Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "No kernel side changes, all tooling fixes plus two tooling cleanups
  that were committed late in the merge window alongside the perf
  annotate fixes, delayed by Arnaldo's European trip"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  perf annotate: Fix segfault with source toggle
  perf annotate: Align struct annotate_args
  perf annotate: Simplify disasm_line allocation and freeing code
  perf annotate: Remove privsize from symbol__annotate() args
  perf probe: Check return value of strlist__add() for -ENOMEM
  perf config: Document missing config options
  perf annotate: Fix perf config option description
  perf annotate: Prefer cmdline option over default config
  perf annotate: Make perf config effective
  perf config: Introduce perf_config_u8()
  perf annotate: Fix --show-nr-samples for tui/stdio2
  perf annotate: Fix --show-total-period for tui/stdio2
  perf annotate/tui: Re-render title bar after switching back from script browser
  tools headers UAPI: Update tools's copy of kvm.h headers
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  perf arch powerpc: Sync powerpc syscall.tbl with the kernel sources
  perf auxtrace: Add auxtrace_record__read_finish()
  perf arm-spe: Fix endless record after being terminated
  perf cs-etm: Fix endless record after being terminated
  perf intel-bts: Fix endless record after being terminated
  ...

Author: torvalds

tools/arch/x86/include/asm/msr-index.h

@@ -512,6 +512,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 

tools/arch/x86/include/uapi/asm/kvm.h

@@ -390,6 +390,7 @@ struct kvm_sync_regs {
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
+#define KVM_STATE_NESTED_MTF_PENDING	0x00000008
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002

tools/perf/Documentation/perf-config.txt

@@ -239,7 +239,6 @@ buildid.*::
 		set buildid.dir to /dev/null. The default is $HOME/.debug
 
 annotate.*::
-	These options work only for TUI.
 	These are in control of addresses, jump function, source code
 	in lines of assembly code from a specific program.
 
@@ -269,6 +268,8 @@ annotate.*::
 		│        mov    (%rdi),%rdx
 		│              return n;
 
+		This option works with tui, stdio2 browsers.
+
         annotate.use_offset::
 		Basing on a first address of a loaded function, offset can be used.
 		Instead of using original addresses of assembly code,
@@ -287,6 +288,8 @@ annotate.*::
 
 		             368:│  mov    0x8(%r14),%rdi
 
+		This option works with tui, stdio2 browsers.
+
 	annotate.jump_arrows::
 		There can be jump instruction among assembly code.
 		Depending on a boolean value of jump_arrows,
@@ -306,6 +309,8 @@ annotate.*::
 		│1330:   mov    %r15,%r10
 		│1333:   cmp    %r15,%r14
 
+		This option works with tui browser.
+
         annotate.show_linenr::
 		When showing source code if this option is 'true',
 		line numbers are printed as below.
@@ -325,6 +330,8 @@ annotate.*::
 		│                     array++;
 		│             }
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_nr_jumps::
 		Let's see a part of assembly code.
 
@@ -335,6 +342,8 @@ annotate.*::
 
 		│1 1382:   movb   $0x1,-0x270(%rbp)
 
+		This option works with tui, stdio2 browsers.
+
         annotate.show_total_period::
 		To compare two records on an instruction base, with this option
 		provided, display total number of samples that belong to a line
@@ -348,11 +357,30 @@ annotate.*::
 
 		99.93 │      mov    %eax,%eax
 
+		This option works with tui, stdio2, stdio browsers.
+
+	annotate.show_nr_samples::
+		By default perf annotate shows percentage of samples. This option
+		can be used to print absolute number of samples. Ex, when set as
+		false:
+
+		Percent│
+		 74.03 │      mov    %fs:0x28,%rax
+
+		When set as true:
+
+		Samples│
+		     6 │      mov    %fs:0x28,%rax
+
+		This option works with tui, stdio2, stdio browsers.
+
 	annotate.offset_level::
 		Default is '1', meaning just jump targets will have offsets show right beside
 		the instruction. When set to '2' 'call' instructions will also have its offsets
 		shown, 3 or higher will show offsets for all instructions.
 
+		This option works with tui, stdio2 browsers.
+
 hist.*::
 	hist.percentage::
 		This option control the way to calculate overhead of filtered entries -
@@ -490,6 +518,12 @@ top.*::
 		column by default.
 		The default is 'true'.
 
+	top.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'top' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf top' to actually use it,
+		the command line option -g must be specified.
+
 man.*::
 	man.viewer::
 		This option can assign a tool to view manual pages when 'help'
@@ -517,6 +551,16 @@ record.*::
 		But if this option is 'no-cache', it will not update the build-id cache.
 		'skip' skips post-processing and does not update the cache.
 
+	record.call-graph::
+		This is identical to 'call-graph.record-mode', except it is
+		applicable only for 'record' subcommand. This option ONLY setup
+		the unwind method. To enable 'perf record' to actually use it,
+		the command line option -g must be specified.
+
+	record.aio::
+		Use 'n' control blocks in asynchronous (Posix AIO) trace writing
+		mode ('n' default: 1, max: 4).
+
 diff.*::
 	diff.order::
 		This option sets the number of columns to sort the result.
@@ -566,6 +610,11 @@ trace.*::
 		"libbeauty", the default, to use the same argument beautifiers used in the
 		strace-like sys_enter+sys_exit lines.
 
+ftrace.*::
+	ftrace.tracer::
+		Can be used to select the default tracer. Possible values are
+		'function' and 'function_graph'.
+
 llvm.*::
 	llvm.clang-path::
 		Path to clang. If omit, search it from $PATH.
@@ -610,6 +659,29 @@ scripts.*::
 	The script gets the same options passed as a full perf script,
 	in particular -i perfdata file, --cpu, --tid
 
+convert.*::
+
+	convert.queue-size::
+		Limit the size of ordered_events queue, so we could control
+		allocation size of perf data files without proper finished
+		round events.
+
+intel-pt.*::
+
+	intel-pt.cache-divisor::
+
+	intel-pt.mispred-all::
+		If set, Intel PT decoder will set the mispred flag on all
+		branches.
+
+auxtrace.*::
+
+	auxtrace.dumpdir::
+		s390 only. The directory to save the auxiliary trace buffer
+		can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
+		If the directory does not exist or has the wrong file type,
+		the current directory is used.
+
 SEE ALSO
 --------
 linkperf:perf[1]

tools/perf/arch/arm/util/cs-etm.c

@@ -858,21 +858,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 	free(ptr);
 }
 
-static int cs_etm_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct cs_etm_recording *ptr =
-			container_of(itr, struct cs_etm_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->cs_etm_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist,
-							     evsel, idx);
-	}
-
-	return -EINVAL;
-}
-
 struct auxtrace_record *cs_etm_record_init(int *err)
 {
 	struct perf_pmu *cs_etm_pmu;
@@ -892,6 +877,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	}
 
 	ptr->cs_etm_pmu			= cs_etm_pmu;
+	ptr->itr.pmu			= cs_etm_pmu;
 	ptr->itr.parse_snapshot_options	= cs_etm_parse_snapshot_options;
 	ptr->itr.recording_options	= cs_etm_recording_options;
 	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
@@ -901,7 +887,7 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
 	ptr->itr.reference		= cs_etm_reference;
 	ptr->itr.free			= cs_etm_recording_free;
-	ptr->itr.read_finish		= cs_etm_read_finish;
+	ptr->itr.read_finish		= auxtrace_record__read_finish;
 
 	*err = 0;
 	return &ptr->itr;

tools/perf/arch/arm64/util/arm-spe.c

@@ -158,20 +158,6 @@ static void arm_spe_recording_free(struct auxtrace_record *itr)
 	free(sper);
 }
 
-static int arm_spe_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct arm_spe_recording *sper =
-			container_of(itr, struct arm_spe_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(sper->evlist, evsel) {
-		if (evsel->core.attr.type == sper->arm_spe_pmu->type)
-			return perf_evlist__enable_event_idx(sper->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *arm_spe_recording_init(int *err,
 					       struct perf_pmu *arm_spe_pmu)
 {
@@ -189,12 +175,13 @@ struct auxtrace_record *arm_spe_recording_init(int *err,
 	}
 
 	sper->arm_spe_pmu = arm_spe_pmu;
+	sper->itr.pmu = arm_spe_pmu;
 	sper->itr.recording_options = arm_spe_recording_options;
 	sper->itr.info_priv_size = arm_spe_info_priv_size;
 	sper->itr.info_fill = arm_spe_info_fill;
 	sper->itr.free = arm_spe_recording_free;
 	sper->itr.reference = arm_spe_reference;
-	sper->itr.read_finish = arm_spe_read_finish;
+	sper->itr.read_finish = auxtrace_record__read_finish;
 	sper->itr.alignment = 0;
 
 	*err = 0;

tools/perf/arch/powerpc/entry/syscalls/syscall.tbl

@@ -517,3 +517,5 @@
 433	common	fspick				sys_fspick
 434	common	pidfd_open			sys_pidfd_open
 435	nospu	clone3				ppc_clone3
+437	common	openat2				sys_openat2
+438	common	pidfd_getfd			sys_pidfd_getfd

tools/perf/arch/x86/util/intel-bts.c

@@ -413,20 +413,6 @@ static int intel_bts_find_snapshot(struct auxtrace_record *itr, int idx,
 	return err;
 }
 
-static int intel_bts_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_bts_recording *btsr =
-			container_of(itr, struct intel_bts_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(btsr->evlist, evsel) {
-		if (evsel->core.attr.type == btsr->intel_bts_pmu->type)
-			return perf_evlist__enable_event_idx(btsr->evlist,
-							     evsel, idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_bts_recording_init(int *err)
 {
 	struct perf_pmu *intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
@@ -447,6 +433,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	}
 
 	btsr->intel_bts_pmu = intel_bts_pmu;
+	btsr->itr.pmu = intel_bts_pmu;
 	btsr->itr.recording_options = intel_bts_recording_options;
 	btsr->itr.info_priv_size = intel_bts_info_priv_size;
 	btsr->itr.info_fill = intel_bts_info_fill;
@@ -456,7 +443,7 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	btsr->itr.find_snapshot = intel_bts_find_snapshot;
 	btsr->itr.parse_snapshot_options = intel_bts_parse_snapshot_options;
 	btsr->itr.reference = intel_bts_reference;
-	btsr->itr.read_finish = intel_bts_read_finish;
+	btsr->itr.read_finish = auxtrace_record__read_finish;
 	btsr->itr.alignment = sizeof(struct branch);
 	return &btsr->itr;
 }

tools/perf/arch/x86/util/intel-pt.c

@@ -1166,20 +1166,6 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
-static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
-{
-	struct intel_pt_recording *ptr =
-			container_of(itr, struct intel_pt_recording, itr);
-	struct evsel *evsel;
-
-	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->intel_pt_pmu->type)
-			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
-							     idx);
-	}
-	return -EINVAL;
-}
-
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
@@ -1200,6 +1186,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	}
 
 	ptr->intel_pt_pmu = intel_pt_pmu;
+	ptr->itr.pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
 	ptr->itr.info_fill = intel_pt_info_fill;
@@ -1209,7 +1196,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 	ptr->itr.find_snapshot = intel_pt_find_snapshot;
 	ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
 	ptr->itr.reference = intel_pt_reference;
-	ptr->itr.read_finish = intel_pt_read_finish;
+	ptr->itr.read_finish = auxtrace_record__read_finish;
 	/*
 	 * Decoding starts at a PSB packet. Minimum PSB period is 2K so 4K
 	 * should give at least 1 PSB per sample.

tools/perf/builtin-annotate.c

@@ -566,6 +566,8 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		return ret;
 
+	annotation_config__init(&annotate.opts);
+
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 	if (argc) {
 		/*
@@ -605,8 +607,6 @@ int cmd_annotate(int argc, const char **argv)
 	if (ret < 0)
 		goto out_delete;
 
-	annotation_config__init();
-
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);

tools/perf/builtin-probe.c

@@ -449,7 +449,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret = probe_file__del_strlist(kfd, klist);
 		if (ret < 0)
 			goto error;
-	}
+	} else if (ret == -ENOMEM)
+		goto error;
 
 	ret2 = probe_file__get_events(ufd, filter, ulist);
 	if (ret2 == 0) {
@@ -459,7 +460,8 @@ static int perf_del_probe_events(struct strfilter *filter)
 		ret2 = probe_file__del_strlist(ufd, ulist);
 		if (ret2 < 0)
 			goto error;
-	}
+	} else if (ret2 == -ENOMEM)
+		goto error;
 
 	if (ret == -ENOENT && ret2 == -ENOENT)
 		pr_warning("\"%s\" does not hit any event.\n", str);