/*
- * Copyright (c) 2007-2013 Nicira, Inc.
+ * 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
#include <net/dsfield.h>
#include <net/sctp/checksum.h>
-#include "checksum.h"
#include "datapath.h"
+#include "gso.h"
+#include "mpls.h"
#include "vlan.h"
#include "vport.h"
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr, int len, bool keep_skb);
+ const struct nlattr *attr, int len);
static int make_writable(struct sk_buff *skb, int write_len)
{
return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
}
+/* The end of the mac header.
+ *
+ * For non-MPLS skbs this will correspond to the network header.
+ * For MPLS skbs it will be before the network_header as the MPLS
+ * label stack lies between the end of the mac header and the network
+ * header. That is, for MPLS skbs the end of the mac header
+ * is the top of the MPLS label stack.
+ */
+static unsigned char *mac_header_end(const struct sk_buff *skb)
+{
+ return skb_mac_header(skb) + skb->mac_len;
+}
+
+static int push_mpls(struct sk_buff *skb,
+ const struct ovs_action_push_mpls *mpls)
+{
+ __be32 *new_mpls_lse;
+ struct ethhdr *hdr;
+
+ if (skb_cow_head(skb, MPLS_HLEN) < 0)
+ return -ENOMEM;
+
+ skb_push(skb, MPLS_HLEN);
+ memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb),
+ skb->mac_len);
+ skb_reset_mac_header(skb);
+
+ new_mpls_lse = (__be32 *)mac_header_end(skb);
+ *new_mpls_lse = mpls->mpls_lse;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_add(skb->csum, csum_partial(new_mpls_lse,
+ MPLS_HLEN, 0));
+
+ 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);
+ skb->protocol = mpls->mpls_ethertype;
+ return 0;
+}
+
+static int pop_mpls(struct sk_buff *skb, const __be16 ethertype)
+{
+ struct ethhdr *hdr;
+ int err;
+
+ err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+ if (unlikely(err))
+ return err;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_sub(skb->csum,
+ csum_partial(mac_header_end(skb),
+ MPLS_HLEN, 0));
+
+ memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb),
+ skb->mac_len);
+
+ __skb_pull(skb, MPLS_HLEN);
+ skb_reset_mac_header(skb);
+
+ /* mac_header_end() is used to locate the ethertype
+ * field correctly in the presence of VLAN tags.
+ */
+ hdr = (struct ethhdr *)(mac_header_end(skb) - ETH_HLEN);
+ hdr->h_proto = ethertype;
+ if (eth_p_mpls(skb->protocol))
+ skb->protocol = ethertype;
+ return 0;
+}
+
+static int set_mpls(struct sk_buff *skb, const __be32 *mpls_lse)
+{
+ __be32 *stack = (__be32 *)mac_header_end(skb);
+ int err;
+
+ err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+ if (unlikely(err))
+ return err;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ __be32 diff[] = { ~(*stack), *mpls_lse };
+ skb->csum = ~csum_partial((char *)diff, sizeof(diff),
+ ~skb->csum);
+ }
+
+ *stack = *mpls_lse;
+
+ return 0;
+}
+
/* remove VLAN header from packet and update csum accordingly. */
static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
{
if (unlikely(err))
return err;
- if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_sub(skb->csum, csum_partial(skb->data
+ (2 * ETH_ALEN), VLAN_HLEN, 0));
vlan_set_encap_proto(skb, vhdr);
skb->mac_header += VLAN_HLEN;
- skb_reset_mac_len(skb);
+ /* Update mac_len for subsequent MPLS actions */
+ skb->mac_len -= VLAN_HLEN;
return 0;
}
if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
return -ENOMEM;
- if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
+ /* Update mac_len for subsequent MPLS actions */
+ skb->mac_len += VLAN_HLEN;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
skb->csum = csum_add(skb->csum, csum_partial(skb->data
+ (2 * ETH_ALEN), VLAN_HLEN, 0));
if (unlikely(err))
return err;
- if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
- skb->csum = csum_sub(skb->csum, csum_partial(eth_hdr(skb),
- ETH_ALEN * 2, 0));
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
- memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
- memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+ ether_addr_copy(eth_hdr(skb)->h_source, eth_key->eth_src);
+ ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
- if (get_ip_summed(skb) == OVS_CSUM_COMPLETE)
- skb->csum = csum_add(skb->csum, csum_partial(eth_hdr(skb),
- ETH_ALEN * 2, 0));
+ ovs_skb_postpush_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
return 0;
}
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
- if (uh->check ||
- get_ip_summed(skb) == OVS_CSUM_PARTIAL) {
+ if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace4(&uh->check, skb,
*addr, new_addr, 1);
if (!uh->check)
}
csum_replace4(&nh->check, *addr, new_addr);
- skb_clear_rxhash(skb);
+ skb_clear_hash(skb);
*addr = new_addr;
}
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
- if (uh->check ||
- get_ip_summed(skb) == OVS_CSUM_PARTIAL) {
+ if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
inet_proto_csum_replace16(&uh->check, skb,
addr, new_addr, 1);
if (!uh->check)
if (recalculate_csum)
update_ipv6_checksum(skb, l4_proto, addr, new_addr);
- skb_clear_rxhash(skb);
+ skb_clear_hash(skb);
memcpy(addr, new_addr, sizeof(__be32[4]));
}
{
inet_proto_csum_replace2(check, skb, *port, new_port, 0);
*port = new_port;
- skb_clear_rxhash(skb);
+ skb_clear_hash(skb);
}
static void set_udp_port(struct sk_buff *skb, __be16 *port, __be16 new_port)
{
struct udphdr *uh = udp_hdr(skb);
- if (uh->check && get_ip_summed(skb) != OVS_CSUM_PARTIAL) {
+ if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
set_tp_port(skb, port, new_port, &uh->check);
if (!uh->check)
uh->check = CSUM_MANGLED_0;
} else {
*port = new_port;
- skb_clear_rxhash(skb);
+ skb_clear_hash(skb);
}
}
/* Carry any checksum errors through. */
sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
- skb_clear_rxhash(skb);
+ skb_clear_hash(skb);
}
return 0;
}
-static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
{
- struct vport *vport;
+ struct vport *vport = ovs_vport_rcu(dp, out_port);
- if (unlikely(!skb))
- return -ENOMEM;
-
- vport = ovs_vport_rcu(dp, out_port);
- if (unlikely(!vport)) {
+ if (likely(vport))
+ ovs_vport_send(vport, skb);
+ else
kfree_skb(skb);
- return -ENODEV;
- }
-
- ovs_vport_send(vport, skb);
- return 0;
}
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
const struct nlattr *a;
int rem;
- BUG_ON(!OVS_CB(skb)->pkt_key);
-
upcall.cmd = OVS_PACKET_CMD_ACTION;
- upcall.key = OVS_CB(skb)->pkt_key;
upcall.userdata = NULL;
upcall.portid = 0;
return ovs_dp_upcall(dp, skb, &upcall);
}
+static bool last_action(const struct nlattr *a, int rem)
+{
+ return a->nla_len == rem;
+}
+
static int sample(struct datapath *dp, struct sk_buff *skb,
const struct nlattr *attr)
{
const struct nlattr *acts_list = NULL;
const struct nlattr *a;
+ struct sk_buff *sample_skb;
int rem;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
switch (nla_type(a)) {
case OVS_SAMPLE_ATTR_PROBABILITY:
- if (net_random() >= nla_get_u32(a))
+ if (prandom_u32() >= nla_get_u32(a))
return 0;
break;
}
}
- return do_execute_actions(dp, skb, nla_data(acts_list),
- nla_len(acts_list), true);
+ rem = nla_len(acts_list);
+ a = nla_data(acts_list);
+
+ /* Actions list is either empty or only contains a single user-space
+ * action, the latter being a special case as it is the only known
+ * usage of the sample action.
+ * In these special cases don't clone the skb as there are no
+ * side-effects in the nested actions.
+ * Otherwise, clone in case the nested actions have side effects. */
+ if (likely(rem == 0 ||
+ (nla_type(a) == OVS_ACTION_ATTR_USERSPACE &&
+ last_action(a, rem)))) {
+ sample_skb = skb;
+ skb_get(skb);
+ } else {
+ sample_skb = skb_clone(skb, GFP_ATOMIC);
+ if (!sample_skb)
+ /* Skip the sample action when out of memory. */
+ return 0;
+ }
+
+ /* Note that do_execute_actions() never consumes skb.
+ * In the case where skb has been cloned above it is the clone that
+ * is consumed. Otherwise the skb_get(skb) call prevents
+ * consumption by do_execute_actions(). Thus, it is safe to simply
+ * return the error code and let the caller (also
+ * do_execute_actions()) free skb on error. */
+ return do_execute_actions(dp, sample_skb, a, rem);
+}
+
+static void execute_hash(struct sk_buff *skb, const struct nlattr *attr)
+{
+ struct sw_flow_key *key = OVS_CB(skb)->pkt_key;
+ struct ovs_action_hash *hash_act = nla_data(attr);
+ u32 hash = 0;
+
+ /* OVS_HASH_ALG_L4 is the only possible hash algorithm. */
+ hash = skb_get_hash(skb);
+ hash = jhash_1word(hash, hash_act->hash_basis);
+ if (!hash)
+ hash = 0x1;
+
+ key->ovs_flow_hash = hash;
}
static int execute_set_action(struct sk_buff *skb,
skb->mark = nla_get_u32(nested_attr);
break;
- case OVS_KEY_ATTR_IPV4_TUNNEL:
- OVS_CB(skb)->tun_key = nla_data(nested_attr);
+ case OVS_KEY_ATTR_TUNNEL_INFO:
+ OVS_CB(skb)->tun_info = nla_data(nested_attr);
break;
case OVS_KEY_ATTR_ETHERNET:
case OVS_KEY_ATTR_SCTP:
err = set_sctp(skb, nla_data(nested_attr));
break;
+
+ case OVS_KEY_ATTR_MPLS:
+ err = set_mpls(skb, nla_data(nested_attr));
+ break;
}
return err;
}
+static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *a)
+{
+ struct sw_flow_key recirc_key;
+ uint32_t hash = OVS_CB(skb)->pkt_key->ovs_flow_hash;
+ int err;
+
+ err = ovs_flow_key_extract(skb, &recirc_key);
+ if (err) {
+ kfree_skb(skb);
+ return err;
+ }
+
+ recirc_key.ovs_flow_hash = hash;
+ recirc_key.recirc_id = nla_get_u32(a);
+
+ ovs_dp_process_packet_with_key(skb, &recirc_key, true);
+
+ return 0;
+}
+
/* Execute a list of actions against 'skb'. */
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr, int len, bool keep_skb)
+ 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
a = nla_next(a, &rem)) {
int err = 0;
- if (prev_port != -1) {
- do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port);
+ 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);
+
prev_port = -1;
}
output_userspace(dp, skb, a);
break;
+ case OVS_ACTION_ATTR_HASH:
+ execute_hash(skb, a);
+ break;
+
+ case OVS_ACTION_ATTR_PUSH_MPLS:
+ err = push_mpls(skb, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_POP_MPLS:
+ err = pop_mpls(skb, nla_get_be16(a));
+ break;
+
case OVS_ACTION_ATTR_PUSH_VLAN:
err = push_vlan(skb, nla_data(a));
if (unlikely(err)) /* skb already freed. */
err = pop_vlan(skb);
break;
+ case OVS_ACTION_ATTR_RECIRC: {
+ struct sk_buff *recirc_skb;
+
+ if (last_action(a, rem))
+ return execute_recirc(dp, skb, a);
+
+ /* Recirc action is the not the last action
+ * of the action list. */
+ recirc_skb = skb_clone(skb, GFP_ATOMIC);
+
+ /* Skip the recirc action when out of memory, but
+ * continue on with the rest of the action list. */
+ if (recirc_skb)
+ err = execute_recirc(dp, recirc_skb, a);
+
+ break;
+ }
+
case OVS_ACTION_ATTR_SET:
err = execute_set_action(skb, nla_data(a));
break;
}
}
- if (prev_port != -1) {
- if (keep_skb)
- skb = skb_clone(skb, GFP_ATOMIC);
-
+ if (prev_port != -1)
do_output(dp, skb, prev_port);
- } else if (!keep_skb)
+ else
consume_skb(skb);
return 0;
}
/* We limit the number of times that we pass into execute_actions()
- * to avoid blowing out the stack in the event that we have a loop. */
-#define MAX_LOOPS 4
+ * to avoid blowing out the stack in the event that we have a loop.
+ *
+ * Each loop adds some (estimated) cost to the kernel stack.
+ * The loop terminates when the max cost is exceeded.
+ * */
+#define RECIRC_STACK_COST 1
+#define DEFAULT_STACK_COST 4
+/* Allow up to 4 regular services, and up to 3 recirculations */
+#define MAX_STACK_COST (DEFAULT_STACK_COST * 4 + RECIRC_STACK_COST * 3)
struct loop_counter {
- u8 count; /* Count. */
+ u8 stack_cost; /* loop stack cost. */
bool looping; /* Loop detected? */
};
static int loop_suppress(struct datapath *dp, struct sw_flow_actions *actions)
{
if (net_ratelimit())
- pr_warn("%s: flow looped %d times, dropping\n",
- ovs_dp_name(dp), MAX_LOOPS);
+ pr_warn("%s: flow loop detected, dropping\n",
+ ovs_dp_name(dp));
actions->actions_len = 0;
return -ELOOP;
}
/* Execute a list of actions against 'skb'. */
-int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb)
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, bool recirc)
{
struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+ const u8 stack_cost = recirc ? RECIRC_STACK_COST : DEFAULT_STACK_COST;
struct loop_counter *loop;
int error;
/* Check whether we've looped too much. */
loop = &__get_cpu_var(loop_counters);
- if (unlikely(++loop->count > MAX_LOOPS))
+ loop->stack_cost += stack_cost;
+ if (unlikely(loop->stack_cost > MAX_STACK_COST))
loop->looping = true;
if (unlikely(loop->looping)) {
error = loop_suppress(dp, acts);
goto out_loop;
}
- OVS_CB(skb)->tun_key = NULL;
- error = do_execute_actions(dp, skb, acts->actions,
- acts->actions_len, false);
+ OVS_CB(skb)->tun_info = NULL;
+ error = do_execute_actions(dp, skb, acts->actions, acts->actions_len);
/* Check whether sub-actions looped too much. */
if (unlikely(loop->looping))
error = loop_suppress(dp, acts);
out_loop:
- /* Decrement loop counter. */
- if (!--loop->count)
+ /* Decrement loop stack cost. */
+ loop->stack_cost -= stack_cost;
+ if (!loop->stack_cost)
loop->looping = false;
return error;