summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--MAINTAINERS3
-rw-r--r--drivers/net/Kconfig8
-rw-r--r--drivers/net/Makefile1
-rw-r--r--drivers/net/vsockmon.c170
-rw-r--r--drivers/vhost/vsock.c8
-rw-r--r--include/linux/virtio_vsock.h1
-rw-r--r--include/net/af_vsock.h13
-rw-r--r--include/uapi/linux/Kbuild1
-rw-r--r--include/uapi/linux/if_arp.h1
-rw-r--r--include/uapi/linux/vsockmon.h60
-rw-r--r--net/vmw_vsock/Makefile2
-rw-r--r--net/vmw_vsock/af_vsock_tap.c114
-rw-r--r--net/vmw_vsock/virtio_transport.c3
-rw-r--r--net/vmw_vsock/virtio_transport_common.c64
14 files changed, 448 insertions, 1 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index b283d5ef7b68..28ea78b12d0c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13317,8 +13317,11 @@ L: netdev@vger.kernel.org
S: Maintained
F: include/linux/virtio_vsock.h
F: include/uapi/linux/virtio_vsock.h
+F: include/uapi/linux/vsockmon.h
+F: net/vmw_vsock/af_vsock_tap.c
F: net/vmw_vsock/virtio_transport_common.c
F: net/vmw_vsock/virtio_transport.c
+F: drivers/net/vsockmon.c
F: drivers/vhost/vsock.c
F: drivers/vhost/vsock.h
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 100fbdc9b95c..83a1616903f8 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -355,6 +355,14 @@ 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 57fc47ad5ab3..b2f6556d8848 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -30,6 +30,7 @@ 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 000000000000..7f0136f2dd9d
--- /dev/null
+++ b/drivers/net/vsockmon.c
@@ -0,0 +1,170 @@
+#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);
+ if (!dev->lstats)
+ return -ENOMEM;
+ return 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 void
+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;
+}
+
+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/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 44eed8eb0725..d939ac1a4997 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -176,6 +176,11 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
restart_tx = true;
}
+ /* Deliver to monitoring devices all correctly transmitted
+ * packets.
+ */
+ virtio_transport_deliver_tap_pkt(pkt);
+
virtio_transport_free_pkt(pkt);
}
if (added)
@@ -383,6 +388,9 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
len = pkt->len;
+ /* Deliver to monitoring devices all received packets */
+ virtio_transport_deliver_tap_pkt(pkt);
+
/* Only accept correctly addressed packets */
if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
virtio_transport_recv_pkt(pkt);
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 584f9a647ad4..ab13f0743da8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -153,5 +153,6 @@ void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt);
void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt);
u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted);
void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
+void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt);
#endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f32ed9ac181a..f9fb566e75cf 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -188,4 +188,17 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
void vsock_remove_sock(struct vsock_sock *vsk);
void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
+/**** TAP ****/
+
+struct vsock_tap {
+ struct net_device *dev;
+ struct module *module;
+ struct list_head list;
+};
+
+int vsock_init_tap(void);
+int vsock_add_tap(struct vsock_tap *vt);
+int vsock_remove_tap(struct vsock_tap *vt);
+void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque);
+
#endif /* __AF_VSOCK_H__ */
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index f8d9fed17ba9..6b0e2758585f 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -477,6 +477,7 @@ header-y += virtio_types.h
header-y += virtio_vsock.h
header-y += virtio_crypto.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/if_arp.h b/include/uapi/linux/if_arp.h
index 4d024d75d64b..cf73510b9238 100644
--- a/include/uapi/linux/if_arp.h
+++ b/include/uapi/linux/if_arp.h
@@ -95,6 +95,7 @@
#define ARPHRD_IP6GRE 823 /* GRE over IPv6 */
#define ARPHRD_NETLINK 824 /* Netlink header */
#define ARPHRD_6LOWPAN 825 /* IPv6 over LoWPAN */
+#define ARPHRD_VSOCKMON 826 /* Vsock monitor header */
#define ARPHRD_VOID 0xFFFF /* Void type, nothing is known */
#define ARPHRD_NONE 0xFFFE /* zero header length */
diff --git a/include/uapi/linux/vsockmon.h b/include/uapi/linux/vsockmon.h
new file mode 100644
index 000000000000..a08b522ef597
--- /dev/null
+++ b/include/uapi/linux/vsockmon.h
@@ -0,0 +1,60 @@
+#ifndef _UAPI_VSOCKMON_H
+#define _UAPI_VSOCKMON_H
+
+#include <linux/virtio_vsock.h>
+
+/*
+ * vsockmon is the AF_VSOCK packet capture device. Packets captured have the
+ * following layout:
+ *
+ * +-----------------------------------+
+ * | vsockmon header |
+ * | (struct af_vsockmon_hdr) |
+ * +-----------------------------------+
+ * | transport header |
+ * | (af_vsockmon_hdr->len bytes long) |
+ * +-----------------------------------+
+ * | payload |
+ * | (until end of packet) |
+ * +-----------------------------------+
+ *
+ * The vsockmon header is a transport-independent description of the packet.
+ * It duplicates some of the information from the transport header so that
+ * no transport-specific knowledge is necessary to process packets.
+ *
+ * The transport header is useful for low-level transport-specific packet
+ * analysis. Transport type is given in af_vsockmon_hdr->transport and
+ * transport header length is given in af_vsockmon_hdr->len.
+ *
+ * If af_vsockmon_hdr->op is AF_VSOCK_OP_PAYLOAD then the payload follows the
+ * transport header. Other ops do not have a payload.
+ */
+
+struct af_vsockmon_hdr {
+ __le64 src_cid;
+ __le64 dst_cid;
+ __le32 src_port;
+ __le32 dst_port;
+ __le16 op; /* enum af_vsockmon_op */
+ __le16 transport; /* enum af_vsockmon_transport */
+ __le16 len; /* Transport header length */
+ __u8 reserved[2];
+};
+
+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_transport {
+ AF_VSOCK_TRANSPORT_UNKNOWN = 0,
+ AF_VSOCK_TRANSPORT_NO_INFO = 1, /* No transport information */
+
+ /* Transport header type: struct virtio_vsock_hdr */
+ AF_VSOCK_TRANSPORT_VIRTIO = 2,
+};
+
+#endif
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
index bc27c70e0e59..09fc2eb29dc8 100644
--- a/net/vmw_vsock/Makefile
+++ b/net/vmw_vsock/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o
obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o
obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o
-vsock-y += af_vsock.o vsock_addr.o
+vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o
vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \
vmci_transport_notify_qstate.o
diff --git a/net/vmw_vsock/af_vsock_tap.c b/net/vmw_vsock/af_vsock_tap.c
new file mode 100644
index 000000000000..98f09b539366
--- /dev/null
+++ b/net/vmw_vsock/af_vsock_tap.c
@@ -0,0 +1,114 @@
+/*
+ * Tap functions for AF_VSOCK sockets.
+ *
+ * Code based on net/netlink/af_netlink.c tap functions.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <net/sock.h>
+#include <net/af_vsock.h>
+#include <linux/if_arp.h>
+
+static DEFINE_SPINLOCK(vsock_tap_lock);
+static struct list_head vsock_tap_all __read_mostly =
+ LIST_HEAD_INIT(vsock_tap_all);
+
+int vsock_add_tap(struct vsock_tap *vt)
+{
+ if (unlikely(vt->dev->type != ARPHRD_VSOCKMON))
+ return -EINVAL;
+
+ __module_get(vt->module);
+
+ spin_lock(&vsock_tap_lock);
+ list_add_rcu(&vt->list, &vsock_tap_all);
+ spin_unlock(&vsock_tap_lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vsock_add_tap);
+
+int vsock_remove_tap(struct vsock_tap *vt)
+{
+ struct vsock_tap *tmp;
+ bool found = false;
+
+ spin_lock(&vsock_tap_lock);
+
+ list_for_each_entry(tmp, &vsock_tap_all, list) {
+ if (vt == tmp) {
+ list_del_rcu(&vt->list);
+ found = true;
+ goto out;
+ }
+ }
+
+ pr_warn("vsock_remove_tap: %p not found\n", vt);
+out:
+ spin_unlock(&vsock_tap_lock);
+
+ synchronize_net();
+
+ if (found)
+ module_put(vt->module);
+
+ return found ? 0 : -ENODEV;
+}
+EXPORT_SYMBOL_GPL(vsock_remove_tap);
+
+static int __vsock_deliver_tap_skb(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ int ret = 0;
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (nskb) {
+ dev_hold(dev);
+
+ nskb->dev = dev;
+ ret = dev_queue_xmit(nskb);
+ if (unlikely(ret > 0))
+ ret = net_xmit_errno(ret);
+
+ dev_put(dev);
+ }
+
+ return ret;
+}
+
+static void __vsock_deliver_tap(struct sk_buff *skb)
+{
+ int ret;
+ struct vsock_tap *tmp;
+
+ list_for_each_entry_rcu(tmp, &vsock_tap_all, list) {
+ ret = __vsock_deliver_tap_skb(skb, tmp->dev);
+ if (unlikely(ret))
+ break;
+ }
+}
+
+void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque)
+{
+ struct sk_buff *skb;
+
+ rcu_read_lock();
+
+ if (likely(list_empty(&vsock_tap_all)))
+ goto out;
+
+ skb = build_skb(opaque);
+ if (skb) {
+ __vsock_deliver_tap(skb);
+ consume_skb(skb);
+ }
+
+out:
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(vsock_deliver_tap);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 68675a151f22..9dffe0282ad4 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -144,6 +144,8 @@ virtio_transport_send_pkt_work(struct work_struct *work)
list_del_init(&pkt->list);
spin_unlock_bh(&vsock->send_pkt_list_lock);
+ virtio_transport_deliver_tap_pkt(pkt);
+
reply = pkt->reply;
sg_init_one(&hdr, &pkt->hdr, sizeof(pkt->hdr));
@@ -370,6 +372,7 @@ static void virtio_transport_rx_work(struct work_struct *work)
}
pkt->len = len - sizeof(pkt->hdr);
+ virtio_transport_deliver_tap_pkt(pkt);
virtio_transport_recv_pkt(pkt);
}
} while (!virtqueue_enable_cb(vq));
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index af087b44ceea..18e24793659f 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -16,6 +16,7 @@
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
#include <linux/virtio_vsock.h>
+#include <uapi/linux/vsockmon.h>
#include <net/sock.h>
#include <net/af_vsock.h>
@@ -85,6 +86,69 @@ out_pkt:
return NULL;
}
+/* Packet capture */
+static struct sk_buff *virtio_transport_build_skb(void *opaque)
+{
+ struct virtio_vsock_pkt *pkt = opaque;
+ unsigned char *t_hdr, *payload;
+ struct af_vsockmon_hdr *hdr;
+ struct sk_buff *skb;
+
+ skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len,
+ GFP_ATOMIC);
+ if (!skb)
+ return NULL;
+
+ hdr = (struct af_vsockmon_hdr *)skb_put(skb, sizeof(*hdr));
+
+ /* pkt->hdr is little-endian so no need to byteswap here */
+ hdr->src_cid = pkt->hdr.src_cid;
+ hdr->src_port = pkt->hdr.src_port;
+ hdr->dst_cid = pkt->hdr.dst_cid;
+ hdr->dst_port = pkt->hdr.dst_port;
+
+ hdr->transport = cpu_to_le16(AF_VSOCK_TRANSPORT_VIRTIO);
+ hdr->len = cpu_to_le16(sizeof(pkt->hdr));
+ memset(hdr->reserved, 0, sizeof(hdr->reserved));
+
+ switch (le16_to_cpu(pkt->hdr.op)) {
+ case VIRTIO_VSOCK_OP_REQUEST:
+ case VIRTIO_VSOCK_OP_RESPONSE:
+ hdr->op = cpu_to_le16(AF_VSOCK_OP_CONNECT);
+ break;
+ case VIRTIO_VSOCK_OP_RST:
+ case VIRTIO_VSOCK_OP_SHUTDOWN:
+ hdr->op = cpu_to_le16(AF_VSOCK_OP_DISCONNECT);
+ break;
+ case VIRTIO_VSOCK_OP_RW:
+ hdr->op = cpu_to_le16(AF_VSOCK_OP_PAYLOAD);
+ break;
+ case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
+ case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
+ hdr->op = cpu_to_le16(AF_VSOCK_OP_CONTROL);
+ break;
+ default:
+ hdr->op = cpu_to_le16(AF_VSOCK_OP_UNKNOWN);
+ break;
+ }
+
+ t_hdr = skb_put(skb, sizeof(pkt->hdr));
+ memcpy(t_hdr, &pkt->hdr, sizeof(pkt->hdr));
+
+ if (pkt->len) {
+ payload = skb_put(skb, pkt->len);
+ memcpy(payload, pkt->buf, pkt->len);
+ }
+
+ return skb;
+}
+
+void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
+{
+ vsock_deliver_tap(virtio_transport_build_skb, pkt);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
+
static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
struct virtio_vsock_pkt_info *info)
{
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-16 13:54:06 +0000