From 9bb36cf66091ddf2d8840e5aa705ad3c93a6279b Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 18 Dec 2020 12:24:21 +0000 Subject: [PATCH] drm/i915: Check for rq->hwsp validity after acquiring RCU lock Since we allow removing the timeline map at runtime, there is a risk that rq->hwsp points into a stale page. To control that risk, we hold the RCU read lock while reading *rq->hwsp, but we missed a couple of important barriers. First, the unpinning / removal of the timeline map must be after all RCU readers into that map are complete, i.e. after an rcu barrier (in this case courtesy of call_rcu()). Secondly, we must make sure that the rq->hwsp we are about to dereference under the RCU lock is valid. In this case, we make the rq->hwsp pointer safe during i915_request_retire() and so we know that rq->hwsp may become invalid only after the request has been signaled. Therefore is the request is not yet signaled when we acquire rq->hwsp under the RCU, we know that rq->hwsp will remain valid for the duration of the RCU read lock. This is a very small window that may lead to either considering the request not completed (causing a delay until the request is checked again, any wait for the request is not affected) or dereferencing an invalid pointer. Fixes: 3adac4689f58 ("drm/i915: Introduce concept of per-timeline (context) HWSP") Signed-off-by: Chris Wilson Cc: Tvrtko Ursulin Cc: # v5.1+ Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20201218122421.18344-1-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 11 +++------ drivers/gpu/drm/i915/gt/intel_timeline.c | 10 ++++---- drivers/gpu/drm/i915/i915_request.h | 37 +++++++++++++++++++++++++---- 3 files changed, 39 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 3c62fd6..f96cd7d 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -134,11 +134,6 @@ static bool remove_signaling_context(struct intel_breadcrumbs *b, return true; } -static inline bool __request_completed(const struct i915_request *rq) -{ - return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno); -} - __maybe_unused static bool check_signal_order(struct intel_context *ce, struct i915_request *rq) { @@ -245,7 +240,7 @@ static void signal_irq_work(struct irq_work *work) list_for_each_entry_rcu(rq, &ce->signals, signal_link) { bool release; - if (!__request_completed(rq)) + if (!__i915_request_is_complete(rq)) break; if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, @@ -380,7 +375,7 @@ static void insert_breadcrumb(struct i915_request *rq) * straight onto a signaled list, and queue the irq worker for * its signal completion. */ - if (__request_completed(rq)) { + if (__i915_request_is_complete(rq)) { irq_signal_request(rq, b); return; } @@ -468,7 +463,7 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq) if (release) intel_context_put(ce); - if (__request_completed(rq)) + if (__i915_request_is_complete(rq)) irq_signal_request(rq, b); i915_request_put(rq); diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 512afac..a005d01 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -126,6 +126,10 @@ static void __rcu_cacheline_free(struct rcu_head *rcu) struct intel_timeline_cacheline *cl = container_of(rcu, typeof(*cl), rcu); + /* Must wait until after all *rq->hwsp are complete before removing */ + i915_gem_object_unpin_map(cl->hwsp->vma->obj); + __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); + i915_active_fini(&cl->active); kfree(cl); } @@ -133,11 +137,6 @@ static void __rcu_cacheline_free(struct rcu_head *rcu) static void __idle_cacheline_free(struct intel_timeline_cacheline *cl) { GEM_BUG_ON(!i915_active_is_idle(&cl->active)); - - i915_gem_object_unpin_map(cl->hwsp->vma->obj); - i915_vma_put(cl->hwsp->vma); - __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); - call_rcu(&cl->rcu, __rcu_cacheline_free); } @@ -179,7 +178,6 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline) return ERR_CAST(vaddr); } - i915_vma_get(hwsp->vma); cl->hwsp = hwsp; cl->vaddr = page_pack_bits(vaddr, cacheline); diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 92e4320..7c4453e 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -440,7 +440,7 @@ static inline u32 hwsp_seqno(const struct i915_request *rq) static inline bool __i915_request_has_started(const struct i915_request *rq) { - return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno - 1); + return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno - 1); } /** @@ -471,11 +471,19 @@ static inline bool __i915_request_has_started(const struct i915_request *rq) */ static inline bool i915_request_started(const struct i915_request *rq) { + bool result; + if (i915_request_signaled(rq)) return true; - /* Remember: started but may have since been preempted! */ - return __i915_request_has_started(rq); + result = true; + rcu_read_lock(); /* the HWSP may be freed at runtime */ + if (likely(!i915_request_signaled(rq))) + /* Remember: started but may have since been preempted! */ + result = __i915_request_has_started(rq); + rcu_read_unlock(); + + return result; } /** @@ -488,10 +496,16 @@ static inline bool i915_request_started(const struct i915_request *rq) */ static inline bool i915_request_is_running(const struct i915_request *rq) { + bool result; + if (!i915_request_is_active(rq)) return false; - return __i915_request_has_started(rq); + rcu_read_lock(); + result = __i915_request_has_started(rq) && i915_request_is_active(rq); + rcu_read_unlock(); + + return result; } /** @@ -515,12 +529,25 @@ static inline bool i915_request_is_ready(const struct i915_request *rq) return !list_empty(&rq->sched.link); } +static inline bool __i915_request_is_complete(const struct i915_request *rq) +{ + return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno); +} + static inline bool i915_request_completed(const struct i915_request *rq) { + bool result; + if (i915_request_signaled(rq)) return true; - return i915_seqno_passed(hwsp_seqno(rq), rq->fence.seqno); + result = true; + rcu_read_lock(); /* the HWSP may be freed at runtime */ + if (likely(!i915_request_signaled(rq))) + result = __i915_request_is_complete(rq); + rcu_read_unlock(); + + return result; } static inline void i915_request_mark_complete(struct i915_request *rq) -- 2.7.4