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

From: Jason Gunthorpe
Date: Thu May 03 2018 - 14:27:10 EST


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@xxxxxxxxxxx>
> > > 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?

Jason