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

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - x86 Intel uncore driver cleanups and enhancements (Kan Liang)

   - group scheduling and other fixes (Song Liu

   - store frame pointer in the sample traces for better profiling
     (Alexey Budankov)

   - compat fixes/enhancements (Eugene Syromiatnikov)

  Tooling side changes, which you can build and install in a single step
  via:

      make -C tools/perf clean install

  perf annotate:

   - Support 'perf annotate --group' for non-explicit recorded event
     "groups", showing multiple columns, one for each event, just like
     when dealing with explicit event groups (those enclosed with {})
     (Jin Yao)

   - Record min/max LBR cycles (>= Skylake) and add 'perf annotate' TUI
     hotkey to show it (c) (Jin Yao)

  perf bpf:

   - Add infrastructure to help in writing eBPF C programs to be used
     with '-e name.c' type events in tools such as 'record' and 'trace',
     with headers for common constructs and an examples directory that
     will get populated as we add more such helpers and the 'perf bpf'
     (Arnaldo Carvalho de Melo)

  perf stat:

   - Display time in precision based on std deviation (Jiri Olsa)

   - Add --table option to display time of each run (Jiri Olsa)

   - Display length strings of each run for --table option (Jiri Olsa)

  perf buildid-cache:

   - Add --list and --purge-all options (Ravi Bangoria)

  perf test:

   - Let 'perf test list' display subtests (Hendrik Brueckner)

  perf pti:

   - Create extra kernel maps to help in decoding samples in x86 PTI
     entry trampolines (Adrian Hunter)

   - Copy x86 PTI entry trampoline sections in the kcore copy used for
     annotation and intel_pt CPU traces decoding (Adrian Hunter)

  ... and a lot of other fixes, enhancements and cleanups I did not
  list, see the shortlog and git log for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (111 commits)
  perf/x86/intel/uncore: Clean up client IMC uncore
  perf/x86/intel/uncore: Expose uncore_pmu_event*() functions
  perf/x86/intel/uncore: Support IIO free-running counters on SKX
  perf/x86/intel/uncore: Add infrastructure for free running counters
  perf/x86/intel/uncore: Add new data structures for free running counters
  perf/x86/intel/uncore: Correct fixed counter index check in generic code
  perf/x86/intel/uncore: Correct fixed counter index check for NHM
  perf/x86/intel/uncore: Introduce customized event_read() for client IMC uncore
  perf/x86: Store user space frame-pointer value on a sample
  perf/core: Wire up compat PERF_EVENT_IOC_QUERY_BPF, PERF_EVENT_IOC_MODIFY_ATTRIBUTES
  perf/core: Fix bad use of igrab()
  perf/core: Fix group scheduling with mixed hw and sw events
  perf kcore_copy: Amend the offset of sections that remap kernel text
  perf kcore_copy: Copy x86 PTI entry trampoline sections
  perf kcore_copy: Get rid of kernel_map
  perf kcore_copy: Iterate phdrs
  perf kcore_copy: Layout sections
  perf kcore_copy: Calculate offset from phnum
  perf kcore_copy: Keep a count of phdrs
  perf kcore_copy: Keep phdr data in a list
  ...

1 files changed, 22 insertions, 22 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 67612ce359ad..08f5e1b42b43 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5120,6 +5120,8 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd,
 	switch (_IOC_NR(cmd)) {
 	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
 	case _IOC_NR(PERF_EVENT_IOC_ID):
+	case _IOC_NR(PERF_EVENT_IOC_QUERY_BPF):
+	case _IOC_NR(PERF_EVENT_IOC_MODIFY_ATTRIBUTES):
 		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
 		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
 			cmd &= ~IOCSIZE_MASK;
@@ -6668,7 +6670,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		if (filter->inode) {
+		if (filter->path.dentry) {
 			event->addr_filters_offs[count] = 0;
 			restart++;
 		}
@@ -7333,7 +7335,7 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
-	if (filter->inode != file_inode(file))
+	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 
 	if (filter->offset > offset + size)
@@ -8686,8 +8688,7 @@ static void free_filters_list(struct list_head *filters)
 	struct perf_addr_filter *filter, *iter;
 
 	list_for_each_entry_safe(filter, iter, filters, entry) {
-		if (filter->inode)
-			iput(filter->inode);
+		path_put(&filter->path);
 		list_del(&filter->entry);
 		kfree(filter);
 	}
@@ -8784,7 +8785,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 		 * Adjust base offset if the filter is associated to a binary
 		 * that needs to be mapped:
 		 */
-		if (filter->inode)
+		if (filter->path.dentry)
 			event->addr_filters_offs[count] =
 				perf_addr_filter_apply(filter, mm);
 
@@ -8858,7 +8859,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 {
 	struct perf_addr_filter *filter = NULL;
 	char *start, *orig, *filename = NULL;
-	struct path path;
 	substring_t args[MAX_OPT_ARGS];
 	int state = IF_STATE_ACTION, token;
 	unsigned int kernel = 0;
@@ -8971,19 +8971,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 					goto fail_free_name;
 
 				/* look up the path and grab its inode */
-				ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+				ret = kern_path(filename, LOOKUP_FOLLOW,
+						&filter->path);
 				if (ret)
 					goto fail_free_name;
 
-				filter->inode = igrab(d_inode(path.dentry));
-				path_put(&path);
 				kfree(filename);
 				filename = NULL;
 
 				ret = -EINVAL;
-				if (!filter->inode ||
-				    !S_ISREG(filter->inode->i_mode))
-					/* free_filters_list() will iput() */
+				if (!filter->path.dentry ||
+				    !S_ISREG(d_inode(filter->path.dentry)
+					     ->i_mode))
 					goto fail;
 
 				event->addr_filters.nr_file_filters++;
@@ -10521,19 +10520,20 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (pmu->task_ctx_nr == perf_sw_context)
 		event->event_caps |= PERF_EV_CAP_SOFTWARE;
 
-	if (group_leader &&
-	    (is_software_event(event) != is_software_event(group_leader))) {
-		if (is_software_event(event)) {
+	if (group_leader) {
+		if (is_software_event(event) &&
+		    !in_software_context(group_leader)) {
 			/*
-			 * If event and group_leader are not both a software
-			 * event, and event is, then group leader is not.
+			 * If the event is a sw event, but the group_leader
+			 * is on hw context.
 			 *
-			 * Allow the addition of software events to !software
-			 * groups, this is safe because software events never
-			 * fail to schedule.
+			 * Allow the addition of software events to hw
+			 * groups, this is safe because software events
+			 * never fail to schedule.
 			 */
-			pmu = group_leader->pmu;
-		} else if (is_software_event(group_leader) &&
+			pmu = group_leader->ctx->pmu;
+		} else if (!is_software_event(event) &&
+			   is_software_event(group_leader) &&
 			   (group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
 			/*
 			 * In case the group is a pure software group, and we