diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 81431c0f0614..ed446bdcbf31 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -107,12 +107,6 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj,	\
 static struct kobj_attribute format_attr_##_var =		\
 	__ATTR(_name, 0444, __rapl_##_var##_show, NULL)
 
-#define RAPL_EVENT_DESC(_name, _config)				\
-{								\
-	.attr	= __ATTR(_name, 0444, rapl_event_show, NULL),	\
-	.config	= _config,					\
-}
-
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
 #define RAPL_EVENT_ATTR_STR(_name, v, str)				\
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1a734e0adfa7..36babfd20648 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1050,13 +1050,13 @@ retry:
 	/*
 	 * One of the few rules of preemptible RCU is that one cannot do
 	 * rcu_read_unlock() while holding a scheduler (or nested) lock when
-	 * part of the read side critical section was preemptible -- see
+	 * part of the read side critical section was irqs-enabled -- see
 	 * rcu_read_unlock_special().
 	 *
 	 * Since ctx->lock nests under rq->lock we must ensure the entire read
-	 * side critical section is non-preemptible.
+	 * side critical section has interrupts disabled.
 	 */
-	preempt_disable();
+	local_irq_save(*flags);
 	rcu_read_lock();
 	ctx = rcu_dereference(task->perf_event_ctxp[ctxn]);
 	if (ctx) {
@@ -1070,21 +1070,22 @@ retry:
 		 * if so.  If we locked the right context, then it
 		 * can't get swapped on us any more.
 		 */
-		raw_spin_lock_irqsave(&ctx->lock, *flags);
+		raw_spin_lock(&ctx->lock);
 		if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) {
-			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+			raw_spin_unlock(&ctx->lock);
 			rcu_read_unlock();
-			preempt_enable();
+			local_irq_restore(*flags);
 			goto retry;
 		}
 
 		if (!atomic_inc_not_zero(&ctx->refcount)) {
-			raw_spin_unlock_irqrestore(&ctx->lock, *flags);
+			raw_spin_unlock(&ctx->lock);
 			ctx = NULL;
 		}
 	}
 	rcu_read_unlock();
-	preempt_enable();
+	if (!ctx)
+		local_irq_restore(*flags);
 	return ctx;
 }
 
@@ -6913,6 +6914,10 @@ static int perf_tp_filter_match(struct perf_event *event,
 {
 	void *record = data->raw->data;
 
+	/* only top level events have filters set */
+	if (event->parent)
+		event = event->parent;
+
 	if (likely(!event->filter) || filter_match_preds(event->filter, record))
 		return 1;
 	return 0;
diff --git a/tools/include/linux/list.h b/tools/include/linux/list.h
index 76b014c96893..a017f1595676 100644
--- a/tools/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,3 +1,4 @@
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 812aeedaea38..f81e549ddfdb 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,2 +1,2 @@
 libbpf_version.h
-FEATURE-DUMP
+FEATURE-DUMP.libbpf
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index fc9af57b666e..a3caaf3eafbd 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -180,7 +180,7 @@ config-clean:
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
 		$(RM) LIBBPF-CFLAGS
-	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP
+	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4252fc22f78f..e176bad19bcb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -61,6 +61,60 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 	__pr_debug = debug;
 }
 
+#define STRERR_BUFSIZE  128
+
+#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
+	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
+	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
+	[ERRCODE_OFFSET(ENDIAN)]	= "Endian missmatch",
+	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
+	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
+	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
+	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
+	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err < __LIBBPF_ERRNO__START) {
+		int ret;
+
+		ret = strerror_r(err, buf, size);
+		buf[size - 1] = '\0';
+		return ret;
+	}
+
+	if (err < __LIBBPF_ERRNO__END) {
+		const char *msg;
+
+		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	snprintf(buf, size, "Unknown libbpf error %d", err);
+	buf[size - 1] = '\0';
+	return -1;
+}
+
+#define CHECK_ERR(action, err, out) do {	\
+	err = action;			\
+	if (err)			\
+		goto out;		\
+} while(0)
+
+
 /* Copied from tools/perf/util/util.h */
 #ifndef zfree
 # define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
@@ -258,7 +312,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
 	if (!obj) {
 		pr_warning("alloc memory failed for %s\n", path);
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	strcpy(obj->path, path);
@@ -305,7 +359,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 
 	if (obj_elf_valid(obj)) {
 		pr_warning("elf init: internal error\n");
-		return -EEXIST;
+		return -LIBBPF_ERRNO__LIBELF;
 	}
 
 	if (obj->efile.obj_buf_sz > 0) {
@@ -331,14 +385,14 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	if (!obj->efile.elf) {
 		pr_warning("failed to open %s as ELF file\n",
 				obj->path);
-		err = -EINVAL;
+		err = -LIBBPF_ERRNO__LIBELF;
 		goto errout;
 	}
 
 	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
 		pr_warning("failed to get EHDR from %s\n",
 				obj->path);
-		err = -EINVAL;
+		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
 	ep = &obj->efile.ehdr;
@@ -346,7 +400,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	if ((ep->e_type != ET_REL) || (ep->e_machine != 0)) {
 		pr_warning("%s is not an eBPF object file\n",
 			obj->path);
-		err = -EINVAL;
+		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
 
@@ -374,14 +428,14 @@ bpf_object__check_endianness(struct bpf_object *obj)
 			goto mismatch;
 		break;
 	default:
-		return -EINVAL;
+		return -LIBBPF_ERRNO__ENDIAN;
 	}
 
 	return 0;
 
 mismatch:
 	pr_warning("Error: endianness mismatch.\n");
-	return -EINVAL;
+	return -LIBBPF_ERRNO__ENDIAN;
 }
 
 static int
@@ -402,7 +456,7 @@ bpf_object__init_kversion(struct bpf_object *obj,
 
 	if (size != sizeof(kver)) {
 		pr_warning("invalid kver section in %s\n", obj->path);
-		return -EINVAL;
+		return -LIBBPF_ERRNO__FORMAT;
 	}
 	memcpy(&kver, data, sizeof(kver));
 	obj->kern_version = kver;
@@ -444,7 +498,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
 		pr_warning("failed to get e_shstrndx from %s\n",
 			   obj->path);
-		return -EINVAL;
+		return -LIBBPF_ERRNO__FORMAT;
 	}
 
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
@@ -456,7 +510,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (gelf_getshdr(scn, &sh) != &sh) {
 			pr_warning("failed to get section header from %s\n",
 				   obj->path);
-			err = -EINVAL;
+			err = -LIBBPF_ERRNO__FORMAT;
 			goto out;
 		}
 
@@ -464,7 +518,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (!name) {
 			pr_warning("failed to get section name from %s\n",
 				   obj->path);
-			err = -EINVAL;
+			err = -LIBBPF_ERRNO__FORMAT;
 			goto out;
 		}
 
@@ -472,7 +526,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		if (!data) {
 			pr_warning("failed to get section data from %s(%s)\n",
 				   name, obj->path);
-			err = -EINVAL;
+			err = -LIBBPF_ERRNO__FORMAT;
 			goto out;
 		}
 		pr_debug("section %s, size %ld, link %d, flags %lx, type=%d\n",
@@ -495,7 +549,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
 					   obj->path);
-				err = -EEXIST;
+				err = -LIBBPF_ERRNO__FORMAT;
 			} else
 				obj->efile.symbols = data;
 		} else if ((sh.sh_type == SHT_PROGBITS) &&
@@ -504,7 +558,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			err = bpf_object__add_program(obj, data->d_buf,
 						      data->d_size, name, idx);
 			if (err) {
-				char errmsg[128];
+				char errmsg[STRERR_BUFSIZE];
+
 				strerror_r(-err, errmsg, sizeof(errmsg));
 				pr_warning("failed to alloc program %s (%s): %s",
 					   name, obj->path, errmsg);
@@ -576,7 +631,7 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 
 		if (!gelf_getrel(data, i, &rel)) {
 			pr_warning("relocation: failed to get %d reloc\n", i);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__FORMAT;
 		}
 
 		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
@@ -587,20 +642,20 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 				 &sym)) {
 			pr_warning("relocation: symbol %"PRIx64" not found\n",
 				   GELF_R_SYM(rel.r_info));
-			return -EINVAL;
+			return -LIBBPF_ERRNO__FORMAT;
 		}
 
 		if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
 			pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
 				   insn_idx, insns[insn_idx].code);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 
 		map_idx = sym.st_value / sizeof(struct bpf_map_def);
 		if (map_idx >= nr_maps) {
 			pr_warning("bpf relocation: map_idx %d large than %d\n",
 				   (int)map_idx, (int)nr_maps - 1);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 
 		prog->reloc_desc[i].insn_idx = insn_idx;
@@ -683,7 +738,7 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds)
 		if (insn_idx >= (int)prog->insns_cnt) {
 			pr_warning("relocation out of range: '%s'\n",
 				   prog->section_name);
-			return -ERANGE;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
 		insns[insn_idx].imm = map_fds[map_idx];
@@ -721,7 +776,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 	if (!obj_elf_valid(obj)) {
 		pr_warning("Internal error: elf object is closed\n");
-		return -EINVAL;
+		return -LIBBPF_ERRNO__INTERNAL;
 	}
 
 	for (i = 0; i < obj->efile.nr_reloc; i++) {
@@ -734,21 +789,21 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warning("internal error at %d\n", __LINE__);
-			return -EINVAL;
+			return -LIBBPF_ERRNO__INTERNAL;
 		}
 
 		prog = bpf_object__find_prog_by_idx(obj, idx);
 		if (!prog) {
 			pr_warning("relocation failed: no %d section\n",
 				   idx);
-			return -ENOENT;
+			return -LIBBPF_ERRNO__RELOC;
 		}
 
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
 						 obj->efile.symbols);
 		if (err)
-			return -EINVAL;
+			return err;
 	}
 	return 0;
 }
@@ -777,13 +832,23 @@ load_program(struct bpf_insn *insns, int insns_cnt,
 		goto out;
 	}
 
-	ret = -EINVAL;
+	ret = -LIBBPF_ERRNO__LOAD;
 	pr_warning("load bpf program failed: %s\n", strerror(errno));
 
-	if (log_buf) {
+	if (log_buf && log_buf[0] != '\0') {
+		ret = -LIBBPF_ERRNO__VERIFY;
 		pr_warning("-- BEGIN DUMP LOG ---\n");
 		pr_warning("\n%s\n", log_buf);
 		pr_warning("-- END LOG --\n");
+	} else {
+		if (insns_cnt >= BPF_MAXINSNS) {
+			pr_warning("Program too large (%d insns), at most %d insns\n",
+				   insns_cnt, BPF_MAXINSNS);
+			ret = -LIBBPF_ERRNO__PROG2BIG;
+		} else if (log_buf) {
+			pr_warning("log buffer is empty\n");
+			ret = -LIBBPF_ERRNO__KVER;
+		}
 	}
 
 out:
@@ -831,7 +896,7 @@ static int bpf_object__validate(struct bpf_object *obj)
 	if (obj->kern_version == 0) {
 		pr_warning("%s doesn't provide kernel version\n",
 			   obj->path);
-		return -EINVAL;
+		return -LIBBPF_ERRNO__KVERSION;
 	}
 	return 0;
 }
@@ -840,32 +905,28 @@ static struct bpf_object *
 __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
+	int err;
 
 	if (elf_version(EV_CURRENT) == EV_NONE) {
 		pr_warning("failed to init libelf for %s\n", path);
-		return NULL;
+		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
 	obj = bpf_object__new(path, obj_buf, obj_buf_sz);
-	if (!obj)
-		return NULL;
+	if (IS_ERR(obj))
+		return obj;
 
-	if (bpf_object__elf_init(obj))
-		goto out;
-	if (bpf_object__check_endianness(obj))
-		goto out;
-	if (bpf_object__elf_collect(obj))
-		goto out;
-	if (bpf_object__collect_reloc(obj))
-		goto out;
-	if (bpf_object__validate(obj))
-		goto out;
+	CHECK_ERR(bpf_object__elf_init(obj), err, out);
+	CHECK_ERR(bpf_object__check_endianness(obj), err, out);
+	CHECK_ERR(bpf_object__elf_collect(obj), err, out);
+	CHECK_ERR(bpf_object__collect_reloc(obj), err, out);
+	CHECK_ERR(bpf_object__validate(obj), err, out);
 
 	bpf_object__elf_finish(obj);
 	return obj;
 out:
 	bpf_object__close(obj);
-	return NULL;
+	return ERR_PTR(err);
 }
 
 struct bpf_object *bpf_object__open(const char *path)
@@ -922,6 +983,8 @@ int bpf_object__unload(struct bpf_object *obj)
 
 int bpf_object__load(struct bpf_object *obj)
 {
+	int err;
+
 	if (!obj)
 		return -EINVAL;
 
@@ -931,18 +994,16 @@ int bpf_object__load(struct bpf_object *obj)
 	}
 
 	obj->loaded = true;
-	if (bpf_object__create_maps(obj))
-		goto out;
-	if (bpf_object__relocate(obj))
-		goto out;
-	if (bpf_object__load_progs(obj))
-		goto out;
+
+	CHECK_ERR(bpf_object__create_maps(obj), err, out);
+	CHECK_ERR(bpf_object__relocate(obj), err, out);
+	CHECK_ERR(bpf_object__load_progs(obj), err, out);
 
 	return 0;
 out:
 	bpf_object__unload(obj);
 	pr_warning("failed to load object '%s'\n", obj->path);
-	return -EINVAL;
+	return err;
 }
 
 void bpf_object__close(struct bpf_object *obj)
@@ -990,10 +1051,18 @@ const char *
 bpf_object__get_name(struct bpf_object *obj)
 {
 	if (!obj)
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	return obj->path;
 }
 
+unsigned int
+bpf_object__get_kversion(struct bpf_object *obj)
+{
+	if (!obj)
+		return 0;
+	return obj->kern_version;
+}
+
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
@@ -1034,16 +1103,16 @@ int bpf_program__get_private(struct bpf_program *prog, void **ppriv)
 	return 0;
 }
 
-const char *bpf_program__title(struct bpf_program *prog, bool dup)
+const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
 {
 	const char *title;
 
 	title = prog->section_name;
-	if (dup) {
+	if (needs_copy) {
 		title = strdup(title);
 		if (!title) {
 			pr_warning("failed to strdup program title\n");
-			return NULL;
+			return ERR_PTR(-ENOMEM);
 		}
 	}
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f16170c95ffd..c9a9aef2806c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,26 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/err.h>
+
+enum libbpf_errno {
+	__LIBBPF_ERRNO__START = 4000,
+
+	/* Something wrong in libelf */
+	LIBBPF_ERRNO__LIBELF = __LIBBPF_ERRNO__START,
+	LIBBPF_ERRNO__FORMAT,	/* BPF object format invalid */
+	LIBBPF_ERRNO__KVERSION,	/* Incorrect or no 'version' section */
+	LIBBPF_ERRNO__ENDIAN,	/* Endian missmatch */
+	LIBBPF_ERRNO__INTERNAL,	/* Internal error in libbpf */
+	LIBBPF_ERRNO__RELOC,	/* Relocation failed */
+	LIBBPF_ERRNO__LOAD,	/* Load program failure for unknown reason */
+	LIBBPF_ERRNO__VERIFY,	/* Kernel verifier blocks program loading */
+	LIBBPF_ERRNO__PROG2BIG,	/* Program too big */
+	LIBBPF_ERRNO__KVER,	/* Incorrect kernel version */
+	__LIBBPF_ERRNO__END,
+};
+
+int libbpf_strerror(int err, char *buf, size_t size);
 
 /*
  * In include/linux/compiler-gcc.h, __printf is defined. However
@@ -36,6 +56,7 @@ void bpf_object__close(struct bpf_object *object);
 int bpf_object__load(struct bpf_object *obj);
 int bpf_object__unload(struct bpf_object *obj);
 const char *bpf_object__get_name(struct bpf_object *obj);
+unsigned int bpf_object__get_kversion(struct bpf_object *obj);
 
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
@@ -63,7 +84,7 @@ int bpf_program__set_private(struct bpf_program *prog, void *priv,
 int bpf_program__get_private(struct bpf_program *prog,
 			     void **ppriv);
 
-const char *bpf_program__title(struct bpf_program *prog, bool dup);
+const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__fd(struct bpf_program *prog);
 
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 7ea078658a87..13293de8869f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -62,7 +62,6 @@ OPTIONS
 --verbose=::
         Verbosity level.
 
--i::
 --no-inherit::
 	Child tasks do not inherit counters.
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 480546d5f13b..dcd9a70c7193 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -78,7 +78,7 @@ clean:
 # The build-test target is not really parallel, don't print the jobs info:
 #
 build-test:
-	@$(MAKE) -f tests/make --no-print-directory
+	@$(MAKE) SHUF=1 -f tests/make --no-print-directory
 
 #
 # All other targets get passed through:
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 0ee6d900e100..e3d3e32c0a93 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1203,12 +1203,13 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
+	if (l->thread == r->thread)
+		return 0;
 	if (l->thread->tid < r->thread->tid)
 		return -1;
 	if (l->thread->tid > r->thread->tid)
 		return 1;
-
-	return 0;
+	return (int)(l->thread - r->thread);
 }
 
 static int avg_cmp(struct work_atoms *l, struct work_atoms *r)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 2f438f76cceb..e77880b5094d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,9 @@ static bool			forever				= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
+static bool			append_file;
+static const char		*output_name;
+static int			output_fd;
 
 static volatile int done = 0;
 
@@ -513,15 +516,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-
-	if (csv_output || stat_config.interval)
-		return;
-
-	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		fprintf(output, " # %8.3f CPUs utilized          ",
-			avg / avg_stats(&walltime_nsecs_stats));
-	else
-		fprintf(output, "                                   ");
 }
 
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
@@ -529,7 +523,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	FILE *output = stat_config.output;
 	double sc =  evsel->scale;
 	const char *fmt;
-	int cpu = cpu_map__id_to_cpu(id);
 
 	if (csv_output) {
 		fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
@@ -542,9 +535,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	aggr_printout(evsel, id, nr);
 
-	if (stat_config.aggr_mode == AGGR_GLOBAL)
-		cpu = 0;
-
 	fprintf(output, fmt, avg, csv_sep);
 
 	if (evsel->unit)
@@ -556,12 +546,24 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
+}
 
-	if (csv_output || stat_config.interval)
-		return;
+static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+{
+	int cpu = cpu_map__id_to_cpu(id);
 
-	perf_stat__print_shadow_stats(output, evsel, avg, cpu,
-				      stat_config.aggr_mode);
+	if (stat_config.aggr_mode == AGGR_GLOBAL)
+		cpu = 0;
+
+	if (nsec_counter(counter))
+		nsec_printout(id, nr, counter, uval);
+	else
+		abs_printout(id, nr, counter, uval);
+
+	if (!csv_output && !stat_config.interval)
+		perf_stat__print_shadow_stats(stat_config.output, counter,
+					      uval, cpu,
+					      stat_config.aggr_mode);
 }
 
 static void print_aggr(char *prefix)
@@ -617,12 +619,7 @@ static void print_aggr(char *prefix)
 				continue;
 			}
 			uval = val * counter->scale;
-
-			if (nsec_counter(counter))
-				nsec_printout(id, nr, counter, uval);
-			else
-				abs_printout(id, nr, counter, uval);
-
+			printout(id, nr, counter, uval);
 			if (!csv_output)
 				print_noise(counter, 1.0);
 
@@ -653,11 +650,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(thread, 0, counter, uval);
-		else
-			abs_printout(thread, 0, counter, uval);
+		printout(thread, 0, counter, uval);
 
 		if (!csv_output)
 			print_noise(counter, 1.0);
@@ -707,11 +700,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 	}
 
 	uval = avg * counter->scale;
-
-	if (nsec_counter(counter))
-		nsec_printout(-1, 0, counter, uval);
-	else
-		abs_printout(-1, 0, counter, uval);
+	printout(-1, 0, counter, uval);
 
 	print_noise(counter, avg);
 
@@ -764,12 +753,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 		}
 
 		uval = val * counter->scale;
-
-		if (nsec_counter(counter))
-			nsec_printout(cpu, 0, counter, uval);
-		else
-			abs_printout(cpu, 0, counter, uval);
-
+		printout(cpu, 0, counter, uval);
 		if (!csv_output)
 			print_noise(counter, 1.0);
 		print_running(run, ena);
@@ -946,6 +930,67 @@ static int stat__set_big_num(const struct option *opt __maybe_unused,
 	return 0;
 }
 
+static const struct option stat_options[] = {
+	OPT_BOOLEAN('T', "transaction", &transaction_run,
+		    "hardware transaction statistics"),
+	OPT_CALLBACK('e', "event", &evsel_list, "event",
+		     "event selector. use 'perf list' to list available events",
+		     parse_events_option),
+	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
+		     "event filter", parse_filter),
+	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+		    "child tasks do not inherit counters"),
+	OPT_STRING('p', "pid", &target.pid, "pid",
+		   "stat events on existing process id"),
+	OPT_STRING('t', "tid", &target.tid, "tid",
+		   "stat events on existing thread id"),
+	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
+		    "system-wide collection from all CPUs"),
+	OPT_BOOLEAN('g', "group", &group,
+		    "put the counters into a counter group"),
+	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
+	OPT_INCR('v', "verbose", &verbose,
+		    "be more verbose (show counter open errors, etc)"),
+	OPT_INTEGER('r', "repeat", &run_count,
+		    "repeat command and print average + stddev (max: 100, forever: 0)"),
+	OPT_BOOLEAN('n', "null", &null_run,
+		    "null run - dont start any counters"),
+	OPT_INCR('d', "detailed", &detailed_run,
+		    "detailed run - start a lot of events"),
+	OPT_BOOLEAN('S', "sync", &sync_run,
+		    "call sync() before starting a run"),
+	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
+			   "print large numbers with thousands\' separators",
+			   stat__set_big_num),
+	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
+		    "list of cpus to monitor in system-wide"),
+	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
+		    "disable CPU count aggregation", AGGR_NONE),
+	OPT_STRING('x', "field-separator", &csv_sep, "separator",
+		   "print counts with custom separator"),
+	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
+		     "monitor event in cgroup name only", parse_cgroups),
+	OPT_STRING('o', "output", &output_name, "file", "output file name"),
+	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
+	OPT_INTEGER(0, "log-fd", &output_fd,
+		    "log output to fd, instead of stderr"),
+	OPT_STRING(0, "pre", &pre_cmd, "command",
+			"command to run prior to the measured command"),
+	OPT_STRING(0, "post", &post_cmd, "command",
+			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
+		    "print counts at regular interval in ms (>= 10)"),
+	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
+		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
+	OPT_UINTEGER('D', "delay", &initial_delay,
+		     "ms to wait before starting measurement after program start"),
+	OPT_END()
+};
+
 static int perf_stat__get_socket(struct cpu_map *map, int cpu)
 {
 	return cpu_map__get_socket(map, cpu, NULL);
@@ -1193,69 +1238,6 @@ static int add_default_attributes(void)
 
 int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	bool append_file = false;
-	int output_fd = 0;
-	const char *output_name	= NULL;
-	const struct option options[] = {
-	OPT_BOOLEAN('T', "transaction", &transaction_run,
-		    "hardware transaction statistics"),
-	OPT_CALLBACK('e', "event", &evsel_list, "event",
-		     "event selector. use 'perf list' to list available events",
-		     parse_events_option),
-	OPT_CALLBACK(0, "filter", &evsel_list, "filter",
-		     "event filter", parse_filter),
-	OPT_BOOLEAN('i', "no-inherit", &no_inherit,
-		    "child tasks do not inherit counters"),
-	OPT_STRING('p', "pid", &target.pid, "pid",
-		   "stat events on existing process id"),
-	OPT_STRING('t', "tid", &target.tid, "tid",
-		   "stat events on existing thread id"),
-	OPT_BOOLEAN('a', "all-cpus", &target.system_wide,
-		    "system-wide collection from all CPUs"),
-	OPT_BOOLEAN('g', "group", &group,
-		    "put the counters into a counter group"),
-	OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"),
-	OPT_INCR('v', "verbose", &verbose,
-		    "be more verbose (show counter open errors, etc)"),
-	OPT_INTEGER('r', "repeat", &run_count,
-		    "repeat command and print average + stddev (max: 100, forever: 0)"),
-	OPT_BOOLEAN('n', "null", &null_run,
-		    "null run - dont start any counters"),
-	OPT_INCR('d', "detailed", &detailed_run,
-		    "detailed run - start a lot of events"),
-	OPT_BOOLEAN('S', "sync", &sync_run,
-		    "call sync() before starting a run"),
-	OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
-			   "print large numbers with thousands\' separators",
-			   stat__set_big_num),
-	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
-		    "list of cpus to monitor in system-wide"),
-	OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode,
-		    "disable CPU count aggregation", AGGR_NONE),
-	OPT_STRING('x', "field-separator", &csv_sep, "separator",
-		   "print counts with custom separator"),
-	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
-		     "monitor event in cgroup name only", parse_cgroups),
-	OPT_STRING('o', "output", &output_name, "file", "output file name"),
-	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
-	OPT_INTEGER(0, "log-fd", &output_fd,
-		    "log output to fd, instead of stderr"),
-	OPT_STRING(0, "pre", &pre_cmd, "command",
-			"command to run prior to the measured command"),
-	OPT_STRING(0, "post", &post_cmd, "command",
-			"command to run after to the measured command"),
-	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
-		    "print counts at regular interval in ms (>= 10)"),
-	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
-		     "aggregate counts per processor socket", AGGR_SOCKET),
-	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
-		     "aggregate counts per physical processor core", AGGR_CORE),
-	OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode,
-		     "aggregate counts per thread", AGGR_THREAD),
-	OPT_UINTEGER('D', "delay", &initial_delay,
-		     "ms to wait before starting measurement after program start"),
-	OPT_END()
-	};
 	const char * const stat_usage[] = {
 		"perf stat [<options>] [<command>]",
 		NULL
@@ -1271,7 +1253,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (evsel_list == NULL)
 		return -ENOMEM;
 
-	argc = parse_options(argc, argv, options, stat_usage,
+	argc = parse_options(argc, argv, stat_options, stat_usage,
 		PARSE_OPT_STOP_AT_NON_OPTION);
 
 	interval = stat_config.interval;
@@ -1281,14 +1263,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (output_name && output_fd) {
 		fprintf(stderr, "cannot use both --output and --log-fd\n");
-		parse_options_usage(stat_usage, options, "o", 1);
-		parse_options_usage(NULL, options, "log-fd", 0);
+		parse_options_usage(stat_usage, stat_options, "o", 1);
+		parse_options_usage(NULL, stat_options, "log-fd", 0);
 		goto out;
 	}
 
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
-		parse_options_usage(stat_usage, options, "log-fd", 0);
+		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
 		goto out;
 	}
 
@@ -1328,8 +1310,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
-			parse_options_usage(stat_usage, options, "B", 1);
-			parse_options_usage(NULL, options, "x", 1);
+			parse_options_usage(stat_usage, stat_options, "B", 1);
+			parse_options_usage(NULL, stat_options, "x", 1);
 			goto out;
 		} else /* Nope, so disable big number formatting */
 			big_num = false;
@@ -1337,11 +1319,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		big_num = false;
 
 	if (!argc && target__none(&target))
-		usage_with_options(stat_usage, options);
+		usage_with_options(stat_usage, stat_options);
 
 	if (run_count < 0) {
 		pr_err("Run count must be a positive number\n");
-		parse_options_usage(stat_usage, options, "r", 1);
+		parse_options_usage(stat_usage, stat_options, "r", 1);
 		goto out;
 	} else if (run_count == 0) {
 		forever = true;
@@ -1351,8 +1333,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
 		fprintf(stderr, "The --per-thread option is only available "
 			"when monitoring via -p -t options.\n");
-		parse_options_usage(NULL, options, "p", 1);
-		parse_options_usage(NULL, options, "t", 1);
+		parse_options_usage(NULL, stat_options, "p", 1);
+		parse_options_usage(NULL, stat_options, "t", 1);
 		goto out;
 	}
 
@@ -1366,9 +1348,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
 
-		parse_options_usage(stat_usage, options, "G", 1);
-		parse_options_usage(NULL, options, "A", 1);
-		parse_options_usage(NULL, options, "a", 1);
+		parse_options_usage(stat_usage, stat_options, "G", 1);
+		parse_options_usage(NULL, stat_options, "A", 1);
+		parse_options_usage(NULL, stat_options, "a", 1);
 		goto out;
 	}
 
@@ -1380,12 +1362,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(evsel_list, &target) < 0) {
 		if (target__has_task(&target)) {
 			pr_err("Problems finding threads of monitor\n");
-			parse_options_usage(stat_usage, options, "p", 1);
-			parse_options_usage(NULL, options, "t", 1);
+			parse_options_usage(stat_usage, stat_options, "p", 1);
+			parse_options_usage(NULL, stat_options, "t", 1);
 		} else if (target__has_cpu(&target)) {
 			perror("failed to parse CPUs map");
-			parse_options_usage(stat_usage, options, "C", 1);
-			parse_options_usage(NULL, options, "a", 1);
+			parse_options_usage(stat_usage, stat_options, "C", 1);
+			parse_options_usage(NULL, stat_options, "a", 1);
 		}
 		goto out;
 	}
@@ -1400,7 +1382,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (interval && interval < 100) {
 		if (interval < 10) {
 			pr_err("print interval must be >= 10ms\n");
-			parse_options_usage(stat_usage, options, "I", 1);
+			parse_options_usage(stat_usage, stat_options, "I", 1);
 			goto out;
 		} else
 			pr_warning("print interval < 100ms. "
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
new file mode 100644
index 000000000000..489fc9ffbcb0
--- /dev/null
+++ b/tools/perf/tests/.gitignore
@@ -0,0 +1,2 @@
+llvm-src-base.c
+llvm-src-kbuild.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 50de2253cff6..f41ebf8849fe 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,9 +31,24 @@ perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o
+perf-y += bpf.o
 perf-y += topology.o
 
+$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_base_prog[] =' >> $@
+	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+	$(Q)echo ';' >> $@
+
+$(OUTPUT)tests/llvm-src-kbuild.c: tests/bpf-script-test-kbuild.c
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_test_kbuild_prog[] =' >> $@
+	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+	$(Q)echo ';' >> $@
+
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 2dfc9ad0e6f2..638875a0960a 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -171,6 +171,5 @@ int test__attr(void)
 	    !lstat(path_perf, &st))
 		return run_dir(path_dir, path_perf);
 
-	fprintf(stderr, " (omitted)");
-	return 0;
+	return TEST_SKIP;
 }
diff --git a/tools/perf/tests/bpf-script-example.c b/tools/perf/tests/bpf-script-example.c
index 410a70b93b93..0ec9c2c03164 100644
--- a/tools/perf/tests/bpf-script-example.c
+++ b/tools/perf/tests/bpf-script-example.c
@@ -1,3 +1,7 @@
+/*
+ * bpf-script-example.c
+ * Test basic LLVM building
+ */
 #ifndef LINUX_VERSION_CODE
 # error Need LINUX_VERSION_CODE
 # error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
diff --git a/tools/perf/tests/bpf-script-test-kbuild.c b/tools/perf/tests/bpf-script-test-kbuild.c
new file mode 100644
index 000000000000..3626924740d8
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-kbuild.c
@@ -0,0 +1,21 @@
+/*
+ * bpf-script-test-kbuild.c
+ * Test include from kernel header
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define SEC(NAME) __attribute__((section(NAME), used))
+
+#include <uapi/linux/fs.h>
+#include <uapi/asm/ptrace.h>
+
+SEC("func=vfs_llseek")
+int bpf_func__vfs_llseek(void *ctx)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
new file mode 100644
index 000000000000..ec16f7812c8b
--- /dev/null
+++ b/tools/perf/tests/bpf.c
@@ -0,0 +1,209 @@
+#include <stdio.h>
+#include <sys/epoll.h>
+#include <util/bpf-loader.h>
+#include <util/evlist.h>
+#include "tests.h"
+#include "llvm.h"
+#include "debug.h"
+#define NR_ITERS       111
+
+#ifdef HAVE_LIBBPF_SUPPORT
+
+static int epoll_pwait_loop(void)
+{
+	int i;
+
+	/* Should fail NR_ITERS times */
+	for (i = 0; i < NR_ITERS; i++)
+		epoll_pwait(-(i + 1), NULL, 0, 0, NULL);
+	return 0;
+}
+
+static struct {
+	enum test_llvm__testcase prog_id;
+	const char *desc;
+	const char *name;
+	const char *msg_compile_fail;
+	const char *msg_load_fail;
+	int (*target_func)(void);
+	int expect_result;
+} bpf_testcase_table[] = {
+	{
+		LLVM_TESTCASE_BASE,
+		"Test basic BPF filtering",
+		"[basic_bpf_test]",
+		"fix 'perf test LLVM' first",
+		"load bpf object failed",
+		&epoll_pwait_loop,
+		(NR_ITERS + 1) / 2,
+	},
+};
+
+static int do_test(struct bpf_object *obj, int (*func)(void),
+		   int expect)
+{
+	struct record_opts opts = {
+		.target = {
+			.uid = UINT_MAX,
+			.uses_mmap = true,
+		},
+		.freq	      = 0,
+		.mmap_pages   = 256,
+		.default_interval = 1,
+	};
+
+	char pid[16];
+	char sbuf[STRERR_BUFSIZE];
+	struct perf_evlist *evlist;
+	int i, ret = TEST_FAIL, err = 0, count = 0;
+
+	struct parse_events_evlist parse_evlist;
+	struct parse_events_error parse_error;
+
+	bzero(&parse_error, sizeof(parse_error));
+	bzero(&parse_evlist, sizeof(parse_evlist));
+	parse_evlist.error = &parse_error;
+	INIT_LIST_HEAD(&parse_evlist.list);
+
+	err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
+	if (err || list_empty(&parse_evlist.list)) {
+		pr_debug("Failed to add events selected by BPF\n");
+		if (!err)
+			return TEST_FAIL;
+	}
+
+	snprintf(pid, sizeof(pid), "%d", getpid());
+	pid[sizeof(pid) - 1] = '\0';
+	opts.target.tid = opts.target.pid = pid;
+
+	/* Instead of perf_evlist__new_default, don't add default events */
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		pr_debug("No ehough memory to create evlist\n");
+		return TEST_FAIL;
+	}
+
+	err = perf_evlist__create_maps(evlist, &opts.target);
+	if (err < 0) {
+		pr_debug("Not enough memory to create thread/cpu maps\n");
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__splice_list_tail(evlist, &parse_evlist.list);
+	evlist->nr_groups = parse_evlist.nr_groups;
+
+	perf_evlist__config(evlist, &opts);
+
+	err = perf_evlist__open(evlist);
+	if (err < 0) {
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
+	if (err < 0) {
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
+		goto out_delete_evlist;
+	}
+
+	perf_evlist__enable(evlist);
+	(*func)();
+	perf_evlist__disable(evlist);
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		union perf_event *event;
+
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			const u32 type = event->header.type;
+
+			if (type == PERF_RECORD_SAMPLE)
+				count ++;
+		}
+	}
+
+	if (count != expect)
+		pr_debug("BPF filter result incorrect\n");
+
+	ret = TEST_OK;
+
+out_delete_evlist:
+	perf_evlist__delete(evlist);
+	return ret;
+}
+
+static struct bpf_object *
+prepare_bpf(void *obj_buf, size_t obj_buf_sz, const char *name)
+{
+	struct bpf_object *obj;
+
+	obj = bpf__prepare_load_buffer(obj_buf, obj_buf_sz, name);
+	if (IS_ERR(obj)) {
+		pr_debug("Compile BPF program failed.\n");
+		return NULL;
+	}
+	return obj;
+}
+
+static int __test__bpf(int index)
+{
+	int ret;
+	void *obj_buf;
+	size_t obj_buf_sz;
+	struct bpf_object *obj;
+
+	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+				       bpf_testcase_table[index].prog_id,
+				       true);
+	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
+		pr_debug("Unable to get BPF object, %s\n",
+			 bpf_testcase_table[index].msg_compile_fail);
+		if (index == 0)
+			return TEST_SKIP;
+		else
+			return TEST_FAIL;
+	}
+
+	obj = prepare_bpf(obj_buf, obj_buf_sz,
+			  bpf_testcase_table[index].name);
+	if (!obj) {
+		ret = TEST_FAIL;
+		goto out;
+	}
+
+	ret = do_test(obj,
+		      bpf_testcase_table[index].target_func,
+		      bpf_testcase_table[index].expect_result);
+out:
+	bpf__clear();
+	return ret;
+}
+
+int test__bpf(void)
+{
+	unsigned int i;
+	int err;
+
+	if (geteuid() != 0) {
+		pr_debug("Only root can run BPF test\n");
+		return TEST_SKIP;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(bpf_testcase_table); i++) {
+		err = __test__bpf(i);
+
+		if (err != TEST_OK)
+			return err;
+	}
+
+	return TEST_OK;
+}
+
+#else
+int test__bpf(void)
+{
+	pr_debug("Skip BPF test because BPF support is not compiled\n");
+	return TEST_SKIP;
+}
+#endif
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 66f72d3d6677..80c442eab767 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -165,6 +165,10 @@ static struct test generic_tests[] = {
 		.desc = "Test topology in session",
 		.func = test_session_topology,
 	},
+	{
+		.desc = "Test BPF filter",
+		.func = test__bpf,
+	},
 	{
 		.func = NULL,
 	},
@@ -192,7 +196,7 @@ static bool perf_test__matches(struct test *test, int curr, int argc, const char
 			continue;
 		}
 
-		if (strstr(test->desc, argv[i]))
+		if (strcasestr(test->desc, argv[i]))
 			return true;
 	}
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 49b1959dda41..a767a6400c5c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -613,16 +613,16 @@ int test__code_reading(void)
 	case TEST_CODE_READING_OK:
 		return 0;
 	case TEST_CODE_READING_NO_VMLINUX:
-		fprintf(stderr, " (no vmlinux)");
+		pr_debug("no vmlinux\n");
 		return 0;
 	case TEST_CODE_READING_NO_KCORE:
-		fprintf(stderr, " (no kcore)");
+		pr_debug("no kcore\n");
 		return 0;
 	case TEST_CODE_READING_NO_ACCESS:
-		fprintf(stderr, " (no access)");
+		pr_debug("no access\n");
 		return 0;
 	case TEST_CODE_READING_NO_KERNEL_OBJ:
-		fprintf(stderr, " (no kernel obj)");
+		pr_debug("no kernel obj\n");
 		return 0;
 	default:
 		return -1;
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 4d4b9837b630..a2e2269aa093 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -90,8 +90,8 @@ int test__keep_tracking(void)
 	evsel->attr.enable_on_exec = 0;
 
 	if (perf_evlist__open(evlist) < 0) {
-		fprintf(stderr, " (not supported)");
-		err = 0;
+		pr_debug("Unable to open dummy and cycles event\n");
+		err = TEST_SKIP;
 		goto out_err;
 	}
 
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 52d55971f66f..bc4cf507cde5 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -2,6 +2,7 @@
 #include <bpf/libbpf.h>
 #include <util/llvm-utils.h>
 #include <util/cache.h>
+#include "llvm.h"
 #include "tests.h"
 #include "debug.h"
 
@@ -11,42 +12,58 @@ static int perf_config_cb(const char *var, const char *val,
 	return perf_default_config(var, val, arg);
 }
 
-/*
- * Randomly give it a "version" section since we don't really load it
- * into kernel
- */
-static const char test_bpf_prog[] =
-	"__attribute__((section(\"do_fork\"), used)) "
-	"int fork(void *ctx) {return 0;} "
-	"char _license[] __attribute__((section(\"license\"), used)) = \"GPL\";"
-	"int _version __attribute__((section(\"version\"), used)) = 0x40100;";
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
 
 	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
-	if (!obj)
-		return -1;
+	if (IS_ERR(obj))
+		return TEST_FAIL;
 	bpf_object__close(obj);
-	return 0;
+	return TEST_OK;
 }
 #else
 static int test__bpf_parsing(void *obj_buf __maybe_unused,
 			     size_t obj_buf_sz __maybe_unused)
 {
-	fprintf(stderr, " (skip bpf parsing)");
-	return 0;
+	pr_debug("Skip bpf parsing\n");
+	return TEST_OK;
 }
 #endif
 
-int test__llvm(void)
+static struct {
+	const char *source;
+	const char *desc;
+} bpf_source_table[__LLVM_TESTCASE_MAX] = {
+	[LLVM_TESTCASE_BASE] = {
+		.source = test_llvm__bpf_base_prog,
+		.desc = "Basic BPF llvm compiling test",
+	},
+	[LLVM_TESTCASE_KBUILD] = {
+		.source = test_llvm__bpf_test_kbuild_prog,
+		.desc = "Test kbuild searching",
+	},
+};
+
+
+int
+test_llvm__fetch_bpf_obj(void **p_obj_buf,
+			 size_t *p_obj_buf_sz,
+			 enum test_llvm__testcase index,
+			 bool force)
 {
-	char *tmpl_new, *clang_opt_new;
-	void *obj_buf;
-	size_t obj_buf_sz;
-	int err, old_verbose;
+	const char *source;
+	const char *desc;
+	const char *tmpl_old, *clang_opt_old;
+	char *tmpl_new = NULL, *clang_opt_new = NULL;
+	int err, old_verbose, ret = TEST_FAIL;
+
+	if (index >= __LLVM_TESTCASE_MAX)
+		return TEST_FAIL;
+
+	source = bpf_source_table[index].source;
+	desc = bpf_source_table[index].desc;
 
 	perf_config(perf_config_cb, NULL);
 
@@ -54,45 +71,100 @@ int test__llvm(void)
 	 * Skip this test if user's .perfconfig doesn't set [llvm] section
 	 * and clang is not found in $PATH, and this is not perf test -v
 	 */
-	if (verbose == 0 && !llvm_param.user_set_param && llvm__search_clang()) {
-		fprintf(stderr, " (no clang, try 'perf test -v LLVM')");
+	if (!force && (verbose == 0 &&
+		       !llvm_param.user_set_param &&
+		       llvm__search_clang())) {
+		pr_debug("No clang and no verbosive, skip this test\n");
 		return TEST_SKIP;
 	}
 
-	old_verbose = verbose;
 	/*
 	 * llvm is verbosity when error. Suppress all error output if
 	 * not 'perf test -v'.
 	 */
+	old_verbose = verbose;
 	if (verbose == 0)
 		verbose = -1;
 
+	*p_obj_buf = NULL;
+	*p_obj_buf_sz = 0;
+
 	if (!llvm_param.clang_bpf_cmd_template)
-		return -1;
+		goto out;
 
 	if (!llvm_param.clang_opt)
 		llvm_param.clang_opt = strdup("");
 
-	err = asprintf(&tmpl_new, "echo '%s' | %s", test_bpf_prog,
-		       llvm_param.clang_bpf_cmd_template);
+	err = asprintf(&tmpl_new, "echo '%s' | %s%s", source,
+		       llvm_param.clang_bpf_cmd_template,
+		       old_verbose ? "" : " 2>/dev/null");
 	if (err < 0)
-		return -1;
+		goto out;
 	err = asprintf(&clang_opt_new, "-xc %s", llvm_param.clang_opt);
 	if (err < 0)
-		return -1;
+		goto out;
 
+	tmpl_old = llvm_param.clang_bpf_cmd_template;
 	llvm_param.clang_bpf_cmd_template = tmpl_new;
+	clang_opt_old = llvm_param.clang_opt;
 	llvm_param.clang_opt = clang_opt_new;
-	err = llvm__compile_bpf("-", &obj_buf, &obj_buf_sz);
+
+	err = llvm__compile_bpf("-", p_obj_buf, p_obj_buf_sz);
+
+	llvm_param.clang_bpf_cmd_template = tmpl_old;
+	llvm_param.clang_opt = clang_opt_old;
 
 	verbose = old_verbose;
-	if (err) {
-		if (!verbose)
-			fprintf(stderr, " (use -v to see error message)");
-		return -1;
-	}
+	if (err)
+		goto out;
 
-	err = test__bpf_parsing(obj_buf, obj_buf_sz);
-	free(obj_buf);
-	return err;
+	ret = TEST_OK;
+out:
+	free(tmpl_new);
+	free(clang_opt_new);
+	if (ret != TEST_OK)
+		pr_debug("Failed to compile test case: '%s'\n", desc);
+	return ret;
+}
+
+int test__llvm(void)
+{
+	enum test_llvm__testcase i;
+
+	for (i = 0; i < __LLVM_TESTCASE_MAX; i++) {
+		int ret;
+		void *obj_buf = NULL;
+		size_t obj_buf_sz = 0;
+
+		ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
+					       i, false);
+
+		if (ret == TEST_OK) {
+			ret = test__bpf_parsing(obj_buf, obj_buf_sz);
+			if (ret != TEST_OK)
+				pr_debug("Failed to parse test case '%s'\n",
+					 bpf_source_table[i].desc);
+		}
+		free(obj_buf);
+
+		switch (ret) {
+		case TEST_SKIP:
+			return TEST_SKIP;
+		case TEST_OK:
+			break;
+		default:
+			/*
+			 * Test 0 is the basic LLVM test. If test 0
+			 * fail, the basic LLVM support not functional
+			 * so the whole test should fail. If other test
+			 * case fail, it can be fixed by adjusting
+			 * config so don't report error.
+			 */
+			if (i == 0)
+				return TEST_FAIL;
+			else
+				return TEST_SKIP;
+		}
+	}
+	return TEST_OK;
 }
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
new file mode 100644
index 000000000000..d91d8f44efee
--- /dev/null
+++ b/tools/perf/tests/llvm.h
@@ -0,0 +1,18 @@
+#ifndef PERF_TEST_LLVM_H
+#define PERF_TEST_LLVM_H
+
+#include <stddef.h> /* for size_t */
+#include <stdbool.h> /* for bool */
+
+extern const char test_llvm__bpf_base_prog[];
+extern const char test_llvm__bpf_test_kbuild_prog[];
+
+enum test_llvm__testcase {
+	LLVM_TESTCASE_BASE,
+	LLVM_TESTCASE_KBUILD,
+	__LLVM_TESTCASE_MAX,
+};
+
+int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz,
+			     enum test_llvm__testcase index, bool force);
+#endif
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2cbd0c6901e3..8ea3dffc5065 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -221,6 +221,11 @@ test_O = $(if $(test_$1),$(test_$1),$(test_default_O))
 
 all:
 
+ifdef SHUF
+run := $(shell shuf -e $(run))
+run_O := $(shell shuf -e $(run_O))
+endif
+
 ifdef DEBUG
 d := $(info run   $(run))
 d := $(info run_O $(run_O))
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index e698742d4fec..a02af503100c 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -366,7 +366,7 @@ int test__switch_tracking(void)
 
 	/* Third event */
 	if (!perf_evlist__can_select_event(evlist, sched_switch)) {
-		fprintf(stderr, " (no sched_switch)");
+		pr_debug("No sched_switch\n");
 		err = 0;
 		goto out;
 	}
@@ -442,7 +442,7 @@ int test__switch_tracking(void)
 	}
 
 	if (perf_evlist__open(evlist) < 0) {
-		fprintf(stderr, " (not supported)");
+		pr_debug("Not supported\n");
 		err = 0;
 		goto out;
 	}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index c80486969f83..3c8734a3abbc 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -66,6 +66,7 @@ int test__fdarray__add(void);
 int test__kmod_path__parse(void);
 int test__thread_map(void);
 int test__llvm(void);
+int test__bpf(void);
 int test_session_topology(void);
 
 #if defined(__arm__) || defined(__aarch64__)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0fc8d7a2fea5..1dd1949b0e79 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1084,6 +1084,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 	int lineno = 0;
+	int nline;
 
 	if (filename)
 		symbol__join_symfs(symfs_filename, filename);
@@ -1179,6 +1180,9 @@ fallback:
 
 		ret = decompress_to_file(m.ext, symfs_filename, fd);
 
+		if (ret)
+			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
+
 		free(m.ext);
 		close(fd);
 
@@ -1204,13 +1208,25 @@ fallback:
 	pr_debug("Executing: %s\n", command);
 
 	file = popen(command, "r");
-	if (!file)
+	if (!file) {
+		pr_err("Failure running %s\n", command);
+		/*
+		 * If we were using debug info should retry with
+		 * original binary.
+		 */
 		goto out_remove_tmp;
+	}
 
-	while (!feof(file))
+	nline = 0;
+	while (!feof(file)) {
 		if (symbol__parse_objdump_line(sym, map, file, privsize,
 			    &lineno) < 0)
 			break;
+		nline++;
+	}
+
+	if (nline == 0)
+		pr_err("No output from %s\n", command);
 
 	/*
 	 * kallsyms does not have symbol sizes so there may a nop at the end.
@@ -1604,6 +1620,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	len = symbol__size(sym);
 
 	if (print_lines) {
+		srcline_full_filename = full_paths;
 		symbol__get_source_line(sym, map, evsel, &source_line, len);
 		print_summary(&source_line, dso->long_name);
 	}
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index ba6f7526b282..4c50411371db 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -26,18 +26,40 @@ static int libbpf_##name(const char *fmt, ...)	\
 	return ret;				\
 }
 
-DEFINE_PRINT_FN(warning, 0)
-DEFINE_PRINT_FN(info, 0)
+DEFINE_PRINT_FN(warning, 1)
+DEFINE_PRINT_FN(info, 1)
 DEFINE_PRINT_FN(debug, 1)
 
 struct bpf_prog_priv {
 	struct perf_probe_event pev;
 };
 
+static bool libbpf_initialized;
+
+struct bpf_object *
+bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
+{
+	struct bpf_object *obj;
+
+	if (!libbpf_initialized) {
+		libbpf_set_print(libbpf_warning,
+				 libbpf_info,
+				 libbpf_debug);
+		libbpf_initialized = true;
+	}
+
+	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
+	if (IS_ERR(obj)) {
+		pr_debug("bpf: failed to load buffer\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return obj;
+}
+
 struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 {
 	struct bpf_object *obj;
-	static bool libbpf_initialized;
 
 	if (!libbpf_initialized) {
 		libbpf_set_print(libbpf_warning,
@@ -53,15 +75,15 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 
 		err = llvm__compile_bpf(filename, &obj_buf, &obj_buf_sz);
 		if (err)
-			return ERR_PTR(err);
+			return ERR_PTR(-BPF_LOADER_ERRNO__COMPILE);
 		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
 		free(obj_buf);
 	} else
 		obj = bpf_object__open(filename);
 
-	if (!obj) {
+	if (IS_ERR(obj)) {
 		pr_debug("bpf: failed to load %s\n", filename);
-		return ERR_PTR(-EINVAL);
+		return obj;
 	}
 
 	return obj;
@@ -96,9 +118,9 @@ config_bpf_program(struct bpf_program *prog)
 	int err;
 
 	config_str = bpf_program__title(prog, false);
-	if (!config_str) {
+	if (IS_ERR(config_str)) {
 		pr_debug("bpf: unable to get title for program\n");
-		return -EINVAL;
+		return PTR_ERR(config_str);
 	}
 
 	priv = calloc(sizeof(*priv), 1);
@@ -113,14 +135,14 @@ config_bpf_program(struct bpf_program *prog)
 	if (err < 0) {
 		pr_debug("bpf: '%s' is not a valid config string\n",
 			 config_str);
-		err = -EINVAL;
+		err = -BPF_LOADER_ERRNO__CONFIG;
 		goto errout;
 	}
 
 	if (pev->group && strcmp(pev->group, PERF_BPF_PROBE_GROUP)) {
 		pr_debug("bpf: '%s': group for event is set and not '%s'.\n",
 			 config_str, PERF_BPF_PROBE_GROUP);
-		err = -EINVAL;
+		err = -BPF_LOADER_ERRNO__GROUP;
 		goto errout;
 	} else if (!pev->group)
 		pev->group = strdup(PERF_BPF_PROBE_GROUP);
@@ -132,9 +154,9 @@ config_bpf_program(struct bpf_program *prog)
 	}
 
 	if (!pev->event) {
-		pr_debug("bpf: '%s': event name is missing\n",
+		pr_debug("bpf: '%s': event name is missing. Section name should be 'key=value'\n",
 			 config_str);
-		err = -EINVAL;
+		err = -BPF_LOADER_ERRNO__EVENTNAME;
 		goto errout;
 	}
 	pr_debug("bpf: config '%s' is ok\n", config_str);
@@ -285,7 +307,7 @@ int bpf__foreach_tev(struct bpf_object *obj,
 				(void **)&priv);
 		if (err || !priv) {
 			pr_debug("bpf: failed to get private field\n");
-			return -EINVAL;
+			return -BPF_LOADER_ERRNO__INTERNAL;
 		}
 
 		pev = &priv->pev;
@@ -308,13 +330,57 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	return 0;
 }
 
+#define ERRNO_OFFSET(e)		((e) - __BPF_LOADER_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
+#define NR_ERRNO	(__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
+
+static const char *bpf_loader_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(CONFIG)]	= "Invalid config string",
+	[ERRCODE_OFFSET(GROUP)]		= "Invalid group name",
+	[ERRCODE_OFFSET(EVENTNAME)]	= "No event name found in config string",
+	[ERRCODE_OFFSET(INTERNAL)]	= "BPF loader internal error",
+	[ERRCODE_OFFSET(COMPILE)]	= "Error when compiling BPF scriptlet",
+};
+
+static int
+bpf_loader_strerror(int err, char *buf, size_t size)
+{
+	char sbuf[STRERR_BUFSIZE];
+	const char *msg;
+
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err >= __LIBBPF_ERRNO__START)
+		return libbpf_strerror(err, buf, size);
+
+	if (err >= __BPF_LOADER_ERRNO__START && err < __BPF_LOADER_ERRNO__END) {
+		msg = bpf_loader_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	if (err >= __BPF_LOADER_ERRNO__END)
+		snprintf(buf, size, "Unknown bpf loader error %d", err);
+	else
+		snprintf(buf, size, "%s",
+			 strerror_r(err, sbuf, sizeof(sbuf)));
+
+	buf[size - 1] = '\0';
+	return -1;
+}
+
 #define bpf__strerror_head(err, buf, size) \
 	char sbuf[STRERR_BUFSIZE], *emsg;\
 	if (!size)\
 		return 0;\
 	if (err < 0)\
 		err = -err;\
-	emsg = strerror_r(err, sbuf, sizeof(sbuf));\
+	bpf_loader_strerror(err, sbuf, sizeof(sbuf));\
+	emsg = sbuf;\
 	switch (err) {\
 	default:\
 		scnprintf(buf, size, "%s", emsg);\
@@ -330,23 +396,62 @@ int bpf__foreach_tev(struct bpf_object *obj,
 	}\
 	buf[size - 1] = '\0';
 
+int bpf__strerror_prepare_load(const char *filename, bool source,
+			       int err, char *buf, size_t size)
+{
+	size_t n;
+	int ret;
+
+	n = snprintf(buf, size, "Failed to load %s%s: ",
+			 filename, source ? " from source" : "");
+	if (n >= size) {
+		buf[size - 1] = '\0';
+		return 0;
+	}
+	buf += n;
+	size -= n;
+
+	ret = bpf_loader_strerror(err, buf, size);
+	buf[size - 1] = '\0';
+	return ret;
+}
+
 int bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
 			int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
 	bpf__strerror_entry(EEXIST, "Probe point exist. Try use 'perf probe -d \"*\"'");
-	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0\n");
-	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file\n");
+	bpf__strerror_entry(EACCES, "You need to be root");
+	bpf__strerror_entry(EPERM, "You need to be root, and /proc/sys/kernel/kptr_restrict should be 0");
+	bpf__strerror_entry(ENOENT, "You need to check probing points in BPF file");
 	bpf__strerror_end(buf, size);
 	return 0;
 }
 
-int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
+int bpf__strerror_load(struct bpf_object *obj,
 		       int err, char *buf, size_t size)
 {
 	bpf__strerror_head(err, buf, size);
-	bpf__strerror_entry(EINVAL, "%s: Are you root and runing a CONFIG_BPF_SYSCALL kernel?",
-			    emsg)
+	case LIBBPF_ERRNO__KVER: {
+		unsigned int obj_kver = bpf_object__get_kversion(obj);
+		unsigned int real_kver;
+
+		if (fetch_kernel_version(&real_kver, NULL, 0)) {
+			scnprintf(buf, size, "Unable to fetch kernel version");
+			break;
+		}
+
+		if (obj_kver != real_kver) {
+			scnprintf(buf, size,
+				  "'version' ("KVER_FMT") doesn't match running kernel ("KVER_FMT")",
+				  KVER_PARAM(obj_kver),
+				  KVER_PARAM(real_kver));
+			break;
+		}
+
+		scnprintf(buf, size, "Failed to load program for unknown reason");
+		break;
+	}
 	bpf__strerror_end(buf, size);
 	return 0;
 }
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index ccd8d7fd79d3..9caf3ae4acf3 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -8,9 +8,21 @@
 #include <linux/compiler.h>
 #include <linux/err.h>
 #include <string.h>
+#include <bpf/libbpf.h>
 #include "probe-event.h"
 #include "debug.h"
 
+enum bpf_loader_errno {
+	__BPF_LOADER_ERRNO__START = __LIBBPF_ERRNO__START - 100,
+	/* Invalid config string */
+	BPF_LOADER_ERRNO__CONFIG = __BPF_LOADER_ERRNO__START,
+	BPF_LOADER_ERRNO__GROUP,	/* Invalid group name */
+	BPF_LOADER_ERRNO__EVENTNAME,	/* Event name is missing */
+	BPF_LOADER_ERRNO__INTERNAL,	/* BPF loader internal error */
+	BPF_LOADER_ERRNO__COMPILE,	/* Error when compiling BPF scriptlet */
+	__BPF_LOADER_ERRNO__END,
+};
+
 struct bpf_object;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
@@ -19,6 +31,11 @@ typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
 
 #ifdef HAVE_LIBBPF_SUPPORT
 struct bpf_object *bpf__prepare_load(const char *filename, bool source);
+int bpf__strerror_prepare_load(const char *filename, bool source,
+			       int err, char *buf, size_t size);
+
+struct bpf_object *bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz,
+					    const char *name);
 
 void bpf__clear(void);
 
@@ -41,6 +58,13 @@ bpf__prepare_load(const char *filename __maybe_unused,
 	return ERR_PTR(-ENOTSUP);
 }
 
+static inline struct bpf_object *
+bpf__prepare_load_buffer(void *obj_buf __maybe_unused,
+					   size_t obj_buf_sz __maybe_unused)
+{
+	return ERR_PTR(-ENOTSUP);
+}
+
 static inline void bpf__clear(void) { }
 
 static inline int bpf__probe(struct bpf_object *obj __maybe_unused) { return 0;}
@@ -67,6 +91,15 @@ __bpf_strerror(char *buf, size_t size)
 	return 0;
 }
 
+static inline
+int bpf__strerror_prepare_load(const char *filename __maybe_unused,
+			       bool source __maybe_unused,
+			       int err __maybe_unused,
+			       char *buf, size_t size)
+{
+	return __bpf_strerror(buf, size);
+}
+
 static inline int
 bpf__strerror_probe(struct bpf_object *obj __maybe_unused,
 		    int err __maybe_unused,
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 4f6a4780bd5f..00724d496d38 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -4,17 +4,18 @@
  */
 
 #include <stdio.h>
-#include <sys/utsname.h>
 #include "util.h"
 #include "debug.h"
 #include "llvm-utils.h"
 #include "cache.h"
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
-		"$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS "	\
-		"$KERNEL_INC_OPTIONS -Wno-unused-value "	\
-		"-Wno-pointer-sign -working-directory "		\
-		"$WORKING_DIR -c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
+		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
+		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
+		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS "		\
+		"-Wno-unused-value -Wno-pointer-sign "		\
+		"-working-directory $WORKING_DIR "		\
+		"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
 
 struct llvm_param llvm_param = {
 	.clang_path = "clang",
@@ -214,18 +215,19 @@ static int detect_kbuild_dir(char **kbuild_dir)
 	const char *suffix_dir = "";
 
 	char *autoconf_path;
-	struct utsname utsname;
 
 	int err;
 
 	if (!test_dir) {
-		err = uname(&utsname);
-		if (err) {
-			pr_warning("uname failed: %s\n", strerror(errno));
-			return -EINVAL;
-		}
+		/* _UTSNAME_LENGTH is 65 */
+		char release[128];
 
-		test_dir = utsname.release;
+		err = fetch_kernel_version(NULL, release,
+					   sizeof(release));
+		if (err)
+			return -EINVAL;
+
+		test_dir = release;
 		prefix_dir = "/lib/modules/";
 		suffix_dir = "/build";
 	}
@@ -326,13 +328,15 @@ get_kbuild_opts(char **kbuild_dir, char **kbuild_include_opts)
 int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		      size_t *p_obj_buf_sz)
 {
-	int err;
-	char clang_path[PATH_MAX];
-	const char *clang_opt = llvm_param.clang_opt;
-	const char *template = llvm_param.clang_bpf_cmd_template;
-	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
-	void *obj_buf = NULL;
 	size_t obj_buf_sz;
+	void *obj_buf = NULL;
+	int err, nr_cpus_avail;
+	unsigned int kernel_version;
+	char linux_version_code_str[64];
+	const char *clang_opt = llvm_param.clang_opt;
+	char clang_path[PATH_MAX], nr_cpus_avail_str[64];
+	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
+	const char *template = llvm_param.clang_bpf_cmd_template;
 
 	if (!template)
 		template = CLANG_BPF_CMD_DEFAULT_TEMPLATE;
@@ -354,6 +358,24 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	 */
 	get_kbuild_opts(&kbuild_dir, &kbuild_include_opts);
 
+	nr_cpus_avail = sysconf(_SC_NPROCESSORS_CONF);
+	if (nr_cpus_avail <= 0) {
+		pr_err(
+"WARNING:\tunable to get available CPUs in this system: %s\n"
+"        \tUse 128 instead.\n", strerror(errno));
+		nr_cpus_avail = 128;
+	}
+	snprintf(nr_cpus_avail_str, sizeof(nr_cpus_avail_str), "%d",
+		 nr_cpus_avail);
+
+	if (fetch_kernel_version(&kernel_version, NULL, 0))
+		kernel_version = 0;
+
+	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
+		 "0x%x", kernel_version);
+
+	force_set_env("NR_CPUS", nr_cpus_avail_str);
+	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
 	force_set_env("CLANG_EXEC", clang_path);
 	force_set_env("CLANG_OPTIONS", clang_opt);
 	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4e38c396a897..afc6b56cf749 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -644,6 +644,12 @@ size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 	return printed;
 }
 
+static void __map_groups__insert(struct map_groups *mg, struct map *map)
+{
+	__maps__insert(&mg->maps[map->type], map);
+	map->groups = mg;
+}
+
 static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
 	struct rb_root *root;
@@ -682,7 +688,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			before->end = map->start;
-			__maps__insert(maps, before);
+			__map_groups__insert(pos->groups, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -696,7 +702,7 @@ static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp
 			}
 
 			after->start = map->end;
-			__maps__insert(maps, after);
+			__map_groups__insert(pos->groups, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bee60583839a..e48d9da75707 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -632,19 +632,20 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
 	struct bpf_object *obj;
 
 	obj = bpf__prepare_load(bpf_file_name, source);
-	if (IS_ERR(obj) || !obj) {
+	if (IS_ERR(obj)) {
 		char errbuf[BUFSIZ];
 		int err;
 
-		err = obj ? PTR_ERR(obj) : -EINVAL;
+		err = PTR_ERR(obj);
 
 		if (err == -ENOTSUP)
 			snprintf(errbuf, sizeof(errbuf),
 				 "BPF support is not compiled");
 		else
-			snprintf(errbuf, sizeof(errbuf),
-				 "BPF object file '%s' is invalid",
-				 bpf_file_name);
+			bpf__strerror_prepare_load(bpf_file_name,
+						   source,
+						   -err, errbuf,
+						   sizeof(errbuf));
 
 		data->error->help = strdup("(add -v to see detail)");
 		data->error->str = strdup(errbuf);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index b51a8bfb40f9..03875f9154e7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1895,9 +1895,8 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 		sym = map__find_symbol(map, addr, NULL);
 	} else {
 		if (tp->symbol && !addr) {
-			ret = kernel_get_symbol_address_by_name(tp->symbol,
-							&addr, true, false);
-			if (ret < 0)
+			if (kernel_get_symbol_address_by_name(tp->symbol,
+						&addr, true, false) < 0)
 				goto out;
 		}
 		if (addr) {
@@ -1905,6 +1904,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 			sym = __find_kernel_function(addr, &map);
 		}
 	}
+
 	if (!sym)
 		goto out;
 
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 89dbeb92c68e..e3b3b92e4458 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -138,6 +138,9 @@ struct strlist *probe_file__get_rawlist(int fd)
 	char *p;
 	struct strlist *sl;
 
+	if (fd < 0)
+		return NULL;
+
 	sl = strlist__new(NULL, NULL);
 
 	fp = fdopen(dup(fd), "r");
@@ -271,6 +274,9 @@ int probe_file__get_events(int fd, struct strfilter *filter,
 	const char *p;
 	int ret = -ENOENT;
 
+	if (!plist)
+		return -EINVAL;
+
 	namelist = __probe_file__get_namelist(fd, true);
 	if (!namelist)
 		return -ENOENT;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 428149bc64d2..c35ffdd360fe 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -29,7 +29,7 @@ static int perf_session__open(struct perf_session *session)
 	struct perf_data_file *file = session->file;
 
 	if (perf_session__read_header(session) < 0) {
-		pr_err("incompatible file format (rerun with -v to learn more)");
+		pr_err("incompatible file format (rerun with -v to learn more)\n");
 		return -1;
 	}
 
@@ -37,17 +37,17 @@ static int perf_session__open(struct perf_session *session)
 		return 0;
 
 	if (!perf_evlist__valid_sample_type(session->evlist)) {
-		pr_err("non matching sample_type");
+		pr_err("non matching sample_type\n");
 		return -1;
 	}
 
 	if (!perf_evlist__valid_sample_id_all(session->evlist)) {
-		pr_err("non matching sample_id_all");
+		pr_err("non matching sample_id_all\n");
 		return -1;
 	}
 
 	if (!perf_evlist__valid_read_format(session->evlist)) {
-		pr_err("non matching read_format");
+		pr_err("non matching read_format\n");
 		return -1;
 	}
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 2a5d8d7698ae..6ac03146889d 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -413,6 +413,11 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
+			fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+		else
+			fprintf(out, "                                   ");
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index cd12c25e4ea4..47b1e36c7ea0 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -3,6 +3,7 @@
 #include "debug.h"
 #include <api/fs/fs.h>
 #include <sys/mman.h>
+#include <sys/utsname.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>
 #endif
@@ -665,3 +666,32 @@ bool find_process(const char *name)
 	closedir(dir);
 	return ret ? false : true;
 }
+
+int
+fetch_kernel_version(unsigned int *puint, char *str,
+		     size_t str_size)
+{
+	struct utsname utsname;
+	int version, patchlevel, sublevel, err;
+
+	if (uname(&utsname))
+		return -1;
+
+	if (str && str_size) {
+		strncpy(str, utsname.release, str_size);
+		str[str_size - 1] = '\0';
+	}
+
+	err = sscanf(utsname.release, "%d.%d.%d",
+		     &version, &patchlevel, &sublevel);
+
+	if (err != 3) {
+		pr_debug("Unablt to get kernel version from uname '%s'\n",
+			 utsname.release);
+		return -1;
+	}
+
+	if (puint)
+		*puint = (version << 16) + (patchlevel << 8) + sublevel;
+	return 0;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 4cfb913aa9e0..dcc659017976 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -350,4 +350,12 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int
 
 int get_stack_size(const char *str, unsigned long *_size);
 
+int fetch_kernel_version(unsigned int *puint,
+			 char *str, size_t str_sz);
+#define KVER_VERSION(x)		(((x) >> 16) & 0xff)
+#define KVER_PATCHLEVEL(x)	(((x) >> 8) & 0xff)
+#define KVER_SUBLEVEL(x)	((x) & 0xff)
+#define KVER_FMT	"%d.%d.%d"
+#define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
+
 #endif /* GIT_COMPAT_UTIL_H */