UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

vhost: cleanups and fixes for 3.10 

Here are vhost cleanups and fixes by Asias He and myself.
 They affect both vhost-net and vhost-scsi devices.
 They also *depend* on both net-next and target-pending,
 where the net and target commits these changes depend on
 are already merged.
 So merging through the common vhost tree.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1.4.13 (GNU/Linux)
 
 iQEcBAABAgAGBQJRgkPOAAoJECgfDbjSjVRp5n8H/jacEkZuZ9WPrNh0YOlmUU1M
 AHrqzdwSPTt5Ic/auqMGgZuMwjLAx22L0JxDjJ2sCjEva3oYajkgBD1q/ebZ09jw
 icemjmq0anXK8QC1gKC6g9olkfxvKAK+x/Tw6Y0WB4wq6zPm5yOJPBirKFx30FX8
 d8+U4QlyH0NijvohSBgKfxfko/dlIfLvsSb2TZu/fTde66xm+M+CE+9pdIyfGOuq
 mnsM7bzoZg7EN61YTi6d8pdgVbV7n6AqAYuJqmuILkARj2LvznjmoMUtxG7/SlAX
 nZYuRX2JRoay+cXEqg8T+lzCeXekXkedgx4L9cmn4zwjYL5PXVB1zLU9k8vU/y4=
 =dk7h
 -----END PGP SIGNATURE-----

Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull vhost cleanups and fixes from Michael Tsirkin:
 "Here are vhost cleanups and fixes by Asias He and myself.  They affect
  both vhost-net and vhost-scsi devices.  They also *depend* on both
  net-next and target-pending, where the net and target commits these
  changes depend on are already merged.  So merging through the common
  vhost tree."

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  vhost_scsi: module rename
  tcm_vhost: header split up
  vhost: src file renames
  vhost: fix error handling in RESET_OWNER ioctl
  tcm_vhost: remove virtio-net.h dependency
  vhost: move per-vq net specific fields out to net
  tcm_vhost: document inflight ref-counting use
  vhost: move vhost-net zerocopy fields to net.c
  tcm_vhost: Wait for pending requests in vhost_scsi_flush()
  vhost: Allow device specific fields per vq
This commit is contained in:
Linus Torvalds 2013-05-02 13:29:14 -07:00
parent 5a148af669 181c04a357
commit e958930041
10 changed files with 533 additions and 346 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/vhost/Kconfig
View File

@ -9,6 +9,10 @@ config VHOST_NET
To compile this driver as a module, choose M here: the module will
be called vhost_net.
if STAGING
source "drivers/vhost/Kconfig.tcm"
endif
config VHOST_SCSI
tristate "VHOST_SCSI TCM fabric driver"
depends on TARGET_CORE && EVENTFD && m
default n
---help---
Say M here to enable the vhost_scsi TCM fabric module
for use with virtio-scsi guests

6
drivers/vhost/Kconfig.tcm
View File

@ -1,6 +0,0 @@
config TCM_VHOST
tristate "TCM_VHOST fabric module"
depends on TARGET_CORE && EVENTFD && m
default n
---help---
Say M here to enable the TCM_VHOST fabric module for use with virtio-scsi guests

3
drivers/vhost/Makefile
View File

@ -1,4 +1,5 @@
obj-$(CONFIG_VHOST_NET) += vhost_net.o
vhost_net-y := vhost.o net.o
obj-$(CONFIG_TCM_VHOST) += tcm_vhost.o
obj-$(CONFIG_VHOST_SCSI) += vhost_scsi.o
vhost_scsi-y := scsi.o

255
drivers/vhost/net.c
View File

@ -64,9 +64,35 @@ enum {
VHOST_NET_VQ_MAX = 2,
};
struct vhost_ubuf_ref {
struct kref kref;
wait_queue_head_t wait;
struct vhost_virtqueue *vq;
};
struct vhost_net_virtqueue {
struct vhost_virtqueue vq;
/* hdr is used to store the virtio header.
* Since each iovec has >= 1 byte length, we never need more than
* header length entries to store the header. */
struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)];
size_t vhost_hlen;
size_t sock_hlen;
/* vhost zerocopy support fields below: */
/* last used idx for outstanding DMA zerocopy buffers */
int upend_idx;
/* first used idx for DMA done zerocopy buffers */
int done_idx;
/* an array of userspace buffers info */
struct ubuf_info *ubuf_info;
/* Reference counting for outstanding ubufs.
* Protected by vq mutex. Writers must also take device mutex. */
struct vhost_ubuf_ref *ubufs;
};
struct vhost_net {
struct vhost_dev dev;
struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
struct vhost_net_virtqueue vqs[VHOST_NET_VQ_MAX];
struct vhost_poll poll[VHOST_NET_VQ_MAX];
/* Number of TX recently submitted.
* Protected by tx vq lock. */
@ -78,6 +104,90 @@ struct vhost_net {
bool tx_flush;
};
static unsigned vhost_zcopy_mask __read_mostly;
void vhost_enable_zcopy(int vq)
{
vhost_zcopy_mask |= 0x1 << vq;
}
static void vhost_zerocopy_done_signal(struct kref *kref)
{
struct vhost_ubuf_ref *ubufs = container_of(kref, struct vhost_ubuf_ref,
kref);
wake_up(&ubufs->wait);
}
struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *vq,
bool zcopy)
{
struct vhost_ubuf_ref *ubufs;
/* No zero copy backend? Nothing to count. */
if (!zcopy)
return NULL;
ubufs = kmalloc(sizeof(*ubufs), GFP_KERNEL);
if (!ubufs)
return ERR_PTR(-ENOMEM);
kref_init(&ubufs->kref);
init_waitqueue_head(&ubufs->wait);
ubufs->vq = vq;
return ubufs;
}
void vhost_ubuf_put(struct vhost_ubuf_ref *ubufs)
{
kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
}
void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
{
kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
kfree(ubufs);
}
int vhost_net_set_ubuf_info(struct vhost_net *n)
{
bool zcopy;
int i;
for (i = 0; i < n->dev.nvqs; ++i) {
zcopy = vhost_zcopy_mask & (0x1 << i);
if (!zcopy)
continue;
n->vqs[i].ubuf_info = kmalloc(sizeof(*n->vqs[i].ubuf_info) *
UIO_MAXIOV, GFP_KERNEL);
if (!n->vqs[i].ubuf_info)
goto err;
}
return 0;
err:
while (i--) {
zcopy = vhost_zcopy_mask & (0x1 << i);
if (!zcopy)
continue;
kfree(n->vqs[i].ubuf_info);
}
return -ENOMEM;
}
void vhost_net_vq_reset(struct vhost_net *n)
{
int i;
for (i = 0; i < VHOST_NET_VQ_MAX; i++) {
n->vqs[i].done_idx = 0;
n->vqs[i].upend_idx = 0;
n->vqs[i].ubufs = NULL;
kfree(n->vqs[i].ubuf_info);
n->vqs[i].ubuf_info = NULL;
n->vqs[i].vhost_hlen = 0;
n->vqs[i].sock_hlen = 0;
}
}
static void vhost_net_tx_packet(struct vhost_net *net)
{
++net->tx_packets;
@ -153,10 +263,12 @@ static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
static int vhost_zerocopy_signal_used(struct vhost_net *net,
struct vhost_virtqueue *vq)
{
struct vhost_net_virtqueue *nvq =
container_of(vq, struct vhost_net_virtqueue, vq);
int i;
int j = 0;
for (i = vq->done_idx; i != vq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
if (vq->heads[i].len == VHOST_DMA_FAILED_LEN)
vhost_net_tx_err(net);
if (VHOST_DMA_IS_DONE(vq->heads[i].len)) {
@ -168,7 +280,7 @@ static int vhost_zerocopy_signal_used(struct vhost_net *net,
break;
}
if (j)
vq->done_idx = i;
nvq->done_idx = i;
return j;
}
@ -198,7 +310,8 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned out, in, s;
int head;
struct msghdr msg = {
@ -224,8 +337,8 @@ static void handle_tx(struct vhost_net *net)
mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
hdr_size = vq->vhost_hlen;
zcopy = vq->ubufs;
hdr_size = nvq->vhost_hlen;
zcopy = nvq->ubufs;
for (;;) {
/* Release DMAs done buffers first */
@ -246,9 +359,10 @@ static void handle_tx(struct vhost_net *net)
/* If more outstanding DMAs, queue the work.
* Handle upend_idx wrap around
*/
num_pends = likely(vq->upend_idx >= vq->done_idx) ?
(vq->upend_idx - vq->done_idx) :
(vq->upend_idx + UIO_MAXIOV - vq->done_idx);
num_pends = likely(nvq->upend_idx >= nvq->done_idx) ?
(nvq->upend_idx - nvq->done_idx) :
(nvq->upend_idx + UIO_MAXIOV -
nvq->done_idx);
if (unlikely(num_pends > VHOST_MAX_PEND))
break;
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
@ -263,45 +377,45 @@ static void handle_tx(struct vhost_net *net)
break;
}
/* Skip header. TODO: support TSO. */
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out);
msg.msg_iovlen = out;
len = iov_length(vq->iov, out);
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
iov_length(vq->hdr, s), hdr_size);
iov_length(nvq->hdr, s), hdr_size);
break;
}
zcopy_used = zcopy && (len >= VHOST_GOODCOPY_LEN ||
vq->upend_idx != vq->done_idx);
nvq->upend_idx != nvq->done_idx);
/* use msg_control to pass vhost zerocopy ubuf info to skb */
if (zcopy_used) {
vq->heads[vq->upend_idx].id = head;
vq->heads[nvq->upend_idx].id = head;
if (!vhost_net_tx_select_zcopy(net) ||
len < VHOST_GOODCOPY_LEN) {
/* copy don't need to wait for DMA done */
vq->heads[vq->upend_idx].len =
vq->heads[nvq->upend_idx].len =
VHOST_DMA_DONE_LEN;
msg.msg_control = NULL;
msg.msg_controllen = 0;
ubufs = NULL;
} else {
struct ubuf_info *ubuf;
ubuf = vq->ubuf_info + vq->upend_idx;
ubuf = nvq->ubuf_info + nvq->upend_idx;
vq->heads[vq->upend_idx].len =
vq->heads[nvq->upend_idx].len =
VHOST_DMA_IN_PROGRESS;
ubuf->callback = vhost_zerocopy_callback;
ubuf->ctx = vq->ubufs;
ubuf->desc = vq->upend_idx;
ubuf->ctx = nvq->ubufs;
ubuf->desc = nvq->upend_idx;
msg.msg_control = ubuf;
msg.msg_controllen = sizeof(ubuf);
ubufs = vq->ubufs;
ubufs = nvq->ubufs;
kref_get(&ubufs->kref);
}
vq->upend_idx = (vq->upend_idx + 1) % UIO_MAXIOV;
nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
@ -309,8 +423,8 @@ static void handle_tx(struct vhost_net *net)
if (zcopy_used) {
if (ubufs)
vhost_ubuf_put(ubufs);
vq->upend_idx = ((unsigned)vq->upend_idx - 1) %
UIO_MAXIOV;
nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
% UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
break;
@ -417,7 +531,8 @@ err:
* read-size critical section for our kind of RCU. */
static void handle_rx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned uninitialized_var(in), log;
struct vhost_log *vq_log;
struct msghdr msg = {
@ -445,8 +560,8 @@ static void handle_rx(struct vhost_net *net)
mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
vhost_hlen = vq->vhost_hlen;
sock_hlen = vq->sock_hlen;
vhost_hlen = nvq->vhost_hlen;
sock_hlen = nvq->sock_hlen;
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
@ -476,11 +591,11 @@ static void handle_rx(struct vhost_net *net)
/* We don't need to be notified again. */
if (unlikely((vhost_hlen)))
/* Skip header. TODO: support TSO. */
move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
move_iovec_hdr(vq->iov, nvq->hdr, vhost_hlen, in);
else
/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
* needed because recvmsg can modify msg_iov. */
copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in);
msg.msg_iovlen = in;
err = sock->ops->recvmsg(NULL, sock, &msg,
sock_len, MSG_DONTWAIT | MSG_TRUNC);
@ -494,7 +609,7 @@ static void handle_rx(struct vhost_net *net)
continue;
}
if (unlikely(vhost_hlen) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&hdr, 0,
memcpy_toiovecend(nvq->hdr, (unsigned char *)&hdr, 0,
vhost_hlen)) {
vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
vq->iov->iov_base);
@ -502,7 +617,7 @@ static void handle_rx(struct vhost_net *net)
}
/* TODO: Should check and handle checksum. */
if (likely(mergeable) &&
memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount,
offsetof(typeof(hdr), num_buffers),
sizeof hdr.num_buffers)) {
vq_err(vq, "Failed num_buffers write");
@ -559,17 +674,34 @@ static int vhost_net_open(struct inode *inode, struct file *f)
{
struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
struct vhost_dev *dev;
int r;
struct vhost_virtqueue **vqs;
int r, i;
if (!n)
return -ENOMEM;
vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
if (!vqs) {
kfree(n);
return -ENOMEM;
}
dev = &n->dev;
n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
r = vhost_dev_init(dev, n->vqs, VHOST_NET_VQ_MAX);
vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq;
vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq;
n->vqs[VHOST_NET_VQ_TX].vq.handle_kick = handle_tx_kick;
n->vqs[VHOST_NET_VQ_RX].vq.handle_kick = handle_rx_kick;
for (i = 0; i < VHOST_NET_VQ_MAX; i++) {
n->vqs[i].ubufs = NULL;
n->vqs[i].ubuf_info = NULL;
n->vqs[i].upend_idx = 0;
n->vqs[i].done_idx = 0;
n->vqs[i].vhost_hlen = 0;
n->vqs[i].sock_hlen = 0;
}
r = vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
if (r < 0) {
kfree(n);
kfree(vqs);
return r;
}
@ -584,7 +716,9 @@ static int vhost_net_open(struct inode *inode, struct file *f)
static void vhost_net_disable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct vhost_poll *poll = n->poll + (vq - n->vqs);
struct vhost_net_virtqueue *nvq =
container_of(vq, struct vhost_net_virtqueue, vq);
struct vhost_poll *poll = n->poll + (nvq - n->vqs);
if (!vq->private_data)
return;
vhost_poll_stop(poll);
@ -593,7 +727,9 @@ static void vhost_net_disable_vq(struct vhost_net *n,
static int vhost_net_enable_vq(struct vhost_net *n,
struct vhost_virtqueue *vq)
{
struct vhost_poll *poll = n->poll + (vq - n->vqs);
struct vhost_net_virtqueue *nvq =
container_of(vq, struct vhost_net_virtqueue, vq);
struct vhost_poll *poll = n->poll + (nvq - n->vqs);
struct socket *sock;
sock = rcu_dereference_protected(vq->private_data,
@ -621,30 +757,30 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n,
static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
struct socket **rx_sock)
{
*tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
*rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
*tx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_TX].vq);
*rx_sock = vhost_net_stop_vq(n, &n->vqs[VHOST_NET_VQ_RX].vq);
}
static void vhost_net_flush_vq(struct vhost_net *n, int index)
{
vhost_poll_flush(n->poll + index);
vhost_poll_flush(&n->dev.vqs[index].poll);
vhost_poll_flush(&n->vqs[index].vq.poll);
}
static void vhost_net_flush(struct vhost_net *n)
{
vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
if (n->dev.vqs[VHOST_NET_VQ_TX].ubufs) {
mutex_lock(&n->dev.vqs[VHOST_NET_VQ_TX].mutex);
if (n->vqs[VHOST_NET_VQ_TX].ubufs) {
mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
n->tx_flush = true;
mutex_unlock(&n->dev.vqs[VHOST_NET_VQ_TX].mutex);
mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
/* Wait for all lower device DMAs done. */
vhost_ubuf_put_and_wait(n->dev.vqs[VHOST_NET_VQ_TX].ubufs);
mutex_lock(&n->dev.vqs[VHOST_NET_VQ_TX].mutex);
vhost_ubuf_put_and_wait(n->vqs[VHOST_NET_VQ_TX].ubufs);
mutex_lock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
n->tx_flush = false;
kref_init(&n->dev.vqs[VHOST_NET_VQ_TX].ubufs->kref);
mutex_unlock(&n->dev.vqs[VHOST_NET_VQ_TX].mutex);
kref_init(&n->vqs[VHOST_NET_VQ_TX].ubufs->kref);
mutex_unlock(&n->vqs[VHOST_NET_VQ_TX].vq.mutex);
}
}
@ -658,6 +794,7 @@ static int vhost_net_release(struct inode *inode, struct file *f)
vhost_net_flush(n);
vhost_dev_stop(&n->dev);
vhost_dev_cleanup(&n->dev, false);
vhost_net_vq_reset(n);
if (tx_sock)
fput(tx_sock->file);
if (rx_sock)
@ -665,6 +802,7 @@ static int vhost_net_release(struct inode *inode, struct file *f)
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
kfree(n->dev.vqs);
kfree(n);
return 0;
}
@ -738,6 +876,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
struct vhost_net_virtqueue *nvq;
struct vhost_ubuf_ref *ubufs, *oldubufs = NULL;
int r;
@ -750,7 +889,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
r = -ENOBUFS;
goto err;
}
vq = n->vqs + index;
vq = &n->vqs[index].vq;
nvq = &n->vqs[index];
mutex_lock(&vq->mutex);
/* Verify that ring has been setup correctly. */
@ -783,8 +923,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
if (r)
goto err_used;
oldubufs = vq->ubufs;
vq->ubufs = ubufs;
oldubufs = nvq->ubufs;
nvq->ubufs = ubufs;
n->tx_packets = 0;
n->tx_zcopy_err = 0;
@ -827,14 +967,21 @@ static long vhost_net_reset_owner(struct vhost_net *n)
struct socket *tx_sock = NULL;
struct socket *rx_sock = NULL;
long err;
struct vhost_memory *memory;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
memory = vhost_dev_reset_owner_prepare();
if (!memory) {
err = -ENOMEM;
goto done;
}
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
err = vhost_dev_reset_owner(&n->dev);
vhost_dev_reset_owner(&n->dev, memory);
vhost_net_vq_reset(n);
done:
mutex_unlock(&n->dev.mutex);
if (tx_sock)
@ -870,10 +1017,10 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
n->dev.acked_features = features;
smp_wmb();
for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
mutex_lock(&n->vqs[i].mutex);
mutex_lock(&n->vqs[i].vq.mutex);
n->vqs[i].vhost_hlen = vhost_hlen;
n->vqs[i].sock_hlen = sock_hlen;
mutex_unlock(&n->vqs[i].mutex);
mutex_unlock(&n->vqs[i].vq.mutex);
}
vhost_net_flush(n);
mutex_unlock(&n->dev.mutex);
@ -910,11 +1057,17 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
return vhost_net_reset_owner(n);
default:
mutex_lock(&n->dev.mutex);
if (ioctl == VHOST_SET_OWNER) {
r = vhost_net_set_ubuf_info(n);
if (r)
goto out;
}
r = vhost_dev_ioctl(&n->dev, ioctl, argp);
if (r == -ENOIOCTLCMD)
r = vhost_vring_ioctl(&n->dev, ioctl, argp);
else
vhost_net_flush(n);
out:
mutex_unlock(&n->dev.mutex);
return r;
}

255
drivers/vhost/tcm_vhost.c → drivers/vhost/scsi.c
View File

@ -45,14 +45,116 @@
#include <target/target_core_configfs.h>
#include <target/configfs_macros.h>
#include <linux/vhost.h>
#include <linux/virtio_net.h> /* TODO vhost.h currently depends on this */
#include <linux/virtio_scsi.h>
#include <linux/llist.h>
#include <linux/bitmap.h>
#include "vhost.c"
#include "vhost.h"
#include "tcm_vhost.h"
#define TCM_VHOST_VERSION "v0.1"
#define TCM_VHOST_NAMELEN 256
#define TCM_VHOST_MAX_CDB_SIZE 32
struct vhost_scsi_inflight {
/* Wait for the flush operation to finish */
struct completion comp;
/* Refcount for the inflight reqs */
struct kref kref;
};
struct tcm_vhost_cmd {
/* Descriptor from vhost_get_vq_desc() for virt_queue segment */
int tvc_vq_desc;
/* virtio-scsi initiator task attribute */
int tvc_task_attr;
/* virtio-scsi initiator data direction */
enum dma_data_direction tvc_data_direction;
/* Expected data transfer length from virtio-scsi header */
u32 tvc_exp_data_len;
/* The Tag from include/linux/virtio_scsi.h:struct virtio_scsi_cmd_req */
u64 tvc_tag;
/* The number of scatterlists associated with this cmd */
u32 tvc_sgl_count;
/* Saved unpacked SCSI LUN for tcm_vhost_submission_work() */
u32 tvc_lun;
/* Pointer to the SGL formatted memory from virtio-scsi */
struct scatterlist *tvc_sgl;
/* Pointer to response */
struct virtio_scsi_cmd_resp __user *tvc_resp;
/* Pointer to vhost_scsi for our device */
struct vhost_scsi *tvc_vhost;
/* Pointer to vhost_virtqueue for the cmd */
struct vhost_virtqueue *tvc_vq;
/* Pointer to vhost nexus memory */
struct tcm_vhost_nexus *tvc_nexus;
/* The TCM I/O descriptor that is accessed via container_of() */
struct se_cmd tvc_se_cmd;
/* work item used for cmwq dispatch to tcm_vhost_submission_work() */
struct work_struct work;
/* Copy of the incoming SCSI command descriptor block (CDB) */
unsigned char tvc_cdb[TCM_VHOST_MAX_CDB_SIZE];
/* Sense buffer that will be mapped into outgoing status */
unsigned char tvc_sense_buf[TRANSPORT_SENSE_BUFFER];
/* Completed commands list, serviced from vhost worker thread */
struct llist_node tvc_completion_list;
/* Used to track inflight cmd */
struct vhost_scsi_inflight *inflight;
};
struct tcm_vhost_nexus {
/* Pointer to TCM session for I_T Nexus */
struct se_session *tvn_se_sess;
};
struct tcm_vhost_nacl {
/* Binary World Wide unique Port Name for Vhost Initiator port */
u64 iport_wwpn;
/* ASCII formatted WWPN for Sas Initiator port */
char iport_name[TCM_VHOST_NAMELEN];
/* Returned by tcm_vhost_make_nodeacl() */
struct se_node_acl se_node_acl;
};
struct vhost_scsi;
struct tcm_vhost_tpg {
/* Vhost port target portal group tag for TCM */
u16 tport_tpgt;
/* Used to track number of TPG Port/Lun Links wrt to explict I_T Nexus shutdown */
int tv_tpg_port_count;
/* Used for vhost_scsi device reference to tpg_nexus, protected by tv_tpg_mutex */
int tv_tpg_vhost_count;
/* list for tcm_vhost_list */
struct list_head tv_tpg_list;
/* Used to protect access for tpg_nexus */
struct mutex tv_tpg_mutex;
/* Pointer to the TCM VHost I_T Nexus for this TPG endpoint */
struct tcm_vhost_nexus *tpg_nexus;
/* Pointer back to tcm_vhost_tport */
struct tcm_vhost_tport *tport;
/* Returned by tcm_vhost_make_tpg() */
struct se_portal_group se_tpg;
/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
struct vhost_scsi *vhost_scsi;
};
struct tcm_vhost_tport {
/* SCSI protocol the tport is providing */
u8 tport_proto_id;
/* Binary World Wide unique Port Name for Vhost Target port */
u64 tport_wwpn;
/* ASCII formatted WWPN for Vhost Target port */
char tport_name[TCM_VHOST_NAMELEN];
/* Returned by tcm_vhost_make_tport() */
struct se_wwn tport_wwn;
};
struct tcm_vhost_evt {
/* event to be sent to guest */
struct virtio_scsi_event event;
/* event list, serviced from vhost worker thread */
struct llist_node list;
};
enum {
VHOST_SCSI_VQ_CTL = 0,
@ -74,13 +176,28 @@ enum {
#define VHOST_SCSI_MAX_VQ 128
#define VHOST_SCSI_MAX_EVENT 128
struct vhost_scsi_virtqueue {
struct vhost_virtqueue vq;
/*
* Reference counting for inflight reqs, used for flush operation. At
* each time, one reference tracks new commands submitted, while we
* wait for another one to reach 0.
*/
struct vhost_scsi_inflight inflights[2];
/*
* Indicate current inflight in use, protected by vq->mutex.
* Writers must also take dev mutex and flush under it.
*/
int inflight_idx;
};
struct vhost_scsi {
/* Protected by vhost_scsi->dev.mutex */
struct tcm_vhost_tpg **vs_tpg;
char vs_vhost_wwpn[TRANSPORT_IQN_LEN];
struct vhost_dev dev;
struct vhost_virtqueue vqs[VHOST_SCSI_MAX_VQ];
struct vhost_scsi_virtqueue vqs[VHOST_SCSI_MAX_VQ];
struct vhost_work vs_completion_work; /* cmd completion work item */
struct llist_head vs_completion_list; /* cmd completion queue */
@ -107,6 +224,59 @@ static int iov_num_pages(struct iovec *iov)
((unsigned long)iov->iov_base & PAGE_MASK)) >> PAGE_SHIFT;
}
void tcm_vhost_done_inflight(struct kref *kref)
{
struct vhost_scsi_inflight *inflight;
inflight = container_of(kref, struct vhost_scsi_inflight, kref);
complete(&inflight->comp);
}
static void tcm_vhost_init_inflight(struct vhost_scsi *vs,
struct vhost_scsi_inflight *old_inflight[])
{
struct vhost_scsi_inflight *new_inflight;
struct vhost_virtqueue *vq;
int idx, i;
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i].vq;
mutex_lock(&vq->mutex);
/* store old infight */
idx = vs->vqs[i].inflight_idx;
if (old_inflight)
old_inflight[i] = &vs->vqs[i].inflights[idx];
/* setup new infight */
vs->vqs[i].inflight_idx = idx ^ 1;
new_inflight = &vs->vqs[i].inflights[idx ^ 1];
kref_init(&new_inflight->kref);
init_completion(&new_inflight->comp);
mutex_unlock(&vq->mutex);
}
}
static struct vhost_scsi_inflight *
tcm_vhost_get_inflight(struct vhost_virtqueue *vq)
{
struct vhost_scsi_inflight *inflight;
struct vhost_scsi_virtqueue *svq;
svq = container_of(vq, struct vhost_scsi_virtqueue, vq);
inflight = &svq->inflights[svq->inflight_idx];
kref_get(&inflight->kref);
return inflight;
}
static void tcm_vhost_put_inflight(struct vhost_scsi_inflight *inflight)
{
kref_put(&inflight->kref, tcm_vhost_done_inflight);
}
static int tcm_vhost_check_true(struct se_portal_group *se_tpg)
{
return 1;
@ -366,7 +536,7 @@ static void tcm_vhost_free_evt(struct vhost_scsi *vs, struct tcm_vhost_evt *evt)
static struct tcm_vhost_evt *tcm_vhost_allocate_evt(struct vhost_scsi *vs,
u32 event, u32 reason)
{
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT];
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
struct tcm_vhost_evt *evt;
if (vs->vs_events_nr > VHOST_SCSI_MAX_EVENT) {
@ -403,13 +573,15 @@ static void vhost_scsi_free_cmd(struct tcm_vhost_cmd *tv_cmd)
kfree(tv_cmd->tvc_sgl);
}
tcm_vhost_put_inflight(tv_cmd->inflight);
kfree(tv_cmd);
}
static void tcm_vhost_do_evt_work(struct vhost_scsi *vs,
struct tcm_vhost_evt *evt)
{
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT];
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
struct virtio_scsi_event *event = &evt->event;
struct virtio_scsi_event __user *eventp;
unsigned out, in;
@ -460,7 +632,7 @@ static void tcm_vhost_evt_work(struct vhost_work *work)
{
struct vhost_scsi *vs = container_of(work, struct vhost_scsi,
vs_event_work);
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT];
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
struct tcm_vhost_evt *evt;
struct llist_node *llnode;
@ -511,8 +683,10 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
v_rsp.sense_len);
ret = copy_to_user(tv_cmd->tvc_resp, &v_rsp, sizeof(v_rsp));
if (likely(ret == 0)) {
struct vhost_scsi_virtqueue *q;
vhost_add_used(tv_cmd->tvc_vq, tv_cmd->tvc_vq_desc, 0);
vq = tv_cmd->tvc_vq - vs->vqs;
q = container_of(tv_cmd->tvc_vq, struct vhost_scsi_virtqueue, vq);
vq = q - vs->vqs;
__set_bit(vq, signal);
} else
pr_err("Faulted on virtio_scsi_cmd_resp\n");
@ -523,10 +697,11 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work)
vq = -1;
while ((vq = find_next_bit(signal, VHOST_SCSI_MAX_VQ, vq + 1))
< VHOST_SCSI_MAX_VQ)
vhost_signal(&vs->dev, &vs->vqs[vq]);
vhost_signal(&vs->dev, &vs->vqs[vq].vq);
}
static struct tcm_vhost_cmd *vhost_scsi_allocate_cmd(
struct vhost_virtqueue *vq,
struct tcm_vhost_tpg *tv_tpg,
struct virtio_scsi_cmd_req *v_req,
u32 exp_data_len,
@ -551,6 +726,7 @@ static struct tcm_vhost_cmd *vhost_scsi_allocate_cmd(
tv_cmd->tvc_exp_data_len = exp_data_len;
tv_cmd->tvc_data_direction = data_direction;
tv_cmd->tvc_nexus = tv_nexus;
tv_cmd->inflight = tcm_vhost_get_inflight(vq);
return tv_cmd;
}
@ -806,7 +982,7 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs,
for (i = 0; i < data_num; i++)
exp_data_len += vq->iov[data_first + i].iov_len;
tv_cmd = vhost_scsi_allocate_cmd(tv_tpg, &v_req,
tv_cmd = vhost_scsi_allocate_cmd(vq, tv_tpg, &v_req,
exp_data_len, data_direction);
if (IS_ERR(tv_cmd)) {
vq_err(vq, "vhost_scsi_allocate_cmd failed %ld\n",
@ -938,17 +1114,35 @@ static void vhost_scsi_handle_kick(struct vhost_work *work)
static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index)
{
vhost_poll_flush(&vs->dev.vqs[index].poll);
vhost_poll_flush(&vs->vqs[index].vq.poll);
}
/* Callers must hold dev mutex */
static void vhost_scsi_flush(struct vhost_scsi *vs)
{
struct vhost_scsi_inflight *old_inflight[VHOST_SCSI_MAX_VQ];
int i;
/* Init new inflight and remember the old inflight */
tcm_vhost_init_inflight(vs, old_inflight);
/*
* The inflight->kref was initialized to 1. We decrement it here to
* indicate the start of the flush operation so that it will reach 0
* when all the reqs are finished.
*/
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
kref_put(&old_inflight[i]->kref, tcm_vhost_done_inflight);
/* Flush both the vhost poll and vhost work */
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
vhost_scsi_flush_vq(vs, i);
vhost_work_flush(&vs->dev, &vs->vs_completion_work);
vhost_work_flush(&vs->dev, &vs->vs_event_work);
/* Wait for all reqs issued before the flush to be finished */
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++)
wait_for_completion(&old_inflight[i]->comp);
}
/*
@ -975,7 +1169,7 @@ static int vhost_scsi_set_endpoint(
/* Verify that ring has been setup correctly. */
for (index = 0; index < vs->dev.nvqs; ++index) {
/* Verify that ring has been setup correctly. */
if (!vhost_vq_access_ok(&vs->vqs[index])) {
if (!vhost_vq_access_ok(&vs->vqs[index].vq)) {
ret = -EFAULT;
goto out;
}
@ -1022,7 +1216,7 @@ static int vhost_scsi_set_endpoint(
memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn,
sizeof(vs->vs_vhost_wwpn));
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i];
vq = &vs->vqs[i].vq;
/* Flushing the vhost_work acts as synchronize_rcu */
mutex_lock(&vq->mutex);
rcu_assign_pointer(vq->private_data, vs_tpg);
@ -1063,7 +1257,7 @@ static int vhost_scsi_clear_endpoint(
mutex_lock(&vs->dev.mutex);
/* Verify that ring has been setup correctly. */
for (index = 0; index < vs->dev.nvqs; ++index) {
if (!vhost_vq_access_ok(&vs->vqs[index])) {
if (!vhost_vq_access_ok(&vs->vqs[index].vq)) {
ret = -EFAULT;
goto err_dev;
}
@ -1103,7 +1297,7 @@ static int vhost_scsi_clear_endpoint(
}
if (match) {
for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
vq = &vs->vqs[i];
vq = &vs->vqs[i].vq;
/* Flushing the vhost_work acts as synchronize_rcu */
mutex_lock(&vq->mutex);
rcu_assign_pointer(vq->private_data, NULL);
@ -1151,24 +1345,39 @@ static int vhost_scsi_set_features(struct vhost_scsi *vs, u64 features)
static int vhost_scsi_open(struct inode *inode, struct file *f)
{
struct vhost_scsi *s;
struct vhost_virtqueue **vqs;
int r, i;
s = kzalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
vqs = kmalloc(VHOST_SCSI_MAX_VQ * sizeof(*vqs), GFP_KERNEL);
if (!vqs) {
kfree(s);
return -ENOMEM;
}
vhost_work_init(&s->vs_completion_work, vhost_scsi_complete_cmd_work);
vhost_work_init(&s->vs_event_work, tcm_vhost_evt_work);
s->vs_events_nr = 0;
s->vs_events_missed = false;
s->vqs[VHOST_SCSI_VQ_CTL].handle_kick = vhost_scsi_ctl_handle_kick;
s->vqs[VHOST_SCSI_VQ_EVT].handle_kick = vhost_scsi_evt_handle_kick;
for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++)
s->vqs[i].handle_kick = vhost_scsi_handle_kick;
r = vhost_dev_init(&s->dev, s->vqs, VHOST_SCSI_MAX_VQ);
vqs[VHOST_SCSI_VQ_CTL] = &s->vqs[VHOST_SCSI_VQ_CTL].vq;
vqs[VHOST_SCSI_VQ_EVT] = &s->vqs[VHOST_SCSI_VQ_EVT].vq;
s->vqs[VHOST_SCSI_VQ_CTL].vq.handle_kick = vhost_scsi_ctl_handle_kick;
s->vqs[VHOST_SCSI_VQ_EVT].vq.handle_kick = vhost_scsi_evt_handle_kick;
for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) {
vqs[i] = &s->vqs[i].vq;
s->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
}
r = vhost_dev_init(&s->dev, vqs, VHOST_SCSI_MAX_VQ);
tcm_vhost_init_inflight(s, NULL);
if (r < 0) {
kfree(vqs);
kfree(s);
return r;
}
@ -1190,6 +1399,7 @@ static int vhost_scsi_release(struct inode *inode, struct file *f)
vhost_dev_cleanup(&s->dev, false);
/* Jobs can re-queue themselves in evt kick handler. Do extra flush. */
vhost_scsi_flush(s);
kfree(s->dev.vqs);
kfree(s);
return 0;
}
@ -1205,7 +1415,7 @@ static long vhost_scsi_ioctl(struct file *f, unsigned int ioctl,
u32 events_missed;
u64 features;
int r, abi_version = VHOST_SCSI_ABI_VERSION;
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT];
struct vhost_virtqueue *vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
switch (ioctl) {
case VHOST_SCSI_SET_ENDPOINT:
@ -1333,7 +1543,7 @@ static void tcm_vhost_do_plug(struct tcm_vhost_tpg *tpg,
else
reason = VIRTIO_SCSI_EVT_RESET_REMOVED;
vq = &vs->vqs[VHOST_SCSI_VQ_EVT];
vq = &vs->vqs[VHOST_SCSI_VQ_EVT].vq;
mutex_lock(&vq->mutex);
tcm_vhost_send_evt(vs, tpg, lun,
VIRTIO_SCSI_T_TRANSPORT_RESET, reason);
@ -1926,7 +2136,8 @@ static void tcm_vhost_exit(void)
destroy_workqueue(tcm_vhost_workqueue);
};
MODULE_DESCRIPTION("TCM_VHOST series fabric driver");
MODULE_DESCRIPTION("VHOST_SCSI series fabric driver");
MODULE_ALIAS("tcm_vhost");
MODULE_LICENSE("GPL");
module_init(tcm_vhost_init);
module_exit(tcm_vhost_exit);

128
drivers/vhost/tcm_vhost.h
View File

@ -1,128 +0,0 @@
#define TCM_VHOST_VERSION "v0.1"
#define TCM_VHOST_NAMELEN 256
#define TCM_VHOST_MAX_CDB_SIZE 32
struct tcm_vhost_cmd {
/* Descriptor from vhost_get_vq_desc() for virt_queue segment */
int tvc_vq_desc;
/* virtio-scsi initiator task attribute */
int tvc_task_attr;
/* virtio-scsi initiator data direction */
enum dma_data_direction tvc_data_direction;
/* Expected data transfer length from virtio-scsi header */
u32 tvc_exp_data_len;
/* The Tag from include/linux/virtio_scsi.h:struct virtio_scsi_cmd_req */
u64 tvc_tag;
/* The number of scatterlists associated with this cmd */
u32 tvc_sgl_count;
/* Saved unpacked SCSI LUN for tcm_vhost_submission_work() */
u32 tvc_lun;
/* Pointer to the SGL formatted memory from virtio-scsi */
struct scatterlist *tvc_sgl;
/* Pointer to response */
struct virtio_scsi_cmd_resp __user *tvc_resp;
/* Pointer to vhost_scsi for our device */
struct vhost_scsi *tvc_vhost;
/* Pointer to vhost_virtqueue for the cmd */
struct vhost_virtqueue *tvc_vq;
/* Pointer to vhost nexus memory */
struct tcm_vhost_nexus *tvc_nexus;
/* The TCM I/O descriptor that is accessed via container_of() */
struct se_cmd tvc_se_cmd;
/* work item used for cmwq dispatch to tcm_vhost_submission_work() */
struct work_struct work;
/* Copy of the incoming SCSI command descriptor block (CDB) */
unsigned char tvc_cdb[TCM_VHOST_MAX_CDB_SIZE];
/* Sense buffer that will be mapped into outgoing status */
unsigned char tvc_sense_buf[TRANSPORT_SENSE_BUFFER];
/* Completed commands list, serviced from vhost worker thread */
struct llist_node tvc_completion_list;
};
struct tcm_vhost_nexus {
/* Pointer to TCM session for I_T Nexus */
struct se_session *tvn_se_sess;
};
struct tcm_vhost_nacl {
/* Binary World Wide unique Port Name for Vhost Initiator port */
u64 iport_wwpn;
/* ASCII formatted WWPN for Sas Initiator port */
char iport_name[TCM_VHOST_NAMELEN];
/* Returned by tcm_vhost_make_nodeacl() */
struct se_node_acl se_node_acl;
};
struct vhost_scsi;
struct tcm_vhost_tpg {
/* Vhost port target portal group tag for TCM */
u16 tport_tpgt;
/* Used to track number of TPG Port/Lun Links wrt to explict I_T Nexus shutdown */
int tv_tpg_port_count;
/* Used for vhost_scsi device reference to tpg_nexus, protected by tv_tpg_mutex */
int tv_tpg_vhost_count;
/* list for tcm_vhost_list */
struct list_head tv_tpg_list;
/* Used to protect access for tpg_nexus */
struct mutex tv_tpg_mutex;
/* Pointer to the TCM VHost I_T Nexus for this TPG endpoint */
struct tcm_vhost_nexus *tpg_nexus;
/* Pointer back to tcm_vhost_tport */
struct tcm_vhost_tport *tport;
/* Returned by tcm_vhost_make_tpg() */
struct se_portal_group se_tpg;
/* Pointer back to vhost_scsi, protected by tv_tpg_mutex */
struct vhost_scsi *vhost_scsi;
};
struct tcm_vhost_tport {
/* SCSI protocol the tport is providing */
u8 tport_proto_id;
/* Binary World Wide unique Port Name for Vhost Target port */
u64 tport_wwpn;
/* ASCII formatted WWPN for Vhost Target port */
char tport_name[TCM_VHOST_NAMELEN];
/* Returned by tcm_vhost_make_tport() */
struct se_wwn tport_wwn;
};
struct tcm_vhost_evt {
/* event to be sent to guest */
struct virtio_scsi_event event;
/* event list, serviced from vhost worker thread */
struct llist_node list;
};
/*
* As per request from MST, keep TCM_VHOST related ioctl defines out of
* linux/vhost.h (user-space) for now..
*/
#include <linux/vhost.h>
/*
* Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
*
* ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
* RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage
* ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
* All the targets under vhost_wwpn can be seen and used by guset.
*/
#define VHOST_SCSI_ABI_VERSION 1
struct vhost_scsi_target {
int abi_version;
char vhost_wwpn[TRANSPORT_IQN_LEN];
unsigned short vhost_tpgt;
unsigned short reserved;
};
/* VHOST_SCSI specific defines */
#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
/* Changing this breaks userspace. */
#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
/* Set and get the events missed flag */
#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)

9
drivers/vhost/test.c
View File

@ -219,13 +219,20 @@ static long vhost_test_reset_owner(struct vhost_test *n)
{
void *priv = NULL;
long err;
struct vhost_memory *memory;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
memory = vhost_dev_reset_owner_prepare();
if (!memory) {
err = -ENOMEM;
goto done;
}
vhost_test_stop(n, &priv);
vhost_test_flush(n);
err = vhost_dev_reset_owner(&n->dev);
vhost_dev_reset_owner(&n->dev, memory);
done:
mutex_unlock(&n->dev.mutex);
return err;

153
drivers/vhost/vhost.c
View File

@ -33,8 +33,6 @@ enum {
VHOST_MEMORY_F_LOG = 0x1,
};
static unsigned vhost_zcopy_mask __read_mostly;
#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
@ -181,8 +179,6 @@ static void vhost_vq_reset(struct vhost_dev *dev,
vq->used_flags = 0;
vq->log_used = false;
vq->log_addr = -1ull;
vq->vhost_hlen = 0;
vq->sock_hlen = 0;
vq->private_data = NULL;
vq->log_base = NULL;
vq->error_ctx = NULL;
@ -191,9 +187,6 @@ static void vhost_vq_reset(struct vhost_dev *dev,
vq->call_ctx = NULL;
vq->call = NULL;
vq->log_ctx = NULL;
vq->upend_idx = 0;
vq->done_idx = 0;
vq->ubufs = NULL;
}
static int vhost_worker(void *data)
@ -253,43 +246,29 @@ static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq)
vq->log = NULL;
kfree(vq->heads);
vq->heads = NULL;
kfree(vq->ubuf_info);
vq->ubuf_info = NULL;
}
void vhost_enable_zcopy(int vq)
{
vhost_zcopy_mask |= 0x1 << vq;
}
/* Helper to allocate iovec buffers for all vqs. */
static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
{
int i;
bool zcopy;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].indirect = kmalloc(sizeof *dev->vqs[i].indirect *
dev->vqs[i]->indirect = kmalloc(sizeof *dev->vqs[i]->indirect *
UIO_MAXIOV, GFP_KERNEL);
dev->vqs[i].log = kmalloc(sizeof *dev->vqs[i].log * UIO_MAXIOV,
dev->vqs[i]->log = kmalloc(sizeof *dev->vqs[i]->log * UIO_MAXIOV,
GFP_KERNEL);
dev->vqs[i].heads = kmalloc(sizeof *dev->vqs[i].heads *
dev->vqs[i]->heads = kmalloc(sizeof *dev->vqs[i]->heads *
UIO_MAXIOV, GFP_KERNEL);
zcopy = vhost_zcopy_mask & (0x1 << i);
if (zcopy)
dev->vqs[i].ubuf_info =
kmalloc(sizeof *dev->vqs[i].ubuf_info *
UIO_MAXIOV, GFP_KERNEL);
if (!dev->vqs[i].indirect || !dev->vqs[i].log ||
!dev->vqs[i].heads ||
(zcopy && !dev->vqs[i].ubuf_info))
if (!dev->vqs[i]->indirect || !dev->vqs[i]->log ||
!dev->vqs[i]->heads)
goto err_nomem;
}
return 0;
err_nomem:
for (; i >= 0; --i)
vhost_vq_free_iovecs(&dev->vqs[i]);
vhost_vq_free_iovecs(dev->vqs[i]);
return -ENOMEM;
}
@ -298,11 +277,11 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
int i;
for (i = 0; i < dev->nvqs; ++i)
vhost_vq_free_iovecs(&dev->vqs[i]);
vhost_vq_free_iovecs(dev->vqs[i]);
}
long vhost_dev_init(struct vhost_dev *dev,
struct vhost_virtqueue *vqs, int nvqs)
struct vhost_virtqueue **vqs, int nvqs)
{
int i;
@ -318,16 +297,15 @@ long vhost_dev_init(struct vhost_dev *dev,
dev->worker = NULL;
for (i = 0; i < dev->nvqs; ++i) {
dev->vqs[i].log = NULL;
dev->vqs[i].indirect = NULL;
dev->vqs[i].heads = NULL;
dev->vqs[i].ubuf_info = NULL;
dev->vqs[i].dev = dev;
mutex_init(&dev->vqs[i].mutex);
vhost_vq_reset(dev, dev->vqs + i);
if (dev->vqs[i].handle_kick)
vhost_poll_init(&dev->vqs[i].poll,
dev->vqs[i].handle_kick, POLLIN, dev);
dev->vqs[i]->log = NULL;
dev->vqs[i]->indirect = NULL;
dev->vqs[i]->heads = NULL;
dev->vqs[i]->dev = dev;
mutex_init(&dev->vqs[i]->mutex);
vhost_vq_reset(dev, dev->vqs[i]);
if (dev->vqs[i]->handle_kick)
vhost_poll_init(&dev->vqs[i]->poll,
dev->vqs[i]->handle_kick, POLLIN, dev);
}
return 0;
@ -408,21 +386,19 @@ err_mm:
return err;
}
/* Caller should have device mutex */
long vhost_dev_reset_owner(struct vhost_dev *dev)
struct vhost_memory *vhost_dev_reset_owner_prepare(void)
{
struct vhost_memory *memory;
/* Restore memory to default empty mapping. */
memory = kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
if (!memory)
return -ENOMEM;
return kmalloc(offsetof(struct vhost_memory, regions), GFP_KERNEL);
}
/* Caller should have device mutex */
void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_memory *memory)
{
vhost_dev_cleanup(dev, true);
/* Restore memory to default empty mapping. */
memory->nregions = 0;
RCU_INIT_POINTER(dev->memory, memory);
return 0;
}
void vhost_dev_stop(struct vhost_dev *dev)
@ -430,9 +406,9 @@ void vhost_dev_stop(struct vhost_dev *dev)
int i;
for (i = 0; i < dev->nvqs; ++i) {
if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
vhost_poll_stop(&dev->vqs[i].poll);
vhost_poll_flush(&dev->vqs[i].poll);
if (dev->vqs[i]->kick && dev->vqs[i]->handle_kick) {
vhost_poll_stop(&dev->vqs[i]->poll);
vhost_poll_flush(&dev->vqs[i]->poll);
}
}
}
@ -443,17 +419,17 @@ void vhost_dev_cleanup(struct vhost_dev *dev, bool locked)
int i;
for (i = 0; i < dev->nvqs; ++i) {
if (dev->vqs[i].error_ctx)
eventfd_ctx_put(dev->vqs[i].error_ctx);
if (dev->vqs[i].error)
fput(dev->vqs[i].error);
if (dev->vqs[i].kick)
fput(dev->vqs[i].kick);
if (dev->vqs[i].call_ctx)
eventfd_ctx_put(dev->vqs[i].call_ctx);
if (dev->vqs[i].call)
fput(dev->vqs[i].call);
vhost_vq_reset(dev, dev->vqs + i);
if (dev->vqs[i]->error_ctx)
eventfd_ctx_put(dev->vqs[i]->error_ctx);
if (dev->vqs[i]->error)
fput(dev->vqs[i]->error);
if (dev->vqs[i]->kick)
fput(dev->vqs[i]->kick);
if (dev->vqs[i]->call_ctx)
eventfd_ctx_put(dev->vqs[i]->call_ctx);
if (dev->vqs[i]->call)
fput(dev->vqs[i]->call);
vhost_vq_reset(dev, dev->vqs[i]);
}
vhost_dev_free_iovecs(dev);
if (dev->log_ctx)
@ -524,14 +500,14 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
for (i = 0; i < d->nvqs; ++i) {
int ok;
mutex_lock(&d->vqs[i].mutex);
mutex_lock(&d->vqs[i]->mutex);
/* If ring is inactive, will check when it's enabled. */
if (d->vqs[i].private_data)
ok = vq_memory_access_ok(d->vqs[i].log_base, mem,
if (d->vqs[i]->private_data)
ok = vq_memory_access_ok(d->vqs[i]->log_base, mem,
log_all);
else
ok = 1;
mutex_unlock(&d->vqs[i].mutex);
mutex_unlock(&d->vqs[i]->mutex);
if (!ok)
return 0;
}
@ -641,7 +617,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
if (idx >= d->nvqs)
return -ENOBUFS;
vq = d->vqs + idx;
vq = d->vqs[idx];
mutex_lock(&vq->mutex);
@ -852,7 +828,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
for (i = 0; i < d->nvqs; ++i) {
struct vhost_virtqueue *vq;
void __user *base = (void __user *)(unsigned long)p;
vq = d->vqs + i;
vq = d->vqs[i];
mutex_lock(&vq->mutex);
/* If ring is inactive, will check when it's enabled. */
if (vq->private_data && !vq_log_access_ok(d, vq, base))
@ -879,9 +855,9 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp)
} else
filep = eventfp;
for (i = 0; i < d->nvqs; ++i) {
mutex_lock(&d->vqs[i].mutex);
d->vqs[i].log_ctx = d->log_ctx;
mutex_unlock(&d->vqs[i].mutex);
mutex_lock(&d->vqs[i]->mutex);
d->vqs[i]->log_ctx = d->log_ctx;
mutex_unlock(&d->vqs[i]->mutex);
}
if (ctx)
eventfd_ctx_put(ctx);
@ -1551,38 +1527,3 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
&vq->used->flags, r);
}
}
static void vhost_zerocopy_done_signal(struct kref *kref)
{
struct vhost_ubuf_ref *ubufs = container_of(kref, struct vhost_ubuf_ref,
kref);
wake_up(&ubufs->wait);
}
struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *vq,
bool zcopy)
{
struct vhost_ubuf_ref *ubufs;
/* No zero copy backend? Nothing to count. */
if (!zcopy)
return NULL;
ubufs = kmalloc(sizeof *ubufs, GFP_KERNEL);
if (!ubufs)
return ERR_PTR(-ENOMEM);
kref_init(&ubufs->kref);
init_waitqueue_head(&ubufs->wait);
ubufs->vq = vq;
return ubufs;
}
void vhost_ubuf_put(struct vhost_ubuf_ref *ubufs)
{
kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
}
void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
{
kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
kfree(ubufs);
}

32
drivers/vhost/vhost.h
View File

@ -54,18 +54,6 @@ struct vhost_log {
struct vhost_virtqueue;
struct vhost_ubuf_ref {
struct kref kref;
wait_queue_head_t wait;
struct vhost_virtqueue *vq;
};
struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *, bool zcopy);
void vhost_ubuf_put(struct vhost_ubuf_ref *);
void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *);
struct ubuf_info;
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
@ -114,10 +102,7 @@ struct vhost_virtqueue {
/* hdr is used to store the virtio header.
* Since each iovec has >= 1 byte length, we never need more than
* header length entries to store the header. */
struct iovec hdr[sizeof(struct virtio_net_hdr_mrg_rxbuf)];
struct iovec *indirect;
size_t vhost_hlen;
size_t sock_hlen;
struct vring_used_elem *heads;
/* We use a kind of RCU to access private pointer.
* All readers access it from worker, which makes it possible to
@ -130,16 +115,6 @@ struct vhost_virtqueue {
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
/* vhost zerocopy support fields below: */
/* last used idx for outstanding DMA zerocopy buffers */
int upend_idx;
/* first used idx for DMA done zerocopy buffers */
int done_idx;
/* an array of userspace buffers info */
struct ubuf_info *ubuf_info;
/* Reference counting for outstanding ubufs.
* Protected by vq mutex. Writers must also take device mutex. */
struct vhost_ubuf_ref *ubufs;
};
struct vhost_dev {
@ -150,7 +125,7 @@ struct vhost_dev {
struct mm_struct *mm;
struct mutex mutex;
unsigned acked_features;
struct vhost_virtqueue *vqs;
struct vhost_virtqueue **vqs;
int nvqs;
struct file *log_file;
struct eventfd_ctx *log_ctx;
@ -159,9 +134,10 @@ struct vhost_dev {
struct task_struct *worker;
};
long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
long vhost_dev_check_owner(struct vhost_dev *);
long vhost_dev_reset_owner(struct vhost_dev *);
struct vhost_memory *vhost_dev_reset_owner_prepare(void);
void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_memory *);
void vhost_dev_cleanup(struct vhost_dev *, bool locked);
void vhost_dev_stop(struct vhost_dev *);
long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);

28
include/uapi/linux/vhost.h
View File

@ -127,4 +127,32 @@ struct vhost_memory {
/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
#define VHOST_NET_F_VIRTIO_NET_HDR 27
/* VHOST_SCSI specific definitions */
/*
* Used by QEMU userspace to ensure a consistent vhost-scsi ABI.
*
* ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate +
* RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage
* ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target.
* All the targets under vhost_wwpn can be seen and used by guset.
*/
#define VHOST_SCSI_ABI_VERSION 1
struct vhost_scsi_target {
int abi_version;
char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */
unsigned short vhost_tpgt;
unsigned short reserved;
};
#define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target)
#define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target)
/* Changing this breaks userspace. */
#define VHOST_SCSI_GET_ABI_VERSION _IOW(VHOST_VIRTIO, 0x42, int)
/* Set and get the events missed flag */
#define VHOST_SCSI_SET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x43, __u32)
#define VHOST_SCSI_GET_EVENTS_MISSED _IOW(VHOST_VIRTIO, 0x44, __u32)
#endif