From aa6f5ffbdba45aa8e19e5048648fc6c7b25376d3 Mon Sep 17 00:00:00 2001 From: merge Date: Thu, 22 Jan 2009 13:55:32 +0000 Subject: MERGE-via-pending-tracking-hist-MERGE-via-stable-tracking-MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040-1232632141 pending-tracking-hist top was MERGE-via-stable-tracking-MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040-1232632141 / fdf777a63bcb59e0dfd78bfe2c6242e01f6d4eb9 ... parent commitmessage: From: merge MERGE-via-stable-tracking-hist-MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040 stable-tracking-hist top was MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040 / 90463bfd2d5a3c8b52f6e6d71024a00e052b0ced ... parent commitmessage: From: merge MERGE-via-mokopatches-tracking-hist-fix-stray-endmenu-patch mokopatches-tracking-hist top was fix-stray-endmenu-patch / 3630e0be570de8057e7f8d2fe501ed353cdf34e6 ... parent commitmessage: From: Andy Green fix-stray-endmenu.patch Signed-off-by: Andy Green --- net/xfrm/Makefile | 4 +- net/xfrm/xfrm_input.c | 25 +-- net/xfrm/xfrm_ipcomp.c | 1 - net/xfrm/xfrm_output.c | 18 +- net/xfrm/xfrm_policy.c | 510 ++++++++++++++++++++++++++++--------------------- net/xfrm/xfrm_proc.c | 41 ++-- net/xfrm/xfrm_state.c | 407 ++++++++++++++++++++------------------- net/xfrm/xfrm_sysctl.c | 85 +++++++++ net/xfrm/xfrm_user.c | 260 ++++++++++++++++++------- 9 files changed, 815 insertions(+), 536 deletions(-) create mode 100644 net/xfrm/xfrm_sysctl.c (limited to 'net/xfrm') diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 0f439a72cca..c631047e1b2 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -3,8 +3,8 @@ # obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ - xfrm_input.o xfrm_output.o xfrm_algo.o + xfrm_input.o xfrm_output.o xfrm_algo.o \ + xfrm_sysctl.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o - diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 75279402ccf..b4a13178fb4 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -104,6 +104,7 @@ EXPORT_SYMBOL(xfrm_prepare_input); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { + struct net *net = dev_net(skb->dev); int err; __be32 seq; struct xfrm_state *x; @@ -127,7 +128,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) sp = secpath_dup(skb->sp); if (!sp) { - XFRM_INC_STATS(LINUX_MIB_XFRMINERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); goto drop; } if (skb->sp) @@ -141,19 +142,19 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) seq = 0; if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) { - XFRM_INC_STATS(LINUX_MIB_XFRMINHDRERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } do { if (skb->sp->len == XFRM_MAX_DEPTH) { - XFRM_INC_STATS(LINUX_MIB_XFRMINBUFFERERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto drop; } - x = xfrm_state_lookup(daddr, spi, nexthdr, family); + x = xfrm_state_lookup(net, daddr, spi, nexthdr, family); if (x == NULL) { - XFRM_INC_STATS(LINUX_MIB_XFRMINNOSTATES); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES); xfrm_audit_state_notfound(skb, family, spi, seq); goto drop; } @@ -162,22 +163,22 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) spin_lock(&x->lock); if (unlikely(x->km.state != XFRM_STATE_VALID)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEINVALID); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); goto drop_unlock; } if ((x->encap ? x->encap->encap_type : 0) != encap_type) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); goto drop_unlock; } if (x->props.replay_window && xfrm_replay_check(x, skb, seq)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATESEQERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR); goto drop_unlock; } if (xfrm_state_check_expire(x)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEEXPIRED); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEEXPIRED); goto drop_unlock; } @@ -198,7 +199,7 @@ resume: x->type->proto); x->stats.integrity_failed++; } - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEPROTOERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR); goto drop_unlock; } @@ -224,7 +225,7 @@ resume: } if (inner_mode->input(x, skb)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEMODEERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMODEERROR); goto drop; } @@ -242,7 +243,7 @@ resume: err = xfrm_parse_spi(skb, nexthdr, &spi, &seq); if (err < 0) { - XFRM_INC_STATS(LINUX_MIB_XFRMINHDRERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); goto drop; } } while (!err); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index c609a4b98e1..42cd18391f4 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -63,7 +63,6 @@ static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) if (len > skb_tailroom(skb)) len = skb_tailroom(skb); - skb->truesize += len; __skb_put(skb, len); len += plen; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index dc50f1e71f7..c235597ba8d 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -41,6 +41,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) { struct dst_entry *dst = skb->dst; struct xfrm_state *x = dst->xfrm; + struct net *net = xs_net(x); if (err <= 0) goto resume; @@ -48,33 +49,33 @@ static int xfrm_output_one(struct sk_buff *skb, int err) do { err = xfrm_state_check_space(x, skb); if (err) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); goto error_nolock; } err = x->outer_mode->output(x, skb); if (err) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTSTATEMODEERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); goto error_nolock; } spin_lock_bh(&x->lock); err = xfrm_state_check_expire(x); if (err) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTSTATEEXPIRED); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED); goto error; } if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output = ++x->replay.oseq; if (unlikely(x->replay.oseq == 0)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTSTATESEQERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR); x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; goto error; } - if (xfrm_aevent_is_on()) + if (xfrm_aevent_is_on(net)) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } @@ -89,12 +90,12 @@ static int xfrm_output_one(struct sk_buff *skb, int err) resume: if (err) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTSTATEPROTOERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); goto error_nolock; } if (!(skb->dst = dst_pop(dst))) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); err = -EHOSTUNREACH; goto error_nolock; } @@ -178,6 +179,7 @@ static int xfrm_output_gso(struct sk_buff *skb) int xfrm_output(struct sk_buff *skb) { + struct net *net = dev_net(skb->dst->dev); int err; if (skb_is_gso(skb)) @@ -186,7 +188,7 @@ int xfrm_output(struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); if (err) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); kfree_skb(skb); return err; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 058f04f54b9..9c068ab3a83 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -34,28 +34,16 @@ #include "xfrm_hash.h" -int sysctl_xfrm_larval_drop __read_mostly = 1; - -#ifdef CONFIG_XFRM_STATISTICS -DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics) __read_mostly; -EXPORT_SYMBOL(xfrm_statistics); -#endif - DEFINE_MUTEX(xfrm_cfg_mutex); EXPORT_SYMBOL(xfrm_cfg_mutex); static DEFINE_RWLOCK(xfrm_policy_lock); -static struct list_head xfrm_policy_all; -unsigned int xfrm_policy_count[XFRM_POLICY_MAX*2]; -EXPORT_SYMBOL(xfrm_policy_count); - static DEFINE_RWLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo *xfrm_policy_afinfo[NPROTO]; static struct kmem_cache *xfrm_dst_cache __read_mostly; -static struct work_struct xfrm_policy_gc_work; static HLIST_HEAD(xfrm_policy_gc_list); static DEFINE_SPINLOCK(xfrm_policy_gc_lock); @@ -63,6 +51,9 @@ static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); static void xfrm_init_pmtu(struct dst_entry *dst); +static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, + int dir); + static inline int __xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl) { @@ -97,7 +88,7 @@ int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, return 0; } -static inline struct dst_entry *__xfrm_dst_lookup(int tos, +static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, xfrm_address_t *saddr, xfrm_address_t *daddr, int family) @@ -109,7 +100,7 @@ static inline struct dst_entry *__xfrm_dst_lookup(int tos, if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); - dst = afinfo->dst_lookup(tos, saddr, daddr); + dst = afinfo->dst_lookup(net, tos, saddr, daddr); xfrm_policy_put_afinfo(afinfo); @@ -121,6 +112,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, xfrm_address_t *prev_daddr, int family) { + struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; xfrm_address_t *daddr = &x->id.daddr; struct dst_entry *dst; @@ -134,7 +126,7 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, int tos, daddr = x->coaddr; } - dst = __xfrm_dst_lookup(tos, saddr, daddr, family); + dst = __xfrm_dst_lookup(net, tos, saddr, daddr, family); if (!IS_ERR(dst)) { if (prev_saddr != saddr) @@ -229,13 +221,14 @@ expired: * SPD calls. */ -struct xfrm_policy *xfrm_policy_alloc(gfp_t gfp) +struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) { struct xfrm_policy *policy; policy = kzalloc(sizeof(struct xfrm_policy), gfp); if (policy) { + write_pnet(&policy->xp_net, net); INIT_LIST_HEAD(&policy->walk.all); INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); @@ -296,6 +289,7 @@ static void xfrm_policy_gc_task(struct work_struct *work) hlist_for_each_entry_safe(policy, entry, tmp, &gc_list, bydst) xfrm_policy_gc_kill(policy); } +static DECLARE_WORK(xfrm_policy_gc_work, xfrm_policy_gc_task); /* Rule must be locked. Release descentant resources, announce * entry dead. The rule must be unlinked from lists to the moment. @@ -322,38 +316,29 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) schedule_work(&xfrm_policy_gc_work); } -struct xfrm_policy_hash { - struct hlist_head *table; - unsigned int hmask; -}; - -static struct hlist_head xfrm_policy_inexact[XFRM_POLICY_MAX*2]; -static struct xfrm_policy_hash xfrm_policy_bydst[XFRM_POLICY_MAX*2] __read_mostly; -static struct hlist_head *xfrm_policy_byidx __read_mostly; -static unsigned int xfrm_idx_hmask __read_mostly; static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; -static inline unsigned int idx_hash(u32 index) +static inline unsigned int idx_hash(struct net *net, u32 index) { - return __idx_hash(index, xfrm_idx_hmask); + return __idx_hash(index, net->xfrm.policy_idx_hmask); } -static struct hlist_head *policy_hash_bysel(struct xfrm_selector *sel, unsigned short family, int dir) +static struct hlist_head *policy_hash_bysel(struct net *net, struct xfrm_selector *sel, unsigned short family, int dir) { - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash = __sel_hash(sel, family, hmask); return (hash == hmask + 1 ? - &xfrm_policy_inexact[dir] : - xfrm_policy_bydst[dir].table + hash); + &net->xfrm.policy_inexact[dir] : + net->xfrm.policy_bydst[dir].table + hash); } -static struct hlist_head *policy_hash_direct(xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, int dir) +static struct hlist_head *policy_hash_direct(struct net *net, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, int dir) { - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash = __addr_hash(daddr, saddr, family, hmask); - return xfrm_policy_bydst[dir].table + hash; + return net->xfrm.policy_bydst[dir].table + hash; } static void xfrm_dst_hash_transfer(struct hlist_head *list, @@ -408,12 +393,12 @@ static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) return ((old_hmask + 1) << 1) - 1; } -static void xfrm_bydst_resize(int dir) +static void xfrm_bydst_resize(struct net *net, int dir) { - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); - struct hlist_head *odst = xfrm_policy_bydst[dir].table; + struct hlist_head *odst = net->xfrm.policy_bydst[dir].table; struct hlist_head *ndst = xfrm_hash_alloc(nsize); int i; @@ -425,20 +410,20 @@ static void xfrm_bydst_resize(int dir) for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(odst + i, ndst, nhashmask); - xfrm_policy_bydst[dir].table = ndst; - xfrm_policy_bydst[dir].hmask = nhashmask; + net->xfrm.policy_bydst[dir].table = ndst; + net->xfrm.policy_bydst[dir].hmask = nhashmask; write_unlock_bh(&xfrm_policy_lock); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } -static void xfrm_byidx_resize(int total) +static void xfrm_byidx_resize(struct net *net, int total) { - unsigned int hmask = xfrm_idx_hmask; + unsigned int hmask = net->xfrm.policy_idx_hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); - struct hlist_head *oidx = xfrm_policy_byidx; + struct hlist_head *oidx = net->xfrm.policy_byidx; struct hlist_head *nidx = xfrm_hash_alloc(nsize); int i; @@ -450,18 +435,18 @@ static void xfrm_byidx_resize(int total) for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); - xfrm_policy_byidx = nidx; - xfrm_idx_hmask = nhashmask; + net->xfrm.policy_byidx = nidx; + net->xfrm.policy_idx_hmask = nhashmask; write_unlock_bh(&xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } -static inline int xfrm_bydst_should_resize(int dir, int *total) +static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total) { - unsigned int cnt = xfrm_policy_count[dir]; - unsigned int hmask = xfrm_policy_bydst[dir].hmask; + unsigned int cnt = net->xfrm.policy_count[dir]; + unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; if (total) *total += cnt; @@ -473,9 +458,9 @@ static inline int xfrm_bydst_should_resize(int dir, int *total) return 0; } -static inline int xfrm_byidx_should_resize(int total) +static inline int xfrm_byidx_should_resize(struct net *net, int total) { - unsigned int hmask = xfrm_idx_hmask; + unsigned int hmask = net->xfrm.policy_idx_hmask; if ((hmask + 1) < xfrm_policy_hashmax && total > hmask) @@ -487,41 +472,40 @@ static inline int xfrm_byidx_should_resize(int total) void xfrm_spd_getinfo(struct xfrmk_spdinfo *si) { read_lock_bh(&xfrm_policy_lock); - si->incnt = xfrm_policy_count[XFRM_POLICY_IN]; - si->outcnt = xfrm_policy_count[XFRM_POLICY_OUT]; - si->fwdcnt = xfrm_policy_count[XFRM_POLICY_FWD]; - si->inscnt = xfrm_policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; - si->outscnt = xfrm_policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; - si->fwdscnt = xfrm_policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; - si->spdhcnt = xfrm_idx_hmask; + si->incnt = init_net.xfrm.policy_count[XFRM_POLICY_IN]; + si->outcnt = init_net.xfrm.policy_count[XFRM_POLICY_OUT]; + si->fwdcnt = init_net.xfrm.policy_count[XFRM_POLICY_FWD]; + si->inscnt = init_net.xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; + si->outscnt = init_net.xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; + si->fwdscnt = init_net.xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; + si->spdhcnt = init_net.xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; read_unlock_bh(&xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_spd_getinfo); static DEFINE_MUTEX(hash_resize_mutex); -static void xfrm_hash_resize(struct work_struct *__unused) +static void xfrm_hash_resize(struct work_struct *work) { + struct net *net = container_of(work, struct net, xfrm.policy_hash_work); int dir, total; mutex_lock(&hash_resize_mutex); total = 0; for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { - if (xfrm_bydst_should_resize(dir, &total)) - xfrm_bydst_resize(dir); + if (xfrm_bydst_should_resize(net, dir, &total)) + xfrm_bydst_resize(net, dir); } - if (xfrm_byidx_should_resize(total)) - xfrm_byidx_resize(total); + if (xfrm_byidx_should_resize(net, total)) + xfrm_byidx_resize(net, total); mutex_unlock(&hash_resize_mutex); } -static DECLARE_WORK(xfrm_hash_work, xfrm_hash_resize); - /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ -static u32 xfrm_gen_index(u8 type, int dir) +static u32 xfrm_gen_index(struct net *net, int dir) { static u32 idx_generator; @@ -536,7 +520,7 @@ static u32 xfrm_gen_index(u8 type, int dir) idx_generator += 8; if (idx == 0) idx = 8; - list = xfrm_policy_byidx + idx_hash(idx); + list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; hlist_for_each_entry(p, entry, list, byidx) { if (p->index == idx) { @@ -566,6 +550,7 @@ static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { + struct net *net = xp_net(policy); struct xfrm_policy *pol; struct xfrm_policy *delpol; struct hlist_head *chain; @@ -573,7 +558,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct dst_entry *gc_list; write_lock_bh(&xfrm_policy_lock); - chain = policy_hash_bysel(&policy->selector, policy->family, dir); + chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); delpol = NULL; newpos = NULL; hlist_for_each_entry(pol, entry, chain, bydst) { @@ -600,27 +585,23 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) else hlist_add_head(&policy->bydst, chain); xfrm_pol_hold(policy); - xfrm_policy_count[dir]++; + net->xfrm.policy_count[dir]++; atomic_inc(&flow_cache_genid); - if (delpol) { - hlist_del(&delpol->bydst); - hlist_del(&delpol->byidx); - list_del(&delpol->walk.all); - xfrm_policy_count[dir]--; - } - policy->index = delpol ? delpol->index : xfrm_gen_index(policy->type, dir); - hlist_add_head(&policy->byidx, xfrm_policy_byidx+idx_hash(policy->index)); + if (delpol) + __xfrm_policy_unlink(delpol, dir); + policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir); + hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = get_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); - list_add(&policy->walk.all, &xfrm_policy_all); + list_add(&policy->walk.all, &net->xfrm.policy_all); write_unlock_bh(&xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); - else if (xfrm_bydst_should_resize(dir, NULL)) - schedule_work(&xfrm_hash_work); + else if (xfrm_bydst_should_resize(net, dir, NULL)) + schedule_work(&net->xfrm.policy_hash_work); read_lock_bh(&xfrm_policy_lock); gc_list = NULL; @@ -654,7 +635,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) } EXPORT_SYMBOL(xfrm_policy_insert); -struct xfrm_policy *xfrm_policy_bysel_ctx(u8 type, int dir, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) @@ -665,7 +646,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(u8 type, int dir, *err = 0; write_lock_bh(&xfrm_policy_lock); - chain = policy_hash_bysel(sel, sel->family, dir); + chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; hlist_for_each_entry(pol, entry, chain, bydst) { if (pol->type == type && @@ -679,10 +660,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(u8 type, int dir, write_unlock_bh(&xfrm_policy_lock); return pol; } - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - list_del(&pol->walk.all); - xfrm_policy_count[dir]--; + __xfrm_policy_unlink(pol, dir); } ret = pol; break; @@ -698,8 +676,8 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(u8 type, int dir, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(u8 type, int dir, u32 id, int delete, - int *err) +struct xfrm_policy *xfrm_policy_byid(struct net *net, u8 type, int dir, u32 id, + int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -711,7 +689,7 @@ struct xfrm_policy *xfrm_policy_byid(u8 type, int dir, u32 id, int delete, *err = 0; write_lock_bh(&xfrm_policy_lock); - chain = xfrm_policy_byidx + idx_hash(id); + chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, entry, chain, byidx) { if (pol->type == type && pol->index == id) { @@ -723,10 +701,7 @@ struct xfrm_policy *xfrm_policy_byid(u8 type, int dir, u32 id, int delete, write_unlock_bh(&xfrm_policy_lock); return pol; } - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - list_del(&pol->walk.all); - xfrm_policy_count[dir]--; + __xfrm_policy_unlink(pol, dir); } ret = pol; break; @@ -744,7 +719,7 @@ EXPORT_SYMBOL(xfrm_policy_byid); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int -xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) +xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info) { int dir, err = 0; @@ -754,7 +729,7 @@ xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) int i; hlist_for_each_entry(pol, entry, - &xfrm_policy_inexact[dir], bydst) { + &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; err = security_xfrm_policy_delete(pol->security); @@ -766,9 +741,9 @@ xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) return err; } } - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { hlist_for_each_entry(pol, entry, - xfrm_policy_bydst[dir].table + i, + net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) continue; @@ -788,35 +763,33 @@ xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) } #else static inline int -xfrm_policy_flush_secctx_check(u8 type, struct xfrm_audit *audit_info) +xfrm_policy_flush_secctx_check(struct net *net, u8 type, struct xfrm_audit *audit_info) { return 0; } #endif -int xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info) +int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) { int dir, err = 0; write_lock_bh(&xfrm_policy_lock); - err = xfrm_policy_flush_secctx_check(type, audit_info); + err = xfrm_policy_flush_secctx_check(net, type, audit_info); if (err) goto out; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy *pol; struct hlist_node *entry; - int i, killed; + int i; - killed = 0; again1: hlist_for_each_entry(pol, entry, - &xfrm_policy_inexact[dir], bydst) { + &net->xfrm.policy_inexact[dir], bydst) { if (pol->type != type) continue; - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); + __xfrm_policy_unlink(pol, dir); write_unlock_bh(&xfrm_policy_lock); xfrm_audit_policy_delete(pol, 1, audit_info->loginuid, @@ -824,22 +797,19 @@ int xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info) audit_info->secid); xfrm_policy_kill(pol); - killed++; write_lock_bh(&xfrm_policy_lock); goto again1; } - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { again2: hlist_for_each_entry(pol, entry, - xfrm_policy_bydst[dir].table + i, + net->xfrm.policy_bydst[dir].table + i, bydst) { if (pol->type != type) continue; - hlist_del(&pol->bydst); - hlist_del(&pol->byidx); - list_del(&pol->walk.all); + __xfrm_policy_unlink(pol, dir); write_unlock_bh(&xfrm_policy_lock); xfrm_audit_policy_delete(pol, 1, @@ -847,14 +817,12 @@ int xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info) audit_info->sessionid, audit_info->secid); xfrm_policy_kill(pol); - killed++; write_lock_bh(&xfrm_policy_lock); goto again2; } } - xfrm_policy_count[dir] -= killed; } atomic_inc(&flow_cache_genid); out: @@ -863,7 +831,7 @@ out: } EXPORT_SYMBOL(xfrm_policy_flush); -int xfrm_policy_walk(struct xfrm_policy_walk *walk, +int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *data) { @@ -880,10 +848,10 @@ int xfrm_policy_walk(struct xfrm_policy_walk *walk, write_lock_bh(&xfrm_policy_lock); if (list_empty(&walk->walk.all)) - x = list_first_entry(&xfrm_policy_all, struct xfrm_policy_walk_entry, all); + x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else x = list_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); - list_for_each_entry_from(x, &xfrm_policy_all, all) { + list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; pol = container_of(x, struct xfrm_policy, walk); @@ -952,7 +920,8 @@ static int xfrm_policy_match(struct xfrm_policy *pol, struct flowi *fl, return ret; } -static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, +static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, + struct flowi *fl, u16 family, u8 dir) { int err; @@ -968,7 +937,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, return NULL; read_lock_bh(&xfrm_policy_lock); - chain = policy_hash_direct(daddr, saddr, family, dir); + chain = policy_hash_direct(net, daddr, saddr, family, dir); ret = NULL; hlist_for_each_entry(pol, entry, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); @@ -985,7 +954,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(u8 type, struct flowi *fl, break; } } - chain = &xfrm_policy_inexact[dir]; + chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, entry, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, dir); if (err) { @@ -1008,14 +977,14 @@ fail: return ret; } -static int xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, - void **objp, atomic_t **obj_refp) +static int xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, + u8 dir, void **objp, atomic_t **obj_refp) { struct xfrm_policy *pol; int err = 0; #ifdef CONFIG_XFRM_SUB_POLICY - pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_SUB, fl, family, dir); + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); if (IS_ERR(pol)) { err = PTR_ERR(pol); pol = NULL; @@ -1023,7 +992,7 @@ static int xfrm_policy_lookup(struct flowi *fl, u16 family, u8 dir, if (pol || err) goto end; #endif - pol = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, fl, family, dir); + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); if (IS_ERR(pol)) { err = PTR_ERR(pol); pol = NULL; @@ -1082,29 +1051,32 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struc static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { - struct hlist_head *chain = policy_hash_bysel(&pol->selector, + struct net *net = xp_net(pol); + struct hlist_head *chain = policy_hash_bysel(net, &pol->selector, pol->family, dir); - list_add(&pol->walk.all, &xfrm_policy_all); + list_add(&pol->walk.all, &net->xfrm.policy_all); hlist_add_head(&pol->bydst, chain); - hlist_add_head(&pol->byidx, xfrm_policy_byidx+idx_hash(pol->index)); - xfrm_policy_count[dir]++; + hlist_add_head(&pol->byidx, net->xfrm.policy_byidx+idx_hash(net, pol->index)); + net->xfrm.policy_count[dir]++; xfrm_pol_hold(pol); - if (xfrm_bydst_should_resize(dir, NULL)) - schedule_work(&xfrm_hash_work); + if (xfrm_bydst_should_resize(net, dir, NULL)) + schedule_work(&net->xfrm.policy_hash_work); } static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir) { + struct net *net = xp_net(pol); + if (hlist_unhashed(&pol->bydst)) return NULL; hlist_del(&pol->bydst); hlist_del(&pol->byidx); list_del(&pol->walk.all); - xfrm_policy_count[dir]--; + net->xfrm.policy_count[dir]--; return pol; } @@ -1126,6 +1098,7 @@ EXPORT_SYMBOL(xfrm_policy_delete); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { + struct net *net = xp_net(pol); struct xfrm_policy *old_pol; #ifdef CONFIG_XFRM_SUB_POLICY @@ -1138,7 +1111,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) sk->sk_policy[dir] = pol; if (pol) { pol->curlft.add_time = get_seconds(); - pol->index = xfrm_gen_index(pol->type, XFRM_POLICY_MAX+dir); + pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir); __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir); } if (old_pol) @@ -1153,7 +1126,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) static struct xfrm_policy *clone_policy(struct xfrm_policy *old, int dir) { - struct xfrm_policy *newp = xfrm_policy_alloc(GFP_ATOMIC); + struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); if (newp) { newp->selector = old->selector; @@ -1193,7 +1166,7 @@ int __xfrm_sk_clone_policy(struct sock *sk) } static int -xfrm_get_saddr(xfrm_address_t *local, xfrm_address_t *remote, +xfrm_get_saddr(struct net *net, xfrm_address_t *local, xfrm_address_t *remote, unsigned short family) { int err; @@ -1201,7 +1174,7 @@ xfrm_get_saddr(xfrm_address_t *local, xfrm_address_t *remote, if (unlikely(afinfo == NULL)) return -EINVAL; - err = afinfo->get_saddr(local, remote); + err = afinfo->get_saddr(net, local, remote); xfrm_policy_put_afinfo(afinfo); return err; } @@ -1213,6 +1186,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { + struct net *net = xp_net(policy); int nx; int i, error; xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); @@ -1231,7 +1205,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, local = &tmpl->saddr; family = tmpl->encap_family; if (xfrm_addr_any(local, family)) { - error = xfrm_get_saddr(&tmp, remote, family); + error = xfrm_get_saddr(net, &tmp, remote, family); if (error) goto fail; local = &tmp; @@ -1545,7 +1519,7 @@ static int stale_bundle(struct dst_entry *dst); * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. */ -int __xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, +int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl, struct sock *sk, int flags) { struct xfrm_policy *policy; @@ -1575,7 +1549,7 @@ restart: policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); err = PTR_ERR(policy); if (IS_ERR(policy)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); goto dropdst; } } @@ -1583,14 +1557,14 @@ restart: if (!policy) { /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || - !xfrm_policy_count[XFRM_POLICY_OUT]) + !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; - policy = flow_cache_lookup(fl, dst_orig->ops->family, + policy = flow_cache_lookup(net, fl, dst_orig->ops->family, dir, xfrm_policy_lookup); err = PTR_ERR(policy); if (IS_ERR(policy)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); goto dropdst; } } @@ -1613,7 +1587,7 @@ restart: default: case XFRM_POLICY_BLOCK: /* Prohibit the flow */ - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLBLOCK); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; @@ -1633,7 +1607,7 @@ restart: */ dst = xfrm_find_bundle(fl, policy, family); if (IS_ERR(dst)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLECHECKERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); err = PTR_ERR(dst); goto error; } @@ -1643,17 +1617,18 @@ restart: #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { - pols[1] = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, + pols[1] = xfrm_policy_lookup_bytype(net, + XFRM_POLICY_TYPE_MAIN, fl, family, XFRM_POLICY_OUT); if (pols[1]) { if (IS_ERR(pols[1])) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); err = PTR_ERR(pols[1]); goto error; } if (pols[1]->action == XFRM_POLICY_BLOCK) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLBLOCK); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; } @@ -1680,27 +1655,27 @@ restart: if (unlikely(nx<0)) { err = nx; - if (err == -EAGAIN && sysctl_xfrm_larval_drop) { + if (err == -EAGAIN && net->xfrm.sysctl_larval_drop) { /* EREMOTE tells the caller to generate * a one-shot blackhole route. */ - XFRM_INC_STATS(LINUX_MIB_XFRMOUTNOSTATES); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); xfrm_pol_put(policy); return -EREMOTE; } if (err == -EAGAIN && (flags & XFRM_LOOKUP_WAIT)) { DECLARE_WAITQUEUE(wait, current); - add_wait_queue(&km_waitq, &wait); + add_wait_queue(&net->xfrm.km_waitq, &wait); set_current_state(TASK_INTERRUPTIBLE); schedule(); set_current_state(TASK_RUNNING); - remove_wait_queue(&km_waitq, &wait); + remove_wait_queue(&net->xfrm.km_waitq, &wait); nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); if (nx == -EAGAIN && signal_pending(current)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTNOSTATES); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); err = -ERESTART; goto error; } @@ -1712,7 +1687,7 @@ restart: err = nx; } if (err < 0) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTNOSTATES); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; } } @@ -1725,7 +1700,7 @@ restart: dst = xfrm_bundle_create(policy, xfrm, nx, fl, dst_orig); err = PTR_ERR(dst); if (IS_ERR(dst)) { - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLEGENERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); goto error; } @@ -1746,9 +1721,9 @@ restart: dst_free(dst); if (pol_dead) - XFRM_INC_STATS(LINUX_MIB_XFRMOUTPOLDEAD); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLDEAD); else - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLECHECKERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); err = -EHOSTUNREACH; goto error; } @@ -1760,7 +1735,7 @@ restart: if (unlikely(err)) { write_unlock_bh(&policy->lock); dst_free(dst); - XFRM_INC_STATS(LINUX_MIB_XFRMOUTBUNDLECHECKERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); goto error; } @@ -1789,10 +1764,10 @@ nopol: } EXPORT_SYMBOL(__xfrm_lookup); -int xfrm_lookup(struct dst_entry **dst_p, struct flowi *fl, +int xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl, struct sock *sk, int flags) { - int err = __xfrm_lookup(dst_p, fl, sk, flags); + int err = __xfrm_lookup(net, dst_p, fl, sk, flags); if (err == -EREMOTE) { dst_release(*dst_p); @@ -1900,6 +1875,7 @@ static inline int secpath_has_nontransport(struct sec_path *sp, int k, int *idxp int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { + struct net *net = dev_net(skb->dev); struct xfrm_policy *pol; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int npols = 0; @@ -1915,7 +1891,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, fl_dir = policy_to_flow_dir(dir); if (__xfrm_decode_session(skb, &fl, family, reverse) < 0) { - XFRM_INC_STATS(LINUX_MIB_XFRMINHDRERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } @@ -1928,7 +1904,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, for (i=skb->sp->len-1; i>=0; i--) { struct xfrm_state *x = skb->sp->xvec[i]; if (!xfrm_selector_match(&x->sel, &fl, family)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINSTATEMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); return 0; } } @@ -1938,24 +1914,24 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl); if (IS_ERR(pol)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } } if (!pol) - pol = flow_cache_lookup(&fl, family, fl_dir, + pol = flow_cache_lookup(net, &fl, family, fl_dir, xfrm_policy_lookup); if (IS_ERR(pol)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } if (!pol) { if (skb->sp && secpath_has_nontransport(skb->sp, 0, &xerr_idx)) { xfrm_secpath_reject(xerr_idx, skb, &fl); - XFRM_INC_STATS(LINUX_MIB_XFRMINNOPOLS); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } return 1; @@ -1967,12 +1943,12 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, npols ++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { - pols[1] = xfrm_policy_lookup_bytype(XFRM_POLICY_TYPE_MAIN, + pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, XFRM_POLICY_IN); if (pols[1]) { if (IS_ERR(pols[1])) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } pols[1]->curlft.use_time = get_seconds(); @@ -1996,11 +1972,11 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, for (pi = 0; pi < npols; pi++) { if (pols[pi] != pol && pols[pi]->action != XFRM_POLICY_ALLOW) { - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLBLOCK); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); goto reject; } if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) { - XFRM_INC_STATS(LINUX_MIB_XFRMINBUFFERERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto reject_error; } for (i = 0; i < pols[pi]->xfrm_nr; i++) @@ -2024,20 +2000,20 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (k < -1) /* "-2 - errored_index" returned */ xerr_idx = -(2+k); - XFRM_INC_STATS(LINUX_MIB_XFRMINTMPLMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } } if (secpath_has_nontransport(sp, k, &xerr_idx)) { - XFRM_INC_STATS(LINUX_MIB_XFRMINTMPLMISMATCH); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } xfrm_pols_put(pols, npols); return 1; } - XFRM_INC_STATS(LINUX_MIB_XFRMINPOLBLOCK); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); reject: xfrm_secpath_reject(xerr_idx, skb, &fl); @@ -2049,15 +2025,16 @@ EXPORT_SYMBOL(__xfrm_policy_check); int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { + struct net *net = dev_net(skb->dev); struct flowi fl; if (xfrm_decode_session(skb, &fl, family) < 0) { /* XXX: we should have something like FWDHDRERROR here. */ - XFRM_INC_STATS(LINUX_MIB_XFRMINHDRERROR); + XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } - return xfrm_lookup(&skb->dst, &fl, NULL, 0) == 0; + return xfrm_lookup(net, &skb->dst, &fl, NULL, 0) == 0; } EXPORT_SYMBOL(__xfrm_route_forward); @@ -2141,7 +2118,7 @@ static void prune_one_bundle(struct xfrm_policy *pol, int (*func)(struct dst_ent write_unlock(&pol->lock); } -static void xfrm_prune_bundles(int (*func)(struct dst_entry *)) +static void xfrm_prune_bundles(struct net *net, int (*func)(struct dst_entry *)) { struct dst_entry *gc_list = NULL; int dir; @@ -2154,11 +2131,11 @@ static void xfrm_prune_bundles(int (*func)(struct dst_entry *)) int i; hlist_for_each_entry(pol, entry, - &xfrm_policy_inexact[dir], bydst) + &net->xfrm.policy_inexact[dir], bydst) prune_one_bundle(pol, func, &gc_list); - table = xfrm_policy_bydst[dir].table; - for (i = xfrm_policy_bydst[dir].hmask; i >= 0; i--) { + table = net->xfrm.policy_bydst[dir].table; + for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { hlist_for_each_entry(pol, entry, table + i, bydst) prune_one_bundle(pol, func, &gc_list); } @@ -2177,14 +2154,14 @@ static int unused_bundle(struct dst_entry *dst) return !atomic_read(&dst->__refcnt); } -static void __xfrm_garbage_collect(void) +static void __xfrm_garbage_collect(struct net *net) { - xfrm_prune_bundles(unused_bundle); + xfrm_prune_bundles(net, unused_bundle); } -static int xfrm_flush_bundles(void) +static int xfrm_flush_bundles(struct net *net) { - xfrm_prune_bundles(stale_bundle); + xfrm_prune_bundles(net, stale_bundle); return 0; } @@ -2370,38 +2347,54 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void { struct net_device *dev = ptr; - if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - switch (event) { case NETDEV_DOWN: - xfrm_flush_bundles(); + xfrm_flush_bundles(dev_net(dev)); } return NOTIFY_DONE; } static struct notifier_block xfrm_dev_notifier = { - xfrm_dev_event, - NULL, - 0 + .notifier_call = xfrm_dev_event, }; #ifdef CONFIG_XFRM_STATISTICS -static int __init xfrm_statistics_init(void) +static int __net_init xfrm_statistics_init(struct net *net) { - if (snmp_mib_init((void **)xfrm_statistics, + int rv; + + if (snmp_mib_init((void **)net->mib.xfrm_statistics, sizeof(struct linux_xfrm_mib)) < 0) return -ENOMEM; + rv = xfrm_proc_init(net); + if (rv < 0) + snmp_mib_free((void **)net->mib.xfrm_statistics); + return rv; +} + +static void xfrm_statistics_fini(struct net *net) +{ + xfrm_proc_fini(net); + snmp_mib_free((void **)net->mib.xfrm_statistics); +} +#else +static int __net_init xfrm_statistics_init(struct net *net) +{ return 0; } + +static void xfrm_statistics_fini(struct net *net) +{ +} #endif -static void __init xfrm_policy_init(void) +static int __net_init xfrm_policy_init(struct net *net) { unsigned int hmask, sz; int dir; - xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", + if (net_eq(net, &init_net)) + xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", sizeof(struct xfrm_dst), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); @@ -2409,39 +2402,124 @@ static void __init xfrm_policy_init(void) hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); - xfrm_policy_byidx = xfrm_hash_alloc(sz); - xfrm_idx_hmask = hmask; - if (!xfrm_policy_byidx) - panic("XFRM: failed to allocate byidx hash\n"); + net->xfrm.policy_byidx = xfrm_hash_alloc(sz); + if (!net->xfrm.policy_byidx) + goto out_byidx; + net->xfrm.policy_idx_hmask = hmask; for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { struct xfrm_policy_hash *htab; - INIT_HLIST_HEAD(&xfrm_policy_inexact[dir]); + net->xfrm.policy_count[dir] = 0; + INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); - htab = &xfrm_policy_bydst[dir]; + htab = &net->xfrm.policy_bydst[dir]; htab->table = xfrm_hash_alloc(sz); - htab->hmask = hmask; if (!htab->table) - panic("XFRM: failed to allocate bydst hash\n"); + goto out_bydst; + htab->hmask = hmask; } - INIT_LIST_HEAD(&xfrm_policy_all); - INIT_WORK(&xfrm_policy_gc_work, xfrm_policy_gc_task); - register_netdevice_notifier(&xfrm_dev_notifier); + INIT_LIST_HEAD(&net->xfrm.policy_all); + INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize); + if (net_eq(net, &init_net)) + register_netdevice_notifier(&xfrm_dev_notifier); + return 0; + +out_bydst: + for (dir--; dir >= 0; dir--) { + struct xfrm_policy_hash *htab; + + htab = &net->xfrm.policy_bydst[dir]; + xfrm_hash_free(htab->table, sz); + } + xfrm_hash_free(net->xfrm.policy_byidx, sz); +out_byidx: + return -ENOMEM; } -void __init xfrm_init(void) +static void xfrm_policy_fini(struct net *net) { -#ifdef CONFIG_XFRM_STATISTICS - xfrm_statistics_init(); + struct xfrm_audit audit_info; + unsigned int sz; + int dir; + + flush_work(&net->xfrm.policy_hash_work); +#ifdef CONFIG_XFRM_SUB_POLICY + audit_info.loginuid = -1; + audit_info.sessionid = -1; + audit_info.secid = 0; + xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, &audit_info); #endif - xfrm_state_init(); - xfrm_policy_init(); + audit_info.loginuid = -1; + audit_info.sessionid = -1; + audit_info.secid = 0; + xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, &audit_info); + flush_work(&xfrm_policy_gc_work); + + WARN_ON(!list_empty(&net->xfrm.policy_all)); + + for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { + struct xfrm_policy_hash *htab; + + WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); + + htab = &net->xfrm.policy_bydst[dir]; + sz = (htab->hmask + 1); + WARN_ON(!hlist_empty(htab->table)); + xfrm_hash_free(htab->table, sz); + } + + sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); + WARN_ON(!hlist_empty(net->xfrm.policy_byidx)); + xfrm_hash_free(net->xfrm.policy_byidx, sz); +} + +static int __net_init xfrm_net_init(struct net *net) +{ + int rv; + + rv = xfrm_statistics_init(net); + if (rv < 0) + goto out_statistics; + rv = xfrm_state_init(net); + if (rv < 0) + goto out_state; + rv = xfrm_policy_init(net); + if (rv < 0) + goto out_policy; + rv = xfrm_sysctl_init(net); + if (rv < 0) + goto out_sysctl; + return 0; + +out_sysctl: + xfrm_policy_fini(net); +out_policy: + xfrm_state_fini(net); +out_state: + xfrm_statistics_fini(net); +out_statistics: + return rv; +} + +static void __net_exit xfrm_net_exit(struct net *net) +{ + xfrm_sysctl_fini(net); + xfrm_policy_fini(net); + xfrm_state_fini(net); + xfrm_statistics_fini(net); +} + +static struct pernet_operations __net_initdata xfrm_net_ops = { + .init = xfrm_net_init, + .exit = xfrm_net_exit, +}; + +void __init xfrm_init(void) +{ + register_pernet_subsys(&xfrm_net_ops); xfrm_input_init(); -#ifdef CONFIG_XFRM_STATISTICS - xfrm_proc_init(); -#endif } #ifdef CONFIG_AUDITSYSCALL @@ -2457,25 +2535,21 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, switch(sel->family) { case AF_INET: - audit_log_format(audit_buf, " src=" NIPQUAD_FMT, - NIPQUAD(sel->saddr.a4)); + audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); - audit_log_format(audit_buf, " dst=" NIPQUAD_FMT, - NIPQUAD(sel->daddr.a4)); + audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4); if (sel->prefixlen_d != 32) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; case AF_INET6: - audit_log_format(audit_buf, " src=" NIP6_FMT, - NIP6(*(struct in6_addr *)sel->saddr.a6)); + audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6); if (sel->prefixlen_s != 128) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); - audit_log_format(audit_buf, " dst=" NIP6_FMT, - NIP6(*(struct in6_addr *)sel->daddr.a6)); + audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6); if (sel->prefixlen_d != 128) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); @@ -2545,7 +2619,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, u32 priority = ~0U; read_lock_bh(&xfrm_policy_lock); - chain = policy_hash_direct(&sel->daddr, &sel->saddr, sel->family, dir); + chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, entry, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { @@ -2554,7 +2628,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, break; } } - chain = &xfrm_policy_inexact[dir]; + chain = &init_net.xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, entry, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type && diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 2b0db13f0cd..a2adb51849a 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -44,32 +44,20 @@ static struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_SENTINEL }; -static unsigned long -fold_field(void *mib[], int offt) -{ - unsigned long res = 0; - int i; - - for_each_possible_cpu(i) { - res += *(((unsigned long *)per_cpu_ptr(mib[0], i)) + offt); - res += *(((unsigned long *)per_cpu_ptr(mib[1], i)) + offt); - } - return res; -} - static int xfrm_statistics_seq_show(struct seq_file *seq, void *v) { + struct net *net = seq->private; int i; for (i=0; xfrm_mib_list[i].name; i++) seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name, - fold_field((void **)xfrm_statistics, - xfrm_mib_list[i].entry)); + snmp_fold_field((void **)net->mib.xfrm_statistics, + xfrm_mib_list[i].entry)); return 0; } static int xfrm_statistics_seq_open(struct inode *inode, struct file *file) { - return single_open(file, xfrm_statistics_seq_show, NULL); + return single_open_net(inode, file, xfrm_statistics_seq_show); } static struct file_operations xfrm_statistics_seq_fops = { @@ -77,21 +65,18 @@ static struct file_operations xfrm_statistics_seq_fops = { .open = xfrm_statistics_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = single_release, + .release = single_release_net, }; -int __init xfrm_proc_init(void) +int __net_init xfrm_proc_init(struct net *net) { - int rc = 0; - - if (!proc_net_fops_create(&init_net, "xfrm_stat", S_IRUGO, + if (!proc_net_fops_create(net, "xfrm_stat", S_IRUGO, &xfrm_statistics_seq_fops)) - goto stat_fail; - - out: - return rc; + return -ENOMEM; + return 0; +} - stat_fail: - rc = -ENOMEM; - goto out; +void xfrm_proc_fini(struct net *net) +{ + proc_net_remove(net, "xfrm_stat"); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 508337f9724..e25ff62ab2a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -24,17 +24,6 @@ #include "xfrm_hash.h" -struct sock *xfrm_nl; -EXPORT_SYMBOL(xfrm_nl); - -u32 sysctl_xfrm_aevent_etime __read_mostly = XFRM_AE_ETIME; -EXPORT_SYMBOL(sysctl_xfrm_aevent_etime); - -u32 sysctl_xfrm_aevent_rseqth __read_mostly = XFRM_AE_SEQT_SIZE; -EXPORT_SYMBOL(sysctl_xfrm_aevent_rseqth); - -u32 sysctl_xfrm_acq_expires __read_mostly = 30; - /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) @@ -44,19 +33,7 @@ u32 sysctl_xfrm_acq_expires __read_mostly = 30; static DEFINE_SPINLOCK(xfrm_state_lock); -/* Hash table to find appropriate SA towards given target (endpoint - * of tunnel or destination of transport mode) allowed by selector. - * - * Main use is finding SA after policy selected tunnel or transport mode. - * Also, it can be used by ah/esp icmp error handler to find offending SA. - */ -static LIST_HEAD(xfrm_state_all); -static struct hlist_head *xfrm_state_bydst __read_mostly; -static struct hlist_head *xfrm_state_bysrc __read_mostly; -static struct hlist_head *xfrm_state_byspi __read_mostly; -static unsigned int xfrm_state_hmask __read_mostly; static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; -static unsigned int xfrm_state_num; static unsigned int xfrm_state_genid; static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); @@ -69,25 +46,27 @@ static void xfrm_audit_state_replay(struct xfrm_state *x, #define xfrm_audit_state_replay(x, s, sq) do { ; } while (0) #endif /* CONFIG_AUDITSYSCALL */ -static inline unsigned int xfrm_dst_hash(xfrm_address_t *daddr, +static inline unsigned int xfrm_dst_hash(struct net *net, + xfrm_address_t *daddr, xfrm_address_t *saddr, u32 reqid, unsigned short family) { - return __xfrm_dst_hash(daddr, saddr, reqid, family, xfrm_state_hmask); + return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } -static inline unsigned int xfrm_src_hash(xfrm_address_t *daddr, +static inline unsigned int xfrm_src_hash(struct net *net, + xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family) { - return __xfrm_src_hash(daddr, saddr, family, xfrm_state_hmask); + return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } static inline unsigned int -xfrm_spi_hash(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) +xfrm_spi_hash(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { - return __xfrm_spi_hash(daddr, spi, proto, family, xfrm_state_hmask); + return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static void xfrm_hash_transfer(struct hlist_head *list, @@ -121,16 +100,16 @@ static void xfrm_hash_transfer(struct hlist_head *list, } } -static unsigned long xfrm_hash_new_size(void) +static unsigned long xfrm_hash_new_size(unsigned int state_hmask) { - return ((xfrm_state_hmask + 1) << 1) * - sizeof(struct hlist_head); + return ((state_hmask + 1) << 1) * sizeof(struct hlist_head); } static DEFINE_MUTEX(hash_resize_mutex); -static void xfrm_hash_resize(struct work_struct *__unused) +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; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; @@ -138,7 +117,7 @@ static void xfrm_hash_resize(struct work_struct *__unused) mutex_lock(&hash_resize_mutex); - nsize = xfrm_hash_new_size(); + nsize = xfrm_hash_new_size(net->xfrm.state_hmask); ndst = xfrm_hash_alloc(nsize); if (!ndst) goto out_unlock; @@ -157,19 +136,19 @@ static void xfrm_hash_resize(struct work_struct *__unused) spin_lock_bh(&xfrm_state_lock); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; - for (i = xfrm_state_hmask; i >= 0; i--) - xfrm_hash_transfer(xfrm_state_bydst+i, ndst, nsrc, nspi, + for (i = net->xfrm.state_hmask; i >= 0; i--) + xfrm_hash_transfer(net->xfrm.state_bydst+i, ndst, nsrc, nspi, nhashmask); - odst = xfrm_state_bydst; - osrc = xfrm_state_bysrc; - ospi = xfrm_state_byspi; - ohashmask = xfrm_state_hmask; + odst = net->xfrm.state_bydst; + osrc = net->xfrm.state_bysrc; + ospi = net->xfrm.state_byspi; + ohashmask = net->xfrm.state_hmask; - xfrm_state_bydst = ndst; - xfrm_state_bysrc = nsrc; - xfrm_state_byspi = nspi; - xfrm_state_hmask = nhashmask; + net->xfrm.state_bydst = ndst; + net->xfrm.state_bysrc = nsrc; + net->xfrm.state_byspi = nspi; + net->xfrm.state_hmask = nhashmask; spin_unlock_bh(&xfrm_state_lock); @@ -182,16 +161,9 @@ out_unlock: mutex_unlock(&hash_resize_mutex); } -static DECLARE_WORK(xfrm_hash_work, xfrm_hash_resize); - -DECLARE_WAIT_QUEUE_HEAD(km_waitq); -EXPORT_SYMBOL(km_waitq); - static DEFINE_RWLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO]; -static struct work_struct xfrm_state_gc_work; -static HLIST_HEAD(xfrm_state_gc_list); static DEFINE_SPINLOCK(xfrm_state_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); @@ -401,20 +373,21 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) kfree(x); } -static void xfrm_state_gc_task(struct work_struct *data) +static void xfrm_state_gc_task(struct work_struct *work) { + struct net *net = container_of(work, struct net, xfrm.state_gc_work); struct xfrm_state *x; struct hlist_node *entry, *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); - hlist_move_list(&xfrm_state_gc_list, &gc_list); + hlist_move_list(&net->xfrm.state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); hlist_for_each_entry_safe(x, entry, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); - wake_up(&km_waitq); + wake_up(&net->xfrm.km_waitq); } static inline unsigned long make_jiffies(long secs) @@ -428,6 +401,7 @@ static inline unsigned long make_jiffies(long secs) static void xfrm_timer_handler(unsigned long data) { struct xfrm_state *x = (struct xfrm_state*)data; + struct net *net = xs_net(x); unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -485,7 +459,7 @@ resched: expired: if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) { x->km.state = XFRM_STATE_EXPIRED; - wake_up(&km_waitq); + wake_up(&net->xfrm.km_waitq); next = 2; goto resched; } @@ -504,13 +478,14 @@ out: static void xfrm_replay_timer_handler(unsigned long data); -struct xfrm_state *xfrm_state_alloc(void) +struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC); if (x) { + write_pnet(&x->xs_net, net); atomic_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); @@ -537,17 +512,20 @@ EXPORT_SYMBOL(xfrm_state_alloc); void __xfrm_state_destroy(struct xfrm_state *x) { + struct net *net = xs_net(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); + hlist_add_head(&x->gclist, &net->xfrm.state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + schedule_work(&net->xfrm.state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); int __xfrm_state_delete(struct xfrm_state *x) { + struct net *net = xs_net(x); int err = -ESRCH; if (x->km.state != XFRM_STATE_DEAD) { @@ -558,7 +536,7 @@ int __xfrm_state_delete(struct xfrm_state *x) hlist_del(&x->bysrc); if (x->id.spi) hlist_del(&x->byspi); - xfrm_state_num--; + net->xfrm.state_num--; spin_unlock(&xfrm_state_lock); /* All xfrm_state objects are created by xfrm_state_alloc. @@ -587,15 +565,15 @@ EXPORT_SYMBOL(xfrm_state_delete); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int -xfrm_state_flush_secctx_check(u8 proto, struct xfrm_audit *audit_info) +xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info) { int i, err = 0; - for (i = 0; i <= xfrm_state_hmask; i++) { + for (i = 0; i <= net->xfrm.state_hmask; i++) { struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, @@ -611,26 +589,26 @@ xfrm_state_flush_secctx_check(u8 proto, struct xfrm_audit *audit_info) } #else static inline int -xfrm_state_flush_secctx_check(u8 proto, struct xfrm_audit *audit_info) +xfrm_state_flush_secctx_check(struct net *net, u8 proto, struct xfrm_audit *audit_info) { return 0; } #endif -int xfrm_state_flush(u8 proto, struct xfrm_audit *audit_info) +int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info) { int i, err = 0; spin_lock_bh(&xfrm_state_lock); - err = xfrm_state_flush_secctx_check(proto, audit_info); + err = xfrm_state_flush_secctx_check(net, proto, audit_info); if (err) goto out; - for (i = 0; i <= xfrm_state_hmask; i++) { + for (i = 0; i <= net->xfrm.state_hmask; i++) { struct hlist_node *entry; struct xfrm_state *x; restart: - hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); @@ -652,7 +630,7 @@ restart: out: spin_unlock_bh(&xfrm_state_lock); - wake_up(&km_waitq); + wake_up(&net->xfrm.km_waitq); return err; } EXPORT_SYMBOL(xfrm_state_flush); @@ -660,8 +638,8 @@ EXPORT_SYMBOL(xfrm_state_flush); void xfrm_sad_getinfo(struct xfrmk_sadinfo *si) { spin_lock_bh(&xfrm_state_lock); - si->sadcnt = xfrm_state_num; - si->sadhcnt = xfrm_state_hmask; + si->sadcnt = init_net.xfrm.state_num; + si->sadhcnt = init_net.xfrm.state_hmask; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&xfrm_state_lock); } @@ -681,13 +659,13 @@ xfrm_init_tempsel(struct xfrm_state *x, struct flowi *fl, return 0; } -static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) +static struct xfrm_state *__xfrm_state_lookup(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { - unsigned int h = xfrm_spi_hash(daddr, spi, proto, family); + unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; struct hlist_node *entry; - hlist_for_each_entry(x, entry, xfrm_state_byspi+h, byspi) { + hlist_for_each_entry(x, entry, net->xfrm.state_byspi+h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto) @@ -713,13 +691,13 @@ static struct xfrm_state *__xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, return NULL; } -static struct xfrm_state *__xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family) +static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family) { - unsigned int h = xfrm_src_hash(daddr, saddr, family); + unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; struct hlist_node *entry; - hlist_for_each_entry(x, entry, xfrm_state_bysrc+h, bysrc) { + hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || x->id.proto != proto) continue; @@ -751,21 +729,23 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { + struct net *net = xs_net(x); + if (use_spi) - return __xfrm_state_lookup(&x->id.daddr, x->id.spi, + return __xfrm_state_lookup(net, &x->id.daddr, x->id.spi, x->id.proto, family); else - return __xfrm_state_lookup_byaddr(&x->id.daddr, + return __xfrm_state_lookup_byaddr(net, &x->id.daddr, &x->props.saddr, x->id.proto, family); } -static void xfrm_hash_grow_check(int have_hash_collision) +static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) { if (have_hash_collision && - (xfrm_state_hmask + 1) < xfrm_state_hashmax && - xfrm_state_num > xfrm_state_hmask) - schedule_work(&xfrm_hash_work); + (net->xfrm.state_hmask + 1) < xfrm_state_hashmax && + net->xfrm.state_num > net->xfrm.state_hmask) + schedule_work(&net->xfrm.state_hash_work); } struct xfrm_state * @@ -774,6 +754,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, struct xfrm_policy *pol, int *err, unsigned short family) { + struct net *net = xp_net(pol); unsigned int h; struct hlist_node *entry; struct xfrm_state *x, *x0, *to_put; @@ -784,8 +765,8 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, to_put = NULL; spin_lock_bh(&xfrm_state_lock); - h = xfrm_dst_hash(daddr, saddr, tmpl->reqid, family); - hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, family); + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == tmpl->reqid && !(x->props.flags & XFRM_STATE_WILDRECV) && @@ -829,13 +810,13 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && - (x0 = __xfrm_state_lookup(daddr, tmpl->id.spi, + (x0 = __xfrm_state_lookup(net, daddr, tmpl->id.spi, tmpl->id.proto, family)) != NULL) { to_put = x0; error = -EEXIST; goto out; } - x = xfrm_state_alloc(); + x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; goto out; @@ -854,19 +835,19 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, if (km_query(x, tmpl, pol) == 0) { x->km.state = XFRM_STATE_ACQ; - list_add(&x->km.all, &xfrm_state_all); - hlist_add_head(&x->bydst, xfrm_state_bydst+h); - h = xfrm_src_hash(daddr, saddr, family); - hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); + list_add(&x->km.all, &net->xfrm.state_all); + hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); + h = xfrm_src_hash(net, daddr, saddr, family); + hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); if (x->id.spi) { - h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, family); - hlist_add_head(&x->byspi, xfrm_state_byspi+h); + h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, family); + hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); } - x->lft.hard_add_expires_seconds = sysctl_xfrm_acq_expires; - x->timer.expires = jiffies + sysctl_xfrm_acq_expires*HZ; + x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; + x->timer.expires = jiffies + net->xfrm.sysctl_acq_expires*HZ; add_timer(&x->timer); - xfrm_state_num++; - xfrm_hash_grow_check(x->bydst.next != NULL); + net->xfrm.state_num++; + xfrm_hash_grow_check(net, x->bydst.next != NULL); } else { x->km.state = XFRM_STATE_DEAD; to_put = x; @@ -886,7 +867,8 @@ out: } struct xfrm_state * -xfrm_stateonly_find(xfrm_address_t *daddr, xfrm_address_t *saddr, +xfrm_stateonly_find(struct net *net, + xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { unsigned int h; @@ -894,8 +876,8 @@ xfrm_stateonly_find(xfrm_address_t *daddr, xfrm_address_t *saddr, struct hlist_node *entry; spin_lock(&xfrm_state_lock); - h = xfrm_dst_hash(daddr, saddr, reqid, family); - hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + h = xfrm_dst_hash(net, daddr, saddr, reqid, family); + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && !(x->props.flags & XFRM_STATE_WILDRECV) && @@ -919,48 +901,50 @@ EXPORT_SYMBOL(xfrm_stateonly_find); static void __xfrm_state_insert(struct xfrm_state *x) { + struct net *net = xs_net(x); unsigned int h; x->genid = ++xfrm_state_genid; - list_add(&x->km.all, &xfrm_state_all); + list_add(&x->km.all, &net->xfrm.state_all); - h = xfrm_dst_hash(&x->id.daddr, &x->props.saddr, + h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); - hlist_add_head(&x->bydst, xfrm_state_bydst+h); + hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); - h = xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family); - hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); + h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); + hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); if (x->id.spi) { - h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, + h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - hlist_add_head(&x->byspi, xfrm_state_byspi+h); + hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); } mod_timer(&x->timer, jiffies + HZ); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); - wake_up(&km_waitq); + wake_up(&net->xfrm.km_waitq); - xfrm_state_num++; + net->xfrm.state_num++; - xfrm_hash_grow_check(x->bydst.next != NULL); + xfrm_hash_grow_check(net, x->bydst.next != NULL); } /* xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { + struct net *net = xs_net(xnew); unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; struct hlist_node *entry; unsigned int h; - h = xfrm_dst_hash(&xnew->id.daddr, &xnew->props.saddr, reqid, family); - hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && x->props.reqid == reqid && !xfrm_addr_cmp(&x->id.daddr, &xnew->id.daddr, family) && @@ -979,13 +963,13 @@ void xfrm_state_insert(struct xfrm_state *x) EXPORT_SYMBOL(xfrm_state_insert); /* xfrm_state_lock is held */ -static struct xfrm_state *__find_acq_core(unsigned short family, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create) +static struct xfrm_state *__find_acq_core(struct net *net, unsigned short family, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create) { - unsigned int h = xfrm_dst_hash(daddr, saddr, reqid, family); + unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || @@ -1017,7 +1001,7 @@ static struct xfrm_state *__find_acq_core(unsigned short family, u8 mode, u32 re if (!create) return NULL; - x = xfrm_state_alloc(); + x = xfrm_state_alloc(net); if (likely(x)) { switch (family) { case AF_INET: @@ -1048,27 +1032,28 @@ static struct xfrm_state *__find_acq_core(unsigned short family, u8 mode, u32 re x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; - x->lft.hard_add_expires_seconds = sysctl_xfrm_acq_expires; + x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); - x->timer.expires = jiffies + sysctl_xfrm_acq_expires*HZ; + x->timer.expires = jiffies + net->xfrm.sysctl_acq_expires*HZ; add_timer(&x->timer); - list_add(&x->km.all, &xfrm_state_all); - hlist_add_head(&x->bydst, xfrm_state_bydst+h); - h = xfrm_src_hash(daddr, saddr, family); - hlist_add_head(&x->bysrc, xfrm_state_bysrc+h); + list_add(&x->km.all, &net->xfrm.state_all); + hlist_add_head(&x->bydst, net->xfrm.state_bydst+h); + h = xfrm_src_hash(net, daddr, saddr, family); + hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h); - xfrm_state_num++; + net->xfrm.state_num++; - xfrm_hash_grow_check(x->bydst.next != NULL); + xfrm_hash_grow_check(net, x->bydst.next != NULL); } return x; } -static struct xfrm_state *__xfrm_find_acq_byseq(u32 seq); +static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 seq); int xfrm_state_add(struct xfrm_state *x) { + struct net *net = xs_net(x); struct xfrm_state *x1, *to_put; int family; int err; @@ -1089,7 +1074,7 @@ int xfrm_state_add(struct xfrm_state *x) } if (use_spi && x->km.seq) { - x1 = __xfrm_find_acq_byseq(x->km.seq); + x1 = __xfrm_find_acq_byseq(net, x->km.seq); if (x1 && ((x1->id.proto != x->id.proto) || xfrm_addr_cmp(&x1->id.daddr, &x->id.daddr, family))) { to_put = x1; @@ -1098,7 +1083,7 @@ int xfrm_state_add(struct xfrm_state *x) } if (use_spi && !x1) - x1 = __find_acq_core(family, x->props.mode, x->props.reqid, + x1 = __find_acq_core(net, family, x->props.mode, x->props.reqid, x->id.proto, &x->id.daddr, &x->props.saddr, 0); @@ -1124,8 +1109,9 @@ EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, int *errp) { + struct net *net = xs_net(orig); int err = -ENOMEM; - struct xfrm_state *x = xfrm_state_alloc(); + struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto error; @@ -1206,9 +1192,9 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) struct hlist_node *entry; if (m->reqid) { - h = xfrm_dst_hash(&m->old_daddr, &m->old_saddr, + h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, entry, xfrm_state_bydst+h, bydst) { + hlist_for_each_entry(x, entry, init_net.xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1223,9 +1209,9 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) return x; } } else { - h = xfrm_src_hash(&m->old_daddr, &m->old_saddr, + h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, entry, xfrm_state_bysrc+h, bysrc) { + hlist_for_each_entry(x, entry, init_net.xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1369,40 +1355,41 @@ int xfrm_state_check_expire(struct xfrm_state *x) EXPORT_SYMBOL(xfrm_state_check_expire); struct xfrm_state * -xfrm_state_lookup(xfrm_address_t *daddr, __be32 spi, u8 proto, +xfrm_state_lookup(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&xfrm_state_lock); - x = __xfrm_state_lookup(daddr, spi, proto, family); + x = __xfrm_state_lookup(net, daddr, spi, proto, family); spin_unlock_bh(&xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup); struct xfrm_state * -xfrm_state_lookup_byaddr(xfrm_address_t *daddr, xfrm_address_t *saddr, +xfrm_state_lookup_byaddr(struct net *net, + xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&xfrm_state_lock); - x = __xfrm_state_lookup_byaddr(daddr, saddr, proto, family); + x = __xfrm_state_lookup_byaddr(net, daddr, saddr, proto, family); spin_unlock_bh(&xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * -xfrm_find_acq(u8 mode, u32 reqid, u8 proto, +xfrm_find_acq(struct net *net, u8 mode, u32 reqid, u8 proto, xfrm_address_t *daddr, xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&xfrm_state_lock); - x = __find_acq_core(family, mode, reqid, proto, daddr, saddr, create); + x = __find_acq_core(net, family, mode, reqid, proto, daddr, saddr, create); spin_unlock_bh(&xfrm_state_lock); return x; @@ -1449,15 +1436,15 @@ EXPORT_SYMBOL(xfrm_state_sort); /* Silly enough, but I'm lazy to build resolution list */ -static struct xfrm_state *__xfrm_find_acq_byseq(u32 seq) +static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 seq) { int i; - for (i = 0; i <= xfrm_state_hmask; i++) { + for (i = 0; i <= net->xfrm.state_hmask; i++) { struct hlist_node *entry; struct xfrm_state *x; - hlist_for_each_entry(x, entry, xfrm_state_bydst+i, bydst) { + hlist_for_each_entry(x, entry, net->xfrm.state_bydst+i, bydst) { if (x->km.seq == seq && x->km.state == XFRM_STATE_ACQ) { xfrm_state_hold(x); @@ -1468,12 +1455,12 @@ static struct xfrm_state *__xfrm_find_acq_byseq(u32 seq) return NULL; } -struct xfrm_state *xfrm_find_acq_byseq(u32 seq) +struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 seq) { struct xfrm_state *x; spin_lock_bh(&xfrm_state_lock); - x = __xfrm_find_acq_byseq(seq); + x = __xfrm_find_acq_byseq(net, seq); spin_unlock_bh(&xfrm_state_lock); return x; } @@ -1494,6 +1481,7 @@ EXPORT_SYMBOL(xfrm_get_acqseq); int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) { + struct net *net = xs_net(x); unsigned int h; struct xfrm_state *x0; int err = -ENOENT; @@ -1511,7 +1499,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) err = -ENOENT; if (minspi == maxspi) { - x0 = xfrm_state_lookup(&x->id.daddr, minspi, x->id.proto, x->props.family); + x0 = xfrm_state_lookup(net, &x->id.daddr, minspi, x->id.proto, x->props.family); if (x0) { xfrm_state_put(x0); goto unlock; @@ -1521,7 +1509,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) u32 spi = 0; for (h=0; hid.daddr, htonl(spi), x->id.proto, x->props.family); + x0 = xfrm_state_lookup(net, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { x->id.spi = htonl(spi); break; @@ -1531,8 +1519,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) } if (x->id.spi) { spin_lock_bh(&xfrm_state_lock); - h = xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family); - hlist_add_head(&x->byspi, xfrm_state_byspi+h); + h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); + hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); spin_unlock_bh(&xfrm_state_lock); err = 0; @@ -1545,7 +1533,7 @@ unlock: } EXPORT_SYMBOL(xfrm_alloc_spi); -int xfrm_state_walk(struct xfrm_state_walk *walk, +int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) { @@ -1558,10 +1546,10 @@ int xfrm_state_walk(struct xfrm_state_walk *walk, spin_lock_bh(&xfrm_state_lock); if (list_empty(&walk->all)) - x = list_first_entry(&xfrm_state_all, struct xfrm_state_walk, all); + x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else x = list_entry(&walk->all, struct xfrm_state_walk, all); - list_for_each_entry_from(x, &xfrm_state_all, all) { + list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; state = container_of(x, struct xfrm_state, km); @@ -1660,7 +1648,7 @@ static void xfrm_replay_timer_handler(unsigned long data) spin_lock(&x->lock); if (x->km.state == XFRM_STATE_VALID) { - if (xfrm_aevent_is_on()) + if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; @@ -1716,7 +1704,7 @@ void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) x->replay.bitmap |= (1U << diff); } - if (xfrm_aevent_is_on()) + if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_UPDATE); } @@ -1749,6 +1737,7 @@ EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 pid) { + struct net *net = xs_net(x); struct km_event c; c.data.hard = hard; @@ -1757,7 +1746,7 @@ void km_state_expired(struct xfrm_state *x, int hard, u32 pid) km_state_notify(x, &c); if (hard) - wake_up(&km_waitq); + wake_up(&net->xfrm.km_waitq); } EXPORT_SYMBOL(km_state_expired); @@ -1800,6 +1789,7 @@ EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid) { + struct net *net = xp_net(pol); struct km_event c; c.data.hard = hard; @@ -1808,7 +1798,7 @@ void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid) km_policy_notify(pol, dir, &c); if (hard) - wake_up(&km_waitq); + wake_up(&net->xfrm.km_waitq); } EXPORT_SYMBOL(km_policy_expired); @@ -1835,7 +1825,7 @@ int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type, EXPORT_SYMBOL(km_migrate); #endif -int km_report(u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) +int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { int err = -EINVAL; int ret; @@ -1844,7 +1834,7 @@ int km_report(u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) read_lock(&xfrm_km_lock); list_for_each_entry(km, &xfrm_km_list, list) { if (km->report) { - ret = km->report(proto, sel, addr); + ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } @@ -2032,8 +2022,9 @@ int xfrm_init_state(struct xfrm_state *x) x->inner_mode = inner_mode; } else { struct xfrm_mode *inner_mode_iaf; + int iafamily = AF_INET; - inner_mode = xfrm_get_mode(x->props.mode, AF_INET); + inner_mode = xfrm_get_mode(x->props.mode, x->props.family); if (inner_mode == NULL) goto error; @@ -2041,22 +2032,17 @@ int xfrm_init_state(struct xfrm_state *x) xfrm_put_mode(inner_mode); goto error; } + x->inner_mode = inner_mode; - inner_mode_iaf = xfrm_get_mode(x->props.mode, AF_INET6); - if (inner_mode_iaf == NULL) - goto error; - - if (!(inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL)) { - xfrm_put_mode(inner_mode_iaf); - goto error; - } + if (x->props.family == AF_INET) + iafamily = AF_INET6; - if (x->props.family == AF_INET) { - x->inner_mode = inner_mode; - x->inner_mode_iaf = inner_mode_iaf; - } else { - x->inner_mode = inner_mode_iaf; - x->inner_mode_iaf = inner_mode; + 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); } } @@ -2080,20 +2066,61 @@ error: EXPORT_SYMBOL(xfrm_init_state); -void __init xfrm_state_init(void) +int __net_init xfrm_state_init(struct net *net) { unsigned int sz; + INIT_LIST_HEAD(&net->xfrm.state_all); + sz = sizeof(struct hlist_head) * 8; - xfrm_state_bydst = xfrm_hash_alloc(sz); - xfrm_state_bysrc = xfrm_hash_alloc(sz); - xfrm_state_byspi = xfrm_hash_alloc(sz); - if (!xfrm_state_bydst || !xfrm_state_bysrc || !xfrm_state_byspi) - panic("XFRM: Cannot allocate bydst/bysrc/byspi hashes."); - xfrm_state_hmask = ((sz / sizeof(struct hlist_head)) - 1); + net->xfrm.state_bydst = xfrm_hash_alloc(sz); + if (!net->xfrm.state_bydst) + goto out_bydst; + net->xfrm.state_bysrc = xfrm_hash_alloc(sz); + if (!net->xfrm.state_bysrc) + goto out_bysrc; + net->xfrm.state_byspi = xfrm_hash_alloc(sz); + if (!net->xfrm.state_byspi) + goto out_byspi; + 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); + INIT_HLIST_HEAD(&net->xfrm.state_gc_list); + INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task); + init_waitqueue_head(&net->xfrm.km_waitq); + return 0; + +out_byspi: + xfrm_hash_free(net->xfrm.state_bysrc, sz); +out_bysrc: + xfrm_hash_free(net->xfrm.state_bydst, sz); +out_bydst: + return -ENOMEM; +} + +void xfrm_state_fini(struct net *net) +{ + struct xfrm_audit audit_info; + unsigned int sz; + + flush_work(&net->xfrm.state_hash_work); + audit_info.loginuid = -1; + audit_info.sessionid = -1; + audit_info.secid = 0; + xfrm_state_flush(net, IPSEC_PROTO_ANY, &audit_info); + flush_work(&net->xfrm.state_gc_work); + + WARN_ON(!list_empty(&net->xfrm.state_all)); - INIT_WORK(&xfrm_state_gc_work, xfrm_state_gc_task); + sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); + WARN_ON(!hlist_empty(net->xfrm.state_byspi)); + 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); } #ifdef CONFIG_AUDITSYSCALL @@ -2109,16 +2136,12 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x, switch(x->props.family) { case AF_INET: - audit_log_format(audit_buf, - " src=" NIPQUAD_FMT " dst=" NIPQUAD_FMT, - NIPQUAD(x->props.saddr.a4), - NIPQUAD(x->id.daddr.a4)); + audit_log_format(audit_buf, " src=%pI4 dst=%pI4", + &x->props.saddr.a4, &x->id.daddr.a4); break; case AF_INET6: - audit_log_format(audit_buf, - " src=" NIP6_FMT " dst=" NIP6_FMT, - NIP6(*(struct in6_addr *)x->props.saddr.a6), - NIP6(*(struct in6_addr *)x->id.daddr.a6)); + audit_log_format(audit_buf, " src=%pI6 dst=%pI6", + x->props.saddr.a6, x->id.daddr.a6); break; } @@ -2134,18 +2157,14 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, switch (family) { case AF_INET: iph4 = ip_hdr(skb); - audit_log_format(audit_buf, - " src=" NIPQUAD_FMT " dst=" NIPQUAD_FMT, - NIPQUAD(iph4->saddr), - NIPQUAD(iph4->daddr)); + audit_log_format(audit_buf, " src=%pI4 dst=%pI4", + &iph4->saddr, &iph4->daddr); break; case AF_INET6: iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, - " src=" NIP6_FMT " dst=" NIP6_FMT - " flowlbl=0x%x%02x%02x", - NIP6(iph6->saddr), - NIP6(iph6->daddr), + " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", + &iph6->saddr,&iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); diff --git a/net/xfrm/xfrm_sysctl.c b/net/xfrm/xfrm_sysctl.c new file mode 100644 index 00000000000..2e6ffb66f06 --- /dev/null +++ b/net/xfrm/xfrm_sysctl.c @@ -0,0 +1,85 @@ +#include +#include +#include + +static void __xfrm_sysctl_init(struct net *net) +{ + net->xfrm.sysctl_aevent_etime = XFRM_AE_ETIME; + net->xfrm.sysctl_aevent_rseqth = XFRM_AE_SEQT_SIZE; + net->xfrm.sysctl_larval_drop = 1; + net->xfrm.sysctl_acq_expires = 30; +} + +#ifdef CONFIG_SYSCTL +static struct ctl_table xfrm_table[] = { + { + .ctl_name = NET_CORE_AEVENT_ETIME, + .procname = "xfrm_aevent_etime", + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .ctl_name = NET_CORE_AEVENT_RSEQTH, + .procname = "xfrm_aevent_rseqth", + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "xfrm_larval_drop", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "xfrm_acq_expires", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + {} +}; + +int __net_init xfrm_sysctl_init(struct net *net) +{ + struct ctl_table *table; + + __xfrm_sysctl_init(net); + + table = kmemdup(xfrm_table, sizeof(xfrm_table), GFP_KERNEL); + if (!table) + goto out_kmemdup; + table[0].data = &net->xfrm.sysctl_aevent_etime; + table[1].data = &net->xfrm.sysctl_aevent_rseqth; + table[2].data = &net->xfrm.sysctl_larval_drop; + table[3].data = &net->xfrm.sysctl_acq_expires; + + net->xfrm.sysctl_hdr = register_net_sysctl_table(net, net_core_path, table); + if (!net->xfrm.sysctl_hdr) + goto out_register; + return 0; + +out_register: + kfree(table); +out_kmemdup: + return -ENOMEM; +} + +void xfrm_sysctl_fini(struct net *net) +{ + struct ctl_table *table; + + table = net->xfrm.sysctl_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->xfrm.sysctl_hdr); + kfree(table); +} +#else +int __net_init xfrm_sysctl_init(struct net *net) +{ + __xfrm_sysctl_init(net); + return 0; +} +#endif diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a278a6f3b99..7877e7975da 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -316,11 +316,12 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs) x->replay_maxdiff = nla_get_u32(rt); } -static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p, +static struct xfrm_state *xfrm_state_construct(struct net *net, + struct xfrm_usersa_info *p, struct nlattr **attrs, int *errp) { - struct xfrm_state *x = xfrm_state_alloc(); + struct xfrm_state *x = xfrm_state_alloc(net); int err = -ENOMEM; if (!x) @@ -367,9 +368,9 @@ static struct xfrm_state *xfrm_state_construct(struct xfrm_usersa_info *p, goto error; x->km.seq = p->seq; - x->replay_maxdiff = sysctl_xfrm_aevent_rseqth; + x->replay_maxdiff = net->xfrm.sysctl_aevent_rseqth; /* sysctl_xfrm_aevent_etime is in 100ms units */ - x->replay_maxage = (sysctl_xfrm_aevent_etime*HZ)/XFRM_AE_ETH_M; + x->replay_maxage = (net->xfrm.sysctl_aevent_etime*HZ)/XFRM_AE_ETH_M; x->preplay.bitmap = 0; x->preplay.seq = x->replay.seq+x->replay_maxdiff; x->preplay.oseq = x->replay.oseq +x->replay_maxdiff; @@ -391,6 +392,7 @@ error_no_put: static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_usersa_info *p = nlmsg_data(nlh); struct xfrm_state *x; int err; @@ -403,7 +405,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; - x = xfrm_state_construct(p, attrs, &err); + x = xfrm_state_construct(net, p, attrs, &err); if (!x) return err; @@ -431,7 +433,8 @@ out: return err; } -static struct xfrm_state *xfrm_user_state_lookup(struct xfrm_usersa_id *p, +static struct xfrm_state *xfrm_user_state_lookup(struct net *net, + struct xfrm_usersa_id *p, struct nlattr **attrs, int *errp) { @@ -440,7 +443,7 @@ static struct xfrm_state *xfrm_user_state_lookup(struct xfrm_usersa_id *p, if (xfrm_id_proto_match(p->proto, IPSEC_PROTO_ANY)) { err = -ESRCH; - x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family); + x = xfrm_state_lookup(net, &p->daddr, p->spi, p->proto, p->family); } else { xfrm_address_t *saddr = NULL; @@ -451,8 +454,8 @@ static struct xfrm_state *xfrm_user_state_lookup(struct xfrm_usersa_id *p, } err = -ESRCH; - x = xfrm_state_lookup_byaddr(&p->daddr, saddr, p->proto, - p->family); + x = xfrm_state_lookup_byaddr(net, &p->daddr, saddr, + p->proto, p->family); } out: @@ -464,6 +467,7 @@ static struct xfrm_state *xfrm_user_state_lookup(struct xfrm_usersa_id *p, static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_state *x; int err = -ESRCH; struct km_event c; @@ -472,7 +476,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, u32 sessionid = NETLINK_CB(skb).sessionid; u32 sid = NETLINK_CB(skb).sid; - x = xfrm_user_state_lookup(p, attrs, &err); + x = xfrm_user_state_lookup(net, p, attrs, &err); if (x == NULL) return err; @@ -615,6 +619,7 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb) static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1]; struct xfrm_dump_info info; @@ -631,7 +636,7 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb) xfrm_state_walk_init(walk, 0); } - (void) xfrm_state_walk(walk, dump_one_state, &info); + (void) xfrm_state_walk(net, walk, dump_one_state, &info); return skb->len; } @@ -703,6 +708,7 @@ nla_put_failure: static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct sk_buff *r_skb; u32 *flags = nlmsg_data(nlh); u32 spid = NETLINK_CB(skb).pid; @@ -715,7 +721,7 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, if (build_spdinfo(r_skb, spid, seq, *flags) < 0) BUG(); - return nlmsg_unicast(xfrm_nl, r_skb, spid); + return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); } static inline size_t xfrm_sadinfo_msgsize(void) @@ -756,6 +762,7 @@ nla_put_failure: static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct sk_buff *r_skb; u32 *flags = nlmsg_data(nlh); u32 spid = NETLINK_CB(skb).pid; @@ -768,18 +775,19 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, if (build_sadinfo(r_skb, spid, seq, *flags) < 0) BUG(); - return nlmsg_unicast(xfrm_nl, r_skb, spid); + return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); } static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_usersa_id *p = nlmsg_data(nlh); struct xfrm_state *x; struct sk_buff *resp_skb; int err = -ESRCH; - x = xfrm_user_state_lookup(p, attrs, &err); + x = xfrm_user_state_lookup(net, p, attrs, &err); if (x == NULL) goto out_noput; @@ -787,7 +795,7 @@ static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(xfrm_nl, resp_skb, NETLINK_CB(skb).pid); + err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).pid); } xfrm_state_put(x); out_noput: @@ -820,6 +828,7 @@ static int verify_userspi_info(struct xfrm_userspi_info *p) static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct xfrm_userspi_info *p; struct sk_buff *resp_skb; @@ -837,7 +846,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, x = NULL; if (p->info.seq) { - x = xfrm_find_acq_byseq(p->info.seq); + x = xfrm_find_acq_byseq(net, p->info.seq); if (x && xfrm_addr_cmp(&x->id.daddr, daddr, family)) { xfrm_state_put(x); x = NULL; @@ -845,7 +854,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, } if (!x) - x = xfrm_find_acq(p->info.mode, p->info.reqid, + x = xfrm_find_acq(net, p->info.mode, p->info.reqid, p->info.id.proto, daddr, &p->info.saddr, 1, family); @@ -863,7 +872,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } - err = nlmsg_unicast(xfrm_nl, resp_skb, NETLINK_CB(skb).pid); + err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).pid); out: xfrm_state_put(x); @@ -1078,9 +1087,9 @@ static void copy_to_user_policy(struct xfrm_policy *xp, struct xfrm_userpolicy_i p->share = XFRM_SHARE_ANY; /* XXX xp->share */ } -static struct xfrm_policy *xfrm_policy_construct(struct xfrm_userpolicy_info *p, struct nlattr **attrs, int *errp) +static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_userpolicy_info *p, struct nlattr **attrs, int *errp) { - struct xfrm_policy *xp = xfrm_policy_alloc(GFP_KERNEL); + struct xfrm_policy *xp = xfrm_policy_alloc(net, GFP_KERNEL); int err; if (!xp) { @@ -1110,6 +1119,7 @@ static struct xfrm_policy *xfrm_policy_construct(struct xfrm_userpolicy_info *p, static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_info *p = nlmsg_data(nlh); struct xfrm_policy *xp; struct km_event c; @@ -1126,7 +1136,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; - xp = xfrm_policy_construct(p, attrs, &err); + xp = xfrm_policy_construct(net, p, attrs, &err); if (!xp) return err; @@ -1263,6 +1273,7 @@ static int xfrm_dump_policy_done(struct netlink_callback *cb) static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = sock_net(skb->sk); struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1]; struct xfrm_dump_info info; @@ -1279,7 +1290,7 @@ static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb) xfrm_policy_walk_init(walk, XFRM_POLICY_TYPE_ANY); } - (void) xfrm_policy_walk(walk, dump_one_policy, &info); + (void) xfrm_policy_walk(net, walk, dump_one_policy, &info); return skb->len; } @@ -1311,6 +1322,7 @@ static struct sk_buff *xfrm_policy_netlink(struct sk_buff *in_skb, static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_policy *xp; struct xfrm_userpolicy_id *p; u8 type = XFRM_POLICY_TYPE_MAIN; @@ -1330,7 +1342,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, return err; if (p->index) - xp = xfrm_policy_byid(type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, type, p->dir, p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1347,7 +1359,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(type, p->dir, &p->sel, ctx, + xp = xfrm_policy_bysel_ctx(net, type, p->dir, &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } @@ -1361,7 +1373,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(xfrm_nl, resp_skb, + err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).pid); } } else { @@ -1390,6 +1402,7 @@ out: static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct km_event c; struct xfrm_usersa_flush *p = nlmsg_data(nlh); struct xfrm_audit audit_info; @@ -1398,13 +1411,14 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, audit_info.loginuid = NETLINK_CB(skb).loginuid; audit_info.sessionid = NETLINK_CB(skb).sessionid; audit_info.secid = NETLINK_CB(skb).sid; - err = xfrm_state_flush(p->proto, &audit_info); + err = xfrm_state_flush(net, p->proto, &audit_info); if (err) return err; c.data.proto = p->proto; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.pid = nlh->nlmsg_pid; + c.net = net; km_state_notify(NULL, &c); return 0; @@ -1457,6 +1471,7 @@ nla_put_failure: static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct sk_buff *r_skb; int err; @@ -1468,7 +1483,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (r_skb == NULL) return -ENOMEM; - x = xfrm_state_lookup(&id->daddr, id->spi, id->proto, id->family); + x = xfrm_state_lookup(net, &id->daddr, id->spi, id->proto, id->family); if (x == NULL) { kfree_skb(r_skb); return -ESRCH; @@ -1486,7 +1501,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (build_aevent(r_skb, x, &c) < 0) BUG(); - err = nlmsg_unicast(xfrm_nl, r_skb, NETLINK_CB(skb).pid); + err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).pid); spin_unlock_bh(&x->lock); xfrm_state_put(x); return err; @@ -1495,6 +1510,7 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct km_event c; int err = - EINVAL; @@ -1509,7 +1525,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, if (!(nlh->nlmsg_flags&NLM_F_REPLACE)) return err; - x = xfrm_state_lookup(&p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family); + x = xfrm_state_lookup(net, &p->sa_id.daddr, p->sa_id.spi, p->sa_id.proto, p->sa_id.family); if (x == NULL) return -ESRCH; @@ -1534,6 +1550,7 @@ out: static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct km_event c; u8 type = XFRM_POLICY_TYPE_MAIN; int err; @@ -1546,13 +1563,14 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, audit_info.loginuid = NETLINK_CB(skb).loginuid; audit_info.sessionid = NETLINK_CB(skb).sessionid; audit_info.secid = NETLINK_CB(skb).sid; - err = xfrm_policy_flush(type, &audit_info); + err = xfrm_policy_flush(net, type, &audit_info); if (err) return err; c.data.type = type; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; c.pid = nlh->nlmsg_pid; + c.net = net; km_policy_notify(NULL, 0, &c); return 0; } @@ -1560,6 +1578,7 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_policy *xp; struct xfrm_user_polexpire *up = nlmsg_data(nlh); struct xfrm_userpolicy_info *p = &up->pol; @@ -1571,7 +1590,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, return err; if (p->index) - xp = xfrm_policy_byid(type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, type, p->dir, p->index, 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1588,7 +1607,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(type, p->dir, &p->sel, ctx, 0, &err); + xp = xfrm_policy_bysel_ctx(net, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -1623,12 +1642,13 @@ out: static int xfrm_add_sa_expire(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_state *x; int err; struct xfrm_user_expire *ue = nlmsg_data(nlh); struct xfrm_usersa_info *p = &ue->state; - x = xfrm_state_lookup(&p->id.daddr, p->id.spi, p->id.proto, p->family); + x = xfrm_state_lookup(net, &p->id.daddr, p->id.spi, p->id.proto, p->family); err = -ENOENT; if (x == NULL) @@ -1657,31 +1677,27 @@ out: static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { + struct net *net = sock_net(skb->sk); struct xfrm_policy *xp; struct xfrm_user_tmpl *ut; int i; struct nlattr *rt = attrs[XFRMA_TMPL]; struct xfrm_user_acquire *ua = nlmsg_data(nlh); - struct xfrm_state *x = xfrm_state_alloc(); + struct xfrm_state *x = xfrm_state_alloc(net); int err = -ENOMEM; if (!x) - return err; + goto nomem; err = verify_newpolicy_info(&ua->policy); - if (err) { - printk("BAD policy passed\n"); - kfree(x); - return err; - } + if (err) + goto bad_policy; /* build an XP */ - xp = xfrm_policy_construct(&ua->policy, attrs, &err); - if (!xp) { - kfree(x); - return err; - } + xp = xfrm_policy_construct(net, &ua->policy, attrs, &err); + if (!xp) + goto free_state; memcpy(&x->id, &ua->id, sizeof(ua->id)); memcpy(&x->props.saddr, &ua->saddr, sizeof(ua->saddr)); @@ -1706,6 +1722,13 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, kfree(xp); return 0; + +bad_policy: + printk("BAD policy passed\n"); +free_state: + kfree(x); +nomem: + return err; } #ifdef CONFIG_XFRM_MIGRATE @@ -1869,6 +1892,7 @@ static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k) { + struct net *net = &init_net; struct sk_buff *skb; skb = nlmsg_new(xfrm_migrate_msgsize(num_migrate, !!k), GFP_ATOMIC); @@ -1879,7 +1903,7 @@ static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, if (build_migrate(skb, m, num_migrate, k, sel, dir, type) < 0) BUG(); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC); } #else static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, @@ -1890,10 +1914,17 @@ static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, } #endif +/* For the xfrm_usersa_info cases we have to work around some 32-bit vs. + * 64-bit compatability issues. On 32-bit the structure is 220 bytes, but + * for 64-bit it gets padded out to 224 bytes. Those bytes are just + * padding and don't have any content we care about. Therefore as long + * as we have enough bytes for the content we can make both cases work. + */ + #define XMSGSIZE(type) sizeof(struct type) static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { - [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), + [XFRM_MSG_NEWSA - XFRM_MSG_BASE] = 220, /* see above */ [XFRM_MSG_DELSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_GETSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id), [XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), @@ -1903,7 +1934,7 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = { [XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_acquire), [XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_expire), [XFRM_MSG_UPDPOLICY - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_info), - [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info), + [XFRM_MSG_UPDSA - XFRM_MSG_BASE] = 220, /* see above */ [XFRM_MSG_POLEXPIRE - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_polexpire), [XFRM_MSG_FLUSHSA - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush), [XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0, @@ -1968,6 +1999,7 @@ static struct xfrm_link { static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); struct nlattr *attrs[XFRMA_MAX+1]; struct xfrm_link *link; int type, err; @@ -1989,7 +2021,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; - return netlink_dump_start(xfrm_nl, skb, nlh, link->dump, link->done); + return netlink_dump_start(net->xfrm.nlsk, skb, nlh, link->dump, link->done); } err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs, XFRMA_MAX, @@ -2033,6 +2065,7 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, struct km_eve static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) { + struct net *net = xs_net(x); struct sk_buff *skb; skb = nlmsg_new(xfrm_expire_msgsize(), GFP_ATOMIC); @@ -2042,11 +2075,12 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) if (build_expire(skb, x, c) < 0) BUG(); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); } static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c) { + struct net *net = xs_net(x); struct sk_buff *skb; skb = nlmsg_new(xfrm_aevent_msgsize(), GFP_ATOMIC); @@ -2056,11 +2090,12 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c) if (build_aevent(skb, x, c) < 0) BUG(); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC); } static int xfrm_notify_sa_flush(struct km_event *c) { + struct net *net = c->net; struct xfrm_usersa_flush *p; struct nlmsghdr *nlh; struct sk_buff *skb; @@ -2081,7 +2116,7 @@ static int xfrm_notify_sa_flush(struct km_event *c) nlmsg_end(skb, nlh); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); } static inline size_t xfrm_sa_len(struct xfrm_state *x) @@ -2111,6 +2146,7 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c) { + struct net *net = xs_net(x); struct xfrm_usersa_info *p; struct xfrm_usersa_id *id; struct nlmsghdr *nlh; @@ -2155,7 +2191,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c) nlmsg_end(skb, nlh); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_SA, GFP_ATOMIC); nla_put_failure: /* Somebody screwed up with xfrm_sa_len! */ @@ -2235,6 +2271,7 @@ nlmsg_failure: static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, struct xfrm_policy *xp, int dir) { + struct net *net = xs_net(x); struct sk_buff *skb; skb = nlmsg_new(xfrm_acquire_msgsize(x, xp), GFP_ATOMIC); @@ -2244,7 +2281,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, if (build_acquire(skb, x, xt, xp, dir) < 0) BUG(); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_ACQUIRE, GFP_ATOMIC); } /* User gives us xfrm_user_policy_info followed by an array of 0 @@ -2253,6 +2290,7 @@ static int xfrm_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *xt, static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, u8 *data, int len, int *dir) { + struct net *net = sock_net(sk); struct xfrm_userpolicy_info *p = (struct xfrm_userpolicy_info *)data; struct xfrm_user_tmpl *ut = (struct xfrm_user_tmpl *) (p + 1); struct xfrm_policy *xp; @@ -2291,7 +2329,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt, if (p->dir > XFRM_POLICY_OUT) return NULL; - xp = xfrm_policy_alloc(GFP_KERNEL); + xp = xfrm_policy_alloc(net, GFP_KERNEL); if (xp == NULL) { *dir = -ENOBUFS; return NULL; @@ -2344,6 +2382,7 @@ nlmsg_failure: static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) { + struct net *net = xp_net(xp); struct sk_buff *skb; skb = nlmsg_new(xfrm_polexpire_msgsize(xp), GFP_ATOMIC); @@ -2353,11 +2392,12 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_eve if (build_polexpire(skb, xp, dir, c) < 0) BUG(); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); } static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) { + struct net *net = xp_net(xp); struct xfrm_userpolicy_info *p; struct xfrm_userpolicy_id *id; struct nlmsghdr *nlh; @@ -2408,7 +2448,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event * nlmsg_end(skb, nlh); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); nlmsg_failure: kfree_skb(skb); @@ -2417,6 +2457,7 @@ nlmsg_failure: static int xfrm_notify_policy_flush(struct km_event *c) { + struct net *net = c->net; struct nlmsghdr *nlh; struct sk_buff *skb; @@ -2432,7 +2473,7 @@ static int xfrm_notify_policy_flush(struct km_event *c) nlmsg_end(skb, nlh); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_POLICY, GFP_ATOMIC); nlmsg_failure: kfree_skb(skb); @@ -2488,8 +2529,8 @@ nla_put_failure: return -EMSGSIZE; } -static int xfrm_send_report(u8 proto, struct xfrm_selector *sel, - xfrm_address_t *addr) +static int xfrm_send_report(struct net *net, u8 proto, + struct xfrm_selector *sel, xfrm_address_t *addr) { struct sk_buff *skb; @@ -2500,7 +2541,59 @@ static int xfrm_send_report(u8 proto, struct xfrm_selector *sel, if (build_report(skb, proto, sel, addr) < 0) BUG(); - return nlmsg_multicast(xfrm_nl, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC); + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_REPORT, GFP_ATOMIC); +} + +static inline size_t xfrm_mapping_msgsize(void) +{ + return NLMSG_ALIGN(sizeof(struct xfrm_user_mapping)); +} + +static int build_mapping(struct sk_buff *skb, struct xfrm_state *x, + xfrm_address_t *new_saddr, __be16 new_sport) +{ + struct xfrm_user_mapping *um; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, 0, 0, XFRM_MSG_MAPPING, sizeof(*um), 0); + if (nlh == NULL) + return -EMSGSIZE; + + um = nlmsg_data(nlh); + + memcpy(&um->id.daddr, &x->id.daddr, sizeof(um->id.daddr)); + um->id.spi = x->id.spi; + um->id.family = x->props.family; + um->id.proto = x->id.proto; + memcpy(&um->new_saddr, new_saddr, sizeof(um->new_saddr)); + memcpy(&um->old_saddr, &x->props.saddr, sizeof(um->old_saddr)); + um->new_sport = new_sport; + um->old_sport = x->encap->encap_sport; + um->reqid = x->props.reqid; + + return nlmsg_end(skb, nlh); +} + +static int xfrm_send_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, + __be16 sport) +{ + struct net *net = xs_net(x); + struct sk_buff *skb; + + if (x->id.proto != IPPROTO_ESP) + return -EINVAL; + + if (!x->encap) + return -EINVAL; + + skb = nlmsg_new(xfrm_mapping_msgsize(), GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + + if (build_mapping(skb, x, ipaddr, sport) < 0) + BUG(); + + return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MAPPING, GFP_ATOMIC); } static struct xfrm_mgr netlink_mgr = { @@ -2511,35 +2604,56 @@ static struct xfrm_mgr netlink_mgr = { .notify_policy = xfrm_send_policy_notify, .report = xfrm_send_report, .migrate = xfrm_send_migrate, + .new_mapping = xfrm_send_mapping, }; -static int __init xfrm_user_init(void) +static int __net_init xfrm_user_net_init(struct net *net) { struct sock *nlsk; - printk(KERN_INFO "Initializing XFRM netlink socket\n"); - - nlsk = netlink_kernel_create(&init_net, NETLINK_XFRM, XFRMNLGRP_MAX, + nlsk = netlink_kernel_create(net, NETLINK_XFRM, XFRMNLGRP_MAX, xfrm_netlink_rcv, NULL, THIS_MODULE); if (nlsk == NULL) return -ENOMEM; - rcu_assign_pointer(xfrm_nl, nlsk); - - xfrm_register_km(&netlink_mgr); - + rcu_assign_pointer(net->xfrm.nlsk, nlsk); return 0; } -static void __exit xfrm_user_exit(void) +static void __net_exit xfrm_user_net_exit(struct net *net) { - struct sock *nlsk = xfrm_nl; + struct sock *nlsk = net->xfrm.nlsk; - xfrm_unregister_km(&netlink_mgr); - rcu_assign_pointer(xfrm_nl, NULL); + rcu_assign_pointer(net->xfrm.nlsk, NULL); synchronize_rcu(); netlink_kernel_release(nlsk); } +static struct pernet_operations xfrm_user_net_ops = { + .init = xfrm_user_net_init, + .exit = xfrm_user_net_exit, +}; + +static int __init xfrm_user_init(void) +{ + int rv; + + printk(KERN_INFO "Initializing XFRM netlink socket\n"); + + rv = register_pernet_subsys(&xfrm_user_net_ops); + if (rv < 0) + return rv; + rv = xfrm_register_km(&netlink_mgr); + if (rv < 0) + unregister_pernet_subsys(&xfrm_user_net_ops); + return rv; +} + +static void __exit xfrm_user_exit(void) +{ + xfrm_unregister_km(&netlink_mgr); + unregister_pernet_subsys(&xfrm_user_net_ops); +} + module_init(xfrm_user_init); module_exit(xfrm_user_exit); MODULE_LICENSE("GPL"); -- cgit v1.2.3