Merge tag 'drm-intel-next-2019-04-17' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- uAPI "Fixes:" patch for the upcoming kernel 5.1, included here too

  We have an Ack from the media folks (only current user) for this
  late tweak

Cross-subsystem Changes:

- ALSA: hda: Fix racy display power access (Takashi, Chris)

Driver Changes:

- DDI and MIPI-DSI clocks fixes for Icelake (Vandita)
- Fix Icelake frequency change/locking (RPS) (Mika)
- Temporarily disable ppGTT read-only bit on Icelake (Mika)
- Add missing Icelake W/As (Mika)
- Enable 12 deep CSB status FIFO on Icelake (Mika)
- Inherit more Icelake code for Elkhartlake (Bob, Jani)

- Handle catastrophic error on engine reset (Mika)
- Shortcut readiness to reset check (Mika)
- Regression fix for GEM_BUSY causing us to report a mixed uabi-class request as not busy (Chris)
- Revert back to max link rate and lane count on eDP (Jani)
- Fix pipe BPP readout for BXT/GLK DSI (Ville)
- Set DP min_bpp to 8*3 for non-RGB output formats (Ville)
- Enable coarse preemption boundaries for Gen8 (Chris)
- Do not enable FEC without DSC (Ville)
- Restore correct BXT DDI latency optim setting calculation (Ville)
- Always reset context's RING registers to avoid running workload twice during reset (Chris)
- Set GPU wedged on driver unload (Janusz)
- Consolidate two similar barries from timeline into one (Chris)
- Only reset the pinned kernel contexts on resume (Chris)
- Wakeref tracking improvements (Chris, Imre)
- Lockdep fixes for shrinker interactions (Chris)
- Bump ready tasks ahead of busywaits in prep of semaphore use (Chris)

- Huge step in splitting display code into fine grained files (Jani)
- Refactor the IRQ init/reset macros for code saving (Paulo)
- Convert IRQ initialization code to uncore MMIO access (Paulo)
- Convert workarounds code to use uncore MMIO access (Chris)
- Nuke drm_crtc_state and use intel_atomic_state instead (Manasi)
- Update SKL clock-gating WA (Radhakrishna, Ville)
- Isolate GuC reset code flow (Chris)
- Expose force_dsc_enable through debugfs (Manasi)
- Header standalone compile testing framework (Jani)
- Code cleanups to reduce driver footprint (Chris)
- PSR code fixes and cleanups (Jose)
- Sparse and kerneldoc updates (Chris)
- Suppress spurious combo PHY B warning (Vile)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190418080426.GA6409@jlahtine-desk.ger.corp.intel.com

14 files changed, 193 insertions, 102 deletions

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index d8d59695619e..ab002cfd3cab 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1077,6 +1077,7 @@ static int cmd_handler_pipe_control(struct parser_exec_state *s)
 	bool index_mode = false;
 	unsigned int post_sync;
 	int ret = 0;
+	u32 hws_pga, val;
 
 	post_sync = (cmd_val(s, 1) & PIPE_CONTROL_POST_SYNC_OP_MASK) >> 14;
 
@@ -1100,6 +1101,15 @@ static int cmd_handler_pipe_control(struct parser_exec_state *s)
 					index_mode = true;
 				ret |= cmd_address_audit(s, gma, sizeof(u64),
 						index_mode);
+				if (ret)
+					return ret;
+				if (index_mode) {
+					hws_pga = s->vgpu->hws_pga[s->ring_id];
+					gma = hws_pga + gma;
+					patch_value(s, cmd_ptr(s, 2), gma);
+					val = cmd_val(s, 1) & (~(1 << 21));
+					patch_value(s, cmd_ptr(s, 1), val);
+				}
 			}
 		}
 	}
@@ -1317,8 +1327,14 @@ static int gen8_update_plane_mmio_from_mi_display_flip(
 			      info->tile_val << 10);
 	}
 
-	vgpu_vreg_t(vgpu, PIPE_FRMCOUNT_G4X(info->pipe))++;
-	intel_vgpu_trigger_virtual_event(vgpu, info->event);
+	if (info->plane == PLANE_PRIMARY)
+		vgpu_vreg_t(vgpu, PIPE_FLIPCOUNT_G4X(info->pipe))++;
+
+	if (info->async_flip)
+		intel_vgpu_trigger_virtual_event(vgpu, info->event);
+	else
+		set_bit(info->event, vgpu->irq.flip_done_event[info->pipe]);
+
 	return 0;
 }
 
@@ -1563,6 +1579,7 @@ static int cmd_handler_mi_flush_dw(struct parser_exec_state *s)
 	unsigned long gma;
 	bool index_mode = false;
 	int ret = 0;
+	u32 hws_pga, val;
 
 	/* Check post-sync and ppgtt bit */
 	if (((cmd_val(s, 0) >> 14) & 0x3) && (cmd_val(s, 1) & (1 << 2))) {
@@ -1573,6 +1590,15 @@ static int cmd_handler_mi_flush_dw(struct parser_exec_state *s)
 		if (cmd_val(s, 0) & (1 << 21))
 			index_mode = true;
 		ret = cmd_address_audit(s, gma, sizeof(u64), index_mode);
+		if (ret)
+			return ret;
+		if (index_mode) {
+			hws_pga = s->vgpu->hws_pga[s->ring_id];
+			gma = hws_pga + gma;
+			patch_value(s, cmd_ptr(s, 1), gma);
+			val = cmd_val(s, 0) & (~(1 << 21));
+			patch_value(s, cmd_ptr(s, 0), val);
+		}
 	}
 	/* Check notify bit */
 	if ((cmd_val(s, 0) & (1 << 8)))
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index e3f9caa7839f..e1c313da6c00 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -407,7 +407,6 @@ static void emulate_vblank_on_pipe(struct intel_vgpu *vgpu, int pipe)
 		if (!pipe_is_enabled(vgpu, pipe))
 			continue;
 
-		vgpu_vreg_t(vgpu, PIPE_FLIPCOUNT_G4X(pipe))++;
 		intel_vgpu_trigger_virtual_event(vgpu, event);
 	}
 
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index 1a93472cb34e..f21b8fb5b37e 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -526,12 +526,13 @@ static void init_vgpu_execlist(struct intel_vgpu *vgpu, int ring_id)
 	vgpu_vreg(vgpu, ctx_status_ptr_reg) = ctx_status_ptr.dw;
 }
 
-static void clean_execlist(struct intel_vgpu *vgpu, unsigned long engine_mask)
+static void clean_execlist(struct intel_vgpu *vgpu,
+			   intel_engine_mask_t engine_mask)
 {
-	unsigned int tmp;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_engine_cs *engine;
 	struct intel_vgpu_submission *s = &vgpu->submission;
+	intel_engine_mask_t tmp;
 
 	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
 		kfree(s->ring_scan_buffer[engine->id]);
@@ -541,18 +542,18 @@ static void clean_execlist(struct intel_vgpu *vgpu, unsigned long engine_mask)
 }
 
 static void reset_execlist(struct intel_vgpu *vgpu,
-		unsigned long engine_mask)
+			   intel_engine_mask_t engine_mask)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_engine_cs *engine;
-	unsigned int tmp;
+	intel_engine_mask_t tmp;
 
 	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
 		init_vgpu_execlist(vgpu, engine->id);
 }
 
 static int init_execlist(struct intel_vgpu *vgpu,
-			 unsigned long engine_mask)
+			 intel_engine_mask_t engine_mask)
 {
 	reset_execlist(vgpu, engine_mask);
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/execlist.h b/drivers/gpu/drm/i915/gvt/execlist.h
index 714d709829a2..5ccc2c695848 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.h
+++ b/drivers/gpu/drm/i915/gvt/execlist.h
@@ -180,6 +180,6 @@ int intel_vgpu_init_execlist(struct intel_vgpu *vgpu);
 int intel_vgpu_submit_execlist(struct intel_vgpu *vgpu, int ring_id);
 
 void intel_vgpu_reset_execlist(struct intel_vgpu *vgpu,
-		unsigned long engine_mask);
+			       intel_engine_mask_t engine_mask);
 
 #endif /*_GVT_EXECLIST_H_*/
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 9814773882ec..c2f7d20f6346 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2504,6 +2504,7 @@ static void clean_spt_oos(struct intel_gvt *gvt)
 	list_for_each_safe(pos, n, &gtt->oos_page_free_list_head) {
 		oos_page = container_of(pos, struct intel_vgpu_oos_page, list);
 		list_del(&oos_page->list);
+		free_page((unsigned long)oos_page->mem);
 		kfree(oos_page);
 	}
 }
@@ -2524,6 +2525,12 @@ static int setup_spt_oos(struct intel_gvt *gvt)
 			ret = -ENOMEM;
 			goto fail;
 		}
+		oos_page->mem = (void *)__get_free_pages(GFP_KERNEL, 0);
+		if (!oos_page->mem) {
+			ret = -ENOMEM;
+			kfree(oos_page);
+			goto fail;
+		}
 
 		INIT_LIST_HEAD(&oos_page->list);
 		INIT_LIST_HEAD(&oos_page->vm_list);
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index edb610dc5d86..32c573aea494 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -222,7 +222,7 @@ struct intel_vgpu_oos_page {
 	struct list_head list;
 	struct list_head vm_list;
 	int id;
-	unsigned char mem[I915_GTT_PAGE_SIZE];
+	void *mem;
 };
 
 #define GTT_ENTRY_NUM_IN_ONE_PAGE 512
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 8bce09de4b82..f5a328b5290a 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -94,7 +94,6 @@ struct intel_vgpu_fence {
 
 struct intel_vgpu_mmio {
 	void *vreg;
-	void *sreg;
 };
 
 #define INTEL_GVT_MAX_BAR_NUM 4
@@ -111,11 +110,9 @@ struct intel_vgpu_cfg_space {
 
 #define vgpu_cfg_space(vgpu) ((vgpu)->cfg_space.virtual_cfg_space)
 
-#define INTEL_GVT_MAX_PIPE 4
-
 struct intel_vgpu_irq {
 	bool irq_warn_once[INTEL_GVT_EVENT_MAX];
-	DECLARE_BITMAP(flip_done_event[INTEL_GVT_MAX_PIPE],
+	DECLARE_BITMAP(flip_done_event[I915_MAX_PIPES],
 		       INTEL_GVT_EVENT_MAX);
 };
 
@@ -144,9 +141,9 @@ enum {
 
 struct intel_vgpu_submission_ops {
 	const char *name;
-	int (*init)(struct intel_vgpu *vgpu, unsigned long engine_mask);
-	void (*clean)(struct intel_vgpu *vgpu, unsigned long engine_mask);
-	void (*reset)(struct intel_vgpu *vgpu, unsigned long engine_mask);
+	int (*init)(struct intel_vgpu *vgpu, intel_engine_mask_t engine_mask);
+	void (*clean)(struct intel_vgpu *vgpu, intel_engine_mask_t engine_mask);
+	void (*reset)(struct intel_vgpu *vgpu, intel_engine_mask_t engine_mask);
 };
 
 struct intel_vgpu_submission {
@@ -449,10 +446,6 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
 	(*(u64 *)(vgpu->mmio.vreg + i915_mmio_reg_offset(reg)))
 #define vgpu_vreg64(vgpu, offset) \
 	(*(u64 *)(vgpu->mmio.vreg + (offset)))
-#define vgpu_sreg_t(vgpu, reg) \
-	(*(u32 *)(vgpu->mmio.sreg + i915_mmio_reg_offset(reg)))
-#define vgpu_sreg(vgpu, offset) \
-	(*(u32 *)(vgpu->mmio.sreg + (offset)))
 
 #define for_each_active_vgpu(gvt, vgpu, id) \
 	idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \
@@ -488,7 +481,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_release_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
-				 unsigned int engine_mask);
+				 intel_engine_mask_t engine_mask);
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index dbc749617922..18f01eeb2510 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -311,7 +311,7 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 			    void *p_data, unsigned int bytes)
 {
-	unsigned int engine_mask = 0;
+	intel_engine_mask_t engine_mask = 0;
 	u32 data;
 
 	write_vreg(vgpu, offset, p_data, bytes);
@@ -750,18 +750,19 @@ static int pri_surf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-	unsigned int index = DSPSURF_TO_PIPE(offset);
-	i915_reg_t surflive_reg = DSPSURFLIVE(index);
-	int flip_event[] = {
-		[PIPE_A] = PRIMARY_A_FLIP_DONE,
-		[PIPE_B] = PRIMARY_B_FLIP_DONE,
-		[PIPE_C] = PRIMARY_C_FLIP_DONE,
-	};
+	u32 pipe = DSPSURF_TO_PIPE(offset);
+	int event = SKL_FLIP_EVENT(pipe, PLANE_PRIMARY);
 
 	write_vreg(vgpu, offset, p_data, bytes);
-	vgpu_vreg_t(vgpu, surflive_reg) = vgpu_vreg(vgpu, offset);
+	vgpu_vreg_t(vgpu, DSPSURFLIVE(pipe)) = vgpu_vreg(vgpu, offset);
+
+	vgpu_vreg_t(vgpu, PIPE_FLIPCOUNT_G4X(pipe))++;
+
+	if (vgpu_vreg_t(vgpu, DSPCNTR(pipe)) & PLANE_CTL_ASYNC_FLIP)
+		intel_vgpu_trigger_virtual_event(vgpu, event);
+	else
+		set_bit(event, vgpu->irq.flip_done_event[pipe]);
 
-	set_bit(flip_event[index], vgpu->irq.flip_done_event[index]);
 	return 0;
 }
 
@@ -771,18 +772,42 @@ static int pri_surf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int spr_surf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
-	unsigned int index = SPRSURF_TO_PIPE(offset);
-	i915_reg_t surflive_reg = SPRSURFLIVE(index);
-	int flip_event[] = {
-		[PIPE_A] = SPRITE_A_FLIP_DONE,
-		[PIPE_B] = SPRITE_B_FLIP_DONE,
-		[PIPE_C] = SPRITE_C_FLIP_DONE,
-	};
+	u32 pipe = SPRSURF_TO_PIPE(offset);
+	int event = SKL_FLIP_EVENT(pipe, PLANE_SPRITE0);
+
+	write_vreg(vgpu, offset, p_data, bytes);
+	vgpu_vreg_t(vgpu, SPRSURFLIVE(pipe)) = vgpu_vreg(vgpu, offset);
+
+	if (vgpu_vreg_t(vgpu, SPRCTL(pipe)) & PLANE_CTL_ASYNC_FLIP)
+		intel_vgpu_trigger_virtual_event(vgpu, event);
+	else
+		set_bit(event, vgpu->irq.flip_done_event[pipe]);
+
+	return 0;
+}
+
+static int reg50080_mmio_write(struct intel_vgpu *vgpu,
+			       unsigned int offset, void *p_data,
+			       unsigned int bytes)
+{
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+	enum pipe pipe = REG_50080_TO_PIPE(offset);
+	enum plane_id plane = REG_50080_TO_PLANE(offset);
+	int event = SKL_FLIP_EVENT(pipe, plane);
 
 	write_vreg(vgpu, offset, p_data, bytes);
-	vgpu_vreg_t(vgpu, surflive_reg) = vgpu_vreg(vgpu, offset);
+	if (plane == PLANE_PRIMARY) {
+		vgpu_vreg_t(vgpu, DSPSURFLIVE(pipe)) = vgpu_vreg(vgpu, offset);
+		vgpu_vreg_t(vgpu, PIPE_FLIPCOUNT_G4X(pipe))++;
+	} else {
+		vgpu_vreg_t(vgpu, SPRSURFLIVE(pipe)) = vgpu_vreg(vgpu, offset);
+	}
+
+	if ((vgpu_vreg(vgpu, offset) & REG50080_FLIP_TYPE_MASK) == REG50080_FLIP_TYPE_ASYNC)
+		intel_vgpu_trigger_virtual_event(vgpu, event);
+	else
+		set_bit(event, vgpu->irq.flip_done_event[pipe]);
 
-	set_bit(flip_event[index], vgpu->irq.flip_done_event[index]);
 	return 0;
 }
 
@@ -1969,6 +1994,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(DSPSURF(PIPE_A), D_ALL, NULL, pri_surf_mmio_write);
 	MMIO_D(DSPOFFSET(PIPE_A), D_ALL);
 	MMIO_D(DSPSURFLIVE(PIPE_A), D_ALL);
+	MMIO_DH(REG_50080(PIPE_A, PLANE_PRIMARY), D_ALL, NULL,
+		reg50080_mmio_write);
 
 	MMIO_D(DSPCNTR(PIPE_B), D_ALL);
 	MMIO_D(DSPADDR(PIPE_B), D_ALL);
@@ -1978,6 +2005,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(DSPSURF(PIPE_B), D_ALL, NULL, pri_surf_mmio_write);
 	MMIO_D(DSPOFFSET(PIPE_B), D_ALL);
 	MMIO_D(DSPSURFLIVE(PIPE_B), D_ALL);
+	MMIO_DH(REG_50080(PIPE_B, PLANE_PRIMARY), D_ALL, NULL,
+		reg50080_mmio_write);
 
 	MMIO_D(DSPCNTR(PIPE_C), D_ALL);
 	MMIO_D(DSPADDR(PIPE_C), D_ALL);
@@ -1987,6 +2016,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(DSPSURF(PIPE_C), D_ALL, NULL, pri_surf_mmio_write);
 	MMIO_D(DSPOFFSET(PIPE_C), D_ALL);
 	MMIO_D(DSPSURFLIVE(PIPE_C), D_ALL);
+	MMIO_DH(REG_50080(PIPE_C, PLANE_PRIMARY), D_ALL, NULL,
+		reg50080_mmio_write);
 
 	MMIO_D(SPRCTL(PIPE_A), D_ALL);
 	MMIO_D(SPRLINOFF(PIPE_A), D_ALL);
@@ -2000,6 +2031,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(SPROFFSET(PIPE_A), D_ALL);
 	MMIO_D(SPRSCALE(PIPE_A), D_ALL);
 	MMIO_D(SPRSURFLIVE(PIPE_A), D_ALL);
+	MMIO_DH(REG_50080(PIPE_A, PLANE_SPRITE0), D_ALL, NULL,
+		reg50080_mmio_write);
 
 	MMIO_D(SPRCTL(PIPE_B), D_ALL);
 	MMIO_D(SPRLINOFF(PIPE_B), D_ALL);
@@ -2013,6 +2046,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(SPROFFSET(PIPE_B), D_ALL);
 	MMIO_D(SPRSCALE(PIPE_B), D_ALL);
 	MMIO_D(SPRSURFLIVE(PIPE_B), D_ALL);
+	MMIO_DH(REG_50080(PIPE_B, PLANE_SPRITE0), D_ALL, NULL,
+		reg50080_mmio_write);
 
 	MMIO_D(SPRCTL(PIPE_C), D_ALL);
 	MMIO_D(SPRLINOFF(PIPE_C), D_ALL);
@@ -2026,6 +2061,8 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(SPROFFSET(PIPE_C), D_ALL);
 	MMIO_D(SPRSCALE(PIPE_C), D_ALL);
 	MMIO_D(SPRSURFLIVE(PIPE_C), D_ALL);
+	MMIO_DH(REG_50080(PIPE_C, PLANE_SPRITE0), D_ALL, NULL,
+		reg50080_mmio_write);
 
 	MMIO_D(HTOTAL(TRANSCODER_A), D_ALL);
 	MMIO_D(HBLANK(TRANSCODER_A), D_ALL);
@@ -2827,26 +2864,26 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_DH(DBUF_CTL, D_SKL_PLUS, NULL, gen9_dbuf_ctl_mmio_write);
 
-	MMIO_D(_MMIO(0xa210), D_SKL_PLUS);
+	MMIO_D(GEN9_PG_ENABLE, D_SKL_PLUS);
 	MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
 	MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
 	MMIO_DFH(GEN9_GAMT_ECO_REG_RW_IA, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DH(_MMIO(0x4ddc), D_SKL_PLUS, NULL, NULL);
-	MMIO_DH(_MMIO(0x42080), D_SKL_PLUS, NULL, NULL);
-	MMIO_D(_MMIO(0x45504), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x45520), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x46000), D_SKL_PLUS);
-	MMIO_DH(_MMIO(0x46010), D_SKL_PLUS, NULL, skl_lcpll_write);
-	MMIO_DH(_MMIO(0x46014), D_SKL_PLUS, NULL, skl_lcpll_write);
-	MMIO_D(_MMIO(0x6C040), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6C048), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6C050), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6C044), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6C04C), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6C054), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6c058), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6c05c), D_SKL_PLUS);
-	MMIO_DH(_MMIO(0x6c060), D_SKL_PLUS, dpll_status_read, NULL);
+	MMIO_DH(MMCD_MISC_CTRL, D_SKL_PLUS, NULL, NULL);
+	MMIO_DH(CHICKEN_PAR1_1, D_SKL_PLUS, NULL, NULL);
+	MMIO_D(DC_STATE_EN, D_SKL_PLUS);
+	MMIO_D(DC_STATE_DEBUG, D_SKL_PLUS);
+	MMIO_D(CDCLK_CTL, D_SKL_PLUS);
+	MMIO_DH(LCPLL1_CTL, D_SKL_PLUS, NULL, skl_lcpll_write);
+	MMIO_DH(LCPLL2_CTL, D_SKL_PLUS, NULL, skl_lcpll_write);
+	MMIO_D(_MMIO(_DPLL1_CFGCR1), D_SKL_PLUS);
+	MMIO_D(_MMIO(_DPLL2_CFGCR1), D_SKL_PLUS);
+	MMIO_D(_MMIO(_DPLL3_CFGCR1), D_SKL_PLUS);
+	MMIO_D(_MMIO(_DPLL1_CFGCR2), D_SKL_PLUS);
+	MMIO_D(_MMIO(_DPLL2_CFGCR2), D_SKL_PLUS);
+	MMIO_D(_MMIO(_DPLL3_CFGCR2), D_SKL_PLUS);
+	MMIO_D(DPLL_CTRL1, D_SKL_PLUS);
+	MMIO_D(DPLL_CTRL2, D_SKL_PLUS);
+	MMIO_DH(DPLL_STATUS, D_SKL_PLUS, dpll_status_read, NULL);
 
 	MMIO_DH(SKL_PS_WIN_POS(PIPE_A, 0), D_SKL_PLUS, NULL, pf_write);
 	MMIO_DH(SKL_PS_WIN_POS(PIPE_A, 1), D_SKL_PLUS, NULL, pf_write);
@@ -2965,40 +3002,41 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(_MMIO(_REG_701C4(PIPE_C, 3)), D_SKL_PLUS, NULL, NULL);
 	MMIO_DH(_MMIO(_REG_701C4(PIPE_C, 4)), D_SKL_PLUS, NULL, NULL);
 
-	MMIO_D(_MMIO(0x70380), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x71380), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_CTL_3_A), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_CTL_3_B), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x72380), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x7239c), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x7039c), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_SURF_3_A), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x8f074), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x8f004), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x8f034), D_SKL_PLUS);
+	MMIO_D(CSR_SSP_BASE, D_SKL_PLUS);
+	MMIO_D(CSR_HTP_SKL, D_SKL_PLUS);
+	MMIO_D(CSR_LAST_WRITE, D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0xb11c), D_SKL_PLUS);
+	MMIO_D(BDW_SCRATCH1, D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x51000), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x6c00c), D_SKL_PLUS);
+	MMIO_D(SKL_DFSM, D_SKL_PLUS);
+	MMIO_D(DISPIO_CR_TX_BMU_CR0, D_SKL_PLUS);
 
-	MMIO_F(_MMIO(0xc800), 0x7f8, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
+	MMIO_F(GEN9_GFX_MOCS(0), 0x7f8, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
 		NULL, NULL);
-	MMIO_F(_MMIO(0xb020), 0x80, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
+	MMIO_F(GEN7_L3CNTLREG2, 0x80, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
 		NULL, NULL);
 
 	MMIO_D(RPM_CONFIG0, D_SKL_PLUS);
 	MMIO_D(_MMIO(0xd08), D_SKL_PLUS);
 	MMIO_D(RC6_LOCATION, D_SKL_PLUS);
-	MMIO_DFH(_MMIO(0x20e0), D_SKL_PLUS, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(_MMIO(0x20ec), D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+	MMIO_DFH(GEN7_FF_SLICE_CS_CHICKEN1, D_SKL_PLUS, F_MODE_MASK,
+		NULL, NULL);
+	MMIO_DFH(GEN9_CS_DEBUG_MODE1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		NULL, NULL);
 
 	/* TRTT */
-	MMIO_DFH(_MMIO(0x4de0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4de4), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4de8), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4dec), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4df0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4df4), D_SKL_PLUS, F_CMD_ACCESS,
+	MMIO_DFH(TRVATTL3PTRDW(0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(TRVATTL3PTRDW(1), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(TRVATTL3PTRDW(2), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(TRVATTL3PTRDW(3), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(TRVADR, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(TRTTE, D_SKL_PLUS, F_CMD_ACCESS,
 		NULL, gen9_trtte_write);
 	MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write);
 
@@ -3011,7 +3049,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(DMA_CTRL, D_SKL_PLUS, NULL, dma_ctrl_write);
 
 	MMIO_D(_MMIO(0x65900), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x1082c0), D_SKL_PLUS);
+	MMIO_D(GEN6_STOLEN_RESERVED, D_SKL_PLUS);
 	MMIO_D(_MMIO(0x4068), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x67054), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x6e560), D_SKL_PLUS);
@@ -3042,8 +3080,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		 NULL, NULL);
 
-	MMIO_D(_MMIO(0x4ab8), D_KBL | D_CFL);
-	MMIO_D(_MMIO(0x2248), D_SKL_PLUS);
+	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL);
 
 	return 0;
 }
@@ -3265,7 +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, _MMIO(MCHBAR_MIRROR_BASE_SNB), 0x40000, NULL, NULL},
+	{D_ALL, MCHBAR_MIRROR_REG_BASE, 0x4000, 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},
@@ -3489,12 +3527,11 @@ int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 		return mmio_info->read(vgpu, offset, pdata, bytes);
 	else {
 		u64 ro_mask = mmio_info->ro_mask;
-		u32 old_vreg = 0, old_sreg = 0;
+		u32 old_vreg = 0;
 		u64 data = 0;
 
 		if (intel_gvt_mmio_has_mode_mask(gvt, mmio_info->offset)) {
 			old_vreg = vgpu_vreg(vgpu, offset);
-			old_sreg = vgpu_sreg(vgpu, offset);
 		}
 
 		if (likely(!ro_mask))
@@ -3516,8 +3553,6 @@ int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 
 			vgpu_vreg(vgpu, offset) = (old_vreg & ~mask)
 					| (vgpu_vreg(vgpu, offset) & mask);
-			vgpu_sreg(vgpu, offset) = (old_sreg & ~mask)
-					| (vgpu_sreg(vgpu, offset) & mask);
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index ed4df2f6d60b..a55178884d67 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -239,7 +239,6 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu, bool dmlr)
 
 	if (dmlr) {
 		memcpy(vgpu->mmio.vreg, mmio, info->mmio_size);
-		memcpy(vgpu->mmio.sreg, mmio, info->mmio_size);
 
 		vgpu_vreg_t(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
 
@@ -280,7 +279,6 @@ void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu, bool dmlr)
 		 * touched
 		 */
 		memcpy(vgpu->mmio.vreg, mmio, GVT_GEN8_MMIO_RESET_OFFSET);
-		memcpy(vgpu->mmio.sreg, mmio, GVT_GEN8_MMIO_RESET_OFFSET);
 	}
 
 }
@@ -296,12 +294,10 @@ int intel_vgpu_init_mmio(struct intel_vgpu *vgpu)
 {
 	const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
 
-	vgpu->mmio.vreg = vzalloc(array_size(info->mmio_size, 2));
+	vgpu->mmio.vreg = vzalloc(info->mmio_size);
 	if (!vgpu->mmio.vreg)
 		return -ENOMEM;
 
-	vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
-
 	intel_vgpu_reset_mmio(vgpu, true);
 
 	return 0;
@@ -315,5 +311,5 @@ int intel_vgpu_init_mmio(struct intel_vgpu *vgpu)
 void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu)
 {
 	vfree(vgpu->mmio.vreg);
-	vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
+	vgpu->mmio.vreg = NULL;
 }
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 76630fbe51b6..e7e14c842be4 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -68,7 +68,7 @@ static struct engine_mmio gen8_engine_mmio_list[] __cacheline_aligned = {
 	{BCS0, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
 	{BCS0, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */
 	{BCS0, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */
-	{BCS0, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */
+	{BCS0, RING_EXCC(BLT_RING_BASE), 0xffff, false}, /* 0x22028 */
 	{RCS0, INVALID_MMIO_REG, 0, false } /* Terminated */
 };
 
@@ -119,7 +119,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 	{BCS0, RING_MI_MODE(BLT_RING_BASE), 0xffff, false}, /* 0x2209c */
 	{BCS0, RING_INSTPM(BLT_RING_BASE), 0xffff, false}, /* 0x220c0 */
 	{BCS0, RING_HWSTAM(BLT_RING_BASE), 0x0, false}, /* 0x22098 */
-	{BCS0, RING_EXCC(BLT_RING_BASE), 0x0, false}, /* 0x22028 */
+	{BCS0, RING_EXCC(BLT_RING_BASE), 0xffff, false}, /* 0x22028 */
 
 	{VCS1, RING_EXCC(GEN8_BSD2_RING_BASE), 0xffff, false}, /* 0x1c028 */
 
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 428d252344f1..3de5b643b266 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -60,6 +60,37 @@
 #define _REG_701C0(pipe, plane) (0x701c0 + pipe * 0x1000 + (plane - 1) * 0x100)
 #define _REG_701C4(pipe, plane) (0x701c4 + pipe * 0x1000 + (plane - 1) * 0x100)
 
+#define SKL_FLIP_EVENT(pipe, plane) (PRIMARY_A_FLIP_DONE + (plane) * 3 + (pipe))
+
+#define PLANE_CTL_ASYNC_FLIP		(1 << 9)
+#define REG50080_FLIP_TYPE_MASK	0x3
+#define REG50080_FLIP_TYPE_ASYNC	0x1
+
+#define REG_50080(_pipe, _plane) ({ \
+	typeof(_pipe) (p) = (_pipe); \
+	typeof(_plane) (q) = (_plane); \
+	(((p) == PIPE_A) ? (((q) == PLANE_PRIMARY) ? (_MMIO(0x50080)) : \
+		(_MMIO(0x50090))) : \
+	(((p) == PIPE_B) ? (((q) == PLANE_PRIMARY) ? (_MMIO(0x50088)) : \
+		(_MMIO(0x50098))) : \
+	(((p) == PIPE_C) ? (((q) == PLANE_PRIMARY) ? (_MMIO(0x5008C)) : \
+		(_MMIO(0x5009C))) : \
+		(_MMIO(0x50080))))); })
+
+#define REG_50080_TO_PIPE(_reg) ({ \
+	typeof(_reg) (reg) = (_reg); \
+	(((reg) == 0x50080 || (reg) == 0x50090) ? (PIPE_A) : \
+	(((reg) == 0x50088 || (reg) == 0x50098) ? (PIPE_B) : \
+	(((reg) == 0x5008C || (reg) == 0x5009C) ? (PIPE_C) : \
+	(INVALID_PIPE)))); })
+
+#define REG_50080_TO_PLANE(_reg) ({ \
+	typeof(_reg) (reg) = (_reg); \
+	(((reg) == 0x50080 || (reg) == 0x50088 || (reg) == 0x5008C) ? \
+		(PLANE_PRIMARY) : \
+	(((reg) == 0x50090 || (reg) == 0x50098 || (reg) == 0x5009C) ? \
+		(PLANE_SPRITE0) : (I915_MAX_PLANES))); })
+
 #define GFX_MODE_BIT_SET_IN_MASK(val, bit) \
 		((((bit) & 0xffff0000) == 0) && !!((val) & (((bit) << 16))))
 
@@ -95,4 +126,7 @@
 #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 2f91281ac000..8998fa5ab198 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -850,13 +850,13 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 }
 
 void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu,
-				unsigned long engine_mask)
+				intel_engine_mask_t engine_mask)
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_engine_cs *engine;
 	struct intel_vgpu_workload *pos, *n;
-	unsigned int tmp;
+	intel_engine_mask_t tmp;
 
 	/* free the unsubmited workloads in the queues. */
 	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
@@ -1149,7 +1149,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu)
  *
  */
 void intel_vgpu_reset_submission(struct intel_vgpu *vgpu,
-		unsigned long engine_mask)
+				 intel_engine_mask_t engine_mask)
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
 
@@ -1239,7 +1239,7 @@ out_shadow_ctx:
  *
  */
 int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
-				     unsigned long engine_mask,
+				     intel_engine_mask_t engine_mask,
 				     unsigned int interface)
 {
 	struct intel_vgpu_submission *s = &vgpu->submission;
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 0635b2c4bed7..90c6756f5453 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -142,12 +142,12 @@ void intel_gvt_wait_vgpu_idle(struct intel_vgpu *vgpu);
 int intel_vgpu_setup_submission(struct intel_vgpu *vgpu);
 
 void intel_vgpu_reset_submission(struct intel_vgpu *vgpu,
-				 unsigned long engine_mask);
+				 intel_engine_mask_t engine_mask);
 
 void intel_vgpu_clean_submission(struct intel_vgpu *vgpu);
 
 int intel_vgpu_select_submission_ops(struct intel_vgpu *vgpu,
-				     unsigned long engine_mask,
+				     intel_engine_mask_t engine_mask,
 				     unsigned int interface);
 
 extern const struct intel_vgpu_submission_ops
@@ -160,6 +160,6 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 void intel_vgpu_destroy_workload(struct intel_vgpu_workload *workload);
 
 void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu,
-				unsigned long engine_mask);
+				intel_engine_mask_t engine_mask);
 
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 314e40121e47..44ce3c2b9ac1 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -526,11 +526,11 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
  * GPU engines. For FLR, engine_mask is ignored.
  */
 void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
-				 unsigned int engine_mask)
+				 intel_engine_mask_t engine_mask)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
-	unsigned int resetting_eng = dmlr ? ALL_ENGINES : engine_mask;
+	intel_engine_mask_t resetting_eng = dmlr ? ALL_ENGINES : engine_mask;
 
 	gvt_dbg_core("------------------------------------------\n");
 	gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n",