net: openvswitch: Support masked set actions.
OVS userspace already probes the openvswitch kernel module for
OVS_ACTION_ATTR_SET_MASKED support. This patch adds the kernel module
implementation of masked set actions.
The existing set action sets many fields at once. When only a subset
of the IP header fields, for example, should be modified, all the IP
fields need to be exact matched so that the other field values can be
copied to the set action. A masked set action allows modification of
an arbitrary subset of the supported header bits without requiring the
rest to be matched.
Masked set action is now supported for all writeable key types, except
for the tunnel key. The set tunnel action is an exception as any
input tunnel info is cleared before action processing starts, so there
is no tunnel info to mask.
The kernel module converts all (non-tunnel) set actions to masked set
actions. This makes action processing more uniform, and results in
less branching and duplicating the action processing code. When
returning actions to userspace, the fully masked set actions are
converted back to normal set actions. We use a kernel internal action
code to be able to tell the userspace provided and converted masked
set actions apart.
Signed-off-by: Jarno Rajahalme <jrajahalme@nicira.com>
Acked-by: Pravin B Shelar <pshelar@nicira.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index b4cffe6..b491c1c 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -185,10 +185,15 @@
return 0;
}
-static int set_mpls(struct sk_buff *skb, struct sw_flow_key *key,
- 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 lse;
int err;
err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN);
@@ -196,14 +201,16 @@
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;
- key->mpls.top_lse = *mpls_lse;
+ *stack = lse;
+ flow_key->mpls.top_lse = lse;
return 0;
}
@@ -230,23 +237,39 @@
ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
}
-static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *key,
- const struct ovs_key_ethernet *eth_key)
+/* 'src' is already properly masked. */
+static void ether_addr_copy_masked(u8 *dst_, const u8 *src_, const u8 *mask_)
+{
+ u16 *dst = (u16 *)dst_;
+ const u16 *src = (const u16 *)src_;
+ const u16 *mask = (const u16 *)mask_;
+
+ 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, struct sw_flow_key *flow_key,
+ const struct ovs_key_ethernet *key,
+ const struct ovs_key_ethernet *mask)
{
int err;
+
err = skb_ensure_writable(skb, ETH_HLEN);
if (unlikely(err))
return err;
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_ALEN * 2);
- ether_addr_copy(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(key->eth.src, eth_key->eth_src);
- ether_addr_copy(key->eth.dst, eth_key->eth_dst);
+ 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;
}
@@ -304,6 +327,15 @@
}
}
+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)
@@ -315,29 +347,29 @@
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, struct sw_flow_key *key,
- 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 = skb_ensure_writable(skb, skb_network_offset(skb) +
@@ -347,36 +379,49 @@
nh = ip_hdr(skb);
- if (ipv4_key->ipv4_src != nh->saddr) {
- set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
- key->ipv4.addr.src = ipv4_key->ipv4_src;
- }
+ /* 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_dst != nh->daddr) {
- set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
- key->ipv4.addr.dst = ipv4_key->ipv4_dst;
+ 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_tos != nh->tos) {
- ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
- key->ip.tos = nh->tos;
+ if (unlikely(new_addr != nh->daddr)) {
+ set_ip_addr(skb, nh, &nh->daddr, new_addr);
+ flow_key->ipv4.addr.dst = new_addr;
+ }
}
-
- if (ipv4_key->ipv4_ttl != nh->ttl) {
- set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
- key->ip.ttl = ipv4_key->ipv4_ttl;
+ 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, struct sw_flow_key *key,
- 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 = skb_ensure_writable(skb, skb_network_offset(skb) +
sizeof(struct ipv6hdr));
@@ -384,71 +429,77 @@
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);
- memcpy(&key->ipv6.addr.src, ipv6_key->ipv6_src,
- sizeof(ipv6_key->ipv6_src));
+ /* 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 (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 (memcmp(ipv6_key->ipv6_dst, daddr, sizeof(ipv6_key->ipv6_dst))) {
+ if (is_ipv6_mask_nonzero(mask->ipv6_dst)) {
unsigned int offset = 0;
int flags = IP6_FH_F_SKIP_RH;
bool recalc_csum = true;
+ __be32 *daddr = (__be32 *)&nh->daddr;
+ __be32 masked[4];
- if (ipv6_ext_hdr(nh->nexthdr))
- recalc_csum = ipv6_find_hdr(skb, &offset,
- NEXTHDR_ROUTING, NULL,
- &flags) != NEXTHDR_ROUTING;
+ mask_ipv6_addr(daddr, key->ipv6_dst, mask->ipv6_dst, masked);
- set_ipv6_addr(skb, ipv6_key->ipv6_proto, daddr,
- ipv6_key->ipv6_dst, recalc_csum);
- memcpy(&key->ipv6.addr.dst, ipv6_key->ipv6_dst,
- sizeof(ipv6_key->ipv6_dst));
+ 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));
+ }
}
-
- set_ipv6_tc(nh, ipv6_key->ipv6_tclass);
- key->ip.tos = ipv6_get_dsfield(nh);
-
- set_ipv6_fl(nh, ntohl(ipv6_key->ipv6_label));
- key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
-
- nh->hop_limit = ipv6_key->ipv6_hlimit;
- key->ip.ttl = ipv6_key->ipv6_hlimit;
+ 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;
+ }
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)
+ __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, struct sw_flow_key *key,
- 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 = skb_ensure_writable(skb, skb_transport_offset(skb) +
@@ -457,23 +508,40 @@
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);
- key->tp.src = 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);
- key->tp.dst = udp_port_key->udp_dst;
- }
+ skb_clear_hash(skb);
return 0;
}
-static int set_tcp(struct sk_buff *skb, struct sw_flow_key *key,
- 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 = skb_ensure_writable(skb, skb_transport_offset(skb) +
@@ -482,50 +550,49 @@
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);
- key->tp.src = tcp_port_key->tcp_src;
+ 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;
}
-
- if (tcp_port_key->tcp_dst != th->dest) {
- set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
- key->tp.dst = tcp_port_key->tcp_dst;
+ 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, struct sw_flow_key *key,
- 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)
{
- struct sctphdr *sh;
- int err;
unsigned int sctphoff = skb_transport_offset(skb);
+ struct sctphdr *sh;
+ __le32 old_correct_csum, new_csum, old_csum;
+ int err;
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);
- key->tp.src = sctp_port_key->sctp_src;
- key->tp.dst = sctp_port_key->sctp_dst;
- }
+ skb_clear_hash(skb);
+ flow_key->tp.src = sh->source;
+ flow_key->tp.dst = sh->dest;
return 0;
}
@@ -653,52 +720,77 @@
key->ovs_flow_hash = hash;
}
-static int execute_set_action(struct sk_buff *skb, struct sw_flow_key *key,
- const struct nlattr *nested_attr)
+static int execute_set_action(struct sk_buff *skb,
+ 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);
- key->phy.priority = skb->priority;
+ 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);
- key->phy.skb_mark = skb->mark;
+ 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)->egress_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, key, 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, key, 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, key, 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, key, 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, key, 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, key, 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, key, nla_data(nested_attr));
+ err = set_mpls(skb, flow_key, nla_data(a), get_mask(a,
+ __be32 *));
break;
}
@@ -818,6 +910,11 @@
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, key, a);
break;