Re: [PATCH V2 2/2] tcm_vhost: Use vq->private_data to indicate if the endpoint is setup

["Michael S. Tsirkin" <mst@redhat.com>]

On Mon, Apr 01, 2013 at 10:13:47AM +0800, Asias He wrote:
> On Sun, Mar 31, 2013 at 11:20:24AM +0300, Michael S. Tsirkin wrote:
> > On Fri, Mar 29, 2013 at 02:22:52PM +0800, Asias He wrote:
> > > On Thu, Mar 28, 2013 at 11:18:22AM +0200, Michael S. Tsirkin wrote:
> > > > On Thu, Mar 28, 2013 at 04:10:02PM +0800, Asias He wrote:
> > > > > On Thu, Mar 28, 2013 at 08:16:59AM +0200, Michael S. Tsirkin wrote:
> > > > > > On Thu, Mar 28, 2013 at 10:17:28AM +0800, Asias He wrote:
> > > > > > > Currently, vs->vs_endpoint is used indicate if the endpoint is setup or
> > > > > > > not. It is set or cleared in vhost_scsi_set_endpoint() or
> > > > > > > vhost_scsi_clear_endpoint() under the vs->dev.mutex lock. However, when
> > > > > > > we check it in vhost_scsi_handle_vq(), we ignored the lock.
> > > > > > > 
> > > > > > > Instead of using the vs->vs_endpoint and the vs->dev.mutex lock to
> > > > > > > indicate the status of the endpoint, we use per virtqueue
> > > > > > > vq->private_data to indicate it. In this way, we can only take the
> > > > > > > vq->mutex lock which is per queue and make the concurrent multiqueue
> > > > > > > process having less lock contention. Further, in the read side of
> > > > > > > vq->private_data, we can even do not take only lock if it is accessed in
> > > > > > > the vhost worker thread, because it is protected by "vhost rcu".
> > > > > > > 
> > > > > > > Signed-off-by: Asias He <asias@redhat.com>
> > > > > > > ---
> > > > > > >  drivers/vhost/tcm_vhost.c | 38 +++++++++++++++++++++++++++++++++-----
> > > > > > >  1 file changed, 33 insertions(+), 5 deletions(-)
> > > > > > > 
> > > > > > > diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c
> > > > > > > index 5e3d4487..0524267 100644
> > > > > > > --- a/drivers/vhost/tcm_vhost.c
> > > > > > > +++ b/drivers/vhost/tcm_vhost.c
> > > > > > > @@ -67,7 +67,6 @@ struct vhost_scsi {
> > > > > > >  	/* Protected by vhost_scsi->dev.mutex */
> > > > > > >  	struct tcm_vhost_tpg *vs_tpg[VHOST_SCSI_MAX_TARGET];
> > > > > > >  	char vs_vhost_wwpn[TRANSPORT_IQN_LEN];
> > > > > > > -	bool vs_endpoint;
> > > > > > >  
> > > > > > >  	struct vhost_dev dev;
> > > > > > >  	struct vhost_virtqueue vqs[VHOST_SCSI_MAX_VQ];
> > > > > > > @@ -91,6 +90,24 @@ static int iov_num_pages(struct iovec *iov)
> > > > > > >  	       ((unsigned long)iov->iov_base & PAGE_MASK)) >> PAGE_SHIFT;
> > > > > > >  }
> > > > > > >  
> > > > > > > +static bool tcm_vhost_check_endpoint(struct vhost_virtqueue *vq)
> > > > > > > +{
> > > > > > > +	bool ret = false;
> > > > > > > +
> > > > > > > +	/*
> > > > > > > +	 * 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
> > > > > > > +	 */
> > > > > > > +	if (rcu_dereference_check(vq->private_data, 1))
> > > > > > > +		ret = true;
> > > > > > > +
> > > > > > > +	return ret;
> > > > > > > +}
> > > > > > > +
> > > > > > >  static int tcm_vhost_check_true(struct se_portal_group *se_tpg)
> > > > > > >  {
> > > > > > >  	return 1;
> > > > > > > @@ -581,8 +598,7 @@ static void vhost_scsi_handle_vq(struct vhost_scsi *vs,
> > > > > > >  	int head, ret;
> > > > > > >  	u8 target;
> > > > > > >  
> > > > > > > -	/* Must use ioctl VHOST_SCSI_SET_ENDPOINT */
> > > > > > > -	if (unlikely(!vs->vs_endpoint))
> > > > > > > +	if (!tcm_vhost_check_endpoint(vq))
> > > > > > >  		return;
> > > > > > >
> > > > > > 
> > > > > > I would just move the check to under vq mutex,
> > > > > > and avoid rcu completely. In vhost-net we are using
> > > > > > private data outside lock so we can't do this,
> > > > > > no such issue here.
> > > > > 
> > > > > Are you talking about:
> > > > > 
> > > > >    handle_tx:
> > > > >            /* TODO: check that we are running from vhost_worker? */
> > > > >            sock = rcu_dereference_check(vq->private_data, 1);
> > > > >            if (!sock)
> > > > >                    return;
> > > > >    
> > > > >            wmem = atomic_read(&sock->sk->sk_wmem_alloc);
> > > > >            if (wmem >= sock->sk->sk_sndbuf) {
> > > > >                    mutex_lock(&vq->mutex);
> > > > >                    tx_poll_start(net, sock);
> > > > >                    mutex_unlock(&vq->mutex);
> > > > >                    return;
> > > > >            }
> > > > >            mutex_lock(&vq->mutex);
> > > > > 
> > > > > Why not do the atomic_read and tx_poll_start under the vq->mutex, and thus do
> > > > > the check under the lock as well.
> > > > >    
> > > > >    handle_rx:
> > > > >            mutex_lock(&vq->mutex);
> > > > >    
> > > > >            /* TODO: check that we are running from vhost_worker? */
> > > > >            struct socket *sock = rcu_dereference_check(vq->private_data, 1);
> > > > >    
> > > > >            if (!sock)
> > > > >                    return;
> > > > >    
> > > > >            mutex_lock(&vq->mutex);
> > > > > 
> > > > > Can't we can do the check under the vq->mutex here?
> > > > > 
> > > > > The rcu is still there but it makes the code easier to read. IMO, If we want to
> > > > > use rcu, use it explicitly and avoid the vhost rcu completely. 
> > > > > 
> > > > > > >  	mutex_lock(&vq->mutex);
> > > > > > > @@ -829,11 +845,12 @@ static int vhost_scsi_set_endpoint(
> > > > > > >  		       sizeof(vs->vs_vhost_wwpn));
> > > > > > >  		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
> > > > > > >  			vq = &vs->vqs[i];
> > > > > > > +			/* Flushing the vhost_work acts as synchronize_rcu */
> > > > > > >  			mutex_lock(&vq->mutex);
> > > > > > > +			rcu_assign_pointer(vq->private_data, vs);
> > > > > > >  			vhost_init_used(vq);
> > > > > > >  			mutex_unlock(&vq->mutex);
> > > > > > >  		}
> > > > > > > -		vs->vs_endpoint = true;
> > > > > > >  		ret = 0;
> > > > > > >  	} else {
> > > > > > >  		ret = -EEXIST;
> > > > > > 
> > > > > > 
> > > > > > There's also some weird smp_mb__after_atomic_inc() with no
> > > > > > atomic in sight just above ... Nicholas what was the point there?
> > > > > > 
> > > > > > 
> > > > > > > @@ -849,6 +866,8 @@ static int vhost_scsi_clear_endpoint(
> > > > > > >  {
> > > > > > >  	struct tcm_vhost_tport *tv_tport;
> > > > > > >  	struct tcm_vhost_tpg *tv_tpg;
> > > > > > > +	struct vhost_virtqueue *vq;
> > > > > > > +	bool match = false;
> > > > > > >  	int index, ret, i;
> > > > > > >  	u8 target;
> > > > > > >  
> > > > > > > @@ -884,9 +903,18 @@ static int vhost_scsi_clear_endpoint(
> > > > > > >  		}
> > > > > > >  		tv_tpg->tv_tpg_vhost_count--;
> > > > > > >  		vs->vs_tpg[target] = NULL;
> > > > > > > -		vs->vs_endpoint = false;
> > > > > > > +		match = true;
> > > > > > >  		mutex_unlock(&tv_tpg->tv_tpg_mutex);
> > > > > > >  	}
> > > > > > > +	if (match) {
> > > > > > > +		for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) {
> > > > > > > +			vq = &vs->vqs[i];
> > > > > > > +			/* Flushing the vhost_work acts as synchronize_rcu */
> > > > > > > +			mutex_lock(&vq->mutex);
> > > > > > > +			rcu_assign_pointer(vq->private_data, NULL);
> > > > > > > +			mutex_unlock(&vq->mutex);
> > > > > > > +		}
> > > > > > > +	}
> > > > > > 
> > > > > > I'm trying to understand what's going on here.
> > > > > > Does vhost_scsi only have a single target?
> > > > > > Because the moment you clear one target you
> > > > > > also set private_data to NULL ...
> > > > > 
> > > > > vhost_scsi supports multi target. Currently, We can not disable specific target
> > > > > under the wwpn. When we clear or set the endpoint, we disable or enable all the
> > > > > targets under the wwpn.
> > > > 
> > > > okay, but changing vs->vs_tpg[target] under dev mutex, then using
> > > > it under vq mutex looks wrong.
> > > 
> > > I do not see a problem here.
> > > 
> > > Access of vs->vs_tpg[target] in vhost_scsi_handle_vq() happens only when
> > > the SET_ENDPOINT is done.
> > 
> > But nothing prevents multiple SET_ENDPOINT calls while
> > the previous one is in progress.
> 
> vhost_scsi_set_endpoint() and vhost_scsi_clear_endpoint() are protected
> by vs->dev.mutex, no?
> 
> And in vhost_scsi_set_endpoint():
> 
> 	if (tv_tpg->tv_tpg_vhost_count != 0) {
> 		mutex_unlock(&tv_tpg->tv_tpg_mutex);
> 		continue;
> 	}
> 
> This prevents calling of vhost_scsi_set_endpoint before we call
> vhost_scsi_clear_endpoint to decrease tv_tpg->tv_tpg_vhost_count.

All this seems to do is prevent reusing the same target
in multiple vhosts.

> > > At that time, the vs->vs_tpg[] is already
> > > ready. Even if the vs->vs_tpg[target] is changed to NULL in
> > > CLEAR_ENDPOINT, it is safe since we fail the request if
> > > vs->vs_tpg[target] is NULL.
> > 
> > We check it without a common lock so it can become NULL
> > after we test it.
> 
> 
> vhost_scsi_handle_vq:
> 
>      tv_tpg = vs->vs_tpg[target];	
>      if (!tv_tpg)
>          we fail the cmd
>      ...
> 
>      INIT_WORK(&tv_cmd->work, tcm_vhost_submission_work);
>      queue_work(tcm_vhost_workqueue, &tv_cmd->work);
> 
> So, after we test tv_tpg, event if vs->vs_tpg[target] become NULL, it
> does not matter if the tpg is not deleted by calling tcm_vhost_drop_tpg().
> tcm_vhost_drop_tpg() will not succeed if we do not call vhost_scsi_clear_endpoint() 
> Becasue, tcm_vhost_drop_tpg -> tcm_vhost_drop_nexus ->  check if (tpg->tv_tpg_vhost_count != 0) 

My point is this:
		tv_tpg = vs->vs_tpg[target];
		if (!tv_tpg) {
			....
			return
		}

                tv_cmd = vhost_scsi_allocate_cmd(tv_tpg, &v_req,

above line can legally reread vs->vs_tpg[target] from array.
You need ACCESS_ONCE if you don't want that.

> Further, the tcm core should fail the cmd if the tpg is gonna when we submit the cmd in
> tcm_vhost_submission_work. (nab, is this true?)
> 
> > > > Since we want to use private_data anyway, how about
> > > > making private_data point at struct tcm_vhost_tpg * ?
> > > > 
> > > > Allocate it dynamically in SET_ENDPOINT (and free old value if any).
> > > 
> > > The struct tcm_vhost_tpg is per target. I assume you want to point
> > > private_data to the 'struct tcm_vhost_tpg *vs_tpg[VHOST_SCSI_MAX_TARGET]'
> > 
> > No, I want to put it at the array of targets.
> 
> tcm_vhost_tpg is allocated in tcm_vhost_make_tpg. There is no array of
> the targets. The targets exist when user create them in host side using
> targetcli tools or /sys/kernel/config interface.

I really simply mean this field:
	        struct tcm_vhost_tpg *vs_tpg[VHOST_SCSI_MAX_TARGET];

allocate it dynamically when endpoint is set, and
set private data for each vq.

> > > > 
> > > > > > 
> > > > > > >  	mutex_unlock(&vs->dev.mutex);
> > > > > > >  	return 0;
> > > > > > >  
> > > > > > > -- 
> > > > > > > 1.8.1.4
> > > > > 
> > > > > -- 
> > > > > Asias
> > > 
> > > -- 
> > > Asias
> 
> -- 
> Asias