diff options
Diffstat (limited to 'drivers/net/xen-netback')
| -rw-r--r-- | drivers/net/xen-netback/common.h | 32 | ||||
| -rw-r--r-- | drivers/net/xen-netback/interface.c | 54 | ||||
| -rw-r--r-- | drivers/net/xen-netback/netback.c | 392 | ||||
| -rw-r--r-- | drivers/net/xen-netback/xenbus.c | 52 |
4 files changed, 423 insertions, 107 deletions
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 5715318d6ba..c47794b9d42 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -87,9 +87,13 @@ struct pending_tx_info { struct xenvif_rx_meta { int id; int size; + int gso_type; int gso_size; }; +#define GSO_BIT(type) \ + (1 << XEN_NETIF_GSO_TYPE_ ## type) + /* Discriminate from any valid pending_idx value. */ #define INVALID_PENDING_IDX 0xFFFF @@ -97,6 +101,13 @@ struct xenvif_rx_meta { #define MAX_PENDING_REQS 256 +/* It's possible for an skb to have a maximal number of frags + * but still be less than MAX_BUFFER_OFFSET in size. Thus the + * worst-case number of copy operations is MAX_SKB_FRAGS per + * ring slot. + */ +#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE) + struct xenvif { /* Unique identifier for this interface. */ domid_t domid; @@ -139,21 +150,23 @@ struct xenvif { */ 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]; + /* This array is allocated seperately as it is large */ + struct gnttab_copy *grant_copy_op; + /* We create one meta structure per ring request we consume, so + * the maximum number is the same as the ring size. + */ + struct xenvif_rx_meta meta[XEN_NETIF_RX_RING_SIZE]; u8 fe_dev_addr[6]; /* Frontend feature information. */ + int gso_mask; + int gso_prefix_mask; + u8 can_sg:1; - u8 gso:1; - u8 gso_prefix:1; - u8 csum:1; + u8 ip_csum:1; + u8 ipv6_csum:1; /* Internal feature information. */ u8 can_queue:1; /* can queue packets for receiver? */ @@ -163,6 +176,7 @@ struct xenvif { unsigned long credit_usec; unsigned long remaining_credit; struct timer_list credit_timeout; + u64 credit_window_start; /* Statistics */ unsigned long rx_gso_checksum_fixup; diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 01bb854c7f6..fff8cddfed8 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -34,6 +34,7 @@ #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> @@ -214,10 +215,14 @@ static netdev_features_t xenvif_fix_features(struct net_device *dev, if (!vif->can_sg) features &= ~NETIF_F_SG; - if (!vif->gso && !vif->gso_prefix) + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV4)) features &= ~NETIF_F_TSO; - if (!vif->csum) + if (~(vif->gso_mask | vif->gso_prefix_mask) & GSO_BIT(TCPV6)) + features &= ~NETIF_F_TSO6; + if (!vif->ip_csum) features &= ~NETIF_F_IP_CSUM; + if (!vif->ipv6_csum) + features &= ~NETIF_F_IPV6_CSUM; return features; } @@ -303,21 +308,31 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, SET_NETDEV_DEV(dev, parent); vif = netdev_priv(dev); + + vif->grant_copy_op = vmalloc(sizeof(struct gnttab_copy) * + MAX_GRANT_COPY_OPS); + if (vif->grant_copy_op == NULL) { + pr_warn("Could not allocate grant copy space for %s\n", name); + free_netdev(dev); + return ERR_PTR(-ENOMEM); + } + vif->domid = domid; vif->handle = handle; vif->can_sg = 1; - vif->csum = 1; + vif->ip_csum = 1; vif->dev = dev; vif->credit_bytes = vif->remaining_credit = ~0UL; vif->credit_usec = 0UL; init_timer(&vif->credit_timeout); - /* Initialize 'expires' now: it's used to track the credit window. */ - vif->credit_timeout.expires = jiffies; + vif->credit_window_start = get_jiffies_64(); dev->netdev_ops = &xenvif_netdev_ops; - dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; - dev->features = dev->hw_features; + dev->hw_features = NETIF_F_SG | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO | NETIF_F_TSO6; + dev->features = dev->hw_features | NETIF_F_RXCSUM; SET_ETHTOOL_OPS(dev, &xenvif_ethtool_ops); dev->tx_queue_len = XENVIF_QUEUE_LENGTH; @@ -363,11 +378,11 @@ int xenvif_connect(struct xenvif *vif, 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; - /* Already connected through? */ - if (vif->tx_irq) - return 0; + BUG_ON(vif->tx_irq); + BUG_ON(vif->task); err = xenvif_map_frontend_rings(vif, tx_ring_ref, rx_ring_ref); if (err < 0) @@ -406,14 +421,16 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref, } init_waitqueue_head(&vif->wq); - vif->task = kthread_create(xenvif_kthread, - (void *)vif, "%s", vif->dev->name); - if (IS_ERR(vif->task)) { + task = kthread_create(xenvif_kthread, + (void *)vif, "%s", vif->dev->name); + if (IS_ERR(task)) { pr_warn("Could not allocate kthread for %s\n", vif->dev->name); - err = PTR_ERR(vif->task); + err = PTR_ERR(task); goto err_rx_unbind; } + vif->task = task; + rtnl_lock(); if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN) dev_set_mtu(vif->dev, ETH_DATA_LEN); @@ -456,6 +473,11 @@ void xenvif_disconnect(struct xenvif *vif) if (netif_carrier_ok(vif->dev)) xenvif_carrier_off(vif); + if (vif->task) { + kthread_stop(vif->task); + vif->task = NULL; + } + if (vif->tx_irq) { if (vif->tx_irq == vif->rx_irq) unbind_from_irqhandler(vif->tx_irq, vif); @@ -466,9 +488,6 @@ void xenvif_disconnect(struct xenvif *vif) vif->tx_irq = 0; } - if (vif->task) - kthread_stop(vif->task); - xenvif_unmap_frontend_rings(vif); } @@ -478,6 +497,7 @@ void xenvif_free(struct xenvif *vif) unregister_netdev(vif->dev); + vfree(vif->grant_copy_op); free_netdev(vif->dev); module_put(THIS_MODULE); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index f3e591c611d..78425554a53 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -39,6 +39,7 @@ #include <linux/udp.h> #include <net/tcp.h> +#include <net/ip6_checksum.h> #include <xen/xen.h> #include <xen/events.h> @@ -109,15 +110,12 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif, return (unsigned long)pfn_to_kaddr(idx_to_pfn(vif, idx)); } -/* - * This is the amount of packet we copy rather than map, so that the - * guest can't fiddle with the contents of the headers while we do - * packet processing on them (netfilter, routing, etc). +/* This is a miniumum size for the linear area to avoid lots of + * calls to __pskb_pull_tail() as we set up checksum offsets. The + * value 128 was chosen as it covers all IPv4 and most likely + * IPv6 headers. */ -#define PKT_PROT_LEN (ETH_HLEN + \ - VLAN_HLEN + \ - sizeof(struct iphdr) + MAX_IPOPTLEN + \ - sizeof(struct tcphdr) + MAX_TCP_OPTION_SPACE) +#define PKT_PROT_LEN 128 static u16 frag_get_pending_idx(skb_frag_t *frag) { @@ -145,7 +143,7 @@ static int max_required_rx_slots(struct xenvif *vif) int max = DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE); /* XXX FIXME: RX path dependent on MAX_SKB_FRAGS */ - if (vif->can_sg || vif->gso || vif->gso_prefix) + if (vif->can_sg || vif->gso_mask || vif->gso_prefix_mask) max += MAX_SKB_FRAGS + 1; /* extra_info + frags */ return max; @@ -317,6 +315,7 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif *vif, req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; meta->size = 0; meta->id = req->id; @@ -339,6 +338,7 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, struct gnttab_copy *copy_gop; struct xenvif_rx_meta *meta; unsigned long bytes; + int gso_type; /* Data must not cross a page boundary. */ BUG_ON(size + offset > PAGE_SIZE<<compound_order(page)); @@ -397,7 +397,14 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb, } /* Leave a gap for the GSO descriptor. */ - if (*head && skb_shinfo(skb)->gso_size && !vif->gso_prefix) + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + else + gso_type = XEN_NETIF_GSO_TYPE_NONE; + + if (*head && ((1 << gso_type) & vif->gso_mask)) vif->rx.req_cons++; *head = 0; /* There must be something in this buffer now. */ @@ -428,14 +435,28 @@ static int xenvif_gop_skb(struct sk_buff *skb, unsigned char *data; int head = 1; int old_meta_prod; + int gso_type; + int gso_size; old_meta_prod = npo->meta_prod; + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { + gso_type = XEN_NETIF_GSO_TYPE_TCPV4; + gso_size = skb_shinfo(skb)->gso_size; + } else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) { + gso_type = XEN_NETIF_GSO_TYPE_TCPV6; + gso_size = skb_shinfo(skb)->gso_size; + } else { + gso_type = XEN_NETIF_GSO_TYPE_NONE; + gso_size = 0; + } + /* Set up a GSO prefix descriptor, if necessary */ - if (skb_shinfo(skb)->gso_size && vif->gso_prefix) { + if ((1 << gso_type) & vif->gso_prefix_mask) { req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; - meta->gso_size = skb_shinfo(skb)->gso_size; + meta->gso_type = gso_type; + meta->gso_size = gso_size; meta->size = 0; meta->id = req->id; } @@ -443,10 +464,13 @@ static int xenvif_gop_skb(struct sk_buff *skb, req = RING_GET_REQUEST(&vif->rx, vif->rx.req_cons++); meta = npo->meta + npo->meta_prod++; - if (!vif->gso_prefix) - meta->gso_size = skb_shinfo(skb)->gso_size; - else + if ((1 << gso_type) & vif->gso_mask) { + meta->gso_type = gso_type; + meta->gso_size = gso_size; + } else { + meta->gso_type = XEN_NETIF_GSO_TYPE_NONE; meta->gso_size = 0; + } meta->size = 0; meta->id = req->id; @@ -584,7 +608,7 @@ void xenvif_rx_action(struct xenvif *vif) if (!npo.copy_prod) return; - BUG_ON(npo.copy_prod > ARRAY_SIZE(vif->grant_copy_op)); + BUG_ON(npo.copy_prod > MAX_GRANT_COPY_OPS); gnttab_batch_copy(vif->grant_copy_op, npo.copy_prod); while ((skb = __skb_dequeue(&rxq)) != NULL) { @@ -592,7 +616,8 @@ void xenvif_rx_action(struct xenvif *vif) vif = netdev_priv(skb->dev); - if (vif->meta[npo.meta_cons].gso_size && vif->gso_prefix) { + if ((1 << vif->meta[npo.meta_cons].gso_type) & + vif->gso_prefix_mask) { resp = RING_GET_RESPONSE(&vif->rx, vif->rx.rsp_prod_pvt++); @@ -629,7 +654,8 @@ void xenvif_rx_action(struct xenvif *vif) vif->meta[npo.meta_cons].size, flags); - if (vif->meta[npo.meta_cons].gso_size && !vif->gso_prefix) { + if ((1 << vif->meta[npo.meta_cons].gso_type) & + vif->gso_mask) { struct xen_netif_extra_info *gso = (struct xen_netif_extra_info *) RING_GET_RESPONSE(&vif->rx, @@ -637,8 +663,8 @@ void xenvif_rx_action(struct xenvif *vif) 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 = XEN_NETIF_GSO_TYPE_TCPV4; gso->u.gso.pad = 0; gso->u.gso.features = 0; @@ -1101,15 +1127,20 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return -EINVAL; } - /* Currently only TCPv4 S.O. is supported. */ - if (gso->u.gso.type != XEN_NETIF_GSO_TYPE_TCPV4) { + switch (gso->u.gso.type) { + case XEN_NETIF_GSO_TYPE_TCPV4: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + break; + case XEN_NETIF_GSO_TYPE_TCPV6: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + break; + default: netdev_err(vif->dev, "Bad GSO type %d.\n", gso->u.gso.type); xenvif_fatal_tx_err(vif); return -EINVAL; } skb_shinfo(skb)->gso_size = gso->u.gso.size; - skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; /* Header must be checked, and gso_segs computed. */ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; @@ -1118,62 +1149,244 @@ static int xenvif_set_skb_gso(struct xenvif *vif, return 0; } -static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) +static inline int maybe_pull_tail(struct sk_buff *skb, unsigned int len, + unsigned int max) { - struct iphdr *iph; - int err = -EPROTO; - int recalculate_partial_csum = 0; + if (skb_headlen(skb) >= len) + return 0; - /* - * A GSO SKB must be CHECKSUM_PARTIAL. However some buggy - * peers can fail to set NETRXF_csum_blank when sending a GSO - * frame. In this case force the SKB to CHECKSUM_PARTIAL and - * recalculate the partial checksum. + /* If we need to pullup then pullup to the max, so we + * won't need to do it again. */ - if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { - vif->rx_gso_checksum_fixup++; - skb->ip_summed = CHECKSUM_PARTIAL; - recalculate_partial_csum = 1; + if (max > skb->len) + max = skb->len; + + if (__pskb_pull_tail(skb, max - skb_headlen(skb)) == NULL) + return -ENOMEM; + + if (skb_headlen(skb) < len) + return -EPROTO; + + return 0; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * maximally sized IP and TCP or UDP headers. + */ +#define MAX_IP_HDR_LEN 128 + +static int checksum_setup_ip(struct xenvif *vif, struct sk_buff *skb, + int recalculate_partial_csum) +{ + unsigned int off; + bool fragment; + int err; + + fragment = false; + + err = maybe_pull_tail(skb, + sizeof(struct iphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (ip_hdr(skb)->frag_off & htons(IP_OFFSET | IP_MF)) + fragment = true; + + off = ip_hdrlen(skb); + + err = -EPROTO; + + if (fragment) + goto out; + + switch (ip_hdr(skb)->protocol) { + case IPPROTO_TCP: + err = maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate_partial_csum) + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); + break; + case IPPROTO_UDP: + err = maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IP_HDR_LEN); + if (err < 0) + goto out; + + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; + } + + if (recalculate_partial_csum) + udp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); + break; + default: + goto out; } - /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ - if (skb->ip_summed != CHECKSUM_PARTIAL) - return 0; + err = 0; + +out: + return err; +} + +/* This value should be large enough to cover a tagged ethernet header plus + * an IPv6 header, all options, and a maximal TCP or UDP header. + */ +#define MAX_IPV6_HDR_LEN 256 + +#define OPT_HDR(type, skb, off) \ + (type *)(skb_network_header(skb) + (off)) + +static int checksum_setup_ipv6(struct xenvif *vif, struct sk_buff *skb, + int recalculate_partial_csum) +{ + int err; + u8 nexthdr; + unsigned int off; + unsigned int len; + bool fragment; + bool done; + + fragment = false; + done = false; + + off = sizeof(struct ipv6hdr); + + err = maybe_pull_tail(skb, off, MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + nexthdr = ipv6_hdr(skb)->nexthdr; + + len = sizeof(struct ipv6hdr) + ntohs(ipv6_hdr(skb)->payload_len); + while (off <= len && !done) { + switch (nexthdr) { + case IPPROTO_DSTOPTS: + case IPPROTO_HOPOPTS: + case IPPROTO_ROUTING: { + struct ipv6_opt_hdr *hp; + + err = maybe_pull_tail(skb, + off + + sizeof(struct ipv6_opt_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ipv6_opt_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_optlen(hp); + break; + } + case IPPROTO_AH: { + struct ip_auth_hdr *hp; + + err = maybe_pull_tail(skb, + off + + sizeof(struct ip_auth_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct ip_auth_hdr, skb, off); + nexthdr = hp->nexthdr; + off += ipv6_authlen(hp); + break; + } + case IPPROTO_FRAGMENT: { + struct frag_hdr *hp; + + err = maybe_pull_tail(skb, + off + + sizeof(struct frag_hdr), + MAX_IPV6_HDR_LEN); + if (err < 0) + goto out; + + hp = OPT_HDR(struct frag_hdr, skb, off); + + if (hp->frag_off & htons(IP6_OFFSET | IP6_MF)) + fragment = true; + + nexthdr = hp->nexthdr; + off += sizeof(struct frag_hdr); + break; + } + default: + done = true; + break; + } + } + + err = -EPROTO; - if (skb->protocol != htons(ETH_P_IP)) + if (!done || fragment) goto out; - iph = (void *)skb->data; - switch (iph->protocol) { + switch (nexthdr) { case IPPROTO_TCP: - if (!skb_partial_csum_set(skb, 4 * iph->ihl, - offsetof(struct tcphdr, check))) + err = maybe_pull_tail(skb, + off + sizeof(struct tcphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) goto out; - if (recalculate_partial_csum) { - struct tcphdr *tcph = tcp_hdr(skb); - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - iph->ihl*4, - IPPROTO_TCP, 0); + if (!skb_partial_csum_set(skb, off, + offsetof(struct tcphdr, check))) { + err = -EPROTO; + goto out; } + + if (recalculate_partial_csum) + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_TCP, 0); break; case IPPROTO_UDP: - if (!skb_partial_csum_set(skb, 4 * iph->ihl, - offsetof(struct udphdr, check))) + err = maybe_pull_tail(skb, + off + sizeof(struct udphdr), + MAX_IPV6_HDR_LEN); + if (err < 0) goto out; - if (recalculate_partial_csum) { - struct udphdr *udph = udp_hdr(skb); - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - iph->ihl*4, - IPPROTO_UDP, 0); + if (!skb_partial_csum_set(skb, off, + offsetof(struct udphdr, check))) { + err = -EPROTO; + goto out; } + + if (recalculate_partial_csum) + udp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - off, + IPPROTO_UDP, 0); break; default: - if (net_ratelimit()) - netdev_err(vif->dev, - "Attempting to checksum a non-TCP/UDP packet, dropping a protocol %d packet\n", - iph->protocol); goto out; } @@ -1183,11 +1396,38 @@ out: return err; } +static int checksum_setup(struct xenvif *vif, struct sk_buff *skb) +{ + int err = -EPROTO; + int recalculate_partial_csum = 0; + + /* A GSO SKB must be CHECKSUM_PARTIAL. However some buggy + * peers can fail to set NETRXF_csum_blank when sending a GSO + * frame. In this case force the SKB to CHECKSUM_PARTIAL and + * recalculate the partial checksum. + */ + if (skb->ip_summed != CHECKSUM_PARTIAL && skb_is_gso(skb)) { + vif->rx_gso_checksum_fixup++; + skb->ip_summed = CHECKSUM_PARTIAL; + recalculate_partial_csum = 1; + } + + /* A non-CHECKSUM_PARTIAL SKB does not require setup. */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (skb->protocol == htons(ETH_P_IP)) + err = checksum_setup_ip(vif, skb, recalculate_partial_csum); + else if (skb->protocol == htons(ETH_P_IPV6)) + err = checksum_setup_ipv6(vif, skb, recalculate_partial_csum); + + return err; +} + static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) { - unsigned long now = jiffies; - unsigned long next_credit = - vif->credit_timeout.expires + + u64 now = get_jiffies_64(); + u64 next_credit = vif->credit_window_start + msecs_to_jiffies(vif->credit_usec / 1000); /* Timer could already be pending in rare cases. */ @@ -1195,8 +1435,8 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return true; /* Passed the point where we can replenish credit? */ - if (time_after_eq(now, next_credit)) { - vif->credit_timeout.expires = now; + if (time_after_eq64(now, next_credit)) { + vif->credit_window_start = now; tx_add_credit(vif); } @@ -1208,6 +1448,7 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) tx_credit_callback; mod_timer(&vif->credit_timeout, next_credit); + vif->credit_window_start = next_credit; return true; } @@ -1215,14 +1456,15 @@ static bool tx_credit_exceeded(struct xenvif *vif, unsigned size) return false; } -static unsigned xenvif_tx_build_gops(struct xenvif *vif) +static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget) { struct gnttab_copy *gop = vif->tx_copy_ops, *request_gop; struct sk_buff *skb; int ret; while ((nr_pending_reqs(vif) + XEN_NETBK_LEGACY_SLOTS_MAX - < MAX_PENDING_REQS)) { + < MAX_PENDING_REQS) && + (skb_queue_len(&vif->tx_queue) < budget)) { struct xen_netif_tx_request txreq; struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; struct page *page; @@ -1244,7 +1486,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif) continue; } - RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, work_to_do); + work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx); if (!work_to_do) break; @@ -1384,14 +1626,13 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif) } -static int xenvif_tx_submit(struct xenvif *vif, int budget) +static int xenvif_tx_submit(struct xenvif *vif) { struct gnttab_copy *gop = vif->tx_copy_ops; struct sk_buff *skb; int work_done = 0; - while (work_done < budget && - (skb = __skb_dequeue(&vif->tx_queue)) != NULL) { + while ((skb = __skb_dequeue(&vif->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; u16 pending_idx; unsigned data_len; @@ -1428,12 +1669,7 @@ static int xenvif_tx_submit(struct xenvif *vif, int budget) xenvif_fill_frags(vif, skb); - /* - * If the initial fragment was < PKT_PROT_LEN then - * pull through some bytes from the other fragments to - * increase the linear region to PKT_PROT_LEN bytes. - */ - if (skb_headlen(skb) < PKT_PROT_LEN && skb_is_nonlinear(skb)) { + if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) { int target = min_t(int, skb->len, PKT_PROT_LEN); __pskb_pull_tail(skb, target - skb_headlen(skb)); } @@ -1471,14 +1707,14 @@ int xenvif_tx_action(struct xenvif *vif, int budget) if (unlikely(!tx_work_todo(vif))) return 0; - nr_gops = xenvif_tx_build_gops(vif); + nr_gops = xenvif_tx_build_gops(vif, budget); if (nr_gops == 0) return 0; gnttab_batch_copy(vif->tx_copy_ops, nr_gops); - work_done = xenvif_tx_submit(vif, nr_gops); + work_done = xenvif_tx_submit(vif); return work_done; } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 1b08d879837..f0358992b04 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -105,6 +105,22 @@ static int netback_probe(struct xenbus_device *dev, goto abort_transaction; } + err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6", + "%d", sg); + if (err) { + message = "writing feature-gso-tcpv6"; + goto abort_transaction; + } + + /* We support partial checksum setup for IPv6 packets */ + err = xenbus_printf(xbt, dev->nodename, + "feature-ipv6-csum-offload", + "%d", 1); + if (err) { + message = "writing feature-ipv6-csum-offload"; + goto abort_transaction; + } + /* We support rx-copy path. */ err = xenbus_printf(xbt, dev->nodename, "feature-rx-copy", "%d", 1); @@ -561,20 +577,50 @@ static int connect_rings(struct backend_info *be) val = 0; vif->can_sg = !!val; + vif->gso_mask = 0; + vif->gso_prefix_mask = 0; + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4", "%d", &val) < 0) val = 0; - vif->gso = !!val; + if (val) + vif->gso_mask |= GSO_BIT(TCPV4); if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix", "%d", &val) < 0) val = 0; - vif->gso_prefix = !!val; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV4); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_mask |= GSO_BIT(TCPV6); + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV6); + + if (vif->gso_mask & vif->gso_prefix_mask) { + xenbus_dev_fatal(dev, err, + "%s: gso and gso prefix flags are not " + "mutually exclusive", + dev->otherend); + return -EOPNOTSUPP; + } if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", "%d", &val) < 0) val = 0; - vif->csum = !val; + vif->ip_csum = !val; + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload", + "%d", &val) < 0) + val = 0; + vif->ipv6_csum = !!val; /* Map the shared frame, irq etc. */ err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref, |