netdev - [PATCH 05/17] xfrm: state: add sequence count to detect hash resizes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 8 Sep 2016 07:54:40 +0200
From:   Steffen Klassert <steffen.klassert@...unet.com>
To:     David Miller <davem@...emloft.net>
CC:     Herbert Xu <herbert@...dor.apana.org.au>,
        Steffen Klassert <steffen.klassert@...unet.com>,
        <netdev@...r.kernel.org>
Subject: [PATCH 05/17] xfrm: state: add sequence count to detect hash resizes

From: Florian Westphal <fw@...len.de>

Once xfrm_state_find is lockless we have to cope with a concurrent
resize opertion.

We use a sequence counter to block in case a resize is in progress
and to detect if we might have missed a state that got moved to
a new hash table.

Signed-off-by: Florian Westphal <fw@...len.de>
Signed-off-by: Steffen Klassert <steffen.klassert@...unet.com>
---
 net/xfrm/xfrm_state.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8e37387..ac4037c 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -36,6 +36,7 @@
  */
 
 static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
+static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
 
 static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
 {
@@ -127,6 +128,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	}
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	write_seqcount_begin(&xfrm_state_hash_generation);
 
 	nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
 	for (i = net->xfrm.state_hmask; i >= 0; i--)
@@ -143,6 +145,7 @@ static void xfrm_hash_resize(struct work_struct *work)
 	net->xfrm.state_byspi = nspi;
 	net->xfrm.state_hmask = nhashmask;
 
+	write_seqcount_end(&xfrm_state_hash_generation);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	osize = (ohashmask + 1) * sizeof(struct hlist_head);
@@ -787,10 +790,13 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	struct xfrm_state *best = NULL;
 	u32 mark = pol->mark.v & pol->mark.m;
 	unsigned short encap_family = tmpl->encap_family;
+	unsigned int sequence;
 	struct km_event c;
 
 	to_put = NULL;
 
+	sequence = read_seqcount_begin(&xfrm_state_hash_generation);
+
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
 	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
@@ -894,6 +900,15 @@ out:
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 	if (to_put)
 		xfrm_state_put(to_put);
+
+	if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
+		*err = -EAGAIN;
+		if (x) {
+			xfrm_state_put(x);
+			x = NULL;
+		}
+	}
+
 	return x;
 }
 
-- 
1.9.1