2019-05-27 14:55:01 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2010-08-18 21:10:35 +08:00
|
|
|
/*
|
|
|
|
|
* Checksum updating actions
|
|
|
|
|
*
|
|
|
|
|
* Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#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>
|
2010-08-23 11:31:14 +08:00
|
|
|
#include <net/ip6_checksum.h>
|
2017-01-09 18:24:21 +08:00
|
|
|
#include <net/sctp/checksum.h>
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
#include <net/act_api.h>
|
2019-03-20 22:00:01 +08:00
|
|
|
#include <net/pkt_cls.h>
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
#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), },
|
|
|
|
|
};
|
|
|
|
|
|
netns: make struct pernet_operations::id unsigned int
Make struct pernet_operations::id unsigned.
There are 2 reasons to do so:
1)
This field is really an index into an zero based array and
thus is unsigned entity. Using negative value is out-of-bound
access by definition.
2)
On x86_64 unsigned 32-bit data which are mixed with pointers
via array indexing or offsets added or subtracted to pointers
are preffered to signed 32-bit data.
"int" being used as an array index needs to be sign-extended
to 64-bit before being used.
void f(long *p, int i)
{
g(p[i]);
}
roughly translates to
movsx rsi, esi
mov rdi, [rsi+...]
call g
MOVSX is 3 byte instruction which isn't necessary if the variable is
unsigned because x86_64 is zero extending by default.
Now, there is net_generic() function which, you guessed it right, uses
"int" as an array index:
static inline void *net_generic(const struct net *net, int id)
{
...
ptr = ng->ptr[id - 1];
...
}
And this function is used a lot, so those sign extensions add up.
Patch snipes ~1730 bytes on allyesconfig kernel (without all junk
messing with code generation):
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
Unfortunately some functions actually grow bigger.
This is a semmingly random artefact of code generation with register
allocator being used differently. gcc decides that some variable
needs to live in new r8+ registers and every access now requires REX
prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be
used which is longer than [r8]
However, overall balance is in negative direction:
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
function old new delta
nfsd4_lock 3886 3959 +73
tipc_link_build_proto_msg 1096 1140 +44
mac80211_hwsim_new_radio 2776 2808 +32
tipc_mon_rcv 1032 1058 +26
svcauth_gss_legacy_init 1413 1429 +16
tipc_bcbase_select_primary 379 392 +13
nfsd4_exchange_id 1247 1260 +13
nfsd4_setclientid_confirm 782 793 +11
...
put_client_renew_locked 494 480 -14
ip_set_sockfn_get 730 716 -14
geneve_sock_add 829 813 -16
nfsd4_sequence_done 721 703 -18
nlmclnt_lookup_host 708 686 -22
nfsd4_lockt 1085 1063 -22
nfs_get_client 1077 1050 -27
tcf_bpf_init 1106 1076 -30
nfsd4_encode_fattr 5997 5930 -67
Total: Before=154856051, After=154854321, chg -0.00%
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
|
|
|
static unsigned int csum_net_id;
|
2016-07-26 07:09:41 +08:00
|
|
|
static struct tc_action_ops act_csum_ops;
|
2016-02-23 07:57:53 +08:00
|
|
|
|
|
|
|
|
static int tcf_csum_init(struct net *net, struct nlattr *nla,
|
2016-07-26 07:09:41 +08:00
|
|
|
struct nlattr *est, struct tc_action **a, int ovr,
|
net/sched: prepare TC actions to properly validate the control action
- pass a pointer to struct tcf_proto in each actions's init() handler,
to allow validating the control action, checking whether the chain
exists and (eventually) refcounting it.
- remove code that validates the control action after a successful call
to the action's init() handler, and replace it with a test that forbids
addition of actions having 'goto_chain' and NULL goto_chain pointer at
the same time.
- add tcf_action_check_ctrlact(), that will validate the control action
and eventually allocate the action 'goto_chain' within the init()
handler.
- add tcf_action_set_ctrlact(), that will assign the control action and
swap the current 'goto_chain' pointer with the new given one.
This disallows 'goto_chain' on actions that don't initialize it properly
in their init() handler, i.e. calling tcf_action_check_ctrlact() after
successful IDR reservation and then calling tcf_action_set_ctrlact()
to assign 'goto_chain' and 'tcf_action' consistently.
By doing this, the kernel does not leak anymore refcounts when a valid
'goto chain' handle is replaced in TC actions, causing kmemleak splats
like the following one:
# tc chain add dev dd0 chain 42 ingress protocol ip flower \
> ip_proto tcp action drop
# tc chain add dev dd0 chain 43 ingress protocol ip flower \
> ip_proto udp action drop
# tc filter add dev dd0 ingress matchall \
> action gact goto chain 42 index 66
# tc filter replace dev dd0 ingress matchall \
> action gact goto chain 43 index 66
# echo scan >/sys/kernel/debug/kmemleak
<...>
unreferenced object 0xffff93c0ee09f000 (size 1024):
comm "tc", pid 2565, jiffies 4295339808 (age 65.426s)
hex dump (first 32 bytes):
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 08 00 06 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<000000009b63f92d>] tc_ctl_chain+0x3d2/0x4c0
[<00000000683a8d72>] rtnetlink_rcv_msg+0x263/0x2d0
[<00000000ddd88f8e>] netlink_rcv_skb+0x4a/0x110
[<000000006126a348>] netlink_unicast+0x1a0/0x250
[<00000000b3340877>] netlink_sendmsg+0x2c1/0x3c0
[<00000000a25a2171>] sock_sendmsg+0x36/0x40
[<00000000f19ee1ec>] ___sys_sendmsg+0x280/0x2f0
[<00000000d0422042>] __sys_sendmsg+0x5e/0xa0
[<000000007a6c61f9>] do_syscall_64+0x5b/0x180
[<00000000ccd07542>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[<0000000013eaa334>] 0xffffffffffffffff
Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain")
Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values")
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 21:59:59 +08:00
|
|
|
int bind, bool rtnl_held, struct tcf_proto *tp,
|
2019-10-30 22:09:05 +08:00
|
|
|
u32 flags, struct netlink_ext_ack *extack)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
2018-08-11 01:51:42 +08:00
|
|
|
struct tcf_csum_params *params_new;
|
2010-08-18 21:10:35 +08:00
|
|
|
struct nlattr *tb[TCA_CSUM_MAX + 1];
|
2019-03-20 22:00:01 +08:00
|
|
|
struct tcf_chain *goto_ch = NULL;
|
2010-08-18 21:10:35 +08:00
|
|
|
struct tc_csum *parm;
|
|
|
|
|
struct tcf_csum *p;
|
|
|
|
|
int ret = 0, err;
|
2019-08-01 21:02:51 +08:00
|
|
|
u32 index;
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
if (nla == 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 20:07:28 +08:00
|
|
|
err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy,
|
|
|
|
|
NULL);
|
2010-08-18 21:10:35 +08:00
|
|
|
if (err < 0)
|
|
|
|
|
return err;
|
|
|
|
|
|
|
|
|
|
if (tb[TCA_CSUM_PARMS] == NULL)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
parm = nla_data(tb[TCA_CSUM_PARMS]);
|
2019-08-01 21:02:51 +08:00
|
|
|
index = parm->index;
|
|
|
|
|
err = tcf_idr_check_alloc(tn, &index, a, bind);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (!err) {
|
2019-10-30 22:09:06 +08:00
|
|
|
ret = tcf_idr_create_from_flags(tn, index, est, a,
|
|
|
|
|
&act_csum_ops, bind, flags);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (ret) {
|
2019-08-01 21:02:51 +08:00
|
|
|
tcf_idr_cleanup(tn, index);
|
2014-02-12 09:07:31 +08:00
|
|
|
return ret;
|
2018-07-05 22:24:32 +08:00
|
|
|
}
|
2010-08-18 21:10:35 +08:00
|
|
|
ret = ACT_P_CREATED;
|
2018-07-05 22:24:32 +08:00
|
|
|
} else if (err > 0) {
|
2013-12-23 21:02:11 +08:00
|
|
|
if (bind)/* dont override defaults */
|
|
|
|
|
return 0;
|
2018-07-05 22:24:30 +08:00
|
|
|
if (!ovr) {
|
|
|
|
|
tcf_idr_release(*a, bind);
|
2010-08-18 21:10:35 +08:00
|
|
|
return -EEXIST;
|
2018-07-05 22:24:30 +08:00
|
|
|
}
|
2018-07-05 22:24:32 +08:00
|
|
|
} else {
|
|
|
|
|
return err;
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
2019-03-20 22:00:01 +08:00
|
|
|
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
|
|
|
|
|
if (err < 0)
|
|
|
|
|
goto release_idr;
|
|
|
|
|
|
2016-07-26 07:09:41 +08:00
|
|
|
p = to_tcf_csum(*a);
|
2018-01-23 01:14:32 +08:00
|
|
|
|
|
|
|
|
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
|
|
|
|
|
if (unlikely(!params_new)) {
|
2019-03-20 22:00:01 +08:00
|
|
|
err = -ENOMEM;
|
|
|
|
|
goto put_chain;
|
2018-01-23 01:14:32 +08:00
|
|
|
}
|
2018-08-11 01:51:42 +08:00
|
|
|
params_new->update_flags = parm->update_flags;
|
2018-01-23 01:14:32 +08:00
|
|
|
|
2018-08-15 02:46:16 +08:00
|
|
|
spin_lock_bh(&p->tcf_lock);
|
2019-03-20 22:00:01 +08:00
|
|
|
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
|
2019-09-24 07:09:18 +08:00
|
|
|
params_new = rcu_replace_pointer(p->params, params_new,
|
|
|
|
|
lockdep_is_held(&p->tcf_lock));
|
2018-08-15 02:46:16 +08:00
|
|
|
spin_unlock_bh(&p->tcf_lock);
|
2018-08-11 01:51:42 +08:00
|
|
|
|
2019-03-20 22:00:01 +08:00
|
|
|
if (goto_ch)
|
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
2018-08-11 01:51:42 +08:00
|
|
|
if (params_new)
|
|
|
|
|
kfree_rcu(params_new, rcu);
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
if (ret == ACT_P_CREATED)
|
2017-08-30 14:31:59 +08:00
|
|
|
tcf_idr_insert(tn, *a);
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
return ret;
|
2019-03-20 22:00:01 +08:00
|
|
|
put_chain:
|
|
|
|
|
if (goto_ch)
|
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
|
|
|
|
release_idr:
|
|
|
|
|
tcf_idr_release(*a, bind);
|
|
|
|
|
return err;
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* 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) ||
|
2016-02-20 06:05:25 +08:00
|
|
|
skb_try_make_writable(skb, hl + ntkoff))
|
2010-08-18 21:10:35 +08:00
|
|
|
return NULL;
|
|
|
|
|
else
|
|
|
|
|
return (void *)(skb_network_header(skb) + ihl);
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
struct icmp6hdr *icmp6h;
|
2013-04-13 02:07:47 +08:00
|
|
|
const struct ipv6hdr *ip6h;
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h));
|
|
|
|
|
if (icmp6h == NULL)
|
|
|
|
|
return 0;
|
|
|
|
|
|
2013-04-13 02:07:47 +08:00
|
|
|
ip6h = ipv6_hdr(skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
struct tcphdr *tcph;
|
2013-04-13 02:07:47 +08:00
|
|
|
const struct iphdr *iph;
|
2010-08-18 21:10:35 +08:00
|
|
|
|
2017-03-23 17:39:40 +08:00
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
|
|
|
|
|
return 1;
|
|
|
|
|
|
2010-08-18 21:10:35 +08:00
|
|
|
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
|
|
|
|
|
if (tcph == NULL)
|
|
|
|
|
return 0;
|
|
|
|
|
|
2013-04-13 02:07:47 +08:00
|
|
|
iph = ip_hdr(skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
struct tcphdr *tcph;
|
2013-04-13 02:07:47 +08:00
|
|
|
const struct ipv6hdr *ip6h;
|
2010-08-18 21:10:35 +08:00
|
|
|
|
2017-03-23 17:39:40 +08:00
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
|
|
|
|
|
return 1;
|
|
|
|
|
|
2010-08-18 21:10:35 +08:00
|
|
|
tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph));
|
|
|
|
|
if (tcph == NULL)
|
|
|
|
|
return 0;
|
|
|
|
|
|
2013-04-13 02:07:47 +08:00
|
|
|
ip6h = ipv6_hdr(skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl, int udplite)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
struct udphdr *udph;
|
2013-04-13 02:07:47 +08:00
|
|
|
const struct iphdr *iph;
|
2010-08-18 21:10:35 +08:00
|
|
|
u16 ul;
|
|
|
|
|
|
net: accept UFO datagrams from tuntap and packet
Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.
Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.
Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.
It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.
To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216fa8 ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1
("net: avoid skb_warn_bad_offload false positives on UFO").
(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.
Tested
Booted a v4.13 guest kernel with QEMU. On a host kernel before this
patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
enabled, same as on a v4.13 host kernel.
A UFO packet sent from the guest appears on the tap device:
host:
nc -l -p -u 8000 &
tcpdump -n -i tap0
guest:
dd if=/dev/zero of=payload.txt bs=1 count=2000
nc -u 192.16.1.1 8000 < payload.txt
Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
packets arriving fragmented:
./with_tap_pair.sh ./tap_send_ufo tap0 tap1
(from https://github.com/wdebruij/kerneltools/tree/master/tests)
Changes
v1 -> v2
- simplified set_offload change (review comment)
- documented test procedure
Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 23:22:25 +08:00
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
|
|
|
|
|
return 1;
|
|
|
|
|
|
2010-08-23 11:27:58 +08:00
|
|
|
/*
|
|
|
|
|
* Support both UDP and UDPLITE checksum algorithms, Don't use
|
|
|
|
|
* udph->len to get the real length without any protocol check,
|
2010-08-18 21:10:35 +08:00
|
|
|
* 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;
|
|
|
|
|
|
2013-04-13 02:07:47 +08:00
|
|
|
iph = ip_hdr(skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl, int udplite)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
struct udphdr *udph;
|
2013-04-13 02:07:47 +08:00
|
|
|
const struct ipv6hdr *ip6h;
|
2010-08-18 21:10:35 +08:00
|
|
|
u16 ul;
|
|
|
|
|
|
net: accept UFO datagrams from tuntap and packet
Tuntap and similar devices can inject GSO packets. Accept type
VIRTIO_NET_HDR_GSO_UDP, even though not generating UFO natively.
Processes are expected to use feature negotiation such as TUNSETOFFLOAD
to detect supported offload types and refrain from injecting other
packets. This process breaks down with live migration: guest kernels
do not renegotiate flags, so destination hosts need to expose all
features that the source host does.
Partially revert the UFO removal from 182e0b6b5846~1..d9d30adf5677.
This patch introduces nearly(*) no new code to simplify verification.
It brings back verbatim tuntap UFO negotiation, VIRTIO_NET_HDR_GSO_UDP
insertion and software UFO segmentation.
It does not reinstate protocol stack support, hardware offload
(NETIF_F_UFO), SKB_GSO_UDP tunneling in SKB_GSO_SOFTWARE or reception
of VIRTIO_NET_HDR_GSO_UDP packets in tuntap.
To support SKB_GSO_UDP reappearing in the stack, also reinstate
logic in act_csum and openvswitch. Achieve equivalence with v4.13 HEAD
by squashing in commit 939912216fa8 ("net: skb_needs_check() removes
CHECKSUM_UNNECESSARY check for tx.") and reverting commit 8d63bee643f1
("net: avoid skb_warn_bad_offload false positives on UFO").
(*) To avoid having to bring back skb_shinfo(skb)->ip6_frag_id,
ipv6_proxy_select_ident is changed to return a __be32 and this is
assigned directly to the frag_hdr. Also, SKB_GSO_UDP is inserted
at the end of the enum to minimize code churn.
Tested
Booted a v4.13 guest kernel with QEMU. On a host kernel before this
patch `ethtool -k eth0` shows UFO disabled. After the patch, it is
enabled, same as on a v4.13 host kernel.
A UFO packet sent from the guest appears on the tap device:
host:
nc -l -p -u 8000 &
tcpdump -n -i tap0
guest:
dd if=/dev/zero of=payload.txt bs=1 count=2000
nc -u 192.16.1.1 8000 < payload.txt
Direct tap to tap transmission of VIRTIO_NET_HDR_GSO_UDP succeeds,
packets arriving fragmented:
./with_tap_pair.sh ./tap_send_ufo tap0 tap1
(from https://github.com/wdebruij/kerneltools/tree/master/tests)
Changes
v1 -> v2
- simplified set_offload change (review comment)
- documented test procedure
Link: http://lkml.kernel.org/r/<CAF=yD-LuUeDuL9YWPJD9ykOZ0QCjNeznPDr6whqZ9NGMNF12Mw@mail.gmail.com>
Fixes: fb652fdfe837 ("macvlan/macvtap: Remove NETIF_F_UFO advertisement.")
Reported-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-21 23:22:25 +08:00
|
|
|
if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
|
|
|
|
|
return 1;
|
|
|
|
|
|
2010-08-23 11:27:58 +08:00
|
|
|
/*
|
|
|
|
|
* Support both UDP and UDPLITE checksum algorithms, Don't use
|
|
|
|
|
* udph->len to get the real length without any protocol check,
|
2010-08-18 21:10:35 +08:00
|
|
|
* 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;
|
|
|
|
|
|
2013-04-13 02:07:47 +08:00
|
|
|
ip6h = ipv6_hdr(skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
2017-01-09 18:24:21 +08:00
|
|
|
static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl,
|
|
|
|
|
unsigned int ipl)
|
|
|
|
|
{
|
|
|
|
|
struct sctphdr *sctph;
|
|
|
|
|
|
2018-03-09 11:06:09 +08:00
|
|
|
if (skb_is_gso(skb) && skb_is_gso_sctp(skb))
|
2017-01-09 18:24:21 +08:00
|
|
|
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;
|
2017-05-18 21:44:40 +08:00
|
|
|
skb->csum_not_inet = 0;
|
2017-01-09 18:24:21 +08:00
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
|
2010-08-18 21:10:35 +08:00
|
|
|
static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
|
|
|
|
|
{
|
2013-04-13 02:07:47 +08:00
|
|
|
const struct iphdr *iph;
|
2010-08-18 21:10:35 +08:00
|
|
|
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)
|
2010-08-23 11:27:58 +08:00
|
|
|
if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4,
|
|
|
|
|
ntohs(iph->tot_len)))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
break;
|
|
|
|
|
case IPPROTO_IGMP:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP)
|
2010-08-23 11:27:58 +08:00
|
|
|
if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4,
|
|
|
|
|
ntohs(iph->tot_len)))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
break;
|
|
|
|
|
case IPPROTO_TCP:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4,
|
2010-08-23 11:27:58 +08:00
|
|
|
ntohs(iph->tot_len)))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
break;
|
|
|
|
|
case IPPROTO_UDP:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
|
2010-08-23 11:27:58 +08:00
|
|
|
ntohs(iph->tot_len), 0))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
break;
|
|
|
|
|
case IPPROTO_UDPLITE:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4,
|
2010-08-23 11:27:58 +08:00
|
|
|
ntohs(iph->tot_len), 1))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
break;
|
2017-01-09 18:24:21 +08:00
|
|
|
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;
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
|
2016-02-20 06:05:25 +08:00
|
|
|
if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
|
2013-04-13 02:07:47 +08:00
|
|
|
ip_send_check(ip_hdr(skb));
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
|
|
fail:
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl,
|
|
|
|
|
unsigned int *pl)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
int off, len, optlen;
|
|
|
|
|
unsigned char *xh = (void *)ip6xh;
|
|
|
|
|
|
|
|
|
|
off = sizeof(*ip6xh);
|
|
|
|
|
len = ixhl - off;
|
|
|
|
|
|
|
|
|
|
while (len > 1) {
|
2010-08-23 11:27:58 +08:00
|
|
|
switch (xh[off]) {
|
2012-05-17 14:00:25 +08:00
|
|
|
case IPV6_TLV_PAD1:
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
2013-04-13 02:07:47 +08:00
|
|
|
ip6xh = (void *)(skb_network_header(skb) + hl);
|
2010-08-18 21:10:35 +08:00
|
|
|
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)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv6_icmp(skb,
|
2010-08-18 21:10:35 +08:00
|
|
|
hl, pl + sizeof(*ip6h)))
|
|
|
|
|
goto fail;
|
|
|
|
|
goto done;
|
|
|
|
|
case IPPROTO_TCP:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv6_tcp(skb,
|
2010-08-18 21:10:35 +08:00
|
|
|
hl, pl + sizeof(*ip6h)))
|
|
|
|
|
goto fail;
|
|
|
|
|
goto done;
|
|
|
|
|
case IPPROTO_UDP:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv6_udp(skb, hl,
|
2010-08-23 11:27:58 +08:00
|
|
|
pl + sizeof(*ip6h), 0))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
goto done;
|
|
|
|
|
case IPPROTO_UDPLITE:
|
|
|
|
|
if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE)
|
2013-04-13 02:07:47 +08:00
|
|
|
if (!tcf_csum_ipv6_udp(skb, hl,
|
2010-08-23 11:27:58 +08:00
|
|
|
pl + sizeof(*ip6h), 1))
|
2010-08-18 21:10:35 +08:00
|
|
|
goto fail;
|
|
|
|
|
goto done;
|
2017-01-09 18:24:21 +08:00
|
|
|
case IPPROTO_SCTP:
|
|
|
|
|
if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) &&
|
|
|
|
|
!tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h)))
|
|
|
|
|
goto fail;
|
|
|
|
|
goto done;
|
2010-08-18 21:10:35 +08:00
|
|
|
default:
|
|
|
|
|
goto ignore_skb;
|
|
|
|
|
}
|
|
|
|
|
} while (pskb_may_pull(skb, hl + 1 + ntkoff));
|
|
|
|
|
|
|
|
|
|
done:
|
|
|
|
|
ignore_skb:
|
|
|
|
|
return 1;
|
|
|
|
|
|
|
|
|
|
fail:
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
|
|
|
|
|
2018-08-12 21:34:51 +08:00
|
|
|
static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
|
|
|
|
|
struct tcf_result *res)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
2016-07-26 07:09:41 +08:00
|
|
|
struct tcf_csum *p = to_tcf_csum(a);
|
2019-02-26 17:57:34 +08:00
|
|
|
bool orig_vlan_tag_present = false;
|
|
|
|
|
unsigned int vlan_hdr_count = 0;
|
2018-01-23 01:14:32 +08:00
|
|
|
struct tcf_csum_params *params;
|
2010-08-18 21:10:35 +08:00
|
|
|
u32 update_flags;
|
2019-02-26 17:57:34 +08:00
|
|
|
__be16 protocol;
|
2018-01-23 01:14:32 +08:00
|
|
|
int action;
|
|
|
|
|
|
2018-07-30 20:30:43 +08:00
|
|
|
params = rcu_dereference_bh(p->params);
|
2010-08-18 21:10:35 +08:00
|
|
|
|
2016-06-06 18:32:53 +08:00
|
|
|
tcf_lastuse_update(&p->tcf_tm);
|
2019-10-30 22:09:01 +08:00
|
|
|
tcf_action_update_bstats(&p->common, skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
|
2018-07-07 03:01:05 +08:00
|
|
|
action = READ_ONCE(p->tcf_action);
|
2010-08-18 21:10:35 +08:00
|
|
|
if (unlikely(action == TC_ACT_SHOT))
|
2018-07-30 20:30:43 +08:00
|
|
|
goto drop;
|
2010-08-18 21:10:35 +08:00
|
|
|
|
2018-01-23 01:14:32 +08:00
|
|
|
update_flags = params->update_flags;
|
sched: consistently handle layer3 header accesses in the presence of VLANs
There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.
However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).
To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.
To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.
v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
bpf_skb_ecn_set_ce()
v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
calling the helper twice
Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-04 04:26:43 +08:00
|
|
|
protocol = skb_protocol(skb, false);
|
2019-02-26 17:57:34 +08:00
|
|
|
again:
|
|
|
|
|
switch (protocol) {
|
2010-08-18 21:10:35 +08:00
|
|
|
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;
|
2020-07-08 01:21:38 +08:00
|
|
|
case cpu_to_be16(ETH_P_8021AD):
|
|
|
|
|
fallthrough;
|
2019-02-26 17:57:34 +08:00
|
|
|
case cpu_to_be16(ETH_P_8021Q):
|
|
|
|
|
if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) {
|
|
|
|
|
protocol = skb->protocol;
|
|
|
|
|
orig_vlan_tag_present = true;
|
|
|
|
|
} else {
|
|
|
|
|
struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data;
|
|
|
|
|
|
|
|
|
|
protocol = vlan->h_vlan_encapsulated_proto;
|
|
|
|
|
skb_pull(skb, VLAN_HLEN);
|
|
|
|
|
skb_reset_network_header(skb);
|
|
|
|
|
vlan_hdr_count++;
|
|
|
|
|
}
|
|
|
|
|
goto again;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
out:
|
|
|
|
|
/* Restore the skb for the pulled VLAN tags */
|
|
|
|
|
while (vlan_hdr_count--) {
|
|
|
|
|
skb_push(skb, VLAN_HLEN);
|
|
|
|
|
skb_reset_network_header(skb);
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return action;
|
|
|
|
|
|
|
|
|
|
drop:
|
2019-10-30 22:09:02 +08:00
|
|
|
tcf_action_inc_drop_qstats(&p->common);
|
2019-02-26 17:57:34 +08:00
|
|
|
action = TC_ACT_SHOT;
|
|
|
|
|
goto out;
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
2016-09-18 20:45:33 +08:00
|
|
|
static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
|
|
|
|
|
int ref)
|
2010-08-18 21:10:35 +08:00
|
|
|
{
|
|
|
|
|
unsigned char *b = skb_tail_pointer(skb);
|
2016-07-26 07:09:41 +08:00
|
|
|
struct tcf_csum *p = to_tcf_csum(a);
|
2018-01-23 01:14:32 +08:00
|
|
|
struct tcf_csum_params *params;
|
2010-08-18 21:10:35 +08:00
|
|
|
struct tc_csum opt = {
|
|
|
|
|
.index = p->tcf_index,
|
2018-07-05 22:24:24 +08:00
|
|
|
.refcnt = refcount_read(&p->tcf_refcnt) - ref,
|
|
|
|
|
.bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
|
2010-08-18 21:10:35 +08:00
|
|
|
};
|
|
|
|
|
struct tcf_t t;
|
|
|
|
|
|
2018-08-15 02:46:16 +08:00
|
|
|
spin_lock_bh(&p->tcf_lock);
|
2018-08-11 01:51:42 +08:00
|
|
|
params = rcu_dereference_protected(p->params,
|
|
|
|
|
lockdep_is_held(&p->tcf_lock));
|
|
|
|
|
opt.action = p->tcf_action;
|
2018-01-23 01:14:32 +08:00
|
|
|
opt.update_flags = params->update_flags;
|
|
|
|
|
|
2012-03-29 17:11:39 +08:00
|
|
|
if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
|
|
|
|
|
goto nla_put_failure;
|
2016-06-06 18:32:55 +08:00
|
|
|
|
|
|
|
|
tcf_tm_dump(&t, &p->tcf_tm);
|
2016-04-26 16:06:18 +08:00
|
|
|
if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD))
|
2012-03-29 17:11:39 +08:00
|
|
|
goto nla_put_failure;
|
2018-08-15 02:46:16 +08:00
|
|
|
spin_unlock_bh(&p->tcf_lock);
|
2010-08-18 21:10:35 +08:00
|
|
|
|
|
|
|
|
return skb->len;
|
|
|
|
|
|
|
|
|
|
nla_put_failure:
|
2018-08-15 02:46:16 +08:00
|
|
|
spin_unlock_bh(&p->tcf_lock);
|
2010-08-18 21:10:35 +08:00
|
|
|
nlmsg_trim(skb, b);
|
|
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
|
2018-01-23 01:14:32 +08:00
|
|
|
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);
|
2018-03-16 07:00:54 +08:00
|
|
|
if (params)
|
|
|
|
|
kfree_rcu(params, rcu);
|
2018-01-23 01:14:32 +08:00
|
|
|
}
|
|
|
|
|
|
2016-02-23 07:57:53 +08:00
|
|
|
static int tcf_csum_walker(struct net *net, struct sk_buff *skb,
|
|
|
|
|
struct netlink_callback *cb, int type,
|
2018-02-15 23:54:58 +08:00
|
|
|
const struct tc_action_ops *ops,
|
|
|
|
|
struct netlink_ext_ack *extack)
|
2016-02-23 07:57:53 +08:00
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
|
|
2018-02-15 23:54:59 +08:00
|
|
|
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
2018-08-30 01:15:35 +08:00
|
|
|
static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index)
|
2016-02-23 07:57:53 +08:00
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
|
|
2017-08-30 14:31:59 +08:00
|
|
|
return tcf_idr_search(tn, a, index);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
2018-05-01 22:17:43 +08:00
|
|
|
static size_t tcf_csum_get_fill_size(const struct tc_action *act)
|
|
|
|
|
{
|
|
|
|
|
return nla_total_size(sizeof(struct tc_csum));
|
|
|
|
|
}
|
|
|
|
|
|
2010-08-18 21:10:35 +08:00
|
|
|
static struct tc_action_ops act_csum_ops = {
|
2010-08-23 11:27:58 +08:00
|
|
|
.kind = "csum",
|
2019-02-10 20:25:00 +08:00
|
|
|
.id = TCA_ID_CSUM,
|
2010-08-23 11:27:58 +08:00
|
|
|
.owner = THIS_MODULE,
|
2018-08-12 21:34:51 +08:00
|
|
|
.act = tcf_csum_act,
|
2010-08-23 11:27:58 +08:00
|
|
|
.dump = tcf_csum_dump,
|
|
|
|
|
.init = tcf_csum_init,
|
2018-01-23 01:14:32 +08:00
|
|
|
.cleanup = tcf_csum_cleanup,
|
2016-02-23 07:57:53 +08:00
|
|
|
.walk = tcf_csum_walker,
|
|
|
|
|
.lookup = tcf_csum_search,
|
2018-05-01 22:17:43 +08:00
|
|
|
.get_fill_size = tcf_csum_get_fill_size,
|
2016-07-26 07:09:41 +08:00
|
|
|
.size = sizeof(struct tcf_csum),
|
2016-02-23 07:57:53 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static __net_init int csum_init_net(struct net *net)
|
|
|
|
|
{
|
|
|
|
|
struct tc_action_net *tn = net_generic(net, csum_net_id);
|
|
|
|
|
|
2019-08-26 01:01:32 +08:00
|
|
|
return tc_action_net_init(net, tn, &act_csum_ops);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
2017-12-12 07:35:03 +08:00
|
|
|
static void __net_exit csum_exit_net(struct list_head *net_list)
|
2016-02-23 07:57:53 +08:00
|
|
|
{
|
2017-12-12 07:35:03 +08:00
|
|
|
tc_action_net_exit(net_list, csum_net_id);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static struct pernet_operations csum_net_ops = {
|
|
|
|
|
.init = csum_init_net,
|
2017-12-12 07:35:03 +08:00
|
|
|
.exit_batch = csum_exit_net,
|
2016-02-23 07:57:53 +08:00
|
|
|
.id = &csum_net_id,
|
|
|
|
|
.size = sizeof(struct tc_action_net),
|
2010-08-18 21:10:35 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
MODULE_DESCRIPTION("Checksum updating actions");
|
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
|
|
|
|
|
|
static int __init csum_init_module(void)
|
|
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
return tcf_register_action(&act_csum_ops, &csum_net_ops);
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void __exit csum_cleanup_module(void)
|
|
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
tcf_unregister_action(&act_csum_ops, &csum_net_ops);
|
2010-08-18 21:10:35 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
module_init(csum_init_module);
|
|
|
|
|
module_exit(csum_cleanup_module);
|