Merge branch 'dynamic_sg' into rdma.git for-next

From Maor Gottlieb says:

====================
This series extends __sg_alloc_table_from_pages to allow chaining of new
pages to an already initialized SG table.

This allows for drivers to utilize the optimization of merging contiguous
pages without a need to pre allocate all the pages and hold them in a very
large temporary buffer prior to the call to SG table initialization.

The last patch changes the Infiniband core to use the new API. It removes
duplicate functionality from the code and benefits from the optimization
of allocating dynamic SG table from pages.

In huge pages system of 2MB page size, without this change, the SG table
would contain x512 SG entries.
====================

* branch 'dynamic_sg':
  RDMA/umem: Move to allocate SG table from pages
  lib/scatterlist: Add support in dynamic allocation of SG table from pages
  tools/testing/scatterlist: Show errors in human readable form
  tools/testing/scatterlist: Rejuvenate bit-rotten test

7 files changed, 87 insertions, 41 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index d0bdb6d447ed..ef755dd5e68f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine)
 	return __reset_engine(engine);
 }
 
-static struct intel_engine_cs *__active_engine(struct i915_request *rq)
+static bool
+__active_engine(struct i915_request *rq, struct intel_engine_cs **active)
 {
 	struct intel_engine_cs *engine, *locked;
+	bool ret = false;
 
 	/*
 	 * Serialise with __i915_request_submit() so that it sees
 	 * is-banned?, or we know the request is already inflight.
+	 *
+	 * Note that rq->engine is unstable, and so we double
+	 * check that we have acquired the lock on the final engine.
 	 */
 	locked = READ_ONCE(rq->engine);
 	spin_lock_irq(&locked->active.lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
 		spin_unlock(&locked->active.lock);
-		spin_lock(&engine->active.lock);
 		locked = engine;
+		spin_lock(&locked->active.lock);
 	}
 
-	engine = NULL;
-	if (i915_request_is_active(rq) && rq->fence.error != -EIO)
-		engine = rq->engine;
+	if (!i915_request_completed(rq)) {
+		if (i915_request_is_active(rq) && rq->fence.error != -EIO)
+			*active = locked;
+		ret = true;
+	}
 
 	spin_unlock_irq(&locked->active.lock);
 
-	return engine;
+	return ret;
 }
 
 static struct intel_engine_cs *active_engine(struct intel_context *ce)
@@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	if (!ce->timeline)
 		return NULL;
 
-	mutex_lock(&ce->timeline->mutex);
-	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
-		if (i915_request_completed(rq))
-			break;
+	rcu_read_lock();
+	list_for_each_entry_rcu(rq, &ce->timeline->requests, link) {
+		if (i915_request_is_active(rq) && i915_request_completed(rq))
+			continue;
 
 		/* Check with the backend if the request is inflight */
-		engine = __active_engine(rq);
-		if (engine)
+		if (__active_engine(rq, &engine))
 			break;
 	}
-	mutex_unlock(&ce->timeline->mutex);
+	rcu_read_unlock();
 
 	return engine;
 }
@@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915)
 	ctx->i915 = i915;
 	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
 	mutex_init(&ctx->mutex);
+	INIT_LIST_HEAD(&ctx->link);
 
 	spin_lock_init(&ctx->stale.lock);
 	INIT_LIST_HEAD(&ctx->stale.engines);
@@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915)
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
-	spin_lock(&i915->gem.contexts.lock);
-	list_add_tail(&ctx->link, &i915->gem.contexts.list);
-	spin_unlock(&i915->gem.contexts.lock);
-
 	return ctx;
 
 err_free:
@@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx,
 				struct drm_i915_file_private *fpriv,
 				u32 *id)
 {
+	struct drm_i915_private *i915 = ctx->i915;
 	struct i915_address_space *vm;
 	int ret;
 
@@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx,
 	/* And finally expose ourselves to userspace via the idr */
 	ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL);
 	if (ret)
-		put_pid(fetch_and_zero(&ctx->pid));
+		goto err_pid;
+
+	spin_lock(&i915->gem.contexts.lock);
+	list_add_tail(&ctx->link, &i915->gem.contexts.list);
+	spin_unlock(&i915->gem.contexts.lock);
+
+	return 0;
 
+err_pid:
+	put_pid(fetch_and_zero(&ctx->pid));
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 12b30075134a..f2eaed6aca3d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 	unsigned int max_segment = i915_sg_segment_size();
 	struct sg_table *st;
 	unsigned int sg_page_sizes;
+	struct scatterlist *sg;
 	int ret;
 
 	st = kmalloc(sizeof(*st), GFP_KERNEL);
@@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj,
 		return ERR_PTR(-ENOMEM);
 
 alloc_table:
-	ret = __sg_alloc_table_from_pages(st, pvec, num_pages,
-					  0, num_pages << PAGE_SHIFT,
-					  max_segment,
-					  GFP_KERNEL);
-	if (ret) {
+	sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0,
+					 num_pages << PAGE_SHIFT, max_segment,
+					 NULL, 0, GFP_KERNEL);
+	if (IS_ERR(sg)) {
 		kfree(st);
-		return ERR_PTR(ret);
+		return ERR_CAST(sg);
 	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 24322ef08aa4..9eeaca957a7e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2060,6 +2060,14 @@ static inline void clear_ports(struct i915_request **ports, int count)
 	memset_p((void **)ports, NULL, count);
 }
 
+static inline void
+copy_ports(struct i915_request **dst, struct i915_request **src, int count)
+{
+	/* A memcpy_p() would be very useful here! */
+	while (count--)
+		WRITE_ONCE(*dst++, *src++); /* avoid write tearing */
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -2648,10 +2656,9 @@ static void process_csb(struct intel_engine_cs *engine)
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-			memcpy(execlists->inflight,
-			       execlists->pending,
-			       execlists_num_ports(execlists) *
-			       sizeof(*execlists->pending));
+			copy_ports(execlists->inflight,
+				   execlists->pending,
+				   execlists_num_ports(execlists));
 			smp_wmb(); /* complete the seqlock */
 			WRITE_ONCE(execlists->active, execlists->inflight);
 
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 8fa9b31a2484..f6d7e33c7099 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -368,6 +368,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu)
 static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 		struct intel_vgpu_creation_params *param)
 {
+	struct drm_i915_private *dev_priv = gvt->gt->i915;
 	struct intel_vgpu *vgpu;
 	int ret;
 
@@ -436,7 +437,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_clean_sched_policy;
 
-	ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
+	if (IS_BROADWELL(dev_priv))
+		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
+	else
+		ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
 	if (ret)
 		goto out_clean_sched_policy;
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 0b2fe55e6194..781a6783affe 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -388,17 +388,38 @@ static bool __request_in_flight(const struct i915_request *signal)
 	 * As we know that there are always preemption points between
 	 * requests, we know that only the currently executing request
 	 * may be still active even though we have cleared the flag.
-	 * However, we can't rely on our tracking of ELSP[0] to known
+	 * However, we can't rely on our tracking of ELSP[0] to know
 	 * which request is currently active and so maybe stuck, as
 	 * the tracking maybe an event behind. Instead assume that
 	 * if the context is still inflight, then it is still active
 	 * even if the active flag has been cleared.
+	 *
+	 * To further complicate matters, if there a pending promotion, the HW
+	 * may either perform a context switch to the second inflight execlists,
+	 * or it may switch to the pending set of execlists. In the case of the
+	 * latter, it may send the ACK and we process the event copying the
+	 * pending[] over top of inflight[], _overwriting_ our *active. Since
+	 * this implies the HW is arbitrating and not struck in *active, we do
+	 * not worry about complete accuracy, but we do require no read/write
+	 * tearing of the pointer [the read of the pointer must be valid, even
+	 * as the array is being overwritten, for which we require the writes
+	 * to avoid tearing.]
+	 *
+	 * Note that the read of *execlists->active may race with the promotion
+	 * of execlists->pending[] to execlists->inflight[], overwritting
+	 * the value at *execlists->active. This is fine. The promotion implies
+	 * that we received an ACK from the HW, and so the context is not
+	 * stuck -- if we do not see ourselves in *active, the inflight status
+	 * is valid. If instead we see ourselves being copied into *active,
+	 * we are inflight and may signal the callback.
 	 */
 	if (!intel_context_inflight(signal->context))
 		return false;
 
 	rcu_read_lock();
-	for (port = __engine_active(signal->engine); (rq = *port); port++) {
+	for (port = __engine_active(signal->engine);
+	     (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */
+	     port++) {
 		if (rq->context == signal->context) {
 			inflight = i915_seqno_passed(rq->fence.seqno,
 						     signal->fence.seqno);
diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
index 295b9829e2da..4cd2038cbe35 100644
--- a/drivers/gpu/drm/i915/i915_sw_fence.c
+++ b/drivers/gpu/drm/i915/i915_sw_fence.c
@@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence,
 
 		do {
 			list_for_each_entry_safe(pos, next, &x->head, entry) {
-				pos->func(pos,
-					  TASK_NORMAL, fence->error,
-					  &extra);
+				int wake_flags;
+
+				wake_flags = fence->error;
+				if (pos->func == autoremove_wake_function)
+					wake_flags = 0;
+
+				pos->func(pos, TASK_NORMAL, wake_flags, &extra);
 			}
 
 			if (list_empty(&extra))
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index f127e633f7ca..397c313a8b69 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -118,11 +118,11 @@ static struct dev_pm_domain pm_domain = {
 
 struct drm_i915_private *mock_gem_device(void)
 {
-	struct drm_i915_private *i915;
-	struct pci_dev *pdev;
 #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
-	struct dev_iommu iommu;
+	static struct dev_iommu fake_iommu = { .priv = (void *)-1 };
 #endif
+	struct drm_i915_private *i915;
+	struct pci_dev *pdev;
 	int err;
 
 	pdev = kzalloc(sizeof(*pdev), GFP_KERNEL);
@@ -141,10 +141,8 @@ struct drm_i915_private *mock_gem_device(void)
 	dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 
 #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
-	/* HACK HACK HACK to disable iommu for the fake device; force identity mapping */
-	memset(&iommu, 0, sizeof(iommu));
-	iommu.priv = (void *)-1;
-	pdev->dev.iommu = &iommu;
+	/* HACK to disable iommu for the fake device; force identity mapping */
+	pdev->dev.iommu = &fake_iommu;
 #endif
 
 	pci_set_drvdata(pdev, i915);