1 files changed, 80 insertions, 45 deletions

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index a30f898dc1c5..419bf5d463bd 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -28,6 +28,11 @@
 
 #include "xfrm_hash.h"
 
+#define xfrm_state_deref_prot(table, net) \
+	rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock))
+
+static void xfrm_state_gc_task(struct work_struct *work);
+
 /* Each xfrm_state may be linked to two tables:
 
    1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl)
@@ -36,6 +41,15 @@
  */
 
 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 DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
+static HLIST_HEAD(xfrm_state_gc_list);
+
+static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
+{
+	return atomic_inc_not_zero(&x->refcnt);
+}
 
 static inline unsigned int xfrm_dst_hash(struct net *net,
 					 const xfrm_address_t *daddr,
@@ -76,18 +90,18 @@ static void xfrm_hash_transfer(struct hlist_head *list,
 		h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr,
 				    x->props.reqid, x->props.family,
 				    nhashmask);
-		hlist_add_head(&x->bydst, ndsttable+h);
+		hlist_add_head_rcu(&x->bydst, ndsttable + h);
 
 		h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr,
 				    x->props.family,
 				    nhashmask);
-		hlist_add_head(&x->bysrc, nsrctable+h);
+		hlist_add_head_rcu(&x->bysrc, nsrctable + h);
 
 		if (x->id.spi) {
 			h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
 					    x->id.proto, x->props.family,
 					    nhashmask);
-			hlist_add_head(&x->byspi, nspitable+h);
+			hlist_add_head_rcu(&x->byspi, nspitable + h);
 		}
 	}
 }
@@ -122,25 +136,29 @@ 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;
+	odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
 	for (i = net->xfrm.state_hmask; i >= 0; i--)
-		xfrm_hash_transfer(net->xfrm.state_bydst+i, ndst, nsrc, nspi,
-				   nhashmask);
+		xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nhashmask);
 
-	odst = net->xfrm.state_bydst;
-	osrc = net->xfrm.state_bysrc;
-	ospi = net->xfrm.state_byspi;
+	osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net);
+	ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net);
 	ohashmask = net->xfrm.state_hmask;
 
-	net->xfrm.state_bydst = ndst;
-	net->xfrm.state_bysrc = nsrc;
-	net->xfrm.state_byspi = nspi;
+	rcu_assign_pointer(net->xfrm.state_bydst, ndst);
+	rcu_assign_pointer(net->xfrm.state_bysrc, nsrc);
+	rcu_assign_pointer(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);
+
+	synchronize_rcu();
+
 	xfrm_hash_free(odst, osize);
 	xfrm_hash_free(osrc, osize);
 	xfrm_hash_free(ospi, osize);
@@ -356,15 +374,16 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x)
 
 static void xfrm_state_gc_task(struct work_struct *work)
 {
-	struct net *net = container_of(work, struct net, xfrm.state_gc_work);
 	struct xfrm_state *x;
 	struct hlist_node *tmp;
 	struct hlist_head gc_list;
 
 	spin_lock_bh(&xfrm_state_gc_lock);
-	hlist_move_list(&net->xfrm.state_gc_list, &gc_list);
+	hlist_move_list(&xfrm_state_gc_list, &gc_list);
 	spin_unlock_bh(&xfrm_state_gc_lock);
 
+	synchronize_rcu();
+
 	hlist_for_each_entry_safe(x, tmp, &gc_list, gclist)
 		xfrm_state_gc_destroy(x);
 }
@@ -501,14 +520,12 @@ EXPORT_SYMBOL(xfrm_state_alloc);
 
 void __xfrm_state_destroy(struct xfrm_state *x)
 {
-	struct net *net = xs_net(x);
-
 	WARN_ON(x->km.state != XFRM_STATE_DEAD);
 
 	spin_lock_bh(&xfrm_state_gc_lock);
-	hlist_add_head(&x->gclist, &net->xfrm.state_gc_list);
+	hlist_add_head(&x->gclist, &xfrm_state_gc_list);
 	spin_unlock_bh(&xfrm_state_gc_lock);
-	schedule_work(&net->xfrm.state_gc_work);
+	schedule_work(&xfrm_state_gc_work);
 }
 EXPORT_SYMBOL(__xfrm_state_destroy);
 
@@ -521,10 +538,10 @@ int __xfrm_state_delete(struct xfrm_state *x)
 		x->km.state = XFRM_STATE_DEAD;
 		spin_lock(&net->xfrm.xfrm_state_lock);
 		list_del(&x->km.all);
-		hlist_del(&x->bydst);
-		hlist_del(&x->bysrc);
+		hlist_del_rcu(&x->bydst);
+		hlist_del_rcu(&x->bysrc);
 		if (x->id.spi)
-			hlist_del(&x->byspi);
+			hlist_del_rcu(&x->byspi);
 		net->xfrm.state_num--;
 		spin_unlock(&net->xfrm.xfrm_state_lock);
 
@@ -660,7 +677,7 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
 	unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry(x, net->xfrm.state_byspi+h, byspi) {
+	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
 		if (x->props.family != family ||
 		    x->id.spi       != spi ||
 		    x->id.proto     != proto ||
@@ -669,7 +686,8 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
 
 		if ((mark & x->mark.m) != x->mark.v)
 			continue;
-		xfrm_state_hold(x);
+		if (!xfrm_state_hold_rcu(x))
+			continue;
 		return x;
 	}
 
@@ -684,7 +702,7 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 	unsigned int h = xfrm_src_hash(net, daddr, saddr, family);
 	struct xfrm_state *x;
 
-	hlist_for_each_entry(x, net->xfrm.state_bysrc+h, bysrc) {
+	hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) {
 		if (x->props.family != family ||
 		    x->id.proto     != proto ||
 		    !xfrm_addr_equal(&x->id.daddr, daddr, family) ||
@@ -693,7 +711,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark,
 
 		if ((mark & x->mark.m) != x->mark.v)
 			continue;
-		xfrm_state_hold(x);
+		if (!xfrm_state_hold_rcu(x))
+			continue;
 		return x;
 	}
 
@@ -776,13 +795,16 @@ 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;
 
-	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	sequence = read_seqcount_begin(&xfrm_state_hash_generation);
+
+	rcu_read_lock();
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
-	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
+	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -798,7 +820,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		goto found;
 
 	h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family);
-	hlist_for_each_entry(x, net->xfrm.state_bydst+h_wildcard, bydst) {
+	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) {
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -851,19 +873,21 @@ found:
 		}
 
 		if (km_query(x, tmpl, pol) == 0) {
+			spin_lock_bh(&net->xfrm.xfrm_state_lock);
 			x->km.state = XFRM_STATE_ACQ;
 			list_add(&x->km.all, &net->xfrm.state_all);
-			hlist_add_head(&x->bydst, net->xfrm.state_bydst+h);
+			hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
 			h = xfrm_src_hash(net, daddr, saddr, encap_family);
-			hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
+			hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
 			if (x->id.spi) {
 				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
-				hlist_add_head(&x->byspi, net->xfrm.state_byspi+h);
+				hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
 			tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
 			net->xfrm.state_num++;
 			xfrm_hash_grow_check(net, x->bydst.next != NULL);
+			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 		} else {
 			x->km.state = XFRM_STATE_DEAD;
 			to_put = x;
@@ -872,13 +896,26 @@ found:
 		}
 	}
 out:
-	if (x)
-		xfrm_state_hold(x);
-	else
+	if (x) {
+		if (!xfrm_state_hold_rcu(x)) {
+			*err = -EAGAIN;
+			x = NULL;
+		}
+	} else {
 		*err = acquire_in_progress ? -EAGAIN : error;
-	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	}
+	rcu_read_unlock();
 	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;
 }
 
@@ -946,16 +983,16 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 
 	h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr,
 			  x->props.reqid, x->props.family);
-	hlist_add_head(&x->bydst, net->xfrm.state_bydst+h);
+	hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
 
 	h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family);
-	hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
+	hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
 
 	if (x->id.spi) {
 		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);
+		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 	}
 
 	tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
@@ -1064,9 +1101,9 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 		xfrm_state_hold(x);
 		tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
 		list_add(&x->km.all, &net->xfrm.state_all);
-		hlist_add_head(&x->bydst, net->xfrm.state_bydst+h);
+		hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
 		h = xfrm_src_hash(net, daddr, saddr, family);
-		hlist_add_head(&x->bysrc, net->xfrm.state_bysrc+h);
+		hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
 
 		net->xfrm.state_num++;
 
@@ -1395,9 +1432,9 @@ xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32
 {
 	struct xfrm_state *x;
 
-	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	rcu_read_lock();
 	x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family);
-	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+	rcu_read_unlock();
 	return x;
 }
 EXPORT_SYMBOL(xfrm_state_lookup);
@@ -1582,7 +1619,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 	if (x->id.spi) {
 		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);
+		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 		err = 0;
@@ -2100,8 +2137,6 @@ int __net_init xfrm_state_init(struct net *net)
 
 	net->xfrm.state_num = 0;
 	INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
-	INIT_HLIST_HEAD(&net->xfrm.state_gc_list);
-	INIT_WORK(&net->xfrm.state_gc_work, xfrm_state_gc_task);
 	spin_lock_init(&net->xfrm.xfrm_state_lock);
 	return 0;
 
@@ -2119,7 +2154,7 @@ void xfrm_state_fini(struct net *net)
 
 	flush_work(&net->xfrm.state_hash_work);
 	xfrm_state_flush(net, IPSEC_PROTO_ANY, false);
-	flush_work(&net->xfrm.state_gc_work);
+	flush_work(&xfrm_state_gc_work);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));