/**
* rspin_until_writer_unlock - inc reader count & spin until writer is gone
* @lock : Pointer to queue rwlock structure
* @writer: Current queue rwlock writer status byte
*
* In interrupt context or at the head of the queue, the reader will just
* increment the reader count & wait until the writer releases the lock.
*/
static __always_inline void
rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
{
while ((cnts & _QW_WMASK) == _QW_LOCKED) {
cpu_relax_lowlatency();
cnts = atomic_read_acquire(&lock->cnts);
}
}
/**
* queued_write_lock_slowpath - acquire write lock of a queue rwlock
* @lock : Pointer to queue rwlock structure
*/
void queued_write_lock_slowpath(struct qrwlock *lock)
{
u32 cnts;
/* Put the writer into the wait queue */
arch_spin_lock(&lock->lock);
/* Try to acquire the lock directly if no reader is present */
if (!atomic_read(&lock->cnts) &&
(atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0))
goto unlock;
/*
* Set the waiting flag to notify readers that a writer is pending,
* or wait for a previous writer to go away.
*/
for (;;) {
struct __qrwlock *l = (struct __qrwlock *)lock;
if (!READ_ONCE(l->wmode) &&
(cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0))
break;
cpu_relax_lowlatency();
}
/* When no more readers, set the locked flag */
for (;;) {
cnts = atomic_read(&lock->cnts);
if ((cnts == _QW_WAITING) &&
(atomic_cmpxchg_acquire(&lock->cnts, _QW_WAITING,
_QW_LOCKED) == _QW_WAITING))
break;
cpu_relax_lowlatency();
}
unlock:
arch_spin_unlock(&lock->lock);
}
/*
* Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
* Can return NULL in case we were the last queued and we updated @lock instead.
*/
static inline struct optimistic_spin_node *
osq_wait_next(struct optimistic_spin_queue *lock,
struct optimistic_spin_node *node,
struct optimistic_spin_node *prev)
{
struct optimistic_spin_node *next = NULL;
int curr = encode_cpu(smp_processor_id());
int old;
/*
* If there is a prev node in queue, then the 'old' value will be
* the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
* we're currently last in queue, then the queue will then become empty.
*/
old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
for (;;) {
if (atomic_read(&lock->tail) == curr &&
atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
/*
* We were the last queued, we moved @lock back. @prev
* will now observe @lock and will complete its
* unlock()/unqueue().
*/
break;
}
/*
* We must xchg() the @node->next value, because if we were to
* leave it in, a concurrent unlock()/unqueue() from
* @node->next might complete Step-A and think its @prev is
* still valid.
*
* If the concurrent unlock()/unqueue() wins the race, we'll
* wait for either @lock to point to us, through its Step-B, or
* wait for a new @node->next from its Step-C.
*/
if (node->next) {
next = xchg(&node->next, NULL);
if (next)
break;
}
cpu_relax_lowlatency();
}
return next;
}
static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
struct vhost_virtqueue *vq,
struct iovec iov[], unsigned int iov_size,
unsigned int *out_num, unsigned int *in_num)
{
unsigned long uninitialized_var(endtime);
int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
out_num, in_num, NULL, NULL);
if (r == vq->num && vq->busyloop_timeout) {
preempt_disable();
endtime = busy_clock() + vq->busyloop_timeout;
while (vhost_can_busy_poll(vq->dev, endtime) &&
vhost_vq_avail_empty(vq->dev, vq))
cpu_relax_lowlatency();
preempt_enable();
r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
out_num, in_num, NULL, NULL);
}
return r;
}
bool osq_lock(struct optimistic_spin_queue *lock)
{
struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
struct optimistic_spin_node *prev, *next;
int curr = encode_cpu(smp_processor_id());
int old;
node->locked = 0;
node->next = NULL;
node->cpu = curr;
/*
* We need both ACQUIRE (pairs with corresponding RELEASE in
* unlock() uncontended, or fastpath) and RELEASE (to publish
* the node fields we just initialised) semantics when updating
* the lock tail.
*/
old = atomic_xchg(&lock->tail, curr);
if (old == OSQ_UNLOCKED_VAL)
return true;
prev = decode_cpu(old);
node->prev = prev;
WRITE_ONCE(prev->next, node);
/*
* Normally @prev is untouchable after the above store; because at that
* moment unlock can proceed and wipe the node element from stack.
*
* However, since our nodes are static per-cpu storage, we're
* guaranteed their existence -- this allows us to apply
* cmpxchg in an attempt to undo our queueing.
*/
while (!READ_ONCE(node->locked)) {
/*
* If we need to reschedule bail... so we can block.
*/
if (need_resched())
goto unqueue;
cpu_relax_lowlatency();
}
return true;
unqueue:
/*
* Step - A -- stabilize @prev
*
* Undo our @prev->next assignment; this will make @prev's
* unlock()/unqueue() wait for a next pointer since @lock points to us
* (or later).
*/
for (;;) {
if (prev->next == node &&
cmpxchg(&prev->next, node, NULL) == node)
break;
/*
* We can only fail the cmpxchg() racing against an unlock(),
* in which case we should observe @node->locked becomming
* true.
*/
if (smp_load_acquire(&node->locked))
return true;
cpu_relax_lowlatency();
/*
* Or we race against a concurrent unqueue()'s step-B, in which
* case its step-C will write us a new @node->prev pointer.
*/
prev = READ_ONCE(node->prev);
}
/*
* Step - B -- stabilize @next
*
* Similar to unlock(), wait for @node->next or move @lock from @node
* back to @prev.
*/
next = osq_wait_next(lock, node, prev);
if (!next)
return false;
/*
* Step - C -- unlink
*
* @prev is stable because its still waiting for a new @prev->next
* pointer, @next is stable because our @node->next pointer is NULL and
* it will wait in Step-A.
*/
WRITE_ONCE(next->prev, prev);
WRITE_ONCE(prev->next, next);
return false;
}
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned out, in;
int head;
struct msghdr msg = {
.msg_name = NULL,
.msg_namelen = 0,
.msg_control = NULL,
.msg_controllen = 0,
.msg_flags = MSG_DONTWAIT,
};
size_t len, total_len = 0;
int err;
size_t hdr_size;
struct socket *sock;
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
bool zcopy, zcopy_used;
mutex_lock(&vq->mutex);
sock = vq->private_data;
if (!sock)
goto out;
vhost_disable_notify(&net->dev, vq);
hdr_size = nvq->vhost_hlen;
zcopy = nvq->ubufs;
for (;;) {
/* Release DMAs done buffers first */
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_net_tx_get_vq_desc(net, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in);
/* On error, stop handling until the next kick. */
if (unlikely(head < 0))
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
}
break;
}
if (in) {
vq_err(vq, "Unexpected descriptor format for TX: "
"out %d, int %d\n", out, in);
break;
}
/* Skip header. TODO: support TSO. */
len = iov_length(vq->iov, out);
iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
iov_iter_advance(&msg.msg_iter, hdr_size);
/* Sanity check */
if (!msg_data_left(&msg)) {
vq_err(vq, "Unexpected header len for TX: "
"%zd expected %zd\n",
len, hdr_size);
break;
}
len = msg_data_left(&msg);
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 = cpu_to_vhost32(vq, head);
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;
atomic_inc(&ubufs->refcount);
nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
} else {
msg.msg_control = NULL;
ubufs = NULL;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(sock, &msg, len);
if (unlikely(err < 0)) {
if (zcopy_used) {
vhost_net_ubuf_put(ubufs);
nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
% UIO_MAXIOV;
}
vhost_discard_vq_desc(vq, 1);
break;
}
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
if (!zcopy_used)
vhost_add_used_and_signal(&net->dev, vq, head, 0);
else
vhost_zerocopy_signal_used(net, vq);
total_len += len;
vhost_net_tx_packet(net);
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
}
out:
mutex_unlock(&vq->mutex);
}
static int peek_head_len(struct sock *sk)
{
struct sk_buff *head;
int len = 0;
unsigned long flags;
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
head = skb_peek(&sk->sk_receive_queue);
if (likely(head)) {
len = head->len;
if (skb_vlan_tag_present(head))
len += VLAN_HLEN;
}
spin_unlock_irqrestore(&sk->sk_receive_queue.lock, flags);
return len;
}
static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
{
struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
struct vhost_virtqueue *vq = &nvq->vq;
unsigned long uninitialized_var(endtime);
int len = peek_head_len(sk);
if (!len && vq->busyloop_timeout) {
/* Both tx vq and rx socket were polled here */
mutex_lock(&vq->mutex);
vhost_disable_notify(&net->dev, vq);
preempt_disable();
endtime = busy_clock() + vq->busyloop_timeout;
while (vhost_can_busy_poll(&net->dev, endtime) &&
skb_queue_empty(&sk->sk_receive_queue) &&
vhost_vq_avail_empty(&net->dev, vq))
cpu_relax_lowlatency();
preempt_enable();
if (vhost_enable_notify(&net->dev, vq))
vhost_poll_queue(&vq->poll);
mutex_unlock(&vq->mutex);
len = peek_head_len(sk);
}
return len;
}
/* This is a multi-buffer version of vhost_get_desc, that works if
* vq has read descriptors only.
* @vq - the relevant virtqueue
* @datalen - data length we'll be reading
* @iovcount - returned count of io vectors we fill
* @log - vhost log
* @log_num - log offset
* @quota - headcount quota, 1 for big buffer
* returns number of buffer heads allocated, negative on error
*/
static int get_rx_bufs(struct vhost_virtqueue *vq,
struct vring_used_elem *heads,
int datalen,
unsigned *iovcount,
struct vhost_log *log,
unsigned *log_num,
unsigned int quota)
{
unsigned int out, in;
int seg = 0;
int headcount = 0;
unsigned d;
int r, nlogs = 0;
/* len is always initialized before use since we are always called with
* datalen > 0.
*/
u32 uninitialized_var(len);
while (datalen > 0 && headcount < quota) {
if (unlikely(seg >= UIO_MAXIOV)) {
r = -ENOBUFS;
goto err;
}
r = vhost_get_vq_desc(vq, vq->iov + seg,
ARRAY_SIZE(vq->iov) - seg, &out,
&in, log, log_num);
if (unlikely(r < 0))
goto err;
d = r;
if (d == vq->num) {
r = 0;
goto err;
}
if (unlikely(out || in <= 0)) {
vq_err(vq, "unexpected descriptor format for RX: "
"out %d, in %d\n", out, in);
r = -EINVAL;
goto err;
}
if (unlikely(log)) {
nlogs += *log_num;
log += *log_num;
}
heads[headcount].id = cpu_to_vhost32(vq, d);
len = iov_length(vq->iov + seg, in);
heads[headcount].len = cpu_to_vhost32(vq, len);
datalen -= len;
++headcount;
seg += in;
}
heads[headcount - 1].len = cpu_to_vhost32(vq, len + datalen);
*iovcount = seg;
if (unlikely(log))
*log_num = nlogs;
/* Detect overrun */
if (unlikely(datalen > 0)) {
r = UIO_MAXIOV + 1;
goto err;
}
return headcount;
err:
vhost_discard_vq_desc(vq, headcount);
return r;
}
