From bcb9aa45d5a0e11ef91245330c53cde214d15e8d Mon Sep 17 00:00:00 2001 From: Niranjana Vishwanathapura Date: Wed, 15 Jun 2022 00:13:47 +0530 Subject: Revert "drm/i915: Hold reference to intel_context over life of i915_request" This reverts commit 1e98d8c52ed5dfbaf273c4423c636525c2ce59e7. The problem with this patch is that it makes i915_request to hold a reference to intel_context, which in turn holds a reference on the VM. This strong back referencing can lead to reference loops which leads to resource leak. An example is the upcoming VM_BIND work which requires VM to hold a reference to some shared VM specific BO. But this BO's dma-resv fences holds reference to the i915_request thus leading to reference loop. v2: Do not use reserved requests for virtual engines Signed-off-by: Niranjana Vishwanathapura Signed-off-by: Ramalingam C Suggested-by: Matthew Brost Reviewed-by: Mathew Brost Link: https://patchwork.freedesktop.org/patch/msgid/20220614184348.23746-3-ramalingam.c@intel.com --- drivers/gpu/drm/i915/i915_request.c | 52 +++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 20 deletions(-) (limited to 'drivers/gpu/drm/i915/i915_request.c') diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 667dda7668cb..62fad16a55e8 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -134,17 +134,42 @@ static void i915_fence_release(struct dma_fence *fence) i915_sw_fence_fini(&rq->semaphore); /* - * Keep one request on each engine for reserved use under mempressure, + * Keep one request on each engine for reserved use under mempressure * do not use with virtual engines as this really is only needed for * kernel contexts. + * + * We do not hold a reference to the engine here and so have to be + * very careful in what rq->engine we poke. The virtual engine is + * referenced via the rq->context and we released that ref during + * i915_request_retire(), ergo we must not dereference a virtual + * engine here. Not that we would want to, as the only consumer of + * the reserved engine->request_pool is the power management parking, + * which must-not-fail, and that is only run on the physical engines. + * + * Since the request must have been executed to be have completed, + * we know that it will have been processed by the HW and will + * not be unsubmitted again, so rq->engine and rq->execution_mask + * at this point is stable. rq->execution_mask will be a single + * bit if the last and _only_ engine it could execution on was a + * physical engine, if it's multiple bits then it started on and + * could still be on a virtual engine. Thus if the mask is not a + * power-of-two we assume that rq->engine may still be a virtual + * engine and so a dangling invalid pointer that we cannot dereference + * + * For example, consider the flow of a bonded request through a virtual + * engine. The request is created with a wide engine mask (all engines + * that we might execute on). On processing the bond, the request mask + * is reduced to one or more engines. If the request is subsequently + * bound to a single engine, it will then be constrained to only + * execute on that engine and never returned to the virtual engine + * after timeslicing away, see __unwind_incomplete_requests(). Thus we + * know that if the rq->execution_mask is a single bit, rq->engine + * can be a physical engine with the exact corresponding mask. */ if (!intel_engine_is_virtual(rq->engine) && - !cmpxchg(&rq->engine->request_pool, NULL, rq)) { - intel_context_put(rq->context); + is_power_of_2(rq->execution_mask) && + !cmpxchg(&rq->engine->request_pool, NULL, rq)) return; - } - - intel_context_put(rq->context); kmem_cache_free(slab_requests, rq); } @@ -921,19 +946,7 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp) } } - /* - * Hold a reference to the intel_context over life of an i915_request. - * Without this an i915_request can exist after the context has been - * destroyed (e.g. request retired, context closed, but user space holds - * a reference to the request from an out fence). In the case of GuC - * submission + virtual engine, the engine that the request references - * is also destroyed which can trigger bad pointer dref in fence ops - * (e.g. i915_fence_get_driver_name). We could likely change these - * functions to avoid touching the engine but let's just be safe and - * hold the intel_context reference. In execlist mode the request always - * eventually points to a physical engine so this isn't an issue. - */ - rq->context = intel_context_get(ce); + rq->context = ce; rq->engine = ce->engine; rq->ring = ce->ring; rq->execution_mask = ce->engine->mask; @@ -1009,7 +1022,6 @@ err_unwind: GEM_BUG_ON(!list_empty(&rq->sched.waiters_list)); err_free: - intel_context_put(ce); kmem_cache_free(slab_requests, rq); err_unreserve: intel_context_unpin(ce); -- cgit