net/tls: Protect from calling tls_dev_del for TLS RX twice

tls_device_offload_cleanup_rx doesn't clear tls_ctx->netdev after
calling tls_dev_del if TLX TX offload is also enabled. Clearing
tls_ctx->netdev gets postponed until tls_device_gc_task. It leaves a
time frame when tls_device_down may get called and call tls_dev_del for
RX one extra time, confusing the driver, which may lead to a crash.

This patch corrects this racy behavior by adding a flag to prevent
tls_device_down from calling tls_dev_del the second time.

Fixes: e8f6979981 ("net/tls: Add generic NIC offload infrastructure")
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20201125221810.69870-1-saeedm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/tls.h

@@ -199,6 +199,12 @@ enum tls_context_flags {
 	 * to be atomic.
 	 */
 	TLS_TX_SYNC_SCHED = 1,
+	/* tls_dev_del was called for the RX side, device state was released,
+	 * but tls_ctx->netdev might still be kept, because TX-side driver
+	 * resources might not be released yet. Used to prevent the second
+	 * tls_dev_del call in tls_device_down if it happens simultaneously.
+	 */
+	TLS_RX_DEV_CLOSED = 2,
 };
 
 struct cipher_context {

net/tls/tls_device.c

@@ -1262,6 +1262,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 	if (tls_ctx->tx_conf != TLS_HW) {
 		dev_put(netdev);
 		tls_ctx->netdev = NULL;
+	} else {
+		set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags);
 	}
 out:
 	up_read(&device_offload_lock);
@@ -1291,7 +1293,8 @@ static int tls_device_down(struct net_device *netdev)
 		if (ctx->tx_conf == TLS_HW)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_TX);
-		if (ctx->rx_conf == TLS_HW)
+		if (ctx->rx_conf == TLS_HW &&
+		    !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags))
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_RX);
 		WRITE_ONCE(ctx->netdev, NULL);