Merge tag 'perf-core-for-mingo' of...

Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

 - Rename the "colors.code" ~/.perfconfig variable to "colors.jump_arrows",
   as it controls just the that UI element in the annotate browser (Taeung Song)

 - Avoid trying to read ELF symtabs from device files, noticed while doing
   memory profiling work (Jiri Olsa)

 - Improve context detection when offering options in the hists browser,
   i.e.  some options don't make sense when the browser is not working with
   a perf.data file ('perf top' mode), only in 'perf report' mode, like
   scripting (Namhyung Kim)

Infrastructure changes:

 - Elliminate duplication in the hists browser filter functions, getting the
   common part into a function that receives callbacks for filtering by
   DSO, thread, etc. (Namhyung Kim)

 - Fix misleadingly indented assignment, found using
   gcc6 -Wmisleading-indentation (Markus Trippelsdorf)

 - Handle LLVM relocation oddities in libbpf, introducing a 'perf test' that
   detects such problems and then fixing the problem, so that the test now
   passes (Wang Nan)

 - More improvements to the build infrastructure to allow reusing the
   feature detection facilities (Wang Nan)

 - Auto initialize the globals needed by cpu__max_{cpu,node}() routines
   (Arnaldo Carvalho de Melo)

Documentation changes:

 - Document the perf sysctls in Documentation/sysctl/kernel.txt (Ben Hutchings)

 - Document a bunch more ~/.perfconfig knobs (Taeung Song)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/sysctl/kernel.txt

@@ -58,6 +58,8 @@ show up in /proc/sys/kernel:
 - panic_on_stackoverflow
 - panic_on_unrecovered_nmi
 - panic_on_warn
+- perf_cpu_time_max_percent
+- perf_event_paranoid
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@@ -639,6 +641,17 @@ allowed to execute.
 
 ==============================================================
 
+perf_event_paranoid:
+
+Controls use of the performance events system by unprivileged
+users (without CAP_SYS_ADMIN).  The default value is 1.
+
+ -1: Allow use of (almost) all events by all users
+>=0: Disallow raw tracepoint access by users without CAP_IOC_LOCK
+>=1: Disallow CPU event access by users without CAP_SYS_ADMIN
+>=2: Disallow kernel profiling by users without CAP_SYS_ADMIN
+
+==============================================================
 
 pid_max:
 

tools/build/Makefile.feature

@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS ?=			\
+FEATURE_TESTS_BASIC :=			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
@@ -56,6 +56,25 @@ FEATURE_TESTS ?=			\
 	get_cpuid			\
 	bpf
 
+# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
+# of all feature tests
+FEATURE_TESTS_EXTRA :=			\
+	bionic				\
+	compile-32			\
+	compile-x32			\
+	cplus-demangle			\
+	hello				\
+	libbabeltrace			\
+	liberty				\
+	liberty-z			\
+	libunwind-debug-frame
+
+FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
+
+ifeq ($(FEATURE_TESTS),all)
+  FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA)
+endif
+
 FEATURE_DISPLAY ?=			\
 	dwarf				\
 	glibc				\

tools/lib/bpf/libbpf.c

@@ -201,6 +201,7 @@ struct bpf_object {
 			Elf_Data *data;
 		} *reloc;
 		int nr_reloc;
+		int maps_shndx;
 	} efile;
 	/*
 	 * All loaded bpf_object is linked in a list, which is
@@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 	 */
 	obj->efile.obj_buf = obj_buf;
 	obj->efile.obj_buf_sz = obj_buf_sz;
+	obj->efile.maps_shndx = -1;
 
 	obj->loaded = false;
 
@@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data,
 }
 
 static int
-bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+bpf_object__init_maps_name(struct bpf_object *obj)
 {
 	int i;
 	Elf_Data *symbols = obj->efile.symbols;
 
-	if (!symbols || maps_shndx < 0)
+	if (!symbols || obj->efile.maps_shndx < 0)
 		return -EINVAL;
 
 	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
@@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
 
 		if (!gelf_getsym(symbols, i, &sym))
 			continue;
-		if (sym.st_shndx != maps_shndx)
+		if (sym.st_shndx != obj->efile.maps_shndx)
 			continue;
 
 		map_name = elf_strptr(obj->efile.elf,
@@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
 	Elf_Scn *scn = NULL;
-	int idx = 0, err = 0, maps_shndx = -1;
+	int idx = 0, err = 0;
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
 	if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		else if (strcmp(name, "maps") == 0) {
 			err = bpf_object__init_maps(obj, data->d_buf,
 						    data->d_size);
-			maps_shndx = idx;
+			obj->efile.maps_shndx = idx;
 		} else if (sh.sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
-	if (maps_shndx >= 0)
-		err = bpf_object__init_maps_name(obj, maps_shndx);
+	if (obj->efile.maps_shndx >= 0)
+		err = bpf_object__init_maps_name(obj);
 out:
 	return err;
 }
@@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
 static int
 bpf_program__collect_reloc(struct bpf_program *prog,
 			   size_t nr_maps, GElf_Shdr *shdr,
-			   Elf_Data *data, Elf_Data *symbols)
+			   Elf_Data *data, Elf_Data *symbols,
+			   int maps_shndx)
 {
 	int i, nrels;
 
@@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
-		pr_debug("relocation: insn_idx=%u\n", insn_idx);
-
 		if (!gelf_getsym(symbols,
 				 GELF_R_SYM(rel.r_info),
 				 &sym)) {
@@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
+		if (sym.st_shndx != maps_shndx) {
+			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
+				   prog->section_name, sym.st_shndx);
+			return -LIBBPF_ERRNO__RELOC;
+		}
+
+		insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+		pr_debug("relocation: insn_idx=%u\n", insn_idx);
+
 		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);
@@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
-						 obj->efile.symbols);
+						 obj->efile.symbols,
+						 obj->efile.maps_shndx);
 		if (err)
 			return err;
 	}

tools/perf/Documentation/perf-config.txt

@@ -62,7 +62,7 @@ Given a $HOME/.perfconfig like this:
 		medium = green, default
 		normal = lightgray, default
 		selected = white, lightgray
-		code = blue, default
+		jump_arrows = blue, default
 		addr = magenta, default
 		root = white, blue
 
@@ -98,6 +98,204 @@ Given a $HOME/.perfconfig like this:
 		order = caller
 		sort-key = function
 
+Variables
+~~~~~~~~~
+
+colors.*::
+	The variables for customizing the colors used in the output for the
+	'report', 'top' and 'annotate' in the TUI. They should specify the
+	foreground and background colors, separated by a comma, for example:
+
+		medium = green, lightgray
+
+	If you want to use the color configured for you terminal, just leave it
+	as 'default', for example:
+
+		medium = default, lightgray
+
+	Available colors:
+	red, yellow, green, cyan, gray, black, blue,
+	white, default, magenta, lightgray
+
+	colors.top::
+		'top' means a overhead percentage which is more than 5%.
+		And values of this variable specify percentage colors.
+		Basic key values are foreground-color 'red' and
+		background-color 'default'.
+	colors.medium::
+		'medium' means a overhead percentage which has more than 0.5%.
+		Default values are 'green' and 'default'.
+	colors.normal::
+		'normal' means the rest of overhead percentages
+		except 'top', 'medium', 'selected'.
+		Default values are 'lightgray' and 'default'.
+	colors.selected::
+		This selects the colors for the current entry in a list of entries
+		from sub-commands (top, report, annotate).
+		Default values are 'black' and 'lightgray'.
+	colors.jump_arrows::
+		Colors for jump arrows on assembly code listings
+		such as 'jns', 'jmp', 'jane', etc.
+		Default values are 'blue', 'default'.
+	colors.addr::
+		This selects colors for addresses from 'annotate'.
+		Default values are 'magenta', 'default'.
+	colors.root::
+		Colors for headers in the output of a sub-commands (top, report).
+		Default values are 'white', 'blue'.
+
+tui.*, gtk.*::
+	Subcommands that can be configured here are 'top', 'report' and 'annotate'.
+	These values are booleans, for example:
+
+	[tui]
+		top = true
+
+	will make the TUI be the default for the 'top' subcommand. Those will be
+	available if the required libs were detected at tool build time.
+
+buildid.*::
+	buildid.dir::
+		Each executable and shared library in modern distributions comes with a
+		content based identifier that, if available, will be inserted in a
+		'perf.data' file header to, at analysis time find what is needed to do
+		symbol resolution, code annotation, etc.
+
+		The recording tools also stores a hard link or copy in a per-user
+		directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
+		and /proc/kcore files to be used at analysis time.
+
+		The buildid.dir variable can be used to either change this directory
+		cache location, or to disable it altogether. If you want to disable it,
+		set buildid.dir to /dev/null. The default is $HOME/.debug
+
+annotate.*::
+	These options work only for TUI.
+	These are in control of addresses, jump function, source code
+	in lines of assembly code from a specific program.
+
+	annotate.hide_src_code::
+		If a program which is analyzed has source code,
+		this option lets 'annotate' print a list of assembly code with the source code.
+		For example, let's see a part of a program. There're four lines.
+		If this option is 'true', they can be printed
+		without source code from a program as below.
+
+		│        push   %rbp
+		│        mov    %rsp,%rbp
+		│        sub    $0x10,%rsp
+		│        mov    (%rdi),%rdx
+
+		But if this option is 'false', source code of the part
+		can be also printed as below. Default is 'false'.
+
+		│      struct rb_node *rb_next(const struct rb_node *node)
+		│      {
+		│        push   %rbp
+		│        mov    %rsp,%rbp
+		│        sub    $0x10,%rsp
+		│              struct rb_node *parent;
+		│
+		│              if (RB_EMPTY_NODE(node))
+		│        mov    (%rdi),%rdx
+		│              return n;
+
+        annotate.use_offset::
+		Basing on a first address of a loaded function, offset can be used.
+		Instead of using original addresses of assembly code,
+		addresses subtracted from a base address can be printed.
+		Let's illustrate an example.
+		If a base address is 0XFFFFFFFF81624d50 as below,
+
+		ffffffff81624d50 <load0>
+
+		an address on assembly code has a specific absolute address as below
+
+		ffffffff816250b8:│  mov    0x8(%r14),%rdi
+
+		but if use_offset is 'true', an address subtracted from a base address is printed.
+		Default is true. This option is only applied to TUI.
+
+		             368:│  mov    0x8(%r14),%rdi
+
+	annotate.jump_arrows::
+		There can be jump instruction among assembly code.
+		Depending on a boolean value of jump_arrows,
+		arrows can be printed or not which represent
+		where do the instruction jump into as below.
+
+		│     ┌──jmp    1333
+		│     │  xchg   %ax,%ax
+		│1330:│  mov    %r15,%r10
+		│1333:└─→cmp    %r15,%r14
+
+		If jump_arrow is 'false', the arrows isn't printed as below.
+		Default is 'false'.
+
+		│      ↓ jmp    1333
+		│        xchg   %ax,%ax
+		│1330:   mov    %r15,%r10
+		│1333:   cmp    %r15,%r14
+
+        annotate.show_linenr::
+		When showing source code if this option is 'true',
+		line numbers are printed as below.
+
+		│1628         if (type & PERF_SAMPLE_IDENTIFIER) {
+		│     ↓ jne    508
+		│1628                 data->id = *array;
+		│1629                 array++;
+		│1630         }
+
+		However if this option is 'false', they aren't printed as below.
+		Default is 'false'.
+
+		│             if (type & PERF_SAMPLE_IDENTIFIER) {
+		│     ↓ jne    508
+		│                     data->id = *array;
+		│                     array++;
+		│             }
+
+        annotate.show_nr_jumps::
+		Let's see a part of assembly code.
+
+		│1382:   movb   $0x1,-0x270(%rbp)
+
+		If use this, the number of branches jumping to that address can be printed as below.
+		Default is 'false'.
+
+		│1 1382:   movb   $0x1,-0x270(%rbp)
+
+        annotate.show_total_period::
+		To compare two records on an instruction base, with this option
+		provided, display total number of samples that belong to a line
+		in assembly code. If this option is 'true', total periods are printed
+		instead of percent values as below.
+
+		  302 │      mov    %eax,%eax
+
+		But if this option is 'false', percent values for overhead are printed i.e.
+		Default is 'false'.
+
+		99.93 │      mov    %eax,%eax
+
+hist.*::
+	hist.percentage::
+		This option control the way to calculate overhead of filtered entries -
+		that means the value of this option is effective only if there's a
+		filter (by comm, dso or symbol name). Suppose a following example:
+
+		       Overhead  Symbols
+		       ........  .......
+		        33.33%     foo
+		        33.33%     bar
+		        33.33%     baz
+
+	       This is an original overhead and we'll filter out the first 'foo'
+	       entry. The value of 'relative' would increase the overhead of 'bar'
+	       and 'baz' to 50.00% for each, while 'absolute' would show their
+	       current overhead (33.33%).
+
 SEE ALSO
 --------
 linkperf:perf[1]

tools/perf/Documentation/perfconfig.example

@@ -5,7 +5,7 @@
 	medium = green, lightgray
 	normal = black, lightgray
 	selected = lightgray, magenta
-	code = blue, lightgray
+	jump_arrows = blue, lightgray
 	addr = magenta, lightgray
 
 [tui]

tools/perf/Makefile.perf

@@ -165,7 +165,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
 endif
 endif
 
+# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
+# Without this setting the output feature dump file misses some features, for
+# example, liberty. Select all checkers so we won't get an incomplete feature
+# dump file.
 ifeq ($(config),1)
+ifdef MAKECMDGOALS
+ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
+FEATURE_TESTS := all
+endif
+endif
 include config/Makefile
 endif
 
@@ -618,7 +627,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean
 	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
 		$(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
-		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c
+		$(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 

tools/perf/tests/.gitignore

 llvm-src-base.c
 llvm-src-kbuild.c
 llvm-src-prologue.c
+llvm-src-relocation.c

tools/perf/tests/Build

@@ -31,7 +31,7 @@ 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 llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
 perf-y += bpf.o
 perf-y += topology.o
 perf-y += cpumap.o
@@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
+$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build
+	$(call rule_mkdir)
+	$(Q)echo '#include <tests/llvm.h>' > $@
+	$(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@
+	$(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

tools/perf/tests/bpf-script-test-relocation.c

+/*
+ * bpf-script-test-relocation.c
+ * Test BPF loader checking relocation
+ */
+#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 BPF_ANY 0
+#define BPF_MAP_TYPE_ARRAY 2
+#define BPF_FUNC_map_lookup_elem 1
+#define BPF_FUNC_map_update_elem 2
+
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+	(void *) BPF_FUNC_map_lookup_elem;
+static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
+	(void *) BPF_FUNC_map_update_elem;
+
+struct bpf_map_def {
+	unsigned int type;
+	unsigned int key_size;
+	unsigned int value_size;
+	unsigned int max_entries;
+};
+
+#define SEC(NAME) __attribute__((section(NAME), used))
+struct bpf_map_def SEC("maps") my_table = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+int this_is_a_global_val;
+
+SEC("func=sys_write")
+int bpf_func__sys_write(void *ctx)
+{
+	int key = 0;
+	int value = 0;
+
+	/*
+	 * Incorrect relocation. Should not allow this program be
+	 * loaded into kernel.
+	 */
+	bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0);
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;

tools/perf/tests/bpf.c

@@ -71,6 +71,15 @@ static struct {
 		(NR_ITERS + 1) / 4,
 	},
 #endif
+	{
+		LLVM_TESTCASE_BPF_RELOCATION,
+		"Test BPF relocation checker",
+		"[bpf_relocation_test]",
+		"fix 'perf test LLVM' first",
+		"libbpf error when dealing with relocation",
+		NULL,
+		0,
+	},
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -190,7 +199,7 @@ static int __test__bpf(int idx)
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
 				       bpf_testcase_table[idx].prog_id,
-				       true);
+				       true, NULL);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
 			 bpf_testcase_table[idx].msg_compile_fail);
@@ -202,14 +211,21 @@ static int __test__bpf(int idx)
 
 	obj = prepare_bpf(obj_buf, obj_buf_sz,
 			  bpf_testcase_table[idx].name);
-	if (!obj) {
+	if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) {
+		if (!obj)
+			pr_debug("Fail to load BPF object: %s\n",
+				 bpf_testcase_table[idx].msg_load_fail);
+		else
+			pr_debug("Success unexpectedly: %s\n",
+				 bpf_testcase_table[idx].msg_load_fail);
 		ret = TEST_FAIL;
 		goto out;
 	}
 
-	ret = do_test(obj,
-		      bpf_testcase_table[idx].target_func,
-		      bpf_testcase_table[idx].expect_result);
+	if (obj)
+		ret = do_test(obj,
+			      bpf_testcase_table[idx].target_func,
+			      bpf_testcase_table[idx].expect_result);
 out:
 	bpf__clear();
 	return ret;

tools/perf/tests/llvm.c

@@ -35,6 +35,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused,
 static struct {
 	const char *source;
 	const char *desc;
+	bool should_load_fail;
 } bpf_source_table[__LLVM_TESTCASE_MAX] = {
 	[LLVM_TESTCASE_BASE] = {
 		.source = test_llvm__bpf_base_prog,
@@ -48,14 +49,19 @@ static struct {
 		.source = test_llvm__bpf_test_prologue_prog,
 		.desc = "Compile source for BPF prologue generation test",
 	},
+	[LLVM_TESTCASE_BPF_RELOCATION] = {
+		.source = test_llvm__bpf_test_relocation,
+		.desc = "Compile source for BPF relocation test",
+		.should_load_fail = true,
+	},
 };
 
-
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
 			 size_t *p_obj_buf_sz,
 			 enum test_llvm__testcase idx,
-			 bool force)
+			 bool force,
+			 bool *should_load_fail)
 {
 	const char *source;
 	const char *desc;
@@ -68,6 +74,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 
 	source = bpf_source_table[idx].source;
 	desc = bpf_source_table[idx].desc;
+	if (should_load_fail)
+		*should_load_fail = bpf_source_table[idx].should_load_fail;
 
 	perf_config(perf_config_cb, NULL);
 
@@ -136,14 +144,15 @@ int test__llvm(int subtest)
 	int ret;
 	void *obj_buf = NULL;
 	size_t obj_buf_sz = 0;
+	bool should_load_fail = false;
 
 	if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
 		return TEST_FAIL;
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-				       subtest, false);
+				       subtest, false, &should_load_fail);
 
-	if (ret == TEST_OK) {
+	if (ret == TEST_OK && !should_load_fail) {
 		ret = test__bpf_parsing(obj_buf, obj_buf_sz);
 		if (ret != TEST_OK) {
 			pr_debug("Failed to parse test case '%s'\n",

tools/perf/tests/llvm.h

@@ -7,14 +7,17 @@
 extern const char test_llvm__bpf_base_prog[];
 extern const char test_llvm__bpf_test_kbuild_prog[];
 extern const char test_llvm__bpf_test_prologue_prog[];
+extern const char test_llvm__bpf_test_relocation[];
 
 enum test_llvm__testcase {
 	LLVM_TESTCASE_BASE,
 	LLVM_TESTCASE_KBUILD,
 	LLVM_TESTCASE_BPF_PROLOGUE,
+	LLVM_TESTCASE_BPF_RELOCATION,
 	__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);
+			     enum test_llvm__testcase index, bool force,
+			     bool *should_load_fail);
 #endif

tools/perf/tests/vmlinux-kallsyms.c

@@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 */
 	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
 		struct symbol *pair, *first_pair;
-		bool backwards = true;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
 
@@ -151,27 +150,14 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 				continue;
 
 			} else {
-				struct rb_node *nnd;
-detour:
-				nnd = backwards ? rb_prev(&pair->rb_node) :
-						  rb_next(&pair->rb_node);
-				if (nnd) {
-					struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
-
-					if (UM(next->start) == mem_start) {
-						pair = next;
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL);
+				if (pair) {
+					if (UM(pair->start) == mem_start)
 						goto next_pair;
-					}
-				}
 
-				if (backwards) {
-					backwards = false;
-					pair = first_pair;
-					goto detour;
+					pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+						 mem_start, sym->name, pair->name);
 				}
-
-				pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
-					 mem_start, sym->name, pair->name);
 			}
 		} else
 			pr_debug("%#" PRIx64 ": %s not on kallsyms\n",

tools/perf/ui/browser.c

@@ -531,8 +531,8 @@ static struct ui_browser_colorset {
 		.bg	  = "yellow",
 	},
 	{
-		.colorset = HE_COLORSET_CODE,
-		.name	  = "code",
+		.colorset = HE_COLORSET_JUMP_ARROWS,
+		.name	  = "jump_arrows",
 		.fg	  = "blue",
 		.bg	  = "default",
 	},

tools/perf/ui/browser.h

@@ -7,7 +7,7 @@
 #define HE_COLORSET_MEDIUM	51
 #define HE_COLORSET_NORMAL	52
 #define HE_COLORSET_SELECTED	53
-#define HE_COLORSET_CODE	54
+#define HE_COLORSET_JUMP_ARROWS	54
 #define HE_COLORSET_ADDR	55
 #define HE_COLORSET_ROOT	56
 

tools/perf/ui/browsers/annotate.c

@@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
-	ui_browser__set_color(browser, HE_COLORSET_CODE);
+	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
 	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
 				 from, to);
 }

tools/perf/ui/browsers/hists.c

@@ -1782,7 +1782,7 @@ static int
 add_thread_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, struct thread *thread)
 {
-	if (thread == NULL)
+	if (!sort__has_thread || thread == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s %s(%d) thread",
@@ -1825,7 +1825,7 @@ static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	    char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s %s DSO",
@@ -1850,7 +1850,7 @@ static int
 add_map_opt(struct hist_browser *browser __maybe_unused,
 	    struct popup_action *act, char **optstr, struct map *map)
 {
-	if (map == NULL)
+	if (!sort__has_dso || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Browse map details") < 0)
@@ -1971,7 +1971,7 @@ static int
 add_socket_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, int socket_id)
 {
-	if (socket_id < 0)
+	if (!sort__has_socket || socket_id < 0)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s Processor Socket %d",
@@ -2263,10 +2263,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			continue;
 		}
 
-		if (!sort__has_sym)
-			goto add_exit_option;
-
-		if (browser->selection == NULL)
+		if (!sort__has_sym || browser->selection == NULL)
 			goto skip_annotation;
 
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -2306,11 +2303,16 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					     &options[nr_options],
 					     socked_id);
 		/* perf script support */
+		if (!is_report_browser(hbt))
+			goto skip_scripting;
+
 		if (browser->he_selection) {
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     thread, NULL);
+			if (sort__has_thread && thread) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     thread, NULL);
+			}
 			/*
 			 * Note that browser->selection != NULL
 			 * when browser->he_selection is not NULL,
@@ -2320,16 +2322,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			 *
 			 * See hist_browser__show_entry.
 			 */
-			nr_options += add_script_opt(browser,
-						     &actions[nr_options],
-						     &options[nr_options],
-						     NULL, browser->selection->sym);
+			if (sort__has_sym && browser->selection->sym) {
+				nr_options += add_script_opt(browser,
+							     &actions[nr_options],
+							     &options[nr_options],
+							     NULL, browser->selection->sym);
+			}
 		}
 		nr_options += add_script_opt(browser, &actions[nr_options],
 					     &options[nr_options], NULL, NULL);
 		nr_options += add_switch_opt(browser, &actions[nr_options],
 					     &options[nr_options]);
-add_exit_option:
+skip_scripting:
 		nr_options += add_exit_opt(browser, &actions[nr_options],
 					   &options[nr_options]);
 

tools/perf/util/cpumap.c

@@ -8,6 +8,10 @@
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
+static int max_cpu_num;
+static int max_node_num;
+static int *cpunode_map;
+
 static struct cpu_map *cpu_map__default_new(void)
 {
 	struct cpu_map *cpus;
@@ -486,6 +490,32 @@ static void set_max_node_num(void)
 		pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
 }
 
+int cpu__max_node(void)
+{
+	if (unlikely(!max_node_num))
+		set_max_node_num();
+
+	return max_node_num;
+}
+
+int cpu__max_cpu(void)
+{
+	if (unlikely(!max_cpu_num))
+		set_max_cpu_num();
+
+	return max_cpu_num;
+}
+
+int cpu__get_node(int cpu)
+{
+	if (unlikely(cpunode_map == NULL)) {
+		pr_debug("cpu_map not initialized\n");
+		return -1;
+	}
+
+	return cpunode_map[cpu];
+}
+
 static int init_cpunode_map(void)
 {
 	int i;

tools/perf/util/cpumap.h

@@ -57,37 +57,11 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
 	return map ? map->map[0] == -1 : true;
 }
 
-int max_cpu_num;
-int max_node_num;
-int *cpunode_map;
-
 int cpu__setup_cpunode_map(void);
 
-static inline int cpu__max_node(void)
-{
-	if (unlikely(!max_node_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_node_num;
-}
-
-static inline int cpu__max_cpu(void)
-{
-	if (unlikely(!max_cpu_num))
-		pr_debug("cpu_map not initialized\n");
-
-	return max_cpu_num;
-}
-
-static inline int cpu__get_node(int cpu)
-{
-	if (unlikely(cpunode_map == NULL)) {
-		pr_debug("cpu_map not initialized\n");
-		return -1;
-	}
-
-	return cpunode_map[cpu];
-}
+int cpu__max_node(void);
+int cpu__max_cpu(void);
+int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 		       int (*f)(struct cpu_map *map, int cpu, void *data),

tools/perf/util/dso.c

@@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso,
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
+
+		ret = -1;
+		if (!is_regular_file(filename))
+			break;
+
 		ret = filename__read_debuglink(filename, debuglink,
 					       size - (debuglink - filename));
 		}

tools/perf/util/evsel.c

@@ -2362,12 +2362,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EPERM:
 	case EACCES:
 		return scnprintf(msg, size,
-		 "You may not have permission to collect %sstats.\n"
-		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
-		 " -1 - Not paranoid at all\n"
-		 "  0 - Disallow raw tracepoint access for unpriv\n"
-		 "  1 - Disallow cpu events for unpriv\n"
-		 "  2 - Disallow kernel profiling for unpriv",
+		 "You may not have permission to collect %sstats.\n\n"
+		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
+		 "which controls use of the performance events system by\n"
+		 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+		 "The default value is 1:\n\n"
+		 "  -1: Allow use of (almost) all events by all users\n"
+		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
+		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
 				 target->system_wide ? "system-wide " : "");
 	case ENOENT:
 		return scnprintf(msg, size, "The %s event is not supported.",

tools/perf/util/hist.c

@@ -1254,28 +1254,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_dso(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (symbol_conf.exclude_other && !h->parent)
-			continue;
-
-		if (hists__filter_entry_by_dso(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__DSO);
-	}
-}
-
 static bool hists__filter_entry_by_thread(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1288,25 +1266,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_thread(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (hists__filter_entry_by_thread(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD);
-	}
-}
-
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1320,25 +1279,6 @@ static bool hists__filter_entry_by_symbol(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_symbol(struct hists *hists)
-{
-	struct rb_node *nd;
-
-	hists->stats.nr_non_filtered_samples = 0;
-
-	hists__reset_filter_stats(hists);
-	hists__reset_col_len(hists);
-
-	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
-		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-		if (hists__filter_entry_by_symbol(hists, h))
-			continue;
-
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
-	}
-}
-
 static bool hists__filter_entry_by_socket(struct hists *hists,
 					  struct hist_entry *he)
 {
@@ -1351,7 +1291,9 @@ static bool hists__filter_entry_by_socket(struct hists *hists,
 	return false;
 }
 
-void hists__filter_by_socket(struct hists *hists)
+typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he);
+
+static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter)
 {
 	struct rb_node *nd;
 
@@ -1363,13 +1305,37 @@ void hists__filter_by_socket(struct hists *hists)
 	for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
 		struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-		if (hists__filter_entry_by_socket(hists, h))
+		if (filter(hists, h))
 			continue;
 
-		hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+		hists__remove_entry_filter(hists, h, type);
 	}
 }
 
+void hists__filter_by_thread(struct hists *hists)
+{
+	hists__filter_by_type(hists, HIST_FILTER__THREAD,
+			      hists__filter_entry_by_thread);
+}
+
+void hists__filter_by_dso(struct hists *hists)
+{
+	hists__filter_by_type(hists, HIST_FILTER__DSO,
+			      hists__filter_entry_by_dso);
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+	hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
+			      hists__filter_entry_by_symbol);
+}
+
+void hists__filter_by_socket(struct hists *hists)
+{
+	hists__filter_by_type(hists, HIST_FILTER__SOCKET,
+			      hists__filter_entry_by_socket);
+}
+
 void events_stats__inc(struct events_stats *stats, u32 type)
 {
 	++stats->nr_events[0];

tools/perf/util/machine.h

@@ -179,6 +179,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine,
 				       mapp, filter);
 }
 
+static inline
+struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
+						   enum map_type type, const char *name,
+						   struct map **mapp,
+						   symbol_filter_t filter)
+{
+	return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
+					       mapp, filter);
+}
+
 static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
 					     struct map **mapp,

tools/perf/util/pmu.c

@@ -153,7 +153,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 	if (fd == -1)
 		return -1;
 
-		sret = read(fd, alias->unit, UNIT_MAX_LEN);
+	sret = read(fd, alias->unit, UNIT_MAX_LEN);
 	if (sret < 0)
 		goto error;
 

tools/perf/util/sort.c

@@ -25,6 +25,7 @@ int		sort__has_parent = 0;
 int		sort__has_sym = 0;
 int		sort__has_dso = 0;
 int		sort__has_socket = 0;
+int		sort__has_thread = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
 
 
@@ -2136,6 +2137,8 @@ static int sort_dimension__add(const char *tok,
 			sort__has_dso = 1;
 		} else if (sd->entry == &sort_socket) {
 			sort__has_socket = 1;
+		} else if (sd->entry == &sort_thread) {
+			sort__has_thread = 1;
 		}
 
 		return __sort_dimension__add(sd);

tools/perf/util/sort.h

@@ -32,9 +32,11 @@ extern const char default_sort_order[];
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
 extern int sort__need_collapse;
+extern int sort__has_dso;
 extern int sort__has_parent;
 extern int sort__has_sym;
 extern int sort__has_socket;
+extern int sort__has_thread;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;

tools/perf/util/stat.c

@@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
 	struct perf_stat_evsel *ps = evsel->priv;
@@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 	perf_stat_evsel_id_init(evsel);
 }
 
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
 	if (evsel->priv == NULL)
@@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 	return 0;
 }
 
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
 	zfree(&evsel->priv);
 }
 
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+					     int ncpus, int nthreads)
 {
 	struct perf_counts *counts;
 
@@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
 	return counts ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
 	perf_counts__delete(evsel->prev_raw_counts);
 	evsel->prev_raw_counts = NULL;
 }
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
 	int ncpus = perf_evsel__nr_cpus(evsel);
 	int nthreads = thread_map__nr(evsel->threads);

tools/perf/util/stat.h

@@ -74,16 +74,6 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				   double avg, int cpu, enum aggr_mode aggr);
 
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
-
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-				      int ncpus, int nthreads);
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
-
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
-
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
 void perf_evlist__reset_stats(struct perf_evlist *evlist);

tools/perf/util/symbol.c

@@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	 * Read the build id if possible. This is required for
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
-	if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+	if (is_regular_file(name) &&
+	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
 
 	/*
@@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 						   root_dir, name, PATH_MAX))
 			continue;
 
+		if (!is_regular_file(name))
+			continue;
+
 		/* Name is now the name of the next image to try */
 		if (symsrc__init(ss, dso, name, symtab_type) < 0)
 			continue;

tools/perf/util/util.c

@@ -691,3 +691,13 @@ const char *perf_tip(const char *dirpath)
 
 	return tip;
 }
+
+bool is_regular_file(const char *file)
+{
+	struct stat st;
+
+	if (stat(file, &st))
+		return false;
+
+	return S_ISREG(st.st_mode);
+}

tools/perf/util/util.h

@@ -343,5 +343,6 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_PARAM(x)	KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
 const char *perf_tip(const char *dirpath);
+bool is_regular_file(const char *file);
 
 #endif /* GIT_COMPAT_UTIL_H */