return 0;
}
-void i915_gem_contexts_lost(struct drm_i915_private *dev_priv)
-{
- struct intel_engine_cs *engine;
- enum intel_engine_id id;
-
- lockdep_assert_held(&dev_priv->drm.struct_mutex);
-
- for_each_engine(engine, dev_priv, id)
- intel_engine_lost_context(engine);
-}
-
void i915_gem_contexts_fini(struct drm_i915_private *i915)
{
lockdep_assert_held(&i915->drm.struct_mutex);
if (ret)
goto out_add;
- ret = gen8_emit_rpcs_config(rq, ce, sseu);
- if (ret)
- goto out_add;
-
/*
* Guarantee context image and the timeline remains pinned until the
* modifying request is retired by setting the ce activity tracker.
* But we only need to take one pin on the account of it. Or in other
* words transfer the pinned ce object to tracked active request.
*/
- if (!i915_active_request_isset(&ce->active_tracker))
- __intel_context_pin(ce);
- __i915_active_request_set(&ce->active_tracker, rq);
+ GEM_BUG_ON(i915_active_is_idle(&ce->active));
+ ret = i915_active_ref(&ce->active, rq->fence.context, rq);
+ if (ret)
+ goto out_add;
+
+ ret = gen8_emit_rpcs_config(rq, ce, sseu);
out_add:
i915_request_add(rq);
/* i915_gem_context.c */
int __must_check i915_gem_contexts_init(struct drm_i915_private *dev_priv);
-void i915_gem_contexts_lost(struct drm_i915_private *dev_priv);
void i915_gem_contexts_fini(struct drm_i915_private *dev_priv);
int i915_gem_context_open(struct drm_i915_private *i915,
#include "i915_drv.h"
#include "i915_globals.h"
+static void call_idle_barriers(struct intel_engine_cs *engine)
+{
+ struct llist_node *node, *next;
+
+ llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks)) {
+ struct i915_active_request *active =
+ container_of((struct list_head *)node,
+ typeof(*active), link);
+
+ INIT_LIST_HEAD(&active->link);
+ RCU_INIT_POINTER(active->request, NULL);
+
+ active->retire(active, NULL);
+ }
+}
+
static void i915_gem_park(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
lockdep_assert_held(&i915->drm.struct_mutex);
- for_each_engine(engine, i915, id)
+ for_each_engine(engine, i915, id) {
+ call_idle_barriers(engine); /* cleanup after wedging */
i915_gem_batch_pool_fini(&engine->batch_pool);
+ }
i915_timelines_park(i915);
i915_vma_parked(i915);
return 0;
/*
- * When shrinking the active list, also consider active contexts.
- * Active contexts are pinned until they are retired, and so can
- * not be simply unbound to retire and unpin their pages. To shrink
- * the contexts, we must wait until the gpu is idle.
- *
- * We don't care about errors here; if we cannot wait upon the GPU,
- * we will free as much as we can and hope to get a second chance.
+ * When shrinking the active list, we should also consider active
+ * contexts. Active contexts are pinned until they are retired, and
+ * so can not be simply unbound to retire and unpin their pages. To
+ * shrink the contexts, we must wait until the gpu is idle and
+ * completed its switch to the kernel context. In short, we do
+ * not have a good mechanism for idling a specific context.
*/
- if (shrink & I915_SHRINK_ACTIVE)
- i915_gem_wait_for_idle(i915,
- I915_WAIT_LOCKED,
- MAX_SCHEDULE_TIMEOUT);
trace_i915_gem_shrink(i915, target, shrink);
i915_retire_requests(i915);
i915_gem_context_get(ce->gem_context); /* for ctx->ppgtt */
- intel_context_get(ce);
smp_mb__before_atomic(); /* flush pin before it is visible */
}
ce->ops->unpin(ce);
i915_gem_context_put(ce->gem_context);
- intel_context_put(ce);
+ intel_context_active_release(ce);
}
mutex_unlock(&ce->pin_mutex);
intel_context_put(ce);
}
-static void intel_context_retire(struct i915_active_request *active,
- struct i915_request *rq)
+static int __context_pin_state(struct i915_vma *vma, unsigned long flags)
{
- struct intel_context *ce =
- container_of(active, typeof(*ce), active_tracker);
+ int err;
- intel_context_unpin(ce);
+ err = i915_vma_pin(vma, 0, 0, flags | PIN_GLOBAL);
+ if (err)
+ return err;
+
+ /*
+ * And mark it as a globally pinned object to let the shrinker know
+ * it cannot reclaim the object until we release it.
+ */
+ vma->obj->pin_global++;
+ vma->obj->mm.dirty = true;
+
+ return 0;
+}
+
+static void __context_unpin_state(struct i915_vma *vma)
+{
+ vma->obj->pin_global--;
+ __i915_vma_unpin(vma);
+}
+
+static void intel_context_retire(struct i915_active *active)
+{
+ struct intel_context *ce = container_of(active, typeof(*ce), active);
+
+ if (ce->state)
+ __context_unpin_state(ce->state);
+
+ intel_context_put(ce);
}
void
mutex_init(&ce->pin_mutex);
- i915_active_request_init(&ce->active_tracker,
- NULL, intel_context_retire);
+ i915_active_init(ctx->i915, &ce->active, intel_context_retire);
+}
+
+int intel_context_active_acquire(struct intel_context *ce, unsigned long flags)
+{
+ int err;
+
+ if (!i915_active_acquire(&ce->active))
+ return 0;
+
+ intel_context_get(ce);
+
+ if (!ce->state)
+ return 0;
+
+ err = __context_pin_state(ce->state, flags);
+ if (err) {
+ i915_active_cancel(&ce->active);
+ intel_context_put(ce);
+ return err;
+ }
+
+ /* Preallocate tracking nodes */
+ if (!i915_gem_context_is_kernel(ce->gem_context)) {
+ err = i915_active_acquire_preallocate_barrier(&ce->active,
+ ce->engine);
+ if (err) {
+ i915_active_release(&ce->active);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+void intel_context_active_release(struct intel_context *ce)
+{
+ /* Nodes preallocated in intel_context_active() */
+ i915_active_acquire_barrier(&ce->active);
+ i915_active_release(&ce->active);
}
static void i915_global_context_shrink(void)
ce->ops->exit(ce);
}
+int intel_context_active_acquire(struct intel_context *ce, unsigned long flags);
+void intel_context_active_release(struct intel_context *ce);
+
static inline struct intel_context *intel_context_get(struct intel_context *ce)
{
kref_get(&ce->ref);
intel_engine_mask_t saturated; /* submitting semaphores too late? */
/**
- * active_tracker: Active tracker for the external rq activity
- * on this intel_context object.
+ * active: Active tracker for the rq activity (inc. external) on this
+ * intel_context object.
*/
- struct i915_active_request active_tracker;
+ struct i915_active active;
const struct intel_context_ops *ops;
bool intel_engine_is_idle(struct intel_engine_cs *engine);
bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
-void intel_engine_lost_context(struct intel_engine_cs *engine);
-
void intel_engines_reset_default_submission(struct drm_i915_private *i915);
unsigned int intel_engines_has_context_isolation(struct drm_i915_private *i915);
{
int err;
+ init_llist_head(&engine->barrier_tasks);
+
err = init_status_page(engine);
if (err)
return err;
if (engine->preempt_context)
intel_context_unpin(engine->preempt_context);
intel_context_unpin(engine->kernel_context);
+ GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
i915_timeline_fini(&engine->timeline);
engine->set_default_submission(engine);
}
-/**
- * intel_engine_lost_context: called when the GPU is reset into unknown state
- * @engine: the engine
- *
- * We have either reset the GPU or otherwise about to lose state tracking of
- * the current GPU logical state (e.g. suspend). On next use, it is therefore
- * imperative that we make no presumptions about the current state and load
- * from scratch.
- */
-void intel_engine_lost_context(struct intel_engine_cs *engine)
-{
- struct intel_context *ce;
-
- lockdep_assert_held(&engine->i915->drm.struct_mutex);
-
- ce = fetch_and_zero(&engine->last_retired_context);
- if (ce)
- intel_context_unpin(ce);
-}
-
bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
{
switch (INTEL_GEN(engine->i915)) {
/* Check again on the next retirement. */
engine->wakeref_serial = engine->serial + 1;
+
+ i915_request_add_barriers(rq);
__i915_request_commit(rq);
return false;
#include <linux/irq_work.h>
#include <linux/kref.h>
#include <linux/list.h>
+#include <linux/llist.h>
#include <linux/types.h>
#include "i915_gem.h"
struct intel_ring *buffer;
struct i915_timeline timeline;
+ struct llist_head barrier_tasks;
struct intel_context *kernel_context; /* pinned */
struct intel_context *preempt_context; /* pinned; optional */
struct intel_engine_execlists execlists;
- /* Contexts are pinned whilst they are active on the GPU. The last
- * context executed remains active whilst the GPU is idle - the
- * switch away and write to the context object only occurs on the
- * next execution. Contexts are only unpinned on retirement of the
- * following request ensuring that we can always write to the object
- * on the context switch even after idling. Across suspend, we switch
- * to the kernel context and trash it as the save may not happen
- * before the hardware is powered down.
- */
- struct intel_context *last_retired_context;
-
/* status_notifier: list of callbacks for context-switch changes */
struct atomic_notifier_head context_status_notifier;
intel_context_free(ce);
}
-static int __context_pin(struct i915_vma *vma)
-{
- unsigned int flags;
- int err;
-
- flags = PIN_GLOBAL | PIN_HIGH;
- flags |= PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
-
- err = i915_vma_pin(vma, 0, 0, flags);
- if (err)
- return err;
-
- vma->obj->pin_global++;
- vma->obj->mm.dirty = true;
-
- return 0;
-}
-
-static void __context_unpin(struct i915_vma *vma)
-{
- vma->obj->pin_global--;
- __i915_vma_unpin(vma);
-}
-
static void execlists_context_unpin(struct intel_context *ce)
{
- struct intel_engine_cs *engine;
-
- /*
- * The tasklet may still be using a pointer to our state, via an
- * old request. However, since we know we only unpin the context
- * on retirement of the following request, we know that the last
- * request referencing us will have had a completion CS interrupt.
- * If we see that it is still active, it means that the tasklet hasn't
- * had the chance to run yet; let it run before we teardown the
- * reference it may use.
- */
- engine = READ_ONCE(ce->inflight);
- if (unlikely(engine)) {
- unsigned long flags;
-
- spin_lock_irqsave(&engine->timeline.lock, flags);
- process_csb(engine);
- spin_unlock_irqrestore(&engine->timeline.lock, flags);
-
- GEM_BUG_ON(READ_ONCE(ce->inflight));
- }
-
i915_gem_context_unpin_hw_id(ce->gem_context);
-
- intel_ring_unpin(ce->ring);
-
i915_gem_object_unpin_map(ce->state->obj);
- __context_unpin(ce->state);
+ intel_ring_unpin(ce->ring);
}
static void
goto err;
GEM_BUG_ON(!ce->state);
- ret = __context_pin(ce->state);
+ ret = intel_context_active_acquire(ce,
+ engine->i915->ggtt.pin_bias |
+ PIN_OFFSET_BIAS |
+ PIN_HIGH);
if (ret)
goto err;
I915_MAP_OVERRIDE);
if (IS_ERR(vaddr)) {
ret = PTR_ERR(vaddr);
- goto unpin_vma;
+ goto unpin_active;
}
ret = intel_ring_pin(ce->ring);
intel_ring_unpin(ce->ring);
unpin_map:
i915_gem_object_unpin_map(ce->state->obj);
-unpin_vma:
- __context_unpin(ce->state);
+unpin_active:
+ intel_context_active_release(ce);
err:
return ret;
}
gen6_ppgtt_unpin(i915_vm_to_ppgtt(vm));
}
-static int __context_pin(struct intel_context *ce)
-{
- struct i915_vma *vma;
- int err;
-
- vma = ce->state;
- if (!vma)
- return 0;
-
- err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
- if (err)
- return err;
-
- /*
- * And mark is as a globally pinned object to let the shrinker know
- * it cannot reclaim the object until we release it.
- */
- vma->obj->pin_global++;
- vma->obj->mm.dirty = true;
-
- return 0;
-}
-
-static void __context_unpin(struct intel_context *ce)
-{
- struct i915_vma *vma;
-
- vma = ce->state;
- if (!vma)
- return;
-
- vma->obj->pin_global--;
- i915_vma_unpin(vma);
-}
-
static void ring_context_unpin(struct intel_context *ce)
{
__context_unpin_ppgtt(ce->gem_context);
- __context_unpin(ce);
}
static struct i915_vma *
ce->state = vma;
}
- err = __context_pin(ce);
+ err = intel_context_active_acquire(ce, PIN_HIGH);
if (err)
return err;
err = __context_pin_ppgtt(ce->gem_context);
if (err)
- goto err_unpin;
+ goto err_active;
return 0;
-err_unpin:
- __context_unpin(ce);
+err_active:
+ intel_context_active_release(ce);
return err;
}
static int mock_context_pin(struct intel_context *ce)
{
+ int ret;
+
if (!ce->ring) {
ce->ring = mock_ring(ce->engine);
if (!ce->ring)
return -ENOMEM;
}
+ ret = intel_context_active_acquire(ce, PIN_HIGH);
+ if (ret)
+ return ret;
+
mock_timeline_pin(ce->ring->timeline);
return 0;
}
{
struct mock_engine *mock =
container_of(engine, typeof(*mock), base);
- struct intel_context *ce;
GEM_BUG_ON(timer_pending(&mock->hw_delay));
- ce = fetch_and_zero(&engine->last_retired_context);
- if (ce)
- intel_context_unpin(ce);
-
intel_context_unpin(engine->kernel_context);
intel_engine_fini_breadcrumbs(engine);
ref->retire = retire;
ref->tree = RB_ROOT;
i915_active_request_init(&ref->last, NULL, last_retire);
+ init_llist_head(&ref->barriers);
ref->count = 0;
}
}
#endif
+int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
+ struct intel_engine_cs *engine)
+{
+ struct drm_i915_private *i915 = engine->i915;
+ unsigned long tmp;
+ int err = 0;
+
+ GEM_BUG_ON(!engine->mask);
+ for_each_engine_masked(engine, i915, engine->mask, tmp) {
+ struct intel_context *kctx = engine->kernel_context;
+ struct active_node *node;
+
+ node = kmem_cache_alloc(global.slab_cache, GFP_KERNEL);
+ if (unlikely(!node)) {
+ err = -ENOMEM;
+ break;
+ }
+
+ i915_active_request_init(&node->base,
+ (void *)engine, node_retire);
+ node->timeline = kctx->ring->timeline->fence_context;
+ node->ref = ref;
+ ref->count++;
+
+ llist_add((struct llist_node *)&node->base.link,
+ &ref->barriers);
+ }
+
+ return err;
+}
+
+void i915_active_acquire_barrier(struct i915_active *ref)
+{
+ struct llist_node *pos, *next;
+
+ i915_active_acquire(ref);
+
+ llist_for_each_safe(pos, next, llist_del_all(&ref->barriers)) {
+ struct intel_engine_cs *engine;
+ struct active_node *node;
+ struct rb_node **p, *parent;
+
+ node = container_of((struct list_head *)pos,
+ typeof(*node), base.link);
+
+ engine = (void *)rcu_access_pointer(node->base.request);
+ RCU_INIT_POINTER(node->base.request, ERR_PTR(-EAGAIN));
+
+ parent = NULL;
+ p = &ref->tree.rb_node;
+ while (*p) {
+ parent = *p;
+ if (rb_entry(parent,
+ struct active_node,
+ node)->timeline < node->timeline)
+ p = &parent->rb_right;
+ else
+ p = &parent->rb_left;
+ }
+ rb_link_node(&node->node, parent, p);
+ rb_insert_color(&node->node, &ref->tree);
+
+ llist_add((struct llist_node *)&node->base.link,
+ &engine->barrier_tasks);
+ }
+ i915_active_release(ref);
+}
+
+void i915_request_add_barriers(struct i915_request *rq)
+{
+ struct intel_engine_cs *engine = rq->engine;
+ struct llist_node *node, *next;
+
+ llist_for_each_safe(node, next, llist_del_all(&engine->barrier_tasks))
+ list_add_tail((struct list_head *)node, &rq->active_list);
+}
+
int i915_active_request_set(struct i915_active_request *active,
struct i915_request *rq)
{
static inline void i915_active_fini(struct i915_active *ref) { }
#endif
+int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
+ struct intel_engine_cs *engine);
+void i915_active_acquire_barrier(struct i915_active *ref);
+void i915_request_add_barriers(struct i915_request *rq);
+
#endif /* _I915_ACTIVE_H_ */
#ifndef _I915_ACTIVE_TYPES_H_
#define _I915_ACTIVE_TYPES_H_
+#include <linux/llist.h>
#include <linux/rbtree.h>
#include <linux/rcupdate.h>
unsigned int count;
void (*retire)(struct i915_active *ref);
+
+ struct llist_head barriers;
};
#endif /* _I915_ACTIVE_TYPES_H_ */
intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-
- mutex_lock(&i915->drm.struct_mutex);
- i915_gem_contexts_lost(i915);
- mutex_unlock(&i915->drm.struct_mutex);
}
void i915_gem_init_swizzling(struct drm_i915_private *dev_priv)
spin_unlock(&rq->lock);
local_irq_enable();
-
- /*
- * The backing object for the context is done after switching to the
- * *next* context. Therefore we cannot retire the previous context until
- * the next context has already started running. However, since we
- * cannot take the required locks at i915_request_submit() we
- * defer the unpinning of the active context to now, retirement of
- * the subsequent request.
- */
- if (engine->last_retired_context)
- intel_context_unpin(engine->last_retired_context);
- engine->last_retired_context = rq->hw_context;
}
static void __retire_engine_upto(struct intel_engine_cs *engine,
rq->infix = rq->ring->emit; /* end of header; start of user payload */
- /* Keep a second pin for the dual retirement along engine and ring */
- __intel_context_pin(ce);
-
intel_context_mark_active(ce);
return rq;
mutex_lock(&i915->drm.struct_mutex);
mock_device_flush(i915);
- i915_gem_contexts_lost(i915);
mutex_unlock(&i915->drm.struct_mutex);
flush_work(&i915->gem.idle_work);
projects / linux.git / commitdiff