Merge branch 'linus' into sched/core

Reason: Bring bakc upstream modification to resolve conflicts Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
author: Thomas Gleixner <tglx@linutronix.de> 2014-02-21 21:36:40 +0100
committer: Thomas Gleixner <tglx@linutronix.de> 2014-02-21 21:37:09 +0100
commit: d97a860c4f3de98ba5040a22f305b7159fe17cff (patch)
tree: 90c2155ec5a1f3115a9eb7a86f25d1a4610227c6 /tools
parent: 3f67d962c64d9b6de9dab81bdbe6d5c94c80d9b9 (diff)
parent: d158fc7f36a25e19791d25a55da5623399a2644f (diff)
download: op-kernel-dev-d97a860c4f3de98ba5040a22f305b7159fe17cff.zip
op-kernel-dev-d97a860c4f3de98ba5040a22f305b7159fe17cff.tar.gz
17 files changed, 406 insertions, 263 deletions
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index cfede86..b22dbb1 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -63,11 +63,35 @@ static int build_id_cache__kcore_dir(char *dir, size_t sz)
 	return 0;
 }
 
+static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
+{
+	char from[PATH_MAX];
+	char to[PATH_MAX];
+	const char *name;
+	u64 addr1 = 0, addr2 = 0;
+	int i;
+
+	scnprintf(from, sizeof(from), "%s/kallsyms", from_dir);
+	scnprintf(to, sizeof(to), "%s/kallsyms", to_dir);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr1 = kallsyms__get_function_start(from, name);
+		if (addr1)
+			break;
+	}
+
+	if (name)
+		addr2 = kallsyms__get_function_start(to, name);
+
+	return addr1 == addr2;
+}
+
 static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 					  size_t to_dir_sz)
 {
 	char from[PATH_MAX];
 	char to[PATH_MAX];
+	char to_subdir[PATH_MAX];
 	struct dirent *dent;
 	int ret = -1;
 	DIR *d;
@@ -86,10 +110,11 @@ static int build_id_cache__kcore_existing(const char *from_dir, char *to_dir,
 			continue;
 		scnprintf(to, sizeof(to), "%s/%s/modules", to_dir,
 			  dent->d_name);
-		if (!compare_proc_modules(from, to)) {
-			scnprintf(to, sizeof(to), "%s/%s", to_dir,
-				  dent->d_name);
-			strlcpy(to_dir, to, to_dir_sz);
+		scnprintf(to_subdir, sizeof(to_subdir), "%s/%s",
+			  to_dir, dent->d_name);
+		if (!compare_proc_modules(from, to) &&
+		    same_kallsyms_reloc(from_dir, to_subdir)) {
+			strlcpy(to_dir, to_subdir, to_dir_sz);
 			ret = 0;
 			break;
 		}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 3c394bf..af47531 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -287,10 +287,7 @@ static void perf_event__synthesize_guest_os(struct machine *machine, void *data)
 	 * have no _text sometimes.
 	 */
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine, "_text");
-	if (err < 0)
-		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-							 machine, "_stext");
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record guest kernel [%d]'s reference"
 		       " relocation symbol.\n", machine->pid);
@@ -457,10 +454,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-						 machine, "_text");
-	if (err < 0)
-		err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-							 machine, "_stext");
+						 machine);
 	if (err < 0)
 		pr_err("Couldn't record kernel reference relocation symbol\n"
 		       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index 67e5d0c..63a0e6f 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -454,7 +454,6 @@ So to start with, in order to add HAVE_PERF_EVENTS to your Kconfig, you
 will need at least this:
 	- asm/perf_event.h - a basic stub will suffice at first
 	- support for atomic64 types (and associated helper functions)
-	- set_perf_event_pending() implemented
 
 If your architecture does have hardware capabilities, you can override the
 weak stub hw_perf_event_init() to register hardware counters.
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 7daa806..e84fa26 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -100,8 +100,8 @@
 
 #ifdef __aarch64__
 #define mb()		asm volatile("dmb ish" ::: "memory")
-#define wmb()		asm volatile("dmb ishld" ::: "memory")
-#define rmb()		asm volatile("dmb ishst" ::: "memory")
+#define wmb()		asm volatile("dmb ishst" ::: "memory")
+#define rmb()		asm volatile("dmb ishld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 2bd13ed..3d90880 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -26,7 +26,6 @@ int test__vmlinux_matches_kallsyms(void)
 	struct map *kallsyms_map, *vmlinux_map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
-	struct ref_reloc_sym ref_reloc_sym = { .name = "_stext", };
 	u64 mem_start, mem_end;
 
 	/*
@@ -70,14 +69,6 @@ int test__vmlinux_matches_kallsyms(void)
 	 */
 	kallsyms_map = machine__kernel_map(&kallsyms, type);
 
-	sym = map__find_symbol_by_name(kallsyms_map, ref_reloc_sym.name, NULL);
-	if (sym == NULL) {
-		pr_debug("dso__find_symbol_by_name ");
-		goto out;
-	}
-
-	ref_reloc_sym.addr = UM(sym->start);
-
 	/*
 	 * Step 5:
 	 *
@@ -89,7 +80,6 @@ int test__vmlinux_matches_kallsyms(void)
 	}
 
 	vmlinux_map = machine__kernel_map(&vmlinux, type);
-	map__kmap(vmlinux_map)->ref_reloc_sym = &ref_reloc_sym;
 
 	/*
 	 * Step 6:
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1fc1c2f..b0f3ca8 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -470,23 +470,32 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	return 1;
 }
 
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_symbol_cb) <= 0)
+		return 0;
+
+	return args.start;
+}
+
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
-				       struct machine *machine,
-				       const char *symbol_name)
+				       struct machine *machine)
 {
 	size_t size;
-	const char *filename, *mmap_name;
-	char path[PATH_MAX];
+	const char *mmap_name;
 	char name_buff[PATH_MAX];
 	struct map *map;
+	struct kmap *kmap;
 	int err;
 	/*
 	 * We should get this from /sys/kernel/sections/.text, but till that is
 	 * available use this, and after it is use this as a fallback for older
 	 * kernels.
 	 */
-	struct process_symbol_args args = { .name = symbol_name, };
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -502,30 +511,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		 * see kernel/perf_event.c __perf_event_mmap
 		 */
 		event->header.misc = PERF_RECORD_MISC_KERNEL;
-		filename = "/proc/kallsyms";
 	} else {
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
-		if (machine__is_default_guest(machine))
-			filename = (char *) symbol_conf.default_guest_kallsyms;
-		else {
-			sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-			filename = path;
-		}
-	}
-
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
-		free(event);
-		return -ENOENT;
 	}
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
+	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", mmap_name, symbol_name) + 1;
+			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
 	size = PERF_ALIGN(size, sizeof(u64));
 	event->mmap.header.type = PERF_RECORD_MMAP;
 	event->mmap.header.size = (sizeof(event->mmap) -
 			(sizeof(event->mmap.filename) - size) + machine->id_hdr_size);
-	event->mmap.pgoff = args.start;
+	event->mmap.pgoff = kmap->ref_reloc_sym->addr;
 	event->mmap.start = map->start;
 	event->mmap.len   = map->end - event->mmap.start;
 	event->mmap.pid   = machine->pid;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index faf6e21..851fa06 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -214,8 +214,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 				   struct machine *machine, bool mmap_data);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
-				       struct machine *machine,
-				       const char *symbol_name);
+				       struct machine *machine);
 
 int perf_event__synthesize_modules(struct perf_tool *tool,
 				   perf_event__handler_t process,
@@ -279,4 +278,7 @@ size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
+u64 kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name);
+
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/include/asm/hash.h b/tools/perf/util/include/asm/hash.h
new file mode 100644
index 0000000..d82b170b
--- /dev/null
+++ b/tools/perf/util/include/asm/hash.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_GENERIC_HASH_H
+#define __ASM_GENERIC_HASH_H
+
+/* Stub */
+
+#endif /* __ASM_GENERIC_HASH_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index ded7459..c872991 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -496,19 +496,22 @@ static int symbol__in_kernel(void *arg, const char *name,
 	return 1;
 }
 
+static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+					   size_t bufsz)
+{
+	if (machine__is_default_guest(machine))
+		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
+	else
+		scnprintf(buf, bufsz, "%s/proc/kallsyms", machine->root_dir);
+}
+
 /* Figure out the start address of kernel map from /proc/kallsyms */
 static u64 machine__get_kernel_start_addr(struct machine *machine)
 {
-	const char *filename;
-	char path[PATH_MAX];
+	char filename[PATH_MAX];
 	struct process_args args;
 
-	if (machine__is_default_guest(machine))
-		filename = (char *)symbol_conf.default_guest_kallsyms;
-	else {
-		sprintf(path, "%s/proc/kallsyms", machine->root_dir);
-		filename = path;
-	}
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return 0;
@@ -829,9 +832,25 @@ static int machine__create_modules(struct machine *machine)
 	return 0;
 }
 
+const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
+	char filename[PATH_MAX];
+	const char *name;
+	u64 addr = 0;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	for (i = 0; (name = ref_reloc_sym_names[i]) != NULL; i++) {
+		addr = kallsyms__get_function_start(filename, name);
+		if (addr)
+			break;
+	}
+	if (!addr)
+		return -1;
 
 	if (kernel == NULL ||
 	    __machine__create_kernel_maps(machine, kernel) < 0)
@@ -850,6 +869,13 @@ int machine__create_kernel_maps(struct machine *machine)
 	 * Now that we have all the maps created, just set the ->end of them:
 	 */
 	map_groups__fixup_end(&machine->kmaps);
+
+	if (maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name,
+					     addr)) {
+		machine__destroy_kernel_maps(machine);
+		return -1;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 4771330..f77e91e 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -18,6 +18,8 @@ union perf_event;
 #define	HOST_KERNEL_ID			(-1)
 #define	DEFAULT_GUEST_KERNEL_ID		(0)
 
+extern const char *ref_reloc_sym_names[];
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 3b97513..39cd2d0 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -39,6 +39,7 @@ void map__init(struct map *map, enum map_type type,
 	map->start    = start;
 	map->end      = end;
 	map->pgoff    = pgoff;
+	map->reloc    = 0;
 	map->dso      = dso;
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
@@ -288,7 +289,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip)
 	if (map->dso->rel)
 		return rip - map->pgoff;
 
-	return map->unmap_ip(map, rip);
+	return map->unmap_ip(map, rip) - map->reloc;
 }
 
 /**
@@ -311,7 +312,7 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	if (map->dso->rel)
 		return map->unmap_ip(map, ip + map->pgoff);
 
-	return ip;
+	return ip + map->reloc;
 }
 
 void map_groups__init(struct map_groups *mg)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 18068c6..257e513 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -36,6 +36,7 @@ struct map {
 	bool			erange_warned;
 	u32			priv;
 	u64			pgoff;
+	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
 	u64			ino;      /* only valid for MMAP2 record */
 	u64			ino_generation;/* only valid for MMAP2 record */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 7594567..3e9f336 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -751,6 +751,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			if (strcmp(elf_name, kmap->ref_reloc_sym->name))
 				continue;
 			kmap->ref_reloc_sym->unrelocated_addr = sym.st_value;
+			map->reloc = kmap->ref_reloc_sym->addr -
+				     kmap->ref_reloc_sym->unrelocated_addr;
 			break;
 		}
 	}
@@ -922,6 +924,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				  (u64)shdr.sh_offset);
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
+new_symbol:
 		/*
 		 * We need to figure out if the object was created from C++ sources
 		 * DWARF DW_compile_unit has this, but we don't always have access
@@ -933,7 +936,6 @@ int dso__load_sym(struct dso *dso, struct map *map,
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
-new_symbol:
 		f = symbol__new(sym.st_value, sym.st_size,
 				GELF_ST_BIND(sym.st_info), elf_name);
 		free(demangled);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 39ce9ad..a9d758a 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -627,7 +627,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *dso, struct map *map,
+static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 			       symbol_filter_t filter)
 {
 	struct map_groups *kmaps = map__kmap(map)->kmaps;
@@ -692,6 +692,12 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map,
 			char dso_name[PATH_MAX];
 			struct dso *ndso;
 
+			if (delta) {
+				/* Kernel was relocated at boot time */
+				pos->start -= delta;
+				pos->end -= delta;
+			}
+
 			if (count == 0) {
 				curr_map = map;
 				goto filter_symbol;
@@ -721,6 +727,10 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map,
 			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
 			map_groups__insert(kmaps, curr_map);
 			++kernel_range;
+		} else if (delta) {
+			/* Kernel was relocated at boot time */
+			pos->start -= delta;
+			pos->end -= delta;
 		}
 filter_symbol:
 		if (filter && filter(curr_map, pos)) {
@@ -976,6 +986,23 @@ static int validate_kcore_modules(const char *kallsyms_filename,
 	return 0;
 }
 
+static int validate_kcore_addresses(const char *kallsyms_filename,
+				    struct map *map)
+{
+	struct kmap *kmap = map__kmap(map);
+
+	if (kmap->ref_reloc_sym && kmap->ref_reloc_sym->name) {
+		u64 start;
+
+		start = kallsyms__get_function_start(kallsyms_filename,
+						     kmap->ref_reloc_sym->name);
+		if (start != kmap->ref_reloc_sym->addr)
+			return -EINVAL;
+	}
+
+	return validate_kcore_modules(kallsyms_filename, map);
+}
+
 struct kcore_mapfn_data {
 	struct dso *dso;
 	enum map_type type;
@@ -1019,8 +1046,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 					     kallsyms_filename))
 		return -EINVAL;
 
-	/* All modules must be present at their original addresses */
-	if (validate_kcore_modules(kallsyms_filename, map))
+	/* Modules and kernel must be present at their original addresses */
+	if (validate_kcore_addresses(kallsyms_filename, map))
 		return -EINVAL;
 
 	md.dso = dso;
@@ -1113,15 +1140,41 @@ out_err:
 	return -EINVAL;
 }
 
+/*
+ * If the kernel is relocated at boot time, kallsyms won't match.  Compute the
+ * delta based on the relocation reference symbol.
+ */
+static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+{
+	struct kmap *kmap = map__kmap(map);
+	u64 addr;
+
+	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
+		return 0;
+
+	addr = kallsyms__get_function_start(filename,
+					    kmap->ref_reloc_sym->name);
+	if (!addr)
+		return -1;
+
+	*delta = addr - kmap->ref_reloc_sym->addr;
+	return 0;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
 		       struct map *map, symbol_filter_t filter)
 {
+	u64 delta = 0;
+
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return -1;
 
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
+	if (kallsyms__delta(map, filename, &delta))
+		return -1;
+
 	symbols__fixup_duplicate(&dso->symbols[map->type]);
 	symbols__fixup_end(&dso->symbols[map->type]);
 
@@ -1133,7 +1186,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (!dso__load_kcore(dso, map, filename))
 		return dso__split_kallsyms_for_kcore(dso, map, filter);
 	else
-		return dso__split_kallsyms(dso, map, filter);
+		return dso__split_kallsyms(dso, map, delta, filter);
 }
 
 static int dso__load_perf_map(struct dso *dso, struct map *map,
@@ -1424,7 +1477,7 @@ static int find_matching_kcore(struct map *map, char *dir, size_t dir_sz)
 			continue;
 		scnprintf(kallsyms_filename, sizeof(kallsyms_filename),
 			  "%s/%s/kallsyms", dir, dent->d_name);
-		if (!validate_kcore_modules(kallsyms_filename, map)) {
+		if (!validate_kcore_addresses(kallsyms_filename, map)) {
 			strlcpy(dir, kallsyms_filename, dir_sz);
 			ret = 0;
 			break;
@@ -1479,7 +1532,7 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 		if (fd != -1) {
 			close(fd);
 			/* If module maps match go with /proc/kallsyms */
-			if (!validate_kcore_modules("/proc/kallsyms", map))
+			if (!validate_kcore_addresses("/proc/kallsyms", map))
 				goto proc_kallsyms;
 		}
 
diff --git a/tools/power/x86/turbostat/.gitignore b/tools/power/x86/turbostat/.gitignore
new file mode 100644
index 0000000..7521370
--- /dev/null
+++ b/tools/power/x86/turbostat/.gitignore
@@ -0,0 +1 @@
+turbostat
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f09641d..d1b3a36 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -5,7 +5,7 @@ DESTDIR		:=
 
 turbostat : turbostat.c
 CFLAGS +=	-Wall
-CFLAGS +=	-I../../../../arch/x86/include/uapi/
+CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/uapi/asm/msr-index.h"'
 
 %: %.c
 	@mkdir -p $(BUILD_OUTPUT)
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9d77f13..77eb130 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -20,8 +20,10 @@
  */
 
 #define _GNU_SOURCE
-#include <asm/msr.h>
+#include MSRHEADER
+#include <stdarg.h>
 #include <stdio.h>
+#include <err.h>
 #include <unistd.h>
 #include <sys/types.h>
 #include <sys/wait.h>
@@ -35,13 +37,16 @@
 #include <string.h>
 #include <ctype.h>
 #include <sched.h>
+#include <cpuid.h>
 
 char *proc_stat = "/proc/stat";
 unsigned int interval_sec = 5;	/* set with -i interval_sec */
 unsigned int verbose;		/* set with -v */
 unsigned int rapl_verbose;	/* set with -R */
+unsigned int rapl_joules;	/* set with -J */
 unsigned int thermal_verbose;	/* set with -T */
-unsigned int summary_only;	/* set with -s */
+unsigned int summary_only;	/* set with -S */
+unsigned int dump_only;		/* set with -s */
 unsigned int skip_c0;
 unsigned int skip_c1;
 unsigned int do_nhm_cstates;
@@ -77,14 +82,32 @@ unsigned int tcc_activation_temp_override;
 double rapl_power_units, rapl_energy_units, rapl_time_units;
 double rapl_joule_counter_range;
 
-#define RAPL_PKG	(1 << 0)
-#define RAPL_CORES	(1 << 1)
-#define RAPL_GFX	(1 << 2)
-#define RAPL_DRAM	(1 << 3)
-#define RAPL_PKG_PERF_STATUS	(1 << 4)
-#define RAPL_DRAM_PERF_STATUS	(1 << 5)
-#define RAPL_PKG_POWER_INFO	(1 << 6)
-#define RAPL_CORE_POLICY	(1 << 7)
+#define RAPL_PKG		(1 << 0)
+					/* 0x610 MSR_PKG_POWER_LIMIT */
+					/* 0x611 MSR_PKG_ENERGY_STATUS */
+#define RAPL_PKG_PERF_STATUS	(1 << 1)
+					/* 0x613 MSR_PKG_PERF_STATUS */
+#define RAPL_PKG_POWER_INFO	(1 << 2)
+					/* 0x614 MSR_PKG_POWER_INFO */
+
+#define RAPL_DRAM		(1 << 3)
+					/* 0x618 MSR_DRAM_POWER_LIMIT */
+					/* 0x619 MSR_DRAM_ENERGY_STATUS */
+					/* 0x61c MSR_DRAM_POWER_INFO */
+#define RAPL_DRAM_PERF_STATUS	(1 << 4)
+					/* 0x61b MSR_DRAM_PERF_STATUS */
+
+#define RAPL_CORES		(1 << 5)
+					/* 0x638 MSR_PP0_POWER_LIMIT */
+					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_CORE_POLICY	(1 << 6)
+					/* 0x63a MSR_PP0_POLICY */
+
+
+#define RAPL_GFX		(1 << 7)
+					/* 0x640 MSR_PP1_POWER_LIMIT */
+					/* 0x641 MSR_PP1_ENERGY_STATUS */
+					/* 0x642 MSR_PP1_POLICY */
 #define	TJMAX_DEFAULT	100
 
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
@@ -234,7 +257,7 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
 	close(fd);
 
 	if (retval != sizeof *msr) {
-		fprintf(stderr, "%s offset 0x%zx read failed\n", pathname, offset);
+		fprintf(stderr, "%s offset 0x%llx read failed\n", pathname, (unsigned long long)offset);
 		return -1;
 	}
 
@@ -296,70 +319,92 @@ void print_header(void)
 		outp += sprintf(outp, "  %%pc10");
 	}
 
-	if (do_rapl & RAPL_PKG)
-		outp += sprintf(outp, "  Pkg_W");
-	if (do_rapl & RAPL_CORES)
-		outp += sprintf(outp, "  Cor_W");
-	if (do_rapl & RAPL_GFX)
-		outp += sprintf(outp, " GFX_W");
-	if (do_rapl & RAPL_DRAM)
-		outp += sprintf(outp, " RAM_W");
-	if (do_rapl & RAPL_PKG_PERF_STATUS)
-		outp += sprintf(outp, " PKG_%%");
-	if (do_rapl & RAPL_DRAM_PERF_STATUS)
-		outp += sprintf(outp, " RAM_%%");
+	if (do_rapl && !rapl_joules) {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, "  Pkg_W");
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, "  Cor_W");
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, " GFX_W");
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, " RAM_W");
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, " PKG_%%");
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, " RAM_%%");
+	} else {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, "  Pkg_J");
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, "  Cor_J");
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, " GFX_J");
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, " RAM_W");
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, " PKG_%%");
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, " RAM_%%");
+		outp += sprintf(outp, " time");
 
+	}
 	outp += sprintf(outp, "\n");
 }
 
 int dump_counters(struct thread_data *t, struct core_data *c,
 	struct pkg_data *p)
 {
-	fprintf(stderr, "t %p, c %p, p %p\n", t, c, p);
+	outp += sprintf(outp, "t %p, c %p, p %p\n", t, c, p);
 
 	if (t) {
-		fprintf(stderr, "CPU: %d flags 0x%x\n", t->cpu_id, t->flags);
-		fprintf(stderr, "TSC: %016llX\n", t->tsc);
-		fprintf(stderr, "aperf: %016llX\n", t->aperf);
-		fprintf(stderr, "mperf: %016llX\n", t->mperf);
-		fprintf(stderr, "c1: %016llX\n", t->c1);
-		fprintf(stderr, "msr0x%x: %08llX\n",
+		outp += sprintf(outp, "CPU: %d flags 0x%x\n",
+			t->cpu_id, t->flags);
+		outp += sprintf(outp, "TSC: %016llX\n", t->tsc);
+		outp += sprintf(outp, "aperf: %016llX\n", t->aperf);
+		outp += sprintf(outp, "mperf: %016llX\n", t->mperf);
+		outp += sprintf(outp, "c1: %016llX\n", t->c1);
+		outp += sprintf(outp, "msr0x%x: %08llX\n",
 			extra_delta_offset32, t->extra_delta32);
-		fprintf(stderr, "msr0x%x: %016llX\n",
+		outp += sprintf(outp, "msr0x%x: %016llX\n",
 			extra_delta_offset64, t->extra_delta64);
-		fprintf(stderr, "msr0x%x: %08llX\n",
+		outp += sprintf(outp, "msr0x%x: %08llX\n",
 			extra_msr_offset32, t->extra_msr32);
-		fprintf(stderr, "msr0x%x: %016llX\n",
+		outp += sprintf(outp, "msr0x%x: %016llX\n",
 			extra_msr_offset64, t->extra_msr64);
 		if (do_smi)
-			fprintf(stderr, "SMI: %08X\n", t->smi_count);
+			outp += sprintf(outp, "SMI: %08X\n", t->smi_count);
 	}
 
 	if (c) {
-		fprintf(stderr, "core: %d\n", c->core_id);
-		fprintf(stderr, "c3: %016llX\n", c->c3);
-		fprintf(stderr, "c6: %016llX\n", c->c6);
-		fprintf(stderr, "c7: %016llX\n", c->c7);
-		fprintf(stderr, "DTS: %dC\n", c->core_temp_c);
+		outp += sprintf(outp, "core: %d\n", c->core_id);
+		outp += sprintf(outp, "c3: %016llX\n", c->c3);
+		outp += sprintf(outp, "c6: %016llX\n", c->c6);
+		outp += sprintf(outp, "c7: %016llX\n", c->c7);
+		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
 	}
 
 	if (p) {
-		fprintf(stderr, "package: %d\n", p->package_id);
-		fprintf(stderr, "pc2: %016llX\n", p->pc2);
-		fprintf(stderr, "pc3: %016llX\n", p->pc3);
-		fprintf(stderr, "pc6: %016llX\n", p->pc6);
-		fprintf(stderr, "pc7: %016llX\n", p->pc7);
-		fprintf(stderr, "pc8: %016llX\n", p->pc8);
-		fprintf(stderr, "pc9: %016llX\n", p->pc9);
-		fprintf(stderr, "pc10: %016llX\n", p->pc10);
-		fprintf(stderr, "Joules PKG: %0X\n", p->energy_pkg);
-		fprintf(stderr, "Joules COR: %0X\n", p->energy_cores);
-		fprintf(stderr, "Joules GFX: %0X\n", p->energy_gfx);
-		fprintf(stderr, "Joules RAM: %0X\n", p->energy_dram);
-		fprintf(stderr, "Throttle PKG: %0X\n", p->rapl_pkg_perf_status);
-		fprintf(stderr, "Throttle RAM: %0X\n", p->rapl_dram_perf_status);
-		fprintf(stderr, "PTM: %dC\n", p->pkg_temp_c);
+		outp += sprintf(outp, "package: %d\n", p->package_id);
+		outp += sprintf(outp, "pc2: %016llX\n", p->pc2);
+		outp += sprintf(outp, "pc3: %016llX\n", p->pc3);
+		outp += sprintf(outp, "pc6: %016llX\n", p->pc6);
+		outp += sprintf(outp, "pc7: %016llX\n", p->pc7);
+		outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
+		outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
+		outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+		outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
+		outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
+		outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
+		outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram);
+		outp += sprintf(outp, "Throttle PKG: %0X\n",
+			p->rapl_pkg_perf_status);
+		outp += sprintf(outp, "Throttle RAM: %0X\n",
+			p->rapl_dram_perf_status);
+		outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
 	}
+
+	outp += sprintf(outp, "\n");
+
 	return 0;
 }
 
@@ -527,19 +572,39 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		fmt6 = " %4.0f**";
 	}
 
-	if (do_rapl & RAPL_PKG)
-		outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float);
-	if (do_rapl & RAPL_CORES)
-		outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float);
-	if (do_rapl & RAPL_GFX)
-		outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float); 
-	if (do_rapl & RAPL_DRAM)
-		outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float);
-	if (do_rapl & RAPL_PKG_PERF_STATUS )
-		outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
-	if (do_rapl & RAPL_DRAM_PERF_STATUS )
-		outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	if (do_rapl && !rapl_joules) {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, fmt6, p->energy_pkg * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, fmt6, p->energy_cores * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, fmt5, p->energy_gfx * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, fmt5, p->energy_dram * rapl_energy_units / interval_float);
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	} else {
+		if (do_rapl & RAPL_PKG)
+			outp += sprintf(outp, fmt6,
+					p->energy_pkg * rapl_energy_units);
+		if (do_rapl & RAPL_CORES)
+			outp += sprintf(outp, fmt6,
+					p->energy_cores * rapl_energy_units);
+		if (do_rapl & RAPL_GFX)
+			outp += sprintf(outp, fmt5,
+					p->energy_gfx * rapl_energy_units);
+		if (do_rapl & RAPL_DRAM)
+			outp += sprintf(outp, fmt5,
+					p->energy_dram * rapl_energy_units);
+		if (do_rapl & RAPL_PKG_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+		if (do_rapl & RAPL_DRAM_PERF_STATUS)
+			outp += sprintf(outp, fmt5, 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+	outp += sprintf(outp, fmt5, interval_float);
 
+	}
 done:
 	outp += sprintf(outp, "\n");
 
@@ -622,12 +687,10 @@ delta_thread(struct thread_data *new, struct thread_data *old,
 	old->tsc = new->tsc - old->tsc;
 
 	/* check for TSC < 1 Mcycles over interval */
-	if (old->tsc < (1000 * 1000)) {
-		fprintf(stderr, "Insanely slow TSC rate, TSC stops in idle?\n");
-		fprintf(stderr, "You can disable all c-states by booting with \"idle=poll\"\n");
-		fprintf(stderr, "or just the deep ones with \"processor.max_cstate=1\"\n");
-		exit(-3);
-	}
+	if (old->tsc < (1000 * 1000))
+		errx(-3, "Insanely slow TSC rate, TSC stops in idle?\n"
+		     "You can disable all c-states by booting with \"idle=poll\"\n"
+		     "or just the deep ones with \"processor.max_cstate=1\"");
 
 	old->c1 = new->c1 - old->c1;
 
@@ -1173,24 +1236,43 @@ void free_all_buffers(void)
 }
 
 /*
+ * Open a file, and exit on failure
+ */
+FILE *fopen_or_die(const char *path, const char *mode)
+{
+	FILE *filep = fopen(path, "r");
+	if (!filep)
+		err(1, "%s: open failed", path);
+	return filep;
+}
+
+/*
+ * Parse a file containing a single int.
+ */
+int parse_int_file(const char *fmt, ...)
+{
+	va_list args;
+	char path[PATH_MAX];
+	FILE *filep;
+	int value;
+
+	va_start(args, fmt);
+	vsnprintf(path, sizeof(path), fmt, args);
+	va_end(args);
+	filep = fopen_or_die(path, "r");
+	if (fscanf(filep, "%d", &value) != 1)
+		err(1, "%s: failed to parse number from file", path);
+	fclose(filep);
+	return value;
+}
+
+/*
  * cpu_is_first_sibling_in_core(cpu)
  * return 1 if given CPU is 1st HT sibling in the core
  */
 int cpu_is_first_sibling_in_core(int cpu)
 {
-	char path[64];
-	FILE *filep;
-	int first_cpu;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &first_cpu);
-	fclose(filep);
-	return (cpu == first_cpu);
+	return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
 }
 
 /*
@@ -1199,53 +1281,17 @@ int cpu_is_first_sibling_in_core(int cpu)
  */
 int cpu_is_first_core_in_package(int cpu)
 {
-	char path[64];
-	FILE *filep;
-	int first_cpu;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &first_cpu);
-	fclose(filep);
-	return (cpu == first_cpu);
+	return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_siblings_list", cpu);
 }
 
 int get_physical_package_id(int cpu)
 {
-	char path[80];
-	FILE *filep;
-	int pkg;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &pkg);
-	fclose(filep);
-	return pkg;
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
 }
 
 int get_core_id(int cpu)
 {
-	char path[80];
-	FILE *filep;
-	int core;
-
-	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
-	fscanf(filep, "%d", &core);
-	fclose(filep);
-	return core;
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
 }
 
 int get_num_ht_siblings(int cpu)
@@ -1257,11 +1303,7 @@ int get_num_ht_siblings(int cpu)
 	char character;
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
-	filep = fopen(path, "r");
-	if (filep == NULL) {
-		perror(path);
-		exit(1);
-	}
+	filep = fopen_or_die(path, "r");
 	/*
 	 * file format:
 	 * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4)
@@ -1331,17 +1373,11 @@ int for_all_proc_cpus(int (func)(int))
 	int cpu_num;
 	int retval;
 
-	fp = fopen(proc_stat, "r");
-	if (fp == NULL) {
-		perror(proc_stat);
-		exit(1);
-	}
+	fp = fopen_or_die(proc_stat, "r");
 
 	retval = fscanf(fp, "cpu %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n");
-	if (retval != 0) {
-		perror("/proc/stat format");
-		exit(1);
-	}
+	if (retval != 0)
+		err(1, "%s: failed to parse format", proc_stat);
 
 	while (1) {
 		retval = fscanf(fp, "cpu%u %*d %*d %*d %*d %*d %*d %*d %*d %*d %*d\n", &cpu_num);
@@ -1445,19 +1481,15 @@ void check_dev_msr()
 {
 	struct stat sb;
 
-	if (stat("/dev/cpu/0/msr", &sb)) {
-		fprintf(stderr, "no /dev/cpu/0/msr\n");
-		fprintf(stderr, "Try \"# modprobe msr\"\n");
-		exit(-5);
-	}
+	if (stat("/dev/cpu/0/msr", &sb))
+		err(-5, "no /dev/cpu/0/msr\n"
+		    "Try \"# modprobe msr\"");
 }
 
 void check_super_user()
 {
-	if (getuid() != 0) {
-		fprintf(stderr, "must be root\n");
-		exit(-6);
-	}
+	if (getuid() != 0)
+		errx(-6, "must be root");
 }
 
 int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
@@ -1479,7 +1511,7 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
 	case 0x3A:	/* IVB */
 	case 0x3E:	/* IVB Xeon */
 	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSW */
+	case 0x3F:	/* HSX */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
 	case 0x37:	/* BYT */
@@ -1595,11 +1627,13 @@ void rapl_probe(unsigned int family, unsigned int model)
 	case 0x2A:
 	case 0x3A:
 	case 0x3C:	/* HSW */
-	case 0x3F:	/* HSW */
 	case 0x45:	/* HSW */
 	case 0x46:	/* HSW */
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
 		break;
+	case 0x3F:	/* HSX */
+		do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
+		break;
 	case 0x2D:
 	case 0x3E:
 		do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_PKG_PERF_STATUS | RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO;
@@ -1978,7 +2012,7 @@ void check_cpuid()
 
 	eax = ebx = ecx = edx = 0;
 
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0));
+	__get_cpuid(0, &max_level, &ebx, &ecx, &edx);
 
 	if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e)
 		genuine_intel = 1;
@@ -1987,7 +2021,7 @@ void check_cpuid()
 		fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ",
 			(char *)&ebx, (char *)&edx, (char *)&ecx);
 
-	asm("cpuid" : "=a" (fms), "=c" (ecx), "=d" (edx) : "a" (1) : "ebx");
+	__get_cpuid(1, &fms, &ebx, &ecx, &edx);
 	family = (fms >> 8) & 0xf;
 	model = (fms >> 4) & 0xf;
 	stepping = fms & 0xf;
@@ -1998,10 +2032,8 @@ void check_cpuid()
 		fprintf(stderr, "%d CPUID levels; family:model:stepping 0x%x:%x:%x (%d:%d:%d)\n",
 			max_level, family, model, stepping, family, model, stepping);
 
-	if (!(edx & (1 << 5))) {
-		fprintf(stderr, "CPUID: no MSR\n");
-		exit(1);
-	}
+	if (!(edx & (1 << 5)))
+		errx(1, "CPUID: no MSR");
 
 	/*
 	 * check max extended function levels of CPUID.
@@ -2009,31 +2041,27 @@ void check_cpuid()
 	 * This check is valid for both Intel and AMD.
 	 */
 	ebx = ecx = edx = 0;
-	asm("cpuid" : "=a" (max_level), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000000));
+	__get_cpuid(0x80000000, &max_level, &ebx, &ecx, &edx);
 
-	if (max_level < 0x80000007) {
-		fprintf(stderr, "CPUID: no invariant TSC (max_level 0x%x)\n", max_level);
-		exit(1);
-	}
+	if (max_level < 0x80000007)
+		errx(1, "CPUID: no invariant TSC (max_level 0x%x)", max_level);
 
 	/*
 	 * Non-Stop TSC is advertised by CPUID.EAX=0x80000007: EDX.bit8
 	 * this check is valid for both Intel and AMD
 	 */
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x80000007));
+	__get_cpuid(0x80000007, &eax, &ebx, &ecx, &edx);
 	has_invariant_tsc = edx & (1 << 8);
 
-	if (!has_invariant_tsc) {
-		fprintf(stderr, "No invariant TSC\n");
-		exit(1);
-	}
+	if (!has_invariant_tsc)
+		errx(1, "No invariant TSC");
 
 	/*
 	 * APERF/MPERF is advertised by CPUID.EAX=0x6: ECX.bit0
 	 * this check is valid for both Intel and AMD
 	 */
 
-	asm("cpuid" : "=a" (eax), "=b" (ebx), "=c" (ecx), "=d" (edx) : "a" (0x6));
+	__get_cpuid(0x6, &eax, &ebx, &ecx, &edx);
 	has_aperf = ecx & (1 << 0);
 	do_dts = eax & (1 << 0);
 	do_ptm = eax & (1 << 6);
@@ -2047,7 +2075,7 @@ void check_cpuid()
 			has_epb ? ", EPB": "");
 
 	if (!has_aperf)
-		exit(-1);
+		errx(-1, "No APERF");
 
 	do_nehalem_platform_info = genuine_intel && has_invariant_tsc;
 	do_nhm_cstates = genuine_intel;	/* all Intel w/ non-stop TSC have NHM counters */
@@ -2067,9 +2095,8 @@ void check_cpuid()
 
 void usage()
 {
-	fprintf(stderr, "%s: [-v][-R][-T][-p|-P|-S][-c MSR# | -s]][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
-		progname);
-	exit(1);
+	errx(1, "%s: [-v][-R][-T][-p|-P|-S][-c MSR#][-C MSR#][-m MSR#][-M MSR#][-i interval_sec | command ...]\n",
+	     progname);
 }
 
 
@@ -2112,19 +2139,15 @@ void topology_probe()
 		fprintf(stderr, "num_cpus %d max_cpu_num %d\n", topo.num_cpus, topo.max_cpu_num);
 
 	cpus = calloc(1, (topo.max_cpu_num  + 1) * sizeof(struct cpu_topology));
-	if (cpus == NULL) {
-		perror("calloc cpus");
-		exit(1);
-	}
+	if (cpus == NULL)
+		err(1, "calloc cpus");
 
 	/*
 	 * Allocate and initialize cpu_present_set
 	 */
 	cpu_present_set = CPU_ALLOC((topo.max_cpu_num + 1));
-	if (cpu_present_set == NULL) {
-		perror("CPU_ALLOC");
-		exit(3);
-	}
+	if (cpu_present_set == NULL)
+		err(3, "CPU_ALLOC");
 	cpu_present_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
 	CPU_ZERO_S(cpu_present_setsize, cpu_present_set);
 	for_all_proc_cpus(mark_cpu_present);
@@ -2133,10 +2156,8 @@ void topology_probe()
 	 * Allocate and initialize cpu_affinity_set
 	 */
 	cpu_affinity_set = CPU_ALLOC((topo.max_cpu_num + 1));
-	if (cpu_affinity_set == NULL) {
-		perror("CPU_ALLOC");
-		exit(3);
-	}
+	if (cpu_affinity_set == NULL)
+		err(3, "CPU_ALLOC");
 	cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 
@@ -2220,8 +2241,7 @@ allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data
 
 	return;
 error:
-	perror("calloc counters");
-	exit(1);
+	err(1, "calloc counters");
 }
 /*
  * init_counter()
@@ -2276,12 +2296,10 @@ int initialize_counters(int cpu_id)
 
 void allocate_output_buffer()
 {
-	output_buffer = calloc(1, (1 + topo.num_cpus) * 256);
+	output_buffer = calloc(1, (1 + topo.num_cpus) * 1024);
 	outp = output_buffer;
-	if (outp == NULL) {
-		perror("calloc");
-		exit(-1);
-	}
+	if (outp == NULL)
+		err(-1, "calloc output buffer");
 }
 
 void setup_all_buffers(void)
@@ -2292,6 +2310,7 @@ void setup_all_buffers(void)
 	allocate_output_buffer();
 	for_all_proc_cpus(initialize_counters);
 }
+
 void turbostat_init()
 {
 	check_cpuid();
@@ -2335,17 +2354,13 @@ int fork_it(char **argv)
 	} else {
 
 		/* parent */
-		if (child_pid == -1) {
-			perror("fork");
-			exit(1);
-		}
+		if (child_pid == -1)
+			err(1, "fork");
 
 		signal(SIGINT, SIG_IGN);
 		signal(SIGQUIT, SIG_IGN);
-		if (waitpid(child_pid, &status, 0) == -1) {
-			perror("wait");
-			exit(status);
-		}
+		if (waitpid(child_pid, &status, 0) == -1)
+			err(status, "waitpid");
 	}
 	/*
 	 * n.b. fork_it() does not check for errors from for_all_cpus()
@@ -2364,13 +2379,30 @@ int fork_it(char **argv)
 	return status;
 }
 
+int get_and_dump_counters(void)
+{
+	int status;
+
+	status = for_all_cpus(get_counters, ODD_COUNTERS);
+	if (status)
+		return status;
+
+	status = for_all_cpus(dump_counters, ODD_COUNTERS);
+	if (status)
+		return status;
+
+	flush_stdout();
+
+	return status;
+}
+
 void cmdline(int argc, char **argv)
 {
 	int opt;
 
 	progname = argv[0];
 
-	while ((opt = getopt(argc, argv, "+pPSvi:sc:sC:m:M:RT:")) != -1) {
+	while ((opt = getopt(argc, argv, "+pPsSvi:c:C:m:M:RJT:")) != -1) {
 		switch (opt) {
 		case 'p':
 			show_core_only++;
@@ -2378,6 +2410,9 @@ void cmdline(int argc, char **argv)
 		case 'P':
 			show_pkg_only++;
 			break;
+		case 's':
+			dump_only++;
+			break;
 		case 'S':
 			summary_only++;
 			break;
@@ -2405,6 +2440,10 @@ void cmdline(int argc, char **argv)
 		case 'T':
 			tcc_activation_temp_override = atoi(optarg);
 			break;
+		case 'J':
+			rapl_joules++;
+			break;
+
 		default:
 			usage();
 		}
@@ -2416,11 +2455,15 @@ int main(int argc, char **argv)
 	cmdline(argc, argv);
 
 	if (verbose)
-		fprintf(stderr, "turbostat v3.5 April 26, 2013"
+		fprintf(stderr, "turbostat v3.6 Dec 2, 2013"
 			" - Len Brown <lenb@kernel.org>\n");
 
 	turbostat_init();
 
+	/* dump counters and exit */
+	if (dump_only)
+		return get_and_dump_counters();
+
 	/*
 	 * if any params left, it must be a command to fork
 	 */
author	Thomas Gleixner <tglx@linutronix.de>	2014-02-21 21:36:40 +0100
committer	Thomas Gleixner <tglx@linutronix.de>	2014-02-21 21:37:09 +0100
commit	d97a860c4f3de98ba5040a22f305b7159fe17cff (patch)
tree	90c2155ec5a1f3115a9eb7a86f25d1a4610227c6 /tools
parent	3f67d962c64d9b6de9dab81bdbe6d5c94c80d9b9 (diff)
parent	d158fc7f36a25e19791d25a55da5623399a2644f (diff)
download	op-kernel-dev-d97a860c4f3de98ba5040a22f305b7159fe17cff.zip op-kernel-dev-d97a860c4f3de98ba5040a22f305b7159fe17cff.tar.gz