[PATCH V3 1/1] drm/amd/amdgpu: Release xcp drm memory after unplug

[Deucher, Alexander]

[Public]

> -----Original Message-----
> From: Meng, Li (Jassmine) <Li.Meng at amd.com>
> Sent: Monday, June 23, 2025 9:53 PM
> To: amd-gfx <amd-gfx at lists.freedesktop.org>
> Cc: Yuan, Perry <Perry.Yuan at amd.com>; Huang, Shimmer
> <Shimmer.Huang at amd.com>; Koenig Christian <Koenig.Christian at amd.com>;
> Lazar, Lijo <Lijo.Lazar at amd.com>; Deucher, Alexander
> <Alexander.Deucher at amd.com>; Meng, Li (Jassmine) <Li.Meng at amd.com>;
> Jiang Liu <gerry at linux.alibaba.com>
> Subject: [PATCH V3 1/1] drm/amd/amdgpu: Release xcp drm memory after unplug
>
> Add a new API amdgpu_xcp_drm_dev_free().
> After unplug xcp device, need to release xcp drm memory etc.
>
> Co-developed-by: Jiang Liu <gerry at linux.alibaba.com>
> Signed-off-by: Jiang Liu <gerry at linux.alibaba.com>
> Signed-off-by: Meng Li <li.meng at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c     |  1 +
>  drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c | 60 +++++++++++++++++----
> drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h |  1 +
>  3 files changed, 53 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> index 322816805bfb..70c44961af95 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xcp.c
> @@ -394,6 +394,7 @@ void amdgpu_xcp_dev_unplug(struct amdgpu_device
> *adev)
>               p_ddev->primary->dev = adev->xcp_mgr->xcp[i].pdev;
>               p_ddev->driver =  adev->xcp_mgr->xcp[i].driver;
>               p_ddev->vma_offset_manager = adev->xcp_mgr-
> >xcp[i].vma_offset_manager;
> +             amdgpu_xcp_drm_dev_free(p_ddev);
>       }
>  }
>
> diff --git a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
> b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
> index faed84172dd4..3a8f3dd19a12 100644
> --- a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
> +++ b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.c
> @@ -45,18 +45,29 @@ static const struct drm_driver amdgpu_xcp_driver = {
>
>  static int8_t pdev_num;
>  static struct xcp_device *xcp_dev[MAX_XCP_PLATFORM_DEVICE];
> +static DEFINE_MUTEX(xcp_mutex);
>
>  int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev)  {
>       struct platform_device *pdev;
>       struct xcp_device *pxcp_dev;
>       char dev_name[20];
> -     int ret;
> +     int ret, i;
> +
> +     guard(mutex)(&xcp_mutex);
>
>       if (pdev_num >= MAX_XCP_PLATFORM_DEVICE)
>               return -ENODEV;
>
> -     snprintf(dev_name, sizeof(dev_name), "amdgpu_xcp_%d", pdev_num);
> +     for (i = 0; i < MAX_XCP_PLATFORM_DEVICE; i++) {
> +             if (!xcp_dev[i])
> +                     break;
> +     }
> +
> +     if (i >= MAX_XCP_PLATFORM_DEVICE)
> +             return -ENODEV;
> +
> +     snprintf(dev_name, sizeof(dev_name), "amdgpu_xcp_%d", i);
>       pdev = platform_device_register_simple(dev_name, -1, NULL, 0);
>       if (IS_ERR(pdev))
>               return PTR_ERR(pdev);
> @@ -72,8 +83,8 @@ int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev)
>               goto out_devres;
>       }
>
> -     xcp_dev[pdev_num] = pxcp_dev;
> -     xcp_dev[pdev_num]->pdev = pdev;
> +     xcp_dev[i] = pxcp_dev;
> +     xcp_dev[i]->pdev = pdev;
>       *ddev = &pxcp_dev->drm;
>       pdev_num++;
>
> @@ -88,16 +99,47 @@ int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev)
> }  EXPORT_SYMBOL(amdgpu_xcp_drm_dev_alloc);
>
> -void amdgpu_xcp_drv_release(void)
> +static void free_xcp_dev(int8_t index)
>  {
> -     for (--pdev_num; pdev_num >= 0; --pdev_num) {
> -             struct platform_device *pdev = xcp_dev[pdev_num]->pdev;
> +     if ((index < MAX_XCP_PLATFORM_DEVICE) && (xcp_dev[index])) {
> +             struct platform_device *pdev = xcp_dev[index]->pdev;
>
>               devres_release_group(&pdev->dev, NULL);
>               platform_device_unregister(pdev);
> -             xcp_dev[pdev_num] = NULL;
> +
> +             xcp_dev[index] = NULL;
> +             pdev_num--;
> +     }
> +}
> +
> +void amdgpu_xcp_drm_dev_free(struct drm_device *ddev) {
> +     int8_t i = MAX_XCP_PLATFORM_DEVICE;

No need to init i here.  You aren't using the assigned value.  With that fixed:
Acked-by: Alex Deucher <alexander.deucher at amd.com>

> +
> +     guard(mutex)(&xcp_mutex);
> +
> +     for (i = 0; i < MAX_XCP_PLATFORM_DEVICE; i++) {
> +             if ((xcp_dev[i]) && (&xcp_dev[i]->drm == ddev)) {
> +                     free_xcp_dev(i);
> +                     break;
> +             }
> +     }
> +}
> +EXPORT_SYMBOL(amdgpu_xcp_drm_dev_free);
> +
> +void amdgpu_xcp_drv_release(void)
> +{
> +     int8_t i = 0;
> +
> +     guard(mutex)(&xcp_mutex);
> +
> +     if (pdev_num > 0) {
> +             for (i = 0; i < MAX_XCP_PLATFORM_DEVICE; i++) {
> +                     free_xcp_dev(i);
> +                     if (pdev_num == 0)
> +                             break;
> +             }
>       }
> -     pdev_num = 0;
>  }
>  EXPORT_SYMBOL(amdgpu_xcp_drv_release);
>
> diff --git a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
> b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
> index c1c4b679bf95..580a1602c8e3 100644
> --- a/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
> +++ b/drivers/gpu/drm/amd/amdxcp/amdgpu_xcp_drv.h
> @@ -25,5 +25,6 @@
>  #define _AMDGPU_XCP_DRV_H_
>
>  int amdgpu_xcp_drm_dev_alloc(struct drm_device **ddev);
> +void amdgpu_xcp_drm_dev_free(struct drm_device *ddev);
>  void amdgpu_xcp_drv_release(void);
>  #endif /* _AMDGPU_XCP_DRV_H_ */
> --
> 2.43.0