From e682adf021be796940be6cc10c07be7f7398c220 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Thu, 7 Nov 2013 17:47:48 +0800 Subject: xfrm: Try to honor policy index if it's supplied by user xfrm code always searches for unused policy index for newly created policy regardless whether or not user space policy index hint supplied. This patch enables such feature so that using "ip xfrm ... index=xxx" can be used by user to set specific policy index. Currently this beahvior is broken, so this patch make it happen as expected. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 16 +++++++++++----- net/xfrm/xfrm_user.c | 10 +++++++++- 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9a91f7431c41..a5bbdfb2874b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -538,7 +538,7 @@ static void xfrm_hash_resize(struct work_struct *work) /* 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(struct net *net, int dir) +static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { static u32 idx_generator; @@ -548,8 +548,14 @@ static u32 xfrm_gen_index(struct net *net, int dir) u32 idx; int found; - idx = (idx_generator | dir); - idx_generator += 8; + if (!index) { + idx = (idx_generator | dir); + idx_generator += 8; + } else { + idx = index; + index = 0; + } + if (idx == 0) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); @@ -672,7 +678,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); } - policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir); + policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); 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; @@ -1192,7 +1198,7 @@ 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(net, XFRM_POLICY_MAX+dir); + pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir); } if (old_pol) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index f964d4c00ffb..4e0546e9bb0a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1189,6 +1189,8 @@ static int verify_policy_type(u8 type) static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) { + int ret; + switch (p->share) { case XFRM_SHARE_ANY: case XFRM_SHARE_SESSION: @@ -1224,7 +1226,13 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p) return -EINVAL; } - return verify_policy_dir(p->dir); + ret = verify_policy_dir(p->dir); + if (ret) + return ret; + if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir)) + return -EINVAL; + + return 0; } static int copy_from_user_sec_ctx(struct xfrm_policy *pol, struct nlattr **attrs) -- cgit From 8d549c4f5d92d80fc6f888fd314e10972ae0ec37 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Thu, 7 Nov 2013 17:47:49 +0800 Subject: xfrm: Using the right namespace to migrate key info because the home agent could surely be run on a different net namespace other than init_net. The original behavior could lead into inconsistent of key info. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 10 +++++----- net/xfrm/xfrm_user.c | 3 ++- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index a5bbdfb2874b..907fd2fa70bc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3076,14 +3076,14 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, } static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel, - u8 dir, u8 type) + u8 dir, u8 type, struct net *net) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; u32 priority = ~0U; read_lock_bh(&xfrm_policy_lock); - chain = policy_hash_direct(&init_net, &sel->daddr, &sel->saddr, sel->family, dir); + chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { @@ -3092,7 +3092,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector break; } } - chain = &init_net.xfrm.policy_inexact[dir]; + chain = &net->xfrm.policy_inexact[dir]; hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type && @@ -3216,7 +3216,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k) + struct xfrm_kmaddress *k, struct net *net) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -3229,7 +3229,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, goto out; /* Stage 1 - find policy */ - if ((pol = xfrm_migrate_policy_find(sel, dir, type)) == NULL) { + if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) { err = -ENOENT; goto out; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4e0546e9bb0a..840cc8d9fbe4 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2137,6 +2137,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type; int err; int n = 0; + struct net *net = sock_net(skb->sk); if (attrs[XFRMA_MIGRATE] == NULL) return -EINVAL; @@ -2154,7 +2155,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, if (!n) return 0; - xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp); + xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net); return 0; } -- cgit From 283bc9f35bbbcb0e9ab4e6d2427da7f9f710d52d Mon Sep 17 00:00:00 2001 From: Fan Du Date: Thu, 7 Nov 2013 17:47:50 +0800 Subject: xfrm: Namespacify xfrm state/policy locks By semantics, xfrm layer is fully name space aware, so will the locks, e.g. xfrm_state/pocliy_lock. Ensure exclusive access into state/policy link list for different name space with one global lock is not right in terms of semantics aspect at first place, as they are indeed mutually independent with each other, but also more seriously causes scalability problem. One practical scenario is on a Open Network Stack, more than hundreds of lxc tenants acts as routers within one host, a global xfrm_state/policy_lock becomes the bottleneck. But onces those locks are decoupled in a per-namespace fashion, locks contend is just with in specific name space scope, without causing additional SPD/SAD access delay for other name space. Also this patch improve scalability while as without changing original xfrm behavior. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 104 ++++++++++++++++++++++++++----------------------- net/xfrm/xfrm_state.c | 104 +++++++++++++++++++++++++------------------------ net/xfrm/xfrm_user.c | 14 +++++-- 3 files changed, 119 insertions(+), 103 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 907fd2fa70bc..73b04d3df44e 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,12 +39,7 @@ #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 -DEFINE_MUTEX(xfrm_cfg_mutex); -EXPORT_SYMBOL(xfrm_cfg_mutex); - -static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock); static struct dst_entry *xfrm_policy_sk_bundles; -static DEFINE_RWLOCK(xfrm_policy_lock); static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo __rcu *xfrm_policy_afinfo[NPROTO] @@ -438,7 +433,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) if (!ndst) return; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(odst + i, ndst, nhashmask); @@ -446,7 +441,7 @@ static void xfrm_bydst_resize(struct net *net, int dir) net->xfrm.policy_bydst[dir].table = ndst; net->xfrm.policy_bydst[dir].hmask = nhashmask; - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } @@ -463,7 +458,7 @@ static void xfrm_byidx_resize(struct net *net, int total) if (!nidx) return; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); @@ -471,7 +466,7 @@ static void xfrm_byidx_resize(struct net *net, int total) net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } @@ -504,7 +499,7 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total) void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; @@ -513,7 +508,7 @@ void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_spd_getinfo); @@ -636,7 +631,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct hlist_head *chain; struct hlist_node *newpos; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); delpol = NULL; newpos = NULL; @@ -647,7 +642,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return -EEXIST; } delpol = pol; @@ -685,7 +680,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); list_add(&policy->walk.all, &net->xfrm.policy_all); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); @@ -705,7 +700,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, struct hlist_head *chain; *err = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); ret = NULL; hlist_for_each_entry(pol, chain, bydst) { @@ -718,7 +713,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, *err = security_xfrm_policy_delete( pol->security); if (*err) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); @@ -727,7 +722,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, break; } } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); @@ -746,7 +741,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, return NULL; *err = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { @@ -757,7 +752,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, *err = security_xfrm_policy_delete( pol->security); if (*err) { - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); @@ -766,7 +761,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, break; } } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); @@ -829,7 +824,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) { int dir, err = 0, cnt = 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, audit_info); if (err) @@ -845,7 +840,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) if (pol->type != type) continue; __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, audit_info->loginuid, @@ -854,7 +849,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) xfrm_policy_kill(pol); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); goto again1; } @@ -866,7 +861,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) if (pol->type != type) continue; __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, @@ -875,7 +870,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) audit_info->secid); xfrm_policy_kill(pol); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); goto again2; } } @@ -884,7 +879,7 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) if (!cnt) err = -ESRCH; out: - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); @@ -904,7 +899,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else @@ -930,7 +925,7 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, } list_del_init(&walk->walk.all); out: - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); @@ -944,14 +939,14 @@ void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type) } EXPORT_SYMBOL(xfrm_policy_walk_init); -void xfrm_policy_walk_done(struct xfrm_policy_walk *walk) +void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) { if (list_empty(&walk->walk.all)) return; - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); @@ -996,7 +991,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (unlikely(!daddr || !saddr)) return NULL; - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_direct(net, daddr, saddr, family, dir); ret = NULL; hlist_for_each_entry(pol, chain, bydst) { @@ -1032,7 +1027,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, if (ret) xfrm_pol_hold(ret); fail: - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } @@ -1109,8 +1104,9 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, const struct flowi *fl) { struct xfrm_policy *pol; + struct net *net = sock_net(sk); - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); if ((pol = sk->sk_policy[dir]) != NULL) { bool match = xfrm_selector_match(&pol->selector, fl, sk->sk_family); @@ -1134,7 +1130,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, pol = NULL; } out: - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } @@ -1172,9 +1168,11 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { - write_lock_bh(&xfrm_policy_lock); + struct net *net = xp_net(pol); + + write_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; @@ -1193,7 +1191,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) return -EINVAL; #endif - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = sk->sk_policy[dir]; sk->sk_policy[dir] = pol; if (pol) { @@ -1210,7 +1208,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) */ __xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir); } - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); @@ -1221,6 +1219,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); + struct net *net = xp_net(old); if (newp) { newp->selector = old->selector; @@ -1239,9 +1238,9 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) newp->type = old->type; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); - write_lock_bh(&xfrm_policy_lock); + write_lock_bh(&net->xfrm.xfrm_policy_lock); __xfrm_policy_link(newp, XFRM_POLICY_MAX+dir); - write_unlock_bh(&xfrm_policy_lock); + write_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; @@ -2112,10 +2111,10 @@ restart: dst_hold(&xdst->u.dst); - spin_lock_bh(&xfrm_policy_sk_bundle_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); xdst->u.dst.next = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = &xdst->u.dst; - spin_unlock_bh(&xfrm_policy_sk_bundle_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); route = xdst->route; } @@ -2440,7 +2439,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } xfrm_nr = ti; if (npols > 1) { - xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); + xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net); tpp = stp; } @@ -2569,10 +2568,10 @@ static void __xfrm_garbage_collect(struct net *net) { struct dst_entry *head, *next; - spin_lock_bh(&xfrm_policy_sk_bundle_lock); + spin_lock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); head = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = NULL; - spin_unlock_bh(&xfrm_policy_sk_bundle_lock); + spin_unlock_bh(&net->xfrm.xfrm_policy_sk_bundle_lock); while (head) { next = head->next; @@ -2956,6 +2955,13 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; + + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + rwlock_init(&net->xfrm.xfrm_policy_lock); + spin_lock_init(&net->xfrm.xfrm_policy_sk_bundle_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + return 0; out_sysctl: @@ -3082,7 +3088,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector struct hlist_head *chain; u32 priority = ~0U; - read_lock_bh(&xfrm_policy_lock); + read_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME*/ chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { if (xfrm_migrate_selector_match(sel, &pol->selector) && @@ -3105,7 +3111,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector if (ret) xfrm_pol_hold(ret); - read_unlock_bh(&xfrm_policy_lock); + read_unlock_bh(&net->xfrm.xfrm_policy_lock); return ret; } @@ -3236,7 +3242,7 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { - if ((x = xfrm_migrate_state_find(mp))) { + if ((x = xfrm_migrate_state_find(mp, net))) { x_cur[nx_cur] = x; nx_cur++; if ((xc = xfrm_state_migrate(x, mp))) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 68c2f357a183..290479d0746d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -35,8 +35,6 @@ destination/tunnel endpoint. (output) */ -static DEFINE_SPINLOCK(xfrm_state_lock); - static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static inline unsigned int xfrm_dst_hash(struct net *net, @@ -127,7 +125,7 @@ static void xfrm_hash_resize(struct work_struct *work) goto out_unlock; } - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; for (i = net->xfrm.state_hmask; i >= 0; i--) @@ -144,7 +142,7 @@ static void xfrm_hash_resize(struct work_struct *work) net->xfrm.state_byspi = nspi; net->xfrm.state_hmask = nhashmask; - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); xfrm_hash_free(odst, osize); @@ -535,14 +533,14 @@ int __xfrm_state_delete(struct xfrm_state *x) if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; - spin_lock(&xfrm_state_lock); + spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); hlist_del(&x->bydst); hlist_del(&x->bysrc); if (x->id.spi) hlist_del(&x->byspi); net->xfrm.state_num--; - spin_unlock(&xfrm_state_lock); + spin_unlock(&net->xfrm.xfrm_state_lock); /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that @@ -603,7 +601,7 @@ int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info) { int i, err = 0, cnt = 0; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_flush_secctx_check(net, proto, audit_info); if (err) goto out; @@ -616,7 +614,7 @@ restart: if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, @@ -627,7 +625,7 @@ restart: if (!err) cnt++; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } @@ -636,7 +634,7 @@ restart: err = 0; out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); wake_up(&net->xfrm.km_waitq); return err; } @@ -644,11 +642,11 @@ EXPORT_SYMBOL(xfrm_state_flush); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; si->sadhcnt = net->xfrm.state_hmask; si->sadhmcnt = xfrm_state_hashmax; - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); @@ -801,7 +799,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, to_put = NULL; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == encap_family && @@ -886,7 +884,7 @@ out: xfrm_state_hold(x); else *err = acquire_in_progress ? -EAGAIN : error; - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); return x; @@ -900,7 +898,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; - spin_lock(&xfrm_state_lock); + spin_lock(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && @@ -918,7 +916,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (rx) xfrm_state_hold(rx); - spin_unlock(&xfrm_state_lock); + spin_unlock(&net->xfrm.xfrm_state_lock); return rx; @@ -957,7 +955,7 @@ static void __xfrm_state_insert(struct xfrm_state *x) xfrm_hash_grow_check(net, x->bydst.next != NULL); } -/* xfrm_state_lock is held */ +/* net->xfrm.xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { struct net *net = xs_net(xnew); @@ -980,14 +978,16 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) void xfrm_state_insert(struct xfrm_state *x) { - spin_lock_bh(&xfrm_state_lock); + struct net *net = xs_net(x); + + spin_lock_bh(&net->xfrm.xfrm_state_lock); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_insert); -/* xfrm_state_lock is held */ +/* net->xfrm.xfrm_state_lock is held */ static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, @@ -1079,7 +1079,7 @@ int xfrm_state_add(struct xfrm_state *x) to_put = NULL; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { @@ -1108,7 +1108,7 @@ int xfrm_state_add(struct xfrm_state *x) err = 0; out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (x1) { xfrm_state_delete(x1); @@ -1203,16 +1203,16 @@ out: return NULL; } -/* xfrm_state_lock is held */ -struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) +/* net->xfrm.xfrm_state_lock is held */ +struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) { unsigned int h; struct xfrm_state *x; if (m->reqid) { - h = xfrm_dst_hash(&init_net, &m->old_daddr, &m->old_saddr, + h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->reqid, m->old_family); - hlist_for_each_entry(x, init_net.xfrm.state_bydst+h, bydst) { + hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1227,9 +1227,9 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) return x; } } else { - h = xfrm_src_hash(&init_net, &m->old_daddr, &m->old_saddr, + h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); - hlist_for_each_entry(x, init_net.xfrm.state_bysrc+h, bysrc) { + hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; @@ -1283,10 +1283,11 @@ int xfrm_state_update(struct xfrm_state *x) struct xfrm_state *x1, *to_put; int err; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); + struct net *net = xs_net(x); to_put = NULL; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; @@ -1306,7 +1307,7 @@ int xfrm_state_update(struct xfrm_state *x) err = 0; out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); @@ -1377,9 +1378,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup); @@ -1391,9 +1392,9 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark, { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); @@ -1405,9 +1406,9 @@ xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } @@ -1416,17 +1417,17 @@ EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, - unsigned short family) + unsigned short family, struct net *net) { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) return -EAFNOSUPPORT; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/ if (afinfo->tmpl_sort) err = afinfo->tmpl_sort(dst, src, n); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_put_afinfo(afinfo); return err; } @@ -1438,13 +1439,15 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, { int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); + struct net *net = xs_net(*dst); + if (!afinfo) return -EAFNOSUPPORT; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (afinfo->state_sort) err = afinfo->state_sort(dst, src, n); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_state_put_afinfo(afinfo); return err; } @@ -1476,9 +1479,9 @@ struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq) { struct xfrm_state *x; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_find_acq_byseq(net, mark, seq); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq_byseq); @@ -1536,10 +1539,10 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) } } if (x->id.spi) { - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); hlist_add_head(&x->byspi, net->xfrm.state_byspi+h); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; } @@ -1562,7 +1565,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, if (walk->seq != 0 && list_empty(&walk->all)) return 0; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else @@ -1586,7 +1589,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, } list_del_init(&walk->all); out: - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_walk); @@ -1600,14 +1603,14 @@ void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto) } EXPORT_SYMBOL(xfrm_state_walk_init); -void xfrm_state_walk_done(struct xfrm_state_walk *walk) +void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { if (list_empty(&walk->all)) return; - spin_lock_bh(&xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); list_del(&walk->all); - spin_unlock_bh(&xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); @@ -2026,6 +2029,7 @@ int __net_init xfrm_state_init(struct net *net) 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); + spin_lock_init(&net->xfrm.xfrm_state_lock); return 0; out_byspi: diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 840cc8d9fbe4..16c84608e81e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -877,7 +877,10 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) static int xfrm_dump_sa_done(struct netlink_callback *cb) { struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1]; - xfrm_state_walk_done(walk); + struct sock *sk = cb->skb->sk; + struct net *net = sock_net(sk); + + xfrm_state_walk_done(walk, net); return 0; } @@ -1555,8 +1558,9 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr static int xfrm_dump_policy_done(struct netlink_callback *cb) { struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1]; + struct net *net = sock_net(cb->skb->sk); - xfrm_policy_walk_done(walk); + xfrm_policy_walk_done(walk, net); return 0; } @@ -2403,9 +2407,11 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) static void xfrm_netlink_rcv(struct sk_buff *skb) { - mutex_lock(&xfrm_cfg_mutex); + struct net *net = sock_net(skb->sk); + + mutex_lock(&net->xfrm.xfrm_cfg_mutex); netlink_rcv_skb(skb, &xfrm_user_rcv_msg); - mutex_unlock(&xfrm_cfg_mutex); + mutex_unlock(&net->xfrm.xfrm_cfg_mutex); } static inline size_t xfrm_expire_msgsize(void) -- cgit From 5b8ef3415a21f173ab115e90ec92c071a03f22d7 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 27 Aug 2013 13:43:30 +0200 Subject: xfrm: Remove ancient sleeping when the SA is in acquire state We now queue packets to the policy if the states are not yet resolved, this replaces the ancient sleeping code. Also the sleeping can cause indefinite task hangs if the needed state does not get resolved. Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 21 ++------------------- net/xfrm/xfrm_state.c | 21 +-------------------- 2 files changed, 3 insertions(+), 39 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 73b04d3df44e..a7487f34e813 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1901,8 +1901,7 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, if (IS_ERR(xdst)) return xdst; - if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 || - (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP)) + if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0) return xdst; dst1 = &xdst->u.dst; @@ -2077,7 +2076,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); int i, err, num_pols, num_xfrms = 0, drop_pols = 0; -restart: dst = NULL; xdst = NULL; route = NULL; @@ -2157,23 +2155,8 @@ restart: return make_blackhole(net, family, dst_orig); } - if (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP) { - DECLARE_WAITQUEUE(wait, current); - add_wait_queue(&net->xfrm.km_waitq, &wait); - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - set_current_state(TASK_RUNNING); - remove_wait_queue(&net->xfrm.km_waitq, &wait); - - if (!signal_pending(current)) { - dst_release(dst); - goto restart; - } - - err = -ERESTART; - } else - err = -EAGAIN; + err = -EAGAIN; XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 290479d0746d..e845066547c4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -372,8 +372,6 @@ static void xfrm_state_gc_task(struct work_struct *work) hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); - - wake_up(&net->xfrm.km_waitq); } static inline unsigned long make_jiffies(long secs) @@ -388,7 +386,6 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) { struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); - struct net *net = xs_net(x); unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -458,12 +455,8 @@ resched: goto out; expired: - if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) { + if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) x->km.state = XFRM_STATE_EXPIRED; - wake_up(&net->xfrm.km_waitq); - next = 2; - goto resched; - } err = __xfrm_state_delete(x); if (!err) @@ -635,7 +628,6 @@ restart: out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); - wake_up(&net->xfrm.km_waitq); return err; } EXPORT_SYMBOL(xfrm_state_flush); @@ -948,8 +940,6 @@ static void __xfrm_state_insert(struct xfrm_state *x) if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); - wake_up(&net->xfrm.km_waitq); - net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); @@ -1658,16 +1648,12 @@ EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { - struct net *net = xs_net(x); struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); - - if (hard) - wake_up(&net->xfrm.km_waitq); } EXPORT_SYMBOL(km_state_expired); @@ -1710,16 +1696,12 @@ EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { - struct net *net = xp_net(pol); struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); - - if (hard) - wake_up(&net->xfrm.km_waitq); } EXPORT_SYMBOL(km_policy_expired); @@ -2028,7 +2010,6 @@ int __net_init xfrm_state_init(struct net *net) 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); spin_lock_init(&net->xfrm.xfrm_state_lock); return 0; -- cgit From ea9884b3acf3311c8a11db67bfab21773f6f82ba Mon Sep 17 00:00:00 2001 From: Fan Du Date: Mon, 16 Dec 2013 18:47:48 +0800 Subject: xfrm: check user specified spi for IPComp IPComp connection between two hosts is broken if given spi bigger than 0xffff. OUTSPI=0x87 INSPI=0x11112 ip xfrm policy update dst 192.168.1.101 src 192.168.1.109 dir out action allow \ tmpl dst 192.168.1.101 src 192.168.1.109 proto comp spi $OUTSPI ip xfrm policy update src 192.168.1.101 dst 192.168.1.109 dir in action allow \ tmpl src 192.168.1.101 dst 192.168.1.109 proto comp spi $INSPI ip xfrm state add src 192.168.1.101 dst 192.168.1.109 proto comp spi $INSPI \ comp deflate ip xfrm state add dst 192.168.1.101 src 192.168.1.109 proto comp spi $OUTSPI \ comp deflate tcpdump can capture outbound ping packet, but inbound packet is dropped with XfrmOutNoStates errors. It looks like spi value used for IPComp is expected to be 16bits wide only. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_user.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 16c84608e81e..4027c4266a87 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -181,7 +181,9 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, attrs[XFRMA_ALG_AEAD] || attrs[XFRMA_ALG_CRYPT] || attrs[XFRMA_ALG_COMP] || - attrs[XFRMA_TFCPAD]) + attrs[XFRMA_TFCPAD] || + (ntohl(p->id.spi) >= 0x10000)) + goto out; break; -- cgit From 776e9dd90ca223b82166eb2835389493b5914cba Mon Sep 17 00:00:00 2001 From: Fan Du Date: Mon, 16 Dec 2013 18:47:49 +0800 Subject: xfrm: export verify_userspi_info for pkfey and netlink interface In order to check against valid IPcomp spi range, export verify_userspi_info for both pfkey and netlink interface. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 24 ++++++++++++++++++++++++ net/xfrm/xfrm_user.c | 25 +------------------------ 2 files changed, 25 insertions(+), 24 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index e845066547c4..a62c25ea3631 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1489,6 +1489,30 @@ u32 xfrm_get_acqseq(void) } EXPORT_SYMBOL(xfrm_get_acqseq); +int verify_spi_info(u8 proto, u32 min, u32 max) +{ + switch (proto) { + case IPPROTO_AH: + case IPPROTO_ESP: + break; + + case IPPROTO_COMP: + /* IPCOMP spi is 16-bits. */ + if (max >= 0x10000) + return -EINVAL; + break; + + default: + return -EINVAL; + } + + if (min > max) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL(verify_spi_info); + int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) { struct net *net = xs_net(x); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4027c4266a87..97681a390402 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1079,29 +1079,6 @@ out_noput: return err; } -static int verify_userspi_info(struct xfrm_userspi_info *p) -{ - switch (p->info.id.proto) { - case IPPROTO_AH: - case IPPROTO_ESP: - break; - - case IPPROTO_COMP: - /* IPCOMP spi is 16-bits. */ - if (p->max >= 0x10000) - return -EINVAL; - break; - - default: - return -EINVAL; - } - - if (p->min > p->max) - return -EINVAL; - - return 0; -} - static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr **attrs) { @@ -1116,7 +1093,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_mark m; p = nlmsg_data(nlh); - err = verify_userspi_info(p); + err = verify_spi_info(p->info.id.proto, p->min, p->max); if (err) goto out_noput; -- cgit From 9b7a787d0da7db3127f6e04f8f8159632da50a36 Mon Sep 17 00:00:00 2001 From: Weilong Chen Date: Tue, 24 Dec 2013 09:43:46 +0800 Subject: xfrm: checkpatch errors with space This patch cleanup some space errors. Signed-off-by: Weilong Chen Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 10 +++++----- net/xfrm/xfrm_proc.c | 2 +- net/xfrm/xfrm_state.c | 10 +++++----- net/xfrm/xfrm_user.c | 4 ++-- 4 files changed, 13 insertions(+), 13 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index a7487f34e813..8a2b9d8e1d58 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1286,7 +1286,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; - for (nx=0, i = 0; i < policy->xfrm_nr; i++) { + for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; @@ -1326,7 +1326,7 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, return nx; fail: - for (nx--; nx>=0; nx--) + for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } @@ -1363,7 +1363,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, return cnx; fail: - for (cnx--; cnx>=0; cnx--) + for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; @@ -2332,7 +2332,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (skb->sp) { int i; - for (i=skb->sp->len-1; i>=0; i--) { + 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(net, LINUX_MIB_XFRMINSTATEMISMATCH); @@ -2987,7 +2987,7 @@ static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(sel->family) { + switch (sel->family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index 80cd1e55b834..fc5abd0b456f 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -52,7 +52,7 @@ 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++) + for (i = 0; xfrm_mib_list[i].name; i++) seq_printf(seq, "%-24s\t%lu\n", xfrm_mib_list[i].name, snmp_fold_field((void __percpu **) net->mib.xfrm_statistics, diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a62c25ea3631..5fe79b42561d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -448,7 +448,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) if (warn) km_state_expired(x, 0, 0); resched: - if (next != LONG_MAX){ + if (next != LONG_MAX) { tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL); } @@ -1348,7 +1348,7 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; - tasklet_hrtimer_start(&x->mtimer, ktime_set(0,0), HRTIMER_MODE_REL); + tasklet_hrtimer_start(&x->mtimer, ktime_set(0, 0), HRTIMER_MODE_REL); return -EINVAL; } @@ -1542,7 +1542,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) x->id.spi = minspi; } else { u32 spi = 0; - for (h=0; hid.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { @@ -2079,7 +2079,7 @@ static void xfrm_audit_helper_sainfo(struct xfrm_state *x, audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); - switch(x->props.family) { + switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); @@ -2109,7 +2109,7 @@ static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", - &iph6->saddr,&iph6->daddr, + &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 97681a390402..e50be4275c6c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1731,11 +1731,11 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct return -EMSGSIZE; id = nlmsg_data(nlh); - memcpy(&id->sa_id.daddr, &x->id.daddr,sizeof(x->id.daddr)); + memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr)); id->sa_id.spi = x->id.spi; id->sa_id.family = x->props.family; id->sa_id.proto = x->id.proto; - memcpy(&id->saddr, &x->props.saddr,sizeof(x->props.saddr)); + memcpy(&id->saddr, &x->props.saddr, sizeof(x->props.saddr)); id->reqid = x->props.reqid; id->flags = c->data.aevent; -- cgit From 3e94c2dcfd7ca297bd7e0a8d96be1e76dec711a3 Mon Sep 17 00:00:00 2001 From: Weilong Chen Date: Tue, 24 Dec 2013 09:43:47 +0800 Subject: xfrm: checkpatch errors with foo * bar This patch clean up some checkpatch errors like this: ERROR: "foo * bar" should be "foo *bar" ERROR: "(foo*)" should be "(foo *)" Signed-off-by: Weilong Chen Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 6 +++--- net/xfrm/xfrm_policy.c | 12 ++++++------ net/xfrm/xfrm_state.c | 8 ++++---- 3 files changed, 13 insertions(+), 13 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 88843996f935..6c7ac016ce3a 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -67,7 +67,7 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) case IPPROTO_COMP: if (!pskb_may_pull(skb, sizeof(struct ip_comp_hdr))) return -EINVAL; - *spi = htonl(ntohs(*(__be16*)(skb_transport_header(skb) + 2))); + *spi = htonl(ntohs(*(__be16 *)(skb_transport_header(skb) + 2))); *seq = 0; return 0; default: @@ -77,8 +77,8 @@ int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq) if (!pskb_may_pull(skb, hlen)) return -EINVAL; - *spi = *(__be32*)(skb_transport_header(skb) + offset); - *seq = *(__be32*)(skb_transport_header(skb) + offset_seq); + *spi = *(__be32 *)(skb_transport_header(skb) + offset); + *seq = *(__be32 *)(skb_transport_header(skb) + offset_seq); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 8a2b9d8e1d58..dc8bd1ba4b3e 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -171,7 +171,7 @@ static inline unsigned long make_jiffies(long secs) static void xfrm_policy_timer(unsigned long data) { - struct xfrm_policy *xp = (struct xfrm_policy*)data; + struct xfrm_policy *xp = (struct xfrm_policy *)data; unsigned long now = get_seconds(); long next = LONG_MAX; int warn = 0; @@ -1758,7 +1758,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, } xdst->num_pols = num_pols; - memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; @@ -2027,7 +2027,7 @@ make_dummy_bundle: } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; - memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); dst_hold(&xdst->u.dst); return &xdst->flo; @@ -2136,7 +2136,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; - memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols); + memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } @@ -3064,8 +3064,8 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, return false; } -static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel, - u8 dir, u8 type, struct net *net) +static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, + u8 dir, u8 type, struct net *net) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 5fe79b42561d..9e6a4d6a9d8f 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -382,7 +382,7 @@ static inline unsigned long make_jiffies(long secs) return secs*HZ; } -static enum hrtimer_restart xfrm_timer_handler(struct hrtimer * me) +static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); @@ -1237,8 +1237,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n } EXPORT_SYMBOL(xfrm_migrate_state_find); -struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, - struct xfrm_migrate *m) +struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, + struct xfrm_migrate *m) { struct xfrm_state *xc; int err; @@ -1630,7 +1630,7 @@ EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(unsigned long data) { - struct xfrm_state *x = (struct xfrm_state*)data; + struct xfrm_state *x = (struct xfrm_state *)data; spin_lock(&x->lock); -- cgit From 02d0892f98a5f43c86a3ee9dc796e529557a9f80 Mon Sep 17 00:00:00 2001 From: Weilong Chen Date: Tue, 24 Dec 2013 09:43:48 +0800 Subject: xfrm: checkpatch erros with space prohibited Fix checkpatch error "space prohibited xxx". Signed-off-by: Weilong Chen Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 6 +++--- net/xfrm/xfrm_user.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index dc8bd1ba4b3e..fbc72b4570de 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1704,7 +1704,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, xfrm_pols_put(pols, *num_pols); return PTR_ERR(pols[1]); } - (*num_pols) ++; + (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } @@ -2378,7 +2378,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol->curlft.use_time = get_seconds(); pols[0] = pol; - npols ++; + npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, @@ -2390,7 +2390,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 0; } pols[1]->curlft.use_time = get_seconds(); - npols ++; + npols++; } } #endif diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e50be4275c6c..334856689b0d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1824,7 +1824,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct xfrm_state *x; struct km_event c; - int err = - EINVAL; + int err = -EINVAL; u32 mark = 0; struct xfrm_mark m; struct xfrm_aevent_id *p = nlmsg_data(nlh); -- cgit From 42054569f9b0da4f9a6cc91709f1a80fa83cb453 Mon Sep 17 00:00:00 2001 From: Weilong Chen Date: Tue, 24 Dec 2013 09:43:49 +0800 Subject: xfrm: fix checkpatch error Fix that "else should follow close brace '}'". Signed-off-by: Weilong Chen Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index fbc72b4570de..b5c315e175a0 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1316,9 +1316,9 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); - } - else if (error == -ESRCH) + } else if (error == -ESRCH) { error = -EAGAIN; + } if (!tmpl->optional) goto fail; -- cgit From 2f3ea9a95c58fd0e4bed18a9c9dfe53739fee3b2 Mon Sep 17 00:00:00 2001 From: Weilong Chen Date: Tue, 24 Dec 2013 09:43:50 +0800 Subject: xfrm: checkpatch erros with inline keyword position Signed-off-by: Weilong Chen Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b5c315e175a0..fe8942bb8bbc 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1641,7 +1641,7 @@ free_dst: goto out; } -static int inline +static inline int xfrm_dst_alloc_copy(void **target, const void *src, int size) { if (!*target) { @@ -1653,7 +1653,7 @@ xfrm_dst_alloc_copy(void **target, const void *src, int size) return 0; } -static int inline +static inline int xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) { #ifdef CONFIG_XFRM_SUB_POLICY @@ -1665,7 +1665,7 @@ xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) #endif } -static int inline +static inline int xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl) { #ifdef CONFIG_XFRM_SUB_POLICY -- cgit From 4ae770bf58ce6315e0f4a1bd4b7e574bdfa59ca9 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Fri, 3 Jan 2014 11:18:29 +0800 Subject: {pktgen, xfrm} Correct xfrm_state_lock usage in xfrm_stateonly_find Acquiring xfrm_state_lock in process context is expected to turn BH off, as this lock is also used in BH context, namely xfrm state timer handler. Otherwise it surprises LOCKDEP with below messages. [ 81.422781] pktgen: Packet Generator for packet performance testing. Version: 2.74 [ 81.725194] [ 81.725211] ========================================================= [ 81.725212] [ INFO: possible irq lock inversion dependency detected ] [ 81.725215] 3.13.0-rc2+ #92 Not tainted [ 81.725216] --------------------------------------------------------- [ 81.725218] kpktgend_0/2780 just changed the state of lock: [ 81.725220] (xfrm_state_lock){+.+...}, at: [] xfrm_stateonly_find+0x41/0x1f0 [ 81.725231] but this lock was taken by another, SOFTIRQ-safe lock in the past: [ 81.725232] (&(&x->lock)->rlock){+.-...} [ 81.725232] [ 81.725232] and interrupts could create inverse lock ordering between them. [ 81.725232] [ 81.725235] [ 81.725235] other info that might help us debug this: [ 81.725237] Possible interrupt unsafe locking scenario: [ 81.725237] [ 81.725238] CPU0 CPU1 [ 81.725240] ---- ---- [ 81.725241] lock(xfrm_state_lock); [ 81.725243] local_irq_disable(); [ 81.725244] lock(&(&x->lock)->rlock); [ 81.725246] lock(xfrm_state_lock); [ 81.725248] [ 81.725249] lock(&(&x->lock)->rlock); [ 81.725251] [ 81.725251] *** DEADLOCK *** [ 81.725251] [ 81.725254] no locks held by kpktgend_0/2780. [ 81.725255] [ 81.725255] the shortest dependencies between 2nd lock and 1st lock: [ 81.725269] -> (&(&x->lock)->rlock){+.-...} ops: 8 { [ 81.725274] HARDIRQ-ON-W at: [ 81.725276] [] __lock_acquire+0x65b/0x1d70 [ 81.725282] [] lock_acquire+0x97/0x130 [ 81.725284] [] _raw_spin_lock+0x36/0x70 [ 81.725289] [] xfrm_timer_handler+0x43/0x290 [ 81.725292] [] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725300] [] tasklet_hi_action+0xd7/0xf0 [ 81.725303] [] __do_softirq+0xe6/0x2d0 [ 81.725305] [] irq_exit+0x96/0xc0 [ 81.725308] [] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725313] [] apic_timer_interrupt+0x6f/0x80 [ 81.725316] [] arch_cpu_idle+0x26/0x30 [ 81.725329] [] cpu_startup_entry+0x88/0x2b0 [ 81.725333] [] start_secondary+0x190/0x1f0 [ 81.725338] IN-SOFTIRQ-W at: [ 81.725340] [] __lock_acquire+0x62d/0x1d70 [ 81.725342] [] lock_acquire+0x97/0x130 [ 81.725344] [] _raw_spin_lock+0x36/0x70 [ 81.725347] [] xfrm_timer_handler+0x43/0x290 [ 81.725349] [] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725352] [] tasklet_hi_action+0xd7/0xf0 [ 81.725355] [] __do_softirq+0xe6/0x2d0 [ 81.725358] [] irq_exit+0x96/0xc0 [ 81.725360] [] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725363] [] apic_timer_interrupt+0x6f/0x80 [ 81.725365] [] arch_cpu_idle+0x26/0x30 [ 81.725368] [] cpu_startup_entry+0x88/0x2b0 [ 81.725370] [] start_secondary+0x190/0x1f0 [ 81.725373] INITIAL USE at: [ 81.725375] [] __lock_acquire+0x32a/0x1d70 [ 81.725385] [] lock_acquire+0x97/0x130 [ 81.725388] [] _raw_spin_lock+0x36/0x70 [ 81.725390] [] xfrm_timer_handler+0x43/0x290 [ 81.725394] [] __tasklet_hrtimer_trampoline+0x17/0x40 [ 81.725398] [] tasklet_hi_action+0xd7/0xf0 [ 81.725401] [] __do_softirq+0xe6/0x2d0 [ 81.725404] [] irq_exit+0x96/0xc0 [ 81.725407] [] smp_apic_timer_interrupt+0x4a/0x60 [ 81.725409] [] apic_timer_interrupt+0x6f/0x80 [ 81.725412] [] arch_cpu_idle+0x26/0x30 [ 81.725415] [] cpu_startup_entry+0x88/0x2b0 [ 81.725417] [] start_secondary+0x190/0x1f0 [ 81.725420] } [ 81.725421] ... key at: [] __key.46349+0x0/0x8 [ 81.725445] ... acquired at: [ 81.725446] [] lock_acquire+0x97/0x130 [ 81.725449] [] _raw_spin_lock+0x36/0x70 [ 81.725452] [] __xfrm_state_delete+0x37/0x140 [ 81.725454] [] xfrm_state_delete+0x2c/0x50 [ 81.725456] [] xfrm_state_flush+0xc7/0x1b0 [ 81.725458] [] pfkey_flush+0x7c/0x100 [af_key] [ 81.725465] [] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725468] [] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725471] [] sock_sendmsg+0xaf/0xc0 [ 81.725476] [] SYSC_sendto+0xfc/0x130 [ 81.725479] [] SyS_sendto+0xe/0x10 [ 81.725482] [] system_call_fastpath+0x16/0x1b [ 81.725484] [ 81.725486] -> (xfrm_state_lock){+.+...} ops: 11 { [ 81.725490] HARDIRQ-ON-W at: [ 81.725493] [] __lock_acquire+0x65b/0x1d70 [ 81.725504] [] lock_acquire+0x97/0x130 [ 81.725507] [] _raw_spin_lock_bh+0x3b/0x70 [ 81.725510] [] xfrm_state_flush+0x2f/0x1b0 [ 81.725513] [] pfkey_flush+0x7c/0x100 [af_key] [ 81.725516] [] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725519] [] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725522] [] sock_sendmsg+0xaf/0xc0 [ 81.725525] [] SYSC_sendto+0xfc/0x130 [ 81.725527] [] SyS_sendto+0xe/0x10 [ 81.725530] [] system_call_fastpath+0x16/0x1b [ 81.725533] SOFTIRQ-ON-W at: [ 81.725534] [] __lock_acquire+0x68a/0x1d70 [ 81.725537] [] lock_acquire+0x97/0x130 [ 81.725539] [] _raw_spin_lock+0x36/0x70 [ 81.725541] [] xfrm_stateonly_find+0x41/0x1f0 [ 81.725544] [] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725547] [] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725550] [] kthread+0xe4/0x100 [ 81.725555] [] ret_from_fork+0x7c/0xb0 [ 81.725565] INITIAL USE at: [ 81.725567] [] __lock_acquire+0x32a/0x1d70 [ 81.725569] [] lock_acquire+0x97/0x130 [ 81.725572] [] _raw_spin_lock_bh+0x3b/0x70 [ 81.725574] [] xfrm_state_flush+0x2f/0x1b0 [ 81.725576] [] pfkey_flush+0x7c/0x100 [af_key] [ 81.725580] [] pfkey_process+0x1c7/0x1f0 [af_key] [ 81.725583] [] pfkey_sendmsg+0x159/0x260 [af_key] [ 81.725586] [] sock_sendmsg+0xaf/0xc0 [ 81.725589] [] SYSC_sendto+0xfc/0x130 [ 81.725594] [] SyS_sendto+0xe/0x10 [ 81.725597] [] system_call_fastpath+0x16/0x1b [ 81.725599] } [ 81.725600] ... key at: [] xfrm_state_lock+0x18/0x50 [ 81.725606] ... acquired at: [ 81.725607] [] check_usage_backwards+0x110/0x150 [ 81.725609] [] mark_lock+0x196/0x2f0 [ 81.725611] [] __lock_acquire+0x68a/0x1d70 [ 81.725614] [] lock_acquire+0x97/0x130 [ 81.725616] [] _raw_spin_lock+0x36/0x70 [ 81.725627] [] xfrm_stateonly_find+0x41/0x1f0 [ 81.725629] [] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725632] [] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725635] [] kthread+0xe4/0x100 [ 81.725637] [] ret_from_fork+0x7c/0xb0 [ 81.725640] [ 81.725641] [ 81.725641] stack backtrace: [ 81.725645] CPU: 0 PID: 2780 Comm: kpktgend_0 Not tainted 3.13.0-rc2+ #92 [ 81.725647] Hardware name: innotek GmbH VirtualBox, BIOS VirtualBox 12/01/2006 [ 81.725649] ffffffff82537b80 ffff880018199988 ffffffff8176af37 0000000000000007 [ 81.725652] ffff8800181999f0 ffff8800181999d8 ffffffff81099358 ffffffff82537b80 [ 81.725655] ffffffff81a32def ffff8800181999f4 0000000000000000 ffff880002cbeaa8 [ 81.725659] Call Trace: [ 81.725664] [] dump_stack+0x46/0x58 [ 81.725667] [] print_irq_inversion_bug.part.42+0x1e8/0x1f0 [ 81.725670] [] check_usage_backwards+0x110/0x150 [ 81.725672] [] mark_lock+0x196/0x2f0 [ 81.725675] [] ? check_usage_forwards+0x150/0x150 [ 81.725685] [] __lock_acquire+0x68a/0x1d70 [ 81.725691] [] ? sched_clock_local+0x25/0x90 [ 81.725694] [] ? sched_clock_cpu+0xa8/0x120 [ 81.725697] [] ? __lock_acquire+0x32a/0x1d70 [ 81.725699] [] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725702] [] lock_acquire+0x97/0x130 [ 81.725704] [] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725707] [] ? sched_clock_local+0x25/0x90 [ 81.725710] [] _raw_spin_lock+0x36/0x70 [ 81.725712] [] ? xfrm_stateonly_find+0x41/0x1f0 [ 81.725715] [] ? lock_release_holdtime.part.26+0x1c/0x1a0 [ 81.725717] [] xfrm_stateonly_find+0x41/0x1f0 [ 81.725721] [] mod_cur_headers+0x793/0x7f0 [pktgen] [ 81.725724] [] pktgen_thread_worker+0xd42/0x1880 [pktgen] [ 81.725727] [] ? pktgen_thread_worker+0xb11/0x1880 [pktgen] [ 81.725729] [] ? trace_hardirqs_on+0xd/0x10 [ 81.725733] [] ? _raw_spin_unlock_irq+0x30/0x40 [ 81.725745] [] ? e1000_clean+0x9d0/0x9d0 [ 81.725751] [] ? __init_waitqueue_head+0x60/0x60 [ 81.725753] [] ? __init_waitqueue_head+0x60/0x60 [ 81.725757] [] ? mod_cur_headers+0x7f0/0x7f0 [pktgen] [ 81.725759] [] kthread+0xe4/0x100 [ 81.725762] [] ? flush_kthread_worker+0x170/0x170 [ 81.725765] [] ret_from_fork+0x7c/0xb0 [ 81.725768] [] ? flush_kthread_worker+0x170/0x170 Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9e6a4d6a9d8f..300744094ad8 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -890,7 +890,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; - spin_lock(&net->xfrm.xfrm_state_lock); + spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) { if (x->props.family == family && @@ -908,7 +908,7 @@ xfrm_stateonly_find(struct net *net, u32 mark, if (rx) xfrm_state_hold(rx); - spin_unlock(&net->xfrm.xfrm_state_lock); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; -- cgit From c454997e68eb013510ba128283ad3b4aefeff630 Mon Sep 17 00:00:00 2001 From: Fan Du Date: Fri, 3 Jan 2014 11:18:32 +0800 Subject: {pktgen, xfrm} Introduce xfrm_state_lookup_byspi for pktgen Introduce xfrm_state_lookup_byspi to find user specified by custom from "pgset spi xxx". Using this scheme, any flow regardless its saddr/daddr could be transform by SA specified with configurable spi. Signed-off-by: Fan Du Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 300744094ad8..62181486ead8 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -915,6 +915,28 @@ xfrm_stateonly_find(struct net *net, u32 mark, } EXPORT_SYMBOL(xfrm_stateonly_find); +struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, + unsigned short family) +{ + struct xfrm_state *x; + struct xfrm_state_walk *w; + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + list_for_each_entry(w, &net->xfrm.state_all, all) { + x = container_of(w, struct xfrm_state, km); + if (x->props.family != family || + x->id.spi != spi) + continue; + + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + xfrm_state_hold(x); + return x; + } + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + return NULL; +} +EXPORT_SYMBOL(xfrm_state_lookup_byspi); + static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); -- cgit From be7928d20bab8517a0e38db2418394e8b2fd6a8e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 7 Jan 2014 23:20:27 +0100 Subject: net: xfrm: xfrm_policy: fix inline not at beginning of declaration Fix three warnings related to: net/xfrm/xfrm_policy.c:1644:1: warning: 'inline' is not at beginning of declaration [-Wold-style-declaration] net/xfrm/xfrm_policy.c:1656:1: warning: 'inline' is not at beginning of declaration [-Wold-style-declaration] net/xfrm/xfrm_policy.c:1668:1: warning: 'inline' is not at beginning of declaration [-Wold-style-declaration] Just removing the inline keyword is sufficient as the compiler will decide on its own about inlining or not. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/xfrm/xfrm_policy.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index a7487f34e813..b39044631b0c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1641,20 +1641,20 @@ free_dst: goto out; } -static int inline -xfrm_dst_alloc_copy(void **target, const void *src, int size) +static int xfrm_dst_alloc_copy(void **target, const void *src, int size) { if (!*target) { *target = kmalloc(size, GFP_ATOMIC); if (!*target) return -ENOMEM; } + memcpy(*target, src, size); return 0; } -static int inline -xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) +static int xfrm_dst_update_parent(struct dst_entry *dst, + const struct xfrm_selector *sel) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -1665,8 +1665,8 @@ xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) #endif } -static int inline -xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl) +static int xfrm_dst_update_origin(struct dst_entry *dst, + const struct flowi *fl) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_dst *xdst = (struct xfrm_dst *)dst; -- cgit From da7c224b1baaeb7543dc7663ae78716f9a6864c1 Mon Sep 17 00:00:00 2001 From: Ying Xue Date: Wed, 8 Jan 2014 10:26:39 +0800 Subject: net: xfrm: xfrm_policy: silence compiler warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix below compiler warning: net/xfrm/xfrm_policy.c:1644:12: warning: ‘xfrm_dst_alloc_copy’ defined but not used [-Wunused-function] Signed-off-by: Ying Xue Signed-off-by: David S. Miller --- net/xfrm/xfrm_policy.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index b39044631b0c..e205c4b56afb 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1641,6 +1641,7 @@ free_dst: goto out; } +#ifdef CONFIG_XFRM_SUB_POLICY static int xfrm_dst_alloc_copy(void **target, const void *src, int size) { if (!*target) { @@ -1652,6 +1653,7 @@ static int xfrm_dst_alloc_copy(void **target, const void *src, int size) memcpy(*target, src, size); return 0; } +#endif static int xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) -- cgit From 63862b5bef7349dd1137e4c70702c67d77565785 Mon Sep 17 00:00:00 2001 From: Aruna-Hewapathirane Date: Sat, 11 Jan 2014 07:15:59 -0500 Subject: net: replace macros net_random and net_srandom with direct calls to prandom This patch removes the net_random and net_srandom macros and replaces them with direct calls to the prandom ones. As new commits only seem to use prandom_u32 there is no use to keep them around. This change makes it easier to grep for users of prandom_u32. Signed-off-by: Aruna-Hewapathirane Suggested-by: Hannes Frederic Sowa Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/xfrm/xfrm_state.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 62181486ead8..8d11d28991a4 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1565,7 +1565,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high) } else { u32 spi = 0; for (h = 0; h < high-low+1; h++) { - spi = low + net_random()%(high-low+1); + spi = low + prandom_u32()%(high-low+1); x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); if (x0 == NULL) { x->id.spi = htonl(spi); -- cgit