Merge tag 'v6.11-rc5' into android-mainline

Linux 6.11-rc5 Signed-off-by: Lee Jones <joneslee@google.com> Change-Id: I636ad79a57de4da27ea1c3bb8e91b864dab35c57
2024-09-02 07:27:06 +01:00
parent 8e0dce3251 5be63fc19f
commit c005598f8f
260 changed files with 3123 additions and 1229 deletions
@@ -260,7 +260,7 @@ Some users depend on strict execution ordering where only one work item
 is in flight at any given time and the work items are processed in
 queueing order. While the combination of ``@max_active`` of 1 and
 ``WQ_UNBOUND`` used to achieve this behavior, this is no longer the
-case. Use ``alloc_ordered_queue()`` instead.
+case. Use alloc_ordered_workqueue() instead.


 Example Execution Scenarios
@@ -42,6 +42,7 @@ properties:
      - focaltech,ft5426
      - focaltech,ft5452
      - focaltech,ft6236
+      - focaltech,ft8201
      - focaltech,ft8719

  reg:
@@ -75,7 +75,7 @@ Here are the main features of EROFS:

 - Support merging tail-end data into a special inode as fragments.

- - Support large folios for uncompressed files.
+ - Support large folios to make use of THPs (Transparent Hugepages);

 - Support direct I/O on uncompressed files to avoid double caching for loop
   devices;
@@ -13,7 +13,7 @@ KSMBD architecture
 The subset of performance related operations belong in kernelspace and
 the other subset which belong to operations which are not really related with
 performance in userspace. So, DCE/RPC management that has historically resulted
-into number of buffer overflow issues and dangerous security bugs and user
+into a number of buffer overflow issues and dangerous security bugs and user
 account management are implemented in user space as ksmbd.mountd.
 File operations that are related with performance (open/read/write/close etc.)
 in kernel space (ksmbd). This also allows for easier integration with VFS
@@ -24,8 +24,8 @@ ksmbd (kernel daemon)

 When the server daemon is started, It starts up a forker thread
 (ksmbd/interface name) at initialization time and open a dedicated port 445
-for listening to SMB requests. Whenever new clients make request, Forker
-thread will accept the client connection and fork a new thread for dedicated
+for listening to SMB requests. Whenever new clients make a request, the Forker
+thread will accept the client connection and fork a new thread for a dedicated
 communication channel between the client and the server. It allows for parallel
 processing of SMB requests(commands) from clients as well as allowing for new
 clients to make new connections. Each instance is named ksmbd/1~n(port number)
@@ -34,12 +34,12 @@ thread can decide to pass through the commands to the user space (ksmbd.mountd),
 currently DCE/RPC commands are identified to be handled through the user space.
 To further utilize the linux kernel, it has been chosen to process the commands
 as workitems and to be executed in the handlers of the ksmbd-io kworker threads.
-It allows for multiplexing of the handlers as the kernel take care of initiating
+It allows for multiplexing of the handlers as the kernel takes care of initiating
 extra worker threads if the load is increased and vice versa, if the load is
-decreased it destroys the extra worker threads. So, after connection is
-established with client. Dedicated ksmbd/1..n(port number) takes complete
+decreased it destroys the extra worker threads. So, after the connection is
+established with the client. Dedicated ksmbd/1..n(port number) takes complete
 ownership of receiving/parsing of SMB commands. Each received command is worked
-in parallel i.e., There can be multiple clients commands which are worked in
+in parallel i.e., there can be multiple client commands which are worked in
 parallel. After receiving each command a separated kernel workitem is prepared
 for each command which is further queued to be handled by ksmbd-io kworkers.
 So, each SMB workitem is queued to the kworkers. This allows the benefit of load
@@ -49,9 +49,9 @@ performance by handling client commands in parallel.
 ksmbd.mountd (user space daemon)
 --------------------------------

-ksmbd.mountd is userspace process to, transfer user account and password that
+ksmbd.mountd is a userspace process to, transfer the user account and password that
 are registered using ksmbd.adduser (part of utils for user space). Further it
-allows sharing information parameters that parsed from smb.conf to ksmbd in
+allows sharing information parameters that are parsed from smb.conf to ksmbd in
 kernel. For the execution part it has a daemon which is continuously running
 and connected to the kernel interface using netlink socket, it waits for the
 requests (dcerpc and share/user info). It handles RPC calls (at a minimum few
@@ -124,7 +124,7 @@ How to run
 1. Download ksmbd-tools(https://github.com/cifsd-team/ksmbd-tools/releases) and
   compile them.

-   - Refer README(https://github.com/cifsd-team/ksmbd-tools/blob/master/README.md)
+   - Refer to README(https://github.com/cifsd-team/ksmbd-tools/blob/master/README.md)
     to know how to use ksmbd.mountd/adduser/addshare/control utils

     $ ./autogen.sh
@@ -133,7 +133,7 @@ How to run

 2. Create /usr/local/etc/ksmbd/ksmbd.conf file, add SMB share in ksmbd.conf file.

-   - Refer ksmbd.conf.example in ksmbd-utils, See ksmbd.conf manpage
+   - Refer to ksmbd.conf.example in ksmbd-utils, See ksmbd.conf manpage
     for details to configure shares.

        $ man ksmbd.conf
@@ -145,7 +145,7 @@ How to run
     $ man ksmbd.adduser
     $ sudo ksmbd.adduser -a <Enter USERNAME for SMB share access>

-4. Insert ksmbd.ko module after build your kernel. No need to load module
+4. Insert the ksmbd.ko module after you build your kernel. No need to load the module
   if ksmbd is built into the kernel.

   - Set ksmbd in menuconfig(e.g. $ make menuconfig)
@@ -175,7 +175,7 @@ Each layer
 1. Enable all component prints
 	# sudo ksmbd.control -d "all"

-2. Enable one of components (smb, auth, vfs, oplock, ipc, conn, rdma)
+2. Enable one of the components (smb, auth, vfs, oplock, ipc, conn, rdma)
 	# sudo ksmbd.control -d "smb"

 3. Show what prints are enabled.
@@ -126,7 +126,7 @@ Ccache

 ``ccache`` can be used with ``clang`` to improve subsequent builds, (though
 KBUILD_BUILD_TIMESTAMP_ should be set to a deterministic value between builds
-in order to avoid 100% cache misses, see Reproducible_builds_ for more info):
+in order to avoid 100% cache misses, see Reproducible_builds_ for more info)::

 	KBUILD_BUILD_TIMESTAMP='' make LLVM=1 CC="ccache clang"

@@ -3504,7 +3504,9 @@ S:	Maintained
 W:	http://linux-atm.sourceforge.net
 F:	drivers/atm/
 F:	include/linux/atm*
+F:	include/linux/sonet.h
 F:	include/uapi/linux/atm*
+F:	include/uapi/linux/sonet.h

 ATMEL MACB ETHERNET DRIVER
 M:	Nicolas Ferre <nicolas.ferre@microchip.com>
@@ -10173,7 +10175,7 @@ F:	Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
 F:	drivers/infiniband/hw/hns/

 HISILICON SAS Controller
-M:	Xiang Chen <chenxiang66@hisilicon.com>
+M:	Yihang Li <liyihang9@huawei.com>
 S:	Supported
 W:	http://www.hisilicon.com
 F:	Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
@@ -12000,7 +12002,7 @@ F:	fs/jfs/
 JME NETWORK DRIVER
 M:	Guo-Fu Tseng <cooldavid@cooldavid.org>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/net/ethernet/jme.*

 JOURNALLING FLASH FILE SYSTEM V2 (JFFS2)
@@ -15884,15 +15886,19 @@ F:	drivers/net/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
+F:	include/linux/ethtool_netlink.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
 F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
-F:	include/linux/netdevice.h
+F:	include/linux/netdev*
+F:	include/linux/platform_data/wiznet.h
 F:	include/uapi/linux/cn_proc.h
+F:	include/uapi/linux/ethtool_netlink.h
 F:	include/uapi/linux/if_*
-F:	include/uapi/linux/netdevice.h
+F:	include/uapi/linux/netdev*
+F:	tools/testing/selftests/drivers/net/
 X:	drivers/net/wireless/

 NETWORKING DRIVERS (WIRELESS)
@@ -15943,14 +15949,28 @@ F:	include/linux/framer/framer-provider.h
 F:	include/linux/framer/framer.h
 F:	include/linux/in.h
 F:	include/linux/indirect_call_wrapper.h
+F:	include/linux/inet.h
+F:	include/linux/inet_diag.h
 F:	include/linux/net.h
-F:	include/linux/netdevice.h
-F:	include/linux/skbuff.h
+F:	include/linux/netdev*
+F:	include/linux/netlink.h
+F:	include/linux/netpoll.h
+F:	include/linux/rtnetlink.h
+F:	include/linux/seq_file_net.h
+F:	include/linux/skbuff*
 F:	include/net/
+F:	include/uapi/linux/genetlink.h
+F:	include/uapi/linux/hsr_netlink.h
 F:	include/uapi/linux/in.h
+F:	include/uapi/linux/inet_diag.h
+F:	include/uapi/linux/nbd-netlink.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/net_namespace.h
-F:	include/uapi/linux/netdevice.h
+F:	include/uapi/linux/netconf.h
+F:	include/uapi/linux/netdev*
+F:	include/uapi/linux/netlink.h
+F:	include/uapi/linux/netlink_diag.h
+F:	include/uapi/linux/rtnetlink.h
 F:	lib/net_utils.c
 F:	lib/random32.c
 F:	net/
@@ -20361,6 +20381,7 @@ F:	Documentation/devicetree/bindings/scsi/
 F:	drivers/scsi/
 F:	drivers/ufs/
 F:	include/scsi/
+F:	include/uapi/scsi/

 SCSI TAPE DRIVER
 M:	Kai Mäkisara <Kai.Makisara@kolumbus.fi>
@@ -21061,6 +21082,7 @@ SOCKET TIMESTAMPING
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
 S:	Maintained
 F:	Documentation/networking/timestamping.rst
+F:	include/linux/net_tstamp.h
 F:	include/uapi/linux/net_tstamp.h
 F:	tools/testing/selftests/net/so_txtime.c

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse

 # *DOCUMENTATION*
@@ -2026,7 +2026,7 @@ nsdeps: modules
 quiet_cmd_gen_compile_commands = GEN     $@
      cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs))

-$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \
+$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \
 	$(if $(KBUILD_EXTMOD)$(KBUILD_MIXED_TREE),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \
 	$(if $(CONFIG_MODULES), $(MODORDER)) FORCE
 	$(call if_changed,gen_compile_commands)
@@ -1540,8 +1540,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_pagesize = min(vma_pagesize, (long)max_map_size);
 	}

-	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE)
+	/*
+	 * Both the canonical IPA and fault IPA must be hugepage-aligned to
+	 * ensure we find the right PFN and lay down the mapping in the right
+	 * place.
+	 */
+	if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) {
 		fault_ipa &= ~(vma_pagesize - 1);
+		ipa &= ~(vma_pagesize - 1);
+	}

 	gfn = ipa >> PAGE_SHIFT;
 	mte_allowed = kvm_vma_mte_allowed(vma);
@@ -33,6 +33,7 @@
 #include <trace/events/kvm.h>

 #include "sys_regs.h"
+#include "vgic/vgic.h"

 #include "trace.h"

@@ -435,6 +436,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 {
 	bool g1;

+	if (!kvm_has_gicv3(vcpu->kvm)) {
+		kvm_inject_undefined(vcpu);
+		return false;
+	}
+
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p, r);

@@ -85,7 +85,7 @@ static void iter_unmark_lpis(struct kvm *kvm)
 	struct vgic_irq *irq;
 	unsigned long intid;

-	xa_for_each(&dist->lpi_xa, intid, irq) {
+	xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
 		xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
 		vgic_put_irq(kvm, irq);
 	}
@@ -417,10 +417,8 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kfree(vgic_cpu->private_irqs);
 	vgic_cpu->private_irqs = NULL;

-	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
-		vgic_unregister_redist_iodev(vcpu);
+	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
 		vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
-	}
 }

 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -448,6 +446,11 @@ void kvm_vgic_destroy(struct kvm *kvm)
 	kvm_vgic_dist_destroy(kvm);

 	mutex_unlock(&kvm->arch.config_lock);
+
+	if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+		kvm_for_each_vcpu(i, vcpu, kvm)
+			vgic_unregister_redist_iodev(vcpu);
+
 	mutex_unlock(&kvm->slots_lock);
 }

@@ -36,6 +36,11 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = {
 * we have to disable IRQs before taking this lock and everything lower
 * than it.
 *
+ * The config_lock has additional ordering requirements:
+ * kvm->slots_lock
+ *   kvm->srcu
+ *     kvm->arch.config_lock
+ *
 * If you need to take multiple locks, always take the upper lock first,
 * then the lower ones, e.g. first take the its_lock, then the irq_lock.
 * If you are already holding a lock and need to take a higher one, you
@@ -346,4 +346,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm);
 void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val);
 int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);

+static inline bool kvm_has_gicv3(struct kvm *kvm)
+{
+	return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) &&
+		irqchip_in_kernel(kvm) &&
+		kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3);
+}
+
 #endif
@@ -303,13 +303,6 @@ int r4k_clockevent_init(void)
 	if (!c0_compare_int_usable())
 		return -ENXIO;

-	/*
-	 * With vectored interrupts things are getting platform specific.
-	 * get_c0_compare_int is a hook to allow a platform to return the
-	 * interrupt number of its liking.
-	 */
-	irq = get_c0_compare_int();
-
 	cd = &per_cpu(mips_clockevent_device, cpu);

 	cd->name		= "MIPS";
@@ -320,7 +313,6 @@ int r4k_clockevent_init(void)
 	min_delta		= calculate_min_delta();

 	cd->rating		= 300;
-	cd->irq			= irq;
 	cd->cpumask		= cpumask_of(cpu);
 	cd->set_next_event	= mips_next_event;
 	cd->event_handler	= mips_event_handler;
@@ -332,6 +324,13 @@ int r4k_clockevent_init(void)

 	cp0_timer_irq_installed = 1;

+	/*
+	 * With vectored interrupts things are getting platform specific.
+	 * get_c0_compare_int is a hook to allow a platform to return the
+	 * interrupt number of its liking.
+	 */
+	irq = get_c0_compare_int();
+
 	if (request_irq(irq, c0_compare_interrupt, flags, "timer",
 			c0_compare_interrupt))
 		pr_err("Failed to request irq %d (timer)\n", irq);
@@ -1724,12 +1724,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 		c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
 			MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
 		c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */
+		change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER,
+				  LOONGSON_CONF6_INTIMER);
 		break;
 	case PRID_IMP_LOONGSON_64G:
 		__cpu_name[cpu] = "ICT Loongson-3";
 		set_elf_platform(cpu, "loongson3a");
 		set_isa(c, MIPS_CPU_ISA_M64R2);
 		decode_cpucfg(c);
+		change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER,
+				  LOONGSON_CONF6_INTIMER);
 		break;
 	default:
 		panic("Unknown Loongson Processor ID!");
@@ -604,6 +604,19 @@ config RANDOMIZE_BASE
 	  as a security feature that deters exploit attempts relying on
 	  knowledge of the location of kernel internals.

+config RANDOMIZE_IDENTITY_BASE
+	bool "Randomize the address of the identity mapping base"
+	depends on RANDOMIZE_BASE
+	default DEBUG_VM
+	help
+	  The identity mapping base address is pinned to zero by default.
+	  Allow randomization of that base to expose otherwise missed
+	  notion of physical and virtual addresses of data structures.
+	  That does not have any impact on the base address at which the
+	  kernel image is loaded.
+
+	  If unsure, say N
+
 config KERNEL_IMAGE_BASE
 	hex "Kernel image base address"
 	range 0x100000 0x1FFFFFE0000000 if !KASAN
@@ -162,7 +162,7 @@ static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr,
 		loc = (long)*reloc + phys_offset;
 		if (loc < min_addr || loc > max_addr)
 			error("64-bit relocation outside of kernel!\n");
-		*(u64 *)loc += offset - __START_KERNEL;
+		*(u64 *)loc += offset;
 	}
 }

@@ -177,7 +177,7 @@ static void kaslr_adjust_got(unsigned long offset)
 	 */
 	for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) {
 		if (*entry)
-			*entry += offset - __START_KERNEL;
+			*entry += offset;
 	}
 }

@@ -252,7 +252,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 	vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);

 	/* choose kernel address space layout: 4 or 3 levels. */
-	BUILD_BUG_ON(!IS_ALIGNED(__START_KERNEL, THREAD_SIZE));
+	BUILD_BUG_ON(!IS_ALIGNED(TEXT_OFFSET, THREAD_SIZE));
 	BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE));
 	BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE);
 	vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE);
@@ -341,7 +341,8 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
 	BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS));
 	max_mappable = max(ident_map_size, MAX_DCSS_ADDR);
 	max_mappable = min(max_mappable, vmemmap_start);
-	__identity_base = round_down(vmemmap_start - max_mappable, rte_size);
+	if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE))
+		__identity_base = round_down(vmemmap_start - max_mappable, rte_size);

 	return asce_limit;
 }
@@ -388,31 +389,25 @@ static void kaslr_adjust_vmlinux_info(long offset)
 #endif
 }

-static void fixup_vmlinux_info(void)
-{
-	vmlinux.entry -= __START_KERNEL;
-	kaslr_adjust_vmlinux_info(-__START_KERNEL);
-}
-
 void startup_kernel(void)
 {
-	unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size;
-	unsigned long nokaslr_offset_phys, kaslr_large_page_offset;
-	unsigned long amode31_lma = 0;
+	unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size;
+	unsigned long nokaslr_text_lma, text_lma = 0, amode31_lma = 0;
+	unsigned long kernel_size = TEXT_OFFSET + vmlinux_size;
+	unsigned long kaslr_large_page_offset;
 	unsigned long max_physmem_end;
 	unsigned long asce_limit;
 	unsigned long safe_addr;
 	psw_t psw;

-	fixup_vmlinux_info();
 	setup_lpp();

 	/*
 	 * Non-randomized kernel physical start address must be _SEGMENT_SIZE
 	 * aligned (see blow).
 	 */
-	nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
-	safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size);
+	nokaslr_text_lma = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
+	safe_addr = PAGE_ALIGN(nokaslr_text_lma + vmlinux_size);

 	/*
 	 * Reserve decompressor memory together with decompression heap,
@@ -456,16 +451,27 @@ void startup_kernel(void)
 	 */
 	kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK;
 	if (kaslr_enabled()) {
-		unsigned long end = ident_map_size - kaslr_large_page_offset;
+		unsigned long size = vmlinux_size + kaslr_large_page_offset;

-		__kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end);
+		text_lma = randomize_within_range(size, _SEGMENT_SIZE, TEXT_OFFSET, ident_map_size);
 	}
-	if (!__kaslr_offset_phys)
-		__kaslr_offset_phys = nokaslr_offset_phys;
-	__kaslr_offset_phys |= kaslr_large_page_offset;
+	if (!text_lma)
+		text_lma = nokaslr_text_lma;
+	text_lma |= kaslr_large_page_offset;
+
+	/*
+	 * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region is
+	 * never accessed via the kernel image mapping as per the linker script:
+	 *
+	 *	. = TEXT_OFFSET;
+	 *
+	 * Therefore, this region could be used for something else and does
+	 * not need to be reserved. See how it is skipped in setup_vmem().
+	 */
+	__kaslr_offset_phys = text_lma - TEXT_OFFSET;
 	kaslr_adjust_vmlinux_info(__kaslr_offset_phys);
-	physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size);
-	deploy_kernel((void *)__kaslr_offset_phys);
+	physmem_reserve(RR_VMLINUX, text_lma, vmlinux_size);
+	deploy_kernel((void *)text_lma);

 	/* vmlinux decompression is done, shrink reserved low memory */
 	physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end);
@@ -488,7 +494,7 @@ void startup_kernel(void)
 		amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, amode31_min, SZ_2G);
 	}
 	if (!amode31_lma)
-		amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size;
+		amode31_lma = text_lma - vmlinux.amode31_size;
 	physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);

 	/*
@@ -504,8 +510,8 @@ void startup_kernel(void)
 	 * - copy_bootdata() must follow setup_vmem() to propagate changes
 	 *   to bootdata made by setup_vmem()
 	 */
-	clear_bss_section(__kaslr_offset_phys);
-	kaslr_adjust_relocs(__kaslr_offset_phys, __kaslr_offset_phys + vmlinux.image_size,
+	clear_bss_section(text_lma);
+	kaslr_adjust_relocs(text_lma, text_lma + vmlinux.image_size,
 			    __kaslr_offset, __kaslr_offset_phys);
 	kaslr_adjust_got(__kaslr_offset);
 	setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit);
@@ -90,7 +90,7 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern
 		}
 		memgap_start = end;
 	}
-	kasan_populate(kernel_start, kernel_end, POPULATE_KASAN_MAP_SHADOW);
+	kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW);
 	kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW);
 	kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW);
 	if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
@@ -475,7 +475,17 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
 				 (unsigned long)__identity_va(end),
 				 POPULATE_IDENTITY);
 	}
-	pgtable_populate(kernel_start, kernel_end, POPULATE_KERNEL);
+
+	/*
+	 * [kernel_start..kernel_start + TEXT_OFFSET] region is never
+	 * accessed as per the linker script:
+	 *
+	 *	. = TEXT_OFFSET;
+	 *
+	 * Therefore, skip mapping TEXT_OFFSET bytes to prevent access to
+	 * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region.
+	 */
+	pgtable_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KERNEL);
 	pgtable_populate(AMODE31_START, AMODE31_END, POPULATE_DIRECT);
 	pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore),
 			 POPULATE_ABS_LOWCORE);
@@ -109,7 +109,12 @@ SECTIONS
 #ifdef CONFIG_KERNEL_UNCOMPRESSED
 	. = ALIGN(PAGE_SIZE);
 	. += AMODE31_SIZE;		/* .amode31 section */
-	. = ALIGN(1 << 20);		/* _SEGMENT_SIZE */
+
+	/*
+	 * Make sure the location counter is not less than TEXT_OFFSET.
+	 * _SEGMENT_SIZE is not available, use ALIGN(1 << 20) instead.
+	 */
+	. = MAX(TEXT_OFFSET, ALIGN(1 << 20));
 #else
 	. = ALIGN(8);
 #endif
@@ -279,8 +279,9 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 #define AMODE31_SIZE		(3 * PAGE_SIZE)

 #define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
-#define __START_KERNEL		0x100000
 #define __NO_KASLR_START_KERNEL	CONFIG_KERNEL_IMAGE_BASE
 #define __NO_KASLR_END_KERNEL	(__NO_KASLR_START_KERNEL + KERNEL_IMAGE_SIZE)

+#define TEXT_OFFSET		0x100000
+
 #endif /* _S390_PAGE_H */
@@ -734,7 +734,23 @@ static void __init memblock_add_physmem_info(void)
 }

 /*
- * Reserve memory used for lowcore/command line/kernel image.
+ * Reserve memory used for lowcore.
+ */
+static void __init reserve_lowcore(void)
+{
+	void *lowcore_start = get_lowcore();
+	void *lowcore_end = lowcore_start + sizeof(struct lowcore);
+	void *start, *end;
+
+	if ((void *)__identity_base < lowcore_end) {
+		start = max(lowcore_start, (void *)__identity_base);
+		end = min(lowcore_end, (void *)(__identity_base + ident_map_size));
+		memblock_reserve(__pa(start), __pa(end));
+	}
+}
+
+/*
+ * Reserve memory used for absolute lowcore/command line/kernel image.
 */
 static void __init reserve_kernel(void)
 {
@@ -918,6 +934,7 @@ void __init setup_arch(char **cmdline_p)

 	/* Do some memory reservations *before* memory is added to memblock */
 	reserve_pgtables();
+	reserve_lowcore();
 	reserve_kernel();
 	reserve_initrd();
 	reserve_certificate_list();
@@ -39,7 +39,7 @@ PHDRS {

 SECTIONS
 {
-	. = __START_KERNEL;
+	. = TEXT_OFFSET;
 	.text : {
 		_stext = .;		/* Start of text section */
 		_text = .;		/* Text and read-only data */
@@ -280,7 +280,7 @@ static int do_reloc(struct section *sec, Elf_Rel *rel)
 	case R_390_GOTOFF64:
 		break;
 	case R_390_64:
-		add_reloc(&relocs64, offset - ehdr.e_entry);
+		add_reloc(&relocs64, offset);
 		break;
 	default:
 		die("Unsupported relocation type: %d\n", r_type);
@@ -111,13 +111,20 @@ static sector_t bio_write_zeroes_limit(struct block_device *bdev)
 		(UINT_MAX >> SECTOR_SHIFT) & ~bs_mask);
 }

+/*
+ * There is no reliable way for the SCSI subsystem to determine whether a
+ * device supports a WRITE SAME operation without actually performing a write
+ * to media. As a result, write_zeroes is enabled by default and will be
+ * disabled if a zeroing operation subsequently fails. This means that this
+ * queue limit is likely to change at runtime.
+ */
 static void __blkdev_issue_write_zeroes(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
-		struct bio **biop, unsigned flags)
+		struct bio **biop, unsigned flags, sector_t limit)
 {
+
 	while (nr_sects) {
-		unsigned int len = min_t(sector_t, nr_sects,
-				bio_write_zeroes_limit(bdev));
+		unsigned int len = min(nr_sects, limit);
 		struct bio *bio;

 		if ((flags & BLKDEV_ZERO_KILLABLE) &&
@@ -141,12 +148,14 @@ static void __blkdev_issue_write_zeroes(struct block_device *bdev,
 static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp, unsigned flags)
 {
+	sector_t limit = bio_write_zeroes_limit(bdev);
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 	int ret = 0;

 	blk_start_plug(&plug);
-	__blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, flags);
+	__blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio,
+			flags, limit);
 	if (bio) {
 		if ((flags & BLKDEV_ZERO_KILLABLE) &&
 		    fatal_signal_pending(current)) {
@@ -165,7 +174,7 @@ static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
 	 * on an I/O error, in which case we'll turn any error into
 	 * "not supported" here.
 	 */
-	if (ret && !bdev_write_zeroes_sectors(bdev))
+	if (ret && !limit)
 		return -EOPNOTSUPP;
 	return ret;
 }
@@ -265,12 +274,14 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
 		unsigned flags)
 {
+	sector_t limit = bio_write_zeroes_limit(bdev);
+
 	if (bdev_read_only(bdev))
 		return -EPERM;

-	if (bdev_write_zeroes_sectors(bdev)) {
+	if (limit) {
 		__blkdev_issue_write_zeroes(bdev, sector, nr_sects,
-				gfp_mask, biop, flags);
+				gfp_mask, biop, flags, limit);
 	} else {
 		if (flags & BLKDEV_ZERO_NOFALLBACK)
 			return -EOPNOTSUPP;
@@ -10,7 +10,6 @@
 #include <stdio.h>
 #include <libgen.h>
 #include <string.h>
-#include <linux/version.h>
 #include <ctype.h>
 #include "utils.h"

@@ -10,7 +10,6 @@
 #include <stdio.h>
 #include <libgen.h>
 #include <string.h>
-#include <linux/version.h>
 #include <ctype.h>
 #include "utils.h"

@@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void)
 		acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
 	if (!strcmp("apple_gmux", acpi_video_backlight_string))
 		acpi_backlight_cmdline = acpi_backlight_apple_gmux;
+	if (!strcmp("dell_uart", acpi_video_backlight_string))
+		acpi_backlight_cmdline = acpi_backlight_dell_uart;
 	if (!strcmp("none", acpi_video_backlight_string))
 		acpi_backlight_cmdline = acpi_backlight_none;
 }
@@ -821,6 +823,21 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		},
 	},

+	/*
+	 * Dell AIO (All in Ones) which advertise an UART attached backlight
+	 * controller board in their ACPI tables (and may even have one), but
+	 * which need native backlight control nevertheless.
+	 */
+	{
+	 /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */
+	 .callback = video_detect_force_native,
+	 /* Dell OptiPlex 7760 AIO */
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7760 AIO"),
+		},
+	},
+
 	/*
 	 * Models which have nvidia-ec-wmi support, but should not use it.
 	 * Note this indicates a likely firmware bug on these models and should
@@ -918,6 +935,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
 	static DEFINE_MUTEX(init_mutex);
 	static bool nvidia_wmi_ec_present;
 	static bool apple_gmux_present;
+	static bool dell_uart_present;
 	static bool native_available;
 	static bool init_done;
 	static long video_caps;
@@ -932,6 +950,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
 				    &video_caps, NULL);
 		nvidia_wmi_ec_present = nvidia_wmi_ec_supported();
 		apple_gmux_present = apple_gmux_detect(NULL, NULL);
+		dell_uart_present = acpi_dev_present("DELL0501", NULL, -1);
 		init_done = true;
 	}
 	if (native)
@@ -962,6 +981,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
 	if (apple_gmux_present)
 		return acpi_backlight_apple_gmux;

+	if (dell_uart_present)
+		return acpi_backlight_dell_uart;
+
 	/* Use ACPI video if available, except when native should be preferred. */
 	if ((video_caps & ACPI_VIDEO_BACKLIGHT) &&
 	     !(native_available && prefer_native_over_acpi_video()))
@@ -208,6 +208,19 @@ static const char* macio_ata_names[] = {
 /* Don't let a DMA segment go all the way to 64K */
 #define MAX_DBDMA_SEG		0xff00

+#ifdef CONFIG_PAGE_SIZE_64KB
+/*
+ * The SCSI core requires the segment size to cover at least a page, so
+ * for 64K page size kernels it must be at least 64K. However the
+ * hardware can't handle 64K, so pata_macio_qc_prep() will split large
+ * requests. To handle the split requests the tablesize must be halved.
+ */
+#define PATA_MACIO_MAX_SEGMENT_SIZE	SZ_64K
+#define PATA_MACIO_SG_TABLESIZE		(MAX_DCMDS / 2)
+#else
+#define PATA_MACIO_MAX_SEGMENT_SIZE	MAX_DBDMA_SEG
+#define PATA_MACIO_SG_TABLESIZE		MAX_DCMDS
+#endif

 /*
 * Wait 1s for disk to answer on IDE bus after a hard reset
@@ -541,7 +554,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)

 		while (sg_len) {
 			/* table overflow should never happen */
-			BUG_ON (pi++ >= MAX_DCMDS);
+			if (WARN_ON_ONCE(pi >= MAX_DCMDS))
+				return AC_ERR_SYSTEM;

 			len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG;
 			table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE);
@@ -553,11 +567,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
 			addr += len;
 			sg_len -= len;
 			++table;
+			++pi;
 		}
 	}

 	/* Should never happen according to Tejun */
-	BUG_ON(!pi);
+	if (WARN_ON_ONCE(!pi))
+		return AC_ERR_SYSTEM;

 	/* Convert the last command to an input/output */
 	table--;
@@ -912,16 +928,10 @@ static int pata_macio_do_resume(struct pata_macio_priv *priv)

 static const struct scsi_host_template pata_macio_sht = {
 	__ATA_BASE_SHT(DRV_NAME),
-	.sg_tablesize		= MAX_DCMDS,
+	.sg_tablesize		= PATA_MACIO_SG_TABLESIZE,
 	/* We may not need that strict one */
 	.dma_boundary		= ATA_DMA_BOUNDARY,
-	/*
-	 * The SCSI core requires the segment size to cover at least a page, so
-	 * for 64K page size kernels this must be at least 64K. However the
-	 * hardware can't handle 64K, so pata_macio_qc_prep() will split large
-	 * requests.
-	 */
-	.max_segment_size	= SZ_64K,
+	.max_segment_size	= PATA_MACIO_MAX_SEGMENT_SIZE,
 	.device_configure	= pata_macio_device_configure,
 	.sdev_groups		= ata_common_sdev_groups,
 	.can_queue		= ATA_DEF_QUEUE,
@@ -2945,9 +2945,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 					       INTEL_ROM_LEGACY_NO_WBS_SUPPORT))
 				set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 					&hdev->quirks);
-			if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22)
-				set_bit(HCI_QUIRK_VALID_LE_STATES,
-					&hdev->quirks);

 			err = btintel_legacy_rom_setup(hdev, &ver);
 			break;
@@ -2956,7 +2953,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		case 0x12:      /* ThP */
 		case 0x13:      /* HrP */
 		case 0x14:      /* CcP */
-			set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
 			fallthrough;
 		case 0x0c:	/* WsP */
 			/* Apply the device specific HCI quirks
@@ -3048,9 +3044,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		/* These variants don't seem to support LE Coded PHY */
 		set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);

-		/* Set Valid LE States quirk */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev, ver.hw_variant);

@@ -3076,9 +3069,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		 */
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

-		/* Apply LE States quirk from solar onwards */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev,
 					INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
@@ -1180,9 +1180,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
 		 */
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

-		/* Apply LE States quirk from solar onwards */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev,
 					INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
@@ -1148,9 +1148,6 @@ static int btmtksdio_setup(struct hci_dev *hdev)
 			}
 		}

-		/* Valid LE States quirk for MediaTek 7921 */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		break;
 	case 0x7663:
 	case 0x7668:
@@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
 	case CHIP_ID_8852C:
 	case CHIP_ID_8851B:
 	case CHIP_ID_8852BT:
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

 		/* RTL8852C needs to transmit mSBC data continuously without
@@ -3956,8 +3956,8 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info & BTUSB_WIDEBAND_SPEECH)
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);

-	if (id->driver_info & BTUSB_VALID_LE_STATES)
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+	if (!(id->driver_info & BTUSB_VALID_LE_STATES))
+		set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);

 	if (id->driver_info & BTUSB_DIGIANSWER) {
 		data->cmdreq_type = USB_TYPE_VENDOR;
@@ -2474,8 +2474,8 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 			set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 				&hdev->quirks);

-		if (data->capabilities & QCA_CAP_VALID_LE_STATES)
-			set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+		if (!(data->capabilities & QCA_CAP_VALID_LE_STATES))
+			set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
 	}

 	return 0;
@@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 	if (opcode & 0x80)
 		set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);

-	set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 	if (hci_register_dev(hdev) < 0) {
 		BT_ERR("Can't register HCI device");
 		hci_free_dev(hdev);
@@ -834,11 +834,13 @@ static void cxl_disable_rch_root_ints(struct cxl_dport *dport)
 void cxl_setup_parent_dport(struct device *host, struct cxl_dport *dport)
 {
 	struct device *dport_dev = dport->dport_dev;
-	struct pci_host_bridge *host_bridge;

-	host_bridge = to_pci_host_bridge(dport_dev);
-	if (host_bridge->native_aer)
-		dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base);
+	if (dport->rch) {
+		struct pci_host_bridge *host_bridge = to_pci_host_bridge(dport_dev);
+
+		if (host_bridge->native_aer)
+			dport->rcrb.aer_cap = cxl_rcrb_to_aer(dport_dev, dport->rcrb.base);
+	}

 	dport->reg_map.host = host;
 	cxl_dport_map_regs(dport);
@@ -278,7 +278,7 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
 			msg = RREG32(mmMP0_SMN_C2PMSG_33);
 			if (msg & 0x80000000)
 				break;
-			usleep_range(1000, 1100);
+			msleep(1);
 		}
 	}

@@ -166,6 +166,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t
 	if (ret)
 		return -EFAULT;

+	if (ta_bin_len > PSP_1_MEG)
+		return -EINVAL;
+
 	copy_pos += sizeof(uint32_t);

 	ta_bin = kzalloc(ta_bin_len, GFP_KERNEL);
@@ -4116,6 +4116,7 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev)

 static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 {
+	char fw_name[53];
 	char ucode_prefix[30];
 	const char *wks = "";
 	int err;
@@ -4149,8 +4150,8 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 	amdgpu_gfx_cp_init_microcode(adev, AMDGPU_UCODE_ID_CP_CE);

 	if (!amdgpu_sriov_vf(adev)) {
-		err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
-					   "amdgpu/%s_rlc.bin", ucode_prefix);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", ucode_prefix);
+		err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 		if (err)
 			goto out;

@@ -176,14 +176,16 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
 		DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
-		/* SDMA seems to miss doorbells sometimes when powergating kicks in.
-		 * Updating the wptr directly will wake it. This is only safe because
-		 * we disallow gfxoff in begin_use() and then allow it again in end_use().
-		 */
-		WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
-		       lower_32_bits(ring->wptr << 2));
-		WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
-		       upper_32_bits(ring->wptr << 2));
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(5, 2, 1)) {
+			/* SDMA seems to miss doorbells sometimes when powergating kicks in.
+			 * Updating the wptr directly will wake it. This is only safe because
+			 * we disallow gfxoff in begin_use() and then allow it again in end_use().
+			 */
+			WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
+			       lower_32_bits(ring->wptr << 2));
+			WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
+			       upper_32_bits(ring->wptr << 2));
+		}
 	} else {
 		DRM_DEBUG("Not using doorbell -- "
 				"mmSDMA%i_GFX_RB_WPTR == 0x%08x "
@@ -39,7 +39,9 @@ static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder)
 static void intel_dp_hdcp_wait_for_cp_irq(struct intel_connector *connector,
 					  int timeout)
 {
-	struct intel_hdcp *hdcp = &connector->hdcp;
+	struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
+	struct intel_dp *dp = &dig_port->dp;
+	struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
 	long ret;

 #define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count))
@@ -99,7 +99,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
 		 * was a bad idea, and is only provided for backwards
 		 * compatibility for older targets.
 		 */
-		return -ENODEV;
+		return -ENOENT;
 	}

 	if (IS_ERR(fw)) {
@@ -1171,8 +1171,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,

 	cstate->num_mixers = num_lm;

-	dpu_enc->connector = conn_state->connector;
-
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];

@@ -1270,6 +1268,8 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc,

 	dpu_enc->commit_done_timedout = false;

+	dpu_enc->connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc);
+
 	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;

 	dpu_enc->wide_bus_en = dpu_encoder_is_widebus_enabled(drm_enc);
@@ -308,8 +308,8 @@ static const u32 wb2_formats_rgb_yuv[] = {
 	{ \
 	.maxdwnscale = SSPP_UNITY_SCALE, \
 	.maxupscale = SSPP_UNITY_SCALE, \
-	.format_list = plane_formats_yuv, \
-	.num_formats = ARRAY_SIZE(plane_formats_yuv), \
+	.format_list = plane_formats, \
+	.num_formats = ARRAY_SIZE(plane_formats), \
 	.virt_format_list = plane_formats, \
 	.virt_num_formats = ARRAY_SIZE(plane_formats), \
 	}
@@ -31,24 +31,14 @@
 * @fmt: Pointer to format string
 */
 #define DPU_DEBUG(fmt, ...)                                                \
-	do {                                                               \
-		if (drm_debug_enabled(DRM_UT_KMS))                         \
-			DRM_DEBUG(fmt, ##__VA_ARGS__); \
-		else                                                       \
-			pr_debug(fmt, ##__VA_ARGS__);                      \
-	} while (0)
+	DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)

 /**
 * DPU_DEBUG_DRIVER - macro for hardware driver logging
 * @fmt: Pointer to format string
 */
 #define DPU_DEBUG_DRIVER(fmt, ...)                                         \
-	do {                                                               \
-		if (drm_debug_enabled(DRM_UT_DRIVER))                      \
-			DRM_ERROR(fmt, ##__VA_ARGS__); \
-		else                                                       \
-			pr_debug(fmt, ##__VA_ARGS__);                      \
-	} while (0)
+	DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)

 #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
 #define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__)
@@ -681,6 +681,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
 			new_state->fb, &layout);
 	if (ret) {
 		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+		if (pstate->aspace)
+			msm_framebuffer_cleanup(new_state->fb, pstate->aspace,
+						pstate->needs_dirtyfb);
 		return ret;
 	}

@@ -744,10 +747,9 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu,
 	min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1;

 	if (MSM_FORMAT_IS_YUV(fmt) &&
-	    (!pipe->sspp->cap->sblk->scaler_blk.len ||
-	     !pipe->sspp->cap->sblk->csc_blk.len)) {
+	    !pipe->sspp->cap->sblk->csc_blk.len) {
 		DPU_DEBUG_PLANE(pdpu,
-				"plane doesn't have scaler/csc for yuv\n");
+				"plane doesn't have csc for yuv\n");
 		return -EINVAL;
 	}

@@ -864,6 +866,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,

 	max_linewidth = pdpu->catalog->caps->max_linewidth;

+	drm_rect_rotate(&pipe_cfg->src_rect,
+			new_plane_state->fb->width, new_plane_state->fb->height,
+			new_plane_state->rotation);
+
 	if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) ||
 	     _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) {
 		/*
@@ -913,6 +919,14 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 		r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2;
 	}

+	drm_rect_rotate_inv(&pipe_cfg->src_rect,
+			    new_plane_state->fb->width, new_plane_state->fb->height,
+			    new_plane_state->rotation);
+	if (r_pipe->sspp)
+		drm_rect_rotate_inv(&r_pipe_cfg->src_rect,
+				    new_plane_state->fb->width, new_plane_state->fb->height,
+				    new_plane_state->rotation);
+
 	ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode);
 	if (ret)
 		return ret;
@@ -1286,6 +1286,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
 	link_info.rate = ctrl->link->link_params.rate;
 	link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING;

+	dp_link_reset_phy_params_vx_px(ctrl->link);
+
 	dp_aux_link_configure(ctrl->aux, &link_info);

 	if (drm_dp_max_downspread(dpcd))
@@ -90,22 +90,22 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel)
 static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel,
 		u32 mode_edid_bpp, u32 mode_pclk_khz)
 {
-	struct dp_link_info *link_info;
+	const struct dp_link_info *link_info;
 	const u32 max_supported_bpp = 30, min_supported_bpp = 18;
-	u32 bpp = 0, data_rate_khz = 0;
+	u32 bpp, data_rate_khz;

-	bpp = min_t(u32, mode_edid_bpp, max_supported_bpp);
+	bpp = min(mode_edid_bpp, max_supported_bpp);

 	link_info = &dp_panel->link_info;
 	data_rate_khz = link_info->num_lanes * link_info->rate * 8;

-	while (bpp > min_supported_bpp) {
+	do {
 		if (mode_pclk_khz * bpp <= data_rate_khz)
-			break;
+			return bpp;
 		bpp -= 6;
-	}
+	} while (bpp > min_supported_bpp);

-	return bpp;
+	return min_supported_bpp;
 }

 int dp_panel_read_sink_caps(struct dp_panel *dp_panel,
@@ -423,8 +423,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel)
 				drm_mode->clock);
 	drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp);

-	dp_panel->dp_mode.bpp = max_t(u32, 18,
-				min_t(u32, dp_panel->dp_mode.bpp, 30));
+	dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp,
+						      dp_panel->dp_mode.drm_mode.clock);
+
 	drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n",
 				dp_panel->dp_mode.bpp);

@@ -577,7 +577,7 @@ static const struct msm_mdss_data sc7180_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
 	.ubwc_static = 0x1e,
-	.highest_bank_bit = 0x3,
+	.highest_bank_bit = 0x1,
 	.reg_bus_bw = 76800,
 };

@@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
 		break;
 	case NVKM_FIRMWARE_IMG_DMA:
 		nvkm_memory_unref(&memory);
-		dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
+		dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl),
+				     fw->img, fw->phys, DMA_TO_DEVICE);
 		break;
 	case NVKM_FIRMWARE_IMG_SGT:
 		nvkm_memory_unref(&memory);
@@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
 		break;
 	case NVKM_FIRMWARE_IMG_DMA: {
 		dma_addr_t addr;
-
 		len = ALIGN(fw->len, PAGE_SIZE);

-		fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
+		fw->img = dma_alloc_noncoherent(fw->device->dev,
+						len, &addr,
+						DMA_TO_DEVICE,
+						GFP_KERNEL);
 		if (fw->img) {
 			memcpy(fw->img, src, fw->len);
 			fw->phys = addr;
@@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
 		nvkm_falcon_fw_dtor_sigs(fw);
 	}

+	/* after last write to the img, sync dma mappings */
+	dma_sync_single_for_device(fw->fw.device->dev,
+				   fw->fw.phys,
+				   sg_dma_len(&fw->fw.mem.sgl),
+				   DMA_TO_DEVICE);
+
 	FLCNFW_DBG(fw, "resetting");
 	fw->func->reset(fw);

@@ -25,12 +25,14 @@ $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \

 uses_generated_oob := \
 	$(obj)/xe_ggtt.o \
+	$(obj)/xe_device.o \
 	$(obj)/xe_gsc.o \
 	$(obj)/xe_gt.o \
 	$(obj)/xe_guc.o \
 	$(obj)/xe_guc_ads.o \
 	$(obj)/xe_guc_pc.o \
 	$(obj)/xe_migrate.o \
+	$(obj)/xe_pat.o \
 	$(obj)/xe_ring_ops.o \
 	$(obj)/xe_vm.o \
 	$(obj)/xe_wa.o \
@@ -132,6 +132,7 @@ static void xe_display_fini_noirq(void *arg)
 		return;

 	intel_display_driver_remove_noirq(xe);
+	intel_opregion_cleanup(xe);
 }

 int xe_display_init_noirq(struct xe_device *xe)
@@ -157,8 +158,10 @@ int xe_display_init_noirq(struct xe_device *xe)
 	intel_display_device_info_runtime_init(xe);

 	err = intel_display_driver_probe_noirq(xe);
-	if (err)
+	if (err) {
+		intel_opregion_cleanup(xe);
 		return err;
+	}

 	return devm_add_action_or_reset(xe->drm.dev, xe_display_fini_noirq, xe);
 }
@@ -280,6 +283,27 @@ static bool suspend_to_idle(void)
 	return false;
 }

+static void xe_display_flush_cleanup_work(struct xe_device *xe)
+{
+	struct intel_crtc *crtc;
+
+	for_each_intel_crtc(&xe->drm, crtc) {
+		struct drm_crtc_commit *commit;
+
+		spin_lock(&crtc->base.commit_lock);
+		commit = list_first_entry_or_null(&crtc->base.commit_list,
+						  struct drm_crtc_commit, commit_entry);
+		if (commit)
+			drm_crtc_commit_get(commit);
+		spin_unlock(&crtc->base.commit_lock);
+
+		if (commit) {
+			wait_for_completion(&commit->cleanup_done);
+			drm_crtc_commit_put(commit);
+		}
+	}
+}
+
 void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
 {
 	bool s2idle = suspend_to_idle();
@@ -297,6 +321,8 @@ void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
 	if (!runtime)
 		intel_display_driver_suspend(xe);

+	xe_display_flush_cleanup_work(xe);
+
 	intel_dp_mst_suspend(xe);

 	intel_hpd_cancel_work(xe);
@@ -7,6 +7,8 @@
 #include "intel_display_types.h"
 #include "intel_dsb_buffer.h"
 #include "xe_bo.h"
+#include "xe_device.h"
+#include "xe_device_types.h"
 #include "xe_gt.h"

 u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)
@@ -16,7 +18,10 @@ u32 intel_dsb_buffer_ggtt_offset(struct intel_dsb_buffer *dsb_buf)

 void intel_dsb_buffer_write(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val)
 {
+	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
 	iosys_map_wr(&dsb_buf->vma->bo->vmap, idx * 4, u32, val);
+	xe_device_l2_flush(xe);
 }

 u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)
@@ -26,9 +31,12 @@ u32 intel_dsb_buffer_read(struct intel_dsb_buffer *dsb_buf, u32 idx)

 void intel_dsb_buffer_memset(struct intel_dsb_buffer *dsb_buf, u32 idx, u32 val, size_t size)
 {
+	struct xe_device *xe = dsb_buf->vma->bo->tile->xe;
+
 	WARN_ON(idx > (dsb_buf->buf_size - size) / sizeof(*dsb_buf->cmd_buf));

 	iosys_map_memset(&dsb_buf->vma->bo->vmap, idx * 4, val, size);
+	xe_device_l2_flush(xe);
 }

 bool intel_dsb_buffer_create(struct intel_crtc *crtc, struct intel_dsb_buffer *dsb_buf, size_t size)
@@ -10,6 +10,7 @@
 #include "intel_fb.h"
 #include "intel_fb_pin.h"
 #include "xe_bo.h"
+#include "xe_device.h"
 #include "xe_ggtt.h"
 #include "xe_gt.h"
 #include "xe_pm.h"
@@ -304,6 +305,8 @@ static struct i915_vma *__xe_pin_fb_vma(const struct intel_framebuffer *fb,
 	if (ret)
 		goto err_unpin;

+	/* Ensure DPT writes are flushed */
+	xe_device_l2_flush(xe);
 	return vma;

 err_unpin:
@@ -80,6 +80,9 @@
 #define   LE_CACHEABILITY_MASK			REG_GENMASK(1, 0)
 #define   LE_CACHEABILITY(value)		REG_FIELD_PREP(LE_CACHEABILITY_MASK, value)

+#define XE2_GAMREQSTRM_CTRL			XE_REG(0x4194)
+#define   CG_DIS_CNTLBUS			REG_BIT(6)
+
 #define CCS_AUX_INV				XE_REG(0x4208)

 #define VD0_AUX_INV				XE_REG(0x4218)
@@ -372,6 +375,11 @@

 #define XEHPC_L3CLOS_MASK(i)			XE_REG_MCR(0xb194 + (i) * 8)

+#define XE2_GLOBAL_INVAL			XE_REG(0xb404)
+
+#define SCRATCH1LPFC				XE_REG(0xb474)
+#define   EN_L3_RW_CCS_CACHE_FLUSH		REG_BIT(0)
+
 #define XE2LPM_L3SQCREG5			XE_REG_MCR(0xb658)

 #define XE2_TDF_CTRL				XE_REG(0xb418)
@@ -429,6 +437,7 @@
 #define   DIS_FIX_EOT1_FLUSH			REG_BIT(9)

 #define TDL_TSL_CHICKEN				XE_REG_MCR(0xe4c4, XE_REG_OPTION_MASKED)
+#define   STK_ID_RESTRICT			REG_BIT(12)
 #define   SLM_WMTP_RESTORE			REG_BIT(11)

 #define ROW_CHICKEN				XE_REG_MCR(0xe4f0, XE_REG_OPTION_MASKED)
@@ -1575,7 +1575,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
 	return bo;
 }

-static void __xe_bo_unpin_map_no_vm(struct drm_device *drm, void *arg)
+static void __xe_bo_unpin_map_no_vm(void *arg)
 {
 	xe_bo_unpin_map_no_vm(arg);
 }
@@ -1590,7 +1590,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile
 	if (IS_ERR(bo))
 		return bo;

-	ret = drmm_add_action_or_reset(&xe->drm, __xe_bo_unpin_map_no_vm, bo);
+	ret = devm_add_action_or_reset(xe->drm.dev, __xe_bo_unpin_map_no_vm, bo);
 	if (ret)
 		return ERR_PTR(ret);

@@ -1638,7 +1638,7 @@ int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, str
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);

-	drmm_release_action(&xe->drm, __xe_bo_unpin_map_no_vm, *src);
+	devm_release_action(xe->drm.dev, __xe_bo_unpin_map_no_vm, *src);
 	*src = bo;

 	return 0;
@@ -54,6 +54,9 @@
 #include "xe_vm.h"
 #include "xe_vram.h"
 #include "xe_wait_user_fence.h"
+#include "xe_wa.h"
+
+#include <generated/xe_wa_oob.h>

 static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 {
@@ -820,6 +823,11 @@ void xe_device_td_flush(struct xe_device *xe)
 	if (!IS_DGFX(xe) || GRAPHICS_VER(xe) < 20)
 		return;

+	if (XE_WA(xe_root_mmio_gt(xe), 16023588340)) {
+		xe_device_l2_flush(xe);
+		return;
+	}
+
 	for_each_gt(gt, xe, id) {
 		if (xe_gt_is_media_type(gt))
 			continue;
@@ -843,6 +851,30 @@ void xe_device_td_flush(struct xe_device *xe)
 	}
 }

+void xe_device_l2_flush(struct xe_device *xe)
+{
+	struct xe_gt *gt;
+	int err;
+
+	gt = xe_root_mmio_gt(xe);
+
+	if (!XE_WA(gt, 16023588340))
+		return;
+
+	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (err)
+		return;
+
+	spin_lock(&gt->global_invl_lock);
+	xe_mmio_write32(gt, XE2_GLOBAL_INVAL, 0x1);
+
+	if (xe_mmio_wait32(gt, XE2_GLOBAL_INVAL, 0x1, 0x0, 150, NULL, true))
+		xe_gt_err_once(gt, "Global invalidation timeout\n");
+	spin_unlock(&gt->global_invl_lock);
+
+	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
 u32 xe_device_ccs_bytes(struct xe_device *xe, u64 size)
 {
 	return xe_device_has_flat_ccs(xe) ?
@@ -162,6 +162,7 @@ u64 xe_device_canonicalize_addr(struct xe_device *xe, u64 address);
 u64 xe_device_uncanonicalize_addr(struct xe_device *xe, u64 address);

 void xe_device_td_flush(struct xe_device *xe);
+void xe_device_l2_flush(struct xe_device *xe);

 static inline bool xe_device_wedged(struct xe_device *xe)
 {
@@ -105,22 +105,35 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,

 static int __xe_exec_queue_init(struct xe_exec_queue *q)
 {
+	struct xe_vm *vm = q->vm;
 	int i, err;

+	if (vm) {
+		err = xe_vm_lock(vm, true);
+		if (err)
+			return err;
+	}
+
 	for (i = 0; i < q->width; ++i) {
 		q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K);
 		if (IS_ERR(q->lrc[i])) {
 			err = PTR_ERR(q->lrc[i]);
-			goto err_lrc;
+			goto err_unlock;
 		}
 	}

+	if (vm)
+		xe_vm_unlock(vm);
+
 	err = q->ops->init(q);
 	if (err)
 		goto err_lrc;

 	return 0;

+err_unlock:
+	if (vm)
+		xe_vm_unlock(vm);
 err_lrc:
 	for (i = i - 1; i >= 0; --i)
 		xe_lrc_put(q->lrc[i]);
@@ -140,15 +153,7 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v
 	if (IS_ERR(q))
 		return q;

-	if (vm) {
-		err = xe_vm_lock(vm, true);
-		if (err)
-			goto err_post_alloc;
-	}
-
 	err = __xe_exec_queue_init(q);
-	if (vm)
-		xe_vm_unlock(vm);
 	if (err)
 		goto err_post_alloc;

@@ -638,7 +643,6 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,

 		if (xe_vm_in_preempt_fence_mode(vm)) {
 			q->lr.context = dma_fence_context_alloc(1);
-			spin_lock_init(&q->lr.lock);

 			err = xe_vm_add_compute_exec_queue(vm, q);
 			if (XE_IOCTL_DBG(xe, err))
@@ -126,8 +126,6 @@ struct xe_exec_queue {
 		u32 seqno;
 		/** @lr.link: link into VM's list of exec queues */
 		struct list_head link;
-		/** @lr.lock: preemption fences lock */
-		spinlock_t lock;
 	} lr;

 	/** @ops: submission backend exec queue operations */
@@ -260,7 +260,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
 	struct xe_tile *tile = gt_to_tile(gt);
 	int ret;

-	if (XE_WA(gt, 14018094691)) {
+	if (XE_WA(tile->primary_gt, 14018094691)) {
 		ret = xe_force_wake_get(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);

 		/*
@@ -278,7 +278,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)

 	ret = gsc_upload(gsc);

-	if (XE_WA(gt, 14018094691))
+	if (XE_WA(tile->primary_gt, 14018094691))
 		xe_force_wake_put(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);

 	if (ret)
@@ -437,7 +437,7 @@ out:
 	return ret;
 }

-static void free_resources(struct drm_device *drm, void *arg)
+static void free_resources(void *arg)
 {
 	struct xe_gsc *gsc = arg;

@@ -501,7 +501,7 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc)
 	gsc->q = q;
 	gsc->wq = wq;

-	err = drmm_add_action_or_reset(&xe->drm, free_resources, gsc);
+	err = devm_add_action_or_reset(xe->drm.dev, free_resources, gsc);
 	if (err)
 		return err;

@@ -11,6 +11,8 @@
 #include <drm/xe_drm.h>
 #include <generated/xe_wa_oob.h>

+#include <generated/xe_wa_oob.h>
+
 #include "instructions/xe_gfxpipe_commands.h"
 #include "instructions/xe_mi_commands.h"
 #include "regs/xe_gt_regs.h"
@@ -95,6 +97,51 @@ void xe_gt_sanitize(struct xe_gt *gt)
 	gt->uc.guc.submission_state.enabled = false;
 }

+static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
+{
+	u32 reg;
+	int err;
+
+	if (!XE_WA(gt, 16023588340))
+		return;
+
+	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (WARN_ON(err))
+		return;
+
+	if (!xe_gt_is_media_type(gt)) {
+		xe_mmio_write32(gt, SCRATCH1LPFC, EN_L3_RW_CCS_CACHE_FLUSH);
+		reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL);
+		reg |= CG_DIS_CNTLBUS;
+		xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg);
+	}
+
+	xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
+	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
+static void xe_gt_disable_host_l2_vram(struct xe_gt *gt)
+{
+	u32 reg;
+	int err;
+
+	if (!XE_WA(gt, 16023588340))
+		return;
+
+	if (xe_gt_is_media_type(gt))
+		return;
+
+	err = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (WARN_ON(err))
+		return;
+
+	reg = xe_mmio_read32(gt, XE2_GAMREQSTRM_CTRL);
+	reg &= ~CG_DIS_CNTLBUS;
+	xe_mmio_write32(gt, XE2_GAMREQSTRM_CTRL, reg);
+
+	xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+}
+
 /**
 * xe_gt_remove() - Clean up the GT structures before driver removal
 * @gt: the GT object
@@ -111,6 +158,8 @@ void xe_gt_remove(struct xe_gt *gt)

 	for (i = 0; i < XE_ENGINE_CLASS_MAX; ++i)
 		xe_hw_fence_irq_finish(&gt->fence_irq[i]);
+
+	xe_gt_disable_host_l2_vram(gt);
 }

 static void gt_reset_worker(struct work_struct *w);
@@ -339,6 +388,7 @@ int xe_gt_init_early(struct xe_gt *gt)

 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	xe_pcode_init(gt);
+	spin_lock_init(&gt->global_invl_lock);

 	return 0;
 }
@@ -508,6 +558,7 @@ int xe_gt_init_hwconfig(struct xe_gt *gt)

 	xe_gt_mcr_init_early(gt);
 	xe_pat_init(gt);
+	xe_gt_enable_host_l2_vram(gt);

 	err = xe_uc_init(&gt->uc);
 	if (err)
@@ -643,6 +694,8 @@ static int do_gt_restart(struct xe_gt *gt)

 	xe_pat_init(gt);

+	xe_gt_enable_host_l2_vram(gt);
+
 	xe_gt_mcr_set_implicit_defaults(gt);
 	xe_reg_sr_apply_mmio(&gt->reg_sr, gt);

@@ -796,6 +849,8 @@ int xe_gt_suspend(struct xe_gt *gt)

 	xe_gt_idle_disable_pg(gt);

+	xe_gt_disable_host_l2_vram(gt);
+
 	XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL));
 	xe_gt_dbg(gt, "suspended\n");

@@ -382,6 +382,18 @@ static void pf_queue_work_func(struct work_struct *w)

 static void acc_queue_work_func(struct work_struct *w);

+static void pagefault_fini(void *arg)
+{
+	struct xe_gt *gt = arg;
+	struct xe_device *xe = gt_to_xe(gt);
+
+	if (!xe->info.has_usm)
+		return;
+
+	destroy_workqueue(gt->usm.acc_wq);
+	destroy_workqueue(gt->usm.pf_wq);
+}
+
 int xe_gt_pagefault_init(struct xe_gt *gt)
 {
 	struct xe_device *xe = gt_to_xe(gt);
@@ -409,10 +421,12 @@ int xe_gt_pagefault_init(struct xe_gt *gt)
 	gt->usm.acc_wq = alloc_workqueue("xe_gt_access_counter_work_queue",
 					 WQ_UNBOUND | WQ_HIGHPRI,
 					 NUM_ACC_QUEUE);
-	if (!gt->usm.acc_wq)
+	if (!gt->usm.acc_wq) {
+		destroy_workqueue(gt->usm.pf_wq);
 		return -ENOMEM;
+	}

-	return 0;
+	return devm_add_action_or_reset(xe->drm.dev, pagefault_fini, gt);
 }

 void xe_gt_pagefault_reset(struct xe_gt *gt)
@@ -362,6 +362,12 @@ struct xe_gt {
 	 */
 	spinlock_t mcr_lock;

+	/**
+	 * @global_invl_lock: protects the register for the duration
+	 *    of a global invalidation of l2 cache
+	 */
+	spinlock_t global_invl_lock;
+
 	/** @wa_active: keep track of active workarounds */
 	struct {
 		/** @wa_active.gt: bitmap with active GT workarounds */
@@ -284,7 +284,7 @@ static void guc_submit_fini(struct drm_device *drm, void *arg)
 	free_submit_wq(guc);
 }

-static void guc_submit_wedged_fini(struct drm_device *drm, void *arg)
+static void guc_submit_wedged_fini(void *arg)
 {
 	struct xe_guc *guc = arg;
 	struct xe_exec_queue *q;
@@ -877,7 +877,7 @@ void xe_guc_submit_wedge(struct xe_guc *guc)

 	xe_gt_assert(guc_to_gt(guc), guc_to_xe(guc)->wedged.mode);

-	err = drmm_add_action_or_reset(&guc_to_xe(guc)->drm,
+	err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
 				       guc_submit_wedged_fini, guc);
 	if (err) {
 		drm_err(&xe->drm, "Failed to register xe_guc_submit clean-up on wedged.mode=2. Although device is wedged.\n");
@@ -148,20 +148,20 @@ static const char *xe_hw_fence_get_driver_name(struct dma_fence *dma_fence)
 {
 	struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);

-	return dev_name(gt_to_xe(fence->ctx->gt)->drm.dev);
+	return dev_name(fence->xe->drm.dev);
 }

 static const char *xe_hw_fence_get_timeline_name(struct dma_fence *dma_fence)
 {
 	struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);

-	return fence->ctx->name;
+	return fence->name;
 }

 static bool xe_hw_fence_signaled(struct dma_fence *dma_fence)
 {
 	struct xe_hw_fence *fence = to_xe_hw_fence(dma_fence);
-	struct xe_device *xe = gt_to_xe(fence->ctx->gt);
+	struct xe_device *xe = fence->xe;
 	u32 seqno = xe_map_rd(xe, &fence->seqno_map, 0, u32);

 	return dma_fence->error ||
@@ -253,7 +253,8 @@ void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx,
 	struct  xe_hw_fence *hw_fence =
 		container_of(fence, typeof(*hw_fence), dma);

-	hw_fence->ctx = ctx;
+	hw_fence->xe = gt_to_xe(ctx->gt);
+	snprintf(hw_fence->name, sizeof(hw_fence->name), "%s", ctx->name);
 	hw_fence->seqno_map = seqno_map;
 	INIT_LIST_HEAD(&hw_fence->irq_link);

@@ -12,6 +12,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>

+struct xe_device;
 struct xe_gt;

 /**
@@ -61,8 +62,10 @@ struct xe_hw_fence_ctx {
 struct xe_hw_fence {
 	/** @dma: base dma fence for hardware fence context */
 	struct dma_fence dma;
-	/** @ctx: hardware fence context */
-	struct xe_hw_fence_ctx *ctx;
+	/** @xe: Xe device for hw fence driver name */
+	struct xe_device *xe;
+	/** @name: name of hardware fence context */
+	char name[MAX_FENCE_NAME_LEN];
 	/** @seqno_map: I/O map for seqno */
 	struct iosys_map seqno_map;
 	/** @irq_link: Link in struct xe_hw_fence_irq.pending */
@@ -30,7 +30,8 @@ static void tiles_fini(void *arg)
 	int id;

 	for_each_tile(tile, xe, id)
-		tile->mmio.regs = NULL;
+		if (tile != xe_device_get_root_tile(xe))
+			tile->mmio.regs = NULL;
 }

 int xe_mmio_probe_tiles(struct xe_device *xe)
@@ -91,9 +92,11 @@ add_mmio_ext:
 static void mmio_fini(void *arg)
 {
 	struct xe_device *xe = arg;
+	struct xe_tile *root_tile = xe_device_get_root_tile(xe);

 	pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs);
 	xe->mmio.regs = NULL;
+	root_tile->mmio.regs = NULL;
 }

 int xe_mmio_init(struct xe_device *xe)
@@ -121,12 +124,29 @@ int xe_mmio_init(struct xe_device *xe)
 	return devm_add_action_or_reset(xe->drm.dev, mmio_fini, xe);
 }

+static void mmio_flush_pending_writes(struct xe_gt *gt)
+{
+#define DUMMY_REG_OFFSET	0x130030
+	struct xe_tile *tile = gt_to_tile(gt);
+	int i;
+
+	if (tile->xe->info.platform != XE_LUNARLAKE)
+		return;
+
+	/* 4 dummy writes */
+	for (i = 0; i < 4; i++)
+		writel(0, tile->mmio.regs + DUMMY_REG_OFFSET);
+}
+
 u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg)
 {
 	struct xe_tile *tile = gt_to_tile(gt);
 	u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
 	u8 val;

+	/* Wa_15015404425 */
+	mmio_flush_pending_writes(gt);
+
 	val = readb((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr);
 	trace_xe_reg_rw(gt, false, addr, val, sizeof(val));

@@ -139,6 +159,9 @@ u16 xe_mmio_read16(struct xe_gt *gt, struct xe_reg reg)
 	u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
 	u16 val;

+	/* Wa_15015404425 */
+	mmio_flush_pending_writes(gt);
+
 	val = readw((reg.ext ? tile->mmio_ext.regs : tile->mmio.regs) + addr);
 	trace_xe_reg_rw(gt, false, addr, val, sizeof(val));

@@ -160,6 +183,9 @@ u32 xe_mmio_read32(struct xe_gt *gt, struct xe_reg reg)
 	u32 addr = xe_mmio_adjusted_addr(gt, reg.addr);
 	u32 val;

+	/* Wa_15015404425 */
+	mmio_flush_pending_writes(gt);
+
 	if (!reg.vf && IS_SRIOV_VF(gt_to_xe(gt)))
 		val = xe_gt_sriov_vf_read32(gt, reg);
 	else
@@ -66,7 +66,6 @@ static struct ctl_table observation_ctl_table[] = {
 	 .extra1 = SYSCTL_ZERO,
 	 .extra2 = SYSCTL_ONE,
 	 },
-	{}
 };

 /**
@@ -7,6 +7,8 @@

 #include <drm/xe_drm.h>

+#include <generated/xe_wa_oob.h>
+
 #include "regs/xe_reg_defs.h"
 #include "xe_assert.h"
 #include "xe_device.h"
@@ -15,6 +17,7 @@
 #include "xe_gt_mcr.h"
 #include "xe_mmio.h"
 #include "xe_sriov.h"
+#include "xe_wa.h"

 #define _PAT_ATS				0x47fc
 #define _PAT_INDEX(index)			_PICK_EVEN_2RANGES(index, 8, \
@@ -382,7 +385,13 @@ void xe_pat_init_early(struct xe_device *xe)
 	if (GRAPHICS_VER(xe) == 20) {
 		xe->pat.ops = &xe2_pat_ops;
 		xe->pat.table = xe2_pat_table;
-		xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table);
+
+		/* Wa_16023588340. XXX: Should use XE_WA */
+		if (GRAPHICS_VERx100(xe) == 2001)
+			xe->pat.n_entries = 28; /* Disable CLOS3 */
+		else
+			xe->pat.n_entries = ARRAY_SIZE(xe2_pat_table);
+
 		xe->pat.idx[XE_CACHE_NONE] = 3;
 		xe->pat.idx[XE_CACHE_WT] = 15;
 		xe->pat.idx[XE_CACHE_WB] = 2;
@@ -91,13 +91,13 @@ int xe_pm_suspend(struct xe_device *xe)
 	for_each_gt(gt, xe, id)
 		xe_gt_suspend_prepare(gt);

+	xe_display_pm_suspend(xe, false);
+
 	/* FIXME: Super racey... */
 	err = xe_bo_evict_all(xe);
 	if (err)
 		goto err;

-	xe_display_pm_suspend(xe, false);
-
 	for_each_gt(gt, xe, id) {
 		err = xe_gt_suspend(gt);
 		if (err) {
@@ -151,11 +151,11 @@ int xe_pm_resume(struct xe_device *xe)

 	xe_irq_resume(xe);

-	xe_display_pm_resume(xe, false);
-
 	for_each_gt(gt, xe, id)
 		xe_gt_resume(gt);

+	xe_display_pm_resume(xe, false);
+
 	err = xe_bo_restore_user(xe);
 	if (err)
 		goto err;
@@ -363,10 +363,11 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
 	mutex_unlock(&xe->mem_access.vram_userfault.lock);

 	if (xe->d3cold.allowed) {
+		xe_display_pm_suspend(xe, true);
+
 		err = xe_bo_evict_all(xe);
 		if (err)
 			goto out;
-		xe_display_pm_suspend(xe, true);
 	}

 	for_each_gt(gt, xe, id) {
@@ -128,8 +128,9 @@ xe_preempt_fence_arm(struct xe_preempt_fence *pfence, struct xe_exec_queue *q,
 {
 	list_del_init(&pfence->link);
 	pfence->q = xe_exec_queue_get(q);
+	spin_lock_init(&pfence->lock);
 	dma_fence_init(&pfence->base, &preempt_fence_ops,
-		      &q->lr.lock, context, seqno);
+		      &pfence->lock, context, seqno);

 	return &pfence->base;
 }
@@ -25,6 +25,8 @@ struct xe_preempt_fence {
 	struct xe_exec_queue *q;
 	/** @preempt_work: work struct which issues preemption */
 	struct work_struct preempt_work;
+	/** @lock: dma-fence fence lock */
+	spinlock_t lock;
 	/** @error: preempt fence is in error state */
 	int error;
 };
@@ -171,12 +171,13 @@ void xe_sched_job_destroy(struct kref *ref)
 	struct xe_sched_job *job =
 		container_of(ref, struct xe_sched_job, refcount);
 	struct xe_device *xe = job_to_xe(job);
+	struct xe_exec_queue *q = job->q;

 	xe_sched_job_free_fences(job);
-	xe_exec_queue_put(job->q);
 	dma_fence_put(job->fence);
 	drm_sched_job_cleanup(&job->drm);
 	job_free(job);
+	xe_exec_queue_put(q);
 	xe_pm_runtime_put(xe);
 }

@@ -309,7 +309,7 @@ DECLARE_EVENT_CLASS(xe_hw_fence,
 		    TP_ARGS(fence),

 		    TP_STRUCT__entry(
-			     __string(dev, __dev_name_gt(fence->ctx->gt))
+			     __string(dev, __dev_name_xe(fence->xe))
 			     __field(u64, ctx)
 			     __field(u32, seqno)
 			     __field(struct xe_hw_fence *, fence)
@@ -486,6 +486,10 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 	  XE_RTP_RULES(GRAPHICS_VERSION(2004), FUNC(xe_rtp_match_first_render_or_compute)),
 	  XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, SLM_WMTP_RESTORE))
 	},
+	{ XE_RTP_NAME("14021402888"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
+	  XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
+	},

 	/* Xe2_HPG */

@@ -538,6 +542,20 @@ static const struct xe_rtp_entry_sr engine_was[] = {
 	  XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
 	  XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
 	},
+	{ XE_RTP_NAME("14021821874"),
+	  XE_RTP_RULES(GRAPHICS_VERSION(2001), FUNC(xe_rtp_match_first_render_or_compute)),
+	  XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, STK_ID_RESTRICT))
+	},
+
+	/* Xe2_LPM */
+
+	{ XE_RTP_NAME("16021639441"),
+	  XE_RTP_RULES(MEDIA_VERSION(2000)),
+	  XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0),
+			     GHWSP_CSB_REPORT_DIS |
+			     PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS,
+			     XE_RTP_ACTION_FLAG(ENGINE_BASE)))
+	},

 	/* Xe2_HPM */

@@ -29,3 +29,4 @@
 13011645652	GRAPHICS_VERSION(2004)
 22019338487	MEDIA_VERSION(2000)
 		GRAPHICS_VERSION(2001)
+16023588340	GRAPHICS_VERSION(2001)
@@ -171,11 +171,13 @@ err_hid_data:
 void amdtp_hid_remove(struct amdtp_cl_data *cli_data)
 {
 	int i;
+	struct amdtp_hid_data *hid_data;

 	for (i = 0; i < cli_data->num_hid_devices; ++i) {
 		if (cli_data->hid_sensor_hubs[i]) {
-			kfree(cli_data->hid_sensor_hubs[i]->driver_data);
+			hid_data = cli_data->hid_sensor_hubs[i]->driver_data;
 			hid_destroy_device(cli_data->hid_sensor_hubs[i]);
+			kfree(hid_data);
 			cli_data->hid_sensor_hubs[i] = NULL;
 		}
 	}
@@ -1248,6 +1248,9 @@ static const struct hid_device_id asus_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY),
 	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+	    USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
+	  QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
 	    USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD),
 	  QUIRK_ROG_CLAYMORE_II_KEYBOARD },
@@ -106,7 +106,7 @@ static void cougar_fix_g6_mapping(void)
 static __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 				 unsigned int *rsize)
 {
-	if (rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
+	if (*rsize >= 117 && rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
 	    (rdesc[115] | rdesc[116] << 8) >= HID_MAX_USAGES) {
 		hid_info(hdev,
 			"usage count exceeds max: fixing up report descriptor\n");
@@ -210,6 +210,7 @@
 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD3	0x1a30
 #define USB_DEVICE_ID_ASUSTEK_ROG_Z13_LIGHTBAR		0x18c6
 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY		0x1abe
+#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X		0x1b4c
 #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD	0x196b
 #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD	0x1869

@@ -520,6 +521,8 @@
 #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100

 #define I2C_VENDOR_ID_GOODIX		0x27c6
+#define I2C_DEVICE_ID_GOODIX_01E8	0x01e8
+#define I2C_DEVICE_ID_GOODIX_01E9	0x01e9
 #define I2C_DEVICE_ID_GOODIX_01F0	0x01f0

 #define USB_VENDOR_ID_GOODTOUCH		0x1aad
@@ -1441,6 +1441,30 @@ static int mt_event(struct hid_device *hid, struct hid_field *field,
 	return 0;
 }

+static __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+			     unsigned int *size)
+{
+	if (hdev->vendor == I2C_VENDOR_ID_GOODIX &&
+	    (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 ||
+	     hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) {
+		if (rdesc[607] == 0x15) {
+			rdesc[607] = 0x25;
+			dev_info(
+				&hdev->dev,
+				"GT7868Q report descriptor fixup is applied.\n");
+		} else {
+			dev_info(
+				&hdev->dev,
+				"The byte is not expected for fixing the report descriptor. \
+It's possible that the touchpad firmware is not suitable for applying the fix. \
+got: %x\n",
+				rdesc[607]);
+		}
+	}
+
+	return rdesc;
+}
+
 static void mt_report(struct hid_device *hid, struct hid_report *report)
 {
 	struct mt_device *td = hid_get_drvdata(hid);
@@ -2035,6 +2059,14 @@ static const struct hid_device_id mt_devices[] = {
 		MT_BT_DEVICE(USB_VENDOR_ID_FRUCTEL,
 			USB_DEVICE_ID_GAMETEL_MT_MODE) },

+	/* Goodix GT7868Q devices */
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+	  HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
+		     I2C_DEVICE_ID_GOODIX_01E8) },
+	{ .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
+	  HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
+		     I2C_DEVICE_ID_GOODIX_01E8) },
+
 	/* GoodTouch panels */
 	{ .driver_data = MT_CLS_NSMU,
 		MT_USB_DEVICE(USB_VENDOR_ID_GOODTOUCH,
@@ -2270,6 +2302,7 @@ static struct hid_driver mt_driver = {
 	.feature_mapping = mt_feature_mapping,
 	.usage_table = mt_grabbed_usages,
 	.event = mt_event,
+	.report_fixup = mt_report_fixup,
 	.report = mt_report,
 	.suspend = pm_ptr(mt_suspend),
 	.reset_resume = pm_ptr(mt_reset_resume),
@@ -1878,12 +1878,14 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage,
 	int fmax = field->logical_maximum;
 	unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid);
 	int resolution_code = code;
-	int resolution = hidinput_calc_abs_res(field, resolution_code);
+	int resolution;

 	if (equivalent_usage == HID_DG_TWIST) {
 		resolution_code = ABS_RZ;
 	}

+	resolution = hidinput_calc_abs_res(field, resolution_code);
+
 	if (equivalent_usage == HID_GD_X) {
 		fmin += features->offset_left;
 		fmax -= features->offset_right;
@@ -182,8 +182,11 @@ static int adc_joystick_set_axes(struct device *dev, struct adc_joystick *joy)
 			swap(range[0], range[1]);
 		}

-		fwnode_property_read_u32(child, "abs-fuzz", &fuzz);
-		fwnode_property_read_u32(child, "abs-flat", &flat);
+		if (fwnode_property_read_u32(child, "abs-fuzz", &fuzz))
+			fuzz = 0;
+
+		if (fwnode_property_read_u32(child, "abs-flat", &flat))
+			flat = 0;

 		input_set_abs_params(joy->input, axes[i].code,
 				     range[0], range[1], fuzz, flat);
@@ -417,6 +417,20 @@ static int uinput_validate_absinfo(struct input_dev *dev, unsigned int code,
 		return -EINVAL;
 	}

+	/*
+	 * Limit number of contacts to a reasonable value (100). This
+	 * ensures that we need less than 2 pages for struct input_mt
+	 * (we are not using in-kernel slot assignment so not going to
+	 * allocate memory for the "red" table), and we should have no
+	 * trouble getting this much memory.
+	 */
+	if (code == ABS_MT_SLOT && max > 99) {
+		printk(KERN_DEBUG
+		       "%s: unreasonably large number of slots requested: %d\n",
+		       UINPUT_NAME, max);
+		return -EINVAL;
+	}
+
 	return 0;
 }

@@ -189,6 +189,7 @@ static const char * const smbus_pnp_ids[] = {
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
 	"LEN2068", /* T14 Gen 1 */
+	"SYN3015", /* HP EliteBook 840 G2 */
 	"SYN3052", /* HP EliteBook 840 G4 */
 	"SYN3221", /* HP 15-ay000 */
 	"SYN323d", /* HP Spectre X360 13-w013dx */
@@ -83,6 +83,7 @@ static inline void i8042_write_command(int val)
 #define SERIO_QUIRK_KBDRESET		BIT(12)
 #define SERIO_QUIRK_DRITEK		BIT(13)
 #define SERIO_QUIRK_NOPNP		BIT(14)
+#define SERIO_QUIRK_FORCENORESTORE	BIT(15)

 /* Quirk table for different mainboards. Options similar or identical to i8042
 * module parameters.
@@ -626,6 +627,15 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		},
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
 	},
+	{
+		/* Fujitsu Lifebook E756 */
+		/* https://bugzilla.suse.com/show_bug.cgi?id=1229056 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E756"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_NOMUX)
+	},
 	{
 		/* Fujitsu Lifebook E5411 */
 		.matches = {
@@ -1149,18 +1159,10 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/*
-		 * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes
-		 * the keyboard very laggy for ~5 seconds after boot and
-		 * sometimes also after resume.
-		 * However both are required for the keyboard to not fail
-		 * completely sometimes after boot or resume.
-		 */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "N150CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1685,6 +1687,8 @@ static void __init i8042_check_quirks(void)
 	if (quirks & SERIO_QUIRK_NOPNP)
 		i8042_nopnp = true;
 #endif
+	if (quirks & SERIO_QUIRK_FORCENORESTORE)
+		i8042_forcenorestore = true;
 }
 #else
 static inline void i8042_check_quirks(void) {}
@@ -1718,7 +1722,7 @@ static int __init i8042_platform_init(void)

 	i8042_check_quirks();

-	pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
+	pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
 		i8042_nokbd ? " nokbd" : "",
 		i8042_noaux ? " noaux" : "",
 		i8042_nomux ? " nomux" : "",
@@ -1738,10 +1742,11 @@ static int __init i8042_platform_init(void)
 		"",
 #endif
 #ifdef CONFIG_PNP
-		i8042_nopnp ? " nopnp" : "");
+		i8042_nopnp ? " nopnp" : "",
 #else
-		"");
+		"",
 #endif
+		i8042_forcenorestore ? " forcenorestore" : "");

 	retval = i8042_pnp_init();
 	if (retval)
@@ -115,6 +115,10 @@ module_param_named(nopnp, i8042_nopnp, bool, 0);
 MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings");
 #endif

+static bool i8042_forcenorestore;
+module_param_named(forcenorestore, i8042_forcenorestore, bool, 0);
+MODULE_PARM_DESC(forcenorestore, "Force no restore on s3 resume, copying s2idle behaviour");
+
 #define DEBUG
 #ifdef DEBUG
 static bool i8042_debug;
@@ -1232,7 +1236,7 @@ static int i8042_pm_suspend(struct device *dev)
 {
 	int i;

-	if (pm_suspend_via_firmware())
+	if (!i8042_forcenorestore && pm_suspend_via_firmware())
 		i8042_controller_reset(true);

 	/* Set up serio interrupts for system wakeup. */
@@ -1248,7 +1252,7 @@ static int i8042_pm_suspend(struct device *dev)

 static int i8042_pm_resume_noirq(struct device *dev)
 {
-	if (!pm_resume_via_firmware())
+	if (i8042_forcenorestore || !pm_resume_via_firmware())
 		i8042_interrupt(0, NULL);

 	return 0;
@@ -1271,7 +1275,7 @@ static int i8042_pm_resume(struct device *dev)
 	 * not restore the controller state to whatever it had been at boot
 	 * time, so we do not need to do anything.
 	 */
-	if (!pm_suspend_via_firmware())
+	if (i8042_forcenorestore || !pm_suspend_via_firmware())
 		return 0;

 	/*
@@ -824,7 +824,7 @@ static void ads7846_read_state(struct ads7846 *ts)
 		m = &ts->msg[msg_idx];
 		error = spi_sync(ts->spi, m);
 		if (error) {
-			dev_err(&ts->spi->dev, "spi_sync --> %d\n", error);
+			dev_err_ratelimited(&ts->spi->dev, "spi_sync --> %d\n", error);
 			packet->ignore = true;
 			return;
 		}
@@ -1474,6 +1474,10 @@ static const struct edt_i2c_chip_data edt_ft6236_data = {
 	.max_support_points = 2,
 };

+static const struct edt_i2c_chip_data edt_ft8201_data = {
+	.max_support_points = 10,
+};
+
 static const struct edt_i2c_chip_data edt_ft8719_data = {
 	.max_support_points = 10,
 };
@@ -1485,6 +1489,7 @@ static const struct i2c_device_id edt_ft5x06_ts_id[] = {
 	{ .name = "ft5452", .driver_data = (long)&edt_ft5452_data },
 	/* Note no edt- prefix for compatibility with the ft6236.c driver */
 	{ .name = "ft6236", .driver_data = (long)&edt_ft6236_data },
+	{ .name = "ft8201", .driver_data = (long)&edt_ft8201_data },
 	{ .name = "ft8719", .driver_data = (long)&edt_ft8719_data },
 	{ /* sentinel */ }
 };
@@ -1500,6 +1505,7 @@ static const struct of_device_id edt_ft5x06_of_match[] = {
 	{ .compatible = "focaltech,ft5452", .data = &edt_ft5452_data },
 	/* Note focaltech vendor prefix for compatibility with ft6236.c */
 	{ .compatible = "focaltech,ft6236", .data = &edt_ft6236_data },
+	{ .compatible = "focaltech,ft8201", .data = &edt_ft8201_data },
 	{ .compatible = "focaltech,ft8719", .data = &edt_ft8719_data },
 	{ /* sentinel */ }
 };
@@ -130,17 +130,6 @@ static int himax_bus_read(struct himax_ts_data *ts, u32 address, void *dst,
 	return 0;
 }

-static int himax_read_mcu(struct himax_ts_data *ts, u32 address, u32 *dst)
-{
-	int error;
-
-	error = himax_bus_read(ts, address, dst, sizeof(dst));
-	if (error)
-		return error;
-
-	return 0;
-}
-
 static void himax_reset(struct himax_ts_data *ts)
 {
 	gpiod_set_value_cansleep(ts->gpiod_rst, 1);
@@ -160,7 +149,8 @@ static int himax_read_product_id(struct himax_ts_data *ts, u32 *product_id)
 {
 	int error;

-	error = himax_read_mcu(ts, HIMAX_REG_ADDR_ICID, product_id);
+	error = himax_bus_read(ts, HIMAX_REG_ADDR_ICID, product_id,
+			       sizeof(*product_id));
 	if (error)
 		return error;

@@ -526,7 +526,7 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 err_unresv:
 	if (hwpt_is_paging(hwpt))
 		iommufd_group_remove_reserved_iova(igroup,
-						   to_hwpt_paging(old_hwpt));
+						   to_hwpt_paging(hwpt));
 err_unlock:
 	mutex_unlock(&idev->igroup->lock);
 	return ERR_PTR(rc);
@@ -273,7 +273,7 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 	return 0;
 }

-const struct iommu_dirty_ops dirty_ops = {
+static const struct iommu_dirty_ops dirty_ops = {
 	.set_dirty_tracking = mock_domain_set_dirty_tracking,
 	.read_and_clear_dirty = mock_domain_read_and_clear_dirty,
 };
@@ -3125,13 +3125,13 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,
 	test->buffer = kzalloc(BUFFER_SIZE, GFP_KERNEL);
 #ifdef CONFIG_HIGHMEM
 	test->highmem = alloc_pages(GFP_KERNEL | __GFP_HIGHMEM, BUFFER_ORDER);
+	if (!test->highmem) {
+		count = -ENOMEM;
+		goto free_test_buffer;
+	}
 #endif

-#ifdef CONFIG_HIGHMEM
-	if (test->buffer && test->highmem) {
-#else
 	if (test->buffer) {
-#endif
 		mutex_lock(&mmc_test_lock);
 		mmc_test_run(test, testcase);
 		mutex_unlock(&mmc_test_lock);
@@ -3139,6 +3139,7 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,

 #ifdef CONFIG_HIGHMEM
 	__free_pages(test->highmem, BUFFER_ORDER);
+free_test_buffer:
 #endif
 	kfree(test->buffer);
 	kfree(test);
@@ -3299,6 +3299,10 @@ int dw_mci_probe(struct dw_mci *host)
 	host->biu_clk = devm_clk_get(host->dev, "biu");
 	if (IS_ERR(host->biu_clk)) {
 		dev_dbg(host->dev, "biu clock not available\n");
+		ret = PTR_ERR(host->biu_clk);
+		if (ret == -EPROBE_DEFER)
+			return ret;
+
 	} else {
 		ret = clk_prepare_enable(host->biu_clk);
 		if (ret) {
@@ -3310,6 +3314,10 @@ int dw_mci_probe(struct dw_mci *host)
 	host->ciu_clk = devm_clk_get(host->dev, "ciu");
 	if (IS_ERR(host->ciu_clk)) {
 		dev_dbg(host->dev, "ciu clock not available\n");
+		ret = PTR_ERR(host->ciu_clk);
+		if (ret == -EPROBE_DEFER)
+			goto err_clk_biu;
+
 		host->bus_hz = host->pdata->bus_hz;
 	} else {
 		ret = clk_prepare_enable(host->ciu_clk);
@@ -1230,7 +1230,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
 	}

 	if (!sbc_error && !(events & MSDC_INT_CMDRDY)) {
-		if (events & MSDC_INT_CMDTMO ||
+		if ((events & MSDC_INT_CMDTMO && !host->hs400_tuning) ||
 		    (!mmc_op_tuning(cmd->opcode) && !host->hs400_tuning))
 			/*
 			 * should not clear fifo/interrupt as the tune data
@@ -1323,9 +1323,9 @@ static void msdc_start_command(struct msdc_host *host,
 static void msdc_cmd_next(struct msdc_host *host,
 		struct mmc_request *mrq, struct mmc_command *cmd)
 {
-	if ((cmd->error &&
-	    !(cmd->error == -EILSEQ &&
-	      (mmc_op_tuning(cmd->opcode) || host->hs400_tuning))) ||
+	if ((cmd->error && !host->hs400_tuning &&
+	     !(cmd->error == -EILSEQ &&
+	     mmc_op_tuning(cmd->opcode))) ||
 	    (mrq->sbc && mrq->sbc->error))
 		msdc_request_done(host, mrq);
 	else if (cmd == mrq->sbc)
@@ -582,7 +582,6 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
 		} else {
 			slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
 		}
-		ipsec->xs->xso.real_dev = NULL;
 	}
 	spin_unlock_bh(&bond->ipsec_lock);
 	rcu_read_unlock();
@@ -599,34 +598,30 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 	struct net_device *real_dev;
 	struct slave *curr_active;
 	struct bonding *bond;
-	int err;
+	bool ok = false;

 	bond = netdev_priv(bond_dev);
 	rcu_read_lock();
 	curr_active = rcu_dereference(bond->curr_active_slave);
+	if (!curr_active)
+		goto out;
 	real_dev = curr_active->dev;

-	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
-		err = false;
+	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
 		goto out;
-	}

-	if (!xs->xso.real_dev) {
-		err = false;
+	if (!xs->xso.real_dev)
 		goto out;
-	}

 	if (!real_dev->xfrmdev_ops ||
 	    !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
-	    netif_is_bond_master(real_dev)) {
-		err = false;
+	    netif_is_bond_master(real_dev))
 		goto out;
-	}

-	err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+	ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
 out:
 	rcu_read_unlock();
-	return err;
+	return ok;
 }

 static const struct xfrmdev_ops bond_xfrmdev_ops = {
@@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond,
 	/* check to see if we are clearing active */
 	if (!slave_dev) {
 		netdev_dbg(bond->dev, "Clearing current active slave\n");
-		RCU_INIT_POINTER(bond->curr_active_slave, NULL);
+		bond_change_active_slave(bond, NULL);
 		bond_select_active_slave(bond);
 	} else {
 		struct slave *old_active = rtnl_dereference(bond->curr_active_slave);
@@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
 	struct ksz_port *prt;
 	struct dsa_port *dp;
 	bool tag_en = false;
-	int ret;

 	dsa_switch_for_each_user_port(dp, dev->ds) {
 		prt = &dev->ports[dp->index];
@@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
 	}

 	if (tag_en) {
-		ret = ptp_schedule_worker(ptp_data->clock, 0);
-		if (ret)
-			return ret;
+		ptp_schedule_worker(ptp_data->clock, 0);
 	} else {
 		ptp_cancel_worker_sync(ptp_data->clock);
 	}
--- a/Show More
+++ b/Show More