Few fixes on GGTT and PPGTT around pin, locks, fence and vgpu.

This also includes GVT fixes with two recent fixes:
 one for recent guest hang regression and another for guest reset fix.
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJdeYQjAAoJEPpiX2QO6xPKk2QH/AjkI/PHztUrwdjVlPJsbkxv
 PtNVGwcS6DxjZa7M3QEAZgi1D/oKqGEyQrmpb8WMsVIv/PUBu/s0UtnMfvGoryxD
 XsZns0FHORV3PZuCj1xdIfYI8v9CeowWG5ZJ+uCdjKLwG+7+QEdWk5qHjL1VvDBh
 +dtO1xgvCUjj8stWykKdWyiLX9M7SAdyhQNbIoIEa9c0z6O6W7tAdHMHivYE89DF
 Ehm2L2yp7ZYhXKH2lOccTJZnPXKvlKfXS0WYyuFS268IrZm3BmtF7zwcHUlkQor8
 pXna6bJXWWD+8B8AT9TOtkvG99zc1GbRSsHannksmn7r3hC9Yxd0ijikzwgN5AU=
 =OXmv
 -----END PGP SIGNATURE-----

Merge tag 'drm-intel-next-fixes-2019-09-11' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Few fixes on GGTT and PPGTT around pin, locks, fence and vgpu.

This also includes GVT fixes with two recent fixes:
one for recent guest hang regression and another for guest reset fix.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911233309.GA18449@intel.com

drivers/gpu/drm/i915/gem/i915_gem_mman.c

@@ -265,7 +265,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
 				       PIN_MAPPABLE |
 				       PIN_NONBLOCK /* NOWARN */ |
-				       PIN_NOSEARCH);
+				       PIN_NOEVICT);
 	if (IS_ERR(vma)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =

drivers/gpu/drm/i915/gt/intel_engine_pm.c

@@ -39,27 +39,32 @@ static int __engine_unpark(struct intel_wakeref *wf)
 
 #if IS_ENABLED(CONFIG_LOCKDEP)
 
-static inline void __timeline_mark_lock(struct intel_context *ce)
+static inline unsigned long __timeline_mark_lock(struct intel_context *ce)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
 	mutex_acquire(&ce->timeline->mutex.dep_map, 2, 0, _THIS_IP_);
-	local_irq_restore(flags);
+
+	return flags;
 }
 
-static inline void __timeline_mark_unlock(struct intel_context *ce)
+static inline void __timeline_mark_unlock(struct intel_context *ce,
+					  unsigned long flags)
 {
 	mutex_release(&ce->timeline->mutex.dep_map, 0, _THIS_IP_);
+	local_irq_restore(flags);
 }
 
 #else
 
-static inline void __timeline_mark_lock(struct intel_context *ce)
+static inline unsigned long __timeline_mark_lock(struct intel_context *ce)
 {
+	return 0;
 }
 
-static inline void __timeline_mark_unlock(struct intel_context *ce)
+static inline void __timeline_mark_unlock(struct intel_context *ce,
+					  unsigned long flags)
 {
 }
 
@@ -68,6 +73,8 @@ static inline void __timeline_mark_unlock(struct intel_context *ce)
 static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 {
 	struct i915_request *rq;
+	unsigned long flags;
+	bool result = true;
 
 	/* Already inside the kernel context, safe to power down. */
 	if (engine->wakeref_serial == engine->serial)
@@ -89,12 +96,12 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * retiring the last request, thus all rings should be empty and
 	 * all timelines idle.
 	 */
-	__timeline_mark_lock(engine->kernel_context);
+	flags = __timeline_mark_lock(engine->kernel_context);
 
 	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
 	if (IS_ERR(rq))
 		/* Context switch failed, hope for the best! Maybe reset? */
-		return true;
+		goto out_unlock;
 
 	intel_timeline_enter(rq->timeline);
 
@@ -110,9 +117,10 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	__intel_wakeref_defer_park(&engine->wakeref);
 	__i915_request_queue(rq, NULL);
 
-	__timeline_mark_unlock(engine->kernel_context);
-
-	return false;
+	result = false;
+out_unlock:
+	__timeline_mark_unlock(engine->kernel_context, flags);
+	return result;
 }
 
 static int __engine_park(struct intel_wakeref *wf)

drivers/gpu/drm/i915/gt/intel_reset.c

@@ -792,6 +792,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
 	struct intel_timeline *tl;
+	unsigned long flags;
 
 	if (!test_bit(I915_WEDGED, &gt->reset.flags))
 		return true;
@@ -811,7 +812,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 	 *
 	 * No more can be submitted until we reset the wedged bit.
 	 */
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry(tl, &timelines->active_list, link) {
 		struct i915_request *rq;
 
@@ -819,7 +820,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		if (!rq)
 			continue;
 
-		spin_unlock(&timelines->lock);
+		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		/*
 		 * All internal dependencies (i915_requests) will have
@@ -832,10 +833,10 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt)
 		i915_request_put(rq);
 
 		/* Restart iteration after droping lock */
-		spin_lock(&timelines->lock);
+		spin_lock_irqsave(&timelines->lock, flags);
 		tl = list_entry(&timelines->active_list, typeof(*tl), link);
 	}
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	intel_gt_sanitize(gt, false);
 

drivers/gpu/drm/i915/gt/intel_timeline.c

@@ -337,6 +337,7 @@ int intel_timeline_pin(struct intel_timeline *tl)
 void intel_timeline_enter(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
+	unsigned long flags;
 
 	lockdep_assert_held(&tl->mutex);
 
@@ -345,14 +346,15 @@ void intel_timeline_enter(struct intel_timeline *tl)
 		return;
 	GEM_BUG_ON(!tl->active_count); /* overflow? */
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_add(&tl->link, &timelines->active_list);
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 }
 
 void intel_timeline_exit(struct intel_timeline *tl)
 {
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
+	unsigned long flags;
 
 	lockdep_assert_held(&tl->mutex);
 
@@ -360,9 +362,9 @@ void intel_timeline_exit(struct intel_timeline *tl)
 	if (--tl->active_count)
 		return;
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_del(&tl->link);
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	/*
 	 * Since this timeline is idle, all bariers upon which we were waiting

drivers/gpu/drm/i915/gvt/scheduler.c

@@ -568,6 +568,16 @@ static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	return 0;
 }
 
+static void update_vreg_in_ctx(struct intel_vgpu_workload *workload)
+{
+	struct intel_vgpu *vgpu = workload->vgpu;
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+	u32 ring_base;
+
+	ring_base = dev_priv->engine[workload->ring_id]->mmio_base;
+	vgpu_vreg_t(vgpu, RING_START(ring_base)) = workload->rb_start;
+}
+
 static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
@@ -1016,6 +1026,13 @@ static int workload_thread(void *priv)
 		if (need_force_wake)
 			intel_uncore_forcewake_get(&gvt->dev_priv->uncore,
 					FORCEWAKE_ALL);
+		/*
+		 * Update the vReg of the vGPU which submitted this
+		 * workload. The vGPU may use these registers for checking
+		 * the context state. The value comes from GPU commands
+		 * in this workload.
+		 */
+		update_vreg_in_ctx(workload);
 
 		ret = dispatch_workload(workload);
 
@@ -1438,9 +1455,6 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 #define same_context(a, b) (((a)->context_id == (b)->context_id) && \
 		((a)->lrca == (b)->lrca))
 
-#define get_last_workload(q) \
-	(list_empty(q) ? NULL : container_of(q->prev, \
-	struct intel_vgpu_workload, list))
 /**
  * intel_vgpu_create_workload - create a vGPU workload
  * @vgpu: a vGPU
@@ -1460,7 +1474,7 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct list_head *q = workload_q_head(vgpu, ring_id);
-	struct intel_vgpu_workload *last_workload = get_last_workload(q);
+	struct intel_vgpu_workload *last_workload = NULL;
 	struct intel_vgpu_workload *workload = NULL;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	u64 ring_context_gpa;
@@ -1486,15 +1500,20 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 	head &= RB_HEAD_OFF_MASK;
 	tail &= RB_TAIL_OFF_MASK;
 
-	if (last_workload && same_context(&last_workload->ctx_desc, desc)) {
-		gvt_dbg_el("ring id %d cur workload == last\n", ring_id);
-		gvt_dbg_el("ctx head %x real head %lx\n", head,
-				last_workload->rb_tail);
-		/*
-		 * cannot use guest context head pointer here,
-		 * as it might not be updated at this time
-		 */
-		head = last_workload->rb_tail;
+	list_for_each_entry_reverse(last_workload, q, list) {
+
+		if (same_context(&last_workload->ctx_desc, desc)) {
+			gvt_dbg_el("ring id %d cur workload == last\n",
+					ring_id);
+			gvt_dbg_el("ctx head %x real head %lx\n", head,
+					last_workload->rb_tail);
+			/*
+			 * cannot use guest context head pointer here,
+			 * as it might not be updated at this time
+			 */
+			head = last_workload->rb_tail;
+			break;
+		}
 	}
 
 	gvt_dbg_el("ring id %d begin a new workload\n", ring_id);

drivers/gpu/drm/i915/i915_drv.h

@@ -961,6 +961,7 @@ struct i915_frontbuffer_tracking {
 };
 
 struct i915_virtual_gpu {
+	struct mutex lock; /* serialises sending of g2v_notify command pkts */
 	bool active;
 	u32 caps;
 };

drivers/gpu/drm/i915/i915_gem.c

@@ -889,12 +889,13 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 
 static long
 wait_for_timelines(struct drm_i915_private *i915,
-		   unsigned int flags, long timeout)
+		   unsigned int wait, long timeout)
 {
 	struct intel_gt_timelines *timelines = &i915->gt.timelines;
 	struct intel_timeline *tl;
+	unsigned long flags;
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry(tl, &timelines->active_list, link) {
 		struct i915_request *rq;
 
@@ -902,7 +903,7 @@ wait_for_timelines(struct drm_i915_private *i915,
 		if (!rq)
 			continue;
 
-		spin_unlock(&timelines->lock);
+		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		/*
 		 * "Race-to-idle".
@@ -913,19 +914,19 @@ wait_for_timelines(struct drm_i915_private *i915,
 		 * want to complete as quickly as possible to avoid prolonged
 		 * stalls, so allow the gpu to boost to maximum clocks.
 		 */
-		if (flags & I915_WAIT_FOR_IDLE_BOOST)
+		if (wait & I915_WAIT_FOR_IDLE_BOOST)
 			gen6_rps_boost(rq);
 
-		timeout = i915_request_wait(rq, flags, timeout);
+		timeout = i915_request_wait(rq, wait, timeout);
 		i915_request_put(rq);
 		if (timeout < 0)
 			return timeout;
 
 		/* restart after reacquiring the lock */
-		spin_lock(&timelines->lock);
+		spin_lock_irqsave(&timelines->lock, flags);
 		tl = list_entry(&timelines->active_list, typeof(*tl), link);
 	}
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	return timeout;
 }
@@ -1026,6 +1027,14 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			return ERR_PTR(ret);
 	}
 
+	if (vma->fence && !i915_gem_object_is_tiled(obj)) {
+		mutex_lock(&vma->vm->mutex);
+		ret = i915_vma_revoke_fence(vma);
+		mutex_unlock(&vma->vm->mutex);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
 	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
 	if (ret)
 		return ERR_PTR(ret);

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -827,10 +827,9 @@ static void mark_tlbs_dirty(struct i915_ppgtt *ppgtt)
 	ppgtt->pd_dirty_engines = ALL_ENGINES;
 }
 
-static int gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
+static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 {
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct drm_i915_private *dev_priv = vm->i915;
+	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
 	enum vgt_g2v_type msg;
 	int i;
 
@@ -839,7 +838,9 @@ static int gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 	else
 		atomic_dec(px_used(ppgtt->pd));
 
-	if (i915_vm_is_4lvl(vm)) {
+	mutex_lock(&dev_priv->vgpu.lock);
+
+	if (i915_vm_is_4lvl(&ppgtt->vm)) {
 		const u64 daddr = px_dma(ppgtt->pd);
 
 		I915_WRITE(vgtif_reg(pdp[0].lo), lower_32_bits(daddr));
@@ -859,9 +860,10 @@ static int gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 				VGT_G2V_PPGTT_L3_PAGE_TABLE_DESTROY);
 	}
 
+	/* g2v_notify atomically (via hv trap) consumes the message packet. */
 	I915_WRITE(vgtif_reg(g2v_notify), msg);
 
-	return 0;
+	mutex_unlock(&dev_priv->vgpu.lock);
 }
 
 /* Index shifts into the pagetable are offset by GEN8_PTE_SHIFT [12] */

drivers/gpu/drm/i915/i915_request.c

@@ -1465,9 +1465,10 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 {
 	struct intel_gt_timelines *timelines = &i915->gt.timelines;
 	struct intel_timeline *tl, *tn;
+	unsigned long flags;
 	LIST_HEAD(free);
 
-	spin_lock(&timelines->lock);
+	spin_lock_irqsave(&timelines->lock, flags);
 	list_for_each_entry_safe(tl, tn, &timelines->active_list, link) {
 		if (!mutex_trylock(&tl->mutex))
 			continue;
@@ -1475,11 +1476,11 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 		intel_timeline_get(tl);
 		GEM_BUG_ON(!tl->active_count);
 		tl->active_count++; /* pin the list element */
-		spin_unlock(&timelines->lock);
+		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		retire_requests(tl);
 
-		spin_lock(&timelines->lock);
+		spin_lock_irqsave(&timelines->lock, flags);
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
@@ -1494,7 +1495,7 @@ bool i915_retire_requests(struct drm_i915_private *i915)
 			list_add(&tl->link, &free);
 		}
 	}
-	spin_unlock(&timelines->lock);
+	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	list_for_each_entry_safe(tl, tn, &free, link)
 		__intel_timeline_free(&tl->kref);

drivers/gpu/drm/i915/i915_vgpu.c

@@ -94,6 +94,7 @@ void i915_detect_vgpu(struct drm_i915_private *dev_priv)
 	dev_priv->vgpu.caps = readl(shared_area + vgtif_offset(vgt_caps));
 
 	dev_priv->vgpu.active = true;
+	mutex_init(&dev_priv->vgpu.lock);
 	DRM_INFO("Virtual GPU for Intel GVT-g detected.\n");
 
 out: