[PATCH 1/6] accel/habanalabs: unmap mapped memory when TLB inv fails

[Oded Gabbay]

From: Koby Elbaz <kelbaz at habana.ai>

Once a memory mapping is added to the page tables, it's followed by
a TLB invalidation request which could potentially fail (HW failure).
Removing the mapping is simply a part of this failure handling routine.
TLB invalidation failure prints were updated to be more accurate.

Signed-off-by: Koby Elbaz <kelbaz at habana.ai>
Reviewed-by: Oded Gabbay <ogabbay at kernel.org>
Signed-off-by: Oded Gabbay <ogabbay at kernel.org>
---
 drivers/accel/habanalabs/common/command_buffer.c | 15 ++++++++++++---
 drivers/accel/habanalabs/common/mmu/mmu.c        |  8 ++++++--
 2 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/accel/habanalabs/common/command_buffer.c b/drivers/accel/habanalabs/common/command_buffer.c
index 3a0535ac28b1..6e09f48750a0 100644
--- a/drivers/accel/habanalabs/common/command_buffer.c
+++ b/drivers/accel/habanalabs/common/command_buffer.c
@@ -45,20 +45,29 @@ static int cb_map_mem(struct hl_ctx *ctx, struct hl_cb *cb)
 	}
 
 	mutex_lock(&hdev->mmu_lock);
+
 	rc = hl_mmu_map_contiguous(ctx, cb->virtual_addr, cb->bus_address, cb->roundup_size);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to map VA %#llx to CB\n", cb->virtual_addr);
-		goto err_va_umap;
+		goto err_va_pool_free;
 	}
+
 	rc = hl_mmu_invalidate_cache(hdev, false, MMU_OP_USERPTR | MMU_OP_SKIP_LOW_CACHE_INV);
+	if (rc)
+		goto err_mmu_unmap;
+
 	mutex_unlock(&hdev->mmu_lock);
 
 	cb->is_mmu_mapped = true;
-	return rc;
 
-err_va_umap:
+	return 0;
+
+err_mmu_unmap:
+	hl_mmu_unmap_contiguous(ctx, cb->virtual_addr, cb->roundup_size);
+err_va_pool_free:
 	mutex_unlock(&hdev->mmu_lock);
 	gen_pool_free(ctx->cb_va_pool, cb->virtual_addr, cb->roundup_size);
+
 	return rc;
 }
 
diff --git a/drivers/accel/habanalabs/common/mmu/mmu.c b/drivers/accel/habanalabs/common/mmu/mmu.c
index 17581b1bcc77..f379e5b461a6 100644
--- a/drivers/accel/habanalabs/common/mmu/mmu.c
+++ b/drivers/accel/habanalabs/common/mmu/mmu.c
@@ -679,7 +679,9 @@ int hl_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard, u32 flags)
 
 	rc = hdev->asic_funcs->mmu_invalidate_cache(hdev, is_hard, flags);
 	if (rc)
-		dev_err_ratelimited(hdev->dev, "MMU cache invalidation failed\n");
+		dev_err_ratelimited(hdev->dev,
+				"%s cache invalidation failed, rc=%d\n",
+				flags == VM_TYPE_USERPTR ? "PMMU" : "HMMU", rc);
 
 	return rc;
 }
@@ -692,7 +694,9 @@ int hl_mmu_invalidate_cache_range(struct hl_device *hdev, bool is_hard,
 	rc = hdev->asic_funcs->mmu_invalidate_cache_range(hdev, is_hard, flags,
 								asid, va, size);
 	if (rc)
-		dev_err_ratelimited(hdev->dev, "MMU cache range invalidation failed\n");
+		dev_err_ratelimited(hdev->dev,
+				"%s cache range invalidation failed: va=%#llx, size=%llu, rc=%d",
+				flags == VM_TYPE_USERPTR ? "PMMU" : "HMMU", va, size, rc);
 
 	return rc;
 }
-- 
2.40.0