Re: [PATCH v4 1/1] drm/xe/guc: Add Wa_14025883347 for GuC DMA failure on reset

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

On 2/2/2026 2:53 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.
>
> v2: Modify error message (Badal)
>      Rename reg bit name (Daniele)
>      Update WA skip condition (Daniele)
>      Update SRAM handling logic (Daniele)
> v3: Reorder WA call (Badal)
>      Wait for GuC ready status (Daniele)
> v4: Update reg name (Badal)
>      Add comment (Daniele)
>      Add extended graphics version (Daniele)
>      Modify rules
>
> 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           | 38 +++++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_wa_oob.rules    |  3 +++
>   3 files changed, 49 insertions(+)
>
> diff --git a/drivers/gpu/drm/xe/regs/xe_guc_regs.h b/drivers/gpu/drm/xe/regs/xe_guc_regs.h
> index 87984713dd12..5faac8316b66 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 BOOT_HASH_CHK				XE_REG(0xc010)
> +#define   GUC_BOOT_UKERNEL_VALID		REG_BIT(31)
> +
>   #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 2efc4678fa73..369b5a8f129a 100644
> --- a/drivers/gpu/drm/xe/xe_guc.c
> +++ b/drivers/gpu/drm/xe/xe_guc.c
> @@ -911,6 +911,41 @@ 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 void 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;
> +	int ret;
> +
> +	guc_status = xe_mmio_read32(&gt->mmio, GUC_STATUS);
> +	if (guc_status & GS_MIA_IN_RESET)
> +		return;
> +
> +	boot_hash_chk = xe_mmio_read32(&gt->mmio, BOOT_HASH_CHK);
> +	if (!(boot_hash_chk & GUC_BOOT_UKERNEL_VALID))
> +		return;
> +
> +	/* Disable idle flow during reset (GuC reset re-enables it automatically) */
> +	xe_mmio_rmw32(&gt->mmio, GUC_MAX_IDLE_COUNT, 0, GUC_IDLE_FLOW_DISABLE);
> +
> +	ret = xe_mmio_wait32(&gt->mmio, GUC_STATUS, GS_UKERNEL_MASK,
> +			     FIELD_PREP(GS_UKERNEL_MASK, XE_GUC_LOAD_STATUS_READY),
> +			     100000, &guc_status, false);
> +	if (ret)
> +		xe_gt_warn(gt, "GuC not ready after disabling idle flow (GUC_STATUS: 0x%x)\n",
> +			   guc_status);
> +
> +	ret = xe_mmio_wait32(&gt->mmio, GUC_SRAM_STATUS, GUC_SRAM_HANDLING_MASK,
> +			     0, 5000, &sram_status, false);
> +	if (ret)
> +		xe_gt_warn(gt, "SRAM handling not complete (GUC_SRAM_STATUS: 0x%x)\n",
> +			   sram_status);
> +}
> +
>   int xe_guc_reset(struct xe_guc *guc)
>   {
>   	struct xe_gt *gt = guc_to_gt(guc);
> @@ -923,6 +958,9 @@ int xe_guc_reset(struct xe_guc *guc)
>   	if (IS_SRIOV_VF(gt_to_xe(gt)))
>   		return xe_gt_sriov_vf_bootstrap(gt);
>   
> +	if (XE_GT_WA(gt, 14025883347))
> +		guc_prevent_fw_dma_failure_on_reset(guc);
> +
>   	xe_mmio_write32(mmio, GDRST, GRDOM_GUC);
>   
>   	ret = xe_mmio_wait32(mmio, GDRST, GRDOM_GUC, 0, 5000, &gdrst, false);
> diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
> index 5cd7fa6d2a5c..ac08f94f90a1 100644
> --- a/drivers/gpu/drm/xe/xe_wa_oob.rules
> +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
> @@ -73,3 +73,6 @@
>   15015404425_disable	PLATFORM(PANTHERLAKE), MEDIA_STEP(B0, FOREVER)
>   16026007364    MEDIA_VERSION(3000)
>   14020316580    MEDIA_VERSION(1301)
> +
> +14025883347	MEDIA_VERSION_RANGE(1301, 3503)
> +		GRAPHICS_VERSION_RANGE(2004, 3005)

We usually avoid having these big ranges in the WA table, in case a new 
derivative gets introduced that doesn't require the WA. If you think it 
is justified in this case, please get an ack from the platform enabling 
side.
Apart from this the patch LGTM, so I'll give my r-b if you get the ack.

Daniele