netback.c

/*
 * Back-end of the driver for virtual network devices. This portion of the
 * driver exports a 'unified' network-device interface that can be accessed
 * by any operating system that implements a compatible front end. A
 * reference front-end implementation can be found in:
 *  drivers/net/xen-netfront.c
 *
 * Copyright (c) 2002-2005, K A Fraser
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include "common.h"

#include <linux/kthread.h>
#include <linux/if_vlan.h>
#include <linux/udp.h>

#include <net/tcp.h>

#include <xen/xen.h>
#include <xen/events.h>
#include <xen/interface/memory.h>

#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>

/* SKB control block overlay is used to store useful information when
 * doing guest RX.
 */
struct skb_cb_overlay {
	int meta_slots_used;
	int peek_slots_count;
};

/* Provide an option to disable split event channels at load time as
 * event channels are limited resource. Split event channels are
 * enabled by default.
 */
bool separate_tx_rx_irq = 1;
module_param(separate_tx_rx_irq, bool, 0644);

/*
 * This is the maximum slots a skb can have. If a guest sends a skb
 * which exceeds this limit it is considered malicious.
 */
#define FATAL_SKB_SLOTS_DEFAULT 20
static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT;
module_param(fatal_skb_slots, uint, 0444);

/*
 * To avoid confusion, we define XEN_NETBK_LEGACY_SLOTS_MAX indicating
 * the maximum slots a valid packet can use. Now this value is defined
 * to be XEN_NETIF_NR_SLOTS_MIN, which is supposed to be supported by
 * all backend.
 */
#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN

/*
 * If head != INVALID_PENDING_RING_IDX, it means this tx request is head of
 * one or more merged tx requests, otherwise it is the continuation of
 * previous tx request.
 */
static inline int pending_tx_is_head(struct xenvif *vif, RING_IDX idx)
{
	return vif->pending_tx_info[idx].head != INVALID_PENDING_RING_IDX;
}

static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx,
			       u8 status);

static void make_tx_response(struct xenvif *vif,
			     struct xen_netif_tx_request *txp,
			     s8       st);

static inline int tx_work_todo(struct xenvif *vif);
static inline int rx_work_todo(struct xenvif *vif);

static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
					     u16      id,
					     s8       st,
					     u16      offset,
					     u16      size,
					     u16      flags);

static inline unsigned long idx_to_pfn(struct xenvif *vif,
				       u16 idx)
{
	return page_to_pfn(vif->mmap_pages[idx]);
}

static inline unsigned long idx_to_kaddr(struct xenvif *vif,
					 u16 idx)
{
	return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx));
}

/*
 * This is the amount of packet we copy rather than map, so that the
 * guest can't fiddle with the contents of the headers while we do
 * packet processing on them (netfilter, routing, etc).
 */
#define PKT_PROT_LEN    (ETH_HLEN + \
			 VLAN_HLEN + \
			 sizeof(struct iphdr) + MAX_IPOPTLEN + \
			 sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE)

static u16 frag_get_pending_idx(skb_frag_t *frag)
{
	return (u16)frag->page_offset;
}

static void frag_set_pending_idx(skb_frag_t *frag, u16 pending_idx)
{
	frag->page_offset = pending_idx;
}

static inline pending_ring_idx_t pending_index(unsigned i)
{
	return i & (MAX_PENDING_REQS-1);
}

static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
{
	return MAX_PENDING_REQS -
		vif->pending_prod + vif->pending_cons;
}

static int max_required_rx_slots(struct xenvif *vif)
{
	int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);

	/* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */
	if (vif->can_sg || vif->gso || vif->gso_prefix)
		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */

	return max;
}

int xenvif_rx_ring_full(struct xenvif *vif)
{
	RING_IDX peek   = vif->rx_req_cons_peek;
	RING_IDX needed = max_required_rx_slots(vif);

	return ((vif->rx.sring->req_prod - peek) < needed) ||
	       ((vif->rx.rsp_prod_pvt + XEN_NETIF_RX_RING_SIZE - peek) < needed);
}

int xenvif_must_stop_queue(struct xenvif *vif)
{
	if (!xenvif_rx_ring_full(vif))
		return 0;

	vif->rx.sring->req_event = vif->rx_req_cons_peek +
		max_required_rx_slots(vif);
	mb(); /* request notification /then/ check the queue */

	return xenvif_rx_ring_full(vif);
}

/*
 * Returns true if we should start a new receive buffer instead of
 * adding 'size' bytes to a buffer which currently contains 'offset'
 * bytes.
 */
static bool start_new_rx_buffer(int offset, unsigned long size, int head)
{
	/* simple case: we have completely filled the current buffer. */
	if (offset == MAX_BUFFER_OFFSET)
		return true;

	/*
	 * complex case: start a fresh buffer if the current frag
	 * would overflow the current buffer but only if:
	 *     (i)   this frag would fit completely in the next buffer
	 * and (ii)  there is already some data in the current buffer
	 * and (iii) this is not the head buffer.
	 *
	 * Where:
	 * - (i) stops us splitting a frag into two copies
	 *   unless the frag is too large for a single buffer.
	 * - (ii) stops us from leaving a buffer pointlessly empty.
	 * - (iii) stops us leaving the first buffer
	 *   empty. Strictly speaking this is already covered
	 *   by (ii) but is explicitly checked because
	 *   netfront relies on the first buffer being
	 *   non-empty and can crash otherwise.
	 *
	 * This means we will effectively linearise small
	 * frags but do not needlessly split large buffers
	 * into multiple copies tend to give large frags their
	 * own buffers as before.
	 */
	if ((offset + size > MAX_BUFFER_OFFSET) &&
	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
		return true;

	return false;
}

/*
 * Figure out how many ring slots we're going to need to send @skb to
 * the guest. This function is essentially a dry run of
 * xenvif_gop_frag_copy.
 */
unsigned int xenvif_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
{
	unsigned int count;
	int i, copy_off;
	struct skb_cb_overlay *sco;

	count = DIV_ROUND_UP(skb_headlen(skb), PAGE_SIZE);

	copy_off = skb_headlen(skb) % PAGE_SIZE;

	if (skb_shinfo(skb)->gso_size)
		count++;

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		unsigned long size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
		unsigned long offset = skb_shinfo(skb)->frags[i].page_offset;
		unsigned long bytes;

		offset &= ~PAGE_MASK;

		while (size > 0) {
			BUG_ON(offset >= PAGE_SIZE);
			BUG_ON(copy_off > MAX_BUFFER_OFFSET);

			bytes = PAGE_SIZE - offset;

			if (bytes > size)
				bytes = size;

			if (start_new_rx_buffer(copy_off, bytes, 0)) {
				count++;
				copy_off = 0;
			}

			if (copy_off + bytes > MAX_BUFFER_OFFSET)
				bytes = MAX_BUFFER_OFFSET - copy_off;

			copy_off += bytes;

			offset += bytes;
			size -= bytes;

			if (offset == PAGE_SIZE)
				offset = 0;
		}
	}

	sco = (struct skb_cb_overlay *)skb->cb;
	sco->peek_slots_count = count;
	return count;
}

struct netrx_pending_operations {
	unsigned copy_prod, copy_cons;
	unsigned meta_prod, meta_cons;
	struct gnttab_copy *copy;
	struct xenvif_rx_meta *meta;
	int copy_off;
	grant_ref_t copy_gref;
};

static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
						 struct netrx_pending_operations *npo)
{
	struct xenvif_rx_meta *meta;
	struct xen_netif_rx_request *req;

	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);

	meta = npo->meta + npo->meta_prod++;
	meta->gso_size = 0;
	meta->size = 0;
	meta->id = req->id;

	npo->copy_off = 0;
	npo->copy_gref = req->gref;

	return meta;
}

/* Set up the grant operations for this fragment. */
static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
				 struct netrx_pending_operations *npo,
				 struct page *page, unsigned long size,
				 unsigned long offset, int head, int *first)
{
	struct gnttab_copy *copy_gop;
	struct xenvif_rx_meta *meta;
	unsigned long bytes;

	/* Data must not cross a page boundary. */
	BUG_ON(size + offset > PAGE_SIZE<<compound_order(page));

	meta = npo->meta + npo->meta_prod - 1;

	/* Skip unused frames from start of page */
	page += offset >> PAGE_SHIFT;
	offset &= ~PAGE_MASK;

	while (size > 0) {
		BUG_ON(offset >= PAGE_SIZE);
		BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);

		bytes = PAGE_SIZE - offset;

		if (bytes > size)
			bytes = size;

		if (start_new_rx_buffer(npo->copy_off, bytes, head)) {
			/*
			 * Netfront requires there to be some data in the head
			 * buffer.
			 */
			BUG_ON(*first);

			meta = get_next_rx_buffer(vif, npo);
		}

		if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
			bytes = MAX_BUFFER_OFFSET - npo->copy_off;

		copy_gop = npo->copy + npo->copy_prod++;
		copy_gop->flags = GNTCOPY_dest_gref;
		copy_gop->len = bytes;

		copy_gop->source.domid = DOMID_SELF;
		copy_gop->source.u.gmfn = virt_to_mfn(page_address(page));
		copy_gop->source.offset = offset;

		copy_gop->dest.domid = vif->domid;
		copy_gop->dest.offset = npo->copy_off;
		copy_gop->dest.u.ref = npo->copy_gref;

		npo->copy_off += bytes;
		meta->size += bytes;

		offset += bytes;
		size -= bytes;

		/* Next frame */
		if (offset == PAGE_SIZE && size) {
			BUG_ON(!PageCompound(page));
			page++;
			offset = 0;
		}

		/* Leave a gap for the GSO descriptor. */
		if (*first && skb_shinfo(skb)->gso_size && !vif->gso_prefix)
			vif->rx.req_cons++;

		*first = 0; /* There must be something in this buffer now. */

	}
}

/*
 * Prepare an SKB to be transmitted to the frontend.
 *
 * This function is responsible for allocating grant operations, meta
 * structures, etc.
 *
 * It returns the number of meta structures consumed. The number of
 * ring slots used is always equal to the number of meta slots used
 * plus the number of GSO descriptors used. Currently, we use either
 * zero GSO descriptors (for non-GSO packets) or one descriptor (for
 * frontend-side LRO).
 */
static int xenvif_gop_skb(struct sk_buff *skb,
			  struct netrx_pending_operations *npo)
{
	struct xenvif *vif = netdev_priv(skb->dev);
	int nr_frags = skb_shinfo(skb)->nr_frags;
	int i;
	struct xen_netif_rx_request *req;
	struct xenvif_rx_meta *meta;
	unsigned char *data;
	int first = 1;
	int old_meta_prod;

	old_meta_prod = npo->meta_prod;

	/* Set up a GSO prefix descriptor, if necessary */
	if (skb_shinfo(skb)->gso_size && vif->gso_prefix) {
		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
		meta = npo->meta + npo->meta_prod++;
		meta->gso_size = skb_shinfo(skb)->gso_size;
		meta->size = 0;
		meta->id = req->id;
	}

	req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
	meta = npo->meta + npo->meta_prod++;

	if (!vif->gso_prefix)
		meta->gso_size = skb_shinfo(skb)->gso_size;
	else
		meta->gso_size = 0;

	meta->size = 0;
	meta->id = req->id;
	npo->copy_off = 0;
	npo->copy_gref = req->gref;

	data = skb->data;
	while (data < skb_tail_pointer(skb)) {
		unsigned int offset = offset_in_page(data);
		unsigned int len = PAGE_SIZE - offset;

		if (data + len > skb_tail_pointer(skb))
			len = skb_tail_pointer(skb) - data;

		xenvif_gop_frag_copy(vif, skb, npo,
				     virt_to_page(data), len, offset, 1, &first);
		data += len;
	}

	for (i = 0; i < nr_frags; i++) {
		xenvif_gop_frag_copy(vif, skb, npo,
				     skb_frag_page(&skb_shinfo(skb)->frags[i]),
				     skb_frag_size(&skb_shinfo(skb)->frags[i]),
				     skb_shinfo(skb)->frags[i].page_offset,
				     0, &first);
	}

	return npo->meta_prod - old_meta_prod;
}

/*
 * This is a twin to xenvif_gop_skb.  Assume that xenvif_gop_skb was
 * used to set up the operations on the top of
 * netrx_pending_operations, which have since been done.  Check that
 * they didn't give any errors and advance over them.
 */
static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots,
			    struct netrx_pending_operations *npo)
{
	struct gnttab_copy     *copy_op;
	int status = XEN_NETIF_RSP_OKAY;
	int i;

	for (i = 0; i < nr_meta_slots; i++) {
		copy_op = npo->copy + npo->copy_cons++;
		if (copy_op->status != GNTST_okay) {
			netdev_dbg(vif->dev,
				   "Bad status %d from copy to DOM%d.\n",
				   copy_op->status, vif->domid);
			status = XEN_NETIF_RSP_ERROR;
		}
	}

	return status;
}

static void xenvif_add_frag_responses(struct xenvif *vif, int status,
				      struct xenvif_rx_meta *meta,
				      int nr_meta_slots)
{
	int i;
	unsigned long offset;

	/* No fragments used */
	if (nr_meta_slots <= 1)
		return;

	nr_meta_slots--;

	for (i = 0; i < nr_meta_slots; i++) {
		int flags;
		if (i == nr_meta_slots - 1)
			flags = 0;
		else
			flags = XEN_NETRXF_more_data;

		offset = 0;
		make_rx_response(vif, meta[i].id, status, offset,
				 meta[i].size, flags);
	}
}

static void xenvif_kick_thread(struct xenvif *vif)
{
	wake_up(&vif->wq);
}

void xenvif_rx_action(struct xenvif *vif)
{
	s8 status;
	u16 flags;
	struct xen_netif_rx_response *resp;
	struct sk_buff_head rxq;
	struct sk_buff *skb;
	LIST_HEAD(notify);
	int ret;
	int nr_frags;
	int count;
	unsigned long offset;
	struct skb_cb_overlay *sco;
	int need_to_notify = 0;

	struct netrx_pending_operations npo = {
		.copy  = vif->grant_copy_op,
		.meta  = vif->meta,
	};

	skb_queue_head_init(&rxq);

	count = 0;

	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
		RING_IDX old_rx_req_cons;

		vif = netdev_priv(skb->dev);
		nr_frags = skb_shinfo(skb)->nr_frags;

		old_rx_req_cons = vif->rx.req_cons;
		sco = (struct skb_cb_overlay *)skb->cb;
		sco->meta_slots_used = xenvif_gop_skb(skb, &npo);

		count += vif->rx.req_cons - old_rx_req_cons;

		__skb_queue_tail(&rxq, skb);

		skb = skb_peek(&vif->rx_queue);
		if (skb == NULL)
			break;
		sco = (struct skb_cb_overlay *)skb->cb;

		/* Filled the batch queue? */
		if (count + sco->peek_slots_count >= XEN_NETIF_RX_RING_SIZE)
			break;
	}

	BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));

	if (!npo.copy_prod)
		return;

	BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op));
	gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod);

	while ((skb = __skb_dequeue(&rxq)) != NULL) {
		sco = (struct skb_cb_overlay *)skb->cb;

		vif = netdev_priv(skb->dev);

		if (vif->meta[npo.meta_cons].gso_size && vif->gso_prefix) {
			resp = RING_GET_RESPONSE(&vif->rx,
						 vif->rx.rsp_prod_pvt++);

			resp->flags = XEN_NETRXF_gso_prefix | XEN_NETRXF_more_data;

			resp->offset = vif->meta[npo.meta_cons].gso_size;
			resp->id = vif->meta[npo.meta_cons].id;
			resp->status = sco->meta_slots_used;

			npo.meta_cons++;
			sco->meta_slots_used--;
		}


		vif->dev->stats.tx_bytes += skb->len;
		vif->dev->stats.tx_packets++;

		status = xenvif_check_gop(vif, sco->meta_slots_used, &npo);

		if (sco->meta_slots_used == 1)
			flags = 0;
		else
			flags = XEN_NETRXF_more_data;

		if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */
			flags |= XEN_NETRXF_csum_blank | XEN_NETRXF_data_validated;
		else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
			/* remote but checksummed. */
			flags |= XEN_NETRXF_data_validated;

		offset = 0;
		resp = make_rx_response(vif, vif->meta[npo.meta_cons].id,
					status, offset,
					vif->meta[npo.meta_cons].size,
					flags);

		if (vif->meta[npo.meta_cons].gso_size && !vif->gso_prefix) {
			struct xen_netif_extra_info *gso =
				(struct xen_netif_extra_info *)
				RING_GET_RESPONSE(&vif->rx,
						  vif->rx.rsp_prod_pvt++);

			resp->flags |= XEN_NETRXF_extra_info;

			gso->u.gso.size = vif->meta[npo.meta_cons].gso_size;
			gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
			gso->u.gso.pad = 0;
			gso->u.gso.features = 0;

			gso->type = XEN_NETIF_EXTRA_TYPE_GSO;
			gso->flags = 0;
		}

		xenvif_add_frag_responses(vif, status,
					  vif->meta + npo.meta_cons + 1,
					  sco->meta_slots_used);

		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);

		if (ret)
			need_to_notify = 1;

		xenvif_notify_tx_completion(vif);

		npo.meta_cons += sco->meta_slots_used;
		dev_kfree_skb(skb);
	}

	if (need_to_notify)
		notify_remote_via_irq(vif->rx_irq);

	/* More work to do? */
	if (!skb_queue_empty(&vif->rx_queue))
		xenvif_kick_thread(vif);
}

void xenvif_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb)
{
	skb_queue_tail(&vif->rx_queue, skb);

	xenvif_kick_thread(vif);
}

void xenvif_check_rx_xenvif(struct xenvif *vif)
{
	int more_to_do;

	RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);

	if (more_to_do)
		napi_schedule(&vif->napi);
}

static void tx_add_credit(struct xenvif *vif)
{
	unsigned long max_burst, max_credit;

	/*
	 * Allow a burst big enough to transmit a jumbo packet of up to 128kB.
	 * Otherwise the interface can seize up due to insufficient credit.
	 */
	max_burst = RING_GET_REQUEST(&vif->tx, vif->tx.req_cons)->size;
	max_burst = min(max_burst, 131072UL);
	max_burst = max(max_burst, vif->credit_bytes);

	/* Take care that adding a new chunk of credit doesn't wrap to zero. */
	max_credit = vif->remaining_credit + vif->credit_bytes;
	if (max_credit < vif->remaining_credit)
		max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */

	vif->remaining_credit = min(max_credit, max_burst);
}

static void tx_credit_callback(unsigned long data)
{
	struct xenvif *vif = (struct xenvif *)data;
	tx_add_credit(vif);
	xenvif_check_rx_xenvif(vif);
}

static void xenvif_tx_err(struct xenvif *vif,
			  struct xen_netif_tx_request *txp, RING_IDX end)
{
	RING_IDX cons = vif->tx.req_cons;

	do {
		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
		if (cons == end)
			break;
		txp = RING_GET_REQUEST(&vif->tx, cons++);
	} while (1);
	vif->tx.req_cons = cons;
}

static void xenvif_fatal_tx_err(struct xenvif *vif)
{
	netdev_err(vif->dev, "fatal error; disabling device\n");
	xenvif_carrier_off(vif);
}

static int xenvif_count_requests(struct xenvif *vif,
				 struct xen_netif_tx_request *first,
				 struct xen_netif_tx_request *txp,
				 int work_to_do)
{
	RING_IDX cons = vif->tx.req_cons;
	int slots = 0;
	int drop_err = 0;
	int more_data;

	if (!(first->flags & XEN_NETTXF_more_data))
		return 0;

	do {
		struct xen_netif_tx_request dropped_tx = { 0 };

		if (slots >= work_to_do) {
			netdev_err(vif->dev,
				   "Asked for %d slots but exceeds this limit\n",
				   work_to_do);
			xenvif_fatal_tx_err(vif);
			return -ENODATA;
		}

		/* This guest is really using too many slots and
		 * considered malicious.
		 */
		if (unlikely(slots >= fatal_skb_slots)) {
			netdev_err(vif->dev,
				   "Malicious frontend using %d slots, threshold %u\n",
				   slots, fatal_skb_slots);
			xenvif_fatal_tx_err(vif);
			return -E2BIG;
		}

		/* Xen network protocol had implicit dependency on
		 * MAX_SKB_FRAGS. XEN_NETBK_LEGACY_SLOTS_MAX is set to
		 * the historical MAX_SKB_FRAGS value 18 to honor the
		 * same behavior as before. Any packet using more than
		 * 18 slots but less than fatal_skb_slots slots is
		 * dropped
		 */
		if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) {
			if (net_ratelimit())
				netdev_dbg(vif->dev,
					   "Too many slots (%d) exceeding limit (%d), dropping packet\n",
					   slots, XEN_NETBK_LEGACY_SLOTS_MAX);
			drop_err = -E2BIG;
		}

		if (drop_err)
			txp = &dropped_tx;

		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + slots),
		       sizeof(*txp));

		/* If the guest submitted a frame >= 64 KiB then
		 * first->size overflowed and following slots will
		 * appear to be larger than the frame.
		 *
		 * This cannot be fatal error as there are buggy
		 * frontends that do this.
		 *
		 * Consume all slots and drop the packet.
		 */
		if (!drop_err && txp->size > first->size) {
			if (net_ratelimit())
				netdev_dbg(vif->dev,
					   "Invalid tx request, slot size %u > remaining size %u\n",
					   txp->size, first->size);
			drop_err = -EIO;
		}

		first->size -= txp->size;
		slots++;

		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
			netdev_err(vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n",
				 txp->offset, txp->size);
			xenvif_fatal_tx_err(vif);
			return -EINVAL;
		}

		more_data = txp->flags & XEN_NETTXF_more_data;

		if (!drop_err)
			txp++;

	} while (more_data);

	if (drop_err) {
		xenvif_tx_err(vif, first, cons + slots);
		return drop_err;
	}

	return slots;
}

static struct page *xenvif_alloc_page(struct xenvif *vif,
				      u16 pending_idx)
{
	struct page *page;

	page = alloc_page(GFP_ATOMIC|__GFP_COLD);
	if (!page)
		return NULL;
	vif->mmap_pages[pending_idx] = page;

	return page;
}

static struct gnttab_copy *xenvif_get_requests(struct xenvif *vif,
					       struct sk_buff *skb,
					       struct xen_netif_tx_request *txp,
					       struct gnttab_copy *gop)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	skb_frag_t *frags = shinfo->frags;
	u16 pending_idx = *((u16 *)skb->data);
	u16 head_idx = 0;
	int slot, start;
	struct page *page;
	pending_ring_idx_t index, start_idx = 0;
	uint16_t dst_offset;
	unsigned int nr_slots;
	struct pending_tx_info *first = NULL;

	/* At this point shinfo->nr_frags is in fact the number of
	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
	 */
	nr_slots = shinfo->nr_frags;

	/* Skip first skb fragment if it is on same page as header fragment. */
	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

	/* Coalesce tx requests, at this point the packet passed in
	 * should be <= 64K. Any packets larger than 64K have been
	 * handled in xenvif_count_requests().
	 */
	for (shinfo->nr_frags = slot = start; slot < nr_slots;
	     shinfo->nr_frags++) {
		struct pending_tx_info *pending_tx_info =
			vif->pending_tx_info;

		page = alloc_page(GFP_ATOMIC|__GFP_COLD);
		if (!page)
			goto err;

		dst_offset = 0;
		first = NULL;
		while (dst_offset < PAGE_SIZE && slot < nr_slots) {
			gop->flags = GNTCOPY_source_gref;

			gop->source.u.ref = txp->gref;
			gop->source.domid = vif->domid;
			gop->source.offset = txp->offset;

			gop->dest.domid = DOMID_SELF;

			gop->dest.offset = dst_offset;
			gop->dest.u.gmfn = virt_to_mfn(page_address(page));

			if (dst_offset + txp->size > PAGE_SIZE) {
				/* This page can only merge a portion
				 * of tx request. Do not increment any
				 * pointer / counter here. The txp
				 * will be dealt with in future
				 * rounds, eventually hitting the
				 * `else` branch.
				 */
				gop->len = PAGE_SIZE - dst_offset;
				txp->offset += gop->len;
				txp->size -= gop->len;
				dst_offset += gop->len; /* quit loop */
			} else {
				/* This tx request can be merged in the page */
				gop->len = txp->size;
				dst_offset += gop->len;

				index = pending_index(vif->pending_cons++);

				pending_idx = vif->pending_ring[index];

				memcpy(&pending_tx_info[pending_idx].req, txp,
				       sizeof(*txp));

				/* Poison these fields, corresponding
				 * fields for head tx req will be set
				 * to correct values after the loop.
				 */
				vif->mmap_pages[pending_idx] = (void *)(~0UL);
				pending_tx_info[pending_idx].head =
					INVALID_PENDING_RING_IDX;

				if (!first) {
					first = &pending_tx_info[pending_idx];
					start_idx = index;
					head_idx = pending_idx;
				}

				txp++;
				slot++;
			}

			gop++;
		}

		first->req.offset = 0;
		first->req.size = dst_offset;
		first->head = start_idx;
		vif->mmap_pages[head_idx] = page;
		frag_set_pending_idx(&frags[shinfo->nr_frags], head_idx);
	}

	BUG_ON(shinfo->nr_frags > MAX_SKB_FRAGS);

	return gop;
err:
	/* Unwind, freeing all pages and sending error responses. */
	while (shinfo->nr_frags-- > start) {
		xenvif_idx_release(vif,
				frag_get_pending_idx(&frags[shinfo->nr_frags]),
				XEN_NETIF_RSP_ERROR);
	}
	/* The head too, if necessary. */
	if (start)
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);

	return NULL;
}

static int xenvif_tx_check_gop(struct xenvif *vif,
			       struct sk_buff *skb,
			       struct gnttab_copy **gopp)
{
	struct gnttab_copy *gop = *gopp;
	u16 pending_idx = *((u16 *)skb->data);
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	struct pending_tx_info *tx_info;
	int nr_frags = shinfo->nr_frags;
	int i, err, start;
	u16 peek; /* peek into next tx request */

	/* Check status of header. */
	err = gop->status;
	if (unlikely(err))
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);

	/* Skip first skb fragment if it is on same page as header fragment. */
	start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);

	for (i = start; i < nr_frags; i++) {
		int j, newerr;
		pending_ring_idx_t head;

		pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
		tx_info = &vif->pending_tx_info[pending_idx];
		head = tx_info->head;

		/* Check error status: if okay then remember grant handle. */
		do {
			newerr = (++gop)->status;
			if (newerr)
				break;
			peek = vif->pending_ring[pending_index(++head)];
		} while (!pending_tx_is_head(vif, peek));

		if (likely(!newerr)) {
			/* Had a previous error? Invalidate this fragment. */
			if (unlikely(err))
				xenvif_idx_release(vif, pending_idx,
						   XEN_NETIF_RSP_OKAY);
			continue;
		}

		/* Error on this fragment: respond to client with an error. */
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);

		/* Not the first error? Preceding frags already invalidated. */
		if (err)
			continue;

		/* First error: invalidate header and preceding fragments. */
		pending_idx = *((u16 *)skb->data);
		xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
		for (j = start; j < i; j++) {
			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);