25 files changed, 611 insertions, 41 deletions

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 5312fae47218..9269de254874 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 7da5e561e89a..cd28335b3d28 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"
 
@@ -5127,6 +5128,7 @@ struct perf_mmap_event {
         int                     maj, min;
         u64                     ino;
         u64                     ino_generation;
+        u32                     prot, flags;
 
         struct {
                 struct perf_event_header        header;
@@ -5168,6 +5170,8 @@ 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);
@@ -5186,6 +5190,8 @@ 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,
@@ -5204,6 +5210,7 @@ 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;
@@ -5234,6 +5241,28 @@ 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);
@@ -5274,6 +5303,8 @@ 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;
@@ -5314,6 +5345,8 @@ 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);
@@ -6896,10 +6929,6 @@ 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 b83184f2d484..93825a17dcce 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 feab94281634..7a3873ff9a4f 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 0c8bf6780e4d..136162c03af1 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 80ba4ff1fe84..a00ec190821a 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 cefdf430d1b4..d2b59af62bc0 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/Makefile.perf b/tools/perf/Makefile.perf
index ae20edfcc3f7..9670a16fa577 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 6a3af0013d68..16c7c11ad06e 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/perf.c b/tools/perf/perf.c
index 78f7b920e548..95c58fc15284 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/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 108f0cd49f4e..96adb730b744 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/util/event.c b/tools/perf/util/event.c
index 65795b835b39..d0281bdfa582 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 d970232cb270..9ba2eb3bdcfd 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -27,6 +27,8 @@ struct mmap2_event {
         u32 min;
         u64 ino;
         u64 ino_generation;
+        u32 prot;
+        u32 flags;
         char filename[PATH_MAX];
 };
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5c28d82b76c4..21154dabc5fa 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -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 5a0a4b2cadc4..30df6187ee02 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 d2bf03575d5f..742f49a85725 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 7409ac8de51c..0e5fea95d596 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 8ccbb32eda25..25c571f4cba6 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 ae2d45110588..7758c72522ef 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/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e108207c5de0..af7da565a750 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 cd9774df3750..1c419321f707 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 45512baaab67..1ec57dd82284 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 5bf0098d6b06..041f0c9cea2b 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/util.c b/tools/perf/util/util.c
index 7fff6be07f07..95aefa78bb07 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 b03da44e94e4..66864364ccb4 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);