net/tls: Inform user space about send buffer availability

A previous fix ("tls: Fix write space handling") assumed that
user space application gets informed about the socket send buffer
availability when tls_push_sg() gets called. Inside tls_push_sg(), in
case do_tcp_sendpages() returns 0, the function returns without calling
ctx->sk_write_space. Further, the new function tls_sw_write_space()
did not invoke ctx->sk_write_space. This leads to situation that user
space application encounters a lockup always waiting for socket send
buffer to become available.

Rather than call ctx->sk_write_space from tls_push_sg(), it should be
called from tls_write_space. So whenever tcp stack invokes
sk->sk_write_space after freeing socket send buffer, we always declare
the same to user space by the way of invoking ctx->sk_write_space.

Fixes: 7463d3a2db ("tls: Fix write space handling")
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/tls/tls_device.c

@@ -558,9 +558,6 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 					     MSG_DONTWAIT | MSG_NOSIGNAL);
 		sk->sk_allocation = sk_allocation;
 	}
-
-	if (!rc)
-		ctx->sk_write_space(sk);
 }
 
 void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)

net/tls/tls_main.c

@@ -146,7 +146,6 @@ retry:
 	}
 
 	ctx->in_tcp_sendpages = false;
-	ctx->sk_write_space(sk);
 
 	return 0;
 }
@@ -228,6 +227,8 @@ static void tls_write_space(struct sock *sk)
 	else
 #endif
 		tls_sw_write_space(sk, ctx);
+
+	ctx->sk_write_space(sk);
 }
 
 static void tls_ctx_free(struct tls_context *ctx)