All of lore.kernel.org
 help / color / mirror / Atom feed
From: 858585 jemmy <jemmy858585@gmail.com>
To: Jason Gunthorpe <jgg@ziepe.ca>
Cc: dledford@redhat.com, akpm@linux-foundation.org,
	qing.huang@oracle.com, Leon Romanovsky <leon@kernel.org>,
	artemyko@mellanox.com, dan.j.williams@intel.com,
	linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org,
	adido@mellanox.com, Gal Shachaf <galsha@mellanox.com>,
	Aviad Yehezkel <aviadye@mellanox.com>,
	Lidong Chen <lidongchen@tencent.com>
Subject: Re: [PATCH] IB/umem: use tgid instead of pid in ib_umem structure
Date: Fri, 4 May 2018 16:51:15 +0800	[thread overview]
Message-ID: <CAOGPPbenmtuFwCuGMFJDZrqK+D5atkhK+srm+2yX=+CAwgjPHQ@mail.gmail.com> (raw)
In-Reply-To: <CAOGPPbd8ysq3XDpa4TYQpWVMmpVo4NPhPw5NWyQS1OSc6rXjQQ@mail.gmail.com>

On Fri, May 4, 2018 at 11:14 AM, 858585 jemmy <jemmy858585@gmail.com> wrote:
> On Thu, May 3, 2018 at 11:33 PM, Jason Gunthorpe <jgg@ziepe.ca> 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?
>
> commit 87773dd56d5405ac28119fcfadacefd35877c18f add pid in ib_umem structure.
>
> and the comment has such information:
> Later a different process with a different mm_struct than the one that
> allocated the ib_umem struct
> ends up releasing it which results in decrementing the new processes
> mm->pinned_vm count past
> zero and wrapping.
>

I think a different process should not have the permission to release ib_umem.
so maybe the reason is not a different process?
can ib_umem_release be invoked in interrupt context?

>>
>> I'm surprised that struct task isn't held in the struct ib_umem..
>>
>> Is group_leader really OK and always guarenteed to return the same
>> struct mm?? For some reason I have this recollection that the leader
>> can change under some situation..
>>
>>> diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
>>> index 9a4e899..8813ba5 100644
>>> --- a/drivers/infiniband/core/umem.c
>>> +++ b/drivers/infiniband/core/umem.c
>>> @@ -119,7 +119,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
>>>       umem->length     = size;
>>>       umem->address    = addr;
>>>       umem->page_shift = PAGE_SHIFT;
>>> -     umem->pid        = get_task_pid(current, PIDTYPE_PID);
>>> +     umem->tgid       = get_task_pid(current->group_leader, PIDTYPE_PID);
>>>       /*
>>>        * We ask for writable memory if any of the following
>>>        * access flags are set.  "Local write" and "remote write"
>>> @@ -132,7 +132,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
>>>                IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
>>>
>>>       if (access & IB_ACCESS_ON_DEMAND) {
>>> -             put_pid(umem->pid);
>>> +             put_pid(umem->tgid);
>>>               ret = ib_umem_odp_get(context, umem, access);
>>>               if (ret) {
>>>                       kfree(umem);
>>> @@ -148,7 +148,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
>>>
>>>       page_list = (struct page **) __get_free_page(GFP_KERNEL);
>>>       if (!page_list) {
>>> -             put_pid(umem->pid);
>>> +             put_pid(umem->tgid);
>>>               kfree(umem);
>>>               return ERR_PTR(-ENOMEM);
>>>       }
>>> @@ -231,7 +231,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
>>>       if (ret < 0) {
>>>               if (need_release)
>>>                       __ib_umem_release(context->device, umem, 0);
>>> -             put_pid(umem->pid);
>>> +             put_pid(umem->tgid);
>>>               kfree(umem);
>>>       } else
>>>               current->mm->pinned_vm = locked;
>>> @@ -274,8 +274,8 @@ void ib_umem_release(struct ib_umem *umem)
>>>
>>>       __ib_umem_release(umem->context->device, umem, 1);
>>>
>>> -     task = get_pid_task(umem->pid, PIDTYPE_PID);
>>> -     put_pid(umem->pid);
>>> +     task = get_pid_task(umem->tgid, PIDTYPE_PID);
>>> +     put_pid(umem->tgid);
>>>       if (!task)
>>>               goto out;
>>>       mm = get_task_mm(task);
>>> diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
>>> index 23159dd..2398849 100644
>>> --- a/include/rdma/ib_umem.h
>>> +++ b/include/rdma/ib_umem.h
>>> @@ -48,7 +48,7 @@ struct ib_umem {
>>>       int                     writable;
>>>       int                     hugetlb;
>>>       struct work_struct      work;
>>> -     struct pid             *pid;
>>> +     struct pid             *tgid;
>>>       struct mm_struct       *mm;
>>>       unsigned long           diff;
>>>       struct ib_umem_odp     *odp_data;
>>> --
>>> 1.8.3.1
>>>

  reply	other threads:[~2018-05-04  8:51 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-03 14:04 [PATCH] IB/umem: use tgid instead of pid in ib_umem structure Lidong Chen
2018-05-03 15:33 ` Jason Gunthorpe
2018-05-03 18:12   ` Leon Romanovsky
2018-05-03 18:26     ` Jason Gunthorpe
2018-05-03 18:43       ` Leon Romanovsky
2018-05-03 22:01         ` Jason Gunthorpe
2018-05-04  8:32           ` 858585 jemmy
2018-05-04 13:39             ` Leon Romanovsky
2018-05-04 15:14               ` lidongchen(陈立东)
2018-05-04  2:41   ` 858585 jemmy
2018-05-04  3:14   ` 858585 jemmy
2018-05-04  8:51     ` 858585 jemmy [this message]
2018-05-04 18:23       ` Jason Gunthorpe
2018-05-07  1:38         ` 858585 jemmy
2018-05-08  6:30           ` Jason Gunthorpe
2018-05-08  8:32             ` 858585 jemmy

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAOGPPbenmtuFwCuGMFJDZrqK+D5atkhK+srm+2yX=+CAwgjPHQ@mail.gmail.com' \
    --to=jemmy858585@gmail.com \
    --cc=adido@mellanox.com \
    --cc=akpm@linux-foundation.org \
    --cc=artemyko@mellanox.com \
    --cc=aviadye@mellanox.com \
    --cc=dan.j.williams@intel.com \
    --cc=dledford@redhat.com \
    --cc=galsha@mellanox.com \
    --cc=jgg@ziepe.ca \
    --cc=leon@kernel.org \
    --cc=lidongchen@tencent.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=qing.huang@oracle.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.