Merge drm/drm-next into drm-misc-next

Backmerging from drm-next to get commit e24e6d6953 ("drm/i915/display:
Implement fb_mmap callback function").

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

Documentation/block/index.rst

@@ -18,7 +18,6 @@ Block
    kyber-iosched
    null_blk
    pr
-   request
    stat
    switching-sched
    writeback_cache_control

Documentation/block/request.rst

@@ -1,99 +0,0 @@
-============================
-struct request documentation
-============================
-
-Jens Axboe <jens.axboe@oracle.com> 27/05/02
-
-
-.. FIXME:
-   No idea about what does mean - seems just some noise, so comment it
-
-   1.0
-   Index
-
-   2.0 Struct request members classification
-
-       2.1 struct request members explanation
-
-   3.0
-
-
-   2.0
-
-
-
-Short explanation of request members
-====================================
-
-Classification flags:
-
-	=	====================
-	D	driver member
-	B	block layer member
-	I	I/O scheduler member
-	=	====================
-
-Unless an entry contains a D classification, a device driver must not access
-this member. Some members may contain D classifications, but should only be
-access through certain macros or functions (eg ->flags).
-
-<linux/blkdev.h>
-
-=============================== ======= =======================================
-Member				Flag	Comment
-=============================== ======= =======================================
-struct list_head queuelist	BI	Organization on various internal
-					queues
-
-``void *elevator_private``	I	I/O scheduler private data
-
-unsigned char cmd[16]		D	Driver can use this for setting up
-					a cdb before execution, see
-					blk_queue_prep_rq
-
-unsigned long flags		DBI	Contains info about data direction,
-					request type, etc.
-
-int rq_status			D	Request status bits
-
-kdev_t rq_dev			DBI	Target device
-
-int errors			DB	Error counts
-
-sector_t sector			DBI	Target location
-
-unsigned long hard_nr_sectors	B	Used to keep sector sane
-
-unsigned long nr_sectors	DBI	Total number of sectors in request
-
-unsigned long hard_nr_sectors	B	Used to keep nr_sectors sane
-
-unsigned short nr_phys_segments	DB	Number of physical scatter gather
-					segments in a request
-
-unsigned short nr_hw_segments	DB	Number of hardware scatter gather
-					segments in a request
-
-unsigned int current_nr_sectors	DB	Number of sectors in first segment
-					of request
-
-unsigned int hard_cur_sectors	B	Used to keep current_nr_sectors sane
-
-int tag				DB	TCQ tag, if assigned
-
-``void *special``		D	Free to be used by driver
-
-``char *buffer``		D	Map of first segment, also see
-					section on bouncing SECTION
-
-``struct completion *waiting``	D	Can be used by driver to get signalled
-					on request completion
-
-``struct bio *bio``		DBI	First bio in request
-
-``struct bio *biotail``		DBI	Last bio in request
-
-``struct request_queue *q``	DB	Request queue this request belongs to
-
-``struct request_list *rl``	B	Request list this request came from
-=============================== ======= =======================================

Documentation/devicetree/bindings/media/i2c/ovti,ov2685.yaml

@@ -49,6 +49,7 @@ properties:
 
         properties:
           data-lanes:
+            minItems: 1
             maxItems: 2
 
         required:

Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-common.yaml

@@ -17,20 +17,11 @@ description:
 properties:
   clocks:
     minItems: 3
-    items:
-      - description: PCIe bridge clock.
-      - description: PCIe bus clock.
-      - description: PCIe PHY clock.
-      - description: Additional required clock entry for imx6sx-pcie,
-           imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep.
+    maxItems: 4
 
   clock-names:
     minItems: 3
-    items:
-      - const: pcie
-      - const: pcie_bus
-      - enum: [ pcie_phy, pcie_aux ]
-      - enum: [ pcie_inbound_axi, pcie_aux ]
+    maxItems: 4
 
   num-lanes:
     const: 1

Documentation/devicetree/bindings/pci/fsl,imx6q-pcie-ep.yaml

@@ -31,6 +31,19 @@ properties:
       - const: dbi
       - const: addr_space
 
+  clocks:
+    minItems: 3
+    items:
+      - description: PCIe bridge clock.
+      - description: PCIe bus clock.
+      - description: PCIe PHY clock.
+      - description: Additional required clock entry for imx6sx-pcie,
+           imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep.
+
+  clock-names:
+    minItems: 3
+    maxItems: 4
+
   interrupts:
     items:
       - description: builtin eDMA interrupter.
@@ -49,6 +62,31 @@ required:
 allOf:
   - $ref: /schemas/pci/snps,dw-pcie-ep.yaml#
   - $ref: /schemas/pci/fsl,imx6q-pcie-common.yaml#
+  - if:
+      properties:
+        compatible:
+          enum:
+            - fsl,imx8mq-pcie-ep
+    then:
+      properties:
+        clocks:
+          minItems: 4
+        clock-names:
+          items:
+            - const: pcie
+            - const: pcie_bus
+            - const: pcie_phy
+            - const: pcie_aux
+    else:
+      properties:
+        clocks:
+          maxItems: 3
+        clock-names:
+          items:
+            - const: pcie
+            - const: pcie_bus
+            - const: pcie_aux
+
 
 unevaluatedProperties: false
 

Documentation/devicetree/bindings/pci/fsl,imx6q-pcie.yaml

@@ -40,6 +40,19 @@ properties:
       - const: dbi
       - const: config
 
+  clocks:
+    minItems: 3
+    items:
+      - description: PCIe bridge clock.
+      - description: PCIe bus clock.
+      - description: PCIe PHY clock.
+      - description: Additional required clock entry for imx6sx-pcie,
+           imx6sx-pcie-ep, imx8mq-pcie, imx8mq-pcie-ep.
+
+  clock-names:
+    minItems: 3
+    maxItems: 4
+
   interrupts:
     items:
       - description: builtin MSI controller.
@@ -77,6 +90,70 @@ required:
 allOf:
   - $ref: /schemas/pci/snps,dw-pcie.yaml#
   - $ref: /schemas/pci/fsl,imx6q-pcie-common.yaml#
+  - if:
+      properties:
+        compatible:
+          enum:
+            - fsl,imx6sx-pcie
+    then:
+      properties:
+        clocks:
+          minItems: 4
+        clock-names:
+          items:
+            - const: pcie
+            - const: pcie_bus
+            - const: pcie_phy
+            - const: pcie_inbound_axi
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - fsl,imx8mq-pcie
+    then:
+      properties:
+        clocks:
+          minItems: 4
+        clock-names:
+          items:
+            - const: pcie
+            - const: pcie_bus
+            - const: pcie_phy
+            - const: pcie_aux
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - fsl,imx6q-pcie
+            - fsl,imx6qp-pcie
+            - fsl,imx7d-pcie
+    then:
+      properties:
+        clocks:
+          maxItems: 3
+        clock-names:
+          items:
+            - const: pcie
+            - const: pcie_bus
+            - const: pcie_phy
+
+  - if:
+      properties:
+        compatible:
+          enum:
+            - fsl,imx8mm-pcie
+            - fsl,imx8mp-pcie
+    then:
+      properties:
+        clocks:
+          maxItems: 3
+        clock-names:
+          items:
+            - const: pcie
+            - const: pcie_bus
+            - const: pcie_aux
 
 unevaluatedProperties: false
 

Documentation/networking/bonding.rst

@@ -776,10 +776,11 @@ peer_notif_delay
 	Specify the delay, in milliseconds, between each peer
 	notification (gratuitous ARP and unsolicited IPv6 Neighbor
 	Advertisement) when they are issued after a failover event.
-	This delay should be a multiple of the link monitor interval
-	(arp_interval or miimon, whichever is active). The default
-	value is 0 which means to match the value of the link monitor
-	interval.
+	This delay should be a multiple of the MII link monitor interval
+	(miimon).
+
+	The valid range is 0 - 300000. The default value is 0, which means
+	to match the value of the MII link monitor interval.
 
 prio
 	Slave priority. A higher number means higher priority.

Documentation/networking/index.rst

@@ -116,8 +116,8 @@ Contents:
    udplite
    vrf
    vxlan
-   x25-iface
    x25
+   x25-iface
    xfrm_device
    xfrm_proc
    xfrm_sync

Documentation/networking/x25-iface.rst

@@ -1,8 +1,7 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-============================-
 X.25 Device Driver Interface
-============================-
+============================
 
 Version 1.1
 

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*

arch/arm/kernel/unwind.c

@@ -308,6 +308,29 @@ static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl,
 	return URC_OK;
 }
 
+static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl)
+{
+	unsigned long bytes = 0;
+	unsigned long insn;
+	unsigned long result = 0;
+
+	/*
+	 * unwind_get_byte() will advance `ctrl` one instruction at a time, so
+	 * loop until we get an instruction byte where bit 7 is not set.
+	 *
+	 * Note: This decodes a maximum of 4 bytes to output 28 bits data where
+	 * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence
+	 * it is sufficient for unwinding the stack.
+	 */
+	do {
+		insn = unwind_get_byte(ctrl);
+		result |= (insn & 0x7f) << (bytes * 7);
+		bytes++;
+	} while (!!(insn & 0x80) && (bytes != sizeof(result)));
+
+	return result;
+}
+
 /*
  * Execute the current unwind instruction.
  */
@@ -361,7 +384,7 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		if (ret)
 			goto error;
 	} else if (insn == 0xb2) {
-		unsigned long uleb128 = unwind_get_byte(ctrl);
+		unsigned long uleb128 = unwind_decode_uleb128(ctrl);
 
 		ctrl->vrs[SP] += 0x204 + (uleb128 << 2);
 	} else {

arch/arm/mach-sa1100/jornada720_ssp.c

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  *  arch/arm/mac-sa1100/jornada720_ssp.c
  *
  *  Copyright (C) 2006/2007 Kristoffer Ericson <Kristoffer.Ericson@gmail.com>
@@ -26,6 +26,7 @@ static unsigned long jornada_ssp_flags;
 
 /**
  * jornada_ssp_reverse - reverses input byte
+ * @byte: input byte to reverse
  *
  * we need to reverse all data we receive from the mcu due to its physical location
  * returns : 01110111 -> 11101110
@@ -46,6 +47,7 @@ EXPORT_SYMBOL(jornada_ssp_reverse);
 
 /**
  * jornada_ssp_byte - waits for ready ssp bus and sends byte
+ * @byte: input byte to transmit
  *
  * waits for fifo buffer to clear and then transmits, if it doesn't then we will
  * timeout after <timeout> rounds. Needs mcu running before its called.
@@ -77,6 +79,7 @@ EXPORT_SYMBOL(jornada_ssp_byte);
 
 /**
  * jornada_ssp_inout - decide if input is command or trading byte
+ * @byte: input byte to send (may be %TXDUMMY)
  *
  * returns : (jornada_ssp_byte(byte)) on success
  *         : %-ETIMEDOUT on timeout failure

arch/arm/vfp/entry.S

@@ -23,6 +23,9 @@
 @
 ENTRY(do_vfp)
 	mov	r1, r10
-	mov	r3, r9
-	b	vfp_entry
+	str	lr, [sp, #-8]!
+	add	r3, sp, #4
+	str	r9, [r3]
+	bl	vfp_entry
+	ldr	pc, [sp], #8
 ENDPROC(do_vfp)

arch/arm/vfp/vfphw.S

@@ -172,13 +172,14 @@ vfp_hw_state_valid:
 					@ out before setting an FPEXC that
 					@ stops us reading stuff
 	VFPFMXR	FPEXC, r1		@ Restore FPEXC last
+	mov	sp, r3			@ we think we have handled things
+	pop	{lr}
 	sub	r2, r2, #4		@ Retry current instruction - if Thumb
 	str	r2, [sp, #S_PC]		@ mode it's two 16-bit instructions,
 					@ else it's one 32-bit instruction, so
 					@ always subtract 4 from the following
 					@ instruction address.
 
-	mov	lr, r3			@ we think we have handled things
 local_bh_enable_and_ret:
 	adr	r0, .
 	mov	r1, #SOFTIRQ_DISABLE_OFFSET
@@ -209,8 +210,9 @@ skip:
 
 process_exception:
 	DBGSTR	"bounce"
+	mov	sp, r3			@ setup for a return to the user code.
+	pop	{lr}
 	mov	r2, sp			@ nothing stacked - regdump is at TOS
-	mov	lr, r3			@ setup for a return to the user code.
 
 	@ Now call the C code to package up the bounce to the support code
 	@   r0 holds the trigger instruction

arch/parisc/include/asm/pgtable.h

@@ -413,12 +413,12 @@ extern void paging_init (void);
  *   For the 64bit version, the offset is extended by 32bit.
  */
 #define __swp_type(x)                     ((x).val & 0x1f)
-#define __swp_offset(x)                   ( (((x).val >> 6) &  0x7) | \
-					  (((x).val >> 8) & ~0x7) )
+#define __swp_offset(x)                   ( (((x).val >> 5) & 0x7) | \
+					  (((x).val >> 10) << 3) )
 #define __swp_entry(type, offset)         ((swp_entry_t) { \
 					    ((type) & 0x1f) | \
-					    ((offset &  0x7) << 6) | \
-					    ((offset & ~0x7) << 8) })
+					    ((offset & 0x7) << 5) | \
+					    ((offset >> 3) << 10) })
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 

arch/parisc/kernel/kexec.c

@@ -4,6 +4,8 @@
 #include <linux/console.h>
 #include <linux/kexec.h>
 #include <linux/delay.h>
+#include <linux/reboot.h>
+
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
 

arch/riscv/kernel/pi/Makefile

@@ -22,7 +22,7 @@ KCOV_INSTRUMENT	:= n
 
 $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \
 			       --remove-section=.note.gnu.property \
-			       --prefix-alloc-sections=.init
+			       --prefix-alloc-sections=.init.pi
 $(obj)/%.pi.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 

arch/riscv/kernel/vmlinux.lds.S

@@ -84,11 +84,8 @@ SECTIONS
 	__init_data_begin = .;
 	INIT_DATA_SECTION(16)
 
-	/* Those sections result from the compilation of kernel/pi/string.c */
-	.init.pidata : {
-		*(.init.srodata.cst8*)
-		*(.init__bug_table*)
-		*(.init.sdata*)
+	.init.pi : {
+		*(.init.pi*)
 	}
 
 	.init.bss : {

arch/x86/events/core.c

@@ -1703,10 +1703,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event)) {
-			data.br_stack = &cpuc->lbr_stack;
-			data.sample_flags |= PERF_SAMPLE_BRANCH_STACK;
-		}
+		if (has_branch_stack(event))
+			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);

arch/x86/events/intel/ds.c

@@ -1229,12 +1229,14 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 		  struct perf_event *event, bool add)
 {
 	struct pmu *pmu = event->pmu;
+
 	/*
 	 * Make sure we get updated with the first PEBS
 	 * event. It will trigger also during removal, but
 	 * that does not hurt:
 	 */
-	bool update = cpuc->n_pebs == 1;
+	if (cpuc->n_pebs == 1)
+		cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW;
 
 	if (needed_cb != pebs_needs_sched_cb(cpuc)) {
 		if (!needed_cb)
@@ -1242,7 +1244,7 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 		else
 			perf_sched_cb_dec(pmu);
 
-		update = true;
+		cpuc->pebs_data_cfg |= PEBS_UPDATE_DS_SW;
 	}
 
 	/*
@@ -1252,24 +1254,13 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 	if (x86_pmu.intel_cap.pebs_baseline && add) {
 		u64 pebs_data_cfg;
 
-		/* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
-		if (cpuc->n_pebs == 1) {
-			cpuc->pebs_data_cfg = 0;
-			cpuc->pebs_record_size = sizeof(struct pebs_basic);
-		}
-
 		pebs_data_cfg = pebs_update_adaptive_cfg(event);
-
-		/* Update pebs_record_size if new event requires more data. */
-		if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
-			cpuc->pebs_data_cfg |= pebs_data_cfg;
-			adaptive_pebs_record_size_update();
-			update = true;
-		}
+		/*
+		 * Be sure to update the thresholds when we change the record.
+		 */
+		if (pebs_data_cfg & ~cpuc->pebs_data_cfg)
+			cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW;
 	}
-
-	if (update)
-		pebs_update_threshold(cpuc);
 }
 
 void intel_pmu_pebs_add(struct perf_event *event)
@@ -1326,9 +1317,17 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
 	wrmsrl(base + idx, value);
 }
 
+static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
+{
+	if (cpuc->n_pebs == cpuc->n_large_pebs &&
+	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
+		intel_pmu_drain_pebs_buffer();
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 pebs_data_cfg = cpuc->pebs_data_cfg & ~PEBS_UPDATE_DS_SW;
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
 	unsigned int idx = hwc->idx;
@@ -1344,11 +1343,22 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 	if (x86_pmu.intel_cap.pebs_baseline) {
 		hwc->config |= ICL_EVENTSEL_ADAPTIVE;
-		if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
-			wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
-			cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+		if (pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+			/*
+			 * drain_pebs() assumes uniform record size;
+			 * hence we need to drain when changing said
+			 * size.
+			 */
+			intel_pmu_drain_large_pebs(cpuc);
+			adaptive_pebs_record_size_update();
+			wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
+			cpuc->active_pebs_data_cfg = pebs_data_cfg;
 		}
 	}
+	if (cpuc->pebs_data_cfg & PEBS_UPDATE_DS_SW) {
+		cpuc->pebs_data_cfg = pebs_data_cfg;
+		pebs_update_threshold(cpuc);
+	}
 
 	if (idx >= INTEL_PMC_IDX_FIXED) {
 		if (x86_pmu.intel_cap.pebs_format < 5)
@@ -1391,9 +1401,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (cpuc->n_pebs == cpuc->n_large_pebs &&
-	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
-		intel_pmu_drain_pebs_buffer();
+	intel_pmu_drain_large_pebs(cpuc);
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 

arch/x86/include/asm/perf_event.h

@@ -121,6 +121,9 @@
 #define PEBS_DATACFG_LBRS	BIT_ULL(3)
 #define PEBS_DATACFG_LBR_SHIFT	24
 
+/* Steal the highest bit of pebs_data_cfg for SW usage */
+#define PEBS_UPDATE_DS_SW	BIT_ULL(63)
+
 /*
  * Intel "Architectural Performance Monitoring" CPUID
  * detection/enumeration details:

arch/x86/kernel/amd_nb.c

@@ -36,6 +36,7 @@
 #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e
 #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4
 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4
+#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc
 
 /* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
@@ -79,6 +80,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) },
 	{}
 };
 

arch/x86/lib/retpoline.S

@@ -144,8 +144,8 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
  */
 	.align 64
 	.skip 63, 0xcc
-SYM_FUNC_START_NOALIGN(zen_untrain_ret);
-
+SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	ANNOTATE_NOENDBR
 	/*
 	 * As executed from zen_untrain_ret, this is:
 	 *

drivers/block/nbd.c

@@ -1666,7 +1666,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 		return -EIO;
 
 	dir = debugfs_create_dir(nbd_name(nbd), nbd_dbg_dir);
-	if (!dir) {
+	if (IS_ERR(dir)) {
 		dev_err(nbd_to_dev(nbd), "Failed to create debugfs dir for '%s'\n",
 			nbd_name(nbd));
 		return -EIO;
@@ -1692,7 +1692,7 @@ static int nbd_dbg_init(void)
 	struct dentry *dbg_dir;
 
 	dbg_dir = debugfs_create_dir("nbd", NULL);
-	if (!dbg_dir)
+	if (IS_ERR(dbg_dir))
 		return -EIO;
 
 	nbd_dbg_dir = dbg_dir;

drivers/block/rnbd/rnbd-proto.h

@@ -241,7 +241,7 @@ static inline blk_opf_t rnbd_to_bio_flags(u32 rnbd_opf)
 		bio_opf = REQ_OP_WRITE;
 		break;
 	case RNBD_OP_FLUSH:
-		bio_opf = REQ_OP_FLUSH | REQ_PREFLUSH;
+		bio_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 		break;
 	case RNBD_OP_DISCARD:
 		bio_opf = REQ_OP_DISCARD;

drivers/block/ublk_drv.c

@@ -1281,7 +1281,7 @@ static inline int ublk_check_cmd_op(u32 cmd_op)
 {
 	u32 ioc_type = _IOC_TYPE(cmd_op);
 
-	if (IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u')
+	if (!IS_ENABLED(CONFIG_BLKDEV_UBLK_LEGACY_OPCODES) && ioc_type != 'u')
 		return -EOPNOTSUPP;
 
 	if (ioc_type != 'u' && ioc_type != 0)

drivers/cxl/core/pci.c

@@ -571,6 +571,7 @@ void read_cdat_data(struct cxl_port *port)
 		/* Don't leave table data allocated on error */
 		devm_kfree(dev, cdat_table);
 		dev_err(dev, "CDAT data read error\n");
+		return;
 	}
 
 	port->cdat.table = cdat_table + sizeof(__le32);

drivers/firewire/net.c

@@ -706,21 +706,22 @@ static void fwnet_receive_packet(struct fw_card *card, struct fw_request *r,
 	int rcode;
 
 	if (destination == IEEE1394_ALL_NODES) {
-		kfree(r);
-
-		return;
-	}
-
-	if (offset != dev->handler.offset)
+		// Although the response to the broadcast packet is not necessarily required, the
+		// fw_send_response() function should still be called to maintain the reference
+		// counting of the object. In the case, the call of function just releases the
+		// object as a result to decrease the reference counting.
+		rcode = RCODE_COMPLETE;
+	} else if (offset != dev->handler.offset) {
 		rcode = RCODE_ADDRESS_ERROR;
-	else if (tcode != TCODE_WRITE_BLOCK_REQUEST)
+	} else if (tcode != TCODE_WRITE_BLOCK_REQUEST) {
 		rcode = RCODE_TYPE_ERROR;
-	else if (fwnet_incoming_packet(dev, payload, length,
-				       source, generation, false) != 0) {
+	} else if (fwnet_incoming_packet(dev, payload, length,
+					 source, generation, false) != 0) {
 		dev_err(&dev->netdev->dev, "incoming packet failure\n");
 		rcode = RCODE_CONFLICT_ERROR;
-	} else
+	} else {
 		rcode = RCODE_COMPLETE;
+	}
 
 	fw_send_response(card, r, rcode);
 }

drivers/firmware/sysfb_simplefb.c

@@ -51,7 +51,8 @@ __init bool sysfb_parse_mode(const struct screen_info *si,
 	 *
 	 * It's not easily possible to fix this in struct screen_info,
 	 * as this could break UAPI. The best solution is to compute
-	 * bits_per_pixel here and ignore lfb_depth. In the loop below,
+	 * bits_per_pixel from the color bits, reserved bits and
+	 * reported lfb_depth, whichever is highest.  In the loop below,
 	 * ignore simplefb formats with alpha bits, as EFI and VESA
 	 * don't specify alpha channels.
 	 */
@@ -60,6 +61,7 @@ __init bool sysfb_parse_mode(const struct screen_info *si,
 					  si->green_size + si->green_pos,
 					  si->blue_size + si->blue_pos),
 				     si->rsvd_size + si->rsvd_pos);
+		bits_per_pixel = max_t(u32, bits_per_pixel, si->lfb_depth);
 	} else {
 		bits_per_pixel = si->lfb_depth;
 	}

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3757,6 +3757,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 		adev->have_atomics_support = ((struct amd_sriov_msg_pf2vf_info *)
 			adev->virt.fw_reserve.p_pf2vf)->pcie_atomic_ops_support_flags ==
 			(PCI_EXP_DEVCAP2_ATOMIC_COMP32 | PCI_EXP_DEVCAP2_ATOMIC_COMP64);
+	/* APUs w/ gfx9 onwards doesn't reply on PCIe atomics, rather it is a
+	 * internal path natively support atomics, set have_atomics_support to true.
+	 */
+	else if ((adev->flags & AMD_IS_APU) &&
+		(adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0)))
+		adev->have_atomics_support = true;
 	else
 		adev->have_atomics_support =
 			!pci_enable_atomic_ops_to_root(adev->pdev,
@@ -4506,7 +4512,11 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 	dev_info(adev->dev, "recover vram bo from shadow start\n");
 	mutex_lock(&adev->shadow_list_lock);
 	list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) {
-		shadow = &vmbo->bo;
+		/* If vm is compute context or adev is APU, shadow will be NULL */
+		if (!vmbo->shadow)
+			continue;
+		shadow = vmbo->shadow;
+
 		/* No need to recover an evicted BO */
 		if (shadow->tbo.resource->mem_type != TTM_PL_TT ||
 		    shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET ||

drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c

@@ -687,9 +687,11 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r
 		if (r)
 			return r;
 
-		r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
-		if (r)
-			goto late_fini;
+		if (adev->gfx.cp_ecc_error_irq.funcs) {
+			r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
+			if (r)
+				goto late_fini;
+		}
 	} else {
 		amdgpu_ras_feature_enable_on_boot(adev, ras_block, 0);
 	}

drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c

@@ -1315,13 +1315,6 @@ static int gfx_v11_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	/* ECC error */
-	r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GRBM_CP,
-				  GFX_11_0_0__SRCID__CP_ECC_ERROR,
-				  &adev->gfx.cp_ecc_error_irq);
-	if (r)
-		return r;
-
 	/* FED error */
 	r = amdgpu_irq_add_id(adev, SOC21_IH_CLIENTID_GFX,
 				  GFX_11_0_0__SRCID__RLC_GC_FED_INTERRUPT,
@@ -4444,7 +4437,6 @@ static int gfx_v11_0_hw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int r;
 
-	amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
@@ -5897,36 +5889,6 @@ static void gfx_v11_0_set_compute_eop_interrupt_state(struct amdgpu_device *adev
 	}
 }
 
-#define CP_ME1_PIPE_INST_ADDR_INTERVAL  0x1
-#define SET_ECC_ME_PIPE_STATE(reg_addr, state) \
-	do { \
-		uint32_t tmp = RREG32_SOC15_IP(GC, reg_addr); \
-		tmp = REG_SET_FIELD(tmp, CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, state); \
-		WREG32_SOC15_IP(GC, reg_addr, tmp); \
-	} while (0)
-
-static int gfx_v11_0_set_cp_ecc_error_state(struct amdgpu_device *adev,
-							struct amdgpu_irq_src *source,
-							unsigned type,
-							enum amdgpu_interrupt_state state)
-{
-	uint32_t ecc_irq_state = 0;
-	uint32_t pipe0_int_cntl_addr = 0;
-	int i = 0;
-
-	ecc_irq_state = (state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0;
-
-	pipe0_int_cntl_addr = SOC15_REG_OFFSET(GC, 0, regCP_ME1_PIPE0_INT_CNTL);
-
-	WREG32_FIELD15_PREREG(GC, 0, CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, ecc_irq_state);
-
-	for (i = 0; i < adev->gfx.mec.num_pipe_per_mec; i++)
-		SET_ECC_ME_PIPE_STATE(pipe0_int_cntl_addr + i * CP_ME1_PIPE_INST_ADDR_INTERVAL,
-					ecc_irq_state);
-
-	return 0;
-}
-
 static int gfx_v11_0_set_eop_interrupt_state(struct amdgpu_device *adev,
 					    struct amdgpu_irq_src *src,
 					    unsigned type,
@@ -6341,11 +6303,6 @@ static const struct amdgpu_irq_src_funcs gfx_v11_0_priv_inst_irq_funcs = {
 	.process = gfx_v11_0_priv_inst_irq,
 };
 
-static const struct amdgpu_irq_src_funcs gfx_v11_0_cp_ecc_error_irq_funcs = {
-	.set = gfx_v11_0_set_cp_ecc_error_state,
-	.process = amdgpu_gfx_cp_ecc_error_irq,
-};
-
 static const struct amdgpu_irq_src_funcs gfx_v11_0_rlc_gc_fed_irq_funcs = {
 	.process = gfx_v11_0_rlc_gc_fed_irq,
 };
@@ -6361,9 +6318,6 @@ static void gfx_v11_0_set_irq_funcs(struct amdgpu_device *adev)
 	adev->gfx.priv_inst_irq.num_types = 1;
 	adev->gfx.priv_inst_irq.funcs = &gfx_v11_0_priv_inst_irq_funcs;
 
-	adev->gfx.cp_ecc_error_irq.num_types = 1; /* CP ECC error */
-	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v11_0_cp_ecc_error_irq_funcs;
-
 	adev->gfx.rlc_gc_fed_irq.num_types = 1; /* 0x80 FED error */
 	adev->gfx.rlc_gc_fed_irq.funcs = &gfx_v11_0_rlc_gc_fed_irq_funcs;
 

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -3764,7 +3764,8 @@ static int gfx_v9_0_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
+		amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 

drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c

@@ -54,6 +54,7 @@ static int jpeg_v3_0_early_init(void *handle)
 
 	switch (adev->ip_versions[UVD_HWIP][0]) {
 	case IP_VERSION(3, 1, 1):
+	case IP_VERSION(3, 1, 2):
 		break;
 	default:
 		harvest = RREG32_SOC15(JPEG, 0, mmCC_UVD_HARVESTING);

drivers/gpu/drm/amd/amdgpu/nv.c

@@ -98,6 +98,16 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode =
 };
 
 /* Sienna Cichlid */
+static const struct amdgpu_video_codec_info sc_video_codecs_encode_array[] = {
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
+};
+
+static const struct amdgpu_video_codecs sc_video_codecs_encode = {
+	.codec_count = ARRAY_SIZE(sc_video_codecs_encode_array),
+	.codec_array = sc_video_codecs_encode_array,
+};
+
 static const struct amdgpu_video_codec_info sc_video_codecs_decode_array_vcn0[] =
 {
 	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4096, 3)},
@@ -136,8 +146,8 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode_vcn1 =
 /* SRIOV Sienna Cichlid, not const since data is controlled by host */
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] =
 {
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
-	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2160, 0)},
+	{codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 7680, 4352, 0)},
 };
 
 static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array_vcn0[] =
@@ -237,12 +247,12 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 		} else {
 			if (adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) {
 				if (encode)
-					*codecs = &nv_video_codecs_encode;
+					*codecs = &sc_video_codecs_encode;
 				else
 					*codecs = &sc_video_codecs_decode_vcn1;
 			} else {
 				if (encode)
-					*codecs = &nv_video_codecs_encode;
+					*codecs = &sc_video_codecs_encode;
 				else
 					*codecs = &sc_video_codecs_decode_vcn0;
 			}
@@ -251,14 +261,14 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
 	case IP_VERSION(3, 0, 16):
 	case IP_VERSION(3, 0, 2):
 		if (encode)
-			*codecs = &nv_video_codecs_encode;
+			*codecs = &sc_video_codecs_encode;
 		else
 			*codecs = &sc_video_codecs_decode_vcn0;
 		return 0;
 	case IP_VERSION(3, 1, 1):
 	case IP_VERSION(3, 1, 2):
 		if (encode)
-			*codecs = &nv_video_codecs_encode;
+			*codecs = &sc_video_codecs_encode;
 		else
 			*codecs = &yc_video_codecs_decode;
 		return 0;

drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c

@@ -1917,9 +1917,11 @@ static int sdma_v4_0_hw_fini(void *handle)
 		return 0;
 	}
 
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		amdgpu_irq_put(adev, &adev->sdma.ecc_irq,
-			       AMDGPU_SDMA_IRQ_INSTANCE0 + i);
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {
+		for (i = 0; i < adev->sdma.num_instances; i++) {
+			amdgpu_irq_put(adev, &adev->sdma.ecc_irq,
+				       AMDGPU_SDMA_IRQ_INSTANCE0 + i);
+		}
 	}
 
 	sdma_v4_0_ctx_switch_enable(adev, false);

drivers/gpu/drm/amd/amdgpu/soc21.c

@@ -711,7 +711,7 @@ static int soc21_common_early_init(void *handle)
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_GFX_PG |
 			AMD_PG_SUPPORT_JPEG;
-		adev->external_rev_id = adev->rev_id + 0x1;
+		adev->external_rev_id = adev->rev_id + 0x80;
 		break;
 
 	default:

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c

@@ -423,3 +423,68 @@ void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool
 
 	PERF_TRACE();
 }
+static void apply_symclk_on_tx_off_wa(struct dc_link *link)
+{
+	/* There are use cases where SYMCLK is referenced by OTG. For instance
+	 * for TMDS signal, OTG relies SYMCLK even if TX video output is off.
+	 * However current link interface will power off PHY when disabling link
+	 * output. This will turn off SYMCLK generated by PHY. The workaround is
+	 * to identify such case where SYMCLK is still in use by OTG when we
+	 * power off PHY. When this is detected, we will temporarily power PHY
+	 * back on and move PHY's SYMCLK state to SYMCLK_ON_TX_OFF by calling
+	 * program_pix_clk interface. When OTG is disabled, we will then power
+	 * off PHY by calling disable link output again.
+	 *
+	 * In future dcn generations, we plan to rework transmitter control
+	 * interface so that we could have an option to set SYMCLK ON TX OFF
+	 * state in one step without this workaround
+	 */
+
+	struct dc *dc = link->ctx->dc;
+	struct pipe_ctx *pipe_ctx = NULL;
+	uint8_t i;
+
+	if (link->phy_state.symclk_ref_cnts.otg > 0) {
+		for (i = 0; i < MAX_PIPES; i++) {
+			pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx->stream && pipe_ctx->stream->link == link && pipe_ctx->top_pipe == NULL) {
+				pipe_ctx->clock_source->funcs->program_pix_clk(
+						pipe_ctx->clock_source,
+						&pipe_ctx->stream_res.pix_clk_params,
+						dc->link_srv->dp_get_encoding_format(
+								&pipe_ctx->link_config.dp_link_settings),
+						&pipe_ctx->pll_settings);
+				link->phy_state.symclk_state = SYMCLK_ON_TX_OFF;
+				break;
+			}
+		}
+	}
+}
+
+void dcn314_disable_link_output(struct dc_link *link,
+		const struct link_resource *link_res,
+		enum signal_type signal)
+{
+	struct dc *dc = link->ctx->dc;
+	const struct link_hwss *link_hwss = get_link_hwss(link, link_res);
+	struct dmcu *dmcu = dc->res_pool->dmcu;
+
+	if (signal == SIGNAL_TYPE_EDP &&
+			link->dc->hwss.edp_backlight_control)
+		link->dc->hwss.edp_backlight_control(link, false);
+	else if (dmcu != NULL && dmcu->funcs->lock_phy)
+		dmcu->funcs->lock_phy(dmcu);
+
+	link_hwss->disable_link_output(link, link_res, signal);
+	link->phy_state.symclk_state = SYMCLK_OFF_TX_OFF;
+	/*
+	 * Add the logic to extract BOTH power up and power down sequences
+	 * from enable/disable link output and only call edp panel control
+	 * in enable_link_dp and disable_link_dp once.
+	 */
+	if (dmcu != NULL && dmcu->funcs->lock_phy)
+		dmcu->funcs->unlock_phy(dmcu);
+	dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_DISABLE_LINK_PHY);
+
+	apply_symclk_on_tx_off_wa(link);
+}

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h

@@ -45,4 +45,6 @@ void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool
 
 void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on);
 
+void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal);
+
 #endif /* __DC_HWSS_DCN314_H__ */

drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c

@@ -105,7 +105,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = {
 	.enable_lvds_link_output = dce110_enable_lvds_link_output,
 	.enable_tmds_link_output = dce110_enable_tmds_link_output,
 	.enable_dp_link_output = dce110_enable_dp_link_output,
-	.disable_link_output = dce110_disable_link_output,
+	.disable_link_output = dcn314_disable_link_output,
 	.z10_restore = dcn31_z10_restore,
 	.z10_save_init = dcn31_z10_save_init,
 	.set_disp_pattern_generator = dcn30_set_disp_pattern_generator,

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c

@@ -810,7 +810,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
 					v->SwathHeightY[k],
 					v->SwathHeightC[k],
 					TWait,
-					v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ?
+					(v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ||
+						v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= MIN_DCFCLK_FREQ_MHZ) ?
 							mode_lib->vba.ip.min_prefetch_in_strobe_us : 0,
 					/* Output */
 					&v->DSTXAfterScaler[k],
@@ -3310,7 +3311,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 							v->swath_width_chroma_ub_this_state[k],
 							v->SwathHeightYThisState[k],
 							v->SwathHeightCThisState[k], v->TWait,
-							v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ?
+							(v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= MIN_DCFCLK_FREQ_MHZ) ?
 									mode_lib->vba.ip.min_prefetch_in_strobe_us : 0,
 
 							/* Output */

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h

@@ -53,6 +53,7 @@
 #define BPP_BLENDED_PIPE 0xffffffff
 
 #define MEM_STROBE_FREQ_MHZ 1600
+#define MIN_DCFCLK_FREQ_MHZ 200
 #define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0
 
 struct display_mode_lib;

drivers/gpu/drm/amd/pm/amdgpu_dpm.c

@@ -36,6 +36,8 @@
 #define amdgpu_dpm_enable_bapm(adev, e) \
 		((adev)->powerplay.pp_funcs->enable_bapm((adev)->powerplay.pp_handle, (e)))
 
+#define amdgpu_dpm_is_legacy_dpm(adev) ((adev)->powerplay.pp_handle == (adev))
+
 int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
@@ -1460,15 +1462,24 @@ int amdgpu_dpm_get_smu_prv_buf_details(struct amdgpu_device *adev,
 
 int amdgpu_dpm_is_overdrive_supported(struct amdgpu_device *adev)
 {
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	struct smu_context *smu = adev->powerplay.pp_handle;
+	if (is_support_sw_smu(adev)) {
+		struct smu_context *smu = adev->powerplay.pp_handle;
 
-	if ((is_support_sw_smu(adev) && smu->od_enabled) ||
-	    (is_support_sw_smu(adev) && smu->is_apu) ||
-		(!is_support_sw_smu(adev) && hwmgr->od_enabled))
-		return true;
+		return (smu->od_enabled || smu->is_apu);
+	} else {
+		struct pp_hwmgr *hwmgr;
 
-	return false;
+		/*
+		 * dpm on some legacy asics don't carry od_enabled member
+		 * as its pp_handle is casted directly from adev.
+		 */
+		if (amdgpu_dpm_is_legacy_dpm(adev))
+			return false;
+
+		hwmgr = (struct pp_hwmgr *)adev->powerplay.pp_handle;
+
+		return hwmgr->od_enabled;
+	}
 }
 
 int amdgpu_dpm_set_pp_table(struct amdgpu_device *adev,

drivers/gpu/drm/ast/ast_main.c

@@ -425,11 +425,12 @@ struct ast_device *ast_device_create(const struct drm_driver *drv,
 		return ERR_PTR(-EIO);
 
 	/*
-	 * If we don't have IO space at all, use MMIO now and
-	 * assume the chip has MMIO enabled by default (rev 0x20
-	 * and higher).
+	 * After AST2500, MMIO is enabled by default, and it should be adopted
+	 * to be compatible with Arm.
 	 */
-	if (!(pci_resource_flags(pdev, 2) & IORESOURCE_IO)) {
+	if (pdev->revision >= 0x40) {
+		ast->ioregs = ast->regs + AST_IO_MM_OFFSET;
+	} else if (!(pci_resource_flags(pdev, 2) & IORESOURCE_IO)) {
 		drm_info(dev, "platform has no IO space, trying MMIO\n");
 		ast->ioregs = ast->regs + AST_IO_MM_OFFSET;
 	}

drivers/gpu/drm/drm_fb_helper.c

@@ -641,19 +641,27 @@ static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y,
 static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, size_t len,
 					       struct drm_rect *clip)
 {
+	u32 line_length = info->fix.line_length;
+	u32 fb_height = info->var.yres;
 	off_t end = off + len;
 	u32 x1 = 0;
-	u32 y1 = off / info->fix.line_length;
+	u32 y1 = off / line_length;
 	u32 x2 = info->var.xres;
-	u32 y2 = DIV_ROUND_UP(end, info->fix.line_length);
+	u32 y2 = DIV_ROUND_UP(end, line_length);
+
+	/* Don't allow any of them beyond the bottom bound of display area */
+	if (y1 > fb_height)
+		y1 = fb_height;
+	if (y2 > fb_height)
+		y2 = fb_height;
 
 	if ((y2 - y1) == 1) {
 		/*
 		 * We've only written to a single scanline. Try to reduce
 		 * the number of horizontal pixels that need an update.
 		 */
-		off_t bit_off = (off % info->fix.line_length) * 8;
-		off_t bit_end = (end % info->fix.line_length) * 8;
+		off_t bit_off = (off % line_length) * 8;
+		off_t bit_end = (end % line_length) * 8;
 
 		x1 = bit_off / info->var.bits_per_pixel;
 		x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel);

drivers/gpu/drm/drm_mipi_dsi.c

@@ -221,7 +221,7 @@ mipi_dsi_device_register_full(struct mipi_dsi_host *host,
 		return dsi;
 	}
 
-	dsi->dev.of_node = info->node;
+	device_set_node(&dsi->dev, of_fwnode_handle(info->node));
 	dsi->channel = info->channel;
 	strlcpy(dsi->name, info->type, sizeof(dsi->name));
 

drivers/gpu/drm/i915/Kconfig

@@ -62,10 +62,11 @@ config DRM_I915_FORCE_PROBE
 	  This is the default value for the i915.force_probe module
 	  parameter. Using the module parameter overrides this option.
 
-	  Force probe the i915 for Intel graphics devices that are
-	  recognized but not properly supported by this kernel version. It is
-	  recommended to upgrade to a kernel version with proper support as soon
-	  as it is available.
+	  Force probe the i915 driver for Intel graphics devices that are
+	  recognized but not properly supported by this kernel version. Force
+	  probing an unsupported device taints the kernel. It is recommended to
+	  upgrade to a kernel version with proper support as soon as it is
+	  available.
 
 	  It can also be used to block the probe of recognized and fully
 	  supported devices.
@@ -75,7 +76,8 @@ config DRM_I915_FORCE_PROBE
 	  Use "<pci-id>[,<pci-id>,...]" to force probe the i915 for listed
 	  devices. For example, "4500" or "4500,4571".
 
-	  Use "*" to force probe the driver for all known devices.
+	  Use "*" to force probe the driver for all known devices. Not
+	  recommended.
 
 	  Use "!" right before the ID to block the probe of the device. For
 	  example, "4500,!4571" forces the probe of 4500 and blocks the probe of

drivers/gpu/drm/i915/Makefile

@@ -194,6 +194,7 @@ i915-y += \
 # general-purpose microcontroller (GuC) support
 i915-y += \
 	  gt/uc/intel_gsc_fw.o \
+	  gt/uc/intel_gsc_proxy.o \
 	  gt/uc/intel_gsc_uc.o \
 	  gt/uc/intel_gsc_uc_heci_cmd_submit.o\
 	  gt/uc/intel_guc.o \
@@ -338,6 +339,7 @@ i915-y += \
 i915-$(CONFIG_DRM_I915_PXP) += \
 	pxp/intel_pxp_cmd.o \
 	pxp/intel_pxp_debugfs.o \
+	pxp/intel_pxp_gsccs.o \
 	pxp/intel_pxp_irq.o \
 	pxp/intel_pxp_pm.o \
 	pxp/intel_pxp_session.o
@@ -373,7 +375,7 @@ obj-$(CONFIG_DRM_I915_GVT_KVMGT) += kvmgt.o
 #
 # Enable locally for CONFIG_DRM_I915_WERROR=y. See also scripts/Makefile.build
 ifdef CONFIG_DRM_I915_WERROR
-    cmd_checkdoc = $(srctree)/scripts/kernel-doc -none $<
+    cmd_checkdoc = $(srctree)/scripts/kernel-doc -none -Werror $<
 endif
 
 # header test
@@ -388,7 +390,7 @@ always-$(CONFIG_DRM_I915_WERROR) += \
 
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
       cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; \
-		$(srctree)/scripts/kernel-doc -none $<; touch $@
+		$(srctree)/scripts/kernel-doc -none -Werror $<; touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
 	$(call if_changed_dep,hdrtest)

drivers/gpu/drm/i915/display/intel_atomic_plane.c

@@ -1028,7 +1028,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 	int ret;
 
 	if (old_obj) {
-		const struct intel_crtc_state *crtc_state =
+		const struct intel_crtc_state *new_crtc_state =
 			intel_atomic_get_new_crtc_state(state,
 							to_intel_crtc(old_plane_state->hw.crtc));
 
@@ -1043,7 +1043,7 @@ intel_prepare_plane_fb(struct drm_plane *_plane,
 		 * This should only fail upon a hung GPU, in which case we
 		 * can safely continue.
 		 */
-		if (intel_crtc_needs_modeset(crtc_state)) {
+		if (new_crtc_state && intel_crtc_needs_modeset(new_crtc_state)) {
 			ret = i915_sw_fence_await_reservation(&state->commit_ready,
 							      old_obj->base.resv,
 							      false, 0,

drivers/gpu/drm/i915/display/intel_dp.c

@@ -1601,6 +1601,11 @@ int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 		pipe_config->dsc.slice_count =
 			drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
 							true);
+		if (!pipe_config->dsc.slice_count) {
+			drm_dbg_kms(&dev_priv->drm, "Unsupported Slice Count %d\n",
+				    pipe_config->dsc.slice_count);
+			return -EINVAL;
+		}
 	} else {
 		u16 dsc_max_output_bpp = 0;
 		u8 dsc_dp_slice_count;

drivers/gpu/drm/i915/display/intel_dpt.c

@@ -43,24 +43,24 @@ static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 static void dpt_insert_page(struct i915_address_space *vm,
 			    dma_addr_t addr,
 			    u64 offset,
-			    enum i915_cache_level level,
+			    unsigned int pat_index,
 			    u32 flags)
 {
 	struct i915_dpt *dpt = i915_vm_to_dpt(vm);
 	gen8_pte_t __iomem *base = dpt->iomem;
 
 	gen8_set_pte(base + offset / I915_GTT_PAGE_SIZE,
-		     vm->pte_encode(addr, level, flags));
+		     vm->pte_encode(addr, pat_index, flags));
 }
 
 static void dpt_insert_entries(struct i915_address_space *vm,
 			       struct i915_vma_resource *vma_res,
-			       enum i915_cache_level level,
+			       unsigned int pat_index,
 			       u32 flags)
 {
 	struct i915_dpt *dpt = i915_vm_to_dpt(vm);
 	gen8_pte_t __iomem *base = dpt->iomem;
-	const gen8_pte_t pte_encode = vm->pte_encode(0, level, flags);
+	const gen8_pte_t pte_encode = vm->pte_encode(0, pat_index, flags);
 	struct sgt_iter sgt_iter;
 	dma_addr_t addr;
 	int i;
@@ -83,7 +83,7 @@ static void dpt_clear_range(struct i915_address_space *vm,
 static void dpt_bind_vma(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash,
 			 struct i915_vma_resource *vma_res,
-			 enum i915_cache_level cache_level,
+			 unsigned int pat_index,
 			 u32 flags)
 {
 	u32 pte_flags;
@@ -98,7 +98,7 @@ static void dpt_bind_vma(struct i915_address_space *vm,
 	if (vma_res->bi.lmem)
 		pte_flags |= PTE_LM;
 
-	vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+	vm->insert_entries(vm, vma_res, pat_index, pte_flags);
 
 	vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
 
@@ -300,7 +300,7 @@ intel_dpt_create(struct intel_framebuffer *fb)
 	vm->vma_ops.bind_vma    = dpt_bind_vma;
 	vm->vma_ops.unbind_vma  = dpt_unbind_vma;
 
-	vm->pte_encode = gen8_ggtt_pte_encode;
+	vm->pte_encode = vm->gt->ggtt->vm.pte_encode;
 
 	dpt->obj = dpt_obj;
 	dpt->obj->is_dpt = true;

drivers/gpu/drm/i915/display/intel_fb.c

@@ -1190,7 +1190,8 @@ bool intel_fb_needs_pot_stride_remap(const struct intel_framebuffer *fb)
 {
 	struct drm_i915_private *i915 = to_i915(fb->base.dev);
 
-	return IS_ALDERLAKE_P(i915) && intel_fb_uses_dpt(&fb->base);
+	return (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) &&
+		intel_fb_uses_dpt(&fb->base);
 }
 
 static int intel_fb_pitch(const struct intel_framebuffer *fb, int color_plane, unsigned int rotation)
@@ -1326,9 +1327,10 @@ plane_view_scanout_stride(const struct intel_framebuffer *fb, int color_plane,
 			  unsigned int tile_width,
 			  unsigned int src_stride_tiles, unsigned int dst_stride_tiles)
 {
+	struct drm_i915_private *i915 = to_i915(fb->base.dev);
 	unsigned int stride_tiles;
 
-	if (IS_ALDERLAKE_P(to_i915(fb->base.dev)))
+	if (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14)
 		stride_tiles = src_stride_tiles;
 	else
 		stride_tiles = dst_stride_tiles;
@@ -1522,7 +1524,8 @@ static void intel_fb_view_init(struct drm_i915_private *i915, struct intel_fb_vi
 	memset(view, 0, sizeof(*view));
 	view->gtt.type = view_type;
 
-	if (view_type == I915_GTT_VIEW_REMAPPED && IS_ALDERLAKE_P(i915))
+	if (view_type == I915_GTT_VIEW_REMAPPED &&
+	    (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14))
 		view->gtt.remapped.plane_alignment = SZ_2M / PAGE_SIZE;
 }
 

drivers/gpu/drm/i915/display/intel_fbdev.c

@@ -40,8 +40,10 @@
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "gem/i915_gem_lmem.h"
+#include "gem/i915_gem_mman.h"
 
 #include "i915_drv.h"
 #include "intel_display_types.h"
@@ -67,6 +69,11 @@ struct intel_fbdev {
 	struct mutex hpd_lock;
 };
 
+static struct intel_fbdev *to_intel_fbdev(struct drm_fb_helper *fb_helper)
+{
+	return container_of(fb_helper, struct intel_fbdev, helper);
+}
+
 static struct intel_frontbuffer *to_frontbuffer(struct intel_fbdev *ifbdev)
 {
 	return ifbdev->fb->frontbuffer;
@@ -79,9 +86,7 @@ static void intel_fbdev_invalidate(struct intel_fbdev *ifbdev)
 
 static int intel_fbdev_set_par(struct fb_info *info)
 {
-	struct drm_fb_helper *fb_helper = info->par;
-	struct intel_fbdev *ifbdev =
-		container_of(fb_helper, struct intel_fbdev, helper);
+	struct intel_fbdev *ifbdev = to_intel_fbdev(info->par);
 	int ret;
 
 	ret = drm_fb_helper_set_par(info);
@@ -93,9 +98,7 @@ static int intel_fbdev_set_par(struct fb_info *info)
 
 static int intel_fbdev_blank(int blank, struct fb_info *info)
 {
-	struct drm_fb_helper *fb_helper = info->par;
-	struct intel_fbdev *ifbdev =
-		container_of(fb_helper, struct intel_fbdev, helper);
+	struct intel_fbdev *ifbdev = to_intel_fbdev(info->par);
 	int ret;
 
 	ret = drm_fb_helper_blank(blank, info);
@@ -108,9 +111,7 @@ static int intel_fbdev_blank(int blank, struct fb_info *info)
 static int intel_fbdev_pan_display(struct fb_var_screeninfo *var,
 				   struct fb_info *info)
 {
-	struct drm_fb_helper *fb_helper = info->par;
-	struct intel_fbdev *ifbdev =
-		container_of(fb_helper, struct intel_fbdev, helper);
+	struct intel_fbdev *ifbdev = to_intel_fbdev(info->par);
 	int ret;
 
 	ret = drm_fb_helper_pan_display(var, info);
@@ -120,6 +121,15 @@ static int intel_fbdev_pan_display(struct fb_var_screeninfo *var,
 	return ret;
 }
 
+static int intel_fbdev_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct intel_fbdev *fbdev = to_intel_fbdev(info->par);
+	struct drm_gem_object *bo = drm_gem_fb_get_obj(&fbdev->fb->base, 0);
+	struct drm_i915_gem_object *obj = to_intel_bo(bo);
+
+	return i915_gem_fb_mmap(obj, vma);
+}
+
 static const struct fb_ops intelfb_ops = {
 	.owner = THIS_MODULE,
 	DRM_FB_HELPER_DEFAULT_OPS,
@@ -131,13 +141,13 @@ static const struct fb_ops intelfb_ops = {
 	.fb_imageblit = drm_fb_helper_cfb_imageblit,
 	.fb_pan_display = intel_fbdev_pan_display,
 	.fb_blank = intel_fbdev_blank,
+	.fb_mmap = intel_fbdev_mmap,
 };
 
 static int intelfb_alloc(struct drm_fb_helper *helper,
 			 struct drm_fb_helper_surface_size *sizes)
 {
-	struct intel_fbdev *ifbdev =
-		container_of(helper, struct intel_fbdev, helper);
+	struct intel_fbdev *ifbdev = to_intel_fbdev(helper);
 	struct drm_framebuffer *fb;
 	struct drm_device *dev = helper->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -163,7 +173,8 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 	obj = ERR_PTR(-ENODEV);
 	if (HAS_LMEM(dev_priv)) {
 		obj = i915_gem_object_create_lmem(dev_priv, size,
-						  I915_BO_ALLOC_CONTIGUOUS);
+						  I915_BO_ALLOC_CONTIGUOUS |
+						  I915_BO_ALLOC_USER);
 	} else {
 		/*
 		 * If the FB is too big, just don't use it since fbdev is not very
@@ -193,8 +204,7 @@ static int intelfb_alloc(struct drm_fb_helper *helper,
 static int intelfb_create(struct drm_fb_helper *helper,
 			  struct drm_fb_helper_surface_size *sizes)
 {
-	struct intel_fbdev *ifbdev =
-		container_of(helper, struct intel_fbdev, helper);
+	struct intel_fbdev *ifbdev = to_intel_fbdev(helper);
 	struct intel_framebuffer *intel_fb = ifbdev->fb;
 	struct drm_device *dev = helper->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);

drivers/gpu/drm/i915/display/intel_plane_initial.c

@@ -110,7 +110,9 @@ initial_plane_vma(struct drm_i915_private *i915,
 	    size * 2 > i915->dsm.usable_size)
 		return NULL;
 
-	obj = i915_gem_object_create_region_at(mem, phys_base, size, 0);
+	obj = i915_gem_object_create_region_at(mem, phys_base, size,
+					       I915_BO_ALLOC_USER |
+					       I915_BO_PREALLOC);
 	if (IS_ERR(obj))
 		return NULL;
 

drivers/gpu/drm/i915/gem/i915_gem_domain.c

@@ -27,8 +27,15 @@ static bool gpu_write_needs_clflush(struct drm_i915_gem_object *obj)
 	if (IS_DGFX(i915))
 		return false;
 
-	return !(obj->cache_level == I915_CACHE_NONE ||
-		 obj->cache_level == I915_CACHE_WT);
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, i915_gem_object_has_cache_level() will
+	 * always return true, because the coherency of such object is managed
+	 * by userspace. Othereise the call here would fall back to checking
+	 * whether the object is un-cached or write-through.
+	 */
+	return !(i915_gem_object_has_cache_level(obj, I915_CACHE_NONE) ||
+		 i915_gem_object_has_cache_level(obj, I915_CACHE_WT));
 }
 
 bool i915_gem_cpu_write_needs_clflush(struct drm_i915_gem_object *obj)
@@ -267,7 +274,13 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 {
 	int ret;
 
-	if (obj->cache_level == cache_level)
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, simply return 0 here without touching
+	 * the cache setting, because such objects should have an immutable
+	 * cache setting by desgin and always managed by userspace.
+	 */
+	if (i915_gem_object_has_cache_level(obj, cache_level))
 		return 0;
 
 	ret = i915_gem_object_wait(obj,
@@ -278,10 +291,8 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return ret;
 
 	/* Always invalidate stale cachelines */
-	if (obj->cache_level != cache_level) {
-		i915_gem_object_set_cache_coherency(obj, cache_level);
-		obj->cache_dirty = true;
-	}
+	i915_gem_object_set_cache_coherency(obj, cache_level);
+	obj->cache_dirty = true;
 
 	/* The cache-level will be applied when each vma is rebound. */
 	return i915_gem_object_unbind(obj,
@@ -306,20 +317,22 @@ int i915_gem_get_caching_ioctl(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	switch (obj->cache_level) {
-	case I915_CACHE_LLC:
-	case I915_CACHE_L3_LLC:
-		args->caching = I915_CACHING_CACHED;
-		break;
-
-	case I915_CACHE_WT:
-		args->caching = I915_CACHING_DISPLAY;
-		break;
-
-	default:
-		args->caching = I915_CACHING_NONE;
-		break;
+	/*
+	 * This ioctl should be disabled for the objects with pat_index
+	 * set by user space.
+	 */
+	if (obj->pat_set_by_user) {
+		err = -EOPNOTSUPP;
+		goto out;
 	}
+
+	if (i915_gem_object_has_cache_level(obj, I915_CACHE_LLC) ||
+	    i915_gem_object_has_cache_level(obj, I915_CACHE_L3_LLC))
+		args->caching = I915_CACHING_CACHED;
+	else if (i915_gem_object_has_cache_level(obj, I915_CACHE_WT))
+		args->caching = I915_CACHING_DISPLAY;
+	else
+		args->caching = I915_CACHING_NONE;
 out:
 	rcu_read_unlock();
 	return err;
@@ -337,6 +350,9 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	if (IS_DGFX(i915))
 		return -ENODEV;
 
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		return -EOPNOTSUPP;
+
 	switch (args->caching) {
 	case I915_CACHING_NONE:
 		level = I915_CACHE_NONE;
@@ -364,6 +380,15 @@ int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 	if (!obj)
 		return -ENOENT;
 
+	/*
+	 * This ioctl should be disabled for the objects with pat_index
+	 * set by user space.
+	 */
+	if (obj->pat_set_by_user) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
 	/*
 	 * The caching mode of proxy object is handled by its generator, and
 	 * not allowed to be changed by userspace.

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -640,9 +640,15 @@ static inline int use_cpu_reloc(const struct reloc_cache *cache,
 	if (DBG_FORCE_RELOC == FORCE_GTT_RELOC)
 		return false;
 
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, i915_gem_object_has_cache_level() always
+	 * return true, otherwise the call would fall back to checking whether
+	 * the object is un-cached.
+	 */
 	return (cache->has_llc ||
 		obj->cache_dirty ||
-		obj->cache_level != I915_CACHE_NONE);
+		!i915_gem_object_has_cache_level(obj, I915_CACHE_NONE));
 }
 
 static int eb_reserve_vma(struct i915_execbuffer *eb,
@@ -1324,7 +1330,10 @@ static void *reloc_iomap(struct i915_vma *batch,
 	if (drm_mm_node_allocated(&cache->node)) {
 		ggtt->vm.insert_page(&ggtt->vm,
 				     i915_gem_object_get_dma_address(obj, page),
-				     offset, I915_CACHE_NONE, 0);
+				     offset,
+				     i915_gem_get_pat_index(ggtt->vm.i915,
+							    I915_CACHE_NONE),
+				     0);
 	} else {
 		offset += page << PAGE_SHIFT;
 	}
@@ -1464,7 +1473,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 			reloc_cache_unmap(&eb->reloc_cache);
 			mutex_lock(&vma->vm->mutex);
 			err = i915_vma_bind(target->vma,
-					    target->vma->obj->cache_level,
+					    target->vma->obj->pat_index,
 					    PIN_GLOBAL, NULL, NULL);
 			mutex_unlock(&vma->vm->mutex);
 			reloc_cache_remap(&eb->reloc_cache, ev->vma->obj);

drivers/gpu/drm/i915/gem/i915_gem_mman.c

@@ -383,7 +383,16 @@ retry:
 	}
 
 	/* Access to snoopable pages through the GTT is incoherent. */
-	if (obj->cache_level != I915_CACHE_NONE && !HAS_LLC(i915)) {
+	/*
+	 * For objects created by userspace through GEM_CREATE with pat_index
+	 * set by set_pat extension, coherency is managed by userspace, make
+	 * sure we don't fail handling the vm fault by calling
+	 * i915_gem_object_has_cache_level() which always return true for such
+	 * objects. Otherwise this helper function would fall back to checking
+	 * whether the object is un-cached.
+	 */
+	if (!(i915_gem_object_has_cache_level(obj, I915_CACHE_NONE) ||
+	      HAS_LLC(i915))) {
 		ret = -EFAULT;
 		goto err_unpin;
 	}
@@ -927,53 +936,15 @@ static struct file *mmap_singleton(struct drm_i915_private *i915)
 	return file;
 }
 
-/*
- * This overcomes the limitation in drm_gem_mmap's assignment of a
- * drm_gem_object as the vma->vm_private_data. Since we need to
- * be able to resolve multiple mmap offsets which could be tied
- * to a single gem object.
- */
-int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+static int
+i915_gem_object_mmap(struct drm_i915_gem_object *obj,
+		     struct i915_mmap_offset *mmo,
+		     struct vm_area_struct *vma)
 {
-	struct drm_vma_offset_node *node;
-	struct drm_file *priv = filp->private_data;
-	struct drm_device *dev = priv->minor->dev;
-	struct drm_i915_gem_object *obj = NULL;
-	struct i915_mmap_offset *mmo = NULL;
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct drm_device *dev = &i915->drm;
 	struct file *anon;
 
-	if (drm_dev_is_unplugged(dev))
-		return -ENODEV;
-
-	rcu_read_lock();
-	drm_vma_offset_lock_lookup(dev->vma_offset_manager);
-	node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager,
-						  vma->vm_pgoff,
-						  vma_pages(vma));
-	if (node && drm_vma_node_is_allowed(node, priv)) {
-		/*
-		 * Skip 0-refcnted objects as it is in the process of being
-		 * destroyed and will be invalid when the vma manager lock
-		 * is released.
-		 */
-		if (!node->driver_private) {
-			mmo = container_of(node, struct i915_mmap_offset, vma_node);
-			obj = i915_gem_object_get_rcu(mmo->obj);
-
-			GEM_BUG_ON(obj && obj->ops->mmap_ops);
-		} else {
-			obj = i915_gem_object_get_rcu
-				(container_of(node, struct drm_i915_gem_object,
-					      base.vma_node));
-
-			GEM_BUG_ON(obj && !obj->ops->mmap_ops);
-		}
-	}
-	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
-	rcu_read_unlock();
-	if (!obj)
-		return node ? -EACCES : -EINVAL;
-
 	if (i915_gem_object_is_readonly(obj)) {
 		if (vma->vm_flags & VM_WRITE) {
 			i915_gem_object_put(obj);
@@ -1005,7 +976,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (obj->ops->mmap_ops) {
 		vma->vm_page_prot = pgprot_decrypted(vm_get_page_prot(vma->vm_flags));
 		vma->vm_ops = obj->ops->mmap_ops;
-		vma->vm_private_data = node->driver_private;
+		vma->vm_private_data = obj->base.vma_node.driver_private;
 		return 0;
 	}
 
@@ -1043,6 +1014,91 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	return 0;
 }
 
+/*
+ * This overcomes the limitation in drm_gem_mmap's assignment of a
+ * drm_gem_object as the vma->vm_private_data. Since we need to
+ * be able to resolve multiple mmap offsets which could be tied
+ * to a single gem object.
+ */
+int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct drm_vma_offset_node *node;
+	struct drm_file *priv = filp->private_data;
+	struct drm_device *dev = priv->minor->dev;
+	struct drm_i915_gem_object *obj = NULL;
+	struct i915_mmap_offset *mmo = NULL;
+
+	if (drm_dev_is_unplugged(dev))
+		return -ENODEV;
+
+	rcu_read_lock();
+	drm_vma_offset_lock_lookup(dev->vma_offset_manager);
+	node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager,
+						  vma->vm_pgoff,
+						  vma_pages(vma));
+	if (node && drm_vma_node_is_allowed(node, priv)) {
+		/*
+		 * Skip 0-refcnted objects as it is in the process of being
+		 * destroyed and will be invalid when the vma manager lock
+		 * is released.
+		 */
+		if (!node->driver_private) {
+			mmo = container_of(node, struct i915_mmap_offset, vma_node);
+			obj = i915_gem_object_get_rcu(mmo->obj);
+
+			GEM_BUG_ON(obj && obj->ops->mmap_ops);
+		} else {
+			obj = i915_gem_object_get_rcu
+				(container_of(node, struct drm_i915_gem_object,
+					      base.vma_node));
+
+			GEM_BUG_ON(obj && !obj->ops->mmap_ops);
+		}
+	}
+	drm_vma_offset_unlock_lookup(dev->vma_offset_manager);
+	rcu_read_unlock();
+	if (!obj)
+		return node ? -EACCES : -EINVAL;
+
+	return i915_gem_object_mmap(obj, mmo, vma);
+}
+
+int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct drm_device *dev = &i915->drm;
+	struct i915_mmap_offset *mmo = NULL;
+	enum i915_mmap_type mmap_type;
+	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
+
+	if (drm_dev_is_unplugged(dev))
+		return -ENODEV;
+
+	/* handle ttm object */
+	if (obj->ops->mmap_ops) {
+		/*
+		 * ttm fault handler, ttm_bo_vm_fault_reserved() uses fake offset
+		 * to calculate page offset so set that up.
+		 */
+		vma->vm_pgoff += drm_vma_node_start(&obj->base.vma_node);
+	} else {
+		/* handle stolen and smem objects */
+		mmap_type = i915_ggtt_has_aperture(ggtt) ? I915_MMAP_TYPE_GTT : I915_MMAP_TYPE_WC;
+		mmo = mmap_offset_attach(obj, mmap_type, NULL);
+		if (!mmo)
+			return -ENODEV;
+	}
+
+	/*
+	 * When we install vm_ops for mmap we are too late for
+	 * the vm_ops->open() which increases the ref_count of
+	 * this obj and then it gets decreased by the vm_ops->close().
+	 * To balance this increase the obj ref_count here.
+	 */
+	obj = i915_gem_object_get(obj);
+	return i915_gem_object_mmap(obj, mmo, vma);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/i915_gem_mman.c"
 #endif

drivers/gpu/drm/i915/gem/i915_gem_mman.h

@@ -29,5 +29,5 @@ void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj);
 
 void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object *obj);
 void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj);
-
+int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma);
 #endif

drivers/gpu/drm/i915/gem/i915_gem_object.c

@@ -45,6 +45,33 @@ static struct kmem_cache *slab_objects;
 
 static const struct drm_gem_object_funcs i915_gem_object_funcs;
 
+unsigned int i915_gem_get_pat_index(struct drm_i915_private *i915,
+				    enum i915_cache_level level)
+{
+	if (drm_WARN_ON(&i915->drm, level >= I915_MAX_CACHE_LEVEL))
+		return 0;
+
+	return INTEL_INFO(i915)->cachelevel_to_pat[level];
+}
+
+bool i915_gem_object_has_cache_level(const struct drm_i915_gem_object *obj,
+				     enum i915_cache_level lvl)
+{
+	/*
+	 * In case the pat_index is set by user space, this kernel mode
+	 * driver should leave the coherency to be managed by user space,
+	 * simply return true here.
+	 */
+	if (obj->pat_set_by_user)
+		return true;
+
+	/*
+	 * Otherwise the pat_index should have been converted from cache_level
+	 * so that the following comparison is valid.
+	 */
+	return obj->pat_index == i915_gem_get_pat_index(obj_to_i915(obj), lvl);
+}
+
 struct drm_i915_gem_object *i915_gem_object_alloc(void)
 {
 	struct drm_i915_gem_object *obj;
@@ -124,7 +151,7 @@ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
-	obj->cache_level = cache_level;
+	obj->pat_index = i915_gem_get_pat_index(i915, cache_level);
 
 	if (cache_level != I915_CACHE_NONE)
 		obj->cache_coherent = (I915_BO_CACHE_COHERENT_FOR_READ |
@@ -139,6 +166,37 @@ void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 		!IS_DGFX(i915);
 }
 
+/**
+ * i915_gem_object_set_pat_index - set PAT index to be used in PTE encode
+ * @obj: #drm_i915_gem_object
+ * @pat_index: PAT index
+ *
+ * This is a clone of i915_gem_object_set_cache_coherency taking pat index
+ * instead of cache_level as its second argument.
+ */
+void i915_gem_object_set_pat_index(struct drm_i915_gem_object *obj,
+				   unsigned int pat_index)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+
+	if (obj->pat_index == pat_index)
+		return;
+
+	obj->pat_index = pat_index;
+
+	if (pat_index != i915_gem_get_pat_index(i915, I915_CACHE_NONE))
+		obj->cache_coherent = (I915_BO_CACHE_COHERENT_FOR_READ |
+				       I915_BO_CACHE_COHERENT_FOR_WRITE);
+	else if (HAS_LLC(i915))
+		obj->cache_coherent = I915_BO_CACHE_COHERENT_FOR_READ;
+	else
+		obj->cache_coherent = 0;
+
+	obj->cache_dirty =
+		!(obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_WRITE) &&
+		!IS_DGFX(i915);
+}
+
 bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);

drivers/gpu/drm/i915/gem/i915_gem_object.h

@@ -20,6 +20,8 @@
 
 enum intel_region_id;
 
+#define obj_to_i915(obj__) to_i915((obj__)->base.dev)
+
 static inline bool i915_gem_object_size_2big(u64 size)
 {
 	struct drm_i915_gem_object *obj;
@@ -30,6 +32,10 @@ static inline bool i915_gem_object_size_2big(u64 size)
 	return false;
 }
 
+unsigned int i915_gem_get_pat_index(struct drm_i915_private *i915,
+				    enum i915_cache_level level);
+bool i915_gem_object_has_cache_level(const struct drm_i915_gem_object *obj,
+				     enum i915_cache_level lvl);
 void i915_gem_init__objects(struct drm_i915_private *i915);
 
 void i915_objects_module_exit(void);
@@ -80,7 +86,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj);
 
 /**
  * i915_gem_object_lookup_rcu - look up a temporary GEM object from its handle
- * @filp: DRM file private date
+ * @file: DRM file private date
  * @handle: userspace handle
  *
  * Returns:
@@ -760,6 +766,8 @@ bool i915_gem_object_has_unknown_state(struct drm_i915_gem_object *obj);
 
 void i915_gem_object_set_cache_coherency(struct drm_i915_gem_object *obj,
 					 unsigned int cache_level);
+void i915_gem_object_set_pat_index(struct drm_i915_gem_object *obj,
+				   unsigned int pat_index);
 bool i915_gem_object_can_bypass_llc(struct drm_i915_gem_object *obj);
 void i915_gem_object_flush_if_display(struct drm_i915_gem_object *obj);
 void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj);

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

@@ -194,6 +194,13 @@ enum i915_cache_level {
 	 * engine.
 	 */
 	I915_CACHE_WT,
+	/**
+	 * @I915_MAX_CACHE_LEVEL:
+	 *
+	 * Mark the last entry in the enum. Used for defining cachelevel_to_pat
+	 * array for cache_level to pat translation table.
+	 */
+	I915_MAX_CACHE_LEVEL,
 };
 
 enum i915_map_type {
@@ -328,6 +335,12 @@ struct drm_i915_gem_object {
  */
 #define I915_BO_ALLOC_GPU_ONLY	  BIT(6)
 #define I915_BO_ALLOC_CCS_AUX	  BIT(7)
+/*
+ * Object is allowed to retain its initial data and will not be cleared on first
+ * access if used along with I915_BO_ALLOC_USER. This is mainly to keep
+ * preallocated framebuffer data intact while transitioning it to i915drmfb.
+ */
+#define I915_BO_PREALLOC	  BIT(8)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \
 			     I915_BO_ALLOC_VOLATILE | \
 			     I915_BO_ALLOC_CPU_CLEAR | \
@@ -335,10 +348,11 @@ struct drm_i915_gem_object {
 			     I915_BO_ALLOC_PM_VOLATILE | \
 			     I915_BO_ALLOC_PM_EARLY | \
 			     I915_BO_ALLOC_GPU_ONLY | \
-			     I915_BO_ALLOC_CCS_AUX)
-#define I915_BO_READONLY          BIT(8)
-#define I915_TILING_QUIRK_BIT     9 /* unknown swizzling; do not release! */
-#define I915_BO_PROTECTED         BIT(10)
+			     I915_BO_ALLOC_CCS_AUX | \
+			     I915_BO_PREALLOC)
+#define I915_BO_READONLY          BIT(9)
+#define I915_TILING_QUIRK_BIT     10 /* unknown swizzling; do not release! */
+#define I915_BO_PROTECTED         BIT(11)
 	/**
 	 * @mem_flags - Mutable placement-related flags
 	 *
@@ -350,15 +364,43 @@ struct drm_i915_gem_object {
 #define I915_BO_FLAG_STRUCT_PAGE BIT(0) /* Object backed by struct pages */
 #define I915_BO_FLAG_IOMEM       BIT(1) /* Object backed by IO memory */
 	/**
-	 * @cache_level: The desired GTT caching level.
+	 * @pat_index: The desired PAT index.
 	 *
-	 * See enum i915_cache_level for possible values, along with what
-	 * each does.
+	 * See hardware specification for valid PAT indices for each platform.
+	 * This field replaces the @cache_level that contains a value of enum
+	 * i915_cache_level since PAT indices are being used by both userspace
+	 * and kernel mode driver for caching policy control after GEN12.
+	 * In the meantime platform specific tables are created to translate
+	 * i915_cache_level into pat index, for more details check the macros
+	 * defined i915/i915_pci.c, e.g. PVC_CACHELEVEL.
+	 * For backward compatibility, this field contains values exactly match
+	 * the entries of enum i915_cache_level for pre-GEN12 platforms (See
+	 * LEGACY_CACHELEVEL), so that the PTE encode functions for these
+	 * legacy platforms can stay the same.
 	 */
-	unsigned int cache_level:3;
+	unsigned int pat_index:6;
+	/**
+	 * @pat_set_by_user: Indicate whether pat_index is set by user space
+	 *
+	 * This field is set to false by default, only set to true if the
+	 * pat_index is set by user space. By design, user space is capable of
+	 * managing caching behavior by setting pat_index, in which case this
+	 * kernel mode driver should never touch the pat_index.
+	 */
+	unsigned int pat_set_by_user:1;
 	/**
 	 * @cache_coherent:
 	 *
+	 * Note: with the change above which replaced @cache_level with pat_index,
+	 * the use of @cache_coherent is limited to the objects created by kernel
+	 * or by userspace without pat index specified.
+	 * Check for @pat_set_by_user to find out if an object has pat index set
+	 * by userspace. The ioctl's to change cache settings have also been
+	 * disabled for the objects with pat index set by userspace. Please don't
+	 * assume @cache_coherent having the flags set as describe here. A helper
+	 * function i915_gem_object_has_cache_level() provides one way to bypass
+	 * the use of this field.
+	 *
 	 * Track whether the pages are coherent with the GPU if reading or
 	 * writing through the CPU caches. The largely depends on the
 	 * @cache_level setting.
@@ -432,6 +474,16 @@ struct drm_i915_gem_object {
 	/**
 	 * @cache_dirty:
 	 *
+	 * Note: with the change above which replaced cache_level with pat_index,
+	 * the use of @cache_dirty is limited to the objects created by kernel
+	 * or by userspace without pat index specified.
+	 * Check for @pat_set_by_user to find out if an object has pat index set
+	 * by userspace. The ioctl's to change cache settings have also been
+	 * disabled for the objects with pat_index set by userspace. Please don't
+	 * assume @cache_dirty is set as describe here. Also see helper function
+	 * i915_gem_object_has_cache_level() for possible ways to bypass the use
+	 * of this field.
+	 *
 	 * Track if we are we dirty with writes through the CPU cache for this
 	 * object. As a result reading directly from main memory might yield
 	 * stale data.

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -469,7 +469,10 @@ enum i915_map_type i915_coherent_map_type(struct drm_i915_private *i915,
 					  struct drm_i915_gem_object *obj,
 					  bool always_coherent)
 {
-	if (i915_gem_object_is_lmem(obj))
+	/*
+	 * Wa_22016122933: always return I915_MAP_WC for MTL
+	 */
+	if (i915_gem_object_is_lmem(obj) || IS_METEORLAKE(i915))
 		return I915_MAP_WC;
 	if (HAS_LLC(i915) || always_coherent)
 		return I915_MAP_WB;

drivers/gpu/drm/i915/gem/i915_gem_region.h

@@ -22,9 +22,7 @@ struct i915_gem_apply_to_region;
  */
 struct i915_gem_apply_to_region_ops {
 	/**
-	 * process_obj - Process the current object
-	 * @apply: Embed this for private data.
-	 * @obj: The current object.
+	 * @process_obj: Process the current object
 	 *
 	 * Note that if this function is part of a ww transaction, and
 	 * if returns -EDEADLK for one of the objects, it may be

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -601,7 +601,14 @@ static int shmem_object_init(struct intel_memory_region *mem,
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 
-	if (HAS_LLC(i915))
+	/*
+	 * MTL doesn't snoop CPU cache by default for GPU access (namely
+	 * 1-way coherency). However some UMD's are currently depending on
+	 * that. Make 1-way coherent the default setting for MTL. A follow
+	 * up patch will extend the GEM_CREATE uAPI to allow UMD's specify
+	 * caching mode at BO creation time
+	 */
+	if (HAS_LLC(i915) || (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)))
 		/* On some devices, we can have the GPU use the LLC (the CPU
 		 * cache) for about a 10% performance improvement
 		 * compared to uncached.  Graphics requests other than

drivers/gpu/drm/i915/gem/i915_gem_shrinker.c

@@ -460,8 +460,6 @@ void i915_gem_shrinker_taints_mutex(struct drm_i915_private *i915,
 	fs_reclaim_release(GFP_KERNEL);
 }
 
-#define obj_to_i915(obj__) to_i915((obj__)->base.dev)
-
 /**
  * i915_gem_object_make_unshrinkable - Hide the object from the shrinker. By
  * default all object types that support shrinking(see IS_SHRINKABLE), will also

drivers/gpu/drm/i915/gem/i915_gem_stolen.c

@@ -535,6 +535,14 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 	/* Basic memrange allocator for stolen space. */
 	drm_mm_init(&i915->mm.stolen, 0, i915->dsm.usable_size);
 
+	/*
+	 * Access to stolen lmem beyond certain size for MTL A0 stepping
+	 * would crash the machine. Disable stolen lmem for userspace access
+	 * by setting usable_size to zero.
+	 */
+	if (IS_METEORLAKE(i915) && INTEL_REVID(i915) == 0x0)
+		i915->dsm.usable_size = 0;
+
 	return 0;
 }
 
@@ -557,7 +565,9 @@ static void dbg_poison(struct i915_ggtt *ggtt,
 
 		ggtt->vm.insert_page(&ggtt->vm, addr,
 				     ggtt->error_capture.start,
-				     I915_CACHE_NONE, 0);
+				     i915_gem_get_pat_index(ggtt->vm.i915,
+							    I915_CACHE_NONE),
+				     0);
 		mb();
 
 		s = io_mapping_map_wc(&ggtt->iomap,

drivers/gpu/drm/i915/gem/i915_gem_ttm.h

@@ -42,8 +42,9 @@ static inline bool i915_ttm_is_ghost_object(struct ttm_buffer_object *bo)
 /**
  * i915_ttm_to_gem - Convert a struct ttm_buffer_object to an embedding
  * struct drm_i915_gem_object.
+ * @bo: Pointer to the ttm buffer object
  *
- * Return: Pointer to the embedding struct ttm_buffer_object.
+ * Return: Pointer to the embedding struct drm_i915_gem_object.
  */
 static inline struct drm_i915_gem_object *
 i915_ttm_to_gem(struct ttm_buffer_object *bo)

drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c

@@ -214,7 +214,8 @@ static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo,
 
 		intel_engine_pm_get(to_gt(i915)->migrate.context->engine);
 		ret = intel_context_migrate_clear(to_gt(i915)->migrate.context, deps,
-						  dst_st->sgl, dst_level,
+						  dst_st->sgl,
+						  i915_gem_get_pat_index(i915, dst_level),
 						  i915_ttm_gtt_binds_lmem(dst_mem),
 						  0, &rq);
 	} else {
@@ -228,9 +229,10 @@ static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo,
 		intel_engine_pm_get(to_gt(i915)->migrate.context->engine);
 		ret = intel_context_migrate_copy(to_gt(i915)->migrate.context,
 						 deps, src_rsgt->table.sgl,
-						 src_level,
+						 i915_gem_get_pat_index(i915, src_level),
 						 i915_ttm_gtt_binds_lmem(bo->resource),
-						 dst_st->sgl, dst_level,
+						 dst_st->sgl,
+						 i915_gem_get_pat_index(i915, dst_level),
 						 i915_ttm_gtt_binds_lmem(dst_mem),
 						 &rq);
 
@@ -576,7 +578,7 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 	struct dma_fence *migration_fence = NULL;
 	struct ttm_tt *ttm = bo->ttm;
 	struct i915_refct_sgt *dst_rsgt;
-	bool clear;
+	bool clear, prealloc_bo;
 	int ret;
 
 	if (GEM_WARN_ON(i915_ttm_is_ghost_object(bo))) {
@@ -632,7 +634,8 @@ int i915_ttm_move(struct ttm_buffer_object *bo, bool evict,
 		return PTR_ERR(dst_rsgt);
 
 	clear = !i915_ttm_cpu_maps_iomem(bo->resource) && (!ttm || !ttm_tt_is_populated(ttm));
-	if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC))) {
+	prealloc_bo = obj->flags & I915_BO_PREALLOC;
+	if (!(clear && ttm && !((ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC) && !prealloc_bo))) {
 		struct i915_deps deps;
 
 		i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);

drivers/gpu/drm/i915/gem/selftests/huge_pages.c

@@ -354,7 +354,7 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
-	obj->cache_level = I915_CACHE_NONE;
+	obj->pat_index = i915_gem_get_pat_index(i915, I915_CACHE_NONE);
 
 	return obj;
 }
@@ -695,8 +695,7 @@ out_put:
 	return err;
 }
 
-static void close_object_list(struct list_head *objects,
-			      struct i915_ppgtt *ppgtt)
+static void close_object_list(struct list_head *objects)
 {
 	struct drm_i915_gem_object *obj, *on;
 
@@ -710,17 +709,36 @@ static void close_object_list(struct list_head *objects,
 	}
 }
 
-static int igt_mock_ppgtt_huge_fill(void *arg)
+static int igt_ppgtt_huge_fill(void *arg)
 {
-	struct i915_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->vm.i915;
-	unsigned long max_pages = ppgtt->vm.total >> PAGE_SHIFT;
+	struct drm_i915_private *i915 = arg;
+	unsigned int supported = RUNTIME_INFO(i915)->page_sizes;
+	bool has_pte64 = GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50);
+	struct i915_address_space *vm;
+	struct i915_gem_context *ctx;
+	unsigned long max_pages;
 	unsigned long page_num;
+	struct file *file;
 	bool single = false;
 	LIST_HEAD(objects);
 	IGT_TIMEOUT(end_time);
 	int err = -ENODEV;
 
+	if (supported == I915_GTT_PAGE_SIZE_4K)
+		return 0;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ctx = hugepage_ctx(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out;
+	}
+	vm = i915_gem_context_get_eb_vm(ctx);
+	max_pages = vm->total >> PAGE_SHIFT;
+
 	for_each_prime_number_from(page_num, 1, max_pages) {
 		struct drm_i915_gem_object *obj;
 		u64 size = page_num << PAGE_SHIFT;
@@ -750,13 +768,14 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
+		vma = i915_vma_instance(obj, vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			break;
 		}
 
-		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		/* vma start must be aligned to BIT(21) to allow 2M PTEs */
+		err = i915_vma_pin(vma, 0, BIT(21), PIN_USER);
 		if (err)
 			break;
 
@@ -784,12 +803,13 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 		GEM_BUG_ON(!expected_gtt);
 		GEM_BUG_ON(size);
 
-		if (expected_gtt & I915_GTT_PAGE_SIZE_4K)
+		if (!has_pte64 && (obj->base.size < I915_GTT_PAGE_SIZE_2M ||
+				   expected_gtt & I915_GTT_PAGE_SIZE_2M))
 			expected_gtt &= ~I915_GTT_PAGE_SIZE_64K;
 
 		i915_vma_unpin(vma);
 
-		if (vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K) {
+		if (!has_pte64 && vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K) {
 			if (!IS_ALIGNED(vma->node.start,
 					I915_GTT_PAGE_SIZE_2M)) {
 				pr_err("node.start(%llx) not aligned to 2M\n",
@@ -808,7 +828,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 		}
 
 		if (vma->resource->page_sizes_gtt != expected_gtt) {
-			pr_err("gtt=%u, expected=%u, size=%zd, single=%s\n",
+			pr_err("gtt=%#x, expected=%#x, size=0x%zx, single=%s\n",
 			       vma->resource->page_sizes_gtt, expected_gtt,
 			       obj->base.size, str_yes_no(!!single));
 			err = -EINVAL;
@@ -823,19 +843,25 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 		single = !single;
 	}
 
-	close_object_list(&objects, ppgtt);
+	close_object_list(&objects);
 
 	if (err == -ENOMEM || err == -ENOSPC)
 		err = 0;
 
+	i915_vm_put(vm);
+out:
+	fput(file);
 	return err;
 }
 
-static int igt_mock_ppgtt_64K(void *arg)
+static int igt_ppgtt_64K(void *arg)
 {
-	struct i915_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->vm.i915;
+	struct drm_i915_private *i915 = arg;
+	bool has_pte64 = GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50);
 	struct drm_i915_gem_object *obj;
+	struct i915_address_space *vm;
+	struct i915_gem_context *ctx;
+	struct file *file;
 	const struct object_info {
 		unsigned int size;
 		unsigned int gtt;
@@ -907,16 +933,41 @@ static int igt_mock_ppgtt_64K(void *arg)
 	if (!HAS_PAGE_SIZES(i915, I915_GTT_PAGE_SIZE_64K))
 		return 0;
 
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ctx = hugepage_ctx(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out;
+	}
+	vm = i915_gem_context_get_eb_vm(ctx);
+
 	for (i = 0; i < ARRAY_SIZE(objects); ++i) {
 		unsigned int size = objects[i].size;
 		unsigned int expected_gtt = objects[i].gtt;
 		unsigned int offset = objects[i].offset;
 		unsigned int flags = PIN_USER;
 
+		/*
+		 * For modern GTT models, the requirements for marking a page-table
+		 * as 64K have been relaxed.  Account for this.
+		 */
+		if (has_pte64) {
+			expected_gtt = 0;
+			if (size >= SZ_64K)
+				expected_gtt |= I915_GTT_PAGE_SIZE_64K;
+			if (size & (SZ_64K - 1))
+				expected_gtt |= I915_GTT_PAGE_SIZE_4K;
+		}
+
 		for (single = 0; single <= 1; single++) {
 			obj = fake_huge_pages_object(i915, size, !!single);
-			if (IS_ERR(obj))
-				return PTR_ERR(obj);
+			if (IS_ERR(obj)) {
+				err = PTR_ERR(obj);
+				goto out_vm;
+			}
 
 			err = i915_gem_object_pin_pages_unlocked(obj);
 			if (err)
@@ -928,7 +979,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			 */
 			obj->mm.page_sizes.sg &= ~I915_GTT_PAGE_SIZE_2M;
 
-			vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
+			vma = i915_vma_instance(obj, vm, NULL);
 			if (IS_ERR(vma)) {
 				err = PTR_ERR(vma);
 				goto out_object_unpin;
@@ -945,7 +996,8 @@ static int igt_mock_ppgtt_64K(void *arg)
 			if (err)
 				goto out_vma_unpin;
 
-			if (!offset && vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K) {
+			if (!has_pte64 && !offset &&
+			    vma->page_sizes.sg & I915_GTT_PAGE_SIZE_64K) {
 				if (!IS_ALIGNED(vma->node.start,
 						I915_GTT_PAGE_SIZE_2M)) {
 					pr_err("node.start(%llx) not aligned to 2M\n",
@@ -964,9 +1016,10 @@ static int igt_mock_ppgtt_64K(void *arg)
 			}
 
 			if (vma->resource->page_sizes_gtt != expected_gtt) {
-				pr_err("gtt=%u, expected=%u, i=%d, single=%s\n",
+				pr_err("gtt=%#x, expected=%#x, i=%d, single=%s offset=%#x size=%#x\n",
 				       vma->resource->page_sizes_gtt,
-				       expected_gtt, i, str_yes_no(!!single));
+				       expected_gtt, i, str_yes_no(!!single),
+				       offset, size);
 				err = -EINVAL;
 				goto out_vma_unpin;
 			}
@@ -982,7 +1035,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 		}
 	}
 
-	return 0;
+	goto out_vm;
 
 out_vma_unpin:
 	i915_vma_unpin(vma);
@@ -992,7 +1045,10 @@ out_object_unpin:
 	i915_gem_object_unlock(obj);
 out_object_put:
 	i915_gem_object_put(obj);
-
+out_vm:
+	i915_vm_put(vm);
+out:
+	fput(file);
 	return err;
 }
 
@@ -1910,8 +1966,6 @@ int i915_gem_huge_page_mock_selftests(void)
 		SUBTEST(igt_mock_exhaust_device_supported_pages),
 		SUBTEST(igt_mock_memory_region_huge_pages),
 		SUBTEST(igt_mock_ppgtt_misaligned_dma),
-		SUBTEST(igt_mock_ppgtt_huge_fill),
-		SUBTEST(igt_mock_ppgtt_64K),
 	};
 	struct drm_i915_private *dev_priv;
 	struct i915_ppgtt *ppgtt;
@@ -1962,6 +2016,8 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_sanity_check),
 		SUBTEST(igt_ppgtt_compact),
 		SUBTEST(igt_ppgtt_mixed),
+		SUBTEST(igt_ppgtt_huge_fill),
+		SUBTEST(igt_ppgtt_64K),
 	};
 
 	if (!HAS_PPGTT(i915)) {

drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c

@@ -66,7 +66,7 @@ static int live_nop_switch(void *arg)
 		ctx[n] = live_context(i915, file);
 		if (IS_ERR(ctx[n])) {
 			err = PTR_ERR(ctx[n]);
-			goto out_file;
+			goto out_ctx;
 		}
 	}
 
@@ -82,7 +82,7 @@ static int live_nop_switch(void *arg)
 			this = igt_request_alloc(ctx[n], engine);
 			if (IS_ERR(this)) {
 				err = PTR_ERR(this);
-				goto out_file;
+				goto out_ctx;
 			}
 			if (rq) {
 				i915_request_await_dma_fence(this, &rq->fence);
@@ -93,10 +93,10 @@ static int live_nop_switch(void *arg)
 		}
 		if (i915_request_wait(rq, 0, 10 * HZ) < 0) {
 			pr_err("Failed to populated %d contexts\n", nctx);
-			intel_gt_set_wedged(to_gt(i915));
+			intel_gt_set_wedged(engine->gt);
 			i915_request_put(rq);
 			err = -EIO;
-			goto out_file;
+			goto out_ctx;
 		}
 		i915_request_put(rq);
 
@@ -107,7 +107,7 @@ static int live_nop_switch(void *arg)
 
 		err = igt_live_test_begin(&t, i915, __func__, engine->name);
 		if (err)
-			goto out_file;
+			goto out_ctx;
 
 		end_time = jiffies + i915_selftest.timeout_jiffies;
 		for_each_prime_number_from(prime, 2, 8192) {
@@ -120,7 +120,7 @@ static int live_nop_switch(void *arg)
 				this = igt_request_alloc(ctx[n % nctx], engine);
 				if (IS_ERR(this)) {
 					err = PTR_ERR(this);
-					goto out_file;
+					goto out_ctx;
 				}
 
 				if (rq) { /* Force submission order */
@@ -149,7 +149,7 @@ static int live_nop_switch(void *arg)
 			if (i915_request_wait(rq, 0, HZ / 5) < 0) {
 				pr_err("Switching between %ld contexts timed out\n",
 				       prime);
-				intel_gt_set_wedged(to_gt(i915));
+				intel_gt_set_wedged(engine->gt);
 				i915_request_put(rq);
 				break;
 			}
@@ -165,7 +165,7 @@ static int live_nop_switch(void *arg)
 
 		err = igt_live_test_end(&t);
 		if (err)
-			goto out_file;
+			goto out_ctx;
 
 		pr_info("Switch latencies on %s: 1 = %lluns, %lu = %lluns\n",
 			engine->name,
@@ -173,6 +173,8 @@ static int live_nop_switch(void *arg)
 			prime - 1, div64_u64(ktime_to_ns(times[1]), prime - 1));
 	}
 
+out_ctx:
+	kfree(ctx);
 out_file:
 	fput(file);
 	return err;

drivers/gpu/drm/i915/gem/selftests/i915_gem_migrate.c

@@ -219,7 +219,7 @@ static int __igt_lmem_pages_migrate(struct intel_gt *gt,
 			continue;
 
 		err = intel_migrate_clear(&gt->migrate, &ww, deps,
-					  obj->mm.pages->sgl, obj->cache_level,
+					  obj->mm.pages->sgl, obj->pat_index,
 					  i915_gem_object_is_lmem(obj),
 					  0xdeadbeaf, &rq);
 		if (rq) {

drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c

@@ -1222,7 +1222,7 @@ static int __igt_mmap_migrate(struct intel_memory_region **placements,
 	}
 
 	err = intel_context_migrate_clear(to_gt(i915)->migrate.context, NULL,
-					  obj->mm.pages->sgl, obj->cache_level,
+					  obj->mm.pages->sgl, obj->pat_index,
 					  i915_gem_object_is_lmem(obj),
 					  expand32(POISON_INUSE), &rq);
 	i915_gem_object_unpin_pages(obj);

drivers/gpu/drm/i915/gt/gen6_ppgtt.c

@@ -109,7 +109,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct i915_vma_resource *vma_res,
-				      enum i915_cache_level cache_level,
+				      unsigned int pat_index,
 				      u32 flags)
 {
 	struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
@@ -117,7 +117,7 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	unsigned int first_entry = vma_res->start / I915_GTT_PAGE_SIZE;
 	unsigned int act_pt = first_entry / GEN6_PTES;
 	unsigned int act_pte = first_entry % GEN6_PTES;
-	const u32 pte_encode = vm->pte_encode(0, cache_level, flags);
+	const u32 pte_encode = vm->pte_encode(0, pat_index, flags);
 	struct sgt_dma iter = sgt_dma(vma_res);
 	gen6_pte_t *vaddr;
 
@@ -227,7 +227,9 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt)
 
 	vm->scratch[0]->encode =
 		vm->pte_encode(px_dma(vm->scratch[0]),
-			       I915_CACHE_NONE, PTE_READ_ONLY);
+			       i915_gem_get_pat_index(vm->i915,
+						      I915_CACHE_NONE),
+			       PTE_READ_ONLY);
 
 	vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K);
 	if (IS_ERR(vm->scratch[1])) {
@@ -278,7 +280,7 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 static void pd_vma_bind(struct i915_address_space *vm,
 			struct i915_vm_pt_stash *stash,
 			struct i915_vma_resource *vma_res,
-			enum i915_cache_level cache_level,
+			unsigned int pat_index,
 			u32 unused)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);

drivers/gpu/drm/i915/gt/gen8_ppgtt.c

@@ -29,7 +29,7 @@ static u64 gen8_pde_encode(const dma_addr_t addr,
 }
 
 static u64 gen8_pte_encode(dma_addr_t addr,
-			   enum i915_cache_level level,
+			   unsigned int pat_index,
 			   u32 flags)
 {
 	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
@@ -40,7 +40,12 @@ static u64 gen8_pte_encode(dma_addr_t addr,
 	if (flags & PTE_LM)
 		pte |= GEN12_PPGTT_PTE_LM;
 
-	switch (level) {
+	/*
+	 * For pre-gen12 platforms pat_index is the same as enum
+	 * i915_cache_level, so the switch-case here is still valid.
+	 * See translation table defined by LEGACY_CACHELEVEL.
+	 */
+	switch (pat_index) {
 	case I915_CACHE_NONE:
 		pte |= PPAT_UNCACHED;
 		break;
@@ -55,6 +60,33 @@ static u64 gen8_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
+static u64 gen12_pte_encode(dma_addr_t addr,
+			    unsigned int pat_index,
+			    u32 flags)
+{
+	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT | GEN8_PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~GEN8_PAGE_RW;
+
+	if (flags & PTE_LM)
+		pte |= GEN12_PPGTT_PTE_LM;
+
+	if (pat_index & BIT(0))
+		pte |= GEN12_PPGTT_PTE_PAT0;
+
+	if (pat_index & BIT(1))
+		pte |= GEN12_PPGTT_PTE_PAT1;
+
+	if (pat_index & BIT(2))
+		pte |= GEN12_PPGTT_PTE_PAT2;
+
+	if (pat_index & BIT(3))
+		pte |= MTL_PPGTT_PTE_PAT3;
+
+	return pte;
+}
+
 static void gen8_ppgtt_notify_vgt(struct i915_ppgtt *ppgtt, bool create)
 {
 	struct drm_i915_private *i915 = ppgtt->vm.i915;
@@ -423,11 +455,11 @@ gen8_ppgtt_insert_pte(struct i915_ppgtt *ppgtt,
 		      struct i915_page_directory *pdp,
 		      struct sgt_dma *iter,
 		      u64 idx,
-		      enum i915_cache_level cache_level,
+		      unsigned int pat_index,
 		      u32 flags)
 {
 	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	const gen8_pte_t pte_encode = ppgtt->vm.pte_encode(0, pat_index, flags);
 	gen8_pte_t *vaddr;
 
 	pd = i915_pd_entry(pdp, gen8_pd_index(idx, 2));
@@ -470,10 +502,10 @@ static void
 xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 			  struct i915_vma_resource *vma_res,
 			  struct sgt_dma *iter,
-			  enum i915_cache_level cache_level,
+			  unsigned int pat_index,
 			  u32 flags)
 {
-	const gen8_pte_t pte_encode = vm->pte_encode(0, cache_level, flags);
+	const gen8_pte_t pte_encode = vm->pte_encode(0, pat_index, flags);
 	unsigned int rem = sg_dma_len(iter->sg);
 	u64 start = vma_res->start;
 	u64 end = start + vma_res->vma_size;
@@ -570,6 +602,7 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 			}
 		} while (rem >= page_size && index < max);
 
+		drm_clflush_virt_range(vaddr, PAGE_SIZE);
 		vma_res->page_sizes_gtt |= page_size;
 	} while (iter->sg && sg_dma_len(iter->sg));
 }
@@ -577,10 +610,10 @@ xehpsdv_ppgtt_insert_huge(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_huge(struct i915_address_space *vm,
 				   struct i915_vma_resource *vma_res,
 				   struct sgt_dma *iter,
-				   enum i915_cache_level cache_level,
+				   unsigned int pat_index,
 				   u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
+	const gen8_pte_t pte_encode = vm->pte_encode(0, pat_index, flags);
 	unsigned int rem = sg_dma_len(iter->sg);
 	u64 start = vma_res->start;
 
@@ -700,17 +733,17 @@ static void gen8_ppgtt_insert_huge(struct i915_address_space *vm,
 
 static void gen8_ppgtt_insert(struct i915_address_space *vm,
 			      struct i915_vma_resource *vma_res,
-			      enum i915_cache_level cache_level,
+			      unsigned int pat_index,
 			      u32 flags)
 {
 	struct i915_ppgtt * const ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma_res);
 
 	if (vma_res->bi.page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		if (HAS_64K_PAGES(vm->i915))
-			xehpsdv_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags);
+		if (GRAPHICS_VER_FULL(vm->i915) >= IP_VER(12, 50))
+			xehpsdv_ppgtt_insert_huge(vm, vma_res, &iter, pat_index, flags);
 		else
-			gen8_ppgtt_insert_huge(vm, vma_res, &iter, cache_level, flags);
+			gen8_ppgtt_insert_huge(vm, vma_res, &iter, pat_index, flags);
 	} else  {
 		u64 idx = vma_res->start >> GEN8_PTE_SHIFT;
 
@@ -719,7 +752,7 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
 				gen8_pdp_for_page_index(vm, idx);
 
 			idx = gen8_ppgtt_insert_pte(ppgtt, pdp, &iter, idx,
-						    cache_level, flags);
+						    pat_index, flags);
 		} while (idx);
 
 		vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
@@ -729,7 +762,7 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
 				    dma_addr_t addr,
 				    u64 offset,
-				    enum i915_cache_level level,
+				    unsigned int pat_index,
 				    u32 flags)
 {
 	u64 idx = offset >> GEN8_PTE_SHIFT;
@@ -743,14 +776,14 @@ static void gen8_ppgtt_insert_entry(struct i915_address_space *vm,
 	GEM_BUG_ON(pt->is_compact);
 
 	vaddr = px_vaddr(pt);
-	vaddr[gen8_pd_index(idx, 0)] = gen8_pte_encode(addr, level, flags);
+	vaddr[gen8_pd_index(idx, 0)] = vm->pte_encode(addr, pat_index, flags);
 	drm_clflush_virt_range(&vaddr[gen8_pd_index(idx, 0)], sizeof(*vaddr));
 }
 
 static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
 					    dma_addr_t addr,
 					    u64 offset,
-					    enum i915_cache_level level,
+					    unsigned int pat_index,
 					    u32 flags)
 {
 	u64 idx = offset >> GEN8_PTE_SHIFT;
@@ -773,20 +806,20 @@ static void __xehpsdv_ppgtt_insert_entry_lm(struct i915_address_space *vm,
 	}
 
 	vaddr = px_vaddr(pt);
-	vaddr[gen8_pd_index(idx, 0) / 16] = gen8_pte_encode(addr, level, flags);
+	vaddr[gen8_pd_index(idx, 0) / 16] = vm->pte_encode(addr, pat_index, flags);
 }
 
 static void xehpsdv_ppgtt_insert_entry(struct i915_address_space *vm,
 				       dma_addr_t addr,
 				       u64 offset,
-				       enum i915_cache_level level,
+				       unsigned int pat_index,
 				       u32 flags)
 {
 	if (flags & PTE_LM)
 		return __xehpsdv_ppgtt_insert_entry_lm(vm, addr, offset,
-						       level, flags);
+						       pat_index, flags);
 
-	return gen8_ppgtt_insert_entry(vm, addr, offset, level, flags);
+	return gen8_ppgtt_insert_entry(vm, addr, offset, pat_index, flags);
 }
 
 static int gen8_init_scratch(struct i915_address_space *vm)
@@ -820,8 +853,10 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 		pte_flags |= PTE_LM;
 
 	vm->scratch[0]->encode =
-		gen8_pte_encode(px_dma(vm->scratch[0]),
-				I915_CACHE_NONE, pte_flags);
+		vm->pte_encode(px_dma(vm->scratch[0]),
+			       i915_gem_get_pat_index(vm->i915,
+						      I915_CACHE_NONE),
+			       pte_flags);
 
 	for (i = 1; i <= vm->top; i++) {
 		struct drm_i915_gem_object *obj;
@@ -963,7 +998,10 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 	 */
 	ppgtt->vm.alloc_scratch_dma = alloc_pt_dma;
 
-	ppgtt->vm.pte_encode = gen8_pte_encode;
+	if (GRAPHICS_VER(gt->i915) >= 12)
+		ppgtt->vm.pte_encode = gen12_pte_encode;
+	else
+		ppgtt->vm.pte_encode = gen8_pte_encode;
 
 	ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND;
 	ppgtt->vm.insert_entries = gen8_ppgtt_insert;

drivers/gpu/drm/i915/gt/gen8_ppgtt.h

@@ -10,13 +10,12 @@
 
 struct i915_address_space;
 struct intel_gt;
-enum i915_cache_level;
 
 struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt,
 				     unsigned long lmem_pt_obj_flags);
 
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
-			 enum i915_cache_level level,
+			 unsigned int pat_index,
 			 u32 flags);
 
 #endif

drivers/gpu/drm/i915/gt/intel_context.c

@@ -578,10 +578,13 @@ void intel_context_bind_parent_child(struct intel_context *parent,
 	child->parallel.parent = parent;
 }
 
-u64 intel_context_get_total_runtime_ns(const struct intel_context *ce)
+u64 intel_context_get_total_runtime_ns(struct intel_context *ce)
 {
 	u64 total, active;
 
+	if (ce->ops->update_stats)
+		ce->ops->update_stats(ce);
+
 	total = ce->stats.runtime.total;
 	if (ce->ops->flags & COPS_RUNTIME_CYCLES)
 		total *= ce->engine->gt->clock_period_ns;

drivers/gpu/drm/i915/gt/intel_context.h

@@ -97,7 +97,7 @@ void intel_context_bind_parent_child(struct intel_context *parent,
 
 /**
  * intel_context_lock_pinned - Stablises the 'pinned' status of the HW context
- * @ce - the context
+ * @ce: the context
  *
  * Acquire a lock on the pinned status of the HW context, such that the context
  * can neither be bound to the GPU or unbound whilst the lock is held, i.e.
@@ -111,7 +111,7 @@ static inline int intel_context_lock_pinned(struct intel_context *ce)
 
 /**
  * intel_context_is_pinned - Reports the 'pinned' status
- * @ce - the context
+ * @ce: the context
  *
  * While in use by the GPU, the context, along with its ring and page
  * tables is pinned into memory and the GTT.
@@ -133,7 +133,7 @@ static inline void intel_context_cancel_request(struct intel_context *ce,
 
 /**
  * intel_context_unlock_pinned - Releases the earlier locking of 'pinned' status
- * @ce - the context
+ * @ce: the context
  *
  * Releases the lock earlier acquired by intel_context_unlock_pinned().
  */
@@ -375,7 +375,7 @@ intel_context_clear_nopreempt(struct intel_context *ce)
 	clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
 }
 
-u64 intel_context_get_total_runtime_ns(const struct intel_context *ce);
+u64 intel_context_get_total_runtime_ns(struct intel_context *ce);
 u64 intel_context_get_avg_runtime_ns(struct intel_context *ce);
 
 static inline u64 intel_context_clock(void)

drivers/gpu/drm/i915/gt/intel_context_types.h

@@ -58,6 +58,8 @@ struct intel_context_ops {
 
 	void (*sched_disable)(struct intel_context *ce);
 
+	void (*update_stats)(struct intel_context *ce);
+
 	void (*reset)(struct intel_context *ce);
 	void (*destroy)(struct kref *kref);
 

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -1515,7 +1515,7 @@ int intel_engines_init(struct intel_gt *gt)
 }
 
 /**
- * intel_engines_cleanup_common - cleans up the engine state created by
+ * intel_engine_cleanup_common - cleans up the engine state created by
  *                                the common initiailizers.
  * @engine: Engine to cleanup.
  *

drivers/gpu/drm/i915/gt/intel_engine_types.h

@@ -289,6 +289,7 @@ struct intel_engine_execlists {
 	 */
 	u8 csb_head;
 
+	/* private: selftest */
 	I915_SELFTEST_DECLARE(struct st_preempt_hang preempt_hang;)
 };
 

drivers/gpu/drm/i915/gt/intel_engine_user.c

@@ -117,7 +117,7 @@ static void set_scheduler_caps(struct drm_i915_private *i915)
 			disabled |= (I915_SCHEDULER_CAP_ENABLED |
 				     I915_SCHEDULER_CAP_PRIORITY);
 
-		if (intel_uc_uses_guc_submission(&to_gt(i915)->uc))
+		if (intel_uc_uses_guc_submission(&engine->gt->uc))
 			enabled |= I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP;
 
 		for (i = 0; i < ARRAY_SIZE(map); i++) {

drivers/gpu/drm/i915/gt/intel_ggtt.c

@@ -220,8 +220,28 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 	}
 }
 
+static u64 mtl_ggtt_pte_encode(dma_addr_t addr,
+			       unsigned int pat_index,
+			       u32 flags)
+{
+	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
+
+	WARN_ON_ONCE(addr & ~GEN12_GGTT_PTE_ADDR_MASK);
+
+	if (flags & PTE_LM)
+		pte |= GEN12_GGTT_PTE_LM;
+
+	if (pat_index & BIT(0))
+		pte |= MTL_GGTT_PTE_PAT0;
+
+	if (pat_index & BIT(1))
+		pte |= MTL_GGTT_PTE_PAT1;
+
+	return pte;
+}
+
 u64 gen8_ggtt_pte_encode(dma_addr_t addr,
-			 enum i915_cache_level level,
+			 unsigned int pat_index,
 			 u32 flags)
 {
 	gen8_pte_t pte = addr | GEN8_PAGE_PRESENT;
@@ -240,25 +260,25 @@ static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte)
 static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 				  dma_addr_t addr,
 				  u64 offset,
-				  enum i915_cache_level level,
+				  unsigned int pat_index,
 				  u32 flags)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	gen8_pte_t __iomem *pte =
 		(gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
 
-	gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags));
+	gen8_set_pte(pte, ggtt->vm.pte_encode(addr, pat_index, flags));
 
 	ggtt->invalidate(ggtt);
 }
 
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma_resource *vma_res,
-				     enum i915_cache_level level,
+				     unsigned int pat_index,
 				     u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags);
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
+	const gen8_pte_t pte_encode = ggtt->vm.pte_encode(0, pat_index, flags);
 	gen8_pte_t __iomem *gte;
 	gen8_pte_t __iomem *end;
 	struct sgt_iter iter;
@@ -315,14 +335,14 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 static void gen6_ggtt_insert_page(struct i915_address_space *vm,
 				  dma_addr_t addr,
 				  u64 offset,
-				  enum i915_cache_level level,
+				  unsigned int pat_index,
 				  u32 flags)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	gen6_pte_t __iomem *pte =
 		(gen6_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE;
 
-	iowrite32(vm->pte_encode(addr, level, flags), pte);
+	iowrite32(vm->pte_encode(addr, pat_index, flags), pte);
 
 	ggtt->invalidate(ggtt);
 }
@@ -335,7 +355,7 @@ static void gen6_ggtt_insert_page(struct i915_address_space *vm,
  */
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma_resource *vma_res,
-				     enum i915_cache_level level,
+				     unsigned int pat_index,
 				     u32 flags)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
@@ -352,7 +372,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 		iowrite32(vm->scratch[0]->encode, gte++);
 	end += (vma_res->node_size + vma_res->guard) / I915_GTT_PAGE_SIZE;
 	for_each_sgt_daddr(addr, iter, vma_res->bi.pages)
-		iowrite32(vm->pte_encode(addr, level, flags), gte++);
+		iowrite32(vm->pte_encode(addr, pat_index, flags), gte++);
 	GEM_BUG_ON(gte > end);
 
 	/* Fill the allocated but "unused" space beyond the end of the buffer */
@@ -387,14 +407,15 @@ struct insert_page {
 	struct i915_address_space *vm;
 	dma_addr_t addr;
 	u64 offset;
-	enum i915_cache_level level;
+	unsigned int pat_index;
 };
 
 static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
 {
 	struct insert_page *arg = _arg;
 
-	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset,
+			      arg->pat_index, 0);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
@@ -403,10 +424,10 @@ static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
 static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
 					  dma_addr_t addr,
 					  u64 offset,
-					  enum i915_cache_level level,
+					  unsigned int pat_index,
 					  u32 unused)
 {
-	struct insert_page arg = { vm, addr, offset, level };
+	struct insert_page arg = { vm, addr, offset, pat_index };
 
 	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
 }
@@ -414,7 +435,7 @@ static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
 struct insert_entries {
 	struct i915_address_space *vm;
 	struct i915_vma_resource *vma_res;
-	enum i915_cache_level level;
+	unsigned int pat_index;
 	u32 flags;
 };
 
@@ -422,7 +443,8 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 {
 	struct insert_entries *arg = _arg;
 
-	gen8_ggtt_insert_entries(arg->vm, arg->vma_res, arg->level, arg->flags);
+	gen8_ggtt_insert_entries(arg->vm, arg->vma_res,
+				 arg->pat_index, arg->flags);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
@@ -430,10 +452,10 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 
 static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
 					     struct i915_vma_resource *vma_res,
-					     enum i915_cache_level level,
+					     unsigned int pat_index,
 					     u32 flags)
 {
-	struct insert_entries arg = { vm, vma_res, level, flags };
+	struct insert_entries arg = { vm, vma_res, pat_index, flags };
 
 	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
 }
@@ -462,7 +484,7 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 void intel_ggtt_bind_vma(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash,
 			 struct i915_vma_resource *vma_res,
-			 enum i915_cache_level cache_level,
+			 unsigned int pat_index,
 			 u32 flags)
 {
 	u32 pte_flags;
@@ -479,7 +501,7 @@ void intel_ggtt_bind_vma(struct i915_address_space *vm,
 	if (vma_res->bi.lmem)
 		pte_flags |= PTE_LM;
 
-	vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+	vm->insert_entries(vm, vma_res, pat_index, pte_flags);
 	vma_res->page_sizes_gtt = I915_GTT_PAGE_SIZE;
 }
 
@@ -628,7 +650,7 @@ err:
 static void aliasing_gtt_bind_vma(struct i915_address_space *vm,
 				  struct i915_vm_pt_stash *stash,
 				  struct i915_vma_resource *vma_res,
-				  enum i915_cache_level cache_level,
+				  unsigned int pat_index,
 				  u32 flags)
 {
 	u32 pte_flags;
@@ -640,10 +662,10 @@ static void aliasing_gtt_bind_vma(struct i915_address_space *vm,
 
 	if (flags & I915_VMA_LOCAL_BIND)
 		ppgtt_bind_vma(&i915_vm_to_ggtt(vm)->alias->vm,
-			       stash, vma_res, cache_level, flags);
+			       stash, vma_res, pat_index, flags);
 
 	if (flags & I915_VMA_GLOBAL_BIND)
-		vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+		vm->insert_entries(vm, vma_res, pat_index, pte_flags);
 
 	vma_res->bound_flags |= flags;
 }
@@ -900,7 +922,9 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 
 	ggtt->vm.scratch[0]->encode =
 		ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]),
-				    I915_CACHE_NONE, pte_flags);
+				    i915_gem_get_pat_index(i915,
+							   I915_CACHE_NONE),
+				    pte_flags);
 
 	return 0;
 }
@@ -981,11 +1005,19 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.vma_ops.bind_vma    = intel_ggtt_bind_vma;
 	ggtt->vm.vma_ops.unbind_vma  = intel_ggtt_unbind_vma;
 
-	ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		ggtt->vm.pte_encode = mtl_ggtt_pte_encode;
+	else
+		ggtt->vm.pte_encode = gen8_ggtt_pte_encode;
 
 	return ggtt_probe_common(ggtt, size);
 }
 
+/*
+ * For pre-gen8 platforms pat_index is the same as enum i915_cache_level,
+ * so these PTE encode functions are left with using cache_level.
+ * See translation table LEGACY_CACHELEVEL.
+ */
 static u64 snb_pte_encode(dma_addr_t addr,
 			  enum i915_cache_level level,
 			  u32 flags)
@@ -1266,7 +1298,9 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm)
 		 */
 		vma->resource->bound_flags = 0;
 		vma->ops->bind_vma(vm, NULL, vma->resource,
-				   obj ? obj->cache_level : 0,
+				   obj ? obj->pat_index :
+					 i915_gem_get_pat_index(vm->i915,
+								I915_CACHE_NONE),
 				   was_bound);
 
 		if (obj) { /* only used during resume => exclusive access */

drivers/gpu/drm/i915/gt/intel_gt_irq.c

@@ -15,6 +15,7 @@
 #include "intel_uncore.h"
 #include "intel_rps.h"
 #include "pxp/intel_pxp_irq.h"
+#include "uc/intel_gsc_proxy.h"
 
 static void guc_irq_handler(struct intel_guc *guc, u16 iir)
 {
@@ -81,6 +82,9 @@ gen11_other_irq_handler(struct intel_gt *gt, const u8 instance,
 	if (instance == OTHER_GSC_INSTANCE)
 		return intel_gsc_irq_handler(gt, iir);
 
+	if (instance == OTHER_GSC_HECI_2_INSTANCE)
+		return intel_gsc_proxy_irq_handler(&gt->uc.gsc, iir);
+
 	WARN_ONCE(1, "unhandled other interrupt instance=0x%x, iir=0x%x\n",
 		  instance, iir);
 }
@@ -100,7 +104,10 @@ static struct intel_gt *pick_gt(struct intel_gt *gt, u8 class, u8 instance)
 	case VIDEO_ENHANCEMENT_CLASS:
 		return media_gt;
 	case OTHER_CLASS:
-		if (instance == OTHER_GSC_INSTANCE && HAS_ENGINE(media_gt, GSC0))
+		if (instance == OTHER_GSC_HECI_2_INSTANCE)
+			return media_gt;
+		if ((instance == OTHER_GSC_INSTANCE || instance == OTHER_KCR_INSTANCE) &&
+		    HAS_ENGINE(media_gt, GSC0))
 			return media_gt;
 		fallthrough;
 	default:
@@ -256,6 +263,7 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	u32 irqs = GT_RENDER_USER_INTERRUPT;
 	u32 guc_mask = intel_uc_wants_guc(&gt->uc) ? GUC_INTR_GUC2HOST : 0;
 	u32 gsc_mask = 0;
+	u32 heci_mask = 0;
 	u32 dmask;
 	u32 smask;
 
@@ -267,10 +275,16 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	dmask = irqs << 16 | irqs;
 	smask = irqs << 16;
 
-	if (HAS_ENGINE(gt, GSC0))
+	if (HAS_ENGINE(gt, GSC0)) {
+		/*
+		 * the heci2 interrupt is enabled via the same register as the
+		 * GSC interrupt, but it has its own mask register.
+		 */
 		gsc_mask = irqs;
-	else if (HAS_HECI_GSC(gt->i915))
+		heci_mask = GSC_IRQ_INTF(1); /* HECI2 IRQ for SW Proxy*/
+	} else if (HAS_HECI_GSC(gt->i915)) {
 		gsc_mask = GSC_IRQ_INTF(0) | GSC_IRQ_INTF(1);
+	}
 
 	BUILD_BUG_ON(irqs & 0xffff0000);
 
@@ -280,7 +294,7 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 	if (CCS_MASK(gt))
 		intel_uncore_write(uncore, GEN12_CCS_RSVD_INTR_ENABLE, smask);
 	if (gsc_mask)
-		intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, gsc_mask);
+		intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_ENABLE, gsc_mask | heci_mask);
 
 	/* Unmask irqs on RCS, BCS, VCS and VECS engines. */
 	intel_uncore_write(uncore, GEN11_RCS0_RSVD_INTR_MASK, ~smask);
@@ -308,6 +322,9 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt)
 		intel_uncore_write(uncore, GEN12_CCS2_CCS3_INTR_MASK, ~dmask);
 	if (gsc_mask)
 		intel_uncore_write(uncore, GEN11_GUNIT_CSME_INTR_MASK, ~gsc_mask);
+	if (heci_mask)
+		intel_uncore_write(uncore, GEN12_HECI2_RSVD_INTR_MASK,
+				   ~REG_FIELD_PREP(ENGINE1_MASK, heci_mask));
 
 	if (guc_mask) {
 		/* the enable bit is common for both GTs but the masks are separate */

drivers/gpu/drm/i915/gt/intel_gt_pm.c

@@ -87,7 +87,7 @@ static int __gt_unpark(struct intel_wakeref *wf)
 
 	intel_rc6_unpark(&gt->rc6);
 	intel_rps_unpark(&gt->rps);
-	i915_pmu_gt_unparked(i915);
+	i915_pmu_gt_unparked(gt);
 	intel_guc_busyness_unpark(gt);
 
 	intel_gt_unpark_requests(gt);
@@ -109,7 +109,7 @@ static int __gt_park(struct intel_wakeref *wf)
 
 	intel_guc_busyness_park(gt);
 	i915_vma_parked(gt);
-	i915_pmu_gt_parked(i915);
+	i915_pmu_gt_parked(gt);
 	intel_rps_park(&gt->rps);
 	intel_rc6_park(&gt->rc6);
 

drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c

@@ -539,7 +539,10 @@ static bool rps_eval(void *data)
 {
 	struct intel_gt *gt = data;
 
-	return HAS_RPS(gt->i915);
+	if (intel_guc_slpc_is_used(&gt->uc.guc))
+		return false;
+	else
+		return HAS_RPS(gt->i915);
 }
 
 DEFINE_INTEL_GT_DEBUGFS_ATTRIBUTE(rps_boost);

drivers/gpu/drm/i915/gt/intel_gt_regs.h

@@ -356,7 +356,11 @@
 #define GEN7_TLB_RD_ADDR			_MMIO(0x4700)
 
 #define GEN12_PAT_INDEX(index)			_MMIO(0x4800 + (index) * 4)
-#define XEHP_PAT_INDEX(index)			MCR_REG(0x4800 + (index) * 4)
+#define _PAT_INDEX(index)			_PICK_EVEN_2RANGES(index, 8, \
+								   0x4800, 0x4804, \
+								   0x4848, 0x484c)
+#define XEHP_PAT_INDEX(index)			MCR_REG(_PAT_INDEX(index))
+#define XELPMP_PAT_INDEX(index)			_MMIO(_PAT_INDEX(index))
 
 #define XEHP_TILE0_ADDR_RANGE			MCR_REG(0x4900)
 #define   XEHP_TILE_LMEM_RANGE_SHIFT		8
@@ -525,6 +529,11 @@
 
 #define GEN8_RC6_CTX_INFO			_MMIO(0x8504)
 
+#define GEN12_SQCNT1				_MMIO(0x8718)
+#define   GEN12_SQCNT1_PMON_ENABLE		REG_BIT(30)
+#define   GEN12_SQCNT1_OABPC			REG_BIT(29)
+#define   GEN12_STRICT_RAR_ENABLE		REG_BIT(23)
+
 #define XEHP_SQCM				MCR_REG(0x8724)
 #define   EN_32B_ACCESS				REG_BIT(30)
 
@@ -1587,6 +1596,7 @@
 
 #define GEN11_GT_INTR_DW(x)			_MMIO(0x190018 + ((x) * 4))
 #define   GEN11_CSME				(31)
+#define   GEN12_HECI_2				(30)
 #define   GEN11_GUNIT				(28)
 #define   GEN11_GUC				(25)
 #define   MTL_MGUC				(24)
@@ -1628,6 +1638,7 @@
 /* irq instances for OTHER_CLASS */
 #define   OTHER_GUC_INSTANCE			0
 #define   OTHER_GTPM_INSTANCE			1
+#define   OTHER_GSC_HECI_2_INSTANCE		3
 #define   OTHER_KCR_INSTANCE			4
 #define   OTHER_GSC_INSTANCE			6
 #define   OTHER_MEDIA_GUC_INSTANCE		16
@@ -1643,6 +1654,7 @@
 #define GEN12_VCS6_VCS7_INTR_MASK		_MMIO(0x1900b4)
 #define GEN11_VECS0_VECS1_INTR_MASK		_MMIO(0x1900d0)
 #define GEN12_VECS2_VECS3_INTR_MASK		_MMIO(0x1900d4)
+#define GEN12_HECI2_RSVD_INTR_MASK		_MMIO(0x1900e4)
 #define GEN11_GUC_SG_INTR_MASK			_MMIO(0x1900e8)
 #define MTL_GUC_MGUC_INTR_MASK			_MMIO(0x1900e8) /* MTL+ */
 #define GEN11_GPM_WGBOXPERF_INTR_MASK		_MMIO(0x1900ec)

drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c

@@ -451,6 +451,33 @@ static ssize_t punit_req_freq_mhz_show(struct kobject *kobj,
 	return sysfs_emit(buff, "%u\n", preq);
 }
 
+static ssize_t slpc_ignore_eff_freq_show(struct kobject *kobj,
+					 struct kobj_attribute *attr,
+					 char *buff)
+{
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+
+	return sysfs_emit(buff, "%u\n", slpc->ignore_eff_freq);
+}
+
+static ssize_t slpc_ignore_eff_freq_store(struct kobject *kobj,
+					  struct kobj_attribute *attr,
+					  const char *buff, size_t count)
+{
+	struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name);
+	struct intel_guc_slpc *slpc = &gt->uc.guc.slpc;
+	int err;
+	u32 val;
+
+	err = kstrtou32(buff, 0, &val);
+	if (err)
+		return err;
+
+	err = intel_guc_slpc_set_ignore_eff_freq(slpc, val);
+	return err ?: count;
+}
+
 struct intel_gt_bool_throttle_attr {
 	struct attribute attr;
 	ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *attr,
@@ -663,6 +690,8 @@ static struct kobj_attribute attr_media_freq_factor_scale =
 INTEL_GT_ATTR_RO(media_RP0_freq_mhz);
 INTEL_GT_ATTR_RO(media_RPn_freq_mhz);
 
+INTEL_GT_ATTR_RW(slpc_ignore_eff_freq);
+
 static const struct attribute *media_perf_power_attrs[] = {
 	&attr_media_freq_factor.attr,
 	&attr_media_freq_factor_scale.attr,
@@ -744,6 +773,12 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj)
 	if (ret)
 		gt_warn(gt, "failed to create punit_req_freq_mhz sysfs (%pe)", ERR_PTR(ret));
 
+	if (intel_uc_uses_guc_slpc(&gt->uc)) {
+		ret = sysfs_create_file(kobj, &attr_slpc_ignore_eff_freq.attr);
+		if (ret)
+			gt_warn(gt, "failed to create ignore_eff_freq sysfs (%pe)", ERR_PTR(ret));
+	}
+
 	if (i915_mmio_reg_valid(intel_gt_perf_limit_reasons_reg(gt))) {
 		ret = sysfs_create_files(kobj, throttle_reason_attrs);
 		if (ret)

drivers/gpu/drm/i915/gt/intel_gtt.c

@@ -468,6 +468,44 @@ void gtt_write_workarounds(struct intel_gt *gt)
 	}
 }
 
+static void xelpmp_setup_private_ppat(struct intel_uncore *uncore)
+{
+	intel_uncore_write(uncore, XELPMP_PAT_INDEX(0),
+			   MTL_PPAT_L4_0_WB);
+	intel_uncore_write(uncore, XELPMP_PAT_INDEX(1),
+			   MTL_PPAT_L4_1_WT);
+	intel_uncore_write(uncore, XELPMP_PAT_INDEX(2),
+			   MTL_PPAT_L4_3_UC);
+	intel_uncore_write(uncore, XELPMP_PAT_INDEX(3),
+			   MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+	intel_uncore_write(uncore, XELPMP_PAT_INDEX(4),
+			   MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+	/*
+	 * Remaining PAT entries are left at the hardware-default
+	 * fully-cached setting
+	 */
+}
+
+static void xelpg_setup_private_ppat(struct intel_gt *gt)
+{
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(0),
+				     MTL_PPAT_L4_0_WB);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(1),
+				     MTL_PPAT_L4_1_WT);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(2),
+				     MTL_PPAT_L4_3_UC);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(3),
+				     MTL_PPAT_L4_0_WB | MTL_2_COH_1W);
+	intel_gt_mcr_multicast_write(gt, XEHP_PAT_INDEX(4),
+				     MTL_PPAT_L4_0_WB | MTL_3_COH_2W);
+
+	/*
+	 * Remaining PAT entries are left at the hardware-default
+	 * fully-cached setting
+	 */
+}
+
 static void tgl_setup_private_ppat(struct intel_uncore *uncore)
 {
 	/* TGL doesn't support LLC or AGE settings */
@@ -603,7 +641,14 @@ void setup_private_pat(struct intel_gt *gt)
 
 	GEM_BUG_ON(GRAPHICS_VER(i915) < 8);
 
-	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
+	if (gt->type == GT_MEDIA) {
+		xelpmp_setup_private_ppat(gt->uncore);
+		return;
+	}
+
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70))
+		xelpg_setup_private_ppat(gt);
+	else if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 		xehp_setup_private_ppat(gt);
 	else if (GRAPHICS_VER(i915) >= 12)
 		tgl_setup_private_ppat(uncore);

drivers/gpu/drm/i915/gt/intel_gtt.h

@@ -88,9 +88,17 @@ typedef u64 gen8_pte_t;
 #define BYT_PTE_SNOOPED_BY_CPU_CACHES	REG_BIT(2)
 #define BYT_PTE_WRITEABLE		REG_BIT(1)
 
+#define MTL_PPGTT_PTE_PAT3	BIT_ULL(62)
 #define GEN12_PPGTT_PTE_LM	BIT_ULL(11)
+#define GEN12_PPGTT_PTE_PAT2	BIT_ULL(7)
+#define GEN12_PPGTT_PTE_PAT1	BIT_ULL(4)
+#define GEN12_PPGTT_PTE_PAT0	BIT_ULL(3)
 
-#define GEN12_GGTT_PTE_LM	BIT_ULL(1)
+#define GEN12_GGTT_PTE_LM		BIT_ULL(1)
+#define MTL_GGTT_PTE_PAT0		BIT_ULL(52)
+#define MTL_GGTT_PTE_PAT1		BIT_ULL(53)
+#define GEN12_GGTT_PTE_ADDR_MASK	GENMASK_ULL(45, 12)
+#define MTL_GGTT_PTE_PAT_MASK		GENMASK_ULL(53, 52)
 
 #define GEN12_PDE_64K BIT(6)
 #define GEN12_PTE_PS64 BIT(8)
@@ -147,7 +155,13 @@ typedef u64 gen8_pte_t;
 #define GEN8_PDE_IPS_64K BIT(11)
 #define GEN8_PDE_PS_2M   BIT(7)
 
-enum i915_cache_level;
+#define MTL_PPAT_L4_CACHE_POLICY_MASK	REG_GENMASK(3, 2)
+#define MTL_PAT_INDEX_COH_MODE_MASK	REG_GENMASK(1, 0)
+#define MTL_PPAT_L4_3_UC	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 3)
+#define MTL_PPAT_L4_1_WT	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 1)
+#define MTL_PPAT_L4_0_WB	REG_FIELD_PREP(MTL_PPAT_L4_CACHE_POLICY_MASK, 0)
+#define MTL_3_COH_2W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 3)
+#define MTL_2_COH_1W	REG_FIELD_PREP(MTL_PAT_INDEX_COH_MODE_MASK, 2)
 
 struct drm_i915_gem_object;
 struct i915_fence_reg;
@@ -216,7 +230,7 @@ struct i915_vma_ops {
 	void (*bind_vma)(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash,
 			 struct i915_vma_resource *vma_res,
-			 enum i915_cache_level cache_level,
+			 unsigned int pat_index,
 			 u32 flags);
 	/*
 	 * Unmap an object from an address space. This usually consists of
@@ -288,7 +302,7 @@ struct i915_address_space {
 		(*alloc_scratch_dma)(struct i915_address_space *vm, int sz);
 
 	u64 (*pte_encode)(dma_addr_t addr,
-			  enum i915_cache_level level,
+			  unsigned int pat_index,
 			  u32 flags); /* Create a valid PTE */
 #define PTE_READ_ONLY	BIT(0)
 #define PTE_LM		BIT(1)
@@ -303,20 +317,20 @@ struct i915_address_space {
 	void (*insert_page)(struct i915_address_space *vm,
 			    dma_addr_t addr,
 			    u64 offset,
-			    enum i915_cache_level cache_level,
+			    unsigned int pat_index,
 			    u32 flags);
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct i915_vma_resource *vma_res,
-			       enum i915_cache_level cache_level,
+			       unsigned int pat_index,
 			       u32 flags);
 	void (*raw_insert_page)(struct i915_address_space *vm,
 				dma_addr_t addr,
 				u64 offset,
-				enum i915_cache_level cache_level,
+				unsigned int pat_index,
 				u32 flags);
 	void (*raw_insert_entries)(struct i915_address_space *vm,
 				   struct i915_vma_resource *vma_res,
-				   enum i915_cache_level cache_level,
+				   unsigned int pat_index,
 				   u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
 
@@ -493,7 +507,7 @@ static inline void i915_vm_put(struct i915_address_space *vm)
 
 /**
  * i915_vm_resv_put - Release a reference on the vm's reservation lock
- * @resv: Pointer to a reservation lock obtained from i915_vm_resv_get()
+ * @vm: The vm whose reservation lock reference we want to release
  */
 static inline void i915_vm_resv_put(struct i915_address_space *vm)
 {
@@ -563,7 +577,7 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt,
 void intel_ggtt_bind_vma(struct i915_address_space *vm,
 			 struct i915_vm_pt_stash *stash,
 			 struct i915_vma_resource *vma_res,
-			 enum i915_cache_level cache_level,
+			 unsigned int pat_index,
 			 u32 flags);
 void intel_ggtt_unbind_vma(struct i915_address_space *vm,
 			   struct i915_vma_resource *vma_res);
@@ -641,7 +655,7 @@ void gen6_ggtt_invalidate(struct i915_ggtt *ggtt);
 void ppgtt_bind_vma(struct i915_address_space *vm,
 		    struct i915_vm_pt_stash *stash,
 		    struct i915_vma_resource *vma_res,
-		    enum i915_cache_level cache_level,
+		    unsigned int pat_index,
 		    u32 flags);
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma_resource *vma_res);

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -1370,7 +1370,9 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs)
 					      cs, GEN12_GFX_CCS_AUX_NV);
 
 	/* Wa_16014892111 */
-	if (IS_DG2(ce->engine->i915))
+	if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) ||
+	    IS_MTL_GRAPHICS_STEP(ce->engine->i915, P, STEP_A0, STEP_B0) ||
+	    IS_DG2(ce->engine->i915))
 		cs = dg2_emit_draw_watermark_setting(cs);
 
 	return cs;

drivers/gpu/drm/i915/gt/intel_migrate.c

@@ -45,7 +45,9 @@ static void xehpsdv_toggle_pdes(struct i915_address_space *vm,
 	 * Insert a dummy PTE into every PT that will map to LMEM to ensure
 	 * we have a correctly setup PDE structure for later use.
 	 */
-	vm->insert_page(vm, 0, d->offset, I915_CACHE_NONE, PTE_LM);
+	vm->insert_page(vm, 0, d->offset,
+			i915_gem_get_pat_index(vm->i915, I915_CACHE_NONE),
+			PTE_LM);
 	GEM_BUG_ON(!pt->is_compact);
 	d->offset += SZ_2M;
 }
@@ -63,7 +65,9 @@ static void xehpsdv_insert_pte(struct i915_address_space *vm,
 	 * alignment is 64K underneath for the pt, and we are careful
 	 * not to access the space in the void.
 	 */
-	vm->insert_page(vm, px_dma(pt), d->offset, I915_CACHE_NONE, PTE_LM);
+	vm->insert_page(vm, px_dma(pt), d->offset,
+			i915_gem_get_pat_index(vm->i915, I915_CACHE_NONE),
+			PTE_LM);
 	d->offset += SZ_64K;
 }
 
@@ -73,7 +77,8 @@ static void insert_pte(struct i915_address_space *vm,
 {
 	struct insert_pte_data *d = data;
 
-	vm->insert_page(vm, px_dma(pt), d->offset, I915_CACHE_NONE,
+	vm->insert_page(vm, px_dma(pt), d->offset,
+			i915_gem_get_pat_index(vm->i915, I915_CACHE_NONE),
 			i915_gem_object_is_lmem(pt->base) ? PTE_LM : 0);
 	d->offset += PAGE_SIZE;
 }
@@ -356,13 +361,13 @@ static int max_pte_pkt_size(struct i915_request *rq, int pkt)
 
 static int emit_pte(struct i915_request *rq,
 		    struct sgt_dma *it,
-		    enum i915_cache_level cache_level,
+		    unsigned int pat_index,
 		    bool is_lmem,
 		    u64 offset,
 		    int length)
 {
 	bool has_64K_pages = HAS_64K_PAGES(rq->engine->i915);
-	const u64 encode = rq->context->vm->pte_encode(0, cache_level,
+	const u64 encode = rq->context->vm->pte_encode(0, pat_index,
 						       is_lmem ? PTE_LM : 0);
 	struct intel_ring *ring = rq->ring;
 	int pkt, dword_length;
@@ -673,17 +678,17 @@ int
 intel_context_migrate_copy(struct intel_context *ce,
 			   const struct i915_deps *deps,
 			   struct scatterlist *src,
-			   enum i915_cache_level src_cache_level,
+			   unsigned int src_pat_index,
 			   bool src_is_lmem,
 			   struct scatterlist *dst,
-			   enum i915_cache_level dst_cache_level,
+			   unsigned int dst_pat_index,
 			   bool dst_is_lmem,
 			   struct i915_request **out)
 {
 	struct sgt_dma it_src = sg_sgt(src), it_dst = sg_sgt(dst), it_ccs;
 	struct drm_i915_private *i915 = ce->engine->i915;
 	u64 ccs_bytes_to_cpy = 0, bytes_to_cpy;
-	enum i915_cache_level ccs_cache_level;
+	unsigned int ccs_pat_index;
 	u32 src_offset, dst_offset;
 	u8 src_access, dst_access;
 	struct i915_request *rq;
@@ -707,12 +712,12 @@ intel_context_migrate_copy(struct intel_context *ce,
 		dst_sz = scatter_list_length(dst);
 		if (src_is_lmem) {
 			it_ccs = it_dst;
-			ccs_cache_level = dst_cache_level;
+			ccs_pat_index = dst_pat_index;
 			ccs_is_src = false;
 		} else if (dst_is_lmem) {
 			bytes_to_cpy = dst_sz;
 			it_ccs = it_src;
-			ccs_cache_level = src_cache_level;
+			ccs_pat_index = src_pat_index;
 			ccs_is_src = true;
 		}
 
@@ -773,7 +778,7 @@ intel_context_migrate_copy(struct intel_context *ce,
 		src_sz = calculate_chunk_sz(i915, src_is_lmem,
 					    bytes_to_cpy, ccs_bytes_to_cpy);
 
-		len = emit_pte(rq, &it_src, src_cache_level, src_is_lmem,
+		len = emit_pte(rq, &it_src, src_pat_index, src_is_lmem,
 			       src_offset, src_sz);
 		if (!len) {
 			err = -EINVAL;
@@ -784,7 +789,7 @@ intel_context_migrate_copy(struct intel_context *ce,
 			goto out_rq;
 		}
 
-		err = emit_pte(rq, &it_dst, dst_cache_level, dst_is_lmem,
+		err = emit_pte(rq, &it_dst, dst_pat_index, dst_is_lmem,
 			       dst_offset, len);
 		if (err < 0)
 			goto out_rq;
@@ -811,7 +816,7 @@ intel_context_migrate_copy(struct intel_context *ce,
 				goto out_rq;
 
 			ccs_sz = GET_CCS_BYTES(i915, len);
-			err = emit_pte(rq, &it_ccs, ccs_cache_level, false,
+			err = emit_pte(rq, &it_ccs, ccs_pat_index, false,
 				       ccs_is_src ? src_offset : dst_offset,
 				       ccs_sz);
 			if (err < 0)
@@ -920,7 +925,7 @@ static int emit_clear(struct i915_request *rq, u32 offset, int size,
 
 	GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
 
-	if (HAS_FLAT_CCS(i915) && ver >= 12)
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50))
 		ring_sz = XY_FAST_COLOR_BLT_DW;
 	else if (ver >= 8)
 		ring_sz = 8;
@@ -931,7 +936,7 @@ static int emit_clear(struct i915_request *rq, u32 offset, int size,
 	if (IS_ERR(cs))
 		return PTR_ERR(cs);
 
-	if (HAS_FLAT_CCS(i915) && ver >= 12) {
+	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
 		*cs++ = XY_FAST_COLOR_BLT_CMD | XY_FAST_COLOR_BLT_DEPTH_32 |
 			(XY_FAST_COLOR_BLT_DW - 2);
 		*cs++ = FIELD_PREP(XY_FAST_COLOR_BLT_MOCS_MASK, mocs) |
@@ -979,7 +984,7 @@ int
 intel_context_migrate_clear(struct intel_context *ce,
 			    const struct i915_deps *deps,
 			    struct scatterlist *sg,
-			    enum i915_cache_level cache_level,
+			    unsigned int pat_index,
 			    bool is_lmem,
 			    u32 value,
 			    struct i915_request **out)
@@ -1027,7 +1032,7 @@ intel_context_migrate_clear(struct intel_context *ce,
 		if (err)
 			goto out_rq;
 
-		len = emit_pte(rq, &it, cache_level, is_lmem, offset, CHUNK_SZ);
+		len = emit_pte(rq, &it, pat_index, is_lmem, offset, CHUNK_SZ);
 		if (len <= 0) {
 			err = len;
 			goto out_rq;
@@ -1074,10 +1079,10 @@ int intel_migrate_copy(struct intel_migrate *m,
 		       struct i915_gem_ww_ctx *ww,
 		       const struct i915_deps *deps,
 		       struct scatterlist *src,
-		       enum i915_cache_level src_cache_level,
+		       unsigned int src_pat_index,
 		       bool src_is_lmem,
 		       struct scatterlist *dst,
-		       enum i915_cache_level dst_cache_level,
+		       unsigned int dst_pat_index,
 		       bool dst_is_lmem,
 		       struct i915_request **out)
 {
@@ -1098,8 +1103,8 @@ int intel_migrate_copy(struct intel_migrate *m,
 		goto out;
 
 	err = intel_context_migrate_copy(ce, deps,
-					 src, src_cache_level, src_is_lmem,
-					 dst, dst_cache_level, dst_is_lmem,
+					 src, src_pat_index, src_is_lmem,
+					 dst, dst_pat_index, dst_is_lmem,
 					 out);
 
 	intel_context_unpin(ce);
@@ -1113,7 +1118,7 @@ intel_migrate_clear(struct intel_migrate *m,
 		    struct i915_gem_ww_ctx *ww,
 		    const struct i915_deps *deps,
 		    struct scatterlist *sg,
-		    enum i915_cache_level cache_level,
+		    unsigned int pat_index,
 		    bool is_lmem,
 		    u32 value,
 		    struct i915_request **out)
@@ -1134,7 +1139,7 @@ intel_migrate_clear(struct intel_migrate *m,
 	if (err)
 		goto out;
 
-	err = intel_context_migrate_clear(ce, deps, sg, cache_level,
+	err = intel_context_migrate_clear(ce, deps, sg, pat_index,
 					  is_lmem, value, out);
 
 	intel_context_unpin(ce);

drivers/gpu/drm/i915/gt/intel_migrate.h

@@ -16,7 +16,6 @@ struct i915_request;
 struct i915_gem_ww_ctx;
 struct intel_gt;
 struct scatterlist;
-enum i915_cache_level;
 
 int intel_migrate_init(struct intel_migrate *m, struct intel_gt *gt);
 
@@ -26,20 +25,20 @@ int intel_migrate_copy(struct intel_migrate *m,
 		       struct i915_gem_ww_ctx *ww,
 		       const struct i915_deps *deps,
 		       struct scatterlist *src,
-		       enum i915_cache_level src_cache_level,
+		       unsigned int src_pat_index,
 		       bool src_is_lmem,
 		       struct scatterlist *dst,
-		       enum i915_cache_level dst_cache_level,
+		       unsigned int dst_pat_index,
 		       bool dst_is_lmem,
 		       struct i915_request **out);
 
 int intel_context_migrate_copy(struct intel_context *ce,
 			       const struct i915_deps *deps,
 			       struct scatterlist *src,
-			       enum i915_cache_level src_cache_level,
+			       unsigned int src_pat_index,
 			       bool src_is_lmem,
 			       struct scatterlist *dst,
-			       enum i915_cache_level dst_cache_level,
+			       unsigned int dst_pat_index,
 			       bool dst_is_lmem,
 			       struct i915_request **out);
 
@@ -48,7 +47,7 @@ intel_migrate_clear(struct intel_migrate *m,
 		    struct i915_gem_ww_ctx *ww,
 		    const struct i915_deps *deps,
 		    struct scatterlist *sg,
-		    enum i915_cache_level cache_level,
+		    unsigned int pat_index,
 		    bool is_lmem,
 		    u32 value,
 		    struct i915_request **out);
@@ -56,7 +55,7 @@ int
 intel_context_migrate_clear(struct intel_context *ce,
 			    const struct i915_deps *deps,
 			    struct scatterlist *sg,
-			    enum i915_cache_level cache_level,
+			    unsigned int pat_index,
 			    bool is_lmem,
 			    u32 value,
 			    struct i915_request **out);

drivers/gpu/drm/i915/gt/intel_mocs.c

@@ -40,6 +40,10 @@ struct drm_i915_mocs_table {
 #define LE_COS(value)		((value) << 15)
 #define LE_SSE(value)		((value) << 17)
 
+/* Defines for the tables (GLOB_MOCS_0 - GLOB_MOCS_16) */
+#define _L4_CACHEABILITY(value)	((value) << 2)
+#define IG_PAT(value)		((value) << 8)
+
 /* Defines for the tables (LNCFMOCS0 - LNCFMOCS31) - two entries per word */
 #define L3_ESC(value)		((value) << 0)
 #define L3_SCC(value)		((value) << 1)
@@ -50,6 +54,7 @@ struct drm_i915_mocs_table {
 /* Helper defines */
 #define GEN9_NUM_MOCS_ENTRIES	64  /* 63-64 are reserved, but configured. */
 #define PVC_NUM_MOCS_ENTRIES	3
+#define MTL_NUM_MOCS_ENTRIES	16
 
 /* (e)LLC caching options */
 /*
@@ -73,6 +78,12 @@ struct drm_i915_mocs_table {
 #define L3_2_RESERVED		_L3_CACHEABILITY(2)
 #define L3_3_WB			_L3_CACHEABILITY(3)
 
+/* L4 caching options */
+#define L4_0_WB			_L4_CACHEABILITY(0)
+#define L4_1_WT			_L4_CACHEABILITY(1)
+#define L4_2_RESERVED		_L4_CACHEABILITY(2)
+#define L4_3_UC			_L4_CACHEABILITY(3)
+
 #define MOCS_ENTRY(__idx, __control_value, __l3cc_value) \
 	[__idx] = { \
 		.control_value = __control_value, \
@@ -416,6 +427,57 @@ static const struct drm_i915_mocs_entry pvc_mocs_table[] = {
 	MOCS_ENTRY(2, 0, L3_3_WB),
 };
 
+static const struct drm_i915_mocs_entry mtl_mocs_table[] = {
+	/* Error - Reserved for Non-Use */
+	MOCS_ENTRY(0,
+		   IG_PAT(0),
+		   L3_LKUP(1) | L3_3_WB),
+	/* Cached - L3 + L4 */
+	MOCS_ENTRY(1,
+		   IG_PAT(1),
+		   L3_LKUP(1) | L3_3_WB),
+	/* L4 - GO:L3 */
+	MOCS_ENTRY(2,
+		   IG_PAT(1),
+		   L3_LKUP(1) | L3_1_UC),
+	/* Uncached - GO:L3 */
+	MOCS_ENTRY(3,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_LKUP(1) | L3_1_UC),
+	/* L4 - GO:Mem */
+	MOCS_ENTRY(4,
+		   IG_PAT(1),
+		   L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+	/* Uncached - GO:Mem */
+	MOCS_ENTRY(5,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_LKUP(1) | L3_GLBGO(1) | L3_1_UC),
+	/* L4 - L3:NoLKUP; GO:L3 */
+	MOCS_ENTRY(6,
+		   IG_PAT(1),
+		   L3_1_UC),
+	/* Uncached - L3:NoLKUP; GO:L3 */
+	MOCS_ENTRY(7,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_1_UC),
+	/* L4 - L3:NoLKUP; GO:Mem */
+	MOCS_ENTRY(8,
+		   IG_PAT(1),
+		   L3_GLBGO(1) | L3_1_UC),
+	/* Uncached - L3:NoLKUP; GO:Mem */
+	MOCS_ENTRY(9,
+		   IG_PAT(1) | L4_3_UC,
+		   L3_GLBGO(1) | L3_1_UC),
+	/* Display - L3; L4:WT */
+	MOCS_ENTRY(14,
+		   IG_PAT(1) | L4_1_WT,
+		   L3_LKUP(1) | L3_3_WB),
+	/* CCS - Non-Displayable */
+	MOCS_ENTRY(15,
+		   IG_PAT(1),
+		   L3_GLBGO(1) | L3_1_UC),
+};
+
 enum {
 	HAS_GLOBAL_MOCS = BIT(0),
 	HAS_ENGINE_MOCS = BIT(1),
@@ -445,7 +507,13 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915,
 	memset(table, 0, sizeof(struct drm_i915_mocs_table));
 
 	table->unused_entries_index = I915_MOCS_PTE;
-	if (IS_PONTEVECCHIO(i915)) {
+	if (IS_METEORLAKE(i915)) {
+		table->size = ARRAY_SIZE(mtl_mocs_table);
+		table->table = mtl_mocs_table;
+		table->n_entries = MTL_NUM_MOCS_ENTRIES;
+		table->uc_index = 9;
+		table->unused_entries_index = 1;
+	} else if (IS_PONTEVECCHIO(i915)) {
 		table->size = ARRAY_SIZE(pvc_mocs_table);
 		table->table = pvc_mocs_table;
 		table->n_entries = PVC_NUM_MOCS_ENTRIES;

drivers/gpu/drm/i915/gt/intel_ppgtt.c

@@ -181,7 +181,7 @@ struct i915_ppgtt *i915_ppgtt_create(struct intel_gt *gt,
 void ppgtt_bind_vma(struct i915_address_space *vm,
 		    struct i915_vm_pt_stash *stash,
 		    struct i915_vma_resource *vma_res,
-		    enum i915_cache_level cache_level,
+		    unsigned int pat_index,
 		    u32 flags)
 {
 	u32 pte_flags;
@@ -199,7 +199,7 @@ void ppgtt_bind_vma(struct i915_address_space *vm,
 	if (vma_res->bi.lmem)
 		pte_flags |= PTE_LM;
 
-	vm->insert_entries(vm, vma_res, cache_level, pte_flags);
+	vm->insert_entries(vm, vma_res, pat_index, pte_flags);
 	wmb();
 }
 

drivers/gpu/drm/i915/gt/intel_rc6.c

@@ -53,11 +53,6 @@ static struct drm_i915_private *rc6_to_i915(struct intel_rc6 *rc)
 	return rc6_to_gt(rc)->i915;
 }
 
-static void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val)
-{
-	intel_uncore_write_fw(uncore, reg, val);
-}
-
 static void gen11_rc6_enable(struct intel_rc6 *rc6)
 {
 	struct intel_gt *gt = rc6_to_gt(rc6);
@@ -72,19 +67,19 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 	 */
 	if (!intel_uc_uses_guc_rc(&gt->uc)) {
 		/* 2b: Program RC6 thresholds.*/
-		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
-		set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
+		intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
+		intel_uncore_write_fw(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
 
-		set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-		set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+		intel_uncore_write_fw(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+		intel_uncore_write_fw(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 		for_each_engine(engine, rc6_to_gt(rc6), id)
-			set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+			intel_uncore_write_fw(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
-		set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
+		intel_uncore_write_fw(uncore, GUC_MAX_IDLE_COUNT, 0xA);
 
-		set(uncore, GEN6_RC_SLEEP, 0);
+		intel_uncore_write_fw(uncore, GEN6_RC_SLEEP, 0);
 
-		set(uncore, GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+		intel_uncore_write_fw(uncore, GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
 	}
 
 	/*
@@ -105,8 +100,8 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 	 * Broadwell+, To be conservative, we want to factor in a context
 	 * switch on top (due to ksoftirqd).
 	 */
-	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 60);
-	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 60);
+	intel_uncore_write_fw(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 60);
+	intel_uncore_write_fw(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 60);
 
 	/* 3a: Enable RC6
 	 *
@@ -122,8 +117,14 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 			GEN6_RC_CTL_RC6_ENABLE |
 			GEN6_RC_CTL_EI_MODE(1);
 
-	/* Wa_16011777198 - Render powergating must remain disabled */
-	if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
+	/*
+	 * Wa_16011777198 and BSpec 52698 - Render powergating must be off.
+	 * FIXME BSpec is outdated, disabling powergating for MTL is just
+	 * temporary wa and should be removed after fixing real cause
+	 * of forcewake timeouts.
+	 */
+	if (IS_METEORLAKE(gt->i915) ||
+	    IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) ||
 	    IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))
 		pg_enable =
 			GEN9_MEDIA_PG_ENABLE |
@@ -141,7 +142,7 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6)
 					      VDN_MFX_POWERGATE_ENABLE(i));
 	}
 
-	set(uncore, GEN9_PG_ENABLE, pg_enable);
+	intel_uncore_write_fw(uncore, GEN9_PG_ENABLE, pg_enable);
 }
 
 static void gen9_rc6_enable(struct intel_rc6 *rc6)
@@ -152,26 +153,26 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 
 	/* 2b: Program RC6 thresholds.*/
 	if (GRAPHICS_VER(rc6_to_i915(rc6)) >= 11) {
-		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
-		set(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
+		intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85);
+		intel_uncore_write_fw(uncore, GEN10_MEDIA_WAKE_RATE_LIMIT, 150);
 	} else if (IS_SKYLAKE(rc6_to_i915(rc6))) {
 		/*
 		 * WaRsDoubleRc6WrlWithCoarsePowerGating:skl Doubling WRL only
 		 * when CPG is enabled
 		 */
-		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
+		intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 108 << 16);
 	} else {
-		set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
+		intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16);
 	}
 
-	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+	intel_uncore_write_fw(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	intel_uncore_write_fw(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 	for_each_engine(engine, rc6_to_gt(rc6), id)
-		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+		intel_uncore_write_fw(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
-	set(uncore, GUC_MAX_IDLE_COUNT, 0xA);
+	intel_uncore_write_fw(uncore, GUC_MAX_IDLE_COUNT, 0xA);
 
-	set(uncore, GEN6_RC_SLEEP, 0);
+	intel_uncore_write_fw(uncore, GEN6_RC_SLEEP, 0);
 
 	/*
 	 * 2c: Program Coarse Power Gating Policies.
@@ -194,11 +195,11 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	 * conservative, we have to factor in a context switch on top (due
 	 * to ksoftirqd).
 	 */
-	set(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
-	set(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
+	intel_uncore_write_fw(uncore, GEN9_MEDIA_PG_IDLE_HYSTERESIS, 250);
+	intel_uncore_write_fw(uncore, GEN9_RENDER_PG_IDLE_HYSTERESIS, 250);
 
 	/* 3a: Enable RC6 */
-	set(uncore, GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
+	intel_uncore_write_fw(uncore, GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */
 
 	rc6->ctl_enable =
 		GEN6_RC_CTL_HW_ENABLE |
@@ -210,8 +211,8 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	 *   - Render/Media PG need to be disabled with RC6.
 	 */
 	if (!NEEDS_WaRsDisableCoarsePowerGating(rc6_to_i915(rc6)))
-		set(uncore, GEN9_PG_ENABLE,
-		    GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
+		intel_uncore_write_fw(uncore, GEN9_PG_ENABLE,
+				      GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
 }
 
 static void gen8_rc6_enable(struct intel_rc6 *rc6)
@@ -221,13 +222,13 @@ static void gen8_rc6_enable(struct intel_rc6 *rc6)
 	enum intel_engine_id id;
 
 	/* 2b: Program RC6 thresholds.*/
-	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
-	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+	intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+	intel_uncore_write_fw(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	intel_uncore_write_fw(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 	for_each_engine(engine, rc6_to_gt(rc6), id)
-		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
-	set(uncore, GEN6_RC_SLEEP, 0);
-	set(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
+		intel_uncore_write_fw(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+	intel_uncore_write_fw(uncore, GEN6_RC_SLEEP, 0);
+	intel_uncore_write_fw(uncore, GEN6_RC6_THRESHOLD, 625); /* 800us/1.28 for TO */
 
 	/* 3: Enable RC6 */
 	rc6->ctl_enable =
@@ -245,20 +246,20 @@ static void gen6_rc6_enable(struct intel_rc6 *rc6)
 	u32 rc6vids, rc6_mask;
 	int ret;
 
-	set(uncore, GEN6_RC1_WAKE_RATE_LIMIT, 1000 << 16);
-	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16 | 30);
-	set(uncore, GEN6_RC6pp_WAKE_RATE_LIMIT, 30);
-	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
-	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
+	intel_uncore_write_fw(uncore, GEN6_RC1_WAKE_RATE_LIMIT, 1000 << 16);
+	intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16 | 30);
+	intel_uncore_write_fw(uncore, GEN6_RC6pp_WAKE_RATE_LIMIT, 30);
+	intel_uncore_write_fw(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
+	intel_uncore_write_fw(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
 
 	for_each_engine(engine, rc6_to_gt(rc6), id)
-		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+		intel_uncore_write_fw(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
-	set(uncore, GEN6_RC_SLEEP, 0);
-	set(uncore, GEN6_RC1e_THRESHOLD, 1000);
-	set(uncore, GEN6_RC6_THRESHOLD, 50000);
-	set(uncore, GEN6_RC6p_THRESHOLD, 150000);
-	set(uncore, GEN6_RC6pp_THRESHOLD, 64000); /* unused */
+	intel_uncore_write_fw(uncore, GEN6_RC_SLEEP, 0);
+	intel_uncore_write_fw(uncore, GEN6_RC1e_THRESHOLD, 1000);
+	intel_uncore_write_fw(uncore, GEN6_RC6_THRESHOLD, 50000);
+	intel_uncore_write_fw(uncore, GEN6_RC6p_THRESHOLD, 150000);
+	intel_uncore_write_fw(uncore, GEN6_RC6pp_THRESHOLD, 64000); /* unused */
 
 	/* We don't use those on Haswell */
 	rc6_mask = GEN6_RC_CTL_RC6_ENABLE;
@@ -372,22 +373,22 @@ static void chv_rc6_enable(struct intel_rc6 *rc6)
 	enum intel_engine_id id;
 
 	/* 2a: Program RC6 thresholds.*/
-	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
-	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
-	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+	intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+	intel_uncore_write_fw(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	intel_uncore_write_fw(uncore, GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
 
 	for_each_engine(engine, rc6_to_gt(rc6), id)
-		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
-	set(uncore, GEN6_RC_SLEEP, 0);
+		intel_uncore_write_fw(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+	intel_uncore_write_fw(uncore, GEN6_RC_SLEEP, 0);
 
 	/* TO threshold set to 500 us (0x186 * 1.28 us) */
-	set(uncore, GEN6_RC6_THRESHOLD, 0x186);
+	intel_uncore_write_fw(uncore, GEN6_RC6_THRESHOLD, 0x186);
 
 	/* Allows RC6 residency counter to work */
-	set(uncore, VLV_COUNTER_CONTROL,
-	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
-			       VLV_MEDIA_RC6_COUNT_EN |
-			       VLV_RENDER_RC6_COUNT_EN));
+	intel_uncore_write_fw(uncore, VLV_COUNTER_CONTROL,
+			      _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+						 VLV_MEDIA_RC6_COUNT_EN |
+						 VLV_RENDER_RC6_COUNT_EN));
 
 	/* 3: Enable RC6 */
 	rc6->ctl_enable = GEN7_RC_CTL_TO_MODE;
@@ -399,22 +400,22 @@ static void vlv_rc6_enable(struct intel_rc6 *rc6)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
-	set(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
-	set(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
+	intel_uncore_write_fw(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 0x00280000);
+	intel_uncore_write_fw(uncore, GEN6_RC_EVALUATION_INTERVAL, 125000);
+	intel_uncore_write_fw(uncore, GEN6_RC_IDLE_HYSTERSIS, 25);
 
 	for_each_engine(engine, rc6_to_gt(rc6), id)
-		set(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
+		intel_uncore_write_fw(uncore, RING_MAX_IDLE(engine->mmio_base), 10);
 
-	set(uncore, GEN6_RC6_THRESHOLD, 0x557);
+	intel_uncore_write_fw(uncore, GEN6_RC6_THRESHOLD, 0x557);
 
 	/* Allows RC6 residency counter to work */
-	set(uncore, VLV_COUNTER_CONTROL,
-	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
-			       VLV_MEDIA_RC0_COUNT_EN |
-			       VLV_RENDER_RC0_COUNT_EN |
-			       VLV_MEDIA_RC6_COUNT_EN |
-			       VLV_RENDER_RC6_COUNT_EN));
+	intel_uncore_write_fw(uncore, VLV_COUNTER_CONTROL,
+			      _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+						 VLV_MEDIA_RC0_COUNT_EN |
+						 VLV_RENDER_RC0_COUNT_EN |
+						 VLV_MEDIA_RC6_COUNT_EN |
+						 VLV_RENDER_RC6_COUNT_EN));
 
 	rc6->ctl_enable =
 	    GEN7_RC_CTL_TO_MODE | VLV_RC_CTL_CTX_RST_PARALLEL;
@@ -575,9 +576,9 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6)
 
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 	if (GRAPHICS_VER(i915) >= 9)
-		set(uncore, GEN9_PG_ENABLE, 0);
-	set(uncore, GEN6_RC_CONTROL, 0);
-	set(uncore, GEN6_RC_STATE, 0);
+		intel_uncore_write_fw(uncore, GEN9_PG_ENABLE, 0);
+	intel_uncore_write_fw(uncore, GEN6_RC_CONTROL, 0);
+	intel_uncore_write_fw(uncore, GEN6_RC_STATE, 0);
 	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
 }
 
@@ -684,7 +685,7 @@ void intel_rc6_unpark(struct intel_rc6 *rc6)
 		return;
 
 	/* Restore HW timers for automatic RC6 entry while busy */
-	set(uncore, GEN6_RC_CONTROL, rc6->ctl_enable);
+	intel_uncore_write_fw(uncore, GEN6_RC_CONTROL, rc6->ctl_enable);
 }
 
 void intel_rc6_park(struct intel_rc6 *rc6)
@@ -704,7 +705,7 @@ void intel_rc6_park(struct intel_rc6 *rc6)
 		return;
 
 	/* Turn off the HW timers and go directly to rc6 */
-	set(uncore, GEN6_RC_CONTROL, GEN6_RC_CTL_RC6_ENABLE);
+	intel_uncore_write_fw(uncore, GEN6_RC_CONTROL, GEN6_RC_CTL_RC6_ENABLE);
 
 	if (HAS_RC6pp(rc6_to_i915(rc6)))
 		target = 0x6; /* deepest rc6 */
@@ -712,7 +713,7 @@ void intel_rc6_park(struct intel_rc6 *rc6)
 		target = 0x5; /* deep rc6 */
 	else
 		target = 0x4; /* normal rc6 */
-	set(uncore, GEN6_RC_STATE, target << RC_SW_TARGET_STATE_SHIFT);
+	intel_uncore_write_fw(uncore, GEN6_RC_STATE, target << RC_SW_TARGET_STATE_SHIFT);
 }
 
 void intel_rc6_disable(struct intel_rc6 *rc6)
@@ -735,7 +736,7 @@ void intel_rc6_fini(struct intel_rc6 *rc6)
 
 	/* We want the BIOS C6 state preserved across loads for MTL */
 	if (IS_METEORLAKE(rc6_to_i915(rc6)) && rc6->bios_state_captured)
-		set(uncore, GEN6_RC_STATE, rc6->bios_rc_state);
+		intel_uncore_write_fw(uncore, GEN6_RC_STATE, rc6->bios_rc_state);
 
 	pctx = fetch_and_zero(&rc6->pctx);
 	if (pctx)
@@ -766,18 +767,18 @@ static u64 vlv_residency_raw(struct intel_uncore *uncore, const i915_reg_t reg)
 	 * before we have set the default VLV_COUNTER_CONTROL value. So always
 	 * set the high bit to be safe.
 	 */
-	set(uncore, VLV_COUNTER_CONTROL,
-	    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
+	intel_uncore_write_fw(uncore, VLV_COUNTER_CONTROL,
+			      _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
 	upper = intel_uncore_read_fw(uncore, reg);
 	do {
 		tmp = upper;
 
-		set(uncore, VLV_COUNTER_CONTROL,
-		    _MASKED_BIT_DISABLE(VLV_COUNT_RANGE_HIGH));
+		intel_uncore_write_fw(uncore, VLV_COUNTER_CONTROL,
+				      _MASKED_BIT_DISABLE(VLV_COUNT_RANGE_HIGH));
 		lower = intel_uncore_read_fw(uncore, reg);
 
-		set(uncore, VLV_COUNTER_CONTROL,
-		    _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
+		intel_uncore_write_fw(uncore, VLV_COUNTER_CONTROL,
+				      _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH));
 		upper = intel_uncore_read_fw(uncore, reg);
 	} while (upper != tmp && --loop);
 

drivers/gpu/drm/i915/gt/intel_workarounds.c

@@ -812,11 +812,25 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
 	wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE);
 }
 
+static void mtl_ctx_gt_tuning_init(struct intel_engine_cs *engine,
+				   struct i915_wa_list *wal)
+{
+	struct drm_i915_private *i915 = engine->i915;
+
+	dg2_ctx_gt_tuning_init(engine, wal);
+
+	if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_B0, STEP_FOREVER) ||
+	    IS_MTL_GRAPHICS_STEP(i915, P, STEP_B0, STEP_FOREVER))
+		wa_add(wal, DRAW_WATERMARK, VERT_WM_VAL, 0x3FF, 0, false);
+}
+
 static void mtl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
+	mtl_ctx_gt_tuning_init(engine, wal);
+
 	if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) ||
 	    IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) {
 		/* Wa_14014947963 */
@@ -1695,14 +1709,20 @@ pvc_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 static void
 xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 {
+	/* Wa_14018778641 / Wa_18018781329 */
+	wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
+	wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
+
+	/* Wa_22016670082 */
+	wa_write_or(wal, GEN12_SQCNT1, GEN12_STRICT_RAR_ENABLE);
+
 	if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) ||
 	    IS_MTL_GRAPHICS_STEP(gt->i915, P, STEP_A0, STEP_B0)) {
 		/* Wa_14014830051 */
 		wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN);
 
-		/* Wa_18018781329 */
-		wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB);
-		wa_mcr_write_or(wal, COMP_MOD_CTRL, FORCE_MISS_FTLB);
+		/* Wa_14015795083 */
+		wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE);
 	}
 
 	/*
@@ -1715,17 +1735,16 @@ xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 static void
 xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 {
-	if (IS_MTL_MEDIA_STEP(gt->i915, STEP_A0, STEP_B0)) {
-		/*
-		 * Wa_18018781329
-		 *
-		 * Note that although these registers are MCR on the primary
-		 * GT, the media GT's versions are regular singleton registers.
-		 */
-		wa_write_or(wal, XELPMP_GSC_MOD_CTRL, FORCE_MISS_FTLB);
-		wa_write_or(wal, XELPMP_VDBX_MOD_CTRL, FORCE_MISS_FTLB);
-		wa_write_or(wal, XELPMP_VEBX_MOD_CTRL, FORCE_MISS_FTLB);
-	}
+	/*
+	 * Wa_14018778641
+	 * Wa_18018781329
+	 *
+	 * Note that although these registers are MCR on the primary
+	 * GT, the media GT's versions are regular singleton registers.
+	 */
+	wa_write_or(wal, XELPMP_GSC_MOD_CTRL, FORCE_MISS_FTLB);
+	wa_write_or(wal, XELPMP_VDBX_MOD_CTRL, FORCE_MISS_FTLB);
+	wa_write_or(wal, XELPMP_VEBX_MOD_CTRL, FORCE_MISS_FTLB);
 
 	debug_dump_steering(gt);
 }
@@ -1743,6 +1762,13 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
  */
 static void gt_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal)
 {
+	if (IS_METEORLAKE(gt->i915)) {
+		if (gt->type != GT_MEDIA)
+			wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
+
+		wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS);
+	}
+
 	if (IS_PONTEVECCHIO(gt->i915)) {
 		wa_mcr_write(wal, XEHPC_L3SCRUB,
 			     SCRUB_CL_DWNGRADE_SHARED | SCRUB_RATE_4B_PER_CLK);
@@ -2939,7 +2965,7 @@ static void
 add_render_compute_tuning_settings(struct drm_i915_private *i915,
 				   struct i915_wa_list *wal)
 {
-	if (IS_DG2(i915))
+	if (IS_METEORLAKE(i915) || IS_DG2(i915))
 		wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512);
 
 	/*

drivers/gpu/drm/i915/gt/selftest_engine_pm.c

@@ -5,6 +5,7 @@
 
 #include <linux/sort.h>
 
+#include "gt/intel_gt_print.h"
 #include "i915_selftest.h"
 #include "intel_engine_regs.h"
 #include "intel_gpu_commands.h"
@@ -402,7 +403,7 @@ static int live_engine_pm(void *arg)
 
 			/* gt wakeref is async (deferred to workqueue) */
 			if (intel_gt_pm_wait_for_idle(gt)) {
-				pr_err("GT failed to idle\n");
+				gt_err(gt, "GT failed to idle\n");
 				return -EINVAL;
 			}
 		}

drivers/gpu/drm/i915/gt/selftest_migrate.c

@@ -137,7 +137,7 @@ err_free_src:
 static int intel_context_copy_ccs(struct intel_context *ce,
 				  const struct i915_deps *deps,
 				  struct scatterlist *sg,
-				  enum i915_cache_level cache_level,
+				  unsigned int pat_index,
 				  bool write_to_ccs,
 				  struct i915_request **out)
 {
@@ -185,7 +185,7 @@ static int intel_context_copy_ccs(struct intel_context *ce,
 		if (err)
 			goto out_rq;
 
-		len = emit_pte(rq, &it, cache_level, true, offset, CHUNK_SZ);
+		len = emit_pte(rq, &it, pat_index, true, offset, CHUNK_SZ);
 		if (len <= 0) {
 			err = len;
 			goto out_rq;
@@ -223,7 +223,7 @@ intel_migrate_ccs_copy(struct intel_migrate *m,
 		       struct i915_gem_ww_ctx *ww,
 		       const struct i915_deps *deps,
 		       struct scatterlist *sg,
-		       enum i915_cache_level cache_level,
+		       unsigned int pat_index,
 		       bool write_to_ccs,
 		       struct i915_request **out)
 {
@@ -243,7 +243,7 @@ intel_migrate_ccs_copy(struct intel_migrate *m,
 	if (err)
 		goto out;
 
-	err = intel_context_copy_ccs(ce, deps, sg, cache_level,
+	err = intel_context_copy_ccs(ce, deps, sg, pat_index,
 				     write_to_ccs, out);
 
 	intel_context_unpin(ce);
@@ -300,7 +300,7 @@ static int clear(struct intel_migrate *migrate,
 			/* Write the obj data into ccs surface */
 			err = intel_migrate_ccs_copy(migrate, &ww, NULL,
 						     obj->mm.pages->sgl,
-						     obj->cache_level,
+						     obj->pat_index,
 						     true, &rq);
 			if (rq && !err) {
 				if (i915_request_wait(rq, 0, HZ) < 0) {
@@ -351,7 +351,7 @@ static int clear(struct intel_migrate *migrate,
 
 			err = intel_migrate_ccs_copy(migrate, &ww, NULL,
 						     obj->mm.pages->sgl,
-						     obj->cache_level,
+						     obj->pat_index,
 						     false, &rq);
 			if (rq && !err) {
 				if (i915_request_wait(rq, 0, HZ) < 0) {
@@ -414,9 +414,9 @@ static int __migrate_copy(struct intel_migrate *migrate,
 			  struct i915_request **out)
 {
 	return intel_migrate_copy(migrate, ww, NULL,
-				  src->mm.pages->sgl, src->cache_level,
+				  src->mm.pages->sgl, src->pat_index,
 				  i915_gem_object_is_lmem(src),
-				  dst->mm.pages->sgl, dst->cache_level,
+				  dst->mm.pages->sgl, dst->pat_index,
 				  i915_gem_object_is_lmem(dst),
 				  out);
 }
@@ -428,9 +428,9 @@ static int __global_copy(struct intel_migrate *migrate,
 			 struct i915_request **out)
 {
 	return intel_context_migrate_copy(migrate->context, NULL,
-					  src->mm.pages->sgl, src->cache_level,
+					  src->mm.pages->sgl, src->pat_index,
 					  i915_gem_object_is_lmem(src),
-					  dst->mm.pages->sgl, dst->cache_level,
+					  dst->mm.pages->sgl, dst->pat_index,
 					  i915_gem_object_is_lmem(dst),
 					  out);
 }
@@ -455,7 +455,7 @@ static int __migrate_clear(struct intel_migrate *migrate,
 {
 	return intel_migrate_clear(migrate, ww, NULL,
 				   obj->mm.pages->sgl,
-				   obj->cache_level,
+				   obj->pat_index,
 				   i915_gem_object_is_lmem(obj),
 				   value, out);
 }
@@ -468,7 +468,7 @@ static int __global_clear(struct intel_migrate *migrate,
 {
 	return intel_context_migrate_clear(migrate->context, NULL,
 					   obj->mm.pages->sgl,
-					   obj->cache_level,
+					   obj->pat_index,
 					   i915_gem_object_is_lmem(obj),
 					   value, out);
 }
@@ -648,7 +648,7 @@ static int live_emit_pte_full_ring(void *arg)
 	 */
 	pr_info("%s emite_pte ring space=%u\n", __func__, rq->ring->space);
 	it = sg_sgt(obj->mm.pages->sgl);
-	len = emit_pte(rq, &it, obj->cache_level, false, 0, CHUNK_SZ);
+	len = emit_pte(rq, &it, obj->pat_index, false, 0, CHUNK_SZ);
 	if (!len) {
 		err = -EINVAL;
 		goto out_rq;
@@ -844,7 +844,7 @@ static int wrap_ktime_compare(const void *A, const void *B)
 
 static int __perf_clear_blt(struct intel_context *ce,
 			    struct scatterlist *sg,
-			    enum i915_cache_level cache_level,
+			    unsigned int pat_index,
 			    bool is_lmem,
 			    size_t sz)
 {
@@ -858,7 +858,7 @@ static int __perf_clear_blt(struct intel_context *ce,
 
 		t0 = ktime_get();
 
-		err = intel_context_migrate_clear(ce, NULL, sg, cache_level,
+		err = intel_context_migrate_clear(ce, NULL, sg, pat_index,
 						  is_lmem, 0, &rq);
 		if (rq) {
 			if (i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT) < 0)
@@ -904,7 +904,8 @@ static int perf_clear_blt(void *arg)
 
 		err = __perf_clear_blt(gt->migrate.context,
 				       dst->mm.pages->sgl,
-				       I915_CACHE_NONE,
+				       i915_gem_get_pat_index(gt->i915,
+							      I915_CACHE_NONE),
 				       i915_gem_object_is_lmem(dst),
 				       sizes[i]);
 
@@ -919,10 +920,10 @@ static int perf_clear_blt(void *arg)
 
 static int __perf_copy_blt(struct intel_context *ce,
 			   struct scatterlist *src,
-			   enum i915_cache_level src_cache_level,
+			   unsigned int src_pat_index,
 			   bool src_is_lmem,
 			   struct scatterlist *dst,
-			   enum i915_cache_level dst_cache_level,
+			   unsigned int dst_pat_index,
 			   bool dst_is_lmem,
 			   size_t sz)
 {
@@ -937,9 +938,9 @@ static int __perf_copy_blt(struct intel_context *ce,
 		t0 = ktime_get();
 
 		err = intel_context_migrate_copy(ce, NULL,
-						 src, src_cache_level,
+						 src, src_pat_index,
 						 src_is_lmem,
-						 dst, dst_cache_level,
+						 dst, dst_pat_index,
 						 dst_is_lmem,
 						 &rq);
 		if (rq) {
@@ -994,10 +995,12 @@ static int perf_copy_blt(void *arg)
 
 		err = __perf_copy_blt(gt->migrate.context,
 				      src->mm.pages->sgl,
-				      I915_CACHE_NONE,
+				      i915_gem_get_pat_index(gt->i915,
+							     I915_CACHE_NONE),
 				      i915_gem_object_is_lmem(src),
 				      dst->mm.pages->sgl,
-				      I915_CACHE_NONE,
+				      i915_gem_get_pat_index(gt->i915,
+							     I915_CACHE_NONE),
 				      i915_gem_object_is_lmem(dst),
 				      sz);
 

drivers/gpu/drm/i915/gt/selftest_mocs.c

@@ -131,13 +131,14 @@ static int read_mocs_table(struct i915_request *rq,
 			   const struct drm_i915_mocs_table *table,
 			   u32 *offset)
 {
+	struct intel_gt *gt = rq->engine->gt;
 	u32 addr;
 
 	if (!table)
 		return 0;
 
 	if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915))
-		addr = global_mocs_offset();
+		addr = global_mocs_offset() + gt->uncore->gsi_offset;
 	else
 		addr = mocs_offset(rq->engine);