xen-netfront.rar_remote

/* * Virtual network driver for conversing with remote driver backends. * */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/ethtool.h> #include <linux/if_ether.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/moduleparam.h> #include <linux/mm.h> #include <linux/slab.h> #include <net/ip.h> #include <xen/xen.h> #include <xen/xenbus.h> #include <xen/events.h> #include <xen/page.h> #include <xen/grant_table.h> #include <xen/interface/io/netif.h> #include <xen/interface/memory.h> #include <xen/interface/grant_table.h> static const struct ethtool_ops xennet_ethtool_ops; struct netfront_cb { struct page *page; unsigned offset; }; #define NETFRONT_SKB_CB(skb) ((struct netfront_cb *)((skb)->cb)) #define RX_COPY_THRESHOLD 256 #define GRANT_INVALID_REF 0 #define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE) #define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE) #define TX_MAX_TARGET min_t(int, NET_RX_RING_SIZE, 256) struct netfront_info { struct list_head list; struct net_device *netdev; struct napi_struct napi; unsigned int evtchn; struct xenbus_device *xbdev; spinlock_t tx_lock; struct xen_netif_tx_front_ring tx; int tx_ring_ref; /* * {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries * are linked from tx_skb_freelist through skb_entry.link. * * NB. Freelist index entries are always going to be less than * PAGE_OFFSET, whereas pointers to skbs will always be equal or * greater than PAGE_OFFSET: we use this property to distinguish * them. */ union skb_entry { struct sk_buff *skb; unsigned long link; } tx_skbs[NET_TX_RING_SIZE]; grant_ref_t gref_tx_head; grant_ref_t grant_tx_ref[NET_TX_RING_SIZE]; unsigned tx_skb_freelist; spinlock_t rx_lock ____cacheline_aligned_in_smp; struct xen_netif_rx_front_ring rx; int rx_ring_ref; /* Receive-ring batched refills. */ #define RX_MIN_TARGET 8 #define RX_DFL_MIN_TARGET 64 #define RX_MAX_TARGET min_t(int, NET_RX_RING_SIZE, 256) unsigned rx_min_target, rx_max_target, rx_target; struct sk_buff_head rx_batch; struct timer_list rx_refill_timer; struct sk_buff *rx_skbs[NET_RX_RING_SIZE]; grant_ref_t gref_rx_head; grant_ref_t grant_rx_ref[NET_RX_RING_SIZE]; unsigned long rx_pfn_array[NET_RX_RING_SIZE]; struct multicall_entry rx_mcl[NET_RX_RING_SIZE+1]; struct mmu_update rx_mmu[NET_RX_RING_SIZE]; /* Statistics */ unsigned long rx_gso_checksum_fixup; }; struct netfront_rx_info { struct xen_netif_rx_response rx; struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1]; }; static void skb_entry_set_link(union skb_entry *list, unsigned short id) { list->link = id; } static int skb_entry_is_link(const union skb_entry *list) { BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link)); return (unsigned long)list->skb < PAGE_OFFSET; } /* * Access macros for acquiring freeing slots in tx_skbs[]. */ static void add_id_to_freelist(unsigned *head, union skb_entry *list, unsigned short id) { skb_entry_set_link(&list[id], *head); *head = id; } static unsigned short get_id_from_freelist(unsigned *head, union skb_entry *list) { unsigned int id = *head; *head = list[id].link; return id; } static int xennet_rxidx(RING_IDX idx) { return idx & (NET_RX_RING_SIZE - 1); } static struct sk_buff *xennet_get_rx_skb(struct netfront_info *np, RING_IDX ri) { int i = xennet_rxidx(ri); struct sk_buff *skb = np->rx_skbs[i]; np->rx_skbs[i] = NULL; return skb; } static grant_ref_t xennet_get_rx_ref(struct netfront_info *np, RING_IDX ri) { int i = xennet_rxidx(ri); grant_ref_t ref = np->grant_rx_ref[i]; np->grant_rx_ref[i] = GRANT_INVALID_REF; return ref; } #ifdef CONFIG_SYSFS static int xennet_sysfs_addif(struct net_device *netdev); static void xennet_sysfs_delif(struct net_device *netdev); #else /* !CONFIG_SYSFS */ #define xennet_sysfs_addif(dev) (0) #define xennet_sysfs_delif(dev) do { } while (0) #endif static int xennet_can_sg(struct net_device *dev) { return dev->features & NETIF_F_SG; } static void rx_refill_timeout(unsigned long data) { struct net_device *dev = (struct net_device *)data; struct netfront_info *np = netdev_priv(dev); napi_schedule(&np->napi); } static int netfront_tx_slot_available(struct netfront_info *np) { return (np->tx.req_prod_pvt - np->tx.rsp_cons) < (TX_MAX_TARGET - MAX_SKB_FRAGS - 2); } static void xennet_maybe_wake_tx(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); if (unlikely(netif_queue_stopped(dev)) && netfront_tx_slot_available(np) && likely(netif_running(dev))) netif_wake_queue(dev); } static void xennet_alloc_rx_buffers(struct net_device *dev) { unsigned short id; struct netfront_info *np = netdev_priv(dev); struct sk_buff *skb; struct page *page; int i, batch_target, notify; RING_IDX req_prod = np->rx.req_prod_pvt; grant_ref_t ref; unsigned long pfn; void *vaddr; struct xen_netif_rx_request *req; if (unlikely(!netif_carrier_ok(dev))) return; /* * Allocate skbuffs greedily, even though we batch updates to the * receive ring. This creates a less bursty demand on the memory * allocator, so should reduce the chance of failed allocation requests * both for ourself and for other kernel subsystems. */ batch_target = np->rx_target - (req_prod - np->rx.rsp_cons); for (i = skb_queue_len(&np->rx_batch); i < batch_target; i++) { skb = __netdev_alloc_skb(dev, RX_COPY_THRESHOLD + NET_IP_ALIGN, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) goto no_skb; /* Align ip header to a 16 bytes boundary */ skb_reserve(skb, NET_IP_ALIGN); page = alloc_page(GFP_ATOMIC | __GFP_NOWARN); if (!page) { kfree_skb(skb); no_skb: /* Any skbuffs queued for refill? Force them out. */ if (i != 0) goto refill; /* Could not allocate any skbuffs. Try again later. */ mod_timer(&np->rx_refill_timer, jiffies + (HZ/10)); break; } skb_shinfo(skb)->frags[0].page = page; skb_shinfo(skb)->nr_frags = 1; __skb_queue_tail(&np->rx_batch, skb); } /* Is the batch large enough to be worthwhile? */ if (i < (np->rx_target/2)) { if (req_prod > np->rx.sring->req_prod) goto push; return; } /* Adjust our fill target if we risked running out of buffers. */ if (((req_prod - np->rx.sring->rsp_prod) < (np->rx_target / 4)) && ((np->rx_target *= 2) > np->rx_max_target)) np->rx_target = np->rx_max_target; refill: for (i = 0; ; i++) { skb = __skb_dequeue(&np->rx_batch); if (skb == NULL) break; skb->dev = dev; id = xennet_rxidx(req_prod + i); BUG_ON(np->rx_skbs[id]); np->rx_skbs[id] = skb; ref = gnttab_claim_grant_reference(&np->gref_rx_head); BUG_ON((signed short)ref < 0); np->grant_rx_ref[id] = ref; pfn = page_to_pfn(skb_shinfo(skb)->frags[0].page); vaddr = page_address(skb_shinfo(skb)->frags[0].page); req = RING_GET_REQUEST(&np->rx, req_prod + i); gnttab_grant_foreign_access_ref(ref, np->xbdev->otherend_id, pfn_to_mfn(pfn), 0); req->id = id; req->gref = ref; } wmb(); /* barrier so backend seens requests */ /* Above is a suitable barrier to ensure backend will see requests. */ np->rx.req_prod_pvt = req_prod + i; push: RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&np->rx, notify); if (notify) notify_remote_via_irq(np->netdev->irq); } static int xennet_open(struct net_device *dev) { struct netfront_info *np = netdev_priv(dev); napi_enable(&np->napi); spin_lock_bh(&np->rx_lock); if (netif_carrier_ok(dev)) { xennet_alloc_rx_buffers(dev); np->rx.sring->rsp_event = np->rx.rsp_cons + 1; if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx)) napi_schedule(&np->napi); } spin_unlock_bh(&np->rx_lock); netif_start_queue(dev); return 0; } static void xennet_tx_buf_gc(struct net_device *dev) { RING_IDX cons, prod; unsigned short id; struct netfront_info *np = netdev