Merge branch 'linus' into sched/urgent, to pick up dependencies

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

165 files changed, 11725 insertions, 1675 deletions

diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 4a96473b180f..ee566e8bd1cf 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -85,7 +85,7 @@ $(OUTPUT)%.i: %.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_i_c)
 
-$(OUTPUT)%.i: %.S FORCE
+$(OUTPUT)%.s: %.S FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_i_c)
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 02db3cdff20f..6b7707270aa3 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS ?=                        \
+FEATURE_TESTS_BASIC :=                  \
         backtrace                       \
         dwarf                           \
         fortify-source                  \
@@ -46,6 +46,7 @@ FEATURE_TESTS ?=			\
         libpython                       \
         libpython-version               \
         libslang                        \
+        libcrypto                       \
         libunwind                       \
         pthread-attr-setaffinity-np     \
         stackprotector-all              \
@@ -56,6 +57,25 @@ FEATURE_TESTS ?=			\
         get_cpuid                       \
         bpf
 
+# FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
+# of all feature tests
+FEATURE_TESTS_EXTRA :=                  \
+        bionic                          \
+        compile-32                      \
+        compile-x32                     \
+        cplus-demangle                  \
+        hello                           \
+        libbabeltrace                   \
+        liberty                         \
+        liberty-z                       \
+        libunwind-debug-frame
+
+FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
+
+ifeq ($(FEATURE_TESTS),all)
+  FEATURE_TESTS := $(FEATURE_TESTS_BASIC) $(FEATURE_TESTS_EXTRA)
+endif
+
 FEATURE_DISPLAY ?=                      \
         dwarf                           \
         glibc                           \
@@ -68,6 +88,7 @@ FEATURE_DISPLAY ?=			\
         libperl                         \
         libpython                       \
         libslang                        \
+        libcrypto                       \
         libunwind                       \
         libdw-dwarf-unwind              \
         zlib                            \
@@ -100,6 +121,14 @@ ifeq ($(feature-all), 1)
   # test-all.c passed - just set all the core feature flags to 1:
   #
   $(foreach feat,$(FEATURE_TESTS),$(call feature_set,$(feat)))
+  #
+  # test-all.c does not comprise these tests, so we need to
+  # for this case to get features proper values
+  #
+  $(call feature_check,compile-32)
+  $(call feature_check,compile-x32)
+  $(call feature_check,bionic)
+  $(call feature_check,libbabeltrace)
 else
   $(foreach feat,$(FEATURE_TESTS),$(call feature_check,$(feat)))
 endif
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index bf8f0352264d..c5f4c417428d 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -23,6 +23,7 @@ FILES=					\
         test-libpython.bin              \
         test-libpython-version.bin      \
         test-libslang.bin               \
+        test-libcrypto.bin              \
         test-libunwind.bin              \
         test-libunwind-debug-frame.bin  \
         test-pthread-attr-setaffinity-np.bin    \
@@ -105,6 +106,9 @@ $(OUTPUT)test-libaudit.bin:
 $(OUTPUT)test-libslang.bin:
         $(BUILD) -I/usr/include/slang -lslang
 
+$(OUTPUT)test-libcrypto.bin:
+        $(BUILD) -lcrypto
+
 $(OUTPUT)test-gtk2.bin:
         $(BUILD) $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 81025cade45f..e499a36c1e4a 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -129,6 +129,10 @@
 # include "test-bpf.c"
 #undef main
 
+#define main main_test_libcrypto
+# include "test-libcrypto.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
         main_test_libpython();
@@ -158,6 +162,7 @@ int main(int argc, char *argv[])
         main_test_lzma();
         main_test_get_cpuid();
         main_test_bpf();
+        main_test_libcrypto();
 
         return 0;
 }
diff --git a/tools/build/feature/test-compile.c b/tools/build/feature/test-compile.c
index 31dbf45bf99c..c54e6551ae4c 100644
--- a/tools/build/feature/test-compile.c
+++ b/tools/build/feature/test-compile.c
@@ -1,4 +1,6 @@
+#include <stdio.h>
 int main(void)
 {
+        printf("Hello World!\n");
         return 0;
 }
diff --git a/tools/build/feature/test-libcrypto.c b/tools/build/feature/test-libcrypto.c
new file mode 100644
index 000000000000..bd79dc7f28d3
--- /dev/null
+++ b/tools/build/feature/test-libcrypto.c
@@ -0,0 +1,17 @@
+#include <openssl/sha.h>
+#include <openssl/md5.h>
+
+int main(void)
+{
+        MD5_CTX context;
+        unsigned char md[MD5_DIGEST_LENGTH + SHA_DIGEST_LENGTH];
+        unsigned char dat[] = "12345";
+
+        MD5_Init(&context);
+        MD5_Update(&context, &dat[0], sizeof(dat));
+        MD5_Final(&md[0], &context);
+
+        SHA1(&dat[0], sizeof(dat), &md[0]);
+
+        return 0;
+}
diff --git a/tools/lib/api/Build b/tools/lib/api/Build
index e8b8a23b9bf4..954c644f7ad9 100644
--- a/tools/lib/api/Build
+++ b/tools/lib/api/Build
@@ -1,3 +1,4 @@
 libapi-y += fd/
 libapi-y += fs/
 libapi-y += cpu.o
+libapi-y += debug.o
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index d85904dc9b38..bbc82c614bee 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -18,6 +18,7 @@ LIBFILE = $(OUTPUT)libapi.a
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
+CFLAGS += -I$(srctree)/tools/lib/api
 
 RM = rm -f
 
diff --git a/tools/lib/api/debug-internal.h b/tools/lib/api/debug-internal.h
new file mode 100644
index 000000000000..188f7880eafe
--- /dev/null
+++ b/tools/lib/api/debug-internal.h
@@ -0,0 +1,20 @@
+#ifndef __API_DEBUG_INTERNAL_H__
+#define __API_DEBUG_INTERNAL_H__
+
+#include "debug.h"
+
+#define __pr(func, fmt, ...)    \
+do {                            \
+        if ((func))             \
+                (func)("libapi: " fmt, ##__VA_ARGS__); \
+} while (0)
+
+extern libapi_print_fn_t __pr_warning;
+extern libapi_print_fn_t __pr_info;
+extern libapi_print_fn_t __pr_debug;
+
+#define pr_warning(fmt, ...)    __pr(__pr_warning, fmt, ##__VA_ARGS__)
+#define pr_info(fmt, ...)       __pr(__pr_info, fmt, ##__VA_ARGS__)
+#define pr_debug(fmt, ...)      __pr(__pr_debug, fmt, ##__VA_ARGS__)
+
+#endif /* __API_DEBUG_INTERNAL_H__ */
diff --git a/tools/lib/api/debug.c b/tools/lib/api/debug.c
new file mode 100644
index 000000000000..5fa5cf500a1f
--- /dev/null
+++ b/tools/lib/api/debug.c
@@ -0,0 +1,28 @@
+#include <stdio.h>
+#include <stdarg.h>
+#include "debug.h"
+#include "debug-internal.h"
+
+static int __base_pr(const char *format, ...)
+{
+        va_list args;
+        int err;
+
+        va_start(args, format);
+        err = vfprintf(stderr, format, args);
+        va_end(args);
+        return err;
+}
+
+libapi_print_fn_t __pr_warning = __base_pr;
+libapi_print_fn_t __pr_info    = __base_pr;
+libapi_print_fn_t __pr_debug;
+
+void libapi_set_print(libapi_print_fn_t warn,
+                      libapi_print_fn_t info,
+                      libapi_print_fn_t debug)
+{
+        __pr_warning = warn;
+        __pr_info    = info;
+        __pr_debug   = debug;
+}
diff --git a/tools/lib/api/debug.h b/tools/lib/api/debug.h
new file mode 100644
index 000000000000..a0872f68fc56
--- /dev/null
+++ b/tools/lib/api/debug.h
@@ -0,0 +1,10 @@
+#ifndef __API_DEBUG_H__
+#define __API_DEBUG_H__
+
+typedef int (*libapi_print_fn_t)(const char *, ...);
+
+void libapi_set_print(libapi_print_fn_t warn,
+                      libapi_print_fn_t info,
+                      libapi_print_fn_t debug);
+
+#endif /* __API_DEBUG_H__ */
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 459599d1b6c4..ef78c22ff44d 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -13,6 +13,7 @@
 #include <sys/mount.h>
 
 #include "fs.h"
+#include "debug-internal.h"
 
 #define _STR(x) #x
 #define STR(x) _STR(x)
@@ -300,6 +301,56 @@ int filename__read_ull(const char *filename, unsigned long long *value)
         return err;
 }
 
+#define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
+
+int filename__read_str(const char *filename, char **buf, size_t *sizep)
+{
+        size_t size = 0, alloc_size = 0;
+        void *bf = NULL, *nbf;
+        int fd, n, err = 0;
+        char sbuf[STRERR_BUFSIZE];
+
+        fd = open(filename, O_RDONLY);
+        if (fd < 0)
+                return -errno;
+
+        do {
+                if (size == alloc_size) {
+                        alloc_size += BUFSIZ;
+                        nbf = realloc(bf, alloc_size);
+                        if (!nbf) {
+                                err = -ENOMEM;
+                                break;
+                        }
+
+                        bf = nbf;
+                }
+
+                n = read(fd, bf + size, alloc_size - size);
+                if (n < 0) {
+                        if (size) {
+                                pr_warning("read failed %d: %s\n", errno,
+                                         strerror_r(errno, sbuf, sizeof(sbuf)));
+                                err = 0;
+                        } else
+                                err = -errno;
+
+                        break;
+                }
+
+                size += n;
+        } while (n > 0);
+
+        if (!err) {
+                *sizep = size;
+                *buf   = bf;
+        } else
+                free(bf);
+
+        close(fd);
+        return err;
+}
+
 int sysfs__read_ull(const char *entry, unsigned long long *value)
 {
         char path[PATH_MAX];
@@ -326,6 +377,19 @@ int sysfs__read_int(const char *entry, int *value)
         return filename__read_int(path, value);
 }
 
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep)
+{
+        char path[PATH_MAX];
+        const char *sysfs = sysfs__mountpoint();
+
+        if (!sysfs)
+                return -1;
+
+        snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
+
+        return filename__read_str(path, buf, sizep);
+}
+
 int sysctl__read_int(const char *sysctl, int *value)
 {
         char path[PATH_MAX];
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index d024a7f682f6..9f6598098dc5 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -2,6 +2,7 @@
 #define __API_FS__
 
 #include <stdbool.h>
+#include <unistd.h>
 
 /*
  * On most systems <limits.h> would have given us this, but  not on some systems
@@ -26,8 +27,10 @@ FS(tracefs)
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
+int filename__read_str(const char *filename, char **buf, size_t *sizep);
 
 int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
+int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
 #endif /* __API_FS__ */
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8334a5a9d5d7..7e543c3102d4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -201,6 +201,7 @@ struct bpf_object {
                         Elf_Data *data;
                 } *reloc;
                 int nr_reloc;
+                int maps_shndx;
         } efile;
         /*
          * All loaded bpf_object is linked in a list, which is
@@ -350,6 +351,7 @@ static struct bpf_object *bpf_object__new(const char *path,
          */
         obj->efile.obj_buf = obj_buf;
         obj->efile.obj_buf_sz = obj_buf_sz;
+        obj->efile.maps_shndx = -1;
 
         obj->loaded = false;
 
@@ -529,12 +531,12 @@ bpf_object__init_maps(struct bpf_object *obj, void *data,
 }
 
 static int
-bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
+bpf_object__init_maps_name(struct bpf_object *obj)
 {
         int i;
         Elf_Data *symbols = obj->efile.symbols;
 
-        if (!symbols || maps_shndx < 0)
+        if (!symbols || obj->efile.maps_shndx < 0)
                 return -EINVAL;
 
         for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
@@ -544,7 +546,7 @@ bpf_object__init_maps_name(struct bpf_object *obj, int maps_shndx)
 
                 if (!gelf_getsym(symbols, i, &sym))
                         continue;
-                if (sym.st_shndx != maps_shndx)
+                if (sym.st_shndx != obj->efile.maps_shndx)
                         continue;
 
                 map_name = elf_strptr(obj->efile.elf,
@@ -572,7 +574,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
         Elf *elf = obj->efile.elf;
         GElf_Ehdr *ep = &obj->efile.ehdr;
         Elf_Scn *scn = NULL;
-        int idx = 0, err = 0, maps_shndx = -1;
+        int idx = 0, err = 0;
 
         /* Elf is corrupted/truncated, avoid calling elf_strptr. */
         if (!elf_rawdata(elf_getscn(elf, ep->e_shstrndx), NULL)) {
@@ -625,7 +627,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                 else if (strcmp(name, "maps") == 0) {
                         err = bpf_object__init_maps(obj, data->d_buf,
                                                     data->d_size);
-                        maps_shndx = idx;
+                        obj->efile.maps_shndx = idx;
                 } else if (sh.sh_type == SHT_SYMTAB) {
                         if (obj->efile.symbols) {
                                 pr_warning("bpf: multiple SYMTAB in %s\n",
@@ -674,8 +676,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
                 pr_warning("Corrupted ELF file: index of strtab invalid\n");
                 return LIBBPF_ERRNO__FORMAT;
         }
-        if (maps_shndx >= 0)
-                err = bpf_object__init_maps_name(obj, maps_shndx);
+        if (obj->efile.maps_shndx >= 0)
+                err = bpf_object__init_maps_name(obj);
 out:
         return err;
 }
@@ -697,7 +699,8 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
 static int
 bpf_program__collect_reloc(struct bpf_program *prog,
                            size_t nr_maps, GElf_Shdr *shdr,
-                           Elf_Data *data, Elf_Data *symbols)
+                           Elf_Data *data, Elf_Data *symbols,
+                           int maps_shndx)
 {
         int i, nrels;
 
@@ -724,9 +727,6 @@ bpf_program__collect_reloc(struct bpf_program *prog,
                         return -LIBBPF_ERRNO__FORMAT;
                 }
 
-                insn_idx = rel.r_offset / sizeof(struct bpf_insn);
-                pr_debug("relocation: insn_idx=%u\n", insn_idx);
-
                 if (!gelf_getsym(symbols,
                                  GELF_R_SYM(rel.r_info),
                                  &sym)) {
@@ -735,6 +735,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
                         return -LIBBPF_ERRNO__FORMAT;
                 }
 
+                if (sym.st_shndx != maps_shndx) {
+                        pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
+                                   prog->section_name, sym.st_shndx);
+                        return -LIBBPF_ERRNO__RELOC;
+                }
+
+                insn_idx = rel.r_offset / sizeof(struct bpf_insn);
+                pr_debug("relocation: insn_idx=%u\n", insn_idx);
+
                 if (insns[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) {
                         pr_warning("bpf: relocation: invalid relo for insns[%d].code 0x%x\n",
                                    insn_idx, insns[insn_idx].code);
@@ -863,7 +872,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 
                 err = bpf_program__collect_reloc(prog, nr_maps,
                                                  shdr, data,
-                                                 obj->efile.symbols);
+                                                 obj->efile.symbols,
+                                                 obj->efile.maps_shndx);
                 if (err)
                         return err;
         }
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 90d2baeb621a..1d57af56814b 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -100,7 +100,7 @@ include $(srctree)/tools/build/Makefile.include
 
 do_compile_shared_library =                     \
         ($(print_shared_lib_compile)            \
-        $(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -s $@ liblockdep.so))
+        $(CC) --shared $^ -o $@ -lpthread -ldl -Wl,-soname='"$@"';$(shell ln -sf $@ liblockdep.so))
 
 do_build_static_lib =                           \
         ($(print_static_lib_build)              \
diff --git a/tools/lib/lockdep/common.c b/tools/lib/lockdep/common.c
index 9be663340f0a..d1c89cc06f5f 100644
--- a/tools/lib/lockdep/common.c
+++ b/tools/lib/lockdep/common.c
@@ -11,11 +11,6 @@ static __thread struct task_struct current_obj;
 bool debug_locks = true;
 bool debug_locks_silent;
 
-__attribute__((constructor)) static void liblockdep_init(void)
-{
-        lockdep_init();
-}
-
 __attribute__((destructor)) static void liblockdep_exit(void)
 {
         debug_check_no_locks_held();
diff --git a/tools/lib/lockdep/include/liblockdep/common.h b/tools/lib/lockdep/include/liblockdep/common.h
index a60c14b9662a..6e66277ec437 100644
--- a/tools/lib/lockdep/include/liblockdep/common.h
+++ b/tools/lib/lockdep/include/liblockdep/common.h
@@ -44,7 +44,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 void lock_release(struct lockdep_map *lock, int nested,
                         unsigned long ip);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void lockdep_init(void);
 
 #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
         { .name = (_name), .key = (void *)(_key), }
diff --git a/tools/lib/lockdep/lockdep.c b/tools/lib/lockdep/lockdep.c
index f42b7e9aa48f..a0a2e3a266af 100644
--- a/tools/lib/lockdep/lockdep.c
+++ b/tools/lib/lockdep/lockdep.c
@@ -1,2 +1,8 @@
 #include <linux/lockdep.h>
+
+/* Trivial API wrappers, we don't (yet) have RCU in user-space: */
+#define hlist_for_each_entry_rcu        hlist_for_each_entry
+#define hlist_add_head_rcu              hlist_add_head
+#define hlist_del_rcu                   hlist_del
+
 #include "../../../kernel/locking/lockdep.c"
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 21cdf869a01b..52844847569c 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -439,7 +439,5 @@ __attribute__((constructor)) static void init_preload(void)
         ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
 #endif
 
-        lockdep_init();
-
         __init_state = done;
 }
diff --git a/tools/lib/lockdep/tests/AA.c b/tools/lib/lockdep/tests/AA.c
index 0f782ff404ac..18211a5f354f 100644
--- a/tools/lib/lockdep/tests/AA.c
+++ b/tools/lib/lockdep/tests/AA.c
@@ -1,13 +1,13 @@
 #include <liblockdep/mutex.h>
 
-void main(void)
+int main(void)
 {
-        pthread_mutex_t a, b;
+        pthread_mutex_t a;
 
         pthread_mutex_init(&a, NULL);
-        pthread_mutex_init(&b, NULL);
 
         pthread_mutex_lock(&a);
-        pthread_mutex_lock(&b);
         pthread_mutex_lock(&a);
+
+        return 0;
 }
diff --git a/tools/lib/lockdep/tests/ABA.c b/tools/lib/lockdep/tests/ABA.c
new file mode 100644
index 000000000000..0f782ff404ac
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABA.c
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+        pthread_mutex_t a, b;
+
+        pthread_mutex_init(&a, NULL);
+        pthread_mutex_init(&b, NULL);
+
+        pthread_mutex_lock(&a);
+        pthread_mutex_lock(&b);
+        pthread_mutex_lock(&a);
+}
diff --git a/tools/lib/lockdep/tests/ABBA_2threads.c b/tools/lib/lockdep/tests/ABBA_2threads.c
new file mode 100644
index 000000000000..cd807d736361
--- /dev/null
+++ b/tools/lib/lockdep/tests/ABBA_2threads.c
@@ -0,0 +1,46 @@
+#include <stdio.h>
+#include <pthread.h>
+
+pthread_mutex_t a = PTHREAD_MUTEX_INITIALIZER;
+pthread_mutex_t b = PTHREAD_MUTEX_INITIALIZER;
+pthread_barrier_t bar;
+
+void *ba_lock(void *arg)
+{
+        int ret, i;
+
+        pthread_mutex_lock(&b);
+
+        if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD)
+                pthread_barrier_destroy(&bar);
+
+        pthread_mutex_lock(&a);
+
+        pthread_mutex_unlock(&a);
+        pthread_mutex_unlock(&b);
+}
+
+int main(void)
+{
+        pthread_t t;
+
+        pthread_barrier_init(&bar, NULL, 2);
+
+        if (pthread_create(&t, NULL, ba_lock, NULL)) {
+                fprintf(stderr, "pthread_create() failed\n");
+                return 1;
+        }
+        pthread_mutex_lock(&a);
+
+        if (pthread_barrier_wait(&bar) == PTHREAD_BARRIER_SERIAL_THREAD)
+                pthread_barrier_destroy(&bar);
+
+        pthread_mutex_lock(&b);
+
+        pthread_mutex_unlock(&b);
+        pthread_mutex_unlock(&a);
+
+        pthread_join(t, NULL);
+
+        return 0;
+}
diff --git a/tools/lib/lockdep/uinclude/linux/compiler.h b/tools/lib/lockdep/uinclude/linux/compiler.h
index 6386dc3182a0..fd3e56a83fc2 100644
--- a/tools/lib/lockdep/uinclude/linux/compiler.h
+++ b/tools/lib/lockdep/uinclude/linux/compiler.h
@@ -3,6 +3,7 @@
 
 #define __used          __attribute__((__unused__))
 #define unlikely
+#define READ_ONCE(x) (x)
 #define WRITE_ONCE(x, val) x=(val)
 #define RCU_INIT_POINTER(p, v) p=(v)
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index c3bd294a63d1..190cc886ab91 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1951,6 +1951,7 @@ process_op(struct event_format *event, struct print_arg *arg, char **tok)
                    strcmp(token, "*") == 0 ||
                    strcmp(token, "^") == 0 ||
                    strcmp(token, "/") == 0 ||
+                   strcmp(token, "%") == 0 ||
                    strcmp(token, "<") == 0 ||
                    strcmp(token, ">") == 0 ||
                    strcmp(token, "<=") == 0 ||
@@ -2397,6 +2398,12 @@ static int arg_num_eval(struct print_arg *arg, long long *val)
                                 break;
                         *val = left + right;
                         break;
+                case '~':
+                        ret = arg_num_eval(arg->op.right, &right);
+                        if (!ret)
+                                break;
+                        *val = ~right;
+                        break;
                 default:
                         do_warning("unknown op '%s'", arg->op.op);
                         ret = 0;
@@ -2634,6 +2641,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 
 free_field:
         free_arg(arg->hex.field);
+        arg->hex.field = NULL;
 out:
         *tok = NULL;
         return EVENT_ERROR;
@@ -2658,8 +2666,10 @@ process_int_array(struct event_format *event, struct print_arg *arg, char **tok)
 
 free_size:
         free_arg(arg->int_array.count);
+        arg->int_array.count = NULL;
 free_field:
         free_arg(arg->int_array.field);
+        arg->int_array.field = NULL;
 out:
         *tok = NULL;
         return EVENT_ERROR;
@@ -3689,6 +3699,9 @@ eval_num_arg(void *data, int size, struct event_format *event, struct print_arg
                 case '/':
                         val = left / right;
                         break;
+                case '%':
+                        val = left % right;
+                        break;
                 case '*':
                         val = left * right;
                         break;
@@ -4971,7 +4984,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
                                                 break;
                                         }
                                 }
-                                if (pevent->long_size == 8 && ls &&
+                                if (pevent->long_size == 8 && ls == 1 &&
                                     sizeof(long) != 8) {
                                         char *p;
 
@@ -5335,41 +5348,45 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
         return false;
 }
 
-void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
-                        struct pevent_record *record, bool use_trace_clock)
+/**
+ * pevent_find_event_by_record - return the event from a given record
+ * @pevent: a handle to the pevent
+ * @record: The record to get the event from
+ *
+ * Returns the associated event for a given record, or NULL if non is
+ * is found.
+ */
+struct event_format *
+pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record)
 {
-        static const char *spaces = "                    "; /* 20 spaces */
-        struct event_format *event;
-        unsigned long secs;
-        unsigned long usecs;
-        unsigned long nsecs;
-        const char *comm;
-        void *data = record->data;
         int type;
-        int pid;
-        int len;
-        int p;
-        bool use_usec_format;
-
-        use_usec_format = is_timestamp_in_us(pevent->trace_clock,
-                                                        use_trace_clock);
-        if (use_usec_format) {
-                secs = record->ts / NSECS_PER_SEC;
-                nsecs = record->ts - secs * NSECS_PER_SEC;
-        }
 
         if (record->size < 0) {
                 do_warning("ug! negative record size %d", record->size);
-                return;
+                return NULL;
         }
 
-        type = trace_parse_common_type(pevent, data);
+        type = trace_parse_common_type(pevent, record->data);
 
-        event = pevent_find_event(pevent, type);
-        if (!event) {
-                do_warning("ug! no event found for type %d", type);
-                return;
-        }
+        return pevent_find_event(pevent, type);
+}
+
+/**
+ * pevent_print_event_task - Write the event task comm, pid and CPU
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ *
+ * Writes the tasks comm, pid and CPU to @s.
+ */
+void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s,
+                             struct event_format *event,
+                             struct pevent_record *record)
+{
+        void *data = record->data;
+        const char *comm;
+        int pid;
 
         pid = parse_common_pid(pevent, data);
         comm = find_cmdline(pevent, pid);
@@ -5377,9 +5394,43 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
         if (pevent->latency_format) {
                 trace_seq_printf(s, "%8.8s-%-5d %3d",
                        comm, pid, record->cpu);
-                pevent_data_lat_fmt(pevent, s, record);
         } else
                 trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
+}
+
+/**
+ * pevent_print_event_time - Write the event timestamp
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ *
+ * Writes the timestamp of the record into @s.
+ */
+void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
+                             struct event_format *event,
+                             struct pevent_record *record,
+                             bool use_trace_clock)
+{
+        unsigned long secs;
+        unsigned long usecs;
+        unsigned long nsecs;
+        int p;
+        bool use_usec_format;
+
+        use_usec_format = is_timestamp_in_us(pevent->trace_clock,
+                                                        use_trace_clock);
+        if (use_usec_format) {
+                secs = record->ts / NSECS_PER_SEC;
+                nsecs = record->ts - secs * NSECS_PER_SEC;
+        }
+
+        if (pevent->latency_format) {
+                trace_seq_printf(s, " %3d", record->cpu);
+                pevent_data_lat_fmt(pevent, s, record);
+        } else
+                trace_seq_printf(s, " [%03d]", record->cpu);
 
         if (use_usec_format) {
                 if (pevent->flags & PEVENT_NSEC_OUTPUT) {
@@ -5387,14 +5438,36 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
                         p = 9;
                 } else {
                         usecs = (nsecs + 500) / NSECS_PER_USEC;
+                        /* To avoid usecs larger than 1 sec */
+                        if (usecs >= 1000000) {
+                                usecs -= 1000000;
+                                secs++;
+                        }
                         p = 6;
                 }
 
-                trace_seq_printf(s, " %5lu.%0*lu: %s: ",
-                                        secs, p, usecs, event->name);
+                trace_seq_printf(s, " %5lu.%0*lu:", secs, p, usecs);
         } else
-                trace_seq_printf(s, " %12llu: %s: ",
-                                        record->ts, event->name);
+                trace_seq_printf(s, " %12llu:", record->ts);
+}
+
+/**
+ * pevent_print_event_data - Write the event data section
+ * @pevent: a handle to the pevent
+ * @s: the trace_seq to write to
+ * @event: the handle to the record's event
+ * @record: The record to get the event from
+ *
+ * Writes the parsing of the record's data to @s.
+ */
+void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s,
+                             struct event_format *event,
+                             struct pevent_record *record)
+{
+        static const char *spaces = "                    "; /* 20 spaces */
+        int len;
+
+        trace_seq_printf(s, " %s: ", event->name);
 
         /* Space out the event names evenly. */
         len = strlen(event->name);
@@ -5404,6 +5477,23 @@ void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
         pevent_event_info(s, event, record);
 }
 
+void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
+                        struct pevent_record *record, bool use_trace_clock)
+{
+        struct event_format *event;
+
+        event = pevent_find_event_by_record(pevent, record);
+        if (!event) {
+                do_warning("ug! no event found for type %d",
+                           trace_parse_common_type(pevent, record->data));
+                return;
+        }
+
+        pevent_print_event_task(pevent, s, event, record);
+        pevent_print_event_time(pevent, s, event, record, use_trace_clock);
+        pevent_print_event_data(pevent, s, event, record);
+}
+
 static int events_id_cmp(const void *a, const void *b)
 {
         struct event_format * const * ea = a;
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 706d9bc24066..9ffde377e89d 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -628,6 +628,16 @@ int pevent_register_print_string(struct pevent *pevent, const char *fmt,
                                  unsigned long long addr);
 int pevent_pid_is_registered(struct pevent *pevent, int pid);
 
+void pevent_print_event_task(struct pevent *pevent, struct trace_seq *s,
+                             struct event_format *event,
+                             struct pevent_record *record);
+void pevent_print_event_time(struct pevent *pevent, struct trace_seq *s,
+                             struct event_format *event,
+                             struct pevent_record *record,
+                             bool use_trace_clock);
+void pevent_print_event_data(struct pevent *pevent, struct trace_seq *s,
+                             struct event_format *event,
+                             struct pevent_record *record);
 void pevent_print_event(struct pevent *pevent, struct trace_seq *s,
                         struct pevent_record *record, bool use_trace_clock);
 
@@ -694,6 +704,9 @@ struct event_format *pevent_find_event(struct pevent *pevent, int id);
 struct event_format *
 pevent_find_event_by_name(struct pevent *pevent, const char *sys, const char *name);
 
+struct event_format *
+pevent_find_event_by_record(struct pevent *pevent, struct pevent_record *record);
+
 void pevent_data_lat_fmt(struct pevent *pevent,
                          struct trace_seq *s, struct pevent_record *record);
 int pevent_data_type(struct pevent *pevent, struct pevent_record *rec);
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index b9ca1e304158..15949e2a7805 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -8,7 +8,7 @@ perf-config - Get and set variables in a configuration file.
 SYNOPSIS
 --------
 [verse]
-'perf config' -l | --list
+'perf config' [<file-option>] -l | --list
 
 DESCRIPTION
 -----------
@@ -21,6 +21,14 @@ OPTIONS
 --list::
         Show current config variables, name and value, for all sections.
 
+--user::
+        For writing and reading options: write to user
+        '$HOME/.perfconfig' file or read it.
+
+--system::
+        For writing and reading options: write to system-wide
+        '$(sysconfdir)/perfconfig' or read it.
+
 CONFIGURATION FILE
 ------------------
 
@@ -30,6 +38,10 @@ The '$HOME/.perfconfig' file is used to store a per-user configuration.
 The file '$(sysconfdir)/perfconfig' can be used to
 store a system-wide default configuration.
 
+When reading or writing, the values are read from the system and user
+configuration files by default, and options '--system' and '--user'
+can be used to tell the command to read from or write to only that location.
+
 Syntax
 ~~~~~~
 
@@ -62,7 +74,7 @@ Given a $HOME/.perfconfig like this:
                 medium = green, default
                 normal = lightgray, default
                 selected = white, lightgray
-                code = blue, default
+                jump_arrows = blue, default
                 addr = magenta, default
                 root = white, blue
 
@@ -98,6 +110,347 @@ Given a $HOME/.perfconfig like this:
                 order = caller
                 sort-key = function
 
+Variables
+~~~~~~~~~
+
+colors.*::
+        The variables for customizing the colors used in the output for the
+        'report', 'top' and 'annotate' in the TUI. They should specify the
+        foreground and background colors, separated by a comma, for example:
+
+                medium = green, lightgray
+
+        If you want to use the color configured for you terminal, just leave it
+        as 'default', for example:
+
+                medium = default, lightgray
+
+        Available colors:
+        red, yellow, green, cyan, gray, black, blue,
+        white, default, magenta, lightgray
+
+        colors.top::
+                'top' means a overhead percentage which is more than 5%.
+                And values of this variable specify percentage colors.
+                Basic key values are foreground-color 'red' and
+                background-color 'default'.
+        colors.medium::
+                'medium' means a overhead percentage which has more than 0.5%.
+                Default values are 'green' and 'default'.
+        colors.normal::
+                'normal' means the rest of overhead percentages
+                except 'top', 'medium', 'selected'.
+                Default values are 'lightgray' and 'default'.
+        colors.selected::
+                This selects the colors for the current entry in a list of entries
+                from sub-commands (top, report, annotate).
+                Default values are 'black' and 'lightgray'.
+        colors.jump_arrows::
+                Colors for jump arrows on assembly code listings
+                such as 'jns', 'jmp', 'jane', etc.
+                Default values are 'blue', 'default'.
+        colors.addr::
+                This selects colors for addresses from 'annotate'.
+                Default values are 'magenta', 'default'.
+        colors.root::
+                Colors for headers in the output of a sub-commands (top, report).
+                Default values are 'white', 'blue'.
+
+tui.*, gtk.*::
+        Subcommands that can be configured here are 'top', 'report' and 'annotate'.
+        These values are booleans, for example:
+
+        [tui]
+                top = true
+
+        will make the TUI be the default for the 'top' subcommand. Those will be
+        available if the required libs were detected at tool build time.
+
+buildid.*::
+        buildid.dir::
+                Each executable and shared library in modern distributions comes with a
+                content based identifier that, if available, will be inserted in a
+                'perf.data' file header to, at analysis time find what is needed to do
+                symbol resolution, code annotation, etc.
+
+                The recording tools also stores a hard link or copy in a per-user
+                directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
+                and /proc/kcore files to be used at analysis time.
+
+                The buildid.dir variable can be used to either change this directory
+                cache location, or to disable it altogether. If you want to disable it,
+                set buildid.dir to /dev/null. The default is $HOME/.debug
+
+annotate.*::
+        These options work only for TUI.
+        These are in control of addresses, jump function, source code
+        in lines of assembly code from a specific program.
+
+        annotate.hide_src_code::
+                If a program which is analyzed has source code,
+                this option lets 'annotate' print a list of assembly code with the source code.
+                For example, let's see a part of a program. There're four lines.
+                If this option is 'true', they can be printed
+                without source code from a program as below.
+
+                │        push   %rbp
+                │        mov    %rsp,%rbp
+                │        sub    $0x10,%rsp
+                │        mov    (%rdi),%rdx
+
+                But if this option is 'false', source code of the part
+                can be also printed as below. Default is 'false'.
+
+                │      struct rb_node *rb_next(const struct rb_node *node)
+                │      {
+                │        push   %rbp
+                │        mov    %rsp,%rbp
+                │        sub    $0x10,%rsp
+                │              struct rb_node *parent;
+                │
+                │              if (RB_EMPTY_NODE(node))
+                │        mov    (%rdi),%rdx
+                │              return n;
+
+        annotate.use_offset::
+                Basing on a first address of a loaded function, offset can be used.
+                Instead of using original addresses of assembly code,
+                addresses subtracted from a base address can be printed.
+                Let's illustrate an example.
+                If a base address is 0XFFFFFFFF81624d50 as below,
+
+                ffffffff81624d50 <load0>
+
+                an address on assembly code has a specific absolute address as below
+
+                ffffffff816250b8:│  mov    0x8(%r14),%rdi
+
+                but if use_offset is 'true', an address subtracted from a base address is printed.
+                Default is true. This option is only applied to TUI.
+
+                             368:│  mov    0x8(%r14),%rdi
+
+        annotate.jump_arrows::
+                There can be jump instruction among assembly code.
+                Depending on a boolean value of jump_arrows,
+                arrows can be printed or not which represent
+                where do the instruction jump into as below.
+
+                │     ┌──jmp    1333
+                │     │  xchg   %ax,%ax
+                │1330:│  mov    %r15,%r10
+                │1333:└─→cmp    %r15,%r14
+
+                If jump_arrow is 'false', the arrows isn't printed as below.
+                Default is 'false'.
+
+                │      ↓ jmp    1333
+                │        xchg   %ax,%ax
+                │1330:   mov    %r15,%r10
+                │1333:   cmp    %r15,%r14
+
+        annotate.show_linenr::
+                When showing source code if this option is 'true',
+                line numbers are printed as below.
+
+                │1628         if (type & PERF_SAMPLE_IDENTIFIER) {
+                │     ↓ jne    508
+                │1628                 data->id = *array;
+                │1629                 array++;
+                │1630         }
+
+                However if this option is 'false', they aren't printed as below.
+                Default is 'false'.
+
+                │             if (type & PERF_SAMPLE_IDENTIFIER) {
+                │     ↓ jne    508
+                │                     data->id = *array;
+                │                     array++;
+                │             }
+
+        annotate.show_nr_jumps::
+                Let's see a part of assembly code.
+
+                │1382:   movb   $0x1,-0x270(%rbp)
+
+                If use this, the number of branches jumping to that address can be printed as below.
+                Default is 'false'.
+
+                │1 1382:   movb   $0x1,-0x270(%rbp)
+
+        annotate.show_total_period::
+                To compare two records on an instruction base, with this option
+                provided, display total number of samples that belong to a line
+                in assembly code. If this option is 'true', total periods are printed
+                instead of percent values as below.
+
+                  302 │      mov    %eax,%eax
+
+                But if this option is 'false', percent values for overhead are printed i.e.
+                Default is 'false'.
+
+                99.93 │      mov    %eax,%eax
+
+hist.*::
+        hist.percentage::
+                This option control the way to calculate overhead of filtered entries -
+                that means the value of this option is effective only if there's a
+                filter (by comm, dso or symbol name). Suppose a following example:
+
+                       Overhead  Symbols
+                       ........  .......
+                        33.33%     foo
+                        33.33%     bar
+                        33.33%     baz
+
+               This is an original overhead and we'll filter out the first 'foo'
+               entry. The value of 'relative' would increase the overhead of 'bar'
+               and 'baz' to 50.00% for each, while 'absolute' would show their
+               current overhead (33.33%).
+
+ui.*::
+        ui.show-headers::
+                This option controls display of column headers (like 'Overhead' and 'Symbol')
+                in 'report' and 'top'. If this option is false, they are hidden.
+                This option is only applied to TUI.
+
+call-graph.*::
+        When sub-commands 'top' and 'report' work with -g/—-children
+        there're options in control of call-graph.
+
+        call-graph.record-mode::
+                The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
+                The value of 'dwarf' is effective only if perf detect needed library
+                (libunwind or a recent version of libdw).
+                'lbr' only work for cpus that support it.
+
+        call-graph.dump-size::
+                The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
+                When using dwarf into record-mode, the default size will be used if omitted.
+
+        call-graph.print-type::
+                The print-types can be graph (graph absolute), fractal (graph relative),
+                flat and folded. This option controls a way to show overhead for each callchain
+                entry. Suppose a following example.
+
+                Overhead  Symbols
+                ........  .......
+                  40.00%  foo
+                          |
+                          ---foo
+                             |
+                             |--50.00%--bar
+                             |          main
+                             |
+                              --50.00%--baz
+                                        main
+
+                This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
+                half and half so 'fractal' shows 50.00% for each
+                (meaning that it assumes 100% total overhead of 'foo').
+
+                The 'graph' uses absolute overhead value of 'foo' as total so each of
+                'bar' and 'baz' callchain will have 20.00% of overhead.
+                If 'flat' is used, single column and linear exposure of call chains.
+                'folded' mean call chains are displayed in a line, separated by semicolons.
+
+        call-graph.order::
+                This option controls print order of callchains. The default is
+                'callee' which means callee is printed at top and then followed by its
+                caller and so on. The 'caller' prints it in reverse order.
+
+                If this option is not set and report.children or top.children is
+                set to true (or the equivalent command line option is given),
+                the default value of this option is changed to 'caller' for the
+                execution of 'perf report' or 'perf top'. Other commands will
+                still default to 'callee'.
+
+        call-graph.sort-key::
+                The callchains are merged if they contain same information.
+                The sort-key option determines a way to compare the callchains.
+                A value of 'sort-key' can be 'function' or 'address'.
+                The default is 'function'.
+
+        call-graph.threshold::
+                When there're many callchains it'd print tons of lines. So perf omits
+                small callchains under a certain overhead (threshold) and this option
+                control the threshold. Default is 0.5 (%). The overhead is calculated
+                by value depends on call-graph.print-type.
+
+        call-graph.print-limit::
+                This is a maximum number of lines of callchain printed for a single
+                histogram entry. Default is 0 which means no limitation.
+
+report.*::
+        report.percent-limit::
+                This one is mostly the same as call-graph.threshold but works for
+                histogram entries. Entries having an overhead lower than this
+                percentage will not be printed. Default is '0'. If percent-limit
+                is '10', only entries which have more than 10% of overhead will be
+                printed.
+
+        report.queue-size::
+                This option sets up the maximum allocation size of the internal
+                event queue for ordering events. Default is 0, meaning no limit.
+
+        report.children::
+                'Children' means functions called from another function.
+                If this option is true, 'perf report' cumulates callchains of children
+                and show (accumulated) total overhead as well as 'Self' overhead.
+                Please refer to the 'perf report' manual. The default is 'true'.
+
+        report.group::
+                This option is to show event group information together.
+                Example output with this turned on, notice that there is one column
+                per event in the group, ref-cycles and cycles:
+
+                # group: {ref-cycles,cycles}
+                # ========
+                #
+                # Samples: 7K of event 'anon group { ref-cycles, cycles }'
+                # Event count (approx.): 6876107743
+                #
+                #         Overhead  Command      Shared Object               Symbol
+                # ................  .......  .................  ...................
+                #
+                    99.84%  99.76%  noploop  noploop            [.] main
+                     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
+                     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
+
+top.*::
+        top.children::
+                Same as 'report.children'. So if it is enabled, the output of 'top'
+                command will have 'Children' overhead column as well as 'Self' overhead
+                column by default.
+                The default is 'true'.
+
+man.*::
+        man.viewer::
+                This option can assign a tool to view manual pages when 'help'
+                subcommand was invoked. Supported tools are 'man', 'woman'
+                (with emacs client) and 'konqueror'. Default is 'man'.
+
+                New man viewer tool can be also added using 'man.<tool>.cmd'
+                or use different path using 'man.<tool>.path' config option.
+
+pager.*::
+        pager.<subcommand>::
+                When the subcommand is run on stdio, determine whether it uses
+                pager or not based on this value. Default is 'unspecified'.
+
+kmem.*::
+        kmem.default::
+                This option decides which allocator is to be analyzed if neither
+                '--slab' nor '--page' option is used. Default is 'slab'.
+
+record.*::
+        record.build-id::
+                This option can be 'cache', 'no-cache' or 'skip'.
+                'cache' is to post-process data and save/update the binaries into
+                the build-id cache (in ~/.debug). This is the default.
+                But if this option is 'no-cache', it will not update the build-id cache.
+                'skip' skips post-processing and does not update the cache.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index 0b1cedeef895..87b2588d1cbd 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -53,6 +53,13 @@ include::itrace.txt[]
 --strip::
         Use with --itrace to strip out non-synthesized events.
 
+-j::
+--jit::
+        Process jitdump files by injecting the mmap records corresponding to jitted
+        functions. This option also generates the ELF images for each jitted function
+        found in the jitdumps files captured in the input perf.data file. Use this option
+        if you are monitoring environment using JIT runtimes, such as Java, DART or V8.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index fbceb631387c..19aa17532a16 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -341,6 +341,12 @@ Specify vmlinux path which has debuginfo.
 --buildid-all::
 Record build-id of all DSOs regardless whether it's actually hit or not.
 
+--all-kernel::
+Configure all used events to run in kernel space.
+
+--all-user::
+Configure all used events to run in user space.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 8a301f6afb37..12113992ac9d 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -117,6 +117,22 @@ OPTIONS
         And default sort keys are changed to comm, dso_from, symbol_from, dso_to
         and symbol_to, see '--branch-stack'.
 
+        If the --mem-mode option is used, the following sort keys are also available
+        (incompatible with --branch-stack):
+        symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
+
+        - symbol_daddr: name of data symbol being executed on at the time of sample
+        - dso_daddr: name of library or module containing the data being executed
+        on at the time of the sample
+        - locked: whether the bus was locked at the time of the sample
+        - tlb: type of tlb access for the data at the time of the sample
+        - mem: type of memory access for the data at the time of the sample
+        - snoop: type of snoop (if any) for the data at the time of the sample
+        - dcacheline: the cacheline the data address is on at the time of the sample
+
+        And the default sort keys are changed to local_weight, mem, sym, dso,
+        symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
+
         If the data file has tracepoint event(s), following (dynamic) sort keys
         are also available:
         trace, trace_fields, [<event>.]<field>[/raw]
@@ -151,22 +167,6 @@ OPTIONS
         By default, every sort keys not specified in -F will be appended
         automatically.
 
-        If --mem-mode option is used, following sort keys are also available
-        (incompatible with --branch-stack):
-        symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
-
-        - symbol_daddr: name of data symbol being executed on at the time of sample
-        - dso_daddr: name of library or module containing the data being executed
-        on at the time of sample
-        - locked: whether the bus was locked at the time of sample
-        - tlb: type of tlb access for the data at the time of sample
-        - mem: type of memory access for the data at the time of sample
-        - snoop: type of snoop (if any) for the data at the time of sample
-        - dcacheline: the cacheline the data address is on at the time of sample
-
-        And default sort keys are changed to local_weight, mem, sym, dso,
-        symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
-
 -p::
 --parent=<regex>::
         A regex filter to identify parent. The parent is a caller of this
@@ -351,7 +351,10 @@ OPTIONS
 
 --percent-limit::
         Do not show entries which have an overhead under that percent.
-        (Default: 0).
+        (Default: 0).  Note that this option also sets the percent limit (threshold)
+        of callchains.  However the default value of callchain threshold is
+        different than the default value of hist entries.  Please see the
+        --call-graph option for details.
 
 --percentage::
         Determine how to display the overhead percentage of filtered entries.
@@ -398,6 +401,9 @@ include::itrace.txt[]
 --raw-trace::
         When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+        Enable hierarchical output.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 52ef7a9d50aa..04f23b404bbc 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -69,6 +69,14 @@ report::
 --scale::
         scale/normalize counter values
 
+-d::
+--detailed::
+        print more detailed statistics, can be specified up to 3 times
+
+           -d:          detailed events, L1 and LLC data cache
+        -d -d:     more detailed events, dTLB and iTLB events
+     -d -d -d:     very detailed events, adding prefetch events
+
 -r::
 --repeat=<n>::
         repeat command and print average + stddev (max: 100). 0 means forever.
@@ -139,6 +147,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
         example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with --per-thread.
+
 --per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
@@ -211,6 +223,29 @@ $ perf stat -- make -j
 
  Wall-clock time elapsed:   719.554352 msecs
 
+CSV FORMAT
+----------
+
+With -x, perf stat is able to output a not-quite-CSV format output
+Commas in the output are not put into "". To make it easy to parse
+it is recommended to use a different character like -x \;
+
+The fields are in this order:
+
+        - optional usec time stamp in fractions of second (with -I xxx)
+        - optional CPU, core, or socket identifier
+        - optional number of logical CPUs aggregated
+        - counter value
+        - unit of the counter value or empty
+        - event name
+        - run time of counter
+        - percentage of measurement time the counter was running
+        - optional variance if multiple values are collected with -r
+        - optional metric value
+        - optional unit of metric
+
+Additional metrics may be printed with all earlier fields being empty.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index b0e60e17db38..19f046f027cd 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -233,6 +233,9 @@ Default is to monitor all CPUS.
 --raw-trace::
         When displaying traceevent output, do not use print fmt or plugins.
 
+--hierarchy::
+        Enable hierarchy output.
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Documentation/perfconfig.example b/tools/perf/Documentation/perfconfig.example
index 767ea2436e1c..1d8d5bc4cd2d 100644
--- a/tools/perf/Documentation/perfconfig.example
+++ b/tools/perf/Documentation/perfconfig.example
@@ -5,7 +5,7 @@
         medium = green, lightgray
         normal = black, lightgray
         selected = lightgray, magenta
-        code = blue, lightgray
+        jump_arrows = blue, lightgray
         addr = magenta, lightgray
 
 [tui]
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index e0ce9573b79b..5950b5a24efd 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -27,3 +27,4 @@ Skip collecing build-id when recording: perf record -B
 To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
 If you prefer Intel style assembly, try: perf annotate -M intel
+For hierarchical output, try: perf report --hierarchy
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index dcd9a70c7193..32a64e619028 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -68,6 +68,20 @@ all tags TAGS:
         $(print_msg)
         $(make)
 
+ifdef MAKECMDGOALS
+has_clean := 0
+ifneq ($(filter clean,$(MAKECMDGOALS)),)
+  has_clean := 1
+endif # clean
+
+ifeq ($(has_clean),1)
+  rest := $(filter-out clean,$(MAKECMDGOALS))
+  ifneq ($(rest),)
+$(rest): clean
+  endif # rest
+endif # has_clean
+endif # MAKECMDGOALS
+
 #
 # The clean target is not really parallel, don't print the jobs info:
 #
@@ -75,10 +89,17 @@ clean:
         $(make)
 
 #
-# The build-test target is not really parallel, don't print the jobs info:
+# The build-test target is not really parallel, don't print the jobs info,
+# it also uses only the tests/make targets that don't pollute the source
+# repository, i.e. that uses O= or builds the tarpkg outside the source
+# repo directories.
+#
+# For a full test, use:
+#
+# make -C tools/perf -f tests/make
 #
 build-test:
-        @$(MAKE) SHUF=1 -f tests/make --no-print-directory
+        @$(MAKE) SHUF=1 -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile SET_PARALLEL=1 --no-print-directory tarpkg out
 
 #
 # All other targets get passed through:
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5d34815c7ccb..4a4fad4182f5 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -58,6 +58,9 @@ include config/utilities.mak
 #
 # Define NO_LIBBIONIC if you do not want bionic support
 #
+# Define NO_LIBCRYPTO if you do not want libcrypto (openssl) support
+# used for generating build-ids for ELFs generated by jitdump.
+#
 # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
 # for dwarf backtrace post unwind.
 #
@@ -136,6 +139,8 @@ $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,AR,$(CROSS_COMPILE)ar)
 $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
+LD += $(EXTRA_LDFLAGS)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
@@ -165,7 +170,16 @@ ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
 endif
 endif
 
+# Set FEATURE_TESTS to 'all' so all possible feature checkers are executed.
+# Without this setting the output feature dump file misses some features, for
+# example, liberty. Select all checkers so we won't get an incomplete feature
+# dump file.
 ifeq ($(config),1)
+ifdef MAKECMDGOALS
+ifeq ($(filter feature-dump,$(MAKECMDGOALS)),feature-dump)
+FEATURE_TESTS := all
+endif
+endif
 include config/Makefile
 endif
 
@@ -618,7 +632,7 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean
         $(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
         $(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
                 $(OUTPUT)util/intel-pt-decoder/inat-tables.c $(OUTPUT)fixdep \
-                $(OUTPUT)tests/llvm-src-{base,kbuild,prologue}.c
+                $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c
         $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
         $(python-clean)
 
diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index 7fbca175099e..18b13518d8d8 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -1,3 +1,4 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 7fbca175099e..18b13518d8d8 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -1,3 +1,4 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 7fbca175099e..56e05f126ad8 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -1,3 +1,6 @@
 ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
+
+HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 7b8b0d1a1b62..c8fe2074d217 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,6 @@
 libperf-y += header.o
 libperf-y += sym-handling.o
+libperf-y += kvm-stat.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/book3s_hcalls.h b/tools/perf/arch/powerpc/util/book3s_hcalls.h
new file mode 100644
index 000000000000..0dd6b7f2d44f
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hcalls.h
@@ -0,0 +1,123 @@
+#ifndef ARCH_PERF_BOOK3S_HV_HCALLS_H
+#define ARCH_PERF_BOOK3S_HV_HCALLS_H
+
+/*
+ * PowerPC HCALL codes : hcall code to name mapping
+ */
+#define kvm_trace_symbol_hcall \
+        {0x4, "H_REMOVE"},                                      \
+        {0x8, "H_ENTER"},                                       \
+        {0xc, "H_READ"},                                        \
+        {0x10, "H_CLEAR_MOD"},                                  \
+        {0x14, "H_CLEAR_REF"},                                  \
+        {0x18, "H_PROTECT"},                                    \
+        {0x1c, "H_GET_TCE"},                                    \
+        {0x20, "H_PUT_TCE"},                                    \
+        {0x24, "H_SET_SPRG0"},                                  \
+        {0x28, "H_SET_DABR"},                                   \
+        {0x2c, "H_PAGE_INIT"},                                  \
+        {0x30, "H_SET_ASR"},                                    \
+        {0x34, "H_ASR_ON"},                                     \
+        {0x38, "H_ASR_OFF"},                                    \
+        {0x3c, "H_LOGICAL_CI_LOAD"},                            \
+        {0x40, "H_LOGICAL_CI_STORE"},                           \
+        {0x44, "H_LOGICAL_CACHE_LOAD"},                         \
+        {0x48, "H_LOGICAL_CACHE_STORE"},                        \
+        {0x4c, "H_LOGICAL_ICBI"},                               \
+        {0x50, "H_LOGICAL_DCBF"},                               \
+        {0x54, "H_GET_TERM_CHAR"},                              \
+        {0x58, "H_PUT_TERM_CHAR"},                              \
+        {0x5c, "H_REAL_TO_LOGICAL"},                            \
+        {0x60, "H_HYPERVISOR_DATA"},                            \
+        {0x64, "H_EOI"},                                        \
+        {0x68, "H_CPPR"},                                       \
+        {0x6c, "H_IPI"},                                        \
+        {0x70, "H_IPOLL"},                                      \
+        {0x74, "H_XIRR"},                                       \
+        {0x78, "H_MIGRATE_DMA"},                                \
+        {0x7c, "H_PERFMON"},                                    \
+        {0xdc, "H_REGISTER_VPA"},                               \
+        {0xe0, "H_CEDE"},                                       \
+        {0xe4, "H_CONFER"},                                     \
+        {0xe8, "H_PROD"},                                       \
+        {0xec, "H_GET_PPP"},                                    \
+        {0xf0, "H_SET_PPP"},                                    \
+        {0xf4, "H_PURR"},                                       \
+        {0xf8, "H_PIC"},                                        \
+        {0xfc, "H_REG_CRQ"},                                    \
+        {0x100, "H_FREE_CRQ"},                                  \
+        {0x104, "H_VIO_SIGNAL"},                                \
+        {0x108, "H_SEND_CRQ"},                                  \
+        {0x110, "H_COPY_RDMA"},                                 \
+        {0x114, "H_REGISTER_LOGICAL_LAN"},                      \
+        {0x118, "H_FREE_LOGICAL_LAN"},                          \
+        {0x11c, "H_ADD_LOGICAL_LAN_BUFFER"},                    \
+        {0x120, "H_SEND_LOGICAL_LAN"},                          \
+        {0x124, "H_BULK_REMOVE"},                               \
+        {0x130, "H_MULTICAST_CTRL"},                            \
+        {0x134, "H_SET_XDABR"},                                 \
+        {0x138, "H_STUFF_TCE"},                                 \
+        {0x13c, "H_PUT_TCE_INDIRECT"},                          \
+        {0x14c, "H_CHANGE_LOGICAL_LAN_MAC"},                    \
+        {0x150, "H_VTERM_PARTNER_INFO"},                        \
+        {0x154, "H_REGISTER_VTERM"},                            \
+        {0x158, "H_FREE_VTERM"},                                \
+        {0x15c, "H_RESET_EVENTS"},                              \
+        {0x160, "H_ALLOC_RESOURCE"},                            \
+        {0x164, "H_FREE_RESOURCE"},                             \
+        {0x168, "H_MODIFY_QP"},                                 \
+        {0x16c, "H_QUERY_QP"},                                  \
+        {0x170, "H_REREGISTER_PMR"},                            \
+        {0x174, "H_REGISTER_SMR"},                              \
+        {0x178, "H_QUERY_MR"},                                  \
+        {0x17c, "H_QUERY_MW"},                                  \
+        {0x180, "H_QUERY_HCA"},                                 \
+        {0x184, "H_QUERY_PORT"},                                \
+        {0x188, "H_MODIFY_PORT"},                               \
+        {0x18c, "H_DEFINE_AQP1"},                               \
+        {0x190, "H_GET_TRACE_BUFFER"},                          \
+        {0x194, "H_DEFINE_AQP0"},                               \
+        {0x198, "H_RESIZE_MR"},                                 \
+        {0x19c, "H_ATTACH_MCQP"},                               \
+        {0x1a0, "H_DETACH_MCQP"},                               \
+        {0x1a4, "H_CREATE_RPT"},                                \
+        {0x1a8, "H_REMOVE_RPT"},                                \
+        {0x1ac, "H_REGISTER_RPAGES"},                           \
+        {0x1b0, "H_DISABLE_AND_GETC"},                          \
+        {0x1b4, "H_ERROR_DATA"},                                \
+        {0x1b8, "H_GET_HCA_INFO"},                              \
+        {0x1bc, "H_GET_PERF_COUNT"},                            \
+        {0x1c0, "H_MANAGE_TRACE"},                              \
+        {0x1d4, "H_FREE_LOGICAL_LAN_BUFFER"},                   \
+        {0x1d8, "H_POLL_PENDING"},                              \
+        {0x1e4, "H_QUERY_INT_STATE"},                           \
+        {0x244, "H_ILLAN_ATTRIBUTES"},                          \
+        {0x250, "H_MODIFY_HEA_QP"},                             \
+        {0x254, "H_QUERY_HEA_QP"},                              \
+        {0x258, "H_QUERY_HEA"},                                 \
+        {0x25c, "H_QUERY_HEA_PORT"},                            \
+        {0x260, "H_MODIFY_HEA_PORT"},                           \
+        {0x264, "H_REG_BCMC"},                                  \
+        {0x268, "H_DEREG_BCMC"},                                \
+        {0x26c, "H_REGISTER_HEA_RPAGES"},                       \
+        {0x270, "H_DISABLE_AND_GET_HEA"},                       \
+        {0x274, "H_GET_HEA_INFO"},                              \
+        {0x278, "H_ALLOC_HEA_RESOURCE"},                        \
+        {0x284, "H_ADD_CONN"},                                  \
+        {0x288, "H_DEL_CONN"},                                  \
+        {0x298, "H_JOIN"},                                      \
+        {0x2a4, "H_VASI_STATE"},                                \
+        {0x2b0, "H_ENABLE_CRQ"},                                \
+        {0x2b8, "H_GET_EM_PARMS"},                              \
+        {0x2d0, "H_SET_MPP"},                                   \
+        {0x2d4, "H_GET_MPP"},                                   \
+        {0x2ec, "H_HOME_NODE_ASSOCIATIVITY"},                   \
+        {0x2f4, "H_BEST_ENERGY"},                               \
+        {0x2fc, "H_XIRR_X"},                                    \
+        {0x300, "H_RANDOM"},                                    \
+        {0x304, "H_COP"},                                       \
+        {0x314, "H_GET_MPP_X"},                                 \
+        {0x31c, "H_SET_MODE"},                                  \
+        {0xf000, "H_RTAS"}                                      \
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/book3s_hv_exits.h b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
new file mode 100644
index 000000000000..e68ba2da8970
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/book3s_hv_exits.h
@@ -0,0 +1,33 @@
+#ifndef ARCH_PERF_BOOK3S_HV_EXITS_H
+#define ARCH_PERF_BOOK3S_HV_EXITS_H
+
+/*
+ * PowerPC Interrupt vectors : exit code to name mapping
+ */
+
+#define kvm_trace_symbol_exit \
+        {0x0,   "RETURN_TO_HOST"}, \
+        {0x100, "SYSTEM_RESET"}, \
+        {0x200, "MACHINE_CHECK"}, \
+        {0x300, "DATA_STORAGE"}, \
+        {0x380, "DATA_SEGMENT"}, \
+        {0x400, "INST_STORAGE"}, \
+        {0x480, "INST_SEGMENT"}, \
+        {0x500, "EXTERNAL"}, \
+        {0x501, "EXTERNAL_LEVEL"}, \
+        {0x502, "EXTERNAL_HV"}, \
+        {0x600, "ALIGNMENT"}, \
+        {0x700, "PROGRAM"}, \
+        {0x800, "FP_UNAVAIL"}, \
+        {0x900, "DECREMENTER"}, \
+        {0x980, "HV_DECREMENTER"}, \
+        {0xc00, "SYSCALL"}, \
+        {0xd00, "TRACE"}, \
+        {0xe00, "H_DATA_STORAGE"}, \
+        {0xe20, "H_INST_STORAGE"}, \
+        {0xe40, "H_EMUL_ASSIST"}, \
+        {0xf00, "PERFMON"}, \
+        {0xf20, "ALTIVEC"}, \
+        {0xf40, "VSX"}
+
+#endif
diff --git a/tools/perf/arch/powerpc/util/kvm-stat.c b/tools/perf/arch/powerpc/util/kvm-stat.c
new file mode 100644
index 000000000000..74eee30398f8
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/kvm-stat.c
@@ -0,0 +1,170 @@
+#include "util/kvm-stat.h"
+#include "util/parse-events.h"
+#include "util/debug.h"
+
+#include "book3s_hv_exits.h"
+#include "book3s_hcalls.h"
+
+#define NR_TPS 4
+
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 40;
+const char *kvm_entry_trace = "kvm_hv:kvm_guest_enter";
+const char *kvm_exit_trace = "kvm_hv:kvm_guest_exit";
+
+define_exit_reasons_table(hv_exit_reasons, kvm_trace_symbol_exit);
+define_exit_reasons_table(hcall_reasons, kvm_trace_symbol_hcall);
+
+/* Tracepoints specific to ppc_book3s_hv */
+const char *ppc_book3s_hv_kvm_tp[] = {
+        "kvm_hv:kvm_guest_enter",
+        "kvm_hv:kvm_guest_exit",
+        "kvm_hv:kvm_hcall_enter",
+        "kvm_hv:kvm_hcall_exit",
+        NULL,
+};
+
+/* 1 extra placeholder for NULL */
+const char *kvm_events_tp[NR_TPS + 1];
+const char *kvm_exit_reason;
+
+static void hcall_event_get_key(struct perf_evsel *evsel,
+                                struct perf_sample *sample,
+                                struct event_key *key)
+{
+        key->info = 0;
+        key->key = perf_evsel__intval(evsel, sample, "req");
+}
+
+static const char *get_hcall_exit_reason(u64 exit_code)
+{
+        struct exit_reasons_table *tbl = hcall_reasons;
+
+        while (tbl->reason != NULL) {
+                if (tbl->exit_code == exit_code)
+                        return tbl->reason;
+                tbl++;
+        }
+
+        pr_debug("Unknown hcall code: %lld\n",
+               (unsigned long long)exit_code);
+        return "UNKNOWN";
+}
+
+static bool hcall_event_end(struct perf_evsel *evsel,
+                            struct perf_sample *sample __maybe_unused,
+                            struct event_key *key __maybe_unused)
+{
+        return (!strcmp(evsel->name, kvm_events_tp[3]));
+}
+
+static bool hcall_event_begin(struct perf_evsel *evsel,
+                              struct perf_sample *sample, struct event_key *key)
+{
+        if (!strcmp(evsel->name, kvm_events_tp[2])) {
+                hcall_event_get_key(evsel, sample, key);
+                return true;
+        }
+
+        return false;
+}
+static void hcall_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+                                   struct event_key *key,
+                                   char *decode)
+{
+        const char *hcall_reason = get_hcall_exit_reason(key->key);
+
+        scnprintf(decode, decode_str_len, "%s", hcall_reason);
+}
+
+static struct kvm_events_ops hcall_events = {
+        .is_begin_event = hcall_event_begin,
+        .is_end_event = hcall_event_end,
+        .decode_key = hcall_event_decode_key,
+        .name = "HCALL-EVENT",
+};
+
+static struct kvm_events_ops exit_events = {
+        .is_begin_event = exit_event_begin,
+        .is_end_event = exit_event_end,
+        .decode_key = exit_event_decode_key,
+        .name = "VM-EXIT"
+};
+
+struct kvm_reg_events_ops kvm_reg_events_ops[] = {
+        { .name = "vmexit", .ops = &exit_events },
+        { .name = "hcall", .ops = &hcall_events },
+        { NULL, NULL },
+};
+
+const char * const kvm_skip_events[] = {
+        NULL,
+};
+
+
+static int is_tracepoint_available(const char *str, struct perf_evlist *evlist)
+{
+        struct parse_events_error err;
+        int ret;
+
+        err.str = NULL;
+        ret = parse_events(evlist, str, &err);
+        if (err.str)
+                pr_err("%s : %s\n", str, err.str);
+        return ret;
+}
+
+static int ppc__setup_book3s_hv(struct perf_kvm_stat *kvm,
+                                struct perf_evlist *evlist)
+{
+        const char **events_ptr;
+        int i, nr_tp = 0, err = -1;
+
+        /* Check for book3s_hv tracepoints */
+        for (events_ptr = ppc_book3s_hv_kvm_tp; *events_ptr; events_ptr++) {
+                err = is_tracepoint_available(*events_ptr, evlist);
+                if (err)
+                        return -1;
+                nr_tp++;
+        }
+
+        for (i = 0; i < nr_tp; i++)
+                kvm_events_tp[i] = ppc_book3s_hv_kvm_tp[i];
+
+        kvm_events_tp[i] = NULL;
+        kvm_exit_reason = "trap";
+        kvm->exit_reasons = hv_exit_reasons;
+        kvm->exit_reasons_isa = "HV";
+
+        return 0;
+}
+
+/* Wrapper to setup kvm tracepoints */
+static int ppc__setup_kvm_tp(struct perf_kvm_stat *kvm)
+{
+        struct perf_evlist *evlist = perf_evlist__new();
+
+        if (evlist == NULL)
+                return -ENOMEM;
+
+        /* Right now, only supported on book3s_hv */
+        return ppc__setup_book3s_hv(kvm, evlist);
+}
+
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm)
+{
+        return ppc__setup_kvm_tp(kvm);
+}
+
+int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid __maybe_unused)
+{
+        int ret;
+
+        ret = ppc__setup_kvm_tp(kvm);
+        if (ret) {
+                kvm->exit_reasons = NULL;
+                kvm->exit_reasons_isa = NULL;
+        }
+
+        return ret;
+}
diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index a5dbc07ec9dc..ed57df2e6d68 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -10,7 +10,7 @@
  */
 
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/sie.h>
 
 define_exit_reasons_table(sie_exit_reasons, sie_intercept_code);
 define_exit_reasons_table(sie_icpt_insn_codes, icpt_insn_codes);
@@ -18,6 +18,12 @@ define_exit_reasons_table(sie_sigp_order_codes, sigp_order_codes);
 define_exit_reasons_table(sie_diagnose_codes, diagnose_codes);
 define_exit_reasons_table(sie_icpt_prog_codes, icpt_prog_codes);
 
+const char *vcpu_id_str = "id";
+const int decode_str_len = 40;
+const char *kvm_exit_reason = "icptcode";
+const char *kvm_entry_trace = "kvm:kvm_s390_sie_enter";
+const char *kvm_exit_trace = "kvm:kvm_s390_sie_exit";
+
 static void event_icpt_insn_get_key(struct perf_evsel *evsel,
                                     struct perf_sample *sample,
                                     struct event_key *key)
@@ -73,7 +79,7 @@ static struct kvm_events_ops exit_events = {
         .name = "VM-EXIT"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
         "kvm:kvm_s390_sie_enter",
         "kvm:kvm_s390_sie_exit",
         "kvm:kvm_s390_intercept_instruction",
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 09ba923debe8..269af2143735 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/x86/tests/rdpmc.c b/tools/perf/arch/x86/tests/rdpmc.c
index 7bb0d13c235f..72193f19d6d7 100644
--- a/tools/perf/arch/x86/tests/rdpmc.c
+++ b/tools/perf/arch/x86/tests/rdpmc.c
@@ -59,7 +59,7 @@ static u64 mmap_read_self(void *addr)
                 u64 quot, rem;
 
                 quot = (cyc >> time_shift);
-                rem = cyc & ((1 << time_shift) - 1);
+                rem = cyc & (((u64)1 << time_shift) - 1);
                 delta = time_offset + quot * time_mult +
                         ((rem * time_mult) >> time_shift);
 
@@ -103,6 +103,7 @@ static int __test__rdpmc(void)
 
         sigfillset(&sa.sa_mask);
         sa.sa_sigaction = segfault_handler;
+        sa.sa_flags = 0;
         sigaction(SIGSEGV, &sa, NULL);
 
         fd = sys_perf_event_open(&attr, 0, -1, -1,
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index 8d8150f1cf9b..d66f9ad4df2e 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -60,7 +60,9 @@ struct branch {
         u64 misc;
 };
 
-static size_t intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_bts_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+                         struct perf_evlist *evlist __maybe_unused)
 {
         return INTEL_BTS_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index f05daacc9e78..a3395179c9ee 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -89,7 +89,7 @@ static int intel_pt_parse_terms_with_default(struct list_head *formats,
 
         *config = attr.config;
 out_free:
-        parse_events__free_terms(terms);
+        parse_events_terms__delete(terms);
         return err;
 }
 
@@ -273,7 +273,9 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
         return attr;
 }
 
-static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+static size_t
+intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+                        struct perf_evlist *evlist __maybe_unused)
 {
         return INTEL_PT_AUXTRACE_PRIV_SIZE;
 }
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 14e4e668fad7..b63d4be655a2 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -1,5 +1,7 @@
 #include "../../util/kvm-stat.h"
-#include <asm/kvm_perf.h>
+#include <asm/svm.h>
+#include <asm/vmx.h>
+#include <asm/kvm.h>
 
 define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
 define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
@@ -11,6 +13,12 @@ static struct kvm_events_ops exit_events = {
         .name = "VM-EXIT"
 };
 
+const char *vcpu_id_str = "vcpu_id";
+const int decode_str_len = 20;
+const char *kvm_exit_reason = "exit_reason";
+const char *kvm_entry_trace = "kvm:kvm_entry";
+const char *kvm_exit_trace = "kvm:kvm_exit";
+
 /*
  * For the mmio events, we treat:
  * the time of MMIO write: kvm_mmio(KVM_TRACE_MMIO_WRITE...) -> kvm_entry
@@ -65,7 +73,7 @@ static void mmio_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
                                   struct event_key *key,
                                   char *decode)
 {
-        scnprintf(decode, DECODE_STR_LEN, "%#lx:%s",
+        scnprintf(decode, decode_str_len, "%#lx:%s",
                   (unsigned long)key->key,
                   key->info == KVM_TRACE_MMIO_WRITE ? "W" : "R");
 }
@@ -109,7 +117,7 @@ static void ioport_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
                                     struct event_key *key,
                                     char *decode)
 {
-        scnprintf(decode, DECODE_STR_LEN, "%#llx:%s",
+        scnprintf(decode, decode_str_len, "%#llx:%s",
                   (unsigned long long)key->key,
                   key->info ? "POUT" : "PIN");
 }
@@ -121,7 +129,7 @@ static struct kvm_events_ops ioport_events = {
         .name = "IO Port Access"
 };
 
-const char * const kvm_events_tp[] = {
+const char *kvm_events_tp[] = {
         "kvm:kvm_entry",
         "kvm:kvm_exit",
         "kvm:kvm_mmio",
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index e4c2c30143b9..5c3cce082cb8 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -1,6 +1,11 @@
+
+/* Various wrappers to make the kernel .S file build in user-space: */
+
 #define memcpy MEMCPY /* don't hide glibc's memcpy() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
+#define _ASM_EXTABLE_FAULT(x, y)
+
 #include "../../../arch/x86/lib/memcpy_64.S"
 /*
  * We need to provide note.GNU-stack section, saying that we want
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index cc5c1267c738..cfe366375c4b 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -245,7 +245,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
                         hists__collapse_resort(hists, NULL);
                         /* Don't sort callchain */
                         perf_evsel__reset_sample_bit(pos, CALLCHAIN);
-                        hists__output_resort(hists, NULL);
+                        perf_evsel__output_resort(pos, NULL);
 
                         if (symbol_conf.event_group &&
                             !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index d93bff7fc0e4..632efc6b79a0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -38,19 +38,7 @@ static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 
 static int build_id_cache__kcore_dir(char *dir, size_t sz)
 {
-        struct timeval tv;
-        struct tm tm;
-        char dt[32];
-
-        if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
-                return -1;
-
-        if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
-                return -1;
-
-        scnprintf(dir, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
-
-        return 0;
+        return fetch_current_timestamp(dir, sz);
 }
 
 static bool same_kallsyms_reloc(const char *from_dir, char *to_dir)
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index f04e804a9fad..c42448ed5dfe 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -13,8 +13,10 @@
 #include "util/util.h"
 #include "util/debug.h"
 
+static bool use_system_config, use_user_config;
+
 static const char * const config_usage[] = {
-        "perf config [options]",
+        "perf config [<file-option>] [options]",
         NULL
 };
 
@@ -25,6 +27,8 @@ enum actions {
 static struct option config_options[] = {
         OPT_SET_UINT('l', "list", &actions,
                      "show current config variables", ACTION_LIST),
+        OPT_BOOLEAN(0, "system", &use_system_config, "use system config file"),
+        OPT_BOOLEAN(0, "user", &use_user_config, "use user config file"),
         OPT_END()
 };
 
@@ -42,10 +46,23 @@ static int show_config(const char *key, const char *value,
 int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int ret = 0;
+        char *user_config = mkpath("%s/.perfconfig", getenv("HOME"));
 
         argc = parse_options(argc, argv, config_options, config_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
+        if (use_system_config && use_user_config) {
+                pr_err("Error: only one config file at a time\n");
+                parse_options_usage(config_usage, config_options, "user", 0);
+                parse_options_usage(NULL, config_options, "system", 0);
+                return -1;
+        }
+
+        if (use_system_config)
+                config_exclusive_filename = perf_etc_perfconfig();
+        else if (use_user_config)
+                config_exclusive_filename = user_config;
+
         switch (actions) {
         case ACTION_LIST:
                 if (argc) {
@@ -53,9 +70,13 @@ int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
                         parse_options_usage(config_usage, config_options, "l", 1);
                 } else {
                         ret = perf_config(show_config, NULL);
-                        if (ret < 0)
+                        if (ret < 0) {
+                                const char * config_filename = config_exclusive_filename;
+                                if (!config_exclusive_filename)
+                                        config_filename = user_config;
                                 pr_err("Nothing configured, "
-                                       "please check your ~/.perfconfig file\n");
+                                       "please check your %s \n", config_filename);
+                        }
                 }
                 break;
         default:
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 36ccc2b8827f..4d72359fd15a 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1264,8 +1264,6 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
         if (ret < 0)
                 return ret;
 
-        perf_config(perf_default_config, NULL);
-
         argc = parse_options(argc, argv, options, diff_usage, 0);
 
         if (symbol__init(NULL) < 0)
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 96c1a4cfbbbf..49d55e21b1b0 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -86,8 +86,7 @@ static int check_emacsclient_version(void)
                 return -1;
         }
 
-        strbuf_remove(&buffer, 0, strlen("emacsclient"));
-        version = atoi(buffer.buf);
+        version = atoi(buffer.buf + strlen("emacsclient"));
 
         if (version < 22) {
                 fprintf(stderr,
@@ -273,7 +272,7 @@ static int perf_help_config(const char *var, const char *value, void *cb)
         if (!prefixcmp(var, "man."))
                 return add_man_viewer_info(var, value);
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 static struct cmdnames main_cmds, other_cmds;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 0022e02ed31a..7fa68663ed72 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -17,6 +17,7 @@
 #include "util/build-id.h"
 #include "util/data.h"
 #include "util/auxtrace.h"
+#include "util/jit.h"
 
 #include <subcmd/parse-options.h>
 
@@ -29,6 +30,7 @@ struct perf_inject {
         bool                    sched_stat;
         bool                    have_auxtrace;
         bool                    strip;
+        bool                    jit_mode;
         const char              *input_name;
         struct perf_data_file   output;
         u64                     bytes_written;
@@ -71,6 +73,15 @@ static int perf_event__repipe_oe_synth(struct perf_tool *tool,
         return perf_event__repipe_synth(tool, event);
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__drop_oe(struct perf_tool *tool __maybe_unused,
+                               union perf_event *event __maybe_unused,
+                               struct ordered_events *oe __maybe_unused)
+{
+        return 0;
+}
+#endif
+
 static int perf_event__repipe_op2_synth(struct perf_tool *tool,
                                         union perf_event *event,
                                         struct perf_session *session
@@ -234,6 +245,31 @@ static int perf_event__repipe_mmap(struct perf_tool *tool,
         return err;
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
+                                       union perf_event *event,
+                                       struct perf_sample *sample,
+                                       struct machine *machine)
+{
+        struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+        u64 n = 0;
+        int ret;
+
+        /*
+         * if jit marker, then inject jit mmaps and generate ELF images
+         */
+        ret = jit_process(inject->session, &inject->output, machine,
+                          event->mmap.filename, sample->pid, &n);
+        if (ret < 0)
+                return ret;
+        if (ret) {
+                inject->bytes_written += n;
+                return 0;
+        }
+        return perf_event__repipe_mmap(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_mmap2(struct perf_tool *tool,
                                    union perf_event *event,
                                    struct perf_sample *sample,
@@ -247,6 +283,31 @@ static int perf_event__repipe_mmap2(struct perf_tool *tool,
         return err;
 }
 
+#ifdef HAVE_JITDUMP
+static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
+                                        union perf_event *event,
+                                        struct perf_sample *sample,
+                                        struct machine *machine)
+{
+        struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
+        u64 n = 0;
+        int ret;
+
+        /*
+         * if jit marker, then inject jit mmaps and generate ELF images
+         */
+        ret = jit_process(inject->session, &inject->output, machine,
+                          event->mmap2.filename, sample->pid, &n);
+        if (ret < 0)
+                return ret;
+        if (ret) {
+                inject->bytes_written += n;
+                return 0;
+        }
+        return perf_event__repipe_mmap2(tool, event, sample, machine);
+}
+#endif
+
 static int perf_event__repipe_fork(struct perf_tool *tool,
                                    union perf_event *event,
                                    struct perf_sample *sample,
@@ -626,12 +687,16 @@ static int __cmd_inject(struct perf_inject *inject)
         ret = perf_session__process_events(session);
 
         if (!file_out->is_pipe) {
-                if (inject->build_ids) {
+                if (inject->build_ids)
                         perf_header__set_feat(&session->header,
                                               HEADER_BUILD_ID);
-                        if (inject->have_auxtrace)
-                                dsos__hit_all(session);
-                }
+                /*
+                 * Keep all buildids when there is unprocessed AUX data because
+                 * it is not known which ones the AUX trace hits.
+                 */
+                if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) &&
+                    inject->have_auxtrace && !inject->itrace_synth_opts.set)
+                        dsos__hit_all(session);
                 /*
                  * The AUX areas have been removed and replaced with
                  * synthesized hardware events, so clear the feature flag and
@@ -703,7 +768,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
         };
         int ret;
 
-        const struct option options[] = {
+        struct option options[] = {
                 OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
                             "Inject build-ids into the output stream"),
                 OPT_STRING('i', "input", &inject.input_name, "file",
@@ -713,6 +778,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
                             "Merge sched-stat and sched-switch for getting events "
                             "where and how long tasks slept"),
+#ifdef HAVE_JITDUMP
+                OPT_BOOLEAN('j', "jit", &inject.jit_mode, "merge jitdump files into perf.data file"),
+#endif
                 OPT_INCR('v', "verbose", &verbose,
                          "be more verbose (show build ids, etc)"),
                 OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
@@ -729,7 +797,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                 "perf inject [<options>]",
                 NULL
         };
-
+#ifndef HAVE_JITDUMP
+        set_option_nobuild(options, 'j', "jit", "NO_LIBELF=1", true);
+#endif
         argc = parse_options(argc, argv, options, inject_usage, 0);
 
         /*
@@ -755,6 +825,29 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
         if (inject.session == NULL)
                 return -1;
 
+        if (inject.build_ids) {
+                /*
+                 * to make sure the mmap records are ordered correctly
+                 * and so that the correct especially due to jitted code
+                 * mmaps. We cannot generate the buildid hit list and
+                 * inject the jit mmaps at the same time for now.
+                 */
+                inject.tool.ordered_events = true;
+                inject.tool.ordering_requires_timestamps = true;
+        }
+#ifdef HAVE_JITDUMP
+        if (inject.jit_mode) {
+                inject.tool.mmap2          = perf_event__jit_repipe_mmap2;
+                inject.tool.mmap           = perf_event__jit_repipe_mmap;
+                inject.tool.ordered_events = true;
+                inject.tool.ordering_requires_timestamps = true;
+                /*
+                 * JIT MMAP injection injects all MMAP events in one go, so it
+                 * does not obey finished_round semantics.
+                 */
+                inject.tool.finished_round = perf_event__drop_oe;
+        }
+#endif
         ret = symbol__init(&inject.session->header.env);
         if (ret < 0)
                 goto out_delete;
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 118010553d0c..4d3340cce9a0 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1834,7 +1834,7 @@ static int __cmd_record(int argc, const char **argv)
         return cmd_record(i, rec_argv, NULL);
 }
 
-static int kmem_config(const char *var, const char *value, void *cb)
+static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
 {
         if (!strcmp(var, "kmem.default")) {
                 if (!strcmp(value, "slab"))
@@ -1847,7 +1847,7 @@ static int kmem_config(const char *var, const char *value, void *cb)
                 return 0;
         }
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 4418d9214872..bff666458b28 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -30,7 +30,6 @@
 #include <math.h>
 
 #ifdef HAVE_KVM_STAT_SUPPORT
-#include <asm/kvm_perf.h>
 #include "util/kvm-stat.h"
 
 void exit_event_get_key(struct perf_evsel *evsel,
@@ -38,12 +37,12 @@ void exit_event_get_key(struct perf_evsel *evsel,
                         struct event_key *key)
 {
         key->info = 0;
-        key->key = perf_evsel__intval(evsel, sample, KVM_EXIT_REASON);
+        key->key = perf_evsel__intval(evsel, sample, kvm_exit_reason);
 }
 
 bool kvm_exit_event(struct perf_evsel *evsel)
 {
-        return !strcmp(evsel->name, KVM_EXIT_TRACE);
+        return !strcmp(evsel->name, kvm_exit_trace);
 }
 
 bool exit_event_begin(struct perf_evsel *evsel,
@@ -59,7 +58,7 @@ bool exit_event_begin(struct perf_evsel *evsel,
 
 bool kvm_entry_event(struct perf_evsel *evsel)
 {
-        return !strcmp(evsel->name, KVM_ENTRY_TRACE);
+        return !strcmp(evsel->name, kvm_entry_trace);
 }
 
 bool exit_event_end(struct perf_evsel *evsel,
@@ -91,7 +90,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
         const char *exit_reason = get_exit_reason(kvm, key->exit_reasons,
                                                   key->key);
 
-        scnprintf(decode, DECODE_STR_LEN, "%s", exit_reason);
+        scnprintf(decode, decode_str_len, "%s", exit_reason);
 }
 
 static bool register_kvm_events_ops(struct perf_kvm_stat *kvm)
@@ -357,7 +356,7 @@ static bool handle_end_event(struct perf_kvm_stat *kvm,
         time_diff = sample->time - time_begin;
 
         if (kvm->duration && time_diff > kvm->duration) {
-                char decode[DECODE_STR_LEN];
+                char decode[decode_str_len];
 
                 kvm->events_ops->decode_key(kvm, &event->key, decode);
                 if (!skip_event(decode)) {
@@ -385,7 +384,8 @@ struct vcpu_event_record *per_vcpu_record(struct thread *thread,
                         return NULL;
                 }
 
-                vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample, VCPU_ID);
+                vcpu_record->vcpu_id = perf_evsel__intval(evsel, sample,
+                                                          vcpu_id_str);
                 thread__set_priv(thread, vcpu_record);
         }
 
@@ -574,7 +574,7 @@ static void show_timeofday(void)
 
 static void print_result(struct perf_kvm_stat *kvm)
 {
-        char decode[DECODE_STR_LEN];
+        char decode[decode_str_len];
         struct kvm_event *event;
         int vcpu = kvm->trace_vcpu;
 
@@ -585,7 +585,7 @@ static void print_result(struct perf_kvm_stat *kvm)
 
         pr_info("\n\n");
         print_vcpu_info(kvm);
-        pr_info("%*s ", DECODE_STR_LEN, kvm->events_ops->name);
+        pr_info("%*s ", decode_str_len, kvm->events_ops->name);
         pr_info("%10s ", "Samples");
         pr_info("%9s ", "Samples%");
 
@@ -604,7 +604,7 @@ static void print_result(struct perf_kvm_stat *kvm)
                 min = get_event_min(event, vcpu);
 
                 kvm->events_ops->decode_key(kvm, &event->key, decode);
-                pr_info("%*s ", DECODE_STR_LEN, decode);
+                pr_info("%*s ", decode_str_len, decode);
                 pr_info("%10llu ", (unsigned long long)ecount);
                 pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
                 pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
@@ -1132,6 +1132,11 @@ exit:
                 _p;                     \
         })
 
+int __weak setup_kvm_events_tp(struct perf_kvm_stat *kvm __maybe_unused)
+{
+        return 0;
+}
+
 static int
 kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 {
@@ -1148,7 +1153,14 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
                 NULL
         };
         const char * const *events_tp;
+        int ret;
+
         events_tp_size = 0;
+        ret = setup_kvm_events_tp(kvm);
+        if (ret < 0) {
+                pr_err("Unable to setup the kvm tracepoints\n");
+                return ret;
+        }
 
         for (events_tp = kvm_events_tp; *events_tp; events_tp++)
                 events_tp_size++;
@@ -1377,6 +1389,12 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
         /*
          * generate the event list
          */
+        err = setup_kvm_events_tp(kvm);
+        if (err < 0) {
+                pr_err("Unable to setup the kvm tracepoints\n");
+                return err;
+        }
+
         kvm->evlist = kvm_live_event_list();
         if (kvm->evlist == NULL) {
                 err = -1;
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 390170041696..88aeac9aa1da 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -6,6 +6,8 @@
 #include "util/tool.h"
 #include "util/session.h"
 #include "util/data.h"
+#include "util/mem-events.h"
+#include "util/debug.h"
 
 #define MEM_OPERATION_LOAD      0x1
 #define MEM_OPERATION_STORE     0x2
@@ -21,11 +23,56 @@ struct perf_mem {
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+static int parse_record_events(const struct option *opt,
+                               const char *str, int unset __maybe_unused)
+{
+        struct perf_mem *mem = *(struct perf_mem **)opt->value;
+        int j;
+
+        if (strcmp(str, "list")) {
+                if (!perf_mem_events__parse(str)) {
+                        mem->operation = 0;
+                        return 0;
+                }
+                exit(-1);
+        }
+
+        for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+                struct perf_mem_event *e = &perf_mem_events[j];
+
+                fprintf(stderr, "%-13s%-*s%s\n",
+                        e->tag,
+                        verbose ? 25 : 0,
+                        verbose ? perf_mem_events__name(j) : "",
+                        e->supported ? ": available" : "");
+        }
+        exit(0);
+}
+
+static const char * const __usage[] = {
+        "perf mem record [<options>] [<command>]",
+        "perf mem record [<options>] -- <command> [<options>]",
+        NULL
+};
+
+static const char * const *record_mem_usage = __usage;
+
 static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 {
         int rec_argc, i = 0, j;
         const char **rec_argv;
         int ret;
+        struct option options[] = {
+        OPT_CALLBACK('e', "event", &mem, "event",
+                     "event selector. use 'perf mem record -e list' to list available events",
+                     parse_record_events),
+        OPT_INCR('v', "verbose", &verbose,
+                 "be more verbose (show counter open errors, etc)"),
+        OPT_END()
+        };
+
+        argc = parse_options(argc, argv, options, record_mem_usage,
+                             PARSE_OPT_STOP_AT_NON_OPTION);
 
         rec_argc = argc + 7; /* max number of arguments */
         rec_argv = calloc(rec_argc + 1, sizeof(char *));
@@ -35,23 +82,40 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
         rec_argv[i++] = "record";
 
         if (mem->operation & MEM_OPERATION_LOAD)
+                perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+
+        if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
                 rec_argv[i++] = "-W";
 
         rec_argv[i++] = "-d";
 
-        if (mem->operation & MEM_OPERATION_LOAD) {
-                rec_argv[i++] = "-e";
-                rec_argv[i++] = "cpu/mem-loads/pp";
-        }
+        for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+                if (!perf_mem_events[j].record)
+                        continue;
+
+                if (!perf_mem_events[j].supported) {
+                        pr_err("failed: event '%s' not supported\n",
+                               perf_mem_events__name(j));
+                        return -1;
+                }
 
-        if (mem->operation & MEM_OPERATION_STORE) {
                 rec_argv[i++] = "-e";
-                rec_argv[i++] = "cpu/mem-stores/pp";
-        }
+                rec_argv[i++] = perf_mem_events__name(j);
+        };
 
-        for (j = 1; j < argc; j++, i++)
+        for (j = 0; j < argc; j++, i++)
                 rec_argv[i] = argv[j];
 
+        if (verbose > 0) {
+                pr_debug("calling: record ");
+
+                while (rec_argv[j]) {
+                        pr_debug("%s ", rec_argv[j]);
+                        j++;
+                }
+                pr_debug("\n");
+        }
+
         ret = cmd_record(i, rec_argv, NULL);
         free(rec_argv);
         return ret;
@@ -298,6 +362,10 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
                 NULL
         };
 
+        if (perf_mem_events__init()) {
+                pr_err("failed: memory events not supported\n");
+                return -1;
+        }
 
         argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
                                         mem_usage, PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 319712a4e02b..515510ecc76a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -32,6 +32,8 @@
 #include "util/parse-branch-options.h"
 #include "util/parse-regs-options.h"
 #include "util/llvm-utils.h"
+#include "util/bpf-loader.h"
+#include "asm/bug.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -49,7 +51,9 @@ struct record {
         const char              *progname;
         int                     realtime_prio;
         bool                    no_buildid;
+        bool                    no_buildid_set;
         bool                    no_buildid_cache;
+        bool                    no_buildid_cache_set;
         bool                    buildid_all;
         unsigned long long      samples;
 };
@@ -320,7 +324,10 @@ try_again:
                 } else {
                         pr_err("failed to mmap with %d (%s)\n", errno,
                                 strerror_r(errno, msg, sizeof(msg)));
-                        rc = -errno;
+                        if (errno)
+                                rc = -errno;
+                        else
+                                rc = -EINVAL;
                 }
                 goto out;
         }
@@ -464,6 +471,29 @@ static void record__init_features(struct record *rec)
         perf_header__clear_feat(&session->header, HEADER_STAT);
 }
 
+static void
+record__finish_output(struct record *rec)
+{
+        struct perf_data_file *file = &rec->file;
+        int fd = perf_data_file__fd(file);
+
+        if (file->is_pipe)
+                return;
+
+        rec->session->header.data_size += rec->bytes_written;
+        file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
+
+        if (!rec->no_buildid) {
+                process_buildids(rec);
+
+                if (rec->buildid_all)
+                        dsos__hit_all(rec->session);
+        }
+        perf_session__write_header(rec->session, rec->evlist, fd, true);
+
+        return;
+}
+
 static volatile int workload_exec_errno;
 
 /*
@@ -482,6 +512,74 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 
 static void snapshot_sig_handler(int sig);
 
+static int record__synthesize(struct record *rec)
+{
+        struct perf_session *session = rec->session;
+        struct machine *machine = &session->machines.host;
+        struct perf_data_file *file = &rec->file;
+        struct record_opts *opts = &rec->opts;
+        struct perf_tool *tool = &rec->tool;
+        int fd = perf_data_file__fd(file);
+        int err = 0;
+
+        if (file->is_pipe) {
+                err = perf_event__synthesize_attrs(tool, session,
+                                                   process_synthesized_event);
+                if (err < 0) {
+                        pr_err("Couldn't synthesize attrs.\n");
+                        goto out;
+                }
+
+                if (have_tracepoints(&rec->evlist->entries)) {
+                        /*
+                         * FIXME err <= 0 here actually means that
+                         * there were no tracepoints so its not really
+                         * an error, just that we don't need to
+                         * synthesize anything.  We really have to
+                         * return this more properly and also
+                         * propagate errors that now are calling die()
+                         */
+                        err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist,
+                                                                  process_synthesized_event);
+                        if (err <= 0) {
+                                pr_err("Couldn't record tracing data.\n");
+                                goto out;
+                        }
+                        rec->bytes_written += err;
+                }
+        }
+
+        if (rec->opts.full_auxtrace) {
+                err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+                                        session, process_synthesized_event);
+                if (err)
+                        goto out;
+        }
+
+        err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
+                                                 machine);
+        WARN_ONCE(err < 0, "Couldn't record kernel reference relocation symbol\n"
+                           "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                           "Check /proc/kallsyms permission or run as root.\n");
+
+        err = perf_event__synthesize_modules(tool, process_synthesized_event,
+                                             machine);
+        WARN_ONCE(err < 0, "Couldn't record kernel module information.\n"
+                           "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
+                           "Check /proc/modules permission or run as root.\n");
+
+        if (perf_guest) {
+                machines__process_guests(&session->machines,
+                                         perf_event__synthesize_guest_os, tool);
+        }
+
+        err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
+                                            process_synthesized_event, opts->sample_address,
+                                            opts->proc_map_timeout);
+out:
+        return err;
+}
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
         int err;
@@ -534,6 +632,16 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 goto out_child;
         }
 
+        err = bpf__apply_obj_config();
+        if (err) {
+                char errbuf[BUFSIZ];
+
+                bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+                pr_err("ERROR: Apply config to BPF failed: %s\n",
+                         errbuf);
+                goto out_child;
+        }
+
         /*
          * Normally perf_session__new would do this, but it doesn't have the
          * evlist.
@@ -566,63 +674,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
         machine = &session->machines.host;
 
-        if (file->is_pipe) {
-                err = perf_event__synthesize_attrs(tool, session,
-                                                   process_synthesized_event);
-                if (err < 0) {
-                        pr_err("Couldn't synthesize attrs.\n");
-                        goto out_child;
-                }
-
-                if (have_tracepoints(&rec->evlist->entries)) {
-                        /*
-                         * FIXME err <= 0 here actually means that
-                         * there were no tracepoints so its not really
-                         * an error, just that we don't need to
-                         * synthesize anything.  We really have to
-                         * return this more properly and also
-                         * propagate errors that now are calling die()
-                         */
-                        err = perf_event__synthesize_tracing_data(tool, fd, rec->evlist,
-                                                                  process_synthesized_event);
-                        if (err <= 0) {
-                                pr_err("Couldn't record tracing data.\n");
-                                goto out_child;
-                        }
-                        rec->bytes_written += err;
-                }
-        }
-
-        if (rec->opts.full_auxtrace) {
-                err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
-                                        session, process_synthesized_event);
-                if (err)
-                        goto out_delete_session;
-        }
-
-        err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
-                                                 machine);
-        if (err < 0)
-                pr_err("Couldn't record kernel reference relocation symbol\n"
-                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-                       "Check /proc/kallsyms permission or run as root.\n");
-
-        err = perf_event__synthesize_modules(tool, process_synthesized_event,
-                                             machine);
+        err = record__synthesize(rec);
         if (err < 0)
-                pr_err("Couldn't record kernel module information.\n"
-                       "Symbol resolution may be skewed if relocation was used (e.g. kexec).\n"
-                       "Check /proc/modules permission or run as root.\n");
-
-        if (perf_guest) {
-                machines__process_guests(&session->machines,
-                                         perf_event__synthesize_guest_os, tool);
-        }
-
-        err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
-                                            process_synthesized_event, opts->sample_address,
-                                            opts->proc_map_timeout);
-        if (err != 0)
                 goto out_child;
 
         if (rec->realtime_prio) {
@@ -758,18 +811,8 @@ out_child:
         /* this will be recalculated during process_buildids() */
         rec->samples = 0;
 
-        if (!err && !file->is_pipe) {
-                rec->session->header.data_size += rec->bytes_written;
-                file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
-
-                if (!rec->no_buildid) {
-                        process_buildids(rec);
-
-                        if (rec->buildid_all)
-                                dsos__hit_all(rec->session);
-                }
-                perf_session__write_header(rec->session, rec->evlist, fd, true);
-        }
+        if (!err)
+                record__finish_output(rec);
 
         if (!err && !quiet) {
                 char samples[128];
@@ -1097,10 +1140,12 @@ struct option __record_options[] = {
         OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
         OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
                     "don't sample"),
-        OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
-                    "do not update the buildid cache"),
-        OPT_BOOLEAN('B', "no-buildid", &record.no_buildid,
-                    "do not collect buildids in perf.data"),
+        OPT_BOOLEAN_SET('N', "no-buildid-cache", &record.no_buildid_cache,
+                        &record.no_buildid_cache_set,
+                        "do not update the buildid cache"),
+        OPT_BOOLEAN_SET('B', "no-buildid", &record.no_buildid,
+                        &record.no_buildid_set,
+                        "do not collect buildids in perf.data"),
         OPT_CALLBACK('G', "cgroup", &record.evlist, "name",
                      "monitor event in cgroup name only",
                      parse_cgroups),
@@ -1136,6 +1181,12 @@ struct option __record_options[] = {
                         "per thread proc mmap processing timeout in ms"),
         OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events,
                     "Record context switch events"),
+        OPT_BOOLEAN_FLAG(0, "all-kernel", &record.opts.all_kernel,
+                         "Configure all used events to run in kernel space.",
+                         PARSE_OPT_EXCLUSIVE),
+        OPT_BOOLEAN_FLAG(0, "all-user", &record.opts.all_user,
+                         "Configure all used events to run in user space.",
+                         PARSE_OPT_EXCLUSIVE),
         OPT_STRING(0, "clang-path", &llvm_param.clang_path, "clang path",
                    "clang binary to use for compiling BPF scriptlets"),
         OPT_STRING(0, "clang-opt", &llvm_param.clang_opt, "clang options",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 2bf537f190a0..7eea49f9ed46 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -75,7 +75,10 @@ static int report__config(const char *var, const char *value, void *cb)
                 return 0;
         }
         if (!strcmp(var, "report.percent-limit")) {
-                rep->min_percent = strtof(value, NULL);
+                double pcnt = strtof(value, NULL);
+
+                rep->min_percent = pcnt;
+                callchain_param.min_percent = pcnt;
                 return 0;
         }
         if (!strcmp(var, "report.children")) {
@@ -87,7 +90,7 @@ static int report__config(const char *var, const char *value, void *cb)
                 return 0;
         }
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 static int hist_iter__report_callback(struct hist_entry_iter *iter,
@@ -466,10 +469,11 @@ static int report__browse_hists(struct report *rep)
         return ret;
 }
 
-static void report__collapse_hists(struct report *rep)
+static int report__collapse_hists(struct report *rep)
 {
         struct ui_progress prog;
         struct perf_evsel *pos;
+        int ret = 0;
 
         ui_progress__init(&prog, rep->nr_entries, "Merging related events...");
 
@@ -481,7 +485,9 @@ static void report__collapse_hists(struct report *rep)
 
                 hists->socket_filter = rep->socket_filter;
 
-                hists__collapse_resort(hists, &prog);
+                ret = hists__collapse_resort(hists, &prog);
+                if (ret < 0)
+                        break;
 
                 /* Non-group events are considered as leader */
                 if (symbol_conf.event_group &&
@@ -494,6 +500,7 @@ static void report__collapse_hists(struct report *rep)
         }
 
         ui_progress__finish();
+        return ret;
 }
 
 static void report__output_resort(struct report *rep)
@@ -504,7 +511,7 @@ static void report__output_resort(struct report *rep)
         ui_progress__init(&prog, rep->nr_entries, "Sorting events for output...");
 
         evlist__for_each(rep->session->evlist, pos)
-                hists__output_resort(evsel__hists(pos), &prog);
+                perf_evsel__output_resort(pos, &prog);
 
         ui_progress__finish();
 }
@@ -561,7 +568,11 @@ static int __cmd_report(struct report *rep)
                 }
         }
 
-        report__collapse_hists(rep);
+        ret = report__collapse_hists(rep);
+        if (ret) {
+                ui__error("failed to process hist entry\n");
+                return ret;
+        }
 
         if (session_done())
                 return 0;
@@ -633,8 +644,10 @@ parse_percent_limit(const struct option *opt, const char *str,
                     int unset __maybe_unused)
 {
         struct report *rep = opt->value;
+        double pcnt = strtof(str, NULL);
 
-        rep->min_percent = strtof(str, NULL);
+        rep->min_percent = pcnt;
+        callchain_param.min_percent = pcnt;
         return 0;
 }
 
@@ -798,6 +811,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                     "only show processor socket that match with this filter"),
         OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
                     "Show raw trace event output (do not use print fmt or plugins)"),
+        OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+                    "Show entries in a hierarchy"),
         OPT_END()
         };
         struct perf_data_file file = {
@@ -907,13 +922,19 @@ repeat:
                 symbol_conf.cumulate_callchain = false;
         }
 
-        if (setup_sorting(session->evlist) < 0) {
-                if (sort_order)
-                        parse_options_usage(report_usage, options, "s", 1);
-                if (field_order)
-                        parse_options_usage(sort_order ? NULL : report_usage,
-                                            options, "F", 1);
-                goto error;
+        if (symbol_conf.report_hierarchy) {
+                /* disable incompatible options */
+                symbol_conf.event_group = false;
+                symbol_conf.cumulate_callchain = false;
+
+                if (field_order) {
+                        pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+                        parse_options_usage(report_usage, options, "F", 1);
+                        parse_options_usage(NULL, options, "hierarchy", 0);
+                        goto error;
+                }
+
+                sort__need_collapse = true;
         }
 
         /* Force tty output for header output and per-thread stat. */
@@ -925,6 +946,15 @@ repeat:
         else
                 use_browser = 0;
 
+        if (setup_sorting(session->evlist) < 0) {
+                if (sort_order)
+                        parse_options_usage(report_usage, options, "s", 1);
+                if (field_order)
+                        parse_options_usage(sort_order ? NULL : report_usage,
+                                            options, "F", 1);
+                goto error;
+        }
+
         if (report.header || report.header_only) {
                 perf_session__fprintf_info(session, stdout,
                                            report.show_full_info);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c691214d820f..57f9a7e7f7d3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,6 +23,7 @@
 #include "util/stat.h"
 #include <linux/bitmap.h>
 #include "asm/bug.h"
+#include "util/mem-events.h"
 
 static char const               *script_name;
 static char const               *generate_script_lang;
@@ -58,6 +59,9 @@ enum perf_output_field {
         PERF_OUTPUT_IREGS           = 1U << 14,
         PERF_OUTPUT_BRSTACK         = 1U << 15,
         PERF_OUTPUT_BRSTACKSYM      = 1U << 16,
+        PERF_OUTPUT_DATA_SRC        = 1U << 17,
+        PERF_OUTPUT_WEIGHT          = 1U << 18,
+        PERF_OUTPUT_BPF_OUTPUT      = 1U << 19,
 };
 
 struct output_option {
@@ -81,6 +85,9 @@ struct output_option {
         {.str = "iregs", .field = PERF_OUTPUT_IREGS},
         {.str = "brstack", .field = PERF_OUTPUT_BRSTACK},
         {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM},
+        {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
+        {.str = "weight",   .field = PERF_OUTPUT_WEIGHT},
+        {.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
 };
 
 /* default set to maintain compatibility with current format */
@@ -101,7 +108,7 @@ static struct {
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
                               PERF_OUTPUT_PERIOD,
 
-                .invalid_fields = PERF_OUTPUT_TRACE,
+                .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
 
         [PERF_TYPE_SOFTWARE] = {
@@ -111,7 +118,7 @@ static struct {
                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-                              PERF_OUTPUT_PERIOD,
+                              PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
 
                 .invalid_fields = PERF_OUTPUT_TRACE,
         },
@@ -121,7 +128,7 @@ static struct {
 
                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
                                   PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
-                                  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
+                                  PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE
         },
 
         [PERF_TYPE_RAW] = {
@@ -131,9 +138,10 @@ static struct {
                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-                              PERF_OUTPUT_PERIOD,
+                              PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
+                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
 
-                .invalid_fields = PERF_OUTPUT_TRACE,
+                .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
 
         [PERF_TYPE_BREAKPOINT] = {
@@ -145,7 +153,7 @@ static struct {
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
                               PERF_OUTPUT_PERIOD,
 
-                .invalid_fields = PERF_OUTPUT_TRACE,
+                .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
 };
 
@@ -242,6 +250,16 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                            PERF_OUTPUT_ADDR, allow_user_set))
                 return -EINVAL;
 
+        if (PRINT_FIELD(DATA_SRC) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC",
+                                        PERF_OUTPUT_DATA_SRC))
+                return -EINVAL;
+
+        if (PRINT_FIELD(WEIGHT) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT",
+                                        PERF_OUTPUT_WEIGHT))
+                return -EINVAL;
+
         if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
                 pr_err("Display of symbols requested but neither sample IP nor "
                            "sample address\nis selected. Hence, no addresses to convert "
@@ -608,6 +626,84 @@ static void print_sample_flags(u32 flags)
         printf("  %-4s ", str);
 }
 
+struct printer_data {
+        int line_no;
+        bool hit_nul;
+        bool is_printable;
+};
+
+static void
+print_sample_bpf_output_printer(enum binary_printer_ops op,
+                                unsigned int val,
+                                void *extra)
+{
+        unsigned char ch = (unsigned char)val;
+        struct printer_data *printer_data = extra;
+
+        switch (op) {
+        case BINARY_PRINT_DATA_BEGIN:
+                printf("\n");
+                break;
+        case BINARY_PRINT_LINE_BEGIN:
+                printf("%17s", !printer_data->line_no ? "BPF output:" :
+                                                        "           ");
+                break;
+        case BINARY_PRINT_ADDR:
+                printf(" %04x:", val);
+                break;
+        case BINARY_PRINT_NUM_DATA:
+                printf(" %02x", val);
+                break;
+        case BINARY_PRINT_NUM_PAD:
+                printf("   ");
+                break;
+        case BINARY_PRINT_SEP:
+                printf("  ");
+                break;
+        case BINARY_PRINT_CHAR_DATA:
+                if (printer_data->hit_nul && ch)
+                        printer_data->is_printable = false;
+
+                if (!isprint(ch)) {
+                        printf("%c", '.');
+
+                        if (!printer_data->is_printable)
+                                break;
+
+                        if (ch == '\0')
+                                printer_data->hit_nul = true;
+                        else
+                                printer_data->is_printable = false;
+                } else {
+                        printf("%c", ch);
+                }
+                break;
+        case BINARY_PRINT_CHAR_PAD:
+                printf(" ");
+                break;
+        case BINARY_PRINT_LINE_END:
+                printf("\n");
+                printer_data->line_no++;
+                break;
+        case BINARY_PRINT_DATA_END:
+        default:
+                break;
+        }
+}
+
+static void print_sample_bpf_output(struct perf_sample *sample)
+{
+        unsigned int nr_bytes = sample->raw_size;
+        struct printer_data printer_data = {0, false, true};
+
+        print_binary(sample->raw_data, nr_bytes, 8,
+                     print_sample_bpf_output_printer, &printer_data);
+
+        if (printer_data.is_printable && printer_data.hit_nul)
+                printf("%17s \"%s\"\n", "BPF string:",
+                       (char *)(sample->raw_data));
+}
+
 struct perf_script {
         struct perf_tool        tool;
         struct perf_session     *session;
@@ -634,6 +730,23 @@ static int perf_evlist__max_name_len(struct perf_evlist *evlist)
         return max;
 }
 
+static size_t data_src__printf(u64 data_src)
+{
+        struct mem_info mi = { .data_src.val = data_src };
+        char decode[100];
+        char out[100];
+        static int maxlen;
+        int len;
+
+        perf_script__meminfo_scnprintf(decode, 100, &mi);
+
+        len = scnprintf(out, 100, "%16" PRIx64 " %s", data_src, decode);
+        if (maxlen < len)
+                maxlen = len;
+
+        return printf("%-*s", maxlen, out);
+}
+
 static void process_event(struct perf_script *script, union perf_event *event,
                           struct perf_sample *sample, struct perf_evsel *evsel,
                           struct addr_location *al)
@@ -673,6 +786,12 @@ static void process_event(struct perf_script *script, union perf_event *event,
         if (PRINT_FIELD(ADDR))
                 print_sample_addr(event, sample, thread, attr);
 
+        if (PRINT_FIELD(DATA_SRC))
+                data_src__printf(sample->data_src);
+
+        if (PRINT_FIELD(WEIGHT))
+                printf("%16" PRIu64, sample->weight);
+
         if (PRINT_FIELD(IP)) {
                 if (!symbol_conf.use_callchain)
                         printf(" ");
@@ -692,6 +811,9 @@ static void process_event(struct perf_script *script, union perf_event *event,
         else if (PRINT_FIELD(BRSTACKSYM))
                 print_sample_brstacksym(event, sample, thread, attr);
 
+        if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
+                print_sample_bpf_output(sample);
+
         printf("\n");
 }
 
@@ -1090,23 +1212,6 @@ static struct script_spec *script_spec__find(const char *spec)
         return NULL;
 }
 
-static struct script_spec *script_spec__findnew(const char *spec,
-                                                struct scripting_ops *ops)
-{
-        struct script_spec *s = script_spec__find(spec);
-
-        if (s)
-                return s;
-
-        s = script_spec__new(spec, ops);
-        if (!s)
-                return NULL;
-
-        script_spec__add(s);
-
-        return s;
-}
-
 int script_spec_register(const char *spec, struct scripting_ops *ops)
 {
         struct script_spec *s;
@@ -1115,9 +1220,11 @@ int script_spec_register(const char *spec, struct scripting_ops *ops)
         if (s)
                 return -1;
 
-        s = script_spec__findnew(spec, ops);
+        s = script_spec__new(spec, ops);
         if (!s)
                 return -1;
+        else
+                script_spec__add(s);
 
         return 0;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 038e877081b6..1f19f2f999c8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,7 @@ static bool			sync_run			= false;
 static unsigned int             initial_delay                   = 0;
 static unsigned int             unit_width                      = 4; /* strlen("unit") */
 static bool                     forever                         = false;
+static bool                     metric_only                     = false;
 static struct timespec          ref_time;
 static struct cpu_map           *aggr_map;
 static aggr_get_id_t            aggr_get_id;
@@ -735,6 +736,191 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
         }
 }
 
+struct outstate {
+        FILE *fh;
+        bool newline;
+        const char *prefix;
+        int  nfields;
+        int  id, nr;
+        struct perf_evsel *evsel;
+};
+
+#define METRIC_LEN  35
+
+static void new_line_std(void *ctx)
+{
+        struct outstate *os = ctx;
+
+        os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+        fputc('\n', os->fh);
+        fputs(os->prefix, os->fh);
+        aggr_printout(os->evsel, os->id, os->nr);
+        if (stat_config.aggr_mode == AGGR_NONE)
+                fprintf(os->fh, "        ");
+        fprintf(os->fh, "                                                 ");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+                             const char *unit, double val)
+{
+        struct outstate *os = ctx;
+        FILE *out = os->fh;
+        int n;
+        bool newline = os->newline;
+
+        os->newline = false;
+
+        if (unit == NULL || fmt == NULL) {
+                fprintf(out, "%-*s", METRIC_LEN, "");
+                return;
+        }
+
+        if (newline)
+                do_new_line_std(os);
+
+        n = fprintf(out, " # ");
+        if (color)
+                n += color_fprintf(out, color, fmt, val);
+        else
+                n += fprintf(out, fmt, val);
+        fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
+static void new_line_csv(void *ctx)
+{
+        struct outstate *os = ctx;
+        int i;
+
+        fputc('\n', os->fh);
+        if (os->prefix)
+                fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+        aggr_printout(os->evsel, os->id, os->nr);
+        for (i = 0; i < os->nfields; i++)
+                fputs(csv_sep, os->fh);
+}
+
+static void print_metric_csv(void *ctx,
+                             const char *color __maybe_unused,
+                             const char *fmt, const char *unit, double val)
+{
+        struct outstate *os = ctx;
+        FILE *out = os->fh;
+        char buf[64], *vals, *ends;
+
+        if (unit == NULL || fmt == NULL) {
+                fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+                return;
+        }
+        snprintf(buf, sizeof(buf), fmt, val);
+        vals = buf;
+        while (isspace(*vals))
+                vals++;
+        ends = vals;
+        while (isdigit(*ends) || *ends == '.')
+                ends++;
+        *ends = 0;
+        while (isspace(*unit))
+                unit++;
+        fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+}
+
+#define METRIC_ONLY_LEN 20
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+        if (!unit)
+                return false;
+        if (strstr(unit, "/sec") ||
+            strstr(unit, "hz") ||
+            strstr(unit, "Hz") ||
+            strstr(unit, "CPUs utilized"))
+                return false;
+        return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+                           const char *unit)
+{
+        if (!strncmp(unit, "of all", 6)) {
+                snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+                         unit);
+                return buf;
+        }
+        return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+                              const char *unit, double val)
+{
+        struct outstate *os = ctx;
+        FILE *out = os->fh;
+        int n;
+        char buf[1024];
+        unsigned mlen = METRIC_ONLY_LEN;
+
+        if (!valid_only_metric(unit))
+                return;
+        unit = fixunit(buf, os->evsel, unit);
+        if (color)
+                n = color_fprintf(out, color, fmt, val);
+        else
+                n = fprintf(out, fmt, val);
+        if (n > METRIC_ONLY_LEN)
+                n = METRIC_ONLY_LEN;
+        if (mlen < strlen(unit))
+                mlen = strlen(unit) + 1;
+        fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+                                  const char *fmt,
+                                  const char *unit, double val)
+{
+        struct outstate *os = ctx;
+        FILE *out = os->fh;
+        char buf[64], *vals, *ends;
+        char tbuf[1024];
+
+        if (!valid_only_metric(unit))
+                return;
+        unit = fixunit(tbuf, os->evsel, unit);
+        snprintf(buf, sizeof buf, fmt, val);
+        vals = buf;
+        while (isspace(*vals))
+                vals++;
+        ends = vals;
+        while (isdigit(*ends) || *ends == '.')
+                ends++;
+        *ends = 0;
+        fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+                                const char *fmt __maybe_unused,
+                                const char *unit, double val __maybe_unused)
+{
+        struct outstate *os = ctx;
+        char tbuf[1024];
+
+        if (!valid_only_metric(unit))
+                return;
+        unit = fixunit(tbuf, os->evsel, unit);
+        if (csv_output)
+                fprintf(os->fh, "%s%s", unit, csv_sep);
+        else
+                fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
 static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
         FILE *output = stat_config.output;
@@ -763,6 +949,28 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
                 fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
+static int first_shadow_cpu(struct perf_evsel *evsel, int id)
+{
+        int i;
+
+        if (!aggr_get_id)
+                return 0;
+
+        if (stat_config.aggr_mode == AGGR_NONE)
+                return id;
+
+        if (stat_config.aggr_mode == AGGR_GLOBAL)
+                return 0;
+
+        for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
+                int cpu2 = perf_evsel__cpus(evsel)->map[i];
+
+                if (aggr_get_id(evsel_list->cpus, cpu2) == id)
+                        return cpu2;
+        }
+        return 0;
+}
+
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
         FILE *output = stat_config.output;
@@ -793,22 +1001,124 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
                 fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 }
 
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+                     char *prefix, u64 run, u64 ena, double noise)
 {
-        int cpu = cpu_map__id_to_cpu(id);
+        struct perf_stat_output_ctx out;
+        struct outstate os = {
+                .fh = stat_config.output,
+                .prefix = prefix ? prefix : "",
+                .id = id,
+                .nr = nr,
+                .evsel = counter,
+        };
+        print_metric_t pm = print_metric_std;
+        void (*nl)(void *);
 
-        if (stat_config.aggr_mode == AGGR_GLOBAL)
-                cpu = 0;
+        if (metric_only) {
+                nl = new_line_metric;
+                if (csv_output)
+                        pm = print_metric_only_csv;
+                else
+                        pm = print_metric_only;
+        } else
+                nl = new_line_std;
+
+        if (csv_output && !metric_only) {
+                static int aggr_fields[] = {
+                        [AGGR_GLOBAL] = 0,
+                        [AGGR_THREAD] = 1,
+                        [AGGR_NONE] = 1,
+                        [AGGR_SOCKET] = 2,
+                        [AGGR_CORE] = 2,
+                };
+
+                pm = print_metric_csv;
+                nl = new_line_csv;
+                os.nfields = 3;
+                os.nfields += aggr_fields[stat_config.aggr_mode];
+                if (counter->cgrp)
+                        os.nfields++;
+        }
+        if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
+                if (metric_only) {
+                        pm(&os, NULL, "", "", 0);
+                        return;
+                }
+                aggr_printout(counter, id, nr);
+
+                fprintf(stat_config.output, "%*s%s",
+                        csv_output ? 0 : 18,
+                        counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+                        csv_sep);
+
+                fprintf(stat_config.output, "%-*s%s",
+                        csv_output ? 0 : unit_width,
+                        counter->unit, csv_sep);
+
+                fprintf(stat_config.output, "%*s",
+                        csv_output ? 0 : -25,
+                        perf_evsel__name(counter));
+
+                if (counter->cgrp)
+                        fprintf(stat_config.output, "%s%s",
+                                csv_sep, counter->cgrp->name);
 
-        if (nsec_counter(counter))
+                if (!csv_output)
+                        pm(&os, NULL, NULL, "", 0);
+                print_noise(counter, noise);
+                print_running(run, ena);
+                if (csv_output)
+                        pm(&os, NULL, NULL, "", 0);
+                return;
+        }
+
+        if (metric_only)
+                /* nothing */;
+        else if (nsec_counter(counter))
                 nsec_printout(id, nr, counter, uval);
         else
                 abs_printout(id, nr, counter, uval);
 
-        if (!csv_output && !stat_config.interval)
-                perf_stat__print_shadow_stats(stat_config.output, counter,
-                                              uval, cpu,
-                                              stat_config.aggr_mode);
+        out.print_metric = pm;
+        out.new_line = nl;
+        out.ctx = &os;
+
+        if (csv_output && !metric_only) {
+                print_noise(counter, noise);
+                print_running(run, ena);
+        }
+
+        perf_stat__print_shadow_stats(counter, uval,
+                                first_shadow_cpu(counter, id),
+                                &out);
+        if (!csv_output && !metric_only) {
+                print_noise(counter, noise);
+                print_running(run, ena);
+        }
+}
+
+static void aggr_update_shadow(void)
+{
+        int cpu, s2, id, s;
+        u64 val;
+        struct perf_evsel *counter;
+
+        for (s = 0; s < aggr_map->nr; s++) {
+                id = aggr_map->map[s];
+                evlist__for_each(evsel_list, counter) {
+                        val = 0;
+                        for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
+                                s2 = aggr_get_id(evsel_list->cpus, cpu);
+                                if (s2 != id)
+                                        continue;
+                                val += perf_counts(counter->counts, cpu, 0)->val;
+                        }
+                        val = val * counter->scale;
+                        perf_stat__update_shadow_stats(counter, &val,
+                                                       first_shadow_cpu(counter, id));
+                }
+        }
 }
 
 static void print_aggr(char *prefix)
@@ -818,12 +1128,23 @@ static void print_aggr(char *prefix)
         int cpu, s, s2, id, nr;
         double uval;
         u64 ena, run, val;
+        bool first;
 
         if (!(aggr_map || aggr_get_id))
                 return;
 
+        aggr_update_shadow();
+
+        /*
+         * With metric_only everything is on a single line.
+         * Without each counter has its own line.
+         */
         for (s = 0; s < aggr_map->nr; s++) {
+                if (prefix && metric_only)
+                        fprintf(output, "%s", prefix);
+
                 id = aggr_map->map[s];
+                first = true;
                 evlist__for_each(evsel_list, counter) {
                         val = ena = run = 0;
                         nr = 0;
@@ -836,41 +1157,20 @@ static void print_aggr(char *prefix)
                                 run += perf_counts(counter->counts, cpu, 0)->run;
                                 nr++;
                         }
-                        if (prefix)
-                                fprintf(output, "%s", prefix);
-
-                        if (run == 0 || ena == 0) {
+                        if (first && metric_only) {
+                                first = false;
                                 aggr_printout(counter, id, nr);
-
-                                fprintf(output, "%*s%s",
-                                        csv_output ? 0 : 18,
-                                        counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-                                        csv_sep);
-
-                                fprintf(output, "%-*s%s",
-                                        csv_output ? 0 : unit_width,
-                                        counter->unit, csv_sep);
-
-                                fprintf(output, "%*s",
-                                        csv_output ? 0 : -25,
-                                        perf_evsel__name(counter));
-
-                                if (counter->cgrp)
-                                        fprintf(output, "%s%s",
-                                                csv_sep, counter->cgrp->name);
-
-                                print_running(run, ena);
-                                fputc('\n', output);
-                                continue;
                         }
-                        uval = val * counter->scale;
-                        printout(id, nr, counter, uval);
-                        if (!csv_output)
-                                print_noise(counter, 1.0);
+                        if (prefix && !metric_only)
+                                fprintf(output, "%s", prefix);
 
-                        print_running(run, ena);
-                        fputc('\n', output);
+                        uval = val * counter->scale;
+                        printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+                        if (!metric_only)
+                                fputc('\n', output);
                 }
+                if (metric_only)
+                        fputc('\n', output);
         }
 }
 
@@ -895,12 +1195,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
                         fprintf(output, "%s", prefix);
 
                 uval = val * counter->scale;
-                printout(thread, 0, counter, uval);
-
-                if (!csv_output)
-                        print_noise(counter, 1.0);
-
-                print_running(run, ena);
+                printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
                 fputc('\n', output);
         }
 }
@@ -914,43 +1209,19 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
         FILE *output = stat_config.output;
         struct perf_stat_evsel *ps = counter->priv;
         double avg = avg_stats(&ps->res_stats[0]);
-        int scaled = counter->counts->scaled;
         double uval;
         double avg_enabled, avg_running;
 
         avg_enabled = avg_stats(&ps->res_stats[1]);
         avg_running = avg_stats(&ps->res_stats[2]);
 
-        if (prefix)
+        if (prefix && !metric_only)
                 fprintf(output, "%s", prefix);
 
-        if (scaled == -1 || !counter->supported) {
-                fprintf(output, "%*s%s",
-                        csv_output ? 0 : 18,
-                        counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-                        csv_sep);
-                fprintf(output, "%-*s%s",
-                        csv_output ? 0 : unit_width,
-                        counter->unit, csv_sep);
-                fprintf(output, "%*s",
-                        csv_output ? 0 : -25,
-                        perf_evsel__name(counter));
-
-                if (counter->cgrp)
-                        fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
-                print_running(avg_running, avg_enabled);
-                fputc('\n', output);
-                return;
-        }
-
         uval = avg * counter->scale;
-        printout(-1, 0, counter, uval);
-
-        print_noise(counter, avg);
-
-        print_running(avg_running, avg_enabled);
-        fprintf(output, "\n");
+        printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
+        if (!metric_only)
+                fprintf(output, "\n");
 }
 
 /*
@@ -972,39 +1243,78 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
                 if (prefix)
                         fprintf(output, "%s", prefix);
 
-                if (run == 0 || ena == 0) {
-                        fprintf(output, "CPU%*d%s%*s%s",
-                                csv_output ? 0 : -4,
-                                perf_evsel__cpus(counter)->map[cpu], csv_sep,
-                                csv_output ? 0 : 18,
-                                counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
-                                csv_sep);
+                uval = val * counter->scale;
+                printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
 
-                                fprintf(output, "%-*s%s",
-                                        csv_output ? 0 : unit_width,
-                                        counter->unit, csv_sep);
+                fputc('\n', output);
+        }
+}
 
-                                fprintf(output, "%*s",
-                                        csv_output ? 0 : -25,
-                                        perf_evsel__name(counter));
+static void print_no_aggr_metric(char *prefix)
+{
+        int cpu;
+        int nrcpus = 0;
+        struct perf_evsel *counter;
+        u64 ena, run, val;
+        double uval;
 
-                        if (counter->cgrp)
-                                fprintf(output, "%s%s",
-                                        csv_sep, counter->cgrp->name);
+        nrcpus = evsel_list->cpus->nr;
+        for (cpu = 0; cpu < nrcpus; cpu++) {
+                bool first = true;
 
-                        print_running(run, ena);
-                        fputc('\n', output);
-                        continue;
+                if (prefix)
+                        fputs(prefix, stat_config.output);
+                evlist__for_each(evsel_list, counter) {
+                        if (first) {
+                                aggr_printout(counter, cpu, 0);
+                                first = false;
+                        }
+                        val = perf_counts(counter->counts, cpu, 0)->val;
+                        ena = perf_counts(counter->counts, cpu, 0)->ena;
+                        run = perf_counts(counter->counts, cpu, 0)->run;
+
+                        uval = val * counter->scale;
+                        printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
                 }
+                fputc('\n', stat_config.output);
+        }
+}
 
-                uval = val * counter->scale;
-                printout(cpu, 0, counter, uval);
-                if (!csv_output)
-                        print_noise(counter, 1.0);
-                print_running(run, ena);
+static int aggr_header_lens[] = {
+        [AGGR_CORE] = 18,
+        [AGGR_SOCKET] = 12,
+        [AGGR_NONE] = 6,
+        [AGGR_THREAD] = 24,
+        [AGGR_GLOBAL] = 0,
+};
 
-                fputc('\n', output);
+static void print_metric_headers(char *prefix)
+{
+        struct perf_stat_output_ctx out;
+        struct perf_evsel *counter;
+        struct outstate os = {
+                .fh = stat_config.output
+        };
+
+        if (prefix)
+                fprintf(stat_config.output, "%s", prefix);
+
+        if (!csv_output)
+                fprintf(stat_config.output, "%*s",
+                        aggr_header_lens[stat_config.aggr_mode], "");
+
+        /* Print metrics headers only */
+        evlist__for_each(evsel_list, counter) {
+                os.evsel = counter;
+                out.ctx = &os;
+                out.print_metric = print_metric_header;
+                out.new_line = new_line_metric;
+                os.evsel = counter;
+                perf_stat__print_shadow_stats(counter, 0,
+                                              0,
+                                              &out);
         }
+        fputc('\n', stat_config.output);
 }
 
 static void print_interval(char *prefix, struct timespec *ts)
@@ -1014,7 +1324,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 
         sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
 
-        if (num_print_interval == 0 && !csv_output) {
+        if (num_print_interval == 0 && !csv_output && !metric_only) {
                 switch (stat_config.aggr_mode) {
                 case AGGR_SOCKET:
                         fprintf(output, "#           time socket cpus             counts %*s events\n", unit_width, "unit");
@@ -1101,6 +1411,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
         else
                 print_header(argc, argv);
 
+        if (metric_only) {
+                static int num_print_iv;
+
+                if (num_print_iv == 0)
+                        print_metric_headers(prefix);
+                if (num_print_iv++ == 25)
+                        num_print_iv = 0;
+                if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+                        fprintf(stat_config.output, "%s", prefix);
+        }
+
         switch (stat_config.aggr_mode) {
         case AGGR_CORE:
         case AGGR_SOCKET:
@@ -1113,10 +1434,16 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
         case AGGR_GLOBAL:
                 evlist__for_each(evsel_list, counter)
                         print_counter_aggr(counter, prefix);
+                if (metric_only)
+                        fputc('\n', stat_config.output);
                 break;
         case AGGR_NONE:
-                evlist__for_each(evsel_list, counter)
-                        print_counter(counter, prefix);
+                if (metric_only)
+                        print_no_aggr_metric(prefix);
+                else {
+                        evlist__for_each(evsel_list, counter)
+                                print_counter(counter, prefix);
+                }
                 break;
         case AGGR_UNSET:
         default:
@@ -1237,6 +1564,8 @@ static const struct option stat_options[] = {
                      "aggregate counts per thread", AGGR_THREAD),
         OPT_UINTEGER('D', "delay", &initial_delay,
                      "ms to wait before starting measurement after program start"),
+        OPT_BOOLEAN(0, "metric-only", &metric_only,
+                        "Only print computed metrics. No raw values"),
         OPT_END()
 };
 
@@ -1435,7 +1764,7 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
  */
 static int add_default_attributes(void)
 {
-        struct perf_event_attr default_attrs[] = {
+        struct perf_event_attr default_attrs0[] = {
 
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK              },
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES        },
@@ -1443,8 +1772,14 @@ static int add_default_attributes(void)
   { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS             },
 
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES              },
+};
+        struct perf_event_attr frontend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
+};
+        struct perf_event_attr backend_attrs[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND  },
+};
+        struct perf_event_attr default_attrs1[] = {
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS            },
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS     },
   { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES           },
@@ -1561,7 +1896,19 @@ static int add_default_attributes(void)
         }
 
         if (!evsel_list->nr_entries) {
-                if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
+                if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
+                        return -1;
+                if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
+                        if (perf_evlist__add_default_attrs(evsel_list,
+                                                frontend_attrs) < 0)
+                                return -1;
+                }
+                if (pmu_have_event("cpu", "stalled-cycles-backend")) {
+                        if (perf_evlist__add_default_attrs(evsel_list,
+                                                backend_attrs) < 0)
+                                return -1;
+                }
+                if (perf_evlist__add_default_attrs(evsel_list, default_attrs1) < 0)
                         return -1;
         }
 
@@ -1825,9 +2172,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
         if (evsel_list == NULL)
                 return -ENOMEM;
 
+        parse_events__shrink_config_terms();
         argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
                                         (const char **) stat_usage,
                                         PARSE_OPT_STOP_AT_NON_OPTION);
+        perf_stat__init_shadow_stats();
 
         if (csv_sep) {
                 csv_output = true;
@@ -1858,6 +2207,16 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
                 goto out;
         }
 
+        if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+                fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+                goto out;
+        }
+
+        if (metric_only && run_count > 1) {
+                fprintf(stderr, "--metric-only is not supported with -r\n");
+                goto out;
+        }
+
         if (output_fd < 0) {
                 fprintf(stderr, "argument to --log-fd must be a > 0\n");
                 parse_options_usage(stat_usage, stat_options, "log-fd", 0);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index bf01cbb0ef23..94af190f6843 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -252,7 +252,8 @@ static void perf_top__print_sym_table(struct perf_top *top)
         char bf[160];
         int printed = 0;
         const int win_width = top->winsize.ws_col - 1;
-        struct hists *hists = evsel__hists(top->sym_evsel);
+        struct perf_evsel *evsel = top->sym_evsel;
+        struct hists *hists = evsel__hists(evsel);
 
         puts(CONSOLE_CLEAR);
 
@@ -288,7 +289,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
         }
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 
         hists__output_recalc_col_len(hists, top->print_entries - printed);
         putchar('\n');
@@ -540,6 +541,7 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 static void perf_top__sort_new_samples(void *arg)
 {
         struct perf_top *t = arg;
+        struct perf_evsel *evsel = t->sym_evsel;
         struct hists *hists;
 
         perf_top__reset_sample_counters(t);
@@ -547,7 +549,7 @@ static void perf_top__sort_new_samples(void *arg)
         if (t->evlist->selected != NULL)
                 t->sym_evsel = t->evlist->selected;
 
-        hists = evsel__hists(t->sym_evsel);
+        hists = evsel__hists(evsel);
 
         if (t->evlist->enabled) {
                 if (t->zero) {
@@ -559,7 +561,7 @@ static void perf_top__sort_new_samples(void *arg)
         }
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 }
 
 static void *display_thread_tui(void *arg)
@@ -1063,7 +1065,7 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
         return parse_callchain_top_opt(arg);
 }
 
-static int perf_top_config(const char *var, const char *value, void *cb)
+static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused)
 {
         if (!strcmp(var, "top.call-graph"))
                 var = "call-graph.record-mode"; /* fall-through */
@@ -1072,7 +1074,7 @@ static int perf_top_config(const char *var, const char *value, void *cb)
                 return 0;
         }
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 static int
@@ -1212,6 +1214,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                      parse_branch_stack),
         OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace,
                     "Show raw trace event output (do not use print fmt or plugins)"),
+        OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
+                    "Show entries in a hierarchy"),
         OPT_END()
         };
         const char * const top_usage[] = {
@@ -1239,10 +1243,30 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                 goto out_delete_evlist;
         }
 
+        if (symbol_conf.report_hierarchy) {
+                /* disable incompatible options */
+                symbol_conf.event_group = false;
+                symbol_conf.cumulate_callchain = false;
+
+                if (field_order) {
+                        pr_err("Error: --hierarchy and --fields options cannot be used together\n");
+                        parse_options_usage(top_usage, options, "fields", 0);
+                        parse_options_usage(NULL, options, "hierarchy", 0);
+                        goto out_delete_evlist;
+                }
+        }
+
         sort__mode = SORT_MODE__TOP;
         /* display thread wants entries to be collapsed in a different tree */
         sort__need_collapse = 1;
 
+        if (top.use_stdio)
+                use_browser = 0;
+        else if (top.use_tui)
+                use_browser = 1;
+
+        setup_browser(false);
+
         if (setup_sorting(top.evlist) < 0) {
                 if (sort_order)
                         parse_options_usage(top_usage, options, "s", 1);
@@ -1252,13 +1276,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                 goto out_delete_evlist;
         }
 
-        if (top.use_stdio)
-                use_browser = 0;
-        else if (top.use_tui)
-                use_browser = 1;
-
-        setup_browser(false);
-
         status = target__validate(target);
         if (status) {
                 target__strerror(target, status, errbuf, BUFSIZ);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 20916dd77aac..8dc98c598b1a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -33,6 +33,7 @@
 #include "util/stat.h"
 #include "trace-event.h"
 #include "util/parse-events.h"
+#include "util/bpf-loader.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -1724,8 +1725,12 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 
         sc->args = sc->tp_format->format.fields;
         sc->nr_args = sc->tp_format->format.nr_fields;
-        /* drop nr field - not relevant here; does not exist on older kernels */
-        if (sc->args && strcmp(sc->args->name, "nr") == 0) {
+        /*
+         * We need to check and discard the first variable '__syscall_nr'
+         * or 'nr' that mean the syscall number. It is needless here.
+         * So drop '__syscall_nr' or 'nr' field but does not exist on older kernels.
+         */
+        if (sc->args && (!strcmp(sc->args->name, "__syscall_nr") || !strcmp(sc->args->name, "nr"))) {
                 sc->args = sc->args->next;
                 --sc->nr_args;
         }
@@ -2177,6 +2182,37 @@ out_dump:
         return 0;
 }
 
+static void bpf_output__printer(enum binary_printer_ops op,
+                                unsigned int val, void *extra)
+{
+        FILE *output = extra;
+        unsigned char ch = (unsigned char)val;
+
+        switch (op) {
+        case BINARY_PRINT_CHAR_DATA:
+                fprintf(output, "%c", isprint(ch) ? ch : '.');
+                break;
+        case BINARY_PRINT_DATA_BEGIN:
+        case BINARY_PRINT_LINE_BEGIN:
+        case BINARY_PRINT_ADDR:
+        case BINARY_PRINT_NUM_DATA:
+        case BINARY_PRINT_NUM_PAD:
+        case BINARY_PRINT_SEP:
+        case BINARY_PRINT_CHAR_PAD:
+        case BINARY_PRINT_LINE_END:
+        case BINARY_PRINT_DATA_END:
+        default:
+                break;
+        }
+}
+
+static void bpf_output__fprintf(struct trace *trace,
+                                struct perf_sample *sample)
+{
+        print_binary(sample->raw_data, sample->raw_size, 8,
+                     bpf_output__printer, trace->output);
+}
+
 static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
                                 union perf_event *event __maybe_unused,
                                 struct perf_sample *sample)
@@ -2189,7 +2225,9 @@ static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
 
         fprintf(trace->output, "%s:", evsel->name);
 
-        if (evsel->tp_format) {
+        if (perf_evsel__is_bpf_output(evsel)) {
+                bpf_output__fprintf(trace, sample);
+        } else if (evsel->tp_format) {
                 event_format__fprintf(evsel->tp_format, sample->cpu,
                                       sample->raw_data, sample->raw_size,
                                       trace->output);
@@ -2586,6 +2624,16 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
         if (err < 0)
                 goto out_error_open;
 
+        err = bpf__apply_obj_config();
+        if (err) {
+                char errbuf[BUFSIZ];
+
+                bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
+                pr_err("ERROR: Apply config to BPF failed: %s\n",
+                         errbuf);
+                goto out_error_open;
+        }
+
         /*
          * Better not use !target__has_task() here because we need to cover the
          * case where no threads were specified in the command line, but a
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 511141b102e8..eca6a912e8c2 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -61,50 +61,45 @@ endif
 
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
-else
-  #
-  # For linking with debug library, run like:
-  #
-  #   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
-  #
-  ifdef LIBUNWIND_DIR
-    LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
-    LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
-  endif
-  LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
-
-  # Set per-feature check compilation flags
-  FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
-  FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 endif
+#
+# For linking with debug library, run like:
+#
+#   make DEBUG=1 LIBUNWIND_DIR=/opt/libunwind/
+#
+ifdef LIBUNWIND_DIR
+  LIBUNWIND_CFLAGS  = -I$(LIBUNWIND_DIR)/include
+  LIBUNWIND_LDFLAGS = -L$(LIBUNWIND_DIR)/lib
+endif
+LIBUNWIND_LDFLAGS += $(LIBUNWIND_LIBS)
+
+# Set per-feature check compilation flags
+FEATURE_CHECK_CFLAGS-libunwind = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind = $(LIBUNWIND_LDFLAGS)
+FEATURE_CHECK_CFLAGS-libunwind-debug-frame = $(LIBUNWIND_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libunwind-debug-frame = $(LIBUNWIND_LDFLAGS)
 
 ifeq ($(NO_PERF_REGS),0)
   CFLAGS += -DHAVE_PERF_REGS_SUPPORT
 endif
 
-ifndef NO_LIBELF
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBDW_DIR=/opt/libdw/
-  ifdef LIBDW_DIR
-    LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
-    LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
+# for linking with debug library, run like:
+# make DEBUG=1 LIBDW_DIR=/opt/libdw/
+ifdef LIBDW_DIR
+  LIBDW_CFLAGS  := -I$(LIBDW_DIR)/include
+  LIBDW_LDFLAGS := -L$(LIBDW_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libdw-dwarf-unwind := $(LIBDW_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libdw-dwarf-unwind := $(LIBDW_LDFLAGS) -ldw
 
-ifdef LIBBABELTRACE
-  # for linking with debug library, run like:
-  # make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
-  ifdef LIBBABELTRACE_DIR
-    LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
-    LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
-  endif
-  FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
-  FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
+# for linking with debug library, run like:
+# make DEBUG=1 LIBBABELTRACE_DIR=/opt/libbabeltrace/
+ifdef LIBBABELTRACE_DIR
+  LIBBABELTRACE_CFLAGS  := -I$(LIBBABELTRACE_DIR)/include
+  LIBBABELTRACE_LDFLAGS := -L$(LIBBABELTRACE_DIR)/lib
 endif
+FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi
 # include ARCH specific config
@@ -145,28 +140,26 @@ ifdef PARSER_DEBUG
   $(call detected_var,PARSER_DEBUG_FLEX)
 endif
 
-ifndef NO_LIBPYTHON
-  # Try different combinations to accommodate systems that only have
-  # python[2][-config] in weird combinations but always preferring
-  # python2 and python2-config as per pep-0394. If we catch a
-  # python[-config] in version 3, the version check will kill it.
-  PYTHON2 := $(if $(call get-executable,python2),python2,python)
-  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
-  PYTHON2_CONFIG := \
-    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
-  override PYTHON_CONFIG := \
-    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+# Try different combinations to accommodate systems that only have
+# python[2][-config] in weird combinations but always preferring
+# python2 and python2-config as per pep-0394. If we catch a
+# python[-config] in version 3, the version check will kill it.
+PYTHON2 := $(if $(call get-executable,python2),python2,python)
+override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+PYTHON2_CONFIG := \
+  $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+override PYTHON_CONFIG := \
+  $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
 
-  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
 
-  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
 
-  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
-endif
+FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
@@ -335,6 +328,13 @@ ifndef NO_LIBELF
   endif # NO_LIBBPF
 endif # NO_LIBELF
 
+ifdef PERF_HAVE_JITDUMP
+  ifndef NO_DWARF
+    $(call detected,CONFIG_JITDUMP)
+    CFLAGS += -DHAVE_JITDUMP
+  endif
+endif
+
 ifeq ($(ARCH),powerpc)
   ifndef NO_DWARF
     CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
@@ -411,6 +411,17 @@ ifndef NO_LIBAUDIT
   endif
 endif
 
+ifndef NO_LIBCRYPTO
+  ifneq ($(feature-libcrypto), 1)
+    msg := $(warning No libcrypto.h found, disables jitted code injection, please install libssl-devel or libssl-dev);
+    NO_LIBCRYPTO := 1
+  else
+    CFLAGS += -DHAVE_LIBCRYPTO_SUPPORT
+    EXTLIBS += -lcrypto
+    $(call detected,CONFIG_CRYPTO)
+  endif
+endif
+
 ifdef NO_NEWT
   NO_SLANG=1
 endif
diff --git a/tools/perf/jvmti/Makefile b/tools/perf/jvmti/Makefile
new file mode 100644
index 000000000000..5ce61a1bda9c
--- /dev/null
+++ b/tools/perf/jvmti/Makefile
@@ -0,0 +1,89 @@
+ARCH=$(shell uname -m)
+
+ifeq ($(ARCH), x86_64)
+JARCH=amd64
+endif
+ifeq ($(ARCH), armv7l)
+JARCH=armhf
+endif
+ifeq ($(ARCH), armv6l)
+JARCH=armhf
+endif
+ifeq ($(ARCH), aarch64)
+JARCH=aarch64
+endif
+ifeq ($(ARCH), ppc64)
+JARCH=powerpc
+endif
+ifeq ($(ARCH), ppc64le)
+JARCH=powerpc
+endif
+
+DESTDIR=/usr/local
+
+VERSION=1
+REVISION=0
+AGE=0
+
+LN=ln -sf
+RM=rm
+
+SLIBJVMTI=libjvmti.so.$(VERSION).$(REVISION).$(AGE)
+VLIBJVMTI=libjvmti.so.$(VERSION)
+SLDFLAGS=-shared -Wl,-soname -Wl,$(VLIBJVMTI)
+SOLIBEXT=so
+
+# The following works at least on fedora 23, you may need the next
+# line for other distros.
+ifneq (,$(wildcard /usr/sbin/update-java-alternatives))
+JDIR=$(shell /usr/sbin/update-java-alternatives -l | head -1 | cut -d ' ' -f 3)
+else
+  ifneq (,$(wildcard /usr/sbin/alternatives))
+    JDIR=$(shell alternatives --display java | tail -1 | cut -d' ' -f 5 | sed 's%/jre/bin/java.%%g')
+  endif
+endif
+ifndef JDIR
+$(error Could not find alternatives command, you need to set JDIR= to point to the root of your Java directory)
+else
+  ifeq (,$(wildcard $(JDIR)/include/jvmti.h))
+  $(error the openjdk development package appears to me missing, install and try again)
+  endif
+endif
+$(info Using Java from $(JDIR))
+# -lrt required in 32-bit mode for clock_gettime()
+LIBS=-lelf -lrt
+INCDIR=-I $(JDIR)/include -I $(JDIR)/include/linux
+
+TARGETS=$(SLIBJVMTI)
+
+SRCS=libjvmti.c jvmti_agent.c
+OBJS=$(SRCS:.c=.o)
+SOBJS=$(OBJS:.o=.lo)
+OPT=-O2 -g -Werror -Wall
+
+CFLAGS=$(INCDIR) $(OPT)
+
+all: $(TARGETS)
+
+.c.o:
+        $(CC) $(CFLAGS) -c $*.c
+.c.lo:
+        $(CC) -fPIC -DPIC $(CFLAGS) -c $*.c -o $*.lo
+
+$(OBJS) $(SOBJS): Makefile jvmti_agent.h ../util/jitdump.h
+
+$(SLIBJVMTI):  $(SOBJS)
+        $(CC) $(CFLAGS) $(SLDFLAGS)  -o $@ $(SOBJS) $(LIBS)
+        $(LN) $@ libjvmti.$(SOLIBEXT)
+
+clean:
+        $(RM) -f *.o *.so.* *.so *.lo
+
+install:
+        -mkdir -p $(DESTDIR)/lib
+        install -m 755 $(SLIBJVMTI) $(DESTDIR)/lib/
+        (cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) $(VLIBJVMTI))
+        (cd $(DESTDIR)/lib; $(LN) $(SLIBJVMTI) libjvmti.$(SOLIBEXT))
+        ldconfig
+
+.SUFFIXES: .c .S .o .lo
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
new file mode 100644
index 000000000000..6461e02ab940
--- /dev/null
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -0,0 +1,465 @@
+/*
+ * jvmti_agent.c: JVMTI agent interface
+ *
+ * Adapted from the Oprofile code in opagent.c:
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2.1 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#include <sys/types.h>
+#include <sys/stat.h> /* for mkdir() */
+#include <stdio.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <syscall.h> /* for gettid() */
+#include <err.h>
+
+#include "jvmti_agent.h"
+#include "../util/jitdump.h"
+
+#define JIT_LANG "java"
+
+static char jit_path[PATH_MAX];
+static void *marker_addr;
+
+/*
+ * padding buffer
+ */
+static const char pad_bytes[7];
+
+static inline pid_t gettid(void)
+{
+        return (pid_t)syscall(__NR_gettid);
+}
+
+static int get_e_machine(struct jitheader *hdr)
+{
+        ssize_t sret;
+        char id[16];
+        int fd, ret = -1;
+        int m = -1;
+        struct {
+                uint16_t e_type;
+                uint16_t e_machine;
+        } info;
+
+        fd = open("/proc/self/exe", O_RDONLY);
+        if (fd == -1)
+                return -1;
+
+        sret = read(fd, id, sizeof(id));
+        if (sret != sizeof(id))
+                goto error;
+
+        /* check ELF signature */
+        if (id[0] != 0x7f || id[1] != 'E' || id[2] != 'L' || id[3] != 'F')
+                goto error;
+
+        sret = read(fd, &info, sizeof(info));
+        if (sret != sizeof(info))
+                goto error;
+
+        m = info.e_machine;
+        if (m < 0)
+                m = 0; /* ELF EM_NONE */
+
+        hdr->elf_mach = m;
+        ret = 0;
+error:
+        close(fd);
+        return ret;
+}
+
+#define NSEC_PER_SEC    1000000000
+static int perf_clk_id = CLOCK_MONOTONIC;
+
+static inline uint64_t
+timespec_to_ns(const struct timespec *ts)
+{
+        return ((uint64_t) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
+}
+
+static inline uint64_t
+perf_get_timestamp(void)
+{
+        struct timespec ts;
+        int ret;
+
+        ret = clock_gettime(perf_clk_id, &ts);
+        if (ret)
+                return 0;
+
+        return timespec_to_ns(&ts);
+}
+
+static int
+debug_cache_init(void)
+{
+        char str[32];
+        char *base, *p;
+        struct tm tm;
+        time_t t;
+        int ret;
+
+        time(&t);
+        localtime_r(&t, &tm);
+
+        base = getenv("JITDUMPDIR");
+        if (!base)
+                base = getenv("HOME");
+        if (!base)
+                base = ".";
+
+        strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm);
+
+        snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base);
+
+        ret = mkdir(jit_path, 0755);
+        if (ret == -1) {
+                if (errno != EEXIST) {
+                        warn("jvmti: cannot create jit cache dir %s", jit_path);
+                        return -1;
+                }
+        }
+
+        snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base);
+        ret = mkdir(jit_path, 0755);
+        if (ret == -1) {
+                if (errno != EEXIST) {
+                        warn("cannot create jit cache dir %s", jit_path);
+                        return -1;
+                }
+        }
+
+        snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str);
+
+        p = mkdtemp(jit_path);
+        if (p != jit_path) {
+                warn("cannot create jit cache dir %s", jit_path);
+                return -1;
+        }
+
+        return 0;
+}
+
+static int
+perf_open_marker_file(int fd)
+{
+        long pgsz;
+
+        pgsz = sysconf(_SC_PAGESIZE);
+        if (pgsz == -1)
+                return -1;
+
+        /*
+         * we mmap the jitdump to create an MMAP RECORD in perf.data file.
+         * The mmap is captured either live (perf record running when we mmap)
+         * or  in deferred mode, via /proc/PID/maps
+         * the MMAP record is used as a marker of a jitdump file for more meta
+         * data info about the jitted code. Perf report/annotate detect this
+         * special filename and process the jitdump file.
+         *
+         * mapping must be PROT_EXEC to ensure it is captured by perf record
+         * even when not using -d option
+         */
+        marker_addr = mmap(NULL, pgsz, PROT_READ|PROT_EXEC, MAP_PRIVATE, fd, 0);
+        return (marker_addr == MAP_FAILED) ? -1 : 0;
+}
+
+static void
+perf_close_marker_file(void)
+{
+        long pgsz;
+
+        if (!marker_addr)
+                return;
+
+        pgsz = sysconf(_SC_PAGESIZE);
+        if (pgsz == -1)
+                return;
+
+        munmap(marker_addr, pgsz);
+}
+
+void *jvmti_open(void)
+{
+        int pad_cnt;
+        char dump_path[PATH_MAX];
+        struct jitheader header;
+        int fd;
+        FILE *fp;
+
+        /*
+         * check if clockid is supported
+         */
+        if (!perf_get_timestamp())
+                warnx("jvmti: kernel does not support %d clock id", perf_clk_id);
+
+        memset(&header, 0, sizeof(header));
+
+        debug_cache_init();
+
+        /*
+         * jitdump file name
+         */
+        snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+
+        fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
+        if (fd == -1)
+                return NULL;
+
+        /*
+         * create perf.data maker for the jitdump file
+         */
+        if (perf_open_marker_file(fd)) {
+                warnx("jvmti: failed to create marker file");
+                return NULL;
+        }
+
+        fp = fdopen(fd, "w+");
+        if (!fp) {
+                warn("jvmti: cannot create %s", dump_path);
+                close(fd);
+                goto error;
+        }
+
+        warnx("jvmti: jitdump in %s", dump_path);
+
+        if (get_e_machine(&header)) {
+                warn("get_e_machine failed\n");
+                goto error;
+        }
+
+        header.magic      = JITHEADER_MAGIC;
+        header.version    = JITHEADER_VERSION;
+        header.total_size = sizeof(header);
+        header.pid        = getpid();
+
+        /* calculate amount of padding '\0' */
+        pad_cnt = PADDING_8ALIGNED(header.total_size);
+        header.total_size += pad_cnt;
+
+        header.timestamp = perf_get_timestamp();
+
+        if (!fwrite(&header, sizeof(header), 1, fp)) {
+                warn("jvmti: cannot write dumpfile header");
+                goto error;
+        }
+
+        /* write padding '\0' if necessary */
+        if (pad_cnt && !fwrite(pad_bytes, pad_cnt, 1, fp)) {
+                warn("jvmti: cannot write dumpfile header padding");
+                goto error;
+        }
+
+        return fp;
+error:
+        fclose(fp);
+        return NULL;
+}
+
+int
+jvmti_close(void *agent)
+{
+        struct jr_code_close rec;
+        FILE *fp = agent;
+
+        if (!fp) {
+                warnx("jvmti: incalid fd in close_agent");
+                return -1;
+        }
+
+        rec.p.id = JIT_CODE_CLOSE;
+        rec.p.total_size = sizeof(rec);
+
+        rec.p.timestamp = perf_get_timestamp();
+
+        if (!fwrite(&rec, sizeof(rec), 1, fp))
+                return -1;
+
+        fclose(fp);
+
+        fp = NULL;
+
+        perf_close_marker_file();
+
+        return 0;
+}
+
+int
+jvmti_write_code(void *agent, char const *sym,
+        uint64_t vma, void const *code, unsigned int const size)
+{
+        static int code_generation = 1;
+        struct jr_code_load rec;
+        size_t sym_len;
+        size_t padding_count;
+        FILE *fp = agent;
+        int ret = -1;
+
+        /* don't care about 0 length function, no samples */
+        if (size == 0)
+                return 0;
+
+        if (!fp) {
+                warnx("jvmti: invalid fd in write_native_code");
+                return -1;
+        }
+
+        sym_len = strlen(sym) + 1;
+
+        rec.p.id           = JIT_CODE_LOAD;
+        rec.p.total_size   = sizeof(rec) + sym_len;
+        padding_count      = PADDING_8ALIGNED(rec.p.total_size);
+        rec.p. total_size += padding_count;
+        rec.p.timestamp    = perf_get_timestamp();
+
+        rec.code_size  = size;
+        rec.vma        = vma;
+        rec.code_addr  = vma;
+        rec.pid        = getpid();
+        rec.tid        = gettid();
+
+        if (code)
+                rec.p.total_size += size;
+
+        /*
+         * If JVM is multi-threaded, nultiple concurrent calls to agent
+         * may be possible, so protect file writes
+         */
+        flockfile(fp);
+
+        /*
+         * get code index inside lock to avoid race condition
+         */
+        rec.code_index = code_generation++;
+
+        ret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
+        fwrite_unlocked(sym, sym_len, 1, fp);
+
+        if (padding_count)
+                fwrite_unlocked(pad_bytes, padding_count, 1, fp);
+
+        if (code)
+                fwrite_unlocked(code, size, 1, fp);
+
+        funlockfile(fp);
+
+        ret = 0;
+
+        return ret;
+}
+
+int
+jvmti_write_debug_info(void *agent, uint64_t code, const char *file,
+                       jvmti_line_info_t *li, int nr_lines)
+{
+        struct jr_code_debug_info rec;
+        size_t sret, len, size, flen;
+        size_t padding_count;
+        uint64_t addr;
+        const char *fn = file;
+        FILE *fp = agent;
+        int i;
+
+        /*
+         * no entry to write
+         */
+        if (!nr_lines)
+                return 0;
+
+        if (!fp) {
+                warnx("jvmti: invalid fd in write_debug_info");
+                return -1;
+        }
+
+        flen = strlen(file) + 1;
+
+        rec.p.id        = JIT_CODE_DEBUG_INFO;
+        size            = sizeof(rec);
+        rec.p.timestamp = perf_get_timestamp();
+        rec.code_addr   = (uint64_t)(uintptr_t)code;
+        rec.nr_entry    = nr_lines;
+
+        /*
+         * on disk source line info layout:
+         * uint64_t : addr
+         * int      : line number
+         * int      : column discriminator
+         * file[]   : source file name
+         * padding  : pad to multiple of 8 bytes
+         */
+        size += nr_lines * sizeof(struct debug_entry);
+        size += flen * nr_lines;
+        /*
+         * pad to 8 bytes
+         */
+        padding_count = PADDING_8ALIGNED(size);
+
+        rec.p.total_size = size + padding_count;
+
+        /*
+         * If JVM is multi-threaded, nultiple concurrent calls to agent
+         * may be possible, so protect file writes
+         */
+        flockfile(fp);
+
+        sret = fwrite_unlocked(&rec, sizeof(rec), 1, fp);
+        if (sret != 1)
+                goto error;
+
+        for (i = 0; i < nr_lines; i++) {
+
+                addr = (uint64_t)li[i].pc;
+                len  = sizeof(addr);
+                sret = fwrite_unlocked(&addr, len, 1, fp);
+                if (sret != 1)
+                        goto error;
+
+                len  = sizeof(li[0].line_number);
+                sret = fwrite_unlocked(&li[i].line_number, len, 1, fp);
+                if (sret != 1)
+                        goto error;
+
+                len  = sizeof(li[0].discrim);
+                sret = fwrite_unlocked(&li[i].discrim, len, 1, fp);
+                if (sret != 1)
+                        goto error;
+
+                sret = fwrite_unlocked(fn, flen, 1, fp);
+                if (sret != 1)
+                        goto error;
+        }
+        if (padding_count)
+                sret = fwrite_unlocked(pad_bytes, padding_count, 1, fp);
+                if (sret != 1)
+                        goto error;
+
+        funlockfile(fp);
+        return 0;
+error:
+        funlockfile(fp);
+        return -1;
+}
diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h
new file mode 100644
index 000000000000..bedf5d0ba9ff
--- /dev/null
+++ b/tools/perf/jvmti/jvmti_agent.h
@@ -0,0 +1,36 @@
+#ifndef __JVMTI_AGENT_H__
+#define __JVMTI_AGENT_H__
+
+#include <sys/types.h>
+#include <stdint.h>
+#include <jvmti.h>
+
+#define __unused __attribute__((unused))
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+typedef struct {
+        unsigned long   pc;
+        int             line_number;
+        int             discrim; /* discriminator -- 0 for now */
+} jvmti_line_info_t;
+
+void *jvmti_open(void);
+int   jvmti_close(void *agent);
+int   jvmti_write_code(void *agent, char const *symbol_name,
+                       uint64_t vma, void const *code,
+                       const unsigned int code_size);
+
+int   jvmti_write_debug_info(void *agent,
+                             uint64_t code,
+                             const char *file,
+                             jvmti_line_info_t *li,
+                             int nr_lines);
+
+#if defined(__cplusplus)
+}
+
+#endif
+#endif /* __JVMTI_H__ */
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
new file mode 100644
index 000000000000..ac12e4b91a92
--- /dev/null
+++ b/tools/perf/jvmti/libjvmti.c
@@ -0,0 +1,304 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <err.h>
+#include <jvmti.h>
+#include <jvmticmlr.h>
+#include <limits.h>
+
+#include "jvmti_agent.h"
+
+static int has_line_numbers;
+void *jvmti_agent;
+
+static jvmtiError
+do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci,
+                    jvmti_line_info_t *tab, jint *nr)
+{
+        jint i, lines = 0;
+        jint nr_lines = 0;
+        jvmtiLineNumberEntry *loc_tab = NULL;
+        jvmtiError ret;
+
+        ret = (*jvmti)->GetLineNumberTable(jvmti, m, &nr_lines, &loc_tab);
+        if (ret != JVMTI_ERROR_NONE)
+                return ret;
+
+        for (i = 0; i < nr_lines; i++) {
+                if (loc_tab[i].start_location < bci) {
+                        tab[lines].pc = (unsigned long)pc;
+                        tab[lines].line_number = loc_tab[i].line_number;
+                        tab[lines].discrim = 0; /* not yet used */
+                        lines++;
+                } else {
+                        break;
+                }
+        }
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)loc_tab);
+        *nr = lines;
+        return JVMTI_ERROR_NONE;
+}
+
+static jvmtiError
+get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t **tab, int *nr_lines)
+{
+        const jvmtiCompiledMethodLoadRecordHeader *hdr;
+        jvmtiCompiledMethodLoadInlineRecord *rec;
+        jvmtiLineNumberEntry *lne = NULL;
+        PCStackInfo *c;
+        jint nr, ret;
+        int nr_total = 0;
+        int i, lines_total = 0;
+
+        if (!(tab && nr_lines))
+                return JVMTI_ERROR_NULL_POINTER;
+
+        /*
+         * Phase 1 -- get the number of lines necessary
+         */
+        for (hdr = compile_info; hdr != NULL; hdr = hdr->next) {
+                if (hdr->kind == JVMTI_CMLR_INLINE_INFO) {
+                        rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr;
+                        for (i = 0; i < rec->numpcs; i++) {
+                                c = rec->pcinfo + i;
+                                nr = 0;
+                                /*
+                                 * unfortunately, need a tab to get the number of lines!
+                                 */
+                                ret = (*jvmti)->GetLineNumberTable(jvmti, c->methods[0], &nr, &lne);
+                                if (ret == JVMTI_ERROR_NONE) {
+                                        /* free what was allocated for nothing */
+                                        (*jvmti)->Deallocate(jvmti, (unsigned char *)lne);
+                                        nr_total += (int)nr;
+                                }
+                        }
+                }
+        }
+
+        if (nr_total == 0)
+                return JVMTI_ERROR_NOT_FOUND;
+
+        /*
+         * Phase 2 -- allocate big enough line table
+         */
+        *tab = malloc(nr_total * sizeof(**tab));
+        if (!*tab)
+                return JVMTI_ERROR_OUT_OF_MEMORY;
+
+        for (hdr = compile_info; hdr != NULL; hdr = hdr->next) {
+                if (hdr->kind == JVMTI_CMLR_INLINE_INFO) {
+                        rec = (jvmtiCompiledMethodLoadInlineRecord *)hdr;
+                        for (i = 0; i < rec->numpcs; i++) {
+                                c = rec->pcinfo + i;
+                                nr = 0;
+                                ret = do_get_line_numbers(jvmti, c->pc,
+                                                          c->methods[0],
+                                                          c->bcis[0],
+                                                          *tab + lines_total,
+                                                          &nr);
+                                if (ret == JVMTI_ERROR_NONE)
+                                        lines_total += nr;
+                        }
+                }
+        }
+        *nr_lines = lines_total;
+        return JVMTI_ERROR_NONE;
+}
+
+static void JNICALL
+compiled_method_load_cb(jvmtiEnv *jvmti,
+                        jmethodID method,
+                        jint code_size,
+                        void const *code_addr,
+                        jint map_length,
+                        jvmtiAddrLocationMap const *map,
+                        const void *compile_info)
+{
+        jvmti_line_info_t *line_tab = NULL;
+        jclass decl_class;
+        char *class_sign = NULL;
+        char *func_name = NULL;
+        char *func_sign = NULL;
+        char *file_name= NULL;
+        char fn[PATH_MAX];
+        uint64_t addr = (uint64_t)(uintptr_t)code_addr;
+        jvmtiError ret;
+        int nr_lines = 0; /* in line_tab[] */
+        size_t len;
+
+        ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method,
+                                                &decl_class);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: cannot get declaring class");
+                return;
+        }
+
+        if (has_line_numbers && map && map_length) {
+                ret = get_line_numbers(jvmti, compile_info, &line_tab, &nr_lines);
+                if (ret != JVMTI_ERROR_NONE) {
+                        warnx("jvmti: cannot get line table for method");
+                        nr_lines = 0;
+                }
+        }
+
+        ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: cannot get source filename ret=%d", ret);
+                goto error;
+        }
+
+        ret = (*jvmti)->GetClassSignature(jvmti, decl_class,
+                                          &class_sign, NULL);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: getclassignature failed");
+                goto error;
+        }
+
+        ret = (*jvmti)->GetMethodName(jvmti, method, &func_name,
+                                      &func_sign, NULL);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: failed getmethodname");
+                goto error;
+        }
+
+        /*
+         * Assume path name is class hierarchy, this is a common practice with Java programs
+         */
+        if (*class_sign == 'L') {
+                int j, i = 0;
+                char *p = strrchr(class_sign, '/');
+                if (p) {
+                        /* drop the 'L' prefix and copy up to the final '/' */
+                        for (i = 0; i < (p - class_sign); i++)
+                                fn[i] = class_sign[i+1];
+                }
+                /*
+                 * append file name, we use loops and not string ops to avoid modifying
+                 * class_sign which is used later for the symbol name
+                 */
+                for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++)
+                        fn[i] = file_name[j];
+                fn[i] = '\0';
+        } else {
+                /* fallback case */
+                strcpy(fn, file_name);
+        }
+        /*
+         * write source line info record if we have it
+         */
+        if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines))
+                warnx("jvmti: write_debug_info() failed");
+
+        len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2;
+        {
+                char str[len];
+                snprintf(str, len, "%s%s%s", class_sign, func_name, func_sign);
+
+                if (jvmti_write_code(jvmti_agent, str, addr, code_addr, code_size))
+                        warnx("jvmti: write_code() failed");
+        }
+error:
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)func_name);
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)func_sign);
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign);
+        (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name);
+        free(line_tab);
+}
+
+static void JNICALL
+code_generated_cb(jvmtiEnv *jvmti,
+                  char const *name,
+                  void const *code_addr,
+                  jint code_size)
+{
+        uint64_t addr = (uint64_t)(unsigned long)code_addr;
+        int ret;
+
+        ret = jvmti_write_code(jvmti_agent, name, addr, code_addr, code_size);
+        if (ret)
+                warnx("jvmti: write_code() failed for code_generated");
+}
+
+JNIEXPORT jint JNICALL
+Agent_OnLoad(JavaVM *jvm, char *options, void *reserved __unused)
+{
+        jvmtiEventCallbacks cb;
+        jvmtiCapabilities caps1;
+        jvmtiJlocationFormat format;
+        jvmtiEnv *jvmti = NULL;
+        jint ret;
+
+        jvmti_agent = jvmti_open();
+        if (!jvmti_agent) {
+                warnx("jvmti: open_agent failed");
+                return -1;
+        }
+
+        /*
+         * Request a JVMTI interface version 1 environment
+         */
+        ret = (*jvm)->GetEnv(jvm, (void *)&jvmti, JVMTI_VERSION_1);
+        if (ret != JNI_OK) {
+                warnx("jvmti: jvmti version 1 not supported");
+                return -1;
+        }
+
+        /*
+         * acquire method_load capability, we require it
+         * request line numbers (optional)
+         */
+        memset(&caps1, 0, sizeof(caps1));
+        caps1.can_generate_compiled_method_load_events = 1;
+
+        ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: acquire compiled_method capability failed");
+                return -1;
+        }
+        ret = (*jvmti)->GetJLocationFormat(jvmti, &format);
+        if (ret == JVMTI_ERROR_NONE && format == JVMTI_JLOCATION_JVMBCI) {
+                memset(&caps1, 0, sizeof(caps1));
+                caps1.can_get_line_numbers = 1;
+                caps1.can_get_source_file_name = 1;
+                ret = (*jvmti)->AddCapabilities(jvmti, &caps1);
+                if (ret == JVMTI_ERROR_NONE)
+                        has_line_numbers = 1;
+        }
+
+        memset(&cb, 0, sizeof(cb));
+
+        cb.CompiledMethodLoad   = compiled_method_load_cb;
+        cb.DynamicCodeGenerated = code_generated_cb;
+
+        ret = (*jvmti)->SetEventCallbacks(jvmti, &cb, sizeof(cb));
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: cannot set event callbacks");
+                return -1;
+        }
+
+        ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
+                        JVMTI_EVENT_COMPILED_METHOD_LOAD, NULL);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: setnotification failed for method_load");
+                return -1;
+        }
+
+        ret = (*jvmti)->SetEventNotificationMode(jvmti, JVMTI_ENABLE,
+                        JVMTI_EVENT_DYNAMIC_CODE_GENERATED, NULL);
+        if (ret != JVMTI_ERROR_NONE) {
+                warnx("jvmti: setnotification failed on code_generated");
+                return -1;
+        }
+        return 0;
+}
+
+JNIEXPORT void JNICALL
+Agent_OnUnload(JavaVM *jvm __unused)
+{
+        int ret;
+
+        ret = jvmti_close(jvmti_agent);
+        if (ret)
+                errx(1, "Error: op_close_agent()");
+}
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index a929618b8eb6..aaee0a782747 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -454,11 +454,12 @@ static void handle_internal_command(int argc, const char **argv)
 
 static void execv_dashed_external(const char **argv)
 {
-        struct strbuf cmd = STRBUF_INIT;
+        char *cmd;
         const char *tmp;
         int status;
 
-        strbuf_addf(&cmd, "perf-%s", argv[0]);
+        if (asprintf(&cmd, "perf-%s", argv[0]) < 0)
+                goto do_die;
 
         /*
          * argv[0] must be the perf command, but the argv array
@@ -467,7 +468,7 @@ static void execv_dashed_external(const char **argv)
          * restore it on error.
          */
         tmp = argv[0];
-        argv[0] = cmd.buf;
+        argv[0] = cmd;
 
         /*
          * if we fail because the command is not found, it is
@@ -475,15 +476,16 @@ static void execv_dashed_external(const char **argv)
          */
         status = run_command_v_opt(argv, 0);
         if (status != -ERR_RUN_COMMAND_EXEC) {
-                if (IS_RUN_COMMAND_ERR(status))
+                if (IS_RUN_COMMAND_ERR(status)) {
+do_die:
                         die("unable to run '%s'", argv[0]);
+                }
                 exit(-status);
         }
         errno = ENOENT; /* as if we called execvp */
 
         argv[0] = tmp;
-
-        strbuf_release(&cmd);
+        zfree(&cmd);
 }
 
 static int run_argv(int *argcp, const char ***argv)
@@ -546,6 +548,8 @@ int main(int argc, const char **argv)
 
         srandom(time(NULL));
 
+        perf_config(perf_default_config, NULL);
+
         /* get debugfs/tracefs mount point from /proc/mounts */
         tracing_path_mount();
 
@@ -613,6 +617,8 @@ int main(int argc, const char **argv)
          */
         pthread__block_sigwinch();
 
+        perf_debug_setup();
+
         while (1) {
                 static int done_help;
                 int was_alias = run_argv(&argc, &argv);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 90129accffbe..5381a01c0610 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -58,6 +58,8 @@ struct record_opts {
         bool         full_auxtrace;
         bool         auxtrace_snapshot_mode;
         bool         record_switch_events;
+        bool         all_kernel;
+        bool         all_user;
         unsigned int freq;
         unsigned int mmap_pages;
         unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index 15c8400240fd..1d95009592eb 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -71,7 +71,10 @@ try:
 except:
         if not audit_package_warned:
                 audit_package_warned = True
-                print "Install the audit-libs-python package to get syscall names"
+                print "Install the audit-libs-python package to get syscall names.\n" \
+                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
+                    "\n  # yum install audit-libs-python (Fedora)" \
+                    "\n  etc.\n"
 
 def syscall_name(id):
         try:
diff --git a/tools/perf/tests/.gitignore b/tools/perf/tests/.gitignore
index bf016c439fbd..8cc30e731c73 100644
--- a/tools/perf/tests/.gitignore
+++ b/tools/perf/tests/.gitignore
@@ -1,3 +1,4 @@
 llvm-src-base.c
 llvm-src-kbuild.c
 llvm-src-prologue.c
+llvm-src-relocation.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 614899b88b37..1ba628ed049a 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -31,7 +31,7 @@ perf-y += sample-parsing.o
 perf-y += parse-no-sample-id-all.o
 perf-y += kmod-path.o
 perf-y += thread-map.o
-perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o
+perf-y += llvm.o llvm-src-base.o llvm-src-kbuild.o llvm-src-prologue.o llvm-src-relocation.o
 perf-y += bpf.o
 perf-y += topology.o
 perf-y += cpumap.o
@@ -59,6 +59,13 @@ $(OUTPUT)tests/llvm-src-prologue.c: tests/bpf-script-test-prologue.c tests/Build
         $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
         $(Q)echo ';' >> $@
 
+$(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/Build
+        $(call rule_mkdir)
+        $(Q)echo '#include <tests/llvm.h>' > $@
+        $(Q)echo 'const char test_llvm__bpf_test_relocation[] =' >> $@
+        $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
+        $(Q)echo ';' >> $@
+
 ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index fb80c9eb6a95..e7664fe3bd33 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -29,14 +29,59 @@
 
 static int fd1;
 static int fd2;
+static int fd3;
 static int overflows;
+static int overflows_2;
+
+volatile long the_var;
+
+
+/*
+ * Use ASM to ensure watchpoint and breakpoint can be triggered
+ * at one instruction.
+ */
+#if defined (__x86_64__)
+extern void __test_function(volatile long *ptr);
+asm (
+        ".globl __test_function\n"
+        "__test_function:\n"
+        "incq (%rdi)\n"
+        "ret\n");
+#elif defined (__aarch64__)
+extern void __test_function(volatile long *ptr);
+asm (
+        ".globl __test_function\n"
+        "__test_function:\n"
+        "str x30, [x0]\n"
+        "ret\n");
+
+#else
+static void __test_function(volatile long *ptr)
+{
+        *ptr = 0x1234;
+}
+#endif
 
 __attribute__ ((noinline))
 static int test_function(void)
 {
+        __test_function(&the_var);
+        the_var++;
         return time(NULL);
 }
 
+static void sig_handler_2(int signum __maybe_unused,
+                          siginfo_t *oh __maybe_unused,
+                          void *uc __maybe_unused)
+{
+        overflows_2++;
+        if (overflows_2 > 10) {
+                ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
+                ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+                ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
+        }
+}
+
 static void sig_handler(int signum __maybe_unused,
                         siginfo_t *oh __maybe_unused,
                         void *uc __maybe_unused)
@@ -54,10 +99,11 @@ static void sig_handler(int signum __maybe_unused,
                  */
                 ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
                 ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+                ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
         }
 }
 
-static int bp_event(void *fn, int setup_signal)
+static int __event(bool is_x, void *addr, int sig)
 {
         struct perf_event_attr pe;
         int fd;
@@ -67,8 +113,8 @@ static int bp_event(void *fn, int setup_signal)
         pe.size = sizeof(struct perf_event_attr);
 
         pe.config = 0;
-        pe.bp_type = HW_BREAKPOINT_X;
-        pe.bp_addr = (unsigned long) fn;
+        pe.bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W;
+        pe.bp_addr = (unsigned long) addr;
         pe.bp_len = sizeof(long);
 
         pe.sample_period = 1;
@@ -86,17 +132,25 @@ static int bp_event(void *fn, int setup_signal)
                 return TEST_FAIL;
         }
 
-        if (setup_signal) {
-                fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
-                fcntl(fd, F_SETSIG, SIGIO);
-                fcntl(fd, F_SETOWN, getpid());
-        }
+        fcntl(fd, F_SETFL, O_RDWR|O_NONBLOCK|O_ASYNC);
+        fcntl(fd, F_SETSIG, sig);
+        fcntl(fd, F_SETOWN, getpid());
 
         ioctl(fd, PERF_EVENT_IOC_RESET, 0);
 
         return fd;
 }
 
+static int bp_event(void *addr, int sig)
+{
+        return __event(true, addr, sig);
+}
+
+static int wp_event(void *addr, int sig)
+{
+        return __event(false, addr, sig);
+}
+
 static long long bp_count(int fd)
 {
         long long count;
@@ -114,7 +168,7 @@ static long long bp_count(int fd)
 int test__bp_signal(int subtest __maybe_unused)
 {
         struct sigaction sa;
-        long long count1, count2;
+        long long count1, count2, count3;
 
         /* setup SIGIO signal handler */
         memset(&sa, 0, sizeof(struct sigaction));
@@ -126,21 +180,52 @@ int test__bp_signal(int subtest __maybe_unused)
                 return TEST_FAIL;
         }
 
+        sa.sa_sigaction = (void *) sig_handler_2;
+        if (sigaction(SIGUSR1, &sa, NULL) < 0) {
+                pr_debug("failed setting up signal handler 2\n");
+                return TEST_FAIL;
+        }
+
         /*
          * We create following events:
          *
-         * fd1 - breakpoint event on test_function with SIGIO
+         * fd1 - breakpoint event on __test_function with SIGIO
          *       signal configured. We should get signal
          *       notification each time the breakpoint is hit
          *
-         * fd2 - breakpoint event on sig_handler without SIGIO
+         * fd2 - breakpoint event on sig_handler with SIGUSR1
+         *       configured. We should get SIGUSR1 each time when
+         *       breakpoint is hit
+         *
+         * fd3 - watchpoint event on __test_function with SIGIO
          *       configured.
          *
          * Following processing should happen:
-         *   - execute test_function
-         *   - fd1 event breakpoint hit -> count1 == 1
-         *   - SIGIO is delivered       -> overflows == 1
-         *   - fd2 event breakpoint hit -> count2 == 1
+         *   Exec:               Action:                       Result:
+         *   incq (%rdi)       - fd1 event breakpoint hit   -> count1 == 1
+         *                     - SIGIO is delivered
+         *   sig_handler       - fd2 event breakpoint hit   -> count2 == 1
+         *                     - SIGUSR1 is delivered
+         *   sig_handler_2                                  -> overflows_2 == 1  (nested signal)
+         *   sys_rt_sigreturn  - return from sig_handler_2
+         *   overflows++                                    -> overflows = 1
+         *   sys_rt_sigreturn  - return from sig_handler
+         *   incq (%rdi)       - fd3 event watchpoint hit   -> count3 == 1       (wp and bp in one insn)
+         *                     - SIGIO is delivered
+         *   sig_handler       - fd2 event breakpoint hit   -> count2 == 2
+         *                     - SIGUSR1 is delivered
+         *   sig_handler_2                                  -> overflows_2 == 2  (nested signal)
+         *   sys_rt_sigreturn  - return from sig_handler_2
+         *   overflows++                                    -> overflows = 2
+         *   sys_rt_sigreturn  - return from sig_handler
+         *   the_var++         - fd3 event watchpoint hit   -> count3 == 2       (standalone watchpoint)
+         *                     - SIGIO is delivered
+         *   sig_handler       - fd2 event breakpoint hit   -> count2 == 3
+         *                     - SIGUSR1 is delivered
+         *   sig_handler_2                                  -> overflows_2 == 3  (nested signal)
+         *   sys_rt_sigreturn  - return from sig_handler_2
+         *   overflows++                                    -> overflows == 3
+         *   sys_rt_sigreturn  - return from sig_handler
          *
          * The test case check following error conditions:
          * - we get stuck in signal handler because of debug
@@ -152,11 +237,13 @@ int test__bp_signal(int subtest __maybe_unused)
          *
          */
 
-        fd1 = bp_event(test_function, 1);
-        fd2 = bp_event(sig_handler, 0);
+        fd1 = bp_event(__test_function, SIGIO);
+        fd2 = bp_event(sig_handler, SIGUSR1);
+        fd3 = wp_event((void *)&the_var, SIGIO);
 
         ioctl(fd1, PERF_EVENT_IOC_ENABLE, 0);
         ioctl(fd2, PERF_EVENT_IOC_ENABLE, 0);
+        ioctl(fd3, PERF_EVENT_IOC_ENABLE, 0);
 
         /*
          * Kick off the test by trigering 'fd1'
@@ -166,15 +253,18 @@ int test__bp_signal(int subtest __maybe_unused)
 
         ioctl(fd1, PERF_EVENT_IOC_DISABLE, 0);
         ioctl(fd2, PERF_EVENT_IOC_DISABLE, 0);
+        ioctl(fd3, PERF_EVENT_IOC_DISABLE, 0);
 
         count1 = bp_count(fd1);
         count2 = bp_count(fd2);
+        count3 = bp_count(fd3);
 
         close(fd1);
         close(fd2);
+        close(fd3);
 
-        pr_debug("count1 %lld, count2 %lld, overflow %d\n",
-                 count1, count2, overflows);
+        pr_debug("count1 %lld, count2 %lld, count3 %lld, overflow %d, overflows_2 %d\n",
+                 count1, count2, count3, overflows, overflows_2);
 
         if (count1 != 1) {
                 if (count1 == 11)
@@ -183,12 +273,18 @@ int test__bp_signal(int subtest __maybe_unused)
                         pr_debug("failed: wrong count for bp1%lld\n", count1);
         }
 
-        if (overflows != 1)
+        if (overflows != 3)
                 pr_debug("failed: wrong overflow hit\n");
 
-        if (count2 != 1)
+        if (overflows_2 != 3)
+                pr_debug("failed: wrong overflow_2 hit\n");
+
+        if (count2 != 3)
                 pr_debug("failed: wrong count for bp2\n");
 
-        return count1 == 1 && overflows == 1 && count2 == 1 ?
+        if (count3 != 2)
+                pr_debug("failed: wrong count for bp3\n");
+
+        return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
                 TEST_OK : TEST_FAIL;
 }
diff --git a/tools/perf/tests/bpf-script-test-relocation.c b/tools/perf/tests/bpf-script-test-relocation.c
new file mode 100644
index 000000000000..93af77421816
--- /dev/null
+++ b/tools/perf/tests/bpf-script-test-relocation.c
@@ -0,0 +1,50 @@
+/*
+ * bpf-script-test-relocation.c
+ * Test BPF loader checking relocation
+ */
+#ifndef LINUX_VERSION_CODE
+# error Need LINUX_VERSION_CODE
+# error Example: for 4.2 kernel, put 'clang-opt="-DLINUX_VERSION_CODE=0x40200" into llvm section of ~/.perfconfig'
+#endif
+#define BPF_ANY 0
+#define BPF_MAP_TYPE_ARRAY 2
+#define BPF_FUNC_map_lookup_elem 1
+#define BPF_FUNC_map_update_elem 2
+
+static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+        (void *) BPF_FUNC_map_lookup_elem;
+static void *(*bpf_map_update_elem)(void *map, void *key, void *value, int flags) =
+        (void *) BPF_FUNC_map_update_elem;
+
+struct bpf_map_def {
+        unsigned int type;
+        unsigned int key_size;
+        unsigned int value_size;
+        unsigned int max_entries;
+};
+
+#define SEC(NAME) __attribute__((section(NAME), used))
+struct bpf_map_def SEC("maps") my_table = {
+        .type = BPF_MAP_TYPE_ARRAY,
+        .key_size = sizeof(int),
+        .value_size = sizeof(int),
+        .max_entries = 1,
+};
+
+int this_is_a_global_val;
+
+SEC("func=sys_write")
+int bpf_func__sys_write(void *ctx)
+{
+        int key = 0;
+        int value = 0;
+
+        /*
+         * Incorrect relocation. Should not allow this program be
+         * loaded into kernel.
+         */
+        bpf_map_update_elem(&this_is_a_global_val, &key, &value, 0);
+        return 0;
+}
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 33689a0cf821..199501c71e27 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -1,7 +1,11 @@
 #include <stdio.h>
 #include <sys/epoll.h>
+#include <util/util.h>
 #include <util/bpf-loader.h>
 #include <util/evlist.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
@@ -71,6 +75,15 @@ static struct {
                 (NR_ITERS + 1) / 4,
         },
 #endif
+        {
+                LLVM_TESTCASE_BPF_RELOCATION,
+                "Test BPF relocation checker",
+                "[bpf_relocation_test]",
+                "fix 'perf test LLVM' first",
+                "libbpf error when dealing with relocation",
+                NULL,
+                0,
+        },
 };
 
 static int do_test(struct bpf_object *obj, int (*func)(void),
@@ -99,7 +112,7 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
         parse_evlist.error = &parse_error;
         INIT_LIST_HEAD(&parse_evlist.list);
 
-        err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj);
+        err = parse_events_load_bpf_obj(&parse_evlist, &parse_evlist.list, obj, NULL);
         if (err || list_empty(&parse_evlist.list)) {
                 pr_debug("Failed to add events selected by BPF\n");
                 return TEST_FAIL;
@@ -190,7 +203,7 @@ static int __test__bpf(int idx)
 
         ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
                                        bpf_testcase_table[idx].prog_id,
-                                       true);
+                                       true, NULL);
         if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
                 pr_debug("Unable to get BPF object, %s\n",
                          bpf_testcase_table[idx].msg_compile_fail);
@@ -202,14 +215,21 @@ static int __test__bpf(int idx)
 
         obj = prepare_bpf(obj_buf, obj_buf_sz,
                           bpf_testcase_table[idx].name);
-        if (!obj) {
+        if ((!!bpf_testcase_table[idx].target_func) != (!!obj)) {
+                if (!obj)
+                        pr_debug("Fail to load BPF object: %s\n",
+                                 bpf_testcase_table[idx].msg_load_fail);
+                else
+                        pr_debug("Success unexpectedly: %s\n",
+                                 bpf_testcase_table[idx].msg_load_fail);
                 ret = TEST_FAIL;
                 goto out;
         }
 
-        ret = do_test(obj,
-                      bpf_testcase_table[idx].target_func,
-                      bpf_testcase_table[idx].expect_result);
+        if (obj)
+                ret = do_test(obj,
+                              bpf_testcase_table[idx].target_func,
+                              bpf_testcase_table[idx].expect_result);
 out:
         bpf__clear();
         return ret;
@@ -227,6 +247,36 @@ const char *test__bpf_subtest_get_desc(int i)
         return bpf_testcase_table[i].desc;
 }
 
+static int check_env(void)
+{
+        int err;
+        unsigned int kver_int;
+        char license[] = "GPL";
+
+        struct bpf_insn insns[] = {
+                BPF_MOV64_IMM(BPF_REG_0, 1),
+                BPF_EXIT_INSN(),
+        };
+
+        err = fetch_kernel_version(&kver_int, NULL, 0);
+        if (err) {
+                pr_debug("Unable to get kernel version\n");
+                return err;
+        }
+
+        err = bpf_load_program(BPF_PROG_TYPE_KPROBE, insns,
+                               sizeof(insns) / sizeof(insns[0]),
+                               license, kver_int, NULL, 0);
+        if (err < 0) {
+                pr_err("Missing basic BPF support, skip this test: %s\n",
+                       strerror(errno));
+                return err;
+        }
+        close(err);
+
+        return 0;
+}
+
 int test__bpf(int i)
 {
         int err;
@@ -239,6 +289,9 @@ int test__bpf(int i)
                 return TEST_SKIP;
         }
 
+        if (check_env())
+                return TEST_SKIP;
+
         err = __test__bpf(i);
         return err;
 }
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 313a48c6b2bc..afc9ad0a0515 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -439,7 +439,7 @@ static int do_test_code_reading(bool try_kcore)
                 .mmap_pages          = UINT_MAX,
                 .user_freq           = UINT_MAX,
                 .user_interval       = ULLONG_MAX,
-                .freq                = 4000,
+                .freq                = 500,
                 .target              = {
                         .uses_mmap   = true,
                 },
@@ -559,7 +559,13 @@ static int do_test_code_reading(bool try_kcore)
                                 evlist = NULL;
                                 continue;
                         }
-                        pr_debug("perf_evlist__open failed\n");
+
+                        if (verbose) {
+                                char errbuf[512];
+                                perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
+                                pr_debug("perf_evlist__open() failed!\n%s\n", errbuf);
+                        }
+
                         goto out_put;
                 }
                 break;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 5e6a86e50fb9..ecf136c385d5 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -191,7 +191,7 @@ static int do_test(struct hists *hists, struct result *expected, size_t nr_expec
          * function since TEST_ASSERT_VAL() returns in case of failure.
          */
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(hists_to_evsel(hists), NULL);
 
         if (verbose > 2) {
                 pr_info("use callchain: %d, cumulate callchain: %d\n",
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 351a42463444..34b945a55d4d 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -145,7 +145,7 @@ int test__hists_filter(int subtest __maybe_unused)
                 struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
-                hists__output_resort(hists, NULL);
+                perf_evsel__output_resort(evsel, NULL);
 
                 if (verbose > 2) {
                         pr_info("Normal histogram\n");
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index b231265148d8..23cce67c7e48 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -156,7 +156,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -256,7 +256,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -310,7 +310,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -388,7 +388,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -491,7 +491,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists, NULL);
+        perf_evsel__output_resort(evsel, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 06f45c1d4256..cff564fb4b66 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -6,12 +6,6 @@
 #include "tests.h"
 #include "debug.h"
 
-static int perf_config_cb(const char *var, const char *val,
-                          void *arg __maybe_unused)
-{
-        return perf_default_config(var, val, arg);
-}
-
 #ifdef HAVE_LIBBPF_SUPPORT
 static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 {
@@ -35,6 +29,7 @@ static int test__bpf_parsing(void *obj_buf __maybe_unused,
 static struct {
         const char *source;
         const char *desc;
+        bool should_load_fail;
 } bpf_source_table[__LLVM_TESTCASE_MAX] = {
         [LLVM_TESTCASE_BASE] = {
                 .source = test_llvm__bpf_base_prog,
@@ -48,14 +43,19 @@ static struct {
                 .source = test_llvm__bpf_test_prologue_prog,
                 .desc = "Compile source for BPF prologue generation test",
         },
+        [LLVM_TESTCASE_BPF_RELOCATION] = {
+                .source = test_llvm__bpf_test_relocation,
+                .desc = "Compile source for BPF relocation test",
+                .should_load_fail = true,
+        },
 };
 
-
 int
 test_llvm__fetch_bpf_obj(void **p_obj_buf,
                          size_t *p_obj_buf_sz,
                          enum test_llvm__testcase idx,
-                         bool force)
+                         bool force,
+                         bool *should_load_fail)
 {
         const char *source;
         const char *desc;
@@ -68,8 +68,8 @@ test_llvm__fetch_bpf_obj(void **p_obj_buf,
 
         source = bpf_source_table[idx].source;
         desc = bpf_source_table[idx].desc;
-
-        perf_config(perf_config_cb, NULL);
+        if (should_load_fail)
+                *should_load_fail = bpf_source_table[idx].should_load_fail;
 
         /*
          * Skip this test if user's .perfconfig doesn't set [llvm] section
@@ -136,14 +136,15 @@ int test__llvm(int subtest)
         int ret;
         void *obj_buf = NULL;
         size_t obj_buf_sz = 0;
+        bool should_load_fail = false;
 
         if ((subtest < 0) || (subtest >= __LLVM_TESTCASE_MAX))
                 return TEST_FAIL;
 
         ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
-                                       subtest, false);
+                                       subtest, false, &should_load_fail);
 
-        if (ret == TEST_OK) {
+        if (ret == TEST_OK && !should_load_fail) {
                 ret = test__bpf_parsing(obj_buf, obj_buf_sz);
                 if (ret != TEST_OK) {
                         pr_debug("Failed to parse test case '%s'\n",
diff --git a/tools/perf/tests/llvm.h b/tools/perf/tests/llvm.h
index 5150b4d6ef50..0eaa604be99d 100644
--- a/tools/perf/tests/llvm.h
+++ b/tools/perf/tests/llvm.h
@@ -7,14 +7,17 @@
 extern const char test_llvm__bpf_base_prog[];
 extern const char test_llvm__bpf_test_kbuild_prog[];
 extern const char test_llvm__bpf_test_prologue_prog[];
+extern const char test_llvm__bpf_test_relocation[];
 
 enum test_llvm__testcase {
         LLVM_TESTCASE_BASE,
         LLVM_TESTCASE_KBUILD,
         LLVM_TESTCASE_BPF_PROLOGUE,
+        LLVM_TESTCASE_BPF_RELOCATION,
         __LLVM_TESTCASE_MAX,
 };
 
 int test_llvm__fetch_bpf_obj(void **p_obj_buf, size_t *p_obj_buf_sz,
-                             enum test_llvm__testcase index, bool force);
+                             enum test_llvm__testcase index, bool force,
+                             bool *should_load_fail);
 #endif
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index f918015512af..cac15d93aea6 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -15,6 +15,7 @@ else
 PERF := .
 PERF_O := $(PERF)
 O_OPT :=
+FULL_O := $(shell readlink -f $(PERF_O) || echo $(PERF_O))
 
 ifneq ($(O),)
   FULL_O := $(shell readlink -f $(O) || echo $(O))
@@ -79,6 +80,7 @@ make_no_libaudit    := NO_LIBAUDIT=1
 make_no_libbionic   := NO_LIBBIONIC=1
 make_no_auxtrace    := NO_AUXTRACE=1
 make_no_libbpf      := NO_LIBBPF=1
+make_no_libcrypto   := NO_LIBCRYPTO=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -102,6 +104,7 @@ make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
 make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1
+make_minimal        += NO_LIBCRYPTO=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -110,6 +113,9 @@ run := make_pure
 # disable features detection
 ifeq ($(MK),Makefile)
 run += make_clean_all
+MAKE_F := $(MAKE)
+else
+MAKE_F := $(MAKE) -f $(MK)
 endif
 run += make_python_perf_so
 run += make_debug
@@ -260,6 +266,8 @@ run := $(shell shuf -e $(run))
 run_O := $(shell shuf -e $(run_O))
 endif
 
+max_width := $(shell echo $(run_O) | sed 's/ /\n/g' | wc -L)
+
 ifdef DEBUG
 d := $(info run   $(run))
 d := $(info run_O $(run_O))
@@ -267,13 +275,13 @@ endif
 
 MAKEFLAGS := --no-print-directory
 
-clean := @(cd $(PERF); make -s -f $(MK) $(O_OPT) clean >/dev/null)
+clean := @(cd $(PERF); $(MAKE_F) -s $(O_OPT) clean >/dev/null)
 
 $(run):
         $(call clean)
         @TMP_DEST=$$(mktemp -d); \
-        cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST $($@)"; \
-        echo "- $@: $$cmd" && echo $$cmd > $@ && \
+        cmd="cd $(PERF) && $(MAKE_F) $($@) $(PARALLEL_OPT) $(O_OPT) DESTDIR=$$TMP_DEST"; \
+        printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1; \
         echo "  test: $(call test,$@)" >> $@ 2>&1; \
         $(call test,$@) && \
@@ -283,8 +291,8 @@ $(run_O):
         $(call clean)
         @TMP_O=$$(mktemp -d); \
         TMP_DEST=$$(mktemp -d); \
-        cmd="cd $(PERF) && make -f $(MK) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST $($(patsubst %_O,%,$@))"; \
-        echo "- $@: $$cmd" && echo $$cmd > $@ && \
+        cmd="cd $(PERF) && $(MAKE_F) $($(patsubst %_O,%,$@)) $(PARALLEL_OPT) O=$$TMP_O DESTDIR=$$TMP_DEST"; \
+        printf "%*.*s: %s\n" $(max_width) $(max_width) "$@" "$$cmd" && echo $$cmd > $@ && \
         ( eval $$cmd ) >> $@ 2>&1 && \
         echo "  test: $(call test_O,$@)" >> $@ 2>&1; \
         $(call test_O,$@) && \
@@ -313,11 +321,43 @@ make_kernelsrc_tools:
         (make -C ../../tools $(PARALLEL_OPT) $(K_O_OPT) perf) > $@ 2>&1 && \
         test -x $(KERNEL_O)/tools/perf/perf && rm -f $@ || (cat $@ ; false)
 
+FEATURES_DUMP_FILE := $(FULL_O)/BUILD_TEST_FEATURE_DUMP
+FEATURES_DUMP_FILE_STATIC := $(FULL_O)/BUILD_TEST_FEATURE_DUMP_STATIC
+
 all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
         @echo OK
+        @rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
 
 out: $(run_O)
         @echo OK
+        @rm -f $(FEATURES_DUMP_FILE) $(FEATURES_DUMP_FILE_STATIC)
+
+ifeq ($(REUSE_FEATURES_DUMP),1)
+$(FEATURES_DUMP_FILE):
+        $(call clean)
+        @cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) feature-dump"; \
+        echo "- $@: $$cmd" && echo $$cmd && \
+        ( eval $$cmd ) > /dev/null 2>&1
+
+$(FEATURES_DUMP_FILE_STATIC):
+        $(call clean)
+        @cmd="cd $(PERF) && make FEATURE_DUMP_COPY=$@ $(O_OPT) LDFLAGS='-static' feature-dump"; \
+        echo "- $@: $$cmd" && echo $$cmd && \
+        ( eval $$cmd ) > /dev/null 2>&1
+
+# Add feature dump dependency for run/run_O targets
+$(foreach t,$(run) $(run_O),$(eval \
+        $(t): $(if $(findstring make_static,$(t)),\
+                $(FEATURES_DUMP_FILE_STATIC),\
+                $(FEATURES_DUMP_FILE))))
+
+# Append 'FEATURES_DUMP=' option to all test cases. For example:
+# make_no_libbpf: NO_LIBBPF=1  --> NO_LIBBPF=1 FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP
+# make_static: LDFLAGS=-static --> LDFLAGS=-static FEATURES_DUMP=/a/b/BUILD_TEST_FEATURE_DUMP_STATIC
+$(foreach t,$(run),$(if $(findstring make_static,$(t)),\
+                        $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE_STATIC)),\
+                        $(eval $(t) := $($(t)) FEATURES_DUMP=$(FEATURES_DUMP_FILE))))
+endif
 
 .PHONY: all $(run) $(run_O) tarpkg clean make_kernelsrc make_kernelsrc_tools
 endif # ifndef MK
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index abe8849d1d70..7865f68dc0d8 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1271,6 +1271,38 @@ static int test__checkevent_precise_max_modifier(struct perf_evlist *evlist)
         return 0;
 }
 
+static int test__checkevent_config_symbol(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "insn") == 0);
+        return 0;
+}
+
+static int test__checkevent_config_raw(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "rawpmu") == 0);
+        return 0;
+}
+
+static int test__checkevent_config_num(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "numpmu") == 0);
+        return 0;
+}
+
+static int test__checkevent_config_cache(struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+        TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "cachepmu") == 0);
+        return 0;
+}
+
 static int count_tracepoints(void)
 {
         struct dirent *events_ent;
@@ -1579,6 +1611,26 @@ static struct evlist_test test__events[] = {
                 .check = test__checkevent_precise_max_modifier,
                 .id    = 47,
         },
+        {
+                .name  = "instructions/name=insn/",
+                .check = test__checkevent_config_symbol,
+                .id    = 48,
+        },
+        {
+                .name  = "r1234/name=rawpmu/",
+                .check = test__checkevent_config_raw,
+                .id    = 49,
+        },
+        {
+                .name  = "4:0x6530160/name=numpmu/",
+                .check = test__checkevent_config_num,
+                .id    = 50,
+        },
+        {
+                .name  = "L1-dcache-misses/name=cachepmu/",
+                .check = test__checkevent_config_cache,
+                .id    = 51,
+        },
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1666,7 +1718,7 @@ static int test_term(struct terms_test *t)
         }
 
         ret = t->check(&terms);
-        parse_events__free_terms(&terms);
+        parse_events_terms__purge(&terms);
 
         return ret;
 }
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f0bfc9e8fd9f..630b0b409b97 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -110,7 +110,6 @@ int test__vmlinux_matches_kallsyms(int subtest __maybe_unused)
          */
         for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
                 struct symbol *pair, *first_pair;
-                bool backwards = true;
 
                 sym  = rb_entry(nd, struct symbol, rb_node);
 
@@ -151,27 +150,14 @@ next_pair:
                                 continue;
 
                         } else {
-                                struct rb_node *nnd;
-detour:
-                                nnd = backwards ? rb_prev(&pair->rb_node) :
-                                                  rb_next(&pair->rb_node);
-                                if (nnd) {
-                                        struct symbol *next = rb_entry(nnd, struct symbol, rb_node);
-
-                                        if (UM(next->start) == mem_start) {
-                                                pair = next;
+                                pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL, NULL);
+                                if (pair) {
+                                        if (UM(pair->start) == mem_start)
                                                 goto next_pair;
-                                        }
-                                }
 
-                                if (backwards) {
-                                        backwards = false;
-                                        pair = first_pair;
-                                        goto detour;
+                                        pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
+                                                 mem_start, sym->name, pair->name);
                                 }
-
-                                pr_debug("%#" PRIx64 ": diff name v: %s k: %s\n",
-                                         mem_start, sym->name, pair->name);
                         }
                 } else
                         pr_debug("%#" PRIx64 ": %s not on kallsyms\n",
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index d37202121689..af68a9d488bf 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -531,8 +531,8 @@ static struct ui_browser_colorset {
                 .bg       = "yellow",
         },
         {
-                .colorset = HE_COLORSET_CODE,
-                .name     = "code",
+                .colorset = HE_COLORSET_JUMP_ARROWS,
+                .name     = "jump_arrows",
                 .fg       = "blue",
                 .bg       = "default",
         },
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 01781de59532..be3b70eb5fca 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -7,7 +7,7 @@
 #define HE_COLORSET_MEDIUM      51
 #define HE_COLORSET_NORMAL      52
 #define HE_COLORSET_SELECTED    53
-#define HE_COLORSET_CODE        54
+#define HE_COLORSET_JUMP_ARROWS 54
 #define HE_COLORSET_ADDR        55
 #define HE_COLORSET_ROOT        56
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 718bd46d47fa..4fc208e82c6f 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -284,7 +284,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
                 to = (u64)btarget->idx;
         }
 
-        ui_browser__set_color(browser, HE_COLORSET_CODE);
+        ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
         __ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
                                  from, to);
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 08c09ad755d2..4b9816555946 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -32,6 +32,7 @@ struct hist_browser {
         bool                 show_headers;
         float                min_pcnt;
         u64                  nr_non_filtered_entries;
+        u64                  nr_hierarchy_entries;
         u64                  nr_callchain_rows;
 };
 
@@ -58,11 +59,11 @@ static int hist_browser__get_folding(struct hist_browser *browser)
 
         for (nd = rb_first(&hists->entries);
              (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-             nd = rb_next(nd)) {
+             nd = rb_hierarchy_next(nd)) {
                 struct hist_entry *he =
                         rb_entry(nd, struct hist_entry, rb_node);
 
-                if (he->unfolded)
+                if (he->leaf && he->unfolded)
                         unfolded_rows += he->nr_rows;
         }
         return unfolded_rows;
@@ -72,7 +73,9 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 {
         u32 nr_entries;
 
-        if (hist_browser__has_filter(hb))
+        if (symbol_conf.report_hierarchy)
+                nr_entries = hb->nr_hierarchy_entries;
+        else if (hist_browser__has_filter(hb))
                 nr_entries = hb->nr_non_filtered_entries;
         else
                 nr_entries = hb->hists->nr_entries;
@@ -247,6 +250,38 @@ static int callchain__count_rows(struct rb_root *chain)
         return n;
 }
 
+static int hierarchy_count_rows(struct hist_browser *hb, struct hist_entry *he,
+                                bool include_children)
+{
+        int count = 0;
+        struct rb_node *node;
+        struct hist_entry *child;
+
+        if (he->leaf)
+                return callchain__count_rows(&he->sorted_chain);
+
+        if (he->has_no_entry)
+                return 1;
+
+        node = rb_first(&he->hroot_out);
+        while (node) {
+                float percent;
+
+                child = rb_entry(node, struct hist_entry, rb_node);
+                percent = hist_entry__get_percent_limit(child);
+
+                if (!child->filtered && percent >= hb->min_pcnt) {
+                        count++;
+
+                        if (include_children && child->unfolded)
+                                count += hierarchy_count_rows(hb, child, true);
+                }
+
+                node = rb_next(node);
+        }
+        return count;
+}
+
 static bool hist_entry__toggle_fold(struct hist_entry *he)
 {
         if (!he)
@@ -326,11 +361,17 @@ static void callchain__init_have_children(struct rb_root *root)
 
 static void hist_entry__init_have_children(struct hist_entry *he)
 {
-        if (!he->init_have_children) {
+        if (he->init_have_children)
+                return;
+
+        if (he->leaf) {
                 he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
                 callchain__init_have_children(&he->sorted_chain);
-                he->init_have_children = true;
+        } else {
+                he->has_children = !RB_EMPTY_ROOT(&he->hroot_out);
         }
+
+        he->init_have_children = true;
 }
 
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
@@ -349,17 +390,49 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
                 has_children = callchain_list__toggle_fold(cl);
 
         if (has_children) {
+                int child_rows = 0;
+
                 hist_entry__init_have_children(he);
                 browser->b.nr_entries -= he->nr_rows;
-                browser->nr_callchain_rows -= he->nr_rows;
 
-                if (he->unfolded)
-                        he->nr_rows = callchain__count_rows(&he->sorted_chain);
+                if (he->leaf)
+                        browser->nr_callchain_rows -= he->nr_rows;
                 else
+                        browser->nr_hierarchy_entries -= he->nr_rows;
+
+                if (symbol_conf.report_hierarchy)
+                        child_rows = hierarchy_count_rows(browser, he, true);
+
+                if (he->unfolded) {
+                        if (he->leaf)
+                                he->nr_rows = callchain__count_rows(&he->sorted_chain);
+                        else
+                                he->nr_rows = hierarchy_count_rows(browser, he, false);
+
+                        /* account grand children */
+                        if (symbol_conf.report_hierarchy)
+                                browser->b.nr_entries += child_rows - he->nr_rows;
+
+                        if (!he->leaf && he->nr_rows == 0) {
+                                he->has_no_entry = true;
+                                he->nr_rows = 1;
+                        }
+                } else {
+                        if (symbol_conf.report_hierarchy)
+                                browser->b.nr_entries -= child_rows - he->nr_rows;
+
+                        if (he->has_no_entry)
+                                he->has_no_entry = false;
+
                         he->nr_rows = 0;
+                }
 
                 browser->b.nr_entries += he->nr_rows;
-                browser->nr_callchain_rows += he->nr_rows;
+
+                if (he->leaf)
+                        browser->nr_callchain_rows += he->nr_rows;
+                else
+                        browser->nr_hierarchy_entries += he->nr_rows;
 
                 return true;
         }
@@ -422,13 +495,38 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
         return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
+static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
+                                 bool unfold __maybe_unused)
+{
+        float percent;
+        struct rb_node *nd;
+        struct hist_entry *child;
+        int n = 0;
+
+        for (nd = rb_first(&he->hroot_out); nd; nd = rb_next(nd)) {
+                child = rb_entry(nd, struct hist_entry, rb_node);
+                percent = hist_entry__get_percent_limit(child);
+                if (!child->filtered && percent >= hb->min_pcnt)
+                        n++;
+        }
+
+        return n;
+}
+
+static void hist_entry__set_folding(struct hist_entry *he,
+                                    struct hist_browser *hb, bool unfold)
 {
         hist_entry__init_have_children(he);
         he->unfolded = unfold ? he->has_children : false;
 
         if (he->has_children) {
-                int n = callchain__set_folding(&he->sorted_chain, unfold);
+                int n;
+
+                if (he->leaf)
+                        n = callchain__set_folding(&he->sorted_chain, unfold);
+                else
+                        n = hierarchy_set_folding(hb, he, unfold);
+
                 he->nr_rows = unfold ? n : 0;
         } else
                 he->nr_rows = 0;
@@ -438,19 +536,38 @@ static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
         struct rb_node *nd;
-        struct hists *hists = browser->hists;
+        struct hist_entry *he;
+        double percent;
 
-        for (nd = rb_first(&hists->entries);
-             (nd = hists__filter_entries(nd, browser->min_pcnt)) != NULL;
-             nd = rb_next(nd)) {
-                struct hist_entry *he = rb_entry(nd, struct hist_entry, rb_node);
-                hist_entry__set_folding(he, unfold);
-                browser->nr_callchain_rows += he->nr_rows;
+        nd = rb_first(&browser->hists->entries);
+        while (nd) {
+                he = rb_entry(nd, struct hist_entry, rb_node);
+
+                /* set folding state even if it's currently folded */
+                nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+                hist_entry__set_folding(he, browser, unfold);
+
+                percent = hist_entry__get_percent_limit(he);
+                if (he->filtered || percent < browser->min_pcnt)
+                        continue;
+
+                if (!he->depth || unfold)
+                        browser->nr_hierarchy_entries++;
+                if (he->leaf)
+                        browser->nr_callchain_rows += he->nr_rows;
+                else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+                        browser->nr_hierarchy_entries++;
+                        he->has_no_entry = true;
+                        he->nr_rows = 1;
+                } else
+                        he->has_no_entry = false;
         }
 }
 
 static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
+        browser->nr_hierarchy_entries = 0;
         browser->nr_callchain_rows = 0;
         __hist_browser__set_folding(browser, unfold);
 
@@ -657,9 +774,24 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         return 1;
 }
 
+static bool check_percent_display(struct rb_node *node, u64 parent_total)
+{
+        struct callchain_node *child;
+
+        if (node == NULL)
+                return false;
+
+        if (rb_next(node))
+                return true;
+
+        child = rb_entry(node, struct callchain_node, rb_node);
+        return callchain_cumul_hits(child) != parent_total;
+}
+
 static int hist_browser__show_callchain_flat(struct hist_browser *browser,
                                              struct rb_root *root,
                                              unsigned short row, u64 total,
+                                             u64 parent_total,
                                              print_callchain_entry_fn print,
                                              struct callchain_print_arg *arg,
                                              check_output_full_fn is_output_full)
@@ -669,7 +801,7 @@ static int hist_browser__show_callchain_flat(struct hist_browser *browser,
         bool need_percent;
 
         node = rb_first(root);
-        need_percent = node && rb_next(node);
+        need_percent = check_percent_display(node, parent_total);
 
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -763,6 +895,7 @@ static char *hist_browser__folded_callchain_str(struct hist_browser *browser,
 static int hist_browser__show_callchain_folded(struct hist_browser *browser,
                                                struct rb_root *root,
                                                unsigned short row, u64 total,
+                                               u64 parent_total,
                                                print_callchain_entry_fn print,
                                                struct callchain_print_arg *arg,
                                                check_output_full_fn is_output_full)
@@ -772,7 +905,7 @@ static int hist_browser__show_callchain_folded(struct hist_browser *browser,
         bool need_percent;
 
         node = rb_first(root);
-        need_percent = node && rb_next(node);
+        need_percent = check_percent_display(node, parent_total);
 
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -844,20 +977,24 @@ next:
         return row - first_row;
 }
 
-static int hist_browser__show_callchain(struct hist_browser *browser,
+static int hist_browser__show_callchain_graph(struct hist_browser *browser,
                                         struct rb_root *root, int level,
                                         unsigned short row, u64 total,
+                                        u64 parent_total,
                                         print_callchain_entry_fn print,
                                         struct callchain_print_arg *arg,
                                         check_output_full_fn is_output_full)
 {
         struct rb_node *node;
         int first_row = row, offset = level * LEVEL_OFFSET_STEP;
-        u64 new_total;
         bool need_percent;
+        u64 percent_total = total;
+
+        if (callchain_param.mode == CHAIN_GRAPH_REL)
+                percent_total = parent_total;
 
         node = rb_first(root);
-        need_percent = node && rb_next(node);
+        need_percent = check_percent_display(node, parent_total);
 
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
@@ -878,7 +1015,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
                         folded_sign = callchain_list__folded(chain);
 
                         row += hist_browser__show_callchain_list(browser, child,
-                                                        chain, row, total,
+                                                        chain, row, percent_total,
                                                         was_first && need_percent,
                                                         offset + extra_offset,
                                                         print, arg);
@@ -893,13 +1030,9 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
                 if (folded_sign == '-') {
                         const int new_level = level + (extra_offset ? 2 : 1);
 
-                        if (callchain_param.mode == CHAIN_GRAPH_REL)
-                                new_total = child->children_hit;
-                        else
-                                new_total = total;
-
-                        row += hist_browser__show_callchain(browser, &child->rb_root,
-                                                            new_level, row, new_total,
+                        row += hist_browser__show_callchain_graph(browser, &child->rb_root,
+                                                            new_level, row, total,
+                                                            child->children_hit,
                                                             print, arg, is_output_full);
                 }
                 if (is_output_full(browser, row))
@@ -910,6 +1043,45 @@ out:
         return row - first_row;
 }
 
+static int hist_browser__show_callchain(struct hist_browser *browser,
+                                        struct hist_entry *entry, int level,
+                                        unsigned short row,
+                                        print_callchain_entry_fn print,
+                                        struct callchain_print_arg *arg,
+                                        check_output_full_fn is_output_full)
+{
+        u64 total = hists__total_period(entry->hists);
+        u64 parent_total;
+        int printed;
+
+        if (symbol_conf.cumulate_callchain)
+                parent_total = entry->stat_acc->period;
+        else
+                parent_total = entry->stat.period;
+
+        if (callchain_param.mode == CHAIN_FLAT) {
+                printed = hist_browser__show_callchain_flat(browser,
+                                                &entry->sorted_chain, row,
+                                                total, parent_total, print, arg,
+                                                is_output_full);
+        } else if (callchain_param.mode == CHAIN_FOLDED) {
+                printed = hist_browser__show_callchain_folded(browser,
+                                                &entry->sorted_chain, row,
+                                                total, parent_total, print, arg,
+                                                is_output_full);
+        } else {
+                printed = hist_browser__show_callchain_graph(browser,
+                                                &entry->sorted_chain, level, row,
+                                                total, parent_total, print, arg,
+                                                is_output_full);
+        }
+
+        if (arg->is_current_entry)
+                browser->he_selection = entry;
+
+        return printed;
+}
+
 struct hpp_arg {
         struct ui_browser *b;
         char folded_sign;
@@ -1006,7 +1178,6 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                                     struct hist_entry *entry,
                                     unsigned short row)
 {
-        char s[256];
         int printed = 0;
         int width = browser->b.width;
         char folded_sign = ' ';
@@ -1031,16 +1202,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         .folded_sign    = folded_sign,
                         .current_entry  = current_entry,
                 };
-                struct perf_hpp hpp = {
-                        .buf            = s,
-                        .size           = sizeof(s),
-                        .ptr            = &arg,
-                };
                 int column = 0;
 
                 hist_browser__gotorc(browser, row, 0);
 
-                perf_hpp__for_each_format(fmt) {
+                hists__for_each_format(browser->hists, fmt) {
+                        char s[2048];
+                        struct perf_hpp hpp = {
+                                .buf    = s,
+                                .size   = sizeof(s),
+                                .ptr    = &arg,
+                        };
+
                         if (perf_hpp__should_skip(fmt, entry->hists) ||
                             column++ < browser->b.horiz_scroll)
                                 continue;
@@ -1065,11 +1238,18 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         }
 
                         if (fmt->color) {
-                                width -= fmt->color(fmt, &hpp, entry);
+                                int ret = fmt->color(fmt, &hpp, entry);
+                                hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+                                /*
+                                 * fmt->color() already used ui_browser to
+                                 * print the non alignment bits, skip it (+ret):
+                                 */
+                                ui_browser__printf(&browser->b, "%s", s + ret);
                         } else {
-                                width -= fmt->entry(fmt, &hpp, entry);
+                                hist_entry__snprintf_alignment(entry, &hpp, fmt, fmt->entry(fmt, &hpp, entry));
                                 ui_browser__printf(&browser->b, "%s", s);
                         }
+                        width -= hpp.buf - s;
                 }
 
                 /* The scroll bar isn't being used */
@@ -1084,43 +1264,246 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                 --row_offset;
 
         if (folded_sign == '-' && row != browser->b.rows) {
-                u64 total = hists__total_period(entry->hists);
                 struct callchain_print_arg arg = {
                         .row_offset = row_offset,
                         .is_current_entry = current_entry,
                 };
 
-                if (callchain_param.mode == CHAIN_GRAPH_REL) {
-                        if (symbol_conf.cumulate_callchain)
-                                total = entry->stat_acc->period;
-                        else
-                                total = entry->stat.period;
-                }
-
-                if (callchain_param.mode == CHAIN_FLAT) {
-                        printed += hist_browser__show_callchain_flat(browser,
-                                        &entry->sorted_chain, row, total,
-                                        hist_browser__show_callchain_entry, &arg,
-                                        hist_browser__check_output_full);
-                } else if (callchain_param.mode == CHAIN_FOLDED) {
-                        printed += hist_browser__show_callchain_folded(browser,
-                                        &entry->sorted_chain, row, total,
+                printed += hist_browser__show_callchain(browser, entry, 1, row,
                                         hist_browser__show_callchain_entry, &arg,
                                         hist_browser__check_output_full);
+        }
+
+        return printed;
+}
+
+static int hist_browser__show_hierarchy_entry(struct hist_browser *browser,
+                                              struct hist_entry *entry,
+                                              unsigned short row,
+                                              int level)
+{
+        int printed = 0;
+        int width = browser->b.width;
+        char folded_sign = ' ';
+        bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+        off_t row_offset = entry->row_offset;
+        bool first = true;
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+        struct hpp_arg arg = {
+                .b              = &browser->b,
+                .current_entry  = current_entry,
+        };
+        int column = 0;
+        int hierarchy_indent = (entry->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+        if (current_entry) {
+                browser->he_selection = entry;
+                browser->selection = &entry->ms;
+        }
+
+        hist_entry__init_have_children(entry);
+        folded_sign = hist_entry__folded(entry);
+        arg.folded_sign = folded_sign;
+
+        if (entry->leaf && row_offset) {
+                row_offset--;
+                goto show_callchain;
+        }
+
+        hist_browser__gotorc(browser, row, 0);
+
+        if (current_entry && browser->b.navkeypressed)
+                ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+        else
+                ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+        ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+        width -= level * HIERARCHY_INDENT;
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&entry->hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                char s[2048];
+                struct perf_hpp hpp = {
+                        .buf            = s,
+                        .size           = sizeof(s),
+                        .ptr            = &arg,
+                };
+
+                if (perf_hpp__should_skip(fmt, entry->hists) ||
+                    column++ < browser->b.horiz_scroll)
+                        continue;
+
+                if (current_entry && browser->b.navkeypressed) {
+                        ui_browser__set_color(&browser->b,
+                                              HE_COLORSET_SELECTED);
                 } else {
-                        printed += hist_browser__show_callchain(browser,
-                                        &entry->sorted_chain, 1, row, total,
-                                        hist_browser__show_callchain_entry, &arg,
-                                        hist_browser__check_output_full);
+                        ui_browser__set_color(&browser->b,
+                                              HE_COLORSET_NORMAL);
+                }
+
+                if (first) {
+                        ui_browser__printf(&browser->b, "%c", folded_sign);
+                        width--;
+                        first = false;
+                } else {
+                        ui_browser__printf(&browser->b, "  ");
+                        width -= 2;
+                }
+
+                if (fmt->color) {
+                        int ret = fmt->color(fmt, &hpp, entry);
+                        hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+                        /*
+                         * fmt->color() already used ui_browser to
+                         * print the non alignment bits, skip it (+ret):
+                         */
+                        ui_browser__printf(&browser->b, "%s", s + ret);
+                } else {
+                        int ret = fmt->entry(fmt, &hpp, entry);
+                        hist_entry__snprintf_alignment(entry, &hpp, fmt, ret);
+                        ui_browser__printf(&browser->b, "%s", s);
+                }
+                width -= hpp.buf - s;
+        }
+
+        ui_browser__write_nstring(&browser->b, "", hierarchy_indent);
+        width -= hierarchy_indent;
+
+        if (column >= browser->b.horiz_scroll) {
+                char s[2048];
+                struct perf_hpp hpp = {
+                        .buf            = s,
+                        .size           = sizeof(s),
+                        .ptr            = &arg,
+                };
+
+                if (current_entry && browser->b.navkeypressed) {
+                        ui_browser__set_color(&browser->b,
+                                              HE_COLORSET_SELECTED);
+                } else {
+                        ui_browser__set_color(&browser->b,
+                                              HE_COLORSET_NORMAL);
                 }
 
-                if (arg.is_current_entry)
-                        browser->he_selection = entry;
+                perf_hpp_list__for_each_format(entry->hpp_list, fmt) {
+                        ui_browser__write_nstring(&browser->b, "", 2);
+                        width -= 2;
+
+                        /*
+                         * No need to call hist_entry__snprintf_alignment()
+                         * since this fmt is always the last column in the
+                         * hierarchy mode.
+                         */
+                        if (fmt->color) {
+                                width -= fmt->color(fmt, &hpp, entry);
+                        } else {
+                                int i = 0;
+
+                                width -= fmt->entry(fmt, &hpp, entry);
+                                ui_browser__printf(&browser->b, "%s", ltrim(s));
+
+                                while (isspace(s[i++]))
+                                        width++;
+                        }
+                }
+        }
+
+        /* The scroll bar isn't being used */
+        if (!browser->b.navkeypressed)
+                width += 1;
+
+        ui_browser__write_nstring(&browser->b, "", width);
+
+        ++row;
+        ++printed;
+
+show_callchain:
+        if (entry->leaf && folded_sign == '-' && row != browser->b.rows) {
+                struct callchain_print_arg carg = {
+                        .row_offset = row_offset,
+                };
+
+                printed += hist_browser__show_callchain(browser, entry,
+                                        level + 1, row,
+                                        hist_browser__show_callchain_entry, &carg,
+                                        hist_browser__check_output_full);
         }
 
         return printed;
 }
 
+static int hist_browser__show_no_entry(struct hist_browser *browser,
+                                       unsigned short row, int level)
+{
+        int width = browser->b.width;
+        bool current_entry = ui_browser__is_current_entry(&browser->b, row);
+        bool first = true;
+        int column = 0;
+        int ret;
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+        int indent = browser->hists->nr_hpp_node - 2;
+
+        if (current_entry) {
+                browser->he_selection = NULL;
+                browser->selection = NULL;
+        }
+
+        hist_browser__gotorc(browser, row, 0);
+
+        if (current_entry && browser->b.navkeypressed)
+                ui_browser__set_color(&browser->b, HE_COLORSET_SELECTED);
+        else
+                ui_browser__set_color(&browser->b, HE_COLORSET_NORMAL);
+
+        ui_browser__write_nstring(&browser->b, "", level * HIERARCHY_INDENT);
+        width -= level * HIERARCHY_INDENT;
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&browser->hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                if (perf_hpp__should_skip(fmt, browser->hists) ||
+                    column++ < browser->b.horiz_scroll)
+                        continue;
+
+                ret = fmt->width(fmt, NULL, hists_to_evsel(browser->hists));
+
+                if (first) {
+                        /* for folded sign */
+                        first = false;
+                        ret++;
+                } else {
+                        /* space between columns */
+                        ret += 2;
+                }
+
+                ui_browser__write_nstring(&browser->b, "", ret);
+                width -= ret;
+        }
+
+        ui_browser__write_nstring(&browser->b, "", indent * HIERARCHY_INDENT);
+        width -= indent * HIERARCHY_INDENT;
+
+        if (column >= browser->b.horiz_scroll) {
+                char buf[32];
+
+                ret = snprintf(buf, sizeof(buf), "no entry >= %.2f%%", browser->min_pcnt);
+                ui_browser__printf(&browser->b, "  %s", buf);
+                width -= ret + 2;
+        }
+
+        /* The scroll bar isn't being used */
+        if (!browser->b.navkeypressed)
+                width += 1;
+
+        ui_browser__write_nstring(&browser->b, "", width);
+        return 1;
+}
+
 static int advance_hpp_check(struct perf_hpp *hpp, int inc)
 {
         advance_hpp(hpp, inc);
@@ -1144,7 +1527,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
                         return ret;
         }
 
-        perf_hpp__for_each_format(fmt) {
+        hists__for_each_format(browser->hists, fmt) {
                 if (perf_hpp__should_skip(fmt, hists)  || column++ < browser->b.horiz_scroll)
                         continue;
 
@@ -1160,11 +1543,96 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char *
         return ret;
 }
 
+static int hists_browser__scnprintf_hierarchy_headers(struct hist_browser *browser, char *buf, size_t size)
+{
+        struct hists *hists = browser->hists;
+        struct perf_hpp dummy_hpp = {
+                .buf    = buf,
+                .size   = size,
+        };
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+        size_t ret = 0;
+        int column = 0;
+        int indent = hists->nr_hpp_node - 2;
+        bool first_node, first_col;
+
+        ret = scnprintf(buf, size, " ");
+        if (advance_hpp_check(&dummy_hpp, ret))
+                return ret;
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                if (column++ < browser->b.horiz_scroll)
+                        continue;
+
+                ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+                if (advance_hpp_check(&dummy_hpp, ret))
+                        break;
+
+                ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
+                if (advance_hpp_check(&dummy_hpp, ret))
+                        break;
+        }
+
+        ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "%*s",
+                        indent * HIERARCHY_INDENT, "");
+        if (advance_hpp_check(&dummy_hpp, ret))
+                return ret;
+
+        first_node = true;
+        list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+                if (!first_node) {
+                        ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, " / ");
+                        if (advance_hpp_check(&dummy_hpp, ret))
+                                break;
+                }
+                first_node = false;
+
+                first_col = true;
+                perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                        char *start;
+
+                        if (perf_hpp__should_skip(fmt, hists))
+                                continue;
+
+                        if (!first_col) {
+                                ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "+");
+                                if (advance_hpp_check(&dummy_hpp, ret))
+                                        break;
+                        }
+                        first_col = false;
+
+                        ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+                        dummy_hpp.buf[ret] = '\0';
+                        rtrim(dummy_hpp.buf);
+
+                        start = ltrim(dummy_hpp.buf);
+                        ret = strlen(start);
+
+                        if (start != dummy_hpp.buf)
+                                memmove(dummy_hpp.buf, start, ret + 1);
+
+                        if (advance_hpp_check(&dummy_hpp, ret))
+                                break;
+                }
+        }
+
+        return ret;
+}
+
 static void hist_browser__show_headers(struct hist_browser *browser)
 {
         char headers[1024];
 
-        hists_browser__scnprintf_headers(browser, headers, sizeof(headers));
+        if (symbol_conf.report_hierarchy)
+                hists_browser__scnprintf_hierarchy_headers(browser, headers,
+                                                           sizeof(headers));
+        else
+                hists_browser__scnprintf_headers(browser, headers,
+                                                 sizeof(headers));
         ui_browser__gotorc(&browser->b, 0, 0);
         ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
         ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
@@ -1196,18 +1664,34 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
         hb->he_selection = NULL;
         hb->selection = NULL;
 
-        for (nd = browser->top; nd; nd = rb_next(nd)) {
+        for (nd = browser->top; nd; nd = rb_hierarchy_next(nd)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
                 float percent;
 
-                if (h->filtered)
+                if (h->filtered) {
+                        /* let it move to sibling */
+                        h->unfolded = false;
                         continue;
+                }
 
                 percent = hist_entry__get_percent_limit(h);
                 if (percent < hb->min_pcnt)
                         continue;
 
-                row += hist_browser__show_entry(hb, h, row);
+                if (symbol_conf.report_hierarchy) {
+                        row += hist_browser__show_hierarchy_entry(hb, h, row,
+                                                                  h->depth);
+                        if (row == browser->rows)
+                                break;
+
+                        if (h->has_no_entry) {
+                                hist_browser__show_no_entry(hb, row, h->depth + 1);
+                                row++;
+                        }
+                } else {
+                        row += hist_browser__show_entry(hb, h, row);
+                }
+
                 if (row == browser->rows)
                         break;
         }
@@ -1225,7 +1709,14 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
                 if (!h->filtered && percent >= min_pcnt)
                         return nd;
 
-                nd = rb_next(nd);
+                /*
+                 * If it's filtered, its all children also were filtered.
+                 * So move to sibling node.
+                 */
+                if (rb_next(nd))
+                        nd = rb_next(nd);
+                else
+                        nd = rb_hierarchy_next(nd);
         }
 
         return NULL;
@@ -1241,7 +1732,7 @@ static struct rb_node *hists__filter_prev_entries(struct rb_node *nd,
                 if (!h->filtered && percent >= min_pcnt)
                         return nd;
 
-                nd = rb_prev(nd);
+                nd = rb_hierarchy_prev(nd);
         }
 
         return NULL;
@@ -1271,8 +1762,8 @@ static void ui_browser__hists_seek(struct ui_browser *browser,
                 nd = browser->top;
                 goto do_offset;
         case SEEK_END:
-                nd = hists__filter_prev_entries(rb_last(browser->entries),
-                                                hb->min_pcnt);
+                nd = rb_hierarchy_last(rb_last(browser->entries));
+                nd = hists__filter_prev_entries(nd, hb->min_pcnt);
                 first = false;
                 break;
         default:
@@ -1306,7 +1797,7 @@ do_offset:
         if (offset > 0) {
                 do {
                         h = rb_entry(nd, struct hist_entry, rb_node);
-                        if (h->unfolded) {
+                        if (h->unfolded && h->leaf) {
                                 u16 remaining = h->nr_rows - h->row_offset;
                                 if (offset > remaining) {
                                         offset -= remaining;
@@ -1318,7 +1809,8 @@ do_offset:
                                         break;
                                 }
                         }
-                        nd = hists__filter_entries(rb_next(nd), hb->min_pcnt);
+                        nd = hists__filter_entries(rb_hierarchy_next(nd),
+                                                   hb->min_pcnt);
                         if (nd == NULL)
                                 break;
                         --offset;
@@ -1327,7 +1819,7 @@ do_offset:
         } else if (offset < 0) {
                 while (1) {
                         h = rb_entry(nd, struct hist_entry, rb_node);
-                        if (h->unfolded) {
+                        if (h->unfolded && h->leaf) {
                                 if (first) {
                                         if (-offset > h->row_offset) {
                                                 offset += h->row_offset;
@@ -1351,7 +1843,7 @@ do_offset:
                                 }
                         }
 
-                        nd = hists__filter_prev_entries(rb_prev(nd),
+                        nd = hists__filter_prev_entries(rb_hierarchy_prev(nd),
                                                         hb->min_pcnt);
                         if (nd == NULL)
                                 break;
@@ -1364,7 +1856,7 @@ do_offset:
                                  * row_offset at its last entry.
                                  */
                                 h = rb_entry(nd, struct hist_entry, rb_node);
-                                if (h->unfolded)
+                                if (h->unfolded && h->leaf)
                                         h->row_offset = h->nr_rows;
                                 break;
                         }
@@ -1378,17 +1870,14 @@ do_offset:
 }
 
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-                                           struct hist_entry *he, FILE *fp)
+                                           struct hist_entry *he, FILE *fp,
+                                           int level)
 {
-        u64 total = hists__total_period(he->hists);
         struct callchain_print_arg arg  = {
                 .fp = fp,
         };
 
-        if (symbol_conf.cumulate_callchain)
-                total = he->stat_acc->period;
-
-        hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+        hist_browser__show_callchain(browser, he, level, 0,
                                      hist_browser__fprintf_callchain_entry, &arg,
                                      hist_browser__check_dump_full);
         return arg.printed;
@@ -1414,7 +1903,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
         if (symbol_conf.use_callchain)
                 printed += fprintf(fp, "%c ", folded_sign);
 
-        perf_hpp__for_each_format(fmt) {
+        hists__for_each_format(browser->hists, fmt) {
                 if (perf_hpp__should_skip(fmt, he->hists))
                         continue;
 
@@ -1425,12 +1914,71 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
                         first = false;
 
                 ret = fmt->entry(fmt, &hpp, he);
+                ret = hist_entry__snprintf_alignment(he, &hpp, fmt, ret);
                 advance_hpp(&hpp, ret);
         }
-        printed += fprintf(fp, "%s\n", rtrim(s));
+        printed += fprintf(fp, "%s\n", s);
 
         if (folded_sign == '-')
-                printed += hist_browser__fprintf_callchain(browser, he, fp);
+                printed += hist_browser__fprintf_callchain(browser, he, fp, 1);
+
+        return printed;
+}
+
+
+static int hist_browser__fprintf_hierarchy_entry(struct hist_browser *browser,
+                                                 struct hist_entry *he,
+                                                 FILE *fp, int level)
+{
+        char s[8192];
+        int printed = 0;
+        char folded_sign = ' ';
+        struct perf_hpp hpp = {
+                .buf = s,
+                .size = sizeof(s),
+        };
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+        bool first = true;
+        int ret;
+        int hierarchy_indent = (he->hists->nr_hpp_node - 2) * HIERARCHY_INDENT;
+
+        printed = fprintf(fp, "%*s", level * HIERARCHY_INDENT, "");
+
+        folded_sign = hist_entry__folded(he);
+        printed += fprintf(fp, "%c", folded_sign);
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&he->hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                if (!first) {
+                        ret = scnprintf(hpp.buf, hpp.size, "  ");
+                        advance_hpp(&hpp, ret);
+                } else
+                        first = false;
+
+                ret = fmt->entry(fmt, &hpp, he);
+                advance_hpp(&hpp, ret);
+        }
+
+        ret = scnprintf(hpp.buf, hpp.size, "%*s", hierarchy_indent, "");
+        advance_hpp(&hpp, ret);
+
+        perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+                ret = scnprintf(hpp.buf, hpp.size, "  ");
+                advance_hpp(&hpp, ret);
+
+                ret = fmt->entry(fmt, &hpp, he);
+                advance_hpp(&hpp, ret);
+        }
+
+        printed += fprintf(fp, "%s\n", rtrim(s));
+
+        if (he->leaf && folded_sign == '-') {
+                printed += hist_browser__fprintf_callchain(browser, he, fp,
+                                                           he->depth + 1);
+        }
 
         return printed;
 }
@@ -1444,8 +1992,16 @@ static int hist_browser__fprintf(struct hist_browser *browser, FILE *fp)
         while (nd) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-                printed += hist_browser__fprintf_entry(browser, h, fp);
-                nd = hists__filter_entries(rb_next(nd), browser->min_pcnt);
+                if (symbol_conf.report_hierarchy) {
+                        printed += hist_browser__fprintf_hierarchy_entry(browser,
+                                                                         h, fp,
+                                                                         h->depth);
+                } else {
+                        printed += hist_browser__fprintf_entry(browser, h, fp);
+                }
+
+                nd = hists__filter_entries(rb_hierarchy_next(nd),
+                                           browser->min_pcnt);
         }
 
         return printed;
@@ -1580,11 +2136,18 @@ static int hists__browser_title(struct hists *hists,
         if (hists->uid_filter_str)
                 printed += snprintf(bf + printed, size - printed,
                                     ", UID: %s", hists->uid_filter_str);
-        if (thread)
-                printed += scnprintf(bf + printed, size - printed,
+        if (thread) {
+                if (sort__has_thread) {
+                        printed += scnprintf(bf + printed, size - printed,
                                     ", Thread: %s(%d)",
                                      (thread->comm_set ? thread__comm_str(thread) : ""),
                                     thread->tid);
+                } else {
+                        printed += scnprintf(bf + printed, size - printed,
+                                    ", Thread: %s",
+                                     (thread->comm_set ? thread__comm_str(thread) : ""));
+                }
+        }
         if (dso)
                 printed += scnprintf(bf + printed, size - printed,
                                     ", DSO: %s", dso->short_name);
@@ -1759,15 +2322,24 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 {
         struct thread *thread = act->thread;
 
+        if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+                return 0;
+
         if (browser->hists->thread_filter) {
                 pstack__remove(browser->pstack, &browser->hists->thread_filter);
                 perf_hpp__set_elide(HISTC_THREAD, false);
                 thread__zput(browser->hists->thread_filter);
                 ui_helpline__pop();
         } else {
-                ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
-                                   thread->comm_set ? thread__comm_str(thread) : "",
-                                   thread->tid);
+                if (sort__has_thread) {
+                        ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
+                                           thread->comm_set ? thread__comm_str(thread) : "",
+                                           thread->tid);
+                } else {
+                        ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s thread\"",
+                                           thread->comm_set ? thread__comm_str(thread) : "");
+                }
+
                 browser->hists->thread_filter = thread__get(thread);
                 perf_hpp__set_elide(HISTC_THREAD, false);
                 pstack__push(browser->pstack, &browser->hists->thread_filter);
@@ -1782,13 +2354,22 @@ static int
 add_thread_opt(struct hist_browser *browser, struct popup_action *act,
                char **optstr, struct thread *thread)
 {
-        if (thread == NULL)
+        int ret;
+
+        if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
                 return 0;
 
-        if (asprintf(optstr, "Zoom %s %s(%d) thread",
-                     browser->hists->thread_filter ? "out of" : "into",
-                     thread->comm_set ? thread__comm_str(thread) : "",
-                     thread->tid) < 0)
+        if (sort__has_thread) {
+                ret = asprintf(optstr, "Zoom %s %s(%d) thread",
+                               browser->hists->thread_filter ? "out of" : "into",
+                               thread->comm_set ? thread__comm_str(thread) : "",
+                               thread->tid);
+        } else {
+                ret = asprintf(optstr, "Zoom %s %s thread",
+                               browser->hists->thread_filter ? "out of" : "into",
+                               thread->comm_set ? thread__comm_str(thread) : "");
+        }
+        if (ret < 0)
                 return 0;
 
         act->thread = thread;
@@ -1801,6 +2382,9 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 {
         struct map *map = act->ms.map;
 
+        if (!sort__has_dso || map == NULL)
+                return 0;
+
         if (browser->hists->dso_filter) {
                 pstack__remove(browser->pstack, &browser->hists->dso_filter);
                 perf_hpp__set_elide(HISTC_DSO, false);
@@ -1825,7 +2409,7 @@ static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
             char **optstr, struct map *map)
 {
-        if (map == NULL)
+        if (!sort__has_dso || map == NULL)
                 return 0;
 
         if (asprintf(optstr, "Zoom %s %s DSO",
@@ -1850,7 +2434,7 @@ static int
 add_map_opt(struct hist_browser *browser __maybe_unused,
             struct popup_action *act, char **optstr, struct map *map)
 {
-        if (map == NULL)
+        if (!sort__has_dso || map == NULL)
                 return 0;
 
         if (asprintf(optstr, "Browse map details") < 0)
@@ -1952,6 +2536,9 @@ add_exit_opt(struct hist_browser *browser __maybe_unused,
 static int
 do_zoom_socket(struct hist_browser *browser, struct popup_action *act)
 {
+        if (!sort__has_socket || act->socket < 0)
+                return 0;
+
         if (browser->hists->socket_filter > -1) {
                 pstack__remove(browser->pstack, &browser->hists->socket_filter);
                 browser->hists->socket_filter = -1;
@@ -1971,7 +2558,7 @@ static int
 add_socket_opt(struct hist_browser *browser, struct popup_action *act,
                char **optstr, int socket_id)
 {
-        if (socket_id < 0)
+        if (!sort__has_socket || socket_id < 0)
                 return 0;
 
         if (asprintf(optstr, "Zoom %s Processor Socket %d",
@@ -1989,17 +2576,60 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
         u64 nr_entries = 0;
         struct rb_node *nd = rb_first(&hb->hists->entries);
 
-        if (hb->min_pcnt == 0) {
+        if (hb->min_pcnt == 0 && !symbol_conf.report_hierarchy) {
                 hb->nr_non_filtered_entries = hb->hists->nr_non_filtered_entries;
                 return;
         }
 
         while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
                 nr_entries++;
-                nd = rb_next(nd);
+                nd = rb_hierarchy_next(nd);
         }
 
         hb->nr_non_filtered_entries = nr_entries;
+        hb->nr_hierarchy_entries = nr_entries;
+}
+
+static void hist_browser__update_percent_limit(struct hist_browser *hb,
+                                               double percent)
+{
+        struct hist_entry *he;
+        struct rb_node *nd = rb_first(&hb->hists->entries);
+        u64 total = hists__total_period(hb->hists);
+        u64 min_callchain_hits = total * (percent / 100);
+
+        hb->min_pcnt = callchain_param.min_percent = percent;
+
+        while ((nd = hists__filter_entries(nd, hb->min_pcnt)) != NULL) {
+                he = rb_entry(nd, struct hist_entry, rb_node);
+
+                if (he->has_no_entry) {
+                        he->has_no_entry = false;
+                        he->nr_rows = 0;
+                }
+
+                if (!he->leaf || !symbol_conf.use_callchain)
+                        goto next;
+
+                if (callchain_param.mode == CHAIN_GRAPH_REL) {
+                        total = he->stat.period;
+
+                        if (symbol_conf.cumulate_callchain)
+                                total = he->stat_acc->period;
+
+                        min_callchain_hits = total * (percent / 100);
+                }
+
+                callchain_param.sort(&he->sorted_chain, he->callchain,
+                                     min_callchain_hits, &callchain_param);
+
+next:
+                nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
+
+                /* force to re-evaluate folding state of callchains */
+                he->init_have_children = false;
+                hist_entry__set_folding(he, hb, false);
+        }
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
@@ -2037,6 +2667,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         "E             Expand all callchains\n"                         \
         "F             Toggle percentage of filtered entries\n"         \
         "H             Display column headers\n"                        \
+        "L             Change percent limit\n"                          \
         "m             Display context menu\n"                          \
         "S             Zoom into current Processor Socket\n"            \
 
@@ -2077,7 +2708,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
         memset(options, 0, sizeof(options));
         memset(actions, 0, sizeof(actions));
 
-        perf_hpp__for_each_format(fmt) {
+        hists__for_each_format(browser->hists, fmt) {
                 perf_hpp__reset_width(fmt, hists);
                 /*
                  * This is done just once, and activates the horizontal scrolling
@@ -2192,6 +2823,24 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                 top->zero = !top->zero;
                         }
                         continue;
+                case 'L':
+                        if (ui_browser__input_window("Percent Limit",
+                                        "Please enter the value you want to hide entries under that percent.",
+                                        buf, "ENTER: OK, ESC: Cancel",
+                                        delay_secs * 2) == K_ENTER) {
+                                char *end;
+                                double new_percent = strtod(buf, &end);
+
+                                if (new_percent < 0 || new_percent > 100) {
+                                        ui_browser__warning(&browser->b, delay_secs * 2,
+                                                "Invalid percent: %.2f", new_percent);
+                                        continue;
+                                }
+
+                                hist_browser__update_percent_limit(browser, new_percent);
+                                hist_browser__reset(browser);
+                        }
+                        continue;
                 case K_F1:
                 case 'h':
                 case '?':
@@ -2263,10 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                         continue;
                 }
 
-                if (!sort__has_sym)
-                        goto add_exit_option;
-
-                if (browser->selection == NULL)
+                if (!sort__has_sym || browser->selection == NULL)
                         goto skip_annotation;
 
                 if (sort__mode == SORT_MODE__BRANCH) {
@@ -2306,11 +2952,16 @@ skip_annotation:
                                              &options[nr_options],
                                              socked_id);
                 /* perf script support */
+                if (!is_report_browser(hbt))
+                        goto skip_scripting;
+
                 if (browser->he_selection) {
-                        nr_options += add_script_opt(browser,
-                                                     &actions[nr_options],
-                                                     &options[nr_options],
-                                                     thread, NULL);
+                        if (sort__has_thread && thread) {
+                                nr_options += add_script_opt(browser,
+                                                             &actions[nr_options],
+                                                             &options[nr_options],
+                                                             thread, NULL);
+                        }
                         /*
                          * Note that browser->selection != NULL
                          * when browser->he_selection is not NULL,
@@ -2320,16 +2971,18 @@ skip_annotation:
                          *
                          * See hist_browser__show_entry.
                          */
-                        nr_options += add_script_opt(browser,
-                                                     &actions[nr_options],
-                                                     &options[nr_options],
-                                                     NULL, browser->selection->sym);
+                        if (sort__has_sym && browser->selection->sym) {
+                                nr_options += add_script_opt(browser,
+                                                             &actions[nr_options],
+                                                             &options[nr_options],
+                                                             NULL, browser->selection->sym);
+                        }
                 }
                 nr_options += add_script_opt(browser, &actions[nr_options],
                                              &options[nr_options], NULL, NULL);
                 nr_options += add_switch_opt(browser, &actions[nr_options],
                                              &options[nr_options]);
-add_exit_option:
+skip_scripting:
                 nr_options += add_exit_opt(browser, &actions[nr_options],
                                            &options[nr_options]);
 
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 0f8dcfdfb10f..bd9bf7e343b1 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -306,7 +306,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
         nr_cols = 0;
 
-        perf_hpp__for_each_format(fmt)
+        hists__for_each_format(hists, fmt)
                 col_types[nr_cols++] = G_TYPE_STRING;
 
         store = gtk_tree_store_newv(nr_cols, col_types);
@@ -317,7 +317,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
         col_idx = 0;
 
-        perf_hpp__for_each_format(fmt) {
+        hists__for_each_format(hists, fmt) {
                 if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
@@ -367,7 +367,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 
                 col_idx = 0;
 
-                perf_hpp__for_each_format(fmt) {
+                hists__for_each_format(hists, fmt) {
                         if (perf_hpp__should_skip(fmt, h->hists))
                                 continue;
 
@@ -396,6 +396,194 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
         gtk_container_add(GTK_CONTAINER(window), view);
 }
 
+static void perf_gtk__add_hierarchy_entries(struct hists *hists,
+                                            struct rb_root *root,
+                                            GtkTreeStore *store,
+                                            GtkTreeIter *parent,
+                                            struct perf_hpp *hpp,
+                                            float min_pcnt)
+{
+        int col_idx = 0;
+        struct rb_node *node;
+        struct hist_entry *he;
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+        u64 total = hists__total_period(hists);
+        int size;
+
+        for (node = rb_first(root); node; node = rb_next(node)) {
+                GtkTreeIter iter;
+                float percent;
+                char *bf;
+
+                he = rb_entry(node, struct hist_entry, rb_node);
+                if (he->filtered)
+                        continue;
+
+                percent = hist_entry__get_percent_limit(he);
+                if (percent < min_pcnt)
+                        continue;
+
+                gtk_tree_store_append(store, &iter, parent);
+
+                col_idx = 0;
+
+                /* the first hpp_list_node is for overhead columns */
+                fmt_node = list_first_entry(&hists->hpp_formats,
+                                            struct perf_hpp_list_node, list);
+                perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                        if (fmt->color)
+                                fmt->color(fmt, hpp, he);
+                        else
+                                fmt->entry(fmt, hpp, he);
+
+                        gtk_tree_store_set(store, &iter, col_idx++, hpp->buf, -1);
+                }
+
+                bf = hpp->buf;
+                size = hpp->size;
+                perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+                        int ret;
+
+                        if (fmt->color)
+                                ret = fmt->color(fmt, hpp, he);
+                        else
+                                ret = fmt->entry(fmt, hpp, he);
+
+                        snprintf(hpp->buf + ret, hpp->size - ret, "  ");
+                        advance_hpp(hpp, ret + 2);
+                }
+
+                gtk_tree_store_set(store, &iter, col_idx, ltrim(rtrim(bf)), -1);
+
+                if (!he->leaf) {
+                        hpp->buf = bf;
+                        hpp->size = size;
+
+                        perf_gtk__add_hierarchy_entries(hists, &he->hroot_out,
+                                                        store, &iter, hpp,
+                                                        min_pcnt);
+
+                        if (!hist_entry__has_hierarchy_children(he, min_pcnt)) {
+                                char buf[32];
+                                GtkTreeIter child;
+
+                                snprintf(buf, sizeof(buf), "no entry >= %.2f%%",
+                                         min_pcnt);
+
+                                gtk_tree_store_append(store, &child, &iter);
+                                gtk_tree_store_set(store, &child, col_idx, buf, -1);
+                        }
+                }
+
+                if (symbol_conf.use_callchain && he->leaf) {
+                        if (callchain_param.mode == CHAIN_GRAPH_REL)
+                                total = symbol_conf.cumulate_callchain ?
+                                        he->stat_acc->period : he->stat.period;
+
+                        perf_gtk__add_callchain(&he->sorted_chain, store, &iter,
+                                                col_idx, total);
+                }
+        }
+
+}
+
+static void perf_gtk__show_hierarchy(GtkWidget *window, struct hists *hists,
+                                     float min_pcnt)
+{
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+        GType col_types[MAX_COLUMNS];
+        GtkCellRenderer *renderer;
+        GtkTreeStore *store;
+        GtkWidget *view;
+        int col_idx;
+        int nr_cols = 0;
+        char s[512];
+        char buf[512];
+        bool first_node, first_col;
+        struct perf_hpp hpp = {
+                .buf            = s,
+                .size           = sizeof(s),
+        };
+
+        hists__for_each_format(hists, fmt) {
+                if (perf_hpp__is_sort_entry(fmt) ||
+                    perf_hpp__is_dynamic_entry(fmt))
+                        break;
+
+                col_types[nr_cols++] = G_TYPE_STRING;
+        }
+        col_types[nr_cols++] = G_TYPE_STRING;
+
+        store = gtk_tree_store_newv(nr_cols, col_types);
+        view = gtk_tree_view_new();
+        renderer = gtk_cell_renderer_text_new();
+
+        col_idx = 0;
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+                                                            -1, fmt->name,
+                                                            renderer, "markup",
+                                                            col_idx++, NULL);
+        }
+
+        /* construct merged column header since sort keys share single column */
+        buf[0] = '\0';
+        first_node = true;
+        list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+                if (!first_node)
+                        strcat(buf, " / ");
+                first_node = false;
+
+                first_col = true;
+                perf_hpp_list__for_each_format(&fmt_node->hpp ,fmt) {
+                        if (perf_hpp__should_skip(fmt, hists))
+                                continue;
+
+                        if (!first_col)
+                                strcat(buf, "+");
+                        first_col = false;
+
+                        fmt->header(fmt, &hpp, hists_to_evsel(hists));
+                        strcat(buf, ltrim(rtrim(hpp.buf)));
+                }
+        }
+
+        gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
+                                                    -1, buf,
+                                                    renderer, "markup",
+                                                    col_idx++, NULL);
+
+        for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+                GtkTreeViewColumn *column;
+
+                column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+                gtk_tree_view_column_set_resizable(column, TRUE);
+
+                if (col_idx == 0) {
+                        gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+                                                          column);
+                }
+        }
+
+        gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
+        g_object_unref(GTK_TREE_MODEL(store));
+
+        perf_gtk__add_hierarchy_entries(hists, &hists->entries, store,
+                                        NULL, &hpp, min_pcnt);
+
+        gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+        g_signal_connect(view, "row-activated",
+                         G_CALLBACK(on_row_activated), NULL);
+        gtk_container_add(GTK_CONTAINER(window), view);
+}
+
 int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
                                   const char *help,
                                   struct hist_browser_timer *hbt __maybe_unused,
@@ -463,7 +651,10 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist,
                                                         GTK_POLICY_AUTOMATIC,
                                                         GTK_POLICY_AUTOMATIC);
 
-                perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
+                if (symbol_conf.report_hierarchy)
+                        perf_gtk__show_hierarchy(scrolled_window, hists, min_pcnt);
+                else
+                        perf_gtk__show_hists(scrolled_window, hists, min_pcnt);
 
                 tab_label = gtk_label_new(evname);
 
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index bf2a66e254ea..3baeaa6e71b5 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -5,6 +5,7 @@
 #include "../util/util.h"
 #include "../util/sort.h"
 #include "../util/evsel.h"
+#include "../util/evlist.h"
 
 /* hist period print (hpp) functions */
 
@@ -371,7 +372,20 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
         return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name, _fn)                \
+static bool perf_hpp__is_hpp_entry(struct perf_hpp_fmt *a)
+{
+        return a->header == hpp__header_fn;
+}
+
+static bool hpp__equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+        if (!perf_hpp__is_hpp_entry(a) || !perf_hpp__is_hpp_entry(b))
+                return false;
+
+        return a->idx == b->idx;
+}
+
+#define HPP__COLOR_PRINT_FNS(_name, _fn, _idx)          \
         {                                               \
                 .name   = _name,                        \
                 .header = hpp__header_fn,               \
@@ -381,9 +395,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
                 .cmp    = hpp__nop_cmp,                 \
                 .collapse = hpp__nop_cmp,               \
                 .sort   = hpp__sort_ ## _fn,            \
+                .idx    = PERF_HPP__ ## _idx,           \
+                .equal  = hpp__equal,                   \
         }
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)            \
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn, _idx)      \
         {                                               \
                 .name   = _name,                        \
                 .header = hpp__header_fn,               \
@@ -393,9 +409,11 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
                 .cmp    = hpp__nop_cmp,                 \
                 .collapse = hpp__nop_cmp,               \
                 .sort   = hpp__sort_ ## _fn,            \
+                .idx    = PERF_HPP__ ## _idx,           \
+                .equal  = hpp__equal,                   \
         }
 
-#define HPP__PRINT_FNS(_name, _fn)                      \
+#define HPP__PRINT_FNS(_name, _fn, _idx)                \
         {                                               \
                 .name   = _name,                        \
                 .header = hpp__header_fn,               \
@@ -404,22 +422,25 @@ static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
                 .cmp    = hpp__nop_cmp,                 \
                 .collapse = hpp__nop_cmp,               \
                 .sort   = hpp__sort_ ## _fn,            \
+                .idx    = PERF_HPP__ ## _idx,           \
+                .equal  = hpp__equal,                   \
         }
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-        HPP__COLOR_PRINT_FNS("Overhead", overhead),
-        HPP__COLOR_PRINT_FNS("sys", overhead_sys),
-        HPP__COLOR_PRINT_FNS("usr", overhead_us),
-        HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
-        HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
-        HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
-        HPP__PRINT_FNS("Samples", samples),
-        HPP__PRINT_FNS("Period", period)
+        HPP__COLOR_PRINT_FNS("Overhead", overhead, OVERHEAD),
+        HPP__COLOR_PRINT_FNS("sys", overhead_sys, OVERHEAD_SYS),
+        HPP__COLOR_PRINT_FNS("usr", overhead_us, OVERHEAD_US),
+        HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys, OVERHEAD_GUEST_SYS),
+        HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US),
+        HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC),
+        HPP__PRINT_FNS("Samples", samples, SAMPLES),
+        HPP__PRINT_FNS("Period", period, PERIOD)
 };
 
-LIST_HEAD(perf_hpp__list);
-LIST_HEAD(perf_hpp__sort_list);
-
+struct perf_hpp_list perf_hpp_list = {
+        .fields = LIST_HEAD_INIT(perf_hpp_list.fields),
+        .sorts  = LIST_HEAD_INIT(perf_hpp_list.sorts),
+};
 
 #undef HPP__COLOR_PRINT_FNS
 #undef HPP__COLOR_ACC_PRINT_FNS
@@ -485,63 +506,60 @@ void perf_hpp__init(void)
                 hpp_dimension__add_output(PERF_HPP__PERIOD);
 }
 
-void perf_hpp__column_register(struct perf_hpp_fmt *format)
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+                                    struct perf_hpp_fmt *format)
 {
-        list_add_tail(&format->list, &perf_hpp__list);
+        list_add_tail(&format->list, &list->fields);
 }
 
-void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+                                        struct perf_hpp_fmt *format)
 {
-        list_del(&format->list);
+        list_add_tail(&format->sort_list, &list->sorts);
 }
 
-void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
-{
-        list_add_tail(&format->sort_list, &perf_hpp__sort_list);
-}
-
-void perf_hpp__column_enable(unsigned col)
-{
-        BUG_ON(col >= PERF_HPP__MAX_INDEX);
-        perf_hpp__column_register(&perf_hpp__format[col]);
-}
-
-void perf_hpp__column_disable(unsigned col)
+void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-        BUG_ON(col >= PERF_HPP__MAX_INDEX);
-        perf_hpp__column_unregister(&perf_hpp__format[col]);
+        list_del(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
 {
+        struct perf_hpp_fmt *fmt, *acc, *ovh, *tmp;
+
         if (is_strict_order(field_order))
                 return;
 
-        perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-        perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
+        ovh = &perf_hpp__format[PERF_HPP__OVERHEAD];
+        acc = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC];
+
+        perf_hpp_list__for_each_format_safe(&perf_hpp_list, fmt, tmp) {
+                if (acc->equal(acc, fmt)) {
+                        perf_hpp__column_unregister(fmt);
+                        continue;
+                }
+
+                if (ovh->equal(ovh, fmt))
+                        fmt->name = "Overhead";
+        }
 }
 
-void perf_hpp__setup_output_field(void)
+static bool fmt_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+        return a->equal && a->equal(a, b);
+}
+
+void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 {
         struct perf_hpp_fmt *fmt;
 
         /* append sort keys to output field */
-        perf_hpp__for_each_sort_list(fmt) {
-                if (!list_empty(&fmt->list))
-                        continue;
-
-                /*
-                 * sort entry fields are dynamically created,
-                 * so they can share a same sort key even though
-                 * the list is empty.
-                 */
-                if (perf_hpp__is_sort_entry(fmt)) {
-                        struct perf_hpp_fmt *pos;
+        perf_hpp_list__for_each_sort_list(list, fmt) {
+                struct perf_hpp_fmt *pos;
 
-                        perf_hpp__for_each_format(pos) {
-                                if (perf_hpp__same_sort_entry(pos, fmt))
-                                        goto next;
-                        }
+                perf_hpp_list__for_each_format(list, pos) {
+                        if (fmt_equal(fmt, pos))
+                                goto next;
                 }
 
                 perf_hpp__column_register(fmt);
@@ -550,27 +568,17 @@ next:
         }
 }
 
-void perf_hpp__append_sort_keys(void)
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list)
 {
         struct perf_hpp_fmt *fmt;
 
         /* append output fields to sort keys */
-        perf_hpp__for_each_format(fmt) {
-                if (!list_empty(&fmt->sort_list))
-                        continue;
-
-                /*
-                 * sort entry fields are dynamically created,
-                 * so they can share a same sort key even though
-                 * the list is empty.
-                 */
-                if (perf_hpp__is_sort_entry(fmt)) {
-                        struct perf_hpp_fmt *pos;
+        perf_hpp_list__for_each_format(list, fmt) {
+                struct perf_hpp_fmt *pos;
 
-                        perf_hpp__for_each_sort_list(pos) {
-                                if (perf_hpp__same_sort_entry(pos, fmt))
-                                        goto next;
-                        }
+                perf_hpp_list__for_each_sort_list(list, pos) {
+                        if (fmt_equal(fmt, pos))
+                                goto next;
                 }
 
                 perf_hpp__register_sort_field(fmt);
@@ -579,20 +587,29 @@ next:
         }
 }
 
-void perf_hpp__reset_output_field(void)
+
+static void fmt_free(struct perf_hpp_fmt *fmt)
+{
+        if (fmt->free)
+                fmt->free(fmt);
+}
+
+void perf_hpp__reset_output_field(struct perf_hpp_list *list)
 {
         struct perf_hpp_fmt *fmt, *tmp;
 
         /* reset output fields */
-        perf_hpp__for_each_format_safe(fmt, tmp) {
+        perf_hpp_list__for_each_format_safe(list, fmt, tmp) {
                 list_del_init(&fmt->list);
                 list_del_init(&fmt->sort_list);
+                fmt_free(fmt);
         }
 
         /* reset sort keys */
-        perf_hpp__for_each_sort_list_safe(fmt, tmp) {
+        perf_hpp_list__for_each_sort_list_safe(list, fmt, tmp) {
                 list_del_init(&fmt->list);
                 list_del_init(&fmt->sort_list);
+                fmt_free(fmt);
         }
 }
 
@@ -606,7 +623,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
         bool first = true;
         struct perf_hpp dummy_hpp;
 
-        perf_hpp__for_each_format(fmt) {
+        hists__for_each_format(hists, fmt) {
                 if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
@@ -624,22 +641,39 @@ unsigned int hists__sort_list_width(struct hists *hists)
         return ret;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+unsigned int hists__overhead_width(struct hists *hists)
 {
-        int idx;
-
-        if (perf_hpp__is_sort_entry(fmt))
-                return perf_hpp__reset_sort_width(fmt, hists);
+        struct perf_hpp_fmt *fmt;
+        int ret = 0;
+        bool first = true;
+        struct perf_hpp dummy_hpp;
 
-        for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
-                if (fmt == &perf_hpp__format[idx])
+        hists__for_each_format(hists, fmt) {
+                if (perf_hpp__is_sort_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
                         break;
+
+                if (first)
+                        first = false;
+                else
+                        ret += 2;
+
+                ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
         }
 
-        if (idx == PERF_HPP__MAX_INDEX)
+        return ret;
+}
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+        if (perf_hpp__is_sort_entry(fmt))
+                return perf_hpp__reset_sort_width(fmt, hists);
+
+        if (perf_hpp__is_dynamic_entry(fmt))
                 return;
 
-        switch (idx) {
+        BUG_ON(fmt->idx >= PERF_HPP__MAX_INDEX);
+
+        switch (fmt->idx) {
         case PERF_HPP__OVERHEAD:
         case PERF_HPP__OVERHEAD_SYS:
         case PERF_HPP__OVERHEAD_US:
@@ -667,7 +701,7 @@ void perf_hpp__set_user_width(const char *width_list_str)
         struct perf_hpp_fmt *fmt;
         const char *ptr = width_list_str;
 
-        perf_hpp__for_each_format(fmt) {
+        perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
                 char *p;
 
                 int len = strtol(ptr, &p, 10);
@@ -679,3 +713,71 @@ void perf_hpp__set_user_width(const char *width_list_str)
                         break;
         }
 }
+
+static int add_hierarchy_fmt(struct hists *hists, struct perf_hpp_fmt *fmt)
+{
+        struct perf_hpp_list_node *node = NULL;
+        struct perf_hpp_fmt *fmt_copy;
+        bool found = false;
+        bool skip = perf_hpp__should_skip(fmt, hists);
+
+        list_for_each_entry(node, &hists->hpp_formats, list) {
+                if (node->level == fmt->level) {
+                        found = true;
+                        break;
+                }
+        }
+
+        if (!found) {
+                node = malloc(sizeof(*node));
+                if (node == NULL)
+                        return -1;
+
+                node->skip = skip;
+                node->level = fmt->level;
+                perf_hpp_list__init(&node->hpp);
+
+                hists->nr_hpp_node++;
+                list_add_tail(&node->list, &hists->hpp_formats);
+        }
+
+        fmt_copy = perf_hpp_fmt__dup(fmt);
+        if (fmt_copy == NULL)
+                return -1;
+
+        if (!skip)
+                node->skip = false;
+
+        list_add_tail(&fmt_copy->list, &node->hpp.fields);
+        list_add_tail(&fmt_copy->sort_list, &node->hpp.sorts);
+
+        return 0;
+}
+
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+                                  struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+        struct perf_hpp_fmt *fmt;
+        struct hists *hists;
+        int ret;
+
+        if (!symbol_conf.report_hierarchy)
+                return 0;
+
+        evlist__for_each(evlist, evsel) {
+                hists = evsel__hists(evsel);
+
+                perf_hpp_list__for_each_sort_list(list, fmt) {
+                        if (perf_hpp__is_dynamic_entry(fmt) &&
+                            !perf_hpp__defined_dynamic_entry(fmt, hists))
+                                continue;
+
+                        ret = add_hierarchy_fmt(hists, fmt);
+                        if (ret < 0)
+                                return ret;
+                }
+        }
+
+        return 0;
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 387110d50b00..7aff5acf3265 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -165,8 +165,28 @@ static size_t __callchain__fprintf_graph(FILE *fp, struct rb_root *root,
         return ret;
 }
 
+/*
+ * If have one single callchain root, don't bother printing
+ * its percentage (100 % in fractal mode and the same percentage
+ * than the hist in graph mode). This also avoid one level of column.
+ *
+ * However when percent-limit applied, it's possible that single callchain
+ * node have different (non-100% in fractal mode) percentage.
+ */
+static bool need_percent_display(struct rb_node *node, u64 parent_samples)
+{
+        struct callchain_node *cnode;
+
+        if (rb_next(node))
+                return true;
+
+        cnode = rb_entry(node, struct callchain_node, rb_node);
+        return callchain_cumul_hits(cnode) != parent_samples;
+}
+
 static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
-                                       u64 total_samples, int left_margin)
+                                       u64 total_samples, u64 parent_samples,
+                                       int left_margin)
 {
         struct callchain_node *cnode;
         struct callchain_list *chain;
@@ -177,13 +197,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
         int ret = 0;
         char bf[1024];
 
-        /*
-         * If have one single callchain root, don't bother printing
-         * its percentage (100 % in fractal mode and the same percentage
-         * than the hist in graph mode). This also avoid one level of column.
-         */
         node = rb_first(root);
-        if (node && !rb_next(node)) {
+        if (node && !need_percent_display(node, parent_samples)) {
                 cnode = rb_entry(node, struct callchain_node, rb_node);
                 list_for_each_entry(chain, &cnode->val, list) {
                         /*
@@ -213,9 +228,15 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                 root = &cnode->rb_root;
         }
 
+        if (callchain_param.mode == CHAIN_GRAPH_REL)
+                total_samples = parent_samples;
+
         ret += __callchain__fprintf_graph(fp, root, total_samples,
                                           1, 1, left_margin);
-        ret += fprintf(fp, "\n");
+        if (ret) {
+                /* do not add a blank line if it printed nothing */
+                ret += fprintf(fp, "\n");
+        }
 
         return ret;
 }
@@ -323,16 +344,19 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
                                             u64 total_samples, int left_margin,
                                             FILE *fp)
 {
+        u64 parent_samples = he->stat.period;
+
+        if (symbol_conf.cumulate_callchain)
+                parent_samples = he->stat_acc->period;
+
         switch (callchain_param.mode) {
         case CHAIN_GRAPH_REL:
-                return callchain__fprintf_graph(fp, &he->sorted_chain,
-                                                symbol_conf.cumulate_callchain ?
-                                                he->stat_acc->period : he->stat.period,
-                                                left_margin);
+                return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
+                                                parent_samples, left_margin);
                 break;
         case CHAIN_GRAPH_ABS:
                 return callchain__fprintf_graph(fp, &he->sorted_chain, total_samples,
-                                                left_margin);
+                                                parent_samples, left_margin);
                 break;
         case CHAIN_FLAT:
                 return callchain__fprintf_flat(fp, &he->sorted_chain, total_samples);
@@ -349,45 +373,66 @@ static size_t hist_entry_callchain__fprintf(struct hist_entry *he,
         return 0;
 }
 
-static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
-                                            struct hists *hists,
-                                            FILE *fp)
+static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
 {
-        int left_margin = 0;
-        u64 total_period = hists->stats.total_period;
+        const char *sep = symbol_conf.field_sep;
+        struct perf_hpp_fmt *fmt;
+        char *start = hpp->buf;
+        int ret;
+        bool first = true;
 
-        if (field_order == NULL && (sort_order == NULL ||
-                                    !prefixcmp(sort_order, "comm"))) {
-                struct perf_hpp_fmt *fmt;
+        if (symbol_conf.exclude_other && !he->parent)
+                return 0;
 
-                perf_hpp__for_each_format(fmt) {
-                        if (!perf_hpp__is_sort_entry(fmt))
-                                continue;
+        hists__for_each_format(he->hists, fmt) {
+                if (perf_hpp__should_skip(fmt, he->hists))
+                        continue;
 
-                        /* must be 'comm' sort entry */
-                        left_margin = fmt->width(fmt, NULL, hists_to_evsel(hists));
-                        left_margin -= thread__comm_len(he->thread);
-                        break;
-                }
+                /*
+                 * If there's no field_sep, we still need
+                 * to display initial '  '.
+                 */
+                if (!sep || !first) {
+                        ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+                        advance_hpp(hpp, ret);
+                } else
+                        first = false;
+
+                if (perf_hpp__use_color() && fmt->color)
+                        ret = fmt->color(fmt, hpp, he);
+                else
+                        ret = fmt->entry(fmt, hpp, he);
+
+                ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
+                advance_hpp(hpp, ret);
         }
-        return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
+
+        return hpp->buf - start;
 }
 
-static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
+static int hist_entry__hierarchy_fprintf(struct hist_entry *he,
+                                         struct perf_hpp *hpp,
+                                         struct hists *hists,
+                                         FILE *fp)
 {
         const char *sep = symbol_conf.field_sep;
         struct perf_hpp_fmt *fmt;
-        char *start = hpp->buf;
-        int ret;
+        struct perf_hpp_list_node *fmt_node;
+        char *buf = hpp->buf;
+        size_t size = hpp->size;
+        int ret, printed = 0;
         bool first = true;
 
         if (symbol_conf.exclude_other && !he->parent)
                 return 0;
 
-        perf_hpp__for_each_format(fmt) {
-                if (perf_hpp__should_skip(fmt, he->hists))
-                        continue;
+        ret = scnprintf(hpp->buf, hpp->size, "%*s", he->depth * HIERARCHY_INDENT, "");
+        advance_hpp(hpp, ret);
 
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
                 /*
                  * If there's no field_sep, we still need
                  * to display initial '  '.
@@ -403,10 +448,47 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp)
                 else
                         ret = fmt->entry(fmt, hpp, he);
 
+                ret = hist_entry__snprintf_alignment(he, hpp, fmt, ret);
                 advance_hpp(hpp, ret);
         }
 
-        return hpp->buf - start;
+        if (!sep)
+                ret = scnprintf(hpp->buf, hpp->size, "%*s",
+                                (hists->nr_hpp_node - 2) * HIERARCHY_INDENT, "");
+        advance_hpp(hpp, ret);
+
+        printed += fprintf(fp, "%s", buf);
+
+        perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+                hpp->buf  = buf;
+                hpp->size = size;
+
+                /*
+                 * No need to call hist_entry__snprintf_alignment() since this
+                 * fmt is always the last column in the hierarchy mode.
+                 */
+                if (perf_hpp__use_color() && fmt->color)
+                        fmt->color(fmt, hpp, he);
+                else
+                        fmt->entry(fmt, hpp, he);
+
+                /*
+                 * dynamic entries are right-aligned but we want left-aligned
+                 * in the hierarchy mode
+                 */
+                printed += fprintf(fp, "%s%s", sep ?: "  ", ltrim(buf));
+        }
+        printed += putc('\n', fp);
+
+        if (symbol_conf.use_callchain && he->leaf) {
+                u64 total = hists__total_period(hists);
+
+                printed += hist_entry_callchain__fprintf(he, total, 0, fp);
+                goto out;
+        }
+
+out:
+        return printed;
 }
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
@@ -418,24 +500,134 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
                 .buf            = bf,
                 .size           = size,
         };
+        u64 total_period = hists->stats.total_period;
 
         if (size == 0 || size > bfsz)
                 size = hpp.size = bfsz;
 
+        if (symbol_conf.report_hierarchy)
+                return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
+
         hist_entry__snprintf(he, &hpp);
 
         ret = fprintf(fp, "%s\n", bf);
 
         if (symbol_conf.use_callchain)
-                ret += hist_entry__callchain_fprintf(he, hists, fp);
+                ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
 
         return ret;
 }
 
+static int print_hierarchy_indent(const char *sep, int indent,
+                                  const char *line, FILE *fp)
+{
+        if (sep != NULL || indent < 2)
+                return 0;
+
+        return fprintf(fp, "%-.*s", (indent - 2) * HIERARCHY_INDENT, line);
+}
+
+static int print_hierarchy_header(struct hists *hists, struct perf_hpp *hpp,
+                                  const char *sep, FILE *fp)
+{
+        bool first_node, first_col;
+        int indent;
+        int depth;
+        unsigned width = 0;
+        unsigned header_width = 0;
+        struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
+
+        indent = hists->nr_hpp_node;
+
+        /* preserve max indent depth for column headers */
+        print_hierarchy_indent(sep, indent, spaces, fp);
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                fmt->header(fmt, hpp, hists_to_evsel(hists));
+                fprintf(fp, "%s%s", hpp->buf, sep ?: "  ");
+        }
+
+        /* combine sort headers with ' / ' */
+        first_node = true;
+        list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+                if (!first_node)
+                        header_width += fprintf(fp, " / ");
+                first_node = false;
+
+                first_col = true;
+                perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                        if (perf_hpp__should_skip(fmt, hists))
+                                continue;
+
+                        if (!first_col)
+                                header_width += fprintf(fp, "+");
+                        first_col = false;
+
+                        fmt->header(fmt, hpp, hists_to_evsel(hists));
+                        rtrim(hpp->buf);
+
+                        header_width += fprintf(fp, "%s", ltrim(hpp->buf));
+                }
+        }
+
+        fprintf(fp, "\n# ");
+
+        /* preserve max indent depth for initial dots */
+        print_hierarchy_indent(sep, indent, dots, fp);
+
+        /* the first hpp_list_node is for overhead columns */
+        fmt_node = list_first_entry(&hists->hpp_formats,
+                                    struct perf_hpp_list_node, list);
+
+        first_col = true;
+        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                if (!first_col)
+                        fprintf(fp, "%s", sep ?: "..");
+                first_col = false;
+
+                width = fmt->width(fmt, hpp, hists_to_evsel(hists));
+                fprintf(fp, "%.*s", width, dots);
+        }
+
+        depth = 0;
+        list_for_each_entry_continue(fmt_node, &hists->hpp_formats, list) {
+                first_col = true;
+                width = depth * HIERARCHY_INDENT;
+
+                perf_hpp_list__for_each_format(&fmt_node->hpp, fmt) {
+                        if (perf_hpp__should_skip(fmt, hists))
+                                continue;
+
+                        if (!first_col)
+                                width++;  /* for '+' sign between column header */
+                        first_col = false;
+
+                        width += fmt->width(fmt, hpp, hists_to_evsel(hists));
+                }
+
+                if (width > header_width)
+                        header_width = width;
+
+                depth++;
+        }
+
+        fprintf(fp, "%s%-.*s", sep ?: "  ", header_width, dots);
+
+        fprintf(fp, "\n#\n");
+
+        return 2;
+}
+
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
                       int max_cols, float min_pcnt, FILE *fp)
 {
         struct perf_hpp_fmt *fmt;
+        struct perf_hpp_list_node *fmt_node;
         struct rb_node *nd;
         size_t ret = 0;
         unsigned int width;
@@ -449,10 +641,11 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
         bool first = true;
         size_t linesz;
         char *line = NULL;
+        unsigned indent;
 
         init_rem_hits();
 
-        perf_hpp__for_each_format(fmt)
+        hists__for_each_format(hists, fmt)
                 perf_hpp__reset_width(fmt, hists);
 
         if (symbol_conf.col_width_list_str)
@@ -463,7 +656,16 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
         fprintf(fp, "# ");
 
-        perf_hpp__for_each_format(fmt) {
+        if (symbol_conf.report_hierarchy) {
+                list_for_each_entry(fmt_node, &hists->hpp_formats, list) {
+                        perf_hpp_list__for_each_format(&fmt_node->hpp, fmt)
+                                perf_hpp__reset_width(fmt, hists);
+                }
+                nr_rows += print_hierarchy_header(hists, &dummy_hpp, sep, fp);
+                goto print_entries;
+        }
+
+        hists__for_each_format(hists, fmt) {
                 if (perf_hpp__should_skip(fmt, hists))
                         continue;
 
@@ -487,7 +689,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
         fprintf(fp, "# ");
 
-        perf_hpp__for_each_format(fmt) {
+        hists__for_each_format(hists, fmt) {
                 unsigned int i;
 
                 if (perf_hpp__should_skip(fmt, hists))
@@ -520,7 +722,9 @@ print_entries:
                 goto out;
         }
 
-        for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
+        indent = hists__overhead_width(hists) + 4;
+
+        for (nd = rb_first(&hists->entries); nd; nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
                 float percent;
 
@@ -536,6 +740,20 @@ print_entries:
                 if (max_rows && ++nr_rows >= max_rows)
                         break;
 
+                /*
+                 * If all children are filtered out or percent-limited,
+                 * display "no entry >= x.xx%" message.
+                 */
+                if (!h->leaf && !hist_entry__has_hierarchy_children(h, min_pcnt)) {
+                        int depth = hists->nr_hpp_node + h->depth + 1;
+
+                        print_hierarchy_indent(sep, depth, spaces, fp);
+                        fprintf(fp, "%*sno entry >= %.2f%%\n", indent, "", min_pcnt);
+
+                        if (max_rows && ++nr_rows >= max_rows)
+                                break;
+                }
+
                 if (h->ms.map == NULL && verbose > 1) {
                         __map_groups__fprintf_maps(h->thread->mg,
                                                    MAP__FUNCTION, fp);
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 5eec53a3f4ac..eea25e2424e9 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -82,6 +82,7 @@ libperf-y += parse-branch-options.o
 libperf-y += parse-regs-options.o
 libperf-y += term.o
 libperf-y += help-unknown-cmd.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
@@ -105,8 +106,17 @@ libperf-y += scripting-engines/
 
 libperf-$(CONFIG_ZLIB) += zlib.o
 libperf-$(CONFIG_LZMA) += lzma.o
+libperf-y += demangle-java.o
+
+ifdef CONFIG_JITDUMP
+libperf-$(CONFIG_LIBELF) += jitdump.o
+libperf-$(CONFIG_LIBELF) += genelf.o
+libperf-$(CONFIG_LIBELF) += genelf_debug.o
+endif
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+# avoid compiler warnings in 32-bit mode
+CFLAGS_genelf_debug.o  += -Wno-packed
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
         $(call rule_mkdir)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 360fda01f3b0..ec164fe70718 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -478,10 +478,11 @@ void auxtrace_heap__pop(struct auxtrace_heap *heap)
                          heap_array[last].ordinal);
 }
 
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+                                       struct perf_evlist *evlist)
 {
         if (itr)
-                return itr->info_priv_size(itr);
+                return itr->info_priv_size(itr, evlist);
         return 0;
 }
 
@@ -852,7 +853,7 @@ int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
         int err;
 
         pr_debug2("Synthesizing auxtrace information\n");
-        priv_size = auxtrace_record__info_priv_size(itr);
+        priv_size = auxtrace_record__info_priv_size(itr, session->evlist);
         ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
         if (!ev)
                 return -ENOMEM;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index b86f90db1352..e5a8e2d4f2af 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -293,7 +293,8 @@ struct auxtrace_record {
         int (*recording_options)(struct auxtrace_record *itr,
                                  struct perf_evlist *evlist,
                                  struct record_opts *opts);
-        size_t (*info_priv_size)(struct auxtrace_record *itr);
+        size_t (*info_priv_size)(struct auxtrace_record *itr,
+                                 struct perf_evlist *evlist);
         int (*info_fill)(struct auxtrace_record *itr,
                          struct perf_session *session,
                          struct auxtrace_info_event *auxtrace_info,
@@ -429,7 +430,8 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 int auxtrace_record__options(struct auxtrace_record *itr,
                              struct perf_evlist *evlist,
                              struct record_opts *opts);
-size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr,
+                                       struct perf_evlist *evlist);
 int auxtrace_record__info_fill(struct auxtrace_record *itr,
                                struct perf_session *session,
                                struct auxtrace_info_event *auxtrace_info,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 540a7efa657e..0967ce601931 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -7,6 +7,7 @@
 
 #include <linux/bpf.h>
 #include <bpf/libbpf.h>
+#include <bpf/bpf.h>
 #include <linux/err.h>
 #include <linux/string.h>
 #include "perf.h"
@@ -16,6 +17,7 @@
 #include "llvm-utils.h"
 #include "probe-event.h"
 #include "probe-finder.h" // for MAX_PROBES
+#include "parse-events.h"
 #include "llvm-utils.h"
 
 #define DEFINE_PRINT_FN(name, level) \
@@ -108,8 +110,8 @@ void bpf__clear(void)
 }
 
 static void
-bpf_prog_priv__clear(struct bpf_program *prog __maybe_unused,
-                     void *_priv)
+clear_prog_priv(struct bpf_program *prog __maybe_unused,
+                void *_priv)
 {
         struct bpf_prog_priv *priv = _priv;
 
@@ -337,7 +339,7 @@ config_bpf_program(struct bpf_program *prog)
         }
         pr_debug("bpf: config '%s' is ok\n", config_str);
 
-        err = bpf_program__set_private(prog, priv, bpf_prog_priv__clear);
+        err = bpf_program__set_private(prog, priv, clear_prog_priv);
         if (err) {
                 pr_debug("Failed to set priv for program '%s'\n", config_str);
                 goto errout;
@@ -739,6 +741,682 @@ int bpf__foreach_tev(struct bpf_object *obj,
         return 0;
 }
 
+enum bpf_map_op_type {
+        BPF_MAP_OP_SET_VALUE,
+        BPF_MAP_OP_SET_EVSEL,
+};
+
+enum bpf_map_key_type {
+        BPF_MAP_KEY_ALL,
+        BPF_MAP_KEY_RANGES,
+};
+
+struct bpf_map_op {
+        struct list_head list;
+        enum bpf_map_op_type op_type;
+        enum bpf_map_key_type key_type;
+        union {
+                struct parse_events_array array;
+        } k;
+        union {
+                u64 value;
+                struct perf_evsel *evsel;
+        } v;
+};
+
+struct bpf_map_priv {
+        struct list_head ops_list;
+};
+
+static void
+bpf_map_op__delete(struct bpf_map_op *op)
+{
+        if (!list_empty(&op->list))
+                list_del(&op->list);
+        if (op->key_type == BPF_MAP_KEY_RANGES)
+                parse_events__clear_array(&op->k.array);
+        free(op);
+}
+
+static void
+bpf_map_priv__purge(struct bpf_map_priv *priv)
+{
+        struct bpf_map_op *pos, *n;
+
+        list_for_each_entry_safe(pos, n, &priv->ops_list, list) {
+                list_del_init(&pos->list);
+                bpf_map_op__delete(pos);
+        }
+}
+
+static void
+bpf_map_priv__clear(struct bpf_map *map __maybe_unused,
+                    void *_priv)
+{
+        struct bpf_map_priv *priv = _priv;
+
+        bpf_map_priv__purge(priv);
+        free(priv);
+}
+
+static int
+bpf_map_op_setkey(struct bpf_map_op *op, struct parse_events_term *term)
+{
+        op->key_type = BPF_MAP_KEY_ALL;
+        if (!term)
+                return 0;
+
+        if (term->array.nr_ranges) {
+                size_t memsz = term->array.nr_ranges *
+                                sizeof(op->k.array.ranges[0]);
+
+                op->k.array.ranges = memdup(term->array.ranges, memsz);
+                if (!op->k.array.ranges) {
+                        pr_debug("No enough memory to alloc indices for map\n");
+                        return -ENOMEM;
+                }
+                op->key_type = BPF_MAP_KEY_RANGES;
+                op->k.array.nr_ranges = term->array.nr_ranges;
+        }
+        return 0;
+}
+
+static struct bpf_map_op *
+bpf_map_op__new(struct parse_events_term *term)
+{
+        struct bpf_map_op *op;
+        int err;
+
+        op = zalloc(sizeof(*op));
+        if (!op) {
+                pr_debug("Failed to alloc bpf_map_op\n");
+                return ERR_PTR(-ENOMEM);
+        }
+        INIT_LIST_HEAD(&op->list);
+
+        err = bpf_map_op_setkey(op, term);
+        if (err) {
+                free(op);
+                return ERR_PTR(err);
+        }
+        return op;
+}
+
+static int
+bpf_map__add_op(struct bpf_map *map, struct bpf_map_op *op)
+{
+        struct bpf_map_priv *priv;
+        const char *map_name;
+        int err;
+
+        map_name = bpf_map__get_name(map);
+        err = bpf_map__get_private(map, (void **)&priv);
+        if (err) {
+                pr_debug("Failed to get private from map %s\n", map_name);
+                return err;
+        }
+
+        if (!priv) {
+                priv = zalloc(sizeof(*priv));
+                if (!priv) {
+                        pr_debug("No enough memory to alloc map private\n");
+                        return -ENOMEM;
+                }
+                INIT_LIST_HEAD(&priv->ops_list);
+
+                if (bpf_map__set_private(map, priv, bpf_map_priv__clear)) {
+                        free(priv);
+                        return -BPF_LOADER_ERRNO__INTERNAL;
+                }
+        }
+
+        list_add_tail(&op->list, &priv->ops_list);
+        return 0;
+}
+
+static struct bpf_map_op *
+bpf_map__add_newop(struct bpf_map *map, struct parse_events_term *term)
+{
+        struct bpf_map_op *op;
+        int err;
+
+        op = bpf_map_op__new(term);
+        if (IS_ERR(op))
+                return op;
+
+        err = bpf_map__add_op(map, op);
+        if (err) {
+                bpf_map_op__delete(op);
+                return ERR_PTR(err);
+        }
+        return op;
+}
+
+static int
+__bpf_map__config_value(struct bpf_map *map,
+                        struct parse_events_term *term)
+{
+        struct bpf_map_def def;
+        struct bpf_map_op *op;
+        const char *map_name;
+        int err;
+
+        map_name = bpf_map__get_name(map);
+
+        err = bpf_map__get_def(map, &def);
+        if (err) {
+                pr_debug("Unable to get map definition from '%s'\n",
+                         map_name);
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+
+        if (def.type != BPF_MAP_TYPE_ARRAY) {
+                pr_debug("Map %s type is not BPF_MAP_TYPE_ARRAY\n",
+                         map_name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+        }
+        if (def.key_size < sizeof(unsigned int)) {
+                pr_debug("Map %s has incorrect key size\n", map_name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE;
+        }
+        switch (def.value_size) {
+        case 1:
+        case 2:
+        case 4:
+        case 8:
+                break;
+        default:
+                pr_debug("Map %s has incorrect value size\n", map_name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+        }
+
+        op = bpf_map__add_newop(map, term);
+        if (IS_ERR(op))
+                return PTR_ERR(op);
+        op->op_type = BPF_MAP_OP_SET_VALUE;
+        op->v.value = term->val.num;
+        return 0;
+}
+
+static int
+bpf_map__config_value(struct bpf_map *map,
+                      struct parse_events_term *term,
+                      struct perf_evlist *evlist __maybe_unused)
+{
+        if (!term->err_val) {
+                pr_debug("Config value not set\n");
+                return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+        }
+
+        if (term->type_val != PARSE_EVENTS__TERM_TYPE_NUM) {
+                pr_debug("ERROR: wrong value type for 'value'\n");
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+        }
+
+        return __bpf_map__config_value(map, term);
+}
+
+static int
+__bpf_map__config_event(struct bpf_map *map,
+                        struct parse_events_term *term,
+                        struct perf_evlist *evlist)
+{
+        struct perf_evsel *evsel;
+        struct bpf_map_def def;
+        struct bpf_map_op *op;
+        const char *map_name;
+        int err;
+
+        map_name = bpf_map__get_name(map);
+        evsel = perf_evlist__find_evsel_by_str(evlist, term->val.str);
+        if (!evsel) {
+                pr_debug("Event (for '%s') '%s' doesn't exist\n",
+                         map_name, term->val.str);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT;
+        }
+
+        err = bpf_map__get_def(map, &def);
+        if (err) {
+                pr_debug("Unable to get map definition from '%s'\n",
+                         map_name);
+                return err;
+        }
+
+        /*
+         * No need to check key_size and value_size:
+         * kernel has already checked them.
+         */
+        if (def.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+                pr_debug("Map %s type is not BPF_MAP_TYPE_PERF_EVENT_ARRAY\n",
+                         map_name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+        }
+
+        op = bpf_map__add_newop(map, term);
+        if (IS_ERR(op))
+                return PTR_ERR(op);
+        op->op_type = BPF_MAP_OP_SET_EVSEL;
+        op->v.evsel = evsel;
+        return 0;
+}
+
+static int
+bpf_map__config_event(struct bpf_map *map,
+                      struct parse_events_term *term,
+                      struct perf_evlist *evlist)
+{
+        if (!term->err_val) {
+                pr_debug("Config value not set\n");
+                return -BPF_LOADER_ERRNO__OBJCONF_CONF;
+        }
+
+        if (term->type_val != PARSE_EVENTS__TERM_TYPE_STR) {
+                pr_debug("ERROR: wrong value type for 'event'\n");
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE;
+        }
+
+        return __bpf_map__config_event(map, term, evlist);
+}
+
+struct bpf_obj_config__map_func {
+        const char *config_opt;
+        int (*config_func)(struct bpf_map *, struct parse_events_term *,
+                           struct perf_evlist *);
+};
+
+struct bpf_obj_config__map_func bpf_obj_config__map_funcs[] = {
+        {"value", bpf_map__config_value},
+        {"event", bpf_map__config_event},
+};
+
+static int
+config_map_indices_range_check(struct parse_events_term *term,
+                               struct bpf_map *map,
+                               const char *map_name)
+{
+        struct parse_events_array *array = &term->array;
+        struct bpf_map_def def;
+        unsigned int i;
+        int err;
+
+        if (!array->nr_ranges)
+                return 0;
+        if (!array->ranges) {
+                pr_debug("ERROR: map %s: array->nr_ranges is %d but range array is NULL\n",
+                         map_name, (int)array->nr_ranges);
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+
+        err = bpf_map__get_def(map, &def);
+        if (err) {
+                pr_debug("ERROR: Unable to get map definition from '%s'\n",
+                         map_name);
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+
+        for (i = 0; i < array->nr_ranges; i++) {
+                unsigned int start = array->ranges[i].start;
+                size_t length = array->ranges[i].length;
+                unsigned int idx = start + length - 1;
+
+                if (idx >= def.max_entries) {
+                        pr_debug("ERROR: index %d too large\n", idx);
+                        return -BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG;
+                }
+        }
+        return 0;
+}
+
+static int
+bpf__obj_config_map(struct bpf_object *obj,
+                    struct parse_events_term *term,
+                    struct perf_evlist *evlist,
+                    int *key_scan_pos)
+{
+        /* key is "map:<mapname>.<config opt>" */
+        char *map_name = strdup(term->config + sizeof("map:") - 1);
+        struct bpf_map *map;
+        int err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+        char *map_opt;
+        size_t i;
+
+        if (!map_name)
+                return -ENOMEM;
+
+        map_opt = strchr(map_name, '.');
+        if (!map_opt) {
+                pr_debug("ERROR: Invalid map config: %s\n", map_name);
+                goto out;
+        }
+
+        *map_opt++ = '\0';
+        if (*map_opt == '\0') {
+                pr_debug("ERROR: Invalid map option: %s\n", term->config);
+                goto out;
+        }
+
+        map = bpf_object__get_map_by_name(obj, map_name);
+        if (!map) {
+                pr_debug("ERROR: Map %s doesn't exist\n", map_name);
+                err = -BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST;
+                goto out;
+        }
+
+        *key_scan_pos += strlen(map_opt);
+        err = config_map_indices_range_check(term, map, map_name);
+        if (err)
+                goto out;
+        *key_scan_pos -= strlen(map_opt);
+
+        for (i = 0; i < ARRAY_SIZE(bpf_obj_config__map_funcs); i++) {
+                struct bpf_obj_config__map_func *func =
+                                &bpf_obj_config__map_funcs[i];
+
+                if (strcmp(map_opt, func->config_opt) == 0) {
+                        err = func->config_func(map, term, evlist);
+                        goto out;
+                }
+        }
+
+        pr_debug("ERROR: Invalid map config option '%s'\n", map_opt);
+        err = -BPF_LOADER_ERRNO__OBJCONF_MAP_OPT;
+out:
+        free(map_name);
+        if (!err)
+                key_scan_pos += strlen(map_opt);
+        return err;
+}
+
+int bpf__config_obj(struct bpf_object *obj,
+                    struct parse_events_term *term,
+                    struct perf_evlist *evlist,
+                    int *error_pos)
+{
+        int key_scan_pos = 0;
+        int err;
+
+        if (!obj || !term || !term->config)
+                return -EINVAL;
+
+        if (!prefixcmp(term->config, "map:")) {
+                key_scan_pos = sizeof("map:") - 1;
+                err = bpf__obj_config_map(obj, term, evlist, &key_scan_pos);
+                goto out;
+        }
+        err = -BPF_LOADER_ERRNO__OBJCONF_OPT;
+out:
+        if (error_pos)
+                *error_pos = key_scan_pos;
+        return err;
+
+}
+
+typedef int (*map_config_func_t)(const char *name, int map_fd,
+                                 struct bpf_map_def *pdef,
+                                 struct bpf_map_op *op,
+                                 void *pkey, void *arg);
+
+static int
+foreach_key_array_all(map_config_func_t func,
+                      void *arg, const char *name,
+                      int map_fd, struct bpf_map_def *pdef,
+                      struct bpf_map_op *op)
+{
+        unsigned int i;
+        int err;
+
+        for (i = 0; i < pdef->max_entries; i++) {
+                err = func(name, map_fd, pdef, op, &i, arg);
+                if (err) {
+                        pr_debug("ERROR: failed to insert value to %s[%u]\n",
+                                 name, i);
+                        return err;
+                }
+        }
+        return 0;
+}
+
+static int
+foreach_key_array_ranges(map_config_func_t func, void *arg,
+                         const char *name, int map_fd,
+                         struct bpf_map_def *pdef,
+                         struct bpf_map_op *op)
+{
+        unsigned int i, j;
+        int err;
+
+        for (i = 0; i < op->k.array.nr_ranges; i++) {
+                unsigned int start = op->k.array.ranges[i].start;
+                size_t length = op->k.array.ranges[i].length;
+
+                for (j = 0; j < length; j++) {
+                        unsigned int idx = start + j;
+
+                        err = func(name, map_fd, pdef, op, &idx, arg);
+                        if (err) {
+                                pr_debug("ERROR: failed to insert value to %s[%u]\n",
+                                         name, idx);
+                                return err;
+                        }
+                }
+        }
+        return 0;
+}
+
+static int
+bpf_map_config_foreach_key(struct bpf_map *map,
+                           map_config_func_t func,
+                           void *arg)
+{
+        int err, map_fd;
+        const char *name;
+        struct bpf_map_op *op;
+        struct bpf_map_def def;
+        struct bpf_map_priv *priv;
+
+        name = bpf_map__get_name(map);
+
+        err = bpf_map__get_private(map, (void **)&priv);
+        if (err) {
+                pr_debug("ERROR: failed to get private from map %s\n", name);
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+        if (!priv || list_empty(&priv->ops_list)) {
+                pr_debug("INFO: nothing to config for map %s\n", name);
+                return 0;
+        }
+
+        err = bpf_map__get_def(map, &def);
+        if (err) {
+                pr_debug("ERROR: failed to get definition from map %s\n", name);
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+        map_fd = bpf_map__get_fd(map);
+        if (map_fd < 0) {
+                pr_debug("ERROR: failed to get fd from map %s\n", name);
+                return map_fd;
+        }
+
+        list_for_each_entry(op, &priv->ops_list, list) {
+                switch (def.type) {
+                case BPF_MAP_TYPE_ARRAY:
+                case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+                        switch (op->key_type) {
+                        case BPF_MAP_KEY_ALL:
+                                err = foreach_key_array_all(func, arg, name,
+                                                            map_fd, &def, op);
+                                break;
+                        case BPF_MAP_KEY_RANGES:
+                                err = foreach_key_array_ranges(func, arg, name,
+                                                               map_fd, &def,
+                                                               op);
+                                break;
+                        default:
+                                pr_debug("ERROR: keytype for map '%s' invalid\n",
+                                         name);
+                                return -BPF_LOADER_ERRNO__INTERNAL;
+                        }
+                        if (err)
+                                return err;
+                        break;
+                default:
+                        pr_debug("ERROR: type of '%s' incorrect\n", name);
+                        return -BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE;
+                }
+        }
+
+        return 0;
+}
+
+static int
+apply_config_value_for_key(int map_fd, void *pkey,
+                           size_t val_size, u64 val)
+{
+        int err = 0;
+
+        switch (val_size) {
+        case 1: {
+                u8 _val = (u8)(val);
+                err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+                break;
+        }
+        case 2: {
+                u16 _val = (u16)(val);
+                err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+                break;
+        }
+        case 4: {
+                u32 _val = (u32)(val);
+                err = bpf_map_update_elem(map_fd, pkey, &_val, BPF_ANY);
+                break;
+        }
+        case 8: {
+                err = bpf_map_update_elem(map_fd, pkey, &val, BPF_ANY);
+                break;
+        }
+        default:
+                pr_debug("ERROR: invalid value size\n");
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE;
+        }
+        if (err && errno)
+                err = -errno;
+        return err;
+}
+
+static int
+apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
+                           struct perf_evsel *evsel)
+{
+        struct xyarray *xy = evsel->fd;
+        struct perf_event_attr *attr;
+        unsigned int key, events;
+        bool check_pass = false;
+        int *evt_fd;
+        int err;
+
+        if (!xy) {
+                pr_debug("ERROR: evsel not ready for map %s\n", name);
+                return -BPF_LOADER_ERRNO__INTERNAL;
+        }
+
+        if (xy->row_size / xy->entry_size != 1) {
+                pr_debug("ERROR: Dimension of target event is incorrect for map %s\n",
+                         name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM;
+        }
+
+        attr = &evsel->attr;
+        if (attr->inherit) {
+                pr_debug("ERROR: Can't put inherit event into map %s\n", name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
+        }
+
+        if (perf_evsel__is_bpf_output(evsel))
+                check_pass = true;
+        if (attr->type == PERF_TYPE_RAW)
+                check_pass = true;
+        if (attr->type == PERF_TYPE_HARDWARE)
+                check_pass = true;
+        if (!check_pass) {
+                pr_debug("ERROR: Event type is wrong for map %s\n", name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;
+        }
+
+        events = xy->entries / (xy->row_size / xy->entry_size);
+        key = *((unsigned int *)pkey);
+        if (key >= events) {
+                pr_debug("ERROR: there is no event %d for map %s\n",
+                         key, name);
+                return -BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE;
+        }
+        evt_fd = xyarray__entry(xy, key, 0);
+        err = bpf_map_update_elem(map_fd, pkey, evt_fd, BPF_ANY);
+        if (err && errno)
+                err = -errno;
+        return err;
+}
+
+static int
+apply_obj_config_map_for_key(const char *name, int map_fd,
+                             struct bpf_map_def *pdef __maybe_unused,
+                             struct bpf_map_op *op,
+                             void *pkey, void *arg __maybe_unused)
+{
+        int err;
+
+        switch (op->op_type) {
+        case BPF_MAP_OP_SET_VALUE:
+                err = apply_config_value_for_key(map_fd, pkey,
+                                                 pdef->value_size,
+                                                 op->v.value);
+                break;
+        case BPF_MAP_OP_SET_EVSEL:
+                err = apply_config_evsel_for_key(name, map_fd, pkey,
+                                                 op->v.evsel);
+                break;
+        default:
+                pr_debug("ERROR: unknown value type for '%s'\n", name);
+                err = -BPF_LOADER_ERRNO__INTERNAL;
+        }
+        return err;
+}
+
+static int
+apply_obj_config_map(struct bpf_map *map)
+{
+        return bpf_map_config_foreach_key(map,
+                                          apply_obj_config_map_for_key,
+                                          NULL);
+}
+
+static int
+apply_obj_config_object(struct bpf_object *obj)
+{
+        struct bpf_map *map;
+        int err;
+
+        bpf_map__for_each(map, obj) {
+                err = apply_obj_config_map(map);
+                if (err)
+                        return err;
+        }
+        return 0;
+}
+
+int bpf__apply_obj_config(void)
+{
+        struct bpf_object *obj, *tmp;
+        int err;
+
+        bpf_object__for_each_safe(obj, tmp) {
+                err = apply_obj_config_object(obj);
+                if (err)
+                        return err;
+        }
+
+        return 0;
+}
+
 #define ERRNO_OFFSET(e)         ((e) - __BPF_LOADER_ERRNO__START)
 #define ERRCODE_OFFSET(c)       ERRNO_OFFSET(BPF_LOADER_ERRNO__##c)
 #define NR_ERRNO        (__BPF_LOADER_ERRNO__END - __BPF_LOADER_ERRNO__START)
@@ -753,6 +1431,20 @@ static const char *bpf_loader_strerror_table[NR_ERRNO] = {
         [ERRCODE_OFFSET(PROLOGUE)]      = "Failed to generate prologue",
         [ERRCODE_OFFSET(PROLOGUE2BIG)]  = "Prologue too big for program",
         [ERRCODE_OFFSET(PROLOGUEOOB)]   = "Offset out of bound for prologue",
+        [ERRCODE_OFFSET(OBJCONF_OPT)]   = "Invalid object config option",
+        [ERRCODE_OFFSET(OBJCONF_CONF)]  = "Config value not set (missing '=')",
+        [ERRCODE_OFFSET(OBJCONF_MAP_OPT)]       = "Invalid object map config option",
+        [ERRCODE_OFFSET(OBJCONF_MAP_NOTEXIST)]  = "Target map doesn't exist",
+        [ERRCODE_OFFSET(OBJCONF_MAP_VALUE)]     = "Incorrect value type for map",
+        [ERRCODE_OFFSET(OBJCONF_MAP_TYPE)]      = "Incorrect map type",
+        [ERRCODE_OFFSET(OBJCONF_MAP_KEYSIZE)]   = "Incorrect map key size",
+        [ERRCODE_OFFSET(OBJCONF_MAP_VALUESIZE)] = "Incorrect map value size",
+        [ERRCODE_OFFSET(OBJCONF_MAP_NOEVT)]     = "Event not found for map setting",
+        [ERRCODE_OFFSET(OBJCONF_MAP_MAPSIZE)]   = "Invalid map size for event setting",
+        [ERRCODE_OFFSET(OBJCONF_MAP_EVTDIM)]    = "Event dimension too large",
+        [ERRCODE_OFFSET(OBJCONF_MAP_EVTINH)]    = "Doesn't support inherit event",
+        [ERRCODE_OFFSET(OBJCONF_MAP_EVTTYPE)]   = "Wrong event type for map",
+        [ERRCODE_OFFSET(OBJCONF_MAP_IDX2BIG)]   = "Index too large",
 };
 
 static int
@@ -872,3 +1564,29 @@ int bpf__strerror_load(struct bpf_object *obj,
         bpf__strerror_end(buf, size);
         return 0;
 }
+
+int bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+                             struct parse_events_term *term __maybe_unused,
+                             struct perf_evlist *evlist __maybe_unused,
+                             int *error_pos __maybe_unused, int err,
+                             char *buf, size_t size)
+{
+        bpf__strerror_head(err, buf, size);
+        bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,
+                            "Can't use this config term with this map type");
+        bpf__strerror_end(buf, size);
+        return 0;
+}
+
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size)
+{
+        bpf__strerror_head(err, buf, size);
+        bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,
+                            "Cannot set event to BPF map in multi-thread tracing");
+        bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,
+                            "%s (Hint: use -i to turn off inherit)", emsg);
+        bpf__strerror_entry(BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,
+                            "Can only put raw, hardware and BPF output event into a BPF map");
+        bpf__strerror_end(buf, size);
+        return 0;
+}
diff --git a/tools/perf/util/bpf-loader.h b/tools/perf/util/bpf-loader.h
index 6fdc0457e2b6..be4311944e3d 100644
--- a/tools/perf/util/bpf-loader.h
+++ b/tools/perf/util/bpf-loader.h
@@ -10,6 +10,7 @@
 #include <string.h>
 #include <bpf/libbpf.h>
 #include "probe-event.h"
+#include "evlist.h"
 #include "debug.h"
 
 enum bpf_loader_errno {
@@ -24,10 +25,25 @@ enum bpf_loader_errno {
         BPF_LOADER_ERRNO__PROLOGUE,     /* Failed to generate prologue */
         BPF_LOADER_ERRNO__PROLOGUE2BIG, /* Prologue too big for program */
         BPF_LOADER_ERRNO__PROLOGUEOOB,  /* Offset out of bound for prologue */
+        BPF_LOADER_ERRNO__OBJCONF_OPT,  /* Invalid object config option */
+        BPF_LOADER_ERRNO__OBJCONF_CONF, /* Config value not set (lost '=')) */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_OPT,      /* Invalid object map config option */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_NOTEXIST, /* Target map not exist */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE,    /* Incorrect value type for map */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_TYPE,     /* Incorrect map type */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_KEYSIZE,  /* Incorrect map key size */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_VALUESIZE,/* Incorrect map value size */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_NOEVT,    /* Event not found for map setting */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_MAPSIZE,  /* Invalid map size for event setting */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_EVTDIM,   /* Event dimension too large */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH,   /* Doesn't support inherit event */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE,  /* Wrong event type for map */
+        BPF_LOADER_ERRNO__OBJCONF_MAP_IDX2BIG,  /* Index too large */
         __BPF_LOADER_ERRNO__END,
 };
 
 struct bpf_object;
+struct parse_events_term;
 #define PERF_BPF_PROBE_GROUP "perf_bpf_probe"
 
 typedef int (*bpf_prog_iter_callback_t)(struct probe_trace_event *tev,
@@ -53,6 +69,16 @@ int bpf__strerror_load(struct bpf_object *obj, int err,
                        char *buf, size_t size);
 int bpf__foreach_tev(struct bpf_object *obj,
                      bpf_prog_iter_callback_t func, void *arg);
+
+int bpf__config_obj(struct bpf_object *obj, struct parse_events_term *term,
+                    struct perf_evlist *evlist, int *error_pos);
+int bpf__strerror_config_obj(struct bpf_object *obj,
+                             struct parse_events_term *term,
+                             struct perf_evlist *evlist,
+                             int *error_pos, int err, char *buf,
+                             size_t size);
+int bpf__apply_obj_config(void);
+int bpf__strerror_apply_obj_config(int err, char *buf, size_t size);
 #else
 static inline struct bpf_object *
 bpf__prepare_load(const char *filename __maybe_unused,
@@ -84,6 +110,21 @@ bpf__foreach_tev(struct bpf_object *obj __maybe_unused,
 }
 
 static inline int
+bpf__config_obj(struct bpf_object *obj __maybe_unused,
+                struct parse_events_term *term __maybe_unused,
+                struct perf_evlist *evlist __maybe_unused,
+                int *error_pos __maybe_unused)
+{
+        return 0;
+}
+
+static inline int
+bpf__apply_obj_config(void)
+{
+        return 0;
+}
+
+static inline int
 __bpf_strerror(char *buf, size_t size)
 {
         if (!size)
@@ -118,5 +159,23 @@ static inline int bpf__strerror_load(struct bpf_object *obj __maybe_unused,
 {
         return __bpf_strerror(buf, size);
 }
+
+static inline int
+bpf__strerror_config_obj(struct bpf_object *obj __maybe_unused,
+                         struct parse_events_term *term __maybe_unused,
+                         struct perf_evlist *evlist __maybe_unused,
+                         int *error_pos __maybe_unused,
+                         int err __maybe_unused,
+                         char *buf, size_t size)
+{
+        return __bpf_strerror(buf, size);
+}
+
+static inline int
+bpf__strerror_apply_obj_config(int err __maybe_unused,
+                               char *buf, size_t size)
+{
+        return __bpf_strerror(buf, size);
+}
 #endif
 #endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 6a7e273a514a..f1479eeef7da 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -166,6 +166,50 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
         return build_id__filename(build_id_hex, bf, size);
 }
 
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
+{
+        char *id_name, *ch;
+        struct stat sb;
+
+        id_name = dso__build_id_filename(dso, bf, size);
+        if (!id_name)
+                goto err;
+        if (access(id_name, F_OK))
+                goto err;
+        if (lstat(id_name, &sb) == -1)
+                goto err;
+        if ((size_t)sb.st_size > size - 1)
+                goto err;
+        if (readlink(id_name, bf, size - 1) < 0)
+                goto err;
+
+        bf[sb.st_size] = '\0';
+
+        /*
+         * link should be:
+         * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
+         */
+        ch = strrchr(bf, '/');
+        if (!ch)
+                goto err;
+        if (ch - 3 < bf)
+                goto err;
+
+        return strncmp(".ko", ch - 3, 3) == 0;
+err:
+        /*
+         * If dso__build_id_filename work, get id_name again,
+         * because id_name points to bf and is broken.
+         */
+        if (id_name)
+                id_name = dso__build_id_filename(dso, bf, size);
+        pr_err("Invalid build id: %s\n", id_name ? :
+                                         dso->long_name ? :
+                                         dso->short_name ? :
+                                         "[unknown]");
+        return false;
+}
+
 #define dsos__for_each_with_build_id(pos, head) \
         list_for_each_entry(pos, head, node)    \
                 if (!pos->has_build_id)         \
@@ -211,6 +255,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
         dsos__for_each_with_build_id(pos, &machine->dsos.head) {
                 const char *name;
                 size_t name_len;
+                bool in_kernel = false;
 
                 if (!pos->hit)
                         continue;
@@ -227,8 +272,11 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
                         name_len = pos->long_name_len + 1;
                 }
 
+                in_kernel = pos->kernel ||
+                                is_kernel_module(name,
+                                        PERF_RECORD_MISC_CPUMODE_UNKNOWN);
                 err = write_buildid(name, name_len, pos->build_id, machine->pid,
-                                    pos->kernel ? kmisc : umisc, fd);
+                                    in_kernel ? kmisc : umisc, fd);
                 if (err)
                         break;
         }
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 27a14a8a945b..64af3e20610d 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -16,6 +16,7 @@ int sysfs__sprintf_build_id(const char *root_dir, char *sbuild_id);
 int filename__sprintf_build_id(const char *pathname, char *sbuild_id);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
+bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
                            struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 07b5d63947b1..3ca453f0c51f 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -23,6 +23,8 @@
 #define PERF_TRACEFS_ENVIRONMENT "PERF_TRACEFS_DIR"
 #define PERF_PAGER_ENVIRONMENT "PERF_PAGER"
 
+extern const char *config_exclusive_filename;
+
 typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
 extern int perf_config(config_fn_t fn, void *);
@@ -31,6 +33,7 @@ extern u64 perf_config_u64(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
+extern const char *perf_etc_perfconfig(void);
 
 char *alias_lookup(const char *alias);
 int split_cmdline(char *cmdline, const char ***argv);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 53c43eb9489e..24b4bd0d7754 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -416,7 +416,7 @@ create_child(struct callchain_node *parent, bool inherit_children)
 /*
  * Fill the node with callchain values
  */
-static void
+static int
 fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 {
         struct callchain_cursor_node *cursor_node;
@@ -433,7 +433,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                 call = zalloc(sizeof(*call));
                 if (!call) {
                         perror("not enough memory for the code path tree");
-                        return;
+                        return -1;
                 }
                 call->ip = cursor_node->ip;
                 call->ms.sym = cursor_node->sym;
@@ -443,6 +443,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                 callchain_cursor_advance(cursor);
                 cursor_node = callchain_cursor_current(cursor);
         }
+        return 0;
 }
 
 static struct callchain_node *
@@ -453,7 +454,19 @@ add_child(struct callchain_node *parent,
         struct callchain_node *new;
 
         new = create_child(parent, false);
-        fill_node(new, cursor);
+        if (new == NULL)
+                return NULL;
+
+        if (fill_node(new, cursor) < 0) {
+                struct callchain_list *call, *tmp;
+
+                list_for_each_entry_safe(call, tmp, &new->val, list) {
+                        list_del(&call->list);
+                        free(call);
+                }
+                free(new);
+                return NULL;
+        }
 
         new->children_hit = 0;
         new->hit = period;
@@ -462,16 +475,32 @@ add_child(struct callchain_node *parent,
         return new;
 }
 
-static s64 match_chain(struct callchain_cursor_node *node,
-                      struct callchain_list *cnode)
+enum match_result {
+        MATCH_ERROR  = -1,
+        MATCH_EQ,
+        MATCH_LT,
+        MATCH_GT,
+};
+
+static enum match_result match_chain(struct callchain_cursor_node *node,
+                                     struct callchain_list *cnode)
 {
         struct symbol *sym = node->sym;
+        u64 left, right;
 
         if (cnode->ms.sym && sym &&
-            callchain_param.key == CCKEY_FUNCTION)
-                return cnode->ms.sym->start - sym->start;
-        else
-                return cnode->ip - node->ip;
+            callchain_param.key == CCKEY_FUNCTION) {
+                left = cnode->ms.sym->start;
+                right = sym->start;
+        } else {
+                left = cnode->ip;
+                right = node->ip;
+        }
+
+        if (left == right)
+                return MATCH_EQ;
+
+        return left > right ? MATCH_GT : MATCH_LT;
 }
 
 /*
@@ -479,7 +508,7 @@ static s64 match_chain(struct callchain_cursor_node *node,
  * give a part of its callchain to the created child.
  * Then create another child to host the given callchain of new branch
  */
-static void
+static int
 split_add_child(struct callchain_node *parent,
                 struct callchain_cursor *cursor,
                 struct callchain_list *to_split,
@@ -491,6 +520,8 @@ split_add_child(struct callchain_node *parent,
 
         /* split */
         new = create_child(parent, true);
+        if (new == NULL)
+                return -1;
 
         /* split the callchain and move a part to the new child */
         old_tail = parent->val.prev;
@@ -524,6 +555,8 @@ split_add_child(struct callchain_node *parent,
 
                 node = callchain_cursor_current(cursor);
                 new = add_child(parent, cursor, period);
+                if (new == NULL)
+                        return -1;
 
                 /*
                  * This is second child since we moved parent's children
@@ -534,7 +567,7 @@ split_add_child(struct callchain_node *parent,
                 cnode = list_first_entry(&first->val, struct callchain_list,
                                          list);
 
-                if (match_chain(node, cnode) < 0)
+                if (match_chain(node, cnode) == MATCH_LT)
                         pp = &p->rb_left;
                 else
                         pp = &p->rb_right;
@@ -545,14 +578,15 @@ split_add_child(struct callchain_node *parent,
                 parent->hit = period;
                 parent->count = 1;
         }
+        return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
              struct callchain_cursor *cursor,
              u64 period);
 
-static void
+static int
 append_chain_children(struct callchain_node *root,
                       struct callchain_cursor *cursor,
                       u64 period)
@@ -564,36 +598,42 @@ append_chain_children(struct callchain_node *root,
 
         node = callchain_cursor_current(cursor);
         if (!node)
-                return;
+                return -1;
 
         /* lookup in childrens */
         while (*p) {
-                s64 ret;
+                enum match_result ret;
 
                 parent = *p;
                 rnode = rb_entry(parent, struct callchain_node, rb_node_in);
 
                 /* If at least first entry matches, rely to children */
                 ret = append_chain(rnode, cursor, period);
-                if (ret == 0)
+                if (ret == MATCH_EQ)
                         goto inc_children_hit;
+                if (ret == MATCH_ERROR)
+                        return -1;
 
-                if (ret < 0)
+                if (ret == MATCH_LT)
                         p = &parent->rb_left;
                 else
                         p = &parent->rb_right;
         }
         /* nothing in children, add to the current node */
         rnode = add_child(root, cursor, period);
+        if (rnode == NULL)
+                return -1;
+
         rb_link_node(&rnode->rb_node_in, parent, p);
         rb_insert_color(&rnode->rb_node_in, &root->rb_root_in);
 
 inc_children_hit:
         root->children_hit += period;
         root->children_count++;
+        return 0;
 }
 
-static int
+static enum match_result
 append_chain(struct callchain_node *root,
              struct callchain_cursor *cursor,
              u64 period)
@@ -602,7 +642,7 @@ append_chain(struct callchain_node *root,
         u64 start = cursor->pos;
         bool found = false;
         u64 matches;
-        int cmp = 0;
+        enum match_result cmp = MATCH_ERROR;
 
         /*
          * Lookup in the current node
@@ -618,7 +658,7 @@ append_chain(struct callchain_node *root,
                         break;
 
                 cmp = match_chain(node, cnode);
-                if (cmp)
+                if (cmp != MATCH_EQ)
                         break;
 
                 found = true;
@@ -628,7 +668,7 @@ append_chain(struct callchain_node *root,
 
         /* matches not, relay no the parent */
         if (!found) {
-                WARN_ONCE(!cmp, "Chain comparison error\n");
+                WARN_ONCE(cmp == MATCH_ERROR, "Chain comparison error\n");
                 return cmp;
         }
 
@@ -636,21 +676,25 @@ append_chain(struct callchain_node *root,
 
         /* we match only a part of the node. Split it and add the new chain */
         if (matches < root->val_nr) {
-                split_add_child(root, cursor, cnode, start, matches, period);
-                return 0;
+                if (split_add_child(root, cursor, cnode, start, matches,
+                                    period) < 0)
+                        return MATCH_ERROR;
+
+                return MATCH_EQ;
         }
 
         /* we match 100% of the path, increment the hit */
         if (matches == root->val_nr && cursor->pos == cursor->nr) {
                 root->hit += period;
                 root->count++;
-                return 0;
+                return MATCH_EQ;
         }
 
         /* We match the node and still have a part remaining */
-        append_chain_children(root, cursor, period);
+        if (append_chain_children(root, cursor, period) < 0)
+                return MATCH_ERROR;
 
-        return 0;
+        return MATCH_EQ;
 }
 
 int callchain_append(struct callchain_root *root,
@@ -662,7 +706,8 @@ int callchain_append(struct callchain_root *root,
 
         callchain_cursor_commit(cursor);
 
-        append_chain_children(&root->node, cursor, period);
+        if (append_chain_children(&root->node, cursor, period) < 0)
+                return -1;
 
         if (cursor->nr > root->max_depth)
                 root->max_depth = cursor->nr;
@@ -690,7 +735,8 @@ merge_chain_branch(struct callchain_cursor *cursor,
 
         if (src->hit) {
                 callchain_cursor_commit(cursor);
-                append_chain_children(dst, cursor, src->hit);
+                if (append_chain_children(dst, cursor, src->hit) < 0)
+                        return -1;
         }
 
         n = rb_first(&src->rb_root_in);
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index e5fb88bab9e1..43e84aa27e4a 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -32,14 +32,15 @@ int perf_config_colorbool(const char *var, const char *value, int stdout_is_tty)
         return 0;
 }
 
-int perf_color_default_config(const char *var, const char *value, void *cb)
+int perf_color_default_config(const char *var, const char *value,
+                              void *cb __maybe_unused)
 {
         if (!strcmp(var, "color.ui")) {
                 perf_use_color_default = perf_config_colorbool(var, value, -1);
                 return 0;
         }
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 static int __color_vsnprintf(char *bf, size_t size, const char *color,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index d3e12e30e1d5..4e727635476e 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -26,7 +26,7 @@ static const char *config_file_name;
 static int config_linenr;
 static int config_file_eof;
 
-static const char *config_exclusive_filename;
+const char *config_exclusive_filename;
 
 static int get_next_char(void)
 {
@@ -434,7 +434,7 @@ static int perf_config_from_file(config_fn_t fn, const char *filename, void *dat
         return ret;
 }
 
-static const char *perf_etc_perfconfig(void)
+const char *perf_etc_perfconfig(void)
 {
         static const char *system_wide;
         if (!system_wide)
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index fa935093a599..9bcf2bed3a6d 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -8,6 +8,10 @@
 #include <linux/bitmap.h>
 #include "asm/bug.h"
 
+static int max_cpu_num;
+static int max_node_num;
+static int *cpunode_map;
+
 static struct cpu_map *cpu_map__default_new(void)
 {
         struct cpu_map *cpus;
@@ -486,6 +490,32 @@ out:
                 pr_err("Failed to read max nodes, using default of %d\n", max_node_num);
 }
 
+int cpu__max_node(void)
+{
+        if (unlikely(!max_node_num))
+                set_max_node_num();
+
+        return max_node_num;
+}
+
+int cpu__max_cpu(void)
+{
+        if (unlikely(!max_cpu_num))
+                set_max_cpu_num();
+
+        return max_cpu_num;
+}
+
+int cpu__get_node(int cpu)
+{
+        if (unlikely(cpunode_map == NULL)) {
+                pr_debug("cpu_map not initialized\n");
+                return -1;
+        }
+
+        return cpunode_map[cpu];
+}
+
 static int init_cpunode_map(void)
 {
         int i;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 71c41b9efabb..81a2562aaa2b 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -57,37 +57,11 @@ 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];
-}
+int cpu__max_node(void);
+int cpu__max_cpu(void);
+int cpu__get_node(int cpu);
 
 int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
                        int (*f)(struct cpu_map *map, int cpu, void *data),
diff --git a/tools/perf/util/ctype.c b/tools/perf/util/ctype.c
index aada3ac5e891..d4a5a21c2a7e 100644
--- a/tools/perf/util/ctype.c
+++ b/tools/perf/util/ctype.c
@@ -32,8 +32,17 @@ unsigned char sane_ctype[256] = {
 
 const char *graph_line =
         "_____________________________________________________________________"
+        "_____________________________________________________________________"
         "_____________________________________________________________________";
 const char *graph_dotted_line =
         "---------------------------------------------------------------------"
         "---------------------------------------------------------------------"
         "---------------------------------------------------------------------";
+const char *spaces =
+        "                                                                     "
+        "                                                                     "
+        "                                                                     ";
+const char *dots =
+        "....................................................................."
+        "....................................................................."
+        ".....................................................................";
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 34cd1e4039d3..811af89ce0bb 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -352,6 +352,84 @@ static int add_tracepoint_values(struct ctf_writer *cw,
         return ret;
 }
 
+static int
+add_bpf_output_values(struct bt_ctf_event_class *event_class,
+                      struct bt_ctf_event *event,
+                      struct perf_sample *sample)
+{
+        struct bt_ctf_field_type *len_type, *seq_type;
+        struct bt_ctf_field *len_field, *seq_field;
+        unsigned int raw_size = sample->raw_size;
+        unsigned int nr_elements = raw_size / sizeof(u32);
+        unsigned int i;
+        int ret;
+
+        if (nr_elements * sizeof(u32) != raw_size)
+                pr_warning("Incorrect raw_size (%u) in bpf output event, skip %lu bytes\n",
+                           raw_size, nr_elements * sizeof(u32) - raw_size);
+
+        len_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_len");
+        len_field = bt_ctf_field_create(len_type);
+        if (!len_field) {
+                pr_err("failed to create 'raw_len' for bpf output event\n");
+                ret = -1;
+                goto put_len_type;
+        }
+
+        ret = bt_ctf_field_unsigned_integer_set_value(len_field, nr_elements);
+        if (ret) {
+                pr_err("failed to set field value for raw_len\n");
+                goto put_len_field;
+        }
+        ret = bt_ctf_event_set_payload(event, "raw_len", len_field);
+        if (ret) {
+                pr_err("failed to set payload to raw_len\n");
+                goto put_len_field;
+        }
+
+        seq_type = bt_ctf_event_class_get_field_by_name(event_class, "raw_data");
+        seq_field = bt_ctf_field_create(seq_type);
+        if (!seq_field) {
+                pr_err("failed to create 'raw_data' for bpf output event\n");
+                ret = -1;
+                goto put_seq_type;
+        }
+
+        ret = bt_ctf_field_sequence_set_length(seq_field, len_field);
+        if (ret) {
+                pr_err("failed to set length of 'raw_data'\n");
+                goto put_seq_field;
+        }
+
+        for (i = 0; i < nr_elements; i++) {
+                struct bt_ctf_field *elem_field =
+                        bt_ctf_field_sequence_get_field(seq_field, i);
+
+                ret = bt_ctf_field_unsigned_integer_set_value(elem_field,
+                                ((u32 *)(sample->raw_data))[i]);
+
+                bt_ctf_field_put(elem_field);
+                if (ret) {
+                        pr_err("failed to set raw_data[%d]\n", i);
+                        goto put_seq_field;
+                }
+        }
+
+        ret = bt_ctf_event_set_payload(event, "raw_data", seq_field);
+        if (ret)
+                pr_err("failed to set payload for raw_data\n");
+
+put_seq_field:
+        bt_ctf_field_put(seq_field);
+put_seq_type:
+        bt_ctf_field_type_put(seq_type);
+put_len_field:
+        bt_ctf_field_put(len_field);
+put_len_type:
+        bt_ctf_field_type_put(len_type);
+        return ret;
+}
+
 static int add_generic_values(struct ctf_writer *cw,
                               struct bt_ctf_event *event,
                               struct perf_evsel *evsel,
@@ -597,6 +675,12 @@ static int process_sample_event(struct perf_tool *tool,
                         return -1;
         }
 
+        if (perf_evsel__is_bpf_output(evsel)) {
+                ret = add_bpf_output_values(event_class, event, sample);
+                if (ret)
+                        return -1;
+        }
+
         cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
         if (cs) {
                 if (is_flush_needed(cs))
@@ -744,6 +828,25 @@ static int add_tracepoint_types(struct ctf_writer *cw,
         return ret;
 }
 
+static int add_bpf_output_types(struct ctf_writer *cw,
+                                struct bt_ctf_event_class *class)
+{
+        struct bt_ctf_field_type *len_type = cw->data.u32;
+        struct bt_ctf_field_type *seq_base_type = cw->data.u32_hex;
+        struct bt_ctf_field_type *seq_type;
+        int ret;
+
+        ret = bt_ctf_event_class_add_field(class, len_type, "raw_len");
+        if (ret)
+                return ret;
+
+        seq_type = bt_ctf_field_type_sequence_create(seq_base_type, "raw_len");
+        if (!seq_type)
+                return -1;
+
+        return bt_ctf_event_class_add_field(class, seq_type, "raw_data");
+}
+
 static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
                              struct bt_ctf_event_class *event_class)
 {
@@ -755,7 +858,8 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
          *                              ctf event header
          *   PERF_SAMPLE_READ         - TODO
          *   PERF_SAMPLE_CALLCHAIN    - TODO
-         *   PERF_SAMPLE_RAW          - tracepoint fields are handled separately
+         *   PERF_SAMPLE_RAW          - tracepoint fields and BPF output
+         *                              are handled separately
          *   PERF_SAMPLE_BRANCH_STACK - TODO
          *   PERF_SAMPLE_REGS_USER    - TODO
          *   PERF_SAMPLE_STACK_USER   - TODO
@@ -824,6 +928,12 @@ static int add_event(struct ctf_writer *cw, struct perf_evsel *evsel)
                         goto err;
         }
 
+        if (perf_evsel__is_bpf_output(evsel)) {
+                ret = add_bpf_output_types(cw, event_class);
+                if (ret)
+                        goto err;
+        }
+
         ret = bt_ctf_stream_class_add_event_class(cw->stream_class, event_class);
         if (ret) {
                 pr("Failed to add event class into stream.\n");
@@ -858,6 +968,23 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
         return 0;
 }
 
+static void cleanup_events(struct perf_session *session)
+{
+        struct perf_evlist *evlist = session->evlist;
+        struct perf_evsel *evsel;
+
+        evlist__for_each(evlist, evsel) {
+                struct evsel_priv *priv;
+
+                priv = evsel->priv;
+                bt_ctf_event_class_put(priv->event_class);
+                zfree(&evsel->priv);
+        }
+
+        perf_evlist__delete(evlist);
+        session->evlist = NULL;
+}
+
 static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
 {
         struct ctf_stream **stream;
@@ -953,6 +1080,12 @@ static struct bt_ctf_field_type *create_int_type(int size, bool sign, bool hex)
             bt_ctf_field_type_integer_set_base(type, BT_CTF_INTEGER_BASE_HEXADECIMAL))
                 goto err;
 
+#if __BYTE_ORDER == __BIG_ENDIAN
+        bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_BIG_ENDIAN);
+#else
+        bt_ctf_field_type_set_byte_order(type, BT_CTF_BYTE_ORDER_LITTLE_ENDIAN);
+#endif
+
         pr2("Created type: INTEGER %d-bit %ssigned %s\n",
             size, sign ? "un" : "", hex ? "hex" : "");
         return type;
@@ -1100,7 +1233,7 @@ static int convert__config(const char *var, const char *value, void *cb)
                 return 0;
         }
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
@@ -1171,6 +1304,7 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
                 (double) c.events_size / 1024.0 / 1024.0,
                 c.events_count);
 
+        cleanup_events(session);
         perf_session__delete(session);
         ctf_writer__cleanup(cw);
 
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 86d9c7302598..8c4212abd19b 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <stdarg.h>
 #include <stdio.h>
+#include <api/debug.h>
 
 #include "cache.h"
 #include "color.h"
@@ -22,7 +23,7 @@ int debug_ordered_events;
 static int redirect_to_stderr;
 int debug_data_convert;
 
-static int _eprintf(int level, int var, const char *fmt, va_list args)
+int veprintf(int level, int var, const char *fmt, va_list args)
 {
         int ret = 0;
 
@@ -36,24 +37,19 @@ static int _eprintf(int level, int var, const char *fmt, va_list args)
         return ret;
 }
 
-int veprintf(int level, int var, const char *fmt, va_list args)
-{
-        return _eprintf(level, var, fmt, args);
-}
-
 int eprintf(int level, int var, const char *fmt, ...)
 {
         va_list args;
         int ret;
 
         va_start(args, fmt);
-        ret = _eprintf(level, var, fmt, args);
+        ret = veprintf(level, var, fmt, args);
         va_end(args);
 
         return ret;
 }
 
-static int __eprintf_time(u64 t, const char *fmt, va_list args)
+static int veprintf_time(u64 t, const char *fmt, va_list args)
 {
         int ret = 0;
         u64 secs, usecs, nsecs = t;
@@ -75,7 +71,7 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
 
         if (var >= level) {
                 va_start(args, fmt);
-                ret = __eprintf_time(t, fmt, args);
+                ret = veprintf_time(t, fmt, args);
                 va_end(args);
         }
 
@@ -91,7 +87,7 @@ void pr_stat(const char *fmt, ...)
         va_list args;
 
         va_start(args, fmt);
-        _eprintf(1, verbose, fmt, args);
+        veprintf(1, verbose, fmt, args);
         va_end(args);
         eprintf(1, verbose, "\n");
 }
@@ -110,40 +106,61 @@ int dump_printf(const char *fmt, ...)
         return ret;
 }
 
+static void trace_event_printer(enum binary_printer_ops op,
+                                unsigned int val, void *extra)
+{
+        const char *color = PERF_COLOR_BLUE;
+        union perf_event *event = (union perf_event *)extra;
+        unsigned char ch = (unsigned char)val;
+
+        switch (op) {
+        case BINARY_PRINT_DATA_BEGIN:
+                printf(".");
+                color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
+                                event->header.size);
+                break;
+        case BINARY_PRINT_LINE_BEGIN:
+                printf(".");
+                break;
+        case BINARY_PRINT_ADDR:
+                color_fprintf(stdout, color, "  %04x: ", val);
+                break;
+        case BINARY_PRINT_NUM_DATA:
+                color_fprintf(stdout, color, " %02x", val);
+                break;
+        case BINARY_PRINT_NUM_PAD:
+                color_fprintf(stdout, color, "   ");
+                break;
+        case BINARY_PRINT_SEP:
+                color_fprintf(stdout, color, "  ");
+                break;
+        case BINARY_PRINT_CHAR_DATA:
+                color_fprintf(stdout, color, "%c",
+                              isprint(ch) ? ch : '.');
+                break;
+        case BINARY_PRINT_CHAR_PAD:
+                color_fprintf(stdout, color, " ");
+                break;
+        case BINARY_PRINT_LINE_END:
+                color_fprintf(stdout, color, "\n");
+                break;
+        case BINARY_PRINT_DATA_END:
+                printf("\n");
+                break;
+        default:
+                break;
+        }
+}
+
 void trace_event(union perf_event *event)
 {
         unsigned char *raw_event = (void *)event;
-        const char *color = PERF_COLOR_BLUE;
-        int i, j;
 
         if (!dump_trace)
                 return;
 
-        printf(".");
-        color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-                      event->header.size);
-
-        for (i = 0; i < event->header.size; i++) {
-                if ((i & 15) == 0) {
-                        printf(".");
-                        color_fprintf(stdout, color, "  %04x: ", i);
-                }
-
-                color_fprintf(stdout, color, " %02x", raw_event[i]);
-
-                if (((i & 15) == 15) || i == event->header.size-1) {
-                        color_fprintf(stdout, color, "  ");
-                        for (j = 0; j < 15-(i & 15); j++)
-                                color_fprintf(stdout, color, "   ");
-                        for (j = i & ~15; j <= i; j++) {
-                                color_fprintf(stdout, color, "%c",
-                                              isprint(raw_event[j]) ?
-                                              raw_event[j] : '.');
-                        }
-                        color_fprintf(stdout, color, "\n");
-                }
-        }
-        printf(".\n");
+        print_binary(raw_event, event->header.size, 16,
+                     trace_event_printer, event);
 }
 
 static struct debug_variable {
@@ -192,3 +209,23 @@ int perf_debug_option(const char *str)
         free(s);
         return 0;
 }
+
+#define DEBUG_WRAPPER(__n, __l)                         \
+static int pr_ ## __n ## _wrapper(const char *fmt, ...) \
+{                                                       \
+        va_list args;                                   \
+        int ret;                                        \
+                                                        \
+        va_start(args, fmt);                            \
+        ret = veprintf(__l, verbose, fmt, args);        \
+        va_end(args);                                   \
+        return ret;                                     \
+}
+
+DEBUG_WRAPPER(warning, 0);
+DEBUG_WRAPPER(debug, 1);
+
+void perf_debug_setup(void)
+{
+        libapi_set_print(pr_warning_wrapper, pr_warning_wrapper, pr_debug_wrapper);
+}
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 8b9a088c32ab..14bafda79eda 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -53,5 +53,6 @@ int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__(
 int veprintf(int level, int var, const char *fmt, va_list args);
 
 int perf_debug_option(const char *str);
+void perf_debug_setup(void);
 
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/demangle-java.c b/tools/perf/util/demangle-java.c
new file mode 100644
index 000000000000..3e6062ab2cdd
--- /dev/null
+++ b/tools/perf/util/demangle-java.c
@@ -0,0 +1,199 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <string.h>
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+
+#include "demangle-java.h"
+
+enum {
+        MODE_PREFIX = 0,
+        MODE_CLASS  = 1,
+        MODE_FUNC   = 2,
+        MODE_TYPE   = 3,
+        MODE_CTYPE  = 3, /* class arg */
+};
+
+#define BASE_ENT(c, n)  [c - 'A']=n
+static const char *base_types['Z' - 'A' + 1] = {
+        BASE_ENT('B', "byte" ),
+        BASE_ENT('C', "char" ),
+        BASE_ENT('D', "double" ),
+        BASE_ENT('F', "float" ),
+        BASE_ENT('I', "int" ),
+        BASE_ENT('J', "long" ),
+        BASE_ENT('S', "short" ),
+        BASE_ENT('Z', "bool" ),
+};
+
+/*
+ * demangle Java symbol between str and end positions and stores
+ * up to maxlen characters into buf. The parser starts in mode.
+ *
+ * Use MODE_PREFIX to process entire prototype till end position
+ * Use MODE_TYPE to process return type if str starts on return type char
+ *
+ *  Return:
+ *      success: buf
+ *      error  : NULL
+ */
+static char *
+__demangle_java_sym(const char *str, const char *end, char *buf, int maxlen, int mode)
+{
+        int rlen = 0;
+        int array = 0;
+        int narg = 0;
+        const char *q;
+
+        if (!end)
+                end = str + strlen(str);
+
+        for (q = str; q != end; q++) {
+
+                if (rlen == (maxlen - 1))
+                        break;
+
+                switch (*q) {
+                case 'L':
+                        if (mode == MODE_PREFIX || mode == MODE_CTYPE) {
+                                if (mode == MODE_CTYPE) {
+                                        if (narg)
+                                                rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+                                        narg++;
+                                }
+                                rlen += scnprintf(buf + rlen, maxlen - rlen, "class ");
+                                if (mode == MODE_PREFIX)
+                                        mode = MODE_CLASS;
+                        } else
+                                buf[rlen++] = *q;
+                        break;
+                case 'B':
+                case 'C':
+                case 'D':
+                case 'F':
+                case 'I':
+                case 'J':
+                case 'S':
+                case 'Z':
+                        if (mode == MODE_TYPE) {
+                                if (narg)
+                                        rlen += scnprintf(buf + rlen, maxlen - rlen, ", ");
+                                rlen += scnprintf(buf + rlen, maxlen - rlen, "%s", base_types[*q - 'A']);
+                                while (array--)
+                                        rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+                                array = 0;
+                                narg++;
+                        } else
+                                buf[rlen++] = *q;
+                        break;
+                case 'V':
+                        if (mode == MODE_TYPE) {
+                                rlen += scnprintf(buf + rlen, maxlen - rlen, "void");
+                                while (array--)
+                                        rlen += scnprintf(buf + rlen, maxlen - rlen, "[]");
+                                array = 0;
+                        } else
+                                buf[rlen++] = *q;
+                        break;
+                case '[':
+                        if (mode != MODE_TYPE)
+                                goto error;
+                        array++;
+                        break;
+                case '(':
+                        if (mode != MODE_FUNC)
+                                goto error;
+                        buf[rlen++] = *q;
+                        mode = MODE_TYPE;
+                        break;
+                case ')':
+                        if (mode != MODE_TYPE)
+                                goto error;
+                        buf[rlen++] = *q;
+                        narg = 0;
+                        break;
+                case ';':
+                        if (mode != MODE_CLASS && mode != MODE_CTYPE)
+                                goto error;
+                        /* safe because at least one other char to process */
+                        if (isalpha(*(q + 1)))
+                                rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+                        if (mode == MODE_CLASS)
+                                mode = MODE_FUNC;
+                        else if (mode == MODE_CTYPE)
+                                mode = MODE_TYPE;
+                        break;
+                case '/':
+                        if (mode != MODE_CLASS && mode != MODE_CTYPE)
+                                goto error;
+                        rlen += scnprintf(buf + rlen, maxlen - rlen, ".");
+                        break;
+                default :
+                        buf[rlen++] = *q;
+                }
+        }
+        buf[rlen] = '\0';
+        return buf;
+error:
+        return NULL;
+}
+
+/*
+ * Demangle Java function signature (openJDK, not GCJ)
+ * input:
+ *      str: string to parse. String is not modified
+ *    flags: comobination of JAVA_DEMANGLE_* flags to modify demangling
+ * return:
+ *      if input can be demangled, then a newly allocated string is returned.
+ *      if input cannot be demangled, then NULL is returned
+ *
+ * Note: caller is responsible for freeing demangled string
+ */
+char *
+java_demangle_sym(const char *str, int flags)
+{
+        char *buf, *ptr;
+        char *p;
+        size_t len, l1 = 0;
+
+        if (!str)
+                return NULL;
+
+        /* find start of retunr type */
+        p = strrchr(str, ')');
+        if (!p)
+                return NULL;
+
+        /*
+         * expansion factor estimated to 3x
+         */
+        len = strlen(str) * 3 + 1;
+        buf = malloc(len);
+        if (!buf)
+                return NULL;
+
+        buf[0] = '\0';
+        if (!(flags & JAVA_DEMANGLE_NORET)) {
+                /*
+                 * get return type first
+                 */
+                ptr = __demangle_java_sym(p + 1, NULL, buf, len, MODE_TYPE);
+                if (!ptr)
+                        goto error;
+
+                /* add space between return type and function prototype */
+                l1 = strlen(buf);
+                buf[l1++] = ' ';
+        }
+
+        /* process function up to return type */
+        ptr = __demangle_java_sym(str, p + 1, buf + l1, len - l1, MODE_PREFIX);
+        if (!ptr)
+                goto error;
+
+        return buf;
+error:
+        free(buf);
+        return NULL;
+}
diff --git a/tools/perf/util/demangle-java.h b/tools/perf/util/demangle-java.h
new file mode 100644
index 000000000000..a981c1f968fe
--- /dev/null
+++ b/tools/perf/util/demangle-java.h
@@ -0,0 +1,10 @@
+#ifndef __PERF_DEMANGLE_JAVA
+#define __PERF_DEMANGLE_JAVA 1
+/*
+ * demangle function flags
+ */
+#define JAVA_DEMANGLE_NORET     0x1 /* do not process return type */
+
+char * java_demangle_sym(const char *str, int flags);
+
+#endif /* __PERF_DEMANGLE_JAVA */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index e8e9a9dbf5e3..8e6395439ca0 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -52,6 +52,11 @@ int dso__read_binary_type_filename(const struct dso *dso,
                         debuglink--;
                 if (*debuglink == '/')
                         debuglink++;
+
+                ret = -1;
+                if (!is_regular_file(filename))
+                        break;
+
                 ret = filename__read_debuglink(filename, debuglink,
                                                size - (debuglink - filename));
                 }
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 7dd5939dea2e..49a11d9d8b8f 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -6,6 +6,8 @@ struct perf_env perf_env;
 
 void perf_env__exit(struct perf_env *env)
 {
+        int i;
+
         zfree(&env->hostname);
         zfree(&env->os_release);
         zfree(&env->version);
@@ -19,6 +21,10 @@ void perf_env__exit(struct perf_env *env)
         zfree(&env->numa_nodes);
         zfree(&env->pmu_mappings);
         zfree(&env->cpu);
+
+        for (i = 0; i < env->caches_cnt; i++)
+                cpu_cache_level__free(&env->caches[i]);
+        zfree(&env->caches);
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
@@ -75,3 +81,10 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
         env->nr_cpus_avail = nr_cpus;
         return 0;
 }
+
+void cpu_cache_level__free(struct cpu_cache_level *cache)
+{
+        free(cache->type);
+        free(cache->map);
+        free(cache->size);
+}
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 0132b9557c02..56cffb60a0b4 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -1,11 +1,23 @@
 #ifndef __PERF_ENV_H
 #define __PERF_ENV_H
 
+#include <linux/types.h>
+
 struct cpu_topology_map {
         int     socket_id;
         int     core_id;
 };
 
+struct cpu_cache_level {
+        u32     level;
+        u32     line_size;
+        u32     sets;
+        u32     ways;
+        char    *type;
+        char    *size;
+        char    *map;
+};
+
 struct perf_env {
         char                    *hostname;
         char                    *os_release;
@@ -31,6 +43,8 @@ struct perf_env {
         char                    *numa_nodes;
         char                    *pmu_mappings;
         struct cpu_topology_map *cpu;
+        struct cpu_cache_level  *caches;
+        int                      caches_cnt;
 };
 
 extern struct perf_env perf_env;
@@ -41,4 +55,5 @@ int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[]);
 
 int perf_env__read_cpu_topology_map(struct perf_env *env);
 
+void cpu_cache_level__free(struct cpu_cache_level *cache);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 85155e91b61b..7bad5c3fa7b7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -282,7 +282,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 strcpy(execname, "");
 
                 /* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-                n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
+                n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %[^\n]\n",
                        &event->mmap2.start, &event->mmap2.len, prot,
                        &event->mmap2.pgoff, &event->mmap2.maj,
                        &event->mmap2.min,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d81f13de2476..86a03836a83f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1181,12 +1181,12 @@ void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
          */
         if (cpus != evlist->cpus) {
                 cpu_map__put(evlist->cpus);
-                evlist->cpus = cpus;
+                evlist->cpus = cpu_map__get(cpus);
         }
 
         if (threads != evlist->threads) {
                 thread_map__put(evlist->threads);
-                evlist->threads = threads;
+                evlist->threads = thread_map__get(threads);
         }
 
         perf_evlist__propagate_maps(evlist);
@@ -1223,6 +1223,9 @@ int perf_evlist__set_filter(struct perf_evlist *evlist, const char *filter)
         int err = 0;
 
         evlist__for_each(evlist, evsel) {
+                if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
+                        continue;
+
                 err = perf_evsel__set_filter(evsel, filter);
                 if (err)
                         break;
@@ -1624,7 +1627,7 @@ size_t perf_evlist__fprintf(struct perf_evlist *evlist, FILE *fp)
         return printed + fprintf(fp, "\n");
 }
 
-int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
+int perf_evlist__strerror_open(struct perf_evlist *evlist,
                                int err, char *buf, size_t size)
 {
         int printed, value;
@@ -1652,7 +1655,25 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
                                     "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
                                     "Hint:\tThe current value is %d.", value);
                 break;
+        case EINVAL: {
+                struct perf_evsel *first = perf_evlist__first(evlist);
+                int max_freq;
+
+                if (sysctl__read_int("kernel/perf_event_max_sample_rate", &max_freq) < 0)
+                        goto out_default;
+
+                if (first->attr.sample_freq < (u64)max_freq)
+                        goto out_default;
+
+                printed = scnprintf(buf, size,
+                                    "Error:\t%s.\n"
+                                    "Hint:\tCheck /proc/sys/kernel/perf_event_max_sample_rate.\n"
+                                    "Hint:\tThe current value is %d and %" PRIu64 " is being requested.",
+                                    emsg, max_freq, first->attr.sample_freq);
+                break;
+        }
         default:
+out_default:
                 scnprintf(buf, size, "%s", emsg);
                 break;
         }
@@ -1723,3 +1744,19 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 
         tracking_evsel->tracking = true;
 }
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist,
+                               const char *str)
+{
+        struct perf_evsel *evsel;
+
+        evlist__for_each(evlist, evsel) {
+                if (!evsel->name)
+                        continue;
+                if (strcmp(str, evsel->name) == 0)
+                        return evsel;
+        }
+
+        return NULL;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 7c4d9a206776..a0d15221db6e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -294,4 +294,7 @@ void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
                                      struct perf_evsel *tracking_evsel);
 
 void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
+
+struct perf_evsel *
+perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cdbaf9b51e42..0902fe418754 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
         if (evsel != NULL)
                 perf_evsel__init(evsel, attr, idx);
 
+        if (perf_evsel__is_bpf_output(evsel)) {
+                evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+                evsel->attr.sample_period = 1;
+        }
+
         return evsel;
 }
 
@@ -898,6 +903,16 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
         if (evsel->precise_max)
                 perf_event_attr__set_max_precise_ip(attr);
 
+        if (opts->all_user) {
+                attr->exclude_kernel = 1;
+                attr->exclude_user   = 0;
+        }
+
+        if (opts->all_kernel) {
+                attr->exclude_kernel = 0;
+                attr->exclude_user   = 1;
+        }
+
         /*
          * Apply event specific term settings,
          * it overloads any global configuration.
@@ -2362,12 +2377,15 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
         case EPERM:
         case EACCES:
                 return scnprintf(msg, size,
-                 "You may not have permission to collect %sstats.\n"
-                 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
-                 " -1 - Not paranoid at all\n"
-                 "  0 - Disallow raw tracepoint access for unpriv\n"
-                 "  1 - Disallow cpu events for unpriv\n"
-                 "  2 - Disallow kernel profiling for unpriv",
+                 "You may not have permission to collect %sstats.\n\n"
+                 "Consider tweaking /proc/sys/kernel/perf_event_paranoid,\n"
+                 "which controls use of the performance events system by\n"
+                 "unprivileged users (without CAP_SYS_ADMIN).\n\n"
+                 "The default value is 1:\n\n"
+                 "  -1: Allow use of (almost) all events by all users\n"
+                 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
+                 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
+                 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
                                  target->system_wide ? "system-wide " : "");
         case ENOENT:
                 return scnprintf(msg, size, "The %s event is not supported.",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8e75434bd01c..501ea6e565f1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -93,10 +93,8 @@ struct perf_evsel {
         const char              *unit;
         struct event_format     *tp_format;
         off_t                   id_offset;
-        union {
-                void            *priv;
-                u64             db_id;
-        };
+        void                    *priv;
+        u64                     db_id;
         struct cgroup_sel       *cgrp;
         void                    *handler;
         struct cpu_map          *cpus;
@@ -364,6 +362,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+        struct perf_event_attr *attr = &evsel->attr;
+
+        return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+                (attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
         bool freq;
         bool verbose;
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
new file mode 100644
index 000000000000..c1ef805c6a8f
--- /dev/null
+++ b/tools/perf/util/genelf.c
@@ -0,0 +1,449 @@
+/*
+ * genelf.c
+ * Copyright (C) 2014, Google, Inc
+ *
+ * Contributed by:
+ *      Stephane Eranian <eranian@gmail.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define JVMTI
+
+#define BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef HAVE_LIBCRYPTO
+
+#define BUILD_ID_MD5
+#undef BUILD_ID_SHA     /* does not seem to work well when linked with Java */
+#undef BUILD_ID_URANDOM /* different uuid for each run */
+
+#ifdef BUILD_ID_SHA
+#include <openssl/sha.h>
+#endif
+
+#ifdef BUILD_ID_MD5
+#include <openssl/md5.h>
+#endif
+#endif
+
+
+typedef struct {
+  unsigned int namesz;  /* Size of entry's owner string */
+  unsigned int descsz;  /* Size of the note descriptor */
+  unsigned int type;    /* Interpretation of the descriptor */
+  char         name[0]; /* Start of the name+desc data */
+} Elf_Note;
+
+struct options {
+        char *output;
+        int fd;
+};
+
+static char shd_string_table[] = {
+        0,
+        '.', 't', 'e', 'x', 't', 0,                     /*  1 */
+        '.', 's', 'h', 's', 't', 'r', 't', 'a', 'b', 0, /*  7 */
+        '.', 's', 'y', 'm', 't', 'a', 'b', 0,           /* 17 */
+        '.', 's', 't', 'r', 't', 'a', 'b', 0,           /* 25 */
+        '.', 'n', 'o', 't', 'e', '.', 'g', 'n', 'u', '.', 'b', 'u', 'i', 'l', 'd', '-', 'i', 'd', 0, /* 33 */
+        '.', 'd', 'e', 'b', 'u', 'g', '_', 'l', 'i', 'n', 'e', 0, /* 52 */
+        '.', 'd', 'e', 'b', 'u', 'g', '_', 'i', 'n', 'f', 'o', 0, /* 64 */
+        '.', 'd', 'e', 'b', 'u', 'g', '_', 'a', 'b', 'b', 'r', 'e', 'v', 0, /* 76 */
+};
+
+static struct buildid_note {
+        Elf_Note desc;          /* descsz: size of build-id, must be multiple of 4 */
+        char     name[4];       /* GNU\0 */
+        char     build_id[20];
+} bnote;
+
+static Elf_Sym symtab[]={
+        /* symbol 0 MUST be the undefined symbol */
+        { .st_name  = 0, /* index in sym_string table */
+          .st_info  = ELF_ST_TYPE(STT_NOTYPE),
+          .st_shndx = 0, /* for now */
+          .st_value = 0x0,
+          .st_other = ELF_ST_VIS(STV_DEFAULT),
+          .st_size  = 0,
+        },
+        { .st_name  = 1, /* index in sym_string table */
+          .st_info  = ELF_ST_BIND(STB_LOCAL) | ELF_ST_TYPE(STT_FUNC),
+          .st_shndx = 1,
+          .st_value = 0, /* for now */
+          .st_other = ELF_ST_VIS(STV_DEFAULT),
+          .st_size  = 0, /* for now */
+        }
+};
+
+#ifdef BUILD_ID_URANDOM
+static void
+gen_build_id(struct buildid_note *note,
+             unsigned long load_addr __maybe_unused,
+             const void *code __maybe_unused,
+             size_t csize __maybe_unused)
+{
+        int fd;
+        size_t sz = sizeof(note->build_id);
+        ssize_t sret;
+
+        fd = open("/dev/urandom", O_RDONLY);
+        if (fd == -1)
+                err(1, "cannot access /dev/urandom for builid");
+
+        sret = read(fd, note->build_id, sz);
+
+        close(fd);
+
+        if (sret != (ssize_t)sz)
+                memset(note->build_id, 0, sz);
+}
+#endif
+
+#ifdef BUILD_ID_SHA
+static void
+gen_build_id(struct buildid_note *note,
+             unsigned long load_addr __maybe_unused,
+             const void *code,
+             size_t csize)
+{
+        if (sizeof(note->build_id) < SHA_DIGEST_LENGTH)
+                errx(1, "build_id too small for SHA1");
+
+        SHA1(code, csize, (unsigned char *)note->build_id);
+}
+#endif
+
+#ifdef BUILD_ID_MD5
+static void
+gen_build_id(struct buildid_note *note, unsigned long load_addr, const void *code, size_t csize)
+{
+        MD5_CTX context;
+
+        if (sizeof(note->build_id) < 16)
+                errx(1, "build_id too small for MD5");
+
+        MD5_Init(&context);
+        MD5_Update(&context, &load_addr, sizeof(load_addr));
+        MD5_Update(&context, code, csize);
+        MD5_Final((unsigned char *)note->build_id, &context);
+}
+#endif
+
+/*
+ * fd: file descriptor open for writing for the output file
+ * load_addr: code load address (could be zero, just used for buildid)
+ * sym: function name (for native code - used as the symbol)
+ * code: the native code
+ * csize: the code size in bytes
+ */
+int
+jit_write_elf(int fd, uint64_t load_addr, const char *sym,
+              const void *code, int csize,
+              void *debug, int nr_debug_entries)
+{
+        Elf *e;
+        Elf_Data *d;
+        Elf_Scn *scn;
+        Elf_Ehdr *ehdr;
+        Elf_Shdr *shdr;
+        char *strsym = NULL;
+        int symlen;
+        int retval = -1;
+
+        if (elf_version(EV_CURRENT) == EV_NONE) {
+                warnx("ELF initialization failed");
+                return -1;
+        }
+
+        e = elf_begin(fd, ELF_C_WRITE, NULL);
+        if (!e) {
+                warnx("elf_begin failed");
+                goto error;
+        }
+
+        /*
+         * setup ELF header
+         */
+        ehdr = elf_newehdr(e);
+        if (!ehdr) {
+                warnx("cannot get ehdr");
+                goto error;
+        }
+
+        ehdr->e_ident[EI_DATA] = GEN_ELF_ENDIAN;
+        ehdr->e_ident[EI_CLASS] = GEN_ELF_CLASS;
+        ehdr->e_machine = GEN_ELF_ARCH;
+        ehdr->e_type = ET_DYN;
+        ehdr->e_entry = GEN_ELF_TEXT_OFFSET;
+        ehdr->e_version = EV_CURRENT;
+        ehdr->e_shstrndx= 2; /* shdr index for section name */
+
+        /*
+         * setup text section
+         */
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                goto error;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                goto error;
+        }
+
+        d->d_align = 16;
+        d->d_off = 0LL;
+        d->d_buf = (void *)code;
+        d->d_type = ELF_T_BYTE;
+        d->d_size = csize;
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                goto error;
+        }
+
+        shdr->sh_name = 1;
+        shdr->sh_type = SHT_PROGBITS;
+        shdr->sh_addr = GEN_ELF_TEXT_OFFSET;
+        shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+        shdr->sh_entsize = 0;
+
+        /*
+         * setup section headers string table
+         */
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                goto error;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                goto error;
+        }
+
+        d->d_align = 1;
+        d->d_off = 0LL;
+        d->d_buf = shd_string_table;
+        d->d_type = ELF_T_BYTE;
+        d->d_size = sizeof(shd_string_table);
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                goto error;
+        }
+
+        shdr->sh_name = 7; /* offset of '.shstrtab' in shd_string_table */
+        shdr->sh_type = SHT_STRTAB;
+        shdr->sh_flags = 0;
+        shdr->sh_entsize = 0;
+
+        /*
+         * setup symtab section
+         */
+        symtab[1].st_size  = csize;
+        symtab[1].st_value = GEN_ELF_TEXT_OFFSET;
+
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                goto error;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                goto error;
+        }
+
+        d->d_align = 8;
+        d->d_off = 0LL;
+        d->d_buf = symtab;
+        d->d_type = ELF_T_SYM;
+        d->d_size = sizeof(symtab);
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                goto error;
+        }
+
+        shdr->sh_name = 17; /* offset of '.symtab' in shd_string_table */
+        shdr->sh_type = SHT_SYMTAB;
+        shdr->sh_flags = 0;
+        shdr->sh_entsize = sizeof(Elf_Sym);
+        shdr->sh_link = 4; /* index of .strtab section */
+
+        /*
+         * setup symbols string table
+         * 2 = 1 for 0 in 1st entry, 1 for the 0 at end of symbol for 2nd entry
+         */
+        symlen = 2 + strlen(sym);
+        strsym = calloc(1, symlen);
+        if (!strsym) {
+                warnx("cannot allocate strsym");
+                goto error;
+        }
+        strcpy(strsym + 1, sym);
+
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                goto error;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                goto error;
+        }
+
+        d->d_align = 1;
+        d->d_off = 0LL;
+        d->d_buf = strsym;
+        d->d_type = ELF_T_BYTE;
+        d->d_size = symlen;
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                goto error;
+        }
+
+        shdr->sh_name = 25; /* offset in shd_string_table */
+        shdr->sh_type = SHT_STRTAB;
+        shdr->sh_flags = 0;
+        shdr->sh_entsize = 0;
+
+        /*
+         * setup build-id section
+         */
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                goto error;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                goto error;
+        }
+
+        /*
+         * build-id generation
+         */
+        gen_build_id(&bnote, load_addr, code, csize);
+        bnote.desc.namesz = sizeof(bnote.name); /* must include 0 termination */
+        bnote.desc.descsz = sizeof(bnote.build_id);
+        bnote.desc.type   = NT_GNU_BUILD_ID;
+        strcpy(bnote.name, "GNU");
+
+        d->d_align = 4;
+        d->d_off = 0LL;
+        d->d_buf = &bnote;
+        d->d_type = ELF_T_BYTE;
+        d->d_size = sizeof(bnote);
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                goto error;
+        }
+
+        shdr->sh_name = 33; /* offset in shd_string_table */
+        shdr->sh_type = SHT_NOTE;
+        shdr->sh_addr = 0x0;
+        shdr->sh_flags = SHF_ALLOC;
+        shdr->sh_size = sizeof(bnote);
+        shdr->sh_entsize = 0;
+
+        if (debug && nr_debug_entries) {
+                retval = jit_add_debug_info(e, load_addr, debug, nr_debug_entries);
+                if (retval)
+                        goto error;
+        } else {
+                if (elf_update(e, ELF_C_WRITE) < 0) {
+                        warnx("elf_update 4 failed");
+                        goto error;
+                }
+        }
+
+        retval = 0;
+error:
+        (void)elf_end(e);
+
+        free(strsym);
+
+
+        return retval;
+}
+
+#ifndef JVMTI
+
+static unsigned char x86_code[] = {
+    0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
+    0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
+    0xCD, 0x80            /* int $0x80 */
+};
+
+static struct options options;
+
+int main(int argc, char **argv)
+{
+        int c, fd, ret;
+
+        while ((c = getopt(argc, argv, "o:h")) != -1) {
+                switch (c) {
+                case 'o':
+                        options.output = optarg;
+                        break;
+                case 'h':
+                        printf("Usage: genelf -o output_file [-h]\n");
+                        return 0;
+                default:
+                        errx(1, "unknown option");
+                }
+        }
+
+        fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666);
+        if (fd == -1)
+                err(1, "cannot create file %s", options.output);
+
+        ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code));
+        close(fd);
+
+        if (ret != 0)
+                unlink(options.output);
+
+        return ret;
+}
+#endif
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
new file mode 100644
index 000000000000..45bf9c6d3257
--- /dev/null
+++ b/tools/perf/util/genelf.h
@@ -0,0 +1,67 @@
+#ifndef __GENELF_H__
+#define __GENELF_H__
+
+/* genelf.c */
+extern int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
+                         const void *code, int csize,
+                         void *debug, int nr_debug_entries);
+/* genelf_debug.c */
+extern int jit_add_debug_info(Elf *e, uint64_t code_addr,
+                              void *debug, int nr_debug_entries);
+
+#if   defined(__arm__)
+#define GEN_ELF_ARCH    EM_ARM
+#define GEN_ELF_ENDIAN  ELFDATA2LSB
+#define GEN_ELF_CLASS   ELFCLASS32
+#elif defined(__aarch64__)
+#define GEN_ELF_ARCH    EM_AARCH64
+#define GEN_ELF_ENDIAN  ELFDATA2LSB
+#define GEN_ELF_CLASS   ELFCLASS64
+#elif defined(__x86_64__)
+#define GEN_ELF_ARCH    EM_X86_64
+#define GEN_ELF_ENDIAN  ELFDATA2LSB
+#define GEN_ELF_CLASS   ELFCLASS64
+#elif defined(__i386__)
+#define GEN_ELF_ARCH    EM_386
+#define GEN_ELF_ENDIAN  ELFDATA2LSB
+#define GEN_ELF_CLASS   ELFCLASS32
+#elif defined(__ppcle__)
+#define GEN_ELF_ARCH    EM_PPC
+#define GEN_ELF_ENDIAN  ELFDATA2LSB
+#define GEN_ELF_CLASS   ELFCLASS64
+#elif defined(__powerpc__)
+#define GEN_ELF_ARCH    EM_PPC64
+#define GEN_ELF_ENDIAN  ELFDATA2MSB
+#define GEN_ELF_CLASS   ELFCLASS64
+#elif defined(__powerpcle__)
+#define GEN_ELF_ARCH    EM_PPC64
+#define GEN_ELF_ENDIAN  ELFDATA2LSB
+#define GEN_ELF_CLASS   ELFCLASS64
+#else
+#error "unsupported architecture"
+#endif
+
+#if GEN_ELF_CLASS == ELFCLASS64
+#define elf_newehdr     elf64_newehdr
+#define elf_getshdr     elf64_getshdr
+#define Elf_Ehdr        Elf64_Ehdr
+#define Elf_Shdr        Elf64_Shdr
+#define Elf_Sym         Elf64_Sym
+#define ELF_ST_TYPE(a)  ELF64_ST_TYPE(a)
+#define ELF_ST_BIND(a)  ELF64_ST_BIND(a)
+#define ELF_ST_VIS(a)   ELF64_ST_VISIBILITY(a)
+#else
+#define elf_newehdr     elf32_newehdr
+#define elf_getshdr     elf32_getshdr
+#define Elf_Ehdr        Elf32_Ehdr
+#define Elf_Shdr        Elf32_Shdr
+#define Elf_Sym         Elf32_Sym
+#define ELF_ST_TYPE(a)  ELF32_ST_TYPE(a)
+#define ELF_ST_BIND(a)  ELF32_ST_BIND(a)
+#define ELF_ST_VIS(a)   ELF32_ST_VISIBILITY(a)
+#endif
+
+/* The .text section is directly after the ELF header */
+#define GEN_ELF_TEXT_OFFSET sizeof(Elf_Ehdr)
+
+#endif
diff --git a/tools/perf/util/genelf_debug.c b/tools/perf/util/genelf_debug.c
new file mode 100644
index 000000000000..5980f7d256b1
--- /dev/null
+++ b/tools/perf/util/genelf_debug.c
@@ -0,0 +1,610 @@
+/*
+ * genelf_debug.c
+ * Copyright (C) 2015, Google, Inc
+ *
+ * Contributed by:
+ *      Stephane Eranian <eranian@google.com>
+ *
+ * Released under the GPL v2.
+ *
+ * based on GPLv2 source code from Oprofile
+ * @remark Copyright 2007 OProfile authors
+ * @author Philippe Elie
+ */
+#include <sys/types.h>
+#include <stdio.h>
+#include <getopt.h>
+#include <stddef.h>
+#include <libelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <fcntl.h>
+#include <err.h>
+#include <dwarf.h>
+
+#include "perf.h"
+#include "genelf.h"
+#include "../util/jitdump.h"
+
+#define BUFFER_EXT_DFL_SIZE     (4 * 1024)
+
+typedef uint32_t uword;
+typedef uint16_t uhalf;
+typedef int32_t  sword;
+typedef int16_t  shalf;
+typedef uint8_t  ubyte;
+typedef int8_t   sbyte;
+
+struct buffer_ext {
+        size_t cur_pos;
+        size_t max_sz;
+        void *data;
+};
+
+static void
+buffer_ext_dump(struct buffer_ext *be, const char *msg)
+{
+        size_t i;
+        warnx("DUMP for %s", msg);
+        for (i = 0 ; i < be->cur_pos; i++)
+                warnx("%4zu 0x%02x", i, (((char *)be->data)[i]) & 0xff);
+}
+
+static inline int
+buffer_ext_add(struct buffer_ext *be, void *addr, size_t sz)
+{
+        void *tmp;
+        size_t be_sz = be->max_sz;
+
+retry:
+        if ((be->cur_pos + sz) < be_sz) {
+                memcpy(be->data + be->cur_pos, addr, sz);
+                be->cur_pos += sz;
+                return 0;
+        }
+
+        if (!be_sz)
+                be_sz = BUFFER_EXT_DFL_SIZE;
+        else
+                be_sz <<= 1;
+
+        tmp = realloc(be->data, be_sz);
+        if (!tmp)
+                return -1;
+
+        be->data   = tmp;
+        be->max_sz = be_sz;
+
+        goto retry;
+}
+
+static void
+buffer_ext_init(struct buffer_ext *be)
+{
+        be->data = NULL;
+        be->cur_pos = 0;
+        be->max_sz = 0;
+}
+
+static inline size_t
+buffer_ext_size(struct buffer_ext *be)
+{
+        return be->cur_pos;
+}
+
+static inline void *
+buffer_ext_addr(struct buffer_ext *be)
+{
+        return be->data;
+}
+
+struct debug_line_header {
+        // Not counting this field
+        uword total_length;
+        // version number (2 currently)
+        uhalf version;
+        // relative offset from next field to
+        // program statement
+        uword prolog_length;
+        ubyte minimum_instruction_length;
+        ubyte default_is_stmt;
+        // line_base - see DWARF 2 specs
+        sbyte line_base;
+        // line_range - see DWARF 2 specs
+        ubyte line_range;
+        // number of opcode + 1
+        ubyte opcode_base;
+        /* follow the array of opcode args nr: ubytes [nr_opcode_base] */
+        /* follow the search directories index, zero terminated string
+         * terminated by an empty string.
+         */
+        /* follow an array of { filename, LEB128, LEB128, LEB128 }, first is
+         * the directory index entry, 0 means current directory, then mtime
+         * and filesize, last entry is followed by en empty string.
+         */
+        /* follow the first program statement */
+} __attribute__((packed));
+
+/* DWARF 2 spec talk only about one possible compilation unit header while
+ * binutils can handle two flavours of dwarf 2, 32 and 64 bits, this is not
+ * related to the used arch, an ELF 32 can hold more than 4 Go of debug
+ * information. For now we handle only DWARF 2 32 bits comp unit. It'll only
+ * become a problem if we generate more than 4GB of debug information.
+ */
+struct compilation_unit_header {
+        uword total_length;
+        uhalf version;
+        uword debug_abbrev_offset;
+        ubyte pointer_size;
+} __attribute__((packed));
+
+#define DW_LNS_num_opcode (DW_LNS_set_isa + 1)
+
+/* field filled at run time are marked with -1 */
+static struct debug_line_header const default_debug_line_header = {
+        .total_length = -1,
+        .version = 2,
+        .prolog_length = -1,
+        .minimum_instruction_length = 1,        /* could be better when min instruction size != 1 */
+        .default_is_stmt = 1,   /* we don't take care about basic block */
+        .line_base = -5,        /* sensible value for line base ... */
+        .line_range = -14,     /* ... and line range are guessed statically */
+        .opcode_base = DW_LNS_num_opcode
+};
+
+static ubyte standard_opcode_length[] =
+{
+        0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1
+};
+#if 0
+{
+        [DW_LNS_advance_pc]   = 1,
+        [DW_LNS_advance_line] = 1,
+        [DW_LNS_set_file] =  1,
+        [DW_LNS_set_column] = 1,
+        [DW_LNS_fixed_advance_pc] = 1,
+        [DW_LNS_set_isa] = 1,
+};
+#endif
+
+/* field filled at run time are marked with -1 */
+static struct compilation_unit_header default_comp_unit_header = {
+        .total_length = -1,
+        .version = 2,
+        .debug_abbrev_offset = 0,     /* we reuse the same abbrev entries for all comp unit */
+        .pointer_size = sizeof(void *)
+};
+
+static void emit_uword(struct buffer_ext *be, uword data)
+{
+        buffer_ext_add(be, &data, sizeof(uword));
+}
+
+static void emit_string(struct buffer_ext *be, const char *s)
+{
+        buffer_ext_add(be, (void *)s, strlen(s) + 1);
+}
+
+static void emit_unsigned_LEB128(struct buffer_ext *be,
+                                 unsigned long data)
+{
+        do {
+                ubyte cur = data & 0x7F;
+                data >>= 7;
+                if (data)
+                        cur |= 0x80;
+                buffer_ext_add(be, &cur, 1);
+        } while (data);
+}
+
+static void emit_signed_LEB128(struct buffer_ext *be, long data)
+{
+        int more = 1;
+        int negative = data < 0;
+        int size = sizeof(long) * CHAR_BIT;
+        while (more) {
+                ubyte cur = data & 0x7F;
+                data >>= 7;
+                if (negative)
+                        data |= - (1 << (size - 7));
+                if ((data == 0 && !(cur & 0x40)) ||
+                    (data == -1l && (cur & 0x40)))
+                        more = 0;
+                else
+                        cur |= 0x80;
+                buffer_ext_add(be, &cur, 1);
+        }
+}
+
+static void emit_extended_opcode(struct buffer_ext *be, ubyte opcode,
+                                 void *data, size_t data_len)
+{
+        buffer_ext_add(be, (char *)"", 1);
+
+        emit_unsigned_LEB128(be, data_len + 1);
+
+        buffer_ext_add(be, &opcode, 1);
+        buffer_ext_add(be, data, data_len);
+}
+
+static void emit_opcode(struct buffer_ext *be, ubyte opcode)
+{
+        buffer_ext_add(be, &opcode, 1);
+}
+
+static void emit_opcode_signed(struct buffer_ext  *be,
+                               ubyte opcode, long data)
+{
+        buffer_ext_add(be, &opcode, 1);
+        emit_signed_LEB128(be, data);
+}
+
+static void emit_opcode_unsigned(struct buffer_ext *be, ubyte opcode,
+                                 unsigned long data)
+{
+        buffer_ext_add(be, &opcode, 1);
+        emit_unsigned_LEB128(be, data);
+}
+
+static void emit_advance_pc(struct buffer_ext *be, unsigned long delta_pc)
+{
+        emit_opcode_unsigned(be, DW_LNS_advance_pc, delta_pc);
+}
+
+static void emit_advance_lineno(struct buffer_ext  *be, long delta_lineno)
+{
+        emit_opcode_signed(be, DW_LNS_advance_line, delta_lineno);
+}
+
+static void emit_lne_end_of_sequence(struct buffer_ext *be)
+{
+        emit_extended_opcode(be, DW_LNE_end_sequence, NULL, 0);
+}
+
+static void emit_set_file(struct buffer_ext *be, unsigned long idx)
+{
+        emit_opcode_unsigned(be, DW_LNS_set_file, idx);
+}
+
+static void emit_lne_define_filename(struct buffer_ext *be,
+                                     const char *filename)
+{
+        buffer_ext_add(be, (void *)"", 1);
+
+        /* LNE field, strlen(filename) + zero termination, 3 bytes for: the dir entry, timestamp, filesize */
+        emit_unsigned_LEB128(be, strlen(filename) + 5);
+        emit_opcode(be, DW_LNE_define_file);
+        emit_string(be, filename);
+        /* directory index 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+        /* last modification date on file 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+        /* filesize 0=do not know */
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void emit_lne_set_address(struct buffer_ext *be,
+                                 void *address)
+{
+        emit_extended_opcode(be, DW_LNE_set_address, &address, sizeof(unsigned long));
+}
+
+static ubyte get_special_opcode(struct debug_entry *ent,
+                                unsigned int last_line,
+                                unsigned long last_vma)
+{
+        unsigned int temp;
+        unsigned long delta_addr;
+
+        /*
+         * delta from line_base
+         */
+        temp = (ent->lineno - last_line) - default_debug_line_header.line_base;
+
+        if (temp >= default_debug_line_header.line_range)
+                return 0;
+
+        /*
+         * delta of addresses
+         */
+        delta_addr = (ent->addr - last_vma) / default_debug_line_header.minimum_instruction_length;
+
+        /* This is not sufficient to ensure opcode will be in [0-256] but
+         * sufficient to ensure when summing with the delta lineno we will
+         * not overflow the unsigned long opcode */
+
+        if (delta_addr <= 256 / default_debug_line_header.line_range) {
+                unsigned long opcode = temp +
+                        (delta_addr * default_debug_line_header.line_range) +
+                        default_debug_line_header.opcode_base;
+
+                return opcode <= 255 ? opcode : 0;
+        }
+        return 0;
+}
+
+static void emit_lineno_info(struct buffer_ext *be,
+                             struct debug_entry *ent, size_t nr_entry,
+                             unsigned long code_addr)
+{
+        size_t i;
+
+        /*
+         * Machine state at start of a statement program
+         * address = 0
+         * file    = 1
+         * line    = 1
+         * column  = 0
+         * is_stmt = default_is_stmt as given in the debug_line_header
+         * basic block = 0
+         * end sequence = 0
+         */
+
+        /* start state of the state machine we take care of */
+        unsigned long last_vma = code_addr;
+        char const  *cur_filename = NULL;
+        unsigned long cur_file_idx = 0;
+        int last_line = 1;
+
+        emit_lne_set_address(be, (void *)code_addr);
+
+        for (i = 0; i < nr_entry; i++, ent = debug_entry_next(ent)) {
+                int need_copy = 0;
+                ubyte special_opcode;
+
+                /*
+                 * check if filename changed, if so add it
+                 */
+                if (!cur_filename || strcmp(cur_filename, ent->name)) {
+                        emit_lne_define_filename(be, ent->name);
+                        cur_filename = ent->name;
+                        emit_set_file(be, ++cur_file_idx);
+                        need_copy = 1;
+                }
+
+                special_opcode = get_special_opcode(ent, last_line, last_vma);
+                if (special_opcode != 0) {
+                        last_line = ent->lineno;
+                        last_vma  = ent->addr;
+                        emit_opcode(be, special_opcode);
+                } else {
+                        /*
+                         * lines differ, emit line delta
+                         */
+                        if (last_line != ent->lineno) {
+                                emit_advance_lineno(be, ent->lineno - last_line);
+                                last_line = ent->lineno;
+                                need_copy = 1;
+                        }
+                        /*
+                         * addresses differ, emit address delta
+                         */
+                        if (last_vma != ent->addr) {
+                                emit_advance_pc(be, ent->addr - last_vma);
+                                last_vma = ent->addr;
+                                need_copy = 1;
+                        }
+                        /*
+                         * add new row to matrix
+                         */
+                        if (need_copy)
+                                emit_opcode(be, DW_LNS_copy);
+                }
+        }
+}
+
+static void add_debug_line(struct buffer_ext *be,
+        struct debug_entry *ent, size_t nr_entry,
+        unsigned long code_addr)
+{
+        struct debug_line_header * dbg_header;
+        size_t old_size;
+
+        old_size = buffer_ext_size(be);
+
+        buffer_ext_add(be, (void *)&default_debug_line_header,
+                 sizeof(default_debug_line_header));
+
+        buffer_ext_add(be, &standard_opcode_length,  sizeof(standard_opcode_length));
+
+        // empty directory entry
+        buffer_ext_add(be, (void *)"", 1);
+
+        // empty filename directory
+        buffer_ext_add(be, (void *)"", 1);
+
+        dbg_header = buffer_ext_addr(be) + old_size;
+        dbg_header->prolog_length = (buffer_ext_size(be) - old_size) -
+                offsetof(struct debug_line_header, minimum_instruction_length);
+
+        emit_lineno_info(be, ent, nr_entry, code_addr);
+
+        emit_lne_end_of_sequence(be);
+
+        dbg_header = buffer_ext_addr(be) + old_size;
+        dbg_header->total_length = (buffer_ext_size(be) - old_size) -
+                offsetof(struct debug_line_header, version);
+}
+
+static void
+add_debug_abbrev(struct buffer_ext *be)
+{
+        emit_unsigned_LEB128(be, 1);
+        emit_unsigned_LEB128(be, DW_TAG_compile_unit);
+        emit_unsigned_LEB128(be, DW_CHILDREN_yes);
+        emit_unsigned_LEB128(be, DW_AT_stmt_list);
+        emit_unsigned_LEB128(be, DW_FORM_data4);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+        emit_unsigned_LEB128(be, 0);
+}
+
+static void
+add_compilation_unit(struct buffer_ext *be,
+                     size_t offset_debug_line)
+{
+        struct compilation_unit_header *comp_unit_header;
+        size_t old_size = buffer_ext_size(be);
+
+        buffer_ext_add(be, &default_comp_unit_header,
+                       sizeof(default_comp_unit_header));
+
+        emit_unsigned_LEB128(be, 1);
+        emit_uword(be, offset_debug_line);
+
+        comp_unit_header = buffer_ext_addr(be) + old_size;
+        comp_unit_header->total_length = (buffer_ext_size(be) - old_size) -
+                offsetof(struct compilation_unit_header, version);
+}
+
+static int
+jit_process_debug_info(uint64_t code_addr,
+                       void *debug, int nr_debug_entries,
+                       struct buffer_ext *dl,
+                       struct buffer_ext *da,
+                       struct buffer_ext *di)
+{
+        struct debug_entry *ent = debug;
+        int i;
+
+        for (i = 0; i < nr_debug_entries; i++) {
+                ent->addr = ent->addr - code_addr;
+                ent = debug_entry_next(ent);
+        }
+        add_compilation_unit(di, buffer_ext_size(dl));
+        add_debug_line(dl, debug, nr_debug_entries, 0);
+        add_debug_abbrev(da);
+        if (0) buffer_ext_dump(da, "abbrev");
+
+        return 0;
+}
+
+int
+jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_entries)
+{
+        Elf_Data *d;
+        Elf_Scn *scn;
+        Elf_Shdr *shdr;
+        struct buffer_ext dl, di, da;
+        int ret;
+
+        buffer_ext_init(&dl);
+        buffer_ext_init(&di);
+        buffer_ext_init(&da);
+
+        ret = jit_process_debug_info(code_addr, debug, nr_debug_entries, &dl, &da, &di);
+        if (ret)
+                return -1;
+        /*
+         * setup .debug_line section
+         */
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                return -1;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                return -1;
+        }
+
+        d->d_align = 1;
+        d->d_off = 0LL;
+        d->d_buf = buffer_ext_addr(&dl);
+        d->d_type = ELF_T_BYTE;
+        d->d_size = buffer_ext_size(&dl);
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                return -1;
+        }
+
+        shdr->sh_name = 52; /* .debug_line */
+        shdr->sh_type = SHT_PROGBITS;
+        shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+        shdr->sh_flags = 0;
+        shdr->sh_entsize = 0;
+
+        /*
+         * setup .debug_info section
+         */
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                return -1;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                return -1;
+        }
+
+        d->d_align = 1;
+        d->d_off = 0LL;
+        d->d_buf = buffer_ext_addr(&di);
+        d->d_type = ELF_T_BYTE;
+        d->d_size = buffer_ext_size(&di);
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                return -1;
+        }
+
+        shdr->sh_name = 64; /* .debug_info */
+        shdr->sh_type = SHT_PROGBITS;
+        shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+        shdr->sh_flags = 0;
+        shdr->sh_entsize = 0;
+
+        /*
+         * setup .debug_abbrev section
+         */
+        scn = elf_newscn(e);
+        if (!scn) {
+                warnx("cannot create section");
+                return -1;
+        }
+
+        d = elf_newdata(scn);
+        if (!d) {
+                warnx("cannot get new data");
+                return -1;
+        }
+
+        d->d_align = 1;
+        d->d_off = 0LL;
+        d->d_buf = buffer_ext_addr(&da);
+        d->d_type = ELF_T_BYTE;
+        d->d_size = buffer_ext_size(&da);
+        d->d_version = EV_CURRENT;
+
+        shdr = elf_getshdr(scn);
+        if (!shdr) {
+                warnx("cannot get section header");
+                return -1;
+        }
+
+        shdr->sh_name = 76; /* .debug_info */
+        shdr->sh_type = SHT_PROGBITS;
+        shdr->sh_addr = 0; /* must be zero or == sh_offset -> dynamic object */
+        shdr->sh_flags = 0;
+        shdr->sh_entsize = 0;
+
+        /*
+         * now we update the ELF image with all the sections
+         */
+        if (elf_update(e, ELF_C_WRITE) < 0) {
+                warnx("elf_update debug failed");
+                return -1;
+        }
+        return 0;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index f50b7235ecb6..73e38e472ecd 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -23,6 +23,8 @@
 #include "strbuf.h"
 #include "build-id.h"
 #include "data.h"
+#include <api/fs/fs.h>
+#include "asm/bug.h"
 
 /*
  * magic2 = "PERFILE2"
@@ -868,6 +870,199 @@ static int write_auxtrace(int fd, struct perf_header *h,
         return err;
 }
 
+static int cpu_cache_level__sort(const void *a, const void *b)
+{
+        struct cpu_cache_level *cache_a = (struct cpu_cache_level *)a;
+        struct cpu_cache_level *cache_b = (struct cpu_cache_level *)b;
+
+        return cache_a->level - cache_b->level;
+}
+
+static bool cpu_cache_level__cmp(struct cpu_cache_level *a, struct cpu_cache_level *b)
+{
+        if (a->level != b->level)
+                return false;
+
+        if (a->line_size != b->line_size)
+                return false;
+
+        if (a->sets != b->sets)
+                return false;
+
+        if (a->ways != b->ways)
+                return false;
+
+        if (strcmp(a->type, b->type))
+                return false;
+
+        if (strcmp(a->size, b->size))
+                return false;
+
+        if (strcmp(a->map, b->map))
+                return false;
+
+        return true;
+}
+
+static int cpu_cache_level__read(struct cpu_cache_level *cache, u32 cpu, u16 level)
+{
+        char path[PATH_MAX], file[PATH_MAX];
+        struct stat st;
+        size_t len;
+
+        scnprintf(path, PATH_MAX, "devices/system/cpu/cpu%d/cache/index%d/", cpu, level);
+        scnprintf(file, PATH_MAX, "%s/%s", sysfs__mountpoint(), path);
+
+        if (stat(file, &st))
+                return 1;
+
+        scnprintf(file, PATH_MAX, "%s/level", path);
+        if (sysfs__read_int(file, (int *) &cache->level))
+                return -1;
+
+        scnprintf(file, PATH_MAX, "%s/coherency_line_size", path);
+        if (sysfs__read_int(file, (int *) &cache->line_size))
+                return -1;
+
+        scnprintf(file, PATH_MAX, "%s/number_of_sets", path);
+        if (sysfs__read_int(file, (int *) &cache->sets))
+                return -1;
+
+        scnprintf(file, PATH_MAX, "%s/ways_of_associativity", path);
+        if (sysfs__read_int(file, (int *) &cache->ways))
+                return -1;
+
+        scnprintf(file, PATH_MAX, "%s/type", path);
+        if (sysfs__read_str(file, &cache->type, &len))
+                return -1;
+
+        cache->type[len] = 0;
+        cache->type = rtrim(cache->type);
+
+        scnprintf(file, PATH_MAX, "%s/size", path);
+        if (sysfs__read_str(file, &cache->size, &len)) {
+                free(cache->type);
+                return -1;
+        }
+
+        cache->size[len] = 0;
+        cache->size = rtrim(cache->size);
+
+        scnprintf(file, PATH_MAX, "%s/shared_cpu_list", path);
+        if (sysfs__read_str(file, &cache->map, &len)) {
+                free(cache->map);
+                free(cache->type);
+                return -1;
+        }
+
+        cache->map[len] = 0;
+        cache->map = rtrim(cache->map);
+        return 0;
+}
+
+static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
+{
+        fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
+{
+        u32 i, cnt = 0;
+        long ncpus;
+        u32 nr, cpu;
+        u16 level;
+
+        ncpus = sysconf(_SC_NPROCESSORS_CONF);
+        if (ncpus < 0)
+                return -1;
+
+        nr = (u32)(ncpus & UINT_MAX);
+
+        for (cpu = 0; cpu < nr; cpu++) {
+                for (level = 0; level < 10; level++) {
+                        struct cpu_cache_level c;
+                        int err;
+
+                        err = cpu_cache_level__read(&c, cpu, level);
+                        if (err < 0)
+                                return err;
+
+                        if (err == 1)
+                                break;
+
+                        for (i = 0; i < cnt; i++) {
+                                if (cpu_cache_level__cmp(&c, &caches[i]))
+                                        break;
+                        }
+
+                        if (i == cnt)
+                                caches[cnt++] = c;
+                        else
+                                cpu_cache_level__free(&c);
+
+                        if (WARN_ONCE(cnt == size, "way too many cpu caches.."))
+                                goto out;
+                }
+        }
+ out:
+        *cntp = cnt;
+        return 0;
+}
+
+#define MAX_CACHES 2000
+
+static int write_cache(int fd, struct perf_header *h __maybe_unused,
+                          struct perf_evlist *evlist __maybe_unused)
+{
+        struct cpu_cache_level caches[MAX_CACHES];
+        u32 cnt = 0, i, version = 1;
+        int ret;
+
+        ret = build_caches(caches, MAX_CACHES, &cnt);
+        if (ret)
+                goto out;
+
+        qsort(&caches, cnt, sizeof(struct cpu_cache_level), cpu_cache_level__sort);
+
+        ret = do_write(fd, &version, sizeof(u32));
+        if (ret < 0)
+                goto out;
+
+        ret = do_write(fd, &cnt, sizeof(u32));
+        if (ret < 0)
+                goto out;
+
+        for (i = 0; i < cnt; i++) {
+                struct cpu_cache_level *c = &caches[i];
+
+                #define _W(v)                                   \
+                        ret = do_write(fd, &c->v, sizeof(u32)); \
+                        if (ret < 0)                            \
+                                goto out;
+
+                _W(level)
+                _W(line_size)
+                _W(sets)
+                _W(ways)
+                #undef _W
+
+                #define _W(v)                                           \
+                        ret = do_write_string(fd, (const char *) c->v); \
+                        if (ret < 0)                                    \
+                                goto out;
+
+                _W(type)
+                _W(size)
+                _W(map)
+                #undef _W
+        }
+
+out:
+        for (i = 0; i < cnt; i++)
+                cpu_cache_level__free(&caches[i]);
+        return ret;
+}
+
 static int write_stat(int fd __maybe_unused,
                       struct perf_header *h __maybe_unused,
                       struct perf_evlist *evlist __maybe_unused)
@@ -1172,6 +1367,18 @@ static void print_stat(struct perf_header *ph __maybe_unused,
         fprintf(fp, "# contains stat data\n");
 }
 
+static void print_cache(struct perf_header *ph __maybe_unused,
+                        int fd __maybe_unused, FILE *fp __maybe_unused)
+{
+        int i;
+
+        fprintf(fp, "# CPU cache info:\n");
+        for (i = 0; i < ph->env.caches_cnt; i++) {
+                fprintf(fp, "#  ");
+                cpu_cache_level__fprintf(fp, &ph->env.caches[i]);
+        }
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
                                FILE *fp)
 {
@@ -1920,6 +2127,68 @@ static int process_auxtrace(struct perf_file_section *section,
         return err;
 }
 
+static int process_cache(struct perf_file_section *section __maybe_unused,
+                         struct perf_header *ph __maybe_unused, int fd __maybe_unused,
+                         void *data __maybe_unused)
+{
+        struct cpu_cache_level *caches;
+        u32 cnt, i, version;
+
+        if (readn(fd, &version, sizeof(version)) != sizeof(version))
+                return -1;
+
+        if (ph->needs_swap)
+                version = bswap_32(version);
+
+        if (version != 1)
+                return -1;
+
+        if (readn(fd, &cnt, sizeof(cnt)) != sizeof(cnt))
+                return -1;
+
+        if (ph->needs_swap)
+                cnt = bswap_32(cnt);
+
+        caches = zalloc(sizeof(*caches) * cnt);
+        if (!caches)
+                return -1;
+
+        for (i = 0; i < cnt; i++) {
+                struct cpu_cache_level c;
+
+                #define _R(v)                                           \
+                        if (readn(fd, &c.v, sizeof(u32)) != sizeof(u32))\
+                                goto out_free_caches;                   \
+                        if (ph->needs_swap)                             \
+                                c.v = bswap_32(c.v);                    \
+
+                _R(level)
+                _R(line_size)
+                _R(sets)
+                _R(ways)
+                #undef _R
+
+                #define _R(v)                           \
+                        c.v = do_read_string(fd, ph);   \
+                        if (!c.v)                       \
+                                goto out_free_caches;
+
+                _R(type)
+                _R(size)
+                _R(map)
+                #undef _R
+
+                caches[i] = c;
+        }
+
+        ph->env.caches = caches;
+        ph->env.caches_cnt = cnt;
+        return 0;
+out_free_caches:
+        free(caches);
+        return -1;
+}
+
 struct feature_ops {
         int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
         void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1962,6 +2231,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
         FEAT_OPP(HEADER_GROUP_DESC,     group_desc),
         FEAT_OPP(HEADER_AUXTRACE,       auxtrace),
         FEAT_OPA(HEADER_STAT,           stat),
+        FEAT_OPF(HEADER_CACHE,          cache),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index cff9892452ee..3d87ca823c0a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -32,6 +32,7 @@ enum {
         HEADER_GROUP_DESC,
         HEADER_AUXTRACE,
         HEADER_STAT,
+        HEADER_CACHE,
         HEADER_LAST_FEATURE,
         HEADER_FEAT_BITS        = 256,
 };
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index dc1e41c9b054..43a98a4dc1e1 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -6,7 +6,8 @@
 static int autocorrect;
 static struct cmdnames aliases;
 
-static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
+static int perf_unknown_cmd_config(const char *var, const char *value,
+                                   void *cb __maybe_unused)
 {
         if (!strcmp(var, "help.autocorrect"))
                 autocorrect = perf_config_int(var,value);
@@ -14,7 +15,7 @@ static int perf_unknown_cmd_config(const char *var, const char *value, void *cb)
         if (!prefixcmp(var, "alias."))
                 add_cmdname(&aliases, var + 6, strlen(var + 6));
 
-        return perf_default_config(var, value, cb);
+        return 0;
 }
 
 static int levenshtein_compare(const void *p1, const void *p2)
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 68a7612019dc..290b3cbf6877 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -179,6 +179,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
         if (h->transaction)
                 hists__new_col_len(hists, HISTC_TRANSACTION,
                                    hist_entry__transaction_len());
+
+        if (h->trace_output)
+                hists__new_col_len(hists, HISTC_TRACE, strlen(h->trace_output));
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -245,6 +248,8 @@ static void he_stat__decay(struct he_stat *he_stat)
         /* XXX need decay for weight too? */
 }
 
+static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
+
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 {
         u64 prev_period = he->stat.period;
@@ -260,21 +265,45 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
 
         diff = prev_period - he->stat.period;
 
-        hists->stats.total_period -= diff;
-        if (!he->filtered)
-                hists->stats.total_non_filtered_period -= diff;
+        if (!he->depth) {
+                hists->stats.total_period -= diff;
+                if (!he->filtered)
+                        hists->stats.total_non_filtered_period -= diff;
+        }
+
+        if (!he->leaf) {
+                struct hist_entry *child;
+                struct rb_node *node = rb_first(&he->hroot_out);
+                while (node) {
+                        child = rb_entry(node, struct hist_entry, rb_node);
+                        node = rb_next(node);
+
+                        if (hists__decay_entry(hists, child))
+                                hists__delete_entry(hists, child);
+                }
+        }
 
         return he->stat.period == 0;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he)
 {
-        rb_erase(&he->rb_node, &hists->entries);
+        struct rb_root *root_in;
+        struct rb_root *root_out;
 
-        if (sort__need_collapse)
-                rb_erase(&he->rb_node_in, &hists->entries_collapsed);
-        else
-                rb_erase(&he->rb_node_in, hists->entries_in);
+        if (he->parent_he) {
+                root_in  = &he->parent_he->hroot_in;
+                root_out = &he->parent_he->hroot_out;
+        } else {
+                if (sort__need_collapse)
+                        root_in = &hists->entries_collapsed;
+                else
+                        root_in = hists->entries_in;
+                root_out = &hists->entries;
+        }
+
+        rb_erase(&he->rb_node_in, root_in);
+        rb_erase(&he->rb_node, root_out);
 
         --hists->nr_entries;
         if (!he->filtered)
@@ -393,6 +422,9 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
                 }
                 INIT_LIST_HEAD(&he->pairs.node);
                 thread__get(he->thread);
+
+                if (!symbol_conf.report_hierarchy)
+                        he->leaf = true;
         }
 
         return he;
@@ -405,6 +437,16 @@ static u8 symbol__parent_filter(const struct symbol *parent)
         return 0;
 }
 
+static void hist_entry__add_callchain_period(struct hist_entry *he, u64 period)
+{
+        if (!symbol_conf.use_callchain)
+                return;
+
+        he->hists->callchain_period += period;
+        if (!he->filtered)
+                he->hists->callchain_non_filtered_period += period;
+}
+
 static struct hist_entry *hists__findnew_entry(struct hists *hists,
                                                struct hist_entry *entry,
                                                struct addr_location *al,
@@ -432,8 +474,10 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
                 cmp = hist_entry__cmp(he, entry);
 
                 if (!cmp) {
-                        if (sample_self)
+                        if (sample_self) {
                                 he_stat__add_period(&he->stat, period, weight);
+                                hist_entry__add_callchain_period(he, period);
+                        }
                         if (symbol_conf.cumulate_callchain)
                                 he_stat__add_period(he->stat_acc, period, weight);
 
@@ -466,6 +510,8 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
         if (!he)
                 return NULL;
 
+        if (sample_self)
+                hist_entry__add_callchain_period(he, period);
         hists->nr_entries++;
 
         rb_link_node(&he->rb_node_in, parent, p);
@@ -951,10 +997,15 @@ out:
 int64_t
 hist_entry__cmp(struct hist_entry *left, struct hist_entry *right)
 {
+        struct hists *hists = left->hists;
         struct perf_hpp_fmt *fmt;
         int64_t cmp = 0;
 
-        perf_hpp__for_each_sort_list(fmt) {
+        hists__for_each_sort_list(hists, fmt) {
+                if (perf_hpp__is_dynamic_entry(fmt) &&
+                    !perf_hpp__defined_dynamic_entry(fmt, hists))
+                        continue;
+
                 cmp = fmt->cmp(fmt, left, right);
                 if (cmp)
                         break;
@@ -966,10 +1017,15 @@ 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 hists *hists = left->hists;
         struct perf_hpp_fmt *fmt;
         int64_t cmp = 0;
 
-        perf_hpp__for_each_sort_list(fmt) {
+        hists__for_each_sort_list(hists, fmt) {
+                if (perf_hpp__is_dynamic_entry(fmt) &&
+                    !perf_hpp__defined_dynamic_entry(fmt, hists))
+                        continue;
+
                 cmp = fmt->collapse(fmt, left, right);
                 if (cmp)
                         break;
@@ -1006,17 +1062,250 @@ void hist_entry__delete(struct hist_entry *he)
 }
 
 /*
+ * If this is not the last column, then we need to pad it according to the
+ * pre-calculated max lenght for this column, otherwise don't bother adding
+ * spaces because that would break viewing this with, for instance, 'less',
+ * that would show tons of trailing spaces when a long C++ demangled method
+ * names is sampled.
+*/
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+                                   struct perf_hpp_fmt *fmt, int printed)
+{
+        if (!list_is_last(&fmt->list, &he->hists->hpp_list->fields)) {
+                const int width = fmt->width(fmt, hpp, hists_to_evsel(he->hists));
+                if (printed < width) {
+                        advance_hpp(hpp, printed);
+                        printed = scnprintf(hpp->buf, hpp->size, "%-*s", width - printed, " ");
+                }
+        }
+
+        return printed;
+}
+
+/*
  * collapse the histogram
  */
 
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
-                                  struct rb_root *root, struct hist_entry *he)
+static void hists__apply_filters(struct hists *hists, struct hist_entry *he);
+static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *he,
+                                       enum hist_filter type);
+
+typedef bool (*fmt_chk_fn)(struct perf_hpp_fmt *fmt);
+
+static bool check_thread_entry(struct perf_hpp_fmt *fmt)
+{
+        return perf_hpp__is_thread_entry(fmt) || perf_hpp__is_comm_entry(fmt);
+}
+
+static void hist_entry__check_and_remove_filter(struct hist_entry *he,
+                                                enum hist_filter type,
+                                                fmt_chk_fn check)
+{
+        struct perf_hpp_fmt *fmt;
+        bool type_match = false;
+        struct hist_entry *parent = he->parent_he;
+
+        switch (type) {
+        case HIST_FILTER__THREAD:
+                if (symbol_conf.comm_list == NULL &&
+                    symbol_conf.pid_list == NULL &&
+                    symbol_conf.tid_list == NULL)
+                        return;
+                break;
+        case HIST_FILTER__DSO:
+                if (symbol_conf.dso_list == NULL)
+                        return;
+                break;
+        case HIST_FILTER__SYMBOL:
+                if (symbol_conf.sym_list == NULL)
+                        return;
+                break;
+        case HIST_FILTER__PARENT:
+        case HIST_FILTER__GUEST:
+        case HIST_FILTER__HOST:
+        case HIST_FILTER__SOCKET:
+        default:
+                return;
+        }
+
+        /* if it's filtered by own fmt, it has to have filter bits */
+        perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+                if (check(fmt)) {
+                        type_match = true;
+                        break;
+                }
+        }
+
+        if (type_match) {
+                /*
+                 * If the filter is for current level entry, propagate
+                 * filter marker to parents.  The marker bit was
+                 * already set by default so it only needs to clear
+                 * non-filtered entries.
+                 */
+                if (!(he->filtered & (1 << type))) {
+                        while (parent) {
+                                parent->filtered &= ~(1 << type);
+                                parent = parent->parent_he;
+                        }
+                }
+        } else {
+                /*
+                 * If current entry doesn't have matching formats, set
+                 * filter marker for upper level entries.  it will be
+                 * cleared if its lower level entries is not filtered.
+                 *
+                 * For lower-level entries, it inherits parent's
+                 * filter bit so that lower level entries of a
+                 * non-filtered entry won't set the filter marker.
+                 */
+                if (parent == NULL)
+                        he->filtered |= (1 << type);
+                else
+                        he->filtered |= (parent->filtered & (1 << type));
+        }
+}
+
+static void hist_entry__apply_hierarchy_filters(struct hist_entry *he)
+{
+        hist_entry__check_and_remove_filter(he, HIST_FILTER__THREAD,
+                                            check_thread_entry);
+
+        hist_entry__check_and_remove_filter(he, HIST_FILTER__DSO,
+                                            perf_hpp__is_dso_entry);
+
+        hist_entry__check_and_remove_filter(he, HIST_FILTER__SYMBOL,
+                                            perf_hpp__is_sym_entry);
+
+        hists__apply_filters(he->hists, he);
+}
+
+static struct hist_entry *hierarchy_insert_entry(struct hists *hists,
+                                                 struct rb_root *root,
+                                                 struct hist_entry *he,
+                                                 struct hist_entry *parent_he,
+                                                 struct perf_hpp_list *hpp_list)
+{
+        struct rb_node **p = &root->rb_node;
+        struct rb_node *parent = NULL;
+        struct hist_entry *iter, *new;
+        struct perf_hpp_fmt *fmt;
+        int64_t cmp;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct hist_entry, rb_node_in);
+
+                cmp = 0;
+                perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+                        cmp = fmt->collapse(fmt, iter, he);
+                        if (cmp)
+                                break;
+                }
+
+                if (!cmp) {
+                        he_stat__add_stat(&iter->stat, &he->stat);
+                        return iter;
+                }
+
+                if (cmp < 0)
+                        p = &parent->rb_left;
+                else
+                        p = &parent->rb_right;
+        }
+
+        new = hist_entry__new(he, true);
+        if (new == NULL)
+                return NULL;
+
+        hists->nr_entries++;
+
+        /* save related format list for output */
+        new->hpp_list = hpp_list;
+        new->parent_he = parent_he;
+
+        hist_entry__apply_hierarchy_filters(new);
+
+        /* some fields are now passed to 'new' */
+        perf_hpp_list__for_each_sort_list(hpp_list, fmt) {
+                if (perf_hpp__is_trace_entry(fmt) || perf_hpp__is_dynamic_entry(fmt))
+                        he->trace_output = NULL;
+                else
+                        new->trace_output = NULL;
+
+                if (perf_hpp__is_srcline_entry(fmt))
+                        he->srcline = NULL;
+                else
+                        new->srcline = NULL;
+
+                if (perf_hpp__is_srcfile_entry(fmt))
+                        he->srcfile = NULL;
+                else
+                        new->srcfile = NULL;
+        }
+
+        rb_link_node(&new->rb_node_in, parent, p);
+        rb_insert_color(&new->rb_node_in, root);
+        return new;
+}
+
+static int hists__hierarchy_insert_entry(struct hists *hists,
+                                         struct rb_root *root,
+                                         struct hist_entry *he)
+{
+        struct perf_hpp_list_node *node;
+        struct hist_entry *new_he = NULL;
+        struct hist_entry *parent = NULL;
+        int depth = 0;
+        int ret = 0;
+
+        list_for_each_entry(node, &hists->hpp_formats, list) {
+                /* skip period (overhead) and elided columns */
+                if (node->level == 0 || node->skip)
+                        continue;
+
+                /* insert copy of 'he' for each fmt into the hierarchy */
+                new_he = hierarchy_insert_entry(hists, root, he, parent, &node->hpp);
+                if (new_he == NULL) {
+                        ret = -1;
+                        break;
+                }
+
+                root = &new_he->hroot_in;
+                new_he->depth = depth++;
+                parent = new_he;
+        }
+
+        if (new_he) {
+                new_he->leaf = true;
+
+                if (symbol_conf.use_callchain) {
+                        callchain_cursor_reset(&callchain_cursor);
+                        if (callchain_merge(&callchain_cursor,
+                                            new_he->callchain,
+                                            he->callchain) < 0)
+                                ret = -1;
+                }
+        }
+
+        /* 'he' is no longer used */
+        hist_entry__delete(he);
+
+        /* return 0 (or -1) since it already applied filters */
+        return ret;
+}
+
+int hists__collapse_insert_entry(struct hists *hists, struct rb_root *root,
+                                 struct hist_entry *he)
 {
         struct rb_node **p = &root->rb_node;
         struct rb_node *parent = NULL;
         struct hist_entry *iter;
         int64_t cmp;
 
+        if (symbol_conf.report_hierarchy)
+                return hists__hierarchy_insert_entry(hists, root, he);
+
         while (*p != NULL) {
                 parent = *p;
                 iter = rb_entry(parent, struct hist_entry, rb_node_in);
@@ -1024,18 +1313,21 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
                 cmp = hist_entry__collapse(iter, he);
 
                 if (!cmp) {
+                        int ret = 0;
+
                         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);
-                                callchain_merge(&callchain_cursor,
-                                                iter->callchain,
-                                                he->callchain);
+                                if (callchain_merge(&callchain_cursor,
+                                                    iter->callchain,
+                                                    he->callchain) < 0)
+                                        ret = -1;
                         }
                         hist_entry__delete(he);
-                        return false;
+                        return ret;
                 }
 
                 if (cmp < 0)
@@ -1047,7 +1339,7 @@ bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
 
         rb_link_node(&he->rb_node_in, parent, p);
         rb_insert_color(&he->rb_node_in, root);
-        return true;
+        return 1;
 }
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists)
@@ -1073,14 +1365,15 @@ static void hists__apply_filters(struct hists *hists, struct hist_entry *he)
         hists__filter_entry_by_socket(hists, he);
 }
 
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
+int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 {
         struct rb_root *root;
         struct rb_node *next;
         struct hist_entry *n;
+        int ret;
 
         if (!sort__need_collapse)
-                return;
+                return 0;
 
         hists->nr_entries = 0;
 
@@ -1095,7 +1388,11 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
                 next = rb_next(&n->rb_node_in);
 
                 rb_erase(&n->rb_node_in, root);
-                if (hists__collapse_insert_entry(hists, &hists->entries_collapsed, n)) {
+                ret = hists__collapse_insert_entry(hists, &hists->entries_collapsed, n);
+                if (ret < 0)
+                        return -1;
+
+                if (ret) {
                         /*
                          * If it wasn't combined with one of the entries already
                          * collapsed, we need to apply the filters that may have
@@ -1106,14 +1403,16 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
                 if (prog)
                         ui_progress__update(prog, 1);
         }
+        return 0;
 }
 
 static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
+        struct hists *hists = a->hists;
         struct perf_hpp_fmt *fmt;
         int64_t cmp = 0;
 
-        perf_hpp__for_each_sort_list(fmt) {
+        hists__for_each_sort_list(hists, fmt) {
                 if (perf_hpp__should_skip(fmt, a->hists))
                         continue;
 
@@ -1154,6 +1453,113 @@ void hists__inc_stats(struct hists *hists, struct hist_entry *h)
         hists->stats.total_period += h->stat.period;
 }
 
+static void hierarchy_recalc_total_periods(struct hists *hists)
+{
+        struct rb_node *node;
+        struct hist_entry *he;
+
+        node = rb_first(&hists->entries);
+
+        hists->stats.total_period = 0;
+        hists->stats.total_non_filtered_period = 0;
+
+        /*
+         * recalculate total period using top-level entries only
+         * since lower level entries only see non-filtered entries
+         * but upper level entries have sum of both entries.
+         */
+        while (node) {
+                he = rb_entry(node, struct hist_entry, rb_node);
+                node = rb_next(node);
+
+                hists->stats.total_period += he->stat.period;
+                if (!he->filtered)
+                        hists->stats.total_non_filtered_period += he->stat.period;
+        }
+}
+
+static void hierarchy_insert_output_entry(struct rb_root *root,
+                                          struct hist_entry *he)
+{
+        struct rb_node **p = &root->rb_node;
+        struct rb_node *parent = NULL;
+        struct hist_entry *iter;
+        struct perf_hpp_fmt *fmt;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct hist_entry, rb_node);
+
+                if (hist_entry__sort(he, iter) > 0)
+                        p = &parent->rb_left;
+                else
+                        p = &parent->rb_right;
+        }
+
+        rb_link_node(&he->rb_node, parent, p);
+        rb_insert_color(&he->rb_node, root);
+
+        /* update column width of dynamic entry */
+        perf_hpp_list__for_each_sort_list(he->hpp_list, fmt) {
+                if (perf_hpp__is_dynamic_entry(fmt))
+                        fmt->sort(fmt, he, NULL);
+        }
+}
+
+static void hists__hierarchy_output_resort(struct hists *hists,
+                                           struct ui_progress *prog,
+                                           struct rb_root *root_in,
+                                           struct rb_root *root_out,
+                                           u64 min_callchain_hits,
+                                           bool use_callchain)
+{
+        struct rb_node *node;
+        struct hist_entry *he;
+
+        *root_out = RB_ROOT;
+        node = rb_first(root_in);
+
+        while (node) {
+                he = rb_entry(node, struct hist_entry, rb_node_in);
+                node = rb_next(node);
+
+                hierarchy_insert_output_entry(root_out, he);
+
+                if (prog)
+                        ui_progress__update(prog, 1);
+
+                if (!he->leaf) {
+                        hists__hierarchy_output_resort(hists, prog,
+                                                       &he->hroot_in,
+                                                       &he->hroot_out,
+                                                       min_callchain_hits,
+                                                       use_callchain);
+                        hists->nr_entries++;
+                        if (!he->filtered) {
+                                hists->nr_non_filtered_entries++;
+                                hists__calc_col_len(hists, he);
+                        }
+
+                        continue;
+                }
+
+                if (!use_callchain)
+                        continue;
+
+                if (callchain_param.mode == CHAIN_GRAPH_REL) {
+                        u64 total = he->stat.period;
+
+                        if (symbol_conf.cumulate_callchain)
+                                total = he->stat_acc->period;
+
+                        min_callchain_hits = total * (callchain_param.min_percent / 100);
+                }
+
+                callchain_param.sort(&he->sorted_chain, he->callchain,
+                                     min_callchain_hits, &callchain_param);
+        }
+}
+
 static void __hists__insert_output_entry(struct rb_root *entries,
                                          struct hist_entry *he,
                                          u64 min_callchain_hits,
@@ -1162,10 +1568,20 @@ static void __hists__insert_output_entry(struct rb_root *entries,
         struct rb_node **p = &entries->rb_node;
         struct rb_node *parent = NULL;
         struct hist_entry *iter;
+        struct perf_hpp_fmt *fmt;
+
+        if (use_callchain) {
+                if (callchain_param.mode == CHAIN_GRAPH_REL) {
+                        u64 total = he->stat.period;
+
+                        if (symbol_conf.cumulate_callchain)
+                                total = he->stat_acc->period;
 
-        if (use_callchain)
+                        min_callchain_hits = total * (callchain_param.min_percent / 100);
+                }
                 callchain_param.sort(&he->sorted_chain, he->callchain,
                                       min_callchain_hits, &callchain_param);
+        }
 
         while (*p != NULL) {
                 parent = *p;
@@ -1179,23 +1595,41 @@ static void __hists__insert_output_entry(struct rb_root *entries,
 
         rb_link_node(&he->rb_node, parent, p);
         rb_insert_color(&he->rb_node, entries);
+
+        perf_hpp_list__for_each_sort_list(&perf_hpp_list, fmt) {
+                if (perf_hpp__is_dynamic_entry(fmt) &&
+                    perf_hpp__defined_dynamic_entry(fmt, he->hists))
+                        fmt->sort(fmt, he, NULL);  /* update column width */
+        }
 }
 
-void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+static void output_resort(struct hists *hists, struct ui_progress *prog,
+                          bool use_callchain)
 {
         struct rb_root *root;
         struct rb_node *next;
         struct hist_entry *n;
+        u64 callchain_total;
         u64 min_callchain_hits;
-        struct perf_evsel *evsel = hists_to_evsel(hists);
-        bool use_callchain;
 
-        if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
-                use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
-        else
-                use_callchain = symbol_conf.use_callchain;
+        callchain_total = hists->callchain_period;
+        if (symbol_conf.filter_relative)
+                callchain_total = hists->callchain_non_filtered_period;
 
-        min_callchain_hits = hists->stats.total_period * (callchain_param.min_percent / 100);
+        min_callchain_hits = callchain_total * (callchain_param.min_percent / 100);
+
+        hists__reset_stats(hists);
+        hists__reset_col_len(hists);
+
+        if (symbol_conf.report_hierarchy) {
+                hists__hierarchy_output_resort(hists, prog,
+                                               &hists->entries_collapsed,
+                                               &hists->entries,
+                                               min_callchain_hits,
+                                               use_callchain);
+                hierarchy_recalc_total_periods(hists);
+                return;
+        }
 
         if (sort__need_collapse)
                 root = &hists->entries_collapsed;
@@ -1205,9 +1639,6 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
         next = rb_first(root);
         hists->entries = RB_ROOT;
 
-        hists__reset_stats(hists);
-        hists__reset_col_len(hists);
-
         while (next) {
                 n = rb_entry(next, struct hist_entry, rb_node_in);
                 next = rb_next(&n->rb_node_in);
@@ -1223,15 +1654,136 @@ void hists__output_resort(struct hists *hists, struct ui_progress *prog)
         }
 }
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog)
+{
+        bool use_callchain;
+
+        if (evsel && symbol_conf.use_callchain && !symbol_conf.show_ref_callgraph)
+                use_callchain = evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN;
+        else
+                use_callchain = symbol_conf.use_callchain;
+
+        output_resort(evsel__hists(evsel), prog, use_callchain);
+}
+
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
+{
+        output_resort(hists, prog, symbol_conf.use_callchain);
+}
+
+static bool can_goto_child(struct hist_entry *he, enum hierarchy_move_dir hmd)
+{
+        if (he->leaf || hmd == HMD_FORCE_SIBLING)
+                return false;
+
+        if (he->unfolded || hmd == HMD_FORCE_CHILD)
+                return true;
+
+        return false;
+}
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node)
+{
+        struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+        while (can_goto_child(he, HMD_NORMAL)) {
+                node = rb_last(&he->hroot_out);
+                he = rb_entry(node, struct hist_entry, rb_node);
+        }
+        return node;
+}
+
+struct rb_node *__rb_hierarchy_next(struct rb_node *node, enum hierarchy_move_dir hmd)
+{
+        struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+        if (can_goto_child(he, hmd))
+                node = rb_first(&he->hroot_out);
+        else
+                node = rb_next(node);
+
+        while (node == NULL) {
+                he = he->parent_he;
+                if (he == NULL)
+                        break;
+
+                node = rb_next(&he->rb_node);
+        }
+        return node;
+}
+
+struct rb_node *rb_hierarchy_prev(struct rb_node *node)
+{
+        struct hist_entry *he = rb_entry(node, struct hist_entry, rb_node);
+
+        node = rb_prev(node);
+        if (node)
+                return rb_hierarchy_last(node);
+
+        he = he->parent_he;
+        if (he == NULL)
+                return NULL;
+
+        return &he->rb_node;
+}
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit)
+{
+        struct rb_node *node;
+        struct hist_entry *child;
+        float percent;
+
+        if (he->leaf)
+                return false;
+
+        node = rb_first(&he->hroot_out);
+        child = rb_entry(node, struct hist_entry, rb_node);
+
+        while (node && child->filtered) {
+                node = rb_next(node);
+                child = rb_entry(node, struct hist_entry, rb_node);
+        }
+
+        if (node)
+                percent = hist_entry__get_percent_limit(child);
+        else
+                percent = 0;
+
+        return node && percent >= limit;
+}
+
 static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h,
                                        enum hist_filter filter)
 {
         h->filtered &= ~(1 << filter);
+
+        if (symbol_conf.report_hierarchy) {
+                struct hist_entry *parent = h->parent_he;
+
+                while (parent) {
+                        he_stat__add_stat(&parent->stat, &h->stat);
+
+                        parent->filtered &= ~(1 << filter);
+
+                        if (parent->filtered)
+                                goto next;
+
+                        /* force fold unfiltered entry for simplicity */
+                        parent->unfolded = false;
+                        parent->has_no_entry = false;
+                        parent->row_offset = 0;
+                        parent->nr_rows = 0;
+next:
+                        parent = parent->parent_he;
+                }
+        }
+
         if (h->filtered)
                 return;
 
         /* force fold unfiltered entry for simplicity */
         h->unfolded = false;
+        h->has_no_entry = false;
         h->row_offset = 0;
         h->nr_rows = 0;
 
@@ -1254,28 +1806,6 @@ static bool hists__filter_entry_by_dso(struct hists *hists,
         return false;
 }
 
-void hists__filter_by_dso(struct hists *hists)
-{
-        struct rb_node *nd;
-
-        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)) {
-                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-                if (symbol_conf.exclude_other && !h->parent)
-                        continue;
-
-                if (hists__filter_entry_by_dso(hists, h))
-                        continue;
-
-                hists__remove_entry_filter(hists, h, HIST_FILTER__DSO);
-        }
-}
-
 static bool hists__filter_entry_by_thread(struct hists *hists,
                                           struct hist_entry *he)
 {
@@ -1288,25 +1818,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
         return false;
 }
 
-void hists__filter_by_thread(struct hists *hists)
-{
-        struct rb_node *nd;
-
-        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)) {
-                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
-
-                if (hists__filter_entry_by_thread(hists, h))
-                        continue;
-
-                hists__remove_entry_filter(hists, h, HIST_FILTER__THREAD);
-        }
-}
-
 static bool hists__filter_entry_by_symbol(struct hists *hists,
                                           struct hist_entry *he)
 {
@@ -1320,7 +1831,21 @@ static bool hists__filter_entry_by_symbol(struct hists *hists,
         return false;
 }
 
-void hists__filter_by_symbol(struct hists *hists)
+static bool hists__filter_entry_by_socket(struct hists *hists,
+                                          struct hist_entry *he)
+{
+        if ((hists->socket_filter > -1) &&
+            (he->socket != hists->socket_filter)) {
+                he->filtered |= (1 << HIST_FILTER__SOCKET);
+                return true;
+        }
+
+        return false;
+}
+
+typedef bool (*filter_fn_t)(struct hists *hists, struct hist_entry *he);
+
+static void hists__filter_by_type(struct hists *hists, int type, filter_fn_t filter)
 {
         struct rb_node *nd;
 
@@ -1332,42 +1857,155 @@ void hists__filter_by_symbol(struct hists *hists)
         for (nd = rb_first(&hists->entries); nd; nd = rb_next(nd)) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
 
-                if (hists__filter_entry_by_symbol(hists, h))
+                if (filter(hists, h))
                         continue;
 
-                hists__remove_entry_filter(hists, h, HIST_FILTER__SYMBOL);
+                hists__remove_entry_filter(hists, h, type);
         }
 }
 
-static bool hists__filter_entry_by_socket(struct hists *hists,
-                                          struct hist_entry *he)
+static void resort_filtered_entry(struct rb_root *root, struct hist_entry *he)
 {
-        if ((hists->socket_filter > -1) &&
-            (he->socket != hists->socket_filter)) {
-                he->filtered |= (1 << HIST_FILTER__SOCKET);
-                return true;
+        struct rb_node **p = &root->rb_node;
+        struct rb_node *parent = NULL;
+        struct hist_entry *iter;
+        struct rb_root new_root = RB_ROOT;
+        struct rb_node *nd;
+
+        while (*p != NULL) {
+                parent = *p;
+                iter = rb_entry(parent, struct hist_entry, rb_node);
+
+                if (hist_entry__sort(he, iter) > 0)
+                        p = &(*p)->rb_left;
+                else
+                        p = &(*p)->rb_right;
         }
 
-        return false;
+        rb_link_node(&he->rb_node, parent, p);
+        rb_insert_color(&he->rb_node, root);
+
+        if (he->leaf || he->filtered)
+                return;
+
+        nd = rb_first(&he->hroot_out);
+        while (nd) {
+                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+                nd = rb_next(nd);
+                rb_erase(&h->rb_node, &he->hroot_out);
+
+                resort_filtered_entry(&new_root, h);
+        }
+
+        he->hroot_out = new_root;
 }
 
-void hists__filter_by_socket(struct hists *hists)
+static void hists__filter_hierarchy(struct hists *hists, int type, const void *arg)
 {
         struct rb_node *nd;
+        struct rb_root new_root = RB_ROOT;
 
         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)) {
+        nd = rb_first(&hists->entries);
+        while (nd) {
                 struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+                int ret;
 
-                if (hists__filter_entry_by_socket(hists, h))
-                        continue;
+                ret = hist_entry__filter(h, type, arg);
 
-                hists__remove_entry_filter(hists, h, HIST_FILTER__SOCKET);
+                /*
+                 * case 1. non-matching type
+                 * zero out the period, set filter marker and move to child
+                 */
+                if (ret < 0) {
+                        memset(&h->stat, 0, sizeof(h->stat));
+                        h->filtered |= (1 << type);
+
+                        nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_CHILD);
+                }
+                /*
+                 * case 2. matched type (filter out)
+                 * set filter marker and move to next
+                 */
+                else if (ret == 1) {
+                        h->filtered |= (1 << type);
+
+                        nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+                }
+                /*
+                 * case 3. ok (not filtered)
+                 * add period to hists and parents, erase the filter marker
+                 * and move to next sibling
+                 */
+                else {
+                        hists__remove_entry_filter(hists, h, type);
+
+                        nd = __rb_hierarchy_next(&h->rb_node, HMD_FORCE_SIBLING);
+                }
+        }
+
+        hierarchy_recalc_total_periods(hists);
+
+        /*
+         * resort output after applying a new filter since filter in a lower
+         * hierarchy can change periods in a upper hierarchy.
+         */
+        nd = rb_first(&hists->entries);
+        while (nd) {
+                struct hist_entry *h = rb_entry(nd, struct hist_entry, rb_node);
+
+                nd = rb_next(nd);
+                rb_erase(&h->rb_node, &hists->entries);
+
+                resort_filtered_entry(&new_root, h);
         }
+
+        hists->entries = new_root;
+}
+
+void hists__filter_by_thread(struct hists *hists)
+{
+        if (symbol_conf.report_hierarchy)
+                hists__filter_hierarchy(hists, HIST_FILTER__THREAD,
+                                        hists->thread_filter);
+        else
+                hists__filter_by_type(hists, HIST_FILTER__THREAD,
+                                      hists__filter_entry_by_thread);
+}
+
+void hists__filter_by_dso(struct hists *hists)
+{
+        if (symbol_conf.report_hierarchy)
+                hists__filter_hierarchy(hists, HIST_FILTER__DSO,
+                                        hists->dso_filter);
+        else
+                hists__filter_by_type(hists, HIST_FILTER__DSO,
+                                      hists__filter_entry_by_dso);
+}
+
+void hists__filter_by_symbol(struct hists *hists)
+{
+        if (symbol_conf.report_hierarchy)
+                hists__filter_hierarchy(hists, HIST_FILTER__SYMBOL,
+                                        hists->symbol_filter_str);
+        else
+                hists__filter_by_type(hists, HIST_FILTER__SYMBOL,
+                                      hists__filter_entry_by_symbol);
+}
+
+void hists__filter_by_socket(struct hists *hists)
+{
+        if (symbol_conf.report_hierarchy)
+                hists__filter_hierarchy(hists, HIST_FILTER__SOCKET,
+                                        &hists->socket_filter);
+        else
+                hists__filter_by_type(hists, HIST_FILTER__SOCKET,
+                                      hists__filter_entry_by_socket);
 }
 
 void events_stats__inc(struct events_stats *stats, u32 type)
@@ -1585,7 +2223,7 @@ int perf_hist_config(const char *var, const char *value)
         return 0;
 }
 
-int __hists__init(struct hists *hists)
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list)
 {
         memset(hists, 0, sizeof(*hists));
         hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
@@ -1594,6 +2232,8 @@ int __hists__init(struct hists *hists)
         hists->entries = RB_ROOT;
         pthread_mutex_init(&hists->lock, NULL);
         hists->socket_filter = -1;
+        hists->hpp_list = hpp_list;
+        INIT_LIST_HEAD(&hists->hpp_formats);
         return 0;
 }
 
@@ -1622,15 +2262,26 @@ static void hists__delete_all_entries(struct hists *hists)
 static void hists_evsel__exit(struct perf_evsel *evsel)
 {
         struct hists *hists = evsel__hists(evsel);
+        struct perf_hpp_fmt *fmt, *pos;
+        struct perf_hpp_list_node *node, *tmp;
 
         hists__delete_all_entries(hists);
+
+        list_for_each_entry_safe(node, tmp, &hists->hpp_formats, list) {
+                perf_hpp_list__for_each_format_safe(&node->hpp, fmt, pos) {
+                        list_del(&fmt->list);
+                        free(fmt);
+                }
+                list_del(&node->list);
+                free(node);
+        }
 }
 
 static int hists_evsel__init(struct perf_evsel *evsel)
 {
         struct hists *hists = evsel__hists(evsel);
 
-        __hists__init(hists);
+        __hists__init(hists, &perf_hpp_list);
         return 0;
 }
 
@@ -1649,3 +2300,9 @@ int hists__init(void)
 
         return err;
 }
+
+void perf_hpp_list__init(struct perf_hpp_list *list)
+{
+        INIT_LIST_HEAD(&list->fields);
+        INIT_LIST_HEAD(&list->sorts);
+}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4ec4822a103..ead18c82294f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -66,6 +66,8 @@ struct hists {
         struct rb_root          entries_collapsed;
         u64                     nr_entries;
         u64                     nr_non_filtered_entries;
+        u64                     callchain_period;
+        u64                     callchain_non_filtered_period;
         struct thread           *thread_filter;
         const struct dso        *dso_filter;
         const char              *uid_filter_str;
@@ -75,6 +77,9 @@ struct hists {
         u64                     event_stream;
         u16                     col_len[HISTC_NR_COLS];
         int                     socket_filter;
+        struct perf_hpp_list    *hpp_list;
+        struct list_head        hpp_formats;
+        int                     nr_hpp_node;
 };
 
 struct hist_entry_iter;
@@ -121,15 +126,21 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
                          int max_stack_depth, void *arg);
 
+struct perf_hpp;
+struct perf_hpp_fmt;
+
 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);
 int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
                               struct hists *hists);
+int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
+                                   struct perf_hpp_fmt *fmt, int printed);
 void hist_entry__delete(struct hist_entry *he);
 
+void perf_evsel__output_resort(struct perf_evsel *evsel, struct ui_progress *prog);
 void hists__output_resort(struct hists *hists, struct ui_progress *prog);
-void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
+int 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__delete_entries(struct hists *hists);
@@ -185,10 +196,10 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel)
 }
 
 int hists__init(void);
-int __hists__init(struct hists *hists);
+int __hists__init(struct hists *hists, struct perf_hpp_list *hpp_list);
 
 struct rb_root *hists__get_rotate_entries_in(struct hists *hists);
-bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
+int hists__collapse_insert_entry(struct hists *hists,
                                   struct rb_root *root, struct hist_entry *he);
 
 struct perf_hpp {
@@ -214,28 +225,64 @@ struct perf_hpp_fmt {
                             struct hist_entry *a, struct hist_entry *b);
         int64_t (*sort)(struct perf_hpp_fmt *fmt,
                         struct hist_entry *a, struct hist_entry *b);
+        bool (*equal)(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b);
+        void (*free)(struct perf_hpp_fmt *fmt);
 
         struct list_head list;
         struct list_head sort_list;
         bool elide;
         int len;
         int user_len;
+        int idx;
+        int level;
+};
+
+struct perf_hpp_list {
+        struct list_head fields;
+        struct list_head sorts;
 };
 
-extern struct list_head perf_hpp__list;
-extern struct list_head perf_hpp__sort_list;
+extern struct perf_hpp_list perf_hpp_list;
+
+struct perf_hpp_list_node {
+        struct list_head        list;
+        struct perf_hpp_list    hpp;
+        int                     level;
+        bool                    skip;
+};
+
+void perf_hpp_list__column_register(struct perf_hpp_list *list,
+                                    struct perf_hpp_fmt *format);
+void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
+                                        struct perf_hpp_fmt *format);
+
+static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
+{
+        perf_hpp_list__column_register(&perf_hpp_list, format);
+}
+
+static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
+{
+        perf_hpp_list__register_sort_field(&perf_hpp_list, format);
+}
+
+#define perf_hpp_list__for_each_format(_list, format) \
+        list_for_each_entry(format, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format(format) \
-        list_for_each_entry(format, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_format_safe(_list, format, tmp) \
+        list_for_each_entry_safe(format, tmp, &(_list)->fields, list)
 
-#define perf_hpp__for_each_format_safe(format, tmp)     \
-        list_for_each_entry_safe(format, tmp, &perf_hpp__list, list)
+#define perf_hpp_list__for_each_sort_list(_list, format) \
+        list_for_each_entry(format, &(_list)->sorts, sort_list)
 
-#define perf_hpp__for_each_sort_list(format) \
-        list_for_each_entry(format, &perf_hpp__sort_list, sort_list)
+#define perf_hpp_list__for_each_sort_list_safe(_list, format, tmp)      \
+        list_for_each_entry_safe(format, tmp, &(_list)->sorts, 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)
+#define hists__for_each_format(hists, format) \
+        perf_hpp_list__for_each_format((hists)->hpp_list, fmt)
+
+#define hists__for_each_sort_list(hists, format) \
+        perf_hpp_list__for_each_sort_list((hists)->hpp_list, fmt)
 
 extern struct perf_hpp_fmt perf_hpp__format[];
 
@@ -254,21 +301,29 @@ 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__setup_output_field(struct perf_hpp_list *list);
+void perf_hpp__reset_output_field(struct perf_hpp_list *list);
+void perf_hpp__append_sort_keys(struct perf_hpp_list *list);
+int perf_hpp__setup_hists_formats(struct perf_hpp_list *list,
+                                  struct perf_evlist *evlist);
 
-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);
 bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format);
 bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists);
+bool perf_hpp__is_trace_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcline_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_srcfile_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_thread_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_comm_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_dso_entry(struct perf_hpp_fmt *fmt);
+bool perf_hpp__is_sym_entry(struct perf_hpp_fmt *fmt);
+
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt);
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg);
 
 static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format,
                                          struct hists *hists)
@@ -372,6 +427,7 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 #endif
 
 unsigned int hists__sort_list_width(struct hists *hists);
+unsigned int hists__overhead_width(struct hists *hists);
 
 void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
                           struct perf_sample *sample, bool nonany_branch_mode);
@@ -381,4 +437,26 @@ 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);
 
+void perf_hpp_list__init(struct perf_hpp_list *list);
+
+enum hierarchy_move_dir {
+        HMD_NORMAL,
+        HMD_FORCE_SIBLING,
+        HMD_FORCE_CHILD,
+};
+
+struct rb_node *rb_hierarchy_last(struct rb_node *node);
+struct rb_node *__rb_hierarchy_next(struct rb_node *node,
+                                    enum hierarchy_move_dir hmd);
+struct rb_node *rb_hierarchy_prev(struct rb_node *node);
+
+static inline struct rb_node *rb_hierarchy_next(struct rb_node *node)
+{
+        return __rb_hierarchy_next(node, HMD_NORMAL);
+}
+
+#define HIERARCHY_INDENT  3
+
+bool hist_entry__has_hierarchy_children(struct hist_entry *he, float limit);
+
 #endif  /* __PERF_HIST_H */
diff --git a/tools/perf/util/jit.h b/tools/perf/util/jit.h
new file mode 100644
index 000000000000..a1e99da0715a
--- /dev/null
+++ b/tools/perf/util/jit.h
@@ -0,0 +1,15 @@
+#ifndef __JIT_H__
+#define __JIT_H__
+
+#include <data.h>
+
+extern int jit_process(struct perf_session *session,
+                       struct perf_data_file *output,
+                       struct machine *machine,
+                       char *filename,
+                       pid_t pid,
+                       u64 *nbytes);
+
+extern int jit_inject_record(const char *filename);
+
+#endif /* __JIT_H__ */
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
new file mode 100644
index 000000000000..cd272cc21e05
--- /dev/null
+++ b/tools/perf/util/jitdump.c
@@ -0,0 +1,697 @@
+#include <sys/types.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <byteswap.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+
+#include "util.h"
+#include "event.h"
+#include "debug.h"
+#include "evlist.h"
+#include "symbol.h"
+#include "strlist.h"
+#include <elf.h>
+
+#include "session.h"
+#include "jit.h"
+#include "jitdump.h"
+#include "genelf.h"
+#include "../builtin.h"
+
+struct jit_buf_desc {
+        struct perf_data_file *output;
+        struct perf_session *session;
+        struct machine *machine;
+        union jr_entry   *entry;
+        void             *buf;
+        uint64_t         sample_type;
+        size_t           bufsize;
+        FILE             *in;
+        bool             needs_bswap; /* handles cross-endianess */
+        void             *debug_data;
+        size_t           nr_debug_entries;
+        uint32_t         code_load_count;
+        u64              bytes_written;
+        struct rb_root   code_root;
+        char             dir[PATH_MAX];
+};
+
+struct debug_line_info {
+        unsigned long vma;
+        unsigned int lineno;
+        /* The filename format is unspecified, absolute path, relative etc. */
+        char const filename[0];
+};
+
+struct jit_tool {
+        struct perf_tool tool;
+        struct perf_data_file   output;
+        struct perf_data_file   input;
+        u64 bytes_written;
+};
+
+#define hmax(a, b) ((a) > (b) ? (a) : (b))
+#define get_jit_tool(t) (container_of(tool, struct jit_tool, tool))
+
+static int
+jit_emit_elf(char *filename,
+             const char *sym,
+             uint64_t code_addr,
+             const void *code,
+             int csize,
+             void *debug,
+             int nr_debug_entries)
+{
+        int ret, fd;
+
+        if (verbose > 0)
+                fprintf(stderr, "write ELF image %s\n", filename);
+
+        fd = open(filename, O_CREAT|O_TRUNC|O_WRONLY, 0644);
+        if (fd == -1) {
+                pr_warning("cannot create jit ELF %s: %s\n", filename, strerror(errno));
+                return -1;
+        }
+
+        ret = jit_write_elf(fd, code_addr, sym, (const void *)code, csize, debug, nr_debug_entries);
+
+        close(fd);
+
+        if (ret)
+                unlink(filename);
+
+        return ret;
+}
+
+static void
+jit_close(struct jit_buf_desc *jd)
+{
+        if (!(jd && jd->in))
+                return;
+        funlockfile(jd->in);
+        fclose(jd->in);
+        jd->in = NULL;
+}
+
+static int
+jit_validate_events(struct perf_session *session)
+{
+        struct perf_evsel *evsel;
+
+        /*
+         * check that all events use CLOCK_MONOTONIC
+         */
+        evlist__for_each(session->evlist, evsel) {
+                if (evsel->attr.use_clockid == 0 || evsel->attr.clockid != CLOCK_MONOTONIC)
+                        return -1;
+        }
+        return 0;
+}
+
+static int
+jit_open(struct jit_buf_desc *jd, const char *name)
+{
+        struct jitheader header;
+        struct jr_prefix *prefix;
+        ssize_t bs, bsz = 0;
+        void *n, *buf = NULL;
+        int ret, retval = -1;
+
+        jd->in = fopen(name, "r");
+        if (!jd->in)
+                return -1;
+
+        bsz = hmax(sizeof(header), sizeof(*prefix));
+
+        buf = malloc(bsz);
+        if (!buf)
+                goto error;
+
+        /*
+         * protect from writer modifying the file while we are reading it
+         */
+        flockfile(jd->in);
+
+        ret = fread(buf, sizeof(header), 1, jd->in);
+        if (ret != 1)
+                goto error;
+
+        memcpy(&header, buf, sizeof(header));
+
+        if (header.magic != JITHEADER_MAGIC) {
+                if (header.magic != JITHEADER_MAGIC_SW)
+                        goto error;
+                jd->needs_bswap = true;
+        }
+
+        if (jd->needs_bswap) {
+                header.version    = bswap_32(header.version);
+                header.total_size = bswap_32(header.total_size);
+                header.pid        = bswap_32(header.pid);
+                header.elf_mach   = bswap_32(header.elf_mach);
+                header.timestamp  = bswap_64(header.timestamp);
+                header.flags      = bswap_64(header.flags);
+        }
+
+        if (verbose > 2)
+                pr_debug("version=%u\nhdr.size=%u\nts=0x%llx\npid=%d\nelf_mach=%d\n",
+                        header.version,
+                        header.total_size,
+                        (unsigned long long)header.timestamp,
+                        header.pid,
+                        header.elf_mach);
+
+        if (header.flags & JITDUMP_FLAGS_RESERVED) {
+                pr_err("jitdump file contains invalid or unsupported flags 0x%llx\n",
+                       (unsigned long long)header.flags & JITDUMP_FLAGS_RESERVED);
+                goto error;
+        }
+
+        /*
+         * validate event is using the correct clockid
+         */
+        if (jit_validate_events(jd->session)) {
+                pr_err("error, jitted code must be sampled with perf record -k 1\n");
+                goto error;
+        }
+
+        bs = header.total_size - sizeof(header);
+
+        if (bs > bsz) {
+                n = realloc(buf, bs);
+                if (!n)
+                        goto error;
+                bsz = bs;
+                buf = n;
+                /* read extra we do not know about */
+                ret = fread(buf, bs - bsz, 1, jd->in);
+                if (ret != 1)
+                        goto error;
+        }
+        /*
+         * keep dirname for generating files and mmap records
+         */
+        strcpy(jd->dir, name);
+        dirname(jd->dir);
+
+        return 0;
+error:
+        funlockfile(jd->in);
+        fclose(jd->in);
+        return retval;
+}
+
+static union jr_entry *
+jit_get_next_entry(struct jit_buf_desc *jd)
+{
+        struct jr_prefix *prefix;
+        union jr_entry *jr;
+        void *addr;
+        size_t bs, size;
+        int id, ret;
+
+        if (!(jd && jd->in))
+                return NULL;
+
+        if (jd->buf == NULL) {
+                size_t sz = getpagesize();
+                if (sz < sizeof(*prefix))
+                        sz = sizeof(*prefix);
+
+                jd->buf = malloc(sz);
+                if (jd->buf == NULL)
+                        return NULL;
+
+                jd->bufsize = sz;
+        }
+
+        prefix = jd->buf;
+
+        /*
+         * file is still locked at this point
+         */
+        ret = fread(prefix, sizeof(*prefix), 1, jd->in);
+        if (ret  != 1)
+                return NULL;
+
+        if (jd->needs_bswap) {
+                prefix->id         = bswap_32(prefix->id);
+                prefix->total_size = bswap_32(prefix->total_size);
+                prefix->timestamp  = bswap_64(prefix->timestamp);
+        }
+        id   = prefix->id;
+        size = prefix->total_size;
+
+        bs = (size_t)size;
+        if (bs < sizeof(*prefix))
+                return NULL;
+
+        if (id >= JIT_CODE_MAX) {
+                pr_warning("next_entry: unknown prefix %d, skipping\n", id);
+                return NULL;
+        }
+        if (bs > jd->bufsize) {
+                void *n;
+                n = realloc(jd->buf, bs);
+                if (!n)
+                        return NULL;
+                jd->buf = n;
+                jd->bufsize = bs;
+        }
+
+        addr = ((void *)jd->buf) + sizeof(*prefix);
+
+        ret = fread(addr, bs - sizeof(*prefix), 1, jd->in);
+        if (ret != 1)
+                return NULL;
+
+        jr = (union jr_entry *)jd->buf;
+
+        switch(id) {
+        case JIT_CODE_DEBUG_INFO:
+                if (jd->needs_bswap) {
+                        uint64_t n;
+                        jr->info.code_addr = bswap_64(jr->info.code_addr);
+                        jr->info.nr_entry  = bswap_64(jr->info.nr_entry);
+                        for (n = 0 ; n < jr->info.nr_entry; n++) {
+                                jr->info.entries[n].addr    = bswap_64(jr->info.entries[n].addr);
+                                jr->info.entries[n].lineno  = bswap_32(jr->info.entries[n].lineno);
+                                jr->info.entries[n].discrim = bswap_32(jr->info.entries[n].discrim);
+                        }
+                }
+                break;
+        case JIT_CODE_CLOSE:
+                break;
+        case JIT_CODE_LOAD:
+                if (jd->needs_bswap) {
+                        jr->load.pid       = bswap_32(jr->load.pid);
+                        jr->load.tid       = bswap_32(jr->load.tid);
+                        jr->load.vma       = bswap_64(jr->load.vma);
+                        jr->load.code_addr = bswap_64(jr->load.code_addr);
+                        jr->load.code_size = bswap_64(jr->load.code_size);
+                        jr->load.code_index= bswap_64(jr->load.code_index);
+                }
+                jd->code_load_count++;
+                break;
+        case JIT_CODE_MOVE:
+                if (jd->needs_bswap) {
+                        jr->move.pid           = bswap_32(jr->move.pid);
+                        jr->move.tid           = bswap_32(jr->move.tid);
+                        jr->move.vma           = bswap_64(jr->move.vma);
+                        jr->move.old_code_addr = bswap_64(jr->move.old_code_addr);
+                        jr->move.new_code_addr = bswap_64(jr->move.new_code_addr);
+                        jr->move.code_size     = bswap_64(jr->move.code_size);
+                        jr->move.code_index    = bswap_64(jr->move.code_index);
+                }
+                break;
+        case JIT_CODE_MAX:
+        default:
+                return NULL;
+        }
+        return jr;
+}
+
+static int
+jit_inject_event(struct jit_buf_desc *jd, union perf_event *event)
+{
+        ssize_t size;
+
+        size = perf_data_file__write(jd->output, event, event->header.size);
+        if (size < 0)
+                return -1;
+
+        jd->bytes_written += size;
+        return 0;
+}
+
+static int jit_repipe_code_load(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+        struct perf_sample sample;
+        union perf_event *event;
+        struct perf_tool *tool = jd->session->tool;
+        uint64_t code, addr;
+        uintptr_t uaddr;
+        char *filename;
+        struct stat st;
+        size_t size;
+        u16 idr_size;
+        const char *sym;
+        uint32_t count;
+        int ret, csize;
+        pid_t pid, tid;
+        struct {
+                u32 pid, tid;
+                u64 time;
+        } *id;
+
+        pid   = jr->load.pid;
+        tid   = jr->load.tid;
+        csize = jr->load.code_size;
+        addr  = jr->load.code_addr;
+        sym   = (void *)((unsigned long)jr + sizeof(jr->load));
+        code  = (unsigned long)jr + jr->load.p.total_size - csize;
+        count = jr->load.code_index;
+        idr_size = jd->machine->id_hdr_size;
+
+        event = calloc(1, sizeof(*event) + idr_size);
+        if (!event)
+                return -1;
+
+        filename = event->mmap2.filename;
+        size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%u.so",
+                        jd->dir,
+                        pid,
+                        count);
+
+        size++; /* for \0 */
+
+        size = PERF_ALIGN(size, sizeof(u64));
+        uaddr = (uintptr_t)code;
+        ret = jit_emit_elf(filename, sym, addr, (const void *)uaddr, csize, jd->debug_data, jd->nr_debug_entries);
+
+        if (jd->debug_data && jd->nr_debug_entries) {
+                free(jd->debug_data);
+                jd->debug_data = NULL;
+                jd->nr_debug_entries = 0;
+        }
+
+        if (ret) {
+                free(event);
+                return -1;
+        }
+        if (stat(filename, &st))
+                memset(&st, 0, sizeof(stat));
+
+        event->mmap2.header.type = PERF_RECORD_MMAP2;
+        event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+        event->mmap2.header.size = (sizeof(event->mmap2) -
+                        (sizeof(event->mmap2.filename) - size) + idr_size);
+
+        event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+        event->mmap2.start = addr;
+        event->mmap2.len   = csize;
+        event->mmap2.pid   = pid;
+        event->mmap2.tid   = tid;
+        event->mmap2.ino   = st.st_ino;
+        event->mmap2.maj   = major(st.st_dev);
+        event->mmap2.min   = minor(st.st_dev);
+        event->mmap2.prot  = st.st_mode;
+        event->mmap2.flags = MAP_SHARED;
+        event->mmap2.ino_generation = 1;
+
+        id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+        if (jd->sample_type & PERF_SAMPLE_TID) {
+                id->pid  = pid;
+                id->tid  = tid;
+        }
+        if (jd->sample_type & PERF_SAMPLE_TIME)
+                id->time = jr->load.p.timestamp;
+
+        /*
+         * create pseudo sample to induce dso hit increment
+         * use first address as sample address
+         */
+        memset(&sample, 0, sizeof(sample));
+        sample.pid  = pid;
+        sample.tid  = tid;
+        sample.time = id->time;
+        sample.ip   = addr;
+
+        ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+        if (ret)
+                return ret;
+
+        ret = jit_inject_event(jd, event);
+        /*
+         * mark dso as use to generate buildid in the header
+         */
+        if (!ret)
+                build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+        return ret;
+}
+
+static int jit_repipe_code_move(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+        struct perf_sample sample;
+        union perf_event *event;
+        struct perf_tool *tool = jd->session->tool;
+        char *filename;
+        size_t size;
+        struct stat st;
+        u16 idr_size;
+        int ret;
+        pid_t pid, tid;
+        struct {
+                u32 pid, tid;
+                u64 time;
+        } *id;
+
+        pid = jr->move.pid;
+        tid =  jr->move.tid;
+        idr_size = jd->machine->id_hdr_size;
+
+        /*
+         * +16 to account for sample_id_all (hack)
+         */
+        event = calloc(1, sizeof(*event) + 16);
+        if (!event)
+                return -1;
+
+        filename = event->mmap2.filename;
+        size = snprintf(filename, PATH_MAX, "%s/jitted-%d-%"PRIu64,
+                 jd->dir,
+                 pid,
+                 jr->move.code_index);
+
+        size++; /* for \0 */
+
+        if (stat(filename, &st))
+                memset(&st, 0, sizeof(stat));
+
+        size = PERF_ALIGN(size, sizeof(u64));
+
+        event->mmap2.header.type = PERF_RECORD_MMAP2;
+        event->mmap2.header.misc = PERF_RECORD_MISC_USER;
+        event->mmap2.header.size = (sizeof(event->mmap2) -
+                        (sizeof(event->mmap2.filename) - size) + idr_size);
+        event->mmap2.pgoff = GEN_ELF_TEXT_OFFSET;
+        event->mmap2.start = jr->move.new_code_addr;
+        event->mmap2.len   = jr->move.code_size;
+        event->mmap2.pid   = pid;
+        event->mmap2.tid   = tid;
+        event->mmap2.ino   = st.st_ino;
+        event->mmap2.maj   = major(st.st_dev);
+        event->mmap2.min   = minor(st.st_dev);
+        event->mmap2.prot  = st.st_mode;
+        event->mmap2.flags = MAP_SHARED;
+        event->mmap2.ino_generation = 1;
+
+        id = (void *)((unsigned long)event + event->mmap.header.size - idr_size);
+        if (jd->sample_type & PERF_SAMPLE_TID) {
+                id->pid  = pid;
+                id->tid  = tid;
+        }
+        if (jd->sample_type & PERF_SAMPLE_TIME)
+                id->time = jr->load.p.timestamp;
+
+        /*
+         * create pseudo sample to induce dso hit increment
+         * use first address as sample address
+         */
+        memset(&sample, 0, sizeof(sample));
+        sample.pid  = pid;
+        sample.tid  = tid;
+        sample.time = id->time;
+        sample.ip   = jr->move.new_code_addr;
+
+        ret = perf_event__process_mmap2(tool, event, &sample, jd->machine);
+        if (ret)
+                return ret;
+
+        ret = jit_inject_event(jd, event);
+        if (!ret)
+                build_id__mark_dso_hit(tool, event, &sample, NULL, jd->machine);
+
+        return ret;
+}
+
+static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
+{
+        void *data;
+        size_t sz;
+
+        if (!(jd && jr))
+                return -1;
+
+        sz  = jr->prefix.total_size - sizeof(jr->info);
+        data = malloc(sz);
+        if (!data)
+                return -1;
+
+        memcpy(data, &jr->info.entries, sz);
+
+        jd->debug_data       = data;
+
+        /*
+         * we must use nr_entry instead of size here because
+         * we cannot distinguish actual entry from padding otherwise
+         */
+        jd->nr_debug_entries = jr->info.nr_entry;
+
+        return 0;
+}
+
+static int
+jit_process_dump(struct jit_buf_desc *jd)
+{
+        union jr_entry *jr;
+        int ret;
+
+        while ((jr = jit_get_next_entry(jd))) {
+                switch(jr->prefix.id) {
+                case JIT_CODE_LOAD:
+                        ret = jit_repipe_code_load(jd, jr);
+                        break;
+                case JIT_CODE_MOVE:
+                        ret = jit_repipe_code_move(jd, jr);
+                        break;
+                case JIT_CODE_DEBUG_INFO:
+                        ret = jit_repipe_debug_info(jd, jr);
+                        break;
+                default:
+                        ret = 0;
+                        continue;
+                }
+        }
+        return ret;
+}
+
+static int
+jit_inject(struct jit_buf_desc *jd, char *path)
+{
+        int ret;
+
+        if (verbose > 0)
+                fprintf(stderr, "injecting: %s\n", path);
+
+        ret = jit_open(jd, path);
+        if (ret)
+                return -1;
+
+        ret = jit_process_dump(jd);
+
+        jit_close(jd);
+
+        if (verbose > 0)
+                fprintf(stderr, "injected: %s (%d)\n", path, ret);
+
+        return 0;
+}
+
+/*
+ * File must be with pattern .../jit-XXXX.dump
+ * where XXXX is the PID of the process which did the mmap()
+ * as captured in the RECORD_MMAP record
+ */
+static int
+jit_detect(char *mmap_name, pid_t pid)
+ {
+        char *p;
+        char *end = NULL;
+        pid_t pid2;
+
+        if (verbose > 2)
+                fprintf(stderr, "jit marker trying : %s\n", mmap_name);
+        /*
+         * get file name
+         */
+        p = strrchr(mmap_name, '/');
+        if (!p)
+                return -1;
+
+        /*
+         * match prefix
+         */
+        if (strncmp(p, "/jit-", 5))
+                return -1;
+
+        /*
+         * skip prefix
+         */
+        p += 5;
+
+        /*
+         * must be followed by a pid
+         */
+        if (!isdigit(*p))
+                return -1;
+
+        pid2 = (int)strtol(p, &end, 10);
+        if (!end)
+                return -1;
+
+        /*
+         * pid does not match mmap pid
+         * pid==0 in system-wide mode (synthesized)
+         */
+        if (pid && pid2 != pid)
+                return -1;
+        /*
+         * validate suffix
+         */
+        if (strcmp(end, ".dump"))
+                return -1;
+
+        if (verbose > 0)
+                fprintf(stderr, "jit marker found: %s\n", mmap_name);
+
+        return 0;
+}
+
+int
+jit_process(struct perf_session *session,
+            struct perf_data_file *output,
+            struct machine *machine,
+            char *filename,
+            pid_t pid,
+            u64 *nbytes)
+{
+        struct perf_evsel *first;
+        struct jit_buf_desc jd;
+        int ret;
+
+        /*
+         * first, detect marker mmap (i.e., the jitdump mmap)
+         */
+        if (jit_detect(filename, pid))
+                return 0;
+
+        memset(&jd, 0, sizeof(jd));
+
+        jd.session = session;
+        jd.output  = output;
+        jd.machine = machine;
+
+        /*
+         * track sample_type to compute id_all layout
+         * perf sets the same sample type to all events as of now
+         */
+        first = perf_evlist__first(session->evlist);
+        jd.sample_type = first->attr.sample_type;
+
+        *nbytes = 0;
+
+        ret = jit_inject(&jd, filename);
+        if (!ret) {
+                *nbytes = jd.bytes_written;
+                ret = 1;
+        }
+
+        return ret;
+}
diff --git a/tools/perf/util/jitdump.h b/tools/perf/util/jitdump.h
new file mode 100644
index 000000000000..b66c1f503d9e
--- /dev/null
+++ b/tools/perf/util/jitdump.h
@@ -0,0 +1,124 @@
+/*
+ * jitdump.h: jitted code info encapsulation file format
+ *
+ * Adapted from OProfile GPLv2 support jidump.h:
+ * Copyright 2007 OProfile authors
+ * Jens Wilke
+ * Daniel Hansel
+ * Copyright IBM Corporation 2007
+ */
+#ifndef JITDUMP_H
+#define JITDUMP_H
+
+#include <sys/time.h>
+#include <time.h>
+#include <stdint.h>
+
+/* JiTD */
+#define JITHEADER_MAGIC         0x4A695444
+#define JITHEADER_MAGIC_SW      0x4454694A
+
+#define PADDING_8ALIGNED(x) ((((x) + 7) & 7) ^ 7)
+
+#define JITHEADER_VERSION 1
+
+enum jitdump_flags_bits {
+        JITDUMP_FLAGS_MAX_BIT,
+};
+
+#define JITDUMP_FLAGS_RESERVED (JITDUMP_FLAGS_MAX_BIT < 64 ? \
+                                (~((1ULL << JITDUMP_FLAGS_MAX_BIT) - 1)) : 0)
+
+struct jitheader {
+        uint32_t magic;         /* characters "jItD" */
+        uint32_t version;       /* header version */
+        uint32_t total_size;    /* total size of header */
+        uint32_t elf_mach;      /* elf mach target */
+        uint32_t pad1;          /* reserved */
+        uint32_t pid;           /* JIT process id */
+        uint64_t timestamp;     /* timestamp */
+        uint64_t flags;         /* flags */
+};
+
+enum jit_record_type {
+        JIT_CODE_LOAD           = 0,
+        JIT_CODE_MOVE           = 1,
+        JIT_CODE_DEBUG_INFO     = 2,
+        JIT_CODE_CLOSE          = 3,
+
+        JIT_CODE_MAX,
+};
+
+/* record prefix (mandatory in each record) */
+struct jr_prefix {
+        uint32_t id;
+        uint32_t total_size;
+        uint64_t timestamp;
+};
+
+struct jr_code_load {
+        struct jr_prefix p;
+
+        uint32_t pid;
+        uint32_t tid;
+        uint64_t vma;
+        uint64_t code_addr;
+        uint64_t code_size;
+        uint64_t code_index;
+};
+
+struct jr_code_close {
+        struct jr_prefix p;
+};
+
+struct jr_code_move {
+        struct jr_prefix p;
+
+        uint32_t pid;
+        uint32_t tid;
+        uint64_t vma;
+        uint64_t old_code_addr;
+        uint64_t new_code_addr;
+        uint64_t code_size;
+        uint64_t code_index;
+};
+
+struct debug_entry {
+        uint64_t addr;
+        int lineno;         /* source line number starting at 1 */
+        int discrim;        /* column discriminator, 0 is default */
+        const char name[0]; /* null terminated filename, \xff\0 if same as previous entry */
+};
+
+struct jr_code_debug_info {
+        struct jr_prefix p;
+
+        uint64_t code_addr;
+        uint64_t nr_entry;
+        struct debug_entry entries[0];
+};
+
+union jr_entry {
+        struct jr_code_debug_info info;
+        struct jr_code_close close;
+        struct jr_code_load load;
+        struct jr_code_move move;
+        struct jr_prefix prefix;
+};
+
+static inline struct debug_entry *
+debug_entry_next(struct debug_entry *ent)
+{
+        void *a = ent + 1;
+        size_t l = strlen(ent->name) + 1;
+        return a + l;
+}
+
+static inline char *
+debug_entry_file(struct debug_entry *ent)
+{
+        void *a = ent + 1;
+        return a;
+}
+
+#endif /* !JITDUMP_H */
diff --git a/tools/perf/util/kvm-stat.h b/tools/perf/util/kvm-stat.h
index ae825d4ec110..d01e73592f6e 100644
--- a/tools/perf/util/kvm-stat.h
+++ b/tools/perf/util/kvm-stat.h
@@ -122,6 +122,7 @@ void exit_event_decode_key(struct perf_kvm_stat *kvm,
 
 bool kvm_exit_event(struct perf_evsel *evsel);
 bool kvm_entry_event(struct perf_evsel *evsel);
+int setup_kvm_events_tp(struct perf_kvm_stat *kvm);
 
 #define define_exit_reasons_table(name, symbols)        \
         static struct exit_reasons_table name[] = {     \
@@ -133,8 +134,13 @@ bool kvm_entry_event(struct perf_evsel *evsel);
  */
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid);
 
-extern const char * const kvm_events_tp[];
+extern const char *kvm_events_tp[];
 extern struct kvm_reg_events_ops kvm_reg_events_ops[];
 extern const char * const kvm_skip_events[];
+extern const char *vcpu_id_str;
+extern const int decode_str_len;
+extern const char *kvm_exit_reason;
+extern const char *kvm_entry_trace;
+extern const char *kvm_exit_trace;
 
 #endif /* __PERF_KVM_STAT_H */
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2c2b443df5ba..1a3e45baf97f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -180,6 +180,16 @@ struct symbol *machine__find_kernel_symbol(struct machine *machine,
 }
 
 static inline
+struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
+                                                   enum map_type type, const char *name,
+                                                   struct map **mapp,
+                                                   symbol_filter_t filter)
+{
+        return map_groups__find_symbol_by_name(&machine->kmaps, type, name,
+                                               mapp, filter);
+}
+
+static inline
 struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
                                              struct map **mapp,
                                              symbol_filter_t filter)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
new file mode 100644
index 000000000000..75465f89a413
--- /dev/null
+++ b/tools/perf/util/mem-events.c
@@ -0,0 +1,255 @@
+#include <stddef.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <api/fs/fs.h>
+#include "mem-events.h"
+#include "debug.h"
+#include "symbol.h"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+        E("ldlat-loads",        "cpu/mem-loads,ldlat=30/P",     "mem-loads"),
+        E("ldlat-stores",       "cpu/mem-stores/P",             "mem-stores"),
+};
+#undef E
+
+#undef E
+
+char *perf_mem_events__name(int i)
+{
+        return (char *)perf_mem_events[i].name;
+}
+
+int perf_mem_events__parse(const char *str)
+{
+        char *tok, *saveptr = NULL;
+        bool found = false;
+        char *buf;
+        int j;
+
+        /* We need buffer that we know we can write to. */
+        buf = malloc(strlen(str) + 1);
+        if (!buf)
+                return -ENOMEM;
+
+        strcpy(buf, str);
+
+        tok = strtok_r((char *)buf, ",", &saveptr);
+
+        while (tok) {
+                for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+                        struct perf_mem_event *e = &perf_mem_events[j];
+
+                        if (strstr(e->tag, tok))
+                                e->record = found = true;
+                }
+
+                tok = strtok_r(NULL, ",", &saveptr);
+        }
+
+        free(buf);
+
+        if (found)
+                return 0;
+
+        pr_err("failed: event '%s' not found, use '-e list' to get list of available events\n", str);
+        return -1;
+}
+
+int perf_mem_events__init(void)
+{
+        const char *mnt = sysfs__mount();
+        bool found = false;
+        int j;
+
+        if (!mnt)
+                return -ENOENT;
+
+        for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+                char path[PATH_MAX];
+                struct perf_mem_event *e = &perf_mem_events[j];
+                struct stat st;
+
+                scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+                          mnt, e->sysfs_name);
+
+                if (!stat(path, &st))
+                        e->supported = found = true;
+        }
+
+        return found ? 0 : -ENOENT;
+}
+
+static const char * const tlb_access[] = {
+        "N/A",
+        "HIT",
+        "MISS",
+        "L1",
+        "L2",
+        "Walker",
+        "Fault",
+};
+
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+        size_t l = 0, i;
+        u64 m = PERF_MEM_TLB_NA;
+        u64 hit, miss;
+
+        sz -= 1; /* -1 for null termination */
+        out[0] = '\0';
+
+        if (mem_info)
+                m = mem_info->data_src.mem_dtlb;
+
+        hit = m & PERF_MEM_TLB_HIT;
+        miss = m & PERF_MEM_TLB_MISS;
+
+        /* already taken care of */
+        m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+        for (i = 0; m && i < ARRAY_SIZE(tlb_access); i++, m >>= 1) {
+                if (!(m & 0x1))
+                        continue;
+                if (l) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                l += scnprintf(out + l, sz - l, tlb_access[i]);
+        }
+        if (*out == '\0')
+                l += scnprintf(out, sz - l, "N/A");
+        if (hit)
+                l += scnprintf(out + l, sz - l, " hit");
+        if (miss)
+                l += scnprintf(out + l, sz - l, " miss");
+
+        return l;
+}
+
+static const char * const mem_lvl[] = {
+        "N/A",
+        "HIT",
+        "MISS",
+        "L1",
+        "LFB",
+        "L2",
+        "L3",
+        "Local RAM",
+        "Remote RAM (1 hop)",
+        "Remote RAM (2 hops)",
+        "Remote Cache (1 hop)",
+        "Remote Cache (2 hops)",
+        "I/O",
+        "Uncached",
+};
+
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+        size_t i, l = 0;
+        u64 m =  PERF_MEM_LVL_NA;
+        u64 hit, miss;
+
+        if (mem_info)
+                m  = mem_info->data_src.mem_lvl;
+
+        sz -= 1; /* -1 for null termination */
+        out[0] = '\0';
+
+        hit = m & PERF_MEM_LVL_HIT;
+        miss = m & PERF_MEM_LVL_MISS;
+
+        /* already taken care of */
+        m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+        for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+                if (!(m & 0x1))
+                        continue;
+                if (l) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                l += scnprintf(out + l, sz - l, mem_lvl[i]);
+        }
+        if (*out == '\0')
+                l += scnprintf(out, sz - l, "N/A");
+        if (hit)
+                l += scnprintf(out + l, sz - l, " hit");
+        if (miss)
+                l += scnprintf(out + l, sz - l, " miss");
+
+        return l;
+}
+
+static const char * const snoop_access[] = {
+        "N/A",
+        "None",
+        "Miss",
+        "Hit",
+        "HitM",
+};
+
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+        size_t i, l = 0;
+        u64 m = PERF_MEM_SNOOP_NA;
+
+        sz -= 1; /* -1 for null termination */
+        out[0] = '\0';
+
+        if (mem_info)
+                m = mem_info->data_src.mem_snoop;
+
+        for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
+                if (!(m & 0x1))
+                        continue;
+                if (l) {
+                        strcat(out, " or ");
+                        l += 4;
+                }
+                l += scnprintf(out + l, sz - l, snoop_access[i]);
+        }
+
+        if (*out == '\0')
+                l += scnprintf(out, sz - l, "N/A");
+
+        return l;
+}
+
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+        u64 mask = PERF_MEM_LOCK_NA;
+        int l;
+
+        if (mem_info)
+                mask = mem_info->data_src.mem_lock;
+
+        if (mask & PERF_MEM_LOCK_NA)
+                l = scnprintf(out, sz, "N/A");
+        else if (mask & PERF_MEM_LOCK_LOCKED)
+                l = scnprintf(out, sz, "Yes");
+        else
+                l = scnprintf(out, sz, "No");
+
+        return l;
+}
+
+int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+{
+        int i = 0;
+
+        i += perf_mem__lvl_scnprintf(out, sz, mem_info);
+        i += scnprintf(out + i, sz - i, "|SNP ");
+        i += perf_mem__snp_scnprintf(out + i, sz - i, mem_info);
+        i += scnprintf(out + i, sz - i, "|TLB ");
+        i += perf_mem__tlb_scnprintf(out + i, sz - i, mem_info);
+        i += scnprintf(out + i, sz - i, "|LCK ");
+        i += perf_mem__lck_scnprintf(out + i, sz - i, mem_info);
+
+        return i;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
new file mode 100644
index 000000000000..5d6d93066a6e
--- /dev/null
+++ b/tools/perf/util/mem-events.h
@@ -0,0 +1,35 @@
+#ifndef __PERF_MEM_EVENTS_H
+#define __PERF_MEM_EVENTS_H
+
+#include <stdbool.h>
+
+struct perf_mem_event {
+        bool            record;
+        bool            supported;
+        const char      *tag;
+        const char      *name;
+        const char      *sysfs_name;
+};
+
+enum {
+        PERF_MEM_EVENTS__LOAD,
+        PERF_MEM_EVENTS__STORE,
+        PERF_MEM_EVENTS__MAX,
+};
+
+extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
+
+int perf_mem_events__parse(const char *str);
+int perf_mem_events__init(void);
+
+char *perf_mem_events__name(int i);
+
+struct mem_info;
+int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);
+
+int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);
+
+#endif /* __PERF_MEM_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 813d9b272c81..4c19d5e79d8c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -279,7 +279,24 @@ const char *event_type(int type)
         return "unknown";
 }
 
+static int parse_events__is_name_term(struct parse_events_term *term)
+{
+        return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
+}
 
+static char *get_config_name(struct list_head *head_terms)
+{
+        struct parse_events_term *term;
+
+        if (!head_terms)
+                return NULL;
+
+        list_for_each_entry(term, head_terms, list)
+                if (parse_events__is_name_term(term))
+                        return term->val.str;
+
+        return NULL;
+}
 
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
@@ -333,11 +350,25 @@ static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES]
         return -1;
 }
 
+typedef int config_term_func_t(struct perf_event_attr *attr,
+                               struct parse_events_term *term,
+                               struct parse_events_error *err);
+static int config_term_common(struct perf_event_attr *attr,
+                              struct parse_events_term *term,
+                              struct parse_events_error *err);
+static int config_attr(struct perf_event_attr *attr,
+                       struct list_head *head,
+                       struct parse_events_error *err,
+                       config_term_func_t config_term);
+
 int parse_events_add_cache(struct list_head *list, int *idx,
-                           char *type, char *op_result1, char *op_result2)
+                           char *type, char *op_result1, char *op_result2,
+                           struct parse_events_error *err,
+                           struct list_head *head_config)
 {
         struct perf_event_attr attr;
-        char name[MAX_NAME_LEN];
+        LIST_HEAD(config_terms);
+        char name[MAX_NAME_LEN], *config_name;
         int cache_type = -1, cache_op = -1, cache_result = -1;
         char *op_result[2] = { op_result1, op_result2 };
         int i, n;
@@ -351,6 +382,7 @@ int parse_events_add_cache(struct list_head *list, int *idx,
         if (cache_type == -1)
                 return -EINVAL;
 
+        config_name = get_config_name(head_config);
         n = snprintf(name, MAX_NAME_LEN, "%s", type);
 
         for (i = 0; (i < 2) && (op_result[i]); i++) {
@@ -391,7 +423,16 @@ int parse_events_add_cache(struct list_head *list, int *idx,
         memset(&attr, 0, sizeof(attr));
         attr.config = cache_type | (cache_op << 8) | (cache_result << 16);
         attr.type = PERF_TYPE_HW_CACHE;
-        return add_event(list, idx, &attr, name, NULL);
+
+        if (head_config) {
+                if (config_attr(&attr, head_config, err,
+                                config_term_common))
+                        return -EINVAL;
+
+                if (get_config_terms(head_config, &config_terms))
+                        return -ENOMEM;
+        }
+        return add_event(list, idx, &attr, config_name ? : name, &config_terms);
 }
 
 static void tracepoint_error(struct parse_events_error *e, int err,
@@ -540,6 +581,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 struct __add_bpf_event_param {
         struct parse_events_evlist *data;
         struct list_head *list;
+        struct list_head *head_config;
 };
 
 static int add_bpf_event(struct probe_trace_event *tev, int fd,
@@ -556,7 +598,8 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
                  tev->group, tev->event, fd);
 
         err = parse_events_add_tracepoint(&new_evsels, &evlist->idx, tev->group,
-                                          tev->event, evlist->error, NULL);
+                                          tev->event, evlist->error,
+                                          param->head_config);
         if (err) {
                 struct perf_evsel *evsel, *tmp;
 
@@ -581,11 +624,12 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
                               struct list_head *list,
-                              struct bpf_object *obj)
+                              struct bpf_object *obj,
+                              struct list_head *head_config)
 {
         int err;
         char errbuf[BUFSIZ];
-        struct __add_bpf_event_param param = {data, list};
+        struct __add_bpf_event_param param = {data, list, head_config};
         static bool registered_unprobe_atexit = false;
 
         if (IS_ERR(obj) || !obj) {
@@ -631,17 +675,99 @@ errout:
         return err;
 }
 
+static int
+parse_events_config_bpf(struct parse_events_evlist *data,
+                        struct bpf_object *obj,
+                        struct list_head *head_config)
+{
+        struct parse_events_term *term;
+        int error_pos;
+
+        if (!head_config || list_empty(head_config))
+                return 0;
+
+        list_for_each_entry(term, head_config, list) {
+                char errbuf[BUFSIZ];
+                int err;
+
+                if (term->type_term != PARSE_EVENTS__TERM_TYPE_USER) {
+                        snprintf(errbuf, sizeof(errbuf),
+                                 "Invalid config term for BPF object");
+                        errbuf[BUFSIZ - 1] = '\0';
+
+                        data->error->idx = term->err_term;
+                        data->error->str = strdup(errbuf);
+                        return -EINVAL;
+                }
+
+                err = bpf__config_obj(obj, term, data->evlist, &error_pos);
+                if (err) {
+                        bpf__strerror_config_obj(obj, term, data->evlist,
+                                                 &error_pos, err, errbuf,
+                                                 sizeof(errbuf));
+                        data->error->help = strdup(
+"Hint:\tValid config terms:\n"
+"     \tmap:[<arraymap>].value<indices>=[value]\n"
+"     \tmap:[<eventmap>].event<indices>=[event]\n"
+"\n"
+"     \twhere <indices> is something like [0,3...5] or [all]\n"
+"     \t(add -v to see detail)");
+                        data->error->str = strdup(errbuf);
+                        if (err == -BPF_LOADER_ERRNO__OBJCONF_MAP_VALUE)
+                                data->error->idx = term->err_val;
+                        else
+                                data->error->idx = term->err_term + error_pos;
+                        return err;
+                }
+        }
+        return 0;
+}
+
+/*
+ * Split config terms:
+ * perf record -e bpf.c/call-graph=fp,map:array.value[0]=1/ ...
+ *  'call-graph=fp' is 'evt config', should be applied to each
+ *  events in bpf.c.
+ * 'map:array.value[0]=1' is 'obj config', should be processed
+ * with parse_events_config_bpf.
+ *
+ * Move object config terms from the first list to obj_head_config.
+ */
+static void
+split_bpf_config_terms(struct list_head *evt_head_config,
+                       struct list_head *obj_head_config)
+{
+        struct parse_events_term *term, *temp;
+
+        /*
+         * Currectly, all possible user config term
+         * belong to bpf object. parse_events__is_hardcoded_term()
+         * happends to be a good flag.
+         *
+         * See parse_events_config_bpf() and
+         * config_term_tracepoint().
+         */
+        list_for_each_entry_safe(term, temp, evt_head_config, list)
+                if (!parse_events__is_hardcoded_term(term))
+                        list_move_tail(&term->list, obj_head_config);
+}
+
 int parse_events_load_bpf(struct parse_events_evlist *data,
                           struct list_head *list,
                           char *bpf_file_name,
-                          bool source)
+                          bool source,
+                          struct list_head *head_config)
 {
+        int err;
         struct bpf_object *obj;
+        LIST_HEAD(obj_head_config);
+
+        if (head_config)
+                split_bpf_config_terms(head_config, &obj_head_config);
 
         obj = bpf__prepare_load(bpf_file_name, source);
         if (IS_ERR(obj)) {
                 char errbuf[BUFSIZ];
-                int err;
 
                 err = PTR_ERR(obj);
 
@@ -659,7 +785,18 @@ int parse_events_load_bpf(struct parse_events_evlist *data,
                 return err;
         }
 
-        return parse_events_load_bpf_obj(data, list, obj);
+        err = parse_events_load_bpf_obj(data, list, obj, head_config);
+        if (err)
+                return err;
+        err = parse_events_config_bpf(data, obj, &obj_head_config);
+
+        /*
+         * Caller doesn't know anything about obj_head_config,
+         * so combine them together again before returnning.
+         */
+        if (head_config)
+                list_splice_tail(&obj_head_config, head_config);
+        return err;
 }
 
 static int
@@ -746,9 +883,59 @@ static int check_type_val(struct parse_events_term *term,
         return -EINVAL;
 }
 
-typedef int config_term_func_t(struct perf_event_attr *attr,
-                               struct parse_events_term *term,
-                               struct parse_events_error *err);
+/*
+ * Update according to parse-events.l
+ */
+static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
+        [PARSE_EVENTS__TERM_TYPE_USER]                  = "<sysfs term>",
+        [PARSE_EVENTS__TERM_TYPE_CONFIG]                = "config",
+        [PARSE_EVENTS__TERM_TYPE_CONFIG1]               = "config1",
+        [PARSE_EVENTS__TERM_TYPE_CONFIG2]               = "config2",
+        [PARSE_EVENTS__TERM_TYPE_NAME]                  = "name",
+        [PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD]         = "period",
+        [PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ]           = "freq",
+        [PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE]    = "branch_type",
+        [PARSE_EVENTS__TERM_TYPE_TIME]                  = "time",
+        [PARSE_EVENTS__TERM_TYPE_CALLGRAPH]             = "call-graph",
+        [PARSE_EVENTS__TERM_TYPE_STACKSIZE]             = "stack-size",
+        [PARSE_EVENTS__TERM_TYPE_NOINHERIT]             = "no-inherit",
+        [PARSE_EVENTS__TERM_TYPE_INHERIT]               = "inherit",
+};
+
+static bool config_term_shrinked;
+
+static bool
+config_term_avail(int term_type, struct parse_events_error *err)
+{
+        if (term_type < 0 || term_type >= __PARSE_EVENTS__TERM_TYPE_NR) {
+                err->str = strdup("Invalid term_type");
+                return false;
+        }
+        if (!config_term_shrinked)
+                return true;
+
+        switch (term_type) {
+        case PARSE_EVENTS__TERM_TYPE_CONFIG:
+        case PARSE_EVENTS__TERM_TYPE_CONFIG1:
+        case PARSE_EVENTS__TERM_TYPE_CONFIG2:
+        case PARSE_EVENTS__TERM_TYPE_NAME:
+                return true;
+        default:
+                if (!err)
+                        return false;
+
+                /* term_type is validated so indexing is safe */
+                if (asprintf(&err->str, "'%s' is not usable in 'perf stat'",
+                             config_term_names[term_type]) < 0)
+                        err->str = NULL;
+                return false;
+        }
+}
+
+void parse_events__shrink_config_terms(void)
+{
+        config_term_shrinked = true;
+}
 
 static int config_term_common(struct perf_event_attr *attr,
                               struct parse_events_term *term,
@@ -815,6 +1002,17 @@ do {									   \
                 return -EINVAL;
         }
 
+        /*
+         * Check term availbility after basic checking so
+         * PARSE_EVENTS__TERM_TYPE_USER can be found and filtered.
+         *
+         * If check availbility at the entry of this function,
+         * user will see "'<sysfs term>' is not usable in 'perf stat'"
+         * if an invalid config term is provided for legacy events
+         * (for example, instructions/badterm/...), which is confusing.
+         */
+        if (!config_term_avail(term->type_term, err))
+                return -EINVAL;
         return 0;
 #undef CHECK_TYPE_VAL
 }
@@ -961,23 +1159,8 @@ int parse_events_add_numeric(struct parse_events_evlist *data,
                         return -ENOMEM;
         }
 
-        return add_event(list, &data->idx, &attr, NULL, &config_terms);
-}
-
-static int parse_events__is_name_term(struct parse_events_term *term)
-{
-        return term->type_term == PARSE_EVENTS__TERM_TYPE_NAME;
-}
-
-static char *pmu_event_name(struct list_head *head_terms)
-{
-        struct parse_events_term *term;
-
-        list_for_each_entry(term, head_terms, list)
-                if (parse_events__is_name_term(term))
-                        return term->val.str;
-
-        return NULL;
+        return add_event(list, &data->idx, &attr,
+                         get_config_name(head_config), &config_terms);
 }
 
 int parse_events_add_pmu(struct parse_events_evlist *data,
@@ -1024,7 +1207,7 @@ int parse_events_add_pmu(struct parse_events_evlist *data,
                 return -EINVAL;
 
         evsel = __add_event(list, &data->idx, &attr,
-                            pmu_event_name(head_config), pmu->cpus,
+                            get_config_name(head_config), pmu->cpus,
                             &config_terms);
         if (evsel) {
                 evsel->unit = info.unit;
@@ -1386,8 +1569,7 @@ int parse_events_terms(struct list_head *terms, const char *str)
                 return 0;
         }
 
-        if (data.terms)
-                parse_events__free_terms(data.terms);
+        parse_events_terms__delete(data.terms);
         return ret;
 }
 
@@ -1395,9 +1577,10 @@ int parse_events(struct perf_evlist *evlist, const char *str,
                  struct parse_events_error *err)
 {
         struct parse_events_evlist data = {
-                .list  = LIST_HEAD_INIT(data.list),
-                .idx   = evlist->nr_entries,
-                .error = err,
+                .list   = LIST_HEAD_INIT(data.list),
+                .idx    = evlist->nr_entries,
+                .error  = err,
+                .evlist = evlist,
         };
         int ret;
 
@@ -2068,12 +2251,29 @@ int parse_events_term__clone(struct parse_events_term **new,
                         term->err_term, term->err_val);
 }
 
-void parse_events__free_terms(struct list_head *terms)
+void parse_events_terms__purge(struct list_head *terms)
 {
         struct parse_events_term *term, *h;
 
-        list_for_each_entry_safe(term, h, terms, list)
+        list_for_each_entry_safe(term, h, terms, list) {
+                if (term->array.nr_ranges)
+                        free(term->array.ranges);
+                list_del_init(&term->list);
                 free(term);
+        }
+}
+
+void parse_events_terms__delete(struct list_head *terms)
+{
+        if (!terms)
+                return;
+        parse_events_terms__purge(terms);
+        free(terms);
+}
+
+void parse_events__clear_array(struct parse_events_array *a)
+{
+        free(a->ranges);
 }
 
 void parse_events_evlist_error(struct parse_events_evlist *data,
@@ -2088,6 +2288,33 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
         WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
 }
 
+static void config_terms_list(char *buf, size_t buf_sz)
+{
+        int i;
+        bool first = true;
+
+        buf[0] = '\0';
+        for (i = 0; i < __PARSE_EVENTS__TERM_TYPE_NR; i++) {
+                const char *name = config_term_names[i];
+
+                if (!config_term_avail(i, NULL))
+                        continue;
+                if (!name)
+                        continue;
+                if (name[0] == '<')
+                        continue;
+
+                if (strlen(buf) + strlen(name) + 2 >= buf_sz)
+                        return;
+
+                if (!first)
+                        strcat(buf, ",");
+                else
+                        first = false;
+                strcat(buf, name);
+        }
+}
+
 /*
  * Return string contains valid config terms of an event.
  * @additional_terms: For terms such as PMU sysfs terms.
@@ -2095,17 +2322,18 @@ void parse_events_evlist_error(struct parse_events_evlist *data,
 char *parse_events_formats_error_string(char *additional_terms)
 {
         char *str;
-        static const char *static_terms = "config,config1,config2,name,"
-                                          "period,freq,branch_type,time,"
-                                          "call-graph,stack-size\n";
+        /* "branch_type" is the longest name */
+        char static_terms[__PARSE_EVENTS__TERM_TYPE_NR *
+                          (sizeof("branch_type") - 1)];
 
+        config_terms_list(static_terms, sizeof(static_terms));
         /* valid terms */
         if (additional_terms) {
-                if (!asprintf(&str, "valid terms: %s,%s",
-                              additional_terms, static_terms))
+                if (asprintf(&str, "valid terms: %s,%s",
+                             additional_terms, static_terms) < 0)
                         goto fail;
         } else {
-                if (!asprintf(&str, "valid terms: %s", static_terms))
+                if (asprintf(&str, "valid terms: %s", static_terms) < 0)
                         goto fail;
         }
         return str;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f1a6db107241..67e493088e81 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -68,11 +68,21 @@ enum {
         PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
         PARSE_EVENTS__TERM_TYPE_STACKSIZE,
         PARSE_EVENTS__TERM_TYPE_NOINHERIT,
-        PARSE_EVENTS__TERM_TYPE_INHERIT
+        PARSE_EVENTS__TERM_TYPE_INHERIT,
+        __PARSE_EVENTS__TERM_TYPE_NR,
+};
+
+struct parse_events_array {
+        size_t nr_ranges;
+        struct {
+                unsigned int start;
+                size_t length;
+        } *ranges;
 };
 
 struct parse_events_term {
         char *config;
+        struct parse_events_array array;
         union {
                 char *str;
                 u64  num;
@@ -98,12 +108,14 @@ struct parse_events_evlist {
         int                        idx;
         int                        nr_groups;
         struct parse_events_error *error;
+        struct perf_evlist        *evlist;
 };
 
 struct parse_events_terms {
         struct list_head *terms;
 };
 
+void parse_events__shrink_config_terms(void);
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
 int parse_events_term__num(struct parse_events_term **term,
                            int type_term, char *config, u64 num,
@@ -115,7 +127,9 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
                               char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
                              struct parse_events_term *term);
-void parse_events__free_terms(struct list_head *terms);
+void parse_events_terms__delete(struct list_head *terms);
+void parse_events_terms__purge(struct list_head *terms);
+void parse_events__clear_array(struct parse_events_array *a);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
@@ -126,18 +140,22 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_load_bpf(struct parse_events_evlist *data,
                           struct list_head *list,
                           char *bpf_file_name,
-                          bool source);
+                          bool source,
+                          struct list_head *head_config);
 /* Provide this function for perf test */
 struct bpf_object;
 int parse_events_load_bpf_obj(struct parse_events_evlist *data,
                               struct list_head *list,
-                              struct bpf_object *obj);
+                              struct bpf_object *obj,
+                              struct list_head *head_config);
 int parse_events_add_numeric(struct parse_events_evlist *data,
                              struct list_head *list,
                              u32 type, u64 config,
                              struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
-                           char *type, char *op_result1, char *op_result2);
+                           char *type, char *op_result1, char *op_result2,
+                           struct parse_events_error *error,
+                           struct list_head *head_config);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
                                 void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 58c5831ffd5c..1477fbc78993 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -9,8 +9,8 @@
 %{
 #include <errno.h>
 #include "../perf.h"
-#include "parse-events-bison.h"
 #include "parse-events.h"
+#include "parse-events-bison.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -111,6 +111,7 @@ do {							\
 %x mem
 %s config
 %x event
+%x array
 
 group           [^,{}/]*[{][^}]*[}][^,{}/]*
 event_pmu       [^,{}/]+[/][^/]*[/][^,{}/]*
@@ -122,7 +123,7 @@ num_dec		[0-9]+
 num_hex         0x[a-fA-F0-9]+
 num_raw_hex     [a-fA-F0-9]+
 name            [a-zA-Z_*?][a-zA-Z0-9_*?.]*
-name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?.]*
+name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 /* If you add a modifier you need to update check_modifier() */
 modifier_event  [ukhpPGHSDI]+
 modifier_bp     [rwx]{1,3}
@@ -176,10 +177,17 @@ modifier_bp	[rwx]{1,3}
 
 }
 
+<array>{
+"]"                     { BEGIN(config); return ']'; }
+{num_dec}               { return value(yyscanner, 10); }
+{num_hex}               { return value(yyscanner, 16); }
+,                       { return ','; }
+"\.\.\."                { return PE_ARRAY_RANGE; }
+}
+
 <config>{
         /*
-         * Please update parse_events_formats_error_string any time
-         * new static term is added.
+         * Please update config_term_names when new static term is added.
          */
 config                  { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1                 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
@@ -196,6 +204,8 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 ,                       { return ','; }
 "/"                     { BEGIN(INITIAL); return '/'; }
 {name_minus}            { return str(yyscanner, PE_NAME); }
+\[all\]                 { return PE_ARRAY_ALL; }
+"["                     { BEGIN(array); return '['; }
 }
 
 <mem>{
@@ -238,6 +248,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults                                { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy                                           { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output                                      { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
         /*
          * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index ad379968d4c1..5be4a5f216d6 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,7 +28,7 @@ do { \
         INIT_LIST_HEAD(list);         \
 } while (0)
 
-static inc_group_count(struct list_head *list,
+static void inc_group_count(struct list_head *list,
                        struct parse_events_evlist *data)
 {
         /* Count groups only have more than 1 members */
@@ -48,6 +48,7 @@ static inc_group_count(struct list_head *list,
 %token PE_PREFIX_MEM PE_PREFIX_RAW PE_PREFIX_GROUP
 %token PE_ERROR
 %token PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
+%token PE_ARRAY_ALL PE_ARRAY_RANGE
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
@@ -64,6 +65,7 @@ static inc_group_count(struct list_head *list,
 %type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT
 %type <num> value_sym
 %type <head> event_config
+%type <head> opt_event_config
 %type <term> event_term
 %type <head> event_pmu
 %type <head> event_legacy_symbol
@@ -82,6 +84,9 @@ static inc_group_count(struct list_head *list,
 %type <head> group_def
 %type <head> group
 %type <head> groups
+%type <array> array
+%type <array> array_term
+%type <array> array_terms
 
 %union
 {
@@ -93,6 +98,7 @@ static inc_group_count(struct list_head *list,
                 char *sys;
                 char *event;
         } tracepoint_name;
+        struct parse_events_array array;
 }
 %%
 
@@ -211,24 +217,14 @@ event_def: event_pmu |
            event_bpf_file
 
 event_pmu:
-PE_NAME '/' event_config '/'
+PE_NAME opt_event_config
 {
         struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
-        parse_events__free_terms($3);
-        $$ = list;
-}
-|
-PE_NAME '/' '/'
-{
-        struct parse_events_evlist *data = _data;
-        struct list_head *list;
-
-        ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
+        ABORT_ON(parse_events_add_pmu(data, list, $1, $2));
+        parse_events_terms__delete($2);
         $$ = list;
 }
 |
@@ -246,7 +242,7 @@ PE_KERNEL_PMU_EVENT sep_dc
 
         ALLOC_LIST(list);
         ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-        parse_events__free_terms(head);
+        parse_events_terms__delete(head);
         $$ = list;
 }
 |
@@ -266,7 +262,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
         ALLOC_LIST(list);
         ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-        parse_events__free_terms(head);
+        parse_events_terms__delete(head);
         $$ = list;
 }
 
@@ -285,7 +281,7 @@ value_sym '/' event_config '/'
 
         ALLOC_LIST(list);
         ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
-        parse_events__free_terms($3);
+        parse_events_terms__delete($3);
         $$ = list;
 }
 |
@@ -302,33 +298,39 @@ value_sym sep_slash_dc
 }
 
 event_legacy_cache:
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
         struct parse_events_evlist *data = _data;
+        struct parse_events_error *error = data->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
+        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5, error, $6));
+        parse_events_terms__delete($6);
         $$ = list;
 }
 |
-PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
+PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT opt_event_config
 {
         struct parse_events_evlist *data = _data;
+        struct parse_events_error *error = data->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
+        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL, error, $4));
+        parse_events_terms__delete($4);
         $$ = list;
 }
 |
-PE_NAME_CACHE_TYPE
+PE_NAME_CACHE_TYPE opt_event_config
 {
         struct parse_events_evlist *data = _data;
+        struct parse_events_error *error = data->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
+        ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL, error, $2));
+        parse_events_terms__delete($2);
         $$ = list;
 }
 
@@ -378,24 +380,7 @@ PE_PREFIX_MEM PE_VALUE sep_dc
 }
 
 event_legacy_tracepoint:
-tracepoint_name
-{
-        struct parse_events_evlist *data = _data;
-        struct parse_events_error *error = data->error;
-        struct list_head *list;
-
-        ALLOC_LIST(list);
-        if (error)
-                error->idx = @1.first_column;
-
-        if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-                                        error, NULL))
-                return -1;
-
-        $$ = list;
-}
-|
-tracepoint_name '/' event_config '/'
+tracepoint_name opt_event_config
 {
         struct parse_events_evlist *data = _data;
         struct parse_events_error *error = data->error;
@@ -406,7 +391,7 @@ tracepoint_name '/' event_config '/'
                 error->idx = @1.first_column;
 
         if (parse_events_add_tracepoint(list, &data->idx, $1.sys, $1.event,
-                                        error, $3))
+                                        error, $2))
                 return -1;
 
         $$ = list;
@@ -433,49 +418,68 @@ PE_NAME ':' PE_NAME
 }
 
 event_legacy_numeric:
-PE_VALUE ':' PE_VALUE
+PE_VALUE ':' PE_VALUE opt_event_config
 {
         struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
+        ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, $4));
+        parse_events_terms__delete($4);
         $$ = list;
 }
 
 event_legacy_raw:
-PE_RAW
+PE_RAW opt_event_config
 {
         struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
+        ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, $2));
+        parse_events_terms__delete($2);
         $$ = list;
 }
 
 event_bpf_file:
-PE_BPF_OBJECT
+PE_BPF_OBJECT opt_event_config
 {
         struct parse_events_evlist *data = _data;
         struct parse_events_error *error = data->error;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_load_bpf(data, list, $1, false));
+        ABORT_ON(parse_events_load_bpf(data, list, $1, false, $2));
+        parse_events_terms__delete($2);
         $$ = list;
 }
 |
-PE_BPF_SOURCE
+PE_BPF_SOURCE opt_event_config
 {
         struct parse_events_evlist *data = _data;
         struct list_head *list;
 
         ALLOC_LIST(list);
-        ABORT_ON(parse_events_load_bpf(data, list, $1, true));
+        ABORT_ON(parse_events_load_bpf(data, list, $1, true, $2));
+        parse_events_terms__delete($2);
         $$ = list;
 }
 
+opt_event_config:
+'/' event_config '/'
+{
+        $$ = $2;
+}
+|
+'/' '/'
+{
+        $$ = NULL;
+}
+|
+{
+        $$ = NULL;
+}
+
 start_terms: event_config
 {
         struct parse_events_terms *data = _data;
@@ -573,6 +577,86 @@ PE_TERM
         ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
         $$ = term;
 }
+|
+PE_NAME array '=' PE_NAME
+{
+        struct parse_events_term *term;
+        int i;
+
+        ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+                                        $1, $4, &@1, &@4));
+
+        term->array = $2;
+        $$ = term;
+}
+|
+PE_NAME array '=' PE_VALUE
+{
+        struct parse_events_term *term;
+
+        ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+                                        $1, $4, &@1, &@4));
+        term->array = $2;
+        $$ = term;
+}
+
+array:
+'[' array_terms ']'
+{
+        $$ = $2;
+}
+|
+PE_ARRAY_ALL
+{
+        $$.nr_ranges = 0;
+        $$.ranges = NULL;
+}
+
+array_terms:
+array_terms ',' array_term
+{
+        struct parse_events_array new_array;
+
+        new_array.nr_ranges = $1.nr_ranges + $3.nr_ranges;
+        new_array.ranges = malloc(sizeof(new_array.ranges[0]) *
+                                  new_array.nr_ranges);
+        ABORT_ON(!new_array.ranges);
+        memcpy(&new_array.ranges[0], $1.ranges,
+               $1.nr_ranges * sizeof(new_array.ranges[0]));
+        memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
+               $3.nr_ranges * sizeof(new_array.ranges[0]));
+        free($1.ranges);
+        free($3.ranges);
+        $$ = new_array;
+}
+|
+array_term
+
+array_term:
+PE_VALUE
+{
+        struct parse_events_array array;
+
+        array.nr_ranges = 1;
+        array.ranges = malloc(sizeof(array.ranges[0]));
+        ABORT_ON(!array.ranges);
+        array.ranges[0].start = $1;
+        array.ranges[0].length = 1;
+        $$ = array;
+}
+|
+PE_VALUE PE_ARRAY_RANGE PE_VALUE
+{
+        struct parse_events_array array;
+
+        ABORT_ON($3 < $1);
+        array.nr_ranges = 1;
+        array.ranges = malloc(sizeof(array.ranges[0]));
+        ABORT_ON(!array.ranges);
+        array.ranges[0].start = $1;
+        array.ranges[0].length = $3 - $1 + 1;
+        $$ = array;
+}
 
 sep_dc: ':' |
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b597bcc8fc78..adef23b1352e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -98,7 +98,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
         char scale[128];
         int fd, ret = -1;
         char path[PATH_MAX];
-        const char *lc;
+        char *lc;
 
         snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
 
@@ -124,6 +124,17 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
         lc = setlocale(LC_NUMERIC, NULL);
 
         /*
+         * The lc string may be allocated in static storage,
+         * so get a dynamic copy to make it survive setlocale
+         * call below.
+         */
+        lc = strdup(lc);
+        if (!lc) {
+                ret = -ENOMEM;
+                goto error;
+        }
+
+        /*
          * force to C locale to ensure kernel
          * scale string is converted correctly.
          * kernel uses default C locale.
@@ -135,6 +146,8 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
         /* restore locale */
         setlocale(LC_NUMERIC, lc);
 
+        free(lc);
+
         ret = 0;
 error:
         close(fd);
@@ -153,7 +166,7 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
         if (fd == -1)
                 return -1;
 
-                sret = read(fd, alias->unit, UNIT_MAX_LEN);
+        sret = read(fd, alias->unit, UNIT_MAX_LEN);
         if (sret < 0)
                 goto error;
 
@@ -284,13 +297,12 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 {
         struct dirent *evt_ent;
         DIR *event_dir;
-        int ret = 0;
 
         event_dir = opendir(dir);
         if (!event_dir)
                 return -EINVAL;
 
-        while (!ret && (evt_ent = readdir(event_dir))) {
+        while ((evt_ent = readdir(event_dir))) {
                 char path[PATH_MAX];
                 char *name = evt_ent->d_name;
                 FILE *file;
@@ -306,17 +318,19 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 
                 snprintf(path, PATH_MAX, "%s/%s", dir, name);
 
-                ret = -EINVAL;
                 file = fopen(path, "r");
-                if (!file)
-                        break;
+                if (!file) {
+                        pr_debug("Cannot open %s\n", path);
+                        continue;
+                }
 
-                ret = perf_pmu__new_alias(head, dir, name, file);
+                if (perf_pmu__new_alias(head, dir, name, file) < 0)
+                        pr_debug("Cannot set up %s\n", name);
                 fclose(file);
         }
 
         closedir(event_dir);
-        return ret;
+        return 0;
 }
 
 /*
@@ -354,7 +368,7 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias,
         list_for_each_entry(term, &alias->terms, list) {
                 ret = parse_events_term__clone(&cloned, term);
                 if (ret) {
-                        parse_events__free_terms(&list);
+                        parse_events_terms__purge(&list);
                         return ret;
                 }
                 list_add_tail(&cloned->list, &list);
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 544509c159ce..b3aabc0d4eb0 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -187,6 +187,9 @@ static void define_event_symbols(struct event_format *event,
                                  const char *ev_name,
                                  struct print_arg *args)
 {
+        if (args == NULL)
+                return;
+
         switch (args->type) {
         case PRINT_NULL:
                 break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d72fafc1c800..fbd05242b4e5 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -205,6 +205,9 @@ static void define_event_symbols(struct event_format *event,
                                  const char *ev_name,
                                  struct print_arg *args)
 {
+        if (args == NULL)
+                return;
+
         switch (args->type) {
         case PRINT_NULL:
                 break;
@@ -1091,8 +1094,6 @@ static int python_start_script(const char *script, int argc, const char **argv)
                 goto error;
         }
 
-        free(command_line);
-
         set_table_handlers(tables);
 
         if (tables->db_export_mode) {
@@ -1101,6 +1102,8 @@ static int python_start_script(const char *script, int argc, const char **argv)
                         goto error;
         }
 
+        free(command_line);
+
         return err;
 error:
         Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 40b7a0d0905b..60b3593d210d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -240,14 +240,6 @@ static int process_event_stub(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-static int process_build_id_stub(struct perf_tool *tool __maybe_unused,
-                                 union perf_event *event __maybe_unused,
-                                 struct perf_session *session __maybe_unused)
-{
-        dump_printf(": unhandled!\n");
-        return 0;
-}
-
 static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
                                        union perf_event *event __maybe_unused,
                                        struct ordered_events *oe __maybe_unused)
@@ -260,23 +252,6 @@ static int process_finished_round(struct perf_tool *tool,
                                   union perf_event *event,
                                   struct ordered_events *oe);
 
-static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
-                                 union perf_event *event __maybe_unused,
-                                 struct perf_session *perf_session
-                                 __maybe_unused)
-{
-        dump_printf(": unhandled!\n");
-        return 0;
-}
-
-static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
-                                union perf_event *event __maybe_unused,
-                                struct perf_session *session __maybe_unused)
-{
-        dump_printf(": unhandled!\n");
-        return 0;
-}
-
 static int skipn(int fd, off_t n)
 {
         char buf[4096];
@@ -303,10 +278,9 @@ static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
         return event->auxtrace.size;
 }
 
-static
-int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
-                                      union perf_event *event __maybe_unused,
-                                      struct perf_session *session __maybe_unused)
+static int process_event_op2_stub(struct perf_tool *tool __maybe_unused,
+                                  union perf_event *event __maybe_unused,
+                                  struct perf_session *session __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
@@ -410,7 +384,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
         if (tool->tracing_data == NULL)
                 tool->tracing_data = process_event_synth_tracing_data_stub;
         if (tool->build_id == NULL)
-                tool->build_id = process_build_id_stub;
+                tool->build_id = process_event_op2_stub;
         if (tool->finished_round == NULL) {
                 if (tool->ordered_events)
                         tool->finished_round = process_finished_round;
@@ -418,13 +392,13 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                         tool->finished_round = process_finished_round_stub;
         }
         if (tool->id_index == NULL)
-                tool->id_index = process_id_index_stub;
+                tool->id_index = process_event_op2_stub;
         if (tool->auxtrace_info == NULL)
-                tool->auxtrace_info = process_event_auxtrace_info_stub;
+                tool->auxtrace_info = process_event_op2_stub;
         if (tool->auxtrace == NULL)
                 tool->auxtrace = process_event_auxtrace_stub;
         if (tool->auxtrace_error == NULL)
-                tool->auxtrace_error = process_event_auxtrace_error_stub;
+                tool->auxtrace_error = process_event_op2_stub;
         if (tool->thread_map == NULL)
                 tool->thread_map = process_event_thread_map_stub;
         if (tool->cpu_map == NULL)
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 1833103768cb..c8680984d2d6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -22,6 +22,7 @@ cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
 
+src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
 build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
@@ -30,6 +31,9 @@ libapikfs = getenv('LIBAPI')
 ext_sources = [f.strip() for f in file('util/python-ext-sources')
                                 if len(f.strip()) > 0 and f[0] != '#']
 
+# use full paths with source files
+ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)
+
 perf = Extension('perf',
                   sources = ext_sources,
                   include_dirs = ['util/include'],
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index ec722346e6ff..93fa136b0025 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -6,6 +6,7 @@
 #include "evsel.h"
 #include "evlist.h"
 #include <traceevent/event-parse.h>
+#include "mem-events.h"
 
 regex_t         parent_regex;
 const char      default_parent_pattern[] = "^sys_|^do_page_fault";
@@ -25,9 +26,19 @@ int		sort__has_parent = 0;
 int             sort__has_sym = 0;
 int             sort__has_dso = 0;
 int             sort__has_socket = 0;
+int             sort__has_thread = 0;
+int             sort__has_comm = 0;
 enum sort_mode  sort__mode = SORT_MODE__NORMAL;
 
-
+/*
+ * Replaces all occurrences of a char used with the:
+ *
+ * -t, --field-separator
+ *
+ * option, that uses a special separator character and don't pad with spaces,
+ * replacing all occurances of this separator in symbol names (and other
+ * output) with a '.' character, that thus it's the only non valid separator.
+*/
 static int repsep_snprintf(char *bf, size_t size, const char *fmt, ...)
 {
         int n;
@@ -80,10 +91,21 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
                                width, width, comm ?: "");
 }
 
+static int hist_entry__thread_filter(struct hist_entry *he, int type, const void *arg)
+{
+        const struct thread *th = arg;
+
+        if (type != HIST_FILTER__THREAD)
+                return -1;
+
+        return th && he->thread != th;
+}
+
 struct sort_entry sort_thread = {
         .se_header      = "  Pid:Command",
         .se_cmp         = sort__thread_cmp,
         .se_snprintf    = hist_entry__thread_snprintf,
+        .se_filter      = hist_entry__thread_filter,
         .se_width_idx   = HISTC_THREAD,
 };
 
@@ -121,6 +143,7 @@ struct sort_entry sort_comm = {
         .se_collapse    = sort__comm_collapse,
         .se_sort        = sort__comm_sort,
         .se_snprintf    = hist_entry__comm_snprintf,
+        .se_filter      = hist_entry__thread_filter,
         .se_width_idx   = HISTC_COMM,
 };
 
@@ -170,10 +193,21 @@ static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
         return _hist_entry__dso_snprintf(he->ms.map, bf, size, width);
 }
 
+static int hist_entry__dso_filter(struct hist_entry *he, int type, const void *arg)
+{
+        const struct dso *dso = arg;
+
+        if (type != HIST_FILTER__DSO)
+                return -1;
+
+        return dso && (!he->ms.map || he->ms.map->dso != dso);
+}
+
 struct sort_entry sort_dso = {
         .se_header      = "Shared Object",
         .se_cmp         = sort__dso_cmp,
         .se_snprintf    = hist_entry__dso_snprintf,
+        .se_filter      = hist_entry__dso_filter,
         .se_width_idx   = HISTC_DSO,
 };
 
@@ -246,10 +280,8 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
                         ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
                         ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
                                         ip - map->unmap_ip(map, sym->start));
-                        ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-                                       width - ret, "");
                 } else {
-                        ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+                        ret += repsep_snprintf(bf + ret, size - ret, "%.*s",
                                                width - ret,
                                                sym->name);
                 }
@@ -257,14 +289,9 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
                 size_t len = BITS_PER_LONG / 4;
                 ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
                                        len, ip);
-                ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-                                       width - ret, "");
         }
 
-        if (ret > width)
-                bf[width] = '\0';
-
-        return width;
+        return ret;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -274,46 +301,56 @@ static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
                                          he->level, bf, size, width);
 }
 
+static int hist_entry__sym_filter(struct hist_entry *he, int type, const void *arg)
+{
+        const char *sym = arg;
+
+        if (type != HIST_FILTER__SYMBOL)
+                return -1;
+
+        return sym && (!he->ms.sym || !strstr(he->ms.sym->name, sym));
+}
+
 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_filter      = hist_entry__sym_filter,
         .se_width_idx   = HISTC_SYMBOL,
 };
 
 /* --sort srcline */
 
+static char *hist_entry__get_srcline(struct hist_entry *he)
+{
+        struct map *map = he->ms.map;
+
+        if (!map)
+                return SRCLINE_UNKNOWN;
+
+        return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
+                           he->ms.sym, true);
+}
+
 static int64_t
 sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        if (!left->srcline) {
-                if (!left->ms.map)
-                        left->srcline = SRCLINE_UNKNOWN;
-                else {
-                        struct map *map = left->ms.map;
-                        left->srcline = get_srcline(map->dso,
-                                           map__rip_2objdump(map, left->ip),
-                                                    left->ms.sym, true);
-                }
-        }
-        if (!right->srcline) {
-                if (!right->ms.map)
-                        right->srcline = SRCLINE_UNKNOWN;
-                else {
-                        struct map *map = right->ms.map;
-                        right->srcline = get_srcline(map->dso,
-                                             map__rip_2objdump(map, right->ip),
-                                                     right->ms.sym, true);
-                }
-        }
+        if (!left->srcline)
+                left->srcline = hist_entry__get_srcline(left);
+        if (!right->srcline)
+                right->srcline = hist_entry__get_srcline(right);
+
         return strcmp(right->srcline, left->srcline);
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
                                         size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
+        if (!he->srcline)
+                he->srcline = hist_entry__get_srcline(he);
+
+        return repsep_snprintf(bf, size, "%-.*s", width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -327,11 +364,14 @@ struct sort_entry sort_srcline = {
 
 static char no_srcfile[1];
 
-static char *get_srcfile(struct hist_entry *e)
+static char *hist_entry__get_srcfile(struct hist_entry *e)
 {
         char *sf, *p;
         struct map *map = e->ms.map;
 
+        if (!map)
+                return no_srcfile;
+
         sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
                          e->ms.sym, false, true);
         if (!strcmp(sf, SRCLINE_UNKNOWN))
@@ -348,25 +388,21 @@ static char *get_srcfile(struct hist_entry *e)
 static int64_t
 sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-        if (!left->srcfile) {
-                if (!left->ms.map)
-                        left->srcfile = no_srcfile;
-                else
-                        left->srcfile = get_srcfile(left);
-        }
-        if (!right->srcfile) {
-                if (!right->ms.map)
-                        right->srcfile = no_srcfile;
-                else
-                        right->srcfile = get_srcfile(right);
-        }
+        if (!left->srcfile)
+                left->srcfile = hist_entry__get_srcfile(left);
+        if (!right->srcfile)
+                right->srcfile = hist_entry__get_srcfile(right);
+
         return strcmp(right->srcfile, left->srcfile);
 }
 
 static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf,
                                         size_t size, unsigned int width)
 {
-        return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile);
+        if (!he->srcfile)
+                he->srcfile = hist_entry__get_srcfile(he);
+
+        return repsep_snprintf(bf, size, "%-.*s", width, he->srcfile);
 }
 
 struct sort_entry sort_srcfile = {
@@ -439,10 +475,21 @@ static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
         return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
 }
 
+static int hist_entry__socket_filter(struct hist_entry *he, int type, const void *arg)
+{
+        int sk = *(const int *)arg;
+
+        if (type != HIST_FILTER__SOCKET)
+                return -1;
+
+        return sk >= 0 && he->socket != sk;
+}
+
 struct sort_entry sort_socket = {
         .se_header      = "Socket",
         .se_cmp         = sort__socket_cmp,
         .se_snprintf    = hist_entry__socket_snprintf,
+        .se_filter      = hist_entry__socket_filter,
         .se_width_idx   = HISTC_SOCKET,
 };
 
@@ -483,9 +530,6 @@ sort__trace_cmp(struct hist_entry *left, struct hist_entry *right)
         if (right->trace_output == NULL)
                 right->trace_output = get_trace_output(right);
 
-        hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output));
-        hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output));
-
         return strcmp(right->trace_output, left->trace_output);
 }
 
@@ -496,11 +540,11 @@ static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf,
 
         evsel = hists_to_evsel(he->hists);
         if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
-                return scnprintf(bf, size, "%-*.*s", width, width, "N/A");
+                return scnprintf(bf, size, "%-.*s", width, "N/A");
 
         if (he->trace_output == NULL)
                 he->trace_output = get_trace_output(he);
-        return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output);
+        return repsep_snprintf(bf, size, "%-.*s", width, he->trace_output);
 }
 
 struct sort_entry sort_trace = {
@@ -532,6 +576,18 @@ static int hist_entry__dso_from_snprintf(struct hist_entry *he, char *bf,
                 return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_from_filter(struct hist_entry *he, int type,
+                                       const void *arg)
+{
+        const struct dso *dso = arg;
+
+        if (type != HIST_FILTER__DSO)
+                return -1;
+
+        return dso && (!he->branch_info || !he->branch_info->from.map ||
+                       he->branch_info->from.map->dso != dso);
+}
+
 static int64_t
 sort__dso_to_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -552,6 +608,18 @@ static int hist_entry__dso_to_snprintf(struct hist_entry *he, char *bf,
                 return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__dso_to_filter(struct hist_entry *he, int type,
+                                     const void *arg)
+{
+        const struct dso *dso = arg;
+
+        if (type != HIST_FILTER__DSO)
+                return -1;
+
+        return dso && (!he->branch_info || !he->branch_info->to.map ||
+                       he->branch_info->to.map->dso != dso);
+}
+
 static int64_t
 sort__sym_from_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -613,10 +681,35 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf,
         return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A");
 }
 
+static int hist_entry__sym_from_filter(struct hist_entry *he, int type,
+                                       const void *arg)
+{
+        const char *sym = arg;
+
+        if (type != HIST_FILTER__SYMBOL)
+                return -1;
+
+        return sym && !(he->branch_info && he->branch_info->from.sym &&
+                        strstr(he->branch_info->from.sym->name, sym));
+}
+
+static int hist_entry__sym_to_filter(struct hist_entry *he, int type,
+                                       const void *arg)
+{
+        const char *sym = arg;
+
+        if (type != HIST_FILTER__SYMBOL)
+                return -1;
+
+        return sym && !(he->branch_info && he->branch_info->to.sym &&
+                        strstr(he->branch_info->to.sym->name, sym));
+}
+
 struct sort_entry sort_dso_from = {
         .se_header      = "Source Shared Object",
         .se_cmp         = sort__dso_from_cmp,
         .se_snprintf    = hist_entry__dso_from_snprintf,
+        .se_filter      = hist_entry__dso_from_filter,
         .se_width_idx   = HISTC_DSO_FROM,
 };
 
@@ -624,6 +717,7 @@ struct sort_entry sort_dso_to = {
         .se_header      = "Target Shared Object",
         .se_cmp         = sort__dso_to_cmp,
         .se_snprintf    = hist_entry__dso_to_snprintf,
+        .se_filter      = hist_entry__dso_to_filter,
         .se_width_idx   = HISTC_DSO_TO,
 };
 
@@ -631,6 +725,7 @@ struct sort_entry sort_sym_from = {
         .se_header      = "Source Symbol",
         .se_cmp         = sort__sym_from_cmp,
         .se_snprintf    = hist_entry__sym_from_snprintf,
+        .se_filter      = hist_entry__sym_from_filter,
         .se_width_idx   = HISTC_SYMBOL_FROM,
 };
 
@@ -638,6 +733,7 @@ struct sort_entry sort_sym_to = {
         .se_header      = "Target Symbol",
         .se_cmp         = sort__sym_to_cmp,
         .se_snprintf    = hist_entry__sym_to_snprintf,
+        .se_filter      = hist_entry__sym_to_filter,
         .se_width_idx   = HISTC_SYMBOL_TO,
 };
 
@@ -797,20 +893,10 @@ sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__locked_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
-        const char *out;
-        u64 mask = PERF_MEM_LOCK_NA;
+        char out[10];
 
-        if (he->mem_info)
-                mask = he->mem_info->data_src.mem_lock;
-
-        if (mask & PERF_MEM_LOCK_NA)
-                out = "N/A";
-        else if (mask & PERF_MEM_LOCK_LOCKED)
-                out = "Yes";
-        else
-                out = "No";
-
-        return repsep_snprintf(bf, size, "%-*s", width, out);
+        perf_mem__lck_scnprintf(out, sizeof(out), he->mem_info);
+        return repsep_snprintf(bf, size, "%.*s", width, out);
 }
 
 static int64_t
@@ -832,54 +918,12 @@ sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
         return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
 }
 
-static const char * const tlb_access[] = {
-        "N/A",
-        "HIT",
-        "MISS",
-        "L1",
-        "L2",
-        "Walker",
-        "Fault",
-};
-#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
-
 static int hist_entry__tlb_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
         char out[64];
-        size_t sz = sizeof(out) - 1; /* -1 for null termination */
-        size_t l = 0, i;
-        u64 m = PERF_MEM_TLB_NA;
-        u64 hit, miss;
-
-        out[0] = '\0';
-
-        if (he->mem_info)
-                m = he->mem_info->data_src.mem_dtlb;
-
-        hit = m & PERF_MEM_TLB_HIT;
-        miss = m & PERF_MEM_TLB_MISS;
-
-        /* already taken care of */
-        m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
-
-        for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
-                if (!(m & 0x1))
-                        continue;
-                if (l) {
-                        strcat(out, " or ");
-                        l += 4;
-                }
-                strncat(out, tlb_access[i], sz - l);
-                l += strlen(tlb_access[i]);
-        }
-        if (*out == '\0')
-                strcpy(out, "N/A");
-        if (hit)
-                strncat(out, " hit", sz - l);
-        if (miss)
-                strncat(out, " miss", sz - l);
 
+        perf_mem__tlb_scnprintf(out, sizeof(out), he->mem_info);
         return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -902,61 +946,12 @@ sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
         return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
 }
 
-static const char * const mem_lvl[] = {
-        "N/A",
-        "HIT",
-        "MISS",
-        "L1",
-        "LFB",
-        "L2",
-        "L3",
-        "Local RAM",
-        "Remote RAM (1 hop)",
-        "Remote RAM (2 hops)",
-        "Remote Cache (1 hop)",
-        "Remote Cache (2 hops)",
-        "I/O",
-        "Uncached",
-};
-#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
-
 static int hist_entry__lvl_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
         char out[64];
-        size_t sz = sizeof(out) - 1; /* -1 for null termination */
-        size_t i, l = 0;
-        u64 m =  PERF_MEM_LVL_NA;
-        u64 hit, miss;
-
-        if (he->mem_info)
-                m  = he->mem_info->data_src.mem_lvl;
-
-        out[0] = '\0';
-
-        hit = m & PERF_MEM_LVL_HIT;
-        miss = m & PERF_MEM_LVL_MISS;
-
-        /* already taken care of */
-        m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
-
-        for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
-                if (!(m & 0x1))
-                        continue;
-                if (l) {
-                        strcat(out, " or ");
-                        l += 4;
-                }
-                strncat(out, mem_lvl[i], sz - l);
-                l += strlen(mem_lvl[i]);
-        }
-        if (*out == '\0')
-                strcpy(out, "N/A");
-        if (hit)
-                strncat(out, " hit", sz - l);
-        if (miss)
-                strncat(out, " miss", sz - l);
 
+        perf_mem__lvl_scnprintf(out, sizeof(out), he->mem_info);
         return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
@@ -979,51 +974,15 @@ sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
         return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
 }
 
-static const char * const snoop_access[] = {
-        "N/A",
-        "None",
-        "Miss",
-        "Hit",
-        "HitM",
-};
-#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
-
 static int hist_entry__snoop_snprintf(struct hist_entry *he, char *bf,
                                     size_t size, unsigned int width)
 {
         char out[64];
-        size_t sz = sizeof(out) - 1; /* -1 for null termination */
-        size_t i, l = 0;
-        u64 m = PERF_MEM_SNOOP_NA;
-
-        out[0] = '\0';
-
-        if (he->mem_info)
-                m = he->mem_info->data_src.mem_snoop;
-
-        for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
-                if (!(m & 0x1))
-                        continue;
-                if (l) {
-                        strcat(out, " or ");
-                        l += 4;
-                }
-                strncat(out, snoop_access[i], sz - l);
-                l += strlen(snoop_access[i]);
-        }
-
-        if (*out == '\0')
-                strcpy(out, "N/A");
 
+        perf_mem__snp_scnprintf(out, sizeof(out), he->mem_info);
         return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
-static inline  u64 cl_address(u64 address)
-{
-        /* return the cacheline of the address */
-        return (address & ~(cacheline_size - 1));
-}
-
 static int64_t
 sort__dcacheline_cmp(struct hist_entry *left, struct hist_entry *right)
 {
@@ -1440,20 +1399,6 @@ struct hpp_sort_entry {
         struct sort_entry *se;
 };
 
-bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
-{
-        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_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
         struct hpp_sort_entry *hse;
@@ -1539,8 +1484,56 @@ static int64_t __sort__hpp_sort(struct perf_hpp_fmt *fmt,
         return sort_fn(a, b);
 }
 
+bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+{
+        return format->header == __sort__hpp_header;
+}
+
+#define MK_SORT_ENTRY_CHK(key)                                  \
+bool perf_hpp__is_ ## key ## _entry(struct perf_hpp_fmt *fmt)   \
+{                                                               \
+        struct hpp_sort_entry *hse;                             \
+                                                                \
+        if (!perf_hpp__is_sort_entry(fmt))                      \
+                return false;                                   \
+                                                                \
+        hse = container_of(fmt, struct hpp_sort_entry, hpp);    \
+        return hse->se == &sort_ ## key ;                       \
+}
+
+MK_SORT_ENTRY_CHK(trace)
+MK_SORT_ENTRY_CHK(srcline)
+MK_SORT_ENTRY_CHK(srcfile)
+MK_SORT_ENTRY_CHK(thread)
+MK_SORT_ENTRY_CHK(comm)
+MK_SORT_ENTRY_CHK(dso)
+MK_SORT_ENTRY_CHK(sym)
+
+
+static bool __sort__hpp_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+        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;
+}
+
+static void hse_free(struct perf_hpp_fmt *fmt)
+{
+        struct hpp_sort_entry *hse;
+
+        hse = container_of(fmt, struct hpp_sort_entry, hpp);
+        free(hse);
+}
+
 static struct hpp_sort_entry *
-__sort_dimension__alloc_hpp(struct sort_dimension *sd)
+__sort_dimension__alloc_hpp(struct sort_dimension *sd, int level)
 {
         struct hpp_sort_entry *hse;
 
@@ -1560,40 +1553,92 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
         hse->hpp.cmp = __sort__hpp_cmp;
         hse->hpp.collapse = __sort__hpp_collapse;
         hse->hpp.sort = __sort__hpp_sort;
+        hse->hpp.equal = __sort__hpp_equal;
+        hse->hpp.free = hse_free;
 
         INIT_LIST_HEAD(&hse->hpp.list);
         INIT_LIST_HEAD(&hse->hpp.sort_list);
         hse->hpp.elide = false;
         hse->hpp.len = 0;
         hse->hpp.user_len = 0;
+        hse->hpp.level = level;
 
         return hse;
 }
 
-bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format)
+static void hpp_free(struct perf_hpp_fmt *fmt)
 {
-        return format->header == __sort__hpp_header;
+        free(fmt);
+}
+
+static struct perf_hpp_fmt *__hpp_dimension__alloc_hpp(struct hpp_dimension *hd,
+                                                       int level)
+{
+        struct perf_hpp_fmt *fmt;
+
+        fmt = memdup(hd->fmt, sizeof(*fmt));
+        if (fmt) {
+                INIT_LIST_HEAD(&fmt->list);
+                INIT_LIST_HEAD(&fmt->sort_list);
+                fmt->free = hpp_free;
+                fmt->level = level;
+        }
+
+        return fmt;
+}
+
+int hist_entry__filter(struct hist_entry *he, int type, const void *arg)
+{
+        struct perf_hpp_fmt *fmt;
+        struct hpp_sort_entry *hse;
+        int ret = -1;
+        int r;
+
+        perf_hpp_list__for_each_format(he->hpp_list, fmt) {
+                if (!perf_hpp__is_sort_entry(fmt))
+                        continue;
+
+                hse = container_of(fmt, struct hpp_sort_entry, hpp);
+                if (hse->se->se_filter == NULL)
+                        continue;
+
+                /*
+                 * hist entry is filtered if any of sort key in the hpp list
+                 * is applied.  But it should skip non-matched filter types.
+                 */
+                r = hse->se->se_filter(he, type, arg);
+                if (r >= 0) {
+                        if (ret < 0)
+                                ret = 0;
+                        ret |= r;
+                }
+        }
+
+        return ret;
 }
 
-static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_sort(struct sort_dimension *sd,
+                                          struct perf_hpp_list *list,
+                                          int level)
 {
-        struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+        struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, level);
 
         if (hse == NULL)
                 return -1;
 
-        perf_hpp__register_sort_field(&hse->hpp);
+        perf_hpp_list__register_sort_field(list, &hse->hpp);
         return 0;
 }
 
-static int __sort_dimension__add_hpp_output(struct sort_dimension *sd)
+static int __sort_dimension__add_hpp_output(struct sort_dimension *sd,
+                                            struct perf_hpp_list *list)
 {
-        struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd);
+        struct hpp_sort_entry *hse = __sort_dimension__alloc_hpp(sd, 0);
 
         if (hse == NULL)
                 return -1;
 
-        perf_hpp__column_register(&hse->hpp);
+        perf_hpp_list__column_register(list, &hse->hpp);
         return 0;
 }
 
@@ -1727,6 +1772,9 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
         if (hde->raw_trace)
                 goto raw_field;
 
+        if (!he->trace_output)
+                he->trace_output = get_trace_output(he);
+
         field = hde->field;
         namelen = strlen(field->name);
         str = he->trace_output;
@@ -1776,6 +1824,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
 
         hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
 
+        if (b == NULL) {
+                update_dynamic_len(hde, a);
+                return 0;
+        }
+
         field = hde->field;
         if (field->flags & FIELD_IS_DYNAMIC) {
                 unsigned long long dyn;
@@ -1790,9 +1843,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt,
         } else {
                 offset = field->offset;
                 size = field->size;
-
-                update_dynamic_len(hde, a);
-                update_dynamic_len(hde, b);
         }
 
         return memcmp(a->raw_data + offset, b->raw_data + offset, size);
@@ -1803,8 +1853,31 @@ bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt)
         return fmt->cmp == __sort__hde_cmp;
 }
 
+static bool __sort__hde_equal(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
+{
+        struct hpp_dynamic_entry *hde_a;
+        struct hpp_dynamic_entry *hde_b;
+
+        if (!perf_hpp__is_dynamic_entry(a) || !perf_hpp__is_dynamic_entry(b))
+                return false;
+
+        hde_a = container_of(a, struct hpp_dynamic_entry, hpp);
+        hde_b = container_of(b, struct hpp_dynamic_entry, hpp);
+
+        return hde_a->field == hde_b->field;
+}
+
+static void hde_free(struct perf_hpp_fmt *fmt)
+{
+        struct hpp_dynamic_entry *hde;
+
+        hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+        free(hde);
+}
+
 static struct hpp_dynamic_entry *
-__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
+__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field,
+                      int level)
 {
         struct hpp_dynamic_entry *hde;
 
@@ -1827,16 +1900,47 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field)
         hde->hpp.cmp = __sort__hde_cmp;
         hde->hpp.collapse = __sort__hde_cmp;
         hde->hpp.sort = __sort__hde_cmp;
+        hde->hpp.equal = __sort__hde_equal;
+        hde->hpp.free = hde_free;
 
         INIT_LIST_HEAD(&hde->hpp.list);
         INIT_LIST_HEAD(&hde->hpp.sort_list);
         hde->hpp.elide = false;
         hde->hpp.len = 0;
         hde->hpp.user_len = 0;
+        hde->hpp.level = level;
 
         return hde;
 }
 
+struct perf_hpp_fmt *perf_hpp_fmt__dup(struct perf_hpp_fmt *fmt)
+{
+        struct perf_hpp_fmt *new_fmt = NULL;
+
+        if (perf_hpp__is_sort_entry(fmt)) {
+                struct hpp_sort_entry *hse, *new_hse;
+
+                hse = container_of(fmt, struct hpp_sort_entry, hpp);
+                new_hse = memdup(hse, sizeof(*hse));
+                if (new_hse)
+                        new_fmt = &new_hse->hpp;
+        } else if (perf_hpp__is_dynamic_entry(fmt)) {
+                struct hpp_dynamic_entry *hde, *new_hde;
+
+                hde = container_of(fmt, struct hpp_dynamic_entry, hpp);
+                new_hde = memdup(hde, sizeof(*hde));
+                if (new_hde)
+                        new_fmt = &new_hde->hpp;
+        } else {
+                new_fmt = memdup(fmt, sizeof(*fmt));
+        }
+
+        INIT_LIST_HEAD(&new_fmt->list);
+        INIT_LIST_HEAD(&new_fmt->sort_list);
+
+        return new_fmt;
+}
+
 static int parse_field_name(char *str, char **event, char **field, char **opt)
 {
         char *event_name, *field_name, *opt_name;
@@ -1908,11 +2012,11 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam
 
 static int __dynamic_dimension__add(struct perf_evsel *evsel,
                                     struct format_field *field,
-                                    bool raw_trace)
+                                    bool raw_trace, int level)
 {
         struct hpp_dynamic_entry *hde;
 
-        hde = __alloc_dynamic_entry(evsel, field);
+        hde = __alloc_dynamic_entry(evsel, field, level);
         if (hde == NULL)
                 return -ENOMEM;
 
@@ -1922,14 +2026,14 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel,
         return 0;
 }
 
-static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
+static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace, int level)
 {
         int ret;
         struct format_field *field;
 
         field = evsel->tp_format->format.fields;
         while (field) {
-                ret = __dynamic_dimension__add(evsel, field, raw_trace);
+                ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
                 if (ret < 0)
                         return ret;
 
@@ -1938,7 +2042,8 @@ static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace)
         return 0;
 }
 
-static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
+static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace,
+                                  int level)
 {
         int ret;
         struct perf_evsel *evsel;
@@ -1947,7 +2052,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
                 if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
                         continue;
 
-                ret = add_evsel_fields(evsel, raw_trace);
+                ret = add_evsel_fields(evsel, raw_trace, level);
                 if (ret < 0)
                         return ret;
         }
@@ -1955,7 +2060,7 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace)
 }
 
 static int add_all_matching_fields(struct perf_evlist *evlist,
-                                   char *field_name, bool raw_trace)
+                                   char *field_name, bool raw_trace, int level)
 {
         int ret = -ESRCH;
         struct perf_evsel *evsel;
@@ -1969,14 +2074,15 @@ static int add_all_matching_fields(struct perf_evlist *evlist,
                 if (field == NULL)
                         continue;
 
-                ret = __dynamic_dimension__add(evsel, field, raw_trace);
+                ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
                 if (ret < 0)
                         break;
         }
         return ret;
 }
 
-static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
+static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok,
+                             int level)
 {
         char *str, *event_name, *field_name, *opt_name;
         struct perf_evsel *evsel;
@@ -2006,12 +2112,12 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
         }
 
         if (!strcmp(field_name, "trace_fields")) {
-                ret = add_all_dynamic_fields(evlist, raw_trace);
+                ret = add_all_dynamic_fields(evlist, raw_trace, level);
                 goto out;
         }
 
         if (event_name == NULL) {
-                ret = add_all_matching_fields(evlist, field_name, raw_trace);
+                ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
                 goto out;
         }
 
@@ -2029,7 +2135,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
         }
 
         if (!strcmp(field_name, "*")) {
-                ret = add_evsel_fields(evsel, raw_trace);
+                ret = add_evsel_fields(evsel, raw_trace, level);
         } else {
                 field = pevent_find_any_field(evsel->tp_format, field_name);
                 if (field == NULL) {
@@ -2038,7 +2144,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok)
                         return -ENOENT;
                 }
 
-                ret = __dynamic_dimension__add(evsel, field, raw_trace);
+                ret = __dynamic_dimension__add(evsel, field, raw_trace, level);
         }
 
 out:
@@ -2046,12 +2152,14 @@ out:
         return ret;
 }
 
-static int __sort_dimension__add(struct sort_dimension *sd)
+static int __sort_dimension__add(struct sort_dimension *sd,
+                                 struct perf_hpp_list *list,
+                                 int level)
 {
         if (sd->taken)
                 return 0;
 
-        if (__sort_dimension__add_hpp_sort(sd) < 0)
+        if (__sort_dimension__add_hpp_sort(sd, list, level) < 0)
                 return -1;
 
         if (sd->entry->se_collapse)
@@ -2062,46 +2170,63 @@ static int __sort_dimension__add(struct sort_dimension *sd)
         return 0;
 }
 
-static int __hpp_dimension__add(struct hpp_dimension *hd)
+static int __hpp_dimension__add(struct hpp_dimension *hd,
+                                struct perf_hpp_list *list,
+                                int level)
 {
-        if (!hd->taken) {
-                hd->taken = 1;
+        struct perf_hpp_fmt *fmt;
 
-                perf_hpp__register_sort_field(hd->fmt);
-        }
+        if (hd->taken)
+                return 0;
+
+        fmt = __hpp_dimension__alloc_hpp(hd, level);
+        if (!fmt)
+                return -1;
+
+        hd->taken = 1;
+        perf_hpp_list__register_sort_field(list, fmt);
         return 0;
 }
 
-static int __sort_dimension__add_output(struct sort_dimension *sd)
+static int __sort_dimension__add_output(struct perf_hpp_list *list,
+                                        struct sort_dimension *sd)
 {
         if (sd->taken)
                 return 0;
 
-        if (__sort_dimension__add_hpp_output(sd) < 0)
+        if (__sort_dimension__add_hpp_output(sd, list) < 0)
                 return -1;
 
         sd->taken = 1;
         return 0;
 }
 
-static int __hpp_dimension__add_output(struct hpp_dimension *hd)
+static int __hpp_dimension__add_output(struct perf_hpp_list *list,
+                                       struct hpp_dimension *hd)
 {
-        if (!hd->taken) {
-                hd->taken = 1;
+        struct perf_hpp_fmt *fmt;
 
-                perf_hpp__column_register(hd->fmt);
-        }
+        if (hd->taken)
+                return 0;
+
+        fmt = __hpp_dimension__alloc_hpp(hd, 0);
+        if (!fmt)
+                return -1;
+
+        hd->taken = 1;
+        perf_hpp_list__column_register(list, fmt);
         return 0;
 }
 
 int hpp_dimension__add_output(unsigned col)
 {
         BUG_ON(col >= PERF_HPP__MAX_INDEX);
-        return __hpp_dimension__add_output(&hpp_sort_dimensions[col]);
+        return __hpp_dimension__add_output(&perf_hpp_list, &hpp_sort_dimensions[col]);
 }
 
-static int sort_dimension__add(const char *tok,
-                               struct perf_evlist *evlist __maybe_unused)
+static int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
+                               struct perf_evlist *evlist __maybe_unused,
+                               int level)
 {
         unsigned int i;
 
@@ -2136,9 +2261,13 @@ static int sort_dimension__add(const char *tok,
                         sort__has_dso = 1;
                 } else if (sd->entry == &sort_socket) {
                         sort__has_socket = 1;
+                } else if (sd->entry == &sort_thread) {
+                        sort__has_thread = 1;
+                } else if (sd->entry == &sort_comm) {
+                        sort__has_comm = 1;
                 }
 
-                return __sort_dimension__add(sd);
+                return __sort_dimension__add(sd, list, level);
         }
 
         for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2147,7 +2276,7 @@ static int sort_dimension__add(const char *tok,
                 if (strncasecmp(tok, hd->name, strlen(tok)))
                         continue;
 
-                return __hpp_dimension__add(hd);
+                return __hpp_dimension__add(hd, list, level);
         }
 
         for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2162,7 +2291,7 @@ static 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);
+                __sort_dimension__add(sd, list, level);
                 return 0;
         }
 
@@ -2178,16 +2307,60 @@ static int sort_dimension__add(const char *tok,
                 if (sd->entry == &sort_mem_daddr_sym)
                         sort__has_sym = 1;
 
-                __sort_dimension__add(sd);
+                __sort_dimension__add(sd, list, level);
                 return 0;
         }
 
-        if (!add_dynamic_entry(evlist, tok))
+        if (!add_dynamic_entry(evlist, tok, level))
                 return 0;
 
         return -ESRCH;
 }
 
+static int setup_sort_list(struct perf_hpp_list *list, char *str,
+                           struct perf_evlist *evlist)
+{
+        char *tmp, *tok;
+        int ret = 0;
+        int level = 0;
+        int next_level = 1;
+        bool in_group = false;
+
+        do {
+                tok = str;
+                tmp = strpbrk(str, "{}, ");
+                if (tmp) {
+                        if (in_group)
+                                next_level = level;
+                        else
+                                next_level = level + 1;
+
+                        if (*tmp == '{')
+                                in_group = true;
+                        else if (*tmp == '}')
+                                in_group = false;
+
+                        *tmp = '\0';
+                        str = tmp + 1;
+                }
+
+                if (*tok) {
+                        ret = sort_dimension__add(list, tok, evlist, level);
+                        if (ret == -EINVAL) {
+                                error("Invalid --sort key: `%s'", tok);
+                                break;
+                        } else if (ret == -ESRCH) {
+                                error("Unknown --sort key: `%s'", tok);
+                                break;
+                        }
+                }
+
+                level = next_level;
+        } while (tmp);
+
+        return ret;
+}
+
 static const char *get_default_sort_order(struct perf_evlist *evlist)
 {
         const char *default_sort_orders[] = {
@@ -2282,7 +2455,7 @@ static char *setup_overhead(char *keys)
 
 static int __setup_sorting(struct perf_evlist *evlist)
 {
-        char *tmp, *tok, *str;
+        char *str;
         const char *sort_keys;
         int ret = 0;
 
@@ -2320,17 +2493,7 @@ static int __setup_sorting(struct perf_evlist *evlist)
                 }
         }
 
-        for (tok = strtok_r(str, ", ", &tmp);
-                        tok; tok = strtok_r(NULL, ", ", &tmp)) {
-                ret = sort_dimension__add(tok, evlist);
-                if (ret == -EINVAL) {
-                        error("Invalid --sort key: `%s'", tok);
-                        break;
-                } else if (ret == -ESRCH) {
-                        error("Unknown --sort key: `%s'", tok);
-                        break;
-                }
-        }
+        ret = setup_sort_list(&perf_hpp_list, str, evlist);
 
         free(str);
         return ret;
@@ -2341,7 +2504,7 @@ 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) {
+        perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
                 if (!perf_hpp__is_sort_entry(fmt))
                         continue;
 
@@ -2401,7 +2564,7 @@ void sort__setup_elide(FILE *output)
         struct perf_hpp_fmt *fmt;
         struct hpp_sort_entry *hse;
 
-        perf_hpp__for_each_format(fmt) {
+        perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
                 if (!perf_hpp__is_sort_entry(fmt))
                         continue;
 
@@ -2413,7 +2576,7 @@ void sort__setup_elide(FILE *output)
          * It makes no sense to elide all of sort entries.
          * Just revert them to show up again.
          */
-        perf_hpp__for_each_format(fmt) {
+        perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
                 if (!perf_hpp__is_sort_entry(fmt))
                         continue;
 
@@ -2421,7 +2584,7 @@ void sort__setup_elide(FILE *output)
                         return;
         }
 
-        perf_hpp__for_each_format(fmt) {
+        perf_hpp_list__for_each_format(&perf_hpp_list, fmt) {
                 if (!perf_hpp__is_sort_entry(fmt))
                         continue;
 
@@ -2429,7 +2592,7 @@ void sort__setup_elide(FILE *output)
         }
 }
 
-static int output_field_add(char *tok)
+static int output_field_add(struct perf_hpp_list *list, char *tok)
 {
         unsigned int i;
 
@@ -2439,7 +2602,7 @@ static int output_field_add(char *tok)
                 if (strncasecmp(tok, sd->name, strlen(tok)))
                         continue;
 
-                return __sort_dimension__add_output(sd);
+                return __sort_dimension__add_output(list, sd);
         }
 
         for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
@@ -2448,7 +2611,7 @@ static int output_field_add(char *tok)
                 if (strncasecmp(tok, hd->name, strlen(tok)))
                         continue;
 
-                return __hpp_dimension__add_output(hd);
+                return __hpp_dimension__add_output(list, hd);
         }
 
         for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
@@ -2457,7 +2620,7 @@ static int output_field_add(char *tok)
                 if (strncasecmp(tok, sd->name, strlen(tok)))
                         continue;
 
-                return __sort_dimension__add_output(sd);
+                return __sort_dimension__add_output(list, sd);
         }
 
         for (i = 0; i < ARRAY_SIZE(memory_sort_dimensions); i++) {
@@ -2466,12 +2629,32 @@ static int output_field_add(char *tok)
                 if (strncasecmp(tok, sd->name, strlen(tok)))
                         continue;
 
-                return __sort_dimension__add_output(sd);
+                return __sort_dimension__add_output(list, sd);
         }
 
         return -ESRCH;
 }
 
+static int setup_output_list(struct perf_hpp_list *list, char *str)
+{
+        char *tmp, *tok;
+        int ret = 0;
+
+        for (tok = strtok_r(str, ", ", &tmp);
+                        tok; tok = strtok_r(NULL, ", ", &tmp)) {
+                ret = output_field_add(list, tok);
+                if (ret == -EINVAL) {
+                        error("Invalid --fields key: `%s'", tok);
+                        break;
+                } else if (ret == -ESRCH) {
+                        error("Unknown --fields key: `%s'", tok);
+                        break;
+                }
+        }
+
+        return ret;
+}
+
 static void reset_dimensions(void)
 {
         unsigned int i;
@@ -2496,7 +2679,7 @@ bool is_strict_order(const char *order)
 
 static int __setup_output_field(void)
 {
-        char *tmp, *tok, *str, *strp;
+        char *str, *strp;
         int ret = -EINVAL;
 
         if (field_order == NULL)
@@ -2516,17 +2699,7 @@ static int __setup_output_field(void)
                 goto out;
         }
 
-        for (tok = strtok_r(strp, ", ", &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;
-                }
-        }
+        ret = setup_output_list(&perf_hpp_list, strp);
 
 out:
         free(str);
@@ -2542,7 +2715,7 @@ int setup_sorting(struct perf_evlist *evlist)
                 return err;
 
         if (parent_pattern != default_parent_pattern) {
-                err = sort_dimension__add("parent", evlist);
+                err = sort_dimension__add(&perf_hpp_list, "parent", evlist, -1);
                 if (err < 0)
                         return err;
         }
@@ -2560,9 +2733,13 @@ int setup_sorting(struct perf_evlist *evlist)
                 return err;
 
         /* copy sort keys to output fields */
-        perf_hpp__setup_output_field();
+        perf_hpp__setup_output_field(&perf_hpp_list);
         /* and then copy output fields to sort keys */
-        perf_hpp__append_sort_keys();
+        perf_hpp__append_sort_keys(&perf_hpp_list);
+
+        /* setup hists-specific output fields */
+        if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0)
+                return -1;
 
         return 0;
 }
@@ -2578,5 +2755,5 @@ void reset_output_field(void)
         sort_order = NULL;
 
         reset_dimensions();
-        perf_hpp__reset_output_field();
+        perf_hpp__reset_output_field(&perf_hpp_list);
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 687bbb124428..3f4e35998119 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -32,9 +32,12 @@ extern const char default_sort_order[];
 extern regex_t ignore_callees_regex;
 extern int have_ignore_callees;
 extern int sort__need_collapse;
+extern int sort__has_dso;
 extern int sort__has_parent;
 extern int sort__has_sym;
 extern int sort__has_socket;
+extern int sort__has_thread;
+extern int sort__has_comm;
 extern enum sort_mode sort__mode;
 extern struct sort_entry sort_comm;
 extern struct sort_entry sort_dso;
@@ -94,9 +97,11 @@ struct hist_entry {
         s32                     socket;
         s32                     cpu;
         u8                      cpumode;
+        u8                      depth;
 
         /* We are added by hists__add_dummy_entry. */
         bool                    dummy;
+        bool                    leaf;
 
         char                    level;
         u8                      filtered;
@@ -113,18 +118,28 @@ struct hist_entry {
                         bool    init_have_children;
                         bool    unfolded;
                         bool    has_children;
+                        bool    has_no_entry;
                 };
         };
         char                    *srcline;
         char                    *srcfile;
         struct symbol           *parent;
-        struct rb_root          sorted_chain;
         struct branch_info      *branch_info;
         struct hists            *hists;
         struct mem_info         *mem_info;
         void                    *raw_data;
         u32                     raw_size;
         void                    *trace_output;
+        struct perf_hpp_list    *hpp_list;
+        struct hist_entry       *parent_he;
+        union {
+                /* this is for hierarchical entry structure */
+                struct {
+                        struct rb_root  hroot_in;
+                        struct rb_root  hroot_out;
+                };                              /* non-leaf entries */
+                struct rb_root  sorted_chain;   /* leaf entry has callchains */
+        };
         struct callchain_root   callchain[0]; /* must be last member */
 };
 
@@ -160,6 +175,17 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
         return period * 100.0 / total_period;
 }
 
+static inline u64 cl_address(u64 address)
+{
+        /* return the cacheline of the address */
+        return (address & ~(cacheline_size - 1));
+}
+
+static inline u64 cl_offset(u64 address)
+{
+        /* return the cacheline of the address */
+        return (address & (cacheline_size - 1));
+}
 
 enum sort_mode {
         SORT_MODE__NORMAL,
@@ -221,6 +247,7 @@ struct sort_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);
+        int     (*se_filter)(struct hist_entry *he, int type, const void *arg);
         u8      se_width_idx;
 };
 
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac03146889d..b33ffb2af2cf 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -2,6 +2,7 @@
 #include "evsel.h"
 #include "stat.h"
 #include "color.h"
+#include "pmu.h"
 
 enum {
         CTX_BIT_USER    = 1 << 0,
@@ -14,6 +15,13 @@ enum {
 
 #define NUM_CTX CTX_BIT_MAX
 
+/*
+ * AGGR_GLOBAL: Use CPU 0
+ * AGGR_SOCKET: Use first CPU of socket
+ * AGGR_CORE: Use first CPU of core
+ * AGGR_NONE: Use matching CPU
+ * AGGR_THREAD: Not supported?
+ */
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
 static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
@@ -28,9 +36,15 @@ static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
 static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+static bool have_frontend_stalled;
 
 struct stats walltime_nsecs_stats;
 
+void perf_stat__init_shadow_stats(void)
+{
+        have_frontend_stalled = pmu_have_event("cpu", "stalled-cycles-frontend");
+}
+
 static int evsel_context(struct perf_evsel *evsel)
 {
         int ctx = 0;
@@ -137,9 +151,10 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
         return color;
 }
 
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
                                           struct perf_evsel *evsel
-                                          __maybe_unused, double avg)
+                                          __maybe_unused, double avg,
+                                          struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -152,14 +167,17 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,
 
         color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
 
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " frontend cycles idle   ");
+        if (ratio)
+                out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+                                  ratio);
+        else
+                out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
 }
 
-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
                                          struct perf_evsel *evsel
-                                         __maybe_unused, double avg)
+                                         __maybe_unused, double avg,
+                                         struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -172,14 +190,13 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,
 
         color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " backend  cycles idle   ");
+        out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
 }
 
-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
                                 struct perf_evsel *evsel __maybe_unused,
-                                double avg)
+                                double avg,
+                                struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -192,14 +209,13 @@ static void print_branch_misses(FILE *out, int cpu,
 
         color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " of all branches        ");
+        out->print_metric(out->ctx, color, "%7.2f%%", "of all branches", ratio);
 }
 
-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
                                    struct perf_evsel *evsel __maybe_unused,
-                                   double avg)
+                                   double avg,
+                                   struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -212,14 +228,13 @@ static void print_l1_dcache_misses(FILE *out, int cpu,
 
         color = get_ratio_color(GRC_CACHE_MISSES, ratio);
 
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " of all L1-dcache hits  ");
+        out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-dcache hits", ratio);
 }
 
-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
                                    struct perf_evsel *evsel __maybe_unused,
-                                   double avg)
+                                   double avg,
+                                   struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -231,15 +246,13 @@ static void print_l1_icache_misses(FILE *out, int cpu,
                 ratio = avg / total * 100.0;
 
         color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " of all L1-icache hits  ");
+        out->print_metric(out->ctx, color, "%7.2f%%", "of all L1-icache hits", ratio);
 }
 
-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
                                     struct perf_evsel *evsel __maybe_unused,
-                                    double avg)
+                                    double avg,
+                                    struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -251,15 +264,13 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
                 ratio = avg / total * 100.0;
 
         color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " of all dTLB cache hits ");
+        out->print_metric(out->ctx, color, "%7.2f%%", "of all dTLB cache hits", ratio);
 }
 
-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
                                     struct perf_evsel *evsel __maybe_unused,
-                                    double avg)
+                                    double avg,
+                                    struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -271,15 +282,13 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
                 ratio = avg / total * 100.0;
 
         color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " of all iTLB cache hits ");
+        out->print_metric(out->ctx, color, "%7.2f%%", "of all iTLB cache hits", ratio);
 }
 
-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
                                   struct perf_evsel *evsel __maybe_unused,
-                                  double avg)
+                                  double avg,
+                                  struct perf_stat_output_ctx *out)
 {
         double total, ratio = 0.0;
         const char *color;
@@ -291,15 +300,15 @@ static void print_ll_cache_misses(FILE *out, int cpu,
                 ratio = avg / total * 100.0;
 
         color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-        fprintf(out, " #  ");
-        color_fprintf(out, color, "%6.2f%%", ratio);
-        fprintf(out, " of all LL-cache hits   ");
+        out->print_metric(out->ctx, color, "%7.2f%%", "of all LL-cache hits", ratio);
 }
 
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-                                   double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+                                   double avg, int cpu,
+                                   struct perf_stat_output_ctx *out)
 {
+        void *ctxp = out->ctx;
+        print_metric_t print_metric = out->print_metric;
         double total, ratio = 0.0, total2;
         int ctx = evsel_context(evsel);
 
@@ -307,119 +316,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
                 total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
                 if (total) {
                         ratio = avg / total;
-                        fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+                        print_metric(ctxp, NULL, "%7.2f ",
+                                        "insn per cycle", ratio);
                 } else {
-                        fprintf(out, "                                   ");
+                        print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
                 }
                 total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
                 total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
                 if (total && avg) {
+                        out->new_line(ctxp);
                         ratio = total / avg;
-                        fprintf(out, "\n");
-                        if (aggr == AGGR_NONE)
-                                fprintf(out, "        ");
-                        fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+                        print_metric(ctxp, NULL, "%7.2f ",
+                                        "stalled cycles per insn",
+                                        ratio);
+                } else if (have_frontend_stalled) {
+                        print_metric(ctxp, NULL, NULL,
+                                     "stalled cycles per insn", 0);
                 }
-
-        } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-                        runtime_branches_stats[ctx][cpu].n != 0) {
-                print_branch_misses(out, cpu, evsel, avg);
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
+                if (runtime_branches_stats[ctx][cpu].n != 0)
+                        print_branch_misses(cpu, evsel, avg, out);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all branches", 0);
         } else if (
                 evsel->attr.type == PERF_TYPE_HW_CACHE &&
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-                        runtime_l1_dcache_stats[ctx][cpu].n != 0) {
-                print_l1_dcache_misses(out, cpu, evsel, avg);
+                                         ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+                if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+                        print_l1_dcache_misses(cpu, evsel, avg, out);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
         } else if (
                 evsel->attr.type == PERF_TYPE_HW_CACHE &&
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-                        runtime_l1_icache_stats[ctx][cpu].n != 0) {
-                print_l1_icache_misses(out, cpu, evsel, avg);
+                                         ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+                if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+                        print_l1_icache_misses(cpu, evsel, avg, out);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
         } else if (
                 evsel->attr.type == PERF_TYPE_HW_CACHE &&
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-                        runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
-                print_dtlb_cache_misses(out, cpu, evsel, avg);
+                                         ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+                if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+                        print_dtlb_cache_misses(cpu, evsel, avg, out);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
         } else if (
                 evsel->attr.type == PERF_TYPE_HW_CACHE &&
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-                        runtime_itlb_cache_stats[ctx][cpu].n != 0) {
-                print_itlb_cache_misses(out, cpu, evsel, avg);
+                                         ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+                if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+                        print_itlb_cache_misses(cpu, evsel, avg, out);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
         } else if (
                 evsel->attr.type == PERF_TYPE_HW_CACHE &&
                 evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
                                         ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-                                        ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-                        runtime_ll_cache_stats[ctx][cpu].n != 0) {
-                print_ll_cache_misses(out, cpu, evsel, avg);
-        } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-                        runtime_cacherefs_stats[ctx][cpu].n != 0) {
+                                         ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+                if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+                        print_ll_cache_misses(cpu, evsel, avg, out);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
+        } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
                 total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
 
                 if (total)
                         ratio = avg * 100 / total;
 
-                fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
-
+                if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+                        print_metric(ctxp, NULL, "%8.3f %%",
+                                     "of all cache refs", ratio);
+                else
+                        print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-                print_stalled_cycles_frontend(out, cpu, evsel, avg);
+                print_stalled_cycles_frontend(cpu, evsel, avg, out);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-                print_stalled_cycles_backend(out, cpu, evsel, avg);
+                print_stalled_cycles_backend(cpu, evsel, avg, out);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
                 total = avg_stats(&runtime_nsecs_stats[cpu]);
 
                 if (total) {
                         ratio = avg / total;
-                        fprintf(out, " # %8.3f GHz                    ", ratio);
+                        print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
                 } else {
-                        fprintf(out, "                                   ");
+                        print_metric(ctxp, NULL, NULL, "Ghz", 0);
                 }
         } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
                 total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
                 if (total)
-                        fprintf(out,
-                                " #   %5.2f%% transactional cycles   ",
-                                100.0 * (avg / total));
+                        print_metric(ctxp, NULL,
+                                        "%7.2f%%", "transactional cycles",
+                                        100.0 * (avg / total));
+                else
+                        print_metric(ctxp, NULL, NULL, "transactional cycles",
+                                     0);
         } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
                 total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
                 total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
                 if (total2 < avg)
                         total2 = avg;
                 if (total)
-                        fprintf(out,
-                                " #   %5.2f%% aborted cycles         ",
+                        print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
                                 100.0 * ((total2-avg) / total));
-        } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-                   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+                else
+                        print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
+        } else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
                 total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
                 if (avg)
                         ratio = total / avg;
 
-                fprintf(out, " # %8.0f cycles / transaction   ", ratio);
-        } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-                   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+                if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+                        print_metric(ctxp, NULL, "%8.0f",
+                                     "cycles / transaction", ratio);
+                else
+                        print_metric(ctxp, NULL, NULL, "cycles / transaction",
+                                     0);
+        } else if (perf_stat_evsel__is(evsel, ELISION_START)) {
                 total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
                 if (avg)
                         ratio = total / avg;
 
-                fprintf(out, " # %8.0f cycles / elision       ", ratio);
+                print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
         } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
                 if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
-                        fprintf(out, " # %8.3f CPUs utilized          ", avg / ratio);
+                        print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+                                     avg / ratio);
                 else
-                        fprintf(out, "                                   ");
+                        print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
         } else if (runtime_nsecs_stats[cpu].n != 0) {
                 char unit = 'M';
+                char unit_buf[10];
 
                 total = avg_stats(&runtime_nsecs_stats[cpu]);
 
@@ -429,9 +464,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
                         ratio *= 1000;
                         unit = 'K';
                 }
-
-                fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+                snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+                print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
         } else {
-                fprintf(out, "                                   ");
+                print_metric(ctxp, NULL, NULL, NULL, 0);
         }
 }
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index afb0c45eba34..4d9b481cf3b6 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -97,7 +97,7 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
         }
 }
 
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
         int i;
         struct perf_stat_evsel *ps = evsel->priv;
@@ -108,7 +108,7 @@ void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
         perf_stat_evsel_id_init(evsel);
 }
 
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
         evsel->priv = zalloc(sizeof(struct perf_stat_evsel));
         if (evsel->priv == NULL)
@@ -117,13 +117,13 @@ int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
         return 0;
 }
 
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
         zfree(&evsel->priv);
 }
 
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-                                      int ncpus, int nthreads)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+                                             int ncpus, int nthreads)
 {
         struct perf_counts *counts;
 
@@ -134,13 +134,13 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
         return counts ? 0 : -ENOMEM;
 }
 
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
         perf_counts__delete(evsel->prev_raw_counts);
         evsel->prev_raw_counts = NULL;
 }
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+static int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
 {
         int ncpus = perf_evsel__nr_cpus(evsel);
         int nthreads = thread_map__nr(evsel->threads);
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 086f4e128d63..0150e786ccc7 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,21 +68,23 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);
 
 extern struct stats walltime_nsecs_stats;
 
+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+                               const char *fmt, double val);
+typedef void (*new_line_t )(void *ctx);
+
+void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
                                     int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
-                                   double avg, int cpu, enum aggr_mode aggr);
-
-void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
-int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
-void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
-
-int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-                                      int ncpus, int nthreads);
-void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
+struct perf_stat_output_ctx {
+        void *ctx;
+        print_metric_t print_metric;
+        new_line_t new_line;
+};
 
-int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+                                   double avg, int cpu,
+                                   struct perf_stat_output_ctx *out);
 
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 25671fa16618..d3d279275432 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -51,30 +51,6 @@ void strbuf_grow(struct strbuf *sb, size_t extra)
         ALLOC_GROW(sb->buf, sb->len + extra + 1, sb->alloc);
 }
 
-static void strbuf_splice(struct strbuf *sb, size_t pos, size_t len,
-                                   const void *data, size_t dlen)
-{
-        if (pos + len < pos)
-                die("you want to use way too much memory");
-        if (pos > sb->len)
-                die("`pos' is too far after the end of the buffer");
-        if (pos + len > sb->len)
-                die("`pos + len' is too far after the end of the buffer");
-
-        if (dlen >= len)
-                strbuf_grow(sb, dlen - len);
-        memmove(sb->buf + pos + dlen,
-                        sb->buf + pos + len,
-                        sb->len - pos - len);
-        memcpy(sb->buf + pos, data, dlen);
-        strbuf_setlen(sb, sb->len + dlen - len);
-}
-
-void strbuf_remove(struct strbuf *sb, size_t pos, size_t len)
-{
-        strbuf_splice(sb, pos, len, NULL, 0);
-}
-
 void strbuf_add(struct strbuf *sb, const void *data, size_t len)
 {
         strbuf_grow(sb, len);
diff --git a/tools/perf/util/strbuf.h b/tools/perf/util/strbuf.h
index 529f2f035249..7a32c838884d 100644
--- a/tools/perf/util/strbuf.h
+++ b/tools/perf/util/strbuf.h
@@ -77,8 +77,6 @@ static inline void strbuf_addch(struct strbuf *sb, int c) {
         sb->buf[sb->len] = '\0';
 }
 
-extern void strbuf_remove(struct strbuf *, size_t pos, size_t len);
-
 extern void strbuf_add(struct strbuf *, const void *, size_t);
 static inline void strbuf_addstr(struct strbuf *sb, const char *s) {
         strbuf_add(sb, s, strlen(s));
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 562b8ebeae5b..b1dd68f358fc 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 "demangle-java.h"
 #include "machine.h"
 #include "vdso.h"
 #include <symbol/kallsyms.h>
@@ -1077,6 +1078,8 @@ new_symbol:
                                 demangle_flags = DMGL_PARAMS | DMGL_ANSI;
 
                         demangled = bfd_demangle(NULL, elf_name, demangle_flags);
+                        if (demangled == NULL)
+                                demangled = java_demangle_sym(elf_name, JAVA_DEMANGLE_NORET);
                         if (demangled != NULL)
                                 elf_name = demangled;
                 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index ab02209a7cf3..e7588dc91518 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1466,7 +1466,8 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
          * Read the build id if possible. This is required for
          * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
          */
-        if (filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+        if (is_regular_file(name) &&
+            filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
                 dso__set_build_id(dso, build_id);
 
         /*
@@ -1487,6 +1488,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
                                                    root_dir, name, PATH_MAX))
                         continue;
 
+                if (!is_regular_file(name))
+                        continue;
+
                 /* Name is now the name of the next image to try */
                 if (symsrc__init(ss, dso, name, symtab_type) < 0)
                         continue;
@@ -1525,6 +1529,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
         if (!runtime_ss && syms_ss)
                 runtime_ss = syms_ss;
 
+        if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
+                if (dso__build_id_is_kmod(dso, name, PATH_MAX))
+                        kmod = true;
+
         if (syms_ss)
                 ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
         else
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ccd1caa40e11..a937053a0ae0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -110,7 +110,8 @@ struct symbol_conf {
                         has_filter,
                         show_ref_callgraph,
                         hide_unresolved,
-                        raw_trace;
+                        raw_trace,
+                        report_hierarchy;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 802bb868d446..8ae051e0ec79 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -10,6 +10,7 @@
 #include <linux/err.h>
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
+#include <api/fs/fs.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index 4d4210d4e13d..1b741646eed0 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -19,7 +19,7 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
         u64 quot, rem;
 
         quot = cyc >> tc->time_shift;
-        rem  = cyc & ((1 << tc->time_shift) - 1);
+        rem  = cyc & (((u64)1 << tc->time_shift) - 1);
         return tc->time_zero + quot * tc->time_mult +
                ((rem * tc->time_mult) >> tc->time_shift);
 }
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index ead9509835d2..b7766c577b01 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -14,6 +14,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <unistd.h>
 #include "callchain.h"
 #include "strlist.h"
@@ -507,54 +508,6 @@ int parse_callchain_record(const char *arg, struct callchain_param *param)
         return ret;
 }
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep)
-{
-        size_t size = 0, alloc_size = 0;
-        void *bf = NULL, *nbf;
-        int fd, n, err = 0;
-        char sbuf[STRERR_BUFSIZE];
-
-        fd = open(filename, O_RDONLY);
-        if (fd < 0)
-                return -errno;
-
-        do {
-                if (size == alloc_size) {
-                        alloc_size += BUFSIZ;
-                        nbf = realloc(bf, alloc_size);
-                        if (!nbf) {
-                                err = -ENOMEM;
-                                break;
-                        }
-
-                        bf = nbf;
-                }
-
-                n = read(fd, bf + size, alloc_size - size);
-                if (n < 0) {
-                        if (size) {
-                                pr_warning("read failed %d: %s\n", errno,
-                                         strerror_r(errno, sbuf, sizeof(sbuf)));
-                                err = 0;
-                        } else
-                                err = -errno;
-
-                        break;
-                }
-
-                size += n;
-        } while (n > 0);
-
-        if (!err) {
-                *sizep = size;
-                *buf   = bf;
-        } else
-                free(bf);
-
-        close(fd);
-        return err;
-}
-
 const char *get_filename_for_perf_kvm(void)
 {
         const char *filename;
@@ -691,3 +644,66 @@ out:
 
         return tip;
 }
+
+bool is_regular_file(const char *file)
+{
+        struct stat st;
+
+        if (stat(file, &st))
+                return false;
+
+        return S_ISREG(st.st_mode);
+}
+
+int fetch_current_timestamp(char *buf, size_t sz)
+{
+        struct timeval tv;
+        struct tm tm;
+        char dt[32];
+
+        if (gettimeofday(&tv, NULL) || !localtime_r(&tv.tv_sec, &tm))
+                return -1;
+
+        if (!strftime(dt, sizeof(dt), "%Y%m%d%H%M%S", &tm))
+                return -1;
+
+        scnprintf(buf, sz, "%s%02u", dt, (unsigned)tv.tv_usec / 10000);
+
+        return 0;
+}
+
+void print_binary(unsigned char *data, size_t len,
+                  size_t bytes_per_line, print_binary_t printer,
+                  void *extra)
+{
+        size_t i, j, mask;
+
+        if (!printer)
+                return;
+
+        bytes_per_line = roundup_pow_of_two(bytes_per_line);
+        mask = bytes_per_line - 1;
+
+        printer(BINARY_PRINT_DATA_BEGIN, 0, extra);
+        for (i = 0; i < len; i++) {
+                if ((i & mask) == 0) {
+                        printer(BINARY_PRINT_LINE_BEGIN, -1, extra);
+                        printer(BINARY_PRINT_ADDR, i, extra);
+                }
+
+                printer(BINARY_PRINT_NUM_DATA, data[i], extra);
+
+                if (((i & mask) == mask) || i == len - 1) {
+                        for (j = 0; j < mask-(i & mask); j++)
+                                printer(BINARY_PRINT_NUM_PAD, -1, extra);
+
+                        printer(BINARY_PRINT_SEP, i, extra);
+                        for (j = i & ~mask; j <= i; j++)
+                                printer(BINARY_PRINT_CHAR_DATA, data[j], extra);
+                        for (j = 0; j < mask-(i & mask); j++)
+                                printer(BINARY_PRINT_CHAR_PAD, i, extra);
+                        printer(BINARY_PRINT_LINE_END, -1, extra);
+                }
+        }
+        printer(BINARY_PRINT_DATA_END, -1, extra);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index fe915e616f9b..d0d50cef8b2a 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -82,6 +82,8 @@
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
+extern const char *spaces;
+extern const char *dots;
 extern char buildid_dir[];
 
 /* On most systems <limits.h> would have given us this, but
@@ -303,7 +305,6 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
                   bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
-int filename__read_str(const char *filename, char **buf, size_t *sizep);
 int perf_event_paranoid(void);
 
 void mem_bswap_64(void *src, int byte_size);
@@ -343,5 +344,27 @@ int fetch_kernel_version(unsigned int *puint,
 #define KVER_PARAM(x)   KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x)
 
 const char *perf_tip(const char *dirpath);
+bool is_regular_file(const char *file);
+int fetch_current_timestamp(char *buf, size_t sz);
+
+enum binary_printer_ops {
+        BINARY_PRINT_DATA_BEGIN,
+        BINARY_PRINT_LINE_BEGIN,
+        BINARY_PRINT_ADDR,
+        BINARY_PRINT_NUM_DATA,
+        BINARY_PRINT_NUM_PAD,
+        BINARY_PRINT_SEP,
+        BINARY_PRINT_CHAR_DATA,
+        BINARY_PRINT_CHAR_PAD,
+        BINARY_PRINT_LINE_END,
+        BINARY_PRINT_DATA_END,
+};
+
+typedef void (*print_binary_t)(enum binary_printer_ops,
+                               unsigned int val,
+                               void *extra);
 
+void print_binary(unsigned char *data, size_t len,
+                  size_t bytes_per_line, print_binary_t printer,
+                  void *extra);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dac7e05a6ac..3fa94e291d16 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1970,7 +1970,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
 }
 
 static void
-dump_cstate_pstate_config_info(family, model)
+dump_cstate_pstate_config_info(unsigned int family, unsigned int model)
 {
         if (!do_nhm_platform_info)
                 return;
@@ -2142,7 +2142,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define RAPL_POWER_GRANULARITY  0x7FFF  /* 15 bit power granularity */
 #define RAPL_TIME_GRANULARITY   0x3F /* 6 bit time granularity */
 
-double get_tdp(model)
+double get_tdp(unsigned int model)
 {
         unsigned long long msr;
 
@@ -2256,7 +2256,7 @@ void rapl_probe(unsigned int family, unsigned int model)
         return;
 }
 
-void perf_limit_reasons_probe(family, model)
+void perf_limit_reasons_probe(unsigned int family, unsigned int model)
 {
         if (!genuine_intel)
                 return;
@@ -2792,7 +2792,7 @@ void process_cpuid()
         perf_limit_reasons_probe(family, model);
 
         if (debug)
-                dump_cstate_pstate_config_info();
+                dump_cstate_pstate_config_info(family, model);
 
         if (has_skl_msrs(family, model))
                 calculate_tsc_tweak();
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 844787a0d7be..5eb49b7f864c 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -33,7 +33,7 @@ if grep -Pq '\x00' < $file
 then
         print_warning Console output contains nul bytes, old qemu still running?
 fi
-egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|Stall ended before state dump start' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
+egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
 if test -s $1.diags
 then
         print_warning Assertion failure in $file $title
@@ -64,10 +64,12 @@ then
         then
                 summary="$summary  lockdep: $n_badness"
         fi
-        n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|Stall ended before state dump start' $1`
+        n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
         if test "$n_stalls" -ne 0
         then
                 summary="$summary  Stalls: $n_stalls"
         fi
         print_warning Summary: $summary
+else
+        rm $1.diags
 fi
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d0c473f65850..d5ce7d7aae3e 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -4,15 +4,16 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall
-TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso \
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall \
+                        check_initial_reg_state sigreturn ldt_gdt
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
                         test_FCMOV test_FCOMI test_FISTTP \
-                        ldt_gdt \
                         vdso_restorer
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
-BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
+BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
 
@@ -40,7 +41,7 @@ clean:
 $(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c
         $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -lm
 
-$(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c
+$(TARGETS_C_64BIT_ALL:%=%_64): %_64: %.c
         $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl
 
 # x86_64 users should be encouraged to install 32-bit libraries
@@ -65,3 +66,9 @@ endif
 sysret_ss_attrs_64: thunks.S
 ptrace_syscall_32: raw_syscall_helper_32.S
 test_syscall_vdso_32: thunks_32.S
+
+# check_initial_reg_state is special: it needs a custom entry, and it
+# needs to be static so that its interpreter doesn't destroy its initial
+# state.
+check_initial_reg_state_32: CFLAGS += -Wl,-ereal_start -static
+check_initial_reg_state_64: CFLAGS += -Wl,-ereal_start -static
diff --git a/tools/testing/selftests/x86/check_initial_reg_state.c b/tools/testing/selftests/x86/check_initial_reg_state.c
new file mode 100644
index 000000000000..6aaed9b85baf
--- /dev/null
+++ b/tools/testing/selftests/x86/check_initial_reg_state.c
@@ -0,0 +1,109 @@
+/*
+ * check_initial_reg_state.c - check that execve sets the correct state
+ * Copyright (c) 2014-2016 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdio.h>
+
+unsigned long ax, bx, cx, dx, si, di, bp, sp, flags;
+unsigned long r8, r9, r10, r11, r12, r13, r14, r15;
+
+asm (
+        ".pushsection .text\n\t"
+        ".type real_start, @function\n\t"
+        ".global real_start\n\t"
+        "real_start:\n\t"
+#ifdef __x86_64__
+        "mov %rax, ax\n\t"
+        "mov %rbx, bx\n\t"
+        "mov %rcx, cx\n\t"
+        "mov %rdx, dx\n\t"
+        "mov %rsi, si\n\t"
+        "mov %rdi, di\n\t"
+        "mov %rbp, bp\n\t"
+        "mov %rsp, sp\n\t"
+        "mov %r8, r8\n\t"
+        "mov %r9, r9\n\t"
+        "mov %r10, r10\n\t"
+        "mov %r11, r11\n\t"
+        "mov %r12, r12\n\t"
+        "mov %r13, r13\n\t"
+        "mov %r14, r14\n\t"
+        "mov %r15, r15\n\t"
+        "pushfq\n\t"
+        "popq flags\n\t"
+#else
+        "mov %eax, ax\n\t"
+        "mov %ebx, bx\n\t"
+        "mov %ecx, cx\n\t"
+        "mov %edx, dx\n\t"
+        "mov %esi, si\n\t"
+        "mov %edi, di\n\t"
+        "mov %ebp, bp\n\t"
+        "mov %esp, sp\n\t"
+        "pushfl\n\t"
+        "popl flags\n\t"
+#endif
+        "jmp _start\n\t"
+        ".size real_start, . - real_start\n\t"
+        ".popsection");
+
+int main()
+{
+        int nerrs = 0;
+
+        if (sp == 0) {
+                printf("[FAIL]\tTest was built incorrectly\n");
+                return 1;
+        }
+
+        if (ax || bx || cx || dx || si || di || bp
+#ifdef __x86_64__
+            || r8 || r9 || r10 || r11 || r12 || r13 || r14 || r15
+#endif
+                ) {
+                printf("[FAIL]\tAll GPRs except SP should be 0\n");
+#define SHOW(x) printf("\t" #x " = 0x%lx\n", x);
+                SHOW(ax);
+                SHOW(bx);
+                SHOW(cx);
+                SHOW(dx);
+                SHOW(si);
+                SHOW(di);
+                SHOW(bp);
+                SHOW(sp);
+#ifdef __x86_64__
+                SHOW(r8);
+                SHOW(r9);
+                SHOW(r10);
+                SHOW(r11);
+                SHOW(r12);
+                SHOW(r13);
+                SHOW(r14);
+                SHOW(r15);
+#endif
+                nerrs++;
+        } else {
+                printf("[OK]\tAll GPRs except SP are 0\n");
+        }
+
+        if (flags != 0x202) {
+                printf("[FAIL]\tFLAGS is 0x%lx, but it should be 0x202\n", flags);
+                nerrs++;
+        } else {
+                printf("[OK]\tFLAGS is 0x202\n");
+        }
+
+        return nerrs ? 1 : 0;
+}
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 5105b49cd8aa..421456784bc6 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -103,6 +103,17 @@ static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
                 err(1, "sigaction");
 }
 
+static void setsigign(int sig, int flags)
+{
+        struct sigaction sa;
+        memset(&sa, 0, sizeof(sa));
+        sa.sa_sigaction = (void *)SIG_IGN;
+        sa.sa_flags = flags;
+        sigemptyset(&sa.sa_mask);
+        if (sigaction(sig, &sa, 0))
+                err(1, "sigaction");
+}
+
 static void clearhandler(int sig)
 {
         struct sigaction sa;
@@ -187,7 +198,7 @@ static void test_ptrace_syscall_restart(void)
 
         printf("[RUN]\tSYSEMU\n");
         if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-                err(1, "PTRACE_SYSCALL");
+                err(1, "PTRACE_SYSEMU");
         wait_trap(chld);
 
         if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -218,7 +229,7 @@ static void test_ptrace_syscall_restart(void)
                 err(1, "PTRACE_SETREGS");
 
         if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-                err(1, "PTRACE_SYSCALL");
+                err(1, "PTRACE_SYSEMU");
         wait_trap(chld);
 
         if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -250,7 +261,7 @@ static void test_ptrace_syscall_restart(void)
                 err(1, "PTRACE_SETREGS");
 
         if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
-                err(1, "PTRACE_SYSCALL");
+                err(1, "PTRACE_SYSEMU");
         wait_trap(chld);
 
         if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
@@ -277,6 +288,119 @@ static void test_ptrace_syscall_restart(void)
         }
 }
 
+static void test_restart_under_ptrace(void)
+{
+        printf("[RUN]\tkernel syscall restart under ptrace\n");
+        pid_t chld = fork();
+        if (chld < 0)
+                err(1, "fork");
+
+        if (chld == 0) {
+                if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+                        err(1, "PTRACE_TRACEME");
+
+                printf("\tChild will take a nap until signaled\n");
+                setsigign(SIGUSR1, SA_RESTART);
+                raise(SIGSTOP);
+
+                syscall(SYS_pause, 0, 0, 0, 0, 0, 0);
+                _exit(0);
+        }
+
+        int status;
+
+        /* Wait for SIGSTOP. */
+        if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+                err(1, "waitpid");
+
+        struct user_regs_struct regs;
+
+        printf("[RUN]\tSYSCALL\n");
+        if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+                err(1, "PTRACE_SYSCALL");
+        wait_trap(chld);
+
+        /* We should be stopped at pause(2) entry. */
+
+        if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+                err(1, "PTRACE_GETREGS");
+
+        if (regs.user_syscall_nr != SYS_pause ||
+            regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+            regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+            regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+                printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+                nerrs++;
+        } else {
+                printf("[OK]\tInitial nr and args are correct\n");
+        }
+
+        /* Interrupt it. */
+        kill(chld, SIGUSR1);
+
+        /* Advance.  We should be stopped at exit. */
+        printf("[RUN]\tSYSCALL\n");
+        if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+                err(1, "PTRACE_SYSCALL");
+        wait_trap(chld);
+
+        if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+                err(1, "PTRACE_GETREGS");
+
+        if (regs.user_syscall_nr != SYS_pause ||
+            regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+            regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+            regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+                printf("[FAIL]\tArgs after SIGUSR1 are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+                nerrs++;
+        } else {
+                printf("[OK]\tArgs after SIGUSR1 are correct (ax = %ld)\n",
+                       (long)regs.user_ax);
+        }
+
+        /* Poke the regs back in.  This must not break anything. */
+        if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+                err(1, "PTRACE_SETREGS");
+
+        /* Catch the (ignored) SIGUSR1. */
+        if (ptrace(PTRACE_CONT, chld, 0, 0) != 0)
+                err(1, "PTRACE_CONT");
+        if (waitpid(chld, &status, 0) != chld)
+                err(1, "waitpid");
+        if (!WIFSTOPPED(status)) {
+                printf("[FAIL]\tChild was stopped for SIGUSR1 (status = 0x%x)\n", status);
+                nerrs++;
+        } else {
+                printf("[OK]\tChild got SIGUSR1\n");
+        }
+
+        /* The next event should be pause(2) again. */
+        printf("[RUN]\tStep again\n");
+        if (ptrace(PTRACE_SYSCALL, chld, 0, 0) != 0)
+                err(1, "PTRACE_SYSCALL");
+        wait_trap(chld);
+
+        /* We should be stopped at pause(2) entry. */
+
+        if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+                err(1, "PTRACE_GETREGS");
+
+        if (regs.user_syscall_nr != SYS_pause ||
+            regs.user_arg0 != 0 || regs.user_arg1 != 0 ||
+            regs.user_arg2 != 0 || regs.user_arg3 != 0 ||
+            regs.user_arg4 != 0 || regs.user_arg5 != 0) {
+                printf("[FAIL]\tpause did not restart (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+                nerrs++;
+        } else {
+                printf("[OK]\tpause(2) restarted correctly\n");
+        }
+
+        /* Kill it. */
+        kill(chld, SIGKILL);
+        if (waitpid(chld, &status, 0) != chld)
+                err(1, "waitpid");
+}
+
 int main()
 {
         printf("[RUN]\tCheck int80 return regs\n");
@@ -290,5 +414,7 @@ int main()
 
         test_ptrace_syscall_restart();
 
+        test_restart_under_ptrace();
+
         return 0;
 }
diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c
index b5aa1bab7416..8a577e7070c6 100644
--- a/tools/testing/selftests/x86/sigreturn.c
+++ b/tools/testing/selftests/x86/sigreturn.c
@@ -54,6 +54,37 @@
 #include <sys/ptrace.h>
 #include <sys/user.h>
 
+/* Pull in AR_xyz defines. */
+typedef unsigned int u32;
+typedef unsigned short u16;
+#include "../../../../arch/x86/include/asm/desc_defs.h"
+
+/*
+ * Copied from asm/ucontext.h, as asm/ucontext.h conflicts badly with the glibc
+ * headers.
+ */
+#ifdef __x86_64__
+/*
+ * UC_SIGCONTEXT_SS will be set when delivering 64-bit or x32 signals on
+ * kernels that save SS in the sigcontext.  All kernels that set
+ * UC_SIGCONTEXT_SS will correctly restore at least the low 32 bits of esp
+ * regardless of SS (i.e. they implement espfix).
+ *
+ * Kernels that set UC_SIGCONTEXT_SS will also set UC_STRICT_RESTORE_SS
+ * when delivering a signal that came from 64-bit code.
+ *
+ * Sigreturn restores SS as follows:
+ *
+ * if (saved SS is valid || UC_STRICT_RESTORE_SS is set ||
+ *     saved CS is not 64-bit)
+ *         new SS = saved SS  (will fail IRET and signal if invalid)
+ * else
+ *         new SS = a flat 32-bit data segment
+ */
+#define UC_SIGCONTEXT_SS       0x2
+#define UC_STRICT_RESTORE_SS   0x4
+#endif
+
 /*
  * In principle, this test can run on Linux emulation layers (e.g.
  * Illumos "LX branded zones").  Solaris-based kernels reserve LDT
@@ -267,6 +298,9 @@ static gregset_t initial_regs, requested_regs, resulting_regs;
 /* Instructions for the SIGUSR1 handler. */
 static volatile unsigned short sig_cs, sig_ss;
 static volatile sig_atomic_t sig_trapped, sig_err, sig_trapno;
+#ifdef __x86_64__
+static volatile sig_atomic_t sig_corrupt_final_ss;
+#endif
 
 /* Abstractions for some 32-bit vs 64-bit differences. */
 #ifdef __x86_64__
@@ -305,9 +339,105 @@ static greg_t *csptr(ucontext_t *ctx)
 }
 #endif
 
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+int cs_bitness(unsigned short cs)
+{
+        uint32_t valid = 0, ar;
+        asm ("lar %[cs], %[ar]\n\t"
+             "jnz 1f\n\t"
+             "mov $1, %[valid]\n\t"
+             "1:"
+             : [ar] "=r" (ar), [valid] "+rm" (valid)
+             : [cs] "r" (cs));
+
+        if (!valid)
+                return -1;
+
+        bool db = (ar & (1 << 22));
+        bool l = (ar & (1 << 21));
+
+        if (!(ar & (1<<11)))
+            return -1;  /* Not code. */
+
+        if (l && !db)
+                return 64;
+        else if (!l && db)
+                return 32;
+        else if (!l && !db)
+                return 16;
+        else
+                return -1;      /* Unknown bitness. */
+}
+
+/*
+ * Checks a given selector for its code bitness or returns -1 if it's not
+ * a usable code segment selector.
+ */
+bool is_valid_ss(unsigned short cs)
+{
+        uint32_t valid = 0, ar;
+        asm ("lar %[cs], %[ar]\n\t"
+             "jnz 1f\n\t"
+             "mov $1, %[valid]\n\t"
+             "1:"
+             : [ar] "=r" (ar), [valid] "+rm" (valid)
+             : [cs] "r" (cs));
+
+        if (!valid)
+                return false;
+
+        if ((ar & AR_TYPE_MASK) != AR_TYPE_RWDATA &&
+            (ar & AR_TYPE_MASK) != AR_TYPE_RWDATA_EXPDOWN)
+                return false;
+
+        return (ar & AR_P);
+}
+
 /* Number of errors in the current test case. */
 static volatile sig_atomic_t nerrs;
 
+static void validate_signal_ss(int sig, ucontext_t *ctx)
+{
+#ifdef __x86_64__
+        bool was_64bit = (cs_bitness(*csptr(ctx)) == 64);
+
+        if (!(ctx->uc_flags & UC_SIGCONTEXT_SS)) {
+                printf("[FAIL]\tUC_SIGCONTEXT_SS was not set\n");
+                nerrs++;
+
+                /*
+                 * This happens on Linux 4.1.  The rest will fail, too, so
+                 * return now to reduce the noise.
+                 */
+                return;
+        }
+
+        /* UC_STRICT_RESTORE_SS is set iff we came from 64-bit mode. */
+        if (!!(ctx->uc_flags & UC_STRICT_RESTORE_SS) != was_64bit) {
+                printf("[FAIL]\tUC_STRICT_RESTORE_SS was wrong in signal %d\n",
+                       sig);
+                nerrs++;
+        }
+
+        if (is_valid_ss(*ssptr(ctx))) {
+                /*
+                 * DOSEMU was written before 64-bit sigcontext had SS, and
+                 * it tries to figure out the signal source SS by looking at
+                 * the physical register.  Make sure that keeps working.
+                 */
+                unsigned short hw_ss;
+                asm ("mov %%ss, %0" : "=rm" (hw_ss));
+                if (hw_ss != *ssptr(ctx)) {
+                        printf("[FAIL]\tHW SS didn't match saved SS\n");
+                        nerrs++;
+                }
+        }
+#endif
+}
+
 /*
  * SIGUSR1 handler.  Sets CS and SS as requested and points IP to the
  * int3 trampoline.  Sets SP to a large known value so that we can see
@@ -317,6 +447,8 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 {
         ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+        validate_signal_ss(sig, ctx);
+
         memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
 
         *csptr(ctx) = sig_cs;
@@ -334,13 +466,16 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
 }
 
 /*
- * Called after a successful sigreturn.  Restores our state so that
- * the original raise(SIGUSR1) returns.
+ * Called after a successful sigreturn (via int3) or from a failed
+ * sigreturn (directly by kernel).  Restores our state so that the
+ * original raise(SIGUSR1) returns.
  */
 static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 {
         ucontext_t *ctx = (ucontext_t*)ctx_void;
 
+        validate_signal_ss(sig, ctx);
+
         sig_err = ctx->uc_mcontext.gregs[REG_ERR];
         sig_trapno = ctx->uc_mcontext.gregs[REG_TRAPNO];
 
@@ -358,41 +493,62 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
         memcpy(&resulting_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
         memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t));
 
+#ifdef __x86_64__
+        if (sig_corrupt_final_ss) {
+                if (ctx->uc_flags & UC_STRICT_RESTORE_SS) {
+                        printf("[FAIL]\tUC_STRICT_RESTORE_SS was set inappropriately\n");
+                        nerrs++;
+                } else {
+                        /*
+                         * DOSEMU transitions from 32-bit to 64-bit mode by
+                         * adjusting sigcontext, and it requires that this work
+                         * even if the saved SS is bogus.
+                         */
+                        printf("\tCorrupting SS on return to 64-bit mode\n");
+                        *ssptr(ctx) = 0;
+                }
+        }
+#endif
+
         sig_trapped = sig;
 }
 
-/*
- * Checks a given selector for its code bitness or returns -1 if it's not
- * a usable code segment selector.
- */
-int cs_bitness(unsigned short cs)
+#ifdef __x86_64__
+/* Tests recovery if !UC_STRICT_RESTORE_SS */
+static void sigusr2(int sig, siginfo_t *info, void *ctx_void)
 {
-        uint32_t valid = 0, ar;
-        asm ("lar %[cs], %[ar]\n\t"
-             "jnz 1f\n\t"
-             "mov $1, %[valid]\n\t"
-             "1:"
-             : [ar] "=r" (ar), [valid] "+rm" (valid)
-             : [cs] "r" (cs));
+        ucontext_t *ctx = (ucontext_t*)ctx_void;
 
-        if (!valid)
-                return -1;
+        if (!(ctx->uc_flags & UC_STRICT_RESTORE_SS)) {
+                printf("[FAIL]\traise(2) didn't set UC_STRICT_RESTORE_SS\n");
+                nerrs++;
+                return;  /* We can't do the rest. */
+        }
 
-        bool db = (ar & (1 << 22));
-        bool l = (ar & (1 << 21));
+        ctx->uc_flags &= ~UC_STRICT_RESTORE_SS;
+        *ssptr(ctx) = 0;
 
-        if (!(ar & (1<<11)))
-            return -1;  /* Not code. */
+        /* Return.  The kernel should recover without sending another signal. */
+}
 
-        if (l && !db)
-                return 64;
-        else if (!l && db)
-                return 32;
-        else if (!l && !db)
-                return 16;
-        else
-                return -1;      /* Unknown bitness. */
+static int test_nonstrict_ss(void)
+{
+        clearhandler(SIGUSR1);
+        clearhandler(SIGTRAP);
+        clearhandler(SIGSEGV);
+        clearhandler(SIGILL);
+        sethandler(SIGUSR2, sigusr2, 0);
+
+        nerrs = 0;
+
+        printf("[RUN]\tClear UC_STRICT_RESTORE_SS and corrupt SS\n");
+        raise(SIGUSR2);
+        if (!nerrs)
+                printf("[OK]\tIt worked\n");
+
+        return nerrs;
 }
+#endif
 
 /* Finds a usable code segment of the requested bitness. */
 int find_cs(int bitness)
@@ -576,6 +732,12 @@ static int test_bad_iret(int cs_bits, unsigned short ss, int force_cs)
                        errdesc, strsignal(sig_trapped));
                 return 0;
         } else {
+                /*
+                 * This also implicitly tests UC_STRICT_RESTORE_SS:
+                 * We check that these signals set UC_STRICT_RESTORE_SS and,
+                 * if UC_STRICT_RESTORE_SS doesn't cause strict behavior,
+                 * then we won't get SIGSEGV.
+                 */
                 printf("[FAIL]\tDid not get SIGSEGV\n");
                 return 1;
         }
@@ -632,6 +794,14 @@ int main()
                                                     GDT3(gdt_data16_idx));
         }
 
+#ifdef __x86_64__
+        /* Nasty ABI case: check SS corruption handling. */
+        sig_corrupt_final_ss = 1;
+        total_nerrs += test_valid_sigreturn(32, false, -1);
+        total_nerrs += test_valid_sigreturn(32, true, -1);
+        sig_corrupt_final_ss = 0;
+#endif
+
         /*
          * We're done testing valid sigreturn cases.  Now we test states
          * for which sigreturn itself will succeed but the subsequent
@@ -680,5 +850,9 @@ int main()
         if (gdt_npdata32_idx)
                 test_bad_iret(32, GDT3(gdt_npdata32_idx), -1);
 
+#ifdef __x86_64__
+        total_nerrs += test_nonstrict_ss();
+#endif
+
         return total_nerrs ? 1 : 0;
 }
diff --git a/tools/testing/selftests/x86/syscall_nt.c b/tools/testing/selftests/x86/syscall_nt.c
index 60c06af4646a..43fcab367fb0 100644
--- a/tools/testing/selftests/x86/syscall_nt.c
+++ b/tools/testing/selftests/x86/syscall_nt.c
@@ -17,6 +17,9 @@
 
 #include <stdio.h>
 #include <unistd.h>
+#include <string.h>
+#include <signal.h>
+#include <err.h>
 #include <sys/syscall.h>
 #include <asm/processor-flags.h>
 
@@ -26,6 +29,8 @@
 # define WIDTH "l"
 #endif
 
+static unsigned int nerrs;
+
 static unsigned long get_eflags(void)
 {
         unsigned long eflags;
@@ -39,16 +44,52 @@ static void set_eflags(unsigned long eflags)
                       : : "rm" (eflags) : "flags");
 }
 
-int main()
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+                       int flags)
 {
-        printf("[RUN]\tSet NT and issue a syscall\n");
-        set_eflags(get_eflags() | X86_EFLAGS_NT);
+        struct sigaction sa;
+        memset(&sa, 0, sizeof(sa));
+        sa.sa_sigaction = handler;
+        sa.sa_flags = SA_SIGINFO | flags;
+        sigemptyset(&sa.sa_mask);
+        if (sigaction(sig, &sa, 0))
+                err(1, "sigaction");
+}
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+}
+
+static void do_it(unsigned long extraflags)
+{
+        unsigned long flags;
+
+        set_eflags(get_eflags() | extraflags);
         syscall(SYS_getpid);
-        if (get_eflags() & X86_EFLAGS_NT) {
-                printf("[OK]\tThe syscall worked and NT is still set\n");
-                return 0;
+        flags = get_eflags();
+        if ((flags & extraflags) == extraflags) {
+                printf("[OK]\tThe syscall worked and flags are still set\n");
         } else {
-                printf("[FAIL]\tThe syscall worked but NT was cleared\n");
-                return 1;
+                printf("[FAIL]\tThe syscall worked but flags were cleared (flags = 0x%lx but expected 0x%lx set)\n",
+                       flags, extraflags);
+                nerrs++;
         }
 }
+
+int main(void)
+{
+        printf("[RUN]\tSet NT and issue a syscall\n");
+        do_it(X86_EFLAGS_NT);
+
+        /*
+         * Now try it again with TF set -- TF forces returns via IRET in all
+         * cases except non-ptregs-using 64-bit full fast path syscalls.
+         */
+
+        sethandler(SIGTRAP, sigtrap, 0);
+
+        printf("[RUN]\tSet NT|TF and issue a syscall\n");
+        do_it(X86_EFLAGS_NT | X86_EFLAGS_TF);
+
+        return nerrs == 0 ? 0 : 1;
+}