From: Eric Huang <jinhuieric.huang@amd.com>
To: "Joshi, Mukul" <Mukul.Joshi@amd.com>,
"amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>
Cc: "Kim, Jonathan" <Jonathan.Kim@amd.com>
Subject: Re: [PATCH] drm/amdkfd: enable grace period for xcp instance
Date: Mon, 10 Jul 2023 18:27:58 -0400 [thread overview]
Message-ID: <2f6bc7c8-ff88-53d1-cf33-dcfa530e2cab@amd.com> (raw)
In-Reply-To: <BL3PR12MB64252080596A0A4C3E3B6960EE30A@BL3PR12MB6425.namprd12.prod.outlook.com>
OK. Mukul, I will resend this patch based on top of yours.
Regards,
Eric
On 2023-07-10 18:24, Joshi, Mukul wrote:
> [AMD Official Use Only - General]
>
>> -----Original Message-----
>> From: amd-gfx <amd-gfx-bounces@lists.freedesktop.org> On Behalf Of Eric
>> Huang
>> Sent: Monday, July 10, 2023 3:46 PM
>> To: amd-gfx@lists.freedesktop.org
>> Cc: Huang, JinHuiEric <JinHuiEric.Huang@amd.com>; Kim, Jonathan
>> <Jonathan.Kim@amd.com>
>> Subject: [PATCH] drm/amdkfd: enable grace period for xcp instance
>>
>> Caution: This message originated from an External Source. Use proper caution
>> when opening attachments, clicking links, or responding.
>>
>>
>> Read/write grace period from/to first xcc instance of xcp in kfd node.
>>
> Hi Eric,
>
> My patch, "drm/amdkfd: Update CWSR grace period for GFX9.4.3", which got missed during the merge
> should handle most of what you are trying to do.
> I will push that patch. Please add on top if there is anything missing.
>
> Hope that works for you.
>
> Thanks,
> Mukul
>
>> Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 11
>> ++++++++--- drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h |
>> 2 +-
>> drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c | 10 +++++++---
>> 3 files changed, 16 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> index de83eccdd9de..a95bcb91dc09 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
>> @@ -1619,10 +1619,15 @@ static int initialize_cpsch(struct
>> device_queue_manager *dqm)
>>
>> init_sdma_bitmaps(dqm);
>>
>> - if (dqm->dev->kfd2kgd->get_iq_wait_times)
>> + if (dqm->dev->kfd2kgd->get_iq_wait_times) {
>> + u32 inst = ffs(dqm->dev->xcc_mask &
>> + (1UL <<
>> + dqm->dev->xcp->id *
>> + dqm->dev->adev->gfx.num_xcc_per_xcp)) -
>> + 1;
>> dqm->dev->kfd2kgd->get_iq_wait_times(dqm->dev->adev,
>> - &dqm->wait_times,
>> - 0);
>> + &dqm->wait_times[inst],
>> + inst);
>> + }
>> return 0;
>> }
>>
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
>> b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
>> index 7dd4b177219d..45959c33b944 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
>> @@ -262,7 +262,7 @@ struct device_queue_manager {
>> /* used for GFX 9.4.3 only */
>> uint32_t current_logical_xcc_start;
>>
>> - uint32_t wait_times;
>> + uint32_t wait_times[MAX_XCP];
>>
>> wait_queue_head_t destroy_wait;
>> };
>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
>> b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
>> index 8fda16e6fee6..dd50164c16cd 100644
>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
>> @@ -292,17 +292,21 @@ static int pm_set_grace_period_v9(struct
>> packet_manager *pm,
>> struct pm4_mec_write_data_mmio *packet;
>> uint32_t reg_offset = 0;
>> uint32_t reg_data = 0;
>> + uint32_t inst = ffs(pm->dqm->dev->xcc_mask &
>> + (1UL <<
>> + pm->dqm->dev->xcp->id *
>> + pm->dqm->dev->adev->gfx.num_xcc_per_xcp)) -
>> + 1;
>>
>> pm->dqm->dev->kfd2kgd->build_grace_period_packet_info(
>> pm->dqm->dev->adev,
>> - pm->dqm->wait_times,
>> + pm->dqm->wait_times[inst],
>> grace_period,
>> ®_offset,
>> ®_data,
>> - 0);
>> + inst);
>>
>> if (grace_period == USE_DEFAULT_GRACE_PERIOD)
>> - reg_data = pm->dqm->wait_times;
>> + reg_data = pm->dqm->wait_times[inst];
>>
>> packet = (struct pm4_mec_write_data_mmio *)buffer;
>> memset(buffer, 0, sizeof(struct pm4_mec_write_data_mmio));
>> --
>> 2.34.1
next prev parent reply other threads:[~2023-07-10 22:28 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-10 19:45 [PATCH] drm/amdkfd: enable grace period for xcp instance Eric Huang
2023-07-10 22:24 ` Joshi, Mukul
2023-07-10 22:27 ` Eric Huang [this message]
-- strict thread matches above, loose matches on Subject: below --
2023-07-11 14:28 Eric Huang
2023-07-11 15:06 ` Kim, Jonathan
2023-07-11 18:38 ` Felix Kuehling
2023-07-11 18:48 ` Eric Huang
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=2f6bc7c8-ff88-53d1-cf33-dcfa530e2cab@amd.com \
--to=jinhuieric.huang@amd.com \
--cc=Jonathan.Kim@amd.com \
--cc=Mukul.Joshi@amd.com \
--cc=amd-gfx@lists.freedesktop.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