summaryrefslogtreecommitdiff
path: root/net/xfrm/xfrm_state.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/xfrm/xfrm_state.c')
-rw-r--r--net/xfrm/xfrm_state.c1151
1 files changed, 948 insertions, 203 deletions
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8be2d926acc2..9e14e453b55c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -14,6 +14,7 @@
*
*/
+#include <linux/compat.h>
#include <linux/workqueue.h>
#include <net/xfrm.h>
#include <linux/pfkeyv2.h>
@@ -33,6 +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);
@@ -44,11 +47,11 @@ static void xfrm_state_gc_task(struct work_struct *work);
*/
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
-static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
static struct kmem_cache *xfrm_state_cache __ro_after_init;
static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
static HLIST_HEAD(xfrm_state_gc_list);
+static HLIST_HEAD(xfrm_state_dev_gc_list);
static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
{
@@ -61,6 +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);
}
@@ -69,6 +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);
}
@@ -76,13 +83,42 @@ 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);
+}
+
+#define XFRM_STATE_INSERT(by, _n, _h, _type) \
+ { \
+ struct xfrm_state *_x = NULL; \
+ \
+ if (_type != XFRM_DEV_OFFLOAD_PACKET) { \
+ hlist_for_each_entry_rcu(_x, _h, by) { \
+ if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \
+ continue; \
+ break; \
+ } \
+ } \
+ \
+ if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \
+ /* SAD is empty or consist from HW SAs only */ \
+ hlist_add_head_rcu(_n, _h); \
+ else \
+ hlist_add_before_rcu(_n, &_x->by); \
+ }
+
static void xfrm_hash_transfer(struct hlist_head *list,
struct hlist_head *ndsttable,
struct hlist_head *nsrctable,
struct hlist_head *nspitable,
+ struct hlist_head *nseqtable,
unsigned int nhashmask)
{
struct hlist_node *tmp;
@@ -94,18 +130,25 @@ static void xfrm_hash_transfer(struct hlist_head *list,
h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr,
x->props.reqid, x->props.family,
nhashmask);
- hlist_add_head_rcu(&x->bydst, ndsttable + h);
+ XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type);
h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr,
x->props.family,
nhashmask);
- hlist_add_head_rcu(&x->bysrc, nsrctable + h);
+ XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type);
if (x->id.spi) {
h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
x->id.proto, x->props.family,
nhashmask);
- hlist_add_head_rcu(&x->byspi, nspitable + h);
+ XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h,
+ x->xso.type);
+ }
+
+ if (x->km.seq) {
+ h = __xfrm_seq_hash(x->km.seq, nhashmask);
+ XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h,
+ x->xso.type);
}
}
}
@@ -118,7 +161,7 @@ static unsigned long xfrm_hash_new_size(unsigned int state_hmask)
static void xfrm_hash_resize(struct work_struct *work)
{
struct net *net = container_of(work, struct net, xfrm.state_hash_work);
- struct hlist_head *ndst, *nsrc, *nspi, *odst, *osrc, *ospi;
+ struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq;
unsigned long nsize, osize;
unsigned int nhashmask, ohashmask;
int i;
@@ -138,25 +181,34 @@ static void xfrm_hash_resize(struct work_struct *work)
xfrm_hash_free(nsrc, nsize);
return;
}
+ nseq = xfrm_hash_alloc(nsize);
+ if (!nseq) {
+ xfrm_hash_free(ndst, nsize);
+ xfrm_hash_free(nsrc, nsize);
+ xfrm_hash_free(nspi, nsize);
+ return;
+ }
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- write_seqcount_begin(&xfrm_state_hash_generation);
+ write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
for (i = net->xfrm.state_hmask; i >= 0; i--)
- xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask);
+ xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask);
osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net);
ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net);
+ oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net);
ohashmask = net->xfrm.state_hmask;
rcu_assign_pointer(net->xfrm.state_bydst, ndst);
rcu_assign_pointer(net->xfrm.state_bysrc, nsrc);
rcu_assign_pointer(net->xfrm.state_byspi, nspi);
+ rcu_assign_pointer(net->xfrm.state_byseq, nseq);
net->xfrm.state_hmask = nhashmask;
- write_seqcount_end(&xfrm_state_hash_generation);
+ write_seqcount_end(&net->xfrm.xfrm_state_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
osize = (ohashmask + 1) * sizeof(struct hlist_head);
@@ -166,12 +218,14 @@ static void xfrm_hash_resize(struct work_struct *work)
xfrm_hash_free(odst, osize);
xfrm_hash_free(osrc, osize);
xfrm_hash_free(ospi, osize);
+ xfrm_hash_free(oseq, osize);
}
static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
static DEFINE_SPINLOCK(xfrm_state_gc_lock);
+static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock);
int __xfrm_state_delete(struct xfrm_state *x);
@@ -370,18 +424,17 @@ void xfrm_unregister_type_offload(const struct xfrm_type_offload *type,
}
EXPORT_SYMBOL(xfrm_unregister_type_offload);
-static const struct xfrm_type_offload *
-xfrm_get_type_offload(u8 proto, unsigned short family, bool try_load)
+void xfrm_set_type_offload(struct xfrm_state *x, bool try_load)
{
const struct xfrm_type_offload *type = NULL;
struct xfrm_state_afinfo *afinfo;
retry:
- afinfo = xfrm_state_get_afinfo(family);
+ afinfo = xfrm_state_get_afinfo(x->props.family);
if (unlikely(afinfo == NULL))
- return NULL;
+ goto out;
- switch (proto) {
+ switch (x->id.proto) {
case IPPROTO_ESP:
type = afinfo->type_offload_esp;
break;
@@ -395,18 +448,16 @@ retry:
rcu_read_unlock();
if (!type && try_load) {
- request_module("xfrm-offload-%d-%d", family, proto);
+ request_module("xfrm-offload-%d-%d", x->props.family,
+ x->id.proto);
try_load = false;
goto retry;
}
- return type;
-}
-
-static void xfrm_put_type_offload(const struct xfrm_type_offload *type)
-{
- module_put(type->owner);
+out:
+ x->type_offload = type;
}
+EXPORT_SYMBOL(xfrm_set_type_offload);
static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = {
[XFRM_MODE_BEET] = {
@@ -423,6 +474,11 @@ static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = {
.flags = XFRM_MODE_FLAG_TUNNEL,
.family = AF_INET,
},
+ [XFRM_MODE_IPTFS] = {
+ .encap = XFRM_MODE_IPTFS,
+ .flags = XFRM_MODE_FLAG_TUNNEL,
+ .family = AF_INET,
+ },
};
static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
@@ -444,6 +500,11 @@ static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = {
.flags = XFRM_MODE_FLAG_TUNNEL,
.family = AF_INET6,
},
+ [XFRM_MODE_IPTFS] = {
+ .encap = XFRM_MODE_IPTFS,
+ .flags = XFRM_MODE_FLAG_TUNNEL,
+ .family = AF_INET6,
+ },
};
static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
@@ -471,26 +532,83 @@ static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family)
return NULL;
}
+static const struct xfrm_mode_cbs __rcu *xfrm_mode_cbs_map[XFRM_MODE_MAX];
+static DEFINE_SPINLOCK(xfrm_mode_cbs_map_lock);
+
+int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs)
+{
+ if (mode >= XFRM_MODE_MAX)
+ return -EINVAL;
+
+ spin_lock_bh(&xfrm_mode_cbs_map_lock);
+ rcu_assign_pointer(xfrm_mode_cbs_map[mode], mode_cbs);
+ spin_unlock_bh(&xfrm_mode_cbs_map_lock);
+
+ return 0;
+}
+EXPORT_SYMBOL(xfrm_register_mode_cbs);
+
+void xfrm_unregister_mode_cbs(u8 mode)
+{
+ if (mode >= XFRM_MODE_MAX)
+ return;
+
+ spin_lock_bh(&xfrm_mode_cbs_map_lock);
+ RCU_INIT_POINTER(xfrm_mode_cbs_map[mode], NULL);
+ spin_unlock_bh(&xfrm_mode_cbs_map_lock);
+ synchronize_rcu();
+}
+EXPORT_SYMBOL(xfrm_unregister_mode_cbs);
+
+static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode)
+{
+ const struct xfrm_mode_cbs *cbs;
+ bool try_load = true;
+
+ if (mode >= XFRM_MODE_MAX)
+ return NULL;
+
+retry:
+ rcu_read_lock();
+
+ cbs = rcu_dereference(xfrm_mode_cbs_map[mode]);
+ if (cbs && !try_module_get(cbs->owner))
+ cbs = NULL;
+
+ rcu_read_unlock();
+
+ if (mode == XFRM_MODE_IPTFS && !cbs && try_load) {
+ request_module("xfrm-iptfs");
+ try_load = false;
+ goto retry;
+ }
+
+ return cbs;
+}
+
void xfrm_state_free(struct xfrm_state *x)
{
kmem_cache_free(xfrm_state_cache, x);
}
EXPORT_SYMBOL(xfrm_state_free);
-static void ___xfrm_state_destroy(struct xfrm_state *x)
+static void xfrm_state_delete_tunnel(struct xfrm_state *x);
+static void xfrm_state_gc_destroy(struct xfrm_state *x)
{
+ if (x->mode_cbs && x->mode_cbs->destroy_state)
+ x->mode_cbs->destroy_state(x);
hrtimer_cancel(&x->mtimer);
- del_timer_sync(&x->rtimer);
- kfree(x->aead);
- kfree(x->aalg);
- kfree(x->ealg);
+ timer_delete_sync(&x->rtimer);
+ kfree_sensitive(x->aead);
+ kfree_sensitive(x->aalg);
+ kfree_sensitive(x->ealg);
kfree(x->calg);
kfree(x->encap);
kfree(x->coaddr);
kfree(x->replay_esn);
kfree(x->preplay_esn);
- if (x->type_offload)
- xfrm_put_type_offload(x->type_offload);
+ xfrm_unset_type_offload(x);
+ xfrm_state_delete_tunnel(x);
if (x->type) {
x->type->destructor(x);
xfrm_put_type(x->type);
@@ -515,7 +633,7 @@ static void xfrm_state_gc_task(struct work_struct *work)
synchronize_rcu();
hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
- ___xfrm_state_destroy(x);
+ xfrm_state_gc_destroy(x);
}
static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
@@ -528,12 +646,14 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
int err = 0;
spin_lock(&x->lock);
+ xfrm_dev_state_update_stats(x);
+
if (x->km.state == XFRM_STATE_DEAD)
goto out;
if (x->km.state == XFRM_STATE_EXPIRED)
goto expired;
if (x->lft.hard_add_expires_seconds) {
- long tmo = x->lft.hard_add_expires_seconds +
+ time64_t tmo = x->lft.hard_add_expires_seconds +
x->curlft.add_time - now;
if (tmo <= 0) {
if (x->xflags & XFRM_SOFT_EXPIRE) {
@@ -550,8 +670,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
next = tmo;
}
if (x->lft.hard_use_expires_seconds) {
- long tmo = x->lft.hard_use_expires_seconds +
- (x->curlft.use_time ? : now) - now;
+ time64_t tmo = x->lft.hard_use_expires_seconds +
+ (READ_ONCE(x->curlft.use_time) ? : now) - now;
if (tmo <= 0)
goto expired;
if (tmo < next)
@@ -560,7 +680,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
if (x->km.dying)
goto resched;
if (x->lft.soft_add_expires_seconds) {
- long tmo = x->lft.soft_add_expires_seconds +
+ time64_t tmo = x->lft.soft_add_expires_seconds +
x->curlft.add_time - now;
if (tmo <= 0) {
warn = 1;
@@ -572,8 +692,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
}
}
if (x->lft.soft_use_expires_seconds) {
- long tmo = x->lft.soft_use_expires_seconds +
- (x->curlft.use_time ? : now) - now;
+ time64_t tmo = x->lft.soft_use_expires_seconds +
+ (READ_ONCE(x->curlft.use_time) ? : now) - now;
if (tmo <= 0)
warn = 1;
else if (tmo < next)
@@ -619,11 +739,13 @@ 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);
- hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
- x->mtimer.function = xfrm_timer_handler;
+ INIT_HLIST_NODE(&x->byseq);
+ hrtimer_setup(&x->mtimer, xfrm_timer_handler, CLOCK_BOOTTIME,
+ HRTIMER_MODE_ABS_SOFT);
timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
x->curlft.add_time = ktime_get_real_seconds();
x->lft.soft_byte_limit = XFRM_INF;
@@ -632,26 +754,58 @@ 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);
+ x->mode_data = NULL;
}
return x;
}
EXPORT_SYMBOL(xfrm_state_alloc);
-void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
+#ifdef CONFIG_XFRM_OFFLOAD
+void xfrm_dev_state_delete(struct xfrm_state *x)
{
- WARN_ON(x->km.state != XFRM_STATE_DEAD);
+ struct xfrm_dev_offload *xso = &x->xso;
+ struct net_device *dev = READ_ONCE(xso->dev);
- if (sync) {
- synchronize_rcu();
- ___xfrm_state_destroy(x);
- } else {
- spin_lock_bh(&xfrm_state_gc_lock);
- hlist_add_head(&x->gclist, &xfrm_state_gc_list);
- spin_unlock_bh(&xfrm_state_gc_lock);
- schedule_work(&xfrm_state_gc_work);
+ if (dev) {
+ dev->xfrmdev_ops->xdo_dev_state_delete(dev, x);
+ spin_lock_bh(&xfrm_state_dev_gc_lock);
+ hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list);
+ spin_unlock_bh(&xfrm_state_dev_gc_lock);
}
}
+EXPORT_SYMBOL_GPL(xfrm_dev_state_delete);
+
+void xfrm_dev_state_free(struct xfrm_state *x)
+{
+ struct xfrm_dev_offload *xso = &x->xso;
+ struct net_device *dev = READ_ONCE(xso->dev);
+
+ if (dev && dev->xfrmdev_ops) {
+ spin_lock_bh(&xfrm_state_dev_gc_lock);
+ if (!hlist_unhashed(&x->dev_gclist))
+ hlist_del(&x->dev_gclist);
+ spin_unlock_bh(&xfrm_state_dev_gc_lock);
+
+ if (dev->xfrmdev_ops->xdo_dev_state_free)
+ dev->xfrmdev_ops->xdo_dev_state_free(dev, x);
+ WRITE_ONCE(xso->dev, NULL);
+ xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+ netdev_put(dev, &xso->dev_tracker);
+ }
+}
+#endif
+
+void __xfrm_state_destroy(struct xfrm_state *x)
+{
+ WARN_ON(x->km.state != XFRM_STATE_DEAD);
+
+ spin_lock_bh(&xfrm_state_gc_lock);
+ hlist_add_head(&x->gclist, &xfrm_state_gc_list);
+ spin_unlock_bh(&xfrm_state_gc_lock);
+ schedule_work(&xfrm_state_gc_work);
+}
EXPORT_SYMBOL(__xfrm_state_destroy);
int __xfrm_state_delete(struct xfrm_state *x)
@@ -661,20 +815,28 @@ 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);
+ xfrm_state_delete_tunnel(x);
+
/* All xfrm_state objects are created by xfrm_state_alloc.
* The xfrm_state_alloc call gives a reference, and that
* is what we are dropping here.
@@ -727,7 +889,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
for (i = 0; i <= net->xfrm.state_hmask; i++) {
struct xfrm_state *x;
- struct xfrm_state_offload *xso;
+ struct xfrm_dev_offload *xso;
hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
xso = &x->xso;
@@ -756,7 +918,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool
}
#endif
-int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync)
+int xfrm_state_flush(struct net *net, u8 proto, bool task_valid)
{
int i, err = 0, cnt = 0;
@@ -778,10 +940,7 @@ restart:
err = xfrm_state_delete(x);
xfrm_audit_state_delete(x, err ? 0 : 1,
task_valid);
- if (sync)
- xfrm_state_put_sync(x);
- else
- xfrm_state_put(x);
+ xfrm_state_put(x);
if (!err)
cnt++;
@@ -801,6 +960,9 @@ EXPORT_SYMBOL(xfrm_state_flush);
int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid)
{
+ struct xfrm_state *x;
+ struct hlist_node *tmp;
+ struct xfrm_dev_offload *xso;
int i, err = 0, cnt = 0;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -810,8 +972,6 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
err = -ESRCH;
for (i = 0; i <= net->xfrm.state_hmask; i++) {
- struct xfrm_state *x;
- struct xfrm_state_offload *xso;
restart:
hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
xso = &x->xso;
@@ -821,6 +981,8 @@ restart:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
err = xfrm_state_delete(x);
+ xfrm_dev_state_free(x);
+
xfrm_audit_state_delete(x, err ? 0 : 1,
task_valid);
xfrm_state_put(x);
@@ -837,6 +999,24 @@ restart:
out:
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+ spin_lock_bh(&xfrm_state_dev_gc_lock);
+restart_gc:
+ hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) {
+ xso = &x->xso;
+
+ if (xso->dev == dev) {
+ spin_unlock_bh(&xfrm_state_dev_gc_lock);
+ xfrm_dev_state_free(x);
+ spin_lock_bh(&xfrm_state_dev_gc_lock);
+ goto restart_gc;
+ }
+
+ }
+ spin_unlock_bh(&xfrm_state_dev_gc_lock);
+
+ xfrm_flush_gc();
+
return err;
}
EXPORT_SYMBOL(xfrm_dev_state_flush);
@@ -927,15 +1107,81 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
x->props.family = tmpl->encap_family;
}
-static struct xfrm_state *__xfrm_state_lookup(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(daddr, spi, proto, family, state_ptrs->hmask);
+ struct xfrm_state *x;
+
+ 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)
+ /* HW states are in the head of list, there is
+ * no need to iterate further.
+ */
+ break;
+
+ /* Packet offload: both policy and SA should
+ * have same device.
+ */
+ if (xdo->dev != x->xso.dev)
+ continue;
+ } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+ /* Skip HW policy for SW lookups */
+ continue;
+#endif
+ 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;
+ return x;
+ }
+
+ return NULL;
+}
+
+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 ||
@@ -952,15 +1198,63 @@ 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) ||
@@ -980,14 +1274,17 @@ 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);
@@ -1004,7 +1301,7 @@ 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.
@@ -1019,21 +1316,31 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
*/
if (x->km.state == XFRM_STATE_VALID) {
if ((x->sel.family &&
- !xfrm_selector_match(&x->sel, fl, x->sel.family)) ||
- !security_xfrm_state_pol_flow_match(x, pol, fl))
+ (x->sel.family != family ||
+ !xfrm_selector_match(&x->sel, fl, family))) ||
+ !security_xfrm_state_pol_flow_match(x, pol,
+ &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 (xfrm_selector_match(&x->sel, fl, x->sel.family) &&
- security_xfrm_state_pol_flow_match(x, pol, fl))
+ if ((!x->sel.family ||
+ (x->sel.family == family &&
+ xfrm_selector_match(&x->sel, fl, family))) &&
+ security_xfrm_state_pol_flow_match(x, pol,
+ &fl->u.__fl_common))
*error = -ESRCH;
}
}
@@ -1045,6 +1352,7 @@ 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;
@@ -1055,14 +1363,22 @@ 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(&xfrm_state_hash_generation);
+ 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 &&
@@ -1073,13 +1389,89 @@ 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, encap_family,
- &best, &acquire_in_progress, &error);
+ &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)
+ /* HW states are in the head of list, there is
+ * no need to iterate further.
+ */
+ break;
+
+ /* Packet offload: both policy and SA should
+ * have same device.
+ */
+ if (pol->xdo.dev != x->xso.dev)
+ continue;
+ } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+ /* Skip HW policy for SW lookups */
+ continue;
+#endif
+ 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, family,
+ &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)
+ /* HW states are in the head of list, there is
+ * no need to iterate further.
+ */
+ break;
+
+ /* Packet offload: both policy and SA should
+ * have same device.
+ */
+ if (pol->xdo.dev != x->xso.dev)
+ continue;
+ } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+ /* Skip HW policy for SW lookups */
+ continue;
+#endif
if (x->props.family == encap_family &&
x->props.reqid == tmpl->reqid &&
(mark & x->mark.m) == x->mark.v &&
@@ -1089,16 +1481,21 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
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);
+ xfrm_state_look_at(pol, x, fl, family,
+ &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(net, mark, daddr, tmpl->id.spi,
- tmpl->id.proto, encap_family)) != NULL) {
+ (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr,
+ tmpl->id.spi, tmpl->id.proto,
+ encap_family,
+ &pol->xdo)) != NULL) {
to_put = x0;
error = -EEXIST;
goto out;
@@ -1124,6 +1521,8 @@ 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) {
@@ -1132,17 +1531,56 @@ found:
x = NULL;
goto out;
}
-
+#ifdef CONFIG_XFRM_OFFLOAD
+ if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+ struct xfrm_dev_offload *xdo = &pol->xdo;
+ struct xfrm_dev_offload *xso = &x->xso;
+ struct net_device *dev = xdo->dev;
+
+ xso->type = XFRM_DEV_OFFLOAD_PACKET;
+ xso->dir = xdo->dir;
+ xso->dev = dev;
+ xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ;
+ netdev_hold(dev, &xso->dev_tracker, GFP_ATOMIC);
+ error = dev->xfrmdev_ops->xdo_dev_state_add(dev, x,
+ NULL);
+ if (error) {
+ xso->dir = 0;
+ netdev_put(dev, &xso->dev_tracker);
+ xso->dev = NULL;
+ xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+ x->km.state = XFRM_STATE_DEAD;
+ to_put = x;
+ x = NULL;
+ goto out;
+ }
+ }
+#endif
if (km_query(x, tmpl, pol) == 0) {
spin_lock_bh(&net->xfrm.xfrm_state_lock);
x->km.state = XFRM_STATE_ACQ;
+ x->dir = XFRM_SA_DIR_OUT;
list_add(&x->km.all, &net->xfrm.state_all);
- hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
+ 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);
h = xfrm_src_hash(net, daddr, saddr, encap_family);
- hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
+ 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);
- hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
+ XFRM_STATE_INSERT(byspi, &x->byspi,
+ net->xfrm.state_byspi + h,
+ x->xso.type);
+ }
+ if (x->km.seq) {
+ h = xfrm_seq_hash(net, x->km.seq);
+ XFRM_STATE_INSERT(byseq, &x->byseq,
+ net->xfrm.state_byseq + h,
+ x->xso.type);
}
x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
hrtimer_start(&x->mtimer,
@@ -1152,11 +1590,24 @@ found:
xfrm_hash_grow_check(net, x->bydst.next != NULL);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
} else {
+#ifdef CONFIG_XFRM_OFFLOAD
+ struct xfrm_dev_offload *xso = &x->xso;
+
+ if (xso->type == XFRM_DEV_OFFLOAD_PACKET) {
+ xfrm_dev_state_delete(x);
+ xfrm_dev_state_free(x);
+ }
+#endif
x->km.state = XFRM_STATE_DEAD;
to_put = x;
x = NULL;
error = -ESRCH;
}
+
+ /* Use the already installed 'fallback' while the CPU-specific
+ * SA acquire is handled*/
+ if (best)
+ x = best;
}
out:
if (x) {
@@ -1167,11 +1618,20 @@ 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);
- if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
+ if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) {
*err = -EAGAIN;
if (x) {
xfrm_state_put(x);
@@ -1238,6 +1698,26 @@ 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);
@@ -1245,18 +1725,31 @@ 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);
- hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
+ XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+ x->xso.type);
h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family);
- hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
+ XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+ x->xso.type);
if (x->id.spi) {
h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto,
x->props.family);
- hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
+ XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
+ x->xso.type);
+ }
+
+ if (x->km.seq) {
+ h = xfrm_seq_hash(net, x->km.seq);
+
+ XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h,
+ x->xso.type);
}
hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
@@ -1266,6 +1759,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
net->xfrm.state_num++;
xfrm_hash_grow_check(net, x->bydst.next != NULL);
+ xfrm_nat_keepalive_state_updated(x);
}
/* net->xfrm.xfrm_state_lock is held */
@@ -1278,12 +1772,14 @@ 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))
@@ -1306,7 +1802,7 @@ 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)
@@ -1323,6 +1819,7 @@ 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;
@@ -1356,6 +1853,7 @@ 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;
@@ -1370,9 +1868,11 @@ static struct xfrm_state *__find_acq_core(struct net *net,
ktime_set(net->xfrm.sysctl_acq_expires, 0),
HRTIMER_MODE_REL_SOFT);
list_add(&x->km.all, &net->xfrm.state_all);
- hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
+ XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+ x->xso.type);
h = xfrm_src_hash(net, daddr, saddr, family);
- hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
+ XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+ x->xso.type);
net->xfrm.state_num++;
@@ -1382,7 +1882,7 @@ 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)
{
@@ -1408,7 +1908,7 @@ 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;
@@ -1418,7 +1918,7 @@ 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);
@@ -1441,8 +1941,33 @@ out:
EXPORT_SYMBOL(xfrm_state_add);
#ifdef CONFIG_XFRM_MIGRATE
-static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
- struct xfrm_encap_tmpl *encap)
+static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security)
+{
+ struct xfrm_user_sec_ctx *uctx;
+ int size = sizeof(*uctx) + security->ctx_len;
+ int err;
+
+ uctx = kmalloc(size, GFP_KERNEL);
+ if (!uctx)
+ return -ENOMEM;
+
+ uctx->exttype = XFRMA_SEC_CTX;
+ uctx->len = size;
+ uctx->ctx_doi = security->ctx_doi;
+ uctx->ctx_alg = security->ctx_alg;
+ uctx->ctx_len = security->ctx_len;
+ memcpy(uctx + 1, security->ctx_str, security->ctx_len);
+ err = security_xfrm_state_alloc(x, uctx);
+ kfree(uctx);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig,
+ struct xfrm_encap_tmpl *encap,
+ struct xfrm_migrate *m)
{
struct net *net = xs_net(orig);
struct xfrm_state *x = xfrm_state_alloc(net);
@@ -1497,6 +2022,10 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
goto error;
}
+ if (orig->security)
+ if (clone_security(x, orig->security))
+ goto error;
+
if (orig->coaddr) {
x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr),
GFP_KERNEL);
@@ -1510,32 +2039,49 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
}
memcpy(&x->mark, &orig->mark, sizeof(x->mark));
-
- if (xfrm_init_state(x) < 0)
- goto error;
+ memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark));
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;
x->replay_maxage = orig->replay_maxage;
- x->curlft.add_time = orig->curlft.add_time;
+ memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft));
x->km.state = orig->km.state;
x->km.seq = orig->km.seq;
x->replay = orig->replay;
x->preplay = orig->preplay;
+ x->mapping_maxage = orig->mapping_maxage;
+ x->lastused = orig->lastused;
+ x->new_mapping = 0;
+ x->new_mapping_sport = 0;
+ x->dir = orig->dir;
+
+ x->mode_cbs = orig->mode_cbs;
+ if (x->mode_cbs && x->mode_cbs->clone_state) {
+ if (x->mode_cbs->clone_state(x, orig))
+ goto error;
+ }
+
+
+ x->props.family = m->new_family;
+ memcpy(&x->id.daddr, &m->new_daddr, sizeof(x->id.daddr));
+ memcpy(&x->props.saddr, &m->new_saddr, sizeof(x->props.saddr));
return x;
error:
+ x->km.state = XFRM_STATE_DEAD;
xfrm_state_put(x);
out:
return NULL;
}
-struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net)
+struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net,
+ u32 if_id)
{
unsigned int h;
struct xfrm_state *x = NULL;
@@ -1551,6 +2097,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
continue;
if (m->reqid && x->props.reqid != m->reqid)
continue;
+ if (if_id != 0 && x->if_id != if_id)
+ continue;
if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
m->old_family) ||
!xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
@@ -1566,6 +2114,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n
if (x->props.mode != m->mode ||
x->id.proto != m->proto)
continue;
+ if (if_id != 0 && x->if_id != if_id)
+ continue;
if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr,
m->old_family) ||
!xfrm_addr_equal(&x->props.saddr, &m->old_saddr,
@@ -1584,16 +2134,23 @@ EXPORT_SYMBOL(xfrm_migrate_state_find);
struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
struct xfrm_migrate *m,
- struct xfrm_encap_tmpl *encap)
+ struct xfrm_encap_tmpl *encap,
+ struct net *net,
+ struct xfrm_user_offload *xuo,
+ struct netlink_ext_ack *extack)
{
struct xfrm_state *xc;
- xc = xfrm_state_clone(x, encap);
+ xc = xfrm_state_clone_and_setup(x, encap, m);
if (!xc)
return NULL;
- memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr));
- memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr));
+ if (xfrm_init_state(xc) < 0)
+ goto error;
+
+ /* configure the hardware if offload is requested */
+ if (xuo && xfrm_dev_state_add(net, xc, xuo, extack))
+ goto error;
/* add state */
if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) {
@@ -1602,11 +2159,15 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x,
xfrm_state_insert(xc);
} else {
if (xfrm_state_add(xc) < 0)
- goto error;
+ goto error_add;
}
return xc;
+error_add:
+ if (xuo)
+ xfrm_dev_state_delete(xc);
error:
+ xc->km.state = XFRM_STATE_DEAD;
xfrm_state_put(xc);
return NULL;
}
@@ -1636,8 +2197,18 @@ int xfrm_state_update(struct xfrm_state *x)
}
if (x1->km.state == XFRM_STATE_ACQ) {
+ if (x->dir && x1->dir != x->dir) {
+ to_put = x1;
+ goto out;
+ }
+
__xfrm_state_insert(x);
x = NULL;
+ } else {
+ if (x1->dir != x->dir) {
+ to_put = x1;
+ goto out;
+ }
}
err = 0;
@@ -1675,7 +2246,7 @@ out:
hrtimer_start(&x1->mtimer, ktime_set(1, 0),
HRTIMER_MODE_REL_SOFT);
- if (x1->curlft.use_time)
+ if (READ_ONCE(x1->curlft.use_time))
xfrm_state_check_expire(x1);
if (x->props.smark.m || x->props.smark.v || x->if_id) {
@@ -1707,8 +2278,15 @@ EXPORT_SYMBOL(xfrm_state_update);
int xfrm_state_check_expire(struct xfrm_state *x)
{
- if (!x->curlft.use_time)
- x->curlft.use_time = ktime_get_real_seconds();
+ /* All counters which are needed to decide if state is expired
+ * are handled by SW for non-packet offload modes. Simply skip
+ * the following update and save extra boilerplate in drivers.
+ */
+ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+ xfrm_dev_state_update_stats(x);
+
+ if (!READ_ONCE(x->curlft.use_time))
+ WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds());
if (x->curlft.bytes >= x->lft.hard_byte_limit ||
x->curlft.packets >= x->lft.hard_packet_limit) {
@@ -1727,14 +2305,30 @@ int xfrm_state_check_expire(struct xfrm_state *x)
}
EXPORT_SYMBOL(xfrm_state_check_expire);
+void xfrm_state_update_stats(struct net *net)
+{
+ struct xfrm_state *x;
+ int i;
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+ for (i = 0; i <= net->xfrm.state_hmask; i++) {
+ hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst)
+ xfrm_dev_state_update_stats(x);
+ }
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+}
+
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;
}
@@ -1745,24 +2339,29 @@ 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);
- spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ rcu_read_lock();
+
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family);
+ rcu_read_unlock();
return x;
}
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;
@@ -1821,6 +2420,7 @@ static int __xfrm6_state_sort_cmp(const void *p)
#endif
case XFRM_MODE_TUNNEL:
case XFRM_MODE_BEET:
+ case XFRM_MODE_IPTFS:
return 4;
}
return 5;
@@ -1847,6 +2447,7 @@ static int __xfrm6_tmpl_sort_cmp(const void *p)
#endif
case XFRM_MODE_TUNNEL:
case XFRM_MODE_BEET:
+ case XFRM_MODE_IPTFS:
return 3;
}
return 4;
@@ -1897,31 +2498,30 @@ 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)
{
- int i;
-
- for (i = 0; i <= net->xfrm.state_hmask; i++) {
- struct xfrm_state *x;
+ unsigned int h = xfrm_seq_hash(net, seq);
+ struct xfrm_state *x;
- hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
- if (x->km.seq == seq &&
- (mark & x->mark.m) == x->mark.v &&
- x->km.state == XFRM_STATE_ACQ) {
- xfrm_state_hold(x);
- return x;
- }
+ 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;
}
}
+
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;
}
@@ -1940,7 +2540,7 @@ u32 xfrm_get_acqseq(void)
}
EXPORT_SYMBOL(xfrm_get_acqseq);
-int verify_spi_info(u8 proto, u32 min, u32 max)
+int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack)
{
switch (proto) {
case IPPROTO_AH:
@@ -1949,34 +2549,41 @@ int verify_spi_info(u8 proto, u32 min, u32 max)
case IPPROTO_COMP:
/* IPCOMP spi is 16-bits. */
- if (max >= 0x10000)
+ if (max >= 0x10000) {
+ NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535");
return -EINVAL;
+ }
break;
default:
+ NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP");
return -EINVAL;
}
- if (min > max)
+ if (min > max) {
+ NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max");
return -EINVAL;
+ }
return 0;
}
EXPORT_SYMBOL(verify_spi_info);
-int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
+int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
+ struct netlink_ext_ack *extack)
{
struct net *net = xs_net(x);
unsigned int h;
struct xfrm_state *x0;
int err = -ENOENT;
- __be32 minspi = htonl(low);
- __be32 maxspi = htonl(high);
- u32 mark = x->mark.v & x->mark.m;
+ u32 range = high - low + 1;
+ __be32 newspi = 0;
spin_lock_bh(&x->lock);
- if (x->km.state == XFRM_STATE_DEAD)
+ if (x->km.state == XFRM_STATE_DEAD) {
+ NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state");
goto unlock;
+ }
err = 0;
if (x->id.spi)
@@ -1984,34 +2591,38 @@ 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) {
- xfrm_state_put(x0);
+ for (h = 0; h < range; h++) {
+ u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high);
+ if (spi == 0)
+ goto next;
+ 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;
}
- x->id.spi = minspi;
- } else {
- u32 spi = 0;
- for (h = 0; h < high-low+1; h++) {
- spi = low + prandom_u32()%(high-low+1);
- x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
- if (x0 == NULL) {
- x->id.spi = htonl(spi);
- break;
- }
- xfrm_state_put(x0);
- }
- }
- if (x->id.spi) {
- spin_lock_bh(&net->xfrm.xfrm_state_lock);
- h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
- hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
+ xfrm_state_put(x0);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
- err = 0;
+next:
+ if (signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto unlock;
+ }
+
+ if (low == high)
+ break;
}
+ if (err)
+ NL_SET_ERR_MSG(extack, "No SPI available in the requested range");
+
unlock:
spin_unlock_bh(&x->lock);
@@ -2104,13 +2715,13 @@ EXPORT_SYMBOL(xfrm_state_walk_done);
static void xfrm_replay_timer_handler(struct timer_list *t)
{
- struct xfrm_state *x = from_timer(x, t, rtimer);
+ struct xfrm_state *x = timer_container_of(x, t, rtimer);
spin_lock(&x->lock);
if (x->km.state == XFRM_STATE_VALID) {
if (xfrm_aevent_is_on(xs_net(x)))
- x->repl->notify(x, XFRM_REPLAY_TIMEOUT);
+ xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT);
else
x->xflags |= XFRM_TIME_DEFER;
}
@@ -2175,7 +2786,7 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol)
}
EXPORT_SYMBOL(km_query);
-int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
+static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
{
int err = -EINVAL;
struct xfrm_mgr *km;
@@ -2190,6 +2801,24 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
rcu_read_unlock();
return err;
}
+
+int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport)
+{
+ int ret = 0;
+
+ if (x->mapping_maxage) {
+ if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage ||
+ x->new_mapping_sport != sport) {
+ x->new_mapping_sport = sport;
+ x->new_mapping = jiffies / HZ;
+ ret = __km_new_mapping(x, ipaddr, sport);
+ }
+ } else {
+ ret = __km_new_mapping(x, ipaddr, sport);
+ }
+
+ return ret;
+}
EXPORT_SYMBOL(km_new_mapping);
void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid)
@@ -2264,17 +2893,74 @@ static bool km_is_alive(const struct km_event *c)
return is_alive;
}
-int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen)
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+static DEFINE_SPINLOCK(xfrm_translator_lock);
+static struct xfrm_translator __rcu *xfrm_translator;
+
+struct xfrm_translator *xfrm_get_translator(void)
+{
+ struct xfrm_translator *xtr;
+
+ rcu_read_lock();
+ xtr = rcu_dereference(xfrm_translator);
+ if (unlikely(!xtr))
+ goto out;
+ if (!try_module_get(xtr->owner))
+ xtr = NULL;
+out:
+ rcu_read_unlock();
+ return xtr;
+}
+EXPORT_SYMBOL_GPL(xfrm_get_translator);
+
+void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+ module_put(xtr->owner);
+}
+EXPORT_SYMBOL_GPL(xfrm_put_translator);
+
+int xfrm_register_translator(struct xfrm_translator *xtr)
+{
+ int err = 0;
+
+ spin_lock_bh(&xfrm_translator_lock);
+ if (unlikely(xfrm_translator != NULL))
+ err = -EEXIST;
+ else
+ rcu_assign_pointer(xfrm_translator, xtr);
+ spin_unlock_bh(&xfrm_translator_lock);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_register_translator);
+
+int xfrm_unregister_translator(struct xfrm_translator *xtr)
+{
+ int err = 0;
+
+ spin_lock_bh(&xfrm_translator_lock);
+ if (likely(xfrm_translator != NULL)) {
+ if (rcu_access_pointer(xfrm_translator) != xtr)
+ err = -EINVAL;
+ else
+ RCU_INIT_POINTER(xfrm_translator, NULL);
+ }
+ spin_unlock_bh(&xfrm_translator_lock);
+ synchronize_rcu();
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_unregister_translator);
+#endif
+
+int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
{
int err;
u8 *data;
struct xfrm_mgr *km;
struct xfrm_policy *pol = NULL;
- if (in_compat_syscall())
- return -EOPNOTSUPP;
-
- if (!optval && !optlen) {
+ if (sockptr_is_null(optval) && !optlen) {
xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
__sk_dst_reset(sk);
@@ -2284,10 +2970,26 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
if (optlen <= 0 || optlen > PAGE_SIZE)
return -EMSGSIZE;
- data = memdup_user(optval, optlen);
+ data = memdup_sockptr(optval, optlen);
if (IS_ERR(data))
return PTR_ERR(data);
+ if (in_compat_syscall()) {
+ struct xfrm_translator *xtr = xfrm_get_translator();
+
+ if (!xtr) {
+ kfree(data);
+ return -EOPNOTSUPP;
+ }
+
+ err = xtr->xlate_user_policy_sockptr(&data, optlen);
+ xfrm_put_translator(xtr);
+ if (err) {
+ kfree(data);
+ return err;
+ }
+ }
+
err = -EINVAL;
rcu_read_lock();
list_for_each_entry_rcu(km, &xfrm_km_list, list) {
@@ -2312,22 +3014,20 @@ EXPORT_SYMBOL(xfrm_user_policy);
static DEFINE_SPINLOCK(xfrm_km_lock);
-int xfrm_register_km(struct xfrm_mgr *km)
+void xfrm_register_km(struct xfrm_mgr *km)
{
spin_lock_bh(&xfrm_km_lock);
list_add_tail_rcu(&km->list, &xfrm_km_list);
spin_unlock_bh(&xfrm_km_lock);
- return 0;
}
EXPORT_SYMBOL(xfrm_register_km);
-int xfrm_unregister_km(struct xfrm_mgr *km)
+void xfrm_unregister_km(struct xfrm_mgr *km)
{
spin_lock_bh(&xfrm_km_lock);
list_del_rcu(&km->list);
spin_unlock_bh(&xfrm_km_lock);
synchronize_rcu();
- return 0;
}
EXPORT_SYMBOL(xfrm_unregister_km);
@@ -2395,20 +3095,17 @@ void xfrm_flush_gc(void)
}
EXPORT_SYMBOL(xfrm_flush_gc);
-/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */
-void xfrm_state_delete_tunnel(struct xfrm_state *x)
+static void xfrm_state_delete_tunnel(struct xfrm_state *x)
{
if (x->tunnel) {
struct xfrm_state *t = x->tunnel;
- if (atomic_read(&t->tunnel_users) == 2)
+ if (atomic_dec_return(&t->tunnel_users) == 1)
xfrm_state_delete(t);
- atomic_dec(&t->tunnel_users);
- xfrm_state_put_sync(t);
+ xfrm_state_put(t);
x->tunnel = NULL;
}
}
-EXPORT_SYMBOL(xfrm_state_delete_tunnel);
u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
{
@@ -2434,6 +3131,9 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
case XFRM_MODE_TUNNEL:
break;
default:
+ if (x->mode_cbs && x->mode_cbs->get_inner_mtu)
+ return x->mode_cbs->get_inner_mtu(x, mtu);
+
WARN_ON_ONCE(1);
break;
}
@@ -2443,7 +3143,7 @@ u32 xfrm_state_mtu(struct xfrm_state *x, int mtu)
}
EXPORT_SYMBOL_GPL(xfrm_state_mtu);
-int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
+int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack)
{
const struct xfrm_mode *inner_mode;
const struct xfrm_mode *outer_mode;
@@ -2451,19 +3151,23 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
int err;
if (family == AF_INET &&
- xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)
+ READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc))
x->props.flags |= XFRM_STATE_NOPMTUDISC;
err = -EPROTONOSUPPORT;
if (x->sel.family != AF_UNSPEC) {
inner_mode = xfrm_get_mode(x->props.mode, x->sel.family);
- if (inner_mode == NULL)
+ if (inner_mode == NULL) {
+ NL_SET_ERR_MSG(extack, "Requested mode not found");
goto error;
+ }
if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) &&
- family != x->sel.family)
+ family != x->sel.family) {
+ NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family");
goto error;
+ }
x->inner_mode = *inner_mode;
} else {
@@ -2471,11 +3175,10 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
int iafamily = AF_INET;
inner_mode = xfrm_get_mode(x->props.mode, x->props.family);
- if (inner_mode == NULL)
- goto error;
-
- if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL))
+ if (inner_mode == NULL) {
+ NL_SET_ERR_MSG(extack, "Requested mode not found");
goto error;
+ }
x->inner_mode = *inner_mode;
@@ -2490,28 +3193,44 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
}
x->type = xfrm_get_type(x->id.proto, family);
- if (x->type == NULL)
+ if (x->type == NULL) {
+ NL_SET_ERR_MSG(extack, "Requested type not found");
goto error;
+ }
- x->type_offload = xfrm_get_type_offload(x->id.proto, family, offload);
-
- err = x->type->init_state(x);
+ err = x->type->init_state(x, extack);
if (err)
goto error;
outer_mode = xfrm_get_mode(x->props.mode, family);
if (!outer_mode) {
+ NL_SET_ERR_MSG(extack, "Requested mode not found");
err = -EPROTONOSUPPORT;
goto error;
}
x->outer_mode = *outer_mode;
- if (init_replay) {
- err = xfrm_init_replay(x);
- if (err)
+ if (x->nat_keepalive_interval) {
+ if (x->dir != XFRM_SA_DIR_OUT) {
+ NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs");
+ err = -EINVAL;
goto error;
+ }
+
+ if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) {
+ NL_SET_ERR_MSG(extack,
+ "NAT keepalive is only supported for UDP encapsulation");
+ err = -EINVAL;
+ goto error;
+ }
}
+ x->mode_cbs = xfrm_get_mode_cbs(x->props.mode);
+ if (x->mode_cbs) {
+ if (x->mode_cbs->init_state)
+ err = x->mode_cbs->init_state(x);
+ module_put(x->mode_cbs->owner);
+ }
error:
return err;
}
@@ -2522,11 +3241,16 @@ int xfrm_init_state(struct xfrm_state *x)
{
int err;
- err = __xfrm_init_state(x, true, false);
- if (!err)
- x->km.state = XFRM_STATE_VALID;
+ err = __xfrm_init_state(x, NULL);
+ if (err)
+ return err;
- return err;
+ err = xfrm_init_replay(x, NULL);
+ if (err)
+ return err;
+
+ x->km.state = XFRM_STATE_VALID;
+ return 0;
}
EXPORT_SYMBOL(xfrm_init_state);
@@ -2552,13 +3276,27 @@ int __net_init xfrm_state_init(struct net *net)
net->xfrm.state_byspi = xfrm_hash_alloc(sz);
if (!net->xfrm.state_byspi)
goto out_byspi;
+ 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;
INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
spin_lock_init(&net->xfrm.xfrm_state_lock);
+ seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation,
+ &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:
xfrm_hash_free(net->xfrm.state_bysrc, sz);
out_bysrc:
@@ -2570,20 +3308,27 @@ out_bydst:
void xfrm_state_fini(struct net *net)
{
unsigned int sz;
+ int i;
flush_work(&net->xfrm.state_hash_work);
+ xfrm_state_flush(net, 0, false);
flush_work(&xfrm_state_gc_work);
- xfrm_state_flush(net, 0, false, true);
WARN_ON(!list_empty(&net->xfrm.state_all));
+ for (i = 0; i <= net->xfrm.state_hmask; i++) {
+ WARN_ON(!hlist_empty(net->xfrm.state_byseq + i));
+ WARN_ON(!hlist_empty(net->xfrm.state_byspi + i));
+ WARN_ON(!hlist_empty(net->xfrm.state_bysrc + i));
+ WARN_ON(!hlist_empty(net->xfrm.state_bydst + i));
+ }
+
sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head);
- WARN_ON(!hlist_empty(net->xfrm.state_byspi));
+ xfrm_hash_free(net->xfrm.state_byseq, sz);
xfrm_hash_free(net->xfrm.state_byspi, sz);
- WARN_ON(!hlist_empty(net->xfrm.state_bysrc));
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
generated by cgit (git 2.34.1) at 2025-12-25 14:49:26 +0000