linux/net/vmw_vsock/virtio_transport.c

806 lines
19 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* virtio transport for vsock
*
* Copyright (C) 2013-2015 Red Hat, Inc.
* Author: Asias He <asias@redhat.com>
* Stefan Hajnoczi <stefanha@redhat.com>
*
* Some of the code is take from Gerd Hoffmann <kraxel@redhat.com>'s
* early virtio-vsock proof-of-concept bits.
*/
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/atomic.h>
#include <linux/virtio.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
#include <linux/virtio_vsock.h>
#include <net/sock.h>
#include <linux/mutex.h>
#include <net/af_vsock.h>
static struct workqueue_struct *virtio_vsock_workqueue;
vsock/virtio: annotate 'the_virtio_vsock' RCU pointer Commit 0deab087b16a ("vsock/virtio: use RCU to avoid use-after-free on the_virtio_vsock") starts to use RCU to protect 'the_virtio_vsock' pointer, but we forgot to annotate it. This patch adds the annotation to fix the following sparse errors: net/vmw_vsock/virtio_transport.c:73:17: error: incompatible types in comparison expression (different address spaces): net/vmw_vsock/virtio_transport.c:73:17: struct virtio_vsock [noderef] __rcu * net/vmw_vsock/virtio_transport.c:73:17: struct virtio_vsock * net/vmw_vsock/virtio_transport.c:171:17: error: incompatible types in comparison expression (different address spaces): net/vmw_vsock/virtio_transport.c:171:17: struct virtio_vsock [noderef] __rcu * net/vmw_vsock/virtio_transport.c:171:17: struct virtio_vsock * net/vmw_vsock/virtio_transport.c:207:17: error: incompatible types in comparison expression (different address spaces): net/vmw_vsock/virtio_transport.c:207:17: struct virtio_vsock [noderef] __rcu * net/vmw_vsock/virtio_transport.c:207:17: struct virtio_vsock * net/vmw_vsock/virtio_transport.c:561:13: error: incompatible types in comparison expression (different address spaces): net/vmw_vsock/virtio_transport.c:561:13: struct virtio_vsock [noderef] __rcu * net/vmw_vsock/virtio_transport.c:561:13: struct virtio_vsock * net/vmw_vsock/virtio_transport.c:612:9: error: incompatible types in comparison expression (different address spaces): net/vmw_vsock/virtio_transport.c:612:9: struct virtio_vsock [noderef] __rcu * net/vmw_vsock/virtio_transport.c:612:9: struct virtio_vsock * net/vmw_vsock/virtio_transport.c:631:9: error: incompatible types in comparison expression (different address spaces): net/vmw_vsock/virtio_transport.c:631:9: struct virtio_vsock [noderef] __rcu * net/vmw_vsock/virtio_transport.c:631:9: struct virtio_vsock * Fixes: 0deab087b16a ("vsock/virtio: use RCU to avoid use-after-free on the_virtio_vsock") Reported-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-07-10 15:12:43 +03:00
static struct virtio_vsock __rcu *the_virtio_vsock;
static DEFINE_MUTEX(the_virtio_vsock_mutex); /* protects the_virtio_vsock */
static struct virtio_transport virtio_transport; /* forward declaration */
struct virtio_vsock {
struct virtio_device *vdev;
struct virtqueue *vqs[VSOCK_VQ_MAX];
/* Virtqueue processing is deferred to a workqueue */
struct work_struct tx_work;
struct work_struct rx_work;
struct work_struct event_work;
/* The following fields are protected by tx_lock. vqs[VSOCK_VQ_TX]
* must be accessed with tx_lock held.
*/
struct mutex tx_lock;
bool tx_run;
struct work_struct send_pkt_work;
struct sk_buff_head send_pkt_queue;
atomic_t queued_replies;
/* The following fields are protected by rx_lock. vqs[VSOCK_VQ_RX]
* must be accessed with rx_lock held.
*/
struct mutex rx_lock;
bool rx_run;
int rx_buf_nr;
int rx_buf_max_nr;
/* The following fields are protected by event_lock.
* vqs[VSOCK_VQ_EVENT] must be accessed with event_lock held.
*/
struct mutex event_lock;
bool event_run;
struct virtio_vsock_event event_list[8];
u32 guest_cid;
bool seqpacket_allow;
};
static u32 virtio_transport_get_local_cid(void)
{
struct virtio_vsock *vsock;
u32 ret;
rcu_read_lock();
vsock = rcu_dereference(the_virtio_vsock);
if (!vsock) {
ret = VMADDR_CID_ANY;
goto out_rcu;
}
ret = vsock->guest_cid;
out_rcu:
rcu_read_unlock();
return ret;
}
static void
virtio_transport_send_pkt_work(struct work_struct *work)
{
struct virtio_vsock *vsock =
container_of(work, struct virtio_vsock, send_pkt_work);
struct virtqueue *vq;
bool added = false;
bool restart_rx = false;
mutex_lock(&vsock->tx_lock);
if (!vsock->tx_run)
goto out;
vq = vsock->vqs[VSOCK_VQ_TX];
for (;;) {
struct scatterlist hdr, buf, *sgs[2];
int ret, in_sg = 0, out_sg = 0;
struct sk_buff *skb;
bool reply;
skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue);
if (!skb)
break;
virtio_transport_deliver_tap_pkt(skb);
reply = virtio_vsock_skb_reply(skb);
sg_init_one(&hdr, virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb)));
sgs[out_sg++] = &hdr;
if (skb->len > 0) {
sg_init_one(&buf, skb->data, skb->len);
sgs[out_sg++] = &buf;
}
ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL);
/* Usually this means that there is no more space available in
* the vq
*/
if (ret < 0) {
virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
break;
}
if (reply) {
struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
int val;
val = atomic_dec_return(&vsock->queued_replies);
/* Do we now have resources to resume rx processing? */
if (val + 1 == virtqueue_get_vring_size(rx_vq))
restart_rx = true;
}
added = true;
}
if (added)
virtqueue_kick(vq);
out:
mutex_unlock(&vsock->tx_lock);
if (restart_rx)
queue_work(virtio_vsock_workqueue, &vsock->rx_work);
}
static int
virtio_transport_send_pkt(struct sk_buff *skb)
{
struct virtio_vsock_hdr *hdr;
struct virtio_vsock *vsock;
int len = skb->len;
hdr = virtio_vsock_hdr(skb);
rcu_read_lock();
vsock = rcu_dereference(the_virtio_vsock);
if (!vsock) {
kfree_skb(skb);
len = -ENODEV;
goto out_rcu;
}
if (le64_to_cpu(hdr->dst_cid) == vsock->guest_cid) {
kfree_skb(skb);
len = -ENODEV;
goto out_rcu;
}
if (virtio_vsock_skb_reply(skb))
atomic_inc(&vsock->queued_replies);
virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb);
queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
out_rcu:
rcu_read_unlock();
return len;
}
static int
virtio_transport_cancel_pkt(struct vsock_sock *vsk)
{
struct virtio_vsock *vsock;
int cnt = 0, ret;
rcu_read_lock();
vsock = rcu_dereference(the_virtio_vsock);
if (!vsock) {
ret = -ENODEV;
goto out_rcu;
}
cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue);
if (cnt) {
struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX];
int new_cnt;
new_cnt = atomic_sub_return(cnt, &vsock->queued_replies);
if (new_cnt + cnt >= virtqueue_get_vring_size(rx_vq) &&
new_cnt < virtqueue_get_vring_size(rx_vq))
queue_work(virtio_vsock_workqueue, &vsock->rx_work);
}
ret = 0;
out_rcu:
rcu_read_unlock();
return ret;
}
static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
{
int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM;
struct scatterlist pkt, *p;
struct virtqueue *vq;
struct sk_buff *skb;
int ret;
vq = vsock->vqs[VSOCK_VQ_RX];
do {
skb = virtio_vsock_alloc_skb(total_len, GFP_KERNEL);
if (!skb)
break;
memset(skb->head, 0, VIRTIO_VSOCK_SKB_HEADROOM);
sg_init_one(&pkt, virtio_vsock_hdr(skb), total_len);
p = &pkt;
ret = virtqueue_add_sgs(vq, &p, 0, 1, skb, GFP_KERNEL);
if (ret < 0) {
kfree_skb(skb);
break;
}
vsock->rx_buf_nr++;
} while (vq->num_free);
if (vsock->rx_buf_nr > vsock->rx_buf_max_nr)
vsock->rx_buf_max_nr = vsock->rx_buf_nr;
virtqueue_kick(vq);
}
static void virtio_transport_tx_work(struct work_struct *work)
{
struct virtio_vsock *vsock =
container_of(work, struct virtio_vsock, tx_work);
struct virtqueue *vq;
bool added = false;
vq = vsock->vqs[VSOCK_VQ_TX];
mutex_lock(&vsock->tx_lock);
if (!vsock->tx_run)
goto out;
do {
struct sk_buff *skb;
unsigned int len;
virtqueue_disable_cb(vq);
while ((skb = virtqueue_get_buf(vq, &len)) != NULL) {
consume_skb(skb);
added = true;
}
} while (!virtqueue_enable_cb(vq));
out:
mutex_unlock(&vsock->tx_lock);
if (added)
queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work);
}
/* Is there space left for replies to rx packets? */
static bool virtio_transport_more_replies(struct virtio_vsock *vsock)
{
struct virtqueue *vq = vsock->vqs[VSOCK_VQ_RX];
int val;
smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */
val = atomic_read(&vsock->queued_replies);
return val < virtqueue_get_vring_size(vq);
}
/* event_lock must be held */
static int virtio_vsock_event_fill_one(struct virtio_vsock *vsock,
struct virtio_vsock_event *event)
{
struct scatterlist sg;
struct virtqueue *vq;
vq = vsock->vqs[VSOCK_VQ_EVENT];
sg_init_one(&sg, event, sizeof(*event));
return virtqueue_add_inbuf(vq, &sg, 1, event, GFP_KERNEL);
}
/* event_lock must be held */
static void virtio_vsock_event_fill(struct virtio_vsock *vsock)
{
size_t i;
for (i = 0; i < ARRAY_SIZE(vsock->event_list); i++) {
struct virtio_vsock_event *event = &vsock->event_list[i];
virtio_vsock_event_fill_one(vsock, event);
}
virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);
}
static void virtio_vsock_reset_sock(struct sock *sk)
{
/* vmci_transport.c doesn't take sk_lock here either. At least we're
* under vsock_table_lock so the sock cannot disappear while we're
* executing.
*/
sk->sk_state = TCP_CLOSE;
sk->sk_err = ECONNRESET;
sk_error_report(sk);
}
static void virtio_vsock_update_guest_cid(struct virtio_vsock *vsock)
{
struct virtio_device *vdev = vsock->vdev;
__le64 guest_cid;
vdev->config->get(vdev, offsetof(struct virtio_vsock_config, guest_cid),
&guest_cid, sizeof(guest_cid));
vsock->guest_cid = le64_to_cpu(guest_cid);
}
/* event_lock must be held */
static void virtio_vsock_event_handle(struct virtio_vsock *vsock,
struct virtio_vsock_event *event)
{
switch (le32_to_cpu(event->id)) {
case VIRTIO_VSOCK_EVENT_TRANSPORT_RESET:
virtio_vsock_update_guest_cid(vsock);
vsock_for_each_connected_socket(&virtio_transport.transport,
virtio_vsock_reset_sock);
break;
}
}
static void virtio_transport_event_work(struct work_struct *work)
{
struct virtio_vsock *vsock =
container_of(work, struct virtio_vsock, event_work);
struct virtqueue *vq;
vq = vsock->vqs[VSOCK_VQ_EVENT];
mutex_lock(&vsock->event_lock);
if (!vsock->event_run)
goto out;
do {
struct virtio_vsock_event *event;
unsigned int len;
virtqueue_disable_cb(vq);
while ((event = virtqueue_get_buf(vq, &len)) != NULL) {
if (len == sizeof(*event))
virtio_vsock_event_handle(vsock, event);
virtio_vsock_event_fill_one(vsock, event);
}
} while (!virtqueue_enable_cb(vq));
virtqueue_kick(vsock->vqs[VSOCK_VQ_EVENT]);
out:
mutex_unlock(&vsock->event_lock);
}
static void virtio_vsock_event_done(struct virtqueue *vq)
{
struct virtio_vsock *vsock = vq->vdev->priv;
if (!vsock)
return;
queue_work(virtio_vsock_workqueue, &vsock->event_work);
}
static void virtio_vsock_tx_done(struct virtqueue *vq)
{
struct virtio_vsock *vsock = vq->vdev->priv;
if (!vsock)
return;
queue_work(virtio_vsock_workqueue, &vsock->tx_work);
}
static void virtio_vsock_rx_done(struct virtqueue *vq)
{
struct virtio_vsock *vsock = vq->vdev->priv;
if (!vsock)
return;
queue_work(virtio_vsock_workqueue, &vsock->rx_work);
}
static bool virtio_transport_seqpacket_allow(u32 remote_cid);
static struct virtio_transport virtio_transport = {
.transport = {
.module = THIS_MODULE,
.get_local_cid = virtio_transport_get_local_cid,
.init = virtio_transport_do_socket_init,
.destruct = virtio_transport_destruct,
.release = virtio_transport_release,
.connect = virtio_transport_connect,
.shutdown = virtio_transport_shutdown,
.cancel_pkt = virtio_transport_cancel_pkt,
.dgram_bind = virtio_transport_dgram_bind,
.dgram_dequeue = virtio_transport_dgram_dequeue,
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_allow = virtio_transport_dgram_allow,
.stream_dequeue = virtio_transport_stream_dequeue,
.stream_enqueue = virtio_transport_stream_enqueue,
.stream_has_data = virtio_transport_stream_has_data,
.stream_has_space = virtio_transport_stream_has_space,
.stream_rcvhiwat = virtio_transport_stream_rcvhiwat,
.stream_is_active = virtio_transport_stream_is_active,
.stream_allow = virtio_transport_stream_allow,
.seqpacket_dequeue = virtio_transport_seqpacket_dequeue,
.seqpacket_enqueue = virtio_transport_seqpacket_enqueue,
.seqpacket_allow = virtio_transport_seqpacket_allow,
.seqpacket_has_data = virtio_transport_seqpacket_has_data,
.notify_poll_in = virtio_transport_notify_poll_in,
.notify_poll_out = virtio_transport_notify_poll_out,
.notify_recv_init = virtio_transport_notify_recv_init,
.notify_recv_pre_block = virtio_transport_notify_recv_pre_block,
.notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue,
.notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
.notify_send_init = virtio_transport_notify_send_init,
.notify_send_pre_block = virtio_transport_notify_send_pre_block,
.notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
.notify_buffer_size = virtio_transport_notify_buffer_size,
},
.send_pkt = virtio_transport_send_pkt,
};
static bool virtio_transport_seqpacket_allow(u32 remote_cid)
{
struct virtio_vsock *vsock;
bool seqpacket_allow;
virtio/vsock: avoid NULL deref in virtio_transport_seqpacket_allow() Make sure the_virtio_vsock is not NULL before dereferencing it. general protection fault, probably for non-canonical address 0xdffffc0000000071: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000388-0x000000000000038f] CPU: 0 PID: 8452 Comm: syz-executor406 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:virtio_transport_seqpacket_allow+0xbf/0x210 net/vmw_vsock/virtio_transport.c:503 Code: e8 c6 d9 ab f8 84 db 0f 84 0f 01 00 00 e8 09 d3 ab f8 48 8d bd 88 03 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 06 0f 8e 2a 01 00 00 44 0f b6 a5 88 03 00 00 RSP: 0018:ffffc90003757c18 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000071 RSI: ffffffff88c908e7 RDI: 0000000000000388 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff88c90a06 R11: 0000000000000000 R12: 0000000000000000 R13: ffffffff88c90840 R14: 0000000000000000 R15: 0000000000000001 FS: 0000000001bee300(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000082 CR3: 000000002847e000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vsock_assign_transport+0x575/0x700 net/vmw_vsock/af_vsock.c:490 vsock_connect+0x200/0xc00 net/vmw_vsock/af_vsock.c:1337 __sys_connect_file+0x155/0x1a0 net/socket.c:1824 __sys_connect+0x161/0x190 net/socket.c:1841 __do_sys_connect net/socket.c:1851 [inline] __se_sys_connect net/socket.c:1848 [inline] __x64_sys_connect+0x6f/0xb0 net/socket.c:1848 do_syscall_64+0x3a/0xb0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x43ee69 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd49e7c788 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000400488 RCX: 000000000043ee69 RDX: 0000000000000010 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 0000000000402e50 R08: 0000000000000000 R09: 0000000000400488 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000402ee0 R13: 0000000000000000 R14: 00000000004ac018 R15: 0000000000400488 Fixes: 53efbba12cc7 ("virtio/vsock: enable SEQPACKET for transport") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Arseny Krasnov <arseny.krasnov@kaspersky.com> Reported-by: syzbot <syzkaller@googlegroups.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-21 17:53:48 +03:00
seqpacket_allow = false;
rcu_read_lock();
vsock = rcu_dereference(the_virtio_vsock);
virtio/vsock: avoid NULL deref in virtio_transport_seqpacket_allow() Make sure the_virtio_vsock is not NULL before dereferencing it. general protection fault, probably for non-canonical address 0xdffffc0000000071: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000388-0x000000000000038f] CPU: 0 PID: 8452 Comm: syz-executor406 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:virtio_transport_seqpacket_allow+0xbf/0x210 net/vmw_vsock/virtio_transport.c:503 Code: e8 c6 d9 ab f8 84 db 0f 84 0f 01 00 00 e8 09 d3 ab f8 48 8d bd 88 03 00 00 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 <0f> b6 04 02 84 c0 74 06 0f 8e 2a 01 00 00 44 0f b6 a5 88 03 00 00 RSP: 0018:ffffc90003757c18 EFLAGS: 00010206 RAX: dffffc0000000000 RBX: 0000000000000001 RCX: 0000000000000000 RDX: 0000000000000071 RSI: ffffffff88c908e7 RDI: 0000000000000388 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff88c90a06 R11: 0000000000000000 R12: 0000000000000000 R13: ffffffff88c90840 R14: 0000000000000000 R15: 0000000000000001 FS: 0000000001bee300(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000082 CR3: 000000002847e000 CR4: 00000000001506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vsock_assign_transport+0x575/0x700 net/vmw_vsock/af_vsock.c:490 vsock_connect+0x200/0xc00 net/vmw_vsock/af_vsock.c:1337 __sys_connect_file+0x155/0x1a0 net/socket.c:1824 __sys_connect+0x161/0x190 net/socket.c:1841 __do_sys_connect net/socket.c:1851 [inline] __se_sys_connect net/socket.c:1848 [inline] __x64_sys_connect+0x6f/0xb0 net/socket.c:1848 do_syscall_64+0x3a/0xb0 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x43ee69 Code: 28 c3 e8 2a 14 00 00 66 2e 0f 1f 84 00 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd49e7c788 EFLAGS: 00000246 ORIG_RAX: 000000000000002a RAX: ffffffffffffffda RBX: 0000000000400488 RCX: 000000000043ee69 RDX: 0000000000000010 RSI: 0000000020000080 RDI: 0000000000000003 RBP: 0000000000402e50 R08: 0000000000000000 R09: 0000000000400488 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000402ee0 R13: 0000000000000000 R14: 00000000004ac018 R15: 0000000000400488 Fixes: 53efbba12cc7 ("virtio/vsock: enable SEQPACKET for transport") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Arseny Krasnov <arseny.krasnov@kaspersky.com> Reported-by: syzbot <syzkaller@googlegroups.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-21 17:53:48 +03:00
if (vsock)
seqpacket_allow = vsock->seqpacket_allow;
rcu_read_unlock();
return seqpacket_allow;
}
static void virtio_transport_rx_work(struct work_struct *work)
{
struct virtio_vsock *vsock =
container_of(work, struct virtio_vsock, rx_work);
struct virtqueue *vq;
vq = vsock->vqs[VSOCK_VQ_RX];
mutex_lock(&vsock->rx_lock);
if (!vsock->rx_run)
goto out;
do {
virtqueue_disable_cb(vq);
for (;;) {
struct sk_buff *skb;
unsigned int len;
if (!virtio_transport_more_replies(vsock)) {
/* Stop rx until the device processes already
* pending replies. Leave rx virtqueue
* callbacks disabled.
*/
goto out;
}
skb = virtqueue_get_buf(vq, &len);
if (!skb)
break;
vsock->rx_buf_nr--;
/* Drop short/long packets */
if (unlikely(len < sizeof(struct virtio_vsock_hdr) ||
len > virtio_vsock_skb_len(skb))) {
kfree_skb(skb);
continue;
}
virtio_vsock_skb_rx_put(skb);
virtio_transport_deliver_tap_pkt(skb);
virtio_transport_recv_pkt(&virtio_transport, skb);
}
} while (!virtqueue_enable_cb(vq));
out:
if (vsock->rx_buf_nr < vsock->rx_buf_max_nr / 2)
virtio_vsock_rx_fill(vsock);
mutex_unlock(&vsock->rx_lock);
}
static int virtio_vsock_vqs_init(struct virtio_vsock *vsock)
{
struct virtio_device *vdev = vsock->vdev;
static const char * const names[] = {
"rx",
"tx",
"event",
};
vq_callback_t *callbacks[] = {
virtio_vsock_rx_done,
virtio_vsock_tx_done,
virtio_vsock_event_done,
};
int ret;
ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, callbacks, names,
NULL);
if (ret < 0)
return ret;
virtio_vsock_update_guest_cid(vsock);
virtio_device_ready(vdev);
mutex_lock(&vsock->tx_lock);
vsock->tx_run = true;
mutex_unlock(&vsock->tx_lock);
mutex_lock(&vsock->rx_lock);
virtio_vsock_rx_fill(vsock);
vsock->rx_run = true;
mutex_unlock(&vsock->rx_lock);
mutex_lock(&vsock->event_lock);
virtio_vsock_event_fill(vsock);
vsock->event_run = true;
mutex_unlock(&vsock->event_lock);
return 0;
}
static void virtio_vsock_vqs_del(struct virtio_vsock *vsock)
{
struct virtio_device *vdev = vsock->vdev;
struct sk_buff *skb;
/* Reset all connected sockets when the VQs disappear */
vsock_for_each_connected_socket(&virtio_transport.transport,
virtio_vsock_reset_sock);
/* Stop all work handlers to make sure no one is accessing the device,
* so we can safely call virtio_reset_device().
*/
mutex_lock(&vsock->rx_lock);
vsock->rx_run = false;
mutex_unlock(&vsock->rx_lock);
mutex_lock(&vsock->tx_lock);
vsock->tx_run = false;
mutex_unlock(&vsock->tx_lock);
mutex_lock(&vsock->event_lock);
vsock->event_run = false;
mutex_unlock(&vsock->event_lock);
/* Flush all device writes and interrupts, device will not use any
* more buffers.
*/
virtio_reset_device(vdev);
mutex_lock(&vsock->rx_lock);
while ((skb = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX])))
kfree_skb(skb);
mutex_unlock(&vsock->rx_lock);
mutex_lock(&vsock->tx_lock);
while ((skb = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_TX])))
kfree_skb(skb);
mutex_unlock(&vsock->tx_lock);
virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue);
/* Delete virtqueues and flush outstanding callbacks if any */
vdev->config->del_vqs(vdev);
}
static int virtio_vsock_probe(struct virtio_device *vdev)
{
struct virtio_vsock *vsock = NULL;
int ret;
ret = mutex_lock_interruptible(&the_virtio_vsock_mutex);
if (ret)
return ret;
/* Only one virtio-vsock device per guest is supported */
if (rcu_dereference_protected(the_virtio_vsock,
lockdep_is_held(&the_virtio_vsock_mutex))) {
ret = -EBUSY;
goto out;
}
vsock = kzalloc(sizeof(*vsock), GFP_KERNEL);
if (!vsock) {
ret = -ENOMEM;
goto out;
}
vsock->vdev = vdev;
vsock->rx_buf_nr = 0;
vsock->rx_buf_max_nr = 0;
atomic_set(&vsock->queued_replies, 0);
mutex_init(&vsock->tx_lock);
mutex_init(&vsock->rx_lock);
mutex_init(&vsock->event_lock);
skb_queue_head_init(&vsock->send_pkt_queue);
INIT_WORK(&vsock->rx_work, virtio_transport_rx_work);
INIT_WORK(&vsock->tx_work, virtio_transport_tx_work);
INIT_WORK(&vsock->event_work, virtio_transport_event_work);
INIT_WORK(&vsock->send_pkt_work, virtio_transport_send_pkt_work);
if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET))
vsock->seqpacket_allow = true;
vdev->priv = vsock;
ret = virtio_vsock_vqs_init(vsock);
if (ret < 0)
goto out;
rcu_assign_pointer(the_virtio_vsock, vsock);
mutex_unlock(&the_virtio_vsock_mutex);
return 0;
out:
kfree(vsock);
mutex_unlock(&the_virtio_vsock_mutex);
return ret;
}
static void virtio_vsock_remove(struct virtio_device *vdev)
{
struct virtio_vsock *vsock = vdev->priv;
mutex_lock(&the_virtio_vsock_mutex);
vdev->priv = NULL;
rcu_assign_pointer(the_virtio_vsock, NULL);
synchronize_rcu();
virtio_vsock_vqs_del(vsock);
/* Other works can be queued before 'config->del_vqs()', so we flush
* all works before to free the vsock object to avoid use after free.
*/
flush_work(&vsock->rx_work);
flush_work(&vsock->tx_work);
flush_work(&vsock->event_work);
flush_work(&vsock->send_pkt_work);
mutex_unlock(&the_virtio_vsock_mutex);
kfree(vsock);
}
#ifdef CONFIG_PM_SLEEP
static int virtio_vsock_freeze(struct virtio_device *vdev)
{
struct virtio_vsock *vsock = vdev->priv;
mutex_lock(&the_virtio_vsock_mutex);
rcu_assign_pointer(the_virtio_vsock, NULL);
synchronize_rcu();
virtio_vsock_vqs_del(vsock);
mutex_unlock(&the_virtio_vsock_mutex);
return 0;
}
static int virtio_vsock_restore(struct virtio_device *vdev)
{
struct virtio_vsock *vsock = vdev->priv;
int ret;
mutex_lock(&the_virtio_vsock_mutex);
/* Only one virtio-vsock device per guest is supported */
if (rcu_dereference_protected(the_virtio_vsock,
lockdep_is_held(&the_virtio_vsock_mutex))) {
ret = -EBUSY;
goto out;
}
ret = virtio_vsock_vqs_init(vsock);
if (ret < 0)
goto out;
rcu_assign_pointer(the_virtio_vsock, vsock);
out:
mutex_unlock(&the_virtio_vsock_mutex);
return ret;
}
#endif /* CONFIG_PM_SLEEP */
static struct virtio_device_id id_table[] = {
{ VIRTIO_ID_VSOCK, VIRTIO_DEV_ANY_ID },
{ 0 },
};
static unsigned int features[] = {
VIRTIO_VSOCK_F_SEQPACKET
};
static struct virtio_driver virtio_vsock_driver = {
.feature_table = features,
.feature_table_size = ARRAY_SIZE(features),
.driver.name = KBUILD_MODNAME,
.driver.owner = THIS_MODULE,
.id_table = id_table,
.probe = virtio_vsock_probe,
.remove = virtio_vsock_remove,
#ifdef CONFIG_PM_SLEEP
.freeze = virtio_vsock_freeze,
.restore = virtio_vsock_restore,
#endif
};
static int __init virtio_vsock_init(void)
{
int ret;
virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0);
if (!virtio_vsock_workqueue)
return -ENOMEM;
vsock: add multi-transports support This patch adds the support of multiple transports in the VSOCK core. With the multi-transports support, we can use vsock with nested VMs (using also different hypervisors) loading both guest->host and host->guest transports at the same time. Major changes: - vsock core module can be loaded regardless of the transports - vsock_core_init() and vsock_core_exit() are renamed to vsock_core_register() and vsock_core_unregister() - vsock_core_register() has a feature parameter (H2G, G2H, DGRAM) to identify which directions the transport can handle and if it's support DGRAM (only vmci) - each stream socket is assigned to a transport when the remote CID is set (during the connect() or when we receive a connection request on a listener socket). The remote CID is used to decide which transport to use: - remote CID <= VMADDR_CID_HOST will use guest->host transport; - remote CID == local_cid (guest->host transport) will use guest->host transport for loopback (host->guest transports don't support loopback); - remote CID > VMADDR_CID_HOST will use host->guest transport; - listener sockets are not bound to any transports since no transport operations are done on it. In this way we can create a listener socket, also if the transports are not loaded or with VMADDR_CID_ANY to listen on all transports. - DGRAM sockets are handled as before, since only the vmci_transport provides this feature. Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-14 12:57:46 +03:00
ret = vsock_core_register(&virtio_transport.transport,
VSOCK_TRANSPORT_F_G2H);
if (ret)
goto out_wq;
vsock/virtio: Initialize core virtio vsock before registering the driver Avoid a race in which static variables in net/vmw_vsock/af_vsock.c are accessed (while handling interrupts) before they are initialized. [ 4.201410] BUG: unable to handle kernel paging request at ffffffffffffffe8 [ 4.207829] IP: vsock_addr_equals_addr+0x3/0x20 [ 4.211379] PGD 28210067 P4D 28210067 PUD 28212067 PMD 0 [ 4.211379] Oops: 0000 [#1] PREEMPT SMP PTI [ 4.211379] Modules linked in: [ 4.211379] CPU: 1 PID: 30 Comm: kworker/1:1 Not tainted 4.14.106-419297-gd7e28cc1f241 #1 [ 4.211379] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 4.211379] Workqueue: virtio_vsock virtio_transport_rx_work [ 4.211379] task: ffffa3273d175280 task.stack: ffffaea1800e8000 [ 4.211379] RIP: 0010:vsock_addr_equals_addr+0x3/0x20 [ 4.211379] RSP: 0000:ffffaea1800ebd28 EFLAGS: 00010286 [ 4.211379] RAX: 0000000000000002 RBX: 0000000000000000 RCX: ffffffffb94e42f0 [ 4.211379] RDX: 0000000000000400 RSI: ffffffffffffffe0 RDI: ffffaea1800ebdd0 [ 4.211379] RBP: ffffaea1800ebd58 R08: 0000000000000001 R09: 0000000000000001 [ 4.211379] R10: 0000000000000000 R11: ffffffffb89d5d60 R12: ffffaea1800ebdd0 [ 4.211379] R13: 00000000828cbfbf R14: 0000000000000000 R15: ffffaea1800ebdc0 [ 4.211379] FS: 0000000000000000(0000) GS:ffffa3273fd00000(0000) knlGS:0000000000000000 [ 4.211379] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4.211379] CR2: ffffffffffffffe8 CR3: 000000002820e001 CR4: 00000000001606e0 [ 4.211379] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4.211379] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4.211379] Call Trace: [ 4.211379] ? vsock_find_connected_socket+0x6c/0xe0 [ 4.211379] virtio_transport_recv_pkt+0x15f/0x740 [ 4.211379] ? detach_buf+0x1b5/0x210 [ 4.211379] virtio_transport_rx_work+0xb7/0x140 [ 4.211379] process_one_work+0x1ef/0x480 [ 4.211379] worker_thread+0x312/0x460 [ 4.211379] kthread+0x132/0x140 [ 4.211379] ? process_one_work+0x480/0x480 [ 4.211379] ? kthread_destroy_worker+0xd0/0xd0 [ 4.211379] ret_from_fork+0x35/0x40 [ 4.211379] Code: c7 47 08 00 00 00 00 66 c7 07 28 00 c7 47 08 ff ff ff ff c7 47 04 ff ff ff ff c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 8b 47 08 <3b> 46 08 75 0a 8b 47 04 3b 46 04 0f 94 c0 c3 31 c0 c3 90 66 2e [ 4.211379] RIP: vsock_addr_equals_addr+0x3/0x20 RSP: ffffaea1800ebd28 [ 4.211379] CR2: ffffffffffffffe8 [ 4.211379] ---[ end trace f31cc4a2e6df3689 ]--- [ 4.211379] Kernel panic - not syncing: Fatal exception in interrupt [ 4.211379] Kernel Offset: 0x37000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 4.211379] Rebooting in 5 seconds.. Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug") Cc: Stefan Hajnoczi <stefanha@redhat.com> Cc: Stefano Garzarella <sgarzare@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: netdev@vger.kernel.org Cc: kernel-team@android.com Cc: stable@vger.kernel.org [4.9+] Signed-off-by: Jorge E. Moreira <jemoreira@google.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-16 23:51:07 +03:00
ret = register_virtio_driver(&virtio_vsock_driver);
if (ret)
vsock/virtio: Initialize core virtio vsock before registering the driver Avoid a race in which static variables in net/vmw_vsock/af_vsock.c are accessed (while handling interrupts) before they are initialized. [ 4.201410] BUG: unable to handle kernel paging request at ffffffffffffffe8 [ 4.207829] IP: vsock_addr_equals_addr+0x3/0x20 [ 4.211379] PGD 28210067 P4D 28210067 PUD 28212067 PMD 0 [ 4.211379] Oops: 0000 [#1] PREEMPT SMP PTI [ 4.211379] Modules linked in: [ 4.211379] CPU: 1 PID: 30 Comm: kworker/1:1 Not tainted 4.14.106-419297-gd7e28cc1f241 #1 [ 4.211379] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 4.211379] Workqueue: virtio_vsock virtio_transport_rx_work [ 4.211379] task: ffffa3273d175280 task.stack: ffffaea1800e8000 [ 4.211379] RIP: 0010:vsock_addr_equals_addr+0x3/0x20 [ 4.211379] RSP: 0000:ffffaea1800ebd28 EFLAGS: 00010286 [ 4.211379] RAX: 0000000000000002 RBX: 0000000000000000 RCX: ffffffffb94e42f0 [ 4.211379] RDX: 0000000000000400 RSI: ffffffffffffffe0 RDI: ffffaea1800ebdd0 [ 4.211379] RBP: ffffaea1800ebd58 R08: 0000000000000001 R09: 0000000000000001 [ 4.211379] R10: 0000000000000000 R11: ffffffffb89d5d60 R12: ffffaea1800ebdd0 [ 4.211379] R13: 00000000828cbfbf R14: 0000000000000000 R15: ffffaea1800ebdc0 [ 4.211379] FS: 0000000000000000(0000) GS:ffffa3273fd00000(0000) knlGS:0000000000000000 [ 4.211379] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4.211379] CR2: ffffffffffffffe8 CR3: 000000002820e001 CR4: 00000000001606e0 [ 4.211379] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4.211379] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4.211379] Call Trace: [ 4.211379] ? vsock_find_connected_socket+0x6c/0xe0 [ 4.211379] virtio_transport_recv_pkt+0x15f/0x740 [ 4.211379] ? detach_buf+0x1b5/0x210 [ 4.211379] virtio_transport_rx_work+0xb7/0x140 [ 4.211379] process_one_work+0x1ef/0x480 [ 4.211379] worker_thread+0x312/0x460 [ 4.211379] kthread+0x132/0x140 [ 4.211379] ? process_one_work+0x480/0x480 [ 4.211379] ? kthread_destroy_worker+0xd0/0xd0 [ 4.211379] ret_from_fork+0x35/0x40 [ 4.211379] Code: c7 47 08 00 00 00 00 66 c7 07 28 00 c7 47 08 ff ff ff ff c7 47 04 ff ff ff ff c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 8b 47 08 <3b> 46 08 75 0a 8b 47 04 3b 46 04 0f 94 c0 c3 31 c0 c3 90 66 2e [ 4.211379] RIP: vsock_addr_equals_addr+0x3/0x20 RSP: ffffaea1800ebd28 [ 4.211379] CR2: ffffffffffffffe8 [ 4.211379] ---[ end trace f31cc4a2e6df3689 ]--- [ 4.211379] Kernel panic - not syncing: Fatal exception in interrupt [ 4.211379] Kernel Offset: 0x37000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 4.211379] Rebooting in 5 seconds.. Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug") Cc: Stefan Hajnoczi <stefanha@redhat.com> Cc: Stefano Garzarella <sgarzare@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: netdev@vger.kernel.org Cc: kernel-team@android.com Cc: stable@vger.kernel.org [4.9+] Signed-off-by: Jorge E. Moreira <jemoreira@google.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-16 23:51:07 +03:00
goto out_vci;
return 0;
vsock/virtio: Initialize core virtio vsock before registering the driver Avoid a race in which static variables in net/vmw_vsock/af_vsock.c are accessed (while handling interrupts) before they are initialized. [ 4.201410] BUG: unable to handle kernel paging request at ffffffffffffffe8 [ 4.207829] IP: vsock_addr_equals_addr+0x3/0x20 [ 4.211379] PGD 28210067 P4D 28210067 PUD 28212067 PMD 0 [ 4.211379] Oops: 0000 [#1] PREEMPT SMP PTI [ 4.211379] Modules linked in: [ 4.211379] CPU: 1 PID: 30 Comm: kworker/1:1 Not tainted 4.14.106-419297-gd7e28cc1f241 #1 [ 4.211379] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014 [ 4.211379] Workqueue: virtio_vsock virtio_transport_rx_work [ 4.211379] task: ffffa3273d175280 task.stack: ffffaea1800e8000 [ 4.211379] RIP: 0010:vsock_addr_equals_addr+0x3/0x20 [ 4.211379] RSP: 0000:ffffaea1800ebd28 EFLAGS: 00010286 [ 4.211379] RAX: 0000000000000002 RBX: 0000000000000000 RCX: ffffffffb94e42f0 [ 4.211379] RDX: 0000000000000400 RSI: ffffffffffffffe0 RDI: ffffaea1800ebdd0 [ 4.211379] RBP: ffffaea1800ebd58 R08: 0000000000000001 R09: 0000000000000001 [ 4.211379] R10: 0000000000000000 R11: ffffffffb89d5d60 R12: ffffaea1800ebdd0 [ 4.211379] R13: 00000000828cbfbf R14: 0000000000000000 R15: ffffaea1800ebdc0 [ 4.211379] FS: 0000000000000000(0000) GS:ffffa3273fd00000(0000) knlGS:0000000000000000 [ 4.211379] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 4.211379] CR2: ffffffffffffffe8 CR3: 000000002820e001 CR4: 00000000001606e0 [ 4.211379] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 4.211379] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 4.211379] Call Trace: [ 4.211379] ? vsock_find_connected_socket+0x6c/0xe0 [ 4.211379] virtio_transport_recv_pkt+0x15f/0x740 [ 4.211379] ? detach_buf+0x1b5/0x210 [ 4.211379] virtio_transport_rx_work+0xb7/0x140 [ 4.211379] process_one_work+0x1ef/0x480 [ 4.211379] worker_thread+0x312/0x460 [ 4.211379] kthread+0x132/0x140 [ 4.211379] ? process_one_work+0x480/0x480 [ 4.211379] ? kthread_destroy_worker+0xd0/0xd0 [ 4.211379] ret_from_fork+0x35/0x40 [ 4.211379] Code: c7 47 08 00 00 00 00 66 c7 07 28 00 c7 47 08 ff ff ff ff c7 47 04 ff ff ff ff c3 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 8b 47 08 <3b> 46 08 75 0a 8b 47 04 3b 46 04 0f 94 c0 c3 31 c0 c3 90 66 2e [ 4.211379] RIP: vsock_addr_equals_addr+0x3/0x20 RSP: ffffaea1800ebd28 [ 4.211379] CR2: ffffffffffffffe8 [ 4.211379] ---[ end trace f31cc4a2e6df3689 ]--- [ 4.211379] Kernel panic - not syncing: Fatal exception in interrupt [ 4.211379] Kernel Offset: 0x37000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) [ 4.211379] Rebooting in 5 seconds.. Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug") Cc: Stefan Hajnoczi <stefanha@redhat.com> Cc: Stefano Garzarella <sgarzare@redhat.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: kvm@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: netdev@vger.kernel.org Cc: kernel-team@android.com Cc: stable@vger.kernel.org [4.9+] Signed-off-by: Jorge E. Moreira <jemoreira@google.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-05-16 23:51:07 +03:00
out_vci:
vsock: add multi-transports support This patch adds the support of multiple transports in the VSOCK core. With the multi-transports support, we can use vsock with nested VMs (using also different hypervisors) loading both guest->host and host->guest transports at the same time. Major changes: - vsock core module can be loaded regardless of the transports - vsock_core_init() and vsock_core_exit() are renamed to vsock_core_register() and vsock_core_unregister() - vsock_core_register() has a feature parameter (H2G, G2H, DGRAM) to identify which directions the transport can handle and if it's support DGRAM (only vmci) - each stream socket is assigned to a transport when the remote CID is set (during the connect() or when we receive a connection request on a listener socket). The remote CID is used to decide which transport to use: - remote CID <= VMADDR_CID_HOST will use guest->host transport; - remote CID == local_cid (guest->host transport) will use guest->host transport for loopback (host->guest transports don't support loopback); - remote CID > VMADDR_CID_HOST will use host->guest transport; - listener sockets are not bound to any transports since no transport operations are done on it. In this way we can create a listener socket, also if the transports are not loaded or with VMADDR_CID_ANY to listen on all transports. - DGRAM sockets are handled as before, since only the vmci_transport provides this feature. Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-14 12:57:46 +03:00
vsock_core_unregister(&virtio_transport.transport);
out_wq:
destroy_workqueue(virtio_vsock_workqueue);
return ret;
}
static void __exit virtio_vsock_exit(void)
{
unregister_virtio_driver(&virtio_vsock_driver);
vsock: add multi-transports support This patch adds the support of multiple transports in the VSOCK core. With the multi-transports support, we can use vsock with nested VMs (using also different hypervisors) loading both guest->host and host->guest transports at the same time. Major changes: - vsock core module can be loaded regardless of the transports - vsock_core_init() and vsock_core_exit() are renamed to vsock_core_register() and vsock_core_unregister() - vsock_core_register() has a feature parameter (H2G, G2H, DGRAM) to identify which directions the transport can handle and if it's support DGRAM (only vmci) - each stream socket is assigned to a transport when the remote CID is set (during the connect() or when we receive a connection request on a listener socket). The remote CID is used to decide which transport to use: - remote CID <= VMADDR_CID_HOST will use guest->host transport; - remote CID == local_cid (guest->host transport) will use guest->host transport for loopback (host->guest transports don't support loopback); - remote CID > VMADDR_CID_HOST will use host->guest transport; - listener sockets are not bound to any transports since no transport operations are done on it. In this way we can create a listener socket, also if the transports are not loaded or with VMADDR_CID_ANY to listen on all transports. - DGRAM sockets are handled as before, since only the vmci_transport provides this feature. Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-11-14 12:57:46 +03:00
vsock_core_unregister(&virtio_transport.transport);
destroy_workqueue(virtio_vsock_workqueue);
}
module_init(virtio_vsock_init);
module_exit(virtio_vsock_exit);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("virtio transport for vsock");
MODULE_DEVICE_TABLE(virtio, id_table);