mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Lizhi Hou <lizhi.hou@amd.com>
To: Mario Limonciello <superm1@kernel.org>, <ogabbay@kernel.org>,
	<quic_jhugo@quicinc.com>, <dri-devel@lists.freedesktop.org>,
	<maciej.falkowski@linux.intel.com>
Cc: <linux-kernel@vger.kernel.org>, <max.zhen@amd.com>,
	<sonal.santan@amd.com>
Subject: Re: [PATCH V1] accel/amdxdna: Enable hardware context priority
Date: Wed, 17 Dec 2025 10:44:40 -0800	[thread overview]
Message-ID: <82d2d957-650f-9523-9090-cb1c5a3ae5f7@amd.com> (raw)
In-Reply-To: <ef6e71e2-ee6f-49d8-981b-97ba2fe13e92@kernel.org>


On 12/17/25 09:59, Mario Limonciello wrote:
> On 12/17/25 11:17 AM, Lizhi Hou wrote:
>> Newer firmware supports hardware context priority. Set the priority 
>> based
>> on application input.
>>
>> Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
>
> Reviewed-by: Mario Limonciello (AMD) <superm1@kernel.org>
>
> This change itself is fine, but while reviewing it I did have a 
> question to ask.
>
> I notice that NPU2, NPU4, NPU5 and NPU6 all use npu4_fw_feature_table. 
> Is this feature really present in F/W for NPU2 devices too?  Or it's 
> really only NPU4 and later feature?
>
> IE I just wonder if it's a non-obvious problem that npu2 device should 
> have it's own fw feature table rather than re-use NPU4's. NPU1 has 
> it's own feature table.

Thanks for checking this. Actually, NPU2 hardware is obsoleted. I will 
create a patch to remove NPU2 completely.


Lizhi

>
>> ---
>>   drivers/accel/amdxdna/aie2_message.c  | 23 ++++++++++++++++++++++-
>>   drivers/accel/amdxdna/aie2_msg_priv.h |  5 +++++
>>   include/uapi/drm/amdxdna_accel.h      |  8 ++++++++
>>   3 files changed, 35 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/accel/amdxdna/aie2_message.c 
>> b/drivers/accel/amdxdna/aie2_message.c
>> index e77a353cadc5..051f4ceaabae 100644
>> --- a/drivers/accel/amdxdna/aie2_message.c
>> +++ b/drivers/accel/amdxdna/aie2_message.c
>> @@ -205,6 +205,27 @@ static int aie2_destroy_context_req(struct 
>> amdxdna_dev_hdl *ndev, u32 id)
>>         return ret;
>>   }
>> +
>> +static u32 aie2_get_context_priority(struct amdxdna_dev_hdl *ndev,
>> +                     struct amdxdna_hwctx *hwctx)
>> +{
>> +    if (!AIE2_FEATURE_ON(ndev, AIE2_PREEMPT))
>> +        return PRIORITY_HIGH;
>> +
>> +    switch (hwctx->qos.priority) {
>> +    case AMDXDNA_QOS_REALTIME_PRIORITY:
>> +        return PRIORITY_REALTIME;
>> +    case AMDXDNA_QOS_HIGH_PRIORITY:
>> +        return PRIORITY_HIGH;
>> +    case AMDXDNA_QOS_NORMAL_PRIORITY:
>> +        return PRIORITY_NORMAL;
>> +    case AMDXDNA_QOS_LOW_PRIORITY:
>> +        return PRIORITY_LOW;
>> +    default:
>> +        return PRIORITY_HIGH;
>> +    }
>> +}
>> +
>>   int aie2_create_context(struct amdxdna_dev_hdl *ndev, struct 
>> amdxdna_hwctx *hwctx)
>>   {
>>       DECLARE_AIE2_MSG(create_ctx, MSG_OP_CREATE_CONTEXT);
>> @@ -221,7 +242,7 @@ int aie2_create_context(struct amdxdna_dev_hdl 
>> *ndev, struct amdxdna_hwctx *hwct
>>       req.num_unused_col = hwctx->num_unused_col;
>>       req.num_cq_pairs_requested = 1;
>>       req.pasid = hwctx->client->pasid;
>> -    req.context_priority = 2;
>> +    req.context_priority = aie2_get_context_priority(ndev, hwctx);
>>         ret = aie2_send_mgmt_msg_wait(ndev, &msg);
>>       if (ret)
>> diff --git a/drivers/accel/amdxdna/aie2_msg_priv.h 
>> b/drivers/accel/amdxdna/aie2_msg_priv.h
>> index cc912b7899ce..728ef56f7f0a 100644
>> --- a/drivers/accel/amdxdna/aie2_msg_priv.h
>> +++ b/drivers/accel/amdxdna/aie2_msg_priv.h
>> @@ -108,6 +108,11 @@ struct cq_pair {
>>       struct cq_info i2x_q;
>>   };
>>   +#define PRIORITY_REALTIME    1
>> +#define PRIORITY_HIGH        2
>> +#define PRIORITY_NORMAL        3
>> +#define PRIORITY_LOW        4
>> +
>>   struct create_ctx_req {
>>       __u32    aie_type;
>>       __u8    start_col;
>> diff --git a/include/uapi/drm/amdxdna_accel.h 
>> b/include/uapi/drm/amdxdna_accel.h
>> index 62c917fd4f7b..9c44db2b3dcd 100644
>> --- a/include/uapi/drm/amdxdna_accel.h
>> +++ b/include/uapi/drm/amdxdna_accel.h
>> @@ -19,6 +19,14 @@ extern "C" {
>>   #define AMDXDNA_INVALID_BO_HANDLE    0
>>   #define AMDXDNA_INVALID_FENCE_HANDLE    0
>>   +/*
>> + * Define hardware context priority
>> + */
>> +#define AMDXDNA_QOS_REALTIME_PRIORITY    0x100
>> +#define AMDXDNA_QOS_HIGH_PRIORITY    0x180
>> +#define AMDXDNA_QOS_NORMAL_PRIORITY    0x200
>> +#define AMDXDNA_QOS_LOW_PRIORITY    0x280
>> +
>>   enum amdxdna_device_type {
>>       AMDXDNA_DEV_TYPE_UNKNOWN = -1,
>>       AMDXDNA_DEV_TYPE_KMQ,
>

  reply	other threads:[~2025-12-18  5:47 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-17 17:17 Lizhi Hou
2025-12-17 17:59 ` Mario Limonciello
2025-12-17 18:44   ` Lizhi Hou [this message]
2025-12-18 18:43   ` Lizhi Hou

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=82d2d957-650f-9523-9090-cb1c5a3ae5f7@amd.com \
    --to=lizhi.hou@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maciej.falkowski@linux.intel.com \
    --cc=max.zhen@amd.com \
    --cc=ogabbay@kernel.org \
    --cc=quic_jhugo@quicinc.com \
    --cc=sonal.santan@amd.com \
    --cc=superm1@kernel.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®