1 files changed, 66 insertions, 120 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c
index 8145851ad23d..0c7fe360f873 100644
--- a/drivers/gpu/drm/i915/gt/intel_ggtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <linux/stop_machine.h>
 
+#include <drm/drm_managed.h>
 #include <drm/i915_drm.h>
 #include <drm/intel-gtt.h>
 
@@ -26,13 +27,6 @@
 #include "intel_gtt.h"
 #include "gen8_ppgtt.h"
 
-static inline bool suspend_retains_ptes(struct i915_address_space *vm)
-{
-	return GRAPHICS_VER(vm->i915) >= 8 &&
-		!HAS_LMEM(vm->i915) &&
-		vm->is_ggtt;
-}
-
 static void i915_ggtt_color_adjust(const struct drm_mm_node *node,
 				   unsigned long color,
 				   u64 *start,
@@ -104,23 +98,6 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915)
 	return 0;
 }
 
-/*
- * Return the value of the last GGTT pte cast to an u64, if
- * the system is supposed to retain ptes across resume. 0 otherwise.
- */
-static u64 read_last_pte(struct i915_address_space *vm)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	gen8_pte_t __iomem *ptep;
-
-	if (!suspend_retains_ptes(vm))
-		return 0;
-
-	GEM_BUG_ON(GRAPHICS_VER(vm->i915) < 8);
-	ptep = (typeof(ptep))ggtt->gsm + (ggtt_total_entries(ggtt) - 1);
-	return readq(ptep);
-}
-
 /**
  * i915_ggtt_suspend_vm - Suspend the memory mappings for a GGTT or DPT VM
  * @vm: The VM to suspend the mappings for
@@ -184,10 +161,7 @@ retry:
 		i915_gem_object_unlock(obj);
 	}
 
-	if (!suspend_retains_ptes(vm))
-		vm->clear_range(vm, 0, vm->total);
-	else
-		i915_vm_to_ggtt(vm)->probed_pte = read_last_pte(vm);
+	vm->clear_range(vm, 0, vm->total);
 
 	vm->skip_pte_rewrite = save_skip_rewrite;
 
@@ -196,10 +170,13 @@ retry:
 
 void i915_ggtt_suspend(struct i915_ggtt *ggtt)
 {
+	struct intel_gt *gt;
+
 	i915_ggtt_suspend_vm(&ggtt->vm);
 	ggtt->invalidate(ggtt);
 
-	intel_gt_check_and_clear_faults(ggtt->vm.gt);
+	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
+		intel_gt_check_and_clear_faults(gt);
 }
 
 void gen6_ggtt_invalidate(struct i915_ggtt *ggtt)
@@ -225,16 +202,21 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
 
 static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 {
-	struct intel_uncore *uncore = ggtt->vm.gt->uncore;
 	struct drm_i915_private *i915 = ggtt->vm.i915;
 
 	gen8_ggtt_invalidate(ggtt);
 
-	if (GRAPHICS_VER(i915) >= 12)
-		intel_uncore_write_fw(uncore, GEN12_GUC_TLB_INV_CR,
-				      GEN12_GUC_TLB_INV_CR_INVALIDATE);
-	else
-		intel_uncore_write_fw(uncore, GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+	if (GRAPHICS_VER(i915) >= 12) {
+		struct intel_gt *gt;
+
+		list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
+			intel_uncore_write_fw(gt->uncore,
+					      GEN12_GUC_TLB_INV_CR,
+					      GEN12_GUC_TLB_INV_CR_INVALIDATE);
+	} else {
+		intel_uncore_write_fw(ggtt->vm.gt->uncore,
+				      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+	}
 }
 
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
@@ -287,8 +269,11 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	 */
 
 	gte = (gen8_pte_t __iomem *)ggtt->gsm;
-	gte += vma_res->start / I915_GTT_PAGE_SIZE;
-	end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
+	gte += (vma_res->start - vma_res->guard) / I915_GTT_PAGE_SIZE;
+	end = gte + vma_res->guard / I915_GTT_PAGE_SIZE;
+	while (gte < end)
+		gen8_set_pte(gte++, vm->scratch[0]->encode);
+	end += (vma_res->node_size + vma_res->guard) / I915_GTT_PAGE_SIZE;
 
 	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
 		gen8_set_pte(gte++, pte_encode | addr);
@@ -338,9 +323,12 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	dma_addr_t addr;
 
 	gte = (gen6_pte_t __iomem *)ggtt->gsm;
-	gte += vma_res->start / I915_GTT_PAGE_SIZE;
-	end = gte + vma_res->node_size / I915_GTT_PAGE_SIZE;
+	gte += (vma_res->start - vma_res->guard) / I915_GTT_PAGE_SIZE;
 
+	end = gte + vma_res->guard / I915_GTT_PAGE_SIZE;
+	while (gte < end)
+		iowrite32(vm->scratch[0]->encode, gte++);
+	end += (vma_res->node_size + vma_res->guard) / I915_GTT_PAGE_SIZE;
 	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
 		iowrite32(vm->pte_encode(addr, level, flags), gte++);
 	GEM_BUG_ON(gte > end);
@@ -361,27 +349,6 @@ static void nop_clear_range(struct i915_address_space *vm,
 {
 }
 
-static void gen8_ggtt_clear_range(struct i915_address_space *vm,
-				  u64 start, u64 length)
-{
-	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
-	unsigned int first_entry = start / I915_GTT_PAGE_SIZE;
-	unsigned int num_entries = length / I915_GTT_PAGE_SIZE;
-	const gen8_pte_t scratch_pte = vm->scratch[0]->encode;
-	gen8_pte_t __iomem *gtt_base =
-		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
-	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
-	int i;
-
-	if (WARN(num_entries > max_entries,
-		 "First entry = %d; Num entries = %d (max=%d)\n",
-		 first_entry, num_entries, max_entries))
-		num_entries = max_entries;
-
-	for (i = 0; i < num_entries; i++)
-		gen8_set_pte(&gtt_base[i], scratch_pte);
-}
-
 static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
 {
 	/*
@@ -551,8 +518,6 @@ static int init_ggtt(struct i915_ggtt *ggtt)
 	struct drm_mm_node *entry;
 	int ret;
 
-	ggtt->pte_lost = true;
-
 	/*
 	 * GuC requires all resources that we're sharing with it to be placed in
 	 * non-WOPCM memory. If GuC is not present or not in use we still need a
@@ -953,8 +918,6 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.cleanup = gen6_gmch_remove;
 	ggtt->vm.insert_page = gen8_ggtt_insert_page;
 	ggtt->vm.clear_range = nop_clear_range;
-	if (intel_scanout_needs_vtd_wa(i915))
-		ggtt->vm.clear_range = gen8_ggtt_clear_range;
 
 	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
 
@@ -979,15 +942,16 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 			I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND;
 	}
 
-	ggtt->invalidate = gen8_ggtt_invalidate;
+	if (intel_uc_wants_guc(&ggtt->vm.gt->uc))
+		ggtt->invalidate = guc_ggtt_invalidate;
+	else
+		ggtt->invalidate = gen8_ggtt_invalidate;
 
 	ggtt->vm.vma_ops.bind_vma    = intel_ggtt_bind_vma;
 	ggtt->vm.vma_ops.unbind_vma  = intel_ggtt_unbind_vma;
 
 	ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
 
-	setup_private_pat(ggtt->vm.gt);
-
 	return ggtt_probe_common(ggtt, size);
 }
 
@@ -1115,7 +1079,7 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.alloc_scratch_dma = alloc_pt_dma;
 
 	ggtt->vm.clear_range = nop_clear_range;
-	if (!HAS_FULL_PPGTT(i915) || intel_scanout_needs_vtd_wa(i915))
+	if (!HAS_FULL_PPGTT(i915))
 		ggtt->vm.clear_range = gen6_ggtt_clear_range;
 	ggtt->vm.insert_page = gen6_ggtt_insert_page;
 	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
@@ -1196,7 +1160,14 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt)
  */
 int i915_ggtt_probe_hw(struct drm_i915_private *i915)
 {
-	int ret;
+	struct intel_gt *gt;
+	int ret, i;
+
+	for_each_gt(gt, i915, i) {
+		ret = intel_gt_assign_ggtt(gt);
+		if (ret)
+			return ret;
+	}
 
 	ret = ggtt_probe_hw(to_gt(i915)->ggtt, to_gt(i915));
 	if (ret)
@@ -1208,35 +1179,25 @@ int i915_ggtt_probe_hw(struct drm_i915_private *i915)
 	return 0;
 }
 
-int i915_ggtt_enable_hw(struct drm_i915_private *i915)
+struct i915_ggtt *i915_ggtt_create(struct drm_i915_private *i915)
 {
-	if (GRAPHICS_VER(i915) < 6)
-		return intel_ggtt_gmch_enable_hw(i915);
+	struct i915_ggtt *ggtt;
 
-	return 0;
-}
+	ggtt = drmm_kzalloc(&i915->drm, sizeof(*ggtt), GFP_KERNEL);
+	if (!ggtt)
+		return ERR_PTR(-ENOMEM);
 
-void i915_ggtt_enable_guc(struct i915_ggtt *ggtt)
-{
-	GEM_BUG_ON(ggtt->invalidate != gen8_ggtt_invalidate);
+	INIT_LIST_HEAD(&ggtt->gt_list);
 
-	ggtt->invalidate = guc_ggtt_invalidate;
-
-	ggtt->invalidate(ggtt);
+	return ggtt;
 }
 
-void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
+int i915_ggtt_enable_hw(struct drm_i915_private *i915)
 {
-	/* XXX Temporary pardon for error unload */
-	if (ggtt->invalidate == gen8_ggtt_invalidate)
-		return;
-
-	/* We should only be called after i915_ggtt_enable_guc() */
-	GEM_BUG_ON(ggtt->invalidate != guc_ggtt_invalidate);
-
-	ggtt->invalidate = gen8_ggtt_invalidate;
+	if (GRAPHICS_VER(i915) < 6)
+		return intel_ggtt_gmch_enable_hw(i915);
 
-	ggtt->invalidate(ggtt);
+	return 0;
 }
 
 /**
@@ -1253,20 +1214,11 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
 {
 	struct i915_vma *vma;
 	bool write_domain_objs = false;
-	bool retained_ptes;
 
 	drm_WARN_ON(&vm->i915->drm, !vm->is_ggtt && !vm->is_dpt);
 
-	/*
-	 * First fill our portion of the GTT with scratch pages if
-	 * they were not retained across suspend.
-	 */
-	retained_ptes = suspend_retains_ptes(vm) &&
-		!i915_vm_to_ggtt(vm)->pte_lost &&
-		!GEM_WARN_ON(i915_vm_to_ggtt(vm)->probed_pte != read_last_pte(vm));
-
-	if (!retained_ptes)
-		vm->clear_range(vm, 0, vm->total);
+	/* First fill our portion of the GTT with scratch pages */
+	vm->clear_range(vm, 0, vm->total);
 
 	/* clflush objects bound into the GGTT and rebind them. */
 	list_for_each_entry(vma, &vm->bound_list, vm_link) {
@@ -1275,16 +1227,16 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
 			atomic_read(&vma->flags) & I915_VMA_BIND_MASK;
 
 		GEM_BUG_ON(!was_bound);
-		if (!retained_ptes) {
-			/*
-			 * Clear the bound flags of the vma resource to allow
-			 * ptes to be repopulated.
-			 */
-			vma->resource->bound_flags = 0;
-			vma->ops->bind_vma(vm, NULL, vma->resource,
-					   obj ? obj->cache_level : 0,
-					   was_bound);
-		}
+
+		/*
+		 * Clear the bound flags of the vma resource to allow
+		 * ptes to be repopulated.
+		 */
+		vma->resource->bound_flags = 0;
+		vma->ops->bind_vma(vm, NULL, vma->resource,
+				   obj ? obj->cache_level : 0,
+				   was_bound);
+
 		if (obj) { /* only used during resume => exclusive access */
 			write_domain_objs |= fetch_and_zero(&obj->write_domain);
 			obj->read_domains |= I915_GEM_DOMAIN_GTT;
@@ -1296,9 +1248,11 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
 
 void i915_ggtt_resume(struct i915_ggtt *ggtt)
 {
+	struct intel_gt *gt;
 	bool flush;
 
-	intel_gt_check_and_clear_faults(ggtt->vm.gt);
+	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
+		intel_gt_check_and_clear_faults(gt);
 
 	flush = i915_ggtt_resume_vm(&ggtt->vm);
 
@@ -1307,13 +1261,5 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt)
 	if (flush)
 		wbinvd_on_all_cpus();
 
-	if (GRAPHICS_VER(ggtt->vm.i915) >= 8)
-		setup_private_pat(ggtt->vm.gt);
-
 	intel_ggtt_restore_fences(ggtt);
 }
-
-void i915_ggtt_mark_pte_lost(struct drm_i915_private *i915, bool val)
-{
-	to_gt(i915)->ggtt->pte_lost = val;
-}