mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: Eli Cohen <elic@nvidia.com>
Cc: mst@redhat.com, virtualization@lists.linux-foundation.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/2] vdpa/mlx5: Support creating resources with uid == 0
Date: Mon, 31 May 2021 14:43:59 +0800	[thread overview]
Message-ID: <3717ebc5-66ce-2d50-1853-49442a8e71e1@redhat.com> (raw)
In-Reply-To: <20210531045914.GB158940@mtl-vdi-166.wap.labs.mlnx>


在 2021/5/31 下午12:59, Eli Cohen 写道:
> On Mon, May 31, 2021 at 11:06:59AM +0800, Jason Wang wrote:
>> 在 2021/5/31 上午11:02, Jason Wang 写道:
>>> 在 2021/5/30 下午3:54, Eli Cohen 写道:
>>>> Currently all resources must be created with uid != 0 which is essential
>>>> userspace processes allocating virtquueue resources. Since this is a
>>>> kernel implementation, it is perfectly legal to open resources with
>>>> uid == 0.
>>>>
>>>> In case frimware supports, avoid allocating user context.
>>>
>>> Typo "frimware".
>>>
>>> Otherwise.
>>>
>>> Acked-by: Jason Wang <jasowang@redhat.com>
>>>
>>> (I don't see any code to check the firmware capability, is this
>>> intended?)
>>
>> Speak too fast. I see the MLX5_CAP_GEN(), so it's fine.
> And I responded too fast :-)


Right and thanks for the quick response :)


>> Thanks
>>
>>
>>> Thanks
>>>
>>>
>>>> Signed-off-by: Eli Cohen <elic@nvidia.com>
>>>> ---
>>>>    drivers/vdpa/mlx5/core/resources.c | 6 ++++++
>>>>    include/linux/mlx5/mlx5_ifc.h      | 4 +++-
>>>>    2 files changed, 9 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/drivers/vdpa/mlx5/core/resources.c
>>>> b/drivers/vdpa/mlx5/core/resources.c
>>>> index 6521cbd0f5c2..836ab9ef0fa6 100644
>>>> --- a/drivers/vdpa/mlx5/core/resources.c
>>>> +++ b/drivers/vdpa/mlx5/core/resources.c
>>>> @@ -54,6 +54,9 @@ static int create_uctx(struct mlx5_vdpa_dev
>>>> *mvdev, u16 *uid)
>>>>        void *in;
>>>>        int err;
>>>>    +    if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0))
>>>> +        return 0;
>>>> +
>>>>        /* 0 means not supported */
>>>>        if (!MLX5_CAP_GEN(mvdev->mdev, log_max_uctx))
>>>>            return -EOPNOTSUPP;
>>>> @@ -79,6 +82,9 @@ static void destroy_uctx(struct mlx5_vdpa_dev
>>>> *mvdev, u32 uid)
>>>>        u32 out[MLX5_ST_SZ_DW(destroy_uctx_out)] = {};
>>>>        u32 in[MLX5_ST_SZ_DW(destroy_uctx_in)] = {};
>>>>    +    if (!uid)
>>>> +        return;
>>>> +
>>>>        MLX5_SET(destroy_uctx_in, in, opcode, MLX5_CMD_OP_DESTROY_UCTX);
>>>>        MLX5_SET(destroy_uctx_in, in, uid, uid);
>>>>    diff --git a/include/linux/mlx5/mlx5_ifc.h
>>>> b/include/linux/mlx5/mlx5_ifc.h
>>>> index 9c68b2da14c6..606d2aeacad4 100644
>>>> --- a/include/linux/mlx5/mlx5_ifc.h
>>>> +++ b/include/linux/mlx5/mlx5_ifc.h
>>>> @@ -1487,7 +1487,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
>>>>        u8         uar_4k[0x1];
>>>>        u8         reserved_at_241[0x9];
>>>>        u8         uar_sz[0x6];
>>>> -    u8         reserved_at_250[0x8];
>>>> +    u8         reserved_at_248[0x2];
>>>> +    u8         umem_uid_0[0x1];
>>>> +    u8         reserved_at_250[0x5];
>>>>        u8         log_pg_sz[0x8];
>>>>          u8         bf[0x1];


  reply	other threads:[~2021-05-31  6:44 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-30  7:54 [PATCH 0/2] vdpa/mlx5: Add support for virtio_vdpa Eli Cohen
2021-05-30  7:54 ` [PATCH 1/2] vdpa/mlx5: Support creating resources with uid == 0 Eli Cohen
2021-05-31  3:02   ` Jason Wang
2021-05-31  3:06     ` Jason Wang
2021-05-31  4:59       ` Eli Cohen
2021-05-31  6:43         ` Jason Wang [this message]
2021-05-31  4:58     ` Eli Cohen
2021-05-30  7:54 ` [PATCH 2/2] vdpa/mlx5: Add support for running with virtio_vdpa Eli Cohen
2021-05-31  3:16   ` Jason Wang
2021-05-31  5:13     ` Eli Cohen
2021-05-31  6:44       ` Jason Wang

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=3717ebc5-66ce-2d50-1853-49442a8e71e1@redhat.com \
    --to=jasowang@redhat.com \
    --cc=elic@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®