OpenCloudOS-Kernel/net/vmw_vsock/virtio_transport_common.c

1194 lines
28 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* common code for virtio vsock
*
* Copyright (C) 2013-2015 Red Hat, Inc.
* Author: Asias He <asias@redhat.com>
* Stefan Hajnoczi <stefanha@redhat.com>
*/
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/virtio_vsock.h>
#include <uapi/linux/vsockmon.h>
#include <net/sock.h>
#include <net/af_vsock.h>
#define CREATE_TRACE_POINTS
#include <trace/events/vsock_virtio_transport_common.h>
/* How long to wait for graceful shutdown of a connection */
#define VSOCK_CLOSE_TIMEOUT (8 * HZ)
/* Threshold for detecting small packets to copy */
#define GOOD_COPY_LEN 128
static const struct virtio_transport *
virtio_transport_get_ops(struct vsock_sock *vsk)
{
const struct vsock_transport *t = vsock_core_get_transport(vsk);
if (WARN_ON(!t))
return NULL;
return container_of(t, struct virtio_transport, transport);
}
static struct virtio_vsock_pkt *
virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
size_t len,
u32 src_cid,
u32 src_port,
u32 dst_cid,
u32 dst_port)
{
struct virtio_vsock_pkt *pkt;
int err;
pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
if (!pkt)
return NULL;
pkt->hdr.type = cpu_to_le16(info->type);
pkt->hdr.op = cpu_to_le16(info->op);
pkt->hdr.src_cid = cpu_to_le64(src_cid);
pkt->hdr.dst_cid = cpu_to_le64(dst_cid);
pkt->hdr.src_port = cpu_to_le32(src_port);
pkt->hdr.dst_port = cpu_to_le32(dst_port);
pkt->hdr.flags = cpu_to_le32(info->flags);
pkt->len = len;
pkt->hdr.len = cpu_to_le32(len);
pkt->reply = info->reply;
pkt->vsk = info->vsk;
if (info->msg && len > 0) {
pkt->buf = kmalloc(len, GFP_KERNEL);
if (!pkt->buf)
goto out_pkt;
pkt->buf_len = len;
err = memcpy_from_msg(pkt->buf, info->msg, len);
if (err)
goto out;
}
trace_virtio_transport_alloc_pkt(src_cid, src_port,
dst_cid, dst_port,
len,
info->type,
info->op,
info->flags);
return pkt;
out:
kfree(pkt->buf);
out_pkt:
kfree(pkt);
return NULL;
}
/* Packet capture */
static struct sk_buff *virtio_transport_build_skb(void *opaque)
{
struct virtio_vsock_pkt *pkt = opaque;
struct af_vsockmon_hdr *hdr;
struct sk_buff *skb;
size_t payload_len;
void *payload_buf;
/* A packet could be split to fit the RX buffer, so we can retrieve
* the payload length from the header and the buffer pointer taking
* care of the offset in the original packet.
*/
payload_len = le32_to_cpu(pkt->hdr.len);
payload_buf = pkt->buf + pkt->off;
skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len,
GFP_ATOMIC);
if (!skb)
return NULL;
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;
}
skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr));
if (payload_len) {
skb_put_data(skb, payload_buf, payload_len);
}
return skb;
}
void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
{
if (pkt->tap_delivered)
return;
vsock_deliver_tap(virtio_transport_build_skb, pkt);
pkt->tap_delivered = true;
}
EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
/* This function can only be used on connecting/connected sockets,
* since a socket assigned to a transport is required.
*
* Do not use on listener sockets!
*/
static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
struct virtio_vsock_pkt_info *info)
{
u32 src_cid, src_port, dst_cid, dst_port;
const struct virtio_transport *t_ops;
struct virtio_vsock_sock *vvs;
struct virtio_vsock_pkt *pkt;
u32 pkt_len = info->pkt_len;
t_ops = virtio_transport_get_ops(vsk);
if (unlikely(!t_ops))
return -EFAULT;
src_cid = t_ops->transport.get_local_cid();
src_port = vsk->local_addr.svm_port;
if (!info->remote_cid) {
dst_cid = vsk->remote_addr.svm_cid;
dst_port = vsk->remote_addr.svm_port;
} else {
dst_cid = info->remote_cid;
dst_port = info->remote_port;
}
vvs = vsk->trans;
/* we can send less than pkt_len bytes */
if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
/* virtio_transport_get_credit might return less than pkt_len credit */
pkt_len = virtio_transport_get_credit(vvs, pkt_len);
/* Do not send zero length OP_RW pkt */
if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW)
return pkt_len;
pkt = virtio_transport_alloc_pkt(info, pkt_len,
src_cid, src_port,
dst_cid, dst_port);
if (!pkt) {
virtio_transport_put_credit(vvs, pkt_len);
return -ENOMEM;
}
virtio_transport_inc_tx_pkt(vvs, pkt);
return t_ops->send_pkt(pkt);
}
static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
struct virtio_vsock_pkt *pkt)
{
if (vvs->rx_bytes + pkt->len > vvs->buf_alloc)
return false;
vvs->rx_bytes += pkt->len;
return true;
}
static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
struct virtio_vsock_pkt *pkt)
{
vvs->rx_bytes -= pkt->len;
vvs->fwd_cnt += pkt->len;
}
void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt)
{
spin_lock_bh(&vvs->rx_lock);
vvs->last_fwd_cnt = vvs->fwd_cnt;
pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt);
pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc);
spin_unlock_bh(&vvs->rx_lock);
}
EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt);
u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit)
{
u32 ret;
spin_lock_bh(&vvs->tx_lock);
ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
if (ret > credit)
ret = credit;
vvs->tx_cnt += ret;
spin_unlock_bh(&vvs->tx_lock);
return ret;
}
EXPORT_SYMBOL_GPL(virtio_transport_get_credit);
void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit)
{
spin_lock_bh(&vvs->tx_lock);
vvs->tx_cnt -= credit;
spin_unlock_bh(&vvs->tx_lock);
}
EXPORT_SYMBOL_GPL(virtio_transport_put_credit);
static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
int type,
struct virtio_vsock_hdr *hdr)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
.type = type,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
static ssize_t
virtio_transport_stream_do_peek(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len)
{
struct virtio_vsock_sock *vvs = vsk->trans;
struct virtio_vsock_pkt *pkt;
size_t bytes, total = 0, off;
int err = -EFAULT;
spin_lock_bh(&vvs->rx_lock);
list_for_each_entry(pkt, &vvs->rx_queue, list) {
off = pkt->off;
if (total == len)
break;
while (total < len && off < pkt->len) {
bytes = len - total;
if (bytes > pkt->len - off)
bytes = pkt->len - off;
/* sk_lock is held by caller so no one else can dequeue.
* Unlock rx_lock since memcpy_to_msg() may sleep.
*/
spin_unlock_bh(&vvs->rx_lock);
err = memcpy_to_msg(msg, pkt->buf + off, bytes);
if (err)
goto out;
spin_lock_bh(&vvs->rx_lock);
total += bytes;
off += bytes;
}
}
spin_unlock_bh(&vvs->rx_lock);
return total;
out:
if (total)
err = total;
return err;
}
static ssize_t
virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len)
{
struct virtio_vsock_sock *vvs = vsk->trans;
struct virtio_vsock_pkt *pkt;
size_t bytes, total = 0;
u32 free_space;
int err = -EFAULT;
spin_lock_bh(&vvs->rx_lock);
while (total < len && !list_empty(&vvs->rx_queue)) {
pkt = list_first_entry(&vvs->rx_queue,
struct virtio_vsock_pkt, list);
bytes = len - total;
if (bytes > pkt->len - pkt->off)
bytes = pkt->len - pkt->off;
/* sk_lock is held by caller so no one else can dequeue.
* Unlock rx_lock since memcpy_to_msg() may sleep.
*/
spin_unlock_bh(&vvs->rx_lock);
err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes);
if (err)
goto out;
spin_lock_bh(&vvs->rx_lock);
total += bytes;
pkt->off += bytes;
if (pkt->off == pkt->len) {
virtio_transport_dec_rx_pkt(vvs, pkt);
list_del(&pkt->list);
virtio_transport_free_pkt(pkt);
}
}
free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt);
spin_unlock_bh(&vvs->rx_lock);
/* To reduce the number of credit update messages,
* don't update credits as long as lots of space is available.
* Note: the limit chosen here is arbitrary. Setting the limit
* too high causes extra messages. Too low causes transmitter
* stalls. As stalls are in theory more expensive than extra
* messages, we set the limit to a high value. TODO: experiment
* with different values.
*/
if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
virtio_transport_send_credit_update(vsk,
VIRTIO_VSOCK_TYPE_STREAM,
NULL);
}
return total;
out:
if (total)
err = total;
return err;
}
ssize_t
virtio_transport_stream_dequeue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len, int flags)
{
if (flags & MSG_PEEK)
return virtio_transport_stream_do_peek(vsk, msg, len);
else
return virtio_transport_stream_do_dequeue(vsk, msg, len);
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);
int
virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len, int flags)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue);
s64 virtio_transport_stream_has_data(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
s64 bytes;
spin_lock_bh(&vvs->rx_lock);
bytes = vvs->rx_bytes;
spin_unlock_bh(&vvs->rx_lock);
return bytes;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data);
static s64 virtio_transport_has_space(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
s64 bytes;
bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
if (bytes < 0)
bytes = 0;
return bytes;
}
s64 virtio_transport_stream_has_space(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
s64 bytes;
spin_lock_bh(&vvs->tx_lock);
bytes = virtio_transport_has_space(vsk);
spin_unlock_bh(&vvs->tx_lock);
return bytes;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space);
int virtio_transport_do_socket_init(struct vsock_sock *vsk,
struct vsock_sock *psk)
{
struct virtio_vsock_sock *vvs;
vvs = kzalloc(sizeof(*vvs), GFP_KERNEL);
if (!vvs)
return -ENOMEM;
vsk->trans = vvs;
vvs->vsk = vsk;
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 17:57:46 +08:00
if (psk && psk->trans) {
struct virtio_vsock_sock *ptrans = psk->trans;
vvs->peer_buf_alloc = ptrans->peer_buf_alloc;
}
if (vsk->buffer_size > VIRTIO_VSOCK_MAX_BUF_SIZE)
vsk->buffer_size = VIRTIO_VSOCK_MAX_BUF_SIZE;
vvs->buf_alloc = vsk->buffer_size;
spin_lock_init(&vvs->rx_lock);
spin_lock_init(&vvs->tx_lock);
INIT_LIST_HEAD(&vvs->rx_queue);
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init);
/* sk_lock held by the caller */
void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val)
{
struct virtio_vsock_sock *vvs = vsk->trans;
if (*val > VIRTIO_VSOCK_MAX_BUF_SIZE)
*val = VIRTIO_VSOCK_MAX_BUF_SIZE;
vvs->buf_alloc = *val;
virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
NULL);
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size);
int
virtio_transport_notify_poll_in(struct vsock_sock *vsk,
size_t target,
bool *data_ready_now)
{
if (vsock_stream_has_data(vsk))
*data_ready_now = true;
else
*data_ready_now = false;
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in);
int
virtio_transport_notify_poll_out(struct vsock_sock *vsk,
size_t target,
bool *space_avail_now)
{
s64 free_space;
free_space = vsock_stream_has_space(vsk);
if (free_space > 0)
*space_avail_now = true;
else if (free_space == 0)
*space_avail_now = false;
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out);
int virtio_transport_notify_recv_init(struct vsock_sock *vsk,
size_t target, struct vsock_transport_recv_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init);
int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk,
size_t target, struct vsock_transport_recv_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block);
int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk,
size_t target, struct vsock_transport_recv_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue);
int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk,
size_t target, ssize_t copied, bool data_read,
struct vsock_transport_recv_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue);
int virtio_transport_notify_send_init(struct vsock_sock *vsk,
struct vsock_transport_send_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init);
int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk,
struct vsock_transport_send_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block);
int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk,
struct vsock_transport_send_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue);
int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk,
ssize_t written, struct vsock_transport_send_notify_data *data)
{
return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue);
u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk)
{
return vsk->buffer_size;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat);
bool virtio_transport_stream_is_active(struct vsock_sock *vsk)
{
return true;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active);
bool virtio_transport_stream_allow(u32 cid, u32 port)
{
return true;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_allow);
int virtio_transport_dgram_bind(struct vsock_sock *vsk,
struct sockaddr_vm *addr)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind);
bool virtio_transport_dgram_allow(u32 cid, u32 port)
{
return false;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow);
int virtio_transport_connect(struct vsock_sock *vsk)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_REQUEST,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_connect);
int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_SHUTDOWN,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.flags = (mode & RCV_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
(mode & SEND_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_shutdown);
int
virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
struct sockaddr_vm *remote_addr,
struct msghdr *msg,
size_t dgram_len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue);
ssize_t
virtio_transport_stream_enqueue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RW,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.msg = msg,
.pkt_len = len,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);
void virtio_transport_destruct(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
kfree(vvs);
}
EXPORT_SYMBOL_GPL(virtio_transport_destruct);
static int virtio_transport_reset(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.reply = !!pkt,
.vsk = vsk,
};
/* Send RST only if the original pkt is not a RST pkt */
if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
return virtio_transport_send_pkt_info(vsk, &info);
}
/* Normally packets are associated with a socket. There may be no socket if an
* attempt was made to connect to a socket that does not exist.
*/
static int virtio_transport_reset_no_sock(const struct virtio_transport *t,
struct virtio_vsock_pkt *pkt)
{
vsock/virtio: fix kernel panic from virtio_transport_reset_no_sock Previous to commit 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug"), vsock_core_init() was called from virtio_vsock_probe(). Now, virtio_transport_reset_no_sock() can be called before vsock_core_init() has the chance to run. [Wed Feb 27 14:17:09 2019] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [Wed Feb 27 14:17:09 2019] #PF error: [normal kernel read fault] [Wed Feb 27 14:17:09 2019] PGD 0 P4D 0 [Wed Feb 27 14:17:09 2019] Oops: 0000 [#1] SMP PTI [Wed Feb 27 14:17:09 2019] CPU: 3 PID: 59 Comm: kworker/3:1 Not tainted 5.0.0-rc7-390-generic-hvi #390 [Wed Feb 27 14:17:09 2019] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [Wed Feb 27 14:17:09 2019] Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] [Wed Feb 27 14:17:09 2019] RIP: 0010:virtio_transport_reset_no_sock+0x8c/0xc0 [vmw_vsock_virtio_transport_common] [Wed Feb 27 14:17:09 2019] Code: 35 8b 4f 14 48 8b 57 08 31 f6 44 8b 4f 10 44 8b 07 48 8d 7d c8 e8 84 f8 ff ff 48 85 c0 48 89 c3 74 2a e8 f7 31 03 00 48 89 df <48> 8b 80 10 01 00 00 e8 68 fb 69 ed 48 8b 75 f0 65 48 33 34 25 28 [Wed Feb 27 14:17:09 2019] RSP: 0018:ffffb42701ab7d40 EFLAGS: 00010282 [Wed Feb 27 14:17:09 2019] RAX: 0000000000000000 RBX: ffff9d79637ee080 RCX: 0000000000000003 [Wed Feb 27 14:17:09 2019] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff9d79637ee080 [Wed Feb 27 14:17:09 2019] RBP: ffffb42701ab7d78 R08: ffff9d796fae70e0 R09: ffff9d796f403500 [Wed Feb 27 14:17:09 2019] R10: ffffb42701ab7d90 R11: 0000000000000000 R12: ffff9d7969d09240 [Wed Feb 27 14:17:09 2019] R13: ffff9d79624e6840 R14: ffff9d7969d09318 R15: ffff9d796d48ff80 [Wed Feb 27 14:17:09 2019] FS: 0000000000000000(0000) GS:ffff9d796fac0000(0000) knlGS:0000000000000000 [Wed Feb 27 14:17:09 2019] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Wed Feb 27 14:17:09 2019] CR2: 0000000000000110 CR3: 0000000427f22000 CR4: 00000000000006e0 [Wed Feb 27 14:17:09 2019] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [Wed Feb 27 14:17:09 2019] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [Wed Feb 27 14:17:09 2019] Call Trace: [Wed Feb 27 14:17:09 2019] virtio_transport_recv_pkt+0x63/0x820 [vmw_vsock_virtio_transport_common] [Wed Feb 27 14:17:09 2019] ? kfree+0x17e/0x190 [Wed Feb 27 14:17:09 2019] ? detach_buf_split+0x145/0x160 [Wed Feb 27 14:17:09 2019] ? __switch_to_asm+0x40/0x70 [Wed Feb 27 14:17:09 2019] virtio_transport_rx_work+0xa0/0x106 [vmw_vsock_virtio_transport] [Wed Feb 27 14:17:09 2019] NET: Registered protocol family 40 [Wed Feb 27 14:17:09 2019] process_one_work+0x167/0x410 [Wed Feb 27 14:17:09 2019] worker_thread+0x4d/0x460 [Wed Feb 27 14:17:09 2019] kthread+0x105/0x140 [Wed Feb 27 14:17:09 2019] ? rescuer_thread+0x360/0x360 [Wed Feb 27 14:17:09 2019] ? kthread_destroy_worker+0x50/0x50 [Wed Feb 27 14:17:09 2019] ret_from_fork+0x35/0x40 [Wed Feb 27 14:17:09 2019] Modules linked in: vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common input_leds vsock serio_raw i2c_piix4 mac_hid qemu_fw_cfg autofs4 cirrus ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net psmouse drm net_failover pata_acpi virtio_blk failover floppy Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug") Reported-by: Alexandru Herghelegiu <aherghelegiu@bitdefender.com> Signed-off-by: Adalbert Lazăr <alazar@bitdefender.com> Co-developed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-06 18:13:53 +08:00
struct virtio_vsock_pkt *reply;
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = le16_to_cpu(pkt->hdr.type),
.reply = true,
};
/* Send RST only if the original pkt is not a RST pkt */
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
vsock/virtio: fix kernel panic from virtio_transport_reset_no_sock Previous to commit 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug"), vsock_core_init() was called from virtio_vsock_probe(). Now, virtio_transport_reset_no_sock() can be called before vsock_core_init() has the chance to run. [Wed Feb 27 14:17:09 2019] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [Wed Feb 27 14:17:09 2019] #PF error: [normal kernel read fault] [Wed Feb 27 14:17:09 2019] PGD 0 P4D 0 [Wed Feb 27 14:17:09 2019] Oops: 0000 [#1] SMP PTI [Wed Feb 27 14:17:09 2019] CPU: 3 PID: 59 Comm: kworker/3:1 Not tainted 5.0.0-rc7-390-generic-hvi #390 [Wed Feb 27 14:17:09 2019] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [Wed Feb 27 14:17:09 2019] Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] [Wed Feb 27 14:17:09 2019] RIP: 0010:virtio_transport_reset_no_sock+0x8c/0xc0 [vmw_vsock_virtio_transport_common] [Wed Feb 27 14:17:09 2019] Code: 35 8b 4f 14 48 8b 57 08 31 f6 44 8b 4f 10 44 8b 07 48 8d 7d c8 e8 84 f8 ff ff 48 85 c0 48 89 c3 74 2a e8 f7 31 03 00 48 89 df <48> 8b 80 10 01 00 00 e8 68 fb 69 ed 48 8b 75 f0 65 48 33 34 25 28 [Wed Feb 27 14:17:09 2019] RSP: 0018:ffffb42701ab7d40 EFLAGS: 00010282 [Wed Feb 27 14:17:09 2019] RAX: 0000000000000000 RBX: ffff9d79637ee080 RCX: 0000000000000003 [Wed Feb 27 14:17:09 2019] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff9d79637ee080 [Wed Feb 27 14:17:09 2019] RBP: ffffb42701ab7d78 R08: ffff9d796fae70e0 R09: ffff9d796f403500 [Wed Feb 27 14:17:09 2019] R10: ffffb42701ab7d90 R11: 0000000000000000 R12: ffff9d7969d09240 [Wed Feb 27 14:17:09 2019] R13: ffff9d79624e6840 R14: ffff9d7969d09318 R15: ffff9d796d48ff80 [Wed Feb 27 14:17:09 2019] FS: 0000000000000000(0000) GS:ffff9d796fac0000(0000) knlGS:0000000000000000 [Wed Feb 27 14:17:09 2019] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Wed Feb 27 14:17:09 2019] CR2: 0000000000000110 CR3: 0000000427f22000 CR4: 00000000000006e0 [Wed Feb 27 14:17:09 2019] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [Wed Feb 27 14:17:09 2019] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [Wed Feb 27 14:17:09 2019] Call Trace: [Wed Feb 27 14:17:09 2019] virtio_transport_recv_pkt+0x63/0x820 [vmw_vsock_virtio_transport_common] [Wed Feb 27 14:17:09 2019] ? kfree+0x17e/0x190 [Wed Feb 27 14:17:09 2019] ? detach_buf_split+0x145/0x160 [Wed Feb 27 14:17:09 2019] ? __switch_to_asm+0x40/0x70 [Wed Feb 27 14:17:09 2019] virtio_transport_rx_work+0xa0/0x106 [vmw_vsock_virtio_transport] [Wed Feb 27 14:17:09 2019] NET: Registered protocol family 40 [Wed Feb 27 14:17:09 2019] process_one_work+0x167/0x410 [Wed Feb 27 14:17:09 2019] worker_thread+0x4d/0x460 [Wed Feb 27 14:17:09 2019] kthread+0x105/0x140 [Wed Feb 27 14:17:09 2019] ? rescuer_thread+0x360/0x360 [Wed Feb 27 14:17:09 2019] ? kthread_destroy_worker+0x50/0x50 [Wed Feb 27 14:17:09 2019] ret_from_fork+0x35/0x40 [Wed Feb 27 14:17:09 2019] Modules linked in: vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common input_leds vsock serio_raw i2c_piix4 mac_hid qemu_fw_cfg autofs4 cirrus ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net psmouse drm net_failover pata_acpi virtio_blk failover floppy Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug") Reported-by: Alexandru Herghelegiu <aherghelegiu@bitdefender.com> Signed-off-by: Adalbert Lazăr <alazar@bitdefender.com> Co-developed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-06 18:13:53 +08:00
reply = virtio_transport_alloc_pkt(&info, 0,
le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port),
le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
if (!reply)
return -ENOMEM;
vsock/virtio: fix kernel panic from virtio_transport_reset_no_sock Previous to commit 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug"), vsock_core_init() was called from virtio_vsock_probe(). Now, virtio_transport_reset_no_sock() can be called before vsock_core_init() has the chance to run. [Wed Feb 27 14:17:09 2019] BUG: unable to handle kernel NULL pointer dereference at 0000000000000110 [Wed Feb 27 14:17:09 2019] #PF error: [normal kernel read fault] [Wed Feb 27 14:17:09 2019] PGD 0 P4D 0 [Wed Feb 27 14:17:09 2019] Oops: 0000 [#1] SMP PTI [Wed Feb 27 14:17:09 2019] CPU: 3 PID: 59 Comm: kworker/3:1 Not tainted 5.0.0-rc7-390-generic-hvi #390 [Wed Feb 27 14:17:09 2019] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014 [Wed Feb 27 14:17:09 2019] Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] [Wed Feb 27 14:17:09 2019] RIP: 0010:virtio_transport_reset_no_sock+0x8c/0xc0 [vmw_vsock_virtio_transport_common] [Wed Feb 27 14:17:09 2019] Code: 35 8b 4f 14 48 8b 57 08 31 f6 44 8b 4f 10 44 8b 07 48 8d 7d c8 e8 84 f8 ff ff 48 85 c0 48 89 c3 74 2a e8 f7 31 03 00 48 89 df <48> 8b 80 10 01 00 00 e8 68 fb 69 ed 48 8b 75 f0 65 48 33 34 25 28 [Wed Feb 27 14:17:09 2019] RSP: 0018:ffffb42701ab7d40 EFLAGS: 00010282 [Wed Feb 27 14:17:09 2019] RAX: 0000000000000000 RBX: ffff9d79637ee080 RCX: 0000000000000003 [Wed Feb 27 14:17:09 2019] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff9d79637ee080 [Wed Feb 27 14:17:09 2019] RBP: ffffb42701ab7d78 R08: ffff9d796fae70e0 R09: ffff9d796f403500 [Wed Feb 27 14:17:09 2019] R10: ffffb42701ab7d90 R11: 0000000000000000 R12: ffff9d7969d09240 [Wed Feb 27 14:17:09 2019] R13: ffff9d79624e6840 R14: ffff9d7969d09318 R15: ffff9d796d48ff80 [Wed Feb 27 14:17:09 2019] FS: 0000000000000000(0000) GS:ffff9d796fac0000(0000) knlGS:0000000000000000 [Wed Feb 27 14:17:09 2019] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [Wed Feb 27 14:17:09 2019] CR2: 0000000000000110 CR3: 0000000427f22000 CR4: 00000000000006e0 [Wed Feb 27 14:17:09 2019] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [Wed Feb 27 14:17:09 2019] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [Wed Feb 27 14:17:09 2019] Call Trace: [Wed Feb 27 14:17:09 2019] virtio_transport_recv_pkt+0x63/0x820 [vmw_vsock_virtio_transport_common] [Wed Feb 27 14:17:09 2019] ? kfree+0x17e/0x190 [Wed Feb 27 14:17:09 2019] ? detach_buf_split+0x145/0x160 [Wed Feb 27 14:17:09 2019] ? __switch_to_asm+0x40/0x70 [Wed Feb 27 14:17:09 2019] virtio_transport_rx_work+0xa0/0x106 [vmw_vsock_virtio_transport] [Wed Feb 27 14:17:09 2019] NET: Registered protocol family 40 [Wed Feb 27 14:17:09 2019] process_one_work+0x167/0x410 [Wed Feb 27 14:17:09 2019] worker_thread+0x4d/0x460 [Wed Feb 27 14:17:09 2019] kthread+0x105/0x140 [Wed Feb 27 14:17:09 2019] ? rescuer_thread+0x360/0x360 [Wed Feb 27 14:17:09 2019] ? kthread_destroy_worker+0x50/0x50 [Wed Feb 27 14:17:09 2019] ret_from_fork+0x35/0x40 [Wed Feb 27 14:17:09 2019] Modules linked in: vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common input_leds vsock serio_raw i2c_piix4 mac_hid qemu_fw_cfg autofs4 cirrus ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops virtio_net psmouse drm net_failover pata_acpi virtio_blk failover floppy Fixes: 22b5c0b63f32 ("vsock/virtio: fix kernel panic after device hot-unplug") Reported-by: Alexandru Herghelegiu <aherghelegiu@bitdefender.com> Signed-off-by: Adalbert Lazăr <alazar@bitdefender.com> Co-developed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-06 18:13:53 +08:00
if (!t) {
virtio_transport_free_pkt(reply);
return -ENOTCONN;
}
return t->send_pkt(reply);
}
static void virtio_transport_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(sk_sleep(sk), &wait);
do {
if (sk_wait_event(sk, &timeout,
sock_flag(sk, SOCK_DONE), &wait))
break;
} while (!signal_pending(current) && timeout);
remove_wait_queue(sk_sleep(sk), &wait);
}
}
static void virtio_transport_do_close(struct vsock_sock *vsk,
bool cancel_timeout)
{
struct sock *sk = sk_vsock(vsk);
sock_set_flag(sk, SOCK_DONE);
vsk->peer_shutdown = SHUTDOWN_MASK;
if (vsock_stream_has_data(vsk) <= 0)
sk->sk_state = TCP_CLOSING;
sk->sk_state_change(sk);
if (vsk->close_work_scheduled &&
(!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
vsk->close_work_scheduled = false;
vsock_remove_sock(vsk);
/* Release refcnt obtained when we scheduled the timeout */
sock_put(sk);
}
}
static void virtio_transport_close_timeout(struct work_struct *work)
{
struct vsock_sock *vsk =
container_of(work, struct vsock_sock, close_work.work);
struct sock *sk = sk_vsock(vsk);
sock_hold(sk);
lock_sock(sk);
if (!sock_flag(sk, SOCK_DONE)) {
(void)virtio_transport_reset(vsk, NULL);
virtio_transport_do_close(vsk, false);
}
vsk->close_work_scheduled = false;
release_sock(sk);
sock_put(sk);
}
/* User context, vsk->sk is locked */
static bool virtio_transport_close(struct vsock_sock *vsk)
{
struct sock *sk = &vsk->sk;
if (!(sk->sk_state == TCP_ESTABLISHED ||
sk->sk_state == TCP_CLOSING))
return true;
/* Already received SHUTDOWN from peer, reply with RST */
if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) {
(void)virtio_transport_reset(vsk, NULL);
return true;
}
if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
(void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK);
if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING))
virtio_transport_wait_close(sk, sk->sk_lingertime);
if (sock_flag(sk, SOCK_DONE)) {
return true;
}
sock_hold(sk);
INIT_DELAYED_WORK(&vsk->close_work,
virtio_transport_close_timeout);
vsk->close_work_scheduled = true;
schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT);
return false;
}
void virtio_transport_release(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
struct virtio_vsock_pkt *pkt, *tmp;
struct sock *sk = &vsk->sk;
bool remove_sock = true;
if (sk->sk_type == SOCK_STREAM)
remove_sock = virtio_transport_close(vsk);
list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) {
list_del(&pkt->list);
virtio_transport_free_pkt(pkt);
}
if (remove_sock)
vsock_remove_sock(vsk);
}
EXPORT_SYMBOL_GPL(virtio_transport_release);
static int
virtio_transport_recv_connecting(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
int err;
int skerr;
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RESPONSE:
sk->sk_state = TCP_ESTABLISHED;
sk->sk_socket->state = SS_CONNECTED;
vsock_insert_connected(vsk);
sk->sk_state_change(sk);
break;
case VIRTIO_VSOCK_OP_INVALID:
break;
case VIRTIO_VSOCK_OP_RST:
skerr = ECONNRESET;
err = 0;
goto destroy;
default:
skerr = EPROTO;
err = -EINVAL;
goto destroy;
}
return 0;
destroy:
virtio_transport_reset(vsk, pkt);
sk->sk_state = TCP_CLOSE;
sk->sk_err = skerr;
sk->sk_error_report(sk);
return err;
}
static void
virtio_transport_recv_enqueue(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_sock *vvs = vsk->trans;
bool can_enqueue, free_pkt = false;
pkt->len = le32_to_cpu(pkt->hdr.len);
pkt->off = 0;
spin_lock_bh(&vvs->rx_lock);
can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt);
if (!can_enqueue) {
free_pkt = true;
goto out;
}
/* Try to copy small packets into the buffer of last packet queued,
* to avoid wasting memory queueing the entire buffer with a small
* payload.
*/
if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) {
struct virtio_vsock_pkt *last_pkt;
last_pkt = list_last_entry(&vvs->rx_queue,
struct virtio_vsock_pkt, list);
/* If there is space in the last packet queued, we copy the
* new packet in its buffer.
*/
if (pkt->len <= last_pkt->buf_len - last_pkt->len) {
memcpy(last_pkt->buf + last_pkt->len, pkt->buf,
pkt->len);
last_pkt->len += pkt->len;
free_pkt = true;
goto out;
}
}
list_add_tail(&pkt->list, &vvs->rx_queue);
out:
spin_unlock_bh(&vvs->rx_lock);
if (free_pkt)
virtio_transport_free_pkt(pkt);
}
static int
virtio_transport_recv_connected(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
int err = 0;
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RW:
virtio_transport_recv_enqueue(vsk, pkt);
sk->sk_data_ready(sk);
return err;
case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
sk->sk_write_space(sk);
break;
case VIRTIO_VSOCK_OP_SHUTDOWN:
if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV)
vsk->peer_shutdown |= RCV_SHUTDOWN;
if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
vsk->peer_shutdown |= SEND_SHUTDOWN;
if (vsk->peer_shutdown == SHUTDOWN_MASK &&
vsock_stream_has_data(vsk) <= 0 &&
!sock_flag(sk, SOCK_DONE)) {
(void)virtio_transport_reset(vsk, NULL);
virtio_transport_do_close(vsk, true);
}
if (le32_to_cpu(pkt->hdr.flags))
sk->sk_state_change(sk);
break;
case VIRTIO_VSOCK_OP_RST:
virtio_transport_do_close(vsk, true);
break;
default:
err = -EINVAL;
break;
}
virtio_transport_free_pkt(pkt);
return err;
}
static void
virtio_transport_recv_disconnecting(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
virtio_transport_do_close(vsk, true);
}
static int
virtio_transport_send_response(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RESPONSE,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
.remote_port = le32_to_cpu(pkt->hdr.src_port),
.reply = true,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
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 17:57:46 +08:00
static bool virtio_transport_space_update(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct virtio_vsock_sock *vvs = vsk->trans;
bool space_available;
/* Listener sockets are not associated with any transport, so we are
* not able to take the state to see if there is space available in the
* remote peer, but since they are only used to receive requests, we
* can assume that there is always space available in the other peer.
*/
if (!vvs)
return true;
/* buf_alloc and fwd_cnt is always included in the hdr */
spin_lock_bh(&vvs->tx_lock);
vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
space_available = virtio_transport_has_space(vsk);
spin_unlock_bh(&vvs->tx_lock);
return space_available;
}
/* Handle server socket */
static int
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 17:57:46 +08:00
virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt,
struct virtio_transport *t)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct vsock_sock *vchild;
struct sock *child;
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 17:57:46 +08:00
int ret;
if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
vsock/virtio: fix null-pointer dereference in virtio_transport_recv_listen() With multi-transport support, listener sockets are not bound to any transport. So, calling virtio_transport_reset(), when an error occurs, on a listener socket produces the following null-pointer dereference: BUG: kernel NULL pointer dereference, address: 00000000000000e8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 20 Comm: kworker/0:1 Not tainted 5.5.0-rc1-ste-00003-gb4be21f316ac-dirty #56 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] RIP: 0010:virtio_transport_send_pkt_info+0x20/0x130 [vmw_vsock_virtio_transport_common] Code: 1f 84 00 00 00 00 00 0f 1f 00 55 48 89 e5 41 57 41 56 41 55 49 89 f5 41 54 49 89 fc 53 48 83 ec 10 44 8b 76 20 e8 c0 ba fe ff <48> 8b 80 e8 00 00 00 e8 64 e3 7d c1 45 8b 45 00 41 8b 8c 24 d4 02 RSP: 0018:ffffc900000b7d08 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff88807bf12728 RCX: 0000000000000000 RDX: ffff88807bf12700 RSI: ffffc900000b7d50 RDI: ffff888035c84000 RBP: ffffc900000b7d40 R08: ffff888035c84000 R09: ffffc900000b7d08 R10: ffff8880781de800 R11: 0000000000000018 R12: ffff888035c84000 R13: ffffc900000b7d50 R14: 0000000000000000 R15: ffff88807bf12724 FS: 0000000000000000(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e8 CR3: 00000000790f4004 CR4: 0000000000160ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: virtio_transport_reset+0x59/0x70 [vmw_vsock_virtio_transport_common] virtio_transport_recv_pkt+0x5bb/0xe50 [vmw_vsock_virtio_transport_common] ? detach_buf_split+0xf1/0x130 virtio_transport_rx_work+0xba/0x130 [vmw_vsock_virtio_transport] process_one_work+0x1c0/0x300 worker_thread+0x45/0x3c0 kthread+0xfc/0x130 ? current_work+0x40/0x40 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: sunrpc kvm_intel kvm vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common irqbypass vsock virtio_rng rng_core CR2: 00000000000000e8 ---[ end trace e75400e2ea2fa824 ]--- This happens because virtio_transport_reset() calls virtio_transport_send_pkt_info() that can be used only on connecting/connected sockets. This patch fixes the issue, using virtio_transport_reset_no_sock() instead of virtio_transport_reset() when we are handling a listener socket. Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-14 02:48:00 +08:00
virtio_transport_reset_no_sock(t, pkt);
return -EINVAL;
}
if (sk_acceptq_is_full(sk)) {
vsock/virtio: fix null-pointer dereference in virtio_transport_recv_listen() With multi-transport support, listener sockets are not bound to any transport. So, calling virtio_transport_reset(), when an error occurs, on a listener socket produces the following null-pointer dereference: BUG: kernel NULL pointer dereference, address: 00000000000000e8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 20 Comm: kworker/0:1 Not tainted 5.5.0-rc1-ste-00003-gb4be21f316ac-dirty #56 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] RIP: 0010:virtio_transport_send_pkt_info+0x20/0x130 [vmw_vsock_virtio_transport_common] Code: 1f 84 00 00 00 00 00 0f 1f 00 55 48 89 e5 41 57 41 56 41 55 49 89 f5 41 54 49 89 fc 53 48 83 ec 10 44 8b 76 20 e8 c0 ba fe ff <48> 8b 80 e8 00 00 00 e8 64 e3 7d c1 45 8b 45 00 41 8b 8c 24 d4 02 RSP: 0018:ffffc900000b7d08 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff88807bf12728 RCX: 0000000000000000 RDX: ffff88807bf12700 RSI: ffffc900000b7d50 RDI: ffff888035c84000 RBP: ffffc900000b7d40 R08: ffff888035c84000 R09: ffffc900000b7d08 R10: ffff8880781de800 R11: 0000000000000018 R12: ffff888035c84000 R13: ffffc900000b7d50 R14: 0000000000000000 R15: ffff88807bf12724 FS: 0000000000000000(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e8 CR3: 00000000790f4004 CR4: 0000000000160ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: virtio_transport_reset+0x59/0x70 [vmw_vsock_virtio_transport_common] virtio_transport_recv_pkt+0x5bb/0xe50 [vmw_vsock_virtio_transport_common] ? detach_buf_split+0xf1/0x130 virtio_transport_rx_work+0xba/0x130 [vmw_vsock_virtio_transport] process_one_work+0x1c0/0x300 worker_thread+0x45/0x3c0 kthread+0xfc/0x130 ? current_work+0x40/0x40 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: sunrpc kvm_intel kvm vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common irqbypass vsock virtio_rng rng_core CR2: 00000000000000e8 ---[ end trace e75400e2ea2fa824 ]--- This happens because virtio_transport_reset() calls virtio_transport_send_pkt_info() that can be used only on connecting/connected sockets. This patch fixes the issue, using virtio_transport_reset_no_sock() instead of virtio_transport_reset() when we are handling a listener socket. Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-14 02:48:00 +08:00
virtio_transport_reset_no_sock(t, pkt);
return -ENOMEM;
}
child = vsock_create_connected(sk);
if (!child) {
vsock/virtio: fix null-pointer dereference in virtio_transport_recv_listen() With multi-transport support, listener sockets are not bound to any transport. So, calling virtio_transport_reset(), when an error occurs, on a listener socket produces the following null-pointer dereference: BUG: kernel NULL pointer dereference, address: 00000000000000e8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 20 Comm: kworker/0:1 Not tainted 5.5.0-rc1-ste-00003-gb4be21f316ac-dirty #56 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] RIP: 0010:virtio_transport_send_pkt_info+0x20/0x130 [vmw_vsock_virtio_transport_common] Code: 1f 84 00 00 00 00 00 0f 1f 00 55 48 89 e5 41 57 41 56 41 55 49 89 f5 41 54 49 89 fc 53 48 83 ec 10 44 8b 76 20 e8 c0 ba fe ff <48> 8b 80 e8 00 00 00 e8 64 e3 7d c1 45 8b 45 00 41 8b 8c 24 d4 02 RSP: 0018:ffffc900000b7d08 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff88807bf12728 RCX: 0000000000000000 RDX: ffff88807bf12700 RSI: ffffc900000b7d50 RDI: ffff888035c84000 RBP: ffffc900000b7d40 R08: ffff888035c84000 R09: ffffc900000b7d08 R10: ffff8880781de800 R11: 0000000000000018 R12: ffff888035c84000 R13: ffffc900000b7d50 R14: 0000000000000000 R15: ffff88807bf12724 FS: 0000000000000000(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e8 CR3: 00000000790f4004 CR4: 0000000000160ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: virtio_transport_reset+0x59/0x70 [vmw_vsock_virtio_transport_common] virtio_transport_recv_pkt+0x5bb/0xe50 [vmw_vsock_virtio_transport_common] ? detach_buf_split+0xf1/0x130 virtio_transport_rx_work+0xba/0x130 [vmw_vsock_virtio_transport] process_one_work+0x1c0/0x300 worker_thread+0x45/0x3c0 kthread+0xfc/0x130 ? current_work+0x40/0x40 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: sunrpc kvm_intel kvm vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common irqbypass vsock virtio_rng rng_core CR2: 00000000000000e8 ---[ end trace e75400e2ea2fa824 ]--- This happens because virtio_transport_reset() calls virtio_transport_send_pkt_info() that can be used only on connecting/connected sockets. This patch fixes the issue, using virtio_transport_reset_no_sock() instead of virtio_transport_reset() when we are handling a listener socket. Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-14 02:48:00 +08:00
virtio_transport_reset_no_sock(t, pkt);
return -ENOMEM;
}
sk_acceptq_added(sk);
lock_sock_nested(child, SINGLE_DEPTH_NESTING);
child->sk_state = TCP_ESTABLISHED;
vchild = vsock_sk(child);
vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port));
vsock_addr_init(&vchild->remote_addr, le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
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 17:57:46 +08:00
ret = vsock_assign_transport(vchild, vsk);
/* Transport assigned (looking at remote_addr) must be the same
* where we received the request.
*/
if (ret || vchild->transport != &t->transport) {
release_sock(child);
vsock/virtio: fix null-pointer dereference in virtio_transport_recv_listen() With multi-transport support, listener sockets are not bound to any transport. So, calling virtio_transport_reset(), when an error occurs, on a listener socket produces the following null-pointer dereference: BUG: kernel NULL pointer dereference, address: 00000000000000e8 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 20 Comm: kworker/0:1 Not tainted 5.5.0-rc1-ste-00003-gb4be21f316ac-dirty #56 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 Workqueue: virtio_vsock virtio_transport_rx_work [vmw_vsock_virtio_transport] RIP: 0010:virtio_transport_send_pkt_info+0x20/0x130 [vmw_vsock_virtio_transport_common] Code: 1f 84 00 00 00 00 00 0f 1f 00 55 48 89 e5 41 57 41 56 41 55 49 89 f5 41 54 49 89 fc 53 48 83 ec 10 44 8b 76 20 e8 c0 ba fe ff <48> 8b 80 e8 00 00 00 e8 64 e3 7d c1 45 8b 45 00 41 8b 8c 24 d4 02 RSP: 0018:ffffc900000b7d08 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff88807bf12728 RCX: 0000000000000000 RDX: ffff88807bf12700 RSI: ffffc900000b7d50 RDI: ffff888035c84000 RBP: ffffc900000b7d40 R08: ffff888035c84000 R09: ffffc900000b7d08 R10: ffff8880781de800 R11: 0000000000000018 R12: ffff888035c84000 R13: ffffc900000b7d50 R14: 0000000000000000 R15: ffff88807bf12724 FS: 0000000000000000(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e8 CR3: 00000000790f4004 CR4: 0000000000160ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: virtio_transport_reset+0x59/0x70 [vmw_vsock_virtio_transport_common] virtio_transport_recv_pkt+0x5bb/0xe50 [vmw_vsock_virtio_transport_common] ? detach_buf_split+0xf1/0x130 virtio_transport_rx_work+0xba/0x130 [vmw_vsock_virtio_transport] process_one_work+0x1c0/0x300 worker_thread+0x45/0x3c0 kthread+0xfc/0x130 ? current_work+0x40/0x40 ? kthread_park+0x90/0x90 ret_from_fork+0x35/0x40 Modules linked in: sunrpc kvm_intel kvm vmw_vsock_virtio_transport vmw_vsock_virtio_transport_common irqbypass vsock virtio_rng rng_core CR2: 00000000000000e8 ---[ end trace e75400e2ea2fa824 ]--- This happens because virtio_transport_reset() calls virtio_transport_send_pkt_info() that can be used only on connecting/connected sockets. This patch fixes the issue, using virtio_transport_reset_no_sock() instead of virtio_transport_reset() when we are handling a listener socket. Fixes: c0cfa2d8a788 ("vsock: add multi-transports support") Signed-off-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-14 02:48:00 +08:00
virtio_transport_reset_no_sock(t, pkt);
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 17:57:46 +08:00
sock_put(child);
return ret;
}
if (virtio_transport_space_update(child, pkt))
child->sk_write_space(child);
vsock_insert_connected(vchild);
vsock_enqueue_accept(sk, child);
virtio_transport_send_response(vchild, pkt);
release_sock(child);
sk->sk_data_ready(sk);
return 0;
}
/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
* lock.
*/
void virtio_transport_recv_pkt(struct virtio_transport *t,
struct virtio_vsock_pkt *pkt)
{
struct sockaddr_vm src, dst;
struct vsock_sock *vsk;
struct sock *sk;
bool space_available;
vsock_addr_init(&src, le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
vsock_addr_init(&dst, le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port));
trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
dst.svm_cid, dst.svm_port,
le32_to_cpu(pkt->hdr.len),
le16_to_cpu(pkt->hdr.type),
le16_to_cpu(pkt->hdr.op),
le32_to_cpu(pkt->hdr.flags),
le32_to_cpu(pkt->hdr.buf_alloc),
le32_to_cpu(pkt->hdr.fwd_cnt));
if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
(void)virtio_transport_reset_no_sock(t, pkt);
goto free_pkt;
}
/* The socket must be in connected or bound table
* otherwise send reset back
*/
sk = vsock_find_connected_socket(&src, &dst);
if (!sk) {
sk = vsock_find_bound_socket(&dst);
if (!sk) {
(void)virtio_transport_reset_no_sock(t, pkt);
goto free_pkt;
}
}
vsk = vsock_sk(sk);
space_available = virtio_transport_space_update(sk, pkt);
lock_sock(sk);
virtio_vsock: Fix race condition in virtio_transport_recv_pkt When client on the host tries to connect(SOCK_STREAM, O_NONBLOCK) to the server on the guest, there will be a panic on a ThunderX2 (armv8a server): [ 463.718844] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 463.718848] Mem abort info: [ 463.718849] ESR = 0x96000044 [ 463.718852] EC = 0x25: DABT (current EL), IL = 32 bits [ 463.718853] SET = 0, FnV = 0 [ 463.718854] EA = 0, S1PTW = 0 [ 463.718855] Data abort info: [ 463.718856] ISV = 0, ISS = 0x00000044 [ 463.718857] CM = 0, WnR = 1 [ 463.718859] user pgtable: 4k pages, 48-bit VAs, pgdp=0000008f6f6e9000 [ 463.718861] [0000000000000000] pgd=0000000000000000 [ 463.718866] Internal error: Oops: 96000044 [#1] SMP [...] [ 463.718977] CPU: 213 PID: 5040 Comm: vhost-5032 Tainted: G O 5.7.0-rc7+ #139 [ 463.718980] Hardware name: GIGABYTE R281-T91-00/MT91-FS1-00, BIOS F06 09/25/2018 [ 463.718982] pstate: 60400009 (nZCv daif +PAN -UAO) [ 463.718995] pc : virtio_transport_recv_pkt+0x4c8/0xd40 [vmw_vsock_virtio_transport_common] [ 463.718999] lr : virtio_transport_recv_pkt+0x1fc/0xd40 [vmw_vsock_virtio_transport_common] [ 463.719000] sp : ffff80002dbe3c40 [...] [ 463.719025] Call trace: [ 463.719030] virtio_transport_recv_pkt+0x4c8/0xd40 [vmw_vsock_virtio_transport_common] [ 463.719034] vhost_vsock_handle_tx_kick+0x360/0x408 [vhost_vsock] [ 463.719041] vhost_worker+0x100/0x1a0 [vhost] [ 463.719048] kthread+0x128/0x130 [ 463.719052] ret_from_fork+0x10/0x18 The race condition is as follows: Task1 Task2 ===== ===== __sock_release virtio_transport_recv_pkt __vsock_release vsock_find_bound_socket (found sk) lock_sock_nested vsock_remove_sock sock_orphan sk_set_socket(sk, NULL) sk->sk_shutdown = SHUTDOWN_MASK ... release_sock lock_sock virtio_transport_recv_connecting sk->sk_socket->state (panic!) The root cause is that vsock_find_bound_socket can't hold the lock_sock, so there is a small race window between vsock_find_bound_socket() and lock_sock(). If __vsock_release() is running in another task, sk->sk_socket will be set to NULL inadvertently. This fixes it by checking sk->sk_shutdown(suggested by Stefano) after lock_sock since sk->sk_shutdown is set to SHUTDOWN_MASK under the protection of lock_sock_nested. Signed-off-by: Jia He <justin.he@arm.com> Reviewed-by: Stefano Garzarella <sgarzare@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-30 09:38:28 +08:00
/* Check if sk has been released before lock_sock */
if (sk->sk_shutdown == SHUTDOWN_MASK) {
(void)virtio_transport_reset_no_sock(t, pkt);
release_sock(sk);
sock_put(sk);
goto free_pkt;
}
/* Update CID in case it has changed after a transport reset event */
vsk->local_addr.svm_cid = dst.svm_cid;
if (space_available)
sk->sk_write_space(sk);
switch (sk->sk_state) {
case TCP_LISTEN:
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 17:57:46 +08:00
virtio_transport_recv_listen(sk, pkt, t);
virtio_transport_free_pkt(pkt);
break;
case TCP_SYN_SENT:
virtio_transport_recv_connecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
case TCP_ESTABLISHED:
virtio_transport_recv_connected(sk, pkt);
break;
case TCP_CLOSING:
virtio_transport_recv_disconnecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
default:
net: virtio_vsock: Enhance connection semantics Whenever the vsock backend on the host sends a packet through the RX queue, it expects an answer on the TX queue. Unfortunately, there is one case where the host side will hang waiting for the answer and might effectively never recover if no timeout mechanism was implemented. This issue happens when the guest side starts binding to the socket, which insert a new bound socket into the list of already bound sockets. At this time, we expect the guest to also start listening, which will trigger the sk_state to move from TCP_CLOSE to TCP_LISTEN. The problem occurs if the host side queued a RX packet and triggered an interrupt right between the end of the binding process and the beginning of the listening process. In this specific case, the function processing the packet virtio_transport_recv_pkt() will find a bound socket, which means it will hit the switch statement checking for the sk_state, but the state won't be changed into TCP_LISTEN yet, which leads the code to pick the default statement. This default statement will only free the buffer, while it should also respond to the host side, by sending a packet on its TX queue. In order to simply fix this unfortunate chain of events, it is important that in case the default statement is entered, and because at this stage we know the host side is waiting for an answer, we must send back a packet containing the operation VIRTIO_VSOCK_OP_RST. One could say that a proper timeout mechanism on the host side will be enough to avoid the backend to hang. But the point of this patch is to ensure the normal use case will be provided with proper responsiveness when it comes to establishing the connection. Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-02-14 19:48:01 +08:00
(void)virtio_transport_reset_no_sock(t, pkt);
virtio_transport_free_pkt(pkt);
break;
}
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 17:57:46 +08:00
release_sock(sk);
/* Release refcnt obtained when we fetched this socket out of the
* bound or connected list.
*/
sock_put(sk);
return;
free_pkt:
virtio_transport_free_pkt(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
{
kfree(pkt->buf);
kfree(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("common code for virtio vsock");