drm/xe: Add xe_guc_pagefault layer

Add xe_guc_pagefault layer (producer) which parses G2H fault messages
messages into struct xe_pagefault, forwards them to the page fault layer
(consumer) for servicing, and provides a vfunc to acknowledge faults to
the GuC upon completion. Replace the old (and incorrect) GT page fault
layer with this new layer throughout the driver.

As part of this change, the ACC handling code has been removed, as it is
dead code that is currently unused.

v2:
 - Include engine instance (Stuart)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Tested-by: Francois Dugast <francois.dugast@intel.com>
Link: https://patch.msgid.link/20251031165416.2871503-7-matthew.brost@intel.com

7 files changed, 113 insertions, 15 deletions

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index cdf9b08b809e..8aa85c93b3d6 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -58,7 +58,6 @@ xe-y += xe_bb.o \
 	xe_gt_freq.o \
 	xe_gt_idle.o \
 	xe_gt_mcr.o \
-	xe_gt_pagefault.o \
 	xe_gt_sysfs.o \
 	xe_gt_throttle.o \
 	xe_gt_topology.o \
@@ -73,6 +72,7 @@ xe-y += xe_bb.o \
 	xe_guc_id_mgr.o \
 	xe_guc_klv_helpers.o \
 	xe_guc_log.o \
+	xe_guc_pagefault.o \
 	xe_guc_pc.o \
 	xe_guc_submit.o \
 	xe_guc_tlb_inval.o \
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index f50bf98f44c9..6d479948bf21 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -32,7 +32,6 @@
 #include "xe_gt_freq.h"
 #include "xe_gt_idle.h"
 #include "xe_gt_mcr.h"
-#include "xe_gt_pagefault.h"
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_pf.h"
 #include "xe_gt_sriov_vf.h"
@@ -645,10 +644,6 @@ int xe_gt_init(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	err = xe_gt_pagefault_init(gt);
-	if (err)
-		return err;
-
 	err = xe_gt_idle_init(&gt->gtidle);
 	if (err)
 		return err;
@@ -855,7 +850,6 @@ static void gt_reset_worker(struct work_struct *w)
 	xe_uc_gucrc_disable(&gt->uc);
 	xe_uc_stop_prepare(&gt->uc);
 	xe_pagefault_reset(gt_to_xe(gt), gt);
-	xe_gt_pagefault_reset(gt);
 
 	xe_uc_stop(&gt->uc);
 
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 536433b061fc..2697d711adb2 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -21,12 +21,12 @@
 #include "xe_devcoredump.h"
 #include "xe_device.h"
 #include "xe_gt.h"
-#include "xe_gt_pagefault.h"
 #include "xe_gt_printk.h"
 #include "xe_gt_sriov_pf_control.h"
 #include "xe_gt_sriov_pf_monitor.h"
 #include "xe_guc.h"
 #include "xe_guc_log.h"
+#include "xe_guc_pagefault.h"
 #include "xe_guc_relay.h"
 #include "xe_guc_submit.h"
 #include "xe_guc_tlb_inval.h"
@@ -1548,10 +1548,6 @@ static int process_g2h_msg(struct xe_guc_ct *ct, u32 *msg, u32 len)
 	case XE_GUC_ACTION_TLB_INVALIDATION_DONE:
 		ret = xe_guc_tlb_inval_done_handler(guc, payload, adj_len);
 		break;
-	case XE_GUC_ACTION_ACCESS_COUNTER_NOTIFY:
-		ret = xe_guc_access_counter_notify_handler(guc, payload,
-							   adj_len);
-		break;
 	case XE_GUC_ACTION_GUC2PF_RELAY_FROM_VF:
 		ret = xe_guc_relay_process_guc2pf(&guc->relay, hxg, hxg_len);
 		break;
diff --git a/drivers/gpu/drm/xe/xe_guc_pagefault.c b/drivers/gpu/drm/xe/xe_guc_pagefault.c
new file mode 100644
index 000000000000..719a18187a31
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_pagefault.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#include "abi/guc_actions_abi.h"
+#include "xe_guc.h"
+#include "xe_guc_ct.h"
+#include "xe_guc_pagefault.h"
+#include "xe_pagefault.h"
+
+static void guc_ack_fault(struct xe_pagefault *pf, int err)
+{
+	u32 vfid = FIELD_GET(PFD_VFID, pf->producer.msg[2]);
+	u32 engine_instance = FIELD_GET(PFD_ENG_INSTANCE, pf->producer.msg[0]);
+	u32 engine_class = FIELD_GET(PFD_ENG_CLASS, pf->producer.msg[0]);
+	u32 pdata = FIELD_GET(PFD_PDATA_LO, pf->producer.msg[0]) |
+		(FIELD_GET(PFD_PDATA_HI, pf->producer.msg[1]) <<
+		 PFD_PDATA_HI_SHIFT);
+	u32 action[] = {
+		XE_GUC_ACTION_PAGE_FAULT_RES_DESC,
+
+		FIELD_PREP(PFR_VALID, 1) |
+		FIELD_PREP(PFR_SUCCESS, !!err) |
+		FIELD_PREP(PFR_REPLY, PFR_ACCESS) |
+		FIELD_PREP(PFR_DESC_TYPE, FAULT_RESPONSE_DESC) |
+		FIELD_PREP(PFR_ASID, pf->consumer.asid),
+
+		FIELD_PREP(PFR_VFID, vfid) |
+		FIELD_PREP(PFR_ENG_INSTANCE, engine_instance) |
+		FIELD_PREP(PFR_ENG_CLASS, engine_class) |
+		FIELD_PREP(PFR_PDATA, pdata),
+	};
+	struct xe_guc *guc = pf->producer.private;
+
+	xe_guc_ct_send(&guc->ct, action, ARRAY_SIZE(action), 0, 0);
+}
+
+static const struct xe_pagefault_ops guc_pagefault_ops = {
+	.ack_fault = guc_ack_fault,
+};
+
+/**
+ * xe_guc_pagefault_handler() - G2H page fault handler
+ * @guc: GuC object
+ * @msg: G2H message
+ * @len: Length of G2H message
+ *
+ * Parse GuC to host (G2H) message into a struct xe_pagefault and forward onto
+ * the Xe page fault layer.
+ *
+ * Return: 0 on success, errno on failure
+ */
+int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len)
+{
+	struct xe_pagefault pf;
+	int i;
+
+#define GUC_PF_MSG_LEN_DW	\
+	(sizeof(struct xe_guc_pagefault_desc) / sizeof(u32))
+
+	BUILD_BUG_ON(GUC_PF_MSG_LEN_DW > XE_PAGEFAULT_PRODUCER_MSG_LEN_DW);
+
+	if (len != GUC_PF_MSG_LEN_DW)
+		return -EPROTO;
+
+	pf.gt = guc_to_gt(guc);
+
+	/*
+	 * XXX: These values happen to match the enum in xe_pagefault_types.h.
+	 * If that changes, we’ll need to remap them here.
+	 */
+	pf.consumer.page_addr = ((u64)FIELD_GET(PFD_VIRTUAL_ADDR_HI, msg[3])
+				      << PFD_VIRTUAL_ADDR_HI_SHIFT) |
+		(FIELD_GET(PFD_VIRTUAL_ADDR_LO, msg[2]) <<
+		 PFD_VIRTUAL_ADDR_LO_SHIFT);
+	pf.consumer.asid = FIELD_GET(PFD_ASID, msg[1]);
+	pf.consumer.access_type = FIELD_GET(PFD_ACCESS_TYPE, msg[2]);
+	pf.consumer.fault_type = FIELD_GET(PFD_FAULT_TYPE, msg[2]);
+	if (FIELD_GET(XE2_PFD_TRVA_FAULT, msg[0]))
+		pf.consumer.fault_level = XE_PAGEFAULT_LEVEL_NACK;
+	else
+		pf.consumer.fault_level = FIELD_GET(PFD_FAULT_LEVEL, msg[0]);
+	pf.consumer.engine_class = FIELD_GET(PFD_ENG_CLASS, msg[0]);
+	pf.consumer.engine_instance = FIELD_GET(PFD_ENG_INSTANCE, msg[0]);
+
+	pf.producer.private = guc;
+	pf.producer.ops = &guc_pagefault_ops;
+	for (i = 0; i < GUC_PF_MSG_LEN_DW; ++i)
+		pf.producer.msg[i] = msg[i];
+
+#undef GUC_PF_MSG_LEN_DW
+
+	return xe_pagefault_handler(guc_to_xe(guc), &pf);
+}
diff --git a/drivers/gpu/drm/xe/xe_guc_pagefault.h b/drivers/gpu/drm/xe/xe_guc_pagefault.h
new file mode 100644
index 000000000000..3bd599e7207c
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_guc_pagefault.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_GUC_PAGEFAULT_H_
+#define _XE_GUC_PAGEFAULT_H_
+
+#include <linux/types.h>
+
+struct xe_guc;
+
+int xe_guc_pagefault_handler(struct xe_guc *guc, u32 *msg, u32 len);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 13af589715a7..55c5a0eb82e1 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -104,8 +104,7 @@ xe_svm_garbage_collector_add_range(struct xe_vm *vm, struct xe_svm_range *range,
 			      &vm->svm.garbage_collector.range_list);
 	spin_unlock(&vm->svm.garbage_collector.lock);
 
-	queue_work(xe_device_get_root_tile(xe)->primary_gt->usm.pf_wq,
-		   &vm->svm.garbage_collector.work);
+	queue_work(xe->usm.pf_wq, &vm->svm.garbage_collector.work);
 }
 
 static void xe_svm_tlb_inval_count_stats_incr(struct xe_gt *gt)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 2b5d25f4dd53..ce2f2c063eba 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -27,7 +27,6 @@
 #include "xe_device.h"
 #include "xe_drm_client.h"
 #include "xe_exec_queue.h"
-#include "xe_gt_pagefault.h"
 #include "xe_migrate.h"
 #include "xe_pat.h"
 #include "xe_pm.h"