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

Pull perf fixes from Ingo Molnar:
 "Misc kernel side fixes:

   - fix event leak
   - fix AMD PMU driver bug
   - fix core event handling bug
   - fix build bug on certain randconfigs

  Plus misc tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/amd/ibs: Fix pmu::stop() nesting
  perf/core: Don't leak event in the syscall error path
  perf/core: Fix time tracking bug with multiplexing
  perf jit: genelf makes assumptions about endian
  perf hists: Fix determination of a callchain node's childlessness
  perf tools: Add missing initialization of perf_sample.cpumode in synthesized samples
  perf tools: Fix build break on powerpc
  perf/x86: Move events_sysfs_show() outside CPU_SUP_INTEL
  perf bench: Fix detached tarball building due to missing 'perf bench memcpy' headers
  perf tests: Fix tarpkg build test error output redirection

5 files changed, 32 insertions, 21 deletions

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 52cf479bc593..dad55d04ffdd 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -56,13 +56,22 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-static struct perf_sample synth_sample = {
+static int perf_tool__process_synth_event(struct perf_tool *tool,
+					  union perf_event *event,
+					  struct machine *machine,
+					  perf_event__handler_t process)
+{
+	struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
 	.time	   = -1,
 	.stream_id = -1,
 	.cpu	   = -1,
 	.period	   = 1,
+	.cpumode   = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK,
+	};
+
+	return process(tool, event, &synth_sample, machine);
 };
 
 /*
@@ -186,7 +195,7 @@ pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	if (perf_event__prepare_comm(event, pid, machine, &tgid, &ppid) != 0)
 		return -1;
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return tgid;
@@ -218,7 +227,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
 
 	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
-	if (process(tool, event, &synth_sample, machine) != 0)
+	if (perf_tool__process_synth_event(tool, event, machine, process) != 0)
 		return -1;
 
 	return 0;
@@ -344,7 +353,7 @@ out:
 		event->mmap2.pid = tgid;
 		event->mmap2.tid = pid;
 
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -402,7 +411,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 
 		memcpy(event->mmap.filename, pos->dso->long_name,
 		       pos->dso->long_name_len + 1);
-		if (process(tool, event, &synth_sample, machine) != 0) {
+		if (perf_tool__process_synth_event(tool, event, machine, process) != 0) {
 			rc = -1;
 			break;
 		}
@@ -472,7 +481,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		/*
 		 * Send the prepared comm event
 		 */
-		if (process(tool, comm_event, &synth_sample, machine) != 0)
+		if (perf_tool__process_synth_event(tool, comm_event, machine, process) != 0)
 			break;
 
 		rc = 0;
@@ -701,7 +710,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
 
-	err = process(tool, event, &synth_sample, machine);
+	err = perf_tool__process_synth_event(tool, event, machine, process);
 	free(event);
 
 	return err;
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index cd67e64a0494..2fbeb59c4bdd 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -9,36 +9,32 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 
 #if   defined(__arm__)
 #define GEN_ELF_ARCH	EM_ARM
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS32
 #elif defined(__aarch64__)
 #define GEN_ELF_ARCH	EM_AARCH64
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS64
 #elif defined(__x86_64__)
 #define GEN_ELF_ARCH	EM_X86_64
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS64
 #elif defined(__i386__)
 #define GEN_ELF_ARCH	EM_386
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS32
-#elif defined(__ppcle__)
-#define GEN_ELF_ARCH	EM_PPC
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
-#define GEN_ELF_CLASS	ELFCLASS64
-#elif defined(__powerpc__)
-#define GEN_ELF_ARCH	EM_PPC64
-#define GEN_ELF_ENDIAN	ELFDATA2MSB
-#define GEN_ELF_CLASS	ELFCLASS64
-#elif defined(__powerpcle__)
+#elif defined(__powerpc64__)
 #define GEN_ELF_ARCH	EM_PPC64
-#define GEN_ELF_ENDIAN	ELFDATA2LSB
 #define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__powerpc__)
+#define GEN_ELF_ARCH	EM_PPC
+#define GEN_ELF_CLASS	ELFCLASS32
 #else
 #error "unsupported architecture"
 #endif
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define GEN_ELF_ENDIAN	ELFDATA2MSB
+#else
+#define GEN_ELF_ENDIAN	ELFDATA2LSB
+#endif
+
 #if GEN_ELF_CLASS == ELFCLASS64
 #define elf_newehdr	elf64_newehdr
 #define elf_getshdr	elf64_getshdr
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 6bc3ecd2e7ca..abf1366e2a24 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -279,6 +279,7 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
 	event.sample.header.misc = PERF_RECORD_MISC_USER;
 	event.sample.header.size = sizeof(struct perf_event_header);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = le64_to_cpu(branch->from);
 	sample.pid = btsq->pid;
 	sample.tid = btsq->tid;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 05d815851be1..407f11b97c8d 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -979,6 +979,7 @@ static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1035,6 +1036,7 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
@@ -1092,6 +1094,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
 	if (!pt->timeless_decoding)
 		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.ip = ptq->state->from_ip;
 	sample.pid = ptq->pid;
 	sample.tid = ptq->tid;
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index cd272cc21e05..ad0c0bb1fbc7 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -417,6 +417,7 @@ static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
 	 * use first address as sample address
 	 */
 	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.pid  = pid;
 	sample.tid  = tid;
 	sample.time = id->time;
@@ -505,6 +506,7 @@ static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
 	 * use first address as sample address
 	 */
 	memset(&sample, 0, sizeof(sample));
+	sample.cpumode = PERF_RECORD_MISC_USER;
 	sample.pid  = pid;
 	sample.tid  = tid;
 	sample.time = id->time;