habanalabs: use PI in MMU cache invalidation

The PS flow for MMU cache invalidation caused timeouts in stress tests.
Use PS + PI flow so no timeouts should happen whatsoever.
Signed-off-by: NOmer Shpigelman <oshpigelman@habana.ai>
Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>

drivers/misc/habanalabs/gaudi/gaudi.c

@@ -2725,6 +2725,12 @@ static int gaudi_mmu_init(struct hl_device *hdev)
 	WREG32(mmSTLB_HOP_CONFIGURATION,
 			hdev->mmu_huge_page_opt ? 0x30440 : 0x40440);
 
+	/*
+	 * The H/W expects the first PI after init to be 1. After wraparound
+	 * we'll write 0.
+	 */
+	gaudi->mmu_cache_inv_pi = 1;
+
 	gaudi->hw_cap_initialized |= HW_CAP_MMU;
 
 	return 0;
@@ -6017,6 +6023,8 @@ static int gaudi_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard,
 	mutex_lock(&hdev->mmu_cache_lock);
 
 	/* L0 & L1 invalidation */
+	WREG32(mmSTLB_INV_PS, 3);
+	WREG32(mmSTLB_CACHE_INV, gaudi->mmu_cache_inv_pi++);
 	WREG32(mmSTLB_INV_PS, 2);
 
 	rc = hl_poll_timeout(

drivers/misc/habanalabs/gaudi/gaudiP.h

@@ -229,6 +229,8 @@ struct gaudi_internal_qman_info {
  * @multi_msi_mode: whether we are working in multi MSI single MSI mode.
  *                  Multi MSI is possible only with IOMMU enabled.
  * @ext_queue_idx: helper index for external queues initialization.
+ * @mmu_cache_inv_pi: PI for MMU cache invalidation flow. The H/W expects an
+ *                    8-bit value so use u8.
  */
 struct gaudi_device {
 	int (*armcp_info_get)(struct hl_device *hdev);
@@ -248,6 +250,7 @@ struct gaudi_device {
 	u32				hw_cap_initialized;
 	u8				multi_msi_mode;
 	u8				ext_queue_idx;
+	u8				mmu_cache_inv_pi;
 };
 
 void gaudi_init_security(struct hl_device *hdev);