Re: [PATCH 2/2] drm/xe/guc: Add Wa_14025883347 for GuC DMA failure on reset

[Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>]

On 1/14/2026 5:00 AM, Sk Anirban wrote:
> Prevent GuC firmware DMA failures during GuC-only reset by disabling
> idle flow and verifying SRAM handling completion. Without this, reset
> can be issued while SRAM handler is copying WOPCM to SRAM,
> causing GuC HW to get stuck.
>
> Signed-off-by: Sk Anirban <sk.anirban@intel.com>
> ---
>   drivers/gpu/drm/xe/regs/xe_guc_regs.h |  8 ++++++
>   drivers/gpu/drm/xe/xe_guc.c           | 37 ++++++++++++++++++++++++++-
>   drivers/gpu/drm/xe/xe_wa_oob.rules    |  9 +++++++
>   3 files changed, 53 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/xe/regs/xe_guc_regs.h b/drivers/gpu/drm/xe/regs/xe_guc_regs.h
> index 87984713dd12..2f38fd231083 100644
> --- a/drivers/gpu/drm/xe/regs/xe_guc_regs.h
> +++ b/drivers/gpu/drm/xe/regs/xe_guc_regs.h
> @@ -40,6 +40,9 @@
>   #define   GS_BOOTROM_JUMP_PASSED		REG_FIELD_PREP(GS_BOOTROM_MASK, 0x76)
>   #define   GS_MIA_IN_RESET			REG_BIT(0)
>   
> +#define GUC_HASH_BOOT_CHECK			XE_REG(0xc010)
> +#define   GUC_BOOT_HASH_CHK			REG_BIT(31)

The naming here is a bit confusing, because the register and the field 
have basically the same name with the word order changed. AFAICS bit 31 
has a different name in the specs, so maybe match that?

> +
>   #define GUC_HEADER_INFO				XE_REG(0xc014)
>   
>   #define GUC_WOPCM_SIZE				XE_REG(0xc050)
> @@ -83,7 +86,12 @@
>   #define   GUC_WOPCM_OFFSET_MASK			REG_GENMASK(31, GUC_WOPCM_OFFSET_SHIFT)
>   #define   HUC_LOADING_AGENT_GUC			REG_BIT(1)
>   #define   GUC_WOPCM_OFFSET_VALID		REG_BIT(0)
> +
> +#define GUC_SRAM_STATUS				XE_REG(0xc398)
> +#define   GUC_SRAM_HANDLING_MASK		REG_GENMASK(8, 7)
> +
>   #define GUC_MAX_IDLE_COUNT			XE_REG(0xc3e4)
> +#define   GUC_IDLE_FLOW_DISABLE			REG_BIT(31)
>   #define GUC_PMTIMESTAMP_LO			XE_REG(0xc3e8)
>   #define GUC_PMTIMESTAMP_HI			XE_REG(0xc3ec)
>   
> diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
> index 44360437beeb..b5ec08a16aaf 100644
> --- a/drivers/gpu/drm/xe/xe_guc.c
> +++ b/drivers/gpu/drm/xe/xe_guc.c
> @@ -900,6 +900,35 @@ int xe_guc_post_load_init(struct xe_guc *guc)
>   	return xe_guc_submit_enable(guc);
>   }
>   
> +/*
> + * Wa_14025883347: Prevent GuC firmware DMA failures during GuC-only reset by ensuring
> + * SRAM save/restore operations are complete before reset.
> + */
> +static int guc_prevent_fw_dma_failure_on_reset(struct xe_guc *guc)
> +{
> +	struct xe_gt *gt = guc_to_gt(guc);
> +	u32 boot_hash_chk, guc_status, sram_status;
> +
> +	guc_status = xe_mmio_read32(&gt->mmio, GUC_STATUS);
> +	if (REG_FIELD_GET(GS_UKERNEL_MASK, guc_status) != XE_GUC_LOAD_STATUS_READY)

Why are we skipping this if the status is different than 
XE_GUC_LOAD_STATUS_READY?
During an SRAM save/restore the status can be different from that.

> +		return 0;
> +
> +	boot_hash_chk = xe_mmio_read32(&gt->mmio, GUC_HASH_BOOT_CHECK);
> +	if (!(boot_hash_chk & GUC_BOOT_HASH_CHK))
> +		return 0;
> +
> +	xe_mmio_rmw32(&gt->mmio, GUC_MAX_IDLE_COUNT, 0, GUC_IDLE_FLOW_DISABLE);

We should re-enable this after the reset, otherwise the GT won't power off.

> +
> +	sram_status = xe_mmio_read32(&gt->mmio, GUC_SRAM_STATUS);

The WA says that we need to poll this register until the status changes, 
not just read it once.

Daniele

> +	if (sram_status & GUC_SRAM_HANDLING_MASK) {
> +		xe_gt_err(gt, "SRAM handling not complete (GUC_SRAM_STATUS: 0x%x)\n",
> +			  sram_status);
> +		return -EIO;
> +	}
> +
> +	return 0;
> +}
> +
>   int xe_guc_reset(struct xe_guc *guc)
>   {
>   	struct xe_gt *gt = guc_to_gt(guc);
> @@ -909,6 +938,12 @@ int xe_guc_reset(struct xe_guc *guc)
>   
>   	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);
>   
> +	if (XE_GT_WA(gt, 14025883347)) {
> +		ret = guc_prevent_fw_dma_failure_on_reset(guc);
> +		if (ret)
> +			goto err_out;
> +	}
> +
>   	if (IS_SRIOV_VF(gt_to_xe(gt)))
>   		return xe_gt_sriov_vf_bootstrap(gt);
>   
> @@ -931,7 +966,7 @@ int xe_guc_reset(struct xe_guc *guc)
>   	return 0;
>   
>   err_out:
> -
> +	xe_gt_err(gt, "custom GuC reset failed with %pe\n", ERR_PTR(ret));
>   	return ret;
>   }
>   
> diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
> index 5cd7fa6d2a5c..ff2efc7a68cc 100644
> --- a/drivers/gpu/drm/xe/xe_wa_oob.rules
> +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
> @@ -73,3 +73,12 @@
>   15015404425_disable	PLATFORM(PANTHERLAKE), MEDIA_STEP(B0, FOREVER)
>   16026007364    MEDIA_VERSION(3000)
>   14020316580    MEDIA_VERSION(1301)
> +
> +14025883347	MEDIA_VERSION(1301)
> +		MEDIA_VERSION(2000)
> +		MEDIA_VERSION(3000)
> +		MEDIA_VERSION(3002)
> +		MEDIA_VERSION(3500)
> +		MEDIA_VERSION(3503)
> +		GRAPHICS_VERSION_RANGE(3000, 3001)
> +		GRAPHICS_VERSION_RANGE(3003, 3005)