49 files changed, 1808 insertions, 292 deletions

diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 56ad4f5287de..112d6e268150 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -3,7 +3,7 @@
 
 #include <stdbool.h>
 #include <stdint.h>
-#include "types.h"
+#include <linux/types.h>
 #include "symbol.h"
 #include "hist.h"
 #include "sort.h"
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6baabe63182b..a904a4cfe7d3 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -25,7 +25,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
         struct addr_location al;
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
         struct thread *thread = machine__findnew_thread(machine, sample->pid,
-                                                        sample->pid);
+                                                        sample->tid);
 
         if (thread == NULL) {
                 pr_err("problem processing %d event, skipping it.\n",
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 845ef865eced..ae392561470b 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -4,7 +4,7 @@
 #define BUILD_ID_SIZE 20
 
 #include "tool.h"
-#include "types.h"
+#include <linux/types.h>
 
 extern struct perf_tool build_id__mark_dso_hit_ops;
 struct dso;
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8d9db454f1a9..48b6d3f50012 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -25,6 +25,84 @@
 
 __thread struct callchain_cursor callchain_cursor;
 
+int
+parse_callchain_report_opt(const char *arg)
+{
+        char *tok, *tok2;
+        char *endptr;
+
+        symbol_conf.use_callchain = true;
+
+        if (!arg)
+                return 0;
+
+        tok = strtok((char *)arg, ",");
+        if (!tok)
+                return -1;
+
+        /* get the output mode */
+        if (!strncmp(tok, "graph", strlen(arg))) {
+                callchain_param.mode = CHAIN_GRAPH_ABS;
+
+        } else if (!strncmp(tok, "flat", strlen(arg))) {
+                callchain_param.mode = CHAIN_FLAT;
+        } else if (!strncmp(tok, "fractal", strlen(arg))) {
+                callchain_param.mode = CHAIN_GRAPH_REL;
+        } else if (!strncmp(tok, "none", strlen(arg))) {
+                callchain_param.mode = CHAIN_NONE;
+                symbol_conf.use_callchain = false;
+                return 0;
+        } else {
+                return -1;
+        }
+
+        /* get the min percentage */
+        tok = strtok(NULL, ",");
+        if (!tok)
+                goto setup;
+
+        callchain_param.min_percent = strtod(tok, &endptr);
+        if (tok == endptr)
+                return -1;
+
+        /* get the print limit */
+        tok2 = strtok(NULL, ",");
+        if (!tok2)
+                goto setup;
+
+        if (tok2[0] != 'c') {
+                callchain_param.print_limit = strtoul(tok2, &endptr, 0);
+                tok2 = strtok(NULL, ",");
+                if (!tok2)
+                        goto setup;
+        }
+
+        /* get the call chain order */
+        if (!strncmp(tok2, "caller", strlen("caller")))
+                callchain_param.order = ORDER_CALLER;
+        else if (!strncmp(tok2, "callee", strlen("callee")))
+                callchain_param.order = ORDER_CALLEE;
+        else
+                return -1;
+
+        /* Get the sort key */
+        tok2 = strtok(NULL, ",");
+        if (!tok2)
+                goto setup;
+        if (!strncmp(tok2, "function", strlen("function")))
+                callchain_param.key = CCKEY_FUNCTION;
+        else if (!strncmp(tok2, "address", strlen("address")))
+                callchain_param.key = CCKEY_ADDRESS;
+        else
+                return -1;
+setup:
+        if (callchain_register_param(&callchain_param) < 0) {
+                pr_err("Can't register callchain params\n");
+                return -1;
+        }
+        return 0;
+}
+
 static void
 rb_insert_callchain(struct rb_root *root, struct callchain_node *chain,
                     enum chain_mode mode)
@@ -538,7 +616,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
         if (sample->callchain == NULL)
                 return 0;
 
-        if (symbol_conf.use_callchain || sort__has_parent) {
+        if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
+            sort__has_parent) {
                 return machine__resolve_callchain(al->machine, evsel, al->thread,
                                                   sample, parent, al, max_stack);
         }
@@ -551,3 +630,45 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
                 return 0;
         return callchain_append(he->callchain, &callchain_cursor, sample->period);
 }
+
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+                        bool hide_unresolved)
+{
+        al->map = node->map;
+        al->sym = node->sym;
+        if (node->map)
+                al->addr = node->map->map_ip(node->map, node->ip);
+        else
+                al->addr = node->ip;
+
+        if (al->sym == NULL) {
+                if (hide_unresolved)
+                        return 0;
+                if (al->map == NULL)
+                        goto out;
+        }
+
+        if (al->map->groups == &al->machine->kmaps) {
+                if (machine__is_host(al->machine)) {
+                        al->cpumode = PERF_RECORD_MISC_KERNEL;
+                        al->level = 'k';
+                } else {
+                        al->cpumode = PERF_RECORD_MISC_GUEST_KERNEL;
+                        al->level = 'g';
+                }
+        } else {
+                if (machine__is_host(al->machine)) {
+                        al->cpumode = PERF_RECORD_MISC_USER;
+                        al->level = '.';
+                } else if (perf_guest) {
+                        al->cpumode = PERF_RECORD_MISC_GUEST_USER;
+                        al->level = 'u';
+                } else {
+                        al->cpumode = PERF_RECORD_MISC_HYPERVISOR;
+                        al->level = 'H';
+                }
+        }
+
+out:
+        return 1;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8ad97e9b119f..8f84423a75da 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -7,6 +7,13 @@
 #include "event.h"
 #include "symbol.h"
 
+enum perf_call_graph_mode {
+        CALLCHAIN_NONE,
+        CALLCHAIN_FP,
+        CALLCHAIN_DWARF,
+        CALLCHAIN_MAX
+};
+
 enum chain_mode {
         CHAIN_NONE,
         CHAIN_FLAT,
@@ -155,6 +162,18 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
                               struct perf_evsel *evsel, struct addr_location *al,
                               int max_stack);
 int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *sample);
+int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+                        bool hide_unresolved);
 
 extern const char record_callchain_help[];
+int parse_callchain_report_opt(const char *arg);
+
+static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
+                                             struct callchain_cursor *src)
+{
+        *dest = *src;
+
+        dest->first = src->curr;
+        dest->nr -= src->pos;
+}
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3e0fdd369ccb..24519e14ac56 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -11,6 +11,7 @@
 #include "util.h"
 #include "cache.h"
 #include "exec_cmd.h"
+#include "util/hist.h"  /* perf_hist_config */
 
 #define MAXNAME (256)
 
@@ -355,6 +356,9 @@ int perf_default_config(const char *var, const char *value,
         if (!prefixcmp(var, "core."))
                 return perf_default_core_config(var, value);
 
+        if (!prefixcmp(var, "hist."))
+                return perf_hist_config(var, value);
+
         /* Add other config variables here. */
         return 0;
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 7fe4994eeb63..c4e55b71010c 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -317,3 +317,163 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
 {
         return cpu_map__build_map(cpus, corep, cpu_map__get_core);
 }
+
+/* setup simple routines to easily access node numbers given a cpu number */
+static int get_max_num(char *path, int *max)
+{
+        size_t num;
+        char *buf;
+        int err = 0;
+
+        if (filename__read_str(path, &buf, &num))
+                return -1;
+
+        buf[num] = '\0';
+
+        /* start on the right, to find highest node num */
+        while (--num) {
+                if ((buf[num] == ',') || (buf[num] == '-')) {
+                        num++;
+                        break;
+                }
+        }
+        if (sscanf(&buf[num], "%d", max) < 1) {
+                err = -1;
+                goto out;
+        }
+
+        /* convert from 0-based to 1-based */
+        (*max)++;
+
+out:
+        free(buf);
+        return err;
+}
+
+/* Determine highest possible cpu in the system for sparse allocation */
+static void set_max_cpu_num(void)
+{
+        const char *mnt;
+        char path[PATH_MAX];
+        int ret = -1;
+
+        /* set up default */
+        max_cpu_num = 4096;
+
+        mnt = sysfs__mountpoint();
+        if (!mnt)
+                goto out;
+
+        /* get the highest possible cpu number for a sparse allocation */
+        ret = snprintf(path, PATH_MAX, "%s/devices/system/cpu/possible", mnt);
+        if (ret == PATH_MAX) {
+                pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+                goto out;
+        }
+
+        ret = get_max_num(path, &max_cpu_num);
+
+out:
+        if (ret)
+                pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
+}
+
+/* Determine highest possible node in the system for sparse allocation */
+static void set_max_node_num(void)
+{
+        const char *mnt;
+        char path[PATH_MAX];
+        int ret = -1;
+
+        /* set up default */
+        max_node_num = 8;
+
+        mnt = sysfs__mountpoint();
+        if (!mnt)
+                goto out;
+
+        /* get the highest possible cpu number for a sparse allocation */
+        ret = snprintf(path, PATH_MAX, "%s/devices/system/node/possible", mnt);
+        if (ret == PATH_MAX) {
+                pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+                goto out;
+        }
+
+        ret = get_max_num(path, &max_node_num);
+
+out:
+        if (ret)
+                pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
+}
+
+static int init_cpunode_map(void)
+{
+        int i;
+
+        set_max_cpu_num();
+        set_max_node_num();
+
+        cpunode_map = calloc(max_cpu_num, sizeof(int));
+        if (!cpunode_map) {
+                pr_err("%s: calloc failed\n", __func__);
+                return -1;
+        }
+
+        for (i = 0; i < max_cpu_num; i++)
+                cpunode_map[i] = -1;
+
+        return 0;
+}
+
+int cpu__setup_cpunode_map(void)
+{
+        struct dirent *dent1, *dent2;
+        DIR *dir1, *dir2;
+        unsigned int cpu, mem;
+        char buf[PATH_MAX];
+        char path[PATH_MAX];
+        const char *mnt;
+        int n;
+
+        /* initialize globals */
+        if (init_cpunode_map())
+                return -1;
+
+        mnt = sysfs__mountpoint();
+        if (!mnt)
+                return 0;
+
+        n = snprintf(path, PATH_MAX, "%s/devices/system/node", mnt);
+        if (n == PATH_MAX) {
+                pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+                return -1;
+        }
+
+        dir1 = opendir(path);
+        if (!dir1)
+                return 0;
+
+        /* walk tree and setup map */
+        while ((dent1 = readdir(dir1)) != NULL) {
+                if (dent1->d_type != DT_DIR || sscanf(dent1->d_name, "node%u", &mem) < 1)
+                        continue;
+
+                n = snprintf(buf, PATH_MAX, "%s/%s", path, dent1->d_name);
+                if (n == PATH_MAX) {
+                        pr_err("sysfs path crossed PATH_MAX(%d) size\n", PATH_MAX);
+                        continue;
+                }
+
+                dir2 = opendir(buf);
+                if (!dir2)
+                        continue;
+                while ((dent2 = readdir(dir2)) != NULL) {
+                        if (dent2->d_type != DT_LNK || sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
+                                continue;
+                        cpunode_map[cpu] = mem;
+                }
+                closedir(dir2);
+        }
+        closedir(dir1);
+        return 0;
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index b123bb9d6f55..61a654849002 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -4,6 +4,9 @@
 #include <stdio.h>
 #include <stdbool.h>
 
+#include "perf.h"
+#include "util/debug.h"
+
 struct cpu_map {
         int nr;
         int map[];
@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
         return map ? map->map[0] == -1 : true;
 }
 
+int max_cpu_num;
+int max_node_num;
+int *cpunode_map;
+
+int cpu__setup_cpunode_map(void);
+
+static inline int cpu__max_node(void)
+{
+        if (unlikely(!max_node_num))
+                pr_debug("cpu_map not initialized\n");
+
+        return max_node_num;
+}
+
+static inline int cpu__max_cpu(void)
+{
+        if (unlikely(!max_cpu_num))
+                pr_debug("cpu_map not initialized\n");
+
+        return max_cpu_num;
+}
+
+static inline int cpu__get_node(int cpu)
+{
+        if (unlikely(cpunode_map == NULL)) {
+                pr_debug("cpu_map not initialized\n");
+                return -1;
+        }
+
+        return cpunode_map[cpu];
+}
+
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 1fbcd8bdc11b..55de44ecebef 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -86,10 +86,17 @@ static int open_file_read(struct perf_data_file *file)
 
 static int open_file_write(struct perf_data_file *file)
 {
+        int fd;
+
         if (check_backup(file))
                 return -1;
 
-        return open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+        fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
+
+        if (fd < 0)
+                pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+
+        return fd;
 }
 
 static int open_file(struct perf_data_file *file)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ab06f1c03655..38efe95a7fdd 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
 #include "map.h"
 #include "build-id.h"
 
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 7defd77105d0..cc66c4049e09 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -747,14 +747,17 @@ struct __find_variable_param {
 static int __die_find_variable_cb(Dwarf_Die *die_mem, void *data)
 {
         struct __find_variable_param *fvp = data;
+        Dwarf_Attribute attr;
         int tag;
 
         tag = dwarf_tag(die_mem);
         if ((tag == DW_TAG_formal_parameter ||
              tag == DW_TAG_variable) &&
-            die_compare_name(die_mem, fvp->name))
+            die_compare_name(die_mem, fvp->name) &&
+        /* Does the DIE have location information or external instance? */
+            (dwarf_attr(die_mem, DW_AT_external, &attr) ||
+             dwarf_attr(die_mem, DW_AT_location, &attr)))
                 return DIE_FIND_CB_END;
-
         if (dwarf_haspc(die_mem, fvp->addr))
                 return DIE_FIND_CB_CONTINUE;
         else
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9d12aa6dd485..65795b835b39 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -699,7 +699,7 @@ void thread__find_addr_map(struct thread *thread,
                            enum map_type type, u64 addr,
                            struct addr_location *al)
 {
-        struct map_groups *mg = &thread->mg;
+        struct map_groups *mg = thread->mg;
         bool load_map = false;
 
         al->machine = machine;
@@ -788,7 +788,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 {
         u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
         struct thread *thread = machine__findnew_thread(machine, sample->pid,
-                                                        sample->pid);
+                                                        sample->tid);
 
         if (thread == NULL)
                 return -1;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 38457d447a13..d970232cb270 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -112,6 +112,30 @@ struct sample_read {
         };
 };
 
+struct ip_callchain {
+        u64 nr;
+        u64 ips[0];
+};
+
+struct branch_flags {
+        u64 mispred:1;
+        u64 predicted:1;
+        u64 in_tx:1;
+        u64 abort:1;
+        u64 reserved:60;
+};
+
+struct branch_entry {
+        u64                     from;
+        u64                     to;
+        struct branch_flags     flags;
+};
+
+struct branch_stack {
+        u64                     nr;
+        struct branch_entry     entries[0];
+};
+
 struct perf_sample {
         u64 ip;
         u32 pid, tid;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0c9926cfb292..a52e9a5bb2d0 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -5,12 +5,12 @@
 #include <stdbool.h>
 #include <stddef.h>
 #include <linux/perf_event.h>
-#include "types.h"
+#include <linux/types.h>
 #include "xyarray.h"
 #include "cgroup.h"
 #include "hist.h"
 #include "symbol.h"
- 
+
 struct perf_counts_values {
         union {
                 struct {
@@ -91,6 +91,11 @@ struct perf_evsel {
         char                    *group_name;
 };
 
+union u64_swap {
+        u64 val64;
+        u32 val32[2];
+};
+
 #define hists_to_evsel(h) container_of(h, struct perf_evsel, hists)
 
 struct cpu_map;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index a2d047bdf4ef..d08cfe499404 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -4,10 +4,10 @@
 #include <linux/perf_event.h>
 #include <sys/types.h>
 #include <stdbool.h>
-#include "types.h"
+#include <linux/bitmap.h>
+#include <linux/types.h>
 #include "event.h"
 
-#include <linux/bitmap.h>
 
 enum {
         HEADER_RESERVED         = 0,    /* always cleared */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f38590d7561b..5a0a4b2cadc4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -4,6 +4,7 @@
 #include "session.h"
 #include "sort.h"
 #include "evsel.h"
+#include "annotate.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -225,14 +226,20 @@ static void he_stat__decay(struct he_stat *he_stat)
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
         u64 prev_period = he->stat.period;
+        u64 diff;
 
         if (prev_period == 0)
                 return true;
 
         he_stat__decay(&he->stat);
+        if (symbol_conf.cumulate_callchain)
+                he_stat__decay(he->stat_acc);
 
+        diff = prev_period - he->stat.period;
+
+        hists->stats.total_period -= diff;
         if (!he->filtered)
-                hists->stats.total_period -= prev_period - he->stat.period;
+                hists->stats.total_non_filtered_period -= diff;
 
         return he->stat.period == 0;
 }
@@ -259,8 +266,11 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
                         if (sort__need_collapse)
                                 rb_erase(&n->rb_node_in, &hists->entries_collapsed);
 
-                        hist_entry__free(n);
                         --hists->nr_entries;
+                        if (!n->filtered)
+                                --hists->nr_non_filtered_entries;
+
+                        hist_entry__free(n);
                 }
         }
 }
@@ -269,14 +279,31 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
  * histogram, sorted on item, collects periods
  */
 
-static struct hist_entry *hist_entry__new(struct hist_entry *template)
+static struct hist_entry *hist_entry__new(struct hist_entry *template,
+                                          bool sample_self)
 {
-        size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-        struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
+        size_t callchain_size = 0;
+        struct hist_entry *he;
+
+        if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+                callchain_size = sizeof(struct callchain_root);
+
+        he = zalloc(sizeof(*he) + callchain_size);
 
         if (he != NULL) {
                 *he = *template;
 
+                if (symbol_conf.cumulate_callchain) {
+                        he->stat_acc = malloc(sizeof(he->stat));
+                        if (he->stat_acc == NULL) {
+                                free(he);
+                                return NULL;
+                        }
+                        memcpy(he->stat_acc, &he->stat, sizeof(he->stat));
+                        if (!sample_self)
+                                memset(&he->stat, 0, sizeof(he->stat));
+                }
+
                 if (he->ms.map)
                         he->ms.map->referenced = true;
 
@@ -288,6 +315,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
                          */
                         he->branch_info = malloc(sizeof(*he->branch_info));
                         if (he->branch_info == NULL) {
+                                free(he->stat_acc);
                                 free(he);
                                 return NULL;
                         }
@@ -317,15 +345,6 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
         return he;
 }
 
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h)
-{
-        if (!h->filtered) {
-                hists__calc_col_len(hists, h);
-                ++hists->nr_entries;
-                hists->stats.total_period += h->stat.period;
-        }
-}
-
 static u8 symbol__parent_filter(const struct symbol *parent)
 {
         if (symbol_conf.exclude_other && parent == NULL)
@@ -335,7 +354,8 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 
 static struct hist_entry *add_hist_entry(struct hists *hists,
                                          struct hist_entry *entry,
-                                         struct addr_location *al)
+                                         struct addr_location *al,
+                                         bool sample_self)
 {
         struct rb_node **p;
         struct rb_node *parent = NULL;
@@ -359,7 +379,10 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
                 cmp = hist_entry__cmp(he, entry);
 
                 if (!cmp) {
-                        he_stat__add_period(&he->stat, period, weight);
+                        if (sample_self)
+                                he_stat__add_period(&he->stat, period, weight);
+                        if (symbol_conf.cumulate_callchain)
+                                he_stat__add_period(he->stat_acc, period, weight);
 
                         /*
                          * This mem info was allocated from sample__resolve_mem
@@ -387,15 +410,17 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
                         p = &(*p)->rb_right;
         }
 
-        he = hist_entry__new(entry);
+        he = hist_entry__new(entry, sample_self);
         if (!he)
                 return NULL;
 
-        hists->nr_entries++;
         rb_link_node(&he->rb_node_in, parent, p);
         rb_insert_color(&he->rb_node_in, hists->entries_in);
 out:
-        he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+        if (sample_self)
+                he_stat__add_cpumode_period(&he->stat, al->cpumode, period);
+        if (symbol_conf.cumulate_callchain)
+                he_stat__add_cpumode_period(he->stat_acc, al->cpumode, period);
         return he;
 }
 
@@ -404,7 +429,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                                       struct symbol *sym_parent,
                                       struct branch_info *bi,
                                       struct mem_info *mi,
-                                      u64 period, u64 weight, u64 transaction)
+                                      u64 period, u64 weight, u64 transaction,
+                                      bool sample_self)
 {
         struct hist_entry entry = {
                 .thread = al->thread,
@@ -429,17 +455,442 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
                 .transaction = transaction,
         };
 
-        return add_hist_entry(hists, &entry, al);
+        return add_hist_entry(hists, &entry, al, sample_self);
+}
+
+static int
+iter_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+                    struct addr_location *al __maybe_unused)
+{
+        return 0;
+}
+
+static int
+iter_add_next_nop_entry(struct hist_entry_iter *iter __maybe_unused,
+                        struct addr_location *al __maybe_unused)
+{
+        return 0;
+}
+
+static int
+iter_prepare_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+        struct perf_sample *sample = iter->sample;
+        struct mem_info *mi;
+
+        mi = sample__resolve_mem(sample, al);
+        if (mi == NULL)
+                return -ENOMEM;
+
+        iter->priv = mi;
+        return 0;
+}
+
+static int
+iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+        u64 cost;
+        struct mem_info *mi = iter->priv;
+        struct hist_entry *he;
+
+        if (mi == NULL)
+                return -EINVAL;
+
+        cost = iter->sample->weight;
+        if (!cost)
+                cost = 1;
+
+        /*
+         * must pass period=weight in order to get the correct
+         * sorting from hists__collapse_resort() which is solely
+         * based on periods. We want sorting be done on nr_events * weight
+         * and this is indirectly achieved by passing period=weight here
+         * and the he_stat__add_period() function.
+         */
+        he = __hists__add_entry(&iter->evsel->hists, al, iter->parent, NULL, mi,
+                                cost, cost, 0, true);
+        if (!he)
+                return -ENOMEM;
+
+        iter->he = he;
+        return 0;
+}
+
+static int
+iter_finish_mem_entry(struct hist_entry_iter *iter,
+                      struct addr_location *al __maybe_unused)
+{
+        struct perf_evsel *evsel = iter->evsel;
+        struct hist_entry *he = iter->he;
+        int err = -EINVAL;
+
+        if (he == NULL)
+                goto out;
+
+        hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+        err = hist_entry__append_callchain(he, iter->sample);
+
+out:
+        /*
+         * We don't need to free iter->priv (mem_info) here since
+         * the mem info was either already freed in add_hist_entry() or
+         * passed to a new hist entry by hist_entry__new().
+         */
+        iter->priv = NULL;
+
+        iter->he = NULL;
+        return err;
+}
+
+static int
+iter_prepare_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+        struct branch_info *bi;
+        struct perf_sample *sample = iter->sample;
+
+        bi = sample__resolve_bstack(sample, al);
+        if (!bi)
+                return -ENOMEM;
+
+        iter->curr = 0;
+        iter->total = sample->branch_stack->nr;
+
+        iter->priv = bi;
+        return 0;
+}
+
+static int
+iter_add_single_branch_entry(struct hist_entry_iter *iter __maybe_unused,
+                             struct addr_location *al __maybe_unused)
+{
+        /* to avoid calling callback function */
+        iter->he = NULL;
+
+        return 0;
+}
+
+static int
+iter_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+        struct branch_info *bi = iter->priv;
+        int i = iter->curr;
+
+        if (bi == NULL)
+                return 0;
+
+        if (iter->curr >= iter->total)
+                return 0;
+
+        al->map = bi[i].to.map;
+        al->sym = bi[i].to.sym;
+        al->addr = bi[i].to.addr;
+        return 1;
+}
+
+static int
+iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+        struct branch_info *bi;
+        struct perf_evsel *evsel = iter->evsel;
+        struct hist_entry *he = NULL;
+        int i = iter->curr;
+        int err = 0;
+
+        bi = iter->priv;
+
+        if (iter->hide_unresolved && !(bi[i].from.sym && bi[i].to.sym))
+                goto out;
+
+        /*
+         * The report shows the percentage of total branches captured
+         * and not events sampled. Thus we use a pseudo period of 1.
+         */
+        he = __hists__add_entry(&evsel->hists, al, iter->parent, &bi[i], NULL,
+                                1, 1, 0, true);
+        if (he == NULL)
+                return -ENOMEM;
+
+        hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+out:
+        iter->he = he;
+        iter->curr++;
+        return err;
+}
+
+static int
+iter_finish_branch_entry(struct hist_entry_iter *iter,
+                         struct addr_location *al __maybe_unused)
+{
+        zfree(&iter->priv);
+        iter->he = NULL;
+
+        return iter->curr >= iter->total ? 0 : -1;
+}
+
+static int
+iter_prepare_normal_entry(struct hist_entry_iter *iter __maybe_unused,
+                          struct addr_location *al __maybe_unused)
+{
+        return 0;
+}
+
+static int
+iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location *al)
+{
+        struct perf_evsel *evsel = iter->evsel;
+        struct perf_sample *sample = iter->sample;
+        struct hist_entry *he;
+
+        he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+                                sample->period, sample->weight,
+                                sample->transaction, true);
+        if (he == NULL)
+                return -ENOMEM;
+
+        iter->he = he;
+        return 0;
+}
+
+static int
+iter_finish_normal_entry(struct hist_entry_iter *iter,
+                         struct addr_location *al __maybe_unused)
+{
+        struct hist_entry *he = iter->he;
+        struct perf_evsel *evsel = iter->evsel;
+        struct perf_sample *sample = iter->sample;
+
+        if (he == NULL)
+                return 0;
+
+        iter->he = NULL;
+
+        hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+        return hist_entry__append_callchain(he, sample);
+}
+
+static int
+iter_prepare_cumulative_entry(struct hist_entry_iter *iter __maybe_unused,
+                              struct addr_location *al __maybe_unused)
+{
+        struct hist_entry **he_cache;
+
+        callchain_cursor_commit(&callchain_cursor);
+
+        /*
+         * This is for detecting cycles or recursions so that they're
+         * cumulated only one time to prevent entries more than 100%
+         * overhead.
+         */
+        he_cache = malloc(sizeof(*he_cache) * (PERF_MAX_STACK_DEPTH + 1));
+        if (he_cache == NULL)
+                return -ENOMEM;
+
+        iter->priv = he_cache;
+        iter->curr = 0;
+
+        return 0;
+}
+
+static int
+iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
+                                 struct addr_location *al)
+{
+        struct perf_evsel *evsel = iter->evsel;
+        struct perf_sample *sample = iter->sample;
+        struct hist_entry **he_cache = iter->priv;
+        struct hist_entry *he;
+        int err = 0;
+
+        he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+                                sample->period, sample->weight,
+                                sample->transaction, true);
+        if (he == NULL)
+                return -ENOMEM;
+
+        iter->he = he;
+        he_cache[iter->curr++] = he;
+
+        callchain_append(he->callchain, &callchain_cursor, sample->period);
+
+        /*
+         * We need to re-initialize the cursor since callchain_append()
+         * advanced the cursor to the end.
+         */
+        callchain_cursor_commit(&callchain_cursor);
+
+        hists__inc_nr_samples(&evsel->hists, he->filtered);
+
+        return err;
+}
+
+static int
+iter_next_cumulative_entry(struct hist_entry_iter *iter,
+                           struct addr_location *al)
+{
+        struct callchain_cursor_node *node;
+
+        node = callchain_cursor_current(&callchain_cursor);
+        if (node == NULL)
+                return 0;
+
+        return fill_callchain_info(al, node, iter->hide_unresolved);
+}
+
+static int
+iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
+                               struct addr_location *al)
+{
+        struct perf_evsel *evsel = iter->evsel;
+        struct perf_sample *sample = iter->sample;
+        struct hist_entry **he_cache = iter->priv;
+        struct hist_entry *he;
+        struct hist_entry he_tmp = {
+                .cpu = al->cpu,
+                .thread = al->thread,
+                .comm = thread__comm(al->thread),
+                .ip = al->addr,
+                .ms = {
+                        .map = al->map,
+                        .sym = al->sym,
+                },
+                .parent = iter->parent,
+        };
+        int i;
+        struct callchain_cursor cursor;
+
+        callchain_cursor_snapshot(&cursor, &callchain_cursor);
+
+        callchain_cursor_advance(&callchain_cursor);
+
+        /*
+         * Check if there's duplicate entries in the callchain.
+         * It's possible that it has cycles or recursive calls.
+         */
+        for (i = 0; i < iter->curr; i++) {
+                if (hist_entry__cmp(he_cache[i], &he_tmp) == 0) {
+                        /* to avoid calling callback function */
+                        iter->he = NULL;
+                        return 0;
+                }
+        }
+
+        he = __hists__add_entry(&evsel->hists, al, iter->parent, NULL, NULL,
+                                sample->period, sample->weight,
+                                sample->transaction, false);
+        if (he == NULL)
+                return -ENOMEM;
+
+        iter->he = he;
+        he_cache[iter->curr++] = he;
+
+        callchain_append(he->callchain, &cursor, sample->period);
+        return 0;
+}
+
+static int
+iter_finish_cumulative_entry(struct hist_entry_iter *iter,
+                             struct addr_location *al __maybe_unused)
+{
+        zfree(&iter->priv);
+        iter->he = NULL;
+
+        return 0;
+}
+
+const struct hist_iter_ops hist_iter_mem = {
+        .prepare_entry          = iter_prepare_mem_entry,
+        .add_single_entry       = iter_add_single_mem_entry,
+        .next_entry             = iter_next_nop_entry,
+        .add_next_entry         = iter_add_next_nop_entry,
+        .finish_entry           = iter_finish_mem_entry,
+};
+
+const struct hist_iter_ops hist_iter_branch = {
+        .prepare_entry          = iter_prepare_branch_entry,
+        .add_single_entry       = iter_add_single_branch_entry,
+        .next_entry             = iter_next_branch_entry,
+        .add_next_entry         = iter_add_next_branch_entry,
+        .finish_entry           = iter_finish_branch_entry,
+};
+
+const struct hist_iter_ops hist_iter_normal = {
+        .prepare_entry          = iter_prepare_normal_entry,
+        .add_single_entry       = iter_add_single_normal_entry,
+        .next_entry             = iter_next_nop_entry,
+        .add_next_entry         = iter_add_next_nop_entry,
+        .finish_entry           = iter_finish_normal_entry,
+};
+
+const struct hist_iter_ops hist_iter_cumulative = {
+        .prepare_entry          = iter_prepare_cumulative_entry,
+        .add_single_entry       = iter_add_single_cumulative_entry,
+        .next_entry             = iter_next_cumulative_entry,
+        .add_next_entry         = iter_add_next_cumulative_entry,
+        .finish_entry           = iter_finish_cumulative_entry,
+};
+
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+                         struct perf_evsel *evsel, struct perf_sample *sample,
+                         int max_stack_depth, void *arg)
+{
+        int err, err2;
+
+        err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
+                                        max_stack_depth);
+        if (err)
+                return err;
+
+        iter->evsel = evsel;
+        iter->sample = sample;
+
+        err = iter->ops->prepare_entry(iter, al);
+        if (err)
+                goto out;
+
+        err = iter->ops->add_single_entry(iter, al);
+        if (err)
+                goto out;
+
+        if (iter->he && iter->add_entry_cb) {
+                err = iter->add_entry_cb(iter, al, true, arg);
+                if (err)
+                        goto out;
+        }
+
+        while (iter->ops->next_entry(iter, al)) {
+                err = iter->ops->add_next_entry(iter, al);
+                if (err)
+                        break;
+
+                if (iter->he && iter->add_entry_cb) {
+                        err = iter->add_entry_cb(iter, al, false, arg);
+                        if (err)
+                                goto out;
+                }
+        }
+
+out:
+        err2 = iter->ops->finish_entry(iter, al);
+        if (!err)
+                err = err2;
+
+        return err;
 }
 
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        struct sort_entry *se;
+        struct perf_hpp_fmt *fmt;
         int64_t cmp = 0;
 
-        list_for_each_entry(se, &hist_entry__sort_list, list) {
-                cmp = se->se_cmp(left, right);
+        perf_hpp__for_each_sort_list(fmt) {
+                if (perf_hpp__should_skip(fmt))
+                        continue;
+
+                cmp = fmt->cmp(left, right);
                 if (cmp)
                         break;
         }
@@ -450,15 +901,14 @@ hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 int64_t
 hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 {
-        struct sort_entry *se;
+        struct perf_hpp_fmt *fmt;
         int64_t cmp = 0;
 
-        list_for_each_entry(se, &hist_entry__sort_list, list) {
-                int64_t (*f)(struct hist_entry *, struct hist_entry *);
-
-                f = se->se_collapse ?: se->se_cmp;
+        perf_hpp__for_each_sort_list(fmt) {
+                if (perf_hpp__should_skip(fmt))
+                        continue;
 
-                cmp = f(left, right);
+                cmp = fmt->collapse(left, right);
                 if (cmp)
                         break;
         }
@@ -470,6 +920,7 @@ void hist_entry__free(struct hist_entry *he)
 {
         zfree(&he->branch_info);
         zfree(&he->mem_info);
+        zfree(&he->stat_acc);
         free_srcline(he->srcline);
         free(he);
 }
@@ -495,6 +946,8 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
                 if (!cmp) {
                         he_stat__add_stat(&iter->stat, &he->stat);
+                        if (symbol_conf.cumulate_callchain)
+                                he_stat__add_stat(iter->stat_acc, he->stat_acc);
 
                         if (symbol_conf.use_callchain) {
                                 callchain_cursor_reset(&callchain_cursor);
@@ -571,64 +1024,50 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
         }
 }
 
-/*
- * reverse the map, sort on period.
- */
-
-static int period_cmp(u64 period_a, u64 period_b)
-{
-        if (period_a > period_b)
-                return 1;
-        if (period_a < period_b)
-                return -1;
-        return 0;
-}
-
-static int hist_entry__sort_on_period(struct hist_entry *a,
-                                      struct hist_entry *b)
+static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
-        int ret;
-        int i, nr_members;
-        struct perf_evsel *evsel;
-        struct hist_entry *pair;
-        u64 *periods_a, *periods_b;
+        struct perf_hpp_fmt *fmt;
+        int64_t cmp = 0;
 
-        ret = period_cmp(a->stat.period, b->stat.period);
-        if (ret || !symbol_conf.event_group)
-                return ret;
+        perf_hpp__for_each_sort_list(fmt) {
+                if (perf_hpp__should_skip(fmt))
+                        continue;
 
-        evsel = hists_to_evsel(a->hists);
-        nr_members = evsel->nr_members;
-        if (nr_members <= 1)
-                return ret;
+                cmp = fmt->sort(a, b);
+                if (cmp)
+                        break;
+        }
 
-        periods_a = zalloc(sizeof(periods_a) * nr_members);
-        periods_b = zalloc(sizeof(periods_b) * nr_members);
+        return cmp;
+}
 
-        if (!periods_a || !periods_b)
-                goto out;
+static void hists__reset_filter_stats(struct hists *hists)
+{
+        hists->nr_non_filtered_entries = 0;
+        hists->stats.total_non_filtered_period = 0;
+}
 
-        list_for_each_entry(pair, &a->pairs.head, pairs.node) {
-                evsel = hists_to_evsel(pair->hists);
-                periods_a[perf_evsel__group_idx(evsel)] = pair->stat.period;
-        }
+void hists__reset_stats(struct hists *hists)
+{
+        hists->nr_entries = 0;
+        hists->stats.total_period = 0;
 
-        list_for_each_entry(pair, &b->pairs.head, pairs.node) {
-                evsel = hists_to_evsel(pair->hists);
-                periods_b[perf_evsel__group_idx(evsel)] = pair->stat.period;
-        }
+        hists__reset_filter_stats(hists);
+}
 
-        for (i = 1; i < nr_members; i++) {
-                ret = period_cmp(periods_a[i], periods_b[i]);
-                if (ret)
-                        break;
-        }
+static void hists__inc_filter_stats(struct hists *hists, struct hist_entry *h)
+{
+        hists->nr_non_filtered_entries++;
+        hists->stats.total_non_filtered_period += h->stat.period;
+}
 
-out:
-        free(periods_a);
-        free(periods_b);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h)
+{
+        if (!h->filtered)
+                hists__inc_filter_stats(hists, h);
 
-        return ret;
+        hists->nr_entries++;
+        hists->stats.total_period += h->stat.period;
 }
 
 static void __hists__insert_output_entry(struct rb_root *entries,
@@ -647,7 +1086,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
                 parent = *p;
                 iter = rb_entry(parent, struct hist_entry, rb_node);
 
-                if (hist_entry__sort_on_period(he, iter) > 0)
+                if (hist_entry__sort(he, iter) > 0)
                         p = &(*p)->rb_left;
                 else
                         p = &(*p)->rb_right;
@@ -674,8 +1113,7 @@ void hists__output_resort(struct hists *hists)
         next = rb_first(root);
         hists->entries = RB_ROOT;
 
-        hists->nr_entries = 0;
-        hists->stats.total_period = 0;
+        hists__reset_stats(hists);
         hists__reset_col_len(hists);
 
         while (next) {
@@ -683,7 +1121,10 @@ void hists__output_resort(struct hists *hists)
                 next = rb_next(&n->rb_node_in);
 
                 __hists__insert_output_entry(&hists->entries, n, min_callchain_hits);
-                hists__inc_nr_entries(hists, n);
+                hists__inc_stats(hists, n);
+
+                if (!n->filtered)
+                        hists__calc_col_len(hists, n);
         }
 }
 
@@ -694,13 +1135,13 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
         if (h->filtered)
                 return;
 
-        ++hists->nr_entries;
-        if (h->ms.unfolded)
-                hists->nr_entries += h->nr_rows;
+        /* force fold unfiltered entry for simplicity */
+        h->ms.unfolded = false;
         h->row_offset = 0;
-        hists->stats.total_period += h->stat.period;
-        hists->stats.nr_events[PERF_RECORD_SAMPLE] += h->stat.nr_events;
 
+        hists->stats.nr_non_filtered_samples += h->stat.nr_events;
+
+        hists__inc_filter_stats(hists, h);
         hists__calc_col_len(hists, h);
 }
 
@@ -721,8 +1162,9 @@ void hists__filter_by_dso(struct hists *hists)
 {
         struct rb_node *nd;
 
-        hists->nr_entries = hists->stats.total_period = 0;
-        hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+        hists->stats.nr_non_filtered_samples = 0;
+
+        hists__reset_filter_stats(hists);
         hists__reset_col_len(hists);
 
         for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -754,8 +1196,9 @@ void hists__filter_by_thread(struct hists *hists)
 {
         struct rb_node *nd;
 
-        hists->nr_entries = hists->stats.total_period = 0;
-        hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+        hists->stats.nr_non_filtered_samples = 0;
+
+        hists__reset_filter_stats(hists);
         hists__reset_col_len(hists);
 
         for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -785,8 +1228,9 @@ void hists__filter_by_symbol(struct hists *hists)
 {
         struct rb_node *nd;
 
-        hists->nr_entries = hists->stats.total_period = 0;
-        hists->stats.nr_events[PERF_RECORD_SAMPLE] = 0;
+        hists->stats.nr_non_filtered_samples = 0;
+
+        hists__reset_filter_stats(hists);
         hists__reset_col_len(hists);
 
         for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
@@ -810,6 +1254,13 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
         events_stats__inc(&hists->stats, type);
 }
 
+void hists__inc_nr_samples(struct hists *hists, bool filtered)
+{
+        events_stats__inc(&hists->stats, PERF_RECORD_SAMPLE);
+        if (!filtered)
+                hists->stats.nr_non_filtered_samples++;
+}
+
 static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
                                                  struct hist_entry *pair)
 {
@@ -841,13 +1292,13 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
                         p = &(*p)->rb_right;
         }
 
-        he = hist_entry__new(pair);
+        he = hist_entry__new(pair, true);
         if (he) {
                 memset(&he->stat, 0, sizeof(he->stat));
                 he->hists = hists;
                 rb_link_node(&he->rb_node_in, parent, p);
                 rb_insert_color(&he->rb_node_in, root);
-                hists__inc_nr_entries(hists, he);
+                hists__inc_stats(hists, he);
                 he->dummy = true;
         }
 out:
@@ -931,3 +1382,30 @@ int hists__link(struct hists *leader, struct hists *other)
 
         return 0;
 }
+
+u64 hists__total_period(struct hists *hists)
+{
+        return symbol_conf.filter_relative ? hists->stats.total_non_filtered_period :
+                hists->stats.total_period;
+}
+
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+                            const char *arg, int unset __maybe_unused)
+{
+        if (!strcmp(arg, "relative"))
+                symbol_conf.filter_relative = true;
+        else if (!strcmp(arg, "absolute"))
+                symbol_conf.filter_relative = false;
+        else
+                return -1;
+
+        return 0;
+}
+
+int perf_hist_config(const char *var, const char *value)
+{
+        if (!strcmp(var, "hist.percentage"))
+                return parse_filter_percentage(NULL, value, 0);
+
+        return 0;
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1f1f513dfe7f..d2bf03575d5f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -37,9 +37,11 @@ enum hist_filter {
  */
 struct events_stats {
         u64 total_period;
+        u64 total_non_filtered_period;
         u64 total_lost;
         u64 total_invalid_chains;
         u32 nr_events[PERF_RECORD_HEADER_MAX];
+        u32 nr_non_filtered_samples;
         u32 nr_lost_warned;
         u32 nr_unknown_events;
         u32 nr_invalid_chains;
@@ -83,6 +85,7 @@ struct hists {
         struct rb_root          entries;
         struct rb_root          entries_collapsed;
         u64                     nr_entries;
+        u64                     nr_non_filtered_entries;
         const struct thread     *thread_filter;
         const struct dso        *dso_filter;
         const char              *uid_filter_str;
@@ -93,12 +96,50 @@ struct hists {
         u16                     col_len[HISTC_NR_COLS];
 };
 
+struct hist_entry_iter;
+
+struct hist_iter_ops {
+        int (*prepare_entry)(struct hist_entry_iter *, struct addr_location *);
+        int (*add_single_entry)(struct hist_entry_iter *, struct addr_location *);
+        int (*next_entry)(struct hist_entry_iter *, struct addr_location *);
+        int (*add_next_entry)(struct hist_entry_iter *, struct addr_location *);
+        int (*finish_entry)(struct hist_entry_iter *, struct addr_location *);
+};
+
+struct hist_entry_iter {
+        int total;
+        int curr;
+
+        bool hide_unresolved;
+
+        struct perf_evsel *evsel;
+        struct perf_sample *sample;
+        struct hist_entry *he;
+        struct symbol *parent;
+        void *priv;
+
+        const struct hist_iter_ops *ops;
+        /* user-defined callback function (optional) */
+        int (*add_entry_cb)(struct hist_entry_iter *iter,
+                            struct addr_location *al, bool single, void *arg);
+};
+
+extern const struct hist_iter_ops hist_iter_normal;
+extern const struct hist_iter_ops hist_iter_branch;
+extern const struct hist_iter_ops hist_iter_mem;
+extern const struct hist_iter_ops hist_iter_cumulative;
+
 struct hist_entry *__hists__add_entry(struct hists *hists,
                                       struct addr_location *al,
                                       struct symbol *parent,
                                       struct branch_info *bi,
                                       struct mem_info *mi, u64 period,
-                                      u64 weight, u64 transaction);
+                                      u64 weight, u64 transaction,
+                                      bool sample_self);
+int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
+                         struct perf_evsel *evsel, struct perf_sample *sample,
+                         int max_stack_depth, void *arg);
+
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__transaction_len(void);
@@ -112,8 +153,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
-void hists__inc_nr_entries(struct hists *hists, struct hist_entry *h);
+u64 hists__total_period(struct hists *hists);
+void hists__reset_stats(struct hists *hists);
+void hists__inc_stats(struct hists *hists, struct hist_entry *h);
 void hists__inc_nr_events(struct hists *hists, u32 type);
+void hists__inc_nr_samples(struct hists *hists, bool filtered);
 void events_stats__inc(struct events_stats *stats, u32 type);
 size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
@@ -124,6 +168,12 @@ void hists__filter_by_dso(struct hists *hists);
 void hists__filter_by_thread(struct hists *hists);
 void hists__filter_by_symbol(struct hists *hists);
 
+static inline bool hists__has_filter(struct hists *hists)
+{
+        return hists->thread_filter || hists->dso_filter ||
+                hists->symbol_filter_str;
+}
+
 u16 hists__col_len(struct hists *hists, enum hist_column col);
 void hists__set_col_len(struct hists *hists, enum hist_column col, u16 len);
 bool hists__new_col_len(struct hists *hists, enum hist_column col, u16 len);
@@ -149,15 +199,30 @@ struct perf_hpp_fmt {
                      struct hist_entry *he);
         int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
                      struct hist_entry *he);
+        int64_t (*cmp)(struct hist_entry *a, struct hist_entry *b);
+        int64_t (*collapse)(struct hist_entry *a, struct hist_entry *b);
+        int64_t (*sort)(struct hist_entry *a, struct hist_entry *b);
 
         struct list_head list;
+        struct list_head sort_list;
+        bool elide;
 };
 
 extern struct list_head perf_hpp__list;
+extern struct list_head perf_hpp__sort_list;
 
 #define perf_hpp__for_each_format(format) \
         list_for_each_entry(format, &perf_hpp__list, list)
 
+#define perf_hpp__for_each_format_safe(format, tmp)     \
+        list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+
+#define perf_hpp__for_each_sort_list(format) \
+        list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+
+#define perf_hpp__for_each_sort_list_safe(format, tmp)  \
+        list_for_each_entry_safe(format, tmp, &perf_hpp__sort_list, sort_list)
+
 extern struct perf_hpp_fmt perf_hpp__format[];
 
 enum {
@@ -167,6 +232,7 @@ enum {
         PERF_HPP__OVERHEAD_US,
         PERF_HPP__OVERHEAD_GUEST_SYS,
         PERF_HPP__OVERHEAD_GUEST_US,
+        PERF_HPP__OVERHEAD_ACC,
         PERF_HPP__SAMPLES,
         PERF_HPP__PERIOD,
 
@@ -175,15 +241,36 @@ enum {
 
 void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
+void perf_hpp__column_disable(unsigned col);
+void perf_hpp__cancel_cumulate(void);
+
+void perf_hpp__register_sort_field(struct perf_hpp_fmt *format);
+void perf_hpp__setup_output_field(void);
+void perf_hpp__reset_output_field(void);
+void perf_hpp__append_sort_keys(void);
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format);
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+
+static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
+{
+        return format->elide;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
 int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-               hpp_field_fn get_field, hpp_callback_fn callback,
-               const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent);
+               hpp_field_fn get_field, const char *fmt,
+               hpp_snprint_fn print_fn, bool fmt_percent);
+int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
+                   hpp_field_fn get_field, const char *fmt,
+                   hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
@@ -250,4 +337,10 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+
+struct option;
+int parse_filter_percentage(const struct option *opt __maybe_unused,
+                            const char *arg, int unset __maybe_unused);
+int perf_hist_config(const char *var, const char *value);
+
 #endif  /* __PERF_HIST_H */
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index bb162e40c76c..01ffd12dc791 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -4,6 +4,9 @@
 #include <string.h>
 #include <linux/bitops.h>
 
+#define DECLARE_BITMAP(name,bits) \
+        unsigned long name[BITS_TO_LONGS(bits)]
+
 int __bitmap_weight(const unsigned long *bitmap, int bits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
                  const unsigned long *bitmap2, int bits);
diff --git a/tools/perf/util/include/linux/export.h b/tools/perf/util/include/linux/export.h
deleted file mode 100644
index b43e2dc21e04..000000000000
--- a/tools/perf/util/include/linux/export.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_MODULE_H
-#define PERF_LINUX_MODULE_H
-
-#define EXPORT_SYMBOL(name)
-
-#endif
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index bfe0a2afd0d2..76ddbc726343 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/types.h>
 
 #include "../../../../include/linux/list.h"
 
diff --git a/tools/perf/util/include/linux/types.h b/tools/perf/util/include/linux/types.h
deleted file mode 100644
index eb464786c084..000000000000
--- a/tools/perf/util/include/linux/types.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _PERF_LINUX_TYPES_H_
-#define _PERF_LINUX_TYPES_H_
-
-#include <asm/types.h>
-
-#ifndef __bitwise
-#define __bitwise
-#endif
-
-#ifndef __le32
-typedef __u32 __bitwise __le32;
-#endif
-
-#define DECLARE_BITMAP(name,bits) \
-        unsigned long name[BITS_TO_LONGS(bits)]
-
-struct list_head {
-        struct list_head *next, *prev;
-};
-
-struct hlist_head {
-        struct hlist_node *first;
-};
-
-struct hlist_node {
-        struct hlist_node *next, **pprev;
-};
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index a53cd0b8c151..7409ac8de51c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -316,6 +316,17 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
                 rb_link_node(&th->rb_node, parent, p);
                 rb_insert_color(&th->rb_node, &machine->threads);
                 machine->last_match = th;
+
+                /*
+                 * We have to initialize map_groups separately
+                 * after rb tree is updated.
+                 *
+                 * The reason is that we call machine__findnew_thread
+                 * within thread__init_map_groups to find the thread
+                 * leader and that would screwed the rb tree.
+                 */
+                if (thread__init_map_groups(th, machine))
+                        return NULL;
         }
 
         return th;
@@ -717,7 +728,7 @@ static char *get_kernel_version(const char *root_dir)
 }
 
 static int map_groups__set_modules_path_dir(struct map_groups *mg,
-                                const char *dir_name)
+                                const char *dir_name, int depth)
 {
         struct dirent *dent;
         DIR *dir = opendir(dir_name);
@@ -742,7 +753,15 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
                             !strcmp(dent->d_name, ".."))
                                 continue;
 
-                        ret = map_groups__set_modules_path_dir(mg, path);
+                        /* Do not follow top-level source and build symlinks */
+                        if (depth == 0) {
+                                if (!strcmp(dent->d_name, "source") ||
+                                    !strcmp(dent->d_name, "build"))
+                                        continue;
+                        }
+
+                        ret = map_groups__set_modules_path_dir(mg, path,
+                                                               depth + 1);
                         if (ret < 0)
                                 goto out;
                 } else {
@@ -786,11 +805,11 @@ static int machine__set_modules_path(struct machine *machine)
         if (!version)
                 return -1;
 
-        snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+        snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s",
                  machine->root_dir, version);
         free(version);
 
-        return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
+        return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 
 static int machine__create_module(void *arg, const char *name, u64 start)
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 39cd2d0faff6..8ccbb32eda25 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -32,6 +32,93 @@ static inline int is_no_dso_memory(const char *filename)
                !strcmp(filename, "[heap]");
 }
 
+static inline int is_android_lib(const char *filename)
+{
+        return !strncmp(filename, "/data/app-lib", 13) ||
+               !strncmp(filename, "/system/lib", 11);
+}
+
+static inline bool replace_android_lib(const char *filename, char *newfilename)
+{
+        const char *libname;
+        char *app_abi;
+        size_t app_abi_length, new_length;
+        size_t lib_length = 0;
+
+        libname  = strrchr(filename, '/');
+        if (libname)
+                lib_length = strlen(libname);
+
+        app_abi = getenv("APP_ABI");
+        if (!app_abi)
+                return false;
+
+        app_abi_length = strlen(app_abi);
+
+        if (!strncmp(filename, "/data/app-lib", 13)) {
+                char *apk_path;
+
+                if (!app_abi_length)
+                        return false;
+
+                new_length = 7 + app_abi_length + lib_length;
+
+                apk_path = getenv("APK_PATH");
+                if (apk_path) {
+                        new_length += strlen(apk_path) + 1;
+                        if (new_length > PATH_MAX)
+                                return false;
+                        snprintf(newfilename, new_length,
+                                 "%s/libs/%s/%s", apk_path, app_abi, libname);
+                } else {
+                        if (new_length > PATH_MAX)
+                                return false;
+                        snprintf(newfilename, new_length,
+                                 "libs/%s/%s", app_abi, libname);
+                }
+                return true;
+        }
+
+        if (!strncmp(filename, "/system/lib/", 11)) {
+                char *ndk, *app;
+                const char *arch;
+                size_t ndk_length;
+                size_t app_length;
+
+                ndk = getenv("NDK_ROOT");
+                app = getenv("APP_PLATFORM");
+
+                if (!(ndk && app))
+                        return false;
+
+                ndk_length = strlen(ndk);
+                app_length = strlen(app);
+
+                if (!(ndk_length && app_length && app_abi_length))
+                        return false;
+
+                arch = !strncmp(app_abi, "arm", 3) ? "arm" :
+                       !strncmp(app_abi, "mips", 4) ? "mips" :
+                       !strncmp(app_abi, "x86", 3) ? "x86" : NULL;
+
+                if (!arch)
+                        return false;
+
+                new_length = 27 + ndk_length +
+                             app_length + lib_length
+                           + strlen(arch);
+
+                if (new_length > PATH_MAX)
+                        return false;
+                snprintf(newfilename, new_length,
+                        "%s/platforms/%s/arch-%s/usr/lib/%s",
+                        ndk, app, arch, libname);
+
+                return true;
+        }
+        return false;
+}
+
 void map__init(struct map *map, enum map_type type,
                u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
@@ -59,8 +146,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
         if (map != NULL) {
                 char newfilename[PATH_MAX];
                 struct dso *dso;
-                int anon, no_dso, vdso;
+                int anon, no_dso, vdso, android;
 
+                android = is_android_lib(filename);
                 anon = is_anon_memory(filename);
                 vdso = is_vdso_map(filename);
                 no_dso = is_no_dso_memory(filename);
@@ -75,6 +163,11 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
                         filename = newfilename;
                 }
 
+                if (android) {
+                        if (replace_android_lib(filename, newfilename))
+                                filename = newfilename;
+                }
+
                 if (vdso) {
                         pgoff = 0;
                         dso = vdso__dso_findnew(dsos__list);
@@ -323,6 +416,7 @@ void map_groups__init(struct map_groups *mg)
                 INIT_LIST_HEAD(&mg->removed_maps[i]);
         }
         mg->machine = NULL;
+        mg->refcnt = 1;
 }
 
 static void maps__delete(struct rb_root *maps)
@@ -358,6 +452,28 @@ void map_groups__exit(struct map_groups *mg)
         }
 }
 
+struct map_groups *map_groups__new(void)
+{
+        struct map_groups *mg = malloc(sizeof(*mg));
+
+        if (mg != NULL)
+                map_groups__init(mg);
+
+        return mg;
+}
+
+void map_groups__delete(struct map_groups *mg)
+{
+        map_groups__exit(mg);
+        free(mg);
+}
+
+void map_groups__put(struct map_groups *mg)
+{
+        if (--mg->refcnt == 0)
+                map_groups__delete(mg);
+}
+
 void map_groups__flush(struct map_groups *mg)
 {
         int type;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index f00f058afb3b..ae2d45110588 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -6,7 +6,7 @@
 #include <linux/rbtree.h>
 #include <stdio.h>
 #include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
 
 enum map_type {
         MAP__FUNCTION = 0,
@@ -59,8 +59,20 @@ struct map_groups {
         struct rb_root   maps[MAP__NR_TYPES];
         struct list_head removed_maps[MAP__NR_TYPES];
         struct machine   *machine;
+        int              refcnt;
 };
 
+struct map_groups *map_groups__new(void);
+void map_groups__delete(struct map_groups *mg);
+
+static inline struct map_groups *map_groups__get(struct map_groups *mg)
+{
+        ++mg->refcnt;
+        return mg;
+}
+
+void map_groups__put(struct map_groups *mg);
+
 static inline struct kmap *map__kmap(struct map *map)
 {
         return (struct kmap *)(map + 1);
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 3322b8446e89..31ee02d4e988 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -57,13 +57,13 @@ void setup_pager(void)
         }
         if (!pager)
                 pager = getenv("PAGER");
-        if (!pager) {
-                if (!access("/usr/bin/pager", X_OK))
-                        pager = "/usr/bin/pager";
-        }
+        if (!(pager || access("/usr/bin/pager", X_OK)))
+                pager = "/usr/bin/pager";
+        if (!(pager || access("/usr/bin/less", X_OK)))
+                pager = "/usr/bin/less";
         if (!pager)
-                pager = "less";
-        else if (!*pager || !strcmp(pager, "cat"))
+                pager = "cat";
+        if (!*pager || !strcmp(pager, "cat"))
                 return;
 
         spawned_pager = 1; /* means we are emitting to terminal */
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1cb4c4b3c70..df094b4ed5ed 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -6,9 +6,8 @@
 
 #include <linux/list.h>
 #include <stdbool.h>
-#include "types.h"
+#include <linux/types.h>
 #include <linux/perf_event.h>
-#include "types.h"
 
 struct list_head;
 struct perf_evsel;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 4eb67ec333f1..0bc87ba46bf3 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -9,7 +9,7 @@
 
 #include <linux/compiler.h>
 #include <linux/list.h>
-#include "types.h"
+#include <linux/types.h>
 #include "util.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -299,6 +299,18 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
+PE_NAME '-' PE_NAME ':' PE_NAME
+{
+        struct parse_events_evlist *data = _data;
+        struct list_head *list;
+        char sys_name[128];
+        snprintf(&sys_name, 128, "%s-%s", $1, $3);
+
+        ALLOC_LIST(list);
+        ABORT_ON(parse_events_add_tracepoint(list, &data->idx, &sys_name, $5));
+        $$ = list;
+}
+|
 PE_NAME ':' PE_NAME
 {
         struct parse_events_evlist *data = _data;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index d6e8b6a8d7f3..79c78f74e0cf 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_REGS_H
 #define __PERF_REGS_H
 
-#include "types.h"
+#include <linux/types.h>
 #include "event.h"
 
 #ifdef HAVE_PERF_REGS_SUPPORT
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 00a7dcb2f55c..7a811eb61f75 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -284,17 +284,17 @@ static int pmu_aliases(const char *name, struct list_head *head)
 static int pmu_alias_terms(struct perf_pmu_alias *alias,
                            struct list_head *terms)
 {
-        struct parse_events_term *term, *clone;
+        struct parse_events_term *term, *cloned;
         LIST_HEAD(list);
         int ret;
 
         list_for_each_entry(term, &alias->terms, list) {
-                ret = parse_events_term__clone(&clone, term);
+                ret = parse_events_term__clone(&cloned, term);
                 if (ret) {
                         parse_events__free_terms(&list);
                         return ret;
                 }
-                list_add_tail(&clone->list, &list);
+                list_add_tail(&cloned->list, &list);
         }
         list_splice(&list, terms);
         return 0;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8b64125a9281..c14a543ce1f3 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -1,7 +1,7 @@
 #ifndef __PMU_H
 #define __PMU_H
 
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df0238654698..9d8eb26f0533 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -511,12 +511,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 
         ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
                                         &pf->sp_die, pf->tvar);
-        if (ret == -ENOENT)
+        if (ret == -ENOENT || ret == -EINVAL)
                 pr_err("Failed to find the location of %s at this address.\n"
                        " Perhaps, it has been optimized out.\n", pf->pvar->var);
         else if (ret == -ENOTSUP)
                 pr_err("Sorry, we don't support this variable location yet.\n");
-        else if (pf->pvar->field) {
+        else if (ret == 0 && pf->pvar->field) {
                 ret = convert_variable_fields(vr_die, pf->pvar->var,
                                               pf->pvar->field, &pf->tvar->ref,
                                               &die_mem);
@@ -985,7 +985,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 
 #if _ELFUTILS_PREREQ(0, 142)
         /* Get the call frame information from this dwarf */
-        pf->cfi = dwarf_getcfi(dbg->dbg);
+        pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
 #endif
 
         off = 0;
@@ -1441,13 +1441,15 @@ static int line_range_walk_cb(const char *fname, int lineno,
                               void *data)
 {
         struct line_finder *lf = data;
+        int err;
 
         if ((strtailcmp(fname, lf->fname) != 0) ||
             (lf->lno_s > lineno || lf->lno_e < lineno))
                 return 0;
 
-        if (line_range_add_line(fname, lineno, lf->lr) < 0)
-                return -EINVAL;
+        err = line_range_add_line(fname, lineno, lf->lr);
+        if (err < 0 && err != -EEXIST)
+                return err;
 
         return 0;
 }
@@ -1473,14 +1475,15 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
 static int line_range_inline_cb(Dwarf_Die *in_die, void *data)
 {
-        find_line_range_by_line(in_die, data);
+        int ret = find_line_range_by_line(in_die, data);
 
         /*
          * We have to check all instances of inlined function, because
          * some execution paths can be optimized out depends on the
-         * function argument of instances
+         * function argument of instances. However, if an error occurs,
+         * it should be handled by the caller.
          */
-        return 0;
+        return ret < 0 ? ret : 0;
 }
 
 /* Search function definition from function name */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 55960f22233c..64a186edc7be 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1625,13 +1625,14 @@ out_delete_map:
 void perf_session__fprintf_info(struct perf_session *session, FILE *fp,
                                 bool full)
 {
-        int fd = perf_data_file__fd(session->file);
         struct stat st;
-        int ret;
+        int fd, ret;
 
         if (session == NULL || fp == NULL)
                 return;
 
+        fd = perf_data_file__fd(session->file);
+
         ret = fstat(fd, &st);
         if (ret == -1)
                 return;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 635cd8f8b22e..45512baaab67 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2,12 +2,18 @@
 #include "hist.h"
 #include "comm.h"
 #include "symbol.h"
+#include "evsel.h"
 
 regex_t         parent_regex;
 const char      default_parent_pattern[] = "^sys_|^do_page_fault";
 const char      *parent_pattern = default_parent_pattern;
 const char      default_sort_order[] = "comm,dso,symbol";
-const char      *sort_order = default_sort_order;
+const char      default_branch_sort_order[] = "comm,dso_from,symbol_from,dso_to,symbol_to";
+const char      default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+const char      default_top_sort_order[] = "dso,symbol";
+const char      default_diff_sort_order[] = "dso,symbol";
+const char      *sort_order;
+const char      *field_order;
 regex_t         ignore_callees_regex;
 int             have_ignore_callees = 0;
 int             sort__need_collapse = 0;
@@ -16,9 +22,6 @@ int		sort__has_sym = 0;
 int             sort__has_dso = 0;
 enum sort_mode  sort__mode = SORT_MODE__NORMAL;
 
-enum sort_type  sort__first_dimension;
-
-LIST_HEAD(hist_entry__sort_list);
 
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
@@ -93,6 +96,12 @@ sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
         return comm__str(right->comm) - comm__str(left->comm);
 }
 
+static int64_t
+sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
+{
+        return strcmp(comm__str(right->comm), comm__str(left->comm));
+}
+
 static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
                                      size_t size, unsigned int width)
 {
@@ -103,6 +112,7 @@ struct sort_entry sort_comm = {
         .se_header      = "Command",
         .se_cmp         = sort__comm_cmp,
         .se_collapse    = sort__comm_collapse,
+        .se_sort        = sort__comm_sort,
         .se_snprintf    = hist_entry__comm_snprintf,
         .se_width_idx   = HISTC_COMM,
 };
@@ -116,7 +126,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
         const char *dso_name_l, *dso_name_r;
 
         if (!dso_l || !dso_r)
-                return cmp_null(dso_l, dso_r);
+                return cmp_null(dso_r, dso_l);
 
         if (verbose) {
                 dso_name_l = dso_l->long_name;
@@ -132,7 +142,7 @@ static int64_t _sort__dso_cmp(struct map *map_l, struct map *map_r)
 static int64_t
 sort__dso_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        return _sort__dso_cmp(left->ms.map, right->ms.map);
+        return _sort__dso_cmp(right->ms.map, left->ms.map);
 }
 
 static int _hist_entry__dso_snprintf(struct map *map, char *bf,
@@ -204,6 +214,15 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
         return _sort__sym_cmp(left->ms.sym, right->ms.sym);
 }
 
+static int64_t
+sort__sym_sort(struct hist_entry *left, struct hist_entry *right)
+{
+        if (!left->ms.sym || !right->ms.sym)
+                return cmp_null(left->ms.sym, right->ms.sym);
+
+        return strcmp(right->ms.sym->name, left->ms.sym->name);
+}
+
 static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
                                      u64 ip, char level, char *bf, size_t size,
                                      unsigned int width)
@@ -250,6 +269,7 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
 struct sort_entry sort_sym = {
         .se_header      = "Symbol",
         .se_cmp         = sort__sym_cmp,
+        .se_sort        = sort__sym_sort,
         .se_snprintf    = hist_entry__sym_snprintf,
         .se_width_idx   = HISTC_SYMBOL,
 };
@@ -277,7 +297,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
                                             map__rip_2objdump(map, right->ip));
                 }
         }
-        return strcmp(left->srcline, right->srcline);
+        return strcmp(right->srcline, left->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
@@ -305,7 +325,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
         if (!sym_l || !sym_r)
                 return cmp_null(sym_l, sym_r);
 
-        return strcmp(sym_l->name, sym_r->name);
+        return strcmp(sym_r->name, sym_l->name);
 }
 
 static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
@@ -1027,19 +1047,194 @@ static struct sort_dimension memory_sort_dimensions[] = {
 
 #undef DIM
 
-static void __sort_dimension__add(struct sort_dimension *sd, enum sort_type idx)
+struct hpp_dimension {
+        const char              *name;
+        struct perf_hpp_fmt     *fmt;
+        int                     taken;
+};
+
+#define DIM(d, n) { .name = n, .fmt = &perf_hpp__format[d], }
+
+static struct hpp_dimension hpp_sort_dimensions[] = {
+        DIM(PERF_HPP__OVERHEAD, "overhead"),
+        DIM(PERF_HPP__OVERHEAD_SYS, "overhead_sys"),
+        DIM(PERF_HPP__OVERHEAD_US, "overhead_us"),
+        DIM(PERF_HPP__OVERHEAD_GUEST_SYS, "overhead_guest_sys"),
+        DIM(PERF_HPP__OVERHEAD_GUEST_US, "overhead_guest_us"),
+        DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
+        DIM(PERF_HPP__SAMPLES, "sample"),
+        DIM(PERF_HPP__PERIOD, "period"),
+};
+
+#undef DIM
+
+struct hpp_sort_entry {
+        struct perf_hpp_fmt hpp;
+        struct sort_entry *se;
+};
+
+bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 {
-        if (sd->taken)
+        struct hpp_sort_entry *hse_a;
+        struct hpp_sort_entry *hse_b;
+
+        if (!perf_hpp__is_sort_entry(a) || !perf_hpp__is_sort_entry(b))
+                return false;
+
+        hse_a = container_of(a, struct hpp_sort_entry, hpp);
+        hse_b = container_of(b, struct hpp_sort_entry, hpp);
+
+        return hse_a->se == hse_b->se;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+        struct hpp_sort_entry *hse;
+
+        if (!perf_hpp__is_sort_entry(fmt))
                 return;
 
+        hse = container_of(fmt, struct hpp_sort_entry, hpp);
+        hists__new_col_len(hists, hse->se->se_width_idx,
+                           strlen(hse->se->se_header));
+}
+
+static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                              struct perf_evsel *evsel)
+{
+        struct hpp_sort_entry *hse;
+        size_t len;
+
+        hse = container_of(fmt, struct hpp_sort_entry, hpp);
+        len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+        return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
+}
+
+static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
+                             struct perf_hpp *hpp __maybe_unused,
+                             struct perf_evsel *evsel)
+{
+        struct hpp_sort_entry *hse;
+
+        hse = container_of(fmt, struct hpp_sort_entry, hpp);
+
+        return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+}
+
+static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+                             struct hist_entry *he)
+{
+        struct hpp_sort_entry *hse;
+        size_t len;
+
+        hse = container_of(fmt, struct hpp_sort_entry, hpp);
+        len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+        return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
+}
+
+static struct hpp_sort_entry *
+__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+{
+        struct hpp_sort_entry *hse;
+
+        hse = malloc(sizeof(*hse));
+        if (hse == NULL) {
+                pr_err("Memory allocation failed\n");
+                return NULL;
+        }
+
+        hse->se = sd->entry;
+        hse->hpp.header = __sort__hpp_header;
+        hse->hpp.width = __sort__hpp_width;
+        hse->hpp.entry = __sort__hpp_entry;
+        hse->hpp.color = NULL;
+
+        hse->hpp.cmp = sd->entry->se_cmp;
+        hse->hpp.collapse = sd->entry->se_collapse ? : sd->entry->se_cmp;
+        hse->hpp.sort = sd->entry->se_sort ? : hse->hpp.collapse;
+
+        INIT_LIST_HEAD(&hse->hpp.list);
+        INIT_LIST_HEAD(&hse->hpp.sort_list);
+        hse->hpp.elide = false;
+
+        return hse;
+}
+
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+        return format->header == __sort__hpp_header;
+}
+
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+{
+        struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+        if (hse == NULL)
+                return -1;
+
+        perf_hpp__register_sort_field(&hse->hpp);
+        return 0;
+}
+
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+{
+        struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+
+        if (hse == NULL)
+                return -1;
+
+        perf_hpp__column_register(&hse->hpp);
+        return 0;
+}
+
+static int __sort_dimension__add(struct sort_dimension *sd)
+{
+        if (sd->taken)
+                return 0;
+
+        if (__sort_dimension__add_hpp_sort(sd) < 0)
+                return -1;
+
         if (sd->entry->se_collapse)
                 sort__need_collapse = 1;
 
-        if (list_empty(&hist_entry__sort_list))
-                sort__first_dimension = idx;
+        sd->taken = 1;
+
+        return 0;
+}
+
+static int __hpp_dimension__add(struct hpp_dimension *hd)
+{
+        if (!hd->taken) {
+                hd->taken = 1;
+
+                perf_hpp__register_sort_field(hd->fmt);
+        }
+        return 0;
+}
+
+static int __sort_dimension__add_output(struct sort_dimension *sd)
+{
+        if (sd->taken)
+                return 0;
+
+        if (__sort_dimension__add_hpp_output(sd) < 0)
+                return -1;
 
-        list_add_tail(&sd->entry->list, &hist_entry__sort_list);
         sd->taken = 1;
+        return 0;
+}
+
+static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+{
+        if (!hd->taken) {
+                hd->taken = 1;
+
+                perf_hpp__column_register(hd->fmt);
+        }
+        return 0;
 }
 
 int sort_dimension__add(const char *tok)
@@ -1068,8 +1263,16 @@ int sort_dimension__add(const char *tok)
                         sort__has_dso = 1;
                 }
 
-                __sort_dimension__add(sd, i);
-                return 0;
+                return __sort_dimension__add(sd);
+        }
+
+        for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+                struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+                if (strncasecmp(tok, hd->name, strlen(tok)))
+                        continue;
+
+                return __hpp_dimension__add(hd);
         }
 
         for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -1084,7 +1287,7 @@ int sort_dimension__add(const char *tok)
                 if (sd->entry == &sort_sym_from || sd->entry == &sort_sym_to)
                         sort__has_sym = 1;
 
-                __sort_dimension__add(sd, i + __SORT_BRANCH_STACK);
+                __sort_dimension__add(sd);
                 return 0;
         }
 
@@ -1100,18 +1303,47 @@ int sort_dimension__add(const char *tok)
                 if (sd->entry == &sort_mem_daddr_sym)
                         sort__has_sym = 1;
 
-                __sort_dimension__add(sd, i + __SORT_MEMORY_MODE);
+                __sort_dimension__add(sd);
                 return 0;
         }
 
         return -ESRCH;
 }
 
-int setup_sorting(void)
+static const char *get_default_sort_order(void)
 {
-        char *tmp, *tok, *str = strdup(sort_order);
+        const char *default_sort_orders[] = {
+                default_sort_order,
+                default_branch_sort_order,
+                default_mem_sort_order,
+                default_top_sort_order,
+                default_diff_sort_order,
+        };
+
+        BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders));
+
+        return default_sort_orders[sort__mode];
+}
+
+static int __setup_sorting(void)
+{
+        char *tmp, *tok, *str;
+        const char *sort_keys = sort_order;
         int ret = 0;
 
+        if (sort_keys == NULL) {
+                if (field_order) {
+                        /*
+                         * If user specified field order but no sort order,
+                         * we'll honor it and not add default sort orders.
+                         */
+                        return 0;
+                }
+
+                sort_keys = get_default_sort_order();
+        }
+
+        str = strdup(sort_keys);
         if (str == NULL) {
                 error("Not enough memory to setup sort keys");
                 return -ENOMEM;
@@ -1133,66 +1365,235 @@ int setup_sorting(void)
         return ret;
 }
 
-static void sort_entry__setup_elide(struct sort_entry *se,
-                                    struct strlist *list,
-                                    const char *list_name, FILE *fp)
+void perf_hpp__set_elide(int idx, bool elide)
+{
+        struct perf_hpp_fmt *fmt;
+        struct hpp_sort_entry *hse;
+
+        perf_hpp__for_each_format(fmt) {
+                if (!perf_hpp__is_sort_entry(fmt))
+                        continue;
+
+                hse = container_of(fmt, struct hpp_sort_entry, hpp);
+                if (hse->se->se_width_idx == idx) {
+                        fmt->elide = elide;
+                        break;
+                }
+        }
+}
+
+static bool __get_elide(struct strlist *list, const char *list_name, FILE *fp)
 {
         if (list && strlist__nr_entries(list) == 1) {
                 if (fp != NULL)
                         fprintf(fp, "# %s: %s\n", list_name,
                                 strlist__entry(list, 0)->s);
-                se->elide = true;
+                return true;
+        }
+        return false;
+}
+
+static bool get_elide(int idx, FILE *output)
+{
+        switch (idx) {
+        case HISTC_SYMBOL:
+                return __get_elide(symbol_conf.sym_list, "symbol", output);
+        case HISTC_DSO:
+                return __get_elide(symbol_conf.dso_list, "dso", output);
+        case HISTC_COMM:
+                return __get_elide(symbol_conf.comm_list, "comm", output);
+        default:
+                break;
         }
+
+        if (sort__mode != SORT_MODE__BRANCH)
+                return false;
+
+        switch (idx) {
+        case HISTC_SYMBOL_FROM:
+                return __get_elide(symbol_conf.sym_from_list, "sym_from", output);
+        case HISTC_SYMBOL_TO:
+                return __get_elide(symbol_conf.sym_to_list, "sym_to", output);
+        case HISTC_DSO_FROM:
+                return __get_elide(symbol_conf.dso_from_list, "dso_from", output);
+        case HISTC_DSO_TO:
+                return __get_elide(symbol_conf.dso_to_list, "dso_to", output);
+        default:
+                break;
+        }
+
+        return false;
 }
 
 void sort__setup_elide(FILE *output)
 {
-        struct sort_entry *se;
+        struct perf_hpp_fmt *fmt;
+        struct hpp_sort_entry *hse;
 
-        sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                "dso", output);
-        sort_entry__setup_elide(&sort_comm, symbol_conf.comm_list,
-                                "comm", output);
-        sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list,
-                                "symbol", output);
-
-        if (sort__mode == SORT_MODE__BRANCH) {
-                sort_entry__setup_elide(&sort_dso_from,
-                                        symbol_conf.dso_from_list,
-                                        "dso_from", output);
-                sort_entry__setup_elide(&sort_dso_to,
-                                        symbol_conf.dso_to_list,
-                                        "dso_to", output);
-                sort_entry__setup_elide(&sort_sym_from,
-                                        symbol_conf.sym_from_list,
-                                        "sym_from", output);
-                sort_entry__setup_elide(&sort_sym_to,
-                                        symbol_conf.sym_to_list,
-                                        "sym_to", output);
-        } else if (sort__mode == SORT_MODE__MEMORY) {
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                        "symbol_daddr", output);
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                        "dso_daddr", output);
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                        "mem", output);
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                        "local_weight", output);
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                        "tlb", output);
-                sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list,
-                                        "snoop", output);
+        perf_hpp__for_each_format(fmt) {
+                if (!perf_hpp__is_sort_entry(fmt))
+                        continue;
+
+                hse = container_of(fmt, struct hpp_sort_entry, hpp);
+                fmt->elide = get_elide(hse->se->se_width_idx, output);
         }
 
         /*
          * It makes no sense to elide all of sort entries.
          * Just revert them to show up again.
          */
-        list_for_each_entry(se, &hist_entry__sort_list, list) {
-                if (!se->elide)
+        perf_hpp__for_each_format(fmt) {
+                if (!perf_hpp__is_sort_entry(fmt))
+                        continue;
+
+                if (!fmt->elide)
                         return;
         }
 
-        list_for_each_entry(se, &hist_entry__sort_list, list)
-                se->elide = false;
+        perf_hpp__for_each_format(fmt) {
+                if (!perf_hpp__is_sort_entry(fmt))
+                        continue;
+
+                fmt->elide = false;
+        }
+}
+
+static int output_field_add(char *tok)
+{
+        unsigned int i;
+
+        for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+                struct sort_dimension *sd = &common_sort_dimensions[i];
+
+                if (strncasecmp(tok, sd->name, strlen(tok)))
+                        continue;
+
+                return __sort_dimension__add_output(sd);
+        }
+
+        for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+                struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+
+                if (strncasecmp(tok, hd->name, strlen(tok)))
+                        continue;
+
+                return __hpp_dimension__add_output(hd);
+        }
+
+        for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
+                struct sort_dimension *sd = &bstack_sort_dimensions[i];
+
+                if (strncasecmp(tok, sd->name, strlen(tok)))
+                        continue;
+
+                return __sort_dimension__add_output(sd);
+        }
+
+        for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
+                struct sort_dimension *sd = &memory_sort_dimensions[i];
+
+                if (strncasecmp(tok, sd->name, strlen(tok)))
+                        continue;
+
+                return __sort_dimension__add_output(sd);
+        }
+
+        return -ESRCH;
+}
+
+static void reset_dimensions(void)
+{
+        unsigned int i;
+
+        for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++)
+                common_sort_dimensions[i].taken = 0;
+
+        for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++)
+                hpp_sort_dimensions[i].taken = 0;
+
+        for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++)
+                bstack_sort_dimensions[i].taken = 0;
+
+        for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++)
+                memory_sort_dimensions[i].taken = 0;
+}
+
+static int __setup_output_field(void)
+{
+        char *tmp, *tok, *str;
+        int ret = 0;
+
+        if (field_order == NULL)
+                return 0;
+
+        reset_dimensions();
+
+        str = strdup(field_order);
+        if (str == NULL) {
+                error("Not enough memory to setup output fields");
+                return -ENOMEM;
+        }
+
+        for (tok = strtok_r(str, ", ", &tmp);
+                        tok; tok = strtok_r(NULL, ", ", &tmp)) {
+                ret = output_field_add(tok);
+                if (ret == -EINVAL) {
+                        error("Invalid --fields key: `%s'", tok);
+                        break;
+                } else if (ret == -ESRCH) {
+                        error("Unknown --fields key: `%s'", tok);
+                        break;
+                }
+        }
+
+        free(str);
+        return ret;
+}
+
+int setup_sorting(void)
+{
+        int err;
+
+        err = __setup_sorting();
+        if (err < 0)
+                return err;
+
+        if (parent_pattern != default_parent_pattern) {
+                err = sort_dimension__add("parent");
+                if (err < 0)
+                        return err;
+        }
+
+        reset_dimensions();
+
+        /*
+         * perf diff doesn't use default hpp output fields.
+         */
+        if (sort__mode != SORT_MODE__DIFF)
+                perf_hpp__init();
+
+        err = __setup_output_field();
+        if (err < 0)
+                return err;
+
+        /* copy sort keys to output fields */
+        perf_hpp__setup_output_field();
+        /* and then copy output fields to sort keys */
+        perf_hpp__append_sort_keys();
+
+        return 0;
+}
+
+void reset_output_field(void)
+{
+        sort__need_collapse = 0;
+        sort__has_parent = 0;
+        sort__has_sym = 0;
+        sort__has_dso = 0;
+
+        field_order = NULL;
+        sort_order = NULL;
+
+        reset_dimensions();
+        perf_hpp__reset_output_field();
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 43e5ff42a609..5bf0098d6b06 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -20,11 +20,12 @@
 
 #include "parse-options.h"
 #include "parse-events.h"
-
+#include "hist.h"
 #include "thread.h"
 
 extern regex_t parent_regex;
 extern const char *sort_order;
+extern const char *field_order;
 extern const char default_parent_pattern[];
 extern const char *parent_pattern;
 extern const char default_sort_order[];
@@ -81,6 +82,7 @@ struct hist_entry {
                 struct list_head head;
         } pairs;
         struct he_stat          stat;
+        struct he_stat          *stat_acc;
         struct map_symbol       ms;
         struct thread           *thread;
         struct comm             *comm;
@@ -129,10 +131,27 @@ static inline void hist_entry__add_pair(struct hist_entry *pair,
         list_add_tail(&pair->pairs.node, &he->pairs.head);
 }
 
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+        u64 period = he->stat.period;
+        u64 total_period = hists__total_period(he->hists);
+
+        if (unlikely(total_period == 0))
+                return 0;
+
+        if (symbol_conf.cumulate_callchain)
+                period = he->stat_acc->period;
+
+        return period * 100.0 / total_period;
+}
+
+
 enum sort_mode {
         SORT_MODE__NORMAL,
         SORT_MODE__BRANCH,
         SORT_MODE__MEMORY,
+        SORT_MODE__TOP,
+        SORT_MODE__DIFF,
 };
 
 enum sort_type {
@@ -179,18 +198,21 @@ struct sort_entry {
 
         int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *);
         int64_t (*se_collapse)(struct hist_entry *, struct hist_entry *);
+        int64_t (*se_sort)(struct hist_entry *, struct hist_entry *);
         int     (*se_snprintf)(struct hist_entry *he, char *bf, size_t size,
                                unsigned int width);
         u8      se_width_idx;
-        bool    elide;
 };
 
 extern struct sort_entry sort_thread;
 extern struct list_head hist_entry__sort_list;
 
 int setup_sorting(void);
+int setup_output_field(void);
+void reset_output_field(void);
 extern int sort_dimension__add(const char *);
 void sort__setup_elide(FILE *fp);
+void perf_hpp__set_elide(int idx, bool elide);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index ae8ccd7227cf..5667fc3e39cf 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_STATS_H
 #define __PERF_STATS_H
 
-#include "types.h"
+#include <linux/types.h>
 
 struct stats
 {
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 43262b83c541..6a0a13d07a28 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -17,7 +17,7 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
-#include <linux/bitops.h>
+#include <linux/bitmap.h>
 
 #include "perf.h"
 #include "svghelper.h"
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index f7b4d6e699ea..e3aff5332e30 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_SVGHELPER_H
 #define __PERF_SVGHELPER_H
 
-#include "types.h"
+#include <linux/types.h>
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 3b7dbf51d4a9..6864661a79dd 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -6,6 +6,7 @@
 #include <inttypes.h>
 
 #include "symbol.h"
+#include "vdso.h"
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
@@ -618,6 +619,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
                 GElf_Shdr shdr;
                 ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
                                 ehdr.e_type == ET_REL ||
+                                is_vdso_map(dso->short_name) ||
                                 elf_section_by_name(elf, &ehdr, &shdr,
                                                      ".gnu.prelink_undo",
                                                      NULL) != NULL);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 95e249779931..7b9096f29cdb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -29,11 +29,12 @@ int vmlinux_path__nr_entries;
 char **vmlinux_path;
 
 struct symbol_conf symbol_conf = {
-        .use_modules      = true,
-        .try_vmlinux_path = true,
-        .annotate_src     = true,
-        .demangle         = true,
-        .symfs            = "",
+        .use_modules            = true,
+        .try_vmlinux_path       = true,
+        .annotate_src           = true,
+        .demangle               = true,
+        .cumulate_callchain     = true,
+        .symfs                  = "",
 };
 
 static enum dso_binary_type binary_type_symtab[] = {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 501e4e722e8e..615c752dd767 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -12,6 +12,7 @@
 #include <byteswap.h>
 #include <libgen.h>
 #include "build-id.h"
+#include "event.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -108,6 +109,7 @@ struct symbol_conf {
                         show_nr_samples,
                         show_total_period,
                         use_callchain,
+                        cumulate_callchain,
                         exclude_other,
                         show_cpu_utilization,
                         initialized,
@@ -115,7 +117,8 @@ struct symbol_conf {
                         annotate_asm_raw,
                         annotate_src,
                         event_group,
-                        demangle;
+                        demangle,
+                        filter_relative;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 3ce0498bdae6..2fde0d5e40b5 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -8,6 +8,22 @@
 #include "debug.h"
 #include "comm.h"
 
+int thread__init_map_groups(struct thread *thread, struct machine *machine)
+{
+        struct thread *leader;
+        pid_t pid = thread->pid_;
+
+        if (pid == thread->tid) {
+                thread->mg = map_groups__new();
+        } else {
+                leader = machine__findnew_thread(machine, pid, pid);
+                if (leader)
+                        thread->mg = map_groups__get(leader->mg);
+        }
+
+        return thread->mg ? 0 : -1;
+}
+
 struct thread *thread__new(pid_t pid, pid_t tid)
 {
         char *comm_str;
@@ -15,7 +31,6 @@ struct thread *thread__new(pid_t pid, pid_t tid)
         struct thread *thread = zalloc(sizeof(*thread));
 
         if (thread != NULL) {
-                map_groups__init(&thread->mg);
                 thread->pid_ = pid;
                 thread->tid = tid;
                 thread->ppid = -1;
@@ -45,7 +60,8 @@ void thread__delete(struct thread *thread)
 {
         struct comm *comm, *tmp;
 
-        map_groups__exit(&thread->mg);
+        map_groups__put(thread->mg);
+        thread->mg = NULL;
         list_for_each_entry_safe(comm, tmp, &thread->comm_list, list) {
                 list_del(&comm->list);
                 comm__free(comm);
@@ -111,18 +127,35 @@ int thread__comm_len(struct thread *thread)
 size_t thread__fprintf(struct thread *thread, FILE *fp)
 {
         return fprintf(fp, "Thread %d %s\n", thread->tid, thread__comm_str(thread)) +
-               map_groups__fprintf(&thread->mg, verbose, fp);
+               map_groups__fprintf(thread->mg, verbose, fp);
 }
 
 void thread__insert_map(struct thread *thread, struct map *map)
 {
-        map_groups__fixup_overlappings(&thread->mg, map, verbose, stderr);
-        map_groups__insert(&thread->mg, map);
+        map_groups__fixup_overlappings(thread->mg, map, verbose, stderr);
+        map_groups__insert(thread->mg, map);
+}
+
+static int thread__clone_map_groups(struct thread *thread,
+                                    struct thread *parent)
+{
+        int i;
+
+        /* This is new thread, we share map groups for process. */
+        if (thread->pid_ == parent->pid_)
+                return 0;
+
+        /* But this one is new process, copy maps. */
+        for (i = 0; i < MAP__NR_TYPES; ++i)
+                if (map_groups__clone(thread->mg, parent->mg, i) < 0)
+                        return -ENOMEM;
+
+        return 0;
 }
 
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 {
-        int i, err;
+        int err;
 
         if (parent->comm_set) {
                 const char *comm = thread__comm_str(parent);
@@ -134,13 +167,8 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
                 thread->comm_set = true;
         }
 
-        for (i = 0; i < MAP__NR_TYPES; ++i)
-                if (map_groups__clone(&thread->mg, &parent->mg, i) < 0)
-                        return -ENOMEM;
-
         thread->ppid = parent->tid;
-
-        return 0;
+        return thread__clone_map_groups(thread, parent);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b29f085aede..3c0c2724f82c 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -13,7 +13,7 @@ struct thread {
                 struct rb_node   rb_node;
                 struct list_head node;
         };
-        struct map_groups       mg;
+        struct map_groups       *mg;
         pid_t                   pid_; /* Not all tools update this */
         pid_t                   tid;
         pid_t                   ppid;
@@ -30,6 +30,7 @@ struct machine;
 struct comm;
 
 struct thread *thread__new(pid_t pid, pid_t tid);
+int thread__init_map_groups(struct thread *thread, struct machine *machine);
 void thread__delete(struct thread *thread);
 static inline void thread__exited(struct thread *thread)
 {
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index dab14d0ad3d0..f92c37abb0a8 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -2,7 +2,7 @@
 #define __PERF_TOP_H 1
 
 #include "tool.h"
-#include "types.h"
+#include <linux/types.h>
 #include <stddef.h>
 #include <stdbool.h>
 #include <termios.h>
diff --git a/tools/perf/util/types.h b/tools/perf/util/types.h
deleted file mode 100644
index c51fa6b70a28..000000000000
--- a/tools/perf/util/types.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef __PERF_TYPES_H
-#define __PERF_TYPES_H
-
-#include <stdint.h>
-
-/*
- * We define u64 as uint64_t for every architecture
- * so that we can print it with "%"PRIx64 without getting warnings.
- */
-typedef uint64_t           u64;
-typedef int64_t            s64;
-typedef unsigned int       u32;
-typedef signed int         s32;
-typedef unsigned short     u16;
-typedef signed short       s16;
-typedef unsigned char      u8;
-typedef signed char        s8;
-
-union u64_swap {
-        u64 val64;
-        u32 val32[2];
-};
-
-#endif /* __PERF_TYPES_H */
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 67db73ec3dab..5ec80a575b50 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -7,7 +7,7 @@
 #include "unwind-libdw.h"
 #include "machine.h"
 #include "thread.h"
-#include "types.h"
+#include <linux/types.h>
 #include "event.h"
 #include "perf_regs.h"
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index b031316f221a..f03061260b4e 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -1,7 +1,7 @@
 #ifndef __UNWIND_H
 #define __UNWIND_H
 
-#include "types.h"
+#include <linux/types.h>
 #include "event.h"
 #include "symbol.h"
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9f66549562bd..7fff6be07f07 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -166,6 +166,8 @@ static ssize_t ion(bool is_read, int fd, void *buf, size_t n)
                 ssize_t ret = is_read ? read(fd, buf, left) :
                                         write(fd, buf, left);
 
+                if (ret < 0 && errno == EINTR)
+                        continue;
                 if (ret <= 0)
                         return ret;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 6995d66f225c..b03da44e94e4 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -69,7 +69,7 @@
 #include <sys/ioctl.h>
 #include <inttypes.h>
 #include <linux/magic.h>
-#include "types.h"
+#include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/debugfs.h>
 #include <termios.h>
diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h
index 2fa967e1a88a..b21a80c6cf8d 100644
--- a/tools/perf/util/values.h
+++ b/tools/perf/util/values.h
@@ -1,7 +1,7 @@
 #ifndef __PERF_VALUES_H
 #define __PERF_VALUES_H
 
-#include "types.h"
+#include <linux/types.h>
 
 struct perf_read_values {
         int threads;