forge/linux-pinenote
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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

Browse source 
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: Andrew J. Bennieston <andrew.bennieston@citrix.com>
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Wei Liu 2014-06-04 10:30:42 +01:00 • committed by David S. Miller
commit e9ce7cb6b1
4 changed files with 837 additions and 608 deletions
Download patch file Download diff file Expand all files Collapse all files

102
drivers/net/xen-netback/common.h
View file

@ -99,22 +99,43 @@ struct xenvif_rx_meta {
*/ */
#define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN #define XEN_NETBK_LEGACY_SLOTS_MAX XEN_NETIF_NR_SLOTS_MIN
struct xenvif { /* Queue name is interface name with "-qNNN" appended */
/* Unique identifier for this interface. */ #define QUEUE_NAME_SIZE (IFNAMSIZ + 5)
domid_t domid;
unsigned int handle;
/* Is this interface disabled? True when backend discovers /* IRQ name is queue name with "-tx" or "-rx" appended */
* frontend is rogue. #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 */ /* Use NAPI for guest TX */
struct napi_struct napi; struct napi_struct napi;
/* When feature-split-event-channels = 0, tx_irq = rx_irq. */ /* When feature-split-event-channels = 0, tx_irq = rx_irq. */
unsigned int tx_irq; unsigned int tx_irq;
/* Only used when feature-split-event-channels = 1 */ /* 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 xen_netif_tx_back_ring tx;
struct sk_buff_head tx_queue; struct sk_buff_head tx_queue;
struct page *mmap_pages[MAX_PENDING_REQS]; struct page *mmap_pages[MAX_PENDING_REQS];
@ -150,7 +171,7 @@ struct xenvif {
/* When feature-split-event-channels = 0, tx_irq = rx_irq. */ /* When feature-split-event-channels = 0, tx_irq = rx_irq. */
unsigned int rx_irq; unsigned int rx_irq;
/* Only used when feature-split-event-channels = 1 */ /* 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 xen_netif_rx_back_ring rx;
struct sk_buff_head rx_queue; struct sk_buff_head rx_queue;
RING_IDX rx_last_skb_slots; RING_IDX rx_last_skb_slots;
@ -165,6 +186,22 @@ struct xenvif {
*/ */
struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE]; 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]; u8 fe_dev_addr[6];
/* Frontend feature information. */ /* Frontend feature information. */
@ -178,19 +215,13 @@ struct xenvif {
/* Internal feature information. */ /* Internal feature information. */
u8 can_queue:1; /* can queue packets for receiver? */ u8 can_queue:1; /* can queue packets for receiver? */
/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */ /* Is this interface disabled? True when backend discovers
unsigned long credit_bytes; * frontend is rogue.
unsigned long credit_usec; */
unsigned long remaining_credit; bool disabled;
struct timer_list credit_timeout;
u64 credit_window_start;
/* Statistics */ /* Queues */
unsigned long rx_gso_checksum_fixup; struct xenvif_queue *queues;
unsigned long tx_zerocopy_sent;
unsigned long tx_zerocopy_success;
unsigned long tx_zerocopy_fail;
unsigned long tx_frag_overflow;
/* Miscellaneous private stuff. */ /* Miscellaneous private stuff. */
struct net_device *dev; struct net_device *dev;
@ -205,7 +236,9 @@ struct xenvif *xenvif_alloc(struct device *parent,
domid_t domid, domid_t domid,
unsigned int handle); 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 long rx_ring_ref, unsigned int tx_evtchn,
unsigned int rx_evtchn); unsigned int rx_evtchn);
void xenvif_disconnect(struct xenvif *vif); void xenvif_disconnect(struct xenvif *vif);
@ -216,44 +249,47 @@ void xenvif_xenbus_fini(void);
int xenvif_schedulable(struct xenvif *vif); 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. */ /* (Un)Map communication rings. */
void xenvif_unmap_frontend_rings(struct xenvif *vif); void xenvif_unmap_frontend_rings(struct xenvif_queue *queue);
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 tx_ring_ref,
grant_ref_t rx_ring_ref); grant_ref_t rx_ring_ref);
/* Check for SKBs from frontend and schedule backend processing */ /* 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. */ /* Prevent the device from generating any further traffic. */
void xenvif_carrier_off(struct xenvif *vif); 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); 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); int xenvif_dealloc_kthread(void *data);
/* Determine whether the needed number of slots (req) are available, /* Determine whether the needed number of slots (req) are available,
* and set req_event if not. * 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 */ /* Callback from stack when TX packet can be released */
void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success); void xenvif_zerocopy_callback(struct ubuf_info *ubuf, bool zerocopy_success);
/* Unmap a pending page and release it back to the guest */ /* 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 - 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 */ /* Callback from stack when TX packet can be released */

538
drivers/net/xen-netback/interface.c
View file

@ -34,7 +34,6 @@
#include <linux/ethtool.h> #include <linux/ethtool.h>
#include <linux/rtnetlink.h> #include <linux/rtnetlink.h>
#include <linux/if_vlan.h> #include <linux/if_vlan.h>
#include <linux/vmalloc.h>
#include <xen/events.h> #include <xen/events.h>
#include <asm/xen/hypercall.h> #include <asm/xen/hypercall.h>
@ -43,6 +42,16 @@
#define XENVIF_QUEUE_LENGTH 32 #define XENVIF_QUEUE_LENGTH 32
#define XENVIF_NAPI_WEIGHT 64 #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) int xenvif_schedulable(struct xenvif *vif)
{ {
return netif_running(vif->dev) && netif_carrier_ok(vif->dev); 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) 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)) if (RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))
napi_schedule(&vif->napi); napi_schedule(&queue->napi);
return IRQ_HANDLED; 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; int work_done;
/* This vif is rogue, we pretend we've there is nothing to do /* This vif is rogue, we pretend we've there is nothing to do
* for this vif to deschedule it from NAPI. But this interface * for this vif to deschedule it from NAPI. But this interface
* will be turned off in thread context later. * will be turned off in thread context later.
*/ */
if (unlikely(vif->disabled)) { if (unlikely(queue->vif->disabled)) {
napi_complete(napi); napi_complete(napi);
return 0; return 0;
} }
work_done = xenvif_tx_action(vif, budget); work_done = xenvif_tx_action(queue, budget);
if (work_done < budget) { if (work_done < budget) {
napi_complete(napi); napi_complete(napi);
xenvif_napi_schedule_or_enable_events(vif); xenvif_napi_schedule_or_enable_events(queue);
} }
return work_done; 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) 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; return IRQ_HANDLED;
} }
@ -99,28 +109,81 @@ static irqreturn_t xenvif_interrupt(int irq, void *dev_id)
return IRQ_HANDLED; return IRQ_HANDLED;
} }
static void xenvif_wake_queue(unsigned long data) int xenvif_queue_stopped(struct xenvif_queue *queue)
{ {
struct xenvif *vif = (struct xenvif *)data; struct net_device *dev = queue->vif->dev;
unsigned int id = queue->id;
return netif_tx_queue_stopped(netdev_get_tx_queue(dev, id));
}
if (netif_queue_stopped(vif->dev)) { void xenvif_wake_queue(struct xenvif_queue *queue)
netdev_err(vif->dev, "draining TX queue\n"); {
vif->rx_queue_purge = true; struct net_device *dev = queue->vif->dev;
xenvif_kick_thread(vif); unsigned int id = queue->id;
netif_wake_queue(vif->dev); 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_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);
} }
} }
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) static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
{ {
struct xenvif *vif = netdev_priv(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; int min_slots_needed;
BUG_ON(skb->dev != dev); BUG_ON(skb->dev != dev);
/* Drop the packet if vif is not ready */ /* Drop the packet if queues are not set up */
if (vif->task == NULL || if (num_queues < 1)
vif->dealloc_task == NULL || 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)) !xenvif_schedulable(vif))
goto drop; 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 * then turn off the queue to give the ring a chance to
* drain. * drain.
*/ */
if (!xenvif_rx_ring_slots_available(vif, min_slots_needed)) { if (!xenvif_rx_ring_slots_available(queue, min_slots_needed)) {
vif->wake_queue.function = xenvif_wake_queue; queue->wake_queue.function = xenvif_wake_queue_callback;
vif->wake_queue.data = (unsigned long)vif; queue->wake_queue.data = (unsigned long)queue;
xenvif_stop_queue(vif); xenvif_stop_queue(queue);
mod_timer(&vif->wake_queue, mod_timer(&queue->wake_queue,
jiffies + rx_drain_timeout_jiffies); jiffies + rx_drain_timeout_jiffies);
} }
skb_queue_tail(&vif->rx_queue, skb); skb_queue_tail(&queue->rx_queue, skb);
xenvif_kick_thread(vif); xenvif_kick_thread(queue);
return NETDEV_TX_OK; 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) static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
{ {
struct xenvif *vif = netdev_priv(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; return &vif->dev->stats;
} }
static void xenvif_up(struct xenvif *vif) static void xenvif_up(struct xenvif *vif)
{ {
napi_enable(&vif->napi); struct xenvif_queue *queue = NULL;
enable_irq(vif->tx_irq); unsigned int num_queues = vif->dev->real_num_tx_queues;
if (vif->tx_irq != vif->rx_irq) unsigned int queue_index;
enable_irq(vif->rx_irq);
xenvif_napi_schedule_or_enable_events(vif); 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) static void xenvif_down(struct xenvif *vif)
{ {
napi_disable(&vif->napi); struct xenvif_queue *queue = NULL;
disable_irq(vif->tx_irq); unsigned int num_queues = vif->dev->real_num_tx_queues;
if (vif->tx_irq != vif->rx_irq) unsigned int queue_index;
disable_irq(vif->rx_irq);
del_timer_sync(&vif->credit_timeout); 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) 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); struct xenvif *vif = netdev_priv(dev);
if (netif_carrier_ok(dev)) if (netif_carrier_ok(dev))
xenvif_up(vif); xenvif_up(vif);
netif_start_queue(dev); netif_tx_start_all_queues(dev);
return 0; return 0;
} }
@ -196,7 +299,7 @@ static int xenvif_close(struct net_device *dev)
struct xenvif *vif = netdev_priv(dev); struct xenvif *vif = netdev_priv(dev);
if (netif_carrier_ok(dev)) if (netif_carrier_ok(dev))
xenvif_down(vif); xenvif_down(vif);
netif_stop_queue(dev); netif_tx_stop_all_queues(dev);
return 0; return 0;
} }
@ -236,29 +339,29 @@ static const struct xenvif_stat {
} xenvif_stats[] = { } xenvif_stats[] = {
{ {
"rx_gso_checksum_fixup", "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 /* If (sent != success + fail), there are probably packets never
* freed up properly! * freed up properly!
*/ */
{ {
"tx_zerocopy_sent", "tx_zerocopy_sent",
offsetof(struct xenvif, tx_zerocopy_sent), offsetof(struct xenvif_stats, tx_zerocopy_sent),
}, },
{ {
"tx_zerocopy_success", "tx_zerocopy_success",
offsetof(struct xenvif, tx_zerocopy_success), offsetof(struct xenvif_stats, tx_zerocopy_success),
}, },
{ {
"tx_zerocopy_fail", "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 /* Number of packets exceeding MAX_SKB_FRAG slots. You should use
* a guest with the same MAX_SKB_FRAG * a guest with the same MAX_SKB_FRAG
*/ */
{ {
"tx_frag_overflow", "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, static void xenvif_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 * data) 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; int i;
unsigned int queue_index;
struct xenvif_stats *vif_stats;
for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) for (i = 0; i < ARRAY_SIZE(xenvif_stats); i++) {
data[i] = *(unsigned long *)(vif + xenvif_stats[i].offset); 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) 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_fix_features = xenvif_fix_features,
.ndo_set_mac_address = eth_mac_addr, .ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr, .ndo_validate_addr = eth_validate_addr,
.ndo_select_queue = xenvif_select_queue,
}; };
struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, 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 net_device *dev;
struct xenvif *vif; struct xenvif *vif;
char name[IFNAMSIZ] = {}; char name[IFNAMSIZ] = {};
int i;
snprintf(name, IFNAMSIZ - 1, "vif%u.%u", domid, handle); 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) { if (dev == NULL) {
pr_warn("Could not allocate netdev for %s\n", name); pr_warn("Could not allocate netdev for %s\n", name);
return ERR_PTR(-ENOMEM); return ERR_PTR(-ENOMEM);
@ -339,15 +451,13 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
vif->can_sg = 1; vif->can_sg = 1;
vif->ip_csum = 1; vif->ip_csum = 1;
vif->dev = dev; vif->dev = dev;
vif->disabled = false; vif->disabled = false;
vif->credit_bytes = vif->remaining_credit = ~0UL; /* Start out with no queues. The call below does not require
vif->credit_usec = 0UL; * rtnl_lock() as it happens before register_netdev().
init_timer(&vif->credit_timeout); */
vif->credit_window_start = get_jiffies_64(); vif->queues = NULL;
netif_set_real_num_tx_queues(dev, 0);
init_timer(&vif->wake_queue);
dev->netdev_ops = &xenvif_netdev_ops; dev->netdev_ops = &xenvif_netdev_ops;
dev->hw_features = NETIF_F_SG | 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; 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 * Initialise a dummy MAC address. We choose the numerically
* largest non-broadcast address to prevent the address getting * 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); memset(dev->dev_addr, 0xFF, ETH_ALEN);
dev->dev_addr[0] &= ~0x01; dev->dev_addr[0] &= ~0x01;
netif_napi_add(dev, &vif->napi, xenvif_poll, XENVIF_NAPI_WEIGHT);
netif_carrier_off(dev); netif_carrier_off(dev);
err = register_netdev(dev); err = register_netdev(dev);
@ -413,76 +493,56 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
return vif; return vif;
} }
int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, int xenvif_init_queue(struct xenvif_queue *queue)
unsigned long rx_ring_ref, unsigned int tx_evtchn,
unsigned int rx_evtchn)
{ {
struct task_struct *task; int err, i;
int err = -ENOMEM;
BUG_ON(vif->tx_irq); queue->credit_bytes = queue->remaining_credit = ~0UL;
BUG_ON(vif->task); queue->credit_usec = 0UL;
BUG_ON(vif->dealloc_task); init_timer(&queue->credit_timeout);
queue->credit_window_start = get_jiffies_64();
err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); skb_queue_head_init(&queue->rx_queue);
if (err < 0) skb_queue_head_init(&queue->tx_queue);
goto err;
init_waitqueue_head(&vif->wq); queue->pending_cons = 0;
init_waitqueue_head(&vif->dealloc_wq); queue->pending_prod = MAX_PENDING_REQS;
for (i = 0; i < MAX_PENDING_REQS; ++i)
queue->pending_ring[i] = i;
if (tx_evtchn == rx_evtchn) { spin_lock_init(&queue->callback_lock);
/* feature-split-event-channels == 0 */ spin_lock_init(&queue->response_lock);
err = bind_interdomain_evtchn_to_irqhandler(
vif->domid, tx_evtchn, xenvif_interrupt, 0,
vif->dev->name, vif);
if (err < 0)
goto err_unmap;
vif->tx_irq = vif->rx_irq = err;
disable_irq(vif->tx_irq);
} else {
/* feature-split-event-channels == 1 */
snprintf(vif->tx_irq_name, sizeof(vif->tx_irq_name),
"%s-tx", vif->dev->name);
err = bind_interdomain_evtchn_to_irqhandler(
vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
vif->tx_irq_name, vif);
if (err < 0)
goto err_unmap;
vif->tx_irq = err;
disable_irq(vif->tx_irq);
snprintf(vif->rx_irq_name, sizeof(vif->rx_irq_name), /* If ballooning is disabled, this will consume real memory, so you
"%s-rx", vif->dev->name); * better enable it. The long term solution would be to use just a
err = bind_interdomain_evtchn_to_irqhandler( * bunch of valid page descriptors, without dependency on ballooning
vif->domid, rx_evtchn, xenvif_rx_interrupt, 0, */
vif->rx_irq_name, vif); err = alloc_xenballooned_pages(MAX_PENDING_REQS,
if (err < 0) queue->mmap_pages,
goto err_tx_unbind; false);
vif->rx_irq = err; if (err) {
disable_irq(vif->rx_irq); netdev_err(queue->vif->dev, "Could not reserve mmap_pages\n");
return -ENOMEM;
} }
task = kthread_create(xenvif_kthread_guest_rx, for (i = 0; i < MAX_PENDING_REQS; i++) {
(void *)vif, "%s-guest-rx", vif->dev->name); queue->pending_tx_info[i].callback_struct = (struct ubuf_info)
if (IS_ERR(task)) { { .callback = xenvif_zerocopy_callback,
pr_warn("Could not allocate kthread for %s\n", vif->dev->name); .ctx = NULL,
err = PTR_ERR(task); .desc = i };
goto err_rx_unbind; queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE;
} }
vif->task = task; init_timer(&queue->wake_queue);
task = kthread_create(xenvif_dealloc_kthread, netif_napi_add(queue->vif->dev, &queue->napi, xenvif_poll,
(void *)vif, "%s-dealloc", vif->dev->name); XENVIF_NAPI_WEIGHT);
if (IS_ERR(task)) {
pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
err = PTR_ERR(task);
goto err_rx_unbind;
}
vif->dealloc_task = task; return 0;
}
void xenvif_carrier_on(struct xenvif *vif)
{
rtnl_lock(); rtnl_lock();
if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
dev_set_mtu(vif->dev, ETH_DATA_LEN); dev_set_mtu(vif->dev, ETH_DATA_LEN);
@ -491,20 +551,89 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
if (netif_running(vif->dev)) if (netif_running(vif->dev))
xenvif_up(vif); xenvif_up(vif);
rtnl_unlock(); rtnl_unlock();
}
wake_up_process(vif->task); int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref,
wake_up_process(vif->dealloc_task); unsigned long rx_ring_ref, unsigned int tx_evtchn,
unsigned int rx_evtchn)
{
struct task_struct *task;
int err = -ENOMEM;
BUG_ON(queue->tx_irq);
BUG_ON(queue->task);
BUG_ON(queue->dealloc_task);
err = xenvif_map_frontend_rings(queue, tx_ring_ref, rx_ring_ref);
if (err < 0)
goto err;
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(
queue->vif->domid, tx_evtchn, xenvif_interrupt, 0,
queue->name, queue);
if (err < 0)
goto err_unmap;
queue->tx_irq = queue->rx_irq = err;
disable_irq(queue->tx_irq);
} else {
/* feature-split-event-channels == 1 */
snprintf(queue->tx_irq_name, sizeof(queue->tx_irq_name),
"%s-tx", queue->name);
err = bind_interdomain_evtchn_to_irqhandler(
queue->vif->domid, tx_evtchn, xenvif_tx_interrupt, 0,
queue->tx_irq_name, queue);
if (err < 0)
goto err_unmap;
queue->tx_irq = err;
disable_irq(queue->tx_irq);
snprintf(queue->rx_irq_name, sizeof(queue->rx_irq_name),
"%s-rx", queue->name);
err = bind_interdomain_evtchn_to_irqhandler(
queue->vif->domid, rx_evtchn, xenvif_rx_interrupt, 0,
queue->rx_irq_name, queue);
if (err < 0)
goto err_tx_unbind;
queue->rx_irq = err;
disable_irq(queue->rx_irq);
}
task = kthread_create(xenvif_kthread_guest_rx,
(void *)queue, "%s-guest-rx", queue->name);
if (IS_ERR(task)) {
pr_warn("Could not allocate kthread for %s\n", queue->name);
err = PTR_ERR(task);
goto err_rx_unbind;
}
queue->task = task;
task = kthread_create(xenvif_dealloc_kthread,
(void *)queue, "%s-dealloc", queue->name);
if (IS_ERR(task)) {
pr_warn("Could not allocate kthread for %s\n", queue->name);
err = PTR_ERR(task);
goto err_rx_unbind;
}
queue->dealloc_task = task;
wake_up_process(queue->task);
wake_up_process(queue->dealloc_task);
return 0; return 0;
err_rx_unbind: err_rx_unbind:
unbind_from_irqhandler(vif->rx_irq, vif); unbind_from_irqhandler(queue->rx_irq, queue);
vif->rx_irq = 0; queue->rx_irq = 0;
err_tx_unbind: err_tx_unbind:
unbind_from_irqhandler(vif->tx_irq, vif); unbind_from_irqhandler(queue->tx_irq, queue);
vif->tx_irq = 0; queue->tx_irq = 0;
err_unmap: err_unmap:
xenvif_unmap_frontend_rings(vif); xenvif_unmap_frontend_rings(queue);
err: err:
module_put(THIS_MODULE); module_put(THIS_MODULE);
return err; return err;
@ -521,38 +650,67 @@ void xenvif_carrier_off(struct xenvif *vif)
rtnl_unlock(); 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) 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)) if (netif_carrier_ok(vif->dev))
xenvif_carrier_off(vif); xenvif_carrier_off(vif);
if (vif->task) { for (queue_index = 0; queue_index < num_queues; ++queue_index) {
del_timer_sync(&vif->wake_queue); queue = &vif->queues[queue_index];
kthread_stop(vif->task);
vif->task = NULL;
}
if (vif->dealloc_task) { if (queue->task) {
kthread_stop(vif->dealloc_task); del_timer_sync(&queue->wake_queue);
vif->dealloc_task = NULL; 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);
} }
vif->tx_irq = 0;
}
xenvif_unmap_frontend_rings(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;
}
xenvif_unmap_frontend_rings(queue);
}
} }
void xenvif_free(struct xenvif *vif) 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 /* Here we want to avoid timeout messages if an skb can be legitimately
* stuck somewhere else. Realistically this could be an another vif's * stuck somewhere else. Realistically this could be an another vif's
* internal or QDisc queue. That another vif also has this * 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) * 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)); DIV_ROUND_UP(XENVIF_QUEUE_LENGTH, (XEN_NETIF_RX_RING_SIZE / MAX_SKB_FRAGS));
for (i = 0; i < MAX_PENDING_REQS; ++i) { unregister_netdev(vif->dev);
if (vif->grant_tx_handle[i] != NETBACK_INVALID_HANDLE) {
unmap_timeout++; for (queue_index = 0; queue_index < num_queues; ++queue_index) {
schedule_timeout(msecs_to_jiffies(1000)); queue = &vif->queues[queue_index];
if (unmap_timeout > worst_case_skb_lifetime &&
net_ratelimit()) xenvif_wait_unmap_timeout(queue, worst_case_skb_lifetime);
netdev_err(vif->dev, free_xenballooned_pages(MAX_PENDING_REQS, queue->mmap_pages);
"Page still granted! Index: %x\n",
i); netif_napi_del(&queue->napi);
/* 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;
}
} }
free_xenballooned_pages(MAX_PENDING_REQS, vif->mmap_pages); /* Free the array of queues. The call below does not require
* rtnl_lock() because it happens after unregister_netdev().
netif_napi_del(&vif->napi); */
netif_set_real_num_tx_queues(vif->dev, 0);
unregister_netdev(vif->dev); vfree(vif->queues);
vif->queues = NULL;
free_netdev(vif->dev); free_netdev(vif->dev);

710
drivers/net/xen-netback/netback.c
View file

File diff suppressed because it is too large Load diff

95
drivers/net/xen-netback/xenbus.c
View file

@ -19,6 +19,8 @@
*/ */
#include "common.h" #include "common.h"
#include <linux/vmalloc.h>
#include <linux/rtnetlink.h>
struct backend_info { struct backend_info {
struct xenbus_device *dev; struct xenbus_device *dev;
@ -34,8 +36,9 @@ struct backend_info {
u8 have_hotplug_status_watch:1; u8 have_hotplug_status_watch:1;
}; };
static int connect_rings(struct backend_info *); static int connect_rings(struct backend_info *be, struct xenvif_queue *queue);
static void connect(struct backend_info *); 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 backend_create_xenvif(struct backend_info *be);
static void unregister_hotplug_status_watch(struct backend_info *be); static void unregister_hotplug_status_watch(struct backend_info *be);
static void set_backend_state(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; int err;
struct xenbus_device *dev = be->dev; struct xenbus_device *dev = be->dev;
unsigned long credit_bytes, credit_usec;
err = connect_rings(be); unsigned int queue_index;
if (err) unsigned int requested_num_queues = 1;
return; struct xenvif_queue *queue;
err = xen_net_read_mac(dev, be->vif->fe_dev_addr); err = xen_net_read_mac(dev, be->vif->fe_dev_addr);
if (err) { if (err) {
@ -496,9 +499,34 @@ static void connect(struct backend_info *be)
return; return;
} }
xen_net_read_rate(dev, &be->vif->credit_bytes, xen_net_read_rate(dev, &credit_bytes, &credit_usec);
&be->vif->credit_usec); read_xenbus_vif_flags(be);
be->vif->remaining_credit = be->vif->credit_bytes;
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); unregister_hotplug_status_watch(be);
err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
@ -507,18 +535,26 @@ static void connect(struct backend_info *be)
if (!err) if (!err)
be->have_hotplug_status_watch = 1; 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; struct xenbus_device *dev = be->dev;
unsigned long tx_ring_ref, rx_ring_ref; 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 err;
int val;
err = xenbus_gather(XBT_NIL, dev->otherend, err = xenbus_gather(XBT_NIL, dev->otherend,
"tx-ring-ref", "%lu", &tx_ring_ref, "tx-ring-ref", "%lu", &tx_ring_ref,
@ -546,6 +582,27 @@ static int connect_rings(struct backend_info *be)
rx_evtchn = tx_evtchn; 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", err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u",
&rx_copy); &rx_copy);
if (err == -ENOENT) { if (err == -ENOENT) {
@ -621,16 +678,6 @@ static int connect_rings(struct backend_info *be)
val = 0; val = 0;
vif->ipv6_csum = !!val; 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; return 0;
} }