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

Pull perf tooling updates from Ingo Molnar:
 "Perf tooling updates and fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf annotate browser: Help for cycling thru hottest instructions with TAB/shift+TAB
  perf stat: Only auto-merge events that are PMU aliases
  perf test: Add test case for PERF_SAMPLE_PHYS_ADDR
  perf script: Support physical address
  perf mem: Support physical address
  perf sort: Add sort option for physical address
  perf tools: Support new sample type for physical address
  perf vendor events powerpc: Remove duplicate events
  perf intel-pt: Fix syntax in documentation of config option
  perf test powerpc: Fix 'Object code reading' test
  perf trace: Support syscall name globbing
  perf syscalltbl: Support glob matching on syscall names
  perf report: Calculate the average cycles of iterations

37 files changed, 368 insertions, 268 deletions

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 2a37ae925d85..140ae638cfd6 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -139,8 +139,9 @@ enum perf_event_sample_format {
         PERF_SAMPLE_IDENTIFIER                  = 1U << 16,
         PERF_SAMPLE_TRANSACTION                 = 1U << 17,
         PERF_SAMPLE_REGS_INTR                   = 1U << 18,
+        PERF_SAMPLE_PHYS_ADDR                   = 1U << 19,
 
-        PERF_SAMPLE_MAX = 1U << 19,             /* non-ABI */
+        PERF_SAMPLE_MAX = 1U << 20,             /* non-ABI */
 };
 
 /*
@@ -814,6 +815,7 @@ enum perf_event_type {
          *      { u64                   transaction; } && PERF_SAMPLE_TRANSACTION
          *      { u64                   abi; # enum perf_sample_regs_abi
          *        u64                   regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
+         *      { u64                   phys_addr;} && PERF_SAMPLE_PHYS_ADDR
          * };
          */
         PERF_RECORD_SAMPLE                      = 9,
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index ab1b0825130a..76971d2e4164 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -873,7 +873,7 @@ amended to take the number of elements as a parameter.
 
         $ cat ~/.perfconfig
         [intel-pt]
-                mispred-all
+                mispred-all = on
 
         $ perf record -e intel_pt//u ./sort 3000
         Bubble sorting array of 3000 elements
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 73496320fca3..4be08a1e3f8d 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -59,6 +59,10 @@ OPTIONS
 --ldload::
         Specify desired latency for loads event.
 
+-p::
+--phys-data::
+        Record/Report sample physical addresses
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 9bdea047c5db..e397453e5a46 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -249,7 +249,10 @@ OPTIONS
 
 -d::
 --data::
-        Record the sample addresses.
+        Record the sample virtual addresses.
+
+--phys-data::
+        Record the sample physical addresses.
 
 -T::
 --timestamp::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9fa84617181e..383a98d992ed 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -137,6 +137,7 @@ OPTIONS
         - mem: type of memory access for the data at the time of the sample
         - snoop: type of snoop (if any) for the data at the time of the sample
         - dcacheline: the cacheline the data address is on at the time of the sample
+        - phys_daddr: physical address of data being executed on at the time of sample
 
         And the default sort keys are changed to local_weight, mem, sym, dso,
         symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5ee8796be96e..18dfcfa38454 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
         srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff,
-        callindent, insn, insnlen, synth.
+        callindent, insn, insnlen, synth, phys_addr.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index c1e3288a2dfb..d53bea6bd571 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -37,7 +37,7 @@ OPTIONS
 --expr::
 --event::
         List of syscalls and other perf events (tracepoints, HW cache events,
-        etc) to show.
+        etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
         See 'perf list' for a complete list of events.
         Prefixing with ! shows all syscalls but the ones specified.  You may
         need to escape it.
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index e001c0290793..0f15634ef82c 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -23,6 +23,7 @@ struct perf_mem {
         bool                    hide_unresolved;
         bool                    dump_raw;
         bool                    force;
+        bool                    phys_addr;
         int                     operation;
         const char              *cpu_list;
         DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -101,6 +102,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
         rec_argv[i++] = "-d";
 
+        if (mem->phys_addr)
+                rec_argv[i++] = "--phys-data";
+
         for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
                 if (!perf_mem_events[j].record)
                         continue;
@@ -161,30 +165,60 @@ dump_raw_samples(struct perf_tool *tool,
         if (al.map != NULL)
                 al.map->dso->hit = 1;
 
-        if (symbol_conf.field_sep) {
-                fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
-                      "%s0x%"PRIx64"%s%s:%s\n";
+        if (mem->phys_addr) {
+                if (symbol_conf.field_sep) {
+                        fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s0x%016"PRIx64
+                              "%s%"PRIu64"%s0x%"PRIx64"%s%s:%s\n";
+                } else {
+                        fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+                              "%s0x%016"PRIx64"%s%5"PRIu64"%s0x%06"PRIx64
+                              "%s%s:%s\n";
+                        symbol_conf.field_sep = " ";
+                }
+
+                printf(fmt,
+                        sample->pid,
+                        symbol_conf.field_sep,
+                        sample->tid,
+                        symbol_conf.field_sep,
+                        sample->ip,
+                        symbol_conf.field_sep,
+                        sample->addr,
+                        symbol_conf.field_sep,
+                        sample->phys_addr,
+                        symbol_conf.field_sep,
+                        sample->weight,
+                        symbol_conf.field_sep,
+                        sample->data_src,
+                        symbol_conf.field_sep,
+                        al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+                        al.sym ? al.sym->name : "???");
         } else {
-                fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
-                      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
-                symbol_conf.field_sep = " ";
-        }
+                if (symbol_conf.field_sep) {
+                        fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+                              "%s0x%"PRIx64"%s%s:%s\n";
+                } else {
+                        fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+                              "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+                        symbol_conf.field_sep = " ";
+                }
 
-        printf(fmt,
-                sample->pid,
-                symbol_conf.field_sep,
-                sample->tid,
-                symbol_conf.field_sep,
-                sample->ip,
-                symbol_conf.field_sep,
-                sample->addr,
-                symbol_conf.field_sep,
-                sample->weight,
-                symbol_conf.field_sep,
-                sample->data_src,
-                symbol_conf.field_sep,
-                al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
-                al.sym ? al.sym->name : "???");
+                printf(fmt,
+                        sample->pid,
+                        symbol_conf.field_sep,
+                        sample->tid,
+                        symbol_conf.field_sep,
+                        sample->ip,
+                        symbol_conf.field_sep,
+                        sample->addr,
+                        symbol_conf.field_sep,
+                        sample->weight,
+                        symbol_conf.field_sep,
+                        sample->data_src,
+                        symbol_conf.field_sep,
+                        al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+                        al.sym ? al.sym->name : "???");
+        }
 out_put:
         addr_location__put(&al);
         return 0;
@@ -224,7 +258,10 @@ static int report_raw_events(struct perf_mem *mem)
         if (ret < 0)
                 goto out_delete;
 
-        printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+        if (mem->phys_addr)
+                printf("# PID, TID, IP, ADDR, PHYS ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+        else
+                printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
 
         ret = perf_session__process_events(session);
 
@@ -254,9 +291,16 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
          * there is no weight (cost) associated with stores, so don't print
          * the column
          */
-        if (!(mem->operation & MEM_OPERATION_LOAD))
-                rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
-                                "dso_daddr,tlb,locked";
+        if (!(mem->operation & MEM_OPERATION_LOAD)) {
+                if (mem->phys_addr)
+                        rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+                                        "dso_daddr,tlb,locked,phys_daddr";
+                else
+                        rep_argv[i++] = "--sort=mem,sym,dso,symbol_daddr,"
+                                        "dso_daddr,tlb,locked";
+        } else if (mem->phys_addr)
+                rep_argv[i++] = "--sort=local_weight,mem,sym,dso,symbol_daddr,"
+                                "dso_daddr,snoop,tlb,locked,phys_daddr";
 
         for (j = 1; j < argc; j++, i++)
                 rep_argv[i] = argv[j];
@@ -373,6 +417,7 @@ int cmd_mem(int argc, const char **argv)
                    "separator for columns, no spaces will be added"
                    " between columns '.' is reserved."),
         OPT_BOOLEAN('f', "force", &mem.force, "don't complain, do it"),
+        OPT_BOOLEAN('p', "phys-data", &mem.phys_addr, "Record/Report sample physical addresses"),
         OPT_END()
         };
         const char *const mem_subcommands[] = { "record", "report", NULL };
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 36d7117a7562..56f8142ff97f 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1604,6 +1604,8 @@ static struct option __record_options[] = {
         OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
                     "per thread counts"),
         OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+        OPT_BOOLEAN(0, "phys-data", &record.opts.sample_phys_addr,
+                    "Record the sample physical addresses"),
         OPT_BOOLEAN(0, "sample-cpu", &record.opts.sample_cpu, "Record the sample cpu"),
         OPT_BOOLEAN_SET('T', "timestamp", &record.opts.sample_time,
                         &record.opts.sample_time_set,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 378f76cdf923..3d4c3b5e1868 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -87,6 +87,7 @@ enum perf_output_field {
         PERF_OUTPUT_BRSTACKINSN     = 1U << 23,
         PERF_OUTPUT_BRSTACKOFF      = 1U << 24,
         PERF_OUTPUT_SYNTH           = 1U << 25,
+        PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
 };
 
 struct output_option {
@@ -119,6 +120,7 @@ struct output_option {
         {.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
         {.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
         {.str = "synth", .field = PERF_OUTPUT_SYNTH},
+        {.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
 };
 
 enum {
@@ -175,7 +177,8 @@ static struct {
                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
                               PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
                               PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT,
+                              PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
+                              PERF_OUTPUT_PHYS_ADDR,
 
                 .invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
         },
@@ -382,6 +385,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                         PERF_OUTPUT_IREGS))
                 return -EINVAL;
 
+        if (PRINT_FIELD(PHYS_ADDR) &&
+                perf_evsel__check_stype(evsel, PERF_SAMPLE_PHYS_ADDR, "PHYS_ADDR",
+                                        PERF_OUTPUT_PHYS_ADDR))
+                return -EINVAL;
+
         return 0;
 }
 
@@ -1446,6 +1454,9 @@ static void process_event(struct perf_script *script,
         if (perf_evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
                 print_sample_bpf_output(sample);
         print_insn(sample, attr, thread, machine);
+
+        if (PRINT_FIELD(PHYS_ADDR))
+                printf("%16" PRIx64, sample->phys_addr);
         printf("\n");
 }
 
@@ -2729,7 +2740,7 @@ int cmd_script(int argc, const char **argv)
                      "Valid types: hw,sw,trace,raw,synth. "
                      "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
                      "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
+                     "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr",
                      parse_output_fields),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 866da7aa54bf..85e992d9215b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1257,7 +1257,7 @@ static bool collect_data(struct perf_evsel *counter,
         if (counter->merged_stat)
                 return false;
         cb(counter, data, true);
-        if (!no_merge)
+        if (!no_merge && counter->auto_merge_stats)
                 collect_all_aliases(counter, cb, data);
         return true;
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d59cdadf3a79..771ddab94bb0 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1261,6 +1261,7 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 static int trace__validate_ev_qualifier(struct trace *trace)
 {
         int err = 0, i;
+        size_t nr_allocated;
         struct str_node *pos;
 
         trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
@@ -1274,13 +1275,18 @@ static int trace__validate_ev_qualifier(struct trace *trace)
                 goto out;
         }
 
+        nr_allocated = trace->ev_qualifier_ids.nr;
         i = 0;
 
         strlist__for_each_entry(pos, trace->ev_qualifier) {
                 const char *sc = pos->s;
-                int id = syscalltbl__id(trace->sctbl, sc);
+                int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
 
                 if (id < 0) {
+                        id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
+                        if (id >= 0)
+                                goto matches;
+
                         if (err == 0) {
                                 fputs("Error:\tInvalid syscall ", trace->output);
                                 err = -EINVAL;
@@ -1290,13 +1296,37 @@ static int trace__validate_ev_qualifier(struct trace *trace)
 
                         fputs(sc, trace->output);
                 }
-
+matches:
                 trace->ev_qualifier_ids.entries[i++] = id;
+                if (match_next == -1)
+                        continue;
+
+                while (1) {
+                        id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
+                        if (id < 0)
+                                break;
+                        if (nr_allocated == trace->ev_qualifier_ids.nr) {
+                                void *entries;
+
+                                nr_allocated += 8;
+                                entries = realloc(trace->ev_qualifier_ids.entries,
+                                                  nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
+                                if (entries == NULL) {
+                                        err = -ENOMEM;
+                                        fputs("\nError:\t Not enough memory for parsing\n", trace->output);
+                                        goto out_free;
+                                }
+                                trace->ev_qualifier_ids.entries = entries;
+                        }
+                        trace->ev_qualifier_ids.nr++;
+                        trace->ev_qualifier_ids.entries[i++] = id;
+                }
         }
 
         if (err < 0) {
                 fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
                       "\nHint:\tand: 'man syscalls'\n", trace->output);
+out_free:
                 zfree(&trace->ev_qualifier_ids.entries);
                 trace->ev_qualifier_ids.nr = 0;
         }
@@ -2814,7 +2844,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
         struct trace *trace = (struct trace *)opt->value;
         const char *s = str;
         char *sep = NULL, *lists[2] = { NULL, NULL, };
-        int len = strlen(str) + 1, err = -1, list;
+        int len = strlen(str) + 1, err = -1, list, idx;
         char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
         char group_name[PATH_MAX];
 
@@ -2831,7 +2861,8 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
                         *sep = '\0';
 
                 list = 0;
-                if (syscalltbl__id(trace->sctbl, s) >= 0) {
+                if (syscalltbl__id(trace->sctbl, s) >= 0 ||
+                    syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
                         list = 1;
                 } else {
                         path__join(group_name, sizeof(group_name), strace_groups_dir, s);
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 2c010dd6a79d..dc442ba21bf6 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -43,6 +43,7 @@ struct record_opts {
         bool         no_samples;
         bool         raw_samples;
         bool         sample_address;
+        bool         sample_phys_addr;
         bool         sample_weight;
         bool         sample_time;
         bool         sample_time_set;
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
index 7e62c46d7a20..c63a919eda98 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -80,11 +80,6 @@
     "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
   },
   {,
-    "EventCode": "0x400F0",
-    "EventName": "PM_LD_MISS_L1",
-    "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
-  },
-  {,
     "EventCode": "0x2E01A",
     "EventName": "PM_CMPLU_STALL_LSU_FLUSH_NEXT",
     "BriefDescription": "Completion stall of one cycle because the LSU requested to flush the next iop in the sequence. It takes 1 cycle for the ISU to process this request before the LSU instruction is allowed to complete"
@@ -374,4 +369,4 @@
     "EventName": "PM_IPTEG_FROM_L31_ECO_MOD",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's ECO L3 on the same chip due to a instruction side request"
   }
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
index 00f3d2a21f31..54cc3be00fc2 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -605,11 +605,6 @@
     "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)"
   },
   {,
-    "EventCode": "0x3689E",
-    "EventName": "PM_L2_RTY_LD",
-    "BriefDescription": "RC retries on PB for any load from core (excludes DCBFs)"
-  },
-  {,
     "EventCode": "0xE08C",
     "EventName": "PM_LSU0_ERAT_HIT",
     "BriefDescription": "Primary ERAT hit.  There is no secondary ERAT"
@@ -715,11 +710,6 @@
     "BriefDescription": "Lifetime, sample of RD machine 0 valid"
   },
   {,
-    "EventCode": "0x468B4",
-    "EventName": "PM_L3_RD0_BUSY",
-    "BriefDescription": "Lifetime, sample of RD machine 0 valid"
-  },
-  {,
     "EventCode": "0x46080",
     "EventName": "PM_L2_DISP_ALL_L2MISS",
     "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
@@ -850,21 +840,11 @@
     "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
   },
   {,
-    "EventCode": "0x2608C",
-    "EventName": "PM_RC0_BUSY",
-    "BriefDescription": "RC mach 0 Busy. Used by PMU to sample ave RC lifetime (mach0 used as sample point)"
-  },
-  {,
     "EventCode": "0x36082",
     "EventName": "PM_L2_LD_DISP",
     "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)."
   },
   {,
-    "EventCode": "0x1609E",
-    "EventName": "PM_L2_LD_DISP",
-    "BriefDescription": "All successful D side load dispatches for this thread (L2 miss + L2 hits)"
-  },
-  {,
     "EventCode": "0xF8B0",
     "EventName": "PM_L3_SW_PREF",
     "BriefDescription": "L3 load prefetch, sourced from a software prefetch stream, was sent to the nest"
@@ -1040,11 +1020,6 @@
     "BriefDescription": "L3 castouts in Mepf state for this thread"
   },
   {,
-    "EventCode": "0x168A0",
-    "EventName": "PM_L3_CO_MEPF",
-    "BriefDescription": "L3 CO of line in Mep state (includes casthrough to memory).  The Mepf state indicates that a line was brought in to satisfy an L3 prefetch request"
-  },
-  {,
     "EventCode": "0x460A2",
     "EventName": "PM_L3_LAT_CI_HIT",
     "BriefDescription": "L3 Lateral Castins Hit"
@@ -1150,11 +1125,6 @@
     "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)"
   },
   {,
-    "EventCode": "0x4689E",
-    "EventName": "PM_L2_RTY_ST",
-    "BriefDescription": "RC retries on PB for any store from core (excludes DCBFs)"
-  },
-  {,
     "EventCode": "0x24040",
     "EventName": "PM_INST_FROM_L2_MEPF",
     "BriefDescription": "The processor's Instruction cache was reloaded from local core's L2 hit without dispatch conflicts on Mepf state. due to an instruction fetch (not prefetch)"
@@ -1255,11 +1225,6 @@
     "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)"
   },
   {,
-    "EventCode": "0x4608C",
-    "EventName": "PM_CO0_BUSY",
-    "BriefDescription": "CO mach 0 Busy. Used by PMU to sample ave CO lifetime (mach0 used as sample point)"
-  },
-  {,
     "EventCode": "0x2C122",
     "EventName": "PM_MRK_DATA_FROM_L3_DISP_CONFLICT_CYC",
     "BriefDescription": "Duration in cycles to reload from local core's L3 with dispatch conflict due to a marked load"
@@ -1395,11 +1360,6 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's Memory due to a instruction side request"
   },
   {,
-    "EventCode": "0x40006",
-    "EventName": "PM_ISLB_MISS",
-    "BriefDescription": "Number of ISLB misses for this thread"
-  },
-  {,
     "EventCode": "0xD8A8",
     "EventName": "PM_ISLB_MISS",
     "BriefDescription": "Instruction SLB miss - Total of all segment sizes"
@@ -1515,11 +1475,6 @@
     "BriefDescription": "All successful I-side dispatches for this thread (excludes i_l2mru_tch reqs)."
   },
   {,
-    "EventCode": "0x3609E",
-    "EventName": "PM_L2_INST",
-    "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
-  },
-  {,
     "EventCode": "0x3504C",
     "EventName": "PM_IPTEG_FROM_DL4",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's L4 on a different Node or Group (Distant) due to a instruction side request"
@@ -1690,11 +1645,6 @@
     "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)"
   },
   {,
-    "EventCode": "0x2609E",
-    "EventName": "PM_L2_LD_HIT",
-    "BriefDescription": "All successful D side load dispatches for this thread that were L2 hits for this thread"
-  },
-  {,
     "EventCode": "0x168AC",
     "EventName": "PM_L3_CI_USAGE",
     "BriefDescription": "Rotating sample of 16 CI or CO actives"
@@ -1795,21 +1745,11 @@
     "BriefDescription": "Rotating sample of 8 WI valid"
   },
   {,
-    "EventCode": "0x260B6",
-    "EventName": "PM_L3_WI0_BUSY",
-    "BriefDescription": "Rotating sample of 8 WI valid (duplicate)"
-  },
-  {,
     "EventCode": "0x368AC",
     "EventName": "PM_L3_CO0_BUSY",
     "BriefDescription": "Lifetime, sample of CO machine 0 valid"
   },
   {,
-    "EventCode": "0x468AC",
-    "EventName": "PM_L3_CO0_BUSY",
-    "BriefDescription": "Lifetime, sample of CO machine 0 valid"
-  },
-  {,
     "EventCode": "0x2E040",
     "EventName": "PM_DPTEG_FROM_L2_MEPF",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 hit without dispatch conflicts on Mepf state. due to a data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
@@ -1840,11 +1780,6 @@
     "BriefDescription": "L3 PF received retry port 0, every retry counted"
   },
   {,
-    "EventCode": "0x260AE",
-    "EventName": "PM_L3_P0_PF_RTY",
-    "BriefDescription": "L3 PF received retry port 0, every retry counted"
-  },
-  {,
     "EventCode": "0x268B2",
     "EventName": "PM_L3_LOC_GUESS_WRONG",
     "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low"
@@ -1895,11 +1830,6 @@
     "BriefDescription": "Lifetime, sample of snooper machine 0 valid"
   },
   {,
-    "EventCode": "0x460AC",
-    "EventName": "PM_L3_SN0_BUSY",
-    "BriefDescription": "Lifetime, sample of snooper machine 0 valid"
-  },
-  {,
     "EventCode": "0x3005C",
     "EventName": "PM_BFU_BUSY",
     "BriefDescription": "Cycles in which all 4 Binary Floating Point units are busy. The BFU is running at capacity"
@@ -1935,11 +1865,6 @@
     "BriefDescription": "Lifetime, sample of PF machine 0 valid"
   },
   {,
-    "EventCode": "0x460B4",
-    "EventName": "PM_L3_PF0_BUSY",
-    "BriefDescription": "Lifetime, sample of PF machine 0 valid"
-  },
-  {,
     "EventCode": "0xC0B0",
     "EventName": "PM_LSU_FLUSH_UE",
     "BriefDescription": "Correctable ECC error on reload data, reported at critical data forward time"
@@ -2085,11 +2010,6 @@
     "BriefDescription": "L3 CO received retry port 1 (memory only), every retry counted"
   },
   {,
-    "EventCode": "0x468AE",
-    "EventName": "PM_L3_P1_CO_RTY",
-    "BriefDescription": "L3 CO received retry port 3 (memory only), every retry counted"
-  },
-  {,
     "EventCode": "0xC0AC",
     "EventName": "PM_LSU_FLUSH_EMSH",
     "BriefDescription": "An ERAT miss was detected after a set-p hit. Erat tracker indicates fail due to tlbmiss and the instruction gets flushed because the instruction was working on the wrong address"
@@ -2195,11 +2115,6 @@
     "BriefDescription": "SNP dispatched for a write and was M (true M); for DMA cacheinj this will pulse if rty/push is required (won't pulse if cacheinj is accepted)"
   },
   {,
-    "EventCode": "0x46886",
-    "EventName": "PM_L2_SN_M_WR_DONE",
-    "BriefDescription": "SNP dispatched for a write and was M (true M); for DMA cacheinj this will pulse if rty/push is required (won't pulse if cacheinj is accepted)"
-  },
-  {,
     "EventCode": "0x489C",
     "EventName": "PM_BR_CORECT_PRED_TAKEN_CMPL",
     "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken.  Counted at completion time"
@@ -2290,21 +2205,11 @@
     "BriefDescription": "SN mach 0 Busy. Used by PMU to sample ave SN lifetime (mach0 used as sample point)"
   },
   {,
-    "EventCode": "0x26090",
-    "EventName": "PM_SN0_BUSY",
-    "BriefDescription": "SN mach 0 Busy. Used by PMU to sample ave SN lifetime (mach0 used as sample point)"
-  },
-  {,
     "EventCode": "0x360AE",
     "EventName": "PM_L3_P0_CO_RTY",
     "BriefDescription": "L3 CO received retry port 0 (memory only), every retry counted"
   },
   {,
-    "EventCode": "0x460AE",
-    "EventName": "PM_L3_P0_CO_RTY",
-    "BriefDescription": "L3 CO received retry port 0 (memory only), every retry counted"
-  },
-  {,
     "EventCode": "0x168A8",
     "EventName": "PM_L3_WI_USAGE",
     "BriefDescription": "Lifetime, sample of Write Inject machine 0 valid"
@@ -2340,26 +2245,11 @@
     "BriefDescription": "L3 PF received retry port 1, every retry counted"
   },
   {,
-    "EventCode": "0x268AE",
-    "EventName": "PM_L3_P1_PF_RTY",
-    "BriefDescription": "L3 PF received retry port 3, every retry counted"
-  },
-  {,
     "EventCode": "0x46082",
     "EventName": "PM_L2_ST_DISP",
     "BriefDescription": "All successful D-side store dispatches for this thread "
   },
   {,
-    "EventCode": "0x1689E",
-    "EventName": "PM_L2_ST_DISP",
-    "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)"
-  },
-  {,
-    "EventCode": "0x36880",
-    "EventName": "PM_L2_INST_MISS",
-    "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
-  },
-  {,
     "EventCode": "0x4609E",
     "EventName": "PM_L2_INST_MISS",
     "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
@@ -2430,11 +2320,6 @@
     "BriefDescription": "# PPC Dispatched"
   },
   {,
-    "EventCode": "0x300F2",
-    "EventName": "PM_INST_DISP",
-    "BriefDescription": "# PPC Dispatched"
-  },
-  {,
     "EventCode": "0x4E05E",
     "EventName": "PM_TM_OUTER_TBEGIN_DISP",
     "BriefDescription": "Number of outer tbegin instructions dispatched. The dispatch unit determines whether the tbegin instruction is outer or nested. This is a speculative count, which includes flushed instructions"
@@ -2460,11 +2345,6 @@
     "BriefDescription": "All successful D-side store dispatches for this thread that were L2 hits"
   },
   {,
-    "EventCode": "0x2689E",
-    "EventName": "PM_L2_ST_HIT",
-    "BriefDescription": "All successful D-side store dispatches that were L2 hits for this thread"
-  },
-  {,
     "EventCode": "0x360A8",
     "EventName": "PM_L3_CO",
     "BriefDescription": "L3 castout occurring (does not include casthrough or log writes (cinj/dmaw))"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
index 47a82568a8df..bc2db636dabf 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
@@ -420,11 +420,6 @@
     "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch"
   },
   {,
-    "EventCode": "0x10016",
-    "EventName": "PM_DSLB_MISS",
-    "BriefDescription": "Data SLB Miss - Total of all segment sizes"
-  },
-  {,
     "EventCode": "0xD0A8",
     "EventName": "PM_DSLB_MISS",
     "BriefDescription": "Data SLB Miss - Total of all segment sizes"
@@ -554,4 +549,4 @@
     "EventName": "PM_MRK_DATA_FROM_L21_SHR_CYC",
     "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L2 on the same chip due to a marked load"
   }
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
index a2c95a99e168..3ef8a10aac86 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
@@ -5,11 +5,6 @@
     "BriefDescription": "Branches that are not strongly biased"
   },
   {,
-    "EventCode": "0x40036",
-    "EventName": "PM_BR_2PATH",
-    "BriefDescription": "Branches that are not strongly biased"
-  },
-  {,
     "EventCode": "0x40056",
     "EventName": "PM_MEM_LOC_THRESH_LSU_HIGH",
     "BriefDescription": "Local memory above threshold for LSU medium"
@@ -124,4 +119,4 @@
     "EventName": "PM_1FLOP_CMPL",
     "BriefDescription": "one flop (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg) operation completed"
   }
-]
\ No newline at end of file
+]
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 761c5a448c56..466a462b26d1 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -237,6 +237,11 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
         thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
         if (!al.map || !al.map->dso) {
+                if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
+                        pr_debug("Hypervisor address can not be resolved - skipping\n");
+                        return 0;
+                }
+
                 pr_debug("thread__find_addr_map failed\n");
                 return -1;
         }
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index 6d028f42b3cf..c3858487159d 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -141,6 +141,9 @@ static bool samples_same(const struct perf_sample *s1,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR)
+                COMP(phys_addr);
+
         return true;
 }
 
@@ -206,6 +209,7 @@ static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
                         .mask   = sample_regs,
                         .regs   = regs,
                 },
+                .phys_addr      = 113,
         };
         struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
         struct perf_sample sample_out;
@@ -305,7 +309,7 @@ int test__sample_parsing(struct test *test __maybe_unused, int subtest __maybe_u
          * were added.  Please actually update the test rather than just change
          * the condition below.
          */
-        if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
+        if (PERF_SAMPLE_MAX > PERF_SAMPLE_PHYS_ADDR << 1) {
                 pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
                 return -1;
         }
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index ba0aee576a2b..786fecaf578e 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -829,7 +829,8 @@ static int annotate_browser__run(struct annotate_browser *browser,
                 "q/ESC/CTRL+C  Exit\n\n"
                 "ENTER         Go to target\n"
                 "ESC           Exit\n"
-                "H             Cycle thru hottest instructions\n"
+                "H             Go to hottest instruction\n"
+                "TAB/shift+TAB Cycle thru hottest instructions\n"
                 "j             Toggle showing jump to target arrows\n"
                 "J             Toggle showing number of jump sources on targets\n"
                 "n             Search next string\n"
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index f4bc2462bc2c..13dfb0a0bdeb 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -931,12 +931,8 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
                                        browser->show_dso);
 
         if (symbol_conf.show_branchflag_count) {
-                if (need_percent)
-                        callchain_list_counts__printf_value(node, chain, NULL,
-                                                            buf, sizeof(buf));
-                else
-                        callchain_list_counts__printf_value(NULL, chain, NULL,
-                                                            buf, sizeof(buf));
+                callchain_list_counts__printf_value(chain, NULL,
+                                                    buf, sizeof(buf));
 
                 if (asprintf(&alloc_str2, "%s%s", str, buf) < 0)
                         str = "Not enough memory!";
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 5c95b8301c67..8bdb7a500181 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -124,12 +124,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
         str = callchain_list__sym_name(chain, bf, sizeof(bf), false);
 
         if (symbol_conf.show_branchflag_count) {
-                if (!period)
-                        callchain_list_counts__printf_value(node, chain, NULL,
-                                                            buf, sizeof(buf));
-                else
-                        callchain_list_counts__printf_value(NULL, chain, NULL,
-                                                            buf, sizeof(buf));
+                callchain_list_counts__printf_value(chain, NULL,
+                                                    buf, sizeof(buf));
 
                 if (asprintf(&alloc_str, "%s%s", str, buf) < 0)
                         str = "Not enough memory!";
@@ -313,7 +309,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
                         if (symbol_conf.show_branchflag_count)
                                 ret += callchain_list_counts__printf_value(
-                                                NULL, chain, fp, NULL, 0);
+                                                chain, fp, NULL, 0);
                         ret += fprintf(fp, "\n");
 
                         if (++entries_printed == callchain_param.print_limit)
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index f320b0777e0d..510b513e0f01 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -588,7 +588,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
                                 call->cycles_count =
                                         cursor_node->branch_flags.cycles;
                                 call->iter_count = cursor_node->nr_loop_iter;
-                                call->samples_count = cursor_node->samples;
+                                call->iter_cycles = cursor_node->iter_cycles;
                         }
                 }
 
@@ -722,7 +722,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
                                 cnode->cycles_count +=
                                         node->branch_flags.cycles;
                                 cnode->iter_count += node->nr_loop_iter;
-                                cnode->samples_count += node->samples;
+                                cnode->iter_cycles += node->iter_cycles;
                         }
                 }
 
@@ -998,7 +998,7 @@ int callchain_merge(struct callchain_cursor *cursor,
 int callchain_cursor_append(struct callchain_cursor *cursor,
                             u64 ip, struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, int samples, u64 branch_from)
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from)
 {
         struct callchain_cursor_node *node = *cursor->last;
 
@@ -1016,7 +1016,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
         node->sym = sym;
         node->branch = branch;
         node->nr_loop_iter = nr_loop_iter;
-        node->samples = samples;
+        node->iter_cycles = iter_cycles;
 
         if (flags)
                 memcpy(&node->branch_flags, flags,
@@ -1306,7 +1306,7 @@ static int branch_to_str(char *bf, int bfsize,
 static int branch_from_str(char *bf, int bfsize,
                            u64 branch_count,
                            u64 cycles_count, u64 iter_count,
-                           u64 samples_count)
+                           u64 iter_cycles)
 {
         int printed = 0, i = 0;
         u64 cycles;
@@ -1318,9 +1318,13 @@ static int branch_from_str(char *bf, int bfsize,
                                 bf + printed, bfsize - printed);
         }
 
-        if (iter_count && samples_count) {
-                printed += count_pri64_printf(i++, "iterations",
-                                iter_count / samples_count,
+        if (iter_count) {
+                printed += count_pri64_printf(i++, "iter",
+                                iter_count,
+                                bf + printed, bfsize - printed);
+
+                printed += count_pri64_printf(i++, "avg_cycles",
+                                iter_cycles / iter_count,
                                 bf + printed, bfsize - printed);
         }
 
@@ -1333,7 +1337,7 @@ static int branch_from_str(char *bf, int bfsize,
 static int counts_str_build(char *bf, int bfsize,
                              u64 branch_count, u64 predicted_count,
                              u64 abort_count, u64 cycles_count,
-                             u64 iter_count, u64 samples_count,
+                             u64 iter_count, u64 iter_cycles,
                              struct branch_type_stat *brtype_stat)
 {
         int printed;
@@ -1346,7 +1350,7 @@ static int counts_str_build(char *bf, int bfsize,
                                 predicted_count, abort_count, brtype_stat);
         } else {
                 printed = branch_from_str(bf, bfsize, branch_count,
-                                cycles_count, iter_count, samples_count);
+                                cycles_count, iter_count, iter_cycles);
         }
 
         if (!printed)
@@ -1358,14 +1362,14 @@ static int counts_str_build(char *bf, int bfsize,
 static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
                                    u64 branch_count, u64 predicted_count,
                                    u64 abort_count, u64 cycles_count,
-                                   u64 iter_count, u64 samples_count,
+                                   u64 iter_count, u64 iter_cycles,
                                    struct branch_type_stat *brtype_stat)
 {
         char str[256];
 
         counts_str_build(str, sizeof(str), branch_count,
                          predicted_count, abort_count, cycles_count,
-                         iter_count, samples_count, brtype_stat);
+                         iter_count, iter_cycles, brtype_stat);
 
         if (fp)
                 return fprintf(fp, "%s", str);
@@ -1373,31 +1377,23 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize,
         return scnprintf(bf, bfsize, "%s", str);
 }
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-                                        struct callchain_list *clist,
+int callchain_list_counts__printf_value(struct callchain_list *clist,
                                         FILE *fp, char *bf, int bfsize)
 {
         u64 branch_count, predicted_count;
         u64 abort_count, cycles_count;
-        u64 iter_count = 0, samples_count = 0;
+        u64 iter_count, iter_cycles;
 
         branch_count = clist->branch_count;
         predicted_count = clist->predicted_count;
         abort_count = clist->abort_count;
         cycles_count = clist->cycles_count;
-
-        if (node) {
-                struct callchain_list *call;
-
-                list_for_each_entry(call, &node->val, list) {
-                        iter_count += call->iter_count;
-                        samples_count += call->samples_count;
-                }
-        }
+        iter_count = clist->iter_count;
+        iter_cycles = clist->iter_cycles;
 
         return callchain_counts_printf(fp, bf, bfsize, branch_count,
                                        predicted_count, abort_count,
-                                       cycles_count, iter_count, samples_count,
+                                       cycles_count, iter_count, iter_cycles,
                                        &clist->brtype_stat);
 }
 
@@ -1523,7 +1519,8 @@ int callchain_cursor__copy(struct callchain_cursor *dst,
 
                 rc = callchain_cursor_append(dst, node->ip, node->map, node->sym,
                                              node->branch, &node->branch_flags,
-                                             node->nr_loop_iter, node->samples,
+                                             node->nr_loop_iter,
+                                             node->iter_cycles,
                                              node->branch_from);
                 if (rc)
                         break;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 97738201464a..1ed6fc61d0a5 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -119,7 +119,7 @@ struct callchain_list {
         u64                     abort_count;
         u64                     cycles_count;
         u64                     iter_count;
-        u64                     samples_count;
+        u64                     iter_cycles;
         struct branch_type_stat brtype_stat;
         char                   *srcline;
         struct list_head        list;
@@ -139,7 +139,7 @@ struct callchain_cursor_node {
         struct branch_flags             branch_flags;
         u64                             branch_from;
         int                             nr_loop_iter;
-        int                             samples;
+        u64                             iter_cycles;
         struct callchain_cursor_node    *next;
 };
 
@@ -201,7 +201,7 @@ static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
                             struct map *map, struct symbol *sym,
                             bool branch, struct branch_flags *flags,
-                            int nr_loop_iter, int samples, u64 branch_from);
+                            int nr_loop_iter, u64 iter_cycles, u64 branch_from);
 
 /* Close a cursor writing session. Initialize for the reader */
 static inline void callchain_cursor_commit(struct callchain_cursor *cursor)
@@ -282,8 +282,7 @@ char *callchain_node__scnprintf_value(struct callchain_node *node,
 int callchain_node__fprintf_value(struct callchain_node *node,
                                   FILE *fp, u64 total);
 
-int callchain_list_counts__printf_value(struct callchain_node *node,
-                                        struct callchain_list *clist,
+int callchain_list_counts__printf_value(struct callchain_list *clist,
                                         FILE *fp, char *bf, int bfsize);
 
 void free_callchain(struct callchain_root *root);
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 423ac82605f3..ee7bcc898d35 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -200,6 +200,7 @@ struct perf_sample {
         u32 cpu;
         u32 raw_size;
         u64 data_src;
+        u64 phys_addr;
         u32 flags;
         u16 insn_len;
         u8  cpumode;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index d9bd632ed7db..4bb89373eb52 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -955,6 +955,9 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
         if (opts->sample_address)
                 perf_evsel__set_sample_bit(evsel, DATA_SRC);
 
+        if (opts->sample_phys_addr)
+                perf_evsel__set_sample_bit(evsel, PHYS_ADDR);
+
         if (opts->no_buffering) {
                 attr->watermark = 0;
                 attr->wakeup_events = 1;
@@ -1464,7 +1467,7 @@ static void __p_sample_type(char *buf, size_t size, u64 value)
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
                 bit_name(IDENTIFIER), bit_name(REGS_INTR), bit_name(DATA_SRC),
-                bit_name(WEIGHT),
+                bit_name(WEIGHT), bit_name(PHYS_ADDR),
                 { .name = NULL, }
         };
 #undef bit_name
@@ -2206,6 +2209,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 }
         }
 
+        data->phys_addr = 0;
+        if (type & PERF_SAMPLE_PHYS_ADDR) {
+                data->phys_addr = *array;
+                array++;
+        }
+
         return 0;
 }
 
@@ -2311,6 +2320,9 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR)
+                result += sizeof(u64);
+
         return result;
 }
 
@@ -2500,6 +2512,11 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                 }
         }
 
+        if (type & PERF_SAMPLE_PHYS_ADDR) {
+                *array = sample->phys_addr;
+                array++;
+        }
+
         return 0;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 351d3b2d8887..dd2c4b5112a5 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -131,6 +131,7 @@ struct perf_evsel {
         bool                    cmdline_group_boundary;
         struct list_head        config_terms;
         int                     bpf_fd;
+        bool                    auto_merge_stats;
         bool                    merged_stat;
         const char *            metric_expr;
         const char *            metric_name;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 9453b2e27015..e60d8d8ea4c2 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -167,6 +167,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
                         symlen = unresolved_col_width + 4 + 2;
                         hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
                 }
+
+                hists__new_col_len(hists, HISTC_MEM_PHYS_DADDR,
+                                   unresolved_col_width + 4 + 2);
+
         } else {
                 symlen = unresolved_col_width + 4 + 2;
                 hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index ee3670a388df..e60dda26a920 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
         HISTC_GLOBAL_WEIGHT,
         HISTC_MEM_DADDR_SYMBOL,
         HISTC_MEM_DADDR_DSO,
+        HISTC_MEM_PHYS_DADDR,
         HISTC_MEM_LOCKED,
         HISTC_MEM_TLB,
         HISTC_MEM_LVL,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 5c8eacaca4f4..df709363ef69 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1635,10 +1635,12 @@ static void ip__resolve_ams(struct thread *thread,
         ams->al_addr = al.addr;
         ams->sym = al.sym;
         ams->map = al.map;
+        ams->phys_addr = 0;
 }
 
 static void ip__resolve_data(struct thread *thread,
-                             u8 m, struct addr_map_symbol *ams, u64 addr)
+                             u8 m, struct addr_map_symbol *ams,
+                             u64 addr, u64 phys_addr)
 {
         struct addr_location al;
 
@@ -1658,6 +1660,7 @@ static void ip__resolve_data(struct thread *thread,
         ams->al_addr = al.addr;
         ams->sym = al.sym;
         ams->map = al.map;
+        ams->phys_addr = phys_addr;
 }
 
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
@@ -1669,12 +1672,18 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
                 return NULL;
 
         ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
-        ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
+        ip__resolve_data(al->thread, al->cpumode, &mi->daddr,
+                         sample->addr, sample->phys_addr);
         mi->data_src.val = sample->data_src;
 
         return mi;
 }
 
+struct iterations {
+        int nr_loop_iter;
+        u64 cycles;
+};
+
 static int add_callchain_ip(struct thread *thread,
                             struct callchain_cursor *cursor,
                             struct symbol **parent,
@@ -1683,11 +1692,12 @@ static int add_callchain_ip(struct thread *thread,
                             u64 ip,
                             bool branch,
                             struct branch_flags *flags,
-                            int nr_loop_iter,
-                            int samples,
+                            struct iterations *iter,
                             u64 branch_from)
 {
         struct addr_location al;
+        int nr_loop_iter = 0;
+        u64 iter_cycles = 0;
 
         al.filtered = 0;
         al.sym = NULL;
@@ -1737,9 +1747,15 @@ static int add_callchain_ip(struct thread *thread,
 
         if (symbol_conf.hide_unresolved && al.sym == NULL)
                 return 0;
+
+        if (iter) {
+                nr_loop_iter = iter->nr_loop_iter;
+                iter_cycles = iter->cycles;
+        }
+
         return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
-                                       branch, flags, nr_loop_iter, samples,
-                                       branch_from);
+                                       branch, flags, nr_loop_iter,
+                                       iter_cycles, branch_from);
 }
 
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
@@ -1760,6 +1776,18 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
         return bi;
 }
 
+static void save_iterations(struct iterations *iter,
+                            struct branch_entry *be, int nr)
+{
+        int i;
+
+        iter->nr_loop_iter = nr;
+        iter->cycles = 0;
+
+        for (i = 0; i < nr; i++)
+                iter->cycles += be[i].flags.cycles;
+}
+
 #define CHASHSZ 127
 #define CHASHBITS 7
 #define NO_ENTRY 0xff
@@ -1767,7 +1795,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 #define PERF_MAX_BRANCH_DEPTH 127
 
 /* Remove loops. */
-static int remove_loops(struct branch_entry *l, int nr)
+static int remove_loops(struct branch_entry *l, int nr,
+                        struct iterations *iter)
 {
         int i, j, off;
         unsigned char chash[CHASHSZ];
@@ -1792,8 +1821,18 @@ static int remove_loops(struct branch_entry *l, int nr)
                                         break;
                                 }
                         if (is_loop) {
-                                memmove(l + i, l + i + off,
-                                        (nr - (i + off)) * sizeof(*l));
+                                j = nr - (i + off);
+                                if (j > 0) {
+                                        save_iterations(iter + i + off,
+                                                l + i, off);
+
+                                        memmove(iter + i, iter + i + off,
+                                                j * sizeof(*iter));
+
+                                        memmove(l + i, l + i + off,
+                                                j * sizeof(*l));
+                                }
+
                                 nr -= off;
                         }
                 }
@@ -1883,7 +1922,7 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
 
                         err = add_callchain_ip(thread, cursor, parent,
                                                root_al, &cpumode, ip,
-                                               branch, flags, 0, 0,
+                                               branch, flags, NULL,
                                                branch_from);
                         if (err)
                                 return (err < 0) ? err : 0;
@@ -1909,7 +1948,6 @@ static int thread__resolve_callchain_sample(struct thread *thread,
         int i, j, err, nr_entries;
         int skip_idx = -1;
         int first_call = 0;
-        int nr_loop_iter;
 
         if (chain)
                 chain_nr = chain->nr;
@@ -1942,6 +1980,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
         if (branch && callchain_param.branch_callstack) {
                 int nr = min(max_stack, (int)branch->nr);
                 struct branch_entry be[nr];
+                struct iterations iter[nr];
 
                 if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
                         pr_warning("corrupted branch chain. skipping...\n");
@@ -1972,38 +2011,21 @@ static int thread__resolve_callchain_sample(struct thread *thread,
                                 be[i] = branch->entries[branch->nr - i - 1];
                 }
 
-                nr_loop_iter = nr;
-                nr = remove_loops(be, nr);
-
-                /*
-                 * Get the number of iterations.
-                 * It's only approximation, but good enough in practice.
-                 */
-                if (nr_loop_iter > nr)
-                        nr_loop_iter = nr_loop_iter - nr + 1;
-                else
-                        nr_loop_iter = 0;
+                memset(iter, 0, sizeof(struct iterations) * nr);
+                nr = remove_loops(be, nr, iter);
 
                 for (i = 0; i < nr; i++) {
-                        if (i == nr - 1)
-                                err = add_callchain_ip(thread, cursor, parent,
-                                                       root_al,
-                                                       NULL, be[i].to,
-                                                       true, &be[i].flags,
-                                                       nr_loop_iter, 1,
-                                                       be[i].from);
-                        else
-                                err = add_callchain_ip(thread, cursor, parent,
-                                                       root_al,
-                                                       NULL, be[i].to,
-                                                       true, &be[i].flags,
-                                                       0, 0, be[i].from);
+                        err = add_callchain_ip(thread, cursor, parent,
+                                               root_al,
+                                               NULL, be[i].to,
+                                               true, &be[i].flags,
+                                               NULL, be[i].from);
 
                         if (!err)
                                 err = add_callchain_ip(thread, cursor, parent, root_al,
                                                        NULL, be[i].from,
                                                        true, &be[i].flags,
-                                                       0, 0, 0);
+                                                       &iter[i], 0);
                         if (err == -EINVAL)
                                 break;
                         if (err)
@@ -2037,7 +2059,7 @@ check_calls:
 
                 err = add_callchain_ip(thread, cursor, parent,
                                        root_al, &cpumode, ip,
-                                       false, NULL, 0, 0, 0);
+                                       false, NULL, NULL, 0);
 
                 if (err)
                         return (err < 0) ? err : 0;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f44aeba51d1f..f6257fb4f08c 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -310,7 +310,7 @@ static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
             struct perf_event_attr *attr,
             char *name, struct cpu_map *cpus,
-            struct list_head *config_terms)
+            struct list_head *config_terms, bool auto_merge_stats)
 {
         struct perf_evsel *evsel;
 
@@ -324,6 +324,7 @@ __add_event(struct list_head *list, int *idx,
         evsel->cpus        = cpu_map__get(cpus);
         evsel->own_cpus    = cpu_map__get(cpus);
         evsel->system_wide = !!cpus;
+        evsel->auto_merge_stats = auto_merge_stats;
 
         if (name)
                 evsel->name = strdup(name);
@@ -339,7 +340,7 @@ static int add_event(struct list_head *list, int *idx,
                      struct perf_event_attr *attr, char *name,
                      struct list_head *config_terms)
 {
-        return __add_event(list, idx, attr, name, NULL, config_terms) ? 0 : -ENOMEM;
+        return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -1209,9 +1210,9 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
                          get_config_name(head_config), &config_terms);
 }
 
-int parse_events_add_pmu(struct parse_events_state *parse_state,
+static int __parse_events_add_pmu(struct parse_events_state *parse_state,
                          struct list_head *list, char *name,
-                         struct list_head *head_config)
+                         struct list_head *head_config, bool auto_merge_stats)
 {
         struct perf_event_attr attr;
         struct perf_pmu_info info;
@@ -1232,7 +1233,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
         if (!head_config) {
                 attr.type = pmu->type;
-                evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL);
+                evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
                 return evsel ? 0 : -ENOMEM;
         }
 
@@ -1254,7 +1255,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
         evsel = __add_event(list, &parse_state->idx, &attr,
                             get_config_name(head_config), pmu->cpus,
-                            &config_terms);
+                            &config_terms, auto_merge_stats);
         if (evsel) {
                 evsel->unit = info.unit;
                 evsel->scale = info.scale;
@@ -1267,6 +1268,13 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
         return evsel ? 0 : -ENOMEM;
 }
 
+int parse_events_add_pmu(struct parse_events_state *parse_state,
+                         struct list_head *list, char *name,
+                         struct list_head *head_config)
+{
+        return __parse_events_add_pmu(parse_state, list, name, head_config, false);
+}
+
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                char *str, struct list_head **listp)
 {
@@ -1296,8 +1304,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
                                         return -1;
                                 list_add_tail(&term->list, head);
 
-                                if (!parse_events_add_pmu(parse_state, list,
-                                                  pmu->name, head)) {
+                                if (!__parse_events_add_pmu(parse_state, list,
+                                                            pmu->name, head, true)) {
                                         pr_debug("%s -> %s/%s/\n", str,
                                                  pmu->name, alias->str);
                                         ok++;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ac863691605f..a7ebd9fe8e40 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1120,6 +1120,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
         if (sample_type & PERF_SAMPLE_DATA_SRC)
                 printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
 
+        if (sample_type & PERF_SAMPLE_PHYS_ADDR)
+                printf(" .. phys_addr: 0x%"PRIx64"\n", sample->phys_addr);
+
         if (sample_type & PERF_SAMPLE_TRANSACTION)
                 printf("... transaction: %" PRIx64 "\n", sample->transaction);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 12359bd986db..eb3ab902a1c0 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1316,6 +1316,47 @@ struct sort_entry sort_mem_dcacheline = {
 };
 
 static int64_t
+sort__phys_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+        uint64_t l = 0, r = 0;
+
+        if (left->mem_info)
+                l = left->mem_info->daddr.phys_addr;
+        if (right->mem_info)
+                r = right->mem_info->daddr.phys_addr;
+
+        return (int64_t)(r - l);
+}
+
+static int hist_entry__phys_daddr_snprintf(struct hist_entry *he, char *bf,
+                                           size_t size, unsigned int width)
+{
+        uint64_t addr = 0;
+        size_t ret = 0;
+        size_t len = BITS_PER_LONG / 4;
+
+        addr = he->mem_info->daddr.phys_addr;
+
+        ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", he->level);
+
+        ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx", len, addr);
+
+        ret += repsep_snprintf(bf + ret, size - ret, "%-*s", width - ret, "");
+
+        if (ret > width)
+                bf[width] = '\0';
+
+        return width;
+}
+
+struct sort_entry sort_mem_phys_daddr = {
+        .se_header      = "Data Physical Address",
+        .se_cmp         = sort__phys_daddr_cmp,
+        .se_snprintf    = hist_entry__phys_daddr_snprintf,
+        .se_width_idx   = HISTC_MEM_PHYS_DADDR,
+};
+
+static int64_t
 sort__abort_cmp(struct hist_entry *left, struct hist_entry *right)
 {
         if (!left->branch_info || !right->branch_info)
@@ -1547,6 +1588,7 @@ static struct sort_dimension memory_sort_dimensions[] = {
         DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
         DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
         DIM(SORT_MEM_DCACHELINE, "dcacheline", sort_mem_dcacheline),
+        DIM(SORT_MEM_PHYS_DADDR, "phys_daddr", sort_mem_phys_daddr),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b7c75597e18f..f36dc4980a6c 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -245,6 +245,7 @@ enum sort_type {
         SORT_MEM_SNOOP,
         SORT_MEM_DCACHELINE,
         SORT_MEM_IADDR_SYMBOL,
+        SORT_MEM_PHYS_DADDR,
 };
 
 /*
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index d00a012cfdfb..2bd6a1f01a1c 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -186,6 +186,7 @@ struct addr_map_symbol {
         struct symbol *sym;
         u64           addr;
         u64           al_addr;
+        u64           phys_addr;
 };
 
 struct branch_info {
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index bbb4c1957578..19e5db90394c 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -19,6 +19,7 @@
 #ifdef HAVE_SYSCALL_TABLE
 #include <linux/compiler.h>
 #include <string.h>
+#include "string2.h"
 #include "util.h"
 
 #if defined(__x86_64__)
@@ -105,6 +106,27 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
         return sc ? sc->id : -1;
 }
 
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        int i;
+        struct syscall *syscalls = tbl->syscalls.entries;
+
+        for (i = *idx + 1; i < tbl->syscalls.nr_entries; ++i) {
+                if (strglobmatch(syscalls[i].name, syscall_glob)) {
+                        *idx = i;
+                        return syscalls[i].id;
+                }
+        }
+
+        return -1;
+}
+
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        *idx = -1;
+        return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
+}
+
 #else /* HAVE_SYSCALL_TABLE */
 
 #include <libaudit.h>
@@ -131,4 +153,15 @@ int syscalltbl__id(struct syscalltbl *tbl, const char *name)
 {
         return audit_name_to_syscall(name, tbl->audit_machine);
 }
+
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl __maybe_unused,
+                                  const char *syscall_glob __maybe_unused, int *idx __maybe_unused)
+{
+        return -1;
+}
+
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx)
+{
+        return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
+}
 #endif /* HAVE_SYSCALL_TABLE */
diff --git a/tools/perf/util/syscalltbl.h b/tools/perf/util/syscalltbl.h
index e2951510484f..e9fb8786da7c 100644
--- a/tools/perf/util/syscalltbl.h
+++ b/tools/perf/util/syscalltbl.h
@@ -17,4 +17,7 @@ void syscalltbl__delete(struct syscalltbl *tbl);
 const char *syscalltbl__name(const struct syscalltbl *tbl, int id);
 int syscalltbl__id(struct syscalltbl *tbl, const char *name);
 
+int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_glob, int *idx);
+int syscalltbl__strglobmatch_next(struct syscalltbl *tbl, const char *syscall_glob, int *idx);
+
 #endif /* __PERF_SYSCALLTBL_H */