cregit-Linux how code gets into the kernel

Release 4.8 net/openvswitch/flow.c

Directory: net/openvswitch
/*
 * Copyright (c) 2007-2014 Nicira, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <net/llc_pdu.h>
#include <linux/kernel.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/llc.h>
#include <linux/module.h>
#include <linux/in.h>
#include <linux/rcupdate.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/sctp.h>
#include <linux/smp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/mpls.h>
#include <net/ndisc.h>

#include "conntrack.h"
#include "datapath.h"
#include "flow.h"
#include "flow_netlink.h"
#include "vport.h"


u64 ovs_flow_used_time(unsigned long flow_jiffies) { struct timespec cur_ts; u64 cur_ms, idle_ms; ktime_get_ts(&cur_ts); idle_ms = jiffies_to_msecs(jiffies - flow_jiffies); cur_ms = (u64)cur_ts.tv_sec * MSEC_PER_SEC + cur_ts.tv_nsec / NSEC_PER_MSEC; return cur_ms - idle_ms; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar4174.55%125.00%
andy zhouandy zhou1018.18%250.00%
jesse grossjesse gross47.27%125.00%
Total55100.00%4100.00%

#define TCP_FLAGS_BE16(tp) (*(__be16 *)&tcp_flag_word(tp) & htons(0x0FFF))
void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, const struct sk_buff *skb) { struct flow_stats *stats; int node = numa_node_id(); int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); stats = rcu_dereference(flow->stats[node]); /* Check if already have node-specific stats. */ if (likely(stats)) { spin_lock(&stats->lock); /* Mark if we write on the pre-allocated stats. */ if (node == 0 && unlikely(flow->stats_last_writer != node)) flow->stats_last_writer = node; } else { stats = rcu_dereference(flow->stats[0]); /* Pre-allocated. */ spin_lock(&stats->lock); /* If the current NUMA-node is the only writer on the * pre-allocated stats keep using them. */ if (unlikely(flow->stats_last_writer != node)) { /* A previous locker may have already allocated the * stats, so we need to check again. If node-specific * stats were already allocated, we update the pre- * allocated stats as we have already locked them. */ if (likely(flow->stats_last_writer != NUMA_NO_NODE) && likely(!rcu_access_pointer(flow->stats[node]))) { /* Try to allocate node-specific stats. */ struct flow_stats *new_stats; new_stats = kmem_cache_alloc_node(flow_stats_cache, GFP_NOWAIT | __GFP_THISNODE | __GFP_NOWARN | __GFP_NOMEMALLOC, node); if (likely(new_stats)) { new_stats->used = jiffies; new_stats->packet_count = 1; new_stats->byte_count = len; new_stats->tcp_flags = tcp_flags; spin_lock_init(&new_stats->lock); rcu_assign_pointer(flow->stats[node], new_stats); goto unlock; } } flow->stats_last_writer = node; } } stats->used = jiffies; stats->packet_count++; stats->byte_count += len; stats->tcp_flags |= tcp_flags; unlock: spin_unlock(&stats->lock); }

Contributors

PersonTokensPropCommitsCommitProp
jarno rajahalmejarno rajahalme18966.55%19.09%
pravin b shelarpravin b shelar4816.90%218.18%
ben pfaffben pfaff207.04%218.18%
jesse grossjesse gross103.52%19.09%
andy zhouandy zhou93.17%19.09%
david rientjesdavid rientjes51.76%19.09%
jiri pirkojiri pirko10.35%19.09%
thomas grafthomas graf10.35%19.09%
andreea-cristina bernatandreea-cristina bernat10.35%19.09%
Total284100.00%11100.00%

/* Must be called with rcu_read_lock or ovs_mutex. */
void ovs_flow_stats_get(const struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, unsigned long *used, __be16 *tcp_flags) { int node; *used = 0; *tcp_flags = 0; memset(ovs_stats, 0, sizeof(*ovs_stats)); for_each_node(node) { struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]); if (stats) { /* Local CPU may write on non-local stats, so we must * block bottom-halves here. */ spin_lock_bh(&stats->lock); if (!*used || time_after(stats->used, *used)) *used = stats->used; *tcp_flags |= stats->tcp_flags; ovs_stats->n_packets += stats->packet_count; ovs_stats->n_bytes += stats->byte_count; spin_unlock_bh(&stats->lock); } } }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar7452.48%228.57%
jarno rajahalmejarno rajahalme6042.55%228.57%
ben pfaffben pfaff42.84%114.29%
andy zhouandy zhou21.42%114.29%
jesse grossjesse gross10.71%114.29%
Total141100.00%7100.00%

/* Called with ovs_mutex. */
void ovs_flow_stats_clear(struct sw_flow *flow) { int node; for_each_node(node) { struct flow_stats *stats = ovsl_dereference(flow->stats[node]); if (stats) { spin_lock_bh(&stats->lock); stats->used = 0; stats->packet_count = 0; stats->byte_count = 0; stats->tcp_flags = 0; spin_unlock_bh(&stats->lock); } } }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar6277.50%240.00%
jarno rajahalmejarno rajahalme1620.00%240.00%
andy zhouandy zhou22.50%120.00%
Total80100.00%5100.00%


static int check_header(struct sk_buff *skb, int len) { if (unlikely(skb->len < len)) return -EINVAL; if (unlikely(!pskb_may_pull(skb, len))) return -ENOMEM; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar3979.59%133.33%
andy zhouandy zhou714.29%133.33%
jesse grossjesse gross36.12%133.33%
Total49100.00%3100.00%


static bool arphdr_ok(struct sk_buff *skb) { return pskb_may_pull(skb, skb_network_offset(skb) + sizeof(struct arp_eth_header)); }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar2278.57%133.33%
andy zhouandy zhou517.86%133.33%
jesse grossjesse gross13.57%133.33%
Total28100.00%3100.00%


static int check_iphdr(struct sk_buff *skb) { unsigned int nh_ofs = skb_network_offset(skb); unsigned int ip_len; int err; err = check_header(skb, nh_ofs + sizeof(struct iphdr)); if (unlikely(err)) return err; ip_len = ip_hdrlen(skb); if (unlikely(ip_len < sizeof(struct iphdr) || skb->len < nh_ofs + ip_len)) return -EINVAL; skb_set_transport_header(skb, nh_ofs + ip_len); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar6971.88%133.33%
jesse grossjesse gross1818.75%133.33%
andy zhouandy zhou99.38%133.33%
Total96100.00%3100.00%


static bool tcphdr_ok(struct sk_buff *skb) { int th_ofs = skb_transport_offset(skb); int tcp_len; if (unlikely(!pskb_may_pull(skb, th_ofs + sizeof(struct tcphdr)))) return false; tcp_len = tcp_hdrlen(skb); if (unlikely(tcp_len < sizeof(struct tcphdr) || skb->len < th_ofs + tcp_len)) return false; return true; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar6076.92%133.33%
jesse grossjesse gross1114.10%133.33%
andy zhouandy zhou78.97%133.33%
Total78100.00%3100.00%


static bool udphdr_ok(struct sk_buff *skb) { return pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)); }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar2278.57%133.33%
andy zhouandy zhou414.29%133.33%
jesse grossjesse gross27.14%133.33%
Total28100.00%3100.00%


static bool sctphdr_ok(struct sk_buff *skb) { return pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct sctphdr)); }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar2175.00%133.33%
andy zhouandy zhou414.29%133.33%
jesse grossjesse gross310.71%133.33%
Total28100.00%3100.00%


static bool icmphdr_ok(struct sk_buff *skb) { return pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct icmphdr)); }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar2382.14%133.33%
andy zhouandy zhou414.29%133.33%
jesse grossjesse gross13.57%133.33%
Total28100.00%3100.00%


static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) { unsigned int nh_ofs = skb_network_offset(skb); unsigned int nh_len; int payload_ofs; struct ipv6hdr *nh; uint8_t nexthdr; __be16 frag_off; int err; err = check_header(skb, nh_ofs + sizeof(*nh)); if (unlikely(err)) return err; nh = ipv6_hdr(skb); nexthdr = nh->nexthdr; payload_ofs = (u8 *)(nh + 1) - skb->data; key->ip.proto = NEXTHDR_NONE; key->ip.tos = ipv6_get_dsfield(nh); key->ip.ttl = nh->hop_limit; key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); key->ipv6.addr.src = nh->saddr; key->ipv6.addr.dst = nh->daddr; payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off); if (frag_off) { if (frag_off & htons(~0x7)) key->ip.frag = OVS_FRAG_TYPE_LATER; else key->ip.frag = OVS_FRAG_TYPE_FIRST; } else { key->ip.frag = OVS_FRAG_TYPE_NONE; } /* Delayed handling of error in ipv6_skip_exthdr() as it * always sets frag_off to a valid value which may be * used to set key->ip.frag above. */ if (unlikely(payload_ofs < 0)) return -EPROTO; nh_len = payload_ofs - nh_ofs; skb_set_transport_header(skb, nh_ofs + nh_len); key->ip.proto = nexthdr; return nh_len; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar19973.70%240.00%
jesse grossjesse gross3412.59%120.00%
andy zhouandy zhou238.52%120.00%
simon hormansimon horman145.19%120.00%
Total270100.00%5100.00%


static bool icmp6hdr_ok(struct sk_buff *skb) { return pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct icmp6hdr)); }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar2071.43%133.33%
jesse grossjesse gross517.86%133.33%
andy zhouandy zhou310.71%133.33%
Total28100.00%3100.00%


static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key) { struct qtag_prefix { __be16 eth_type; /* ETH_P_8021Q */ __be16 tci; }; struct qtag_prefix *qp; if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16))) return 0; if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) + sizeof(__be16)))) return -ENOMEM; qp = (struct qtag_prefix *) skb->data; key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT); __skb_pull(skb, sizeof(struct qtag_prefix)); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar8771.31%350.00%
andy zhouandy zhou1814.75%116.67%
jesse grossjesse gross1512.30%116.67%
ansis attekaansis atteka21.64%116.67%
Total122100.00%6100.00%


static __be16 parse_ethertype(struct sk_buff *skb) { struct llc_snap_hdr { u8 dsap; /* Always 0xAA */ u8 ssap; /* Always 0xAA */ u8 ctrl; u8 oui[3]; __be16 ethertype; }; struct llc_snap_hdr *llc; __be16 proto; proto = *(__be16 *) skb->data; __skb_pull(skb, sizeof(__be16)); if (eth_proto_is_802_3(proto)) return proto; if (skb->len < sizeof(struct llc_snap_hdr)) return htons(ETH_P_802_2); if (unlikely(!pskb_may_pull(skb, sizeof(struct llc_snap_hdr)))) return htons(0); llc = (struct llc_snap_hdr *) skb->data; if (llc->dsap != LLC_SAP_SNAP || llc->ssap != LLC_SAP_SNAP || (llc->oui[0] | llc->oui[1] | llc->oui[2]) != 0) return htons(ETH_P_802_2); __skb_pull(skb, sizeof(struct llc_snap_hdr)); if (eth_proto_is_802_3(llc->ethertype)) return llc->ethertype; return htons(ETH_P_802_2); }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar14269.95%228.57%
jesse grossjesse gross3718.23%114.29%
andy zhouandy zhou157.39%114.29%
david s. millerdavid s. miller41.97%114.29%
ansis attekaansis atteka31.48%114.29%
alexander duyckalexander duyck20.99%114.29%
Total203100.00%7100.00%


static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, int nh_len) { struct icmp6hdr *icmp = icmp6_hdr(skb); /* The ICMPv6 type and code fields use the 16-bit transport port * fields, so we need to store them in 16-bit network byte order. */ key->tp.src = htons(icmp->icmp6_type); key->tp.dst = htons(icmp->icmp6_code); memset(&key->ipv6.nd, 0, sizeof(key->ipv6.nd)); if (icmp->icmp6_code == 0 && (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || icmp->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) { int icmp_len = skb->len - skb_transport_offset(skb); struct nd_msg *nd; int offset; /* In order to process neighbor discovery options, we need the * entire packet. */ if (unlikely(icmp_len < sizeof(*nd))) return 0; if (unlikely(skb_linearize(skb))) return -ENOMEM; nd = (struct nd_msg *)skb_transport_header(skb); key->ipv6.nd.target = nd->target; icmp_len -= sizeof(*nd); offset = 0; while (icmp_len >= 8) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)(nd->opt + offset); int opt_len = nd_opt->nd_opt_len * 8; if (unlikely(!opt_len || opt_len > icmp_len)) return 0; /* Store the link layer address if the appropriate * option is provided. It is considered an error if * the same link layer option is specified twice. */ if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LL_ADDR && opt_len == 8) { if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll))) goto invalid; ether_addr_copy(key->ipv6.nd.sll, &nd->opt[offset+sizeof(*nd_opt)]); } else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR && opt_len == 8) { if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll))) goto invalid; ether_addr_copy(key->ipv6.nd.tll, &nd->opt[offset+sizeof(*nd_opt)]); } icmp_len -= opt_len; offset += opt_len; } } return 0; invalid: memset(&key->ipv6.nd.target, 0, sizeof(key->ipv6.nd.target)); memset(key->ipv6.nd.sll, 0, sizeof(key->ipv6.nd.sll)); memset(key->ipv6.nd.tll, 0, sizeof(key->ipv6.nd.tll)); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
pravin b shelarpravin b shelar33975.84%233.33%
jesse grossjesse gross9721.70%116.67%
andy zhouandy zhou61.34%116.67%
mehak mahajanmehak mahajan30.67%116.67%
joe perchesjoe perches20.45%116.67%
Total447100.00%6100.00%

/** * key_extract - extracts a flow key from an Ethernet frame. * @skb: sk_buff that contains the frame, with skb->data pointing to the * Ethernet header * @key: output flow key * * The caller must ensure that skb->len >= ETH_HLEN. * * Returns 0 if successful, otherwise a negative errno value. * * Initializes @skb header pointers as follows: * * - skb->mac_header: the Ethernet header. * * - skb->network_header: just past the Ethernet header, or just past the * VLAN header, to the first byte of the Ethernet payload. * * - skb->transport_header: If key->eth.type is ETH_P_IP or ETH_P_IPV6 * on output, then just past the IP header, if one is present and * of a correct length, otherwise the same as skb->network_header. * For other key->eth.type values it is left untouched. */
static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) { int error; struct ethhdr *eth; /* Flags are always used as part of stats */ key->tp.flags = 0; skb_reset_mac_header(skb); /* Link layer. We are guaranteed to have at least the 14 byte Ethernet * header in the linear data area. */ eth = eth_hdr(skb); ether_addr_copy(key->eth.src, eth->h_source); ether_addr_copy(key->eth.dst, eth->h_dest); __skb_pull(skb, 2 * ETH_ALEN); /* We are going to push all headers that we pull, so no need to * update skb->csum here. */ key->eth.tci = 0; if (skb_vlan_tag_present(skb)) key->eth.tci = htons(skb->vlan_tci); else if (eth->h_proto == htons(ETH_P_8021Q)) if (unlikely(parse_vlan(skb, key))) return -ENOMEM; key->eth.type = parse_ethertype(skb); if (unlikely(key->eth.type == htons(0))) return -ENOMEM; skb_reset_network_header(skb); skb_reset_mac_len(skb); __skb_push(skb, skb->data - skb_mac_header(skb)); /* Network layer. */ if (key->eth.type == htons(ETH_P_IP)) { struct iphdr *nh; __be16 offset; error = check_iphdr(skb); if (unlikely(error)) { memset(&key->ip, 0, sizeof(key->ip)); memset(&key->ipv4, 0, sizeof(key->ipv4)); if (error == -EINVAL) { skb->transport_header = skb->network_header; error = 0; } return error; } nh = ip_hdr(skb); key->ipv4.addr.src = nh->saddr; key->ipv4.addr.dst = nh->daddr; key->ip.proto = nh->protocol; key->ip.tos = nh->tos; key->ip.ttl = nh->ttl; offset = nh->frag_off & htons(IP_OFFSET); if (offset) { key->ip.frag = OVS_FRAG_TYPE_LATER; return 0; } if (nh->frag_off & htons(IP_MF) || skb_shinfo(skb)->gso_type & SKB_GSO_UDP) key->ip.frag = OVS_FRAG_TYPE_FIRST; else key->ip.frag = OVS_FRAG_TYPE_NONE; /* Transport layer. */ if (key->ip.proto == IPPROTO_TCP) { if (tcphdr_ok(skb)) { struct tcphdr *tcp = tcp_hdr(skb); key->tp.src = tcp->source; key->tp.dst = tcp->dest; key->tp.flags = TCP_FLAGS_BE16(tcp); } else { memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == IPPROTO_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); key->tp.src = udp->source; key->tp.dst = udp->dest; } else { memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == IPPROTO_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); key->tp.src = sctp->source; key->tp.dst = sctp->dest; } else { memset(&key->tp, 0, sizeof(key->tp)); } } else if (key->ip.proto == IPPROTO_ICMP) { if (icmphdr_ok(skb)) { struct icmphdr *icmp = icmp_hdr(skb); /* The ICMP type and code fields use the 16-bit * transport port fields, so we need to store * them in 16-bit network byte order. */ key->tp.src = htons(icmp->type); key->tp.dst = htons(icmp->code); } else { memset(&key->tp, 0, sizeof(key->tp)); } } } else if (key->eth.type == htons(ETH_P_ARP) || key->eth.type == htons(ETH_P_RARP)) { struct arp_eth_header *arp; bool arp_available = arphdr_ok(skb); arp = (struct arp_eth_header *)skb_network_header(skb); if (arp_available && arp->ar_hrd == htons(ARPHRD_ETHER) && arp->ar_pro == htons(ETH_P_IP) && arp->ar_hln == ETH_ALEN && arp->ar_pln == 4) { /* We only match on the lower 8 bits of the opcode. */ if (ntohs(arp->ar_op) <= 0xff) key->ip.proto = ntohs(arp->ar_op); else key->ip.proto = 0; memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src)); memcpy