diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7011e87be6d0..1248fc1937f8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2143,19 +2143,19 @@ static __initconst const u64 knl_hw_cache_extra_regs
  * However, there are some cases which may change PEBS status, e.g. PMI
  * throttle. The PEBS_ENABLE should be updated where the status changes.
  */
-static void __intel_pmu_disable_all(void)
+static __always_inline void __intel_pmu_disable_all(bool bts)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
 
-	if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
+	if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
 		intel_pmu_disable_bts();
 }
 
-static void intel_pmu_disable_all(void)
+static __always_inline void intel_pmu_disable_all(void)
 {
-	__intel_pmu_disable_all();
+	__intel_pmu_disable_all(true);
 	intel_pmu_pebs_disable_all();
 	intel_pmu_lbr_disable_all();
 }
@@ -2186,6 +2186,49 @@ static void intel_pmu_enable_all(int added)
 	__intel_pmu_enable_all(added, false);
 }
 
+static noinline int
+__intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries,
+				  unsigned int cnt, unsigned long flags)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	intel_pmu_lbr_read();
+	cnt = min_t(unsigned int, cnt, x86_pmu.lbr_nr);
+
+	memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt);
+	intel_pmu_enable_all(0);
+	local_irq_restore(flags);
+	return cnt;
+}
+
+static int
+intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+
+	/* must not have branches... */
+	local_irq_save(flags);
+	__intel_pmu_disable_all(false); /* we don't care about BTS */
+	__intel_pmu_pebs_disable_all();
+	__intel_pmu_lbr_disable();
+	/*            ... until here */
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+}
+
+static int
+intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt)
+{
+	unsigned long flags;
+
+	/* must not have branches... */
+	local_irq_save(flags);
+	__intel_pmu_disable_all(false); /* we don't care about BTS */
+	__intel_pmu_pebs_disable_all();
+	__intel_pmu_arch_lbr_disable();
+	/*            ... until here */
+	return __intel_pmu_snapshot_branch_stack(entries, cnt, flags);
+}
+
 /*
  * Workaround for:
  *   Intel Errata AAK100 (model 26)
@@ -2929,7 +2972,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 		apic_write(APIC_LVTPC, APIC_DM_NMI);
 	intel_bts_disable_local();
 	cpuc->enabled = 0;
-	__intel_pmu_disable_all();
+	__intel_pmu_disable_all(true);
 	handled = intel_pmu_drain_bts_buffer();
 	handled += intel_bts_interrupt();
 	status = intel_pmu_get_status();
@@ -6283,9 +6326,21 @@ __init int intel_pmu_init(void)
 			x86_pmu.lbr_nr = 0;
 	}
 
-	if (x86_pmu.lbr_nr)
+	if (x86_pmu.lbr_nr) {
 		pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr);
 
+		/* only support branch_stack snapshot for perfmon >= v2 */
+		if (x86_pmu.disable_all == intel_pmu_disable_all) {
+			if (boot_cpu_has(X86_FEATURE_ARCH_LBR)) {
+				static_call_update(perf_snapshot_branch_stack,
+						   intel_pmu_snapshot_arch_branch_stack);
+			} else {
+				static_call_update(perf_snapshot_branch_stack,
+						   intel_pmu_snapshot_branch_stack);
+			}
+		}
+	}
+
 	intel_pmu_check_extra_regs(x86_pmu.extra_regs);
 
 	/* Support full width counters using alternative MSR range */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8647713276a7..ac5991fea9ee 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1301,7 +1301,7 @@ void intel_pmu_pebs_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
 	if (cpuc->pebs_enabled)
-		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+		__intel_pmu_pebs_disable_all();
 }
 
 static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 9e6d6eaeb4cb..6b72e9b55c69 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -228,20 +228,6 @@ static void __intel_pmu_lbr_enable(bool pmi)
 		wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
 }
 
-static void __intel_pmu_lbr_disable(void)
-{
-	u64 debugctl;
-
-	if (static_cpu_has(X86_FEATURE_ARCH_LBR)) {
-		wrmsrl(MSR_ARCH_LBR_CTL, 0);
-		return;
-	}
-
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
-}
-
 void intel_pmu_lbr_reset_32(void)
 {
 	int i;
@@ -779,8 +765,12 @@ void intel_pmu_lbr_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (cpuc->lbr_users && !vlbr_exclude_host())
+	if (cpuc->lbr_users && !vlbr_exclude_host()) {
+		if (static_cpu_has(X86_FEATURE_ARCH_LBR))
+			return __intel_pmu_arch_lbr_disable();
+
 		__intel_pmu_lbr_disable();
+	}
 }
 
 void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index e3ac05c97b5e..0e3e596e33cd 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -1240,6 +1240,25 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
+static __always_inline void __intel_pmu_pebs_disable_all(void)
+{
+	wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+}
+
+static __always_inline void __intel_pmu_arch_lbr_disable(void)
+{
+	wrmsrl(MSR_ARCH_LBR_CTL, 0);
+}
+
+static __always_inline void __intel_pmu_lbr_disable(void)
+{
+	u64 debugctl;
+
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+}
+
 int intel_pmu_save_and_restart(struct perf_event *event);
 
 struct event_constraint *
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fe156a8170aa..0cbc5dfe1110 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -57,6 +57,7 @@ struct perf_guest_info_callbacks {
 #include <linux/cgroup.h>
 #include <linux/refcount.h>
 #include <linux/security.h>
+#include <linux/static_call.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -1612,4 +1613,26 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event,
 extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr);
 #endif
 
+/*
+ * Snapshot branch stack on software events.
+ *
+ * Branch stack can be very useful in understanding software events. For
+ * example, when a long function, e.g. sys_perf_event_open, returns an
+ * errno, it is not obvious why the function failed. Branch stack could
+ * provide very helpful information in this type of scenarios.
+ *
+ * On software event, it is necessary to stop the hardware branch recorder
+ * fast. Otherwise, the hardware register/buffer will be flushed with
+ * entries of the triggering event. Therefore, static call is used to
+ * stop the hardware recorder.
+ */
+
+/*
+ * cnt is the number of entries allocated for entries.
+ * Return number of entries copied to .
+ */
+typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries,
+					   unsigned int cnt);
+DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
+
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 51cfd91cc387..d21326558d42 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4877,6 +4877,27 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5076,7 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index fe1e857324e6..39eaaff81953 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -10,6 +10,7 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/module.h>
+#include <linux/static_call.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
@@ -526,7 +527,7 @@ out:
 }
 
 #define NO_START_TIME 1
-static u64 notrace bpf_prog_start_time(void)
+static __always_inline u64 notrace bpf_prog_start_time(void)
 {
 	u64 start = NO_START_TIME;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 744e8726c5b2..349f80aa9e7d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -13435,3 +13435,5 @@ struct cgroup_subsys perf_event_cgrp_subsys = {
 	.threaded	= true,
 };
 #endif /* CONFIG_CGROUP_PERF */
+
+DEFINE_STATIC_CALL_RET0(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 8e2eb950aa82..067e88c3d2ee 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1017,6 +1017,34 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags)
+{
+#ifndef CONFIG_X86
+	return -ENOENT;
+#else
+	static const u32 br_entry_size = sizeof(struct perf_branch_entry);
+	u32 entry_cnt = size / br_entry_size;
+
+	entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt);
+
+	if (unlikely(flags))
+		return -EINVAL;
+
+	if (!entry_cnt)
+		return -ENOENT;
+
+	return entry_cnt * br_entry_size;
+#endif
+}
+
+static const struct bpf_func_proto bpf_get_branch_snapshot_proto = {
+	.func		= bpf_get_branch_snapshot,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
 static const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1132,6 +1160,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_snprintf_proto;
 	case BPF_FUNC_get_func_ip:
 		return &bpf_get_func_ip_proto_tracing;
+	case BPF_FUNC_get_branch_snapshot:
+		return &bpf_get_branch_snapshot_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 51cfd91cc387..d21326558d42 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4877,6 +4877,27 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5076,7 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 141d8da687d2..50fc5561110a 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -13,6 +13,18 @@
 
 DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
 
+noinline int bpf_testmod_loop_test(int n)
+{
+	int i, sum = 0;
+
+	/* the primary goal of this test is to test LBR. Create a lot of
+	 * branches in the function, so we can catch it easily.
+	 */
+	for (i = 0; i < n; i++)
+		sum += i;
+	return sum;
+}
+
 noinline ssize_t
 bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		      struct bin_attribute *bin_attr,
@@ -24,7 +36,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		.len = len,
 	};
 
-	trace_bpf_testmod_test_read(current, &ctx);
+	/* This is always true. Use the check to make sure the compiler
+	 * doesn't remove bpf_testmod_loop_test.
+	 */
+	if (bpf_testmod_loop_test(101) > 100)
+		trace_bpf_testmod_test_read(current, &ctx);
 
 	return -EIO; /* always fail */
 }
@@ -71,4 +87,3 @@ module_exit(bpf_testmod_exit);
 MODULE_AUTHOR("Andrii Nakryiko");
 MODULE_DESCRIPTION("BPF selftests module");
 MODULE_LICENSE("Dual BSD/GPL");
-
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 4739b15b2a97..15d355af8d1d 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -30,7 +30,7 @@ static int duration = 0;
 	.output_len = sizeof(struct core_reloc_module_output),		\
 	.prog_sec_name = sec_name,					\
 	.raw_tp_name = tp_name,						\
-	.trigger = trigger_module_test_read,				\
+	.trigger = __trigger_module_test_read,				\
 	.needs_testmod = true,						\
 }
 
@@ -475,19 +475,11 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test)
 	return 0;
 }
 
-static int trigger_module_test_read(const struct core_reloc_test_case *test)
+static int __trigger_module_test_read(const struct core_reloc_test_case *test)
 {
 	struct core_reloc_module_output *exp = (void *)test->output;
-	int fd, err;
-
-	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
-	err = -errno;
-	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err))
-		return err;
-
-	read(fd, NULL, exp->len); /* request expected number of bytes */
-	close(fd);
 
+	trigger_module_test_read(exp->len);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
new file mode 100644
index 000000000000..f81db9135ae4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "get_branch_snapshot.skel.h"
+
+static int *pfd_array;
+static int cpu_cnt;
+
+static int create_perf_events(void)
+{
+	struct perf_event_attr attr = {0};
+	int cpu;
+
+	/* create perf event */
+	attr.size = sizeof(attr);
+	attr.type = PERF_TYPE_RAW;
+	attr.config = 0x1b00;
+	attr.sample_type = PERF_SAMPLE_BRANCH_STACK;
+	attr.branch_sample_type = PERF_SAMPLE_BRANCH_KERNEL |
+		PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY;
+
+	cpu_cnt = libbpf_num_possible_cpus();
+	pfd_array = malloc(sizeof(int) * cpu_cnt);
+	if (!pfd_array) {
+		cpu_cnt = 0;
+		return 1;
+	}
+
+	for (cpu = 0; cpu < cpu_cnt; cpu++) {
+		pfd_array[cpu] = syscall(__NR_perf_event_open, &attr,
+					 -1, cpu, -1, PERF_FLAG_FD_CLOEXEC);
+		if (pfd_array[cpu] < 0)
+			break;
+	}
+
+	return cpu == 0;
+}
+
+static void close_perf_events(void)
+{
+	int cpu = 0;
+	int fd;
+
+	while (cpu++ < cpu_cnt) {
+		fd = pfd_array[cpu];
+		if (fd < 0)
+			break;
+		close(fd);
+	}
+	free(pfd_array);
+}
+
+void test_get_branch_snapshot(void)
+{
+	struct get_branch_snapshot *skel = NULL;
+	int err;
+
+	if (create_perf_events()) {
+		test__skip();  /* system doesn't support LBR */
+		goto cleanup;
+	}
+
+	skel = get_branch_snapshot__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "get_branch_snapshot__open_and_load"))
+		goto cleanup;
+
+	err = kallsyms_find("bpf_testmod_loop_test", &skel->bss->address_low);
+	if (!ASSERT_OK(err, "kallsyms_find"))
+		goto cleanup;
+
+	err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high);
+	if (!ASSERT_OK(err, "kallsyms_find_next"))
+		goto cleanup;
+
+	err = get_branch_snapshot__attach(skel);
+	if (!ASSERT_OK(err, "get_branch_snapshot__attach"))
+		goto cleanup;
+
+	trigger_module_test_read(100);
+
+	if (skel->bss->total_entries < 16) {
+		/* too few entries for the hit/waste test */
+		test__skip();
+		goto cleanup;
+	}
+
+	ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr");
+
+	/* Given we stop LBR in software, we will waste a few entries.
+	 * But we should try to waste as few as possible entries. We are at
+	 * about 7 on x86_64 systems.
+	 * Add a check for < 10 so that we get heads-up when something
+	 * changes and wastes too many entries.
+	 */
+	ASSERT_LT(skel->bss->wasted_entries, 10, "check_wasted_entries");
+
+cleanup:
+	get_branch_snapshot__destroy(skel);
+	close_perf_events();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index d85a69b7ce44..1797a6e4d6d8 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -6,45 +6,6 @@
 
 static int duration;
 
-static int trigger_module_test_read(int read_sz)
-{
-	int fd, err;
-
-	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
-	err = -errno;
-	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err))
-		return err;
-
-	read(fd, NULL, read_sz);
-	close(fd);
-
-	return 0;
-}
-
-static int trigger_module_test_write(int write_sz)
-{
-	int fd, err;
-	char *buf = malloc(write_sz);
-
-	if (!buf)
-		return -ENOMEM;
-
-	memset(buf, 'a', write_sz);
-	buf[write_sz-1] = '\0';
-
-	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
-	err = -errno;
-	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) {
-		free(buf);
-		return err;
-	}
-
-	write(fd, buf, write_sz);
-	close(fd);
-	free(buf);
-	return 0;
-}
-
 static int delete_module(const char *name, int flags)
 {
 	return syscall(__NR_delete_module, name, flags);
diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
new file mode 100644
index 000000000000..a1b139888048
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_hits = 0;
+__u64 address_low = 0;
+__u64 address_high = 0;
+int wasted_entries = 0;
+long total_entries = 0;
+
+#define ENTRY_CNT 32
+struct perf_branch_entry entries[ENTRY_CNT] = {};
+
+static inline bool in_range(__u64 val)
+{
+	return (val >= address_low) && (val < address_high);
+}
+
+SEC("fexit/bpf_testmod_loop_test")
+int BPF_PROG(test1, int n, int ret)
+{
+	long i;
+
+	total_entries = bpf_get_branch_snapshot(entries, sizeof(entries), 0);
+	total_entries /= sizeof(struct perf_branch_entry);
+
+	for (i = 0; i < ENTRY_CNT; i++) {
+		if (i >= total_entries)
+			break;
+		if (in_range(entries[i].from) && in_range(entries[i].to))
+			test1_hits++;
+		else if (!test1_hits)
+			wasted_entries++;
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index cc1cd240445d..2ed01f615d20 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -743,6 +743,45 @@ int cd_flavor_subdir(const char *exec_name)
 	return chdir(flavor);
 }
 
+int trigger_module_test_read(int read_sz)
+{
+	int fd, err;
+
+	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmod_file_open"))
+		return err;
+
+	read(fd, NULL, read_sz);
+	close(fd);
+
+	return 0;
+}
+
+int trigger_module_test_write(int write_sz)
+{
+	int fd, err;
+	char *buf = malloc(write_sz);
+
+	if (!buf)
+		return -ENOMEM;
+
+	memset(buf, 'a', write_sz);
+	buf[write_sz-1] = '\0';
+
+	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmod_file_open")) {
+		free(buf);
+		return err;
+	}
+
+	write(fd, buf, write_sz);
+	close(fd);
+	free(buf);
+	return 0;
+}
+
 #define MAX_BACKTRACE_SZ 128
 void crash_handler(int signum)
 {
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index c8c2bf878f67..94bef0aa74cf 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -291,6 +291,8 @@ int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
 int extract_build_id(char *build_id, size_t size);
 int kern_sync_rcu(void);
+int trigger_module_test_read(int read_sz);
+int trigger_module_test_write(int write_sz);
 
 #ifdef __x86_64__
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index e7a19b04d4ea..5100a169b72b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <ctype.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -117,6 +118,42 @@ out:
 	return err;
 }
 
+/* find the address of the next symbol of the same type, this can be used
+ * to determine the end of a function.
+ */
+int kallsyms_find_next(const char *sym, unsigned long long *addr)
+{
+	char type, found_type, name[500];
+	unsigned long long value;
+	bool found = false;
+	int err = 0;
+	FILE *f;
+
+	f = fopen("/proc/kallsyms", "r");
+	if (!f)
+		return -EINVAL;
+
+	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
+		/* Different types of symbols in kernel modules are mixed
+		 * in /proc/kallsyms. Only return the next matching type.
+		 * Use tolower() for type so that 'T' matches 't'.
+		 */
+		if (found && found_type == tolower(type)) {
+			*addr = value;
+			goto out;
+		}
+		if (strcmp(name, sym) == 0) {
+			found = true;
+			found_type = tolower(type);
+		}
+	}
+	err = -ENOENT;
+
+out:
+	fclose(f);
+	return err;
+}
+
 void read_trace_pipe(void)
 {
 	int trace_fd;
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index d907b445524d..bc8ed86105d9 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -16,6 +16,11 @@ long ksym_get_addr(const char *name);
 /* open kallsyms and find addresses on the fly, faster than load + search. */
 int kallsyms_find(const char *sym, unsigned long long *addr);
 
+/* find the address of the next symbol, this can be used to determine the
+ * end of a function
+ */
+int kallsyms_find_next(const char *sym, unsigned long long *addr);
+
 void read_trace_pipe(void);
 
 ssize_t get_uprobe_offset(const void *addr, ssize_t base);