linux/net/sched/sch_choke.c

518 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* net/sched/sch_choke.c CHOKE scheduler
*
* Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com>
* Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com>
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/vmalloc.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/inet_ecn.h>
#include <net/red.h>
#include <net/flow_dissector.h>
/*
CHOKe stateless AQM for fair bandwidth allocation
=================================================
CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for
unresponsive flows) is a variant of RED that penalizes misbehaving flows but
maintains no flow state. The difference from RED is an additional step
during the enqueuing process. If average queue size is over the
low threshold (qmin), a packet is chosen at random from the queue.
If both the new and chosen packet are from the same flow, both
are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it
needs to access packets in queue randomly. It has a minimal class
interface to allow overriding the builtin flow classifier with
filters.
Source:
R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless
Active Queue Management Scheme for Approximating Fair Bandwidth Allocation",
IEEE INFOCOM, 2000.
A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial
Characteristics", IEEE/ACM Transactions on Networking, 2004
*/
/* Upper bound on size of sk_buff table (packets) */
#define CHOKE_MAX_QUEUE (128*1024 - 1)
struct choke_sched_data {
/* Parameters */
u32 limit;
unsigned char flags;
struct red_parms parms;
/* Variables */
struct red_vars vars;
struct {
u32 prob_drop; /* Early probability drops */
u32 prob_mark; /* Early probability marks */
u32 forced_drop; /* Forced drops, qavg > max_thresh */
u32 forced_mark; /* Forced marks, qavg > max_thresh */
u32 pdrop; /* Drops due to queue limits */
u32 matched; /* Drops to flow match */
} stats;
unsigned int head;
unsigned int tail;
unsigned int tab_mask; /* size - 1 */
struct sk_buff **tab;
};
/* number of elements in queue including holes */
static unsigned int choke_len(const struct choke_sched_data *q)
{
return (q->tail - q->head) & q->tab_mask;
}
/* Is ECN parameter configured */
static int use_ecn(const struct choke_sched_data *q)
{
return q->flags & TC_RED_ECN;
}
/* Should packets over max just be dropped (versus marked) */
static int use_harddrop(const struct choke_sched_data *q)
{
return q->flags & TC_RED_HARDDROP;
}
/* Move head pointer forward to skip over holes */
static void choke_zap_head_holes(struct choke_sched_data *q)
{
do {
q->head = (q->head + 1) & q->tab_mask;
if (q->head == q->tail)
break;
} while (q->tab[q->head] == NULL);
}
/* Move tail pointer backwards to reuse holes */
static void choke_zap_tail_holes(struct choke_sched_data *q)
{
do {
q->tail = (q->tail - 1) & q->tab_mask;
if (q->head == q->tail)
break;
} while (q->tab[q->tail] == NULL);
}
/* Drop packet from queue array by creating a "hole" */
static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx,
struct sk_buff **to_free)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb = q->tab[idx];
q->tab[idx] = NULL;
if (idx == q->head)
choke_zap_head_holes(q);
if (idx == q->tail)
choke_zap_tail_holes(q);
qdisc_qstats_backlog_dec(sch, skb);
qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
qdisc_drop(skb, sch, to_free);
--sch->q.qlen;
}
struct choke_skb_cb {
u8 keys_valid;
struct flow_keys_digest keys;
};
static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
{
qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb));
return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data;
}
/*
* Compare flow of two packets
* Returns true only if source and destination address and port match.
* false for special cases
*/
static bool choke_match_flow(struct sk_buff *skb1,
struct sk_buff *skb2)
{
struct flow_keys temp;
if (skb1->protocol != skb2->protocol)
return false;
if (!choke_skb_cb(skb1)->keys_valid) {
choke_skb_cb(skb1)->keys_valid = 1;
skb_flow_dissect_flow_keys(skb1, &temp, 0);
make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp);
}
if (!choke_skb_cb(skb2)->keys_valid) {
choke_skb_cb(skb2)->keys_valid = 1;
skb_flow_dissect_flow_keys(skb2, &temp, 0);
make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp);
}
return !memcmp(&choke_skb_cb(skb1)->keys,
&choke_skb_cb(skb2)->keys,
sizeof(choke_skb_cb(skb1)->keys));
}
/*
* Select a packet at random from queue
* HACK: since queue can have holes from previous deletion; retry several
* times to find a random skb but then just give up and return the head
* Will return NULL if queue is empty (q->head == q->tail)
*/
static struct sk_buff *choke_peek_random(const struct choke_sched_data *q,
unsigned int *pidx)
{
struct sk_buff *skb;
int retrys = 3;
do {
*pidx = (q->head + get_random_u32_below(choke_len(q))) & q->tab_mask;
skb = q->tab[*pidx];
if (skb)
return skb;
} while (--retrys > 0);
return q->tab[*pidx = q->head];
}
/*
* Compare new packet with random packet in queue
* returns true if matched and sets *pidx
*/
static bool choke_match_random(const struct choke_sched_data *q,
struct sk_buff *nskb,
unsigned int *pidx)
{
struct sk_buff *oskb;
if (q->head == q->tail)
return false;
oskb = choke_peek_random(q, pidx);
return choke_match_flow(oskb, nskb);
}
static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct choke_sched_data *q = qdisc_priv(sch);
const struct red_parms *p = &q->parms;
choke_skb_cb(skb)->keys_valid = 0;
/* Compute average queue usage (see RED) */
q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen);
if (red_is_idling(&q->vars))
red_end_of_idle_period(&q->vars);
/* Is queue small? */
if (q->vars.qavg <= p->qth_min)
q->vars.qcount = -1;
else {
unsigned int idx;
/* Draw a packet at random from queue and compare flow */
if (choke_match_random(q, skb, &idx)) {
q->stats.matched++;
choke_drop_by_idx(sch, idx, to_free);
goto congestion_drop;
}
/* Queue is large, always mark/drop */
if (q->vars.qavg > p->qth_max) {
q->vars.qcount = -1;
qdisc_qstats_overlimit(sch);
if (use_harddrop(q) || !use_ecn(q) ||
!INET_ECN_set_ce(skb)) {
q->stats.forced_drop++;
goto congestion_drop;
}
q->stats.forced_mark++;
} else if (++q->vars.qcount) {
if (red_mark_probability(p, &q->vars, q->vars.qavg)) {
q->vars.qcount = 0;
q->vars.qR = red_random(p);
qdisc_qstats_overlimit(sch);
if (!use_ecn(q) || !INET_ECN_set_ce(skb)) {
q->stats.prob_drop++;
goto congestion_drop;
}
q->stats.prob_mark++;
}
} else
q->vars.qR = red_random(p);
}
/* Admit new packet */
if (sch->q.qlen < q->limit) {
q->tab[q->tail] = skb;
q->tail = (q->tail + 1) & q->tab_mask;
++sch->q.qlen;
qdisc_qstats_backlog_inc(sch, skb);
return NET_XMIT_SUCCESS;
}
q->stats.pdrop++;
return qdisc_drop(skb, sch, to_free);
congestion_drop:
qdisc_drop(skb, sch, to_free);
return NET_XMIT_CN;
}
static struct sk_buff *choke_dequeue(struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb;
if (q->head == q->tail) {
if (!red_is_idling(&q->vars))
red_start_of_idle_period(&q->vars);
return NULL;
}
skb = q->tab[q->head];
q->tab[q->head] = NULL;
choke_zap_head_holes(q);
--sch->q.qlen;
qdisc_qstats_backlog_dec(sch, skb);
qdisc_bstats_update(sch, skb);
return skb;
}
static void choke_reset(struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
while (q->head != q->tail) {
struct sk_buff *skb = q->tab[q->head];
q->head = (q->head + 1) & q->tab_mask;
if (!skb)
continue;
rtnl_qdisc_drop(skb, sch);
}
sch_choke: avoid potential panic in choke_reset() If choke_init() could not allocate q->tab, we would crash later in choke_reset(). BUG: KASAN: null-ptr-deref in memset include/linux/string.h:366 [inline] BUG: KASAN: null-ptr-deref in choke_reset+0x208/0x340 net/sched/sch_choke.c:326 Write of size 8 at addr 0000000000000000 by task syz-executor822/7022 CPU: 1 PID: 7022 Comm: syz-executor822 Not tainted 5.7.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 __kasan_report.cold+0x5/0x4d mm/kasan/report.c:515 kasan_report+0x33/0x50 mm/kasan/common.c:625 check_memory_region_inline mm/kasan/generic.c:187 [inline] check_memory_region+0x141/0x190 mm/kasan/generic.c:193 memset+0x20/0x40 mm/kasan/common.c:85 memset include/linux/string.h:366 [inline] choke_reset+0x208/0x340 net/sched/sch_choke.c:326 qdisc_reset+0x6b/0x520 net/sched/sch_generic.c:910 dev_deactivate_queue.constprop.0+0x13c/0x240 net/sched/sch_generic.c:1138 netdev_for_each_tx_queue include/linux/netdevice.h:2197 [inline] dev_deactivate_many+0xe2/0xba0 net/sched/sch_generic.c:1195 dev_deactivate+0xf8/0x1c0 net/sched/sch_generic.c:1233 qdisc_graft+0xd25/0x1120 net/sched/sch_api.c:1051 tc_modify_qdisc+0xbab/0x1a00 net/sched/sch_api.c:1670 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5454 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2469 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6bf/0x7e0 net/socket.c:2362 ___sys_sendmsg+0x100/0x170 net/socket.c:2416 __sys_sendmsg+0xec/0x1b0 net/socket.c:2449 do_syscall_64+0xf6/0x7d0 arch/x86/entry/common.c:295 Fixes: 77e62da6e60c ("sch_choke: drop all packets in queue during reset") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-25 22:19:51 +00:00
if (q->tab)
memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
q->head = q->tail = 0;
red_restart(&q->vars);
}
static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
[TCA_CHOKE_PARMS] = { .len = sizeof(struct tc_red_qopt) },
[TCA_CHOKE_STAB] = { .len = RED_STAB_SIZE },
[TCA_CHOKE_MAX_P] = { .type = NLA_U32 },
};
static void choke_free(void *addr)
{
kvfree(addr);
}
static int choke_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_CHOKE_MAX + 1];
const struct tc_red_qopt *ctl;
int err;
struct sk_buff **old = NULL;
unsigned int mask;
u32 max_P;
net: sched: validate stab values iproute2 package is well behaved, but malicious user space can provide illegal shift values and trigger UBSAN reports. Add stab parameter to red_check_params() to validate user input. syzbot reported: UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18 shift exponent 111 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327 red_calc_qavg_from_idle_time include/net/red.h:312 [inline] red_calc_qavg include/net/red.h:353 [inline] choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221 __dev_xmit_skb net/core/dev.c:3837 [inline] __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150 neigh_hh_output include/net/neighbour.h:499 [inline] neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535 dccp_finish_passive_close net/dccp/proto.c:123 [inline] dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118 dccp_terminate_connection net/dccp/proto.c:958 [inline] dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478 __sock_release+0xcd/0x280 net/socket.c:599 sock_close+0x18/0x20 net/socket.c:1258 __fput+0x288/0x920 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-03-10 16:26:41 +00:00
u8 *stab;
if (opt == NULL)
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(tb, TCA_CHOKE_MAX, opt,
choke_policy, NULL);
if (err < 0)
return err;
if (tb[TCA_CHOKE_PARMS] == NULL ||
tb[TCA_CHOKE_STAB] == NULL)
return -EINVAL;
max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
ctl = nla_data(tb[TCA_CHOKE_PARMS]);
net: sched: validate stab values iproute2 package is well behaved, but malicious user space can provide illegal shift values and trigger UBSAN reports. Add stab parameter to red_check_params() to validate user input. syzbot reported: UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18 shift exponent 111 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327 red_calc_qavg_from_idle_time include/net/red.h:312 [inline] red_calc_qavg include/net/red.h:353 [inline] choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221 __dev_xmit_skb net/core/dev.c:3837 [inline] __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150 neigh_hh_output include/net/neighbour.h:499 [inline] neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535 dccp_finish_passive_close net/dccp/proto.c:123 [inline] dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118 dccp_terminate_connection net/dccp/proto.c:958 [inline] dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478 __sock_release+0xcd/0x280 net/socket.c:599 sock_close+0x18/0x20 net/socket.c:1258 __fput+0x288/0x920 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-03-10 16:26:41 +00:00
stab = nla_data(tb[TCA_CHOKE_STAB]);
if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab))
return -EINVAL;
if (ctl->limit > CHOKE_MAX_QUEUE)
return -EINVAL;
mask = roundup_pow_of_two(ctl->limit + 1) - 1;
if (mask != q->tab_mask) {
struct sk_buff **ntab;
ntab = kvcalloc(mask + 1, sizeof(struct sk_buff *), GFP_KERNEL);
if (!ntab)
return -ENOMEM;
sch_tree_lock(sch);
old = q->tab;
if (old) {
unsigned int oqlen = sch->q.qlen, tail = 0;
unsigned dropped = 0;
while (q->head != q->tail) {
struct sk_buff *skb = q->tab[q->head];
q->head = (q->head + 1) & q->tab_mask;
if (!skb)
continue;
if (tail < mask) {
ntab[tail++] = skb;
continue;
}
dropped += qdisc_pkt_len(skb);
qdisc_qstats_backlog_dec(sch, skb);
--sch->q.qlen;
rtnl_qdisc_drop(skb, sch);
}
qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped);
q->head = 0;
q->tail = tail;
}
q->tab_mask = mask;
q->tab = ntab;
} else
sch_tree_lock(sch);
q->flags = ctl->flags;
q->limit = ctl->limit;
red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
ctl->Plog, ctl->Scell_log,
net: sched: validate stab values iproute2 package is well behaved, but malicious user space can provide illegal shift values and trigger UBSAN reports. Add stab parameter to red_check_params() to validate user input. syzbot reported: UBSAN: shift-out-of-bounds in ./include/net/red.h:312:18 shift exponent 111 is too large for 64-bit type 'long unsigned int' CPU: 1 PID: 14662 Comm: syz-executor.3 Not tainted 5.12.0-rc2-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 ubsan_epilogue+0xb/0x5a lib/ubsan.c:148 __ubsan_handle_shift_out_of_bounds.cold+0xb1/0x181 lib/ubsan.c:327 red_calc_qavg_from_idle_time include/net/red.h:312 [inline] red_calc_qavg include/net/red.h:353 [inline] choke_enqueue.cold+0x18/0x3dd net/sched/sch_choke.c:221 __dev_xmit_skb net/core/dev.c:3837 [inline] __dev_queue_xmit+0x1943/0x2e00 net/core/dev.c:4150 neigh_hh_output include/net/neighbour.h:499 [inline] neigh_output include/net/neighbour.h:508 [inline] ip6_finish_output2+0x911/0x1700 net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x4c1/0xe10 net/ipv6/ip6_output.c:161 ip6_finish_output+0x35/0x200 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x1e4/0x530 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] ip6_xmit+0x127e/0x1eb0 net/ipv6/ip6_output.c:320 inet6_csk_xmit+0x358/0x630 net/ipv6/inet6_connection_sock.c:135 dccp_transmit_skb+0x973/0x12c0 net/dccp/output.c:138 dccp_send_reset+0x21b/0x2b0 net/dccp/output.c:535 dccp_finish_passive_close net/dccp/proto.c:123 [inline] dccp_finish_passive_close+0xed/0x140 net/dccp/proto.c:118 dccp_terminate_connection net/dccp/proto.c:958 [inline] dccp_close+0xb3c/0xe60 net/dccp/proto.c:1028 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:478 __sock_release+0xcd/0x280 net/socket.c:599 sock_close+0x18/0x20 net/socket.c:1258 __fput+0x288/0x920 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:140 tracehook_notify_resume include/linux/tracehook.h:189 [inline] Fixes: 8afa10cbe281 ("net_sched: red: Avoid illegal values") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-03-10 16:26:41 +00:00
stab,
max_P);
red_set_vars(&q->vars);
if (q->head == q->tail)
red_end_of_idle_period(&q->vars);
sch_tree_unlock(sch);
choke_free(old);
return 0;
}
static int choke_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
return choke_change(sch, opt, extack);
}
static int choke_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct nlattr *opts = NULL;
struct tc_red_qopt opt = {
.limit = q->limit,
.flags = q->flags,
.qth_min = q->parms.qth_min >> q->parms.Wlog,
.qth_max = q->parms.qth_max >> q->parms.Wlog,
.Wlog = q->parms.Wlog,
.Plog = q->parms.Plog,
.Scell_log = q->parms.Scell_log,
};
opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (opts == NULL)
goto nla_put_failure;
if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) ||
nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P))
goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
nla_nest_cancel(skb, opts);
return -EMSGSIZE;
}
static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
struct choke_sched_data *q = qdisc_priv(sch);
struct tc_choke_xstats st = {
.early = q->stats.prob_drop + q->stats.forced_drop,
.marked = q->stats.prob_mark + q->stats.forced_mark,
.pdrop = q->stats.pdrop,
.matched = q->stats.matched,
};
return gnet_stats_copy_app(d, &st, sizeof(st));
}
static void choke_destroy(struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
choke_free(q->tab);
}
static struct sk_buff *choke_peek_head(struct Qdisc *sch)
{
struct choke_sched_data *q = qdisc_priv(sch);
return (q->head != q->tail) ? q->tab[q->head] : NULL;
}
static struct Qdisc_ops choke_qdisc_ops __read_mostly = {
.id = "choke",
.priv_size = sizeof(struct choke_sched_data),
.enqueue = choke_enqueue,
.dequeue = choke_dequeue,
.peek = choke_peek_head,
.init = choke_init,
.destroy = choke_destroy,
.reset = choke_reset,
.change = choke_change,
.dump = choke_dump,
.dump_stats = choke_dump_stats,
.owner = THIS_MODULE,
};
net/sched: Add module aliases for cls_,sch_,act_ modules No functional change intended, aliases will be used in followup commits. Note for backporters: you may need to add aliases also for modules that are already removed in mainline kernel but still in your version. Patches were generated with the help of Coccinelle scripts like: cat >scripts/coccinelle/misc/tcf_alias.cocci <<EOD virtual patch virtual report @ haskernel @ @@ @ tcf_has_kind depends on report && haskernel @ identifier ops; constant K; @@ static struct tcf_proto_ops ops = { .kind = K, ... }; +char module_alias = K; EOD /usr/bin/spatch -D report --cocci-file scripts/coccinelle/misc/tcf_alias.cocci \ --dir . \ -I ./arch/x86/include -I ./arch/x86/include/generated -I ./include \ -I ./arch/x86/include/uapi -I ./arch/x86/include/generated/uapi \ -I ./include/uapi -I ./include/generated/uapi \ --include ./include/linux/compiler-version.h --include ./include/linux/kconfig.h \ --jobs 8 --chunksize 1 2>/dev/null | \ sed 's/char module_alias = "\([^"]*\)";/MODULE_ALIAS_NET_CLS("\1");/' And analogously for: static struct tc_action_ops ops = { .kind = K, static struct Qdisc_ops ops = { .id = K, (Someone familiar would be able to fit those into one .cocci file without sed post processing.) Signed-off-by: Michal Koutný <mkoutny@suse.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@nvidia.com> Link: https://lore.kernel.org/r/20240201130943.19536-3-mkoutny@suse.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-01 13:09:41 +00:00
MODULE_ALIAS_NET_SCH("choke");
static int __init choke_module_init(void)
{
return register_qdisc(&choke_qdisc_ops);
}
static void __exit choke_module_exit(void)
{
unregister_qdisc(&choke_qdisc_ops);
}
module_init(choke_module_init)
module_exit(choke_module_exit)
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Choose and keep responsive flows scheduler");