Merge tag 'v4.12-rc6' into perf/core, to pick up fixes

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

21 files changed, 182 insertions, 161 deletions

diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index e6c9902c6d82..165c2b1d4317 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -240,9 +240,13 @@ Add a probe on schedule() function 12th line with recording cpu local variable:
  or
  ./perf probe --add='schedule:12 cpu'
 
- this will add one or more probes which has the name start with "schedule".
+Add one or more probes which has the name start with "schedule".
 
- Add probes on lines in schedule() function which calls update_rq_clock().
+ ./perf probe schedule*
+ or
+ ./perf probe --add='schedule*'
+
+Add probes on lines in schedule() function which calls update_rq_clock().
 
  ./perf probe 'schedule;update_rq_clock*'
  or
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index dfbb506d2c34..142606c0ec9c 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -39,7 +39,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 54acba221558..51ec2d20068a 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -149,10 +149,8 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
                 print "id=%d, args=%s\n" % \
                 (id, args),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-                common_pid, common_comm):
-                print_header(event_name, common_cpu, common_secs, common_nsecs,
-                common_pid, common_comm)
+def trace_unhandled(event_name, context, event_fields_dict):
+                print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
 
 def print_header(event_name, cpu, secs, nsecs, pid, comm):
         print "%-20s %5u %05u.%09u %8u %-20s " % \
@@ -321,7 +319,7 @@ So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
 you're interested in - basically find the tracepoint(s) you're
 interested in by looking at the list of available events shown by
-'perf list' and/or look in /sys/kernel/debug/tracing events for
+'perf list' and/or look in /sys/kernel/debug/tracing/events/ for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
 generate a skeleton script using 'perf script -g python' and modify the
@@ -334,7 +332,7 @@ right place, you can have your script listed alongside the other
 scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -383,8 +381,6 @@ source tree:
 
 ----
 # ls -al kernel-source/tools/perf/scripts/python
-
-root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
 total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
@@ -399,7 +395,7 @@ otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -437,7 +433,7 @@ EVENT HANDLERS
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
@@ -532,7 +528,7 @@ can implement a set of optional functions:
 gives scripts a chance to do setup tasks:
 
 ----
-def trace_begin:
+def trace_begin():
     pass
 ----
 
@@ -541,7 +537,7 @@ def trace_begin:
  as display results:
 
 ----
-def trace_end:
+def trace_end():
     pass
 ----
 
@@ -550,8 +546,7 @@ def trace_end:
  of common arguments are passed into it:
 
 ----
-def trace_unhandled(event_name, context, common_cpu, common_secs,
-        common_nsecs, common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     pass
 ----
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 8354d04b392f..1f4fbc9a3292 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -19,18 +19,18 @@ CFLAGS := $(EXTRA_CFLAGS) $(EXTRA_WARNINGS)
 
 include $(srctree)/tools/scripts/Makefile.arch
 
-$(call detected_var,ARCH)
+$(call detected_var,SRCARCH)
 
 NO_PERF_REGS := 1
 
 # Additional ARCH settings for ppc
-ifeq ($(ARCH),powerpc)
+ifeq ($(SRCARCH),powerpc)
   NO_PERF_REGS := 0
   LIBUNWIND_LIBS := -lunwind -lunwind-ppc64
 endif
 
 # Additional ARCH settings for x86
-ifeq ($(ARCH),x86)
+ifeq ($(SRCARCH),x86)
   $(call detected,CONFIG_X86)
   ifeq (${IS_64_BIT}, 1)
     CFLAGS += -DHAVE_ARCH_X86_64_SUPPORT -DHAVE_SYSCALL_TABLE -I$(OUTPUT)arch/x86/include/generated
@@ -43,12 +43,12 @@ ifeq ($(ARCH),x86)
   NO_PERF_REGS := 0
 endif
 
-ifeq ($(ARCH),arm)
+ifeq ($(SRCARCH),arm)
   NO_PERF_REGS := 0
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
-ifeq ($(ARCH),arm64)
+ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
@@ -61,7 +61,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -115,9 +115,9 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
-FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi
+FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
--include $(src-perf)/arch/$(ARCH)/Makefile
+-include $(src-perf)/arch/$(SRCARCH)/Makefile
 
 ifdef PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
   CFLAGS += -DHAVE_ARCH_REGS_QUERY_REGISTER_OFFSET
@@ -228,12 +228,12 @@ ifeq ($(DEBUG),0)
 endif
 
 INC_FLAGS += -I$(src-perf)/util/include
-INC_FLAGS += -I$(src-perf)/arch/$(ARCH)/include
+INC_FLAGS += -I$(src-perf)/arch/$(SRCARCH)/include
 INC_FLAGS += -I$(srctree)/tools/include/uapi
 INC_FLAGS += -I$(srctree)/tools/include/
-INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi
-INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/
-INC_FLAGS += -I$(srctree)/tools/arch/$(ARCH)/
+INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi
+INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/include/
+INC_FLAGS += -I$(srctree)/tools/arch/$(SRCARCH)/
 
 # $(obj-perf)      for generated common-cmds.h
 # $(obj-perf)/util for generated bison/flex headers
@@ -355,7 +355,7 @@ ifndef NO_LIBELF
 
   ifndef NO_DWARF
     ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
-      msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
+      msg := $(warning DWARF register mappings have not been defined for architecture $(SRCARCH), DWARF support disabled);
       NO_DWARF := 1
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
@@ -380,7 +380,7 @@ ifndef NO_LIBELF
         CFLAGS += -DHAVE_BPF_PROLOGUE
         $(call detected,CONFIG_BPF_PROLOGUE)
       else
-        msg := $(warning BPF prologue is not supported by architecture $(ARCH), missing regs_query_register_offset());
+        msg := $(warning BPF prologue is not supported by architecture $(SRCARCH), missing regs_query_register_offset());
       endif
     else
       msg := $(warning DWARF support is off, BPF prologue is disabled);
@@ -406,7 +406,7 @@ ifdef PERF_HAVE_JITDUMP
   endif
 endif
 
-ifeq ($(ARCH),powerpc)
+ifeq ($(SRCARCH),powerpc)
   ifndef NO_DWARF
     CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
   endif
@@ -487,7 +487,7 @@ else
 endif
 
 ifndef NO_LOCAL_LIBUNWIND
-  ifeq ($(ARCH),$(filter $(ARCH),arm arm64))
+  ifeq ($(SRCARCH),$(filter $(SRCARCH),arm arm64))
     $(call feature_check,libunwind-debug-frame)
     ifneq ($(feature-libunwind-debug-frame), 1)
       msg := $(warning No debug_frame support found in libunwind);
@@ -740,7 +740,7 @@ ifeq (${IS_64_BIT}, 1)
       NO_PERF_READ_VDSO32 := 1
     endif
   endif
-  ifneq ($(ARCH), x86)
+  ifneq ($(SRCARCH), x86)
     NO_PERF_READ_VDSOX32 := 1
   endif
   ifndef NO_PERF_READ_VDSOX32
@@ -769,7 +769,7 @@ ifdef LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE
-  ifeq ($(ARCH),x86)
+  ifeq ($(SRCARCH),x86)
     ifeq ($(feature-get_cpuid), 0)
       msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
       NO_AUXTRACE := 1
@@ -872,7 +872,7 @@ sysconfdir = $(prefix)/etc
 ETC_PERFCONFIG = etc/perfconfig
 endif
 ifndef lib
-ifeq ($(ARCH)$(IS_64_BIT), x861)
+ifeq ($(SRCARCH)$(IS_64_BIT), x861)
 lib = lib64
 else
 lib = lib
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 79fe31f20a17..5008f51a08a2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -226,7 +226,7 @@ endif
 
 ifeq ($(config),0)
 include $(srctree)/tools/scripts/Makefile.arch
--include arch/$(ARCH)/Makefile
+-include arch/$(SRCARCH)/Makefile
 endif
 
 # The FEATURE_DUMP_EXPORT holds location of the actual
diff --git a/tools/perf/arch/Build b/tools/perf/arch/Build
index 109eb75cf7de..d9b6af837c7d 100644
--- a/tools/perf/arch/Build
+++ b/tools/perf/arch/Build
@@ -1,2 +1,2 @@
 libperf-y += common.o
-libperf-y += $(ARCH)/
+libperf-y += $(SRCARCH)/
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 9213a1273697..999a4e878162 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -2,7 +2,7 @@ hostprogs := jevents
 
 jevents-y       += json.o jsmn.o jevents.o
 pmu-events-y    += pmu-events.o
-JDIR            =  pmu-events/arch/$(ARCH)
+JDIR            =  pmu-events/arch/$(SRCARCH)
 JSON            =  $(shell [ -d $(JDIR) ] &&                            \
                         find $(JDIR) -name '*.json' -o -name 'mapfile.csv')
 #
@@ -10,4 +10,4 @@ JSON		=  $(shell [ -d $(JDIR) ] &&				\
 # directory and create tables in pmu-events.c.
 #
 $(OUTPUT)pmu-events/pmu-events.c: $(JSON) $(JEVENTS)
-        $(Q)$(call echo-cmd,gen)$(JEVENTS) $(ARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V)
+        $(Q)$(call echo-cmd,gen)$(JEVENTS) $(SRCARCH) pmu-events/arch $(OUTPUT)pmu-events/pmu-events.c $(V)
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index af58ebc243ef..84222bdb8689 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -75,7 +75,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B
         $(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
         $(Q)echo ';' >> $@
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc))
+ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 1f14e7612cbb..94b7c7b02bde 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,6 +229,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
         unsigned char buf2[BUFSZ];
         size_t ret_len;
         u64 objdump_addr;
+        const char *objdump_name;
+        char decomp_name[KMOD_DECOMP_LEN];
         int ret;
 
         pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -289,9 +291,25 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
                 state->done[state->done_cnt++] = al.map->start;
         }
 
+        objdump_name = al.map->dso->long_name;
+        if (dso__needs_decompress(al.map->dso)) {
+                if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
+                                                 decomp_name,
+                                                 sizeof(decomp_name)) < 0) {
+                        pr_debug("decompression failed\n");
+                        return -1;
+                }
+
+                objdump_name = decomp_name;
+        }
+
         /* Read the object code using objdump */
         objdump_addr = map__rip_2objdump(al.map, al.addr);
-        ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+        ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
+
+        if (dso__needs_decompress(al.map->dso))
+                unlink(objdump_name);
+
         if (ret > 0) {
                 /*
                  * The kernel maps are inaccurate - assume objdump is right in
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 32873ec91a4e..cf00ebad2ef5 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -83,7 +83,7 @@ int test__task_exit(int subtest __maybe_unused)
 
         evsel = perf_evlist__first(evlist);
         evsel->attr.task = 1;
-        evsel->attr.sample_freq = 0;
+        evsel->attr.sample_freq = 1;
         evsel->attr.inherit = 0;
         evsel->attr.watermark = 0;
         evsel->attr.wakeup_events = 1;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1367d7e35242..ddbd56df9187 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1321,6 +1321,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
         char linkname[PATH_MAX];
         char *build_id_filename;
         char *build_id_path = NULL;
+        char *pos;
 
         if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
             !dso__is_kcore(dso))
@@ -1340,7 +1341,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
         if (!build_id_path)
                 return -1;
 
-        dirname(build_id_path);
+        /*
+         * old style build-id cache has name of XX/XXXXXXX.. while
+         * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+         * extract the build-id part of dirname in the new style only.
+         */
+        pos = strrchr(build_id_path, '/');
+        if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+                dirname(build_id_path);
 
         if (dso__is_kcore(dso) ||
             readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
@@ -1423,31 +1431,10 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
                                 sizeof(symfs_filename));
                 }
         } else if (dso__needs_decompress(dso)) {
-                char tmp[PATH_MAX];
-                struct kmod_path m;
-                int fd;
-                bool ret;
-
-                if (kmod_path__parse_ext(&m, symfs_filename))
-                        goto out;
-
-                snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
-
-                fd = mkstemp(tmp);
-                if (fd < 0) {
-                        free(m.ext);
-                        goto out;
-                }
-
-                ret = decompress_to_file(m.ext, symfs_filename, fd);
-
-                if (ret)
-                        pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
-
-                free(m.ext);
-                close(fd);
+                char tmp[KMOD_DECOMP_LEN];
 
-                if (!ret)
+                if (dso__decompress_kmodule_path(dso, symfs_filename,
+                                                 tmp, sizeof(tmp)) < 0)
                         goto out;
 
                 strcpy(symfs_filename, tmp);
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 168cc49654e7..e0148b081bdf 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -278,51 +278,6 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
         return bf;
 }
 
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
-{
-        char *id_name = NULL, *ch;
-        struct stat sb;
-        char sbuild_id[SBUILD_ID_SIZE];
-
-        if (!dso->has_build_id)
-                goto err;
-
-        build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-        id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
-        if (!id_name)
-                goto err;
-        if (access(id_name, F_OK))
-                goto err;
-        if (lstat(id_name, &sb) == -1)
-                goto err;
-        if ((size_t)sb.st_size > size - 1)
-                goto err;
-        if (readlink(id_name, bf, size - 1) < 0)
-                goto err;
-
-        bf[sb.st_size] = '\0';
-
-        /*
-         * link should be:
-         * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
-         */
-        ch = strrchr(bf, '/');
-        if (!ch)
-                goto err;
-        if (ch - 3 < bf)
-                goto err;
-
-        free(id_name);
-        return strncmp(".ko", ch - 3, 3) == 0;
-err:
-        pr_err("Invalid build id: %s\n", id_name ? :
-                                         dso->long_name ? :
-                                         dso->short_name ? :
-                                         "[unknown]");
-        free(id_name);
-        return false;
-}
-
 #define dsos__for_each_with_build_id(pos, head) \
         list_for_each_entry(pos, head, node)    \
                 if (!pos->has_build_id)         \
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 8a89b195c1fc..96690a55c62c 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -17,7 +17,6 @@ char *build_id_cache__kallsyms_path(const char *sbuild_id, char *bf,
                                     size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
                            struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index b27d127cdf68..4e7ab611377a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -248,6 +248,64 @@ bool dso__needs_decompress(struct dso *dso)
                 dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+{
+        int fd = -1;
+        struct kmod_path m;
+
+        if (!dso__needs_decompress(dso))
+                return -1;
+
+        if (kmod_path__parse_ext(&m, dso->long_name))
+                return -1;
+
+        if (!m.comp)
+                goto out;
+
+        fd = mkstemp(tmpbuf);
+        if (fd < 0) {
+                dso->load_errno = errno;
+                goto out;
+        }
+
+        if (!decompress_to_file(m.ext, name, fd)) {
+                dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+                close(fd);
+                fd = -1;
+        }
+
+out:
+        free(m.ext);
+        return fd;
+}
+
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
+{
+        char tmpbuf[] = KMOD_DECOMP_NAME;
+        int fd;
+
+        fd = decompress_kmodule(dso, name, tmpbuf);
+        unlink(tmpbuf);
+        return fd;
+}
+
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+                                 char *pathname, size_t len)
+{
+        char tmpbuf[] = KMOD_DECOMP_NAME;
+        int fd;
+
+        fd = decompress_kmodule(dso, name, tmpbuf);
+        if (fd < 0) {
+                unlink(tmpbuf);
+                return -1;
+        }
+
+        strncpy(pathname, tmpbuf, len);
+        close(fd);
+        return 0;
+}
+
 /*
  * Parses kernel module specified in @path and updates
  * @m argument like:
@@ -396,7 +454,7 @@ static int do_open(char *name)
 
 static int __open_dso(struct dso *dso, struct machine *machine)
 {
-        int fd;
+        int fd = -EINVAL;
         char *root_dir = (char *)"";
         char *name = malloc(PATH_MAX);
 
@@ -407,15 +465,30 @@ static int __open_dso(struct dso *dso, struct machine *machine)
                 root_dir = machine->root_dir;
 
         if (dso__read_binary_type_filename(dso, dso->binary_type,
-                                            root_dir, name, PATH_MAX)) {
-                free(name);
-                return -EINVAL;
-        }
+                                            root_dir, name, PATH_MAX))
+                goto out;
 
         if (!is_regular_file(name))
-                return -EINVAL;
+                goto out;
+
+        if (dso__needs_decompress(dso)) {
+                char newpath[KMOD_DECOMP_LEN];
+                size_t len = sizeof(newpath);
+
+                if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
+                        fd = -dso->load_errno;
+                        goto out;
+                }
+
+                strcpy(name, newpath);
+        }
 
         fd = do_open(name);
+
+        if (dso__needs_decompress(dso))
+                unlink(name);
+
+out:
         free(name);
         return fd;
 }
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 5fe2ab5877bd..bd061ba7b47c 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -244,6 +244,12 @@ bool is_supported_compression(const char *ext);
 bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+                                 char *pathname, size_t len);
+
+#define KMOD_DECOMP_NAME  "/tmp/perf-kmod-XXXXXX"
+#define KMOD_DECOMP_LEN   sizeof(KMOD_DECOMP_NAME)
 
 struct kmod_path {
         char *name;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e4f7902d5afa..cda44b0e821c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -273,8 +273,20 @@ struct perf_evsel *perf_evsel__new_cycles(void)
         struct perf_evsel *evsel;
 
         event_attr_init(&attr);
+        /*
+         * Unnamed union member, not supported as struct member named
+         * initializer in older compilers such as gcc 4.4.7
+         *
+         * Just for probing the precise_ip:
+         */
+        attr.sample_period = 1;
 
         perf_event_attr__set_max_precise_ip(&attr);
+        /*
+         * Now let the usual logic to set up the perf_event_attr defaults
+         * to kick in when we return and before perf_evsel__open() is called.
+         */
+        attr.sample_period = 0;
 
         evsel = perf_evsel__new(&attr);
         if (evsel == NULL)
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 5cac8d5e009a..b5baff3007bb 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -841,7 +841,7 @@ static int write_group_desc(int fd, struct perf_header *h __maybe_unused,
 
 /*
  * default get_cpuid(): nothing gets recorded
- * actual implementation must be in arch/$(ARCH)/util/header.c
+ * actual implementation must be in arch/$(SRCARCH)/util/header.c
  */
 int __weak get_cpuid(char *buffer __maybe_unused, size_t sz __maybe_unused)
 {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9d92af7d0718..40de3cb40d21 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1219,7 +1219,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
         fprintf(ofp, "# be retrieved using Python functions of the form "
                 "common_*(context).\n");
 
-        fprintf(ofp, "# See the perf-trace-python Documentation for the list "
+        fprintf(ofp, "# See the perf-script-python Documentation for the list "
                 "of available functions.\n\n");
 
         fprintf(ofp, "import os\n");
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 1fb2efae4f02..502505cf236a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -637,40 +637,6 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
         return 0;
 }
 
-static int decompress_kmodule(struct dso *dso, const char *name,
-                              enum dso_binary_type type)
-{
-        int fd = -1;
-        char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
-        struct kmod_path m;
-
-        if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
-            type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
-            type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
-                return -1;
-
-        if (kmod_path__parse_ext(&m, dso->long_name) || !m.comp)
-                return -1;
-
-        fd = mkstemp(tmpbuf);
-        if (fd < 0) {
-                dso->load_errno = errno;
-                goto out;
-        }
-
-        if (!decompress_to_file(m.ext, name, fd)) {
-                dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
-                close(fd);
-                fd = -1;
-        }
-
-        unlink(tmpbuf);
-
-out:
-        free(m.ext);
-        return fd;
-}
-
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
         return ss->dynsym || ss->opdsec;
@@ -702,9 +668,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
         int fd;
 
         if (dso__needs_decompress(dso)) {
-                fd = decompress_kmodule(dso, name, type);
+                fd = dso__decompress_kmodule_fd(dso, name);
                 if (fd < 0)
                         return -1;
+
+                type = dso->symtab_type;
         } else {
                 fd = open(name, O_RDONLY);
                 if (fd < 0) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8f2b068ff756..e7a98dbd2aed 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1562,10 +1562,6 @@ int dso__load(struct dso *dso, struct map *map)
         if (!runtime_ss && syms_ss)
                 runtime_ss = syms_ss;
 
-        if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-                if (dso__build_id_is_kmod(dso, name, PATH_MAX))
-                        kmod = true;
-
         if (syms_ss)
                 ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
         else
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index da45c4be5fb3..7755a5e0fe5e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -178,6 +178,14 @@ frame_callback(Dwfl_Frame *state, void *arg)
         Dwarf_Addr pc;
         bool isactivation;
 
+        if (!dwfl_frame_pc(state, &pc, NULL)) {
+                pr_err("%s", dwfl_errmsg(-1));
+                return DWARF_CB_ABORT;
+        }
+
+        // report the module before we query for isactivation
+        report_module(pc, ui);
+
         if (!dwfl_frame_pc(state, &pc, &isactivation)) {
                 pr_err("%s", dwfl_errmsg(-1));
                 return DWARF_CB_ABORT;