Re: [PATCH] IB/umem: use tgid instead of pid in ib_umem structure

[Jason Gunthorpe <jgg@ziepe.ca>]

On Thu, May 03, 2018 at 09:43:01PM +0300, Leon Romanovsky wrote:
> On Thu, May 03, 2018 at 12:26:56PM -0600, Jason Gunthorpe wrote:
> > On Thu, May 03, 2018 at 09:12:35PM +0300, Leon Romanovsky wrote:
> > > On Thu, May 03, 2018 at 09:33:10AM -0600, Jason Gunthorpe wrote:
> > > > On Thu, May 03, 2018 at 10:04:34PM +0800, Lidong Chen wrote:
> > > > > The userspace may invoke ibv_reg_mr and ibv_dereg_mr by different threads.
> > > > > If when ibv_dereg_mr invoke and the thread which invoked ibv_reg_mr has
> > > > > exited, get_pid_task will return NULL, ib_umem_release does not decrease
> > > > > mm->pinned_vm. This patch fixes it by use tgid.
> > > > >
> > > > > Signed-off-by: Lidong Chen <lidongchen@tencent.com>
> > > > >  drivers/infiniband/core/umem.c | 12 ++++++------
> > > > >  include/rdma/ib_umem.h         |  2 +-
> > > > >  2 files changed, 7 insertions(+), 7 deletions(-)
> > > >
> > > > Why are we even using a struct pid for this? Does anyone know?
> > > >
> > >
> > > Can it be related to "fork" support?
> >
> > Not sure..
> >
> > Ideally we want to hold the struct mm, but we can't hold it long
> > term, so pid is a surrogate for that.
> >
> > > > I'm surprised that struct task isn't held in the struct ib_umem..
> > > >
> > >
> > > I think that this code can be removed and all accesses to mm_struct can
> > > be done with "current->mm".
> >
> > That sounds wrong for fork support, as the mm used in destroy MUST
> > exactly match the mm used in create..
> >
> > How does this accounting work in fork anyhow?
> 
> We are not supporting fork, so this is why I proposed to remove it.

Er, the new kabi certainly can call reg and dereg across a fork

Jason