accel/habanalabs: mask part of hmmu page fault captured address

When receiving page fault from hmmu, the captured address is scrambled
both by HW and by driver. The driver part is unscrambled but the HW
part isn't getting unscrambled.
To avoid declaring wrong address, the HW scrambled part will be
masked.

Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
Dani Liberman 2023-05-08 11:06:17 +03:00 committed by Oded Gabbay
parent 7e63f317c0
commit 5d658d0c51
1 changed files with 12 additions and 4 deletions

View File

@ -162,6 +162,9 @@
#define PSOC_RAZWI_ENG_STR_SIZE 128
#define PSOC_RAZWI_MAX_ENG_PER_RTR 5
/* HW scrambles only bits 0-25 */
#define HW_UNSCRAMBLED_BITS_MASK GENMASK_ULL(63, 26)
struct gaudi2_razwi_info {
u32 axuser_xy;
u32 rtr_ctrl;
@ -8835,11 +8838,16 @@ static void gaudi2_handle_page_error(struct hl_device *hdev, u64 mmu_base, bool
addr <<= 32;
addr |= RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_PAGE_ERROR_CAPTURE_VA));
if (!is_pmmu)
addr = gaudi2_mmu_descramble_addr(hdev, addr);
if (is_pmmu) {
dev_err_ratelimited(hdev->dev, "PMMU page fault on va 0x%llx\n", addr);
} else {
addr = gaudi2_mmu_descramble_addr(hdev, addr);
addr &= HW_UNSCRAMBLED_BITS_MASK;
dev_err_ratelimited(hdev->dev, "HMMU page fault on va range 0x%llx - 0x%llx\n",
addr, addr + ~HW_UNSCRAMBLED_BITS_MASK);
}
dev_err_ratelimited(hdev->dev, "%s page fault on va 0x%llx\n",
is_pmmu ? "PMMU" : "HMMU", addr);
hl_handle_page_fault(hdev, addr, 0, is_pmmu, event_mask);
WREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID), 0);