Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
To: Vivek Kasireddy <vivek.kasireddy@intel.com>,
	<dri-devel@lists.freedesktop.org>,
	<intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH v3 3/5] drm/xe/pf: Add a helper function to get a VF's backing object in LMEM
Date: Thu, 4 Sep 2025 00:52:15 +0200	[thread overview]
Message-ID: <ddc725e1-8906-4e03-8590-c75c0ea351f4@intel.com> (raw)
In-Reply-To: <20250903223403.1261824-4-vivek.kasireddy@intel.com>



On 9/4/2025 12:30 AM, Vivek Kasireddy wrote:
> To properly import a dmabuf that is associated with a VF (or that
> originates in a Guest VM that includes a VF), we need to know where
> in LMEM the VF's allocated regions exist. Therefore, introduce a
> new helper to return the object that backs the VF's regions in LMEM.
> 
> v2:
> - Make the helper return the LMEM object instead of the start address.
> 
> Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 23 ++++++++++++++++++++++
>  drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h |  1 +
>  2 files changed, 24 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> index c8f0320d032f..e01f5b340999 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
> @@ -1542,6 +1542,29 @@ u64 xe_gt_sriov_pf_config_get_lmem(struct xe_gt *gt, unsigned int vfid)
>  	return size;
>  }
>  
> +/**
> + * xe_gt_sriov_pf_config_get_lmem_obj - Get VF's LMEM BO.
> + * @gt: the &xe_gt
> + * @vfid: the VF identifier
> + *
> + * This function can only be called on PF.
> + *
> + * Return: BO that is backing VF's quota in LMEM.
> + */
> +struct xe_bo *xe_gt_sriov_pf_config_get_lmem_obj(struct xe_gt *gt,
> +						 unsigned int vfid)
> +{
> +	struct xe_gt_sriov_config *config;
> +	struct xe_bo *lmem_obj;
> +
> +	mutex_lock(xe_gt_sriov_pf_master_mutex(gt));
> +	config = pf_pick_vf_config(gt, vfid);
> +	lmem_obj = config->lmem_obj;
> +	mutex_unlock(xe_gt_sriov_pf_master_mutex(gt));
> +
> +	return lmem_obj;

note that this bo pointer might be stale outside master-mutex
as now nothing prevents other code or user to unprovision VF

I guess you at least need to use xe_bo_get()/put()
and/or introduce some logic that would mark this BO as used

> +}
> +
>  /**
>   * xe_gt_sriov_pf_config_set_lmem - Provision VF with LMEM.
>   * @gt: the &xe_gt (can't be media)
> diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h
> index 513e6512a575..bef459003de1 100644
> --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h
> +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.h
> @@ -31,6 +31,7 @@ int xe_gt_sriov_pf_config_set_fair_dbs(struct xe_gt *gt, unsigned int vfid, unsi
>  int xe_gt_sriov_pf_config_bulk_set_dbs(struct xe_gt *gt, unsigned int vfid, unsigned int num_vfs,
>  				       u32 num_dbs);
>  
> +struct xe_bo *xe_gt_sriov_pf_config_get_lmem_obj(struct xe_gt *gt, unsigned int vfid);

and please place this declaration as last one in "lmem" group

>  u64 xe_gt_sriov_pf_config_get_lmem(struct xe_gt *gt, unsigned int vfid);
>  int xe_gt_sriov_pf_config_set_lmem(struct xe_gt *gt, unsigned int vfid, u64 size);
>  int xe_gt_sriov_pf_config_set_fair_lmem(struct xe_gt *gt, unsigned int vfid, unsigned int num_vfs);


  reply	other threads:[~2025-09-03 22:52 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-03 22:30 [PATCH v3 0/5] drm/xe/sriov: Don't migrate dmabuf BO to System RAM while running in VM Vivek Kasireddy
2025-09-03 22:30 ` [PATCH v3 1/5] PCI/P2PDMA: Don't enforce ACS check for device functions of Intel GPUs Vivek Kasireddy
2025-09-04 15:15   ` Logan Gunthorpe
2025-09-05  4:42     ` Kasireddy, Vivek
2025-09-03 22:30 ` [PATCH v3 2/5] drm/xe/dmabuf: Don't migrate BO to System RAM while running in VF mode Vivek Kasireddy
2025-09-03 22:30 ` [PATCH v3 3/5] drm/xe/pf: Add a helper function to get a VF's backing object in LMEM Vivek Kasireddy
2025-09-03 22:52   ` Michal Wajdeczko [this message]
2025-09-03 22:30 ` [PATCH v3 4/5] drm/xe/bo: Create new dma_addr array for dmabuf BOs associated with VFs Vivek Kasireddy
2025-09-16 20:25   ` Thomas Hellström
2025-09-17  2:45     ` Matthew Brost
2025-09-03 22:30 ` [PATCH v3 5/5] drm/xe/pt: Add an additional check for dmabuf BOs while doing bind Vivek Kasireddy
2025-09-03 23:18 ` ✗ CI.checkpatch: warning for drm/xe/sriov: Don't migrate dmabuf BO to System RAM while running in VM (rev3) Patchwork
2025-09-03 23:19 ` ✓ CI.KUnit: success " Patchwork
2025-09-04  0:04 ` ✓ Xe.CI.BAT: " Patchwork
2025-09-04  8:56 ` ✗ 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=ddc725e1-8906-4e03-8590-c75c0ea351f4@intel.com \
    --to=michal.wajdeczko@intel.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=vivek.kasireddy@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