This is a note to let you know that I've just added the patch titled
xfrm: state: fix out-of-bounds read during lookup
to the 6.13-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
xfrm-state-fix-out-of-bounds-read-during-lookup.patch
and it can be found in the queue-6.13 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 4dad9a8c8bc308098cdb2a9d73858e6fc27fedcc
Author: Florian Westphal <fw@xxxxxxxxx>
Date: Thu Nov 28 15:26:25 2024 +0100
xfrm: state: fix out-of-bounds read during lookup
[ Upstream commit e952837f3ddb0ff726d5b582aa1aad9aa38d024d ]
lookup and resize can run in parallel.
The xfrm_state_hash_generation seqlock ensures a retry, but the hash
functions can observe a hmask value that is too large for the new hlist
array.
rehash does:
rcu_assign_pointer(net->xfrm.state_bydst, ndst) [..]
net->xfrm.state_hmask = nhashmask;
While state lookup does:
h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
This is only safe in case the update to state_bydst is larger than
net->xfrm.xfrm_state_hmask (or if the lookup function gets
serialized via state spinlock again).
Fix this by prefetching state_hmask and the associated pointers.
The xfrm_state_hash_generation seqlock retry will ensure that the pointer
and the hmask will be consistent.
The existing helpers, like xfrm_dst_hash(), are now unsafe for RCU side,
add lockdep assertions to document that they are only safe for insert
side.
xfrm_state_lookup_byaddr() uses the spinlock rather than RCU.
AFAICS this is an oversight from back when state lookup was converted to
RCU, this lock should be replaced with RCU in a future patch.
Reported-by: syzbot+5f9f31cb7d985f584d8e@xxxxxxxxxxxxxxxxxxxxxxxxx
Closes: https://lore.kernel.org/netdev/CACT4Y+azwfrE3uz6A5ZErov5YN2LYBN5KrsymBerT36VU8qzBA@xxxxxxxxxxxxxx/
Diagnosed-by: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
Fixes: c2f672fc9464 ("xfrm: state lookup can be lockless")
Signed-off-by: Florian Westphal <fw@xxxxxxxxx>
Signed-off-by: Steffen Klassert <steffen.klassert@xxxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 67ca7ac955a37..1781728ca4285 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -34,6 +34,8 @@
#define xfrm_state_deref_prot(table, net) \
rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+#define xfrm_state_deref_check(table, net) \
+ rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
static void xfrm_state_gc_task(struct work_struct *work);
@@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net,
u32 reqid,
unsigned short family)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask);
}
@@ -70,6 +74,8 @@ static inline unsigned int xfrm_src_hash(struct net *net,
const xfrm_address_t *saddr,
unsigned short family)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask);
}
@@ -77,11 +83,15 @@ static inline unsigned int
xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr,
__be32 spi, u8 proto, unsigned short family)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask);
}
static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
{
+ lockdep_assert_held(&net->xfrm.xfrm_state_lock);
+
return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
}
@@ -1041,16 +1051,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl,
x->props.family = tmpl->encap_family;
}
-static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
+struct xfrm_hash_state_ptrs {
+ const struct hlist_head *bydst;
+ const struct hlist_head *bysrc;
+ const struct hlist_head *byspi;
+ unsigned int hmask;
+};
+
+static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs)
+{
+ unsigned int sequence;
+
+ do {
+ sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
+
+ ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net);
+ ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net);
+ ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net);
+ ptrs->hmask = net->xfrm.state_hmask;
+ } while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence));
+}
+
+static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs,
+ u32 mark,
const xfrm_address_t *daddr,
__be32 spi, u8 proto,
unsigned short family,
struct xfrm_dev_offload *xdo)
{
- unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+ unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
struct xfrm_state *x;
- hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+ hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
#ifdef CONFIG_XFRM_OFFLOAD
if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) {
if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1084,15 +1116,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark,
return NULL;
}
-static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs,
+ u32 mark,
const xfrm_address_t *daddr,
__be32 spi, u8 proto,
unsigned short family)
{
- unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
+ unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask);
struct xfrm_state *x;
- hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+ hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) {
if (x->props.family != family ||
x->id.spi != spi ||
x->id.proto != proto ||
@@ -1114,6 +1147,7 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
__be32 spi, u8 proto,
unsigned short family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct hlist_head *state_cache_input;
struct xfrm_state *x = NULL;
int cpu = get_cpu();
@@ -1135,7 +1169,9 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
goto out;
}
- x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
if (x && x->km.state == XFRM_STATE_VALID) {
spin_lock_bh(&net->xfrm.xfrm_state_lock);
@@ -1155,15 +1191,16 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
}
EXPORT_SYMBOL(xfrm_input_state_lookup);
-static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
+static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs,
+ u32 mark,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
- unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
+ unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask);
struct xfrm_state *x;
- hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
+ hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) {
if (x->props.family != family ||
x->id.proto != proto ||
!xfrm_addr_equal(&x->id.daddr, daddr, family) ||
@@ -1183,14 +1220,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
static inline struct xfrm_state *
__xfrm_state_locate(struct xfrm_state *x, int use_spi, int family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct net *net = xs_net(x);
u32 mark = x->mark.v & x->mark.m;
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
if (use_spi)
- return __xfrm_state_lookup(net, mark, &x->id.daddr,
+ return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr,
x->id.spi, x->id.proto, family);
else
- return __xfrm_state_lookup_byaddr(net, mark,
+ return __xfrm_state_lookup_byaddr(&state_ptrs, mark,
&x->id.daddr,
&x->props.saddr,
x->id.proto, family);
@@ -1264,6 +1304,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
unsigned short family, u32 if_id)
{
static xfrm_address_t saddr_wildcard = { };
+ struct xfrm_hash_state_ptrs state_ptrs;
struct net *net = xp_net(pol);
unsigned int h, h_wildcard;
struct xfrm_state *x, *x0, *to_put;
@@ -1328,8 +1369,10 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */
WARN_ON(1);
- h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
- hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask);
+ hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) {
#ifdef CONFIG_XFRM_OFFLOAD
if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1362,8 +1405,9 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
if (best || acquire_in_progress)
goto found;
- h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
- hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
+ h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid,
+ encap_family, state_ptrs.hmask);
+ hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) {
#ifdef CONFIG_XFRM_OFFLOAD
if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
@@ -1401,7 +1445,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
if (!x && !error && !acquire_in_progress) {
if (tmpl->id.spi &&
- (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+ (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr,
tmpl->id.spi, tmpl->id.proto,
encap_family,
&pol->xdo)) != NULL) {
@@ -2180,10 +2224,13 @@ struct xfrm_state *
xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
u8 proto, unsigned short family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct xfrm_state *x;
rcu_read_lock();
- x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
rcu_read_unlock();
return x;
}
@@ -2194,10 +2241,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark,
const xfrm_address_t *daddr, const xfrm_address_t *saddr,
u8 proto, unsigned short family)
{
+ struct xfrm_hash_state_ptrs state_ptrs;
struct xfrm_state *x;
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family);
+
+ xfrm_hash_ptrs_get(net, &state_ptrs);
+
+ x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
return x;
}
