linux/net/sched/act_skbedit.c

473 lines
13 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2008, Intel Corporation.
*
* Author: Alexander Duyck <alexander.h.duyck@intel.com>
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/dsfield.h>
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
#include <net/pkt_cls.h>
#include <linux/tc_act/tc_skbedit.h>
#include <net/tc_act/tc_skbedit.h>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
static unsigned int skbedit_net_id;
static struct tc_action_ops act_skbedit_ops;
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params,
struct sk_buff *skb)
{
u16 queue_mapping = params->queue_mapping;
if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
u32 hash = skb_get_hash(skb);
queue_mapping += hash % params->mapping_mod;
}
return netdev_cap_txqueue(skb->dev, queue_mapping);
}
static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_skbedit_params *params;
int action;
tcf_lastuse_update(&d->tcf_tm);
bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb);
params = rcu_dereference_bh(d->params);
action = READ_ONCE(d->tcf_action);
if (params->flags & SKBEDIT_F_PRIORITY)
skb->priority = params->priority;
if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
int wlen = skb_network_offset(skb);
sched: consistently handle layer3 header accesses in the presence of VLANs There are a couple of places in net/sched/ that check skb->protocol and act on the value there. However, in the presence of VLAN tags, the value stored in skb->protocol can be inconsistent based on whether VLAN acceleration is enabled. The commit quoted in the Fixes tag below fixed the users of skb->protocol to use a helper that will always see the VLAN ethertype. However, most of the callers don't actually handle the VLAN ethertype, but expect to find the IP header type in the protocol field. This means that things like changing the ECN field, or parsing diffserv values, stops working if there's a VLAN tag, or if there are multiple nested VLAN tags (QinQ). To fix this, change the helper to take an argument that indicates whether the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we make sure to skip all of them, so behaviour is consistent even in QinQ mode. To make the helper usable from the ECN code, move it to if_vlan.h instead of pkt_sched.h. v3: - Remove empty lines - Move vlan variable definitions inside loop in skb_protocol() - Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and bpf_skb_ecn_set_ce() v2: - Use eth_type_vlan() helper in skb_protocol() - Also fix code that reads skb->protocol directly - Change a couple of 'if/else if' statements to switch constructs to avoid calling the helper twice Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com> Fixes: d8b9605d2697 ("net: sched: fix skb->protocol use in case of accelerated vlan path") Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-04 04:26:43 +08:00
switch (skb_protocol(skb, true)) {
case htons(ETH_P_IP):
wlen += sizeof(struct iphdr);
if (!pskb_may_pull(skb, wlen))
goto err;
skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
break;
case htons(ETH_P_IPV6):
wlen += sizeof(struct ipv6hdr);
if (!pskb_may_pull(skb, wlen))
goto err;
skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
break;
}
}
if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
net: sched: use queue_mapping to pick tx queue This patch fixes issue: * If we install tc filters with act_skbedit in clsact hook. It doesn't work, because netdev_core_pick_tx() overwrites queue_mapping. $ tc filter ... action skbedit queue_mapping 1 And this patch is useful: * We can use FQ + EDT to implement efficient policies. Tx queues are picked by xps, ndo_select_queue of netdev driver, or skb hash in netdev_core_pick_tx(). In fact, the netdev driver, and skb hash are _not_ under control. xps uses the CPUs map to select Tx queues, but we can't figure out which task_struct of pod/containter running on this cpu in most case. We can use clsact filters to classify one pod/container traffic to one Tx queue. Why ? In containter networking environment, there are two kinds of pod/ containter/net-namespace. One kind (e.g. P1, P2), the high throughput is key in these applications. But avoid running out of network resource, the outbound traffic of these pods is limited, using or sharing one dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods (e.g. Pn), the low latency of data access is key. And the traffic is not limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc. This choice provides two benefits. First, contention on the HTB/FQ Qdisc lock is significantly reduced since fewer CPUs contend for the same queue. More importantly, Qdisc contention can be eliminated completely if each CPU has its own FIFO Qdisc for the second kind of pods. There must be a mechanism in place to support classifying traffic based on pods/container to different Tx queues. Note that clsact is outside of Qdisc while Qdisc can run a classifier to select a sub-queue under the lock. In general recording the decision in the skb seems a little heavy handed. This patch introduces a per-CPU variable, suggested by Eric. The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit(). - Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag is set in qdisc->enqueue() though tx queue has been selected in netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared firstly in __dev_queue_xmit(), is useful: - Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy: For example, eth0, macvlan in pod, which root Qdisc install skbedit queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping because there is no filters in clsact or tx Qdisc of this netdev. Same action taked in eth0, ixgbe in Host. - Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it in __dev_queue_xmit when processing next packets. For performance reasons, use the static key. If user does not config the NET_EGRESS, the patch will not be compiled. +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | q1 | qn v v v HTB/FQ HTB/FQ ... FIFO Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:45 +08:00
skb->dev->real_num_tx_queues > params->queue_mapping) {
#ifdef CONFIG_NET_EGRESS
netdev_xmit_skip_txqueue(true);
#endif
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb));
net: sched: use queue_mapping to pick tx queue This patch fixes issue: * If we install tc filters with act_skbedit in clsact hook. It doesn't work, because netdev_core_pick_tx() overwrites queue_mapping. $ tc filter ... action skbedit queue_mapping 1 And this patch is useful: * We can use FQ + EDT to implement efficient policies. Tx queues are picked by xps, ndo_select_queue of netdev driver, or skb hash in netdev_core_pick_tx(). In fact, the netdev driver, and skb hash are _not_ under control. xps uses the CPUs map to select Tx queues, but we can't figure out which task_struct of pod/containter running on this cpu in most case. We can use clsact filters to classify one pod/container traffic to one Tx queue. Why ? In containter networking environment, there are two kinds of pod/ containter/net-namespace. One kind (e.g. P1, P2), the high throughput is key in these applications. But avoid running out of network resource, the outbound traffic of these pods is limited, using or sharing one dedicated Tx queues assigned HTB/TBF/FQ Qdisc. Other kind of pods (e.g. Pn), the low latency of data access is key. And the traffic is not limited. Pods use or share other dedicated Tx queues assigned FIFO Qdisc. This choice provides two benefits. First, contention on the HTB/FQ Qdisc lock is significantly reduced since fewer CPUs contend for the same queue. More importantly, Qdisc contention can be eliminated completely if each CPU has its own FIFO Qdisc for the second kind of pods. There must be a mechanism in place to support classifying traffic based on pods/container to different Tx queues. Note that clsact is outside of Qdisc while Qdisc can run a classifier to select a sub-queue under the lock. In general recording the decision in the skb seems a little heavy handed. This patch introduces a per-CPU variable, suggested by Eric. The xmit.skip_txqueue flag is firstly cleared in __dev_queue_xmit(). - Tx Qdisc may install that skbedit actions, then xmit.skip_txqueue flag is set in qdisc->enqueue() though tx queue has been selected in netdev_tx_queue_mapping() or netdev_core_pick_tx(). That flag is cleared firstly in __dev_queue_xmit(), is useful: - Avoid picking Tx queue with netdev_tx_queue_mapping() in next netdev in such case: eth0 macvlan - eth0.3 vlan - eth0 ixgbe-phy: For example, eth0, macvlan in pod, which root Qdisc install skbedit queue_mapping, send packets to eth0.3, vlan in host. In __dev_queue_xmit() of eth0.3, clear the flag, does not select tx queue according to skb->queue_mapping because there is no filters in clsact or tx Qdisc of this netdev. Same action taked in eth0, ixgbe in Host. - Avoid picking Tx queue for next packet. If we set xmit.skip_txqueue in tx Qdisc (qdisc->enqueue()), the proper way to clear it is clearing it in __dev_queue_xmit when processing next packets. For performance reasons, use the static key. If user does not config the NET_EGRESS, the patch will not be compiled. +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | q1 | qn v v v HTB/FQ HTB/FQ ... FIFO Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:45 +08:00
}
if (params->flags & SKBEDIT_F_MARK) {
skb->mark &= ~params->mask;
skb->mark |= params->mark & params->mask;
}
if (params->flags & SKBEDIT_F_PTYPE)
skb->pkt_type = params->ptype;
return action;
err:
qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
return TC_ACT_SHOT;
}
static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes,
u64 packets, u64 drops,
u64 lastuse, bool hw)
{
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_t *tm = &d->tcf_tm;
tcf_action_update_stats(a, bytes, packets, drops, hw);
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
[TCA_SKBEDIT_PARMS] = { .len = sizeof(struct tc_skbedit) },
[TCA_SKBEDIT_PRIORITY] = { .len = sizeof(u32) },
[TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) },
[TCA_SKBEDIT_MARK] = { .len = sizeof(u32) },
[TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) },
[TCA_SKBEDIT_MASK] = { .len = sizeof(u32) },
[TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) },
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
[TCA_SKBEDIT_QUEUE_MAPPING_MAX] = { .len = sizeof(u16) },
};
static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
struct tcf_proto *tp, u32 act_flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
bool bind = act_flags & TCA_ACT_FLAGS_BIND;
struct tcf_skbedit_params *params_new;
struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
struct tcf_chain *goto_ch = NULL;
struct tc_skbedit *parm;
struct tcf_skbedit *d;
u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
u16 *queue_mapping = NULL, *ptype = NULL;
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
u16 mapping_mod = 1;
bool exists = false;
int ret = 0, err;
u32 index;
if (nla == NULL)
return -EINVAL;
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 20:07:28 +08:00
err = nla_parse_nested_deprecated(tb, TCA_SKBEDIT_MAX, nla,
skbedit_policy, NULL);
if (err < 0)
return err;
if (tb[TCA_SKBEDIT_PARMS] == NULL)
return -EINVAL;
if (tb[TCA_SKBEDIT_PRIORITY] != NULL) {
flags |= SKBEDIT_F_PRIORITY;
priority = nla_data(tb[TCA_SKBEDIT_PRIORITY]);
}
if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) {
flags |= SKBEDIT_F_QUEUE_MAPPING;
queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]);
}
if (tb[TCA_SKBEDIT_PTYPE] != NULL) {
ptype = nla_data(tb[TCA_SKBEDIT_PTYPE]);
if (!skb_pkt_type_ok(*ptype))
return -EINVAL;
flags |= SKBEDIT_F_PTYPE;
}
if (tb[TCA_SKBEDIT_MARK] != NULL) {
flags |= SKBEDIT_F_MARK;
mark = nla_data(tb[TCA_SKBEDIT_MARK]);
}
if (tb[TCA_SKBEDIT_MASK] != NULL) {
flags |= SKBEDIT_F_MASK;
mask = nla_data(tb[TCA_SKBEDIT_MASK]);
}
if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) {
u16 *queue_mapping_max;
if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] ||
!tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) {
NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping.");
return -EINVAL;
}
queue_mapping_max =
nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]);
if (*queue_mapping_max < *queue_mapping) {
NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min.");
return -EINVAL;
}
mapping_mod = *queue_mapping_max - *queue_mapping + 1;
flags |= SKBEDIT_F_TXQ_SKBHASH;
}
if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
flags |= SKBEDIT_F_INHERITDSFIELD;
}
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
exists = err;
if (exists && bind)
return 0;
if (!flags) {
net sched actions: fix invalid pointer dereferencing if skbedit flags missing When application fails to pass flags in netlink TLV for a new skbedit action, the kernel results in the following oops: [ 8.307732] BUG: unable to handle kernel paging request at 0000000000021130 [ 8.309167] PGD 80000000193d1067 P4D 80000000193d1067 PUD 180e0067 PMD 0 [ 8.310595] Oops: 0000 [#1] SMP PTI [ 8.311334] Modules linked in: kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel aes_x86_64 crypto_simd cryptd glue_helper serio_raw [ 8.314190] CPU: 1 PID: 397 Comm: tc Not tainted 4.17.0-rc3+ #357 [ 8.315252] RIP: 0010:__tcf_idr_release+0x33/0x140 [ 8.316203] RSP: 0018:ffffa0718038f840 EFLAGS: 00010246 [ 8.317123] RAX: 0000000000000001 RBX: 0000000000021100 RCX: 0000000000000000 [ 8.319831] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000021100 [ 8.321181] RBP: 0000000000000000 R08: 000000000004adf8 R09: 0000000000000122 [ 8.322645] R10: 0000000000000000 R11: ffffffff9e5b01ed R12: 0000000000000000 [ 8.324157] R13: ffffffff9e0d3cc0 R14: 0000000000000000 R15: 0000000000000000 [ 8.325590] FS: 00007f591292e700(0000) GS:ffff8fcf5bc40000(0000) knlGS:0000000000000000 [ 8.327001] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8.327987] CR2: 0000000000021130 CR3: 00000000180e6004 CR4: 00000000001606a0 [ 8.329289] Call Trace: [ 8.329735] tcf_skbedit_init+0xa7/0xb0 [ 8.330423] tcf_action_init_1+0x362/0x410 [ 8.331139] ? try_to_wake_up+0x44/0x430 [ 8.331817] tcf_action_init+0x103/0x190 [ 8.332511] tc_ctl_action+0x11a/0x220 [ 8.333174] rtnetlink_rcv_msg+0x23d/0x2e0 [ 8.333902] ? _cond_resched+0x16/0x40 [ 8.334569] ? __kmalloc_node_track_caller+0x5b/0x2c0 [ 8.335440] ? rtnl_calcit.isra.31+0xf0/0xf0 [ 8.336178] netlink_rcv_skb+0xdb/0x110 [ 8.336855] netlink_unicast+0x167/0x220 [ 8.337550] netlink_sendmsg+0x2a7/0x390 [ 8.338258] sock_sendmsg+0x30/0x40 [ 8.338865] ___sys_sendmsg+0x2c5/0x2e0 [ 8.339531] ? pagecache_get_page+0x27/0x210 [ 8.340271] ? filemap_fault+0xa2/0x630 [ 8.340943] ? page_add_file_rmap+0x108/0x200 [ 8.341732] ? alloc_set_pte+0x2aa/0x530 [ 8.342573] ? finish_fault+0x4e/0x70 [ 8.343332] ? __handle_mm_fault+0xbc1/0x10d0 [ 8.344337] ? __sys_sendmsg+0x53/0x80 [ 8.345040] __sys_sendmsg+0x53/0x80 [ 8.345678] do_syscall_64+0x4f/0x100 [ 8.346339] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 8.347206] RIP: 0033:0x7f591191da67 [ 8.347831] RSP: 002b:00007fff745abd48 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 8.349179] RAX: ffffffffffffffda RBX: 00007fff745abe70 RCX: 00007f591191da67 [ 8.350431] RDX: 0000000000000000 RSI: 00007fff745abdc0 RDI: 0000000000000003 [ 8.351659] RBP: 000000005af35251 R08: 0000000000000001 R09: 0000000000000000 [ 8.352922] R10: 00000000000005f1 R11: 0000000000000246 R12: 0000000000000000 [ 8.354183] R13: 00007fff745afed0 R14: 0000000000000001 R15: 00000000006767c0 [ 8.355400] Code: 41 89 d4 53 89 f5 48 89 fb e8 aa 20 fd ff 85 c0 0f 84 ed 00 00 00 48 85 db 0f 84 cf 00 00 00 40 84 ed 0f 85 cd 00 00 00 45 84 e4 <8b> 53 30 74 0d 85 d2 b8 ff ff ff ff 0f 8f b3 00 00 00 8b 43 2c [ 8.358699] RIP: __tcf_idr_release+0x33/0x140 RSP: ffffa0718038f840 [ 8.359770] CR2: 0000000000021130 [ 8.360438] ---[ end trace 60c66be45dfc14f0 ]--- The caller calls action's ->init() and passes pointer to "struct tc_action *a", which later may be initialized to point at the existing action, otherwise "struct tc_action *a" is still invalid, and therefore dereferencing it is an error as happens in tcf_idr_release, where refcnt is decremented. So in case of missing flags tcf_idr_release must be called only for existing actions. v2: - prepare patch for net tree Fixes: 5e1567aeb7fe ("net sched: skbedit action fix late binding") Signed-off-by: Roman Mashak <mrv@mojatatu.com> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-11 22:55:09 +08:00
if (exists)
tcf_idr_release(*a, bind);
else
tcf_idr_cleanup(tn, index);
return -EINVAL;
}
if (!exists) {
ret = tcf_idr_create(tn, index, est, a,
&act_skbedit_ops, bind, true, act_flags);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
d = to_skbedit(*a);
ret = ACT_P_CREATED;
} else {
d = to_skbedit(*a);
if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
}
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
if (unlikely(!params_new)) {
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
err = -ENOMEM;
goto put_chain;
}
params_new->flags = flags;
if (flags & SKBEDIT_F_PRIORITY)
params_new->priority = *priority;
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
if (flags & SKBEDIT_F_QUEUE_MAPPING) {
params_new->queue_mapping = *queue_mapping;
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
params_new->mapping_mod = mapping_mod;
}
if (flags & SKBEDIT_F_MARK)
params_new->mark = *mark;
if (flags & SKBEDIT_F_PTYPE)
params_new->ptype = *ptype;
/* default behaviour is to use all the bits */
params_new->mask = 0xffffffff;
if (flags & SKBEDIT_F_MASK)
params_new->mask = *mask;
spin_lock_bh(&d->tcf_lock);
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
params_new = rcu_replace_pointer(d->params, params_new,
lockdep_is_held(&d->tcf_lock));
spin_unlock_bh(&d->tcf_lock);
if (params_new)
kfree_rcu(params_new, rcu);
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
return ret;
net/sched: act_skbedit: validate the control action inside init() the following script: # tc qdisc add dev crash0 clsact # tc filter add dev crash0 egress matchall \ > action skbedit ptype host pass index 90 # tc actions replace action skbedit \ > ptype host goto chain 42 index 90 cookie c1a0c1a0 # tc actions show action skbedit had the following output: Error: Failed to init TC action chain. We have an error talking to the kernel total acts 1 action order 0: skbedit ptype host goto chain 42 index 90 ref 2 bind 1 cookie c1a0c1a0 Then, the first packet transmitted by crash0 made the kernel crash: BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 3 PID: 3467 Comm: kworker/3:3 Not tainted 5.0.0-rc4.gotochain_crash+ #536 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Workqueue: ipv6_addrconf addrconf_dad_work RIP: 0010:tcf_action_exec+0xb8/0x100 Code: 00 00 00 20 74 1d 83 f8 03 75 09 49 83 c4 08 4d 39 ec 75 bc 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 49 8b 97 a8 00 00 00 <48> 8b 12 48 89 55 00 48 83 c4 10 5b 5d 41 5c 41 5d 41 5e 41 5f c3 RSP: 0018:ffffb50a81e1fad0 EFLAGS: 00010246 RAX: 000000002000002a RBX: ffff9aa47ba4ea00 RCX: 0000000000000001 RDX: 0000000000000000 RSI: ffff9aa469eeb3c0 RDI: ffff9aa47ba4ea00 RBP: ffffb50a81e1fb70 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: ffff9aa47bce0638 R12: ffff9aa4793b0c00 R13: ffff9aa4793b0c08 R14: 0000000000000001 R15: ffff9aa469eeb3c0 FS: 0000000000000000(0000) GS:ffff9aa474780000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000007360e005 CR4: 00000000001606e0 Call Trace: tcf_classify+0x58/0x120 __dev_queue_xmit+0x40a/0x890 ? ndisc_next_option+0x50/0x50 ? ___neigh_create+0x4d5/0x680 ? ip6_finish_output2+0x1b5/0x590 ip6_finish_output2+0x1b5/0x590 ? ip6_output+0x68/0x110 ip6_output+0x68/0x110 ? nf_hook.constprop.28+0x79/0xc0 ndisc_send_skb+0x248/0x2e0 ndisc_send_ns+0xf8/0x200 ? addrconf_dad_work+0x389/0x4b0 addrconf_dad_work+0x389/0x4b0 ? __switch_to_asm+0x34/0x70 ? process_one_work+0x195/0x380 ? addrconf_dad_completed+0x370/0x370 process_one_work+0x195/0x380 worker_thread+0x30/0x390 ? process_one_work+0x380/0x380 kthread+0x113/0x130 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: act_skbedit veth ip6table_filter ip6_tables iptable_filter binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ext4 snd_hda_codec_generic snd_hda_intel snd_hda_codec snd_hwdep mbcache snd_hda_core jbd2 snd_seq snd_seq_device snd_pcm aesni_intel crypto_simd cryptd snd_timer glue_helper snd joydev soundcore pcspkr virtio_balloon i2c_piix4 nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs ata_generic pata_acpi qxl drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm virtio_net net_failover drm failover virtio_blk virtio_console ata_piix virtio_pci crc32c_intel serio_raw libata virtio_ring virtio floppy dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000000 Validating the control action within tcf_skbedit_init() proved to fix the above issue. A TDC selftest is added to verify the correct behavior. Fixes: db50514f9a9c ("net: sched: add termination action to allow goto chain") Fixes: 97763dc0f401 ("net_sched: reject unknown tcfa_action values") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-20 22:00:11 +08:00
put_chain:
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
release_idr:
tcf_idr_release(*a, bind);
return err;
}
static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_skbedit_params *params;
struct tc_skbedit opt = {
.index = d->tcf_index,
.refcnt = refcount_read(&d->tcf_refcnt) - ref,
.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
};
u64 pure_flags = 0;
struct tcf_t t;
spin_lock_bh(&d->tcf_lock);
params = rcu_dereference_protected(d->params,
lockdep_is_held(&d->tcf_lock));
opt.action = d->tcf_action;
if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_PRIORITY) &&
nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) &&
nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_MARK) &&
nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_PTYPE) &&
nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype))
goto nla_put_failure;
if ((params->flags & SKBEDIT_F_MASK) &&
nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask))
goto nla_put_failure;
if (params->flags & SKBEDIT_F_INHERITDSFIELD)
pure_flags |= SKBEDIT_F_INHERITDSFIELD;
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
if (params->flags & SKBEDIT_F_TXQ_SKBHASH) {
if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX,
params->queue_mapping + params->mapping_mod - 1))
goto nla_put_failure;
pure_flags |= SKBEDIT_F_TXQ_SKBHASH;
}
if (pure_flags != 0 &&
nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
goto nla_put_failure;
tcf_tm_dump(&t, &d->tcf_tm);
if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
goto nla_put_failure;
spin_unlock_bh(&d->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&d->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static void tcf_skbedit_cleanup(struct tc_action *a)
{
struct tcf_skbedit *d = to_skbedit(a);
struct tcf_skbedit_params *params;
params = rcu_dereference_protected(d->params, 1);
if (params)
kfree_rcu(params, rcu);
}
static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
return tcf_idr_search(tn, a, index);
}
static size_t tcf_skbedit_get_fill_size(const struct tc_action *act)
{
return nla_total_size(sizeof(struct tc_skbedit))
+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */
+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */
net: sched: support hash selecting tx queue This patch allows users to pick queue_mapping, range from A to B. Then we can load balance packets from A to B tx queue. The range is an unsigned 16bit value in decimal format. $ tc filter ... action skbedit queue_mapping skbhash A B "skbedit queue_mapping QUEUE_MAPPING" (from "man 8 tc-skbedit") is enhanced with flags: SKBEDIT_F_TXQ_SKBHASH +----+ +----+ +----+ | P1 | | P2 | | Pn | +----+ +----+ +----+ | | | +-----------+-----------+ | | clsact/skbedit | MQ v +-----------+-----------+ | q0 | qn | qm v v v HTB/FQ FIFO ... FIFO For example: If P1 sends out packets to different Pods on other host, and we want distribute flows from qn - qm. Then we can use skb->hash as hash. setup commands: $ NETDEV=eth0 $ ip netns add n1 $ ip link add ipv1 link $NETDEV type ipvlan mode l2 $ ip link set ipv1 netns n1 $ ip netns exec n1 ifconfig ipv1 2.2.2.100/24 up $ tc qdisc add dev $NETDEV clsact $ tc filter add dev $NETDEV egress protocol ip prio 1 \ flower skip_hw src_ip 2.2.2.100 action skbedit queue_mapping skbhash 2 6 $ tc qdisc add dev $NETDEV handle 1: root mq $ tc qdisc add dev $NETDEV parent 1:1 handle 2: htb $ tc class add dev $NETDEV parent 2: classid 2:1 htb rate 100kbit $ tc class add dev $NETDEV parent 2: classid 2:2 htb rate 200kbit $ tc qdisc add dev $NETDEV parent 1:2 tbf rate 100mbit burst 100mb latency 1 $ tc qdisc add dev $NETDEV parent 1:3 pfifo $ tc qdisc add dev $NETDEV parent 1:4 pfifo $ tc qdisc add dev $NETDEV parent 1:5 pfifo $ tc qdisc add dev $NETDEV parent 1:6 pfifo $ tc qdisc add dev $NETDEV parent 1:7 pfifo $ ip netns exec n1 iperf3 -c 2.2.2.1 -i 1 -t 10 -P 10 pick txqueue from 2 - 6: $ ethtool -S $NETDEV | grep -i tx_queue_[0-9]_bytes tx_queue_0_bytes: 42 tx_queue_1_bytes: 0 tx_queue_2_bytes: 11442586444 tx_queue_3_bytes: 7383615334 tx_queue_4_bytes: 3981365579 tx_queue_5_bytes: 3983235051 tx_queue_6_bytes: 6706236461 tx_queue_7_bytes: 42 tx_queue_8_bytes: 0 tx_queue_9_bytes: 0 txqueues 2 - 6 are mapped to classid 1:3 - 1:7 $ tc -s class show dev $NETDEV ... class mq 1:3 root leaf 8002: Sent 11949133672 bytes 7929798 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:4 root leaf 8003: Sent 7710449050 bytes 5117279 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:5 root leaf 8004: Sent 4157648675 bytes 2758990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:6 root leaf 8005: Sent 4159632195 bytes 2759990 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 class mq 1:7 root leaf 8006: Sent 7003169603 bytes 4646912 pkt (dropped 0, overlimits 0 requeues 0) backlog 0b 0p requeues 0 ... Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jakub Kicinski <kuba@kernel.org> Cc: Jonathan Lemon <jonathan.lemon@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Alexander Lobakin <alobakin@pm.me> Cc: Paolo Abeni <pabeni@redhat.com> Cc: Talal Ahmad <talalahmad@google.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Ilias Apalodimas <ilias.apalodimas@linaro.org> Cc: Kees Cook <keescook@chromium.org> Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com> Cc: Antoine Tenart <atenart@kernel.org> Cc: Wei Wang <weiwan@google.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Tonghao Zhang <xiangxia.m.yue@gmail.com> Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-04-16 00:40:46 +08:00
+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */
+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */
+ nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */
+ nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */
+ nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */
}
static int tcf_skbedit_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;
if (is_tcf_skbedit_mark(act)) {
entry->id = FLOW_ACTION_MARK;
entry->mark = tcf_skbedit_mark(act);
} else if (is_tcf_skbedit_ptype(act)) {
entry->id = FLOW_ACTION_PTYPE;
entry->ptype = tcf_skbedit_ptype(act);
} else if (is_tcf_skbedit_priority(act)) {
entry->id = FLOW_ACTION_PRIORITY;
entry->priority = tcf_skbedit_priority(act);
} else if (is_tcf_skbedit_queue_mapping(act)) {
NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used");
return -EOPNOTSUPP;
} else if (is_tcf_skbedit_inheritdsfield(act)) {
NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used");
return -EOPNOTSUPP;
} else {
NL_SET_ERR_MSG_MOD(extack, "Unsupported skbedit option offload");
return -EOPNOTSUPP;
}
*index_inc = 1;
} else {
struct flow_offload_action *fl_action = entry_data;
if (is_tcf_skbedit_mark(act))
fl_action->id = FLOW_ACTION_MARK;
else if (is_tcf_skbedit_ptype(act))
fl_action->id = FLOW_ACTION_PTYPE;
else if (is_tcf_skbedit_priority(act))
fl_action->id = FLOW_ACTION_PRIORITY;
else
return -EOPNOTSUPP;
}
return 0;
}
static struct tc_action_ops act_skbedit_ops = {
.kind = "skbedit",
.id = TCA_ID_SKBEDIT,
.owner = THIS_MODULE,
.act = tcf_skbedit_act,
.stats_update = tcf_skbedit_stats_update,
.dump = tcf_skbedit_dump,
.init = tcf_skbedit_init,
.cleanup = tcf_skbedit_cleanup,
.walk = tcf_skbedit_walker,
.get_fill_size = tcf_skbedit_get_fill_size,
.lookup = tcf_skbedit_search,
.offload_act_setup = tcf_skbedit_offload_act_setup,
.size = sizeof(struct tcf_skbedit),
};
static __net_init int skbedit_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, skbedit_net_id);
return tc_action_net_init(net, tn, &act_skbedit_ops);
}
static void __net_exit skbedit_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, skbedit_net_id);
}
static struct pernet_operations skbedit_net_ops = {
.init = skbedit_init_net,
.exit_batch = skbedit_exit_net,
.id = &skbedit_net_id,
.size = sizeof(struct tc_action_net),
};
MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>");
MODULE_DESCRIPTION("SKB Editing");
MODULE_LICENSE("GPL");
static int __init skbedit_init_module(void)
{
return tcf_register_action(&act_skbedit_ops, &skbedit_net_ops);
}
static void __exit skbedit_cleanup_module(void)
{
tcf_unregister_action(&act_skbedit_ops, &skbedit_net_ops);
}
module_init(skbedit_init_module);
module_exit(skbedit_cleanup_module);