summaryrefslogtreecommitdiff
path: root/net/openvswitch/actions.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch/actions.c')
-rw-r--r--net/openvswitch/actions.c324
1 files changed, 146 insertions, 178 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index ca3ebfdb3023..792ca44a461d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -17,71 +17,38 @@
#include <linux/if_vlan.h>
#include <net/dst.h>
+#include <net/gso.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/mpls.h>
+
+#if IS_ENABLED(CONFIG_PSAMPLE)
+#include <net/psample.h>
+#endif
+
#include <net/sctp/checksum.h>
#include "datapath.h"
+#include "drop.h"
#include "flow.h"
#include "conntrack.h"
#include "vport.h"
#include "flow_netlink.h"
#include "openvswitch_trace.h"
-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;
-};
-
-#define MAX_L2_LEN (VLAN_ETH_HLEN + 3 * MPLS_HLEN)
-struct ovs_frag_data {
- unsigned long dst;
- struct vport *vport;
- struct ovs_skb_cb cb;
- __be16 inner_protocol;
- 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];
-};
-
-static DEFINE_PER_CPU(struct ovs_frag_data, ovs_frag_data_storage);
-
-#define DEFERRED_ACTION_FIFO_SIZE 10
-#define OVS_RECURSION_LIMIT 5
-#define OVS_DEFERRED_ACTION_THRESHOLD (OVS_RECURSION_LIMIT - 2)
-struct action_fifo {
- int head;
- int tail;
- /* Deferred action fifo queue storage. */
- 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;
-static struct action_flow_keys __percpu *flow_keys;
-static DEFINE_PER_CPU(int, exec_actions_level);
+struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
/* 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 ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
+ struct action_flow_keys *keys = &ovs_pcpu->flow_keys;
+ int level = ovs_pcpu->exec_level;
struct sw_flow_key *key = NULL;
if (level <= OVS_DEFERRED_ACTION_THRESHOLD) {
@@ -125,10 +92,9 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
const struct nlattr *actions,
const int actions_len)
{
- struct action_fifo *fifo;
+ struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
struct deferred_action *da;
- fifo = this_cpu_ptr(action_fifos);
da = action_fifo_put(fifo);
if (da) {
da->skb = skb;
@@ -230,14 +196,18 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key)
static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key,
const struct ovs_action_push_vlan *vlan)
{
+ int err;
+
if (skb_vlan_tag_present(skb)) {
invalidate_flow_key(key);
} 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_CFI_MASK);
+ err = skb_vlan_push(skb, vlan->vlan_tpid,
+ ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK);
+ skb_reset_mac_len(skb);
+ return err;
}
/* 'src' is already properly masked. */
@@ -309,11 +279,18 @@ static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
return 0;
}
-static int push_nsh(struct sk_buff *skb, struct sw_flow_key *key,
- const struct nshhdr *nh)
+static noinline_for_stack int push_nsh(struct sk_buff *skb,
+ struct sw_flow_key *key,
+ const struct nlattr *a)
{
+ u8 buffer[NSH_HDR_MAX_LEN];
+ struct nshhdr *nh = (struct nshhdr *)buffer;
int err;
+ err = nsh_hdr_from_nlattr(a, nh, NSH_HDR_MAX_LEN);
+ if (err)
+ return err;
+
err = nsh_push(skb, nh);
if (err)
return err;
@@ -595,69 +572,6 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
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)
@@ -776,11 +690,11 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
static int ovs_vport_output(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
- struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
+ struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
struct vport *vport = data->vport;
if (skb_cow_head(skb, data->l2_len) < 0) {
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_NOMEM);
return -ENOMEM;
}
@@ -828,7 +742,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
- data = this_cpu_ptr(&ovs_frag_data_storage);
+ data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
data->dst = skb->_skb_refdst;
data->vport = vport;
data->cb = *OVS_CB(skb);
@@ -851,6 +765,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
struct sk_buff *skb, u16 mru,
struct sw_flow_key *key)
{
+ enum ovs_drop_reason reason;
u16 orig_network_offset = 0;
if (eth_p_mpls(skb->protocol)) {
@@ -860,6 +775,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
if (skb_network_offset(skb) > MAX_L2_LEN) {
OVS_NLERR(1, "L2 header too long to fragment");
+ reason = OVS_DROP_FRAG_L2_TOO_LONG;
goto err;
}
@@ -869,7 +785,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
prepare_frag(vport, skb, orig_network_offset,
ovs_key_mac_proto(key));
- dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL, 1,
+ dst_init(&ovs_rt.dst, &ovs_dst_ops, NULL,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_rt.dst.dev = vport->dev;
@@ -886,7 +802,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
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_init(&ovs_rt.dst, &ovs_dst_ops, NULL,
DST_OBSOLETE_NONE, DST_NOCOUNT);
ovs_rt.dst.dev = vport->dev;
@@ -900,12 +816,13 @@ static void ovs_fragment(struct net *net, struct vport *vport,
WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
ovs_vport_name(vport), ntohs(key->eth.type), mru,
vport->dev->mtu);
+ reason = OVS_DROP_FRAG_INVALID_PROTO;
goto err;
}
return;
err:
- kfree_skb(skb);
+ ovs_kfree_skb_reason(skb, reason);
}
static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
@@ -913,7 +830,9 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
{
struct vport *vport = ovs_vport_rcu(dp, out_port);
- if (likely(vport)) {
+ if (likely(vport &&
+ netif_running(vport->dev) &&
+ netif_carrier_ok(vport->dev))) {
u16 mru = OVS_CB(skb)->mru;
u32 cutlen = OVS_CB(skb)->cutlen;
@@ -932,10 +851,10 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port,
ovs_fragment(net, vport, skb, mru, key);
} else {
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_PKT_TOO_BIG);
}
} else {
- kfree_skb(skb);
+ kfree_skb_reason(skb, SKB_DROP_REASON_DEV_READY);
}
}
@@ -952,16 +871,17 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
upcall.cmd = OVS_PACKET_CMD_ACTION;
upcall.mru = OVS_CB(skb)->mru;
- for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
- a = nla_next(a, &rem)) {
+ nla_for_each_nested(a, attr, rem) {
switch (nla_type(a)) {
case OVS_USERSPACE_ATTR_USERDATA:
upcall.userdata = a;
break;
case OVS_USERSPACE_ATTR_PID:
- if (dp->user_features &
- OVS_DP_F_DISPATCH_UPCALL_PER_CPU)
+ if (OVS_CB(skb)->upcall_pid)
+ upcall.portid = OVS_CB(skb)->upcall_pid;
+ else if (dp->user_features &
+ OVS_DP_F_DISPATCH_UPCALL_PER_CPU)
upcall.portid =
ovs_dp_get_upcall_portid(dp,
smp_processor_id());
@@ -1009,7 +929,7 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb,
return clone_execute(dp, skb, key, 0, nla_data(actions),
nla_len(actions), true, false);
- consume_skb(skb);
+ ovs_kfree_skb_reason(skb, OVS_DROP_IP_TTL);
return 0;
}
@@ -1025,23 +945,33 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
struct nlattr *sample_arg;
int rem = nla_len(attr);
const struct sample_arg *arg;
+ u32 init_probability;
bool clone_flow_key;
+ int err;
/* 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);
+ init_probability = OVS_CB(skb)->probability;
if ((arg->probability != U32_MAX) &&
(!arg->probability || get_random_u32() > arg->probability)) {
if (last)
- consume_skb(skb);
+ ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION);
return 0;
}
+ OVS_CB(skb)->probability = arg->probability;
+
clone_flow_key = !arg->exec;
- return clone_execute(dp, skb, key, 0, actions, rem, last,
- clone_flow_key);
+ err = clone_execute(dp, skb, key, 0, actions, rem, last,
+ clone_flow_key);
+
+ if (!last)
+ OVS_CB(skb)->probability = init_probability;
+
+ return err;
}
/* When 'last' is true, clone() should always consume the 'skb'.
@@ -1072,8 +1002,16 @@ static void execute_hash(struct sk_buff *skb, struct sw_flow_key *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);
+ if (hash_act->hash_alg == OVS_HASH_ALG_L4) {
+ /* OVS_HASH_ALG_L4 hasing type. */
+ hash = skb_get_hash(skb);
+ } else if (hash_act->hash_alg == OVS_HASH_ALG_SYM_L4) {
+ /* OVS_HASH_ALG_SYM_L4 hashing type. NOTE: this doesn't
+ * extend past an encapsulated header.
+ */
+ hash = __skb_get_hash_symmetric(skb);
+ }
+
hash = jhash_1word(hash, hash_act->hash_basis);
if (!hash)
hash = 0x1;
@@ -1129,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb,
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 *));
@@ -1169,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb,
case OVS_KEY_ATTR_CT_LABELS:
case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4:
case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6:
+ case OVS_KEY_ATTR_NSH:
err = -EINVAL;
break;
}
@@ -1273,6 +1208,44 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key)
return 0;
}
+#if IS_ENABLED(CONFIG_PSAMPLE)
+static void execute_psample(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *attr)
+{
+ struct psample_group psample_group = {};
+ struct psample_metadata md = {};
+ const struct nlattr *a;
+ u32 rate;
+ int rem;
+
+ nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) {
+ switch (nla_type(a)) {
+ case OVS_PSAMPLE_ATTR_GROUP:
+ psample_group.group_num = nla_get_u32(a);
+ break;
+
+ case OVS_PSAMPLE_ATTR_COOKIE:
+ md.user_cookie = nla_data(a);
+ md.user_cookie_len = nla_len(a);
+ break;
+ }
+ }
+
+ psample_group.net = ovs_dp_get_net(dp);
+ md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex;
+ md.trunc_size = skb->len - OVS_CB(skb)->cutlen;
+ md.rate_as_probability = 1;
+
+ rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX;
+
+ psample_sample_packet(&psample_group, skb, rate, &md);
+}
+#else
+static void execute_psample(struct datapath *dp, struct sk_buff *skb,
+ const struct nlattr *attr)
+{}
+#endif
+
/* Execute a list of actions against 'skb'. */
static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
struct sw_flow_key *key,
@@ -1288,6 +1261,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
if (trace_ovs_do_execute_action_enabled())
trace_ovs_do_execute_action(dp, skb, key, a, rem);
+ /* Actions that rightfully have to consume the skb should do it
+ * and return directly.
+ */
switch (nla_type(a)) {
case OVS_ACTION_ATTR_OUTPUT: {
int port = nla_get_u32(a);
@@ -1323,6 +1299,10 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
output_userspace(dp, skb, key, a, attr,
len, OVS_CB(skb)->cutlen);
OVS_CB(skb)->cutlen = 0;
+ if (nla_is_last(a, rem)) {
+ consume_skb(skb);
+ return 0;
+ }
break;
case OVS_ACTION_ATTR_HASH:
@@ -1419,17 +1399,9 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
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);
+ case OVS_ACTION_ATTR_PUSH_NSH:
+ err = push_nsh(skb, key, nla_data(a));
break;
- }
case OVS_ACTION_ATTR_POP_NSH:
err = pop_nsh(skb, key);
@@ -1437,7 +1409,7 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
case OVS_ACTION_ATTR_METER:
if (ovs_meter_execute(dp, skb, key, nla_get_u32(a))) {
- consume_skb(skb);
+ ovs_kfree_skb_reason(skb, OVS_DROP_METER);
return 0;
}
break;
@@ -1468,15 +1440,33 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
return dec_ttl_exception_handler(dp, skb,
key, a);
break;
+
+ case OVS_ACTION_ATTR_DROP: {
+ enum ovs_drop_reason reason = nla_get_u32(a)
+ ? OVS_DROP_EXPLICIT_WITH_ERROR
+ : OVS_DROP_EXPLICIT;
+
+ ovs_kfree_skb_reason(skb, reason);
+ return 0;
+ }
+
+ case OVS_ACTION_ATTR_PSAMPLE:
+ execute_psample(dp, skb, a);
+ OVS_CB(skb)->cutlen = 0;
+ if (nla_is_last(a, rem)) {
+ consume_skb(skb);
+ return 0;
+ }
+ break;
}
if (unlikely(err)) {
- kfree_skb(skb);
+ ovs_kfree_skb_reason(skb, OVS_DROP_ACTION_ERROR);
return err;
}
}
- consume_skb(skb);
+ ovs_kfree_skb_reason(skb, OVS_DROP_LAST_ACTION);
return 0;
}
@@ -1510,16 +1500,15 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
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);
+ __this_cpu_inc(ovs_pcpu_storage->exec_level);
err = do_execute_actions(dp, skb, clone,
actions, len);
if (clone_flow_key)
- __this_cpu_dec(exec_actions_level);
+ __this_cpu_dec(ovs_pcpu_storage->exec_level);
} else { /* Recirc action */
clone->recirc_id = recirc_id;
ovs_dp_process_packet(skb, clone);
@@ -1538,7 +1527,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
/* Out of per CPU action FIFO space. Drop the 'skb' and
* log an error.
*/
- kfree_skb(skb);
+ ovs_kfree_skb_reason(skb, OVS_DROP_DEFERRED_LIMIT);
if (net_ratelimit()) {
if (actions) { /* Sample action */
@@ -1555,7 +1544,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
static void process_deferred_actions(struct datapath *dp)
{
- struct action_fifo *fifo = this_cpu_ptr(action_fifos);
+ struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
/* Do not touch the FIFO in case there is no deferred actions. */
if (action_fifo_is_empty(fifo))
@@ -1586,11 +1575,11 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
{
int err, level;
- level = __this_cpu_inc_return(exec_actions_level);
+ level = __this_cpu_inc_return(ovs_pcpu_storage->exec_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);
+ ovs_kfree_skb_reason(skb, OVS_DROP_RECURSION_LIMIT);
err = -ENETDOWN;
goto out;
}
@@ -1603,27 +1592,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
process_deferred_actions(dp);
out:
- __this_cpu_dec(exec_actions_level);
+ __this_cpu_dec(ovs_pcpu_storage->exec_level);
return err;
}
-
-int action_fifos_init(void)
-{
- action_fifos = alloc_percpu(struct action_fifo);
- 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);
-}