[PATCH net-next] tls: Skip zerocopy path for ITER_KVEC

[PATCH net-next] tls: Skip zerocopy path for ITER_KVEC

[Doron Roberts-Kedes]

The zerocopy path ultimately calls iov_iter_get_pages, which defines the
step function for ITER_KVECs as simply, return -EFAULT. Taking the
non-zerocopy path for ITER_KVECs avoids the unnecessary fallback. 

See https://lore.kernel.org/lkml/20150401023311.GL29656@ZenIV.linux.org.uk/T/#u
for a discussion of why zerocopy for vmalloc data is not a good idea. 

Discovered while testing NBD traffic encrypted with ktls.

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
---
 net/tls/tls_sw.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4618f1c31137..ef15e35232dd 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -426,7 +426,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			full_record = true;
 		}
 
-		if (full_record || eor) {
+		bool iskvec = msg->msg_iter.type & ITER_KVEC;
+		if (!iskvec && (full_record || eor)) {
 			ret = zerocopy_from_iter(sk, &msg->msg_iter,
 				try_to_copy, &ctx->sg_plaintext_num_elem,
 				&ctx->sg_plaintext_size,
@@ -804,7 +805,8 @@ int tls_sw_recvmsg(struct sock *sk,
 			page_count = iov_iter_npages(&msg->msg_iter,
 						     MAX_SKB_FRAGS);
 			to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
-			if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
+			bool iskvec = msg->msg_iter.type & ITER_KVEC;
+			if (!iskvec && to_copy <= len && page_count < MAX_SKB_FRAGS &&
 			    likely(!(flags & MSG_PEEK)))  {
 				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
 				int pages = 0;
-- 
2.17.1

Re: [PATCH net-next] tls: Skip zerocopy path for ITER_KVEC

[David Miller]

From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Fri, 20 Jul 2018 11:19:00 -0700

> The zerocopy path ultimately calls iov_iter_get_pages, which defines the
> step function for ITER_KVECs as simply, return -EFAULT. Taking the
> non-zerocopy path for ITER_KVECs avoids the unnecessary fallback. 
> 
> See https://lore.kernel.org/lkml/20150401023311.GL29656@ZenIV.linux.org.uk/T/#u
> for a discussion of why zerocopy for vmalloc data is not a good idea. 
> 
> Discovered while testing NBD traffic encrypted with ktls.
> 
> Fixes: c46234ebb4d1 ("tls: RX path for ktls")
> Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>

Applied to net-next, thanks.

Re: [PATCH net-next] tls: Skip zerocopy path for ITER_KVEC

[David Miller]

From: David Miller <davem@davemloft.net>
Date: Tue, 24 Jul 2018 14:38:02 -0700 (PDT)

> From: Doron Roberts-Kedes <doronrk@fb.com>
> Date: Fri, 20 Jul 2018 11:19:00 -0700
> 
>> The zerocopy path ultimately calls iov_iter_get_pages, which defines the
>> step function for ITER_KVECs as simply, return -EFAULT. Taking the
>> non-zerocopy path for ITER_KVECs avoids the unnecessary fallback. 
>> 
>> See https://lore.kernel.org/lkml/20150401023311.GL29656@ZenIV.linux.org.uk/T/#u
>> for a discussion of why zerocopy for vmalloc data is not a good idea. 
>> 
>> Discovered while testing NBD traffic encrypted with ktls.
>> 
>> Fixes: c46234ebb4d1 ("tls: RX path for ktls")
>> Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
> 
> Applied to net-next, thanks.

Actually, I reverted.  Please fix this warning:

net/tls/tls_sw.c: In function ‘tls_sw_sendmsg’:
net/tls/tls_sw.c:414:3: warning: ISO C90 forbids mixed declarations and code [-Wdeclaration-after-statement]
   bool iskvec = msg->msg_iter.type & ITER_KVEC;
   ^~~~
net/tls/tls_sw.c: In function ‘tls_sw_recvmsg’:
net/tls/tls_sw.c:823:4: warning: ISO C90 forbids mixed declarations and code [-Wdeclaration-after-statement]
    bool iskvec = msg->msg_iter.type & ITER_KVEC;
    ^~~~

[PATCH net-next v2] tls: Skip zerocopy path for ITER_KVEC

[Doron Roberts-Kedes]

The zerocopy path ultimately calls iov_iter_get_pages, which defines the
step function for ITER_KVECs as simply, return -EFAULT. Taking the
non-zerocopy path for ITER_KVECs avoids the unnecessary fallback.

See https://lore.kernel.org/lkml/20150401023311.GL29656@ZenIV.linux.org.uk/T/#u
for a discussion of why zerocopy for vmalloc data is not a good idea.

Discovered while testing NBD traffic encrypted with ktls.

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
---
 net/tls/tls_sw.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1f3d9789af30..da584dc7d633 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -377,6 +377,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int record_room;
 	bool full_record;
 	int orig_size;
+	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -ENOTSUPP;
@@ -425,8 +426,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 			try_to_copy -= required_size - ctx->sg_encrypted_size;
 			full_record = true;
 		}
-
-		if (full_record || eor) {
+		if (!is_kvec && (full_record || eor)) {
 			ret = zerocopy_from_iter(sk, &msg->msg_iter,
 				try_to_copy, &ctx->sg_plaintext_num_elem,
 				&ctx->sg_plaintext_size,
@@ -764,6 +764,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool cmsg = false;
 	int target, err = 0;
 	long timeo;
+	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
 
 	flags |= nonblock;
 
@@ -807,7 +808,7 @@ int tls_sw_recvmsg(struct sock *sk,
 			page_count = iov_iter_npages(&msg->msg_iter,
 						     MAX_SKB_FRAGS);
 			to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
-			if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
+			if (!is_kvec && to_copy <= len && page_count < MAX_SKB_FRAGS &&
 			    likely(!(flags & MSG_PEEK)))  {
 				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
 				int pages = 0;
-- 
2.17.1