Merge branch 'perf/core' into perf/urgent, to pick up the latest fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

39 files changed, 1242 insertions, 123 deletions

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 5312fae4721..9269de25487 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -705,6 +705,7 @@ enum perf_event_type {
 	 *	u32				min;
 	 *	u64				ino;
 	 *	u64				ino_generation;
+	 *	u32				prot, flags;
 	 *	char				filename[];
 	 * 	struct sample_id		sample_id;
 	 * };
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5fa58e4cffa..a33d9a2bcbd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -40,6 +40,7 @@
 #include <linux/mm_types.h>
 #include <linux/cgroup.h>
 #include <linux/module.h>
+#include <linux/mman.h>
 
 #include "internal.h"
 
@@ -5128,6 +5129,7 @@ struct perf_mmap_event {
 	int			maj, min;
 	u64			ino;
 	u64			ino_generation;
+	u32			prot, flags;
 
 	struct {
 		struct perf_event_header	header;
@@ -5169,6 +5171,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 		mmap_event->event_id.header.size += sizeof(mmap_event->min);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino);
 		mmap_event->event_id.header.size += sizeof(mmap_event->ino_generation);
+		mmap_event->event_id.header.size += sizeof(mmap_event->prot);
+		mmap_event->event_id.header.size += sizeof(mmap_event->flags);
 	}
 
 	perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
@@ -5187,6 +5191,8 @@ static void perf_event_mmap_output(struct perf_event *event,
 		perf_output_put(&handle, mmap_event->min);
 		perf_output_put(&handle, mmap_event->ino);
 		perf_output_put(&handle, mmap_event->ino_generation);
+		perf_output_put(&handle, mmap_event->prot);
+		perf_output_put(&handle, mmap_event->flags);
 	}
 
 	__output_copy(&handle, mmap_event->file_name,
@@ -5205,6 +5211,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	struct file *file = vma->vm_file;
 	int maj = 0, min = 0;
 	u64 ino = 0, gen = 0;
+	u32 prot = 0, flags = 0;
 	unsigned int size;
 	char tmp[16];
 	char *buf = NULL;
@@ -5235,6 +5242,28 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		gen = inode->i_generation;
 		maj = MAJOR(dev);
 		min = MINOR(dev);
+
+		if (vma->vm_flags & VM_READ)
+			prot |= PROT_READ;
+		if (vma->vm_flags & VM_WRITE)
+			prot |= PROT_WRITE;
+		if (vma->vm_flags & VM_EXEC)
+			prot |= PROT_EXEC;
+
+		if (vma->vm_flags & VM_MAYSHARE)
+			flags = MAP_SHARED;
+		else
+			flags = MAP_PRIVATE;
+
+		if (vma->vm_flags & VM_DENYWRITE)
+			flags |= MAP_DENYWRITE;
+		if (vma->vm_flags & VM_MAYEXEC)
+			flags |= MAP_EXECUTABLE;
+		if (vma->vm_flags & VM_LOCKED)
+			flags |= MAP_LOCKED;
+		if (vma->vm_flags & VM_HUGETLB)
+			flags |= MAP_HUGETLB;
+
 		goto got_name;
 	} else {
 		name = (char *)arch_vma_name(vma);
@@ -5275,6 +5304,8 @@ got_name:
 	mmap_event->min = min;
 	mmap_event->ino = ino;
 	mmap_event->ino_generation = gen;
+	mmap_event->prot = prot;
+	mmap_event->flags = flags;
 
 	if (!(vma->vm_flags & VM_EXEC))
 		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -5315,6 +5346,8 @@ void perf_event_mmap(struct vm_area_struct *vma)
 		/* .min (attr_mmap2 only) */
 		/* .ino (attr_mmap2 only) */
 		/* .ino_generation (attr_mmap2 only) */
+		/* .prot (attr_mmap2 only) */
+		/* .flags (attr_mmap2 only) */
 	};
 
 	perf_event_mmap_event(&mmap_event);
@@ -6897,10 +6930,6 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 	if (ret)
 		return -EFAULT;
 
-	/* disabled for now */
-	if (attr->mmap2)
-		return -EINVAL;
-
 	if (attr->__reserved_1)
 		return -EINVAL;
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index b83184f2d48..93825a17dcc 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -765,6 +765,9 @@ static void free_arg(struct print_arg *arg)
 	case PRINT_BSTRING:
 		free(arg->string.string);
 		break;
+	case PRINT_BITMASK:
+		free(arg->bitmask.bitmask);
+		break;
 	case PRINT_DYNAMIC_ARRAY:
 		free(arg->dynarray.index);
 		break;
@@ -2268,6 +2271,7 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
 	case PRINT_FIELD ... PRINT_SYMBOL:
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		ret = 0;
@@ -2296,6 +2300,7 @@ static char *arg_eval (struct print_arg *arg)
 	case PRINT_FIELD ... PRINT_SYMBOL:
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 	default:
 		do_warning("invalid eval type %d", arg->type);
 		break;
@@ -2683,6 +2688,35 @@ process_str(struct event_format *event __maybe_unused, struct print_arg *arg,
 	return EVENT_ERROR;
 }
 
+static enum event_type
+process_bitmask(struct event_format *event __maybe_unused, struct print_arg *arg,
+	    char **tok)
+{
+	enum event_type type;
+	char *token;
+
+	if (read_expect_type(EVENT_ITEM, &token) < 0)
+		goto out_free;
+
+	arg->type = PRINT_BITMASK;
+	arg->bitmask.bitmask = token;
+	arg->bitmask.offset = -1;
+
+	if (read_expected(EVENT_DELIM, ")") < 0)
+		goto out_err;
+
+	type = read_token(&token);
+	*tok = token;
+
+	return type;
+
+ out_free:
+	free_token(token);
+ out_err:
+	*tok = NULL;
+	return EVENT_ERROR;
+}
+
 static struct pevent_function_handler *
 find_func_handler(struct pevent *pevent, char *func_name)
 {
@@ -2797,6 +2831,10 @@ process_function(struct event_format *event, struct print_arg *arg,
 		free_token(token);
 		return process_str(event, arg, tok);
 	}
+	if (strcmp(token, "__get_bitmask") == 0) {
+		free_token(token);
+		return process_bitmask(event, arg, tok);
+	}
 	if (strcmp(token, "__get_dynamic_array") == 0) {
 		free_token(token);
 		return process_dynamic_array(event, arg, tok);
@@ -3324,6 +3362,7 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
 		return eval_type(val, arg, 0);
 	case PRINT_STRING:
 	case PRINT_BSTRING:
+	case PRINT_BITMASK:
 		return 0;
 	case PRINT_FUNC: {
 		struct trace_seq s;
@@ -3556,6 +3595,60 @@ static void print_str_to_seq(struct trace_seq *s, const char *format,
 		trace_seq_printf(s, format, str);
 }
 
+static void print_bitmask_to_seq(struct pevent *pevent,
+				 struct trace_seq *s, const char *format,
+				 int len_arg, const void *data, int size)
+{
+	int nr_bits = size * 8;
+	int str_size = (nr_bits + 3) / 4;
+	int len = 0;
+	char buf[3];
+	char *str;
+	int index;
+	int i;
+
+	/*
+	 * The kernel likes to put in commas every 32 bits, we
+	 * can do the same.
+	 */
+	str_size += (nr_bits - 1) / 32;
+
+	str = malloc(str_size + 1);
+	if (!str) {
+		do_warning("%s: not enough memory!", __func__);
+		return;
+	}
+	str[str_size] = 0;
+
+	/* Start out with -2 for the two chars per byte */
+	for (i = str_size - 2; i >= 0; i -= 2) {
+		/*
+		 * data points to a bit mask of size bytes.
+		 * In the kernel, this is an array of long words, thus
+		 * endianess is very important.
+		 */
+		if (pevent->file_bigendian)
+			index = size - (len + 1);
+		else
+			index = len;
+
+		snprintf(buf, 3, "%02x", *((unsigned char *)data + index));
+		memcpy(str + i, buf, 2);
+		len++;
+		if (!(len & 3) && i > 0) {
+			i--;
+			str[i] = ',';
+		}
+	}
+
+	if (len_arg >= 0)
+		trace_seq_printf(s, format, len_arg, str);
+	else
+		trace_seq_printf(s, format, str);
+
+	free(str);
+}
+
 static void print_str_arg(struct trace_seq *s, void *data, int size,
 			  struct event_format *event, const char *format,
 			  int len_arg, struct print_arg *arg)
@@ -3691,6 +3784,23 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	case PRINT_BSTRING:
 		print_str_to_seq(s, format, len_arg, arg->string.string);
 		break;
+	case PRINT_BITMASK: {
+		int bitmask_offset;
+		int bitmask_size;
+
+		if (arg->bitmask.offset == -1) {
+			struct format_field *f;
+
+			f = pevent_find_any_field(event, arg->bitmask.bitmask);
+			arg->bitmask.offset = f->offset;
+		}
+		bitmask_offset = data2host4(pevent, data + arg->bitmask.offset);
+		bitmask_size = bitmask_offset >> 16;
+		bitmask_offset &= 0xffff;
+		print_bitmask_to_seq(pevent, s, format, len_arg,
+				     data + bitmask_offset, bitmask_size);
+		break;
+	}
 	case PRINT_OP:
 		/*
 		 * The only op for string should be ? :
@@ -4822,6 +4932,9 @@ static void print_args(struct print_arg *args)
 	case PRINT_BSTRING:
 		printf("__get_str(%s)", args->string.string);
 		break;
+	case PRINT_BITMASK:
+		printf("__get_bitmask(%s)", args->bitmask.bitmask);
+		break;
 	case PRINT_TYPE:
 		printf("(%s)", args->typecast.type);
 		print_args(args->typecast.item);
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index feab9428163..7a3873ff9a4 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -107,8 +107,8 @@ typedef int (*pevent_event_handler_func)(struct trace_seq *s,
 typedef int (*pevent_plugin_load_func)(struct pevent *pevent);
 typedef int (*pevent_plugin_unload_func)(struct pevent *pevent);
 
-struct plugin_option {
-	struct plugin_option		*next;
+struct pevent_plugin_option {
+	struct pevent_plugin_option	*next;
 	void				*handle;
 	char				*file;
 	char				*name;
@@ -135,7 +135,7 @@ struct plugin_option {
  * PEVENT_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
  *
- *   struct plugin_option PEVENT_PLUGIN_OPTIONS[] = {
+ *   struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
  *	{
  *		.name = "option-name",
  *		.plugin_alias = "overide-file-name", (optional)
@@ -208,6 +208,11 @@ struct print_arg_string {
 	int			offset;
 };
 
+struct print_arg_bitmask {
+	char			*bitmask;
+	int			offset;
+};
+
 struct print_arg_field {
 	char			*name;
 	struct format_field	*field;
@@ -274,6 +279,7 @@ enum print_arg_type {
 	PRINT_DYNAMIC_ARRAY,
 	PRINT_OP,
 	PRINT_FUNC,
+	PRINT_BITMASK,
 };
 
 struct print_arg {
@@ -288,6 +294,7 @@ struct print_arg {
 		struct print_arg_hex		hex;
 		struct print_arg_func		func;
 		struct print_arg_string		string;
+		struct print_arg_bitmask	bitmask;
 		struct print_arg_op		op;
 		struct print_arg_dynarray	dynarray;
 	};
@@ -354,6 +361,8 @@ enum pevent_func_arg_type {
 
 enum pevent_flag {
 	PEVENT_NSEC_OUTPUT		= 1,	/* output in NSECS */
+	PEVENT_DISABLE_SYS_PLUGINS	= 1 << 1,
+	PEVENT_DISABLE_PLUGINS		= 1 << 2,
 };
 
 #define PEVENT_ERRORS 							      \
@@ -410,9 +419,19 @@ enum pevent_errno {
 
 struct plugin_list;
 
+#define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
+
 struct plugin_list *traceevent_load_plugins(struct pevent *pevent);
 void traceevent_unload_plugins(struct plugin_list *plugin_list,
 			       struct pevent *pevent);
+char **traceevent_plugin_list_options(void);
+void traceevent_plugin_free_options_list(char **list);
+int traceevent_plugin_add_options(const char *name,
+				  struct pevent_plugin_option *options);
+void traceevent_plugin_remove_options(struct pevent_plugin_option *options);
+void traceevent_print_plugins(struct trace_seq *s,
+			      const char *prefix, const char *suffix,
+			      const struct plugin_list *list);
 
 struct cmdline;
 struct cmdline_list;
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index 0c8bf6780e4..136162c03af 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -18,6 +18,7 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#include <stdio.h>
 #include <string.h>
 #include <dlfcn.h>
 #include <stdlib.h>
@@ -30,12 +31,207 @@
 
 #define LOCAL_PLUGIN_DIR ".traceevent/plugins"
 
+static struct registered_plugin_options {
+	struct registered_plugin_options	*next;
+	struct pevent_plugin_option		*options;
+} *registered_options;
+
+static struct trace_plugin_options {
+	struct trace_plugin_options	*next;
+	char				*plugin;
+	char				*option;
+	char				*value;
+} *trace_plugin_options;
+
 struct plugin_list {
 	struct plugin_list	*next;
 	char			*name;
 	void			*handle;
 };
 
+/**
+ * traceevent_plugin_list_options - get list of plugin options
+ *
+ * Returns an array of char strings that list the currently registered
+ * plugin options in the format of <plugin>:<option>. This list can be
+ * used by toggling the option.
+ *
+ * Returns NULL if there's no options registered. On error it returns
+ * INVALID_PLUGIN_LIST_OPTION
+ *
+ * Must be freed with traceevent_plugin_free_options_list().
+ */
+char **traceevent_plugin_list_options(void)
+{
+	struct registered_plugin_options *reg;
+	struct pevent_plugin_option *op;
+	char **list = NULL;
+	char *name;
+	int count = 0;
+
+	for (reg = registered_options; reg; reg = reg->next) {
+		for (op = reg->options; op->name; op++) {
+			char *alias = op->plugin_alias ? op->plugin_alias : op->file;
+			char **temp = list;
+
+			name = malloc(strlen(op->name) + strlen(alias) + 2);
+			if (!name)
+				goto err;
+
+			sprintf(name, "%s:%s", alias, op->name);
+			list = realloc(list, count + 2);
+			if (!list) {
+				list = temp;
+				free(name);
+				goto err;
+			}
+			list[count++] = name;
+			list[count] = NULL;
+		}
+	}
+	return list;
+
+ err:
+	while (--count >= 0)
+		free(list[count]);
+	free(list);
+
+	return INVALID_PLUGIN_LIST_OPTION;
+}
+
+void traceevent_plugin_free_options_list(char **list)
+{
+	int i;
+
+	if (!list)
+		return;
+
+	if (list == INVALID_PLUGIN_LIST_OPTION)
+		return;
+
+	for (i = 0; list[i]; i++)
+		free(list[i]);
+
+	free(list);
+}
+
+static int
+update_option(const char *file, struct pevent_plugin_option *option)
+{
+	struct trace_plugin_options *op;
+	char *plugin;
+
+	if (option->plugin_alias) {
+		plugin = strdup(option->plugin_alias);
+		if (!plugin)
+			return -1;
+	} else {
+		char *p;
+		plugin = strdup(file);
+		if (!plugin)
+			return -1;
+		p = strstr(plugin, ".");
+		if (p)
+			*p = '\0';
+	}
+
+	/* first look for named options */
+	for (op = trace_plugin_options; op; op = op->next) {
+		if (!op->plugin)
+			continue;
+		if (strcmp(op->plugin, plugin) != 0)
+			continue;
+		if (strcmp(op->option, option->name) != 0)
+			continue;
+
+		option->value = op->value;
+		option->set ^= 1;
+		goto out;
+	}
+
+	/* first look for unnamed options */
+	for (op = trace_plugin_options; op; op = op->next) {
+		if (op->plugin)
+			continue;
+		if (strcmp(op->option, option->name) != 0)
+			continue;
+
+		option->value = op->value;
+		option->set ^= 1;
+		break;
+	}
+
+ out:
+	free(plugin);
+	return 0;
+}
+
+/**
+ * traceevent_plugin_add_options - Add a set of options by a plugin
+ * @name: The name of the plugin adding the options
+ * @options: The set of options being loaded
+ *
+ * Sets the options with the values that have been added by user.
+ */
+int traceevent_plugin_add_options(const char *name,
+				  struct pevent_plugin_option *options)
+{
+	struct registered_plugin_options *reg;
+
+	reg = malloc(sizeof(*reg));
+	if (!reg)
+		return -1;
+	reg->next = registered_options;
+	reg->options = options;
+	registered_options = reg;
+
+	while (options->name) {
+		update_option(name, options);
+		options++;
+	}
+	return 0;
+}
+
+/**
+ * traceevent_plugin_remove_options - remove plugin options that were registered
+ * @options: Options to removed that were registered with traceevent_plugin_add_options
+ */
+void traceevent_plugin_remove_options(struct pevent_plugin_option *options)
+{
+	struct registered_plugin_options **last;
+	struct registered_plugin_options *reg;
+
+	for (last = &registered_options; *last; last = &(*last)->next) {
+		if ((*last)->options == options) {
+			reg = *last;
+			*last = reg->next;
+			free(reg);
+			return;
+		}
+	}
+}
+
+/**
+ * traceevent_print_plugins - print out the list of plugins loaded
+ * @s: the trace_seq descripter to write to
+ * @prefix: The prefix string to add before listing the option name
+ * @suffix: The suffix string ot append after the option name
+ * @list: The list of plugins (usually returned by traceevent_load_plugins()
+ *
+ * Writes to the trace_seq @s the list of plugins (files) that is
+ * returned by traceevent_load_plugins(). Use @prefix and @suffix for formating:
+ * @prefix = "  ", @suffix = "\n".
+ */
+void traceevent_print_plugins(struct trace_seq *s,
+			      const char *prefix, const char *suffix,
+			      const struct plugin_list *list)
+{
+	while (list) {
+		trace_seq_printf(s, "%s%s%s", prefix, list->name, suffix);
+		list = list->next;
+	}
+}
+
 static void
 load_plugin(struct pevent *pevent, const char *path,
 	    const char *file, void *data)
@@ -148,12 +344,17 @@ load_plugins(struct pevent *pevent, const char *suffix,
 	char *path;
 	char *envdir;
 
+	if (pevent->flags & PEVENT_DISABLE_PLUGINS)
+		return;
+
 	/*
 	 * If a system plugin directory was defined,
 	 * check that first.
 	 */
 #ifdef PLUGIN_DIR
-	load_plugins_dir(pevent, suffix, PLUGIN_DIR, load_plugin, data);
+	if (!(pevent->flags & PEVENT_DISABLE_SYS_PLUGINS))
+		load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+				 load_plugin, data);
 #endif
 
 	/*
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index 80ba4ff1fe8..a00ec190821 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -33,6 +33,29 @@ static int cpus = -1;
 
 #define STK_BLK 10
 
+struct pevent_plugin_option plugin_options[] =
+{
+	{
+		.name = "parent",
+		.plugin_alias = "ftrace",
+		.description =
+		"Print parent of functions for function events",
+	},
+	{
+		.name = "indent",
+		.plugin_alias = "ftrace",
+		.description =
+		"Try to show function call indents, based on parents",
+		.set = 1,
+	},
+	{
+		.name = NULL,
+	}
+};
+
+static struct pevent_plugin_option *ftrace_parent = &plugin_options[0];
+static struct pevent_plugin_option *ftrace_indent = &plugin_options[1];
+
 static void add_child(struct func_stack *stack, const char *child, int pos)
 {
 	int i;
@@ -119,7 +142,8 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 
 	parent = pevent_find_function(pevent, pfunction);
 
-	index = add_and_get_index(parent, func, record->cpu);
+	if (parent && ftrace_indent->set)
+		index = add_and_get_index(parent, func, record->cpu);
 
 	trace_seq_printf(s, "%*s", index*3, "");
 
@@ -128,11 +152,13 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 	else
 		trace_seq_printf(s, "0x%llx", function);
 
-	trace_seq_printf(s, " <-- ");
-	if (parent)
-		trace_seq_printf(s, "%s", parent);
-	else
-		trace_seq_printf(s, "0x%llx", pfunction);
+	if (ftrace_parent->set) {
+		trace_seq_printf(s, " <-- ");
+		if (parent)
+			trace_seq_printf(s, "%s", parent);
+		else
+			trace_seq_printf(s, "0x%llx", pfunction);
+	}
 
 	return 0;
 }
@@ -141,6 +167,9 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 {
 	pevent_register_event_handler(pevent, -1, "ftrace", "function",
 				      function_handler, NULL);
+
+	traceevent_plugin_add_options("ftrace", plugin_options);
+
 	return 0;
 }
 
@@ -157,6 +186,8 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 		free(fstack[i].stack);
 	}
 
+	traceevent_plugin_remove_options(plugin_options);
+
 	free(fstack);
 	fstack = NULL;
 	cpus = -1;
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index cefdf430d1b..d2b59af62bc 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,22 @@ OPTIONS
 	By default, every sort keys not specified in -F will be appended
 	automatically.
 
+	If --mem-mode option is used, following sort keys are also available
+	(incompatible with --branch-stack):
+	symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+	- symbol_daddr: name of data symbol being executed on at the time of sample
+	- dso_daddr: name of library or module containing the data being executed
+	on at the time of sample
+	- locked: whether the bus was locked at the time of sample
+	- tlb: type of tlb access for the data at the time of sample
+	- mem: type of memory access for the data at the time of sample
+	- snoop: type of snoop (if any) for the data at the time of sample
+	- dcacheline: the cacheline the data address is on at the time of sample
+
+	And default sort keys are changed to local_weight, mem, sym, dso,
+	symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -260,6 +276,13 @@ OPTIONS
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
 
+--mem-mode::
+	Use the data addresses of samples in addition to instruction addresses
+	to build the histograms.  To generate meaningful output, the perf.data
+	file must have been obtained using perf record -d -W and using a
+	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
+	'perf mem' for simpler access.
+
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index bc5990c33dc..5e0f986dff3 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -43,27 +43,6 @@ TIMECHART OPTIONS
 
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
-
-EXAMPLES
---------
-
-$ perf timechart record git pull
-
-  [ perf record: Woken up 13 times to write data ]
-  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
-
-$ perf timechart
-
-  Written 10.2 seconds of trace to output.svg.
-
-Record system-wide timechart:
-
-  $ perf timechart record
-
-  then generate timechart and highlight 'gcc' tasks:
-
-  $ perf timechart --highlight gcc
-
 -n::
 --proc-num::
         Print task info for at least given number of tasks.
@@ -88,6 +67,26 @@ RECORD OPTIONS
 --callchain::
         Do call-graph (stack chain/backtrace) recording
 
+EXAMPLES
+--------
+
+$ perf timechart record git pull
+
+  [ perf record: Woken up 13 times to write data ]
+  [ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
+
+$ perf timechart
+
+  Written 10.2 seconds of trace to output.svg.
+
+Record system-wide timechart:
+
+  $ perf timechart record
+
+  then generate timechart and highlight 'gcc' tasks:
+
+  $ perf timechart --highlight gcc
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ae20edfcc3f..9670a16fa57 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -819,15 +819,15 @@ TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol
 TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
-	$(RM) TAGS
+	$(QUIET_GEN)$(RM) TAGS; \
 	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
 
 tags:
-	$(RM) tags
+	$(QUIET_GEN)$(RM) tags; \
 	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
-	$(RM) cscope*
+	$(QUIET_GEN)$(RM) cscope*; \
 	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
 
 ### Detect prefix changes
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 6a3af0013d6..16c7c11ad06 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -72,7 +72,7 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	if (ret)
 		return ret;
 
-	if (&inject->output.is_pipe)
+	if (!inject->output.is_pipe)
 		return 0;
 
 	return perf_event__repipe_synth(tool, event);
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index cdcd4eb3a57..c63fa292507 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -288,6 +288,13 @@ static void cleanup_params(void)
 	memset(&params, 0, sizeof(params));
 }
 
+static void pr_err_with_code(const char *msg, int err)
+{
+	pr_err("%s", msg);
+	pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+	pr_err("\n");
+}
+
 static int
 __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -379,7 +386,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		ret = parse_probe_event_argv(argc, argv);
 		if (ret < 0) {
-			pr_err("  Error: Parse Error.  (%d)\n", ret);
+			pr_err_with_code("  Error: Command Parse Error.", ret);
 			return ret;
 		}
 	}
@@ -419,8 +426,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 		ret = show_perf_probe_events();
 		if (ret < 0)
-			pr_err("  Error: Failed to show event list. (%d)\n",
-			       ret);
+			pr_err_with_code("  Error: Failed to show event list.", ret);
 		return ret;
 	}
 	if (params.show_funcs) {
@@ -445,8 +451,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		strfilter__delete(params.filter);
 		params.filter = NULL;
 		if (ret < 0)
-			pr_err("  Error: Failed to show functions."
-			       " (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
 	}
 
@@ -464,7 +469,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 		ret = show_line_range(&params.line_range, params.target);
 		if (ret < 0)
-			pr_err("  Error: Failed to show lines. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show lines.", ret);
 		return ret;
 	}
 	if (params.show_vars) {
@@ -485,7 +490,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		strfilter__delete(params.filter);
 		params.filter = NULL;
 		if (ret < 0)
-			pr_err("  Error: Failed to show vars. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to show vars.", ret);
 		return ret;
 	}
 #endif
@@ -493,7 +498,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (params.dellist) {
 		ret = del_perf_probe_events(params.dellist);
 		if (ret < 0) {
-			pr_err("  Error: Failed to delete events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to delete events.", ret);
 			return ret;
 		}
 	}
@@ -504,7 +509,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 					    params.target,
 					    params.force_add);
 		if (ret < 0) {
-			pr_err("  Error: Failed to add events. (%d)\n", ret);
+			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
 	}
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 4f100b54ba8..f30ac5e5d27 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -299,7 +299,11 @@ else
       NO_LIBUNWIND := 1
       NO_LIBDW_DWARF_UNWIND := 1
     else
-      msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]/glibc-static);
+      ifneq ($(filter s% -static%,$(LDFLAGS),),)
+        msg := $(error No static glibc found, please install glibc-static);
+      else
+        msg := $(error No gnu/libc-version.h found, please install glibc-dev[el]);
+      endif
     endif
   else
     ifndef NO_LIBDW_DWARF_UNWIND
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 78f7b920e54..95c58fc1528 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -458,6 +458,7 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
+	cacheline_size = sysconf(_SC_LEVEL1_DCACHE_LINESIZE);
 
 	cmd = perf_extract_argv0_path(argv[0]);
 	if (!cmd)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 802e3cd50f6..6f8b01bc603 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -3,6 +3,8 @@
  *
  * Builtin regression testing command: ever growing number of sanity tests
  */
+#include <unistd.h>
+#include <string.h>
 #include "builtin.h"
 #include "intlist.h"
 #include "tests.h"
@@ -50,10 +52,18 @@ static struct test {
 		.func = test__pmu,
 	},
 	{
-		.desc = "Test dso data interface",
+		.desc = "Test dso data read",
 		.func = test__dso_data,
 	},
 	{
+		.desc = "Test dso data cache",
+		.func = test__dso_data_cache,
+	},
+	{
+		.desc = "Test dso data reopen",
+		.func = test__dso_data_reopen,
+	},
+	{
 		.desc = "roundtrip evsel->name check",
 		.func = test__perf_evsel__roundtrip_name_test,
 	},
@@ -172,6 +182,34 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
 	return false;
 }
 
+static int run_test(struct test *test)
+{
+	int status, err = -1, child = fork();
+
+	if (child < 0) {
+		pr_err("failed to fork test: %s\n", strerror(errno));
+		return -1;
+	}
+
+	if (!child) {
+		pr_debug("test child forked, pid %d\n", getpid());
+		err = test->func();
+		exit(err);
+	}
+
+	wait(&status);
+
+	if (WIFEXITED(status)) {
+		err = WEXITSTATUS(status);
+		pr_debug("test child finished with %d\n", err);
+	} else if (WIFSIGNALED(status)) {
+		err = -1;
+		pr_debug("test child interrupted\n");
+	}
+
+	return err;
+}
+
 static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 {
 	int i = 0;
@@ -200,7 +238,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 
 		pr_debug("\n--- start ---\n");
-		err = tests[curr].func();
+		err = run_test(&tests[curr]);
 		pr_debug("---- end ----\n%s:", tests[curr].desc);
 
 		switch (err) {
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 3e6cb171e3d..630808cd7cc 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -1,22 +1,27 @@
-#include "util.h"
-
 #include <stdlib.h>
 #include <linux/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <string.h>
-
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <api/fs/fs.h>
+#include "util.h"
 #include "machine.h"
 #include "symbol.h"
 #include "tests.h"
 
 static char *test_file(int size)
 {
-	static char buf_templ[] = "/tmp/test-XXXXXX";
+#define TEMPL "/tmp/perf-test-XXXXXX"
+	static char buf_templ[sizeof(TEMPL)];
 	char *templ = buf_templ;
 	int fd, i;
 	unsigned char *buf;
 
+	strcpy(buf_templ, TEMPL);
+#undef TEMPL
+
 	fd = mkstemp(templ);
 	if (fd < 0) {
 		perror("mkstemp failed");
@@ -150,3 +155,204 @@ int test__dso_data(void)
 	unlink(file);
 	return 0;
 }
+
+static long open_files_cnt(void)
+{
+	char path[PATH_MAX];
+	struct dirent *dent;
+	DIR *dir;
+	long nr = 0;
+
+	scnprintf(path, PATH_MAX, "%s/self/fd", procfs__mountpoint());
+	pr_debug("fd path: %s\n", path);
+
+	dir = opendir(path);
+	TEST_ASSERT_VAL("failed to open fd directory", dir);
+
+	while ((dent = readdir(dir)) != NULL) {
+		if (!strcmp(dent->d_name, ".") ||
+		    !strcmp(dent->d_name, ".."))
+			continue;
+
+		nr++;
+	}
+
+	closedir(dir);
+	return nr - 1;
+}
+
+static struct dso **dsos;
+
+static int dsos__create(int cnt, int size)
+{
+	int i;
+
+	dsos = malloc(sizeof(dsos) * cnt);
+	TEST_ASSERT_VAL("failed to alloc dsos array", dsos);
+
+	for (i = 0; i < cnt; i++) {
+		char *file;
+
+		file = test_file(size);
+		TEST_ASSERT_VAL("failed to get dso file", file);
+
+		dsos[i] = dso__new(file);
+		TEST_ASSERT_VAL("failed to get dso", dsos[i]);
+	}
+
+	return 0;
+}
+
+static void dsos__delete(int cnt)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		struct dso *dso = dsos[i];
+
+		unlink(dso->name);
+		dso__delete(dso);
+	}
+
+	free(dsos);
+}
+
+static int set_fd_limit(int n)
+{
+	struct rlimit rlim;
+
+	if (getrlimit(RLIMIT_NOFILE, &rlim))
+		return -1;
+
+	pr_debug("file limit %ld, new %d\n", (long) rlim.rlim_cur, n);
+
+	rlim.rlim_cur = n;
+	return setrlimit(RLIMIT_NOFILE, &rlim);
+}
+
+int test__dso_data_cache(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int dso_cnt, limit, i, fd;
+
+	memset(&machine, 0, sizeof(machine));
+
+	/* set as system limit */
+	limit = nr * 4;
+	TEST_ASSERT_VAL("failed to set file limit", !set_fd_limit(limit));
+
+	/* and this is now our dso open FDs limit + 1 extra */
+	dso_cnt = limit / 2 + 1;
+	TEST_ASSERT_VAL("failed to create dsos\n",
+		!dsos__create(dso_cnt, TEST_FILE_SIZE));
+
+	for (i = 0; i < (dso_cnt - 1); i++) {
+		struct dso *dso = dsos[i];
+
+		/*
+		 * Open dsos via dso__data_fd or dso__data_read_offset.
+		 * Both opens the data file and keep it open.
+		 */
+		if (i % 2) {
+			fd = dso__data_fd(dso, &machine);
+			TEST_ASSERT_VAL("failed to get fd", fd > 0);
+		} else {
+			#define BUFSIZE 10
+			u8 buf[BUFSIZE];
+			ssize_t n;
+
+			n = dso__data_read_offset(dso, &machine, 0, buf, BUFSIZE);
+			TEST_ASSERT_VAL("failed to read dso", n == BUFSIZE);
+		}
+	}
+
+	/* open +1 dso over the allowed limit */
+	fd = dso__data_fd(dsos[i], &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* should force the first one to be closed */
+	TEST_ASSERT_VAL("failed to close dsos[0]", dsos[0]->data.fd == -1);
+
+	/* cleanup everything */
+	dsos__delete(dso_cnt);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
+
+int test__dso_data_reopen(void)
+{
+	struct machine machine;
+	long nr_end, nr = open_files_cnt();
+	int fd, fd_extra;
+
+#define dso_0 (dsos[0])
+#define dso_1 (dsos[1])
+#define dso_2 (dsos[2])
+
+	memset(&machine, 0, sizeof(machine));
+
+	/*
+	 * Test scenario:
+	 * - create 3 dso objects
+	 * - set process file descriptor limit to current
+	 *   files count + 3
+	 * - test that the first dso gets closed when we
+	 *   reach the files count limit
+	 */
+
+	/* Make sure we are able to open 3 fds anyway */
+	TEST_ASSERT_VAL("failed to set file limit",
+			!set_fd_limit((nr + 3)));
+
+	TEST_ASSERT_VAL("failed to create dsos\n", !dsos__create(3, TEST_FILE_SIZE));
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/* open dso_1 */
+	fd = dso__data_fd(dso_1, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * open extra file descriptor and we just
+	 * reached the files count limit
+	 */
+	fd_extra = open("/dev/null", O_RDONLY);
+	TEST_ASSERT_VAL("failed to open extra fd", fd_extra > 0);
+
+	/* open dso_2 */
+	fd = dso__data_fd(dso_2, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_0 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_0", dso_0->data.fd == -1);
+
+	/* open dso_0 */
+	fd = dso__data_fd(dso_0, &machine);
+	TEST_ASSERT_VAL("failed to get fd", fd > 0);
+
+	/*
+	 * dso_1 should get closed, because we reached
+	 * the file descriptor limit
+	 */
+	TEST_ASSERT_VAL("failed to close dso_1", dso_1->data.fd == -1);
+
+	/* cleanup everything */
+	close(fd_extra);
+	dsos__delete(3);
+
+	/* Make sure we did not leak any file descriptor. */
+	nr_end = open_files_cnt();
+	pr_debug("nr start %ld, nr stop %ld\n", nr, nr_end);
+	TEST_ASSERT_VAL("failed leadking files", nr == nr_end);
+	return 0;
+}
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 108f0cd49f4..96adb730b74 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -15,7 +15,7 @@ static int mmap_handler(struct perf_tool *tool __maybe_unused,
 			struct perf_sample *sample __maybe_unused,
 			struct machine *machine)
 {
-	return machine__process_mmap_event(machine, event, NULL);
+	return machine__process_mmap2_event(machine, event, NULL);
 }
 
 static int init_live_machine(struct machine *machine)
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 2f92d6e7ee0..69a71ff84e0 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -205,8 +205,7 @@ $(run):
 	( eval $$cmd ) >> $@ 2>&1; \
 	echo "  test: $(call test,$@)" >> $@ 2>&1; \
 	$(call test,$@) && \
-	rm -f $@ \
-	rm -rf $$TMP_DEST
+	rm -rf $@ $$TMP_DEST || (cat $@ ; false)
 
 $(run_O):
 	$(call clean)
@@ -217,9 +216,7 @@ $(run_O):
 	( eval $$cmd ) >> $@ 2>&1 && \
 	echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
 	$(call test_O,$@) && \
-	rm -f $@ && \
-	rm -rf $$TMP_O \
-	rm -rf $$TMP_DEST
+	rm -rf $@ $$TMP_O $$TMP_DEST || (cat $@ ; false)
 
 tarpkg:
 	@cmd="$(PERF)/tests/perf-targz-src-pkg $(PERF)"; \
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 022bb68fd9c..ed64790a395 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -28,6 +28,8 @@ int test__syscall_open_tp_fields(void);
 int test__pmu(void);
 int test__attr(void);
 int test__dso_data(void);
+int test__dso_data_cache(void);
+int test__dso_data_reopen(void);
 int test__parse_events(void);
 int test__hists_link(void);
 int test__python_use(void);
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 64453d63b97..819f10414f0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1,3 +1,6 @@
+#include <asm/bug.h>
+#include <sys/time.h>
+#include <sys/resource.h>
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
@@ -136,7 +139,48 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
-static int open_dso(struct dso *dso, struct machine *machine)
+/*
+ * Global list of open DSOs and the counter.
+ */
+static LIST_HEAD(dso__data_open);
+static long dso__data_open_cnt;
+
+static void dso__list_add(struct dso *dso)
+{
+	list_add_tail(&dso->data.open_entry, &dso__data_open);
+	dso__data_open_cnt++;
+}
+
+static void dso__list_del(struct dso *dso)
+{
+	list_del(&dso->data.open_entry);
+	WARN_ONCE(dso__data_open_cnt <= 0,
+		  "DSO data fd counter out of bounds.");
+	dso__data_open_cnt--;
+}
+
+static void close_first_dso(void);
+
+static int do_open(char *name)
+{
+	int fd;
+
+	do {
+		fd = open(name, O_RDONLY);
+		if (fd >= 0)
+			return fd;
+
+		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		if (!dso__data_open_cnt || errno != EMFILE)
+			break;
+
+		close_first_dso();
+	} while (1);
+
+	return -1;
+}
+
+static int __open_dso(struct dso *dso, struct machine *machine)
 {
 	int fd;
 	char *root_dir = (char *)"";
@@ -154,11 +198,130 @@ static int open_dso(struct dso *dso, struct machine *machine)
 		return -EINVAL;
 	}
 
-	fd = open(name, O_RDONLY);
+	fd = do_open(name);
 	free(name);
 	return fd;
 }
 
+static void check_data_close(void);
+
+/**
+ * dso_close - Open DSO data file
+ * @dso: dso object
+ *
+ * Open @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static int open_dso(struct dso *dso, struct machine *machine)
+{
+	int fd = __open_dso(dso, machine);
+
+	if (fd > 0) {
+		dso__list_add(dso);
+		/*
+		 * Check if we crossed the allowed number
+		 * of opened DSOs and close one if needed.
+		 */
+		check_data_close();
+	}
+
+	return fd;
+}
+
+static void close_data_fd(struct dso *dso)
+{
+	if (dso->data.fd >= 0) {
+		close(dso->data.fd);
+		dso->data.fd = -1;
+		dso->data.file_size = 0;
+		dso__list_del(dso);
+	}
+}
+
+/**
+ * dso_close - Close DSO data file
+ * @dso: dso object
+ *
+ * Close @dso's data file descriptor and updates
+ * list/count of open DSO objects.
+ */
+static void close_dso(struct dso *dso)
+{
+	close_data_fd(dso);
+}
+
+static void close_first_dso(void)
+{
+	struct dso *dso;
+
+	dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
+	close_dso(dso);
+}
+
+static rlim_t get_fd_limit(void)
+{
+	struct rlimit l;
+	rlim_t limit = 0;
+
+	/* Allow half of the current open fd limit. */
+	if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
+		if (l.rlim_cur == RLIM_INFINITY)
+			limit = l.rlim_cur;
+		else
+			limit = l.rlim_cur / 2;
+	} else {
+		pr_err("failed to get fd limit\n");
+		limit = 1;
+	}
+
+	return limit;
+}
+
+static bool may_cache_fd(void)
+{
+	static rlim_t limit;
+
+	if (!limit)
+		limit = get_fd_limit();
+
+	if (limit == RLIM_INFINITY)
+		return true;
+
+	return limit > (rlim_t) dso__data_open_cnt;
+}
+
+/*
+ * Check and close LRU dso if we crossed allowed limit
+ * for opened dso file descriptors. The limit is half
+ * of the RLIMIT_NOFILE files opened.
+*/
+static void check_data_close(void)
+{
+	bool cache_fd = may_cache_fd();
+
+	if (!cache_fd)
+		close_first_dso();
+}
+
+/**
+ * dso__data_close - Close DSO data file
+ * @dso: dso object
+ *
+ * External interface to close @dso's data file descriptor.
+ */
+void dso__data_close(struct dso *dso)
+{
+	close_dso(dso);
+}
+
+/**
+ * dso__data_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.
+ */
 int dso__data_fd(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
@@ -168,8 +331,13 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND)
-		return open_dso(dso, machine);
+	if (dso->data.fd >= 0)
+		return dso->data.fd;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
+		dso->data.fd = open_dso(dso, machine);
+		return dso->data.fd;
+	}
 
 	do {
 		int fd;
@@ -178,7 +346,7 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 
 		fd = open_dso(dso, machine);
 		if (fd >= 0)
-			return fd;
+			return dso->data.fd = fd;
 
 	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
 
@@ -260,16 +428,10 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, struct machine *machine,
-		 u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 	ssize_t ret;
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return -1;
 
 	do {
 		u64 cache_offset;
@@ -283,16 +445,16 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 		ret = -EINVAL;
 
-		if (-1 == lseek(fd, cache_offset, SEEK_SET))
+		if (-1 == lseek(dso->data.fd, cache_offset, SEEK_SET))
 			break;
 
-		ret = read(fd, cache->data, DSO__DATA_CACHE_SIZE);
+		ret = read(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE);
 		if (ret <= 0)
 			break;
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->cache, cache);
+		dso_cache__insert(&dso->data.cache, cache);
 
 		ret = dso_cache__memcpy(cache, offset, data, size);
 
@@ -301,24 +463,27 @@ dso_cache__read(struct dso *dso, struct machine *machine,
 	if (ret <= 0)
 		free(cache);
 
-	close(fd);
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, u64 offset,
+			      u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->cache, offset);
+	cache = dso_cache__find(&dso->data.cache, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, machine, offset, data, size);
+		return dso_cache__read(dso, offset, data, size);
 }
 
-ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
-			      u64 offset, u8 *data, ssize_t size)
+/*
+ * Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
+ * in the rb_tree. Any read to already cached data is served
+ * by cached data.
+ */
+static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -326,7 +491,7 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, machine, offset, p, size);
+		ret = dso_cache_read(dso, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -346,6 +511,67 @@ ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 	return r;
 }
 
+static int data_file_size(struct dso *dso)
+{
+	struct stat st;
+
+	if (!dso->data.file_size) {
+		if (fstat(dso->data.fd, &st)) {
+			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			return -1;
+		}
+		dso->data.file_size = st.st_size;
+	}
+
+	return 0;
+}
+
+static ssize_t data_read_offset(struct dso *dso, u64 offset,
+				u8 *data, ssize_t size)
+{
+	if (data_file_size(dso))
+		return -1;
+
+	/* Check the offset sanity. */
+	if (offset > dso->data.file_size)
+		return -1;
+
+	if (offset + size < offset)
+		return -1;
+
+	return cached_read(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_offset - Read data from dso file offset
+ * @dso: dso object
+ * @machine: machine object
+ * @offset: file offset
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso file offset. Open
+ * dso data file and use cached_read to get the data.
+ */
+ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
+{
+	if (dso__data_fd(dso, machine) < 0)
+		return -1;
+
+	return data_read_offset(dso, offset, data, size);
+}
+
+/**
+ * dso__data_read_addr - Read data from dso address
+ * @dso: dso object
+ * @machine: machine object
+ * @add: virtual memory address
+ * @data: buffer to store data
+ * @size: size of the @data buffer
+ *
+ * External interface to read data from dso address.
+ */
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size)
@@ -473,7 +699,8 @@ struct dso *dso__new(const char *name)
 		dso__set_short_name(dso, dso->name, false);
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
-		dso->cache = RB_ROOT;
+		dso->data.cache = RB_ROOT;
+		dso->data.fd = -1;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->loaded = 0;
@@ -485,6 +712,7 @@ struct dso *dso__new(const char *name)
 		dso->kernel = DSO_TYPE_USER;
 		dso->needs_swap = DSO_SWAP__UNSET;
 		INIT_LIST_HEAD(&dso->node);
+		INIT_LIST_HEAD(&dso->data.open_entry);
 	}
 
 	return dso;
@@ -506,7 +734,8 @@ void dso__delete(struct dso *dso)
 		dso->long_name_allocated = false;
 	}
 
-	dso_cache__free(&dso->cache);
+	dso__data_close(dso);
+	dso_cache__free(&dso->data.cache);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
 	free(dso);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 38efe95a7fd..ad553ba257b 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -76,7 +76,6 @@ struct dso {
 	struct list_head node;
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
-	struct rb_root	 cache;
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
@@ -99,6 +98,15 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+
+	/* dso data file */
+	struct {
+		struct rb_root	 cache;
+		int		 fd;
+		size_t		 file_size;
+		struct list_head open_entry;
+	} data;
+
 	char		 name[0];
 };
 
@@ -141,7 +149,47 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 
+/*
+ * The dso__data_* external interface provides following functions:
+ *   dso__data_fd
+ *   dso__data_close
+ *   dso__data_read_offset
+ *   dso__data_read_addr
+ *
+ * Please refer to the dso.c object code for each function and
+ * arguments documentation. Following text tries to explain the
+ * dso file descriptor caching.
+ *
+ * The dso__data* interface allows caching of opened file descriptors
+ * to speed up the dso data accesses. The idea is to leave the file
+ * descriptor opened ideally for the whole life of the dso object.
+ *
+ * The current usage of the dso__data_* interface is as follows:
+ *
+ * Get DSO's fd:
+ *   int fd = dso__data_fd(dso, machine);
+ *   USE 'fd' SOMEHOW
+ *
+ * Read DSO's data:
+ *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
+ *   n = dso__data_read_addr(dso_0, &machine, 0, buf, BUFSIZE);
+ *
+ * Eventually close DSO's fd:
+ *   dso__data_close(dso);
+ *
+ * It is not necessary to close the DSO object data file. Each time new
+ * DSO data file is opened, the limit (RLIMIT_NOFILE/2) is checked. Once
+ * it is crossed, the oldest opened DSO object is closed.
+ *
+ * The dso__delete function calls close_dso function to ensure the
+ * data file descriptor gets closed/unmapped before the dso object
+ * is freed.
+ *
+ * TODO
+*/
 int dso__data_fd(struct dso *dso, struct machine *machine);
+void dso__data_close(struct dso *dso);
+
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size);
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 65795b835b3..d0281bdfa58 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,4 +1,5 @@
 #include <linux/types.h>
+#include <sys/mman.h>
 #include "event.h"
 #include "debug.h"
 #include "hist.h"
@@ -178,13 +179,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		return -1;
 	}
 
-	event->header.type = PERF_RECORD_MMAP;
+	event->header.type = PERF_RECORD_MMAP2;
 
 	while (1) {
 		char bf[BUFSIZ];
 		char prot[5];
 		char execname[PATH_MAX];
 		char anonstr[] = "//anon";
+		unsigned int ino;
 		size_t size;
 		ssize_t n;
 
@@ -195,15 +197,20 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		strcpy(execname, "");
 
 		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
-		       &event->mmap.start, &event->mmap.len, prot,
-		       &event->mmap.pgoff,
-		       execname);
+		n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+		       &event->mmap2.start, &event->mmap2.len, prot,
+		       &event->mmap2.pgoff, &event->mmap2.maj,
+		       &event->mmap2.min,
+		       &ino, execname);
+
 		/*
  		 * Anon maps don't have the execname.
  		 */
-		if (n < 4)
+		if (n < 7)
 			continue;
+
+		event->mmap2.ino = (u64)ino;
+
 		/*
 		 * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
 		 */
@@ -212,6 +219,21 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		else
 			event->header.misc = PERF_RECORD_MISC_GUEST_USER;
 
+		/* map protection and flags bits */
+		event->mmap2.prot = 0;
+		event->mmap2.flags = 0;
+		if (prot[0] == 'r')
+			event->mmap2.prot |= PROT_READ;
+		if (prot[1] == 'w')
+			event->mmap2.prot |= PROT_WRITE;
+		if (prot[2] == 'x')
+			event->mmap2.prot |= PROT_EXEC;
+
+		if (prot[3] == 's')
+			event->mmap2.flags |= MAP_SHARED;
+		else
+			event->mmap2.flags |= MAP_PRIVATE;
+
 		if (prot[2] != 'x') {
 			if (!mmap_data || prot[0] != 'r')
 				continue;
@@ -223,15 +245,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			strcpy(execname, anonstr);
 
 		size = strlen(execname) + 1;
-		memcpy(event->mmap.filename, execname, size);
+		memcpy(event->mmap2.filename, execname, size);
 		size = PERF_ALIGN(size, sizeof(u64));
-		event->mmap.len -= event->mmap.start;
-		event->mmap.header.size = (sizeof(event->mmap) -
-					(sizeof(event->mmap.filename) - size));
-		memset(event->mmap.filename + size, 0, machine->id_hdr_size);
-		event->mmap.header.size += machine->id_hdr_size;
-		event->mmap.pid = tgid;
-		event->mmap.tid = pid;
+		event->mmap2.len -= event->mmap.start;
+		event->mmap2.header.size = (sizeof(event->mmap2) -
+					(sizeof(event->mmap2.filename) - size));
+		memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+		event->mmap2.header.size += machine->id_hdr_size;
+		event->mmap2.pid = tgid;
+		event->mmap2.tid = pid;
 
 		if (process(tool, event, &synth_sample, machine) != 0) {
 			rc = -1;
@@ -612,12 +634,15 @@ size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64
-			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c %s\n",
+			   " %02x:%02x %"PRIu64" %"PRIu64"]: %c%c%c%c %s\n",
 		       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
 		       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
 		       event->mmap2.min, event->mmap2.ino,
 		       event->mmap2.ino_generation,
-		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+		       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+		       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+		       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
 		       event->mmap2.filename);
 }
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index d970232cb27..e5dd40addb3 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -7,6 +7,7 @@
 #include "../perf.h"
 #include "map.h"
 #include "build-id.h"
+#include "perf_regs.h"
 
 struct mmap_event {
 	struct perf_event_header header;
@@ -27,6 +28,8 @@ struct mmap2_event {
 	u32 min;
 	u64 ino;
 	u64 ino_generation;
+	u32 prot;
+	u32 flags;
 	char filename[PATH_MAX];
 };
 
@@ -87,6 +90,10 @@ struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
+
+	/* Cached values/mask filled by first register access. */
+	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_mask;
 };
 
 struct stack_dump {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5c28d82b76c..8606175fe1e 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -589,10 +589,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	}
 
 	/*
-	 * We default some events to a 1 default interval. But keep
+	 * We default some events to have a default interval. But keep
 	 * it a weak assumption overridable by the user.
 	 */
-	if (!attr->sample_period || (opts->user_freq != UINT_MAX &&
+	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
 				     opts->user_interval != ULLONG_MAX)) {
 		if (opts->freq) {
 			perf_evsel__set_sample_bit(evsel, PERIOD);
@@ -659,6 +659,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		perf_evsel__set_sample_bit(evsel, WEIGHT);
 
 	attr->mmap  = track;
+	attr->mmap2 = track && !perf_missing_features.mmap2;
 	attr->comm  = track;
 
 	if (opts->sample_transaction)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 5a0a4b2cadc..30df6187ee0 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -128,6 +128,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			       + unresolved_col_width + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
 					   symlen);
+			hists__new_col_len(hists, HISTC_MEM_DCACHELINE,
+					   symlen + 1);
 		} else {
 			symlen = unresolved_col_width + 4 + 2;
 			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
@@ -439,9 +441,10 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.map	= al->map,
 			.sym	= al->sym,
 		},
-		.cpu	= al->cpu,
-		.ip	= al->addr,
-		.level	= al->level,
+		.cpu	 = al->cpu,
+		.cpumode = al->cpumode,
+		.ip	 = al->addr,
+		.level	 = al->level,
 		.stat = {
 			.nr_events = 1,
 			.period	= period,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d2bf03575d5..742f49a8572 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -72,6 +72,7 @@ enum hist_column {
 	HISTC_MEM_TLB,
 	HISTC_MEM_LVL,
 	HISTC_MEM_SNOOP,
+	HISTC_MEM_DCACHELINE,
 	HISTC_TRANSACTION,
 	HISTC_NR_COLS, /* Last entry */
 };
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7409ac8de51..0e5fea95d59 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1060,6 +1060,8 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.pid, event->mmap2.maj,
 			event->mmap2.min, event->mmap2.ino,
 			event->mmap2.ino_generation,
+			event->mmap2.prot,
+			event->mmap2.flags,
 			event->mmap2.filename, type);
 
 	if (map == NULL)
@@ -1105,7 +1107,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 
 	map = map__new(&machine->user_dsos, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			event->mmap.pid, 0, 0, 0, 0,
+			event->mmap.pid, 0, 0, 0, 0, 0, 0,
 			event->mmap.filename,
 			type);
 
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8ccbb32eda2..25c571f4cba 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -138,7 +138,7 @@ void map__init(struct map *map, enum map_type type,
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen, char *filename,
+		     u64 ino_gen, u32 prot, u32 flags, char *filename,
 		     enum map_type type)
 {
 	struct map *map = malloc(sizeof(*map));
@@ -157,6 +157,8 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		map->min = d_min;
 		map->ino = ino;
 		map->ino_generation = ino_gen;
+		map->prot = prot;
+		map->flags = flags;
 
 		if ((anon || no_dso) && type == MAP__FUNCTION) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ae2d4511058..7758c72522e 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -35,6 +35,8 @@ struct map {
 	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
+	u32			prot;
+	u32			flags;
 	u64			pgoff;
 	u64			reloc;
 	u32			maj, min; /* only valid for MMAP2 record */
@@ -118,7 +120,7 @@ void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
-		     u64 ino_gen,
+		     u64 ino_gen, u32 prot, u32 flags,
 		     char *filename, enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index a3539ef30b1..43168fb0d9a 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,11 +1,15 @@
 #include <errno.h>
 #include "perf_regs.h"
+#include "event.h"
 
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if (regs->cache_mask & (1 << id))
+		goto out;
+
 	if (!(mask & (1 << id)))
 		return -EINVAL;
 
@@ -14,6 +18,10 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 			idx++;
 	}
 
-	*valp = regs->regs[idx];
+	regs->cache_mask |= (1 << id);
+	regs->cache_regs[id] = regs->regs[idx];
+
+out:
+	*valp = regs->cache_regs[id];
 	return 0;
 }
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index 79c78f74e0c..980dbf76bc9 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -2,7 +2,8 @@
 #define __PERF_REGS_H
 
 #include <linux/types.h>
-#include "event.h"
+
+struct regs_dump;
 
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
@@ -11,6 +12,7 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
 #else
 #define PERF_REGS_MASK	0
+#define PERF_REGS_MAX	0
 
 static inline const char *perf_reg_name(int id __maybe_unused)
 {
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 0d1542f33d8..9a0a1839a37 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -628,11 +628,11 @@ static int __show_line_range(struct line_range *lr, const char *module)
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	debuginfo__delete(dinfo);
-	if (ret == 0) {
+	if (ret == 0 || ret == -ENOENT) {
 		pr_warning("Specified source line is not found.\n");
 		return -ENOENT;
 	} else if (ret < 0) {
-		pr_warning("Debuginfo analysis failed. (%d)\n", ret);
+		pr_warning("Debuginfo analysis failed.\n");
 		return ret;
 	}
 
@@ -641,7 +641,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	ret = get_real_path(tmp, lr->comp_dir, &lr->path);
 	free(tmp);	/* Free old path */
 	if (ret < 0) {
-		pr_warning("Failed to find source file. (%d)\n", ret);
+		pr_warning("Failed to find source file path.\n");
 		return ret;
 	}
 
@@ -721,9 +721,14 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
 						max_vls, externs);
 	if (ret <= 0) {
-		pr_err("Failed to find variables at %s (%d)\n", buf, ret);
+		if (ret == 0 || ret == -ENOENT) {
+			pr_err("Failed to find the address of %s\n", buf);
+			ret = -ENOENT;
+		} else
+			pr_warning("Debuginfo analysis failed.\n");
 		goto end;
 	}
+
 	/* Some variables are found */
 	fprintf(stdout, "Available variables at %s\n", buf);
 	for (i = 0; i < ret; i++) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 9d8eb26f053..98e30476641 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -573,14 +573,13 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
 		/* Search again in global variables */
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+			pr_warning("Failed to find '%s' in this function.\n",
+				   pf->pvar->var);
 			ret = -ENOENT;
 	}
 	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
-	if (ret < 0)
-		pr_warning("Failed to find '%s' in this function.\n",
-			   pf->pvar->var);
 	return ret;
 }
 
@@ -1281,7 +1280,11 @@ out:
 	return ret;
 }
 
-/* Find available variables at given probe point */
+/*
+ * Find available variables at given probe point
+ * Return the number of found probe points. Return 0 if there is no
+ * matched probe point. Return <0 if an error occurs.
+ */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
 				      struct variable_list **vls,
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e108207c5de..af7da565a75 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -215,6 +215,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_STRING:
+	case PRINT_BITMASK:
 		break;
 	case PRINT_TYPE:
 		define_event_symbols(event, ev_name, args->typecast.item);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cd9774df375..1c419321f70 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -197,6 +197,7 @@ static void define_event_symbols(struct event_format *event,
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
 	case PRINT_FUNC:
+	case PRINT_BITMASK:
 		/* we should warn... */
 		return;
 	}
@@ -622,6 +623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			fprintf(ofp, "%s=", f->name);
 			if (f->flags & FIELD_IS_STRING ||
 			    f->flags & FIELD_IS_FLAG ||
+			    f->flags & FIELD_IS_ARRAY ||
 			    f->flags & FIELD_IS_SYMBOLIC)
 				fprintf(ofp, "%%s");
 			else if (f->flags & FIELD_IS_SIGNED)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 45512baaab6..1ec57dd8228 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1,3 +1,4 @@
+#include <sys/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -784,6 +785,104 @@ static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
+static inline  u64 cl_address(u64 address)
+{
+	/* return the cacheline of the address */
+	return (address & ~(cacheline_size - 1));
+}
+
+static int64_t
+sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	u64 l, r;
+	struct map *l_map, *r_map;
+
+	if (!left->mem_info)  return -1;
+	if (!right->mem_info) return 1;
+
+	/* group event types together */
+	if (left->cpumode > right->cpumode) return -1;
+	if (left->cpumode < right->cpumode) return 1;
+
+	l_map = left->mem_info->daddr.map;
+	r_map = right->mem_info->daddr.map;
+
+	/* if both are NULL, jump to sort on al_addr instead */
+	if (!l_map && !r_map)
+		goto addr;
+
+	if (!l_map) return -1;
+	if (!r_map) return 1;
+
+	if (l_map->maj > r_map->maj) return -1;
+	if (l_map->maj < r_map->maj) return 1;
+
+	if (l_map->min > r_map->min) return -1;
+	if (l_map->min < r_map->min) return 1;
+
+	if (l_map->ino > r_map->ino) return -1;
+	if (l_map->ino < r_map->ino) return 1;
+
+	if (l_map->ino_generation > r_map->ino_generation) return -1;
+	if (l_map->ino_generation < r_map->ino_generation) return 1;
+
+	/*
+	 * Addresses with no major/minor numbers are assumed to be
+	 * anonymous in userspace.  Sort those on pid then address.
+	 *
+	 * The kernel and non-zero major/minor mapped areas are
+	 * assumed to be unity mapped.  Sort those on address.
+	 */
+
+	if ((left->cpumode != PERF_RECORD_MISC_KERNEL) &&
+	    (!(l_map->flags & MAP_SHARED)) &&
+	    !l_map->maj && !l_map->min && !l_map->ino &&
+	    !l_map->ino_generation) {
+		/* userspace anonymous */
+
+		if (left->thread->pid_ > right->thread->pid_) return -1;
+		if (left->thread->pid_ < right->thread->pid_) return 1;
+	}
+
+addr:
+	/* al_addr does all the right addr - start + offset calculations */
+	l = cl_address(left->mem_info->daddr.al_addr);
+	r = cl_address(right->mem_info->daddr.al_addr);
+
+	if (l > r) return -1;
+	if (l < r) return 1;
+
+	return 0;
+}
+
+static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
+					  size_t size, unsigned int width)
+{
+
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+	char level = he->level;
+
+	if (he->mem_info) {
+		addr = cl_address(he->mem_info->daddr.al_addr);
+		map = he->mem_info->daddr.map;
+		sym = he->mem_info->daddr.sym;
+
+		/* print [s] for shared data mmaps */
+		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
+		     map && (map->type == MAP__VARIABLE) &&
+		    (map->flags & MAP_SHARED) &&
+		    (map->maj || map->min || map->ino ||
+		     map->ino_generation))
+			level = 's';
+		else if (!map)
+			level = 'X';
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, level, bf, size,
+					 width);
+}
+
 struct sort_entry sort_mispredict = {
 	.se_header	= "Branch Mispredicted",
 	.se_cmp		= sort__mispredict_cmp,
@@ -876,6 +975,13 @@ struct sort_entry sort_mem_snoop = {
 	.se_width_idx	= HISTC_MEM_SNOOP,
 };
 
+struct sort_entry sort_mem_dcacheline = {
+	.se_header	= "Data Cacheline",
+	.se_cmp		= sort__dcacheline_cmp,
+	.se_snprintf	= hist_entry__dcacheline_snprintf,
+	.se_width_idx	= HISTC_MEM_DCACHELINE,
+};
+
 static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1043,6 +1149,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
 	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
 	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
 	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
+	DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 5bf0098d6b0..041f0c9cea2 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -89,6 +89,7 @@ struct hist_entry {
 	u64			ip;
 	u64			transaction;
 	s32			cpu;
+	u8			cpumode;
 
 	struct hist_entry_diff	diff;
 
@@ -185,6 +186,7 @@ enum sort_type {
 	SORT_MEM_TLB,
 	SORT_MEM_LVL,
 	SORT_MEM_SNOOP,
+	SORT_MEM_DCACHELINE,
 };
 
 /*
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index bd5768d74f0..25578b98f5c 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -250,7 +250,6 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 
 	/* Check the .eh_frame section for unwinding info */
 	offset = elf_section_offset(fd, ".eh_frame_hdr");
-	close(fd);
 
 	if (offset)
 		ret = unwind_spec_ehframe(dso, machine, offset,
@@ -271,7 +270,6 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 
 	/* Check the .debug_frame section for unwinding info */
 	*offset = elf_section_offset(fd, ".debug_frame");
-	close(fd);
 
 	if (*offset)
 		return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7fff6be07f0..95aefa78bb0 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -17,6 +17,7 @@
  * XXX We need to find a better place for these things...
  */
 unsigned int page_size;
+int cacheline_size;
 
 bool test_attr__enabled;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b03da44e94e..66864364ccb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -304,6 +304,7 @@ char *rtrim(char *s);
 void dump_stack(void);
 
 extern unsigned int page_size;
+extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);