All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Timur Kristóf" <timur.kristof@gmail.com>
To: Jesse Zhang <Jesse.Zhang@amd.com>, amd-gfx@lists.freedesktop.org
Cc: Alexander.Deucher@amd.com,
	Christian Koenig <christian.koenig@amd.com>,
	 Lijo.Lazar@amd.com, Mario.Novales@amd.com, Manu.Rastogi@amd.com,
	 Jiongyu.Zhu@amd.com
Subject: Re: [PATCH v4 05/13] drm/amdgpu/gfx12: save and restore a gfx HQD
Date: Thu, 19 Nov 2026 12:35:54 +0100	[thread overview]
Message-ID: <8d7613f7203172334b3c295ec73cd9d83cec8340.camel@gmail.com> (raw)
In-Reply-To: <20261105030612.726542-5-Jesse.Zhang@amd.com>

On Thu, 2026-11-05 at 11:05 +0800, Jesse Zhang wrote:
> Implement the gfx callbacks to save and restore a gfx HQD for gfx12:
> - save_hqd() saves the HQD offset, CSMD read pointer and write
> pointer
>   of the gfx HQD of a doorbell, and whether the queue is the one
>   connected to its pipe;
> - restore_hqd() writes them into the MQD after a reset, for MES to
> map
>   the queue again where it was. A queue switched out of the pipe
> resumes
>   from the preemption status the PFP saved in its MQD, also in the
>   middle of an IB. The queue the pipe was executing has its state in
> the
>   PFP, which the reset cleared: it restarts after the work submitted
> so
>   far instead, and that work is dropped.
> 
> v4: Rename to save_hqd()/restore_hqd() (Timur).
> 
> Signed-off-by: Jesse Zhang <Jesse.Zhang@amd.com>

The code looks good, though I didn't test the series yet on GFX12 yet.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>


> ---
>  drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 83
> ++++++++++++++++++++++++++
>  1 file changed, 83 insertions(+)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
> b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
> index cb15dad0e57b..484e876fe235 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
> @@ -274,6 +274,11 @@ static void gfx_v12_0_set_imu_funcs(struct
> amdgpu_device *adev);
>  static int gfx_v12_0_get_cu_info(struct amdgpu_device *adev,
>  				 struct amdgpu_cu_info *cu_info);
>  static uint64_t gfx_v12_0_get_gpu_clock_counter(struct amdgpu_device
> *adev);
> +static bool gfx_v12_0_save_hqd(struct amdgpu_device *adev, u32
> doorbell_index,
> +			       struct amdgpu_gfx_saved_hqd *hqd);
> +static bool gfx_v12_0_restore_hqd(struct amdgpu_device *adev, void
> *m,
> +				  u32 ring_size,
> +				  const struct amdgpu_gfx_saved_hqd
> *hqd);
>  static void gfx_v12_0_select_se_sh(struct amdgpu_device *adev, u32
> se_num,
>  				   u32 sh_num, u32 instance, int
> xcc_id);
>  static u32 gfx_v12_0_get_wgp_active_bitmap_per_sh(struct
> amdgpu_device *adev);
> @@ -962,6 +967,8 @@ static const struct amdgpu_gfx_funcs
> gfx_v12_0_gfx_funcs = {
>  	.update_perfmon_mgcg = &gfx_v12_0_update_perf_clk,
>  	.get_gfx_shadow_info = &gfx_v12_0_get_gfx_shadow_info,
>  	.get_hdp_flush_mask = &amdgpu_gfx_get_hdp_flush_mask,
> +	.save_hqd = &gfx_v12_0_save_hqd,
> +	.restore_hqd = &gfx_v12_0_restore_hqd,
>  };
>  
>  static int gfx_v12_0_gpu_early_init(struct amdgpu_device *adev)
> @@ -3853,6 +3860,82 @@ static int gfx_v12_0_wait_for_idle(struct
> amdgpu_ip_block *ip_block)
>  	return -ETIMEDOUT;
>  }
>  
> +#define GFX12_HPD_QUEUE_STATE_CONNECTED_MIN	3
> +#define GFX12_HPD_QUEUE_STATE_CONNECTED_MAX	15
> +
> +static bool gfx_v12_0_save_hqd(struct amdgpu_device *adev, u32
> doorbell_index,
> +			       struct amdgpu_gfx_saved_hqd *hqd)
> +{
> +	u32 me, pipe, queue, status, state;
> +
> +	memset(hqd, 0, sizeof(*hqd));
> +	hqd->doorbell_index = doorbell_index;
> +	if (!gfx_v12_0_detect_hung_queue(adev, doorbell_index, &me,
> &pipe, &queue))
> +		return true;
> +
> +	amdgpu_gfx_off_ctrl(adev, false);
> +	mutex_lock(&adev->srbm_mutex);
> +	soc24_grbm_select(adev, me, pipe, queue, 0);
> +	hqd->on_hqd = RREG32_SOC15(GC, 0, regCP_GFX_HQD_ACTIVE) &
> +		      CP_GFX_HQD_ACTIVE__ACTIVE_MASK;
> +	if (!hqd->on_hqd)
> +		goto out;
> +	hqd->mqd_addr = RREG32_SOC15(GC, 0, regCP_GFX_MQD_BASE_ADDR)
> |
> +			(u64)RREG32_SOC15(GC, 0,
> regCP_GFX_MQD_BASE_ADDR_HI) << 32;
> +	hqd->offset = RREG32_SOC15(GC, 0, regCP_GFX_HQD_OFFSET);
> +	hqd->csmd_rptr = RREG32_SOC15(GC, 0,
> regCP_GFX_HQD_CSMD_RPTR);
> +	hqd->wptr = RREG32_SOC15(GC, 0, regCP_GFX_HQD_WPTR) |
> +		    (u64)RREG32_SOC15(GC, 0, regCP_GFX_HQD_WPTR_HI)
> << 32;
> +	status = RREG32_SOC15(GC, 0, regCP_GFX_HPD_STATUS0);
> +	state = REG_GET_FIELD(status, CP_GFX_HPD_STATUS0,
> QUEUE_STATE);
> +	hqd->connected =
> +		state >= GFX12_HPD_QUEUE_STATE_CONNECTED_MIN &&
> +		state <= GFX12_HPD_QUEUE_STATE_CONNECTED_MAX &&
> +		REG_GET_FIELD(status, CP_GFX_HPD_STATUS0,
> MAPPED_QUEUE) == queue;
> +out:
> +	soc24_grbm_select(adev, 0, 0, 0, 0);
> +	mutex_unlock(&adev->srbm_mutex);
> +	amdgpu_gfx_off_ctrl(adev, true);
> +
> +	return true;
> +}
> +
> +static bool gfx_v12_0_restore_hqd(struct amdgpu_device *adev, void
> *m,
> +				  u32 ring_size,
> +				  const struct amdgpu_gfx_saved_hqd
> *hqd)
> +{
> +	struct v12_gfx_mqd *mqd = m;
> +	u32 wptr = lower_32_bits(hqd->wptr) & ((ring_size >> 2) -
> 1);
> +	u32 *status;
> +
> +	/*
> +	 * MQD dwords 32-41 (reserved_32..41) are the PFP preemption
> status,
> +	 * mcbp_status_pfp: the offset and chained IB size and
> address of IB1
> +	 * (32-35) and IB2 (36-39), rb_preempt (40: preempted in the
> ring) and
> +	 * completion_status (41: 0 IB not started, 1 preempted
> inside an IB,
> +	 * 2 IB completed, 3 IB resumed). The PFP saves it when the
> queue is
> +	 * switched out of the pipe and resumes from it when the
> queue runs
> +	 * again, at the HQD offset. That survives the reset for a
> queue that
> +	 * was switched out. The queue the pipe executed has its
> state in the
> +	 * PFP, which the reset cleared: restart it at the write
> pointer with
> +	 * no IB to resume, and drop its work in flight.
> +	 */
> +	if (hqd->connected) {
> +		mqd->cp_gfx_hqd_offset = wptr;
> +		mqd->cp_gfx_hqd_csmd_rptr = wptr;
> +		for (status = &mqd->reserved_32; status <= &mqd-
> >reserved_41; status++)
> +			*status = 0;
> +	} else {
> +		mqd->cp_gfx_hqd_offset = hqd->offset;
> +		mqd->cp_gfx_hqd_csmd_rptr = hqd->csmd_rptr;
> +	}
> +	mqd->cp_gfx_hqd_wptr = lower_32_bits(hqd->wptr);
> +	mqd->cp_gfx_hqd_wptr_hi = upper_32_bits(hqd->wptr);
> +	mqd->cp_gfx_hqd_active = 0;
> +
> +	return hqd->connected;
> +}
> +
>  static uint64_t gfx_v12_0_get_gpu_clock_counter(struct amdgpu_device
> *adev)
>  {
>  	uint64_t clock = 0;

  reply	other threads:[~2026-11-19 11:36 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-05  3:05 [PATCH v4 01/13] drm/amdgpu: pass the device to the multi ring reset helpers Jesse Zhang
2026-11-05  3:05 ` [PATCH v4 02/13] drm/amdgpu/ring: During multi-queue reset, only call begin helper if needed Jesse Zhang
2026-11-11 23:52   ` Daniel Campos Ramos
2026-11-19 11:34   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 03/13] drm/amdgpu: add an engine scope to the IP block soft reset Jesse Zhang
2026-11-19 11:35   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 04/13] drm/amdgpu/gfx: add callbacks to save and restore a gfx HQD Jesse Zhang
2026-11-19 11:35   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 05/13] drm/amdgpu/gfx12: " Jesse Zhang
2026-11-19 11:35   ` Timur Kristóf [this message]
2026-11-05  3:05 ` [PATCH v4 06/13] drm/amdgpu/gfx11: " Jesse Zhang
2026-11-19 11:36   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 07/13] drm/amdgpu/userq: add a helper to signal the fences of a queue up to a point Jesse Zhang
2026-11-19 11:36   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 08/13] drm/amdgpu/userq: add helpers to keep the user queues of one engine across a reset Jesse Zhang
2026-11-19 11:36   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 09/13] drm/amdgpu/gfx12: add a gfx engine soft reset Jesse Zhang
2026-11-19 11:42   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 10/13] drm/amdgpu/gfx11: " Jesse Zhang
2026-11-19 11:47   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 11/13] drm/amdgpu/userq: reset the gfx engine when a gfx user queue reset fails Jesse Zhang
2026-11-19 11:47   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 12/13] drm/amdgpu/gfx12: enable the gfx engine soft reset Jesse Zhang
2026-11-19 11:47   ` Timur Kristóf
2026-11-05  3:05 ` [PATCH v4 13/13] drm/amdgpu/gfx11: " Jesse Zhang
2026-11-19 11:47   ` Timur Kristóf
2026-11-10  2:06 ` [PATCH v4 01/13] drm/amdgpu: pass the device to the multi ring reset helpers Zhang, Jesse(Jie)
2026-11-11 15:28   ` Timur Kristóf
2026-11-19 11:33 ` Timur Kristóf

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=8d7613f7203172334b3c295ec73cd9d83cec8340.camel@gmail.com \
    --to=timur.kristof@gmail.com \
    --cc=Alexander.Deucher@amd.com \
    --cc=Jesse.Zhang@amd.com \
    --cc=Jiongyu.Zhu@amd.com \
    --cc=Lijo.Lazar@amd.com \
    --cc=Manu.Rastogi@amd.com \
    --cc=Mario.Novales@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.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 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.