From 257a4b018d1b514a1cc738e3ca11b566d8f3a3d8 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 26 Dec 2017 17:34:44 +1100 Subject: xfrm: Forbid state updates from changing encap type Currently we allow state updates to competely replace the contents of x->encap. This is bad because on the user side ESP only sets up header lengths depending on encap_type once when the state is first created. This could result in the header lengths getting out of sync with the actual state configuration. In practice key managers will never do a state update to change the encapsulation type. Only the port numbers need to be changed as the peer NAT entry is updated. Therefore this patch adds a check in xfrm_state_update to forbid any changes to the encap_type. Signed-off-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 500b3391f474..1e80f68e2266 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1534,8 +1534,12 @@ out: err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { - if (x->encap && x1->encap) + if (x->encap && x1->encap && + x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); + else if (x->encap || x1->encap) + goto fail; + if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } @@ -1552,6 +1556,8 @@ out: x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } + +fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); -- cgit v1.2.3 From 862591bf4f519d1b8d859af720fafeaebdd0162a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 27 Dec 2017 23:25:45 +0100 Subject: xfrm: skip policies marked as dead while rehashing syzkaller triggered following KASAN splat: BUG: KASAN: slab-out-of-bounds in xfrm_hash_rebuild+0xdbe/0xf00 net/xfrm/xfrm_policy.c:618 read of size 2 at addr ffff8801c8e92fe4 by task kworker/1:1/23 [..] Workqueue: events xfrm_hash_rebuild [..] __asan_report_load2_noabort+0x14/0x20 mm/kasan/report.c:428 xfrm_hash_rebuild+0xdbe/0xf00 net/xfrm/xfrm_policy.c:618 process_one_work+0xbbf/0x1b10 kernel/workqueue.c:2112 worker_thread+0x223/0x1990 kernel/workqueue.c:2246 [..] The reproducer triggers: 1016 if (error) { 1017 list_move_tail(&walk->walk.all, &x->all); 1018 goto out; 1019 } in xfrm_policy_walk() via pfkey (it sets tiny rcv space, dump callback returns -ENOBUFS). In this case, *walk is located the pfkey socket struct, so this socket becomes visible in the global policy list. It looks like this is intentional -- phony walker has walk.dead set to 1 and all other places skip such "policies". Ccing original authors of the two commits that seem to expose this issue (first patch missed ->dead check, second patch adds pfkey sockets to policies dumper list). Fixes: 880a6fab8f6ba5b ("xfrm: configure policy hash table thresholds by netlink") Fixes: 12a169e7d8f4b1c ("ipsec: Put dumpers on the dump list") Cc: Herbert Xu Cc: Timo Teras Cc: Christophe Gouault Reported-by: syzbot Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 70aa5cb0c659..2ef6db98e9ba 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -609,7 +609,8 @@ static void xfrm_hash_rebuild(struct work_struct *work) /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { - if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { + if (policy->walk.dead || + xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { /* skip socket policies */ continue; } -- cgit v1.2.3 From 2f10a61cee8fdb9f8da90f5db687e1862b22cf06 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Sun, 31 Dec 2017 16:18:56 +0100 Subject: xfrm: fix rcu usage in xfrm_get_type_offload request_module can sleep, thus we cannot hold rcu_read_lock() while calling it. The function also jumps back and takes rcu_read_lock() again (in xfrm_state_get_afinfo()), resulting in an imbalance. This codepath is triggered whenever a new offloaded state is created. Fixes: ffdb5211da1c ("xfrm: Auto-load xfrm offload modules") Reported-by: syzbot+ca425f44816d749e8eb49755567a75ee48cf4a30@syzkaller.appspotmail.com Signed-off-by: Sabrina Dubroca Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_state.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 1e80f68e2266..429957412633 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -313,13 +313,14 @@ retry: if ((type && !try_module_get(type->owner))) type = NULL; + rcu_read_unlock(); + if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); try_load = 0; goto retry; } - rcu_read_unlock(); return type; } -- cgit v1.2.3 From d16b46e4fd8bc6063624605f25b8c0835bb1fbe3 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Thu, 4 Jan 2018 22:25:07 +1100 Subject: xfrm: Use __skb_queue_tail in xfrm_trans_queue We do not need locking in xfrm_trans_queue because it is designed to use per-CPU buffers. However, the original code incorrectly used skb_queue_tail which takes the lock. This patch switches it to __skb_queue_tail instead. Reported-and-tested-by: Artem Savkov Fixes: acf568ee859f ("xfrm: Reinject transport-mode packets...") Signed-off-by: Herbert Xu Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 3f6f6f8c9fa5..5b2409746ae0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -518,7 +518,7 @@ int xfrm_trans_queue(struct sk_buff *skb, return -ENOBUFS; XFRM_TRANS_SKB_CB(skb)->finish = finish; - skb_queue_tail(&trans->queue, skb); + __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } -- cgit v1.2.3 From b1bdcb59b64f806ef08d25a85c39ffb3ad841ce6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 6 Jan 2018 01:13:08 +0100 Subject: xfrm: don't call xfrm_policy_cache_flush while holding spinlock xfrm_policy_cache_flush can sleep, so it cannot be called while holding a spinlock. We could release the lock first, but I don't see why we need to invoke this function here in first place, the packet path won't reuse an xdst entry unless its still valid. While at it, add an annotation to xfrm_policy_cache_flush, it would have probably caught this bug sooner. Fixes: ec30d78c14a813 ("xfrm: add xdst pcpu cache") Reported-by: syzbot+e149f7d1328c26f9c12f@syzkaller.appspotmail.com Signed-off-by: Florian Westphal 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 2ef6db98e9ba..bc5eae12fb09 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -975,8 +975,6 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) } if (!cnt) err = -ESRCH; - else - xfrm_policy_cache_flush(); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; @@ -1744,6 +1742,8 @@ void xfrm_policy_cache_flush(void) bool found = 0; int cpu; + might_sleep(); + local_bh_disable(); rcu_read_lock(); for_each_possible_cpu(cpu) { -- cgit v1.2.3 From 76a4201191814a0061cb5c861fafb9ecaa764846 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Wed, 10 Jan 2018 12:14:28 +0100 Subject: xfrm: Fix a race in the xdst pcpu cache. We need to run xfrm_resolve_and_create_bundle() with bottom halves off. Otherwise we may reuse an already released dst_enty when the xfrm lookup functions are called from process context. Fixes: c30d78c14a813db39a647b6a348b428 ("xfrm: add xdst pcpu cache") Reported-by: Darius Ski Signed-off-by: Steffen Klassert --- net/xfrm/xfrm_policy.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'net/xfrm') diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index bc5eae12fb09..bd6b0e7a0ee4 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2063,8 +2063,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (num_xfrms <= 0) goto make_dummy_bundle; + local_bh_disable(); xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, - xflo->dst_orig); + xflo->dst_orig); + local_bh_enable(); + if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err != -EAGAIN) @@ -2151,9 +2154,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } + local_bh_disable(); xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); + local_bh_enable(); + if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); -- cgit v1.2.3