perf: Support only inheriting events if cloned with CLONE_THREAD

Adds bit perf_event_attr::inherit_thread, to restricting inheriting
events only if the child was cloned with CLONE_THREAD.

This option supports the case where an event is supposed to be
process-wide only (including subthreads), but should not propagate
beyond the current process's shared environment.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Marco Elver <elver@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/YBvj6eJR%2FDY2TsEB@hirez.programming.kicks-ass.net/

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3d478ab..1660039 100644 (file)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -958,7 +958,7 @@ extern void __perf_event_task_sched_in(struct task_struct *prev,
                                       struct task_struct *task);
 extern void __perf_event_task_sched_out(struct task_struct *prev,
                                        struct task_struct *next);
-extern int perf_event_init_task(struct task_struct *child);
+extern int perf_event_init_task(struct task_struct *child, u64 clone_flags);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
 extern void perf_event_delayed_put(struct task_struct *task);
@@ -1449,7 +1449,8 @@ perf_event_task_sched_in(struct task_struct *prev,
 static inline void
 perf_event_task_sched_out(struct task_struct *prev,
                          struct task_struct *next)                     { }
-static inline int perf_event_init_task(struct task_struct *child)      { return 0; }
+static inline int perf_event_init_task(struct task_struct *child,
+                                      u64 clone_flags)                 { return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)     { }
 static inline void perf_event_free_task(struct task_struct *task)      { }
 static inline void perf_event_delayed_put(struct task_struct *task)    { }

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index ad15e40..813efb6 100644 (file)
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -389,7 +389,8 @@ struct perf_event_attr {
                                cgroup         :  1, /* include cgroup events */
                                text_poke      :  1, /* include text poke events */
                                build_id       :  1, /* use build id in mmap2 events */
-                               __reserved_1   : 29;
+                               inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
+                               __reserved_1   : 28;
 
        union {
                __u32           wakeup_events;    /* wakeup every n events */

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 10ed2cd..3e3c00f 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11653,6 +11653,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
            (attr->sample_type & PERF_SAMPLE_WEIGHT_STRUCT))
                return -EINVAL;
 
+       if (!attr->inherit && attr->inherit_thread)
+               return -EINVAL;
+
 out:
        return ret;
 
@@ -12873,12 +12876,13 @@ static int
 inherit_task_group(struct perf_event *event, struct task_struct *parent,
                   struct perf_event_context *parent_ctx,
                   struct task_struct *child, int ctxn,
-                  int *inherited_all)
+                  u64 clone_flags, int *inherited_all)
 {
        int ret;
        struct perf_event_context *child_ctx;
 
-       if (!event->attr.inherit) {
+       if (!event->attr.inherit ||
+           (event->attr.inherit_thread && !(clone_flags & CLONE_THREAD))) {
                *inherited_all = 0;
                return 0;
        }
@@ -12910,7 +12914,8 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent,
 /*
  * Initialize the perf_event context in task_struct
  */
-static int perf_event_init_context(struct task_struct *child, int ctxn)
+static int perf_event_init_context(struct task_struct *child, int ctxn,
+                                  u64 clone_flags)
 {
        struct perf_event_context *child_ctx, *parent_ctx;
        struct perf_event_context *cloned_ctx;
@@ -12950,7 +12955,8 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
         */
        perf_event_groups_for_each(event, &parent_ctx->pinned_groups) {
                ret = inherit_task_group(event, parent, parent_ctx,
-                                        child, ctxn, &inherited_all);
+                                        child, ctxn, clone_flags,
+                                        &inherited_all);
                if (ret)
                        goto out_unlock;
        }
@@ -12966,7 +12972,8 @@ static int perf_event_init_context(struct task_struct *child, int ctxn)
 
        perf_event_groups_for_each(event, &parent_ctx->flexible_groups) {
                ret = inherit_task_group(event, parent, parent_ctx,
-                                        child, ctxn, &inherited_all);
+                                        child, ctxn, clone_flags,
+                                        &inherited_all);
                if (ret)
                        goto out_unlock;
        }
@@ -13008,7 +13015,7 @@ out_unlock:
 /*
  * Initialize the perf_event context in task_struct
  */
-int perf_event_init_task(struct task_struct *child)
+int perf_event_init_task(struct task_struct *child, u64 clone_flags)
 {
        int ctxn, ret;
 
@@ -13017,7 +13024,7 @@ int perf_event_init_task(struct task_struct *child)
        INIT_LIST_HEAD(&child->perf_event_list);
 
        for_each_task_context_nr(ctxn) {
-               ret = perf_event_init_context(child, ctxn);
+               ret = perf_event_init_context(child, ctxn, clone_flags);
                if (ret) {
                        perf_event_free_task(child);
                        return ret;

diff --git a/kernel/fork.c b/kernel/fork.c
index 0acc8ed..3728a64 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2078,7 +2078,7 @@ static __latent_entropy struct task_struct *copy_process(
        if (retval)
                goto bad_fork_cleanup_policy;
 
-       retval = perf_event_init_task(p);
+       retval = perf_event_init_task(p, clone_flags);
        if (retval)
                goto bad_fork_cleanup_policy;
        retval = audit_alloc(p);