1601 lines · 39.7 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* * Copyright (c) 2007-2017 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h>#include <linux/in.h>#include <linux/ip.h>#include <linux/openvswitch.h>#include <linux/sctp.h>#include <linux/tcp.h>#include <linux/udp.h>#include <linux/in6.h>#include <linux/if_arp.h>#include <linux/if_vlan.h> #include <net/dst.h>#include <net/gso.h>#include <net/ip.h>#include <net/ipv6.h>#include <net/ip6_fib.h>#include <net/ip6_route.h>#include <net/checksum.h>#include <net/dsfield.h>#include <net/mpls.h> #if IS_ENABLED(CONFIG_PSAMPLE)#include <net/psample.h>#endif #include <net/sctp/checksum.h> #include "datapath.h"#include "drop.h"#include "flow.h"#include "conntrack.h"#include "vport.h"#include "flow_netlink.h"#include "openvswitch_trace.h" struct ovs_pcpu_storage __percpu *ovs_pcpu_storage; /* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys' * space. Return NULL if out of key spaces. */static struct sw_flow_key *clone_key(const struct sw_flow_key *key_){	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);	struct action_flow_keys *keys = &ovs_pcpu->flow_keys;	int level = ovs_pcpu->exec_level;	struct sw_flow_key *key = NULL; 	if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {		key = &keys->key[level - 1];		*key = *key_;	} 	return key;} static void action_fifo_init(struct action_fifo *fifo){	fifo->head = 0;	fifo->tail = 0;} static bool action_fifo_is_empty(const struct action_fifo *fifo){	return (fifo->head == fifo->tail);} static struct deferred_action *action_fifo_get(struct action_fifo *fifo){	if (action_fifo_is_empty(fifo))		return NULL; 	return &fifo->fifo[fifo->tail++];} static struct deferred_action *action_fifo_put(struct action_fifo *fifo){	if (fifo->head >= DEFERRED_ACTION_FIFO_SIZE - 1)		return NULL; 	return &fifo->fifo[fifo->head++];} /* Return true if fifo is not full */static struct deferred_action *add_deferred_actions(struct sk_buff *skb,				    const struct sw_flow_key *key,				    const struct nlattr *actions,				    const int actions_len){	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);	struct deferred_action *da; 	da = action_fifo_put(fifo);	if (da) {		da->skb = skb;		da->actions = actions;		da->actions_len = actions_len;		da->pkt_key = *key;	} 	return da;} static void invalidate_flow_key(struct sw_flow_key *key){	key->mac_proto |= SW_FLOW_KEY_INVALID;} static bool is_flow_key_valid(const struct sw_flow_key *key){	return !(key->mac_proto & SW_FLOW_KEY_INVALID);} static int clone_execute(struct datapath *dp, struct sk_buff *skb,			 struct sw_flow_key *key,			 u32 recirc_id,			 const struct nlattr *actions, int len,			 bool last, bool clone_flow_key); static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,			      struct sw_flow_key *key,			      const struct nlattr *attr, int len); static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,		     __be32 mpls_lse, __be16 mpls_ethertype, __u16 mac_len){	int err; 	err = skb_mpls_push(skb, mpls_lse, mpls_ethertype, mac_len, !!mac_len);	if (err)		return err; 	if (!mac_len)		key->mac_proto = MAC_PROTO_NONE; 	invalidate_flow_key(key);	return 0;} static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,		    const __be16 ethertype){	int err; 	err = skb_mpls_pop(skb, ethertype, skb->mac_len,			   ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET);	if (err)		return err; 	if (ethertype == htons(ETH_P_TEB))		key->mac_proto = MAC_PROTO_ETHERNET; 	invalidate_flow_key(key);	return 0;} static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,		    const __be32 *mpls_lse, const __be32 *mask){	struct mpls_shim_hdr *stack;	__be32 lse;	int err; 	if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))		return -ENOMEM; 	stack = mpls_hdr(skb);	lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);	err = skb_mpls_update_lse(skb, lse);	if (err)		return err; 	flow_key->mpls.lse[0] = lse;	return 0;} static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key){	int err; 	err = skb_vlan_pop(skb);	if (skb_vlan_tag_present(skb)) {		invalidate_flow_key(key);	} else {		key->eth.vlan.tci = 0;		key->eth.vlan.tpid = 0;	}	return err;} static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,		     const struct ovs_action_push_vlan *vlan){	int err; 	if (skb_vlan_tag_present(skb)) {		invalidate_flow_key(key);	} else {		key->eth.vlan.tci = vlan->vlan_tci;		key->eth.vlan.tpid = vlan->vlan_tpid;	}	err = skb_vlan_push(skb, vlan->vlan_tpid,			    ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);	skb_reset_mac_len(skb);	return err;} /* 'src' is already properly masked. */static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_){	u16 *dst = (u16 *)dst_;	const u16 *src = (const u16 *)src_;	const u16 *mask = (const u16 *)mask_; 	OVS_SET_MASKED(dst[0], src[0], mask[0]);	OVS_SET_MASKED(dst[1], src[1], mask[1]);	OVS_SET_MASKED(dst[2], src[2], mask[2]);} static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,			const struct ovs_key_ethernet *key,			const struct ovs_key_ethernet *mask){	int err; 	err = skb_ensure_writable(skb, ETH_HLEN);	if (unlikely(err))		return err; 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); 	ether_addr_copy_masked(eth_hdr(skb)->h_source, key->eth_src,			       mask->eth_src);	ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,			       mask->eth_dst); 	skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2); 	ether_addr_copy(flow_key->eth.src, eth_hdr(skb)->h_source);	ether_addr_copy(flow_key->eth.dst, eth_hdr(skb)->h_dest);	return 0;} /* pop_eth does not support VLAN packets as this action is never called * for them. */static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key){	int err; 	err = skb_eth_pop(skb);	if (err)		return err; 	/* safe right before invalidate_flow_key */	key->mac_proto = MAC_PROTO_NONE;	invalidate_flow_key(key);	return 0;} static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,		    const struct ovs_action_push_eth *ethh){	int err; 	err = skb_eth_push(skb, ethh->addresses.eth_dst,			   ethh->addresses.eth_src);	if (err)		return err; 	/* safe right before invalidate_flow_key */	key->mac_proto = MAC_PROTO_ETHERNET;	invalidate_flow_key(key);	return 0;} static noinline_for_stack int push_nsh(struct sk_buff *skb,				       struct sw_flow_key *key,				       const struct nlattr *a){	u8 buffer[NSH_HDR_MAX_LEN];	struct nshhdr *nh = (struct nshhdr *)buffer;	int err; 	err = nsh_hdr_from_nlattr(a, nh, NSH_HDR_MAX_LEN);	if (err)		return err; 	err = nsh_push(skb, nh);	if (err)		return err; 	/* safe right before invalidate_flow_key */	key->mac_proto = MAC_PROTO_NONE;	invalidate_flow_key(key);	return 0;} static int pop_nsh(struct sk_buff *skb, struct sw_flow_key *key){	int err; 	err = nsh_pop(skb);	if (err)		return err; 	/* safe right before invalidate_flow_key */	if (skb->protocol == htons(ETH_P_TEB))		key->mac_proto = MAC_PROTO_ETHERNET;	else		key->mac_proto = MAC_PROTO_NONE;	invalidate_flow_key(key);	return 0;} static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,				  __be32 addr, __be32 new_addr){	int transport_len = skb->len - skb_transport_offset(skb); 	if (nh->frag_off & htons(IP_OFFSET))		return; 	if (nh->protocol == IPPROTO_TCP) {		if (likely(transport_len >= sizeof(struct tcphdr)))			inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,						 addr, new_addr, true);	} else if (nh->protocol == IPPROTO_UDP) {		if (likely(transport_len >= sizeof(struct udphdr))) {			struct udphdr *uh = udp_hdr(skb); 			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {				inet_proto_csum_replace4(&uh->check, skb,							 addr, new_addr, true);				if (!uh->check)					uh->check = CSUM_MANGLED_0;			}		}	}} static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,			__be32 *addr, __be32 new_addr){	update_ip_l4_checksum(skb, nh, *addr, new_addr);	csum_replace4(&nh->check, *addr, new_addr);	skb_clear_hash(skb);	ovs_ct_clear(skb, NULL);	*addr = new_addr;} static void update_ipv6_checksum(struct sk_buff *skb, u8 l4_proto,				 __be32 addr[4], const __be32 new_addr[4]){	int transport_len = skb->len - skb_transport_offset(skb); 	if (l4_proto == NEXTHDR_TCP) {		if (likely(transport_len >= sizeof(struct tcphdr)))			inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,						  addr, new_addr, true);	} else if (l4_proto == NEXTHDR_UDP) {		if (likely(transport_len >= sizeof(struct udphdr))) {			struct udphdr *uh = udp_hdr(skb); 			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {				inet_proto_csum_replace16(&uh->check, skb,							  addr, new_addr, true);				if (!uh->check)					uh->check = CSUM_MANGLED_0;			}		}	} else if (l4_proto == NEXTHDR_ICMP) {		if (likely(transport_len >= sizeof(struct icmp6hdr)))			inet_proto_csum_replace16(&icmp6_hdr(skb)->icmp6_cksum,						  skb, addr, new_addr, true);	}} static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],			   const __be32 mask[4], __be32 masked[4]){	masked[0] = OVS_MASKED(old[0], addr[0], mask[0]);	masked[1] = OVS_MASKED(old[1], addr[1], mask[1]);	masked[2] = OVS_MASKED(old[2], addr[2], mask[2]);	masked[3] = OVS_MASKED(old[3], addr[3], mask[3]);} static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,			  __be32 addr[4], const __be32 new_addr[4],			  bool recalculate_csum){	if (recalculate_csum)		update_ipv6_checksum(skb, l4_proto, addr, new_addr); 	skb_clear_hash(skb);	ovs_ct_clear(skb, NULL);	memcpy(addr, new_addr, sizeof(__be32[4]));} static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask){	u8 old_ipv6_tclass = ipv6_get_dsfield(nh); 	ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask); 	if (skb->ip_summed == CHECKSUM_COMPLETE)		csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12),			     (__force __wsum)(ipv6_tclass << 12)); 	ipv6_change_dsfield(nh, ~mask, ipv6_tclass);} static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask){	u32 ofl; 	ofl = nh->flow_lbl[0] << 16 |  nh->flow_lbl[1] << 8 |  nh->flow_lbl[2];	fl = OVS_MASKED(ofl, fl, mask); 	/* Bits 21-24 are always unmasked, so this retains their values. */	nh->flow_lbl[0] = (u8)(fl >> 16);	nh->flow_lbl[1] = (u8)(fl >> 8);	nh->flow_lbl[2] = (u8)fl; 	if (skb->ip_summed == CHECKSUM_COMPLETE)		csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl));} static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask){	new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask); 	if (skb->ip_summed == CHECKSUM_COMPLETE)		csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8),			     (__force __wsum)(new_ttl << 8));	nh->hop_limit = new_ttl;} static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,		       u8 mask){	new_ttl = OVS_MASKED(nh->ttl, new_ttl, mask); 	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));	nh->ttl = new_ttl;} static int set_ipv4(struct sk_buff *skb, struct sw_flow_key *flow_key,		    const struct ovs_key_ipv4 *key,		    const struct ovs_key_ipv4 *mask){	struct iphdr *nh;	__be32 new_addr;	int err; 	err = skb_ensure_writable(skb, skb_network_offset(skb) +				  sizeof(struct iphdr));	if (unlikely(err))		return err; 	nh = ip_hdr(skb); 	/* Setting an IP addresses is typically only a side effect of	 * matching on them in the current userspace implementation, so it	 * makes sense to check if the value actually changed.	 */	if (mask->ipv4_src) {		new_addr = OVS_MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src); 		if (unlikely(new_addr != nh->saddr)) {			set_ip_addr(skb, nh, &nh->saddr, new_addr);			flow_key->ipv4.addr.src = new_addr;		}	}	if (mask->ipv4_dst) {		new_addr = OVS_MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst); 		if (unlikely(new_addr != nh->daddr)) {			set_ip_addr(skb, nh, &nh->daddr, new_addr);			flow_key->ipv4.addr.dst = new_addr;		}	}	if (mask->ipv4_tos) {		ipv4_change_dsfield(nh, ~mask->ipv4_tos, key->ipv4_tos);		flow_key->ip.tos = nh->tos;	}	if (mask->ipv4_ttl) {		set_ip_ttl(skb, nh, key->ipv4_ttl, mask->ipv4_ttl);		flow_key->ip.ttl = nh->ttl;	} 	return 0;} 

Lines 1–500 of 1601.