[PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops

[Ding, Pixel]

This is for retry init.

If the driver fails before late_init, the IRQ handler is not registered then. We need to know if the FLR is done at this point. I think maybe we also can leverage this interface to handle some special cases in future. Any concern about it?
— 
Sincerely Yours,
Pixel








On 23/10/2017, 7:01 PM, "Liu, Monk" <Monk.Liu at amd.com> wrote:

>I don't see this is a necessary patch, driver already have the implement to check if VF FLR is completed or not, see "xgpu_ai/vi_mailbox_flr_work()"
>
>Driver won't do gpu reset until this function received the NOTIFICATION_CMPL message
>
>Do you have any particular reason to add this wait_reset ? if so please send out the patch that use this interface 
>
>BR Monk
>
>-----Original Message-----
>From: amd-gfx [mailto:amd-gfx-bounces at lists.freedesktop.org] On Behalf Of Pixel Ding
>Sent: 2017年10月23日 18:04
>To: amd-gfx at lists.freedesktop.org
>Cc: Sun, Gary <Gary.Sun at amd.com>; Ding, Pixel <Pixel.Ding at amd.com>; Li, Bingley <Bingley.Li at amd.com>
>Subject: [PATCH 6/7] drm/amdgpu/virt: add wait_reset virt ops
>
>From: pding <Pixel.Ding at amd.com>
>
>Driver can use this interface to check if there's a function level reset done in hypervisor.
>
>Signed-off-by: pding <Pixel.Ding at amd.com>
>---
> drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 16 ++++++++++++++++  drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h |  2 ++
> drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c    |  1 +
> drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c    |  6 ++++++
> 4 files changed, 25 insertions(+)
>
>diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
>index 33dac7e..6a4a901 100644
>--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
>+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
>@@ -231,6 +231,22 @@ int amdgpu_virt_reset_gpu(struct amdgpu_device *adev)  }
> 
> /**
>+ * amdgpu_virt_wait_reset() - wait for reset gpu completed
>+ * @amdgpu:	amdgpu device.
>+ * Wait for GPU reset completed.
>+ * Return: Zero if reset success, otherwise will return error.
>+ */
>+int amdgpu_virt_wait_reset(struct amdgpu_device *adev) {
>+	struct amdgpu_virt *virt = &adev->virt;
>+
>+	if (!virt->ops || !virt->ops->wait_reset)
>+		return -EINVAL;
>+
>+	return virt->ops->wait_reset(adev);
>+}
>+
>+/**
>  * amdgpu_virt_alloc_mm_table() - alloc memory for mm table
>  * @amdgpu:	amdgpu device.
>  * MM table is used by UVD and VCE for its initialization diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
>index 81efb9d..d149aca 100644
>--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
>+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
>@@ -55,6 +55,7 @@ struct amdgpu_virt_ops {
> 	int (*req_full_gpu)(struct amdgpu_device *adev, bool init);
> 	int (*rel_full_gpu)(struct amdgpu_device *adev, bool init);
> 	int (*reset_gpu)(struct amdgpu_device *adev);
>+	int (*wait_reset)(struct amdgpu_device *adev);
> 	void (*trans_msg)(struct amdgpu_device *adev, u32 req, u32 data1, u32 data2, u32 data3);  };
> 
>@@ -286,6 +287,7 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);  int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init);  int amdgpu_virt_release_full_gpu(struct amdgpu_device *adev, bool init);  int amdgpu_virt_reset_gpu(struct amdgpu_device *adev);
>+int amdgpu_virt_wait_reset(struct amdgpu_device *adev);
> int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job);  int amdgpu_virt_alloc_mm_table(struct amdgpu_device *adev);  void amdgpu_virt_free_mm_table(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
>index b4906d2..f91aab3 100644
>--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
>+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
>@@ -353,5 +353,6 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
> 	.req_full_gpu	= xgpu_ai_request_full_gpu_access,
> 	.rel_full_gpu	= xgpu_ai_release_full_gpu_access,
> 	.reset_gpu = xgpu_ai_request_reset,
>+	.wait_reset = NULL,
> 	.trans_msg = xgpu_ai_mailbox_trans_msg,  }; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
>index c25a831..27b03c7 100644
>--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
>+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
>@@ -458,6 +458,11 @@ static int xgpu_vi_request_reset(struct amdgpu_device *adev)
> 	return xgpu_vi_send_access_requests(adev, IDH_REQ_GPU_RESET_ACCESS);  }
> 
>+static int xgpu_vi_wait_reset_cmpl(struct amdgpu_device *adev) {
>+	return xgpu_vi_poll_msg(adev, IDH_FLR_NOTIFICATION_CMPL); }
>+
> static int xgpu_vi_request_full_gpu_access(struct amdgpu_device *adev,
> 					   bool init)
> {
>@@ -613,5 +618,6 @@ const struct amdgpu_virt_ops xgpu_vi_virt_ops = {
> 	.req_full_gpu		= xgpu_vi_request_full_gpu_access,
> 	.rel_full_gpu		= xgpu_vi_release_full_gpu_access,
> 	.reset_gpu		= xgpu_vi_request_reset,
>+	.wait_reset             = xgpu_vi_wait_reset_cmpl,
> 	.trans_msg		= NULL, /* Does not need to trans VF errors to host. */
> };
>--
>2.9.5
>
>_______________________________________________
>amd-gfx mailing list
>amd-gfx at lists.freedesktop.org
>https://lists.freedesktop.org/mailman/listinfo/amd-gfx