sync code with last improvements from OpenBSD

sys/dev/pci/drm/drm_aperture.c

@@ -32,17 +32,13 @@
  *
  *	static int remove_conflicting_framebuffers(struct pci_dev *pdev)
  *	{
- *		bool primary = false;
  *		resource_size_t base, size;
  *		int ret;
  *
  *		base = pci_resource_start(pdev, 0);
  *		size = pci_resource_len(pdev, 0);
- *	#ifdef CONFIG_X86
- *		primary = pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
- *	#endif
  *
- *		return drm_aperture_remove_conflicting_framebuffers(base, size, primary,
+ *		return drm_aperture_remove_conflicting_framebuffers(base, size,
  *		                                                    &example_driver);
  *	}
  *
@@ -165,7 +161,6 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware);
  * drm_aperture_remove_conflicting_framebuffers - remove existing framebuffers in the given range
  * @base: the aperture's base address in physical memory
  * @size: aperture size in bytes
- * @primary: also kick vga16fb if present
  * @req_driver: requesting DRM driver
  *
  * This function removes graphics device drivers which use the memory range described by
@@ -175,9 +170,9 @@ EXPORT_SYMBOL(devm_aperture_acquire_from_firmware);
  * 0 on success, or a negative errno code otherwise
  */
 int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size,
-						 bool primary, const struct drm_driver *req_driver)
+						 const struct drm_driver *req_driver)
 {
-	return aperture_remove_conflicting_devices(base, size, primary, req_driver->name);
+	return aperture_remove_conflicting_devices(base, size, false, req_driver->name);
 }
 EXPORT_SYMBOL(drm_aperture_remove_conflicting_framebuffers);
 

sys/dev/pci/drm/i915/gt/gen8_engine_cs.c

@@ -165,14 +165,60 @@ static u32 preparser_disable(bool state)
 	return MI_ARB_CHECK | 1 << 8 | state;
 }
 
-u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg)
+static i915_reg_t gen12_get_aux_inv_reg(struct intel_engine_cs *engine)
 {
-	u32 gsi_offset = gt->uncore->gsi_offset;
+	switch (engine->id) {
+	case RCS0:
+		return GEN12_CCS_AUX_INV;
+	case BCS0:
+		return GEN12_BCS0_AUX_INV;
+	case VCS0:
+		return GEN12_VD0_AUX_INV;
+	case VCS2:
+		return GEN12_VD2_AUX_INV;
+	case VECS0:
+		return GEN12_VE0_AUX_INV;
+	case CCS0:
+		return GEN12_CCS0_AUX_INV;
+	default:
+		return INVALID_MMIO_REG;
+	}
+}
+
+static bool gen12_needs_ccs_aux_inv(struct intel_engine_cs *engine)
+{
+	i915_reg_t reg = gen12_get_aux_inv_reg(engine);
+
+	if (IS_PONTEVECCHIO(engine->i915))
+		return false;
+
+	/*
+	 * So far platforms supported by i915 having flat ccs do not require
+	 * AUX invalidation. Check also whether the engine requires it.
+	 */
+	return i915_mmio_reg_valid(reg) && !HAS_FLAT_CCS(engine->i915);
+}
+
+u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs)
+{
+	i915_reg_t inv_reg = gen12_get_aux_inv_reg(engine);
+	u32 gsi_offset = engine->gt->uncore->gsi_offset;
+
+	if (!gen12_needs_ccs_aux_inv(engine))
+		return cs;
 
 	*cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN;
 	*cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset;
 	*cs++ = AUX_INV;
-	*cs++ = MI_NOOP;
+
+	*cs++ = MI_SEMAPHORE_WAIT_TOKEN |
+		MI_SEMAPHORE_REGISTER_POLL |
+		MI_SEMAPHORE_POLL |
+		MI_SEMAPHORE_SAD_EQ_SDD;
+	*cs++ = 0;
+	*cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset;
+	*cs++ = 0;
+	*cs++ = 0;
 
 	return cs;
 }
@@ -181,7 +227,11 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 {
 	struct intel_engine_cs *engine = rq->engine;
 
-	if (mode & EMIT_FLUSH) {
+	/*
+	 * On Aux CCS platforms the invalidation of the Aux
+	 * table requires quiescing memory traffic beforehand
+	 */
+	if (mode & EMIT_FLUSH || gen12_needs_ccs_aux_inv(engine)) {
 		u32 flags = 0;
 		u32 *cs;
 
@@ -236,10 +286,9 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 		else if (engine->class == COMPUTE_CLASS)
 			flags &= ~PIPE_CONTROL_3D_ENGINE_FLAGS;
 
-		if (!HAS_FLAT_CCS(rq->engine->i915))
-			count = 8 + 4;
-		else
-			count = 8;
+		count = 8;
+		if (gen12_needs_ccs_aux_inv(rq->engine))
+			count += 8;
 
 		cs = intel_ring_begin(rq, count);
 		if (IS_ERR(cs))
@@ -254,11 +303,7 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 		cs = gen8_emit_pipe_control(cs, flags, LRC_PPHWSP_SCRATCH_ADDR);
 
-		if (!HAS_FLAT_CCS(rq->engine->i915)) {
-			/* hsdes: 1809175790 */
-			cs = gen12_emit_aux_table_inv(rq->engine->gt, cs,
-						      GEN12_CCS_AUX_INV);
-		}
+		cs = gen12_emit_aux_table_inv(engine, cs);
 
 		*cs++ = preparser_disable(false);
 		intel_ring_advance(rq, cs);
@@ -269,21 +314,14 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode)
 
 int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 {
-	intel_engine_mask_t aux_inv = 0;
-	u32 cmd, *cs;
+	u32 cmd = 4;
+	u32 *cs;
 
-	cmd = 4;
 	if (mode & EMIT_INVALIDATE) {
 		cmd += 2;
 
-		if (!HAS_FLAT_CCS(rq->engine->i915) &&
-		    (rq->engine->class == VIDEO_DECODE_CLASS ||
-		     rq->engine->class == VIDEO_ENHANCEMENT_CLASS)) {
-			aux_inv = rq->engine->mask &
-				~GENMASK(_BCS(I915_MAX_BCS - 1), BCS0);
-			if (aux_inv)
-				cmd += 4;
-		}
+		if (gen12_needs_ccs_aux_inv(rq->engine))
+			cmd += 8;
 	}
 
 	cs = intel_ring_begin(rq, cmd);
@@ -314,14 +352,7 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode)
 	*cs++ = 0; /* upper addr */
 	*cs++ = 0; /* value */
 
-	if (aux_inv) { /* hsdes: 1809175790 */
-		if (rq->engine->class == VIDEO_DECODE_CLASS)
-			cs = gen12_emit_aux_table_inv(rq->engine->gt,
-						      cs, GEN12_VD0_AUX_INV);
-		else
-			cs = gen12_emit_aux_table_inv(rq->engine->gt,
-						      cs, GEN12_VE0_AUX_INV);
-	}
+	cs = gen12_emit_aux_table_inv(rq->engine, cs);
 
 	if (mode & EMIT_INVALIDATE)
 		*cs++ = preparser_disable(false);

sys/dev/pci/drm/i915/gt/gen8_engine_cs.h

@@ -13,6 +13,7 @@
 #include "intel_gt_regs.h"
 #include "intel_gpu_commands.h"
 
+struct intel_engine_cs;
 struct intel_gt;
 struct i915_request;
 
@@ -46,7 +47,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
 u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
 u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs);
 
-u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg);
+u32 *gen12_emit_aux_table_inv(struct intel_engine_cs *engine, u32 *cs);
 
 static inline u32 *
 __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset)

sys/dev/pci/drm/i915/gt/intel_gpu_commands.h

@@ -120,6 +120,7 @@
 #define   MI_SEMAPHORE_TARGET(engine)	((engine)<<15)
 #define MI_SEMAPHORE_WAIT	MI_INSTR(0x1c, 2) /* GEN8+ */
 #define MI_SEMAPHORE_WAIT_TOKEN	MI_INSTR(0x1c, 3) /* GEN12+ */
+#define   MI_SEMAPHORE_REGISTER_POLL	(1 << 16)
 #define   MI_SEMAPHORE_POLL		(1 << 15)
 #define   MI_SEMAPHORE_SAD_GT_SDD	(0 << 12)
 #define   MI_SEMAPHORE_SAD_GTE_SDD	(1 << 12)

sys/dev/pci/drm/i915/gt/intel_lrc.c

@@ -1301,10 +1301,7 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 	    IS_DG2_G11(ce->engine->i915))
 		cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0);
 
-	/* hsdes: 1809175790 */
-	if (!HAS_FLAT_CCS(ce->engine->i915))
-		cs = gen12_emit_aux_table_inv(ce->engine->gt,
-					      cs, GEN12_CCS_AUX_INV);
+	cs = gen12_emit_aux_table_inv(ce->engine, cs);
 
 	/* Wa_16014892111 */
 	if (IS_DG2(ce->engine->i915))
@@ -1327,17 +1324,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs)
 						    PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE,
 						    0);
 
-	/* hsdes: 1809175790 */
-	if (!HAS_FLAT_CCS(ce->engine->i915)) {
-		if (ce->engine->class == VIDEO_DECODE_CLASS)
-			cs = gen12_emit_aux_table_inv(ce->engine->gt,
-						      cs, GEN12_VD0_AUX_INV);
-		else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS)
-			cs = gen12_emit_aux_table_inv(ce->engine->gt,
-						      cs, GEN12_VE0_AUX_INV);
-	}
-
-	return cs;
+	return gen12_emit_aux_table_inv(ce->engine, cs);
 }
 
 static void

sys/dev/pci/drm/i915/i915_driver.c

@@ -603,7 +603,6 @@ static int i915_pcode_init(struct drm_i915_private *i915)
 static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 {
 	struct pci_dev *pdev = dev_priv->drm.pdev;
-	struct pci_dev *root_pdev;
 	int ret;
 
 	if (i915_inject_probe_failure(dev_priv))
@@ -715,17 +714,6 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 
 	intel_bw_init_hw(dev_priv);
 
-	/*
-	 * FIXME: Temporary hammer to avoid freezing the machine on our DGFX
-	 * This should be totally removed when we handle the pci states properly
-	 * on runtime PM and on s2idle cases.
-	 */
-#ifdef notyet
-	root_pdev = pcie_find_root_port(pdev);
-	if (root_pdev)
-		pci_d3cold_disable(root_pdev);
-#endif
-
 	return 0;
 
 err_msi:
@@ -751,16 +739,11 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv)
 	STUB();
 #ifdef notyet
 	struct pci_dev *pdev = dev_priv->drm.pdev;
-	struct pci_dev *root_pdev;
 
 	i915_perf_fini(dev_priv);
 
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
-
-	root_pdev = pcie_find_root_port(pdev);
-	if (root_pdev)
-		pci_d3cold_enable(root_pdev);
 #endif
 }
 
@@ -1785,6 +1768,8 @@ static int intel_runtime_suspend(struct device *kdev)
 {
 	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
 	struct intel_runtime_pm *rpm = &dev_priv->runtime_pm;
+	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
+	struct pci_dev *root_pdev;
 	struct intel_gt *gt;
 	int ret, i;
 
@@ -1834,6 +1819,15 @@ static int intel_runtime_suspend(struct device *kdev)
 		drm_err(&dev_priv->drm,
 			"Unclaimed access detected prior to suspending\n");
 
+	/*
+	 * FIXME: Temporary hammer to avoid freezing the machine on our DGFX
+	 * This should be totally removed when we handle the pci states properly
+	 * on runtime PM.
+	 */
+	root_pdev = pcie_find_root_port(pdev);
+	if (root_pdev)
+		pci_d3cold_disable(root_pdev);
+
 	rpm->suspended = true;
 
 	/*
@@ -1872,6 +1866,8 @@ static int intel_runtime_resume(struct device *kdev)
 {
 	struct drm_i915_private *dev_priv = kdev_to_i915(kdev);
 	struct intel_runtime_pm *rpm = &dev_priv->runtime_pm;
+	struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
+	struct pci_dev *root_pdev;
 	struct intel_gt *gt;
 	int ret, i;
 
@@ -1885,6 +1881,11 @@ static int intel_runtime_resume(struct device *kdev)
 
 	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 	rpm->suspended = false;
+
+	root_pdev = pcie_find_root_port(pdev);
+	if (root_pdev)
+		pci_d3cold_enable(root_pdev);
+
 	if (intel_uncore_unclaimed_mmio(&dev_priv->uncore))
 		drm_dbg(&dev_priv->drm,
 			"Unclaimed access during suspend, bios?\n");

sys/dev/pci/drm/include/drm/display/drm_dp.h

@@ -1525,7 +1525,7 @@ enum drm_dp_phy {
 
 #define DP_BRANCH_OUI_HEADER_SIZE	0xc
 #define DP_RECEIVER_CAP_SIZE		0xf
-#define DP_DSC_RECEIVER_CAP_SIZE        0xf
+#define DP_DSC_RECEIVER_CAP_SIZE        0x10 /* DSC Capabilities 0x60 through 0x6F */
 #define EDP_PSR_RECEIVER_CAP_SIZE	2
 #define EDP_DISPLAY_CTL_CAP_SIZE	3
 #define DP_LTTPR_COMMON_CAP_SIZE	8

sys/dev/pci/drm/include/drm/drm_aperture.h

@@ -13,14 +13,13 @@ int devm_aperture_acquire_from_firmware(struct drm_device *dev, resource_size_t
 					resource_size_t size);
 
 int drm_aperture_remove_conflicting_framebuffers(resource_size_t base, resource_size_t size,
-						 bool primary, const struct drm_driver *req_driver);
+						 const struct drm_driver *req_driver);
 
 int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
 						     const struct drm_driver *req_driver);
 
 /**
  * drm_aperture_remove_framebuffers - remove all existing framebuffers
- * @primary: also kick vga16fb if present
  * @req_driver: requesting DRM driver
  *
  * This function removes all graphics device drivers. Use this function on systems
@@ -30,9 +29,9 @@ int drm_aperture_remove_conflicting_pci_framebuffers(struct pci_dev *pdev,
  * 0 on success, or a negative errno code otherwise
  */
 static inline int
-drm_aperture_remove_framebuffers(bool primary, const struct drm_driver *req_driver)
+drm_aperture_remove_framebuffers(const struct drm_driver *req_driver)
 {
-	return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1, primary,
+	return drm_aperture_remove_conflicting_framebuffers(0, (resource_size_t)-1,
 							    req_driver);
 }