Merge tag 'drm-intel-next-fixes-2020-10-22' of...

Merge tag 'drm-intel-next-fixes-2020-10-22' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

- Tweak initia DPCD backlight.enabled value (Sean)
- Initialize reserved MOCS indices (Ayaz)
- Mark initial fb obj as WT on eLLC machines to avoid rcu lockup (Ville)
- Support parsing of oversize batches (Chris)
- Delay execlists processing for TGL (Chris)
- Use the active reference on the vma during error capture (Chris)
- Widen CSB pointer (Chris)
- Wait for CSB entries on TGL (Chris)
- Fix unwind for scratch page allocation (Chris)
- Exclude low patches of stolen memory (Chris)
- Force VT'd workarounds when running as a guest OS (Chris)
- Drop runtime-pm assert from vpgu io accessors (Chris)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20201022205613.GA3469192@intel.com

drivers/gpu/drm/i915/Kconfig.debug

@@ -153,6 +153,7 @@ config DRM_I915_SELFTEST
 	select DRM_EXPORT_FOR_TESTS if m
 	select FAULT_INJECTION
 	select PRIME_NUMBERS
+	select CRC32
 	help
 	  Choose this option to allow the driver to perform selftests upon
 	  loading; also requires the i915.selftest=1 module parameter. To

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

@@ -3434,6 +3434,14 @@ initial_plane_vma(struct drm_i915_private *i915,
 	if (IS_ERR(obj))
 		return NULL;
 
+	/*
+	 * Mark it WT ahead of time to avoid changing the
+	 * cache_level during fbdev initialization. The
+	 * unbind there would get stuck waiting for rcu.
+	 */
+	i915_gem_object_set_cache_coherency(obj, HAS_WT(i915) ?
+					    I915_CACHE_WT : I915_CACHE_NONE);
+
 	switch (plane_config->tiling) {
 	case I915_TILING_NONE:
 		break;

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

@@ -52,17 +52,11 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 	}
 }
 
-/*
- * Read the current backlight value from DPCD register(s) based
- * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported
- */
-static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
+static bool intel_dp_aux_backlight_dpcd_mode(struct intel_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
-	u8 read_val[2] = { 0x0 };
 	u8 mode_reg;
-	u16 level = 0;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_EDP_BACKLIGHT_MODE_SET_REGISTER,
@@ -70,15 +64,29 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 		drm_dbg_kms(&i915->drm,
 			    "Failed to read the DPCD register 0x%x\n",
 			    DP_EDP_BACKLIGHT_MODE_SET_REGISTER);
-		return 0;
+		return false;
 	}
 
+	return (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) ==
+	       DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD;
+}
+
+/*
+ * Read the current backlight value from DPCD register(s) based
+ * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported
+ */
+static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
+{
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+	u8 read_val[2] = { 0x0 };
+	u16 level = 0;
+
 	/*
 	 * If we're not in DPCD control mode yet, the programmed brightness
 	 * value is meaningless and we should assume max brightness
 	 */
-	if ((mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) !=
-	    DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD)
+	if (!intel_dp_aux_backlight_dpcd_mode(connector))
 		return connector->panel.backlight.max;
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
@@ -319,7 +327,8 @@ static int intel_dp_aux_setup_backlight(struct intel_connector *connector,
 
 	panel->backlight.min = 0;
 	panel->backlight.level = intel_dp_aux_get_backlight(connector);
-	panel->backlight.enabled = panel->backlight.level != 0;
+	panel->backlight.enabled = intel_dp_aux_backlight_dpcd_mode(connector) &&
+				   panel->backlight.level != 0;
 
 	return 0;
 }

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -287,8 +287,8 @@ struct i915_execbuffer {
 	u64 invalid_flags; /** Set of execobj.flags that are invalid */
 	u32 context_flags; /** Set of execobj.flags to insert from the ctx */
 
+	u64 batch_len; /** Length of batch within object */
 	u32 batch_start_offset; /** Location within object of batch */
-	u32 batch_len; /** Length of batch within object */
 	u32 batch_flags; /** Flags composed for emit_bb_start() */
 	struct intel_gt_buffer_pool_node *batch_pool; /** pool node for batch buffer */
 
@@ -871,6 +871,10 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 
 	if (eb->batch_len == 0)
 		eb->batch_len = eb->batch->vma->size - eb->batch_start_offset;
+	if (unlikely(eb->batch_len == 0)) { /* impossible! */
+		drm_dbg(&i915->drm, "Invalid batch length\n");
+		return -EINVAL;
+	}
 
 	return 0;
 
@@ -2424,7 +2428,7 @@ static int eb_parse(struct i915_execbuffer *eb)
 	struct drm_i915_private *i915 = eb->i915;
 	struct intel_gt_buffer_pool_node *pool = eb->batch_pool;
 	struct i915_vma *shadow, *trampoline, *batch;
-	unsigned int len;
+	unsigned long len;
 	int err;
 
 	if (!eb_use_cmdparser(eb)) {
@@ -2449,6 +2453,8 @@ static int eb_parse(struct i915_execbuffer *eb)
 	} else {
 		len += I915_CMD_PARSER_TRAMPOLINE_SIZE;
 	}
+	if (unlikely(len < eb->batch_len)) /* last paranoid check of overflow */
+		return -EINVAL;
 
 	if (!pool) {
 		pool = intel_gt_get_buffer_pool(eb->engine->gt, len);

drivers/gpu/drm/i915/gem/i915_gem_stolen.c

@@ -53,8 +53,10 @@ int i915_gem_stolen_insert_node(struct drm_i915_private *i915,
 				struct drm_mm_node *node, u64 size,
 				unsigned alignment)
 {
-	return i915_gem_stolen_insert_node_in_range(i915, node, size,
-						    alignment, 0, U64_MAX);
+	return i915_gem_stolen_insert_node_in_range(i915, node,
+						    size, alignment,
+						    I915_GEM_STOLEN_BIAS,
+						    U64_MAX);
 }
 
 void i915_gem_stolen_remove_node(struct drm_i915_private *i915,

drivers/gpu/drm/i915/gem/i915_gem_stolen.h

@@ -30,4 +30,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 					       resource_size_t stolen_offset,
 					       resource_size_t size);
 
+#define I915_GEM_STOLEN_BIAS SZ_128K
+
 #endif /* __I915_GEM_STOLEN_H__ */

drivers/gpu/drm/i915/gt/gen6_ppgtt.c

@@ -239,18 +239,24 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 			       I915_CACHE_NONE, PTE_READ_ONLY);
 
 	vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
-	if (IS_ERR(vm->scratch[1]))
-		return PTR_ERR(vm->scratch[1]);
+	if (IS_ERR(vm->scratch[1])) {
+		ret = PTR_ERR(vm->scratch[1]);
+		goto err_scratch0;
+	}
 
 	ret = pin_pt_dma(vm, vm->scratch[1]);
-	if (ret) {
-		i915_gem_object_put(vm->scratch[1]);
-		return ret;
-	}
+	if (ret)
+		goto err_scratch1;
 
 	fill32_px(vm->scratch[1], vm->scratch[0]->encode);
 
 	return 0;
+
+err_scratch1:
+	i915_gem_object_put(vm->scratch[1]);
+err_scratch0:
+	i915_gem_object_put(vm->scratch[0]);
+	return ret;
 }
 
 static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt)

drivers/gpu/drm/i915/gt/gen8_ppgtt.c

@@ -604,7 +604,8 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 	return 0;
 
 free_scratch:
-	free_scratch(vm);
+	while (i--)
+		i915_gem_object_put(vm->scratch[i]);
 	return -ENOMEM;
 }
 

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -278,7 +278,7 @@ struct intel_engine_execlists {
 	 *
 	 * Note these register may be either mmio or HWSP shadow.
 	 */
-	u32 *csb_status;
+	u64 *csb_status;
 
 	/**
 	 * @csb_size: context status buffer FIFO size

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -1140,9 +1140,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 
 			/* Check in case we rollback so far we wrap [size/2] */
 			if (intel_ring_direction(rq->ring,
-						 intel_ring_wrap(rq->ring,
-								 rq->tail),
-						 rq->ring->tail) > 0)
+						 rq->tail,
+						 rq->ring->tail + 8) > 0)
 				rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE;
 
 			active = rq;
@@ -2464,7 +2463,7 @@ cancel_port_requests(struct intel_engine_execlists * const execlists)
 }
 
 static inline void
-invalidate_csb_entries(const u32 *first, const u32 *last)
+invalidate_csb_entries(const u64 *first, const u64 *last)
 {
 	clflush((void *)first);
 	clflush((void *)last);
@@ -2496,14 +2495,25 @@ invalidate_csb_entries(const u32 *first, const u32 *last)
  *     bits 47-57: sw context id of the lrc the GT switched away from
  *     bits 58-63: sw counter of the lrc the GT switched away from
  */
-static inline bool
-gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
-{
-	u32 lower_dw = csb[0];
-	u32 upper_dw = csb[1];
-	bool ctx_to_valid = GEN12_CSB_CTX_VALID(lower_dw);
-	bool ctx_away_valid = GEN12_CSB_CTX_VALID(upper_dw);
-	bool new_queue = lower_dw & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE;
+static inline bool gen12_csb_parse(const u64 *csb)
+{
+	bool ctx_away_valid;
+	bool new_queue;
+	u64 entry;
+
+	/* HSD#22011248461 */
+	entry = READ_ONCE(*csb);
+	if (unlikely(entry == -1)) {
+		preempt_disable();
+		if (wait_for_atomic_us((entry = READ_ONCE(*csb)) != -1, 50))
+			GEM_WARN_ON("50us CSB timeout");
+		preempt_enable();
+	}
+	WRITE_ONCE(*(u64 *)csb, -1);
+
+	ctx_away_valid = GEN12_CSB_CTX_VALID(upper_32_bits(entry));
+	new_queue =
+		lower_32_bits(entry) & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE;
 
 	/*
 	 * The context switch detail is not guaranteed to be 5 when a preemption
@@ -2513,7 +2523,7 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	 * would require some extra handling, but we don't support that.
 	 */
 	if (!ctx_away_valid || new_queue) {
-		GEM_BUG_ON(!ctx_to_valid);
+		GEM_BUG_ON(!GEN12_CSB_CTX_VALID(lower_32_bits(entry)));
 		return true;
 	}
 
@@ -2522,12 +2532,11 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 	 * context switch on an unsuccessful wait instruction since we always
 	 * use polling mode.
 	 */
-	GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_dw));
+	GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_32_bits(entry)));
 	return false;
 }
 
-static inline bool
-gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
+static inline bool gen8_csb_parse(const u64 *csb)
 {
 	return *csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED);
 }
@@ -2535,7 +2544,7 @@ gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb)
 static void process_csb(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
-	const u32 * const buf = execlists->csb_status;
+	const u64 * const buf = execlists->csb_status;
 	const u8 num_entries = execlists->csb_size;
 	u8 head, tail;
 
@@ -2616,12 +2625,14 @@ static void process_csb(struct intel_engine_cs *engine)
 		 */
 
 		ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n",
-			     head, buf[2 * head + 0], buf[2 * head + 1]);
+			     head,
+			     upper_32_bits(buf[head]),
+			     lower_32_bits(buf[head]));
 
 		if (INTEL_GEN(engine->i915) >= 12)
-			promote = gen12_csb_parse(execlists, buf + 2 * head);
+			promote = gen12_csb_parse(buf + head);
 		else
-			promote = gen8_csb_parse(execlists, buf + 2 * head);
+			promote = gen8_csb_parse(buf + head);
 		if (promote) {
 			struct i915_request * const *old = execlists->active;
 
@@ -2649,6 +2660,9 @@ static void process_csb(struct intel_engine_cs *engine)
 			smp_wmb(); /* complete the seqlock */
 			WRITE_ONCE(execlists->active, execlists->inflight);
 
+			/* XXX Magic delay for tgl */
+			ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR);
+
 			WRITE_ONCE(execlists->pending[0], NULL);
 		} else {
 			if (GEM_WARN_ON(!*execlists->active)) {
@@ -4005,6 +4019,8 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 	WRITE_ONCE(*execlists->csb_write, reset_value);
 	wmb(); /* Make sure this is visible to HW (paranoia?) */
 
+	/* Check that the GPU does indeed update the CSB entries! */
+	memset(execlists->csb_status, -1, (reset_value + 1) * sizeof(u64));
 	invalidate_csb_entries(&execlists->csb_status[0],
 			       &execlists->csb_status[reset_value]);
 
@@ -5157,7 +5173,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 	}
 
 	execlists->csb_status =
-		&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
+		(u64 *)&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX];
 
 	execlists->csb_write =
 		&engine->status_page.addr[intel_hws_csb_write_index(i915)];

drivers/gpu/drm/i915/gt/intel_mocs.c

@@ -234,11 +234,17 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = {
 		   L3_1_UC)
 
 static const struct drm_i915_mocs_entry tgl_mocs_table[] = {
-	/* Base - Error (Reserved for Non-Use) */
-	MOCS_ENTRY(0, 0x0, 0x0),
-	/* Base - Reserved */
-	MOCS_ENTRY(1, 0x0, 0x0),
-
+	/*
+	 * NOTE:
+	 * Reserved and unspecified MOCS indices have been set to (L3 + LCC).
+	 * These reserved entries should never be used, they may be changed
+	 * to low performant variants with better coherency in the future if
+	 * more entries are needed. We are programming index I915_MOCS_PTE(1)
+	 * only, __init_mocs_table() take care to program unused index with
+	 * this entry.
+	 */
+	MOCS_ENTRY(1, LE_3_WB | LE_TC_1_LLC | LE_LRUM(3),
+		   L3_3_WB),
 	GEN11_MOCS_ENTRIES,
 
 	/* Implicitly enable L1 - HDC:L1 + L3 + LLC */

drivers/gpu/drm/i915/gt/selftest_reset.c

@@ -3,9 +3,203 @@
  * Copyright © 2018 Intel Corporation
  */
 
+#include <linux/crc32.h>
+
+#include "gem/i915_gem_stolen.h"
+
+#include "i915_memcpy.h"
 #include "i915_selftest.h"
 #include "selftests/igt_reset.h"
 #include "selftests/igt_atomic.h"
+#include "selftests/igt_spinner.h"
+
+static int
+__igt_reset_stolen(struct intel_gt *gt,
+		   intel_engine_mask_t mask,
+		   const char *msg)
+{
+	struct i915_ggtt *ggtt = &gt->i915->ggtt;
+	const struct resource *dsm = &gt->i915->dsm;
+	resource_size_t num_pages, page;
+	struct intel_engine_cs *engine;
+	intel_wakeref_t wakeref;
+	enum intel_engine_id id;
+	struct igt_spinner spin;
+	long max, count;
+	void *tmp;
+	u32 *crc;
+	int err;
+
+	if (!drm_mm_node_allocated(&ggtt->error_capture))
+		return 0;
+
+	num_pages = resource_size(dsm) >> PAGE_SHIFT;
+	if (!num_pages)
+		return 0;
+
+	crc = kmalloc_array(num_pages, sizeof(u32), GFP_KERNEL);
+	if (!crc)
+		return -ENOMEM;
+
+	tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!tmp) {
+		err = -ENOMEM;
+		goto err_crc;
+	}
+
+	igt_global_reset_lock(gt);
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+
+	err = igt_spinner_init(&spin, gt);
+	if (err)
+		goto err_lock;
+
+	for_each_engine(engine, gt, id) {
+		struct intel_context *ce;
+		struct i915_request *rq;
+
+		if (!(mask & engine->mask))
+			continue;
+
+		if (!intel_engine_can_store_dword(engine))
+			continue;
+
+		ce = intel_context_create(engine);
+		if (IS_ERR(ce)) {
+			err = PTR_ERR(ce);
+			goto err_spin;
+		}
+		rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK);
+		intel_context_put(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_spin;
+		}
+		i915_request_add(rq);
+	}
+
+	for (page = 0; page < num_pages; page++) {
+		dma_addr_t dma = (dma_addr_t)dsm->start + (page << PAGE_SHIFT);
+		void __iomem *s;
+		void *in;
+
+		ggtt->vm.insert_page(&ggtt->vm, dma,
+				     ggtt->error_capture.start,
+				     I915_CACHE_NONE, 0);
+		mb();
+
+		s = io_mapping_map_wc(&ggtt->iomap,
+				      ggtt->error_capture.start,
+				      PAGE_SIZE);
+
+		if (!__drm_mm_interval_first(&gt->i915->mm.stolen,
+					     page << PAGE_SHIFT,
+					     ((page + 1) << PAGE_SHIFT) - 1))
+			memset32(s, STACK_MAGIC, PAGE_SIZE / sizeof(u32));
+
+		in = s;
+		if (i915_memcpy_from_wc(tmp, s, PAGE_SIZE))
+			in = tmp;
+		crc[page] = crc32_le(0, in, PAGE_SIZE);
+
+		io_mapping_unmap(s);
+	}
+	mb();
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE);
+
+	if (mask == ALL_ENGINES) {
+		intel_gt_reset(gt, mask, NULL);
+	} else {
+		for_each_engine(engine, gt, id) {
+			if (mask & engine->mask)
+				intel_engine_reset(engine, NULL);
+		}
+	}
+
+	max = -1;
+	count = 0;
+	for (page = 0; page < num_pages; page++) {
+		dma_addr_t dma = (dma_addr_t)dsm->start + (page << PAGE_SHIFT);
+		void __iomem *s;
+		void *in;
+		u32 x;
+
+		ggtt->vm.insert_page(&ggtt->vm, dma,
+				     ggtt->error_capture.start,
+				     I915_CACHE_NONE, 0);
+		mb();
+
+		s = io_mapping_map_wc(&ggtt->iomap,
+				      ggtt->error_capture.start,
+				      PAGE_SIZE);
+
+		in = s;
+		if (i915_memcpy_from_wc(tmp, s, PAGE_SIZE))
+			in = tmp;
+		x = crc32_le(0, in, PAGE_SIZE);
+
+		if (x != crc[page] &&
+		    !__drm_mm_interval_first(&gt->i915->mm.stolen,
+					     page << PAGE_SHIFT,
+					     ((page + 1) << PAGE_SHIFT) - 1)) {
+			pr_debug("unused stolen page %pa modified by GPU reset\n",
+				 &page);
+			if (count++ == 0)
+				igt_hexdump(in, PAGE_SIZE);
+			max = page;
+		}
+
+		io_mapping_unmap(s);
+	}
+	mb();
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE);
+
+	if (count > 0) {
+		pr_info("%s reset clobbered %ld pages of stolen, last clobber at page %ld\n",
+			msg, count, max);
+	}
+	if (max >= I915_GEM_STOLEN_BIAS >> PAGE_SHIFT) {
+		pr_err("%s reset clobbered unreserved area [above %x] of stolen; may cause severe faults\n",
+		       msg, I915_GEM_STOLEN_BIAS);
+		err = -EINVAL;
+	}
+
+err_spin:
+	igt_spinner_fini(&spin);
+
+err_lock:
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
+	igt_global_reset_unlock(gt);
+
+	kfree(tmp);
+err_crc:
+	kfree(crc);
+	return err;
+}
+
+static int igt_reset_device_stolen(void *arg)
+{
+	return __igt_reset_stolen(arg, ALL_ENGINES, "device");
+}
+
+static int igt_reset_engines_stolen(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err;
+
+	if (!intel_has_reset_engine(gt))
+		return 0;
+
+	for_each_engine(engine, gt, id) {
+		err = __igt_reset_stolen(gt, engine->mask, engine->name);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
 
 static int igt_global_reset(void *arg)
 {
@@ -164,6 +358,8 @@ int intel_reset_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_global_reset), /* attempt to recover GPU first */
+		SUBTEST(igt_reset_device_stolen),
+		SUBTEST(igt_reset_engines_stolen),
 		SUBTEST(igt_wedged_reset),
 		SUBTEST(igt_atomic_reset),
 		SUBTEST(igt_atomic_engine_reset),

drivers/gpu/drm/i915/i915_drv.h

@@ -33,6 +33,8 @@
 #include <uapi/drm/i915_drm.h>
 #include <uapi/drm/drm_fourcc.h>
 
+#include <asm/hypervisor.h>
+
 #include <linux/io-mapping.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
@@ -1760,7 +1762,9 @@ static inline bool intel_vtd_active(void)
 	if (intel_iommu_gfx_mapped)
 		return true;
 #endif
-	return false;
+
+	/* Running as a guest, we assume the host is enforcing VT'd */
+	return !hypervisor_is_type(X86_HYPER_NATIVE);
 }
 
 static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)

drivers/gpu/drm/i915/i915_gpu_error.c

@@ -1312,7 +1312,7 @@ capture_vma(struct intel_engine_capture_vma *next,
 	}
 
 	strcpy(c->name, name);
-	c->vma = i915_vma_get(vma);
+	c->vma = vma; /* reference held while active */
 
 	c->next = next;
 	return c;
@@ -1402,7 +1402,6 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee,
 						 compress));
 
 		i915_active_release(&vma->active);
-		i915_vma_put(vma);
 
 		capture = this->next;
 		kfree(this);

drivers/gpu/drm/i915/intel_uncore.c

@@ -1209,6 +1209,18 @@ unclaimed_reg_debug(struct intel_uncore *uncore,
 		spin_unlock(&uncore->debug->lock);
 }
 
+#define __vgpu_read(x) \
+static u##x \
+vgpu_read##x(struct intel_uncore *uncore, i915_reg_t reg, bool trace) { \
+	u##x val = __raw_uncore_read##x(uncore, reg); \
+	trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \
+	return val; \
+}
+__vgpu_read(8)
+__vgpu_read(16)
+__vgpu_read(32)
+__vgpu_read(64)
+
 #define GEN2_READ_HEADER(x) \
 	u##x val = 0; \
 	assert_rpm_wakelock_held(uncore->rpm);
@@ -1414,6 +1426,16 @@ __gen_reg_write_funcs(gen8);
 #undef GEN6_WRITE_FOOTER
 #undef GEN6_WRITE_HEADER
 
+#define __vgpu_write(x) \
+static void \
+vgpu_write##x(struct intel_uncore *uncore, i915_reg_t reg, u##x val, bool trace) { \
+	trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \
+	__raw_uncore_write##x(uncore, reg, val); \
+}
+__vgpu_write(8)
+__vgpu_write(16)
+__vgpu_write(32)
+
 #define ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, x) \
 do { \
 	(uncore)->funcs.mmio_writeb = x##_write8; \
@@ -1735,7 +1757,10 @@ static void uncore_raw_init(struct intel_uncore *uncore)
 {
 	GEM_BUG_ON(intel_uncore_has_forcewake(uncore));
 
-	if (IS_GEN(uncore->i915, 5)) {
+	if (intel_vgpu_active(uncore->i915)) {
+		ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, vgpu);
+		ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, vgpu);
+	} else if (IS_GEN(uncore->i915, 5)) {
 		ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, gen5);
 		ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, gen5);
 	} else {