[PATCH 2/2] crypto: caam - Use bounce buffer for unaligned RSA destination buffers

The rsa-caam driver directly DMA-maps the destination buffer supplied by
the caller via req->dst without checking whether it meets the cacheline
alignment requirements of DMA-incoherent hardware such as i.MX8.

On CPUs with non-coherent DMA caches, if the destination buffer shares a
cacheline with other data (i.e. it is not cacheline-aligned), cache
writeback/invalidation during DMA can corrupt adjacent memory or cause
stale data to be read back. This manifests as intermittent -EKEYREJECTED
errors when loading signed kernel modules.

When any segment of req->dst is not cacheline-aligned in either its
start offset or length, allocate a single contiguous aligned bounce
buffer covering the full dst_len rounded up to a cacheline multiple,
redirect the operation to it, and copy the result back to the original
destination once the hardware has completed successfully.

Introduce a helper sg_is_dma_aligned() that checks both sg->offset and
sg->length for cacheline alignment. Checking sg->offset suffices for
the start address since physical pages are always page-aligned and
PAGE_SIZE is a multiple of dma_get_cache_alignment(). sg->length is
also checked to ensure the buffer end does not share a cacheline with
adjacent memory.

The intermittent error 'Key was rejected by service' on i.MX8 with CAAM
can be triggered when loading signed kernel modules:

    for i in $(seq 1 100); do
        sudo modprobe xfs 2>&1 && echo "SUCCESS on attempt $i" \
        && sudo rmmod xfs || echo "FAILED on attempt $i"
    done

Signed-off-by: Changwei Zou <[email protected]>
Assisted-by: OpenCode:claude-sonnet-4.6
---
 drivers/crypto/caam/caampkc.c | 77 ++++++++++++++++++++++++++++++++++-
 drivers/crypto/caam/caampkc.h |  6 +++
 2 files changed, 82 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 840271840cce..11c6b07f5dad 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -59,6 +59,40 @@ static void rsa_io_unmap(struct device *dev, struct rsa_edesc *edesc,
 				 DMA_TO_DEVICE);
 }
 
+static int do_rsa_bounce_buf(struct akcipher_request *req, int req_err)
+{
+	struct caam_rsa_req_ctx *req_ctx = akcipher_request_ctx(req);
+	int nents, err = 0;
+
+	if (!req_ctx->bounce_buf)
+		return 0;
+
+	/* Only copy back to the original destination on success */
+	if (!req_err) {
+		nents = sg_nents_for_len(req_ctx->orig_dst, req->dst_len);
+		if (nents < 0)
+			err = nents;
+		else if (sg_copy_from_buffer(req_ctx->orig_dst, nents,
+					     req_ctx->bounce_buf,
+					     req->dst_len) != req->dst_len)
+			err = -EFAULT;
+	}
+
+	kfree(req_ctx->bounce_buf);
+	req_ctx->bounce_buf = NULL;
+	req->dst = req_ctx->orig_dst;
+
+	return err;
+}
+
+static inline void rsa_bounce_buf_done(struct akcipher_request *req, int *err)
+{
+	int cperr = do_rsa_bounce_buf(req, *err);
+
+	if (!*err)
+		*err = cperr;
+}
+
 static void rsa_pub_unmap(struct device *dev, struct rsa_edesc *edesc,
 			  struct akcipher_request *req)
 {
@@ -138,6 +172,7 @@ static void rsa_pub_done(struct device *dev, u32 *desc, u32 err, void *context)
 	rsa_pub_unmap(dev, edesc, req);
 	rsa_io_unmap(dev, edesc, req);
 	kfree(edesc);
+	rsa_bounce_buf_done(req, &ecode);
 
 	/*
 	 * If no backlog flag, the completion of the request is done
@@ -181,6 +216,7 @@ static void rsa_priv_f_done(struct device *dev, u32 *desc, u32 err,
 
 	rsa_io_unmap(dev, edesc, req);
 	kfree(edesc);
+	rsa_bounce_buf_done(req, &ecode);
 
 	/*
 	 * If no backlog flag, the completion of the request is done
@@ -246,6 +282,12 @@ static int caam_rsa_count_leading_zeros(struct scatterlist *sgl,
 	return tbytes - nbytes;
 }
 
+static inline bool sg_is_dma_aligned(struct scatterlist *sg)
+{
+	return IS_ALIGNED(sg->offset, dma_get_cache_alignment()) &&
+	       IS_ALIGNED(sg->length, dma_get_cache_alignment());
+}
+
 static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 					 size_t desclen)
 {
@@ -291,11 +333,34 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 				     req_ctx->fixup_src_len);
 	dst_nents = sg_nents_for_len(req->dst, req->dst_len);
 
+	req_ctx->bounce_buf = NULL;
+	req_ctx->orig_dst = req->dst;
+	if (req->dst_len > 0) {
+		struct scatterlist *sg;
+		int i;
+
+		for_each_sg(req->dst, sg, dst_nents, i) {
+			if (!sg_is_dma_aligned(sg)) {
+				req_ctx->bounce_buf =
+					kzalloc(ALIGN(req->dst_len,
+						      dma_get_cache_alignment()),
+						flags);
+				if (!req_ctx->bounce_buf)
+					return ERR_PTR(-ENOMEM);
+				sg_init_one(&req_ctx->dst, req_ctx->bounce_buf,
+					    req->dst_len);
+				req->dst = &req_ctx->dst;
+				dst_nents = 1;
+				break;
+			}
+		}
+	}
+
 	mapped_src_nents = dma_map_sg(dev, req_ctx->fixup_src, src_nents,
 				      DMA_TO_DEVICE);
 	if (unlikely(!mapped_src_nents)) {
 		dev_err(dev, "unable to map source\n");
-		return ERR_PTR(-ENOMEM);
+		goto bounce_fail;
 	}
 	mapped_dst_nents = dma_map_sg(dev, req->dst, dst_nents,
 				      DMA_FROM_DEVICE);
@@ -368,6 +433,10 @@ static struct rsa_edesc *rsa_edesc_alloc(struct akcipher_request *req,
 	dma_unmap_sg(dev, req->dst, dst_nents, DMA_FROM_DEVICE);
 src_fail:
 	dma_unmap_sg(dev, req_ctx->fixup_src, src_nents, DMA_TO_DEVICE);
+bounce_fail:
+	kfree(req_ctx->bounce_buf);
+	req_ctx->bounce_buf = NULL;
+	req->dst = req_ctx->orig_dst;
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -409,6 +478,7 @@ static int akcipher_do_one_req(struct crypto_engine *engine, void *areq)
 		}
 		rsa_io_unmap(jrdev, req_ctx->edesc, req);
 		kfree(req_ctx->edesc);
+		rsa_bounce_buf_done(req, &ret);
 	} else {
 		ret = 0;
 	}
@@ -723,6 +793,7 @@ static int akcipher_enqueue_req(struct device *jrdev,
 		}
 		rsa_io_unmap(jrdev, edesc, req);
 		kfree(edesc);
+		rsa_bounce_buf_done(req, &ret);
 	}
 
 	return ret;
@@ -764,6 +835,7 @@ static int caam_rsa_enc(struct akcipher_request *req)
 init_fail:
 	rsa_io_unmap(jrdev, edesc, req);
 	kfree(edesc);
+	rsa_bounce_buf_done(req, &ret);
 	return ret;
 }
 
@@ -793,6 +865,7 @@ static int caam_rsa_dec_priv_f1(struct akcipher_request *req)
 init_fail:
 	rsa_io_unmap(jrdev, edesc, req);
 	kfree(edesc);
+	rsa_bounce_buf_done(req, &ret);
 	return ret;
 }
 
@@ -822,6 +895,7 @@ static int caam_rsa_dec_priv_f2(struct akcipher_request *req)
 init_fail:
 	rsa_io_unmap(jrdev, edesc, req);
 	kfree(edesc);
+	rsa_bounce_buf_done(req, &ret);
 	return ret;
 }
 
@@ -851,6 +925,7 @@ static int caam_rsa_dec_priv_f3(struct akcipher_request *req)
 init_fail:
 	rsa_io_unmap(jrdev, edesc, req);
 	kfree(edesc);
+	rsa_bounce_buf_done(req, &ret);
 	return ret;
 }
 
diff --git a/drivers/crypto/caam/caampkc.h b/drivers/crypto/caam/caampkc.h
index 96d03704c9be..efad91d6058f 100644
--- a/drivers/crypto/caam/caampkc.h
+++ b/drivers/crypto/caam/caampkc.h
@@ -103,6 +103,9 @@ struct caam_rsa_ctx {
  * @src           : input scatterlist (stripped of leading zeros)
  * @fixup_src     : input scatterlist (that might be stripped of leading zeros)
  * @fixup_src_len : length of the fixup_src input scatterlist
+ * @dst           : destination scatterlist backed by bounce buffer (if needed)
+ * @bounce_buf    : DMA-aligned bounce buffer for destination (or NULL)
+ * @orig_dst      : original destination scatterlist (before bounce substitution)
  * @edesc         : s/w-extended rsa descriptor
  * @akcipher_op_done : callback used when operation is done
  */
@@ -110,6 +113,9 @@ struct caam_rsa_req_ctx {
 	struct scatterlist src[2];
 	struct scatterlist *fixup_src;
 	unsigned int fixup_src_len;
+	struct scatterlist dst;
+	u8 *bounce_buf;
+	struct scatterlist *orig_dst;
 	struct rsa_edesc *edesc;
 	void (*akcipher_op_done)(struct device *jrdev, u32 *desc, u32 err,
 				 void *context);
-- 
2.43.0