Merge tag 'perf-tools-2020-08-14' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull more perf tools updates from Arnaldo Carvalho de Melo:
 "Fixes:
   - Fixes for 'perf bench numa'.

   - Always memset source before memcpy in 'perf bench mem'.

   - Quote CC and CXX for their arguments to fix build in environments
     using those variables to pass more than just the compiler names.

   - Fix module symbol processing, addressing regression detected via
     "perf test".

   - Allow multiple probes in record+script_probe_vfs_getname.sh 'perf
     test' entry.

  Improvements:
   - Add script to autogenerate socket family name id->string table from
     copy of kernel header, used so far in 'perf trace'.

   - 'perf ftrace' improvements to provide similar options for this
     utility so that one can go from 'perf record', 'perf trace', etc to
     'perf ftrace' just by changing the name of the subcommand.

   - Prefer new "sched:sched_waking" trace event when it exists in 'perf
     sched' post processing.

   - Update POWER9 metrics to utilize other metrics.

   - Fall back to querying debuginfod if debuginfo not found locally.

  Miscellaneous:
   - Sync various kvm headers with kernel sources"

* tag 'perf-tools-2020-08-14' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (40 commits)
  perf ftrace: Make option description initials all capital letters
  perf build-ids: Fall back to debuginfod query if debuginfo not found
  perf bench numa: Remove dead code in parse_nodes_opt()
  perf stat: Update POWER9 metrics to utilize other metrics
  perf ftrace: Add change log
  perf: ftrace: Add set_tracing_options() to set all trace options
  perf ftrace: Add option --tid to filter by thread id
  perf ftrace: Add option -D/--delay to delay tracing
  perf: ftrace: Allow set graph depth by '--graph-opts'
  perf ftrace: Add support for trace option tracing_thresh
  perf ftrace: Add option 'verbose' to show more info for graph tracer
  perf ftrace: Add support for tracing option 'irq-info'
  perf ftrace: Add support for trace option funcgraph-irqs
  perf ftrace: Add support for trace option sleep-time
  perf ftrace: Add support for tracing option 'func_stack_trace'
  perf tools: Add general function to parse sublevel options
  perf ftrace: Add option '--inherit' to trace children processes
  perf ftrace: Show trace column header
  perf ftrace: Add option '-m/--buffer-size' to set per-cpu buffer size
  perf ftrace: Factor out function write_tracing_file_int()
  ...

Author: torvalds

MAINTAINERS

@@ -13566,6 +13566,7 @@ F:	arch/*/kernel/perf_event*.c
 F:	include/linux/perf_event.h
 F:	include/uapi/linux/perf_event.h
 F:	kernel/events/*
+F:	tools/lib/perf/
 F:	tools/perf/
 
 PERFORMANCE EVENTS SUBSYSTEM ARM64 PMU EVENTS

tools/arch/s390/include/uapi/asm/kvm.h

@@ -231,11 +231,13 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_GSCB   (1UL << 9)
 #define KVM_SYNC_BPBC   (1UL << 10)
 #define KVM_SYNC_ETOKEN (1UL << 11)
+#define KVM_SYNC_DIAG318 (1UL << 12)
 
 #define KVM_SYNC_S390_VALID_FIELDS \
 	(KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \
 	 KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \
-	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN)
+	 KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN | \
+	 KVM_SYNC_DIAG318)
 
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
@@ -264,7 +266,8 @@ struct kvm_sync_regs {
 	__u8 reserved2 : 7;
 	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
-	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
+	__u64 diag318;		/* diagnose 0x318 info */
+	__u8 padding2[184];	/* sdnx needs to be 256byte aligned */
 	union {
 		__u8 sdnx[SDNXL];  /* state description annex */
 		struct {

tools/build/Makefile.feature

@@ -8,7 +8,7 @@ endif
 
 feature_check = $(eval $(feature_check_code))
 define feature_check_code
-  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC=$(CC) CXX=$(CXX) CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
+  feature-$(1) := $(shell $(MAKE) OUTPUT=$(OUTPUT_FEATURES) CC="$(CC)" CXX="$(CXX)" CFLAGS="$(EXTRA_CFLAGS) $(FEATURE_CHECK_CFLAGS-$(1))" CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))" LDFLAGS="$(LDFLAGS) $(FEATURE_CHECK_LDFLAGS-$(1))" -C $(feature_dir) $(OUTPUT_FEATURES)test-$1.bin >/dev/null 2>/dev/null && echo 1 || echo 0)
 endef
 
 feature_set = $(eval $(feature_set_code))
@@ -98,7 +98,8 @@ FEATURE_TESTS_EXTRA :=                  \
          llvm-version                   \
          clang                          \
          libbpf                         \
-         libpfm4
+         libpfm4                        \
+         libdebuginfod
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 

tools/build/feature/Makefile

@@ -26,6 +26,7 @@ FILES=                                          \
          test-libelf-gelf_getnote.bin           \
          test-libelf-getshdrstrndx.bin          \
          test-libelf-mmap.bin                   \
+         test-libdebuginfod.bin                 \
          test-libnuma.bin                       \
          test-numa_num_possible_cpus.bin        \
          test-libperl.bin                       \
@@ -157,6 +158,9 @@ $(OUTPUT)test-libelf-gelf_getnote.bin:
 $(OUTPUT)test-libelf-getshdrstrndx.bin:
 	$(BUILD) -lelf
 
+$(OUTPUT)test-libdebuginfod.bin:
+	$(BUILD) -ldebuginfod
+
 $(OUTPUT)test-libnuma.bin:
 	$(BUILD) -lnuma
 

tools/build/feature/test-libdebuginfod.c

@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <elfutils/debuginfod.h>
+
+int main(void)
+{
+	debuginfod_client* c = debuginfod_begin();
+	return (long)c;
+}

tools/include/uapi/linux/kvm.h

@@ -289,6 +289,7 @@ struct kvm_run {
 		/* KVM_EXIT_FAIL_ENTRY */
 		struct {
 			__u64 hardware_entry_failure_reason;
+			__u32 cpu;
 		} fail_entry;
 		/* KVM_EXIT_EXCEPTION */
 		struct {
@@ -1031,6 +1032,9 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_SECURE_GUEST 181
 #define KVM_CAP_HALT_POLL 182
 #define KVM_CAP_ASYNC_PF_INT 183
+#define KVM_CAP_LAST_CPU 184
+#define KVM_CAP_SMALLER_MAXPHYADDR 185
+#define KVM_CAP_S390_DIAG318 186
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/include/uapi/linux/vhost.h

@@ -91,6 +91,8 @@
 
 /* Use message type V2 */
 #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+/* IOTLB can accept batching hints */
+#define VHOST_BACKEND_F_IOTLB_BATCH  0x2
 
 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
 #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)

tools/lib/perf/Documentation/libperf-counting.txt

@@ -7,13 +7,13 @@ libperf-counting - counting interface
 
 DESCRIPTION
 -----------
-The counting interface provides API to meassure and get count for specific perf events.
+The counting interface provides API to measure and get count for specific perf events.
 
 The following test tries to explain count on `counting.c` example.
 
 It is by no means complete guide to counting, but shows libperf basic API for counting.
 
-The `counting.c` comes with libbperf package and can be compiled and run like:
+The `counting.c` comes with libperf package and can be compiled and run like:
 
 [source,bash]
 --
@@ -26,7 +26,8 @@ count 176242, enabled 176242, run 176242
 It requires root access, because of the `PERF_COUNT_SW_CPU_CLOCK` event,
 which is available only for root.
 
-The `counting.c` example monitors two events on the current process and displays their count, in a nutshel it:
+The `counting.c` example monitors two events on the current process and displays
+their count, in a nutshell it:
 
 * creates events
 * adds them to the event list
@@ -152,7 +153,7 @@ Configure event list with the thread map and open events:
 --
 
 Both events are created as disabled (note the `disabled = 1` assignment above),
-so we need to enable the whole list explicitely (both events).
+so we need to enable the whole list explicitly (both events).
 
 From this moment events are counting and we can do our workload.
 
@@ -167,7 +168,8 @@ When we are done we disable the events list.
  79         perf_evlist__disable(evlist);
 --
 
-Now we need to get the counts from events, following code iterates throught the events list and read counts:
+Now we need to get the counts from events, following code iterates through the
+events list and read counts:
 
 [source,c]
 --
@@ -178,7 +180,7 @@ Now we need to get the counts from events, following code iterates throught the
  85         }
 --
 
-And finaly cleanup.
+And finally cleanup.
 
 We close the whole events list (both events) and remove it together with the threads map:
 

tools/lib/perf/Documentation/libperf-sampling.txt

@@ -8,13 +8,13 @@ libperf-sampling - sampling interface
 
 DESCRIPTION
 -----------
-The sampling interface provides API to meassure and get count for specific perf events.
+The sampling interface provides API to measure and get count for specific perf events.
 
 The following test tries to explain count on `sampling.c` example.
 
 It is by no means complete guide to sampling, but shows libperf basic API for sampling.
 
-The `sampling.c` comes with libbperf package and can be compiled and run like:
+The `sampling.c` comes with libperf package and can be compiled and run like:
 
 [source,bash]
 --
@@ -33,7 +33,8 @@ cpu   0, pid   4465, tid   4470, ip         7f84fe0ebebf, period             176
 
 It requires root access, because it uses hardware cycles event.
 
-The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a nutshel it:
+The `sampling.c` example profiles/samples all CPUs with hardware cycles, in a
+nutshell it:
 
 - creates events
 - adds them to the event list
@@ -90,7 +91,7 @@ Once the setup is complete we start by defining cycles event using the `struct p
  36         };
 --
 
-Next step is to prepare cpus map.
+Next step is to prepare CPUs map.
 
 In this case we will monitor all the available CPUs:
 
@@ -152,7 +153,7 @@ Once the events list is open, we can create memory maps AKA perf ring buffers:
 --
 
 The event is created as disabled (note the `disabled = 1` assignment above),
-so we need to enable the events list explicitely.
+so we need to enable the events list explicitly.
 
 From this moment the cycles event is sampling.
 
@@ -212,7 +213,7 @@ Each sample needs to get parsed:
 106                                 cpu, pid, tid, ip, period);
 --
 
-And finaly cleanup.
+And finally cleanup.
 
 We close the whole events list (both events) and remove it together with the threads map:
 

tools/lib/perf/Documentation/libperf.txt

@@ -29,7 +29,7 @@ SYNOPSIS
   void libperf_init(libperf_print_fn_t fn);
 --
 
-*API to handle cpu maps:*
+*API to handle CPU maps:*
 
 [source,c]
 --
@@ -217,7 +217,7 @@ Following objects are key to the libperf interface:
 
 [horizontal]
 
-struct perf_cpu_map:: Provides a cpu list abstraction.
+struct perf_cpu_map:: Provides a CPU list abstraction.
 
 struct perf_thread_map:: Provides a thread list abstraction.