Merge branch 'master' [vanilla Linus master] into libata-dev.git/upstream

Two bits were appended to the end of the bitfield
list in struct scsi_device.  Resolve that conflict
by including both bits.

Conflicts:
	include/scsi/scsi_device.h

61 files changed, 2443 insertions, 980 deletions

diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index a3dbadb26ef..7065cd6fbdf 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 
 DESCRIPTION
 -----------
-This 'perf bench' command is general framework for benchmark suites.
+This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
@@ -45,14 +45,20 @@ SUBSYSTEM
 'sched'::
 	Scheduler and IPC mechanisms.
 
+'mem'::
+	Memory access performance.
+
+'all'::
+	All benchmark subsystems.
+
 SUITES FOR 'sched'
 ~~~~~~~~~~~~~~~~~~
 *messaging*::
 Suite for evaluating performance of scheduler and IPC mechanisms.
 Based on hackbench by Rusty Russell.
 
-Options of *pipe*
-^^^^^^^^^^^^^^^^^
+Options of *messaging*
+^^^^^^^^^^^^^^^^^^^^^^
 -p::
 --pipe::
 Use pipe() instead of socketpair()
@@ -115,6 +121,72 @@ Example of *pipe*
                 59004 ops/sec
 ---------------------
 
+SUITES FOR 'mem'
+~~~~~~~~~~~~~~~~
+*memcpy*::
+Suite for evaluating performance of simple memory copy in various ways.
+
+Options of *memcpy*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to copy (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to copy (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-movsq and x86-64-movsb are supported.
+
+-i::
+--iterations::
+Repeat memcpy invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memcpy.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memcpy.
+
+*memset*::
+Suite for evaluating performance of simple memory set in various ways.
+
+Options of *memset*
+^^^^^^^^^^^^^^^^^^^
+-l::
+--length::
+Specify length of memory to set (default: 1MB).
+Available units are B, KB, MB, GB and TB (case insensitive).
+
+-r::
+--routine::
+Specify routine to set (default: default).
+Available routines are depend on the architecture.
+On x86-64, x86-64-unrolled, x86-64-stosq and x86-64-stosb are supported.
+
+-i::
+--iterations::
+Repeat memset invocation this number of times.
+
+-c::
+--cycle::
+Use perf's cpu-cycles event instead of gettimeofday syscall.
+
+-o::
+--only-prefault::
+Show only the result with page faults before memset.
+
+-n::
+--no-prefault::
+Show only the result without page faults before memset.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 2d89f02719b..495210a612c 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -57,7 +57,7 @@ OPTIONS
 
 -s::
 --sort=::
-	Sort by key(s): pid, comm, dso, symbol, parent.
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline.
 
 -p::
 --parent=<regex>::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 4a5680cb242..5b80d84d6b4 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -112,7 +112,7 @@ Default is to monitor all CPUS.
 
 -s::
 --sort::
-	Sort by key(s): pid, comm, dso, symbol, parent
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline.
 
 -n::
 --show-nr-samples::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0eee64cfe9a..75d74e5db8d 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -155,7 +155,7 @@ endif
 
 ### --- END CONFIGURATION SECTION ---
 
-BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)/util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
+BASIC_CFLAGS = -Iutil/include -Iarch/$(ARCH)/include -I$(OUTPUT)util -I$(TRACE_EVENT_DIR) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 BASIC_LDFLAGS =
 
 # Guard against environment variables
@@ -503,6 +503,7 @@ else
 		LIB_OBJS += $(OUTPUT)ui/progress.o
 		LIB_OBJS += $(OUTPUT)ui/util.o
 		LIB_OBJS += $(OUTPUT)ui/tui/setup.o
+		LIB_OBJS += $(OUTPUT)ui/tui/util.o
 		LIB_H += ui/browser.h
 		LIB_H += ui/browsers/map.h
 		LIB_H += ui/helpline.h
@@ -522,13 +523,18 @@ else
 		msg := $(warning GTK2 not found, disables GTK2 support. Please install gtk2-devel or libgtk2.0-dev);
 		BASIC_CFLAGS += -DNO_GTK2_SUPPORT
 	else
+		ifeq ($(call try-cc,$(SOURCE_GTK2_INFOBAR),$(FLAGS_GTK2)),y)
+			BASIC_CFLAGS += -DHAVE_GTK_INFO_BAR
+		endif
 		BASIC_CFLAGS += $(shell pkg-config --cflags gtk+-2.0)
 		EXTLIBS += $(shell pkg-config --libs gtk+-2.0)
 		LIB_OBJS += $(OUTPUT)ui/gtk/browser.o
 		LIB_OBJS += $(OUTPUT)ui/gtk/setup.o
+		LIB_OBJS += $(OUTPUT)ui/gtk/util.o
 		# Make sure that it'd be included only once.
 		ifneq ($(findstring -DNO_NEWT_SUPPORT,$(BASIC_CFLAGS)),)
 			LIB_OBJS += $(OUTPUT)ui/setup.o
+			LIB_OBJS += $(OUTPUT)ui/util.o
 		endif
 	endif
 endif
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 71557225bf9..02dad5d3359 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -24,21 +24,21 @@
 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		use_cycle;
+static int		cycle_fd;
 static bool		only_prefault;
 static bool		no_prefault;
 
 static const struct option options[] = {
 	OPT_STRING('l', "length", &length_str, "1MB",
 		    "Specify length of memory to copy. "
-		    "available unit: B, MB, GB (upper and lower)"),
+		    "Available units: B, KB, MB, GB and TB (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('c', "cycle", &use_cycle,
+		    "Use cycles event instead of gettimeofday() for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
 		    "Show only the result with page faults before memcpy()"),
 	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -76,27 +76,27 @@ static const char * const bench_mem_memcpy_usage[] = {
 	NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-	if (clock_fd < 0 && errno == ENOSYS)
+	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 	else
-		BUG_ON(clock_fd < 0);
+		BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
 	int ret;
 	u64 clk;
 
-	ret = read(clock_fd, &clk, sizeof(u64));
+	ret = read(cycle_fd, &clk, sizeof(u64));
 	BUG_ON(ret != sizeof(u64));
 
 	return clk;
@@ -119,9 +119,9 @@ static void alloc_mem(void **dst, void **src, size_t length)
 		die("memory allocation failed - maybe length is too large?\n");
 }
 
-static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+static u64 do_memcpy_cycle(memcpy_t fn, size_t len, bool prefault)
 {
-	u64 clock_start = 0ULL, clock_end = 0ULL;
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
 	void *src = NULL, *dst = NULL;
 	int i;
 
@@ -130,14 +130,14 @@ static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
 	if (prefault)
 		fn(dst, src, len);
 
-	clock_start = get_clock();
+	cycle_start = get_cycle();
 	for (i = 0; i < iterations; ++i)
 		fn(dst, src, len);
-	clock_end = get_clock();
+	cycle_end = get_cycle();
 
 	free(src);
 	free(dst);
-	return clock_end - clock_start;
+	return cycle_end - cycle_start;
 }
 
 static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
@@ -182,17 +182,17 @@ int bench_mem_memcpy(int argc, const char **argv,
 	int i;
 	size_t len;
 	double result_bps[2];
-	u64 result_clock[2];
+	u64 result_cycle[2];
 
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memcpy_usage, 0);
 
-	if (use_clock)
-		init_clock();
+	if (use_cycle)
+		init_cycle();
 
 	len = (size_t)perf_atoll((char *)length_str);
 
-	result_clock[0] = result_clock[1] = 0ULL;
+	result_cycle[0] = result_cycle[1] = 0ULL;
 	result_bps[0] = result_bps[1] = 0.0;
 
 	if ((s64)len <= 0) {
@@ -223,11 +223,11 @@ int bench_mem_memcpy(int argc, const char **argv,
 
 	if (!only_prefault && !no_prefault) {
 		/* show both of results */
-		if (use_clock) {
-			result_clock[0] =
-				do_memcpy_clock(routines[i].fn, len, false);
-			result_clock[1] =
-				do_memcpy_clock(routines[i].fn, len, true);
+		if (use_cycle) {
+			result_cycle[0] =
+				do_memcpy_cycle(routines[i].fn, len, false);
+			result_cycle[1] =
+				do_memcpy_cycle(routines[i].fn, len, true);
 		} else {
 			result_bps[0] =
 				do_memcpy_gettimeofday(routines[i].fn,
@@ -237,9 +237,9 @@ int bench_mem_memcpy(int argc, const char **argv,
 						len, true);
 		}
 	} else {
-		if (use_clock) {
-			result_clock[pf] =
-				do_memcpy_clock(routines[i].fn,
+		if (use_cycle) {
+			result_cycle[pf] =
+				do_memcpy_cycle(routines[i].fn,
 						len, only_prefault);
 		} else {
 			result_bps[pf] =
@@ -251,12 +251,12 @@ int bench_mem_memcpy(int argc, const char **argv,
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte\n",
-					(double)result_clock[0]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte\n",
+					(double)result_cycle[0]
 					/ (double)len);
-				printf(" %14lf Clock/Byte (with prefault)\n",
-					(double)result_clock[1]
+				printf(" %14lf Cycle/Byte (with prefault)\n",
+					(double)result_cycle[1]
 					/ (double)len);
 			} else {
 				print_bps(result_bps[0]);
@@ -265,9 +265,9 @@ int bench_mem_memcpy(int argc, const char **argv,
 				printf(" (with prefault)\n");
 			}
 		} else {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte",
-					(double)result_clock[pf]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte",
+					(double)result_cycle[pf]
 					/ (double)len);
 			} else
 				print_bps(result_bps[pf]);
@@ -277,17 +277,17 @@ int bench_mem_memcpy(int argc, const char **argv,
 		break;
 	case BENCH_FORMAT_SIMPLE:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
+			if (use_cycle) {
 				printf("%lf %lf\n",
-					(double)result_clock[0] / (double)len,
-					(double)result_clock[1] / (double)len);
+					(double)result_cycle[0] / (double)len,
+					(double)result_cycle[1] / (double)len);
 			} else {
 				printf("%lf %lf\n",
 					result_bps[0], result_bps[1]);
 			}
 		} else {
-			if (use_clock) {
-				printf("%lf\n", (double)result_clock[pf]
+			if (use_cycle) {
+				printf("%lf\n", (double)result_cycle[pf]
 					/ (double)len);
 			} else
 				printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index e9079185bd7..350cc955726 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -24,21 +24,21 @@
 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		use_cycle;
+static int		cycle_fd;
 static bool		only_prefault;
 static bool		no_prefault;
 
 static const struct option options[] = {
 	OPT_STRING('l', "length", &length_str, "1MB",
-		    "Specify length of memory to copy. "
-		    "available unit: B, MB, GB (upper and lower)"),
+		    "Specify length of memory to set. "
+		    "Available units: B, KB, MB, GB and TB (upper and lower)"),
 	OPT_STRING('r', "routine", &routine, "default",
-		    "Specify routine to copy"),
+		    "Specify routine to set"),
 	OPT_INTEGER('i', "iterations", &iterations,
 		    "repeat memset() invocation this number of times"),
-	OPT_BOOLEAN('c', "clock", &use_clock,
-		    "Use CPU clock for measuring"),
+	OPT_BOOLEAN('c', "cycle", &use_cycle,
+		    "Use cycles event instead of gettimeofday() for measuring"),
 	OPT_BOOLEAN('o', "only-prefault", &only_prefault,
 		    "Show only the result with page faults before memset()"),
 	OPT_BOOLEAN('n', "no-prefault", &no_prefault,
@@ -76,27 +76,27 @@ static const char * const bench_mem_memset_usage[] = {
 	NULL
 };
 
-static struct perf_event_attr clock_attr = {
+static struct perf_event_attr cycle_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES
 };
 
-static void init_clock(void)
+static void init_cycle(void)
 {
-	clock_fd = sys_perf_event_open(&clock_attr, getpid(), -1, -1, 0);
+	cycle_fd = sys_perf_event_open(&cycle_attr, getpid(), -1, -1, 0);
 
-	if (clock_fd < 0 && errno == ENOSYS)
+	if (cycle_fd < 0 && errno == ENOSYS)
 		die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
 	else
-		BUG_ON(clock_fd < 0);
+		BUG_ON(cycle_fd < 0);
 }
 
-static u64 get_clock(void)
+static u64 get_cycle(void)
 {
 	int ret;
 	u64 clk;
 
-	ret = read(clock_fd, &clk, sizeof(u64));
+	ret = read(cycle_fd, &clk, sizeof(u64));
 	BUG_ON(ret != sizeof(u64));
 
 	return clk;
@@ -115,9 +115,9 @@ static void alloc_mem(void **dst, size_t length)
 		die("memory allocation failed - maybe length is too large?\n");
 }
 
-static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
+static u64 do_memset_cycle(memset_t fn, size_t len, bool prefault)
 {
-	u64 clock_start = 0ULL, clock_end = 0ULL;
+	u64 cycle_start = 0ULL, cycle_end = 0ULL;
 	void *dst = NULL;
 	int i;
 
@@ -126,13 +126,13 @@ static u64 do_memset_clock(memset_t fn, size_t len, bool prefault)
 	if (prefault)
 		fn(dst, -1, len);
 
-	clock_start = get_clock();
+	cycle_start = get_cycle();
 	for (i = 0; i < iterations; ++i)
 		fn(dst, i, len);
-	clock_end = get_clock();
+	cycle_end = get_cycle();
 
 	free(dst);
-	return clock_end - clock_start;
+	return cycle_end - cycle_start;
 }
 
 static double do_memset_gettimeofday(memset_t fn, size_t len, bool prefault)
@@ -176,17 +176,17 @@ int bench_mem_memset(int argc, const char **argv,
 	int i;
 	size_t len;
 	double result_bps[2];
-	u64 result_clock[2];
+	u64 result_cycle[2];
 
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memset_usage, 0);
 
-	if (use_clock)
-		init_clock();
+	if (use_cycle)
+		init_cycle();
 
 	len = (size_t)perf_atoll((char *)length_str);
 
-	result_clock[0] = result_clock[1] = 0ULL;
+	result_cycle[0] = result_cycle[1] = 0ULL;
 	result_bps[0] = result_bps[1] = 0.0;
 
 	if ((s64)len <= 0) {
@@ -217,11 +217,11 @@ int bench_mem_memset(int argc, const char **argv,
 
 	if (!only_prefault && !no_prefault) {
 		/* show both of results */
-		if (use_clock) {
-			result_clock[0] =
-				do_memset_clock(routines[i].fn, len, false);
-			result_clock[1] =
-				do_memset_clock(routines[i].fn, len, true);
+		if (use_cycle) {
+			result_cycle[0] =
+				do_memset_cycle(routines[i].fn, len, false);
+			result_cycle[1] =
+				do_memset_cycle(routines[i].fn, len, true);
 		} else {
 			result_bps[0] =
 				do_memset_gettimeofday(routines[i].fn,
@@ -231,9 +231,9 @@ int bench_mem_memset(int argc, const char **argv,
 						len, true);
 		}
 	} else {
-		if (use_clock) {
-			result_clock[pf] =
-				do_memset_clock(routines[i].fn,
+		if (use_cycle) {
+			result_cycle[pf] =
+				do_memset_cycle(routines[i].fn,
 						len, only_prefault);
 		} else {
 			result_bps[pf] =
@@ -245,12 +245,12 @@ int bench_mem_memset(int argc, const char **argv,
 	switch (bench_format) {
 	case BENCH_FORMAT_DEFAULT:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte\n",
-					(double)result_clock[0]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte\n",
+					(double)result_cycle[0]
 					/ (double)len);
-				printf(" %14lf Clock/Byte (with prefault)\n ",
-					(double)result_clock[1]
+				printf(" %14lf Cycle/Byte (with prefault)\n ",
+					(double)result_cycle[1]
 					/ (double)len);
 			} else {
 				print_bps(result_bps[0]);
@@ -259,9 +259,9 @@ int bench_mem_memset(int argc, const char **argv,
 				printf(" (with prefault)\n");
 			}
 		} else {
-			if (use_clock) {
-				printf(" %14lf Clock/Byte",
-					(double)result_clock[pf]
+			if (use_cycle) {
+				printf(" %14lf Cycle/Byte",
+					(double)result_cycle[pf]
 					/ (double)len);
 			} else
 				print_bps(result_bps[pf]);
@@ -271,17 +271,17 @@ int bench_mem_memset(int argc, const char **argv,
 		break;
 	case BENCH_FORMAT_SIMPLE:
 		if (!only_prefault && !no_prefault) {
-			if (use_clock) {
+			if (use_cycle) {
 				printf("%lf %lf\n",
-					(double)result_clock[0] / (double)len,
-					(double)result_clock[1] / (double)len);
+					(double)result_cycle[0] / (double)len,
+					(double)result_cycle[1] / (double)len);
 			} else {
 				printf("%lf %lf\n",
 					result_bps[0], result_bps[1]);
 			}
 		} else {
-			if (use_clock) {
-				printf("%lf\n", (double)result_clock[pf]
+			if (use_cycle) {
+				printf("%lf\n", (double)result_cycle[pf]
 					/ (double)len);
 			} else
 				printf("%lf\n", result_bps[pf]);
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b0e74ab2d7a..1f310021644 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -33,7 +33,7 @@ struct bench_suite {
 };
 						\
 /* sentinel: easy for help */
-#define suite_all { "all", "test all suite (pseudo suite)", NULL }
+#define suite_all { "all", "Test all benchmark suites", NULL }
 
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
@@ -75,7 +75,7 @@ static struct bench_subsys subsystems[] = {
 	  "memory access performance",
 	  mem_suites },
 	{ "all",		/* sentinel: easy for help */
-	  "test all subsystem (pseudo subsystem)",
+	  "all benchmark subsystem",
 	  NULL },
 	{ NULL,
 	  NULL,
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index acd78dc2834..0dd5a058f76 100644
--- a/tools/perf/builtin-evlist.c
+++ b/