Commit 0803e040 authored by Linus Torvalds's avatar Linus Torvalds

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

Pull virtio/vhost updates from Michael Tsirkin:

 - new vsock device support in host and guest

 - platform IOMMU support in host and guest, including compatibility
   quirks for legacy systems.

 - misc fixes and cleanups.

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  VSOCK: Use kvfree()
  vhost: split out vringh Kconfig
  vhost: detect 32 bit integer wrap around
  vhost: new device IOTLB API
  vhost: drop vringh dependency
  vhost: convert pre sorted vhost memory array to interval tree
  vhost: introduce vhost memory accessors
  VSOCK: Add Makefile and Kconfig
  VSOCK: Introduce vhost_vsock.ko
  VSOCK: Introduce virtio_transport.ko
  VSOCK: Introduce virtio_vsock_common.ko
  VSOCK: defer sock removal to transports
  VSOCK: transport-specific vsock_transport functions
  vhost: drop vringh dependency
  vop: pull in vhost Kconfig
  virtio: new feature to detect IOMMU device quirk
  balloon: check the number of available pages in leak balloon
  vhost: lockless enqueuing
  vhost: simplify work flushing
parents 80fac0f5 b226acab
......@@ -12419,6 +12419,19 @@ S: Maintained
F: drivers/media/v4l2-core/videobuf2-*
F: include/media/videobuf2-*
VIRTIO AND VHOST VSOCK DRIVER
M: Stefan Hajnoczi <stefanha@redhat.com>
L: kvm@vger.kernel.org
L: virtualization@lists.linux-foundation.org
L: netdev@vger.kernel.org
S: Maintained
F: include/linux/virtio_vsock.h
F: include/uapi/linux/virtio_vsock.h
F: net/vmw_vsock/virtio_transport_common.c
F: net/vmw_vsock/virtio_transport.c
F: drivers/vhost/vsock.c
F: drivers/vhost/vsock.h
VIRTUAL SERIO DEVICE DRIVER
M: Stephen Chandler Paul <thatslyude@gmail.com>
S: Maintained
......
......@@ -138,6 +138,7 @@ obj-$(CONFIG_OF) += of/
obj-$(CONFIG_SSB) += ssb/
obj-$(CONFIG_BCMA) += bcma/
obj-$(CONFIG_VHOST_RING) += vhost/
obj-$(CONFIG_VHOST) += vhost/
obj-$(CONFIG_VLYNQ) += vlynq/
obj-$(CONFIG_STAGING) += staging/
obj-y += platform/
......
......@@ -146,3 +146,7 @@ config VOP
More information about the Intel MIC family as well as the Linux
OS and tools for MIC to use with this driver are available from
<http://software.intel.com/en-us/mic-developer>.
if VOP
source "drivers/vhost/Kconfig.vringh"
endif
......@@ -52,5 +52,5 @@ config CAIF_VIRTIO
The caif driver for CAIF over Virtio.
if CAIF_VIRTIO
source "drivers/vhost/Kconfig"
source "drivers/vhost/Kconfig.vringh"
endif
......@@ -2,7 +2,6 @@ config VHOST_NET
tristate "Host kernel accelerator for virtio net"
depends on NET && EVENTFD && (TUN || !TUN) && (MACVTAP || !MACVTAP)
select VHOST
select VHOST_RING
---help---
This kernel module can be loaded in host kernel to accelerate
guest networking with virtio_net. Not to be confused with virtio_net
......@@ -15,17 +14,24 @@ config VHOST_SCSI
tristate "VHOST_SCSI TCM fabric driver"
depends on TARGET_CORE && EVENTFD && m
select VHOST
select VHOST_RING
default n
---help---
Say M here to enable the vhost_scsi TCM fabric module
for use with virtio-scsi guests
config VHOST_RING
tristate
config VHOST_VSOCK
tristate "vhost virtio-vsock driver"
depends on VSOCKETS && EVENTFD
select VIRTIO_VSOCKETS_COMMON
select VHOST
default n
---help---
This option is selected by any driver which needs to access
the host side of a virtio ring.
This kernel module can be loaded in the host kernel to provide AF_VSOCK
sockets for communicating with guests. The guests must have the
virtio_transport.ko driver loaded to use the virtio-vsock device.
To compile this driver as a module, choose M here: the module will be called
vhost_vsock.
config VHOST
tristate
......
config VHOST_RING
tristate
---help---
This option is selected by any driver which needs to access
the host side of a virtio ring.
......@@ -4,5 +4,9 @@ vhost_net-y := net.o
obj-$(CONFIG_VHOST_SCSI) += vhost_scsi.o
vhost_scsi-y := scsi.o
obj-$(CONFIG_VHOST_VSOCK) += vhost_vsock.o
vhost_vsock-y := vsock.o
obj-$(CONFIG_VHOST_RING) += vringh.o
obj-$(CONFIG_VHOST) += vhost.o
......@@ -61,7 +61,8 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
enum {
VHOST_NET_FEATURES = VHOST_FEATURES |
(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
(1ULL << VIRTIO_NET_F_MRG_RXBUF)
(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
(1ULL << VIRTIO_F_IOMMU_PLATFORM)
};
enum {
......@@ -334,7 +335,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
{
unsigned long uninitialized_var(endtime);
int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
out_num, in_num, NULL, NULL);
out_num, in_num, NULL, NULL);
if (r == vq->num && vq->busyloop_timeout) {
preempt_disable();
......@@ -344,7 +345,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
cpu_relax_lowlatency();
preempt_enable();
r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
out_num, in_num, NULL, NULL);
out_num, in_num, NULL, NULL);
}
return r;
......@@ -377,6 +378,9 @@ static void handle_tx(struct vhost_net *net)
if (!sock)
goto out;
if (!vq_iotlb_prefetch(vq))
goto out;
vhost_disable_notify(&net->dev, vq);
hdr_size = nvq->vhost_hlen;
......@@ -652,6 +656,10 @@ static void handle_rx(struct vhost_net *net)
sock = vq->private_data;
if (!sock)
goto out;
if (!vq_iotlb_prefetch(vq))
goto out;
vhost_disable_notify(&net->dev, vq);
vhost_net_disable_vq(net, vq);
......@@ -1052,20 +1060,20 @@ 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;
struct vhost_umem *umem;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
memory = vhost_dev_reset_owner_prepare();
if (!memory) {
umem = vhost_dev_reset_owner_prepare();
if (!umem) {
err = -ENOMEM;
goto done;
}
vhost_net_stop(n, &tx_sock, &rx_sock);
vhost_net_flush(n);
vhost_dev_reset_owner(&n->dev, memory);
vhost_dev_reset_owner(&n->dev, umem);
vhost_net_vq_reset(n);
done:
mutex_unlock(&n->dev.mutex);
......@@ -1096,10 +1104,14 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
}
mutex_lock(&n->dev.mutex);
if ((features & (1 << VHOST_F_LOG_ALL)) &&
!vhost_log_access_ok(&n->dev)) {
mutex_unlock(&n->dev.mutex);
return -EFAULT;
!vhost_log_access_ok(&n->dev))
goto out_unlock;
if ((features & (1ULL << VIRTIO_F_IOMMU_PLATFORM))) {
if (vhost_init_device_iotlb(&n->dev, true))
goto out_unlock;
}
for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
mutex_lock(&n->vqs[i].vq.mutex);
n->vqs[i].vq.acked_features = features;
......@@ -1109,6 +1121,10 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
}
mutex_unlock(&n->dev.mutex);
return 0;
out_unlock:
mutex_unlock(&n->dev.mutex);
return -EFAULT;
}
static long vhost_net_set_owner(struct vhost_net *n)
......@@ -1182,9 +1198,40 @@ static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
}
#endif
static ssize_t vhost_net_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct vhost_net *n = file->private_data;
struct vhost_dev *dev = &n->dev;
int noblock = file->f_flags & O_NONBLOCK;
return vhost_chr_read_iter(dev, to, noblock);
}
static ssize_t vhost_net_chr_write_iter(struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct vhost_net *n = file->private_data;
struct vhost_dev *dev = &n->dev;
return vhost_chr_write_iter(dev, from);
}
static unsigned int vhost_net_chr_poll(struct file *file, poll_table *wait)
{
struct vhost_net *n = file->private_data;
struct vhost_dev *dev = &n->dev;
return vhost_chr_poll(file, dev, wait);
}
static const struct file_operations vhost_net_fops = {
.owner = THIS_MODULE,
.release = vhost_net_release,
.read_iter = vhost_net_chr_read_iter,
.write_iter = vhost_net_chr_write_iter,
.poll = vhost_net_chr_poll,
.unlocked_ioctl = vhost_net_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = vhost_net_compat_ioctl,
......
This diff is collapsed.
......@@ -15,13 +15,15 @@
struct vhost_work;
typedef void (*vhost_work_fn_t)(struct vhost_work *work);
#define VHOST_WORK_QUEUED 1
struct vhost_work {
struct list_head node;
struct llist_node node;
vhost_work_fn_t fn;
wait_queue_head_t done;
int flushing;
unsigned queue_seq;
unsigned done_seq;
unsigned long flags;
};
/* Poll a file (eventfd or socket) */
......@@ -53,6 +55,27 @@ struct vhost_log {
u64 len;
};
#define START(node) ((node)->start)
#define LAST(node) ((node)->last)
struct vhost_umem_node {
struct rb_node rb;
struct list_head link;
__u64 start;
__u64 last;
__u64 size;
__u64 userspace_addr;
__u32 perm;
__u32 flags_padding;
__u64 __subtree_last;
};
struct vhost_umem {
struct rb_root umem_tree;
struct list_head umem_list;
int numem;
};
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
......@@ -98,10 +121,12 @@ struct vhost_virtqueue {
u64 log_addr;
struct iovec iov[UIO_MAXIOV];
struct iovec iotlb_iov[64];
struct iovec *indirect;
struct vring_used_elem *heads;
/* Protected by virtqueue mutex. */
struct vhost_memory *memory;
struct vhost_umem *umem;
struct vhost_umem *iotlb;
void *private_data;
u64 acked_features;
/* Log write descriptors */
......@@ -118,25 +143,35 @@ struct vhost_virtqueue {
u32 busyloop_timeout;
};
struct vhost_msg_node {
struct vhost_msg msg;
struct vhost_virtqueue *vq;
struct list_head node;
};
struct vhost_dev {
struct vhost_memory *memory;
struct mm_struct *mm;
struct mutex mutex;
struct vhost_virtqueue **vqs;
int nvqs;
struct file *log_file;
struct eventfd_ctx *log_ctx;
spinlock_t work_lock;
struct list_head work_list;
struct llist_head work_list;
struct task_struct *worker;
struct vhost_umem *umem;
struct vhost_umem *iotlb;
spinlock_t iotlb_lock;
struct list_head read_list;
struct list_head pending_list;
wait_queue_head_t wait;
};
void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
long vhost_dev_set_owner(struct vhost_dev *dev);
bool vhost_dev_has_owner(struct vhost_dev *dev);
long vhost_dev_check_owner(struct vhost_dev *);
struct vhost_memory *vhost_dev_reset_owner_prepare(void);
void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_memory *);
struct vhost_umem *vhost_dev_reset_owner_prepare(void);
void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *);
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);
......@@ -165,6 +200,21 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len);
int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
void vhost_enqueue_msg(struct vhost_dev *dev,
struct list_head *head,
struct vhost_msg_node *node);
struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev,
struct list_head *head);
unsigned int vhost_chr_poll(struct file *file, struct vhost_dev *dev,
poll_table *wait);
ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
int noblock);
ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
struct iov_iter *from);
int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
#define vq_err(vq, fmt, ...) do { \
pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
......
/*
* vhost transport for vsock
*
* Copyright (C) 2013-2015 Red Hat, Inc.
* Author: Asias He <asias@redhat.com>
* Stefan Hajnoczi <stefanha@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2.
*/
#include <linux/miscdevice.h>
#include <linux/atomic.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <net/sock.h>
#include <linux/virtio_vsock.h>
#include <linux/vhost.h>
#include <net/af_vsock.h>
#include "vhost.h"
#define VHOST_VSOCK_DEFAULT_HOST_CID 2
enum {
VHOST_VSOCK_FEATURES = VHOST_FEATURES,
};
/* Used to track all the vhost_vsock instances on the system. */
static DEFINE_SPINLOCK(vhost_vsock_lock);
static LIST_HEAD(vhost_vsock_list);
struct vhost_vsock {
struct vhost_dev dev;
struct vhost_virtqueue vqs[2];
/* Link to global vhost_vsock_list, protected by vhost_vsock_lock */
struct list_head list;
struct vhost_work send_pkt_work;
spinlock_t send_pkt_list_lock;
struct list_head send_pkt_list; /* host->guest pending packets */
atomic_t queued_replies;
u32 guest_cid;
};
static u32 vhost_transport_get_local_cid(void)
{
return VHOST_VSOCK_DEFAULT_HOST_CID;
}
static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
{
struct vhost_vsock *vsock;
spin_lock_bh(&vhost_vsock_lock);
list_for_each_entry(vsock, &vhost_vsock_list, list) {
u32 other_cid = vsock->guest_cid;
/* Skip instances that have no CID yet */
if (other_cid == 0)
continue;
if (other_cid == guest_cid) {
spin_unlock_bh(&vhost_vsock_lock);
return vsock;
}
}
spin_unlock_bh(&vhost_vsock_lock);
return NULL;
}
static void
vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
struct vhost_virtqueue *vq)
{
struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
bool added = false;
bool restart_tx = false;
mutex_lock(&vq->mutex);
if (!vq->private_data)
goto out;
/* Avoid further vmexits, we're already processing the virtqueue */
vhost_disable_notify(&vsock->dev, vq);
for (;;) {
struct virtio_vsock_pkt *pkt;
struct iov_iter iov_iter;
unsigned out, in;
size_t nbytes;
size_t len;
int head;
spin_lock_bh(&vsock->send_pkt_list_lock);
if (list_empty(&vsock->send_pkt_list)) {
spin_unlock_bh(&vsock->send_pkt_list_lock);
vhost_enable_notify(&vsock->dev, vq);
break;
}
pkt = list_first_entry(&vsock->send_pkt_list,
struct virtio_vsock_pkt, list);
list_del_init(&pkt->list);
spin_unlock_bh(&vsock->send_pkt_list_lock);
head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
&out, &in, NULL, NULL);
if (head < 0) {
spin_lock_bh(&vsock->send_pkt_list_lock);
list_add(&pkt->list, &vsock->send_pkt_list);
spin_unlock_bh(&vsock->send_pkt_list_lock);
break;
}
if (head == vq->num) {
spin_lock_bh(&vsock->send_pkt_list_lock);
list_add(&pkt->list, &vsock->send_pkt_list);
spin_unlock_bh(&vsock->send_pkt_list_lock);
/* We cannot finish yet if more buffers snuck in while
* re-enabling notify.
*/
if (unlikely(vhost_enable_notify(&vsock->dev, vq))) {
vhost_disable_notify(&vsock->dev, vq);
continue;
}
break;
}
if (out) {
virtio_transport_free_pkt(pkt);
vq_err(vq, "Expected 0 output buffers, got %u\n", out);
break;
}
len = iov_length(&vq->iov[out], in);
iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len);
nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
if (nbytes != sizeof(pkt->hdr)) {
virtio_transport_free_pkt(pkt);
vq_err(vq, "Faulted on copying pkt hdr\n");
break;
}
nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter);
if (nbytes != pkt->len) {
virtio_transport_free_pkt(pkt);
vq_err(vq, "Faulted on copying pkt buf\n");
break;
}
vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
added = true;
if (pkt->reply) {
int val;
val = atomic_dec_return(&vsock->queued_replies);
/* Do we have resources to resume tx processing? */
if (val + 1 == tx_vq->num)
restart_tx = true;
}
virtio_transport_free_pkt(pkt);
}
if (added)
vhost_signal(&vsock->dev, vq);
out:
mutex_unlock(&vq->mutex);
if (restart_tx)
vhost_poll_queue(&tx_vq->poll);
}
static void vhost_transport_send_pkt_work(struct vhost_work *work)
{
struct vhost_virtqueue *vq;
struct vhost_vsock *vsock;
vsock = container_of(work, struct vhost_vsock, send_pkt_work);
vq = &vsock->vqs[VSOCK_VQ_RX];
vhost_transport_do_send_pkt(vsock, vq);
}
static int
vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
{
struct vhost_vsock *vsock;
struct vhost_virtqueue *vq;
int len = pkt->len;
/* Find the vhost_vsock according to guest context id */
vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid));
if (!vsock) {
virtio_transport_free_pkt(pkt);
return -ENODEV;
}
vq = &vsock->vqs[VSOCK_VQ_RX];
if (pkt->reply)
atomic_inc(&vsock->queued_replies);
spin_lock_bh(&vsock->send_pkt_list_lock);
list_add_tail(&pkt->list, &vsock->send_pkt_list);
spin_unlock_bh(&vsock->send_pkt_list_lock);
vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
return len;
}
static struct virtio_vsock_pkt *
vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
unsigned int out, unsigned int in)
{
struct virtio_vsock_pkt *pkt;
struct iov_iter iov_iter;
size_t nbytes;
size_t len;
if (in != 0) {
vq_err(vq, "Expected 0 input buffers, got %u\n", in);
return NULL;
}
pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
if (!pkt)
return NULL;
len = iov_length(vq->iov, out);
iov_iter_init(&iov_iter, WRITE, vq->iov, out, len);
nbytes = copy_from_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
if (nbytes != sizeof(pkt->hdr)) {
vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n",
sizeof(pkt->hdr), nbytes);
kfree(pkt);
return NULL;
}
if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM)
pkt->len = le32_to_cpu(pkt->hdr.len);
/* No payload */
if (!pkt->len)
return pkt;
/* The pkt is too big */
if (pkt->len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
kfree(pkt);
return NULL;
}