All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Kim, Jonathan" <Jonathan.Kim@amd.com>
To: "Kuehling, Felix" <Felix.Kuehling@amd.com>,
	"amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>
Subject: RE: [PATCH] drm/amdgpu: fix amdgpu pmu to use hwc->config instead of hwc->conf
Date: Thu, 6 Feb 2020 20:23:29 +0000	[thread overview]
Message-ID: <DM6PR12MB4314E3C7A7C820FFFBB880CA851D0@DM6PR12MB4314.namprd12.prod.outlook.com> (raw)
In-Reply-To: <d8b406a2-f920-6634-f382-58387894bf93@amd.com>

[AMD Official Use Only - Approved for External Use]

Thanks for pointing that out Felix.  I'll append that as well to the comments for the commit.

Jon

-----Original Message-----
From: Kuehling, Felix <Felix.Kuehling@amd.com> 
Sent: Thursday, February 6, 2020 3:08 PM
To: Kim, Jonathan <Jonathan.Kim@amd.com>; amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdgpu: fix amdgpu pmu to use hwc->config instead of hwc->conf

On 2020-02-06 12:08, Jonathan Kim wrote:
> hwc->conf was designated specifically for AMD APU IOMMU purposes.  
> hwc->This
> could cause problems in performance and/or function since APU IOMMU 
> implementation is elsewhere.

It's actually worse than that. hwc is a union of anonymous structures. 
hwc->conf and hwc->config are in different members of that union. So 
hwc->conf aliases some other variable in the structure that hwc->config
is in. If I did the math right, hwc->conf aliases hwc->last_tag.

Anyway, the patch is

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>


>
> Signed-off-by: Jonathan Kim <Jonathan.Kim@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c | 15 ++++++++-------
>   1 file changed, 8 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
> index 07914e34bc25..1311d6aec5d4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pmu.c
> @@ -52,7 +52,7 @@ static int amdgpu_perf_event_init(struct perf_event *event)
>   		return -ENOENT;
>   
>   	/* update the hw_perf_event struct with config data */
> -	hwc->conf = event->attr.config;
> +	hwc->config = event->attr.config;
>   
>   	return 0;
>   }
> @@ -74,9 +74,9 @@ static void amdgpu_perf_start(struct perf_event *event, int flags)
>   	switch (pe->pmu_perf_type) {
>   	case PERF_TYPE_AMDGPU_DF:
>   		if (!(flags & PERF_EF_RELOAD))
> -			pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
> +			pe->adev->df.funcs->pmc_start(pe->adev, hwc->config, 1);
>   
> -		pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 0);
> +		pe->adev->df.funcs->pmc_start(pe->adev, hwc->config, 0);
>   		break;
>   	default:
>   		break;
> @@ -101,7 +101,7 @@ static void amdgpu_perf_read(struct perf_event *event)
>   
>   		switch (pe->pmu_perf_type) {
>   		case PERF_TYPE_AMDGPU_DF:
> -			pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->conf,
> +			pe->adev->df.funcs->pmc_get_count(pe->adev, hwc->config,
>   							  &count);
>   			break;
>   		default:
> @@ -126,7 +126,7 @@ static void amdgpu_perf_stop(struct perf_event *event, int flags)
>   
>   	switch (pe->pmu_perf_type) {
>   	case PERF_TYPE_AMDGPU_DF:
> -		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 0);
> +		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->config, 0);
>   		break;
>   	default:
>   		break;
> @@ -156,7 +156,8 @@ static int amdgpu_perf_add(struct perf_event *event, int flags)
>   
>   	switch (pe->pmu_perf_type) {
>   	case PERF_TYPE_AMDGPU_DF:
> -		retval = pe->adev->df.funcs->pmc_start(pe->adev, hwc->conf, 1);
> +		retval = pe->adev->df.funcs->pmc_start(pe->adev,
> +						       hwc->config, 1);
>   		break;
>   	default:
>   		return 0;
> @@ -184,7 +185,7 @@ static void amdgpu_perf_del(struct perf_event *event, int flags)
>   
>   	switch (pe->pmu_perf_type) {
>   	case PERF_TYPE_AMDGPU_DF:
> -		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->conf, 1);
> +		pe->adev->df.funcs->pmc_stop(pe->adev, hwc->config, 1);
>   		break;
>   	default:
>   		break;
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

      reply	other threads:[~2020-02-06 20:23 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-06 17:08 [PATCH] drm/amdgpu: fix amdgpu pmu to use hwc->config instead of hwc->conf Jonathan Kim
2020-02-06 20:08 ` Felix Kuehling
2020-02-06 20:23   ` Kim, Jonathan [this message]

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=DM6PR12MB4314E3C7A7C820FFFBB880CA851D0@DM6PR12MB4314.namprd12.prod.outlook.com \
    --to=jonathan.kim@amd.com \
    --cc=Felix.Kuehling@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.