Merging upstream version 6.9.7.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 25 insertions, 16 deletions

diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index ab8536c4fd..fa9e9853c5 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -100,10 +100,9 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
 {
 	struct xe_bo *bo = xe_vma_bo(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
-	unsigned int num_shared = 2; /* slots for bind + move */
 	int err;
 
-	err = xe_vm_prepare_vma(exec, vma, num_shared);
+	err = xe_vm_lock_vma(exec, vma);
 	if (err)
 		return err;
 
@@ -287,9 +286,9 @@ static bool get_pagefault(struct pf_queue *pf_queue, struct pagefault *pf)
 	bool ret = false;
 
 	spin_lock_irq(&pf_queue->lock);
-	if (pf_queue->head != pf_queue->tail) {
+	if (pf_queue->tail != pf_queue->head) {
 		desc = (const struct xe_guc_pagefault_desc *)
-			(pf_queue->data + pf_queue->head);
+			(pf_queue->data + pf_queue->tail);
 
 		pf->fault_level = FIELD_GET(PFD_FAULT_LEVEL, desc->dw0);
 		pf->trva_fault = FIELD_GET(XE2_PFD_TRVA_FAULT, desc->dw0);
@@ -307,7 +306,7 @@ static bool get_pagefault(struct pf_queue *pf_queue, struct pagefault *pf)
 		pf->page_addr |= FIELD_GET(PFD_VIRTUAL_ADDR_LO, desc->dw2) <<
 			PFD_VIRTUAL_ADDR_LO_SHIFT;
 
-		pf_queue->head = (pf_queue->head + PF_MSG_LEN_DW) %
+		pf_queue->tail = (pf_queue->tail + PF_MSG_LEN_DW) %
 			PF_QUEUE_NUM_DW;
 		ret = true;
 	}
@@ -320,7 +319,7 @@ static bool pf_queue_full(struct pf_queue *pf_queue)
 {
 	lockdep_assert_held(&pf_queue->lock);
 
-	return CIRC_SPACE(pf_queue->tail, pf_queue->head, PF_QUEUE_NUM_DW) <=
+	return CIRC_SPACE(pf_queue->head, pf_queue->tail, PF_QUEUE_NUM_DW) <=
 		PF_MSG_LEN_DW;
 }
 
@@ -333,6 +332,11 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	u32 asid;
 	bool full;
 
+	/*
+	 * The below logic doesn't work unless PF_QUEUE_NUM_DW % PF_MSG_LEN_DW == 0
+	 */
+	BUILD_BUG_ON(PF_QUEUE_NUM_DW % PF_MSG_LEN_DW);
+
 	if (unlikely(len != PF_MSG_LEN_DW))
 		return -EPROTO;
 
@@ -342,8 +346,8 @@ int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	spin_lock_irqsave(&pf_queue->lock, flags);
 	full = pf_queue_full(pf_queue);
 	if (!full) {
-		memcpy(pf_queue->data + pf_queue->tail, msg, len * sizeof(u32));
-		pf_queue->tail = (pf_queue->tail + len) % PF_QUEUE_NUM_DW;
+		memcpy(pf_queue->data + pf_queue->head, msg, len * sizeof(u32));
+		pf_queue->head = (pf_queue->head + 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");
@@ -389,7 +393,7 @@ static void pf_queue_work_func(struct work_struct *w)
 		send_pagefault_reply(&gt->uc.guc, &reply);
 
 		if (time_after(jiffies, threshold) &&
-		    pf_queue->head != pf_queue->tail) {
+		    pf_queue->tail != pf_queue->head) {
 			queue_work(gt->usm.pf_wq, w);
 			break;
 		}
@@ -564,9 +568,9 @@ static bool get_acc(struct acc_queue *acc_queue, struct acc *acc)
 	bool ret = false;
 
 	spin_lock(&acc_queue->lock);
-	if (acc_queue->head != acc_queue->tail) {
+	if (acc_queue->tail != acc_queue->head) {
 		desc = (const struct xe_guc_acc_desc *)
-			(acc_queue->data + acc_queue->head);
+			(acc_queue->data + acc_queue->tail);
 
 		acc->granularity = FIELD_GET(ACC_GRANULARITY, desc->dw2);
 		acc->sub_granularity = FIELD_GET(ACC_SUBG_HI, desc->dw1) << 31 |
@@ -579,7 +583,7 @@ static bool get_acc(struct acc_queue *acc_queue, struct acc *acc)
 		acc->va_range_base = make_u64(desc->dw3 & ACC_VIRTUAL_ADDR_RANGE_HI,
 					      desc->dw2 & ACC_VIRTUAL_ADDR_RANGE_LO);
 
-		acc_queue->head = (acc_queue->head + ACC_MSG_LEN_DW) %
+		acc_queue->tail = (acc_queue->tail + ACC_MSG_LEN_DW) %
 				  ACC_QUEUE_NUM_DW;
 		ret = true;
 	}
@@ -607,7 +611,7 @@ static void acc_queue_work_func(struct work_struct *w)
 		}
 
 		if (time_after(jiffies, threshold) &&
-		    acc_queue->head != acc_queue->tail) {
+		    acc_queue->tail != acc_queue->head) {
 			queue_work(gt->usm.acc_wq, w);
 			break;
 		}
@@ -618,7 +622,7 @@ static bool acc_queue_full(struct acc_queue *acc_queue)
 {
 	lockdep_assert_held(&acc_queue->lock);
 
-	return CIRC_SPACE(acc_queue->tail, acc_queue->head, ACC_QUEUE_NUM_DW) <=
+	return CIRC_SPACE(acc_queue->head, acc_queue->tail, ACC_QUEUE_NUM_DW) <=
 		ACC_MSG_LEN_DW;
 }
 
@@ -629,6 +633,11 @@ int xe_guc_access_counter_notify_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	u32 asid;
 	bool full;
 
+	/*
+	 * The below logic doesn't work unless ACC_QUEUE_NUM_DW % ACC_MSG_LEN_DW == 0
+	 */
+	BUILD_BUG_ON(ACC_QUEUE_NUM_DW % ACC_MSG_LEN_DW);
+
 	if (unlikely(len != ACC_MSG_LEN_DW))
 		return -EPROTO;
 
@@ -638,9 +647,9 @@ int xe_guc_access_counter_notify_handler(struct xe_guc *guc, u32 *msg, u32 len)
 	spin_lock(&acc_queue->lock);
 	full = acc_queue_full(acc_queue);
 	if (!full) {
-		memcpy(acc_queue->data + acc_queue->tail, msg,
+		memcpy(acc_queue->data + acc_queue->head, msg,
 		       len * sizeof(u32));
-		acc_queue->tail = (acc_queue->tail + len) % ACC_QUEUE_NUM_DW;
+		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");