diff options
Diffstat (limited to 'drivers/gpu/drm/i915')
| -rw-r--r-- | drivers/gpu/drm/i915/display/intel_display.c | 24 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_breadcrumbs.c | 303 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h | 8 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_context.c | 15 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_context_types.h | 23 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_lrc.c | 60 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_mocs.c | 14 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_rps.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gt/shmem_utils.c | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/gvt.h | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_perf.c | 9 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_reg.h | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_request.h | 2 |
13 files changed, 295 insertions, 178 deletions
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 99e682563d47..3bfe6ed67da1 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -18021,16 +18021,6 @@ int intel_modeset_init_nogem(struct drm_i915_private *i915) if (!HAS_GMCH(i915)) sanitize_watermarks(i915); - /* - * Force all active planes to recompute their states. So that on - * mode_setcrtc after probe, all the intel_plane_state variables - * are already calculated and there is no assert_plane warnings - * during bootup. - */ - ret = intel_initial_commit(dev); - if (ret) - drm_dbg_kms(&i915->drm, "Initial commit in probe failed.\n"); - return 0; } @@ -18039,11 +18029,21 @@ int intel_modeset_init(struct drm_i915_private *i915) { int ret; - intel_overlay_setup(i915); - if (!HAS_DISPLAY(i915)) return 0; + /* + * Force all active planes to recompute their states. So that on + * mode_setcrtc after probe, all the intel_plane_state variables + * are already calculated and there is no assert_plane warnings + * during bootup. + */ + ret = intel_initial_commit(&i915->drm); + if (ret) + return ret; + + intel_overlay_setup(i915); + ret = intel_fbdev_init(&i915->drm); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index d8b206e53660..a24cc1ff08a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -30,18 +30,21 @@ #include "i915_trace.h" #include "intel_breadcrumbs.h" #include "intel_context.h" +#include "intel_engine_pm.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" -static void irq_enable(struct intel_engine_cs *engine) +static bool irq_enable(struct intel_engine_cs *engine) { if (!engine->irq_enable) - return; + return false; /* Caller disables interrupts */ spin_lock(&engine->gt->irq_lock); engine->irq_enable(engine); spin_unlock(&engine->gt->irq_lock); + + return true; } static void irq_disable(struct intel_engine_cs *engine) @@ -57,12 +60,11 @@ static void irq_disable(struct intel_engine_cs *engine) static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || b->irq_armed) - return; - - if (!intel_gt_pm_get_if_awake(b->irq_engine->gt)) + /* + * Since we are waiting on a request, the GPU should be busy + * and should have its own rpm reference. + */ + if (GEM_WARN_ON(!intel_gt_pm_get_if_awake(b->irq_engine->gt))) return; /* @@ -73,25 +75,24 @@ static void __intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) */ WRITE_ONCE(b->irq_armed, true); - /* - * Since we are waiting on a request, the GPU should be busy - * and should have its own rpm reference. This is tracked - * by i915->gt.awake, we can forgo holding our own wakref - * for the interrupt as before i915->gt.awake is released (when - * the driver is idle) we disarm the breadcrumbs. - */ - - if (!b->irq_enabled++) - irq_enable(b->irq_engine); + /* Requests may have completed before we could enable the interrupt. */ + if (!b->irq_enabled++ && irq_enable(b->irq_engine)) + irq_work_queue(&b->irq_work); } -static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +static void intel_breadcrumbs_arm_irq(struct intel_breadcrumbs *b) { - lockdep_assert_held(&b->irq_lock); - - if (!b->irq_engine || !b->irq_armed) + if (!b->irq_engine) return; + spin_lock(&b->irq_lock); + if (!b->irq_armed) + __intel_breadcrumbs_arm_irq(b); + spin_unlock(&b->irq_lock); +} + +static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ GEM_BUG_ON(!b->irq_enabled); if (!--b->irq_enabled) irq_disable(b->irq_engine); @@ -100,20 +101,37 @@ static void __intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) intel_gt_pm_put_async(b->irq_engine->gt); } +static void intel_breadcrumbs_disarm_irq(struct intel_breadcrumbs *b) +{ + spin_lock(&b->irq_lock); + if (b->irq_armed) + __intel_breadcrumbs_disarm_irq(b); + spin_unlock(&b->irq_lock); +} + static void add_signaling_context(struct intel_breadcrumbs *b, struct intel_context *ce) { - intel_context_get(ce); - list_add_tail(&ce->signal_link, &b->signalers); - if (list_is_first(&ce->signal_link, &b->signalers)) - __intel_breadcrumbs_arm_irq(b); + lockdep_assert_held(&ce->signal_lock); + + spin_lock(&b->signalers_lock); + list_add_rcu(&ce->signal_link, &b->signalers); + spin_unlock(&b->signalers_lock); } -static void remove_signaling_context(struct intel_breadcrumbs *b, +static bool remove_signaling_context(struct intel_breadcrumbs *b, struct intel_context *ce) { - list_del(&ce->signal_link); - intel_context_put(ce); + lockdep_assert_held(&ce->signal_lock); + + if (!list_empty(&ce->signals)) + return false; + + spin_lock(&b->signalers_lock); + list_del_rcu(&ce->signal_link); + spin_unlock(&b->signalers_lock); + + return true; } static inline bool __request_completed(const struct i915_request *rq) @@ -174,73 +192,103 @@ static void add_retire(struct intel_breadcrumbs *b, struct intel_timeline *tl) intel_engine_add_retire(b->irq_engine, tl); } -static bool __signal_request(struct i915_request *rq, struct list_head *signals) +static bool __signal_request(struct i915_request *rq) { - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); + GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)); if (!__dma_fence_signal(&rq->fence)) { i915_request_put(rq); return false; } - list_add_tail(&rq->signal_link, signals); return true; } +static struct llist_node * +slist_add(struct llist_node *node, struct llist_node *head) +{ + node->next = head; + return node; +} + static void signal_irq_work(struct irq_work *work) { struct intel_breadcrumbs *b = container_of(work, typeof(*b), irq_work); const ktime_t timestamp = ktime_get(); - struct intel_context *ce, *cn; - struct list_head *pos, *next; - LIST_HEAD(signal); - - spin_lock(&b->irq_lock); + struct llist_node *signal, *sn; + struct intel_context *ce; - if (list_empty(&b->signalers)) - __intel_breadcrumbs_disarm_irq(b); + signal = NULL; + if (unlikely(!llist_empty(&b->signaled_requests))) + signal = llist_del_all(&b->signaled_requests); - list_splice_init(&b->signaled_requests, &signal); + /* + * Keep the irq armed until the interrupt after all listeners are gone. + * + * Enabling/disabling the interrupt is rather costly, roughly a couple + * of hundred microseconds. If we are proactive and enable/disable + * the interrupt around every request that wants a breadcrumb, we + * quickly drown in the extra orders of magnitude of latency imposed + * on request submission. + * + * So we try to be lazy, and keep the interrupts enabled until no + * more listeners appear within a breadcrumb interrupt interval (that + * is until a request completes that no one cares about). The + * observation is that listeners come in batches, and will often + * listen to a bunch of requests in succession. Though note on icl+, + * interrupts are always enabled due to concerns with rc6 being + * dysfunctional with per-engine interrupt masking. + * + * We also try to avoid raising too many interrupts, as they may + * be generated by userspace batches and it is unfortunately rather + * too easy to drown the CPU under a flood of GPU interrupts. Thus + * whenever no one appears to be listening, we turn off the interrupts. + * Fewer interrupts should conserve power -- at the very least, fewer + * interrupt draw less ire from other users of the system and tools + * like powertop. + */ + if (!signal && READ_ONCE(b->irq_armed) && list_empty(&b->signalers)) + intel_breadcrumbs_disarm_irq(b); - list_for_each_entry_safe(ce, cn, &b->signalers, signal_link) { - GEM_BUG_ON(list_empty(&ce->signals)); + rcu_read_lock(); + list_for_each_entry_rcu(ce, &b->signalers, signal_link) { + struct i915_request *rq; - list_for_each_safe(pos, next, &ce->signals) { - struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + list_for_each_entry_rcu(rq, &ce->signals, signal_link) { + bool release; - GEM_BUG_ON(!check_signal_order(ce, rq)); if (!__request_completed(rq)) break; + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, + &rq->fence.flags)) + break; + /* * Queue for execution after dropping the signaling * spinlock as the callback chain may end up adding * more signalers to the same context or engine. */ - __signal_request(rq, &signal); - } + spin_lock(&ce->signal_lock); + list_del_rcu(&rq->signal_link); + release = remove_signaling_context(b, ce); + spin_unlock(&ce->signal_lock); - /* - * We process the list deletion in bulk, only using a list_add - * (not list_move) above but keeping the status of - * rq->signal_link known with the I915_FENCE_FLAG_SIGNAL bit. - */ - if (!list_is_first(pos, &ce->signals)) { - /* Advance the list to the first incomplete request */ - __list_del_many(&ce->signals, pos); - if (&ce->signals == pos) { /* now empty */ + if (__signal_request(rq)) + /* We own signal_node now, xfer to local list */ + signal = slist_add(&rq->signal_node, signal); + + if (release) { add_retire(b, ce->timeline); - remove_signaling_context(b, ce); + intel_context_put(ce); } } } + rcu_read_unlock(); - spin_unlock(&b->irq_lock); - - list_for_each_safe(pos, next, &signal) { + llist_for_each_safe(signal, sn, signal) { struct i915_request *rq = - list_entry(pos, typeof(*rq), signal_link); + llist_entry(signal, typeof(*rq), signal_node); struct list_head cb_list; spin_lock(&rq->lock); @@ -251,6 +299,9 @@ static void signal_irq_work(struct irq_work *work) i915_request_put(rq); } + + if (!READ_ONCE(b->irq_armed) && !list_empty(&b->signalers)) + intel_breadcrumbs_arm_irq(b); } struct intel_breadcrumbs * @@ -262,14 +313,15 @@ intel_breadcrumbs_create(struct intel_engine_cs *irq_engine) if (!b) return NULL; - spin_lock_init(&b->irq_lock); + b->irq_engine = irq_engine; + + spin_lock_init(&b->signalers_lock); INIT_LIST_HEAD(&b->signalers); - INIT_LIST_HEAD(&b->signaled_requests); + init_llist_head(&b->signaled_requests); + spin_lock_init(&b->irq_lock); init_irq_work(&b->irq_work, signal_irq_work); - b->irq_engine = irq_engine; - return b; } @@ -292,27 +344,28 @@ void intel_breadcrumbs_reset(struct intel_breadcrumbs *b) void intel_breadcrumbs_park(struct intel_breadcrumbs *b) { - unsigned long flags; - - if (!READ_ONCE(b->irq_armed)) - return; - - spin_lock_irqsave(&b->irq_lock, flags); - __intel_breadcrumbs_disarm_irq(b); - spin_unlock_irqrestore(&b->irq_lock, flags); - - if (!list_empty(&b->signalers)) - irq_work_queue(&b->irq_work); + /* Kick the work once more to drain the signalers */ + irq_work_sync(&b->irq_work); + while (unlikely(READ_ONCE(b->irq_armed))) { + local_irq_disable(); + signal_irq_work(&b->irq_work); + local_irq_enable(); + cond_resched(); + } + GEM_BUG_ON(!list_empty(&b->signalers)); } void intel_breadcrumbs_free(struct intel_breadcrumbs *b) { + irq_work_sync(&b->irq_work); + GEM_BUG_ON(!list_empty(&b->signalers)); + GEM_BUG_ON(b->irq_armed); kfree(b); } -static void insert_breadcrumb(struct i915_request *rq, - struct intel_breadcrumbs *b) +static void insert_breadcrumb(struct i915_request *rq) { + struct intel_breadcrumbs *b = READ_ONCE(rq->engine)->breadcrumbs; struct intel_context *ce = rq->context; struct list_head *pos; @@ -327,12 +380,14 @@ static void insert_breadcrumb(struct i915_request *rq, * its signal completion. */ if (__request_completed(rq)) { - if (__signal_request(rq, &b->signaled_requests)) + if (__signal_request(rq) && + llist_add(&rq->signal_node, &b->signaled_requests)) irq_work_queue(&b->irq_work); return; } if (list_empty(&ce->signals)) { + intel_context_get(ce); add_signaling_context(b, ce); pos = &ce->signals; } else { @@ -358,18 +413,22 @@ static void insert_breadcrumb(struct i915_request *rq, break; } } - list_add(&rq->signal_link, pos); + list_add_rcu(&rq->signal_link, pos); GEM_BUG_ON(!check_signal_order(ce, rq)); + GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)); set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - /* Check after attaching to irq, interrupt may have already fired. */ - if (__request_completed(rq)) - irq_work_queue(&b->irq_work); + /* + * Defer enabling the interrupt to after HW submission and recheck + * the request as it may have completed and raised the interrupt as + * we were attaching it into the lists. + */ + irq_work_queue(&b->irq_work); } bool i915_request_enable_breadcrumb(struct i915_request *rq) { - struct intel_breadcrumbs *b; + struct intel_context *ce = rq->context; /* Serialises with i915_request_retire() using rq->lock */ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags)) @@ -384,67 +443,30 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq) if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) return true; - /* - * rq->engine is locked by rq->engine->active.lock. That however - * is not known until after rq->engine has been dereferenced and - * the lock acquired. Hence we acquire the lock and then validate - * that rq->engine still matches the lock we hold for it. - * - * Here, we are using the breadcrumb lock as a proxy for the - * rq->engine->active.lock, and we know that since the breadcrumb - * will be serialised within i915_request_submit/i915_request_unsubmit, - * the engine cannot change while active as long as we hold the - * breadcrumb lock on that engine. - * - * From the dma_fence_enable_signaling() path, we are outside of the - * request submit/unsubmit path, and so we must be more careful to - * acquire the right lock. - */ - b = READ_ONCE(rq->engine)->breadcrumbs; - spin_lock(&b->irq_lock); - while (unlikely(b != READ_ONCE(rq->engine)->breadcrumbs)) { - spin_unlock(&b->irq_lock); - b = READ_ONCE(rq->engine)->breadcrumbs; - spin_lock(&b->irq_lock); - } - - /* - * Now that we are finally serialised with request submit/unsubmit, - * [with b->irq_lock] and with i915_request_retire() [via checking - * SIGNALED with rq->lock] confirm the request is indeed active. If - * it is no longer active, the breadcrumb will be attached upon - * i915_request_submit(). - */ + spin_lock(&ce->signal_lock); if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) - insert_breadcrumb(rq, b); - - spin_unlock(&b->irq_lock); + insert_breadcrumb(rq); + spin_unlock(&ce->signal_lock); return true; } void i915_request_cancel_breadcrumb(struct i915_request *rq) { - struct intel_breadcrumbs *b = rq->engine->breadcrumbs; + struct intel_context *ce = rq->context; + bool release; - /* - * We must wait for b->irq_lock so that we know the interrupt handler - * has released its reference to the intel_context and has completed - * the DMA_FENCE_FLAG_SIGNALED_BIT/I915_FENCE_FLAG_SIGNAL dance (if - * required). - */ - spin_lock(&b->irq_lock); - if (test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) { - struct intel_context *ce = rq->context; + if (!test_and_clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags)) + return; - list_del(&rq->signal_link); - if (list_empty(&ce->signals)) - remove_signaling_context(b, ce); + spin_lock(&ce->signal_lock); + list_del_rcu(&rq->signal_link); + release = remove_signaling_context(rq->engine->breadcrumbs, ce); + spin_unlock(&ce->signal_lock); + if (release) + intel_context_put(ce); - clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags); - i915_request_put(rq); - } - spin_unlock(&b->irq_lock); + i915_request_put(rq); } static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p) @@ -454,18 +476,17 @@ static void print_signals(struct intel_breadcrumbs *b, struct drm_printer *p) drm_printf(p, "Signals:\n"); - spin_lock_irq(&b->irq_lock); - list_for_each_entry(ce, &b->signalers, signal_link) { - list_for_each_entry(rq, &ce->signals, signal_link) { + rcu_read_lock(); + list_for_each_entry_rcu(ce, &b->signalers, signal_link) { + list_for_each_entry_rcu(rq, &ce->signals, signal_link) drm_printf(p, "\t[%llx:%llx%s] @ %dms\n", rq->fence.context, rq->fence.seqno, i915_request_completed(rq) ? "!" : i915_request_started(rq) ? "*" : "", jiffies_to_msecs(jiffies - rq->emitted_jiffies)); - } } - spin_unlock_irq(&b->irq_lock); + rcu_read_unlock(); } void intel_engine_print_breadcrumbs(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h index 8e53b9942695..a74bb3062bd8 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs_types.h @@ -29,18 +29,16 @@ * the overhead of waking that client is much preferred. */ struct intel_breadcrumbs { - spinlock_t irq_lock; /* protects the lists used in hardirq context */ - /* Not all breadcrumbs are attached to physical HW */ struct intel_engine_cs *irq_engine; + spinlock_t signalers_lock; /* protects the list of signalers */ struct list_head signalers; - struct list_head signaled_requests; + struct llist_head signaled_requests; + spinlock_t irq_lock; /* protects the interrupt from hardirq context */ struct irq_work irq_work; /* for use from inside irq_lock */ - unsigned int irq_enabled; - bool irq_armed; }; diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 92a3f25c4006..349e7fa1488d 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -25,11 +25,18 @@ static struct intel_context *intel_context_alloc(void) return kmem_cache_zalloc(global.slab_ce, GFP_KERNEL); } -void intel_context_free(struct intel_context *ce) +static void rcu_context_free(struct rcu_head *rcu) { + struct intel_context *ce = container_of(rcu, typeof(*ce), rcu); + kmem_cache_free(global.slab_ce, ce); } +void intel_context_free(struct intel_context *ce) +{ + call_rcu(&ce->rcu, rcu_context_free); +} + struct intel_context * intel_context_create(struct intel_engine_cs *engine) { @@ -356,8 +363,7 @@ static int __intel_context_active(struct i915_active *active) } void -intel_context_init(struct intel_context *ce, - struct intel_engine_cs *engine) +intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine) { GEM_BUG_ON(!engine->cops); GEM_BUG_ON(!engine->gt->vm); @@ -373,7 +379,8 @@ intel_context_init(struct intel_context *ce, ce->vm = i915_vm_get(engine->gt->vm); - INIT_LIST_HEAD(&ce->signal_link); + /* NB ce->signal_link/lock is used under RCU */ + spin_lock_init(&ce->signal_lock); INIT_LIST_HEAD(&ce->signals); mutex_init(&ce->pin_mutex); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 552cb57a2e8c..52fa9c132746 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -25,6 +25,7 @@ DECLARE_EWMA(runtime, 3, 8); struct i915_gem_context; struct i915_gem_ww_ctx; struct i915_vma; +struct intel_breadcrumbs; struct intel_context; struct intel_ring; @@ -44,7 +45,16 @@ struct intel_context_ops { }; struct intel_context { - struct kref ref; + /* + * Note: Some fields may be accessed under RCU. + * + * Unless otherwise noted a field can safely be assumed to be protected + * by strong reference counting. + */ + union { + struct kref ref; /* no kref_get_unless_zero()! */ + struct rcu_head rcu; + }; struct intel_engine_cs *engine; struct intel_engine_cs *inflight; @@ -54,8 +64,15 @@ struct intel_context { struct i915_address_space *vm; struct i915_gem_context __rcu *gem_context; - struct list_head signal_link; - struct list_head signals; + /* + * @signal_lock protects the list of requests that need signaling, + * @signals. While there are any requests that need signaling, + * we add the context to the breadcrumbs worker, and remove it + * upon completion/cancellation of the last request. + */ + struct list_head signal_link; /* Accessed under RCU */ + struct list_head signals; /* Guarded by signal_lock */ + spinlock_t signal_lock; /* protects signals, the list of requests */ struct i915_vma *state; struct intel_ring *ring; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 9bb16bdf93cf..0952bf157234 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -182,6 +182,7 @@ struct virtual_engine { struct intel_engine_cs base; struct intel_context context; + struct rcu_work rcu; /* * We allow only a single request through the virtual engine at a time @@ -5425,33 +5426,57 @@ static struct list_head *virtual_queue(struct virtual_engine *ve) return &ve->base.execlists.default_priolist.requests[0]; } -static void virtual_context_destroy(struct kref *kref) +static void rcu_virtual_context_destroy(struct work_struct *wrk) { struct virtual_engine *ve = - container_of(kref, typeof(*ve), context.ref); + container_of(wrk, typeof(*ve), rcu.work); unsigned int n; - GEM_BUG_ON(!list_empty(virtual_queue(ve))); - GEM_BUG_ON(ve->request); GEM_BUG_ON(ve->context.inflight); + /* Preempt-to-busy may leave a stale request behind. */ + if (unlikely(ve->request)) { + struct i915_request *old; + + spin_lock_irq(&ve->base.active.lock); + + old = fetch_and_zero(&ve->request); + if (old) { + GEM_BUG_ON(!i915_request_completed(old)); + __i915_request_submit(old); + i915_request_put(old); + } + + spin_unlock_irq(&ve->base.active.lock); + } + + /* + * Flush the tasklet in case it is still running on another core. + * + * This needs to be done before we remove ourselves from the siblings' + * rbtrees as in the case it is running in parallel, it may reinsert + * the rb_node into a sibling. + */ + tasklet_kill(&ve->base.execlists.tasklet); + + /* Decouple ourselves from the siblings, no more access allowed. */ for (n = 0; n < ve->num_siblings; n++) { struct intel_engine_cs *sibling = ve->siblings[n]; struct rb_node *node = &ve->nodes[sibling->id].rb; - unsigned long flags; if (RB_EMPTY_NODE(node)) continue; - spin_lock_irqsave(&sibling->active.lock, flags); + spin_lock_irq(&sibling->active.lock); /* Detachment is lazily performed in the execlists tasklet */ if (!RB_EMPTY_NODE(node)) rb_erase_cached(node, &sibling->execlists.virtual); - spin_unlock_irqrestore(&sibling->active.lock, flags); + spin_unlock_irq(&sibling->active.lock); } GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet)); + GEM_BUG_ON(!list_empty(virtual_queue(ve))); if (ve->context.state) __execlists_context_fini(&ve->context); @@ -5464,6 +5489,27 @@ static void virtual_context_destroy(struct kref *kref) kfree(ve); } +static void virtual_context_destroy(struct kref *kref) +{ + struct virtual_engine *ve = + container_of(kref, typeof(*ve), context.ref); + + GEM_BUG_ON(!list_empty(&ve->context.signals)); + + /* + * When destroying the virtual engine, we have to be aware that + * it may still be in use from an hardirq/softirq context causing + * the resubmission of a completed request (background completion + * due to preempt-to-busy). Before we can free the engine, we need + * to flush the submission code and tasklets that are still potentially + * accessing the engine. Flushing the tasklets requires process context, + * and since we can guard the resubmit onto the engine with an RCU read + * lock, we can delegate the free of the engine to an RCU worker. + */ + INIT_RCU_WORK(&ve->rcu, rcu_virtual_context_destroy); + queue_rcu_work(system_wq, &ve->rcu); +} + static void virtual_engine_initial_hint(struct virtual_engine *ve) { int swp; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 313e51e7d4f7..4f74706967fd 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -131,7 +131,19 @@ static const struct drm_i915_mocs_entry skl_mocs_table[] = { GEN9_MOCS_ENTRIES, MOCS_ENTRY(I915_MOCS_CACHED, LE_3_WB | LE_TC_2_LLC_ELLC | LE_LRUM(3), - L3_3_WB) + L3_3_WB), + + /* + * mocs:63 + * - used by the L3 for all of its evictions. + * Thus it is expected to allow LLC cacheability to enable coherent + * flows to be maintained. + * - used to force L3 uncachable cycles. + * Thus it is expected to make the surface L3 uncacheable. + */ + MOCS_ENTRY(63, + LE_3_WB | LE_TC_1_LLC | LE_LRUM(3), + L3_1_UC) }; /* NOTE: the LE_TGT_CACHE is not used on Broxton */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index e6a00eea0631..c1c9cc0ad3b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -883,6 +883,10 @@ void intel_rps_park(struct intel_rps *rps) adj = -2; rps->last_adj = adj; rps->cur_freq = max_t(int, rps->cur_freq + adj, rps->min_freq); + if (rps->cur_freq < rps->efficient_freq) { + rps->cur_freq = rps->efficient_freq; + rps->last_adj = 0; + } GT_TRACE(rps_to_gt(rps), "park:%x\n", rps->cur_freq); } diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index f011ea42487e..463af675fadd 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -103,10 +103,13 @@ static int __shmem_rw(struct file *file, loff_t off, return PTR_ERR(page); vaddr = kmap(page); - if (write) + if (write) { memcpy(vaddr + offset_in_page(off), ptr, this); - else + set_page_dirty(page); + } else { memcpy(ptr, vaddr + offset_in_page(off), this); + } + mark_page_accessed(page); kunmap(page); put_page(page); diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 9831361f181e..a81cf0f01e78 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -255,7 +255,7 @@ struct intel_gvt_mmio { #define F_CMD_ACCESS (1 << 3) /* This reg has been accessed by a VM */ #define F_ACCESSED (1 << 4) -/* This reg has been accessed through GPU commands */ +/* This reg could be accessed by unaligned address */ #define F_UNALIGN (1 << 6) /* This reg is in GVT's mmio save-restor list and in hardware * logical context image diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index e94976976571..3640d0e229d2 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -909,8 +909,13 @@ static int gen8_oa_read(struct i915_perf_stream *stream, DRM_I915_PERF_RECORD_OA_REPORT_LOST); if (ret) return ret; - intel_uncore_write(uncore, oastatus_reg, - oastatus & ~GEN8_OASTATUS_REPORT_LOST); + + intel_uncore_rmw(uncore, oastatus_reg, + GEN8_OASTATUS_COUNTER_OVERFLOW | + GEN8_OASTATUS_REPORT_LOST, + IS_GEN_RANGE(uncore->i915, 8, 10) ? + (GEN8_OASTATUS_HEAD_POINTER_WRAP | + GEN8_OASTATUS_TAIL_POINTER_WRAP) : 0); } return gen8_append_oa_reports(stream, buf, count, offset); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 664f3bf9af03..5cd83eac940c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -676,6 +676,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GEN7_OASTATUS2_MEM_SELECT_GGTT (1 << 0) /* 0: PPGTT, 1: GGTT */ #define GEN8_OASTATUS _MMIO(0x2b08) +#define GEN8_OASTATUS_TAIL_POINTER_WRAP (1 << 17) +#define GEN8_OASTATUS_HEAD_POINTER_WRAP (1 << 16) #define GEN8_OASTATUS_OVERRUN_STATUS (1 << 3) #define GEN8_OASTATUS_COUNTER_OVERFLOW (1 << 2) #define GEN8_OASTATUS_OABUFFER_OVERFLOW (1 << 1) diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h index 16b721080195..620b6fab2c5c 100644 --- a/drivers/gpu/drm/i915/i915_request.h +++ b/drivers/gpu/drm/i915/i915_request.h @@ -176,7 +176,9 @@ struct i915_request { struct intel_context *context; struct intel_ring *ring; struct intel_timeline __rcu *timeline; + struct list_head signal_link; + struct llist_node signal_node; /* * The rcu epoch of when this request was allocated. Used to judiciously |