crypto: rsa-pkcs1pad - Avoid copying output when possible

In the vast majority of cases (2^-32 on 32-bit and 2^-64 on 64-bit)
cases, the result from encryption/signing will require no padding.

This patch makes these two operations write their output directly
to the final destination.  Only in the exceedingly rare cases where
fixup is needed to we copy it out and back to add the leading zeroes.

This patch also makes use of the crypto_akcipher_set_crypt API
instead of writing the akcipher request directly.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index ebd8514..8ccfdd7 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -185,37 +185,36 @@
 	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
 	struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
-	size_t pad_len = ctx->key_size - req_ctx->child_req.dst_len;
-	size_t chunk_len, pad_left;
-	struct sg_mapping_iter miter;
+	unsigned int pad_len;
+	unsigned int len;
+	u8 *out_buf;
 
-	if (!err) {
-		if (pad_len) {
-			sg_miter_start(&miter, req->dst,
-					sg_nents_for_len(req->dst, pad_len),
-					SG_MITER_ATOMIC | SG_MITER_TO_SG);
+	if (err)
+		goto out;
 
-			pad_left = pad_len;
-			while (pad_left) {
-				sg_miter_next(&miter);
+	len = req_ctx->child_req.dst_len;
+	pad_len = ctx->key_size - len;
 
-				chunk_len = min(miter.length, pad_left);
-				memset(miter.addr, 0, chunk_len);
-				pad_left -= chunk_len;
-			}
+	/* Four billion to one */
+	if (likely(!pad_len))
+		goto out;
 
-			sg_miter_stop(&miter);
-		}
+	out_buf = kzalloc(ctx->key_size, GFP_ATOMIC);
+	err = -ENOMEM;
+	if (!out_buf)
+		goto out;
 
-		sg_pcopy_from_buffer(req->dst,
-				sg_nents_for_len(req->dst, ctx->key_size),
-				req_ctx->out_buf, req_ctx->child_req.dst_len,
-				pad_len);
-	}
+	sg_copy_to_buffer(req->dst, sg_nents_for_len(req->dst, len),
+			  out_buf + pad_len, len);
+	sg_copy_from_buffer(req->dst,
+			    sg_nents_for_len(req->dst, ctx->key_size),
+			    out_buf, ctx->key_size);
+	kzfree(out_buf);
+
+out:
 	req->dst_len = ctx->key_size;
 
 	kfree(req_ctx->in_buf);
-	kzfree(req_ctx->out_buf);
 
 	return err;
 }
@@ -255,15 +254,6 @@
 		return -EOVERFLOW;
 	}
 
-	/*
-	 * Replace both input and output to add the padding in the input and
-	 * the potential missing leading zeros in the output.
-	 */
-	req_ctx->child_req.src = req_ctx->in_sg;
-	req_ctx->child_req.src_len = ctx->key_size - 1;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
 				  GFP_KERNEL);
 	if (!req_ctx->in_buf)
@@ -291,6 +281,10 @@
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
 
+	/* Reuse output buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
+				   req->dst, ctx->key_size - 1, req->dst_len);
+
 	err = crypto_akcipher_encrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -372,12 +366,6 @@
 	if (!ctx->key_size || req->src_len != ctx->key_size)
 		return -EINVAL;
 
-	/* Reuse input buffer, output to a new buffer */
-	req_ctx->child_req.src = req->src;
-	req_ctx->child_req.src_len = req->src_len;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size ;
-
 	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
@@ -389,6 +377,11 @@
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_decrypt_complete_cb, req);
 
+	/* Reuse input buffer, output to a new buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req->src,
+				   req_ctx->out_sg, req->src_len,
+				   ctx->key_size);
+
 	err = crypto_akcipher_decrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -422,15 +415,6 @@
 		return -EOVERFLOW;
 	}
 
-	/*
-	 * Replace both input and output to add the padding in the input and
-	 * the potential missing leading zeros in the output.
-	 */
-	req_ctx->child_req.src = req_ctx->in_sg;
-	req_ctx->child_req.src_len = ctx->key_size - 1;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->in_buf = kmalloc(ctx->key_size - 1 - req->src_len,
 				  GFP_KERNEL);
 	if (!req_ctx->in_buf)
@@ -447,19 +431,14 @@
 	pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf,
 			ctx->key_size - 1 - req->src_len, req->src);
 
-	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
-	if (!req_ctx->out_buf) {
-		kfree(req_ctx->in_buf);
-		return -ENOMEM;
-	}
-
-	pkcs1pad_sg_set_buf(req_ctx->out_sg, req_ctx->out_buf,
-			ctx->key_size, NULL);
-
 	akcipher_request_set_tfm(&req_ctx->child_req, ctx->child);
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_encrypt_sign_complete_cb, req);
 
+	/* Reuse output buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
+				   req->dst, ctx->key_size - 1, req->dst_len);
+
 	err = crypto_akcipher_sign(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||
@@ -559,12 +538,6 @@
 	if (!ctx->key_size || req->src_len < ctx->key_size)
 		return -EINVAL;
 
-	/* Reuse input buffer, output to a new buffer */
-	req_ctx->child_req.src = req->src;
-	req_ctx->child_req.src_len = req->src_len;
-	req_ctx->child_req.dst = req_ctx->out_sg;
-	req_ctx->child_req.dst_len = ctx->key_size;
-
 	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
@@ -576,6 +549,11 @@
 	akcipher_request_set_callback(&req_ctx->child_req, req->base.flags,
 			pkcs1pad_verify_complete_cb, req);
 
+	/* Reuse input buffer, output to a new buffer */
+	akcipher_request_set_crypt(&req_ctx->child_req, req->src,
+				   req_ctx->out_sg, req->src_len,
+				   ctx->key_size);
+
 	err = crypto_akcipher_verify(&req_ctx->child_req);
 	if (err != -EINPROGRESS &&
 			(err != -EBUSY ||