#include <linux/in6.h>
#include <linux/if_arp.h>
#include <linux/if_vlan.h>
+
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/checksum.h>
#include <net/dsfield.h>
+#include <net/mpls.h>
#include <net/sctp/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,
+ struct sw_flow_key *key,
const struct nlattr *attr, int len);
-static int make_writable(struct sk_buff *skb, int write_len)
+struct deferred_action {
+ struct sk_buff *skb;
+ const struct nlattr *actions;
+
+ /* Store pkt_key clone when creating deferred action. */
+ struct sw_flow_key pkt_key;
+};
+
+#define DEFERRED_ACTION_FIFO_SIZE 10
+struct action_fifo {
+ int head;
+ int tail;
+ /* Deferred action fifo queue storage. */
+ struct deferred_action fifo[DEFERRED_ACTION_FIFO_SIZE];
+};
+
+static struct action_fifo __percpu *action_fifos;
+#define EXEC_ACTIONS_LEVEL_LIMIT 4 /* limit used to detect packet
+ * looping by the network stack
+ */
+static DEFINE_PER_CPU(int, exec_actions_level);
+
+static void action_fifo_init(struct action_fifo *fifo)
{
- if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
- return 0;
+ fifo->head = 0;
+ fifo->tail = 0;
+}
- return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+static bool action_fifo_is_empty(const struct action_fifo *fifo)
+{
+ return (fifo->head == fifo->tail);
}
-/* 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)
+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 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)
+{
+ struct action_fifo *fifo;
+ struct deferred_action *da;
+
+ fifo = this_cpu_ptr(action_fifos);
+ da = action_fifo_put(fifo);
+ if (da) {
+ da->skb = skb;
+ da->actions = attr;
+ da->pkt_key = *key;
+ }
+
+ return da;
+}
+
+static void invalidate_flow_key(struct sw_flow_key *key)
+{
+ key->eth.type = htons(0);
+}
+
+static bool is_flow_key_valid(const struct sw_flow_key *key)
{
- return skb_mac_header(skb) + skb->mac_len;
+ return !!key->eth.type;
}
-static int push_mpls(struct sk_buff *skb,
+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;
+ /* Networking stack do not allow simultaneous Tunnel and MPLS GSO. */
+ if (skb_encapsulation(skb))
+ return -ENOTSUPP;
+
if (skb_cow_head(skb, MPLS_HLEN) < 0)
return -ENOMEM;
skb->mac_len);
skb_reset_mac_header(skb);
- new_mpls_lse = (__be32 *)mac_header_end(skb);
+ new_mpls_lse = (__be32 *)skb_mpls_header(skb);
*new_mpls_lse = mpls->mpls_lse;
if (skb->ip_summed == CHECKSUM_COMPLETE)
if (!ovs_skb_get_inner_protocol(skb))
ovs_skb_set_inner_protocol(skb, skb->protocol);
skb->protocol = mpls->mpls_ethertype;
+
+ invalidate_flow_key(key);
return 0;
}
-static int pop_mpls(struct sk_buff *skb, const __be16 ethertype)
+static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key,
+ const __be16 ethertype)
{
struct ethhdr *hdr;
int err;
- err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+ err = skb_ensure_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));
+ skb_postpull_rcsum(skb, skb_mpls_header(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);
- /* mac_header_end() is used to locate the ethertype
+ /* skb_mpls_header() is used to locate the ethertype
* field correctly in the presence of VLAN tags.
*/
- hdr = (struct ethhdr *)(mac_header_end(skb) - ETH_HLEN);
+ hdr = (struct ethhdr *)(skb_mpls_header(skb) - ETH_HLEN);
hdr->h_proto = ethertype;
if (eth_p_mpls(skb->protocol))
skb->protocol = ethertype;
+
+ invalidate_flow_key(key);
return 0;
}
-static int set_mpls(struct sk_buff *skb, const __be32 *mpls_lse)
+/* 'KEY' must not have any bits set outside of the 'MASK' */
+#define MASKED(OLD, KEY, MASK) ((KEY) | ((OLD) & ~(MASK)))
+#define SET_MASKED(OLD, KEY, MASK) ((OLD) = MASKED(OLD, KEY, MASK))
+
+static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
+ const __be32 *mpls_lse, const __be32 *mask)
{
- __be32 *stack = (__be32 *)mac_header_end(skb);
+ __be32 *stack;
+ __be32 lse;
int err;
- err = make_writable(skb, skb->mac_len + MPLS_HLEN);
+ err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
if (unlikely(err))
return err;
+ stack = (__be32 *)skb_mpls_header(skb);
+ lse = MASKED(*stack, *mpls_lse, *mask);
if (skb->ip_summed == CHECKSUM_COMPLETE) {
- __be32 diff[] = { ~(*stack), *mpls_lse };
+ __be32 diff[] = { ~(*stack), lse };
+
skb->csum = ~csum_partial((char *)diff, sizeof(diff),
~skb->csum);
}
- *stack = *mpls_lse;
-
+ *stack = lse;
+ flow_key->mpls.top_lse = lse;
return 0;
}
-/* remove VLAN header from packet and update csum accordingly. */
-static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
+static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
{
- struct vlan_hdr *vhdr;
int err;
- err = make_writable(skb, VLAN_ETH_HLEN);
- if (unlikely(err))
- return err;
-
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->csum = csum_sub(skb->csum, csum_partial(skb->data
- + (2 * ETH_ALEN), VLAN_HLEN, 0));
-
- vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
- *current_tci = vhdr->h_vlan_TCI;
-
- memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
- __skb_pull(skb, VLAN_HLEN);
-
- vlan_set_encap_proto(skb, vhdr);
- skb->mac_header += VLAN_HLEN;
- /* Update mac_len for subsequent MPLS actions */
- skb->mac_len -= VLAN_HLEN;
-
- return 0;
+ err = skb_vlan_pop(skb);
+ if (skb_vlan_tag_present(skb))
+ invalidate_flow_key(key);
+ else
+ key->eth.tci = 0;
+ return err;
}
-static int pop_vlan(struct sk_buff *skb)
+static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
+ const struct ovs_action_push_vlan *vlan)
{
- __be16 tci;
- int err;
-
- if (likely(vlan_tx_tag_present(skb))) {
- vlan_set_tci(skb, 0);
- } else {
- if (unlikely(skb->protocol != htons(ETH_P_8021Q) ||
- skb->len < VLAN_ETH_HLEN))
- return 0;
-
- err = __pop_vlan_tci(skb, &tci);
- if (err)
- return err;
- }
- /* move next vlan tag to hw accel tag */
- if (likely(skb->protocol != htons(ETH_P_8021Q) ||
- skb->len < VLAN_ETH_HLEN))
- return 0;
-
- err = __pop_vlan_tci(skb, &tci);
- if (unlikely(err))
- return err;
-
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), ntohs(tci));
- return 0;
+ if (skb_vlan_tag_present(skb))
+ invalidate_flow_key(key);
+ else
+ key->eth.tci = vlan->vlan_tci;
+ return skb_vlan_push(skb, vlan->vlan_tpid,
+ ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
}
-static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan)
+/* 'src' is already properly masked. */
+static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
{
- if (unlikely(vlan_tx_tag_present(skb))) {
- u16 current_tag;
-
- /* push down current VLAN tag */
- current_tag = vlan_tx_tag_get(skb);
-
- if (!__vlan_put_tag(skb, skb->vlan_proto, current_tag))
- return -ENOMEM;
-
- /* 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));
+ u16 *dst = (u16 *)dst_;
+ const u16 *src = (const u16 *)src_;
+ const u16 *mask = (const u16 *)mask_;
- }
- __vlan_hwaccel_put_tag(skb, vlan->vlan_tpid, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
- return 0;
+ SET_MASKED(dst[0], src[0], mask[0]);
+ SET_MASKED(dst[1], src[1], mask[1]);
+ SET_MASKED(dst[2], src[2], mask[2]);
}
-static int set_eth_addr(struct sk_buff *skb,
- const struct ovs_key_ethernet *eth_key)
+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 = make_writable(skb, ETH_HLEN);
+
+ 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(eth_hdr(skb)->h_source, eth_key->eth_src);
- ether_addr_copy(eth_hdr(skb)->h_dest, eth_key->eth_dst);
+ 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);
ovs_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;
}
-static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
- __be32 *addr, __be32 new_addr)
+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, 1);
+ addr, new_addr, 1);
} 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, 1);
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);
*addr = new_addr;
{
int transport_len = skb->len - skb_transport_offset(skb);
- if (l4_proto == IPPROTO_TCP) {
+ 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);
- } else if (l4_proto == IPPROTO_UDP) {
+ } else if (l4_proto == NEXTHDR_UDP) {
if (likely(transport_len >= sizeof(struct udphdr))) {
struct udphdr *uh = udp_hdr(skb);
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);
}
}
+static void mask_ipv6_addr(const __be32 old[4], const __be32 addr[4],
+ const __be32 mask[4], __be32 masked[4])
+{
+ masked[0] = MASKED(old[0], addr[0], mask[0]);
+ masked[1] = MASKED(old[1], addr[1], mask[1]);
+ masked[2] = MASKED(old[2], addr[2], mask[2]);
+ masked[3] = 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)
+ if (likely(recalculate_csum))
update_ipv6_checksum(skb, l4_proto, addr, new_addr);
skb_clear_hash(skb);
memcpy(addr, new_addr, sizeof(__be32[4]));
}
-static void set_ipv6_tc(struct ipv6hdr *nh, u8 tc)
+static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
{
- nh->priority = tc >> 4;
- nh->flow_lbl[0] = (nh->flow_lbl[0] & 0x0F) | ((tc & 0x0F) << 4);
+ /* Bits 21-24 are always unmasked, so this retains their values. */
+ SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
+ SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
+ SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
}
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl)
+static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
+ u8 mask)
{
- nh->flow_lbl[0] = (nh->flow_lbl[0] & 0xF0) | (fl & 0x000F0000) >> 16;
- nh->flow_lbl[1] = (fl & 0x0000FF00) >> 8;
- nh->flow_lbl[2] = fl & 0x000000FF;
-}
+ new_ttl = MASKED(nh->ttl, new_ttl, mask);
-static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
-{
csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
nh->ttl = new_ttl;
}
-static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
+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 = make_writable(skb, skb_network_offset(skb) +
- sizeof(struct iphdr));
+ err = skb_ensure_writable(skb, skb_network_offset(skb) +
+ sizeof(struct iphdr));
if (unlikely(err))
return err;
nh = ip_hdr(skb);
- if (ipv4_key->ipv4_src != nh->saddr)
- set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
-
- if (ipv4_key->ipv4_dst != nh->daddr)
- set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
+ /* 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 = MASKED(nh->saddr, key->ipv4_src, mask->ipv4_src);
- if (ipv4_key->ipv4_tos != nh->tos)
- ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
+ 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 = MASKED(nh->daddr, key->ipv4_dst, mask->ipv4_dst);
- if (ipv4_key->ipv4_ttl != nh->ttl)
- set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
+ 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;
}
-static int set_ipv6(struct sk_buff *skb, const struct ovs_key_ipv6 *ipv6_key)
+static bool is_ipv6_mask_nonzero(const __be32 addr[4])
+{
+ return !!(addr[0] | addr[1] | addr[2] | addr[3]);
+}
+
+static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
+ const struct ovs_key_ipv6 *key,
+ const struct ovs_key_ipv6 *mask)
{
struct ipv6hdr *nh;
int err;
- __be32 *saddr;
- __be32 *daddr;
- err = make_writable(skb, skb_network_offset(skb) +
- sizeof(struct ipv6hdr));
+ err = skb_ensure_writable(skb, skb_network_offset(skb) +
+ sizeof(struct ipv6hdr));
if (unlikely(err))
return err;
nh = ipv6_hdr(skb);
- saddr = (__be32 *)&nh->saddr;
- daddr = (__be32 *)&nh->daddr;
- if (memcmp(ipv6_key->ipv6_src, saddr, sizeof(ipv6_key->ipv6_src)))
- set_ipv6_addr(skb, ipv6_key->ipv6_proto, saddr,
- ipv6_key->ipv6_src, true);
+ /* 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 (is_ipv6_mask_nonzero(mask->ipv6_src)) {
+ __be32 *saddr = (__be32 *)&nh->saddr;
+ __be32 masked[4];
+
+ mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked);
- if (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
+ if (unlikely(memcmp(saddr, masked, sizeof(masked)))) {
+ set_ipv6_addr(skb, key->ipv6_proto, saddr, masked,
+ true);
+ memcpy(&flow_key->ipv6.addr.src, masked,
+ sizeof(flow_key->ipv6.addr.src));
+ }
+ }
+ if (is_ipv6_mask_nonzero(mask->ipv6_dst)) {
unsigned int offset = 0;
- int flags = OVS_IP6T_FH_F_SKIP_RH;
+ int flags = IP6_FH_F_SKIP_RH;
bool recalc_csum = true;
-
- if (ipv6_ext_hdr(nh->nexthdr))
- recalc_csum = ipv6_find_hdr(skb, &offset,
- NEXTHDR_ROUTING, NULL,
- &flags) != NEXTHDR_ROUTING;
-
- set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
- ipv6_key->ipv6_dst, recalc_csum);
+ __be32 *daddr = (__be32 *)&nh->daddr;
+ __be32 masked[4];
+
+ mask_ipv6_addr(daddr, key->ipv6_dst, mask->ipv6_dst, masked);
+
+ if (unlikely(memcmp(daddr, masked, sizeof(masked)))) {
+ if (ipv6_ext_hdr(nh->nexthdr))
+ recalc_csum = (ipv6_find_hdr(skb, &offset,
+ NEXTHDR_ROUTING,
+ NULL, &flags)
+ != NEXTHDR_ROUTING);
+
+ set_ipv6_addr(skb, key->ipv6_proto, daddr, masked,
+ recalc_csum);
+ memcpy(&flow_key->ipv6.addr.dst, masked,
+ sizeof(flow_key->ipv6.addr.dst));
+ }
+ }
+ if (mask->ipv6_tclass) {
+ ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+ flow_key->ip.tos = ipv6_get_dsfield(nh);
+ }
+ if (mask->ipv6_label) {
+ set_ipv6_fl(nh, ntohl(key->ipv6_label),
+ ntohl(mask->ipv6_label));
+ flow_key->ipv6.label =
+ *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
+ }
+ if (mask->ipv6_hlimit) {
+ SET_MASKED(nh->hop_limit, key->ipv6_hlimit, mask->ipv6_hlimit);
+ flow_key->ip.ttl = nh->hop_limit;
}
-
- set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
- set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
- nh->hop_limit = ipv6_key->ipv6_hlimit;
-
return 0;
}
-/* Must follow make_writable() since that can move the skb data. */
+/* 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)
+ __be16 new_port, __sum16 *check)
{
inet_proto_csum_replace2(check, skb, *port, new_port, 0);
*port = new_port;
- 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 && 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_hash(skb);
- }
-}
-
-static int set_udp(struct sk_buff *skb, const struct ovs_key_udp *udp_port_key)
+static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+ const struct ovs_key_udp *key,
+ const struct ovs_key_udp *mask)
{
struct udphdr *uh;
+ __be16 src, dst;
int err;
- err = make_writable(skb, skb_transport_offset(skb) +
- sizeof(struct udphdr));
+ err = skb_ensure_writable(skb, skb_transport_offset(skb) +
+ sizeof(struct udphdr));
if (unlikely(err))
return err;
uh = udp_hdr(skb);
- if (udp_port_key->udp_src != uh->source)
- set_udp_port(skb, &uh->source, udp_port_key->udp_src);
+ /* Either of the masks is non-zero, so do not bother checking them. */
+ src = MASKED(uh->source, key->udp_src, mask->udp_src);
+ dst = MASKED(uh->dest, key->udp_dst, mask->udp_dst);
+
+ if (uh->check && skb->ip_summed != CHECKSUM_PARTIAL) {
+ if (likely(src != uh->source)) {
+ set_tp_port(skb, &uh->source, src, &uh->check);
+ flow_key->tp.src = src;
+ }
+ if (likely(dst != uh->dest)) {
+ set_tp_port(skb, &uh->dest, dst, &uh->check);
+ flow_key->tp.dst = dst;
+ }
+
+ if (unlikely(!uh->check))
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ uh->source = src;
+ uh->dest = dst;
+ flow_key->tp.src = src;
+ flow_key->tp.dst = dst;
+ }
- if (udp_port_key->udp_dst != uh->dest)
- set_udp_port(skb, &uh->dest, udp_port_key->udp_dst);
+ skb_clear_hash(skb);
return 0;
}
-static int set_tcp(struct sk_buff *skb, const struct ovs_key_tcp *tcp_port_key)
+static int set_tcp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+ const struct ovs_key_tcp *key,
+ const struct ovs_key_tcp *mask)
{
struct tcphdr *th;
+ __be16 src, dst;
int err;
- err = make_writable(skb, skb_transport_offset(skb) +
- sizeof(struct tcphdr));
+ err = skb_ensure_writable(skb, skb_transport_offset(skb) +
+ sizeof(struct tcphdr));
if (unlikely(err))
return err;
th = tcp_hdr(skb);
- if (tcp_port_key->tcp_src != th->source)
- set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
-
- if (tcp_port_key->tcp_dst != th->dest)
- set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
+ src = MASKED(th->source, key->tcp_src, mask->tcp_src);
+ if (likely(src != th->source)) {
+ set_tp_port(skb, &th->source, src, &th->check);
+ flow_key->tp.src = src;
+ }
+ dst = MASKED(th->dest, key->tcp_dst, mask->tcp_dst);
+ if (likely(dst != th->dest)) {
+ set_tp_port(skb, &th->dest, dst, &th->check);
+ flow_key->tp.dst = dst;
+ }
+ skb_clear_hash(skb);
return 0;
}
-static int set_sctp(struct sk_buff *skb,
- const struct ovs_key_sctp *sctp_port_key)
+static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
+ const struct ovs_key_sctp *key,
+ const struct ovs_key_sctp *mask)
{
+ unsigned int sctphoff = skb_transport_offset(skb);
struct sctphdr *sh;
+ __le32 old_correct_csum, new_csum, old_csum;
int err;
- unsigned int sctphoff = skb_transport_offset(skb);
- err = make_writable(skb, sctphoff + sizeof(struct sctphdr));
+ err = skb_ensure_writable(skb, sctphoff + sizeof(struct sctphdr));
if (unlikely(err))
return err;
sh = sctp_hdr(skb);
- if (sctp_port_key->sctp_src != sh->source ||
- sctp_port_key->sctp_dst != sh->dest) {
- __le32 old_correct_csum, new_csum, old_csum;
+ old_csum = sh->checksum;
+ old_correct_csum = sctp_compute_cksum(skb, sctphoff);
- old_csum = sh->checksum;
- old_correct_csum = sctp_compute_cksum(skb, sctphoff);
+ sh->source = MASKED(sh->source, key->sctp_src, mask->sctp_src);
+ sh->dest = MASKED(sh->dest, key->sctp_dst, mask->sctp_dst);
- sh->source = sctp_port_key->sctp_src;
- sh->dest = sctp_port_key->sctp_dst;
+ new_csum = sctp_compute_cksum(skb, sctphoff);
- new_csum = sctp_compute_cksum(skb, sctphoff);
+ /* Carry any checksum errors through. */
+ sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
- /* Carry any checksum errors through. */
- sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
-
- skb_clear_hash(skb);
- }
+ skb_clear_hash(skb);
+ flow_key->tp.src = sh->source;
+ flow_key->tp.dst = sh->dest;
return 0;
}
}
static int output_userspace(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr)
+ struct sw_flow_key *key, const struct nlattr *attr,
+ const struct nlattr *actions, int actions_len)
{
+ struct ovs_tunnel_info info;
struct dp_upcall_info upcall;
const struct nlattr *a;
int rem;
+ memset(&upcall, 0, sizeof(upcall));
upcall.cmd = OVS_PACKET_CMD_ACTION;
- upcall.userdata = NULL;
- upcall.portid = 0;
for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
a = nla_next(a, &rem)) {
case OVS_USERSPACE_ATTR_PID:
upcall.portid = nla_get_u32(a);
break;
+
+ case OVS_USERSPACE_ATTR_EGRESS_TUN_PORT: {
+ /* Get out tunnel info. */
+ struct vport *vport;
+
+ vport = ovs_vport_rcu(dp, nla_get_u32(a));
+ if (vport) {
+ int err;
+
+ err = ovs_vport_get_egress_tun_info(vport, skb,
+ &info);
+ if (!err)
+ upcall.egress_tun_info = &info;
+ }
+ break;
}
- }
- return ovs_dp_upcall(dp, skb, &upcall);
-}
+ case OVS_USERSPACE_ATTR_ACTIONS: {
+ /* Include actions. */
+ upcall.actions = actions;
+ upcall.actions_len = actions_len;
+ break;
+ }
-static bool last_action(const struct nlattr *a, int rem)
-{
- return a->nla_len == rem;
+ } /* End of switch. */
+ }
+
+ return ovs_dp_upcall(dp, skb, key, &upcall);
}
static int sample(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *attr)
+ struct sw_flow_key *key, const struct nlattr *attr,
+ const struct nlattr *actions, int actions_len)
{
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)) {
+ u32 probability;
+
switch (nla_type(a)) {
case OVS_SAMPLE_ATTR_PROBABILITY:
- if (prandom_u32() >= nla_get_u32(a))
+ probability = nla_get_u32(a);
+ if (!probability || prandom_u32() > probability)
return 0;
break;
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;
- }
+ /* Actions list is empty, do nothing */
+ if (unlikely(!rem))
+ 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);
+ /* 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. */
+ 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));
+
+ kfree_skb(skb);
+ }
+ return 0;
}
-static void execute_hash(struct sk_buff *skb, const struct nlattr *attr)
+static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
+ 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;
}
static int execute_set_action(struct sk_buff *skb,
- const struct nlattr *nested_attr)
+ struct sw_flow_key *flow_key,
+ const struct nlattr *a)
+{
+ /* Only tunnel set execution is supported without a mask. */
+ if (nla_type(a) == OVS_KEY_ATTR_TUNNEL_INFO) {
+ OVS_CB(skb)->egress_tun_info = nla_data(a);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+/* Mask is at the midpoint of the data. */
+#define get_mask(a, type) ((const type)nla_data(a) + 1)
+
+static int execute_masked_set_action(struct sk_buff *skb,
+ struct sw_flow_key *flow_key,
+ const struct nlattr *a)
{
int err = 0;
- switch (nla_type(nested_attr)) {
+ switch (nla_type(a)) {
case OVS_KEY_ATTR_PRIORITY:
- skb->priority = nla_get_u32(nested_attr);
+ SET_MASKED(skb->priority, nla_get_u32(a), *get_mask(a, u32 *));
+ flow_key->phy.priority = skb->priority;
break;
case OVS_KEY_ATTR_SKB_MARK:
- skb->mark = nla_get_u32(nested_attr);
+ SET_MASKED(skb->mark, nla_get_u32(a), *get_mask(a, u32 *));
+ flow_key->phy.skb_mark = skb->mark;
break;
case OVS_KEY_ATTR_TUNNEL_INFO:
- OVS_CB(skb)->tun_info = nla_data(nested_attr);
+ /* Masked data not supported for tunnel. */
+ err = -EINVAL;
break;
case OVS_KEY_ATTR_ETHERNET:
- err = set_eth_addr(skb, nla_data(nested_attr));
+ err = set_eth_addr(skb, flow_key, nla_data(a),
+ get_mask(a, struct ovs_key_ethernet *));
break;
case OVS_KEY_ATTR_IPV4:
- err = set_ipv4(skb, nla_data(nested_attr));
+ err = set_ipv4(skb, flow_key, nla_data(a),
+ get_mask(a, struct ovs_key_ipv4 *));
break;
case OVS_KEY_ATTR_IPV6:
- err = set_ipv6(skb, nla_data(nested_attr));
+ err = set_ipv6(skb, flow_key, nla_data(a),
+ get_mask(a, struct ovs_key_ipv6 *));
break;
case OVS_KEY_ATTR_TCP:
- err = set_tcp(skb, nla_data(nested_attr));
+ err = set_tcp(skb, flow_key, nla_data(a),
+ get_mask(a, struct ovs_key_tcp *));
break;
case OVS_KEY_ATTR_UDP:
- err = set_udp(skb, nla_data(nested_attr));
+ err = set_udp(skb, flow_key, nla_data(a),
+ get_mask(a, struct ovs_key_udp *));
break;
case OVS_KEY_ATTR_SCTP:
- err = set_sctp(skb, nla_data(nested_attr));
+ err = set_sctp(skb, flow_key, nla_data(a),
+ get_mask(a, struct ovs_key_sctp *));
break;
case OVS_KEY_ATTR_MPLS:
- err = set_mpls(skb, nla_data(nested_attr));
+ err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
+ __be32 *));
break;
}
}
static int execute_recirc(struct datapath *dp, struct sk_buff *skb,
- const struct nlattr *a)
+ struct sw_flow_key *key,
+ const struct nlattr *a, int rem)
{
- struct sw_flow_key recirc_key;
- int err;
+ struct deferred_action *da;
- err = ovs_flow_key_extract_recirc(nla_get_u32(a), OVS_CB(skb)->pkt_key,
- skb, &recirc_key);
- if (err) {
- kfree_skb(skb);
- return err;
+ if (!is_flow_key_valid(key)) {
+ int err;
+
+ err = ovs_flow_key_update(skb, key);
+ if (err)
+ return 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);
+
+ /* Skip the recirc action when out of memory, but
+ * continue on with the rest of the action list.
+ */
+ if (!skb)
+ return 0;
}
+ da = add_deferred_actions(skb, key, NULL);
+ if (da) {
+ da->pkt_key.recirc_id = nla_get_u32(a);
+ } else {
+ kfree_skb(skb);
- ovs_dp_process_packet_with_key(skb, &recirc_key, true);
+ if (net_ratelimit())
+ pr_warn("%s: deferred action limit reached, drop recirc action\n",
+ ovs_dp_name(dp));
+ }
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)
+ 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. */
+ * is slightly obscure just to avoid that.
+ */
int prev_port = -1;
const struct nlattr *a;
int rem;
break;
case OVS_ACTION_ATTR_USERSPACE:
- output_userspace(dp, skb, a);
+ output_userspace(dp, skb, key, a, attr, len);
break;
case OVS_ACTION_ATTR_HASH:
- execute_hash(skb, a);
+ execute_hash(skb, key, a);
break;
case OVS_ACTION_ATTR_PUSH_MPLS:
- err = push_mpls(skb, nla_data(a));
+ err = push_mpls(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_POP_MPLS:
- err = pop_mpls(skb, nla_get_be16(a));
+ err = pop_mpls(skb, key, nla_get_be16(a));
break;
case OVS_ACTION_ATTR_PUSH_VLAN:
- err = push_vlan(skb, nla_data(a));
- if (unlikely(err)) /* skb already freed. */
- return err;
+ err = push_vlan(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_POP_VLAN:
- err = pop_vlan(skb);
+ err = pop_vlan(skb, key);
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);
-
+ case OVS_ACTION_ATTR_RECIRC:
+ err = execute_recirc(dp, skb, key, a, rem);
+ if (nla_is_last(a, rem)) {
+ /* 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, nla_data(a));
+ err = execute_set_action(skb, key, nla_data(a));
+ break;
+
+ case OVS_ACTION_ATTR_SET_MASKED:
+ case OVS_ACTION_ATTR_SET_TO_MASKED:
+ err = execute_masked_set_action(skb, key, nla_data(a));
break;
case OVS_ACTION_ATTR_SAMPLE:
- err = sample(dp, skb, a);
+ err = sample(dp, skb, key, a, attr, len);
break;
}
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.
- *
- * 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 stack_cost; /* loop stack cost. */
- bool looping; /* Loop detected? */
-};
-
-static DEFINE_PER_CPU(struct loop_counter, loop_counters);
-
-static int loop_suppress(struct datapath *dp, struct sw_flow_actions *actions)
+static void process_deferred_actions(struct datapath *dp)
{
- if (net_ratelimit())
- pr_warn("%s: flow loop detected, dropping\n",
- ovs_dp_name(dp));
- actions->actions_len = 0;
- return -ELOOP;
+ struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+
+ /* Do not touch the FIFO in case there is no deferred actions. */
+ if (action_fifo_is_empty(fifo))
+ return;
+
+ /* Finishing executing all deferred actions. */
+ do {
+ struct deferred_action *da = action_fifo_get(fifo);
+ struct sk_buff *skb = da->skb;
+ struct sw_flow_key *key = &da->pkt_key;
+ const struct nlattr *actions = da->actions;
+
+ if (actions)
+ do_execute_actions(dp, skb, key, actions,
+ nla_len(actions));
+ else
+ ovs_dp_process_packet(skb, key);
+ } while (!action_fifo_is_empty(fifo));
+
+ /* Reset FIFO for the next packet. */
+ action_fifo_init(fifo);
}
/* Execute a list of actions against '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);
- 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);
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
+ 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));
+
kfree_skb(skb);
- goto out_loop;
+ return -ELOOP;
}
- OVS_CB(skb)->tun_info = NULL;
- error = do_execute_actions(dp, skb, acts->actions, acts->actions_len);
+ this_cpu_inc(exec_actions_level);
+ err = do_execute_actions(dp, skb, key,
+ acts->actions, acts->actions_len);
+
+ if (!level)
+ 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.
+ */
+ return err;
+}
- /* Check whether sub-actions looped too much. */
- if (unlikely(loop->looping))
- error = loop_suppress(dp, acts);
+int action_fifos_init(void)
+{
+ action_fifos = alloc_percpu(struct action_fifo);
+ if (!action_fifos)
+ return -ENOMEM;
-out_loop:
- /* Decrement loop stack cost. */
- loop->stack_cost -= stack_cost;
- if (!loop->stack_cost)
- loop->looping = false;
+ return 0;
+}
- return error;
+void action_fifos_exit(void)
+{
+ free_percpu(action_fifos);
}