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

@@ -17,31 +17,31 @@
 #define smp_store_release(p, v)						\
 do {									\
 	union { typeof(*p) __val; char __c[1]; } __u =			\
-		{ .__val = (__force typeof(*p)) (v) }; 		\
+		{ .__val = (v) }; 					\
 									\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
 				: "=Q" (*p)				\
-				: "r" (*(__u8 *)__u.__c)	\
+				: "r" (*(__u8_alias_t *)__u.__c)	\
 				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
 				: "=Q" (*p)				\
-				: "r" (*(__u16 *)__u.__c)	\
+				: "r" (*(__u16_alias_t *)__u.__c)	\
 				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
 				: "=Q" (*p)				\
-				: "r" (*(__u32 *)__u.__c)	\
+				: "r" (*(__u32_alias_t *)__u.__c)	\
 				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
 				: "=Q" (*p)				\
-				: "r" (*(__u64 *)__u.__c)	\
+				: "r" (*(__u64_alias_t *)__u.__c)	\
 				: "memory");				\
 		break;							\
 	default:							\
@@ -53,27 +53,28 @@ do {								\
 
 #define smp_load_acquire(p)						\
 ({									\
-	union { typeof(*p) __val; char __c[1]; } __u;		\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__c = { 0 } };					\
 									\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
-			: "=r" (*(__u8 *)__u.__c)		\
+			: "=r" (*(__u8_alias_t *)__u.__c)		\
 			: "Q" (*p) : "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
-			: "=r" (*(__u16 *)__u.__c)		\
+			: "=r" (*(__u16_alias_t *)__u.__c)		\
 			: "Q" (*p) : "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
-			: "=r" (*(__u32 *)__u.__c)		\
+			: "=r" (*(__u32_alias_t *)__u.__c)		\
 			: "Q" (*p) : "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
-			: "=r" (*(__u64 *)__u.__c)		\
+			: "=r" (*(__u64_alias_t *)__u.__c)		\
 			: "Q" (*p) : "memory");				\
 		break;							\
 	default:							\

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;

tools/perf/examples/bpf/augmented_raw_syscalls.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Augment the raw_syscalls tracepoints with the contents of the pointer arguments.
+ *
+ * Test it with:
+ *
+ * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null
+ *
+ * This exactly matches what is marshalled into the raw_syscall:sys_enter
+ * payload expected by the 'perf trace' beautifiers.
+ *
+ * For now it just uses the existing tracepoint augmentation code in 'perf
+ * trace', in the next csets we'll hook up these with the sys_enter/sys_exit
+ * code that will combine entry/exit in a strace like way.
+ */
+
+#include <stdio.h>
+#include <linux/socket.h>
+
+/* bpf-output associated map */
+struct bpf_map SEC("maps") __augmented_syscalls__ = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = __NR_CPUS__,
+};
+
+struct syscall_enter_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	unsigned long	   args[6];
+};
+
+struct syscall_exit_args {
+	unsigned long long common_tp_fields;
+	long		   syscall_nr;
+	long		   ret;
+};
+
+struct augmented_filename {
+	unsigned int	size;
+	int		reserved;
+	char		value[256];
+};
+
+#define SYS_OPEN 2
+#define SYS_OPENAT 257
+
+SEC("raw_syscalls:sys_enter")
+int sys_enter(struct syscall_enter_args *args)
+{
+	struct {
+		struct syscall_enter_args args;
+		struct augmented_filename filename;
+	} augmented_args;
+	unsigned int len = sizeof(augmented_args);
+	const void *filename_arg = NULL;
+
+	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	/*
+	 * Yonghong and Edward Cree sayz:
+	 *
+	 * https://www.spinics.net/lists/netdev/msg531645.html
+	 *
+	 * >>   R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1
+	 * >> 10: (bf) r1 = r6
+	 * >> 11: (07) r1 += 16
+	 * >> 12: (05) goto pc+2
+	 * >> 15: (79) r3 = *(u64 *)(r1 +0)
+	 * >> dereference of modified ctx ptr R1 off=16 disallowed
+	 * > Aha, we at least got a different error message this time.
+	 * > And indeed llvm has done that optimisation, rather than the more obvious
+	 * > 11: r3 = *(u64 *)(r1 +16)
+	 * > because it wants to have lots of reads share a single insn.  You may be able
+	 * > to defeat that optimisation by adding compiler barriers, idk.  Maybe someone
+	 * > with llvm knowledge can figure out how to stop it (ideally, llvm would know
+	 * > when it's generating for bpf backend and not do that).  -O0?  ¯\_(ツ)_/¯
+	 *
+	 * The optimization mostly likes below:
+	 *
+	 *	br1:
+	 * 	...
+	 *	r1 += 16
+	 *	goto merge
+	 *	br2:
+	 *	...
+	 *	r1 += 20
+	 *	goto merge
+	 *	merge:
+	 *	*(u64 *)(r1 + 0)
+	 *
+	 * The compiler tries to merge common loads. There is no easy way to
+	 * stop this compiler optimization without turning off a lot of other
+	 * optimizations. The easiest way is to add barriers:
+	 *
+	 * 	 __asm__ __volatile__("": : :"memory")
+	 *
+	 * 	 after the ctx memory access to prevent their down stream merging.
+	 */
+	switch (augmented_args.args.syscall_nr) {
+	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
+			__asm__ __volatile__("": : :"memory");
+			 break;
+	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
+			 break;
+	}
+
+	if (filename_arg != NULL) {
+		augmented_args.filename.reserved = 0;
+		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
+							      sizeof(augmented_args.filename.value),
+							      filename_arg);
+		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
+			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
+			len &= sizeof(augmented_args.filename.value) - 1;
+		}
+	} else {
+		len = sizeof(augmented_args.args);
+	}
+
+	perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+	return 0;
+}
+
+SEC("raw_syscalls:sys_exit")
+int sys_exit(struct syscall_exit_args *args)
+{
+	return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */
+}
+
+license(GPL);

tools/perf/jvmti/jvmti_agent.c

@@ -125,7 +125,7 @@ perf_get_timestamp(void)
 }
 
 static int
-debug_cache_init(void)
+create_jit_cache_dir(void)
 {
 	char str[32];
 	char *base, *p;
@@ -144,8 +144,13 @@ debug_cache_init(void)
 
 	strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because %s/.debug/"
+			" is too long, please check the cwd, JITDUMPDIR, and"
+			" HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
@@ -154,20 +159,32 @@ debug_cache_init(void)
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", base);
+		return -1;
+	}
 	ret = mkdir(jit_path, 0755);
 	if (ret == -1) {
 		if (errno != EEXIST) {
-			warn("cannot create jit cache dir %s", jit_path);
+			warn("jvmti: cannot create jit cache dir %s", jit_path);
 			return -1;
 		}
 	}
 
-	snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
-
+	ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jit cache dir because"
+			" %s/.debug/jit/%s.XXXXXXXX is too long, please check"
+			" the cwd, JITDUMPDIR, and HOME variables",
+			base, str);
+		return -1;
+	}
 	p = mkdtemp(jit_path);
 	if (p != jit_path) {
-		warn("cannot create jit cache dir %s", jit_path);
+		warn("jvmti: cannot create jit cache dir %s", jit_path);
 		return -1;
 	}
 
@@ -228,7 +245,7 @@ void *jvmti_open(void)
 {
 	char dump_path[PATH_MAX];
 	struct jitheader header;
-	int fd;
+	int fd, ret;
 	FILE *fp;
 
 	init_arch_timestamp();
@@ -245,12 +262,22 @@ void *jvmti_open(void)
 
 	memset(&header, 0, sizeof(header));
 
-	debug_cache_init();
+	/*
+	 * jitdump file dir
+	 */
+	if (create_jit_cache_dir() < 0)
+		return NULL;
 
 	/*
 	 * jitdump file name
 	 */
-	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	if (ret >= PATH_MAX) {
+		warnx("jvmti: cannot generate jitdump file full path because"
+			" %s/jit-%i.dump is too long, please check the cwd,"
+			" JITDUMPDIR, and HOME variables", jit_path, getpid());
+		return NULL;
+	}
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)

tools/perf/tests/attr/test-record-group-sampling

@@ -37,4 +37,3 @@ sample_freq=0
 sample_period=0
 freq=0
 write_backward=0
-sample_id_all=0

tools/perf/util/evlist.c

@@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist)
 		leader->forced_leader = true;
 	}
 }
+
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list,
+						 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;
+}

tools/perf/util/evlist.h

@@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
 
 void perf_evlist__force_leader(struct perf_evlist *evlist);
 
+struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist,
+						 struct perf_evsel *evsel);
+
 #endif /* __PERF_EVLIST_H */

tools/perf/util/evsel.c

@@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		attr->sample_freq    = 0;
 		attr->sample_period  = 0;
 		attr->write_backward = 0;
-		attr->sample_id_all  = 0;
 	}
 
 	if (opts->no_samples)

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

@@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->have_calc_cyc_to_tsc = false;
 		intel_pt_calc_cyc_to_tsc(decoder, true);
 	}
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
@@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
 		decoder->timestamp = timestamp;
 
 	decoder->timestamp_insn_cnt = 0;
+
+	intel_pt_log_to("Setting timestamp", decoder->timestamp);
 }
 
 /* Walk PSB+ packets when already in sync. */

tools/perf/util/intel-pt-decoder/intel-pt-log.c

@@ -31,6 +31,11 @@ static FILE *f;
 static char log_name[MAX_LOG_NAME];
 bool intel_pt_enable_logging;
 
+void *intel_pt_log_fp(void)
+{
+	return f;
+}
+
 void intel_pt_log_enable(void)
 {
 	intel_pt_enable_logging = true;

tools/perf/util/intel-pt-decoder/intel-pt-log.h

@@ -22,6 +22,7 @@
 
 struct intel_pt_pkt;
 
+void *intel_pt_log_fp(void);
 void intel_pt_log_enable(void);
 void intel_pt_log_disable(void);
 void intel_pt_log_set_name(const char *name);

tools/perf/util/intel-pt.c

@@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 	intel_pt_dump(pt, buf, len);
 }
 
+static void intel_pt_log_event(union perf_event *event)
+{
+	FILE *f = intel_pt_log_fp();
+
+	if (!intel_pt_enable_logging || !f)
+		return;
+
+	perf_event__fprintf(event, f);
+}
+
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
@@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session,
 		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
 		err = intel_pt_context_switch(pt, event, sample);
 
-	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     perf_event__name(event->header.type), event->header.type,
-		     sample->cpu, sample->time, timestamp);
+	intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
+		     event->header.type, sample->cpu, sample->time, timestamp);
+	intel_pt_log_event(event);
 
 	return err;
 }

tools/perf/util/pmu.c

@@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
-			if (strncmp(pname, name, strlen(pname)))
+			if (strcmp(pname, name))
 				continue;
 		}