Merge tag 'perf-tools-for-v5.19-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "Intel PT:

   - Allow hardware tracing on KVM test programs. In this case, the VM
     is not running an OS, but only the functions loaded into it by the
     hypervisor test program, and conveniently, loaded at the same
     virtual addresses.

   - Improve documentation:
      - Add link to perf wiki's page

   - Cleanups:
      - Delete now unused perf-with-kcore.sh script
      - Remove unused machines__find_host()

  ARM SPE (Statistical Profile Extensions):

   - Add man page entry.

  Vendor Events:

   - Update various Intel event topics

   - Update various microarch events

   - Fix various cstate metrics

   - Fix Alderlake metric groups

   - Add sapphirerapids events

   - Add JSON files for ARM Cortex A34, A35, A55, A510, A65, A73, A75,
     A77, A78, A710, X1, X2 and Neoverse E1

   - Update Cortex A57/A72

  perf stat:

   - Introduce stats for the user and system rusage times

  perf c2c:

   - Prep work to support ARM systems

  perf annotate:

   - Add --percent-limit option

  perf lock:

   - Add -t/--thread option for report

   - Do not discard broken lock stats

  perf bench:

   - Add breakpoint benchmarks

  perf test:

   - Limit to only run executable scripts in tests

   - Add basic perf record tests

   - Add stat record+report test

   - Add basic stat and topdown group test

   - Skip several tests when the user hasn't permission to perform them

   - Fix test case 81 ("perf record tests") on s390x

  perf version:

   - debuginfod support improvements

  perf scripting python:

   - Expose symbol offset and source information

  perf build:

   - Error for BPF skeletons without LIBBPF

   - Use Python devtools for version autodetection rather than runtime

  Miscellaneous:

   - Add riscv64 support to 'perf jitdump'

   - Various fixes/tidy ups related to cpu_map

   - Fixes for handling Intel hybrid systems"

* tag 'perf-tools-for-v5.19-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (122 commits)
  perf intel-pt: Add guest_code support
  perf kvm report: Add guest_code support
  perf script: Add guest_code support
  perf tools: Add guest_code support
  perf tools: Factor out thread__set_guest_comm()
  perf tools: Add machine to machines back pointer
  perf vendors events arm64: Update Cortex A57/A72
  perf vendors events arm64: Arm Neoverse E1
  perf vendors events arm64: Arm Cortex-X2
  perf vendors events arm64: Arm Cortex-X1
  perf vendors events arm64: Arm Cortex-A710
  perf vendors events arm64: Arm Cortex-A78
  perf vendors events arm64: Arm Cortex-A77
  perf vendors events arm64: Arm Cortex-A75
  perf vendors events arm64: Arm Cortex-A73
  perf vendors events arm64: Arm Cortex-A65
  perf vendors events arm64: Arm Cortex-A510
  perf vendors events arm64: Arm Cortex-A55
  perf vendors events arm64: Arm Cortex-A35
  perf vendors events arm64: Arm Cortex-A34
  ...

7 files changed, 62 insertions, 14 deletions

diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index a09315538a30..ed66f2e38464 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -59,6 +59,10 @@ static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
+	/* Recomputing all_cpus, so start with a blank slate. */
+	perf_cpu_map__put(evlist->all_cpus);
+	evlist->all_cpus = NULL;
+
 	perf_evlist__for_each_evsel(evlist, evsel)
 		__perf_evlist__propagate_maps(evlist, evsel);
 }
@@ -474,6 +478,9 @@ mmap_per_evsel(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 			 */
 			refcount_set(&map->refcnt, 2);
 
+			if (ops->idx)
+				ops->idx(evlist, evsel, mp, idx);
+
 			if (ops->mmap(map, mp, *output, evlist_cpu) < 0)
 				return -1;
 
@@ -516,9 +523,6 @@ mmap_per_thread(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 		int output = -1;
 		int output_overwrite = -1;
 
-		if (ops->idx)
-			ops->idx(evlist, mp, thread, false);
-
 		if (mmap_per_evsel(evlist, ops, thread, mp, 0, thread,
 				   &output, &output_overwrite))
 			goto out_unmap;
@@ -543,9 +547,6 @@ mmap_per_cpu(struct perf_evlist *evlist, struct perf_evlist_mmap_ops *ops,
 		int output = -1;
 		int output_overwrite = -1;
 
-		if (ops->idx)
-			ops->idx(evlist, mp, cpu, true);
-
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (mmap_per_evsel(evlist, ops, cpu, mp, cpu,
 					   thread, &output, &output_overwrite))
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 210ea7c06ce8..c1d58673f6ef 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -328,6 +328,17 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 	return 0;
 }
 
+static int perf_evsel__ioctl(struct perf_evsel *evsel, int ioc, void *arg,
+			     int cpu_map_idx, int thread)
+{
+	int *fd = FD(evsel, cpu_map_idx, thread);
+
+	if (fd == NULL || *fd < 0)
+		return -1;
+
+	return ioctl(*fd, ioc, arg);
+}
+
 static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 				 int ioc,  void *arg,
 				 int cpu_map_idx)
@@ -335,13 +346,7 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-		int err;
-		int *fd = FD(evsel, cpu_map_idx, thread);
-
-		if (fd == NULL || *fd < 0)
-			return -1;
-
-		err = ioctl(*fd, ioc, arg);
+		int err = perf_evsel__ioctl(evsel, ioc, arg, cpu_map_idx, thread);
 
 		if (err)
 			return err;
@@ -355,6 +360,21 @@ int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
 }
 
+int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread)
+{
+	struct perf_cpu cpu __maybe_unused;
+	int idx;
+	int err;
+
+	perf_cpu_map__for_each_cpu(cpu, idx, evsel->cpus) {
+		err = perf_evsel__ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, idx, thread);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 int perf_evsel__enable(struct perf_evsel *evsel)
 {
 	int i;
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index e3e64f37db7b..6f89aec3e608 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -38,7 +38,8 @@ struct perf_evlist {
 };
 
 typedef void
-(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_mmap_param*, int, bool);
+(*perf_evlist_mmap__cb_idx_t)(struct perf_evlist*, struct perf_evsel*,
+			      struct perf_mmap_param*, int);
 typedef struct perf_mmap*
 (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int);
 typedef int
diff --git a/tools/lib/perf/include/internal/lib.h b/tools/lib/perf/include/internal/lib.h
index 5175d491b2d4..85471a4b900f 100644
--- a/tools/lib/perf/include/internal/lib.h
+++ b/tools/lib/perf/include/internal/lib.h
@@ -9,4 +9,6 @@ extern unsigned int page_size;
 ssize_t readn(int fd, void *buf, size_t n);
 ssize_t writen(int fd, const void *buf, size_t n);
 
+ssize_t preadn(int fd, void *buf, size_t n, off_t offs);
+
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 4a2edbdb5e2b..24de795b09bb 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -31,4 +31,7 @@ LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_c
 	     (idx) < perf_cpu_map__nr(cpus);			\
 	     (idx)++, (cpu) = perf_cpu_map__cpu(cpus, idx))
 
+#define perf_cpu_map__for_each_idx(idx, cpus)				\
+	for ((idx) = 0; (idx) < perf_cpu_map__nr(cpus); (idx)++)
+
 #endif /* __LIBPERF_CPUMAP_H */
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 2a9516b42d15..699c0ed97d34 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -36,6 +36,7 @@ LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int
 				 struct perf_counts_values *count);
 LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
 LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
+LIBPERF_API int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread);
 LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
 LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
diff --git a/tools/lib/perf/lib.c b/tools/lib/perf/lib.c
index 18658931fc71..696fb0ea67c6 100644
--- a/tools/lib/perf/lib.c
+++ b/tools/lib/perf/lib.c
@@ -38,6 +38,26 @@ ssize_t readn(int fd, void *buf, size_t n)
 	return ion(true, fd, buf, n);
 }
 
+ssize_t preadn(int fd, void *buf, size_t n, off_t offs)
+{
+	size_t left = n;
+
+	while (left) {
+		ssize_t ret = pread(fd, buf, left, offs);
+
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			return ret;
+
+		left -= ret;
+		buf  += ret;
+		offs += ret;
+	}
+
+	return n;
+}
+
 /*
  * Write exactly 'n' bytes or return an error.
  */