From da916e96e2dedcb2d40de77a7def833d315b81a6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 25 Oct 2024 10:21:41 +0200 Subject: perf: Make perf_pmu_unregister() useable Previously it was only safe to call perf_pmu_unregister() if there were no active events of that pmu around -- which was impossible to guarantee since it races all sorts against perf_init_event(). Rework the whole thing by: - keeping track of all events for a given pmu - 'hiding' the pmu from perf_init_event() - waiting for the appropriate (s)rcu grace periods such that all prior references to the PMU will be completed - detaching all still existing events of that pmu (see first point) and moving them to a new REVOKED state. - actually freeing the pmu data. Where notably the new REVOKED state must inhibit all event actions from reaching code that wants to use event->pmu. Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Ravi Bangoria Link: https://lkml.kernel.org/r/20250307193723.525402029@infradead.org --- include/linux/perf_event.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0069ba6866a4..7f49a58b271d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -325,6 +325,9 @@ struct perf_output_handle; struct pmu { struct list_head entry; + spinlock_t events_lock; + struct list_head events; + struct module *module; struct device *dev; struct device *parent; @@ -622,9 +625,10 @@ struct perf_addr_filter_range { * enum perf_event_state - the states of an event: */ enum perf_event_state { - PERF_EVENT_STATE_DEAD = -4, - PERF_EVENT_STATE_EXIT = -3, - PERF_EVENT_STATE_ERROR = -2, + PERF_EVENT_STATE_DEAD = -5, + PERF_EVENT_STATE_REVOKED = -4, /* pmu gone, must not touch */ + PERF_EVENT_STATE_EXIT = -3, /* task died, still inherit */ + PERF_EVENT_STATE_ERROR = -2, /* scheduling error, can enable */ PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, @@ -865,6 +869,7 @@ struct perf_event { void *security; #endif struct list_head sb_list; + struct list_head pmu_list; /* * Certain events gets forwarded to another pmu internally by over- @@ -1155,7 +1160,7 @@ extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); -extern void perf_pmu_unregister(struct pmu *pmu); +extern int perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); @@ -1760,7 +1765,7 @@ static inline bool needs_branch_stack(struct perf_event *event) static inline bool has_aux(struct perf_event *event) { - return event->pmu->setup_aux; + return event->pmu && event->pmu->setup_aux; } static inline bool has_aux_action(struct perf_event *event) -- cgit v1.2.3