Merge tag 'drm-intel-next-2019-01-24' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

- Track all runtime-PM wakerefs and other rpm improvements (Chris)
- Fix ILK-IVB primary plane enable delays (Juha-Pekka)
- Differentiate between gtt->mutex and ppgtt->mutex (Chris)
- Prevent concurrent GGTT update and use on Braswell (Chris)
- Fix CNL macros for DDI vswing (Aditya)
- Fix static code analysis warning (RK)
- Only dump GPU state on set-wedged if interesting (Chris)
- Port F detection improvements (Imre)
- userptr mutex lock fixes (Chris)
- Fix on MST allocation by propagating error value at compute_config (Lyude)
- Serialise concurrent calls to set_wedge (Chris)
- Unify reset functionality into i915_reset.c (Chris)
- Switch to kernel fixed size types (Jani)
- Limit the for_each_set_bit to the valid range (Chris)
- Fix wakeref cooie handling (Tvrtko)
- IRQs handling improvements (Chris)
- Selftests improvements (Chris)
- Remove superfluous PANEL_POWER_OFF macro (Jani)
- Global seqno fix (Chris)
- DSI fixes (Hans)
- Refactor out intel_context_init() (Chris)
- Show all active engines on hangcheck (Chris)
- PSR2 fixes and improvements (Jose)
- Do a posting read after irq install on Ice Lake (Daniele)
- Add few more device IDs for Ice Lake (Rodrigo)
- Mark up priority boost on preemption (Chris)
- Add color management LUT validation helper (Matt)
- Split out intel_crt_present to platform specific setup (Jani)
- LVDS and TV clean up and improvements (Jani)
- Simplify CRT VBT check for per-VLV/DDI (Jani)
- De-inline intel_context_init() (Chris)
- Backlight fixes (Maarten)
- Enable fastset for non-boot modesets (Maarten)
- Make HW readout mark CRTC scaler as in use (Maarten)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190128181000.GA5284@intel.com

drivers/gpu/drm/drm_color_mgmt.c

@@ -462,3 +462,47 @@ int drm_plane_create_color_properties(struct drm_plane *plane,
 	return 0;
 }
 EXPORT_SYMBOL(drm_plane_create_color_properties);
+
+/**
+ * drm_color_lut_check - check validity of lookup table
+ * @lut: property blob containing LUT to check
+ * @tests: bitmask of tests to run
+ *
+ * Helper to check whether a userspace-provided lookup table is valid and
+ * satisfies hardware requirements.  Drivers pass a bitmask indicating which of
+ * the tests in &drm_color_lut_tests should be performed.
+ *
+ * Returns 0 on success, -EINVAL on failure.
+ */
+int drm_color_lut_check(struct drm_property_blob *lut,
+			uint32_t tests)
+{
+	struct drm_color_lut *entry;
+	int i;
+
+	if (!lut || !tests)
+		return 0;
+
+	entry = lut->data;
+	for (i = 0; i < drm_color_lut_size(lut); i++) {
+		if (tests & DRM_COLOR_LUT_EQUAL_CHANNELS) {
+			if (entry[i].red != entry[i].blue ||
+			    entry[i].red != entry[i].green) {
+				DRM_DEBUG_KMS("All LUT entries must have equal r/g/b\n");
+				return -EINVAL;
+			}
+		}
+
+		if (i > 0 && tests & DRM_COLOR_LUT_NON_DECREASING) {
+			if (entry[i].red < entry[i - 1].red ||
+			    entry[i].green < entry[i - 1].green ||
+			    entry[i].blue < entry[i - 1].blue) {
+				DRM_DEBUG_KMS("LUT entries must never decrease.\n");
+				return -EINVAL;
+			}
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_color_lut_check);

drivers/gpu/drm/i915/Kconfig.debug

@@ -21,11 +21,11 @@ config DRM_I915_DEBUG
         select DEBUG_FS
         select PREEMPT_COUNT
         select I2C_CHARDEV
+        select STACKDEPOT
         select DRM_DP_AUX_CHARDEV
         select X86_MSR # used by igt/pm_rpm
         select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
         select DRM_DEBUG_MM if DRM=y
-        select STACKDEPOT if DRM=y # for DRM_DEBUG_MM
 	select DRM_DEBUG_SELFTEST
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
@@ -173,6 +173,7 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	bool "Enable extra state checking for runtime PM"
 	depends on DRM_I915
 	default n
+	select STACKDEPOT
 	help
 	  Choose this option to turn on extra state checking for the
 	  runtime PM functionality. This may introduce overhead during

drivers/gpu/drm/i915/Makefile

@@ -40,9 +40,10 @@ i915-y := i915_drv.o \
 	  i915_mm.o \
 	  i915_params.o \
 	  i915_pci.o \
+	  i915_reset.o \
 	  i915_suspend.o \
-	  i915_syncmap.o \
 	  i915_sw_fence.o \
+	  i915_syncmap.o \
 	  i915_sysfs.o \
 	  intel_csr.o \
 	  intel_device_info.o \
@@ -166,6 +167,7 @@ i915-$(CONFIG_DRM_I915_SELFTEST) += \
 	selftests/i915_random.o \
 	selftests/i915_selftest.o \
 	selftests/igt_flush_test.o \
+	selftests/igt_live_test.o \
 	selftests/igt_reset.o \
 	selftests/igt_spinner.o
 
@@ -198,3 +200,4 @@ endif
 i915-y += intel_lpe_audio.o
 
 obj-$(CONFIG_DRM_I915) += i915.o
+obj-$(CONFIG_DRM_I915_GVT_KVMGT) += gvt/kvmgt.o

drivers/gpu/drm/i915/gvt/Makefile

@@ -7,4 +7,3 @@ GVT_SOURCE := gvt.o aperture_gm.o handlers.o vgpu.o trace_points.o firmware.o \
 
 ccflags-y				+= -I$(src) -I$(src)/$(GVT_DIR)
 i915-y					+= $(addprefix $(GVT_DIR)/, $(GVT_SOURCE))
-obj-$(CONFIG_DRM_I915_GVT_KVMGT)	+= $(GVT_DIR)/kvmgt.o

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

@@ -180,7 +180,7 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu)
 	}
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
@@ -206,7 +206,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 	_clear_vgpu_fence(vgpu);
 
 	mutex_unlock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 	return 0;
 out_free_fence:
 	gvt_vgpu_err("Failed to alloc fences\n");
@@ -219,7 +219,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 		vgpu->fence.regs[i] = NULL;
 	}
 	mutex_unlock(&dev_priv->drm.struct_mutex);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 	return -ENOSPC;
 }
 
@@ -317,7 +317,7 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu)
 
 	intel_runtime_pm_get(dev_priv);
 	_clear_vgpu_fence(vgpu);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 /**

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

@@ -55,10 +55,10 @@ struct sub_op_bits {
 	int low;
 };
 struct decode_info {
-	char *name;
+	const char *name;
 	int op_len;
 	int nr_sub_op;
-	struct sub_op_bits *sub_op;
+	const struct sub_op_bits *sub_op;
 };
 
 #define   MAX_CMD_BUDGET			0x7fffffff
@@ -375,7 +375,7 @@ typedef int (*parser_cmd_handler)(struct parser_exec_state *s);
 #define ADDR_FIX_5(x1, x2, x3, x4, x5)  (ADDR_FIX_1(x1) | ADDR_FIX_4(x2, x3, x4, x5))
 
 struct cmd_info {
-	char *name;
+	const char *name;
 	u32 opcode;
 
 #define F_LEN_MASK	(1U<<0)
@@ -399,10 +399,10 @@ struct cmd_info {
 #define R_VECS	(1 << VECS)
 #define R_ALL (R_RCS | R_VCS | R_BCS | R_VECS)
 	/* rings that support this cmd: BLT/RCS/VCS/VECS */
-	uint16_t rings;
+	u16 rings;
 
 	/* devices that support this cmd: SNB/IVB/HSW/... */
-	uint16_t devices;
+	u16 devices;
 
 	/* which DWords are address that need fix up.
 	 * bit 0 means a 32-bit non address operand in command
@@ -412,20 +412,20 @@ struct cmd_info {
 	 * No matter the address length, each address only takes
 	 * one bit in the bitmap.
 	 */
-	uint16_t addr_bitmap;
+	u16 addr_bitmap;
 
 	/* flag == F_LEN_CONST : command length
 	 * flag == F_LEN_VAR : length bias bits
 	 * Note: length is in DWord
 	 */
-	uint8_t	len;
+	u8 len;
 
 	parser_cmd_handler handler;
 };
 
 struct cmd_entry {
 	struct hlist_node hlist;
-	struct cmd_info *info;
+	const struct cmd_info *info;
 };
 
 enum {
@@ -474,7 +474,7 @@ struct parser_exec_state {
 	int saved_buf_addr_type;
 	bool is_ctx_wa;
 
-	struct cmd_info *info;
+	const struct cmd_info *info;
 
 	struct intel_vgpu_workload *workload;
 };
@@ -485,12 +485,12 @@ struct parser_exec_state {
 static unsigned long bypass_scan_mask = 0;
 
 /* ring ALL, type = 0 */
-static struct sub_op_bits sub_op_mi[] = {
+static const struct sub_op_bits sub_op_mi[] = {
 	{31, 29},
 	{28, 23},
 };
 
-static struct decode_info decode_info_mi = {
+static const struct decode_info decode_info_mi = {
 	"MI",
 	OP_LEN_MI,
 	ARRAY_SIZE(sub_op_mi),
@@ -498,12 +498,12 @@ static struct decode_info decode_info_mi = {
 };
 
 /* ring RCS, command type 2 */
-static struct sub_op_bits sub_op_2d[] = {
+static const struct sub_op_bits sub_op_2d[] = {
 	{31, 29},
 	{28, 22},
 };
 
-static struct decode_info decode_info_2d = {
+static const struct decode_info decode_info_2d = {
 	"2D",
 	OP_LEN_2D,
 	ARRAY_SIZE(sub_op_2d),
@@ -511,14 +511,14 @@ static struct decode_info decode_info_2d = {
 };
 
 /* ring RCS, command type 3 */
-static struct sub_op_bits sub_op_3d_media[] = {
+static const struct sub_op_bits sub_op_3d_media[] = {
 	{31, 29},
 	{28, 27},
 	{26, 24},
 	{23, 16},
 };
 
-static struct decode_info decode_info_3d_media = {
+static const struct decode_info decode_info_3d_media = {
 	"3D_Media",
 	OP_LEN_3D_MEDIA,
 	ARRAY_SIZE(sub_op_3d_media),
@@ -526,7 +526,7 @@ static struct decode_info decode_info_3d_media = {
 };
 
 /* ring VCS, command type 3 */
-static struct sub_op_bits sub_op_mfx_vc[] = {
+static const struct sub_op_bits sub_op_mfx_vc[] = {
 	{31, 29},
 	{28, 27},
 	{26, 24},
@@ -534,7 +534,7 @@ static struct sub_op_bits sub_op_mfx_vc[] = {
 	{20, 16},
 };
 
-static struct decode_info decode_info_mfx_vc = {
+static const struct decode_info decode_info_mfx_vc = {
 	"MFX_VC",
 	OP_LEN_MFX_VC,
 	ARRAY_SIZE(sub_op_mfx_vc),
@@ -542,7 +542,7 @@ static struct decode_info decode_info_mfx_vc = {
 };
 
 /* ring VECS, command type 3 */
-static struct sub_op_bits sub_op_vebox[] = {
+static const struct sub_op_bits sub_op_vebox[] = {
 	{31, 29},
 	{28, 27},
 	{26, 24},
@@ -550,14 +550,14 @@ static struct sub_op_bits sub_op_vebox[] = {
 	{20, 16},
 };
 
-static struct decode_info decode_info_vebox = {
+static const struct decode_info decode_info_vebox = {
 	"VEBOX",
 	OP_LEN_VEBOX,
 	ARRAY_SIZE(sub_op_vebox),
 	sub_op_vebox,
 };
 
-static struct decode_info *ring_decode_info[I915_NUM_ENGINES][8] = {
+static const struct decode_info *ring_decode_info[I915_NUM_ENGINES][8] = {
 	[RCS] = {
 		&decode_info_mi,
 		NULL,
@@ -616,7 +616,7 @@ static struct decode_info *ring_decode_info[I915_NUM_ENGINES][8] = {
 
 static inline u32 get_opcode(u32 cmd, int ring_id)
 {
-	struct decode_info *d_info;
+	const struct decode_info *d_info;
 
 	d_info = ring_decode_info[ring_id][CMD_TYPE(cmd)];
 	if (d_info == NULL)
@@ -625,7 +625,7 @@ static inline u32 get_opcode(u32 cmd, int ring_id)
 	return cmd >> (32 - d_info->op_len);
 }
 
-static inline struct cmd_info *find_cmd_entry(struct intel_gvt *gvt,
+static inline const struct cmd_info *find_cmd_entry(struct intel_gvt *gvt,
 		unsigned int opcode, int ring_id)
 {
 	struct cmd_entry *e;
@@ -638,7 +638,7 @@ static inline struct cmd_info *find_cmd_entry(struct intel_gvt *gvt,
 	return NULL;
 }
 
-static inline struct cmd_info *get_cmd_info(struct intel_gvt *gvt,
+static inline const struct cmd_info *get_cmd_info(struct intel_gvt *gvt,
 		u32 cmd, int ring_id)
 {
 	u32 opcode;
@@ -657,7 +657,7 @@ static inline u32 sub_op_val(u32 cmd, u32 hi, u32 low)
 
 static inline void print_opcode(u32 cmd, int ring_id)
 {
-	struct decode_info *d_info;
+	const struct decode_info *d_info;
 	int i;
 
 	d_info = ring_decode_info[ring_id][CMD_TYPE(cmd)];
@@ -776,7 +776,7 @@ static inline int ip_gma_advance(struct parser_exec_state *s,
 	return 0;
 }
 
-static inline int get_cmd_length(struct cmd_info *info, u32 cmd)
+static inline int get_cmd_length(const struct cmd_info *info, u32 cmd)
 {
 	if ((info->flag & F_LEN_MASK) == F_LEN_CONST)
 		return info->len;
@@ -901,7 +901,8 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 	 * It's good enough to support initializing mmio by lri command in
 	 * vgpu inhibit context on KBL.
 	 */
-	if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) &&
+	if ((IS_KABYLAKE(s->vgpu->gvt->dev_priv)
+		|| IS_COFFEELAKE(s->vgpu->gvt->dev_priv)) &&
 			intel_gvt_mmio_is_in_ctx(gvt, offset) &&
 			!strncmp(cmd, "lri", 3)) {
 		intel_gvt_hypervisor_read_gpa(s->vgpu,
@@ -1280,9 +1281,7 @@ static int gen8_check_mi_display_flip(struct parser_exec_state *s,
 	if (!info->async_flip)
 		return 0;
 
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		stride = vgpu_vreg_t(s->vgpu, info->stride_reg) & GENMASK(9, 0);
 		tile = (vgpu_vreg_t(s->vgpu, info->ctrl_reg) &
 				GENMASK(12, 10)) >> 10;
@@ -1310,9 +1309,7 @@ static int gen8_update_plane_mmio_from_mi_display_flip(
 
 	set_mask_bits(&vgpu_vreg_t(vgpu, info->surf_reg), GENMASK(31, 12),
 		      info->surf_val << 12);
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		set_mask_bits(&vgpu_vreg_t(vgpu, info->stride_reg), GENMASK(9, 0),
 			      info->stride_val);
 		set_mask_bits(&vgpu_vreg_t(vgpu, info->ctrl_reg), GENMASK(12, 10),
@@ -1336,9 +1333,7 @@ static int decode_mi_display_flip(struct parser_exec_state *s,
 
 	if (IS_BROADWELL(dev_priv))
 		return gen8_decode_mi_display_flip(s, info);
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 9)
 		return skl_decode_mi_display_flip(s, info);
 
 	return -ENODEV;
@@ -1643,8 +1638,8 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s)
 static int find_bb_size(struct parser_exec_state *s, unsigned long *bb_size)
 {
 	unsigned long gma = 0;
-	struct cmd_info *info;
-	uint32_t cmd_len = 0;
+	const struct cmd_info *info;
+	u32 cmd_len = 0;
 	bool bb_end = false;
 	struct intel_vgpu *vgpu = s->vgpu;
 	u32 cmd;
@@ -1842,7 +1837,7 @@ static int cmd_handler_mi_batch_buffer_start(struct parser_exec_state *s)
 
 static int mi_noop_index;
 
-static struct cmd_info cmd_info[] = {
+static const struct cmd_info cmd_info[] = {
 	{"MI_NOOP", OP_MI_NOOP, F_LEN_CONST, R_ALL, D_ALL, 0, 1, NULL},
 
 	{"MI_SET_PREDICATE", OP_MI_SET_PREDICATE, F_LEN_CONST, R_ALL, D_ALL,
@@ -2521,7 +2516,7 @@ static void add_cmd_entry(struct intel_gvt *gvt, struct cmd_entry *e)
 static int cmd_parser_exec(struct parser_exec_state *s)
 {
 	struct intel_vgpu *vgpu = s->vgpu;
-	struct cmd_info *info;
+	const struct cmd_info *info;
 	u32 cmd;
 	int ret = 0;
 
@@ -2683,7 +2678,7 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 					I915_GTT_PAGE_SIZE)))
 		return -EINVAL;
 
-	ring_tail = wa_ctx->indirect_ctx.size + 3 * sizeof(uint32_t);
+	ring_tail = wa_ctx->indirect_ctx.size + 3 * sizeof(u32);
 	ring_size = round_up(wa_ctx->indirect_ctx.size + CACHELINE_BYTES,
 			PAGE_SIZE);
 	gma_head = wa_ctx->indirect_ctx.guest_gma;
@@ -2850,7 +2845,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 
 static int combine_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
-	uint32_t per_ctx_start[CACHELINE_DWORDS] = {0};
+	u32 per_ctx_start[CACHELINE_DWORDS] = {0};
 	unsigned char *bb_start_sva;
 
 	if (!wa_ctx->per_ctx.valid)
@@ -2895,10 +2890,10 @@ int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	return 0;
 }
 
-static struct cmd_info *find_cmd_entry_any_ring(struct intel_gvt *gvt,
+static const struct cmd_info *find_cmd_entry_any_ring(struct intel_gvt *gvt,
 		unsigned int opcode, unsigned long rings)
 {
-	struct cmd_info *info = NULL;
+	const struct cmd_info *info = NULL;
 	unsigned int ring;
 
 	for_each_set_bit(ring, &rings, I915_NUM_ENGINES) {
@@ -2913,7 +2908,7 @@ static int init_cmd_table(struct intel_gvt *gvt)
 {
 	int i;
 	struct cmd_entry *e;
-	struct cmd_info	*info;
+	const struct cmd_info *info;
 	unsigned int gen_type;
 
 	gen_type = intel_gvt_get_device_type(gvt);

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

@@ -198,7 +198,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			SDE_PORTC_HOTPLUG_CPT |
 			SDE_PORTD_HOTPLUG_CPT);
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv)) {
 		vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTA_HOTPLUG_SPT |
 				SDE_PORTE_HOTPLUG_SPT);
 		vgpu_vreg_t(vgpu, SKL_FUSE_STATUS) |=
@@ -273,7 +274,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 		vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDID_DETECTED;
 	}
 
-	if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) &&
+	if ((IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+	     IS_COFFEELAKE(dev_priv)) &&
 			intel_vgpu_has_monitor_on_port(vgpu, PORT_E)) {
 		vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTE_HOTPLUG_SPT;
 	}
@@ -453,7 +455,8 @@ void intel_vgpu_clean_display(struct intel_vgpu *vgpu)
 {
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv))
 		clean_virtual_dp_monitor(vgpu, PORT_D);
 	else
 		clean_virtual_dp_monitor(vgpu, PORT_B);
@@ -476,7 +479,8 @@ int intel_vgpu_init_display(struct intel_vgpu *vgpu, u64 resolution)
 
 	intel_vgpu_init_i2c_edid(vgpu);
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) ||
+	    IS_COFFEELAKE(dev_priv))
 		return setup_virtual_dp_monitor(vgpu, PORT_D, GVT_DP_D,
 						resolution);
 	else

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

@@ -29,7 +29,6 @@
  */
 
 #include <linux/dma-buf.h>
-#include <drm/drmP.h>
 #include <linux/vfio.h>
 
 #include "i915_drv.h"
@@ -164,9 +163,7 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 
 	obj->read_domains = I915_GEM_DOMAIN_GTT;
 	obj->write_domain = 0;
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		unsigned int tiling_mode = 0;
 		unsigned int stride = 0;
 

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

@@ -77,16 +77,32 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
 	return chr;
 }
 
+static inline int cnp_get_port_from_gmbus0(u32 gmbus0)
+{
+	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
+	int port = -EINVAL;
+
+	if (port_select == GMBUS_PIN_1_BXT)
+		port = PORT_B;
+	else if (port_select == GMBUS_PIN_2_BXT)
+		port = PORT_C;
+	else if (port_select == GMBUS_PIN_3_BXT)
+		port = PORT_D;
+	else if (port_select == GMBUS_PIN_4_CNP)
+		port = PORT_E;
+	return port;
+}
+
 static inline int bxt_get_port_from_gmbus0(u32 gmbus0)
 {
 	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
 	int port = -EINVAL;
 
-	if (port_select == 1)
+	if (port_select == GMBUS_PIN_1_BXT)
 		port = PORT_B;
-	else if (port_select == 2)
+	else if (port_select == GMBUS_PIN_2_BXT)
 		port = PORT_C;
-	else if (port_select == 3)
+	else if (port_select == GMBUS_PIN_3_BXT)
 		port = PORT_D;
 	return port;
 }
@@ -96,13 +112,13 @@ static inline int get_port_from_gmbus0(u32 gmbus0)
 	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
 	int port = -EINVAL;
 
-	if (port_select == 2)
+	if (port_select == GMBUS_PIN_VGADDC)
 		port = PORT_E;
-	else if (port_select == 4)
+	else if (port_select == GMBUS_PIN_DPC)
 		port = PORT_C;
-	else if (port_select == 5)
+	else if (port_select == GMBUS_PIN_DPB)
 		port = PORT_B;
-	else if (port_select == 6)
+	else if (port_select == GMBUS_PIN_DPD)
 		port = PORT_D;
 	return port;
 }
@@ -133,6 +149,8 @@ static int gmbus0_mmio_write(struct intel_vgpu *vgpu,
 
 	if (IS_BROXTON(dev_priv))
 		port = bxt_get_port_from_gmbus0(pin_select);
+	else if (IS_COFFEELAKE(dev_priv))
+		port = cnp_get_port_from_gmbus0(pin_select);
 	else
 		port = get_port_from_gmbus0(pin_select);
 	if (WARN_ON(port < 0))

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

@@ -151,9 +151,7 @@ static u32 intel_vgpu_get_stride(struct intel_vgpu *vgpu, int pipe,
 	u32 stride_reg = vgpu_vreg_t(vgpu, DSPSTRIDE(pipe)) & stride_mask;
 	u32 stride = stride_reg;
 
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		switch (tiled) {
 		case PLANE_CTL_TILED_LINEAR:
 			stride = stride_reg * 64;
@@ -217,9 +215,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	if (!plane->enabled)
 		return -ENODEV;
 
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 9) {
 		plane->tiled = val & PLANE_CTL_TILED_MASK;
 		fmt = skl_format_to_drm(
 			val & PLANE_CTL_FORMAT_MASK,
@@ -260,9 +256,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	}
 
 	plane->stride = intel_vgpu_get_stride(vgpu, pipe, plane->tiled,
-		(IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv)) ?
+		(INTEL_GEN(dev_priv) >= 9) ?
 			(_PRI_PLANE_STRIDE_MASK >> 6) :
 				_PRI_PLANE_STRIDE_MASK, plane->bpp);
 

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

@@ -187,52 +187,6 @@ static const struct intel_gvt_ops intel_gvt_ops = {
 	.write_protect_handler = intel_vgpu_page_track_handler,
 };
 
-/**
- * intel_gvt_init_host - Load MPT modules and detect if we're running in host
- *
- * This function is called at the driver loading stage. If failed to find a
- * loadable MPT module or detect currently we're running in a VM, then GVT-g
- * will be disabled
- *
- * Returns:
- * Zero on success, negative error code if failed.
- *
- */
-int intel_gvt_init_host(void)
-{
-	if (intel_gvt_host.initialized)
-		return 0;
-
-	/* Xen DOM U */
-	if (xen_domain() && !xen_initial_domain())
-		return -ENODEV;
-
-	/* Try to load MPT modules for hypervisors */
-	if (xen_initial_domain()) {
-		/* In Xen dom0 */
-		intel_gvt_host.mpt = try_then_request_module(
-				symbol_get(xengt_mpt), "xengt");
-		intel_gvt_host.hypervisor_type = INTEL_GVT_HYPERVISOR_XEN;
-	} else {
-#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
-		/* not in Xen. Try KVMGT */
-		intel_gvt_host.mpt = try_then_request_module(
-				symbol_get(kvmgt_mpt), "kvmgt");
-		intel_gvt_host.hypervisor_type = INTEL_GVT_HYPERVISOR_KVM;
-#endif
-	}
-
-	/* Fail to load MPT modules - bail out */
-	if (!intel_gvt_host.mpt)
-		return -EINVAL;
-
-	gvt_dbg_core("Running with hypervisor %s in host mode\n",
-			supported_hypervisors[intel_gvt_host.hypervisor_type]);
-
-	intel_gvt_host.initialized = true;
-	return 0;
-}
-
 static void init_device_info(struct intel_gvt *gvt)
 {
 	struct intel_gvt_device_info *info = &gvt->device_info;
@@ -316,7 +270,6 @@ void intel_gvt_clean_device(struct drm_i915_private *dev_priv)
 		return;
 
 	intel_gvt_destroy_idle_vgpu(gvt->idle_vgpu);
-	intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt);
 	intel_gvt_cleanup_vgpu_type_groups(gvt);
 	intel_gvt_clean_vgpu_types(gvt);
 
@@ -352,13 +305,6 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 	struct intel_vgpu *vgpu;
 	int ret;
 
-	/*
-	 * Cannot initialize GVT device without intel_gvt_host gets
-	 * initialized first.
-	 */
-	if (WARN_ON(!intel_gvt_host.initialized))
-		return -EINVAL;
-
 	if (WARN_ON(dev_priv->gvt))
 		return -EEXIST;
 
@@ -420,13 +366,6 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 		goto out_clean_types;
 	}
 
-	ret = intel_gvt_hypervisor_host_init(&dev_priv->drm.pdev->dev, gvt,
-				&intel_gvt_ops);
-	if (ret) {
-		gvt_err("failed to register gvt-g host device: %d\n", ret);
-		goto out_clean_types;
-	}
-
 	vgpu = intel_gvt_create_idle_vgpu(gvt);
 	if (IS_ERR(vgpu)) {
 		ret = PTR_ERR(vgpu);
@@ -441,6 +380,8 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 
 	gvt_dbg_core("gvt device initialization is done\n");
 	dev_priv->gvt = gvt;
+	intel_gvt_host.dev = &dev_priv->drm.pdev->dev;
+	intel_gvt_host.initialized = true;
 	return 0;
 
 out_clean_types:
@@ -467,6 +408,45 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
-MODULE_SOFTDEP("pre: kvmgt");
-#endif
+int
+intel_gvt_register_hypervisor(struct intel_gvt_mpt *m)
+{
+	int ret;
+	void *gvt;
+
+	if (!intel_gvt_host.initialized)
+		return -ENODEV;
+
+	if (m->type != INTEL_GVT_HYPERVISOR_KVM &&
+	    m->type != INTEL_GVT_HYPERVISOR_XEN)
+		return -EINVAL;
+
+	/* Get a reference for device model module */
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	intel_gvt_host.mpt = m;
+	intel_gvt_host.hypervisor_type = m->type;
+	gvt = (void *)kdev_to_i915(intel_gvt_host.dev)->gvt;
+
+	ret = intel_gvt_hypervisor_host_init(intel_gvt_host.dev, gvt,
+					     &intel_gvt_ops);
+	if (ret < 0) {
+		gvt_err("Failed to init %s hypervisor module\n",
+			supported_hypervisors[intel_gvt_host.hypervisor_type]);
+		module_put(THIS_MODULE);
+		return -ENODEV;
+	}
+	gvt_dbg_core("Running with hypervisor %s in host mode\n",
+		     supported_hypervisors[intel_gvt_host.hypervisor_type]);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(intel_gvt_register_hypervisor);
+
+void
+intel_gvt_unregister_hypervisor(void)
+{
+	intel_gvt_hypervisor_host_exit(intel_gvt_host.dev);
+	module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(intel_gvt_unregister_hypervisor);

drivers/gpu/drm/i915/gvt/gvt.h

@@ -52,12 +52,8 @@
 
 #define GVT_MAX_VGPU 8
 
-enum {
-	INTEL_GVT_HYPERVISOR_XEN = 0,
-	INTEL_GVT_HYPERVISOR_KVM,
-};
-
 struct intel_gvt_host {
+	struct device *dev;
 	bool initialized;
 	int hypervisor_type;
 	struct intel_gvt_mpt *mpt;
@@ -597,7 +593,7 @@ static inline void mmio_hw_access_pre(struct drm_i915_private *dev_priv)
 
 static inline void mmio_hw_access_post(struct drm_i915_private *dev_priv)
 {
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 }
 
 /**

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

@@ -57,6 +57,8 @@ unsigned long intel_gvt_get_device_type(struct intel_gvt *gvt)
 		return D_KBL;
 	else if (IS_BROXTON(gvt->dev_priv))
 		return D_BXT;
+	else if (IS_COFFEELAKE(gvt->dev_priv))
+		return D_CFL;
 
 	return 0;
 }
@@ -276,14 +278,12 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
 	u32 old, new;
-	uint32_t ack_reg_offset;
+	u32 ack_reg_offset;
 
 	old = vgpu_vreg(vgpu, offset);
 	new = CALC_MODE_MASK_REG(old, *(u32 *)p_data);
 
-	if (IS_SKYLAKE(vgpu->gvt->dev_priv)
-		|| IS_KABYLAKE(vgpu->gvt->dev_priv)
-		|| IS_BROXTON(vgpu->gvt->dev_priv)) {
+	if (INTEL_GEN(vgpu->gvt->dev_priv)  >=  9) {
 		switch (offset) {
 		case FORCEWAKE_RENDER_GEN9_REG:
 			ack_reg_offset = FORCEWAKE_ACK_RENDER_GEN9_REG;
@@ -833,7 +833,7 @@ static int dp_aux_ch_ctl_trans_done(struct intel_vgpu *vgpu, u32 value,
 }
 
 static void dp_aux_ch_ctl_link_training(struct intel_vgpu_dpcd_data *dpcd,
-		uint8_t t)
+		u8 t)
 {
 	if ((t & DPCD_TRAINING_PATTERN_SET_MASK) == DPCD_TRAINING_PATTERN_1) {
 		/* training pattern 1 for CR */
@@ -889,9 +889,7 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
 	write_vreg(vgpu, offset, p_data, bytes);
 	data = vgpu_vreg(vgpu, offset);
 
-	if ((IS_SKYLAKE(vgpu->gvt->dev_priv)
-		|| IS_KABYLAKE(vgpu->gvt->dev_priv)
-		|| IS_BROXTON(vgpu->gvt->dev_priv))
+	if ((INTEL_GEN(vgpu->gvt->dev_priv) >= 9)
 		&& offset != _REG_SKL_DP_AUX_CH_CTL(port_index)) {
 		/* SKL DPB/C/D aux ctl register changed */
 		return 0;
@@ -919,7 +917,7 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
 
 	if (op == GVT_AUX_NATIVE_WRITE) {
 		int t;
-		uint8_t buf[16];
+		u8 buf[16];
 
 		if ((addr + len + 1) >= DPCD_SIZE) {
 			/*
@@ -1407,7 +1405,8 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 	switch (cmd) {
 	case GEN9_PCODE_READ_MEM_LATENCY:
 		if (IS_SKYLAKE(vgpu->gvt->dev_priv)
-			 || IS_KABYLAKE(vgpu->gvt->dev_priv)) {
+			 || IS_KABYLAKE(vgpu->gvt->dev_priv)
+			 || IS_COFFEELAKE(vgpu->gvt->dev_priv)) {
 			/**
 			 * "Read memory latency" command on gen9.
 			 * Below memory latency values are read
@@ -1431,7 +1430,8 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 		break;
 	case SKL_PCODE_CDCLK_CONTROL:
 		if (IS_SKYLAKE(vgpu->gvt->dev_priv)
-			 || IS_KABYLAKE(vgpu->gvt->dev_priv))
+			 || IS_KABYLAKE(vgpu->gvt->dev_priv)
+			 || IS_COFFEELAKE(vgpu->gvt->dev_priv))
 			*data0 = SKL_CDCLK_READY_FOR_CHANGE;
 		break;
 	case GEN6_PCODE_READ_RC6VIDS:
@@ -3041,8 +3041,8 @@ 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);
-	MMIO_D(_MMIO(0x2248), D_KBL | D_SKL);
+	MMIO_D(_MMIO(0x4ab8), D_KBL | D_CFL);
+	MMIO_D(_MMIO(0x2248), D_SKL_PLUS);
 
 	return 0;
 }
@@ -3302,7 +3302,8 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 		if (ret)
 			goto err;
 	} else if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)) {
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_COFFEELAKE(dev_priv)) {
 		ret = init_broadwell_mmio_info(gvt);
 		if (ret)
 			goto err;

drivers/gpu/drm/i915/gvt/hypercall.h

@@ -33,13 +33,19 @@
 #ifndef _GVT_HYPERCALL_H_
 #define _GVT_HYPERCALL_H_
 
+enum hypervisor_type {
+	INTEL_GVT_HYPERVISOR_XEN = 0,
+	INTEL_GVT_HYPERVISOR_KVM,
+};
+
 /*
  * Specific GVT-g MPT modules function collections. Currently GVT-g supports
  * both Xen and KVM by providing dedicated hypervisor-related MPT modules.
  */
 struct intel_gvt_mpt {
+	enum hypervisor_type type;
 	int (*host_init)(struct device *dev, void *gvt, const void *ops);
-	void (*host_exit)(struct device *dev, void *gvt);
+	void (*host_exit)(struct device *dev);
 	int (*attach_vgpu)(void *vgpu, unsigned long *handle);
 	void (*detach_vgpu)(unsigned long handle);
 	int (*inject_msi)(unsigned long handle, u32 addr, u16 data);
@@ -67,6 +73,5 @@ struct intel_gvt_mpt {
 };
 
 extern struct intel_gvt_mpt xengt_mpt;
-extern struct intel_gvt_mpt kvmgt_mpt;
 
 #endif /* _GVT_HYPERCALL_H_ */

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

@@ -581,9 +581,7 @@ static void gen8_init_irq(
 
 		SET_BIT_INFO(irq, 4, PRIMARY_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C);
 		SET_BIT_INFO(irq, 5, SPRITE_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C);
-	} else if (IS_SKYLAKE(gvt->dev_priv)
-			|| IS_KABYLAKE(gvt->dev_priv)
-			|| IS_BROXTON(gvt->dev_priv)) {
+	} else if (INTEL_GEN(gvt->dev_priv) >= 9) {
 		SET_BIT_INFO(irq, 25, AUX_CHANNEL_B, INTEL_GVT_IRQ_INFO_DE_PORT);
 		SET_BIT_INFO(irq, 26, AUX_CHANNEL_C, INTEL_GVT_IRQ_INFO_DE_PORT);
 		SET_BIT_INFO(irq, 27, AUX_CHANNEL_D, INTEL_GVT_IRQ_INFO_DE_PORT);

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

@@ -627,6 +627,12 @@ static int intel_vgpu_open(struct mdev_device *mdev)
 		goto undo_iommu;
 	}
 
+	/* Take a module reference as mdev core doesn't take
+	 * a reference for vendor driver.
+	 */
+	if (!try_module_get(THIS_MODULE))
+		goto undo_group;
+
 	ret = kvmgt_guest_init(mdev);
 	if (ret)
 		goto undo_group;
@@ -679,6 +685,9 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu)
 					&vgpu->vdev.group_notifier);
 	WARN(ret, "vfio_unregister_notifier for group failed: %d\n", ret);
 
+	/* dereference module reference taken at open */
+	module_put(THIS_MODULE);
+
 	info = (struct kvmgt_guest_info *)vgpu->handle;
 	kvmgt_guest_exit(info);
 
@@ -703,7 +712,7 @@ static void intel_vgpu_release_work(struct work_struct *work)
 	__intel_vgpu_release(vgpu);
 }
 
-static uint64_t intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
+static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
 {
 	u32 start_lo, start_hi;
 	u32 mem_type;
@@ -730,10 +739,10 @@ static uint64_t intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
 	return ((u64)start_hi << 32) | start_lo;
 }
 
-static int intel_vgpu_bar_rw(struct intel_vgpu *vgpu, int bar, uint64_t off,
+static int intel_vgpu_bar_rw(struct intel_vgpu *vgpu, int bar, u64 off,
 			     void *buf, unsigned int count, bool is_write)
 {
-	uint64_t bar_start = intel_vgpu_get_bar_addr(vgpu, bar);
+	u64 bar_start = intel_vgpu_get_bar_addr(vgpu, bar);
 	int ret;
 
 	if (is_write)
@@ -745,13 +754,13 @@ static int intel_vgpu_bar_rw(struct intel_vgpu *vgpu, int bar, uint64_t off,
 	return ret;
 }
 
-static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, uint64_t off)
+static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, u64 off)
 {
 	return off >= vgpu_aperture_offset(vgpu) &&
 	       off < vgpu_aperture_offset(vgpu) + vgpu_aperture_sz(vgpu);
 }
 
-static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, uint64_t off,
+static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off,
 		void *buf, unsigned long count, bool is_write)
 {
 	void *aperture_va;
@@ -783,7 +792,7 @@ static ssize_t intel_vgpu_rw(struct mdev_device *mdev, char *buf,
 {
 	struct intel_vgpu *vgpu = mdev_get_drvdata(mdev);
 	unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos);
-	uint64_t pos = *ppos & VFIO_PCI_OFFSET_MASK;
+	u64 pos = *ppos & VFIO_PCI_OFFSET_MASK;
 	int ret = -EINVAL;
 
 
@@ -1029,7 +1038,7 @@ static int intel_vgpu_get_irq_count(struct intel_vgpu *vgpu, int type)
 
 static int intel_vgpu_set_intx_mask(struct intel_vgpu *vgpu,
 			unsigned int index, unsigned int start,
-			unsigned int count, uint32_t flags,
+			unsigned int count, u32 flags,
 			void *data)
 {
 	return 0;
@@ -1037,21 +1046,21 @@ static int intel_vgpu_set_intx_mask(struct intel_vgpu *vgpu,
 
 static int intel_vgpu_set_intx_unmask(struct intel_vgpu *vgpu,
 			unsigned int index, unsigned int start,
-			unsigned int count, uint32_t flags, void *data)
+			unsigned int count, u32 flags, void *data)
 {
 	return 0;
 }
 
 static int intel_vgpu_set_intx_trigger(struct intel_vgpu *vgpu,
 		unsigned int index, unsigned int start, unsigned int count,
-		uint32_t flags, void *data)
+		u32 flags, void *data)
 {
 	return 0;
 }
 
 static int intel_vgpu_set_msi_trigger(struct intel_vgpu *vgpu,
 		unsigned int index, unsigned int start, unsigned int count,
-		uint32_t flags, void *data)
+		u32 flags, void *data)
 {
 	struct eventfd_ctx *trigger;
 
@@ -1070,12 +1079,12 @@ static int intel_vgpu_set_msi_trigger(struct intel_vgpu *vgpu,
 	return 0;
 }
 
-static int intel_vgpu_set_irqs(struct intel_vgpu *vgpu, uint32_t flags,
+static int intel_vgpu_set_irqs(struct intel_vgpu *vgpu, u32 flags,
 		unsigned int index, unsigned int start, unsigned int count,
 		void *data)
 {
 	int (*func)(struct intel_vgpu *vgpu, unsigned int index,
-			unsigned int start, unsigned int count, uint32_t flags,
+			unsigned int start, unsigned int count, u32 flags,
 			void *data) = NULL;
 
 	switch (index) {
@@ -1467,7 +1476,7 @@ static int kvmgt_host_init(struct device *dev, void *gvt, const void *ops)
 	return mdev_register_device(dev, &intel_vgpu_ops);
 }
 
-static void kvmgt_host_exit(struct device *dev, void *gvt)
+static void kvmgt_host_exit(struct device *dev)
 {
 	mdev_unregister_device(dev);
 }
@@ -1849,7 +1858,8 @@ static bool kvmgt_is_valid_gfn(unsigned long handle, unsigned long gfn)
 	return ret;
 }
 
-struct intel_gvt_mpt kvmgt_mpt = {
+static struct intel_gvt_mpt kvmgt_mpt = {
+	.type = INTEL_GVT_HYPERVISOR_KVM,
 	.host_init = kvmgt_host_init,
 	.host_exit = kvmgt_host_exit,
 	.attach_vgpu = kvmgt_attach_vgpu,
@@ -1868,15 +1878,17 @@ struct intel_gvt_mpt kvmgt_mpt = {
 	.put_vfio_device = kvmgt_put_vfio_device,
 	.is_valid_gfn = kvmgt_is_valid_gfn,
 };
-EXPORT_SYMBOL_GPL(kvmgt_mpt);
 
 static int __init kvmgt_init(void)
 {
+	if (intel_gvt_register_hypervisor(&kvmgt_mpt) < 0)
+		return -ENODEV;
 	return 0;
 }
 
 static void __exit kvmgt_exit(void)
 {
+	intel_gvt_unregister_hypervisor();
 }
 
 module_init(kvmgt_init);

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

@@ -57,7 +57,7 @@ int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa)
 	(reg >= gvt->device_info.gtt_start_offset \
 	 && reg < gvt->device_info.gtt_start_offset + gvt_ggtt_sz(gvt))
 
-static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
+static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, u64 pa,
 		void *p_data, unsigned int bytes, bool read)
 {
 	struct intel_gvt *gvt = NULL;
@@ -99,7 +99,7 @@ static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
  * Returns:
  * Zero on success, negative error code if failed
  */
-int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
+int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, u64 pa,
 		void *p_data, unsigned int bytes)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
@@ -171,7 +171,7 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
  * Returns:
  * Zero on success, negative error code if failed
  */
-int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
+int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, u64 pa,
 		void *p_data, unsigned int bytes)
 {
 	struct intel_gvt *gvt = vgpu->gvt;

drivers/gpu/drm/i915/gvt/mmio.h

@@ -43,15 +43,16 @@ struct intel_vgpu;
 #define D_SKL	(1 << 1)
 #define D_KBL	(1 << 2)
 #define D_BXT	(1 << 3)
+#define D_CFL	(1 << 4)
 
-#define D_GEN9PLUS	(D_SKL | D_KBL | D_BXT)
-#define D_GEN8PLUS	(D_BDW | D_SKL | D_KBL | D_BXT)
+#define D_GEN9PLUS	(D_SKL | D_KBL | D_BXT | D_CFL)
+#define D_GEN8PLUS	(D_BDW | D_SKL | D_KBL | D_BXT | D_CFL)
 
-#define D_SKL_PLUS	(D_SKL | D_KBL | D_BXT)
-#define D_BDW_PLUS	(D_BDW | D_SKL | D_KBL | D_BXT)
+#define D_SKL_PLUS	(D_SKL | D_KBL | D_BXT | D_CFL)
+#define D_BDW_PLUS	(D_BDW | D_SKL | D_KBL | D_BXT | D_CFL)
 
 #define D_PRE_SKL	(D_BDW)
-#define D_ALL		(D_BDW | D_SKL | D_KBL | D_BXT)
+#define D_ALL		(D_BDW | D_SKL | D_KBL | D_BXT | D_CFL)
 
 typedef int (*gvt_mmio_func)(struct intel_vgpu *, unsigned int, void *,
 			     unsigned int);

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

@@ -353,8 +353,7 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
 	 */
 	fw = intel_uncore_forcewake_for_reg(dev_priv, reg,
 					    FW_REG_READ | FW_REG_WRITE);
-	if (ring_id == RCS && (IS_SKYLAKE(dev_priv) ||
-			IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)))
+	if (ring_id == RCS && (INTEL_GEN(dev_priv) >= 9))
 		fw |= FORCEWAKE_RENDER;
 
 	intel_uncore_forcewake_get(dev_priv, fw);
@@ -391,7 +390,8 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 	if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
 		return;
 
-	if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) && ring_id == RCS)
+	if ((IS_KABYLAKE(dev_priv)  || IS_BROXTON(dev_priv)
+		|| IS_COFFEELAKE(dev_priv)) && ring_id == RCS)
 		return;
 
 	if (!pre && !gen9_render_mocs.initialized)
@@ -457,9 +457,7 @@ static void switch_mmio(struct intel_vgpu *pre,
 	u32 old_v, new_v;
 
 	dev_priv = pre ? pre->gvt->dev_priv : next->gvt->dev_priv;
-	if (IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv)
-		|| IS_BROXTON(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 9)
 		switch_mocs(pre, next, ring_id);
 
 	for (mmio = dev_priv->gvt->engine_mmio_list.mmio;
@@ -471,8 +469,8 @@ static void switch_mmio(struct intel_vgpu *pre,
 		 * state image on kabylake, it's initialized by lri command and
 		 * save or restore with context together.
 		 */
-		if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv))
-			&& mmio->in_context)
+		if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)
+			|| IS_COFFEELAKE(dev_priv)) && mmio->in_context)
 			continue;
 
 		// save
@@ -565,9 +563,7 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt)
 {
 	struct engine_mmio *mmio;
 
-	if (IS_SKYLAKE(gvt->dev_priv) ||
-		IS_KABYLAKE(gvt->dev_priv) ||
-		IS_BROXTON(gvt->dev_priv))
+	if (INTEL_GEN(gvt->dev_priv) >= 9)
 		gvt->engine_mmio_list.mmio = gen9_engine_mmio_list;
 	else
 		gvt->engine_mmio_list.mmio = gen8_engine_mmio_list;

drivers/gpu/drm/i915/gvt/mpt.h

@@ -50,11 +50,10 @@
  * Zero on success, negative error code if failed
  */
 static inline int intel_gvt_hypervisor_host_init(struct device *dev,
-			void *gvt, const void *ops)
+						 void *gvt, const void *ops)
 {
-	/* optional to provide */
 	if (!intel_gvt_host.mpt->host_init)
-		return 0;
+		return -ENODEV;
 
 	return intel_gvt_host.mpt->host_init(dev, gvt, ops);
 }
@@ -62,14 +61,13 @@ static inline int intel_gvt_hypervisor_host_init(struct device *dev,
 /**
  * intel_gvt_hypervisor_host_exit - exit GVT-g host side
  */
-static inline void intel_gvt_hypervisor_host_exit(struct device *dev,
-			void *gvt)
+static inline void intel_gvt_hypervisor_host_exit(struct device *dev)
 {
 	/* optional to provide */
 	if (!intel_gvt_host.mpt->host_exit)
 		return;
 
-	intel_gvt_host.mpt->host_exit(dev, gvt);
+	intel_gvt_host.mpt->host_exit(dev);
 }
 
 /**
@@ -362,4 +360,7 @@ static inline bool intel_gvt_hypervisor_is_valid_gfn(
 	return intel_gvt_host.mpt->is_valid_gfn(vgpu->handle, gfn);
 }
 
+int intel_gvt_register_hypervisor(struct intel_gvt_mpt *);
+void intel_gvt_unregister_hypervisor(void);
+
 #endif /* _GVT_MPT_H_ */

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

@@ -94,7 +94,7 @@ static void gvt_balance_timeslice(struct gvt_sched_data *sched_data)
 {
 	struct vgpu_sched_data *vgpu_data;
 	struct list_head *pos;
-	static uint64_t stage_check;
+	static u64 stage_check;
 	int stage = stage_check++ % GVT_TS_BALANCE_STAGE_NUM;
 
 	/* The timeslice accumulation reset at stage 0, which is
@@ -474,6 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		}
 	}
 	spin_unlock_bh(&scheduler->mmio_context_lock);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put_unchecked(dev_priv);
 	mutex_unlock(&vgpu->gvt->sched_lock);
 }

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

@@ -299,7 +299,8 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	void *shadow_ring_buffer_va;
 	u32 *cs;
 
-	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915))
+	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915)
+		|| IS_COFFEELAKE(req->i915))
 		&& is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
@@ -939,9 +940,7 @@ static int workload_thread(void *priv)
 	struct intel_vgpu_workload *workload = NULL;
 	struct intel_vgpu *vgpu = NULL;
 	int ret;
-	bool need_force_wake = IS_SKYLAKE(gvt->dev_priv)
-			|| IS_KABYLAKE(gvt->dev_priv)
-			|| IS_BROXTON(gvt->dev_priv);
+	bool need_force_wake = (INTEL_GEN(gvt->dev_priv) >= 9);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	kfree(p);
@@ -997,7 +996,7 @@ static int workload_thread(void *priv)
 			intel_uncore_forcewake_put(gvt->dev_priv,
 					FORCEWAKE_ALL);
 
-		intel_runtime_pm_put(gvt->dev_priv);
+		intel_runtime_pm_put_unchecked(gvt->dev_priv);
 		if (ret && (vgpu_is_vm_unhealthy(ret)))
 			enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
 	}
@@ -1451,7 +1450,7 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 		mutex_lock(&dev_priv->drm.struct_mutex);
 		ret = intel_gvt_scan_and_shadow_workload(workload);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
-		intel_runtime_pm_put(dev_priv);
+		intel_runtime_pm_put_unchecked(dev_priv);
 	}
 
 	if (ret && (vgpu_is_vm_unhealthy(ret))) {

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

@@ -61,7 +61,7 @@ struct shadow_indirect_ctx {
 	unsigned long guest_gma;
 	unsigned long shadow_gma;
 	void *shadow_va;
-	uint32_t size;
+	u32 size;
 };
 
 #define PER_CTX_ADDR_MASK 0xfffff000

drivers/gpu/drm/i915/gvt/trace.h

@@ -228,7 +228,7 @@ TRACE_EVENT(oos_sync,
 TRACE_EVENT(gvt_command,
 	TP_PROTO(u8 vgpu_id, u8 ring_id, u32 ip_gma, u32 *cmd_va,
 		u32 cmd_len,  u32 buf_type, u32 buf_addr_type,
-		void *workload, char *cmd_name),
+		void *workload, const char *cmd_name),
 
 	TP_ARGS(vgpu_id, ring_id, ip_gma, cmd_va, cmd_len, buf_type,
 		buf_addr_type, workload, cmd_name),

drivers/gpu/drm/i915/i915_drv.c

@@ -48,6 +48,7 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "i915_pmu.h"
+#include "i915_reset.h"
 #include "i915_query.h"
 #include "i915_vgpu.h"
 #include "intel_drv.h"
@@ -905,6 +906,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv)
 	mutex_init(&dev_priv->pps_mutex);
 
 	i915_memcpy_init_early(dev_priv);
+	intel_runtime_pm_init_early(dev_priv);
 
 	ret = i915_workqueues_init(dev_priv);
 	if (ret < 0)
@@ -1779,6 +1781,9 @@ void i915_driver_unload(struct drm_device *dev)
 
 	i915_driver_unregister(dev_priv);
 
+	/* Flush any external code that still may be under the RCU lock */
+	synchronize_rcu();
+
 	if (i915_gem_suspend(dev_priv))
 		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
 
@@ -1807,8 +1812,7 @@ void i915_driver_unload(struct drm_device *dev)
 	i915_driver_cleanup_mmio(dev_priv);
 
 	enable_rpm_wakeref_asserts(dev_priv);
-
-	WARN_ON(atomic_read(&dev_priv->runtime_pm.wakeref_count));
+	intel_runtime_pm_cleanup(dev_priv);
 }
 
 static void i915_driver_release(struct drm_device *dev)
@@ -2010,6 +2014,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 out:
 	enable_rpm_wakeref_asserts(dev_priv);
+	if (!dev_priv->uncore.user_forcewake.count)
+		intel_runtime_pm_cleanup(dev_priv);
 
 	return ret;
 }
@@ -2200,211 +2206,6 @@ static int i915_resume_switcheroo(struct drm_device *dev)
 	return i915_drm_resume(dev);
 }
 
-/**
- * i915_reset - reset chip after a hang
- * @i915: #drm_i915_private to reset
- * @stalled_mask: mask of the stalled engines with the guilty requests
- * @reason: user error message for why we are resetting
- *
- * Reset the chip.  Useful if a hang is detected. Marks the device as wedged
- * on failure.
- *
- * Caller must hold the struct_mutex.
- *
- * Procedure is fairly simple:
- *   - reset the chip using the reset reg
- *   - re-init context state
- *   - re-init hardware status page
- *   - re-init ring buffer
- *   - re-init interrupt state
- *   - re-init display
- */
-void i915_reset(struct drm_i915_private *i915,
-		unsigned int stalled_mask,
-		const char *reason)
-{
-	struct i915_gpu_error *error = &i915->gpu_error;
-	int ret;
-	int i;
-
-	GEM_TRACE("flags=%lx\n", error->flags);
-
-	might_sleep();
-	lockdep_assert_held(&i915->drm.struct_mutex);
-	assert_rpm_wakelock_held(i915);
-	GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, &error->flags));
-
-	if (!test_bit(I915_RESET_HANDOFF, &error->flags))
-		return;
-
-	/* Clear any previous failed attempts at recovery. Time to try again. */
-	if (!i915_gem_unset_wedged(i915))
-		goto wakeup;
-
-	if (reason)
-		dev_notice(i915->drm.dev, "Resetting chip for %s\n", reason);
-	error->reset_count++;
-
-	ret = i915_gem_reset_prepare(i915);
-	if (ret) {
-		dev_err(i915->drm.dev, "GPU recovery failed\n");
-		goto taint;
-	}
-
-	if (!intel_has_gpu_reset(i915)) {
-		if (i915_modparams.reset)
-			dev_err(i915->drm.dev, "GPU reset not supported\n");
-		else
-			DRM_DEBUG_DRIVER("GPU reset disabled\n");
-		goto error;
-	}
-
-	for (i = 0; i < 3; i++) {
-		ret = intel_gpu_reset(i915, ALL_ENGINES);
-		if (ret == 0)
-			break;
-
-		msleep(100);
-	}
-	if (ret) {
-		dev_err(i915->drm.dev, "Failed to reset chip\n");
-		goto taint;
-	}
-
-	/* Ok, now get things going again... */
-
-	/*
-	 * Everything depends on having the GTT running, so we need to start
-	 * there.
-	 */
-	ret = i915_ggtt_enable_hw(i915);
-	if (ret) {
-		DRM_ERROR("Failed to re-enable GGTT following reset (%d)\n",
-			  ret);
-		goto error;
-	}
-
-	i915_gem_reset(i915, stalled_mask);
-	intel_overlay_reset(i915);
-
-	/*
-	 * Next we need to restore the context, but we don't use those
-	 * yet either...
-	 *
-	 * Ring buffer needs to be re-initialized in the KMS case, or if X
-	 * was running at the time of the reset (i.e. we weren't VT
-	 * switched away).
-	 */
-	ret = i915_gem_init_hw(i915);
-	if (ret) {
-		DRM_ERROR("Failed to initialise HW following reset (%d)\n",
-			  ret);
-		goto error;
-	}
-
-	i915_queue_hangcheck(i915);
-
-finish:
-	i915_gem_reset_finish(i915);
-wakeup:
-	clear_bit(I915_RESET_HANDOFF, &error->flags);
-	wake_up_bit(&error->flags, I915_RESET_HANDOFF);
-	return;
-
-taint:
-	/*
-	 * History tells us that if we cannot reset the GPU now, we
-	 * never will. This then impacts everything that is run
-	 * subsequently. On failing the reset, we mark the driver
-	 * as wedged, preventing further execution on the GPU.
-	 * We also want to go one step further and add a taint to the
-	 * kernel so that any subsequent faults can be traced back to
-	 * this failure. This is important for CI, where if the
-	 * GPU/driver fails we would like to reboot and restart testing
-	 * rather than continue on into oblivion. For everyone else,
-	 * the system should still plod along, but they have been warned!
-	 */
-	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-error:
-	i915_gem_set_wedged(i915);
-	i915_retire_requests(i915);
-	goto finish;
-}
-
-static inline int intel_gt_reset_engine(struct drm_i915_private *dev_priv,
-					struct intel_engine_cs *engine)
-{
-	return intel_gpu_reset(dev_priv, intel_engine_flag(engine));
-}
-
-/**
- * i915_reset_engine - reset GPU engine to recover from a hang
- * @engine: engine to reset
- * @msg: reason for GPU reset; or NULL for no dev_notice()
- *
- * Reset a specific GPU engine. Useful if a hang is detected.
- * Returns zero on successful reset or otherwise an error code.
- *
- * Procedure is:
- *  - identifies the request that caused the hang and it is dropped
- *  - reset engine (which will force the engine to idle)
- *  - re-init/configure engine
- */
-int i915_reset_engine(struct intel_engine_cs *engine, const char *msg)
-{
-	struct i915_gpu_error *error = &engine->i915->gpu_error;
-	struct i915_request *active_request;
-	int ret;
-
-	GEM_TRACE("%s flags=%lx\n", engine->name, error->flags);
-	GEM_BUG_ON(!test_bit(I915_RESET_ENGINE + engine->id, &error->flags));
-
-	active_request = i915_gem_reset_prepare_engine(engine);
-	if (IS_ERR_OR_NULL(active_request)) {
-		/* Either the previous reset failed, or we pardon the reset. */
-		ret = PTR_ERR(active_request);
-		goto out;
-	}
-
-	if (msg)
-		dev_notice(engine->i915->drm.dev,
-			   "Resetting %s for %s\n", engine->name, msg);
-	error->reset_engine_count[engine->id]++;
-
-	if (!engine->i915->guc.execbuf_client)
-		ret = intel_gt_reset_engine(engine->i915, engine);
-	else
-		ret = intel_guc_reset_engine(&engine->i915->guc, engine);
-	if (ret) {
-		/* If we fail here, we expect to fallback to a global reset */
-		DRM_DEBUG_DRIVER("%sFailed to reset %s, ret=%d\n",
-				 engine->i915->guc.execbuf_client ? "GuC " : "",
-				 engine->name, ret);
-		goto out;
-	}
-
-	/*
-	 * The request that caused the hang is stuck on elsp, we know the
-	 * active request and can drop it, adjust head to skip the offending
-	 * request to resume executing remaining requests in the queue.
-	 */
-	i915_gem_reset_engine(engine, active_request, true);
-
-	/*
-	 * The engine and its registers (and workarounds in case of render)
-	 * have been reset to their default values. Follow the init_ring
-	 * process to program RING_MODE, HWSP and re-enable submission.
-	 */
-	ret = engine->init_hw(engine);
-	if (ret)
-		goto out;
-
-out:
-	intel_engine_cancel_stop_cs(engine);
-	i915_gem_reset_finish_engine(engine);
-	return ret;
-}
-
 static int i915_pm_prepare(struct device *kdev)
 {
 	struct pci_dev *pdev = to_pci_dev(kdev);
@@ -2965,7 +2766,7 @@ static int intel_runtime_suspend(struct device *kdev)
 	}
 
 	enable_rpm_wakeref_asserts(dev_priv);
-	WARN_ON_ONCE(atomic_read(&dev_priv->runtime_pm.wakeref_count));
+	intel_runtime_pm_cleanup(dev_priv);
 
 	if (intel_uncore_arm_unclaimed_mmio_detection(dev_priv))
 		DRM_ERROR("Unclaimed access detected prior to suspending\n");

drivers/gpu/drm/i915/i915_gem_context.c

@@ -321,6 +321,14 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
 	return desc;
 }
 
+void
+intel_context_init(struct intel_context *ce,
+		   struct i915_gem_context *ctx,
+		   struct intel_engine_cs *engine)
+{
+	ce->gem_context = ctx;
+}
+
 static struct i915_gem_context *
 __create_hw_context(struct drm_i915_private *dev_priv,
 		    struct drm_i915_file_private *file_priv)
@@ -338,11 +346,8 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->i915 = dev_priv;
 	ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL);
 
-	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
-		struct intel_context *ce = &ctx->__engine[n];
-
-		ce->gem_context = ctx;
-	}
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++)
+		intel_context_init(&ctx->__engine[n], ctx, dev_priv->engine[n]);
 
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);

drivers/gpu/drm/i915/i915_gem_context.h

@@ -364,4 +364,8 @@ static inline void i915_gem_context_put(struct i915_gem_context *ctx)
 	kref_put(&ctx->ref, i915_gem_context_release);
 }
 
+void intel_context_init(struct intel_context *ce,
+			struct i915_gem_context *ctx,
+			struct intel_engine_cs *engine);
+
 #endif /* !__I915_GEM_CONTEXT_H__ */

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -2202,6 +2202,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
 	struct sync_file *out_fence = NULL;
+	intel_wakeref_t wakeref;
 	int out_fence_fd = -1;
 	int err;
 
@@ -2272,7 +2273,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	 * wakeref that we hold until the GPU has been idle for at least
 	 * 100ms.
 	 */
-	intel_runtime_pm_get(eb.i915);
+	wakeref = intel_runtime_pm_get(eb.i915);
 
 	err = i915_mutex_lock_interruptible(dev);
 	if (err)
@@ -2424,7 +2425,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		eb_release_vmas(&eb);
 	mutex_unlock(&dev->struct_mutex);
 err_rpm:
-	intel_runtime_pm_put(eb.i915);
+	intel_runtime_pm_put(eb.i915, wakeref);
 	i915_gem_context_put(eb.ctx);
 err_destroy:
 	eb_destroy(&eb);

drivers/gpu/drm/i915/i915_gem_fence_reg.c

@@ -209,6 +209,7 @@ static void fence_write(struct drm_i915_fence_reg *fence,
 static int fence_update(struct drm_i915_fence_reg *fence,
 			struct i915_vma *vma)
 {
+	intel_wakeref_t wakeref;
 	int ret;
 
 	if (vma) {
@@ -256,9 +257,10 @@ static int fence_update(struct drm_i915_fence_reg *fence,
 	 * If the device is currently powered down, we will defer the write
 	 * to the runtime resume, see i915_gem_restore_fences().
 	 */
-	if (intel_runtime_pm_get_if_in_use(fence->i915)) {
+	wakeref = intel_runtime_pm_get_if_in_use(fence->i915);
+	if (wakeref) {
 		fence_write(fence, vma);
-		intel_runtime_pm_put(fence->i915);
+		intel_runtime_pm_put(fence->i915, wakeref);
 	}
 
 	if (vma) {
@@ -553,8 +555,8 @@ void i915_gem_restore_fences(struct drm_i915_private *dev_priv)
 void
 i915_gem_detect_bit_6_swizzle(struct drm_i915_private *dev_priv)
 {
-	uint32_t swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
-	uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
+	u32 swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+	u32 swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
 
 	if (INTEL_GEN(dev_priv) >= 8 || IS_VALLEYVIEW(dev_priv)) {
 		/*
@@ -577,7 +579,7 @@ i915_gem_detect_bit_6_swizzle(struct drm_i915_private *dev_priv)
 				swizzle_y = I915_BIT_6_SWIZZLE_NONE;
 			}
 		} else {
-			uint32_t dimm_c0, dimm_c1;
+			u32 dimm_c0, dimm_c1;
 			dimm_c0 = I915_READ(MAD_DIMM_C0);
 			dimm_c1 = I915_READ(MAD_DIMM_C1);
 			dimm_c0 &= MAD_DIMM_A_SIZE_MASK | MAD_DIMM_B_SIZE_MASK;
@@ -609,7 +611,7 @@ i915_gem_detect_bit_6_swizzle(struct drm_i915_private *dev_priv)
 		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
 	} else if (IS_MOBILE(dev_priv) ||
 		   IS_I915G(dev_priv) || IS_I945G(dev_priv)) {
-		uint32_t dcc;
+		u32 dcc;
 
 		/* On 9xx chipsets, channel interleave by the CPU is
 		 * determined by DCC.  For single-channel, neither the CPU

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -37,6 +37,7 @@
 
 #include "i915_drv.h"
 #include "i915_vgpu.h"
+#include "i915_reset.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
@@ -473,8 +474,7 @@ static void vm_free_page(struct i915_address_space *vm, struct page *page)
 	spin_unlock(&vm->free_pages.lock);
 }
 
-static void i915_address_space_init(struct i915_address_space *vm,
-				    struct drm_i915_private *dev_priv)
+static void i915_address_space_init(struct i915_address_space *vm, int subclass)
 {
 	/*
 	 * The vm->mutex must be reclaim safe (for use in the shrinker).
@@ -482,6 +482,7 @@ static void i915_address_space_init(struct i915_address_space *vm,
 	 * attempt holding the lock is immediately reported by lockdep.
 	 */
 	mutex_init(&vm->mutex);
+	lockdep_set_subclass(&vm->mutex, subclass);
 	i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex);
 
 	GEM_BUG_ON(!vm->total);
@@ -1547,7 +1548,7 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	/* From bdw, there is support for read-only pages in the PPGTT. */
 	ppgtt->vm.has_read_only = true;
 
-	i915_address_space_init(&ppgtt->vm, i915);
+	i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT);
 
 	/* There are only few exceptions for gen >=6. chv and bxt.
 	 * And we are not sure about the latter so play safe for now.
@@ -1996,7 +1997,7 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 
 	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * I915_GTT_PAGE_SIZE;
 
-	i915_address_space_init(&ppgtt->base.vm, i915);
+	i915_address_space_init(&ppgtt->base.vm, VM_CLASS_PPGTT);
 
 	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
 	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
@@ -2527,6 +2528,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
 	struct drm_i915_gem_object *obj = vma->obj;
+	intel_wakeref_t wakeref;
 	u32 pte_flags;
 
 	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
@@ -2534,9 +2536,8 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	if (i915_gem_object_is_readonly(obj))
 		pte_flags |= PTE_READ_ONLY;
 
-	intel_runtime_pm_get(i915);
-	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-	intel_runtime_pm_put(i915);
+	with_intel_runtime_pm(i915, wakeref)
+		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 
@@ -2553,10 +2554,10 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 static void ggtt_unbind_vma(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
+	intel_wakeref_t wakeref;
 
-	intel_runtime_pm_get(i915);
-	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-	intel_runtime_pm_put(i915);
+	with_intel_runtime_pm(i915, wakeref)
+		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
 }
 
 static int aliasing_gtt_bind_vma(struct i915_vma *vma,
@@ -2588,9 +2589,12 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 	}
 
 	if (flags & I915_VMA_GLOBAL_BIND) {
-		intel_runtime_pm_get(i915);
-		vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
-		intel_runtime_pm_put(i915);
+		intel_wakeref_t wakeref;
+
+		with_intel_runtime_pm(i915, wakeref) {
+			vma->vm->insert_entries(vma->vm, vma,
+						cache_level, pte_flags);
+		}
 	}
 
 	return 0;
@@ -2601,9 +2605,11 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 	struct drm_i915_private *i915 = vma->vm->i915;
 
 	if (vma->flags & I915_VMA_GLOBAL_BIND) {
-		intel_runtime_pm_get(i915);
-		vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
-		intel_runtime_pm_put(i915);
+		struct i915_address_space *vm = vma->vm;
+		intel_wakeref_t wakeref;
+
+		with_intel_runtime_pm(i915, wakeref)
+			vm->clear_range(vm, vma->node.start, vma->size);
 	}
 
 	if (vma->flags & I915_VMA_LOCAL_BIND) {
@@ -3227,7 +3233,8 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
 
 	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
-	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
+	if (intel_ggtt_update_needs_vtd_wa(dev_priv) ||
+	    IS_CHERRYVIEW(dev_priv) /* fails with concurrent use/update */) {
 		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
 		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
 		if (ggtt->vm.clear_range != nop_clear_range)
@@ -3428,7 +3435,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	 * and beyond the end of the GTT if we do not provide a guard.
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_address_space_init(&ggtt->vm, dev_priv);
+	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
 
 	ggtt->vm.is_ggtt = true;
 

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -288,6 +288,8 @@ struct i915_address_space {
 	bool closed;
 
 	struct mutex mutex; /* protects vma and our lists */
+#define VM_CLASS_GGTT 0
+#define VM_CLASS_PPGTT 1
 
 	u64 scratch_pte;
 	struct i915_page_dma scratch_page;

drivers/gpu/drm/i915/i915_gem_object.h

@@ -57,6 +57,7 @@ struct drm_i915_gem_object_ops {
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
 #define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
 #define I915_GEM_OBJECT_IS_PROXY	BIT(2)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(3)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
@@ -387,6 +388,12 @@ i915_gem_object_is_proxy(const struct drm_i915_gem_object *obj)
 	return obj->ops->flags & I915_GEM_OBJECT_IS_PROXY;
 }
 
+static inline bool
+i915_gem_object_needs_async_cancel(const struct drm_i915_gem_object *obj)
+{
+	return obj->ops->flags & I915_GEM_OBJECT_ASYNC_CANCEL;
+}
+
 static inline bool
 i915_gem_object_is_active(const struct drm_i915_gem_object *obj)
 {

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -153,6 +153,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 		{ &i915->mm.bound_list, I915_SHRINK_BOUND },
 		{ NULL, 0 },
 	}, *phase;
+	intel_wakeref_t wakeref = 0;
 	unsigned long count = 0;
 	unsigned long scanned = 0;
 	bool unlock;
@@ -182,9 +183,11 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	 * device just to recover a little memory. If absolutely necessary,
 	 * we will force the wake during oom-notifier.
 	 */
-	if ((flags & I915_SHRINK_BOUND) &&
-	    !intel_runtime_pm_get_if_in_use(i915))
-		flags &= ~I915_SHRINK_BOUND;
+	if (flags & I915_SHRINK_BOUND) {
+		wakeref = intel_runtime_pm_get_if_in_use(i915);
+		if (!wakeref)
+			flags &= ~I915_SHRINK_BOUND;
+	}
 
 	/*
 	 * As we may completely rewrite the (un)bound list whilst unbinding
@@ -265,7 +268,7 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	}
 
 	if (flags & I915_SHRINK_BOUND)
-		intel_runtime_pm_put(i915);
+		intel_runtime_pm_put(i915, wakeref);
 
 	i915_retire_requests(i915);
 
@@ -292,14 +295,15 @@ i915_gem_shrink(struct drm_i915_private *i915,
  */
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
 {
-	unsigned long freed;
-
-	intel_runtime_pm_get(i915);
-	freed = i915_gem_shrink(i915, -1UL, NULL,
-				I915_SHRINK_BOUND |
-				I915_SHRINK_UNBOUND |
-				I915_SHRINK_ACTIVE);
-	intel_runtime_pm_put(i915);
+	intel_wakeref_t wakeref;
+	unsigned long freed = 0;
+
+	with_intel_runtime_pm(i915, wakeref) {
+		freed = i915_gem_shrink(i915, -1UL, NULL,
+					I915_SHRINK_BOUND |
+					I915_SHRINK_UNBOUND |
+					I915_SHRINK_ACTIVE);
+	}
 
 	return freed;
 }
@@ -370,14 +374,16 @@ i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 					 I915_SHRINK_BOUND |
 					 I915_SHRINK_UNBOUND);
 	if (sc->nr_scanned < sc->nr_to_scan && current_is_kswapd()) {
-		intel_runtime_pm_get(i915);
-		freed += i915_gem_shrink(i915,
-					 sc->nr_to_scan - sc->nr_scanned,
-					 &sc->nr_scanned,
-					 I915_SHRINK_ACTIVE |
-					 I915_SHRINK_BOUND |
-					 I915_SHRINK_UNBOUND);
-		intel_runtime_pm_put(i915);
+		intel_wakeref_t wakeref;
+
+		with_intel_runtime_pm(i915, wakeref) {
+			freed += i915_gem_shrink(i915,
+						 sc->nr_to_scan - sc->nr_scanned,
+						 &sc->nr_scanned,
+						 I915_SHRINK_ACTIVE |
+						 I915_SHRINK_BOUND |
+						 I915_SHRINK_UNBOUND);
+		}
 	}
 
 	shrinker_unlock(i915, unlock);
@@ -392,12 +398,13 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 		container_of(nb, struct drm_i915_private, mm.oom_notifier);
 	struct drm_i915_gem_object *obj;
 	unsigned long unevictable, bound, unbound, freed_pages;
+	intel_wakeref_t wakeref;
 
-	intel_runtime_pm_get(i915);
-	freed_pages = i915_gem_shrink(i915, -1UL, NULL,
-				      I915_SHRINK_BOUND |
-				      I915_SHRINK_UNBOUND);
-	intel_runtime_pm_put(i915);
+	freed_pages = 0;
+	with_intel_runtime_pm(i915, wakeref)
+		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
+					       I915_SHRINK_BOUND |
+					       I915_SHRINK_UNBOUND);
 
 	/* Because we may be allocating inside our own driver, we cannot
 	 * assert that there are no objects with pinned pages that are not
@@ -435,6 +442,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		container_of(nb, struct drm_i915_private, mm.vmap_notifier);
 	struct i915_vma *vma, *next;
 	unsigned long freed_pages = 0;
+	intel_wakeref_t wakeref;
 	bool unlock;
 
 	if (!shrinker_lock(i915, 0, &unlock))
@@ -446,12 +454,11 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 				   MAX_SCHEDULE_TIMEOUT))
 		goto out;
 
-	intel_runtime_pm_get(i915);
-	freed_pages += i915_gem_shrink(i915, -1UL, NULL,
-				       I915_SHRINK_BOUND |
-				       I915_SHRINK_UNBOUND |
-				       I915_SHRINK_VMAPS);
-	intel_runtime_pm_put(i915);
+	with_intel_runtime_pm(i915, wakeref)
+		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
+					       I915_SHRINK_BOUND |
+					       I915_SHRINK_UNBOUND |
+					       I915_SHRINK_VMAPS);
 
 	/* We also want to clear any cached iomaps as they wrap vmap */
 	list_for_each_entry_safe(vma, next,

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1082,7 +1082,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 /* The error capture is special as tries to run underneath the normal
  * locking rules - so we use the raw version of the i915_gem_active lookup.
  */
-static inline uint32_t
+static inline u32
 __active_get_seqno(struct i915_gem_active *active)
 {
 	struct i915_request *request;
@@ -1153,11 +1153,11 @@ static u32 capture_error_bo(struct drm_i915_error_buffer *err,
  *
  * It's only a small step better than a random number in its current form.
  */
-static uint32_t i915_error_generate_code(struct drm_i915_private *dev_priv,
-					 struct i915_gpu_state *error,
-					 int *engine_id)
+static u32 i915_error_generate_code(struct drm_i915_private *dev_priv,
+				    struct i915_gpu_state *error,
+				    int *engine_id)
 {
-	uint32_t error_code = 0;
+	u32 error_code = 0;
 	int i;
 
 	/* IPEHR would be an ideal way to detect errors, as it's the gross

drivers/gpu/drm/i915/i915_gpu_error.h

@@ -271,8 +271,8 @@ struct i915_gpu_error {
 #define I915_RESET_BACKOFF	0
 #define I915_RESET_HANDOFF	1
 #define I915_RESET_MODESET	2
+#define I915_RESET_ENGINE	3
 #define I915_WEDGED		(BITS_PER_LONG - 1)
-#define I915_RESET_ENGINE	(I915_WEDGED - I915_NUM_ENGINES)
 
 	/** Number of times an engine has been reset */
 	u32 reset_engine_count[I915_NUM_ENGINES];
@@ -283,6 +283,8 @@ struct i915_gpu_error {
 	/** Reason for the current *global* reset */
 	const char *reason;
 
+	struct mutex wedge_mutex; /* serialises wedging/unwedging */
+
 	/**
 	 * Waitqueue to signal when a hang is detected. Used to for waiters
 	 * to release the struct_mutex for the reset to procede.

drivers/gpu/drm/i915/i915_perf.c

@@ -1365,7 +1365,7 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream)
 	free_oa_buffer(dev_priv);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, stream->wakeref);
 
 	if (stream->ctx)
 		oa_put_render_ctx_id(stream);
@@ -2087,7 +2087,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	 *   In our case we are expecting that taking pm + FORCEWAKE
 	 *   references will effectively disable RC6.
 	 */
-	intel_runtime_pm_get(dev_priv);
+	stream->wakeref = intel_runtime_pm_get(dev_priv);
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 
 	ret = alloc_oa_buffer(dev_priv);
@@ -2123,7 +2123,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	put_oa_config(dev_priv, stream->oa_config);
 
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(dev_priv, stream->wakeref);
 
 err_config:
 	if (stream->ctx)
@@ -3021,7 +3021,7 @@ static bool chv_is_valid_mux_addr(struct drm_i915_private *dev_priv, u32 addr)
 		(addr >= 0x182300 && addr <= 0x1823A4);
 }
 
-static uint32_t mask_reg_value(u32 reg, u32 val)
+static u32 mask_reg_value(u32 reg, u32 val)
 {
 	/* HALF_SLICE_CHICKEN2 is programmed with a the
 	 * WaDisableSTUnitPowerOptimization workaround. Make sure the value

drivers/gpu/drm/i915/i915_request.c

@@ -29,6 +29,7 @@
 #include <linux/sched/signal.h>
 
 #include "i915_drv.h"
+#include "i915_reset.h"
 
 static const char *i915_fence_get_driver_name(struct dma_fence *fence)
 {
@@ -197,7 +198,7 @@ static void __retire_engine_request(struct intel_engine_cs *engine,
 	spin_unlock(&engine->timeline.lock);
 
 	spin_lock(&rq->lock);
-	if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &rq->fence.flags))
+	if (!i915_request_signaled(rq))
 		dma_fence_signal_locked(&rq->fence);
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags))
 		intel_engine_cancel_signaling(rq);
@@ -342,6 +343,13 @@ static void move_to_timeline(struct i915_request *request,
 	spin_unlock(&request->timeline->lock);
 }
 
+static u32 next_global_seqno(struct i915_timeline *tl)
+{
+	if (!++tl->seqno)
+		++tl->seqno;
+	return tl->seqno;
+}
+
 void __i915_request_submit(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
@@ -358,7 +366,7 @@ void __i915_request_submit(struct i915_request *request)
 
 	GEM_BUG_ON(request->global_seqno);
 
-	seqno = timeline_get_seqno(&engine->timeline);
+	seqno = next_global_seqno(&engine->timeline);
 	GEM_BUG_ON(!seqno);
 	GEM_BUG_ON(intel_engine_signaled(engine, seqno));