Re: [PATCH xfrm-next v7 6/8] xfrm: speed-up lookup of HW policies

[Leon Romanovsky <leon@kernel.org>]

On Wed, Nov 23, 2022 at 11:36:19AM +0200, Leon Romanovsky wrote:
> On Wed, Nov 23, 2022 at 09:37:20AM +0100, Steffen Klassert wrote:
> > On Tue, Nov 22, 2022 at 03:57:43PM +0200, Leon Romanovsky wrote:
> > > On Tue, Nov 22, 2022 at 02:10:02PM +0100, Steffen Klassert wrote:
> > > > On Mon, Nov 21, 2022 at 03:01:42PM +0200, Leon Romanovsky wrote:
> > > > > On Mon, Nov 21, 2022 at 01:43:49PM +0100, Steffen Klassert wrote:
> > > > > > On Mon, Nov 21, 2022 at 02:02:52PM +0200, Leon Romanovsky wrote:
> > > > > > 
> > > > > > If policy and state do not match here, this means the lookup
> > > > > > returned the wrong state. The correct state might still sit
> > > > > > in the database. At this point, you should either have found
> > > > > > a matching state, or no state at all.
> > > > > 
> > > > > I check for "x" because of "x = NULL" above.
> > > > 
> > > > This does not change the fact that the lookup returned the wrong state.
> > > 
> > > Steffen, but this is exactly why we added this check - to catch wrong
> > > states and configurations. 
> > 
> > No, you have to adjust the lookup so that this can't happen.
> > This is not a missconfiguration, The lookup found the wrong
> > SA, this is a difference.
> > 
> > Use the offload type and dev as a lookup key and don't consider
> > SAs that don't match this in the lookup.
> > 
> > This is really not too hard to do. The thing that could be a bit
> > more difficult is that the lookup should be only adjusted when
> > we really have HW policies installed. Otherwise this affects
> > even systems that don't use this kind of offload.
> 
> Thanks for an explanation, trying it now.

Something like that?

The code is untested yet.

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 5076f9d7a752..5819023c32ba 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1115,6 +1115,19 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	rcu_read_lock();
 	h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
 	hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) {
+		if (IS_ENABLED(CONFIG_XFRM_OFFLOAD) &&
+		    pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				/* HW states are in the head of list, there is no need
+				 * to iterate further.
+				 */
+				break;
+
+			/* Packet offload: both policy and SA should have same device */
+			if (pol->xdo.dev != x->xso.dev)
+				continue;
+		}
+
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -1132,6 +1145,19 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 
 	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) {
+		if (IS_ENABLED(CONFIG_XFRM_OFFLOAD) &&
+		    pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+				/* HW states are in the head of list, there is no need
+				 * to iterate further.
+				 */
+				break;
+
+			/* Packet offload: both policy and SA should have same device */
+			if (pol->xdo.dev != x->xso.dev)
+				continue;
+		}
+
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -1185,6 +1211,17 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 			goto out;
 		}
 
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			memcpy(&x->xso, &pol->xdo, sizeof(x->xso));
+			error = pol->xdo.dev->xfrmdev_ops->xdo_dev_state_add(x);
+			if (error) {
+				x->km.state = XFRM_STATE_DEAD;
+				to_put = x;
+				x = NULL;
+				goto out;
+			}
+		}
+
 		if (km_query(x, tmpl, pol) == 0) {
 			spin_lock_bh(&net->xfrm.xfrm_state_lock);
 			x->km.state = XFRM_STATE_ACQ;