linux/net/sched/sch_etf.c
Eric Dumazet a1211bf9a7 sched: etf: do not assume all sockets are full blown
skb->sk does not always point to a full blown socket,
we need to use sk_fullsock() before accessing fields which
only make sense on full socket.

BUG: KASAN: use-after-free in report_sock_error+0x286/0x300 net/sched/sch_etf.c:141
Read of size 1 at addr ffff88805eb9b245 by task syz-executor.5/9630

CPU: 1 PID: 9630 Comm: syz-executor.5 Not tainted 5.7.0-rc2-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x188/0x20d lib/dump_stack.c:118
 print_address_description.constprop.0.cold+0xd3/0x315 mm/kasan/report.c:382
 __kasan_report.cold+0x35/0x4d mm/kasan/report.c:511
 kasan_report+0x33/0x50 mm/kasan/common.c:625
 report_sock_error+0x286/0x300 net/sched/sch_etf.c:141
 etf_enqueue_timesortedlist+0x389/0x740 net/sched/sch_etf.c:170
 __dev_xmit_skb net/core/dev.c:3710 [inline]
 __dev_queue_xmit+0x154a/0x30a0 net/core/dev.c:4021
 neigh_hh_output include/net/neighbour.h:499 [inline]
 neigh_output include/net/neighbour.h:508 [inline]
 ip6_finish_output2+0xfb5/0x25b0 net/ipv6/ip6_output.c:117
 __ip6_finish_output+0x442/0xab0 net/ipv6/ip6_output.c:143
 ip6_finish_output+0x34/0x1f0 net/ipv6/ip6_output.c:153
 NF_HOOK_COND include/linux/netfilter.h:296 [inline]
 ip6_output+0x239/0x810 net/ipv6/ip6_output.c:176
 dst_output include/net/dst.h:435 [inline]
 NF_HOOK include/linux/netfilter.h:307 [inline]
 NF_HOOK include/linux/netfilter.h:301 [inline]
 ip6_xmit+0xe1a/0x2090 net/ipv6/ip6_output.c:280
 tcp_v6_send_synack+0x4e7/0x960 net/ipv6/tcp_ipv6.c:521
 tcp_rtx_synack+0x10d/0x1a0 net/ipv4/tcp_output.c:3916
 inet_rtx_syn_ack net/ipv4/inet_connection_sock.c:669 [inline]
 reqsk_timer_handler+0x4c2/0xb40 net/ipv4/inet_connection_sock.c:763
 call_timer_fn+0x1ac/0x780 kernel/time/timer.c:1405
 expire_timers kernel/time/timer.c:1450 [inline]
 __run_timers kernel/time/timer.c:1774 [inline]
 __run_timers kernel/time/timer.c:1741 [inline]
 run_timer_softirq+0x623/0x1600 kernel/time/timer.c:1787
 __do_softirq+0x26c/0x9f7 kernel/softirq.c:292
 invoke_softirq kernel/softirq.c:373 [inline]
 irq_exit+0x192/0x1d0 kernel/softirq.c:413
 exiting_irq arch/x86/include/asm/apic.h:546 [inline]
 smp_apic_timer_interrupt+0x19e/0x600 arch/x86/kernel/apic/apic.c:1140
 apic_timer_interrupt+0xf/0x20 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:des_encrypt+0x157/0x9c0 lib/crypto/des.c:792
Code: 85 22 06 00 00 41 31 dc 41 8b 4d 04 44 89 e2 41 83 e4 3f 4a 8d 3c a5 60 72 72 88 81 e2 3f 3f 3f 3f 48 89 f8 48 c1 e8 03 31 d9 <0f> b6 34 28 48 89 f8 c1 c9 04 83 e0 07 83 c0 03 40 38 f0 7c 09 40
RSP: 0018:ffffc90003b5f6c0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13
RAX: 1ffffffff10e4e55 RBX: 00000000d2f846d0 RCX: 00000000d2f846d0
RDX: 0000000012380612 RSI: ffffffff839863ca RDI: ffffffff887272a8
RBP: dffffc0000000000 R08: ffff888091d0a380 R09: 0000000000800081
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000012
R13: ffff8880a8ae8078 R14: 00000000c545c93e R15: 0000000000000006
 cipher_crypt_one crypto/cipher.c:75 [inline]
 crypto_cipher_encrypt_one+0x124/0x210 crypto/cipher.c:82
 crypto_cbcmac_digest_update+0x1b5/0x250 crypto/ccm.c:830
 crypto_shash_update+0xc4/0x120 crypto/shash.c:119
 shash_ahash_update+0xa3/0x110 crypto/shash.c:246
 crypto_ahash_update include/crypto/hash.h:547 [inline]
 hash_sendmsg+0x518/0xad0 crypto/algif_hash.c:102
 sock_sendmsg_nosec net/socket.c:652 [inline]
 sock_sendmsg+0xcf/0x120 net/socket.c:672
 ____sys_sendmsg+0x308/0x7e0 net/socket.c:2362
 ___sys_sendmsg+0x100/0x170 net/socket.c:2416
 __sys_sendmmsg+0x195/0x480 net/socket.c:2506
 __do_sys_sendmmsg net/socket.c:2535 [inline]
 __se_sys_sendmmsg net/socket.c:2532 [inline]
 __x64_sys_sendmmsg+0x99/0x100 net/socket.c:2532
 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295
 entry_SYSCALL_64_after_hwframe+0x49/0xb3
RIP: 0033:0x45c829
Code: 0d b7 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 db b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f6d9528ec78 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000004fc080 RCX: 000000000045c829
RDX: 0000000000000001 RSI: 0000000020002640 RDI: 0000000000000004
RBP: 000000000078bf00 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 00000000000008d7 R14: 00000000004cb7aa R15: 00007f6d9528f6d4

Fixes: 4b15c70753 ("net/sched: Make etf report drops on error_queue")
Fixes: 25db26a913 ("net/sched: Introduce the ETF Qdisc")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Cc: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Reviewed-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-22 19:20:28 -07:00

522 lines
12 KiB
C

// SPDX-License-Identifier: GPL-2.0
/* net/sched/sch_etf.c Earliest TxTime First queueing discipline.
*
* Authors: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
* Vinicius Costa Gomes <vinicius.gomes@intel.com>
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
#include <linux/rbtree.h>
#include <linux/skbuff.h>
#include <linux/posix-timers.h>
#include <net/netlink.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/sock.h>
#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON)
#define SKIP_SOCK_CHECK_IS_SET(x) ((x)->flags & TC_ETF_SKIP_SOCK_CHECK)
struct etf_sched_data {
bool offload;
bool deadline_mode;
bool skip_sock_check;
int clockid;
int queue;
s32 delta; /* in ns */
ktime_t last; /* The txtime of the last skb sent to the netdevice. */
struct rb_root_cached head;
struct qdisc_watchdog watchdog;
ktime_t (*get_time)(void);
};
static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = {
[TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) },
};
static inline int validate_input_params(struct tc_etf_qopt *qopt,
struct netlink_ext_ack *extack)
{
/* Check if params comply to the following rules:
* * Clockid and delta must be valid.
*
* * Dynamic clockids are not supported.
*
* * Delta must be a positive integer.
*
* Also note that for the HW offload case, we must
* expect that system clocks have been synchronized to PHC.
*/
if (qopt->clockid < 0) {
NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
return -ENOTSUPP;
}
if (qopt->clockid != CLOCK_TAI) {
NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used");
return -EINVAL;
}
if (qopt->delta < 0) {
NL_SET_ERR_MSG(extack, "Delta must be positive");
return -EINVAL;
}
return 0;
}
static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
{
struct etf_sched_data *q = qdisc_priv(sch);
ktime_t txtime = nskb->tstamp;
struct sock *sk = nskb->sk;
ktime_t now;
if (q->skip_sock_check)
goto skip;
if (!sk || !sk_fullsock(sk))
return false;
if (!sock_flag(sk, SOCK_TXTIME))
return false;
/* We don't perform crosstimestamping.
* Drop if packet's clockid differs from qdisc's.
*/
if (sk->sk_clockid != q->clockid)
return false;
if (sk->sk_txtime_deadline_mode != q->deadline_mode)
return false;
skip:
now = q->get_time();
if (ktime_before(txtime, now) || ktime_before(txtime, q->last))
return false;
return true;
}
static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct rb_node *p;
p = rb_first_cached(&q->head);
if (!p)
return NULL;
return rb_to_skb(p);
}
static void reset_watchdog(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb = etf_peek_timesortedlist(sch);
ktime_t next;
if (!skb) {
qdisc_watchdog_cancel(&q->watchdog);
return;
}
next = ktime_sub_ns(skb->tstamp, q->delta);
qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
}
static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
{
struct sock_exterr_skb *serr;
struct sk_buff *clone;
ktime_t txtime = skb->tstamp;
struct sock *sk = skb->sk;
if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors))
return;
clone = skb_clone(skb, GFP_ATOMIC);
if (!clone)
return;
serr = SKB_EXT_ERR(clone);
serr->ee.ee_errno = err;
serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME;
serr->ee.ee_type = 0;
serr->ee.ee_code = code;
serr->ee.ee_pad = 0;
serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
serr->ee.ee_info = txtime; /* low part of tstamp */
if (sock_queue_err_skb(sk, clone))
kfree_skb(clone);
}
static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL;
ktime_t txtime = nskb->tstamp;
bool leftmost = true;
if (!is_packet_valid(sch, nskb)) {
report_sock_error(nskb, EINVAL,
SO_EE_CODE_TXTIME_INVALID_PARAM);
return qdisc_drop(nskb, sch, to_free);
}
while (*p) {
struct sk_buff *skb;
parent = *p;
skb = rb_to_skb(parent);
if (ktime_compare(txtime, skb->tstamp) >= 0) {
p = &parent->rb_right;
leftmost = false;
} else {
p = &parent->rb_left;
}
}
rb_link_node(&nskb->rbnode, parent, p);
rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost);
qdisc_qstats_backlog_inc(sch, nskb);
sch->q.qlen++;
/* Now we may need to re-arm the qdisc watchdog for the next packet. */
reset_watchdog(sch);
return NET_XMIT_SUCCESS;
}
static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb,
ktime_t now)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct sk_buff *to_free = NULL;
struct sk_buff *tmp = NULL;
skb_rbtree_walk_from_safe(skb, tmp) {
if (ktime_after(skb->tstamp, now))
break;
rb_erase_cached(&skb->rbnode, &q->head);
/* The rbnode field in the skb re-uses these fields, now that
* we are done with the rbnode, reset them.
*/
skb->next = NULL;
skb->prev = NULL;
skb->dev = qdisc_dev(sch);
report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
qdisc_qstats_backlog_dec(sch, skb);
qdisc_drop(skb, sch, &to_free);
qdisc_qstats_overlimit(sch);
sch->q.qlen--;
}
kfree_skb_list(to_free);
}
static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb)
{
struct etf_sched_data *q = qdisc_priv(sch);
rb_erase_cached(&skb->rbnode, &q->head);
/* The rbnode field in the skb re-uses these fields, now that
* we are done with the rbnode, reset them.
*/
skb->next = NULL;
skb->prev = NULL;
skb->dev = qdisc_dev(sch);
qdisc_qstats_backlog_dec(sch, skb);
qdisc_bstats_update(sch, skb);
q->last = skb->tstamp;
sch->q.qlen--;
}
static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
ktime_t now, next;
skb = etf_peek_timesortedlist(sch);
if (!skb)
return NULL;
now = q->get_time();
/* Drop if packet has expired while in queue. */
if (ktime_before(skb->tstamp, now)) {
timesortedlist_drop(sch, skb, now);
skb = NULL;
goto out;
}
/* When in deadline mode, dequeue as soon as possible and change the
* txtime from deadline to (now + delta).
*/
if (q->deadline_mode) {
timesortedlist_remove(sch, skb);
skb->tstamp = now;
goto out;
}
next = ktime_sub_ns(skb->tstamp, q->delta);
/* Dequeue only if now is within the [txtime - delta, txtime] range. */
if (ktime_after(now, next))
timesortedlist_remove(sch, skb);
else
skb = NULL;
out:
/* Now we may need to re-arm the qdisc watchdog for the next packet. */
reset_watchdog(sch);
return skb;
}
static void etf_disable_offload(struct net_device *dev,
struct etf_sched_data *q)
{
struct tc_etf_qopt_offload etf = { };
const struct net_device_ops *ops;
int err;
if (!q->offload)
return;
ops = dev->netdev_ops;
if (!ops->ndo_setup_tc)
return;
etf.queue = q->queue;
etf.enable = 0;
err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
if (err < 0)
pr_warn("Couldn't disable ETF offload for queue %d\n",
etf.queue);
}
static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q,
struct netlink_ext_ack *extack)
{
const struct net_device_ops *ops = dev->netdev_ops;
struct tc_etf_qopt_offload etf = { };
int err;
if (q->offload)
return 0;
if (!ops->ndo_setup_tc) {
NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload");
return -EOPNOTSUPP;
}
etf.queue = q->queue;
etf.enable = 1;
err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
if (err < 0) {
NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload");
return err;
}
return 0;
}
static int etf_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
struct nlattr *tb[TCA_ETF_MAX + 1];
struct tc_etf_qopt *qopt;
int err;
if (!opt) {
NL_SET_ERR_MSG(extack,
"Missing ETF qdisc options which are mandatory");
return -EINVAL;
}
err = nla_parse_nested_deprecated(tb, TCA_ETF_MAX, opt, etf_policy,
extack);
if (err < 0)
return err;
if (!tb[TCA_ETF_PARMS]) {
NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters");
return -EINVAL;
}
qopt = nla_data(tb[TCA_ETF_PARMS]);
pr_debug("delta %d clockid %d offload %s deadline %s\n",
qopt->delta, qopt->clockid,
OFFLOAD_IS_ON(qopt) ? "on" : "off",
DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
err = validate_input_params(qopt, extack);
if (err < 0)
return err;
q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
if (OFFLOAD_IS_ON(qopt)) {
err = etf_enable_offload(dev, q, extack);
if (err < 0)
return err;
}
/* Everything went OK, save the parameters used. */
q->delta = qopt->delta;
q->clockid = qopt->clockid;
q->offload = OFFLOAD_IS_ON(qopt);
q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
q->skip_sock_check = SKIP_SOCK_CHECK_IS_SET(qopt);
switch (q->clockid) {
case CLOCK_REALTIME:
q->get_time = ktime_get_real;
break;
case CLOCK_MONOTONIC:
q->get_time = ktime_get;
break;
case CLOCK_BOOTTIME:
q->get_time = ktime_get_boottime;
break;
case CLOCK_TAI:
q->get_time = ktime_get_clocktai;
break;
default:
NL_SET_ERR_MSG(extack, "Clockid is not supported");
return -ENOTSUPP;
}
qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid);
return 0;
}
static void timesortedlist_clear(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct rb_node *p = rb_first_cached(&q->head);
while (p) {
struct sk_buff *skb = rb_to_skb(p);
p = rb_next(p);
rb_erase_cached(&skb->rbnode, &q->head);
rtnl_kfree_skbs(skb, skb);
sch->q.qlen--;
}
}
static void etf_reset(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
/* Only cancel watchdog if it's been initialized. */
if (q->watchdog.qdisc == sch)
qdisc_watchdog_cancel(&q->watchdog);
/* No matter which mode we are on, it's safe to clear both lists. */
timesortedlist_clear(sch);
__qdisc_reset_queue(&sch->q);
sch->qstats.backlog = 0;
sch->q.qlen = 0;
q->last = 0;
}
static void etf_destroy(struct Qdisc *sch)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
/* Only cancel watchdog if it's been initialized. */
if (q->watchdog.qdisc == sch)
qdisc_watchdog_cancel(&q->watchdog);
etf_disable_offload(dev, q);
}
static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct etf_sched_data *q = qdisc_priv(sch);
struct tc_etf_qopt opt = { };
struct nlattr *nest;
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (!nest)
goto nla_put_failure;
opt.delta = q->delta;
opt.clockid = q->clockid;
if (q->offload)
opt.flags |= TC_ETF_OFFLOAD_ON;
if (q->deadline_mode)
opt.flags |= TC_ETF_DEADLINE_MODE_ON;
if (q->skip_sock_check)
opt.flags |= TC_ETF_SKIP_SOCK_CHECK;
if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static struct Qdisc_ops etf_qdisc_ops __read_mostly = {
.id = "etf",
.priv_size = sizeof(struct etf_sched_data),
.enqueue = etf_enqueue_timesortedlist,
.dequeue = etf_dequeue_timesortedlist,
.peek = etf_peek_timesortedlist,
.init = etf_init,
.reset = etf_reset,
.destroy = etf_destroy,
.dump = etf_dump,
.owner = THIS_MODULE,
};
static int __init etf_module_init(void)
{
return register_qdisc(&etf_qdisc_ops);
}
static void __exit etf_module_exit(void)
{
unregister_qdisc(&etf_qdisc_ops);
}
module_init(etf_module_init)
module_exit(etf_module_exit)
MODULE_LICENSE("GPL");