Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "Although there isn't tonnes of code in terms of line count, there are
  a fair few headline features which I've noted both in the tag and also
  in the merge commits when I pulled everything together.

  The part I'm most pleased with is that we had 35 contributors this
  time around, which feels like a big jump from the usual small group of
  core arm64 arch developers. Hopefully they all enjoyed it so much that
  they'll continue to contribute, but we'll see.

  It's probably worth highlighting that we've pulled in a branch from
  the risc-v folks which moves our CPU topology code out to where it can
  be shared with others.

  Summary:

   - 52-bit virtual addressing in the kernel

   - New ABI to allow tagged user pointers to be dereferenced by
     syscalls

   - Early RNG seeding by the bootloader

   - Improve robustness of SMP boot

   - Fix TLB invalidation in light of recent architectural
     clarifications

   - Support for i.MX8 DDR PMU

   - Remove direct LSE instruction patching in favour of static keys

   - Function error injection using kprobes

   - Support for the PPTT "thread" flag introduced by ACPI 6.3

   - Move PSCI idle code into proper cpuidle driver

   - Relaxation of implicit I/O memory barriers

   - Build with RELR relocations when toolchain supports them

   - Numerous cleanups and non-critical fixes"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (114 commits)
  arm64: remove __iounmap
  arm64: atomics: Use K constraint when toolchain appears to support it
  arm64: atomics: Undefine internal macros after use
  arm64: lse: Make ARM64_LSE_ATOMICS depend on JUMP_LABEL
  arm64: asm: Kill 'asm/atomic_arch.h'
  arm64: lse: Remove unused 'alt_lse' assembly macro
  arm64: atomics: Remove atomic_ll_sc compilation unit
  arm64: avoid using hard-coded registers for LSE atomics
  arm64: atomics: avoid out-of-line ll/sc atomics
  arm64: Use correct ll/sc atomic constraints
  jump_label: Don't warn on __exit jump entries
  docs/perf: Add documentation for the i.MX8 DDR PMU
  perf/imx_ddr: Add support for AXI ID filtering
  arm64: kpti: ensure patched kernel text is fetched from PoU
  arm64: fix fixmap copy for 16K pages and 48-bit VA
  perf/smmuv3: Validate groups for global filtering
  perf/smmuv3: Validate group size
  arm64: Relax Documentation/arm64/tagged-pointers.rst
  arm64: kvm: Replace hardcoded '1' with SYS_PAR_EL1_F
  arm64: mm: Ignore spurious translation faults taken from the kernel
  ...

24 files changed, 399 insertions, 408 deletions

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b1fdc486aed8..9323bcc40a58 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -894,7 +894,7 @@ static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int _
 	u32 midr = read_cpuid_id();
 
 	/* Cavium ThunderX pass 1.x and 2.x */
-	return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX,
+	return midr_is_cpu_model_range(midr, MIDR_THUNDERX,
 		MIDR_CPU_VAR_REV(0, 0),
 		MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK));
 }
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index d1048173fd8a..e4d6af2fdec7 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -11,6 +11,7 @@
 #include <linux/cpu_pm.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/psci.h>
 
 #include <asm/cpuidle.h>
 #include <asm/cpu_ops.h>
@@ -46,17 +47,58 @@ int arm_cpuidle_suspend(int index)
 
 #define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags))
 
+static int psci_acpi_cpu_init_idle(unsigned int cpu)
+{
+	int i, count;
+	struct acpi_lpi_state *lpi;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+
+	/*
+	 * If the PSCI cpu_suspend function hook has not been initialized
+	 * idle states must not be enabled, so bail out
+	 */
+	if (!psci_ops.cpu_suspend)
+		return -EOPNOTSUPP;
+
+	if (unlikely(!pr || !pr->flags.has_lpi))
+		return -EINVAL;
+
+	count = pr->power.count - 1;
+	if (count <= 0)
+		return -ENODEV;
+
+	for (i = 0; i < count; i++) {
+		u32 state;
+
+		lpi = &pr->power.lpi_states[i + 1];
+		/*
+		 * Only bits[31:0] represent a PSCI power_state while
+		 * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification
+		 */
+		state = lpi->address;
+		if (!psci_power_state_is_valid(state)) {
+			pr_warn("Invalid PSCI power state %#x\n", state);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 int acpi_processor_ffh_lpi_probe(unsigned int cpu)
 {
-	return arm_cpuidle_init(cpu);
+	return psci_acpi_cpu_init_idle(cpu);
 }
 
 int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
 {
+	u32 state = lpi->address;
+
 	if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags))
-		return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend,
-						lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter,
+						lpi->index, state);
 	else
-		return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+		return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter,
+					     lpi->index, state);
 }
 #endif
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 876055e37352..05933c065732 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -33,7 +33,7 @@
 DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
 static struct cpuinfo_arm64 boot_cpu_data;
 
-static char *icache_policy_str[] = {
+static const char *icache_policy_str[] = {
 	[0 ... ICACHE_POLICY_PIPT]	= "RESERVED/UNKNOWN",
 	[ICACHE_POLICY_VIPT]		= "VIPT",
 	[ICACHE_POLICY_PIPT]		= "PIPT",
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 320a30dbe35e..84a822748c84 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -30,9 +30,9 @@
  * Context tracking subsystem.  Used to instrument transitions
  * between user and kernel mode.
  */
-	.macro ct_user_exit
+	.macro ct_user_exit_irqoff
 #ifdef CONFIG_CONTEXT_TRACKING
-	bl	context_tracking_user_exit
+	bl	enter_from_user_mode
 #endif
 	.endm
 
@@ -792,8 +792,8 @@ el0_cp15:
 	/*
 	 * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_cp15instr
@@ -805,8 +805,8 @@ el0_da:
 	 * Data abort handling
 	 */
 	mrs	x26, far_el1
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	clear_address_tag x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -818,11 +818,11 @@ el0_ia:
 	 */
 	mrs	x26, far_el1
 	gic_prio_kentry_setup tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
-	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -832,8 +832,8 @@ el0_fpsimd_acc:
 	/*
 	 * Floating Point or Advanced SIMD access
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_acc
@@ -842,8 +842,8 @@ el0_sve_acc:
 	/*
 	 * Scalable Vector Extension access
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_sve_acc
@@ -852,8 +852,8 @@ el0_fpsimd_exc:
 	/*
 	 * Floating Point, Advanced SIMD or SVE exception
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_fpsimd_exc
@@ -868,11 +868,11 @@ el0_sp_pc:
 	 * Stack or PC alignment exception handling
 	 */
 	gic_prio_kentry_setup tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
-	ct_user_exit
 	mov	x0, x26
 	mov	x1, x25
 	mov	x2, sp
@@ -882,8 +882,8 @@ el0_undef:
 	/*
 	 * Undefined instruction
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, sp
 	bl	do_undefinstr
 	b	ret_to_user
@@ -891,8 +891,8 @@ el0_sys:
 	/*
 	 * System instructions, for trapped cache maintenance instructions
 	 */
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, x25
 	mov	x1, sp
 	bl	do_sysinstr
@@ -902,17 +902,18 @@ el0_dbg:
 	 * Debug exception handling
 	 */
 	tbnz	x24, #0, el0_inv		// EL0 only
+	mrs	x24, far_el1
 	gic_prio_kentry_setup tmp=x3
-	mrs	x0, far_el1
+	ct_user_exit_irqoff
+	mov	x0, x24
 	mov	x1, x25
 	mov	x2, sp
 	bl	do_debug_exception
 	enable_da_f
-	ct_user_exit
 	b	ret_to_user
 el0_inv:
+	ct_user_exit_irqoff
 	enable_daif
-	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
 	mov	x2, x25
@@ -925,13 +926,13 @@ el0_irq:
 	kernel_entry 0
 el0_irq_naked:
 	gic_prio_irq_setup pmr=x20, tmp=x0
+	ct_user_exit_irqoff
 	enable_da_f
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 
-	ct_user_exit
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	tbz	x22, #55, 1f
 	bl	do_el0_irq_bp_hardening
@@ -958,13 +959,14 @@ ENDPROC(el1_error)
 el0_error:
 	kernel_entry 0
 el0_error_naked:
-	mrs	x1, esr_el1
+	mrs	x25, esr_el1
 	gic_prio_kentry_setup tmp=x2
+	ct_user_exit_irqoff
 	enable_dbg
 	mov	x0, sp
+	mov	x1, x25
 	bl	do_serror
 	enable_da_f
-	ct_user_exit
 	b	ret_to_user
 ENDPROC(el0_error)
 
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2cdacd1c141b..989b1944cb71 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -102,6 +102,8 @@ pe_header:
 	 *  x23        stext() .. start_kernel()  physical misalignment/KASLR offset
 	 *  x28        __create_page_tables()     callee preserved temp register
 	 *  x19/x20    __primary_switch()         callee preserved temp registers
+	 *  x24        __primary_switch() .. relocate_kernel()
+	 *                                        current RELR displacement
 	 */
 ENTRY(stext)
 	bl	preserve_boot_args
@@ -308,15 +310,15 @@ __create_page_tables:
 	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
+#ifdef CONFIG_ARM64_VA_BITS_52
 	mrs_s	x6, SYS_ID_AA64MMFR2_EL1
 	and	x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT)
 	mov	x5, #52
 	cbnz	x6, 1f
 #endif
-	mov	x5, #VA_BITS
+	mov	x5, #VA_BITS_MIN
 1:
-	adr_l	x6, vabits_user
+	adr_l	x6, vabits_actual
 	str	x5, [x6]
 	dmb	sy
 	dc	ivac, x6		// Invalidate potentially stale cache line
@@ -724,14 +726,22 @@ __secondary_switched:
 
 	adr_l	x0, secondary_data
 	ldr	x1, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
+	cbz	x1, __secondary_too_slow
 	mov	sp, x1
 	ldr	x2, [x0, #CPU_BOOT_TASK]
+	cbz	x2, __secondary_too_slow
 	msr	sp_el0, x2
 	mov	x29, #0
 	mov	x30, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
 
+__secondary_too_slow:
+	wfe
+	wfi
+	b	__secondary_too_slow
+ENDPROC(__secondary_too_slow)
+
 /*
  * The booting CPU updates the failed status @__early_cpu_boot_status,
  * with MMU turned off.
@@ -772,7 +782,7 @@ ENTRY(__enable_mmu)
 	phys_to_ttbr x1, x1
 	phys_to_ttbr x2, x2
 	msr	ttbr0_el1, x2			// load TTBR0
-	offset_ttbr1 x1
+	offset_ttbr1 x1, x3
 	msr	ttbr1_el1, x1			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
@@ -789,8 +799,8 @@ ENTRY(__enable_mmu)
 ENDPROC(__enable_mmu)
 
 ENTRY(__cpu_secondary_check52bitva)
-#ifdef CONFIG_ARM64_USER_VA_BITS_52
-	ldr_l	x0, vabits_user
+#ifdef CONFIG_ARM64_VA_BITS_52
+	ldr_l	x0, vabits_actual
 	cmp	x0, #52
 	b.ne	2f
 
@@ -834,14 +844,93 @@ __relocate_kernel:
 
 0:	cmp	x9, x10
 	b.hs	1f
-	ldp	x11, x12, [x9], #24
-	ldr	x13, [x9, #-8]
-	cmp	w12, #R_AARCH64_RELATIVE
+	ldp	x12, x13, [x9], #24
+	ldr	x14, [x9, #-8]
+	cmp	w13, #R_AARCH64_RELATIVE
 	b.ne	0b
-	add	x13, x13, x23			// relocate
-	str	x13, [x11, x23]
+	add	x14, x14, x23			// relocate
+	str	x14, [x12, x23]
 	b	0b
-1:	ret
+
+1:
+#ifdef CONFIG_RELR
+	/*
+	 * Apply RELR relocations.
+	 *
+	 * RELR is a compressed format for storing relative relocations. The
+	 * encoded sequence of entries looks like:
+	 * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ]
+	 *
+	 * i.e. start with an address, followed by any number of bitmaps. The
+	 * address entry encodes 1 relocation. The subsequent bitmap entries
+	 * encode up to 63 relocations each, at subsequent offsets following
+	 * the last address entry.
+	 *
+	 * The bitmap entries must have 1 in the least significant bit. The
+	 * assumption here is that an address cannot have 1 in lsb. Odd
+	 * addresses are not supported. Any odd addresses are stored in the RELA
+	 * section, which is handled above.
+	 *
+	 * Excluding the least significant bit in the bitmap, each non-zero
+	 * bit in the bitmap represents a relocation to be applied to
+	 * a corresponding machine word that follows the base address
+	 * word. The second least significant bit represents the machine
+	 * word immediately following the initial address, and each bit
+	 * that follows represents the next word, in linear order. As such,
+	 * a single bitmap can encode up to 63 relocations in a 64-bit object.
+	 *
+	 * In this implementation we store the address of the next RELR table
+	 * entry in x9, the address being relocated by the current address or
+	 * bitmap entry in x13 and the address being relocated by the current
+	 * bit in x14.
+	 *
+	 * Because addends are stored in place in the binary, RELR relocations
+	 * cannot be applied idempotently. We use x24 to keep track of the
+	 * currently applied displacement so that we can correctly relocate if
+	 * __relocate_kernel is called twice with non-zero displacements (i.e.
+	 * if there is both a physical misalignment and a KASLR displacement).
+	 */
+	ldr	w9, =__relr_offset		// offset to reloc table
+	ldr	w10, =__relr_size		// size of reloc table
+	add	x9, x9, x11			// __va(.relr)
+	add	x10, x9, x10			// __va(.relr) + sizeof(.relr)
+
+	sub	x15, x23, x24			// delta from previous offset
+	cbz	x15, 7f				// nothing to do if unchanged
+	mov	x24, x23			// save new offset
+
+2:	cmp	x9, x10
+	b.hs	7f
+	ldr	x11, [x9], #8
+	tbnz	x11, #0, 3f			// branch to handle bitmaps
+	add	x13, x11, x23
+	ldr	x12, [x13]			// relocate address entry
+	add	x12, x12, x15
+	str	x12, [x13], #8			// adjust to start of bitmap
+	b	2b
+
+3:	mov	x14, x13
+4:	lsr	x11, x11, #1
+	cbz	x11, 6f
+	tbz	x11, #0, 5f			// skip bit if not set
+	ldr	x12, [x14]			// relocate bit
+	add	x12, x12, x15
+	str	x12, [x14]
+
+5:	add	x14, x14, #8			// move to next bit's address
+	b	4b
+
+6:	/*
+	 * Move to the next bitmap's address. 8 is the word size, and 63 is the
+	 * number of significant bits in a bitmap entry.
+	 */
+	add	x13, x13, #(8 * 63)
+	b	2b
+
+7:
+#endif
+	ret
+
 ENDPROC(__relocate_kernel)
 #endif
 
@@ -854,6 +943,9 @@ __primary_switch:
 	adrp	x1, init_pg_dir
 	bl	__enable_mmu
 #ifdef CONFIG_RELOCATABLE
+#ifdef CONFIG_RELR
+	mov	x24, #0				// no RELR displacement yet
+#endif
 	bl	__relocate_kernel
 #ifdef CONFIG_RANDOMIZE_BASE
 	ldr	x8, =__primary_switched
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 2f4a2ce7264b..38bcd4d4e43b 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -22,14 +22,14 @@
  * Even switching to our copied tables will cause a changed output address at
  * each stage of the walk.
  */
-.macro break_before_make_ttbr_switch zero_page, page_table, tmp
+.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2
 	phys_to_ttbr \tmp, \zero_page
 	msr	ttbr1_el1, \tmp
 	isb
 	tlbi	vmalle1
 	dsb	nsh
 	phys_to_ttbr \tmp, \page_table
-	offset_ttbr1 \tmp
+	offset_ttbr1 \tmp, \tmp2
 	msr	ttbr1_el1, \tmp
 	isb
 .endm
@@ -70,7 +70,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	 * We execute from ttbr0, change ttbr1 to our copied linear map tables
 	 * with a break-before-make via the zero page
 	 */
-	break_before_make_ttbr_switch	x5, x0, x6
+	break_before_make_ttbr_switch	x5, x0, x6, x8
 
 	mov	x21, x1
 	mov	x30, x2
@@ -101,7 +101,7 @@ ENTRY(swsusp_arch_suspend_exit)
 	dsb	ish		/* wait for PoU cleaning to finish */
 
 	/* switch to the restored kernels page tables */
-	break_before_make_ttbr_switch	x25, x21, x6
+	break_before_make_ttbr_switch	x25, x21, x6, x8
 
 	ic	ialluis
 	dsb	ish
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 9341fcc6e809..e0a7fce0e01c 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -496,7 +496,7 @@ int swsusp_arch_resume(void)
 		rc = -ENOMEM;
 		goto out;
 	}
-	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+	rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END);
 	if (rc)
 		goto out;
 
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
new file mode 100644
index 000000000000..25a2a9b479c2
--- /dev/null
+++ b/arch/arm64/kernel/image-vars.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Linker script variables to be set after section resolution, as
+ * ld.lld does not like variables assigned before SECTIONS is processed.
+ */
+#ifndef __ARM64_KERNEL_IMAGE_VARS_H
+#define __ARM64_KERNEL_IMAGE_VARS_H
+
+#ifndef LINKER_SCRIPT
+#error This file should only be included in vmlinux.lds.S
+#endif
+
+#ifdef CONFIG_EFI
+
+__efistub_stext_offset = stext - _text;
+
+/*
+ * The EFI stub has its own symbol namespace prefixed by __efistub_, to
+ * isolate it from the kernel proper. The following symbols are legally
+ * accessed by the stub, so provide some aliases to make them accessible.
+ * Only include data symbols here, or text symbols of functions that are
+ * guaranteed to be safe when executed at another offset than they were
+ * linked at. The routines below are all implemented in assembler in a
+ * position independent manner
+ */
+__efistub_memcmp		= __pi_memcmp;
+__efistub_memchr		= __pi_memchr;
+__efistub_memcpy		= __pi_memcpy;
+__efistub_memmove		= __pi_memmove;
+__efistub_memset		= __pi_memset;
+__efistub_strlen		= __pi_strlen;
+__efistub_strnlen		= __pi_strnlen;
+__efistub_strcmp		= __pi_strcmp;
+__efistub_strncmp		= __pi_strncmp;
+__efistub_strrchr		= __pi_strrchr;
+__efistub___flush_dcache_area	= __pi___flush_dcache_area;
+
+#ifdef CONFIG_KASAN
+__efistub___memcpy		= __pi_memcpy;
+__efistub___memmove		= __pi_memmove;
+__efistub___memset		= __pi_memset;
+#endif
+
+__efistub__text			= _text;
+__efistub__end			= _end;
+__efistub__edata		= _edata;
+__efistub_screen_info		= screen_info;
+
+#endif
+
+#endif /* __ARM64_KERNEL_IMAGE_VARS_H */
diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h
index 2b85c0d6fa3d..c7d38c660372 100644
--- a/arch/arm64/kernel/image.h
+++ b/arch/arm64/kernel/image.h
@@ -65,46 +65,4 @@
 	DEFINE_IMAGE_LE64(_kernel_offset_le, TEXT_OFFSET);	\
 	DEFINE_IMAGE_LE64(_kernel_flags_le, __HEAD_FLAGS);
 
-#ifdef CONFIG_EFI
-
-/*
- * Use ABSOLUTE() to avoid ld.lld treating this as a relative symbol:
- * https://github.com/ClangBuiltLinux/linux/issues/561
- */
-__efistub_stext_offset = ABSOLUTE(stext - _text);
-
-/*
- * The EFI stub has its own symbol namespace prefixed by __efistub_, to
- * isolate it from the kernel proper. The following symbols are legally
- * accessed by the stub, so provide some aliases to make them accessible.
- * Only include data symbols here, or text symbols of functions that are
- * guaranteed to be safe when executed at another offset than they were
- * linked at. The routines below are all implemented in assembler in a
- * position independent manner
- */
-__efistub_memcmp		= __pi_memcmp;
-__efistub_memchr		= __pi_memchr;
-__efistub_memcpy		= __pi_memcpy;
-__efistub_memmove		= __pi_memmove;
-__efistub_memset		= __pi_memset;
-__efistub_strlen		= __pi_strlen;
-__efistub_strnlen		= __pi_strnlen;
-__efistub_strcmp		= __pi_strcmp;
-__efistub_strncmp		= __pi_strncmp;
-__efistub_strrchr		= __pi_strrchr;
-__efistub___flush_dcache_area	= __pi___flush_dcache_area;
-
-#ifdef CONFIG_KASAN
-__efistub___memcpy		= __pi_memcpy;
-__efistub___memmove		= __pi_memmove;
-__efistub___memset		= __pi_memset;
-#endif
-
-__efistub__text			= _text;
-__efistub__end			= _end;
-__efistub__edata		= _edata;
-__efistub_screen_info		= screen_info;
-
-#endif
-
 #endif /* __ARM64_KERNEL_IMAGE_H */
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 84b059ed04fc..d801a7094076 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -26,7 +26,7 @@
 #define AARCH64_INSN_N_BIT	BIT(22)
 #define AARCH64_INSN_LSL_12	BIT(22)
 
-static int aarch64_insn_encoding_class[] = {
+static const int aarch64_insn_encoding_class[] = {
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_UNKNOWN,
 	AARCH64_INSN_CLS_UNKNOWN,
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 708051655ad9..416f537bf614 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -62,9 +62,6 @@ out:
 	return default_cmdline;
 }
 
-extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size,
-				       pgprot_t prot);
-
 /*
  * This routine will be executed with the kernel mapped at its default virtual
  * address, and if it returns successfully, the kernel will be remapped, and
@@ -93,7 +90,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * attempt at mapping the FDT in setup_machine()
 	 */
 	early_fixmap_init();
-	fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
+	fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	if (!fdt)
 		return 0;
 
@@ -116,15 +113,15 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	/*
 	 * OK, so we are proceeding with KASLR enabled. Calculate a suitable
 	 * kernel image offset from the seed. Let's place the kernel in the
-	 * middle half of the VMALLOC area (VA_BITS - 2), and stay clear of
+	 * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of
 	 * the lower and upper quarters to avoid colliding with other
 	 * allocations.
 	 * Even if we could randomize at page granularity for 16k and 64k pages,
 	 * let's always round to 2 MB so we don't interfere with the ability to
 	 * map using contiguous PTEs
 	 */
-	mask = ((1UL << (VA_BITS - 2)) - 1) & ~(SZ_2M - 1);
-	offset = BIT(VA_BITS - 3) + (seed & mask);
+	mask = ((1UL << (VA_BITS_MIN - 2)) - 1) & ~(SZ_2M - 1);
+	offset = BIT(VA_BITS_MIN - 3) + (seed & mask);
 
 	/* use the top 16 bits to randomize the linear region */
 	memstart_offset_seed = seed >> 48;
diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c
index 2514fd6f12cb..29a9428486a5 100644
--- a/arch/arm64/kernel/kexec_image.c
+++ b/arch/arm64/kernel/kexec_image.c
@@ -84,7 +84,7 @@ static void *image_load(struct kimage *image,
 
 	kbuf.buffer = kernel;
 	kbuf.bufsz = kernel_len;
-	kbuf.mem = 0;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf.memsz = le64_to_cpu(h->image_size);
 	text_offset = le64_to_cpu(h->text_offset);
 	kbuf.buf_align = MIN_KIMG_ALIGN;
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 58871333737a..7b08bf9499b6 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -27,6 +27,8 @@
 #define FDT_PROP_INITRD_END	"linux,initrd-end"
 #define FDT_PROP_BOOTARGS	"bootargs"
 #define FDT_PROP_KASLR_SEED	"kaslr-seed"
+#define FDT_PROP_RNG_SEED	"rng-seed"
+#define RNG_SEED_SIZE		128
 
 const struct kexec_file_ops * const kexec_file_loaders[] = {
 	&kexec_image_ops,
@@ -102,6 +104,19 @@ static int setup_dtb(struct kimage *image,
 				FDT_PROP_KASLR_SEED);
 	}
 
+	/* add rng-seed */
+	if (rng_is_initialized()) {
+		u8 rng_seed[RNG_SEED_SIZE];
+		get_random_bytes(rng_seed, RNG_SEED_SIZE);
+		ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed,
+				RNG_SEED_SIZE);
+		if (ret)
+			goto out;
+	} else {
+		pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+				FDT_PROP_RNG_SEED);
+	}
+
 out:
 	if (ret)
 		return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
@@ -110,7 +125,8 @@ out:
 }
 
 /*
- * More space needed so that we can add initrd, bootargs and kaslr-seed.
+ * More space needed so that we can add initrd, bootargs, kaslr-seed, and
+ * rng-seed.
  */
 #define DTB_EXTRA_SPACE 0x1000
 
@@ -177,7 +193,7 @@ int load_other_segments(struct kimage *image,
 	if (initrd) {
 		kbuf.buffer = initrd;
 		kbuf.bufsz = initrd_len;
-		kbuf.mem = 0;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		kbuf.memsz = initrd_len;
 		kbuf.buf_align = 0;
 		/* within 1GB-aligned window of up to 32GB in size */
@@ -204,7 +220,7 @@ int load_other_segments(struct kimage *image,
 	dtb_len = fdt_totalsize(dtb);
 	kbuf.buffer = dtb;
 	kbuf.bufsz = dtb_len;
-	kbuf.mem = 0;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf.memsz = dtb_len;
 	/* not across 2MB boundary */
 	kbuf.buf_align = SZ_2M;
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index 044c0ae4d6c8..b182442b87a3 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -302,7 +302,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 		/* sort by type, symbol index and addend */
 		sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL);
 
-		if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0)
+		if (!str_has_prefix(secstrings + dstsec->sh_name, ".init"))
 			core_plts += count_plts(syms, rels, numrels,
 						sechdrs[i].sh_info, dstsec);
 		else
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 96e90e270042..a0b4f1bca491 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -19,6 +19,7 @@
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
+#include <linux/smp.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -157,7 +158,6 @@ armv8pmu_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%03llx\n", pmu_attr->id);
 }
 
-#define ARMV8_EVENT_ATTR_RESOLVE(m) #m
 #define ARMV8_EVENT_ATTR(name, config) \
 	PMU_EVENT_ATTR(name, armv8_event_attr_##name, \
 		       config, armv8pmu_events_sysfs_show)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index f674f28df663..03689c0beb34 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>
@@ -38,6 +39,7 @@
 #include <trace/events/power.h>
 #include <linux/percpu.h>
 #include <linux/thread_info.h>
+#include <linux/prctl.h>
 
 #include <asm/alternative.h>
 #include <asm/arch_gicv3.h>
@@ -307,11 +309,18 @@ static void tls_thread_flush(void)
 	}
 }
 
+static void flush_tagged_addr_state(void)
+{
+	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI))
+		clear_thread_flag(TIF_TAGGED_ADDR);
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	flush_tagged_addr_state();
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -565,3 +574,70 @@ void arch_setup_new_exec(void)
 
 	ptrauth_thread_init_user(current);
 }
+
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_disabled;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;
+
+	/*
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled.
+	 */
+	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
+		return -EINVAL;
+
+	update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(void)
+{
+	if (is_compat_task())
+		return -EINVAL;
+
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		return PR_TAGGED_ADDR_ENABLE;
+
+	return 0;
+}
+
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+static int zero;
+static int one = 1;
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr_disabled",
+		.mode		= 0644,
+		.data		= &tagged_addr_disabled,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{ }
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+	return 0;
+}
+
+core_initcall(tagged_addr_init);
+#endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 85ee7d07889e..c9f72b2665f1 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -46,6 +46,11 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static bool cpu_psci_cpu_can_disable(unsigned int cpu)
+{
+	return !psci_tos_resident_on(cpu);
+}
+
 static int cpu_psci_cpu_disable(unsigned int cpu)
 {
 	/* Fail early if we don't have CPU_OFF support */
@@ -105,14 +110,11 @@ static int cpu_psci_cpu_kill(unsigned int cpu)
 
 const struct cpu_operations cpu_psci_ops = {
 	.name		= "psci",
-#ifdef CONFIG_CPU_IDLE
-	.cpu_init_idle	= psci_cpu_init_idle,
-	.cpu_suspend	= psci_cpu_suspend_enter,
-#endif
 	.cpu_init	= cpu_psci_cpu_init,
 	.cpu_prepare	= cpu_psci_cpu_prepare,
 	.cpu_boot	= cpu_psci_cpu_boot,
 #ifdef CONFIG_HOTPLUG_CPU
+	.cpu_can_disable = cpu_psci_cpu_can_disable,
 	.cpu_disable	= cpu_psci_cpu_disable,
 	.cpu_die	= cpu_psci_cpu_die,
 	.cpu_kill	= cpu_psci_cpu_kill,
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 3cf3b135027e..21176d02e21a 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -870,7 +870,7 @@ static int sve_set(struct task_struct *target,
 		goto out;
 
 	/*
-	 * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by
+	 * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
 	 * sve_set_vector_length(), which will also validate them for us:
 	 */
 	ret = sve_set_vector_length(target, header.vl,
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 9c4bad7d7131..56f664561754 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -170,9 +170,13 @@ static void __init smp_build_mpidr_hash(void)
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	void *dt_virt = fixmap_remap_fdt(dt_phys);
+	int size;
+	void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
 	const char *name;
 
+	if (dt_virt)
+		memblock_reserve(dt_phys, size);
+
 	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
 		pr_crit("\n"
 			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
@@ -184,6 +188,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
 			cpu_relax();
 	}
 
+	/* Early fixups are done, map the FDT as read-only now */
+	fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
+
 	name = of_flat_dt_get_machine_name();
 	if (!name)
 		return;
@@ -357,6 +364,15 @@ void __init setup_arch(char **cmdline_p)
 	}
 }
 
+static inline bool cpu_can_disable(unsigned int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable)
+		return cpu_ops[cpu]->cpu_can_disable(cpu);
+#endif
+	return false;
+}
+
 static int __init topology_init(void)
 {
 	int i;
@@ -366,7 +382,7 @@ static int __init topology_init(void)
 
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_data.cpu, i);
-		cpu->hotpluggable = 1;
+		cpu->hotpluggable = cpu_can_disable(i);
 		register_cpu(cpu, i);
 	}
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 018a33e01b0e..dc9fe879c279 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -123,7 +123,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		 * time out.
 		 */
 		wait_for_completion_timeout(&cpu_running,
-					    msecs_to_jiffies(1000));
+					    msecs_to_jiffies(5000));
 
 		if (!cpu_online(cpu)) {
 			pr_crit("CPU%u: failed to come online\n", cpu);
@@ -136,6 +136,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 
 	secondary_data.task = NULL;
 	secondary_data.stack = NULL;
+	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
 	if (ret && status) {
 
@@ -146,6 +147,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		default:
 			pr_err("CPU%u: failed in unknown state : 0x%lx\n",
 					cpu, status);
+			cpus_stuck_in_kernel++;
 			break;
 		case CPU_KILL_ME:
 			if (!op_cpu_kill(cpu)) {
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 76c2739ba8a4..c8a3fee00c11 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -19,7 +19,7 @@
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
-volatile unsigned long __section(".mmuoff.data.read")
+volatile unsigned long __section(.mmuoff.data.read)
 secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 0825c4a856e3..fa9528dfd0ce 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -14,250 +14,13 @@
 #include <linux/acpi.h>
 #include <linux/arch_topology.h>
 #include <linux/cacheinfo.h>
-#include <linux/cpu.h>
-#include <linux/cpumask.h>
 #include <linux/init.h>
 #include <linux/percpu.h>
-#include <linux/node.h>
-#include <linux/nodemask.h>
-#include <linux/of.h>
-#include <linux/sched.h>
-#include <linux/sched/topology.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
-#include <linux/string.h>
 
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
-static int __init get_cpu_for_node(struct device_node *node)
-{
-	struct device_node *cpu_node;
-	int cpu;
-
-	cpu_node = of_parse_phandle(node, "cpu", 0);
-	if (!cpu_node)
-		return -1;
-
-	cpu = of_cpu_node_to_id(cpu_node);
-	if (cpu >= 0)
-		topology_parse_cpu_capacity(cpu_node, cpu);
-	else
-		pr_crit("Unable to find CPU node for %pOF\n", cpu_node);
-
-	of_node_put(cpu_node);
-	return cpu;
-}
-
-static int __init parse_core(struct device_node *core, int package_id,
-			     int core_id)
-{
-	char name[10];
-	bool leaf = true;
-	int i = 0;
-	int cpu;
-	struct device_node *t;
-
-	do {
-		snprintf(name, sizeof(name), "thread%d", i);
-		t = of_get_child_by_name(core, name);
-		if (t) {
-			leaf = false;
-			cpu = get_cpu_for_node(t);
-			if (cpu >= 0) {
-				cpu_topology[cpu].package_id = package_id;
-				cpu_topology[cpu].core_id = core_id;
-				cpu_topology[cpu].thread_id = i;
-			} else {
-				pr_err("%pOF: Can't get CPU for thread\n",
-				       t);
-				of_node_put(t);
-				return -EINVAL;
-			}
-			of_node_put(t);
-		}
-		i++;
-	} while (t);
-
-	cpu = get_cpu_for_node(core);
-	if (cpu >= 0) {
-		if (!leaf) {
-			pr_err("%pOF: Core has both threads and CPU\n",
-			       core);
-			return -EINVAL;
-		}
-
-		cpu_topology[cpu].package_id = package_id;
-		cpu_topology[cpu].core_id = core_id;
-	} else if (leaf) {
-		pr_err("%pOF: Can't get CPU for leaf core\n", core);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int __init parse_cluster(struct device_node *cluster, int depth)
-{
-	char name[10];
-	bool leaf = true;
-	bool has_cores = false;
-	struct device_node *c;
-	static int package_id __initdata;
-	int core_id = 0;
-	int i, ret;
-
-	/*
-	 * First check for child clusters; we currently ignore any
-	 * information about the nesting of clusters and present the
-	 * scheduler with a flat list of them.
-	 */
-	i = 0;
-	do {
-		snprintf(name, sizeof(name), "cluster%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			leaf = false;
-			ret = parse_cluster(c, depth + 1);
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
-		i++;
-	} while (c);
-
-	/* Now check for cores */
-	i = 0;
-	do {
-		snprintf(name, sizeof(name), "core%d", i);
-		c = of_get_child_by_name(cluster, name);
-		if (c) {
-			has_cores = true;
-
-			if (depth == 0) {
-				pr_err("%pOF: cpu-map children should be clusters\n",
-				       c);
-				of_node_put(c);
-				return -EINVAL;
-			}
-
-			if (leaf) {
-				ret = parse_core(c, package_id, core_id++);
-			} else {
-				pr_err("%pOF: Non-leaf cluster with core %s\n",
-				       cluster, name);
-				ret = -EINVAL;
-			}
-
-			of_node_put(c);
-			if (ret != 0)
-				return ret;
-		}
-		i++;
-	} while (c);
-
-	if (leaf && !has_cores)
-		pr_warn("%pOF: empty cluster\n", cluster);
-
-	if (leaf)
-		package_id++;
-
-	return 0;
-}
-
-static int __init parse_dt_topology(void)
-{
-	struct device_node *cn, *map;
-	int ret = 0;
-	int cpu;
-
-	cn = of_find_node_by_path("/cpus");
-	if (!cn) {
-		pr_err("No CPU information found in DT\n");
-		return 0;
-	}
-
-	/*
-	 * When topology is provided cpu-map is essentially a root
-	 * cluster with restricted subnodes.
-	 */
-	map = of_get_child_by_name(cn, "cpu-map");
-	if (!map)
-		goto out;
-
-	ret = parse_cluster(map, 0);
-	if (ret != 0)
-		goto out_map;
-
-	topology_normalize_cpu_scale();
-
-	/*
-	 * Check that all cores are in the topology; the SMP code will
-	 * only mark cores described in the DT as possible.
-	 */
-	for_each_possible_cpu(cpu)
-		if (cpu_topology[cpu].package_id == -1)
-			ret = -EINVAL;
-
-out_map:
-	of_node_put(map);
-out:
-	of_node_put(cn);
-	return ret;
-}
-
-/*
- * cpu topology table
- */
-struct cpu_topology cpu_topology[NR_CPUS];
-EXPORT_SYMBOL_GPL(cpu_topology);
-
-const struct cpumask *cpu_coregroup_mask(int cpu)
-{
-	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
-
-	/* Find the smaller of NUMA, core or LLC siblings */
-	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
-		/* not numa in package, lets use the package siblings */
-		core_mask = &cpu_topology[cpu].core_sibling;
-	}
-	if (cpu_topology[cpu].llc_id != -1) {
-		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
-			core_mask = &cpu_topology[cpu].llc_sibling;
-	}
-
-	return core_mask;
-}
-
-static void update_siblings_masks(unsigned int cpuid)
-{
-	struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
-	int cpu;
-
-	/* update core and thread sibling masks */
-	for_each_online_cpu(cpu) {
-		cpu_topo = &cpu_topology[cpu];
-
-		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
-			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
-			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
-		}
-
-		if (cpuid_topo->package_id != cpu_topo->package_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
-
-		if (cpuid_topo->core_id != cpu_topo->core_id)
-			continue;
-
-		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
-		cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
-	}
-}
-
 void store_cpu_topology(unsigned int cpuid)
 {
 	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
@@ -296,60 +59,31 @@ topology_populated:
 	update_siblings_masks(cpuid);
 }
 
-static void clear_cpu_topology(int cpu)
-{
-	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
-	cpumask_clear(&cpu_topo->llc_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
-
-	cpumask_clear(&cpu_topo->core_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
-	cpumask_clear(&cpu_topo->thread_sibling);
-	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
-}
-
-static void __init reset_cpu_topology(void)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct cpu_topology *cpu_topo = &cpu_topology[cpu];
-
-		cpu_topo->thread_id = -1;
-		cpu_topo->core_id = 0;
-		cpu_topo->package_id = -1;
-		cpu_topo->llc_id = -1;
-
-		clear_cpu_topology(cpu);
-	}
-}
-
-void remove_cpu_topology(unsigned int cpu)
+#ifdef CONFIG_ACPI
+static bool __init acpi_cpu_is_threaded(int cpu)
 {
-	int sibling;
+	int is_threaded = acpi_pptt_cpu_is_thread(cpu);
 
-	for_each_cpu(sibling, topology_core_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
-	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
-	for_each_cpu(sibling, topology_llc_cpumask(cpu))
-		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
+	/*
+	 * if the PPTT doesn't have thread information, assume a homogeneous
+	 * machine and return the current CPU's thread state.
+	 */
+	if (is_threaded < 0)
+		is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
 
-	clear_cpu_topology(cpu);
+	return !!is_threaded;
 }
 
-#ifdef CONFIG_ACPI
 /*
  * Propagate the topology information of the processor_topology_node tree to the
  * cpu_topology array.
  */
-static int __init parse_acpi_topology(void)
+int __init parse_acpi_topology(void)
 {
-	bool is_threaded;
 	int cpu, topology_id;
 
-	is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK;
+	if (acpi_disabled)
+		return 0;
 
 	for_each_possible_cpu(cpu) {
 		int i, cache_id;
@@ -358,7 +92,7 @@ static int __init parse_acpi_topology(void)
 		if (topology_id < 0)
 			return topology_id;
 
-		if (is_threaded) {
+		if (acpi_cpu_is_threaded(cpu)) {
 			cpu_topology[cpu].thread_id = topology_id;
 			topology_id = find_acpi_cpu_topology(cpu, 1);
 			cpu_topology[cpu].core_id   = topology_id;
@@ -384,24 +118,6 @@ static int __init parse_acpi_topology(void)
 
 	return 0;
 }
-
-#else
-static inline int __init parse_acpi_topology(void)
-{
-	return -EINVAL;
-}
 #endif
 
-void __init init_cpu_topology(void)
-{
-	reset_cpu_topology();
 
-	/*
-	 * Discard anything that was parsed if we hit an error so we
-	 * don't use partial information.
-	 */
-	if (!acpi_disabled && parse_acpi_topology())
-		reset_cpu_topology();
-	else if (of_have_populated_dt() && parse_dt_topology())
-		reset_cpu_topology();
-}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 32893b3d9164..34739e80211b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -7,9 +7,11 @@
  */
 
 #include <linux/bug.h>
+#include <linux/context_tracking.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
+#include <linux/kprobes.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
@@ -511,7 +513,7 @@ struct sys64_hook {
 	void (*handler)(unsigned int esr, struct pt_regs *regs);
 };
 
-static struct sys64_hook sys64_hooks[] = {
+static const struct sys64_hook sys64_hooks[] = {
 	{
 		.esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK,
 		.esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL,
@@ -636,7 +638,7 @@ static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
 	arm64_compat_skip_faulting_instruction(regs, 4);
 }
 
-static struct sys64_hook cp15_32_hooks[] = {
+static const struct sys64_hook cp15_32_hooks[] = {
 	{
 		.esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK,
 		.esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ,
@@ -656,7 +658,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 	arm64_compat_skip_faulting_instruction(regs, 4);
 }
 
-static struct sys64_hook cp15_64_hooks[] = {
+static const struct sys64_hook cp15_64_hooks[] = {
 	{
 		.esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK,
 		.esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT,
@@ -667,7 +669,7 @@ static struct sys64_hook cp15_64_hooks[] = {
 
 asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
 {
-	struct sys64_hook *hook, *hook_base;
+	const struct sys64_hook *hook, *hook_base;
 
 	if (!cp15_cond_valid(esr, regs)) {
 		/*
@@ -707,7 +709,7 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
 
 asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 {
-	struct sys64_hook *hook;
+	const struct sys64_hook *hook;
 
 	for (hook = sys64_hooks; hook->handler; hook++)
 		if ((hook->esr_mask & esr) == hook->esr_val) {
@@ -744,6 +746,7 @@ static const char *esr_class_str[] = {
 	[ESR_ELx_EC_SMC64]		= "SMC (AArch64)",
 	[ESR_ELx_EC_SYS64]		= "MSR/MRS (AArch64)",
 	[ESR_ELx_EC_SVE]		= "SVE",
+	[ESR_ELx_EC_ERET]		= "ERET/ERETAA/ERETAB",
 	[ESR_ELx_EC_IMP_DEF]		= "EL3 IMP DEF",
 	[ESR_ELx_EC_IABT_LOW]		= "IABT (lower EL)",
 	[ESR_ELx_EC_IABT_CUR]		= "IABT (current EL)",
@@ -900,6 +903,13 @@ asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr)
 		nmi_exit();
 }
 
+asmlinkage void enter_from_user_mode(void)
+{
+	CT_WARN_ON(ct_state() != CONTEXT_USER);
+	user_exit_irqoff();
+}
+NOKPROBE_SYMBOL(enter_from_user_mode);
+
 void __pte_error(const char *file, int line, unsigned long val)
 {
 	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 7fa008374907..aa76f7259668 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -200,6 +200,15 @@ SECTIONS
 	__rela_offset	= ABSOLUTE(ADDR(.rela.dyn) - KIMAGE_VADDR);
 	__rela_size	= SIZEOF(.rela.dyn);
 
+#ifdef CONFIG_RELR
+	.relr.dyn : ALIGN(8) {
+		*(.relr.dyn)
+	}
+
+	__relr_offset	= ABSOLUTE(ADDR(.relr.dyn) - KIMAGE_VADDR);
+	__relr_size	= SIZEOF(.relr.dyn);
+#endif
+
 	. = ALIGN(SEGMENT_ALIGN);
 	__initdata_end = .;
 	__init_end = .;
@@ -245,6 +254,8 @@ SECTIONS
 	HEAD_SYMBOLS
 }
 
+#include "image-vars.h"
+
 /*
  * The HYP init code and ID map text can't be longer than a page each,
  * and should not cross a page boundary.