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/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/networking/xfrm_device.rst

@@ -5,6 +5,7 @@ XFRM device - offloading the IPsec computations
 ===============================================
 
 Shannon Nelson <[email protected]>
+Leon Romanovsky <[email protected]>
 
 
 Overview
@@ -18,17 +19,39 @@ can radically increase throughput and decrease CPU utilization.  The XFRM
 Device interface allows NIC drivers to offer to the stack access to the
 hardware offload.
 
+Right now, there are two types of hardware offload that kernel supports.
+ * IPsec crypto offload:
+   * NIC performs encrypt/decrypt
+   * Kernel does everything else
+ * IPsec packet offload:
+   * NIC performs encrypt/decrypt
+   * NIC does encapsulation
+   * Kernel and NIC have SA and policy in-sync
+   * NIC handles the SA and policies states
+   * The Kernel talks to the keymanager
+
 Userland access to the offload is typically through a system such as
 libreswan or KAME/raccoon, but the iproute2 'ip xfrm' command set can
 be handy when experimenting.  An example command might look something
-like this::
+like this for crypto offload:
 
   ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \
      reqid 0x07 replay-window 32 \
      aead 'rfc4106(gcm(aes))' 0x44434241343332312423222114131211f4f3f2f1 128 \
      sel src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp \
      offload dev eth4 dir in
 
+and for packet offload
+
+  ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \
+     reqid 0x07 replay-window 32 \
+     aead 'rfc4106(gcm(aes))' 0x44434241343332312423222114131211f4f3f2f1 128 \
+     sel src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp \
+     offload packet dev eth4 dir in
+
+  ip x p add src 14.0.0.70 dst 14.0.0.52 offload packet dev eth4 dir in
+  tmpl src 14.0.0.70 dst 14.0.0.52 proto esp reqid 10000 mode transport
+
 Yes, that's ugly, but that's what shell scripts and/or libreswan are for.
 
 
@@ -40,17 +63,24 @@ Callbacks to implement
 
   /* from include/linux/netdevice.h */
   struct xfrmdev_ops {
+        /* Crypto and Packet offload callbacks */
 	int	(*xdo_dev_state_add) (struct xfrm_state *x);
 	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
 	void	(*xdo_dev_state_free) (struct xfrm_state *x);
 	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
 				       struct xfrm_state *x);
 	void    (*xdo_dev_state_advance_esn) (struct xfrm_state *x);
+
+        /* Solely packet offload callbacks */
+	void    (*xdo_dev_state_update_curlft) (struct xfrm_state *x);
+	int	(*xdo_dev_policy_add) (struct xfrm_policy *x);
+	void	(*xdo_dev_policy_delete) (struct xfrm_policy *x);
+	void	(*xdo_dev_policy_free) (struct xfrm_policy *x);
   };
 
-The NIC driver offering ipsec offload will need to implement these
-callbacks to make the offload available to the network stack's
-XFRM subsystem.  Additionally, the feature bits NETIF_F_HW_ESP and
+The NIC driver offering ipsec offload will need to implement callbacks
+relevant to supported offload to make the offload available to the network
+stack's XFRM subsystem. Additionally, the feature bits NETIF_F_HW_ESP and
 NETIF_F_HW_ESP_TX_CSUM will signal the availability of the offload.
 
 
@@ -79,7 +109,8 @@ and an indication of whether it is for Rx or Tx.  The driver should
 
 		===========   ===================================
 		0             success
-		-EOPNETSUPP   offload not supported, try SW IPsec
+		-EOPNETSUPP   offload not supported, try SW IPsec,
+                              not applicable for packet offload mode
 		other         fail the request
 		===========   ===================================
 
@@ -96,6 +127,7 @@ will serviceable.  This can check the packet information to be sure the
 offload can be supported (e.g. IPv4 or IPv6, no IPv4 options, etc) and
 return true of false to signify its support.
 
+Crypto offload mode:
 When ready to send, the driver needs to inspect the Tx packet for the
 offload information, including the opaque context, and set up the packet
 send accordingly::
@@ -139,13 +171,25 @@ the stack in xfrm_input().
 In ESN mode, xdo_dev_state_advance_esn() is called from xfrm_replay_advance_esn().
 Driver will check packet seq number and update HW ESN state machine if needed.
 
+Packet offload mode:
+HW adds and deletes XFRM headers. So in RX path, XFRM stack is bypassed if HW
+reported success. In TX path, the packet lefts kernel without extra header
+and not encrypted, the HW is responsible to perform it.
+
 When the SA is removed by the user, the driver's xdo_dev_state_delete()
-is asked to disable the offload.  Later, xdo_dev_state_free() is called
-from a garbage collection routine after all reference counts to the state
+and xdo_dev_policy_delete() are asked to disable the offload.  Later,
+xdo_dev_state_free() and xdo_dev_policy_free() are called from a garbage
+collection routine after all reference counts to the state and policy
 have been removed and any remaining resources can be cleared for the
 offload state.  How these are used by the driver will depend on specific
 hardware needs.
 
 As a netdev is set to DOWN the XFRM stack's netdev listener will call
-xdo_dev_state_delete() and xdo_dev_state_free() on any remaining offloaded
-states.
+xdo_dev_state_delete(), xdo_dev_policy_delete(), xdo_dev_state_free() and
+xdo_dev_policy_free() on any remaining offloaded states.
+
+Outcome of HW handling packets, the XFRM core can't count hard, soft limits.
+The HW/driver are responsible to perform it and provide accurate data when
+xdo_dev_state_update_curlft() is called. In case of one of these limits
+occuried, the driver needs to call to xfrm_state_check_expire() to make sure
+that XFRM performs rekeying sequence.

drivers/net/ethernet/chelsio/inline_crypto/ch_ipsec/chcr_ipsec.c

@@ -283,6 +283,10 @@ static int ch_ipsec_xfrm_add_state(struct xfrm_state *x)
 		pr_debug("Cannot offload xfrm states with geniv other than seqiv\n");
 		return -EINVAL;
 	}
+	if (x->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) {
+		pr_debug("Unsupported xfrm offload\n");
+		return -EINVAL;
+	}
 
 	sa_entry = kzalloc(sizeof(*sa_entry), GFP_KERNEL);
 	if (!sa_entry) {

drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c

@@ -585,6 +585,11 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
 		return -EINVAL;
 	}
 
+	if (xs->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) {
+		netdev_err(dev, "Unsupported ipsec offload type\n");
+		return -EINVAL;
+	}
+
 	if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) {
 		struct rx_sa rsa;
 

drivers/net/ethernet/intel/ixgbevf/ipsec.c

@@ -280,6 +280,11 @@ static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs)
 		return -EINVAL;
 	}
 
+	if (xs->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) {
+		netdev_err(dev, "Unsupported ipsec offload type\n");
+		return -EINVAL;
+	}
+
 	if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) {
 		struct rx_sa rsa;
 

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -1245,4 +1245,5 @@ int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_t
 int mlx5e_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi);
 int mlx5e_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats);
 #endif
+int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
 #endif /* __MLX5_EN_H__ */

drivers/net/ethernet/mellanox/mlx5/core/en/fs.h

@@ -84,7 +84,8 @@ enum {
 	MLX5E_ARFS_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 #endif
 #ifdef CONFIG_MLX5_EN_IPSEC
-	MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
+	MLX5E_ACCEL_FS_POL_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
+	MLX5E_ACCEL_FS_ESP_FT_LEVEL,
 	MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
 #endif
 };

drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c

@@ -162,7 +162,6 @@ mlx5e_tc_meter_modify(struct mlx5_core_dev *mdev,
 			   MLX5_ACCESS_ASO_OPC_MOD_FLOW_METER);
 
 	aso_ctrl = &aso_wqe->aso_ctrl;
-	memset(aso_ctrl, 0, sizeof(*aso_ctrl));
 	aso_ctrl->data_mask_mode = MLX5_ASO_DATA_MASK_MODE_BYTEWISE_64BYTE << 6;
 	aso_ctrl->condition_1_0_operand = MLX5_ASO_ALWAYS_TRUE |
 					  MLX5_ASO_ALWAYS_TRUE << 4;