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

Pull perf fixes from Ingo Molnar:
 "Two kprobes fixes and a handful of tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf tools: Make sparc64 arch point to sparc
  perf symbols: Define EM_AARCH64 for older OSes
  perf top: Fix SIGBUS on sparc64
  perf tools: Fix probing for PERF_FLAG_FD_CLOEXEC flag
  perf tools: Fix pthread_attr_setaffinity_np build error
  perf tools: Define _GNU_SOURCE on pthread_attr_setaffinity_np feature check
  perf bench: Fix order of arguments to memcpy_alloc_mem
  kprobes/x86: Check for invalid ftrace location in __recover_probed_insn()
  kprobes/x86: Use 5-byte NOP when the code might be modified by ftrace

tools/perf/bench/mem-memcpy.c

@@ -289,7 +289,7 @@ static u64 do_memcpy_cycle(const struct routine *r, size_t len, bool prefault)
 	memcpy_t fn = r->fn.memcpy;
 	int i;
 
-	memcpy_alloc_mem(&src, &dst, len);
+	memcpy_alloc_mem(&dst, &src, len);
 
 	if (prefault)
 		fn(dst, src, len);
@@ -312,7 +312,7 @@ static double do_memcpy_gettimeofday(const struct routine *r, size_t len,
 	void *src = NULL, *dst = NULL;
 	int i;
 
-	memcpy_alloc_mem(&src, &dst, len);
+	memcpy_alloc_mem(&dst, &src, len);
 
 	if (prefault)
 		fn(dst, src, len);

tools/perf/config/Makefile.arch

@@ -21,6 +21,10 @@ ifeq ($(RAW_ARCH),x86_64)
   endif
 endif
 
+ifeq ($(RAW_ARCH),sparc64)
+  ARCH ?= sparc
+endif
+
 ARCH ?= $(RAW_ARCH)
 
 LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)

tools/perf/config/feature-checks/Makefile

@@ -49,7 +49,7 @@ test-hello.bin:
 	$(BUILD)
 
 test-pthread-attr-setaffinity-np.bin:
-	$(BUILD) -Werror -lpthread
+	$(BUILD) -D_GNU_SOURCE -Werror -lpthread
 
 test-stackprotector-all.bin:
 	$(BUILD) -Werror -fstack-protector-all

tools/perf/config/feature-checks/test-pthread-attr-setaffinity-np.c

@@ -5,10 +5,11 @@ int main(void)
 {
 	int ret = 0;
 	pthread_attr_t thread_attr;
+	cpu_set_t cs;
 
 	pthread_attr_init(&thread_attr);
 	/* don't care abt exact args, just the API itself in libpthread */
-	ret = pthread_attr_setaffinity_np(&thread_attr, 0, NULL);
+	ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cs), &cs);
 
 	return ret;
 }

tools/perf/util/cloexec.c

@@ -25,6 +25,10 @@ static int perf_flag_probe(void)
 	if (cpu < 0)
 		cpu = 0;
 
+	/*
+	 * Using -1 for the pid is a workaround to avoid gratuitous jump label
+	 * changes.
+	 */
 	while (1) {
 		/* check cloexec flag */
 		fd = sys_perf_event_open(&attr, pid, cpu, -1,
@@ -47,16 +51,24 @@ static int perf_flag_probe(void)
 		  err, strerror_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+	while (1) {
+		fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
+		if (fd < 0 && pid == -1 && errno == EACCES) {
+			pid = 0;
+			continue;
+		}
+		break;
+	}
 	err = errno;
 
+	if (fd >= 0)
+		close(fd);
+
 	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
 		      err, strerror_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
-	close(fd);
-
 	return 0;
 }
 

tools/perf/util/evlist.h

@@ -28,7 +28,7 @@ struct perf_mmap {
 	int		 mask;
 	int		 refcnt;
 	unsigned int	 prev;
-	char		 event_copy[PERF_SAMPLE_MAX_SIZE];
+	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
 struct perf_evlist {

tools/perf/util/symbol-elf.c

@@ -11,6 +11,11 @@
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
+#ifndef EM_AARCH64
+#define EM_AARCH64	183  /* ARM 64 bit */
+#endif
+
+
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
 extern char *cplus_demangle(const char *, int);