android_kernel_samsung_msm8976/net/ipv6/xfrm6_policy.c

407 lines
9.1 KiB
C
Raw Permalink Normal View History

/*
* xfrm6_policy.c: based on xfrm4_policy.c
*
* Authors:
* Mitsuru KANDA @USAGI
* Kazunori MIYAZAWA @USAGI
* Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* IPv6 support
* YOSHIFUJI Hideaki
* Split up af-specific portion
*
*/
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <net/addrconf.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
static struct xfrm_policy_afinfo xfrm6_policy_afinfo;
static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
const xfrm_address_t *saddr,
BACKPORT: net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. [backport of upstream 077fbac405bfc6d41419ad6c1725804ad4e9887c] Bug: 63589535 Test: https://android-review.googlesource.com/452776/ passes Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Change-Id: I76120fba036e21780ced31ad390faf491ea81e52
2017-08-10 17:11:33 +00:00
const xfrm_address_t *daddr,
u32 mark)
{
struct flowi6 fl6;
struct dst_entry *dst;
int err;
memset(&fl6, 0, sizeof(fl6));
BACKPORT: net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. [backport of upstream 077fbac405bfc6d41419ad6c1725804ad4e9887c] Bug: 63589535 Test: https://android-review.googlesource.com/452776/ passes Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Change-Id: I76120fba036e21780ced31ad390faf491ea81e52
2017-08-10 17:11:33 +00:00
fl6.flowi6_mark = mark;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
dst = ip6_route_output(net, NULL, &fl6);
err = dst->error;
if (dst->error) {
dst_release(dst);
dst = ERR_PTR(err);
}
return dst;
}
static int xfrm6_get_saddr(struct net *net,
BACKPORT: net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. [backport of upstream 077fbac405bfc6d41419ad6c1725804ad4e9887c] Bug: 63589535 Test: https://android-review.googlesource.com/452776/ passes Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Change-Id: I76120fba036e21780ced31ad390faf491ea81e52
2017-08-10 17:11:33 +00:00
xfrm_address_t *saddr, xfrm_address_t *daddr,
u32 mark)
{
struct dst_entry *dst;
struct net_device *dev;
BACKPORT: net: xfrm: support setting an output mark. On systems that use mark-based routing it may be necessary for routing lookups to use marks in order for packets to be routed correctly. An example of such a system is Android, which uses socket marks to route packets via different networks. Currently, routing lookups in tunnel mode always use a mark of zero, making routing incorrect on such systems. This patch adds a new output_mark element to the xfrm state and a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output mark differs from the existing xfrm mark in two ways: 1. The xfrm mark is used to match xfrm policies and states, while the xfrm output mark is used to set the mark (and influence the routing) of the packets emitted by those states. 2. The existing mark is constrained to be a subset of the bits of the originating socket or transformed packet, but the output mark is arbitrary and depends only on the state. The use of a separate mark provides additional flexibility. For example: - A packet subject to two transforms (e.g., transport mode inside tunnel mode) can have two different output marks applied to it, one for the transport mode SA and one for the tunnel mode SA. - On a system where socket marks determine routing, the packets emitted by an IPsec tunnel can be routed based on a mark that is determined by the tunnel, not by the marks of the unencrypted packets. - Support for setting the output marks can be introduced without breaking any existing setups that employ both mark-based routing and xfrm tunnel mode. Simply changing the code to use the xfrm mark for routing output packets could xfrm mark could change behaviour in a way that breaks these setups. If the output mark is unspecified or set to zero, the mark is not set or changed. [backport of upstream 077fbac405bfc6d41419ad6c1725804ad4e9887c] Bug: 63589535 Test: https://android-review.googlesource.com/452776/ passes Tested: make allyesconfig; make -j64 Tested: https://android-review.googlesource.com/452776 Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Change-Id: I76120fba036e21780ced31ad390faf491ea81e52
2017-08-10 17:11:33 +00:00
dst = xfrm6_dst_lookup(net, 0, NULL, daddr, mark);
if (IS_ERR(dst))
return -EHOSTUNREACH;
dev = ip6_dst_idev(dst)->dev;
ipv6_dev_get_saddr(dev_net(dev), dev,
(struct in6_addr *)&daddr->a6, 0,
(struct in6_addr *)&saddr->a6);
dst_release(dst);
return 0;
}
static int xfrm6_get_tos(const struct flowi *fl)
{
return 0;
}
net: ipv6: fix oops in inet_putpeer() Commit 97bab73f (inet: Hide route peer accesses behind helpers.) introduced a bug in xfrm6_policy_destroy(). The xfrm_dst's _rt6i_peer member is not initialized, causing a false positive result from inetpeer_ptr_is_peer(), which in turn causes a NULL pointer dereference in inet_putpeer(). Pid: 314, comm: kworker/0:1 Not tainted 3.6.0-rc1+ #17 To Be Filled By O.E.M. To Be Filled By O.E.M./P4S800D-X EIP: 0060:[<c03abf93>] EFLAGS: 00010246 CPU: 0 EIP is at inet_putpeer+0xe/0x16 EAX: 00000000 EBX: f3481700 ECX: 00000000 EDX: 000dd641 ESI: f3481700 EDI: c05e949c EBP: f551def4 ESP: f551def4 DS: 007b ES: 007b FS: 0000 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 00000070 CR3: 3243d000 CR4: 00000750 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: ffff0ff0 DR7: 00000400 f551df04 c0423de1 00000000 f3481700 f551df18 c038d5f7 f254b9f8 f551df28 f34f85d8 f551df20 c03ef48d f551df3c c0396870 f30697e8 f24e1738 c05e98f4 f5509540 c05cd2b4 f551df7c c0142d2b c043feb5 f5509540 00000000 c05cd2e8 [<c0423de1>] xfrm6_dst_destroy+0x42/0xdb [<c038d5f7>] dst_destroy+0x1d/0xa4 [<c03ef48d>] xfrm_bundle_flo_delete+0x2b/0x36 [<c0396870>] flow_cache_gc_task+0x85/0x9f [<c0142d2b>] process_one_work+0x122/0x441 [<c043feb5>] ? apic_timer_interrupt+0x31/0x38 [<c03967eb>] ? flow_cache_new_hashrnd+0x2b/0x2b [<c0143e2d>] worker_thread+0x113/0x3cc Fix by adding a init_dst() callback to struct xfrm_policy_afinfo to properly initialize the dst's peer pointer. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-08-20 09:56:56 +00:00
static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst)
{
struct rt6_info *rt = (struct rt6_info *)xdst;
rt6_init_peer(rt, net->ipv6.peers);
}
static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
if (dst->ops->family == AF_INET6) {
struct rt6_info *rt = (struct rt6_info*)dst;
path->path_cookie = rt6_get_cookie(rt);
}
path->u.rt6.rt6i_nfheader_len = nfheader_len;
return 0;
}
static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
struct rt6_info *rt = (struct rt6_info*)xdst->route;
xdst->u.dst.dev = dev;
dev_hold(dev);
xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
if (!xdst->u.rt6.rt6i_idev) {
dev_put(dev);
return -ENODEV;
}
rt6_transfer_peer(&xdst->u.rt6, rt);
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
xdst->u.rt6.rt6i_node = rt->rt6i_node;
xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
xdst->u.rt6.rt6i_src = rt->rt6i_src;
return 0;
}
static inline void
_decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
{
struct flowi6 *fl6 = &fl->u.ip6;
int onlyproto = 0;
xfrm6: avoid potential infinite loop in _decode_session6() commit d9f92772e8ec388d070752ee8f187ef8fa18621f upstream. syzbot found a way to trigger an infinitie loop by overflowing @offset variable that has been forced to use u16 for some very obscure reason in the past. We probably want to look at NEXTHDR_FRAGMENT handling which looks wrong, in a separate patch. In net-next, we shall try to use skb_header_pointer() instead of pskb_may_pull(). watchdog: BUG: soft lockup - CPU#1 stuck for 134s! [syz-executor738:4553] Modules linked in: irq event stamp: 13885653 hardirqs last enabled at (13885652): [<ffffffff878009d5>] restore_regs_and_return_to_kernel+0x0/0x2b hardirqs last disabled at (13885653): [<ffffffff87800905>] interrupt_entry+0xb5/0xf0 arch/x86/entry/entry_64.S:625 softirqs last enabled at (13614028): [<ffffffff84df0809>] tun_napi_alloc_frags drivers/net/tun.c:1478 [inline] softirqs last enabled at (13614028): [<ffffffff84df0809>] tun_get_user+0x1dd9/0x4290 drivers/net/tun.c:1825 softirqs last disabled at (13614032): [<ffffffff84df1b6f>] tun_get_user+0x313f/0x4290 drivers/net/tun.c:1942 CPU: 1 PID: 4553 Comm: syz-executor738 Not tainted 4.17.0-rc3+ #40 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:check_kcov_mode kernel/kcov.c:67 [inline] RIP: 0010:__sanitizer_cov_trace_pc+0x20/0x50 kernel/kcov.c:101 RSP: 0018:ffff8801d8cfe250 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: ffff8801d88a8080 RBX: ffff8801d7389e40 RCX: 0000000000000006 RDX: 0000000000000000 RSI: ffffffff868da4ad RDI: ffff8801c8a53277 RBP: ffff8801d8cfe250 R08: ffff8801d88a8080 R09: ffff8801d8cfe3e8 R10: ffffed003b19fc87 R11: ffff8801d8cfe43f R12: ffff8801c8a5327f R13: 0000000000000000 R14: ffff8801c8a4e5fe R15: ffff8801d8cfe3e8 FS: 0000000000d88940(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffff600400 CR3: 00000001acab3000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: _decode_session6+0xc1d/0x14f0 net/ipv6/xfrm6_policy.c:150 __xfrm_decode_session+0x71/0x140 net/xfrm/xfrm_policy.c:2368 xfrm_decode_session_reverse include/net/xfrm.h:1213 [inline] icmpv6_route_lookup+0x395/0x6e0 net/ipv6/icmp.c:372 icmp6_send+0x1982/0x2da0 net/ipv6/icmp.c:551 icmpv6_send+0x17a/0x300 net/ipv6/ip6_icmp.c:43 ip6_input_finish+0x14e1/0x1a30 net/ipv6/ip6_input.c:305 NF_HOOK include/linux/netfilter.h:288 [inline] ip6_input+0xe1/0x5e0 net/ipv6/ip6_input.c:327 dst_input include/net/dst.h:450 [inline] ip6_rcv_finish+0x29c/0xa10 net/ipv6/ip6_input.c:71 NF_HOOK include/linux/netfilter.h:288 [inline] ipv6_rcv+0xeb8/0x2040 net/ipv6/ip6_input.c:208 __netif_receive_skb_core+0x2468/0x3650 net/core/dev.c:4646 __netif_receive_skb+0x2c/0x1e0 net/core/dev.c:4711 netif_receive_skb_internal+0x126/0x7b0 net/core/dev.c:4785 napi_frags_finish net/core/dev.c:5226 [inline] napi_gro_frags+0x631/0xc40 net/core/dev.c:5299 tun_get_user+0x3168/0x4290 drivers/net/tun.c:1951 tun_chr_write_iter+0xb9/0x154 drivers/net/tun.c:1996 call_write_iter include/linux/fs.h:1784 [inline] do_iter_readv_writev+0x859/0xa50 fs/read_write.c:680 do_iter_write+0x185/0x5f0 fs/read_write.c:959 vfs_writev+0x1c7/0x330 fs/read_write.c:1004 do_writev+0x112/0x2f0 fs/read_write.c:1039 __do_sys_writev fs/read_write.c:1112 [inline] __se_sys_writev fs/read_write.c:1109 [inline] __x64_sys_writev+0x75/0xb0 fs/read_write.c:1109 do_syscall_64+0x1b1/0x800 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x49/0xbe Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com> Reported-by: syzbot+0053c8...@syzkaller.appspotmail.com Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> [bwh: Backported to 3.16: adjust context] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
2018-05-12 09:49:30 +00:00
u32 offset = skb_network_header_len(skb);
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct ipv6_opt_hdr *exthdr;
const unsigned char *nh = skb_network_header(skb);
u8 nexthdr = nh[IP6CB(skb)->nhoff];
memset(fl6, 0, sizeof(struct flowi6));
fl6->flowi6_mark = skb->mark;
fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
while (nh + offset + 1 < skb->data ||
pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
nh = skb_network_header(skb);
exthdr = (struct ipv6_opt_hdr *)(nh + offset);
switch (nexthdr) {
case NEXTHDR_FRAGMENT:
onlyproto = 1;
case NEXTHDR_ROUTING:
case NEXTHDR_HOP:
case NEXTHDR_DEST:
offset += ipv6_optlen(exthdr);
nexthdr = exthdr->nexthdr;
exthdr = (struct ipv6_opt_hdr *)(nh + offset);
break;
case IPPROTO_UDP:
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-27 19:10:57 +00:00
case IPPROTO_UDPLITE:
case IPPROTO_TCP:
case IPPROTO_SCTP:
case IPPROTO_DCCP:
if (!onlyproto && (nh + offset + 4 < skb->data ||
pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
__be16 *ports = (__be16 *)exthdr;
fl6->fl6_sport = ports[!!reverse];
fl6->fl6_dport = ports[!reverse];
}
fl6->flowi6_proto = nexthdr;
return;
case IPPROTO_ICMPV6:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 2 - skb->data)) {
u8 *icmp = (u8 *)exthdr;
fl6->fl6_icmp_type = icmp[0];
fl6->fl6_icmp_code = icmp[1];
}
fl6->flowi6_proto = nexthdr;
return;
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
struct ip6_mh *mh;
mh = (struct ip6_mh *)exthdr;
fl6->fl6_mh_type = mh->ip6mh_type;
}
fl6->flowi6_proto = nexthdr;
return;
#endif
/* XXX Why are there these headers? */
case IPPROTO_AH:
case IPPROTO_ESP:
case IPPROTO_COMP:
default:
fl6->fl6_ipsec_spi = 0;
fl6->flowi6_proto = nexthdr;
return;
}
}
}
static inline int xfrm6_garbage_collect(struct dst_ops *ops)
{
struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops);
xfrm6_policy_afinfo.garbage_collect(net);
return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
}
static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->update_pmtu(path, sk, skb, mtu);
}
static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->redirect(path, sk, skb);
}
static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
dst_destroy_metrics_generic(dst);
if (rt6_has_peer(&xdst->u.rt6)) {
struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
inet_putpeer(peer);
}
xfrm_dst_destroy(xdst);
}
static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int unregister)
{
struct xfrm_dst *xdst;
if (!unregister)
return;
xdst = (struct xfrm_dst *)dst;
if (xdst->u.rt6.rt6i_idev->dev == dev) {
struct inet6_dev *loopback_idev =
in6_dev_get(dev_net(dev)->loopback_dev);
BUG_ON(!loopback_idev);
do {
in6_dev_put(xdst->u.rt6.rt6i_idev);
xdst->u.rt6.rt6i_idev = loopback_idev;
in6_dev_hold(loopback_idev);
xdst = (struct xfrm_dst *)xdst->u.dst.child;
} while (xdst->u.dst.xfrm);
__in6_dev_put(loopback_idev);
}
xfrm_dst_ifdown(dst, dev);
}
static struct dst_ops xfrm6_dst_ops = {
.family = AF_INET6,
.protocol = cpu_to_be16(ETH_P_IPV6),
.gc = xfrm6_garbage_collect,
.update_pmtu = xfrm6_update_pmtu,
.redirect = xfrm6_redirect,
net: Implement read-only protection and COW'ing of metrics. Routing metrics are now copy-on-write. Initially a route entry points it's metrics at a read-only location. If a routing table entry exists, it will point there. Else it will point at the all zero metric place-holder called 'dst_default_metrics'. The writeability state of the metrics is stored in the low bits of the metrics pointer, we have two bits left to spare if we want to store more states. For the initial implementation, COW is implemented simply via kmalloc. However future enhancements will change this to place the writable metrics somewhere else, in order to increase sharing. Very likely this "somewhere else" will be the inetpeer cache. Note also that this means that metrics updates may transiently fail if we cannot COW the metrics successfully. But even by itself, this patch should decrease memory usage and increase cache locality especially for routing workloads. In those cases the read-only metric copies stay in place and never get written to. TCP workloads where metrics get updated, and those rare cases where PMTU triggers occur, will take a very slight performance hit. But that hit will be alleviated when the long-term writable metrics move to a more sharable location. Since the metrics storage went from a u32 array of RTAX_MAX entries to what is essentially a pointer, some retooling of the dst_entry layout was necessary. Most importantly, we need to preserve the alignment of the reference count so that it doesn't share cache lines with the read-mostly state, as per Eric Dumazet's alignment assertion checks. The only non-trivial bit here is the move of the 'flags' member into the writeable cacheline. This is OK since we are always accessing the flags around the same moment when we made a modification to the reference count. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-27 04:51:05 +00:00
.cow_metrics = dst_cow_metrics_generic,
.destroy = xfrm6_dst_destroy,
.ifdown = xfrm6_dst_ifdown,
.local_out = __ip6_local_out,
.gc_thresh = 32768,
};
static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
.family = AF_INET6,
.dst_ops = &xfrm6_dst_ops,
.dst_lookup = xfrm6_dst_lookup,
.get_saddr = xfrm6_get_saddr,
.decode_session = _decode_session6,
.get_tos = xfrm6_get_tos,
net: ipv6: fix oops in inet_putpeer() Commit 97bab73f (inet: Hide route peer accesses behind helpers.) introduced a bug in xfrm6_policy_destroy(). The xfrm_dst's _rt6i_peer member is not initialized, causing a false positive result from inetpeer_ptr_is_peer(), which in turn causes a NULL pointer dereference in inet_putpeer(). Pid: 314, comm: kworker/0:1 Not tainted 3.6.0-rc1+ #17 To Be Filled By O.E.M. To Be Filled By O.E.M./P4S800D-X EIP: 0060:[<c03abf93>] EFLAGS: 00010246 CPU: 0 EIP is at inet_putpeer+0xe/0x16 EAX: 00000000 EBX: f3481700 ECX: 00000000 EDX: 000dd641 ESI: f3481700 EDI: c05e949c EBP: f551def4 ESP: f551def4 DS: 007b ES: 007b FS: 0000 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 00000070 CR3: 3243d000 CR4: 00000750 DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000 DR6: ffff0ff0 DR7: 00000400 f551df04 c0423de1 00000000 f3481700 f551df18 c038d5f7 f254b9f8 f551df28 f34f85d8 f551df20 c03ef48d f551df3c c0396870 f30697e8 f24e1738 c05e98f4 f5509540 c05cd2b4 f551df7c c0142d2b c043feb5 f5509540 00000000 c05cd2e8 [<c0423de1>] xfrm6_dst_destroy+0x42/0xdb [<c038d5f7>] dst_destroy+0x1d/0xa4 [<c03ef48d>] xfrm_bundle_flo_delete+0x2b/0x36 [<c0396870>] flow_cache_gc_task+0x85/0x9f [<c0142d2b>] process_one_work+0x122/0x441 [<c043feb5>] ? apic_timer_interrupt+0x31/0x38 [<c03967eb>] ? flow_cache_new_hashrnd+0x2b/0x2b [<c0143e2d>] worker_thread+0x113/0x3cc Fix by adding a init_dst() callback to struct xfrm_policy_afinfo to properly initialize the dst's peer pointer. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-08-20 09:56:56 +00:00
.init_dst = xfrm6_init_dst,
.init_path = xfrm6_init_path,
.fill_dst = xfrm6_fill_dst,
.blackhole_route = ip6_blackhole_route,
};
static int __init xfrm6_policy_init(void)
{
return xfrm_policy_register_afinfo(&xfrm6_policy_afinfo);
}
static void xfrm6_policy_fini(void)
{
xfrm_policy_unregister_afinfo(&xfrm6_policy_afinfo);
}
#ifdef CONFIG_SYSCTL
static struct ctl_table xfrm6_policy_table[] = {
{
.procname = "xfrm6_gc_thresh",
.data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
static int __net_init xfrm6_net_init(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
table = xfrm6_policy_table;
if (!net_eq(net, &init_net)) {
table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL);
if (!table)
goto err_alloc;
table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
if (!hdr)
goto err_reg;
net->ipv6.sysctl.xfrm6_hdr = hdr;
return 0;
err_reg:
if (!net_eq(net, &init_net))
kfree(table);
err_alloc:
return -ENOMEM;
}
static void __net_exit xfrm6_net_exit(struct net *net)
{
struct ctl_table *table;
if (net->ipv6.sysctl.xfrm6_hdr == NULL)
return;
table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr);
if (!net_eq(net, &init_net))
kfree(table);
}
static struct pernet_operations xfrm6_net_ops = {
.init = xfrm6_net_init,
.exit = xfrm6_net_exit,
};
#endif
int __init xfrm6_init(void)
{
int ret;
dst_entries_init(&xfrm6_dst_ops);
ret = xfrm6_policy_init();
if (ret) {
dst_entries_destroy(&xfrm6_dst_ops);
goto out;
}
ret = xfrm6_state_init();
if (ret)
goto out_policy;
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&xfrm6_net_ops);
#endif
out:
return ret;
out_policy:
xfrm6_policy_fini();
goto out;
}
void xfrm6_fini(void)
{
#ifdef CONFIG_SYSCTL
unregister_pernet_subsys(&xfrm6_net_ops);
#endif
xfrm6_policy_fini();
xfrm6_state_fini();
dst_entries_destroy(&xfrm6_dst_ops);
}