diff options
Diffstat (limited to 'net/xfrm/xfrm_state.c')
| -rw-r--r-- | net/xfrm/xfrm_state.c | 1808 |
1 files changed, 1413 insertions, 395 deletions
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 6c0956d10db6..9e14e453b55c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * xfrm_state.c * @@ -13,6 +14,7 @@ * */ +#include <linux/compat.h> #include <linux/workqueue.h> #include <net/xfrm.h> #include <linux/pfkeyv2.h> @@ -26,10 +28,14 @@ #include <linux/interrupt.h> #include <linux/kernel.h> +#include <crypto/aead.h> + #include "xfrm_hash.h" #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); @@ -41,10 +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) { @@ -57,6 +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); } @@ -65,6 +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); } @@ -72,13 +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; @@ -90,18 +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); } } } @@ -114,7 +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; @@ -134,25 +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); @@ -162,76 +218,147 @@ 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); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); -bool km_is_alive(const struct km_event *c); +static bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); -static DEFINE_SPINLOCK(xfrm_type_lock); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - const struct xfrm_type **typemap; int err = 0; - if (unlikely(afinfo == NULL)) + if (!afinfo) return -EAFNOSUPPORT; - typemap = afinfo->type_map; - spin_lock_bh(&xfrm_type_lock); - if (likely(typemap[type->proto] == NULL)) - typemap[type->proto] = type; - else - err = -EEXIST; - spin_unlock_bh(&xfrm_type_lock); +#define X(afi, T, name) do { \ + WARN_ON((afi)->type_ ## name); \ + (afi)->type_ ## name = (T); \ + } while (0) + + switch (type->proto) { + case IPPROTO_COMP: + X(afinfo, type, comp); + break; + case IPPROTO_AH: + X(afinfo, type, ah); + break; + case IPPROTO_ESP: + X(afinfo, type, esp); + break; + case IPPROTO_IPIP: + X(afinfo, type, ipip); + break; + case IPPROTO_DSTOPTS: + X(afinfo, type, dstopts); + break; + case IPPROTO_ROUTING: + X(afinfo, type, routing); + break; + case IPPROTO_IPV6: + X(afinfo, type, ipip6); + break; + default: + WARN_ON(1); + err = -EPROTONOSUPPORT; + break; + } +#undef X rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type); -int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) +void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - const struct xfrm_type **typemap; - int err = 0; if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; - typemap = afinfo->type_map; - spin_lock_bh(&xfrm_type_lock); + return; - if (unlikely(typemap[type->proto] != type)) - err = -ENOENT; - else - typemap[type->proto] = NULL; - spin_unlock_bh(&xfrm_type_lock); +#define X(afi, T, name) do { \ + WARN_ON((afi)->type_ ## name != (T)); \ + (afi)->type_ ## name = NULL; \ + } while (0) + + switch (type->proto) { + case IPPROTO_COMP: + X(afinfo, type, comp); + break; + case IPPROTO_AH: + X(afinfo, type, ah); + break; + case IPPROTO_ESP: + X(afinfo, type, esp); + break; + case IPPROTO_IPIP: + X(afinfo, type, ipip); + break; + case IPPROTO_DSTOPTS: + X(afinfo, type, dstopts); + break; + case IPPROTO_ROUTING: + X(afinfo, type, routing); + break; + case IPPROTO_IPV6: + X(afinfo, type, ipip6); + break; + default: + WARN_ON(1); + break; + } +#undef X rcu_read_unlock(); - return err; } EXPORT_SYMBOL(xfrm_unregister_type); static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) { + const struct xfrm_type *type = NULL; struct xfrm_state_afinfo *afinfo; - const struct xfrm_type **typemap; - const struct xfrm_type *type; int modload_attempted = 0; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; - typemap = afinfo->type_map; - type = READ_ONCE(typemap[proto]); + switch (proto) { + case IPPROTO_COMP: + type = afinfo->type_comp; + break; + case IPPROTO_AH: + type = afinfo->type_ah; + break; + case IPPROTO_ESP: + type = afinfo->type_esp; + break; + case IPPROTO_IPIP: + type = afinfo->type_ipip; + break; + case IPPROTO_DSTOPTS: + type = afinfo->type_dstopts; + break; + case IPPROTO_ROUTING: + type = afinfo->type_routing; + break; + case IPPROTO_IPV6: + type = afinfo->type_ipip6; + break; + default: + break; + } + if (unlikely(type && !try_module_get(type->owner))) type = NULL; @@ -251,198 +378,246 @@ static void xfrm_put_type(const struct xfrm_type *type) module_put(type->owner); } -static DEFINE_SPINLOCK(xfrm_type_offload_lock); int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - const struct xfrm_type_offload **typemap; int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; - typemap = afinfo->type_offload_map; - spin_lock_bh(&xfrm_type_offload_lock); - if (likely(typemap[type->proto] == NULL)) - typemap[type->proto] = type; - else - err = -EEXIST; - spin_unlock_bh(&xfrm_type_offload_lock); + switch (type->proto) { + case IPPROTO_ESP: + WARN_ON(afinfo->type_offload_esp); + afinfo->type_offload_esp = type; + break; + default: + WARN_ON(1); + err = -EPROTONOSUPPORT; + break; + } + rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type_offload); -int xfrm_unregister_type_offload(const struct xfrm_type_offload *type, - unsigned short family) +void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, + unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - const struct xfrm_type_offload **typemap; - int err = 0; if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; - typemap = afinfo->type_offload_map; - spin_lock_bh(&xfrm_type_offload_lock); + return; - if (unlikely(typemap[type->proto] != type)) - err = -ENOENT; - else - typemap[type->proto] = NULL; - spin_unlock_bh(&xfrm_type_offload_lock); + switch (type->proto) { + case IPPROTO_ESP: + WARN_ON(afinfo->type_offload_esp != type); + afinfo->type_offload_esp = NULL; + break; + default: + WARN_ON(1); + break; + } rcu_read_unlock(); - return err; } EXPORT_SYMBOL(xfrm_unregister_type_offload); -static const struct xfrm_type_offload *xfrm_get_type_offload(u8 proto, unsigned short family) +void xfrm_set_type_offload(struct xfrm_state *x, bool try_load) { + const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; - const struct xfrm_type_offload **typemap; - const struct xfrm_type_offload *type; - afinfo = xfrm_state_get_afinfo(family); +retry: + afinfo = xfrm_state_get_afinfo(x->props.family); if (unlikely(afinfo == NULL)) - return NULL; - typemap = afinfo->type_offload_map; + goto out; + + switch (x->id.proto) { + case IPPROTO_ESP: + type = afinfo->type_offload_esp; + break; + default: + break; + } - type = typemap[proto]; if ((type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); - return type; -} -static void xfrm_put_type_offload(const struct xfrm_type_offload *type) -{ - module_put(type->owner); -} - -static DEFINE_SPINLOCK(xfrm_mode_lock); -int xfrm_register_mode(struct xfrm_mode *mode, int family) -{ - struct xfrm_state_afinfo *afinfo; - struct xfrm_mode **modemap; - int err; - - if (unlikely(mode->encap >= XFRM_MODE_MAX)) - return -EINVAL; - - afinfo = xfrm_state_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; + if (!type && try_load) { + request_module("xfrm-offload-%d-%d", x->props.family, + x->id.proto); + try_load = false; + goto retry; + } - err = -EEXIST; - modemap = afinfo->mode_map; - spin_lock_bh(&xfrm_mode_lock); - if (modemap[mode->encap]) - goto out; +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] = { + .encap = XFRM_MODE_BEET, + .flags = XFRM_MODE_FLAG_TUNNEL, + .family = AF_INET, + }, + [XFRM_MODE_TRANSPORT] = { + .encap = XFRM_MODE_TRANSPORT, + .family = AF_INET, + }, + [XFRM_MODE_TUNNEL] = { + .encap = XFRM_MODE_TUNNEL, + .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] = { + [XFRM_MODE_BEET] = { + .encap = XFRM_MODE_BEET, + .flags = XFRM_MODE_FLAG_TUNNEL, + .family = AF_INET6, + }, + [XFRM_MODE_ROUTEOPTIMIZATION] = { + .encap = XFRM_MODE_ROUTEOPTIMIZATION, + .family = AF_INET6, + }, + [XFRM_MODE_TRANSPORT] = { + .encap = XFRM_MODE_TRANSPORT, + .family = AF_INET6, + }, + [XFRM_MODE_TUNNEL] = { + .encap = XFRM_MODE_TUNNEL, + .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) +{ + const struct xfrm_mode *mode; - err = -ENOENT; - if (!try_module_get(afinfo->owner)) - goto out; + if (unlikely(encap >= XFRM_MODE_MAX)) + return NULL; - mode->afinfo = afinfo; - modemap[mode->encap] = mode; - err = 0; + switch (family) { + case AF_INET: + mode = &xfrm4_mode_map[encap]; + if (mode->family == family) + return mode; + break; + case AF_INET6: + mode = &xfrm6_mode_map[encap]; + if (mode->family == family) + return mode; + break; + default: + break; + } -out: - spin_unlock_bh(&xfrm_mode_lock); - rcu_read_unlock(); - return err; + return NULL; } -EXPORT_SYMBOL(xfrm_register_mode); -int xfrm_unregister_mode(struct xfrm_mode *mode, int family) -{ - struct xfrm_state_afinfo *afinfo; - struct xfrm_mode **modemap; - int err; +static const struct xfrm_mode_cbs __rcu *xfrm_mode_cbs_map[XFRM_MODE_MAX]; +static DEFINE_SPINLOCK(xfrm_mode_cbs_map_lock); - if (unlikely(mode->encap >= XFRM_MODE_MAX)) +int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs) +{ + if (mode >= XFRM_MODE_MAX) return -EINVAL; - afinfo = xfrm_state_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return -EAFNOSUPPORT; + 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); - err = -ENOENT; - modemap = afinfo->mode_map; - spin_lock_bh(&xfrm_mode_lock); - if (likely(modemap[mode->encap] == mode)) { - modemap[mode->encap] = NULL; - module_put(mode->afinfo->owner); - err = 0; - } + return 0; +} +EXPORT_SYMBOL(xfrm_register_mode_cbs); - spin_unlock_bh(&xfrm_mode_lock); - rcu_read_unlock(); - return err; +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); +EXPORT_SYMBOL(xfrm_unregister_mode_cbs); -static struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) +static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode) { - struct xfrm_state_afinfo *afinfo; - struct xfrm_mode *mode; - int modload_attempted = 0; + const struct xfrm_mode_cbs *cbs; + bool try_load = true; - if (unlikely(encap >= XFRM_MODE_MAX)) + if (mode >= XFRM_MODE_MAX) return NULL; retry: - afinfo = xfrm_state_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return NULL; + rcu_read_lock(); - mode = READ_ONCE(afinfo->mode_map[encap]); - if (unlikely(mode && !try_module_get(mode->owner))) - mode = NULL; + cbs = rcu_dereference(xfrm_mode_cbs_map[mode]); + if (cbs && !try_module_get(cbs->owner)) + cbs = NULL; rcu_read_unlock(); - if (!mode && !modload_attempted) { - request_module("xfrm-mode-%d-%d", family, encap); - modload_attempted = 1; + + if (mode == XFRM_MODE_IPTFS && !cbs && try_load) { + request_module("xfrm-iptfs"); + try_load = false; goto retry; } - return mode; + return cbs; } -static void xfrm_put_mode(struct xfrm_mode *mode) +void xfrm_state_free(struct xfrm_state *x) { - module_put(mode->owner); + kmem_cache_free(xfrm_state_cache, x); } +EXPORT_SYMBOL(xfrm_state_free); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); static void xfrm_state_gc_destroy(struct xfrm_state *x) { - tasklet_hrtimer_cancel(&x->mtimer); - del_timer_sync(&x->rtimer); - kfree(x->aead); - kfree(x->aalg); - kfree(x->ealg); + if (x->mode_cbs && x->mode_cbs->destroy_state) + x->mode_cbs->destroy_state(x); + hrtimer_cancel(&x->mtimer); + 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->inner_mode) - xfrm_put_mode(x->inner_mode); - if (x->inner_mode_iaf) - xfrm_put_mode(x->inner_mode_iaf); - if (x->outer_mode) - xfrm_put_mode(x->outer_mode); - 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); } + if (x->xfrag.page) + put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); - kfree(x); + xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) @@ -463,20 +638,22 @@ static void xfrm_state_gc_task(struct work_struct *work) static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { - struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); - struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); - unsigned long now = get_seconds(); - long next = LONG_MAX; + struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer); + enum hrtimer_restart ret = HRTIMER_NORESTART; + time64_t now = ktime_get_real_seconds(); + time64_t next = TIME64_MAX; int warn = 0; 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) { @@ -493,8 +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) @@ -503,7 +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; @@ -515,8 +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) @@ -527,8 +704,9 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (warn) km_state_expired(x, 0, 0); resched: - if (next != LONG_MAX) { - tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL); + if (next != TIME64_MAX) { + hrtimer_forward_now(&x->mtimer, ktime_set(next, 0)); + ret = HRTIMER_RESTART; } goto out; @@ -545,44 +723,80 @@ expired: out: spin_unlock(&x->lock); - return HRTIMER_NORESTART; + return ret; } -static void xfrm_replay_timer_handler(unsigned long data); +static void xfrm_replay_timer_handler(struct timer_list *t); struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; - x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC); + x = kmem_cache_zalloc(xfrm_state_cache, GFP_ATOMIC); if (x) { write_pnet(&x->xs_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); - tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler, - CLOCK_BOOTTIME, HRTIMER_MODE_ABS); - setup_timer(&x->rtimer, xfrm_replay_timer_handler, - (unsigned long)x); - x->curlft.add_time = get_seconds(); + 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; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; - x->inner_mode = NULL; - x->inner_mode_iaf = NULL; + x->pcpu_num = UINT_MAX; spin_lock_init(&x->lock); + x->mode_data = NULL; } return x; } EXPORT_SYMBOL(xfrm_state_alloc); +#ifdef CONFIG_XFRM_OFFLOAD +void xfrm_dev_state_delete(struct xfrm_state *x) +{ + struct xfrm_dev_offload *xso = &x->xso; + struct net_device *dev = READ_ONCE(xso->dev); + + 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); @@ -601,17 +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); 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. @@ -664,7 +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; @@ -724,17 +949,20 @@ restart: } } } +out: + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) err = 0; -out: - spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } 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); @@ -744,8 +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; @@ -755,6 +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); @@ -771,6 +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); @@ -779,42 +1025,163 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; - si->sadhcnt = net->xfrm.state_hmask; + si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); static void +__xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) +{ + const struct flowi4 *fl4 = &fl->u.ip4; + + sel->daddr.a4 = fl4->daddr; + sel->saddr.a4 = fl4->saddr; + sel->dport = xfrm_flowi_dport(fl, &fl4->uli); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl, &fl4->uli); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET; + sel->prefixlen_d = 32; + sel->prefixlen_s = 32; + sel->proto = fl4->flowi4_proto; + sel->ifindex = fl4->flowi4_oif; +} + +static void +__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) +{ + const struct flowi6 *fl6 = &fl->u.ip6; + + /* Initialize temporary selector matching only to current session. */ + *(struct in6_addr *)&sel->daddr = fl6->daddr; + *(struct in6_addr *)&sel->saddr = fl6->saddr; + sel->dport = xfrm_flowi_dport(fl, &fl6->uli); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl, &fl6->uli); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET6; + sel->prefixlen_d = 128; + sel->prefixlen_s = 128; + sel->proto = fl6->flowi6_proto; + sel->ifindex = fl6->flowi6_oif; +} + +static void xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { - struct xfrm_state_afinfo *afinfo = xfrm_state_afinfo_get_rcu(family); + switch (family) { + case AF_INET: + __xfrm4_init_tempsel(&x->sel, fl); + break; + case AF_INET6: + __xfrm6_init_tempsel(&x->sel, fl); + break; + } - if (!afinfo) - return; + x->id = tmpl->id; - afinfo->init_tempsel(&x->sel, fl); + switch (tmpl->encap_family) { + case AF_INET: + if (x->id.daddr.a4 == 0) + x->id.daddr.a4 = daddr->a4; + x->props.saddr = tmpl->saddr; + if (x->props.saddr.a4 == 0) + x->props.saddr.a4 = saddr->a4; + break; + case AF_INET6: + if (ipv6_addr_any((struct in6_addr *)&x->id.daddr)) + memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); + memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); + if (ipv6_addr_any((struct in6_addr *)&x->props.saddr)) + memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); + break; + } - if (family != tmpl->encap_family) { - afinfo = xfrm_state_afinfo_get_rcu(tmpl->encap_family); - if (!afinfo) - return; + x->props.mode = tmpl->mode; + x->props.reqid = tmpl->reqid; + x->props.family = tmpl->encap_family; +} + +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; } - afinfo->init_temprop(x, tmpl, daddr, saddr); + + 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 || @@ -831,15 +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) || @@ -859,14 +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); @@ -883,7 +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. @@ -898,21 +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; } } @@ -921,9 +1349,10 @@ struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, - unsigned short family) + 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; @@ -934,48 +1363,139 @@ 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 && + 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); + &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 && + 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, 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; @@ -1000,6 +1520,9 @@ found: * to current session. */ 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) { @@ -1008,29 +1531,83 @@ 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; - tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, + ktime_set(net->xfrm.sysctl_acq_expires, 0), + HRTIMER_MODE_REL_SOFT); net->xfrm.state_num++; 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) { @@ -1041,11 +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); @@ -1057,7 +1643,7 @@ out: } struct xfrm_state * -xfrm_stateonly_find(struct net *net, u32 mark, +xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { @@ -1070,6 +1656,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (x->props.family == family && x->props.reqid == 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, family) && mode == x->props.mode && @@ -1111,6 +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); @@ -1118,27 +1725,41 @@ 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); } - tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); 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 */ @@ -1150,11 +1771,15 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) struct xfrm_state *x; 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)) @@ -1177,7 +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, u8 proto, + u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) @@ -1194,6 +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; @@ -1227,20 +1853,26 @@ 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; x->props.mode = mode; x->props.reqid = reqid; + x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); - tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, + 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++; @@ -1250,7 +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) { @@ -1276,7 +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; @@ -1286,7 +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->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); @@ -1309,8 +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); @@ -1335,6 +1992,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); + x->geniv = orig->geniv; if (!x->aead) goto error; } @@ -1364,6 +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); @@ -1377,31 +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; @@ -1417,6 +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, @@ -1432,6 +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, @@ -1450,16 +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)) { @@ -1468,11 +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; } @@ -1502,8 +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; @@ -1525,8 +2230,12 @@ out: err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { - if (x->encap && x1->encap) + if (x->encap && x1->encap && + x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); + else if (x->encap || x1->encap) + goto fail; + if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } @@ -1535,14 +2244,30 @@ out: memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; - tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL); - if (x1->curlft.use_time) + hrtimer_start(&x1->mtimer, ktime_set(1, 0), + HRTIMER_MODE_REL_SOFT); + if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); + if (x->props.smark.m || x->props.smark.v || x->if_id) { + spin_lock_bh(&net->xfrm.xfrm_state_lock); + + if (x->props.smark.m || x->props.smark.v) + x1->props.smark = x->props.smark; + + if (x->if_id) + x1->if_id = x->if_id; + + __xfrm_state_bump_genids(x1); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + } + err = 0; x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } + +fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); @@ -1553,13 +2278,20 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { - if (!x->curlft.use_time) - x->curlft.use_time = get_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) { x->km.state = XFRM_STATE_EXPIRED; - tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT); return -EINVAL; } @@ -1573,14 +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; } @@ -1591,24 +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, - 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, 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; @@ -1616,72 +2369,159 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY -int +#if IS_ENABLED(CONFIG_IPV6) +/* distribution counting sort function for xfrm_state and xfrm_tmpl */ +static void +__xfrm6_sort(void **dst, void **src, int n, + int (*cmp)(const void *p), int maxclass) +{ + int count[XFRM_MAX_DEPTH] = { }; + int class[XFRM_MAX_DEPTH]; + int i; + + for (i = 0; i < n; i++) { + int c = cmp(src[i]); + + class[i] = c; + count[c]++; + } + + for (i = 2; i < maxclass; i++) + count[i] += count[i - 1]; + + for (i = 0; i < n; i++) { + dst[count[class[i] - 1]++] = src[i]; + src[i] = NULL; + } +} + +/* Rule for xfrm_state: + * + * rule 1: select IPsec transport except AH + * rule 2: select MIPv6 RO or inbound trigger + * rule 3: select IPsec transport AH + * rule 4: select IPsec tunnel + * rule 5: others + */ +static int __xfrm6_state_sort_cmp(const void *p) +{ + const struct xfrm_state *v = p; + + switch (v->props.mode) { + case XFRM_MODE_TRANSPORT: + if (v->id.proto != IPPROTO_AH) + return 1; + else + return 3; +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case XFRM_MODE_ROUTEOPTIMIZATION: + case XFRM_MODE_IN_TRIGGER: + return 2; +#endif + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + case XFRM_MODE_IPTFS: + return 4; + } + return 5; +} + +/* Rule for xfrm_tmpl: + * + * rule 1: select IPsec transport + * rule 2: select MIPv6 RO or inbound trigger + * rule 3: select IPsec tunnel + * rule 4: others + */ +static int __xfrm6_tmpl_sort_cmp(const void *p) +{ + const struct xfrm_tmpl *v = p; + + switch (v->mode) { + case XFRM_MODE_TRANSPORT: + return 1; +#if IS_ENABLED(CONFIG_IPV6_MIP6) + case XFRM_MODE_ROUTEOPTIMIZATION: + case XFRM_MODE_IN_TRIGGER: + return 2; +#endif + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + case XFRM_MODE_IPTFS: + return 3; + } + return 4; +} +#else +static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; } +static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; } + +static inline void +__xfrm6_sort(void **dst, void **src, int n, + int (*cmp)(const void *p), int maxclass) +{ + int i; + + for (i = 0; i < n; i++) + dst[i] = src[i]; +} +#endif /* CONFIG_IPV6 */ + +void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, - unsigned short family, struct net *net) + unsigned short family) { - int err = 0; - struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - if (!afinfo) - return -EAFNOSUPPORT; + int i; - spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/ - if (afinfo->tmpl_sort) - err = afinfo->tmpl_sort(dst, src, n); - spin_unlock_bh(&net->xfrm.xfrm_state_lock); - rcu_read_unlock(); - return err; + if (family == AF_INET6) + __xfrm6_sort((void **)dst, (void **)src, n, + __xfrm6_tmpl_sort_cmp, 5); + else + for (i = 0; i < n; i++) + dst[i] = src[i]; } -EXPORT_SYMBOL(xfrm_tmpl_sort); -int +void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family) { - int err = 0; - struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); - struct net *net = xs_net(*src); - - if (!afinfo) - return -EAFNOSUPPORT; + int i; - spin_lock_bh(&net->xfrm.xfrm_state_lock); - if (afinfo->state_sort) - err = afinfo->state_sort(dst, src, n); - spin_unlock_bh(&net->xfrm.xfrm_state_lock); - rcu_read_unlock(); - return err; + if (family == AF_INET6) + __xfrm6_sort((void **)dst, (void **)src, n, + __xfrm6_state_sort_cmp, 6); + else + for (i = 0; i < n; i++) + dst[i] = src[i]; } -EXPORT_SYMBOL(xfrm_state_sort); #endif /* 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; } @@ -1700,7 +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: @@ -1709,34 +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) @@ -1744,34 +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); @@ -1862,15 +2713,15 @@ void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) } EXPORT_SYMBOL(xfrm_state_walk_done); -static void xfrm_replay_timer_handler(unsigned long data) +static void xfrm_replay_timer_handler(struct timer_list *t) { - struct xfrm_state *x = (struct xfrm_state *)data; + 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; } @@ -1935,7 +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; @@ -1950,6 +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) @@ -2007,7 +2876,7 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address } EXPORT_SYMBOL(km_report); -bool km_is_alive(const struct km_event *c) +static bool km_is_alive(const struct km_event *c) { struct xfrm_mgr *km; bool is_alive = false; @@ -2023,22 +2892,104 @@ bool km_is_alive(const struct km_event *c) return is_alive; } -EXPORT_SYMBOL(km_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 (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); + return 0; + } + 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) { @@ -2052,6 +3003,7 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); + __sk_dst_reset(sk); err = 0; } @@ -2062,22 +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); @@ -2125,6 +3075,7 @@ struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family) return rcu_dereference(xfrm_state_afinfo[family]); } +EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) { @@ -2138,80 +3089,98 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) return afinfo; } -/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ -void xfrm_state_delete_tunnel(struct xfrm_state *x) +void xfrm_flush_gc(void) +{ + flush_work(&xfrm_state_gc_work); +} +EXPORT_SYMBOL(xfrm_flush_gc); + +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(t); x->tunnel = NULL; } } -EXPORT_SYMBOL(xfrm_state_delete_tunnel); -int xfrm_state_mtu(struct xfrm_state *x, int mtu) +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); + struct crypto_aead *aead; + u32 blksize, net_adj = 0; + + if (x->km.state != XFRM_STATE_VALID || + !type || type->proto != IPPROTO_ESP) + return mtu - x->props.header_len; - if (x->km.state == XFRM_STATE_VALID && - type && type->get_mtu) - return type->get_mtu(x, mtu); + aead = x->data; + blksize = ALIGN(crypto_aead_blocksize(aead), 4); + + switch (x->props.mode) { + case XFRM_MODE_TRANSPORT: + case XFRM_MODE_BEET: + if (x->props.family == AF_INET) + net_adj = sizeof(struct iphdr); + else if (x->props.family == AF_INET6) + net_adj = sizeof(struct ipv6hdr); + break; + 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); - return mtu - x->props.header_len; + WARN_ON_ONCE(1); + break; + } + + return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - + net_adj) & ~(blksize - 1)) + net_adj - 2; } +EXPORT_SYMBOL_GPL(xfrm_state_mtu); -int __xfrm_init_state(struct xfrm_state *x, bool init_replay) +int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { - struct xfrm_state_afinfo *afinfo; - struct xfrm_mode *inner_mode; + const struct xfrm_mode *inner_mode; + const struct xfrm_mode *outer_mode; int family = x->props.family; int err; - err = -EAFNOSUPPORT; - afinfo = xfrm_state_get_afinfo(family); - if (!afinfo) - goto error; - - err = 0; - if (afinfo->init_flags) - err = afinfo->init_flags(x); - - rcu_read_unlock(); - - if (err) - goto error; + if (family == AF_INET && + 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) { - xfrm_put_mode(inner_mode); + NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family"); goto error; } - x->inner_mode = inner_mode; + x->inner_mode = *inner_mode; } else { - struct xfrm_mode *inner_mode_iaf; + const struct xfrm_mode *inner_mode_iaf; 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)) { - xfrm_put_mode(inner_mode); + if (inner_mode == NULL) { + NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } - x->inner_mode = inner_mode; + + x->inner_mode = *inner_mode; if (x->props.family == AF_INET) iafamily = AF_INET6; @@ -2219,36 +3188,49 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay) inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily); if (inner_mode_iaf) { if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL) - x->inner_mode_iaf = inner_mode_iaf; - else - xfrm_put_mode(inner_mode_iaf); + x->inner_mode_iaf = *inner_mode_iaf; } } 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); - - err = x->type->init_state(x); + err = x->type->init_state(x, extack); if (err) goto error; - x->outer_mode = xfrm_get_mode(x->props.mode, family); - if (x->outer_mode == NULL) { + 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; } - if (init_replay) { - err = xfrm_init_replay(x); - if (err) + x->outer_mode = *outer_mode; + 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; - } + } - x->km.state = XFRM_STATE_VALID; + 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; } @@ -2257,7 +3239,18 @@ EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x) { - return __xfrm_init_state(x, true); + int err; + + err = __xfrm_init_state(x, NULL); + if (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); @@ -2266,6 +3259,10 @@ int __net_init xfrm_state_init(struct net *net) { unsigned int sz; + if (net_eq(net, &init_net)) + xfrm_state_cache = KMEM_CACHE(xfrm_state, + SLAB_HWCACHE_ALIGN | SLAB_PANIC); + INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; @@ -2279,13 +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: @@ -2297,20 +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, IPSEC_PROTO_ANY, false); + xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); 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 |