Re: [PATCH for-next 4/4] RDMA/efa: CQ notifications

From: Jason Gunthorpe <jgg@nvidia.com>
To: Gal Pressman <galpress@amazon.com>
Cc: Doug Ledford <dledford@redhat.com>,
	linux-rdma@vger.kernel.org,
	Alexander Matushevsky <matua@amazon.com>,
	Firas JahJah <firasj@amazon.com>,
	Yossi Leybovich <sleybo@amazon.com>
Subject: Re: [PATCH for-next 4/4] RDMA/efa: CQ notifications
Date: Thu, 2 Sep 2021 12:10:29 -0300	[thread overview]
Message-ID: <20210902151029.GV1721383@nvidia.com> (raw)
In-Reply-To: <3a5fb37a-dd72-e322-f7c6-790ee4e04efa@amazon.com>

On Thu, Sep 02, 2021 at 06:09:39PM +0300, Gal Pressman wrote:
> On 02/09/2021 16:02, Jason Gunthorpe wrote:
> > On Thu, Sep 02, 2021 at 10:03:16AM +0300, Gal Pressman wrote:
> >> On 01/09/2021 18:36, Jason Gunthorpe wrote:
> >>> On Wed, Sep 01, 2021 at 05:24:43PM +0300, Gal Pressman wrote:
> >>>> On 01/09/2021 14:57, Jason Gunthorpe wrote:
> >>>>> On Wed, Sep 01, 2021 at 02:50:42PM +0300, Gal Pressman wrote:
> >>>>>> On 20/08/2021 21:27, Jason Gunthorpe wrote:
> >>>>>>> On Wed, Aug 11, 2021 at 06:11:31PM +0300, Gal Pressman wrote:
> >>>>>>>> diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c
> >>>>>>>> index 417dea5f90cf..29db4dec02f0 100644
> >>>>>>>> +++ b/drivers/infiniband/hw/efa/efa_main.c
> >>>>>>>> @@ -67,6 +67,46 @@ static void efa_release_bars(struct efa_dev *dev, int bars_mask)
> >>>>>>>>  	pci_release_selected_regions(pdev, release_bars);
> >>>>>>>>  }
> >>>>>>>>  
> >>>>>>>> +static void efa_process_comp_eqe(struct efa_dev *dev, struct efa_admin_eqe *eqe)
> >>>>>>>> +{
> >>>>>>>> +	u16 cqn = eqe->u.comp_event.cqn;
> >>>>>>>> +	struct efa_cq *cq;
> >>>>>>>> +
> >>>>>>>> +	cq = xa_load(&dev->cqs_xa, cqn);
> >>>>>>>> +	if (unlikely(!cq)) {
> >>>>>>>
> >>>>>>> This seems unlikely to be correct, what prevents cq from being
> >>>>>>> destroyed concurrently?
> >>>>>>>
> >>>>>>> A comp_handler cannot be running after cq destroy completes.
> >>>>>>
> >>>>>> Sorry for the long turnaround, was OOO.
> >>>>>>
> >>>>>> The CQ cannot be destroyed until all completion events are acked.
> >>>>>> https://github.com/linux-rdma/rdma-core/blob/7fd01f0c6799f0ecb99cae03c22cf7ff61ffbf5a/libibverbs/man/ibv_get_cq_event.3#L45
> >>>>>> https://github.com/linux-rdma/rdma-core/blob/7fd01f0c6799f0ecb99cae03c22cf7ff61ffbf5a/libibverbs/cmd_cq.c#L208
> >>>>>
> >>>>> That is something quite different, and in userspace.
> >>>>>
> >>>>> What in the kernel prevents tha xa_load and the xa_erase from racing together?
> >>>>
> >>>> Good point.
> >>>> I think we need to surround efa_process_comp_eqe() with an rcu_read_lock() and
> >>>> have a synchronize_rcu() after removing it from the xarray in
> >>>> destroy_cq.
> >>>
> >>> Try to avoid synchronize_rcu()
> >>
> >> I don't see how that's possible?
> > 
> > Usually people use call_rcu() instead
> 
> Oh nice, thanks.
> 
> I think the code would be much simpler using synchronize_rcu(), and the
> destroy_cq flow is usually on the cold path anyway. I also prefer to be certain
> that the CQ is freed once the destroy verb returns and not rely on the callback
> scheduling.

I would not be happy to see synchronize_rcu on uverbs destroy
functions, it is too easy to DOS the kernel with that.

Jason