51 files changed, 447 insertions, 183 deletions

diff --git a/tools/include/asm-generic/bitops.h b/tools/include/asm-generic/bitops.h
index 6eedba1f7732..653d1bad77de 100644
--- a/tools/include/asm-generic/bitops.h
+++ b/tools/include/asm-generic/bitops.h
@@ -22,6 +22,8 @@
 #error only <linux/bitops.h> can be included directly
 #endif
 
+#include <asm-generic/bitops/hweight.h>
+
 #include <asm-generic/bitops/atomic.h>
 
 #endif /* __TOOLS_ASM_GENERIC_BITOPS_H */
diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000000..318bb2b202b0
--- /dev/null
+++ b/tools/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1 @@
+#include "../../../../include/asm-generic/bitops/arch_hweight.h"
diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000000..0afd644aff83
--- /dev/null
+++ b/tools/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1 @@
+#include "../../../../include/asm-generic/bitops/const_hweight.h"
diff --git a/tools/include/asm-generic/bitops/hweight.h b/tools/include/asm-generic/bitops/hweight.h
new file mode 100644
index 000000000000..290120c01a8e
--- /dev/null
+++ b/tools/include/asm-generic/bitops/hweight.h
@@ -0,0 +1,7 @@
+#ifndef _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+#define _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_
+
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
+
+#endif /* _TOOLS_LINUX_ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h
index 26005a15e7e2..5ad9ee1dd7f6 100644
--- a/tools/include/linux/bitops.h
+++ b/tools/include/linux/bitops.h
@@ -1,9 +1,9 @@
 #ifndef _TOOLS_LINUX_BITOPS_H_
 #define _TOOLS_LINUX_BITOPS_H_
 
+#include <asm/types.h>
 #include <linux/kernel.h>
 #include <linux/compiler.h>
-#include <asm/hweight.h>
 
 #ifndef __WORDSIZE
 #define __WORDSIZE (__SIZEOF_LONG__ * 8)
@@ -19,6 +19,11 @@
 #define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 #define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
 
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
 /*
  * Include this here because some architectures need generic_ffs/fls in
  * scope
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
index a74fba6d7743..86ea2d7b8845 100644
--- a/tools/lib/api/fs/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
@@ -67,7 +67,7 @@ int debugfs_valid_mountpoint(const char *debugfs)
 
         if (statfs(debugfs, &st_fs) < 0)
                 return -ENOENT;
-        else if (st_fs.f_type != (long) DEBUGFS_MAGIC)
+        else if ((long)st_fs.f_type != (long)DEBUGFS_MAGIC)
                 return -ENOENT;
 
         return 0;
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index 65d9be3f9887..128ef6332a6b 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -79,7 +79,7 @@ static int fs__valid_mount(const char *fs, long magic)
 
         if (statfs(fs, &st_fs) < 0)
                 return -ENOENT;
-        else if (st_fs.f_type != magic)
+        else if ((long)st_fs.f_type != magic)
                 return -ENOENT;
 
         return 0;
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 6f803609e498..0b0112c80f22 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -317,7 +317,7 @@ int pthread_mutex_destroy(pthread_mutex_t *mutex)
          *
          * TODO: Hook into free() and add that check there as well.
          */
-        debug_check_no_locks_freed(mutex, mutex + sizeof(*mutex));
+        debug_check_no_locks_freed(mutex, sizeof(*mutex));
         __del_lock(__get_lock(mutex));
         return ll_pthread_mutex_destroy(mutex);
 }
@@ -341,7 +341,7 @@ int pthread_rwlock_destroy(pthread_rwlock_t *rwlock)
 {
         try_init_preload();
 
-        debug_check_no_locks_freed(rwlock, rwlock + sizeof(*rwlock));
+        debug_check_no_locks_freed(rwlock, sizeof(*rwlock));
         __del_lock(__get_lock(rwlock));
         return ll_pthread_rwlock_destroy(rwlock);
 }
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 83e2887f91a3..fbbfdc39271d 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -6,12 +6,15 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
 tools/include/asm/bug.h
+tools/include/asm-generic/bitops/arch_hweight.h
 tools/include/asm-generic/bitops/atomic.h
+tools/include/asm-generic/bitops/const_hweight.h
 tools/include/asm-generic/bitops/__ffs.h
 tools/include/asm-generic/bitops/__fls.h
 tools/include/asm-generic/bitops/find.h
 tools/include/asm-generic/bitops/fls64.h
 tools/include/asm-generic/bitops/fls.h
+tools/include/asm-generic/bitops/hweight.h
 tools/include/asm-generic/bitops.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
@@ -19,6 +22,8 @@ tools/include/linux/export.h
 tools/include/linux/hash.h
 tools/include/linux/log2.h
 tools/include/linux/types.h
+include/asm-generic/bitops/arch_hweight.h
+include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
@@ -29,6 +34,7 @@ include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
 lib/find_next_bit.c
+lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 67a03a825b3c..aa6a50447c32 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -232,12 +232,15 @@ LIB_H += ../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += ../include/linux/bitops.h
+LIB_H += ../include/asm-generic/bitops/arch_hweight.h
 LIB_H += ../include/asm-generic/bitops/atomic.h
+LIB_H += ../include/asm-generic/bitops/const_hweight.h
 LIB_H += ../include/asm-generic/bitops/find.h
 LIB_H += ../include/asm-generic/bitops/fls64.h
 LIB_H += ../include/asm-generic/bitops/fls.h
 LIB_H += ../include/asm-generic/bitops/__ffs.h
 LIB_H += ../include/asm-generic/bitops/__fls.h
+LIB_H += ../include/asm-generic/bitops/hweight.h
 LIB_H += ../include/asm-generic/bitops.h
 LIB_H += ../include/linux/compiler.h
 LIB_H += ../include/linux/log2.h
@@ -255,7 +258,6 @@ LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += ../include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
-LIB_H += util/include/asm/hweight.h
 LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
@@ -462,10 +464,12 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
-ifeq ($(RAW_ARCH),x86_64)
+ifeq ($(ARCH), x86)
+ifeq ($(IS_64_BIT), 1)
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memset-x86-64-asm.o
 endif
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-hash.o
 BUILTIN_OBJS += $(OUTPUT)bench/futex-wake.o
@@ -743,6 +747,9 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c $(OUTPUT)PERF-CFLAGS
 $(OUTPUT)util/rbtree.o: ../../lib/rbtree.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
+$(OUTPUT)util/hweight.o: ../../lib/hweight.c $(OUTPUT)PERF-CFLAGS
+        $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
+
 $(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c $(OUTPUT)PERF-CFLAGS
         $(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) -Wno-unused-parameter -DETC_PERFCONFIG='"$(ETC_PERFCONFIG_SQ)"' $<
 
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3bb50eac5542..0c370f81e002 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -103,7 +103,7 @@ static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
                 return NULL;
         }
 
-        result = dwarf_cfi_addrframe(cfi, pc, &frame);
+        result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
         if (result) {
                 pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
                 return NULL;
@@ -128,7 +128,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
                 return NULL;
         }
 
-        result = dwarf_cfi_addrframe(cfi, pc, &frame);
+        result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
         if (result) {
                 pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
                 return NULL;
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
  *              yet used)
  *      -1 in case of errors
  */
-static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
+static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc)
 {
         int             rc = -1;
         Dwfl            *dwfl;
@@ -155,6 +155,7 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
         Dwarf_Addr      start = pc;
         Dwarf_Addr      end = pc;
         bool            signalp;
+        const char      *exec_file = dso->long_name;
 
         dwfl = dso->dwfl;
 
@@ -165,8 +166,10 @@ static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
                         return -1;
                 }
 
-                if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) {
-                        pr_debug("dwfl_report_offline() failed %s\n",
+                mod = dwfl_report_elf(dwfl, exec_file, exec_file, -1,
+                                                map_start, false);
+                if (!mod) {
+                        pr_debug("dwfl_report_elf() failed %s\n",
                                                 dwarf_errmsg(-1));
                         /*
                          * We normally cache the DWARF debug info and never
@@ -256,10 +259,10 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
                 return skip_slot;
         }
 
-        rc = check_return_addr(dso, ip);
+        rc = check_return_addr(dso, al.map->start, ip);
 
-        pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
-                                dso->long_name, chain->nr, ip, rc);
+        pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
+                                dso->long_name, al.sym->name, ip, rc);
 
         if (rc == 0) {
                 /*
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 07a8d7646a15..005cc283790c 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -19,12 +19,12 @@
 #include <stdlib.h>
 #include <signal.h>
 #include <sys/wait.h>
-#include <linux/unistd.h>
 #include <string.h>
 #include <errno.h>
 #include <assert.h>
 #include <sys/time.h>
 #include <sys/types.h>
+#include <sys/syscall.h>
 
 #include <pthread.h>
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e7417fe97a97..747f86103599 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -232,7 +232,7 @@ static int __cmd_annotate(struct perf_annotate *ann)
                 if (nr_samples > 0) {
                         total_nr_samples += nr_samples;
                         hists__collapse_resort(hists, NULL);
-                        hists__output_resort(hists);
+                        hists__output_resort(hists, NULL);
 
                         if (symbol_conf.event_group &&
                             !perf_evsel__is_group_leader(pos))
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 1ce425d101a9..1fd96c13f199 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -545,6 +545,42 @@ hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
         return __hist_entry__cmp_compute(p_left, p_right, c);
 }
 
+static int64_t
+hist_entry__cmp_nop(struct hist_entry *left __maybe_unused,
+                    struct hist_entry *right __maybe_unused)
+{
+        return 0;
+}
+
+static int64_t
+hist_entry__cmp_baseline(struct hist_entry *left, struct hist_entry *right)
+{
+        if (sort_compute)
+                return 0;
+
+        if (left->stat.period == right->stat.period)
+                return 0;
+        return left->stat.period > right->stat.period ? 1 : -1;
+}
+
+static int64_t
+hist_entry__cmp_delta(struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute(right, left, COMPUTE_DELTA);
+}
+
+static int64_t
+hist_entry__cmp_ratio(struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute(right, left, COMPUTE_RATIO);
+}
+
+static int64_t
+hist_entry__cmp_wdiff(struct hist_entry *left, struct hist_entry *right)
+{
+        return hist_entry__cmp_compute(right, left, COMPUTE_WEIGHTED_DIFF);
+}
+
 static void insert_hist_entry_by_compute(struct rb_root *root,
                                          struct hist_entry *he,
                                          int c)
@@ -605,7 +641,7 @@ static void hists__process(struct hists *hists)
                 hists__precompute(hists);
                 hists__compute_resort(hists);
         } else {
-                hists__output_resort(hists);
+                hists__output_resort(hists, NULL);
         }
 
         hists__fprintf(hists, true, 0, 0, 0, stdout);
@@ -1038,27 +1074,35 @@ static void data__hpp_register(struct data__file *d, int idx)
         fmt->header = hpp__header;
         fmt->width  = hpp__width;
         fmt->entry  = hpp__entry_global;
+        fmt->cmp    = hist_entry__cmp_nop;
+        fmt->collapse = hist_entry__cmp_nop;
 
         /* TODO more colors */
         switch (idx) {
         case PERF_HPP_DIFF__BASELINE:
                 fmt->color = hpp__color_baseline;
+                fmt->sort  = hist_entry__cmp_baseline;
                 break;
         case PERF_HPP_DIFF__DELTA:
                 fmt->color = hpp__color_delta;
+                fmt->sort  = hist_entry__cmp_delta;
                 break;
         case PERF_HPP_DIFF__RATIO:
                 fmt->color = hpp__color_ratio;
+                fmt->sort  = hist_entry__cmp_ratio;
                 break;
         case PERF_HPP_DIFF__WEIGHTED_DIFF:
                 fmt->color = hpp__color_wdiff;
+                fmt->sort  = hist_entry__cmp_wdiff;
                 break;
         default:
+                fmt->sort  = hist_entry__cmp_nop;
                 break;
         }
 
         init_header(d, dfmt);
         perf_hpp__column_register(fmt);
+        perf_hpp__register_sort_field(fmt);
 }
 
 static void ui_init(void)
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 011195e38f21..198f3c3aff95 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -19,7 +19,9 @@
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
         int i;
-        const struct option list_options[] = {
+        bool raw_dump = false;
+        struct option list_options[] = {
+                OPT_BOOLEAN(0, "raw-dump", &raw_dump, "Dump raw events"),
                 OPT_END()
         };
         const char * const list_usage[] = {
@@ -27,11 +29,18 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                 NULL
         };
 
+        set_option_flag(list_options, 0, "raw-dump", PARSE_OPT_HIDDEN);
+
         argc = parse_options(argc, argv, list_options, list_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
 
         setup_pager();
 
+        if (raw_dump) {
+                print_events(NULL, true);
+                return 0;
+        }
+
         if (argc == 0) {
                 print_events(NULL, false);
                 return 0;
@@ -53,8 +62,6 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
                         print_hwcache_events(NULL, false);
                 else if (strcmp(argv[i], "pmu") == 0)
                         print_pmu_events(NULL, false);
-                else if (strcmp(argv[i], "--raw-dump") == 0)
-                        print_events(NULL, true);
                 else {
                         char *sep = strchr(argv[i], ':'), *s;
                         int sep_idx;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 39367609c707..072ae8ad67fc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -457,6 +457,19 @@ static void report__collapse_hists(struct report *rep)
         ui_progress__finish();
 }
 
+static void report__output_resort(struct report *rep)
+{
+        struct ui_progress prog;
+        struct perf_evsel *pos;
+
+        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);
+
+        ui_progress__finish();
+}
+
 static int __cmd_report(struct report *rep)
 {
         int ret;
@@ -505,13 +518,20 @@ static int __cmd_report(struct report *rep)
         if (session_done())
                 return 0;
 
+        /*
+         * recalculate number of entries after collapsing since it
+         * might be changed during the collapse phase.
+         */
+        rep->nr_entries = 0;
+        evlist__for_each(session->evlist, pos)
+                rep->nr_entries += evsel__hists(pos)->nr_entries;
+
         if (rep->nr_entries == 0) {
                 ui__error("The %s file has no samples!\n", file->path);
                 return 0;
         }
 
-        evlist__for_each(session->evlist, pos)
-                hists__output_resort(evsel__hists(pos));
+        report__output_resort(rep);
 
         return report__browse_hists(rep);
 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 0aa7747ff139..616f0fcb4701 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -66,7 +66,6 @@
 #include <sys/utsname.h>
 #include <sys/mman.h>
 
-#include <linux/unistd.h>
 #include <linux/types.h>
 
 static volatile int done;
@@ -285,7 +284,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
         }
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         hists__output_recalc_col_len(hists, top->print_entries - printed);
         putchar('\n');
@@ -554,7 +553,7 @@ static void perf_top__sort_new_samples(void *arg)
         }
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 }
 
 static void *display_thread_tui(void *arg)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 5d4b039fe1ed..648e31ff4021 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -20,7 +20,7 @@ NO_PERF_REGS := 1
 
 # Additional ARCH settings for x86
 ifeq ($(ARCH),x86)
-  ifeq (${IS_X86_64}, 1)
+  ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT
     ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memset_64.S
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index 851cd0172a76..ff95a68741d1 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -1,7 +1,7 @@
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
+RAW_ARCH := $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
@@ -9,23 +9,23 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/tile.*/tile/ )
 
 # Additional ARCH settings for x86
-ifeq ($(ARCH),i386)
-  override ARCH := x86
+ifeq ($(RAW_ARCH),i386)
+  ARCH ?= x86
 endif
 
-ifeq ($(ARCH),x86_64)
-  override ARCH := x86
-  IS_X86_64 := 0
-  ifeq (, $(findstring m32,$(CFLAGS)))
-    IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -x c - | tail -n 1)
-    RAW_ARCH := x86_64
+ifeq ($(RAW_ARCH),x86_64)
+  ARCH ?= x86
+
+  ifneq (, $(findstring m32,$(CFLAGS)))
+    RAW_ARCH := x86_32
   endif
 endif
 
-ifeq (${IS_X86_64}, 1)
+ARCH ?= $(RAW_ARCH)
+
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
   IS_64_BIT := 1
-else ifeq ($(ARCH),x86)
-  IS_64_BIT := 0
 else
-  IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+  IS_64_BIT := 0
 endif
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index a3b13d7dc1d4..6ef68165c9db 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,7 +6,6 @@
 #include <sys/syscall.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
-#include <asm/unistd.h>
 
 #if defined(__i386__)
 #define mb()            asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
diff --git a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
index 790ceba6ad3f..28431d1bbcf5 100644
--- a/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/perl/Perf-Trace-Util/Context.c
@@ -5,7 +5,10 @@
  *      ANY CHANGES MADE HERE WILL BE LOST! 
  *
  */
-
+#include <stdbool.h>
+#ifndef HAS_BOOL
+# define HAS_BOOL 1
+#endif
 #line 1 "Context.xs"
 /*
  * Context.xs.  XS interfaces for perf script.
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index ab28cca2cb97..0bf06bec68c7 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -11,6 +11,9 @@
 #include "thread.h"
 #include "callchain.h"
 
+/* For bsearch. We try to unwind functions in shared object. */
+#include <stdlib.h>
+
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
                         union perf_event *event,
                         struct perf_sample *sample __maybe_unused,
@@ -28,7 +31,7 @@ static int init_live_machine(struct machine *machine)
                                                   mmap_handler, machine, true);
 }
 
-#define MAX_STACK 6
+#define MAX_STACK 8
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
@@ -37,6 +40,8 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
         static const char *funcs[MAX_STACK] = {
                 "test__arch_unwind_sample",
                 "unwind_thread",
+                "compare",
+                "bsearch",
                 "krava_3",
                 "krava_2",
                 "krava_1",
@@ -88,10 +93,37 @@ static int unwind_thread(struct thread *thread)
         return err;
 }
 
+static int global_unwind_retval = -INT_MAX;
+
+__attribute__ ((noinline))
+static int compare(void *p1, void *p2)
+{
+        /* Any possible value should be 'thread' */
+        struct thread *thread = *(struct thread **)p1;
+
+        if (global_unwind_retval == -INT_MAX)
+                global_unwind_retval = unwind_thread(thread);
+
+        return p1 - p2;
+}
+
 __attribute__ ((noinline))
 static int krava_3(struct thread *thread)
 {
-        return unwind_thread(thread);
+        struct thread *array[2] = {thread, thread};
+        void *fp = &bsearch;
+        /*
+         * make _bsearch a volatile function pointer to
+         * prevent potential optimization, which may expand
+         * bsearch and call compare directly from this function,
+         * instead of libc shared object.
+         */
+        void *(*volatile _bsearch)(void *, void *, size_t,
+                        size_t, int (*)(void *, void *));
+
+        _bsearch = fp;
+        _bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+        return global_unwind_retval;
 }
 
 __attribute__ ((noinline))
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 614d5c4978ab..8d110dec393e 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -187,7 +187,7 @@ 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);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("use callchain: %d, cumulate callchain: %d\n",
@@ -454,12 +454,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
          *   30.00%    10.00%     perf  perf           [.] cmd_record
          *   20.00%     0.00%     bash  libc           [.] malloc
          *   10.00%    10.00%     bash  [kernel]       [k] page_fault
-         *   10.00%    10.00%     perf  [kernel]       [k] schedule
-         *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
+         *   10.00%    10.00%     bash  bash           [.] xmalloc
          *   10.00%    10.00%     perf  [kernel]       [k] page_fault
-         *   10.00%    10.00%     perf  libc           [.] free
          *   10.00%    10.00%     perf  libc           [.] malloc
-         *   10.00%    10.00%     bash  bash           [.] xmalloc
+         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *   10.00%    10.00%     perf  libc           [.] free
+         *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
          */
         struct result expected[] = {
                 { 7000, 2000, "perf", "perf",     "main" },
@@ -468,12 +468,12 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 { 3000, 1000, "perf", "perf",     "cmd_record" },
                 { 2000,    0, "bash", "libc",     "malloc" },
                 { 1000, 1000, "bash", "[kernel]", "page_fault" },
-                { 1000, 1000, "perf", "[kernel]", "schedule" },
-                { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
+                { 1000, 1000, "bash", "bash",     "xmalloc" },
                 { 1000, 1000, "perf", "[kernel]", "page_fault" },
+                { 1000, 1000, "perf", "[kernel]", "schedule" },
                 { 1000, 1000, "perf", "libc",     "free" },
                 { 1000, 1000, "perf", "libc",     "malloc" },
-                { 1000, 1000, "bash", "bash",     "xmalloc" },
+                { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
         };
 
         symbol_conf.use_callchain = false;
@@ -537,10 +537,13 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  malloc
          *                  main
          *
-         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *   10.00%    10.00%     bash  bash           [.] xmalloc
          *              |
-         *              --- schedule
-         *                  run_command
+         *              --- xmalloc
+         *                  malloc
+         *                  xmalloc     <--- NOTE: there's a cycle
+         *                  malloc
+         *                  xmalloc
          *                  main
          *
          *   10.00%     0.00%     perf  [kernel]       [k] sys_perf_event_open
@@ -556,6 +559,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  run_command
          *                  main
          *
+         *   10.00%    10.00%     perf  [kernel]       [k] schedule
+         *              |
+         *              --- schedule
+         *                  run_command
+         *                  main
+         *
          *   10.00%    10.00%     perf  libc           [.] free
          *              |
          *              --- free
@@ -570,15 +579,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
          *                  run_command
          *                  main
          *
-         *   10.00%    10.00%     bash  bash           [.] xmalloc
-         *              |
-         *              --- xmalloc
-         *                  malloc
-         *                  xmalloc     <--- NOTE: there's a cycle
-         *                  malloc
-         *                  xmalloc
-         *                  main
-         *
          */
         struct result expected[] = {
                 { 7000, 2000, "perf", "perf",     "main" },
@@ -587,12 +587,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 { 3000, 1000, "perf", "perf",     "cmd_record" },
                 { 2000,    0, "bash", "libc",     "malloc" },
                 { 1000, 1000, "bash", "[kernel]", "page_fault" },
-                { 1000, 1000, "perf", "[kernel]", "schedule" },
+                { 1000, 1000, "bash", "bash",     "xmalloc" },
                 { 1000,    0, "perf", "[kernel]", "sys_perf_event_open" },
                 { 1000, 1000, "perf", "[kernel]", "page_fault" },
+                { 1000, 1000, "perf", "[kernel]", "schedule" },
                 { 1000, 1000, "perf", "libc",     "free" },
                 { 1000, 1000, "perf", "libc",     "malloc" },
-                { 1000, 1000, "bash", "bash",     "xmalloc" },
         };
         struct callchain_result expected_callchain[] = {
                 {
@@ -622,9 +622,12 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "bash",     "main" }, },
                 },
                 {
-                        3, {    { "[kernel]", "schedule" },
-                                { "perf",     "run_command" },
-                                { "perf",     "main" }, },
+                        6, {    { "bash",     "xmalloc" },
+                                { "libc",     "malloc" },
+                                { "bash",     "xmalloc" },
+                                { "libc",     "malloc" },
+                                { "bash",     "xmalloc" },
+                                { "bash",     "main" }, },
                 },
                 {
                         3, {    { "[kernel]", "sys_perf_event_open" },
@@ -638,6 +641,11 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "perf",     "main" }, },
                 },
                 {
+                        3, {    { "[kernel]", "schedule" },
+                                { "perf",     "run_command" },
+                                { "perf",     "main" }, },
+                },
+                {
                         4, {    { "libc",     "free" },
                                 { "perf",     "cmd_record" },
                                 { "perf",     "run_command" },
@@ -649,14 +657,6 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                                 { "perf",     "run_command" },
                                 { "perf",     "main" }, },
                 },
-                {
-                        6, {    { "bash",     "xmalloc" },
-                                { "libc",     "malloc" },
-                                { "bash",     "xmalloc" },
-                                { "libc",     "malloc" },
-                                { "bash",     "xmalloc" },
-                                { "bash",     "main" }, },
-                },
         };
 
         symbol_conf.use_callchain = true;
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 74f257a81265..59e53db7914c 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -138,7 +138,7 @@ int test__hists_filter(void)
                 struct hists *hists = evsel__hists(evsel);
 
                 hists__collapse_resort(hists, NULL);
-                hists__output_resort(hists);
+                hists__output_resort(hists, 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 a748f2be1222..f5547610da02 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -152,7 +152,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -252,7 +252,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -306,7 +306,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -384,7 +384,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
@@ -487,7 +487,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine)
                 goto out;
 
         hists__collapse_resort(hists, NULL);
-        hists__output_resort(hists);
+        hists__output_resort(hists, NULL);
 
         if (verbose > 2) {
                 pr_info("[fields = %s, sort = %s]\n", field_order, sort_order);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index e6bb04b5b09b..788506eef567 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -550,7 +550,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
         bool need_percent;
 
         node = rb_first(root);
-        need_percent = !!rb_next(node);
+        need_percent = node && rb_next(node);
 
         while (node) {
                 struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index dc0d095f318c..482adae3cc44 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -204,6 +204,9 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
                 if (ret)
                         return ret;
 
+                if (a->thread != b->thread || !symbol_conf.use_callchain)
+                        return 0;
+
                 ret = b->callchain->max_depth - a->callchain->max_depth;
         }
         return ret;
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 2f612562978c..3c38f25b1695 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,5 +1,8 @@
 #include <signal.h>
 #include <stdbool.h>
+#ifdef HAVE_BACKTRACE_SUPPORT
+#include <execinfo.h>
+#endif
 
 #include "../../util/cache.h"
 #include "../../util/debug.h"
@@ -88,6 +91,25 @@ int ui__getch(int delay_secs)
         return SLkp_getkey();
 }
 
+#ifdef HAVE_BACKTRACE_SUPPORT
+static void ui__signal_backtrace(int sig)
+{
+        void *stackdump[32];
+        size_t size;
+
+        ui__exit(false);
+        psignal(sig, "perf");
+
+        printf("-------- backtrace --------\n");
+        size = backtrace(stackdump, ARRAY_SIZE(stackdump));
+        backtrace_symbols_fd(stackdump, size, STDOUT_FILENO);
+
+        exit(0);
+}
+#else
+# define ui__signal_backtrace  ui__signal
+#endif
+
 static void ui__signal(int sig)
 {
         ui__exit(false);
@@ -122,8 +144,8 @@ int ui__init(void)
         ui_browser__init();
         tui_progress__init();
 
-        signal(SIGSEGV, ui__signal);
-        signal(SIGFPE, ui__signal);
+        signal(SIGSEGV, ui__signal_backtrace);
+        signal(SIGFPE, ui__signal_backtrace);
         signal(SIGINT, ui__signal);
         signal(SIGQUIT, ui__signal);
         signal(SIGTERM, ui__signal);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 79999ceaf2be..01bc4e23a2cf 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -177,14 +177,17 @@ static int lock__parse(struct ins_operands *ops)
                 goto out_free_ops;
 
         ops->locked.ins = ins__find(name);
+        free(name);
+
         if (ops->locked.ins == NULL)
                 goto out_free_ops;
 
         if (!ops->locked.ins->ops)
                 return 0;
 
-        if (ops->locked.ins->ops->parse)
-                ops->locked.ins->ops->parse(ops->locked.ops);
+        if (ops->locked.ins->ops->parse &&
+            ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+                goto out_free_ops;
 
         return 0;
 
@@ -208,6 +211,13 @@ static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void lock__delete(struct ins_operands *ops)
 {
+        struct ins *ins = ops->locked.ins;
+
+        if (ins && ins->ops->free)
+                ins->ops->free(ops->locked.ops);
+        else
+                ins__delete(ops->locked.ops);
+
         zfree(&ops->locked.ops);
         zfree(&ops->target.raw);
         zfree(&ops->target.name);
@@ -531,8 +541,8 @@ static void disasm_line__init_ins(struct disasm_line *dl)
         if (!dl->ins->ops)
                 return;
 
-        if (dl->ins->ops->parse)
-                dl->ins->ops->parse(&dl->ops);
+        if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+                dl->ins = NULL;
 }
 
 static int disasm_line__parse(char *line, char **namep, char **rawp)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 0784a9420528..cadbdc90a5cb 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -116,11 +116,6 @@ struct annotation {
         struct annotated_source *src;
 };
 
-struct sannotation {
-        struct annotation annotation;
-        struct symbol     symbol;
-};
-
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
 {
         return (((void *)&notes->src->histograms) +
@@ -129,8 +124,7 @@ static inline struct sym_hist *annotation__histogram(struct annotation *notes, i
 
 static inline struct annotation *symbol__annotation(struct symbol *sym)
 {
-        struct sannotation *a = container_of(sym, struct sannotation, symbol);
-        return &a->annotation;
+        return (void *)sym - symbol_conf.priv_size;
 }
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 5cf9e1b5989d..d04d770d90f6 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -71,7 +71,9 @@ extern char *perf_path(const char *fmt, ...) __attribute__((format (printf, 1, 2
 extern char *perf_pathdup(const char *fmt, ...)
         __attribute__((format (printf, 1, 2)));
 
+#ifndef __UCLIBC__
 /* Matches the libc/libbsd function attribute so we declare this unconditionally: */
 extern size_t strlcpy(char *dest, const char *src, size_t size);
+#endif
 
 #endif /* __PERF_CACHE_H */
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 64b377e591e4..14e7a123d43b 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -841,3 +841,33 @@ char *callchain_list__sym_name(struct callchain_list *cl,
 
         return bf;
 }
+
+static void free_callchain_node(struct callchain_node *node)
+{
+        struct callchain_list *list, *tmp;
+        struct callchain_node *child;
+        struct rb_node *n;
+
+        list_for_each_entry_safe(list, tmp, &node->val, list) {
+                list_del(&list->list);
+                free(list);
+        }
+
+        n = rb_first(&node->rb_root_in);
+        while (n) {
+                child = container_of(n, struct callchain_node, rb_node_in);
+                n = rb_next(n);
+                rb_erase(&child->rb_node_in, &node->rb_root_in);
+
+                free_callchain_node(child);
+                free(child);
+        }
+}
+
+void free_callchain(struct callchain_root *root)
+{
+        if (!symbol_conf.use_callchain)
+                return;
+
+        free_callchain_node(&root->node);
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index dbc08cf5f970..c0ec1acc38e4 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -198,4 +198,6 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 char *callchain_list__sym_name(struct callchain_list *cl,
                                char *bf, size_t bfsize, bool show_dso);
 
+void free_callchain(struct callchain_root *root);
+
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index cbab1fb77b1d..2e507b5025a3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1445,7 +1445,7 @@ int perf_evlist__strerror_tp(struct perf_evlist *evlist __maybe_unused,
         case ENOENT:
                 scnprintf(buf, size, "%s",
                           "Error:\tUnable to find debugfs\n"
-                          "Hint:\tWas your kernel was compiled with debugfs support?\n"
+                          "Hint:\tWas your kernel compiled with debugfs support?\n"
                           "Hint:\tIs the debugfs filesystem mounted?\n"
                           "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'");
                 break;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6e88b9e395df..182395546ddc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
+#include "ui/progress.h"
 #include <math.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -303,7 +304,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
         size_t callchain_size = 0;
         struct hist_entry *he;
 
-        if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain)
+        if (symbol_conf.use_callchain)
                 callchain_size = sizeof(struct callchain_root);
 
         he = zalloc(sizeof(*he) + callchain_size);
@@ -736,7 +737,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter,
         iter->he = he;
         he_cache[iter->curr++] = he;
 
-        callchain_append(he->callchain, &callchain_cursor, sample->period);
+        hist_entry__append_callchain(he, sample);
 
         /*
          * We need to re-initialize the cursor since callchain_append()
@@ -809,7 +810,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter,
         iter->he = he;
         he_cache[iter->curr++] = he;
 
-        callchain_append(he->callchain, &cursor, sample->period);
+        if (symbol_conf.use_callchain)
+                callchain_append(he->callchain, &cursor, sample->period);
         return 0;
 }
 
@@ -945,6 +947,7 @@ void hist_entry__free(struct hist_entry *he)
         zfree(&he->mem_info);
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
+        free_callchain(he->callchain);
         free(he);
 }
 
@@ -987,6 +990,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused,
                 else
                         p = &(*p)->rb_right;
         }
+        hists->nr_entries++;
 
         rb_link_node(&he->rb_node_in, parent, p);
         rb_insert_color(&he->rb_node_in, root);
@@ -1024,7 +1028,10 @@ void hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
         if (!sort__need_collapse)
                 return;
 
+        hists->nr_entries = 0;
+
         root = hists__get_rotate_entries_in(hists);
+
         next = rb_first(root);
 
         while (next) {
@@ -1119,7 +1126,7 @@ static void __hists__insert_output_entry(struct rb_root *entries,
         rb_insert_color(&he->rb_node, entries);
 }
 
-void hists__output_resort(struct hists *hists)
+void hists__output_resort(struct hists *hists, struct ui_progress *prog)
 {
         struct rb_root *root;
         struct rb_node *next;
@@ -1148,6 +1155,9 @@ void hists__output_resort(struct hists *hists)
 
                 if (!n->filtered)
                         hists__calc_col_len(hists, n);
+
+                if (prog)
+                        ui_progress__update(prog, 1);
         }
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d0ef9a19a744..46bd50344f85 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -121,7 +121,7 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
                               struct hists *hists);
 void hist_entry__free(struct hist_entry *);
 
-void hists__output_resort(struct hists *hists);
+void hists__output_resort(struct hists *hists, struct ui_progress *prog);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
diff --git a/tools/perf/util/hweight.c b/tools/perf/util/hweight.c
deleted file mode 100644
index 5c1d0d099f0d..000000000000
--- a/tools/perf/util/hweight.c
+++ /dev/null
@@ -1,31 +0,0 @@
-#include <linux/bitops.h>
-
-/**
- * hweightN - returns the hamming weight of a N-bit word
- * @x: the word to weigh
- *
- * The Hamming Weight of a number is the total number of bits set in it.
- */
-
-unsigned int hweight32(unsigned int w)
-{
-        unsigned int res = w - ((w >> 1) & 0x55555555);
-        res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
-        res = (res + (res >> 4)) & 0x0F0F0F0F;
-        res = res + (res >> 8);
-        return (res + (res >> 16)) & 0x000000FF;
-}
-
-unsigned long hweight64(__u64 w)
-{
-#if BITS_PER_LONG == 32
-        return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
-#elif BITS_PER_LONG == 64
-        __u64 res = w - ((w >> 1) & 0x5555555555555555ul);
-        res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
-        res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
-        res = res + (res >> 8);
-        res = res + (res >> 16);
-        return (res + (res >> 32)) & 0x00000000000000FFul;
-#endif
-}
diff --git a/tools/perf/util/include/asm/hweight.h b/tools/perf/util/include/asm/hweight.h
deleted file mode 100644
index 36cf26d434a5..000000000000
--- a/tools/perf/util/include/asm/hweight.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef PERF_HWEIGHT_H
-#define PERF_HWEIGHT_H
-
-#include <linux/types.h>
-unsigned int hweight32(unsigned int w);
-unsigned long hweight64(__u64 w);
-
-#endif /* PERF_HWEIGHT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 94de3e48b490..1bca3a9f2b16 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -389,7 +389,6 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
         if (th != NULL) {
                 rb_link_node(&th->rb_node, parent, p);
                 rb_insert_color(&th->rb_node, &machine->threads);
-                machine->last_match = th;
 
                 /*
                  * We have to initialize map_groups separately
@@ -400,9 +399,12 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
                  * leader and that would screwed the rb tree.
                  */
                 if (thread__init_map_groups(th, machine)) {
+                        rb_erase(&th->rb_node, &machine->threads);
                         thread__delete(th);
                         return NULL;
                 }
+
+                machine->last_match = th;
         }
 
         return th;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 6951a9d42339..0e42438b1e59 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -116,6 +116,22 @@ struct thread;
 #define map__for_each_symbol(map, pos, n)       \
         dso__for_each_symbol(map->dso, pos, n, map->type)
 
+/* map__for_each_symbol_with_name - iterate over the symbols in the given map
+ *                                  that have the given name
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @sym_name: the symbol name
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @filter: to use when loading the DSO
+ */
+#define __map__for_each_symbol_by_name(map, sym_name, pos, filter)      \
+        for (pos = map__find_symbol_by_name(map, sym_name, filter);     \
+             pos && strcmp(pos->name, sym_name) == 0;           \
+             pos = symbol__next_by_name(pos))
+
+#define map__for_each_symbol_by_name(map, sym_name, pos)                \
+        __map__for_each_symbol_by_name(map, sym_name, (pos), NULL)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 28eb1417cb2a..919937eb0be2 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -446,7 +446,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
         }
 
         for (i = 0; i < ntevs; i++) {
-                if (tevs[i].point.address) {
+                if (tevs[i].point.address && !tevs[i].point.retprobe) {
                         tmp = strdup(reloc_sym->name);
                         if (!tmp)
                                 return -ENOMEM;
@@ -495,9 +495,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
         }
 
         if (ntevs == 0) {       /* No error but failed to find probe point. */
-                pr_warning("Probe point '%s' not found.\n",
+                pr_warning("Probe point '%s' not found in debuginfo.\n",
                            synthesize_perf_probe_point(&pev->point));
-                return -ENOENT;
+                if (need_dwarf)
+                        return -ENOENT;
+                return 0;
         }
         /* Error path : ntevs < 0 */
         pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
@@ -2050,9 +2052,11 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
         pr_debug("Writing event: %s\n", buf);
         if (!probe_event_dry_run) {
                 ret = write(fd, buf, strlen(buf));
-                if (ret <= 0)
+                if (ret <= 0) {
+                        ret = -errno;
                         pr_warning("Failed to write event: %s\n",
                                    strerror_r(errno, sbuf, sizeof(sbuf)));
+                }
         }
         free(buf);
         return ret;
@@ -2189,18 +2193,17 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
         return ret;
 }
 
-static char *looking_function_name;
-static int num_matched_functions;
-
-static int probe_function_filter(struct map *map __maybe_unused,
-                                      struct symbol *sym)
+static int find_probe_functions(struct map *map, char *name)
 {
-        if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
-            strcmp(looking_function_name, sym->name) == 0) {
-                num_matched_functions++;
-                return 0;
+        int found = 0;
+        struct symbol *sym;
+
+        map__for_each_symbol_by_name(map, name, sym) {
+                if (sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL)
+                        found++;
         }
-        return 1;
+
+        return found;
 }
 
 #define strdup_or_goto(str, label)      \
@@ -2218,10 +2221,10 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
         struct kmap *kmap = NULL;
         struct ref_reloc_sym *reloc_sym = NULL;
         struct symbol *sym;
-        struct rb_node *nd;
         struct probe_trace_event *tev;
         struct perf_probe_point *pp = &pev->point;
         struct probe_trace_point *tp;
+        int num_matched_functions;
         int ret, i;
 
         /* Init maps of given executable or kernel */
@@ -2238,10 +2241,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
          * Load matched symbols: Since the different local symbols may have
          * same name but different addresses, this lists all the symbols.
          */
-        num_matched_functions = 0;
-        looking_function_name = pp->function;
-        ret = map__load(map, probe_function_filter);
-        if (ret || num_matched_functions == 0) {
+        num_matched_functions = find_probe_functions(map, pp->function);
+        if (num_matched_functions == 0) {
                 pr_err("Failed to find symbol %s in %s\n", pp->function,
                         target ? : "kernel");
                 ret = -ENOENT;
@@ -2253,7 +2254,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
                 goto out;
         }
 
-        if (!pev->uprobes) {
+        if (!pev->uprobes && !pp->retprobe) {
                 kmap = map__kmap(map);
                 reloc_sym = kmap->ref_reloc_sym;
                 if (!reloc_sym) {
@@ -2271,7 +2272,8 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
         }
 
         ret = 0;
-        map__for_each_symbol(map, sym, nd) {
+
+        map__for_each_symbol_by_name(map, pp->function, sym) {
                 tev = (*tevs) + ret;
                 tp = &tev->point;
                 if (ret == num_matched_functions) {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index c7918f83b300..b5247d777f0e 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -989,8 +989,24 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
         int ret = 0;
 
 #if _ELFUTILS_PREREQ(0, 142)
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        GElf_Shdr shdr;
+
         /* Get the call frame information from this dwarf */
-        pf->cfi = dwarf_getcfi_elf(dwarf_getelf(dbg->dbg));
+        elf = dwarf_getelf(dbg->dbg);
+        if (elf == NULL)
+                return -EINVAL;
+
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                return -EINVAL;
+
+        if (elf_section_by_name(elf, &ehdr, &shdr, ".eh_frame", NULL) &&
+            shdr.sh_type == SHT_PROGBITS) {
+                pf->cfi = dwarf_getcfi_elf(elf);
+        } else {
+                pf->cfi = dwarf_getcfi(dbg->dbg);
+        }
 #endif
 
         off = 0;
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 16a475a7d492..6c6a6953fa93 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-util/hweight.c
+../../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index c24c5b83156c..a194702a0a2f 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -396,6 +396,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
                                             const char *name)
 {
         struct rb_node *n;
+        struct symbol_name_rb_node *s;
 
         if (symbols == NULL)
                 return NULL;
@@ -403,7 +404,6 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
         n = symbols->rb_node;
 
         while (n) {
-                struct symbol_name_rb_node *s;
                 int cmp;
 
                 s = rb_entry(n, struct symbol_name_rb_node, rb_node);
@@ -414,10 +414,24 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
                 else if (cmp > 0)
                         n = n->rb_right;
                 else
-                        return &s->sym;
+                        break;
         }
 
-        return NULL;
+        if (n == NULL)
+                return NULL;
+
+        /* return first symbol that has same name (if any) */
+        for (n = rb_prev(n); n; n = rb_prev(n)) {
+                struct symbol_name_rb_node *tmp;
+
+                tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
+                if (strcmp(tmp->sym.name, s->sym.name))
+                        break;
+
+                s = tmp;
+        }
+
+        return &s->sym;
 }
 
 struct symbol *dso__find_symbol(struct dso *dso,
@@ -436,6 +450,17 @@ struct symbol *dso__next_symbol(struct symbol *sym)
         return symbols__next(sym);
 }
 
+struct symbol *symbol__next_by_name(struct symbol *sym)
+{
+        struct symbol_name_rb_node *s = container_of(sym, struct symbol_name_rb_node, sym);
+        struct rb_node *n = rb_next(&s->rb_node);
+
+        return n ? &rb_entry(n, struct symbol_name_rb_node, rb_node)->sym : NULL;
+}
+
+ /*
+  * Teturns first symbol that matched with @name.
+  */
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name)
 {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9d602e9c6f59..1650dcb3a67b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -231,6 +231,7 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
                                 u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
                                         const char *name);
+struct symbol *symbol__next_by_name(struct symbol *sym);
 
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 struct symbol *dso__next_symbol(struct symbol *sym);
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 371219a6daf1..6edf535f65c2 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -185,6 +185,28 @@ static u64 elf_section_offset(int fd, const char *name)
         return offset;
 }
 
+#ifndef NO_LIBUNWIND_DEBUG_FRAME
+static int elf_is_exec(int fd, const char *name)
+{
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        int retval = 0;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return 0;
+        if (gelf_getehdr(elf, &ehdr) == NULL)
+                goto out;
+
+        retval = (ehdr.e_type == ET_EXEC);
+
+out:
+        elf_end(elf);
+        pr_debug("unwind: elf_is_exec(%s): %d\n", name, retval);
+        return retval;
+}
+#endif
+
 struct table_entry {
         u32 start_ip_offset;
         u32 fde_offset;
@@ -322,8 +344,12 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
         /* Check the .debug_frame section for unwinding info */
         if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
+                int fd = dso__data_fd(map->dso, ui->machine);
+                int is_exec = elf_is_exec(fd, map->dso->name);
+                unw_word_t base = is_exec ? 0 : map->start;
+
                 memset(&di, 0, sizeof(di));
-                if (dwarf_find_debug_frame(0, &di, ip, 0, map->dso->name,
+                if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
                                            map->start, map->end))
                         return dwarf_search_unwind_table(as, ip, &di, pi,
                                                          need_unwind_info, arg);
diff --git a/tools/power/cpupower/utils/cpupower.c b/tools/power/cpupower/utils/cpupower.c
index 7cdcf88659c7..9ea914378985 100644
--- a/tools/power/cpupower/utils/cpupower.c
+++ b/tools/power/cpupower/utils/cpupower.c
@@ -199,7 +199,7 @@ int main(int argc, const char *argv[])
         }
 
         get_cpu_info(0, &cpupower_cpu_info);
-        run_as_root = !getuid();
+        run_as_root = !geteuid();
         if (run_as_root) {
                 ret = uname(&uts);
                 if (!ret && !strcmp(uts.machine, "x86_64") &&
diff --git a/tools/power/cpupower/utils/helpers/sysfs.c b/tools/power/cpupower/utils/helpers/sysfs.c
index 09afe5d87f2b..4e8fe2c7b054 100644
--- a/tools/power/cpupower/utils/helpers/sysfs.c
+++ b/tools/power/cpupower/utils/helpers/sysfs.c
@@ -361,7 +361,7 @@ unsigned int sysfs_get_idlestate_count(unsigned int cpu)
 
         snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpuidle");
         if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode))
-                return -ENODEV;
+                return 0;
 
         snprintf(file, SYSFS_PATH_MAX, PATH_TO_CPU "cpu%u/cpuidle/state0", cpu);
         if (stat(file, &statbuf) != 0 || !S_ISDIR(statbuf.st_mode))
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index 33a5c06d95ca..e238c9559caf 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -62,7 +62,7 @@ static int _check_execveat_fail(int fd, const char *path, int flags,
 }
 
 static int check_execveat_invoked_rc(int fd, const char *path, int flags,
-                                     int expected_rc)
+                                     int expected_rc, int expected_rc2)
 {
         int status;
         int rc;
@@ -98,9 +98,10 @@ static int check_execveat_invoked_rc(int fd, const char *path, int flags,
                         child, status);
                 return 1;
         }
-        if (WEXITSTATUS(status) != expected_rc) {
-                printf("[FAIL] (child %d exited with %d not %d)\n",
-                        child, WEXITSTATUS(status), expected_rc);
+        if ((WEXITSTATUS(status) != expected_rc) &&
+            (WEXITSTATUS(status) != expected_rc2)) {
+                printf("[FAIL] (child %d exited with %d not %d nor %d)\n",
+                        child, WEXITSTATUS(status), expected_rc, expected_rc2);
                 return 1;
         }
         printf("[OK]\n");
@@ -109,7 +110,7 @@ static int check_execveat_invoked_rc(int fd, const char *path, int flags,
 
 static int check_execveat(int fd, const char *path, int flags)
 {
-        return check_execveat_invoked_rc(fd, path, flags, 99);
+        return check_execveat_invoked_rc(fd, path, flags, 99, 99);
 }
 
 static char *concat(const char *left, const char *right)
@@ -179,11 +180,11 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
          */
         fd = open(longpath, O_RDONLY);
         if (fd > 0) {
-                printf("Invoke copy of '%s' via filename of length %lu:\n",
+                printf("Invoke copy of '%s' via filename of length %zu:\n",
                         src, strlen(longpath));
                 fail += check_execveat(fd, "", AT_EMPTY_PATH);
         } else {
-                printf("Failed to open length %lu filename, errno=%d (%s)\n",
+                printf("Failed to open length %zu filename, errno=%d (%s)\n",
                         strlen(longpath), errno, strerror(errno));
                 fail++;
         }
@@ -192,9 +193,15 @@ static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
          * Execute as a long pathname relative to ".".  If this is a script,
          * the interpreter will launch but fail to open the script because its
          * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX.
+         *
+         * The failure code is usually 127 (POSIX: "If a command is not found,
+         * the exit status shall be 127."), but some systems give 126 (POSIX:
+         * "If the command name is found, but it is not an executable utility,
+         * the exit status shall be 126."), so allow either.
          */
         if (is_script)
-                fail += check_execveat_invoked_rc(dot_dfd, longpath, 0, 127);
+                fail += check_execveat_invoked_rc(dot_dfd, longpath, 0,
+                                                  127, 126);
         else
                 fail += check_execveat(dot_dfd, longpath, 0);
 
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index 94dae65eea41..8519e9ee97e3 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -536,10 +536,9 @@ int main(int argc, char *argv[])
 {
         struct mq_attr attr;
         char *option, *next_option;
-        int i, cpu;
+        int i, cpu, rc;
         struct sigaction sa;
         poptContext popt_context;
-        char rc;
         void *retval;
 
         main_thread = pthread_self();
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 4c4b1f631ecf..077828c889f1 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -7,7 +7,7 @@ BINARIES += transhuge-stress
 
 all: $(BINARIES)
 %: %.c
-        $(CC) $(CFLAGS) -o $@ $^
+        $(CC) $(CFLAGS) -o $@ $^ -lrt
 
 run_tests: all
         @/bin/sh ./run_vmtests || (echo "vmtests: [FAIL]"; exit 1)