rpc: Add -EPERM processing for xs_udp_send_request()
If an iptables drop rule is added for an nfs server, the client can end up in a softlockup. Because of the way that xs_sendpages() is structured, the -EPERM is ignored since the prior bits of the packet may have been successfully queued and thus xs_sendpages() returns a non-zero value. Then, xs_udp_send_request() thinks that because some bits were queued it should return -EAGAIN. We then try the request again and again, resulting in cpu spinning. Reproducer: 1) open a file on the nfs server '/nfs/foo' (mounted using udp) 2) iptables -A OUTPUT -d <nfs server ip> -j DROP 3) write to /nfs/foo 4) close /nfs/foo 5) iptables -D OUTPUT -d <nfs server ip> -j DROP The softlockup occurs in step 4 above. The previous patch, allows xs_sendpages() to return both a sent count and any error values that may have occurred. Thus, if we get an -EPERM, return that to the higher level code. With this patch in place we can successfully abort the above sequence and avoid the softlockup. I also tried the above test case on an nfs mount on tcp and although the system does not softlockup, I still ended up with the 'hung_task' firing after 120 seconds, due to the i/o being stuck. The tcp case appears a bit harder to fix, since -EPERM appears to get ignored much lower down in the stack and does not propogate up to xs_sendpages(). This case is not quite as insidious as the softlockup and it is not addressed here. Reported-by: Yigong Lou <ylou@akamai.com> Signed-off-by: Jason Baron <jbaron@akamai.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
This commit is contained in:
parent
f279cd008f
commit
3dedbb5ca1
|
@ -1913,6 +1913,7 @@ call_transmit_status(struct rpc_task *task)
|
||||||
case -EHOSTDOWN:
|
case -EHOSTDOWN:
|
||||||
case -EHOSTUNREACH:
|
case -EHOSTUNREACH:
|
||||||
case -ENETUNREACH:
|
case -ENETUNREACH:
|
||||||
|
case -EPERM:
|
||||||
if (RPC_IS_SOFTCONN(task)) {
|
if (RPC_IS_SOFTCONN(task)) {
|
||||||
xprt_end_transmit(task);
|
xprt_end_transmit(task);
|
||||||
rpc_exit(task, task->tk_status);
|
rpc_exit(task, task->tk_status);
|
||||||
|
@ -2018,6 +2019,7 @@ call_status(struct rpc_task *task)
|
||||||
case -EHOSTDOWN:
|
case -EHOSTDOWN:
|
||||||
case -EHOSTUNREACH:
|
case -EHOSTUNREACH:
|
||||||
case -ENETUNREACH:
|
case -ENETUNREACH:
|
||||||
|
case -EPERM:
|
||||||
if (RPC_IS_SOFTCONN(task)) {
|
if (RPC_IS_SOFTCONN(task)) {
|
||||||
rpc_exit(task, status);
|
rpc_exit(task, status);
|
||||||
break;
|
break;
|
||||||
|
|
|
@ -644,6 +644,10 @@ static int xs_udp_send_request(struct rpc_task *task)
|
||||||
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
|
dprintk("RPC: xs_udp_send_request(%u) = %d\n",
|
||||||
xdr->len - req->rq_bytes_sent, status);
|
xdr->len - req->rq_bytes_sent, status);
|
||||||
|
|
||||||
|
/* firewall is blocking us, don't return -EAGAIN or we end up looping */
|
||||||
|
if (status == -EPERM)
|
||||||
|
goto process_status;
|
||||||
|
|
||||||
if (sent > 0 || status == 0) {
|
if (sent > 0 || status == 0) {
|
||||||
req->rq_xmit_bytes_sent += sent;
|
req->rq_xmit_bytes_sent += sent;
|
||||||
if (sent >= req->rq_slen)
|
if (sent >= req->rq_slen)
|
||||||
|
@ -652,6 +656,7 @@ static int xs_udp_send_request(struct rpc_task *task)
|
||||||
status = -EAGAIN;
|
status = -EAGAIN;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
process_status:
|
||||||
switch (status) {
|
switch (status) {
|
||||||
case -ENOTSOCK:
|
case -ENOTSOCK:
|
||||||
status = -ENOTCONN;
|
status = -ENOTCONN;
|
||||||
|
@ -667,6 +672,7 @@ static int xs_udp_send_request(struct rpc_task *task)
|
||||||
case -ENOBUFS:
|
case -ENOBUFS:
|
||||||
case -EPIPE:
|
case -EPIPE:
|
||||||
case -ECONNREFUSED:
|
case -ECONNREFUSED:
|
||||||
|
case -EPERM:
|
||||||
/* When the server has died, an ICMP port unreachable message
|
/* When the server has died, an ICMP port unreachable message
|
||||||
* prompts ECONNREFUSED. */
|
* prompts ECONNREFUSED. */
|
||||||
clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
|
clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
|
||||||
|
|
Loading…
Reference in a new issue