Merge tag 'drm-intel-fixes-2023-01-12' of...

Merge tag 'drm-intel-fixes-2023-01-12' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes

- Reserve enough fence slot for i915_vma_unbind_vsync (Nirmoy)
- Fix potential use after free (Rob Clark)
- Reset engines twice in case of reset failure (Chris)
- Use multi-cast registers for SVG Unit registers (Gustavo)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Y8AbHelGeXc5eQ8U@intel.com

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1688,6 +1688,10 @@ void i915_gem_init__contexts(struct drm_i915_private *i915)
 	init_contexts(&i915->gem.contexts);
 }
 
+/*
+ * Note that this implicitly consumes the ctx reference, by placing
+ * the ctx in the context_xa.
+ */
 static void gem_context_register(struct i915_gem_context *ctx,
 				 struct drm_i915_file_private *fpriv,
 				 u32 id)
@@ -1703,10 +1707,6 @@ static void gem_context_register(struct i915_gem_context *ctx,
 	snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
 		 current->comm, pid_nr(ctx->pid));
 
-	/* And finally expose ourselves to userspace via the idr */
-	old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
-	WARN_ON(old);
-
 	spin_lock(&ctx->client->ctx_lock);
 	list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list);
 	spin_unlock(&ctx->client->ctx_lock);
@@ -1714,6 +1714,10 @@ static void gem_context_register(struct i915_gem_context *ctx,
 	spin_lock(&i915->gem.contexts.lock);
 	list_add_tail(&ctx->link, &i915->gem.contexts.list);
 	spin_unlock(&i915->gem.contexts.lock);
+
+	/* And finally expose ourselves to userspace via the idr */
+	old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
+	WARN_ON(old);
 }
 
 int i915_gem_context_open(struct drm_i915_private *i915,
@@ -2199,14 +2203,22 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv,
 	if (IS_ERR(ctx))
 		return ctx;
 
+	/*
+	 * One for the xarray and one for the caller.  We need to grab
+	 * the reference *prior* to making the ctx visble to userspace
+	 * in gem_context_register(), as at any point after that
+	 * userspace can try to race us with another thread destroying
+	 * the context under our feet.
+	 */
+	i915_gem_context_get(ctx);
+
 	gem_context_register(ctx, file_priv, id);
 
 	old = xa_erase(&file_priv->proto_context_xa, id);
 	GEM_BUG_ON(old != pc);
 	proto_context_close(file_priv->dev_priv, pc);
 
-	/* One for the xarray and one for the caller */
-	return i915_gem_context_get(ctx);
+	return ctx;
 }
 
 struct i915_gem_context *

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

@@ -406,10 +406,10 @@
 #define GEN9_WM_CHICKEN3			_MMIO(0x5588)
 #define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
 
-#define CHICKEN_RASTER_1			_MMIO(0x6204)
+#define CHICKEN_RASTER_1			MCR_REG(0x6204)
 #define   DIS_SF_ROUND_NEAREST_EVEN		REG_BIT(8)
 
-#define CHICKEN_RASTER_2			_MMIO(0x6208)
+#define CHICKEN_RASTER_2			MCR_REG(0x6208)
 #define   TBIMR_FAST_CLIP			REG_BIT(5)
 
 #define VFLSKPD					MCR_REG(0x62a8)

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

@@ -278,6 +278,7 @@ static int ilk_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask,
 static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 {
 	struct intel_uncore *uncore = gt->uncore;
+	int loops = 2;
 	int err;
 
 	/*
@@ -285,18 +286,39 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 	 * for fifo space for the write or forcewake the chip for
 	 * the read
 	 */
-	intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
+	do {
+		intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
 
-	/* Wait for the device to ack the reset requests */
-	err = __intel_wait_for_register_fw(uncore,
-					   GEN6_GDRST, hw_domain_mask, 0,
-					   500, 0,
-					   NULL);
+		/*
+		 * Wait for the device to ack the reset requests.
+		 *
+		 * On some platforms, e.g. Jasperlake, we see that the
+		 * engine register state is not cleared until shortly after
+		 * GDRST reports completion, causing a failure as we try
+		 * to immediately resume while the internal state is still
+		 * in flux. If we immediately repeat the reset, the second
+		 * reset appears to serialise with the first, and since
+		 * it is a no-op, the registers should retain their reset
+		 * value. However, there is still a concern that upon
+		 * leaving the second reset, the internal engine state
+		 * is still in flux and not ready for resuming.
+		 */
+		err = __intel_wait_for_register_fw(uncore, GEN6_GDRST,
+						   hw_domain_mask, 0,
+						   2000, 0,
+						   NULL);
+	} while (err == 0 && --loops);
 	if (err)
 		GT_TRACE(gt,
 			 "Wait for 0x%08x engines reset failed\n",
 			 hw_domain_mask);
 
+	/*
+	 * As we have observed that the engine state is still volatile
+	 * after GDRST is acked, impose a small delay to let everything settle.
+	 */
+	udelay(50);
+
 	return err;
 }
 

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

@@ -645,7 +645,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 				   struct i915_wa_list *wal)
 {
-	wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
+	wa_mcr_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
 	wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
 			     REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
 	wa_mcr_add(wal,
@@ -775,7 +775,7 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
 		wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000);
 
 	/* Wa_15010599737:dg2 */
-	wa_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+	wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
 }
 
 static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,

drivers/gpu/drm/i915/i915_vma.c

@@ -2116,7 +2116,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm)
 	if (!obj->mm.rsgt)
 		return -EBUSY;
 
-	err = dma_resv_reserve_fences(obj->base.resv, 1);
+	err = dma_resv_reserve_fences(obj->base.resv, 2);
 	if (err)
 		return -EBUSY;