summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDave Airlie <airlied@redhat.com>2020-03-13 09:41:15 +1000
committerDave Airlie <airlied@redhat.com>2020-03-13 09:41:30 +1000
commitf31d83f047e190bc636505e9b9c31a34e25bfebe (patch)
tree76a588d2427e25dc0f8afd1790eac4c92a6a1605
parentd94432653519031f89d2a30cc917e29a02f0200d (diff)
parent14a0d527a479eb2cb6067f9e5e163e1bf35db2a9 (diff)
Merge tag 'drm-intel-fixes-2020-03-12' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes
drm/i915 fixes for v5.6-rc6: - hard lockup fix - GVT fixes - 32-bit alignment issue fix - timeline wait fixes - cacheline_retire and free Signed-off-by: Dave Airlie <airlied@redhat.com> From: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/87lfo6ksvw.fsf@intel.com
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c3
-rw-r--r--drivers/gpu/drm/i915/gt/intel_lrc.c29
-rw-r--r--drivers/gpu/drm/i915/gt/intel_timeline.c8
-rw-r--r--drivers/gpu/drm/i915/gvt/display.c3
-rw-r--r--drivers/gpu/drm/i915/gvt/opregion.c5
-rw-r--r--drivers/gpu/drm/i915/gvt/vgpu.c12
-rw-r--r--drivers/gpu/drm/i915/i915_request.c28
-rw-r--r--drivers/gpu/drm/i915/i915_request.h2
-rw-r--r--drivers/gpu/drm/i915/i915_utils.h5
9 files changed, 66 insertions, 29 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 60c984e10c4a..7643a30ba4cd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -423,7 +423,8 @@ eb_validate_vma(struct i915_execbuffer *eb,
if (unlikely(entry->flags & eb->invalid_flags))
return -EINVAL;
- if (unlikely(entry->alignment && !is_power_of_2(entry->alignment)))
+ if (unlikely(entry->alignment &&
+ !is_power_of_2_u64(entry->alignment)))
return -EINVAL;
/*
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index fe8a59aaa629..940e7f7df69a 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1679,11 +1679,9 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
if (!intel_engine_has_timeslices(engine))
return false;
- if (list_is_last(&rq->sched.link, &engine->active.requests))
- return false;
-
- hint = max(rq_prio(list_next_entry(rq, sched.link)),
- engine->execlists.queue_priority_hint);
+ hint = engine->execlists.queue_priority_hint;
+ if (!list_is_last(&rq->sched.link, &engine->active.requests))
+ hint = max(hint, rq_prio(list_next_entry(rq, sched.link)));
return hint >= effective_prio(rq);
}
@@ -1725,6 +1723,18 @@ static void set_timeslice(struct intel_engine_cs *engine)
set_timer_ms(&engine->execlists.timer, active_timeslice(engine));
}
+static void start_timeslice(struct intel_engine_cs *engine)
+{
+ struct intel_engine_execlists *execlists = &engine->execlists;
+
+ execlists->switch_priority_hint = execlists->queue_priority_hint;
+
+ if (timer_pending(&execlists->timer))
+ return;
+
+ set_timer_ms(&execlists->timer, timeslice(engine));
+}
+
static void record_preemption(struct intel_engine_execlists *execlists)
{
(void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++);
@@ -1888,11 +1898,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
* Even if ELSP[1] is occupied and not worthy
* of timeslices, our queue might be.
*/
- if (!execlists->timer.expires &&
- need_timeslice(engine, last))
- set_timer_ms(&execlists->timer,
- timeslice(engine));
-
+ start_timeslice(engine);
return;
}
}
@@ -1927,7 +1933,8 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
if (last && !can_merge_rq(last, rq)) {
spin_unlock(&ve->base.active.lock);
- return; /* leave this for another */
+ start_timeslice(engine);
+ return; /* leave this for another sibling */
}
ENGINE_TRACE(engine,
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 87716529cd2f..d8d9f1179c2b 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -192,11 +192,15 @@ static void cacheline_release(struct intel_timeline_cacheline *cl)
static void cacheline_free(struct intel_timeline_cacheline *cl)
{
+ if (!i915_active_acquire_if_busy(&cl->active)) {
+ __idle_cacheline_free(cl);
+ return;
+ }
+
GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE));
cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE);
- if (i915_active_is_idle(&cl->active))
- __idle_cacheline_free(cl);
+ i915_active_release(&cl->active);
}
int intel_timeline_init(struct intel_timeline *timeline,
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index e1c313da6c00..a62bdf9be682 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -457,7 +457,8 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
/* TODO: add more platforms support */
- if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+ if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+ IS_COFFEELAKE(dev_priv)) {
if (connected) {
vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
SFUSE_STRAP_DDID_DETECTED;
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 867e7629025b..33569b910ed5 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -147,15 +147,14 @@ static void virt_vbt_generation(struct vbt *v)
/* there's features depending on version! */
v->header.version = 155;
v->header.header_size = sizeof(v->header);
- v->header.vbt_size = sizeof(struct vbt) - sizeof(v->header);
+ v->header.vbt_size = sizeof(struct vbt);
v->header.bdb_offset = offsetof(struct vbt, bdb_header);
strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK");
v->bdb_header.version = 186; /* child_dev_size = 33 */
v->bdb_header.header_size = sizeof(v->bdb_header);
- v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header)
- - sizeof(struct bdb_header);
+ v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header);
/* general features */
v->general_features_header.id = BDB_GENERAL_FEATURES;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 487af6ea9972..345c2aa3b491 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -272,10 +272,17 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
{
struct intel_gvt *gvt = vgpu->gvt;
- mutex_lock(&vgpu->vgpu_lock);
-
WARN(vgpu->active, "vGPU is still active!\n");
+ /*
+ * remove idr first so later clean can judge if need to stop
+ * service if no active vgpu.
+ */
+ mutex_lock(&gvt->lock);
+ idr_remove(&gvt->vgpu_idr, vgpu->id);
+ mutex_unlock(&gvt->lock);
+
+ mutex_lock(&vgpu->vgpu_lock);
intel_gvt_debugfs_remove_vgpu(vgpu);
intel_vgpu_clean_sched_policy(vgpu);
intel_vgpu_clean_submission(vgpu);
@@ -290,7 +297,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
mutex_unlock(&vgpu->vgpu_lock);
mutex_lock(&gvt->lock);
- idr_remove(&gvt->vgpu_idr, vgpu->id);
if (idr_is_empty(&gvt->vgpu_idr))
intel_gvt_clean_irq(gvt);
intel_gvt_update_vgpu_types(gvt);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index dcaa85a91090..a18b2a244706 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -527,19 +527,31 @@ submit_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
return NOTIFY_DONE;
}
+static void irq_semaphore_cb(struct irq_work *wrk)
+{
+ struct i915_request *rq =
+ container_of(wrk, typeof(*rq), semaphore_work);
+
+ i915_schedule_bump_priority(rq, I915_PRIORITY_NOSEMAPHORE);
+ i915_request_put(rq);
+}
+
static int __i915_sw_fence_call
semaphore_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
{
- struct i915_request *request =
- container_of(fence, typeof(*request), semaphore);
+ struct i915_request *rq = container_of(fence, typeof(*rq), semaphore);
switch (state) {
case FENCE_COMPLETE:
- i915_schedule_bump_priority(request, I915_PRIORITY_NOSEMAPHORE);
+ if (!(READ_ONCE(rq->sched.attr.priority) & I915_PRIORITY_NOSEMAPHORE)) {
+ i915_request_get(rq);
+ init_irq_work(&rq->semaphore_work, irq_semaphore_cb);
+ irq_work_queue(&rq->semaphore_work);
+ }
break;
case FENCE_FREE:
- i915_request_put(request);
+ i915_request_put(rq);
break;
}
@@ -776,8 +788,8 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
struct dma_fence *fence;
int err;
- GEM_BUG_ON(i915_request_timeline(rq) ==
- rcu_access_pointer(signal->timeline));
+ if (i915_request_timeline(rq) == rcu_access_pointer(signal->timeline))
+ return 0;
if (i915_request_started(signal))
return 0;
@@ -821,7 +833,7 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
return 0;
err = 0;
- if (intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
+ if (!intel_timeline_sync_is_later(i915_request_timeline(rq), fence))
err = i915_sw_fence_await_dma_fence(&rq->submit,
fence, 0,
I915_FENCE_GFP);
@@ -1318,9 +1330,9 @@ void __i915_request_queue(struct i915_request *rq,
* decide whether to preempt the entire chain so that it is ready to
* run at the earliest possible convenience.
*/
- i915_sw_fence_commit(&rq->semaphore);
if (attr && rq->engine->schedule)
rq->engine->schedule(rq, attr);
+ i915_sw_fence_commit(&rq->semaphore);
i915_sw_fence_commit(&rq->submit);
}
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index f57eadcf3583..fccc339949ec 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -26,6 +26,7 @@
#define I915_REQUEST_H
#include <linux/dma-fence.h>
+#include <linux/irq_work.h>
#include <linux/lockdep.h>
#include "gem/i915_gem_context_types.h"
@@ -208,6 +209,7 @@ struct i915_request {
};
struct list_head execute_cb;
struct i915_sw_fence semaphore;
+ struct irq_work semaphore_work;
/*
* A list of everyone we wait upon, and everyone who waits upon us.
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index b0ade76bec90..d34141f7dcd8 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -234,6 +234,11 @@ static inline u64 ptr_to_u64(const void *ptr)
__idx; \
})
+static inline bool is_power_of_2_u64(u64 n)
+{
+ return (n != 0 && ((n & (n - 1)) == 0));
+}
+
static inline void __list_del_many(struct list_head *head,
struct list_head *first)
{