Merge branch 'i2c/for-current' into i2c/for-5.11

27 files changed, 145 insertions, 54 deletions

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6890fc4b063a..ce8516e4de34 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -749,6 +749,7 @@ else
   PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
   PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
   PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+  PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
   PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
   FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 347809649ba2..379819244b91 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -361,12 +361,13 @@
 437	common	openat2			sys_openat2
 438	common	pidfd_getfd		sys_pidfd_getfd
 439	common	faccessat2		sys_faccessat2
+440	common	process_madvise		sys_process_madvise
 
 #
-# x32-specific system call numbers start at 512 to avoid cache impact
-# for native 64-bit operation. The __x32_compat_sys stubs are created
-# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
-# is defined.
+# Due to a historical design error, certain syscalls are numbered differently
+# in x32 as compared to native x86_64.  These syscalls have numbers 512-547.
+# Do not add new syscalls to this range.  Numbers 548 and above are available
+# for non-x32 use.
 #
 512	x32	rt_sigaction		compat_sys_rt_sigaction
 513	x32	rt_sigreturn		compat_sys_x32_rt_sigreturn
@@ -404,3 +405,5 @@
 545	x32	execveat		compat_sys_execveat
 546	x32	preadv2			compat_sys_preadv64v2
 547	x32	pwritev2		compat_sys_pwritev64v2
+# This is the end of the legacy x32 range.  Numbers 548 and above are
+# not special and are not to be used for x32-specific syscalls.
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 4e40402a4f81..478078fb0f22 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -38,6 +38,13 @@ static int sample_ustack(struct perf_sample *sample,
 	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
 
 	memcpy(buf, (void *) sp, stack_size);
+#ifdef MEMORY_SANITIZER
+	/*
+	 * Copying the stack may copy msan poison, avoid false positives in the
+	 * unwinder by removing the poison here.
+	 */
+	__msan_unpoison(buf, stack_size);
+#endif
 	stack->data = (char *) buf;
 	stack->size = stack_size;
 	return 0;
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 9ad015a1e202..6eb45a2aa8db 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -2,6 +2,9 @@
 
 /* Various wrappers to make the kernel .S file build in user-space: */
 
+// memcpy_orig and memcpy_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name)                      \
+        SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #define memcpy MEMCPY /* don't hide glibc's memcpy() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index d550bd526162..6f093c483842 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -1,4 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+// memset_orig and memset_erms are being defined as SYM_L_LOCAL but we need it
+#define SYM_FUNC_START_LOCAL(name)                      \
+        SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #define memset MEMSET /* don't hide glibc's memset() */
 #define altinstr_replacement text
 #define globl p2align 4; .globl
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 584e2e1a3793..cefc71506409 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1222,8 +1222,10 @@ static int __cmd_diff(void)
 		if (compute == COMPUTE_STREAM) {
 			d->evlist_streams = evlist__create_streams(
 						d->session->evlist, 5);
-			if (!d->evlist_streams)
+			if (!d->evlist_streams) {
+				ret = -ENOMEM;
 				goto out_delete;
+			}
 		}
 	}
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 452a75fe68e5..0462dc8db2e3 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -779,25 +779,15 @@ static int __cmd_inject(struct perf_inject *inject)
 			dsos__hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
-		 * synthesized hardware events, so clear the feature flag and
-		 * remove the evsel.
+		 * synthesized hardware events, so clear the feature flag.
 		 */
 		if (inject->itrace_synth_opts.set) {
-			struct evsel *evsel;
-
 			perf_header__clear_feat(&session->header,
 						HEADER_AUXTRACE);
 			if (inject->itrace_synth_opts.last_branch ||
 			    inject->itrace_synth_opts.add_last_branch)
 				perf_header__set_feat(&session->header,
 						      HEADER_BRANCH_STACK);
-			evsel = perf_evlist__id2evsel_strict(session->evlist,
-							     inject->aux_id);
-			if (evsel) {
-				pr_debug("Deleting %s\n", evsel__name(evsel));
-				evlist__remove(session->evlist, evsel);
-				evsel__delete(evsel);
-			}
 		}
 		session->header.data_offset = output_data_offset;
 		session->header.data_size = inject->bytes_written;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index f0a1dbacb46c..a2f1e53f37a7 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -406,7 +406,7 @@ static int report_lock_acquire_event(struct evsel *evsel,
 	struct lock_seq_stat *seq;
 	const char *name = evsel__strval(evsel, sample, "name");
 	u64 tmp	 = evsel__intval(evsel, sample, "lockdep_addr");
-	int flag = evsel__intval(evsel, sample, "flag");
+	int flag = evsel__intval(evsel, sample, "flags");
 
 	memcpy(&addr, &tmp, sizeof(void *));
 
@@ -621,7 +621,7 @@ static int report_lock_release_event(struct evsel *evsel,
 	case SEQ_STATE_READ_ACQUIRED:
 		seq->read_count--;
 		BUG_ON(seq->read_count < 0);
-		if (!seq->read_count) {
+		if (seq->read_count) {
 			ls->nr_release++;
 			goto end;
 		}
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 44a75f234db1..de80534473af 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -4639,9 +4639,9 @@ do_concat:
 	err = 0;
 
 	if (lists[0]) {
-		struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
-					       "event selector. use 'perf list' to list available events",
-					       parse_events_option);
+		struct option o = {
+			.value = &trace->evlist,
+		};
 		err = parse_events_option(&o, lists[0], 0);
 	}
 out:
@@ -4655,9 +4655,12 @@ static int trace__parse_cgroups(const struct option *opt, const char *str, int u
 {
 	struct trace *trace = opt->value;
 
-	if (!list_empty(&trace->evlist->core.entries))
-		return parse_cgroups(opt, str, unset);
-
+	if (!list_empty(&trace->evlist->core.entries)) {
+		struct option o = {
+			.value = &trace->evlist,
+		};
+		return parse_cgroups(&o, str, unset);
+	}
 	trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
 
 	return 0;
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index de3193552277..00f4fcffa815 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -329,7 +329,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
         "MetricGroup": "Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index f31794d3b926..0dd8b13b5cfb 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -323,7 +323,7 @@
     },
     {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "MetricExpr": "( ( ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) * 1048576 ) / 1000000000 ) / duration_time",
         "MetricGroup": "Memory_BW;SoC",
         "MetricName": "DRAM_BW_Use"
     },
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2491d167bf76..83638097c3bc 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -95,7 +95,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-__no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -126,7 +126,7 @@ __no_tail_call noinline int test_dwarf_unwind__thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-__no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -145,7 +145,7 @@ __no_tail_call noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 	return p1 - p2;
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -164,12 +164,12 @@ __no_tail_call noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 	return global_unwind_retval;
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
 	return test_dwarf_unwind__krava_3(thread);
 }
 
-__no_tail_call noinline int test_dwarf_unwind__krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
 	return test_dwarf_unwind__krava_2(thread);
 }
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 8d84fdbed6a6..18fde2f179cd 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -44,7 +44,7 @@ perf_script_branch_samples() {
 	#   touch  6512          1         branches:u:      ffffb22082e0 strcmp+0xa0 (/lib/aarch64-linux-gnu/ld-2.27.so)
 	#   touch  6512          1         branches:u:      ffffb2208320 strcmp+0xe0 (/lib/aarch64-linux-gnu/ld-2.27.so)
 	perf script -F,-time -i ${perfdata} | \
-		egrep " +$1 +[0-9]+ .* +branches:([u|k]:)? +"
+		egrep " +$1 +[0-9]+ .* +branches:(.*:)? +"
 }
 
 perf_report_branch_samples() {
@@ -105,7 +105,7 @@ arm_cs_iterate_devices() {
 		#     `> device_name = 'tmc_etf0'
 		device_name=$(basename $path)
 
-		if is_device_sink $path $devce_name; then
+		if is_device_sink $path $device_name; then
 
 			record_touch_file $device_name $2 &&
 			perf_script_branch_samples touch &&
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a07626f07208..b0e1880cf992 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2963,7 +2963,7 @@ static int perf_evsel__hists_browse(struct evsel *evsel, int nr_events,
 	struct popup_action actions[MAX_OPTIONS];
 	int nr_options = 0;
 	int key = -1;
-	char buf[64];
+	char buf[128];
 	int delay_secs = hbt ? hbt->refresh : 0;
 
 #define HIST_BROWSER_HELP_COMMON					\
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 8763772f1095..6b410c3d52dc 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -102,6 +102,8 @@ int build_id__sprintf(const struct build_id *build_id, char *bf)
 	const u8 *raw = build_id->data;
 	size_t i;
 
+	bf[0] = 0x0;
+
 	for (i = 0; i < build_id->size; ++i) {
 		sprintf(bid, "%02x", *raw);
 		++raw;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index aa898014ad12..7b2d471a6419 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -356,9 +356,25 @@ bool die_is_signed_type(Dwarf_Die *tp_die)
 bool die_is_func_def(Dwarf_Die *dw_die)
 {
 	Dwarf_Attribute attr;
+	Dwarf_Addr addr = 0;
+
+	if (dwarf_tag(dw_die) != DW_TAG_subprogram)
+		return false;
+
+	if (dwarf_attr(dw_die, DW_AT_declaration, &attr))
+		return false;
 
-	return (dwarf_tag(dw_die) == DW_TAG_subprogram &&
-		dwarf_attr(dw_die, DW_AT_declaration, &attr) == NULL);
+	/*
+	 * DW_AT_declaration can be lost from function declaration
+	 * by gcc's bug #97060.
+	 * So we need to check this subprogram DIE has DW_AT_inline
+	 * or an entry address.
+	 */
+	if (!dwarf_attr(dw_die, DW_AT_inline, &attr) &&
+	    die_entrypc(dw_die, &addr) < 0)
+		return false;
+
+	return true;
 }
 
 /**
@@ -373,6 +389,7 @@ bool die_is_func_def(Dwarf_Die *dw_die)
 int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr)
 {
 	Dwarf_Addr base, end;
+	Dwarf_Attribute attr;
 
 	if (!addr)
 		return -EINVAL;
@@ -380,6 +397,13 @@ int die_entrypc(Dwarf_Die *dw_die, Dwarf_Addr *addr)
 	if (dwarf_entrypc(dw_die, addr) == 0)
 		return 0;
 
+	/*
+	 *  Since the dwarf_ranges() will return 0 if there is no
+	 * DW_AT_ranges attribute, we should check it first.
+	 */
+	if (!dwarf_attr(dw_die, DW_AT_ranges, &attr))
+		return -ENOENT;
+
 	return dwarf_ranges(dw_die, 0, &base, addr, &end) < 0 ? -ENOENT : 0;
 }
 
diff --git a/tools/perf/util/hashmap.c b/tools/perf/util/hashmap.c
index a405dad068f5..3c20b126d60d 100644
--- a/tools/perf/util/hashmap.c
+++ b/tools/perf/util/hashmap.c
@@ -15,6 +15,9 @@
 /* make sure libbpf doesn't use kernel-only integer typedefs */
 #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
 
+/* prevent accidental re-addition of reallocarray() */
+#pragma GCC poison reallocarray
+
 /* start with 4 buckets */
 #define HASHMAP_MIN_CAP_BITS 2
 
diff --git a/tools/perf/util/hashmap.h b/tools/perf/util/hashmap.h
index e0af36b0e5d8..10a4c4cd13cf 100644
--- a/tools/perf/util/hashmap.h
+++ b/tools/perf/util/hashmap.h
@@ -15,6 +15,9 @@
 static inline size_t hash_bits(size_t h, int bits)
 {
 	/* shuffle bits and return requested number of upper bits */
+	if (bits == 0)
+		return 0;
+
 #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__)
 	/* LP64 case */
 	return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits);
@@ -25,6 +28,18 @@ static inline size_t hash_bits(size_t h, int bits)
 #endif
 }
 
+/* generic C-string hashing function */
+static inline size_t str_hash(const char *s)
+{
+	size_t h = 0;
+
+	while (*s) {
+		h = h * 31 + *s;
+		s++;
+	}
+	return h;
+}
+
 typedef size_t (*hashmap_hash_fn)(const void *key, void *ctx);
 typedef bool (*hashmap_equal_fn)(const void *key1, const void *key2, void *ctx);
 
@@ -162,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value);
  * @key: key to iterate entries for
  */
 #define hashmap__for_each_key_entry(map, cur, _key)			    \
-	for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
-					     map->cap_bits);		    \
-		     map->buckets ? map->buckets[bkt] : NULL; });	    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
 	     cur;							    \
 	     cur = cur->next)						    \
 		if (map->equal_fn(cur->key, (_key), map->ctx))
 
 #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key)		    \
-	for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\
-					     map->cap_bits);		    \
-		     cur = map->buckets ? map->buckets[bkt] : NULL; });	    \
+	for (cur = map->buckets						    \
+		     ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \
+		     : NULL;						    \
 	     cur && ({ tmp = cur->next; true; });			    \
 	     cur = tmp)							    \
 		if (map->equal_fn(cur->key, (_key), map->ctx))
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index b8a5159361b4..5acf053fca7d 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -25,6 +25,7 @@
 
 /* SYM_L_* -- linkage of symbols */
 #define SYM_L_GLOBAL(name)			.globl name
+#define SYM_L_WEAK(name)			.weak name
 #define SYM_L_LOCAL(name)			/* nothing */
 
 #define ALIGN __ALIGN
@@ -84,6 +85,12 @@
 	SYM_END(name, SYM_T_FUNC)
 #endif
 
+/* SYM_FUNC_START_WEAK -- use for weak functions */
+#ifndef SYM_FUNC_START_WEAK
+#define SYM_FUNC_START_WEAK(name)			\
+	SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN)
+#endif
+
 /*
  * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
  * SYM_FUNC_START_WEAK, ...
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7d4194ffc5b0..15385ea00190 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -786,11 +786,20 @@ static int machine__process_ksymbol_unregister(struct machine *machine,
 					       union perf_event *event,
 					       struct perf_sample *sample __maybe_unused)
 {
+	struct symbol *sym;
 	struct map *map;
 
 	map = maps__find(&machine->kmaps, event->ksymbol.addr);
-	if (map)
+	if (!map)
+		return 0;
+
+	if (map != machine->vmlinux_map)
 		maps__remove(&machine->kmaps, map);
+	else {
+		sym = dso__find_symbol(map->dso, map->map_ip(map, map->start));
+		if (sym)
+			dso__delete_symbol(map->dso, sym);
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2c4061035f77..76dd349aa48d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1885,8 +1885,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 	if (lr->file && strtailcmp(lr->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
-	if (die_is_func_def(sp_die) &&
-	    die_match_name(sp_die, lr->function)) {
+	if (die_match_name(sp_die, lr->function) && die_is_func_def(sp_die)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 7cbd024e3e63..c83c2c6564e0 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1592,7 +1592,6 @@ static void _free_command_line(wchar_t **command_line, int num)
 static int python_start_script(const char *script, int argc, const char **argv)
 {
 	struct tables *tables = &tables_global;
-	PyMODINIT_FUNC (*initfunc)(void);
 #if PY_MAJOR_VERSION < 3
 	const char **command_line;
 #else
@@ -1607,20 +1606,18 @@ static int python_start_script(const char *script, int argc, const char **argv)
 	FILE *fp;
 
 #if PY_MAJOR_VERSION < 3
-	initfunc = initperf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(const char *));
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
+	PyImport_AppendInittab(name, initperf_trace_context);
 #else
-	initfunc = PyInit_perf_trace_context;
 	command_line = malloc((argc + 1) * sizeof(wchar_t *));
 	command_line[0] = Py_DecodeLocale(script, NULL);
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+	PyImport_AppendInittab(name, PyInit_perf_trace_context);
 #endif
-
-	PyImport_AppendInittab(name, initfunc);
 	Py_Initialize();
 
 #if PY_MAJOR_VERSION < 3
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 7a5f03764702..098080287c68 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -595,6 +595,7 @@ static void perf_event__mmap2_swap(union perf_event *event,
 	event->mmap2.maj   = bswap_32(event->mmap2.maj);
 	event->mmap2.min   = bswap_32(event->mmap2.min);
 	event->mmap2.ino   = bswap_64(event->mmap2.ino);
+	event->mmap2.ino_generation = bswap_64(event->mmap2.ino_generation);
 
 	if (sample_id_all) {
 		void *data = &event->mmap2.filename;
@@ -710,6 +711,18 @@ static void perf_event__namespaces_swap(union perf_event *event,
 		swap_sample_id_all(event, &event->namespaces.link_info[i]);
 }
 
+static void perf_event__cgroup_swap(union perf_event *event, bool sample_id_all)
+{
+	event->cgroup.id = bswap_64(event->cgroup.id);
+
+	if (sample_id_all) {
+		void *data = &event->cgroup.path;
+
+		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
+		swap_sample_id_all(event, data);
+	}
+}
+
 static u8 revbyte(u8 b)
 {
 	int rev = (b >> 4) | ((b & 0xf) << 4);
@@ -952,6 +965,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_SWITCH]		  = perf_event__switch_swap,
 	[PERF_RECORD_SWITCH_CPU_WIDE]	  = perf_event__switch_swap,
 	[PERF_RECORD_NAMESPACES]	  = perf_event__namespaces_swap,
+	[PERF_RECORD_CGROUP]		  = perf_event__cgroup_swap,
 	[PERF_RECORD_TEXT_POKE]		  = perf_event__text_poke_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 4b57c0c07632..a963b5b8eb72 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -324,13 +324,10 @@ static int first_shadow_cpu(struct perf_stat_config *config,
 	struct evlist *evlist = evsel->evlist;
 	int i;
 
-	if (!config->aggr_get_id)
-		return 0;
-
 	if (config->aggr_mode == AGGR_NONE)
 		return id;
 
-	if (config->aggr_mode == AGGR_GLOBAL)
+	if (!config->aggr_get_id)
 		return 0;
 
 	for (i = 0; i < evsel__nr_cpus(evsel); i++) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 6138866665df..0d14abdf3d72 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -515,6 +515,13 @@ void dso__insert_symbol(struct dso *dso, struct symbol *sym)
 	}
 }
 
+void dso__delete_symbol(struct dso *dso, struct symbol *sym)
+{
+	rb_erase_cached(&sym->rb_node, &dso->symbols);
+	symbol__delete(sym);
+	dso__reset_find_symbol_cache(dso);
+}
+
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
 {
 	if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index f4801c488def..954d6a049ee2 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -131,6 +131,8 @@ int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
 
 void dso__insert_symbol(struct dso *dso,
 			struct symbol *sym);
+void dso__delete_symbol(struct dso *dso,
+			struct symbol *sym);
 
 struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 8a23391558cf..d9c624377da7 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -563,6 +563,9 @@ int perf_event__synthesize_cgroups(struct perf_tool *tool,
 	char cgrp_root[PATH_MAX];
 	size_t mount_len;  /* length of mount point in the path */
 
+	if (!tool || !tool->cgroup_events)
+		return 0;
+
 	if (cgroupfs_find_mountpoint(cgrp_root, PATH_MAX, "perf_event") < 0) {
 		pr_debug("cannot find cgroup mount point\n");
 		return -1;