提交 e9ce7cb6 编写于 作者: W Wei Liu 提交者: David S. Miller

xen-netback: Factor queue-specific data into queue struct

In preparation for multi-queue support in xen-netback, move the
queue-specific data from struct xenvif into struct xenvif_queue, and
update the rest of the code to use this.

Also adds loops over queues where appropriate, even though only one is
configured at this point, and uses alloc_netdev_mq() and the
corresponding multi-queue netif wake/start/stop functions in preparation
for multiple active queues.

Finally, implements a trivial queue selection function suitable for
ndo_select_queue, which simply returns 0 for a single queue and uses
skb_get_hash() to compute the queue index otherwise.
Signed-off-by: NAndrew J. Bennieston <andrew.bennieston@citrix.com>
Signed-off-by: NWei Liu <wei.liu2@citrix.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 a55d9766
......@@ -99,22 +99,43 @@ struct xenvif_rx_meta {
*/
#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
unsigned int handle;
/* Queue name is interface name with "-qNNN" appended */
#define QUEUE_NAME_SIZE (IFNAMSIZ + 5)
/* Is this interface disabled? True when backend discovers
* frontend is rogue.
/* IRQ name is queue name with "-tx" or "-rx" appended */
#define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3)
struct xenvif;
struct xenvif_stats {
/* Stats fields to be updated per-queue.
* A subset of struct net_device_stats that contains only the
* fields that are updated in netback.c for each queue.
*/
bool disabled;
unsigned int rx_bytes;
unsigned int rx_packets;
unsigned int tx_bytes;
unsigned int tx_packets;
/* Additional stats used by xenvif */
unsigned long rx_gso_checksum_fixup;
unsigned long tx_zerocopy_sent;
unsigned long tx_zerocopy_success;
unsigned long tx_zerocopy_fail;
unsigned long tx_frag_overflow;
};
struct xenvif_queue { /* Per-queue data for xenvif */
unsigned int id; /* Queue ID, 0-based */
char name[QUEUE_NAME_SIZE]; /* DEVNAME-qN */
struct xenvif *vif; /* Parent VIF */
/* Use NAPI for guest TX */
struct napi_struct napi;
/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
unsigned int tx_irq;
/* Only used when feature-split-event-channels = 1 */
char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
char tx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-tx */
struct xen_netif_tx_back_ring tx;
struct sk_buff_head tx_queue;
struct page *mmap_pages[MAX_PENDING_REQS];
......@@ -150,7 +171,7 @@ struct xenvif {
/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
unsigned int rx_irq;
/* Only used when feature-split-event-channels = 1 */
char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */
struct xen_netif_rx_back_ring rx;
struct sk_buff_head rx_queue;
RING_IDX rx_last_skb_slots;
......@@ -165,6 +186,22 @@ struct xenvif {
*/
struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE];
/* 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;
u64 credit_window_start;
/* Statistics */
struct xenvif_stats stats;
};
struct xenvif {
/* Unique identifier for this interface. */
domid_t domid;
unsigned int handle;
u8 fe_dev_addr[6];
/* Frontend feature information. */
......@@ -178,19 +215,13 @@ struct xenvif {
/* Internal feature information. */
u8 can_queue:1; /* can queue packets for receiver? */
/* 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;
u64 credit_window_start;
/* Is this interface disabled? True when backend discovers
* frontend is rogue.
*/
bool disabled;
/* Statistics */
unsigned long rx_gso_checksum_fixup;
unsigned long tx_zerocopy_sent;
unsigned long tx_zerocopy_success;
unsigned long tx_zerocopy_fail;
unsigned long tx_frag_overflow;
/* Queues */
struct xenvif_queue *queues;
/* Miscellaneous private stuff. */
struct net_device *dev;
......@@ -205,7 +236,9 @@ struct xenvif *xenvif_alloc(struct device *parent,
domid_t domid,
unsigned int handle);
int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
int xenvif_init_queue(struct xenvif_queue *queue);
int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
unsigned long rx_ring_ref, unsigned int tx_evtchn,
unsigned int rx_evtchn);
void xenvif_disconnect(struct xenvif *vif);
......@@ -216,44 +249,47 @@ void xenvif_xenbus_fini(void);
int xenvif_schedulable(struct xenvif *vif);
int xenvif_must_stop_queue(struct xenvif *vif);
int xenvif_must_stop_queue(struct xenvif_queue *queue);
int xenvif_queue_stopped(struct xenvif_queue *queue);
void xenvif_wake_queue(struct xenvif_queue *queue);
/* (Un)Map communication rings. */
void xenvif_unmap_frontend_rings(struct xenvif *vif);
int xenvif_map_frontend_rings(struct xenvif *vif,
void xenvif_unmap_frontend_rings(struct xenvif_queue *queue);
int xenvif_map_frontend_rings(struct xenvif_queue *queue,
grant_ref_t tx_ring_ref,
grant_ref_t rx_ring_ref);
/* Check for SKBs from frontend and schedule backend processing */
void xenvif_napi_schedule_or_enable_events(struct xenvif *vif);
void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue);
/* Prevent the device from generating any further traffic. */
void xenvif_carrier_off(struct xenvif *vif);
int xenvif_tx_action(struct xenvif *vif, int budget);
int xenvif_tx_action(struct xenvif_queue *queue, int budget);
int xenvif_kthread_guest_rx(void *data);
void xenvif_kick_thread(struct xenvif *vif);
void xenvif_kick_thread(struct xenvif_queue *queue);
int xenvif_dealloc_kthread(void *data);
/* Determine whether the needed number of slots (req) are available,
* and set req_event if not.
*/
bool xenvif_rx_ring_slots_available(struct xenvif *vif, int needed);
bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed);
void xenvif_stop_queue(struct xenvif *vif);
void xenvif_carrier_on(struct xenvif *vif);
/* Callback from stack when TX packet can be released */
void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
/* Unmap a pending page and release it back to the guest */
void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx);
void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
static inline pending_ring_idx_t nr_pending_reqs(struct xenvif *vif)
static inline pending_ring_idx_t nr_pending_reqs(struct xenvif_queue *queue)
{
return MAX_PENDING_REQS -
vif->pending_prod + vif->pending_cons;
queue->pending_prod + queue->pending_cons;
}
/* Callback from stack when TX packet can be released */
......
......@@ -34,7 +34,6 @@
#include <linux/ethtool.h>
#include <linux/rtnetlink.h>
#include <linux/if_vlan.h>
#include <linux/vmalloc.h>
#include <xen/events.h>
#include <asm/xen/hypercall.h>
......@@ -43,6 +42,16 @@
#define XENVIF_QUEUE_LENGTH 32
#define XENVIF_NAPI_WEIGHT 64
static inline void xenvif_stop_queue(struct xenvif_queue *queue)
{
struct net_device *dev = queue->vif->dev;
if (!queue->vif->can_queue)
return;
netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id));
}
int xenvif_schedulable(struct xenvif *vif)
{
return netif_running(vif->dev) && netif_carrier_ok(vif->dev);
......@@ -50,33 +59,34 @@ int xenvif_schedulable(struct xenvif *vif)
static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
{
struct xenvif *vif = dev_id;
struct xenvif_queue *queue = dev_id;
if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))
napi_schedule(&vif->napi);
if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))
napi_schedule(&queue->napi);
return IRQ_HANDLED;
}
static int xenvif_poll(struct napi_struct *napi, int budget)
int xenvif_poll(struct napi_struct *napi, int budget)
{
struct xenvif *vif = container_of(napi, struct xenvif, napi);
struct xenvif_queue *queue =
container_of(napi, struct xenvif_queue, napi);
int work_done;
/* This vif is rogue, we pretend we've there is nothing to do
* for this vif to deschedule it from NAPI. But this interface
* will be turned off in thread context later.
*/
if (unlikely(vif->disabled)) {
if (unlikely(queue->vif->disabled)) {
napi_complete(napi);
return 0;
}
work_done = xenvif_tx_action(vif, budget);
work_done = xenvif_tx_action(queue, budget);
if (work_done < budget) {
napi_complete(napi);
xenvif_napi_schedule_or_enable_events(vif);
xenvif_napi_schedule_or_enable_events(queue);
}
return work_done;
......@@ -84,9 +94,9 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
{
struct xenvif *vif = dev_id;
struct xenvif_queue *queue = dev_id;
xenvif_kick_thread(vif);
xenvif_kick_thread(queue);
return IRQ_HANDLED;
}
......@@ -99,28 +109,81 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}
static void xenvif_wake_queue(unsigned long data)
int xenvif_queue_stopped(struct xenvif_queue *queue)
{
struct net_device *dev = queue->vif->dev;
unsigned int id = queue->id;
return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id));
}
void xenvif_wake_queue(struct xenvif_queue *queue)
{
struct net_device *dev = queue->vif->dev;
unsigned int id = queue->id;
netif_tx_wake_queue(netdev_get_tx_queue(dev, id));
}
/* Callback to wake the queue and drain it on timeout */
static void xenvif_wake_queue_callback(unsigned long data)
{
struct xenvif *vif = (struct xenvif *)data;
struct xenvif_queue *queue = (struct xenvif_queue *)data;
if (xenvif_queue_stopped(queue)) {
netdev_err(queue->vif->dev, "draining TX queue\n");
queue->rx_queue_purge = true;
xenvif_kick_thread(queue);
xenvif_wake_queue(queue);
}
}
if (netif_queue_stopped(vif->dev)) {
netdev_err(vif->dev, "draining TX queue\n");
vif->rx_queue_purge = true;
xenvif_kick_thread(vif);
netif_wake_queue(vif->dev);
static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
void *accel_priv, select_queue_fallback_t fallback)
{
struct xenvif *vif = netdev_priv(dev);
unsigned int num_queues = dev->real_num_tx_queues;
u32 hash;
u16 queue_index;
/* First, check if there is only one queue to optimise the
* single-queue or old frontend scenario.
*/
if (num_queues == 1) {
queue_index = 0;
} else {
/* Use skb_get_hash to obtain an L4 hash if available */
hash = skb_get_hash(skb);
queue_index = hash % num_queues;
}
return queue_index;
}
static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
struct xenvif_queue *queue = NULL;
unsigned int num_queues = dev->real_num_tx_queues;
u16 index;
int min_slots_needed;
BUG_ON(skb->dev != dev);
/* Drop the packet if vif is not ready */
if (vif->task == NULL ||
vif->dealloc_task == NULL ||
/* Drop the packet if queues are not set up */
if (num_queues < 1)
goto drop;
/* Obtain the queue to be used to transmit this packet */
index = skb_get_queue_mapping(skb);
if (index >= num_queues) {
pr_warn_ratelimited("Invalid queue %hu for packet on interface %s\n.",
index, vif->dev->name);
index %= num_queues;
}
queue = &vif->queues[index];
/* Drop the packet if queue is not ready */
if (queue->task == NULL ||
queue->dealloc_task == NULL ||
!xenvif_schedulable(vif))
goto drop;
......@@ -139,16 +202,16 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
* then turn off the queue to give the ring a chance to
* drain.
*/
if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) {
vif->wake_queue.function = xenvif_wake_queue;
vif->wake_queue.data = (unsigned long)vif;
xenvif_stop_queue(vif);
mod_timer(&vif->wake_queue,
if (!xenvif_rx_ring_slots_available(queue, min_slots_needed)) {
queue->wake_queue.function = xenvif_wake_queue_callback;
queue->wake_queue.data = (unsigned long)queue;
xenvif_stop_queue(queue);
mod_timer(&queue->wake_queue,
jiffies + rx_drain_timeout_jiffies);
}
skb_queue_tail(&vif->rx_queue, skb);
xenvif_kick_thread(vif);
skb_queue_tail(&queue->rx_queue, skb);
xenvif_kick_thread(queue);
return NETDEV_TX_OK;
......@@ -161,25 +224,65 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{
struct xenvif *vif = netdev_priv(dev);
struct xenvif_queue *queue = NULL;
unsigned int num_queues = dev->real_num_tx_queues;
unsigned long rx_bytes = 0;
unsigned long rx_packets = 0;
unsigned long tx_bytes = 0;
unsigned long tx_packets = 0;
unsigned int index;
if (vif->queues == NULL)
goto out;
/* Aggregate tx and rx stats from each queue */
for (index = 0; index < num_queues; ++index) {
queue = &vif->queues[index];
rx_bytes += queue->stats.rx_bytes;
rx_packets += queue->stats.rx_packets;
tx_bytes += queue->stats.tx_bytes;
tx_packets += queue->stats.tx_packets;
}
out:
vif->dev->stats.rx_bytes = rx_bytes;
vif->dev->stats.rx_packets = rx_packets;
vif->dev->stats.tx_bytes = tx_bytes;
vif->dev->stats.tx_packets = tx_packets;
return &vif->dev->stats;
}
static void xenvif_up(struct xenvif *vif)
{
napi_enable(&vif->napi);
enable_irq(vif->tx_irq);
if (vif->tx_irq != vif->rx_irq)
enable_irq(vif->rx_irq);
xenvif_napi_schedule_or_enable_events(vif);
struct xenvif_queue *queue = NULL;
unsigned int num_queues = vif->dev->real_num_tx_queues;
unsigned int queue_index;
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
queue = &vif->queues[queue_index];
napi_enable(&queue->napi);
enable_irq(queue->tx_irq);
if (queue->tx_irq != queue->rx_irq)
enable_irq(queue->rx_irq);
xenvif_napi_schedule_or_enable_events(queue);
}
}
static void xenvif_down(struct xenvif *vif)
{
napi_disable(&vif->napi);
disable_irq(vif->tx_irq);
if (vif->tx_irq != vif->rx_irq)
disable_irq(vif->rx_irq);
del_timer_sync(&vif->credit_timeout);
struct xenvif_queue *queue = NULL;
unsigned int num_queues = vif->dev->real_num_tx_queues;
unsigned int queue_index;
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
queue = &vif->queues[queue_index];
napi_disable(&queue->napi);
disable_irq(queue->tx_irq);
if (queue->tx_irq != queue->rx_irq)
disable_irq(queue->rx_irq);
del_timer_sync(&queue->credit_timeout);
}
}
static int xenvif_open(struct net_device *dev)
......@@ -187,7 +290,7 @@ 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);
netif_tx_start_all_queues(dev);
return 0;
}
......@@ -196,7 +299,7 @@ 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);
netif_tx_stop_all_queues(dev);
return 0;
}
......@@ -236,29 +339,29 @@ static const struct xenvif_stat {
} xenvif_stats[] = {
{
"rx_gso_checksum_fixup",
offsetof(struct xenvif, rx_gso_checksum_fixup)
offsetof(struct xenvif_stats, rx_gso_checksum_fixup)
},
/* If (sent != success + fail), there are probably packets never
* freed up properly!
*/
{
"tx_zerocopy_sent",
offsetof(struct xenvif, tx_zerocopy_sent),
offsetof(struct xenvif_stats, tx_zerocopy_sent),
},
{
"tx_zerocopy_success",
offsetof(struct xenvif, tx_zerocopy_success),
offsetof(struct xenvif_stats, tx_zerocopy_success),
},
{
"tx_zerocopy_fail",
offsetof(struct xenvif, tx_zerocopy_fail)
offsetof(struct xenvif_stats, tx_zerocopy_fail)
},
/* Number of packets exceeding MAX_SKB_FRAG slots. You should use
* a guest with the same MAX_SKB_FRAG
*/
{
"tx_frag_overflow",
offsetof(struct xenvif, tx_frag_overflow)
offsetof(struct xenvif_stats, tx_frag_overflow)
},
};
......@@ -275,11 +378,20 @@ static int xenvif_get_sset_count(struct net_device *dev, int string_set)
static void xenvif_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 * data)
{
void *vif = netdev_priv(dev);
struct xenvif *vif = netdev_priv(dev);
unsigned int num_queues = dev->real_num_tx_queues;
int i;
for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++)
data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset);
unsigned int queue_index;
struct xenvif_stats *vif_stats;
for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
unsigned long accum = 0;
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
vif_stats = &vif->queues[queue_index].stats;
accum += *(unsigned long *)(vif_stats + xenvif_stats[i].offset);
}
data[i] = accum;
}
}
static void xenvif_get_strings(struct net_device *dev, u32 stringset, u8 * data)
......@@ -312,6 +424,7 @@ static const struct net_device_ops xenvif_netdev_ops = {
.ndo_fix_features = xenvif_fix_features,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_select_queue = xenvif_select_queue,
};
struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
......@@ -321,10 +434,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
struct net_device *dev;
struct xenvif *vif;
char name[IFNAMSIZ] = {};
int i;
snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle);
dev = alloc_netdev(sizeof(struct xenvif), name, ether_setup);
dev = alloc_netdev_mq(sizeof(struct xenvif), name, ether_setup, 1);
if (dev == NULL) {
pr_warn("Could not allocate netdev for %s\n", name);
return ERR_PTR(-ENOMEM);
......@@ -339,15 +451,13 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
vif->can_sg = 1;
vif->ip_csum = 1;
vif->dev = dev;
vif->disabled = false;
vif->credit_bytes = vif->remaining_credit = ~0UL;
vif->credit_usec = 0UL;
init_timer(&vif->credit_timeout);
vif->credit_window_start = get_jiffies_64();
init_timer(&vif->wake_queue);
/* Start out with no queues. The call below does not require
* rtnl_lock() as it happens before register_netdev().
*/
vif->queues = NULL;
netif_set_real_num_tx_queues(dev, 0);
dev->netdev_ops = &xenvif_netdev_ops;
dev->hw_features = NETIF_F_SG |
......@@ -358,34 +468,6 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
dev->tx_queue_len = XENVIF_QUEUE_LENGTH;
skb_queue_head_init(&vif->rx_queue);
skb_queue_head_init(&vif->tx_queue);
vif->pending_cons = 0;
vif->pending_prod = MAX_PENDING_REQS;
for (i = 0; i < MAX_PENDING_REQS; i++)
vif->pending_ring[i] = i;
spin_lock_init(&vif->callback_lock);
spin_lock_init(&vif->response_lock);
/* If ballooning is disabled, this will consume real memory, so you
* better enable it. The long term solution would be to use just a
* bunch of valid page descriptors, without dependency on ballooning
*/
err = alloc_xenballooned_pages(MAX_PENDING_REQS,
vif->mmap_pages,
false);
if (err) {
netdev_err(dev, "Could not reserve mmap_pages\n");
return ERR_PTR(-ENOMEM);
}
for (i = 0; i < MAX_PENDING_REQS; i++) {
vif->pending_tx_info[i].callback_struct = (struct ubuf_info)
{ .callback = xenvif_zerocopy_callback,
.ctx = NULL,
.desc = i };
vif->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
}
/*
* Initialise a dummy MAC address. We choose the numerically
* largest non-broadcast address to prevent the address getting
......@@ -395,8 +477,6 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
memset(dev->dev_addr, 0xFF, ETH_ALEN);
dev->dev_addr[0] &= ~0x01;
netif_napi_add(dev, &vif->napi, xenvif_poll, XENVIF_NAPI_WEIGHT);
netif_carrier_off(dev);
err = register_netdev(dev);
......@@ -413,98 +493,147 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
return vif;
}
int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
int xenvif_init_queue(struct xenvif_queue *queue)
{
int err, i;
queue->credit_bytes = queue->remaining_credit = ~0UL;
queue->credit_usec = 0UL;
init_timer(&queue->credit_timeout);
queue->credit_window_start = get_jiffies_64();
skb_queue_head_init(&queue->rx_queue);
skb_queue_head_init(&queue->tx_queue);
queue->pending_cons = 0;
queue->pending_prod = MAX_PENDING_REQS;
for (i = 0; i < MAX_PENDING_REQS; ++i)
queue->pending_ring[i] = i;
spin_lock_init(&queue->callback_lock);
spin_lock_init(&queue->response_lock);
/* If ballooning is disabled, this will consume real memory, so you
* better enable it. The long term solution would be to use just a
* bunch of valid page descriptors, without dependency on ballooning
*/
err = alloc_xenballooned_pages(MAX_PENDING_REQS,
queue->mmap_pages,
false);
if (err) {
netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n");
return -ENOMEM;
}
for (i = 0; i < MAX_PENDING_REQS; i++) {
queue->pending_tx_info[i].callback_struct = (struct ubuf_info)
{ .callback = xenvif_zerocopy_callback,
.ctx = NULL,
.desc = i };
queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
}
init_timer(&queue->wake_queue);
netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
XENVIF_NAPI_WEIGHT);
return 0;
}
void xenvif_carrier_on(struct xenvif *vif)
{
rtnl_lock();
if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
dev_set_mtu(vif->dev, ETH_DATA_LEN);
netdev_update_features(vif->dev);
netif_carrier_on(vif->dev);
if (netif_running(vif->dev))
xenvif_up(vif);
rtnl_unlock();
}
int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
unsigned long rx_ring_ref, unsigned int tx_evtchn,
unsigned int rx_evtchn)
{
struct task_struct *task;
int err = -ENOMEM;
BUG_ON(vif->tx_irq);
BUG_ON(vif->task);
BUG_ON(vif->dealloc_task);
BUG_ON(queue->tx_irq);
BUG_ON(queue->task);
BUG_ON(queue->dealloc_task);
err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref);
err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref);
if (err < 0)
goto err;
init_waitqueue_head(&vif->wq);
init_waitqueue_head(&vif->dealloc_wq);
init_waitqueue_head(&queue->wq);
init_waitqueue_head(&queue->dealloc_wq);
if (tx_evtchn == rx_evtchn) {
/* feature-split-event-channels == 0 */
err = bind_interdomain_evtchn_to_irqhandler(
vif->domid, tx_evtchn, xenvif_interrupt, 0,
vif->dev->name, vif);
queue->vif->domid, tx_evtchn, xenvif_interrupt, 0,
queue->name, queue);
if (err < 0)
goto err_unmap;
vif->tx_irq = vif->rx_irq = err;
disable_irq(vif->tx_irq);
queue->tx_irq = queue->rx_irq = err;
disable_irq(queue->tx_irq);
} else {
/* feature-split-event-channels == 1 */
snprintf(vif->tx_irq_name, sizeof(vif->tx_irq_name),
"%s-tx", vif->dev->name);
snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
"%s-tx", queue->name);
err = bind_interdomain_evtchn_to_irqhandler(
vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
vif->tx_irq_name, vif);
queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
queue->tx_irq_name, queue);
if (err < 0)
goto err_unmap;
vif->tx_irq = err;
disable_irq(vif->tx_irq);
queue->tx_irq = err;
disable_irq(queue->tx_irq);
snprintf(vif->rx_irq_name, sizeof(vif->rx_irq_name),
"%s-rx", vif->dev->name);
snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
"%s-rx", queue->name);
err = bind_interdomain_evtchn_to_irqhandler(
vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
vif->rx_irq_name, vif);
queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
queue->rx_irq_name, queue);
if (err < 0)
goto err_tx_unbind;
vif->rx_irq = err;
disable_irq(vif->rx_irq);
queue->rx_irq = err;
disable_irq(queue->rx_irq);
}
task = kthread_create(xenvif_kthread_guest_rx,
(void *)vif, "%s-guest-rx", vif->dev->name);
(void *)queue, "%s-guest-rx", queue->name);
if (IS_ERR(task)) {
pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
pr_warn("Could not allocate kthread for %s\n", queue->name);
err = PTR_ERR(task);
goto err_rx_unbind;
}
vif->task = task;
queue->task = task;
task = kthread_create(xenvif_dealloc_kthread,
(void *)vif, "%s-dealloc", vif->dev->name);
(void *)queue, "%s-dealloc", queue->name);
if (IS_ERR(task)) {
pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
pr_warn("Could not allocate kthread for %s\n", queue->name);
err = PTR_ERR(task);
goto err_rx_unbind;
}
queue->dealloc_task = task;
vif->dealloc_task = task;
rtnl_lock();
if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
dev_set_mtu(vif->dev, ETH_DATA_LEN);
netdev_update_features(vif->dev);
netif_carrier_on(vif->dev);
if (netif_running(vif->dev))
xenvif_up(vif);
rtnl_unlock();
wake_up_process(vif->task);
wake_up_process(vif->dealloc_task);
wake_up_process(queue->task);
wake_up_process(queue->dealloc_task);
return 0;
err_rx_unbind:
unbind_from_irqhandler(vif->rx_irq, vif);
vif->rx_irq = 0;
unbind_from_irqhandler(queue->rx_irq, queue);
queue->rx_irq = 0;
err_tx_unbind:
unbind_from_irqhandler(vif->tx_irq, vif);
vif->tx_irq = 0;
unbind_from_irqhandler(queue->tx_irq, queue);
queue->tx_irq = 0;
err_unmap:
xenvif_unmap_frontend_rings(vif);
xenvif_unmap_frontend_rings(queue);
err:
module_put(THIS_MODULE);
return err;
......@@ -521,38 +650,67 @@ void xenvif_carrier_off(struct xenvif *vif)
rtnl_unlock();
}
static void xenvif_wait_unmap_timeout(struct xenvif_queue *queue,
unsigned int worst_case_skb_lifetime)
{
int i, unmap_timeout = 0;
for (i = 0; i < MAX_PENDING_REQS; ++i) {
if (queue->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
unmap_timeout++;
schedule_timeout(msecs_to_jiffies(1000));
if (unmap_timeout > worst_case_skb_lifetime &&
net_ratelimit())
netdev_err(queue->vif->dev,
"Page still granted! Index: %x\n",
i);
i = -1;
}
}
}
void xenvif_disconnect(struct xenvif *vif)
{
struct xenvif_queue *queue = NULL;
unsigned int num_queues = vif->dev->real_num_tx_queues;
unsigned int queue_index;
if (netif_carrier_ok(vif->dev))
xenvif_carrier_off(vif);
if (vif->task) {
del_timer_sync(&vif->wake_queue);
kthread_stop(vif->task);
vif->task = NULL;
}
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
queue = &vif->queues[queue_index];
if (vif->dealloc_task) {
kthread_stop(vif->dealloc_task);
vif->dealloc_task = NULL;
}
if (queue->task) {
del_timer_sync(&queue->wake_queue);
kthread_stop(queue->task);
queue->task = NULL;
}
if (vif->tx_irq) {
if (vif->tx_irq == vif->rx_irq)
unbind_from_irqhandler(vif->tx_irq, vif);
else {
unbind_from_irqhandler(vif->tx_irq, vif);
unbind_from_irqhandler(vif->rx_irq, vif);
if (queue->dealloc_task) {
kthread_stop(queue->dealloc_task);
queue->dealloc_task = NULL;
}
if (queue->tx_irq) {
if (queue->tx_irq == queue->rx_irq)
unbind_from_irqhandler(queue->tx_irq, queue);
else {
unbind_from_irqhandler(queue->tx_irq, queue);
unbind_from_irqhandler(queue->rx_irq, queue);
}
queue->tx_irq = 0;
}
vif->tx_irq = 0;
}
xenvif_unmap_frontend_rings(vif);
xenvif_unmap_frontend_rings(queue);
}
}
void xenvif_free(struct xenvif *vif)
{
int i, unmap_timeout = 0;
struct xenvif_queue *queue = NULL;
unsigned int num_queues = vif->dev->real_num_tx_queues;
unsigned int queue_index;
/* Here we want to avoid timeout messages if an skb can be legitimately
* stuck somewhere else. Realistically this could be an another vif's
* internal or QDisc queue. That another vif also has this
......@@ -567,31 +725,23 @@ void xenvif_free(struct xenvif *vif)
unsigned int worst_case_skb_lifetime = (rx_drain_timeout_msecs/1000) *
DIV_ROUND_UP(XENVIF_QUEUE_LENGTH, (XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS));
for (i = 0; i < MAX_PENDING_REQS; ++i) {
if (vif->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
unmap_timeout++;
schedule_timeout(msecs_to_jiffies(1000));
if (unmap_timeout > worst_case_skb_lifetime &&
net_ratelimit())
netdev_err(vif->dev,
"Page still granted! Index: %x\n",
i);
/* If there are still unmapped pages, reset the loop to
* start checking again. We shouldn't exit here until
* dealloc thread and NAPI instance release all the
* pages. If a kernel bug causes the skbs to stall
* somewhere, the interface cannot be brought down
* properly.
*/
i = -1;
}
}
unregister_netdev(vif->dev);
free_xenballooned_pages(MAX_PENDING_REQS, vif->mmap_pages);
for (queue_index = 0; queue_index < num_queues; ++queue_index) {
queue = &vif->queues[queue_index];
netif_napi_del(&vif->napi);
xenvif_wait_unmap_timeout(queue, worst_case_skb_lifetime);
free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
unregister_netdev(vif->dev);
netif_napi_del(&queue->napi);
}
/* Free the array of queues. The call below does not require
* rtnl_lock() because it happens after unregister_netdev().
*/
netif_set_real_num_tx_queues(vif->dev, 0);
vfree(vif->queues);
vif->queues = NULL;
free_netdev(vif->dev);
......
......@@ -70,33 +70,33 @@ unsigned int rx_drain_timeout_jiffies;
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,
static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
u8 status);
static void make_tx_response(struct xenvif *vif,
static void make_tx_response(struct xenvif_queue *queue,
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 inline int tx_work_todo(struct xenvif_queue *queue);
static inline int rx_work_todo(struct xenvif_queue *queue);
static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue,
u16 id,
s8 st,
u16 offset,
u16 size,
u16 flags);
static inline unsigned long idx_to_pfn(struct xenvif *vif,
static inline unsigned long idx_to_pfn(struct xenvif_queue *queue,
u16 idx)
{
return page_to_pfn(vif->mmap_pages[idx]);
return page_to_pfn(queue->mmap_pages[idx]);
}
static inline unsigned long idx_to_kaddr(struct xenvif *vif,
static inline unsigned long idx_to_kaddr(struct xenvif_queue *queue,
u16 idx)
{
return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx));
return (unsigned long)pfn_to_kaddr(idx_to_pfn(queue, idx));
}
#define callback_param(vif, pending_idx) \
......@@ -104,13 +104,13 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif,
/* Find the containing VIF's structure from a pointer in pending_tx_info array
*/
static inline struct xenvif *ubuf_to_vif(const struct ubuf_info *ubuf)
static inline struct xenvif_queue *ubuf_to_queue(const 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,
struct xenvif_queue,
pending_tx_info[0]);
}
......@@ -136,24 +136,24 @@ 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)
bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed)
{
RING_IDX prod, cons;
do {
prod = vif->rx.sring->req_prod;
cons = vif->rx.req_cons;
prod = queue->rx.sring->req_prod;
cons = queue->rx.req_cons;
if (prod - cons >= needed)
return true;
vif->rx.sring->req_event = prod + 1;
queue->rx.sring->req_event = prod + 1;
/* Make sure event is visible before we check prod
* again.
*/
mb();
} while (vif->rx.sring->req_prod != prod);
} while (queue->rx.sring->req_prod != prod);
return false;
}
......@@ -207,13 +207,13 @@ struct netrx_pending_operations {
grant_ref_t copy_gref;
};
static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue,
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++);
req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++);
meta = npo->meta + npo->meta_prod++;
meta->gso_type = XEN_NETIF_GSO_TYPE_NONE;
......@@ -231,11 +231,11 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif,
* 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,
static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb,
struct netrx_pending_operations *npo,
struct page *page, unsigned long size,
unsigned long offset, int *head,
struct xenvif *foreign_vif,
struct xenvif_queue *foreign_queue,
grant_ref_t foreign_gref)
{
struct gnttab_copy *copy_gop;
......@@ -268,7 +268,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
*/
BUG_ON(*head);
meta = get_next_rx_buffer(vif, npo);
meta = get_next_rx_buffer(queue, npo);
}
if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
......@@ -278,8 +278,8 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
copy_gop->flags = GNTCOPY_dest_gref;
copy_gop->len = bytes;
if (foreign_vif) {
copy_gop->source.domid = foreign_vif->domid;
if (foreign_queue) {
copy_gop->source.domid = foreign_queue->vif->domid;
copy_gop->source.u.ref = foreign_gref;
copy_gop->flags |= GNTCOPY_source_gref;
} else {
......@@ -289,7 +289,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
}
copy_gop->source.offset = offset;
copy_gop->dest.domid = vif->domid;
copy_gop->dest.domid = queue->vif->domid;
copy_gop->dest.offset = npo->copy_off;
copy_gop->dest.u.ref = npo->copy_gref;
......@@ -314,8 +314,8 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
}
if (*head && ((1 << gso_type) & vif->gso_mask))
vif->rx.req_cons++;
if (*head && ((1 << gso_type) & queue->vif->gso_mask))
queue->rx.req_cons++;
*head = 0; /* There must be something in this buffer now. */
......@@ -337,13 +337,13 @@ static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb,
const int i,
const struct ubuf_info *ubuf)
{
struct xenvif *foreign_vif = ubuf_to_vif(ubuf);
struct xenvif_queue *foreign_queue = ubuf_to_queue(ubuf);
do {
u16 pending_idx = ubuf->desc;
if (skb_shinfo(skb)->frags[i].page.p ==
foreign_vif->mmap_pages[pending_idx])
foreign_queue->mmap_pages[pending_idx])
break;
ubuf = (struct ubuf_info *) ubuf->ctx;
} while (ubuf);
......@@ -364,7 +364,8 @@ static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb,
* frontend-side LRO).
*/
static int xenvif_gop_skb(struct sk_buff *skb,
struct netrx_pending_operations *npo)
struct netrx_pending_operations *npo,
struct xenvif_queue *queue)
{
struct xenvif *vif = netdev_priv(skb->dev);
int nr_frags = skb_shinfo(skb)->nr_frags;
......@@ -390,7 +391,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
/* 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++);
req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++);
meta = npo->meta + npo->meta_prod++;
meta->gso_type = gso_type;
meta->gso_size = skb_shinfo(skb)->gso_size;
......@@ -398,7 +399,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
meta->id = req->id;
}
req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++);
req = RING_GET_REQUEST(&queue->rx, queue->rx.req_cons++);
meta = npo->meta + npo->meta_prod++;
if ((1 << gso_type) & vif->gso_mask) {
......@@ -422,7 +423,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
if (data + len > skb_tail_pointer(skb))
len = skb_tail_pointer(skb) - data;
xenvif_gop_frag_copy(vif, skb, npo,
xenvif_gop_frag_copy(queue, skb, npo,
virt_to_page(data), len, offset, &head,
NULL,
0);
......@@ -433,7 +434,7 @@ static int xenvif_gop_skb(struct sk_buff *skb,
/* This variable also signals whether foreign_gref has a real
* value or not.
*/
struct xenvif *foreign_vif = NULL;
struct xenvif_queue *foreign_queue = NULL;
grant_ref_t foreign_gref;
if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
......@@ -458,8 +459,9 @@ static int xenvif_gop_skb(struct sk_buff *skb,
if (likely(ubuf)) {
u16 pending_idx = ubuf->desc;
foreign_vif = ubuf_to_vif(ubuf);
foreign_gref = foreign_vif->pending_tx_info[pending_idx].req.gref;
foreign_queue = ubuf_to_queue(ubuf);
foreign_gref =
foreign_queue->pending_tx_info[pending_idx].req.gref;
/* Just a safety measure. If this was the last
* element on the list, the for loop will
* iterate again if a local page were added to
......@@ -477,13 +479,13 @@ static int xenvif_gop_skb(struct sk_buff *skb,
*/
ubuf = head_ubuf;
}
xenvif_gop_frag_copy(vif, skb, npo,
xenvif_gop_frag_copy(queue, 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_vif ? foreign_gref : UINT_MAX);
foreign_queue,
foreign_queue ? foreign_gref : UINT_MAX);
}
return npo->meta_prod - old_meta_prod;
......@@ -515,7 +517,7 @@ static int xenvif_check_gop(struct xenvif *vif, int nr_meta_slots,
return status;
}
static void xenvif_add_frag_responses(struct xenvif *vif, int status,
static void xenvif_add_frag_responses(struct xenvif_queue *queue, int status,
struct xenvif_rx_meta *meta,
int nr_meta_slots)
{
......@@ -536,7 +538,7 @@ static void xenvif_add_frag_responses(struct xenvif *vif, int status,
flags = XEN_NETRXF_more_data;
offset = 0;
make_rx_response(vif, meta[i].id, status, offset,
make_rx_response(queue, meta[i].id, status, offset,
meta[i].size, flags);
}
}
......@@ -547,12 +549,12 @@ struct xenvif_rx_cb {
#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb)
void xenvif_kick_thread(struct xenvif *vif)
void xenvif_kick_thread(struct xenvif_queue *queue)
{
wake_up(&vif->wq);
wake_up(&queue->wq);
}
static void xenvif_rx_action(struct xenvif *vif)
static void xenvif_rx_action(struct xenvif_queue *queue)
{
s8 status;
u16 flags;
......@@ -565,13 +567,13 @@ static void xenvif_rx_action(struct xenvif *vif)
bool need_to_notify = false;
struct netrx_pending_operations npo = {
.copy = vif->grant_copy_op,
.meta = vif->meta,
.copy = queue->grant_copy_op,
.meta = queue->meta,
};
skb_queue_head_init(&rxq);
while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) {
RING_IDX max_slots_needed;
RING_IDX old_req_cons;
RING_IDX ring_slots_used;
......@@ -614,42 +616,42 @@ static void xenvif_rx_action(struct xenvif *vif)
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);
if (!xenvif_rx_ring_slots_available(queue, max_slots_needed)) {
skb_queue_head(&queue->rx_queue, skb);
need_to_notify = true;
vif->rx_last_skb_slots = max_slots_needed;
queue->rx_last_skb_slots = max_slots_needed;
break;
} else
vif->rx_last_skb_slots = 0;
queue->rx_last_skb_slots = 0;
old_req_cons = vif->rx.req_cons;
XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo);
ring_slots_used = vif->rx.req_cons - old_req_cons;
old_req_cons = queue->rx.req_cons;
XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue);
ring_slots_used = queue->rx.req_cons - old_req_cons;
BUG_ON(ring_slots_used > max_slots_needed);
__skb_queue_tail(&rxq, skb);
}
BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
BUG_ON(npo.meta_prod > ARRAY_SIZE(queue->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);
gnttab_batch_copy(queue->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++);
if ((1 << queue->meta[npo.meta_cons].gso_type) &
queue->vif->gso_prefix_mask) {
resp = RING_GET_RESPONSE(&queue->rx,
queue->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->offset = queue->meta[npo.meta_cons].gso_size;
resp->id = queue->meta[npo.meta_cons].id;
resp->status = XENVIF_RX_CB(skb)->meta_slots_used;
npo.meta_cons++;
......@@ -657,10 +659,10 @@ static void xenvif_rx_action(struct xenvif *vif)
}
vif->dev->stats.tx_bytes += skb->len;
vif->dev->stats.tx_packets++;
queue->stats.tx_bytes += skb->len;
queue->stats.tx_packets++;
status = xenvif_check_gop(vif,
status = xenvif_check_gop(queue->vif,
XENVIF_RX_CB(skb)->meta_slots_used,
&npo);
......@@ -676,22 +678,22 @@ static void xenvif_rx_action(struct xenvif *vif)
flags |= XEN_NETRXF_data_validated;
offset = 0;
resp = make_rx_response(vif, vif->meta[npo.meta_cons].id,
resp = make_rx_response(queue, queue->meta[npo.meta_cons].id,
status, offset,
vif->meta[npo.meta_cons].size,
queue->meta[npo.meta_cons].size,
flags);
if ((1 << vif->meta[npo.meta_cons].gso_type) &
vif->gso_mask) {
if ((1 << queue->meta[npo.meta_cons].gso_type) &
queue->vif->gso_mask) {
struct xen_netif_extra_info *gso =
(struct xen_netif_extra_info *)
RING_GET_RESPONSE(&vif->rx,
vif->rx.rsp_prod_pvt++);
RING_GET_RESPONSE(&queue->rx,
queue->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.type = queue->meta[npo.meta_cons].gso_type;
gso->u.gso.size = queue->meta[npo.meta_cons].gso_size;
gso->u.gso.pad = 0;
gso->u.gso.features = 0;
......@@ -699,11 +701,11 @@ static void xenvif_rx_action(struct xenvif *vif)
gso->flags = 0;
}
xenvif_add_frag_responses(vif, status,
vif->meta + npo.meta_cons + 1,
xenvif_add_frag_responses(queue, status,
queue->meta + npo.meta_cons + 1,
XENVIF_RX_CB(skb)->meta_slots_used);
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->rx, ret);
need_to_notify |= !!ret;
......@@ -713,20 +715,20 @@ static void xenvif_rx_action(struct xenvif *vif)
done:
if (need_to_notify)
notify_remote_via_irq(vif->rx_irq);
notify_remote_via_irq(queue->rx_irq);
}
void xenvif_napi_schedule_or_enable_events(struct xenvif *vif)
void xenvif_napi_schedule_or_enable_events(struct xenvif_queue *queue)
{
int more_to_do;
RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
RING_FINAL_CHECK_FOR_REQUESTS(&queue->tx, more_to_do);
if (more_to_do)
napi_schedule(&vif->napi);
napi_schedule(&queue->napi);
}
static void tx_add_credit(struct xenvif *vif)
static void tx_add_credit(struct xenvif_queue *queue)
{
unsigned long max_burst, max_credit;
......@@ -734,55 +736,57 @@ static void tx_add_credit(struct xenvif *vif)
* 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 = RING_GET_REQUEST(&queue->tx, queue->tx.req_cons)->size;
max_burst = min(max_burst, 131072UL);
max_burst = max(max_burst, vif->credit_bytes);
max_burst = max(max_burst, queue->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 = queue->remaining_credit + queue->credit_bytes;
if (max_credit < queue->remaining_credit)
max_credit = ULONG_MAX; /* wrapped: clamp to ULONG_MAX */
vif->remaining_credit = min(max_credit, max_burst);
queue->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_napi_schedule_or_enable_events(vif);
struct xenvif_queue *queue = (struct xenvif_queue *)data;
tx_add_credit(queue);
xenvif_napi_schedule_or_enable_events(queue);
}
static void xenvif_tx_err(struct xenvif *vif,
static void xenvif_tx_err(struct xenvif_queue *queue,
struct xen_netif_tx_request *txp, RING_IDX end)
{
RING_IDX cons = vif->tx.req_cons;
RING_IDX cons = queue->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);
spin_lock_irqsave(&queue->response_lock, flags);
make_tx_response(queue, txp, XEN_NETIF_RSP_ERROR);
spin_unlock_irqrestore(&queue->response_lock, flags);
if (cons == end)
break;
txp = RING_GET_REQUEST(&vif->tx, cons++);
txp = RING_GET_REQUEST(&queue->tx, cons++);
} while (1);
vif->tx.req_cons = cons;
queue->tx.req_cons = cons;
}
static void xenvif_fatal_tx_err(struct xenvif *vif)
{
netdev_err(vif->dev, "fatal error; disabling device\n");
vif->disabled = true;
xenvif_kick_thread(vif);
/* Disable the vif from queue 0's kthread */
if (vif->queues)
xenvif_kick_thread(&vif->queues[0]);
}
static int xenvif_count_requests(struct xenvif *vif,
static int xenvif_count_requests(struct xenvif_queue *queue,
struct xen_netif_tx_request *first,
struct xen_netif_tx_request *txp,
int work_to_do)
{
RING_IDX cons = vif->tx.req_cons;
RING_IDX cons = queue->tx.req_cons;
int slots = 0;
int drop_err = 0;
int more_data;
......@@ -794,10 +798,10 @@ static int xenvif_count_requests(struct xenvif *vif,
struct xen_netif_tx_request dropped_tx = { 0 };
if (slots >= work_to_do) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Asked for %d slots but exceeds this limit\n",
work_to_do);
xenvif_fatal_tx_err(vif);
xenvif_fatal_tx_err(queue->vif);
return -ENODATA;
}
......@@ -805,10 +809,10 @@ static int xenvif_count_requests(struct xenvif *vif,
* considered malicious.
*/
if (unlikely(slots >= fatal_skb_slots)) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Malicious frontend using %d slots, threshold %u\n",
slots, fatal_skb_slots);
xenvif_fatal_tx_err(vif);
xenvif_fatal_tx_err(queue->vif);
return -E2BIG;
}
......@@ -821,7 +825,7 @@ static int xenvif_count_requests(struct xenvif *vif,
*/
if (!drop_err && slots >= XEN_NETBK_LEGACY_SLOTS_MAX) {
if (net_ratelimit())
netdev_dbg(vif->dev,
netdev_dbg(queue->vif->dev,
"Too many slots (%d) exceeding limit (%d), dropping packet\n",
slots, XEN_NETBK_LEGACY_SLOTS_MAX);
drop_err = -E2BIG;
......@@ -830,7 +834,7 @@ static int xenvif_count_requests(struct xenvif *vif,
if (drop_err)
txp = &dropped_tx;
memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + slots),
memcpy(txp, RING_GET_REQUEST(&queue->tx, cons + slots),
sizeof(*txp));
/* If the guest submitted a frame >= 64 KiB then
......@@ -844,7 +848,7 @@ static int xenvif_count_requests(struct xenvif *vif,
*/
if (!drop_err && txp->size > first->size) {
if (net_ratelimit())
netdev_dbg(vif->dev,
netdev_dbg(queue->vif->dev,
"Invalid tx request, slot size %u > remaining size %u\n",
txp->size, first->size);
drop_err = -EIO;
......@@ -854,9 +858,9 @@ static int xenvif_count_requests(struct xenvif *vif,
slots++;
if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
netdev_err(vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n",
netdev_err(queue->vif->dev, "Cross page boundary, txp->offset: %x, size: %u\n",
txp->offset, txp->size);
xenvif_fatal_tx_err(vif);
xenvif_fatal_tx_err(queue->vif);
return -EINVAL;
}
......@@ -868,7 +872,7 @@ static int xenvif_count_requests(struct xenvif *vif,
} while (more_data);
if (drop_err) {
xenvif_tx_err(vif, first, cons + slots);
xenvif_tx_err(queue, first, cons + slots);
return drop_err;
}
......@@ -882,17 +886,17 @@ struct xenvif_tx_cb {
#define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb)
static inline void xenvif_tx_create_map_op(struct xenvif *vif,
static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue,
u16 pending_idx,
struct xen_netif_tx_request *txp,
struct gnttab_map_grant_ref *mop)
{
vif->pages_to_map[mop-vif->tx_map_ops] = vif->mmap_pages[pending_idx];
gnttab_set_map_op(mop, idx_to_kaddr(vif, pending_idx),
queue->pages_to_map[mop-queue->tx_map_ops] = queue->mmap_pages[pending_idx];
gnttab_set_map_op(mop, idx_to_kaddr(queue, pending_idx),
GNTMAP_host_map | GNTMAP_readonly,
txp->gref, vif->domid);
txp->gref, queue->vif->domid);
memcpy(&vif->pending_tx_info[pending_idx].req, txp,
memcpy(&queue->pending_tx_info[pending_idx].req, txp,
sizeof(*txp));
}
......@@ -913,7 +917,7 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size)
return skb;
}
static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue,
struct sk_buff *skb,
struct xen_netif_tx_request *txp,
struct gnttab_map_grant_ref *gop)
......@@ -940,9 +944,9 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
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_map_op(vif, pending_idx, txp, gop);
index = pending_index(queue->pending_cons++);
pending_idx = queue->pending_ring[index];
xenvif_tx_create_map_op(queue, pending_idx, txp, gop);
frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx);
}
......@@ -950,7 +954,7 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
struct sk_buff *nskb = xenvif_alloc_skb(0);
if (unlikely(nskb == NULL)) {
if (net_ratelimit())
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Can't allocate the frag_list skb.\n");
return NULL;
}
......@@ -960,9 +964,9 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
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_map_op(vif, pending_idx, txp, gop);
index = pending_index(queue->pending_cons++);
pending_idx = queue->pending_ring[index];
xenvif_tx_create_map_op(queue, pending_idx, txp, gop);
frag_set_pending_idx(&frags[shinfo->nr_frags],
pending_idx);
}
......@@ -973,34 +977,34 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif *vif,
return gop;
}
static inline void xenvif_grant_handle_set(struct xenvif *vif,
static inline void xenvif_grant_handle_set(struct xenvif_queue *queue,
u16 pending_idx,
grant_handle_t handle)
{
if (unlikely(vif->grant_tx_handle[pending_idx] !=
if (unlikely(queue->grant_tx_handle[pending_idx] !=
NETBACK_INVALID_HANDLE)) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Trying to overwrite active handle! pending_idx: %x\n",
pending_idx);
BUG();
}
vif->grant_tx_handle[pending_idx] = handle;
queue->grant_tx_handle[pending_idx] = handle;
}
static inline void xenvif_grant_handle_reset(struct xenvif *vif,
static inline void xenvif_grant_handle_reset(struct xenvif_queue *queue,
u16 pending_idx)
{
if (unlikely(vif->grant_tx_handle[pending_idx] ==
if (unlikely(queue->grant_tx_handle[pending_idx] ==
NETBACK_INVALID_HANDLE)) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Trying to unmap invalid handle! pending_idx: %x\n",
pending_idx);
BUG();
}
vif->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE;
queue->grant_tx_handle[pending_idx] = NETBACK_INVALID_HANDLE;
}
static int xenvif_tx_check_gop(struct xenvif *vif,
static int xenvif_tx_check_gop(struct xenvif_queue *queue,
struct sk_buff *skb,
struct gnttab_map_grant_ref **gopp_map,
struct gnttab_copy **gopp_copy)
......@@ -1017,12 +1021,12 @@ static int xenvif_tx_check_gop(struct xenvif *vif,
(*gopp_copy)++;
if (unlikely(err)) {
if (net_ratelimit())
netdev_dbg(vif->dev,
netdev_dbg(queue->vif->dev,
"Grant copy of header failed! status: %d pending_idx: %u ref: %u\n",
(*gopp_copy)->status,
pending_idx,
(*gopp_copy)->source.u.ref);
xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR);
}
check_frags:
......@@ -1035,24 +1039,24 @@ static int xenvif_tx_check_gop(struct xenvif *vif,
newerr = gop_map->status;
if (likely(!newerr)) {
xenvif_grant_handle_set(vif,
xenvif_grant_handle_set(queue,
pending_idx,
gop_map->handle);
/* Had a previous error? Invalidate this fragment. */
if (unlikely(err))
xenvif_idx_unmap(vif, pending_idx);
xenvif_idx_unmap(queue, pending_idx);
continue;
}
/* Error on this fragment: respond to client with an error. */
if (net_ratelimit())
netdev_dbg(vif->dev,
netdev_dbg(queue->vif->dev,
"Grant map of %d. frag failed! status: %d pending_idx: %u ref: %u\n",
i,
gop_map->status,
pending_idx,
gop_map->ref);
xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_ERROR);
xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_ERROR);
/* Not the first error? Preceding frags already invalidated. */
if (err)
......@@ -1060,7 +1064,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif,
/* First error: invalidate preceding fragments. */
for (j = 0; j < i; j++) {
pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
xenvif_idx_unmap(vif, pending_idx);
xenvif_idx_unmap(queue, pending_idx);
}
/* Remember the error: invalidate all subsequent fragments. */
......@@ -1084,7 +1088,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif,
shinfo = skb_shinfo(first_skb);
for (j = 0; j < shinfo->nr_frags; j++) {
pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
xenvif_idx_unmap(vif, pending_idx);
xenvif_idx_unmap(queue, pending_idx);
}
}
......@@ -1092,7 +1096,7 @@ static int xenvif_tx_check_gop(struct xenvif *vif,
return err;
}
static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
static void xenvif_fill_frags(struct xenvif_queue *queue, struct sk_buff *skb)
{
struct skb_shared_info *shinfo = skb_shinfo(skb);
int nr_frags = shinfo->nr_frags;
......@@ -1110,23 +1114,23 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
/* If this is not the first frag, chain it to the previous*/
if (prev_pending_idx == INVALID_PENDING_IDX)
skb_shinfo(skb)->destructor_arg =
&callback_param(vif, pending_idx);
&callback_param(queue, pending_idx);
else
callback_param(vif, prev_pending_idx).ctx =
&callback_param(vif, pending_idx);
callback_param(queue, prev_pending_idx).ctx =
&callback_param(queue, pending_idx);
callback_param(vif, pending_idx).ctx = NULL;
callback_param(queue, pending_idx).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));
txp = &queue->pending_tx_info[pending_idx].req;
page = virt_to_page(idx_to_kaddr(queue, 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]);
get_page(queue->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
......@@ -1136,33 +1140,33 @@ static void xenvif_fill_frags(struct xenvif *vif, struct sk_buff *skb)
skb->pfmemalloc = false;
}
static int xenvif_get_extras(struct xenvif *vif,
static int xenvif_get_extras(struct xenvif_queue *queue,
struct xen_netif_extra_info *extras,
int work_to_do)
{
struct xen_netif_extra_info extra;
RING_IDX cons = vif->tx.req_cons;
RING_IDX cons = queue->tx.req_cons;
do {
if (unlikely(work_to_do-- <= 0)) {
netdev_err(vif->dev, "Missing extra info\n");
xenvif_fatal_tx_err(vif);
netdev_err(queue->vif->dev, "Missing extra info\n");
xenvif_fatal_tx_err(queue->vif);
return -EBADR;
}
memcpy(&extra, RING_GET_REQUEST(&vif->tx, cons),
memcpy(&extra, RING_GET_REQUEST(&queue->tx, cons),
sizeof(extra));
if (unlikely(!extra.type ||
extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) {
vif->tx.req_cons = ++cons;
netdev_err(vif->dev,
queue->tx.req_cons = ++cons;
netdev_err(queue->vif->dev,
"Invalid extra type: %d\n", extra.type);
xenvif_fatal_tx_err(vif);
xenvif_fatal_tx_err(queue->vif);
return -EINVAL;
}
memcpy(&extras[extra.type - 1], &extra, sizeof(extra));
vif->tx.req_cons = ++cons;
queue->tx.req_cons = ++cons;
} while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE);
return work_to_do;
......@@ -1197,7 +1201,7 @@ static int xenvif_set_skb_gso(struct xenvif *vif,
return 0;
}
static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
static int checksum_setup(struct xenvif_queue *queue, struct sk_buff *skb)
{
bool recalculate_partial_csum = false;
......@@ -1207,7 +1211,7 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
* recalculate the partial checksum.
*/
if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) {
vif->rx_gso_checksum_fixup++;
queue->stats.rx_gso_checksum_fixup++;
skb->ip_summed = CHECKSUM_PARTIAL;
recalculate_partial_csum = true;
}
......@@ -1219,31 +1223,31 @@ static int checksum_setup(struct xenvif *vif, struct sk_buff *skb)
return skb_checksum_setup(skb, recalculate_partial_csum);
}
static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
static bool tx_credit_exceeded(struct xenvif_queue *queue, unsigned size)
{
u64 now = get_jiffies_64();
u64 next_credit = vif->credit_window_start +
msecs_to_jiffies(vif->credit_usec / 1000);
u64 next_credit = queue->credit_window_start +
msecs_to_jiffies(queue->credit_usec / 1000);
/* Timer could already be pending in rare cases. */
if (timer_pending(&vif->credit_timeout))
if (timer_pending(&queue->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);
queue->credit_window_start = now;
tx_add_credit(queue);
}
/* 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 =
if (size > queue->remaining_credit) {
queue->credit_timeout.data =
(unsigned long)queue;
queue->credit_timeout.function =
tx_credit_callback;
mod_timer(&vif->credit_timeout,
mod_timer(&queue->credit_timeout,
next_credit);
vif->credit_window_start = next_credit;
queue->credit_window_start = next_credit;
return true;
}
......@@ -1251,16 +1255,16 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size)
return false;
}
static void xenvif_tx_build_gops(struct xenvif *vif,
static void xenvif_tx_build_gops(struct xenvif_queue *queue,
int budget,
unsigned *copy_ops,
unsigned *map_ops)
{
struct gnttab_map_grant_ref *gop = vif->tx_map_ops, *request_gop;
struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop;
struct sk_buff *skb;
int ret;
while (skb_queue_len(&vif->tx_queue) < budget) {
while (skb_queue_len(&queue->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];
......@@ -1270,69 +1274,69 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
unsigned int data_len;
pending_ring_idx_t index;
if (vif->tx.sring->req_prod - vif->tx.req_cons >
if (queue->tx.sring->req_prod - queue->tx.req_cons >
XEN_NETIF_TX_RING_SIZE) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Impossible number of requests. "
"req_prod %d, req_cons %d, size %ld\n",
vif->tx.sring->req_prod, vif->tx.req_cons,
queue->tx.sring->req_prod, queue->tx.req_cons,
XEN_NETIF_TX_RING_SIZE);
xenvif_fatal_tx_err(vif);
xenvif_fatal_tx_err(queue->vif);
break;
}
work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&queue->tx);
if (!work_to_do)
break;
idx = vif->tx.req_cons;
idx = queue->tx.req_cons;
rmb(); /* Ensure that we see the request before we copy it. */
memcpy(&txreq, RING_GET_REQUEST(&vif->tx, idx), sizeof(txreq));
memcpy(&txreq, RING_GET_REQUEST(&queue->tx, idx), sizeof(txreq));
/* Credit-based scheduling. */
if (txreq.size > vif->remaining_credit &&
tx_credit_exceeded(vif, txreq.size))
if (txreq.size > queue->remaining_credit &&
tx_credit_exceeded(queue, txreq.size))
break;
vif->remaining_credit -= txreq.size;
queue->remaining_credit -= txreq.size;
work_to_do--;
vif->tx.req_cons = ++idx;
queue->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 = xenvif_get_extras(queue, extras,
work_to_do);
idx = vif->tx.req_cons;
idx = queue->tx.req_cons;
if (unlikely(work_to_do < 0))
break;
}
ret = xenvif_count_requests(vif, &txreq, txfrags, work_to_do);
ret = xenvif_count_requests(queue, &txreq, txfrags, work_to_do);
if (unlikely(ret < 0))
break;
idx += ret;
if (unlikely(txreq.size < ETH_HLEN)) {
netdev_dbg(vif->dev,
netdev_dbg(queue->vif->dev,
"Bad packet size: %d\n", txreq.size);
xenvif_tx_err(vif, &txreq, idx);
xenvif_tx_err(queue, &txreq, idx);
break;
}
/* No crossing a page as the payload mustn't fragment. */
if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"txreq.offset: %x, size: %u, end: %lu\n",
txreq.offset, txreq.size,
(txreq.offset&~PAGE_MASK) + txreq.size);
xenvif_fatal_tx_err(vif);
xenvif_fatal_tx_err(queue->vif);
break;
}
index = pending_index(vif->pending_cons);
pending_idx = vif->pending_ring[index];
index = pending_index(queue->pending_cons);
pending_idx = queue->pending_ring[index];
data_len = (txreq.size > PKT_PROT_LEN &&
ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
......@@ -1340,9 +1344,9 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
skb = xenvif_alloc_skb(data_len);
if (unlikely(skb == NULL)) {
netdev_dbg(vif->dev,
netdev_dbg(queue->vif->dev,
"Can't allocate a skb in start_xmit.\n");
xenvif_tx_err(vif, &txreq, idx);
xenvif_tx_err(queue, &txreq, idx);
break;
}
......@@ -1350,7 +1354,7 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
struct xen_netif_extra_info *gso;
gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
if (xenvif_set_skb_gso(vif, skb, gso)) {
if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
/* Failure in xenvif_set_skb_gso is fatal. */
kfree_skb(skb);
break;
......@@ -1360,18 +1364,18 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
XENVIF_TX_CB(skb)->pending_idx = pending_idx;
__skb_put(skb, data_len);
vif->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref;
vif->tx_copy_ops[*copy_ops].source.domid = vif->domid;
vif->tx_copy_ops[*copy_ops].source.offset = txreq.offset;
queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref;
queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid;
queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset;
vif->tx_copy_ops[*copy_ops].dest.u.gmfn =
queue->tx_copy_ops[*copy_ops].dest.u.gmfn =
virt_to_mfn(skb->data);
vif->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF;
vif->tx_copy_ops[*copy_ops].dest.offset =
queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF;
queue->tx_copy_ops[*copy_ops].dest.offset =
offset_in_page(skb->data);
vif->tx_copy_ops[*copy_ops].len = data_len;
vif->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref;
queue->tx_copy_ops[*copy_ops].len = data_len;
queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref;
(*copy_ops)++;
......@@ -1380,42 +1384,42 @@ static void xenvif_tx_build_gops(struct xenvif *vif,
skb_shinfo(skb)->nr_frags++;
frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
pending_idx);
xenvif_tx_create_map_op(vif, pending_idx, &txreq, gop);
xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop);
gop++;
} else {
frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
INVALID_PENDING_IDX);
memcpy(&vif->pending_tx_info[pending_idx].req, &txreq,
memcpy(&queue->pending_tx_info[pending_idx].req, &txreq,
sizeof(txreq));
}
vif->pending_cons++;
queue->pending_cons++;
request_gop = xenvif_get_requests(vif, skb, txfrags, gop);
request_gop = xenvif_get_requests(queue, skb, txfrags, gop);
if (request_gop == NULL) {
kfree_skb(skb);
xenvif_tx_err(vif, &txreq, idx);
xenvif_tx_err(queue, &txreq, idx);
break;
}
gop = request_gop;
__skb_queue_tail(&vif->tx_queue, skb);
__skb_queue_tail(&queue->tx_queue, skb);
vif->tx.req_cons = idx;
queue->tx.req_cons = idx;
if (((gop-vif->tx_map_ops) >= ARRAY_SIZE(vif->tx_map_ops)) ||
(*copy_ops >= ARRAY_SIZE(vif->tx_copy_ops)))
if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) ||
(*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops)))
break;
}
(*map_ops) = gop - vif->tx_map_ops;
(*map_ops) = gop - queue->tx_map_ops;
return;
}
/* Consolidate skb with a frag_list into a brand new one with local pages on
* frags. Returns 0 or -ENOMEM if can't allocate new pages.
*/
static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *skb)
{
unsigned int offset = skb_headlen(skb);
skb_frag_t frags[MAX_SKB_FRAGS];
......@@ -1423,10 +1427,10 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
struct ubuf_info *uarg;
struct sk_buff *nskb = skb_shinfo(skb)->frag_list;
vif->tx_zerocopy_sent += 2;
vif->tx_frag_overflow++;
queue->stats.tx_zerocopy_sent += 2;
queue->stats.tx_frag_overflow++;
xenvif_fill_frags(vif, nskb);
xenvif_fill_frags(queue, nskb);
/* Subtract frags size, we will correct it later */
skb->truesize -= skb->data_len;
skb->len += nskb->len;
......@@ -1478,37 +1482,37 @@ static int xenvif_handle_frag_list(struct xenvif *vif, struct sk_buff *skb)
return 0;
}
static int xenvif_tx_submit(struct xenvif *vif)
static int xenvif_tx_submit(struct xenvif_queue *queue)
{
struct gnttab_map_grant_ref *gop_map = vif->tx_map_ops;
struct gnttab_copy *gop_copy = vif->tx_copy_ops;
struct gnttab_map_grant_ref *gop_map = queue->tx_map_ops;
struct gnttab_copy *gop_copy = queue->tx_copy_ops;
struct sk_buff *skb;
int work_done = 0;
while ((skb = __skb_dequeue(&vif->tx_queue)) != NULL) {
while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) {
struct xen_netif_tx_request *txp;
u16 pending_idx;
unsigned data_len;
pending_idx = XENVIF_TX_CB(skb)->pending_idx;
txp = &vif->pending_tx_info[pending_idx].req;
txp = &queue->pending_tx_info[pending_idx].req;
/* Check the remap error code. */
if (unlikely(xenvif_tx_check_gop(vif, skb, &gop_map, &gop_copy))) {
if (unlikely(xenvif_tx_check_gop(queue, skb, &gop_map, &gop_copy))) {
skb_shinfo(skb)->nr_frags = 0;
kfree_skb(skb);
continue;
}
data_len = skb->len;
callback_param(vif, pending_idx).ctx = NULL;
callback_param(queue, pending_idx).ctx = NULL;
if (data_len < txp->size) {
/* Append the packet payload as a fragment. */
txp->offset += data_len;
txp->size -= data_len;
} else {
/* Schedule a response immediately. */
xenvif_idx_release(vif, pending_idx,
xenvif_idx_release(queue, pending_idx,
XEN_NETIF_RSP_OKAY);
}
......@@ -1517,12 +1521,12 @@ static int xenvif_tx_submit(struct xenvif *vif)
else if (txp->flags & XEN_NETTXF_data_validated)
skb->ip_summed = CHECKSUM_UNNECESSARY;
xenvif_fill_frags(vif, skb);
xenvif_fill_frags(queue, skb);
if (unlikely(skb_has_frag_list(skb))) {
if (xenvif_handle_frag_list(vif, skb)) {
if (xenvif_handle_frag_list(queue, skb)) {
if (net_ratelimit())
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Not enough memory to consolidate frag_list!\n");
skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
kfree_skb(skb);
......@@ -1535,12 +1539,12 @@ static int xenvif_tx_submit(struct xenvif *vif)
__pskb_pull_tail(skb, target - skb_headlen(skb));
}
skb->dev = vif->dev;
skb->dev = queue->vif->dev;
skb->protocol = eth_type_trans(skb, skb->dev);
skb_reset_network_header(skb);
if (checksum_setup(vif, skb)) {
netdev_dbg(vif->dev,
if (checksum_setup(queue, skb)) {
netdev_dbg(queue->vif->dev,
"Can't setup checksum in net_tx_action\n");
/* We have to set this flag to trigger the callback */
if (skb_shinfo(skb)->destructor_arg)
......@@ -1565,8 +1569,8 @@ static int xenvif_tx_submit(struct xenvif *vif)
DIV_ROUND_UP(skb->len - hdrlen, mss);
}
vif->dev->stats.rx_bytes += skb->len;
vif->dev->stats.rx_packets++;
queue->stats.rx_bytes += skb->len;
queue->stats.rx_packets++;
work_done++;
......@@ -1577,7 +1581,7 @@ static int xenvif_tx_submit(struct xenvif *vif)
*/
if (skb_shinfo(skb)->destructor_arg) {
skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
vif->tx_zerocopy_sent++;
queue->stats.tx_zerocopy_sent++;
}
netif_receive_skb(skb);
......@@ -1590,47 +1594,47 @@ void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success)
{
unsigned long flags;
pending_ring_idx_t index;
struct xenvif *vif = ubuf_to_vif(ubuf);
struct xenvif_queue *queue = ubuf_to_queue(ubuf);
/* This is the only place where we grab this lock, to protect callbacks
* from each other.
*/
spin_lock_irqsave(&vif->callback_lock, flags);
spin_lock_irqsave(&queue->callback_lock, flags);
do {
u16 pending_idx = ubuf->desc;
ubuf = (struct ubuf_info *) ubuf->ctx;
BUG_ON(vif->dealloc_prod - vif->dealloc_cons >=
BUG_ON(queue->dealloc_prod - queue->dealloc_cons >=
MAX_PENDING_REQS);
index = pending_index(vif->dealloc_prod);
vif->dealloc_ring[index] = pending_idx;
index = pending_index(queue->dealloc_prod);
queue->dealloc_ring[index] = pending_idx;
/* Sync with xenvif_tx_dealloc_action:
* insert idx then incr producer.
*/
smp_wmb();
vif->dealloc_prod++;
queue->dealloc_prod++;
} while (ubuf);
wake_up(&vif->dealloc_wq);
spin_unlock_irqrestore(&vif->callback_lock, flags);
wake_up(&queue->dealloc_wq);
spin_unlock_irqrestore(&queue->callback_lock, flags);
if (likely(zerocopy_success))
vif->tx_zerocopy_success++;
queue->stats.tx_zerocopy_success++;
else
vif->tx_zerocopy_fail++;
queue->stats.tx_zerocopy_fail++;
}
static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue)
{
struct gnttab_unmap_grant_ref *gop;
pending_ring_idx_t dc, dp;
u16 pending_idx, pending_idx_release[MAX_PENDING_REQS];
unsigned int i = 0;
dc = vif->dealloc_cons;
gop = vif->tx_unmap_ops;
dc = queue->dealloc_cons;
gop = queue->tx_unmap_ops;
/* Free up any grants we have finished using */
do {
dp = vif->dealloc_prod;
dp = queue->dealloc_prod;
/* Ensure we see all indices enqueued by all
* xenvif_zerocopy_callback().
......@@ -1638,38 +1642,38 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
smp_rmb();
while (dc != dp) {
BUG_ON(gop - vif->tx_unmap_ops > MAX_PENDING_REQS);
BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
pending_idx =
vif->dealloc_ring[pending_index(dc++)];
queue->dealloc_ring[pending_index(dc++)];
pending_idx_release[gop-vif->tx_unmap_ops] =
pending_idx_release[gop-queue->tx_unmap_ops] =
pending_idx;
vif->pages_to_unmap[gop-vif->tx_unmap_ops] =
vif->mmap_pages[pending_idx];
queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
queue->mmap_pages[pending_idx];
gnttab_set_unmap_op(gop,
idx_to_kaddr(vif, pending_idx),
idx_to_kaddr(queue, pending_idx),
GNTMAP_host_map,
vif->grant_tx_handle[pending_idx]);
xenvif_grant_handle_reset(vif, pending_idx);
queue->grant_tx_handle[pending_idx]);
xenvif_grant_handle_reset(queue, pending_idx);
++gop;
}
} while (dp != vif->dealloc_prod);
} while (dp != queue->dealloc_prod);
vif->dealloc_cons = dc;
queue->dealloc_cons = dc;
if (gop - vif->tx_unmap_ops > 0) {
if (gop - queue->tx_unmap_ops > 0) {
int ret;
ret = gnttab_unmap_refs(vif->tx_unmap_ops,
ret = gnttab_unmap_refs(queue->tx_unmap_ops,
NULL,
vif->pages_to_unmap,
gop - vif->tx_unmap_ops);
queue->pages_to_unmap,
gop - queue->tx_unmap_ops);
if (ret) {
netdev_err(vif->dev, "Unmap fail: nr_ops %tx ret %d\n",
gop - vif->tx_unmap_ops, ret);
for (i = 0; i < gop - vif->tx_unmap_ops; ++i) {
netdev_err(queue->vif->dev, "Unmap fail: nr_ops %tx ret %d\n",
gop - queue->tx_unmap_ops, ret);
for (i = 0; i < gop - queue->tx_unmap_ops; ++i) {
if (gop[i].status != GNTST_okay)
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
" host_addr: %llx handle: %x status: %d\n",
gop[i].host_addr,
gop[i].handle,
......@@ -1679,91 +1683,91 @@ static inline void xenvif_tx_dealloc_action(struct xenvif *vif)
}
}
for (i = 0; i < gop - vif->tx_unmap_ops; ++i)
xenvif_idx_release(vif, pending_idx_release[i],
for (i = 0; i < gop - queue->tx_unmap_ops; ++i)
xenvif_idx_release(queue, pending_idx_release[i],
XEN_NETIF_RSP_OKAY);
}
/* Called after netfront has transmitted */
int xenvif_tx_action(struct xenvif *vif, int budget)
int xenvif_tx_action(struct xenvif_queue *queue, int budget)
{
unsigned nr_mops, nr_cops = 0;
int work_done, ret;
if (unlikely(!tx_work_todo(vif)))
if (unlikely(!tx_work_todo(queue)))
return 0;
xenvif_tx_build_gops(vif, budget, &nr_cops, &nr_mops);
xenvif_tx_build_gops(queue, budget, &nr_cops, &nr_mops);
if (nr_cops == 0)
return 0;
gnttab_batch_copy(vif->tx_copy_ops, nr_cops);
gnttab_batch_copy(queue->tx_copy_ops, nr_cops);
if (nr_mops != 0) {
ret = gnttab_map_refs(vif->tx_map_ops,
ret = gnttab_map_refs(queue->tx_map_ops,
NULL,
vif->pages_to_map,
queue->pages_to_map,
nr_mops);
BUG_ON(ret);
}
work_done = xenvif_tx_submit(vif);
work_done = xenvif_tx_submit(queue);
return work_done;
}
static void xenvif_idx_release(struct xenvif *vif, u16 pending_idx,
static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
u8 status)
{
struct pending_tx_info *pending_tx_info;
pending_ring_idx_t index;
unsigned long flags;
pending_tx_info = &vif->pending_tx_info[pending_idx];
spin_lock_irqsave(&vif->response_lock, flags);
make_tx_response(vif, &pending_tx_info->req, status);
index = pending_index(vif->pending_prod);
vif->pending_ring[index] = pending_idx;
pending_tx_info = &queue->pending_tx_info[pending_idx];
spin_lock_irqsave(&queue->response_lock, flags);
make_tx_response(queue, &pending_tx_info->req, status);
index = pending_index(queue->pending_prod);
queue->pending_ring[index] = pending_idx;
/* TX shouldn't use the index before we give it back here */
mb();
vif->pending_prod++;
spin_unlock_irqrestore(&vif->response_lock, flags);
queue->pending_prod++;
spin_unlock_irqrestore(&queue->response_lock, flags);
}
static void make_tx_response(struct xenvif *vif,
static void make_tx_response(struct xenvif_queue *queue,
struct xen_netif_tx_request *txp,
s8 st)
{
RING_IDX i = vif->tx.rsp_prod_pvt;
RING_IDX i = queue->tx.rsp_prod_pvt;
struct xen_netif_tx_response *resp;
int notify;
resp = RING_GET_RESPONSE(&vif->tx, i);
resp = RING_GET_RESPONSE(&queue->tx, i);
resp->id = txp->id;
resp->status = st;
if (txp->flags & XEN_NETTXF_extra_info)
RING_GET_RESPONSE(&vif->tx, ++i)->status = XEN_NETIF_RSP_NULL;
RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
vif->tx.rsp_prod_pvt = ++i;
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->tx, notify);
queue->tx.rsp_prod_pvt = ++i;
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&queue->tx, notify);
if (notify)
notify_remote_via_irq(vif->tx_irq);
notify_remote_via_irq(queue->tx_irq);
}
static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue,
u16 id,
s8 st,
u16 offset,
u16 size,
u16 flags)
{
RING_IDX i = vif->rx.rsp_prod_pvt;
RING_IDX i = queue->rx.rsp_prod_pvt;
struct xen_netif_rx_response *resp;
resp = RING_GET_RESPONSE(&vif->rx, i);
resp = RING_GET_RESPONSE(&queue->rx, i);
resp->offset = offset;
resp->flags = flags;
resp->id = id;
......@@ -1771,26 +1775,26 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
if (st < 0)
resp->status = (s16)st;
vif->rx.rsp_prod_pvt = ++i;
queue->rx.rsp_prod_pvt = ++i;
return resp;
}
void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx)
void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx)
{
int ret;
struct gnttab_unmap_grant_ref tx_unmap_op;
gnttab_set_unmap_op(&tx_unmap_op,
idx_to_kaddr(vif, pending_idx),
idx_to_kaddr(queue, pending_idx),
GNTMAP_host_map,
vif->grant_tx_handle[pending_idx]);
xenvif_grant_handle_reset(vif, pending_idx);
queue->grant_tx_handle[pending_idx]);
xenvif_grant_handle_reset(queue, pending_idx);
ret = gnttab_unmap_refs(&tx_unmap_op, NULL,
&vif->mmap_pages[pending_idx], 1);
&queue->mmap_pages[pending_idx], 1);
if (ret) {
netdev_err(vif->dev,
netdev_err(queue->vif->dev,
"Unmap fail: ret: %d pending_idx: %d host_addr: %llx handle: %x status: %d\n",
ret,
pending_idx,
......@@ -1800,41 +1804,40 @@ void xenvif_idx_unmap(struct xenvif *vif, u16 pending_idx)
BUG();
}
xenvif_idx_release(vif, pending_idx, XEN_NETIF_RSP_OKAY);
xenvif_idx_release(queue, pending_idx, XEN_NETIF_RSP_OKAY);
}
static inline int rx_work_todo(struct xenvif *vif)
static inline int rx_work_todo(struct xenvif_queue *queue)
{
return (!skb_queue_empty(&vif->rx_queue) &&
xenvif_rx_ring_slots_available(vif, vif->rx_last_skb_slots)) ||
vif->rx_queue_purge;
return (!skb_queue_empty(&queue->rx_queue) &&
xenvif_rx_ring_slots_available(queue, queue->rx_last_skb_slots)) ||
queue->rx_queue_purge;
}
static inline int tx_work_todo(struct xenvif *vif)
static inline int tx_work_todo(struct xenvif_queue *queue)
{
if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->tx)))
if (likely(RING_HAS_UNCONSUMED_REQUESTS(&queue->tx)))
return 1;
return 0;
}
static inline bool tx_dealloc_work_todo(struct xenvif *vif)
static inline bool tx_dealloc_work_todo(struct xenvif_queue *queue)
{
return vif->dealloc_cons != vif->dealloc_prod;
return queue->dealloc_cons != queue->dealloc_prod;
}
void xenvif_unmap_frontend_rings(struct xenvif *vif)
void xenvif_unmap_frontend_rings(struct xenvif_queue *queue)
{
if (vif->tx.sring)
xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
vif->tx.sring);
if (vif->rx.sring)
xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(vif),
vif->rx.sring);
if (queue->tx.sring)
xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif),
queue->tx.sring);
if (queue->rx.sring)
xenbus_unmap_ring_vfree(xenvif_to_xenbus_device(queue->vif),
queue->rx.sring);
}
int xenvif_map_frontend_rings(struct xenvif *vif,
int xenvif_map_frontend_rings(struct xenvif_queue *queue,
grant_ref_t tx_ring_ref,
grant_ref_t rx_ring_ref)
{
......@@ -1844,85 +1847,78 @@ int xenvif_map_frontend_rings(struct xenvif *vif,
int err = -ENOMEM;
err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif),
tx_ring_ref, &addr);
if (err)
goto err;
txs = (struct xen_netif_tx_sring *)addr;
BACK_RING_INIT(&vif->tx, txs, PAGE_SIZE);
BACK_RING_INIT(&queue->tx, txs, PAGE_SIZE);
err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(vif),
err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif),
rx_ring_ref, &addr);
if (err)
goto err;
rxs = (struct xen_netif_rx_sring *)addr;
BACK_RING_INIT(&vif->rx, rxs, PAGE_SIZE);
BACK_RING_INIT(&queue->rx, rxs, PAGE_SIZE);
return 0;
err:
xenvif_unmap_frontend_rings(vif);
xenvif_unmap_frontend_rings(queue);
return err;
}
void xenvif_stop_queue(struct xenvif *vif)
{
if (!vif->can_queue)
return;
netif_stop_queue(vif->dev);
}
static void xenvif_start_queue(struct xenvif *vif)
static void xenvif_start_queue(struct xenvif_queue *queue)
{
if (xenvif_schedulable(vif))
netif_wake_queue(vif->dev);
if (xenvif_schedulable(queue->vif))
xenvif_wake_queue(queue);
}
int xenvif_kthread_guest_rx(void *data)
{
struct xenvif *vif = data;
struct xenvif_queue *queue = data;
struct sk_buff *skb;
while (!kthread_should_stop()) {
wait_event_interruptible(vif->wq,
rx_work_todo(vif) ||
vif->disabled ||
wait_event_interruptible(queue->wq,
rx_work_todo(queue) ||
queue->vif->disabled ||
kthread_should_stop());
/* This frontend is found to be rogue, disable it in
* kthread context. Currently this is only set when
* netback finds out frontend sends malformed packet,
* but we cannot disable the interface in softirq
* context so we defer it here.
* context so we defer it here, if this thread is
* associated with queue 0.
*/
if (unlikely(vif->disabled && netif_carrier_ok(vif->dev)))
xenvif_carrier_off(vif);
if (unlikely(queue->vif->disabled && netif_carrier_ok(queue->vif->dev) && queue->id == 0))
xenvif_carrier_off(queue->vif);
if (kthread_should_stop())
break;
if (vif->rx_queue_purge) {
skb_queue_purge(&vif->rx_queue);
vif->rx_queue_purge = false;
if (queue->rx_queue_purge) {
skb_queue_purge(&queue->rx_queue);
queue->rx_queue_purge = false;
}
if (!skb_queue_empty(&vif->rx_queue))
xenvif_rx_action(vif);
if (!skb_queue_empty(&queue->rx_queue))
xenvif_rx_action(queue);
if (skb_queue_empty(&vif->rx_queue) &&
netif_queue_stopped(vif->dev)) {
del_timer_sync(&vif->wake_queue);
xenvif_start_queue(vif);
if (skb_queue_empty(&queue->rx_queue) &&
xenvif_queue_stopped(queue)) {
del_timer_sync(&queue->wake_queue);
xenvif_start_queue(queue);
}
cond_resched();
}
/* Bin any remaining skbs */
while ((skb = skb_dequeue(&vif->rx_queue)) != NULL)
while ((skb = skb_dequeue(&queue->rx_queue)) != NULL)
dev_kfree_skb(skb);
return 0;
......@@ -1930,22 +1926,22 @@ int xenvif_kthread_guest_rx(void *data)
int xenvif_dealloc_kthread(void *data)
{
struct xenvif *vif = data;
struct xenvif_queue *queue = data;
while (!kthread_should_stop()) {
wait_event_interruptible(vif->dealloc_wq,
tx_dealloc_work_todo(vif) ||
wait_event_interruptible(queue->dealloc_wq,
tx_dealloc_work_todo(queue) ||
kthread_should_stop());
if (kthread_should_stop())
break;
xenvif_tx_dealloc_action(vif);
xenvif_tx_dealloc_action(queue);
cond_resched();
}
/* Unmap anything remaining*/
if (tx_dealloc_work_todo(vif))
xenvif_tx_dealloc_action(vif);
if (tx_dealloc_work_todo(queue))
xenvif_tx_dealloc_action(queue);
return 0;
}
......
......@@ -19,6 +19,8 @@
*/
#include "common.h"
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
struct backend_info {
struct xenbus_device *dev;
......@@ -34,8 +36,9 @@ struct backend_info {
u8 have_hotplug_status_watch:1;
};
static int connect_rings(struct backend_info *);
static void connect(struct backend_info *);
static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
static void connect(struct backend_info *be);
static int read_xenbus_vif_flags(struct backend_info *be);
static void backend_create_xenvif(struct backend_info *be);
static void unregister_hotplug_status_watch(struct backend_info *be);
static void set_backend_state(struct backend_info *be,
......@@ -485,10 +488,10 @@ static void connect(struct backend_info *be)
{
int err;
struct xenbus_device *dev = be->dev;
err = connect_rings(be);
if (err)
return;
unsigned long credit_bytes, credit_usec;
unsigned int queue_index;
unsigned int requested_num_queues = 1;
struct xenvif_queue *queue;
err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
if (err) {
......@@ -496,9 +499,34 @@ static void connect(struct backend_info *be)
return;
}
xen_net_read_rate(dev, &be->vif->credit_bytes,
&be->vif->credit_usec);
be->vif->remaining_credit = be->vif->credit_bytes;
xen_net_read_rate(dev, &credit_bytes, &credit_usec);
read_xenbus_vif_flags(be);
be->vif->queues = vzalloc(requested_num_queues *
sizeof(struct xenvif_queue));
rtnl_lock();
netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues);
rtnl_unlock();
for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) {
queue = &be->vif->queues[queue_index];
queue->vif = be->vif;
queue->id = queue_index;
snprintf(queue->name, sizeof(queue->name), "%s-q%u",
be->vif->dev->name, queue->id);
err = xenvif_init_queue(queue);
if (err)
goto err;
queue->remaining_credit = credit_bytes;
err = connect_rings(be, queue);
if (err)
goto err;
}
xenvif_carrier_on(be->vif);
unregister_hotplug_status_watch(be);
err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
......@@ -507,18 +535,26 @@ static void connect(struct backend_info *be)
if (!err)
be->have_hotplug_status_watch = 1;
netif_wake_queue(be->vif->dev);
netif_tx_wake_all_queues(be->vif->dev);
return;
err:
vfree(be->vif->queues);
be->vif->queues = NULL;
rtnl_lock();
netif_set_real_num_tx_queues(be->vif->dev, 0);
rtnl_unlock();
return;
}
static int connect_rings(struct backend_info *be)
static int connect_rings(struct backend_info *be, struct xenvif_queue *queue)
{
struct xenvif *vif = be->vif;
struct xenbus_device *dev = be->dev;
unsigned long tx_ring_ref, rx_ring_ref;
unsigned int tx_evtchn, rx_evtchn, rx_copy;
unsigned int tx_evtchn, rx_evtchn;
int err;
int val;
err = xenbus_gather(XBT_NIL, dev->otherend,
"tx-ring-ref", "%lu", &tx_ring_ref,
......@@ -546,6 +582,27 @@ static int connect_rings(struct backend_info *be)
rx_evtchn = tx_evtchn;
}
/* Map the shared frame, irq etc. */
err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref,
tx_evtchn, rx_evtchn);
if (err) {
xenbus_dev_fatal(dev, err,
"mapping shared-frames %lu/%lu port tx %u rx %u",
tx_ring_ref, rx_ring_ref,
tx_evtchn, rx_evtchn);
return err;
}
return 0;
}
static int read_xenbus_vif_flags(struct backend_info *be)
{
struct xenvif *vif = be->vif;
struct xenbus_device *dev = be->dev;
unsigned int rx_copy;
int err, val;
err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
&rx_copy);
if (err == -ENOENT) {
......@@ -621,16 +678,6 @@ static int connect_rings(struct backend_info *be)
val = 0;
vif->ipv6_csum = !!val;
/* Map the shared frame, irq etc. */
err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref,
tx_evtchn, rx_evtchn);
if (err) {
xenbus_dev_fatal(dev, err,
"mapping shared-frames %lu/%lu port tx %u rx %u",
tx_ring_ref, rx_ring_ref,
tx_evtchn, rx_evtchn);
return err;
}
return 0;
}
......
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