Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/acme/linux into perf/core

Pull in the latest perf/core improvements and fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

tools/perf/Documentation/perf-record.txt

@@ -58,6 +58,10 @@ OPTIONS
 --tid=::
         Record events on existing thread ID.
 
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
 -r::
 --realtime=::
 	Collect data with this RT SCHED_FIFO priority.

tools/perf/Documentation/perf-top.txt

@@ -78,6 +78,10 @@ Default is to monitor all CPUS.
 --tid=<tid>::
         Profile events on existing thread ID.
 
+-u::
+--uid=::
+        Record events in threads owned by uid. Name or number.
+
 -r <priority>::
 --realtime=<priority>::
 	Collect data with this RT SCHED_FIFO priority.

tools/perf/Makefile

@@ -61,7 +61,7 @@ ifeq ($(ARCH),x86_64)
 	ifeq (${IS_X86_64}, 1)
 		RAW_ARCH := x86_64
 		ARCH_CFLAGS := -DARCH_X86_64
-		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+		ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
 	endif
 endif
 
@@ -104,7 +104,7 @@ endif
 
 CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
-ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 ALL_LDFLAGS = $(LDFLAGS)
 STRIP ?= strip
 
@@ -168,10 +168,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-# Those must not be GNU-specific; they are shared with perl/ which may
-# be built by a different compiler. (Note that this is an artifact now
-# but it still might be nice to keep that distinction.)
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -362,8 +359,10 @@ BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
 ifeq ($(RAW_ARCH),x86_64)
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memset.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
 BUILTIN_OBJS += $(OUTPUT)builtin-evlist.o

tools/perf/bench/bench.h

@@ -4,6 +4,7 @@
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv, const char *prefix __used);
+extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
 #define BENCH_FORMAT_DEFAULT		0

tools/perf/bench/mem-memcpy-x86-64-asm-def.h

@@ -2,3 +2,11 @@
 MEMCPY_FN(__memcpy,
 	"x86-64-unrolled",
 	"unrolled memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c,
+	"x86-64-movsq",
+	"movsq-based memcpy() in arch/x86/lib/memcpy_64.S")
+
+MEMCPY_FN(memcpy_c_e,
+	"x86-64-movsb",
+	"movsb-based memcpy() in arch/x86/lib/memcpy_64.S")

tools/perf/bench/mem-memcpy-x86-64-asm.S

@@ -1,2 +1,6 @@
-
+#define memcpy MEMCPY /* don't hide glibc's memcpy() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemcpy_c globl memcpy_c; memcpy_c
+#define Lmemcpy_c_e globl memcpy_c_e; memcpy_c_e
 #include "../../../arch/x86/lib/memcpy_64.S"

tools/perf/bench/mem-memcpy.c

@@ -24,6 +24,7 @@
 
 static const char	*length_str	= "1MB";
 static const char	*routine	= "default";
+static int		iterations	= 1;
 static bool		use_clock;
 static int		clock_fd;
 static bool		only_prefault;
@@ -35,6 +36,8 @@ static const struct option options[] = {
 		    "available unit: B, MB, GB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
 		    "Specify routine to copy"),
+	OPT_INTEGER('i', "iterations", &iterations,
+		    "repeat memcpy() invocation this number of times"),
 	OPT_BOOLEAN('c', "clock", &use_clock,
 		    "Use CPU clock for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
@@ -121,14 +124,16 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
 {
 	u64 clock_start = 0ULL, clock_end = 0ULL;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
 	if (prefault)
 		fn(dst, src, len);
 
 	clock_start = get_clock();
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	clock_end = get_clock();
 
 	free(src);
@@ -140,14 +145,16 @@ static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
 {
 	struct timeval tv_start, tv_end, tv_diff;
 	void *src = NULL, *dst = NULL;
+	int i;
 
 	alloc_mem(&src, &dst, len);
 
 	if (prefault)
 		fn(dst, src, len);
 
 	BUG_ON(gettimeofday(&tv_start, NULL));
-	fn(dst, src, len);
+	for (i = 0; i < iterations; ++i)
+		fn(dst, src, len);
 	BUG_ON(gettimeofday(&tv_end, NULL));
 
 	timersub(&tv_end, &tv_start, &tv_diff);

tools/perf/bench/mem-memset-arch.h

@@ -0,0 +1,12 @@
+
+#ifdef ARCH_X86_64
+
+#define MEMSET_FN(fn, name, desc)		\
+	extern void *fn(void *, int, size_t);
+
+#include "mem-memset-x86-64-asm-def.h"
+
+#undef MEMSET_FN
+
+#endif
+

tools/perf/bench/mem-memset-x86-64-asm-def.h

@@ -0,0 +1,12 @@
+
+MEMSET_FN(__memset,
+	"x86-64-unrolled",
+	"unrolled memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c,
+	"x86-64-stosq",
+	"movsq-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_c_e,
+	"x86-64-stosb",
+	"movsb-based memset() in arch/x86/lib/memset_64.S")

tools/perf/bench/mem-memset-x86-64-asm.S

@@ -0,0 +1,6 @@
+#define memset MEMSET /* don't hide glibc's memset() */
+#define altinstr_replacement text
+#define globl p2align 4; .globl
+#define Lmemset_c globl memset_c; memset_c
+#define Lmemset_c_e globl memset_c_e; memset_c_e
+#include "../../../arch/x86/lib/memset_64.S"