Message ID | 20160813102154.14338-3-ggarcia@deic.uab.cat |
---|---|
State | Changes Requested, archived |
Delegated to: | David Miller |
Headers | show |
+#define DEFAULT_MTU (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + sizeof(struct af_vsockmon_hdr)); It is better. On Sat, Aug 13, 2016 at 6:21 PM, <ggarcia@abra.uab.cat> wrote: > From: Gerard Garcia <ggarcia@deic.uab.cat> > > Add vsockmon virtual network device that receives packets from the vsock > transports and exposes them to user space. > > Based on the nlmon device. > > Signed-off-by: Gerard Garcia <ggarcia@deic.uab.cat> > --- > drivers/net/Kconfig | 8 ++ > drivers/net/Makefile | 1 + > drivers/net/vsockmon.c | 168 ++++++++++++++++++++++++++++++++++++++++++ > include/uapi/linux/Kbuild | 1 + > include/uapi/linux/vsockmon.h | 38 ++++++++++ > 5 files changed, 216 insertions(+) > create mode 100644 drivers/net/vsockmon.c > create mode 100644 include/uapi/linux/vsockmon.h > > diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig > index 0c5415b..42c43b6 100644 > --- a/drivers/net/Kconfig > +++ b/drivers/net/Kconfig > @@ -330,6 +330,14 @@ config NET_VRF > This option enables the support for mapping interfaces into VRF's. The > support enables VRF devices. > > +config VSOCKMON > + tristate "Virtual vsock monitoring device" > + depends on VHOST_VSOCK > + ---help--- > + This option enables a monitoring net device for vsock sockets. It is > + mostly intended for developers or support to debug vsock issues. If > + unsure, say N. > + > endif # NET_CORE > > config SUNGEM_PHY > diff --git a/drivers/net/Makefile b/drivers/net/Makefile > index 7336cbd..e2188d4 100644 > --- a/drivers/net/Makefile > +++ b/drivers/net/Makefile > @@ -28,6 +28,7 @@ obj-$(CONFIG_GENEVE) += geneve.o > obj-$(CONFIG_GTP) += gtp.o > obj-$(CONFIG_NLMON) += nlmon.o > obj-$(CONFIG_NET_VRF) += vrf.o > +obj-$(CONFIG_VSOCKMON) += vsockmon.o > > # > # Networking Drivers > diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c > new file mode 100644 > index 0000000..9ad4f0a > --- /dev/null > +++ b/drivers/net/vsockmon.c > @@ -0,0 +1,168 @@ > +#include <linux/module.h> > +#include <linux/kernel.h> > +#include <linux/if_arp.h> > +#include <net/rtnetlink.h> > +#include <net/sock.h> > +#include <net/af_vsock.h> > +#include <uapi/linux/vsockmon.h> > +#include <linux/virtio_vsock.h> > + > +/* Virtio transport max packet size plus header */ > +#define DEFAULT_MTU VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + sizeof(struct af_vsockmon_hdr); > + > +struct pcpu_lstats { > + u64 rx_packets; > + u64 rx_bytes; > + struct u64_stats_sync syncp; > +}; > + > +static int vsockmon_dev_init(struct net_device *dev) > +{ > + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); > + return dev->lstats == NULL ? -ENOMEM : 0; > +} > + > +static void vsockmon_dev_uninit(struct net_device *dev) > +{ > + free_percpu(dev->lstats); > +} > + > +struct vsockmon { > + struct vsock_tap vt; > +}; > + > +static int vsockmon_open(struct net_device *dev) > +{ > + struct vsockmon *vsockmon = netdev_priv(dev); > + > + vsockmon->vt.dev = dev; > + vsockmon->vt.module = THIS_MODULE; > + return vsock_add_tap(&vsockmon->vt); > +} > + > +static int vsockmon_close(struct net_device *dev) { > + struct vsockmon *vsockmon = netdev_priv(dev); > + > + return vsock_remove_tap(&vsockmon->vt); > +} > + > +static netdev_tx_t vsockmon_xmit(struct sk_buff *skb, struct net_device *dev) > +{ > + int len = skb->len; > + struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); > + > + u64_stats_update_begin(&stats->syncp); > + stats->rx_bytes += len; > + stats->rx_packets++; > + u64_stats_update_end(&stats->syncp); > + > + dev_kfree_skb(skb); > + > + return NETDEV_TX_OK; > +} > + > +static struct rtnl_link_stats64 * > +vsockmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) > +{ > + int i; > + u64 bytes = 0, packets = 0; > + > + for_each_possible_cpu(i) { > + const struct pcpu_lstats *vstats; > + u64 tbytes, tpackets; > + unsigned int start; > + > + vstats = per_cpu_ptr(dev->lstats, i); > + > + do { > + start = u64_stats_fetch_begin_irq(&vstats->syncp); > + tbytes = vstats->rx_bytes; > + tpackets = vstats->rx_packets; > + } while (u64_stats_fetch_retry_irq(&vstats->syncp, start)); > + > + packets += tpackets; > + bytes += tbytes; > + } > + > + stats->rx_packets = packets; > + stats->tx_packets = 0; > + > + stats->rx_bytes = bytes; > + stats->tx_bytes = 0; > + > + return stats; > +} > + > +static int vsockmon_is_valid_mtu(int new_mtu) > +{ > + return new_mtu >= (int) sizeof(struct af_vsockmon_hdr); > +} > + > +static int vsockmon_change_mtu(struct net_device *dev, int new_mtu) > +{ > + if (!vsockmon_is_valid_mtu(new_mtu)) > + return -EINVAL; > + > + dev->mtu = new_mtu; > + return 0; > +} > + > +static const struct net_device_ops vsockmon_ops = { > + .ndo_init = vsockmon_dev_init, > + .ndo_uninit = vsockmon_dev_uninit, > + .ndo_open = vsockmon_open, > + .ndo_stop = vsockmon_close, > + .ndo_start_xmit = vsockmon_xmit, > + .ndo_get_stats64 = vsockmon_get_stats64, > + .ndo_change_mtu = vsockmon_change_mtu, > +}; > + > +static u32 always_on(struct net_device *dev) > +{ > + return 1; > +} > + > +static const struct ethtool_ops vsockmon_ethtool_ops = { > + .get_link = always_on, > +}; > + > +static void vsockmon_setup(struct net_device *dev) > +{ > + dev->type = ARPHRD_VSOCKMON; > + dev->priv_flags |= IFF_NO_QUEUE; > + > + dev->netdev_ops = &vsockmon_ops; > + dev->ethtool_ops = &vsockmon_ethtool_ops; > + dev->destructor = free_netdev; > + > + dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | > + NETIF_F_HIGHDMA | NETIF_F_LLTX; > + > + dev->flags = IFF_NOARP; > + > + dev->mtu = DEFAULT_MTU; > +} > + > +static struct rtnl_link_ops vsockmon_link_ops __read_mostly = { > + .kind = "vsockmon", > + .priv_size = sizeof(struct vsockmon), > + .setup = vsockmon_setup, > +}; > + > +static __init int vsockmon_register(void) > +{ > + return rtnl_link_register(&vsockmon_link_ops); > +} > + > +static __exit void vsockmon_unregister(void) > +{ > + rtnl_link_unregister(&vsockmon_link_ops); > +} > + > +module_init(vsockmon_register); > +module_exit(vsockmon_unregister); > + > +MODULE_LICENSE("GPL v2"); > +MODULE_AUTHOR("Gerard Garcia <ggarcia@deic.uab.cat>"); > +MODULE_DESCRIPTION("Vsock monitoring device. Based on nlmon device."); > +MODULE_ALIAS_RTNL_LINK("vsockmon"); > diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild > index 185f8ea..ef7f878 100644 > --- a/include/uapi/linux/Kbuild > +++ b/include/uapi/linux/Kbuild > @@ -456,6 +456,7 @@ header-y += virtio_scsi.h > header-y += virtio_types.h > header-y += virtio_vsock.h > header-y += vm_sockets.h > +header-y += vsockmon.h > header-y += vt.h > header-y += vtpm_proxy.h > header-y += wait.h > diff --git a/include/uapi/linux/vsockmon.h b/include/uapi/linux/vsockmon.h > new file mode 100644 > index 0000000..0e9c54e > --- /dev/null > +++ b/include/uapi/linux/vsockmon.h > @@ -0,0 +1,38 @@ > +#ifndef _UAPI_VSOCKMON_H > +#define _UAPI_VSOCKMON_H > + > +#include <linux/virtio_vsock.h> > + > +/* > + * Structure of packets received through the vsockmon device. > + * > + * Note that after the vsockmon header comes the transport header (len bytes and > + * type specified by t) and if the packet op is AF_VSOCK_OP_PAYLOAD then comes > + * the payload. > + */ > + > +struct af_vsockmon_hdr { > + __le64 src_cid; > + __le64 dst_cid; > + __le32 src_port; > + __le32 dst_port; > + __le16 op; /* enum af_vsockmon_op */ > + __le16 t; /* enum af_vosckmon_t */ > + __le16 len; /* Transport header length */ > +} __attribute__((packed)); > + > +enum af_vsockmon_op { > + AF_VSOCK_OP_UNKNOWN = 0, > + AF_VSOCK_OP_CONNECT = 1, > + AF_VSOCK_OP_DISCONNECT = 2, > + AF_VSOCK_OP_CONTROL = 3, > + AF_VSOCK_OP_PAYLOAD = 4, > +}; > + > +enum af_vsockmon_t { > + AF_VSOCK_T_UNKNOWN = 0, > + AF_VSOCK_T_NO_INFO = 1, /* No transport information */ > + AF_VSOCK_T_VIRTIO = 2, /* Virtio transport header (struct virtio_vsock_hdr) */ > +}; > + > +#endif > -- > 2.9.1 >
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 0c5415b..42c43b6 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -330,6 +330,14 @@ config NET_VRF This option enables the support for mapping interfaces into VRF's. The support enables VRF devices. +config VSOCKMON + tristate "Virtual vsock monitoring device" + depends on VHOST_VSOCK + ---help--- + This option enables a monitoring net device for vsock sockets. It is + mostly intended for developers or support to debug vsock issues. If + unsure, say N. + endif # NET_CORE config SUNGEM_PHY diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 7336cbd..e2188d4 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_GENEVE) += geneve.o obj-$(CONFIG_GTP) += gtp.o obj-$(CONFIG_NLMON) += nlmon.o obj-$(CONFIG_NET_VRF) += vrf.o +obj-$(CONFIG_VSOCKMON) += vsockmon.o # # Networking Drivers diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c new file mode 100644 index 0000000..9ad4f0a --- /dev/null +++ b/drivers/net/vsockmon.c @@ -0,0 +1,168 @@ +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/if_arp.h> +#include <net/rtnetlink.h> +#include <net/sock.h> +#include <net/af_vsock.h> +#include <uapi/linux/vsockmon.h> +#include <linux/virtio_vsock.h> + +/* Virtio transport max packet size plus header */ +#define DEFAULT_MTU VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + sizeof(struct af_vsockmon_hdr); + +struct pcpu_lstats { + u64 rx_packets; + u64 rx_bytes; + struct u64_stats_sync syncp; +}; + +static int vsockmon_dev_init(struct net_device *dev) +{ + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + return dev->lstats == NULL ? -ENOMEM : 0; +} + +static void vsockmon_dev_uninit(struct net_device *dev) +{ + free_percpu(dev->lstats); +} + +struct vsockmon { + struct vsock_tap vt; +}; + +static int vsockmon_open(struct net_device *dev) +{ + struct vsockmon *vsockmon = netdev_priv(dev); + + vsockmon->vt.dev = dev; + vsockmon->vt.module = THIS_MODULE; + return vsock_add_tap(&vsockmon->vt); +} + +static int vsockmon_close(struct net_device *dev) { + struct vsockmon *vsockmon = netdev_priv(dev); + + return vsock_remove_tap(&vsockmon->vt); +} + +static netdev_tx_t vsockmon_xmit(struct sk_buff *skb, struct net_device *dev) +{ + int len = skb->len; + struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); + + u64_stats_update_begin(&stats->syncp); + stats->rx_bytes += len; + stats->rx_packets++; + u64_stats_update_end(&stats->syncp); + + dev_kfree_skb(skb); + + return NETDEV_TX_OK; +} + +static struct rtnl_link_stats64 * +vsockmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + int i; + u64 bytes = 0, packets = 0; + + for_each_possible_cpu(i) { + const struct pcpu_lstats *vstats; + u64 tbytes, tpackets; + unsigned int start; + + vstats = per_cpu_ptr(dev->lstats, i); + + do { + start = u64_stats_fetch_begin_irq(&vstats->syncp); + tbytes = vstats->rx_bytes; + tpackets = vstats->rx_packets; + } while (u64_stats_fetch_retry_irq(&vstats->syncp, start)); + + packets += tpackets; + bytes += tbytes; + } + + stats->rx_packets = packets; + stats->tx_packets = 0; + + stats->rx_bytes = bytes; + stats->tx_bytes = 0; + + return stats; +} + +static int vsockmon_is_valid_mtu(int new_mtu) +{ + return new_mtu >= (int) sizeof(struct af_vsockmon_hdr); +} + +static int vsockmon_change_mtu(struct net_device *dev, int new_mtu) +{ + if (!vsockmon_is_valid_mtu(new_mtu)) + return -EINVAL; + + dev->mtu = new_mtu; + return 0; +} + +static const struct net_device_ops vsockmon_ops = { + .ndo_init = vsockmon_dev_init, + .ndo_uninit = vsockmon_dev_uninit, + .ndo_open = vsockmon_open, + .ndo_stop = vsockmon_close, + .ndo_start_xmit = vsockmon_xmit, + .ndo_get_stats64 = vsockmon_get_stats64, + .ndo_change_mtu = vsockmon_change_mtu, +}; + +static u32 always_on(struct net_device *dev) +{ + return 1; +} + +static const struct ethtool_ops vsockmon_ethtool_ops = { + .get_link = always_on, +}; + +static void vsockmon_setup(struct net_device *dev) +{ + dev->type = ARPHRD_VSOCKMON; + dev->priv_flags |= IFF_NO_QUEUE; + + dev->netdev_ops = &vsockmon_ops; + dev->ethtool_ops = &vsockmon_ethtool_ops; + dev->destructor = free_netdev; + + dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | + NETIF_F_HIGHDMA | NETIF_F_LLTX; + + dev->flags = IFF_NOARP; + + dev->mtu = DEFAULT_MTU; +} + +static struct rtnl_link_ops vsockmon_link_ops __read_mostly = { + .kind = "vsockmon", + .priv_size = sizeof(struct vsockmon), + .setup = vsockmon_setup, +}; + +static __init int vsockmon_register(void) +{ + return rtnl_link_register(&vsockmon_link_ops); +} + +static __exit void vsockmon_unregister(void) +{ + rtnl_link_unregister(&vsockmon_link_ops); +} + +module_init(vsockmon_register); +module_exit(vsockmon_unregister); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Gerard Garcia <ggarcia@deic.uab.cat>"); +MODULE_DESCRIPTION("Vsock monitoring device. Based on nlmon device."); +MODULE_ALIAS_RTNL_LINK("vsockmon"); diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index 185f8ea..ef7f878 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -456,6 +456,7 @@ header-y += virtio_scsi.h header-y += virtio_types.h header-y += virtio_vsock.h header-y += vm_sockets.h +header-y += vsockmon.h header-y += vt.h header-y += vtpm_proxy.h header-y += wait.h diff --git a/include/uapi/linux/vsockmon.h b/include/uapi/linux/vsockmon.h new file mode 100644 index 0000000..0e9c54e --- /dev/null +++ b/include/uapi/linux/vsockmon.h @@ -0,0 +1,38 @@ +#ifndef _UAPI_VSOCKMON_H +#define _UAPI_VSOCKMON_H + +#include <linux/virtio_vsock.h> + +/* + * Structure of packets received through the vsockmon device. + * + * Note that after the vsockmon header comes the transport header (len bytes and + * type specified by t) and if the packet op is AF_VSOCK_OP_PAYLOAD then comes + * the payload. + */ + +struct af_vsockmon_hdr { + __le64 src_cid; + __le64 dst_cid; + __le32 src_port; + __le32 dst_port; + __le16 op; /* enum af_vsockmon_op */ + __le16 t; /* enum af_vosckmon_t */ + __le16 len; /* Transport header length */ +} __attribute__((packed)); + +enum af_vsockmon_op { + AF_VSOCK_OP_UNKNOWN = 0, + AF_VSOCK_OP_CONNECT = 1, + AF_VSOCK_OP_DISCONNECT = 2, + AF_VSOCK_OP_CONTROL = 3, + AF_VSOCK_OP_PAYLOAD = 4, +}; + +enum af_vsockmon_t { + AF_VSOCK_T_UNKNOWN = 0, + AF_VSOCK_T_NO_INFO = 1, /* No transport information */ + AF_VSOCK_T_VIRTIO = 2, /* Virtio transport header (struct virtio_vsock_hdr) */ +}; + +#endif