summaryrefslogtreecommitdiff
path: root/drivers/vhost
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vhost')
-rw-r--r--drivers/vhost/net.c129
-rw-r--r--drivers/vhost/scsi.c17
-rw-r--r--drivers/vhost/test.c6
-rw-r--r--drivers/vhost/vhost.c56
-rw-r--r--drivers/vhost/vhost.h10
5 files changed, 81 insertions, 137 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 027be91db139..831eb4fd197d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -15,7 +15,6 @@
#include <linux/moduleparam.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
-#include <linux/rcupdate.h>
#include <linux/file.h>
#include <linux/slab.h>
@@ -277,12 +276,12 @@ static void copy_iovec_hdr(const struct iovec *from, struct iovec *to,
* of used idx. Once lower device DMA done contiguously, we will signal KVM
* guest used idx.
*/
-static int vhost_zerocopy_signal_used(struct vhost_net *net,
- struct vhost_virtqueue *vq)
+static void 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 i, add;
int j = 0;
for (i = nvq->done_idx; i != nvq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
@@ -290,15 +289,17 @@ static int vhost_zerocopy_signal_used(struct vhost_net *net,
vhost_net_tx_err(net);
if (VHOST_DMA_IS_DONE(vq->heads[i].len)) {
vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
- vhost_add_used_and_signal(vq->dev, vq,
- vq->heads[i].id, 0);
++j;
} else
break;
}
- if (j)
- nvq->done_idx = i;
- return j;
+ while (j) {
+ add = min(UIO_MAXIOV - nvq->done_idx, j);
+ vhost_add_used_and_signal_n(vq->dev, vq,
+ &vq->heads[nvq->done_idx], add);
+ nvq->done_idx = (nvq->done_idx + add) % UIO_MAXIOV;
+ j -= add;
+ }
}
static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
@@ -307,6 +308,11 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
struct vhost_virtqueue *vq = ubufs->vq;
int cnt = atomic_read(&ubufs->kref.refcount);
+ /* set len to mark this desc buffers done DMA */
+ vq->heads[ubuf->desc].len = success ?
+ VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
+ vhost_net_ubuf_put(ubufs);
+
/*
* Trigger polling thread if guest stopped submitting new buffers:
* in this case, the refcount after decrement will eventually reach 1
@@ -317,10 +323,6 @@ static void vhost_zerocopy_callback(struct ubuf_info *ubuf, bool success)
*/
if (cnt <= 2 || !(cnt % 16))
vhost_poll_queue(&vq->poll);
- /* set len to mark this desc buffers done DMA */
- vq->heads[ubuf->desc].len = success ?
- VHOST_DMA_DONE_LEN : VHOST_DMA_FAILED_LEN;
- vhost_net_ubuf_put(ubufs);
}
/* Expects to be always run from workqueue - which acts as
@@ -346,12 +348,11 @@ static void handle_tx(struct vhost_net *net)
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
bool zcopy, zcopy_used;
- /* TODO: check that we are running from vhost_worker? */
- sock = rcu_dereference_check(vq->private_data, 1);
+ mutex_lock(&vq->mutex);
+ sock = vq->private_data;
if (!sock)
- return;
+ goto out;
- mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
hdr_size = nvq->vhost_hlen;
@@ -362,6 +363,13 @@ static void handle_tx(struct vhost_net *net)
if (zcopy)
vhost_zerocopy_signal_used(net, vq);
+ /* If more outstanding DMAs, queue the work.
+ * Handle upend_idx wrap around
+ */
+ if (unlikely((nvq->upend_idx + vq->num - VHOST_MAX_PEND)
+ % UIO_MAXIOV == nvq->done_idx))
+ break;
+
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
@@ -371,17 +379,6 @@ static void handle_tx(struct vhost_net *net)
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
- int num_pends;
-
- /* If more outstanding DMAs, queue the work.
- * Handle upend_idx wrap around
- */
- 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))) {
vhost_disable_notify(&net->dev, vq);
continue;
@@ -404,43 +401,36 @@ static void handle_tx(struct vhost_net *net)
iov_length(nvq->hdr, s), hdr_size);
break;
}
- zcopy_used = zcopy && (len >= VHOST_GOODCOPY_LEN ||
- nvq->upend_idx != nvq->done_idx);
+
+ zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
+ && (nvq->upend_idx + 1) % UIO_MAXIOV !=
+ nvq->done_idx
+ && vhost_net_tx_select_zcopy(net);
/* use msg_control to pass vhost zerocopy ubuf info to skb */
if (zcopy_used) {
+ struct ubuf_info *ubuf;
+ ubuf = nvq->ubuf_info + nvq->upend_idx;
+
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[nvq->upend_idx].len =
- VHOST_DMA_DONE_LEN;
- msg.msg_control = NULL;
- msg.msg_controllen = 0;
- ubufs = NULL;
- } else {
- struct ubuf_info *ubuf;
- ubuf = nvq->ubuf_info + nvq->upend_idx;
-
- vq->heads[nvq->upend_idx].len =
- VHOST_DMA_IN_PROGRESS;
- ubuf->callback = vhost_zerocopy_callback;
- ubuf->ctx = nvq->ubufs;
- ubuf->desc = nvq->upend_idx;
- msg.msg_control = ubuf;
- msg.msg_controllen = sizeof(ubuf);
- ubufs = nvq->ubufs;
- kref_get(&ubufs->kref);
- }
+ vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
+ ubuf->callback = vhost_zerocopy_callback;
+ ubuf->ctx = nvq->ubufs;
+ ubuf->desc = nvq->upend_idx;
+ msg.msg_control = ubuf;
+ msg.msg_controllen = sizeof(ubuf);
+ ubufs = nvq->ubufs;
+ kref_get(&ubufs->kref);
nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
- } else
+ } else {
msg.msg_control = NULL;
+ ubufs = NULL;
+ }
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
if (zcopy_used) {
- if (ubufs)
- vhost_net_ubuf_put(ubufs);
+ vhost_net_ubuf_put(ubufs);
nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
% UIO_MAXIOV;
}
@@ -461,7 +451,7 @@ static void handle_tx(struct vhost_net *net)
break;
}
}
-
+out:
mutex_unlock(&vq->mutex);
}
@@ -570,14 +560,14 @@ static void handle_rx(struct vhost_net *net)
s16 headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
- /* TODO: check that we are running from vhost_worker? */
- struct socket *sock = rcu_dereference_check(vq->private_data, 1);
-
- if (!sock)
- return;
+ struct socket *sock;
mutex_lock(&vq->mutex);
+ sock = vq->private_data;
+ if (!sock)
+ goto out;
vhost_disable_notify(&net->dev, vq);
+
vhost_hlen = nvq->vhost_hlen;
sock_hlen = nvq->sock_hlen;
@@ -652,7 +642,7 @@ static void handle_rx(struct vhost_net *net)
break;
}
}
-
+out:
mutex_unlock(&vq->mutex);
}
@@ -750,8 +740,7 @@ static int vhost_net_enable_vq(struct vhost_net *n,
struct vhost_poll *poll = n->poll + (nvq - n->vqs);
struct socket *sock;
- sock = rcu_dereference_protected(vq->private_data,
- lockdep_is_held(&vq->mutex));
+ sock = vq->private_data;
if (!sock)
return 0;
@@ -764,10 +753,9 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n,
struct socket *sock;
mutex_lock(&vq->mutex);
- sock = rcu_dereference_protected(vq->private_data,
- lockdep_is_held(&vq->mutex));
+ sock = vq->private_data;
vhost_net_disable_vq(n, vq);
- rcu_assign_pointer(vq->private_data, NULL);
+ vq->private_data = NULL;
mutex_unlock(&vq->mutex);
return sock;
}
@@ -923,8 +911,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
}
/* start polling new socket */
- oldsock = rcu_dereference_protected(vq->private_data,
- lockdep_is_held(&vq->mutex));
+ oldsock = vq->private_data;
if (sock != oldsock) {
ubufs = vhost_net_ubuf_alloc(vq,
sock && vhost_sock_zcopy(sock));
@@ -934,7 +921,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
}
vhost_net_disable_vq(n, vq);
- rcu_assign_pointer(vq->private_data, sock);
+ vq->private_data = sock;
r = vhost_init_used(vq);
if (r)
goto err_used;
@@ -968,7 +955,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
return 0;
err_used:
- rcu_assign_pointer(vq->private_data, oldsock);
+ vq->private_data = oldsock;
vhost_net_enable_vq(n, vq);
if (ubufs)
vhost_net_ubuf_put_wait_and_free(ubufs);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 06adf31a9248..0c27c7df1b09 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -902,19 +902,15 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq)
int head, ret;
u8 target;
+ mutex_lock(&vq->mutex);
/*
* We can handle the vq only after the endpoint is setup by calling the
* VHOST_SCSI_SET_ENDPOINT ioctl.
- *
- * TODO: Check that we are running from vhost_worker which acts
- * as read-side critical section for vhost kind of RCU.
- * See the comments in struct vhost_virtqueue in drivers/vhost/vhost.h
*/
- vs_tpg = rcu_dereference_check(vq->private_data, 1);
+ vs_tpg = vq->private_data;
if (!vs_tpg)
- return;
+ goto out;
- mutex_lock(&vq->mutex);
vhost_disable_notify(&vs->dev, vq);
for (;;) {
@@ -1064,6 +1060,7 @@ err_free:
vhost_scsi_free_cmd(cmd);
err_cmd:
vhost_scsi_send_bad_target(vs, vq, head, out);
+out:
mutex_unlock(&vq->mutex);
}
@@ -1232,9 +1229,8 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
sizeof(vs->vs_vhost_wwpn));
for (i = 0; i < VHOST_SCSI_MAX_VQ; 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);
+ vq->private_data = vs_tpg;
vhost_init_used(vq);
mutex_unlock(&vq->mutex);
}
@@ -1313,9 +1309,8 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs,
if (match) {
for (i = 0; i < VHOST_SCSI_MAX_VQ; 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);
+ vq->private_data = NULL;
mutex_unlock(&vq->mutex);
}
}
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index a73ea217f24d..339eae85859a 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -13,7 +13,6 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
-#include <linux/rcupdate.h>
#include <linux/file.h>
#include <linux/slab.h>
@@ -200,9 +199,8 @@ static long vhost_test_run(struct vhost_test *n, int test)
priv = test ? n : NULL;
/* start polling new socket */
- oldpriv = rcu_dereference_protected(vq->private_data,
- lockdep_is_held(&vq->mutex));
- rcu_assign_pointer(vq->private_data, priv);
+ oldpriv = vq->private_data;
+ vq->private_data = priv;
r = vhost_init_used(&n->vqs[index]);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index e58cf0001cee..9a9502a4aa50 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -13,7 +13,7 @@
#include <linux/eventfd.h>
#include <linux/vhost.h>
-#include <linux/socket.h> /* memcpy_fromiovec */
+#include <linux/uio.h>
#include <linux/mm.h>
#include <linux/mmu_context.h>
#include <linux/miscdevice.h>
@@ -1332,48 +1332,9 @@ EXPORT_SYMBOL_GPL(vhost_discard_vq_desc);
* want to notify the guest, using eventfd. */
int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
{
- struct vring_used_elem __user *used;
+ struct vring_used_elem heads = { head, len };
- /* The virtqueue contains a ring of used buffers. Get a pointer to the
- * next entry in that used ring. */
- used = &vq->used->ring[vq->last_used_idx % vq->num];
- if (__put_user(head, &used->id)) {
- vq_err(vq, "Failed to write used id");
- return -EFAULT;
- }
- if (__put_user(len, &used->len)) {
- vq_err(vq, "Failed to write used len");
- return -EFAULT;
- }
- /* Make sure buffer is written before we update index. */
- smp_wmb();
- if (__put_user(vq->last_used_idx + 1, &vq->used->idx)) {
- vq_err(vq, "Failed to increment used idx");
- return -EFAULT;
- }
- if (unlikely(vq->log_used)) {
- /* Make sure data is seen before log. */
- smp_wmb();
- /* Log used ring entry write. */
- log_write(vq->log_base,
- vq->log_addr +
- ((void __user *)used - (void __user *)vq->used),
- sizeof *used);
- /* Log used index update. */
- log_write(vq->log_base,
- vq->log_addr + offsetof(struct vring_used, idx),
- sizeof vq->used->idx);
- if (vq->log_ctx)
- eventfd_signal(vq->log_ctx, 1);
- }
- vq->last_used_idx++;
- /* If the driver never bothers to signal in a very long while,
- * used index might wrap around. If that happens, invalidate
- * signalled_used index we stored. TODO: make sure driver
- * signals at least once in 2^16 and remove this. */
- if (unlikely(vq->last_used_idx == vq->signalled_used))
- vq->signalled_used_valid = false;
- return 0;
+ return vhost_add_used_n(vq, &heads, 1);
}
EXPORT_SYMBOL_GPL(vhost_add_used);
@@ -1387,7 +1348,16 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
start = vq->last_used_idx % vq->num;
used = vq->used->ring + start;
- if (__copy_to_user(used, heads, count * sizeof *used)) {
+ if (count == 1) {
+ if (__put_user(heads[0].id, &used->id)) {
+ vq_err(vq, "Failed to write used id");
+ return -EFAULT;
+ }
+ if (__put_user(heads[0].len, &used->len)) {
+ vq_err(vq, "Failed to write used len");
+ return -EFAULT;
+ }
+ } else if (__copy_to_user(used, heads, count * sizeof *used)) {
vq_err(vq, "Failed to write used");
return -EFAULT;
}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 42298cd23c73..4465ed5f316d 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -103,14 +103,8 @@ struct vhost_virtqueue {
struct iovec iov[UIO_MAXIOV];
struct iovec *indirect;
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
- * flush the vhost_work instead of synchronize_rcu. Therefore readers do
- * not need to call rcu_read_lock/rcu_read_unlock: the beginning of
- * vhost_work execution acts instead of rcu_read_lock() and the end of
- * vhost_work execution acts instead of rcu_read_unlock().
- * Writers use virtqueue mutex. */
- void __rcu *private_data;
+ /* Protected by virtqueue mutex. */
+ void *private_data;
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
generated by cgit v1.2.3 (git 2.39.0) at 2024-08-07 03:52:10 +0300