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: Omer Shpigelman <oshpigelman@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
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;
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(
* @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);
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);