accel/habanalabs: return tlb inv error code upon failure

Now that CQ-completion based jobs do not trigger a reset upon failure,
failure of such jobs (e.g., MMU cache invalidation) should be handled
by the caller itself depending on the error code returned to it.

Signed-off-by: Koby Elbaz <kelbaz@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

diff --git a/drivers/accel/habanalabs/gaudi/gaudi.c b/drivers/accel/habanalabs/gaudi/gaudi.c
index a9d8467..08a4b1c 100644 (file)
--- a/drivers/accel/habanalabs/gaudi/gaudi.c
+++ b/drivers/accel/habanalabs/gaudi/gaudi.c
@@ -3725,7 +3725,7 @@ static int gaudi_mmu_init(struct hl_device *hdev)
                if (rc) {
                        dev_err(hdev->dev,
                                "failed to set hop0 addr for asid %d\n", i);
-                       goto err;
+                       return rc;
                }
        }
 
@@ -3736,7 +3736,9 @@ static int gaudi_mmu_init(struct hl_device *hdev)
        /* mem cache invalidation */
        WREG32(mmSTLB_MEM_CACHE_INVALIDATION, 1);
 
-       hl_mmu_invalidate_cache(hdev, true, 0);
+       rc = hl_mmu_invalidate_cache(hdev, true, 0);
+       if (rc)
+               return rc;
 
        WREG32(mmMMU_UP_MMU_ENABLE, 1);
        WREG32(mmMMU_UP_SPI_MASK, 0xF);
@@ -3752,9 +3754,6 @@ static int gaudi_mmu_init(struct hl_device *hdev)
        gaudi->hw_cap_initialized |= HW_CAP_MMU;
 
        return 0;
-
-err:
-       return rc;
 }
 
 static int gaudi_load_firmware_to_device(struct hl_device *hdev)
@@ -8420,19 +8419,26 @@ static int gaudi_internal_cb_pool_init(struct hl_device *hdev,
        }
 
        mutex_lock(&hdev->mmu_lock);
+
        rc = hl_mmu_map_contiguous(ctx, hdev->internal_cb_va_base,
                        hdev->internal_cb_pool_dma_addr,
                        HOST_SPACE_INTERNAL_CB_SZ);
-
-       hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
-       mutex_unlock(&hdev->mmu_lock);
-
        if (rc)
                goto unreserve_internal_cb_pool;
 
+       rc = hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
+       if (rc)
+               goto unmap_internal_cb_pool;
+
+       mutex_unlock(&hdev->mmu_lock);
+
        return 0;
 
+unmap_internal_cb_pool:
+       hl_mmu_unmap_contiguous(ctx, hdev->internal_cb_va_base,
+                       HOST_SPACE_INTERNAL_CB_SZ);
 unreserve_internal_cb_pool:
+       mutex_unlock(&hdev->mmu_lock);
        hl_unreserve_va_block(hdev, ctx, hdev->internal_cb_va_base,
                        HOST_SPACE_INTERNAL_CB_SZ);
 destroy_internal_cb_pool:

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 94d53cd..247a6e2 100644 (file)
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -10239,16 +10239,23 @@ static int gaudi2_debugfs_read_dma(struct hl_device *hdev, u64 addr, u32 size, v
 
        /* Create mapping on asic side */
        mutex_lock(&hdev->mmu_lock);
+
        rc = hl_mmu_map_contiguous(ctx, reserved_va_base, host_mem_dma_addr, SZ_2M);
-       hl_mmu_invalidate_cache_range(hdev, false,
+       if (rc) {
+               dev_err(hdev->dev, "Failed to create mapping on asic mmu\n");
+               goto unreserve_va;
+       }
+
+       rc = hl_mmu_invalidate_cache_range(hdev, false,
                                      MMU_OP_USERPTR | MMU_OP_SKIP_LOW_CACHE_INV,
                                      ctx->asid, reserved_va_base, SZ_2M);
-       mutex_unlock(&hdev->mmu_lock);
        if (rc) {
-               dev_err(hdev->dev, "Failed to create mapping on asic mmu\n");
+               hl_mmu_unmap_contiguous(ctx, reserved_va_base, SZ_2M);
                goto unreserve_va;
        }
 
+       mutex_unlock(&hdev->mmu_lock);
+
        /* Enable MMU on KDMA */
        gaudi2_kdma_set_mmbp_asid(hdev, false, ctx->asid);
 
@@ -10277,11 +10284,16 @@ static int gaudi2_debugfs_read_dma(struct hl_device *hdev, u64 addr, u32 size, v
        gaudi2_kdma_set_mmbp_asid(hdev, true, HL_KERNEL_ASID_ID);
 
        mutex_lock(&hdev->mmu_lock);
-       hl_mmu_unmap_contiguous(ctx, reserved_va_base, SZ_2M);
-       hl_mmu_invalidate_cache_range(hdev, false, MMU_OP_USERPTR,
+
+       rc = hl_mmu_unmap_contiguous(ctx, reserved_va_base, SZ_2M);
+       if (rc)
+               goto unreserve_va;
+
+       rc = hl_mmu_invalidate_cache_range(hdev, false, MMU_OP_USERPTR,
                                      ctx->asid, reserved_va_base, SZ_2M);
-       mutex_unlock(&hdev->mmu_lock);
+
 unreserve_va:
+       mutex_unlock(&hdev->mmu_lock);
        hl_unreserve_va_block(hdev, ctx, reserved_va_base, SZ_2M);
 free_data_buffer:
        hl_asic_dma_free_coherent(hdev, SZ_2M, host_mem_virtual_addr, host_mem_dma_addr);
@@ -10334,17 +10346,24 @@ static int gaudi2_internal_cb_pool_init(struct hl_device *hdev, struct hl_ctx *c
        }
 
        mutex_lock(&hdev->mmu_lock);
+
        rc = hl_mmu_map_contiguous(ctx, hdev->internal_cb_va_base, hdev->internal_cb_pool_dma_addr,
                                        HOST_SPACE_INTERNAL_CB_SZ);
-       hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
-       mutex_unlock(&hdev->mmu_lock);
-
        if (rc)
                goto unreserve_internal_cb_pool;
 
+       rc = hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR);
+       if (rc)
+               goto unmap_internal_cb_pool;
+
+       mutex_unlock(&hdev->mmu_lock);
+
        return 0;
 
+unmap_internal_cb_pool:
+       hl_mmu_unmap_contiguous(ctx, hdev->internal_cb_va_base, HOST_SPACE_INTERNAL_CB_SZ);
 unreserve_internal_cb_pool:
+       mutex_unlock(&hdev->mmu_lock);
        hl_unreserve_va_block(hdev, ctx, hdev->internal_cb_va_base, HOST_SPACE_INTERNAL_CB_SZ);
 destroy_internal_cb_pool:
        gen_pool_destroy(hdev->internal_cb_pool);