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

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

struct pending_tx_info {
	struct xen_netif_tx_request req;
	struct xenvif *vif;
};
typedef unsigned int pending_ring_idx_t;

struct netbk_rx_meta {
	int id;
	int size;
	int gso_size;
};

#define MAX_PENDING_REQS 256

#define MAX_BUFFER_OFFSET PAGE_SIZE

/* extra field used in struct page */
union page_ext {
	struct {
#if BITS_PER_LONG < 64
#define IDX_WIDTH   8
#define GROUP_WIDTH (BITS_PER_LONG - IDX_WIDTH)
		unsigned int group:GROUP_WIDTH;
		unsigned int idx:IDX_WIDTH;
#else
		unsigned int group, idx;
#endif
	} e;
	void *mapping;
};

struct xen_netbk {
	wait_queue_head_t wq;
	struct task_struct *task;

	struct sk_buff_head rx_queue;
	struct sk_buff_head tx_queue;

	struct timer_list net_timer;

	struct page *mmap_pages[MAX_PENDING_REQS];

	pending_ring_idx_t pending_prod;
	pending_ring_idx_t pending_cons;
	struct list_head net_schedule_list;

	/* Protect the net_schedule_list in netif. */
	spinlock_t net_schedule_list_lock;

	atomic_t netfront_count;

	struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
	struct gnttab_copy tx_copy_ops[MAX_PENDING_REQS];

	u16 pending_ring[MAX_PENDING_REQS];

	/*
	 * Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
	 * head/fragment page uses 2 copy operations because it
	 * straddles two buffers in the frontend.
	 */
	struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
	struct netbk_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
};

static struct xen_netbk *xen_netbk;
static int xen_netbk_group_nr;

void xen_netbk_add_xenvif(struct xenvif *vif)
{
	int i;
	int min_netfront_count;
	int min_group = 0;
	struct xen_netbk *netbk;

	min_netfront_count = atomic_read(&xen_netbk[0].netfront_count);
	for (i = 0; i < xen_netbk_group_nr; i++) {
		int netfront_count = atomic_read(&xen_netbk[i].netfront_count);
		if (netfront_count < min_netfront_count) {
			min_group = i;
			min_netfront_count = netfront_count;
		}
	}

	netbk = &xen_netbk[min_group];

	vif->netbk = netbk;
	atomic_inc(&netbk->netfront_count);
}

void xen_netbk_remove_xenvif(struct xenvif *vif)
{
	struct xen_netbk *netbk = vif->netbk;
	vif->netbk = NULL;
	atomic_dec(&netbk->netfront_count);
}

static void xen_netbk_idx_release(struct xen_netbk *netbk, u16 pending_idx);
static void make_tx_response(struct xenvif *vif,
			     struct xen_netif_tx_request *txp,
			     s8       st);
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 xen_netbk *netbk,
				       unsigned int idx)
{
	return page_to_pfn(netbk->mmap_pages[idx]);
}

static inline unsigned long idx_to_kaddr(struct xen_netbk *netbk,
					 unsigned int idx)
{
	return (unsigned long)pfn_to_kaddr(idx_to_pfn(netbk, idx));
}

/* extra field used in struct page */
static inline void set_page_ext(struct page *pg, struct xen_netbk *netbk,
				unsigned int idx)
{
	unsigned int group = netbk - xen_netbk;
	union page_ext ext = { .e = { .group = group + 1, .idx = idx } };

	BUILD_BUG_ON(sizeof(ext) > sizeof(ext.mapping));
	pg->mapping = ext.mapping;
}

static int get_page_ext(struct page *pg,
			unsigned int *pgroup, unsigned int *pidx)
{
	union page_ext ext = { .mapping = pg->mapping };
	struct xen_netbk *netbk;
	unsigned int group, idx;

	group = ext.e.group - 1;

	if (group < 0 || group >= xen_netbk_group_nr)
		return 0;

	netbk = &xen_netbk[group];

	idx = ext.e.idx;

	if ((idx < 0) || (idx >= MAX_PENDING_REQS))
		return 0;

	if (netbk->mmap_pages[idx] != pg)
		return 0;

	*pgroup = group;
	*pidx = idx;

	return 1;
}

/*
 * 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 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 xen_netbk *netbk)
{
	return MAX_PENDING_REQS -
		netbk->pending_prod + netbk->pending_cons;
}

static void xen_netbk_kick_thread(struct xen_netbk *netbk)
{
	wake_up(&netbk->wq);
}

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

	if (vif->can_sg || vif->gso || vif->gso_prefix)
		max += MAX_SKB_FRAGS + 1; /* extra_info + frags */

	return max;
}

int xen_netbk_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 xen_netbk_must_stop_queue(struct xenvif *vif)
{
	if (!xen_netbk_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 xen_netbk_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
 * netbk_gop_frag_copy.
 */
unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb)
{
	unsigned int count;
	int i, copy_off;

	count = DIV_ROUND_UP(
			offset_in_page(skb->data)+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_shinfo(skb)->frags[i].size;
		unsigned long bytes;
		while (size > 0) {
			BUG_ON(copy_off > MAX_BUFFER_OFFSET);

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

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

			copy_off += bytes;
			size -= bytes;
		}
	}
	return count;
}

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

static struct netbk_rx_meta *get_next_rx_buffer(struct xenvif *vif,
						struct netrx_pending_operations *npo)
{
	struct netbk_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. If it's a flipping
 * interface, we also set up the unmap request from here.
 */
static void netbk_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)
{
	struct gnttab_copy *copy_gop;
	struct netbk_rx_meta *meta;
	/*
	 * These variables a used iff get_page_ext returns true,
	 * in which case they are guaranteed to be initialized.
	 */
	unsigned int uninitialized_var(group), uninitialized_var(idx);
	int foreign = get_page_ext(page, &group, &idx);
	unsigned long bytes;

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

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

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

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

			meta = get_next_rx_buffer(vif, npo);
		}

		bytes = size;
		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;
		if (foreign) {
			struct xen_netbk *netbk = &xen_netbk[group];
			struct pending_tx_info *src_pend;

			src_pend = &netbk->pending_tx_info[idx];

			copy_gop->source.domid = src_pend->vif->domid;
			copy_gop->source.u.ref = src_pend->req.gref;
			copy_gop->flags |= GNTCOPY_source_gref;
		} else {
			void *vaddr = page_address(page);
			copy_gop->source.domid = DOMID_SELF;
			copy_gop->source.u.gmfn = virt_to_mfn(vaddr);
		}
		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;
		copy_gop->len = bytes;

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

		offset += bytes;
		size -= bytes;

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

		*head = 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 netbk_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 netbk_rx_meta *meta;
	unsigned char *data;
	int head = 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;

		netbk_gop_frag_copy(vif, skb, npo,
				    virt_to_page(data), len, offset, &head);
		data += len;
	}

	for (i = 0; i < nr_frags; i++) {
		netbk_gop_frag_copy(vif, skb, npo,
				    skb_shinfo(skb)->frags[i].page,
				    skb_shinfo(skb)->frags[i].size,
				    skb_shinfo(skb)->frags[i].page_offset,
				    &head);
	}

	return npo->meta_prod - old_meta_prod;
}

/*
 * This is a twin to netbk_gop_skb.  Assume that netbk_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 netbk_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 netbk_add_frag_responses(struct xenvif *vif, int status,
				     struct netbk_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);
	}
}

struct skb_cb_overlay {
	int meta_slots_used;
};

static void xen_netbk_rx_action(struct xen_netbk *netbk)
{
	struct xenvif *vif = NULL, *tmp;
	s8 status;
	u16 irq, 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;

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

	skb_queue_head_init(&rxq);

	count = 0;

	while ((skb = skb_dequeue(&netbk->rx_queue)) != NULL) {
		vif = netdev_priv(skb->dev);
		nr_frags = skb_shinfo(skb)->nr_frags;

		sco = (struct skb_cb_overlay *)skb->cb;
		sco->meta_slots_used = netbk_gop_skb(skb, &npo);

		count += nr_frags + 1;

		__skb_queue_tail(&rxq, skb);

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

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

	if (!npo.copy_prod)
		return;

	BUG_ON(npo.copy_prod > ARRAY_SIZE(netbk->grant_copy_op));
	ret = HYPERVISOR_grant_table_op(GNTTABOP_copy, &netbk->grant_copy_op,
					npo.copy_prod);
	BUG_ON(ret != 0);

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

		vif = netdev_priv(skb->dev);

		if (netbk->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 = netbk->meta[npo.meta_cons].gso_size;
			resp->id = netbk->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 = netbk_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, netbk->meta[npo.meta_cons].id,
					status, offset,
					netbk->meta[npo.meta_cons].size,
					flags);

		if (netbk->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 = netbk->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;
		}

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

		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
		irq = vif->irq;
		if (ret && list_empty(&vif->notify_list))
			list_add_tail(&vif->notify_list, &notify);

		xenvif_notify_tx_completion(vif);

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

	list_for_each_entry_safe(vif, tmp, &notify, notify_list) {
		notify_remote_via_irq(vif->irq);
		list_del_init(&vif->notify_list);
	}

	/* More work to do? */
	if (!skb_queue_empty(&netbk->rx_queue) &&
			!timer_pending(&netbk->net_timer))
		xen_netbk_kick_thread(netbk);
}

void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb)
{
	struct xen_netbk *netbk = vif->netbk;

	skb_queue_tail(&netbk->rx_queue, skb);

	xen_netbk_kick_thread(netbk);
}

static void xen_netbk_alarm(unsigned long data)
{
	struct xen_netbk *netbk = (struct xen_netbk *)data;
	xen_netbk_kick_thread(netbk);
}

static int __on_net_schedule_list(struct xenvif *vif)
{
	return !list_empty(&vif->schedule_list);
}

/* Must be called with net_schedule_list_lock held */
static void remove_from_net_schedule_list(struct xenvif *vif)
{
	if (likely(__on_net_schedule_list(vif))) {
		list_del_init(&vif->schedule_list);
		xenvif_put(vif);
	}
}

static struct xenvif *poll_net_schedule_list(struct xen_netbk *netbk)
{
	struct xenvif *vif = NULL;

	spin_lock_irq(&netbk->net_schedule_list_lock);
	if (list_empty(&netbk->net_schedule_list))
		goto out;

	vif = list_first_entry(&netbk->net_schedule_list,
			       struct xenvif, schedule_list);
	if (!vif)
		goto out;

	xenvif_get(vif);

	remove_from_net_schedule_list(vif);
out:
	spin_unlock_irq(&netbk->net_schedule_list_lock);
	return vif;
}

void xen_netbk_schedule_xenvif(struct xenvif *vif)
{
	unsigned long flags;
	struct xen_netbk *netbk = vif->netbk;

	if (__on_net_schedule_list(vif))
		goto kick;

	spin_lock_irqsave(&netbk->net_schedule_list_lock, flags);
	if (!__on_net_schedule_list(vif) &&
	    likely(xenvif_schedulable(vif))) {
		list_add_tail(&vif->schedule_list, &netbk->net_schedule_list);
		xenvif_get(vif);
	}
	spin_unlock_irqrestore(&netbk->net_schedule_list_lock, flags);

kick:
	smp_mb();
	if ((nr_pending_reqs(netbk) < (MAX_PENDING_REQS/2)) &&
	    !list_empty(&netbk->net_schedule_list))
		xen_netbk_kick_thread(netbk);
}

void xen_netbk_deschedule_xenvif(struct xenvif *vif)
{
	struct xen_netbk *netbk = vif->netbk;
	spin_lock_irq(&netbk->net_schedule_list_lock);
	remove_from_net_schedule_list(vif);
	spin_unlock_irq(&netbk->net_schedule_list_lock);
}

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

	RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);

	if (more_to_do)
		xen_netbk_schedule_xenvif(vif);
}

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);
	xen_netbk_check_rx_xenvif(vif);
}

static void netbk_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;
	xen_netbk_check_rx_xenvif(vif);
	xenvif_put(vif);
}

static int netbk_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 frags = 0;

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

	do {
		if (frags >= work_to_do) {
			netdev_dbg(vif->dev, "Need more frags\n");
			return -frags;
		}

		if (unlikely(frags >= MAX_SKB_FRAGS)) {
			netdev_dbg(vif->dev, "Too many frags\n");
			return -frags;
		}

		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
		       sizeof(*txp));
		if (txp->size > first->size) {
			netdev_dbg(vif->dev, "Frags galore\n");
			return -frags;
		}

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

		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
			netdev_dbg(vif->dev, "txp->offset: %x, size: %u\n",
				 txp->offset, txp->size);
			return -frags;
		}
	} while ((txp++)->flags & XEN_NETTXF_more_data);
	return frags;
}

static struct page *xen_netbk_alloc_page(struct xen_netbk *netbk,
					 struct sk_buff *skb,
					 unsigned long pending_idx)
{
	struct page *page;
	page = alloc_page(GFP_KERNEL|__GFP_COLD);
	if (!page)
		return NULL;
	set_page_ext(page, netbk, pending_idx);
	netbk->mmap_pages[pending_idx] = page;
	return page;
}

static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
						  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;
	unsigned long pending_idx = *((u16 *)skb->data);
	int i, start;

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

	for (i = start; i < shinfo->nr_frags; i++, txp++) {
		struct page *page;
		pending_ring_idx_t index;
		struct pending_tx_info *pending_tx_info =
			netbk->pending_tx_info;

		index = pending_index(netbk->pending_cons++);
		pending_idx = netbk->pending_ring[index];
		page = xen_netbk_alloc_page(netbk, skb, pending_idx);
		if (!page)
			return NULL;

		netbk->mmap_pages[pending_idx] = page;

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

		gop->dest.u.gmfn = virt_to_mfn(page_address(page));
		gop->dest.domid = DOMID_SELF;
		gop->dest.offset = txp->offset;

		gop->len = txp->size;
		gop->flags = GNTCOPY_source_gref;

		gop++;

		memcpy(&pending_tx_info[pending_idx].req, txp, sizeof(*txp));
		xenvif_get(vif);
		pending_tx_info[pending_idx].vif = vif;
		frags[i].page = (void *)pending_idx;
	}

	return gop;
}

static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
				  struct sk_buff *skb,
				  struct gnttab_copy **gopp)
{
	struct gnttab_copy *gop = *gopp;
	int pending_idx = *((u16 *)skb->data);
	struct pending_tx_info *pending_tx_info = netbk->pending_tx_info;
	struct xenvif *vif = pending_tx_info[pending_idx].vif;
	struct xen_netif_tx_request *txp;
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int nr_frags = shinfo->nr_frags;
	int i, err, start;

	/* Check status of header. */
	err = gop->status;
	if (unlikely(err)) {
		pending_ring_idx_t index;
		index = pending_index(netbk->pending_prod++);
		txp = &pending_tx_info[pending_idx].req;
		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
		netbk->pending_ring[index] = pending_idx;
		xenvif_put(vif);
	}

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

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

		pending_idx = (unsigned long)shinfo->frags[i].page;

		/* Check error status: if okay then remember grant handle. */
		newerr = (++gop)->status;
		if (likely(!newerr)) {
			/* Had a previous error? Invalidate this fragment. */
			if (unlikely(err))
				xen_netbk_idx_release(netbk, pending_idx);
			continue;
		}

		/* Error on this fragment: respond to client with an error. */
		txp = &netbk->pending_tx_info[pending_idx].req;
		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
		index = pending_index(netbk->pending_prod++);
		netbk->pending_ring[index] = pending_idx;