Merge tag 'ipsec-next-2022-12-09' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next

Steffen Klassert says:

====================
ipsec-next 2022-12-09

1) Add xfrm packet offload core API.
   From Leon Romanovsky.

2) Add xfrm packet offload support for mlx5.
   From Leon Romanovsky and Raed Salem.

3) Fix a typto in a error message.
   From Colin Ian King.

* tag 'ipsec-next-2022-12-09' of git://git.kernel.org/pub/scm/linux/kernel/git/klassert/ipsec-next: (38 commits)
  xfrm: Fix spelling mistake "oflload" -> "offload"
  net/mlx5e: Open mlx5 driver to accept IPsec packet offload
  net/mlx5e: Handle ESN update events
  net/mlx5e: Handle hardware IPsec limits events
  net/mlx5e: Update IPsec soft and hard limits
  net/mlx5e: Store all XFRM SAs in Xarray
  net/mlx5e: Provide intermediate pointer to access IPsec struct
  net/mlx5e: Skip IPsec encryption for TX path without matching policy
  net/mlx5e: Add statistics for Rx/Tx IPsec offloaded flows
  net/mlx5e: Improve IPsec flow steering autogroup
  net/mlx5e: Configure IPsec packet offload flow steering
  net/mlx5e: Use same coding pattern for Rx and Tx flows
  net/mlx5e: Add XFRM policy offload logic
  net/mlx5e: Create IPsec policy offload tables
  net/mlx5e: Generalize creation of default IPsec miss group and rule
  net/mlx5e: Group IPsec miss handles into separate struct
  net/mlx5e: Make clear what IPsec rx_err does
  net/mlx5e: Flatten the IPsec RX add rule path
  net/mlx5e: Refactor FTE setup code to be more clear
  net/mlx5e: Move IPsec flow table creation to separate function
  ...
====================

Link: https://lore.kernel.org/r/20221209093310.4018731-1-steffen.klassert@secunet.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

5 files changed, 385 insertions, 32 deletions

diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 21269e8f2db4..4aff76c6f12e 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -132,6 +132,16 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 	if (xo->flags & XFRM_GRO || x->xso.dir == XFRM_DEV_OFFLOAD_IN)
 		return skb;
 
+	/* The packet was sent to HW IPsec packet offload engine,
+	 * but to wrong device. Drop the packet, so it won't skip
+	 * XFRM stack.
+	 */
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET && x->xso.dev != dev) {
+		kfree_skb(skb);
+		dev_core_stats_tx_dropped_inc(dev);
+		return NULL;
+	}
+
 	/* This skb was already validated on the upper/virtual dev */
 	if ((x->xso.dev != dev) && (x->xso.real_dev == dev))
 		return skb;
@@ -229,6 +239,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	struct xfrm_dev_offload *xso = &x->xso;
 	xfrm_address_t *saddr;
 	xfrm_address_t *daddr;
+	bool is_packet_offload;
 
 	if (!x->type_offload) {
 		NL_SET_ERR_MSG(extack, "Type doesn't support offload");
@@ -241,11 +252,13 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		return -EINVAL;
 	}
 
-	if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND)) {
+	if (xuo->flags &
+	    ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND | XFRM_OFFLOAD_PACKET)) {
 		NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request");
 		return -EINVAL;
 	}
 
+	is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET;
 	dev = dev_get_by_index(net, xuo->ifindex);
 	if (!dev) {
 		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
@@ -260,7 +273,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 					x->props.family,
 					xfrm_smark_get(0, x));
 		if (IS_ERR(dst))
-			return 0;
+			return (is_packet_offload) ? -EINVAL : 0;
 
 		dev = dst->dev;
 
@@ -271,7 +284,7 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) {
 		xso->dev = NULL;
 		dev_put(dev);
-		return 0;
+		return (is_packet_offload) ? -EINVAL : 0;
 	}
 
 	if (x->props.flags & XFRM_STATE_ESN &&
@@ -291,14 +304,28 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 	else
 		xso->dir = XFRM_DEV_OFFLOAD_OUT;
 
+	if (is_packet_offload)
+		xso->type = XFRM_DEV_OFFLOAD_PACKET;
+	else
+		xso->type = XFRM_DEV_OFFLOAD_CRYPTO;
+
 	err = dev->xfrmdev_ops->xdo_dev_state_add(x);
 	if (err) {
 		xso->dev = NULL;
 		xso->dir = 0;
 		xso->real_dev = NULL;
 		netdev_put(dev, &xso->dev_tracker);
-
-		if (err != -EOPNOTSUPP) {
+		xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+
+		/* User explicitly requested packet offload mode and configured
+		 * policy in addition to the XFRM state. So be civil to users,
+		 * and return an error instead of taking fallback path.
+		 *
+		 * This WARN_ON() can be seen as a documentation for driver
+		 * authors to do not return -EOPNOTSUPP in packet offload mode.
+		 */
+		WARN_ON(err == -EOPNOTSUPP && is_packet_offload);
+		if (err != -EOPNOTSUPP || is_packet_offload) {
 			NL_SET_ERR_MSG(extack, "Device failed to offload this state");
 			return err;
 		}
@@ -308,6 +335,69 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 }
 EXPORT_SYMBOL_GPL(xfrm_dev_state_add);
 
+int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
+			struct xfrm_user_offload *xuo, u8 dir,
+			struct netlink_ext_ack *extack)
+{
+	struct xfrm_dev_offload *xdo = &xp->xdo;
+	struct net_device *dev;
+	int err;
+
+	if (!xuo->flags || xuo->flags & ~XFRM_OFFLOAD_PACKET) {
+		/* We support only packet offload mode and it means
+		 * that user must set XFRM_OFFLOAD_PACKET bit.
+		 */
+		NL_SET_ERR_MSG(extack, "Unrecognized flags in offload request");
+		return -EINVAL;
+	}
+
+	dev = dev_get_by_index(net, xuo->ifindex);
+	if (!dev)
+		return -EINVAL;
+
+	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_policy_add) {
+		xdo->dev = NULL;
+		dev_put(dev);
+		NL_SET_ERR_MSG(extack, "Policy offload is not supported");
+		return -EINVAL;
+	}
+
+	xdo->dev = dev;
+	netdev_tracker_alloc(dev, &xdo->dev_tracker, GFP_ATOMIC);
+	xdo->real_dev = dev;
+	xdo->type = XFRM_DEV_OFFLOAD_PACKET;
+	switch (dir) {
+	case XFRM_POLICY_IN:
+		xdo->dir = XFRM_DEV_OFFLOAD_IN;
+		break;
+	case XFRM_POLICY_OUT:
+		xdo->dir = XFRM_DEV_OFFLOAD_OUT;
+		break;
+	case XFRM_POLICY_FWD:
+		xdo->dir = XFRM_DEV_OFFLOAD_FWD;
+		break;
+	default:
+		xdo->dev = NULL;
+		dev_put(dev);
+		NL_SET_ERR_MSG(extack, "Unrecognized offload direction");
+		return -EINVAL;
+	}
+
+	err = dev->xfrmdev_ops->xdo_dev_policy_add(xp);
+	if (err) {
+		xdo->dev = NULL;
+		xdo->real_dev = NULL;
+		xdo->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+		xdo->dir = 0;
+		netdev_put(dev, &xdo->dev_tracker);
+		NL_SET_ERR_MSG(extack, "Device failed to offload this policy");
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xfrm_dev_policy_add);
+
 bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 {
 	int mtu;
@@ -318,8 +408,9 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 	if (!x->type_offload || x->encap)
 		return false;
 
-	if ((!dev || (dev == xfrm_dst_path(dst)->dev)) &&
-	    (!xdst->child->xfrm)) {
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET ||
+	    ((!dev || (dev == xfrm_dst_path(dst)->dev)) &&
+	     !xdst->child->xfrm)) {
 		mtu = xfrm_state_mtu(x, xdst->child_mtu_cached);
 		if (skb->len <= mtu)
 			goto ok;
@@ -410,8 +501,10 @@ static int xfrm_api_check(struct net_device *dev)
 
 static int xfrm_dev_down(struct net_device *dev)
 {
-	if (dev->features & NETIF_F_HW_ESP)
+	if (dev->features & NETIF_F_HW_ESP) {
 		xfrm_dev_state_flush(dev_net(dev), dev, true);
+		xfrm_dev_policy_flush(dev_net(dev), dev, true);
+	}
 
 	return NOTIFY_DONE;
 }
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 78cb8d0a6a18..ff114d68cc43 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -492,7 +492,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 	struct xfrm_state *x = dst->xfrm;
 	struct net *net = xs_net(x);
 
-	if (err <= 0)
+	if (err <= 0 || x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
 		goto resume;
 
 	do {
@@ -717,6 +717,16 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		break;
 	}
 
+	if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
+		if (!xfrm_dev_offload_ok(skb, x)) {
+			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+			kfree_skb(skb);
+			return -EHOSTUNREACH;
+		}
+
+		return xfrm_output_resume(sk, skb, 0);
+	}
+
 	secpath_reset(skb);
 
 	if (xfrm_dev_offload_ok(skb, x)) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 9b9e2765363d..e9eb82c5457d 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -425,6 +425,7 @@ void xfrm_policy_destroy(struct xfrm_policy *policy)
 	if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer))
 		BUG();
 
+	xfrm_dev_policy_free(policy);
 	call_rcu(&policy->rcu, xfrm_policy_destroy_rcu);
 }
 EXPORT_SYMBOL(xfrm_policy_destroy);
@@ -535,7 +536,7 @@ redo:
 		__get_hash_thresh(net, pol->family, dir, &dbits, &sbits);
 		h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr,
 				pol->family, nhashmask, dbits, sbits);
-		if (!entry0) {
+		if (!entry0 || pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
 			hlist_del_rcu(&pol->bydst);
 			hlist_add_head_rcu(&pol->bydst, ndsttable + h);
 			h0 = h;
@@ -866,7 +867,7 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
 				break;
 		}
 
-		if (newpos)
+		if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
 			hlist_add_behind_rcu(&policy->bydst, newpos);
 		else
 			hlist_add_head_rcu(&policy->bydst, &n->hhead);
@@ -1347,7 +1348,7 @@ static void xfrm_hash_rebuild(struct work_struct *work)
 			else
 				break;
 		}
-		if (newpos)
+		if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
 			hlist_add_behind_rcu(&policy->bydst, newpos);
 		else
 			hlist_add_head_rcu(&policy->bydst, chain);
@@ -1524,7 +1525,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain,
 			break;
 	}
 
-	if (newpos)
+	if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
 		hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos);
 	else
 		hlist_add_head_rcu(&policy->bydst_inexact_list, chain);
@@ -1561,9 +1562,12 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain,
 			break;
 	}
 
-	if (newpos)
+	if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET)
 		hlist_add_behind_rcu(&policy->bydst, &newpos->bydst);
 	else
+		/* Packet offload policies enter to the head
+		 * to speed-up lookups.
+		 */
 		hlist_add_head_rcu(&policy->bydst, chain);
 
 	return delpol;
@@ -1769,12 +1773,41 @@ xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 	}
 	return err;
 }
+
+static inline int xfrm_dev_policy_flush_secctx_check(struct net *net,
+						     struct net_device *dev,
+						     bool task_valid)
+{
+	struct xfrm_policy *pol;
+	int err = 0;
+
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		if (pol->walk.dead ||
+		    xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX ||
+		    pol->xdo.dev != dev)
+			continue;
+
+		err = security_xfrm_policy_delete(pol->security);
+		if (err) {
+			xfrm_audit_policy_delete(pol, 0, task_valid);
+			return err;
+		}
+	}
+	return err;
+}
 #else
 static inline int
 xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid)
 {
 	return 0;
 }
+
+static inline int xfrm_dev_policy_flush_secctx_check(struct net *net,
+						     struct net_device *dev,
+						     bool task_valid)
+{
+	return 0;
+}
 #endif
 
 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
@@ -1814,6 +1847,44 @@ out:
 }
 EXPORT_SYMBOL(xfrm_policy_flush);
 
+int xfrm_dev_policy_flush(struct net *net, struct net_device *dev,
+			  bool task_valid)
+{
+	int dir, err = 0, cnt = 0;
+	struct xfrm_policy *pol;
+
+	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+
+	err = xfrm_dev_policy_flush_secctx_check(net, dev, task_valid);
+	if (err)
+		goto out;
+
+again:
+	list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+		dir = xfrm_policy_id2dir(pol->index);
+		if (pol->walk.dead ||
+		    dir >= XFRM_POLICY_MAX ||
+		    pol->xdo.dev != dev)
+			continue;
+
+		__xfrm_policy_unlink(pol, dir);
+		spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+		cnt++;
+		xfrm_audit_policy_delete(pol, 1, task_valid);
+		xfrm_policy_kill(pol);
+		spin_lock_bh(&net->xfrm.xfrm_policy_lock);
+		goto again;
+	}
+	if (cnt)
+		__xfrm_policy_inexact_flush(net);
+	else
+		err = -ESRCH;
+out:
+	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+	return err;
+}
+EXPORT_SYMBOL(xfrm_dev_policy_flush);
+
 int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 		     int (*func)(struct xfrm_policy *, int, int, void*),
 		     void *data)
@@ -2113,6 +2184,9 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 			break;
 		}
 	}
+	if (ret && ret->xdo.type == XFRM_DEV_OFFLOAD_PACKET)
+		goto skip_inexact;
+
 	bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id);
 	if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr,
 							 daddr))
@@ -2245,6 +2319,7 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
 	pol = __xfrm_policy_unlink(pol, dir);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 	if (pol) {
+		xfrm_dev_policy_delete(pol);
 		xfrm_policy_kill(pol);
 		return 0;
 	}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 9ec481fbfb63..cc1d0ea42672 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -84,6 +84,25 @@ static unsigned int xfrm_seq_hash(struct net *net, u32 seq)
 	return __xfrm_seq_hash(seq, net->xfrm.state_hmask);
 }
 
+#define XFRM_STATE_INSERT(by, _n, _h, _type)                               \
+	{                                                                  \
+		struct xfrm_state *_x = NULL;                              \
+									   \
+		if (_type != XFRM_DEV_OFFLOAD_PACKET) {                    \
+			hlist_for_each_entry_rcu(_x, _h, by) {             \
+				if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \
+					continue;                          \
+				break;                                     \
+			}                                                  \
+		}                                                          \
+									   \
+		if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET)        \
+			/* SAD is empty or consist from HW SAs only */     \
+			hlist_add_head_rcu(_n, _h);                        \
+		else                                                       \
+			hlist_add_before_rcu(_n, &_x->by);                 \
+	}
+
 static void xfrm_hash_transfer(struct hlist_head *list,
 			       struct hlist_head *ndsttable,
 			       struct hlist_head *nsrctable,
@@ -100,23 +119,25 @@ 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_rcu(&x->bydst, ndsttable + h);
+		XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type);
 
 		h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr,
 				    x->props.family,
 				    nhashmask);
-		hlist_add_head_rcu(&x->bysrc, nsrctable + h);
+		XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type);
 
 		if (x->id.spi) {
 			h = __xfrm_spi_hash(&x->id.daddr, x->id.spi,
 					    x->id.proto, x->props.family,
 					    nhashmask);
-			hlist_add_head_rcu(&x->byspi, nspitable + h);
+			XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h,
+					  x->xso.type);
 		}
 
 		if (x->km.seq) {
 			h = __xfrm_seq_hash(x->km.seq, nhashmask);
-			hlist_add_head_rcu(&x->byseq, nseqtable + h);
+			XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h,
+					  x->xso.type);
 		}
 	}
 }
@@ -549,6 +570,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 	int err = 0;
 
 	spin_lock(&x->lock);
+	xfrm_dev_state_update_curlft(x);
+
 	if (x->km.state == XFRM_STATE_DEAD)
 		goto out;
 	if (x->km.state == XFRM_STATE_EXPIRED)
@@ -951,6 +974,49 @@ 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,
+						  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);
+	struct xfrm_state *x;
+
+	hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) {
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (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 (xdo->dev != x->xso.dev)
+				continue;
+		} else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+			/* Skip HW policy for SW lookups */
+			continue;
+#endif
+		if (x->props.family != family ||
+		    x->id.spi       != spi ||
+		    x->id.proto     != proto ||
+		    !xfrm_addr_equal(&x->id.daddr, daddr, family))
+			continue;
+
+		if ((mark & x->mark.m) != x->mark.v)
+			continue;
+		if (!xfrm_state_hold_rcu(x))
+			continue;
+		return x;
+	}
+
+	return NULL;
+}
+
 static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark,
 					      const xfrm_address_t *daddr,
 					      __be32 spi, u8 proto,
@@ -1092,6 +1158,23 @@ 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) {
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (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;
+		} else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+			/* Skip HW policy for SW lookups */
+			continue;
+#endif
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -1109,6 +1192,23 @@ 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) {
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (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;
+		} else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET)
+			/* Skip HW policy for SW lookups */
+			continue;
+#endif
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
@@ -1126,8 +1226,10 @@ found:
 	x = best;
 	if (!x && !error && !acquire_in_progress) {
 		if (tmpl->id.spi &&
-		    (x0 = __xfrm_state_lookup(net, mark, daddr, tmpl->id.spi,
-					      tmpl->id.proto, encap_family)) != NULL) {
+		    (x0 = __xfrm_state_lookup_all(net, mark, daddr,
+						  tmpl->id.spi, tmpl->id.proto,
+						  encap_family,
+						  &pol->xdo)) != NULL) {
 			to_put = x0;
 			error = -EEXIST;
 			goto out;
@@ -1161,21 +1263,53 @@ found:
 			x = NULL;
 			goto out;
 		}
-
+#ifdef CONFIG_XFRM_OFFLOAD
+		if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) {
+			struct xfrm_dev_offload *xdo = &pol->xdo;
+			struct xfrm_dev_offload *xso = &x->xso;
+
+			xso->type = XFRM_DEV_OFFLOAD_PACKET;
+			xso->dir = xdo->dir;
+			xso->dev = xdo->dev;
+			xso->real_dev = xdo->real_dev;
+			netdev_tracker_alloc(xso->dev, &xso->dev_tracker,
+					     GFP_ATOMIC);
+			error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x);
+			if (error) {
+				xso->dir = 0;
+				netdev_put(xso->dev, &xso->dev_tracker);
+				xso->dev = NULL;
+				xso->real_dev = NULL;
+				xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+				x->km.state = XFRM_STATE_DEAD;
+				to_put = x;
+				x = NULL;
+				goto out;
+			}
+		}
+#endif
 		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_rcu(&x->bydst, net->xfrm.state_bydst + h);
+			XFRM_STATE_INSERT(bydst, &x->bydst,
+					  net->xfrm.state_bydst + h,
+					  x->xso.type);
 			h = xfrm_src_hash(net, daddr, saddr, encap_family);
-			hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
+			XFRM_STATE_INSERT(bysrc, &x->bysrc,
+					  net->xfrm.state_bysrc + h,
+					  x->xso.type);
 			if (x->id.spi) {
 				h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family);
-				hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
+				XFRM_STATE_INSERT(byspi, &x->byspi,
+						  net->xfrm.state_byspi + h,
+						  x->xso.type);
 			}
 			if (x->km.seq) {
 				h = xfrm_seq_hash(net, x->km.seq);
-				hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h);
+				XFRM_STATE_INSERT(byseq, &x->byseq,
+						  net->xfrm.state_byseq + h,
+						  x->xso.type);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
 			hrtimer_start(&x->mtimer,
@@ -1185,6 +1319,18 @@ found:
 			xfrm_hash_grow_check(net, x->bydst.next != NULL);
 			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 		} else {
+#ifdef CONFIG_XFRM_OFFLOAD
+			struct xfrm_dev_offload *xso = &x->xso;
+
+			if (xso->type == XFRM_DEV_OFFLOAD_PACKET) {
+				xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
+				xso->dir = 0;
+				netdev_put(xso->dev, &xso->dev_tracker);
+				xso->dev = NULL;
+				xso->real_dev = NULL;
+				xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+			}
+#endif
 			x->km.state = XFRM_STATE_DEAD;
 			to_put = x;
 			x = NULL;
@@ -1280,22 +1426,26 @@ 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_rcu(&x->bydst, net->xfrm.state_bydst + h);
+	XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+			  x->xso.type);
 
 	h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family);
-	hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
+	XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+			  x->xso.type);
 
 	if (x->id.spi) {
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto,
 				  x->props.family);
 
-		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
+		XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
+				  x->xso.type);
 	}
 
 	if (x->km.seq) {
 		h = xfrm_seq_hash(net, x->km.seq);
 
-		hlist_add_head_rcu(&x->byseq, net->xfrm.state_byseq + h);
+		XFRM_STATE_INSERT(byseq, &x->byseq, net->xfrm.state_byseq + h,
+				  x->xso.type);
 	}
 
 	hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
@@ -1409,9 +1559,11 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 			      ktime_set(net->xfrm.sysctl_acq_expires, 0),
 			      HRTIMER_MODE_REL_SOFT);
 		list_add(&x->km.all, &net->xfrm.state_all);
-		hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
+		XFRM_STATE_INSERT(bydst, &x->bydst, net->xfrm.state_bydst + h,
+				  x->xso.type);
 		h = xfrm_src_hash(net, daddr, saddr, family);
-		hlist_add_head_rcu(&x->bysrc, net->xfrm.state_bysrc + h);
+		XFRM_STATE_INSERT(bysrc, &x->bysrc, net->xfrm.state_bysrc + h,
+				  x->xso.type);
 
 		net->xfrm.state_num++;
 
@@ -1786,6 +1938,8 @@ EXPORT_SYMBOL(xfrm_state_update);
 
 int xfrm_state_check_expire(struct xfrm_state *x)
 {
+	xfrm_dev_state_update_curlft(x);
+
 	if (!x->curlft.use_time)
 		x->curlft.use_time = ktime_get_real_seconds();
 
@@ -2094,7 +2248,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high,
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
 		x->id.spi = newspi;
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
-		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
+		XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h,
+				  x->xso.type);
 		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 		err = 0;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 0eb4696661c8..cf5172d4ce68 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -956,6 +956,8 @@ static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb)
 	xuo->ifindex = xso->dev->ifindex;
 	if (xso->dir == XFRM_DEV_OFFLOAD_IN)
 		xuo->flags = XFRM_OFFLOAD_INBOUND;
+	if (xso->type == XFRM_DEV_OFFLOAD_PACKET)
+		xuo->flags |= XFRM_OFFLOAD_PACKET;
 
 	return 0;
 }
@@ -1890,6 +1892,15 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net,
 	if (attrs[XFRMA_IF_ID])
 		xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
 
+	/* configure the hardware if offload is requested */
+	if (attrs[XFRMA_OFFLOAD_DEV]) {
+		err = xfrm_dev_policy_add(net, xp,
+					  nla_data(attrs[XFRMA_OFFLOAD_DEV]),
+					  p->dir, extack);
+		if (err)
+			goto error;
+	}
+
 	return xp;
  error:
 	*errp = err;
@@ -1929,6 +1940,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	xfrm_audit_policy_add(xp, err ? 0 : 1, true);
 
 	if (err) {
+		xfrm_dev_policy_delete(xp);
 		security_xfrm_policy_free(xp->security);
 		kfree(xp);
 		return err;
@@ -2041,6 +2053,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 		err = xfrm_mark_put(skb, &xp->mark);
 	if (!err)
 		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -3379,6 +3393,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
 		err = xfrm_mark_put(skb, &xp->mark);
 	if (!err)
 		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -3497,6 +3513,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
 		err = xfrm_mark_put(skb, &xp->mark);
 	if (!err)
 		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -3580,6 +3598,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e
 		err = xfrm_mark_put(skb, &xp->mark);
 	if (!err)
 		err = xfrm_if_id_put(skb, xp->if_id);
+	if (!err && xp->xdo.dev)
+		err = copy_user_offload(&xp->xdo, skb);
 	if (err)
 		goto out_free_skb;