Make AF_ALG sendmsg() support MSG_SPLICE_PAGES. This causes pages to be
spliced from the source iterator if possible (the iterator must be
ITER_BVEC and the pages must be spliceable).
This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.
[!] Note that this makes use of netfs_extract_iter_to_sg() from netfslib.
This probably needs moving to core code somewhere.
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx>
cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
cc: Eric Dumazet <edumazet@xxxxxxxxxx>
cc: Jakub Kicinski <kuba@xxxxxxxxxx>
cc: Paolo Abeni <pabeni@xxxxxxxxxx>
cc: Jens Axboe <axboe@xxxxxxxxx>
cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
cc: linux-crypto@xxxxxxxxxxxxxxx
cc: netdev@xxxxxxxxxxxxxxx
---
crypto/Kconfig | 1 +
crypto/af_alg.c | 29 +++++++++++++++++++++++++++--
crypto/algif_aead.c | 22 +++++++++++-----------
crypto/algif_skcipher.c | 8 ++++----
4 files changed, 43 insertions(+), 17 deletions(-)
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 9c86f7045157..8c04ecbb4395 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -1297,6 +1297,7 @@ menu "Userspace interface"
config CRYPTO_USER_API
tristate
+ select NETFS_SUPPORT # for netfs_extract_iter_to_sg()
config CRYPTO_USER_API_HASH
tristate "Hash algorithms"
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index feb989b32606..80ab4f6e018c 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -22,6 +22,7 @@
#include <linux/sched/signal.h>
#include <linux/security.h>
#include <linux/string.h>
+#include <linux/netfs.h>
#include <keys/user-type.h>
#include <keys/trusted-type.h>
#include <keys/encrypted-type.h>
@@ -970,6 +971,10 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
bool init = false;
int err = 0;
+ if ((msg->msg_flags & MSG_SPLICE_PAGES) &&
+ !iov_iter_is_bvec(&msg->msg_iter))
+ return -EINVAL;
+
if (msg->msg_controllen) {
err = af_alg_cmsg_send(msg, &con);
if (err)
@@ -1015,7 +1020,7 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
while (size) {
struct scatterlist *sg;
size_t len = size;
- size_t plen;
+ ssize_t plen;
/* use the existing memory in an allocated page */
if (ctx->merge) {
@@ -1060,7 +1065,27 @@ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
if (sgl->cur)
sg_unmark_end(sg + sgl->cur - 1);
- if (1 /* TODO check MSG_SPLICE_PAGES */) {
+ if (msg->msg_flags & MSG_SPLICE_PAGES) {
+ struct sg_table sgtable = {
+ .sgl = sg,
+ .nents = sgl->cur,
+ .orig_nents = sgl->cur,
+ };
+
+ plen = netfs_extract_iter_to_sg(&msg->msg_iter, len,
+ &sgtable, MAX_SGL_ENTS, 0);
+ if (plen < 0) {
+ err = plen;
+ goto unlock;
+ }
+
+ for (; sgl->cur < sgtable.nents; sgl->cur++)
+ get_page(sg_page(&sg[sgl->cur]));
+ len -= plen;
+ ctx->used += plen;
+ copied += plen;
+ size -= plen;
+ } else {
do {
struct page *pg;
unsigned int i = sgl->cur;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 42493b4d8ce4..279eb17a1dfc 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -9,8 +9,8 @@
* The following concept of the memory management is used:
*
* The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is
- * filled by user space with the data submitted via sendpage/sendmsg. Filling
- * up the TX SGL does not cause a crypto operation -- the data will only be
+ * filled by user space with the data submitted via sendpage. Filling up
+ * the TX SGL does not cause a crypto operation -- the data will only be
* tracked by the kernel. Upon receipt of one recvmsg call, the caller must
* provide a buffer which is tracked with the RX SGL.
*
@@ -113,19 +113,19 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg,
}
/*
- * Data length provided by caller via sendmsg/sendpage that has not
- * yet been processed.
+ * Data length provided by caller via sendmsg that has not yet been
+ * processed.
*/
used = ctx->used;
/*
- * Make sure sufficient data is present -- note, the same check is
- * also present in sendmsg/sendpage. The checks in sendpage/sendmsg
- * shall provide an information to the data sender that something is
- * wrong, but they are irrelevant to maintain the kernel integrity.
- * We need this check here too in case user space decides to not honor
- * the error message in sendmsg/sendpage and still call recvmsg. This
- * check here protects the kernel integrity.
+ * Make sure sufficient data is present -- note, the same check is also
+ * present in sendmsg. The checks in sendmsg shall provide an
+ * information to the data sender that something is wrong, but they are
+ * irrelevant to maintain the kernel integrity. We need this check
+ * here too in case user space decides to not honor the error message
+ * in sendmsg and still call recvmsg. This check here protects the
+ * kernel integrity.
*/
if (!aead_sufficient_data(sk))
return -EINVAL;
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index ee8890ee8f33..021f9ce7e87c 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -9,10 +9,10 @@
* The following concept of the memory management is used:
*
* The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is
- * filled by user space with the data submitted via sendpage/sendmsg. Filling
- * up the TX SGL does not cause a crypto operation -- the data will only be
- * tracked by the kernel. Upon receipt of one recvmsg call, the caller must
- * provide a buffer which is tracked with the RX SGL.
+ * filled by user space with the data submitted via sendmsg. Filling up the TX
+ * SGL does not cause a crypto operation -- the data will only be tracked by
+ * the kernel. Upon receipt of one recvmsg call, the caller must provide a
+ * buffer which is tracked with the RX SGL.
*
* During the processing of the recvmsg operation, the cipher request is
* allocated and prepared. As part of the recvmsg operation, the processed
