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 <linux/highmem.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>

/* 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);

/* When guest ring is filled up, qdisc queues the packets for us, but we have
 * to timeout them, otherwise other guests' packets can get stuck there
 */
unsigned int rx_drain_timeout_msecs = 10000;
module_param(rx_drain_timeout_msecs, uint, 0444);
unsigned int rx_drain_timeout_jiffies;

/*
 * 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);

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));
}

/* Find the containing VIF's structure from a pointer in pending_tx_info array
 */
static inline struct xenvif* ubuf_to_vif(struct ubuf_info *ubuf)
{
	u16 pending_idx = ubuf->desc;
	struct pending_tx_info *temp =
		container_of(ubuf, struct pending_tx_info, callback_struct);
	return container_of(temp - pending_idx,
			    struct xenvif,
			    pending_tx_info[0]);
}

/* This is a miniumum size for the linear area to avoid lots of
 * calls to __pskb_pull_tail() as we set up checksum offsets. The
 * value 128 was chosen as it covers all IPv4 and most likely
 * IPv6 headers.
 */
#define PKT_PROT_LEN 128

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);
}

bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed)
{
	RING_IDX prod, cons;

	do {
		prod = vif->rx.sring->req_prod;
		cons = vif->rx.req_cons;

		if (prod - cons >= needed)
			return true;

		vif->rx.sring->req_event = prod + 1;

		/* Make sure event is visible before we check prod
		 * again.
		 */
		mb();
	} while (vif->rx.sring->req_prod != prod);

	return false;
}

/*
 * 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;
}

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_type = XEN_NETIF_GSO_TYPE_NONE;
	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 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,
				 struct xenvif *foreign_vif,
				 grant_ref_t foreign_gref)
{
	struct gnttab_copy *copy_gop;
	struct xenvif_rx_meta *meta;
	unsigned long bytes;
	int gso_type = XEN_NETIF_GSO_TYPE_NONE;

	/* 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(*head);

			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;

		if (foreign_vif) {
			copy_gop->source.domid = foreign_vif->domid;
			copy_gop->source.u.ref = foreign_gref;
			copy_gop->flags |= GNTCOPY_source_gref;
		} else {
			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 (skb_is_gso(skb)) {
			if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
				gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
			else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
				gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
		}

		if (*head && ((1 << gso_type) & vif->gso_mask))
			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 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 head = 1;
	int old_meta_prod;
	int gso_type;
	struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg;
	grant_ref_t foreign_grefs[MAX_SKB_FRAGS];
	struct xenvif *foreign_vif = NULL;

	old_meta_prod = npo->meta_prod;

	gso_type = XEN_NETIF_GSO_TYPE_NONE;
	if (skb_is_gso(skb)) {
		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
			gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
			gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
	}

	/* Set up a GSO prefix descriptor, if necessary */
	if ((1 << gso_type) & vif->gso_prefix_mask) {
		req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
		meta = npo->meta + npo->meta_prod++;
		meta->gso_type = gso_type;
		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 ((1 << gso_type) & vif->gso_mask) {
		meta->gso_type = gso_type;
		meta->gso_size = skb_shinfo(skb)->gso_size;
	} else {
		meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
		meta->gso_size = 0;
	}

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

	if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
		 (ubuf->callback == &xenvif_zerocopy_callback)) {
		int i = 0;
		foreign_vif = ubuf_to_vif(ubuf);

		do {
			u16 pending_idx = ubuf->desc;
			foreign_grefs[i++] =
				foreign_vif->pending_tx_info[pending_idx].req.gref;
			ubuf = (struct ubuf_info *) ubuf->ctx;
		} while (ubuf);
	}

	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, &head,
				     NULL,
				     0);
		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,
				     &head,
				     foreign_vif,
				     foreign_grefs[i]);
	}

	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);
	}
}

struct xenvif_rx_cb {
	int meta_slots_used;
};

#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)

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

static 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;
	unsigned long offset;
	bool need_to_notify = false;

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

	skb_queue_head_init(&rxq);

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

		/* We need a cheap worse case estimate for the number of
		 * slots we'll use.
		 */

		max_slots_needed = DIV_ROUND_UP(offset_in_page(skb->data) +
						skb_headlen(skb),
						PAGE_SIZE);
		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
			unsigned int size;
			size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
			max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
		}
		if (skb_is_gso(skb) &&
		   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
			max_slots_needed++;

		/* If the skb may not fit then bail out now */
		if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) {
			skb_queue_head(&vif->rx_queue, skb);
			need_to_notify = true;
			vif->rx_last_skb_slots = max_slots_needed;
			break;
		} else
			vif->rx_last_skb_slots = 0;

		XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo);
		BUG_ON(XENVIF_RX_CB(skb)->meta_slots_used > max_slots_needed);

		__skb_queue_tail(&rxq, skb);
	}

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

	if (!npo.copy_prod)
		goto done;

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

	while ((skb = __skb_dequeue(&rxq)) != NULL) {

		if ((1 << vif->meta[npo.meta_cons].gso_type) &
		    vif->gso_prefix_mask) {
			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 = XENVIF_RX_CB(skb)->meta_slots_used;

			npo.meta_cons++;
			XENVIF_RX_CB(skb)->meta_slots_used--;
		}


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

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

		if (XENVIF_RX_CB(skb)->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 ((1 << vif->meta[npo.meta_cons].gso_type) &
		    vif->gso_mask) {
			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.type = vif->meta[npo.meta_cons].gso_type;
			gso->u.gso.size = vif->meta[npo.meta_cons].gso_size;
			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,
					  XENVIF_RX_CB(skb)->meta_slots_used);

		RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);

		need_to_notify |= !!ret;

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

done:
	if (need_to_notify)
		notify_remote_via_irq(vif->rx_irq);
}

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;
	unsigned long flags;

	do {
		spin_lock_irqsave(&vif->response_lock, flags);
		make_tx_response(vif, txp, XEN_NETIF_RSP_ERROR);
		spin_unlock_irqrestore(&vif->response_lock, flags);
		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;
}


struct xenvif_tx_cb {
	u16 pending_idx;
};

#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb)

static inline void xenvif_tx_create_gop(struct xenvif *vif,
					u16 pending_idx,
					struct xen_netif_tx_request *txp,
					struct gnttab_map_grant_ref *gop)
{
	vif->pages_to_map[gop-vif->tx_map_ops] = vif->mmap_pages[pending_idx];
	gnttab_set_map_op(gop, idx_to_kaddr(vif, pending_idx),
			  GNTMAP_host_map | GNTMAP_readonly,
			  txp->gref, vif->domid);

	memcpy(&vif->pending_tx_info[pending_idx].req, txp,
	       sizeof(*txp));
}

static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
{
	struct sk_buff *skb =
		alloc_skb(size + NET_SKB_PAD + NET_IP_ALIGN,
			  GFP_ATOMIC | __GFP_NOWARN);
	if (unlikely(skb == NULL))
		return NULL;

	/* Packets passed to netif_rx() must have some headroom. */
	skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);

	/* Initialize it here to avoid later surprises */
	skb_shinfo(skb)->destructor_arg = NULL;

	return skb;
}

static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
							struct sk_buff *skb,
							struct xen_netif_tx_request *txp,
							struct gnttab_map_grant_ref *gop)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	skb_frag_t *frags = shinfo->frags;
	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
	int start;
	pending_ring_idx_t index;
	unsigned int nr_slots, frag_overflow = 0;

	/* At this point shinfo->nr_frags is in fact the number of
	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
	 */
	if (shinfo->nr_frags > MAX_SKB_FRAGS) {
		frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;
		BUG_ON(frag_overflow > MAX_SKB_FRAGS);
		shinfo->nr_frags = MAX_SKB_FRAGS;
	}
	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);

	for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots;
	     shinfo->nr_frags++, txp++, gop++) {
		index = pending_index(vif->pending_cons++);
		pending_idx = vif->pending_ring[index];
		xenvif_tx_create_gop(vif, pending_idx, txp, gop);
		frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
	}

	if (frag_overflow) {
		struct sk_buff *nskb = xenvif_alloc_skb(0);
		if (unlikely(nskb == NULL)) {
			if (net_ratelimit())
				netdev_err(vif->dev,
					   "Can't allocate the frag_list skb.\n");
			return NULL;
		}

		shinfo = skb_shinfo(nskb);
		frags = shinfo->frags;

		for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow;
		     shinfo->nr_frags++, txp++, gop++) {
			index = pending_index(vif->pending_cons++);
			pending_idx = vif->pending_ring[index];
			xenvif_tx_create_gop(vif, pending_idx, txp, gop);
			frag_set_pending_idx(&frags[shinfo->nr_frags],
					     pending_idx);
		}

		skb_shinfo(skb)->frag_list = nskb;
	}

	return gop;
}

static inline void xenvif_grant_handle_set(struct xenvif *vif,
					   u16 pending_idx,
					   grant_handle_t handle)
{
	if (unlikely(vif->grant_tx_handle[pending_idx] !=
		     NETBACK_INVALID_HANDLE)) {
		netdev_err(vif->dev,
			   "Trying to overwrite active handle! pending_idx: %x\n",
			   pending_idx);
		BUG();
	}
	vif->grant_tx_handle[pending_idx] = handle;
}

static inline void xenvif_grant_handle_reset(struct xenvif *vif,
					     u16 pending_idx)
{
	if (unlikely(vif->grant_tx_handle[pending_idx] ==
		     NETBACK_INVALID_HANDLE)) {
		netdev_err(vif->dev,
			   "Trying to unmap invalid handle! pending_idx: %x\n",
			   pending_idx);
		BUG();
	}
	vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE;
}

static int xenvif_tx_check_gop(struct xenvif *vif,
			       struct sk_buff *skb,
			       struct gnttab_map_grant_ref **gopp)
{
	struct gnttab_map_grant_ref *gop = *gopp;
	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	struct pending_tx_info *tx_info;
	int nr_frags = shinfo->nr_frags;
	int i, err, start;
	struct sk_buff *first_skb = NULL;

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

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

check_frags:
	for (i = start; i < nr_frags; i++) {
		int j, newerr;

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

		/* Check error status: if okay then remember grant handle. */
		newerr = (++gop)->status;

		if (likely(!newerr)) {
			xenvif_grant_handle_set(vif, pending_idx , gop->handle);
			/* Had a previous error? Invalidate this fragment. */
			if (unlikely(err))
				xenvif_idx_unmap(vif, pending_idx);
			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. */
		if (!first_skb)
			pending_idx = XENVIF_TX_CB(skb)->pending_idx;
		else
			pending_idx = XENVIF_TX_CB(skb)->pending_idx;
		xenvif_idx_unmap(vif, pending_idx);
		for (j = start; j < i; j++) {
			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
			xenvif_idx_unmap(vif, pending_idx);
		}

		/* Remember the error: invalidate all subsequent fragments. */
		err = newerr;
	}

	if (skb_has_frag_list(skb)) {
		first_skb = skb;
		skb = shinfo->frag_list;
		shinfo = skb_shinfo(skb);
		nr_frags = shinfo->nr_frags;
		start = 0;

		goto check_frags;
	}

	/* There was a mapping error in the frag_list skb. We have to unmap
	 * the first skb's frags
	 */
	if (first_skb && err) {
		int j;
		shinfo = skb_shinfo(first_skb);
		pending_idx = XENVIF_TX_CB(skb)->pending_idx;
		start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx);
		for (j = start; j < shinfo->nr_frags; j++) {
			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
			xenvif_idx_unmap(vif, pending_idx);
		}
	}

	*gopp = gop + 1;
	return err;
}

static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
{
	struct skb_shared_info *shinfo = skb_shinfo(skb);
	int nr_frags = shinfo->nr_frags;
	int i;
	u16 prev_pending_idx = INVALID_PENDING_IDX;

	if (skb_shinfo(skb)->destructor_arg)
		prev_pending_idx = XENVIF_TX_CB(skb)->pending_idx;

	for (i = 0; i < nr_frags; i++) {
		skb_frag_t *frag = shinfo->frags + i;
		struct xen_netif_tx_request *txp;
		struct page *page;
		u16 pending_idx;

		pending_idx = frag_get_pending_idx(frag);

		/* If this is not the first frag, chain it to the previous*/
		if (unlikely(prev_pending_idx == INVALID_PENDING_IDX))
			skb_shinfo(skb)->destructor_arg =
				&vif->pending_tx_info[pending_idx].callback_struct;
		else if (likely(pending_idx != prev_pending_idx))
			vif->pending_tx_info[prev_pending_idx].callback_struct.ctx =
				&(vif->pending_tx_info[pending_idx].callback_struct);

		vif->pending_tx_info[pending_idx].callback_struct.ctx = NULL;
		prev_pending_idx = pending_idx;

		txp = &vif->pending_tx_info[pending_idx].req;
		page = virt_to_page(idx_to_kaddr(vif, pending_idx));
		__skb_fill_page_desc(skb, i, page, txp->offset, txp->size);
		skb->len += txp->size;
		skb->data_len += txp->size;
		skb->truesize += txp->size;

		/* Take an extra reference to offset network stack's put_page */
		get_page(vif->mmap_pages[pending_idx]);
	}
	/* FIXME: __skb_fill_page_desc set this to true because page->pfmemalloc
	 * overlaps with "index", and "mapping" is not set. I think mapping
	 * should be set. If delivered to local stack, it would drop this
	 * skb in sk_filter unless the socket has the right to use it.
	 */
	skb->pfmemalloc	= false;
}

static int xenvif_get_extras(struct xenvif *vif,
				struct xen_netif_extra_info *extras,
				int work_to_do)
{
	struct xen_netif_extra_info extra;
	RING_IDX cons = vif->tx.req_cons;

	do {
		if (unlikely(work_to_do-- <= 0)) {
			netdev_err(vif->dev, "Missing extra info\n");
			xenvif_fatal_tx_err(vif);
			return -EBADR;
		}

		memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons),
		       sizeof(extra));
		if (unlikely(!extra.type ||
			     extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
			vif->tx.req_cons = ++cons;
			netdev_err(vif->dev,
				   "Invalid extra type: %d\n", extra.type);
			xenvif_fatal_tx_err(vif);
			return -EINVAL;
		}

		memcpy(&extras[extra.type - 1], &extra, sizeof(extra));
		vif->tx.req_cons = ++cons;
	} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);

	return work_to_do;
}

static int xenvif_set_skb_gso(struct xenvif *vif,
			      struct sk_buff *skb,
			      struct xen_netif_extra_info *gso)
{
	if (!gso->u.gso.size) {
		netdev_err(vif->dev, "GSO size must not be zero.\n");
		xenvif_fatal_tx_err(vif);
		return -EINVAL;
	}

	switch (gso->u.gso.type) {
	case XEN_NETIF_GSO_TYPE_TCPV4:
		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
		break;
	case XEN_NETIF_GSO_TYPE_TCPV6:
		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
		break;
	default:
		netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type);
		xenvif_fatal_tx_err(vif);
		return -EINVAL;
	}

	skb_shinfo(skb)->gso_size = gso->u.gso.size;
	/* gso_segs will be calculated later */

	return 0;
}

static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
{
	bool recalculate_partial_csum = false;

	/* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy
	 * peers can fail to set NETRXF_csum_blank when sending a GSO
	 * frame. In this case force the SKB to CHECKSUM_PARTIAL and
	 * recalculate the partial checksum.
	 */
	if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
		vif->rx_gso_checksum_fixup++;
		skb->ip_summed = CHECKSUM_PARTIAL;
		recalculate_partial_csum = true;
	}

	/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
	if (skb->ip_summed != CHECKSUM_PARTIAL)
		return 0;

	return skb_checksum_setup(skb, recalculate_partial_csum);
}

static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
{
	u64 now = get_jiffies_64();
	u64 next_credit = vif->credit_window_start +
		msecs_to_jiffies(vif->credit_usec / 1000);

	/* Timer could already be pending in rare cases. */
	if (timer_pending(&vif->credit_timeout))
		return true;

	/* Passed the point where we can replenish credit? */
	if (time_after_eq64(now, next_credit)) {
		vif->credit_window_start = now;
		tx_add_credit(vif);
	}

	/* Still too big to send right now? Set a callback. */
	if (size > vif->remaining_credit) {
		vif->credit_timeout.data     =
			(unsigned long)vif;
		vif->credit_timeout.function =
			tx_credit_callback;
		mod_timer(&vif->credit_timeout,
			  next_credit);
		vif->credit_window_start = next_credit;

		return true;
	}

	return false;
}

static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
{
	struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop;
	struct sk_buff *skb;
	int ret;

	while (skb_queue_len(&vif->tx_queue) < budget) {
		struct xen_netif_tx_request txreq;
		struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX];
		struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1];
		u16 pending_idx;
		RING_IDX idx;
		int work_to_do;
		unsigned int data_len;
		pending_ring_idx_t index;

		if (vif->tx.sring->req_prod - vif->tx.req_cons >
		    XEN_NETIF_TX_RING_SIZE) {
			netdev_err(vif->dev,
				   "Impossible number of requests. "
				   "req_prod %d, req_cons %d, size %ld\n",
				   vif->tx.sring->req_prod, vif->tx.req_cons,
				   XEN_NETIF_TX_RING_SIZE);
			xenvif_fatal_tx_err(vif);
			continue;
		}

		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
		if (!work_to_do)
			break;

		idx = vif->tx.req_cons;
		rmb(); /* Ensure that we see the request before we copy it. */
		memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq));

		/* Credit-based scheduling. */
		if (txreq.size > vif->remaining_credit &&
		    tx_credit_exceeded(vif, txreq.size))
			break;

		vif->remaining_credit -= txreq.size;

		work_to_do--;
		vif->tx.req_cons = ++idx;

		memset(extras, 0, sizeof(extras));
		if (txreq.flags & XEN_NETTXF_extra_info) {
			work_to_do = xenvif_get_extras(vif, extras,
						       work_to_do);
			idx = vif->tx.req_cons;
			if (unlikely(work_to_do < 0))