tmp_suning_uos_patched/net/ipv4/tcp_fastopen.c
Christoph Paasch dfea2aa654 tcp: Do not call tcp_fastopen_reset_cipher from interrupt context
tcp_fastopen_reset_cipher really cannot be called from interrupt
context. It allocates the tcp_fastopen_context with GFP_KERNEL and
calls crypto_alloc_cipher, which allocates all kind of stuff with
GFP_KERNEL.

Thus, we might sleep when the key-generation is triggered by an
incoming TFO cookie-request which would then happen in interrupt-
context, as shown by enabling CONFIG_DEBUG_ATOMIC_SLEEP:

[   36.001813] BUG: sleeping function called from invalid context at mm/slub.c:1266
[   36.003624] in_atomic(): 1, irqs_disabled(): 0, pid: 1016, name: packetdrill
[   36.004859] CPU: 1 PID: 1016 Comm: packetdrill Not tainted 4.1.0-rc7 #14
[   36.006085] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
[   36.008250]  00000000000004f2 ffff88007f8838a8 ffffffff8171d53a ffff880075a084a8
[   36.009630]  ffff880075a08000 ffff88007f8838c8 ffffffff810967d3 ffff88007f883928
[   36.011076]  0000000000000000 ffff88007f8838f8 ffffffff81096892 ffff88007f89be00
[   36.012494] Call Trace:
[   36.012953]  <IRQ>  [<ffffffff8171d53a>] dump_stack+0x4f/0x6d
[   36.014085]  [<ffffffff810967d3>] ___might_sleep+0x103/0x170
[   36.015117]  [<ffffffff81096892>] __might_sleep+0x52/0x90
[   36.016117]  [<ffffffff8118e887>] kmem_cache_alloc_trace+0x47/0x190
[   36.017266]  [<ffffffff81680d82>] ? tcp_fastopen_reset_cipher+0x42/0x130
[   36.018485]  [<ffffffff81680d82>] tcp_fastopen_reset_cipher+0x42/0x130
[   36.019679]  [<ffffffff81680f01>] tcp_fastopen_init_key_once+0x61/0x70
[   36.020884]  [<ffffffff81680f2c>] __tcp_fastopen_cookie_gen+0x1c/0x60
[   36.022058]  [<ffffffff816814ff>] tcp_try_fastopen+0x58f/0x730
[   36.023118]  [<ffffffff81671788>] tcp_conn_request+0x3e8/0x7b0
[   36.024185]  [<ffffffff810e3872>] ? __module_text_address+0x12/0x60
[   36.025327]  [<ffffffff8167b2e1>] tcp_v4_conn_request+0x51/0x60
[   36.026410]  [<ffffffff816727e0>] tcp_rcv_state_process+0x190/0xda0
[   36.027556]  [<ffffffff81661f97>] ? __inet_lookup_established+0x47/0x170
[   36.028784]  [<ffffffff8167c2ad>] tcp_v4_do_rcv+0x16d/0x3d0
[   36.029832]  [<ffffffff812e6806>] ? security_sock_rcv_skb+0x16/0x20
[   36.030936]  [<ffffffff8167cc8a>] tcp_v4_rcv+0x77a/0x7b0
[   36.031875]  [<ffffffff816af8c3>] ? iptable_filter_hook+0x33/0x70
[   36.032953]  [<ffffffff81657d22>] ip_local_deliver_finish+0x92/0x1f0
[   36.034065]  [<ffffffff81657f1a>] ip_local_deliver+0x9a/0xb0
[   36.035069]  [<ffffffff81657c90>] ? ip_rcv+0x3d0/0x3d0
[   36.035963]  [<ffffffff81657569>] ip_rcv_finish+0x119/0x330
[   36.036950]  [<ffffffff81657ba7>] ip_rcv+0x2e7/0x3d0
[   36.037847]  [<ffffffff81610652>] __netif_receive_skb_core+0x552/0x930
[   36.038994]  [<ffffffff81610a57>] __netif_receive_skb+0x27/0x70
[   36.040033]  [<ffffffff81610b72>] process_backlog+0xd2/0x1f0
[   36.041025]  [<ffffffff81611482>] net_rx_action+0x122/0x310
[   36.042007]  [<ffffffff81076743>] __do_softirq+0x103/0x2f0
[   36.042978]  [<ffffffff81723e3c>] do_softirq_own_stack+0x1c/0x30

This patch moves the call to tcp_fastopen_init_key_once to the places
where a listener socket creates its TFO-state, which always happens in
user-context (either from the setsockopt, or implicitly during the
listen()-call)

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
Fixes: 222e83d2e0 ("tcp: switch tcp_fastopen key generation to net_get_random_once")
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-06-23 02:38:10 -07:00

314 lines
9.1 KiB
C

#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <net/inetpeer.h>
#include <net/tcp.h>
int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE;
struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
void tcp_fastopen_init_key_once(bool publish)
{
static u8 key[TCP_FASTOPEN_KEY_LENGTH];
/* tcp_fastopen_reset_cipher publishes the new context
* atomically, so we allow this race happening here.
*
* All call sites of tcp_fastopen_cookie_gen also check
* for a valid cookie, so this is an acceptable risk.
*/
if (net_get_random_once(key, sizeof(key)) && publish)
tcp_fastopen_reset_cipher(key, sizeof(key));
}
static void tcp_fastopen_ctx_free(struct rcu_head *head)
{
struct tcp_fastopen_context *ctx =
container_of(head, struct tcp_fastopen_context, rcu);
crypto_free_cipher(ctx->tfm);
kfree(ctx);
}
int tcp_fastopen_reset_cipher(void *key, unsigned int len)
{
int err;
struct tcp_fastopen_context *ctx, *octx;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
ctx->tfm = crypto_alloc_cipher("aes", 0, 0);
if (IS_ERR(ctx->tfm)) {
err = PTR_ERR(ctx->tfm);
error: kfree(ctx);
pr_err("TCP: TFO aes cipher alloc error: %d\n", err);
return err;
}
err = crypto_cipher_setkey(ctx->tfm, key, len);
if (err) {
pr_err("TCP: TFO cipher key error: %d\n", err);
crypto_free_cipher(ctx->tfm);
goto error;
}
memcpy(ctx->key, key, len);
spin_lock(&tcp_fastopen_ctx_lock);
octx = rcu_dereference_protected(tcp_fastopen_ctx,
lockdep_is_held(&tcp_fastopen_ctx_lock));
rcu_assign_pointer(tcp_fastopen_ctx, ctx);
spin_unlock(&tcp_fastopen_ctx_lock);
if (octx)
call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
return err;
}
static bool __tcp_fastopen_cookie_gen(const void *path,
struct tcp_fastopen_cookie *foc)
{
struct tcp_fastopen_context *ctx;
bool ok = false;
rcu_read_lock();
ctx = rcu_dereference(tcp_fastopen_ctx);
if (ctx) {
crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
foc->len = TCP_FASTOPEN_COOKIE_SIZE;
ok = true;
}
rcu_read_unlock();
return ok;
}
/* Generate the fastopen cookie by doing aes128 encryption on both
* the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
* addresses. For the longer IPv6 addresses use CBC-MAC.
*
* XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
*/
static bool tcp_fastopen_cookie_gen(struct request_sock *req,
struct sk_buff *syn,
struct tcp_fastopen_cookie *foc)
{
if (req->rsk_ops->family == AF_INET) {
const struct iphdr *iph = ip_hdr(syn);
__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
return __tcp_fastopen_cookie_gen(path, foc);
}
#if IS_ENABLED(CONFIG_IPV6)
if (req->rsk_ops->family == AF_INET6) {
const struct ipv6hdr *ip6h = ipv6_hdr(syn);
struct tcp_fastopen_cookie tmp;
if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
struct in6_addr *buf = (struct in6_addr *) tmp.val;
int i;
for (i = 0; i < 4; i++)
buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
return __tcp_fastopen_cookie_gen(buf, foc);
}
}
#endif
return false;
}
static bool tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct dst_entry *dst,
struct request_sock *req)
{
struct tcp_sock *tp;
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
u32 end_seq;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (!child)
return false;
spin_lock(&queue->fastopenq->lock);
queue->fastopenq->qlen++;
spin_unlock(&queue->fastopenq->lock);
/* Initialize the child socket. Have to fix some values to take
* into account the child is a Fast Open socket and is created
* only out of the bits carried in the SYN packet.
*/
tp = tcp_sk(child);
tp->fastopen_rsk = req;
tcp_rsk(req)->tfo_listener = true;
/* RFC1323: The window in SYN & SYN/ACK segments is never
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the SYN table of the parent
* because it's been added to the accept queue directly.
*/
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
atomic_set(&req->rsk_refcnt, 1);
/* Add the child socket directly into the accept queue */
inet_csk_reqsk_queue_add(sk, req, child);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
tcp_init_metrics(child);
tcp_init_buffer_space(child);
/* Queue the data carried in the SYN packet. We need to first
* bump skb's refcnt because the caller will attempt to free it.
* Note that IPv6 might also have used skb_get() trick
* in tcp_v6_conn_request() to keep this SYN around (treq->pktopts)
* So we need to eventually get a clone of the packet,
* before inserting it in sk_receive_queue.
*
* XXX (TFO) - we honor a zero-payload TFO request for now,
* (any reason not to?) but no need to queue the skb since
* there is no data. How about SYN+FIN?
*/
end_seq = TCP_SKB_CB(skb)->end_seq;
if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
struct sk_buff *skb2;
if (unlikely(skb_shared(skb)))
skb2 = skb_clone(skb, GFP_ATOMIC);
else
skb2 = skb_get(skb);
if (likely(skb2)) {
skb_dst_drop(skb2);
__skb_pull(skb2, tcp_hdrlen(skb));
skb_set_owner_r(skb2, child);
__skb_queue_tail(&child->sk_receive_queue, skb2);
tp->syn_data_acked = 1;
/* u64_stats_update_begin(&tp->syncp) not needed here,
* as we certainly are not changing upper 32bit value (0)
*/
tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
} else {
end_seq = TCP_SKB_CB(skb)->seq + 1;
}
}
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
sk->sk_data_ready(sk);
bh_unlock_sock(child);
sock_put(child);
WARN_ON(!req->sk);
return true;
}
static bool tcp_fastopen_queue_check(struct sock *sk)
{
struct fastopen_queue *fastopenq;
/* Make sure the listener has enabled fastopen, and we don't
* exceed the max # of pending TFO requests allowed before trying
* to validating the cookie in order to avoid burning CPU cycles
* unnecessarily.
*
* XXX (TFO) - The implication of checking the max_qlen before
* processing a cookie request is that clients can't differentiate
* between qlen overflow causing Fast Open to be disabled
* temporarily vs a server not supporting Fast Open at all.
*/
fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
if (!fastopenq || fastopenq->max_qlen == 0)
return false;
if (fastopenq->qlen >= fastopenq->max_qlen) {
struct request_sock *req1;
spin_lock(&fastopenq->lock);
req1 = fastopenq->rskq_rst_head;
if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) {
spin_unlock(&fastopenq->lock);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
return false;
}
fastopenq->rskq_rst_head = req1->dl_next;
fastopenq->qlen--;
spin_unlock(&fastopenq->lock);
reqsk_put(req1);
}
return true;
}
/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
* may be updated and return the client in the SYN-ACK later. E.g., Fast Open
* cookie request (foc->len == 0).
*/
bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
struct dst_entry *dst)
{
struct tcp_fastopen_cookie valid_foc = { .len = -1 };
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
if (foc->len == 0) /* Client requests a cookie */
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
(syn_data || foc->len >= 0) &&
tcp_fastopen_queue_check(sk))) {
foc->len = -1;
return false;
}
if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
goto fastopen;
if (foc->len >= 0 && /* Client presents or requests a cookie */
tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
foc->len == valid_foc.len &&
!memcmp(foc->val, valid_foc.val, foc->len)) {
/* Cookie is valid. Create a (full) child socket to accept
* the data in SYN before returning a SYN-ACK to ack the
* data. If we fail to create the socket, fall back and
* ack the ISN only but includes the same cookie.
*
* Note: Data-less SYN with valid cookie is allowed to send
* data in SYN_RECV state.
*/
fastopen:
if (tcp_fastopen_create_child(sk, skb, dst, req)) {
foc->len = -1;
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENPASSIVE);
return true;
}
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
} else if (foc->len > 0) /* Client presents an invalid cookie */
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
valid_foc.exp = foc->exp;
*foc = valid_foc;
return false;
}
EXPORT_SYMBOL(tcp_try_fastopen);