OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity

virtio, vhost: fixes, features

Browse Source 
IOTLB support in vhost-user.
 A bunch of fixes all over the place.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJZMZNVAAoJECgfDbjSjVRpmJ0H/R9zMmXg6SclYlQ2qnHKXWrG
 GAzwvQ+qHG2SfcmbR+FlTBsnTRz7nSPS4yvDgxRaO22ew2zROZdMDif0fsZWxByr
 a5QbmMMSHL++75vNieIM7Ar7eWhTjD+eG8J1k6qB5krEVILlHupYeYzez/xBiW0H
 GBkPG7zXkApqZSTxdTyGfOljz7O4kYJaqJx/oUYO5vGglcDz8YHXp1WamvVRgnab
 5aLP722DOvubbhs3b3XAA3Zqxonc3uLn049+yAVCSwRlGaXbxj/P+cCx3dYehnoR
 qA6IMmwQdjOCSP8R8QIe6beRMX97z7JPVy/JAY8Fwe7gl0vEvB1ZNmmZGTBhp5I=
 =ErJZ
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

virtio, vhost: fixes, features

IOTLB support in vhost-user.
A bunch of fixes all over the place.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Fri 02 Jun 2017 17:33:25 BST
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream:
  spec/vhost-user spec: Add IOMMU support
  vhost-user: add slave-req-fd support
  vhost-user: add vhost_user to hold the chr
  vhost: rework IOTLB messaging
  vhost: propagate errors in vhost_device_iotlb_miss()
  virtio-serial: fix segfault on disconnect
  virtio: add virtqueue_alloc_element tracepoint
  virtio-serial-bus: Unset hotplug handler when unrealize

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2017-06-02 17:46:22 +01:00
commit c6e84fbd44
10 changed files with 413 additions and 82 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

116
docs/specs/vhost-user.txt
View File

@ -97,6 +97,25 @@ Depending on the request type, payload can be:
log offset: offset from start of supplied file descriptor
where logging starts (i.e. where guest address 0 would be logged)
* An IOTLB message
---------------------------------------------------------
| iova | size | user address | permissions flags | type |
---------------------------------------------------------
IOVA: a 64-bit I/O virtual address programmed by the guest
Size: a 64-bit size
User address: a 64-bit user address
Permissions: a 8-bit value:
- 0: No access
- 1: Read access
- 2: Write access
- 3: Read/Write access
Type: a 8-bit IOTLB message type:
- 1: IOTLB miss
- 2: IOTLB update
- 3: IOTLB invalidate
- 4: IOTLB access fail
In QEMU the vhost-user message is implemented with the following struct:
typedef struct VhostUserMsg {
@ -109,6 +128,7 @@ typedef struct VhostUserMsg {
struct vhost_vring_addr addr;
VhostUserMemory memory;
VhostUserLog log;
struct vhost_iotlb_msg iotlb;
};
} QEMU_PACKED VhostUserMsg;
@ -139,6 +159,7 @@ in the ancillary data:
* VHOST_USER_SET_VRING_KICK
* VHOST_USER_SET_VRING_CALL
* VHOST_USER_SET_VRING_ERR
* VHOST_USER_SET_SLAVE_REQ_FD
If Master is unable to send the full message or receives a wrong reply it will
close the connection. An optional reconnection mechanism can be implemented.
@ -252,6 +273,50 @@ Once the source has finished migration, rings will be stopped by
the source. No further update must be done before rings are
restarted.
IOMMU support
-------------
When the VIRTIO_F_IOMMU_PLATFORM feature has been negotiated, the master
sends IOTLB entries update & invalidation by sending VHOST_USER_IOTLB_MSG
requests to the slave with a struct vhost_iotlb_msg as payload. For update
events, the iotlb payload has to be filled with the update message type (2),
the I/O virtual address, the size, the user virtual address, and the
permissions flags. Addresses and size must be within vhost memory regions set
via the VHOST_USER_SET_MEM_TABLE request. For invalidation events, the iotlb
payload has to be filled with the invalidation message type (3), the I/O virtual
address and the size. On success, the slave is expected to reply with a zero
payload, non-zero otherwise.
The slave relies on the slave communcation channel (see "Slave communication"
section below) to send IOTLB miss and access failure events, by sending
VHOST_USER_SLAVE_IOTLB_MSG requests to the master with a struct vhost_iotlb_msg
as payload. For miss events, the iotlb payload has to be filled with the miss
message type (1), the I/O virtual address and the permissions flags. For access
failure event, the iotlb payload has to be filled with the access failure
message type (4), the I/O virtual address and the permissions flags.
For synchronization purpose, the slave may rely on the reply-ack feature,
so the master may send a reply when operation is completed if the reply-ack
feature is negotiated and slaves requests a reply. For miss events, completed
operation means either master sent an update message containing the IOTLB entry
containing requested address and permission, or master sent nothing if the IOTLB
miss message is invalid (invalid IOVA or permission).
The master isn't expected to take the initiative to send IOTLB update messages,
as the slave sends IOTLB miss messages for the guest virtual memory areas it
needs to access.
Slave communication
-------------------
An optional communication channel is provided if the slave declares
VHOST_USER_PROTOCOL_F_SLAVE_REQ protocol feature, to allow the slave to make
requests to the master.
The fd is provided via VHOST_USER_SET_SLAVE_REQ_FD ancillary data.
A slave may then send VHOST_USER_SLAVE_* messages to the master
using this fd communication channel.
Protocol features
-----------------
@ -260,9 +325,10 @@ Protocol features
#define VHOST_USER_PROTOCOL_F_RARP 2
#define VHOST_USER_PROTOCOL_F_REPLY_ACK 3
#define VHOST_USER_PROTOCOL_F_MTU 4
#define VHOST_USER_PROTOCOL_F_SLAVE_REQ 5
Message types
-------------
Master message types
--------------------
* VHOST_USER_GET_FEATURES
@ -486,6 +552,52 @@ Message types
If VHOST_USER_PROTOCOL_F_REPLY_ACK is negotiated, slave must respond
with zero in case the specified MTU is valid, or non-zero otherwise.
* VHOST_USER_SET_SLAVE_REQ_FD
Id: 21
Equivalent ioctl: N/A
Master payload: N/A
Set the socket file descriptor for slave initiated requests. It is passed
in the ancillary data.
This request should be sent only when VHOST_USER_F_PROTOCOL_FEATURES
has been negotiated, and protocol feature bit VHOST_USER_PROTOCOL_F_SLAVE_REQ
bit is present in VHOST_USER_GET_PROTOCOL_FEATURES.
If VHOST_USER_PROTOCOL_F_REPLY_ACK is negotiated, slave must respond
with zero for success, non-zero otherwise.
* VHOST_USER_IOTLB_MSG
Id: 22
Equivalent ioctl: N/A (equivalent to VHOST_IOTLB_MSG message type)
Master payload: struct vhost_iotlb_msg
Slave payload: u64
Send IOTLB messages with struct vhost_iotlb_msg as payload.
Master sends such requests to update and invalidate entries in the device
IOTLB. The slave has to acknowledge the request with sending zero as u64
payload for success, non-zero otherwise.
This request should be send only when VIRTIO_F_IOMMU_PLATFORM feature
has been successfully negotiated.
Slave message types
-------------------
* VHOST_USER_SLAVE_IOTLB_MSG
Id: 1
Equivalent ioctl: N/A (equivalent to VHOST_IOTLB_MSG message type)
Slave payload: struct vhost_iotlb_msg
Master payload: N/A
Send IOTLB messages with struct vhost_iotlb_msg as payload.
Slave sends such requests to notify of an IOTLB miss, or an IOTLB
access failure. If VHOST_USER_PROTOCOL_F_REPLY_ACK is negotiated,
and slave set the VHOST_USER_NEED_REPLY flag, master must respond with
zero when operation is successfully completed, or non-zero otherwise.
This request should be send only when VIRTIO_F_IOMMU_PLATFORM feature
has been successfully negotiated.
VHOST_USER_PROTOCOL_F_REPLY_ACK:
-------------------------------
The original vhost-user specification only demands replies for certain

6
hw/char/virtio-serial-bus.c
View File

@ -186,6 +186,9 @@ static void do_flush_queued_data(VirtIOSerialPort *port, VirtQueue *vq,
port->elem->out_sg[i].iov_base
+ port->iov_offset,
buf_size);
if (!port->elem) { /* bail if we got disconnected */
return;
}
if (port->throttled) {
port->iov_idx = i;
if (ret > 0) {
@ -1121,6 +1124,9 @@ static void virtio_serial_device_unrealize(DeviceState *dev, Error **errp)
timer_free(vser->post_load->timer);
g_free(vser->post_load);
}
qbus_set_hotplug_handler(BUS(&vser->bus), NULL, errp);
virtio_cleanup(vdev);
}

1
hw/net/vhost_net.c
View File

@ -77,6 +77,7 @@ static const int user_feature_bits[] = {
VIRTIO_NET_F_HOST_UFO,
VIRTIO_NET_F_MRG_RXBUF,
VIRTIO_NET_F_MTU,
VIRTIO_F_IOMMU_PLATFORM,
/* This bit implies RARP isn't sent by QEMU out of band */
VIRTIO_NET_F_GUEST_ANNOUNCE,

1
hw/virtio/trace-events
View File

@ -1,6 +1,7 @@
# See docs/tracing.txt for syntax documentation.
# hw/virtio/virtio.c
virtqueue_alloc_element(void *elem, size_t sz, unsigned in_num, unsigned out_num) "elem %p size %zd in_num %u out_num %u"
virtqueue_fill(void *vq, const void *elem, unsigned int len, unsigned int idx) "vq %p elem %p len %u idx %u"
virtqueue_flush(void *vq, unsigned int count) "vq %p count %u"
virtqueue_pop(void *vq, void *elem, unsigned int in_num, unsigned int out_num) "vq %p elem %p in_num %u out_num %u"

132
hw/virtio/vhost-backend.c
View File

@ -192,7 +192,6 @@ static void vhost_kernel_iotlb_read(void *opaque)
ssize_t len;
while ((len = read((uintptr_t)dev->opaque, &msg, sizeof msg)) > 0) {
struct vhost_iotlb_msg *imsg = &msg.iotlb;
if (len < sizeof msg) {
error_report("Wrong vhost message len: %d", (int)len);
break;
@ -201,49 +200,18 @@ static void vhost_kernel_iotlb_read(void *opaque)
error_report("Unknown vhost iotlb message type");
break;
}
switch (imsg->type) {
case VHOST_IOTLB_MISS:
vhost_device_iotlb_miss(dev, imsg->iova,
imsg->perm != VHOST_ACCESS_RO);
break;
case VHOST_IOTLB_UPDATE:
case VHOST_IOTLB_INVALIDATE:
error_report("Unexpected IOTLB message type");
break;
case VHOST_IOTLB_ACCESS_FAIL:
/* FIXME: report device iotlb error */
break;
default:
break;
}
vhost_backend_handle_iotlb_msg(dev, &msg.iotlb);
}
}
static int vhost_kernel_update_device_iotlb(struct vhost_dev *dev,
uint64_t iova, uint64_t uaddr,
uint64_t len,
IOMMUAccessFlags perm)
static int vhost_kernel_send_device_iotlb_msg(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg)
{
struct vhost_msg msg;
msg.type = VHOST_IOTLB_MSG;
msg.iotlb.iova = iova;
msg.iotlb.uaddr = uaddr;
msg.iotlb.size = len;
msg.iotlb.type = VHOST_IOTLB_UPDATE;
switch (perm) {
case IOMMU_RO:
msg.iotlb.perm = VHOST_ACCESS_RO;
break;
case IOMMU_WO:
msg.iotlb.perm = VHOST_ACCESS_WO;
break;
case IOMMU_RW:
msg.iotlb.perm = VHOST_ACCESS_RW;
break;
default:
g_assert_not_reached();
}
msg.type = VHOST_IOTLB_MSG;
msg.iotlb = *imsg;
if (write((uintptr_t)dev->opaque, &msg, sizeof msg) != sizeof msg) {
error_report("Fail to update device iotlb");
@ -253,24 +221,6 @@ static int vhost_kernel_update_device_iotlb(struct vhost_dev *dev,
return 0;
}
static int vhost_kernel_invalidate_device_iotlb(struct vhost_dev *dev,
uint64_t iova, uint64_t len)
{
struct vhost_msg msg;
msg.type = VHOST_IOTLB_MSG;
msg.iotlb.iova = iova;
msg.iotlb.size = len;
msg.iotlb.type = VHOST_IOTLB_INVALIDATE;
if (write((uintptr_t)dev->opaque, &msg, sizeof msg) != sizeof msg) {
error_report("Fail to invalidate device iotlb");
return -EFAULT;
}
return 0;
}
static void vhost_kernel_set_iotlb_callback(struct vhost_dev *dev,
int enabled)
{
@ -311,8 +261,7 @@ static const VhostOps kernel_ops = {
.vhost_vsock_set_running = vhost_kernel_vsock_set_running,
#endif /* CONFIG_VHOST_VSOCK */
.vhost_set_iotlb_callback = vhost_kernel_set_iotlb_callback,
.vhost_update_device_iotlb = vhost_kernel_update_device_iotlb,
.vhost_invalidate_device_iotlb = vhost_kernel_invalidate_device_iotlb,
.vhost_send_device_iotlb_msg = vhost_kernel_send_device_iotlb_msg,
};
int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
@ -333,3 +282,70 @@ int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
return r;
}
int vhost_backend_update_device_iotlb(struct vhost_dev *dev,
uint64_t iova, uint64_t uaddr,
uint64_t len,
IOMMUAccessFlags perm)
{
struct vhost_iotlb_msg imsg;
imsg.iova = iova;
imsg.uaddr = uaddr;
imsg.size = len;
imsg.type = VHOST_IOTLB_UPDATE;
switch (perm) {
case IOMMU_RO:
imsg.perm = VHOST_ACCESS_RO;
break;
case IOMMU_WO:
imsg.perm = VHOST_ACCESS_WO;
break;
case IOMMU_RW:
imsg.perm = VHOST_ACCESS_RW;
break;
default:
return -EINVAL;
}
return dev->vhost_ops->vhost_send_device_iotlb_msg(dev, &imsg);
}
int vhost_backend_invalidate_device_iotlb(struct vhost_dev *dev,
uint64_t iova, uint64_t len)
{
struct vhost_iotlb_msg imsg;
imsg.iova = iova;
imsg.size = len;
imsg.type = VHOST_IOTLB_INVALIDATE;
return dev->vhost_ops->vhost_send_device_iotlb_msg(dev, &imsg);
}
int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg)
{
int ret = 0;
switch (imsg->type) {
case VHOST_IOTLB_MISS:
ret = vhost_device_iotlb_miss(dev, imsg->iova,
imsg->perm != VHOST_ACCESS_RO);
break;
case VHOST_IOTLB_ACCESS_FAIL:
/* FIXME: report device iotlb error */
error_report("Access failure IOTLB message type not supported");
ret = -ENOTSUP;
break;
case VHOST_IOTLB_UPDATE:
case VHOST_IOTLB_INVALIDATE:
default:
error_report("Unexpected IOTLB message type");
ret = -EINVAL;
break;
}
return ret;
}

194
hw/virtio/vhost-user.c
View File

@ -32,6 +32,7 @@ enum VhostUserProtocolFeature {
VHOST_USER_PROTOCOL_F_RARP = 2,
VHOST_USER_PROTOCOL_F_REPLY_ACK = 3,
VHOST_USER_PROTOCOL_F_NET_MTU = 4,
VHOST_USER_PROTOCOL_F_SLAVE_REQ = 5,
VHOST_USER_PROTOCOL_F_MAX
};
@ -60,9 +61,17 @@ typedef enum VhostUserRequest {
VHOST_USER_SET_VRING_ENABLE = 18,
VHOST_USER_SEND_RARP = 19,
VHOST_USER_NET_SET_MTU = 20,
VHOST_USER_SET_SLAVE_REQ_FD = 21,
VHOST_USER_IOTLB_MSG = 22,
VHOST_USER_MAX
} VhostUserRequest;
typedef enum VhostUserSlaveRequest {
VHOST_USER_SLAVE_NONE = 0,
VHOST_USER_SLAVE_IOTLB_MSG = 1,
VHOST_USER_SLAVE_MAX
} VhostUserSlaveRequest;
typedef struct VhostUserMemoryRegion {
uint64_t guest_phys_addr;
uint64_t memory_size;
@ -97,6 +106,7 @@ typedef struct VhostUserMsg {
struct vhost_vring_addr addr;
VhostUserMemory memory;
VhostUserLog log;
struct vhost_iotlb_msg iotlb;
} payload;
} QEMU_PACKED VhostUserMsg;
@ -110,6 +120,11 @@ static VhostUserMsg m __attribute__ ((unused));
/* The version of the protocol we support */
#define VHOST_USER_VERSION (0x1)
struct vhost_user {
CharBackend *chr;
int slave_fd;
};
static bool ioeventfd_enabled(void)
{
return kvm_enabled() && kvm_eventfds_enabled();
@ -117,7 +132,8 @@ static bool ioeventfd_enabled(void)
static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
{
CharBackend *chr = dev->opaque;
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->chr;
uint8_t *p = (uint8_t *) msg;
int r, size = VHOST_USER_HDR_SIZE;
@ -202,7 +218,8 @@ static bool vhost_user_one_time_request(VhostUserRequest request)
static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
int *fds, int fd_num)
{
CharBackend *chr = dev->opaque;
struct vhost_user *u = dev->opaque;
CharBackend *chr = u->chr;
int ret, size = VHOST_USER_HDR_SIZE + msg->size;
/*
@ -572,14 +589,130 @@ static int vhost_user_reset_device(struct vhost_dev *dev)
return 0;
}
static void slave_read(void *opaque)
{
struct vhost_dev *dev = opaque;
struct vhost_user *u = dev->opaque;
VhostUserMsg msg = { 0, };
int size, ret = 0;
/* Read header */
size = read(u->slave_fd, &msg, VHOST_USER_HDR_SIZE);
if (size != VHOST_USER_HDR_SIZE) {
error_report("Failed to read from slave.");
goto err;
}
if (msg.size > VHOST_USER_PAYLOAD_SIZE) {
error_report("Failed to read msg header."
" Size %d exceeds the maximum %zu.", msg.size,
VHOST_USER_PAYLOAD_SIZE);
goto err;
}
/* Read payload */
size = read(u->slave_fd, &msg.payload, msg.size);
if (size != msg.size) {
error_report("Failed to read payload from slave.");
goto err;
}
switch (msg.request) {
case VHOST_USER_SLAVE_IOTLB_MSG:
ret = vhost_backend_handle_iotlb_msg(dev, &msg.payload.iotlb);
break;
default:
error_report("Received unexpected msg type.");
ret = -EINVAL;
}
/*
* REPLY_ACK feature handling. Other reply types has to be managed
* directly in their request handlers.
*/
if (msg.flags & VHOST_USER_NEED_REPLY_MASK) {
msg.flags &= ~VHOST_USER_NEED_REPLY_MASK;
msg.flags |= VHOST_USER_REPLY_MASK;
msg.payload.u64 = !!ret;
msg.size = sizeof(msg.payload.u64);
size = write(u->slave_fd, &msg, VHOST_USER_HDR_SIZE + msg.size);
if (size != VHOST_USER_HDR_SIZE + msg.size) {
error_report("Failed to send msg reply to slave.");
goto err;
}
}
return;
err:
qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
close(u->slave_fd);
u->slave_fd = -1;
return;
}
static int vhost_setup_slave_channel(struct vhost_dev *dev)
{
VhostUserMsg msg = {
.request = VHOST_USER_SET_SLAVE_REQ_FD,
.flags = VHOST_USER_VERSION,
};
struct vhost_user *u = dev->opaque;
int sv[2], ret = 0;
bool reply_supported = virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK);
if (!virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_SLAVE_REQ)) {
return 0;
}
if (socketpair(PF_UNIX, SOCK_STREAM, 0, sv) == -1) {
error_report("socketpair() failed");
return -1;
}
u->slave_fd = sv[0];
qemu_set_fd_handler(u->slave_fd, slave_read, NULL, dev);
if (reply_supported) {
msg.flags |= VHOST_USER_NEED_REPLY_MASK;
}
ret = vhost_user_write(dev, &msg, &sv[1], 1);
if (ret) {
goto out;
}
if (reply_supported) {
ret = process_message_reply(dev, &msg);
}
out:
close(sv[1]);
if (ret) {
qemu_set_fd_handler(u->slave_fd, NULL, NULL, NULL);
close(u->slave_fd);
u->slave_fd = -1;
}
return ret;
}
static int vhost_user_init(struct vhost_dev *dev, void *opaque)
{
uint64_t features;
uint64_t features, protocol_features;
struct vhost_user *u;
int err;
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
dev->opaque = opaque;
u = g_new0(struct vhost_user, 1);
u->chr = opaque;
u->slave_fd = -1;
dev->opaque = u;
err = vhost_user_get_features(dev, &features);
if (err < 0) {
@ -590,12 +723,13 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
dev->backend_features |= 1ULL << VHOST_USER_F_PROTOCOL_FEATURES;
err = vhost_user_get_u64(dev, VHOST_USER_GET_PROTOCOL_FEATURES,
&features);
&protocol_features);
if (err < 0) {
return err;
}
dev->protocol_features = features & VHOST_USER_PROTOCOL_FEATURE_MASK;
dev->protocol_features =
protocol_features & VHOST_USER_PROTOCOL_FEATURE_MASK;
err = vhost_user_set_protocol_features(dev, dev->protocol_features);
if (err < 0) {
return err;
@ -609,6 +743,16 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
return err;
}
}
if (virtio_has_feature(features, VIRTIO_F_IOMMU_PLATFORM) &&
!(virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_SLAVE_REQ) &&
virtio_has_feature(dev->protocol_features,
VHOST_USER_PROTOCOL_F_REPLY_ACK))) {
error_report("IOMMU support requires reply-ack and "
"slave-req protocol features.");
return -1;
}
}
if (dev->migration_blocker == NULL &&
@ -619,13 +763,26 @@ static int vhost_user_init(struct vhost_dev *dev, void *opaque)
"VHOST_USER_PROTOCOL_F_LOG_SHMFD feature.");
}
err = vhost_setup_slave_channel(dev);
if (err < 0) {
return err;
}
return 0;
}
static int vhost_user_cleanup(struct vhost_dev *dev)
{
struct vhost_user *u;
assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER);
u = dev->opaque;
if (u->slave_fd >= 0) {
close(u->slave_fd);
u->slave_fd = -1;
}
g_free(u);
dev->opaque = 0;
return 0;
@ -722,6 +879,29 @@ static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu)
return 0;
}
static int vhost_user_send_device_iotlb_msg(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg)
{
VhostUserMsg msg = {
.request = VHOST_USER_IOTLB_MSG,
.size = sizeof(msg.payload.iotlb),
.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
.payload.iotlb = *imsg,
};
if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
return -EFAULT;
}
return process_message_reply(dev, &msg);
}
static void vhost_user_set_iotlb_callback(struct vhost_dev *dev, int enabled)
{
/* No-op as the receive channel is not dedicated to IOTLB messages. */
}
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_backend_init = vhost_user_init,
@ -746,4 +926,6 @@ const VhostOps user_ops = {
.vhost_migration_done = vhost_user_migration_done,
.vhost_backend_can_merge = vhost_user_can_merge,
.vhost_net_set_mtu = vhost_user_net_set_mtu,
.vhost_set_iotlb_callback = vhost_user_set_iotlb_callback,
.vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg,
};

19
hw/virtio/vhost.c
View File

@ -724,8 +724,8 @@ static void vhost_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
struct vhost_dev *hdev = iommu->hdev;
hwaddr iova = iotlb->iova + iommu->iommu_offset;
if (hdev->vhost_ops->vhost_invalidate_device_iotlb(hdev, iova,
iotlb->addr_mask + 1)) {
if (vhost_backend_invalidate_device_iotlb(hdev, iova,
iotlb->addr_mask + 1)) {
error_report("Fail to invalidate device iotlb");
}
}
@ -971,18 +971,20 @@ static int vhost_memory_region_lookup(struct vhost_dev *hdev,
return -EFAULT;
}
void vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write)
int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write)
{
IOMMUTLBEntry iotlb;
uint64_t uaddr, len;
int ret = -EFAULT;
rcu_read_lock();
iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as,
iova, write);
if (iotlb.target_as != NULL) {
if (vhost_memory_region_lookup(dev, iotlb.translated_addr,
&uaddr, &len)) {
ret = vhost_memory_region_lookup(dev, iotlb.translated_addr,
&uaddr, &len);
if (ret) {
error_report("Fail to lookup the translated address "
"%"PRIx64, iotlb.translated_addr);
goto out;
@ -991,14 +993,17 @@ void vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write)
len = MIN(iotlb.addr_mask + 1, len);
iova = iova & ~iotlb.addr_mask;
if (dev->vhost_ops->vhost_update_device_iotlb(dev, iova, uaddr,
len, iotlb.perm)) {
ret = vhost_backend_update_device_iotlb(dev, iova, uaddr,
len, iotlb.perm);
if (ret) {
error_report("Fail to update device iotlb");
goto out;
}
}
out:
rcu_read_unlock();
return ret;
}
static int vhost_virtqueue_start(struct vhost_dev *dev,

1
hw/virtio/virtio.c
View File

@ -815,6 +815,7 @@ static void *virtqueue_alloc_element(size_t sz, unsigned out_num, unsigned in_nu
assert(sz >= sizeof(VirtQueueElement));
elem = g_malloc(out_sg_end);
trace_virtqueue_alloc_element(elem, sz, in_num, out_num);
elem->out_num = out_num;
elem->in_num = in_num;
elem->in_addr = (void *)elem + in_addr_ofs;

23
include/hw/virtio/vhost-backend.h
View File

@ -27,6 +27,7 @@ struct vhost_vring_file;
struct vhost_vring_state;
struct vhost_vring_addr;
struct vhost_scsi_target;
struct vhost_iotlb_msg;
typedef int (*vhost_backend_init)(struct vhost_dev *dev, void *opaque);
typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
@ -81,12 +82,8 @@ typedef int (*vhost_vsock_set_guest_cid_op)(struct vhost_dev *dev,
typedef int (*vhost_vsock_set_running_op)(struct vhost_dev *dev, int start);
typedef void (*vhost_set_iotlb_callback_op)(struct vhost_dev *dev,
int enabled);
typedef int (*vhost_update_device_iotlb_op)(struct vhost_dev *dev,
uint64_t iova, uint64_t uaddr,
uint64_t len,
IOMMUAccessFlags perm);
typedef int (*vhost_invalidate_device_iotlb_op)(struct vhost_dev *dev,
uint64_t iova, uint64_t len);
typedef int (*vhost_send_device_iotlb_msg_op)(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg);
typedef struct VhostOps {
VhostBackendType backend_type;
@ -120,8 +117,7 @@ typedef struct VhostOps {
vhost_vsock_set_guest_cid_op vhost_vsock_set_guest_cid;
vhost_vsock_set_running_op vhost_vsock_set_running;
vhost_set_iotlb_callback_op vhost_set_iotlb_callback;
vhost_update_device_iotlb_op vhost_update_device_iotlb;
vhost_invalidate_device_iotlb_op vhost_invalidate_device_iotlb;
vhost_send_device_iotlb_msg_op vhost_send_device_iotlb_msg;
} VhostOps;
extern const VhostOps user_ops;
@ -129,4 +125,15 @@ extern const VhostOps user_ops;
int vhost_set_backend_type(struct vhost_dev *dev,
VhostBackendType backend_type);
int vhost_backend_update_device_iotlb(struct vhost_dev *dev,
uint64_t iova, uint64_t uaddr,
uint64_t len,
IOMMUAccessFlags perm);
int vhost_backend_invalidate_device_iotlb(struct vhost_dev *dev,
uint64_t iova, uint64_t len);
int vhost_backend_handle_iotlb_msg(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg);
#endif /* VHOST_BACKEND_H */

2
include/hw/virtio/vhost.h
View File

@ -105,5 +105,5 @@ bool vhost_has_free_slot(void);
int vhost_net_set_backend(struct vhost_dev *hdev,
struct vhost_vring_file *file);
void vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write);
int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write);
#endif