Merge tag 'perf-tools-fixes-for-v5.19-2022-07-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - BPF program info linear (BPIL) data is accessed assuming 64-bit
   alignment resulting in undefined behavior as the data is just byte
   aligned. Fix it, Found using -fsanitize=undefined.

 - Fix 'perf offcpu' build on old kernels wrt task_struct's
   state/__state field.

 - Fix perf_event_attr.sample_type setting on the 'offcpu-time' event
   synthesized by the 'perf offcpu' tool.

 - Don't bail out when synthesizing PERF_RECORD_ events for pre-existing
   threads when one goes away while parsing its procfs entries.

 - Don't sort the task scan result from /proc, its not needed and
   introduces bugs when the main thread isn't the first one to be
   processed.

 - Fix uninitialized 'offset' variable on aarch64 in the unwind code.

 - Sync KVM headers with the kernel sources.

* tag 'perf-tools-fixes-for-v5.19-2022-07-02' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf synthetic-events: Ignore dead threads during event synthesis
  perf synthetic-events: Don't sort the task scan result from /proc
  perf unwind: Fix unitialized 'offset' variable on aarch64
  tools headers UAPI: Sync linux/kvm.h with the kernel sources
  perf bpf: 8 byte align bpil data
  tools kvm headers arm64: Update KVM headers from the kernel sources
  perf offcpu: Accept allowed sample types only
  perf offcpu: Fix build failure on old kernels

7 files changed, 46 insertions, 15 deletions

diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c
index e271e05e51bc..80b1d2b3729b 100644
--- a/tools/perf/util/bpf-utils.c
+++ b/tools/perf/util/bpf-utils.c
@@ -149,11 +149,10 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		count = bpf_prog_info_read_offset_u32(&info, desc->count_offset);
 		size  = bpf_prog_info_read_offset_u32(&info, desc->size_offset);
 
-		data_len += count * size;
+		data_len += roundup(count * size, sizeof(__u64));
 	}
 
 	/* step 3: allocate continuous memory */
-	data_len = roundup(data_len, sizeof(__u64));
 	info_linear = malloc(sizeof(struct perf_bpil) + data_len);
 	if (!info_linear)
 		return ERR_PTR(-ENOMEM);
@@ -180,7 +179,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays)
 		bpf_prog_info_set_offset_u64(&info_linear->info,
 					     desc->array_offset,
 					     ptr_to_u64(ptr));
-		ptr += count * size;
+		ptr += roundup(count * size, sizeof(__u64));
 	}
 
 	/* step 5: call syscall again to get required arrays */
diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c
index b73e84a02264..f289b7713598 100644
--- a/tools/perf/util/bpf_off_cpu.c
+++ b/tools/perf/util/bpf_off_cpu.c
@@ -265,6 +265,12 @@ int off_cpu_write(struct perf_session *session)
 
 	sample_type = evsel->core.attr.sample_type;
 
+	if (sample_type & ~OFFCPU_SAMPLE_TYPES) {
+		pr_err("not supported sample type: %llx\n",
+		       (unsigned long long)sample_type);
+		return -1;
+	}
+
 	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER)) {
 		if (evsel->core.id)
 			sid = evsel->core.id[0];
@@ -319,7 +325,6 @@ int off_cpu_write(struct perf_session *session)
 		}
 		if (sample_type & PERF_SAMPLE_CGROUP)
 			data.array[n++] = key.cgroup_id;
-		/* TODO: handle more sample types */
 
 		size = n * sizeof(u64);
 		data.hdr.size = size;
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 792ae2847080..cc6d7fd55118 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -71,6 +71,11 @@ struct {
 	__uint(max_entries, 1);
 } cgroup_filter SEC(".maps");
 
+/* new kernel task_struct definition */
+struct task_struct___new {
+	long __state;
+} __attribute__((preserve_access_index));
+
 /* old kernel task_struct definition */
 struct task_struct___old {
 	long state;
@@ -93,14 +98,17 @@ const volatile bool uses_cgroup_v1 = false;
  */
 static inline int get_task_state(struct task_struct *t)
 {
-	if (bpf_core_field_exists(t->__state))
-		return BPF_CORE_READ(t, __state);
+	/* recast pointer to capture new type for compiler */
+	struct task_struct___new *t_new = (void *)t;
 
-	/* recast pointer to capture task_struct___old type for compiler */
-	struct task_struct___old *t_old = (void *)t;
+	if (bpf_core_field_exists(t_new->__state)) {
+		return BPF_CORE_READ(t_new, __state);
+	} else {
+		/* recast pointer to capture old type for compiler */
+		struct task_struct___old *t_old = (void *)t;
 
-	/* now use old "state" name of the field */
-	return BPF_CORE_READ(t_old, state);
+		return BPF_CORE_READ(t_old, state);
+	}
 }
 
 static inline __u64 get_cgroup_id(struct task_struct *t)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ce499c5da8d7..094b0a9c0bc0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -48,6 +48,7 @@
 #include "util.h"
 #include "hashmap.h"
 #include "pmu-hybrid.h"
+#include "off_cpu.h"
 #include "../perf-sys.h"
 #include "util/parse-branch-options.h"
 #include <internal/xyarray.h>
@@ -1102,6 +1103,11 @@ static void evsel__set_default_freq_period(struct record_opts *opts,
 	}
 }
 
+static bool evsel__is_offcpu_event(struct evsel *evsel)
+{
+	return evsel__is_bpf_output(evsel) && !strcmp(evsel->name, OFFCPU_EVENT);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1366,6 +1372,9 @@ void evsel__config(struct evsel *evsel, struct record_opts *opts,
 	 */
 	if (evsel__is_dummy_event(evsel))
 		evsel__reset_sample_bit(evsel, BRANCH_STACK);
+
+	if (evsel__is_offcpu_event(evsel))
+		evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES;
 }
 
 int evsel__set_filter(struct evsel *evsel, const char *filter)
diff --git a/tools/perf/util/off_cpu.h b/tools/perf/util/off_cpu.h
index 548008f74d42..2dd67c60f211 100644
--- a/tools/perf/util/off_cpu.h
+++ b/tools/perf/util/off_cpu.h
@@ -1,6 +1,8 @@
 #ifndef PERF_UTIL_OFF_CPU_H
 #define PERF_UTIL_OFF_CPU_H
 
+#include <linux/perf_event.h>
+
 struct evlist;
 struct target;
 struct perf_session;
@@ -8,6 +10,13 @@ struct record_opts;
 
 #define OFFCPU_EVENT  "offcpu-time"
 
+#define OFFCPU_SAMPLE_TYPES  (PERF_SAMPLE_IDENTIFIER | PERF_SAMPLE_IP | \
+			      PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \
+			      PERF_SAMPLE_ID | PERF_SAMPLE_CPU | \
+			      PERF_SAMPLE_PERIOD | PERF_SAMPLE_CALLCHAIN | \
+			      PERF_SAMPLE_CGROUP)
+
+
 #ifdef HAVE_BPF_SKEL
 int off_cpu_prepare(struct evlist *evlist, struct target *target,
 		    struct record_opts *opts);
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 27acdc5e5723..84d17bd4efae 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -754,7 +754,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
 		 machine->root_dir, pid);
 
-	n = scandir(filename, &dirent, filter_task, alphasort);
+	n = scandir(filename, &dirent, filter_task, NULL);
 	if (n < 0)
 		return n;
 
@@ -767,11 +767,12 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (*end)
 			continue;
 
-		rc = -1;
+		/* some threads may exit just after scan, ignore it */
 		if (perf_event__prepare_comm(comm_event, pid, _pid, machine,
 					     &tgid, &ppid, &kernel_thread) != 0)
-			break;
+			continue;
 
+		rc = -1;
 		if (perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						ppid, process, machine) < 0)
 			break;
@@ -987,7 +988,7 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 		return 0;
 
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
-	n = scandir(proc_path, &dirent, filter_task, alphasort);
+	n = scandir(proc_path, &dirent, filter_task, NULL);
 	if (n < 0)
 		return err;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6e5b8cce47bf..81b6bd6e1536 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -197,7 +197,7 @@ out_err:
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 static u64 elf_section_offset(int fd, const char *name)
 {
-	u64 address, offset;
+	u64 address, offset = 0;
 
 	if (elf_section_address_and_offset(fd, name, &address, &offset))
 		return 0;