Re: [PATCH] RDMA/rxe: For invalidate compare according to set keys in mr

[Bob Pearson <rpearsonhpe@gmail.com>]

On 7/22/22 11:50, haris iqbal wrote:
> On Fri, Jul 22, 2022 at 5:14 PM Jason Gunthorpe <jgg@ziepe.ca> wrote:
>>
>> On Fri, Jul 22, 2022 at 05:10:46PM +0200, haris iqbal wrote:
>>> On Fri, Jul 15, 2022 at 11:21 AM haris iqbal <haris.phnx@gmail.com> wrote:
>>>>
>>>> On Thu, Jul 7, 2022 at 9:30 AM Md Haris Iqbal <haris.phnx@gmail.com> wrote:
>>>>>
>>>>> The 'rkey' input can be an lkey or rkey, and in rxe the lkey or rkey have
>>>>> the same value, including the variant bits.
>>>>>
>>>>> So, if mr->rkey is set, compare the invalidate key with it, otherwise
>>>>> compare with the mr->lkey.
>>>>>
>>>>> Since we already did a lookup on the non-varient bits to get this far,
>>>>> the check's only purpose is to confirm that the wqe has the correct
>>>>> variant bits.
>>>>>
>>>>> Fixes: 001345339f4c ("RDMA/rxe: Separate HW and SW l/rkeys")
>>>>> Cc: rpearsonhpe@gmail.com
>>>>> Signed-off-by: Md Haris Iqbal <haris.phnx@gmail.com>
>>>>> ---
>>>>>  drivers/infiniband/sw/rxe/rxe_loc.h |  2 +-
>>>>>  drivers/infiniband/sw/rxe/rxe_mr.c  | 12 ++++++------
>>>>>  2 files changed, 7 insertions(+), 7 deletions(-)
>>>>>
>>>>> diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
>>>>> index 0e022ae1b8a5..37484a559d20 100644
>>>>> --- a/drivers/infiniband/sw/rxe/rxe_loc.h
>>>>> +++ b/drivers/infiniband/sw/rxe/rxe_loc.h
>>>>> @@ -77,7 +77,7 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
>>>>>                          enum rxe_mr_lookup_type type);
>>>>>  int mr_check_range(struct rxe_mr *mr, u64 iova, size_t length);
>>>>>  int advance_dma_data(struct rxe_dma_info *dma, unsigned int length);
>>>>> -int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey);
>>>>> +int rxe_invalidate_mr(struct rxe_qp *qp, u32 key);
>>>>>  int rxe_reg_fast_mr(struct rxe_qp *qp, struct rxe_send_wqe *wqe);
>>>>>  int rxe_mr_set_page(struct ib_mr *ibmr, u64 addr);
>>>>>  int rxe_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
>>>>> diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
>>>>> index fc3942e04a1f..3add52129006 100644
>>>>> --- a/drivers/infiniband/sw/rxe/rxe_mr.c
>>>>> +++ b/drivers/infiniband/sw/rxe/rxe_mr.c
>>>>> @@ -576,22 +576,22 @@ struct rxe_mr *lookup_mr(struct rxe_pd *pd, int access, u32 key,
>>>>>         return mr;
>>>>>  }
>>>>>
>>>>> -int rxe_invalidate_mr(struct rxe_qp *qp, u32 rkey)
>>>>> +int rxe_invalidate_mr(struct rxe_qp *qp, u32 key)
>>>>>  {
>>>>>         struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
>>>>>         struct rxe_mr *mr;
>>>>>         int ret;
>>>>>
>>>>> -       mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8);
>>>>> +       mr = rxe_pool_get_index(&rxe->mr_pool, key >> 8);
>>>>>         if (!mr) {
>>>>> -               pr_err("%s: No MR for rkey %#x\n", __func__, rkey);
>>>>> +               pr_err("%s: No MR for key %#x\n", __func__, key);
>>>>>                 ret = -EINVAL;
>>>>>                 goto err;
>>>>>         }
>>>>>
>>>>> -       if (rkey != mr->rkey) {
>>>>> -               pr_err("%s: rkey (%#x) doesn't match mr->rkey (%#x)\n",
>>>>> -                       __func__, rkey, mr->rkey);
>>>>> +       if (mr->rkey ? (key != mr->rkey) : (key != mr->lkey)) {
>>>>> +               pr_err("%s: wr key (%#x) doesn't match mr key (%#x)\n",
>>>>> +                       __func__, key, (mr->rkey ? mr->rkey : mr->lkey));
>>>>>                 ret = -EINVAL;
>>>>>                 goto err_drop_ref;
>>>>>         }
>>>>
>>>> Ping.
>>>
>>> Ping.
>>>
>>> Does this need more discussions or changes?
>>
>> I was hoping Bob would say something but I am happy with it..
> 
> Thanks Jason for the response.
> We can wait for Bob to share his thoughts.
> 
>>
>> JasonFine by me

Reviewed-by: Bob Pearson <rpearsonhpe@gmail.com>