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>

1 files changed, 173 insertions, 18 deletions

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;