linux/drivers/net/xen-netfront.c
Linus Torvalds 1ee2dcc224 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net
Pull networking fixes from David Miller:
 "Mostly these are fixes for fallout due to merge window changes, as
  well as cures for problems that have been with us for a much longer
  period of time"

 1) Johannes Berg noticed two major deficiencies in our genetlink
    registration.  Some genetlink protocols we passing in constant
    counts for their ops array rather than something like
    ARRAY_SIZE(ops) or similar.  Also, some genetlink protocols were
    using fixed IDs for their multicast groups.

    We have to retain these fixed IDs to keep existing userland tools
    working, but reserve them so that other multicast groups used by
    other protocols can not possibly conflict.

    In dealing with these two problems, we actually now use less state
    management for genetlink operations and multicast groups.

 2) When configuring interface hardware timestamping, fix several
    drivers that simply do not validate that the hwtstamp_config value
    is one the driver actually supports.  From Ben Hutchings.

 3) Invalid memory references in mwifiex driver, from Amitkumar Karwar.

 4) In dev_forward_skb(), set the skb->protocol in the right order
    relative to skb_scrub_packet().  From Alexei Starovoitov.

 5) Bridge erroneously fails to use the proper wrapper functions to make
    calls to netdev_ops->ndo_vlan_rx_{add,kill}_vid.  Fix from Toshiaki
    Makita.

 6) When detaching a bridge port, make sure to flush all VLAN IDs to
    prevent them from leaking, also from Toshiaki Makita.

 7) Put in a compromise for TCP Small Queues so that deep queued devices
    that delay TX reclaim non-trivially don't have such a performance
    decrease.  One particularly problematic area is 802.11 AMPDU in
    wireless.  From Eric Dumazet.

 8) Fix crashes in tcp_fastopen_cache_get(), we can see NULL socket dsts
    here.  Fix from Eric Dumzaet, reported by Dave Jones.

 9) Fix use after free in ipv6 SIT driver, from Willem de Bruijn.

10) When computing mergeable buffer sizes, virtio-net fails to take the
    virtio-net header into account.  From Michael Dalton.

11) Fix seqlock deadlock in ip4_datagram_connect() wrt.  statistic
    bumping, this one has been with us for a while.  From Eric Dumazet.

12) Fix NULL deref in the new TIPC fragmentation handling, from Erik
    Hugne.

13) 6lowpan bit used for traffic classification was wrong, from Jukka
    Rissanen.

14) macvlan has the same issue as normal vlans did wrt.  propagating LRO
    disabling down to the real device, fix it the same way.  From Michal
    Kubecek.

15) CPSW driver needs to soft reset all slaves during suspend, from
    Daniel Mack.

16) Fix small frame pacing in FQ packet scheduler, from Eric Dumazet.

17) The xen-netfront RX buffer refill timer isn't properly scheduled on
    partial RX allocation success, from Ma JieYue.

18) When ipv6 ping protocol support was added, the AF_INET6 protocol
    initialization cleanup path on failure was borked a little.  Fix
    from Vlad Yasevich.

19) If a socket disconnects during a read/recvmsg/recvfrom/etc that
    blocks we can do the wrong thing with the msg_name we write back to
    userspace.  From Hannes Frederic Sowa.  There is another fix in the
    works from Hannes which will prevent future problems of this nature.

20) Fix route leak in VTI tunnel transmit, from Fan Du.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (106 commits)
  genetlink: make multicast groups const, prevent abuse
  genetlink: pass family to functions using groups
  genetlink: add and use genl_set_err()
  genetlink: remove family pointer from genl_multicast_group
  genetlink: remove genl_unregister_mc_group()
  hsr: don't call genl_unregister_mc_group()
  quota/genetlink: use proper genetlink multicast APIs
  drop_monitor/genetlink: use proper genetlink multicast APIs
  genetlink: only pass array to genl_register_family_with_ops()
  tcp: don't update snd_nxt, when a socket is switched from repair mode
  atm: idt77252: fix dev refcnt leak
  xfrm: Release dst if this dst is improper for vti tunnel
  netlink: fix documentation typo in netlink_set_err()
  be2net: Delete secondary unicast MAC addresses during be_close
  be2net: Fix unconditional enabling of Rx interface options
  net, virtio_net: replace the magic value
  ping: prevent NULL pointer dereference on write to msg_name
  bnx2x: Prevent "timeout waiting for state X"
  bnx2x: prevent CFC attention
  bnx2x: Prevent panic during DMAE timeout
  ...
2013-11-19 15:50:47 -08:00

2138 lines
52 KiB
C

/*
* Virtual network driver for conversing with remote driver backends.
*
* Copyright (c) 2002-2005, K A Fraser
* Copyright (c) 2005, XenSource Ltd
*
* 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.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/ethtool.h>
#include <linux/if_ether.h>
#include <net/tcp.h>
#include <linux/udp.h>
#include <linux/moduleparam.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <net/ip.h>
#include <asm/xen/page.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/events.h>
#include <xen/page.h>
#include <xen/platform_pci.h>
#include <xen/grant_table.h>
#include <xen/interface/io/netif.h>
#include <xen/interface/memory.h>
#include <xen/interface/grant_table.h>
static const struct ethtool_ops xennet_ethtool_ops;
struct netfront_cb {
int pull_to;
};
#define NETFRONT_SKB_CB(skb) ((struct netfront_cb *)((skb)->cb))
#define RX_COPY_THRESHOLD 256
#define GRANT_INVALID_REF 0
#define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
#define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
#define TX_MAX_TARGET min_t(int, NET_TX_RING_SIZE, 256)
struct netfront_stats {
u64 rx_packets;
u64 tx_packets;
u64 rx_bytes;
u64 tx_bytes;
struct u64_stats_sync syncp;
};
struct netfront_info {
struct list_head list;
struct net_device *netdev;
struct napi_struct napi;
/* Split event channels support, tx_* == rx_* when using
* single event channel.
*/
unsigned int tx_evtchn, rx_evtchn;
unsigned int tx_irq, rx_irq;
/* Only used when split event channels support is enabled */
char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
struct xenbus_device *xbdev;
spinlock_t tx_lock;
struct xen_netif_tx_front_ring tx;
int tx_ring_ref;
/*
* {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries
* are linked from tx_skb_freelist through skb_entry.link.
*
* NB. Freelist index entries are always going to be less than
* PAGE_OFFSET, whereas pointers to skbs will always be equal or
* greater than PAGE_OFFSET: we use this property to distinguish
* them.
*/
union skb_entry {
struct sk_buff *skb;
unsigned long link;
} tx_skbs[NET_TX_RING_SIZE];
grant_ref_t gref_tx_head;
grant_ref_t grant_tx_ref[NET_TX_RING_SIZE];
unsigned tx_skb_freelist;
spinlock_t rx_lock ____cacheline_aligned_in_smp;
struct xen_netif_rx_front_ring rx;
int rx_ring_ref;
/* Receive-ring batched refills. */
#define RX_MIN_TARGET 8
#define RX_DFL_MIN_TARGET 64
#define RX_MAX_TARGET min_t(int, NET_RX_RING_SIZE, 256)
unsigned rx_min_target, rx_max_target, rx_target;
struct sk_buff_head rx_batch;
struct timer_list rx_refill_timer;
struct sk_buff *rx_skbs[NET_RX_RING_SIZE];
grant_ref_t gref_rx_head;
grant_ref_t grant_rx_ref[NET_RX_RING_SIZE];
unsigned long rx_pfn_array[NET_RX_RING_SIZE];
struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1];
struct mmu_update rx_mmu[NET_RX_RING_SIZE];
/* Statistics */
struct netfront_stats __percpu *stats;
unsigned long rx_gso_checksum_fixup;
};
struct netfront_rx_info {
struct xen_netif_rx_response rx;
struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1];
};
static void skb_entry_set_link(union skb_entry *list, unsigned short id)
{
list->link = id;
}
static int skb_entry_is_link(const union skb_entry *list)
{
BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link));
return (unsigned long)list->skb < PAGE_OFFSET;
}
/*
* Access macros for acquiring freeing slots in tx_skbs[].
*/
static void add_id_to_freelist(unsigned *head, union skb_entry *list,
unsigned short id)
{
skb_entry_set_link(&list[id], *head);
*head = id;
}
static unsigned short get_id_from_freelist(unsigned *head,
union skb_entry *list)
{
unsigned int id = *head;
*head = list[id].link;
return id;
}
static int xennet_rxidx(RING_IDX idx)
{
return idx & (NET_RX_RING_SIZE - 1);
}
static struct sk_buff *xennet_get_rx_skb(struct netfront_info *np,
RING_IDX ri)
{
int i = xennet_rxidx(ri);
struct sk_buff *skb = np->rx_skbs[i];
np->rx_skbs[i] = NULL;
return skb;
}
static grant_ref_t xennet_get_rx_ref(struct netfront_info *np,
RING_IDX ri)
{
int i = xennet_rxidx(ri);
grant_ref_t ref = np->grant_rx_ref[i];
np->grant_rx_ref[i] = GRANT_INVALID_REF;
return ref;
}
#ifdef CONFIG_SYSFS
static int xennet_sysfs_addif(struct net_device *netdev);
static void xennet_sysfs_delif(struct net_device *netdev);
#else /* !CONFIG_SYSFS */
#define xennet_sysfs_addif(dev) (0)
#define xennet_sysfs_delif(dev) do { } while (0)
#endif
static bool xennet_can_sg(struct net_device *dev)
{
return dev->features & NETIF_F_SG;
}
static void rx_refill_timeout(unsigned long data)
{
struct net_device *dev = (struct net_device *)data;
struct netfront_info *np = netdev_priv(dev);
napi_schedule(&np->napi);
}
static int netfront_tx_slot_available(struct netfront_info *np)
{
return (np->tx.req_prod_pvt - np->tx.rsp_cons) <
(TX_MAX_TARGET - MAX_SKB_FRAGS - 2);
}
static void xennet_maybe_wake_tx(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
if (unlikely(netif_queue_stopped(dev)) &&
netfront_tx_slot_available(np) &&
likely(netif_running(dev)))
netif_wake_queue(dev);
}
static void xennet_alloc_rx_buffers(struct net_device *dev)
{
unsigned short id;
struct netfront_info *np = netdev_priv(dev);
struct sk_buff *skb;
struct page *page;
int i, batch_target, notify;
RING_IDX req_prod = np->rx.req_prod_pvt;
grant_ref_t ref;
unsigned long pfn;
void *vaddr;
struct xen_netif_rx_request *req;
if (unlikely(!netif_carrier_ok(dev)))
return;
/*
* Allocate skbuffs greedily, even though we batch updates to the
* receive ring. This creates a less bursty demand on the memory
* allocator, so should reduce the chance of failed allocation requests
* both for ourself and for other kernel subsystems.
*/
batch_target = np->rx_target - (req_prod - np->rx.rsp_cons);
for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) {
skb = __netdev_alloc_skb(dev, RX_COPY_THRESHOLD + NET_IP_ALIGN,
GFP_ATOMIC | __GFP_NOWARN);
if (unlikely(!skb))
goto no_skb;
/* Align ip header to a 16 bytes boundary */
skb_reserve(skb, NET_IP_ALIGN);
page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
if (!page) {
kfree_skb(skb);
no_skb:
/* Could not allocate any skbuffs. Try again later. */
mod_timer(&np->rx_refill_timer,
jiffies + (HZ/10));
/* Any skbuffs queued for refill? Force them out. */
if (i != 0)
goto refill;
break;
}
skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
__skb_queue_tail(&np->rx_batch, skb);
}
/* Is the batch large enough to be worthwhile? */
if (i < (np->rx_target/2)) {
if (req_prod > np->rx.sring->req_prod)
goto push;
return;
}
/* Adjust our fill target if we risked running out of buffers. */
if (((req_prod - np->rx.sring->rsp_prod) < (np->rx_target / 4)) &&
((np->rx_target *= 2) > np->rx_max_target))
np->rx_target = np->rx_max_target;
refill:
for (i = 0; ; i++) {
skb = __skb_dequeue(&np->rx_batch);
if (skb == NULL)
break;
skb->dev = dev;
id = xennet_rxidx(req_prod + i);
BUG_ON(np->rx_skbs[id]);
np->rx_skbs[id] = skb;
ref = gnttab_claim_grant_reference(&np->gref_rx_head);
BUG_ON((signed short)ref < 0);
np->grant_rx_ref[id] = ref;
pfn = page_to_pfn(skb_frag_page(&skb_shinfo(skb)->frags[0]));
vaddr = page_address(skb_frag_page(&skb_shinfo(skb)->frags[0]));
req = RING_GET_REQUEST(&np->rx, req_prod + i);
gnttab_grant_foreign_access_ref(ref,
np->xbdev->otherend_id,
pfn_to_mfn(pfn),
0);
req->id = id;
req->gref = ref;
}
wmb(); /* barrier so backend seens requests */
/* Above is a suitable barrier to ensure backend will see requests. */
np->rx.req_prod_pvt = req_prod + i;
push:
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->rx, notify);
if (notify)
notify_remote_via_irq(np->rx_irq);
}
static int xennet_open(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
napi_enable(&np->napi);
spin_lock_bh(&np->rx_lock);
if (netif_carrier_ok(dev)) {
xennet_alloc_rx_buffers(dev);
np->rx.sring->rsp_event = np->rx.rsp_cons + 1;
if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
napi_schedule(&np->napi);
}
spin_unlock_bh(&np->rx_lock);
netif_start_queue(dev);
return 0;
}
static void xennet_tx_buf_gc(struct net_device *dev)
{
RING_IDX cons, prod;
unsigned short id;
struct netfront_info *np = netdev_priv(dev);
struct sk_buff *skb;
BUG_ON(!netif_carrier_ok(dev));
do {
prod = np->tx.sring->rsp_prod;
rmb(); /* Ensure we see responses up to 'rp'. */
for (cons = np->tx.rsp_cons; cons != prod; cons++) {
struct xen_netif_tx_response *txrsp;
txrsp = RING_GET_RESPONSE(&np->tx, cons);
if (txrsp->status == XEN_NETIF_RSP_NULL)
continue;
id = txrsp->id;
skb = np->tx_skbs[id].skb;
if (unlikely(gnttab_query_foreign_access(
np->grant_tx_ref[id]) != 0)) {
pr_alert("%s: warning -- grant still in use by backend domain\n",
__func__);
BUG();
}
gnttab_end_foreign_access_ref(
np->grant_tx_ref[id], GNTMAP_readonly);
gnttab_release_grant_reference(
&np->gref_tx_head, np->grant_tx_ref[id]);
np->grant_tx_ref[id] = GRANT_INVALID_REF;
add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, id);
dev_kfree_skb_irq(skb);
}
np->tx.rsp_cons = prod;
/*
* Set a new event, then check for race with update of tx_cons.
* Note that it is essential to schedule a callback, no matter
* how few buffers are pending. Even if there is space in the
* transmit ring, higher layers may be blocked because too much
* data is outstanding: in such cases notification from Xen is
* likely to be the only kick that we'll get.
*/
np->tx.sring->rsp_event =
prod + ((np->tx.sring->req_prod - prod) >> 1) + 1;
mb(); /* update shared area */
} while ((cons == prod) && (prod != np->tx.sring->rsp_prod));
xennet_maybe_wake_tx(dev);
}
static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
struct xen_netif_tx_request *tx)
{
struct netfront_info *np = netdev_priv(dev);
char *data = skb->data;
unsigned long mfn;
RING_IDX prod = np->tx.req_prod_pvt;
int frags = skb_shinfo(skb)->nr_frags;
unsigned int offset = offset_in_page(data);
unsigned int len = skb_headlen(skb);
unsigned int id;
grant_ref_t ref;
int i;
/* While the header overlaps a page boundary (including being
larger than a page), split it it into page-sized chunks. */
while (len > PAGE_SIZE - offset) {
tx->size = PAGE_SIZE - offset;
tx->flags |= XEN_NETTXF_more_data;
len -= tx->size;
data += tx->size;
offset = 0;
id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
np->tx_skbs[id].skb = skb_get(skb);
tx = RING_GET_REQUEST(&np->tx, prod++);
tx->id = id;
ref = gnttab_claim_grant_reference(&np->gref_tx_head);
BUG_ON((signed short)ref < 0);
mfn = virt_to_mfn(data);
gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id,
mfn, GNTMAP_readonly);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = len;
tx->flags = 0;
}
/* Grant backend access to each skb fragment page. */
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
struct page *page = skb_frag_page(frag);
len = skb_frag_size(frag);
offset = frag->page_offset;
/* Data must not cross a page boundary. */
BUG_ON(len + offset > PAGE_SIZE<<compound_order(page));
/* Skip unused frames from start of page */
page += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
while (len > 0) {
unsigned long bytes;
BUG_ON(offset >= PAGE_SIZE);
bytes = PAGE_SIZE - offset;
if (bytes > len)
bytes = len;
tx->flags |= XEN_NETTXF_more_data;
id = get_id_from_freelist(&np->tx_skb_freelist,
np->tx_skbs);
np->tx_skbs[id].skb = skb_get(skb);
tx = RING_GET_REQUEST(&np->tx, prod++);
tx->id = id;
ref = gnttab_claim_grant_reference(&np->gref_tx_head);
BUG_ON((signed short)ref < 0);
mfn = pfn_to_mfn(page_to_pfn(page));
gnttab_grant_foreign_access_ref(ref,
np->xbdev->otherend_id,
mfn, GNTMAP_readonly);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = bytes;
tx->flags = 0;
offset += bytes;
len -= bytes;
/* Next frame */
if (offset == PAGE_SIZE && len) {
BUG_ON(!PageCompound(page));
page++;
offset = 0;
}
}
}
np->tx.req_prod_pvt = prod;
}
/*
* Count how many ring slots are required to send the frags of this
* skb. Each frag might be a compound page.
*/
static int xennet_count_skb_frag_slots(struct sk_buff *skb)
{
int i, frags = skb_shinfo(skb)->nr_frags;
int pages = 0;
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
unsigned long size = skb_frag_size(frag);
unsigned long offset = frag->page_offset;
/* Skip unused frames from start of page */
offset &= ~PAGE_MASK;
pages += PFN_UP(offset + size);
}
return pages;
}
static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
unsigned short id;
struct netfront_info *np = netdev_priv(dev);
struct netfront_stats *stats = this_cpu_ptr(np->stats);
struct xen_netif_tx_request *tx;
char *data = skb->data;
RING_IDX i;
grant_ref_t ref;
unsigned long mfn;
int notify;
int slots;
unsigned int offset = offset_in_page(data);
unsigned int len = skb_headlen(skb);
unsigned long flags;
/* If skb->len is too big for wire format, drop skb and alert
* user about misconfiguration.
*/
if (unlikely(skb->len > XEN_NETIF_MAX_TX_SIZE)) {
net_alert_ratelimited(
"xennet: skb->len = %u, too big for wire format\n",
skb->len);
goto drop;
}
slots = DIV_ROUND_UP(offset + len, PAGE_SIZE) +
xennet_count_skb_frag_slots(skb);
if (unlikely(slots > MAX_SKB_FRAGS + 1)) {
net_alert_ratelimited(
"xennet: skb rides the rocket: %d slots\n", slots);
goto drop;
}
spin_lock_irqsave(&np->tx_lock, flags);
if (unlikely(!netif_carrier_ok(dev) ||
(slots > 1 && !xennet_can_sg(dev)) ||
netif_needs_gso(skb, netif_skb_features(skb)))) {
spin_unlock_irqrestore(&np->tx_lock, flags);
goto drop;
}
i = np->tx.req_prod_pvt;
id = get_id_from_freelist(&np->tx_skb_freelist, np->tx_skbs);
np->tx_skbs[id].skb = skb;
tx = RING_GET_REQUEST(&np->tx, i);
tx->id = id;
ref = gnttab_claim_grant_reference(&np->gref_tx_head);
BUG_ON((signed short)ref < 0);
mfn = virt_to_mfn(data);
gnttab_grant_foreign_access_ref(
ref, np->xbdev->otherend_id, mfn, GNTMAP_readonly);
tx->gref = np->grant_tx_ref[id] = ref;
tx->offset = offset;
tx->size = len;
tx->flags = 0;
if (skb->ip_summed == CHECKSUM_PARTIAL)
/* local packet? */
tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
/* remote but checksummed. */
tx->flags |= XEN_NETTXF_data_validated;
if (skb_shinfo(skb)->gso_size) {
struct xen_netif_extra_info *gso;
gso = (struct xen_netif_extra_info *)
RING_GET_REQUEST(&np->tx, ++i);
tx->flags |= XEN_NETTXF_extra_info;
gso->u.gso.size = skb_shinfo(skb)->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;
}
np->tx.req_prod_pvt = i + 1;
xennet_make_frags(skb, dev, tx);
tx->size = skb->len;
RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->tx, notify);
if (notify)
notify_remote_via_irq(np->tx_irq);
u64_stats_update_begin(&stats->syncp);
stats->tx_bytes += skb->len;
stats->tx_packets++;
u64_stats_update_end(&stats->syncp);
/* Note: It is not safe to access skb after xennet_tx_buf_gc()! */
xennet_tx_buf_gc(dev);
if (!netfront_tx_slot_available(np))
netif_stop_queue(dev);
spin_unlock_irqrestore(&np->tx_lock, flags);
return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static int xennet_close(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
netif_stop_queue(np->netdev);
napi_disable(&np->napi);
return 0;
}
static void xennet_move_rx_slot(struct netfront_info *np, struct sk_buff *skb,
grant_ref_t ref)
{
int new = xennet_rxidx(np->rx.req_prod_pvt);
BUG_ON(np->rx_skbs[new]);
np->rx_skbs[new] = skb;
np->grant_rx_ref[new] = ref;
RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->id = new;
RING_GET_REQUEST(&np->rx, np->rx.req_prod_pvt)->gref = ref;
np->rx.req_prod_pvt++;
}
static int xennet_get_extras(struct netfront_info *np,
struct xen_netif_extra_info *extras,
RING_IDX rp)
{
struct xen_netif_extra_info *extra;
struct device *dev = &np->netdev->dev;
RING_IDX cons = np->rx.rsp_cons;
int err = 0;
do {
struct sk_buff *skb;
grant_ref_t ref;
if (unlikely(cons + 1 == rp)) {
if (net_ratelimit())
dev_warn(dev, "Missing extra info\n");
err = -EBADR;
break;
}
extra = (struct xen_netif_extra_info *)
RING_GET_RESPONSE(&np->rx, ++cons);
if (unlikely(!extra->type ||
extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
if (net_ratelimit())
dev_warn(dev, "Invalid extra type: %d\n",
extra->type);
err = -EINVAL;
} else {
memcpy(&extras[extra->type - 1], extra,
sizeof(*extra));
}
skb = xennet_get_rx_skb(np, cons);
ref = xennet_get_rx_ref(np, cons);
xennet_move_rx_slot(np, skb, ref);
} while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE);
np->rx.rsp_cons = cons;
return err;
}
static int xennet_get_responses(struct netfront_info *np,
struct netfront_rx_info *rinfo, RING_IDX rp,
struct sk_buff_head *list)
{
struct xen_netif_rx_response *rx = &rinfo->rx;
struct xen_netif_extra_info *extras = rinfo->extras;
struct device *dev = &np->netdev->dev;
RING_IDX cons = np->rx.rsp_cons;
struct sk_buff *skb = xennet_get_rx_skb(np, cons);
grant_ref_t ref = xennet_get_rx_ref(np, cons);
int max = MAX_SKB_FRAGS + (rx->status <= RX_COPY_THRESHOLD);
int slots = 1;
int err = 0;
unsigned long ret;
if (rx->flags & XEN_NETRXF_extra_info) {
err = xennet_get_extras(np, extras, rp);
cons = np->rx.rsp_cons;
}
for (;;) {
if (unlikely(rx->status < 0 ||
rx->offset + rx->status > PAGE_SIZE)) {
if (net_ratelimit())
dev_warn(dev, "rx->offset: %x, size: %u\n",
rx->offset, rx->status);
xennet_move_rx_slot(np, skb, ref);
err = -EINVAL;
goto next;
}
/*
* This definitely indicates a bug, either in this driver or in
* the backend driver. In future this should flag the bad
* situation to the system controller to reboot the backend.
*/
if (ref == GRANT_INVALID_REF) {
if (net_ratelimit())
dev_warn(dev, "Bad rx response id %d.\n",
rx->id);
err = -EINVAL;
goto next;
}
ret = gnttab_end_foreign_access_ref(ref, 0);
BUG_ON(!ret);
gnttab_release_grant_reference(&np->gref_rx_head, ref);
__skb_queue_tail(list, skb);
next:
if (!(rx->flags & XEN_NETRXF_more_data))
break;
if (cons + slots == rp) {
if (net_ratelimit())
dev_warn(dev, "Need more slots\n");
err = -ENOENT;
break;
}
rx = RING_GET_RESPONSE(&np->rx, cons + slots);
skb = xennet_get_rx_skb(np, cons + slots);
ref = xennet_get_rx_ref(np, cons + slots);
slots++;
}
if (unlikely(slots > max)) {
if (net_ratelimit())
dev_warn(dev, "Too many slots\n");
err = -E2BIG;
}
if (unlikely(err))
np->rx.rsp_cons = cons + slots;
return err;
}
static int xennet_set_skb_gso(struct sk_buff *skb,
struct xen_netif_extra_info *gso)
{
if (!gso->u.gso.size) {
if (net_ratelimit())
pr_warn("GSO size must not be zero\n");
return -EINVAL;
}
/* Currently only TCPv4 S.O. is supported. */
if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) {
if (net_ratelimit())
pr_warn("Bad GSO type %d\n", gso->u.gso.type);
return -EINVAL;
}
skb_shinfo(skb)->gso_size = gso->u.gso.size;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
/* Header must be checked, and gso_segs computed. */
skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
skb_shinfo(skb)->gso_segs = 0;
return 0;
}
static RING_IDX xennet_fill_frags(struct netfront_info *np,
struct sk_buff *skb,
struct sk_buff_head *list)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
RING_IDX cons = np->rx.rsp_cons;
struct sk_buff *nskb;
while ((nskb = __skb_dequeue(list))) {
struct xen_netif_rx_response *rx =
RING_GET_RESPONSE(&np->rx, ++cons);
skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0];
if (shinfo->nr_frags == MAX_SKB_FRAGS) {
unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
BUG_ON(pull_to <= skb_headlen(skb));
__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
}
BUG_ON(shinfo->nr_frags >= MAX_SKB_FRAGS);
skb_add_rx_frag(skb, shinfo->nr_frags, skb_frag_page(nfrag),
rx->offset, rx->status, PAGE_SIZE);
skb_shinfo(nskb)->nr_frags = 0;
kfree_skb(nskb);
}
return cons;
}
static int checksum_setup(struct net_device *dev, struct sk_buff *skb)
{
struct iphdr *iph;
int err = -EPROTO;
int recalculate_partial_csum = 0;
/*
* 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)) {
struct netfront_info *np = netdev_priv(dev);
np->rx_gso_checksum_fixup++;
skb->ip_summed = CHECKSUM_PARTIAL;
recalculate_partial_csum = 1;
}
/* A non-CHECKSUM_PARTIAL SKB does not require setup. */
if (skb->ip_summed != CHECKSUM_PARTIAL)
return 0;
if (skb->protocol != htons(ETH_P_IP))
goto out;
iph = (void *)skb->data;
switch (iph->protocol) {
case IPPROTO_TCP:
if (!skb_partial_csum_set(skb, 4 * iph->ihl,
offsetof(struct tcphdr, check)))
goto out;
if (recalculate_partial_csum) {
struct tcphdr *tcph = tcp_hdr(skb);
tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
skb->len - iph->ihl*4,
IPPROTO_TCP, 0);
}
break;
case IPPROTO_UDP:
if (!skb_partial_csum_set(skb, 4 * iph->ihl,
offsetof(struct udphdr, check)))
goto out;
if (recalculate_partial_csum) {
struct udphdr *udph = udp_hdr(skb);
udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
skb->len - iph->ihl*4,
IPPROTO_UDP, 0);
}
break;
default:
if (net_ratelimit())
pr_err("Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n",
iph->protocol);
goto out;
}
err = 0;
out:
return err;
}
static int handle_incoming_queue(struct net_device *dev,
struct sk_buff_head *rxq)
{
struct netfront_info *np = netdev_priv(dev);
struct netfront_stats *stats = this_cpu_ptr(np->stats);
int packets_dropped = 0;
struct sk_buff *skb;
while ((skb = __skb_dequeue(rxq)) != NULL) {
int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
if (pull_to > skb_headlen(skb))
__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
/* Ethernet work: Delayed to here as it peeks the header. */
skb->protocol = eth_type_trans(skb, dev);
if (checksum_setup(dev, skb)) {
kfree_skb(skb);
packets_dropped++;
dev->stats.rx_errors++;
continue;
}
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
/* Pass it up. */
napi_gro_receive(&np->napi, skb);
}
return packets_dropped;
}
static int xennet_poll(struct napi_struct *napi, int budget)
{
struct netfront_info *np = container_of(napi, struct netfront_info, napi);
struct net_device *dev = np->netdev;
struct sk_buff *skb;
struct netfront_rx_info rinfo;
struct xen_netif_rx_response *rx = &rinfo.rx;
struct xen_netif_extra_info *extras = rinfo.extras;
RING_IDX i, rp;
int work_done;
struct sk_buff_head rxq;
struct sk_buff_head errq;
struct sk_buff_head tmpq;
unsigned long flags;
int err;
spin_lock(&np->rx_lock);
skb_queue_head_init(&rxq);
skb_queue_head_init(&errq);
skb_queue_head_init(&tmpq);
rp = np->rx.sring->rsp_prod;
rmb(); /* Ensure we see queued responses up to 'rp'. */
i = np->rx.rsp_cons;
work_done = 0;
while ((i != rp) && (work_done < budget)) {
memcpy(rx, RING_GET_RESPONSE(&np->rx, i), sizeof(*rx));
memset(extras, 0, sizeof(rinfo.extras));
err = xennet_get_responses(np, &rinfo, rp, &tmpq);
if (unlikely(err)) {
err:
while ((skb = __skb_dequeue(&tmpq)))
__skb_queue_tail(&errq, skb);
dev->stats.rx_errors++;
i = np->rx.rsp_cons;
continue;
}
skb = __skb_dequeue(&tmpq);
if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
struct xen_netif_extra_info *gso;
gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
if (unlikely(xennet_set_skb_gso(skb, gso))) {
__skb_queue_head(&tmpq, skb);
np->rx.rsp_cons += skb_queue_len(&tmpq);
goto err;
}
}
NETFRONT_SKB_CB(skb)->pull_to = rx->status;
if (NETFRONT_SKB_CB(skb)->pull_to > RX_COPY_THRESHOLD)
NETFRONT_SKB_CB(skb)->pull_to = RX_COPY_THRESHOLD;
skb_shinfo(skb)->frags[0].page_offset = rx->offset;
skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status);
skb->data_len = rx->status;
skb->len += rx->status;
i = xennet_fill_frags(np, skb, &tmpq);
if (rx->flags & XEN_NETRXF_csum_blank)
skb->ip_summed = CHECKSUM_PARTIAL;
else if (rx->flags & XEN_NETRXF_data_validated)
skb->ip_summed = CHECKSUM_UNNECESSARY;
__skb_queue_tail(&rxq, skb);
np->rx.rsp_cons = ++i;
work_done++;
}
__skb_queue_purge(&errq);
work_done -= handle_incoming_queue(dev, &rxq);
/* If we get a callback with very few responses, reduce fill target. */
/* NB. Note exponential increase, linear decrease. */
if (((np->rx.req_prod_pvt - np->rx.sring->rsp_prod) >
((3*np->rx_target) / 4)) &&
(--np->rx_target < np->rx_min_target))
np->rx_target = np->rx_min_target;
xennet_alloc_rx_buffers(dev);
if (work_done < budget) {
int more_to_do = 0;
napi_gro_flush(napi, false);
local_irq_save(flags);
RING_FINAL_CHECK_FOR_RESPONSES(&np->rx, more_to_do);
if (!more_to_do)
__napi_complete(napi);
local_irq_restore(flags);
}
spin_unlock(&np->rx_lock);
return work_done;
}
static int xennet_change_mtu(struct net_device *dev, int mtu)
{
int max = xennet_can_sg(dev) ?
XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER : ETH_DATA_LEN;
if (mtu > max)
return -EINVAL;
dev->mtu = mtu;
return 0;
}
static struct rtnl_link_stats64 *xennet_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
struct netfront_info *np = netdev_priv(dev);
int cpu;
for_each_possible_cpu(cpu) {
struct netfront_stats *stats = per_cpu_ptr(np->stats, cpu);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&stats->syncp);
rx_packets = stats->rx_packets;
tx_packets = stats->tx_packets;
rx_bytes = stats->rx_bytes;
tx_bytes = stats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->rx_errors = dev->stats.rx_errors;
tot->tx_dropped = dev->stats.tx_dropped;
return tot;
}
static void xennet_release_tx_bufs(struct netfront_info *np)
{
struct sk_buff *skb;
int i;
for (i = 0; i < NET_TX_RING_SIZE; i++) {
/* Skip over entries which are actually freelist references */
if (skb_entry_is_link(&np->tx_skbs[i]))
continue;
skb = np->tx_skbs[i].skb;
gnttab_end_foreign_access_ref(np->grant_tx_ref[i],
GNTMAP_readonly);
gnttab_release_grant_reference(&np->gref_tx_head,
np->grant_tx_ref[i]);
np->grant_tx_ref[i] = GRANT_INVALID_REF;
add_id_to_freelist(&np->tx_skb_freelist, np->tx_skbs, i);
dev_kfree_skb_irq(skb);
}
}
static void xennet_release_rx_bufs(struct netfront_info *np)
{
struct mmu_update *mmu = np->rx_mmu;
struct multicall_entry *mcl = np->rx_mcl;
struct sk_buff_head free_list;
struct sk_buff *skb;
unsigned long mfn;
int xfer = 0, noxfer = 0, unused = 0;
int id, ref;
dev_warn(&np->netdev->dev, "%s: fix me for copying receiver.\n",
__func__);
return;
skb_queue_head_init(&free_list);
spin_lock_bh(&np->rx_lock);
for (id = 0; id < NET_RX_RING_SIZE; id++) {
ref = np->grant_rx_ref[id];
if (ref == GRANT_INVALID_REF) {
unused++;
continue;
}
skb = np->rx_skbs[id];
mfn = gnttab_end_foreign_transfer_ref(ref);
gnttab_release_grant_reference(&np->gref_rx_head, ref);
np->grant_rx_ref[id] = GRANT_INVALID_REF;
if (0 == mfn) {
skb_shinfo(skb)->nr_frags = 0;
dev_kfree_skb(skb);
noxfer++;
continue;
}
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
/* Remap the page. */
const struct page *page =
skb_frag_page(&skb_shinfo(skb)->frags[0]);
unsigned long pfn = page_to_pfn(page);
void *vaddr = page_address(page);
MULTI_update_va_mapping(mcl, (unsigned long)vaddr,
mfn_pte(mfn, PAGE_KERNEL),
0);
mcl++;
mmu->ptr = ((u64)mfn << PAGE_SHIFT)
| MMU_MACHPHYS_UPDATE;
mmu->val = pfn;
mmu++;
set_phys_to_machine(pfn, mfn);
}
__skb_queue_tail(&free_list, skb);
xfer++;
}
dev_info(&np->netdev->dev, "%s: %d xfer, %d noxfer, %d unused\n",
__func__, xfer, noxfer, unused);
if (xfer) {
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
/* Do all the remapping work and M2P updates. */
MULTI_mmu_update(mcl, np->rx_mmu, mmu - np->rx_mmu,
NULL, DOMID_SELF);
mcl++;
HYPERVISOR_multicall(np->rx_mcl, mcl - np->rx_mcl);
}
}
__skb_queue_purge(&free_list);
spin_unlock_bh(&np->rx_lock);
}
static void xennet_uninit(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
xennet_release_tx_bufs(np);
xennet_release_rx_bufs(np);
gnttab_free_grant_references(np->gref_tx_head);
gnttab_free_grant_references(np->gref_rx_head);
}
static netdev_features_t xennet_fix_features(struct net_device *dev,
netdev_features_t features)
{
struct netfront_info *np = netdev_priv(dev);
int val;
if (features & NETIF_F_SG) {
if (xenbus_scanf(XBT_NIL, np->xbdev->otherend, "feature-sg",
"%d", &val) < 0)
val = 0;
if (!val)
features &= ~NETIF_F_SG;
}
if (features & NETIF_F_TSO) {
if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
"feature-gso-tcpv4", "%d", &val) < 0)
val = 0;
if (!val)
features &= ~NETIF_F_TSO;
}
return features;
}
static int xennet_set_features(struct net_device *dev,
netdev_features_t features)
{
if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN) {
netdev_info(dev, "Reducing MTU because no SG offload");
dev->mtu = ETH_DATA_LEN;
}
return 0;
}
static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id)
{
struct netfront_info *np = dev_id;
struct net_device *dev = np->netdev;
unsigned long flags;
spin_lock_irqsave(&np->tx_lock, flags);
xennet_tx_buf_gc(dev);
spin_unlock_irqrestore(&np->tx_lock, flags);
return IRQ_HANDLED;
}
static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id)
{
struct netfront_info *np = dev_id;
struct net_device *dev = np->netdev;
if (likely(netif_carrier_ok(dev) &&
RING_HAS_UNCONSUMED_RESPONSES(&np->rx)))
napi_schedule(&np->napi);
return IRQ_HANDLED;
}
static irqreturn_t xennet_interrupt(int irq, void *dev_id)
{
xennet_tx_interrupt(irq, dev_id);
xennet_rx_interrupt(irq, dev_id);
return IRQ_HANDLED;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
static void xennet_poll_controller(struct net_device *dev)
{
xennet_interrupt(0, dev);
}
#endif
static const struct net_device_ops xennet_netdev_ops = {
.ndo_open = xennet_open,
.ndo_uninit = xennet_uninit,
.ndo_stop = xennet_close,
.ndo_start_xmit = xennet_start_xmit,
.ndo_change_mtu = xennet_change_mtu,
.ndo_get_stats64 = xennet_get_stats64,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_fix_features = xennet_fix_features,
.ndo_set_features = xennet_set_features,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = xennet_poll_controller,
#endif
};
static struct net_device *xennet_create_dev(struct xenbus_device *dev)
{
int i, err;
struct net_device *netdev;
struct netfront_info *np;
netdev = alloc_etherdev(sizeof(struct netfront_info));
if (!netdev)
return ERR_PTR(-ENOMEM);
np = netdev_priv(netdev);
np->xbdev = dev;
spin_lock_init(&np->tx_lock);
spin_lock_init(&np->rx_lock);
skb_queue_head_init(&np->rx_batch);
np->rx_target = RX_DFL_MIN_TARGET;
np->rx_min_target = RX_DFL_MIN_TARGET;
np->rx_max_target = RX_MAX_TARGET;
init_timer(&np->rx_refill_timer);
np->rx_refill_timer.data = (unsigned long)netdev;
np->rx_refill_timer.function = rx_refill_timeout;
err = -ENOMEM;
np->stats = alloc_percpu(struct netfront_stats);
if (np->stats == NULL)
goto exit;
for_each_possible_cpu(i) {
struct netfront_stats *xen_nf_stats;
xen_nf_stats = per_cpu_ptr(np->stats, i);
u64_stats_init(&xen_nf_stats->syncp);
}
/* Initialise tx_skbs as a free chain containing every entry. */
np->tx_skb_freelist = 0;
for (i = 0; i < NET_TX_RING_SIZE; i++) {
skb_entry_set_link(&np->tx_skbs[i], i+1);
np->grant_tx_ref[i] = GRANT_INVALID_REF;
}
/* Clear out rx_skbs */
for (i = 0; i < NET_RX_RING_SIZE; i++) {
np->rx_skbs[i] = NULL;
np->grant_rx_ref[i] = GRANT_INVALID_REF;
}
/* A grant for every tx ring slot */
if (gnttab_alloc_grant_references(TX_MAX_TARGET,
&np->gref_tx_head) < 0) {
pr_alert("can't alloc tx grant refs\n");
err = -ENOMEM;
goto exit_free_stats;
}
/* A grant for every rx ring slot */
if (gnttab_alloc_grant_references(RX_MAX_TARGET,
&np->gref_rx_head) < 0) {
pr_alert("can't alloc rx grant refs\n");
err = -ENOMEM;
goto exit_free_tx;
}
netdev->netdev_ops = &xennet_netdev_ops;
netif_napi_add(netdev, &np->napi, xennet_poll, 64);
netdev->features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
NETIF_F_GSO_ROBUST;
netdev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO;
/*
* Assume that all hw features are available for now. This set
* will be adjusted by the call to netdev_update_features() in
* xennet_connect() which is the earliest point where we can
* negotiate with the backend regarding supported features.
*/
netdev->features |= netdev->hw_features;
SET_ETHTOOL_OPS(netdev, &xennet_ethtool_ops);
SET_NETDEV_DEV(netdev, &dev->dev);
netif_set_gso_max_size(netdev, XEN_NETIF_MAX_TX_SIZE - MAX_TCP_HEADER);
np->netdev = netdev;
netif_carrier_off(netdev);
return netdev;
exit_free_tx:
gnttab_free_grant_references(np->gref_tx_head);
exit_free_stats:
free_percpu(np->stats);
exit:
free_netdev(netdev);
return ERR_PTR(err);
}
/**
* Entry point to this code when a new device is created. Allocate the basic
* structures and the ring buffers for communication with the backend, and
* inform the backend of the appropriate details for those.
*/
static int netfront_probe(struct xenbus_device *dev,
const struct xenbus_device_id *id)
{
int err;
struct net_device *netdev;
struct netfront_info *info;
netdev = xennet_create_dev(dev);
if (IS_ERR(netdev)) {
err = PTR_ERR(netdev);
xenbus_dev_fatal(dev, err, "creating netdev");
return err;
}
info = netdev_priv(netdev);
dev_set_drvdata(&dev->dev, info);
err = register_netdev(info->netdev);
if (err) {
pr_warn("%s: register_netdev err=%d\n", __func__, err);
goto fail;
}
err = xennet_sysfs_addif(info->netdev);
if (err) {
unregister_netdev(info->netdev);
pr_warn("%s: add sysfs failed err=%d\n", __func__, err);
goto fail;
}
return 0;
fail:
free_netdev(netdev);
dev_set_drvdata(&dev->dev, NULL);
return err;
}
static void xennet_end_access(int ref, void *page)
{
/* This frees the page as a side-effect */
if (ref != GRANT_INVALID_REF)
gnttab_end_foreign_access(ref, 0, (unsigned long)page);
}
static void xennet_disconnect_backend(struct netfront_info *info)
{
/* Stop old i/f to prevent errors whilst we rebuild the state. */
spin_lock_bh(&info->rx_lock);
spin_lock_irq(&info->tx_lock);
netif_carrier_off(info->netdev);
spin_unlock_irq(&info->tx_lock);
spin_unlock_bh(&info->rx_lock);
if (info->tx_irq && (info->tx_irq == info->rx_irq))
unbind_from_irqhandler(info->tx_irq, info);
if (info->tx_irq && (info->tx_irq != info->rx_irq)) {
unbind_from_irqhandler(info->tx_irq, info);
unbind_from_irqhandler(info->rx_irq, info);
}
info->tx_evtchn = info->rx_evtchn = 0;
info->tx_irq = info->rx_irq = 0;
/* End access and free the pages */
xennet_end_access(info->tx_ring_ref, info->tx.sring);
xennet_end_access(info->rx_ring_ref, info->rx.sring);
info->tx_ring_ref = GRANT_INVALID_REF;
info->rx_ring_ref = GRANT_INVALID_REF;
info->tx.sring = NULL;
info->rx.sring = NULL;
}
/**
* We are reconnecting to the backend, due to a suspend/resume, or a backend
* driver restart. We tear down our netif structure and recreate it, but
* leave the device-layer structures intact so that this is transparent to the
* rest of the kernel.
*/
static int netfront_resume(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
dev_dbg(&dev->dev, "%s\n", dev->nodename);
xennet_disconnect_backend(info);
return 0;
}
static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
{
char *s, *e, *macstr;
int i;
macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL);
if (IS_ERR(macstr))
return PTR_ERR(macstr);
for (i = 0; i < ETH_ALEN; i++) {
mac[i] = simple_strtoul(s, &e, 16);
if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) {
kfree(macstr);
return -ENOENT;
}
s = e+1;
}
kfree(macstr);
return 0;
}
static int setup_netfront_single(struct netfront_info *info)
{
int err;
err = xenbus_alloc_evtchn(info->xbdev, &info->tx_evtchn);
if (err < 0)
goto fail;
err = bind_evtchn_to_irqhandler(info->tx_evtchn,
xennet_interrupt,
0, info->netdev->name, info);
if (err < 0)
goto bind_fail;
info->rx_evtchn = info->tx_evtchn;
info->rx_irq = info->tx_irq = err;
return 0;
bind_fail:
xenbus_free_evtchn(info->xbdev, info->tx_evtchn);
info->tx_evtchn = 0;
fail:
return err;
}
static int setup_netfront_split(struct netfront_info *info)
{
int err;
err = xenbus_alloc_evtchn(info->xbdev, &info->tx_evtchn);
if (err < 0)
goto fail;
err = xenbus_alloc_evtchn(info->xbdev, &info->rx_evtchn);
if (err < 0)
goto alloc_rx_evtchn_fail;
snprintf(info->tx_irq_name, sizeof(info->tx_irq_name),
"%s-tx", info->netdev->name);
err = bind_evtchn_to_irqhandler(info->tx_evtchn,
xennet_tx_interrupt,
0, info->tx_irq_name, info);
if (err < 0)
goto bind_tx_fail;
info->tx_irq = err;
snprintf(info->rx_irq_name, sizeof(info->rx_irq_name),
"%s-rx", info->netdev->name);
err = bind_evtchn_to_irqhandler(info->rx_evtchn,
xennet_rx_interrupt,
0, info->rx_irq_name, info);
if (err < 0)
goto bind_rx_fail;
info->rx_irq = err;
return 0;
bind_rx_fail:
unbind_from_irqhandler(info->tx_irq, info);
info->tx_irq = 0;
bind_tx_fail:
xenbus_free_evtchn(info->xbdev, info->rx_evtchn);
info->rx_evtchn = 0;
alloc_rx_evtchn_fail:
xenbus_free_evtchn(info->xbdev, info->tx_evtchn);
info->tx_evtchn = 0;
fail:
return err;
}
static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
{
struct xen_netif_tx_sring *txs;
struct xen_netif_rx_sring *rxs;
int err;
struct net_device *netdev = info->netdev;
unsigned int feature_split_evtchn;
info->tx_ring_ref = GRANT_INVALID_REF;
info->rx_ring_ref = GRANT_INVALID_REF;
info->rx.sring = NULL;
info->tx.sring = NULL;
netdev->irq = 0;
err = xenbus_scanf(XBT_NIL, info->xbdev->otherend,
"feature-split-event-channels", "%u",
&feature_split_evtchn);
if (err < 0)
feature_split_evtchn = 0;
err = xen_net_read_mac(dev, netdev->dev_addr);
if (err) {
xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
goto fail;
}
txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH);
if (!txs) {
err = -ENOMEM;
xenbus_dev_fatal(dev, err, "allocating tx ring page");
goto fail;
}
SHARED_RING_INIT(txs);
FRONT_RING_INIT(&info->tx, txs, PAGE_SIZE);
err = xenbus_grant_ring(dev, virt_to_mfn(txs));
if (err < 0)
goto grant_tx_ring_fail;
info->tx_ring_ref = err;
rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH);
if (!rxs) {
err = -ENOMEM;
xenbus_dev_fatal(dev, err, "allocating rx ring page");
goto alloc_rx_ring_fail;
}
SHARED_RING_INIT(rxs);
FRONT_RING_INIT(&info->rx, rxs, PAGE_SIZE);
err = xenbus_grant_ring(dev, virt_to_mfn(rxs));
if (err < 0)
goto grant_rx_ring_fail;
info->rx_ring_ref = err;
if (feature_split_evtchn)
err = setup_netfront_split(info);
/* setup single event channel if
* a) feature-split-event-channels == 0
* b) feature-split-event-channels == 1 but failed to setup
*/
if (!feature_split_evtchn || (feature_split_evtchn && err))
err = setup_netfront_single(info);
if (err)
goto alloc_evtchn_fail;
return 0;
/* If we fail to setup netfront, it is safe to just revoke access to
* granted pages because backend is not accessing it at this point.
*/
alloc_evtchn_fail:
gnttab_end_foreign_access_ref(info->rx_ring_ref, 0);
grant_rx_ring_fail:
free_page((unsigned long)rxs);
alloc_rx_ring_fail:
gnttab_end_foreign_access_ref(info->tx_ring_ref, 0);
grant_tx_ring_fail:
free_page((unsigned long)txs);
fail:
return err;
}
/* Common code used when first setting up, and when resuming. */
static int talk_to_netback(struct xenbus_device *dev,
struct netfront_info *info)
{
const char *message;
struct xenbus_transaction xbt;
int err;
/* Create shared ring, alloc event channel. */
err = setup_netfront(dev, info);
if (err)
goto out;
again:
err = xenbus_transaction_start(&xbt);
if (err) {
xenbus_dev_fatal(dev, err, "starting transaction");
goto destroy_ring;
}
err = xenbus_printf(xbt, dev->nodename, "tx-ring-ref", "%u",
info->tx_ring_ref);
if (err) {
message = "writing tx ring-ref";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "rx-ring-ref", "%u",
info->rx_ring_ref);
if (err) {
message = "writing rx ring-ref";
goto abort_transaction;
}
if (info->tx_evtchn == info->rx_evtchn) {
err = xenbus_printf(xbt, dev->nodename,
"event-channel", "%u", info->tx_evtchn);
if (err) {
message = "writing event-channel";
goto abort_transaction;
}
} else {
err = xenbus_printf(xbt, dev->nodename,
"event-channel-tx", "%u", info->tx_evtchn);
if (err) {
message = "writing event-channel-tx";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename,
"event-channel-rx", "%u", info->rx_evtchn);
if (err) {
message = "writing event-channel-rx";
goto abort_transaction;
}
}
err = xenbus_printf(xbt, dev->nodename, "request-rx-copy", "%u",
1);
if (err) {
message = "writing request-rx-copy";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-rx-notify", "%d", 1);
if (err) {
message = "writing feature-rx-notify";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", 1);
if (err) {
message = "writing feature-sg";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4", "%d", 1);
if (err) {
message = "writing feature-gso-tcpv4";
goto abort_transaction;
}
err = xenbus_transaction_end(xbt, 0);
if (err) {
if (err == -EAGAIN)
goto again;
xenbus_dev_fatal(dev, err, "completing transaction");
goto destroy_ring;
}
return 0;
abort_transaction:
xenbus_transaction_end(xbt, 1);
xenbus_dev_fatal(dev, err, "%s", message);
destroy_ring:
xennet_disconnect_backend(info);
out:
return err;
}
static int xennet_connect(struct net_device *dev)
{
struct netfront_info *np = netdev_priv(dev);
int i, requeue_idx, err;
struct sk_buff *skb;
grant_ref_t ref;
struct xen_netif_rx_request *req;
unsigned int feature_rx_copy;
err = xenbus_scanf(XBT_NIL, np->xbdev->otherend,
"feature-rx-copy", "%u", &feature_rx_copy);
if (err != 1)
feature_rx_copy = 0;
if (!feature_rx_copy) {
dev_info(&dev->dev,
"backend does not support copying receive path\n");
return -ENODEV;
}
err = talk_to_netback(np->xbdev, np);
if (err)
return err;
rtnl_lock();
netdev_update_features(dev);
rtnl_unlock();
spin_lock_bh(&np->rx_lock);
spin_lock_irq(&np->tx_lock);
/* Step 1: Discard all pending TX packet fragments. */
xennet_release_tx_bufs(np);
/* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */
for (requeue_idx = 0, i = 0; i < NET_RX_RING_SIZE; i++) {
skb_frag_t *frag;
const struct page *page;
if (!np->rx_skbs[i])
continue;
skb = np->rx_skbs[requeue_idx] = xennet_get_rx_skb(np, i);
ref = np->grant_rx_ref[requeue_idx] = xennet_get_rx_ref(np, i);
req = RING_GET_REQUEST(&np->rx, requeue_idx);
frag = &skb_shinfo(skb)->frags[0];
page = skb_frag_page(frag);
gnttab_grant_foreign_access_ref(
ref, np->xbdev->otherend_id,
pfn_to_mfn(page_to_pfn(page)),
0);
req->gref = ref;
req->id = requeue_idx;
requeue_idx++;
}
np->rx.req_prod_pvt = requeue_idx;
/*
* Step 3: All public and private state should now be sane. Get
* ready to start sending and receiving packets and give the driver
* domain a kick because we've probably just requeued some
* packets.
*/
netif_carrier_on(np->netdev);
notify_remote_via_irq(np->tx_irq);
if (np->tx_irq != np->rx_irq)
notify_remote_via_irq(np->rx_irq);
xennet_tx_buf_gc(dev);
xennet_alloc_rx_buffers(dev);
spin_unlock_irq(&np->tx_lock);
spin_unlock_bh(&np->rx_lock);
return 0;
}
/**
* Callback received when the backend's state changes.
*/
static void netback_changed(struct xenbus_device *dev,
enum xenbus_state backend_state)
{
struct netfront_info *np = dev_get_drvdata(&dev->dev);
struct net_device *netdev = np->netdev;
dev_dbg(&dev->dev, "%s\n", xenbus_strstate(backend_state));
switch (backend_state) {
case XenbusStateInitialising:
case XenbusStateInitialised:
case XenbusStateReconfiguring:
case XenbusStateReconfigured:
case XenbusStateUnknown:
case XenbusStateClosed:
break;
case XenbusStateInitWait:
if (dev->state != XenbusStateInitialising)
break;
if (xennet_connect(netdev) != 0)
break;
xenbus_switch_state(dev, XenbusStateConnected);
break;
case XenbusStateConnected:
netdev_notify_peers(netdev);
break;
case XenbusStateClosing:
xenbus_frontend_closed(dev);
break;
}
}
static const struct xennet_stat {
char name[ETH_GSTRING_LEN];
u16 offset;
} xennet_stats[] = {
{
"rx_gso_checksum_fixup",
offsetof(struct netfront_info, rx_gso_checksum_fixup)
},
};
static int xennet_get_sset_count(struct net_device *dev, int string_set)
{
switch (string_set) {
case ETH_SS_STATS:
return ARRAY_SIZE(xennet_stats);
default:
return -EINVAL;
}
}
static void xennet_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 * data)
{
void *np = netdev_priv(dev);
int i;
for (i = 0; i < ARRAY_SIZE(xennet_stats); i++)
data[i] = *(unsigned long *)(np + xennet_stats[i].offset);
}
static void xennet_get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
int i;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(xennet_stats); i++)
memcpy(data + i * ETH_GSTRING_LEN,
xennet_stats[i].name, ETH_GSTRING_LEN);
break;
}
}
static const struct ethtool_ops xennet_ethtool_ops =
{
.get_link = ethtool_op_get_link,
.get_sset_count = xennet_get_sset_count,
.get_ethtool_stats = xennet_get_ethtool_stats,
.get_strings = xennet_get_strings,
};
#ifdef CONFIG_SYSFS
static ssize_t show_rxbuf_min(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
struct netfront_info *info = netdev_priv(netdev);
return sprintf(buf, "%u\n", info->rx_min_target);
}
static ssize_t store_rxbuf_min(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t len)
{
struct net_device *netdev = to_net_dev(dev);
struct netfront_info *np = netdev_priv(netdev);
char *endp;
unsigned long target;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
target = simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EBADMSG;
if (target < RX_MIN_TARGET)
target = RX_MIN_TARGET;
if (target > RX_MAX_TARGET)
target = RX_MAX_TARGET;
spin_lock_bh(&np->rx_lock);
if (target > np->rx_max_target)
np->rx_max_target = target;
np->rx_min_target = target;
if (target > np->rx_target)
np->rx_target = target;
xennet_alloc_rx_buffers(netdev);
spin_unlock_bh(&np->rx_lock);
return len;
}
static ssize_t show_rxbuf_max(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
struct netfront_info *info = netdev_priv(netdev);
return sprintf(buf, "%u\n", info->rx_max_target);
}
static ssize_t store_rxbuf_max(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t len)
{
struct net_device *netdev = to_net_dev(dev);
struct netfront_info *np = netdev_priv(netdev);
char *endp;
unsigned long target;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
target = simple_strtoul(buf, &endp, 0);
if (endp == buf)
return -EBADMSG;
if (target < RX_MIN_TARGET)
target = RX_MIN_TARGET;
if (target > RX_MAX_TARGET)
target = RX_MAX_TARGET;
spin_lock_bh(&np->rx_lock);
if (target < np->rx_min_target)
np->rx_min_target = target;
np->rx_max_target = target;
if (target < np->rx_target)
np->rx_target = target;
xennet_alloc_rx_buffers(netdev);
spin_unlock_bh(&np->rx_lock);
return len;
}
static ssize_t show_rxbuf_cur(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct net_device *netdev = to_net_dev(dev);
struct netfront_info *info = netdev_priv(netdev);
return sprintf(buf, "%u\n", info->rx_target);
}
static struct device_attribute xennet_attrs[] = {
__ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf_min, store_rxbuf_min),
__ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf_max, store_rxbuf_max),
__ATTR(rxbuf_cur, S_IRUGO, show_rxbuf_cur, NULL),
};
static int xennet_sysfs_addif(struct net_device *netdev)
{
int i;
int err;
for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++) {
err = device_create_file(&netdev->dev,
&xennet_attrs[i]);
if (err)
goto fail;
}
return 0;
fail:
while (--i >= 0)
device_remove_file(&netdev->dev, &xennet_attrs[i]);
return err;
}
static void xennet_sysfs_delif(struct net_device *netdev)
{
int i;
for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++)
device_remove_file(&netdev->dev, &xennet_attrs[i]);
}
#endif /* CONFIG_SYSFS */
static const struct xenbus_device_id netfront_ids[] = {
{ "vif" },
{ "" }
};
static int xennet_remove(struct xenbus_device *dev)
{
struct netfront_info *info = dev_get_drvdata(&dev->dev);
dev_dbg(&dev->dev, "%s\n", dev->nodename);
xennet_disconnect_backend(info);
xennet_sysfs_delif(info->netdev);
unregister_netdev(info->netdev);
del_timer_sync(&info->rx_refill_timer);
free_percpu(info->stats);
free_netdev(info->netdev);
return 0;
}
static DEFINE_XENBUS_DRIVER(netfront, ,
.probe = netfront_probe,
.remove = xennet_remove,
.resume = netfront_resume,
.otherend_changed = netback_changed,
);
static int __init netif_init(void)
{
if (!xen_domain())
return -ENODEV;
if (xen_hvm_domain() && !xen_platform_pci_unplug)
return -ENODEV;
pr_info("Initialising Xen virtual ethernet driver\n");
return xenbus_register_frontend(&netfront_driver);
}
module_init(netif_init);
static void __exit netif_exit(void)
{
xenbus_unregister_driver(&netfront_driver);
}
module_exit(netif_exit);
MODULE_DESCRIPTION("Xen virtual network device frontend");
MODULE_LICENSE("GPL");
MODULE_ALIAS("xen:vif");
MODULE_ALIAS("xennet");