14 files changed, 72 insertions, 32 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ac9805e0bc76..70de8f6b3aee 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1723,15 +1723,14 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
         err = asprintf(&command,
                  "%s %s%s --start-address=0x%016" PRIx64
                  " --stop-address=0x%016" PRIx64
-                 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
+                 " -l -d %s %s -C \"$1\" 2>/dev/null|grep -v \"$1:\"|expand",
                  opts->objdump_path ?: "objdump",
                  opts->disassembler_style ? "-M " : "",
                  opts->disassembler_style ?: "",
                  map__rip_2objdump(map, sym->start),
                  map__rip_2objdump(map, sym->end),
                  opts->show_asm_raw ? "" : "--no-show-raw",
-                 opts->annotate_src ? "-S" : "",
-                 symfs_filename, symfs_filename);
+                 opts->annotate_src ? "-S" : "");
 
         if (err < 0) {
                 pr_err("Failure allocating memory for the command to run\n");
@@ -1756,7 +1755,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
                 close(stdout_fd[0]);
                 dup2(stdout_fd[1], 1);
                 close(stdout_fd[1]);
-                execl("/bin/sh", "sh", "-c", command, NULL);
+                execl("/bin/sh", "sh", "-c", command, "--", symfs_filename,
+                      NULL);
                 perror(command);
                 exit(-1);
         }
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 89512504551b..39c0004f2886 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module)
         }
         PM.run(*Module);
 
-        return std::move(Buffer);
+        return Buffer;
 }
 
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 32ef7bdca1cf..dc2212e12184 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -766,6 +766,7 @@ 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->iter_cycles += node->iter_cycles;
+                        cnode->from_count++;
                 }
         }
 
@@ -1345,10 +1346,10 @@ 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 iter_cycles)
+                           u64 iter_cycles, u64 from_count)
 {
         int printed = 0, i = 0;
-        u64 cycles;
+        u64 cycles, v = 0;
 
         cycles = cycles_count / branch_count;
         if (cycles) {
@@ -1357,14 +1358,16 @@ static int branch_from_str(char *bf, int bfsize,
                                 bf + printed, bfsize - printed);
         }
 
-        if (iter_count) {
-                printed += count_pri64_printf(i++, "iter",
-                                iter_count,
-                                bf + printed, bfsize - printed);
+        if (iter_count && from_count) {
+                v = iter_count / from_count;
+                if (v) {
+                        printed += count_pri64_printf(i++, "iter",
+                                        v, bf + printed, bfsize - printed);
 
-                printed += count_pri64_printf(i++, "avg_cycles",
-                                iter_cycles / iter_count,
-                                bf + printed, bfsize - printed);
+                        printed += count_pri64_printf(i++, "avg_cycles",
+                                        iter_cycles / iter_count,
+                                        bf + printed, bfsize - printed);
+                }
         }
 
         if (i)
@@ -1377,6 +1380,7 @@ 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 iter_cycles,
+                             u64 from_count,
                              struct branch_type_stat *brtype_stat)
 {
         int printed;
@@ -1389,7 +1393,8 @@ 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, iter_cycles);
+                                cycles_count, iter_count, iter_cycles,
+                                from_count);
         }
 
         if (!printed)
@@ -1402,13 +1407,14 @@ 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 iter_cycles,
+                                   u64 from_count,
                                    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, iter_cycles, brtype_stat);
+                         iter_count, iter_cycles, from_count, brtype_stat);
 
         if (fp)
                 return fprintf(fp, "%s", str);
@@ -1422,6 +1428,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
         u64 branch_count, predicted_count;
         u64 abort_count, cycles_count;
         u64 iter_count, iter_cycles;
+        u64 from_count;
 
         branch_count = clist->branch_count;
         predicted_count = clist->predicted_count;
@@ -1429,11 +1436,12 @@ int callchain_list_counts__printf_value(struct callchain_list *clist,
         cycles_count = clist->cycles_count;
         iter_count = clist->iter_count;
         iter_cycles = clist->iter_cycles;
+        from_count = clist->from_count;
 
         return callchain_counts_printf(fp, bf, bfsize, branch_count,
                                        predicted_count, abort_count,
                                        cycles_count, iter_count, iter_cycles,
-                                       &clist->brtype_stat);
+                                       from_count, &clist->brtype_stat);
 }
 
 static void free_callchain_node(struct callchain_node *node)
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 154560b1eb65..99d38ac019b8 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -118,6 +118,7 @@ struct callchain_list {
                 bool            has_children;
         };
         u64                     branch_count;
+        u64                     from_count;
         u64                     predicted_count;
         u64                     abort_count;
         u64                     cycles_count;
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 1ccbd3342069..383674f448fc 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
         if (!cpu_list)
                 return cpu_map__read_all_cpu_map();
 
-        if (!isdigit(*cpu_list))
+        /*
+         * must handle the case of empty cpumap to cover
+         * TOPOLOGY header for NUMA nodes with no CPU
+         * ( e.g., because of CPU hotplug)
+         */
+        if (!isdigit(*cpu_list) && *cpu_list != '\0')
                 goto out;
 
         while (isdigit(*cpu_list)) {
@@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
 
         if (nr_cpus > 0)
                 cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-        else
+        else if (*cpu_list != '\0')
                 cpus = cpu_map__default_new();
+        else
+                cpus = cpu_map__dummy_new();
 invalid:
         free(tmp_cpus);
 out:
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-map.c
index d7823e3508fc..7b2300588ece 100644
--- a/tools/perf/util/find-vdso-map.c
+++ b/tools/perf/util/find-map.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-static int find_vdso_map(void **start, void **end)
+static int find_map(void **start, void **end, const char *name)
 {
         FILE *maps;
         char line[128];
@@ -7,7 +7,7 @@ static int find_vdso_map(void **start, void **end)
 
         maps = fopen("/proc/self/maps", "r");
         if (!maps) {
-                fprintf(stderr, "vdso: cannot open maps\n");
+                fprintf(stderr, "cannot open maps\n");
                 return -1;
         }
 
@@ -21,8 +21,7 @@ static int find_vdso_map(void **start, void **end)
                 if (m < 0)
                         continue;
 
-                if (!strncmp(&line[m], VDSO__MAP_NAME,
-                             sizeof(VDSO__MAP_NAME) - 1))
+                if (!strncmp(&line[m], name, strlen(name)))
                         found = 1;
         }
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 6fcb3bce0442..143f7057d581 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2005,7 +2005,7 @@ static void save_iterations(struct iterations *iter,
 {
         int i;
 
-        iter->nr_loop_iter = nr;
+        iter->nr_loop_iter++;
         iter->cycles = 0;
 
         for (i = 0; i < nr; i++)
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 93f74d8d3cdd..42c3e5a229d2 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
-char *perf_mem_events__name(int i)
+char * __weak perf_mem_events__name(int i)
 {
         if (i == PERF_MEM_EVENTS__LOAD) {
                 if (!mem_loads_name__init) {
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 897589507d97..ea523d3b248f 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -391,8 +391,10 @@ void ordered_events__free(struct ordered_events *oe)
          * Current buffer might not have all the events allocated
          * yet, we need to free only allocated ones ...
          */
-        list_del(&oe->buffer->list);
-        ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+        if (oe->buffer) {
+                list_del(&oe->buffer->list);
+                ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+        }
 
         /* ... and continue with the rest */
         list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 63f758c655d5..64d1f36dee99 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -17,6 +17,8 @@ if cc == "clang":
             vars[var] = sub("-mcet", "", vars[var])
         if not clang_has_option("-fcf-protection"):
             vars[var] = sub("-fcf-protection", "", vars[var])
+        if not clang_has_option("-fstack-clash-protection"):
+            vars[var] = sub("-fstack-clash-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/strbuf.c b/tools/perf/util/strbuf.c
index 9005fbe0780e..23092fd6451d 100644
--- a/tools/perf/util/strbuf.c
+++ b/tools/perf/util/strbuf.c
@@ -109,7 +109,6 @@ static int strbuf_addv(struct strbuf *sb, const char *fmt, va_list ap)
                         return ret;
                 }
                 len = vsnprintf(sb->buf + sb->len, sb->alloc - sb->len, fmt, ap_saved);
-                va_end(ap_saved);
                 if (len > strbuf_avail(sb)) {
                         pr_debug("this should not happen, your vsnprintf is broken");
                         va_end(ap_saved);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 66a84d5846c8..dca7dfae69ad 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -19,6 +19,20 @@
 #define EM_AARCH64      183  /* ARM 64 bit */
 #endif
 
+#ifndef ELF32_ST_VISIBILITY
+#define ELF32_ST_VISIBILITY(o)  ((o) & 0x03)
+#endif
+
+/* For ELF64 the definitions are the same.  */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o)  ELF32_ST_VISIBILITY (o)
+#endif
+
+/* How to extract information held in the st_other field.  */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(val) ELF64_ST_VISIBILITY (val)
+#endif
+
 typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
@@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
         return GELF_ST_TYPE(sym->st_info);
 }
 
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+        return GELF_ST_VISIBILITY(sym->st_other);
+}
+
 #ifndef STT_GNU_IFUNC
 #define STT_GNU_IFUNC 10
 #endif
@@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
         return elf_sym__type(sym) == STT_NOTYPE &&
                 sym->st_name != 0 &&
                 sym->st_shndx != SHN_UNDEF &&
-                sym->st_shndx != SHN_ABS;
+                sym->st_shndx != SHN_ABS &&
+                elf_sym__visibility(sym) != STV_HIDDEN &&
+                elf_sym__visibility(sym) != STV_INTERNAL;
 }
 
 static bool elf_sym__filter(GElf_Sym *sym)
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 01f2c7385e38..48efad6d0f90 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -614,6 +614,7 @@ out:
 static bool symbol__is_idle(const char *name)
 {
         const char * const idle_symbols[] = {
+                "arch_cpu_idle",
                 "cpu_idle",
                 "cpu_startup_entry",
                 "intel_idle",
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 741af209b19d..3702cba11d7d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -18,10 +18,10 @@
 #include "debug.h"
 
 /*
- * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * Include definition of find_map() also used in perf-read-vdso.c for
  * building perf-read-vdso32 and perf-read-vdsox32.
  */
-#include "find-vdso-map.c"
+#include "find-map.c"
 
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
@@ -76,7 +76,7 @@ static char *get_file(struct vdso_file *vdso_file)
         if (vdso_file->found)
                 return vdso_file->temp_file_name;
 
-        if (vdso_file->error || find_vdso_map(&start, &end))
+        if (vdso_file->error || find_map(&start, &end, VDSO__MAP_NAME))
                 return NULL;
 
         size = end - start;