Merge tag 'perf-tools-fixes-for-v5.10-2020-11-17' of...

Merge tag 'perf-tools-fixes-for-v5.10-2020-11-17' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Fix file corruption due to event deletion in 'perf inject'.

 - Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem
   memcpy', silencing perf build warning.

 - Avoid an msan warning in a copied stack in 'perf test'.

 - Correct tracepoint field name "flags" in ARM's CS-ETM hardware
   tracing 'perf test' entry.

 - Update branch sample pattern for cs-etm to cope with excluding guest
   in userspace counting.

 - Don't free "lock_seq_stat" if read_count isn't zero in 'perf lock'.

* tag 'perf-tools-fixes-for-v5.10-2020-11-17' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf test: Avoid an msan warning in a copied stack.
  perf inject: Fix file corruption due to event deletion
  perf test: Update branch sample pattern for cs-etm
  perf test: Fix a typo in cs-etm testing
  tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy'
  perf lock: Don't free "lock_seq_stat" if read_count isn't zero
  perf lock: Correct field name "flags"

tools/arch/x86/lib/memcpy_64.S

@@ -16,8 +16,6 @@
  * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
  */
 
-.weak memcpy
-
 /*
  * memcpy - Copy a memory block.
  *
@@ -30,7 +28,7 @@
  * rax original destination
  */
 SYM_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
+SYM_FUNC_START_WEAK(memcpy)
 	ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memcpy_erms", X86_FEATURE_ERMS
 
@@ -51,14 +49,14 @@ EXPORT_SYMBOL(__memcpy)
  * memcpy_erms() - enhanced fast string memcpy. This is faster and
  * simpler than memcpy. Use memcpy_erms when possible.
  */
-SYM_FUNC_START(memcpy_erms)
+SYM_FUNC_START_LOCAL(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
 	ret
 SYM_FUNC_END(memcpy_erms)
 
-SYM_FUNC_START(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %rdi, %rax
 
 	cmpq $0x20, %rdx

tools/arch/x86/lib/memset_64.S

@@ -4,8 +4,7 @@
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
-
-.weak memset
+#include <asm/export.h>
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses fast
@@ -18,7 +17,7 @@
  *
  * rax   original destination
  */
-SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START_WEAK(memset)
 SYM_FUNC_START(__memset)
 	/*
 	 * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
@@ -44,6 +43,8 @@ SYM_FUNC_START(__memset)
 	ret
 SYM_FUNC_END(__memset)
 SYM_FUNC_END_ALIAS(memset)
+EXPORT_SYMBOL(memset)
+EXPORT_SYMBOL(__memset)
 
 /*
  * ISO C memset - set a memory block to a byte value. This function uses
@@ -56,7 +57,7 @@ SYM_FUNC_END_ALIAS(memset)
  *
  * rax   original destination
  */
-SYM_FUNC_START(memset_erms)
+SYM_FUNC_START_LOCAL(memset_erms)
 	movq %rdi,%r9
 	movb %sil,%al
 	movq %rdx,%rcx
@@ -65,7 +66,7 @@ SYM_FUNC_START(memset_erms)
 	ret
 SYM_FUNC_END(memset_erms)
 
-SYM_FUNC_START(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
 	movq %rdi,%r10
 
 	/* expand byte value  */

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;

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

tools/perf/bench/mem-memset-x86-64-asm.S

 /* 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

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;

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;
 		}

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 &&

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, ...