xen-netback: switch to NAPI + kthread 1:1 model
This patch implements 1:1 model netback. NAPI and kthread are utilized to do the weight-lifting job: - NAPI is used for guest side TX (host side RX) - kthread is used for guest side RX (host side TX) Xenvif and xen_netbk are made into one structure to reduce code size. This model provides better scheduling fairness among vifs. It is also prerequisite for implementing multiqueue for Xen netback. Signed-off-by: Wei Liu <wei.liu2@citrix.com> Acked-by: Ian Campbell <ian.campbell@citrix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
Wei Liu
David S. Miller
parent
43e9d19432
commit
b3f980bd82
|
|
@ -45,31 +45,109 @@
|
|||
#include <xen/grant_table.h>
|
||||
#include <xen/xenbus.h>
|
||||
|
||||
struct xen_netbk;
|
||||
typedef unsigned int pending_ring_idx_t;
|
||||
#define INVALID_PENDING_RING_IDX (~0U)
|
||||
|
||||
/* For the head field in pending_tx_info: it is used to indicate
|
||||
* whether this tx info is the head of one or more coalesced requests.
|
||||
*
|
||||
* When head != INVALID_PENDING_RING_IDX, it means the start of a new
|
||||
* tx requests queue and the end of previous queue.
|
||||
*
|
||||
* An example sequence of head fields (I = INVALID_PENDING_RING_IDX):
|
||||
*
|
||||
* ...|0 I I I|5 I|9 I I I|...
|
||||
* -->|<-INUSE----------------
|
||||
*
|
||||
* After consuming the first slot(s) we have:
|
||||
*
|
||||
* ...|V V V V|5 I|9 I I I|...
|
||||
* -----FREE->|<-INUSE--------
|
||||
*
|
||||
* where V stands for "valid pending ring index". Any number other
|
||||
* than INVALID_PENDING_RING_IDX is OK. These entries are considered
|
||||
* free and can contain any number other than
|
||||
* INVALID_PENDING_RING_IDX. In practice we use 0.
|
||||
*
|
||||
* The in use non-INVALID_PENDING_RING_IDX (say 0, 5 and 9 in the
|
||||
* above example) number is the index into pending_tx_info and
|
||||
* mmap_pages arrays.
|
||||
*/
|
||||
struct pending_tx_info {
|
||||
struct xen_netif_tx_request req; /* coalesced tx request */
|
||||
pending_ring_idx_t head; /* head != INVALID_PENDING_RING_IDX
|
||||
* if it is head of one or more tx
|
||||
* reqs
|
||||
*/
|
||||
};
|
||||
|
||||
#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
|
||||
#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
|
||||
|
||||
struct xenvif_rx_meta {
|
||||
int id;
|
||||
int size;
|
||||
int gso_size;
|
||||
};
|
||||
|
||||
/* Discriminate from any valid pending_idx value. */
|
||||
#define INVALID_PENDING_IDX 0xFFFF
|
||||
|
||||
#define MAX_BUFFER_OFFSET PAGE_SIZE
|
||||
|
||||
#define MAX_PENDING_REQS 256
|
||||
|
||||
struct xenvif {
|
||||
/* Unique identifier for this interface. */
|
||||
domid_t domid;
|
||||
unsigned int handle;
|
||||
|
||||
/* Reference to netback processing backend. */
|
||||
struct xen_netbk *netbk;
|
||||
|
||||
u8 fe_dev_addr[6];
|
||||
|
||||
/* Use NAPI for guest TX */
|
||||
struct napi_struct napi;
|
||||
/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
|
||||
unsigned int tx_irq;
|
||||
unsigned int rx_irq;
|
||||
/* Only used when feature-split-event-channels = 1 */
|
||||
char tx_irq_name[IFNAMSIZ+4]; /* DEVNAME-tx */
|
||||
char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
|
||||
|
||||
/* List of frontends to notify after a batch of frames sent. */
|
||||
struct list_head notify_list;
|
||||
|
||||
/* The shared rings and indexes. */
|
||||
struct xen_netif_tx_back_ring tx;
|
||||
struct sk_buff_head tx_queue;
|
||||
struct page *mmap_pages[MAX_PENDING_REQS];
|
||||
pending_ring_idx_t pending_prod;
|
||||
pending_ring_idx_t pending_cons;
|
||||
u16 pending_ring[MAX_PENDING_REQS];
|
||||
struct pending_tx_info pending_tx_info[MAX_PENDING_REQS];
|
||||
|
||||
/* Coalescing tx requests before copying makes number of grant
|
||||
* copy ops greater or equal to number of slots required. In
|
||||
* worst case a tx request consumes 2 gnttab_copy.
|
||||
*/
|
||||
struct gnttab_copy tx_copy_ops[2*MAX_PENDING_REQS];
|
||||
|
||||
|
||||
/* Use kthread for guest RX */
|
||||
struct task_struct *task;
|
||||
wait_queue_head_t wq;
|
||||
/* 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 */
|
||||
struct xen_netif_rx_back_ring rx;
|
||||
struct sk_buff_head rx_queue;
|
||||
|
||||
/* Allow xenvif_start_xmit() to peek ahead in the rx request
|
||||
* ring. This is a prediction of what rx_req_cons will be
|
||||
* once all queued skbs are put on the ring.
|
||||
*/
|
||||
RING_IDX rx_req_cons_peek;
|
||||
|
||||
/* Given MAX_BUFFER_OFFSET of 4096 the worst case is that each
|
||||
* head/fragment page uses 2 copy operations because it
|
||||
* straddles two buffers in the frontend.
|
||||
*/
|
||||
struct gnttab_copy grant_copy_op[2*XEN_NETIF_RX_RING_SIZE];
|
||||
struct xenvif_rx_meta meta[2*XEN_NETIF_RX_RING_SIZE];
|
||||
|
||||
|
||||
u8 fe_dev_addr[6];
|
||||
|
||||
/* Frontend feature information. */
|
||||
u8 can_sg:1;
|
||||
|
|
@ -80,13 +158,6 @@ struct xenvif {
|
|||
/* Internal feature information. */
|
||||
u8 can_queue:1; /* can queue packets for receiver? */
|
||||
|
||||
/*
|
||||
* Allow xenvif_start_xmit() to peek ahead in the rx request
|
||||
* ring. This is a prediction of what rx_req_cons will be
|
||||
* once all queued skbs are put on the ring.
|
||||
*/
|
||||
RING_IDX rx_req_cons_peek;
|
||||
|
||||
/* Transmit shaping: allow 'credit_bytes' every 'credit_usec'. */
|
||||
unsigned long credit_bytes;
|
||||
unsigned long credit_usec;
|
||||
|
|
@ -97,11 +168,7 @@ struct xenvif {
|
|||
unsigned long rx_gso_checksum_fixup;
|
||||
|
||||
/* Miscellaneous private stuff. */
|
||||
struct list_head schedule_list;
|
||||
atomic_t refcnt;
|
||||
struct net_device *dev;
|
||||
|
||||
wait_queue_head_t waiting_to_free;
|
||||
};
|
||||
|
||||
static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
|
||||
|
|
@ -109,9 +176,6 @@ static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif)
|
|||
return to_xenbus_device(vif->dev->dev.parent);
|
||||
}
|
||||
|
||||
#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
|
||||
#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
|
||||
|
||||
struct xenvif *xenvif_alloc(struct device *parent,
|
||||
domid_t domid,
|
||||
unsigned int handle);
|
||||
|
|
@ -121,9 +185,6 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
|
|||
unsigned int rx_evtchn);
|
||||
void xenvif_disconnect(struct xenvif *vif);
|
||||
|
||||
void xenvif_get(struct xenvif *vif);
|
||||
void xenvif_put(struct xenvif *vif);
|
||||
|
||||
int xenvif_xenbus_init(void);
|
||||
void xenvif_xenbus_fini(void);
|
||||
|
||||
|
|
@ -139,18 +200,8 @@ int xen_netbk_map_frontend_rings(struct xenvif *vif,
|
|||
grant_ref_t tx_ring_ref,
|
||||
grant_ref_t rx_ring_ref);
|
||||
|
||||
/* (De)Register a xenvif with the netback backend. */
|
||||
void xen_netbk_add_xenvif(struct xenvif *vif);
|
||||
void xen_netbk_remove_xenvif(struct xenvif *vif);
|
||||
|
||||
/* (De)Schedule backend processing for a xenvif */
|
||||
void xen_netbk_schedule_xenvif(struct xenvif *vif);
|
||||
void xen_netbk_deschedule_xenvif(struct xenvif *vif);
|
||||
|
||||
/* Check for SKBs from frontend and schedule backend processing */
|
||||
void xen_netbk_check_rx_xenvif(struct xenvif *vif);
|
||||
/* Receive an SKB from the frontend */
|
||||
void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb);
|
||||
|
||||
/* Queue an SKB for transmission to the frontend */
|
||||
void xen_netbk_queue_tx_skb(struct xenvif *vif, struct sk_buff *skb);
|
||||
|
|
@ -163,6 +214,11 @@ void xenvif_carrier_off(struct xenvif *vif);
|
|||
/* Returns number of ring slots required to send an skb to the frontend */
|
||||
unsigned int xen_netbk_count_skb_slots(struct xenvif *vif, struct sk_buff *skb);
|
||||
|
||||
int xen_netbk_tx_action(struct xenvif *vif, int budget);
|
||||
void xen_netbk_rx_action(struct xenvif *vif);
|
||||
|
||||
int xen_netbk_kthread(void *data);
|
||||
|
||||
extern bool separate_tx_rx_irq;
|
||||
|
||||
#endif /* __XEN_NETBACK__COMMON_H__ */
|
||||
|
|
|
|||
|
|
@ -30,6 +30,7 @@
|
|||
|
||||
#include "common.h"
|
||||
|
||||
#include <linux/kthread.h>
|
||||
#include <linux/ethtool.h>
|
||||
#include <linux/rtnetlink.h>
|
||||
#include <linux/if_vlan.h>
|
||||
|
|
@ -38,17 +39,7 @@
|
|||
#include <asm/xen/hypercall.h>
|
||||
|
||||
#define XENVIF_QUEUE_LENGTH 32
|
||||
|
||||
void xenvif_get(struct xenvif *vif)
|
||||
{
|
||||
atomic_inc(&vif->refcnt);
|
||||
}
|
||||
|
||||
void xenvif_put(struct xenvif *vif)
|
||||
{
|
||||
if (atomic_dec_and_test(&vif->refcnt))
|
||||
wake_up(&vif->waiting_to_free);
|
||||
}
|
||||
#define XENVIF_NAPI_WEIGHT 64
|
||||
|
||||
int xenvif_schedulable(struct xenvif *vif)
|
||||
{
|
||||
|
|
@ -64,21 +55,55 @@ static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id)
|
|||
{
|
||||
struct xenvif *vif = dev_id;
|
||||
|
||||
if (vif->netbk == NULL)
|
||||
return IRQ_HANDLED;
|
||||
|
||||
xen_netbk_schedule_xenvif(vif);
|
||||
if (RING_HAS_UNCONSUMED_REQUESTS(&vif->tx))
|
||||
napi_schedule(&vif->napi);
|
||||
|
||||
return IRQ_HANDLED;
|
||||
}
|
||||
|
||||
static int xenvif_poll(struct napi_struct *napi, int budget)
|
||||
{
|
||||
struct xenvif *vif = container_of(napi, struct xenvif, napi);
|
||||
int work_done;
|
||||
|
||||
work_done = xen_netbk_tx_action(vif, budget);
|
||||
|
||||
if (work_done < budget) {
|
||||
int more_to_do = 0;
|
||||
unsigned long flags;
|
||||
|
||||
/* It is necessary to disable IRQ before calling
|
||||
* RING_HAS_UNCONSUMED_REQUESTS. Otherwise we might
|
||||
* lose event from the frontend.
|
||||
*
|
||||
* Consider:
|
||||
* RING_HAS_UNCONSUMED_REQUESTS
|
||||
* <frontend generates event to trigger napi_schedule>
|
||||
* __napi_complete
|
||||
*
|
||||
* This handler is still in scheduled state so the
|
||||
* event has no effect at all. After __napi_complete
|
||||
* this handler is descheduled and cannot get
|
||||
* scheduled again. We lose event in this case and the ring
|
||||
* will be completely stalled.
|
||||
*/
|
||||
|
||||
local_irq_save(flags);
|
||||
|
||||
RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
|
||||
if (!more_to_do)
|
||||
__napi_complete(napi);
|
||||
|
||||
local_irq_restore(flags);
|
||||
}
|
||||
|
||||
return work_done;
|
||||
}
|
||||
|
||||
static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id)
|
||||
{
|
||||
struct xenvif *vif = dev_id;
|
||||
|
||||
if (vif->netbk == NULL)
|
||||
return IRQ_HANDLED;
|
||||
|
||||
if (xenvif_rx_schedulable(vif))
|
||||
netif_wake_queue(vif->dev);
|
||||
|
||||
|
|
@ -99,7 +124,8 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
|
|||
|
||||
BUG_ON(skb->dev != dev);
|
||||
|
||||
if (vif->netbk == NULL)
|
||||
/* Drop the packet if vif is not ready */
|
||||
if (vif->task == NULL)
|
||||
goto drop;
|
||||
|
||||
/* Drop the packet if the target domain has no receive buffers. */
|
||||
|
|
@ -108,7 +134,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
|
|||
|
||||
/* Reserve ring slots for the worst-case number of fragments. */
|
||||
vif->rx_req_cons_peek += xen_netbk_count_skb_slots(vif, skb);
|
||||
xenvif_get(vif);
|
||||
|
||||
if (vif->can_queue && xen_netbk_must_stop_queue(vif))
|
||||
netif_stop_queue(dev);
|
||||
|
|
@ -123,11 +148,6 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
|
|||
return NETDEV_TX_OK;
|
||||
}
|
||||
|
||||
void xenvif_receive_skb(struct xenvif *vif, struct sk_buff *skb)
|
||||
{
|
||||
netif_rx_ni(skb);
|
||||
}
|
||||
|
||||
void xenvif_notify_tx_completion(struct xenvif *vif)
|
||||
{
|
||||
if (netif_queue_stopped(vif->dev) && xenvif_rx_schedulable(vif))
|
||||
|
|
@ -142,7 +162,7 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
|
|||
|
||||
static void xenvif_up(struct xenvif *vif)
|
||||
{
|
||||
xen_netbk_add_xenvif(vif);
|
||||
napi_enable(&vif->napi);
|
||||
enable_irq(vif->tx_irq);
|
||||
if (vif->tx_irq != vif->rx_irq)
|
||||
enable_irq(vif->rx_irq);
|
||||
|
|
@ -151,12 +171,11 @@ static void xenvif_up(struct xenvif *vif)
|
|||
|
||||
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);
|
||||
xen_netbk_deschedule_xenvif(vif);
|
||||
xen_netbk_remove_xenvif(vif);
|
||||
}
|
||||
|
||||
static int xenvif_open(struct net_device *dev)
|
||||
|
|
@ -272,11 +291,12 @@ 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);
|
||||
if (dev == NULL) {
|
||||
pr_warn("Could not allocate netdev\n");
|
||||
pr_warn("Could not allocate netdev for %s\n", name);
|
||||
return ERR_PTR(-ENOMEM);
|
||||
}
|
||||
|
||||
|
|
@ -285,14 +305,9 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
|
|||
vif = netdev_priv(dev);
|
||||
vif->domid = domid;
|
||||
vif->handle = handle;
|
||||
vif->netbk = NULL;
|
||||
vif->can_sg = 1;
|
||||
vif->csum = 1;
|
||||
atomic_set(&vif->refcnt, 1);
|
||||
init_waitqueue_head(&vif->waiting_to_free);
|
||||
vif->dev = dev;
|
||||
INIT_LIST_HEAD(&vif->schedule_list);
|
||||
INIT_LIST_HEAD(&vif->notify_list);
|
||||
|
||||
vif->credit_bytes = vif->remaining_credit = ~0UL;
|
||||
vif->credit_usec = 0UL;
|
||||
|
|
@ -307,6 +322,16 @@ 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;
|
||||
for (i = 0; i < MAX_PENDING_REQS; i++)
|
||||
vif->mmap_pages[i] = NULL;
|
||||
|
||||
/*
|
||||
* Initialise a dummy MAC address. We choose the numerically
|
||||
* largest non-broadcast address to prevent the address getting
|
||||
|
|
@ -316,6 +341,8 @@ 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);
|
||||
|
|
@ -377,7 +404,14 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
|
|||
disable_irq(vif->rx_irq);
|
||||
}
|
||||
|
||||
xenvif_get(vif);
|
||||
init_waitqueue_head(&vif->wq);
|
||||
vif->task = kthread_create(xen_netbk_kthread,
|
||||
(void *)vif, vif->dev->name);
|
||||
if (IS_ERR(vif->task)) {
|
||||
pr_warn("Could not allocate kthread for %s\n", vif->dev->name);
|
||||
err = PTR_ERR(vif->task);
|
||||
goto err_rx_unbind;
|
||||
}
|
||||
|
||||
rtnl_lock();
|
||||
if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
|
||||
|
|
@ -388,7 +422,13 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
|
|||
xenvif_up(vif);
|
||||
rtnl_unlock();
|
||||
|
||||
wake_up_process(vif->task);
|
||||
|
||||
return 0;
|
||||
|
||||
err_rx_unbind:
|
||||
unbind_from_irqhandler(vif->rx_irq, vif);
|
||||
vif->rx_irq = 0;
|
||||
err_tx_unbind:
|
||||
unbind_from_irqhandler(vif->tx_irq, vif);
|
||||
vif->tx_irq = 0;
|
||||
|
|
@ -408,7 +448,6 @@ void xenvif_carrier_off(struct xenvif *vif)
|
|||
if (netif_running(dev))
|
||||
xenvif_down(vif);
|
||||
rtnl_unlock();
|
||||
xenvif_put(vif);
|
||||
}
|
||||
|
||||
void xenvif_disconnect(struct xenvif *vif)
|
||||
|
|
@ -422,9 +461,6 @@ void xenvif_disconnect(struct xenvif *vif)
|
|||
if (netif_carrier_ok(vif->dev))
|
||||
xenvif_carrier_off(vif);
|
||||
|
||||
atomic_dec(&vif->refcnt);
|
||||
wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
|
||||
|
||||
if (vif->tx_irq) {
|
||||
if (vif->tx_irq == vif->rx_irq)
|
||||
unbind_from_irqhandler(vif->tx_irq, vif);
|
||||
|
|
@ -438,6 +474,11 @@ void xenvif_disconnect(struct xenvif *vif)
|
|||
need_module_put = 1;
|
||||
}
|
||||
|
||||
if (vif->task)
|
||||
kthread_stop(vif->task);
|
||||
|
||||
netif_napi_del(&vif->napi);
|
||||
|
||||
unregister_netdev(vif->dev);
|
||||
|
||||
xen_netbk_unmap_frontend_rings(vif);
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
Loading…
Reference in a new issue