diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c9412dee17daabc1cb131bb517ad431207..6c4e523dc1e2e6b53d44bf6a540bc168bcde1eca 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7316,6 +7316,21 @@ int perf_event_account_interrupt(struct perf_event *event)
 	return __perf_event_account_interrupt(event, 1);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7336,6 +7351,12 @@ static int __perf_event_overflow(struct perf_event *event,
 
 	ret = __perf_event_account_interrupt(event, throttle);
 
+	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
 	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index e6c9902c6d82b0e2535059c1a915356e84856589..165c2b1d43177b7df8870d85d7911a1a615ce7e7 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 dfbb506d2c349744399637c78148fe6446b124bc..142606c0ec9c1dcbb9329f23cb9b9bc65085c419 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 54acba22155865a8fafc7629b9e3987c061fed47..51ec2d20068ad5df7b0a00a0983b5ec08d49979a 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/arch/common.c b/tools/perf/arch/common.c
index 837067f48a4c54a88b883e8de6dc95df0dd5b3d0..6b40e9f017404f87877668645f7afa8f28649788 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -26,6 +26,7 @@ const char *const arm64_triplets[] = {
 
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
+	"powerpc-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
 	"powerpc64-linux-gnu-",
 	"powerpc64le-linux-gnu-",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a935b502373253217d6f43680e6b88a6ab143bfe..ad9324d1daf9f29a990a0d8f903563873ac91ef9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1578,6 +1578,7 @@ static void print_header(int argc, const char **argv)
 static void print_footer(void)
 {
 	FILE *output = stat_config.output;
+	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
@@ -1590,7 +1591,9 @@ static void print_footer(void)
 	}
 	fprintf(output, "\n\n");
 
-	if (print_free_counters_hint)
+	if (print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d014350adc526722da3a12f29421cd6d3c00f4af..4b2a5d2981970baf86e4e458ef4ced256fc98c0e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -681,6 +681,10 @@ static struct syscall_fmt {
 	{ .name	    = "mlockall",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mmap",	    .hexret = true,
+/* The standard mmap maps to old_mmap on s390x */
+#if defined(__s390x__)
+	.alias = "old_mmap",
+#endif
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
 			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index e7664fe3bd33739fd92be2579c30102e481e8f03..8ba2c4618fe90231d1157e8218bf10a2cb82f6a0 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -288,3 +288,17 @@ int test__bp_signal(int subtest __maybe_unused)
 	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
+
+bool test__bp_signal_is_supported(void)
+{
+/*
+ * The powerpc so far does not have support to even create
+ * instruction breakpoint using the perf event interface.
+ * Once it's there we can release this.
+ */
+#ifdef __powerpc__
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 9e08d297f1a905f57554bf6fd7b9555e980ad10a..3ccfd58a8c3cf3e8b16cc513a67324b8f11eae7b 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -97,10 +97,12 @@ static struct test generic_tests[] = {
 	{
 		.desc = "Breakpoint overflow signal handler",
 		.func = test__bp_signal,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Breakpoint overflow sampling",
 		.func = test__bp_signal_overflow,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",
@@ -401,6 +403,11 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		if (!perf_test__matches(t, curr, argc, argv))
 			continue;
 
+		if (t->is_supported && !t->is_supported()) {
+			pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
+			continue;
+		}
+
 		pr_info("%2d: %-*s:", i, width, t->desc);
 
 		if (intlist__find(skiplist, i)) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 1f14e7612cbb1615e993c73758a3c9ac7024a0e1..94b7c7b02bdefbb33f2987677c11b3577ab062ec 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/tests.h b/tools/perf/tests/tests.h
index 6318596294032602b2858acf42c2aa80993fdac9..577363809c9b1b54731f7e80b291278bf2764e78 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -34,6 +34,7 @@ struct test {
 		int (*get_nr)(void);
 		const char *(*get_desc)(int subtest);
 	} subtest;
+	bool (*is_supported)(void);
 };
 
 /* Tests */
@@ -99,6 +100,8 @@ const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(int subtest);
 
+bool test__bp_signal_is_supported(void);
+
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 683f8340460c1777f82f35860b3bb581a07f222a..ddbd56df91878884a4de5da2a29aae991e0689a0 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -239,10 +239,20 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 	const char *s = strchr(ops->raw, '+');
 	const char *c = strchr(ops->raw, ',');
 
-	if (c++ != NULL)
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
 		ops->target.addr = strtoull(c, NULL, 16);
-	else
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
 		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
 
 	if (s++ != NULL) {
 		ops->target.offset = strtoull(s, NULL, 16);
@@ -257,10 +267,27 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
+	const char *c = strchr(ops->raw, ',');
+
 	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
 }
 
 static struct ins_ops jump_ops = {
@@ -1294,6 +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))
@@ -1313,7 +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 ||
@@ -1396,31 +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);
@@ -1429,7 +1443,7 @@ int symbol__disassemble(struct symbol *sym, struct map *map, const char *arch_na
 	snprintf(command, sizeof(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 \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 168cc49654e7a4b18f69d177e29373f8a13e3471..e0148b081bdfbb7cead2c118a51ca81bd238e740 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 8a89b195c1fc3a5c36d7ca260dafe9c6b3fa8262..96690a55c62c40394444a8f23df1cd03b840acfe 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 a96a99d2369f800634025bcdfa9838d1d6bc9d97..4e7ab611377acd56c1be78cbd983058e5ce5142b 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:
@@ -335,6 +393,21 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 	return 0;
 }
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine)
+{
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (m->kmod && m->comp)
+		dso->symtab_type++;
+
+	dso__set_short_name(dso, strdup(m->name), true);
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
@@ -381,7 +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);
 
@@ -392,15 +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 12350b17172730adf0dffdf324cb9e0b4a4be2ba..bd061ba7b47cc8eab2ff05e4027dc22990d7c7ef 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;
@@ -259,6 +265,9 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false)
 #define kmod_path__parse_ext(__m, __p)  __kmod_path__parse(__m, __p, false, true)
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine);
+
 /*
  * The dso__data_* external interface provides following functions:
  *   dso__data_get_fd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 314a07151fb772377752dae62658b79ffdc87cd6..5cac8d5e009a88ff096d9e2f8026e39e8567c595 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1469,8 +1469,16 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename, cpumode))
-			dso->kernel = dso_type;
+		if (dso_type != DSO_TYPE_USER) {
+			struct kmod_path m = { .name = NULL, };
+
+			if (!kmod_path__parse_name(&m, filename) && m.kmod)
+				dso__set_module_info(dso, &m, machine);
+			else
+				dso->kernel = dso_type;
+
+			free(m.name);
+		}
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index d97e014c3df395e51e61da31f9624e12927a43b2..d7f31cb0a4cbeb41e6c02d58323a8848ff82cfc4 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -572,16 +572,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 		if (dso == NULL)
 			goto out_unlock;
 
-		if (machine__is_host(machine))
-			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
-		else
-			dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-
-		/* _KMODULE_COMP should be next to _KMODULE */
-		if (m->kmod && m->comp)
-			dso->symtab_type++;
-
-		dso__set_short_name(dso, strdup(m->name), true);
+		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9d92af7d07182e662b1a6d7ad5e66c0147a78234..40de3cb40d2100fe918f26795ae29ae702d62665 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 e7ee47f7377ab17bbb414be4240cf01565ae863a..502505cf236af30226b22ff82878098060f19862 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -637,43 +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 (type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		name = dso->long_name;
-
-	if (kmod_path__parse_ext(&m, 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;
@@ -705,9 +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 8f2b068ff7564900c989d1cdec96757c1b3ab45b..e7a98dbd2aed9133d99f38b71b3cac9fb297e0d6 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 943a06291587b064c3649569dd85b356805a7fab..da45c4be5fb3e77ee59131602667b4d675bc3a40 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -39,6 +39,14 @@ static int __report_module(struct addr_location *al, u64 ip,
 		return 0;
 
 	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (mod) {
+		Dwarf_Addr s;
+
+		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+		if (s != al->map->start)
+			mod = 0;
+	}
+
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
 				      dso->long_name, -1, al->map->start,
@@ -224,7 +232,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 
 	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui->max_stack)
+	if (err && ui->max_stack != max_stack)
 		err = 0;
 
 	/*