/*
- * Copyright (c) 2007-2015 Nicira, Inc.
+ * Copyright (c) 2007-2017 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
#include "datapath.h"
#include "conntrack.h"
#include "gso.h"
-#include "vlan.h"
#include "vport.h"
+#include "flow_netlink.h"
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
struct deferred_action {
struct sk_buff *skb;
const struct nlattr *actions;
+ int actions_len;
/* Store pkt_key clone when creating deferred action. */
struct sw_flow_key pkt_key;
struct vport *vport;
struct ovs_gso_cb cb;
__be16 inner_protocol;
- __u16 vlan_tci;
+ u16 network_offset; /* valid only for MPLS */
+ u16 vlan_tci;
__be16 vlan_proto;
unsigned int l2_len;
+ u8 mac_proto;
u8 l2_data[MAX_L2_LEN];
};
-#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0)
static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
-#endif
#define DEFERRED_ACTION_FIFO_SIZE 10
+#define OVS_RECURSION_LIMIT 4
+#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
struct action_fifo {
int head;
int tail;
struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
};
+struct action_flow_keys {
+ struct sw_flow_key key[OVS_DEFERRED_ACTION_THRESHOLD];
+};
+
static struct action_fifo __percpu *action_fifos;
-#define EXEC_ACTIONS_LEVEL_LIMIT 4 /* limit used to detect packet
- * looping by the network stack
- */
+static struct action_flow_keys __percpu *flow_keys;
static DEFINE_PER_CPU(int, exec_actions_level);
+/* 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 action_flow_keys *keys = this_cpu_ptr(flow_keys);
+ int level = this_cpu_read(exec_actions_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;
/* Return queue entry 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 *attr)
+ const struct sw_flow_key *key,
+ const struct nlattr *actions,
+ const int actions_len)
{
struct action_fifo *fifo;
struct deferred_action *da;
da = action_fifo_put(fifo);
if (da) {
da->skb = skb;
- da->actions = attr;
+ da->actions = actions;
+ da->actions_len = actions_len;
da->pkt_key = *key;
}
static void invalidate_flow_key(struct sw_flow_key *key)
{
- key->eth.type = htons(0);
+ key->mac_proto |= SW_FLOW_KEY_INVALID;
}
static bool is_flow_key_valid(const struct sw_flow_key *key)
{
- return !!key->eth.type;
+ 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 void update_ethertype(struct sk_buff *skb, struct ethhdr *hdr,
+ __be16 ethertype)
+{
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ __be16 diff[] = { ~(hdr->h_proto), ethertype };
+
+ skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
+ }
+
+ hdr->h_proto = ethertype;
}
static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_mpls *mpls)
{
- __be32 *new_mpls_lse;
- struct ethhdr *hdr;
+ struct mpls_shim_hdr *new_mpls_lse;
/* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
- if (skb_encapsulation(skb))
+ if (skb->encapsulation)
return -ENOTSUPP;
if (skb_cow_head(skb, MPLS_HLEN) < 0)
return -ENOMEM;
+ if (!ovs_skb_get_inner_protocol(skb)) {
+ skb_set_inner_network_header(skb, skb->mac_len);
+ ovs_skb_set_inner_protocol(skb, skb->protocol);
+ }
+
skb_push(skb, MPLS_HLEN);
memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
skb_reset_mac_header(skb);
+#ifdef MPLS_HEADER_IS_L3
+ skb_set_network_header(skb, skb->mac_len);
+#endif
- new_mpls_lse = (__be32 *)skb_mpls_header(skb);
- *new_mpls_lse = mpls->mpls_lse;
+ new_mpls_lse = mpls_hdr(skb);
+ new_mpls_lse->label_stack_entry = mpls->mpls_lse;
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
- MPLS_HLEN, 0));
+ skb_postpush_rcsum(skb, new_mpls_lse, MPLS_HLEN);
- hdr = eth_hdr(skb);
- hdr->h_proto = mpls->mpls_ethertype;
- if (!ovs_skb_get_inner_protocol(skb))
- ovs_skb_set_inner_protocol(skb, skb->protocol);
+ if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET)
+ update_ethertype(skb, eth_hdr(skb), mpls->mpls_ethertype);
skb->protocol = mpls->mpls_ethertype;
invalidate_flow_key(key);
static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
const __be16 ethertype)
{
- struct ethhdr *hdr;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
- skb_postpull_rcsum(skb, skb_mpls_header(skb), MPLS_HLEN);
+ skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN);
memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
skb->mac_len);
__skb_pull(skb, MPLS_HLEN);
skb_reset_mac_header(skb);
+ skb_set_network_header(skb, skb->mac_len);
- /* skb_mpls_header() is used to locate the ethertype
- * field correctly in the presence of VLAN tags.
- */
- hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
- hdr->h_proto = ethertype;
+ if (ovs_key_mac_proto(key) == MAC_PROTO_ETHERNET) {
+ struct ethhdr *hdr;
+
+ /* mpls_hdr() is used to locate the ethertype
+ * field correctly in the presence of VLAN tags.
+ */
+ hdr = (struct ethhdr *)((void*)mpls_hdr(skb) - ETH_HLEN);
+ update_ethertype(skb, hdr, ethertype);
+ }
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
const __be32 *mpls_lse, const __be32 *mask)
{
- __be32 *stack;
+ struct mpls_shim_hdr *stack;
__be32 lse;
int err;
if (unlikely(err))
return err;
- stack = (__be32 *)skb_mpls_header(skb);
- lse = OVS_MASKED(*stack, *mpls_lse, *mask);
+ stack = mpls_hdr(skb);
+ lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
if (skb->ip_summed == CHECKSUM_COMPLETE) {
- __be32 diff[] = { ~(*stack), lse };
+ __be32 diff[] = { ~(stack->label_stack_entry), lse };
- skb->csum = ~csum_partial((char *)diff, sizeof(diff),
- ~skb->csum);
+ skb->csum = csum_partial((char *)diff, sizeof(diff), skb->csum);
}
- *stack = lse;
- flow_key->mpls.top_lse = lse;
+ stack->label_stack_entry = lse;
+ flow_key->mpls.lse[0] = lse;
return 0;
}
int err;
err = skb_vlan_pop(skb);
- if (skb_vlan_tag_present(skb))
+ if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
- else
- key->eth.tci = 0;
+ } 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)
{
- if (skb_vlan_tag_present(skb))
+ if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
- else
- key->eth.tci = vlan->vlan_tci;
+ } else {
+ key->eth.vlan.tci = vlan->vlan_tci;
+ key->eth.vlan.tpid = vlan->vlan_tpid;
+ }
return skb_vlan_push(skb, vlan->vlan_tpid,
- ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+ ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
}
/* 'src' is already properly masked. */
ether_addr_copy_masked(eth_hdr(skb)->h_dest, key->eth_dst,
mask->eth_dst);
- ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
+ 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)
+{
+ skb_pull_rcsum(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ /* 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)
+{
+ struct ethhdr *hdr;
+
+ /* Add the new Ethernet header */
+ if (skb_cow_head(skb, ETH_HLEN) < 0)
+ return -ENOMEM;
+
+ skb_push(skb, ETH_HLEN);
+ skb_reset_mac_header(skb);
+ skb_reset_mac_len(skb);
+
+ hdr = eth_hdr(skb);
+ ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
+ ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
+ hdr->h_proto = skb->protocol;
+
+ skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+
+ /* safe right before invalidate_flow_key */
+ key->mac_proto = MAC_PROTO_ETHERNET;
+ invalidate_flow_key(key);
+ return 0;
+}
+
+static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct nshhdr *nh)
+{
+ int err;
+
+ err = ovs_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 = ovs_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)
{
if (nh->protocol == IPPROTO_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
- addr, new_addr, 1);
+ 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, 1);
+ addr, new_addr, true);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
}
if (l4_proto == NEXTHDR_TCP) {
if (likely(transport_len >= sizeof(struct tcphdr)))
inet_proto_csum_replace16(&tcp_hdr(skb)->check, skb,
- addr, new_addr, 1);
+ 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, 1);
+ 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, 1);
+ skb, addr, new_addr, true);
}
}
mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
- set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+ set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked,
true);
memcpy(&flow_key->ipv6.addr.src, masked,
sizeof(flow_key->ipv6.addr.src));
NULL, &flags)
!= NEXTHDR_ROUTING);
- set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+ set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked,
recalc_csum);
memcpy(&flow_key->ipv6.addr.dst, masked,
sizeof(flow_key->ipv6.addr.dst));
return 0;
}
+static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
+ const struct nlattr *a)
+{
+ struct nshhdr *nh;
+ size_t length;
+ int err;
+ u8 flags;
+ u8 ttl;
+ int i;
+
+ struct ovs_key_nsh key;
+ struct ovs_key_nsh mask;
+
+ err = nsh_key_from_nlattr(a, &key, &mask);
+ if (err)
+ return err;
+
+ /* Make sure the NSH base header is there */
+ if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN))
+ return -ENOMEM;
+
+ nh = nsh_hdr(skb);
+ length = nsh_hdr_len(nh);
+
+ /* Make sure the whole NSH header is there */
+ err = skb_ensure_writable(skb, skb_network_offset(skb) +
+ length);
+ if (unlikely(err))
+ return err;
+
+ nh = nsh_hdr(skb);
+ skb_postpull_rcsum(skb, nh, length);
+ flags = nsh_get_flags(nh);
+ flags = OVS_MASKED(flags, key.base.flags, mask.base.flags);
+ flow_key->nsh.base.flags = flags;
+ ttl = nsh_get_ttl(nh);
+ ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl);
+ flow_key->nsh.base.ttl = ttl;
+ nsh_set_flags_and_ttl(nh, flags, ttl);
+ nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr,
+ mask.base.path_hdr);
+ flow_key->nsh.base.path_hdr = nh->path_hdr;
+ switch (nh->mdtype) {
+ case NSH_M_TYPE1:
+ for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) {
+ nh->md1.context[i] =
+ OVS_MASKED(nh->md1.context[i], key.context[i],
+ mask.context[i]);
+ }
+ memcpy(flow_key->nsh.context, nh->md1.context,
+ sizeof(nh->md1.context));
+ break;
+ case NSH_M_TYPE2:
+ memset(flow_key->nsh.context, 0,
+ sizeof(flow_key->nsh.context));
+ break;
+ default:
+ return -EINVAL;
+ }
+ skb_postpush_rcsum(skb, nh, length);
+ return 0;
+}
+
/* Must follow skb_ensure_writable() since that can move the skb data. */
static void set_tp_port(struct sk_buff *skb, __be16 *port,
__be16 new_port, __sum16 *check)
{
- inet_proto_csum_replace2(check, skb, *port, new_port, 0);
+ inet_proto_csum_replace2(check, skb, *port, new_port, false);
*port = new_port;
}
return 0;
}
-#if LINUX_VERSION_CODE >= KERNEL_VERSION(3,10,0)
static int ovs_vport_output(OVS_VPORT_OUTPUT_PARAMS)
{
- struct ovs_frag_data *data = get_pcpu_ptr(ovs_frag_data_storage);
+ struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
struct vport *vport = data->vport;
if (skb_cow_head(skb, data->l2_len) < 0) {
__skb_dst_copy(skb, data->dst);
*OVS_GSO_CB(skb) = data->cb;
ovs_skb_set_inner_protocol(skb, data->inner_protocol);
- skb->vlan_tci = data->vlan_tci;
- skb->vlan_proto = data->vlan_proto;
+ if (data->vlan_tci & VLAN_CFI_MASK)
+ __vlan_hwaccel_put_tag(skb, data->vlan_proto, data->vlan_tci & ~VLAN_CFI_MASK);
+ else
+ __vlan_hwaccel_clear_tag(skb);
/* Reconstruct the MAC header. */
skb_push(skb, data->l2_len);
memcpy(skb->data, &data->l2_data, data->l2_len);
- ovs_skb_postpush_rcsum(skb, skb->data, data->l2_len);
+ skb_postpush_rcsum(skb, skb->data, data->l2_len);
skb_reset_mac_header(skb);
- ovs_vport_send(vport, skb);
+ if (eth_p_mpls(skb->protocol)) {
+ skb->inner_network_header = skb->network_header;
+ skb_set_network_header(skb, data->network_offset);
+ skb_reset_mac_len(skb);
+ }
+
+ ovs_vport_send(vport, skb, data->mac_proto);
return 0;
}
/* prepare_frag() is called once per (larger-than-MTU) frame; its inverse is
* ovs_vport_output(), which is called once per fragmented packet.
*/
-static void prepare_frag(struct vport *vport, struct sk_buff *skb)
+static void prepare_frag(struct vport *vport, struct sk_buff *skb,
+ u16 orig_network_offset, u8 mac_proto)
{
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
- data = get_pcpu_ptr(ovs_frag_data_storage);
+ data = this_cpu_ptr(&ovs_frag_data_storage);
data->dst = (unsigned long) skb_dst(skb);
data->vport = vport;
data->cb = *OVS_GSO_CB(skb);
data->inner_protocol = ovs_skb_get_inner_protocol(skb);
- data->vlan_tci = skb->vlan_tci;
+ data->network_offset = orig_network_offset;
+ if (skb_vlan_tag_present(skb))
+ data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
+ else
+ data->vlan_tci = 0;
data->vlan_proto = skb->vlan_proto;
+ data->mac_proto = mac_proto;
data->l2_len = hlen;
memcpy(&data->l2_data, skb->data, hlen);
skb_pull(skb, hlen);
}
-static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
- __be16 ethertype)
+static void ovs_fragment(struct net *net, struct vport *vport,
+ struct sk_buff *skb, u16 mru,
+ struct sw_flow_key *key)
{
+ u16 orig_network_offset = 0;
+
+ if (eth_p_mpls(skb->protocol)) {
+ orig_network_offset = skb_network_offset(skb);
+ skb->network_header = skb->inner_network_header;
+ }
+
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
goto err;
}
- if (ethertype == htons(ETH_P_IP)) {
+ if (key->eth.type == htons(ETH_P_IP)) {
struct dst_entry ovs_dst;
unsigned long orig_dst;
- prepare_frag(vport, skb);
+ prepare_frag(vport, skb, orig_network_offset,
+ ovs_key_mac_proto(key));
dst_init(&ovs_dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_dst.dev = vport->dev;
skb_dst_set_noref(skb, &ovs_dst);
IPCB(skb)->frag_max_size = mru;
- ip_do_fragment(skb->sk, skb, ovs_vport_output);
+ ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
refdst_drop(orig_dst);
- } else if (ethertype == htons(ETH_P_IPV6)) {
+ } else if (key->eth.type == htons(ETH_P_IPV6)) {
const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
unsigned long orig_dst;
struct rt6_info ovs_rt;
- if (!v6ops) {
+ if (!v6ops)
goto err;
- }
- prepare_frag(vport, skb);
+ prepare_frag(vport, skb, orig_network_offset,
+ ovs_key_mac_proto(key));
memset(&ovs_rt, 0, sizeof(ovs_rt));
dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
DST_OBSOLETE_NONE, DST_NOCOUNT);
orig_dst = (unsigned long) skb_dst(skb);
skb_dst_set_noref(skb, &ovs_rt.dst);
IP6CB(skb)->frag_max_size = mru;
-
+#ifdef HAVE_IP_LOCAL_OUT_TAKES_NET
+ v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
+#else
v6ops->fragment(skb->sk, skb, ovs_vport_output);
+#endif
refdst_drop(orig_dst);
} else {
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
- ovs_vport_name(vport), ntohs(ethertype), mru,
+ ovs_vport_name(vport), ntohs(key->eth.type), mru,
vport->dev->mtu);
goto err;
}
err:
kfree_skb(skb);
}
-#else /* < 3.10 */
-static void ovs_fragment(struct vport *vport, struct sk_buff *skb, u16 mru,
- __be16 ethertype)
-{
- WARN_ONCE(1, "Fragment unavailable ->%s: eth=%04x, MRU=%d, MTU=%d.",
- ovs_vport_name(vport), ntohs(ethertype), mru,
- vport->dev->mtu);
- kfree_skb(skb);
-}
-#endif
static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
struct sw_flow_key *key)
if (likely(vport)) {
u16 mru = OVS_CB(skb)->mru;
+ u32 cutlen = OVS_CB(skb)->cutlen;
- if (likely(!mru || (skb->len <= mru + ETH_HLEN))) {
- ovs_vport_send(vport, skb);
- } else if (mru <= vport->dev->mtu) {
- __be16 ethertype = key->eth.type;
+ if (unlikely(cutlen > 0)) {
+ if (skb->len - cutlen > ovs_mac_header_len(key))
+ pskb_trim(skb, skb->len - cutlen);
+ else
+ pskb_trim(skb, ovs_mac_header_len(key));
+ }
- if (!is_flow_key_valid(key)) {
- if (eth_p_mpls(skb->protocol))
- ethertype = ovs_skb_get_inner_protocol(skb);
- else
- ethertype = vlan_get_protocol(skb);
- }
+ if (likely(!mru ||
+ (skb->len <= mru + vport->dev->hard_header_len))) {
+ ovs_vport_send(vport, skb, ovs_key_mac_proto(key));
+ } else if (mru <= vport->dev->mtu) {
+ struct net *net = ovs_dp_get_net(dp);
- ovs_fragment(vport, skb, mru, ethertype);
+ ovs_fragment(net, vport, skb, mru, key);
} else {
OVS_NLERR(true, "Cannot fragment IP frames");
kfree_skb(skb);
kfree_skb(skb);
}
}
+
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
- const struct nlattr *actions, int actions_len)
+ const struct nlattr *actions, int actions_len,
+ uint32_t cutlen)
{
- struct ip_tunnel_info info;
struct dp_upcall_info upcall;
const struct nlattr *a;
- int rem;
+ int rem, err;
memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_ACTION;
upcall.mru = OVS_CB(skb)->mru;
+ SKB_INIT_FILL_METADATA_DST(skb);
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
switch (nla_type(a)) {
vport = ovs_vport_rcu(dp, nla_get_u32(a));
if (vport) {
- int err;
-
- upcall.egress_tun_info = &info;
- err = ovs_vport_get_egress_tun_info(vport, skb,
- &upcall);
- if (err)
- upcall.egress_tun_info = NULL;
+ err = dev_fill_metadata_dst(vport->dev, skb);
+ if (!err)
+ upcall.egress_tun_info = skb_tunnel_info(skb);
}
break;
} /* End of switch. */
}
- return ovs_dp_upcall(dp, skb, key, &upcall);
+ err = ovs_dp_upcall(dp, skb, key, &upcall, cutlen);
+ SKB_RESTORE_FILL_METADATA_DST(skb);
+ return err;
}
+/* When 'last' is true, sample() should always consume the 'skb'.
+ * Otherwise, sample() should keep 'skb' intact regardless what
+ * actions are executed within sample().
+ */
static int sample(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key, const struct nlattr *attr,
- const struct nlattr *actions, int actions_len)
+ bool last)
{
- const struct nlattr *acts_list = NULL;
- const struct nlattr *a;
- int rem;
-
- for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
- a = nla_next(a, &rem)) {
- u32 probability;
-
- switch (nla_type(a)) {
- case OVS_SAMPLE_ATTR_PROBABILITY:
- probability = nla_get_u32(a);
- if (!probability || prandom_u32() > probability)
- return 0;
- break;
-
- case OVS_SAMPLE_ATTR_ACTIONS:
- acts_list = a;
- break;
- }
- }
-
- rem = nla_len(acts_list);
- a = nla_data(acts_list);
-
- /* Actions list is empty, do nothing */
- if (unlikely(!rem))
- return 0;
-
- /* The only known usage of sample action is having a single user-space
- * action. Treat this usage as a special case.
- * The output_userspace() should clone the skb to be sent to the
- * user space. This skb will be consumed by its caller.
- */
- if (likely(nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
- nla_is_last(a, rem)))
- return output_userspace(dp, skb, key, a, actions, actions_len);
-
- skb = skb_clone(skb, GFP_ATOMIC);
- if (!skb)
- /* Skip the sample action when out of memory. */
+ struct nlattr *actions;
+ struct nlattr *sample_arg;
+ int rem = nla_len(attr);
+ const struct sample_arg *arg;
+ bool clone_flow_key;
+
+ /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */
+ sample_arg = nla_data(attr);
+ arg = nla_data(sample_arg);
+ actions = nla_next(sample_arg, &rem);
+
+ if ((arg->probability != U32_MAX) &&
+ (!arg->probability || prandom_u32() > arg->probability)) {
+ if (last)
+ consume_skb(skb);
return 0;
+ }
- if (!add_deferred_actions(skb, key, a)) {
- if (net_ratelimit())
- pr_warn("%s: deferred actions limit reached, dropping sample action\n",
- ovs_dp_name(dp));
+ clone_flow_key = !arg->exec;
+ return clone_execute(dp, skb, key, 0, actions, rem, last,
+ clone_flow_key);
+}
- kfree_skb(skb);
- }
- return 0;
+/* When 'last' is true, clone() should always consume the 'skb'.
+ * Otherwise, clone() should keep 'skb' intact regardless what
+ * actions are executed within clone().
+ */
+static int clone(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key, const struct nlattr *attr,
+ bool last)
+{
+ struct nlattr *actions;
+ struct nlattr *clone_arg;
+ int rem = nla_len(attr);
+ bool dont_clone_flow_key;
+
+ /* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+ clone_arg = nla_data(attr);
+ dont_clone_flow_key = nla_get_u32(clone_arg);
+ actions = nla_next(clone_arg, &rem);
+
+ return clone_execute(dp, skb, key, 0, actions, rem, last,
+ !dont_clone_flow_key);
}
static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
get_mask(a, struct ovs_key_ethernet *));
break;
+ case OVS_KEY_ATTR_NSH:
+ err = set_nsh(skb, flow_key, a);
+ break;
+
case OVS_KEY_ATTR_IPV4:
err = set_ipv4(skb, flow_key, nla_data(a),
get_mask(a, struct ovs_key_ipv4 *));
case OVS_KEY_ATTR_CT_ZONE:
case OVS_KEY_ATTR_CT_MARK:
case OVS_KEY_ATTR_CT_LABELS:
+ case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4:
+ case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6:
err = -EINVAL;
break;
}
static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
- const struct nlattr *a, int rem)
+ const struct nlattr *a, bool last)
{
- struct deferred_action *da;
+ u32 recirc_id;
if (!is_flow_key_valid(key)) {
int err;
}
BUG_ON(!is_flow_key_valid(key));
- if (!nla_is_last(a, rem)) {
- /* Recirc action is the not the last action
- * of the action list, need to clone the skb.
- */
- skb = skb_clone(skb, GFP_ATOMIC);
+ recirc_id = nla_get_u32(a);
+ return clone_execute(dp, skb, key, recirc_id, NULL, 0, last, true);
+}
- /* Skip the recirc action when out of memory, but
- * continue on with the rest of the action list.
- */
- if (!skb)
- return 0;
- }
+static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb,
+ struct sw_flow_key *key,
+ const struct nlattr *attr, bool last)
+{
+ const struct nlattr *actions, *cpl_arg;
+ const struct check_pkt_len_arg *arg;
+ int rem = nla_len(attr);
+ bool clone_flow_key;
- da = add_deferred_actions(skb, key, NULL);
- if (da) {
- da->pkt_key.recirc_id = nla_get_u32(a);
- } else {
- kfree_skb(skb);
+ /* The first netlink attribute in 'attr' is always
+ * 'OVS_CHECK_PKT_LEN_ATTR_ARG'.
+ */
+ cpl_arg = nla_data(attr);
+ arg = nla_data(cpl_arg);
- if (net_ratelimit())
- pr_warn("%s: deferred action limit reached, drop recirc action\n",
- ovs_dp_name(dp));
+ if (skb->len <= arg->pkt_len) {
+ /* Second netlink attribute in 'attr' is always
+ * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'.
+ */
+ actions = nla_next(cpl_arg, &rem);
+ clone_flow_key = !arg->exec_for_lesser_equal;
+ } else {
+ /* Third netlink attribute in 'attr' is always
+ * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER'.
+ */
+ actions = nla_next(cpl_arg, &rem);
+ actions = nla_next(actions, &rem);
+ clone_flow_key = !arg->exec_for_greater;
}
- return 0;
+ return clone_execute(dp, skb, key, 0, nla_data(actions),
+ nla_len(actions), last, clone_flow_key);
}
/* Execute a list of actions against 'skb'. */
struct sw_flow_key *key,
const struct nlattr *attr, int len)
{
- /* Every output action needs a separate clone of 'skb', but the common
- * case is just a single output action, so that doing a clone and
- * then freeing the original skbuff is wasteful. So the following code
- * is slightly obscure just to avoid that.
- */
- int prev_port = -1;
const struct nlattr *a;
int rem;
a = nla_next(a, &rem)) {
int err = 0;
- if (unlikely(prev_port != -1)) {
- struct sk_buff *out_skb = skb_clone(skb, GFP_ATOMIC);
-
- if (out_skb)
- do_output(dp, out_skb, prev_port, key);
+ switch (nla_type(a)) {
+ case OVS_ACTION_ATTR_OUTPUT: {
+ int port = nla_get_u32(a);
+ struct sk_buff *clone;
+
+ /* Every output action needs a separate clone
+ * of 'skb', In case the output action is the
+ * last action, cloning can be avoided.
+ */
+ if (nla_is_last(a, rem)) {
+ do_output(dp, skb, port, key);
+ /* 'skb' has been used for output.
+ */
+ return 0;
+ }
- prev_port = -1;
+ clone = skb_clone(skb, GFP_ATOMIC);
+ if (clone)
+ do_output(dp, clone, port, key);
+ OVS_CB(skb)->cutlen = 0;
+ break;
}
- switch (nla_type(a)) {
- case OVS_ACTION_ATTR_OUTPUT:
- prev_port = nla_get_u32(a);
+ case OVS_ACTION_ATTR_TRUNC: {
+ struct ovs_action_trunc *trunc = nla_data(a);
+
+ if (skb->len > trunc->max_len)
+ OVS_CB(skb)->cutlen = skb->len - trunc->max_len;
break;
+ }
case OVS_ACTION_ATTR_USERSPACE:
- output_userspace(dp, skb, key, a, attr, len);
+ output_userspace(dp, skb, key, a, attr,
+ len, OVS_CB(skb)->cutlen);
+ OVS_CB(skb)->cutlen = 0;
break;
case OVS_ACTION_ATTR_HASH:
err = pop_vlan(skb, key);
break;
- case OVS_ACTION_ATTR_RECIRC:
- err = execute_recirc(dp, skb, key, a, rem);
- if (nla_is_last(a, rem)) {
+ case OVS_ACTION_ATTR_RECIRC: {
+ bool last = nla_is_last(a, rem);
+
+ err = execute_recirc(dp, skb, key, a, last);
+ if (last) {
/* If this is the last action, the skb has
* been consumed or freed.
* Return immediately.
return err;
}
break;
+ }
case OVS_ACTION_ATTR_SET:
err = execute_set_action(skb, key, nla_data(a));
err = execute_masked_set_action(skb, key, nla_data(a));
break;
- case OVS_ACTION_ATTR_SAMPLE:
- err = sample(dp, skb, key, a, attr, len);
+ case OVS_ACTION_ATTR_SAMPLE: {
+ bool last = nla_is_last(a, rem);
+
+ err = sample(dp, skb, key, a, last);
+ if (last)
+ return err;
+
break;
+ }
case OVS_ACTION_ATTR_CT:
if (!is_flow_key_valid(key)) {
if (err)
return err == -EINPROGRESS ? 0 : err;
break;
+
+ case OVS_ACTION_ATTR_CT_CLEAR:
+ err = ovs_ct_clear(skb, key);
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_ETH:
+ err = push_eth(skb, key, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_POP_ETH:
+ err = pop_eth(skb, key);
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_NSH: {
+ u8 buffer[NSH_HDR_MAX_LEN];
+ struct nshhdr *nh = (struct nshhdr *)buffer;
+
+ err = nsh_hdr_from_nlattr(nla_data(a), nh,
+ NSH_HDR_MAX_LEN);
+ if (unlikely(err))
+ break;
+ err = push_nsh(skb, key, nh);
+ break;
+ }
+
+ case OVS_ACTION_ATTR_POP_NSH:
+ err = pop_nsh(skb, key);
+ break;
+
+ case OVS_ACTION_ATTR_METER:
+ if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) {
+ consume_skb(skb);
+ return 0;
+ }
+ break;
+
+ case OVS_ACTION_ATTR_CLONE: {
+ bool last = nla_is_last(a, rem);
+
+ err = clone(dp, skb, key, a, last);
+ if (last)
+ return err;
+ break;
+ }
+
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN: {
+ bool last = nla_is_last(a, rem);
+
+ err = execute_check_pkt_len(dp, skb, key, a, last);
+ if (last)
+ return err;
+
+ break;
+ }
}
if (unlikely(err)) {
}
}
- if (prev_port != -1)
- do_output(dp, skb, prev_port, key);
- else
- consume_skb(skb);
+ consume_skb(skb);
+ return 0;
+}
+
+/* Execute the actions on the clone of the packet. The effect of the
+ * execution does not affect the original 'skb' nor the original 'key'.
+ *
+ * The execution may be deferred in case the actions can not be executed
+ * immediately.
+ */
+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)
+{
+ struct deferred_action *da;
+ struct sw_flow_key *clone;
+
+ skb = last ? skb : skb_clone(skb, GFP_ATOMIC);
+ if (!skb) {
+ /* Out of memory, skip this action.
+ */
+ return 0;
+ }
+
+ /* When clone_flow_key is false, the 'key' will not be change
+ * by the actions, then the 'key' can be used directly.
+ * Otherwise, try to clone key from the next recursion level of
+ * 'flow_keys'. If clone is successful, execute the actions
+ * without deferring.
+ */
+ clone = clone_flow_key ? clone_key(key) : key;
+ if (clone) {
+ int err = 0;
+ if (actions) { /* Sample action */
+ if (clone_flow_key)
+ __this_cpu_inc(exec_actions_level);
+
+ err = do_execute_actions(dp, skb, clone,
+ actions, len);
+
+ if (clone_flow_key)
+ __this_cpu_dec(exec_actions_level);
+ } else { /* Recirc action */
+ clone->recirc_id = recirc_id;
+ ovs_dp_process_packet(skb, clone);
+ }
+ return err;
+ }
+
+ /* Out of 'flow_keys' space. Defer actions */
+ da = add_deferred_actions(skb, key, actions, len);
+ if (da) {
+ if (!actions) { /* Recirc action */
+ key = &da->pkt_key;
+ key->recirc_id = recirc_id;
+ }
+ } else {
+ /* Out of per CPU action FIFO space. Drop the 'skb' and
+ * log an error.
+ */
+ kfree_skb(skb);
+
+ if (net_ratelimit()) {
+ if (actions) { /* Sample action */
+ pr_warn("%s: deferred action limit reached, drop sample action\n",
+ ovs_dp_name(dp));
+ } else { /* Recirc action */
+ pr_warn("%s: deferred action limit reached, drop recirc action\n",
+ ovs_dp_name(dp));
+ }
+ }
+ }
return 0;
}
struct sk_buff *skb = da->skb;
struct sw_flow_key *key = &da->pkt_key;
const struct nlattr *actions = da->actions;
+ int actions_len = da->actions_len;
if (actions)
- do_execute_actions(dp, skb, key, actions,
- nla_len(actions));
+ do_execute_actions(dp, skb, key, actions, actions_len);
else
ovs_dp_process_packet(skb, key);
} while (!action_fifo_is_empty(fifo));
const struct sw_flow_actions *acts,
struct sw_flow_key *key)
{
- int level = this_cpu_read(exec_actions_level);
- int err;
-
- if (unlikely(level >= EXEC_ACTIONS_LEVEL_LIMIT)) {
- if (net_ratelimit())
- pr_warn("%s: packet loop detected, dropping.\n",
- ovs_dp_name(dp));
+ int err, level;
+ level = __this_cpu_inc_return(exec_actions_level);
+ if (unlikely(level > OVS_RECURSION_LIMIT)) {
+ net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
+ ovs_dp_name(dp));
kfree_skb(skb);
- return -ELOOP;
+ err = -ENETDOWN;
+ goto out;
}
- this_cpu_inc(exec_actions_level);
+ OVS_CB(skb)->acts_origlen = acts->orig_len;
err = do_execute_actions(dp, skb, key,
acts->actions, acts->actions_len);
- if (!level)
+ if (level == 1)
process_deferred_actions(dp);
- this_cpu_dec(exec_actions_level);
-
- /* This return status currently does not reflect the errors
- * encounted during deferred actions execution. Probably needs to
- * be fixed in the future.
- */
+out:
+ __this_cpu_dec(exec_actions_level);
return err;
}
if (!action_fifos)
return -ENOMEM;
+ flow_keys = alloc_percpu(struct action_flow_keys);
+ if (!flow_keys) {
+ free_percpu(action_fifos);
+ return -ENOMEM;
+ }
+
return 0;
}
void action_fifos_exit(void)
{
free_percpu(action_fifos);
+ free_percpu(flow_keys);
}
projects / mirror_ovs.git / blobdiff