diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 8d772bd6894d..efd14c79fab4 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -28,6 +28,44 @@ extern tracepoint_ptr_t __stop___tracepoints_ptrs[]; DEFINE_SRCU(tracepoint_srcu); EXPORT_SYMBOL_GPL(tracepoint_srcu); +enum tp_transition_sync { + TP_TRANSITION_SYNC_1_0_1, + TP_TRANSITION_SYNC_N_2_1, + + _NR_TP_TRANSITION_SYNC, +}; + +struct tp_transition_snapshot { + unsigned long rcu; + unsigned long srcu; + bool ongoing; +}; + +/* Protected by tracepoints_mutex */ +static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC]; + +static void tp_rcu_get_state(enum tp_transition_sync sync) +{ + struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync]; + + /* Keep the latest get_state snapshot. */ + snapshot->rcu = get_state_synchronize_rcu(); + snapshot->srcu = start_poll_synchronize_srcu(&tracepoint_srcu); + snapshot->ongoing = true; +} + +static void tp_rcu_cond_sync(enum tp_transition_sync sync) +{ + struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync]; + + if (!snapshot->ongoing) + return; + cond_synchronize_rcu(snapshot->rcu); + if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu)) + synchronize_srcu(&tracepoint_srcu); + snapshot->ongoing = false; +} + /* Set to 1 to enable tracepoint debug output */ static const int tracepoint_debug; @@ -311,6 +349,11 @@ static int tracepoint_add_func(struct tracepoint *tp, */ switch (nr_func_state(tp_funcs)) { case TP_FUNC_1: /* 0->1 */ + /* + * Make sure new static func never uses old data after a + * 1->0->1 transition sequence. + */ + tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1); /* Set static call to first function */ tracepoint_update_call(tp, tp_funcs); /* Both iterator and static call handle NULL tp->funcs */ @@ -325,10 +368,15 @@ static int tracepoint_add_func(struct tracepoint *tp, * Requires ordering between RCU assign/dereference and * static call update/call. */ - rcu_assign_pointer(tp->funcs, tp_funcs); - break; + fallthrough; case TP_FUNC_N: /* N->N+1 (N>1) */ rcu_assign_pointer(tp->funcs, tp_funcs); + /* + * Make sure static func never uses incorrect data after a + * N->...->2->1 (N>1) transition sequence. + */ + if (tp_funcs[0].data != old[0].data) + tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); break; default: WARN_ON_ONCE(1); @@ -372,24 +420,23 @@ static int tracepoint_remove_func(struct tracepoint *tp, /* Both iterator and static call handle NULL tp->funcs */ rcu_assign_pointer(tp->funcs, NULL); /* - * Make sure new func never uses old data after a 1->0->1 - * transition sequence. - * Considering that transition 0->1 is the common case - * and don't have rcu-sync, issue rcu-sync after - * transition 1->0 to break that sequence by waiting for - * readers to be quiescent. + * Make sure new static func never uses old data after a + * 1->0->1 transition sequence. */ - tracepoint_synchronize_unregister(); + tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1); break; case TP_FUNC_1: /* 2->1 */ rcu_assign_pointer(tp->funcs, tp_funcs); /* - * On 2->1 transition, RCU sync is needed before setting - * static call to first callback, because the observer - * may have loaded any prior tp->funcs after the last one - * associated with an rcu-sync. + * Make sure static func never uses incorrect data after a + * N->...->2->1 (N>2) transition sequence. If the first + * element's data has changed, then force the synchronization + * to prevent current readers that have loaded the old data + * from calling the new function. */ - tracepoint_synchronize_unregister(); + if (tp_funcs[0].data != old[0].data) + tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); + tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1); /* Set static call to first function */ tracepoint_update_call(tp, tp_funcs); break; @@ -397,6 +444,12 @@ static int tracepoint_remove_func(struct tracepoint *tp, fallthrough; case TP_FUNC_N: rcu_assign_pointer(tp->funcs, tp_funcs); + /* + * Make sure static func never uses incorrect data after a + * N->...->2->1 (N>2) transition sequence. + */ + if (tp_funcs[0].data != old[0].data) + tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1); break; default: WARN_ON_ONCE(1);