1 files changed, 64 insertions, 99 deletions

diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 6717a636b1d9..a054d6010ae0 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -14,14 +14,15 @@
 #include "abi/guc_actions_abi.h"
 #include "xe_bo.h"
 #include "xe_gt.h"
+#include "xe_gt_printk.h"
 #include "xe_gt_stats.h"
-#include "xe_gt_tlb_invalidation.h"
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
 #include "xe_migrate.h"
 #include "xe_svm.h"
 #include "xe_trace_bo.h"
 #include "xe_vm.h"
+#include "xe_vram_types.h"
 
 struct pagefault {
 	u64 page_addr;
@@ -68,35 +69,12 @@ static bool access_is_atomic(enum access_type access_type)
 
 static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma)
 {
-	return BIT(tile->id) & vma->tile_present &&
-		!(BIT(tile->id) & vma->tile_invalidated);
-}
-
-static bool vma_matches(struct xe_vma *vma, u64 page_addr)
-{
-	if (page_addr > xe_vma_end(vma) - 1 ||
-	    page_addr + SZ_4K - 1 < xe_vma_start(vma))
-		return false;
-
-	return true;
-}
-
-static struct xe_vma *lookup_vma(struct xe_vm *vm, u64 page_addr)
-{
-	struct xe_vma *vma = NULL;
-
-	if (vm->usm.last_fault_vma) {   /* Fast lookup */
-		if (vma_matches(vm->usm.last_fault_vma, page_addr))
-			vma = vm->usm.last_fault_vma;
-	}
-	if (!vma)
-		vma = xe_vm_find_overlapping_vma(vm, page_addr, SZ_4K);
-
-	return vma;
+	return xe_vm_has_valid_gpu_mapping(tile, vma->tile_present,
+					   vma->tile_invalidated);
 }
 
 static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
-		       bool atomic, unsigned int id)
+		       bool need_vram_move, struct xe_vram_region *vram)
 {
 	struct xe_bo *bo = xe_vma_bo(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
@@ -106,24 +84,11 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
 	if (err)
 		return err;
 
-	if (atomic && IS_DGFX(vm->xe)) {
-		if (xe_vma_is_userptr(vma)) {
-			err = -EACCES;
-			return err;
-		}
-
-		/* Migrate to VRAM, move should invalidate the VMA first */
-		err = xe_bo_migrate(bo, XE_PL_VRAM0 + id);
-		if (err)
-			return err;
-	} else if (bo) {
-		/* Create backing store if needed */
-		err = xe_bo_validate(bo, vm, true);
-		if (err)
-			return err;
-	}
+	if (!bo)
+		return 0;
 
-	return 0;
+	return need_vram_move ? xe_bo_migrate(bo, vram->placement, NULL, exec) :
+		xe_bo_validate(bo, vm, true, exec);
 }
 
 static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma,
@@ -131,19 +96,23 @@ static int handle_vma_pagefault(struct xe_gt *gt, struct xe_vma *vma,
 {
 	struct xe_vm *vm = xe_vma_vm(vma);
 	struct xe_tile *tile = gt_to_tile(gt);
+	struct xe_validation_ctx ctx;
 	struct drm_exec exec;
 	struct dma_fence *fence;
-	ktime_t end = 0;
-	int err;
+	int err, needs_vram;
 
 	lockdep_assert_held_write(&vm->lock);
 
+	needs_vram = xe_vma_need_vram_for_atomic(vm->xe, vma, atomic);
+	if (needs_vram < 0 || (needs_vram && xe_vma_is_userptr(vma)))
+		return needs_vram < 0 ? needs_vram : -EACCES;
+
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT, 1);
 	xe_gt_stats_incr(gt, XE_GT_STATS_ID_VMA_PAGEFAULT_KB, xe_vma_size(vma) / 1024);
 
 	trace_xe_vma_pagefault(vma);
 
-	/* Check if VMA is valid */
+	/* Check if VMA is valid, opportunistic check only */
 	if (vma_is_valid(tile, vma) && !atomic)
 		return 0;
 
@@ -158,32 +127,31 @@ retry_userptr:
 	}
 
 	/* Lock VM and BOs dma-resv */
-	drm_exec_init(&exec, 0, 0);
+	xe_validation_ctx_init(&ctx, &vm->xe->val, &exec, (struct xe_val_flags) {});
 	drm_exec_until_all_locked(&exec) {
-		err = xe_pf_begin(&exec, vma, atomic, tile->id);
+		err = xe_pf_begin(&exec, vma, needs_vram == 1, tile->mem.vram);
 		drm_exec_retry_on_contention(&exec);
-		if (xe_vm_validate_should_retry(&exec, err, &end))
-			err = -EAGAIN;
+		xe_validation_retry_on_oom(&ctx, &err);
 		if (err)
 			goto unlock_dma_resv;
 
 		/* Bind VMA only to the GT that has faulted */
 		trace_xe_vma_pf_bind(vma);
+		xe_vm_set_validation_exec(vm, &exec);
 		fence = xe_vma_rebind(vm, vma, BIT(tile->id));
+		xe_vm_set_validation_exec(vm, NULL);
 		if (IS_ERR(fence)) {
 			err = PTR_ERR(fence);
-			if (xe_vm_validate_should_retry(&exec, err, &end))
-				err = -EAGAIN;
+			xe_validation_retry_on_oom(&ctx, &err);
 			goto unlock_dma_resv;
 		}
 	}
 
 	dma_fence_wait(fence, false);
 	dma_fence_put(fence);
-	vma->tile_invalidated &= ~BIT(tile->id);
 
 unlock_dma_resv:
-	drm_exec_fini(&exec);
+	xe_validation_ctx_fini(&ctx);
 	if (err == -EAGAIN)
 		goto retry_userptr;
 
@@ -231,7 +199,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
 		goto unlock_vm;
 	}
 
-	vma = lookup_vma(vm, pf->page_addr);
+	vma = xe_vm_find_vma_by_addr(vm, pf->page_addr);
 	if (!vma) {
 		err = -EINVAL;
 		goto unlock_vm;
@@ -266,22 +234,22 @@ static int send_pagefault_reply(struct xe_guc *guc,
 	return xe_guc_ct_send(&guc->ct, action, ARRAY_SIZE(action), 0, 0);
 }
 
-static void print_pagefault(struct xe_device *xe, struct pagefault *pf)
+static void print_pagefault(struct xe_gt *gt, struct pagefault *pf)
 {
-	drm_dbg(&xe->drm, "\n\tASID: %d\n"
-		 "\tVFID: %d\n"
-		 "\tPDATA: 0x%04x\n"
-		 "\tFaulted Address: 0x%08x%08x\n"
-		 "\tFaultType: %d\n"
-		 "\tAccessType: %d\n"
-		 "\tFaultLevel: %d\n"
-		 "\tEngineClass: %d %s\n"
-		 "\tEngineInstance: %d\n",
-		 pf->asid, pf->vfid, pf->pdata, upper_32_bits(pf->page_addr),
-		 lower_32_bits(pf->page_addr),
-		 pf->fault_type, pf->access_type, pf->fault_level,
-		 pf->engine_class, xe_hw_engine_class_to_str(pf->engine_class),
-		 pf->engine_instance);
+	xe_gt_dbg(gt, "\n\tASID: %d\n"
+		  "\tVFID: %d\n"
+		  "\tPDATA: 0x%04x\n"
+		  "\tFaulted Address: 0x%08x%08x\n"
+		  "\tFaultType: %d\n"
+		  "\tAccessType: %d\n"
+		  "\tFaultLevel: %d\n"
+		  "\tEngineClass: %d %s\n"
+		  "\tEngineInstance: %d\n",
+		  pf->asid, pf->vfid, pf->pdata, upper_32_bits(pf->page_addr),
+		  lower_32_bits(pf->page_addr),
+		  pf->fault_type, pf->access_type, pf->fault_level,
+		  pf->engine_class, xe_hw_engine_class_to_str(pf->engine_class),
+		  pf->engine_instance);
 }
 
 #define PF_MSG_LEN_DW	4
@@ -333,7 +301,6 @@ static bool pf_queue_full(struct pf_queue *pf_queue)
 int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
-	struct xe_device *xe = gt_to_xe(gt);
 	struct pf_queue *pf_queue;
 	unsigned long flags;
 	u32 asid;
@@ -358,7 +325,7 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 			pf_queue->num_dw;
 		queue_work(gt->usm.pf_wq, &pf_queue->worker);
 	} else {
-		drm_warn(&xe->drm, "PF Queue full, shouldn't be possible");
+		xe_gt_warn(gt, "PageFault Queue full, shouldn't be possible\n");
 	}
 	spin_unlock_irqrestore(&pf_queue->lock, flags);
 
@@ -371,7 +338,6 @@ static void pf_queue_work_func(struct work_struct *w)
 {
 	struct pf_queue *pf_queue = container_of(w, struct pf_queue, worker);
 	struct xe_gt *gt = pf_queue->gt;
-	struct xe_device *xe = gt_to_xe(gt);
 	struct xe_guc_pagefault_reply reply = {};
 	struct pagefault pf = {};
 	unsigned long threshold;
@@ -382,9 +348,9 @@ static void pf_queue_work_func(struct work_struct *w)
 	while (get_pagefault(pf_queue, &pf)) {
 		ret = handle_pagefault(gt, &pf);
 		if (unlikely(ret)) {
-			print_pagefault(xe, &pf);
+			print_pagefault(gt, &pf);
 			pf.fault_unsuccessful = 1;
-			drm_dbg(&xe->drm, "Fault response: Unsuccessful %d\n", ret);
+			xe_gt_dbg(gt, "Fault response: Unsuccessful %pe\n", ERR_PTR(ret));
 		}
 
 		reply.dw0 = FIELD_PREP(PFR_VALID, 1) |
@@ -538,21 +504,21 @@ static int sub_granularity_in_byte(int val)
 	return (granularity_in_byte(val) / 32);
 }
 
-static void print_acc(struct xe_device *xe, struct acc *acc)
+static void print_acc(struct xe_gt *gt, struct acc *acc)
 {
-	drm_warn(&xe->drm, "Access counter request:\n"
-		 "\tType: %s\n"
-		 "\tASID: %d\n"
-		 "\tVFID: %d\n"
-		 "\tEngine: %d:%d\n"
-		 "\tGranularity: 0x%x KB Region/ %d KB sub-granularity\n"
-		 "\tSub_Granularity Vector: 0x%08x\n"
-		 "\tVA Range base: 0x%016llx\n",
-		 acc->access_type ? "AC_NTFY_VAL" : "AC_TRIG_VAL",
-		 acc->asid, acc->vfid, acc->engine_class, acc->engine_instance,
-		 granularity_in_byte(acc->granularity) / SZ_1K,
-		 sub_granularity_in_byte(acc->granularity) / SZ_1K,
-		 acc->sub_granularity, acc->va_range_base);
+	xe_gt_warn(gt, "Access counter request:\n"
+		   "\tType: %s\n"
+		   "\tASID: %d\n"
+		   "\tVFID: %d\n"
+		   "\tEngine: %d:%d\n"
+		   "\tGranularity: 0x%x KB Region/ %d KB sub-granularity\n"
+		   "\tSub_Granularity Vector: 0x%08x\n"
+		   "\tVA Range base: 0x%016llx\n",
+		   acc->access_type ? "AC_NTFY_VAL" : "AC_TRIG_VAL",
+		   acc->asid, acc->vfid, acc->engine_class, acc->engine_instance,
+		   granularity_in_byte(acc->granularity) / SZ_1K,
+		   sub_granularity_in_byte(acc->granularity) / SZ_1K,
+		   acc->sub_granularity, acc->va_range_base);
 }
 
 static struct xe_vma *get_acc_vma(struct xe_vm *vm, struct acc *acc)
@@ -567,6 +533,7 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 	struct xe_tile *tile = gt_to_tile(gt);
+	struct xe_validation_ctx ctx;
 	struct drm_exec exec;
 	struct xe_vm *vm;
 	struct xe_vma *vma;
@@ -596,15 +563,14 @@ static int handle_acc(struct xe_gt *gt, struct acc *acc)
 		goto unlock_vm;
 
 	/* Lock VM and BOs dma-resv */
-	drm_exec_init(&exec, 0, 0);
+	xe_validation_ctx_init(&ctx, &vm->xe->val, &exec, (struct xe_val_flags) {});
 	drm_exec_until_all_locked(&exec) {
-		ret = xe_pf_begin(&exec, vma, true, tile->id);
+		ret = xe_pf_begin(&exec, vma, IS_DGFX(vm->xe), tile->mem.vram);
 		drm_exec_retry_on_contention(&exec);
-		if (ret)
-			break;
+		xe_validation_retry_on_oom(&ctx, &ret);
 	}
 
-	drm_exec_fini(&exec);
+	xe_validation_ctx_fini(&ctx);
 unlock_vm:
 	up_read(&vm->lock);
 	xe_vm_put(vm);
@@ -650,7 +616,6 @@ static void acc_queue_work_func(struct work_struct *w)
 {
 	struct acc_queue *acc_queue = container_of(w, struct acc_queue, worker);
 	struct xe_gt *gt = acc_queue->gt;
-	struct xe_device *xe = gt_to_xe(gt);
 	struct acc acc = {};
 	unsigned long threshold;
 	int ret;
@@ -660,8 +625,8 @@ static void acc_queue_work_func(struct work_struct *w)
 	while (get_acc(acc_queue, &acc)) {
 		ret = handle_acc(gt, &acc);
 		if (unlikely(ret)) {
-			print_acc(xe, &acc);
-			drm_warn(&xe->drm, "ACC: Unsuccessful %d\n", ret);
+			print_acc(gt, &acc);
+			xe_gt_warn(gt, "ACC: Unsuccessful %pe\n", ERR_PTR(ret));
 		}
 
 		if (time_after(jiffies, threshold) &&
@@ -706,7 +671,7 @@ int xe_guc_access_counter_notify_handler(struct xe_guc *guc, u32 *msg, u32 len)
 		acc_queue->head = (acc_queue->head + len) % ACC_QUEUE_NUM_DW;
 		queue_work(gt->usm.acc_wq, &acc_queue->worker);
 	} else {
-		drm_warn(&gt_to_xe(gt)->drm, "ACC Queue full, dropping ACC");
+		xe_gt_warn(gt, "ACC Queue full, dropping ACC\n");
 	}
 	spin_unlock(&acc_queue->lock);