drivers/gpu/drm/xe/xe_guc.c

// SPDX-License-Identifier: MIT
/*
 * Copyright © 2022 Intel Corporation
 */

#include "xe_guc.h"

#include <linux/iopoll.h>
#include <drm/drm_managed.h>

#include <generated/xe_wa_oob.h>

#include "abi/guc_actions_abi.h"
#include "abi/guc_errors_abi.h"
#include "abi/guc_klvs_abi.h"
#include "regs/xe_gt_regs.h"
#include "regs/xe_gtt_defs.h"
#include "regs/xe_guc_regs.h"
#include "regs/xe_irq_regs.h"
#include "xe_bo.h"
#include "xe_configfs.h"
#include "xe_device.h"
#include "xe_force_wake.h"
#include "xe_gt.h"
#include "xe_gt_printk.h"
#include "xe_gt_sriov_vf.h"
#include "xe_gt_throttle.h"
#include "xe_gt_sriov_pf_migration.h"
#include "xe_guc_ads.h"
#include "xe_guc_buf.h"
#include "xe_guc_capture.h"
#include "xe_guc_ct.h"
#include "xe_guc_db_mgr.h"
#include "xe_guc_engine_activity.h"
#include "xe_guc_hwconfig.h"
#include "xe_guc_klv_helpers.h"
#include "xe_guc_log.h"
#include "xe_guc_pc.h"
#include "xe_guc_rc.h"
#include "xe_guc_relay.h"
#include "xe_guc_submit.h"
#include "xe_memirq.h"
#include "xe_mmio.h"
#include "xe_platform_types.h"
#include "xe_sleep.h"
#include "xe_sriov.h"
#include "xe_sriov_pf_migration.h"
#include "xe_uc.h"
#include "xe_uc_fw.h"
#include "xe_wa.h"
#include "xe_wopcm.h"

static u32 guc_bo_ggtt_addr(struct xe_guc *guc,
			    struct xe_bo *bo)
{
	struct xe_device *xe = guc_to_xe(guc);
	u32 addr;

	/*
	 * For most BOs, the address on the allocating tile is fine. However for
	 * some, e.g. G2G CTB, the address on a specific tile is required as it
	 * might be different for each tile. So, just always ask for the address
	 * on the target GuC.
	 */
	addr = __xe_bo_ggtt_addr(bo, gt_to_tile(guc_to_gt(guc))->id);

	/* GuC addresses above GUC_GGTT_TOP don't map through the GTT */
	xe_assert(xe, addr >= xe_wopcm_size(guc_to_xe(guc)));
	xe_assert(xe, addr < GUC_GGTT_TOP);
	xe_assert(xe, xe_bo_size(bo) <= GUC_GGTT_TOP - addr);

	return addr;
}

static u32 guc_ctl_debug_flags(struct xe_guc *guc)
{
	u32 level = xe_guc_log_get_level(&guc->log);
	u32 flags = 0;

	if (!GUC_LOG_LEVEL_IS_VERBOSE(level))
		flags |= GUC_LOG_DISABLED;
	else
		flags |= FIELD_PREP(GUC_LOG_VERBOSITY, GUC_LOG_LEVEL_TO_VERBOSITY(level));

	return flags;
}

static u32 guc_ctl_feature_flags(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	u32 flags = GUC_CTL_ENABLE_LITE_RESTORE;

	if (!xe->info.skip_guc_pc)
		flags |= GUC_CTL_ENABLE_SLPC;

	if (xe_configfs_get_psmi_enabled(to_pci_dev(xe->drm.dev)))
		flags |= GUC_CTL_ENABLE_PSMI_LOGGING;

	if (xe_guc_using_main_gamctrl_queues(guc))
		flags |= GUC_CTL_MAIN_GAMCTRL_QUEUES;

	if (xe_device_is_l2_flush_optimized(xe) && xe_gt_is_media_type(guc_to_gt(guc)))
		flags |= GUC_CTL_ENABLE_L2FLUSH_OPT;

	/*
	 * On GuC firmware 70.66 and above, the GUC_FEATURE_KLV_DISABLE_MULTI_QUEUE
	 * Feature KLV is used instead.
	 */
	if (!xe_configfs_get_enable_multi_queue(to_pci_dev(xe->drm.dev)) &&
	    !GUC_FIRMWARE_VER_AT_LEAST(guc, 70, 66))
		flags |= GUC_CTL_DISABLE_MULTI_QUEUE;

	return flags;
}

static u32 guc_ctl_log_params_flags(struct xe_guc *guc)
{
	u32 offset = guc_bo_ggtt_addr(guc, guc->log.bo) >> PAGE_SHIFT;
	u32 flags;

	#if (((XE_GUC_LOG_CRASH_DUMP_BUFFER_SIZE) % SZ_1M) == 0)
	#define LOG_UNIT SZ_1M
	#define LOG_FLAG GUC_LOG_LOG_ALLOC_UNITS
	#else
	#define LOG_UNIT SZ_4K
	#define LOG_FLAG 0
	#endif

	#if (((XE_GUC_LOG_STATE_CAPTURE_BUFFER_SIZE) % SZ_1M) == 0)
	#define CAPTURE_UNIT SZ_1M
	#define CAPTURE_FLAG GUC_LOG_CAPTURE_ALLOC_UNITS
	#else
	#define CAPTURE_UNIT SZ_4K
	#define CAPTURE_FLAG 0
	#endif

	BUILD_BUG_ON(!XE_GUC_LOG_CRASH_DUMP_BUFFER_SIZE);
	BUILD_BUG_ON(!IS_ALIGNED(XE_GUC_LOG_CRASH_DUMP_BUFFER_SIZE, LOG_UNIT));
	BUILD_BUG_ON(!XE_GUC_LOG_EVENT_DATA_BUFFER_SIZE);
	BUILD_BUG_ON(!IS_ALIGNED(XE_GUC_LOG_EVENT_DATA_BUFFER_SIZE, LOG_UNIT));
	BUILD_BUG_ON(!XE_GUC_LOG_STATE_CAPTURE_BUFFER_SIZE);
	BUILD_BUG_ON(!IS_ALIGNED(XE_GUC_LOG_STATE_CAPTURE_BUFFER_SIZE, CAPTURE_UNIT));

	flags = GUC_LOG_VALID |
		GUC_LOG_NOTIFY_ON_HALF_FULL |
		CAPTURE_FLAG |
		LOG_FLAG |
		FIELD_PREP(GUC_LOG_CRASH_DUMP, XE_GUC_LOG_CRASH_DUMP_BUFFER_SIZE / LOG_UNIT - 1) |
		FIELD_PREP(GUC_LOG_EVENT_DATA, XE_GUC_LOG_EVENT_DATA_BUFFER_SIZE / LOG_UNIT - 1) |
		FIELD_PREP(GUC_LOG_STATE_CAPTURE, XE_GUC_LOG_STATE_CAPTURE_BUFFER_SIZE /
			   CAPTURE_UNIT - 1) |
		FIELD_PREP(GUC_LOG_BUF_ADDR, offset);

	#undef LOG_UNIT
	#undef LOG_FLAG
	#undef CAPTURE_UNIT
	#undef CAPTURE_FLAG

	return flags;
}

static u32 guc_ctl_ads_flags(struct xe_guc *guc)
{
	u32 ads = guc_bo_ggtt_addr(guc, guc->ads.bo) >> PAGE_SHIFT;
	u32 flags = FIELD_PREP(GUC_ADS_ADDR, ads);

	return flags;
}

static bool needs_wa_dual_queue(struct xe_gt *gt)
{
	/*
	 * The DUAL_QUEUE_WA tells the GuC to not allow concurrent submissions
	 * on RCS and CCSes with different address spaces, which on DG2 is
	 * required as a WA for an HW bug.
	 */
	if (XE_GT_WA(gt, 22011391025))
		return true;

	/*
	 * On newer platforms, the HW has been updated to not allow parallel
	 * execution of different address spaces, so the RCS/CCS will stall the
	 * context switch if one of the other RCS/CCSes is busy with a different
	 * address space. While functionally correct, having a submission
	 * stalled on the HW limits the GuC ability to shuffle things around and
	 * can cause complications if the non-stalled submission runs for a long
	 * time, because the GuC doesn't know that the stalled submission isn't
	 * actually running and might declare it as hung. Therefore, we enable
	 * the DUAL_QUEUE_WA on all newer platforms on GTs that have CCS engines
	 * to move management back to the GuC.
	 */
	if (CCS_INSTANCES(gt) && GRAPHICS_VERx100(gt_to_xe(gt)) >= 1270)
		return true;

	return false;
}

static u32 guc_ctl_wa_flags(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	struct xe_gt *gt = guc_to_gt(guc);
	u32 flags = 0;

	if (XE_GT_WA(gt, 22012773006))
		flags |= GUC_WA_POLLCS;

	if (XE_GT_WA(gt, 14014475959))
		flags |= GUC_WA_HOLD_CCS_SWITCHOUT;

	if (needs_wa_dual_queue(gt))
		flags |= GUC_WA_DUAL_QUEUE;

	/*
	 * Wa_22011802037: FIXME - there's more to be done than simply setting
	 * this flag: make sure each CS is stopped when preparing for GT reset
	 * and wait for pending MI_FW.
	 */
	if (GRAPHICS_VERx100(xe) < 1270)
		flags |= GUC_WA_PRE_PARSER;

	if (XE_GT_WA(gt, 22012727170) || XE_GT_WA(gt, 22012727685))
		flags |= GUC_WA_CONTEXT_ISOLATION;

	if (XE_GT_WA(gt, 18020744125) &&
	    !xe_hw_engine_mask_per_class(gt, XE_ENGINE_CLASS_RENDER))
		flags |= GUC_WA_RCS_REGS_IN_CCS_REGS_LIST;

	if (XE_GT_WA(gt, 14018913170))
		flags |= GUC_WA_ENABLE_TSC_CHECK_ON_RC6;

	if (XE_GT_WA(gt, 16023683509))
		flags |= GUC_WA_SAVE_RESTORE_MCFG_REG_AT_MC6;

	return flags;
}

static u32 guc_ctl_devid(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);

	return (((u32)xe->info.devid) << 16) | xe->info.revid;
}

static void guc_print_params(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	u32 *params = guc->params;
	int i;

	BUILD_BUG_ON(sizeof(guc->params) != GUC_CTL_MAX_DWORDS * sizeof(u32));
	BUILD_BUG_ON(GUC_CTL_MAX_DWORDS + 2 != SOFT_SCRATCH_COUNT);

	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
		xe_gt_dbg(gt, "GuC param[%2d] = 0x%08x\n", i, params[i]);
}

static void guc_init_params(struct xe_guc *guc)
{
	u32 *params = guc->params;

	params[GUC_CTL_LOG_PARAMS] = guc_ctl_log_params_flags(guc);
	params[GUC_CTL_FEATURE] = 0;
	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
	params[GUC_CTL_ADS] = guc_ctl_ads_flags(guc);
	params[GUC_CTL_WA] = 0;
	params[GUC_CTL_DEVID] = guc_ctl_devid(guc);

	guc_print_params(guc);
}

static void guc_init_params_post_hwconfig(struct xe_guc *guc)
{
	u32 *params = guc->params;

	params[GUC_CTL_LOG_PARAMS] = guc_ctl_log_params_flags(guc);
	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
	params[GUC_CTL_ADS] = guc_ctl_ads_flags(guc);
	params[GUC_CTL_WA] = guc_ctl_wa_flags(guc);
	params[GUC_CTL_DEVID] = guc_ctl_devid(guc);

	guc_print_params(guc);
}

/*
 * Initialize the GuC parameter block before starting the firmware
 * transfer. These parameters are read by the firmware on startup
 * and cannot be changed thereafter.
 */
static void guc_write_params(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	int i;

	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);

	xe_mmio_write32(&gt->mmio, SOFT_SCRATCH(0), 0);

	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
		xe_mmio_write32(&gt->mmio, SOFT_SCRATCH(1 + i), guc->params[i]);
}

static int guc_action_register_g2g_buffer(struct xe_guc *guc, u32 type, u32 dst_tile, u32 dst_dev,
					  u32 desc_addr, u32 buff_addr, u32 size)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_device *xe = gt_to_xe(gt);
	u32 action[] = {
		XE_GUC_ACTION_REGISTER_G2G,
		FIELD_PREP(XE_G2G_REGISTER_SIZE, size / SZ_4K - 1) |
		FIELD_PREP(XE_G2G_REGISTER_TYPE, type) |
		FIELD_PREP(XE_G2G_REGISTER_TILE, dst_tile) |
		FIELD_PREP(XE_G2G_REGISTER_DEVICE, dst_dev),
		desc_addr,
		buff_addr,
	};

	xe_assert(xe, (type == XE_G2G_TYPE_IN) || (type == XE_G2G_TYPE_OUT));
	xe_assert(xe, !(size % SZ_4K));

	return xe_guc_ct_send_block(&guc->ct, action, ARRAY_SIZE(action));
}

static int guc_action_deregister_g2g_buffer(struct xe_guc *guc, u32 type, u32 dst_tile, u32 dst_dev)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_device *xe = gt_to_xe(gt);
	u32 action[] = {
		XE_GUC_ACTION_DEREGISTER_G2G,
		FIELD_PREP(XE_G2G_DEREGISTER_TYPE, type) |
		FIELD_PREP(XE_G2G_DEREGISTER_TILE, dst_tile) |
		FIELD_PREP(XE_G2G_DEREGISTER_DEVICE, dst_dev),
	};

	xe_assert(xe, (type == XE_G2G_TYPE_IN) || (type == XE_G2G_TYPE_OUT));

	return xe_guc_ct_send_block(&guc->ct, action, ARRAY_SIZE(action));
}

#define G2G_DEV(gt)	(((gt)->info.type == XE_GT_TYPE_MAIN) ? 0 : 1)

#define G2G_BUFFER_SIZE (SZ_4K)
#define G2G_DESC_SIZE (64)
#define G2G_DESC_AREA_SIZE (SZ_4K)

/*
 * Generate a unique id for each bi-directional CTB for each pair of
 * near and far tiles/devices. The id can then be used as an index into
 * a single allocation that is sub-divided into multiple CTBs.
 *
 * For example, with two devices per tile and two tiles, the table should
 * look like:
 *           Far <tile>.<dev>
 *         0.0   0.1   1.0   1.1
 * N 0.0  --/-- 00/01 02/03 04/05
 * e 0.1  01/00 --/-- 06/07 08/09
 * a 1.0  03/02 07/06 --/-- 10/11
 * r 1.1  05/04 09/08 11/10 --/--
 *
 * Where each entry is Rx/Tx channel id.
 *
 * So GuC #3 (tile 1, dev 1) talking to GuC #2 (tile 1, dev 0) would
 * be reading from channel #11 and writing to channel #10. Whereas,
 * GuC #2 talking to GuC #3 would be read on #10 and write to #11.
 */
static unsigned int g2g_slot(u32 near_tile, u32 near_dev, u32 far_tile, u32 far_dev,
			     u32 type, u32 max_inst, bool have_dev)
{
	u32 near = near_tile, far = far_tile;
	u32 idx = 0, x, y, direction;
	int i;

	if (have_dev) {
		near = (near << 1) | near_dev;
		far = (far << 1) | far_dev;
	}

	/* No need to send to one's self */
	if (far == near)
		return -1;

	if (far > near) {
		/* Top right table half */
		x = far;
		y = near;

		/* T/R is 'forwards' direction */
		direction = type;
	} else {
		/* Bottom left table half */
		x = near;
		y = far;

		/* B/L is 'backwards' direction */
		direction = (1 - type);
	}

	/* Count the rows prior to the target */
	for (i = y; i > 0; i--)
		idx += max_inst - i;

	/* Count this row up to the target */
	idx += (x - 1 - y);

	/* Slots are in Rx/Tx pairs */
	idx *= 2;

	/* Pick Rx/Tx direction */
	idx += direction;

	return idx;
}

static int guc_g2g_register(struct xe_guc *near_guc, struct xe_gt *far_gt, u32 type, bool have_dev)
{
	struct xe_gt *near_gt = guc_to_gt(near_guc);
	struct xe_device *xe = gt_to_xe(near_gt);
	struct xe_bo *g2g_bo;
	u32 near_tile = gt_to_tile(near_gt)->id;
	u32 near_dev = G2G_DEV(near_gt);
	u32 far_tile = gt_to_tile(far_gt)->id;
	u32 far_dev = G2G_DEV(far_gt);
	u32 max = xe->info.gt_count;
	u32 base, desc, buf;
	int slot;

	/* G2G is not allowed between different cards */
	xe_assert(xe, xe == gt_to_xe(far_gt));

	g2g_bo = near_guc->g2g.bo;
	xe_assert(xe, g2g_bo);

	slot = g2g_slot(near_tile, near_dev, far_tile, far_dev, type, max, have_dev);
	xe_assert(xe, slot >= 0);

	base = guc_bo_ggtt_addr(near_guc, g2g_bo);
	desc = base + slot * G2G_DESC_SIZE;
	buf = base + G2G_DESC_AREA_SIZE + slot * G2G_BUFFER_SIZE;

	xe_assert(xe, (desc - base + G2G_DESC_SIZE) <= G2G_DESC_AREA_SIZE);
	xe_assert(xe, (buf - base + G2G_BUFFER_SIZE) <= xe_bo_size(g2g_bo));

	return guc_action_register_g2g_buffer(near_guc, type, far_tile, far_dev,
					      desc, buf, G2G_BUFFER_SIZE);
}

static void guc_g2g_deregister(struct xe_guc *guc, u32 far_tile, u32 far_dev, u32 type)
{
	guc_action_deregister_g2g_buffer(guc, type, far_tile, far_dev);
}

static u32 guc_g2g_size(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_device *xe = gt_to_xe(gt);
	unsigned int count = xe->info.gt_count;
	u32 num_channels = (count * (count - 1)) / 2;

	xe_assert(xe, num_channels * XE_G2G_TYPE_LIMIT * G2G_DESC_SIZE <= G2G_DESC_AREA_SIZE);

	return num_channels * XE_G2G_TYPE_LIMIT * G2G_BUFFER_SIZE + G2G_DESC_AREA_SIZE;
}

static bool xe_guc_g2g_wanted(struct xe_device *xe)
{
	/* Can't do GuC to GuC communication if there is only one GuC */
	if (xe->info.gt_count <= 1)
		return false;

	/* No current user */
	return false;
}

static int guc_g2g_alloc(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_device *xe = gt_to_xe(gt);
	struct xe_tile *tile = gt_to_tile(gt);
	struct xe_bo *bo;
	u32 g2g_size;

	if (guc->g2g.bo)
		return 0;

	if (gt->info.id != 0) {
		struct xe_gt *root_gt = xe_device_get_gt(xe, 0);
		struct xe_guc *root_guc = &root_gt->uc.guc;
		struct xe_bo *bo;

		bo = xe_bo_get(root_guc->g2g.bo);
		if (!bo)
			return -ENODEV;

		guc->g2g.bo = bo;
		guc->g2g.owned = false;
		return 0;
	}

	g2g_size = guc_g2g_size(guc);
	bo = xe_managed_bo_create_pin_map(xe, tile, g2g_size,
					  XE_BO_FLAG_VRAM_IF_DGFX(tile) |
					  XE_BO_FLAG_GGTT |
					  XE_BO_FLAG_GGTT_ALL |
					  XE_BO_FLAG_GGTT_INVALIDATE |
					  XE_BO_FLAG_PINNED_NORESTORE);
	if (IS_ERR(bo))
		return PTR_ERR(bo);

	xe_map_memset(xe, &bo->vmap, 0, 0, g2g_size);
	guc->g2g.bo = bo;
	guc->g2g.owned = true;

	return 0;
}

static void guc_g2g_fini(struct xe_guc *guc)
{
	if (!guc->g2g.bo)
		return;

	/* Unpinning the owned object is handled by generic shutdown */
	if (!guc->g2g.owned)
		xe_bo_put(guc->g2g.bo);

	guc->g2g.bo = NULL;
}

static int guc_g2g_start(struct xe_guc *guc)
{
	struct xe_gt *far_gt, *gt = guc_to_gt(guc);
	struct xe_device *xe = gt_to_xe(gt);
	unsigned int i, j;
	int t, err;
	bool have_dev;

	if (!guc->g2g.bo) {
		int ret;

		ret = guc_g2g_alloc(guc);
		if (ret)
			return ret;
	}

	/* GuC interface will need extending if more GT device types are ever created. */
	xe_gt_assert(gt, (gt->info.type == XE_GT_TYPE_MAIN) || (gt->info.type == XE_GT_TYPE_MEDIA));

	/* Channel numbering depends on whether there are multiple GTs per tile */
	have_dev = xe->info.gt_count > xe->info.tile_count;

	for_each_gt(far_gt, xe, i) {
		u32 far_tile, far_dev;

		if (far_gt->info.id == gt->info.id)
			continue;

		far_tile = gt_to_tile(far_gt)->id;
		far_dev = G2G_DEV(far_gt);

		for (t = 0; t < XE_G2G_TYPE_LIMIT; t++) {
			err = guc_g2g_register(guc, far_gt, t, have_dev);
			if (err) {
				while (--t >= 0)
					guc_g2g_deregister(guc, far_tile, far_dev, t);
				goto err_deregister;
			}
		}
	}

	return 0;

err_deregister:
	for_each_gt(far_gt, xe, j) {
		u32 tile, dev;

		if (far_gt->info.id == gt->info.id)
			continue;

		if (j >= i)
			break;

		tile = gt_to_tile(far_gt)->id;
		dev = G2G_DEV(far_gt);

		for (t = 0; t < XE_G2G_TYPE_LIMIT; t++)
			guc_g2g_deregister(guc, tile, dev, t);
	}

	return err;
}

static int __guc_opt_in_features_enable(struct xe_guc *guc, u64 addr, u32 num_dwords)
{
	u32 action[] = {
		XE_GUC_ACTION_OPT_IN_FEATURE_KLV,
		lower_32_bits(addr),
		upper_32_bits(addr),
		num_dwords
	};

	return xe_guc_ct_send_block(&guc->ct, action, ARRAY_SIZE(action));
}

static bool supports_dynamic_ics(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	struct xe_gt *gt = guc_to_gt(guc);

	/* Dynamic ICS is available for PVC and Xe2 and newer platforms. */
	if (xe->info.platform != XE_PVC && GRAPHICS_VER(xe) < 20)
		return false;

	/*
	 * The feature is currently not compatible with multi-lrc, so the GuC
	 * does not support it at all on the media engines (which are the main
	 * users of mlrc). On the primary GT side, to avoid it being used in
	 * conjunction with mlrc, we only enable it if we are in single CCS
	 * mode.
	 */
	if (xe_gt_is_media_type(gt) || gt->ccs_mode > 1)
		return false;

	/*
	 * Dynamic ICS requires GuC v70.40.1, which maps to compatibility
	 * version v1.18.4.
	 */
	return GUC_SUBMIT_VER(guc) >= MAKE_GUC_VER(1, 18, 4);
}

#define OPT_IN_MAX_DWORDS 16
int xe_guc_opt_in_features_enable(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	CLASS(xe_guc_buf, buf)(&guc->buf, OPT_IN_MAX_DWORDS);
	u32 count = 0;
	u32 *klvs;
	int ret;

	if (!xe_guc_buf_is_valid(buf))
		return -ENOBUFS;

	klvs = xe_guc_buf_cpu_ptr(buf);

	/*
	 * The extra CAT error type opt-in was added in GuC v70.17.0, which maps
	 * to compatibility version v1.7.0.
	 * Note that the GuC allows enabling this KLV even on platforms that do
	 * not support the extra type; in such case the returned type variable
	 * will be set to a known invalid value which we can check against.
	 */
	if (GUC_SUBMIT_VER(guc) >= MAKE_GUC_VER(1, 7, 0))
		klvs[count++] = PREP_GUC_KLV_TAG(OPT_IN_FEATURE_EXT_CAT_ERR_TYPE);

	/*
	 * The uncorrectable local error notification opt-in was added in
	 * GuC v70.38.0, which maps to compatibility version v1.18.0.
	 */
	if (GUC_SUBMIT_VER(guc) >= MAKE_GUC_VER(1, 18, 0) &&
	    guc_to_gt(guc)->info.has_uncorrectable_error_reporting)
		klvs[count++] =
			PREP_GUC_KLV_TAG(OPT_IN_FEATURE_UNCORRECTABLE_LOCAL_ERROR_NOTIFICATION);

	if (supports_dynamic_ics(guc))
		klvs[count++] = PREP_GUC_KLV_TAG(OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH);

	if (count) {
		xe_assert(xe, count <= OPT_IN_MAX_DWORDS);

		ret = __guc_opt_in_features_enable(guc, xe_guc_buf_flush(buf), count);
		if (ret < 0) {
			xe_gt_err(guc_to_gt(guc),
				  "failed to enable GuC opt-in features: %pe\n",
				  ERR_PTR(ret));
			return ret;
		}
	}

	return 0;
}

static void guc_fini_hw(void *arg)
{
	struct xe_guc *guc = arg;
	struct xe_gt *gt = guc_to_gt(guc);

	xe_with_force_wake(fw_ref, gt_to_fw(gt), XE_FORCEWAKE_ALL)
		xe_uc_sanitize_reset(&guc_to_gt(guc)->uc);

	guc_g2g_fini(guc);
}

static void vf_guc_fini_hw(void *arg)
{
	struct xe_guc *guc = arg;

	xe_gt_sriov_vf_reset(guc_to_gt(guc));
}

/**
 * xe_guc_comm_init_early - early initialization of GuC communication
 * @guc: the &xe_guc to initialize
 *
 * Must be called prior to first MMIO communication with GuC firmware.
 */
void xe_guc_comm_init_early(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);

	if (xe_gt_is_media_type(gt))
		guc->notify_reg = MED_GUC_HOST_INTERRUPT;
	else
		guc->notify_reg = GUC_HOST_INTERRUPT;
}

static int xe_guc_realloc_post_hwconfig(struct xe_guc *guc)
{
	struct xe_tile *tile = gt_to_tile(guc_to_gt(guc));
	struct xe_device *xe = guc_to_xe(guc);
	int ret;

	if (!IS_DGFX(guc_to_xe(guc)))
		return 0;

	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->fw.bo);
	if (ret)
		return ret;

	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->log.bo);
	if (ret)
		return ret;

	ret = xe_managed_bo_reinit_in_vram(xe, tile, &guc->ads.bo);
	if (ret)
		return ret;

	return 0;
}

static int vf_guc_init_noalloc(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	int err;

	err = xe_gt_sriov_vf_bootstrap(gt);
	if (err)
		return err;

	err = xe_gt_sriov_vf_query_config(gt);
	if (err)
		return err;

	return 0;
}

int xe_guc_init_noalloc(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	struct xe_gt *gt = guc_to_gt(guc);
	int ret;

	xe_guc_comm_init_early(guc);

	ret = xe_guc_ct_init_noalloc(&guc->ct);
	if (ret)
		goto out;

	ret = xe_guc_relay_init(&guc->relay);
	if (ret)
		goto out;

	if (IS_SRIOV_VF(xe)) {
		ret = vf_guc_init_noalloc(guc);
		if (ret)
			goto out;
	}

	return 0;

out:
	xe_gt_err(gt, "GuC init failed with %pe\n", ERR_PTR(ret));
	return ret;
}

int xe_guc_init(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	struct xe_gt *gt = guc_to_gt(guc);
	int ret;

	guc->fw.type = XE_UC_FW_TYPE_GUC;
	ret = xe_uc_fw_init(&guc->fw);
	if (ret)
		return ret;

	if (!xe_uc_fw_is_enabled(&guc->fw))
		return 0;

	/* Disable page reclaim if GuC FW does not support */
	if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 14, 0))
		xe->info.has_page_reclaim_hw_assist = false;

	/* Disable indirect_ring_state if missing GuC 70.53+ WA 14025515070. */
	if (gt->info.has_indirect_ring_state &&
	    XE_GT_WA(gt, 14025515070) &&
	    GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 26, 0)) {
		gt->info.has_indirect_ring_state = 0;
		xe_gt_notice(gt, "indirect ring state requires WA in GuC submit ver 1.26+\n");
	}

	if (IS_SRIOV_VF(xe)) {
		ret = devm_add_action_or_reset(xe->drm.dev, vf_guc_fini_hw, guc);
		if (ret)
			goto out;

		ret = xe_guc_ct_init(&guc->ct);
		if (ret)
			goto out;
		return 0;
	}

	ret = xe_guc_log_init(&guc->log);
	if (ret)
		goto out;

	ret = xe_guc_capture_init(guc);
	if (ret)
		goto out;

	ret = xe_guc_ads_init(&guc->ads);
	if (ret)
		goto out;

	ret = xe_guc_ct_init(&guc->ct);
	if (ret)
		goto out;

	xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_LOADABLE);

	ret = devm_add_action_or_reset(xe->drm.dev, guc_fini_hw, guc);
	if (ret)
		goto out;

	guc_init_params(guc);

	return 0;

out:
	xe_gt_err(gt, "GuC init failed with %pe\n", ERR_PTR(ret));
	return ret;
}

static int vf_guc_init_post_hwconfig(struct xe_guc *guc)
{
	int err;

	err = xe_guc_submit_init(guc, xe_gt_sriov_vf_guc_ids(guc_to_gt(guc)));
	if (err)
		return err;

	err = xe_guc_buf_cache_init(&guc->buf);
	if (err)
		return err;

	/* XXX xe_guc_db_mgr_init not needed for now */

	return 0;
}

static u32 guc_additional_cache_size(struct xe_device *xe)
{
	if (IS_SRIOV_PF(xe) && xe_sriov_pf_migration_supported(xe))
		return XE_GT_SRIOV_PF_MIGRATION_GUC_DATA_MAX_SIZE;
	else
		return 0; /* Fallback to default size */
}

/**
 * xe_guc_init_post_hwconfig - initialize GuC post hwconfig load
 * @guc: The GuC object
 *
 * Return: 0 on success, negative error code on error.
 */
int xe_guc_init_post_hwconfig(struct xe_guc *guc)
{
	int ret;

	if (IS_SRIOV_VF(guc_to_xe(guc)))
		return vf_guc_init_post_hwconfig(guc);

	ret = xe_guc_realloc_post_hwconfig(guc);
	if (ret)
		return ret;

	ret = xe_guc_ct_init_post_hwconfig(&guc->ct);
	if (ret)
		return ret;

	guc_init_params_post_hwconfig(guc);

	ret = xe_guc_submit_init(guc, ~0);
	if (ret)
		return ret;

	ret = xe_guc_db_mgr_init(&guc->dbm, ~0);
	if (ret)
		return ret;

	ret = xe_guc_pc_init(&guc->pc);
	if (ret)
		return ret;

	ret = xe_guc_rc_init(guc);
	if (ret)
		return ret;

	ret = xe_guc_engine_activity_init(guc);
	if (ret)
		return ret;

	ret = xe_guc_buf_cache_init_with_size(&guc->buf,
					      guc_additional_cache_size(guc_to_xe(guc)));
	if (ret)
		return ret;

	return xe_guc_ads_init_post_hwconfig(&guc->ads);
}

int xe_guc_post_load_init(struct xe_guc *guc)
{
	int ret;

	xe_guc_ads_populate_post_load(&guc->ads);

	ret = xe_guc_opt_in_features_enable(guc);
	if (ret)
		return ret;

	if (xe_guc_g2g_wanted(guc_to_xe(guc))) {
		ret = guc_g2g_start(guc);
		if (ret)
			return ret;
	}

	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);
	struct xe_mmio *mmio = &gt->mmio;
	u32 guc_status, gdrst;
	int ret;

	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);

	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);
	if (ret) {
		xe_gt_err(gt, "GuC reset timed out, GDRST=%#x\n", gdrst);
		goto err_out;
	}

	guc_status = xe_mmio_read32(mmio, GUC_STATUS);
	if (!(guc_status & GS_MIA_IN_RESET)) {
		xe_gt_err(gt, "GuC status: %#x, MIA core expected to be in reset\n",
			  guc_status);
		ret = -EIO;
		goto err_out;
	}

	return 0;

err_out:

	return ret;
}

static void guc_prepare_xfer(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_mmio *mmio = &gt->mmio;
	struct xe_device *xe =  guc_to_xe(guc);
	u32 shim_flags = GUC_ENABLE_READ_CACHE_LOGIC |
		GUC_ENABLE_READ_CACHE_FOR_SRAM_DATA |
		GUC_ENABLE_READ_CACHE_FOR_WOPCM_DATA |
		GUC_ENABLE_MIA_CLOCK_GATING;

	if (GRAPHICS_VERx100(xe) < 1250)
		shim_flags |= GUC_DISABLE_SRAM_INIT_TO_ZEROES |
				GUC_ENABLE_MIA_CACHING;

	if (GRAPHICS_VER(xe) >= 20 || xe->info.platform == XE_PVC)
		shim_flags |= REG_FIELD_PREP(GUC_MOCS_INDEX_MASK, gt->mocs.uc_index);

	/* Must program this register before loading the ucode with DMA */
	xe_mmio_write32(mmio, GUC_SHIM_CONTROL, shim_flags);

	xe_mmio_write32(mmio, GT_PM_CONFIG, GT_DOORBELL_ENABLE);

	/* Make sure GuC receives ARAT interrupts */
	xe_mmio_rmw32(mmio, PMINTRMSK, ARAT_EXPIRED_INTRMSK, 0);
}

/*
 * Supporting MMIO & in memory RSA
 */
static int guc_xfer_rsa(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	u32 rsa[UOS_RSA_SCRATCH_COUNT];
	size_t copied;
	int i;

	if (guc->fw.rsa_size > 256) {
		u32 rsa_ggtt_addr = xe_bo_ggtt_addr(guc->fw.bo) +
				    xe_uc_fw_rsa_offset(&guc->fw);
		xe_mmio_write32(&gt->mmio, UOS_RSA_SCRATCH(0), rsa_ggtt_addr);
		return 0;
	}

	copied = xe_uc_fw_copy_rsa(&guc->fw, rsa, sizeof(rsa));
	if (copied < sizeof(rsa))
		return -ENOMEM;

	for (i = 0; i < UOS_RSA_SCRATCH_COUNT; i++)
		xe_mmio_write32(&gt->mmio, UOS_RSA_SCRATCH(i), rsa[i]);

	return 0;
}

/*
 * Wait for the GuC to start up.
 *
 * Measurements indicate this should take no more than 20ms (assuming the GT
 * clock is at maximum frequency). However, thermal throttling and other issues
 * can prevent the clock hitting max and thus making the load take significantly
 * longer. Allow up to 3s as a safety margin in normal builds. For
 * CONFIG_DRM_XE_DEBUG allow up to 10s to account for slower execution, issues
 * in PCODE, driver, fan, etc.
 *
 * Keep checking the GUC_STATUS every 10ms with a debug message every 100
 * attempts as a "I'm slow, but alive" message. Regardless, if it takes more
 * than 200ms, emit a warning.
 */

#if IS_ENABLED(CONFIG_DRM_XE_DEBUG)
#define GUC_LOAD_TIMEOUT_SEC	20
#else
#define GUC_LOAD_TIMEOUT_SEC	3
#endif
#define GUC_LOAD_TIME_WARN_MSEC	200

static void print_load_status_err(struct xe_gt *gt, u32 status)
{
	struct xe_mmio *mmio = &gt->mmio;
	u32 ukernel = REG_FIELD_GET(GS_UKERNEL_MASK, status);
	u32 bootrom = REG_FIELD_GET(GS_BOOTROM_MASK, status);

	xe_gt_err(gt, "load failed: status: Reset = %d, BootROM = 0x%02X, UKernel = 0x%02X, MIA = 0x%02X, Auth = 0x%02X\n",
		  REG_FIELD_GET(GS_MIA_IN_RESET, status),
		  bootrom, ukernel,
		  REG_FIELD_GET(GS_MIA_MASK, status),
		  REG_FIELD_GET(GS_AUTH_STATUS_MASK, status));

	switch (bootrom) {
	case XE_BOOTROM_STATUS_NO_KEY_FOUND:
		xe_gt_err(gt, "invalid key requested, header = 0x%08X\n",
			  xe_mmio_read32(mmio, GUC_HEADER_INFO));
		break;
	case XE_BOOTROM_STATUS_RSA_FAILED:
		xe_gt_err(gt, "firmware signature verification failed\n");
		break;
	case XE_BOOTROM_STATUS_PROD_KEY_CHECK_FAILURE:
		xe_gt_err(gt, "firmware production part check failure\n");
		break;
	}

	switch (ukernel) {
	case XE_GUC_LOAD_STATUS_HWCONFIG_START:
		xe_gt_err(gt, "still extracting hwconfig table.\n");
		break;
	case XE_GUC_LOAD_STATUS_EXCEPTION:
		xe_gt_err(gt, "firmware exception. EIP: %#x\n",
			  xe_mmio_read32(mmio, SOFT_SCRATCH(13)));
		break;
	case XE_GUC_LOAD_STATUS_INIT_DATA_INVALID:
		xe_gt_err(gt, "illegal init/ADS data\n");
		break;
	case XE_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID:
		xe_gt_err(gt, "illegal register in save/restore workaround list\n");
		break;
	case XE_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR:
		xe_gt_err(gt, "illegal workaround KLV data\n");
		break;
	case XE_GUC_LOAD_STATUS_INVALID_FTR_FLAG:
		xe_gt_err(gt, "illegal feature flag specified\n");
		break;
	}
}

/*
 * Check GUC_STATUS looking for known terminal states (either completion or
 * failure) of either the microkernel status field or the boot ROM status field.
 *
 * Returns 1 for successful completion, -1 for failure and 0 for any
 * intermediate state.
 */
static int guc_load_done(struct xe_gt *gt, u32 *status, u32 *tries)
{
	u32 ukernel, bootrom;

	*status = xe_mmio_read32(&gt->mmio, GUC_STATUS);
	ukernel = REG_FIELD_GET(GS_UKERNEL_MASK, *status);
	bootrom = REG_FIELD_GET(GS_BOOTROM_MASK, *status);

	switch (ukernel) {
	case XE_GUC_LOAD_STATUS_READY:
		return 1;
	case XE_GUC_LOAD_STATUS_ERROR_DEVID_BUILD_MISMATCH:
	case XE_GUC_LOAD_STATUS_GUC_PREPROD_BUILD_MISMATCH:
	case XE_GUC_LOAD_STATUS_ERROR_DEVID_INVALID_GUCTYPE:
	case XE_GUC_LOAD_STATUS_HWCONFIG_ERROR:
	case XE_GUC_LOAD_STATUS_BOOTROM_VERSION_MISMATCH:
	case XE_GUC_LOAD_STATUS_DPC_ERROR:
	case XE_GUC_LOAD_STATUS_EXCEPTION:
	case XE_GUC_LOAD_STATUS_INIT_DATA_INVALID:
	case XE_GUC_LOAD_STATUS_MPU_DATA_INVALID:
	case XE_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID:
	case XE_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR:
	case XE_GUC_LOAD_STATUS_INVALID_FTR_FLAG:
		return -1;
	}

	switch (bootrom) {
	case XE_BOOTROM_STATUS_NO_KEY_FOUND:
	case XE_BOOTROM_STATUS_RSA_FAILED:
	case XE_BOOTROM_STATUS_PAVPC_FAILED:
	case XE_BOOTROM_STATUS_WOPCM_FAILED:
	case XE_BOOTROM_STATUS_LOADLOC_FAILED:
	case XE_BOOTROM_STATUS_JUMP_FAILED:
	case XE_BOOTROM_STATUS_RC6CTXCONFIG_FAILED:
	case XE_BOOTROM_STATUS_MPUMAP_INCORRECT:
	case XE_BOOTROM_STATUS_EXCEPTION:
	case XE_BOOTROM_STATUS_PROD_KEY_CHECK_FAILURE:
		return -1;
	}

	if (++*tries >= 100) {
		struct xe_guc_pc *guc_pc = &gt->uc.guc.pc;

		*tries = 0;
		xe_gt_dbg(gt, "GuC load still in progress, freq = %dMHz (req %dMHz), status = 0x%08X [0x%02X/%02X]\n",
			  xe_guc_pc_get_act_freq(guc_pc),
			  xe_guc_pc_get_cur_freq_fw(guc_pc),
			  *status, ukernel, bootrom);
	}

	return 0;
}

static int guc_wait_ucode(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_guc_pc *guc_pc = &gt->uc.guc.pc;
	u32 before_freq, act_freq, cur_freq;
	u32 status = 0, tries = 0;
	int load_result, ret;
	ktime_t before;
	u64 delta_ms;

	before_freq = xe_guc_pc_get_act_freq(guc_pc);
	before = ktime_get();

	ret = poll_timeout_us(load_result = guc_load_done(gt, &status, &tries), load_result,
			      10 * USEC_PER_MSEC,
			      GUC_LOAD_TIMEOUT_SEC * USEC_PER_SEC, false);

	delta_ms = ktime_to_ms(ktime_sub(ktime_get(), before));
	act_freq = xe_guc_pc_get_act_freq(guc_pc);
	cur_freq = xe_guc_pc_get_cur_freq_fw(guc_pc);

	if (ret || load_result <= 0) {
		xe_gt_err(gt, "load failed: status = 0x%08X, time = %lldms, freq = %dMHz (req %dMHz)\n",
			  status, delta_ms, xe_guc_pc_get_act_freq(guc_pc),
			  xe_guc_pc_get_cur_freq_fw(guc_pc));
		print_load_status_err(gt, status);

		return -EPROTO;
	}

	if (delta_ms > GUC_LOAD_TIME_WARN_MSEC) {
		xe_gt_warn(gt, "GuC load: excessive init time: %lldms! [status = 0x%08X]\n",
			   delta_ms, status);
		xe_gt_warn(gt, "GuC load: excessive init time: [freq = %dMHz (req = %dMHz), before = %dMHz, perf_limit_reasons = 0x%08X]\n",
			   act_freq, cur_freq, before_freq,
			   xe_gt_throttle_get_limit_reasons(gt));
	} else {
		xe_gt_dbg(gt, "GuC load: init took %lldms, freq = %dMHz (req = %dMHz), before = %dMHz, status = 0x%08X\n",
			  delta_ms, act_freq, cur_freq, before_freq, status);
	}

	return 0;
}
ALLOW_ERROR_INJECTION(guc_wait_ucode, ERRNO);

static int __xe_guc_upload(struct xe_guc *guc)
{
	int ret;

	/* Raise GT freq to speed up HuC/GuC load */
	xe_guc_pc_raise_unslice(&guc->pc);

	guc_write_params(guc);
	guc_prepare_xfer(guc);

	/*
	 * Note that GuC needs the CSS header plus uKernel code to be copied
	 * by the DMA engine in one operation, whereas the RSA signature is
	 * loaded separately, either by copying it to the UOS_RSA_SCRATCH
	 * register (if key size <= 256) or through a ggtt-pinned vma (if key
	 * size > 256). The RSA size and therefore the way we provide it to the
	 * HW is fixed for each platform and hard-coded in the bootrom.
	 */
	ret = guc_xfer_rsa(guc);
	if (ret)
		goto out;
	/*
	 * Current uCode expects the code to be loaded at 8k; locations below
	 * this are used for the stack.
	 */
	ret = xe_uc_fw_upload(&guc->fw, 0x2000, UOS_MOVE);
	if (ret)
		goto out;

	/* Wait for authentication */
	ret = guc_wait_ucode(guc);
	if (ret)
		goto out;

	xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_RUNNING);
	return 0;

out:
	xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_LOAD_FAIL);
	return ret;
}

static int vf_guc_min_load_for_hwconfig(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	int ret;

	ret = xe_guc_hwconfig_init(guc);
	if (ret)
		return ret;

	ret = xe_guc_enable_communication(guc);
	if (ret)
		return ret;

	ret = xe_gt_sriov_vf_connect(gt);
	if (ret)
		goto err_out;

	ret = xe_gt_sriov_vf_query_runtime(gt);
	if (ret)
		goto err_out;

	return 0;

err_out:
	xe_guc_sanitize(guc);
	return ret;
}

/**
 * xe_guc_min_load_for_hwconfig - load minimal GuC and read hwconfig table
 * @guc: The GuC object
 *
 * This function uploads a minimal GuC that does not support submissions but
 * in a state where the hwconfig table can be read. Next, it reads and parses
 * the hwconfig table so it can be used for subsequent steps in the driver load.
 * Lastly, it enables CT communication (XXX: this is needed for PFs/VFs only).
 *
 * Return: 0 on success, negative error code on error.
 */
int xe_guc_min_load_for_hwconfig(struct xe_guc *guc)
{
	int ret;

	if (IS_SRIOV_VF(guc_to_xe(guc)))
		return vf_guc_min_load_for_hwconfig(guc);

	xe_guc_ads_populate_minimal(&guc->ads);

	xe_guc_pc_init_early(&guc->pc);

	ret = __xe_guc_upload(guc);
	if (ret)
		return ret;

	ret = xe_guc_hwconfig_init(guc);
	if (ret)
		return ret;

	ret = xe_guc_enable_communication(guc);
	if (ret)
		return ret;

	return 0;
}

int xe_guc_upload(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);

	xe_guc_ads_populate(&guc->ads);

	if (xe_guc_using_main_gamctrl_queues(guc))
		xe_mmio_write32(&gt->mmio, MAIN_GAMCTRL_MODE, MAIN_GAMCTRL_QUEUE_SELECT);

	return __xe_guc_upload(guc);
}

static void guc_handle_mmio_msg(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	u32 msg;

	if (IS_SRIOV_VF(guc_to_xe(guc)))
		return;

	xe_force_wake_assert_held(gt_to_fw(gt), XE_FW_GT);

	msg = xe_mmio_read32(&gt->mmio, SOFT_SCRATCH(15));
	msg &= XE_GUC_RECV_MSG_EXCEPTION |
		XE_GUC_RECV_MSG_CRASH_DUMP_POSTED;
	xe_mmio_write32(&gt->mmio, SOFT_SCRATCH(15), 0);

	if (msg & XE_GUC_RECV_MSG_CRASH_DUMP_POSTED)
		xe_gt_err(gt, "Received early GuC crash dump notification!\n");

	if (msg & XE_GUC_RECV_MSG_EXCEPTION)
		xe_gt_err(gt, "Received early GuC exception notification!\n");
}

static void guc_enable_irq(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	u32 events = xe_gt_is_media_type(gt) ?
		REG_FIELD_PREP(ENGINE0_MASK, GUC_INTR_GUC2HOST)  :
		REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST);

	/* Primary GuC and media GuC share a single enable bit */
	xe_mmio_write32(&gt->mmio, GUC_SG_INTR_ENABLE,
			REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST));

	/*
	 * There are separate mask bits for primary and media GuCs, so use
	 * a RMW operation to avoid clobbering the other GuC's setting.
	 */
	xe_mmio_rmw32(&gt->mmio, GUC_SG_INTR_MASK, events, 0);
}

int xe_guc_enable_communication(struct xe_guc *guc)
{
	struct xe_device *xe = guc_to_xe(guc);
	int err;

	if (IS_SRIOV_VF(xe) && xe_device_has_memirq(xe)) {
		struct xe_gt *gt = guc_to_gt(guc);
		struct xe_tile *tile = gt_to_tile(gt);

		err = xe_memirq_init_guc(&tile->memirq, guc);
		if (err)
			return err;
	} else {
		guc_enable_irq(guc);
	}

	err = xe_guc_ct_enable(&guc->ct);
	if (err)
		return err;

	guc_handle_mmio_msg(guc);

	return 0;
}

/**
 * xe_guc_softreset() - Soft reset GuC
 * @guc: The GuC object
 *
 * Send soft reset command to GuC through mmio send.
 *
 * Return: 0 if success, otherwise error code
 */
int xe_guc_softreset(struct xe_guc *guc)
{
	u32 action[] = {
		XE_GUC_ACTION_CLIENT_SOFT_RESET,
	};
	int ret;

	if (!xe_uc_fw_is_running(&guc->fw))
		return 0;

	ret = xe_guc_mmio_send(guc, action, ARRAY_SIZE(action));
	if (ret)
		return ret;

	return 0;
}

int xe_guc_suspend(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	int ret;

	ret = xe_guc_softreset(guc);
	if (ret) {
		xe_gt_err(gt, "GuC suspend failed: %pe\n", ERR_PTR(ret));
		return ret;
	}

	xe_guc_sanitize(guc);
	return 0;
}

void xe_guc_notify(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	const u32 default_notify_data = 0;

	/*
	 * Both GUC_HOST_INTERRUPT and MED_GUC_HOST_INTERRUPT can pass
	 * additional payload data to the GuC but this capability is not
	 * used by the firmware yet. Use default value in the meantime.
	 */
	xe_mmio_write32(&gt->mmio, guc->notify_reg, default_notify_data);
}

int xe_guc_auth_huc(struct xe_guc *guc, u32 rsa_addr)
{
	u32 action[] = {
		XE_GUC_ACTION_AUTHENTICATE_HUC,
		rsa_addr
	};

	return xe_guc_ct_send_block(&guc->ct, action, ARRAY_SIZE(action));
}

#define MAX_RETRIES_ON_FLR	2
#define MIN_SLEEP_MS_ON_FLR	256

int xe_guc_mmio_send_recv(struct xe_guc *guc, const u32 *request,
			  u32 len, u32 *response_buf)
{
	struct xe_device *xe = guc_to_xe(guc);
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_mmio *mmio = &gt->mmio;
	struct xe_reg reply_reg = xe_gt_is_media_type(gt) ?
		MED_VF_SW_FLAG(0) : VF_SW_FLAG(0);
	const u32 LAST_INDEX = VF_SW_FLAG_COUNT - 1;
	unsigned int sleep_period_ms = 1;
	unsigned int lost = 0;
	u32 header;
	int ret;
	int i;

	BUILD_BUG_ON(VF_SW_FLAG_COUNT != MED_VF_SW_FLAG_COUNT);

	xe_assert(xe, len);
	xe_assert(xe, len <= VF_SW_FLAG_COUNT);
	xe_assert(xe, len <= MED_VF_SW_FLAG_COUNT);
	xe_assert(xe, FIELD_GET(GUC_HXG_MSG_0_ORIGIN, request[0]) ==
		  GUC_HXG_ORIGIN_HOST);
	xe_assert(xe, FIELD_GET(GUC_HXG_MSG_0_TYPE, request[0]) ==
		  GUC_HXG_TYPE_REQUEST);

retry:
	/* Not in critical data-path, just do if else for GT type */
	if (xe_gt_is_media_type(gt)) {
		for (i = 0; i < len; ++i)
			xe_mmio_write32(mmio, MED_VF_SW_FLAG(i),
					request[i]);
		xe_mmio_read32(mmio, MED_VF_SW_FLAG(LAST_INDEX));
	} else {
		for (i = 0; i < len; ++i)
			xe_mmio_write32(mmio, VF_SW_FLAG(i),
					request[i]);
		xe_mmio_read32(mmio, VF_SW_FLAG(LAST_INDEX));
	}

	xe_guc_notify(guc);

	ret = xe_mmio_wait32(mmio, reply_reg, GUC_HXG_MSG_0_ORIGIN,
			     FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_GUC),
			     50000, &header, false);
	if (ret) {
		/* scratch registers might be cleared during FLR, try once more */
		if (!header) {
			if (++lost > MAX_RETRIES_ON_FLR) {
				xe_gt_err(gt, "GuC mmio request %#x: lost, too many retries %u\n",
					  request[0], lost);
				return -ENOLINK;
			}
			xe_gt_dbg(gt, "GuC mmio request %#x: lost, trying again\n", request[0]);
			xe_sleep_relaxed_ms(MIN_SLEEP_MS_ON_FLR);
			goto retry;
		}
timeout:
		xe_gt_err(gt, "GuC mmio request %#x: no reply %#x\n",
			  request[0], header);
		return ret;
	}

	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) ==
	    GUC_HXG_TYPE_NO_RESPONSE_BUSY) {
		/*
		 * Once we got a BUSY reply we must wait again for the final
		 * response but this time we can't use ORIGIN mask anymore.
		 * To spot a right change in the reply, we take advantage that
		 * response SUCCESS and FAILURE differ only by the single bit
		 * and all other bits are set and can be used as a new mask.
		 */
		u32 resp_bits = GUC_HXG_TYPE_RESPONSE_SUCCESS & GUC_HXG_TYPE_RESPONSE_FAILURE;
		u32 resp_mask = FIELD_PREP(GUC_HXG_MSG_0_TYPE, resp_bits);

		BUILD_BUG_ON(FIELD_MAX(GUC_HXG_MSG_0_TYPE) != GUC_HXG_TYPE_RESPONSE_SUCCESS);
		BUILD_BUG_ON((GUC_HXG_TYPE_RESPONSE_SUCCESS ^ GUC_HXG_TYPE_RESPONSE_FAILURE) != 1);

		ret = xe_mmio_wait32(mmio, reply_reg, resp_mask, resp_mask,
				     2000000, &header, false);

		if (unlikely(FIELD_GET(GUC_HXG_MSG_0_ORIGIN, header) !=
			     GUC_HXG_ORIGIN_GUC))
			goto proto;
		if (unlikely(ret)) {
			if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) !=
			    GUC_HXG_TYPE_NO_RESPONSE_BUSY)
				goto proto;
			goto timeout;
		}
	}

	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) ==
	    GUC_HXG_TYPE_NO_RESPONSE_RETRY) {
		u32 reason = FIELD_GET(GUC_HXG_RETRY_MSG_0_REASON, header);

		xe_gt_dbg(gt, "GuC mmio request %#x: retrying, reason %#x\n",
			  request[0], reason);

		xe_sleep_exponential_ms(&sleep_period_ms, 256);
		goto retry;
	}

	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) ==
	    GUC_HXG_TYPE_RESPONSE_FAILURE) {
		u32 hint = FIELD_GET(GUC_HXG_FAILURE_MSG_0_HINT, header);
		u32 error = FIELD_GET(GUC_HXG_FAILURE_MSG_0_ERROR, header);

		if (unlikely(error == XE_GUC_RESPONSE_VF_MIGRATED)) {
			xe_gt_dbg(gt, "GuC mmio request %#x rejected due to MIGRATION (hint %#x)\n",
				  request[0], hint);
			return -EREMCHG;
		}

		xe_gt_err(gt, "GuC mmio request %#x: failure %#x hint %#x\n",
			  request[0], error, hint);
		return -ENXIO;
	}

	if (FIELD_GET(GUC_HXG_MSG_0_TYPE, header) !=
	    GUC_HXG_TYPE_RESPONSE_SUCCESS) {
proto:
		xe_gt_err(gt, "GuC mmio request %#x: unexpected reply %#x\n",
			  request[0], header);
		return -EPROTO;
	}

	/* Just copy entire possible message response */
	if (response_buf) {
		response_buf[0] = header;

		for (i = 1; i < VF_SW_FLAG_COUNT; i++) {
			reply_reg.addr += sizeof(u32);
			response_buf[i] = xe_mmio_read32(mmio, reply_reg);
		}
	}

	/* Use data from the GuC response as our return value */
	return FIELD_GET(GUC_HXG_RESPONSE_MSG_0_DATA0, header);
}
ALLOW_ERROR_INJECTION(xe_guc_mmio_send_recv, ERRNO);

int xe_guc_mmio_send(struct xe_guc *guc, const u32 *request, u32 len)
{
	return xe_guc_mmio_send_recv(guc, request, len, NULL);
}

static int guc_self_cfg(struct xe_guc *guc, u16 key, u16 len, u64 val)
{
	struct xe_device *xe = guc_to_xe(guc);
	u32 request[HOST2GUC_SELF_CFG_REQUEST_MSG_LEN] = {
		FIELD_PREP(GUC_HXG_MSG_0_ORIGIN, GUC_HXG_ORIGIN_HOST) |
		FIELD_PREP(GUC_HXG_MSG_0_TYPE, GUC_HXG_TYPE_REQUEST) |
		FIELD_PREP(GUC_HXG_REQUEST_MSG_0_ACTION,
			   GUC_ACTION_HOST2GUC_SELF_CFG),
		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_KEY, key) |
		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_1_KLV_LEN, len),
		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_2_VALUE32,
			   lower_32_bits(val)),
		FIELD_PREP(HOST2GUC_SELF_CFG_REQUEST_MSG_3_VALUE64,
			   upper_32_bits(val)),
	};
	int ret;

	xe_assert(xe, len <= 2);
	xe_assert(xe, len != 1 || !upper_32_bits(val));

	/* Self config must go over MMIO */
	ret = xe_guc_mmio_send(guc, request, ARRAY_SIZE(request));

	if (unlikely(ret < 0))
		return ret;
	if (unlikely(ret > 1))
		return -EPROTO;
	if (unlikely(!ret))
		return -ENOKEY;

	return 0;
}

int xe_guc_self_cfg32(struct xe_guc *guc, u16 key, u32 val)
{
	return guc_self_cfg(guc, key, 1, val);
}

int xe_guc_self_cfg64(struct xe_guc *guc, u16 key, u64 val)
{
	return guc_self_cfg(guc, key, 2, val);
}

static void xe_guc_sw_0_irq_handler(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);

	if (IS_SRIOV_VF(gt_to_xe(gt)))
		xe_gt_sriov_vf_migrated_event_handler(gt);
}

void xe_guc_irq_handler(struct xe_guc *guc, const u16 iir)
{
	if (iir & GUC_INTR_GUC2HOST)
		xe_guc_ct_irq_handler(&guc->ct);

	if (iir & GUC_INTR_SW_INT_0)
		xe_guc_sw_0_irq_handler(guc);
}

void xe_guc_sanitize(struct xe_guc *guc)
{
	xe_uc_fw_sanitize(&guc->fw);
	xe_guc_ct_disable(&guc->ct);
	xe_guc_submit_disable(guc);
}

int xe_guc_reset_prepare(struct xe_guc *guc)
{
	return xe_guc_submit_reset_prepare(guc);
}

void xe_guc_reset_wait(struct xe_guc *guc)
{
	xe_guc_submit_reset_wait(guc);
}

void xe_guc_stop_prepare(struct xe_guc *guc)
{
	if (!IS_SRIOV_VF(guc_to_xe(guc)))
		xe_guc_pc_stop(&guc->pc);
}

void xe_guc_stop(struct xe_guc *guc)
{
	xe_guc_ct_stop(&guc->ct);

	xe_guc_submit_stop(guc);
}

int xe_guc_start(struct xe_guc *guc)
{
	return xe_guc_submit_start(guc);
}

/**
 * xe_guc_runtime_suspend() - GuC runtime suspend
 * @guc: The GuC object
 *
 * Stop further runs of submission tasks on given GuC and runtime suspend
 * GuC CT.
 */
void xe_guc_runtime_suspend(struct xe_guc *guc)
{
	xe_guc_submit_pause(guc);
	xe_guc_submit_disable(guc);
	xe_guc_ct_runtime_suspend(&guc->ct);
}

/**
 * xe_guc_runtime_resume() - GuC runtime resume
 * @guc: The GuC object
 *
 * Runtime resume GuC CT and allow further runs of submission tasks on
 * given GuC.
 */
void xe_guc_runtime_resume(struct xe_guc *guc)
{
	/*
	 * Runtime PM flows are not applicable for VFs, so it's safe to
	 * directly enable IRQ.
	 */
	guc_enable_irq(guc);

	xe_guc_ct_runtime_resume(&guc->ct);
	xe_guc_submit_enable(guc);
	xe_guc_submit_unpause(guc);
}

int xe_guc_print_info(struct xe_guc *guc, struct drm_printer *p)
{
	struct xe_gt *gt = guc_to_gt(guc);
	u32 status;
	int i;

	xe_uc_fw_print(&guc->fw, p);

	if (!IS_SRIOV_VF(gt_to_xe(gt))) {
		CLASS(xe_force_wake, fw_ref)(gt_to_fw(gt), XE_FW_GT);
		if (!fw_ref.domains)
			return -EIO;

		status = xe_mmio_read32(&gt->mmio, GUC_STATUS);

		drm_printf(p, "\nGuC status 0x%08x:\n", status);
		drm_printf(p, "\tBootrom status = 0x%x\n",
			   REG_FIELD_GET(GS_BOOTROM_MASK, status));
		drm_printf(p, "\tuKernel status = 0x%x\n",
			   REG_FIELD_GET(GS_UKERNEL_MASK, status));
		drm_printf(p, "\tMIA Core status = 0x%x\n",
			   REG_FIELD_GET(GS_MIA_MASK, status));
		drm_printf(p, "\tLog level = %d\n",
			   xe_guc_log_get_level(&guc->log));

		drm_puts(p, "\nScratch registers:\n");
		for (i = 0; i < SOFT_SCRATCH_COUNT; i++) {
			drm_printf(p, "\t%2d: \t0x%x\n",
				   i, xe_mmio_read32(&gt->mmio, SOFT_SCRATCH(i)));
		}
	}

	drm_puts(p, "\n");
	xe_guc_ct_print(&guc->ct, p, false);

	drm_puts(p, "\n");
	xe_guc_submit_print(guc, p);

	return 0;
}

/**
 * xe_guc_declare_wedged() - Declare GuC wedged
 * @guc: the GuC object
 *
 * Wedge the GuC which stops all submission, saves desired debug state, and
 * cleans up anything which could timeout.
 */
void xe_guc_declare_wedged(struct xe_guc *guc)
{
	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);

	xe_guc_reset_prepare(guc);
	xe_guc_ct_stop(&guc->ct);
	xe_guc_submit_wedge(guc);
}

/**
 * xe_guc_using_main_gamctrl_queues() - Detect which reporting queues to use.
 * @guc: The GuC object
 *
 * For Xe3p and beyond, we want to program the hardware to use the
 * "Main GAMCTRL queue" rather than the legacy queue before we upload
 * the GuC firmware.  This will allow the GuC to use a new set of
 * registers for pagefault handling and avoid some unnecessary
 * complications with MCR register range handling.
 *
 * Return: true if can use new main gamctrl queues.
 */
bool xe_guc_using_main_gamctrl_queues(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);

	/*
	 * For Xe3p media gt (35), the GuC and the CS subunits may be still Xe3
	 * that lacks the Main GAMCTRL support. Reserved bits from the GMD_ID
	 * inform the IP version of the subunits.
	 */
	if (xe_gt_is_media_type(gt) && MEDIA_VER(gt_to_xe(gt)) == 35) {
		u32 val = xe_mmio_read32(&gt->mmio, GMD_ID);
		u32 subip = REG_FIELD_GET(GMD_ID_SUBIP_FLAG_MASK, val);

		if (!subip)
			return true;

		xe_gt_WARN(gt, subip != 1,
			   "GMD_ID has unknown value in the SUBIP_FLAG field - 0x%x\n",
			   subip);

		return false;
	}

	return GT_VER(gt) >= 35;
}

bool xe_guc_has_paging_engine(struct xe_guc *guc)
{
	struct xe_gt *gt = guc_to_gt(guc);
	struct xe_device *xe = gt_to_xe(gt);

	/*
	 * On newer platforms the GuC now has a dedicated engine class for the
	 * special PAGING engine, which is the driver reserved BCS engine used
	 * for KMD paging/binding operations. GuC requires KMD to refer to this
	 * using the special PAGING engine class. Note that there is no new hw
	 * engine here, this is purely a sw view in the GuC itself, which we
	 * need to respect.
	 */

	if (IS_SRIOV_VF(xe))
		return xe_gt_sriov_vf_paging_engines(gt);

	return xe->info.platform >= XE_NOVALAKE_S &&
	       GUC_FIRMWARE_VER_AT_LEAST(guc, 70, 69, 0);
}

/**
 * xe_hwe_guc_logical_instance - Get the GuC-aligned logical instance of a
 * hardware engine.
 * @hwe: Hardware engine.
 *
 * For GuC backend usage, we should no longer use the raw logical instance
 * directly. This helper must be used to retrieve the logical instance of the
 * hardware engine, taking care of any necessary adjustments (such as the GuC
 * PAGING engine mapping). This is assumed to be used in conjunction with the
 * GuC engine class.
 *
 * Return: Logical instance, taking into account for stuff like GuC PAGING
 * engine mapping.
 */
u16 xe_hwe_guc_logical_instance(struct xe_hw_engine *hwe)
{
	struct xe_gt *gt = hwe->gt;

	if (xe_guc_has_paging_engine(&hwe->gt->uc.guc) &&
	    xe_gt_is_usm_hwe(gt, hwe)) {
		int shift = gt->usm.paging_hwe0->logical_instance;

		xe_gt_assert(gt, shift <= hwe->logical_instance);

		/* GUC_PAGING_CLASS:guc_logical_instance */
		return hwe->logical_instance - shift;
	}

	return hwe->logical_instance;
}

#if IS_ENABLED(CONFIG_DRM_XE_KUNIT_TEST)
#include "tests/xe_guc_g2g_test.c"
#endif