21 files changed, 424 insertions, 81 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 623fce7d5fcd..afd6fcc1e8b9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -431,6 +431,9 @@
 	arcrimi=	[HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
 			Format: <io>,<irq>,<nodeID>
 
+	arm64.no32bit_el0 [ARM64] Unconditionally disable the execution of
+			32 bit applications.
+
 	arm64.nobti	[ARM64] Unconditionally disable Branch Target
 			Identification support
 
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 7ef8de58f7f8..3a39395bd9d3 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -62,6 +62,7 @@ Sphinx\ [#f1]_         2.4.4            sphinx-build --version
 cpio                   any              cpio --version
 GNU tar                1.28             tar --version
 gtags (optional)       6.6.5            gtags --version
+mkimage (optional)     2017.01          mkimage --version
 ====================== ===============  ========================================
 
 .. [#f1] Sphinx is needed only to build the Kernel documentation
@@ -189,6 +190,14 @@ The kernel build requires GNU GLOBAL version 6.6.5 or later to generate
 tag files through ``make gtags``.  This is due to its use of the gtags
 ``-C (--directory)`` flag.
 
+mkimage
+-------
+
+This tool is used when building a Flat Image Tree (FIT), commonly used on ARM
+platforms. The tool is available via the ``u-boot-tools`` package or can be
+built from the U-Boot source code. See the instructions at
+https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
+
 System utilities
 ****************
 
diff --git a/MAINTAINERS b/MAINTAINERS
index aea47e04c3a5..9db17a2fe3b0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3051,6 +3051,13 @@ F:	drivers/mmc/host/sdhci-of-arasan.c
 N:	zynq
 N:	xilinx
 
+ARM64 FIT SUPPORT
+M:	Simon Glass <sjg@chromium.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	arch/arm64/boot/Makefile
+F:	scripts/make_fit.py
+
 ARM64 PORT (AARCH64 ARCHITECTURE)
 M:	Catalin Marinas <catalin.marinas@arm.com>
 M:	Will Deacon <will@kernel.org>
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 0e075d3c546b..b8b1d4f4a572 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -154,6 +154,10 @@ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 # Default target when executing plain make
 boot		:= arch/arm64/boot
 
+BOOT_TARGETS	:= Image vmlinuz.efi image.fit
+
+PHONY += $(BOOT_TARGETS)
+
 ifeq ($(CONFIG_EFI_ZBOOT),)
 KBUILD_IMAGE	:= $(boot)/Image.gz
 else
@@ -162,8 +166,10 @@ endif
 
 all:	$(notdir $(KBUILD_IMAGE))
 
-vmlinuz.efi: Image
-Image vmlinuz.efi: vmlinux
+image.fit: dtbs
+
+vmlinuz.efi image.fit: Image
+$(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 Image.%: Image
@@ -215,6 +221,7 @@ virtconfig:
 define archhelp
   echo  '* Image.gz      - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
   echo  '  Image         - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
+  echo  '  image.fit     - Flat Image Tree (arch/$(ARCH)/boot/image.fit)'
   echo  '  install       - Install uncompressed kernel'
   echo  '  zinstall      - Install compressed kernel'
   echo  '                  Install using (your) ~/bin/installkernel or'
diff --git a/arch/arm64/boot/.gitignore b/arch/arm64/boot/.gitignore
index af5dc61f8b43..abaae9de1bdd 100644
--- a/arch/arm64/boot/.gitignore
+++ b/arch/arm64/boot/.gitignore
@@ -2,3 +2,4 @@
 Image
 Image.gz
 vmlinuz*
+image.fit
diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile
index a5a787371117..607a67a649c4 100644
--- a/arch/arm64/boot/Makefile
+++ b/arch/arm64/boot/Makefile
@@ -16,7 +16,8 @@
 
 OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 
-targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo Image.zst
+targets := Image Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo \
+	Image.zst image.fit
 
 $(obj)/Image: vmlinux FORCE
 	$(call if_changed,objcopy)
@@ -39,6 +40,9 @@ $(obj)/Image.lzo: $(obj)/Image FORCE
 $(obj)/Image.zst: $(obj)/Image FORCE
 	$(call if_changed,zstd)
 
+$(obj)/image.fit: $(obj)/Image $(obj)/dts/dtbs-list FORCE
+	$(call if_changed,fit)
+
 EFI_ZBOOT_PAYLOAD	:= Image
 EFI_ZBOOT_BFD_TARGET	:= elf64-littleaarch64
 EFI_ZBOOT_MACH_TYPE	:= ARM64
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index ab8b396428da..6f9ad2d2bb40 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -50,16 +50,12 @@
 	msr	daif, \flags
 	.endm
 
-	.macro	enable_dbg
-	msr	daifclr, #8
-	.endm
-
 	.macro	disable_step_tsk, flgs, tmp
 	tbz	\flgs, #TIF_SINGLESTEP, 9990f
 	mrs	\tmp, mdscr_el1
 	bic	\tmp, \tmp, #DBG_MDSCR_SS
 	msr	mdscr_el1, \tmp
-	isb	// Synchronise with enable_dbg
+	isb	// Take effect before a subsequent clear of DAIF.D
 9990:
 	.endm
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 52f076afeb96..936389e9aecb 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,7 @@
 #define ARM_CPU_PART_CORTEX_X2		0xD48
 #define ARM_CPU_PART_NEOVERSE_N2	0xD49
 #define ARM_CPU_PART_CORTEX_A78C	0xD4B
+#define ARM_CPU_PART_NEOVERSE_V2	0xD4F
 
 #define APM_CPU_PART_XGENE		0x000
 #define APM_CPU_VAR_POTENZA		0x00
@@ -159,6 +160,7 @@
 #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
 #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
 #define MIDR_CORTEX_A78C	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
+#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 0a7186a93882..d4d7451c2c12 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -5,7 +5,6 @@
 #ifndef __ASM_IRQFLAGS_H
 #define __ASM_IRQFLAGS_H
 
-#include <asm/alternative.h>
 #include <asm/barrier.h>
 #include <asm/ptrace.h>
 #include <asm/sysreg.h>
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 6aafbb789991..4e753908b801 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -15,17 +15,23 @@
 
 #define JUMP_LABEL_NOP_SIZE		AARCH64_INSN_SIZE
 
+#define JUMP_TABLE_ENTRY(key, label)			\
+	".pushsection	__jump_table, \"aw\"\n\t"	\
+	".align		3\n\t"				\
+	".long		1b - ., %l["#label"] - .\n\t"	\
+	".quad		%c0 - .\n\t"			\
+	".popsection\n\t"				\
+	:  :  "i"(key) :  : label
+
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
+	char *k = &((char *)key)[branch];
+
 	asm goto(
 		"1:	nop					\n\t"
-		 "	.pushsection	__jump_table, \"aw\"	\n\t"
-		 "	.align		3			\n\t"
-		 "	.long		1b - ., %l[l_yes] - .	\n\t"
-		 "	.quad		%c0 - .			\n\t"
-		 "	.popsection				\n\t"
-		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
+		JUMP_TABLE_ENTRY(k, l_yes)
+		);
 
 	return false;
 l_yes:
@@ -35,15 +41,11 @@ l_yes:
 static __always_inline bool arch_static_branch_jump(struct static_key * const key,
 						    const bool branch)
 {
+	char *k = &((char *)key)[branch];
 	asm goto(
 		"1:	b		%l[l_yes]		\n\t"
-		 "	.pushsection	__jump_table, \"aw\"	\n\t"
-		 "	.align		3			\n\t"
-		 "	.long		1b - ., %l[l_yes] - .	\n\t"
-		 "	.quad		%c0 - .			\n\t"
-		 "	.popsection				\n\t"
-		 :  :  "i"(&((char *)key)[branch]) :  : l_yes);
-
+		JUMP_TABLE_ENTRY(k, l_yes)
+		);
 	return false;
 l_yes:
 	return true;
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 9e8999592f3a..af3b206fa423 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1036,18 +1036,18 @@
  * Permission Indirection Extension (PIE) permission encodings.
  * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension).
  */
-#define PIE_NONE_O	0x0
-#define PIE_R_O		0x1
-#define PIE_X_O		0x2
-#define PIE_RX_O	0x3
-#define PIE_RW_O	0x5
-#define PIE_RWnX_O	0x6
-#define PIE_RWX_O	0x7
-#define PIE_R		0x8
-#define PIE_GCS		0x9
-#define PIE_RX		0xa
-#define PIE_RW		0xc
-#define PIE_RWX		0xe
+#define PIE_NONE_O	UL(0x0)
+#define PIE_R_O		UL(0x1)
+#define PIE_X_O		UL(0x2)
+#define PIE_RX_O	UL(0x3)
+#define PIE_RW_O	UL(0x5)
+#define PIE_RWnX_O	UL(0x6)
+#define PIE_RWX_O	UL(0x7)
+#define PIE_R		UL(0x8)
+#define PIE_GCS		UL(0x9)
+#define PIE_RX		UL(0xa)
+#define PIE_RW		UL(0xc)
+#define PIE_RWX		UL(0xe)
 
 #define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))
 
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index dba8fcec7f33..e0e7b93c16cc 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -26,6 +26,7 @@
 #include <linux/libfdt.h>
 #include <linux/smp.h>
 #include <linux/serial_core.h>
+#include <linux/suspend.h>
 #include <linux/pgtable.h>
 
 #include <acpi/ghes.h>
@@ -227,6 +228,15 @@ done:
 		if (earlycon_acpi_spcr_enable)
 			early_init_dt_scan_chosen_stdout();
 	} else {
+#ifdef CONFIG_HIBERNATION
+		struct acpi_table_header *facs = NULL;
+		acpi_get_table(ACPI_SIG_FACS, 1, &facs);
+		if (facs) {
+			swsusp_hardware_signature =
+				((struct acpi_table_facs *)facs)->hardware_signature;
+			acpi_put_table(facs);
+		}
+#endif
 		acpi_parse_spcr(earlycon_acpi_spcr_enable, true);
 		if (IS_ENABLED(CONFIG_ACPI_BGRT))
 			acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c
index aad399796e81..48c1aa456af9 100644
--- a/arch/arm64/kernel/pi/idreg-override.c
+++ b/arch/arm64/kernel/pi/idreg-override.c
@@ -108,6 +108,7 @@ static const struct ftr_set_desc pfr0 __prel64_initconst = {
 	.override	= &id_aa64pfr0_override,
 	.fields		= {
 	        FIELD("sve", ID_AA64PFR0_EL1_SVE_SHIFT, pfr0_sve_filter),
+		FIELD("el0", ID_AA64PFR0_EL1_EL0_SHIFT, NULL),
 		{}
 	},
 };
@@ -223,6 +224,7 @@ static const struct {
 	{ "nokaslr",			"arm64_sw.nokaslr=1" },
 	{ "rodata=off",			"arm64_sw.rodataoff=1" },
 	{ "arm64.nolva",		"id_aa64mmfr2.varange=0" },
+	{ "arm64.no32bit_el0",		"id_aa64pfr0.el0=1" },
 };
 
 static int __init parse_hexdigit(const char *p, u64 *v)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 65a052bf741f..a096e2451044 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -298,8 +298,15 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
 	dynamic_scs_init();
 
 	/*
-	 * Unmask SError as soon as possible after initializing earlycon so
-	 * that we can report any SErrors immediately.
+	 * The primary CPU enters the kernel with all DAIF exceptions masked.
+	 *
+	 * We must unmask Debug and SError before preemption or scheduling is
+	 * possible to ensure that these are consistently unmasked across
+	 * threads, and we want to unmask SError as soon as possible after
+	 * initializing earlycon so that we can report any SErrors immediately.
+	 *
+	 * IRQ and FIQ will be unmasked after the root irqchip has been
+	 * detected and initialized.
 	 */
 	local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 4ced34f62dab..31c8b3094dd7 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -264,6 +264,13 @@ asmlinkage notrace void secondary_start_kernel(void)
 	set_cpu_online(cpu, true);
 	complete(&cpu_running);
 
+	/*
+	 * Secondary CPUs enter the kernel with all DAIF exceptions masked.
+	 *
+	 * As with setup_arch() we must unmask Debug and SError exceptions, and
+	 * as the root irqchip has already been detected and initialized we can
+	 * unmask IRQ and FIQ at the same time.
+	 */
 	local_daif_restore(DAIF_PROCCTX);
 
 	/*
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 9d40f3ffd8d2..f4bc6c5bac06 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -135,14 +135,6 @@ SYM_FUNC_START(cpu_do_resume)
 
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
-
-	/*
-	 * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking
-	 * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug
-	 * exception. Mask them until local_daif_restore() in cpu_suspend()
-	 * resets them.
-	 */
-	disable_daif
 	msr	mdscr_el1, x10
 
 	msr	sctlr_el1, x12
@@ -466,8 +458,6 @@ SYM_FUNC_START(__cpu_setup)
 	msr	cpacr_el1, xzr			// Reset cpacr_el1
 	mov	x1, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x1			// access to the DCC from EL0
-	isb					// Unmask debug exceptions now,
-	enable_dbg				// since this is per-cpu
 	reset_pmuserenr_el0 x1			// Disable PMU access from EL0
 	reset_amuserenr_el0 x1			// Disable AMU access from EL0
 
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 44267a92bce5..3c126c6d306b 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -315,23 +315,19 @@ void acpi_tb_parse_fadt(void)
 				       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
 				       NULL, FALSE, TRUE, &acpi_gbl_dsdt_index);
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (!acpi_gbl_reduced_hardware) {
-		if (acpi_gbl_FADT.facs) {
-			acpi_tb_install_standard_table((acpi_physical_address)
-						       acpi_gbl_FADT.facs,
-						       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
-						       NULL, FALSE, TRUE,
-						       &acpi_gbl_facs_index);
-		}
-		if (acpi_gbl_FADT.Xfacs) {
-			acpi_tb_install_standard_table((acpi_physical_address)
-						       acpi_gbl_FADT.Xfacs,
-						       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
-						       NULL, FALSE, TRUE,
-						       &acpi_gbl_xfacs_index);
-		}
+	if (acpi_gbl_FADT.facs) {
+		acpi_tb_install_standard_table((acpi_physical_address)
+					       acpi_gbl_FADT.facs,
+					       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
+					       NULL, FALSE, TRUE,
+					       &acpi_gbl_facs_index);
+	}
+	if (acpi_gbl_FADT.Xfacs) {
+		acpi_tb_install_standard_table((acpi_physical_address)
+					       acpi_gbl_FADT.Xfacs,
+					       ACPI_TABLE_ORIGIN_INTERNAL_PHYSICAL,
+					       NULL, FALSE, TRUE,
+					       &acpi_gbl_xfacs_index);
 	}
 }
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index bb4a56e5673a..15fa68a5ea6e 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -36,12 +36,7 @@ acpi_status acpi_tb_initialize_facs(void)
 {
 	struct acpi_table_facs *facs;
 
-	/* If Hardware Reduced flag is set, there is no FACS */
-
-	if (acpi_gbl_reduced_hardware) {
-		acpi_gbl_FACS = NULL;
-		return (AE_OK);
-	} else if (acpi_gbl_FADT.Xfacs &&
+	if (acpi_gbl_FADT.Xfacs &&
 		   (!acpi_gbl_FADT.facs
 		    || !acpi_gbl_use32_bit_facs_addresses)) {
 		(void)acpi_get_table_by_index(acpi_gbl_xfacs_index,
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 3179747cbd2c..afa1099b6b8e 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -504,6 +504,22 @@ quiet_cmd_uimage = UIMAGE  $@
 			-a $(UIMAGE_LOADADDR) -e $(UIMAGE_ENTRYADDR) \
 			-n '$(UIMAGE_NAME)' -d $< $@
 
+# Flat Image Tree (FIT)
+# This allows for packaging of a kernel and all devicetrees files, using
+# compression.
+# ---------------------------------------------------------------------------
+
+MAKE_FIT := $(srctree)/scripts/make_fit.py
+
+# Use this to override the compression algorithm
+FIT_COMPRESSION ?= gzip
+
+quiet_cmd_fit = FIT     $@
+      cmd_fit = $(MAKE_FIT) -o $@ --arch $(UIMAGE_ARCH) --os linux \
+		--name '$(UIMAGE_NAME)' \
+		$(if $(findstring 1,$(KBUILD_VERBOSE)),-v) \
+		--compress $(FIT_COMPRESSION) -k $< @$(word 2,$^)
+
 # XZ
 # ---------------------------------------------------------------------------
 # Use xzkern to compress the kernel image and xzmisc to compress other things.
diff --git a/scripts/make_fit.py b/scripts/make_fit.py
new file mode 100755
index 000000000000..3de90c5a094b
--- /dev/null
+++ b/scripts/make_fit.py
@@ -0,0 +1,290 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Copyright 2024 Google LLC
+# Written by Simon Glass <sjg@chromium.org>
+#
+
+"""Build a FIT containing a lot of devicetree files
+
+Usage:
+    make_fit.py -A arm64 -n 'Linux-6.6' -O linux
+        -o arch/arm64/boot/image.fit -k /tmp/kern/arch/arm64/boot/image.itk
+        @arch/arm64/boot/dts/dtbs-list -E -c gzip
+
+Creates a FIT containing the supplied kernel and a set of devicetree files,
+either specified individually or listed in a file (with an '@' prefix).
+
+Use -E to generate an external FIT (where the data is placed after the
+FIT data structure). This allows parsing of the data without loading
+the entire FIT.
+
+Use -c to compress the data, using bzip2, gzip, lz4, lzma, lzo and
+zstd algorithms.
+
+The resulting FIT can be booted by bootloaders which support FIT, such
+as U-Boot, Linuxboot, Tianocore, etc.
+
+Note that this tool does not yet support adding a ramdisk / initrd.
+"""
+
+import argparse
+import collections
+import os
+import subprocess
+import sys
+import tempfile
+import time
+
+import libfdt
+
+
+# Tool extension and the name of the command-line tools
+CompTool = collections.namedtuple('CompTool', 'ext,tools')
+
+COMP_TOOLS = {
+    'bzip2': CompTool('.bz2', 'bzip2'),
+    'gzip': CompTool('.gz', 'pigz,gzip'),
+    'lz4': CompTool('.lz4', 'lz4'),
+    'lzma': CompTool('.lzma', 'lzma'),
+    'lzo': CompTool('.lzo', 'lzop'),
+    'zstd': CompTool('.zstd', 'zstd'),
+}
+
+
+def parse_args():
+    """Parse the program ArgumentParser
+
+    Returns:
+        Namespace object containing the arguments
+    """
+    epilog = 'Build a FIT from a directory tree containing .dtb files'
+    parser = argparse.ArgumentParser(epilog=epilog, fromfile_prefix_chars='@')
+    parser.add_argument('-A', '--arch', type=str, required=True,
+          help='Specifies the architecture')
+    parser.add_argument('-c', '--compress', type=str, default='none',
+          help='Specifies the compression')
+    parser.add_argument('-E', '--external', action='store_true',
+          help='Convert the FIT to use external data')
+    parser.add_argument('-n', '--name', type=str, required=True,
+          help='Specifies the name')
+    parser.add_argument('-o', '--output', type=str, required=True,
+          help='Specifies the output file (.fit)')
+    parser.add_argument('-O', '--os', type=str, required=True,
+          help='Specifies the operating system')
+    parser.add_argument('-k', '--kernel', type=str, required=True,
+          help='Specifies the (uncompressed) kernel input file (.itk)')
+    parser.add_argument('-v', '--verbose', action='store_true',
+                        help='Enable verbose output')
+    parser.add_argument('dtbs', type=str, nargs='*',
+          help='Specifies the devicetree files to process')
+
+    return parser.parse_args()
+
+
+def setup_fit(fsw, name):
+    """Make a start on writing the FIT
+
+    Outputs the root properties and the 'images' node
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        name (str): Name of kernel image
+    """
+    fsw.INC_SIZE = 65536
+    fsw.finish_reservemap()
+    fsw.begin_node('')
+    fsw.property_string('description', f'{name} with devicetree set')
+    fsw.property_u32('#address-cells', 1)
+
+    fsw.property_u32('timestamp', int(time.time()))
+    fsw.begin_node('images')
+
+
+def write_kernel(fsw, data, args):
+    """Write out the kernel image
+
+    Writes a kernel node along with the required properties
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        data (bytes): Data to write (possibly compressed)
+        args (Namespace): Contains necessary strings:
+            arch: FIT architecture, e.g. 'arm64'
+            fit_os: Operating Systems, e.g. 'linux'
+            name: Name of OS, e.g. 'Linux-6.6.0-rc7'
+            compress: Compression algorithm to use, e.g. 'gzip'
+    """
+    with fsw.add_node('kernel'):
+        fsw.property_string('description', args.name)
+        fsw.property_string('type', 'kernel_noload')
+        fsw.property_string('arch', args.arch)
+        fsw.property_string('os', args.os)
+        fsw.property_string('compression', args.compress)
+        fsw.property('data', data)
+        fsw.property_u32('load', 0)
+        fsw.property_u32('entry', 0)
+
+
+def finish_fit(fsw, entries):
+    """Finish the FIT ready for use
+
+    Writes the /configurations node and subnodes
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        entries (list of tuple): List of configurations:
+            str: Description of model
+            str: Compatible stringlist
+    """
+    fsw.end_node()
+    seq = 0
+    with fsw.add_node('configurations'):
+        for model, compat in entries:
+            seq += 1
+            with fsw.add_node(f'conf-{seq}'):
+                fsw.property('compatible', bytes(compat))
+                fsw.property_string('description', model)
+                fsw.property_string('fdt', f'fdt-{seq}')
+                fsw.property_string('kernel', 'kernel')
+    fsw.end_node()
+
+
+def compress_data(inf, compress):
+    """Compress data using a selected algorithm
+
+    Args:
+        inf (IOBase): Filename containing the data to compress
+        compress (str): Compression algorithm, e.g. 'gzip'
+
+    Return:
+        bytes: Compressed data
+    """
+    if compress == 'none':
+        return inf.read()
+
+    comp = COMP_TOOLS.get(compress)
+    if not comp:
+        raise ValueError(f"Unknown compression algorithm '{compress}'")
+
+    with tempfile.NamedTemporaryFile() as comp_fname:
+        with open(comp_fname.name, 'wb') as outf:
+            done = False
+            for tool in comp.tools.split(','):
+                try:
+                    subprocess.call([tool, '-c'], stdin=inf, stdout=outf)
+                    done = True
+                    break
+                except FileNotFoundError:
+                    pass
+            if not done:
+                raise ValueError(f'Missing tool(s): {comp.tools}\n')
+            with open(comp_fname.name, 'rb') as compf:
+                comp_data = compf.read()
+    return comp_data
+
+
+def output_dtb(fsw, seq, fname, arch, compress):
+    """Write out a single devicetree to the FIT
+
+    Args:
+        fsw (libfdt.FdtSw): Object to use for writing
+        seq (int): Sequence number (1 for first)
+        fmame (str): Filename containing the DTB
+        arch: FIT architecture, e.g. 'arm64'
+        compress (str): Compressed algorithm, e.g. 'gzip'
+
+    Returns:
+        tuple:
+            str: Model name
+            bytes: Compatible stringlist
+    """
+    with fsw.add_node(f'fdt-{seq}'):
+        # Get the compatible / model information
+        with open(fname, 'rb') as inf:
+            data = inf.read()
+        fdt = libfdt.FdtRo(data)
+        model = fdt.getprop(0, 'model').as_str()
+        compat = fdt.getprop(0, 'compatible')
+
+        fsw.property_string('description', model)
+        fsw.property_string('type', 'flat_dt')
+        fsw.property_string('arch', arch)
+        fsw.property_string('compression', compress)
+        fsw.property('compatible', bytes(compat))
+
+        with open(fname, 'rb') as inf:
+            compressed = compress_data(inf, compress)
+        fsw.property('data', compressed)
+    return model, compat
+
+
+def build_fit(args):
+    """Build the FIT from the provided files and arguments
+
+    Args:
+        args (Namespace): Program arguments
+
+    Returns:
+        tuple:
+            bytes: FIT data
+            int: Number of configurations generated
+            size: Total uncompressed size of data
+    """
+    seq = 0
+    size = 0
+    fsw = libfdt.FdtSw()
+    setup_fit(fsw, args.name)
+    entries = []
+
+    # Handle the kernel
+    with open(args.kernel, 'rb') as inf:
+        comp_data = compress_data(inf, args.compress)
+    size += os.path.getsize(args.kernel)
+    write_kernel(fsw, comp_data, args)
+
+    for fname in args.dtbs:
+        # Ignore overlay (.dtbo) files
+        if os.path.splitext(fname)[1] == '.dtb':
+            seq += 1
+            size += os.path.getsize(fname)
+            model, compat = output_dtb(fsw, seq, fname, args.arch, args.compress)
+            entries.append([model, compat])
+
+    finish_fit(fsw, entries)
+
+    # Include the kernel itself in the returned file count
+    return fsw.as_fdt().as_bytearray(), seq + 1, size
+
+
+def run_make_fit():
+    """Run the tool's main logic"""
+    args = parse_args()
+
+    out_data, count, size = build_fit(args)
+    with open(args.output, 'wb') as outf:
+        outf.write(out_data)
+
+    ext_fit_size = None
+    if args.external:
+        mkimage = os.environ.get('MKIMAGE', 'mkimage')
+        subprocess.check_call([mkimage, '-E', '-F', args.output],
+                              stdout=subprocess.DEVNULL)
+
+        with open(args.output, 'rb') as inf:
+            data = inf.read()
+        ext_fit = libfdt.FdtRo(data)
+        ext_fit_size = ext_fit.totalsize()
+
+    if args.verbose:
+        comp_size = len(out_data)
+        print(f'FIT size {comp_size:#x}/{comp_size / 1024 / 1024:.1f} MB',
+              end='')
+        if ext_fit_size:
+            print(f', header {ext_fit_size:#x}/{ext_fit_size / 1024:.1f} KB',
+                  end='')
+        print(f', {count} files, uncompressed {size / 1024 / 1024:.1f} MB')
+
+
+if __name__ == "__main__":
+    sys.exit(run_make_fit())
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
index ccc13e991376..cd8420e8c3ad 100644
--- a/tools/arch/arm64/include/asm/sysreg.h
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -701,18 +701,18 @@
  * Permission Indirection Extension (PIE) permission encodings.
  * Encodings with the _O suffix, have overlays applied (Permission Overlay Extension).
  */
-#define PIE_NONE_O	0x0
-#define PIE_R_O		0x1
-#define PIE_X_O		0x2
-#define PIE_RX_O	0x3
-#define PIE_RW_O	0x5
-#define PIE_RWnX_O	0x6
-#define PIE_RWX_O	0x7
-#define PIE_R		0x8
-#define PIE_GCS		0x9
-#define PIE_RX		0xa
-#define PIE_RW		0xc
-#define PIE_RWX		0xe
+#define PIE_NONE_O	UL(0x0)
+#define PIE_R_O		UL(0x1)
+#define PIE_X_O		UL(0x2)
+#define PIE_RX_O	UL(0x3)
+#define PIE_RW_O	UL(0x5)
+#define PIE_RWnX_O	UL(0x6)
+#define PIE_RWX_O	UL(0x7)
+#define PIE_R		UL(0x8)
+#define PIE_GCS		UL(0x9)
+#define PIE_RX		UL(0xa)
+#define PIE_RW		UL(0xc)
+#define PIE_RWX		UL(0xe)
 
 #define PIRx_ELx_PERM(idx, perm)	((perm) << ((idx) * 4))