Merge tag 'perf-core-for-mingo-20160908' of...

Merge tag 'perf-core-for-mingo-20160908' 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:

- Add branch stack / basic block info to 'perf annotate --stdio', where for
  each branch, we add an asm comment after the instruction with information on
  how often it was taken and predicted. See example with color output at:

    http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

  (Peter Zijlstra)

- Only open an evsel in CPUs in its cpu map, fixing some use cases in
  systems with multiple PMUs with different CPU maps (Mark Rutland)

- Fix handling of huge TLB maps, recognizing it as anonymous (Wang Nan)

Infrastructure changes:

- Remove the symbol filtering code, i.e. the callbacks passed to all functions
  that could end up loading a DSO symtab, simplifying the code, eventually
  allowing what we should have had since day one: removing the 'map' parameter
  from dso__load() functions (Arnaldo Carvalho de Melo)

Arch specific build fixes:

- Fix detached tarball build on powerpc, where we were still accessing a
  file outside tools/ (Ravi Bangoria)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

tools/lib/api/fs/fs.c

@@ -34,6 +34,10 @@
 #define TRACEFS_MAGIC          0x74726163
 #endif
 
+#ifndef HUGETLBFS_MAGIC
+#define HUGETLBFS_MAGIC        0x958458f6
+#endif
+
 static const char * const sysfs__fs_known_mountpoints[] = {
 	"/sys",
 	0,
@@ -67,6 +71,10 @@ static const char * const tracefs__known_mountpoints[] = {
 	0,
 };
 
+static const char * const hugetlbfs__known_mountpoints[] = {
+	0,
+};
+
 struct fs {
 	const char		*name;
 	const char * const	*mounts;
@@ -80,6 +88,7 @@ enum {
 	FS__PROCFS  = 1,
 	FS__DEBUGFS = 2,
 	FS__TRACEFS = 3,
+	FS__HUGETLBFS = 4,
 };
 
 #ifndef TRACEFS_MAGIC
@@ -107,6 +116,11 @@ static struct fs fs__entries[] = {
 		.mounts	= tracefs__known_mountpoints,
 		.magic	= TRACEFS_MAGIC,
 	},
+	[FS__HUGETLBFS] = {
+		.name	= "hugetlbfs",
+		.mounts = hugetlbfs__known_mountpoints,
+		.magic	= HUGETLBFS_MAGIC,
+	},
 };
 
 static bool fs__read_mounts(struct fs *fs)
@@ -265,6 +279,7 @@ FS(sysfs,   FS__SYSFS);
 FS(procfs,  FS__PROCFS);
 FS(debugfs, FS__DEBUGFS);
 FS(tracefs, FS__TRACEFS);
+FS(hugetlbfs, FS__HUGETLBFS);
 
 int filename__read_int(const char *filename, int *value)
 {

tools/lib/api/fs/fs.h

@@ -21,6 +21,7 @@ FS(sysfs)
 FS(procfs)
 FS(debugfs)
 FS(tracefs)
+FS(hugetlbfs)
 
 #undef FS
 

tools/perf/arch/powerpc/util/sym-handling.c

@@ -108,7 +108,7 @@ void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
 	int i = 0;
 
 	map = get_target_map(pev->target, pev->uprobes);
-	if (!map || map__load(map, NULL) < 0)
+	if (!map || map__load(map) < 0)
 		return;
 
 	for (i = 0; i < ntevs; i++) {

tools/perf/builtin-annotate.c

@@ -30,6 +30,7 @@
 #include "util/tool.h"
 #include "util/data.h"
 #include "arch/common.h"
+#include "util/block-range.h"
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>
@@ -46,6 +47,103 @@ struct perf_annotate {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+/*
+ * Given one basic block:
+ *
+ *	from	to		branch_i
+ *	* ----> *
+ *		|
+ *		| block
+ *		v
+ *		* ----> *
+ *		from	to	branch_i+1
+ *
+ * where the horizontal are the branches and the vertical is the executed
+ * block of instructions.
+ *
+ * We count, for each 'instruction', the number of blocks that covered it as
+ * well as count the ratio each branch is taken.
+ *
+ * We can do this without knowing the actual instruction stream by keeping
+ * track of the address ranges. We break down ranges such that there is no
+ * overlap and iterate from the start until the end.
+ *
+ * @acme: once we parse the objdump output _before_ processing the samples,
+ * we can easily fold the branch.cycles IPC bits in.
+ */
+static void process_basic_block(struct addr_map_symbol *start,
+				struct addr_map_symbol *end,
+				struct branch_flags *flags)
+{
+	struct symbol *sym = start->sym;
+	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
+	struct block_range_iter iter;
+	struct block_range *entry;
+
+	/*
+	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
+	 */
+	if (!start->addr || start->addr > end->addr)
+		return;
+
+	iter = block_range__create(start->addr, end->addr);
+	if (!block_range_iter__valid(&iter))
+		return;
+
+	/*
+	 * First block in range is a branch target.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_target);
+	entry->entry++;
+
+	do {
+		entry = block_range_iter(&iter);
+
+		entry->coverage++;
+		entry->sym = sym;
+
+		if (notes)
+			notes->max_coverage = max(notes->max_coverage, entry->coverage);
+
+	} while (block_range_iter__next(&iter));
+
+	/*
+	 * Last block in rage is a branch.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_branch);
+	entry->taken++;
+	if (flags->predicted)
+		entry->pred++;
+}
+
+static void process_branch_stack(struct branch_stack *bs, struct addr_location *al,
+				 struct perf_sample *sample)
+{
+	struct addr_map_symbol *prev = NULL;
+	struct branch_info *bi;
+	int i;
+
+	if (!bs || !bs->nr)
+		return;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return;
+
+	for (i = bs->nr - 1; i >= 0; i--) {
+		/*
+		 * XXX filter against symbol
+		 */
+		if (prev)
+			process_basic_block(prev, &bi[i].from, &bi[i].flags);
+		prev = &bi[i].to;
+	}
+
+	free(bi);
+}
+
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
@@ -72,6 +170,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	/*
+	 * XXX filtered samples can still have branch entires pointing into our
+	 * symbol and are missed.
+	 */
+	process_branch_stack(sample->branch_stack, al, sample);
+
 	sample->period = 1;
 	sample->weight = 1;
 

tools/perf/builtin-inject.c

@@ -429,7 +429,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
 			al.map->dso->hit = 1;
-			if (map__load(al.map, NULL) >= 0) {
+			if (map__load(al.map) >= 0) {
 				dso__inject_build_id(al.map->dso, tool, machine);
 				/*
 				 * If this fails, too bad, let the other side

tools/perf/builtin-kmem.c

@@ -330,7 +330,7 @@ static int build_alloc_func_list(void)
 	}
 
 	kernel_map = machine__kernel_map(machine);
-	if (map__load(kernel_map, NULL) < 0) {
+	if (map__load(kernel_map) < 0) {
 		pr_err("cannot load kernel map\n");
 		return -ENOENT;
 	}
@@ -979,7 +979,7 @@ static void __print_slab_result(struct rb_root *root,
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = machine__find_kernel_function(machine, addr, &map, NULL);
+				sym = machine__find_kernel_function(machine, addr, &map);
 		} else
 			addr = data->ptr;
 
@@ -1043,8 +1043,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite,
-						    &map, NULL);
+		sym = machine__find_kernel_function(machine, data->callsite, &map);
 		if (sym && sym->name)
 			caller = sym->name;
 		else
@@ -1086,8 +1085,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite,
-						    &map, NULL);
+		sym = machine__find_kernel_function(machine, data->callsite, &map);
 		if (sym && sym->name)
 			caller = sym->name;
 		else

tools/perf/builtin-script.c

@@ -522,11 +522,11 @@ static void print_sample_brstacksym(struct perf_sample *sample,
 
 		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
 		if (alf.map)
-			alf.sym = map__find_symbol(alf.map, alf.addr, NULL);
+			alf.sym = map__find_symbol(alf.map, alf.addr);
 
 		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		if (alt.map)
-			alt.sym = map__find_symbol(alt.map, alt.addr, NULL);
+			alt.sym = map__find_symbol(alt.map, alt.addr);
 
 		symbol__fprintf_symname_offs(alf.sym, &alf, stdout);
 		putchar('/');

tools/perf/builtin-top.c

@@ -657,34 +657,6 @@ static void *display_thread(void *arg)
 	return NULL;
 }
 
-static int symbol_filter(struct map *map, struct symbol *sym)
-{
-	const char *name = sym->name;
-
-	if (!__map__is_kernel(map))
-		return 0;
-	/*
-	 * ppc64 uses function descriptors and appends a '.' to the
-	 * start of every instruction address. Remove it.
-	 */
-	if (name[0] == '.')
-		name++;
-
-	if (!strcmp(name, "_text") ||
-	    !strcmp(name, "_etext") ||
-	    !strcmp(name, "_sinittext") ||
-	    !strncmp("init_module", name, 11) ||
-	    !strncmp("cleanup_module", name, 14) ||
-	    strstr(name, "_text_start") ||
-	    strstr(name, "_text_end"))
-		return 1;
-
-	if (symbol__is_idle(sym))
-		sym->idle = 1;
-
-	return 0;
-}
-
 static int hist_iter__top_callback(struct hist_entry_iter *iter,
 				   struct addr_location *al, bool single,
 				   void *arg)
@@ -949,8 +921,6 @@ static int __cmd_top(struct perf_top *top)
 	if (top->session == NULL)
 		return -1;
 
-	machines__set_symbol_filter(&top->session->machines, symbol_filter);
-
 	if (!objdump_path) {
 		ret = perf_env__lookup_objdump(&top->session->header.env);
 		if (ret)

tools/perf/perf-sys.h

@@ -20,7 +20,6 @@
 #endif
 
 #ifdef __powerpc__
-#include "../../arch/powerpc/include/uapi/asm/unistd.h"
 #define CPUINFO_PROC	{"cpu"}
 #endif
 

tools/perf/tests/code-reading.c

@@ -263,7 +263,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 	 * Converting addresses for use by objdump requires more information.
 	 * map__load() does that.  See map__rip_2objdump() for details.
 	 */
-	if (map__load(al.map, NULL))
+	if (map__load(al.map))
 		return -1;
 
 	/* objdump struggles with kcore - try each map only once */
@@ -511,7 +511,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	/* Load kernel map */
 	map = machine__kernel_map(machine);
-	ret = map__load(map, NULL);
+	ret = map__load(map);
 	if (ret < 0) {
 		pr_debug("map__load failed\n");
 		goto out_err;

tools/perf/tests/vmlinux-kallsyms.c

@@ -8,14 +8,6 @@
 #include "debug.h"
 #include "machine.h"
 
-static int vmlinux_matches_kallsyms_filter(struct map *map __maybe_unused,
-					   struct symbol *sym)
-{
-	bool *visited = symbol__priv(sym);
-	*visited = true;
-	return 0;
-}
-
 #define UM(x) kallsyms_map->unmap_ip(kallsyms_map, (x))
 
 int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
@@ -62,7 +54,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true, NULL) <= 0) {
+	if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true) <= 0) {
 		pr_debug("dso__load_kallsyms ");
 		goto out;
 	}
@@ -100,8 +92,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 	 * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
 	 * to fixup the symbols.
 	 */
-	if (machine__load_vmlinux_path(&vmlinux, type,
-				       vmlinux_matches_kallsyms_filter) <= 0) {
+	if (machine__load_vmlinux_path(&vmlinux, type) <= 0) {
 		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
 		err = TEST_SKIP;
 		goto out;
@@ -127,7 +118,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 		mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
 
 		first_pair = machine__find_kernel_symbol(&kallsyms, type,
-							 mem_start, NULL, NULL);
+							 mem_start, NULL);
 		pair = first_pair;
 
 		if (pair && UM(pair->start) == mem_start) {
@@ -156,7 +147,7 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
 				 */
 				continue;
 			} else {
-				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL);
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL);
 				if (pair) {
 					if (UM(pair->start) == mem_start)
 						goto next_pair;

tools/perf/ui/browsers/annotate.c

@@ -495,7 +495,7 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 	if (!ins__is_call(dl->ins))
 		return false;
 
-	if (map_groups__find_ams(&target, NULL) ||
+	if (map_groups__find_ams(&target) ||
 	    map__rip_2objdump(target.map, target.map->map_ip(target.map,
 							     target.addr)) !=
 	    dl->ops.target.addr) {

tools/perf/ui/browsers/map.c

@@ -52,9 +52,9 @@ static int map_browser__search(struct map_browser *browser)
 
 	if (target[0] == '0' && tolower(target[1]) == 'x') {
 		u64 addr = strtoull(target, NULL, 16);
-		sym = map__find_symbol(browser->map, addr, NULL);
+		sym = map__find_symbol(browser->map, addr);
 	} else
-		sym = map__find_symbol_by_name(browser->map, target, NULL);
+		sym = map__find_symbol_by_name(browser->map, target);
 
 	if (sym != NULL) {
 		u32 *idx = symbol__browser_index(sym);

tools/perf/util/Build

 libperf-y += alias.o
 libperf-y += annotate.o
+libperf-y += block-range.o
 libperf-y += build-id.o
 libperf-y += config.o
 libperf-y += ctype.o

tools/perf/util/annotate.c

@@ -17,6 +17,7 @@
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
+#include "block-range.h"
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
@@ -859,6 +860,89 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 	return percent;
 }
 
+static const char *annotate__address_color(struct block_range *br)
+{
+	double cov = block_range__coverage(br);
+
+	if (cov >= 0) {
+		/* mark red for >75% coverage */
+		if (cov > 0.75)
+			return PERF_COLOR_RED;
+
+		/* mark dull for <1% coverage */
+		if (cov < 0.01)
+			return PERF_COLOR_NORMAL;
+	}
+
+	return PERF_COLOR_MAGENTA;
+}
+
+static const char *annotate__asm_color(struct block_range *br)
+{
+	double cov = block_range__coverage(br);
+
+	if (cov >= 0) {
+		/* mark dull for <1% coverage */
+		if (cov < 0.01)
+			return PERF_COLOR_NORMAL;
+	}
+
+	return PERF_COLOR_BLUE;
+}
+
+static void annotate__branch_printf(struct block_range *br, u64 addr)
+{
+	bool emit_comment = true;
+
+	if (!br)
+		return;
+
+#if 1
+	if (br->is_target && br->start == addr) {
+		struct block_range *branch = br;
+		double p;
+
+		/*
+		 * Find matching branch to our target.
+		 */
+		while (!branch->is_branch)
+			branch = block_range__next(branch);
+
+		p = 100 *(double)br->entry / branch->coverage;
+
+		if (p > 0.1) {
+			if (emit_comment) {
+				emit_comment = false;
+				printf("\t#");
+			}
+
+			/*
+			 * The percentage of coverage joined at this target in relation
+			 * to the next branch.
+			 */
+			printf(" +%.2f%%", p);
+		}
+	}
+#endif
+	if (br->is_branch && br->end == addr) {
+		double p = 100*(double)br->taken / br->coverage;
+
+		if (p > 0.1) {
+			if (emit_comment) {
+				emit_comment = false;
+				printf("\t#");
+			}
+
+			/*
+			 * The percentage of coverage leaving at this branch, and
+			 * its prediction ratio.
+			 */
+			printf(" -%.2f%% (p:%.2f%%)", p, 100*(double)br->pred  / br->taken);
+		}
+	}
+}
+
+
 static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 start,
 		      struct perf_evsel *evsel, u64 len, int min_pcnt, int printed,
 		      int max_lines, struct disasm_line *queue)
@@ -878,6 +962,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		s64 offset = dl->offset;
 		const u64 addr = start + offset;
 		struct disasm_line *next;
+		struct block_range *br;
 
 		next = disasm__get_next_ip_line(&notes->src->source, dl);
 
@@ -947,8 +1032,12 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		}
 
 		printf(" :	");
-		color_fprintf(stdout, PERF_COLOR_MAGENTA, "  %" PRIx64 ":", addr);
-		color_fprintf(stdout, PERF_COLOR_BLUE, "%s\n", dl->line);
+
+		br = block_range__find(addr);
+		color_fprintf(stdout, annotate__address_color(br), "  %" PRIx64 ":", addr);
+		color_fprintf(stdout, annotate__asm_color(br), "%s", dl->line);
+		annotate__branch_printf(br, addr);
+		printf("\n");
 
 		if (ppercents != &percent)
 			free(ppercents);
@@ -1077,7 +1166,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			.addr = dl->ops.target.addr,
 		};
 
-		if (!map_groups__find_ams(&target, NULL) &&
+		if (!map_groups__find_ams(&target) &&
 		    target.sym->start == target.al_addr)
 			dl->ops.target.name = strdup(target.sym->name);
 	}

tools/perf/util/annotate.h

@@ -130,6 +130,7 @@ struct annotated_source {
 
 struct annotation {
 	pthread_mutex_t		lock;
+	u64			max_coverage;
 	struct annotated_source *src;
 };
 

tools/perf/util/block-range.c

+#include "block-range.h"
+#include "annotate.h"
+
+struct {
+	struct rb_root root;
+	u64 blocks;
+} block_ranges;
+
+static void block_range__debug(void)
+{
+	/*
+	 * XXX still paranoid for now; see if we can make this depend on
+	 * DEBUG=1 builds.
+	 */
+#if 1
+	struct rb_node *rb;
+	u64 old = 0; /* NULL isn't executable */
+
+	for (rb = rb_first(&block_ranges.root); rb; rb = rb_next(rb)) {
+		struct block_range *entry = rb_entry(rb, struct block_range, node);
+
+		assert(old < entry->start);
+		assert(entry->start <= entry->end); /* single instruction block; jump to a jump */
+
+		old = entry->end;
+	}
+#endif
+}
+
+struct block_range *block_range__find(u64 addr)
+{
+	struct rb_node **p = &block_ranges.root.rb_node;
+	struct rb_node *parent = NULL;
+	struct block_range *entry;
+
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct block_range, node);
+
+		if (addr < entry->start)
+			p = &parent->rb_left;
+		else if (addr > entry->end)
+			p = &parent->rb_right;
+		else
+			return entry;
+	}
+
+	return NULL;
+}
+
+static inline void rb_link_left_of_node(struct rb_node *left, struct rb_node *node)
+{
+	struct rb_node **p = &node->rb_left;
+	while (*p) {
+		node = *p;
+		p = &node->rb_right;
+	}
+	rb_link_node(left, node, p);
+}
+
+static inline void rb_link_right_of_node(struct rb_node *right, struct rb_node *node)
+{
+	struct rb_node **p = &node->rb_right;
+	while (*p) {
+		node = *p;
+		p = &node->rb_left;
+	}
+	rb_link_node(right, node, p);
+}
+
+/**
+ * block_range__create
+ * @start: branch target starting this basic block
+ * @end:   branch ending this basic block
+ *
+ * Create all the required block ranges to precisely span the given range.
+ */
+struct block_range_iter block_range__create(u64 start, u64 end)
+{
+	struct rb_node **p = &block_ranges.root.rb_node;
+	struct rb_node *n, *parent = NULL;
+	struct block_range *next, *entry = NULL;
+	struct block_range_iter iter = { NULL, NULL };
+
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct block_range, node);
+
+		if (start < entry->start)
+			p = &parent->rb_left;
+		else if (start > entry->end)
+			p = &parent->rb_right;
+		else
+			break;
+	}
+
+	/*
+	 * Didn't find anything.. there's a hole at @start, however @end might
+	 * be inside/behind the next range.
+	 */
+	if (!*p) {
+		if (!entry) /* tree empty */
+			goto do_whole;
+
+		/*
+		 * If the last node is before, advance one to find the next.
+		 */
+		n = parent;
+		if (entry->end < start) {
+			n = rb_next(n);
+			if (!n)
+				goto do_whole;
+		}
+		next = rb_entry(n, struct block_range, node);
+
+		if (next->start <= end) { /* add head: [start...][n->start...] */
+			struct block_range *head = malloc(sizeof(struct block_range));
+			if (!head)
+				return iter;
+
+			*head = (struct block_range){
+				.start		= start,
+				.end		= next->start - 1,
+				.is_target	= 1,
+				.is_branch	= 0,
+			};
+
+			rb_link_left_of_node(&head->node, &next->node);
+			rb_insert_color(&head->node, &block_ranges.root);
+			block_range__debug();
+
+			iter.start = head;
+			goto do_tail;
+		}
+
+do_whole:
+		/*
+		 * The whole [start..end] range is non-overlapping.
+		 */
+		entry = malloc(sizeof(struct block_range));
+		if (!entry)
+			return iter;
+
+		*entry = (struct block_range){
+			.start		= start,
+			.end		= end,
+			.is_target	= 1,
+			.is_branch	= 1,
+		};
+
+		rb_link_node(&entry->node, parent, p);
+		rb_insert_color(&entry->node, &block_ranges.root);
+		block_range__debug();
+
+		iter.start = entry;
+		iter.end   = entry;
+		goto done;
+	}
+
+	/*
+	 * We found a range that overlapped with ours, split if needed.
+	 */
+	if (entry->start < start) { /* split: [e->start...][start...] */
+		struct block_range *head = malloc(sizeof(struct block_range));
+		if (!head)
+			return iter;
+
+		*head = (struct block_range){
+			.start		= entry->start,
+			.end		= start - 1,
+			.is_target	= entry->is_target,
+			.is_branch	= 0,
+
+			.coverage	= entry->coverage,
+			.entry		= entry->entry,
+		};
+
+		entry->start		= start;
+		entry->is_target	= 1;
+		entry->entry		= 0;
+
+		rb_link_left_of_node(&head->node, &entry->node);
+		rb_insert_color(&head->node, &block_ranges.root);
+		block_range__debug();
+
+	} else if (entry->start == start)
+		entry->is_target = 1;
+
+	iter.start = entry;
+
+do_tail:
+	/*
+	 * At this point we've got: @iter.start = [@start...] but @end can still be
+	 * inside or beyond it.
+	 */
+	entry = iter.start;
+	for (;;) {
+		/*
+		 * If @end is inside @entry, split.
+		 */
+		if (end < entry->end) { /* split: [...end][...e->end] */
+			struct block_range *tail = malloc(sizeof(struct block_range));
+			if (!tail)
+				return iter;
+
+			*tail = (struct block_range){
+				.start		= end + 1,
+				.end		= entry->end,
+				.is_target	= 0,
+				.is_branch	= entry->is_branch,
+
+				.coverage	= entry->coverage,
+				.taken		= entry->taken,
+				.pred		= entry->pred,
+			};
+
+			entry->end		= end;
+			entry->is_branch	= 1;
+			entry->taken		= 0;
+			entry->pred		= 0;
+
+			rb_link_right_of_node(&tail->node, &entry->node);
+			rb_insert_color(&tail->node, &block_ranges.root);
+			block_range__debug();
+
+			iter.end = entry;
+			goto done;
+		}
+
+		/*
+		 * If @end matches @entry, done
+		 */
+		if (end == entry->end) {
+			entry->is_branch = 1;
+			iter.end = entry;
+			goto done;
+		}
+
+		next = block_range__next(entry);
+		if (!next)
+			goto add_tail;
+
+		/*
+		 * If @end is in beyond @entry but not inside @next, add tail.
+		 */
+		if (end < next->start) { /* add tail: [...e->end][...end] */
+			struct block_range *tail;
+add_tail:
+			tail = malloc(sizeof(struct block_range));
+			if (!tail)
+				return iter;
+
+			*tail = (struct block_range){
+				.start		= entry->end + 1,
+				.end		= end,
+				.is_target	= 0,
+				.is_branch	= 1,
+			};
+
+			rb_link_right_of_node(&tail->node, &entry->node);
+			rb_insert_color(&tail->node, &block_ranges.root);
+			block_range__debug();
+
+			iter.end = tail;
+			goto done;
+		}
+
+		/*
+		 * If there is a hole between @entry and @next, fill it.
+		 */
+		if (entry->end + 1 != next->start) {
+			struct block_range *hole = malloc(sizeof(struct block_range));
+			if (!hole)
+				return iter;
+
+			*hole = (struct block_range){
+				.start		= entry->end + 1,
+				.end		= next->start - 1,
+				.is_target	= 0,
+				.is_branch	= 0,
+			};
+
+			rb_link_left_of_node(&hole->node, &next->node);
+			rb_insert_color(&hole->node, &block_ranges.root);
+			block_range__debug();
+		}
+
+		entry = next;
+	}
+
+done:
+	assert(iter.start->start == start && iter.start->is_target);
+	assert(iter.end->end == end && iter.end->is_branch);
+
+	block_ranges.blocks++;
+
+	return iter;
+}
+
+
+/*
+ * Compute coverage as:
+ *
+ *    br->coverage / br->sym->max_coverage
+ *
+ * This ensures each symbol has a 100% spot, to reflect that each symbol has a
+ * most covered section.
+ *
+ * Returns [0-1] for coverage and -1 if we had no data what so ever or the
+ * symbol does not exist.
+ */
+double block_range__coverage(struct block_range *br)
+{
+	struct symbol *sym;
+
+	if (!br) {
+		if (block_ranges.blocks)
+			return 0;
+
+		return -1;
+	}
+
+	sym = br->sym;
+	if (!sym)
+		return -1;
+
+	return (double)br->coverage / symbol__annotation(sym)->max_coverage;
+}

tools/perf/util/block-range.h

+#ifndef __PERF_BLOCK_RANGE_H
+#define __PERF_BLOCK_RANGE_H
+
+#include "symbol.h"
+
+/*
+ * struct block_range - non-overlapping parts of basic blocks
+ * @node:	treenode
+ * @start:	inclusive start of range
+ * @end:	inclusive end of range
+ * @is_target:	@start is a jump target
+ * @is_branch:	@end is a branch instruction
+ * @coverage:	number of blocks that cover this range
+ * @taken:	number of times the branch is taken (requires @is_branch)
+ * @pred:	number of times the taken branch was predicted
+ */
+struct block_range {
+	struct rb_node node;
+
+	struct symbol *sym;
+
+	u64 start;
+	u64 end;
+
+	int is_target, is_branch;
+
+	u64 coverage;
+	u64 entry;
+	u64 taken;
+	u64 pred;
+};
+
+static inline struct block_range *block_range__next(struct block_range *br)
+{
+	struct rb_node *n = rb_next(&br->node);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct block_range, node);
+}
+
+struct block_range_iter {
+	struct block_range *start;
+	struct block_range *end;
+};
+
+static inline struct block_range *block_range_iter(struct block_range_iter *iter)
+{
+	return iter->start;
+}
+
+static inline bool block_range_iter__next(struct block_range_iter *iter)
+{
+	if (iter->start == iter->end)
+		return false;
+
+	iter->start = block_range__next(iter->start);
+	return true;
+}
+
+static inline bool block_range_iter__valid(struct block_range_iter *iter)
+{
+	if (!iter->start || !iter->end)
+		return false;
+	return true;
+}
+
+extern struct block_range *block_range__find(u64 addr);
+extern struct block_range_iter block_range__create(u64 start, u64 end);
+extern double block_range__coverage(struct block_range *br);
+
+#endif /* __PERF_BLOCK_RANGE_H */

tools/perf/util/event.c

 #include <linux/types.h>
 #include <sys/mman.h>
+#include <api/fs/fs.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -248,6 +249,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	bool truncation = false;
 	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
+#ifdef MAP_HUGETLB
+	const char *hugetlbfs_mnt = hugetlbfs__mountpoint();
+	int hugetlbfs_mnt_len = hugetlbfs_mnt ? strlen(hugetlbfs_mnt) : 0;
+#endif
 
 	if (machine__is_default_guest(machine))
 		return 0;
@@ -342,6 +347,12 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
+#ifdef MAP_HUGETLB
+		if (!strncmp(execname, hugetlbfs_mnt, hugetlbfs_mnt_len)) {
+			strcpy(execname, anonstr);
+			event->mmap2.flags |= MAP_HUGETLB;
+		}
+#endif
 
 		size = strlen(execname) + 1;
 		memcpy(event->mmap2.filename, execname, size);
@@ -1286,7 +1297,7 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
 		 * must be done prior to using kernel maps.
 		 */
 		if (load_map)
-			map__load(al->map, machine->symbol_filter);
+			map__load(al->map);
 		al->addr = al->map->map_ip(al->map, al->addr);
 	}
 }
@@ -1297,8 +1308,7 @@ void thread__find_addr_location(struct thread *thread,
 {
 	thread__find_addr_map(thread, cpumode, type, addr, al);
 	if (al->map != NULL)
-		al->sym = map__find_symbol(al->map, al->addr,
-					   thread->mg->machine->symbol_filter);
+		al->sym = map__find_symbol(al->map, al->addr);
 	else
 		al->sym = NULL;
 }
@@ -1359,8 +1369,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 			al->filtered |= (1 << HIST_FILTER__DSO);
 		}
 
-		al->sym = map__find_symbol(al->map, al->addr,
-					   machine->symbol_filter);
+		al->sym = map__find_symbol(al->map, al->addr);
 	}
 
 	if (symbol_conf.sym_list &&
@@ -1416,5 +1425,5 @@ void thread__resolve(struct thread *thread, struct addr_location *al,
 	al->sym = NULL;
 
 	if (al->map)
-		al->sym = map__find_symbol(al->map, al->addr, NULL);
+		al->sym = map__find_symbol(al->map, al->addr);
 }

tools/perf/util/evlist.c

@@ -1032,16 +1032,18 @@ perf_evlist__should_poll(struct perf_evlist *evlist __maybe_unused,
 }
 
 static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
-				       struct mmap_params *mp, int cpu,
+				       struct mmap_params *mp, int cpu_idx,
 				       int thread, int *_output, int *_output_backward)
 {
 	struct perf_evsel *evsel;
 	int revent;
+	int evlist_cpu = cpu_map__cpu(evlist->cpus, cpu_idx);
 
 	evlist__for_each_entry(evlist, evsel) {
 		struct perf_mmap *maps = evlist->mmap;
 		int *output = _output;
 		int fd;
+		int cpu;
 
 		if (evsel->attr.write_backward) {
 			output = _output_backward;
@@ -1060,6 +1062,10 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 		if (evsel->system_wide && thread)
 			continue;
 
+		cpu = cpu_map__idx(evsel->cpus, evlist_cpu);
+		if (cpu == -1)
+			continue;
+
 		fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {

tools/perf/util/intel-bts.c

@@ -346,7 +346,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
 		goto out_put;
 
 	/* Load maps to ensure dso->is_64_bit has been updated */
-	map__load(al.map, machine->symbol_filter);
+	map__load(al.map);
 
 	x86_64 = al.map->dso->is_64_bit;
 

tools/perf/util/intel-pt.c

@@ -477,7 +477,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 		start_ip = *ip;
 
 		/* Load maps to ensure dso->is_64_bit has been updated */
-		map__load(al.map, machine->symbol_filter);
+		map__load(al.map);
 
 		x86_64 = al.map->dso->is_64_bit;
 
@@ -1294,7 +1294,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	if (!map)
 		return 0;
 
-	if (map__load(map, machine->symbol_filter))
+	if (map__load(map))
 		return 0;
 
 	start = dso__first_symbol(map->dso, MAP__FUNCTION);

tools/perf/util/machine.c

@@ -41,7 +41,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->pid = pid;
 
-	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
 	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
@@ -148,7 +147,6 @@ void machines__init(struct machines *machines)
 {
 	machine__init(&machines->host, "", HOST_KERNEL_ID);
 	machines->guests = RB_ROOT;
-	machines->symbol_filter = NULL;
 }
 
 void machines__exit(struct machines *machines)
@@ -172,8 +170,6 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
 		return NULL;
 	}
 
-	machine->symbol_filter = machines->symbol_filter;
-
 	while (*p != NULL) {
 		parent = *p;
 		pos = rb_entry(parent, struct machine, rb_node);
@@ -189,21 +185,6 @@ struct machine *machines__add(struct machines *machines, pid_t pid,
 	return machine;
 }
 
-void machines__set_symbol_filter(struct machines *machines,
-				 symbol_filter_t symbol_filter)
-{
-	struct rb_node *nd;
-
-	machines->symbol_filter = symbol_filter;
-	machines->host.symbol_filter = symbol_filter;
-
-	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
-		struct machine *machine = rb_entry(nd, struct machine, rb_node);
-
-		machine->symbol_filter = symbol_filter;
-	}
-}
-
 void machines__set_comm_exec(struct machines *machines, bool comm_exec)
 {
 	struct rb_node *nd;
@@ -916,10 +897,10 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 }
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore, symbol_filter_t filter)
+			     enum map_type type, bool no_kcore)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore, filter);
+	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore);
 
 	if (ret > 0) {
 		dso__set_loaded(map->dso, type);
@@ -935,16 +916,15 @@ int __machine__load_kallsyms(struct machine *machine, const char *filename,
 }
 
 int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter)
+			   enum map_type type)
 {
-	return __machine__load_kallsyms(machine, filename, type, false, filter);
+	return __machine__load_kallsyms(machine, filename, type, false);
 }
 
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-			       symbol_filter_t filter)
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = dso__load_vmlinux_path(map->dso, map, filter);
+	int ret = dso__load_vmlinux_path(map->dso, map);
 
 	if (ret > 0)
 		dso__set_loaded(map->dso, type);
@@ -1313,7 +1293,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			/*
 			 * preload dso of guest kernel and modules
 			 */
-			dso__load(kernel, machine__kernel_map(machine), NULL);
+			dso__load(kernel, machine__kernel_map(machine));
 		}
 	}
 	return 0;
@@ -2115,7 +2095,7 @@ int machine__get_kernel_start(struct machine *machine)
 	 */
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
-		err = map__load(map, machine->symbol_filter);
+		err = map__load(map);
 		if (map->start)
 			machine->kernel_start = map->start;
 	}
@@ -2131,7 +2111,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 {
 	struct machine *machine = vmachine;
 	struct map *map;
-	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map,  NULL);
+	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map);
 
 	if (sym == NULL)
 		return NULL;

tools/perf/util/machine.h

@@ -41,7 +41,6 @@ struct machine {
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	u64		  kernel_start;
-	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
 	union { /* Tool specific area */
 		void	  *priv;
@@ -110,7 +109,6 @@ typedef void (*machine__process_t)(struct machine *machine, void *data);
 struct machines {
 	struct machine host;
 	struct rb_root guests;
-	symbol_filter_t symbol_filter;
 };
 
 void machines__init(struct machines *machines);
@@ -128,8 +126,6 @@ struct machine *machines__findnew(struct machines *machines, pid_t pid);
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
 char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
-void machines__set_symbol_filter(struct machines *machines,
-				 symbol_filter_t symbol_filter);
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
@@ -178,40 +174,33 @@ size_t machine__fprintf(struct machine *machine, FILE *fp);
 static inline
 struct symbol *machine__find_kernel_symbol(struct machine *machine,
 					   enum map_type type, u64 addr,
-					   struct map **mapp,
-					   symbol_filter_t filter)
+					   struct map **mapp)
 {
-	return map_groups__find_symbol(&machine->kmaps, type, addr,
-				       mapp, filter);
+	return map_groups__find_symbol(&machine->kmaps, type, addr, mapp);
 }
 
 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)
+						   struct map **mapp)
 {
-	return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
-					       mapp, filter);
+	return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
-					     struct map **mapp,
-					     symbol_filter_t filter)
+					     struct map **mapp)
 {
 	return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
-					   mapp, filter);
+					   mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 						     const char *name,
-						     struct map **mapp,
-						     symbol_filter_t filter)
+						     struct map **mapp)
 {
-	return map_groups__find_function_by_name(&machine->kmaps, name, mapp,
-						 filter);
+	return map_groups__find_function_by_name(&machine->kmaps, name, mapp);
 }
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
@@ -219,11 +208,10 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 int arch__fix_module_text_start(u64 *start, const char *name);
 
 int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore, symbol_filter_t filter);
+			     enum map_type type, bool no_kcore);
 int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type, symbol_filter_t filter);
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type,
-			       symbol_filter_t filter);
+			   enum map_type type);
+int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
 
 size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm);

tools/perf/util/map.c

@@ -6,6 +6,7 @@
 #include <string.h>
 #include <stdio.h>
 #include <unistd.h>
+#include <sys/mman.h>
 #include "map.h"
 #include "thread.h"
 #include "strlist.h"
@@ -24,9 +25,15 @@ const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__VARIABLE] = "Variables",
 };
 
-static inline int is_anon_memory(const char *filename)
+static inline int is_anon_memory(const char *filename, u32 flags)
 {
-	return !strcmp(filename, "//anon") ||
+	u32 anon_flags = 0;
+
+#ifdef MAP_HUGETLB
+	anon_flags |= MAP_HUGETLB;
+#endif
+	return flags & anon_flags ||
+	       !strcmp(filename, "//anon") ||
 	       !strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
 	       !strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
 }
@@ -155,7 +162,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		int anon, no_dso, vdso, android;
 
 		android = is_android_lib(filename);
-		anon = is_anon_memory(filename);
+		anon = is_anon_memory(filename, flags);
 		vdso = is_vdso_map(filename);
 		no_dso = is_no_dso_memory(filename);
 
@@ -279,7 +286,7 @@ void map__fixup_end(struct map *map)
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *map, symbol_filter_t filter)
+int map__load(struct map *map)
 {
 	const char *name = map->dso->long_name;
 	int nr;
@@ -287,7 +294,7 @@ int map__load(struct map *map, symbol_filter_t filter)
 	if (dso__loaded(map->dso, map->type))
 		return 0;
 
-	nr = dso__load(map->dso, map, filter);
+	nr = dso__load(map->dso, map);
 	if (nr < 0) {
 		if (map->dso->has_build_id) {
 			char sbuild_id[SBUILD_ID_SIZE];
@@ -312,9 +319,6 @@ int map__load(struct map *map, symbol_filter_t filter)
 			pr_warning("%.*s was updated (is prelink enabled?). "
 				"Restart the long running apps that use it!\n",
 				   (int)real_len, name);
-		} else if (filter) {
-			pr_warning("no symbols passed the given filter.\n");
-			return -2;	/* Empty but maybe by the filter */
 		} else {
 			pr_warning("no symbols found in %s, maybe install "
 				   "a debug package?\n", name);
@@ -331,19 +335,17 @@ int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
 	return strcmp(namea, nameb);
 }
 
-struct symbol *map__find_symbol(struct map *map, u64 addr,
-				symbol_filter_t filter)
+struct symbol *map__find_symbol(struct map *map, u64 addr)
 {
-	if (map__load(map, filter) < 0)
+	if (map__load(map) < 0)
 		return NULL;
 
 	return dso__find_symbol(map->dso, map->type, addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
-					symbol_filter_t filter)
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 {
-	if (map__load(map, filter) < 0)
+	if (map__load(map) < 0)
 		return NULL;
 
 	if (!dso__sorted_by_name(map->dso, map->type))
@@ -556,23 +558,22 @@ void map_groups__put(struct map_groups *mg)
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
-				       struct map **mapp,
-				       symbol_filter_t filter)
+				       struct map **mapp)
 {
 	struct map *map = map_groups__find(mg, type, addr);
 
 	/* Ensure map is loaded before using map->map_ip */
-	if (map != NULL && map__load(map, filter) >= 0) {
+	if (map != NULL && map__load(map) >= 0) {
 		if (mapp != NULL)
 			*mapp = map;
-		return map__find_symbol(map, map->map_ip(map, addr), filter);
+		return map__find_symbol(map, map->map_ip(map, addr));
 	}
 
 	return NULL;
 }
 
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
-					 struct map **mapp, symbol_filter_t filter)
+					 struct map **mapp)
 {
 	struct symbol *sym;
 	struct rb_node *nd;
@@ -582,7 +583,7 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 
-		sym = map__find_symbol_by_name(pos, name, filter);
+		sym = map__find_symbol_by_name(pos, name);
 
 		if (sym == NULL)
 			continue;
@@ -600,15 +601,14 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
-					       struct map **mapp,
-					       symbol_filter_t filter)
+					       struct map **mapp)
 {
-	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp, filter);
+	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp);
 
 	return sym;
 }
 
-int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
+int map_groups__find_ams(struct addr_map_symbol *ams)
 {
 	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
 		if (ams->map->groups == NULL)
@@ -620,7 +620,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	}
 
 	ams->al_addr = ams->map->map_ip(ams->map, ams->addr);
-	ams->sym = map__find_symbol(ams->map, ams->al_addr, filter);
+	ams->sym = map__find_symbol(ams->map, ams->al_addr);
 
 	return ams->sym ? 0 : -1;
 }

tools/perf/util/map.h

@@ -127,17 +127,14 @@ struct thread;
  * @map: the 'struct map *' in which symbols itereated
  * @sym_name: the symbol name
  * @pos: the 'struct symbol *' to use as a loop cursor
- * @filter: to use when loading the DSO
  */
-#define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
-	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
+#define __map__for_each_symbol_by_name(map, sym_name, pos)	\
+	for (pos = map__find_symbol_by_name(map, sym_name);	\
 	     pos && arch__compare_symbol_names(pos->name, sym_name) == 0;	\
 	     pos = symbol__next_by_name(pos))
 
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
-	__map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
-
-typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
+	__map__for_each_symbol_by_name(map, sym_name, (pos))
 
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 void map__init(struct map *map, enum map_type type,
@@ -173,11 +170,9 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 			 FILE *fp);
 
-int map__load(struct map *map, symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *map,
-				u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
-					symbol_filter_t filter);
+int map__load(struct map *map);
+struct symbol *map__find_symbol(struct map *map, u64 addr);
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name);
 void map__fixup_start(struct map *map);
 void map__fixup_end(struct map *map);
 
@@ -191,7 +186,7 @@ struct map *maps__find(struct maps *maps, u64 addr);
 struct map *maps__first(struct maps *maps);
 struct map *map__next(struct map *map);
 struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
-                                         struct map **mapp, symbol_filter_t filter);
+                                         struct map **mapp);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct thread *thread,
@@ -231,25 +226,22 @@ static inline struct map *map_groups__next(struct map *map)
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
-				       struct map **mapp,
-				       symbol_filter_t filter);
+				       struct map **mapp);
 
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
-					       struct map **mapp,
-					       symbol_filter_t filter);
+					       struct map **mapp);
 
 struct addr_map_symbol;
 
-int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter);
+int map_groups__find_ams(struct addr_map_symbol *ams);
 
 static inline
 struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
-						 const char *name, struct map **mapp,
-						 symbol_filter_t filter)
+						 const char *name, struct map **mapp)
 {
-	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
+	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp);
 }
 
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,

tools/perf/util/pmu.c

@@ -445,14 +445,23 @@ static struct cpu_map *pmu_cpumask(const char *name)
 	FILE *file;
 	struct cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
+	const char *templates[] = {
+		 "%s/bus/event_source/devices/%s/cpumask",
+		 "%s/bus/event_source/devices/%s/cpus",
+		 NULL
+	};
+	const char **template;
 
 	if (!sysfs)
 		return NULL;
 
-	snprintf(path, PATH_MAX,
-		 "%s/bus/event_source/devices/%s/cpumask", sysfs, name);
+	for (template = templates; *template; template++) {
+		snprintf(path, PATH_MAX, *template, sysfs, name);
+		if (stat(path, &st) == 0)
+			break;
+	}
 
-	if (stat(path, &st) < 0)
+	if (!*template)
 		return NULL;
 
 	file = fopen(path, "r");

tools/perf/util/probe-event.c

@@ -110,13 +110,12 @@ void exit_probe_symbol_maps(void)
 static struct symbol *__find_kernel_function_by_name(const char *name,
 						     struct map **mapp)
 {
-	return machine__find_kernel_function_by_name(host_machine, name, mapp,
-						     NULL);
+	return machine__find_kernel_function_by_name(host_machine, name, mapp);
 }
 
 static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
 {
-	return machine__find_kernel_function(host_machine, addr, mapp, NULL);
+	return machine__find_kernel_function(host_machine, addr, mapp);
 }
 
 static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
@@ -125,7 +124,7 @@ static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 	struct kmap *kmap;
 	struct map *map = machine__kernel_map(host_machine);
 
-	if (map__load(map, NULL) < 0)
+	if (map__load(map) < 0)
 		return NULL;
 
 	kmap = map__kmap(map);
@@ -351,9 +350,9 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 	vmlinux_name = symbol_conf.vmlinux_name;
 	dso->load_errno = 0;
 	if (vmlinux_name)
-		ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL);
+		ret = dso__load_vmlinux(dso, map, vmlinux_name, false);
 	else
-		ret = dso__load_vmlinux_path(dso, map, NULL);
+		ret = dso__load_vmlinux_path(dso, map);
 found:
 	*pdso = dso;
 	return ret;
@@ -1999,7 +1998,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 		map = dso__new_map(tp->module);
 		if (!map)
 			goto out;
-		sym = map__find_symbol(map, addr, NULL);
+		sym = map__find_symbol(map, addr);
 	} else {
 		if (tp->symbol && !addr) {
 			if (kernel_get_symbol_address_by_name(tp->symbol,
@@ -2704,7 +2703,7 @@ static int find_probe_functions(struct map *map, char *name,
 	struct symbol *sym;
 	struct rb_node *tmp;
 
-	if (map__load(map, NULL) < 0)
+	if (map__load(map) < 0)
 		return 0;
 
 	map__for_each_symbol(map, sym, tmp) {
@@ -3368,7 +3367,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 		return -EINVAL;
 	}
 
-	ret = map__load(map, NULL);
+	ret = map__load(map);
 	if (ret) {
 		if (ret == -2) {
 			char *str = strfilter__string(_filter);

tools/perf/util/symbol-elf.c

@@ -254,8 +254,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map,
-				symbol_filter_t filter)
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map)
 {
 	uint32_t nr_rel_entries, idx;
 	GElf_Sym sym;
@@ -351,13 +350,9 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			if (!f)
 				goto out_elf_end;
 
-			if (filter && filter(map, f))
-				symbol__delete(f);
-			else {
 			symbols__insert(&dso->symbols[map->type], f);
 			++nr;
 		}
-		}
 	} else if (shdr_rel_plt.sh_type == SHT_REL) {
 		GElf_Rel pos_mem, *pos;
 		elf_section__for_each_rel(reldata, pos, pos_mem, idx,
@@ -381,14 +376,10 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			if (!f)
 				goto out_elf_end;
 
-			if (filter && filter(map, f))
-				symbol__delete(f);
-			else {
 			symbols__insert(&dso->symbols[map->type], f);
 			++nr;
 		}
 	}
-	}
 
 	err = 0;
 out_elf_end:
@@ -825,9 +816,8 @@ static u64 ref_reloc(struct kmap *kmap)
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
-int dso__load_sym(struct dso *dso, struct map *map,
-		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
-		  symbol_filter_t filter, int kmodule)
+int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
+		  struct symsrc *runtime_ss, int kmodule)
 {
 	struct kmap *kmap = dso->kernel ? map__kmap(map) : NULL;
 	struct map_groups *kmaps = kmap ? map__kmaps(map) : NULL;
@@ -1124,13 +1114,9 @@ int dso__load_sym(struct dso *dso, struct map *map,
 
 		arch__sym_update(f, &sym);
 
-		if (filter && filter(curr_map, f))
-			symbol__delete(f);
-		else {
-			symbols__insert(&curr_dso->symbols[curr_map->type], f);
+		__symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel);
 		nr++;
 	}
-	}
 
 	/*
 	 * For misannotated, zeroed, ASM function sizes.

tools/perf/util/symbol-minimal.c

@@ -287,8 +287,7 @@ void symsrc__destroy(struct symsrc *ss)
 
 int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
 				struct symsrc *ss __maybe_unused,
-				struct map *map __maybe_unused,
-				symbol_filter_t filter __maybe_unused)
+				struct map *map __maybe_unused)
 {
 	return 0;
 }
@@ -334,7 +333,6 @@ enum dso_type dso__type_fd(int fd)
 int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  struct symsrc *ss,
 		  struct symsrc *runtime_ss __maybe_unused,
-		  symbol_filter_t filter __maybe_unused,
 		  int kmodule __maybe_unused)
 {
 	unsigned char build_id[BUILD_ID_SIZE];

tools/perf/util/symbol.h

@@ -241,16 +241,13 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 bool symsrc__has_symtab(struct symsrc *ss);
 bool symsrc__possibly_runtime(struct symsrc *ss);
 
-int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter);
+int dso__load(struct dso *dso, struct map *map);
 int dso__load_vmlinux(struct dso *dso, struct map *map,
-		      const char *vmlinux, bool vmlinux_allocated,
-		      symbol_filter_t filter);
-int dso__load_vmlinux_path(struct dso *dso, struct map *map,
-			   symbol_filter_t filter);
+		      const char *vmlinux, bool vmlinux_allocated);
+int dso__load_vmlinux_path(struct dso *dso, struct map *map);
 int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
-			 bool no_kcore, symbol_filter_t filter);
-int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
-		       symbol_filter_t filter);
+			 bool no_kcore);
+int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
 
 void dso__insert_symbol(struct dso *dso, enum map_type type,
 			struct symbol *sym);
@@ -294,16 +291,15 @@ size_t symbol__fprintf(struct symbol *sym, FILE *fp);
 bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
-bool symbol__is_idle(struct symbol *sym);
 int symbol__config_symfs(const struct option *opt __maybe_unused,
 			 const char *dir, int unset __maybe_unused);
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
-		  struct symsrc *runtime_ss, symbol_filter_t filter,
-		  int kmodule);
+		  struct symsrc *runtime_ss, int kmodule);
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
-				struct map *map, symbol_filter_t filter);
+				struct map *map);
 
+void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
 void symbols__fixup_end(struct rb_root *symbols);