Merge tag 'perf-tools-for-v6.5-2-2023-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next

Pull more perf tools updates from Namhyung Kim:
 "These are remaining changes and fixes for this cycle.

  Build:

   - Allow generating vmlinux.h from BTF using `make GEN_VMLINUX_H=1`
     and skip if the vmlinux has no BTF.

   - Replace deprecated clang -target xxx option by --target=xxx.

  perf record:

   - Print event attributes with well known type and config symbols in
     the debug output like below:

       # perf record -e cycles,cpu-clock -C0 -vv true
       <SNIP>
       ------------------------------------------------------------
       perf_event_attr:
         type                             0 (PERF_TYPE_HARDWARE)
         size                             136
         config                           0 (PERF_COUNT_HW_CPU_CYCLES)
         { sample_period, sample_freq }   4000
         sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
         read_format                      ID
         disabled                         1
         inherit                          1
         freq                             1
         sample_id_all                    1
         exclude_guest                    1
       ------------------------------------------------------------
       sys_perf_event_open: pid -1  cpu 0  group_fd -1  flags 0x8 = 5
       ------------------------------------------------------------
       perf_event_attr:
         type                             1 (PERF_TYPE_SOFTWARE)
         size                             136
         config                           0 (PERF_COUNT_SW_CPU_CLOCK)
         { sample_period, sample_freq }   4000
         sample_type                      IP|TID|TIME|CPU|PERIOD|IDENTIFIER
         read_format                      ID
         disabled                         1
         inherit                          1
         freq                             1
         sample_id_all                    1
         exclude_guest                    1

   - Update AMD IBS event error message since it now support per-process
     profiling but no priviledge filters.

       $ sudo perf record -e ibs_op//k -C 0
       Error:
       AMD IBS doesn't support privilege filtering. Try again without
       the privilege modifiers (like 'k') at the end.

  perf lock contention:

   - Support CSV style output using -x option

       $ sudo perf lock con -ab -x, sleep 1
       # output: contended, total wait, max wait, avg wait, type, caller
       19, 194232, 21415, 10222, spinlock, process_one_work+0x1f0
       15, 162748, 23843, 10849, rwsem:R, do_user_addr_fault+0x40e
       4, 86740, 23415, 21685, rwlock:R, ep_poll_callback+0x2d
       1, 84281, 84281, 84281, mutex, iwl_mvm_async_handlers_wk+0x135
       8, 67608, 27404, 8451, spinlock, __queue_work+0x174
       3, 58616, 31125, 19538, rwsem:W, do_mprotect_pkey+0xff
       3, 52953, 21172, 17651, rwlock:W, do_epoll_wait+0x248
       2, 30324, 19704, 15162, rwsem:R, do_madvise+0x3ad
       1, 24619, 24619, 24619, spinlock, rcu_core+0xd4

   - Add --output option to save the data to a file not to be interfered
     by other debug messages.

  Test:

   - Fix event parsing test on ARM where there's no raw PMU nor supports
     PERF_PMU_CAP_EXTENDED_HW_TYPE.

   - Update the lock contention test case for CSV output.

   - Fix a segfault in the daemon command test.

  Vendor events (JSON):

   - Add has_event() to check if the given event is available on system
     at runtime. On Intel machines, some transaction events may not be
     present when TSC extensions are disabled.

   - Update Intel event metrics.

  Misc:

   - Sort symbols by name using an external array of pointers instead of
     a rbtree node in the symbol. This will save 16-bytes or 24-bytes
     per symbol whether the sorting is actually requested or not.

   - Fix unwinding DWARF callstacks using libdw when --symfs option is
     used"

* tag 'perf-tools-for-v6.5-2-2023-07-06' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next: (38 commits)
  perf test: Fix event parsing test when PERF_PMU_CAP_EXTENDED_HW_TYPE isn't supported.
  perf test: Fix event parsing test on Arm
  perf evsel amd: Fix IBS error message
  perf: unwind: Fix symfs with libdw
  perf symbol: Fix uninitialized return value in symbols__find_by_name()
  perf test: Test perf lock contention CSV output
  perf lock contention: Add --output option
  perf lock contention: Add -x option for CSV style output
  perf lock: Remove stale comments
  perf vendor events intel: Update tigerlake to 1.13
  perf vendor events intel: Update skylakex to 1.31
  perf vendor events intel: Update skylake to 57
  perf vendor events intel: Update sapphirerapids to 1.14
  perf vendor events intel: Update icelakex to 1.21
  perf vendor events intel: Update icelake to 1.19
  perf vendor events intel: Update cascadelakex to 1.19
  perf vendor events intel: Update meteorlake to 1.03
  perf vendor events intel: Add rocketlake events/metrics
  perf vendor metrics intel: Make transaction metrics conditional
  perf jevents: Support for has_event function
  ...

28 files changed, 407 insertions, 145 deletions

diff --git a/tools/perf/util/bpf_skel/.gitignore b/tools/perf/util/bpf_skel/.gitignore
index 7a1c832825de..cd01455e1b53 100644
--- a/tools/perf/util/bpf_skel/.gitignore
+++ b/tools/perf/util/bpf_skel/.gitignore
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 .tmp
 *.skel.h
+vmlinux.h
diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 1d48226ae75d..8d3cfbb3cc65 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -416,8 +416,6 @@ int contention_end(u64 *ctx)
 	return 0;
 }
 
-struct rq {};
-
 extern struct rq runqueues __ksym;
 
 struct rq___old {
diff --git a/tools/perf/util/bpf_skel/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
index c7ed51b0c1ef..ab84a6e1da5e 100644
--- a/tools/perf/util/bpf_skel/vmlinux.h
+++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
@@ -171,4 +171,14 @@ struct bpf_perf_event_data_kern {
 	struct perf_sample_data *data;
 	struct perf_event	*event;
 } __attribute__((preserve_access_index));
+
+/*
+ * If 'struct rq' isn't defined for lock_contention.bpf.c, for the sake of
+ * rq___old and rq___new, then the type for the 'runqueue' variable ends up
+ * being a forward declaration (BTF_KIND_FWD) while the kernel has it defined
+ * (BTF_KIND_STRUCT). The definition appears in vmlinux.h rather than
+ * lock_contention.bpf.c for consistency with a generated vmlinux.h.
+ */
+struct rq {};
+
 #endif // __VMLINUX_H
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 046fbfcfdaab..bdfead36b83a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1320,7 +1320,9 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 			dso->id = *id;
 		dso__set_long_name_id(dso, dso->name, id, false);
 		dso__set_short_name(dso, dso->name, false);
-		dso->symbols = dso->symbol_names = RB_ROOT_CACHED;
+		dso->symbols = RB_ROOT_CACHED;
+		dso->symbol_names = NULL;
+		dso->symbol_names_len = 0;
 		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT_CACHED;
 		dso->srclines = RB_ROOT_CACHED;
@@ -1364,7 +1366,8 @@ void dso__delete(struct dso *dso)
 	inlines__tree_delete(&dso->inlined_nodes);
 	srcline__tree_delete(&dso->srclines);
 	symbols__delete(&dso->symbols);
-
+	dso->symbol_names_len = 0;
+	zfree(&dso->symbol_names);
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
 		dso->short_name_allocated = false;
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index b23a157c914d..b41c9782c754 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -150,7 +150,8 @@ struct dso {
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
 	struct rb_root_cached symbols;
-	struct rb_root_cached symbol_names;
+	struct symbol	 **symbol_names;
+	size_t		 symbol_names_len;
 	struct rb_root_cached inlined_nodes;
 	struct rb_root_cached srclines;
 	struct {
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 3860b0c74829..4cbb092e0684 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -581,15 +581,14 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 	maps__zput(al->maps);
 	map__zput(al->map);
 	thread__zput(al->thread);
+	al->thread = thread__get(thread);
 
 	al->addr = addr;
 	al->cpumode = cpumode;
 	al->filtered = 0;
 
-	if (machine == NULL) {
-		al->map = NULL;
+	if (machine == NULL)
 		return NULL;
-	}
 
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
 		al->level = 'k';
@@ -605,7 +604,6 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 		al->level = 'u';
 	} else {
 		al->level = 'H';
-		al->map = NULL;
 
 		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
 			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
@@ -619,7 +617,6 @@ struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
 		return NULL;
 	}
 	al->maps = maps__get(maps);
-	al->thread = thread__get(thread);
 	al->map = map__get(maps__find(maps, al->addr));
 	if (al->map != NULL) {
 		/*
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f607b5bddc76..762e2b2634a5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2924,25 +2924,19 @@ static bool find_process(const char *name)
 	return ret ? false : true;
 }
 
-static bool is_amd(const char *arch, const char *cpuid)
+int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused,
+				     char *msg __maybe_unused,
+				     size_t size __maybe_unused)
 {
-	return arch && !strcmp("x86", arch) && cpuid && strstarts(cpuid, "AuthenticAMD");
-}
-
-static bool is_amd_ibs(struct evsel *evsel)
-{
-	return evsel->core.attr.precise_ip
-	    || (evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3));
+	return 0;
 }
 
 int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			 int err, char *msg, size_t size)
 {
-	struct perf_env *env = evsel__env(evsel);
-	const char *arch = perf_env__arch(env);
-	const char *cpuid = perf_env__cpuid(env);
 	char sbuf[STRERR_BUFSIZE];
 	int printed = 0, enforced = 0;
+	int ret;
 
 	switch (err) {
 	case EPERM:
@@ -3044,16 +3038,6 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size,
 	"Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
 					evsel__name(evsel));
-		if (is_amd(arch, cpuid)) {
-			if (is_amd_ibs(evsel)) {
-				if (evsel->core.attr.exclude_kernel)
-					return scnprintf(msg, size,
-	"AMD IBS can't exclude kernel events.  Try running at a higher privilege level.");
-				if (!evsel->core.system_wide)
-					return scnprintf(msg, size,
-	"AMD IBS may only be available in system-wide/per-cpu mode.  Try using -a, or -C and workload affinity");
-			}
-		}
 
 		break;
 	case ENODATA:
@@ -3063,6 +3047,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 		break;
 	}
 
+	ret = arch_evsel__open_strerror(evsel, msg, size);
+	if (ret)
+		return ret;
+
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg | grep -i perf may provide additional information.\n",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9f06d6cd5379..848534ec74fa 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -311,6 +311,7 @@ void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
 
 void arch_evsel__set_sample_weight(struct evsel *evsel);
 void arch__post_evsel_config(struct evsel *evsel, struct perf_event_attr *attr);
+int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size);
 
 int evsel__set_filter(struct evsel *evsel, const char *filter);
 int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index f4e52919324e..4814262e3805 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -8,6 +8,7 @@
 #include "cpumap.h"
 #include "cputopo.h"
 #include "debug.h"
+#include "evlist.h"
 #include "expr.h"
 #include "expr-bison.h"
 #include "expr-flex.h"
@@ -474,3 +475,23 @@ out:
 	pr_debug2("literal: %s = %f\n", literal, result);
 	return result;
 }
+
+/* Does the event 'id' parse? Determine via ctx->ids if possible. */
+double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id)
+{
+	struct evlist *tmp;
+	double ret;
+
+	if (hashmap__find(ctx->ids, id, /*value=*/NULL))
+		return 1.0;
+
+	if (!compute_ids)
+		return 0.0;
+
+	tmp = evlist__new();
+	if (!tmp)
+		return NAN;
+	ret = parse_event(tmp, id) ? 0 : 1;
+	evlist__delete(tmp);
+	return ret;
+}
diff --git a/tools/perf/util/expr.h b/tools/perf/util/expr.h
index eaa44b24c555..3c1e49b3e35d 100644
--- a/tools/perf/util/expr.h
+++ b/tools/perf/util/expr.h
@@ -54,5 +54,6 @@ int expr__find_ids(const char *expr, const char *one,
 double expr_id_data__value(const struct expr_id_data *data);
 double expr_id_data__source_count(const struct expr_id_data *data);
 double expr__get_literal(const char *literal, const struct expr_scanner_ctx *ctx);
+double expr__has_event(const struct expr_parse_ctx *ctx, bool compute_ids, const char *id);
 
 #endif
diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l
index 4fbf353e78e7..dbb117414710 100644
--- a/tools/perf/util/expr.l
+++ b/tools/perf/util/expr.l
@@ -113,6 +113,7 @@ min		{ return MIN; }
 if		{ return IF; }
 else		{ return ELSE; }
 source_count	{ return SOURCE_COUNT; }
+has_event	{ return HAS_EVENT; }
 {literal}	{ return literal(yyscanner, sctx); }
 {number}	{ return value(yyscanner); }
 {symbol}	{ return str(yyscanner, ID, sctx->runtime); }
diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y
index f04963eb6be0..dd504afd8f36 100644
--- a/tools/perf/util/expr.y
+++ b/tools/perf/util/expr.y
@@ -37,7 +37,7 @@
 	} ids;
 }
 
-%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT EXPR_ERROR
+%token ID NUMBER MIN MAX IF ELSE LITERAL D_RATIO SOURCE_COUNT HAS_EVENT EXPR_ERROR
 %left MIN MAX IF
 %left '|'
 %left '^'
@@ -199,6 +199,12 @@ expr: NUMBER
 }
 | ID				{ $$ = handle_id(ctx, $1, compute_ids, /*source_count=*/false); }
 | SOURCE_COUNT '(' ID ')'	{ $$ = handle_id(ctx, $3, compute_ids, /*source_count=*/true); }
+| HAS_EVENT '(' ID ')'
+{
+	$$.val = expr__has_event(ctx, compute_ids, $3);
+	$$.ids = NULL;
+	free($3);
+}
 | expr '|' expr
 {
 	if (is_const($1.val) && is_const($3.val)) {
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 4e8e243a6e4b..c6c9c2228578 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -25,7 +25,7 @@
 		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
-		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
+		"-c \"$CLANG_SOURCE\" --target=bpf $CLANG_EMIT_LLVM -g -O2 -o - $LLVM_OPTIONS_PIPE"
 
 struct llvm_param llvm_param = {
 	.clang_path = "clang",
@@ -569,7 +569,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		pr_err("ERROR:\tunable to compile %s\n", path);
 		pr_err("Hint:\tCheck error message shown above.\n");
 		pr_err("Hint:\tYou can also pre-compile it into .o using:\n");
-		pr_err("     \t\tclang -target bpf -O2 -c %s\n", path);
+		pr_err("     \t\tclang --target=bpf -O2 -c %s\n", path);
 		pr_err("     \twith proper -I and -D options.\n");
 		goto errout;
 	}
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index f30d34903aa4..f64b83004421 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -390,7 +390,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr)
 	return dso__find_symbol(map__dso(map), addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
+struct symbol *map__find_symbol_by_name_idx(struct map *map, const char *name, size_t *idx)
 {
 	struct dso *dso;
 
@@ -398,10 +398,16 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 		return NULL;
 
 	dso = map__dso(map);
-	if (!dso__sorted_by_name(dso))
-		dso__sort_by_name(dso);
+	dso__sort_by_name(dso);
+
+	return dso__find_symbol_by_name(dso, name, idx);
+}
+
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
+{
+	size_t idx;
 
-	return dso__find_symbol_by_name(dso, name);
+	return map__find_symbol_by_name_idx(map, name, &idx);
 }
 
 struct map *map__clone(struct map *from)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 66a87b3d9965..1b53d53adc86 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -148,16 +148,17 @@ struct thread;
  * @map: the 'struct map *' in which symbols are iterated
  * @sym_name: the symbol name
  * @pos: the 'struct symbol *' to use as a loop cursor
+ * @idx: the cursor index in the symbol names array
  */
-#define __map__for_each_symbol_by_name(map, sym_name, pos)	\
-	for (pos = map__find_symbol_by_name(map, sym_name);	\
+#define __map__for_each_symbol_by_name(map, sym_name, pos, idx)		\
+	for (pos = map__find_symbol_by_name_idx(map, sym_name, &idx);	\
 	     pos &&						\
 	     !symbol__match_symbol_name(pos->name, sym_name,	\
 					SYMBOL_TAG_INCLUDE__DEFAULT_ONLY); \
-	     pos = symbol__next_by_name(pos))
+	     pos = dso__next_symbol_by_name(map__dso(map), &idx))
 
-#define map__for_each_symbol_by_name(map, sym_name, pos)		\
-	__map__for_each_symbol_by_name(map, sym_name, (pos))
+#define map__for_each_symbol_by_name(map, sym_name, pos, idx)	\
+	__map__for_each_symbol_by_name(map, sym_name, (pos), idx)
 
 void map__init(struct map *map,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
@@ -202,6 +203,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 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);
+struct symbol *map__find_symbol_by_name_idx(struct map *map, const char *name, size_t *idx);
 void map__fixup_start(struct map *map);
 void map__fixup_end(struct map *map);
 
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 7e5e7b30510d..2247991451f3 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -1,11 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <inttypes.h>
 #include <stdio.h>
+#include <stdlib.h>
 #include <stdbool.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
 #include "util/evsel_fprintf.h"
+#include "trace-event.h"
 
 struct bit_names {
 	int bit;
@@ -71,6 +73,170 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 	__p_bits(buf, size, value, bits);
 }
 
+#define ENUM_ID_TO_STR_CASE(x) case x: return (#x);
+static const char *stringify_perf_type_id(u64 value)
+{
+	switch (value) {
+	ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE)
+	ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE)
+	ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT)
+	ENUM_ID_TO_STR_CASE(PERF_TYPE_HW_CACHE)
+	ENUM_ID_TO_STR_CASE(PERF_TYPE_RAW)
+	ENUM_ID_TO_STR_CASE(PERF_TYPE_BREAKPOINT)
+	default:
+		return NULL;
+	}
+}
+
+static const char *stringify_perf_hw_id(u64 value)
+{
+	switch (value) {
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CPU_CYCLES)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_INSTRUCTIONS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_REFERENCES)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_MISSES)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_BRANCH_INSTRUCTIONS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_BRANCH_MISSES)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_BUS_CYCLES)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_STALLED_CYCLES_FRONTEND)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_STALLED_CYCLES_BACKEND)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_REF_CPU_CYCLES)
+	default:
+		return NULL;
+	}
+}
+
+static const char *stringify_perf_hw_cache_id(u64 value)
+{
+	switch (value) {
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_L1D)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_L1I)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_LL)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_DTLB)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_ITLB)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_BPU)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_NODE)
+	default:
+		return NULL;
+	}
+}
+
+static const char *stringify_perf_hw_cache_op_id(u64 value)
+{
+	switch (value) {
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_OP_READ)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_OP_WRITE)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_OP_PREFETCH)
+	default:
+		return NULL;
+	}
+}
+
+static const char *stringify_perf_hw_cache_op_result_id(u64 value)
+{
+	switch (value) {
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_RESULT_ACCESS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_HW_CACHE_RESULT_MISS)
+	default:
+		return NULL;
+	}
+}
+
+static const char *stringify_perf_sw_id(u64 value)
+{
+	switch (value) {
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CPU_CLOCK)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_TASK_CLOCK)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_PAGE_FAULTS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CONTEXT_SWITCHES)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CPU_MIGRATIONS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_PAGE_FAULTS_MIN)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_PAGE_FAULTS_MAJ)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_ALIGNMENT_FAULTS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_EMULATION_FAULTS)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_DUMMY)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_BPF_OUTPUT)
+	ENUM_ID_TO_STR_CASE(PERF_COUNT_SW_CGROUP_SWITCHES)
+	default:
+		return NULL;
+	}
+}
+#undef ENUM_ID_TO_STR_CASE
+
+#define PRINT_ID(_s, _f)					\
+do {								\
+	const char *__s = _s;					\
+	if (__s == NULL)					\
+		snprintf(buf, size, _f, value);			\
+	else							\
+		snprintf(buf, size, _f" (%s)", value, __s);	\
+} while (0)
+#define print_id_unsigned(_s)	PRINT_ID(_s, "%"PRIu64)
+#define print_id_hex(_s)	PRINT_ID(_s, "%#"PRIx64)
+
+static void __p_type_id(char *buf, size_t size, u64 value)
+{
+	print_id_unsigned(stringify_perf_type_id(value));
+}
+
+static void __p_config_hw_id(char *buf, size_t size, u64 value)
+{
+	print_id_hex(stringify_perf_hw_id(value));
+}
+
+static void __p_config_sw_id(char *buf, size_t size, u64 value)
+{
+	print_id_hex(stringify_perf_sw_id(value));
+}
+
+static void __p_config_hw_cache_id(char *buf, size_t size, u64 value)
+{
+	const char *hw_cache_str = stringify_perf_hw_cache_id(value & 0xff);
+	const char *hw_cache_op_str =
+		stringify_perf_hw_cache_op_id((value & 0xff00) >> 8);
+	const char *hw_cache_op_result_str =
+		stringify_perf_hw_cache_op_result_id((value & 0xff0000) >> 16);
+
+	if (hw_cache_str == NULL || hw_cache_op_str == NULL ||
+	    hw_cache_op_result_str == NULL) {
+		snprintf(buf, size, "%#"PRIx64, value);
+	} else {
+		snprintf(buf, size, "%#"PRIx64" (%s | %s | %s)", value,
+			 hw_cache_op_result_str, hw_cache_op_str, hw_cache_str);
+	}
+}
+
+#ifdef HAVE_LIBTRACEEVENT
+static void __p_config_tracepoint_id(char *buf, size_t size, u64 value)
+{
+	char *str = tracepoint_id_to_name(value);
+
+	print_id_hex(str);
+	free(str);
+}
+#endif
+
+static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
+{
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+		return __p_config_hw_id(buf, size, value);
+	case PERF_TYPE_SOFTWARE:
+		return __p_config_sw_id(buf, size, value);
+	case PERF_TYPE_HW_CACHE:
+		return __p_config_hw_cache_id(buf, size, value);
+	case PERF_TYPE_TRACEPOINT:
+#ifdef HAVE_LIBTRACEEVENT
+		return __p_config_tracepoint_id(buf, size, value);
+#endif
+	case PERF_TYPE_RAW:
+	case PERF_TYPE_BREAKPOINT:
+	default:
+		snprintf(buf, size, "%#"PRIx64, value);
+		return;
+	}
+}
+
 #define BUF_SIZE		1024
 
 #define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
@@ -79,16 +245,18 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
 #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
 #define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
+#define p_type_id(val)		__p_type_id(buf, BUF_SIZE, val)
+#define p_config_id(val)	__p_config_id(buf, BUF_SIZE, attr->type, val)
 
-#define PRINT_ATTRn(_n, _f, _p)				\
+#define PRINT_ATTRn(_n, _f, _p, _a)			\
 do {							\
-	if (attr->_f) {					\
+	if (_a || attr->_f) {				\
 		_p(attr->_f);				\
 		ret += attr__fprintf(fp, _n, buf, priv);\
 	}						\
 } while (0)
 
-#define PRINT_ATTRf(_f, _p)	PRINT_ATTRn(#_f, _f, _p)
+#define PRINT_ATTRf(_f, _p)	PRINT_ATTRn(#_f, _f, _p, false)
 
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv)
@@ -96,10 +264,10 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	char buf[BUF_SIZE];
 	int ret = 0;
 
-	PRINT_ATTRf(type, p_unsigned);
+	PRINT_ATTRn("type", type, p_type_id, true);
 	PRINT_ATTRf(size, p_unsigned);
-	PRINT_ATTRf(config, p_hex);
-	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
+	PRINT_ATTRn("config", config, p_config_id, true);
+	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned, false);
 	PRINT_ATTRf(sample_type, p_sample_type);
 	PRINT_ATTRf(read_format, p_read_format);
 
@@ -141,10 +309,10 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(remove_on_exec, p_unsigned);
 	PRINT_ATTRf(sigtrap, p_unsigned);
 
-	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
+	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned, false);
 	PRINT_ATTRf(bp_type, p_unsigned);
-	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
-	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
+	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex, false);
+	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex, false);
 	PRINT_ATTRf(branch_sample_type, p_branch_sample_type);
 	PRINT_ATTRf(sample_regs_user, p_hex);
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 64fa568a5426..7f984a7f16ca 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -928,6 +928,31 @@ err:
 	return NULL;
 }
 
+/* Creates the PMU when sysfs scanning fails. */
+struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus)
+{
+	struct perf_pmu *pmu = zalloc(sizeof(*pmu));
+
+	if (!pmu)
+		return NULL;
+
+	pmu->name = strdup("cpu");
+	if (!pmu->name) {
+		free(pmu);
+		return NULL;
+	}
+
+	pmu->is_core = true;
+	pmu->type = PERF_TYPE_RAW;
+	pmu->cpus = cpu_map__online();
+
+	INIT_LIST_HEAD(&pmu->format);
+	INIT_LIST_HEAD(&pmu->aliases);
+	INIT_LIST_HEAD(&pmu->caps);
+	list_add_tail(&pmu->list, core_pmus);
+	return pmu;
+}
+
 void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
 {
 	struct perf_pmu_format *format;
@@ -1427,7 +1452,7 @@ bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu)
 
 bool perf_pmu__auto_merge_stats(const struct perf_pmu *pmu)
 {
-	return pmu->is_core && perf_pmus__num_core_pmus() == 1;
+	return !pmu->is_core || perf_pmus__num_core_pmus() == 1;
 }
 
 bool perf_pmu__have_event(const struct perf_pmu *pmu, const char *name)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8807a624e918..203b92860e3c 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -286,6 +286,7 @@ int perf_pmu__event_source_devices_fd(void);
 int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
 
 struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
+struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 0866dee3fc62..3cd9de42139e 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -153,7 +153,12 @@ static void pmu_read_sysfs(bool core_only)
 
 	closedir(dir);
 	if (core_only) {
-		read_sysfs_core_pmus = true;
+		if (!list_empty(&core_pmus))
+			read_sysfs_core_pmus = true;
+		else {
+			if (perf_pmu__create_placeholder_core_pmu(&core_pmus))
+				read_sysfs_core_pmus = true;
+		}
 	} else {
 		read_sysfs_core_pmus = true;
 		read_sysfs_all_pmus = true;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6e2110d605fb..16822a8a540f 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -74,7 +74,6 @@ int init_probe_symbol_maps(bool user_only)
 {
 	int ret;
 
-	symbol_conf.sort_by_name = true;
 	symbol_conf.allow_aliases = true;
 	ret = symbol__init(NULL);
 	if (ret < 0) {
@@ -382,6 +381,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
 	struct symbol *sym;
 	u64 address = 0;
 	int ret = -ENOENT;
+	size_t idx;
 
 	/* This can work only for function-name based one */
 	if (!pp->function || pp->file)
@@ -392,7 +392,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
 		return -EINVAL;
 
 	/* Find the address of given function */
-	map__for_each_symbol_by_name(map, pp->function, sym) {
+	map__for_each_symbol_by_name(map, pp->function, sym, idx) {
 		if (uprobes) {
 			address = sym->start;
 			if (sym->type == STT_GNU_IFUNC)
@@ -3738,7 +3738,6 @@ out:
 int show_available_funcs(const char *target, struct nsinfo *nsi,
 			 struct strfilter *_filter, bool user)
 {
-        struct rb_node *nd;
 	struct map *map;
 	struct dso *dso;
 	int ret;
@@ -3767,17 +3766,16 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
 		goto end;
 	}
 	dso = map__dso(map);
-	if (!dso__sorted_by_name(dso))
-		dso__sort_by_name(dso);
+	dso__sort_by_name(dso);
 
 	/* Show all (filtered) symbols */
 	setup_pager();
 
-	for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) {
-		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
+	for (size_t i = 0; i < dso->symbol_names_len; i++) {
+		struct symbol *pos = dso->symbol_names[i];
 
-		if (strfilter__compare(_filter, pos->sym.name))
-			printf("%s\n", pos->sym.name);
+		if (strfilter__compare(_filter, pos->name))
+			printf("%s\n", pos->name);
 	}
 end:
 	map__put(map);
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a7b2cb05dc86..4eed8ec23994 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -124,6 +124,14 @@ int metricgroup__copy_metric_events(struct evlist *evlist, struct cgroup *cgrp,
 }
 
 /*
+ * Add this one here not to drag util/trace-event-info.c
+ */
+char *tracepoint_id_to_name(u64 config)
+{
+	return NULL;
+}
+
+/*
  * XXX: All these evsel destructors need some better mechanism, like a linked
  * list of destructors registered when the relevant code indeed is used instead
  * of having more and more calls in perf_evsel__delete(). -- acme
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index d275d3bef7d5..f849f9ef68e6 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -440,38 +440,35 @@ static struct symbol *symbols__next(struct symbol *sym)
 	return NULL;
 }
 
-static void symbols__insert_by_name(struct rb_root_cached *symbols, struct symbol *sym)
+static int symbols__sort_name_cmp(const void *vlhs, const void *vrhs)
 {
-	struct rb_node **p = &symbols->rb_root.rb_node;
-	struct rb_node *parent = NULL;
-	struct symbol_name_rb_node *symn, *s;
-	bool leftmost = true;
+	const struct symbol *lhs = *((const struct symbol **)vlhs);
+	const struct symbol *rhs = *((const struct symbol **)vrhs);
 
-	symn = container_of(sym, struct symbol_name_rb_node, sym);
-
-	while (*p != NULL) {
-		parent = *p;
-		s = rb_entry(parent, struct symbol_name_rb_node, rb_node);
-		if (strcmp(sym->name, s->sym.name) < 0)
-			p = &(*p)->rb_left;
-		else {
-			p = &(*p)->rb_right;
-			leftmost = false;
-		}
-	}
-	rb_link_node(&symn->rb_node, parent, p);
-	rb_insert_color_cached(&symn->rb_node, symbols, leftmost);
+	return strcmp(lhs->name, rhs->name);
 }
 
-static void symbols__sort_by_name(struct rb_root_cached *symbols,
-				  struct rb_root_cached *source)
+static struct symbol **symbols__sort_by_name(struct rb_root_cached *source, size_t *len)
 {
 	struct rb_node *nd;
+	struct symbol **result;
+	size_t i = 0, size = 0;
+
+	for (nd = rb_first_cached(source); nd; nd = rb_next(nd))
+		size++;
+
+	result = malloc(sizeof(*result) * size);
+	if (!result)
+		return NULL;
 
 	for (nd = rb_first_cached(source); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
-		symbols__insert_by_name(symbols, pos);
+
+		result[i++] = pos;
 	}
+	qsort(result, size, sizeof(*result), symbols__sort_name_cmp);
+	*len = size;
+	return result;
 }
 
 int symbol__match_symbol_name(const char *name, const char *str,
@@ -491,48 +488,53 @@ int symbol__match_symbol_name(const char *name, const char *str,
 		return arch__compare_symbol_names(name, str);
 }
 
-static struct symbol *symbols__find_by_name(struct rb_root_cached *symbols,
+static struct symbol *symbols__find_by_name(struct symbol *symbols[],
+					    size_t symbols_len,
 					    const char *name,
-					    enum symbol_tag_include includes)
+					    enum symbol_tag_include includes,
+					    size_t *found_idx)
 {
-	struct rb_node *n;
-	struct symbol_name_rb_node *s = NULL;
+	size_t i, lower = 0, upper = symbols_len;
+	struct symbol *s = NULL;
 
-	if (symbols == NULL)
-		return NULL;
+	if (found_idx)
+		*found_idx = SIZE_MAX;
 
-	n = symbols->rb_root.rb_node;
+	if (!symbols_len)
+		return NULL;
 
-	while (n) {
+	while (lower < upper) {
 		int cmp;
 
-		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		cmp = symbol__match_symbol_name(s->sym.name, name, includes);
+		i = (lower + upper) / 2;
+		cmp = symbol__match_symbol_name(symbols[i]->name, name, includes);
 
 		if (cmp > 0)
-			n = n->rb_left;
+			upper = i;
 		else if (cmp < 0)
-			n = n->rb_right;
-		else
+			lower = i + 1;
+		else {
+			if (found_idx)
+				*found_idx = i;
+			s = symbols[i];
 			break;
+		}
 	}
-
-	if (n == NULL)
-		return NULL;
-
-	if (includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY)
+	if (s && includes != SYMBOL_TAG_INCLUDE__DEFAULT_ONLY) {
 		/* return first symbol that has same name (if any) */
-		for (n = rb_prev(n); n; n = rb_prev(n)) {
-			struct symbol_name_rb_node *tmp;
-
-			tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
-			if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
+		for (; i > 0; i--) {
+			struct symbol *tmp = symbols[i - 1];
+
+			if (!arch__compare_symbol_names(tmp->name, s->name)) {
+				if (found_idx)
+					*found_idx = i - 1;
+				s = tmp;
+			} else
 				break;
-
-			s = tmp;
 		}
-
-	return &s->sym;
+	}
+	assert(!found_idx || !s || s == symbols[*found_idx]);
+	return s;
 }
 
 void dso__reset_find_symbol_cache(struct dso *dso)
@@ -590,31 +592,41 @@ struct symbol *dso__next_symbol(struct symbol *sym)
 	return symbols__next(sym);
 }
 
-struct symbol *symbol__next_by_name(struct symbol *sym)
+struct symbol *dso__next_symbol_by_name(struct dso *dso, size_t *idx)
 {
-	struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
-	struct rb_node *n = rb_next(&s->rb_node);
+	if (*idx + 1 >= dso->symbol_names_len)
+		return NULL;
 
-	return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
+	++*idx;
+	return dso->symbol_names[*idx];
 }
 
  /*
   * Returns first symbol that matched with @name.
   */
-struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name)
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name, size_t *idx)
 {
-	struct symbol *s = symbols__find_by_name(&dso->symbol_names, name,
-						 SYMBOL_TAG_INCLUDE__NONE);
+	struct symbol *s = symbols__find_by_name(dso->symbol_names, dso->symbol_names_len,
+						name, SYMBOL_TAG_INCLUDE__NONE, idx);
 	if (!s)
-		s = symbols__find_by_name(&dso->symbol_names, name,
-					  SYMBOL_TAG_INCLUDE__DEFAULT_ONLY);
+		s = symbols__find_by_name(dso->symbol_names, dso->symbol_names_len,
+					name, SYMBOL_TAG_INCLUDE__DEFAULT_ONLY, idx);
 	return s;
 }
 
 void dso__sort_by_name(struct dso *dso)
 {
-	dso__set_sorted_by_name(dso);
-	return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
+	mutex_lock(&dso->lock);
+	if (!dso__sorted_by_name(dso)) {
+		size_t len;
+
+		dso->symbol_names = symbols__sort_by_name(&dso->symbols, &len);
+		if (dso->symbol_names) {
+			dso->symbol_names_len = len;
+			dso__set_sorted_by_name(dso);
+		}
+	}
+	mutex_unlock(&dso->lock);
 }
 
 /*
@@ -2656,10 +2668,6 @@ int symbol__init(struct perf_env *env)
 
 	symbol__elf_init();
 
-	if (symbol_conf.sort_by_name)
-		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
-					  sizeof(struct symbol));
-
 	if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
 		return -1;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 5ca8665dd2c1..af87c46b3f89 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -43,8 +43,7 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 
 /**
  * A symtab entry. When allocated this may be preceded by an annotation (see
- * symbol__annotation), a browser_index (see symbol__browser_index) and rb_node
- * to sort by name (see struct symbol_name_rb_node).
+ * symbol__annotation) and/or a browser_index (see symbol__browser_index).
  */
 struct symbol {
 	struct rb_node	rb_node;
@@ -95,11 +94,6 @@ static inline size_t symbol__size(const struct symbol *sym)
 struct strlist;
 struct intlist;
 
-struct symbol_name_rb_node {
-	struct rb_node	rb_node;
-	struct symbol	sym;
-};
-
 static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
 {
 	return path__join(bf, size, symbol_conf.symfs, path);
@@ -136,9 +130,9 @@ void dso__delete_symbol(struct dso *dso,
 
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
 struct symbol *dso__find_symbol_nocache(struct dso *dso, u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
 
-struct symbol *symbol__next_by_name(struct symbol *sym);
+struct symbol *dso__next_symbol_by_name(struct dso *dso, size_t *idx);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name, size_t *idx);
 
 struct symbol *dso__first_symbol(struct dso *dso);
 struct symbol *dso__last_symbol(struct dso *dso);
diff --git a/tools/perf/util/symbol_conf.h b/tools/perf/util/symbol_conf.h
index f26f81eb8252..0b589570d1d0 100644
--- a/tools/perf/util/symbol_conf.h
+++ b/tools/perf/util/symbol_conf.h
@@ -18,7 +18,6 @@ struct symbol_conf {
 			show_kernel_path,
 			use_modules,
 			allow_aliases,
-			sort_by_name,
 			show_nr_samples,
 			show_total_period,
 			use_callchain,
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index d9e5ad040b6a..088f4abf230f 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -63,13 +63,11 @@ size_t dso__fprintf_symbols_by_name(struct dso *dso,
 				    FILE *fp)
 {
 	size_t ret = 0;
-	struct rb_node *nd;
-	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first_cached(&dso->symbol_names); nd; nd = rb_next(nd)) {
-		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
-		ret += fprintf(fp, "%s\n", pos->sym.name);
-	}
+	for (size_t i = 0; i < dso->symbol_names_len; i++) {
+		struct symbol *pos = dso->symbol_names[i];
 
+		ret += fprintf(fp, "%s\n", pos->name);
+	}
 	return ret;
 }
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index c24b3a15e319..319ccf09a435 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -466,6 +466,18 @@ next:
 	return NULL;
 }
 
+char *tracepoint_id_to_name(u64 config)
+{
+	struct tracepoint_path *path = tracepoint_id_to_path(config);
+	char *buf = NULL;
+
+	if (path && asprintf(&buf, "%s:%s", path->system, path->name) < 0)
+		buf = NULL;
+
+	put_tracepoints_path(path);
+	return buf;
+}
+
 static struct tracepoint_path *tracepoint_name_to_path(const char *name)
 {
 	struct tracepoint_path *path = zalloc(sizeof(*path));
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index a0cff184b1cd..a69ee29419f3 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -62,6 +62,12 @@ unsigned long long eval_flag(const char *flag);
 
 int read_tracing_data(int fd, struct list_head *pattrs);
 
+/*
+ * Return the tracepoint name in the format "subsystem:event_name",
+ * callers should free the returned string.
+ */
+char *tracepoint_id_to_name(u64 config);
+
 struct tracing_data {
 	/* size is only valid if temp is 'true' */
 	ssize_t size;
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 83eea968482e..2a96df4c8d42 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -66,9 +66,13 @@ static int __report_module(struct addr_location *al, u64 ip,
 			mod = 0;
 	}
 
-	if (!mod)
-		mod = dwfl_report_elf(ui->dwfl, dso->short_name, dso->long_name, -1,
+	if (!mod) {
+		char filename[PATH_MAX];
+
+		__symbol__join_symfs(filename, sizeof(filename), dso->long_name);
+		mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
 				      map__start(al->map) - map__pgoff(al->map), false);
+	}
 	if (!mod) {
 		char filename[PATH_MAX];