Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/arm/kernel/.gitignore b/arch/arm/kernel/.gitignore
index c5f676c..bbb90f9 100644
--- a/arch/arm/kernel/.gitignore
+++ b/arch/arm/kernel/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
 vmlinux.lds
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 8b679e2..79588b5 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -53,8 +53,8 @@
 obj-$(CONFIG_HAVE_ARM_TWD)	+= smp_twd.o
 obj-$(CONFIG_ARM_ARCH_TIMER)	+= arch_timer.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= entry-ftrace.o
-obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
-obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o patch.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o patch.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 # Main staffs in KPROBES are in arch/arm/probes/ .
@@ -106,4 +106,6 @@
 
 obj-$(CONFIG_HAVE_ARM_SMCCC)	+= smccc-call.o
 
+obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += spectre.o
+
 extra-y := $(head-y) vmlinux.lds
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index c125582..b5e2179 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -10,6 +10,7 @@
 #include <linux/errno.h>
 
 #include <asm/delay.h>
+#include <asm/arch_timer.h>
 
 #include <clocksource/arm_arch_timer.h>
 
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 98bdea5..82e96ac 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -7,7 +7,6 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/string.h>
-#include <linux/cryptohash.h>
 #include <linux/delay.h>
 #include <linux/in6.h>
 #include <linux/syscalls.h>
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 4ce2e29..70993af 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -11,9 +11,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
-#ifdef CONFIG_KVM_ARM_HOST
-#include <linux/kvm_host.h>
-#endif
 #include <asm/cacheflush.h>
 #include <asm/kexec-internal.h>
 #include <asm/glue-df.h>
@@ -36,15 +33,6 @@
 #if defined(__APCS_26__)
 #error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32
 #endif
-/*
- * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854
- *	      miscompiles find_get_entry(), and can result in EXT3 and EXT4
- *	      filesystem corruption (possibly other FS too).
- */
-#if defined(GCC_VERSION) && GCC_VERSION >= 40800 && GCC_VERSION < 40803
-#error Your compiler is too buggy; it is known to miscompile kernels
-#error and result in filesystem corruption and oopses.
-#endif
 
 int main(void)
 {
@@ -171,14 +159,6 @@
   DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER);
   DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
   BLANK();
-#ifdef CONFIG_KVM_ARM_HOST
-  DEFINE(VCPU_GUEST_CTXT,	offsetof(struct kvm_vcpu, arch.ctxt));
-  DEFINE(VCPU_HOST_CTXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
-  DEFINE(CPU_CTXT_VFP,		offsetof(struct kvm_cpu_context, vfp));
-  DEFINE(CPU_CTXT_GP_REGS,	offsetof(struct kvm_cpu_context, gp_regs));
-  DEFINE(GP_REGS_USR,		offsetof(struct kvm_regs, usr_regs));
-#endif
-  BLANK();
 #ifdef CONFIG_VDSO
   DEFINE(VDSO_DATA_SIZE,	sizeof(union vdso_data_store));
 #endif
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 8288151..373b61f 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -91,8 +91,6 @@
 static int __init parse_tag_ramdisk(const struct tag *tag)
 {
 	rd_image_start = tag->u.ramdisk.start;
-	rd_doload = (tag->u.ramdisk.flags & 1) == 0;
-	rd_prompt = (tag->u.ramdisk.flags & 2) == 0;
 
 	if (tag->u.ramdisk.size)
 		rd_size = tag->u.ramdisk.size;
diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c
index 312cb89..3c2faf2 100644
--- a/arch/arm/kernel/atags_proc.c
+++ b/arch/arm/kernel/atags_proc.c
@@ -17,9 +17,9 @@
 	return simple_read_from_buffer(buf, count, ppos, b->data, b->size);
 }
 
-static const struct file_operations atags_fops = {
-	.read = atags_read,
-	.llseek = default_llseek,
+static const struct proc_ops atags_proc_ops = {
+	.proc_read	= atags_read,
+	.proc_lseek	= default_llseek,
 };
 
 #define BOOT_PARAMS_SIZE 1536
@@ -42,7 +42,7 @@
 	size_t size;
 
 	if (tag->hdr.tag != ATAG_CORE) {
-		pr_info("No ATAGs?");
+		pr_info("No ATAGs?\n");
 		return -EINVAL;
 	}
 
@@ -61,7 +61,7 @@
 	b->size = size;
 	memcpy(b->data, atags_copy, size);
 
-	tags_entry = proc_create_data("atags", 0400, NULL, &atags_fops, b);
+	tags_entry = proc_create_data("atags", 0400, NULL, &atags_proc_ops, b);
 	if (!tags_entry)
 		goto nomem;
 
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index ed46ca6..e7ef2b5 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -252,23 +252,6 @@
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CONTAQ, PCI_DEVICE_ID_CONTAQ_82C693, pci_fixup_cy82c693);
 
-static void pci_fixup_it8152(struct pci_dev *dev)
-{
-	int i;
-	/* fixup for ITE 8152 devices */
-	/* FIXME: add defines for class 0x68000 and 0x80103 */
-	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_HOST ||
-	    dev->class == 0x68000 ||
-	    dev->class == 0x80103) {
-		for (i = 0; i < PCI_NUM_RESOURCES; i++) {
-			dev->resource[i].start = 0;
-			dev->resource[i].end   = 0;
-			dev->resource[i].flags = 0;
-		}
-	}
-}
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ITE, PCI_DEVICE_ID_ITE_8152, pci_fixup_it8152);
-
 /*
  * If the bus contains any of these devices, then we must not turn on
  * parity checking of any kind.  Currently this is CyberPro 20x0 only.
@@ -411,8 +394,7 @@
 	return irq;
 }
 
-static int pcibios_init_resource(int busnr, struct pci_sys_data *sys,
-				 int io_optional)
+static int pcibios_init_resource(int busnr, struct pci_sys_data *sys)
 {
 	int ret;
 	struct resource_entry *window;
@@ -422,14 +404,6 @@
 			 &iomem_resource, sys->mem_offset);
 	}
 
-	/*
-	 * If a platform says I/O port support is optional, we don't add
-	 * the default I/O space.  The platform is responsible for adding
-	 * any I/O space it needs.
-	 */
-	if (io_optional)
-		return 0;
-
 	resource_list_for_each_entry(window, &sys->resources)
 		if (resource_type(window->res) == IORESOURCE_IO)
 			return 0;
@@ -479,7 +453,7 @@
 
 		if (ret > 0) {
 
-			ret = pcibios_init_resource(nr, sys, hw->io_optional);
+			ret = pcibios_init_resource(nr, sys);
 			if (ret)  {
 				pci_free_host_bridge(bridge);
 				break;
@@ -497,9 +471,6 @@
 				bridge->sysdata = sys;
 				bridge->busnr = sys->busnr;
 				bridge->ops = hw->ops;
-				bridge->msi = hw->msi_ctrl;
-				bridge->align_resource =
-						hw->align_resource;
 
 				ret = pci_scan_root_bus_bridge(bridge);
 			}
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index 093368e..e168462 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -11,7 +11,7 @@
 extern struct of_cpuidle_method __cpuidle_method_of_table[];
 
 static const struct of_cpuidle_method __cpuidle_method_of_table_sentinel
-	__used __section(__cpuidle_method_of_table_end);
+	__used __section("__cpuidle_method_of_table_end");
 
 static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init;
 
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index e112072..d92f44b 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -89,11 +89,18 @@
 2:		teq     r1, #'\n'
 		bne	3f
 		mov	r1, #'\r'
-		waituart r2, r3
+#ifdef CONFIG_DEBUG_UART_FLOW_CONTROL
+		waituartcts r2, r3
+#endif
+		waituarttxrdy r2, r3
 		senduart r1, r3
 		busyuart r2, r3
 		mov	r1, #'\n'
-3:		waituart r2, r3
+3:
+#ifdef CONFIG_DEBUG_UART_FLOW_CONTROL
+		waituartcts r2, r3
+#endif
+		waituarttxrdy r2, r3
 		senduart r1, r3
 		busyuart r2, r3
 		b	1b
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 4e09883..28311dd 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -29,7 +29,7 @@
 extern struct of_cpu_method __cpu_method_of_table[];
 
 static const struct of_cpu_method __cpu_method_of_table_sentinel
-	__used __section(__cpu_method_of_table_end);
+	__used __section("__cpu_method_of_table_end");
 
 
 static int __init set_smp_ops_by_method(struct device_node *node)
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index 1824229..254ab71 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -78,13 +78,32 @@
 EXPORT_SYMBOL(elf_set_personality);
 
 /*
- * Set READ_IMPLIES_EXEC if:
- *  - the binary requires an executable stack
- *  - we're running on a CPU which doesn't support NX.
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically.
+ *
+ * The decision process for determining the results are:
+ *
+ *                 CPU: | lacks NX*  | has NX     |
+ * ELF:                 |            |            |
+ * ---------------------|------------|------------|
+ * missing PT_GNU_STACK | exec-all   | exec-all   |
+ * PT_GNU_STACK == RWX  | exec-all   | exec-stack |
+ * PT_GNU_STACK == RW   | exec-all   | exec-none  |
+ *
+ *  exec-all  : all PROT_READ user mappings are executable, except when
+ *              backed by files on a noexec-filesystem.
+ *  exec-none : only PROT_EXEC user mappings are executable.
+ *  exec-stack: only the stack and PROT_EXEC user mappings are executable.
+ *
+ *  *this column has no architectural effect: NX markings are ignored by
+ *   hardware, but may have behavioral effects when "wants X" collides with
+ *   "cannot be X" constraints in memory permission flags, as in
+ *   https://lkml.kernel.org/r/20190418055759.GA3155@mellanox.com
+ *
  */
 int arm_elf_read_implies_exec(int executable_stack)
 {
-	if (executable_stack != EXSTACK_DISABLE_X)
+	if (executable_stack == EXSTACK_DEFAULT)
 		return 1;
 	if (cpu_architecture() < CPU_ARCH_ARMv6)
 		return 1;
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index b62d74a..c3ebe35 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -204,7 +204,7 @@
 	svc_entry
 	irq_handler
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
 	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
@@ -219,7 +219,7 @@
 
 	.ltorg
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 svc_preempt:
 	mov	r8, lr
 1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
@@ -596,11 +596,9 @@
 	tstne	r0, #0x04000000			@ bit 26 set on both ARM and Thumb-2
 	reteq	lr
 	and	r8, r0, #0x00000f00		@ mask out CP number
- THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
-	add	r6, r10, #TI_USED_CP
- ARM(	strb	r7, [r6, r8, lsr #8]	)	@ set appropriate used_cp[]
- THUMB(	strb	r7, [r6, r8]		)	@ set appropriate used_cp[]
+	add	r6, r10, r8, lsr #8		@ add used_cp[] array offset first
+	strb	r7, [r6, #TI_USED_CP]		@ set appropriate used_cp[]
 #ifdef CONFIG_IWMMXT
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
@@ -609,7 +607,7 @@
 	bcs	iwmmxt_task_enable
 #endif
  ARM(	add	pc, pc, r8, lsr #6	)
- THUMB(	lsl	r8, r8, #2		)
+ THUMB(	lsr	r8, r8, #6		)
  THUMB(	add	pc, r8			)
 	nop
 
@@ -1007,12 +1005,11 @@
 	sub	lr, lr, #\correction
 	.endif
 
-	@
-	@ Save r0, lr_<exception> (parent PC) and spsr_<exception>
-	@ (parent CPSR)
-	@
+	@ Save r0, lr_<exception> (parent PC)
 	stmia	sp, {r0, lr}		@ save r0, lr
-	mrs	lr, spsr
+
+	@ Save spsr_<exception> (parent CPSR)
+2:	mrs	lr, spsr
 	str	lr, [sp, #8]		@ save spsr
 
 	@
@@ -1033,6 +1030,44 @@
 	movs	pc, lr			@ branch to handler in SVC mode
 ENDPROC(vector_\name)
 
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+	.subsection 1
+	.align 5
+vector_bhb_loop8_\name:
+	.if \correction
+	sub	lr, lr, #\correction
+	.endif
+
+	@ Save r0, lr_<exception> (parent PC)
+	stmia	sp, {r0, lr}
+
+	@ bhb workaround
+	mov	r0, #8
+3:	b	. + 4
+	subs	r0, r0, #1
+	bne	3b
+	dsb
+	isb
+	b	2b
+ENDPROC(vector_bhb_loop8_\name)
+
+vector_bhb_bpiall_\name:
+	.if \correction
+	sub	lr, lr, #\correction
+	.endif
+
+	@ Save r0, lr_<exception> (parent PC)
+	stmia	sp, {r0, lr}
+
+	@ bhb workaround
+	mcr	p15, 0, r0, c7, c5, 6	@ BPIALL
+	@ isb not needed due to "movs pc, lr" in the vector stub
+	@ which gives a "context synchronisation".
+	b	2b
+ENDPROC(vector_bhb_bpiall_\name)
+	.previous
+#endif
+
 	.align	2
 	@ handler addresses follow this label
 1:
@@ -1041,6 +1076,10 @@
 	.section .stubs, "ax", %progbits
 	@ This must be the first word
 	.word	vector_swi
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+	.word	vector_bhb_loop8_swi
+	.word	vector_bhb_bpiall_swi
+#endif
 
 vector_rst:
  ARM(	swi	SYS_ERROR0	)
@@ -1155,8 +1194,10 @@
  * FIQ "NMI" handler
  *-----------------------------------------------------------------------------
  * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86
- * systems.
+ * systems. This must be the last vector stub, so lets place it in its own
+ * subsection.
  */
+	.subsection 2
 	vector_stub	fiq, FIQ_MODE, 4
 
 	.long	__fiq_usr			@  0  (USR_26 / USR_32)
@@ -1189,6 +1230,30 @@
 	W(b)	vector_irq
 	W(b)	vector_fiq
 
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+	.section .vectors.bhb.loop8, "ax", %progbits
+.L__vectors_bhb_loop8_start:
+	W(b)	vector_rst
+	W(b)	vector_bhb_loop8_und
+	W(ldr)	pc, .L__vectors_bhb_loop8_start + 0x1004
+	W(b)	vector_bhb_loop8_pabt
+	W(b)	vector_bhb_loop8_dabt
+	W(b)	vector_addrexcptn
+	W(b)	vector_bhb_loop8_irq
+	W(b)	vector_bhb_loop8_fiq
+
+	.section .vectors.bhb.bpiall, "ax", %progbits
+.L__vectors_bhb_bpiall_start:
+	W(b)	vector_rst
+	W(b)	vector_bhb_bpiall_und
+	W(ldr)	pc, .L__vectors_bhb_bpiall_start + 0x1008
+	W(b)	vector_bhb_bpiall_pabt
+	W(b)	vector_bhb_bpiall_dabt
+	W(b)	vector_addrexcptn
+	W(b)	vector_bhb_bpiall_irq
+	W(b)	vector_bhb_bpiall_fiq
+#endif
+
 	.data
 	.align	2
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 271cb8a..bd619da 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -163,12 +163,36 @@
  */
 
 	.align	5
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+ENTRY(vector_bhb_loop8_swi)
+	sub	sp, sp, #PT_REGS_SIZE
+	stmia	sp, {r0 - r12}
+	mov	r8, #8
+1:	b	2f
+2:	subs	r8, r8, #1
+	bne	1b
+	dsb
+	isb
+	b	3f
+ENDPROC(vector_bhb_loop8_swi)
+
+	.align	5
+ENTRY(vector_bhb_bpiall_swi)
+	sub	sp, sp, #PT_REGS_SIZE
+	stmia	sp, {r0 - r12}
+	mcr	p15, 0, r8, c7, c5, 6	@ BPIALL
+	isb
+	b	3f
+ENDPROC(vector_bhb_bpiall_swi)
+#endif
+	.align	5
 ENTRY(vector_swi)
 #ifdef CONFIG_CPU_V7M
 	v7m_exception_entry
 #else
 	sub	sp, sp, #PT_REGS_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0 - r12
+3:
  ARM(	add	r8, sp, #S_PC		)
  ARM(	stmdb	r8, {sp, lr}^		)	@ Calling sp, lr
  THUMB(	mov	r8, sp			)
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index cd1234c..98ca3e3 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -98,8 +98,8 @@
 
 	memcpy(base + offset, start, length);
 	if (!cache_is_vipt_nonaliasing())
-		flush_icache_range((unsigned long)base + offset, offset +
-				   length);
+		flush_icache_range((unsigned long)base + offset,
+				   (unsigned long)base + offset + length);
 	flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length);
 }
 
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index bda949f..3c83b5d 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -22,6 +22,7 @@
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 #include <asm/set_memory.h>
+#include <asm/patch.h>
 
 #ifdef CONFIG_THUMB2_KERNEL
 #define	NOP		0xf85deb04	/* pop.w {lr} */
@@ -35,9 +36,7 @@
 {
 	int *command = data;
 
-	set_kernel_text_rw();
 	ftrace_modify_all_code(*command);
-	set_kernel_text_ro();
 
 	return 0;
 }
@@ -59,21 +58,20 @@
 
 int ftrace_arch_code_modify_prepare(void)
 {
-	set_all_modules_text_rw();
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
 {
-	set_all_modules_text_ro();
 	/* Make sure any TLB misses during machine stop are cleared. */
 	flush_tlb_all();
 	return 0;
 }
 
-static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
+static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr,
+					 bool warn)
 {
-	return arm_gen_branch_link(pc, addr);
+	return arm_gen_branch_link(pc, addr, warn);
 }
 
 static int ftrace_modify_code(unsigned long pc, unsigned long old,
@@ -81,26 +79,21 @@
 {
 	unsigned long replaced;
 
-	if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) {
+	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
 		old = __opcode_to_mem_thumb32(old);
-		new = __opcode_to_mem_thumb32(new);
-	} else {
+	else
 		old = __opcode_to_mem_arm(old);
-		new = __opcode_to_mem_arm(new);
-	}
 
 	if (validate) {
-		if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+		if (copy_from_kernel_nofault(&replaced, (void *)pc,
+				MCOUNT_INSN_SIZE))
 			return -EFAULT;
 
 		if (replaced != old)
 			return -EINVAL;
 	}
 
-	if (probe_kernel_write((void *)pc, &new, MCOUNT_INSN_SIZE))
-		return -EPERM;
-
-	flush_icache_range(pc, pc + MCOUNT_INSN_SIZE);
+	__patch_text((void *)pc, new);
 
 	return 0;
 }
@@ -112,14 +105,14 @@
 	int ret;
 
 	pc = (unsigned long)&ftrace_call;
-	new = ftrace_call_replace(pc, (unsigned long)func);
+	new = ftrace_call_replace(pc, (unsigned long)func, true);
 
 	ret = ftrace_modify_code(pc, 0, new, false);
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 	if (!ret) {
 		pc = (unsigned long)&ftrace_regs_call;
-		new = ftrace_call_replace(pc, (unsigned long)func);
+		new = ftrace_call_replace(pc, (unsigned long)func, true);
 
 		ret = ftrace_modify_code(pc, 0, new, false);
 	}
@@ -132,10 +125,22 @@
 {
 	unsigned long new, old;
 	unsigned long ip = rec->ip;
+	unsigned long aaddr = adjust_address(rec, addr);
+	struct module *mod = NULL;
+
+#ifdef CONFIG_ARM_MODULE_PLTS
+	mod = rec->arch.mod;
+#endif
 
 	old = ftrace_nop_replace(rec);
 
-	new = ftrace_call_replace(ip, adjust_address(rec, addr));
+	new = ftrace_call_replace(ip, aaddr, !mod);
+#ifdef CONFIG_ARM_MODULE_PLTS
+	if (!new && mod) {
+		aaddr = get_module_plt(mod, ip, aaddr);
+		new = ftrace_call_replace(ip, aaddr, true);
+	}
+#endif
 
 	return ftrace_modify_code(rec->ip, old, new, true);
 }
@@ -148,9 +153,9 @@
 	unsigned long new, old;
 	unsigned long ip = rec->ip;
 
-	old = ftrace_call_replace(ip, adjust_address(rec, old_addr));
+	old = ftrace_call_replace(ip, adjust_address(rec, old_addr), true);
 
-	new = ftrace_call_replace(ip, adjust_address(rec, addr));
+	new = ftrace_call_replace(ip, adjust_address(rec, addr), true);
 
 	return ftrace_modify_code(rec->ip, old, new, true);
 }
@@ -160,12 +165,29 @@
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
+	unsigned long aaddr = adjust_address(rec, addr);
 	unsigned long ip = rec->ip;
 	unsigned long old;
 	unsigned long new;
 	int ret;
 
-	old = ftrace_call_replace(ip, adjust_address(rec, addr));
+#ifdef CONFIG_ARM_MODULE_PLTS
+	/* mod is only supplied during module loading */
+	if (!mod)
+		mod = rec->arch.mod;
+	else
+		rec->arch.mod = mod;
+#endif
+
+	old = ftrace_call_replace(ip, aaddr,
+				  !IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || !mod);
+#ifdef CONFIG_ARM_MODULE_PLTS
+	if (!old && mod) {
+		aaddr = get_module_plt(mod, ip, aaddr);
+		old = ftrace_call_replace(ip, aaddr, true);
+	}
+#endif
+
 	new = ftrace_nop_replace(rec);
 	ret = ftrace_modify_code(ip, old, new, true);
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 5ceed4d..4af5c76 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -10,6 +10,7 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
+#include <linux/pgtable.h>
 
 #include <asm/assembler.h>
 #include <asm/cp15.h>
@@ -18,7 +19,6 @@
 #include <asm/asm-offsets.h>
 #include <asm/memory.h>
 #include <asm/thread_info.h>
-#include <asm/pgtable.h>
 
 #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING)
 #include CONFIG_DEBUG_LL_INCLUDE
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index b06d9ea..b1423fb 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -246,6 +246,9 @@
 	case ARM_DEBUG_ARCH_V7_ECP14:
 	case ARM_DEBUG_ARCH_V7_1:
 	case ARM_DEBUG_ARCH_V8:
+	case ARM_DEBUG_ARCH_V8_1:
+	case ARM_DEBUG_ARCH_V8_2:
+	case ARM_DEBUG_ARCH_V8_4:
 		ARM_DBG_WRITE(c0, c2, 2, (dscr | ARM_DSCR_MDBGEN));
 		isb();
 		break;
@@ -544,7 +547,7 @@
 		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		return -EINVAL;
 	}
@@ -609,12 +612,12 @@
 		/* Allow halfword watchpoints and breakpoints. */
 		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	case 3:
 		/* Allow single byte watchpoint. */
 		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -925,7 +928,7 @@
 		break;
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
 		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
-		/* Fall through */
+		fallthrough;
 	case ARM_ENTRY_SYNC_WATCHPOINT:
 		watchpoint_handler(addr, fsr, regs);
 		break;
@@ -974,7 +977,7 @@
 		ARM_DBG_READ(c1, c1, 4, oslsr);
 		if (oslsr & ARM_OSLSR_OSLM0)
 			return true;
-		/* Else, fall through */
+		fallthrough;
 	default:
 		return false;
 	}
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 6607fa8..26d8e03 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -189,19 +189,19 @@
 ENDPROC(__hyp_stub_install_secondary)
 
 __hyp_stub_do_trap:
+#ifdef ZIMAGE
 	teq	r0, #HVC_SET_VECTORS
 	bne	1f
+	/* Only the ZIMAGE stubs can change the HYP vectors */
 	mcr	p15, 4, r1, c12, c0, 0	@ set HVBAR
 	b	__hyp_stub_exit
+#endif
 
 1:	teq	r0, #HVC_SOFT_RESTART
-	bne	1f
+	bne	2f
 	bx	r1
 
-1:	teq	r0, #HVC_RESET_VECTORS
-	beq	__hyp_stub_exit
-
-	ldr	r0, =HVC_STUB_ERR
+2:	ldr	r0, =HVC_STUB_ERR
 	__ERET
 
 __hyp_stub_exit:
@@ -210,26 +210,9 @@
 ENDPROC(__hyp_stub_do_trap)
 
 /*
- * __hyp_set_vectors: Call this after boot to set the initial hypervisor
- * vectors as part of hypervisor installation.  On an SMP system, this should
- * be called on each CPU.
- *
- * r0 must be the physical address of the new vector table (which must lie in
- * the bottom 4GB of physical address space.
- *
- * r0 must be 32-byte aligned.
- *
- * Before calling this, you must check that the stub hypervisor is installed
- * everywhere, by waiting for any secondary CPUs to be brought up and then
- * checking that BOOT_CPU_MODE_HAVE_HYP(__boot_cpu_mode) is true.
- *
- * If not, there is a pre-existing hypervisor, some CPUs failed to boot, or
- * something else went wrong... in such cases, trying to install a new
- * hypervisor is unlikely to work as desired.
- *
- * When you call into your shiny new hypervisor, sp_hyp will contain junk,
- * so you will need to set that to something sensible at the new hypervisor's
- * initialisation entry point.
+ * __hyp_set_vectors is only used when ZIMAGE must bounce between HYP
+ * and SVC. For the kernel itself, the vectors are set once and for
+ * all by the stubs.
  */
 ENTRY(__hyp_set_vectors)
 	mov	r1, r0
@@ -245,12 +228,6 @@
 	ret	lr
 ENDPROC(__hyp_soft_restart)
 
-ENTRY(__hyp_reset_vectors)
-	mov	r0, #HVC_RESET_VECTORS
-	__HVC(0)
-	ret	lr
-ENDPROC(__hyp_reset_vectors)
-
 #ifndef ZIMAGE
 .align 2
 .L__boot_cpu_mode_offset:
diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c
index 2e844b7..db0acbb 100644
--- a/arch/arm/kernel/insn.c
+++ b/arch/arm/kernel/insn.c
@@ -3,8 +3,9 @@
 #include <linux/kernel.h>
 #include <asm/opcodes.h>
 
-static unsigned long
-__arm_gen_branch_thumb2(unsigned long pc, unsigned long addr, bool link)
+static unsigned long __arm_gen_branch_thumb2(unsigned long pc,
+					     unsigned long addr, bool link,
+					     bool warn)
 {
 	unsigned long s, j1, j2, i1, i2, imm10, imm11;
 	unsigned long first, second;
@@ -12,7 +13,7 @@
 
 	offset = (long)addr - (long)(pc + 4);
 	if (offset < -16777216 || offset > 16777214) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(warn);
 		return 0;
 	}
 
@@ -33,8 +34,8 @@
 	return __opcode_thumb32_compose(first, second);
 }
 
-static unsigned long
-__arm_gen_branch_arm(unsigned long pc, unsigned long addr, bool link)
+static unsigned long __arm_gen_branch_arm(unsigned long pc, unsigned long addr,
+					  bool link, bool warn)
 {
 	unsigned long opcode = 0xea000000;
 	long offset;
@@ -44,7 +45,7 @@
 
 	offset = (long)addr - (long)(pc + 8);
 	if (unlikely(offset < -33554432 || offset > 33554428)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(warn);
 		return 0;
 	}
 
@@ -54,10 +55,10 @@
 }
 
 unsigned long
-__arm_gen_branch(unsigned long pc, unsigned long addr, bool link)
+__arm_gen_branch(unsigned long pc, unsigned long addr, bool link, bool warn)
 {
 	if (IS_ENABLED(CONFIG_THUMB2_KERNEL))
-		return __arm_gen_branch_thumb2(pc, addr, link);
+		return __arm_gen_branch_thumb2(pc, addr, link, warn);
 	else
-		return __arm_gen_branch_arm(pc, addr, link);
+		return __arm_gen_branch_arm(pc, addr, link, warn);
 }
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ee51403..698b6f6 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -18,7 +18,6 @@
  *  IRQ's are in fact implemented a bit like signal handlers for the kernel.
  *  Naturally it's not a 1:1 relation, but there are similarities.
  */
-#include <linux/kernel_stat.h>
 #include <linux/signal.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index 0dcae78..d2b4ac0 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -16,6 +16,7 @@
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
+#include "iwmmxt.h"
 
 #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B)
 #define PJ4(code...)		code
@@ -113,33 +114,33 @@
 
 concan_dump:
 
-	wstrw	wCSSF, [r1, #MMX_WCSSF]
-	wstrw	wCASF, [r1, #MMX_WCASF]
-	wstrw	wCGR0, [r1, #MMX_WCGR0]
-	wstrw	wCGR1, [r1, #MMX_WCGR1]
-	wstrw	wCGR2, [r1, #MMX_WCGR2]
-	wstrw	wCGR3, [r1, #MMX_WCGR3]
+	wstrw	wCSSF, r1, MMX_WCSSF
+	wstrw	wCASF, r1, MMX_WCASF
+	wstrw	wCGR0, r1, MMX_WCGR0
+	wstrw	wCGR1, r1, MMX_WCGR1
+	wstrw	wCGR2, r1, MMX_WCGR2
+	wstrw	wCGR3, r1, MMX_WCGR3
 
 1:	@ MUP? wRn
 	tst	r2, #0x2
 	beq	2f
 
-	wstrd	wR0,  [r1, #MMX_WR0]
-	wstrd	wR1,  [r1, #MMX_WR1]
-	wstrd	wR2,  [r1, #MMX_WR2]
-	wstrd	wR3,  [r1, #MMX_WR3]
-	wstrd	wR4,  [r1, #MMX_WR4]
-	wstrd	wR5,  [r1, #MMX_WR5]
-	wstrd	wR6,  [r1, #MMX_WR6]
-	wstrd	wR7,  [r1, #MMX_WR7]
-	wstrd	wR8,  [r1, #MMX_WR8]
-	wstrd	wR9,  [r1, #MMX_WR9]
-	wstrd	wR10, [r1, #MMX_WR10]
-	wstrd	wR11, [r1, #MMX_WR11]
-	wstrd	wR12, [r1, #MMX_WR12]
-	wstrd	wR13, [r1, #MMX_WR13]
-	wstrd	wR14, [r1, #MMX_WR14]
-	wstrd	wR15, [r1, #MMX_WR15]
+	wstrd	wR0,  r1, MMX_WR0
+	wstrd	wR1,  r1, MMX_WR1
+	wstrd	wR2,  r1, MMX_WR2
+	wstrd	wR3,  r1, MMX_WR3
+	wstrd	wR4,  r1, MMX_WR4
+	wstrd	wR5,  r1, MMX_WR5
+	wstrd	wR6,  r1, MMX_WR6
+	wstrd	wR7,  r1, MMX_WR7
+	wstrd	wR8,  r1, MMX_WR8
+	wstrd	wR9,  r1, MMX_WR9
+	wstrd	wR10, r1, MMX_WR10
+	wstrd	wR11, r1, MMX_WR11
+	wstrd	wR12, r1, MMX_WR12
+	wstrd	wR13, r1, MMX_WR13
+	wstrd	wR14, r1, MMX_WR14
+	wstrd	wR15, r1, MMX_WR15
 
 2:	teq	r0, #0				@ anything to load?
 	reteq	lr				@ if not, return
@@ -147,30 +148,30 @@
 concan_load:
 
 	@ Load wRn
-	wldrd	wR0,  [r0, #MMX_WR0]
-	wldrd	wR1,  [r0, #MMX_WR1]
-	wldrd	wR2,  [r0, #MMX_WR2]
-	wldrd	wR3,  [r0, #MMX_WR3]
-	wldrd	wR4,  [r0, #MMX_WR4]
-	wldrd	wR5,  [r0, #MMX_WR5]
-	wldrd	wR6,  [r0, #MMX_WR6]
-	wldrd	wR7,  [r0, #MMX_WR7]
-	wldrd	wR8,  [r0, #MMX_WR8]
-	wldrd	wR9,  [r0, #MMX_WR9]
-	wldrd	wR10, [r0, #MMX_WR10]
-	wldrd	wR11, [r0, #MMX_WR11]
-	wldrd	wR12, [r0, #MMX_WR12]
-	wldrd	wR13, [r0, #MMX_WR13]
-	wldrd	wR14, [r0, #MMX_WR14]
-	wldrd	wR15, [r0, #MMX_WR15]
+	wldrd	wR0,  r0, MMX_WR0
+	wldrd	wR1,  r0, MMX_WR1
+	wldrd	wR2,  r0, MMX_WR2
+	wldrd	wR3,  r0, MMX_WR3
+	wldrd	wR4,  r0, MMX_WR4
+	wldrd	wR5,  r0, MMX_WR5
+	wldrd	wR6,  r0, MMX_WR6
+	wldrd	wR7,  r0, MMX_WR7
+	wldrd	wR8,  r0, MMX_WR8
+	wldrd	wR9,  r0, MMX_WR9
+	wldrd	wR10, r0, MMX_WR10
+	wldrd	wR11, r0, MMX_WR11
+	wldrd	wR12, r0, MMX_WR12
+	wldrd	wR13, r0, MMX_WR13
+	wldrd	wR14, r0, MMX_WR14
+	wldrd	wR15, r0, MMX_WR15
 
 	@ Load wCx
-	wldrw	wCSSF, [r0, #MMX_WCSSF]
-	wldrw	wCASF, [r0, #MMX_WCASF]
-	wldrw	wCGR0, [r0, #MMX_WCGR0]
-	wldrw	wCGR1, [r0, #MMX_WCGR1]
-	wldrw	wCGR2, [r0, #MMX_WCGR2]
-	wldrw	wCGR3, [r0, #MMX_WCGR3]
+	wldrw	wCSSF, r0, MMX_WCSSF
+	wldrw	wCASF, r0, MMX_WCASF
+	wldrw	wCGR0, r0, MMX_WCGR0
+	wldrw	wCGR1, r0, MMX_WCGR1
+	wldrw	wCGR2, r0, MMX_WCGR2
+	wldrw	wCGR3, r0, MMX_WCGR3
 
 	@ clear CUP/MUP (only if r1 != 0)
 	teq	r1, #0
diff --git a/arch/arm/kernel/iwmmxt.h b/arch/arm/kernel/iwmmxt.h
new file mode 100644
index 0000000..fb62728
--- /dev/null
+++ b/arch/arm/kernel/iwmmxt.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __IWMMXT_H__
+#define __IWMMXT_H__
+
+.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
+.set .LwR\b, \b
+.set .Lr\b, \b
+.endr
+
+.set .LwCSSF, 0x2
+.set .LwCASF, 0x3
+.set .LwCGR0, 0x8
+.set .LwCGR1, 0x9
+.set .LwCGR2, 0xa
+.set .LwCGR3, 0xb
+
+.macro wldrd, reg:req, base:req, offset:req
+.inst 0xedd00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+.macro wldrw, reg:req, base:req, offset:req
+.inst 0xfd900100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+.macro wstrd, reg:req, base:req, offset:req
+.inst 0xedc00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+.macro wstrw, reg:req, base:req, offset:req
+.inst 0xfd800100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2)
+.endm
+
+#ifdef __clang__
+
+#define wCon c1
+
+.macro tmrc, dest:req, control:req
+mrc p1, 0, \dest, \control, c0, 0
+.endm
+
+.macro tmcr, control:req, src:req
+mcr p1, 0, \src, \control, c0, 0
+.endm
+#endif
+
+#endif
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index 6a95b92..22f937e 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -154,22 +154,38 @@
 	return 0;
 }
 
-static struct undef_hook kgdb_brkpt_hook = {
+static struct undef_hook kgdb_brkpt_arm_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_BREAKINST,
-	.cpsr_mask		= MODE_MASK,
+	.cpsr_mask		= PSR_T_BIT | MODE_MASK,
 	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_brk_fn
 };
 
-static struct undef_hook kgdb_compiled_brkpt_hook = {
+static struct undef_hook kgdb_brkpt_thumb_hook = {
+	.instr_mask		= 0xffff,
+	.instr_val		= KGDB_BREAKINST & 0xffff,
+	.cpsr_mask		= PSR_T_BIT | MODE_MASK,
+	.cpsr_val		= PSR_T_BIT | SVC_MODE,
+	.fn			= kgdb_brk_fn
+};
+
+static struct undef_hook kgdb_compiled_brkpt_arm_hook = {
 	.instr_mask		= 0xffffffff,
 	.instr_val		= KGDB_COMPILED_BREAK,
-	.cpsr_mask		= MODE_MASK,
+	.cpsr_mask		= PSR_T_BIT | MODE_MASK,
 	.cpsr_val		= SVC_MODE,
 	.fn			= kgdb_compiled_brk_fn
 };
 
+static struct undef_hook kgdb_compiled_brkpt_thumb_hook = {
+	.instr_mask		= 0xffff,
+	.instr_val		= KGDB_COMPILED_BREAK & 0xffff,
+	.cpsr_mask		= PSR_T_BIT | MODE_MASK,
+	.cpsr_val		= PSR_T_BIT | SVC_MODE,
+	.fn			= kgdb_compiled_brk_fn
+};
+
 static int __kgdb_notify(struct die_args *args, unsigned long cmd)
 {
 	struct pt_regs *regs = args->regs;
@@ -210,8 +226,10 @@
 	if (ret != 0)
 		return ret;
 
-	register_undef_hook(&kgdb_brkpt_hook);
-	register_undef_hook(&kgdb_compiled_brkpt_hook);
+	register_undef_hook(&kgdb_brkpt_arm_hook);
+	register_undef_hook(&kgdb_brkpt_thumb_hook);
+	register_undef_hook(&kgdb_compiled_brkpt_arm_hook);
+	register_undef_hook(&kgdb_compiled_brkpt_thumb_hook);
 
 	return 0;
 }
@@ -224,8 +242,10 @@
  */
 void kgdb_arch_exit(void)
 {
-	unregister_undef_hook(&kgdb_brkpt_hook);
-	unregister_undef_hook(&kgdb_compiled_brkpt_hook);
+	unregister_undef_hook(&kgdb_brkpt_arm_hook);
+	unregister_undef_hook(&kgdb_brkpt_thumb_hook);
+	unregister_undef_hook(&kgdb_compiled_brkpt_arm_hook);
+	unregister_undef_hook(&kgdb_compiled_brkpt_thumb_hook);
 	unregister_die_notifier(&kgdb_notifier);
 }
 
@@ -236,7 +256,7 @@
 	/* patch_text() only supports int-sized breakpoints */
 	BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE);
 
-	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+	err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
 				BREAK_INSTR_SIZE);
 	if (err)
 		return err;
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 734adeb..2b09dad 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -10,9 +10,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/memblock.h>
-#include <asm/pgtable.h>
 #include <linux/of_fdt.h>
-#include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/kexec-internal.h>
diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c
index b647741..1fc309b 100644
--- a/arch/arm/kernel/module-plts.c
+++ b/arch/arm/kernel/module-plts.c
@@ -4,17 +4,15 @@
  */
 
 #include <linux/elf.h>
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sort.h>
+#include <linux/moduleloader.h>
 
 #include <asm/cache.h>
 #include <asm/opcodes.h>
 
-#define PLT_ENT_STRIDE		L1_CACHE_BYTES
-#define PLT_ENT_COUNT		(PLT_ENT_STRIDE / sizeof(u32))
-#define PLT_ENT_SIZE		(sizeof(struct plt_entries) / PLT_ENT_COUNT)
-
 #ifdef CONFIG_THUMB2_KERNEL
 #define PLT_ENT_LDR		__opcode_to_mem_thumb32(0xf8dff000 | \
 							(PLT_ENT_STRIDE - 4))
@@ -23,9 +21,11 @@
 						    (PLT_ENT_STRIDE - 8))
 #endif
 
-struct plt_entries {
-	u32	ldr[PLT_ENT_COUNT];
-	u32	lit[PLT_ENT_COUNT];
+static const u32 fixed_plts[] = {
+#ifdef CONFIG_DYNAMIC_FTRACE
+	FTRACE_ADDR,
+	MCOUNT_ADDR,
+#endif
 };
 
 static bool in_init(const struct module *mod, unsigned long loc)
@@ -33,14 +33,40 @@
 	return loc - (u32)mod->init_layout.base < mod->init_layout.size;
 }
 
+static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt)
+{
+	int i;
+
+	if (!ARRAY_SIZE(fixed_plts) || pltsec->plt_count)
+		return;
+	pltsec->plt_count = ARRAY_SIZE(fixed_plts);
+
+	for (i = 0; i < ARRAY_SIZE(plt->ldr); ++i)
+		plt->ldr[i] = PLT_ENT_LDR;
+
+	BUILD_BUG_ON(sizeof(fixed_plts) > sizeof(plt->lit));
+	memcpy(plt->lit, fixed_plts, sizeof(fixed_plts));
+}
+
 u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val)
 {
 	struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
 							  &mod->arch.init;
+	struct plt_entries *plt;
+	int idx;
 
-	struct plt_entries *plt = (struct plt_entries *)pltsec->plt->sh_addr;
-	int idx = 0;
+	/* cache the address, ELF header is available only during module load */
+	if (!pltsec->plt_ent)
+		pltsec->plt_ent = (struct plt_entries *)pltsec->plt->sh_addr;
+	plt = pltsec->plt_ent;
 
+	prealloc_fixed(pltsec, plt);
+
+	for (idx = 0; idx < ARRAY_SIZE(fixed_plts); ++idx)
+		if (plt->lit[idx] == val)
+			return (u32)&plt->ldr[idx];
+
+	idx = 0;
 	/*
 	 * Look for an existing entry pointing to 'val'. Given that the
 	 * relocations are sorted, this will be the last entry we allocated.
@@ -188,8 +214,8 @@
 int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 			      char *secstrings, struct module *mod)
 {
-	unsigned long core_plts = 0;
-	unsigned long init_plts = 0;
+	unsigned long core_plts = ARRAY_SIZE(fixed_plts);
+	unsigned long init_plts = ARRAY_SIZE(fixed_plts);
 	Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum;
 	Elf32_Sym *syms = NULL;
 
@@ -244,6 +270,7 @@
 	mod->arch.core.plt->sh_size = round_up(core_plts * PLT_ENT_SIZE,
 					       sizeof(struct plt_entries));
 	mod->arch.core.plt_count = 0;
+	mod->arch.core.plt_ent = NULL;
 
 	mod->arch.init.plt->sh_type = SHT_NOBITS;
 	mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
@@ -251,6 +278,7 @@
 	mod->arch.init.plt->sh_size = round_up(init_plts * PLT_ENT_SIZE,
 					       sizeof(struct plt_entries));
 	mod->arch.init.plt_count = 0;
+	mod->arch.init.plt_ent = NULL;
 
 	pr_debug("%s: plt=%x, init.plt=%x\n", __func__,
 		 mod->arch.core.plt->sh_size, mod->arch.init.plt->sh_size);
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index deef17f..e15444b 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -17,7 +17,6 @@
 #include <linux/string.h>
 #include <linux/gfp.h>
 
-#include <asm/pgtable.h>
 #include <asm/sections.h>
 #include <asm/smp_plat.h>
 #include <asm/unwind.h>
@@ -55,6 +54,13 @@
 }
 #endif
 
+bool module_init_section(const char *name)
+{
+	return strstarts(name, ".init") ||
+		strstarts(name, ".ARM.extab.init") ||
+		strstarts(name, ".ARM.exidx.init");
+}
+
 bool module_exit_section(const char *name)
 {
 	return strstarts(name, ".exit") ||
@@ -409,8 +415,17 @@
 #ifdef CONFIG_ARM_UNWIND
 	int i;
 
-	for (i = 0; i < ARM_SEC_MAX; i++)
-		if (mod->arch.unwind[i])
-			unwind_table_del(mod->arch.unwind[i]);
+	for (i = 0; i < ARM_SEC_MAX; i++) {
+		unwind_table_del(mod->arch.unwind[i]);
+		mod->arch.unwind[i] = NULL;
+	}
+#endif
+}
+
+void __weak module_arch_freeing_init(struct module *mod)
+{
+#ifdef CONFIG_ARM_UNWIND
+	unwind_table_del(mod->arch.unwind[ARM_SEC_INIT]);
+	mod->arch.unwind[ARM_SEC_INIT] = NULL;
 #endif
 }
diff --git a/arch/arm/kernel/module.lds b/arch/arm/kernel/module.lds
deleted file mode 100644
index 79cb6af..0000000
--- a/arch/arm/kernel/module.lds
+++ /dev/null
@@ -1,5 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-SECTIONS {
-	.plt : { BYTE(0) }
-	.init.plt : { BYTE(0) }
-}
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index d0a05a3..e9e828b 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,10 +16,10 @@
 	unsigned int insn;
 };
 
+#ifdef CONFIG_MMU
 static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
-	__acquires(&patch_lock)
 {
 	unsigned int uintaddr = (uintptr_t) addr;
 	bool module = !core_kernel_text(uintaddr);
@@ -34,8 +34,6 @@
 
 	if (flags)
 		raw_spin_lock_irqsave(&patch_lock, *flags);
-	else
-		__acquire(&patch_lock);
 
 	set_fixmap(fixmap, page_to_phys(page));
 
@@ -43,15 +41,19 @@
 }
 
 static void __kprobes patch_unmap(int fixmap, unsigned long *flags)
-	__releases(&patch_lock)
 {
 	clear_fixmap(fixmap);
 
 	if (flags)
 		raw_spin_unlock_irqrestore(&patch_lock, *flags);
-	else
-		__release(&patch_lock);
 }
+#else
+static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
+{
+	return addr;
+}
+static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { }
+#endif
 
 void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap)
 {
@@ -64,8 +66,6 @@
 
 	if (remap)
 		waddr = patch_map(addr, FIX_TEXT_POKE0, &flags);
-	else
-		__acquire(&patch_lock);
 
 	if (thumb2 && __opcode_is_thumb16(insn)) {
 		*(u16 *)waddr = __opcode_to_mem_thumb16(insn);
@@ -102,8 +102,7 @@
 	if (waddr != addr) {
 		flush_kernel_vmap_range(waddr, twopage ? size / 2 : size);
 		patch_unmap(FIX_TEXT_POKE0, &flags);
-	} else
-		__release(&patch_lock);
+	}
 
 	flush_icache_range((uintptr_t)(addr),
 			   (uintptr_t)(addr) + size);
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 3b69a76..1626dfc 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -62,9 +62,10 @@
 void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct frame_tail __user *tail;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->is_in_guest()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -98,9 +99,10 @@
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	struct stackframe fr;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
+	if (guest_cbs && guest_cbs->is_in_guest()) {
 		/* We don't support guest os callchain now */
 		return;
 	}
@@ -111,18 +113,21 @@
 
 unsigned long perf_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
-		return perf_guest_cbs->get_guest_ip();
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
+
+	if (guest_cbs && guest_cbs->is_in_guest())
+		return guest_cbs->get_guest_ip();
 
 	return instruction_pointer(regs);
 }
 
 unsigned long perf_misc_flags(struct pt_regs *regs)
 {
+	struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs();
 	int misc = 0;
 
-	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
-		if (perf_guest_cbs->is_user_mode())
+	if (guest_cbs && guest_cbs->is_in_guest()) {
+		if (guest_cbs->is_user_mode())
 			misc |= PERF_RECORD_MISC_GUEST_USER;
 		else
 			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
index 05fe92a..0529f90 100644
--- a/arch/arm/kernel/perf_regs.c
+++ b/arch/arm/kernel/perf_regs.c
@@ -32,8 +32,7 @@
 }
 
 void perf_get_regs_user(struct perf_regs *regs_user,
-			struct pt_regs *regs,
-			struct pt_regs *regs_user_copy)
+			struct pt_regs *regs)
 {
 	regs_user->regs = task_pt_regs(current);
 	regs_user->abi = perf_reg_abi(current);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index e7fac12..9f199b1 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -36,6 +36,8 @@
 #include <asm/tls.h>
 #include <asm/vdso.h>
 
+#include "signal.h"
+
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
 unsigned long __stack_chk_guard __read_mostly;
@@ -69,7 +71,7 @@
 		arm_pm_idle();
 	else
 		cpu_do_idle();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 void arch_cpu_idle_prepare(void)
@@ -223,9 +225,8 @@
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
-int
-copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p, unsigned long tls)
+int copy_thread(unsigned long clone_flags, unsigned long stack_start,
+		unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -280,21 +281,6 @@
 	return 1;
 }
 
-/*
- * fill in the fpe structure for a core dump...
- */
-int dump_fpu (struct pt_regs *regs, struct user_fp *fp)
-{
-	struct thread_info *thread = current_thread_info();
-	int used_math = thread->used_cp[1] | thread->used_cp[2];
-
-	if (used_math)
-		memcpy(fp, &thread->fpstate.soft, sizeof (*fp));
-
-	return used_math != 0;
-}
-EXPORT_SYMBOL(dump_fpu);
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
@@ -429,7 +415,7 @@
 	npages = 1; /* for sigpage */
 	npages += vdso_total_pages;
 
-	if (down_write_killable(&mm->mmap_sem))
+	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 	hint = sigpage_addr(mm, npages);
 	addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0);
@@ -456,7 +442,7 @@
 	arm_install_vdso(mm, addr + PAGE_SIZE);
 
  up_fail:
-	up_write(&mm->mmap_sem);
+	mmap_write_unlock(mm);
 	return ret;
 }
 #endif
diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c
index aba6b2a..d4392e1 100644
--- a/arch/arm/kernel/psci_smp.c
+++ b/arch/arm/kernel/psci_smp.c
@@ -51,7 +51,7 @@
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-int psci_cpu_disable(unsigned int cpu)
+static int psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
 	if (!psci_ops.cpu_off)
@@ -64,7 +64,7 @@
 	return 0;
 }
 
-void psci_cpu_die(unsigned int cpu)
+static void psci_cpu_die(unsigned int cpu)
 {
 	u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN <<
 		    PSCI_0_2_POWER_STATE_TYPE_SHIFT;
@@ -76,7 +76,7 @@
 	panic("psci: cpu %d failed to shutdown\n", cpu);
 }
 
-int psci_cpu_kill(unsigned int cpu)
+static int psci_cpu_kill(unsigned int cpu)
 {
 	int err, i;
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index db94015..2771e68 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -25,7 +25,6 @@
 #include <linux/tracehook.h>
 #include <linux/unistd.h>
 
-#include <asm/pgtable.h>
 #include <asm/traps.h>
 
 #define CREATE_TRACE_POINTS
@@ -570,14 +569,9 @@
 
 static int gpr_get(struct task_struct *target,
 		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+		   struct membuf to)
 {
-	struct pt_regs *regs = task_pt_regs(target);
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   regs,
-				   0, sizeof(*regs));
+	return membuf_write(&to, task_pt_regs(target), sizeof(struct pt_regs));
 }
 
 static int gpr_set(struct task_struct *target,
@@ -603,12 +597,10 @@
 
 static int fpa_get(struct task_struct *target,
 		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+		   struct membuf to)
 {
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &task_thread_info(target)->fpstate,
-				   0, sizeof(struct user_fp));
+	return membuf_write(&to, &task_thread_info(target)->fpstate,
+				 sizeof(struct user_fp));
 }
 
 static int fpa_set(struct task_struct *target,
@@ -643,41 +635,20 @@
  *	vfp_set() ignores this chunk
  *
  * 1 word for the FPSCR
- *
- * The bounds-checking logic built into user_regset_copyout and friends
- * means that we can make a simple sequence of calls to map the relevant data
- * to/from the specified slice of the user regset structure.
  */
 static int vfp_get(struct task_struct *target,
 		   const struct user_regset *regset,
-		   unsigned int pos, unsigned int count,
-		   void *kbuf, void __user *ubuf)
+		   struct membuf to)
 {
-	int ret;
 	struct thread_info *thread = task_thread_info(target);
 	struct vfp_hard_struct const *vfp = &thread->vfpstate.hard;
-	const size_t user_fpregs_offset = offsetof(struct user_vfp, fpregs);
 	const size_t user_fpscr_offset = offsetof(struct user_vfp, fpscr);
 
 	vfp_sync_hwstate(thread);
 
-	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  &vfp->fpregs,
-				  user_fpregs_offset,
-				  user_fpregs_offset + sizeof(vfp->fpregs));
-	if (ret)
-		return ret;
-
-	ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf,
-				       user_fpregs_offset + sizeof(vfp->fpregs),
-				       user_fpscr_offset);
-	if (ret)
-		return ret;
-
-	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &vfp->fpscr,
-				   user_fpscr_offset,
-				   user_fpscr_offset + sizeof(vfp->fpscr));
+	membuf_write(&to, vfp->fpregs, sizeof(vfp->fpregs));
+	membuf_zero(&to, user_fpscr_offset - sizeof(vfp->fpregs));
+	return membuf_store(&to, vfp->fpscr);
 }
 
 /*
@@ -740,7 +711,7 @@
 		.n = ELF_NGREG,
 		.size = sizeof(u32),
 		.align = sizeof(u32),
-		.get = gpr_get,
+		.regset_get = gpr_get,
 		.set = gpr_set
 	},
 	[REGSET_FPR] = {
@@ -752,7 +723,7 @@
 		.n = sizeof(struct user_fp) / sizeof(u32),
 		.size = sizeof(u32),
 		.align = sizeof(u32),
-		.get = fpa_get,
+		.regset_get = fpa_get,
 		.set = fpa_set
 	},
 #ifdef CONFIG_VFP
@@ -765,7 +736,7 @@
 		.n = ARM_VFPREGS_SIZE / sizeof(u32),
 		.size = sizeof(u32),
 		.align = sizeof(u32),
-		.get = vfp_get,
+		.regset_get = vfp_get,
 		.set = vfp_set
 	},
 #endif /* CONFIG_VFP */
@@ -923,7 +894,7 @@
 
 	/* Do seccomp after ptrace; syscall may have changed. */
 #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
-	if (secure_computing(NULL) == -1)
+	if (secure_computing() == -1)
 		return -1;
 #else
 	/* XXX: remove this once OABI gets fixed */
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index bb18ed0..0ce388f 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -88,11 +88,11 @@
  * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
  * kexec'd kernel to use any and all RAM as it sees fit, without having to
  * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
- * functionality embodied in disable_nonboot_cpus() to achieve this.
+ * functionality embodied in smp_shutdown_nonboot_cpus() to achieve this.
  */
 void machine_shutdown(void)
 {
-	disable_nonboot_cpus();
+	smp_shutdown_nonboot_cpus(reboot_cpu);
 }
 
 /*
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 5e15b59..218d524 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -27,26 +27,26 @@
 	ldr	r3, [r0],#4
 
 	/* Is it a destination page. Put destination address to r4 */
-	tst	r3,#1,0
+	tst	r3,#1
 	beq	1f
 	bic	r4,r3,#1
 	b	0b
 1:
 	/* Is it an indirection page */
-	tst	r3,#2,0
+	tst	r3,#2
 	beq	1f
 	bic	r0,r3,#2
 	b	0b
 1:
 
 	/* are we done ? */
-	tst	r3,#4,0
+	tst	r3,#4
 	beq	1f
 	b	2f
 
 1:
 	/* is it source ? */
-	tst	r3,#8,0
+	tst	r3,#8
 	beq	0b
 	bic r3,r3,#8
 	mov r6,#1024
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 43d6a60..b06602c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -846,20 +846,26 @@
 
 static void __init request_standard_resources(const struct machine_desc *mdesc)
 {
-	struct memblock_region *region;
+	phys_addr_t start, end, res_end;
 	struct resource *res;
+	u64 i;
 
 	kernel_code.start   = virt_to_phys(_text);
 	kernel_code.end     = virt_to_phys(__init_begin - 1);
 	kernel_data.start   = virt_to_phys(_sdata);
 	kernel_data.end     = virt_to_phys(_end - 1);
 
-	for_each_memblock(memory, region) {
-		phys_addr_t start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
-		phys_addr_t end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
+	for_each_mem_range(i, &start, &end) {
 		unsigned long boot_alias_start;
 
 		/*
+		 * In memblock, end points to the first byte after the
+		 * range while in resourses, end points to the last byte in
+		 * the range.
+		 */
+		res_end = end - 1;
+
+		/*
 		 * Some systems have a special memory alias which is only
 		 * used for booting.  We need to advertise this region to
 		 * kexec-tools so they know where bootable RAM is located.
@@ -872,7 +878,7 @@
 				      __func__, sizeof(*res));
 			res->name = "System RAM (boot alias)";
 			res->start = boot_alias_start;
-			res->end = phys_to_idmap(end);
+			res->end = phys_to_idmap(res_end);
 			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 			request_resource(&iomem_resource, res);
 		}
@@ -883,7 +889,7 @@
 			      sizeof(*res));
 		res->name  = "System RAM";
 		res->start = start;
-		res->end = end;
+		res->end = res_end;
 		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
@@ -1175,8 +1181,6 @@
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
 	conswitchp = &vga_con;
-#elif defined(CONFIG_DUMMY_CONSOLE)
-	conswitchp = &dummy_con;
 #endif
 #endif
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index c01f76c..2f81d3a 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -596,7 +596,7 @@
 		switch (retval) {
 		case -ERESTART_RESTARTBLOCK:
 			restart -= 2;
-			/* Fall through */
+			fallthrough;
 		case -ERESTARTNOHAND:
 		case -ERESTARTSYS:
 		case -ERESTARTNOINTR:
@@ -669,7 +669,6 @@
 			} else if (thread_flags & _TIF_UPROBE) {
 				uprobe_notify_resume(regs);
 			} else {
-				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
 			}
@@ -715,7 +714,9 @@
 /* Defer to generic check */
 asmlinkage void addr_limit_check_failed(void)
 {
+#ifdef CONFIG_MMU
 	addr_limit_user_check();
+#endif
 }
 
 #ifdef CONFIG_DEBUG_RSEQ
diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h
index b7b838b..cb076d3 100644
--- a/arch/arm/kernel/signal.h
+++ b/arch/arm/kernel/signal.h
@@ -9,3 +9,5 @@
 	struct siginfo info;
 	struct sigframe sig;
 };
+
+extern struct page *get_signal_page(void);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 46e1be9..8aa7fa9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -26,6 +26,7 @@
 #include <linux/completion.h>
 #include <linux/cpufreq.h>
 #include <linux/irq_work.h>
+#include <linux/kernel_stat.h>
 
 #include <linux/atomic.h>
 #include <asm/bugs.h>
@@ -37,8 +38,6 @@
 #include <asm/idmap.h>
 #include <asm/topology.h>
 #include <asm/mmu_context.h>
-#include <asm/pgtable.h>
-#include <asm/pgalloc.h>
 #include <asm/procinfo.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -67,18 +66,26 @@
 	IPI_CPU_STOP,
 	IPI_IRQ_WORK,
 	IPI_COMPLETION,
+	NR_IPI,
 	/*
 	 * CPU_BACKTRACE is special and not included in NR_IPI
 	 * or tracable with trace_ipi_*
 	 */
-	IPI_CPU_BACKTRACE,
+	IPI_CPU_BACKTRACE = NR_IPI,
 	/*
 	 * SGI8-15 can be reserved by secure firmware, and thus may
 	 * not be usable by the kernel. Please keep the above limited
 	 * to at most 8 entries.
 	 */
+	MAX_IPI
 };
 
+static int ipi_irq_base __read_mostly;
+static int nr_ipi __read_mostly = NR_IPI;
+static struct irq_desc *ipi_desc[MAX_IPI] __read_mostly;
+
+static void ipi_setup(int cpu);
+
 static DECLARE_COMPLETION(cpu_running);
 
 static struct smp_operations smp_ops __ro_after_init;
@@ -228,6 +235,17 @@
 	return cpu != 0;
 }
 
+static void ipi_teardown(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++)
+		disable_percpu_irq(ipi_irq_base + i);
+}
+
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
@@ -249,6 +267,7 @@
 	 * and we must not schedule until we're ready to give up the cpu.
 	 */
 	set_cpu_online(cpu, false);
+	ipi_teardown(cpu);
 
 	/*
 	 * OK - migrate IRQs away from this CPU
@@ -413,7 +432,6 @@
 #endif
 	pr_debug("CPU%u: Booted secondary processor\n", cpu);
 
-	preempt_disable();
 	trace_hardirqs_off();
 
 	/*
@@ -424,6 +442,8 @@
 
 	notify_cpu_starting(cpu);
 
+	ipi_setup(cpu);
+
 	calibrate_delay();
 
 	smp_store_cpu_info(cpu);
@@ -502,14 +522,6 @@
 	}
 }
 
-static void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
-void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
-{
-	if (!__smp_cross_call)
-		__smp_cross_call = fn;
-}
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
 #define S(x,s)	[x] = s
 	S(IPI_WAKEUP, "CPU wakeup interrupts"),
@@ -521,38 +533,28 @@
 	S(IPI_COMPLETION, "completion interrupts"),
 };
 
-static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
-{
-	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
-	__smp_cross_call(target, ipinr);
-}
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
 
 void show_ipi_list(struct seq_file *p, int prec)
 {
 	unsigned int cpu, i;
 
 	for (i = 0; i < NR_IPI; i++) {
+		unsigned int irq;
+
+		if (!ipi_desc[i])
+			continue;
+
+		irq = irq_desc_get_irq(ipi_desc[i]);
 		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ",
-				   __get_irq_stat(cpu, ipi_irqs[i]));
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
 
 		seq_printf(p, " %s\n", ipi_types[i]);
 	}
 }
 
-u64 smp_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = 0;
-	int i;
-
-	for (i = 0; i < NR_IPI; i++)
-		sum += __get_irq_stat(cpu, ipi_irqs[i]);
-
-	return sum;
-}
-
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	smp_cross_call(mask, IPI_CALL_FUNC);
@@ -629,15 +631,12 @@
 	handle_IPI(ipinr, regs);
 }
 
-void handle_IPI(int ipinr, struct pt_regs *regs)
+static void do_handle_IPI(int ipinr)
 {
 	unsigned int cpu = smp_processor_id();
-	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	if ((unsigned)ipinr < NR_IPI) {
+	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
-		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
-	}
 
 	switch (ipinr) {
 	case IPI_WAKEUP:
@@ -645,9 +644,7 @@
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
-		irq_enter();
 		tick_receive_broadcast();
-		irq_exit();
 		break;
 #endif
 
@@ -656,36 +653,26 @@
 		break;
 
 	case IPI_CALL_FUNC:
-		irq_enter();
 		generic_smp_call_function_interrupt();
-		irq_exit();
 		break;
 
 	case IPI_CPU_STOP:
-		irq_enter();
 		ipi_cpu_stop(cpu);
-		irq_exit();
 		break;
 
 #ifdef CONFIG_IRQ_WORK
 	case IPI_IRQ_WORK:
-		irq_enter();
 		irq_work_run();
-		irq_exit();
 		break;
 #endif
 
 	case IPI_COMPLETION:
-		irq_enter();
 		ipi_complete(cpu);
-		irq_exit();
 		break;
 
 	case IPI_CPU_BACKTRACE:
 		printk_nmi_enter();
-		irq_enter();
-		nmi_cpu_backtrace(regs);
-		irq_exit();
+		nmi_cpu_backtrace(get_irq_regs());
 		printk_nmi_exit();
 		break;
 
@@ -697,9 +684,67 @@
 
 	if ((unsigned)ipinr < NR_IPI)
 		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
+}
+
+/* Legacy version, should go away once all irqchips have been converted */
+void handle_IPI(int ipinr, struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	irq_enter();
+	do_handle_IPI(ipinr);
+	irq_exit();
+
 	set_irq_regs(old_regs);
 }
 
+static irqreturn_t ipi_handler(int irq, void *data)
+{
+	do_handle_IPI(irq - ipi_irq_base);
+	return IRQ_HANDLED;
+}
+
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
+{
+	trace_ipi_raise_rcuidle(target, ipi_types[ipinr]);
+	__ipi_send_mask(ipi_desc[ipinr], target);
+}
+
+static void ipi_setup(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++)
+		enable_percpu_irq(ipi_irq_base + i, 0);
+}
+
+void __init set_smp_ipi_range(int ipi_base, int n)
+{
+	int i;
+
+	WARN_ON(n < MAX_IPI);
+	nr_ipi = min(n, MAX_IPI);
+
+	for (i = 0; i < nr_ipi; i++) {
+		int err;
+
+		err = request_percpu_irq(ipi_base + i, ipi_handler,
+					 "IPI", &irq_stat);
+		WARN_ON(err);
+
+		ipi_desc[i] = irq_to_desc(ipi_base + i);
+		irq_set_status_flags(ipi_base + i, IRQ_HIDDEN);
+	}
+
+	ipi_irq_base = ipi_base;
+
+	/* Setup the boot CPU immediately */
+	ipi_setup(smp_processor_id());
+}
+
 void smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
@@ -807,7 +852,7 @@
 
 static void raise_nmi(cpumask_t *mask)
 {
-	__smp_cross_call(mask, IPI_CPU_BACKTRACE);
+	__ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask);
 }
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
diff --git a/arch/arm/kernel/spectre.c b/arch/arm/kernel/spectre.c
new file mode 100644
index 0000000..0dcefc3
--- /dev/null
+++ b/arch/arm/kernel/spectre.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/bpf.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+
+#include <asm/spectre.h>
+
+static bool _unprivileged_ebpf_enabled(void)
+{
+#ifdef CONFIG_BPF_SYSCALL
+	return !sysctl_unprivileged_bpf_disabled;
+#else
+	return false;
+#endif
+}
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+static unsigned int spectre_v2_state;
+static unsigned int spectre_v2_methods;
+
+void spectre_v2_update_state(unsigned int state, unsigned int method)
+{
+	if (state > spectre_v2_state)
+		spectre_v2_state = state;
+	spectre_v2_methods |= method;
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	const char *method;
+
+	if (spectre_v2_state == SPECTRE_UNAFFECTED)
+		return sprintf(buf, "%s\n", "Not affected");
+
+	if (spectre_v2_state != SPECTRE_MITIGATED)
+		return sprintf(buf, "%s\n", "Vulnerable");
+
+	if (_unprivileged_ebpf_enabled())
+		return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n");
+
+	switch (spectre_v2_methods) {
+	case SPECTRE_V2_METHOD_BPIALL:
+		method = "Branch predictor hardening";
+		break;
+
+	case SPECTRE_V2_METHOD_ICIALLU:
+		method = "I-cache invalidation";
+		break;
+
+	case SPECTRE_V2_METHOD_SMC:
+	case SPECTRE_V2_METHOD_HVC:
+		method = "Firmware call";
+		break;
+
+	case SPECTRE_V2_METHOD_LOOP8:
+		method = "History overwrite";
+		break;
+
+	default:
+		method = "Multiple mitigations";
+		break;
+	}
+
+	return sprintf(buf, "Mitigation: %s\n", method);
+}
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 76ea417..db798ea 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -54,8 +54,7 @@
 
 	frame->sp = frame->fp;
 	frame->fp = *(unsigned long *)(fp);
-	frame->pc = frame->lr;
-	frame->lr = *(unsigned long *)(fp + 4);
+	frame->pc = *(unsigned long *)(fp + 4);
 #else
 	/* check current frame pointer is within bounds */
 	if (fp < low + 12 || fp > high - 4)
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index e126386..43f0a3e 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -3,12 +3,11 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
+#include <linux/pgtable.h>
 
 #include <asm/bugs.h>
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
 #include <asm/memory.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index e640871..6166ba3 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -97,12 +97,12 @@
 {
 	int si_code;
 
-	down_read(&current->mm->mmap_sem);
+	mmap_read_lock(current->mm);
 	if (find_vma(current->mm, addr) == NULL)
 		si_code = SEGV_MAPERR;
 	else
 		si_code = SEGV_ACCERR;
-	up_read(&current->mm->mmap_sem);
+	mmap_read_unlock(current->mm);
 
 	pr_debug("SWP{B} emulation: access caused memory abort!\n");
 	arm_notify_die("Illegal memory access", regs,
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 17bd32b..075a2e0 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -248,25 +248,21 @@
 	__u64 data;
 } __attribute__ ((packed,aligned(4)));
 
+#ifdef CONFIG_EPOLL
 asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd,
 				   struct oabi_epoll_event __user *event)
 {
 	struct oabi_epoll_event user;
 	struct epoll_event kernel;
-	mm_segment_t fs;
-	long ret;
 
-	if (op == EPOLL_CTL_DEL)
-		return sys_epoll_ctl(epfd, op, fd, NULL);
-	if (copy_from_user(&user, event, sizeof(user)))
+	if (ep_op_has_event(op) &&
+	    copy_from_user(&user, event, sizeof(user)))
 		return -EFAULT;
+
 	kernel.events = user.events;
 	kernel.data   = user.data;
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = sys_epoll_ctl(epfd, op, fd, &kernel);
-	set_fs(fs);
-	return ret;
+
+	return do_epoll_ctl(epfd, op, fd, &kernel, false);
 }
 
 asmlinkage long sys_oabi_epoll_wait(int epfd,
@@ -303,6 +299,20 @@
 	kfree(kbuf);
 	return err ? -EFAULT : ret;
 }
+#else
+asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd,
+				   struct oabi_epoll_event __user *event)
+{
+	return -EINVAL;
+}
+
+asmlinkage long sys_oabi_epoll_wait(int epfd,
+				    struct oabi_epoll_event __user *events,
+				    int maxevents, int timeout)
+{
+	return -EINVAL;
+}
+#endif
 
 struct oabi_sembuf {
 	unsigned short	sem_num;
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 9d9b1db..d3a85f0 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -18,6 +18,7 @@
 #include <asm/memory.h>
 #include <asm/system_info.h>
 #include <asm/traps.h>
+#include <asm/tcm.h>
 
 #define TCMTR_FORMAT_MASK	0xe0000000U
 
@@ -30,8 +31,8 @@
 extern char __dtcm_start, __sdtcm_data, __edtcm_data;
 
 /* These will be increased as we run */
-u32 dtcm_end = DTCM_OFFSET;
-u32 itcm_end = ITCM_OFFSET;
+static u32 dtcm_end = DTCM_OFFSET;
+static u32 itcm_end = ITCM_OFFSET;
 
 /*
  * TCM memory resources
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index b996b2c..09b149b 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -8,7 +8,7 @@
  *  This file contains the ARM-specific time handling details:
  *  reading the RTC at bootup, etc...
  */
-#include <linux/clk-provider.h>
+#include <linux/clockchips.h>
 #include <linux/clocksource.h>
 #include <linux/errno.h>
 #include <linux/export.h>
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
+#include <linux/of_clk.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/sched_clock.h>
@@ -107,5 +108,6 @@
 		of_clk_init(NULL);
 #endif
 		timer_probe();
+		tick_setup_hrtimer_broadcast();
 	}
 }
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 8d2e61d..ef0058d 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -95,7 +95,7 @@
 				 GFP_NOWAIT);
 
 	for_each_possible_cpu(cpu) {
-		const u32 *rate;
+		const __be32 *rate;
 		int len;
 
 		/* too early to use cpu->of_node */
@@ -178,15 +178,6 @@
 #endif
 
 /*
- * The current assumption is that we can power gate each core independently.
- * This will be superseded by DT binding once available.
- */
-const struct cpumask *cpu_corepower_mask(int cpu)
-{
-	return &cpu_topology[cpu].thread_sibling;
-}
-
-/*
  * store_cpu_topology is called at boot when only one cpu is running
  * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
  * which prevents simultaneous write access to cpu_topology array
@@ -241,20 +232,6 @@
 	update_siblings_masks(cpuid);
 }
 
-static inline int cpu_corepower_flags(void)
-{
-	return SD_SHARE_PKG_RESOURCES  | SD_SHARE_POWERDOMAIN;
-}
-
-static struct sched_domain_topology_level arm_topology[] = {
-#ifdef CONFIG_SCHED_MC
-	{ cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) },
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
-#endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
-
 /*
  * init_cpu_topology is called at boot when only one cpu is running
  * which prevent simultaneous write access to cpu_topology array
@@ -265,7 +242,4 @@
 	smp_wmb();
 
 	parse_dt_topology();
-
-	/* Set scheduler topology descriptor */
-	set_sched_topology(arm_topology);
 }
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 97a5125..2d9e72a 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -30,6 +30,7 @@
 #include <linux/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/exception.h>
+#include <asm/spectre.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
 #include <asm/ptrace.h>
@@ -62,21 +63,24 @@
 
 static void dump_mem(const char *, const char *, unsigned long, unsigned long);
 
-void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
+void dump_backtrace_entry(unsigned long where, unsigned long from,
+			  unsigned long frame, const char *loglvl)
 {
 	unsigned long end = frame + 4 + sizeof(struct pt_regs);
 
 #ifdef CONFIG_KALLSYMS
-	printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
+	printk("%s[<%08lx>] (%ps) from [<%08lx>] (%pS)\n",
+		loglvl, where, (void *)where, from, (void *)from);
 #else
-	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
+	printk("%sFunction entered at [<%08lx>] from [<%08lx>]\n",
+		loglvl, where, from);
 #endif
 
 	if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE))
-		dump_mem("", "Exception stack", frame + 4, end);
+		dump_mem(loglvl, "Exception stack", frame + 4, end);
 }
 
-void dump_backtrace_stm(u32 *stack, u32 instruction)
+void dump_backtrace_stm(u32 *stack, u32 instruction, const char *loglvl)
 {
 	char str[80], *p;
 	unsigned int x;
@@ -88,12 +92,12 @@
 			if (++x == 6) {
 				x = 0;
 				p = str;
-				printk("%s\n", str);
+				printk("%s%s\n", loglvl, str);
 			}
 		}
 	}
 	if (p != str)
-		printk("%s\n", str);
+		printk("%s%s\n", loglvl, str);
 }
 
 #ifndef CONFIG_ARM_UNWIND
@@ -201,17 +205,19 @@
 }
 
 #ifdef CONFIG_ARM_UNWIND
-static inline void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+static inline void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+				  const char *loglvl)
 {
-	unwind_backtrace(regs, tsk);
+	unwind_backtrace(regs, tsk, loglvl);
 }
 #else
-static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+			   const char *loglvl)
 {
 	unsigned int fp, mode;
 	int ok = 1;
 
-	printk("Backtrace: ");
+	printk("%sBacktrace: ", loglvl);
 
 	if (!tsk)
 		tsk = current;
@@ -238,18 +244,20 @@
 	pr_cont("\n");
 
 	if (ok)
-		c_backtrace(fp, mode);
+		c_backtrace(fp, mode, loglvl);
 }
 #endif
 
-void show_stack(struct task_struct *tsk, unsigned long *sp)
+void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 {
-	dump_backtrace(NULL, tsk);
+	dump_backtrace(NULL, tsk, loglvl);
 	barrier();
 }
 
 #ifdef CONFIG_PREEMPT
 #define S_PREEMPT " PREEMPT"
+#elif defined(CONFIG_PREEMPT_RT)
+#define S_PREEMPT " PREEMPT_RT"
 #else
 #define S_PREEMPT ""
 #endif
@@ -286,7 +294,7 @@
 	if (!user_mode(regs) || in_interrupt()) {
 		dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp,
 			 THREAD_SIZE + (unsigned long)task_stack_page(tsk));
-		dump_backtrace(regs, tsk);
+		dump_backtrace(regs, tsk, KERN_EMERG);
 		dump_instr(KERN_EMERG, regs);
 	}
 
@@ -389,7 +397,7 @@
 	u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
 #endif
 
-	if (probe_kernel_address((unsigned *)pc, bkpt))
+	if (get_kernel_nofault(bkpt, (void *)pc))
 		return 0;
 
 	return bkpt == insn;
@@ -564,7 +572,7 @@
 		if (fatal_signal_pending(current))
 			return 0;
 
-		ret = flush_cache_user_range(start, start + chunk);
+		ret = flush_icache_user_range(start, start + chunk);
 		if (ret)
 			return ret;
 
@@ -661,10 +669,10 @@
 	if (user_debug & UDBG_SYSCALL) {
 		pr_err("[%d] %s: arm syscall %d\n",
 		       task_pid_nr(current), current->comm, no);
-		dump_instr("", regs);
+		dump_instr(KERN_ERR, regs);
 		if (user_mode(regs)) {
 			__show_regs(regs);
-			c_backtrace(frame_pointer(regs), processor_mode(regs));
+			c_backtrace(frame_pointer(regs), processor_mode(regs), KERN_ERR);
 		}
 	}
 #endif
@@ -799,10 +807,59 @@
 }
 #endif
 
+#ifndef CONFIG_CPU_V7M
+static void copy_from_lma(void *vma, void *lma_start, void *lma_end)
+{
+	memcpy(vma, lma_start, lma_end - lma_start);
+}
+
+static void flush_vectors(void *vma, size_t offset, size_t size)
+{
+	unsigned long start = (unsigned long)vma + offset;
+	unsigned long end = start + size;
+
+	flush_icache_range(start, end);
+}
+
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+int spectre_bhb_update_vectors(unsigned int method)
+{
+	extern char __vectors_bhb_bpiall_start[], __vectors_bhb_bpiall_end[];
+	extern char __vectors_bhb_loop8_start[], __vectors_bhb_loop8_end[];
+	void *vec_start, *vec_end;
+
+	if (system_state > SYSTEM_SCHEDULING) {
+		pr_err("CPU%u: Spectre BHB workaround too late - system vulnerable\n",
+		       smp_processor_id());
+		return SPECTRE_VULNERABLE;
+	}
+
+	switch (method) {
+	case SPECTRE_V2_METHOD_LOOP8:
+		vec_start = __vectors_bhb_loop8_start;
+		vec_end = __vectors_bhb_loop8_end;
+		break;
+
+	case SPECTRE_V2_METHOD_BPIALL:
+		vec_start = __vectors_bhb_bpiall_start;
+		vec_end = __vectors_bhb_bpiall_end;
+		break;
+
+	default:
+		pr_err("CPU%u: unknown Spectre BHB state %d\n",
+		       smp_processor_id(), method);
+		return SPECTRE_VULNERABLE;
+	}
+
+	copy_from_lma(vectors_page, vec_start, vec_end);
+	flush_vectors(vectors_page, 0, vec_end - vec_start);
+
+	return SPECTRE_MITIGATED;
+}
+#endif
+
 void __init early_trap_init(void *vectors_base)
 {
-#ifndef CONFIG_CPU_V7M
-	unsigned long vectors = (unsigned long)vectors_base;
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	unsigned i;
@@ -823,17 +880,20 @@
 	 * into the vector page, mapped at 0xffff0000, and ensure these
 	 * are visible to the instruction stream.
 	 */
-	memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start);
-	memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start);
+	copy_from_lma(vectors_base, __vectors_start, __vectors_end);
+	copy_from_lma(vectors_base + 0x1000, __stubs_start, __stubs_end);
 
 	kuser_init(vectors_base);
 
-	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
+	flush_vectors(vectors_base, 0, PAGE_SIZE * 2);
+}
 #else /* ifndef CONFIG_CPU_V7M */
+void __init early_trap_init(void *vectors_base)
+{
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated
 	 * memory area. The address is configurable and so a table in the kernel
 	 * image can be used.
 	 */
-#endif
 }
+#endif
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 4574e6a..d2bd0df 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -444,7 +444,7 @@
 		ctrl.vrs[PC] = ctrl.vrs[LR];
 
 	/* check for infinite loop */
-	if (frame->pc == ctrl.vrs[PC])
+	if (frame->pc == ctrl.vrs[PC] && frame->sp == ctrl.vrs[SP])
 		return -URC_FAILURE;
 
 	frame->fp = ctrl.vrs[FP];
@@ -455,7 +455,8 @@
 	return URC_OK;
 }
 
-void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk)
+void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk,
+		      const char *loglvl)
 {
 	struct stackframe frame;
 
@@ -493,7 +494,7 @@
 		urc = unwind_frame(&frame);
 		if (urc < 0)
 			break;
-		dump_backtrace_entry(where, frame.pc, frame.sp - 4);
+		dump_backtrace_entry(where, frame.pc, frame.sp - 4, loglvl);
 	}
 }
 
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 6c69a55..fddd08a 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -23,6 +23,8 @@
 #include <asm/vdso.h>
 #include <asm/vdso_datapage.h>
 #include <clocksource/arm_arch_timer.h>
+#include <vdso/helpers.h>
+#include <vdso/vsyscall.h>
 
 #define MAX_SYMNAME	64
 
@@ -37,7 +39,7 @@
  * The VDSO data page.
  */
 static union vdso_data_store vdso_data_store __page_aligned_data;
-static struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = vdso_data_store.data;
 
 static struct page *vdso_data_page __ro_after_init;
 static const struct vm_special_mapping vdso_data_mapping = {
@@ -77,7 +79,7 @@
 /* Cached result of boot-time check for whether the arch timer exists,
  * and if so, whether the virtual counter is useable.
  */
-static bool cntvct_ok __ro_after_init;
+bool cntvct_ok __ro_after_init;
 
 static bool __init cntvct_functional(void)
 {
@@ -182,6 +184,7 @@
 	if (!cntvct_ok) {
 		vdso_nullpatch_one(&einfo, "__vdso_gettimeofday");
 		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime");
+		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64");
 	}
 }
 
@@ -238,7 +241,7 @@
 	return PTR_ERR_OR_ZERO(vma);
 }
 
-/* assumes mmap_sem is write-locked */
+/* assumes mmap_lock is write-locked */
 void arm_install_vdso(struct mm_struct *mm, unsigned long addr)
 {
 	struct vm_area_struct *vma;
@@ -264,84 +267,3 @@
 		mm->context.vdso = addr;
 }
 
-static void vdso_write_begin(struct vdso_data *vdata)
-{
-	++vdso_data->seq_count;
-	smp_wmb(); /* Pairs with smp_rmb in vdso_read_retry */
-}
-
-static void vdso_write_end(struct vdso_data *vdata)
-{
-	smp_wmb(); /* Pairs with smp_rmb in vdso_read_begin */
-	++vdso_data->seq_count;
-}
-
-static bool tk_is_cntvct(const struct timekeeper *tk)
-{
-	if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
-		return false;
-
-	if (tk->tkr_mono.clock->archdata.clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
-		return false;
-
-	return true;
-}
-
-/**
- * update_vsyscall - update the vdso data page
- *
- * Increment the sequence counter, making it odd, indicating to
- * userspace that an update is in progress.  Update the fields used
- * for coarse clocks and, if the architected system timer is in use,
- * the fields used for high precision clocks.  Increment the sequence
- * counter again, making it even, indicating to userspace that the
- * update is finished.
- *
- * Userspace is expected to sample seq_count before reading any other
- * fields from the data page.  If seq_count is odd, userspace is
- * expected to wait until it becomes even.  After copying data from
- * the page, userspace must sample seq_count again; if it has changed
- * from its previous value, userspace must retry the whole sequence.
- *
- * Calls to update_vsyscall are serialized by the timekeeping core.
- */
-void update_vsyscall(struct timekeeper *tk)
-{
-	struct timespec64 *wtm = &tk->wall_to_monotonic;
-
-	if (!cntvct_ok) {
-		/* The entry points have been zeroed, so there is no
-		 * point in updating the data page.
-		 */
-		return;
-	}
-
-	vdso_write_begin(vdso_data);
-
-	vdso_data->tk_is_cntvct			= tk_is_cntvct(tk);
-	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
-	vdso_data->xtime_coarse_nsec		= (u32)(tk->tkr_mono.xtime_nsec >>
-							tk->tkr_mono.shift);
-	vdso_data->wtm_clock_sec		= wtm->tv_sec;
-	vdso_data->wtm_clock_nsec		= wtm->tv_nsec;
-
-	if (vdso_data->tk_is_cntvct) {
-		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
-		vdso_data->xtime_clock_sec	= tk->xtime_sec;
-		vdso_data->xtime_clock_snsec	= tk->tkr_mono.xtime_nsec;
-		vdso_data->cs_mult		= tk->tkr_mono.mult;
-		vdso_data->cs_shift		= tk->tkr_mono.shift;
-		vdso_data->cs_mask		= tk->tkr_mono.mask;
-	}
-
-	vdso_write_end(vdso_data);
-
-	flush_dcache_page(virt_to_page(vdso_data));
-}
-
-void update_vsyscall_tz(void)
-{
-	vdso_data->tz_minuteswest	= sys_tz.tz_minuteswest;
-	vdso_data->tz_dsttime		= sys_tz.tz_dsttime;
-	flush_dcache_page(virt_to_page(vdso_data));
-}
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 8c74037..f14c236 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -9,15 +9,13 @@
 
 #include <linux/sizes.h>
 
-#include <asm-generic/vmlinux.lds.h>
+#include <asm/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/mpu.h>
 #include <asm/page.h>
 
-#include "vmlinux.lds.h"
-
 OUTPUT_ARCH(arm)
 ENTRY(stext)
 
@@ -42,6 +40,10 @@
 		ARM_DISCARD
 		*(.alt.smp.init)
 		*(.pv_table)
+#ifndef CONFIG_ARM_UNWIND
+		*(.ARM.exidx) *(.ARM.exidx.*)
+		*(.ARM.extab) *(.ARM.extab.*)
+#endif
 	}
 
 	. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
@@ -70,8 +72,6 @@
 	ARM_UNWIND_SECTIONS
 #endif
 
-	NOTES
-
 	_etext = .;			/* End of text and rodata section */
 
 	ARM_VECTORS
@@ -114,7 +114,7 @@
 
 	. = ALIGN(THREAD_SIZE);
 	_sdata = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	.data.ro_after_init : AT(ADDR(.data.ro_after_init) - LOAD_OFFSET) {
 		*(.data..ro_after_init)
 	}
@@ -154,6 +154,10 @@
 	_end = .;
 
 	STABS_DEBUG
+	DWARF_DEBUG
+	ARM_DETAILS
+
+	ARM_ASSERTS
 }
 
 /*
@@ -164,14 +168,6 @@
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
 
-/*
- * The HYP init code can't be more than a page long,
- * and should not cross a page boundary.
- * The above comment applies as well.
- */
-ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE,
-	"HYP init code too big or misaligned")
-
 #ifdef CONFIG_XIP_DEFLATED_DATA
 /*
  * The .bss is used as a stack area for __inflate_kernel_data() whose stack
@@ -180,7 +176,7 @@
 ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA")
 #endif
 
-#ifdef CONFIG_ARM_MPU
+#if defined(CONFIG_ARM_MPU) && !defined(CONFIG_COMPILE_TEST)
 /*
  * Due to PMSAv7 restriction on base address and size we have to
  * enforce minimal alignment restrictions. It was seen that weaker
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 23150c0..f7f4620 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -8,15 +8,13 @@
 #include "vmlinux-xip.lds.S"
 #else
 
-#include <asm-generic/vmlinux.lds.h>
+#include <linux/pgtable.h>
+#include <asm/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/mpu.h>
 #include <asm/page.h>
-#include <asm/pgtable.h>
-
-#include "vmlinux.lds.h"
 
 OUTPUT_ARCH(arm)
 ENTRY(stext)
@@ -43,6 +41,10 @@
 #ifndef CONFIG_SMP_ON_UP
 		*(.alt.smp.init)
 #endif
+#ifndef CONFIG_ARM_UNWIND
+		*(.ARM.exidx) *(.ARM.exidx.*)
+		*(.ARM.extab) *(.ARM.extab.*)
+#endif
 	}
 
 	. = PAGE_OFFSET + TEXT_OFFSET;
@@ -81,8 +83,6 @@
 	ARM_UNWIND_SECTIONS
 #endif
 
-	NOTES
-
 #ifdef CONFIG_STRICT_KERNEL_RWX
 	. = ALIGN(1<<SECTION_SHIFT);
 #else
@@ -143,7 +143,7 @@
 	__init_end = .;
 
 	_sdata = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
@@ -153,6 +153,10 @@
 	_end = .;
 
 	STABS_DEBUG
+	DWARF_DEBUG
+	ARM_DETAILS
+
+	ARM_ASSERTS
 }
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
@@ -172,12 +176,4 @@
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
 
-/*
- * The HYP init code can't be more than a page long,
- * and should not cross a page boundary.
- * The above comment applies as well.
- */
-ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE,
-	"HYP init code too big or misaligned")
-
 #endif /* CONFIG_XIP_KERNEL */
diff --git a/arch/arm/kernel/vmlinux.lds.h b/arch/arm/kernel/vmlinux.lds.h
deleted file mode 100644
index 8247bc1..0000000
--- a/arch/arm/kernel/vmlinux.lds.h
+++ /dev/null
@@ -1,137 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifdef CONFIG_HOTPLUG_CPU
-#define ARM_CPU_DISCARD(x)
-#define ARM_CPU_KEEP(x)		x
-#else
-#define ARM_CPU_DISCARD(x)	x
-#define ARM_CPU_KEEP(x)
-#endif
-
-#if (defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)) || \
-	defined(CONFIG_GENERIC_BUG) || defined(CONFIG_JUMP_LABEL)
-#define ARM_EXIT_KEEP(x)	x
-#define ARM_EXIT_DISCARD(x)
-#else
-#define ARM_EXIT_KEEP(x)
-#define ARM_EXIT_DISCARD(x)	x
-#endif
-
-#ifdef CONFIG_MMU
-#define ARM_MMU_KEEP(x)		x
-#define ARM_MMU_DISCARD(x)
-#else
-#define ARM_MMU_KEEP(x)
-#define ARM_MMU_DISCARD(x)	x
-#endif
-
-#define PROC_INFO							\
-		. = ALIGN(4);						\
-		__proc_info_begin = .;					\
-		*(.proc.info.init)					\
-		__proc_info_end = .;
-
-#define HYPERVISOR_TEXT							\
-		__hyp_text_start = .;					\
-		*(.hyp.text)						\
-		__hyp_text_end = .;
-
-#define IDMAP_TEXT							\
-		ALIGN_FUNCTION();					\
-		__idmap_text_start = .;					\
-		*(.idmap.text)						\
-		__idmap_text_end = .;					\
-		. = ALIGN(PAGE_SIZE);					\
-		__hyp_idmap_text_start = .;				\
-		*(.hyp.idmap.text)					\
-		__hyp_idmap_text_end = .;
-
-#define ARM_DISCARD							\
-		*(.ARM.exidx.exit.text)					\
-		*(.ARM.extab.exit.text)					\
-		*(.ARM.exidx.text.exit)					\
-		*(.ARM.extab.text.exit)					\
-		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))		\
-		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))		\
-		ARM_EXIT_DISCARD(EXIT_TEXT)				\
-		ARM_EXIT_DISCARD(EXIT_DATA)				\
-		EXIT_CALL						\
-		ARM_MMU_DISCARD(*(.text.fixup))				\
-		ARM_MMU_DISCARD(*(__ex_table))				\
-		*(.discard)						\
-		*(.discard.*)
-
-#define ARM_TEXT							\
-		IDMAP_TEXT						\
-		__entry_text_start = .;					\
-		*(.entry.text)						\
-		__entry_text_end = .;					\
-		IRQENTRY_TEXT						\
-		SOFTIRQENTRY_TEXT					\
-		TEXT_TEXT						\
-		SCHED_TEXT						\
-		CPUIDLE_TEXT						\
-		LOCK_TEXT						\
-		HYPERVISOR_TEXT						\
-		KPROBES_TEXT						\
-		*(.gnu.warning)						\
-		*(.glue_7)						\
-		*(.glue_7t)						\
-		. = ALIGN(4);						\
-		*(.got)			/* Global offset table */	\
-		ARM_CPU_KEEP(PROC_INFO)
-
-/* Stack unwinding tables */
-#define ARM_UNWIND_SECTIONS						\
-	. = ALIGN(8);							\
-	.ARM.unwind_idx : {						\
-		__start_unwind_idx = .;					\
-		*(.ARM.exidx*)						\
-		__stop_unwind_idx = .;					\
-	}								\
-	.ARM.unwind_tab : {						\
-		__start_unwind_tab = .;					\
-		*(.ARM.extab*)						\
-		__stop_unwind_tab = .;					\
-	}
-
-/*
- * The vectors and stubs are relocatable code, and the
- * only thing that matters is their relative offsets
- */
-#define ARM_VECTORS							\
-	__vectors_start = .;						\
-	.vectors 0xffff0000 : AT(__vectors_start) {			\
-		*(.vectors)						\
-	}								\
-	. = __vectors_start + SIZEOF(.vectors);				\
-	__vectors_end = .;						\
-									\
-	__stubs_start = .;						\
-	.stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) {		\
-		*(.stubs)						\
-	}								\
-	. = __stubs_start + SIZEOF(.stubs);				\
-	__stubs_end = .;						\
-									\
-	PROVIDE(vector_fiq_offset = vector_fiq - ADDR(.vectors));
-
-#define ARM_TCM								\
-	__itcm_start = ALIGN(4);					\
-	.text_itcm ITCM_OFFSET : AT(__itcm_start - LOAD_OFFSET) {	\
-		__sitcm_text = .;					\
-		*(.tcm.text)						\
-		*(.tcm.rodata)						\
-		. = ALIGN(4);						\
-		__eitcm_text = .;					\
-	}								\
-	. = __itcm_start + SIZEOF(.text_itcm);				\
-									\
-	__dtcm_start = .;						\
-	.data_dtcm DTCM_OFFSET : AT(__dtcm_start - LOAD_OFFSET) {	\
-		__sdtcm_data = .;					\
-		*(.tcm.data)						\
-		. = ALIGN(4);						\
-		__edtcm_data = .;					\
-	}								\
-	. = __dtcm_start + SIZEOF(.data_dtcm);