -679,7 +686,7 @@ void x86_pmu_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 		u64 val;
 
@@ -736,7 +743,7 @@ void x86_pmu_enable_all(int added)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 
 		if (!test_bit(idx, cpuc->active_mask))
@@ -975,7 +982,6 @@ EXPORT_SYMBOL_GPL(perf_assign_events);
 
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
-	int num_counters = hybrid(cpuc->pmu, num_counters);
 	struct event_constraint *c;
 	struct perf_event *e;
 	int n0, i, wmin, wmax, unsched = 0;
@@ -1051,7 +1057,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 
 	/* slow path */
 	if (i != n) {
-		int gpmax = num_counters;
+		int gpmax = x86_pmu_max_num_counters(cpuc->pmu);
 
 		/*
 		 * Do not allow scheduling of more than half the available
@@ -1072,7 +1078,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		 * the extra Merge events needed by large increment events.
 		 */
 		if (x86_pmu.flags & PMU_FL_PAIR) {
-			gpmax = num_counters - cpuc->n_pair;
+			gpmax -= cpuc->n_pair;
 			WARN_ON(gpmax <= 0);
 		}
 
@@ -1157,12 +1163,10 @@ static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event,
  */
 static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
 {
-	int num_counters = hybrid(cpuc->pmu, num_counters);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	struct perf_event *event;
 	int n, max_count;
 
-	max_count = num_counters + num_counters_fixed;
+	max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu);
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
@@ -1234,8 +1238,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 		fallthrough;
 	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 +
-				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base = x86_pmu_fixed_ctr_addr(idx - INTEL_PMC_IDX_FIXED);
 		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) |
 					INTEL_PMC_FIXED_RDPMC_BASE;
 		break;
@@ -1519,19 +1522,22 @@ static void x86_pmu_start(struct perf_event *event, int flags)
 void perf_event_print_debug(void)
 {
 	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+	unsigned long *cntr_mask, *fixed_cntr_mask;
+	struct event_constraint *pebs_constraints;
+	struct cpu_hw_events *cpuc;
 	u64 pebs, debugctl;
-	int cpu = smp_processor_id();
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
-	int num_counters = hybrid(cpuc->pmu, num_counters);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
-	struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
-	unsigned long flags;
-	int idx;
+	int cpu, idx;
 
-	if (!num_counters)
-		return;
+	guard(irqsave)();
 
-	local_irq_save(flags);
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_events, cpu);
+	cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+	fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
+	pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
+
+	if (!*(u64 *)cntr_mask)
+		return;
 
 	if (x86_pmu.version >= 2) {
 		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
@@ -1555,7 +1561,7 @@ void perf_event_print_debug(void)
 	}
 	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
-	for (idx = 0; idx < num_counters; idx++) {
+	for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
 		rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
 		rdmsrl(x86_pmu_event_addr(idx), pmc_count);
 
@@ -1568,15 +1574,14 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
 			cpu, idx, prev_left);
 	}
-	for (idx = 0; idx < num_counters_fixed; idx++) {
+	for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
+		rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
 			cpu, idx, pmc_count);
 	}
-	local_irq_restore(flags);
 }
 
 void x86_pmu_stop(struct perf_event *event, int flags)
@@ -1682,7 +1687,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	 */
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -2038,18 +2043,15 @@ static void _x86_pmu_read(struct perf_event *event)
 	static_call(x86_pmu_update)(event);
 }
 
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
-			  u64 intel_ctrl)
+void x86_pmu_show_pmu_cap(struct pmu *pmu)
 {
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
-	pr_info("... generic registers:      %d\n",     num_counters);
+	pr_info("... generic registers:      %d\n",     x86_pmu_num_counters(pmu));
 	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %lu\n",
-			hweight64((((1ULL << num_counters_fixed) - 1)
-					<< INTEL_PMC_IDX_FIXED) & intel_ctrl));
-	pr_info("... event mask:             %016Lx\n", intel_ctrl);
+	pr_info("... fixed-purpose events:   %d\n",     x86_pmu_num_counters_fixed(pmu));
+	pr_info("... event mask:             %016Lx\n", hybrid(pmu, intel_ctrl));
 }
 
 static int __init init_hw_perf_events(void)
@@ -2086,7 +2088,7 @@ static int __init init_hw_perf_events(void)
 	pmu_check_apic();
 
 	/* sanity check that the hardware exists or is emulated */
-	if (!check_hw_exists(&pmu, x86_pmu.num_counters, x86_pmu.num_counters_fixed))
+	if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask))
 		goto out_bad_pmu;
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
@@ -2097,14 +2099,17 @@ static int __init init_hw_perf_events(void)
 		quirk->func();
 
 	if (!x86_pmu.intel_ctrl)
-		x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+		x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+
+	if (!x86_pmu.config_mask)
+		x86_pmu.config_mask = X86_RAW_EVENT_MASK;
 
 	perf_events_lapic_init();
 	register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
 
 	unconstrained = (struct event_constraint)
-		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
-				   0, x86_pmu.num_counters, 0, 0);
+		__EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64,
+				   0, x86_pmu_num_counters(NULL), 0, 0);
 
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
@@ -2113,11 +2118,8 @@ static int __init init_hw_perf_events(void)
 
 	pmu.attr_update = x86_pmu.attr_update;
 
-	if (!is_hybrid()) {
-		x86_pmu_show_pmu_cap(x86_pmu.num_counters,
-				     x86_pmu.num_counters_fixed,
-				     x86_pmu.intel_ctrl);
-	}
+	if (!is_hybrid())
+		x86_pmu_show_pmu_cap(NULL);
 
 	if (!x86_pmu.read)
 		x86_pmu.read = _x86_pmu_read;
@@ -2481,10 +2483,10 @@ void perf_clear_dirty_counters(void)
 	for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
 		if (i >= INTEL_PMC_IDX_FIXED) {
 			/* Metrics and fake events don't have corresponding HW counters. */
-			if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+			if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
 				continue;
 
-			wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
+			wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
 		} else {
 			wrmsrl(x86_pmu_event_addr(i), 0);
 		}
@@ -2547,6 +2549,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 			      struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
+	static DEFINE_MUTEX(rdpmc_mutex);
 	unsigned long val;
 	ssize_t ret;
 
@@ -2560,6 +2563,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 	if (x86_pmu.attr_rdpmc_broken)
 		return -ENOTSUPP;
 
+	guard(mutex)(&rdpmc_mutex);
+
 	if (val != x86_pmu.attr_rdpmc) {
 		/*
 		 * Changing into or out of never available or always available,
@@ -2813,6 +2818,46 @@ static unsigned long get_segment_base(unsigned int segment)
 	return get_desc_base(desc);
 }
 
+#ifdef CONFIG_UPROBES
+/*
+ * Heuristic-based check if uprobe is installed at the function entry.
+ *
+ * Under assumption of user code being compiled with frame pointers,
+ * `push %rbp/%ebp` is a good indicator that we indeed are.
+ *
+ * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern.
+ * If we get this wrong, captured stack trace might have one extra bogus
+ * entry, but the rest of stack trace will still be meaningful.
+ */
+static bool is_uprobe_at_func_entry(struct pt_regs *regs)
+{
+	struct arch_uprobe *auprobe;
+
+	if (!current->utask)
+		return false;
+
+	auprobe = current->utask->auprobe;
+	if (!auprobe)
+		return false;
+
+	/* push %rbp/%ebp */
+	if (auprobe->insn[0] == 0x55)
+		return true;
+
+	/* endbr64 (64-bit only) */
+	if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+		return true;
+
+	return false;
+}
+
+#else
+static bool is_uprobe_at_func_entry(struct pt_regs *regs)
+{
+	return false;
+}
+#endif /* CONFIG_UPROBES */
+
 #ifdef CONFIG_IA32_EMULATION
 
 #include <linux/compat.h>
@@ -2824,6 +2869,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 	unsigned long ss_base, cs_base;
 	struct stack_frame_ia32 frame;
 	const struct stack_frame_ia32 __user *fp;
+	u32 ret_addr;
 
 	if (user_64bit_mode(regs))
 		return 0;
@@ -2833,6 +2879,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 
 	fp = compat_ptr(ss_base + regs->bp);
 	pagefault_disable();
+
+	/* see perf_callchain_user() below for why we do this */
+	if (is_uprobe_at_func_entry(regs) &&
+	    !get_user(ret_addr, (const u32 __user *)regs->sp))
+		perf_callchain_store(entry, ret_addr);
+
 	while (entry->nr < entry->max_stack) {
 		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
@@ -2861,6 +2913,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 {
 	struct stack_frame frame;
 	const struct stack_frame __user *fp;
+	unsigned long ret_addr;
 
 	if (perf_guest_state()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2884,6 +2937,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		return;
 
 	pagefault_disable();
+
+	/*
+	 * If we are called from uprobe handler, and we are indeed at the very
+	 * entry to user function (which is normally a `push %rbp` instruction,
+	 * under assumption of application being compiled with frame pointers),
+	 * we should read return address from *regs->sp before proceeding
+	 * to follow frame pointers, otherwise we'll skip immediate caller
+	 * as %rbp is not yet setup.
+	 */
+	if (is_uprobe_at_func_entry(regs) &&
+	    !get_user(ret_addr, (const unsigned long __user *)regs->sp))
+		perf_callchain_store(entry, ret_addr);
+
 	while (entry->nr < entry->max_stack) {
 		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
@@ -2983,8 +3049,8 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 	 * base PMU holds the correct number of counters for P-cores.
 	 */
 	cap->version		= x86_pmu.version;
-	cap->num_counters_gp	= x86_pmu.num_counters;
-	cap->num_counters_fixed	= x86_pmu.num_counters_fixed;
+	cap->num_counters_gp	= x86_pmu_num_counters(NULL);
+	cap->num_counters_fixed	= x86_pmu_num_counters_fixed(NULL);
 	cap->bit_width_gp	= x86_pmu.cntval_bits;
 	cap->bit_width_fixed	= x86_pmu.cntval_bits;
 	cap->events_mask	= (unsigned int)x86_pmu.events_maskl;