drm/xe: Use GuC to do GGTT invalidations for the GuC firmware

Only the GuC should be issuing TLB invalidations if it is enabled. Part
of this patch is sanitize the device on driver unload to ensure we do
not send GuC based TLB invalidations during driver unload.
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>

drivers/gpu/drm/xe/xe_device.c

@@ -215,6 +215,16 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 	return ERR_PTR(err);
 }
 
+static void xe_device_sanitize(struct drm_device *drm, void *arg)
+{
+	struct xe_device *xe = arg;
+	struct xe_gt *gt;
+	u8 id;
+
+	for_each_gt(gt, xe, id)
+		xe_gt_sanitize(gt);
+}
+
 int xe_device_probe(struct xe_device *xe)
 {
 	struct xe_gt *gt;
@@ -274,6 +284,10 @@ int xe_device_probe(struct xe_device *xe)
 
 	xe_debugfs_register(xe);
 
+	err = drmm_add_action_or_reset(&xe->drm, xe_device_sanitize, xe);
+	if (err)
+		return err;
+
 	return 0;
 
 err_irq_shutdown:

drivers/gpu/drm/xe/xe_ggtt.c

@@ -13,6 +13,7 @@
 #include "xe_device.h"
 #include "xe_bo.h"
 #include "xe_gt.h"
+#include "xe_gt_tlb_invalidation.h"
 #include "xe_map.h"
 #include "xe_mmio.h"
 #include "xe_wopcm.h"
@@ -200,10 +201,17 @@ void xe_ggtt_invalidate(struct xe_gt *gt)
 	 * therefore flushing WC buffers.  Is that really true here?
 	 */
 	xe_mmio_write32(gt, GFX_FLSH_CNTL_GEN6.reg, GFX_FLSH_CNTL_EN);
-	if (xe_device_guc_submission_enabled(gt_to_xe(gt))) {
+
+	if (gt->uc.guc.submission_state.enabled) {
+		int seqno;
+
+		seqno = xe_gt_tlb_invalidation_guc(gt);
+		XE_WARN_ON(seqno <= 0);
+		if (seqno > 0)
+			xe_gt_tlb_invalidation_wait(gt, seqno);
+	} else if (xe_device_guc_submission_enabled(gt_to_xe(gt))) {
 		struct xe_device *xe = gt_to_xe(gt);
 
-		/* TODO: also use vfunc here */
 		if (xe->info.platform == XE_PVC) {
 			xe_mmio_write32(gt, PVC_GUC_TLB_INV_DESC1.reg,
 					PVC_GUC_TLB_INV_DESC1_INVALIDATE);

drivers/gpu/drm/xe/xe_gt.c

@@ -196,6 +196,15 @@ static int gt_ttm_mgr_init(struct xe_gt *gt)
 	return 0;
 }
 
+void xe_gt_sanitize(struct xe_gt *gt)
+{
+	/*
+	 * FIXME: if xe_uc_sanitize is called here, on TGL driver will not
+	 * reload
+	 */
+	gt->uc.guc.submission_state.enabled = false;
+}
+
 static void gt_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_gt *gt = arg;
@@ -662,6 +671,8 @@ static int gt_reset(struct xe_gt *gt)
 
 	drm_info(&xe->drm, "GT reset started\n");
 
+	xe_gt_sanitize(gt);
+
 	xe_device_mem_access_get(gt_to_xe(gt));
 	err = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
 	if (err)
@@ -742,6 +753,8 @@ int xe_gt_suspend(struct xe_gt *gt)
 	if (!xe_device_guc_submission_enabled(gt_to_xe(gt)))
 		return -ENODEV;
 
+	xe_gt_sanitize(gt);
+
 	xe_device_mem_access_get(gt_to_xe(gt));
 	err = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
 	if (err)

drivers/gpu/drm/xe/xe_gt.h

@@ -26,6 +26,7 @@ int xe_gt_suspend(struct xe_gt *gt);
 int xe_gt_resume(struct xe_gt *gt);
 void xe_gt_reset_async(struct xe_gt *gt);
 void xe_gt_migrate_wait(struct xe_gt *gt);
+void xe_gt_sanitize(struct xe_gt *gt);
 
 struct xe_gt *xe_find_full_gt(struct xe_gt *gt);
 

drivers/gpu/drm/xe/xe_gt_pagefault.c

@@ -240,7 +240,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
 		goto retry_userptr;
 
 	if (!ret) {
-		ret = xe_gt_tlb_invalidation(gt, NULL, vma);
+		ret = xe_gt_tlb_invalidation_vma(gt, NULL, vma);
 		if (ret >= 0)
 			ret = 0;
 	}

drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c

@@ -135,8 +135,34 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 	return ret;
 }
 
+#define MAKE_INVAL_OP(type)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
+		XE_GUC_TLB_INVAL_MODE_HEAVY << XE_GUC_TLB_INVAL_MODE_SHIFT | \
+		XE_GUC_TLB_INVAL_FLUSH_CACHE)
+
 /**
- * xe_gt_tlb_invalidation - Issue a TLB invalidation on this GT
+ * xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC
+ * @gt: graphics tile
+ *
+ * Issue a TLB invalidation for the GuC. Completion of TLB is asynchronous and
+ * caller can use seqno + xe_gt_tlb_invalidation_wait to wait for completion.
+ *
+ * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
+ * negative error code on error.
+ */
+int xe_gt_tlb_invalidation_guc(struct xe_gt *gt)
+{
+	u32 action[] = {
+		XE_GUC_ACTION_TLB_INVALIDATION,
+		0,  /* seqno, replaced in send_tlb_invalidation */
+		MAKE_INVAL_OP(XE_GUC_TLB_INVAL_GUC),
+	};
+
+	return send_tlb_invalidation(&gt->uc.guc, NULL, action,
+				     ARRAY_SIZE(action));
+}
+
+/**
+ * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA
  * @gt: graphics tile
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion, can be NULL
@@ -150,9 +176,9 @@ static int send_tlb_invalidation(struct xe_guc *guc,
  * Return: Seqno which can be passed to xe_gt_tlb_invalidation_wait on success,
  * negative error code on error.
  */
-int xe_gt_tlb_invalidation(struct xe_gt *gt,
-			   struct xe_gt_tlb_invalidation_fence *fence,
-			   struct xe_vma *vma)
+int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
+			       struct xe_gt_tlb_invalidation_fence *fence,
+			       struct xe_vma *vma)
 {
 	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
@@ -161,12 +187,9 @@ int xe_gt_tlb_invalidation(struct xe_gt *gt,
 
 	XE_BUG_ON(!vma);
 
+	action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
+	action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
 	if (!xe->info.has_range_tlb_invalidation) {
-		action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
-		action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
-#define MAKE_INVAL_OP(type)	((type << XE_GUC_TLB_INVAL_TYPE_SHIFT) | \
-		XE_GUC_TLB_INVAL_MODE_HEAVY << XE_GUC_TLB_INVAL_MODE_SHIFT | \
-		XE_GUC_TLB_INVAL_FLUSH_CACHE)
 		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_FULL);
 	} else {
 		u64 start = vma->start;
@@ -205,8 +228,6 @@ int xe_gt_tlb_invalidation(struct xe_gt *gt,
 		XE_BUG_ON(length & GENMASK(ilog2(SZ_16M) - 1, ilog2(SZ_2M) + 1));
 		XE_BUG_ON(!IS_ALIGNED(start, length));
 
-		action[len++] = XE_GUC_ACTION_TLB_INVALIDATION;
-		action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */
 		action[len++] = MAKE_INVAL_OP(XE_GUC_TLB_INVAL_PAGE_SELECTIVE);
 		action[len++] = vma->vm->usm.asid;
 		action[len++] = lower_32_bits(start);

drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h

@@ -16,9 +16,10 @@ struct xe_vma;
 
 int xe_gt_tlb_invalidation_init(struct xe_gt *gt);
 void xe_gt_tlb_invalidation_reset(struct xe_gt *gt);
-int xe_gt_tlb_invalidation(struct xe_gt *gt,
-			   struct xe_gt_tlb_invalidation_fence *fence,
-			   struct xe_vma *vma);
+int xe_gt_tlb_invalidation_guc(struct xe_gt *gt);
+int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
+			       struct xe_gt_tlb_invalidation_fence *fence,
+			       struct xe_vma *vma);
 int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno);
 int xe_guc_tlb_invalidation_done_handler(struct xe_guc *guc, u32 *msg, u32 len);
 

drivers/gpu/drm/xe/xe_guc.c

@@ -309,6 +309,7 @@ int xe_guc_init_post_hwconfig(struct xe_guc *guc)
 int xe_guc_post_load_init(struct xe_guc *guc)
 {
 	xe_guc_ads_populate_post_load(&guc->ads);
+	guc->submission_state.enabled = true;
 
 	return 0;
 }
@@ -795,6 +796,7 @@ void xe_guc_sanitize(struct xe_guc *guc)
 {
 	xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_LOADABLE);
 	xe_guc_ct_disable(&guc->ct);
+	guc->submission_state.enabled = false;
 }
 
 int xe_guc_reset_prepare(struct xe_guc *guc)

drivers/gpu/drm/xe/xe_guc_types.h

@@ -60,6 +60,8 @@ struct xe_guc {
 			/** @patch: patch version of GuC submission */
 			u32 patch;
 		} version;
+		/** @enabled: submission is enabled */
+		bool enabled;
 	} submission_state;
 	/** @hwconfig: Hardware config state */
 	struct {

drivers/gpu/drm/xe/xe_pt.c

@@ -1506,7 +1506,7 @@ static void invalidation_fence_work_func(struct work_struct *w)
 		container_of(w, struct invalidation_fence, work);
 
 	trace_xe_gt_tlb_invalidation_fence_work_func(&ifence->base);
-	xe_gt_tlb_invalidation(ifence->gt, &ifence->base, ifence->vma);
+	xe_gt_tlb_invalidation_vma(ifence->gt, &ifence->base, ifence->vma);
 }
 
 static int invalidation_fence_init(struct xe_gt *gt,

drivers/gpu/drm/xe/xe_uc.c

@@ -88,10 +88,15 @@ static int uc_reset(struct xe_uc *uc)
 	return 0;
 }
 
-static int uc_sanitize(struct xe_uc *uc)
+void xe_uc_sanitize(struct xe_uc *uc)
 {
 	xe_huc_sanitize(&uc->huc);
 	xe_guc_sanitize(&uc->guc);
+}
+
+static int xe_uc_sanitize_reset(struct xe_uc *uc)
+{
+	xe_uc_sanitize(uc);
 
 	return uc_reset(uc);
 }
@@ -129,7 +134,7 @@ int xe_uc_init_hw(struct xe_uc *uc)
 	if (!xe_device_guc_submission_enabled(uc_to_xe(uc)))
 		return 0;
 
-	ret = uc_sanitize(uc);
+	ret = xe_uc_sanitize_reset(uc);
 	if (ret)
 		return ret;
 

drivers/gpu/drm/xe/xe_uc.h

@@ -17,5 +17,6 @@ void xe_uc_stop_prepare(struct xe_uc *uc);
 int xe_uc_stop(struct xe_uc *uc);
 int xe_uc_start(struct xe_uc *uc);
 int xe_uc_suspend(struct xe_uc *uc);
+void xe_uc_sanitize(struct xe_uc *uc);
 
 #endif

drivers/gpu/drm/xe/xe_vm.c

@@ -3356,7 +3356,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma)
 		if (xe_pt_zap_ptes(gt, vma)) {
 			gt_needs_invalidate |= BIT(id);
 			xe_device_wmb(xe);
-			seqno[id] = xe_gt_tlb_invalidation(gt, NULL, vma);
+			seqno[id] = xe_gt_tlb_invalidation_vma(gt, NULL, vma);
 			if (seqno[id] < 0)
 				return seqno[id];
 		}