For preparing decryption request, several memory chunks are required
(aead_req, sgin, sgout, iv, aad). For submitting the decrypt request to
an accelerator, it is required that the buffers which are read by the
accelerator must be dma-able and not come from stack. The buffers for
aad and iv can be separately kmalloced each, but it is inefficient.
This patch does a combined allocation for preparing decryption request
and then segments into aead_req || sgin || sgout || iv || aad.
Signed-off-by: Vakul Garg
---
Changes since v2:
- Rebased to not require following Doron Roberts-Kedes's patch.
"net/tls: Calculate nsg for zerocopy path without skb_cow_data."
include/net/tls.h | 4 -
net/tls/tls_sw.c | 238 --
2 files changed, 142 insertions(+), 100 deletions(-)
diff --git a/include/net/tls.h b/include/net/tls.h
index d8b3b6578c01..d5c683e8bb22 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -124,10 +124,6 @@ struct tls_sw_context_rx {
struct sk_buff *recv_pkt;
u8 control;
bool decrypted;
-
- char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE];
- char rx_aad_plaintext[TLS_AAD_SPACE_SIZE];
-
};
struct tls_record_info {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 83d67df33f0c..52fbe727d7c1 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -48,19 +48,13 @@ static int tls_do_decryption(struct sock *sk,
struct scatterlist *sgout,
char *iv_recv,
size_t data_len,
-struct sk_buff *skb,
-gfp_t flags)
+struct aead_request *aead_req)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- struct aead_request *aead_req;
-
int ret;
- aead_req = aead_request_alloc(ctx->aead_recv, flags);
- if (!aead_req)
- return -ENOMEM;
-
+ aead_request_set_tfm(aead_req, ctx->aead_recv);
aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
aead_request_set_crypt(aead_req, sgin, sgout,
data_len + tls_ctx->rx.tag_size,
@@ -69,8 +63,6 @@ static int tls_do_decryption(struct sock *sk,
crypto_req_done, >async_wait);
ret = crypto_wait_req(crypto_aead_decrypt(aead_req), >async_wait);
-
- aead_request_free(aead_req);
return ret;
}
@@ -657,8 +649,132 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int
flags,
return skb;
}
+/* This function decrypts the input skb into either out_iov or in out_sg
+ * or in skb buffers itself. The input parameter 'zc' indicates if
+ * zero-copy mode needs to be tried or not. With zero-copy mode, either
+ * out_iov or out_sg must be non-NULL. In case both out_iov and out_sg are
+ * NULL, then the decryption happens inside skb buffers itself, i.e.
+ * zero-copy gets disabled and 'zc' is updated.
+ */
+
+static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
+ struct iov_iter *out_iov,
+ struct scatterlist *out_sg,
+ int *chunk, bool *zc)
+{
+ struct tls_context *tls_ctx = tls_get_ctx(sk);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+ struct strp_msg *rxm = strp_msg(skb);
+ int n_sgin, n_sgout, nsg, mem_size, aead_size, err, pages = 0;
+ struct aead_request *aead_req;
+ struct sk_buff *unused;
+ u8 *aad, *iv, *mem = NULL;
+ struct scatterlist *sgin = NULL;
+ struct scatterlist *sgout = NULL;
+ const int data_len = rxm->full_len - tls_ctx->rx.overhead_size;
+
+ if (*zc && (out_iov || out_sg)) {
+ if (out_iov)
+ n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1;
+ else
+ n_sgout = sg_nents(out_sg);
+ } else {
+ n_sgout = 0;
+ *zc = false;
+ }
+
+ n_sgin = skb_cow_data(skb, 0, );
+ if (n_sgin < 1)
+ return -EBADMSG;
+
+ /* Increment to accommodate AAD */
+ n_sgin = n_sgin + 1;
+
+ nsg = n_sgin + n_sgout;
+
+ aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv);
+ mem_size = aead_size + (nsg * sizeof(struct scatterlist));
+ mem_size = mem_size + TLS_AAD_SPACE_SIZE;
+ mem_size = mem_size + crypto_aead_ivsize(ctx->aead_recv);
+
+ /* Allocate a single block of memory which contains
+* aead_req || sgin[] || sgout[] || aad || iv.
+* This order achieves correct alignment for aead_req, sgin, sgout.
+*/
+ mem = kmalloc(mem_size, sk->sk_allocation);
+ if (!mem)
+ return -ENOMEM;
+
+ /* Segment the allocated memory */
+ aead_req = (struct aead_request *)mem;
+ sgin =
