Merge drm/drm-next into drm-misc-next

Backmerging 5.2-rc1 to -misc-next for robher

Signed-off-by: Sean Paul <seanpaul@chromium.org>

23 files changed, 191 insertions, 99 deletions

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 148be8e1a090..3d5f1cb6a76c 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -15,7 +15,6 @@ config DRM_I915
 	select IRQ_WORK
 	# i915 depends on ACPI_VIDEO when ACPI is enabled
 	# but for select to work, need to select ACPI_VIDEO's dependencies, ick
-	select BACKLIGHT_LCD_SUPPORT if ACPI
 	select BACKLIGHT_CLASS_DEVICE if ACPI
 	select INPUT if ACPI
 	select ACPI_VIDEO if ACPI
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index 2ec89bcb59f1..8a9606f91e68 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -196,9 +196,9 @@ DEFINE_SIMPLE_ATTRIBUTE(vgpu_scan_nonprivbb_fops,
 int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu)
 {
 	struct dentry *ent;
-	char name[10] = "";
+	char name[16] = "";
 
-	sprintf(name, "vgpu%d", vgpu->id);
+	snprintf(name, 16, "vgpu%d", vgpu->id);
 	vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root);
 	if (!vgpu->debugfs)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 4e1e425189ba..41c8ebc60c63 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -45,6 +45,7 @@ static int vgpu_gem_get_pages(
 	int i, ret;
 	gen8_pte_t __iomem *gtt_entries;
 	struct intel_vgpu_fb_info *fb_info;
+	u32 page_num;
 
 	fb_info = (struct intel_vgpu_fb_info *)obj->gvt_info;
 	if (WARN_ON(!fb_info))
@@ -54,14 +55,15 @@ static int vgpu_gem_get_pages(
 	if (unlikely(!st))
 		return -ENOMEM;
 
-	ret = sg_alloc_table(st, fb_info->size, GFP_KERNEL);
+	page_num = obj->base.size >> PAGE_SHIFT;
+	ret = sg_alloc_table(st, page_num, GFP_KERNEL);
 	if (ret) {
 		kfree(st);
 		return ret;
 	}
 	gtt_entries = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm +
 		(fb_info->start >> PAGE_SHIFT);
-	for_each_sg(st->sgl, sg, fb_info->size, i) {
+	for_each_sg(st->sgl, sg, page_num, i) {
 		sg->offset = 0;
 		sg->length = PAGE_SIZE;
 		sg_dma_address(sg) =
@@ -158,7 +160,7 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 		return NULL;
 
 	drm_gem_private_object_init(dev, &obj->base,
-		info->size << PAGE_SHIFT);
+		roundup(info->size, PAGE_SIZE));
 	i915_gem_object_init(obj, &intel_vgpu_gem_ops);
 
 	obj->read_domains = I915_GEM_DOMAIN_GTT;
@@ -206,11 +208,12 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		struct intel_vgpu_fb_info *info,
 		int plane_id)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_vgpu_primary_plane_format p;
 	struct intel_vgpu_cursor_plane_format c;
 	int ret, tile_height = 1;
 
+	memset(info, 0, sizeof(*info));
+
 	if (plane_id == DRM_PLANE_TYPE_PRIMARY) {
 		ret = intel_vgpu_decode_primary_plane(vgpu, &p);
 		if (ret)
@@ -267,8 +270,7 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		return -EINVAL;
 	}
 
-	info->size = (info->stride * roundup(info->height, tile_height)
-		      + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	info->size = info->stride * roundup(info->height, tile_height);
 	if (info->size == 0) {
 		gvt_vgpu_err("fb size is zero\n");
 		return -EINVAL;
@@ -278,11 +280,6 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		gvt_vgpu_err("Not aligned fb address:0x%llx\n", info->start);
 		return -EFAULT;
 	}
-	if (((info->start >> PAGE_SHIFT) + info->size) >
-		ggtt_total_entries(&dev_priv->ggtt)) {
-		gvt_vgpu_err("Invalid GTT offset or size\n");
-		return -EFAULT;
-	}
 
 	if (!intel_gvt_ggtt_validate_range(vgpu, info->start, info->size)) {
 		gvt_vgpu_err("invalid gma addr\n");
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index c2f7d20f6346..08c74e65836b 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -811,7 +811,7 @@ static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
 
 /* Allocate shadow page table without guest page. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
-		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type)
+		struct intel_vgpu *vgpu, enum intel_gvt_gtt_type type)
 {
 	struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
@@ -861,7 +861,7 @@ err_free_spt:
 
 /* Allocate shadow page table associated with specific gfn. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
-		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type,
+		struct intel_vgpu *vgpu, enum intel_gvt_gtt_type type,
 		unsigned long gfn, bool guest_pde_ips)
 {
 	struct intel_vgpu_ppgtt_spt *spt;
@@ -936,7 +936,7 @@ static int ppgtt_invalidate_spt_by_shadow_entry(struct intel_vgpu *vgpu,
 {
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *s;
-	intel_gvt_gtt_type_t cur_pt_type;
+	enum intel_gvt_gtt_type cur_pt_type;
 
 	GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(e->type)));
 
@@ -1076,6 +1076,9 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 	} else {
 		int type = get_next_pt_type(we->type);
 
+		if (!gtt_type_is_pt(type))
+			goto err;
+
 		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
@@ -1855,7 +1858,7 @@ static void vgpu_free_mm(struct intel_vgpu_mm *mm)
  * Zero on success, negative error code in pointer if failed.
  */
 struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[])
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[])
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct intel_vgpu_mm *mm;
@@ -2309,7 +2312,7 @@ int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu,
 }
 
 static int alloc_scratch_pages(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t type)
+		enum intel_gvt_gtt_type type)
 {
 	struct intel_vgpu_gtt *gtt = &vgpu->gtt;
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
@@ -2594,7 +2597,7 @@ struct intel_vgpu_mm *intel_vgpu_find_ppgtt_mm(struct intel_vgpu *vgpu,
  * Zero on success, negative error code if failed.
  */
 struct intel_vgpu_mm *intel_vgpu_get_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[])
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[])
 {
 	struct intel_vgpu_mm *mm;
 
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 32c573aea494..42d0394f0de2 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -95,8 +95,8 @@ struct intel_gvt_gtt {
 	unsigned long scratch_mfn;
 };
 
-typedef enum {
-	GTT_TYPE_INVALID = -1,
+enum intel_gvt_gtt_type {
+	GTT_TYPE_INVALID = 0,
 
 	GTT_TYPE_GGTT_PTE,
 
@@ -124,7 +124,7 @@ typedef enum {
 	GTT_TYPE_PPGTT_PML4_PT,
 
 	GTT_TYPE_MAX,
-} intel_gvt_gtt_type_t;
+};
 
 enum intel_gvt_mm_type {
 	INTEL_GVT_MM_GGTT,
@@ -148,7 +148,7 @@ struct intel_vgpu_mm {
 
 	union {
 		struct {
-			intel_gvt_gtt_type_t root_entry_type;
+			enum intel_gvt_gtt_type root_entry_type;
 			/*
 			 * The 4 PDPs in ring context. For 48bit addressing,
 			 * only PDP0 is valid and point to PML4. For 32it
@@ -169,7 +169,7 @@ struct intel_vgpu_mm {
 };
 
 struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[]);
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[]);
 
 static inline void intel_vgpu_mm_get(struct intel_vgpu_mm *mm)
 {
@@ -233,7 +233,7 @@ struct intel_vgpu_ppgtt_spt {
 	struct intel_vgpu *vgpu;
 
 	struct {
-		intel_gvt_gtt_type_t type;
+		enum intel_gvt_gtt_type type;
 		bool pde_ips; /* for 64KB PTEs */
 		void *vaddr;
 		struct page *page;
@@ -241,7 +241,7 @@ struct intel_vgpu_ppgtt_spt {
 	} shadow_page;
 
 	struct {
-		intel_gvt_gtt_type_t type;
+		enum intel_gvt_gtt_type type;
 		bool pde_ips; /* for 64KB PTEs */
 		unsigned long gfn;
 		unsigned long write_cnt;
@@ -267,7 +267,7 @@ struct intel_vgpu_mm *intel_vgpu_find_ppgtt_mm(struct intel_vgpu *vgpu,
 		u64 pdps[]);
 
 struct intel_vgpu_mm *intel_vgpu_get_ppgtt_mm(struct intel_vgpu *vgpu,
-		intel_gvt_gtt_type_t root_entry_type, u64 pdps[]);
+		enum intel_gvt_gtt_type root_entry_type, u64 pdps[]);
 
 int intel_vgpu_put_ppgtt_mm(struct intel_vgpu *vgpu, u64 pdps[]);
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 18f01eeb2510..90673fca792f 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1206,7 +1206,7 @@ static int pvinfo_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 
 static int handle_g2v_notification(struct intel_vgpu *vgpu, int notification)
 {
-	intel_gvt_gtt_type_t root_entry_type = GTT_TYPE_PPGTT_ROOT_L4_ENTRY;
+	enum intel_gvt_gtt_type root_entry_type = GTT_TYPE_PPGTT_ROOT_L4_ENTRY;
 	struct intel_vgpu_mm *mm;
 	u64 *pdps;
 
@@ -3303,7 +3303,7 @@ void intel_gvt_clean_mmio_info(struct intel_gvt *gvt)
 /* Special MMIO blocks. */
 static struct gvt_mmio_block mmio_blocks[] = {
 	{D_SKL_PLUS, _MMIO(CSR_MMIO_START_RANGE), 0x3000, NULL, NULL},
-	{D_ALL, MCHBAR_MIRROR_REG_BASE, 0x4000, NULL, NULL},
+	{D_ALL, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL},
 	{D_ALL, _MMIO(VGT_PVINFO_PAGE), VGT_PVINFO_SIZE,
 		pvinfo_mmio_read, pvinfo_mmio_write},
 	{D_ALL, LGC_PALETTE(PIPE_A, 0), 1024, NULL, NULL},
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index e7e14c842be4..edf6d646eb25 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -132,6 +132,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 
 	{RCS0, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */
 	{RCS0, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */
+	{RCS0, _MMIO(0x20D8), 0xffff, true}, /* 0x20d8 */
 
 	{RCS0, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
 	{RCS0, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 3de5b643b266..33aaa14bfdde 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -126,7 +126,4 @@
 #define RING_GFX_MODE(base)	_MMIO((base) + 0x29c)
 #define VF_GUARDBAND		_MMIO(0x83a4)
 
-/* define the effective range of MCHBAR register on Sandybridge+ */
-#define MCHBAR_MIRROR_REG_BASE	_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x4000)
-
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 8998fa5ab198..7c99bbc3e2b8 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -1343,7 +1343,7 @@ static int prepare_mm(struct intel_vgpu_workload *workload)
 	struct execlist_ctx_descriptor_format *desc = &workload->ctx_desc;
 	struct intel_vgpu_mm *mm;
 	struct intel_vgpu *vgpu = workload->vgpu;
-	intel_gvt_gtt_type_t root_entry_type;
+	enum intel_gvt_gtt_type root_entry_type;
 	u64 pdps[GVT_RING_CTX_NR_PDPS];
 
 	switch (desc->addressing_mode) {
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index db88ce4d5509..ad01c92aaf74 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4199,7 +4199,7 @@ static bool discard_backing_storage(struct drm_i915_gem_object *obj)
 	 * acquiring such a reference whilst we are in the middle of
 	 * freeing the object.
 	 */
-	return atomic_long_read(&obj->base.filp->f_count) == 1;
+	return file_count(obj->base.filp) == 1;
 }
 
 static void __i915_gem_free_objects(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 3d672c9edb94..c83d2a195d15 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1666,6 +1666,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 					     len)) {
 end_user:
 				user_access_end();
+end:
 				kvfree(relocs);
 				err = -EFAULT;
 				goto err;
@@ -1685,7 +1686,7 @@ end_user:
 		 * relocations were valid.
 		 */
 		if (!user_access_begin(urelocs, size))
-			goto end_user;
+			goto end;
 
 		for (copied = 0; copied < nreloc; copied++)
 			unsafe_put_user(-1,
@@ -2697,7 +2698,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		 * when we did the "copy_from_user()" above.
 		 */
 		if (!user_access_begin(user_exec_list, count * sizeof(*user_exec_list)))
-			goto end_user;
+			goto end;
 
 		for (i = 0; i < args->buffer_count; i++) {
 			if (!(exec2_list[i].offset & UPDATE))
@@ -2711,6 +2712,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		}
 end_user:
 		user_access_end();
+end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 215bf3fef10c..8079ea3af103 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -122,7 +122,7 @@ userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 	while (it) {
 		struct drm_i915_gem_object *obj;
 
-		if (!range->blockable) {
+		if (!mmu_notifier_range_blockable(range)) {
 			ret = -EAGAIN;
 			break;
 		}
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index b836721d3b13..f6c78c0fa74b 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -425,6 +425,26 @@ void __i915_request_submit(struct i915_request *request)
 	if (i915_gem_context_is_banned(request->gem_context))
 		i915_request_skip(request, -EIO);
 
+	/*
+	 * Are we using semaphores when the gpu is already saturated?
+	 *
+	 * Using semaphores incurs a cost in having the GPU poll a
+	 * memory location, busywaiting for it to change. The continual
+	 * memory reads can have a noticeable impact on the rest of the
+	 * system with the extra bus traffic, stalling the cpu as it too
+	 * tries to access memory across the bus (perf stat -e bus-cycles).
+	 *
+	 * If we installed a semaphore on this request and we only submit
+	 * the request after the signaler completed, that indicates the
+	 * system is overloaded and using semaphores at this time only
+	 * increases the amount of work we are doing. If so, we disable
+	 * further use of semaphores until we are idle again, whence we
+	 * optimistically try again.
+	 */
+	if (request->sched.semaphores &&
+	    i915_sw_fence_signaled(&request->semaphore))
+		request->hw_context->saturated |= request->sched.semaphores;
+
 	/* We may be recursing from the signal callback of another i915 fence */
 	spin_lock_nested(&request->lock, SINGLE_DEPTH_NESTING);
 
@@ -432,6 +452,7 @@ void __i915_request_submit(struct i915_request *request)
 	set_bit(I915_FENCE_FLAG_ACTIVE, &request->fence.flags);
 
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &request->fence.flags) &&
+	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &request->fence.flags) &&
 	    !i915_request_enable_breadcrumb(request))
 		intel_engine_queue_breadcrumbs(engine);
 
@@ -799,6 +820,39 @@ err_unreserve:
 }
 
 static int
+i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
+{
+	if (list_is_first(&signal->ring_link, &signal->ring->request_list))
+		return 0;
+
+	signal = list_prev_entry(signal, ring_link);
+	if (i915_timeline_sync_is_later(rq->timeline, &signal->fence))
+		return 0;
+
+	return i915_sw_fence_await_dma_fence(&rq->submit,
+					     &signal->fence, 0,
+					     I915_FENCE_GFP);
+}
+
+static intel_engine_mask_t
+already_busywaiting(struct i915_request *rq)
+{
+	/*
+	 * Polling a semaphore causes bus traffic, delaying other users of
+	 * both the GPU and CPU. We want to limit the impact on others,
+	 * while taking advantage of early submission to reduce GPU
+	 * latency. Therefore we restrict ourselves to not using more
+	 * than one semaphore from each source, and not using a semaphore
+	 * if we have detected the engine is saturated (i.e. would not be
+	 * submitted early and cause bus traffic reading an already passed
+	 * semaphore).
+	 *
+	 * See the are-we-too-late? check in __i915_request_submit().
+	 */
+	return rq->sched.semaphores | rq->hw_context->saturated;
+}
+
+static int
 emit_semaphore_wait(struct i915_request *to,
 		    struct i915_request *from,
 		    gfp_t gfp)
@@ -811,11 +865,15 @@ emit_semaphore_wait(struct i915_request *to,
 	GEM_BUG_ON(INTEL_GEN(to->i915) < 8);
 
 	/* Just emit the first semaphore we see as request space is limited. */
-	if (to->sched.semaphores & from->engine->mask)
+	if (already_busywaiting(to) & from->engine->mask)
 		return i915_sw_fence_await_dma_fence(&to->submit,
 						     &from->fence, 0,
 						     I915_FENCE_GFP);
 
+	err = i915_request_await_start(to, from);
+	if (err < 0)
+		return err;
+
 	err = i915_sw_fence_await_dma_fence(&to->semaphore,
 					    &from->fence, 0,
 					    I915_FENCE_GFP);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 36726392e737..961268f66c63 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -52,11 +52,8 @@ void i915_vma_free(struct i915_vma *vma)
 
 static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 {
-	unsigned long entries[12];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char buf[512];
 
 	if (!vma->node.stack) {
@@ -65,8 +62,8 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 		return;
 	}
 
-	depot_fetch_stack(vma->node.stack, &trace);
-	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	nr_entries = stack_depot_fetch(vma->node.stack, &entries);
+	stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0);
 	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
 			 vma->node.start, vma->node.size, reason, buf);
 }
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 3cbffd400b1b..832cb6b1e9bd 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/kthread.h>
+#include <trace/events/dma_fence.h>
 #include <uapi/linux/sched/types.h>
 
 #include "i915_drv.h"
@@ -80,9 +81,39 @@ static inline bool __request_completed(const struct i915_request *rq)
 	return i915_seqno_passed(__hwsp_seqno(rq), rq->fence.seqno);
 }
 
+static bool
+__dma_fence_signal(struct dma_fence *fence)
+{
+	return !test_and_set_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
+}
+
+static void
+__dma_fence_signal__timestamp(struct dma_fence *fence, ktime_t timestamp)
+{
+	fence->timestamp = timestamp;
+	set_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags);
+	trace_dma_fence_signaled(fence);
+}
+
+static void
+__dma_fence_signal__notify(struct dma_fence *fence)
+{
+	struct dma_fence_cb *cur, *tmp;
+
+	lockdep_assert_held(fence->lock);
+	lockdep_assert_irqs_disabled();
+
+	list_for_each_entry_safe(cur, tmp, &fence->cb_list, node) {
+		INIT_LIST_HEAD(&cur->node);
+		cur->func(fence, cur);
+	}
+	INIT_LIST_HEAD(&fence->cb_list);
+}
+
 void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	const ktime_t timestamp = ktime_get();
 	struct intel_context *ce, *cn;
 	struct list_head *pos, *next;
 	LIST_HEAD(signal);
@@ -104,6 +135,10 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 
 			GEM_BUG_ON(!test_bit(I915_FENCE_FLAG_SIGNAL,
 					     &rq->fence.flags));
+			clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+
+			if (!__dma_fence_signal(&rq->fence))
+				continue;
 
 			/*
 			 * Queue for execution after dropping the signaling
@@ -111,14 +146,6 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 			 * more signalers to the same context or engine.
 			 */
 			i915_request_get(rq);
-
-			/*
-			 * We may race with direct invocation of
-			 * dma_fence_signal(), e.g. i915_request_retire(),
-			 * so we need to acquire our reference to the request
-			 * before we cancel the breadcrumb.
-			 */
-			clear_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
 			list_add_tail(&rq->signal_link, &signal);
 		}
 
@@ -141,7 +168,12 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 		struct i915_request *rq =
 			list_entry(pos, typeof(*rq), signal_link);
 
-		dma_fence_signal(&rq->fence);
+		__dma_fence_signal__timestamp(&rq->fence, timestamp);
+
+		spin_lock(&rq->lock);
+		__dma_fence_signal__notify(&rq->fence);
+		spin_unlock(&rq->lock);
+
 		i915_request_put(rq);
 	}
 }
@@ -243,19 +275,17 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
 
 bool i915_request_enable_breadcrumb(struct i915_request *rq)
 {
-	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
-
-	GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
+	lockdep_assert_held(&rq->lock);
+	lockdep_assert_irqs_disabled();
 
-	if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags))
-		return true;
-
-	spin_lock(&b->irq_lock);
-	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags) &&
-	    !__request_completed(rq)) {
+	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
+		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
 		struct intel_context *ce = rq->hw_context;
 		struct list_head *pos;
 
+		spin_lock(&b->irq_lock);
+		GEM_BUG_ON(test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags));
+
 		__intel_breadcrumbs_arm_irq(b);
 
 		/*
@@ -284,8 +314,8 @@ bool i915_request_enable_breadcrumb(struct i915_request *rq)
 			list_move_tail(&ce->signal_link, &b->signalers);
 
 		set_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags);
+		spin_unlock(&b->irq_lock);
 	}
-	spin_unlock(&b->irq_lock);
 
 	return !__request_completed(rq);
 }
@@ -294,9 +324,15 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 {
 	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
 
-	if (!test_bit(I915_FENCE_FLAG_SIGNAL, &rq->fence.flags))
-		return;
+	lockdep_assert_held(&rq->lock);
+	lockdep_assert_irqs_disabled();
 
+	/*
+	 * 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->hw_context;
diff --git a/drivers/gpu/drm/i915/intel_context.c b/drivers/gpu/drm/i915/intel_context.c
index 8931e0fee873..924cc556223a 100644
--- a/drivers/gpu/drm/i915/intel_context.c
+++ b/drivers/gpu/drm/i915/intel_context.c
@@ -230,6 +230,7 @@ intel_context_init(struct intel_context *ce,
 	ce->gem_context = ctx;
 	ce->engine = engine;
 	ce->ops = engine->cops;
+	ce->saturated = 0;
 
 	INIT_LIST_HEAD(&ce->signal_link);
 	INIT_LIST_HEAD(&ce->signals);
diff --git a/drivers/gpu/drm/i915/intel_context_types.h b/drivers/gpu/drm/i915/intel_context_types.h
index 68b4ca1611e0..339c7437fe82 100644
--- a/drivers/gpu/drm/i915/intel_context_types.h
+++ b/drivers/gpu/drm/i915/intel_context_types.h
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 
 #include "i915_active_types.h"
+#include "intel_engine_types.h"
 
 struct i915_gem_context;
 struct i915_vma;
@@ -58,6 +59,8 @@ struct intel_context {
 	atomic_t pin_count;
 	struct mutex pin_mutex; /* guards pinning and associated on-gpuing */
 
+	intel_engine_mask_t saturated; /* submitting semaphores too late? */
+
 	/**
 	 * active_tracker: Active tracker for the external rq activity
 	 * on this intel_context object.
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 5454930f6aa8..2eb62ed9e7cb 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12082,6 +12082,7 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 			  struct intel_crtc_state *pipe_config,
 			  bool adjust)
 {
+	struct intel_crtc *crtc = to_intel_crtc(current_config->base.crtc);
 	bool ret = true;
 	bool fixup_inherited = adjust &&
 		(current_config->base.mode.private_flags & I915_MODE_FLAG_INHERITED) &&
@@ -12303,6 +12304,14 @@ intel_pipe_config_compare(struct drm_i915_private *dev_priv,
 		PIPE_CONF_CHECK_X(gmch_pfit.pgm_ratios);
 	PIPE_CONF_CHECK_X(gmch_pfit.lvds_border_bits);
 
+	/*
+	 * Changing the EDP transcoder input mux
+	 * (A_ONOFF vs. A_ON) requires a full modeset.
+	 */
+	if (IS_HASWELL(dev_priv) && crtc->pipe == PIPE_A &&
+	    current_config->cpu_transcoder == TRANSCODER_EDP)
+		PIPE_CONF_CHECK_BOOL(pch_pfit.enabled);
+
 	if (!adjust) {
 		PIPE_CONF_CHECK_I(pipe_src_w);
 		PIPE_CONF_CHECK_I(pipe_src_h);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index c805a0966395..5679f2fffb7c 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -1280,6 +1280,10 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 	if (!HAS_FBC(dev_priv))
 		return 0;
 
+	/* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
+	if (IS_GEMINILAKE(dev_priv))
+		return 0;
+
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
 		return 1;
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 37f60cb8e9e1..46cd0e70aecb 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -23,7 +23,6 @@
  */
 
 #include <linux/circ_buf.h>
-#include <trace/events/dma_fence.h>
 
 #include "intel_guc_submission.h"
 #include "intel_lrc_reg.h"
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index e1005d7b75fd..34be2cfd0ec8 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -207,7 +207,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(VIDEO_DIP_CTL, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VIDEO_DIP_DATA, *data);
 		data++;
@@ -215,7 +214,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VIDEO_DIP_DATA, 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -282,7 +280,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -290,7 +287,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -364,7 +360,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -372,7 +367,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -439,7 +433,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -447,7 +440,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -514,7 +506,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), *data);
@@ -524,7 +515,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	for (; i < data_size; i += 4)
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), 0);
-	mmiowb();
 
 	val |= hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index e94b5b1bc1b7..e7c7be4911c1 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -311,10 +311,17 @@ retry:
 	pipe_config->base.mode_changed = pipe_config->has_psr;
 	pipe_config->crc_enabled = enable;
 
-	if (IS_HASWELL(dev_priv) && crtc->pipe == PIPE_A) {
+	if (IS_HASWELL(dev_priv) &&
+	    pipe_config->base.active && crtc->pipe == PIPE_A &&
+	    pipe_config->cpu_transcoder == TRANSCODER_EDP) {
+		bool old_need_power_well = pipe_config->pch_pfit.enabled ||
+			pipe_config->pch_pfit.force_thru;
+		bool new_need_power_well = pipe_config->pch_pfit.enabled ||
+			enable;
+
 		pipe_config->pch_pfit.force_thru = enable;
-		if (pipe_config->cpu_transcoder == TRANSCODER_EDP &&
-		    pipe_config->pch_pfit.enabled != enable)
+
+		if (old_need_power_well != new_need_power_well)
 			pipe_config->base.connectors_changed = true;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d4f4262d0fee..6150e35bf7b5 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -64,31 +64,20 @@
 static noinline depot_stack_handle_t __save_depot_stack(void)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-		.skip = 1,
-	};
-
-	save_stack_trace(&trace);
-	if (trace.nr_entries &&
-	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
-		trace.nr_entries--;
+	unsigned int n;
 
-	return depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
 }
 
 static void __print_depot_stack(depot_stack_handle_t stack,
 				char *buf, int sz, int indent)
 {
-	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 
-	depot_fetch_stack(stack, &trace);
-	snprint_stack_trace(buf, sz, &trace, indent);
+	nr_entries = stack_depot_fetch(stack, &entries);
+	stack_trace_snprint(buf, sz, entries, nr_entries, indent);
 }
 
 static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)