18 files changed, 190 insertions, 325 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 5b6922e28ef2..aa667fa71158 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -2166,7 +2166,8 @@ static void
 init_vbt_missing_defaults(struct drm_i915_private *i915)
 {
 	enum port port;
-	int ports = PORT_A | PORT_B | PORT_C | PORT_D | PORT_E | PORT_F;
+	int ports = BIT(PORT_A) | BIT(PORT_B) | BIT(PORT_C) |
+		    BIT(PORT_D) | BIT(PORT_E) | BIT(PORT_F);
 
 	if (!HAS_DDI(i915) && !IS_CHERRYVIEW(i915))
 		return;
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3bad4e00f7be..0a8a2395c8ac 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -5746,16 +5746,18 @@ static void bdw_set_pipemisc(const struct intel_crtc_state *crtc_state)
 
 	switch (crtc_state->pipe_bpp) {
 	case 18:
-		val |= PIPEMISC_DITHER_6_BPC;
+		val |= PIPEMISC_6_BPC;
 		break;
 	case 24:
-		val |= PIPEMISC_DITHER_8_BPC;
+		val |= PIPEMISC_8_BPC;
 		break;
 	case 30:
-		val |= PIPEMISC_DITHER_10_BPC;
+		val |= PIPEMISC_10_BPC;
 		break;
 	case 36:
-		val |= PIPEMISC_DITHER_12_BPC;
+		/* Port output 12BPC defined for ADLP+ */
+		if (DISPLAY_VER(dev_priv) > 12)
+			val |= PIPEMISC_12_BPC_ADLP;
 		break;
 	default:
 		MISSING_CASE(crtc_state->pipe_bpp);
@@ -5808,15 +5810,27 @@ int bdw_get_pipemisc_bpp(struct intel_crtc *crtc)
 
 	tmp = intel_de_read(dev_priv, PIPEMISC(crtc->pipe));
 
-	switch (tmp & PIPEMISC_DITHER_BPC_MASK) {
-	case PIPEMISC_DITHER_6_BPC:
+	switch (tmp & PIPEMISC_BPC_MASK) {
+	case PIPEMISC_6_BPC:
 		return 18;
-	case PIPEMISC_DITHER_8_BPC:
+	case PIPEMISC_8_BPC:
 		return 24;
-	case PIPEMISC_DITHER_10_BPC:
+	case PIPEMISC_10_BPC:
 		return 30;
-	case PIPEMISC_DITHER_12_BPC:
-		return 36;
+	/*
+	 * PORT OUTPUT 12 BPC defined for ADLP+.
+	 *
+	 * TODO:
+	 * For previous platforms with DSI interface, bits 5:7
+	 * are used for storing pipe_bpp irrespective of dithering.
+	 * Since the value of 12 BPC is not defined for these bits
+	 * on older platforms, need to find a workaround for 12 BPC
+	 * MIPI DSI HW readout.
+	 */
+	case PIPEMISC_12_BPC_ADLP:
+		if (DISPLAY_VER(dev_priv) > 12)
+			return 36;
+		fallthrough;
 	default:
 		MISSING_CASE(tmp);
 		return 0;
@@ -11361,13 +11375,19 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_C);
 		vlv_dsi_init(dev_priv);
-	} else if (DISPLAY_VER(dev_priv) >= 9) {
+	} else if (DISPLAY_VER(dev_priv) == 10) {
 		intel_ddi_init(dev_priv, PORT_A);
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_C);
 		intel_ddi_init(dev_priv, PORT_D);
 		intel_ddi_init(dev_priv, PORT_E);
 		intel_ddi_init(dev_priv, PORT_F);
+	} else if (DISPLAY_VER(dev_priv) >= 9) {
+		intel_ddi_init(dev_priv, PORT_A);
+		intel_ddi_init(dev_priv, PORT_B);
+		intel_ddi_init(dev_priv, PORT_C);
+		intel_ddi_init(dev_priv, PORT_D);
+		intel_ddi_init(dev_priv, PORT_E);
 	} else if (HAS_DDI(dev_priv)) {
 		u32 found;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index a8abc9af5ff4..4a6419d7be93 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,10 +25,8 @@
 #include "i915_gem_clflush.h"
 #include "i915_gem_context.h"
 #include "i915_gem_ioctls.h"
-#include "i915_sw_fence_work.h"
 #include "i915_trace.h"
 #include "i915_user_extensions.h"
-#include "i915_memcpy.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -1456,6 +1454,10 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
 		int err;
 		struct intel_engine_cs *engine = eb->engine;
 
+		/* If we need to copy for the cmdparser, we will stall anyway */
+		if (eb_use_cmdparser(eb))
+			return ERR_PTR(-EWOULDBLOCK);
+
 		if (!reloc_can_use_engine(engine)) {
 			engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
 			if (!engine)
@@ -2372,217 +2374,6 @@ shadow_batch_pin(struct i915_execbuffer *eb,
 	return vma;
 }
 
-struct eb_parse_work {
-	struct dma_fence_work base;
-	struct intel_engine_cs *engine;
-	struct i915_vma *batch;
-	struct i915_vma *shadow;
-	struct i915_vma *trampoline;
-	unsigned long batch_offset;
-	unsigned long batch_length;
-	unsigned long *jump_whitelist;
-	const void *batch_map;
-	void *shadow_map;
-};
-
-static int __eb_parse(struct dma_fence_work *work)
-{
-	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-	int ret;
-	bool cookie;
-
-	cookie = dma_fence_begin_signalling();
-	ret = intel_engine_cmd_parser(pw->engine,
-				      pw->batch,
-				      pw->batch_offset,
-				      pw->batch_length,
-				      pw->shadow,
-				      pw->jump_whitelist,
-				      pw->shadow_map,
-				      pw->batch_map);
-	dma_fence_end_signalling(cookie);
-
-	return ret;
-}
-
-static void __eb_parse_release(struct dma_fence_work *work)
-{
-	struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-
-	if (!IS_ERR_OR_NULL(pw->jump_whitelist))
-		kfree(pw->jump_whitelist);
-
-	if (pw->batch_map)
-		i915_gem_object_unpin_map(pw->batch->obj);
-	else
-		i915_gem_object_unpin_pages(pw->batch->obj);
-
-	i915_gem_object_unpin_map(pw->shadow->obj);
-
-	if (pw->trampoline)
-		i915_active_release(&pw->trampoline->active);
-	i915_active_release(&pw->shadow->active);
-	i915_active_release(&pw->batch->active);
-}
-
-static const struct dma_fence_work_ops eb_parse_ops = {
-	.name = "eb_parse",
-	.work = __eb_parse,
-	.release = __eb_parse_release,
-};
-
-static inline int
-__parser_mark_active(struct i915_vma *vma,
-		     struct intel_timeline *tl,
-		     struct dma_fence *fence)
-{
-	struct intel_gt_buffer_pool_node *node = vma->private;
-
-	return i915_active_ref(&node->active, tl->fence_context, fence);
-}
-
-static int
-parser_mark_active(struct eb_parse_work *pw, struct intel_timeline *tl)
-{
-	int err;
-
-	mutex_lock(&tl->mutex);
-
-	err = __parser_mark_active(pw->shadow, tl, &pw->base.dma);
-	if (err)
-		goto unlock;
-
-	if (pw->trampoline) {
-		err = __parser_mark_active(pw->trampoline, tl, &pw->base.dma);
-		if (err)
-			goto unlock;
-	}
-
-unlock:
-	mutex_unlock(&tl->mutex);
-	return err;
-}
-
-static int eb_parse_pipeline(struct i915_execbuffer *eb,
-			     struct i915_vma *shadow,
-			     struct i915_vma *trampoline)
-{
-	struct eb_parse_work *pw;
-	struct drm_i915_gem_object *batch = eb->batch->vma->obj;
-	bool needs_clflush;
-	int err;
-
-	GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset));
-	GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length));
-
-	pw = kzalloc(sizeof(*pw), GFP_KERNEL);
-	if (!pw)
-		return -ENOMEM;
-
-	err = i915_active_acquire(&eb->batch->vma->active);
-	if (err)
-		goto err_free;
-
-	err = i915_active_acquire(&shadow->active);
-	if (err)
-		goto err_batch;
-
-	if (trampoline) {
-		err = i915_active_acquire(&trampoline->active);
-		if (err)
-			goto err_shadow;
-	}
-
-	pw->shadow_map = i915_gem_object_pin_map(shadow->obj, I915_MAP_WB);
-	if (IS_ERR(pw->shadow_map)) {
-		err = PTR_ERR(pw->shadow_map);
-		goto err_trampoline;
-	}
-
-	needs_clflush =
-		!(batch->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
-	pw->batch_map = ERR_PTR(-ENODEV);
-	if (needs_clflush && i915_has_memcpy_from_wc())
-		pw->batch_map = i915_gem_object_pin_map(batch, I915_MAP_WC);
-
-	if (IS_ERR(pw->batch_map)) {
-		err = i915_gem_object_pin_pages(batch);
-		if (err)
-			goto err_unmap_shadow;
-		pw->batch_map = NULL;
-	}
-
-	pw->jump_whitelist =
-		intel_engine_cmd_parser_alloc_jump_whitelist(eb->batch_len,
-							     trampoline);
-	if (IS_ERR(pw->jump_whitelist)) {
-		err = PTR_ERR(pw->jump_whitelist);
-		goto err_unmap_batch;
-	}
-
-	dma_fence_work_init(&pw->base, &eb_parse_ops);
-
-	pw->engine = eb->engine;
-	pw->batch = eb->batch->vma;
-	pw->batch_offset = eb->batch_start_offset;
-	pw->batch_length = eb->batch_len;
-	pw->shadow = shadow;
-	pw->trampoline = trampoline;
-
-	/* Mark active refs early for this worker, in case we get interrupted */
-	err = parser_mark_active(pw, eb->context->timeline);
-	if (err)
-		goto err_commit;
-
-	err = dma_resv_reserve_shared(pw->batch->resv, 1);
-	if (err)
-		goto err_commit;
-
-	err = dma_resv_reserve_shared(shadow->resv, 1);
-	if (err)
-		goto err_commit;
-
-	/* Wait for all writes (and relocs) into the batch to complete */
-	err = i915_sw_fence_await_reservation(&pw->base.chain,
-					      pw->batch->resv, NULL, false,
-					      0, I915_FENCE_GFP);
-	if (err < 0)
-		goto err_commit;
-
-	/* Keep the batch alive and unwritten as we parse */
-	dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
-
-	/* Force execution to wait for completion of the parser */
-	dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
-
-	dma_fence_work_commit_imm(&pw->base);
-	return 0;
-
-err_commit:
-	i915_sw_fence_set_error_once(&pw->base.chain, err);
-	dma_fence_work_commit_imm(&pw->base);
-	return err;
-
-err_unmap_batch:
-	if (pw->batch_map)
-		i915_gem_object_unpin_map(batch);
-	else
-		i915_gem_object_unpin_pages(batch);
-err_unmap_shadow:
-	i915_gem_object_unpin_map(shadow->obj);
-err_trampoline:
-	if (trampoline)
-		i915_active_release(&trampoline->active);
-err_shadow:
-	i915_active_release(&shadow->active);
-err_batch:
-	i915_active_release(&eb->batch->vma->active);
-err_free:
-	kfree(pw);
-	return err;
-}
-
 static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma)
 {
 	/*
@@ -2672,7 +2463,15 @@ static int eb_parse(struct i915_execbuffer *eb)
 		goto err_trampoline;
 	}
 
-	err = eb_parse_pipeline(eb, shadow, trampoline);
+	err = dma_resv_reserve_shared(shadow->resv, 1);
+	if (err)
+		goto err_trampoline;
+
+	err = intel_engine_cmd_parser(eb->engine,
+				      eb->batch->vma,
+				      eb->batch_start_offset,
+				      eb->batch_len,
+				      shadow, trampoline);
 	if (err)
 		goto err_unpin_batch;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index f4fb68e8955a..e382b7f2353b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -62,6 +62,7 @@ static void try_to_writeback(struct drm_i915_gem_object *obj,
 	switch (obj->mm.madv) {
 	case I915_MADV_DONTNEED:
 		i915_gem_object_truncate(obj);
+		return;
 	case __I915_MADV_PURGED:
 		return;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 7487bab11f0b..458f797a9e1e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -133,7 +133,6 @@ static int i915_gem_userptr_get_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;
 	struct page **pvec;
 	int ret;
 
@@ -153,13 +152,11 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 	spin_unlock(&i915->mm.notifier_lock);
 
 alloc_table:
-	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)) {
-		ret = PTR_ERR(sg);
+	ret = sg_alloc_table_from_pages_segment(st, pvec, num_pages, 0,
+						num_pages << PAGE_SHIFT,
+						max_segment, GFP_KERNEL);
+	if (ret)
 		goto err;
-	}
 
 	ret = i915_gem_gtt_prepare_pages(obj, st);
 	if (ret) {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 4df505e4c53a..16162fc2782d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -125,6 +125,10 @@ static int igt_gpu_reloc(void *arg)
 	intel_gt_pm_get(&eb.i915->gt);
 
 	for_each_uabi_engine(eb.engine, eb.i915) {
+		if (intel_engine_requires_cmd_parser(eb.engine) ||
+		    intel_engine_using_cmd_parser(eb.engine))
+			continue;
+
 		reloc_cache_init(&eb.reloc_cache, eb.i915);
 		memset(map, POISON_INUSE, 4096);
 
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index 21c8b7350b7a..da4f5eb43ac2 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -303,10 +303,7 @@ static void __gen8_ppgtt_alloc(struct i915_address_space * const vm,
 			__i915_gem_object_pin_pages(pt->base);
 			i915_gem_object_make_unshrinkable(pt->base);
 
-			if (lvl ||
-			    gen8_pt_count(*start, end) < I915_PDES ||
-			    intel_vgpu_active(vm->i915))
-				fill_px(pt, vm->scratch[lvl]->encode);
+			fill_px(pt, vm->scratch[lvl]->encode);
 
 			spin_lock(&pd->lock);
 			if (likely(!pd->entry[idx])) {
diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
index cac7f3f44642..f8948de72036 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c
@@ -348,7 +348,7 @@ static struct i915_fence_reg *fence_find(struct i915_ggtt *ggtt)
 	if (intel_has_pending_fb_unpin(ggtt->vm.i915))
 		return ERR_PTR(-EAGAIN);
 
-	return ERR_PTR(-EDEADLK);
+	return ERR_PTR(-ENOBUFS);
 }
 
 int __i915_vma_pin_fence(struct i915_vma *vma)
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 98eb48c24c46..cde0a477fb49 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1977,6 +1977,21 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 	if (drm_WARN_ON(&i915->drm, !engine))
 		return -EINVAL;
 
+	/*
+	 * Due to d3_entered is used to indicate skipping PPGTT invalidation on
+	 * vGPU reset, it's set on D0->D3 on PCI config write, and cleared after
+	 * vGPU reset if in resuming.
+	 * In S0ix exit, the device power state also transite from D3 to D0 as
+	 * S3 resume, but no vGPU reset (triggered by QEMU devic model). After
+	 * S0ix exit, all engines continue to work. However the d3_entered
+	 * remains set which will break next vGPU reset logic (miss the expected
+	 * PPGTT invalidation).
+	 * Engines can only work in D0. Thus the 1st elsp write gives GVT a
+	 * chance to clear d3_entered.
+	 */
+	if (vgpu->d3_entered)
+		vgpu->d3_entered = false;
+
 	execlist = &vgpu->submission.execlist[engine->id];
 
 	execlist->elsp_dwords.data[3 - execlist->elsp_dwords.index] = data;
@@ -3134,6 +3149,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(_MMIO(0xb100), D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(_MMIO(0xb10c), D_BDW, F_CMD_ACCESS, NULL, NULL);
 	MMIO_D(_MMIO(0xb110), D_BDW);
+	MMIO_D(GEN9_SCRATCH_LNCF1, D_BDW_PLUS);
 
 	MMIO_F(_MMIO(0x24d0), 48, F_CMD_ACCESS | F_CMD_WRITE_PATCH, 0, 0,
 		D_BDW_PLUS, NULL, force_nonpriv_write);
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index b8ac80765461..f776c470914d 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -105,6 +105,8 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{RCS0, COMMON_SLICE_CHICKEN2, 0xffff, true}, /* 0x7014 */
 	{RCS0, GEN9_CS_DEBUG_MODE1, 0xffff, false}, /* 0x20ec */
 	{RCS0, GEN8_L3SQCREG4, 0, false}, /* 0xb118 */
+	{RCS0, GEN9_SCRATCH1, 0, false}, /* 0xb11c */
+	{RCS0, GEN9_SCRATCH_LNCF1, 0, false}, /* 0xb008 */
 	{RCS0, GEN7_HALF_SLICE_CHICKEN1, 0xffff, true}, /* 0xe100 */
 	{RCS0, HALF_SLICE_CHICKEN2, 0xffff, true}, /* 0xe180 */
 	{RCS0, HALF_SLICE_CHICKEN3, 0xffff, true}, /* 0xe184 */
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 3992c25a191d..a3b4d99d64b9 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1145,19 +1145,41 @@ find_reg(const struct intel_engine_cs *engine, u32 addr)
 static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		       struct drm_i915_gem_object *src_obj,
 		       unsigned long offset, unsigned long length,
-		       void *dst, const void *src)
+		       bool *needs_clflush_after)
 {
-	bool needs_clflush =
-		!(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
-	if (src) {
-		GEM_BUG_ON(!needs_clflush);
-		i915_unaligned_memcpy_from_wc(dst, src + offset, length);
-	} else {
-		struct scatterlist *sg;
+	unsigned int src_needs_clflush;
+	unsigned int dst_needs_clflush;
+	void *dst, *src;
+	int ret;
+
+	ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
+	if (ret)
+		return ERR_PTR(ret);
+
+	dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB);
+	i915_gem_object_finish_access(dst_obj);
+	if (IS_ERR(dst))
+		return dst;
+
+	ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
+	if (ret) {
+		i915_gem_object_unpin_map(dst_obj);
+		return ERR_PTR(ret);
+	}
+
+	src = ERR_PTR(-ENODEV);
+	if (src_needs_clflush && i915_has_memcpy_from_wc()) {
+		src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
+		if (!IS_ERR(src)) {
+			i915_unaligned_memcpy_from_wc(dst,
+						      src + offset,
+						      length);
+			i915_gem_object_unpin_map(src_obj);
+		}
+	}
+	if (IS_ERR(src)) {
+		unsigned long x, n, remain;
 		void *ptr;
-		unsigned int x, sg_ofs;
-		unsigned long remain;
 
 		/*
 		 * We can avoid clflushing partial cachelines before the write
@@ -1168,40 +1190,34 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 		 * validate up to the end of the batch.
 		 */
 		remain = length;
-		if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+		if (dst_needs_clflush & CLFLUSH_BEFORE)
 			remain = round_up(remain,
 					  boot_cpu_data.x86_clflush_size);
 
 		ptr = dst;
 		x = offset_in_page(offset);
-		sg = i915_gem_object_get_sg(src_obj, offset >> PAGE_SHIFT, &sg_ofs, false);
-
-		while (remain) {
-			unsigned long sg_max = sg->length >> PAGE_SHIFT;
-
-			for (; remain && sg_ofs < sg_max; sg_ofs++) {
-				unsigned long len = min(remain, PAGE_SIZE - x);
-				void *map;
-
-				map = kmap_atomic(nth_page(sg_page(sg), sg_ofs));
-				if (needs_clflush)
-					drm_clflush_virt_range(map + x, len);
-				memcpy(ptr, map + x, len);
-				kunmap_atomic(map);
-
-				ptr += len;
-				remain -= len;
-				x = 0;
-			}
-
-			sg_ofs = 0;
-			sg = sg_next(sg);
+		for (n = offset >> PAGE_SHIFT; remain; n++) {
+			int len = min(remain, PAGE_SIZE - x);
+
+			src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
+			if (src_needs_clflush)
+				drm_clflush_virt_range(src + x, len);
+			memcpy(ptr, src + x, len);
+			kunmap_atomic(src);
+
+			ptr += len;
+			remain -= len;
+			x = 0;
 		}
 	}
 
+	i915_gem_object_finish_access(src_obj);
+
 	memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
 
 	/* dst_obj is returned with vmap pinned */
+	*needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER;
+
 	return dst;
 }
 
@@ -1360,6 +1376,9 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
 	if (target_cmd_index == offset)
 		return 0;
 
+	if (IS_ERR(jump_whitelist))
+		return PTR_ERR(jump_whitelist);
+
 	if (!test_bit(target_cmd_index, jump_whitelist)) {
 		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
 			  jump_target);
@@ -1369,28 +1388,10 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
 	return 0;
 }
 
-/**
- * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser()
- * @batch_length: length of the commands in batch_obj
- * @trampoline: Whether jump trampolines are used.
- *
- * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser().
- * This has to be preallocated, because the command parser runs in signaling context,
- * and may not allocate any memory.
- *
- * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use
- * IS_ERR() to check for errors. Must bre freed() with kfree().
- *
- * NULL is a valid value, meaning no allocation was required.
- */
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
-							    bool trampoline)
+static unsigned long *alloc_whitelist(u32 batch_length)
 {
 	unsigned long *jmp;
 
-	if (trampoline)
-		return NULL;
-
 	/*
 	 * We expect batch_length to be less than 256KiB for known users,
 	 * i.e. we need at most an 8KiB bitmap allocation which should be
@@ -1415,9 +1416,7 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
  * @batch_offset: byte offset in the batch at which execution starts
  * @batch_length: length of the commands in batch_obj
  * @shadow: validated copy of the batch buffer in question
- * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist()
- * @shadow_map: mapping to @shadow vma
- * @batch_map: mapping to @batch vma
+ * @trampoline: true if we need to trampoline into privileged execution
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1425,21 +1424,21 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
+
 int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			    struct i915_vma *batch,
 			    unsigned long batch_offset,
 			    unsigned long batch_length,
 			    struct i915_vma *shadow,
-			    unsigned long *jump_whitelist,
-			    void *shadow_map,
-			    const void *batch_map)
+			    bool trampoline)
 {
 	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
+	bool needs_clflush_after = false;
+	unsigned long *jump_whitelist;
 	u64 batch_addr, shadow_addr;
 	int ret = 0;
-	bool trampoline = !jump_whitelist;
 
 	GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
 	GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
@@ -1447,8 +1446,18 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 				     batch->size));
 	GEM_BUG_ON(!batch_length);
 
-	cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length,
-			 shadow_map, batch_map);
+	cmd = copy_batch(shadow->obj, batch->obj,
+			 batch_offset, batch_length,
+			 &needs_clflush_after);
+	if (IS_ERR(cmd)) {
+		DRM_DEBUG("CMD: Failed to copy batch\n");
+		return PTR_ERR(cmd);
+	}
+
+	jump_whitelist = NULL;
+	if (!trampoline)
+		/* Defer failure until attempted use */
+		jump_whitelist = alloc_whitelist(batch_length);
 
 	shadow_addr = gen8_canonical_addr(shadow->node.start);
 	batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
@@ -1549,6 +1558,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 
 	i915_gem_object_flush_map(shadow->obj);
 
+	if (!IS_ERR_OR_NULL(jump_whitelist))
+		kfree(jump_whitelist);
+	i915_gem_object_unpin_map(shadow->obj);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 38ff2fb89744..b30397b04529 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1906,17 +1906,12 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 int intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
-							    bool trampoline);
-
 int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			    struct i915_vma *batch,
 			    unsigned long batch_offset,
 			    unsigned long batch_length,
 			    struct i915_vma *shadow,
-			    unsigned long *jump_whitelist,
-			    void *shadow_map,
-			    const void *batch_map);
+			    bool trampoline);
 #define I915_CMD_PARSER_TRAMPOLINE_SIZE 8
 
 /* intel_device_info.c */
diff --git a/drivers/gpu/drm/i915/i915_globals.c b/drivers/gpu/drm/i915/i915_globals.c
index 77f1911c463b..3acb0b6be284 100644
--- a/drivers/gpu/drm/i915/i915_globals.c
+++ b/drivers/gpu/drm/i915/i915_globals.c
@@ -138,7 +138,7 @@ void i915_globals_unpark(void)
 	atomic_inc(&active);
 }
 
-static void __exit __i915_globals_flush(void)
+static void  __i915_globals_flush(void)
 {
 	atomic_inc(&active); /* skip shrinking */
 
@@ -148,7 +148,7 @@ static void __exit __i915_globals_flush(void)
 	atomic_dec(&active);
 }
 
-void __exit i915_globals_exit(void)
+void i915_globals_exit(void)
 {
 	GEM_BUG_ON(atomic_read(&active));
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 35c97c39f125..966664610c8c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -727,9 +727,18 @@ static void err_print_gt(struct drm_i915_error_state_buf *m,
 	if (GRAPHICS_VER(m->i915) >= 12) {
 		int i;
 
-		for (i = 0; i < GEN12_SFC_DONE_MAX; i++)
+		for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
+			/*
+			 * SFC_DONE resides in the VD forcewake domain, so it
+			 * only exists if the corresponding VCS engine is
+			 * present.
+			 */
+			if (!HAS_ENGINE(gt->_gt, _VCS(i * 2)))
+				continue;
+
 			err_printf(m, "  SFC_DONE[%d]: 0x%08x\n", i,
 				   gt->sfc_done[i]);
+		}
 
 		err_printf(m, "  GAM_DONE: 0x%08x\n", gt->gam_done);
 	}
@@ -1581,6 +1590,14 @@ static void gt_record_regs(struct intel_gt_coredump *gt)
 
 	if (GRAPHICS_VER(i915) >= 12) {
 		for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
+			/*
+			 * SFC_DONE resides in the VD forcewake domain, so it
+			 * only exists if the corresponding VCS engine is
+			 * present.
+			 */
+			if (!HAS_ENGINE(gt->_gt, _VCS(i * 2)))
+				continue;
+
 			gt->sfc_done[i] =
 				intel_uncore_read(uncore, GEN12_SFC_DONE(i));
 		}
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 83b500bb170c..2880ec57c97d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -1195,6 +1195,7 @@ static int __init i915_init(void)
 	err = pci_register_driver(&i915_pci_driver);
 	if (err) {
 		i915_pmu_exit();
+		i915_globals_exit();
 		return err;
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 94fde5ca26ae..476bb3b9ad11 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -422,7 +422,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   GEN12_HCP_SFC_LOCK_ACK_BIT		REG_BIT(1)
 #define   GEN12_HCP_SFC_USAGE_BIT			REG_BIT(0)
 
-#define GEN12_SFC_DONE(n)		_MMIO(0x1cc00 + (n) * 0x100)
+#define GEN12_SFC_DONE(n)		_MMIO(0x1cc000 + (n) * 0x1000)
 #define GEN12_SFC_DONE_MAX		4
 
 #define RING_PP_DIR_BASE(base)		_MMIO((base) + 0x228)
@@ -6163,11 +6163,17 @@ enum {
 #define   PIPEMISC_HDR_MODE_PRECISION	(1 << 23) /* icl+ */
 #define   PIPEMISC_OUTPUT_COLORSPACE_YUV  (1 << 11)
 #define   PIPEMISC_PIXEL_ROUNDING_TRUNC	REG_BIT(8) /* tgl+ */
-#define   PIPEMISC_DITHER_BPC_MASK	(7 << 5)
-#define   PIPEMISC_DITHER_8_BPC		(0 << 5)
-#define   PIPEMISC_DITHER_10_BPC	(1 << 5)
-#define   PIPEMISC_DITHER_6_BPC		(2 << 5)
-#define   PIPEMISC_DITHER_12_BPC	(3 << 5)
+/*
+ * For Display < 13, Bits 5-7 of PIPE MISC represent DITHER BPC with
+ * valid values of: 6, 8, 10 BPC.
+ * ADLP+, the bits 5-7 represent PORT OUTPUT BPC with valid values of:
+ * 6, 8, 10, 12 BPC.
+ */
+#define   PIPEMISC_BPC_MASK		(7 << 5)
+#define   PIPEMISC_8_BPC		(0 << 5)
+#define   PIPEMISC_10_BPC		(1 << 5)
+#define   PIPEMISC_6_BPC		(2 << 5)
+#define   PIPEMISC_12_BPC_ADLP		(4 << 5) /* adlp+ */
 #define   PIPEMISC_DITHER_ENABLE	(1 << 4)
 #define   PIPEMISC_DITHER_TYPE_MASK	(3 << 2)
 #define   PIPEMISC_DITHER_TYPE_SP	(0 << 2)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 1014c71cf7f5..37aef1308573 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1426,10 +1426,8 @@ i915_request_await_execution(struct i915_request *rq,
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
-			i915_sw_fence_set_error_once(&rq->submit, fence->error);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 			continue;
-		}
 
 		if (fence->context == rq->fence.context)
 			continue;
@@ -1527,10 +1525,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
 
 	do {
 		fence = *child++;
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
-			i915_sw_fence_set_error_once(&rq->submit, fence->error);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 			continue;
-		}
 
 		/*
 		 * Requests on the same timeline are explicitly ordered, along
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 7eaa92fee421..e0a10f36acc1 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -325,7 +325,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 			info->pipe_mask &= ~BIT(PIPE_C);
 			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
 		}
-	} else if (HAS_DISPLAY(dev_priv) && GRAPHICS_VER(dev_priv) >= 9) {
+	} else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) {
 		u32 dfsm = intel_de_read(dev_priv, SKL_DFSM);
 
 		if (dfsm & SKL_DFSM_PIPE_A_DISABLE) {
@@ -340,7 +340,8 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 			info->pipe_mask &= ~BIT(PIPE_C);
 			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
 		}
-		if (GRAPHICS_VER(dev_priv) >= 12 &&
+
+		if (DISPLAY_VER(dev_priv) >= 12 &&
 		    (dfsm & TGL_DFSM_PIPE_D_DISABLE)) {
 			info->pipe_mask &= ~BIT(PIPE_D);
 			info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D);
@@ -352,10 +353,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 		if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE)
 			info->display.has_fbc = 0;
 
-		if (GRAPHICS_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
+		if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
 			info->display.has_dmc = 0;
 
-		if (GRAPHICS_VER(dev_priv) >= 10 &&
+		if (DISPLAY_VER(dev_priv) >= 10 &&
 		    (dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE))
 			info->display.has_dsc = 0;
 	}