Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Mostly tooling fixes, but also some kernel side fixes: uncore PMU
  driver fix, user regs sampling fix and an instruction decoder fix that
  unbreaks PEBS precise sampling"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/uncore/hsw-ep: Handle systems with only two SBOXes
  perf/x86_64: Improve user regs sampling
  perf: Move task_pt_regs sampling into arch code
  x86: Fix off-by-one in instruction decoder
  perf hists browser: Fix segfault when showing callchain
  perf callchain: Free callchains when hist entries are deleted
  perf hists: Fix children sort key behavior
  perf diff: Fix to sort by baseline field by default
  perf list: Fix --raw-dump option
  perf probe: Fix crash in dwarf_getcfi_elf
  perf probe: Fix to fall back to find probe point in symbols
  perf callchain: Append callchains only when requested
  perf ui/tui: Print backtrace symbols when segfault occurs
  perf report: Show progress bar for output resorting

26 files changed, 371 insertions, 77 deletions

diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 6e4379c67cbc..592dda3f21ff 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -28,3 +28,11 @@ u64 perf_reg_abi(struct task_struct *task)
 {
         return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                        struct pt_regs *regs,
+                        struct pt_regs *regs_user_copy)
+{
+        regs_user->regs = task_pt_regs(current);
+        regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 6762ad705587..3f62b35fb6f1 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -50,3 +50,11 @@ u64 perf_reg_abi(struct task_struct *task)
         else
                 return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                        struct pt_regs *regs,
+                        struct pt_regs *regs_user_copy)
+{
+        regs_user->regs = task_pt_regs(current);
+        regs_user->abi = perf_reg_abi(current);
+}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 18eb78bbdd10..863d9b02563e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)       ((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)        (data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV            0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX        2
+#define UNCORE_EXTRA_PCI_DEV_MAX        3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX               8
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 745b158e9a65..21af6149edf2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -891,6 +891,7 @@ void snbep_uncore_cpu_init(void)
 enum {
         SNBEP_PCI_QPI_PORT0_FILTER,
         SNBEP_PCI_QPI_PORT1_FILTER,
+        HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2026,6 +2027,17 @@ void hswep_uncore_cpu_init(void)
 {
         if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
                 hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+        /* Detect 6-8 core systems with only two SBOXes */
+        if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+                u32 capid4;
+
+                pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+                                      0x94, &capid4);
+                if (((capid4 >> 6) & 0x3) == 0)
+                        hswep_uncore_sbox.num_boxes = 2;
+        }
+
         uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2287,6 +2299,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
                 .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
                                                    SNBEP_PCI_QPI_PORT1_FILTER),
         },
+        { /* PCU.3 (for Capability registers) */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+                .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+                                                   HSWEP_PCI_PCU_3),
+        },
         { /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..781861cc5ee8 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
         return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                        struct pt_regs *regs,
+                        struct pt_regs *regs_user_copy)
+{
+        regs_user->regs = task_pt_regs(current);
+        regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
                        (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task)
         else
                 return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+                        struct pt_regs *regs,
+                        struct pt_regs *regs_user_copy)
+{
+        struct pt_regs *user_regs = task_pt_regs(current);
+
+        /*
+         * If we're in an NMI that interrupted task_pt_regs setup, then
+         * we can't sample user regs at all.  This check isn't really
+         * sufficient, though, as we could be in an NMI inside an interrupt
+         * that happened during task_pt_regs setup.
+         */
+        if (regs->sp > (unsigned long)&user_regs->r11 &&
+            regs->sp <= (unsigned long)(user_regs + 1)) {
+                regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+                regs_user->regs = NULL;
+                return;
+        }
+
+        /*
+         * RIP, flags, and the argument registers are usually saved.
+         * orig_ax is probably okay, too.
+         */
+        regs_user_copy->ip = user_regs->ip;
+        regs_user_copy->cx = user_regs->cx;
+        regs_user_copy->dx = user_regs->dx;
+        regs_user_copy->si = user_regs->si;
+        regs_user_copy->di = user_regs->di;
+        regs_user_copy->r8 = user_regs->r8;
+        regs_user_copy->r9 = user_regs->r9;
+        regs_user_copy->r10 = user_regs->r10;
+        regs_user_copy->r11 = user_regs->r11;
+        regs_user_copy->orig_ax = user_regs->orig_ax;
+        regs_user_copy->flags = user_regs->flags;
+
+        /*
+         * Don't even try to report the "rest" regs.
+         */
+        regs_user_copy->bx = -1;
+        regs_user_copy->bp = -1;
+        regs_user_copy->r12 = -1;
+        regs_user_copy->r13 = -1;
+        regs_user_copy->r14 = -1;
+        regs_user_copy->r15 = -1;
+
+        /*
+         * For this to be at all useful, we need a reasonable guess for
+         * sp and the ABI.  Be careful: we're in NMI context, and we're
+         * considering current to be the current task, so we should
+         * be careful not to look at any other percpu variables that might
+         * change during context switches.
+         */
+        if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+            task_thread_info(current)->status & TS_COMPAT) {
+                /* Easy case: we're in a compat syscall. */
+                regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
+                regs_user_copy->sp = user_regs->sp;
+                regs_user_copy->cs = user_regs->cs;
+                regs_user_copy->ss = user_regs->ss;
+        } else if (user_regs->orig_ax != -1) {
+                /*
+                 * We're probably in a 64-bit syscall.
+                 * Warning: this code is severely racy.  At least it's better
+                 * than just blindly copying user_regs.
+                 */
+                regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
+                regs_user_copy->sp = this_cpu_read(old_rsp);
+                regs_user_copy->cs = __USER_CS;
+                regs_user_copy->ss = __USER_DS;
+                regs_user_copy->cx = -1;  /* usually contains garbage */
+        } else {
+                /* We're probably in an interrupt or exception. */
+                regs_user->abi = user_64bit_mode(user_regs) ?
+                        PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
+                regs_user_copy->sp = user_regs->sp;
+                regs_user_copy->cs = user_regs->cs;
+                regs_user_copy->ss = user_regs->ss;
+        }
+
+        regs_user->regs = regs_user_copy;
+}
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 2480978b31cc..1313ae6b478b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -28,7 +28,7 @@
 
 /* Verify next sizeof(t) bytes can be on the same instruction */
 #define validate_next(t, insn, n)       \
-        ((insn)->next_byte + sizeof(t) + n < (insn)->end_kaddr)
+        ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
 
 #define __get_next(t, insn)     \
         ({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 486e84ccb1f9..4f7a61ca4b39 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,11 +79,6 @@ struct perf_branch_stack {
         struct perf_branch_entry        entries[0];
 };
 
-struct perf_regs {
-        __u64           abi;
-        struct pt_regs  *regs;
-};
-
 struct task_struct;
 
 /*
@@ -610,7 +605,14 @@ struct perf_sample_data {
                 u32     reserved;
         }                               cpu_entry;
         struct perf_callchain_entry     *callchain;
+
+        /*
+         * regs_user may point to task_pt_regs or to regs_user_copy, depending
+         * on arch details.
+         */
         struct perf_regs                regs_user;
+        struct pt_regs                  regs_user_copy;
+
         struct perf_regs                regs_intr;
         u64                             stack_user_size;
 } ____cacheline_aligned;
diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h
index 3c73d5fe18be..a5f98d53d732 100644
--- a/include/linux/perf_regs.h
+++ b/include/linux/perf_regs.h
@@ -1,11 +1,19 @@
 #ifndef _LINUX_PERF_REGS_H
 #define _LINUX_PERF_REGS_H
 
+struct perf_regs {
+        __u64           abi;
+        struct pt_regs  *regs;
+};
+
 #ifdef CONFIG_HAVE_PERF_REGS
 #include <asm/perf_regs.h>
 u64 perf_reg_value(struct pt_regs *regs, int idx);
 int perf_reg_validate(u64 mask);
 u64 perf_reg_abi(struct task_struct *task);
+void perf_get_regs_user(struct perf_regs *regs_user,
+                        struct pt_regs *regs,
+                        struct pt_regs *regs_user_copy);
 #else
 static inline u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
@@ -21,5 +29,13 @@ static inline u64 perf_reg_abi(struct task_struct *task)
 {
         return PERF_SAMPLE_REGS_ABI_NONE;
 }
+
+static inline void perf_get_regs_user(struct perf_regs *regs_user,
+                                      struct pt_regs *regs,
+                                      struct pt_regs *regs_user_copy)
+{
+        regs_user->regs = task_pt_regs(current);
+        regs_user->abi = perf_reg_abi(current);
+}
 #endif /* CONFIG_HAVE_PERF_REGS */
 #endif /* _LINUX_PERF_REGS_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4c1ee7f2bebc..882f835a0d85 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4461,18 +4461,14 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 }
 
 static void perf_sample_regs_user(struct perf_regs *regs_user,
-                                  struct pt_regs *regs)
+                                  struct pt_regs *regs,
+                                  struct pt_regs *regs_user_copy)
 {
-        if (!user_mode(regs)) {
-                if (current->mm)
-                        regs = task_pt_regs(current);
-                else
-                        regs = NULL;
-        }
-
-        if (regs) {
-                regs_user->abi  = perf_reg_abi(current);
+        if (user_mode(regs)) {
+                regs_user->abi = perf_reg_abi(current);
                 regs_user->regs = regs;
+        } else if (current->mm) {
+                perf_get_regs_user(regs_user, regs, regs_user_copy);
         } else {
                 regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
                 regs_user->regs = NULL;
@@ -4951,7 +4947,8 @@ void perf_prepare_sample(struct perf_event_header *header,
         }
 
         if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
-                perf_sample_regs_user(&data->regs_user, regs);
+                perf_sample_regs_user(&data->regs_user, regs,
+                                      &data->regs_user_copy);
 
         if (sample_type & PERF_SAMPLE_REGS_USER) {
                 /* regs dump ABI info */
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..961cea183a83 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -285,7 +285,7 @@ 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 +554,7 @@ 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/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/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/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/probe-event.c b/tools/perf/util/probe-event.c
index 28eb1417cb2a..7f9b8632e433 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -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);
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;