summaryrefslogtreecommitdiff
path: root/net/xfrm
diff options
context:
space:
mode:
Diffstat (limited to 'net/xfrm')
-rw-r--r--net/xfrm/espintcp.c4
-rw-r--r--net/xfrm/xfrm_compat.c6
-rw-r--r--net/xfrm/xfrm_device.c2
-rw-r--r--net/xfrm/xfrm_input.c2
-rw-r--r--net/xfrm/xfrm_interface_core.c7
-rw-r--r--net/xfrm/xfrm_output.c43
-rw-r--r--net/xfrm/xfrm_policy.c15
-rw-r--r--net/xfrm/xfrm_replay.c10
-rw-r--r--net/xfrm/xfrm_state.c335
-rw-r--r--net/xfrm/xfrm_user.c103
10 files changed, 440 insertions, 87 deletions
diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c
index fe82e2d07300..fc7a603b04f1 100644
--- a/net/xfrm/espintcp.c
+++ b/net/xfrm/espintcp.c
@@ -171,8 +171,10 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb)
struct espintcp_ctx *ctx = espintcp_getctx(sk);
if (skb_queue_len(&ctx->out_queue) >=
- READ_ONCE(net_hotdata.max_backlog))
+ READ_ONCE(net_hotdata.max_backlog)) {
+ kfree_skb(skb);
return -ENOBUFS;
+ }
__skb_queue_tail(&ctx->out_queue, skb);
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
index 91357ccaf4af..5b9ee63e30b6 100644
--- a/net/xfrm/xfrm_compat.c
+++ b/net/xfrm/xfrm_compat.c
@@ -132,6 +132,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
[XFRMA_MTIMER_THRESH] = { .type = NLA_U32 },
[XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT),
[XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 },
+ [XFRMA_SA_PCPU] = { .type = NLA_U32 },
};
static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
@@ -282,9 +283,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
case XFRMA_MTIMER_THRESH:
case XFRMA_SA_DIR:
case XFRMA_NAT_KEEPALIVE_INTERVAL:
+ case XFRMA_SA_PCPU:
return xfrm_nla_cpy(dst, src, nla_len(src));
default:
- BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL);
+ BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_PCPU);
pr_warn_once("unsupported nla_type %d\n", src->nla_type);
return -EOPNOTSUPP;
}
@@ -439,7 +441,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
int err;
if (type > XFRMA_MAX) {
- BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL);
+ BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_PCPU);
NL_SET_ERR_MSG(extack, "Bad attribute");
return -EOPNOTSUPP;
}
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index b33c4591e09a..32ad8f3fc81e 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -373,7 +373,6 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
xdo->dev = dev;
netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC);
- xdo->real_dev = dev;
xdo->type = XFRM_DEV_OFFLOAD_PACKET;
switch (dir) {
case XFRM_POLICY_IN:
@@ -395,7 +394,6 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
err = dev->xfrmdev_ops->xdo_dev_policy_add(xp, extack);
if (err) {
xdo->dev = NULL;
- xdo->real_dev = NULL;
xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
xdo->dir = 0;
netdev_put(dev, &xdo->dev_tracker);
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 749e7eea99e4..841a60a6fbfe 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -572,7 +572,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
goto drop;
}
- x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
+ x = xfrm_input_state_lookup(net, mark, daddr, spi, nexthdr, family);
if (x == NULL) {
secpath_reset(skb);
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 98f1e2b67c76..b95d882f9dbc 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -874,7 +874,7 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
return -EINVAL;
}
- if (p.collect_md) {
+ if (p.collect_md || xi->p.collect_md) {
NL_SET_ERR_MSG(extack, "collect_md can't be changed");
return -EINVAL;
}
@@ -885,11 +885,6 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
} else {
if (xi->dev != dev)
return -EEXIST;
- if (xi->p.collect_md) {
- NL_SET_ERR_MSG(extack,
- "device can't be changed to collect_md");
- return -EINVAL;
- }
}
return xfrmi_update(xi, &p);
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index e5722c95b8bb..a30538a980cc 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -610,6 +610,40 @@ out:
}
EXPORT_SYMBOL_GPL(xfrm_output_resume);
+static int xfrm_dev_direct_output(struct sock *sk, struct xfrm_state *x,
+ struct sk_buff *skb)
+{
+ struct dst_entry *dst = skb_dst(skb);
+ struct net *net = xs_net(x);
+ int err;
+
+ dst = skb_dst_pop(skb);
+ if (!dst) {
+ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+ kfree_skb(skb);
+ return -EHOSTUNREACH;
+ }
+ skb_dst_set(skb, dst);
+ nf_reset_ct(skb);
+
+ err = skb_dst(skb)->ops->local_out(net, sk, skb);
+ if (unlikely(err != 1)) {
+ kfree_skb(skb);
+ return err;
+ }
+
+ /* In transport mode, network destination is
+ * directly reachable, while in tunnel mode,
+ * inner packet network may not be. In packet
+ * offload type, HW is responsible for hard
+ * header packet mangling so directly xmit skb
+ * to netdevice.
+ */
+ skb->dev = x->xso.dev;
+ __skb_push(skb, skb->dev->hard_header_len);
+ return dev_queue_xmit(skb);
+}
+
static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
return xfrm_output_resume(sk, skb, 1);
@@ -729,6 +763,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
return -EHOSTUNREACH;
}
+ /* Exclusive direct xmit for tunnel mode, as
+ * some filtering or matching rules may apply
+ * in transport mode.
+ */
+ if (x->props.mode == XFRM_MODE_TUNNEL)
+ return xfrm_dev_direct_output(sk, x, skb);
+
return xfrm_output_resume(sk, skb, 0);
}
@@ -752,7 +793,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
skb->encapsulation = 1;
if (skb_is_gso(skb)) {
- if (skb->inner_protocol)
+ if (skb->inner_protocol && x->props.mode == XFRM_MODE_TUNNEL)
return xfrm_output_gso(net, sk, skb);
skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index a2ea9dbac90b..2c42d83fbaa2 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -434,6 +434,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp)
if (policy) {
write_pnet(&policy->xp_net, net);
INIT_LIST_HEAD(&policy->walk.all);
+ INIT_HLIST_HEAD(&policy->state_cache_list);
INIT_HLIST_NODE(&policy->bydst);
INIT_HLIST_NODE(&policy->byidx);
rwlock_init(&policy->lock);
@@ -475,6 +476,9 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
static void xfrm_policy_kill(struct xfrm_policy *policy)
{
+ struct net *net = xp_net(policy);
+ struct xfrm_state *x;
+
xfrm_dev_policy_delete(policy);
write_lock_bh(&policy->lock);
@@ -490,6 +494,13 @@ static void xfrm_policy_kill(struct xfrm_policy *policy)
if (del_timer(&policy->timer))
xfrm_pol_put(policy);
+ /* XXX: Flush state cache */
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ hlist_for_each_entry_rcu(x, &policy->state_cache_list, state_cache) {
+ hlist_del_init_rcu(&x->state_cache);
+ }
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
xfrm_pol_put(policy);
}
@@ -1570,6 +1581,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
struct xfrm_policy *delpol;
struct hlist_head *chain;
+ /* Sanitize mark before store */
+ policy->mark.v &= policy->mark.m;
+
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);
if (chain)
@@ -3275,6 +3289,7 @@ no_transform:
dst_release(dst);
dst = dst_orig;
}
+
ok:
xfrm_pols_put(pols, drop_pols);
if (dst && dst->xfrm &&
diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c
index bc56c6305725..235bbefc2aba 100644
--- a/net/xfrm/xfrm_replay.c
+++ b/net/xfrm/xfrm_replay.c
@@ -714,10 +714,12 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff
oseq += skb_shinfo(skb)->gso_segs;
}
- if (unlikely(xo->seq.low < replay_esn->oseq)) {
- XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi;
- xo->seq.hi = oseq_hi;
- replay_esn->oseq_hi = oseq_hi;
+ if (unlikely(oseq < replay_esn->oseq)) {
+ replay_esn->oseq_hi = ++oseq_hi;
+ if (xo->seq.low < replay_esn->oseq) {
+ XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi;
+ xo->seq.hi = oseq_hi;
+ }
if (replay_esn->oseq_hi == 0) {
replay_esn->oseq--;
replay_esn->oseq_hi--;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 37478d36a8df..6f99fd2d966c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -34,6 +34,8 @@
#define xfrm_state_deref_prot(table, net) \
rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+#define xfrm_state_deref_check(table, net) \
+ rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
static void xfrm_state_gc_task(struct work_struct *work);
@@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net,
u32 reqid,
unsigned short family)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
}
@@ -70,6 +74,8 @@ static inline unsigned int xfrm_src_hash(struct net *net,
const xfrm_address_t *saddr,
unsigned short family)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
}
@@ -77,11 +83,15 @@ static inline unsigned int
xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
__be32 spi, u8 proto, unsigned short family)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
}
static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
}
@@ -665,6 +675,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
refcount_set(&x->refcnt, 1);
atomic_set(&x->tunnel_users, 0);
INIT_LIST_HEAD(&x->km.all);
+ INIT_HLIST_NODE(&x->state_cache);
INIT_HLIST_NODE(&x->bydst);
INIT_HLIST_NODE(&x->bysrc);
INIT_HLIST_NODE(&x->byspi);
@@ -679,6 +690,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
x->lft.hard_packet_limit = XFRM_INF;
x->replay_maxage = 0;
x->replay_maxdiff = 0;
+ x->pcpu_num = UINT_MAX;
spin_lock_init(&x->lock);
}
return x;
@@ -743,21 +755,24 @@ int __xfrm_state_delete(struct xfrm_state *x)
if (x->km.state != XFRM_STATE_DEAD) {
x->km.state = XFRM_STATE_DEAD;
+
spin_lock(&net->xfrm.xfrm_state_lock);
list_del(&x->km.all);
hlist_del_rcu(&x->bydst);
hlist_del_rcu(&x->bysrc);
if (x->km.seq)
hlist_del_rcu(&x->byseq);
+ if (!hlist_unhashed(&x->state_cache))
+ hlist_del_rcu(&x->state_cache);
+ if (!hlist_unhashed(&x->state_cache_input))
+ hlist_del_rcu(&x->state_cache_input);
+
if (x->id.spi)
hlist_del_rcu(&x->byspi);
net->xfrm.state_num--;
xfrm_nat_keepalive_state_updated(x);
spin_unlock(&net->xfrm.xfrm_state_lock);
- if (x->encap_sk)
- sock_put(rcu_dereference_raw(x->encap_sk));
-
xfrm_dev_state_delete(x);
/* All xfrm_state objects are created by xfrm_state_alloc.
@@ -1033,16 +1048,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
x->props.family = tmpl->encap_family;
}
-static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
+struct xfrm_hash_state_ptrs {
+ const struct hlist_head *bydst;
+ const struct hlist_head *bysrc;
+ const struct hlist_head *byspi;
+ unsigned int hmask;
+};
+
+static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs)
+{
+ unsigned int sequence;
+
+ do {
+ sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+ ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net);
+ ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net);
+ ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net);
+ ptrs->hmask = net->xfrm.state_hmask;
+ } while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence));
+}
+
+static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs,
+ u32 mark,
const xfrm_address_t *daddr,
__be32 spi, u8 proto,
unsigned short family,
struct xfrm_dev_offload *xdo)
{
- unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+ unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
struct xfrm_state *x;
- hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+ hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
#ifdef CONFIG_XFRM_OFFLOAD
if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) {
if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1076,15 +1113,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
return NULL;
}
-static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs,
+ u32 mark,
const xfrm_address_t *daddr,
__be32 spi, u8 proto,
unsigned short family)
{
- unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+ unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
struct xfrm_state *x;
- hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+ hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
if (x->props.family != family ||
x->id.spi != spi ||
x->id.proto != proto ||
@@ -1101,15 +1139,63 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
return NULL;
}
-static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
+ const xfrm_address_t *daddr,
+ __be32 spi, u8 proto,
+ unsigned short family)
+{
+ struct xfrm_hash_state_ptrs state_ptrs;
+ struct hlist_head *state_cache_input;
+ struct xfrm_state *x = NULL;
+
+ state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);
+
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
+ if (x->props.family != family ||
+ x->id.spi != spi ||
+ x->id.proto != proto ||
+ !xfrm_addr_equal(&x->id.daddr, daddr, family))
+ continue;
+
+ if ((mark & x->mark.m) != x->mark.v)
+ continue;
+ if (!xfrm_state_hold_rcu(x))
+ continue;
+ goto out;
+ }
+
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
+
+ if (x && x->km.state == XFRM_STATE_VALID) {
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ if (hlist_unhashed(&x->state_cache_input)) {
+ hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
+ } else {
+ hlist_del_rcu(&x->state_cache_input);
+ hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
+ }
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ }
+
+out:
+ rcu_read_unlock();
+ return x;
+}
+EXPORT_SYMBOL(xfrm_input_state_lookup);
+
+static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs,
+ u32 mark,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
- unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
+ unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask);
struct xfrm_state *x;
- hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
+ hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) {
if (x->props.family != family ||
x->id.proto != proto ||
!xfrm_addr_equal(&x->id.daddr, daddr, family) ||
@@ -1129,14 +1215,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
static inline struct xfrm_state *
__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct net *net = xs_net(x);
u32 mark = x->mark.v & x->mark.m;
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
if (use_spi)
- return __xfrm_state_lookup(net, mark, &x->id.daddr,
+ return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr,
x->id.spi, x->id.proto, family);
else
- return __xfrm_state_lookup_byaddr(net, mark,
+ return __xfrm_state_lookup_byaddr(&state_ptrs, mark,
&x->id.daddr,
&x->props.saddr,
x->id.proto, family);
@@ -1153,7 +1242,7 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision)
static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
const struct flowi *fl, unsigned short family,
struct xfrm_state **best, int *acq_in_progress,
- int *error)
+ int *error, unsigned int pcpu_id)
{
/* Resolution logic:
* 1. There is a valid state with matching selector. Done.
@@ -1174,13 +1263,18 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
&fl->u.__fl_common))
return;
+ if (x->pcpu_num != UINT_MAX && x->pcpu_num != pcpu_id)
+ return;
+
if (!*best ||
+ ((*best)->pcpu_num == UINT_MAX && x->pcpu_num == pcpu_id) ||
(*best)->km.dying > x->km.dying ||
((*best)->km.dying == x->km.dying &&
(*best)->curlft.add_time < x->curlft.add_time))
*best = x;
} else if (x->km.state == XFRM_STATE_ACQ) {
- *acq_in_progress = 1;
+ if (!*best || x->pcpu_num == pcpu_id)
+ *acq_in_progress = 1;
} else if (x->km.state == XFRM_STATE_ERROR ||
x->km.state == XFRM_STATE_EXPIRED) {
if ((!x->sel.family ||
@@ -1199,6 +1293,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
unsigned short family, u32 if_id)
{
static xfrm_address_t saddr_wildcard = { };
+ struct xfrm_hash_state_ptrs state_ptrs;
struct net *net = xp_net(pol);
unsigned int h, h_wildcard;
struct xfrm_state *x, *x0, *to_put;
@@ -1209,14 +1304,63 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
unsigned short encap_family = tmpl->encap_family;
unsigned int sequence;
struct km_event c;
+ unsigned int pcpu_id;
+ bool cached = false;
+
+ /* We need the cpu id just as a lookup key,
+ * we don't require it to be stable.
+ */
+ pcpu_id = raw_smp_processor_id();
to_put = NULL;
sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
rcu_read_lock();
- h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
- hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) {
+ if (x->props.family == encap_family &&
+ x->props.reqid == tmpl->reqid &&
+ (mark & x->mark.m) == x->mark.v &&
+ x->if_id == if_id &&
+ !(x->props.flags & XFRM_STATE_WILDRECV) &&
+ xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
+ tmpl->mode == x->props.mode &&
+ tmpl->id.proto == x->id.proto &&
+ (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+ xfrm_state_look_at(pol, x, fl, encap_family,
+ &best, &acquire_in_progress, &error, pcpu_id);
+ }
+
+ if (best)
+ goto cached;
+
+ hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) {
+ if (x->props.family == encap_family &&
+ x->props.reqid == tmpl->reqid &&
+ (mark & x->mark.m) == x->mark.v &&
+ x->if_id == if_id &&
+ !(x->props.flags & XFRM_STATE_WILDRECV) &&
+ xfrm_addr_equal(&x->id.daddr, daddr, encap_family) &&
+ tmpl->mode == x->props.mode &&
+ tmpl->id.proto == x->id.proto &&
+ (tmpl->id.spi == x->id.spi || !tmpl->id.spi))
+ xfrm_state_look_at(pol, x, fl, family,
+ &best, &acquire_in_progress, &error, pcpu_id);
+ }
+
+cached:
+ cached = true;
+ if (best)
+ goto found;
+ else if (error)
+ best = NULL;
+ else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */
+ WARN_ON(1);
+
+ h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask);
+ hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) {
#ifdef CONFIG_XFRM_OFFLOAD
if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1244,13 +1388,14 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, family,
- &best, &acquire_in_progress, &error);
+ &best, &acquire_in_progress, &error, pcpu_id);
}
if (best || acquire_in_progress)
goto found;
- h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
- hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
+ h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid,
+ encap_family, state_ptrs.hmask);
+ hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) {
#ifdef CONFIG_XFRM_OFFLOAD
if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1278,14 +1423,17 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
tmpl->id.proto == x->id.proto &&
(tmpl->id.spi == x->id.spi || !tmpl->id.spi))
xfrm_state_look_at(pol, x, fl, family,
- &best, &acquire_in_progress, &error);
+ &best, &acquire_in_progress, &error, pcpu_id);
}
found:
- x = best;
+ if (!(pol->flags & XFRM_POLICY_CPU_ACQUIRE) ||
+ (best && (best->pcpu_num == pcpu_id)))
+ x = best;
+
if (!x && !error && !acquire_in_progress) {
if (tmpl->id.spi &&
- (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+ (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr,
tmpl->id.spi, tmpl->id.proto,
encap_family,
&pol->xdo)) != NULL) {
@@ -1314,6 +1462,8 @@ found:
xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
memcpy(&x->mark, &pol->mark, sizeof(x->mark));
x->if_id = if_id;
+ if ((pol->flags & XFRM_POLICY_CPU_ACQUIRE) && best)
+ x->pcpu_num = pcpu_id;
error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid);
if (error) {
@@ -1330,7 +1480,6 @@ found:
xso->type = XFRM_DEV_OFFLOAD_PACKET;
xso->dir = xdo->dir;
xso->dev = xdo->dev;
- xso->real_dev = xdo->real_dev;
xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ;
netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC);
error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL);
@@ -1338,7 +1487,6 @@ found:
xso->dir = 0;
netdev_put(xso->dev, &xso->dev_tracker);
xso->dev = NULL;
- xso->real_dev = NULL;
xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
x->km.state = XFRM_STATE_DEAD;
to_put = x;
@@ -1352,6 +1500,7 @@ found:
x->km.state = XFRM_STATE_ACQ;
x->dir = XFRM_SA_DIR_OUT;
list_add(&x->km.all, &net->xfrm.state_all);
+ h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
XFRM_STATE_INSERT(bydst, &x->bydst,
net->xfrm.state_bydst + h,
x->xso.type);
@@ -1359,6 +1508,7 @@ found:
XFRM_STATE_INSERT(bysrc, &x->bysrc,
net->xfrm.state_bysrc + h,
x->xso.type);
+ INIT_HLIST_NODE(&x->state_cache);
if (x->id.spi) {
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
XFRM_STATE_INSERT(byspi, &x->byspi,
@@ -1392,6 +1542,11 @@ found:
x = NULL;
error = -ESRCH;
}
+
+ /* Use the already installed 'fallback' while the CPU-specific
+ * SA acquire is handled*/
+ if (best)
+ x = best;
}
out:
if (x) {
@@ -1402,6 +1557,15 @@ out:
} else {
*err = acquire_in_progress ? -EAGAIN : error;
}
+
+ if (x && x->km.state == XFRM_STATE_VALID && !cached &&
+ (!(pol->flags & XFRM_POLICY_CPU_ACQUIRE) || x->pcpu_num == pcpu_id)) {
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ if (hlist_unhashed(&x->state_cache))
+ hlist_add_head_rcu(&x->state_cache, &pol->state_cache_list);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ }
+
rcu_read_unlock();
if (to_put)
xfrm_state_put(to_put);
@@ -1473,6 +1637,26 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
}
EXPORT_SYMBOL(xfrm_state_lookup_byspi);
+static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 spi, u8 proto)
+{
+ struct xfrm_state *x;
+ unsigned int i;
+
+ rcu_read_lock();
+ for (i = 0; i <= net->xfrm.state_hmask; i++) {
+ hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) {
+ if (x->id.spi == spi && x->id.proto == proto) {
+ if (!xfrm_state_hold_rcu(x))
+ continue;
+ rcu_read_unlock();
+ return x;
+ }
+ }
+ }
+ rcu_read_unlock();
+ return NULL;
+}
+
static void __xfrm_state_insert(struct xfrm_state *x)
{
struct net *net = xs_net(x);
@@ -1480,6 +1664,9 @@ static void __xfrm_state_insert(struct xfrm_state *x)
list_add(&x->km.all, &net->xfrm.state_all);
+ /* Sanitize mark before store */
+ x->mark.v &= x->mark.m;
+
h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
x->props.reqid, x->props.family);
XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
@@ -1524,12 +1711,14 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
unsigned int h;
u32 mark = xnew->mark.v & xnew->mark.m;
u32 if_id = xnew->if_id;
+ u32 cpu_id = xnew->pcpu_num;
h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
if (x->props.family == family &&
x->props.reqid == reqid &&
x->if_id == if_id &&
+ x->pcpu_num == cpu_id &&
(mark & x->mark.m) == x->mark.v &&
xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) &&
xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family))
@@ -1552,7 +1741,7 @@ EXPORT_SYMBOL(xfrm_state_insert);
static struct xfrm_state *__find_acq_core(struct net *net,
const struct xfrm_mark *m,
unsigned short family, u8 mode,
- u32 reqid, u32 if_id, u8 proto,
+ u32 reqid, u32 if_id, u32 pcpu_num, u8 proto,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
int create)
@@ -1569,6 +1758,7 @@ static struct xfrm_state *__find_acq_core(struct net *net,
x->id.spi != 0 ||
x->id.proto != proto ||
(mark & x->mark.m) != x->mark.v ||
+ x->pcpu_num != pcpu_num ||
!xfrm_addr_equal(&x->id.daddr, daddr, family) ||
!xfrm_addr_equal(&x->props.saddr, saddr, family))
continue;
@@ -1602,6 +1792,7 @@ static struct xfrm_state *__find_acq_core(struct net *net,
break;
}
+ x->pcpu_num = pcpu_num;
x->km.state = XFRM_STATE_ACQ;
x->id.proto = proto;
x->props.family = family;
@@ -1630,7 +1821,7 @@ static struct xfrm_state *__find_acq_core(struct net *net,
return x;
}
-static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq);
+static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num);
int xfrm_state_add(struct xfrm_state *x)
{
@@ -1656,7 +1847,7 @@ int xfrm_state_add(struct xfrm_state *x)
}
if (use_spi && x->km.seq) {
- x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq);
+ x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq, x->pcpu_num);
if (x1 && ((x1->id.proto != x->id.proto) ||
!xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) {
to_put = x1;
@@ -1666,7 +1857,7 @@ int xfrm_state_add(struct xfrm_state *x)
if (use_spi && !x1)
x1 = __find_acq_core(net, &x->mark, family, x->props.mode,
- x->props.reqid, x->if_id, x->id.proto,
+ x->props.reqid, x->if_id, x->pcpu_num, x->id.proto,
&x->id.daddr, &x->props.saddr, 0);
__xfrm_state_bump_genids(x);
@@ -1791,6 +1982,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
x->props.flags = orig->props.flags;
x->props.extra_flags = orig->props.extra_flags;
+ x->pcpu_num = orig->pcpu_num;
x->if_id = orig->if_id;
x->tfcpad = orig->tfcpad;
x->replay_maxdiff = orig->replay_maxdiff;
@@ -2041,10 +2233,13 @@ struct xfrm_state *
xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
u8 proto, unsigned short family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct xfrm_state *x;
rcu_read_lock();
- x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
rcu_read_unlock();
return x;
}
@@ -2055,10 +2250,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
const xfrm_address_t *daddr, const xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
+
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
@@ -2066,13 +2265,14 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
struct xfrm_state *
xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
- u32 if_id, u8 proto, const xfrm_address_t *daddr,
+ u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr,
const xfrm_address_t *saddr, int create, unsigned short family)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create);
+ x = __find_acq_core(net, mark, family, mode, reqid, if_id, pcpu_num,
+ proto, daddr, saddr, create);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
@@ -2207,7 +2407,7 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n,
/* Silly enough, but I'm lazy to build resolution list */
-static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
+static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num)
{
unsigned int h = xfrm_seq_hash(net, seq);
struct xfrm_state *x;
@@ -2215,6 +2415,7 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s
hlist_for_each_entry_rcu(x, net->xfrm.state_byseq + h, byseq) {
if (x->km.seq == seq &&
(mark & x->mark.m) == x->mark.v &&
+ x->pcpu_num == pcpu_num &&
x->km.state == XFRM_STATE_ACQ) {
xfrm_state_hold(x);
return x;
@@ -2224,12 +2425,12 @@ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 s
return NULL;
}
-struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq)
+struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num)
{
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- x = __xfrm_find_acq_byseq(net, mark, seq);
+ x = __xfrm_find_acq_byseq(net, mark, seq, pcpu_num);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
@@ -2284,10 +2485,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
unsigned int h;
struct xfrm_state *x0;
int err = -ENOENT;
- __be32 minspi = htonl(low);
- __be32 maxspi = htonl(high);
+ u32 range = high - low + 1;
__be32 newspi = 0;
- u32 mark = x->mark.v & x->mark.m;
spin_lock_bh(&x->lock);
if (x->km.state == XFRM_STATE_DEAD) {
@@ -2301,38 +2500,34 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
err = -ENOENT;
- if (minspi == maxspi) {
- x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family);
- if (x0) {
- NL_SET_ERR_MSG(extack, "Requested SPI is already in use");
- xfrm_state_put(x0);
+ for (h = 0; h < range; h++) {
+ u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high);
+ newspi = htonl(spi);
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ x0 = xfrm_state_lookup_spi_proto(net, newspi, x->id.proto);
+ if (!x0) {
+ x->id.spi = newspi;
+ h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family);
+ XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ err = 0;
goto unlock;
}
- newspi = minspi;
- } else {
- u32 spi = 0;
- for (h = 0; h < high-low+1; h++) {
- spi = get_random_u32_inclusive(low, high);
- x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
- if (x0 == NULL) {
- newspi = htonl(spi);
- break;
- }
- xfrm_state_put(x0);
+ xfrm_state_put(x0);
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+ if (signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto unlock;
}
+
+ if (low == high)
+ break;
}
- if (newspi) {
- spin_lock_bh(&net->xfrm.xfrm_state_lock);
- x->id.spi = newspi;
- h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
- XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
- x->xso.type);
- spin_unlock_bh(&net->xfrm.xfrm_state_lock);
- err = 0;
- } else {
+ if (err)
NL_SET_ERR_MSG(extack, "No SPI available in the requested range");
- }
unlock:
spin_unlock_bh(&x->lock);
@@ -2988,6 +3183,11 @@ int __net_init xfrm_state_init(struct net *net)
net->xfrm.state_byseq = xfrm_hash_alloc(sz);
if (!net->xfrm.state_byseq)
goto out_byseq;
+
+ net->xfrm.state_cache_input = alloc_percpu(struct hlist_head);
+ if (!net->xfrm.state_cache_input)
+ goto out_state_cache_input;
+
net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1);
net->xfrm.state_num = 0;
@@ -2997,6 +3197,8 @@ int __net_init xfrm_state_init(struct net *net)
&net->xfrm.xfrm_state_lock);
return 0;
+out_state_cache_input:
+ xfrm_hash_free(net->xfrm.state_byseq, sz);
out_byseq:
xfrm_hash_free(net->xfrm.state_byspi, sz);
out_byspi:
@@ -3026,6 +3228,7 @@ void xfrm_state_fini(struct net *net)
xfrm_hash_free(net->xfrm.state_bysrc, sz);
WARN_ON(!hlist_empty(net->xfrm.state_bydst));
xfrm_hash_free(net->xfrm.state_bydst, sz);
+ free_percpu(net->xfrm.state_cache_input);
}
#ifdef CONFIG_AUDITSYSCALL
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index e3b8ce89831a..d41e5642625e 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -178,6 +178,28 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
"Replay seq and seq_hi should be 0 for output SA");
return -EINVAL;
}
+
+ if (!(p->flags & XFRM_STATE_ESN)) {
+ if (rs->oseq_hi) {
+ NL_SET_ERR_MSG(
+ extack,
+ "Replay oseq_hi should be 0 in non-ESN mode for output SA");
+ return -EINVAL;
+ }
+ if (rs->oseq == U32_MAX) {
+ NL_SET_ERR_MSG(
+ extack,
+ "Replay oseq should be less than 0xFFFFFFFF in non-ESN mode for output SA");
+ return -EINVAL;
+ }
+ } else {
+ if (rs->oseq == U32_MAX && rs->oseq_hi == U32_MAX) {
+ NL_SET_ERR_MSG(
+ extack,
+ "Replay oseq and oseq_hi should be less than 0xFFFFFFFF for output SA");
+ return -EINVAL;
+ }
+ }
if (rs->bmp_len) {
NL_SET_ERR_MSG(extack, "Replay bmp_len should 0 for output SA");
return -EINVAL;
@@ -190,6 +212,28 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
"Replay oseq and oseq_hi should be 0 for input SA");
return -EINVAL;
}
+ if (!(p->flags & XFRM_STATE_ESN)) {
+ if (rs->seq_hi) {
+ NL_SET_ERR_MSG(
+ extack,
+ "Replay seq_hi should be 0 in non-ESN mode for input SA");
+ return -EINVAL;
+ }
+
+ if (rs->seq == U32_MAX) {
+ NL_SET_ERR_MSG(
+ extack,
+ "Replay seq should be less than 0xFFFFFFFF in non-ESN mode for input SA");
+ return -EINVAL;
+ }
+ } else {
+ if (rs->seq == U32_MAX && rs->seq_hi == U32_MAX) {
+ NL_SET_ERR_MSG(
+ extack,
+ "Replay seq and seq_hi should be less than 0xFFFFFFFF for input SA");
+ return -EINVAL;
+ }
+ }
}
return 0;
@@ -460,6 +504,12 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
}
}
+ if (!sa_dir && attrs[XFRMA_SA_PCPU]) {
+ NL_SET_ERR_MSG(extack, "SA_PCPU only supported with SA_DIR");
+ err = -EINVAL;
+ goto out;
+ }
+
out:
return err;
}
@@ -841,6 +891,12 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
x->nat_keepalive_interval =
nla_get_u32(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]);
+ if (attrs[XFRMA_SA_PCPU]) {
+ x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]);
+ if (x->pcpu_num >= num_possible_cpus())
+ goto error;
+ }
+
err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack);
if (err)
goto error;
@@ -1296,6 +1352,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
if (ret)
goto out;
}
+ if (x->pcpu_num != UINT_MAX) {
+ ret = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num);
+ if (ret)
+ goto out;
+ }
if (x->dir)
ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir);
@@ -1700,6 +1761,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
u32 mark;
struct xfrm_mark m;
u32 if_id = 0;
+ u32 pcpu_num = UINT_MAX;
p = nlmsg_data(nlh);
err = verify_spi_info(p->info.id.proto, p->min, p->max, extack);
@@ -1716,8 +1778,16 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
if (attrs[XFRMA_IF_ID])
if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+ if (attrs[XFRMA_SA_PCPU]) {
+ pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]);
+ if (pcpu_num >= num_possible_cpus()) {
+ err = -EINVAL;
+ goto out_noput;
+ }
+ }
+
if (p->info.seq) {
- x = xfrm_find_acq_byseq(net, mark, p->info.seq);
+ x = xfrm_find_acq_byseq(net, mark, p->info.seq, pcpu_num);
if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) {
xfrm_state_put(x);
x = NULL;
@@ -1726,7 +1796,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!x)
x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid,
- if_id, p->info.id.proto, daddr,
+ if_id, pcpu_num, p->info.id.proto, daddr,
&p->info.saddr, 1,
family);
err = -ENOENT;
@@ -2526,7 +2596,8 @@ static inline unsigned int xfrm_aevent_msgsize(struct xfrm_state *x)
+ nla_total_size(sizeof(struct xfrm_mark))
+ nla_total_size(4) /* XFRM_AE_RTHR */
+ nla_total_size(4) /* XFRM_AE_ETHR */
- + nla_total_size(sizeof(x->dir)); /* XFRMA_SA_DIR */
+ + nla_total_size(sizeof(x->dir)) /* XFRMA_SA_DIR */
+ + nla_total_size(4); /* XFRMA_SA_PCPU */
}
static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
@@ -2582,6 +2653,11 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
err = xfrm_if_id_put(skb, x->if_id);
if (err)
goto out_cancel;
+ if (x->pcpu_num != UINT_MAX) {
+ err = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num);
+ if (err)
+ goto out_cancel;
+ }
if (x->dir) {
err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir);
@@ -2852,6 +2928,13 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh,
xfrm_mark_get(attrs, &mark);
+ if (attrs[XFRMA_SA_PCPU]) {
+ x->pcpu_num = nla_get_u32(attrs[XFRMA_SA_PCPU]);
+ err = -EINVAL;
+ if (x->pcpu_num >= num_possible_cpus())
+ goto free_state;
+ }
+
err = verify_newpolicy_info(&ua->policy, extack);
if (err)
goto free_state;
@@ -3182,6 +3265,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
[XFRMA_MTIMER_THRESH] = { .type = NLA_U32 },
[XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT),
[XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 },
+ [XFRMA_SA_PCPU] = { .type = NLA_U32 },
};
EXPORT_SYMBOL_GPL(xfrma_policy);
@@ -3348,7 +3432,8 @@ static inline unsigned int xfrm_expire_msgsize(void)
{
return NLMSG_ALIGN(sizeof(struct xfrm_user_expire)) +
nla_total_size(sizeof(struct xfrm_mark)) +
- nla_total_size(sizeof_field(struct xfrm_state, dir));
+ nla_total_size(sizeof_field(struct xfrm_state, dir)) +
+ nla_total_size(4); /* XFRMA_SA_PCPU */
}
static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c)
@@ -3374,6 +3459,11 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct
err = xfrm_if_id_put(skb, x->if_id);
if (err)
return err;
+ if (x->pcpu_num != UINT_MAX) {
+ err = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num);
+ if (err)
+ return err;
+ }
if (x->dir) {
err = nla_put_u8(skb, XFRMA_SA_DIR, x->dir);
@@ -3481,6 +3571,8 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
}
if (x->if_id)
l += nla_total_size(sizeof(x->if_id));
+ if (x->pcpu_num)
+ l += nla_total_size(sizeof(x->pcpu_num));
/* Must count x->lastused as it may become non-zero behind our back. */
l += nla_total_size_64bit(sizeof(u64));
@@ -3587,6 +3679,7 @@ static inline unsigned int xfrm_acquire_msgsize(struct xfrm_state *x,
+ nla_total_size(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr)
+ nla_total_size(sizeof(struct xfrm_mark))
+ nla_total_size(xfrm_user_sec_ctx_size(x->security))
+ + nla_total_size(4) /* XFRMA_SA_PCPU */
+ userpolicy_type_attrsize();
}
@@ -3623,6 +3716,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
err = xfrm_if_id_put(skb, xp->if_id);
if (!err && xp->xdo.dev)
err = copy_user_offload(&xp->xdo, skb);
+ if (!err && x->pcpu_num != UINT_MAX)
+ err = nla_put_u32(skb, XFRMA_SA_PCPU, x->pcpu_num);
if (err) {
nlmsg_cancel(skb, nlh);
return err;
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-29 05:58:43 +0300