22 files changed, 149 insertions, 96 deletions

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f3bf9297bcc0..1bd64e7404b9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -553,9 +553,16 @@ ifndef NO_LIBELF
         ifeq ($(feature-libbpf), 1)
           EXTLIBS += -lbpf
           $(call detected,CONFIG_LIBBPF_DYNAMIC)
+
+          $(call feature_check,libbpf-btf__load_from_kernel_by_id)
+          ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1)
+            CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+          endif
         else
           dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
         endif
+      else
+	CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
       endif
     endif
 
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index af4d63af8072..e8b577d33e53 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
+	u64 bit;
 
 	sper->evlist = evlist;
 
@@ -245,6 +246,15 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 */
 	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
 
+	/*
+	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+	 * inform that the resulting output's SPE samples contain physical addresses
+	 * where applicable.
+	 */
+	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
+	if (arm_spe_evsel->core.attr.config & bit)
+		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
+
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
 	if (err)
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index d2ce31e28cd7..41c1596e5207 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -8,27 +8,6 @@
 #include "callchain.h"
 #include "record.h"
 
-/* On arm64, kernel text segment starts at high memory address,
- * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
- * address, like 0xffff 0000 00ax xxxx. When only small amount of
- * memory is used by modules, gap between end of module's text segment
- * and start of kernel text segment may reach 2G.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-#define SYMBOL_LIMIT (1 << 12) /* 4K */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
-			(strchr(p->name, '[') == NULL && strchr(c->name, '[')))
-		/* Limit range of last symbol in module and kernel */
-		p->end += SYMBOL_LIMIT;
-	else
-		p->end = c->start;
-	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
-
 void arch__add_leaf_frame_record_opts(struct record_opts *opts)
 {
 	opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 8a79c4126e5b..0115f3166568 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,4 @@
 perf-y += header.o
-perf-y += machine.o
 perf-y += kvm-stat.o
 perf-y += perf_regs.o
 perf-y += mem-events.o
diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c
deleted file mode 100644
index e652a1aa8132..000000000000
--- a/tools/perf/arch/powerpc/util/machine.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <string.h>
-#include <internal/lib.h> // page_size
-#include "debug.h"
-#include "symbol.h"
-
-/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000
- * whereas the modules are located at very high memory addresses,
- * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very high.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
-		/* Limit the range of last kernel symbol */
-		p->end += page_size;
-	else
-		p->end = c->start;
-	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index 7644a4f6d4a4..98bc3f39d5f3 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
 
 	return 0;
 }
-
-/* On s390 kernel text segment start is located at very low memory addresses,
- * for example 0x10000. Modules are located at very high memory addresses,
- * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very big.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
-		/* Last kernel symbol mapped to end of page */
-		p->end = roundup(p->end, page_size);
-	else
-		p->end = c->start;
-	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 207c56805c55..0ed177991ad0 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -9,6 +9,8 @@
 #include "../../../util/perf_regs.h"
 #include "../../../util/debug.h"
 #include "../../../util/event.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmu-hybrid.h"
 
 const struct sample_reg sample_reg_masks[] = {
 	SMPL_REG(AX, PERF_REG_X86_AX),
@@ -284,12 +286,22 @@ uint64_t arch__intr_reg_mask(void)
 		.disabled 		= 1,
 		.exclude_kernel		= 1,
 	};
+	struct perf_pmu *pmu;
 	int fd;
 	/*
 	 * In an unnamed union, init it here to build on older gcc versions
 	 */
 	attr.sample_period = 1;
 
+	if (perf_pmu__has_hybrid()) {
+		/*
+		 * The same register set is supported among different hybrid PMUs.
+		 * Only check the first available one.
+		 */
+		pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list);
+		attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+	}
+
 	event_attr_init(&attr);
 
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 44e1f8a44087..20eed1e53f80 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -311,6 +311,7 @@ err_out:
 
 	/* BUG_ON due to failure in allocation of orig_mask/mask */
 	BUG_ON(-1);
+	return NULL;
 }
 
 static cpu_set_t *bind_to_node(int target_node)
@@ -364,6 +365,7 @@ err_out:
 
 	/* BUG_ON due to failure in allocation of orig_mask/mask */
 	BUG_ON(-1);
+	return NULL;
 }
 
 static void bind_to_cpumask(cpu_set_t *mask)
@@ -1738,7 +1740,7 @@ static int __bench_numa(const char *name)
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
 	if (g->p.show_details >= 2) {
-		char tname[14 + 2 * 10 + 1];
+		char tname[14 + 2 * 11 + 1];
 		struct thread_data *td;
 		for (p = 0; p < g->p.nr_proc; p++) {
 			for (t = 0; t < g->p.nr_threads; t++) {
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 454505d343fa..eb3f7d4bb324 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -60,6 +60,7 @@ Following tests are defined (with perf commands):
   perf record -R kill                           (test-record-raw)
   perf record -c 2 -e arm_spe_0// -- kill       (test-record-spe-period)
   perf record -e arm_spe_0/period=3/ -- kill    (test-record-spe-period-term)
+  perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address)
   perf stat -e cycles kill                      (test-stat-basic)
   perf stat kill                                (test-stat-default)
   perf stat -d kill                             (test-stat-detailed-1)
diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address
new file mode 100644
index 000000000000..7ebcf5012ce3
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-spe-physical-address
@@ -0,0 +1,12 @@
+[config]
+command = record
+args    = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1
+ret     = 1
+arch    = aarch64
+
+[event-10:base-record-spe]
+# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR
+sample_type=622727
+
+# dummy event
+[event-1:base-record-spe]
\ No newline at end of file
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 57b9591f7cbb..17c023823713 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -222,11 +222,11 @@ static int __test__bpf(int idx)
 
 	ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
 				       bpf_testcase_table[idx].prog_id,
-				       true, NULL);
+				       false, NULL);
 	if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
 		pr_debug("Unable to get BPF object, %s\n",
 			 bpf_testcase_table[idx].msg_compile_fail);
-		if (idx == 0)
+		if ((idx == 0) || (ret == TEST_SKIP))
 			return TEST_SKIP;
 		else
 			return TEST_FAIL;
@@ -364,9 +364,11 @@ static int test__bpf_prologue_test(struct test_suite *test __maybe_unused,
 static struct test_case bpf_tests[] = {
 #ifdef HAVE_LIBBPF_SUPPORT
 	TEST_CASE("Basic BPF filtering", basic_bpf_test),
-	TEST_CASE("BPF pinning", bpf_pinning),
+	TEST_CASE_REASON("BPF pinning", bpf_pinning,
+			"clang isn't installed or environment missing BPF support"),
 #ifdef HAVE_BPF_PROLOGUE
-	TEST_CASE("BPF prologue generation", bpf_prologue_test),
+	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test,
+			"clang isn't installed or environment missing BPF support"),
 #else
 	TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"),
 #endif
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index fac3717d9ba1..d336cda94a11 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -279,6 +279,7 @@ static const char *shell_test__description(char *description, size_t size,
 {
 	FILE *fp;
 	char filename[PATH_MAX];
+	int ch;
 
 	path__join(filename, sizeof(filename), path, name);
 	fp = fopen(filename, "r");
@@ -286,7 +287,9 @@ static const char *shell_test__description(char *description, size_t size,
 		return NULL;
 
 	/* Skip shebang */
-	while (fgetc(fp) != '\n');
+	do {
+		ch = fgetc(fp);
+	} while (ch != EOF && ch != '\n');
 
 	description = fgets(description, size, fp);
 	fclose(fp);
@@ -417,7 +420,8 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
 			.priv = &st,
 		};
 
-		if (!perf_test__matches(test_suite.desc, curr, argc, argv))
+		if (test_suite.desc == NULL ||
+		    !perf_test__matches(test_suite.desc, curr, argc, argv))
 			continue;
 
 		st.file = ent->d_name;
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index b30dba455f36..9c9ef33e0b3c 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -5,6 +5,16 @@
 set -e
 
 for p in $(perf list --raw-dump pmu); do
+  # In powerpc, skip the events for hv_24x7 and hv_gpci.
+  # These events needs input values to be filled in for
+  # core, chip, partition id based on system.
+  # Example: hv_24x7/CPM_ADJUNCT_INST,domain=?,core=?/
+  # hv_gpci/event,partition_id=?/
+  # Hence skip these events for ppc.
+  if echo "$p" |grep -Eq 'hv_24x7|hv_gpci' ; then
+    echo "Skipping: Event '$p' in powerpc"
+    continue
+  fi
   echo "Testing $p"
   result=$(perf stat -e "$p" true 2>&1)
   if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 6de53b7ef5ff..e4cb4f1806ff 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -29,7 +29,6 @@ cleanup_files()
 	rm -f ${file}
 	rm -f "${perfdata}.old"
 	trap - exit term int
-	kill -2 $$
 	exit $glb_err
 }
 
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index ee1e3dcbc0bd..d23a9e322ff5 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -109,6 +109,17 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 			&& strncmp(session->header.env.arch, "aarch64", 7))
 		return TEST_SKIP;
 
+	/*
+	 * In powerpc pSeries platform, not all the topology information
+	 * are exposed via sysfs. Due to restriction, detail like
+	 * physical_package_id will be set to -1. Hence skip this
+	 * test if physical_package_id returns -1 for cpu from perf_cpu_map.
+	 */
+	if (strncmp(session->header.env.arch, "powerpc", 7)) {
+		if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1)
+			return TEST_SKIP;
+	}
+
 	TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
 
 	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index d2b64e3f588b..1a80151baed9 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.size = sizeof(struct perf_event_attr);
 	attr.type = PERF_TYPE_HARDWARE;
-	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type = evsel->core.attr.sample_type &
+				(PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
 			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
-			    PERF_SAMPLE_WEIGHT;
+			    PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
 	if (spe->timeless_decoding)
 		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
 	else
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 94624733af7e..8271ab764eb5 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -22,7 +22,8 @@
 #include "record.h"
 #include "util/synthetic-events.h"
 
-struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
+#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+struct btf *btf__load_from_kernel_by_id(__u32 id)
 {
        struct btf *btf;
 #pragma GCC diagnostic push
@@ -32,6 +33,7 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
 
        return err ? ERR_PTR(err) : btf;
 }
+#endif
 
 int __weak bpf_prog_load(enum bpf_prog_type prog_type,
 			 const char *prog_name __maybe_unused,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 45a30040ec8d..a7f93f5a1ac8 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 	struct branch_entry *entries = perf_sample__branch_entries(sample);
 	uint64_t i;
 
-	printf("%s: nr:%" PRIu64 "\n",
-		!callstack ? "... branch stack" : "... branch callstack",
-		sample->branch_stack->nr);
+	if (!callstack) {
+		printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+	} else {
+		/* the reason of adding 1 to nr is because after expanding
+		 * branch stack it generates nr + 1 callstack records. e.g.,
+		 *         B()->C()
+		 *         A()->B()
+		 * the final callstack should be:
+		 *         C()
+		 *         B()
+		 *         A()
+		 */
+		printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+	}
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &entries[i];
@@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 				(unsigned)e->flags.reserved,
 				e->flags.type ? branch_type_name(e->flags.type) : "");
 		} else {
-			printf("..... %2"PRIu64": %016" PRIx64 "\n",
-				i, i > 0 ? e->from : e->to);
+			if (i == 0) {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n"
+				       "..... %2"PRIu64": %016" PRIx64 "\n",
+						i, e->to, i+1, e->from);
+			} else {
+				printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+			}
 		}
 	}
 }
@@ -2576,7 +2592,7 @@ int perf_session__process_events(struct perf_session *session)
 	if (perf_data__is_pipe(session->data))
 		return __perf_session__process_pipe_events(session);
 
-	if (perf_data__is_dir(session->data))
+	if (perf_data__is_dir(session->data) && session->data->dir.nr)
 		return __perf_session__process_dir_events(session);
 
 	return __perf_session__process_events(session);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 817a2de264b4..c1af37e11f98 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -472,9 +472,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
 int perf_event__process_stat_event(struct perf_session *session,
 				   union perf_event *event)
 {
-	struct perf_counts_values count;
+	struct perf_counts_values count, *ptr;
 	struct perf_record_stat *st = &event->stat;
 	struct evsel *counter;
+	int cpu_map_idx;
 
 	count.val = st->val;
 	count.ena = st->ena;
@@ -485,8 +486,18 @@ int perf_event__process_stat_event(struct perf_session *session,
 		pr_err("Failed to resolve counter for stat event.\n");
 		return -EINVAL;
 	}
-
-	*perf_counts(counter->counts, st->cpu, st->thread) = count;
+	cpu_map_idx = perf_cpu_map__idx(evsel__cpus(counter), (struct perf_cpu){.cpu = st->cpu});
+	if (cpu_map_idx == -1) {
+		pr_err("Invalid CPU %d for event %s.\n", st->cpu, evsel__name(counter));
+		return -EINVAL;
+	}
+	ptr = perf_counts(counter->counts, cpu_map_idx, st->thread);
+	if (ptr == NULL) {
+		pr_err("Failed to find perf count for CPU %d thread %d on event %s.\n",
+			st->cpu, st->thread, evsel__name(counter));
+		return -EINVAL;
+	}
+	*ptr = count;
 	counter->supported = true;
 	return 0;
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 31cd59a2b66e..ecd377938eea 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&dso->symbols);
+		symbols__fixup_end(&dso->symbols, false);
 		symbols__fixup_duplicate(&dso->symbols);
 		if (kmap) {
 			/*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dea0fc495185..f72baf636724 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
-void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
-	p->end = c->start;
-}
-
 const char * __weak arch__normalize_symbol_name(const char *name)
 {
 	return name;
@@ -217,7 +212,8 @@ again:
 	}
 }
 
-void symbols__fixup_end(struct rb_root_cached *symbols)
+/* Update zero-sized symbols using the address of the next symbol */
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
 {
 	struct rb_node *nd, *prevnd = rb_first_cached(symbols);
 	struct symbol *curr, *prev;
@@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
 		prev = curr;
 		curr = rb_entry(nd, struct symbol, rb_node);
 
-		if (prev->end == prev->start || prev->end != curr->start)
-			arch__symbols__fixup_end(prev, curr);
+		/*
+		 * On some architecture kernel text segment start is located at
+		 * some low memory address, while modules are located at high
+		 * memory addresses (or vice versa).  The gap between end of
+		 * kernel text segment and beginning of first module's text
+		 * segment is very big.  Therefore do not fill this gap and do
+		 * not assign it to the kernel dso map (kallsyms).
+		 *
+		 * In kallsyms, it determines module symbols using '[' character
+		 * like in:
+		 *   ffffffffc1937000 T hdmi_driver_init  [snd_hda_codec_hdmi]
+		 */
+		if (prev->end == prev->start) {
+			/* Last kernel/module symbol mapped to end of page */
+			if (is_kallsyms && (!strchr(prev->name, '[') !=
+					    !strchr(curr->name, '[')))
+				prev->end = roundup(prev->end + 4096, 4096);
+			else
+				prev->end = curr->start;
+
+			pr_debug4("%s sym:%s end:%#" PRIx64 "\n",
+				  __func__, prev->name, prev->end);
+		}
 	}
 
 	/* Last entry */
@@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (kallsyms__delta(kmap, filename, &delta))
 		return -1;
 
-	symbols__fixup_end(&dso->symbols);
+	symbols__fixup_end(&dso->symbols, true);
 	symbols__fixup_duplicate(&dso->symbols);
 
 	if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
@@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
 #undef bfd_asymbol_section
 #endif
 
-	symbols__fixup_end(&dso->symbols);
+	symbols__fixup_end(&dso->symbols, false);
 	symbols__fixup_duplicate(&dso->symbols);
 	dso->adjust_symbols = 1;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fbf866d82dcc..0b893dcc8ea6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
 		       bool kernel);
 void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root_cached *symbols);
-void symbols__fixup_end(struct rb_root_cached *symbols);
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms);
 void maps__fixup_end(struct maps *maps);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
@@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name);
 #define SYMBOL_A 0
 #define SYMBOL_B 1
 
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
 int arch__compare_symbol_names(const char *namea, const char *nameb);
 int arch__compare_symbol_names_n(const char *namea, const char *nameb,
 				 unsigned int n);