Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull perf fixes from Thomas Gleixner:
 "A bunch of perf tooling fixes:

   - Make the Intel PT SQL viewer more robust

   - Make the Intel PT debug log more useful

   - Support weak groups in perf record so it's behaving the same way as
     perf stat

   - Display the LBR stats in callchain entries properly in perf top

   - Handle different PMu names with common prefix properlin in pert
     stat

   - Start syscall augmenting in perf trace. Preparation for
     architecture independent eBPF instrumentation of syscalls.

   - Fix build breakage in JVMTI perf lib

   - Fix arm64 tools build failure wrt smp_load_{acquire,release}"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf tools: Do not zero sample_id_all for group members
  perf tools: Fix undefined symbol scnprintf in libperf-jvmti.so
  perf beauty: Use SRCARCH, ARCH=x86_64 must map to "x86" to find the headers
  perf intel-pt: Add MTC and CYC timestamps to debug log
  perf intel-pt: Add more event information to debug log
  perf scripts python: exported-sql-viewer.py: Fix table find when table re-ordered
  perf scripts python: exported-sql-viewer.py: Add help window
  perf scripts python: exported-sql-viewer.py: Add Selected branches report
  perf scripts python: exported-sql-viewer.py: Fall back to /usr/local/lib/libxed.so
  perf top: Display the LBR stats in callchain entry
  perf stat: Handle different PMU names with common prefix
  perf record: Support weak groups
  perf evlist: Move perf_evsel__reset_weak_group into evlist
  perf augmented_syscalls: Start collecting pathnames in the BPF program
  perf trace: Fix setting of augmented payload when using eBPF + raw_syscalls
  perf trace: When augmenting raw_syscalls plug raw_syscalls:sys_exit too
  perf examples bpf: Start augmenting raw_syscalls:sys_{start,exit}
  tools headers barrier: Fix arm64 tools build failure wrt smp_load_{acquire,release}

tools/arch/arm64/include/asm/barrier.h

@@ -14,74 +14,75 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
-#define smp_store_release(p, v)					\
-do {								\
-	union { typeof(*p) __val; char __c[1]; } __u =		\
-		{ .__val = (__force typeof(*p)) (v) }; 		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("stlrb %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u8 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("stlrh %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u16 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("stlr %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u32 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("stlr %1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u64 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
+#define smp_store_release(p, v)						\
+do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (v) }; 					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u8_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u16_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u32_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u64_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
 } while (0)
 
-#define smp_load_acquire(p)					\
-({								\
-	union { typeof(*p) __val; char __c[1]; } __u;		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("ldarb %w0, %1"			\
-			: "=r" (*(__u8 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("ldarh %w0, %1"			\
-			: "=r" (*(__u16 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("ldar %w0, %1"			\
-			: "=r" (*(__u32 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("ldar %0, %1"			\
-			: "=r" (*(__u64 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
-	__u.__val;						\
+#define smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__c = { 0 } };					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (*(__u8_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (*(__u16_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (*(__u32_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (*(__u64_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
+	__u.__val;							\
 })
 
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */

tools/perf/Documentation/perf-list.txt

@@ -55,7 +55,6 @@ counted. The following modifiers exist:
  S - read sample value (PERF_SAMPLE_READ)
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
-     only supported in 'perf stat' for now.
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:

tools/perf/Makefile.perf

@@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
-arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl

tools/perf/builtin-record.c

@@ -391,7 +391,12 @@ static int record__open(struct record *rec)
 					ui__warning("%s\n", msg);
 				goto try_again;
 			}
-
+			if ((errno == EINVAL || errno == EBADF) &&
+			    pos->leader != pos &&
+			    pos->weak_group) {
+			        pos = perf_evlist__reset_weak_group(evlist, pos);
+				goto try_again;
+			}
 			rc = -errno;
 			perf_evsel__open_strerror(pos, &opts->target,
 						  errno, msg, sizeof(msg));

tools/perf/builtin-stat.c

@@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)
 	return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID;
 }
 
-static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
-{
-	struct perf_evsel *c2, *leader;
-	bool is_open = true;
-
-	leader = evsel->leader;
-	pr_debug("Weak group for %s/%d failed\n",
-			leader->name, leader->nr_members);
-
-	/*
-	 * for_each_group_member doesn't work here because it doesn't
-	 * include the first entry.
-	 */
-	evlist__for_each_entry(evsel_list, c2) {
-		if (c2 == evsel)
-			is_open = false;
-		if (c2->leader == leader) {
-			if (is_open)
-				perf_evsel__close(c2);
-			c2->leader = c2;
-			c2->nr_members = 0;
-		}
-	}
-	return leader;
-}
-
 static bool is_target_alive(struct target *_target,
 			    struct thread_map *threads)
 {
@@ -477,7 +451,7 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			if ((errno == EINVAL || errno == EBADF) &&
 			    counter->leader != counter &&
 			    counter->weak_group) {
-				counter = perf_evsel__reset_weak_group(counter);
+				counter = perf_evlist__reset_weak_group(evsel_list, counter);
 				goto try_again;
 			}
 

tools/perf/builtin-top.c

@@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv)
 		}
 	}
 
+	if (opts->branch_stack && callchain_param.enabled)
+		symbol_conf.show_branchflag_count = true;
+
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
 	perf_hpp_list.need_collapse = 1;

tools/perf/builtin-trace.c

@@ -108,6 +108,7 @@ struct trace {
 	} stats;
 	unsigned int		max_stack;
 	unsigned int		min_stack;
+	bool			raw_augmented_syscalls;
 	bool			not_ev_qualifier;
 	bool			live;
 	bool			full_time;
@@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
 	return printed;
 }
 
-static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size)
+static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented)
 {
 	void *augmented_args = NULL;
+	/*
+	 * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
+	 * and there we get all 6 syscall args plus the tracepoint common
+	 * fields (sizeof(long)) and the syscall_nr (another long). So we check
+	 * if that is the case and if so don't look after the sc->args_size,
+	 * but always after the full raw_syscalls:sys_enter payload, which is
+	 * fixed.
+	 *
+	 * We'll revisit this later to pass s->args_size to the BPF augmenter
+	 * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
+	 * copies only what we need for each syscall, like what happens when we
+	 * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
+	 * traffic to just what is needed for each syscall.
+	 */
+	int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size;
 
-	*augmented_args_size = sample->raw_size - sc->args_size;
+	*augmented_args_size = sample->raw_size - args_size;
 	if (*augmented_args_size > 0)
-		augmented_args = sample->raw_data + sc->args_size;
+		augmented_args = sample->raw_data + args_size;
 
 	return augmented_args;
 }
@@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	 * here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
 	 */
 	if (evsel != trace->syscalls.events.sys_enter)
-		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+		augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	ttrace->entry_time = sample->time;
 	msg = ttrace->entry_str;
 	printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
@@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse
 		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size);
+	augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls);
 	syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
 	fprintf(trace->output, "%s", msg);
 	err = 0;
@@ -3501,7 +3517,15 @@ int cmd_trace(int argc, const char **argv)
 		evsel->handler = trace__sys_enter;
 
 		evlist__for_each_entry(trace.evlist, evsel) {
+			bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+
+			if (raw_syscalls_sys_exit) {
+				trace.raw_augmented_syscalls = true;
+				goto init_augmented_syscall_tp;
+			}
+
 			if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
+init_augmented_syscall_tp:
 				perf_evsel__init_augmented_syscall_tp(evsel);
 				perf_evsel__init_augmented_syscall_tp_ret(evsel);
 				evsel->handler = trace__sys_exit;