diff options
Diffstat (limited to 'drivers/gpu/drm/i915/i915_active.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_active.c | 152 |
1 files changed, 88 insertions, 64 deletions
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index 7412abf166a8..6b0c1162505a 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -92,8 +92,7 @@ static void debug_active_init(struct i915_active *ref) static void debug_active_activate(struct i915_active *ref) { lockdep_assert_held(&ref->tree_lock); - if (!atomic_read(&ref->count)) /* before the first inc */ - debug_object_activate(ref, &active_debug_desc); + debug_object_activate(ref, &active_debug_desc); } static void debug_active_deactivate(struct i915_active *ref) @@ -213,7 +212,7 @@ active_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb) struct i915_active_fence *active = container_of(cb, typeof(*active), cb); - return cmpxchg(__active_fence_slot(active), fence, NULL) == fence; + return try_cmpxchg(__active_fence_slot(active), &fence, NULL); } static void @@ -258,10 +257,9 @@ static struct active_node *__active_lookup(struct i915_active *ref, u64 idx) * claimed the cache and we know that is does not match our * idx. If, and only if, the timeline is currently zero is it * worth competing to claim it atomically for ourselves (for - * only the winner of that race will cmpxchg return the old - * value of 0). + * only the winner of that race will cmpxchg succeed). */ - if (!cached && !cmpxchg64(&it->timeline, 0, idx)) + if (!cached && try_cmpxchg64(&it->timeline, &cached, idx)) return it; } @@ -422,12 +420,12 @@ replace_barrier(struct i915_active *ref, struct i915_active_fence *active) * we can use it to substitute for the pending idle-barrer * request that we want to emit on the kernel_context. */ - __active_del_barrier(ref, node_from_active(active)); - return true; + return __active_del_barrier(ref, node_from_active(active)); } int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) { + u64 idx = i915_request_timeline(rq)->fence_context; struct dma_fence *fence = &rq->fence; struct i915_active_fence *active; int err; @@ -437,18 +435,24 @@ int i915_active_add_request(struct i915_active *ref, struct i915_request *rq) if (err) return err; - active = active_instance(ref, i915_request_timeline(rq)->fence_context); - if (!active) { - err = -ENOMEM; - goto out; - } + do { + active = active_instance(ref, idx); + if (!active) { + err = -ENOMEM; + goto out; + } - if (replace_barrier(ref, active)) { - RCU_INIT_POINTER(active->fence, NULL); - atomic_dec(&ref->count); - } - if (!__i915_active_fence_set(active, fence)) + if (replace_barrier(ref, active)) { + RCU_INIT_POINTER(active->fence, NULL); + atomic_dec(&ref->count); + } + } while (unlikely(is_barrier(active))); + + fence = __i915_active_fence_set(active, fence); + if (!fence) __i915_active_acquire(ref); + else + dma_fence_put(fence); out: i915_active_release(ref); @@ -467,13 +471,9 @@ __i915_active_set_fence(struct i915_active *ref, return NULL; } - rcu_read_lock(); prev = __i915_active_fence_set(active, fence); - if (prev) - prev = dma_fence_get_rcu(prev); - else + if (!prev) __i915_active_acquire(ref); - rcu_read_unlock(); return prev; } @@ -526,24 +526,6 @@ int i915_active_acquire(struct i915_active *ref) return err; } -int i915_active_acquire_for_context(struct i915_active *ref, u64 idx) -{ - struct i915_active_fence *active; - int err; - - err = i915_active_acquire(ref); - if (err) - return err; - - active = active_instance(ref, idx); - if (!active) { - i915_active_release(ref); - return -ENOMEM; - } - - return 0; /* return with active ref */ -} - void i915_active_release(struct i915_active *ref) { debug_active_assert(ref); @@ -1017,10 +999,11 @@ void i915_request_add_active_barriers(struct i915_request *rq) * * Records the new @fence as the last active fence along its timeline in * this active tracker, moving the tracking callbacks from the previous - * fence onto this one. Returns the previous fence (if not already completed), - * which the caller must ensure is executed before the new fence. To ensure - * that the order of fences within the timeline of the i915_active_fence is - * understood, it should be locked by the caller. + * fence onto this one. Gets and returns a reference to the previous fence + * (if not already completed), which the caller must put after making sure + * that it is executed before the new fence. To ensure that the order of + * fences within the timeline of the i915_active_fence is understood, it + * should be locked by the caller. */ struct dma_fence * __i915_active_fence_set(struct i915_active_fence *active, @@ -1029,7 +1012,23 @@ __i915_active_fence_set(struct i915_active_fence *active, struct dma_fence *prev; unsigned long flags; - if (fence == rcu_access_pointer(active->fence)) + /* + * In case of fences embedded in i915_requests, their memory is + * SLAB_FAILSAFE_BY_RCU, then it can be reused right after release + * by new requests. Then, there is a risk of passing back a pointer + * to a new, completely unrelated fence that reuses the same memory + * while tracked under a different active tracker. Combined with i915 + * perf open/close operations that build await dependencies between + * engine kernel context requests and user requests from different + * timelines, this can lead to dependency loops and infinite waits. + * + * As a countermeasure, we try to get a reference to the active->fence + * first, so if we succeed and pass it back to our user then it is not + * released and potentially reused by an unrelated request before the + * user has a chance to set up an await dependency on it. + */ + prev = i915_active_fence_get(active); + if (fence == prev) return fence; GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)); @@ -1038,27 +1037,56 @@ __i915_active_fence_set(struct i915_active_fence *active, * Consider that we have two threads arriving (A and B), with * C already resident as the active->fence. * - * A does the xchg first, and so it sees C or NULL depending - * on the timing of the interrupt handler. If it is NULL, the - * previous fence must have been signaled and we know that - * we are first on the timeline. If it is still present, - * we acquire the lock on that fence and serialise with the interrupt - * handler, in the process removing it from any future interrupt - * callback. A will then wait on C before executing (if present). - * - * As B is second, it sees A as the previous fence and so waits for - * it to complete its transition and takes over the occupancy for - * itself -- remembering that it needs to wait on A before executing. + * Both A and B have got a reference to C or NULL, depending on the + * timing of the interrupt handler. Let's assume that if A has got C + * then it has locked C first (before B). * * Note the strong ordering of the timeline also provides consistent * nesting rules for the fence->lock; the inner lock is always the * older lock. */ spin_lock_irqsave(fence->lock, flags); - prev = xchg(__active_fence_slot(active), fence); - if (prev) { - GEM_BUG_ON(prev == fence); + if (prev) spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + + /* + * A does the cmpxchg first, and so it sees C or NULL, as before, or + * something else, depending on the timing of other threads and/or + * interrupt handler. If not the same as before then A unlocks C if + * applicable and retries, starting from an attempt to get a new + * active->fence. Meanwhile, B follows the same path as A. + * Once A succeeds with cmpxch, B fails again, retires, gets A from + * active->fence, locks it as soon as A completes, and possibly + * succeeds with cmpxchg. + */ + while (cmpxchg(__active_fence_slot(active), prev, fence) != prev) { + if (prev) { + spin_unlock(prev->lock); + dma_fence_put(prev); + } + spin_unlock_irqrestore(fence->lock, flags); + + prev = i915_active_fence_get(active); + GEM_BUG_ON(prev == fence); + + spin_lock_irqsave(fence->lock, flags); + if (prev) + spin_lock_nested(prev->lock, SINGLE_DEPTH_NESTING); + } + + /* + * If prev is NULL then the previous fence must have been signaled + * and we know that we are first on the timeline. If it is still + * present then, having the lock on that fence already acquired, we + * serialise with the interrupt handler, in the process of removing it + * from any future interrupt callback. A will then wait on C before + * executing (if present). + * + * As B is second, it sees A as the previous fence and so waits for + * it to complete its transition and takes over the occupancy for + * itself -- remembering that it needs to wait on A before executing. + */ + if (prev) { __list_del_entry(&active->cb.node); spin_unlock(prev->lock); /* serialise with prev->cb_list */ } @@ -1075,11 +1103,7 @@ int i915_active_fence_set(struct i915_active_fence *active, int err = 0; /* Must maintain timeline ordering wrt previous active requests */ - rcu_read_lock(); fence = __i915_active_fence_set(active, &rq->fence); - if (fence) /* but the previous fence may not belong to that timeline! */ - fence = dma_fence_get_rcu(fence); - rcu_read_unlock(); if (fence) { err = i915_request_await_dma_fence(rq, fence); dma_fence_put(fence); |