aboutgitcodebugslistschat
path: root/tcp_splice.c
diff options
context:
space:
mode:
authorDavid Gibson <david@gibson.dropbear.id.au>2023-11-30 13:02:18 +1100
committerStefano Brivio <sbrivio@redhat.com>2023-12-04 09:51:24 +0100
commit705549f83494ebd23987e87de38045d8200b4efd (patch)
treed7dc4ca2516549e3c2f1e2b2252ffedd176d243e /tcp_splice.c
parent788d2fe3ce7231b520b139712d721e9d481b49ea (diff)
downloadpasst-705549f83494ebd23987e87de38045d8200b4efd.tar
passt-705549f83494ebd23987e87de38045d8200b4efd.tar.gz
passt-705549f83494ebd23987e87de38045d8200b4efd.tar.bz2
passt-705549f83494ebd23987e87de38045d8200b4efd.tar.lz
passt-705549f83494ebd23987e87de38045d8200b4efd.tar.xz
passt-705549f83494ebd23987e87de38045d8200b4efd.tar.zst
passt-705549f83494ebd23987e87de38045d8200b4efd.zip
flow,tcp: Use epoll_ref type including flow and side
Currently TCP uses the 'flow' epoll_ref field for both connected sockets and timers, which consists of just the index of the relevant flow (connection). This is just fine for timers, for while it obviously works, it's subtly incomplete for sockets on spliced connections. In that case we want to know which side of the connection the event is occurring on as well as which connection. At present, we deduce that information by looking at the actual fd, and comparing it to the fds of the sockets on each side. When we use the flow table for more things, we expect more cases where something will need to know a specific side of a specific flow for an event, but nothing more. Therefore add a new 'flowside' epoll_ref field, with exactly that information. We use it for TCP connected sockets. This allows us to directly know the side for spliced connections. For "tap" connections, it's pretty meaningless, since the side is always the socket side. It still makes logical sense though, and it may become important for future flow table work. Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Diffstat (limited to 'tcp_splice.c')
-rw-r--r--tcp_splice.c37
1 files changed, 12 insertions, 25 deletions
diff --git a/tcp_splice.c b/tcp_splice.c
index 4ab0813..69ea79d 100644
--- a/tcp_splice.c
+++ b/tcp_splice.c
@@ -128,8 +128,10 @@ static int tcp_splice_epoll_ctl(const struct ctx *c,
{
int m = conn->in_epoll ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
union epoll_ref ref[SIDES] = {
- { .type = EPOLL_TYPE_TCP, .fd = conn->s[0], .flow = FLOW_IDX(conn) },
- { .type = EPOLL_TYPE_TCP, .fd = conn->s[1], .flow = FLOW_IDX(conn) }
+ { .type = EPOLL_TYPE_TCP, .fd = conn->s[0],
+ .flowside = FLOW_SIDX(conn, 0) },
+ { .type = EPOLL_TYPE_TCP, .fd = conn->s[1],
+ .flowside = FLOW_SIDX(conn, 1) }
};
struct epoll_event ev[SIDES] = { { .data.u64 = ref[0].u64 },
{ .data.u64 = ref[1].u64 } };
@@ -481,13 +483,13 @@ bool tcp_splice_conn_from_sock(const struct ctx *c,
* tcp_splice_sock_handler() - Handler for socket mapped to spliced connection
* @c: Execution context
* @conn: Connection state
- * @s: Socket fd on which an event has occurred
+ * @side: Side of the connection on which an event has occurred
* @events: epoll events bitmap
*
* #syscalls:pasta splice
*/
void tcp_splice_sock_handler(struct ctx *c, struct tcp_splice_conn *conn,
- int s, uint32_t events)
+ int side, uint32_t events)
{
uint8_t lowat_set_flag, lowat_act_flag;
int eof, never_read;
@@ -507,30 +509,15 @@ void tcp_splice_sock_handler(struct ctx *c, struct tcp_splice_conn *conn,
}
if (events & EPOLLOUT) {
- if (s == conn->s[0]) {
- conn_event(c, conn, ~OUT_WAIT_0);
- fromside = 1;
- } else {
- conn_event(c, conn, ~OUT_WAIT_1);
- fromside = 0;
- }
+ fromside = !side;
+ conn_event(c, conn, side == 0 ? ~OUT_WAIT_0 : ~OUT_WAIT_1);
} else {
- fromside = s == conn->s[0] ? 0 : 1;
- }
-
- if (events & EPOLLRDHUP) {
- if (s == conn->s[0])
- conn_event(c, conn, FIN_RCVD_0);
- else
- conn_event(c, conn, FIN_RCVD_1);
+ fromside = side;
}
- if (events & EPOLLHUP) {
- if (s == conn->s[0])
- conn_event(c, conn, FIN_SENT_0); /* Fake, but implied */
- else
- conn_event(c, conn, FIN_SENT_1);
- }
+ if (events & EPOLLRDHUP)
+ /* For side 0 this is fake, but implied */
+ conn_event(c, conn, side == 0 ? FIN_RCVD_0 : FIN_RCVD_1);
swap:
eof = 0;