habanalabs/gaudi: scrub HBM to a specific value

In order to enhance debuggability, we will scrub the whole HBM to
a specific value, in case HBM scrubbing is enabled. Scrubbing will be
performed after reset and after user closes the FD.

Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 88e181521d906c65207fcef741bb63d1eb33c726..55b133e34ac4d54baaed03473ca246752bbf97dc 100644 (file)
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -4193,6 +4193,11 @@ static int gaudi_hw_init(struct hl_device *hdev)
                goto disable_msi;
        }
 
+       /* Scrub both SRAM and DRAM */
+       rc = hdev->asic_funcs->scrub_device_mem(hdev, 0, 0);
+       if (rc)
+               return rc;
+
        /* Perform read from the device to flush all configuration */
        RREG32(mmHW_STATE);
 
@@ -4757,8 +4762,8 @@ static int gaudi_hbm_scrubbing(struct hl_device *hdev)
                                "Doing HBM scrubbing for 0x%09llx - 0x%09llx\n",
                                cur_addr, cur_addr + chunk_size);
 
-                       WREG32(mmDMA0_CORE_SRC_BASE_LO + dma_offset, 0);
-                       WREG32(mmDMA0_CORE_SRC_BASE_HI + dma_offset, 0);
+                       WREG32(mmDMA0_CORE_SRC_BASE_LO + dma_offset, 0xdeadbeaf);
+                       WREG32(mmDMA0_CORE_SRC_BASE_HI + dma_offset, 0xdeadbeaf);
                        WREG32(mmDMA0_CORE_DST_BASE_LO + dma_offset,
                                                lower_32_bits(cur_addr));
                        WREG32(mmDMA0_CORE_DST_BASE_HI + dma_offset,