cdc_ncm: Add support for moving NDP to end of NCM frame

NCM specs are not actually mandating a specific position in the frame for
the NDP (Network Datagram Pointer). However, some Huawei devices will
ignore our aggregates if it is not placed after the datagrams it points
to. Add support for doing just this, in a per-device configurable way.
While at it, update NCM subdrivers, disabling this functionality in all of
them, except in huawei_cdc_ncm where it is enabled instead.
We aren't making any distinction between different Huawei NCM devices,
based on what the vendor driver does. Standard NCM devices are left
unaffected: if they are compliant, they should be always usable, still
stay on the safe side.

This change has been tested and working with a Huawei E3131 device (which
works regardless of NDP position), a Huawei E3531 (also working both
ways) and an E3372 (which mandates NDP to be after indexed datagrams).

V1->V2:
- corrected wrong NDP acronym definition
- fixed possible NULL pointer dereference
- patch cleanup
V2->V3:
- Properly account for the NDP size when writing new packets to SKB
Signed-off-by: NEnrico Mioso <mrkiko.rs@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/usb/cdc_mbim.c

@@ -158,7 +158,7 @@ static int cdc_mbim_bind(struct usbnet *dev, struct usb_interface *intf)
 	if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
 		goto err;
 
-	ret = cdc_ncm_bind_common(dev, intf, data_altsetting);
+	ret = cdc_ncm_bind_common(dev, intf, data_altsetting, 0);
 	if (ret)
 		goto err;
 

drivers/net/usb/cdc_ncm.c

@@ -684,10 +684,12 @@ static void cdc_ncm_free(struct cdc_ncm_ctx *ctx)
 		ctx->tx_curr_skb = NULL;
 	}
 
+	kfree(ctx->delayed_ndp16);
+
 	kfree(ctx);
 }
 
-int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting)
+int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags)
 {
 	const struct usb_cdc_union_desc *union_desc = NULL;
 	struct cdc_ncm_ctx *ctx;
@@ -855,6 +857,17 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 	/* finish setting up the device specific data */
 	cdc_ncm_setup(dev);
 
+	/* Device-specific flags */
+	ctx->drvflags = drvflags;
+
+	/* Allocate the delayed NDP if needed. */
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
+		ctx->delayed_ndp16 = kzalloc(ctx->max_ndp_size, GFP_KERNEL);
+		if (!ctx->delayed_ndp16)
+			goto error2;
+		dev_info(&intf->dev, "NDP will be placed at end of frame for this device.");
+	}
+
 	/* override ethtool_ops */
 	dev->net->ethtool_ops = &cdc_ncm_ethtool_ops;
 
@@ -954,8 +967,11 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
 		return -ENODEV;
 
-	/* The NCM data altsetting is fixed */
-	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM);
+	/* The NCM data altsetting is fixed, so we hard-coded it.
+	 * Additionally, generic NCM devices are assumed to accept arbitrarily
+	 * placed NDP.
+	 */
+	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
 
 	/*
 	 * We should get an event when network connection is "connected" or
@@ -986,6 +1002,14 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 	struct usb_cdc_ncm_nth16 *nth16 = (void *)skb->data;
 	size_t ndpoffset = le16_to_cpu(nth16->wNdpIndex);
 
+	/* If NDP should be moved to the end of the NCM package, we can't follow the
+	* NTH16 header as we would normally do. NDP isn't written to the SKB yet, and
+	* the wNdpIndex field in the header is actually not consistent with reality. It will be later.
+	*/
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
+		if (ctx->delayed_ndp16->dwSignature == sign)
+			return ctx->delayed_ndp16;
+
 	/* follow the chain of NDPs, looking for a match */
 	while (ndpoffset) {
 		ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb->data + ndpoffset);
@@ -995,7 +1019,8 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 	}
 
 	/* align new NDP */
-	cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max);
+	if (!(ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END))
+		cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max);
 
 	/* verify that there is room for the NDP and the datagram (reserve) */
 	if ((ctx->tx_max - skb->len - reserve) < ctx->max_ndp_size)
@@ -1008,7 +1033,11 @@ static struct usb_cdc_ncm_ndp16 *cdc_ncm_ndp(struct cdc_ncm_ctx *ctx, struct sk_
 		nth16->wNdpIndex = cpu_to_le16(skb->len);
 
 	/* push a new empty NDP */
-	ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size);
+	if (!(ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END))
+		ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size);
+	else
+		ndp16 = ctx->delayed_ndp16;
+
 	ndp16->dwSignature = sign;
 	ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) + sizeof(struct usb_cdc_ncm_dpe16));
 	return ndp16;
@@ -1023,6 +1052,15 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 	struct sk_buff *skb_out;
 	u16 n = 0, index, ndplen;
 	u8 ready2send = 0;
+	u32 delayed_ndp_size;
+
+	/* When our NDP gets written in cdc_ncm_ndp(), then skb_out->len gets updated
+	 * accordingly. Otherwise, we should check here.
+	 */
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
+		delayed_ndp_size = ctx->max_ndp_size;
+	else
+		delayed_ndp_size = 0;
 
 	/* if there is a remaining skb, it gets priority */
 	if (skb != NULL) {
@@ -1077,7 +1115,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 		cdc_ncm_align_tail(skb_out,  ctx->tx_modulus, ctx->tx_remainder, ctx->tx_max);
 
 		/* check if we had enough room left for both NDP and frame */
-		if (!ndp16 || skb_out->len + skb->len > ctx->tx_max) {
+		if (!ndp16 || skb_out->len + skb->len + delayed_ndp_size > ctx->tx_max) {
 			if (n == 0) {
 				/* won't fit, MTU problem? */
 				dev_kfree_skb_any(skb);
@@ -1150,6 +1188,17 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign)
 		/* variables will be reset at next call */
 	}
 
+	/* If requested, put NDP at end of frame. */
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
+		nth16 = (struct usb_cdc_ncm_nth16 *)skb_out->data;
+		cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_max);
+		nth16->wNdpIndex = cpu_to_le16(skb_out->len);
+		memcpy(skb_put(skb_out, ctx->max_ndp_size), ctx->delayed_ndp16, ctx->max_ndp_size);
+
+		/* Zero out delayed NDP - signature checking will naturally fail. */
+		ndp16 = memset(ctx->delayed_ndp16, 0, ctx->max_ndp_size);
+	}
+
 	/* If collected data size is less or equal ctx->min_tx_pkt
 	 * bytes, we send buffers as it is. If we get more data, it
 	 * would be more efficient for USB HS mobile device with DMA

drivers/net/usb/huawei_cdc_ncm.c

@@ -73,11 +73,14 @@ static int huawei_cdc_ncm_bind(struct usbnet *usbnet_dev,
 	struct usb_driver *subdriver = ERR_PTR(-ENODEV);
 	int ret = -ENODEV;
 	struct huawei_cdc_ncm_state *drvstate = (void *)&usbnet_dev->data;
+	int drvflags = 0;
 
 	/* altsetting should always be 1 for NCM devices - so we hard-coded
-	 * it here
+	 * it here. Some huawei devices will need the NDP part of the NCM package to
+	 * be at the end of the frame.
 	 */
-	ret = cdc_ncm_bind_common(usbnet_dev, intf, 1);
+	drvflags |= CDC_NCM_FLAG_NDP_TO_END;
+	ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags);
 	if (ret)
 		goto err;
 

include/linux/usb/cdc_ncm.h

@@ -80,6 +80,9 @@
 #define CDC_NCM_TIMER_INTERVAL_MIN		5UL
 #define CDC_NCM_TIMER_INTERVAL_MAX		(U32_MAX / NSEC_PER_USEC)
 
+/* Driver flags */
+#define CDC_NCM_FLAG_NDP_TO_END	0x02		/* NDP is placed at end of frame */
+
 #define cdc_ncm_comm_intf_is_mbim(x)  ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \
 				       (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE)
 #define cdc_ncm_data_intf_is_mbim(x)  ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB)
@@ -103,9 +106,11 @@ struct cdc_ncm_ctx {
 
 	spinlock_t mtx;
 	atomic_t stop;
+	int drvflags;
 
 	u32 timer_interval;
 	u32 max_ndp_size;
+	struct usb_cdc_ncm_ndp16 *delayed_ndp16;
 
 	u32 tx_timer_pending;
 	u32 tx_curr_frame_num;
@@ -133,7 +138,7 @@ struct cdc_ncm_ctx {
 };
 
 u8 cdc_ncm_select_altsetting(struct usb_interface *intf);
-int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
+int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags);
 void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
 int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);