Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR. Conflicts: drivers/net/ethernet/faraday/ftgmac100.c 4186c8d9e6 ("net: ftgmac100: Ensure tx descriptor updates are visible") e24a6c8746 ("net: ftgmac100: Get link speed and duplex for NC-SI") https://lore.kernel.org/0b851ec5-f91d-4dd3-99da-e81b98c9ed28@kernel.org net/ipv4/tcp.c bac76cf898 ("tcp: fix forever orphan socket caused by tcp_abort") edefba66d9 ("tcp: rstreason: introduce SK_RST_REASON_TCP_STATE for active reset") https://lore.kernel.org/20240828112207.5c199d41@canb.auug.org.au No adjacent changes. Link: https://patch.msgid.link/20240829130829.39148-1-pabeni@redhat.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-12-28 16:52:18 +00:00 · 2024-08-08 14:03:51 -07:00 · 2024-08-08 14:03:51 -07:00 · 3cbd2090d3
commit 3cbd2090d3
parent bf4d87f884 0dd5dd63ba
261 changed files with 2619 additions and 1193 deletions
--- a/.mailmap
+++ b/.mailmap
@ -614,6 +614,7 @@ Simon Kelley <simon@thekelleys.org.uk>
 Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org>
 Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
 Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
+Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
 Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
 Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@ -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
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.yaml
@ -42,6 +42,7 @@ properties:
      - focaltech,ft5426
      - focaltech,ft5452
      - focaltech,ft6236
+      - focaltech,ft8201
      - focaltech,ft8719

  reg:
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@ -629,18 +629,6 @@ The preferred style for long (multi-line) comments is:
 	 * with beginning and ending almost-blank lines.
 	 */

-For files in net/ and drivers/net/ the preferred style for long (multi-line)
-comments is a little different.
-
-.. code-block:: c
-
-	/* The preferred comment style for files in net/ and drivers/net
-	 * looks like this.
-	 *
-	 * It is nearly the same as the generally preferred comment style,
-	 * but there is no initial almost-blank line.
-	 */
-
 It's also important to comment data, whether they are basic types or derived
 types.  To this end, use just one data declaration per line (no commas for
 multiple data declarations).  This leaves you room for a small comment on each
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@ -355,23 +355,6 @@ just do it. As a result, a sequence of smaller series gets merged quicker and
 with better review coverage. Re-posting large series also increases the mailing
 list traffic.

-Multi-line comments
-~~~~~~~~~~~~~~~~~~~
-
-Comment style convention is slightly different for networking and most of
-the tree.  Instead of this::
-
-  /*
-   * foobar blah blah blah
-   * another line of text
-   */
-
-it is requested that you make it look like this::
-
-  /* foobar blah blah blah
-   * another line of text
-   */
-
 Local variable ordering ("reverse xmas tree", "RCS")
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

--- a/6
+++ b/6
@ -10176,7 +10176,7 @@ 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
@ -12168,7 +12168,7 @@ KERNEL NFSD, SUNRPC, AND LOCKD SERVERS
 M:	Chuck Lever <chuck.lever@oracle.com>
 M:	Jeff Layton <jlayton@kernel.org>
 R:	Neil Brown <neilb@suse.de>
-R:	Olga Kornievskaia <kolga@netapp.com>
+R:	Olga Kornievskaia <okorniev@redhat.com>
 R:	Dai Ngo <Dai.Ngo@oracle.com>
 R:	Tom Talpey <tom@talpey.com>
 L:	linux-nfs@vger.kernel.org
@ -18547,7 +18547,6 @@ F:	drivers/crypto/intel/qat/

 QCOM AUDIO (ASoC) DRIVERS
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
-M:	Banajit Goswami <bgoswami@quicinc.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 L:	linux-arm-msm@vger.kernel.org
 S:	Supported
@ -20377,6 +20376,7 @@ 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>
--- a/2
+++ b/2
@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 11
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse

 # *DOCUMENTATION*
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@ -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);
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@ -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);

--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@ -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);
 	}
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@ -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);
 }

--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@ -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
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@ -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
--- a/arch/loongarch/include/asm/dma-direct.h
+++ b/arch/loongarch/include/asm/dma-direct.h
@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _LOONGARCH_DMA_DIRECT_H
-#define _LOONGARCH_DMA_DIRECT_H
-
-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
-
-#endif /* _LOONGARCH_DMA_DIRECT_H */
--- a/arch/loongarch/include/asm/hw_irq.h
+++ b/arch/loongarch/include/asm/hw_irq.h
@ -9,6 +9,8 @@

 extern atomic_t irq_err_count;

+#define ARCH_IRQ_INIT_FLAGS	IRQ_NOPROBE
+
 /*
 * interrupt-retrigger: NOP for now. This may not be appropriate for all
 * machines, we'll see ...
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@ -76,7 +76,6 @@ static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
 #endif

 void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
-void kvm_reset_timer(struct kvm_vcpu *vcpu);
 void kvm_save_timer(struct kvm_vcpu *vcpu);
 void kvm_restore_timer(struct kvm_vcpu *vcpu);

--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@ -530,6 +530,10 @@ SYM_FUNC_END(_restore_lasx_context)

 #ifdef CONFIG_CPU_HAS_LBT
 STACK_FRAME_NON_STANDARD _restore_fp
+#ifdef CONFIG_CPU_HAS_LSX
 STACK_FRAME_NON_STANDARD _restore_lsx
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
 STACK_FRAME_NON_STANDARD _restore_lasx
 #endif
+#endif
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@ -102,9 +102,6 @@ void __init init_IRQ(void)
 	mp_ops.init_ipi();
 #endif

-	for (i = 0; i < NR_IRQS; i++)
-		irq_set_noprobe(i);
-
 	for_each_possible_cpu(i) {
 		page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order);

--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@ -277,6 +277,10 @@ SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)

 #ifdef CONFIG_CPU_HAS_LBT
 STACK_FRAME_NON_STANDARD kvm_restore_fpu
+#ifdef CONFIG_CPU_HAS_LSX
 STACK_FRAME_NON_STANDARD kvm_restore_lsx
+#endif
+#ifdef CONFIG_CPU_HAS_LASX
 STACK_FRAME_NON_STANDARD kvm_restore_lasx
 #endif
+#endif
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@ -188,10 +188,3 @@ void kvm_save_timer(struct kvm_vcpu *vcpu)
 	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
 	preempt_enable();
 }
-
-void kvm_reset_timer(struct kvm_vcpu *vcpu)
-{
-	write_gcsr_timercfg(0);
-	kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TCFG, 0);
-	hrtimer_cancel(&vcpu->arch.swtimer);
-}
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@ -647,7 +647,7 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
 				vcpu->kvm->arch.time_offset = (signed long)(v - drdtime());
 			break;
 		case KVM_REG_LOONGARCH_VCPU_RESET:
-			kvm_reset_timer(vcpu);
+			vcpu->arch.st.guest_addr = 0;
 			memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
 			memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
 			break;
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@ -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);
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@ -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!");
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@ -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
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@ -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);
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@ -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);
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@ -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
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@ -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 */
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@ -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();
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@ -39,7 +39,7 @@ PHDRS {

 SECTIONS
 {
-	. = __START_KERNEL;
+	. = TEXT_OFFSET;
 	.text : {
 		_stext = .;		/* Start of text section */
 		_text = .;		/* Text and read-only data */
--- a/arch/s390/tools/relocs.c
+++ b/arch/s390/tools/relocs.c
@ -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);
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@ -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;
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@ -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()))
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@ -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,
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@ -12,6 +12,7 @@
 #include <linux/acpi.h>
 #include <acpi/acpi_bus.h>
 #include <asm/unaligned.h>
+#include <linux/efi.h>

 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@ -26,6 +27,8 @@
 #define ECDSA_OFFSET		644
 #define ECDSA_HEADER_LEN	320

+#define BTINTEL_EFI_DSBR	L"UefiCnvCommonDSBR"
+
 enum {
 	DSM_SET_WDISABLE2_DELAY = 1,
 	DSM_SET_RESET_METHOD = 3,
@ -2616,6 +2619,120 @@ static u8 btintel_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb)
 	return hci_skb_pkt_type(skb);
 }

+/*
+ * UefiCnvCommonDSBR UEFI variable provides information from the OEM platforms
+ * if they have replaced the BRI (Bluetooth Radio Interface) resistor to
+ * overcome the potential STEP errors on their designs. Based on the
+ * configauration, bluetooth firmware shall adjust the BRI response line drive
+ * strength. The below structure represents DSBR data.
+ * struct {
+ *	u8 header;
+ *	u32 dsbr;
+ * } __packed;
+ *
+ * header - defines revision number of the structure
+ * dsbr - defines drive strength BRI response
+ *	bit0
+ *		0 - instructs bluetooth firmware to use default values
+ *		1 - instructs bluetooth firmware to override default values
+ *	bit3:1
+ *		Reserved
+ *	bit7:4
+ *		DSBR override values (only if bit0 is set. Default value is 0xF
+ *	bit31:7
+ *		Reserved
+ * Expected values for dsbr field:
+ *	1. 0xF1 - indicates that the resistor on board is 33 Ohm
+ *	2. 0x00 or 0xB1 - indicates that the resistor on board is 10 Ohm
+ *	3. Non existing UEFI variable or invalid (none of the above) - indicates
+ *	   that the resistor on board is 10 Ohm
+ * Even if uefi variable is not present, driver shall send 0xfc0a command to
+ * firmware to use default values.
+ *
+ */
+static int btintel_uefi_get_dsbr(u32 *dsbr_var)
+{
+	struct btintel_dsbr {
+		u8 header;
+		u32 dsbr;
+	} __packed data;
+
+	efi_status_t status;
+	unsigned long data_size = 0;
+	efi_guid_t guid = EFI_GUID(0xe65d8884, 0xd4af, 0x4b20, 0x8d, 0x03,
+				   0x77, 0x2e, 0xcc, 0x3d, 0xa5, 0x31);
+
+	if (!IS_ENABLED(CONFIG_EFI))
+		return -EOPNOTSUPP;
+
+	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE))
+		return -EOPNOTSUPP;
+
+	status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
+				  NULL);
+
+	if (status != EFI_BUFFER_TOO_SMALL || !data_size)
+		return -EIO;
+
+	status = efi.get_variable(BTINTEL_EFI_DSBR, &guid, NULL, &data_size,
+				  &data);
+
+	if (status != EFI_SUCCESS)
+		return -ENXIO;
+
+	*dsbr_var = data.dsbr;
+	return 0;
+}
+
+static int btintel_set_dsbr(struct hci_dev *hdev, struct intel_version_tlv *ver)
+{
+	struct btintel_dsbr_cmd {
+		u8 enable;
+		u8 dsbr;
+	} __packed;
+
+	struct btintel_dsbr_cmd cmd;
+	struct sk_buff *skb;
+	u8 status;
+	u32 dsbr;
+	bool apply_dsbr;
+	int err;
+
+	/* DSBR command needs to be sent for BlazarI + B0 step product after
+	 * downloading IML image.
+	 */
+	apply_dsbr = (ver->img_type == BTINTEL_IMG_IML &&
+		((ver->cnvi_top & 0xfff) == BTINTEL_CNVI_BLAZARI) &&
+		INTEL_CNVX_TOP_STEP(ver->cnvi_top) == 0x01);
+
+	if (!apply_dsbr)
+		return 0;
+
+	dsbr = 0;
+	err = btintel_uefi_get_dsbr(&dsbr);
+	if (err < 0)
+		bt_dev_dbg(hdev, "Error reading efi: %ls  (%d)",
+			   BTINTEL_EFI_DSBR, err);
+
+	cmd.enable = dsbr & BIT(0);
+	cmd.dsbr = dsbr >> 4 & 0xF;
+
+	bt_dev_info(hdev, "dsbr: enable: 0x%2.2x value: 0x%2.2x", cmd.enable,
+		    cmd.dsbr);
+
+	skb = __hci_cmd_sync(hdev, 0xfc0a, sizeof(cmd), &cmd,  HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb))
+		return -bt_to_errno(PTR_ERR(skb));
+
+	status = skb->data[0];
+	kfree_skb(skb);
+
+	if (status)
+		return -bt_to_errno(status);
+
+	return 0;
+}
+
 int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
 				 struct intel_version_tlv *ver)
 {
@ -2650,6 +2767,13 @@ int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
 	if (err)
 		return err;

+	/* set drive strength of BRI response */
+	err = btintel_set_dsbr(hdev, ver);
+	if (err) {
+		bt_dev_err(hdev, "Failed to send dsbr command (%d)", err);
+		return err;
+	}
+
 	/* If image type returned is BTINTEL_IMG_IML, then controller supports
 	 * intermediate loader image
 	 */
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@ -449,6 +449,23 @@ static bool ps_wakeup(struct btnxpuart_dev *nxpdev)
 	return false;
 }

+static void ps_cleanup(struct btnxpuart_dev *nxpdev)
+{
+	struct ps_data *psdata = &nxpdev->psdata;
+	u8 ps_state;
+
+	mutex_lock(&psdata->ps_lock);
+	ps_state = psdata->ps_state;
+	mutex_unlock(&psdata->ps_lock);
+
+	if (ps_state != PS_STATE_AWAKE)
+		ps_control(psdata->hdev, PS_STATE_AWAKE);
+
+	ps_cancel_timer(nxpdev);
+	cancel_work_sync(&psdata->work);
+	mutex_destroy(&psdata->ps_lock);
+}
+
 static int send_ps_cmd(struct hci_dev *hdev, void *data)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
@ -1363,7 +1380,6 @@ static int btnxpuart_close(struct hci_dev *hdev)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);

-	ps_wakeup(nxpdev);
 	serdev_device_close(nxpdev->serdev);
 	skb_queue_purge(&nxpdev->txq);
 	if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) {
@ -1516,8 +1532,8 @@ static void nxp_serdev_remove(struct serdev_device *serdev)
 			nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
 			nxp_set_baudrate_cmd(hdev, NULL);
 		}
-		ps_cancel_timer(nxpdev);
 	}
+	ps_cleanup(nxpdev);
 	hci_unregister_dev(hdev);
 	hci_free_dev(hdev);
 }
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@ -698,6 +698,10 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
 		rc = tpm2_get_cc_attrs_tbl(chip);
 		if (rc)
 			goto init_irq_cleanup;
+
+		rc = tpm2_sessions_init(chip);
+		if (rc)
+			goto init_irq_cleanup;
 	}

 	return tpm_chip_register(chip);
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@ -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);
 		}
 	}

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@ -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);
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@ -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;

--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@ -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 "
--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
@ -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))
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@ -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)) {
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@ -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);
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@ -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), \
 	}
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@ -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__)
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@ -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;
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@ -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))
--- a/drivers/gpu/drm/msm/dp/dp_panel.c
+++ b/drivers/gpu/drm/msm/dp/dp_panel.c
@ -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);

--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@ -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,
 };

--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
@ -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;
--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
@ -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);

--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@ -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 \
--- a/drivers/gpu/drm/xe/display/xe_display.c
+++ b/drivers/gpu/drm/xe/display/xe_display.c
@ -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);
--- a/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
+++ b/drivers/gpu/drm/xe/display/xe_dsb_buffer.c
@ -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)
--- a/drivers/gpu/drm/xe/display/xe_fb_pin.c
+++ b/drivers/gpu/drm/xe/display/xe_fb_pin.c
@ -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:
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@ -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)
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@ -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;
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@ -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) ?
--- a/drivers/gpu/drm/xe/xe_device.h
+++ b/drivers/gpu/drm/xe/xe_device.h
@ -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)
 {
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@ -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))
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@ -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 */
--- a/drivers/gpu/drm/xe/xe_gsc.c
+++ b/drivers/gpu/drm/xe/xe_gsc.c
@ -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 @@ int xe_gsc_init(struct xe_gsc *gsc)
 	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;

--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@ -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");

--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@ -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)
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@ -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 */
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@ -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");
--- a/drivers/gpu/drm/xe/xe_hw_fence.c
+++ b/drivers/gpu/drm/xe/xe_hw_fence.c
@ -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);

--- a/drivers/gpu/drm/xe/xe_hw_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_hw_fence_types.h
@ -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 */
--- a/drivers/gpu/drm/xe/xe_mmio.c
+++ b/drivers/gpu/drm/xe/xe_mmio.c
@ -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 @@ int xe_mmio_probe_tiles(struct xe_device *xe)
 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
--- a/drivers/gpu/drm/xe/xe_observation.c
+++ b/drivers/gpu/drm/xe/xe_observation.c
@ -66,7 +66,6 @@ static struct ctl_table observation_ctl_table[] = {
 	 .extra1 = SYSCTL_ZERO,
 	 .extra2 = SYSCTL_ONE,
 	 },
-	{}
 };

 /**
--- a/drivers/gpu/drm/xe/xe_pat.c
+++ b/drivers/gpu/drm/xe/xe_pat.c
@ -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;
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@ -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) {
--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
+++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
@ -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;
 }
--- a/drivers/gpu/drm/xe/xe_preempt_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
@ -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;
 };
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@ -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);
 }

--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@ -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)
--- a/drivers/gpu/drm/xe/xe_wa.c
+++ b/drivers/gpu/drm/xe/xe_wa.c
@ -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 */

--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@ -29,3 +29,4 @@
 13011645652	GRAPHICS_VERSION(2004)
 22019338487	MEDIA_VERSION(2000)
 		GRAPHICS_VERSION(2001)
+16023588340	GRAPHICS_VERSION(2001)
--- a/drivers/input/joystick/adc-joystick.c
+++ b/drivers/input/joystick/adc-joystick.c
@ -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);
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@ -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;
 }

--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@ -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 */
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@ -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)
--- a/drivers/input/serio/i8042.c
+++ b/drivers/input/serio/i8042.c
@ -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;

 	/*
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@ -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;
 		}
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@ -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 */ }
 };
--- a/drivers/input/touchscreen/himax_hx83112b.c
+++ b/drivers/input/touchscreen/himax_hx83112b.c
@ -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;

--- a/drivers/mmc/core/mmc_test.c
+++ b/drivers/mmc/core/mmc_test.c
@ -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);
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@ -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);
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@ -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)
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@ -427,6 +427,8 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 			     struct netlink_ext_ack *extack)
 {
 	struct net_device *bond_dev = xs->xso.dev;
+	struct net_device *real_dev;
+	netdevice_tracker tracker;
 	struct bond_ipsec *ipsec;
 	struct bonding *bond;
 	struct slave *slave;
@ -438,74 +440,80 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
 	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
 	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave) {
-		rcu_read_unlock();
-		return -ENODEV;
+	real_dev = slave ? slave->dev : NULL;
+	netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+	rcu_read_unlock();
+	if (!real_dev) {
+		err = -ENODEV;
+		goto out;
 	}

-	if (!slave->dev->xfrmdev_ops ||
-	    !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
-	    netif_is_bond_master(slave->dev)) {
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+	    netif_is_bond_master(real_dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
-		rcu_read_unlock();
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}

-	ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+	ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL);
 	if (!ipsec) {
-		rcu_read_unlock();
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto out;
 	}
-	xs->xso.real_dev = slave->dev;

-	err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
+	xs->xso.real_dev = real_dev;
+	err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
 	if (!err) {
 		ipsec->xs = xs;
 		INIT_LIST_HEAD(&ipsec->list);
-		spin_lock_bh(&bond->ipsec_lock);
+		mutex_lock(&bond->ipsec_lock);
 		list_add(&ipsec->list, &bond->ipsec_list);
-		spin_unlock_bh(&bond->ipsec_lock);
+		mutex_unlock(&bond->ipsec_lock);
 	} else {
 		kfree(ipsec);
 	}
-	rcu_read_unlock();
+out:
+	netdev_put(real_dev, &tracker);
 	return err;
 }

 static void bond_ipsec_add_sa_all(struct bonding *bond)
 {
 	struct net_device *bond_dev = bond->dev;
+	struct net_device *real_dev;
 	struct bond_ipsec *ipsec;
 	struct slave *slave;

-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave)
-		goto out;
+	slave = rtnl_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	if (!real_dev)
+		return;

-	if (!slave->dev->xfrmdev_ops ||
-	    !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
-	    netif_is_bond_master(slave->dev)) {
-		spin_lock_bh(&bond->ipsec_lock);
+	mutex_lock(&bond->ipsec_lock);
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_add ||
+	    netif_is_bond_master(real_dev)) {
 		if (!list_empty(&bond->ipsec_list))
-			slave_warn(bond_dev, slave->dev,
+			slave_warn(bond_dev, real_dev,
 				   "%s: no slave xdo_dev_state_add\n",
 				   __func__);
-		spin_unlock_bh(&bond->ipsec_lock);
 		goto out;
 	}

-	spin_lock_bh(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
-		ipsec->xs->xso.real_dev = slave->dev;
-		if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
-			slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+		/* If new state is added before ipsec_lock acquired */
+		if (ipsec->xs->xso.real_dev == real_dev)
+			continue;
+
+		ipsec->xs->xso.real_dev = real_dev;
+		if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
+			slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
 			ipsec->xs->xso.real_dev = NULL;
 		}
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
 out:
-	rcu_read_unlock();
+	mutex_unlock(&bond->ipsec_lock);
 }

 /**
@ -515,6 +523,8 @@ static void bond_ipsec_add_sa_all(struct bonding *bond)
 static void bond_ipsec_del_sa(struct xfrm_state *xs)
 {
 	struct net_device *bond_dev = xs->xso.dev;
+	struct net_device *real_dev;
+	netdevice_tracker tracker;
 	struct bond_ipsec *ipsec;
 	struct bonding *bond;
 	struct slave *slave;
@ -525,6 +535,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
 	rcu_read_lock();
 	bond = netdev_priv(bond_dev);
 	slave = rcu_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+	rcu_read_unlock();

 	if (!slave)
 		goto out;
@ -532,18 +545,19 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
 	if (!xs->xso.real_dev)
 		goto out;

-	WARN_ON(xs->xso.real_dev != slave->dev);
+	WARN_ON(xs->xso.real_dev != real_dev);

-	if (!slave->dev->xfrmdev_ops ||
-	    !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
-	    netif_is_bond_master(slave->dev)) {
-		slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
+	if (!real_dev->xfrmdev_ops ||
+	    !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+	    netif_is_bond_master(real_dev)) {
+		slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
 		goto out;
 	}

-	slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+	real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
 out:
-	spin_lock_bh(&bond->ipsec_lock);
+	netdev_put(real_dev, &tracker);
+	mutex_lock(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
 		if (ipsec->xs == xs) {
 			list_del(&ipsec->list);
@ -551,40 +565,72 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
 			break;
 		}
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
-	rcu_read_unlock();
+	mutex_unlock(&bond->ipsec_lock);
 }

 static void bond_ipsec_del_sa_all(struct bonding *bond)
 {
 	struct net_device *bond_dev = bond->dev;
+	struct net_device *real_dev;
 	struct bond_ipsec *ipsec;
 	struct slave *slave;

-	rcu_read_lock();
-	slave = rcu_dereference(bond->curr_active_slave);
-	if (!slave) {
-		rcu_read_unlock();
+	slave = rtnl_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	if (!real_dev)
 		return;
-	}

-	spin_lock_bh(&bond->ipsec_lock);
+	mutex_lock(&bond->ipsec_lock);
 	list_for_each_entry(ipsec, &bond->ipsec_list, list) {
 		if (!ipsec->xs->xso.real_dev)
 			continue;

-		if (!slave->dev->xfrmdev_ops ||
-		    !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
-		    netif_is_bond_master(slave->dev)) {
-			slave_warn(bond_dev, slave->dev,
+		if (!real_dev->xfrmdev_ops ||
+		    !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
+		    netif_is_bond_master(real_dev)) {
+			slave_warn(bond_dev, real_dev,
 				   "%s: no slave xdo_dev_state_delete\n",
 				   __func__);
 		} else {
-			slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+			real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+			if (real_dev->xfrmdev_ops->xdo_dev_state_free)
+				real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
 		}
 	}
-	spin_unlock_bh(&bond->ipsec_lock);
+	mutex_unlock(&bond->ipsec_lock);
+}
+
+static void bond_ipsec_free_sa(struct xfrm_state *xs)
+{
+	struct net_device *bond_dev = xs->xso.dev;
+	struct net_device *real_dev;
+	netdevice_tracker tracker;
+	struct bonding *bond;
+	struct slave *slave;
+
+	if (!bond_dev)
+		return;
+
+	rcu_read_lock();
+	bond = netdev_priv(bond_dev);
+	slave = rcu_dereference(bond->curr_active_slave);
+	real_dev = slave ? slave->dev : NULL;
+	netdev_hold(real_dev, &tracker, GFP_ATOMIC);
 	rcu_read_unlock();
+
+	if (!slave)
+		goto out;
+
+	if (!xs->xso.real_dev)
+		goto out;
+
+	WARN_ON(xs->xso.real_dev != real_dev);
+
+	if (real_dev && real_dev->xfrmdev_ops &&
+	    real_dev->xfrmdev_ops->xdo_dev_state_free)
+		real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
+out:
+	netdev_put(real_dev, &tracker);
 }

 /**
@ -627,6 +673,7 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 static const struct xfrmdev_ops bond_xfrmdev_ops = {
 	.xdo_dev_state_add = bond_ipsec_add_sa,
 	.xdo_dev_state_delete = bond_ipsec_del_sa,
+	.xdo_dev_state_free = bond_ipsec_free_sa,
 	.xdo_dev_offload_ok = bond_ipsec_offload_ok,
 };
 #endif /* CONFIG_XFRM_OFFLOAD */
@ -5877,7 +5924,7 @@ void bond_setup(struct net_device *bond_dev)
 	/* set up xfrm device ops (only supported in active-backup right now) */
 	bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
 	INIT_LIST_HEAD(&bond->ipsec_list);
-	spin_lock_init(&bond->ipsec_lock);
+	mutex_init(&bond->ipsec_lock);
 #endif /* CONFIG_XFRM_OFFLOAD */

 	/* don't acquire bond device's netif_tx_lock when transmitting */
@ -5926,6 +5973,10 @@ static void bond_uninit(struct net_device *bond_dev)
 		__bond_release_one(bond_dev, slave->dev, true, true);
 	netdev_info(bond_dev, "Released all slaves\n");

+#ifdef CONFIG_XFRM_OFFLOAD
+	mutex_destroy(&bond->ipsec_lock);
+#endif /* CONFIG_XFRM_OFFLOAD */
+
 	bond_set_slave_arr(bond, NULL, NULL);

 	list_del_rcu(&bond->bond_list);
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@ -582,7 +582,7 @@ static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
 	(*processed)++;
 	return true;

- drop:
+drop:
 	/* Clean rxdes0 (which resets own bit) */
 	rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask);
 	priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer);
@ -666,6 +666,11 @@ static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv)
 	ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat);
 	txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask);

+	/* Ensure the descriptor config is visible before setting the tx
+	 * pointer.
+	 */
+	smp_wmb();
+
 	priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv, pointer);

 	return true;
@ -819,6 +824,11 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	dma_wmb();
 	first->txdes0 = cpu_to_le32(f_ctl_stat);

+	/* Ensure the descriptor config is visible before setting the tx
+	 * pointer.
+	 */
+	smp_wmb();
+
 	/* Update next TX pointer */
 	priv->tx_pointer = pointer;

@ -839,7 +849,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,

 	return NETDEV_TX_OK;

- dma_err:
+dma_err:
 	if (net_ratelimit())
 		netdev_err(netdev, "map tx fragment failed\n");

@ -861,7 +871,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	 * last fragment, so we know ftgmac100_free_tx_packet()
 	 * hasn't freed the skb yet.
 	 */
- drop:
+drop:
 	/* Drop the packet */
 	dev_kfree_skb_any(skb);
 	netdev->stats.tx_dropped++;
@ -1354,7 +1364,7 @@ static void ftgmac100_reset(struct ftgmac100 *priv)
 	ftgmac100_init_all(priv, true);

 	netdev_dbg(netdev, "Reset done !\n");
- bail:
+bail:
 	if (priv->mii_bus)
 		mutex_unlock(&priv->mii_bus->mdio_lock);
 	if (netdev->phydev)
@ -1554,16 +1564,16 @@ static int ftgmac100_open(struct net_device *netdev)

 	return 0;

- err_ncsi:
+err_ncsi:
 	phy_stop(netdev->phydev);
 	napi_disable(&priv->napi);
 	netif_stop_queue(netdev);
- err_alloc:
+err_alloc:
 	ftgmac100_free_buffers(priv);
 	free_irq(netdev->irq, netdev);
- err_irq:
+err_irq:
 	netif_napi_del(&priv->napi);
- err_hw:
+err_hw:
 	iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
 	ftgmac100_free_rings(priv);
 	return err;
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@ -52,32 +52,6 @@ static int mana_hwc_verify_resp_msg(const struct hwc_caller_ctx *caller_ctx,
 	return 0;
 }

-static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
-				 const struct gdma_resp_hdr *resp_msg)
-{
-	struct hwc_caller_ctx *ctx;
-	int err;
-
-	if (!test_bit(resp_msg->response.hwc_msg_id,
-		      hwc->inflight_msg_res.map)) {
-		dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n",
-			resp_msg->response.hwc_msg_id);
-		return;
-	}
-
-	ctx = hwc->caller_ctx + resp_msg->response.hwc_msg_id;
-	err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
-	if (err)
-		goto out;
-
-	ctx->status_code = resp_msg->status;
-
-	memcpy(ctx->output_buf, resp_msg, resp_len);
-out:
-	ctx->error = err;
-	complete(&ctx->comp_event);
-}
-
 static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
 				struct hwc_work_request *req)
 {
@ -101,6 +75,40 @@ static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
 	return err;
 }

+static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
+				 struct hwc_work_request *rx_req)
+{
+	const struct gdma_resp_hdr *resp_msg = rx_req->buf_va;
+	struct hwc_caller_ctx *ctx;
+	int err;
+
+	if (!test_bit(resp_msg->response.hwc_msg_id,
+		      hwc->inflight_msg_res.map)) {
+		dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n",
+			resp_msg->response.hwc_msg_id);
+		mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+		return;
+	}
+
+	ctx = hwc->caller_ctx + resp_msg->response.hwc_msg_id;
+	err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len);
+	if (err)
+		goto out;
+
+	ctx->status_code = resp_msg->status;
+
+	memcpy(ctx->output_buf, resp_msg, resp_len);
+out:
+	ctx->error = err;
+
+	/* Must post rx wqe before complete(), otherwise the next rx may
+	 * hit no_wqe error.
+	 */
+	mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+
+	complete(&ctx->comp_event);
+}
+
 static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
 					struct gdma_event *event)
 {
@ -235,14 +243,12 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id,
 		return;
 	}

-	mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, resp);
+	mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req);

-	/* Do no longer use 'resp', because the buffer is posted to the HW
-	 * in the below mana_hwc_post_rx_wqe().
+	/* Can no longer use 'resp', because the buffer is posted to the HW
+	 * in mana_hwc_handle_resp() above.
 	 */
 	resp = NULL;
-
-	mana_hwc_post_rx_wqe(hwc_rxq, rx_req);
 }

 static void mana_hwc_tx_event_handler(void *ctx, u32 gdma_txq_id,
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
@ -32,7 +32,7 @@
 #define IONIC_ADMIN_DOORBELL_DEADLINE	(HZ / 2)	/* 500ms */
 #define IONIC_TX_DOORBELL_DEADLINE	(HZ / 100)	/* 10ms */
 #define IONIC_RX_MIN_DOORBELL_DEADLINE	(HZ / 100)	/* 10ms */
-#define IONIC_RX_MAX_DOORBELL_DEADLINE	(HZ * 5)	/* 5s */
+#define IONIC_RX_MAX_DOORBELL_DEADLINE	(HZ * 4)	/* 4s */

 struct ionic_dev_bar {
 	void __iomem *vaddr;
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@ -3220,7 +3220,7 @@ int ionic_lif_alloc(struct ionic *ionic)
 	netdev->netdev_ops = &ionic_netdev_ops;
 	ionic_ethtool_set_ops(netdev);

-	netdev->watchdog_timeo = 2 * HZ;
+	netdev->watchdog_timeo = 5 * HZ;
 	netif_carrier_off(netdev);

 	lif->identity = lid;
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@ -1459,6 +1459,7 @@ static const struct prueth_pdata am654_icssg_pdata = {

 static const struct prueth_pdata am64x_icssg_pdata = {
 	.fdqring_mode = K3_RINGACC_RING_MODE_RING,
+	.quirk_10m_link_issue = 1,
 	.switch_mode = 1,
 };

--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@ -1653,7 +1653,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
 	sock = sockfd_lookup(fd, &err);
 	if (!sock) {
 		pr_debug("gtp socket fd=%d not found\n", fd);
-		return NULL;
+		return ERR_PTR(err);
 	}

 	sk = sock->sk;
--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
@ -725,22 +725,25 @@ int iwl_acpi_get_wgds_table(struct iwl_fw_runtime *fwrt)
 				entry = &wifi_pkg->package.elements[entry_idx];
 				entry_idx++;
 				if (entry->type != ACPI_TYPE_INTEGER ||
-				    entry->integer.value > num_profiles) {
+				    entry->integer.value > num_profiles ||
+				    entry->integer.value <
+					rev_data[idx].min_profiles) {
 					ret = -EINVAL;
 					goto out_free;
 				}
-				num_profiles = entry->integer.value;

 				/*
-				 * this also validates >= min_profiles since we
-				 * otherwise wouldn't have gotten the data when
-				 * looking up in ACPI
+				 * Check to see if we received package count
+				 * same as max # of profiles
 				 */
 				if (wifi_pkg->package.count !=
 				    hdr_size + profile_size * num_profiles) {
 					ret = -EINVAL;
 					goto out_free;
 				}
+
+				/* Number of valid profiles */
+				num_profiles = entry->integer.value;
 			}
 			goto read_table;
 		}
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@ -3348,7 +3348,7 @@ void iwl_fw_dbg_stop_restart_recording(struct iwl_fw_runtime *fwrt,
 {
 	int ret __maybe_unused = 0;

-	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status))
+	if (!iwl_trans_fw_running(fwrt->trans))
 		return;

 	if (fw_has_capa(&fwrt->fw->ucode_capa,
--- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h
@ -85,6 +85,10 @@ struct iwl_cfg;
 *	May sleep
 * @wimax_active: invoked when WiMax becomes active. May sleep
 * @time_point: called when transport layer wants to collect debug data
+ * @device_powered_off: called upon resume from hibernation but not only.
+ *	Op_mode needs to reset its internal state because the device did not
+ *	survive the system state transition. The firmware is no longer running,
+ *	etc...
 */
 struct iwl_op_mode_ops {
 	struct iwl_op_mode *(*start)(struct iwl_trans *trans,
@ -107,6 +111,7 @@ struct iwl_op_mode_ops {
 	void (*time_point)(struct iwl_op_mode *op_mode,
 			   enum iwl_fw_ini_time_point tp_id,
 			   union iwl_dbg_tlv_tp_data *tp_data);
+	void (*device_powered_off)(struct iwl_op_mode *op_mode);
 };

 int iwl_opmode_register(const char *name, const struct iwl_op_mode_ops *ops);
@ -204,4 +209,11 @@ static inline void iwl_op_mode_time_point(struct iwl_op_mode *op_mode,
 	op_mode->ops->time_point(op_mode, tp_id, tp_data);
 }

+static inline void iwl_op_mode_device_powered_off(struct iwl_op_mode *op_mode)
+{
+	if (!op_mode || !op_mode->ops || !op_mode->ops->device_powered_off)
+		return;
+	op_mode->ops->device_powered_off(op_mode);
+}
+
 #endif /* __iwl_op_mode_h__ */
--- a/Show More
+++ b/Show More