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

Author: airlied

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

@@ -52,33 +52,41 @@ 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,
 			      &mode_reg) != 1) {
 		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;
 	}
 
@@ -2522,20 +2532,19 @@ 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);
 }
 
 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)];