From 031097d9e079e40dce401031d1012e83d80eaf01 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 27 Nov 2019 12:16:41 -0800
Subject: net: skmsg: fix TLS 1.3 crash with full sk_msg

TLS 1.3 started using the entry at the end of the SG array
for chaining-in the single byte content type entry. This mostly
works:

[ E E E E E E . . ]
  ^           ^
   start       end

                 E < content type
               /
[ E E E E E E C . ]
  ^           ^
   start       end

(Where E denotes a populated SG entry; C denotes a chaining entry.)

If the array is full, however, the end will point to the start:

[ E E E E E E E E ]
  ^
   start
   end

And we end up overwriting the start:

    E < content type
   /
[ C E E E E E E E ]
  ^
   start
   end

The sg array is supposed to be a circular buffer with start and
end markers pointing anywhere. In case where start > end
(i.e. the circular buffer has "wrapped") there is an extra entry
reserved at the end to chain the two halves together.

[ E E E E E E . . l ]

(Where l is the reserved entry for "looping" back to front.

As suggested by John, let's reserve another entry for chaining
SG entries after the main circular buffer. Note that this entry
has to be pointed to by the end entry so its position is not fixed.

Examples of full messages:

[ E E E E E E E E . l ]
  ^               ^
   start           end

   <---------------.
[ E E . E E E E E E l ]
      ^ ^
   end   start

Now the end will always point to an unused entry, so TLS 1.3
can always use it.

Fixes: 130b392c6cd6 ("net: tls: Add tls 1.3 support")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c  | 8 ++++----
 net/core/skmsg.c   | 2 +-
 net/ipv4/tcp_bpf.c | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'net')

diff --git a/net/core/filter.c b/net/core/filter.c
index b0ed048585ba..f1e703eed3d2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2299,7 +2299,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	WARN_ON_ONCE(last_sge == first_sge);
 	shift = last_sge > first_sge ?
 		last_sge - first_sge - 1 :
-		MAX_SKB_FRAGS - first_sge + last_sge - 1;
+		NR_MSG_FRAG_IDS - first_sge + last_sge - 1;
 	if (!shift)
 		goto out;
 
@@ -2308,8 +2308,8 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	do {
 		u32 move_from;
 
-		if (i + shift >= MAX_MSG_FRAGS)
-			move_from = i + shift - MAX_MSG_FRAGS;
+		if (i + shift >= NR_MSG_FRAG_IDS)
+			move_from = i + shift - NR_MSG_FRAG_IDS;
 		else
 			move_from = i + shift;
 		if (move_from == msg->sg.end)
@@ -2323,7 +2323,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start,
 	} while (1);
 
 	msg->sg.end = msg->sg.end - shift > msg->sg.end ?
-		      msg->sg.end - shift + MAX_MSG_FRAGS :
+		      msg->sg.end - shift + NR_MSG_FRAG_IDS :
 		      msg->sg.end - shift;
 out:
 	msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index a469d2124f3f..ded2d5227678 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -421,7 +421,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	copied = skb->len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
-	msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge;
+	msg->sg.end = num_sge;
 	msg->skb = skb;
 
 	sk_psock_queue_msg(psock, msg);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 8a56e09cfb0e..e38705165ac9 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
 static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 				struct sk_msg *msg, int *copied, int flags)
 {
-	bool cork = false, enospc = msg->sg.start == msg->sg.end;
+	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
 	u32 tosend, delta = 0;
 	int ret;
-- 
cgit v1.2.3