[PATCH net 2/7] net/mlx5e: ipsec: Block eswitch mode changes before accessing priv->ipsec

[Tariq Toukan <tariqt@nvidia.com>]

From: Cosmin Ratiu <cratiu@nvidia.com>

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

Move the mode block before the first context access and release it on
all error paths. Keep the atomic acquire-placeholder path exempt, since
it creates no hardware state and cannot take sleeping locks.

Fixes: 22239eb258bc ("net/mlx5e: Prevent tunnel reformat when tunnel mode not allowed")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 34 ++++++++++++-------
 1 file changed, 21 insertions(+), 13 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 841ecdc2c4d9..1488faece80e 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 mlx5e_ipsec *ipsec;
@@ -779,20 +780,30 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 	int err;
 
 	priv = netdev_priv(dev);
-	if (!priv->ipsec)
-		return -EOPNOTSUPP;
+	if (!is_acq) {
+		err = mlx5_eswitch_block_mode(priv->mdev, true);
+		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;
 	}
@@ -806,10 +817,6 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 		goto err_xfrm;
 	}
 
-	err = mlx5_eswitch_block_mode(priv->mdev, true);
-	if (err)
-		goto unblock_ipsec;
-
 	if (x->props.mode == XFRM_MODE_TUNNEL &&
 	    x->xso.type == XFRM_DEV_OFFLOAD_PACKET) {
 		allow_tunnel_mode = mlx5e_ipsec_fs_tunnel_allowed(sa_entry);
@@ -817,7 +824,7 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Packet offload tunnel mode is disabled due to encap settings");
 			err = -EINVAL;
-			goto unblock_mode;
+			goto unblock_ipsec;
 		}
 	}
 
@@ -893,12 +900,13 @@ static int mlx5e_xfrm_add_state(struct net_device *dev,
 unblock_encap:
 	if (allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(priv->mdev);
-unblock_mode:
-	mlx5_eswitch_unblock_mode(priv->mdev);
 unblock_ipsec:
 	mlx5_eswitch_unblock_ipsec(priv->mdev);
 err_xfrm:
 	kfree(sa_entry);
+unblock_mode:
+	if (!is_acq)
+		mlx5_eswitch_unblock_mode(priv->mdev);
 	NL_SET_ERR_MSG_WEAK_MOD(extack, "Device failed to offload this state");
 	return err;
 }
-- 
2.44.0