forked from Minki/linux
653cd284a8
Recently, ops->init() and ops->dump() of all actions were modified to always obtain tcf_lock when accessing private action state. Actions that don't depend on tcf_lock for synchronization with their data path use non-bh locking API. However, tcf_lock is also used to protect rate estimator stats in softirq context by timer callback. Change ops->init() and ops->dump() of all actions to disable bh when using tcf_lock to prevent deadlock reported by following lockdep warning: [ 105.470398] ================================ [ 105.475014] WARNING: inconsistent lock state [ 105.479628] 4.18.0-rc8+ #664 Not tainted [ 105.483897] -------------------------------- [ 105.488511] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 105.494871] swapper/16/0 [HC0[0]:SC1[1]:HE1:SE0] takes: [ 105.500449] 00000000f86c012e (&(&p->tcfa_lock)->rlock){+.?.}, at: est_fetch_counters+0x3c/0xa0 [ 105.509696] {SOFTIRQ-ON-W} state was registered at: [ 105.514925] _raw_spin_lock+0x2c/0x40 [ 105.519022] tcf_bpf_init+0x579/0x820 [act_bpf] [ 105.523990] tcf_action_init_1+0x4e4/0x660 [ 105.528518] tcf_action_init+0x1ce/0x2d0 [ 105.532880] tcf_exts_validate+0x1d8/0x200 [ 105.537416] fl_change+0x55a/0x268b [cls_flower] [ 105.542469] tc_new_tfilter+0x748/0xa20 [ 105.546738] rtnetlink_rcv_msg+0x56a/0x6d0 [ 105.551268] netlink_rcv_skb+0x18d/0x200 [ 105.555628] netlink_unicast+0x2d0/0x370 [ 105.559990] netlink_sendmsg+0x3b9/0x6a0 [ 105.564349] sock_sendmsg+0x6b/0x80 [ 105.568271] ___sys_sendmsg+0x4a1/0x520 [ 105.572547] __sys_sendmsg+0xd7/0x150 [ 105.576655] do_syscall_64+0x72/0x2c0 [ 105.580757] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 105.586243] irq event stamp: 489296 [ 105.590084] hardirqs last enabled at (489296): [<ffffffffb507e639>] _raw_spin_unlock_irq+0x29/0x40 [ 105.599765] hardirqs last disabled at (489295): [<ffffffffb507e745>] _raw_spin_lock_irq+0x15/0x50 [ 105.609277] softirqs last enabled at (489292): [<ffffffffb413a6a3>] irq_enter+0x83/0xa0 [ 105.618001] softirqs last disabled at (489293): [<ffffffffb413a800>] irq_exit+0x140/0x190 [ 105.626813] other info that might help us debug this: [ 105.633976] Possible unsafe locking scenario: [ 105.640526] CPU0 [ 105.643325] ---- [ 105.646125] lock(&(&p->tcfa_lock)->rlock); [ 105.650747] <Interrupt> [ 105.653717] lock(&(&p->tcfa_lock)->rlock); [ 105.658514] *** DEADLOCK *** [ 105.665349] 1 lock held by swapper/16/0: [ 105.669629] #0: 00000000a640ad99 ((&est->timer)){+.-.}, at: call_timer_fn+0x10b/0x550 [ 105.678200] stack backtrace: [ 105.683194] CPU: 16 PID: 0 Comm: swapper/16 Not tainted 4.18.0-rc8+ #664 [ 105.690249] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 105.698626] Call Trace: [ 105.701421] <IRQ> [ 105.703791] dump_stack+0x92/0xeb [ 105.707461] print_usage_bug+0x336/0x34c [ 105.711744] mark_lock+0x7c9/0x980 [ 105.715500] ? print_shortest_lock_dependencies+0x2e0/0x2e0 [ 105.721424] ? check_usage_forwards+0x230/0x230 [ 105.726315] __lock_acquire+0x923/0x26f0 [ 105.730597] ? debug_show_all_locks+0x240/0x240 [ 105.735478] ? mark_lock+0x493/0x980 [ 105.739412] ? check_chain_key+0x140/0x1f0 [ 105.743861] ? __lock_acquire+0x836/0x26f0 [ 105.748323] ? lock_acquire+0x12e/0x290 [ 105.752516] lock_acquire+0x12e/0x290 [ 105.756539] ? est_fetch_counters+0x3c/0xa0 [ 105.761084] _raw_spin_lock+0x2c/0x40 [ 105.765099] ? est_fetch_counters+0x3c/0xa0 [ 105.769633] est_fetch_counters+0x3c/0xa0 [ 105.773995] est_timer+0x87/0x390 [ 105.777670] ? est_fetch_counters+0xa0/0xa0 [ 105.782210] ? lock_acquire+0x12e/0x290 [ 105.786410] call_timer_fn+0x161/0x550 [ 105.790512] ? est_fetch_counters+0xa0/0xa0 [ 105.795055] ? del_timer_sync+0xd0/0xd0 [ 105.799249] ? __lock_is_held+0x93/0x110 [ 105.803531] ? mark_held_locks+0x20/0xe0 [ 105.807813] ? _raw_spin_unlock_irq+0x29/0x40 [ 105.812525] ? est_fetch_counters+0xa0/0xa0 [ 105.817069] ? est_fetch_counters+0xa0/0xa0 [ 105.821610] run_timer_softirq+0x3c4/0x9f0 [ 105.826064] ? lock_acquire+0x12e/0x290 [ 105.830257] ? __bpf_trace_timer_class+0x10/0x10 [ 105.835237] ? __lock_is_held+0x25/0x110 [ 105.839517] __do_softirq+0x11d/0x7bf [ 105.843542] irq_exit+0x140/0x190 [ 105.847208] smp_apic_timer_interrupt+0xac/0x3b0 [ 105.852182] apic_timer_interrupt+0xf/0x20 [ 105.856628] </IRQ> [ 105.859081] RIP: 0010:cpuidle_enter_state+0xd8/0x4d0 [ 105.864395] Code: 46 ff 48 89 44 24 08 0f 1f 44 00 00 31 ff e8 cf ec 46 ff 80 7c 24 07 00 0f 85 1d 02 00 00 e8 9f 90 4b ff fb 66 0f 1f 44 00 00 <4c> 8b 6c 24 08 4d 29 fd 0f 80 36 03 00 00 4c 89 e8 48 ba cf f7 53 [ 105.884288] RSP: 0018:ffff8803ad94fd20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 [ 105.892494] RAX: 0000000000000000 RBX: ffffe8fb300829c0 RCX: ffffffffb41e19e1 [ 105.899988] RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffff8803ad9358ac [ 105.907503] RBP: ffffffffb6636300 R08: 0000000000000004 R09: 0000000000000000 [ 105.914997] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000004 [ 105.922487] R13: ffffffffb6636140 R14: ffffffffb66362d8 R15: 000000188d36091b [ 105.929988] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.935232] do_idle+0x28e/0x320 [ 105.938817] ? arch_cpu_idle_exit+0x40/0x40 [ 105.943361] ? mark_lock+0x8c1/0x980 [ 105.947295] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.952619] cpu_startup_entry+0xc2/0xd0 [ 105.956900] ? cpu_in_idle+0x20/0x20 [ 105.960830] ? _raw_spin_unlock_irqrestore+0x32/0x60 [ 105.966146] ? trace_hardirqs_on_caller+0x141/0x2d0 [ 105.971391] start_secondary+0x2b5/0x360 [ 105.975669] ? set_cpu_sibling_map+0x1330/0x1330 [ 105.980654] secondary_startup_64+0xa5/0xb0 Taking tcf_lock in sample action with bh disabled causes lockdep to issue a warning regarding possible irq lock inversion dependency between tcf_lock, and psample_groups_lock that is taken when holding tcf_lock in sample init: [ 162.108959] Possible interrupt unsafe locking scenario: [ 162.116386] CPU0 CPU1 [ 162.121277] ---- ---- [ 162.126162] lock(psample_groups_lock); [ 162.130447] local_irq_disable(); [ 162.136772] lock(&(&p->tcfa_lock)->rlock); [ 162.143957] lock(psample_groups_lock); [ 162.150813] <Interrupt> [ 162.153808] lock(&(&p->tcfa_lock)->rlock); [ 162.158608] *** DEADLOCK *** In order to prevent potential lock inversion dependency between tcf_lock and psample_groups_lock, extract call to psample_group_get() from tcf_lock protected section in sample action init function. Fixes:4e232818bd
("net: sched: act_mirred: remove dependency on rtnl lock") Fixes:764e9a2448
("net: sched: act_vlan: remove dependency on rtnl lock") Fixes:729e012609
("net: sched: act_tunnel_key: remove dependency on rtnl lock") Fixes:d772849566
("net: sched: act_sample: remove dependency on rtnl lock") Fixes:e8917f4370
("net: sched: act_gact: remove dependency on rtnl lock") Fixes:b6a2b971c0
("net: sched: act_csum: remove dependency on rtnl lock") Fixes:2142236b45
("net: sched: act_bpf: remove dependency on rtnl lock") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
718 lines
16 KiB
C
718 lines
16 KiB
C
/*
|
|
* Checksum updating actions
|
|
*
|
|
* Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License as published by the Free
|
|
* Software Foundation; either version 2 of the License, or (at your option)
|
|
* any later version.
|
|
*
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/netlink.h>
|
|
#include <net/netlink.h>
|
|
#include <linux/rtnetlink.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <net/ip.h>
|
|
#include <net/ipv6.h>
|
|
#include <net/icmp.h>
|
|
#include <linux/icmpv6.h>
|
|
#include <linux/igmp.h>
|
|
#include <net/tcp.h>
|
|
#include <net/udp.h>
|
|
#include <net/ip6_checksum.h>
|
|
#include <net/sctp/checksum.h>
|
|
|
|
#include <net/act_api.h>
|
|
|
|
#include <linux/tc_act/tc_csum.h>
|
|
#include <net/tc_act/tc_csum.h>
|
|
|
|
static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = {
|
|
[TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), },
|
|
};
|
|
|
|
static unsigned int csum_net_id;
|
|
static struct tc_action_ops act_csum_ops;
|
|
|
|
static int tcf_csum_init(struct net *net, struct nlattr *nla,
|
|
struct nlattr *est, struct tc_action **a, int ovr,
|
|
int bind, bool rtnl_held,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
struct tcf_csum_params *params_new;
|
|
struct nlattr *tb[TCA_CSUM_MAX + 1];
|
|
struct tc_csum *parm;
|
|
struct tcf_csum *p;
|
|
int ret = 0, err;
|
|
|
|
if (nla == NULL)
|
|
return -EINVAL;
|
|
|
|
err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy, NULL);
|
|
if (err < 0)
|
|
return err;
|
|
|
|
if (tb[TCA_CSUM_PARMS] == NULL)
|
|
return -EINVAL;
|
|
parm = nla_data(tb[TCA_CSUM_PARMS]);
|
|
|
|
err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
|
|
if (!err) {
|
|
ret = tcf_idr_create(tn, parm->index, est, a,
|
|
&act_csum_ops, bind, true);
|
|
if (ret) {
|
|
tcf_idr_cleanup(tn, parm->index);
|
|
return ret;
|
|
}
|
|
ret = ACT_P_CREATED;
|
|
} else if (err > 0) {
|
|
if (bind)/* dont override defaults */
|
|
return 0;
|
|
if (!ovr) {
|
|
tcf_idr_release(*a, bind);
|
|
return -EEXIST;
|
|
}
|
|
} else {
|
|
return err;
|
|
}
|
|
|
|
p = to_tcf_csum(*a);
|
|
|
|
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
|
|
if (unlikely(!params_new)) {
|
|
tcf_idr_release(*a, bind);
|
|
return -ENOMEM;
|
|
}
|
|
params_new->update_flags = parm->update_flags;
|
|
|
|
spin_lock_bh(&p->tcf_lock);
|
|
p->tcf_action = parm->action;
|
|
rcu_swap_protected(p->params, params_new,
|
|
lockdep_is_held(&p->tcf_lock));
|
|
spin_unlock_bh(&p->tcf_lock);
|
|
|
|
if (params_new)
|
|
kfree_rcu(params_new, rcu);
|
|
|
|
if (ret == ACT_P_CREATED)
|
|
tcf_idr_insert(tn, *a);
|
|
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* tcf_csum_skb_nextlayer - Get next layer pointer
|
|
* @skb: sk_buff to use
|
|
* @ihl: previous summed headers length
|
|
* @ipl: complete packet length
|
|
* @jhl: next header length
|
|
*
|
|
* Check the expected next layer availability in the specified sk_buff.
|
|
* Return the next layer pointer if pass, NULL otherwise.
|
|
*/
|
|
static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
|
|
unsigned int ihl, unsigned int ipl,
|
|
unsigned int jhl)
|
|
{
|
|
int ntkoff = skb_network_offset(skb);
|
|
int hl = ihl + jhl;
|
|
|
|
if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
|
|
skb_try_make_writable(skb, hl + ntkoff))
|
|
return NULL;
|
|
else
|
|
return (void *)(skb_network_header(skb) + ihl);
|
|
}
|
|
|
|
static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl)
|
|
{
|
|
struct icmphdr *icmph;
|
|
|
|
icmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmph));
|
|
if (icmph == NULL)
|
|
return 0;
|
|
|
|
icmph->checksum = 0;
|
|
skb->csum = csum_partial(icmph, ipl - ihl, 0);
|
|
icmph->checksum = csum_fold(skb->csum);
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv4_igmp(struct sk_buff *skb,
|
|
unsigned int ihl, unsigned int ipl)
|
|
{
|
|
struct igmphdr *igmph;
|
|
|
|
igmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*igmph));
|
|
if (igmph == NULL)
|
|
return 0;
|
|
|
|
igmph->csum = 0;
|
|
skb->csum = csum_partial(igmph, ipl - ihl, 0);
|
|
igmph->csum = csum_fold(skb->csum);
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl)
|
|
{
|
|
struct icmp6hdr *icmp6h;
|
|
const struct ipv6hdr *ip6h;
|
|
|
|
icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h));
|
|
if (icmp6h == NULL)
|
|
return 0;
|
|
|
|
ip6h = ipv6_hdr(skb);
|
|
icmp6h->icmp6_cksum = 0;
|
|
skb->csum = csum_partial(icmp6h, ipl - ihl, 0);
|
|
icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
|
|
ipl - ihl, IPPROTO_ICMPV6,
|
|
skb->csum);
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl)
|
|
{
|
|
struct tcphdr *tcph;
|
|
const struct iphdr *iph;
|
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
|
|
return 1;
|
|
|
|
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
|
|
if (tcph == NULL)
|
|
return 0;
|
|
|
|
iph = ip_hdr(skb);
|
|
tcph->check = 0;
|
|
skb->csum = csum_partial(tcph, ipl - ihl, 0);
|
|
tcph->check = tcp_v4_check(ipl - ihl,
|
|
iph->saddr, iph->daddr, skb->csum);
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl)
|
|
{
|
|
struct tcphdr *tcph;
|
|
const struct ipv6hdr *ip6h;
|
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
|
|
return 1;
|
|
|
|
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
|
|
if (tcph == NULL)
|
|
return 0;
|
|
|
|
ip6h = ipv6_hdr(skb);
|
|
tcph->check = 0;
|
|
skb->csum = csum_partial(tcph, ipl - ihl, 0);
|
|
tcph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
|
|
ipl - ihl, IPPROTO_TCP,
|
|
skb->csum);
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl, int udplite)
|
|
{
|
|
struct udphdr *udph;
|
|
const struct iphdr *iph;
|
|
u16 ul;
|
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
|
|
return 1;
|
|
|
|
/*
|
|
* Support both UDP and UDPLITE checksum algorithms, Don't use
|
|
* udph->len to get the real length without any protocol check,
|
|
* UDPLITE uses udph->len for another thing,
|
|
* Use iph->tot_len, or just ipl.
|
|
*/
|
|
|
|
udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph));
|
|
if (udph == NULL)
|
|
return 0;
|
|
|
|
iph = ip_hdr(skb);
|
|
ul = ntohs(udph->len);
|
|
|
|
if (udplite || udph->check) {
|
|
|
|
udph->check = 0;
|
|
|
|
if (udplite) {
|
|
if (ul == 0)
|
|
skb->csum = csum_partial(udph, ipl - ihl, 0);
|
|
else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl))
|
|
skb->csum = csum_partial(udph, ul, 0);
|
|
else
|
|
goto ignore_obscure_skb;
|
|
} else {
|
|
if (ul != ipl - ihl)
|
|
goto ignore_obscure_skb;
|
|
|
|
skb->csum = csum_partial(udph, ul, 0);
|
|
}
|
|
|
|
udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr,
|
|
ul, iph->protocol,
|
|
skb->csum);
|
|
|
|
if (!udph->check)
|
|
udph->check = CSUM_MANGLED_0;
|
|
}
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
ignore_obscure_skb:
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl, int udplite)
|
|
{
|
|
struct udphdr *udph;
|
|
const struct ipv6hdr *ip6h;
|
|
u16 ul;
|
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
|
|
return 1;
|
|
|
|
/*
|
|
* Support both UDP and UDPLITE checksum algorithms, Don't use
|
|
* udph->len to get the real length without any protocol check,
|
|
* UDPLITE uses udph->len for another thing,
|
|
* Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl.
|
|
*/
|
|
|
|
udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph));
|
|
if (udph == NULL)
|
|
return 0;
|
|
|
|
ip6h = ipv6_hdr(skb);
|
|
ul = ntohs(udph->len);
|
|
|
|
udph->check = 0;
|
|
|
|
if (udplite) {
|
|
if (ul == 0)
|
|
skb->csum = csum_partial(udph, ipl - ihl, 0);
|
|
|
|
else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl))
|
|
skb->csum = csum_partial(udph, ul, 0);
|
|
|
|
else
|
|
goto ignore_obscure_skb;
|
|
} else {
|
|
if (ul != ipl - ihl)
|
|
goto ignore_obscure_skb;
|
|
|
|
skb->csum = csum_partial(udph, ul, 0);
|
|
}
|
|
|
|
udph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ul,
|
|
udplite ? IPPROTO_UDPLITE : IPPROTO_UDP,
|
|
skb->csum);
|
|
|
|
if (!udph->check)
|
|
udph->check = CSUM_MANGLED_0;
|
|
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
|
|
ignore_obscure_skb:
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl,
|
|
unsigned int ipl)
|
|
{
|
|
struct sctphdr *sctph;
|
|
|
|
if (skb_is_gso(skb) && skb_is_gso_sctp(skb))
|
|
return 1;
|
|
|
|
sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph));
|
|
if (!sctph)
|
|
return 0;
|
|
|
|
sctph->checksum = sctp_compute_cksum(skb,
|
|
skb_network_offset(skb) + ihl);
|
|
skb->ip_summed = CHECKSUM_NONE;
|
|
skb->csum_not_inet = 0;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
|
|
{
|
|
const struct iphdr *iph;
|
|
int ntkoff;
|
|
|
|
ntkoff = skb_network_offset(skb);
|
|
|
|
if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff))
|
|
goto fail;
|
|
|
|
iph = ip_hdr(skb);
|
|
|
|
switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) {
|
|
case IPPROTO_ICMP:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
|
|
if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4,
|
|
ntohs(iph->tot_len)))
|
|
goto fail;
|
|
break;
|
|
case IPPROTO_IGMP:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP)
|
|
if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4,
|
|
ntohs(iph->tot_len)))
|
|
goto fail;
|
|
break;
|
|
case IPPROTO_TCP:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
|
|
if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4,
|
|
ntohs(iph->tot_len)))
|
|
goto fail;
|
|
break;
|
|
case IPPROTO_UDP:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
|
|
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
|
|
ntohs(iph->tot_len), 0))
|
|
goto fail;
|
|
break;
|
|
case IPPROTO_UDPLITE:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
|
|
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
|
|
ntohs(iph->tot_len), 1))
|
|
goto fail;
|
|
break;
|
|
case IPPROTO_SCTP:
|
|
if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
|
|
!tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len)))
|
|
goto fail;
|
|
break;
|
|
}
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
|
|
if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
|
|
goto fail;
|
|
|
|
ip_send_check(ip_hdr(skb));
|
|
}
|
|
|
|
return 1;
|
|
|
|
fail:
|
|
return 0;
|
|
}
|
|
|
|
static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl,
|
|
unsigned int *pl)
|
|
{
|
|
int off, len, optlen;
|
|
unsigned char *xh = (void *)ip6xh;
|
|
|
|
off = sizeof(*ip6xh);
|
|
len = ixhl - off;
|
|
|
|
while (len > 1) {
|
|
switch (xh[off]) {
|
|
case IPV6_TLV_PAD1:
|
|
optlen = 1;
|
|
break;
|
|
case IPV6_TLV_JUMBO:
|
|
optlen = xh[off + 1] + 2;
|
|
if (optlen != 6 || len < 6 || (off & 3) != 2)
|
|
/* wrong jumbo option length/alignment */
|
|
return 0;
|
|
*pl = ntohl(*(__be32 *)(xh + off + 2));
|
|
goto done;
|
|
default:
|
|
optlen = xh[off + 1] + 2;
|
|
if (optlen > len)
|
|
/* ignore obscure options */
|
|
goto done;
|
|
break;
|
|
}
|
|
off += optlen;
|
|
len -= optlen;
|
|
}
|
|
|
|
done:
|
|
return 1;
|
|
}
|
|
|
|
static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags)
|
|
{
|
|
struct ipv6hdr *ip6h;
|
|
struct ipv6_opt_hdr *ip6xh;
|
|
unsigned int hl, ixhl;
|
|
unsigned int pl;
|
|
int ntkoff;
|
|
u8 nexthdr;
|
|
|
|
ntkoff = skb_network_offset(skb);
|
|
|
|
hl = sizeof(*ip6h);
|
|
|
|
if (!pskb_may_pull(skb, hl + ntkoff))
|
|
goto fail;
|
|
|
|
ip6h = ipv6_hdr(skb);
|
|
|
|
pl = ntohs(ip6h->payload_len);
|
|
nexthdr = ip6h->nexthdr;
|
|
|
|
do {
|
|
switch (nexthdr) {
|
|
case NEXTHDR_FRAGMENT:
|
|
goto ignore_skb;
|
|
case NEXTHDR_ROUTING:
|
|
case NEXTHDR_HOP:
|
|
case NEXTHDR_DEST:
|
|
if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff))
|
|
goto fail;
|
|
ip6xh = (void *)(skb_network_header(skb) + hl);
|
|
ixhl = ipv6_optlen(ip6xh);
|
|
if (!pskb_may_pull(skb, hl + ixhl + ntkoff))
|
|
goto fail;
|
|
ip6xh = (void *)(skb_network_header(skb) + hl);
|
|
if ((nexthdr == NEXTHDR_HOP) &&
|
|
!(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl)))
|
|
goto fail;
|
|
nexthdr = ip6xh->nexthdr;
|
|
hl += ixhl;
|
|
break;
|
|
case IPPROTO_ICMPV6:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP)
|
|
if (!tcf_csum_ipv6_icmp(skb,
|
|
hl, pl + sizeof(*ip6h)))
|
|
goto fail;
|
|
goto done;
|
|
case IPPROTO_TCP:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
|
|
if (!tcf_csum_ipv6_tcp(skb,
|
|
hl, pl + sizeof(*ip6h)))
|
|
goto fail;
|
|
goto done;
|
|
case IPPROTO_UDP:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
|
|
if (!tcf_csum_ipv6_udp(skb, hl,
|
|
pl + sizeof(*ip6h), 0))
|
|
goto fail;
|
|
goto done;
|
|
case IPPROTO_UDPLITE:
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
|
|
if (!tcf_csum_ipv6_udp(skb, hl,
|
|
pl + sizeof(*ip6h), 1))
|
|
goto fail;
|
|
goto done;
|
|
case IPPROTO_SCTP:
|
|
if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
|
|
!tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h)))
|
|
goto fail;
|
|
goto done;
|
|
default:
|
|
goto ignore_skb;
|
|
}
|
|
} while (pskb_may_pull(skb, hl + 1 + ntkoff));
|
|
|
|
done:
|
|
ignore_skb:
|
|
return 1;
|
|
|
|
fail:
|
|
return 0;
|
|
}
|
|
|
|
static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
|
|
struct tcf_result *res)
|
|
{
|
|
struct tcf_csum *p = to_tcf_csum(a);
|
|
struct tcf_csum_params *params;
|
|
u32 update_flags;
|
|
int action;
|
|
|
|
params = rcu_dereference_bh(p->params);
|
|
|
|
tcf_lastuse_update(&p->tcf_tm);
|
|
bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
|
|
|
|
action = READ_ONCE(p->tcf_action);
|
|
if (unlikely(action == TC_ACT_SHOT))
|
|
goto drop;
|
|
|
|
update_flags = params->update_flags;
|
|
switch (tc_skb_protocol(skb)) {
|
|
case cpu_to_be16(ETH_P_IP):
|
|
if (!tcf_csum_ipv4(skb, update_flags))
|
|
goto drop;
|
|
break;
|
|
case cpu_to_be16(ETH_P_IPV6):
|
|
if (!tcf_csum_ipv6(skb, update_flags))
|
|
goto drop;
|
|
break;
|
|
}
|
|
|
|
return action;
|
|
|
|
drop:
|
|
qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats));
|
|
return TC_ACT_SHOT;
|
|
}
|
|
|
|
static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
|
|
int ref)
|
|
{
|
|
unsigned char *b = skb_tail_pointer(skb);
|
|
struct tcf_csum *p = to_tcf_csum(a);
|
|
struct tcf_csum_params *params;
|
|
struct tc_csum opt = {
|
|
.index = p->tcf_index,
|
|
.refcnt = refcount_read(&p->tcf_refcnt) - ref,
|
|
.bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
|
|
};
|
|
struct tcf_t t;
|
|
|
|
spin_lock_bh(&p->tcf_lock);
|
|
params = rcu_dereference_protected(p->params,
|
|
lockdep_is_held(&p->tcf_lock));
|
|
opt.action = p->tcf_action;
|
|
opt.update_flags = params->update_flags;
|
|
|
|
if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
|
|
goto nla_put_failure;
|
|
|
|
tcf_tm_dump(&t, &p->tcf_tm);
|
|
if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD))
|
|
goto nla_put_failure;
|
|
spin_unlock_bh(&p->tcf_lock);
|
|
|
|
return skb->len;
|
|
|
|
nla_put_failure:
|
|
spin_unlock_bh(&p->tcf_lock);
|
|
nlmsg_trim(skb, b);
|
|
return -1;
|
|
}
|
|
|
|
static void tcf_csum_cleanup(struct tc_action *a)
|
|
{
|
|
struct tcf_csum *p = to_tcf_csum(a);
|
|
struct tcf_csum_params *params;
|
|
|
|
params = rcu_dereference_protected(p->params, 1);
|
|
if (params)
|
|
kfree_rcu(params, rcu);
|
|
}
|
|
|
|
static int tcf_csum_walker(struct net *net, struct sk_buff *skb,
|
|
struct netlink_callback *cb, int type,
|
|
const struct tc_action_ops *ops,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
|
}
|
|
|
|
static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index,
|
|
struct netlink_ext_ack *extack)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
return tcf_idr_search(tn, a, index);
|
|
}
|
|
|
|
static size_t tcf_csum_get_fill_size(const struct tc_action *act)
|
|
{
|
|
return nla_total_size(sizeof(struct tc_csum));
|
|
}
|
|
|
|
static int tcf_csum_delete(struct net *net, u32 index)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
return tcf_idr_delete_index(tn, index);
|
|
}
|
|
|
|
static struct tc_action_ops act_csum_ops = {
|
|
.kind = "csum",
|
|
.type = TCA_ACT_CSUM,
|
|
.owner = THIS_MODULE,
|
|
.act = tcf_csum_act,
|
|
.dump = tcf_csum_dump,
|
|
.init = tcf_csum_init,
|
|
.cleanup = tcf_csum_cleanup,
|
|
.walk = tcf_csum_walker,
|
|
.lookup = tcf_csum_search,
|
|
.get_fill_size = tcf_csum_get_fill_size,
|
|
.delete = tcf_csum_delete,
|
|
.size = sizeof(struct tcf_csum),
|
|
};
|
|
|
|
static __net_init int csum_init_net(struct net *net)
|
|
{
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
return tc_action_net_init(tn, &act_csum_ops);
|
|
}
|
|
|
|
static void __net_exit csum_exit_net(struct list_head *net_list)
|
|
{
|
|
tc_action_net_exit(net_list, csum_net_id);
|
|
}
|
|
|
|
static struct pernet_operations csum_net_ops = {
|
|
.init = csum_init_net,
|
|
.exit_batch = csum_exit_net,
|
|
.id = &csum_net_id,
|
|
.size = sizeof(struct tc_action_net),
|
|
};
|
|
|
|
MODULE_DESCRIPTION("Checksum updating actions");
|
|
MODULE_LICENSE("GPL");
|
|
|
|
static int __init csum_init_module(void)
|
|
{
|
|
return tcf_register_action(&act_csum_ops, &csum_net_ops);
|
|
}
|
|
|
|
static void __exit csum_cleanup_module(void)
|
|
{
|
|
tcf_unregister_action(&act_csum_ops, &csum_net_ops);
|
|
}
|
|
|
|
module_init(csum_init_module);
|
|
module_exit(csum_cleanup_module);
|