Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>
To: <intel-xe@lists.freedesktop.org>
Cc: <matthew.brost@intel.com>, <thomas.hellstrom@linux.intel.com>,
	<oak.zeng@intel.com>
Subject: Re: [RFC 12/12] drm/xe/vm: Add debug prints for SVM range prefetch
Date: Tue, 11 Mar 2025 11:57:55 +0530	[thread overview]
Message-ID: <846a35e8-2997-4530-b152-3cd8f2166f62@intel.com> (raw)
In-Reply-To: <20250310124341.1819568-13-himal.prasad.ghimiray@intel.com>



On 10-03-2025 18:13, Himal Prasad Ghimiray wrote:
> Introduce debug logs for the prefetch operation of SVM ranges.
> 
> Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> ---
>   drivers/gpu/drm/xe/xe_vm.c | 7 ++++++-
>   1 file changed, 6 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index a1607283a5fe..b2b0824b8777 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -2372,6 +2372,7 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_vma_ops *vops,
>   			xa_store(&op->prefetch_range.range, i, svm_range, GFP_KERNEL);
>   			op->prefetch_range.ranges_count++;
>   			vops->flags |= XE_VMA_OPS_HAS_SVM_PREFETCH;
> +			xe_svm_range_debug(svm_range, "PREFETCH - RANGE CREATED");
>   
>   			if (range_end > xe_svm_range_end(svm_range) &&
>   			    xe_svm_range_end(svm_range) < xe_vma_end(vma)) {
> @@ -2869,6 +2870,7 @@ static int prefetch_ranges_lock_and_prep(struct xe_vm *vm,
>   						vm->usm.asid, (u64)&vm->svm.gpusvm, err);
>   					return -ENODATA;
>   				}
> +				xe_svm_range_debug(svm_range, "PREFETCH - RANGE MIGRATED TO VRAM");
>   			}
>   
>   			err = xe_svm_range_get_pages(vm, svm_range, &ctx);
> @@ -2878,8 +2880,11 @@ static int prefetch_ranges_lock_and_prep(struct xe_vm *vm,
>   
>   				drm_err(&vm->xe->drm, "Get pages failed, asid=%u, gpusvm=0x%016llx, errno %d\n",
>   					vm->usm.asid, (u64)&vm->svm.gpusvm, err);
> -				return err;
> +				err = -ENODATA;
>   			}
> +			if (err)
> +				return err;

 > -				return err;
 > +				err = -ENODATA;
 >   			}
 > +			if (err)
 > +				return err;

not needed. will remove in next version.

> +			xe_svm_range_debug(svm_range, "PREFETCH - RANGE GET PAGES DONE");
>   		}
>   	}
>   	return err;


  reply	other threads:[~2025-03-11  6:28 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-03-10 12:43 [RFC 00/12] Prefetch Support for svm ranges Himal Prasad Ghimiray
2025-03-10 12:35 ` ✓ CI.Patch_applied: success for " Patchwork
2025-03-10 12:35 ` ✓ CI.checkpatch: " Patchwork
2025-03-10 12:36 ` ✓ CI.KUnit: " Patchwork
2025-03-10 12:43 ` [RFC 01/12] drm/xe: Introduce xe_vma_op_prefetch_range struct for prefetch of ranges Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 02/12] drm/xe: Make xe_svm_alloc_vram public Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 03/12] drm/xe/svm: Helper to add tile masks to svm ranges Himal Prasad Ghimiray
2025-03-10 19:19   ` Matthew Brost
2025-03-11  6:26     ` Ghimiray, Himal Prasad
2025-03-10 12:43 ` [RFC 04/12] drm/xe/svm: Make to_xe_range a public function Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 05/12] drm/xe/svm: Make xe_svm_range_* end/start/size public Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 06/12] drm/xe/vm: Update xe_vma_ops_incr_pt_update_ops to take an increment value Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 07/12] drm/xe/vm: Add an identifier in xe_vma_ops for svm prefetch Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 08/12] drm/xe: Rename lookup_vma function to xe_find_vma_by_addr Himal Prasad Ghimiray
2025-03-28  2:58   ` Matthew Brost
2025-03-10 12:43 ` [RFC 09/12] drm/xe/svm: Allow unaligned addresses and ranges for prefetch Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 10/12] drm/xe/svm: Refactor usage of drm_gpusvm* function in xe_svm Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 11/12] drm/xe/svm: Implement prefetch support for SVM ranges Himal Prasad Ghimiray
2025-03-10 12:43 ` [RFC 12/12] drm/xe/vm: Add debug prints for SVM range prefetch Himal Prasad Ghimiray
2025-03-11  6:27   ` Ghimiray, Himal Prasad [this message]
2025-03-10 12:53 ` ✓ CI.Build: success for Prefetch Support for svm ranges Patchwork
2025-03-10 12:55 ` ✗ CI.Hooks: failure " Patchwork
2025-03-10 12:56 ` ✓ CI.checksparse: success " Patchwork
2025-03-10 13:17 ` ✓ Xe.CI.BAT: " Patchwork
2025-03-11  8:57 ` ✗ Xe.CI.Full: failure " Patchwork

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=846a35e8-2997-4530-b152-3cd8f2166f62@intel.com \
    --to=himal.prasad.ghimiray@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=matthew.brost@intel.com \
    --cc=oak.zeng@intel.com \
    --cc=thomas.hellstrom@linux.intel.com \
    /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