Merge remote-tracking branch 'kernel/drm-xe-next' into drm-tip

# Conflicts:
#	drivers/gpu/drm/xe/xe_rtp.c

drivers/gpu/drm/xe/instructions/xe_alu_commands.h

+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2025 Intel Corporation
+ */
+
+#ifndef _XE_ALU_COMMANDS_H_
+#define _XE_ALU_COMMANDS_H_
+
+#include "instructions/xe_instr_defs.h"
+
+/* Instruction Opcodes */
+#define CS_ALU_OPCODE_NOOP			0x000
+#define CS_ALU_OPCODE_FENCE_RD			0x001
+#define CS_ALU_OPCODE_FENCE_WR			0x002
+#define CS_ALU_OPCODE_LOAD			0x080
+#define CS_ALU_OPCODE_LOADINV			0x480
+#define CS_ALU_OPCODE_LOAD0			0x081
+#define CS_ALU_OPCODE_LOAD1			0x481
+#define CS_ALU_OPCODE_LOADIND			0x082
+#define CS_ALU_OPCODE_ADD			0x100
+#define CS_ALU_OPCODE_SUB			0x101
+#define CS_ALU_OPCODE_AND			0x102
+#define CS_ALU_OPCODE_OR			0x103
+#define CS_ALU_OPCODE_XOR			0x104
+#define CS_ALU_OPCODE_SHL			0x105
+#define CS_ALU_OPCODE_SHR			0x106
+#define CS_ALU_OPCODE_SAR			0x107
+#define CS_ALU_OPCODE_STORE			0x180
+#define CS_ALU_OPCODE_STOREINV			0x580
+#define CS_ALU_OPCODE_STOREIND			0x181
+
+/* Instruction Operands */
+#define CS_ALU_OPERAND_REG(n)			REG_FIELD_PREP(GENMASK(3, 0), (n))
+#define CS_ALU_OPERAND_REG0			0x0
+#define CS_ALU_OPERAND_REG1			0x1
+#define CS_ALU_OPERAND_REG2			0x2
+#define CS_ALU_OPERAND_REG3			0x3
+#define CS_ALU_OPERAND_REG4			0x4
+#define CS_ALU_OPERAND_REG5			0x5
+#define CS_ALU_OPERAND_REG6			0x6
+#define CS_ALU_OPERAND_REG7			0x7
+#define CS_ALU_OPERAND_REG8			0x8
+#define CS_ALU_OPERAND_REG9			0x9
+#define CS_ALU_OPERAND_REG10			0xa
+#define CS_ALU_OPERAND_REG11			0xb
+#define CS_ALU_OPERAND_REG12			0xc
+#define CS_ALU_OPERAND_REG13			0xd
+#define CS_ALU_OPERAND_REG14			0xe
+#define CS_ALU_OPERAND_REG15			0xf
+#define CS_ALU_OPERAND_SRCA			0x20
+#define CS_ALU_OPERAND_SRCB			0x21
+#define CS_ALU_OPERAND_ACCU			0x31
+#define CS_ALU_OPERAND_ZF			0x32
+#define CS_ALU_OPERAND_CF			0x33
+#define CS_ALU_OPERAND_NA			0 /* N/A operand */
+
+/* Command Streamer ALU Instructions */
+#define CS_ALU_INSTR(opcode, op1, op2)		(REG_FIELD_PREP(GENMASK(31, 20), (opcode)) | \
+						 REG_FIELD_PREP(GENMASK(19, 10), (op1)) | \
+						 REG_FIELD_PREP(GENMASK(9, 0), (op2)))
+
+#define __CS_ALU_INSTR(opcode, op1, op2)	CS_ALU_INSTR(CS_ALU_OPCODE_##opcode, \
+							     CS_ALU_OPERAND_##op1, \
+							     CS_ALU_OPERAND_##op2)
+
+#define CS_ALU_INSTR_NOOP			__CS_ALU_INSTR(NOOP, NA, NA)
+#define CS_ALU_INSTR_LOAD(op1, op2)		__CS_ALU_INSTR(LOAD, op1, op2)
+#define CS_ALU_INSTR_LOADINV(op1, op2)		__CS_ALU_INSTR(LOADINV, op1, op2)
+#define CS_ALU_INSTR_LOAD0(op1)			__CS_ALU_INSTR(LOAD0, op1, NA)
+#define CS_ALU_INSTR_LOAD1(op1)			__CS_ALU_INSTR(LOAD1, op1, NA)
+#define CS_ALU_INSTR_ADD			__CS_ALU_INSTR(ADD, NA, NA)
+#define CS_ALU_INSTR_SUB			__CS_ALU_INSTR(SUB, NA, NA)
+#define CS_ALU_INSTR_AND			__CS_ALU_INSTR(AND, NA, NA)
+#define CS_ALU_INSTR_OR				__CS_ALU_INSTR(OR, NA, NA)
+#define CS_ALU_INSTR_XOR			__CS_ALU_INSTR(XOR, NA, NA)
+#define CS_ALU_INSTR_STORE(op1, op2)		__CS_ALU_INSTR(STORE, op1, op2)
+#define CS_ALU_INSTR_STOREINV(op1, op2)		__CS_ALU_INSTR(STOREINV, op1, op2)
+
+#endif

drivers/gpu/drm/xe/instructions/xe_gfxpipe_commands.h

@@ -137,6 +137,7 @@
 #define CMD_3DSTATE_CLIP_MESH			GFXPIPE_3D_CMD(0x0, 0x81)
 #define CMD_3DSTATE_SBE_MESH			GFXPIPE_3D_CMD(0x0, 0x82)
 #define CMD_3DSTATE_CPSIZE_CONTROL_BUFFER	GFXPIPE_3D_CMD(0x0, 0x83)
+#define CMD_3DSTATE_COARSE_PIXEL		GFXPIPE_3D_CMD(0x0, 0x89)
 
 #define CMD_3DSTATE_DRAWING_RECTANGLE		GFXPIPE_3D_CMD(0x1, 0x0)
 #define CMD_3DSTATE_CHROMA_KEY			GFXPIPE_3D_CMD(0x1, 0x4)

drivers/gpu/drm/xe/instructions/xe_mi_commands.h

@@ -32,6 +32,7 @@
 #define MI_BATCH_BUFFER_END		__MI_INSTR(0xA)
 #define MI_TOPOLOGY_FILTER		__MI_INSTR(0xD)
 #define MI_FORCE_WAKEUP			__MI_INSTR(0x1D)
+#define MI_MATH(n)			(__MI_INSTR(0x1A) | XE_INSTR_NUM_DW((n) + 1))
 
 #define MI_STORE_DATA_IMM		__MI_INSTR(0x20)
 #define   MI_SDI_GGTT			REG_BIT(22)
@@ -61,6 +62,10 @@
 #define MI_LOAD_REGISTER_MEM		(__MI_INSTR(0x29) | XE_INSTR_NUM_DW(4))
 #define   MI_LRM_USE_GGTT		REG_BIT(22)
 
+#define MI_LOAD_REGISTER_REG		(__MI_INSTR(0x2a) | XE_INSTR_NUM_DW(3))
+#define   MI_LRR_DST_CS_MMIO		REG_BIT(19)
+#define   MI_LRR_SRC_CS_MMIO		REG_BIT(18)
+
 #define MI_COPY_MEM_MEM			(__MI_INSTR(0x2e) | XE_INSTR_NUM_DW(5))
 #define   MI_COPY_MEM_MEM_SRC_GGTT	REG_BIT(22)
 #define   MI_COPY_MEM_MEM_DST_GGTT	REG_BIT(21)

drivers/gpu/drm/xe/regs/xe_engine_regs.h

@@ -184,6 +184,10 @@
 #define   PREEMPT_GPGPU_LEVEL_MASK		PREEMPT_GPGPU_LEVEL(1, 1)
 #define   PREEMPT_3D_OBJECT_LEVEL		REG_BIT(0)
 
+#define CS_GPR_DATA(base, n)			XE_REG((base) + 0x600 + (n) * 4)
+#define CS_GPR_REG(base, n)			CS_GPR_DATA((base), (n) * 2)
+#define CS_GPR_REG_UDW(base, n)			CS_GPR_DATA((base), (n) * 2 + 1)
+
 #define VDBOX_CGCTL3F08(base)			XE_REG((base) + 0x3f08)
 #define   CG3DDISHRS_CLKGATE_DIS		REG_BIT(5)
 

drivers/gpu/drm/xe/xe_device.c

@@ -504,7 +504,15 @@ ALLOW_ERROR_INJECTION(xe_device_create, ERRNO); /* See xe_pci_probe() */
 
 static bool xe_driver_flr_disabled(struct xe_device *xe)
 {
-	return xe_mmio_read32(xe_root_tile_mmio(xe), GU_CNTL_PROTECTED) & DRIVERINT_FLR_DIS;
+	if (IS_SRIOV_VF(xe))
+		return true;
+
+	if (xe_mmio_read32(xe_root_tile_mmio(xe), GU_CNTL_PROTECTED) & DRIVERINT_FLR_DIS) {
+		drm_info(&xe->drm, "Driver-FLR disabled by BIOS\n");
+		return true;
+	}
+
+	return false;
 }
 
 /*
@@ -522,7 +530,7 @@ static bool xe_driver_flr_disabled(struct xe_device *xe)
  */
 static void __xe_driver_flr(struct xe_device *xe)
 {
-	const unsigned int flr_timeout = 3 * MICRO; /* specs recommend a 3s wait */
+	const unsigned int flr_timeout = 3 * USEC_PER_SEC; /* specs recommend a 3s wait */
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
 	int ret;
 
@@ -568,10 +576,8 @@ static void __xe_driver_flr(struct xe_device *xe)
 
 static void xe_driver_flr(struct xe_device *xe)
 {
-	if (xe_driver_flr_disabled(xe)) {
-		drm_info_once(&xe->drm, "BIOS Disabled Driver-FLR\n");
+	if (xe_driver_flr_disabled(xe))
 		return;
-	}
 
 	__xe_driver_flr(xe);
 }

drivers/gpu/drm/xe/xe_eu_stall.c

@@ -222,13 +222,7 @@ int xe_eu_stall_init(struct xe_gt *gt)
 		goto exit_free;
 	}
 
-	ret = devm_add_action_or_reset(xe->drm.dev, xe_eu_stall_fini, gt);
-	if (ret)
-		goto exit_destroy;
-
-	return 0;
-exit_destroy:
-	destroy_workqueue(gt->eu_stall->buf_ptr_poll_wq);
+	return devm_add_action_or_reset(xe->drm.dev, xe_eu_stall_fini, gt);
 exit_free:
 	mutex_destroy(&gt->eu_stall->stream_lock);
 	kfree(gt->eu_stall);

drivers/gpu/drm/xe/xe_force_wake.c

@@ -49,9 +49,6 @@ void xe_force_wake_init_gt(struct xe_gt *gt, struct xe_force_wake *fw)
 	fw->gt = gt;
 	spin_lock_init(&fw->lock);
 
-	/* Assuming gen11+ so assert this assumption is correct */
-	xe_gt_assert(gt, GRAPHICS_VER(gt_to_xe(gt)) >= 11);
-
 	if (xe->info.graphics_verx100 >= 1270) {
 		init_domain(fw, XE_FW_DOMAIN_ID_GT,
 			    FORCEWAKE_GT,
@@ -67,9 +64,6 @@ void xe_force_wake_init_engines(struct xe_gt *gt, struct xe_force_wake *fw)
 {
 	int i, j;
 
-	/* Assuming gen11+ so assert this assumption is correct */
-	xe_gt_assert(gt, GRAPHICS_VER(gt_to_xe(gt)) >= 11);
-
 	if (!xe_gt_is_media_type(gt))
 		init_domain(fw, XE_FW_DOMAIN_ID_RENDER,
 			    FORCEWAKE_RENDER,

drivers/gpu/drm/xe/xe_gt.c

@@ -12,8 +12,10 @@
 
 #include <generated/xe_wa_oob.h>
 
+#include "instructions/xe_alu_commands.h"
 #include "instructions/xe_gfxpipe_commands.h"
 #include "instructions/xe_mi_commands.h"
+#include "regs/xe_engine_regs.h"
 #include "regs/xe_gt_regs.h"
 #include "xe_assert.h"
 #include "xe_bb.h"
@@ -176,15 +178,6 @@ static int emit_nop_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	return 0;
 }
 
-/*
- * Convert back from encoded value to type-safe, only to be used when reg.mcr
- * is true
- */
-static struct xe_reg_mcr to_xe_reg_mcr(const struct xe_reg reg)
-{
-	return (const struct xe_reg_mcr){.__reg.raw = reg.raw };
-}
-
 static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 {
 	struct xe_reg_sr *sr = &q->hwe->reg_lrc;
@@ -194,6 +187,7 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	struct xe_bb *bb;
 	struct dma_fence *fence;
 	long timeout;
+	int count_rmw = 0;
 	int count = 0;
 
 	if (q->hwe->class == XE_ENGINE_CLASS_RENDER)
@@ -206,30 +200,32 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 	if (IS_ERR(bb))
 		return PTR_ERR(bb);
 
-	xa_for_each(&sr->xa, idx, entry)
-		++count;
+	/* count RMW registers as those will be handled separately */
+	xa_for_each(&sr->xa, idx, entry) {
+		if (entry->reg.masked || entry->clr_bits == ~0)
+			++count;
+		else
+			++count_rmw;
+	}
 
-	if (count) {
+	if (count || count_rmw)
 		xe_gt_dbg(gt, "LRC WA %s save-restore batch\n", sr->name);
 
+	if (count) {
+		/* emit single LRI with all non RMW regs */
+
 		bb->cs[bb->len++] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(count);
 
 		xa_for_each(&sr->xa, idx, entry) {
 			struct xe_reg reg = entry->reg;
-			struct xe_reg_mcr reg_mcr = to_xe_reg_mcr(reg);
 			u32 val;
 
-			/*
-			 * Skip reading the register if it's not really needed
-			 */
 			if (reg.masked)
 				val = entry->clr_bits << 16;
-			else if (entry->clr_bits + 1)
-				val = (reg.mcr ?
-				       xe_gt_mcr_unicast_read_any(gt, reg_mcr) :
-				       xe_mmio_read32(&gt->mmio, reg)) & (~entry->clr_bits);
-			else
+			else if (entry->clr_bits == ~0)
 				val = 0;
+			else
+				continue;
 
 			val |= entry->set_bits;
 
@@ -239,6 +235,52 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q)
 		}
 	}
 
+	if (count_rmw) {
+		/* emit MI_MATH for each RMW reg */
+
+		xa_for_each(&sr->xa, idx, entry) {
+			if (entry->reg.masked || entry->clr_bits == ~0)
+				continue;
+
+			bb->cs[bb->len++] = MI_LOAD_REGISTER_REG | MI_LRR_DST_CS_MMIO;
+			bb->cs[bb->len++] = entry->reg.addr;
+			bb->cs[bb->len++] = CS_GPR_REG(0, 0).addr;
+
+			bb->cs[bb->len++] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(2) |
+					    MI_LRI_LRM_CS_MMIO;
+			bb->cs[bb->len++] = CS_GPR_REG(0, 1).addr;
+			bb->cs[bb->len++] = entry->clr_bits;
+			bb->cs[bb->len++] = CS_GPR_REG(0, 2).addr;
+			bb->cs[bb->len++] = entry->set_bits;
+
+			bb->cs[bb->len++] = MI_MATH(8);
+			bb->cs[bb->len++] = CS_ALU_INSTR_LOAD(SRCA, REG0);
+			bb->cs[bb->len++] = CS_ALU_INSTR_LOADINV(SRCB, REG1);
+			bb->cs[bb->len++] = CS_ALU_INSTR_AND;
+			bb->cs[bb->len++] = CS_ALU_INSTR_STORE(REG0, ACCU);
+			bb->cs[bb->len++] = CS_ALU_INSTR_LOAD(SRCA, REG0);
+			bb->cs[bb->len++] = CS_ALU_INSTR_LOAD(SRCB, REG2);
+			bb->cs[bb->len++] = CS_ALU_INSTR_OR;
+			bb->cs[bb->len++] = CS_ALU_INSTR_STORE(REG0, ACCU);
+
+			bb->cs[bb->len++] = MI_LOAD_REGISTER_REG | MI_LRR_SRC_CS_MMIO;
+			bb->cs[bb->len++] = CS_GPR_REG(0, 0).addr;
+			bb->cs[bb->len++] = entry->reg.addr;
+
+			xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x\n",
+				  entry->reg.addr, entry->clr_bits, entry->set_bits);
+		}
+
+		/* reset used GPR */
+		bb->cs[bb->len++] = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(3) | MI_LRI_LRM_CS_MMIO;
+		bb->cs[bb->len++] = CS_GPR_REG(0, 0).addr;
+		bb->cs[bb->len++] = 0;
+		bb->cs[bb->len++] = CS_GPR_REG(0, 1).addr;
+		bb->cs[bb->len++] = 0;
+		bb->cs[bb->len++] = CS_GPR_REG(0, 2).addr;
+		bb->cs[bb->len++] = 0;
+	}
+
 	xe_lrc_emit_hwe_state_instructions(q, bb);
 
 	job = xe_bb_create_job(q, bb);

drivers/gpu/drm/xe/xe_gt_clock.c

@@ -40,11 +40,8 @@ static u32 get_crystal_clock_freq(u32 rpm_config_reg)
 	}
 }
 
-int xe_gt_clock_init(struct xe_gt *gt)
+static void check_ctc_mode(struct xe_gt *gt)
 {
-	u32 c0 = xe_mmio_read32(&gt->mmio, RPM_CONFIG0);
-	u32 freq = 0;
-
 	/*
 	 * CTC_MODE[0] = 1 is definitely not supported for Xe2 and later
 	 * platforms.  In theory it could be a valid setting for pre-Xe2
@@ -57,7 +54,17 @@ int xe_gt_clock_init(struct xe_gt *gt)
 	 */
 	if (xe_mmio_read32(&gt->mmio, CTC_MODE) & CTC_SOURCE_DIVIDE_LOGIC)
 		xe_gt_warn(gt, "CTC_MODE[0] is set; this is unexpected and undocumented\n");
+}
+
+int xe_gt_clock_init(struct xe_gt *gt)
+{
+	u32 freq;
+	u32 c0;
+
+	if (!IS_SRIOV_VF(gt_to_xe(gt)))
+		check_ctc_mode(gt);
 
+	c0 = xe_mmio_read32(&gt->mmio, RPM_CONFIG0);
 	freq = get_crystal_clock_freq(c0);
 
 	/*

drivers/gpu/drm/xe/xe_gt_pagefault.c

@@ -240,7 +240,7 @@ static int handle_pagefault(struct xe_gt *gt, struct pagefault *pf)
 	atomic = access_is_atomic(pf->access_type);
 
 	if (xe_vma_is_cpu_addr_mirror(vma))
-		err = xe_svm_handle_pagefault(vm, vma, gt_to_tile(gt),
+		err = xe_svm_handle_pagefault(vm, vma, gt,
 					      pf->page_addr, atomic);
 	else
 		err = handle_vma_pagefault(gt, vma, atomic);

drivers/gpu/drm/xe/xe_gt_sriov_pf_service.c

@@ -112,7 +112,6 @@ static const struct xe_reg tgl_runtime_regs[] = {
 	XELP_GT_SLICE_ENABLE,		/* _MMIO(0x9138) */
 	XELP_GT_GEOMETRY_DSS_ENABLE,	/* _MMIO(0x913c) */
 	GT_VEBOX_VDBOX_DISABLE,		/* _MMIO(0x9140) */
-	CTC_MODE,			/* _MMIO(0xa26c) */
 	HUC_KERNEL_LOAD_INFO,		/* _MMIO(0xc1dc) */
 };
 
@@ -124,7 +123,6 @@ static const struct xe_reg ats_m_runtime_regs[] = {
 	XELP_GT_GEOMETRY_DSS_ENABLE,	/* _MMIO(0x913c) */
 	GT_VEBOX_VDBOX_DISABLE,		/* _MMIO(0x9140) */
 	XEHP_GT_COMPUTE_DSS_ENABLE,	/* _MMIO(0x9144) */
-	CTC_MODE,			/* _MMIO(0xa26c) */
 	HUC_KERNEL_LOAD_INFO,		/* _MMIO(0xc1dc) */
 };
 
@@ -136,7 +134,6 @@ static const struct xe_reg pvc_runtime_regs[] = {
 	GT_VEBOX_VDBOX_DISABLE,		/* _MMIO(0x9140) */
 	XEHP_GT_COMPUTE_DSS_ENABLE,	/* _MMIO(0x9144) */
 	XEHPC_GT_COMPUTE_DSS_ENABLE_EXT,/* _MMIO(0x9148) */
-	CTC_MODE,			/* _MMIO(0xA26C) */
 	HUC_KERNEL_LOAD_INFO,		/* _MMIO(0xc1dc) */
 };
 
@@ -150,7 +147,6 @@ static const struct xe_reg ver_1270_runtime_regs[] = {
 	GT_VEBOX_VDBOX_DISABLE,		/* _MMIO(0x9140) */
 	XEHP_GT_COMPUTE_DSS_ENABLE,	/* _MMIO(0x9144) */
 	XEHPC_GT_COMPUTE_DSS_ENABLE_EXT,/* _MMIO(0x9148) */
-	CTC_MODE,			/* _MMIO(0xa26c) */
 	HUC_KERNEL_LOAD_INFO,		/* _MMIO(0xc1dc) */
 };
 
@@ -167,7 +163,6 @@ static const struct xe_reg ver_2000_runtime_regs[] = {
 	XE2_GT_COMPUTE_DSS_2,		/* _MMIO(0x914c) */
 	XE2_GT_GEOMETRY_DSS_1,		/* _MMIO(0x9150) */
 	XE2_GT_GEOMETRY_DSS_2,		/* _MMIO(0x9154) */
-	CTC_MODE,			/* _MMIO(0xa26c) */
 	HUC_KERNEL_LOAD_INFO,		/* _MMIO(0xc1dc) */
 };
 
@@ -185,7 +180,6 @@ static const struct xe_reg ver_3000_runtime_regs[] = {
 	XE2_GT_COMPUTE_DSS_2,		/* _MMIO(0x914c) */
 	XE2_GT_GEOMETRY_DSS_1,		/* _MMIO(0x9150) */
 	XE2_GT_GEOMETRY_DSS_2,		/* _MMIO(0x9154) */
-	CTC_MODE,			/* _MMIO(0xa26c) */
 	HUC_KERNEL_LOAD_INFO,		/* _MMIO(0xc1dc) */
 };
 

drivers/gpu/drm/xe/xe_gt_stats.c

@@ -27,6 +27,7 @@ void xe_gt_stats_incr(struct xe_gt *gt, const enum xe_gt_stats_id id, int incr)
 }
 
 static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = {
+	"svm_pagefault_count",
 	"tlb_inval_count",
 	"vma_pagefault_count",
 	"vma_pagefault_kb",

drivers/gpu/drm/xe/xe_gt_stats_types.h

@@ -7,6 +7,7 @@
 #define _XE_GT_STATS_TYPES_H_
 
 enum xe_gt_stats_id {
+	XE_GT_STATS_ID_SVM_PAGEFAULT_COUNT,
 	XE_GT_STATS_ID_TLB_INVAL,
 	XE_GT_STATS_ID_VMA_PAGEFAULT_COUNT,
 	XE_GT_STATS_ID_VMA_PAGEFAULT_KB,

drivers/gpu/drm/xe/xe_lrc.c

@@ -1445,6 +1445,7 @@ static int dump_gfxpipe_command(struct drm_printer *p,
 	MATCH3D(3DSTATE_CLIP_MESH);
 	MATCH3D(3DSTATE_SBE_MESH);
 	MATCH3D(3DSTATE_CPSIZE_CONTROL_BUFFER);
+	MATCH3D(3DSTATE_COARSE_PIXEL);
 
 	MATCH3D(3DSTATE_DRAWING_RECTANGLE);
 	MATCH3D(3DSTATE_CHROMA_KEY);

drivers/gpu/drm/xe/xe_memirq.c

@@ -86,7 +86,7 @@ static const char *guc_name(struct xe_guc *guc)
  *   This object needs to be 4KiB aligned.
  *
  * - _`Interrupt Source Report Page`: this is the equivalent of the
- *   GEN11_GT_INTR_DWx registers, with each bit in those registers being
+ *   GT_INTR_DWx registers, with each bit in those registers being
  *   mapped to a byte here. The offsets are the same, just bytes instead
  *   of bits. This object needs to be cacheline aligned.
  *

drivers/gpu/drm/xe/xe_mmio.c

@@ -204,8 +204,9 @@ void xe_mmio_write32(struct xe_mmio *mmio, struct xe_reg reg, u32 val)
 
 	trace_xe_reg_rw(mmio, true, addr, val, sizeof(val));
 
-	if (!reg.vf && mmio->sriov_vf_gt)
-		xe_gt_sriov_vf_write32(mmio->sriov_vf_gt, reg, val);
+	if (!reg.vf && IS_SRIOV_VF(mmio->tile->xe))
+		xe_gt_sriov_vf_write32(mmio->sriov_vf_gt ?:
+				       mmio->tile->primary_gt, reg, val);
 	else
 		writel(val, mmio->regs + addr);
 }
@@ -218,8 +219,9 @@ u32 xe_mmio_read32(struct xe_mmio *mmio, struct xe_reg reg)
 	/* Wa_15015404425 */
 	mmio_flush_pending_writes(mmio);
 
-	if (!reg.vf && mmio->sriov_vf_gt)
-		val = xe_gt_sriov_vf_read32(mmio->sriov_vf_gt, reg);
+	if (!reg.vf && IS_SRIOV_VF(mmio->tile->xe))
+		val = xe_gt_sriov_vf_read32(mmio->sriov_vf_gt ?:
+					    mmio->tile->primary_gt, reg);
 	else
 		val = readl(mmio->regs + addr);
 

drivers/gpu/drm/xe/xe_reg_sr.c

@@ -173,6 +173,9 @@ void xe_reg_sr_apply_mmio(struct xe_reg_sr *sr, struct xe_gt *gt)
 	if (xa_empty(&sr->xa))
 		return;
 
+	if (IS_SRIOV_VF(gt_to_xe(gt)))
+		return;
+
 	xe_gt_dbg(gt, "Applying %s save-restore MMIOs\n", sr->name);
 
 	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);

drivers/gpu/drm/xe/xe_rtp.c

@@ -258,9 +258,6 @@ void xe_rtp_process_to_sr(struct xe_rtp_process_ctx *ctx,
 
 	rtp_get_context(ctx, &hwe, &gt, &xe);
 
-	if (IS_SRIOV_VF(xe))
-		return;
-
 	xe_assert(xe, entries);
 
 	for (entry = entries; entry - entries < n_entries; entry++) {

drivers/gpu/drm/xe/xe_svm.c

@@ -4,6 +4,7 @@
  */
 
 #include "xe_bo.h"
+#include "xe_gt_stats.h"
 #include "xe_gt_tlb_invalidation.h"
 #include "xe_migrate.h"
 #include "xe_module.h"
@@ -713,7 +714,7 @@ static int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
  * xe_svm_handle_pagefault() - SVM handle page fault
  * @vm: The VM.
  * @vma: The CPU address mirror VMA.
- * @tile: The tile upon the fault occurred.
+ * @gt: The gt upon the fault occurred.
  * @fault_addr: The GPU fault address.
  * @atomic: The fault atomic access bit.
  *
@@ -723,7 +724,7 @@ static int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
  * Return: 0 on success, negative error code on error.
  */
 int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
-			    struct xe_tile *tile, u64 fault_addr,
+			    struct xe_gt *gt, u64 fault_addr,
 			    bool atomic)
 {
 	struct drm_gpusvm_ctx ctx = {
@@ -737,12 +738,15 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
 	struct drm_gpusvm_range *r;
 	struct drm_exec exec;
 	struct dma_fence *fence;
+	struct xe_tile *tile = gt_to_tile(gt);
 	ktime_t end = 0;
 	int err;
 
 	lockdep_assert_held_write(&vm->lock);
 	xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(vma));
 
+	xe_gt_stats_incr(gt, XE_GT_STATS_ID_SVM_PAGEFAULT_COUNT, 1);
+
 retry:
 	/* Always process UNMAPs first so view SVM ranges is current */
 	err = xe_svm_garbage_collector(vm);

drivers/gpu/drm/xe/xe_svm.h

@@ -12,10 +12,11 @@
 #define XE_INTERCONNECT_VRAM DRM_INTERCONNECT_DRIVER
 
 struct xe_bo;
-struct xe_vram_region;
+struct xe_gt;
 struct xe_tile;
 struct xe_vm;
 struct xe_vma;
+struct xe_vram_region;
 
 /** struct xe_svm_range - SVM range */
 struct xe_svm_range {
@@ -64,7 +65,7 @@ void xe_svm_fini(struct xe_vm *vm);
 void xe_svm_close(struct xe_vm *vm);
 
 int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
-			    struct xe_tile *tile, u64 fault_addr,
+			    struct xe_gt *gt, u64 fault_addr,
 			    bool atomic);
 
 bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end);
@@ -102,7 +103,7 @@ void xe_svm_close(struct xe_vm *vm)
 
 static inline
 int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
-			    struct xe_tile *tile, u64 fault_addr,
+			    struct xe_gt *gt, u64 fault_addr,
 			    bool atomic)
 {
 	return 0;