[PATCH net V3 7/8] net/mlx5e: Block E-Switch mode changes during IPsec state creation

[Tariq Toukan <tariqt@nvidia.com>]

From: Cosmin Ratiu <cratiu@nvidia.com>

mlx5e_xfrm_add_state() reads priv->ipsec before blocking eswitch mode
changes. A concurrent profile change can free the saved IPsec context
and cause use-after-free.

The temporary mode reservation was added in commit 22239eb258bc
("net/mlx5e: Prevent tunnel reformat when tunnel mode not allowed")
after saving priv->ipsec but the race was actually enabled by the
"Fixes" commit.
Extend the reservation to cover obtaining the context as well.

Use mlx5_eswitch_block_mode(mdev, false) for the temporary reservation,
as policy creation does, to check operation ownership under mode_lock
without rejecting existing eswitch users. This allows reusing existing
IPsec tables while TC rules exist on VF representors.

Check the context only after taking the mode reservation, so a
concurrent mode change consistently returns -EBUSY and a missing context
returns -EOPNOTSUPP, preserving software fallback for crypto offload.
Keep the atomic acquire-placeholder path exempt, since it creates no
hardware state and cannot take sleeping locks.

This was found by Sashiko, during review of the last patch in the
series. No reproduction attempted, as it seems quite a tricky race to
successfully trigger.

Fixes: 7a9fb35e8c3a ("net/mlx5e: Do not reload ethernet ports when changing eswitch mode")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 37 ++++++++++++-------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 3cd0b36a02e7..fa6cb51fdb93 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -771,6 +771,7 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 				struct xfrm_state *x,
 				struct netlink_ext_ack *extack)
 {
+	bool is_acq = x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ;
 	struct mlx5e_ipsec_sa_entry *sa_entry = NULL;
 	bool allow_tunnel_mode = false;
 	struct mlx5_core_dev *mdev;
@@ -787,20 +788,31 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 		NL_SET_ERR_MSG_MOD(extack, "Eswitch busy, can't add state");
 		return -EBUSY;
 	}
-	if (!priv->ipsec)
-		return -EOPNOTSUPP;
+
+	if (!is_acq) {
+		err = mlx5_eswitch_block_mode(mdev, false);
+		if (err)
+			return err;
+	}
 
 	ipsec = priv->ipsec;
-	gfp = (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) ? GFP_ATOMIC : GFP_KERNEL;
+	if (!ipsec) {
+		err = -EOPNOTSUPP;
+		goto unblock_mode;
+	}
+
+	gfp = is_acq ? GFP_ATOMIC : GFP_KERNEL;
 	sa_entry = kzalloc_obj(*sa_entry, gfp);
-	if (!sa_entry)
-		return -ENOMEM;
+	if (!sa_entry) {
+		err = -ENOMEM;
+		goto unblock_mode;
+	}
 
 	sa_entry->x = x;
 	sa_entry->dev = dev;
 	sa_entry->ipsec = ipsec;
 	/* Check if this SA is originated from acquire flow temporary SA */
-	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) {
+	if (is_acq) {
 		x->xso.offload_handle = (unsigned long)sa_entry;
 		return 0;
 	}
@@ -814,21 +826,17 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 		goto err_xfrm;
 	}
 
-	err = mlx5_eswitch_block_mode(mdev, true);
-	if (err)
-		goto unblock_ipsec;
-
 	if (x->props.mode == XFRM_MODE_TUNNEL &&
 	    x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
 		err = mlx5e_ipsec_fs_tunnel_allowed(sa_entry);
 		if (err < 0)
-			goto unblock_mode;
+			goto unblock_ipsec;
 		allow_tunnel_mode = err;
 		if (!allow_tunnel_mode) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Packet offload tunnel mode is disabled due to encap settings");
 			err = -EINVAL;
-			goto unblock_mode;
+			goto unblock_ipsec;
 		}
 	}
 
@@ -904,13 +912,14 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 unblock_encap:
 	if (allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-unblock_mode:
-	mlx5_eswitch_unblock_mode(mdev);
 unblock_ipsec:
 	mlx5_eswitch_unblock_ipsec(mdev);
 err_xfrm:
 	kfree(sa_entry);
 	NL_SET_ERR_MSG_WEAK_MOD(extack, "Device failed to offload this state");
+unblock_mode:
+	if (!is_acq)
+		mlx5_eswitch_unblock_mode(mdev);
 	return err;
 }
 
-- 
2.44.0