提交 f942dc25 编写于 作者: I Ian Campbell 提交者: David S. Miller

xen network backend driver

netback is the host side counterpart to the frontend driver in
drivers/net/xen-netfront.c. The PV protocol is also implemented by
frontend drivers in other OSes too, such as the BSDs and even Windows.

The patch is based on the driver from the xen.git pvops kernel tree but
has been put through the checkpatch.pl wringer plus several manual
cleanup passes and review iterations. The driver has been moved from
drivers/xen/netback to drivers/net/xen-netback.

One major change from xen.git is that the guest transmit path (i.e. what
looks like receive to netback) has been significantly reworked to remove
the dependency on the out of tree PageForeign page flag (a core kernel
patch which enables a per page destructor callback on the final
put_page). This page flag was used in order to implement a grant map
based transmit path (where guest pages are mapped directly into SKB
frags). Instead this version of netback uses grant copy operations into
regular memory belonging to the backend domain. Reinstating the grant
map functionality is something which I would like to revisit in the
future.

Note that this driver depends on 2e820f58 "xen/irq: implement
bind_interdomain_evtchn_to_irqhandler for backend drivers" which is in
linux next via the "xen-two" tree and is intended for the 2.6.39 merge
window:
        git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen.git stable/backends
this branch has only that single commit since 2.6.38-rc2 and is safe for
cross merging into the net branch.
Signed-off-by: NIan Campbell <ian.campbell@citrix.com>
Reviewed-by: NBen Hutchings <bhutchings@solarflare.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 e0da2481
......@@ -2953,12 +2953,38 @@ config XEN_NETDEV_FRONTEND
select XEN_XENBUS_FRONTEND
default y
help
The network device frontend driver allows the kernel to
access network devices exported exported by a virtual
machine containing a physical network device driver. The
frontend driver is intended for unprivileged guest domains;
if you are compiling a kernel for a Xen guest, you almost
certainly want to enable this.
This driver provides support for Xen paravirtual network
devices exported by a Xen network driver domain (often
domain 0).
The corresponding Linux backend driver is enabled by the
CONFIG_XEN_NETDEV_BACKEND option.
If you are compiling a kernel for use as Xen guest, you
should say Y here. To compile this driver as a module, chose
M here: the module will be called xen-netfront.
config XEN_NETDEV_BACKEND
tristate "Xen backend network device"
depends on XEN_BACKEND
help
This driver allows the kernel to act as a Xen network driver
domain which exports paravirtual network devices to other
Xen domains. These devices can be accessed by any operating
system that implements a compatible front end.
The corresponding Linux frontend driver is enabled by the
CONFIG_XEN_NETDEV_FRONTEND configuration option.
The backend driver presents a standard network device
endpoint for each paravirtual network device to the driver
domain network stack. These can then be bridged or routed
etc in order to provide full network connectivity.
If you are compiling a kernel to run in a Xen network driver
domain (often this is domain 0) you should say Y here. To
compile this driver as a module, chose M here: the module
will be called xen-netback.
config ISERIES_VETH
tristate "iSeries Virtual Ethernet driver support"
......
......@@ -172,6 +172,7 @@ obj-$(CONFIG_SLIP) += slip.o
obj-$(CONFIG_SLHC) += slhc.o
obj-$(CONFIG_XEN_NETDEV_FRONTEND) += xen-netfront.o
obj-$(CONFIG_XEN_NETDEV_BACKEND) += xen-netback/
obj-$(CONFIG_DUMMY) += dummy.o
obj-$(CONFIG_IFB) += ifb.o
......
obj-$(CONFIG_XEN_NETDEV_BACKEND) := xen-netback.o
xen-netback-y := netback.o xenbus.o interface.o
/*
* 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.
*/
#ifndef __XEN_NETBACK__COMMON_H__
#define __XEN_NETBACK__COMMON_H__
#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/ip.h>
#include <linux/in.h>
#include <linux/io.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/wait.h>
#include <linux/sched.h>
#include <xen/interface/io/netif.h>
#include <xen/interface/grant_table.h>
#include <xen/grant_table.h>
#include <xen/xenbus.h>
struct xen_netbk;
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
unsigned int handle;
/* Reference to netback processing backend. */
struct xen_netbk *netbk;
u8 fe_dev_addr[6];
/* Physical parameters of the comms window. */
grant_handle_t tx_shmem_handle;
grant_ref_t tx_shmem_ref;
grant_handle_t rx_shmem_handle;
grant_ref_t rx_shmem_ref;
unsigned int irq;
/* List of frontends to notify after a batch of frames sent. */
struct list_head notify_list;
/* The shared rings and indexes. */
struct xen_netif_tx_back_ring tx;
struct xen_netif_rx_back_ring rx;
struct vm_struct *tx_comms_area;
struct vm_struct *rx_comms_area;
/* Flags that must not be set in dev->features */
u32 features_disabled;
/* Frontend feature information. */
u8 can_sg:1;
u8 gso:1;
u8 gso_prefix:1;
u8 csum:1;
/* Internal feature information. */
u8 can_queue:1; /* can queue packets for receiver? */
/*
* Allow xenvif_start_xmit() to peek ahead in the rx request
* ring. This is a prediction of what rx_req_cons will be
* once all queued skbs are put on the ring.
*/
RING_IDX rx_req_cons_peek;
/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
unsigned long credit_bytes;
unsigned long credit_usec;
unsigned long remaining_credit;
struct timer_list credit_timeout;
/* Statistics */
unsigned long rx_gso_checksum_fixup;
/* Miscellaneous private stuff. */
struct list_head schedule_list;
atomic_t refcnt;
struct net_device *dev;
wait_queue_head_t waiting_to_free;
};
#define XEN_NETIF_TX_RING_SIZE __RING_SIZE((struct xen_netif_tx_sring *)0, PAGE_SIZE)
#define XEN_NETIF_RX_RING_SIZE __RING_SIZE((struct xen_netif_rx_sring *)0, PAGE_SIZE)
struct xenvif *xenvif_alloc(struct device *parent,
domid_t domid,
unsigned int handle);
int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
unsigned long rx_ring_ref, unsigned int evtchn);
void xenvif_disconnect(struct xenvif *vif);
void xenvif_get(struct xenvif *vif);
void xenvif_put(struct xenvif *vif);
int xenvif_xenbus_init(void);
int xenvif_schedulable(struct xenvif *vif);
int xen_netbk_rx_ring_full(struct xenvif *vif);
int xen_netbk_must_stop_queue(struct xenvif *vif);
/* (Un)Map communication rings. */
void xen_netbk_unmap_frontend_rings(struct xenvif *vif);
int xen_netbk_map_frontend_rings(struct xenvif *vif,
grant_ref_t tx_ring_ref,
grant_ref_t rx_ring_ref);
/* (De)Register a xenvif with the netback backend. */
void xen_netbk_add_xenvif(struct xenvif *vif);
void xen_netbk_remove_xenvif(struct xenvif *vif);
/* (De)Schedule backend processing for a xenvif */
void xen_netbk_schedule_xenvif(struct xenvif *vif);
void xen_netbk_deschedule_xenvif(struct xenvif *vif);
/* Check for SKBs from frontend and schedule backend processing */
void xen_netbk_check_rx_xenvif(struct xenvif *vif);
/* Receive an SKB from the frontend */
void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb);
/* Queue an SKB for transmission to the frontend */
void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb);
/* Notify xenvif that ring now has space to send an skb to the frontend */
void xenvif_notify_tx_completion(struct xenvif *vif);
/* Returns number of ring slots required to send an skb to the frontend */
unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
#endif /* __XEN_NETBACK__COMMON_H__ */
/*
* Network-device interface management.
*
* Copyright (c) 2004-2005, Keir 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/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <xen/events.h>
#include <asm/xen/hypercall.h>
#define XENVIF_QUEUE_LENGTH 32
void xenvif_get(struct xenvif *vif)
{
atomic_inc(&vif->refcnt);
}
void xenvif_put(struct xenvif *vif)
{
if (atomic_dec_and_test(&vif->refcnt))
wake_up(&vif->waiting_to_free);
}
int xenvif_schedulable(struct xenvif *vif)
{
return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
}
static int xenvif_rx_schedulable(struct xenvif *vif)
{
return xenvif_schedulable(vif) && !xen_netbk_rx_ring_full(vif);
}
static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
{
struct xenvif *vif = dev_id;
if (vif->netbk == NULL)
return IRQ_NONE;
xen_netbk_schedule_xenvif(vif);
if (xenvif_rx_schedulable(vif))
netif_wake_queue(vif->dev);
return IRQ_HANDLED;
}
static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
BUG_ON(skb->dev != dev);
if (vif->netbk == NULL)
goto drop;
/* Drop the packet if the target domain has no receive buffers. */
if (!xenvif_rx_schedulable(vif))
goto drop;
/* Reserve ring slots for the worst-case number of fragments. */
vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb);
xenvif_get(vif);
if (vif->can_queue && xen_netbk_must_stop_queue(vif))
netif_stop_queue(dev);
xen_netbk_queue_tx_skb(vif, skb);
return NETDEV_TX_OK;
drop:
vif->dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb)
{
netif_rx_ni(skb);
}
void xenvif_notify_tx_completion(struct xenvif *vif)
{
if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
netif_wake_queue(vif->dev);
}
static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
return &vif->dev->stats;
}
static void xenvif_up(struct xenvif *vif)
{
xen_netbk_add_xenvif(vif);
enable_irq(vif->irq);
xen_netbk_check_rx_xenvif(vif);
}
static void xenvif_down(struct xenvif *vif)
{
disable_irq(vif->irq);
xen_netbk_deschedule_xenvif(vif);
xen_netbk_remove_xenvif(vif);
}
static int xenvif_open(struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
if (netif_carrier_ok(dev))
xenvif_up(vif);
netif_start_queue(dev);
return 0;
}
static int xenvif_close(struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
if (netif_carrier_ok(dev))
xenvif_down(vif);
netif_stop_queue(dev);
return 0;
}
static int xenvif_change_mtu(struct net_device *dev, int mtu)
{
struct xenvif *vif = netdev_priv(dev);
int max = vif->can_sg ? 65535 - VLAN_ETH_HLEN : ETH_DATA_LEN;
if (mtu > max)
return -EINVAL;
dev->mtu = mtu;
return 0;
}
static void xenvif_set_features(struct xenvif *vif)
{
struct net_device *dev = vif->dev;
u32 features = dev->features;
if (vif->can_sg)
features |= NETIF_F_SG;
if (vif->gso || vif->gso_prefix)
features |= NETIF_F_TSO;
if (vif->csum)
features |= NETIF_F_IP_CSUM;
features &= ~(vif->features_disabled);
if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN)
dev->mtu = ETH_DATA_LEN;
dev->features = features;
}
static int xenvif_set_tx_csum(struct net_device *dev, u32 data)
{
struct xenvif *vif = netdev_priv(dev);
if (data) {
if (!vif->csum)
return -EOPNOTSUPP;
vif->features_disabled &= ~NETIF_F_IP_CSUM;
} else {
vif->features_disabled |= NETIF_F_IP_CSUM;
}
xenvif_set_features(vif);
return 0;
}
static int xenvif_set_sg(struct net_device *dev, u32 data)
{
struct xenvif *vif = netdev_priv(dev);
if (data) {
if (!vif->can_sg)
return -EOPNOTSUPP;
vif->features_disabled &= ~NETIF_F_SG;
} else {
vif->features_disabled |= NETIF_F_SG;
}
xenvif_set_features(vif);
return 0;
}
static int xenvif_set_tso(struct net_device *dev, u32 data)
{
struct xenvif *vif = netdev_priv(dev);
if (data) {
if (!vif->gso && !vif->gso_prefix)
return -EOPNOTSUPP;
vif->features_disabled &= ~NETIF_F_TSO;
} else {
vif->features_disabled |= NETIF_F_TSO;
}
xenvif_set_features(vif);
return 0;
}
static const struct xenvif_stat {
char name[ETH_GSTRING_LEN];
u16 offset;
} xenvif_stats[] = {
{
"rx_gso_checksum_fixup",
offsetof(struct xenvif, rx_gso_checksum_fixup)
},
};
static int xenvif_get_sset_count(struct net_device *dev, int string_set)
{
switch (string_set) {
case ETH_SS_STATS:
return ARRAY_SIZE(xenvif_stats);
default:
return -EINVAL;
}
}
static void xenvif_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 * data)
{
void *vif = netdev_priv(dev);
int i;
for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
}
static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
{
int i;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
memcpy(data + i * ETH_GSTRING_LEN,
xenvif_stats[i].name, ETH_GSTRING_LEN);
break;
}
}
static struct ethtool_ops xenvif_ethtool_ops = {
.get_tx_csum = ethtool_op_get_tx_csum,
.set_tx_csum = xenvif_set_tx_csum,
.get_sg = ethtool_op_get_sg,
.set_sg = xenvif_set_sg,
.get_tso = ethtool_op_get_tso,
.set_tso = xenvif_set_tso,
.get_link = ethtool_op_get_link,
.get_sset_count = xenvif_get_sset_count,
.get_ethtool_stats = xenvif_get_ethtool_stats,
.get_strings = xenvif_get_strings,
};
static struct net_device_ops xenvif_netdev_ops = {
.ndo_start_xmit = xenvif_start_xmit,
.ndo_get_stats = xenvif_get_stats,
.ndo_open = xenvif_open,
.ndo_stop = xenvif_close,
.ndo_change_mtu = xenvif_change_mtu,
};
struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
unsigned int handle)
{
int err;
struct net_device *dev;
struct xenvif *vif;
char name[IFNAMSIZ] = {};
snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
if (dev == NULL) {
pr_warn("Could not allocate netdev\n");
return ERR_PTR(-ENOMEM);
}
SET_NETDEV_DEV(dev, parent);
vif = netdev_priv(dev);
vif->domid = domid;
vif->handle = handle;
vif->netbk = NULL;
vif->can_sg = 1;
vif->csum = 1;
atomic_set(&vif->refcnt, 1);
init_waitqueue_head(&vif->waiting_to_free);
vif->dev = dev;
INIT_LIST_HEAD(&vif->schedule_list);
INIT_LIST_HEAD(&vif->notify_list);
vif->credit_bytes = vif->remaining_credit = ~0UL;
vif->credit_usec = 0UL;
init_timer(&vif->credit_timeout);
/* Initialize 'expires' now: it's used to track the credit window. */
vif->credit_timeout.expires = jiffies;
dev->netdev_ops = &xenvif_netdev_ops;
xenvif_set_features(vif);
SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops);
dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
/*
* Initialise a dummy MAC address. We choose the numerically
* largest non-broadcast address to prevent the address getting
* stolen by an Ethernet bridge for STP purposes.
* (FE:FF:FF:FF:FF:FF)
*/
memset(dev->dev_addr, 0xFF, ETH_ALEN);
dev->dev_addr[0] &= ~0x01;
netif_carrier_off(dev);
err = register_netdev(dev);
if (err) {
netdev_warn(dev, "Could not register device: err=%d\n", err);
free_netdev(dev);
return ERR_PTR(err);
}
netdev_dbg(dev, "Successfully created xenvif\n");
return vif;
}
int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
unsigned long rx_ring_ref, unsigned int evtchn)
{
int err = -ENOMEM;
/* Already connected through? */
if (vif->irq)
return 0;
xenvif_set_features(vif);
err = xen_netbk_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
if (err < 0)
goto err;
err = bind_interdomain_evtchn_to_irqhandler(
vif->domid, evtchn, xenvif_interrupt, 0,
vif->dev->name, vif);
if (err < 0)
goto err_unmap;
vif->irq = err;
disable_irq(vif->irq);
xenvif_get(vif);
rtnl_lock();
netif_carrier_on(vif->dev);
if (netif_running(vif->dev))
xenvif_up(vif);
rtnl_unlock();
return 0;
err_unmap:
xen_netbk_unmap_frontend_rings(vif);
err:
return err;
}
void xenvif_disconnect(struct xenvif *vif)
{
struct net_device *dev = vif->dev;
if (netif_carrier_ok(dev)) {
rtnl_lock();
netif_carrier_off(dev); /* discard queued packets */
if (netif_running(dev))
xenvif_down(vif);
rtnl_unlock();
xenvif_put(vif);
}
atomic_dec(&vif->refcnt);
wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
del_timer_sync(&vif->credit_timeout);
if (vif->irq)
unbind_from_irqhandler(vif->irq, vif);
unregister_netdev(vif->dev);
xen_netbk_unmap_frontend_rings(vif);
free_netdev(vif->dev);
}
此差异已折叠。
/*
* Xenbus code for netif backend
*
* Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au>
* 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 as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include "common.h"
struct backend_info {
struct xenbus_device *dev;
struct xenvif *vif;
enum xenbus_state frontend_state;
struct xenbus_watch hotplug_status_watch;
int have_hotplug_status_watch:1;
};
static int connect_rings(struct backend_info *);
static void connect(struct backend_info *);
static void backend_create_xenvif(struct backend_info *be);
static void unregister_hotplug_status_watch(struct backend_info *be);
static int netback_remove(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
unregister_hotplug_status_watch(be);
if (be->vif) {
kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
xenvif_disconnect(be->vif);
be->vif = NULL;
}
kfree(be);
dev_set_drvdata(&dev->dev, NULL);
return 0;
}
/**
* Entry point to this code when a new device is created. Allocate the basic
* structures and switch to InitWait.
*/
static int netback_probe(struct xenbus_device *dev,
const struct xenbus_device_id *id)
{
const char *message;
struct xenbus_transaction xbt;
int err;
int sg;
struct backend_info *be = kzalloc(sizeof(struct backend_info),
GFP_KERNEL);
if (!be) {
xenbus_dev_fatal(dev, -ENOMEM,
"allocating backend structure");
return -ENOMEM;
}
be->dev = dev;
dev_set_drvdata(&dev->dev, be);
sg = 1;
do {
err = xenbus_transaction_start(&xbt);
if (err) {
xenbus_dev_fatal(dev, err, "starting transaction");
goto fail;
}
err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", sg);
if (err) {
message = "writing feature-sg";
goto abort_transaction;
}
err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4",
"%d", sg);
if (err) {
message = "writing feature-gso-tcpv4";
goto abort_transaction;
}
/* We support rx-copy path. */
err = xenbus_printf(xbt, dev->nodename,
"feature-rx-copy", "%d", 1);
if (err) {
message = "writing feature-rx-copy";
goto abort_transaction;
}
/*
* We don't support rx-flip path (except old guests who don't
* grok this feature flag).
*/
err = xenbus_printf(xbt, dev->nodename,
"feature-rx-flip", "%d", 0);
if (err) {
message = "writing feature-rx-flip";
goto abort_transaction;
}
err = xenbus_transaction_end(xbt, 0);
} while (err == -EAGAIN);
if (err) {
xenbus_dev_fatal(dev, err, "completing transaction");
goto fail;
}
err = xenbus_switch_state(dev, XenbusStateInitWait);
if (err)
goto fail;
/* This kicks hotplug scripts, so do it immediately. */
backend_create_xenvif(be);
return 0;
abort_transaction:
xenbus_transaction_end(xbt, 1);
xenbus_dev_fatal(dev, err, "%s", message);
fail:
pr_debug("failed");
netback_remove(dev);
return err;
}
/*
* Handle the creation of the hotplug script environment. We add the script
* and vif variables to the environment, for the benefit of the vif-* hotplug
* scripts.
*/
static int netback_uevent(struct xenbus_device *xdev,
struct kobj_uevent_env *env)
{
struct backend_info *be = dev_get_drvdata(&xdev->dev);
char *val;
val = xenbus_read(XBT_NIL, xdev->nodename, "script", NULL);
if (IS_ERR(val)) {
int err = PTR_ERR(val);
xenbus_dev_fatal(xdev, err, "reading script");
return err;
} else {
if (add_uevent_var(env, "script=%s", val)) {
kfree(val);
return -ENOMEM;
}
kfree(val);
}
if (!be || !be->vif)
return 0;
return add_uevent_var(env, "vif=%s", be->vif->dev->name);
}
static void backend_create_xenvif(struct backend_info *be)
{
int err;
long handle;
struct xenbus_device *dev = be->dev;
if (be->vif != NULL)
return;
err = xenbus_scanf(XBT_NIL, dev->nodename, "handle", "%li", &handle);
if (err != 1) {
xenbus_dev_fatal(dev, err, "reading handle");
return;
}
be->vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle);
if (IS_ERR(be->vif)) {
err = PTR_ERR(be->vif);
be->vif = NULL;
xenbus_dev_fatal(dev, err, "creating interface");
return;
}
kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE);
}
static void disconnect_backend(struct xenbus_device *dev)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
if (be->vif) {
xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status");
xenvif_disconnect(be->vif);
be->vif = NULL;
}
}
/**
* Callback received when the frontend's state changes.
*/
static void frontend_changed(struct xenbus_device *dev,
enum xenbus_state frontend_state)
{
struct backend_info *be = dev_get_drvdata(&dev->dev);
pr_debug("frontend state %s", xenbus_strstate(frontend_state));
be->frontend_state = frontend_state;
switch (frontend_state) {
case XenbusStateInitialising:
if (dev->state == XenbusStateClosed) {
printk(KERN_INFO "%s: %s: prepare for reconnect\n",
__func__, dev->nodename);
xenbus_switch_state(dev, XenbusStateInitWait);
}
break;
case XenbusStateInitialised:
break;
case XenbusStateConnected:
if (dev->state == XenbusStateConnected)
break;
backend_create_xenvif(be);
if (be->vif)
connect(be);
break;
case XenbusStateClosing:
if (be->vif)
kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE);
disconnect_backend(dev);
xenbus_switch_state(dev, XenbusStateClosing);
break;
case XenbusStateClosed:
xenbus_switch_state(dev, XenbusStateClosed);
if (xenbus_dev_is_online(dev))
break;
/* fall through if not online */
case XenbusStateUnknown:
device_unregister(&dev->dev);
break;
default:
xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
frontend_state);
break;
}
}
static void xen_net_read_rate(struct xenbus_device *dev,
unsigned long *bytes, unsigned long *usec)
{
char *s, *e;
unsigned long b, u;
char *ratestr;
/* Default to unlimited bandwidth. */
*bytes = ~0UL;
*usec = 0;
ratestr = xenbus_read(XBT_NIL, dev->nodename, "rate", NULL);
if (IS_ERR(ratestr))
return;
s = ratestr;
b = simple_strtoul(s, &e, 10);
if ((s == e) || (*e != ','))
goto fail;
s = e + 1;
u = simple_strtoul(s, &e, 10);
if ((s == e) || (*e != '\0'))
goto fail;
*bytes = b;
*usec = u;
kfree(ratestr);
return;
fail:
pr_warn("Failed to parse network rate limit. Traffic unlimited.\n");
kfree(ratestr);
}
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 void unregister_hotplug_status_watch(struct backend_info *be)
{
if (be->have_hotplug_status_watch) {
unregister_xenbus_watch(&be->hotplug_status_watch);
kfree(be->hotplug_status_watch.node);
}
be->have_hotplug_status_watch = 0;
}
static void hotplug_status_changed(struct xenbus_watch *watch,
const char **vec,
unsigned int vec_size)
{
struct backend_info *be = container_of(watch,
struct backend_info,
hotplug_status_watch);
char *str;
unsigned int len;
str = xenbus_read(XBT_NIL, be->dev->nodename, "hotplug-status", &len);
if (IS_ERR(str))
return;
if (len == sizeof("connected")-1 && !memcmp(str, "connected", len)) {
xenbus_switch_state(be->dev, XenbusStateConnected);
/* Not interested in this watch anymore. */
unregister_hotplug_status_watch(be);
}
kfree(str);
}
static void connect(struct backend_info *be)
{
int err;
struct xenbus_device *dev = be->dev;
err = connect_rings(be);
if (err)
return;
err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
if (err) {
xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
return;
}
xen_net_read_rate(dev, &be->vif->credit_bytes,
&be->vif->credit_usec);
be->vif->remaining_credit = be->vif->credit_bytes;
unregister_hotplug_status_watch(be);
err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
hotplug_status_changed,
"%s/%s", dev->nodename, "hotplug-status");
if (err) {
/* Switch now, since we can't do a watch. */
xenbus_switch_state(dev, XenbusStateConnected);
} else {
be->have_hotplug_status_watch = 1;
}
netif_wake_queue(be->vif->dev);
}
static int connect_rings(struct backend_info *be)
{
struct xenvif *vif = be->vif;
struct xenbus_device *dev = be->dev;
unsigned long tx_ring_ref, rx_ring_ref;
unsigned int evtchn, rx_copy;
int err;
int val;
err = xenbus_gather(XBT_NIL, dev->otherend,
"tx-ring-ref", "%lu", &tx_ring_ref,
"rx-ring-ref", "%lu", &rx_ring_ref,
"event-channel", "%u", &evtchn, NULL);
if (err) {
xenbus_dev_fatal(dev, err,
"reading %s/ring-ref and event-channel",
dev->otherend);
return err;
}
err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
&rx_copy);
if (err == -ENOENT) {
err = 0;
rx_copy = 0;
}
if (err < 0) {
xenbus_dev_fatal(dev, err, "reading %s/request-rx-copy",
dev->otherend);
return err;
}
if (!rx_copy)
return -EOPNOTSUPP;
if (vif->dev->tx_queue_len != 0) {
if (xenbus_scanf(XBT_NIL, dev->otherend,
"feature-rx-notify", "%d", &val) < 0)
val = 0;
if (val)
vif->can_queue = 1;
else
/* Must be non-zero for pfifo_fast to work. */
vif->dev->tx_queue_len = 1;
}
if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg",
"%d", &val) < 0)
val = 0;
vif->can_sg = !!val;
if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4",
"%d", &val) < 0)
val = 0;
vif->gso = !!val;
if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix",
"%d", &val) < 0)
val = 0;
vif->gso_prefix = !!val;
if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload",
"%d", &val) < 0)
val = 0;
vif->csum = !val;
/* Map the shared frame, irq etc. */
err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref, evtchn);
if (err) {
xenbus_dev_fatal(dev, err,
"mapping shared-frames %lu/%lu port %u",
tx_ring_ref, rx_ring_ref, evtchn);
return err;
}
return 0;
}
/* ** Driver Registration ** */
static const struct xenbus_device_id netback_ids[] = {
{ "vif" },
{ "" }
};
static struct xenbus_driver netback = {
.name = "vif",
.owner = THIS_MODULE,
.ids = netback_ids,
.probe = netback_probe,
.remove = netback_remove,
.uevent = netback_uevent,
.otherend_changed = frontend_changed,
};
int xenvif_xenbus_init(void)
{
return xenbus_register_backend(&netback);
}
......@@ -359,7 +359,7 @@ static void xennet_tx_buf_gc(struct net_device *dev)
struct xen_netif_tx_response *txrsp;
txrsp = RING_GET_RESPONSE(&np->tx, cons);
if (txrsp->status == NETIF_RSP_NULL)
if (txrsp->status == XEN_NETIF_RSP_NULL)
continue;
id = txrsp->id;
......@@ -416,7 +416,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
larger than a page), split it it into page-sized chunks. */
while (len > PAGE_SIZE - offset) {
tx->size = PAGE_SIZE - offset;
tx->flags |= NETTXF_more_data;
tx->flags |= XEN_NETTXF_more_data;
len -= tx->size;
data += tx->size;
offset = 0;
......@@ -442,7 +442,7 @@ static void xennet_make_frags(struct sk_buff *skb, struct net_device *dev,
for (i = 0; i < frags; i++) {
skb_frag_t *frag = skb_shinfo(skb)->frags + i;
tx->flags |= NETTXF_more_data;
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);
......@@ -517,10 +517,10 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
tx->flags = 0;
if (skb->ip_summed == CHECKSUM_PARTIAL)
/* local packet? */
tx->flags |= NETTXF_csum_blank | NETTXF_data_validated;
tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated;
else if (skb->ip_summed == CHECKSUM_UNNECESSARY)
/* remote but checksummed. */
tx->flags |= NETTXF_data_validated;
tx->flags |= XEN_NETTXF_data_validated;
if (skb_shinfo(skb)->gso_size) {
struct xen_netif_extra_info *gso;
......@@ -531,7 +531,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
if (extra)
extra->flags |= XEN_NETIF_EXTRA_FLAG_MORE;
else
tx->flags |= NETTXF_extra_info;
tx->flags |= XEN_NETTXF_extra_info;
gso->u.gso.size = skb_shinfo(skb)->gso_size;
gso->u.gso.type = XEN_NETIF_GSO_TYPE_TCPV4;
......@@ -651,7 +651,7 @@ static int xennet_get_responses(struct netfront_info *np,
int err = 0;
unsigned long ret;
if (rx->flags & NETRXF_extra_info) {
if (rx->flags & XEN_NETRXF_extra_info) {
err = xennet_get_extras(np, extras, rp);
cons = np->rx.rsp_cons;
}
......@@ -688,7 +688,7 @@ static int xennet_get_responses(struct netfront_info *np,
__skb_queue_tail(list, skb);
next:
if (!(rx->flags & NETRXF_more_data))
if (!(rx->flags & XEN_NETRXF_more_data))
break;
if (cons + frags == rp) {
......@@ -983,9 +983,9 @@ static int xennet_poll(struct napi_struct *napi, int budget)
skb->truesize += skb->data_len - (RX_COPY_THRESHOLD - len);
skb->len += skb->data_len;
if (rx->flags & NETRXF_csum_blank)
if (rx->flags & XEN_NETRXF_csum_blank)
skb->ip_summed = CHECKSUM_PARTIAL;
else if (rx->flags & NETRXF_data_validated)
else if (rx->flags & XEN_NETRXF_data_validated)
skb->ip_summed = CHECKSUM_UNNECESSARY;
__skb_queue_tail(&rxq, skb);
......
......@@ -22,50 +22,50 @@
/*
* This is the 'wire' format for packets:
* Request 1: netif_tx_request -- NETTXF_* (any flags)
* [Request 2: netif_tx_extra] (only if request 1 has NETTXF_extra_info)
* [Request 3: netif_tx_extra] (only if request 2 has XEN_NETIF_EXTRA_MORE)
* Request 4: netif_tx_request -- NETTXF_more_data
* Request 5: netif_tx_request -- NETTXF_more_data
* Request 1: xen_netif_tx_request -- XEN_NETTXF_* (any flags)
* [Request 2: xen_netif_extra_info] (only if request 1 has XEN_NETTXF_extra_info)
* [Request 3: xen_netif_extra_info] (only if request 2 has XEN_NETIF_EXTRA_MORE)
* Request 4: xen_netif_tx_request -- XEN_NETTXF_more_data
* Request 5: xen_netif_tx_request -- XEN_NETTXF_more_data
* ...
* Request N: netif_tx_request -- 0
* Request N: xen_netif_tx_request -- 0
*/
/* Protocol checksum field is blank in the packet (hardware offload)? */
#define _NETTXF_csum_blank (0)
#define NETTXF_csum_blank (1U<<_NETTXF_csum_blank)
#define _XEN_NETTXF_csum_blank (0)
#define XEN_NETTXF_csum_blank (1U<<_XEN_NETTXF_csum_blank)
/* Packet data has been validated against protocol checksum. */
#define _NETTXF_data_validated (1)
#define NETTXF_data_validated (1U<<_NETTXF_data_validated)
#define _XEN_NETTXF_data_validated (1)
#define XEN_NETTXF_data_validated (1U<<_XEN_NETTXF_data_validated)
/* Packet continues in the next request descriptor. */
#define _NETTXF_more_data (2)
#define NETTXF_more_data (1U<<_NETTXF_more_data)
#define _XEN_NETTXF_more_data (2)
#define XEN_NETTXF_more_data (1U<<_XEN_NETTXF_more_data)
/* Packet to be followed by extra descriptor(s). */
#define _NETTXF_extra_info (3)
#define NETTXF_extra_info (1U<<_NETTXF_extra_info)
#define _XEN_NETTXF_extra_info (3)
#define XEN_NETTXF_extra_info (1U<<_XEN_NETTXF_extra_info)
struct xen_netif_tx_request {
grant_ref_t gref; /* Reference to buffer page */
uint16_t offset; /* Offset within buffer page */
uint16_t flags; /* NETTXF_* */
uint16_t flags; /* XEN_NETTXF_* */
uint16_t id; /* Echoed in response message. */
uint16_t size; /* Packet size in bytes. */
};
/* Types of netif_extra_info descriptors. */
#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
#define XEN_NETIF_EXTRA_TYPE_MAX (2)
/* Types of xen_netif_extra_info descriptors. */
#define XEN_NETIF_EXTRA_TYPE_NONE (0) /* Never used - invalid */
#define XEN_NETIF_EXTRA_TYPE_GSO (1) /* u.gso */
#define XEN_NETIF_EXTRA_TYPE_MAX (2)
/* netif_extra_info flags. */
#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
/* xen_netif_extra_info flags. */
#define _XEN_NETIF_EXTRA_FLAG_MORE (0)
#define XEN_NETIF_EXTRA_FLAG_MORE (1U<<_XEN_NETIF_EXTRA_FLAG_MORE)
/* GSO types - only TCPv4 currently supported. */
#define XEN_NETIF_GSO_TYPE_TCPV4 (1)
#define XEN_NETIF_GSO_TYPE_TCPV4 (1)
/*
* This structure needs to fit within both netif_tx_request and
......@@ -107,7 +107,7 @@ struct xen_netif_extra_info {
struct xen_netif_tx_response {
uint16_t id;
int16_t status; /* NETIF_RSP_* */
int16_t status; /* XEN_NETIF_RSP_* */
};
struct xen_netif_rx_request {
......@@ -116,25 +116,29 @@ struct xen_netif_rx_request {
};
/* Packet data has been validated against protocol checksum. */
#define _NETRXF_data_validated (0)
#define NETRXF_data_validated (1U<<_NETRXF_data_validated)
#define _XEN_NETRXF_data_validated (0)
#define XEN_NETRXF_data_validated (1U<<_XEN_NETRXF_data_validated)
/* Protocol checksum field is blank in the packet (hardware offload)? */
#define _NETRXF_csum_blank (1)
#define NETRXF_csum_blank (1U<<_NETRXF_csum_blank)
#define _XEN_NETRXF_csum_blank (1)
#define XEN_NETRXF_csum_blank (1U<<_XEN_NETRXF_csum_blank)
/* Packet continues in the next request descriptor. */
#define _NETRXF_more_data (2)
#define NETRXF_more_data (1U<<_NETRXF_more_data)
#define _XEN_NETRXF_more_data (2)
#define XEN_NETRXF_more_data (1U<<_XEN_NETRXF_more_data)
/* Packet to be followed by extra descriptor(s). */
#define _NETRXF_extra_info (3)
#define NETRXF_extra_info (1U<<_NETRXF_extra_info)
#define _XEN_NETRXF_extra_info (3)
#define XEN_NETRXF_extra_info (1U<<_XEN_NETRXF_extra_info)
/* GSO Prefix descriptor. */
#define _XEN_NETRXF_gso_prefix (4)
#define XEN_NETRXF_gso_prefix (1U<<_XEN_NETRXF_gso_prefix)
struct xen_netif_rx_response {
uint16_t id;
uint16_t offset; /* Offset in page of start of received packet */
uint16_t flags; /* NETRXF_* */
uint16_t flags; /* XEN_NETRXF_* */
int16_t status; /* -ve: BLKIF_RSP_* ; +ve: Rx'ed pkt size. */
};
......@@ -149,10 +153,10 @@ DEFINE_RING_TYPES(xen_netif_rx,
struct xen_netif_rx_request,
struct xen_netif_rx_response);
#define NETIF_RSP_DROPPED -2
#define NETIF_RSP_ERROR -1
#define NETIF_RSP_OKAY 0
/* No response: used for auxiliary requests (e.g., netif_tx_extra). */
#define NETIF_RSP_NULL 1
#define XEN_NETIF_RSP_DROPPED -2
#define XEN_NETIF_RSP_ERROR -1
#define XEN_NETIF_RSP_OKAY 0
/* No response: used for auxiliary requests (e.g., xen_netif_extra_info). */
#define XEN_NETIF_RSP_NULL 1
#endif
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册