summaryrefslogtreecommitdiff
path: root/drivers/vhost
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vhost')
-rw-r--r--drivers/vhost/net.c3
-rw-r--r--drivers/vhost/vhost.c99
-rw-r--r--drivers/vhost/vhost.h3
-rw-r--r--drivers/vhost/vsock.c74
4 files changed, 140 insertions, 39 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 353c93bc459b..681d0eade82f 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -751,7 +751,8 @@ static void handle_rx(struct vhost_net *net)
vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
headcount);
if (unlikely(vq_log))
- vhost_log_write(vq, vq_log, log, vhost_len);
+ vhost_log_write(vq, vq_log, log, vhost_len,
+ vq->iov, in);
total_len += vhost_len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 4c5625cb540c..2383caf88b67 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1646,13 +1646,87 @@ static int log_write(void __user *log_base,
return r;
}
+static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
+{
+ struct vhost_umem *umem = vq->umem;
+ struct vhost_umem_node *u;
+ u64 start, end, l, min;
+ int r;
+ bool hit = false;
+
+ while (len) {
+ min = len;
+ /* More than one GPAs can be mapped into a single HVA. So
+ * iterate all possible umems here to be safe.
+ */
+ list_for_each_entry(u, &umem->umem_list, link) {
+ if (u->userspace_addr > hva - 1 + len ||
+ u->userspace_addr - 1 + u->size < hva)
+ continue;
+ start = max(u->userspace_addr, hva);
+ end = min(u->userspace_addr - 1 + u->size,
+ hva - 1 + len);
+ l = end - start + 1;
+ r = log_write(vq->log_base,
+ u->start + start - u->userspace_addr,
+ l);
+ if (r < 0)
+ return r;
+ hit = true;
+ min = min(l, min);
+ }
+
+ if (!hit)
+ return -EFAULT;
+
+ len -= min;
+ hva += min;
+ }
+
+ return 0;
+}
+
+static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
+{
+ struct iovec iov[64];
+ int i, ret;
+
+ if (!vq->iotlb)
+ return log_write(vq->log_base, vq->log_addr + used_offset, len);
+
+ ret = translate_desc(vq, (uintptr_t)vq->used + used_offset,
+ len, iov, 64, VHOST_ACCESS_WO);
+ if (ret < 0)
+ return ret;
+
+ for (i = 0; i < ret; i++) {
+ ret = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
+ iov[i].iov_len);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
- unsigned int log_num, u64 len)
+ unsigned int log_num, u64 len, struct iovec *iov, int count)
{
int i, r;
/* Make sure data written is seen before log. */
smp_wmb();
+
+ if (vq->iotlb) {
+ for (i = 0; i < count; i++) {
+ r = log_write_hva(vq, (uintptr_t)iov[i].iov_base,
+ iov[i].iov_len);
+ if (r < 0)
+ return r;
+ }
+ return 0;
+ }
+
for (i = 0; i < log_num; ++i) {
u64 l = min(log[i].len, len);
r = log_write(vq->log_base, log[i].addr, l);
@@ -1682,9 +1756,8 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
smp_wmb();
/* Log used flag write. */
used = &vq->used->flags;
- log_write(vq->log_base, vq->log_addr +
- (used - (void __user *)vq->used),
- sizeof vq->used->flags);
+ log_used(vq, (used - (void __user *)vq->used),
+ sizeof vq->used->flags);
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
@@ -1702,9 +1775,8 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
smp_wmb();
/* Log avail event write */
used = vhost_avail_event(vq);
- log_write(vq->log_base, vq->log_addr +
- (used - (void __user *)vq->used),
- sizeof *vhost_avail_event(vq));
+ log_used(vq, (used - (void __user *)vq->used),
+ sizeof *vhost_avail_event(vq));
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
@@ -2103,10 +2175,8 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
/* 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),
- count * sizeof *used);
+ log_used(vq, ((void __user *)used - (void __user *)vq->used),
+ count * sizeof *used);
}
old = vq->last_used_idx;
new = (vq->last_used_idx += count);
@@ -2145,10 +2215,11 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
return -EFAULT;
}
if (unlikely(vq->log_used)) {
+ /* Make sure used idx is seen before log. */
+ smp_wmb();
/* Log used index update. */
- log_write(vq->log_base,
- vq->log_addr + offsetof(struct vring_used, idx),
- sizeof vq->used->idx);
+ log_used(vq, offsetof(struct vring_used, idx),
+ sizeof vq->used->idx);
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 78f3c5fc02e4..e8efe1af7487 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -199,7 +199,8 @@ bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
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);
+ unsigned int log_num, u64 len,
+ struct iovec *iov, int count);
int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 0ec970ca64ce..3cefd602b5b1 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -15,6 +15,7 @@
#include <net/sock.h>
#include <linux/virtio_vsock.h>
#include <linux/vhost.h>
+#include <linux/hashtable.h>
#include <net/af_vsock.h>
#include "vhost.h"
@@ -27,14 +28,14 @@ enum {
/* Used to track all the vhost_vsock instances on the system. */
static DEFINE_SPINLOCK(vhost_vsock_lock);
-static LIST_HEAD(vhost_vsock_list);
+static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8);
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;
+ /* Link to global vhost_vsock_hash, writes use vhost_vsock_lock */
+ struct hlist_node hash;
struct vhost_work send_pkt_work;
spinlock_t send_pkt_list_lock;
@@ -50,12 +51,14 @@ static u32 vhost_transport_get_local_cid(void)
return VHOST_VSOCK_DEFAULT_HOST_CID;
}
+/* Callers that dereference the return value must hold vhost_vsock_lock or the
+ * RCU read lock.
+ */
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) {
+ hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) {
u32 other_cid = vsock->guest_cid;
/* Skip instances that have no CID yet */
@@ -63,11 +66,9 @@ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
continue;
if (other_cid == guest_cid) {
- spin_unlock_bh(&vhost_vsock_lock);
return vsock;
}
}
- spin_unlock_bh(&vhost_vsock_lock);
return NULL;
}
@@ -198,9 +199,12 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
struct vhost_virtqueue *vq;
int len = pkt->len;
+ rcu_read_lock();
+
/* Find the vhost_vsock according to guest context id */
vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid));
if (!vsock) {
+ rcu_read_unlock();
virtio_transport_free_pkt(pkt);
return -ENODEV;
}
@@ -215,6 +219,8 @@ vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
spin_unlock_bh(&vsock->send_pkt_list_lock);
vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+
+ rcu_read_unlock();
return len;
}
@@ -224,12 +230,15 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
struct vhost_vsock *vsock;
struct virtio_vsock_pkt *pkt, *n;
int cnt = 0;
+ int ret = -ENODEV;
LIST_HEAD(freeme);
+ rcu_read_lock();
+
/* Find the vhost_vsock according to guest context id */
vsock = vhost_vsock_get(vsk->remote_addr.svm_cid);
if (!vsock)
- return -ENODEV;
+ goto out;
spin_lock_bh(&vsock->send_pkt_list_lock);
list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
@@ -255,7 +264,10 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
vhost_poll_queue(&tx_vq->poll);
}
- return 0;
+ ret = 0;
+out:
+ rcu_read_unlock();
+ return ret;
}
static struct virtio_vsock_pkt *
@@ -508,6 +520,8 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
goto out;
}
+ vsock->guest_cid = 0; /* no CID assigned yet */
+
atomic_set(&vsock->queued_replies, 0);
vqs[VSOCK_VQ_TX] = &vsock->vqs[VSOCK_VQ_TX];
@@ -521,10 +535,6 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
spin_lock_init(&vsock->send_pkt_list_lock);
INIT_LIST_HEAD(&vsock->send_pkt_list);
vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work);
-
- spin_lock_bh(&vhost_vsock_lock);
- list_add_tail(&vsock->list, &vhost_vsock_list);
- spin_unlock_bh(&vhost_vsock_lock);
return 0;
out:
@@ -551,13 +561,21 @@ static void vhost_vsock_reset_orphans(struct sock *sk)
* executing.
*/
- if (!vhost_vsock_get(vsk->remote_addr.svm_cid)) {
- sock_set_flag(sk, SOCK_DONE);
- vsk->peer_shutdown = SHUTDOWN_MASK;
- sk->sk_state = SS_UNCONNECTED;
- sk->sk_err = ECONNRESET;
- sk->sk_error_report(sk);
- }
+ /* If the peer is still valid, no need to reset connection */
+ if (vhost_vsock_get(vsk->remote_addr.svm_cid))
+ return;
+
+ /* If the close timeout is pending, let it expire. This avoids races
+ * with the timeout callback.
+ */
+ if (vsk->close_work_scheduled)
+ return;
+
+ sock_set_flag(sk, SOCK_DONE);
+ vsk->peer_shutdown = SHUTDOWN_MASK;
+ sk->sk_state = SS_UNCONNECTED;
+ sk->sk_err = ECONNRESET;
+ sk->sk_error_report(sk);
}
static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
@@ -565,9 +583,13 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
struct vhost_vsock *vsock = file->private_data;
spin_lock_bh(&vhost_vsock_lock);
- list_del(&vsock->list);
+ if (vsock->guest_cid)
+ hash_del_rcu(&vsock->hash);
spin_unlock_bh(&vhost_vsock_lock);
+ /* Wait for other CPUs to finish using vsock */
+ synchronize_rcu();
+
/* Iterating over all connections for all CIDs to find orphans is
* inefficient. Room for improvement here. */
vsock_for_each_connected_socket(vhost_vsock_reset_orphans);
@@ -607,12 +629,18 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
return -EINVAL;
/* Refuse if CID is already in use */
+ spin_lock_bh(&vhost_vsock_lock);
other = vhost_vsock_get(guest_cid);
- if (other && other != vsock)
+ if (other && other != vsock) {
+ spin_unlock_bh(&vhost_vsock_lock);
return -EADDRINUSE;
+ }
+
+ if (vsock->guest_cid)
+ hash_del_rcu(&vsock->hash);
- spin_lock_bh(&vhost_vsock_lock);
vsock->guest_cid = guest_cid;
+ hash_add_rcu(vhost_vsock_hash, &vsock->hash, vsock->guest_cid);
spin_unlock_bh(&vhost_vsock_lock);
return 0;
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-01 14:17:53 +0000