linux/net/sched/act_ct.c

1644 lines
40 KiB
C
Raw Normal View History

net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/* -
* net/sched/act_ct.c Connection Tracking action
*
* Authors: Paul Blakey <paulb@mellanox.com>
* Yossi Kuperman <yossiku@mellanox.com>
* Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/rhashtable.h>
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/act_api.h>
#include <net/ip.h>
#include <net/ipv6_frag.h>
#include <uapi/linux/tc_act/tc_ct.h>
#include <net/tc_act/tc_ct.h>
#include <net/tc_wrapper.h>
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
#include <net/netfilter/nf_flow_table.h>
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_acct.h>
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#include <net/netfilter/nf_conntrack_act_ct.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <uapi/linux/netfilter/nf_nat.h>
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
static struct workqueue_struct *act_ct_wq;
static struct rhashtable zones_ht;
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
static DEFINE_MUTEX(zones_mutex);
struct tcf_ct_flow_table {
struct rhash_head node; /* In zones tables */
struct rcu_work rwork;
struct nf_flowtable nf_ft;
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
refcount_t ref;
u16 zone;
bool dying;
};
static const struct rhashtable_params zones_params = {
.head_offset = offsetof(struct tcf_ct_flow_table, node),
.key_offset = offsetof(struct tcf_ct_flow_table, zone),
.key_len = sizeof_field(struct tcf_ct_flow_table, zone),
.automatic_shrinking = true,
};
static struct flow_action_entry *
tcf_ct_flow_table_flow_action_get_next(struct flow_action *flow_action)
{
int i = flow_action->num_entries++;
return &flow_action->entries[i];
}
static void tcf_ct_add_mangle_action(struct flow_action *action,
enum flow_action_mangle_base htype,
u32 offset,
u32 mask,
u32 val)
{
struct flow_action_entry *entry;
entry = tcf_ct_flow_table_flow_action_get_next(action);
entry->id = FLOW_ACTION_MANGLE;
entry->mangle.htype = htype;
entry->mangle.mask = ~mask;
entry->mangle.offset = offset;
entry->mangle.val = val;
}
/* The following nat helper functions check if the inverted reverse tuple
* (target) is different then the current dir tuple - meaning nat for ports
* and/or ip is needed, and add the relevant mangle actions.
*/
static void
tcf_ct_flow_table_add_action_nat_ipv4(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3)))
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4,
offsetof(struct iphdr, saddr),
0xFFFFFFFF,
be32_to_cpu(target.src.u3.ip));
if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3)))
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP4,
offsetof(struct iphdr, daddr),
0xFFFFFFFF,
be32_to_cpu(target.dst.u3.ip));
}
static void
tcf_ct_add_ipv6_addr_mangle_action(struct flow_action *action,
union nf_inet_addr *addr,
u32 offset)
{
int i;
for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i++)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
i * sizeof(u32) + offset,
0xFFFFFFFF, be32_to_cpu(addr->ip6[i]));
}
static void
tcf_ct_flow_table_add_action_nat_ipv6(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
if (memcmp(&target.src.u3, &tuple->src.u3, sizeof(target.src.u3)))
tcf_ct_add_ipv6_addr_mangle_action(action, &target.src.u3,
offsetof(struct ipv6hdr,
saddr));
if (memcmp(&target.dst.u3, &tuple->dst.u3, sizeof(target.dst.u3)))
tcf_ct_add_ipv6_addr_mangle_action(action, &target.dst.u3,
offsetof(struct ipv6hdr,
daddr));
}
static void
tcf_ct_flow_table_add_action_nat_tcp(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
__be16 target_src = target.src.u.tcp.port;
__be16 target_dst = target.dst.u.tcp.port;
if (target_src != tuple->src.u.tcp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
offsetof(struct tcphdr, source),
0xFFFF, be16_to_cpu(target_src));
if (target_dst != tuple->dst.u.tcp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
offsetof(struct tcphdr, dest),
0xFFFF, be16_to_cpu(target_dst));
}
static void
tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_tuple target,
struct flow_action *action)
{
__be16 target_src = target.src.u.udp.port;
__be16 target_dst = target.dst.u.udp.port;
if (target_src != tuple->src.u.udp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
offsetof(struct udphdr, source),
0xFFFF, be16_to_cpu(target_src));
if (target_dst != tuple->dst.u.udp.port)
tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
offsetof(struct udphdr, dest),
0xFFFF, be16_to_cpu(target_dst));
}
static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct,
enum ip_conntrack_dir dir,
struct flow_action *action)
{
struct nf_conn_labels *ct_labels;
struct flow_action_entry *entry;
enum ip_conntrack_info ctinfo;
u32 *act_ct_labels;
entry = tcf_ct_flow_table_flow_action_get_next(action);
entry->id = FLOW_ACTION_CT_METADATA;
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
entry->ct_metadata.mark = READ_ONCE(ct->mark);
#endif
ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
IP_CT_ESTABLISHED_REPLY;
/* aligns with the CT reference on the SKB nf_ct_set */
entry->ct_metadata.cookie = (unsigned long)ct | ctinfo;
entry->ct_metadata.orig_dir = dir == IP_CT_DIR_ORIGINAL;
act_ct_labels = entry->ct_metadata.labels;
ct_labels = nf_ct_labels_find(ct);
if (ct_labels)
memcpy(act_ct_labels, ct_labels->bits, NF_CT_LABELS_MAX_SIZE);
else
memset(act_ct_labels, 0, NF_CT_LABELS_MAX_SIZE);
}
static int tcf_ct_flow_table_add_action_nat(struct net *net,
struct nf_conn *ct,
enum ip_conntrack_dir dir,
struct flow_action *action)
{
const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
struct nf_conntrack_tuple target;
if (!(ct->status & IPS_NAT_MASK))
return 0;
nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple);
switch (tuple->src.l3num) {
case NFPROTO_IPV4:
tcf_ct_flow_table_add_action_nat_ipv4(tuple, target,
action);
break;
case NFPROTO_IPV6:
tcf_ct_flow_table_add_action_nat_ipv6(tuple, target,
action);
break;
default:
return -EOPNOTSUPP;
}
switch (nf_ct_protonum(ct)) {
case IPPROTO_TCP:
tcf_ct_flow_table_add_action_nat_tcp(tuple, target, action);
break;
case IPPROTO_UDP:
tcf_ct_flow_table_add_action_nat_udp(tuple, target, action);
break;
default:
return -EOPNOTSUPP;
}
return 0;
}
static int tcf_ct_flow_table_fill_actions(struct net *net,
const struct flow_offload *flow,
enum flow_offload_tuple_dir tdir,
struct nf_flow_rule *flow_rule)
{
struct flow_action *action = &flow_rule->rule->action;
int num_entries = action->num_entries;
struct nf_conn *ct = flow->ct;
enum ip_conntrack_dir dir;
int i, err;
switch (tdir) {
case FLOW_OFFLOAD_DIR_ORIGINAL:
dir = IP_CT_DIR_ORIGINAL;
break;
case FLOW_OFFLOAD_DIR_REPLY:
dir = IP_CT_DIR_REPLY;
break;
default:
return -EOPNOTSUPP;
}
err = tcf_ct_flow_table_add_action_nat(net, ct, dir, action);
if (err)
goto err_nat;
tcf_ct_flow_table_add_action_meta(ct, dir, action);
return 0;
err_nat:
/* Clear filled actions */
for (i = num_entries; i < action->num_entries; i++)
memset(&action->entries[i], 0, sizeof(action->entries[i]));
action->num_entries = num_entries;
return err;
}
static struct nf_flowtable_type flowtable_ct = {
.action = tcf_ct_flow_table_fill_actions,
.owner = THIS_MODULE,
};
static int tcf_ct_flow_table_get(struct net *net, struct tcf_ct_params *params)
{
struct tcf_ct_flow_table *ct_ft;
int err = -ENOMEM;
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
mutex_lock(&zones_mutex);
ct_ft = rhashtable_lookup_fast(&zones_ht, &params->zone, zones_params);
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
if (ct_ft && refcount_inc_not_zero(&ct_ft->ref))
goto out_unlock;
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
ct_ft = kzalloc(sizeof(*ct_ft), GFP_KERNEL);
if (!ct_ft)
goto err_alloc;
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
refcount_set(&ct_ft->ref, 1);
ct_ft->zone = params->zone;
err = rhashtable_insert_fast(&zones_ht, &ct_ft->node, zones_params);
if (err)
goto err_insert;
ct_ft->nf_ft.type = &flowtable_ct;
ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD |
NF_FLOWTABLE_COUNTER;
err = nf_flow_table_init(&ct_ft->nf_ft);
if (err)
goto err_init;
write_pnet(&ct_ft->nf_ft.net, net);
__module_get(THIS_MODULE);
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
out_unlock:
params->ct_ft = ct_ft;
params->nf_ft = &ct_ft->nf_ft;
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
mutex_unlock(&zones_mutex);
return 0;
err_init:
rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
err_insert:
kfree(ct_ft);
err_alloc:
net/sched: act_ct: fix lockdep splat in tcf_ct_flow_table_get Convert zones_lock spinlock to zones_mutex mutex, and struct (tcf_ct_flow_table)->ref to a refcount, so that control path can use regular GFP_KERNEL allocations from standard process context. This is more robust in case of memory pressure. The refcount is needed because tcf_ct_flow_table_put() can be called from RCU callback, thus in BH context. The issue was spotted by syzbot, as rhashtable_init() was called with a spinlock held, which is bad since GFP_KERNEL allocations can sleep. Note to developers : Please make sure your patches are tested with CONFIG_DEBUG_ATOMIC_SLEEP=y BUG: sleeping function called from invalid context at mm/slab.h:565 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 9582, name: syz-executor610 2 locks held by syz-executor610/9582: #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnl_lock net/core/rtnetlink.c:72 [inline] #0: ffffffff8a34eb80 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x3f9/0xad0 net/core/rtnetlink.c:5437 #1: ffffffff8a3961b8 (zones_lock){+...}, at: spin_lock_bh include/linux/spinlock.h:343 [inline] #1: ffffffff8a3961b8 (zones_lock){+...}, at: tcf_ct_flow_table_get+0xa3/0x1700 net/sched/act_ct.c:67 Preemption disabled at: [<0000000000000000>] 0x0 CPU: 0 PID: 9582 Comm: syz-executor610 Not tainted 5.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x188/0x20d lib/dump_stack.c:118 ___might_sleep.cold+0x1f4/0x23d kernel/sched/core.c:6798 slab_pre_alloc_hook mm/slab.h:565 [inline] slab_alloc_node mm/slab.c:3227 [inline] kmem_cache_alloc_node_trace+0x272/0x790 mm/slab.c:3593 __do_kmalloc_node mm/slab.c:3615 [inline] __kmalloc_node+0x38/0x60 mm/slab.c:3623 kmalloc_node include/linux/slab.h:578 [inline] kvmalloc_node+0x61/0xf0 mm/util.c:574 kvmalloc include/linux/mm.h:645 [inline] kvzalloc include/linux/mm.h:653 [inline] bucket_table_alloc+0x8b/0x480 lib/rhashtable.c:175 rhashtable_init+0x3d2/0x750 lib/rhashtable.c:1054 nf_flow_table_init+0x16d/0x310 net/netfilter/nf_flow_table_core.c:498 tcf_ct_flow_table_get+0xe33/0x1700 net/sched/act_ct.c:82 tcf_ct_init+0xba4/0x18a6 net/sched/act_ct.c:1050 tcf_action_init_1+0x697/0xa20 net/sched/act_api.c:945 tcf_action_init+0x1e9/0x2f0 net/sched/act_api.c:1001 tcf_action_add+0xdb/0x370 net/sched/act_api.c:1411 tc_ctl_action+0x366/0x456 net/sched/act_api.c:1466 rtnetlink_rcv_msg+0x44e/0xad0 net/core/rtnetlink.c:5440 netlink_rcv_skb+0x15a/0x410 net/netlink/af_netlink.c:2478 netlink_unicast_kernel net/netlink/af_netlink.c:1303 [inline] netlink_unicast+0x537/0x740 net/netlink/af_netlink.c:1329 netlink_sendmsg+0x882/0xe10 net/netlink/af_netlink.c:1918 sock_sendmsg_nosec net/socket.c:652 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:672 ____sys_sendmsg+0x6b9/0x7d0 net/socket.c:2343 ___sys_sendmsg+0x100/0x170 net/socket.c:2397 __sys_sendmsg+0xec/0x1b0 net/socket.c:2430 do_syscall_64+0xf6/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x4403d9 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 fb 13 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffd719af218 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00000000004002c8 RCX: 00000000004403d9 RDX: 0000000000000000 RSI: 0000000020000300 RDI: 0000000000000003 RBP: 00000000006ca018 R08: 0000000000000005 R09: 00000000004002c8 R10: 0000000000000008 R11: 00000000000 Fixes: c34b961a2492 ("net/sched: act_ct: Create nf flow table per zone") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Paul Blakey <paulb@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-03-09 00:27:48 +03:00
mutex_unlock(&zones_mutex);
return err;
}
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
struct flow_block *block;
ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
/* Remove any remaining callbacks before cleanup */
block = &ct_ft->nf_ft.flow_block;
down_write(&ct_ft->nf_ft.flow_block_lock);
list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
list_del(&block_cb->list);
flow_block_cb_free(block_cb);
}
up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);
module_put(THIS_MODULE);
}
static void tcf_ct_flow_table_put(struct tcf_ct_flow_table *ct_ft)
{
if (refcount_dec_and_test(&ct_ft->ref)) {
rhashtable_remove_fast(&zones_ht, &ct_ft->node, zones_params);
INIT_RCU_WORK(&ct_ft->rwork, tcf_ct_flow_table_cleanup_work);
queue_rcu_work(act_ct_wq, &ct_ft->rwork);
}
}
static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry,
struct nf_conn_act_ct_ext *act_ct_ext, u8 dir)
{
entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC;
entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir];
}
static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
struct nf_conn *ct,
bool tcp)
{
struct nf_conn_act_ct_ext *act_ct_ext;
struct flow_offload *entry;
int err;
if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
return;
entry = flow_offload_alloc(ct);
if (!entry) {
WARN_ON_ONCE(1);
goto err_alloc;
}
if (tcp) {
ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
}
act_ct_ext = nf_conn_act_ct_ext_find(ct);
if (act_ct_ext) {
tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
}
err = flow_offload_add(&ct_ft->nf_ft, entry);
if (err)
goto err_add;
return;
err_add:
flow_offload_free(entry);
err_alloc:
clear_bit(IPS_OFFLOAD_BIT, &ct->status);
}
static void tcf_ct_flow_table_process_conn(struct tcf_ct_flow_table *ct_ft,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo)
{
bool tcp = false;
if ((ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) ||
!test_bit(IPS_ASSURED_BIT, &ct->status))
return;
switch (nf_ct_protonum(ct)) {
case IPPROTO_TCP:
tcp = true;
if (ct->proto.tcp.state != TCP_CONNTRACK_ESTABLISHED)
return;
break;
case IPPROTO_UDP:
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE: {
struct nf_conntrack_tuple *tuple;
if (ct->status & IPS_NAT_MASK)
return;
tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
/* No support for GRE v1 */
if (tuple->src.u.gre.key || tuple->dst.u.gre.key)
return;
break;
}
#endif
default:
return;
}
if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
ct->status & IPS_SEQ_ADJUST)
return;
tcf_ct_flow_table_add(ct_ft, ct, tcp);
}
static bool
tcf_ct_flow_table_fill_tuple_ipv4(struct sk_buff *skb,
struct flow_offload_tuple *tuple,
struct tcphdr **tcph)
{
struct flow_ports *ports;
unsigned int thoff;
struct iphdr *iph;
size_t hdrsize;
u8 ipproto;
if (!pskb_network_may_pull(skb, sizeof(*iph)))
return false;
iph = ip_hdr(skb);
thoff = iph->ihl * 4;
if (ip_is_fragment(iph) ||
unlikely(thoff != sizeof(struct iphdr)))
return false;
ipproto = iph->protocol;
switch (ipproto) {
case IPPROTO_TCP:
hdrsize = sizeof(struct tcphdr);
break;
case IPPROTO_UDP:
hdrsize = sizeof(*ports);
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE:
hdrsize = sizeof(struct gre_base_hdr);
break;
#endif
default:
return false;
}
if (iph->ttl <= 1)
return false;
if (!pskb_network_may_pull(skb, thoff + hdrsize))
return false;
switch (ipproto) {
case IPPROTO_TCP:
*tcph = (void *)(skb_network_header(skb) + thoff);
fallthrough;
case IPPROTO_UDP:
ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
tuple->src_port = ports->source;
tuple->dst_port = ports->dest;
break;
case IPPROTO_GRE: {
struct gre_base_hdr *greh;
greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff);
if ((greh->flags & GRE_VERSION) != GRE_VERSION_0)
return false;
break;
}
}
iph = ip_hdr(skb);
tuple->src_v4.s_addr = iph->saddr;
tuple->dst_v4.s_addr = iph->daddr;
tuple->l3proto = AF_INET;
tuple->l4proto = ipproto;
return true;
}
static bool
tcf_ct_flow_table_fill_tuple_ipv6(struct sk_buff *skb,
struct flow_offload_tuple *tuple,
struct tcphdr **tcph)
{
struct flow_ports *ports;
struct ipv6hdr *ip6h;
unsigned int thoff;
size_t hdrsize;
u8 nexthdr;
if (!pskb_network_may_pull(skb, sizeof(*ip6h)))
return false;
ip6h = ipv6_hdr(skb);
thoff = sizeof(*ip6h);
nexthdr = ip6h->nexthdr;
switch (nexthdr) {
case IPPROTO_TCP:
hdrsize = sizeof(struct tcphdr);
break;
case IPPROTO_UDP:
hdrsize = sizeof(*ports);
break;
#ifdef CONFIG_NF_CT_PROTO_GRE
case IPPROTO_GRE:
hdrsize = sizeof(struct gre_base_hdr);
break;
#endif
default:
return false;
}
if (ip6h->hop_limit <= 1)
return false;
if (!pskb_network_may_pull(skb, thoff + hdrsize))
return false;
switch (nexthdr) {
case IPPROTO_TCP:
*tcph = (void *)(skb_network_header(skb) + thoff);
fallthrough;
case IPPROTO_UDP:
ports = (struct flow_ports *)(skb_network_header(skb) + thoff);
tuple->src_port = ports->source;
tuple->dst_port = ports->dest;
break;
case IPPROTO_GRE: {
struct gre_base_hdr *greh;
greh = (struct gre_base_hdr *)(skb_network_header(skb) + thoff);
if ((greh->flags & GRE_VERSION) != GRE_VERSION_0)
return false;
break;
}
}
ip6h = ipv6_hdr(skb);
tuple->src_v6 = ip6h->saddr;
tuple->dst_v6 = ip6h->daddr;
tuple->l3proto = AF_INET6;
tuple->l4proto = nexthdr;
return true;
}
static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
struct sk_buff *skb,
u8 family)
{
struct nf_flowtable *nf_ft = &p->ct_ft->nf_ft;
struct flow_offload_tuple_rhash *tuplehash;
struct flow_offload_tuple tuple = {};
enum ip_conntrack_info ctinfo;
struct tcphdr *tcph = NULL;
struct flow_offload *flow;
struct nf_conn *ct;
u8 dir;
switch (family) {
case NFPROTO_IPV4:
if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph))
return false;
break;
case NFPROTO_IPV6:
if (!tcf_ct_flow_table_fill_tuple_ipv6(skb, &tuple, &tcph))
return false;
break;
default:
return false;
}
tuplehash = flow_offload_lookup(nf_ft, &tuple);
if (!tuplehash)
return false;
dir = tuplehash->tuple.dir;
flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
ct = flow->ct;
if (tcph && (unlikely(tcph->fin || tcph->rst))) {
flow_offload_teardown(flow);
return false;
}
ctinfo = dir == FLOW_OFFLOAD_DIR_ORIGINAL ? IP_CT_ESTABLISHED :
IP_CT_ESTABLISHED_REPLY;
flow_offload_refresh(nf_ft, flow);
nf_conntrack_get(&ct->ct_general);
nf_ct_set(skb, ct, ctinfo);
if (nf_ft->flags & NF_FLOWTABLE_COUNTER)
nf_ct_acct_update(ct, dir, skb->len);
return true;
}
static int tcf_ct_flow_tables_init(void)
{
return rhashtable_init(&zones_ht, &zones_params);
}
static void tcf_ct_flow_tables_uninit(void)
{
rhashtable_destroy(&zones_ht);
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
static struct tc_action_ops act_ct_ops;
struct tc_ct_action_net {
struct tc_action_net tn; /* Must be first */
bool labels;
};
/* Determine whether skb->_nfct is equal to the result of conntrack lookup. */
static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb,
struct tcf_ct_params *p)
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
return false;
if (!net_eq(net, read_pnet(&ct->ct_net)))
goto drop_ct;
if (nf_ct_zone(ct)->id != p->zone)
goto drop_ct;
if (p->helper) {
struct nf_conn_help *help;
help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER);
if (help && rcu_access_pointer(help->helper) != p->helper)
goto drop_ct;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
/* Force conntrack entry direction. */
if ((p->ct_action & TCA_CT_ACT_FORCE) &&
CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) {
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (nf_ct_is_confirmed(ct))
nf_ct_kill(ct);
goto drop_ct;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
return true;
drop_ct:
nf_ct_put(ct);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
return false;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
/* Trim the skb to the length specified by the IP/IPv6 header,
* removing any trailing lower-layer padding. This prepares the skb
* for higher-layer processing that assumes skb->len excludes padding
* (such as nf_ip_checksum). The caller needs to pull the skb to the
* network header, and ensure ip_hdr/ipv6_hdr points to valid data.
*/
static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family)
{
unsigned int len;
switch (family) {
case NFPROTO_IPV4:
len = ntohs(ip_hdr(skb)->tot_len);
break;
case NFPROTO_IPV6:
len = sizeof(struct ipv6hdr)
+ ntohs(ipv6_hdr(skb)->payload_len);
break;
default:
len = skb->len;
}
return pskb_trim_rcsum(skb, len);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
static u8 tcf_ct_skb_nf_family(struct sk_buff *skb)
{
u8 family = NFPROTO_UNSPEC;
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>
2020-07-03 23:26:43 +03:00
switch (skb_protocol(skb, true)) {
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
case htons(ETH_P_IP):
family = NFPROTO_IPV4;
break;
case htons(ETH_P_IPV6):
family = NFPROTO_IPV6;
break;
default:
break;
}
return family;
}
static int tcf_ct_ipv4_is_fragment(struct sk_buff *skb, bool *frag)
{
unsigned int len;
len = skb_network_offset(skb) + sizeof(struct iphdr);
if (unlikely(skb->len < len))
return -EINVAL;
if (unlikely(!pskb_may_pull(skb, len)))
return -ENOMEM;
*frag = ip_is_fragment(ip_hdr(skb));
return 0;
}
static int tcf_ct_ipv6_is_fragment(struct sk_buff *skb, bool *frag)
{
unsigned int flags = 0, len, payload_ofs = 0;
unsigned short frag_off;
int nexthdr;
len = skb_network_offset(skb) + sizeof(struct ipv6hdr);
if (unlikely(skb->len < len))
return -EINVAL;
if (unlikely(!pskb_may_pull(skb, len)))
return -ENOMEM;
nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags);
if (unlikely(nexthdr < 0))
return -EPROTO;
*frag = flags & IP6_FH_F_FRAG;
return 0;
}
static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb,
u8 family, u16 zone, bool *defrag)
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
{
enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
int err = 0;
bool frag;
u16 mru;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
/* Previously seen (loopback)? Ignore. */
ct = nf_ct_get(skb, &ctinfo);
if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED)
return 0;
if (family == NFPROTO_IPV4)
err = tcf_ct_ipv4_is_fragment(skb, &frag);
else
err = tcf_ct_ipv6_is_fragment(skb, &frag);
if (err || !frag)
return err;
skb_get(skb);
mru = tc_skb_cb(skb)->mru;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (family == NFPROTO_IPV4) {
enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone;
memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
local_bh_disable();
err = ip_defrag(net, skb, user);
local_bh_enable();
if (err && err != -EINPROGRESS)
return err;
if (!err) {
*defrag = true;
mru = IPCB(skb)->frag_max_size;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
} else { /* NFPROTO_IPV6 */
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone;
memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm));
err = nf_ct_frag6_gather(net, skb, user);
if (err && err != -EINPROGRESS)
goto out_free;
if (!err) {
*defrag = true;
mru = IP6CB(skb)->frag_max_size;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
#else
err = -EOPNOTSUPP;
goto out_free;
#endif
}
net/sched: act_ct: fix wild memory access when clearing fragments while testing re-assembly/re-fragmentation using act_ct, it's possible to observe a crash like the following one: KASAN: maybe wild-memory-access in range [0x0001000000000448-0x000100000000044f] CPU: 50 PID: 0 Comm: swapper/50 Tainted: G S 5.12.0-rc7+ #424 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017 RIP: 0010:inet_frag_rbtree_purge+0x50/0xc0 Code: 00 fc ff df 48 89 c3 31 ed 48 89 df e8 a9 7a 38 ff 4c 89 fe 48 89 df 49 89 c6 e8 5b 3a 38 ff 48 8d 7b 40 48 89 f8 48 c1 e8 03 <42> 80 3c 20 00 75 59 48 8d bb d0 00 00 00 4c 8b 6b 40 48 89 f8 48 RSP: 0018:ffff888c31449db8 EFLAGS: 00010203 RAX: 0000200000000089 RBX: 000100000000040e RCX: ffffffff989eb960 RDX: 0000000000000140 RSI: ffffffff97cfb977 RDI: 000100000000044e RBP: 0000000000000900 R08: 0000000000000000 R09: ffffed1186289350 R10: 0000000000000003 R11: ffffed1186289350 R12: dffffc0000000000 R13: 000100000000040e R14: 0000000000000000 R15: ffff888155e02160 FS: 0000000000000000(0000) GS:ffff888c31440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005600cb70a5b8 CR3: 0000000a2c014005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> inet_frag_destroy+0xa9/0x150 call_timer_fn+0x2d/0x180 run_timer_softirq+0x4fe/0xe70 __do_softirq+0x197/0x5a0 irq_exit_rcu+0x1de/0x200 sysvec_apic_timer_interrupt+0x6b/0x80 </IRQ> when act_ct temporarily stores an IP fragment, restoring the skb qdisc cb results in putting random data in FRAG_CB(), and this causes those "wild" memory accesses later, when the rbtree is purged. Never overwrite the skb cb in case tcf_ct_handle_fragments() returns -EINPROGRESS. Fixes: ae372cb1750f ("net/sched: act_ct: fix restore the qdisc_skb_cb after defrag") Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support") Reported-by: Shuang Li <shuali@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-04-26 18:45:51 +03:00
if (err != -EINPROGRESS)
tc_skb_cb(skb)->mru = mru;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
skb_clear_hash(skb);
skb->ignore_df = 1;
return err;
out_free:
kfree_skb(skb);
return err;
}
static void tcf_ct_params_free(struct tcf_ct_params *params)
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
{
if (params->helper) {
#if IS_ENABLED(CONFIG_NF_NAT)
if (params->ct_action & TCA_CT_ACT_NAT)
nf_nat_helper_put(params->helper);
#endif
nf_conntrack_helper_put(params->helper);
}
if (params->ct_ft)
tcf_ct_flow_table_put(params->ct_ft);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (params->tmpl)
nf_ct_put(params->tmpl);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
kfree(params);
}
static void tcf_ct_params_free_rcu(struct rcu_head *head)
{
struct tcf_ct_params *params;
params = container_of(head, struct tcf_ct_params, rcu);
tcf_ct_params_free(params);
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)
u32 new_mark;
if (!mask)
return;
new_mark = mark | (READ_ONCE(ct->mark) & ~(mask));
if (READ_ONCE(ct->mark) != new_mark) {
WRITE_ONCE(ct->mark, new_mark);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (nf_ct_is_confirmed(ct))
nf_conntrack_event_cache(IPCT_MARK, ct);
}
#endif
}
static void tcf_ct_act_set_labels(struct nf_conn *ct,
u32 *labels,
u32 *labels_m)
{
#if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)
size_t labels_sz = sizeof_field(struct tcf_ct_params, labels);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (!memchr_inv(labels_m, 0, labels_sz))
return;
nf_connlabels_replace(ct, labels, labels_m, 4);
#endif
}
static int tcf_ct_act_nat(struct sk_buff *skb,
struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
int ct_action,
struct nf_nat_range2 *range,
bool commit)
{
#if IS_ENABLED(CONFIG_NF_NAT)
int err, action = 0;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (!(ct_action & TCA_CT_ACT_NAT))
return NF_ACCEPT;
if (ct_action & TCA_CT_ACT_NAT_SRC)
action |= BIT(NF_NAT_MANIP_SRC);
if (ct_action & TCA_CT_ACT_NAT_DST)
action |= BIT(NF_NAT_MANIP_DST);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit);
if (action & BIT(NF_NAT_MANIP_SRC))
tc_skb_cb(skb)->post_ct_snat = 1;
if (action & BIT(NF_NAT_MANIP_DST))
tc_skb_cb(skb)->post_ct_dnat = 1;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
return err;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
#else
return NF_ACCEPT;
#endif
}
TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
{
struct net *net = dev_net(skb->dev);
enum ip_conntrack_info ctinfo;
struct tcf_ct *c = to_ct(a);
struct nf_conn *tmpl = NULL;
struct nf_hook_state state;
bool cached, commit, clear;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
int nh_ofs, err, retval;
struct tcf_ct_params *p;
bool add_helper = false;
bool skip_add = false;
bool defrag = false;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
struct nf_conn *ct;
u8 family;
p = rcu_dereference_bh(c->params);
retval = READ_ONCE(c->tcf_action);
commit = p->ct_action & TCA_CT_ACT_COMMIT;
clear = p->ct_action & TCA_CT_ACT_CLEAR;
tmpl = p->tmpl;
tcf_lastuse_update(&c->tcf_tm);
tcf_action_update_bstats(&c->common, skb);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (clear) {
tc_skb_cb(skb)->post_ct = false;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
nf_ct_put(ct);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
}
2021-03-22 21:13:22 +03:00
goto out_clear;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
family = tcf_ct_skb_nf_family(skb);
if (family == NFPROTO_UNSPEC)
goto drop;
/* The conntrack module expects to be working at L3.
* We also try to pull the IPv4/6 header to linear area
*/
nh_ofs = skb_network_offset(skb);
skb_pull_rcsum(skb, nh_ofs);
err = tcf_ct_handle_fragments(net, skb, family, p->zone, &defrag);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (err == -EINPROGRESS) {
retval = TC_ACT_STOLEN;
net/sched: act_ct: fix wild memory access when clearing fragments while testing re-assembly/re-fragmentation using act_ct, it's possible to observe a crash like the following one: KASAN: maybe wild-memory-access in range [0x0001000000000448-0x000100000000044f] CPU: 50 PID: 0 Comm: swapper/50 Tainted: G S 5.12.0-rc7+ #424 Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017 RIP: 0010:inet_frag_rbtree_purge+0x50/0xc0 Code: 00 fc ff df 48 89 c3 31 ed 48 89 df e8 a9 7a 38 ff 4c 89 fe 48 89 df 49 89 c6 e8 5b 3a 38 ff 48 8d 7b 40 48 89 f8 48 c1 e8 03 <42> 80 3c 20 00 75 59 48 8d bb d0 00 00 00 4c 8b 6b 40 48 89 f8 48 RSP: 0018:ffff888c31449db8 EFLAGS: 00010203 RAX: 0000200000000089 RBX: 000100000000040e RCX: ffffffff989eb960 RDX: 0000000000000140 RSI: ffffffff97cfb977 RDI: 000100000000044e RBP: 0000000000000900 R08: 0000000000000000 R09: ffffed1186289350 R10: 0000000000000003 R11: ffffed1186289350 R12: dffffc0000000000 R13: 000100000000040e R14: 0000000000000000 R15: ffff888155e02160 FS: 0000000000000000(0000) GS:ffff888c31440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00005600cb70a5b8 CR3: 0000000a2c014005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> inet_frag_destroy+0xa9/0x150 call_timer_fn+0x2d/0x180 run_timer_softirq+0x4fe/0xe70 __do_softirq+0x197/0x5a0 irq_exit_rcu+0x1de/0x200 sysvec_apic_timer_interrupt+0x6b/0x80 </IRQ> when act_ct temporarily stores an IP fragment, restoring the skb qdisc cb results in putting random data in FRAG_CB(), and this causes those "wild" memory accesses later, when the rbtree is purged. Never overwrite the skb cb in case tcf_ct_handle_fragments() returns -EINPROGRESS. Fixes: ae372cb1750f ("net/sched: act_ct: fix restore the qdisc_skb_cb after defrag") Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support") Reported-by: Shuang Li <shuali@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-04-26 18:45:51 +03:00
goto out_clear;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
if (err)
goto drop;
err = tcf_ct_skb_network_trim(skb, family);
if (err)
goto drop;
/* If we are recirculating packets to match on ct fields and
* committing with a separate ct action, then we don't need to
* actually run the packet through conntrack twice unless it's for a
* different zone.
*/
cached = tcf_ct_skb_nfct_cached(net, skb, p);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (!cached) {
if (tcf_ct_flow_table_lookup(p, skb, family)) {
skip_add = true;
goto do_nat;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
/* Associate skb with specified zone. */
if (tmpl) {
nf_conntrack_put(skb_nfct(skb));
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
nf_conntrack_get(&tmpl->ct_general);
nf_ct_set(skb, tmpl, IP_CT_NEW);
}
state.hook = NF_INET_PRE_ROUTING;
state.net = net;
state.pf = family;
err = nf_conntrack_in(skb, &state);
if (err != NF_ACCEPT)
goto out_push;
}
do_nat:
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
ct = nf_ct_get(skb, &ctinfo);
if (!ct)
goto out_push;
nf_ct_deliver_cached_events(ct);
nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit);
if (err != NF_ACCEPT)
goto drop;
if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) {
err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC);
if (err)
goto drop;
add_helper = true;
if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) {
if (!nfct_seqadj_ext_add(ct))
goto drop;
}
}
if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) {
if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT)
goto drop;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (commit) {
tcf_ct_act_set_mark(ct, p->mark, p->mark_mask);
tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
if (!nf_ct_is_confirmed(ct))
nf_conn_act_ct_ext_add(ct);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
/* This will take care of sending queued events
* even if the connection is already confirmed.
*/
if (nf_conntrack_confirm(skb) != NF_ACCEPT)
goto drop;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
if (!skip_add)
tcf_ct_flow_table_process_conn(p->ct_ft, ct, ctinfo);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
out_push:
skb_push_rcsum(skb, nh_ofs);
tc_skb_cb(skb)->post_ct = true;
tc_skb_cb(skb)->zone = p->zone;
2021-03-22 21:13:22 +03:00
out_clear:
if (defrag)
qdisc_skb_cb(skb)->pkt_len = skb->len;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
return retval;
drop:
tcf_action_inc_drop_qstats(&c->common);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
return TC_ACT_SHOT;
}
static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
[TCA_CT_ACTION] = { .type = NLA_U16 },
[TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)),
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
[TCA_CT_ZONE] = { .type = NLA_U16 },
[TCA_CT_MARK] = { .type = NLA_U32 },
[TCA_CT_MARK_MASK] = { .type = NLA_U32 },
[TCA_CT_LABELS] = { .type = NLA_BINARY,
.len = 128 / BITS_PER_BYTE },
[TCA_CT_LABELS_MASK] = { .type = NLA_BINARY,
.len = 128 / BITS_PER_BYTE },
[TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 },
[TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 },
[TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
[TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
[TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
[TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
[TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN },
[TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 },
[TCA_CT_HELPER_PROTO] = { .type = NLA_U8 },
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
};
static int tcf_ct_fill_params_nat(struct tcf_ct_params *p,
struct tc_ct *parm,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
struct nf_nat_range2 *range;
if (!(p->ct_action & TCA_CT_ACT_NAT))
return 0;
if (!IS_ENABLED(CONFIG_NF_NAT)) {
NL_SET_ERR_MSG_MOD(extack, "Netfilter nat isn't enabled in kernel");
return -EOPNOTSUPP;
}
if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
return 0;
if ((p->ct_action & TCA_CT_ACT_NAT_SRC) &&
(p->ct_action & TCA_CT_ACT_NAT_DST)) {
NL_SET_ERR_MSG_MOD(extack, "dnat and snat can't be enabled at the same time");
return -EOPNOTSUPP;
}
range = &p->range;
if (tb[TCA_CT_NAT_IPV4_MIN]) {
struct nlattr *max_attr = tb[TCA_CT_NAT_IPV4_MAX];
p->ipv4_range = true;
range->flags |= NF_NAT_RANGE_MAP_IPS;
range->min_addr.ip =
nla_get_in_addr(tb[TCA_CT_NAT_IPV4_MIN]);
range->max_addr.ip = max_attr ?
nla_get_in_addr(max_attr) :
range->min_addr.ip;
} else if (tb[TCA_CT_NAT_IPV6_MIN]) {
struct nlattr *max_attr = tb[TCA_CT_NAT_IPV6_MAX];
p->ipv4_range = false;
range->flags |= NF_NAT_RANGE_MAP_IPS;
range->min_addr.in6 =
nla_get_in6_addr(tb[TCA_CT_NAT_IPV6_MIN]);
range->max_addr.in6 = max_attr ?
nla_get_in6_addr(max_attr) :
range->min_addr.in6;
}
if (tb[TCA_CT_NAT_PORT_MIN]) {
range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
range->min_proto.all = nla_get_be16(tb[TCA_CT_NAT_PORT_MIN]);
range->max_proto.all = tb[TCA_CT_NAT_PORT_MAX] ?
nla_get_be16(tb[TCA_CT_NAT_PORT_MAX]) :
range->min_proto.all;
}
return 0;
}
static void tcf_ct_set_key_val(struct nlattr **tb,
void *val, int val_type,
void *mask, int mask_type,
int len)
{
if (!tb[val_type])
return;
nla_memcpy(val, tb[val_type], len);
if (!mask)
return;
if (mask_type == TCA_CT_UNSPEC || !tb[mask_type])
memset(mask, 0xff, len);
else
nla_memcpy(mask, tb[mask_type], len);
}
static int tcf_ct_fill_params(struct net *net,
struct tcf_ct_params *p,
struct tc_ct *parm,
struct nlattr **tb,
struct netlink_ext_ack *extack)
{
struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
struct nf_conntrack_zone zone;
int err, family, proto, len;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
struct nf_conn *tmpl;
char *name;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
p->zone = NF_CT_DEFAULT_ZONE_ID;
tcf_ct_set_key_val(tb,
&p->ct_action, TCA_CT_ACTION,
NULL, TCA_CT_UNSPEC,
sizeof(p->ct_action));
if (p->ct_action & TCA_CT_ACT_CLEAR)
return 0;
err = tcf_ct_fill_params_nat(p, parm, tb, extack);
if (err)
return err;
if (tb[TCA_CT_MARK]) {
if (!IS_ENABLED(CONFIG_NF_CONNTRACK_MARK)) {
NL_SET_ERR_MSG_MOD(extack, "Conntrack mark isn't enabled.");
return -EOPNOTSUPP;
}
tcf_ct_set_key_val(tb,
&p->mark, TCA_CT_MARK,
&p->mark_mask, TCA_CT_MARK_MASK,
sizeof(p->mark));
}
if (tb[TCA_CT_LABELS]) {
if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) {
NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled.");
return -EOPNOTSUPP;
}
if (!tn->labels) {
NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length");
return -EOPNOTSUPP;
}
tcf_ct_set_key_val(tb,
p->labels, TCA_CT_LABELS,
p->labels_mask, TCA_CT_LABELS_MASK,
sizeof(p->labels));
}
if (tb[TCA_CT_ZONE]) {
if (!IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES)) {
NL_SET_ERR_MSG_MOD(extack, "Conntrack zones isn't enabled.");
return -EOPNOTSUPP;
}
tcf_ct_set_key_val(tb,
&p->zone, TCA_CT_ZONE,
NULL, TCA_CT_UNSPEC,
sizeof(p->zone));
}
nf_ct_zone_init(&zone, p->zone, NF_CT_DEFAULT_ZONE_DIR, 0);
tmpl = nf_ct_tmpl_alloc(net, &zone, GFP_KERNEL);
if (!tmpl) {
NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template");
return -ENOMEM;
}
p->tmpl = tmpl;
if (tb[TCA_CT_HELPER_NAME]) {
name = nla_data(tb[TCA_CT_HELPER_NAME]);
len = nla_len(tb[TCA_CT_HELPER_NAME]);
if (len > 16 || name[len - 1] != '\0') {
NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name.");
err = -EINVAL;
goto err;
}
family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET;
proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP;
err = nf_ct_add_helper(tmpl, name, family, proto,
p->ct_action & TCA_CT_ACT_NAT, &p->helper);
if (err) {
NL_SET_ERR_MSG_MOD(extack, "Failed to add helper");
goto err;
}
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
return 0;
err:
nf_ct_put(p->tmpl);
p->tmpl = NULL;
return err;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
static int tcf_ct_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
struct tcf_proto *tp, u32 flags,
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, act_ct_ops.net_id);
bool bind = flags & TCA_ACT_FLAGS_BIND;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
struct tcf_ct_params *params = NULL;
struct nlattr *tb[TCA_CT_MAX + 1];
struct tcf_chain *goto_ch = NULL;
struct tc_ct *parm;
struct tcf_ct *c;
int err, res = 0;
u32 index;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (!nla) {
NL_SET_ERR_MSG_MOD(extack, "Ct requires attributes to be passed");
return -EINVAL;
}
err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack);
if (err < 0)
return err;
if (!tb[TCA_CT_PARMS]) {
NL_SET_ERR_MSG_MOD(extack, "Missing required ct parameters");
return -EINVAL;
}
parm = nla_data(tb[TCA_CT_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (err < 0)
return err;
if (!err) {
err = tcf_idr_create_from_flags(tn, index, est, a,
&act_ct_ops, bind, flags);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (err) {
tcf_idr_cleanup(tn, index);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
return err;
}
res = ACT_P_CREATED;
} else {
if (bind)
return 0;
if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
tcf_idr_release(*a, bind);
return -EEXIST;
}
}
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto cleanup;
c = to_ct(*a);
params = kzalloc(sizeof(*params), GFP_KERNEL);
if (unlikely(!params)) {
err = -ENOMEM;
goto cleanup;
}
err = tcf_ct_fill_params(net, params, parm, tb, extack);
if (err)
goto cleanup;
err = tcf_ct_flow_table_get(net, params);
if (err)
goto cleanup;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
spin_lock_bh(&c->tcf_lock);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
params = rcu_replace_pointer(c->params, params,
lockdep_is_held(&c->tcf_lock));
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
spin_unlock_bh(&c->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (params)
call_rcu(&params->rcu, tcf_ct_params_free_rcu);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
return res;
cleanup:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
if (params)
tcf_ct_params_free(params);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
tcf_idr_release(*a, bind);
return err;
}
static void tcf_ct_cleanup(struct tc_action *a)
{
struct tcf_ct_params *params;
struct tcf_ct *c = to_ct(a);
params = rcu_dereference_protected(c->params, 1);
if (params)
call_rcu(&params->rcu, tcf_ct_params_free_rcu);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
static int tcf_ct_dump_key_val(struct sk_buff *skb,
void *val, int val_type,
void *mask, int mask_type,
int len)
{
int err;
if (mask && !memchr_inv(mask, 0, len))
return 0;
err = nla_put(skb, val_type, len, val);
if (err)
return err;
if (mask_type != TCA_CT_UNSPEC) {
err = nla_put(skb, mask_type, len, mask);
if (err)
return err;
}
return 0;
}
static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p)
{
struct nf_nat_range2 *range = &p->range;
if (!(p->ct_action & TCA_CT_ACT_NAT))
return 0;
if (!(p->ct_action & (TCA_CT_ACT_NAT_SRC | TCA_CT_ACT_NAT_DST)))
return 0;
if (range->flags & NF_NAT_RANGE_MAP_IPS) {
if (p->ipv4_range) {
if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MIN,
range->min_addr.ip))
return -1;
if (nla_put_in_addr(skb, TCA_CT_NAT_IPV4_MAX,
range->max_addr.ip))
return -1;
} else {
if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MIN,
&range->min_addr.in6))
return -1;
if (nla_put_in6_addr(skb, TCA_CT_NAT_IPV6_MAX,
&range->max_addr.in6))
return -1;
}
}
if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) {
if (nla_put_be16(skb, TCA_CT_NAT_PORT_MIN,
range->min_proto.all))
return -1;
if (nla_put_be16(skb, TCA_CT_NAT_PORT_MAX,
range->max_proto.all))
return -1;
}
return 0;
}
static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper)
{
if (!helper)
return 0;
if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) ||
nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) ||
nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum))
return -1;
return 0;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_ct *c = to_ct(a);
struct tcf_ct_params *p;
struct tc_ct opt = {
.index = c->tcf_index,
.refcnt = refcount_read(&c->tcf_refcnt) - ref,
.bindcnt = atomic_read(&c->tcf_bindcnt) - bind,
};
struct tcf_t t;
spin_lock_bh(&c->tcf_lock);
p = rcu_dereference_protected(c->params,
lockdep_is_held(&c->tcf_lock));
opt.action = c->tcf_action;
if (tcf_ct_dump_key_val(skb,
&p->ct_action, TCA_CT_ACTION,
NULL, TCA_CT_UNSPEC,
sizeof(p->ct_action)))
goto nla_put_failure;
if (p->ct_action & TCA_CT_ACT_CLEAR)
goto skip_dump;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) &&
tcf_ct_dump_key_val(skb,
&p->mark, TCA_CT_MARK,
&p->mark_mask, TCA_CT_MARK_MASK,
sizeof(p->mark)))
goto nla_put_failure;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
tcf_ct_dump_key_val(skb,
p->labels, TCA_CT_LABELS,
p->labels_mask, TCA_CT_LABELS_MASK,
sizeof(p->labels)))
goto nla_put_failure;
if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) &&
tcf_ct_dump_key_val(skb,
&p->zone, TCA_CT_ZONE,
NULL, TCA_CT_UNSPEC,
sizeof(p->zone)))
goto nla_put_failure;
if (tcf_ct_dump_nat(skb, p))
goto nla_put_failure;
if (tcf_ct_dump_helper(skb, p->helper))
goto nla_put_failure;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
skip_dump:
if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &c->tcf_tm);
if (nla_put_64bit(skb, TCA_CT_TM, sizeof(t), &t, TCA_CT_PAD))
goto nla_put_failure;
spin_unlock_bh(&c->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&c->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static void tcf_stats_update(struct tc_action *a, u64 bytes, u64 packets,
u64 drops, u64 lastuse, bool hw)
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
{
struct tcf_ct *c = to_ct(a);
tcf_action_update_stats(a, bytes, packets, drops, hw);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
c->tcf_tm.lastuse = max_t(u64, c->tcf_tm.lastuse, lastuse);
}
static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data,
u32 *index_inc, bool bind,
struct netlink_ext_ack *extack)
{
if (bind) {
struct flow_action_entry *entry = entry_data;
entry->id = FLOW_ACTION_CT;
entry->ct.action = tcf_ct_action(act);
entry->ct.zone = tcf_ct_zone(act);
entry->ct.flow_table = tcf_ct_ft(act);
*index_inc = 1;
} else {
struct flow_offload_action *fl_action = entry_data;
fl_action->id = FLOW_ACTION_CT;
}
return 0;
}
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
static struct tc_action_ops act_ct_ops = {
.kind = "ct",
.id = TCA_ID_CT,
.owner = THIS_MODULE,
.act = tcf_ct_act,
.dump = tcf_ct_dump,
.init = tcf_ct_init,
.cleanup = tcf_ct_cleanup,
.stats_update = tcf_stats_update,
.offload_act_setup = tcf_ct_offload_act_setup,
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
.size = sizeof(struct tcf_ct),
};
static __net_init int ct_init_net(struct net *net)
{
unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8;
struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (nf_connlabels_get(net, n_bits - 1)) {
tn->labels = false;
pr_err("act_ct: Failed to set connlabels length");
} else {
tn->labels = true;
}
return tc_action_net_init(net, &tn->tn, &act_ct_ops);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
static void __net_exit ct_exit_net(struct list_head *net_list)
{
struct net *net;
rtnl_lock();
list_for_each_entry(net, net_list, exit_list) {
struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
if (tn->labels)
nf_connlabels_put(net);
}
rtnl_unlock();
tc_action_net_exit(net_list, act_ct_ops.net_id);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
static struct pernet_operations ct_net_ops = {
.init = ct_init_net,
.exit_batch = ct_exit_net,
.id = &act_ct_ops.net_id,
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
.size = sizeof(struct tc_ct_action_net),
};
static int __init ct_init_module(void)
{
int err;
act_ct_wq = alloc_ordered_workqueue("act_ct_workqueue", 0);
if (!act_ct_wq)
return -ENOMEM;
err = tcf_ct_flow_tables_init();
if (err)
goto err_tbl_init;
err = tcf_register_action(&act_ct_ops, &ct_net_ops);
if (err)
goto err_register;
static_branch_inc(&tcf_frag_xmit_count);
return 0;
err_register:
tcf_ct_flow_tables_uninit();
err_tbl_init:
destroy_workqueue(act_ct_wq);
return err;
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
static void __exit ct_cleanup_module(void)
{
static_branch_dec(&tcf_frag_xmit_count);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
tcf_unregister_action(&act_ct_ops, &ct_net_ops);
tcf_ct_flow_tables_uninit();
destroy_workqueue(act_ct_wq);
net/sched: Introduce action ct Allow sending a packet to conntrack module for connection tracking. The packet will be marked with conntrack connection's state, and any metadata such as conntrack mark and label. This state metadata can later be matched against with tc classifers, for example with the flower classifier as below. In addition to committing new connections the user can optionally specific a zone to track within, set a mark/label and configure nat with an address range and port range. Usage is as follows: $ tc qdisc add dev ens1f0_0 ingress $ tc qdisc add dev ens1f0_1 ingress $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 2 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_state +trk+new \ action ct zone 2 commit mark 0xbb nat src addr 5.5.5.7 pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_0 ingress \ prio 1 chain 2 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 0 proto ip \ flower ip_proto tcp ct_state -trk \ action ct zone 2 pipe \ action goto chain 1 $ tc filter add dev ens1f0_1 ingress \ prio 1 chain 1 proto ip \ flower ct_zone 2 ct_mark 0xbb ct_state +trk+est \ action ct nat pipe \ action mirred egress redirect dev ens1f0_0 Signed-off-by: Paul Blakey <paulb@mellanox.com> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: Yossi Kuperman <yossiku@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Changelog: V5->V6: Added CONFIG_NF_DEFRAG_IPV6 in handle fragments ipv6 case V4->V5: Reordered nf_conntrack_put() in tcf_ct_skb_nfct_cached() V3->V4: Added strict_start_type for act_ct policy V2->V3: Fixed david's comments: Removed extra newline after rcu in tcf_ct_params , and indent of break in act_ct.c V1->V2: Fixed parsing of ranges TCA_CT_NAT_IPV6_MAX as 'else' case overwritten ipv4 max Refactored NAT_PORT_MIN_MAX range handling as well Added ipv4/ipv6 defragmentation Removed extra skb pull push of nw offset in exectute nat Refactored tcf_ct_skb_network_trim after pull Removed TCA_ACT_CT define Signed-off-by: David S. Miller <davem@davemloft.net>
2019-07-09 10:30:48 +03:00
}
module_init(ct_init_module);
module_exit(ct_cleanup_module);
MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>");
MODULE_AUTHOR("Yossi Kuperman <yossiku@mellanox.com>");
MODULE_AUTHOR("Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>");
MODULE_DESCRIPTION("Connection tracking action");
MODULE_LICENSE("GPL v2");