在 2018/3/13 17:40, Leon Romanovsky 写道:
> On Tue, Mar 13, 2018 at 04:59:56PM +0800, oulijun wrote:
>> 在 2018/3/12 22:16, Leon Romanovsky 写道:
>>> From: Leon Romanovsky <leonro@xxxxxxxxxxxx>
>>>
>>> Hi,
>>>
>>> The reason to this patchset is described in "RDMA/mlx4: Clear all
>>> allocated memory by default" accommodated with relevant crash report.
>>>
>> Hi， leon
>> I have noted your patchset and know the patch RDMA/mlx4: Clear all allocated memory by default
>> how to test the crash on others? I want to know if all places need to use kzalloc instead of
>> kmalloc and use kcalloc instead of kmalloc_array?
>
> I'm working on new version of this fix which won't require from driver authors
> such changes from kmalloc to kzalloc.
>
> In meantime, you can take latest rdma-next compile with KASAN enabled
> and run ibv_rc_pingpong, if the server's memory is dirty, you will get crash
> for PD object.
>
> 59 struct ib_pd *hns_roce_alloc_pd(struct ib_device *ib_dev,
> 60 struct ib_ucontext *context,
> 61 struct ib_udata *udata)
> 62 {
> 63 struct hns_roce_dev *hr_dev = to_hr_dev(ib_dev);
> 64 struct device *dev = hr_dev->dev;
> 65 struct hns_roce_pd *pd;
> 66 int ret;
> 67
> 68 pd = kmalloc(sizeof(*pd), GFP_KERNEL);
> 69 if (!pd)
> 70 return ERR_PTR(-ENOMEM);
>
> Thanks
>
Thanks， it is fine to me.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
