Merge tag 'x86-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core x86 updates from Ingo Molnar: "x86 CPU features support: - Generate the <asm/cpufeaturemasks.h> header based on build config (H. Peter Anvin, Xin Li) - x86 CPUID parsing updates and fixes (Ahmed S. Darwish) - Introduce the 'setcpuid=' boot parameter (Brendan Jackman) - Enable modifying CPU bug flags with '{clear,set}puid=' (Brendan Jackman) - Utilize CPU-type for CPU matching (Pawan Gupta) - Warn about unmet CPU feature dependencies (Sohil Mehta) - Prepare for new Intel Family numbers (Sohil Mehta) Percpu code: - Standardize & reorganize the x86 percpu layout and related cleanups (Brian Gerst) - Convert the stackprotector canary to a regular percpu variable (Brian Gerst) - Add a percpu subsection for cache hot data (Brian Gerst) - Unify __pcpu_op{1,2}_N() macros to __pcpu_op_N() (Uros Bizjak) - Construct __percpu_seg_override from __percpu_seg (Uros Bizjak) MM: - Add support for broadcast TLB invalidation using AMD's INVLPGB instruction (Rik van Riel) - Rework ROX cache to avoid writable copy (Mike Rapoport) - PAT: restore large ROX pages after fragmentation (Kirill A. Shutemov, Mike Rapoport) - Make memremap(MEMREMAP_WB) map memory as encrypted by default (Kirill A. Shutemov) - Robustify page table initialization (Kirill A. Shutemov) - Fix flush_tlb_range() when used for zapping normal PMDs (Jann Horn) - Clear _PAGE_DIRTY for kernel mappings when we clear _PAGE_RW (Matthew Wilcox) KASLR: - x86/kaslr: Reduce KASLR entropy on most x86 systems, to support PCI BAR space beyond the 10TiB region (CONFIG_PCI_P2PDMA=y) (Balbir Singh) CPU bugs: - Implement FineIBT-BHI mitigation (Peter Zijlstra) - speculation: Simplify and make CALL_NOSPEC consistent (Pawan Gupta) - speculation: Add a conditional CS prefix to CALL_NOSPEC (Pawan Gupta) - RFDS: Exclude P-only parts from the RFDS affected list (Pawan Gupta) System calls: - Break up entry/common.c (Brian Gerst) - Move sysctls into arch/x86 (Joel Granados) Intel LAM support updates: (Maciej Wieczor-Retman) - selftests/lam: Move cpu_has_la57() to use cpuinfo flag - selftests/lam: Skip test if LAM is disabled - selftests/lam: Test get_user() LAM pointer handling AMD SMN access updates: - Add SMN offsets to exclusive region access (Mario Limonciello) - Add support for debugfs access to SMN registers (Mario Limonciello) - Have HSMP use SMN through AMD_NODE (Yazen Ghannam) Power management updates: (Patryk Wlazlyn) - Allow calling mwait_play_dead with an arbitrary hint - ACPI/processor_idle: Add FFH state handling - intel_idle: Provide the default enter_dead() handler - Eliminate mwait_play_dead_cpuid_hint() Build system: - Raise the minimum GCC version to 8.1 (Brian Gerst) - Raise the minimum LLVM version to 15.0.0 (Nathan Chancellor) Kconfig: (Arnd Bergmann) - Add cmpxchg8b support back to Geode CPUs - Drop 32-bit "bigsmp" machine support - Rework CONFIG_GENERIC_CPU compiler flags - Drop configuration options for early 64-bit CPUs - Remove CONFIG_HIGHMEM64G support - Drop CONFIG_SWIOTLB for PAE - Drop support for CONFIG_HIGHPTE - Document CONFIG_X86_INTEL_MID as 64-bit-only - Remove old STA2x11 support - Only allow CONFIG_EISA for 32-bit Headers: - Replace __ASSEMBLY__ with __ASSEMBLER__ in UAPI and non-UAPI headers (Thomas Huth) Assembly code & machine code patching: - x86/alternatives: Simplify alternative_call() interface (Josh Poimboeuf) - x86/alternatives: Simplify callthunk patching (Peter Zijlstra) - KVM: VMX: Use named operands in inline asm (Josh Poimboeuf) - x86/hyperv: Use named operands in inline asm (Josh Poimboeuf) - x86/traps: Cleanup and robustify decode_bug() (Peter Zijlstra) - x86/kexec: Merge x86_32 and x86_64 code using macros from <asm/asm.h> (Uros Bizjak) - Use named operands in inline asm (Uros Bizjak) - Improve performance by using asm_inline() for atomic locking instructions (Uros Bizjak) Earlyprintk: - Harden early_serial (Peter Zijlstra) NMI handler: - Add an emergency handler in nmi_desc & use it in nmi_shootdown_cpus() (Waiman Long) Miscellaneous fixes and cleanups: - by Ahmed S. Darwish, Andy Shevchenko, Ard Biesheuvel, Artem Bityutskiy, Borislav Petkov, Brendan Jackman, Brian Gerst, Dan Carpenter, Dr. David Alan Gilbert, H. Peter Anvin, Ingo Molnar, Josh Poimboeuf, Kevin Brodsky, Mike Rapoport, Lukas Bulwahn, Maciej Wieczor-Retman, Max Grobecker, Patryk Wlazlyn, Pawan Gupta, Peter Zijlstra, Philip Redkin, Qasim Ijaz, Rik van Riel, Thomas Gleixner, Thorsten Blum, Tom Lendacky, Tony Luck, Uros Bizjak, Vitaly Kuznetsov, Xin Li, liuye" * tag 'x86-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (211 commits) zstd: Increase DYNAMIC_BMI2 GCC version cutoff from 4.8 to 11.0 to work around compiler segfault x86/asm: Make asm export of __ref_stack_chk_guard unconditional x86/mm: Only do broadcast flush from reclaim if pages were unmapped perf/x86/intel, x86/cpu: Replace Pentium 4 model checks with VFM ones perf/x86/intel, x86/cpu: Simplify Intel PMU initialization x86/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in non-UAPI headers x86/headers: Replace __ASSEMBLY__ with __ASSEMBLER__ in UAPI headers x86/locking/atomic: Improve performance by using asm_inline() for atomic locking instructions x86/asm: Use asm_inline() instead of asm() in clwb() x86/asm: Use CLFLUSHOPT and CLWB mnemonics in <asm/special_insns.h> x86/hweight: Use asm_inline() instead of asm() x86/hweight: Use ASM_CALL_CONSTRAINT in inline asm() x86/hweight: Use named operands in inline asm() x86/stackprotector/64: Only export __ref_stack_chk_guard on CONFIG_SMP x86/head/64: Avoid Clang < 17 stack protector in startup code x86/kexec: Merge x86_32 and x86_64 code using macros from <asm/asm.h> x86/runtime-const: Add the RUNTIME_CONST_PTR assembly macro x86/cpu/intel: Limit the non-architectural constant_tsc model checks x86/mm/pat: Replace Intel x86_model checks with VFM ones x86/cpu/intel: Fix fast string initialization for extended Families ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2025-03-24 22:06:11 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2025-03-24 22:06:11 -0700
commit: e34c38057a131d14e47b4acb461564d9f351b9f7 (patch)
tree: b2a2b707c0c97927493cf85c0418594c06c76f19
parent: 327ecdbc0fda28da3563a34426f63d80384062be (diff)
parent: 1400c87e6cac47eb243f260352c854474d9a9073 (diff)
346 files changed, 5002 insertions, 4671 deletions
diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
index 0585d02b9a6c..ad15417d39f9 100644
--- a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
+++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst
@@ -29,14 +29,6 @@ Below is the list of affected Intel processors [#f1]_:
    RAPTORLAKE_S            06_BFH
    ===================  ============
 
-As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and
-RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as
-vulnerable in Linux because they share the same family/model with an affected
-part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or
-CPUID.HYBRID. This information could be used to distinguish between the
-affected and unaffected parts, but it is deemed not worth adding complexity as
-the reporting is fixed automatically when these parts enumerate RFDS_NO.
-
 Mitigation
 ==========
 Intel released a microcode update that enables software to clear sensitive
diff --git a/Documentation/admin-guide/kdump/kdump.rst b/Documentation/admin-guide/kdump/kdump.rst
index 5376890adbeb..1f7f14c6e184 100644
--- a/Documentation/admin-guide/kdump/kdump.rst
+++ b/Documentation/admin-guide/kdump/kdump.rst
@@ -180,10 +180,6 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
 1) On i386, enable high memory support under "Processor type and
    features"::
 
-	CONFIG_HIGHMEM64G=y
-
-   or::
-
 	CONFIG_HIGHMEM4G
 
 2) With CONFIG_SMP=y, usually nr_cpus=1 need specified on the kernel
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 60f98de36f82..866427da6add 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -416,10 +416,6 @@
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
-			For X86-32, this can also be used to specify an APIC
-			driver name.
-			Format: apic=driver_name
-			Examples: apic=bigsmp
 
 	apic_extnmi=	[APIC,X86,EARLY] External NMI delivery setting
 			Format: { bsp (default) | all | none }
@@ -7679,13 +7675,6 @@
 				16 - SIGBUS faults
 			Example: user_debug=31
 
-	userpte=
-			[X86,EARLY] Flags controlling user PTE allocations.
-
-				nohigh = do not allocate PTE pages in
-					HIGHMEM regardless of setting
-					of CONFIG_HIGHPTE.
-
 	vdso=		[X86,SH,SPARC]
 			On X86_32, this is an alias for vdso32=.  Otherwise:
 
diff --git a/Documentation/arch/x86/usb-legacy-support.rst b/Documentation/arch/x86/usb-legacy-support.rst
index e01c08b7c981..b17bf122270a 100644
--- a/Documentation/arch/x86/usb-legacy-support.rst
+++ b/Documentation/arch/x86/usb-legacy-support.rst
@@ -20,11 +20,7 @@ It has several drawbacks, though:
    features (wheel, extra buttons, touchpad mode) of the real PS/2 mouse may
    not be available.
 
-2) If CONFIG_HIGHMEM64G is enabled, the PS/2 mouse emulation can cause
-   system crashes, because the SMM BIOS is not expecting to be in PAE mode.
-   The Intel E7505 is a typical machine where this happens.
-
-3) If AMD64 64-bit mode is enabled, again system crashes often happen,
+2) If AMD64 64-bit mode is enabled, again system crashes often happen,
    because the SMM BIOS isn't expecting the CPU to be in 64-bit mode.  The
    BIOS manufacturers only test with Windows, and Windows doesn't do 64-bit
    yet.
@@ -38,11 +34,6 @@ Problem 1)
   compiled-in, too.
 
 Problem 2)
-  can currently only be solved by either disabling HIGHMEM64G
-  in the kernel config or USB Legacy support in the BIOS. A BIOS update
-  could help, but so far no such update exists.
-
-Problem 3)
   is usually fixed by a BIOS update. Check the board
   manufacturers web site. If an update is not available, disable USB
   Legacy support in the BIOS. If this alone doesn't help, try also adding
diff --git a/Makefile b/Makefile
index 8b6764d44a61..d138b17b8840 100644
--- a/Makefile
+++ b/Makefile
@@ -1014,6 +1014,9 @@ CC_FLAGS_CFI	:= -fsanitize=kcfi
 ifdef CONFIG_CFI_ICALL_NORMALIZE_INTEGERS
 	CC_FLAGS_CFI	+= -fsanitize-cfi-icall-experimental-normalize-integers
 endif
+ifdef CONFIG_FINEIBT_BHI
+	CC_FLAGS_CFI	+= -fsanitize-kcfi-arity
+endif
 ifdef CONFIG_RUST
 	# Always pass -Zsanitizer-cfi-normalize-integers as CONFIG_RUST selects
 	# CONFIG_CFI_ICALL_NORMALIZE_INTEGERS.
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1815748f5d2a..bae5edf348ef 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -381,7 +381,7 @@ void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
 void iounmap(volatile void __iomem *io_addr);
 #define iounmap iounmap
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size);
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
 #define arch_memremap_wb arch_memremap_wb
 
 /*
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 89f1c97f3079..748698e91a4b 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -436,7 +436,7 @@ void __arm_iomem_set_ro(void __iomem *ptr, size_t size)
 	set_memory_ro((unsigned long)ptr, PAGE_ALIGN(size) / PAGE_SIZE);
 }
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (__force void *)arch_ioremap_caller(phys_addr, size,
 						   MT_MEMORY_RW,
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 1a8f6914ee59..d638cc87807e 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -248,7 +248,7 @@ void __iomem *pci_remap_cfgspace(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL_GPL(pci_remap_cfgspace);
 #endif
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (void *)phys_addr;
 }
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1c5c641075d2..0257f4aa7ff4 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -136,7 +136,7 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw())
 #include <asm-generic/io.h>
 
 #ifdef CONFIG_MMU
-#define arch_memremap_wb(addr, size)	\
+#define arch_memremap_wb(addr, size, flags)	\
 	((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL))
 #endif
 
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 79ea97d4797e..8be91974e786 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -440,25 +440,24 @@ void __init arch_cpu_finalize_init(void)
 	os_check_bugs();
 }
 
-void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void apply_seal_endbr(s32 *start, s32 *end)
 {
 }
 
-void apply_retpolines(s32 *start, s32 *end, struct module *mod)
+void apply_retpolines(s32 *start, s32 *end)
 {
 }
 
-void apply_returns(s32 *start, s32 *end, struct module *mod)
+void apply_returns(s32 *start, s32 *end)
 {
 }
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 }
 
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			struct module *mod)
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0e27ebd7e36a..98bd4935280c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ config X86
 	select ARCH_HAS_DMA_OPS			if GART_IOMMU || XEN
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_EXECMEM_ROX		if X86_64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -132,7 +133,7 @@ config X86
 	select ARCH_SUPPORTS_AUTOFDO_CLANG
 	select ARCH_SUPPORTS_PROPELLER_CLANG    if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CMPXCHG64
+	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CX8
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
@@ -232,7 +233,7 @@ config X86
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_EISA
+	select HAVE_EISA			if X86_32
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
@@ -277,7 +278,7 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select MMU_GATHER_RCU_TABLE_FREE	if PARAVIRT
+	select MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_MERGE_VMAS
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
@@ -285,7 +286,7 @@ config X86
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_SETUP_PER_CPU_AREA
 	select HAVE_SOFTIRQ_ON_OWN_STACK
-	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
+	select HAVE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if HAVE_OBJTOOL
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_OBJTOOL
@@ -426,15 +427,6 @@ config PGTABLE_LEVELS
 	default 3 if X86_PAE
 	default 2
 
-config CC_HAS_SANE_STACKPROTECTOR
-	bool
-	default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) $(CLANG_FLAGS)) if 64BIT
-	default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC) $(CLANG_FLAGS))
-	help
-	  We have to make sure stack protector is unconditionally disabled if
-	  the compiler produces broken code or if it does not let us control
-	  the segment on 32-bit kernels.
-
 menu "Processor type and features"
 
 config SMP
@@ -530,12 +522,6 @@ config X86_FRED
 	  ring transitions and exception/interrupt handling if the
 	  system supports it.
 
-config X86_BIGSMP
-	bool "Support for big SMP systems with more than 8 CPUs"
-	depends on SMP && X86_32
-	help
-	  This option is needed for the systems that have more than 8 CPUs.
-
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
 	default y
@@ -553,13 +539,12 @@ config X86_EXTENDED_PLATFORM
 		AMD Elan
 		RDC R-321x SoC
 		SGI 320/540 (Visual Workstation)
-		STA2X11-based (e.g. Northville)
-		Moorestown MID devices
 
 	  64-bit platforms (CONFIG_64BIT=y):
 		Numascale NumaChip
 		ScaleMP vSMP
 		SGI Ultraviolet
+		Merrifield/Moorefield MID devices
 
 	  If you have one of these systems, or if you want to build a
 	  generic distribution kernel, say Y here - otherwise say N.
@@ -604,8 +589,31 @@ config X86_UV
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
 
-# Following is an alphabetically sorted list of 32 bit extended platforms
-# Please maintain the alphabetic order if and when there are additions
+config X86_INTEL_MID
+	bool "Intel Z34xx/Z35xx MID platform support"
+	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
+	depends on PCI
+	depends on X86_64 || (EXPERT && PCI_GOANY)
+	depends on X86_IO_APIC
+	select I2C
+	select DW_APB_TIMER
+	select INTEL_SCU_PCI
+	help
+	  Select to build a kernel capable of supporting 64-bit Intel MID
+	  (Mobile Internet Device) platform systems which do not have
+	  the PCI legacy interfaces.
+
+	  The only supported devices are the 22nm Merrified (Z34xx)
+	  and Moorefield (Z35xx) SoC used in the Intel Edison board and
+	  a small number of Android devices such as the Asus Zenfone 2,
+	  Asus FonePad 8 and Dell Venue 7.
+
+	  If you are building for a PC class system or non-MID tablet
+	  SoCs like Bay Trail (Z36xx/Z37xx), say N here.
+
+	  Intel MID platforms are based on an Intel processor and chipset which
+	  consume less power than most of the x86 derivatives.
 
 config X86_GOLDFISH
 	bool "Goldfish (Virtual Platform)"
@@ -615,6 +623,9 @@ config X86_GOLDFISH
 	  for Android development. Unless you are building for the Android
 	  Goldfish emulator say N here.
 
+# Following is an alphabetically sorted list of 32 bit extended platforms
+# Please maintain the alphabetic order if and when there are additions
+
 config X86_INTEL_CE
 	bool "CE4100 TV platform"
 	depends on PCI
@@ -630,24 +641,6 @@ config X86_INTEL_CE
 	  This option compiles in support for the CE4100 SOC for settop
 	  boxes and media devices.
 
-config X86_INTEL_MID
-	bool "Intel MID platform support"
-	depends on X86_EXTENDED_PLATFORM
-	depends on X86_PLATFORM_DEVICES
-	depends on PCI
-	depends on X86_64 || (PCI_GOANY && X86_32)
-	depends on X86_IO_APIC
-	select I2C
-	select DW_APB_TIMER
-	select INTEL_SCU_PCI
-	help
-	  Select to build a kernel capable of supporting Intel MID (Mobile
-	  Internet Device) platform systems which do not have the PCI legacy
-	  interfaces. If you are building for a PC class system say N here.
-
-	  Intel MID platforms are based on an Intel processor and chipset which
-	  consume less power than most of the x86 derivatives.
-
 config X86_INTEL_QUARK
 	bool "Intel Quark platform support"
 	depends on X86_32
@@ -729,18 +722,6 @@ config X86_RDC321X
 	  as R-8610-(G).
 	  If you don't have one of these chips, you should say N here.
 
-config X86_32_NON_STANDARD
-	bool "Support non-standard 32-bit SMP architectures"
-	depends on X86_32 && SMP
-	depends on X86_EXTENDED_PLATFORM
-	help
-	  This option compiles in the bigsmp and STA2X11 default
-	  subarchitectures.  It is intended for a generic binary
-	  kernel. If you select them all, kernel will probe it one by
-	  one and will fallback to default.
-
-# Alphabetically sorted list of Non standard 32 bit platforms
-
 config X86_SUPPORTS_MEMORY_FAILURE
 	def_bool y
 	# MCE code calls memory_failure():
@@ -750,19 +731,6 @@ config X86_SUPPORTS_MEMORY_FAILURE
 	depends on X86_64 || !SPARSEMEM
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 
-config STA2X11
-	bool "STA2X11 Companion Chip Support"
-	depends on X86_32_NON_STANDARD && PCI
-	select SWIOTLB
-	select MFD_STA2X11
-	select GPIOLIB
-	help
-	  This adds support for boards based on the STA2X11 IO-Hub,
-	  a.k.a. "ConneXt". The chip is used in place of the standard
-	  PC chipset, so all "standard" peripherals are missing. If this
-	  option is selected the kernel will still be able to boot on
-	  standard PC machines.
-
 config X86_32_IRIS
 	tristate "Eurobraille/Iris poweroff module"
 	depends on X86_32
@@ -1012,8 +980,7 @@ config NR_CPUS_RANGE_BEGIN
 config NR_CPUS_RANGE_END
 	int
 	depends on X86_32
-	default   64 if  SMP &&  X86_BIGSMP
-	default    8 if  SMP && !X86_BIGSMP
+	default    8 if  SMP
 	default    1 if !SMP
 
 config NR_CPUS_RANGE_END
@@ -1026,7 +993,6 @@ config NR_CPUS_RANGE_END
 config NR_CPUS_DEFAULT
 	int
 	depends on X86_32
-	default   32 if  X86_BIGSMP
 	default    8 if  SMP
 	default    1 if !SMP
 
@@ -1102,7 +1068,7 @@ config UP_LATE_INIT
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors" if !PCI_MSI
 	default PCI_MSI
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP
 	help
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -1127,7 +1093,7 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
+	depends on X86_64 || SMP || X86_UP_APIC || PCI_MSI
 	select IRQ_DOMAIN_HIERARCHY
 
 config ACPI_MADT_WAKEUP
@@ -1396,15 +1362,11 @@ config X86_CPUID
 	  with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
 	  /dev/cpu/31/cpuid.
 
-choice
-	prompt "High Memory Support"
-	default HIGHMEM4G
+config HIGHMEM4G
+	bool "High Memory Support"
 	depends on X86_32
-
-config NOHIGHMEM
-	bool "off"
 	help
-	  Linux can use up to 64 Gigabytes of physical memory on x86 systems.
+	  Linux can use up to 4 Gigabytes of physical memory on x86 systems.
 	  However, the address space of 32-bit x86 processors is only 4
 	  Gigabytes large. That means that, if you have a large amount of
 	  physical memory, not all of it can be "permanently mapped" by the
@@ -1420,38 +1382,9 @@ config NOHIGHMEM
 	  possible.
 
 	  If the machine has between 1 and 4 Gigabytes physical RAM, then
-	  answer "4GB" here.
-
-	  If more than 4 Gigabytes is used then answer "64GB" here. This
-	  selection turns Intel PAE (Physical Address Extension) mode on.
-	  PAE implements 3-level paging on IA32 processors. PAE is fully
-	  supported by Linux, PAE mode is implemented on all recent Intel
-	  processors (Pentium Pro and better). NOTE: If you say "64GB" here,
-	  then the kernel will not boot on CPUs that don't support PAE!
-
-	  The actual amount of total physical memory will either be
-	  auto detected or can be forced by using a kernel command line option
-	  such as "mem=256M". (Try "man bootparam" or see the documentation of
-	  your boot loader (lilo or loadlin) about how to pass options to the
-	  kernel at boot time.)
-
-	  If unsure, say "off".
-
-config HIGHMEM4G
-	bool "4GB"
-	help
-	  Select this if you have a 32-bit processor and between 1 and 4
-	  gigabytes of physical RAM.
-
-config HIGHMEM64G
-	bool "64GB"
-	depends on X86_HAVE_PAE
-	select X86_PAE
-	help
-	  Select this if you have a 32-bit processor and more than 4
-	  gigabytes of physical RAM.
+	  answer "Y" here.
 
-endchoice
+	  If unsure, say N.
 
 choice
 	prompt "Memory split" if EXPERT
@@ -1497,14 +1430,12 @@ config PAGE_OFFSET
 	depends on X86_32
 
 config HIGHMEM
-	def_bool y
-	depends on X86_32 && (HIGHMEM64G || HIGHMEM4G)
+	def_bool HIGHMEM4G
 
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && X86_HAVE_PAE
 	select PHYS_ADDR_T_64BIT
-	select SWIOTLB
 	help
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It
@@ -1574,8 +1505,7 @@ config AMD_MEM_ENCRYPT
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
-	default y if X86_BIGSMP
+	depends on X86_64
 	select USE_PERCPU_NUMA_NODE_ID
 	select OF_NUMA if OF
 	help
@@ -1588,9 +1518,6 @@ config NUMA
 	  For 64-bit this is recommended if the system is Intel Core i7
 	  (or later), AMD Opteron, or EM64T NUMA.
 
-	  For 32-bit this is only needed if you boot a 32-bit
-	  kernel on a 64-bit NUMA platform.
-
 	  Otherwise, you should say N.
 
 config AMD_NUMA
@@ -1629,7 +1556,7 @@ config ARCH_FLATMEM_ENABLE
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
-	depends on X86_64 || NUMA || X86_32 || X86_32_NON_STANDARD
+	depends on X86_64 || NUMA || X86_32
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
@@ -1675,15 +1602,6 @@ config X86_PMEM_LEGACY
 
 	  Say Y if unsure.
 
-config HIGHPTE
-	bool "Allocate 3rd-level pagetables from highmem"
-	depends on HIGHMEM
-	help
-	  The VM uses one page table entry for each page of physical memory.
-	  For systems with a lot of RAM, this can be wasteful of precious
-	  low memory.  Setting this option will put user-space page table
-	  entries in high memory.
-
 config X86_CHECK_BIOS_CORRUPTION
 	bool "Check for low memory corruption"
 	help
@@ -2451,18 +2369,20 @@ config CC_HAS_NAMED_AS
 	def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null)
 	depends on CC_IS_GCC
 
+#
+# -fsanitize=kernel-address (KASAN) and -fsanitize=thread (KCSAN)
+# are incompatible with named address spaces with GCC < 13.3
+# (see GCC PR sanitizer/111736 and also PR sanitizer/115172).
+#
+
 config CC_HAS_NAMED_AS_FIXED_SANITIZERS
-	def_bool CC_IS_GCC && GCC_VERSION >= 130300
+	def_bool y
+	depends on !(KASAN || KCSAN) || GCC_VERSION >= 130300
+	depends on !(UBSAN_BOOL && KASAN) || GCC_VERSION >= 140200
 
 config USE_X86_SEG_SUPPORT
-	def_bool y
-	depends on CC_HAS_NAMED_AS
-	#
-	# -fsanitize=kernel-address (KASAN) and -fsanitize=thread
-	# (KCSAN) are incompatible with named address spaces with
-	# GCC < 13.3 - see GCC PR sanitizer/111736.
-	#
-	depends on !(KASAN || KCSAN) || CC_HAS_NAMED_AS_FIXED_SANITIZERS
+	def_bool CC_HAS_NAMED_AS
+	depends on CC_HAS_NAMED_AS_FIXED_SANITIZERS
 
 config CC_HAS_SLS
 	def_bool $(cc-option,-mharden-sls=all)
@@ -2473,6 +2393,10 @@ config CC_HAS_RETURN_THUNK
 config CC_HAS_ENTRY_PADDING
 	def_bool $(cc-option,-fpatchable-function-entry=16,16)
 
+config CC_HAS_KCFI_ARITY
+	def_bool $(cc-option,-fsanitize=kcfi -fsanitize-kcfi-arity)
+	depends on CC_IS_CLANG && !RUST
+
 config FUNCTION_PADDING_CFI
 	int
 	default 59 if FUNCTION_ALIGNMENT_64B
@@ -2498,6 +2422,10 @@ config FINEIBT
 	depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE
 	select CALL_PADDING
 
+config FINEIBT_BHI
+	def_bool y
+	depends on FINEIBT && CC_HAS_KCFI_ARITY
+
 config HAVE_CALL_THUNKS
 	def_bool y
 	depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL
@@ -3202,4 +3130,6 @@ config HAVE_ATOMIC_IOMAP
 
 source "arch/x86/kvm/Kconfig"
 
+source "arch/x86/Kconfig.cpufeatures"
+
 source "arch/x86/Kconfig.assembler"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2a7279d80460..753b8763abae 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Put here option for CPU selection and depending optimization
 choice
-	prompt "Processor family"
-	default M686 if X86_32
-	default GENERIC_CPU if X86_64
+	prompt "x86-32 Processor family"
+	depends on X86_32
+	default M686
 	help
 	  This is the processor type of your CPU. This information is
 	  used for optimizing purposes. In order to compile a kernel
@@ -31,7 +31,6 @@ choice
 	  - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron.
 	  - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D).
 	  - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird).
-	  - "Opteron/Athlon64/Hammer/K8" for all K8 and newer AMD CPUs.
 	  - "Crusoe" for the Transmeta Crusoe series.
 	  - "Efficeon" for the Transmeta Efficeon series.
 	  - "Winchip-C6" for original IDT Winchip.
@@ -42,13 +41,10 @@ choice
 	  - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
 	  - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
 	  - "VIA C7" for VIA C7.
-	  - "Intel P4" for the Pentium 4/Netburst microarchitecture.
-	  - "Core 2/newer Xeon" for all core2 and newer Intel CPUs.
 	  - "Intel Atom" for the Atom-microarchitecture CPUs.
-	  - "Generic-x86-64" for a kernel which runs on any x86-64 CPU.
 
 	  See each option's help text for additional details. If you don't know
-	  what to do, choose "486".
+	  what to do, choose "Pentium-Pro".
 
 config M486SX
 	bool "486SX"
@@ -114,11 +110,11 @@ config MPENTIUMIII
 	  extensions.
 
 config MPENTIUMM
-	bool "Pentium M"
+	bool "Pentium M/Pentium Dual Core/Core Solo/Core Duo"
 	depends on X86_32
 	help
 	  Select this for Intel Pentium M (not Pentium-4 M)
-	  notebook chips.
+	  "Merom" Core Solo/Duo notebook chips
 
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
@@ -139,22 +135,10 @@ config MPENTIUM4
 		-Mobile Pentium 4
 		-Mobile Pentium 4 M
 		-Extreme Edition (Gallatin)
-		-Prescott
-		-Prescott 2M
-		-Cedar Mill
-		-Presler
-		-Smithfiled
 	    Xeons (Intel Xeon, Xeon MP, Xeon LV, Xeon MV) corename:
 		-Foster
 		-Prestonia
 		-Gallatin
-		-Nocona
-		-Irwindale
-		-Cranford
-		-Potomac
-		-Paxville
-		-Dempsey
-
 
 config MK6
 	bool "K6/K6-II/K6-III"
@@ -172,13 +156,6 @@ config MK7
 	  some extended instructions, and passes appropriate optimization
 	  flags to GCC.
 
-config MK8
-	bool "Opteron/Athlon64/Hammer/K8"
-	help
-	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
-	  Enables use of some extended instructions, and passes appropriate
-	  optimization flags to GCC.
-
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
@@ -258,42 +235,14 @@ config MVIAC7
 	  Select this for a VIA C7.  Selecting this uses the correct cache
 	  shift and tells gcc to treat the CPU as a 686.
 
-config MPSC
-	bool "Intel P4 / older Netburst based Xeon"
-	depends on X86_64
-	help
-	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
-	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
-	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
-	  Netburst core and shouldn't use this option. You can distinguish them
-	  using the cpu family field
-	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
-
-config MCORE2
-	bool "Core 2/newer Xeon"
-	help
-
-	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
-	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
-	  (not a typo)
-
 config MATOM
 	bool "Intel Atom"
 	help
-
 	  Select this for the Intel Atom platform. Intel Atom CPUs have an
 	  in-order pipelining architecture and thus can benefit from
 	  accordingly optimized code. Use a recent GCC with specific Atom
 	  support in order to fully benefit from selecting this option.
 
-config GENERIC_CPU
-	bool "Generic-x86-64"
-	depends on X86_64
-	help
-	  Generic x86-64 CPU.
-	  Run equally well on all x86-64 CPUs.
-
 endchoice
 
 config X86_GENERIC
@@ -317,8 +266,8 @@ config X86_INTERNODE_CACHE_SHIFT
 
 config X86_L1_CACHE_SHIFT
 	int
-	default "7" if MPENTIUM4 || MPSC
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "7" if MPENTIUM4
+	default "6" if MK7 || MPENTIUMM || MATOM || MVIAC7 || X86_GENERIC || X86_64
 	default "4" if MELAN || M486SX || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
@@ -336,51 +285,35 @@ config X86_ALIGNMENT_16
 
 config X86_INTEL_USERCOPY
 	def_bool y
-	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK7 || MEFFICEON
 
 config X86_USE_PPRO_CHECKSUM
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
-
-#
-# P6_NOPs are a relatively minor optimization that require a family >=
-# 6 processor, except that it is broken on certain VIA chips.
-# Furthermore, AMD chips prefer a totally different sequence of NOPs
-# (which work on all CPUs).  In addition, it looks like Virtual PC
-# does not understand them.
-#
-# As a result, disallow these if we're not compiling for X86_64 (these
-# NOPs do work on all x86-64 capable chips); the list of processors in
-# the right-hand clause are the cores that benefit from this optimization.
-#
-config X86_P6_NOP
-	def_bool y
-	depends on X86_64
-	depends on (MCORE2 || MPENTIUM4 || MPSC)
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MATOM
 
 config X86_TSC
 	def_bool y
-	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
+	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MATOM) || X86_64
 
 config X86_HAVE_PAE
 	def_bool y
-	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC7 || MCORE2 || MATOM || X86_64
+	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC7 || MATOM || X86_64
 
-config X86_CMPXCHG64
+config X86_CX8
 	def_bool y
-	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7
+	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7 || MGEODEGX1 || MGEODE_LX
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || MATOM || MGEODE_LX || X86_64)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
-	default "5" if X86_32 && X86_CMPXCHG64
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MK7)
+	default "5" if X86_32 && X86_CX8
 	default "4"
 
 config X86_DEBUGCTLMSR
@@ -401,6 +334,10 @@ menuconfig PROCESSOR_SELECT
 	  This lets you choose what x86 vendor support code your kernel
 	  will include.
 
+config BROADCAST_TLB_FLUSH
+	def_bool y
+	depends on CPU_SUP_AMD && 64BIT
+
 config CPU_SUP_INTEL
 	default y
 	bool "Support Intel processors" if PROCESSOR_SELECT
diff --git a/arch/x86/Kconfig.cpufeatures b/arch/x86/Kconfig.cpufeatures
new file mode 100644
index 000000000000..e12d5b7e39a2
--- /dev/null
+++ b/arch/x86/Kconfig.cpufeatures
@@ -0,0 +1,201 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# x86 feature bits (see arch/x86/include/asm/cpufeatures.h) that are
+# either REQUIRED to be enabled, or DISABLED (always ignored) for this
+# particular compile-time configuration.  The tests for these features
+# are turned into compile-time constants via the generated
+# <asm/cpufeaturemasks.h>.
+#
+# The naming of these variables *must* match asm/cpufeatures.h, e.g.,
+#     X86_FEATURE_ALWAYS <==> X86_REQUIRED_FEATURE_ALWAYS
+#     X86_FEATURE_FRED   <==> X86_DISABLED_FEATURE_FRED
+#
+# And these REQUIRED and DISABLED config options are manipulated in an
+# AWK script as the following example:
+#
+#                          +----------------------+
+#                          |    X86_FRED = y ?    |
+#                          +----------------------+
+#                              /             \
+#                           Y /               \ N
+#  +-------------------------------------+   +-------------------------------+
+#  | X86_DISABLED_FEATURE_FRED undefined |   | X86_DISABLED_FEATURE_FRED = y |
+#  +-------------------------------------+   +-------------------------------+
+#                                                        |
+#                                                        |
+#     +-------------------------------------------+      |
+#     | X86_FEATURE_FRED: feature word 12, bit 17 | ---->|
+#     +-------------------------------------------+      |
+#                                                        |
+#                                                        |
+#                                     +-------------------------------+
+#                                     | set bit 17 of DISABLED_MASK12 |
+#                                     +-------------------------------+
+#
+
+config X86_REQUIRED_FEATURE_ALWAYS
+	def_bool y
+
+config X86_REQUIRED_FEATURE_NOPL
+	def_bool y
+	depends on X86_64 || X86_P6_NOP
+
+config X86_REQUIRED_FEATURE_CX8
+	def_bool y
+	depends on X86_CX8
+
+# this should be set for all -march=.. options where the compiler
+# generates cmov.
+config X86_REQUIRED_FEATURE_CMOV
+	def_bool y
+	depends on X86_CMOV
+
+# this should be set for all -march= options where the compiler
+# generates movbe.
+config X86_REQUIRED_FEATURE_MOVBE
+	def_bool y
+	depends on MATOM
+
+config X86_REQUIRED_FEATURE_CPUID
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_UP
+	def_bool y
+	depends on !SMP
+
+config X86_REQUIRED_FEATURE_FPU
+	def_bool y
+	depends on !MATH_EMULATION
+
+config X86_REQUIRED_FEATURE_PAE
+	def_bool y
+	depends on X86_64 || X86_PAE
+
+config X86_REQUIRED_FEATURE_PSE
+	def_bool y
+	depends on X86_64 && !PARAVIRT_XXL
+
+config X86_REQUIRED_FEATURE_PGE
+	def_bool y
+	depends on X86_64 && !PARAVIRT_XXL
+
+config X86_REQUIRED_FEATURE_MSR
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_FXSR
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_XMM
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_XMM2
+	def_bool y
+	depends on X86_64
+
+config X86_REQUIRED_FEATURE_LM
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_UMIP
+	def_bool y
+	depends on !X86_UMIP
+
+config X86_DISABLED_FEATURE_VME
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_K6_MTRR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_CYRIX_ARR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_CENTAUR_MCR
+	def_bool y
+	depends on X86_64
+
+config X86_DISABLED_FEATURE_PCID
+	def_bool y
+	depends on !X86_64
+
+config X86_DISABLED_FEATURE_PKU
+	def_bool y
+	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
+
+config X86_DISABLED_FEATURE_OSPKE
+	def_bool y
+	depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
+
+config X86_DISABLED_FEATURE_LA57
+	def_bool y
+	depends on !X86_5LEVEL
+
+config X86_DISABLED_FEATURE_PTI
+	def_bool y
+	depends on !MITIGATION_PAGE_TABLE_ISOLATION
+
+config X86_DISABLED_FEATURE_RETPOLINE
+	def_bool y
+	depends on !MITIGATION_RETPOLINE
+
+config X86_DISABLED_FEATURE_RETPOLINE_LFENCE
+	def_bool y
+	depends on !MITIGATION_RETPOLINE
+
+config X86_DISABLED_FEATURE_RETHUNK
+	def_bool y
+	depends on !MITIGATION_RETHUNK
+
+config X86_DISABLED_FEATURE_UNRET
+	def_bool y
+	depends on !MITIGATION_UNRET_ENTRY
+
+config X86_DISABLED_FEATURE_CALL_DEPTH
+	def_bool y
+	depends on !MITIGATION_CALL_DEPTH_TRACKING
+
+config X86_DISABLED_FEATURE_LAM
+	def_bool y
+	depends on !ADDRESS_MASKING
+
+config X86_DISABLED_FEATURE_ENQCMD
+	def_bool y
+	depends on !INTEL_IOMMU_SVM
+
+config X86_DISABLED_FEATURE_SGX
+	def_bool y
+	depends on !X86_SGX
+
+config X86_DISABLED_FEATURE_XENPV
+	def_bool y
+	depends on !XEN_PV
+
+config X86_DISABLED_FEATURE_TDX_GUEST
+	def_bool y
+	depends on !INTEL_TDX_GUEST
+
+config X86_DISABLED_FEATURE_USER_SHSTK
+	def_bool y
+	depends on !X86_USER_SHADOW_STACK
+
+config X86_DISABLED_FEATURE_IBT
+	def_bool y
+	depends on !X86_KERNEL_IBT
+
+config X86_DISABLED_FEATURE_FRED
+	def_bool y
+	depends on !X86_FRED
+
+config X86_DISABLED_FEATURE_SEV_SNP
+	def_bool y
+	depends on !KVM_AMD_SEV
+
+config X86_DISABLED_FEATURE_INVLPGB
+	def_bool y
+	depends on !BROADCAST_TLB_FLUSH
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 3ba7e185924e..0fc7e8fd1a2e 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -142,14 +142,7 @@ ifeq ($(CONFIG_X86_32),y)
         KBUILD_CFLAGS += -ffreestanding
     endif
 
-    ifeq ($(CONFIG_STACKPROTECTOR),y)
-        ifeq ($(CONFIG_SMP),y)
-            KBUILD_CFLAGS += -mstack-protector-guard-reg=fs \
-                             -mstack-protector-guard-symbol=__ref_stack_chk_guard
-        else
-            KBUILD_CFLAGS += -mstack-protector-guard=global
-        endif
-    endif
+        percpu_seg := fs
 else
         BITS := 64
         UTS_MACHINE := x86_64
@@ -180,25 +173,24 @@ else
 	# Use -mskip-rax-setup if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
 
-        # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
-        cflags-$(CONFIG_MK8)		+= -march=k8
-        cflags-$(CONFIG_MPSC)		+= -march=nocona
-        cflags-$(CONFIG_MCORE2)		+= -march=core2
-        cflags-$(CONFIG_MATOM)		+= -march=atom
-        cflags-$(CONFIG_GENERIC_CPU)	+= -mtune=generic
-        KBUILD_CFLAGS += $(cflags-y)
-
-        rustflags-$(CONFIG_MK8)		+= -Ctarget-cpu=k8
-        rustflags-$(CONFIG_MPSC)	+= -Ctarget-cpu=nocona
-        rustflags-$(CONFIG_MCORE2)	+= -Ctarget-cpu=core2
-        rustflags-$(CONFIG_MATOM)	+= -Ctarget-cpu=atom
-        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ztune-cpu=generic
-        KBUILD_RUSTFLAGS += $(rustflags-y)
+        KBUILD_CFLAGS += -march=x86-64 -mtune=generic
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
         KBUILD_RUSTFLAGS += -Cno-redzone=y
         KBUILD_RUSTFLAGS += -Ccode-model=kernel
+
+        percpu_seg := gs
+endif
+
+ifeq ($(CONFIG_STACKPROTECTOR),y)
+    ifeq ($(CONFIG_SMP),y)
+	KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg)
+	KBUILD_CFLAGS += -mstack-protector-guard-symbol=__ref_stack_chk_guard
+    else
+	KBUILD_CFLAGS += -mstack-protector-guard=global
+    endif
 endif
 
 #
@@ -279,6 +271,21 @@ archheaders:
 	$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
 
 ###
+# <asm/cpufeaturemasks.h> header generation
+
+cpufeaturemasks.hdr := arch/x86/include/generated/asm/cpufeaturemasks.h
+cpufeaturemasks.awk := $(srctree)/arch/x86/tools/cpufeaturemasks.awk
+cpufeatures_hdr := $(srctree)/arch/x86/include/asm/cpufeatures.h
+targets += $(cpufeaturemasks.hdr)
+quiet_cmd_gen_featuremasks = GEN     $@
+      cmd_gen_featuremasks = $(AWK) -f $(cpufeaturemasks.awk) $(cpufeatures_hdr) $(KCONFIG_CONFIG) > $@
+
+$(cpufeaturemasks.hdr): $(cpufeaturemasks.awk) $(cpufeatures_hdr) $(KCONFIG_CONFIG) FORCE
+	$(shell mkdir -p $(dir $@))
+	$(call if_changed,gen_featuremasks)
+archprepare: $(cpufeaturemasks.hdr)
+
+###
 # Kernel objects
 
 libs-y  += arch/x86/lib/
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 94834c4b5e5e..af7de9a42752 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -24,7 +24,6 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # Please note, that patches that add -march=athlon-xp and friends are pointless.
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
-cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
 cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
 cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
@@ -32,9 +31,7 @@ cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
-cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
-cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
-	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
+cflags-$(CONFIG_MATOM)		+= -march=atom
 
 # AMD Elan support
 cflags-$(CONFIG_MELAN)		+= -march=i486
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 0f24f7ebec9b..38f17a1e1e36 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -16,7 +16,7 @@
 
 #define STACK_SIZE	1024	/* Minimum number of bytes for stack */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stdarg.h>
 #include <linux/types.h>
@@ -327,6 +327,6 @@ void probe_cards(int unsafe);
 /* video-vesa.c */
 void vesa_store_edid(void);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* BOOT_BOOT_H */
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0d37420cad02..1cdcd4aaf395 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -235,7 +235,7 @@ static void handle_relocations(void *output, unsigned long output_len,
 
 	/*
 	 * Process relocations: 32 bit relocations first then 64 bit after.
-	 * Three sets of binary relocations are added to the end of the kernel
+	 * Two sets of binary relocations are added to the end of the kernel
 	 * before compression. Each relocation table entry is the kernel
 	 * address of the location which needs to be updated stored as a
 	 * 32-bit value which is sign extended to 64 bits.
@@ -245,8 +245,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 	 * kernel bits...
 	 * 0 - zero terminator for 64 bit relocations
 	 * 64 bit relocation repeated
-	 * 0 - zero terminator for inverse 32 bit relocations
-	 * 32 bit inverse relocation repeated
 	 * 0 - zero terminator for 32 bit relocations
 	 * 32 bit relocation repeated
 	 *
@@ -263,16 +261,6 @@ static void handle_relocations(void *output, unsigned long output_len,
 		*(uint32_t *)ptr += delta;
 	}
 #ifdef CONFIG_X86_64
-	while (*--reloc) {
-		long extended = *reloc;
-		extended += map;
-
-		ptr = (unsigned long)extended;
-		if (ptr < min_addr || ptr > max_addr)
-			error("inverse 32-bit relocation outside of kernel!\n");
-
-		*(int32_t *)ptr -= delta;
-	}
 	for (reloc--; *reloc; reloc--) {
 		long extended = *reloc;
 		extended += map;
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 0aae4d4ed615..f82de8de5dc6 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -22,10 +22,11 @@
 # include "boot.h"
 #endif
 #include <linux/types.h>
+#include <asm/cpufeaturemasks.h>
 #include <asm/intel-family.h>
 #include <asm/processor-flags.h>
-#include <asm/required-features.h>
 #include <asm/msr-index.h>
+
 #include "string.h"
 #include "msr.h"
 
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index d75237ba7ce9..0cabdacb2a2f 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -3,7 +3,6 @@
 #include "bitops.h"
 
 #include <asm/processor-flags.h>
-#include <asm/required-features.h>
 #include <asm/msr-index.h>
 #include "cpuflags.h"
 
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index da0ccc5de538..22d730b227e3 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -12,8 +12,6 @@
 
 #include <stdio.h>
 
-#include "../include/asm/required-features.h"
-#include "../include/asm/disabled-features.h"
 #include "../include/asm/cpufeatures.h"
 #include "../include/asm/vmxfeatures.h"
 #include "../kernel/cpu/capflags.c"
@@ -23,6 +21,7 @@ int main(void)
 	int i, j;
 	const char *str;
 
+	printf("#include <asm/cpufeaturemasks.h>\n\n");
 	printf("static const char x86_cap_strs[] =\n");
 
 	for (i = 0; i < NCAPINTS; i++) {
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
index 581296255b39..d5d091e03bd3 100644
--- a/arch/x86/configs/xen.config
+++ b/arch/x86/configs/xen.config
@@ -1,6 +1,4 @@
 # global x86 required specific stuff
-# On 32-bit HIGHMEM4G is not allowed
-CONFIG_HIGHMEM64G=y
 CONFIG_64BIT=y
 
 # These enable us to allow some of the
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index eb153eff9331..b37881bb9f15 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -17,6 +17,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/frame.h>
 
 #define STATE1	%xmm0
@@ -1071,6 +1072,7 @@ SYM_FUNC_END(_aesni_inc)
  *		      size_t len, u8 *iv)
  */
 SYM_FUNC_START(aesni_ctr_enc)
+	ANNOTATE_NOENDBR
 	FRAME_BEGIN
 	cmp $16, LEN
 	jb .Lctr_enc_just_ret
diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
index 646477a13e11..1dfef28c1266 100644
--- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S
@@ -16,6 +16,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
@@ -882,7 +883,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16)
 	jmp .Ldec_max24;
 SYM_FUNC_END(__camellia_dec_blk16)
 
-SYM_FUNC_START(camellia_ecb_enc_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_enc_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -907,7 +908,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way)
 	RET;
 SYM_FUNC_END(camellia_ecb_enc_16way)
 
-SYM_FUNC_START(camellia_ecb_dec_16way)
+SYM_TYPED_FUNC_START(camellia_ecb_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
@@ -937,7 +938,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way)
 	RET;
 SYM_FUNC_END(camellia_ecb_dec_16way)
 
-SYM_FUNC_START(camellia_cbc_dec_16way)
+SYM_TYPED_FUNC_START(camellia_cbc_dec_16way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst (16 blocks)
diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
index a0eb94e53b1b..b1c9b9450555 100644
--- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 
 #define CAMELLIA_TABLE_BYTE_LEN 272
diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S
index 816b6bb8bded..824cb94de6c2 100644
--- a/arch/x86/crypto/camellia-x86_64-asm_64.S
+++ b/arch/x86/crypto/camellia-x86_64-asm_64.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "camellia-x86_64-asm_64.S"
 .text
@@ -177,7 +178,7 @@
 	bswapq				RAB0; \
 	movq RAB0,			4*2(RIO);
 
-SYM_FUNC_START(__camellia_enc_blk)
+SYM_TYPED_FUNC_START(__camellia_enc_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -224,7 +225,7 @@ SYM_FUNC_START(__camellia_enc_blk)
 	RET;
 SYM_FUNC_END(__camellia_enc_blk)
 
-SYM_FUNC_START(camellia_dec_blk)
+SYM_TYPED_FUNC_START(camellia_dec_blk)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -411,7 +412,7 @@ SYM_FUNC_END(camellia_dec_blk)
 		bswapq				RAB1; \
 		movq RAB1,			12*2(RIO);
 
-SYM_FUNC_START(__camellia_enc_blk_2way)
+SYM_TYPED_FUNC_START(__camellia_enc_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -460,7 +461,7 @@ SYM_FUNC_START(__camellia_enc_blk_2way)
 	RET;
 SYM_FUNC_END(__camellia_enc_blk_2way)
 
-SYM_FUNC_START(camellia_dec_blk_2way)
+SYM_TYPED_FUNC_START(camellia_dec_blk_2way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
index 97e283621851..84e47f7f6188 100644
--- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -9,6 +9,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/frame.h>
 #include "glue_helper-asm-avx.S"
 
@@ -656,7 +657,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx)
 	RET;
 SYM_FUNC_END(__serpent_dec_blk8_avx)
 
-SYM_FUNC_START(serpent_ecb_enc_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_enc_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -674,7 +675,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx)
 	RET;
 SYM_FUNC_END(serpent_ecb_enc_8way_avx)
 
-SYM_FUNC_START(serpent_ecb_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_ecb_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -692,7 +693,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx)
 	RET;
 SYM_FUNC_END(serpent_ecb_dec_8way_avx)
 
-SYM_FUNC_START(serpent_cbc_dec_8way_avx)
+SYM_TYPED_FUNC_START(serpent_cbc_dec_8way_avx)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
index d2288bf38a8a..071e90e7f0d8 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S
@@ -6,6 +6,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 
 .file "twofish-x86_64-asm-3way.S"
 .text
@@ -220,7 +221,7 @@
 	rorq $32,			RAB2; \
 	outunpack3(mov, RIO, 2, RAB, 2);
 
-SYM_FUNC_START(__twofish_enc_blk_3way)
+SYM_TYPED_FUNC_START(__twofish_enc_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
@@ -269,7 +270,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way)
 	RET;
 SYM_FUNC_END(__twofish_enc_blk_3way)
 
-SYM_FUNC_START(twofish_dec_blk_3way)
+SYM_TYPED_FUNC_START(twofish_dec_blk_3way)
 	/* input:
 	 *	%rdi: ctx, CTX
 	 *	%rsi: dst
diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S
index 775af290cd19..e08b4ba07b93 100644
--- a/arch/x86/crypto/twofish-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-x86_64-asm_64.S
@@ -8,6 +8,7 @@
 .text
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm-offsets.h>
 
 #define a_offset	0
@@ -202,7 +203,7 @@
 	xor	%r8d,		d ## D;\
 	ror	$1,		d ## D;
 
-SYM_FUNC_START(twofish_enc_blk)
+SYM_TYPED_FUNC_START(twofish_enc_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
@@ -255,7 +256,7 @@ SYM_FUNC_START(twofish_enc_blk)
 	RET
 SYM_FUNC_END(twofish_enc_blk)
 
-SYM_FUNC_START(twofish_dec_blk)
+SYM_TYPED_FUNC_START(twofish_dec_blk)
 	pushq    R1
 
 	/* %rdi contains the ctx address */
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index ce1cc1622385..72cae8e0ce85 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -7,12 +7,13 @@ KASAN_SANITIZE := n
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
 
-CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_syscall_32.o		+= -fno-stack-protector
+CFLAGS_syscall_64.o		+= -fno-stack-protector
 
 obj-y				:= entry.o entry_$(BITS).o syscall_$(BITS).o
-obj-y				+= common.o
 
 obj-y				+= vdso/
 obj-y				+= vsyscall/
@@ -23,4 +24,3 @@ CFLAGS_REMOVE_entry_fred.o	+= -pg $(CC_FLAGS_FTRACE)
 obj-$(CONFIG_X86_FRED)		+= entry_64_fred.o entry_fred.o
 
 obj-$(CONFIG_IA32_EMULATION)	+= entry_64_compat.o syscall_32.o
-obj-$(CONFIG_X86_X32_ABI)	+= syscall_x32.o
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index ea81770629ee..cb0911c5dc5d 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -431,6 +431,7 @@ For 32-bit we have the following conventions - kernel is built with
 /* rdi:	arg1 ... normal C conventions. rax is saved/restored. */
 .macro THUNK name, func
 SYM_FUNC_START(\name)
+	ANNOTATE_NOENDBR
 	pushq %rbp
 	movq %rsp, %rbp
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
deleted file mode 100644
index 14db5b85114c..000000000000
--- a/arch/x86/entry/common.c
+++ /dev/null
@@ -1,524 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * common.c - C code for kernel entry and exit
- * Copyright (c) 2015 Andrew Lutomirski
- *
- * Based on asm and ptrace code by many authors.  The code here originated
- * in ptrace.c and signal.c.
- */
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-#include <linux/entry-common.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/ptrace.h>
-#include <linux/export.h>
-#include <linux/nospec.h>
-#include <linux/syscalls.h>
-#include <linux/uaccess.h>
-#include <linux/init.h>
-
-#ifdef CONFIG_XEN_PV
-#include <xen/xen-ops.h>
-#include <xen/events.h>
-#endif
-
-#include <asm/apic.h>
-#include <asm/desc.h>
-#include <asm/traps.h>
-#include <asm/vdso.h>
-#include <asm/cpufeature.h>
-#include <asm/fpu/api.h>
-#include <asm/nospec-branch.h>
-#include <asm/io_bitmap.h>
-#include <asm/syscall.h>
-#include <asm/irq_stack.h>
-
-#ifdef CONFIG_X86_64
-
-static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
-{
-	/*
-	 * Convert negative numbers to very high and thus out of range
-	 * numbers for comparisons.
-	 */
-	unsigned int unr = nr;
-
-	if (likely(unr < NR_syscalls)) {
-		unr = array_index_nospec(unr, NR_syscalls);
-		regs->ax = x64_sys_call(regs, unr);
-		return true;
-	}
-	return false;
-}
-
-static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
-{
-	/*
-	 * Adjust the starting offset of the table, and convert numbers
-	 * < __X32_SYSCALL_BIT to very high and thus out of range
-	 * numbers for comparisons.
-	 */
-	unsigned int xnr = nr - __X32_SYSCALL_BIT;
-
-	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
-		xnr = array_index_nospec(xnr, X32_NR_syscalls);
-		regs->ax = x32_sys_call(regs, xnr);
-		return true;
-	}
-	return false;
-}
-
-/* Returns true to return using SYSRET, or false to use IRET */
-__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
-{
-	add_random_kstack_offset();
-	nr = syscall_enter_from_user_mode(regs, nr);
-
-	instrumentation_begin();
-
-	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
-		/* Invalid system call, but still a system call. */
-		regs->ax = __x64_sys_ni_syscall(regs);
-	}
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-
-	/*
-	 * Check that the register state is valid for using SYSRET to exit
-	 * to userspace.  Otherwise use the slower but fully capable IRET
-	 * exit path.
-	 */
-
-	/* XEN PV guests always use the IRET path */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
-		return false;
-
-	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
-	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
-		return false;
-
-	/* CS and SS must match the values set in MSR_STAR */
-	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
-		return false;
-
-	/*
-	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
-	 * in kernel space.  This essentially lets the user take over
-	 * the kernel, since userspace controls RSP.
-	 *
-	 * TASK_SIZE_MAX covers all user-accessible addresses other than
-	 * the deprecated vsyscall page.
-	 */
-	if (unlikely(regs->ip >= TASK_SIZE_MAX))
-		return false;
-
-	/*
-	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
-	 * restoring TF results in a trap from userspace immediately after
-	 * SYSRET.
-	 */
-	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
-		return false;
-
-	/* Use SYSRET to exit to userspace */
-	return true;
-}
-#endif
-
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
-static __always_inline int syscall_32_enter(struct pt_regs *regs)
-{
-	if (IS_ENABLED(CONFIG_IA32_EMULATION))
-		current_thread_info()->status |= TS_COMPAT;
-
-	return (int)regs->orig_ax;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
-
-static int ia32_emulation_override_cmdline(char *arg)
-{
-	return kstrtobool(arg, &__ia32_enabled);
-}
-early_param("ia32_emulation", ia32_emulation_override_cmdline);
-#endif
-
-/*
- * Invoke a 32-bit syscall.  Called with IRQs on in CT_STATE_KERNEL.
- */
-static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
-{
-	/*
-	 * Convert negative numbers to very high and thus out of range
-	 * numbers for comparisons.
-	 */
-	unsigned int unr = nr;
-
-	if (likely(unr < IA32_NR_syscalls)) {
-		unr = array_index_nospec(unr, IA32_NR_syscalls);
-		regs->ax = ia32_sys_call(regs, unr);
-	} else if (nr != -1) {
-		regs->ax = __ia32_sys_ni_syscall(regs);
-	}
-}
-
-#ifdef CONFIG_IA32_EMULATION
-static __always_inline bool int80_is_external(void)
-{
-	const unsigned int offs = (0x80 / 32) * 0x10;
-	const u32 bit = BIT(0x80 % 32);
-
-	/* The local APIC on XENPV guests is fake */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
-		return false;
-
-	/*
-	 * If vector 0x80 is set in the APIC ISR then this is an external
-	 * interrupt. Either from broken hardware or injected by a VMM.
-	 *
-	 * Note: In guest mode this is only valid for secure guests where
-	 * the secure module fully controls the vAPIC exposed to the guest.
-	 */
-	return apic_read(APIC_ISR + offs) & bit;
-}
-
-/**
- * do_int80_emulation - 32-bit legacy syscall C entry from asm
- * @regs: syscall arguments in struct pt_args on the stack.
- *
- * This entry point can be used by 32-bit and 64-bit programs to perform
- * 32-bit system calls.  Instances of INT $0x80 can be found inline in
- * various programs and libraries.  It is also used by the vDSO's
- * __kernel_vsyscall fallback for hardware that doesn't support a faster
- * entry method.  Restarted 32-bit system calls also fall back to INT
- * $0x80 regardless of what instruction was originally used to do the
- * system call.
- *
- * This is considered a slow path.  It is not used by most libc
- * implementations on modern hardware except during process startup.
- *
- * The arguments for the INT $0x80 based syscall are on stack in the
- * pt_regs structure:
- *   eax:				system call number
- *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
- */
-__visible noinstr void do_int80_emulation(struct pt_regs *regs)
-{
-	int nr;
-
-	/* Kernel does not use INT $0x80! */
-	if (unlikely(!user_mode(regs))) {
-		irqentry_enter(regs);
-		instrumentation_begin();
-		panic("Unexpected external interrupt 0x80\n");
-	}
-
-	/*
-	 * Establish kernel context for instrumentation, including for
-	 * int80_is_external() below which calls into the APIC driver.
-	 * Identical for soft and external interrupts.
-	 */
-	enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	add_random_kstack_offset();
-
-	/* Validate that this is a soft interrupt to the extent possible */
-	if (unlikely(int80_is_external()))
-		panic("Unexpected external interrupt 0x80\n");
-
-	/*
-	 * The low level idtentry code pushed -1 into regs::orig_ax
-	 * and regs::ax contains the syscall number.
-	 *
-	 * User tracing code (ptrace or signal handlers) might assume
-	 * that the regs::orig_ax contains a 32-bit number on invoking
-	 * a 32-bit syscall.
-	 *
-	 * Establish the syscall convention by saving the 32bit truncated
-	 * syscall number in regs::orig_ax and by invalidating regs::ax.
-	 */
-	regs->orig_ax = regs->ax & GENMASK(31, 0);
-	regs->ax = -ENOSYS;
-
-	nr = syscall_32_enter(regs);
-
-	local_irq_enable();
-	nr = syscall_enter_from_user_mode_work(regs, nr);
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-}
-
-#ifdef CONFIG_X86_FRED
-/*
- * A FRED-specific INT80 handler is warranted for the follwing reasons:
- *
- * 1) As INT instructions and hardware interrupts are separate event
- *    types, FRED does not preclude the use of vector 0x80 for external
- *    interrupts. As a result, the FRED setup code does not reserve
- *    vector 0x80 and calling int80_is_external() is not merely
- *    suboptimal but actively incorrect: it could cause a system call
- *    to be incorrectly ignored.
- *
- * 2) It is called only for handling vector 0x80 of event type
- *    EVENT_TYPE_SWINT and will never be called to handle any external
- *    interrupt (event type EVENT_TYPE_EXTINT).
- *
- * 3) FRED has separate entry flows depending on if the event came from
- *    user space or kernel space, and because the kernel does not use
- *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
- *    falls through to fred_bad_type() if the event type is
- *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
- *    an INT insn, it can only be from a user level.
- *
- * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
- *    likely take a different approach if it is ever needed: it
- *    probably belongs in either fred_intx()/ fred_other() or
- *    asm_fred_entrypoint_user(), depending on if this ought to be done
- *    for all entries from userspace or only system
- *    calls.
- *
- * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
- */
-DEFINE_FREDENTRY_RAW(int80_emulation)
-{
-	int nr;
-
-	enter_from_user_mode(regs);
-
-	instrumentation_begin();
-	add_random_kstack_offset();
-
-	/*
-	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
-	 * syscall number.
-	 *
-	 * User tracing code (ptrace or signal handlers) might assume
-	 * that the regs::orig_ax contains a 32-bit number on invoking
-	 * a 32-bit syscall.
-	 *
-	 * Establish the syscall convention by saving the 32bit truncated
-	 * syscall number in regs::orig_ax and by invalidating regs::ax.
-	 */
-	regs->orig_ax = regs->ax & GENMASK(31, 0);
-	regs->ax = -ENOSYS;
-
-	nr = syscall_32_enter(regs);
-
-	local_irq_enable();
-	nr = syscall_enter_from_user_mode_work(regs, nr);
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-}
-#endif
-#else /* CONFIG_IA32_EMULATION */
-
-/* Handles int $0x80 on a 32bit kernel */
-__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
-{
-	int nr = syscall_32_enter(regs);
-
-	add_random_kstack_offset();
-	/*
-	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
-	 * orig_ax, the int return value truncates it. This matches
-	 * the semantics of syscall_get_nr().
-	 */
-	nr = syscall_enter_from_user_mode(regs, nr);
-	instrumentation_begin();
-
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-}
-#endif /* !CONFIG_IA32_EMULATION */
-
-static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
-{
-	int nr = syscall_32_enter(regs);
-	int res;
-
-	add_random_kstack_offset();
-	/*
-	 * This cannot use syscall_enter_from_user_mode() as it has to
-	 * fetch EBP before invoking any of the syscall entry work
-	 * functions.
-	 */
-	syscall_enter_from_user_mode_prepare(regs);
-
-	instrumentation_begin();
-	/* Fetch EBP from where the vDSO stashed it. */
-	if (IS_ENABLED(CONFIG_X86_64)) {
-		/*
-		 * Micro-optimization: the pointer we're following is
-		 * explicitly 32 bits, so it can't be out of range.
-		 */
-		res = __get_user(*(u32 *)&regs->bp,
-			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
-	} else {
-		res = get_user(*(u32 *)&regs->bp,
-		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
-	}
-
-	if (res) {
-		/* User code screwed up. */
-		regs->ax = -EFAULT;
-
-		local_irq_disable();
-		instrumentation_end();
-		irqentry_exit_to_user_mode(regs);
-		return false;
-	}
-
-	nr = syscall_enter_from_user_mode_work(regs, nr);
-
-	/* Now this is just like a normal syscall. */
-	do_syscall_32_irqs_on(regs, nr);
-
-	instrumentation_end();
-	syscall_exit_to_user_mode(regs);
-	return true;
-}
-
-/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
-__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
-{
-	/*
-	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
-	 * convention.  Adjust regs so it looks like we entered using int80.
-	 */
-	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
-					vdso_image_32.sym_int80_landing_pad;
-
-	/*
-	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
-	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
-	 * Fix it up.
-	 */
-	regs->ip = landing_pad;
-
-	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
-	if (!__do_fast_syscall_32(regs))
-		return false;
-
-	/*
-	 * Check that the register state is valid for using SYSRETL/SYSEXIT
-	 * to exit to userspace.  Otherwise use the slower but fully capable
-	 * IRET exit path.
-	 */
-
-	/* XEN PV guests always use the IRET path */
-	if (cpu_feature_enabled(X86_FEATURE_XENPV))
-		return false;
-
-	/* EIP must point to the VDSO landing pad */
-	if (unlikely(regs->ip != landing_pad))
-		return false;
-
-	/* CS and SS must match the values set in MSR_STAR */
-	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
-		return false;
-
-	/* If the TF, RF, or VM flags are set, use IRET */
-	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
-		return false;
-
-	/* Use SYSRETL/SYSEXIT to exit to userspace */
-	return true;
-}
-
-/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
-__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
-{
-	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
-	regs->sp = regs->bp;
-
-	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
-	regs->flags |= X86_EFLAGS_IF;
-
-	return do_fast_syscall_32(regs);
-}
-#endif
-
-SYSCALL_DEFINE0(ni_syscall)
-{
-	return -ENOSYS;
-}
-
-#ifdef CONFIG_XEN_PV
-#ifndef CONFIG_PREEMPTION
-/*
- * Some hypercalls issued by the toolstack can take many 10s of
- * seconds. Allow tasks running hypercalls via the privcmd driver to
- * be voluntarily preempted even if full kernel preemption is
- * disabled.
- *
- * Such preemptible hypercalls are bracketed by
- * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
- * calls.
- */
-DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
-EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
-
-/*
- * In case of scheduling the flag must be cleared and restored after
- * returning from schedule as the task might move to a different CPU.
- */
-static __always_inline bool get_and_clear_inhcall(void)
-{
-	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);
-
-	__this_cpu_write(xen_in_preemptible_hcall, false);
-	return inhcall;
-}
-
-static __always_inline void restore_inhcall(bool inhcall)
-{
-	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
-}
-#else
-static __always_inline bool get_and_clear_inhcall(void) { return false; }
-static __always_inline void restore_inhcall(bool inhcall) { }
-#endif
-
-static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
-{
-	struct pt_regs *old_regs = set_irq_regs(regs);
-
-	inc_irq_stat(irq_hv_callback_count);
-
-	xen_evtchn_do_upcall();
-
-	set_irq_regs(old_regs);
-}
-
-__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
-{
-	irqentry_state_t state = irqentry_enter(regs);
-	bool inhcall;
-
-	instrumentation_begin();
-	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
-
-	inhcall = get_and_clear_inhcall();
-	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
-		irqentry_exit_cond_resched();
-		instrumentation_end();
-		restore_inhcall(inhcall);
-	} else {
-		instrumentation_end();
-		irqentry_exit(regs, state);
-	}
-}
-#endif /* CONFIG_XEN_PV */
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9ecc..d3caa31240ed 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -5,6 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/segment.h>
@@ -17,6 +18,7 @@
 .pushsection .noinstr.text, "ax"
 
 SYM_FUNC_START(entry_ibpb)
+	ANNOTATE_NOENDBR
 	movl	$MSR_IA32_PRED_CMD, %ecx
 	movl	$PRED_CMD_IBPB, %eax
 	xorl	%edx, %edx
@@ -52,7 +54,6 @@ EXPORT_SYMBOL_GPL(mds_verw_sel);
 
 THUNK warn_thunk_thunk, __warn_thunk
 
-#ifndef CONFIG_X86_64
 /*
  * Clang's implementation of TLS stack cookies requires the variable in
  * question to be a TLS variable. If the variable happens to be defined as an
@@ -63,7 +64,6 @@ THUNK warn_thunk_thunk, __warn_thunk
  * entirely in the C code, and use an alias emitted by the linker script
  * instead.
  */
-#ifdef CONFIG_STACKPROTECTOR
+#if defined(CONFIG_STACKPROTECTOR) && defined(CONFIG_SMP)
 EXPORT_SYMBOL(__ref_stack_chk_guard);
 #endif
-#endif
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 20be5758c2d2..92c0b4a94e0a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1153,7 +1153,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 * is using the thread stack right now, so it's safe for us to use it.
 	 */
 	movl	%esp, %ebx
-	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esp
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	exc_nmi
 	movl	%ebx, %esp
 
@@ -1217,7 +1217,7 @@ SYM_CODE_START(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movl	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esi
+	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esi
 	leal	-TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
 
 	call	make_task_dead
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93c..f40bdf97d390 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -92,7 +92,7 @@ SYM_CODE_START(entry_SYSCALL_64)
 	/* tss.sp2 is scratch space. */
 	movq	%rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
@@ -175,6 +175,7 @@ SYM_CODE_END(entry_SYSCALL_64)
  */
 .pushsection .text, "ax"
 SYM_FUNC_START(__switch_to_asm)
+	ANNOTATE_NOENDBR
 	/*
 	 * Save callee-saved registers
 	 * This must match the order in inactive_task_frame
@@ -192,7 +193,7 @@ SYM_FUNC_START(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
+	movq	%rbx, PER_CPU_VAR(__stack_chk_guard)
 #endif
 
 	/*
@@ -742,6 +743,7 @@ _ASM_NOKPROBE(common_interrupt_return)
  * Is in entry.text as it shouldn't be instrumented.
  */
 SYM_FUNC_START(asm_load_gs_index)
+	ANNOTATE_NOENDBR
 	FRAME_BEGIN
 	swapgs
 .Lgs_change:
@@ -1166,7 +1168,7 @@ SYM_CODE_START(asm_exc_nmi)
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
 	pushq	5*8(%rdx)	/* pt_regs->ss */
 	pushq	4*8(%rdx)	/* pt_regs->rsp */
@@ -1484,7 +1486,7 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
 	/* Prevent any naive code from trying to unwind to our caller. */
 	xorl	%ebp, %ebp
 
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rax
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rax
 	leaq	-PTREGS_SIZE(%rax), %rsp
 	UNWIND_HINT_REGS
 
@@ -1526,6 +1528,7 @@ SYM_CODE_END(rewind_stack_and_make_dead)
  * refactored in the future if needed.
  */
 SYM_FUNC_START(clear_bhb_loop)
+	ANNOTATE_NOENDBR
 	push	%rbp
 	mov	%rsp, %rbp
 	movl	$5, %ecx
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index ed0a5f2dc129..a45e1125fc6c 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -57,7 +57,7 @@ SYM_CODE_START(entry_SYSENTER_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	popq	%rax
 
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS		/* pt_regs->ss */
@@ -193,7 +193,7 @@ SYM_CODE_START(entry_SYSCALL_compat)
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
 
 	/* Switch to the kernel stack */
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S
index a02bc6f3d2e6..29c5c32c16c3 100644
--- a/arch/x86/entry/entry_64_fred.S
+++ b/arch/x86/entry/entry_64_fred.S
@@ -58,6 +58,7 @@ SYM_CODE_END(asm_fred_entrypoint_kernel)
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 SYM_FUNC_START(asm_fred_entry_from_kvm)
+	ANNOTATE_NOENDBR
 	push %rbp
 	mov %rsp, %rbp
 
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cc9950d7104..2b15ea17bb7c 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -1,10 +1,16 @@
-// SPDX-License-Identifier: GPL-2.0
-/* System call table for i386. */
+// SPDX-License-Identifier: GPL-2.0-only
+/* 32-bit system call dispatch */
 
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
+#include <linux/entry-common.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+#include <asm/apic.h>
+#include <asm/traps.h>
+#include <asm/cpufeature.h>
 #include <asm/syscall.h>
 
 #ifdef CONFIG_IA32_EMULATION
@@ -41,4 +47,324 @@ long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
 	#include <asm/syscalls_32.h>
 	default: return __ia32_sys_ni_syscall(regs);
 	}
-};
+}
+
+static __always_inline int syscall_32_enter(struct pt_regs *regs)
+{
+	if (IS_ENABLED(CONFIG_IA32_EMULATION))
+		current_thread_info()->status |= TS_COMPAT;
+
+	return (int)regs->orig_ax;
+}
+
+#ifdef CONFIG_IA32_EMULATION
+bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
+
+static int __init ia32_emulation_override_cmdline(char *arg)
+{
+	return kstrtobool(arg, &__ia32_enabled);
+}
+early_param("ia32_emulation", ia32_emulation_override_cmdline);
+#endif
+
+/*
+ * Invoke a 32-bit syscall.  Called with IRQs on in CT_STATE_KERNEL.
+ */
+static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Convert negative numbers to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int unr = nr;
+
+	if (likely(unr < IA32_NR_syscalls)) {
+		unr = array_index_nospec(unr, IA32_NR_syscalls);
+		regs->ax = ia32_sys_call(regs, unr);
+	} else if (nr != -1) {
+		regs->ax = __ia32_sys_ni_syscall(regs);
+	}
+}
+
+#ifdef CONFIG_IA32_EMULATION
+static __always_inline bool int80_is_external(void)
+{
+	const unsigned int offs = (0x80 / 32) * 0x10;
+	const u32 bit = BIT(0x80 % 32);
+
+	/* The local APIC on XENPV guests is fake */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/*
+	 * If vector 0x80 is set in the APIC ISR then this is an external
+	 * interrupt. Either from broken hardware or injected by a VMM.
+	 *
+	 * Note: In guest mode this is only valid for secure guests where
+	 * the secure module fully controls the vAPIC exposed to the guest.
+	 */
+	return apic_read(APIC_ISR + offs) & bit;
+}
+
+/**
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls.  Instances of INT $0x80 can be found inline in
+ * various programs and libraries.  It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method.  Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path.  It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * The arguments for the INT $0x80 based syscall are on stack in the
+ * pt_regs structure:
+ *   eax:				system call number
+ *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
+ */
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
+{
+	int nr;
+
+	/* Kernel does not use INT $0x80! */
+	if (unlikely(!user_mode(regs))) {
+		irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Unexpected external interrupt 0x80\n");
+	}
+
+	/*
+	 * Establish kernel context for instrumentation, including for
+	 * int80_is_external() below which calls into the APIC driver.
+	 * Identical for soft and external interrupts.
+	 */
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/* Validate that this is a soft interrupt to the extent possible */
+	if (unlikely(int80_is_external()))
+		panic("Unexpected external interrupt 0x80\n");
+
+	/*
+	 * The low level idtentry code pushed -1 into regs::orig_ax
+	 * and regs::ax contains the syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+
+#ifdef CONFIG_X86_FRED
+/*
+ * A FRED-specific INT80 handler is warranted for the follwing reasons:
+ *
+ * 1) As INT instructions and hardware interrupts are separate event
+ *    types, FRED does not preclude the use of vector 0x80 for external
+ *    interrupts. As a result, the FRED setup code does not reserve
+ *    vector 0x80 and calling int80_is_external() is not merely
+ *    suboptimal but actively incorrect: it could cause a system call
+ *    to be incorrectly ignored.
+ *
+ * 2) It is called only for handling vector 0x80 of event type
+ *    EVENT_TYPE_SWINT and will never be called to handle any external
+ *    interrupt (event type EVENT_TYPE_EXTINT).
+ *
+ * 3) FRED has separate entry flows depending on if the event came from
+ *    user space or kernel space, and because the kernel does not use
+ *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
+ *    falls through to fred_bad_type() if the event type is
+ *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
+ *    an INT insn, it can only be from a user level.
+ *
+ * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
+ *    likely take a different approach if it is ever needed: it
+ *    probably belongs in either fred_intx()/ fred_other() or
+ *    asm_fred_entrypoint_user(), depending on if this ought to be done
+ *    for all entries from userspace or only system
+ *    calls.
+ *
+ * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
+ */
+DEFINE_FREDENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/*
+	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
+	 * syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#endif /* CONFIG_X86_FRED */
+
+#else /* CONFIG_IA32_EMULATION */
+
+/* Handles int $0x80 on a 32bit kernel */
+__visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
+{
+	int nr = syscall_32_enter(regs);
+
+	add_random_kstack_offset();
+	/*
+	 * Subtlety here: if ptrace pokes something larger than 2^31-1 into
+	 * orig_ax, the int return value truncates it. This matches
+	 * the semantics of syscall_get_nr().
+	 */
+	nr = syscall_enter_from_user_mode(regs, nr);
+	instrumentation_begin();
+
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#endif /* !CONFIG_IA32_EMULATION */
+
+static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
+{
+	int nr = syscall_32_enter(regs);
+	int res;
+
+	add_random_kstack_offset();
+	/*
+	 * This cannot use syscall_enter_from_user_mode() as it has to
+	 * fetch EBP before invoking any of the syscall entry work
+	 * functions.
+	 */
+	syscall_enter_from_user_mode_prepare(regs);
+
+	instrumentation_begin();
+	/* Fetch EBP from where the vDSO stashed it. */
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		/*
+		 * Micro-optimization: the pointer we're following is
+		 * explicitly 32 bits, so it can't be out of range.
+		 */
+		res = __get_user(*(u32 *)&regs->bp,
+			 (u32 __user __force *)(unsigned long)(u32)regs->sp);
+	} else {
+		res = get_user(*(u32 *)&regs->bp,
+		       (u32 __user __force *)(unsigned long)(u32)regs->sp);
+	}
+
+	if (res) {
+		/* User code screwed up. */
+		regs->ax = -EFAULT;
+
+		local_irq_disable();
+		instrumentation_end();
+		irqentry_exit_to_user_mode(regs);
+		return false;
+	}
+
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+
+	/* Now this is just like a normal syscall. */
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+	return true;
+}
+
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
+{
+	/*
+	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
+	 * convention.  Adjust regs so it looks like we entered using int80.
+	 */
+	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
+					vdso_image_32.sym_int80_landing_pad;
+
+	/*
+	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
+	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
+	 * Fix it up.
+	 */
+	regs->ip = landing_pad;
+
+	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
+	if (!__do_fast_syscall_32(regs))
+		return false;
+
+	/*
+	 * Check that the register state is valid for using SYSRETL/SYSEXIT
+	 * to exit to userspace.  Otherwise use the slower but fully capable
+	 * IRET exit path.
+	 */
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* EIP must point to the VDSO landing pad */
+	if (unlikely(regs->ip != landing_pad))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
+		return false;
+
+	/* If the TF, RF, or VM flags are set, use IRET */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
+		return false;
+
+	/* Use SYSRETL/SYSEXIT to exit to userspace */
+	return true;
+}
+
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
+{
+	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
+	regs->sp = regs->bp;
+
+	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
+	regs->flags |= X86_EFLAGS_IF;
+
+	return do_fast_syscall_32(regs);
+}
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index ba8354424860..b6e68ea98b83 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -1,15 +1,20 @@
-// SPDX-License-Identifier: GPL-2.0
-/* System call table for x86-64. */
+// SPDX-License-Identifier: GPL-2.0-only
+/* 64-bit system call dispatch */
 
 #include <linux/linkage.h>
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <linux/syscalls.h>
+#include <linux/entry-common.h>
+#include <linux/nospec.h>
 #include <asm/syscall.h>
 
 #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
 #define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
 #include <asm/syscalls_64.h>
+#ifdef CONFIG_X86_X32_ABI
+#include <asm/syscalls_x32.h>
+#endif
 #undef  __SYSCALL
 
 #undef  __SYSCALL_NORETURN
@@ -33,4 +38,104 @@ long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
 	#include <asm/syscalls_64.h>
 	default: return __x64_sys_ni_syscall(regs);
 	}
-};
+}
+
+#ifdef CONFIG_X86_X32_ABI
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_x32.h>
+	default: return __x64_sys_ni_syscall(regs);
+	}
+}
+#endif
+
+static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Convert negative numbers to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int unr = nr;
+
+	if (likely(unr < NR_syscalls)) {
+		unr = array_index_nospec(unr, NR_syscalls);
+		regs->ax = x64_sys_call(regs, unr);
+		return true;
+	}
+	return false;
+}
+
+static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
+{
+	/*
+	 * Adjust the starting offset of the table, and convert numbers
+	 * < __X32_SYSCALL_BIT to very high and thus out of range
+	 * numbers for comparisons.
+	 */
+	unsigned int xnr = nr - __X32_SYSCALL_BIT;
+
+	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
+		xnr = array_index_nospec(xnr, X32_NR_syscalls);
+		regs->ax = x32_sys_call(regs, xnr);
+		return true;
+	}
+	return false;
+}
+
+/* Returns true to return using SYSRET, or false to use IRET */
+__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
+{
+	add_random_kstack_offset();
+	nr = syscall_enter_from_user_mode(regs, nr);
+
+	instrumentation_begin();
+
+	if (!do_syscall_x64(regs, nr) && !do_syscall_x32(regs, nr) && nr != -1) {
+		/* Invalid system call, but still a system call. */
+		regs->ax = __x64_sys_ni_syscall(regs);
+	}
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+
+	/*
+	 * Check that the register state is valid for using SYSRET to exit
+	 * to userspace.  Otherwise use the slower but fully capable IRET
+	 * exit path.
+	 */
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
+	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
+		return false;
+
+	/*
+	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+	 * in kernel space.  This essentially lets the user take over
+	 * the kernel, since userspace controls RSP.
+	 *
+	 * TASK_SIZE_MAX covers all user-accessible addresses other than
+	 * the deprecated vsyscall page.
+	 */
+	if (unlikely(regs->ip >= TASK_SIZE_MAX))
+		return false;
+
+	/*
+	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
+	 * restoring TF results in a trap from userspace immediately after
+	 * SYSRET.
+	 */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
+		return false;
+
+	/* Use SYSRET to exit to userspace */
+	return true;
+}
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
deleted file mode 100644
index fb77908f44f3..000000000000
--- a/arch/x86/entry/syscall_x32.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* System call table for x32 ABI. */
-
-#include <linux/linkage.h>
-#include <linux/sys.h>
-#include <linux/cache.h>
-#include <linux/syscalls.h>
-#include <asm/syscall.h>
-
-#define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
-#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
-#include <asm/syscalls_x32.h>
-#undef  __SYSCALL
-
-#undef  __SYSCALL_NORETURN
-#define __SYSCALL_NORETURN __SYSCALL
-
-#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
-{
-	switch (nr) {
-	#include <asm/syscalls_x32.h>
-	default: return __x64_sys_ni_syscall(regs);
-	}
-};
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3f0ec87d5db4..ac007ea00979 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -396,7 +396,7 @@
 381	i386	pkey_alloc		sys_pkey_alloc
 382	i386	pkey_free		sys_pkey_free
 383	i386	statx			sys_statx
-384	i386	arch_prctl		sys_arch_prctl			compat_sys_arch_prctl
+384	i386	arch_prctl		sys_arch_prctl
 385	i386	io_pgetevents		sys_io_pgetevents_time32	compat_sys_io_pgetevents
 386	i386	rseq			sys_rseq
 393	i386	semget			sys_semget
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index c9216ac4fb1e..bf9f4f63e1b4 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -133,6 +133,7 @@ KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS_32 += -DBUILD_VDSO
 
 ifdef CONFIG_MITIGATION_RETPOLINE
 ifneq ($(RETPOLINE_VDSO_CFLAGS),)
diff --git a/arch/x86/entry/vdso/extable.h b/arch/x86/entry/vdso/extable.h
index b56f6b012941..baba612b832c 100644
--- a/arch/x86/entry/vdso/extable.h
+++ b/arch/x86/entry/vdso/extable.h
@@ -7,7 +7,7 @@
  * vDSO uses a dedicated handler the addresses are relative to the overall
  * exception table, not each individual entry.
  */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define _ASM_VDSO_EXTABLE_HANDLE(from, to)	\
 	ASM_VDSO_EXTABLE_HANDLE from to
 
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 39e6efc1a9ca..bfc7cabf4017 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -48,8 +48,7 @@ int __init init_vdso_image(const struct vdso_image *image)
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
-						image->alt_len),
-			   NULL);
+						image->alt_len));
 
 	return 0;
 }
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 833478ffbbf5..6866cc5acb0b 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2849,7 +2849,7 @@ static bool is_uprobe_at_func_entry(struct pt_regs *regs)
 		return true;
 
 	/* endbr64 (64-bit only) */
-	if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn))
+	if (user_64bit_mode(regs) && is_endbr((u32 *)auprobe->insn))
 		return true;
 
 	return false;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index dc38dec244c1..1ac39611fea8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4735,9 +4735,9 @@ static int adl_hw_config(struct perf_event *event)
 	return -EOPNOTSUPP;
 }
 
-static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
+static enum intel_cpu_type adl_get_hybrid_cpu_type(void)
 {
-	return HYBRID_INTEL_CORE;
+	return INTEL_CPU_TYPE_CORE;
 }
 
 static inline bool erratum_hsw11(struct perf_event *event)
@@ -5082,7 +5082,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 
 static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 {
-	u8 cpu_type = get_this_hybrid_cpu_type();
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+	enum intel_cpu_type cpu_type = c->topo.intel_type;
 	int i;
 
 	/*
@@ -5091,7 +5092,7 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 	 * on it. There should be a fixup function provided for these
 	 * troublesome CPUs (->get_hybrid_cpu_type).
 	 */
-	if (cpu_type == HYBRID_INTEL_NONE) {
+	if (cpu_type == INTEL_CPU_TYPE_UNKNOWN) {
 		if (x86_pmu.get_hybrid_cpu_type)
 			cpu_type = x86_pmu.get_hybrid_cpu_type();
 		else
@@ -5108,16 +5109,16 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
 		u32 native_id;
 
-		if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big)
+		if (cpu_type == INTEL_CPU_TYPE_CORE && pmu_type == hybrid_big)
 			return &x86_pmu.hybrid_pmu[i];
-		if (cpu_type == HYBRID_INTEL_ATOM) {
+		if (cpu_type == INTEL_CPU_TYPE_ATOM) {
 			if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
 
-			native_id = get_this_hybrid_cpu_native_id();
-			if (native_id == skt_native_id && pmu_type == hybrid_small)
+			native_id = c->topo.intel_native_model_id;
+			if (native_id == INTEL_ATOM_SKT_NATIVE_ID && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
-			if (native_id == cmt_native_id && pmu_type == hybrid_tiny)
+			if (native_id == INTEL_ATOM_CMT_NATIVE_ID && pmu_type == hybrid_tiny)
 				return &x86_pmu.hybrid_pmu[i];
 		}
 	}
@@ -6583,15 +6584,21 @@ __init int intel_pmu_init(void)
 	char *name;
 	struct x86_hybrid_pmu *pmu;
 
+	/* Architectural Perfmon was introduced starting with Core "Yonah" */
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
 		switch (boot_cpu_data.x86) {
-		case 0x6:
-			return p6_pmu_init();
-		case 0xb:
+		case  6:
+			if (boot_cpu_data.x86_vfm < INTEL_CORE_YONAH)
+				return p6_pmu_init();
+			break;
+		case 11:
 			return knc_pmu_init();
-		case 0xf:
+		case 15:
 			return p4_pmu_init();
 		}
+
+		pr_cont("unsupported CPU family %d model %d ",
+			boot_cpu_data.x86, boot_cpu_data.x86_model);
 		return -ENODEV;
 	}
 
@@ -6739,7 +6746,7 @@ __init int intel_pmu_init(void)
 	case INTEL_ATOM_SILVERMONT_D:
 	case INTEL_ATOM_SILVERMONT_MID:
 	case INTEL_ATOM_AIRMONT:
-	case INTEL_ATOM_AIRMONT_MID:
+	case INTEL_ATOM_SILVERMONT_MID2:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index 844bc4fc4724..fb726c6fc6e7 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -10,6 +10,7 @@
 #include <linux/perf_event.h>
 
 #include <asm/perf_event_p4.h>
+#include <asm/cpu_device_id.h>
 #include <asm/hardirq.h>
 #include <asm/apic.h>
 
@@ -732,9 +733,9 @@ static bool p4_event_match_cpu_model(unsigned int event_idx)
 {
 	/* INSTR_COMPLETED event only exist for model 3, 4, 6 (Prescott) */
 	if (event_idx == P4_EVENT_INSTR_COMPLETED) {
-		if (boot_cpu_data.x86_model != 3 &&
-			boot_cpu_data.x86_model != 4 &&
-			boot_cpu_data.x86_model != 6)
+		if (boot_cpu_data.x86_vfm != INTEL_P4_PRESCOTT &&
+		    boot_cpu_data.x86_vfm != INTEL_P4_PRESCOTT_2M &&
+		    boot_cpu_data.x86_vfm != INTEL_P4_CEDARMILL)
 			return false;
 	}
 
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index a6cffb4f4ef5..65b45e9d7016 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -2,6 +2,8 @@
 #include <linux/perf_event.h>
 #include <linux/types.h>
 
+#include <asm/cpu_device_id.h>
+
 #include "../perf_event.h"
 
 /*
@@ -248,30 +250,8 @@ __init int p6_pmu_init(void)
 {
 	x86_pmu = p6_pmu;
 
-	switch (boot_cpu_data.x86_model) {
-	case  1: /* Pentium Pro */
+	if (boot_cpu_data.x86_vfm == INTEL_PENTIUM_PRO)
 		x86_add_quirk(p6_pmu_rdpmc_quirk);
-		break;
-
-	case  3: /* Pentium II - Klamath */
-	case  5: /* Pentium II - Deschutes */
-	case  6: /* Pentium II - Mendocino */
-		break;
-
-	case  7: /* Pentium III - Katmai */
-	case  8: /* Pentium III - Coppermine */
-	case 10: /* Pentium III Xeon */
-	case 11: /* Pentium III - Tualatin */
-		break;
-
-	case  9: /* Pentium M - Banias */
-	case 13: /* Pentium M - Dothan */
-		break;
-
-	default:
-		pr_cont("unsupported p6 CPU model %d ", boot_cpu_data.x86_model);
-		return -ENODEV;
-	}
 
 	memcpy(hw_cache_event_ids, p6_hw_cache_event_ids,
 		sizeof(hw_cache_event_ids));
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8e5a4c3c5b95..2c0ce0e9545e 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -674,18 +674,6 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
-/*
- * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
- * of the core. Bits 31-24 indicates its core type (Core or Atom)
- * and Bits [23:0] indicates the native model ID of the core.
- * Core type and native model ID are defined in below enumerations.
- */
-enum hybrid_cpu_type {
-	HYBRID_INTEL_NONE,
-	HYBRID_INTEL_ATOM	= 0x20,
-	HYBRID_INTEL_CORE	= 0x40,
-};
-
 #define X86_HYBRID_PMU_ATOM_IDX		0
 #define X86_HYBRID_PMU_CORE_IDX		1
 #define X86_HYBRID_PMU_TINY_IDX		2
@@ -702,11 +690,6 @@ enum hybrid_pmu_type {
 	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
 };
 
-enum atom_native_id {
-	cmt_native_id           = 0x2,  /* Crestmont */
-	skt_native_id           = 0x3,  /* Skymont */
-};
-
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
 	const char			*name;
@@ -993,7 +976,7 @@ struct x86_pmu {
 	 */
 	int				num_hybrid_pmus;
 	struct x86_hybrid_pmu		*hybrid_pmu;
-	enum hybrid_cpu_type (*get_hybrid_cpu_type)	(void);
+	enum intel_cpu_type (*get_hybrid_cpu_type)	(void);
 };
 
 struct x86_perf_task_context_opt {
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index cc8c3bd0e7c2..1f7c3082a36d 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -239,5 +239,4 @@ void hyperv_setup_mmu_ops(void)
 
 	pr_info("Using hypercall for remote TLB flush\n");
 	pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
-	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 58f4ddecc5fa..4566000e15c4 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -8,6 +8,7 @@ generated-y += syscalls_x32.h
 generated-y += unistd_32_ia32.h
 generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
+generated-y += cpufeaturemasks.h
 
 generic-y += early_ioremap.h
 generic-y += fprobe.h
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 3b3d3aa19acd..4a37a8bd87fd 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -15,7 +15,7 @@
 #define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature))
 #define ALT_CALL_ALWAYS		ALT_DIRECT_CALL(X86_FEATURE_ALWAYS)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stddef.h>
 
@@ -87,20 +87,19 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
  * instructions were patched in already:
  */
 extern int alternatives_patched;
-struct module;
 
 extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			       struct module *mod);
-extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
-extern void apply_returns(s32 *start, s32 *end, struct module *mod);
-extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
 extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
-			  s32 *start_cfi, s32 *end_cfi, struct module *mod);
+			  s32 *start_cfi, s32 *end_cfi);
+
+struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
-	struct alt_instr		*alt_start, *alt_end;
 };
 
 #ifdef CONFIG_CALL_THUNKS
@@ -237,10 +236,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * references: i.e., if used for a function, it would add the PLT
  * suffix.
  */
-#define alternative_call(oldfunc, newfunc, ft_flags, output, input...)			\
+#define alternative_call(oldfunc, newfunc, ft_flags, output, input, clobbers...)	\
 	asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags)	\
 		: ALT_OUTPUT_SP(output)							\
-		: [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+		: [old] "i" (oldfunc), [new] "i" (newfunc)				\
+		  COMMA(input)								\
+		: clobbers)
 
 /*
  * Like alternative_call, but there are two features and respective functions.
@@ -249,24 +250,14 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, old function is used.
  */
 #define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2,		\
-			   output, input...)						\
+			   output, input, clobbers...)					\
 	asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1,	\
 		"call %c[new2]", ft_flags2)						\
 		: ALT_OUTPUT_SP(output)							\
 		: [old] "i" (oldfunc), [new1] "i" (newfunc1),				\
-		  [new2] "i" (newfunc2), ## input)
-
-/*
- * use this macro(s) if you need more than one output parameter
- * in alternative_io
- */
-#define ASM_OUTPUT2(a...) a
-
-/*
- * use this macro if you need clobbers but no inputs in
- * alternative_{input,io,call}()
- */
-#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+		  [new2] "i" (newfunc2)							\
+		  COMMA(input)								\
+		: clobbers)
 
 #define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__
 
@@ -286,7 +277,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 void BUG_func(void);
 void nop_func(void);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #ifdef CONFIG_SMP
 	.macro LOCK_PREFIX
@@ -369,6 +360,6 @@ void nop_func(void);
 	ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS,	\
 	newinstr_yes, ft_flags
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 4c4efb93045e..adfa0854cf2d 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -27,7 +27,6 @@ struct amd_l3_cache {
 };
 
 struct amd_northbridge {
-	struct pci_dev *root;
 	struct pci_dev *misc;
 	struct pci_dev *link;
 	struct amd_l3_cache l3_cache;
diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd_node.h
index 113ad3e8ee40..23fe617898a8 100644
--- a/arch/x86/include/asm/amd_node.h
+++ b/arch/x86/include/asm/amd_node.h
@@ -30,7 +30,31 @@ static inline u16 amd_num_nodes(void)
 	return topology_amd_nodes_per_pkg() * topology_max_packages();
 }
 
+#ifdef CONFIG_AMD_NODE
 int __must_check amd_smn_read(u16 node, u32 address, u32 *value);
 int __must_check amd_smn_write(u16 node, u32 address, u32 value);
 
+/* Should only be used by the HSMP driver. */
+int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write);
+#else
+static inline int __must_check amd_smn_read(u16 node, u32 address, u32 *value) { return -ENODEV; }
+static inline int __must_check amd_smn_write(u16 node, u32 address, u32 value) { return -ENODEV; }
+
+static inline int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_AMD_NODE */
+
+/* helper for use with read_poll_timeout */
+static inline int smn_read_register(u32 reg)
+{
+	int data, rc;
+
+	rc = amd_smn_read(0, reg, &data);
+	if (rc)
+		return rc;
+
+	return data;
+}
 #endif /*_ASM_X86_AMD_NODE_H_*/
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f21ff1932699..c903d358405d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -99,8 +99,8 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
 	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
-		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
-		       ASM_OUTPUT2("0" (v), "m" (*addr)));
+		       ASM_OUTPUT("=r" (v), "=m" (*addr)),
+		       ASM_INPUT("0" (v), "m" (*addr)));
 }
 
 static inline u32 native_apic_mem_read(u32 reg)
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index ba88edd0d58b..b5982b94bdba 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -16,9 +16,10 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 	unsigned int res;
 
-	asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT)
-			 : "="REG_OUT (res)
-			 : REG_IN (w));
+	asm_inline (ALTERNATIVE("call __sw_hweight32",
+				"popcntl %[val], %[cnt]", X86_FEATURE_POPCNT)
+			 : [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT
+			 : [val] REG_IN (w));
 
 	return res;
 }
@@ -44,9 +45,10 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
 	unsigned long res;
 
-	asm (ALTERNATIVE("call __sw_hweight64", "popcntq %1, %0", X86_FEATURE_POPCNT)
-			 : "="REG_OUT (res)
-			 : REG_IN (w));
+	asm_inline (ALTERNATIVE("call __sw_hweight64",
+				"popcntq %[val], %[cnt]", X86_FEATURE_POPCNT)
+			 : [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT
+			 : [val] REG_IN (w));
 
 	return res;
 }
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 3674006e3974..11c6fecc3ad7 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -16,10 +16,10 @@
 #include <asm/gsseg.h>
 #include <asm/nospec-branch.h>
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 extern void cmpxchg8b_emu(void);
 #endif
 
-#if defined(__GENKSYMS__) && defined(CONFIG_STACKPROTECTOR)
+#ifdef CONFIG_STACKPROTECTOR
 extern unsigned long __ref_stack_chk_guard;
 #endif
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 2bec0c89a95c..cc2881576c2c 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ASM_H
 #define _ASM_X86_ASM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 # define __ASM_FORM(x, ...)		x,## __VA_ARGS__
 # define __ASM_FORM_RAW(x, ...)		x,## __VA_ARGS__
 # define __ASM_FORM_COMMA(x, ...)	x,## __VA_ARGS__,
@@ -113,7 +113,7 @@
 
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifndef __pic__
 static __always_inline __pure void *rip_rel_ptr(void *p)
 {
@@ -144,7 +144,7 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 # include <asm/extable_fixup_types.h>
 
 /* Exception table entry */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 # define _ASM_EXTABLE_TYPE(from, to, type)			\
 	.pushsection "__ex_table","a" ;				\
@@ -164,7 +164,7 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 #  define _ASM_NOKPROBE(entry)
 # endif
 
-#else /* ! __ASSEMBLY__ */
+#else /* ! __ASSEMBLER__ */
 
 # define DEFINE_EXTABLE_TYPE_REG \
 	".macro extable_type_reg type:req reg:req\n"						\
@@ -213,6 +213,17 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
+/* Insert a comma if args are non-empty */
+#define COMMA(x...)		__COMMA(x)
+#define __COMMA(...)		, ##__VA_ARGS__
+
+/*
+ * Combine multiple asm inline constraint args into a single arg for passing to
+ * another macro.
+ */
+#define ASM_OUTPUT(x...)	x
+#define ASM_INPUT(x...)		x
+
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -221,7 +232,7 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
  */
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define _ASM_EXTABLE(from, to)					\
 	_ASM_EXTABLE_TYPE(from, to, EX_TYPE_DEFAULT)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 55b4d24356ea..75743f1dfd4e 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -30,14 +30,14 @@ static __always_inline void arch_atomic_set(atomic_t *v, int i)
 
 static __always_inline void arch_atomic_add(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "addl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "addl %1, %0"
 		     : "+m" (v->counter)
 		     : "ir" (i) : "memory");
 }
 
 static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "subl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "subl %1, %0"
 		     : "+m" (v->counter)
 		     : "ir" (i) : "memory");
 }
@@ -50,14 +50,14 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "incl %0"
+	asm_inline volatile(LOCK_PREFIX "incl %0"
 		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_inc arch_atomic_inc
 
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "decl %0"
+	asm_inline volatile(LOCK_PREFIX "decl %0"
 		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_dec arch_atomic_dec
@@ -116,7 +116,7 @@ static __always_inline int arch_atomic_xchg(atomic_t *v, int new)
 
 static __always_inline void arch_atomic_and(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "andl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "andl %1, %0"
 			: "+m" (v->counter)
 			: "ir" (i)
 			: "memory");
@@ -134,7 +134,7 @@ static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v)
 
 static __always_inline void arch_atomic_or(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "orl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "orl %1, %0"
 			: "+m" (v->counter)
 			: "ir" (i)
 			: "memory");
@@ -152,7 +152,7 @@ static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v)
 
 static __always_inline void arch_atomic_xor(int i, atomic_t *v)
 {
-	asm volatile(LOCK_PREFIX "xorl %1,%0"
+	asm_inline volatile(LOCK_PREFIX "xorl %1, %0"
 			: "+m" (v->counter)
 			: "ir" (i)
 			: "memory");
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6c6e9b9f98a4..ab838205c1c6 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -48,17 +48,20 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 	ATOMIC64_EXPORT(atomic64_##sym)
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %c[func]" \
+#ifdef CONFIG_X86_CX8
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	asm volatile("call %c[func]"					\
 		     : ALT_OUTPUT_SP(out) \
-		     : [func] "i" (atomic64_##g##_cx8), ## in)
+		     : [func] "i" (atomic64_##g##_cx8)			\
+		       COMMA(in)					\
+		     : clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
 #else
-#define __alternative_atomic64(f, g, out, in...) \
-	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
-			 X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8,	\
+			 X86_FEATURE_CX8, ASM_OUTPUT(out),		\
+			 ASM_INPUT(in), clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
 	ATOMIC64_DECL_ONE(sym##_386)
@@ -69,8 +72,8 @@ ATOMIC64_DECL_ONE(inc_386);
 ATOMIC64_DECL_ONE(dec_386);
 #endif
 
-#define alternative_atomic64(f, out, in...) \
-	__alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+#define alternative_atomic64(f, out, in, clobbers...) \
+	__alternative_atomic64(f, f, ASM_OUTPUT(out), ASM_INPUT(in), clobbers)
 
 ATOMIC64_DECL(read);
 ATOMIC64_DECL(set);
@@ -105,9 +108,10 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 	s64 o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
-	alternative_atomic64(xchg, "=&A" (o),
-			     "S" (v), "b" (low), "c" (high)
-			     : "memory");
+	alternative_atomic64(xchg,
+			     "=&A" (o),
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "memory");
 	return o;
 }
 #define arch_atomic64_xchg arch_atomic64_xchg
@@ -116,23 +120,25 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
-	alternative_atomic64(set, /* no output */,
-			     "S" (v), "b" (low), "c" (high)
-			     : "eax", "edx", "memory");
+	alternative_atomic64(set,
+			     /* no output */,
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "eax", "edx", "memory");
 }
 
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
+	alternative_atomic64(read, "=&A" (r), "c" (v), "memory");
 	return r;
 }
 
 static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
@@ -140,8 +146,9 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_sub_return arch_atomic64_sub_return
@@ -149,8 +156,10 @@ static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(inc_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(inc_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
@@ -158,8 +167,10 @@ static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(dec_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(dec_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
@@ -167,28 +178,34 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	__alternative_atomic64(inc, inc_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(inc, inc_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	__alternative_atomic64(dec, dec_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(dec, dec_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
@@ -197,8 +214,9 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
 	alternative_atomic64(add_unless,
-			     ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
-			     "S" (v) : "memory");
+			     ASM_OUTPUT("+A" (a), "+c" (low), "+D" (high)),
+			     "S" (v),
+			     "memory");
 	return (int)a;
 }
 #define arch_atomic64_add_unless arch_atomic64_add_unless
@@ -206,8 +224,10 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
-	alternative_atomic64(inc_not_zero, "=&a" (r),
-			     "S" (v) : "ecx", "edx", "memory");
+	alternative_atomic64(inc_not_zero,
+			     "=&a" (r),
+			     "S" (v),
+			     "ecx", "edx", "memory");
 	return r;
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
@@ -215,8 +235,10 @@ static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(dec_if_positive, "=&A" (r),
-			     "S" (v) : "ecx", "memory");
+	alternative_atomic64(dec_if_positive,
+			     "=&A" (r),
+			     "S" (v),
+			     "ecx", "memory");
 	return r;
 }
 #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index ae12acae5b06..87b496325b5b 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -22,14 +22,14 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "addq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "addq %1, %0"
 		     : "=m" (v->counter)
 		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "subq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "subq %1, %0"
 		     : "=m" (v->counter)
 		     : "er" (i), "m" (v->counter) : "memory");
 }
@@ -42,7 +42,7 @@ static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "incq %0"
+	asm_inline volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
 		     : "m" (v->counter) : "memory");
 }
@@ -50,7 +50,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
 
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "decq %0"
+	asm_inline volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
 		     : "m" (v->counter) : "memory");
 }
@@ -110,7 +110,7 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
 
 static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "andq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "andq %1, %0"
 			: "+m" (v->counter)
 			: "er" (i)
 			: "memory");
@@ -128,7 +128,7 @@ static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 
 static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "orq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "orq %1, %0"
 			: "+m" (v->counter)
 			: "er" (i)
 			: "memory");
@@ -146,7 +146,7 @@ static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 
 static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
-	asm volatile(LOCK_PREFIX "xorq %1,%0"
+	asm_inline volatile(LOCK_PREFIX "xorq %1, %0"
 			: "+m" (v->counter)
 			: "er" (i)
 			: "memory");
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index b96d45944c59..100413aff640 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -52,12 +52,12 @@ static __always_inline void
 arch_set_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "orb %b1,%0"
+		asm_inline volatile(LOCK_PREFIX "orb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" (CONST_MASK(nr))
 			: "memory");
 	} else {
-		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
+		asm_inline volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
@@ -72,11 +72,11 @@ static __always_inline void
 arch_clear_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "andb %b1,%0"
+		asm_inline volatile(LOCK_PREFIX "andb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" (~CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
+		asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
@@ -98,7 +98,7 @@ static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
 		volatile unsigned long *addr)
 {
 	bool negative;
-	asm volatile(LOCK_PREFIX "xorb %2,%1"
+	asm_inline volatile(LOCK_PREFIX "xorb %2,%1"
 		CC_SET(s)
 		: CC_OUT(s) (negative), WBYTE_ADDR(addr)
 		: "iq" ((char)mask) : "memory");
@@ -122,11 +122,11 @@ static __always_inline void
 arch_change_bit(long nr, volatile unsigned long *addr)
 {
 	if (__builtin_constant_p(nr)) {
-		asm volatile(LOCK_PREFIX "xorb %b1,%0"
+		asm_inline volatile(LOCK_PREFIX "xorb %b1,%0"
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" (CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
+		asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
 			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 3e5b111e619d..3f02ff6d333d 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -74,7 +74,7 @@
 # define BOOT_STACK_SIZE	0x1000
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern unsigned int output_len;
 extern const unsigned long kernel_text_size;
 extern const unsigned long kernel_total_size;
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index e85ac0c7c039..f0e9acf72547 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -17,13 +17,17 @@
  * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit.
  */
 #define INSN_ASOP		0x67
+#define INSN_LOCK		0xf0
 #define OPCODE_ESCAPE		0x0f
 #define SECOND_BYTE_OPCODE_UD1	0xb9
 #define SECOND_BYTE_OPCODE_UD2	0x0b
 
 #define BUG_NONE		0xffff
-#define BUG_UD1			0xfffe
-#define BUG_UD2			0xfffd
+#define BUG_UD2			0xfffe
+#define BUG_UD1			0xfffd
+#define BUG_UD1_UBSAN		0xfffc
+#define BUG_EA			0xffea
+#define BUG_LOCK		0xfff0
 
 #ifdef CONFIG_GENERIC_BUG
 
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 31d19c815f99..3e51ba459154 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -101,6 +101,16 @@ enum cfi_mode {
 
 extern enum cfi_mode cfi_mode;
 
+#ifdef CONFIG_FINEIBT_BHI
+extern bool cfi_bhi;
+#else
+#define cfi_bhi (0)
+#endif
+
+typedef u8 bhi_thunk[32];
+extern bhi_thunk __bhi_args[];
+extern bhi_thunk __bhi_args_end[];
+
 struct pt_regs;
 
 #ifdef CONFIG_CFI_CLANG
@@ -125,6 +135,18 @@ static inline int cfi_get_offset(void)
 #define cfi_get_offset cfi_get_offset
 
 extern u32 cfi_get_func_hash(void *func);
+extern int cfi_get_func_arity(void *func);
+
+#ifdef CONFIG_FINEIBT
+extern bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type);
+#else
+static inline bool
+decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	return false;
+}
+
+#endif
 
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
@@ -137,6 +159,10 @@ static inline u32 cfi_get_func_hash(void *func)
 {
 	return 0;
 }
+static inline int cfi_get_func_arity(void *func)
+{
+	return 0;
+}
 #endif /* CONFIG_CFI_CLANG */
 
 #if HAS_KERNEL_IBT == 1
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index fd8afc1f5f6b..b61f32c3459f 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -44,22 +44,22 @@ extern void __add_wrong_size(void)
 	        __typeof__ (*(ptr)) __ret = (arg);			\
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
-			asm volatile (lock #op "b %b0, %1\n"		\
+			asm_inline volatile (lock #op "b %b0, %1"	\
 				      : "+q" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
-			asm volatile (lock #op "w %w0, %1\n"		\
+			asm_inline volatile (lock #op "w %w0, %1"	\
 				      : "+r" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_L:					\
-			asm volatile (lock #op "l %0, %1\n"		\
+			asm_inline volatile (lock #op "l %0, %1"	\
 				      : "+r" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_Q:					\
-			asm volatile (lock #op "q %q0, %1\n"		\
+			asm_inline volatile (lock #op "q %q0, %1"	\
 				      : "+r" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
@@ -91,7 +91,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_B:						\
 	{								\
 		volatile u8 *__ptr = (volatile u8 *)(ptr);		\
-		asm volatile(lock "cmpxchgb %2,%1"			\
+		asm_inline volatile(lock "cmpxchgb %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "q" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -100,7 +100,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_W:						\
 	{								\
 		volatile u16 *__ptr = (volatile u16 *)(ptr);		\
-		asm volatile(lock "cmpxchgw %2,%1"			\
+		asm_inline volatile(lock "cmpxchgw %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "r" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -109,7 +109,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_L:						\
 	{								\
 		volatile u32 *__ptr = (volatile u32 *)(ptr);		\
-		asm volatile(lock "cmpxchgl %2,%1"			\
+		asm_inline volatile(lock "cmpxchgl %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "r" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -118,7 +118,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_Q:						\
 	{								\
 		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
-		asm volatile(lock "cmpxchgq %2,%1"			\
+		asm_inline volatile(lock "cmpxchgq %2, %1"		\
 			     : "=a" (__ret), "+m" (*__ptr)		\
 			     : "r" (__new), "0" (__old)			\
 			     : "memory");				\
@@ -165,7 +165,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_B:						\
 	{								\
 		volatile u8 *__ptr = (volatile u8 *)(_ptr);		\
-		asm volatile(lock "cmpxchgb %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgb %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -177,7 +177,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_W:						\
 	{								\
 		volatile u16 *__ptr = (volatile u16 *)(_ptr);		\
-		asm volatile(lock "cmpxchgw %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgw %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -189,7 +189,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_L:						\
 	{								\
 		volatile u32 *__ptr = (volatile u32 *)(_ptr);		\
-		asm volatile(lock "cmpxchgl %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgl %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
@@ -201,7 +201,7 @@ extern void __add_wrong_size(void)
 	case __X86_CASE_Q:						\
 	{								\
 		volatile u64 *__ptr = (volatile u64 *)(_ptr);		\
-		asm volatile(lock "cmpxchgq %[new], %[ptr]"		\
+		asm_inline volatile(lock "cmpxchgq %[new], %[ptr]"	\
 			     CC_SET(z)					\
 			     : CC_OUT(z) (success),			\
 			       [ptr] "+m" (*__ptr),			\
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 8806c646d452..371f7906019e 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -19,7 +19,7 @@ union __u64_halves {
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg8b %[ptr]"			\
 		     : [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
@@ -45,7 +45,7 @@ static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg8b %[ptr]"			\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
 		       [ptr] "+m" (*(_ptr)),				\
@@ -69,7 +69,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 
 #define arch_cmpxchg64 __cmpxchg64
 
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 5e241306db26..71d1e72ed879 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -38,7 +38,7 @@ union __u128_halves {
 	union __u128_halves o = { .full = (_old), },			\
 			    n = { .full = (_new), };			\
 									\
-	asm volatile(_lock "cmpxchg16b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg16b %[ptr]"			\
 		     : [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
@@ -65,7 +65,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old,
 			    n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(_lock "cmpxchg16b %[ptr]"				\
+	asm_inline volatile(_lock "cmpxchg16b %[ptr]"			\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
 		       [ptr] "+m" (*(_ptr)),				\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 98eced5084ca..ad235dda1ded 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -12,7 +12,6 @@
 #ifndef CONFIG_SMP
 #define cpu_physical_id(cpu)			boot_cpu_physical_apicid
 #define cpu_acpi_id(cpu)			0
-#define safe_smp_processor_id()			0
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -50,20 +49,6 @@ static inline void split_lock_init(void) {}
 static inline void bus_lock_init(void) {}
 #endif
 
-#ifdef CONFIG_CPU_SUP_INTEL
-u8 get_this_hybrid_cpu_type(void);
-u32 get_this_hybrid_cpu_native_id(void);
-#else
-static inline u8 get_this_hybrid_cpu_type(void)
-{
-	return 0;
-}
-
-static inline u32 get_this_hybrid_cpu_native_id(void)
-{
-	return 0;
-}
-#endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
 #else
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index ba32e0f44cba..6be777a06944 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -57,7 +57,7 @@
 #define X86_CPU_ID_FLAG_ENTRY_VALID	BIT(0)
 
 /**
- * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
+ * X86_MATCH_CPU -  Base macro for CPU matching
  * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *		The name is expanded to X86_VENDOR_@_vendor
  * @_family:	The family number or X86_FAMILY_ANY
@@ -74,47 +74,18 @@
  * into another macro at the usage site for good reasons, then please
  * start this local macro with X86_MATCH to allow easy grepping.
  */
-#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
-						    _steppings, _feature, _data) { \
-	.vendor		= X86_VENDOR_##_vendor,				\
-	.family		= _family,					\
-	.model		= _model,					\
-	.steppings	= _steppings,					\
-	.feature	= _feature,					\
-	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
-	.driver_data	= (unsigned long) _data				\
-}
-
-#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
-						    _steppings, _feature, _data) { \
+#define X86_MATCH_CPU(_vendor, _family, _model, _steppings, _feature, _type, _data) { \
 	.vendor		= _vendor,					\
 	.family		= _family,					\
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
 	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
+	.type		= _type,					\
 	.driver_data	= (unsigned long) _data				\
 }
 
 /**
- * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Macro for CPU matching
- * @_vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
- *		The name is expanded to X86_VENDOR_@_vendor
- * @_family:	The family number or X86_FAMILY_ANY
- * @_model:	The model number, model constant or X86_MODEL_ANY
- * @_feature:	A X86_FEATURE bit or X86_FEATURE_ANY
- * @_data:	Driver specific data or NULL. The internal storage
- *		format is unsigned long. The supplied value, pointer
- *		etc. is casted to unsigned long internally.
- *
- * The steppings arguments of X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE() is
- * set to wildcards.
- */
-#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, feature, data) \
-	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(vendor, family, model, \
-						X86_STEPPING_ANY, feature, data)
-
-/**
  * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature
  * @vendor:	The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY
  *		The name is expanded to X86_VENDOR_@vendor
@@ -123,13 +94,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data)	\
-	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family,		\
-					   X86_MODEL_ANY, feature, data)
+#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data)		\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, family, X86_MODEL_ANY,		\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VENDOR_FEATURE - Macro for matching vendor and CPU feature
@@ -139,12 +107,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data)			\
-	X86_MATCH_VENDOR_FAM_FEATURE(vendor, X86_FAMILY_ANY, feature, data)
+#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data)				\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, X86_FAMILY_ANY, X86_MODEL_ANY,	\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_FEATURE - Macro for matching a CPU feature
@@ -152,12 +118,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_FEATURE(feature, data)				\
-	X86_MATCH_VENDOR_FEATURE(ANY, feature, data)
+#define X86_MATCH_FEATURE(feature, data)					\
+	X86_MATCH_CPU(X86_VENDOR_ANY, X86_FAMILY_ANY, X86_MODEL_ANY,		\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VENDOR_FAM_MODEL - Match vendor, family and model
@@ -168,13 +132,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set to wildcards.
  */
-#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data)		\
-	X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model,	\
-					   X86_FEATURE_ANY, data)
+#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data)			\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, family, model, X86_STEPPING_ANY,	\
+		      X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VENDOR_FAM - Match vendor and family
@@ -184,12 +145,10 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is casted to unsigned long internally.
- *
- * All other missing arguments to X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are
- * set of wildcards.
  */
-#define X86_MATCH_VENDOR_FAM(vendor, family, data)			\
-	X86_MATCH_VENDOR_FAM_MODEL(vendor, family, X86_MODEL_ANY, data)
+#define X86_MATCH_VENDOR_FAM(vendor, family, data)				\
+	X86_MATCH_CPU(X86_VENDOR_##vendor, family, X86_MODEL_ANY,		\
+		      X86_STEPPING_ANY, X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VFM - Match encoded vendor/family/model
@@ -197,34 +156,26 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is cast to unsigned long internally.
- *
- * Stepping and feature are set to wildcards
  */
-#define X86_MATCH_VFM(vfm, data)			\
-	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
-		VFM_VENDOR(vfm),			\
-		VFM_FAMILY(vfm),			\
-		VFM_MODEL(vfm),				\
-		X86_STEPPING_ANY, X86_FEATURE_ANY, data)
+#define X86_MATCH_VFM(vfm, data)						\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm),	VFM_MODEL(vfm),		\
+		      X86_STEPPING_ANY, X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data)
 
 #define __X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
- * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping
+ * X86_MATCH_VFM_STEPS - Match encoded vendor/family/model and steppings
+ *			 range.
  * @vfm:	Encoded 8-bits each for vendor, family, model
- * @steppings:	Bitmask of steppings to match
+ * @min_step:	Lowest stepping number to match
+ * @max_step:	Highest stepping number to match
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is cast to unsigned long internally.
- *
- * feature is set to wildcard
  */
-#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data)	\
-	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(		\
-		VFM_VENDOR(vfm),				\
-		VFM_FAMILY(vfm),				\
-		VFM_MODEL(vfm),					\
-		__X86_STEPPINGS(min_step, max_step),		\
-		X86_FEATURE_ANY, data)
+#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data)			\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm),		\
+		      __X86_STEPPINGS(min_step, max_step), X86_FEATURE_ANY,	\
+		      X86_CPU_TYPE_ANY, data)
 
 /**
  * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature
@@ -233,15 +184,22 @@
  * @data:	Driver specific data or NULL. The internal storage
  *		format is unsigned long. The supplied value, pointer
  *		etc. is cast to unsigned long internally.
- *
- * Steppings is set to wildcard
  */
-#define X86_MATCH_VFM_FEATURE(vfm, feature, data)	\
-	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
-		VFM_VENDOR(vfm),			\
-		VFM_FAMILY(vfm),			\
-		VFM_MODEL(vfm),				\
-		X86_STEPPING_ANY, feature, data)
+#define X86_MATCH_VFM_FEATURE(vfm, feature, data)				\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm),		\
+		      X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data)
+
+/**
+ * X86_MATCH_VFM_CPU_TYPE - Match encoded vendor/family/model/type
+ * @vfm:	Encoded 8-bits each for vendor, family, model
+ * @type:	CPU type e.g. P-core, E-core
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is cast to unsigned long internally.
+ */
+#define X86_MATCH_VFM_CPU_TYPE(vfm, type, data)				\
+	X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm),	\
+		      X86_STEPPING_ANY, X86_FEATURE_ANY, type, data)
 
 extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
 extern bool x86_match_min_microcode_rev(const struct x86_cpu_id *table);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index de1ad09fe8d7..893cbca37fe9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -4,11 +4,12 @@
 
 #include <asm/processor.h>
 
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#if defined(__KERNEL__) && !defined(__ASSEMBLER__)
 
 #include <asm/asm.h>
 #include <linux/bitops.h>
 #include <asm/alternative.h>
+#include <asm/cpufeaturemasks.h>
 
 enum cpuid_leafs
 {
@@ -37,92 +38,19 @@ enum cpuid_leafs
 	NR_CPUID_WORDS,
 };
 
-#define X86_CAP_FMT_NUM "%d:%d"
-#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31)
-
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
-#define X86_CAP_FMT "%s"
-#define x86_cap_flag(flag) x86_cap_flags[flag]
 
 /*
  * In order to save room, we index into this array by doing
  * X86_BUG_<name> - NCAPINTS*32.
  */
 extern const char * const x86_bug_flags[NBUGINTS*32];
+#define x86_bug_flag(flag) x86_bug_flags[flag]
 
 #define test_cpu_cap(c, bit)						\
 	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-/*
- * There are 32 bits/features in each mask word.  The high bits
- * (selected with (bit>>5) give us the word number and the low 5
- * bits give us the bit/feature number inside the word.
- * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
- * see if it is set in the mask word.
- */
-#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
-	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
-
-/*
- * {REQUIRED,DISABLED}_MASK_CHECK below may seem duplicated with the
- * following BUILD_BUG_ON_ZERO() check but when NCAPINTS gets changed, all
- * header macros which use NCAPINTS need to be changed. The duplicated macro
- * use causes the compiler to issue errors for all headers so that all usage
- * sites can be corrected.
- */
-#define REQUIRED_MASK_BIT_SET(feature_bit)		\
-	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) ||	\
-	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
-
-#define DISABLED_MASK_BIT_SET(feature_bit)				\
-	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
-	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) ||	\
-	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
-
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
 	 test_cpu_cap(c, bit))
@@ -149,6 +77,7 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 
 extern void setup_clear_cpu_cap(unsigned int bit);
 extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
+void check_cpufeature_deps(struct cpuinfo_x86 *c);
 
 #define setup_force_cpu_cap(bit) do {			\
 							\
@@ -208,5 +137,5 @@ t_no:
 #define CPU_FEATURE_TYPEVAL		boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
 					boot_cpu_data.x86_model
 
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */
 #endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 508c0dad116b..c0462be0c5f6 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -2,14 +2,6 @@
 #ifndef _ASM_X86_CPUFEATURES_H
 #define _ASM_X86_CPUFEATURES_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
 /*
  * Defines x86 CPU feature bits
  */
@@ -338,6 +330,7 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* "clzero" CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* "irperf" Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */
+#define X86_FEATURE_INVLPGB		(13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */
 #define X86_FEATURE_RDPRU		(13*32+ 4) /* "rdpru" Read processor register at user level */
 #define X86_FEATURE_WBNOINVD		(13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */
 #define X86_FEATURE_AMD_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index b2b9b4ef3dae..d5749b25fa10 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -1,222 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * CPUID-related helpers/definitions
- */
 
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
-#include <linux/types.h>
-
-#include <asm/string.h>
-
-struct cpuid_regs {
-	u32 eax, ebx, ecx, edx;
-};
-
-enum cpuid_regs_idx {
-	CPUID_EAX = 0,
-	CPUID_EBX,
-	CPUID_ECX,
-	CPUID_EDX,
-};
-
-#define CPUID_LEAF_MWAIT	0x5
-#define CPUID_LEAF_DCA		0x9
-#define CPUID_LEAF_XSTATE	0x0d
-#define CPUID_LEAF_TSC		0x15
-#define CPUID_LEAF_FREQ		0x16
-#define CPUID_LEAF_TILE		0x1d
-
-#ifdef CONFIG_X86_32
-bool have_cpuid_p(void);
-#else
-static inline bool have_cpuid_p(void)
-{
-	return true;
-}
-#endif
-static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
-				unsigned int *ecx, unsigned int *edx)
-{
-	/* ecx is often an input as well as an output. */
-	asm volatile("cpuid"
-	    : "=a" (*eax),
-	      "=b" (*ebx),
-	      "=c" (*ecx),
-	      "=d" (*edx)
-	    : "0" (*eax), "2" (*ecx)
-	    : "memory");
-}
-
-#define native_cpuid_reg(reg)					\
-static inline unsigned int native_cpuid_##reg(unsigned int op)	\
-{								\
-	unsigned int eax = op, ebx, ecx = 0, edx;		\
-								\
-	native_cpuid(&eax, &ebx, &ecx, &edx);			\
-								\
-	return reg;						\
-}
-
-/*
- * Native CPUID functions returning a single datum.
- */
-native_cpuid_reg(eax)
-native_cpuid_reg(ebx)
-native_cpuid_reg(ecx)
-native_cpuid_reg(edx)
-
-#ifdef CONFIG_PARAVIRT_XXL
-#include <asm/paravirt.h>
-#else
-#define __cpuid			native_cpuid
-#endif
-
-/*
- * Generic CPUID function
- * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
- * resulting in stale register contents being returned.
- */
-static inline void cpuid(unsigned int op,
-			 unsigned int *eax, unsigned int *ebx,
-			 unsigned int *ecx, unsigned int *edx)
-{
-	*eax = op;
-	*ecx = 0;
-	__cpuid(eax, ebx, ecx, edx);
-}
-
-/* Some CPUID calls want 'count' to be placed in ecx */
-static inline void cpuid_count(unsigned int op, int count,
-			       unsigned int *eax, unsigned int *ebx,
-			       unsigned int *ecx, unsigned int *edx)
-{
-	*eax = op;
-	*ecx = count;
-	__cpuid(eax, ebx, ecx, edx);
-}
-
-/*
- * CPUID functions returning a single datum
- */
-static inline unsigned int cpuid_eax(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return eax;
-}
-
-static inline unsigned int cpuid_ebx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return ebx;
-}
-
-static inline unsigned int cpuid_ecx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return ecx;
-}
-
-static inline unsigned int cpuid_edx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return edx;
-}
-
-static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs)
-{
-	regs[CPUID_EAX] = leaf;
-	regs[CPUID_ECX] = subleaf;
-	__cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
-}
-
-#define cpuid_subleaf(leaf, subleaf, regs) {		\
-	static_assert(sizeof(*(regs)) == 16);		\
-	__cpuid_read(leaf, subleaf, (u32 *)(regs));	\
-}
-
-#define cpuid_leaf(leaf, regs) {			\
-	static_assert(sizeof(*(regs)) == 16);		\
-	__cpuid_read(leaf, 0, (u32 *)(regs));		\
-}
-
-static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf,
-				    enum cpuid_regs_idx regidx, u32 *reg)
-{
-	u32 regs[4];
-
-	__cpuid_read(leaf, subleaf, regs);
-	*reg = regs[regidx];
-}
-
-#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) {		\
-	static_assert(sizeof(*(reg)) == 4);			\
-	__cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg));	\
-}
-
-#define cpuid_leaf_reg(leaf, regidx, reg) {			\
-	static_assert(sizeof(*(reg)) == 4);			\
-	__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg));	\
-}
-
-static __always_inline bool cpuid_function_is_indexed(u32 function)
-{
-	switch (function) {
-	case 4:
-	case 7:
-	case 0xb:
-	case 0xd:
-	case 0xf:
-	case 0x10:
-	case 0x12:
-	case 0x14:
-	case 0x17:
-	case 0x18:
-	case 0x1d:
-	case 0x1e:
-	case 0x1f:
-	case 0x24:
-	case 0x8000001d:
-		return true;
-	}
-
-	return false;
-}
-
-#define for_each_possible_hypervisor_cpuid_base(function) \
-	for (function = 0x40000000; function < 0x40010000; function += 0x100)
-
-static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
-{
-	uint32_t base, eax, signature[3];
-
-	for_each_possible_hypervisor_cpuid_base(base) {
-		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
-
-		/*
-		 * This must not compile to "call memcmp" because it's called
-		 * from PVH early boot code before instrumentation is set up
-		 * and memcmp() itself may be instrumented.
-		 */
-		if (!__builtin_memcmp(sig, signature, 12) &&
-		    (leaves == 0 || ((eax - base) >= leaves)))
-			return base;
-	}
-
-	return 0;
-}
+#include <asm/cpuid/api.h>
 
 #endif /* _ASM_X86_CPUID_H */
diff --git a/arch/x86/include/asm/cpuid/api.h b/arch/x86/include/asm/cpuid/api.h
new file mode 100644
index 000000000000..9c180c9cc58e
--- /dev/null
+++ b/arch/x86/include/asm/cpuid/api.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CPUID_API_H
+#define _ASM_X86_CPUID_API_H
+
+#include <asm/cpuid/types.h>
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+
+#include <asm/string.h>
+
+/*
+ * Raw CPUID accessors:
+ */
+
+#ifdef CONFIG_X86_32
+bool have_cpuid_p(void);
+#else
+static inline bool have_cpuid_p(void)
+{
+	return true;
+}
+#endif
+
+static inline void native_cpuid(u32 *eax, u32 *ebx,
+				u32 *ecx, u32 *edx)
+{
+	/* ecx is often an input as well as an output. */
+	asm volatile("cpuid"
+	    : "=a" (*eax),
+	      "=b" (*ebx),
+	      "=c" (*ecx),
+	      "=d" (*edx)
+	    : "0" (*eax), "2" (*ecx)
+	    : "memory");
+}
+
+#define NATIVE_CPUID_REG(reg)					\
+static inline u32 native_cpuid_##reg(u32 op)	\
+{								\
+	u32 eax = op, ebx, ecx = 0, edx;		\
+								\
+	native_cpuid(&eax, &ebx, &ecx, &edx);			\
+								\
+	return reg;						\
+}
+
+/*
+ * Native CPUID functions returning a single datum:
+ */
+NATIVE_CPUID_REG(eax)
+NATIVE_CPUID_REG(ebx)
+NATIVE_CPUID_REG(ecx)
+NATIVE_CPUID_REG(edx)
+
+#ifdef CONFIG_PARAVIRT_XXL
+# include <asm/paravirt.h>
+#else
+# define __cpuid native_cpuid
+#endif
+
+/*
+ * Generic CPUID function
+ *
+ * Clear ECX since some CPUs (Cyrix MII) do not set or clear ECX
+ * resulting in stale register contents being returned.
+ */
+static inline void cpuid(u32 op,
+			 u32 *eax, u32 *ebx,
+			 u32 *ecx, u32 *edx)
+{
+	*eax = op;
+	*ecx = 0;
+	__cpuid(eax, ebx, ecx, edx);
+}
+
+/* Some CPUID calls want 'count' to be placed in ECX */
+static inline void cpuid_count(u32 op, int count,
+			       u32 *eax, u32 *ebx,
+			       u32 *ecx, u32 *edx)
+{
+	*eax = op;
+	*ecx = count;
+	__cpuid(eax, ebx, ecx, edx);
+}
+
+/*
+ * CPUID functions returning a single datum:
+ */
+
+static inline u32 cpuid_eax(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return eax;
+}
+
+static inline u32 cpuid_ebx(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return ebx;
+}
+
+static inline u32 cpuid_ecx(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return ecx;
+}
+
+static inline u32 cpuid_edx(u32 op)
+{
+	u32 eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return edx;
+}
+
+static inline void __cpuid_read(u32 leaf, u32 subleaf, u32 *regs)
+{
+	regs[CPUID_EAX] = leaf;
+	regs[CPUID_ECX] = subleaf;
+	__cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX);
+}
+
+#define cpuid_subleaf(leaf, subleaf, regs) {		\
+	static_assert(sizeof(*(regs)) == 16);		\
+	__cpuid_read(leaf, subleaf, (u32 *)(regs));	\
+}
+
+#define cpuid_leaf(leaf, regs) {			\
+	static_assert(sizeof(*(regs)) == 16);		\
+	__cpuid_read(leaf, 0, (u32 *)(regs));		\
+}
+
+static inline void __cpuid_read_reg(u32 leaf, u32 subleaf,
+				    enum cpuid_regs_idx regidx, u32 *reg)
+{
+	u32 regs[4];
+
+	__cpuid_read(leaf, subleaf, regs);
+	*reg = regs[regidx];
+}
+
+#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) {		\
+	static_assert(sizeof(*(reg)) == 4);			\
+	__cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg));	\
+}
+
+#define cpuid_leaf_reg(leaf, regidx, reg) {			\
+	static_assert(sizeof(*(reg)) == 4);			\
+	__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg));	\
+}
+
+static __always_inline bool cpuid_function_is_indexed(u32 function)
+{
+	switch (function) {
+	case 4:
+	case 7:
+	case 0xb:
+	case 0xd:
+	case 0xf:
+	case 0x10:
+	case 0x12:
+	case 0x14:
+	case 0x17:
+	case 0x18:
+	case 0x1d:
+	case 0x1e:
+	case 0x1f:
+	case 0x24:
+	case 0x8000001d:
+		return true;
+	}
+
+	return false;
+}
+
+#define for_each_possible_hypervisor_cpuid_base(function) \
+	for (function = 0x40000000; function < 0x40010000; function += 0x100)
+
+static inline u32 hypervisor_cpuid_base(const char *sig, u32 leaves)
+{
+	u32 base, eax, signature[3];
+
+	for_each_possible_hypervisor_cpuid_base(base) {
+		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
+
+		/*
+		 * This must not compile to "call memcmp" because it's called
+		 * from PVH early boot code before instrumentation is set up
+		 * and memcmp() itself may be instrumented.
+		 */
+		if (!__builtin_memcmp(sig, signature, 12) &&
+		    (leaves == 0 || ((eax - base) >= leaves)))
+			return base;
+	}
+
+	return 0;
+}
+
+#endif /* _ASM_X86_CPUID_API_H */
diff --git a/arch/x86/include/asm/cpuid/types.h b/arch/x86/include/asm/cpuid/types.h
new file mode 100644
index 000000000000..8582e27e836d
--- /dev/null
+++ b/arch/x86/include/asm/cpuid/types.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_CPUID_TYPES_H
+#define _ASM_X86_CPUID_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * Types for raw CPUID access:
+ */
+
+struct cpuid_regs {
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+};
+
+enum cpuid_regs_idx {
+	CPUID_EAX = 0,
+	CPUID_EBX,
+	CPUID_ECX,
+	CPUID_EDX,
+};
+
+#define CPUID_LEAF_MWAIT	0x05
+#define CPUID_LEAF_DCA		0x09
+#define CPUID_LEAF_XSTATE	0x0d
+#define CPUID_LEAF_TSC		0x15
+#define CPUID_LEAF_FREQ		0x16
+#define CPUID_LEAF_TILE		0x1d
+
+#endif /* _ASM_X86_CPUID_TYPES_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 4acfd57de8f1..70f6b60ad67b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_CPUMASK_H
 #define _ASM_X86_CPUMASK_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cpumask.h>
 
 extern void setup_cpu_local_masks(void);
@@ -34,5 +34,5 @@ static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp
 
 #define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index bf5953883ec3..cc4a3f725b37 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -5,52 +5,28 @@
 #include <linux/build_bug.h>
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/cache.h>
 #include <asm/percpu.h>
 
 struct task_struct;
 
-struct pcpu_hot {
-	union {
-		struct {
-			struct task_struct	*current_task;
-			int			preempt_count;
-			int			cpu_number;
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-			u64			call_depth;
-#endif
-			unsigned long		top_of_stack;
-			void			*hardirq_stack_ptr;
-			u16			softirq_pending;
-#ifdef CONFIG_X86_64
-			bool			hardirq_stack_inuse;
-#else
-			void			*softirq_stack_ptr;
-#endif
-		};
-		u8	pad[64];
-	};
-};
-static_assert(sizeof(struct pcpu_hot) == 64);
-
-DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
-
-/* const-qualified alias to pcpu_hot, aliased by linker. */
-DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
-			const_pcpu_hot);
+DECLARE_PER_CPU_CACHE_HOT(struct task_struct *, current_task);
+/* const-qualified alias provided by the linker. */
+DECLARE_PER_CPU_CACHE_HOT(struct task_struct * const __percpu_seg_override,
+			  const_current_task);
 
 static __always_inline struct task_struct *get_current(void)
 {
 	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
-		return this_cpu_read_const(const_pcpu_hot.current_task);
+		return this_cpu_read_const(const_current_task);
 
-	return this_cpu_read_stable(pcpu_hot.current_task);
+	return this_cpu_read_stable(current_task);
 }
 
 #define current get_current()
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_CURRENT_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 62dc9f59ea76..ec95fe44fa3a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,7 +46,6 @@ struct gdt_page {
 } __attribute__((aligned(PAGE_SIZE)));
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
-DECLARE_INIT_PER_CPU(gdt_page);
 
 /* Provide the original GDT */
 static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index d440a65af8f3..7e6b9314758a 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -58,7 +58,7 @@
 
 #define DESC_USER		(_DESC_DPL(3))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -166,7 +166,7 @@ struct desc_ptr {
 	unsigned long address;
 } __attribute__((packed)) ;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* Boot IDT definitions */
 #define	BOOT_IDT_ENTRIES	32
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
deleted file mode 100644
index c492bdc97b05..000000000000
--- a/arch/x86/include/asm/disabled-features.h
+++ /dev/null
@@ -1,161 +0,0 @@
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#define _ASM_X86_DISABLED_FEATURES_H
-
-/* These features, although they might be available in a CPU
- * will not be used because the compile options to support
- * them are not present.
- *
- * This code allows them to be checked and disabled at
- * compile time without an explicit #ifdef.  Use
- * cpu_feature_enabled().
- */
-
-#ifdef CONFIG_X86_UMIP
-# define DISABLE_UMIP	0
-#else
-# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
-#endif
-
-#ifdef CONFIG_X86_64
-# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
-# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
-# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
-# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
-# define DISABLE_PCID		0
-#else
-# define DISABLE_VME		0
-# define DISABLE_K6_MTRR	0
-# define DISABLE_CYRIX_ARR	0
-# define DISABLE_CENTAUR_MCR	0
-# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
-#endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		0
-# define DISABLE_OSPKE		0
-#else
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
-#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
-
-#ifdef CONFIG_X86_5LEVEL
-# define DISABLE_LA57	0
-#else
-# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
-# define DISABLE_PTI		0
-#else
-# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETPOLINE
-# define DISABLE_RETPOLINE	0
-#else
-# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
-				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETHUNK
-# define DISABLE_RETHUNK	0
-#else
-# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_UNRET_ENTRY
-# define DISABLE_UNRET		0
-#else
-# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-# define DISABLE_CALL_DEPTH_TRACKING	0
-#else
-# define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
-#endif
-
-#ifdef CONFIG_ADDRESS_MASKING
-# define DISABLE_LAM		0
-#else
-# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
-#endif
-
-#ifdef CONFIG_INTEL_IOMMU_SVM
-# define DISABLE_ENQCMD		0
-#else
-# define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
-#endif
-
-#ifdef CONFIG_X86_SGX
-# define DISABLE_SGX	0
-#else
-# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
-#endif
-
-#ifdef CONFIG_XEN_PV
-# define DISABLE_XENPV		0
-#else
-# define DISABLE_XENPV		(1 << (X86_FEATURE_XENPV & 31))
-#endif
-
-#ifdef CONFIG_INTEL_TDX_GUEST
-# define DISABLE_TDX_GUEST	0
-#else
-# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
-#endif
-
-#ifdef CONFIG_X86_USER_SHADOW_STACK
-#define DISABLE_USER_SHSTK	0
-#else
-#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
-#endif
-
-#ifdef CONFIG_X86_KERNEL_IBT
-#define DISABLE_IBT	0
-#else
-#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
-#endif
-
-#ifdef CONFIG_X86_FRED
-# define DISABLE_FRED	0
-#else
-# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
-#endif
-
-#ifdef CONFIG_KVM_AMD_SEV
-#define DISABLE_SEV_SNP		0
-#else
-#define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
-#endif
-
-/*
- * Make sure to add features to the correct mask
- */
-#define DISABLED_MASK0	(DISABLE_VME)
-#define DISABLED_MASK1	0
-#define DISABLED_MASK2	0
-#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	(DISABLE_PCID)
-#define DISABLED_MASK5	0
-#define DISABLED_MASK6	0
-#define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	(DISABLE_XENPV|DISABLE_TDX_GUEST)
-#define DISABLED_MASK9	(DISABLE_SGX)
-#define DISABLED_MASK10	0
-#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
-#define DISABLED_MASK13	0
-#define DISABLED_MASK14	0
-#define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
-			 DISABLE_ENQCMD)
-#define DISABLED_MASK17	0
-#define DISABLED_MASK18	(DISABLE_IBT)
-#define DISABLED_MASK19	(DISABLE_SEV_SNP)
-#define DISABLED_MASK20	0
-#define DISABLED_MASK21	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 430fca13bb56..302e11b15da8 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_DWARF2_H
 #define _ASM_X86_DWARF2_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #warning "asm/dwarf2.h should be only included in pure assembly files"
 #endif
 
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1fb83d47711f..128602612eca 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -54,8 +54,9 @@ typedef struct user_i387_struct elf_fpregset_t;
 #define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
 #define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
 #define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative offset to GOT */
+#define R_X86_64_GOTPCRELX	41
+#define R_X86_64_REX_GOTPCRELX	42
 #define R_X86_64_32		10	/* Direct 32 bit zero extended */
 #define R_X86_64_32S		11	/* Direct 32 bit sign extended */
 #define R_X86_64_16		12	/* Direct 16 bit zero extended */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index d0dcefb5cc59..4519c9f35ba0 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -31,7 +31,7 @@
 /* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */
 #define FIXMAP_PMD_TOP	507
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/kernel.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
@@ -196,5 +196,5 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
 void __early_set_fixmap(enum fixed_addresses idx,
 			phys_addr_t phys, pgprot_t flags);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
index fb42659f6e98..0ab65073c1cc 100644
--- a/arch/x86/include/asm/frame.h
+++ b/arch/x86/include/asm/frame.h
@@ -11,7 +11,7 @@
 
 #ifdef CONFIG_FRAME_POINTER
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro FRAME_BEGIN
 	push %_ASM_BP
@@ -51,7 +51,7 @@
 .endm
 #endif /* CONFIG_X86_64 */
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #define FRAME_BEGIN				\
 	"push %" _ASM_BP "\n"			\
@@ -82,18 +82,18 @@ static inline unsigned long encode_frame_pointer(struct pt_regs *regs)
 
 #endif /* CONFIG_X86_64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define FRAME_OFFSET __ASM_SEL(4, 8)
 
 #else /* !CONFIG_FRAME_POINTER */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro ENCODE_FRAME_POINTER ptregs_offset=0
 .endm
 
-#else /* !__ASSEMBLY */
+#else /* !__ASSEMBLER__ */
 
 #define ENCODE_FRAME_POINTER
 
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
index 25ca00bd70e8..2a29e5216881 100644
--- a/arch/x86/include/asm/fred.h
+++ b/arch/x86/include/asm/fred.h
@@ -32,7 +32,7 @@
 #define FRED_CONFIG_INT_STKLVL(l)	(_AT(unsigned long, l) << 9)
 #define FRED_CONFIG_ENTRYPOINT(p)	_AT(unsigned long, (p))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_X86_FRED
 #include <linux/kernel.h>
@@ -113,6 +113,6 @@ static inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) {
 static inline void fred_sync_rsp0(unsigned long rsp0) { }
 static inline void fred_update_rsp0(void) { }
 #endif /* CONFIG_X86_FRED */
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* ASM_X86_FRED_H */
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index 9e7e8ca8e299..02f239569b93 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_FSGSBASE_H
 #define _ASM_FSGSBASE_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_X86_64
 
@@ -80,6 +80,6 @@ extern unsigned long x86_fsgsbase_read_task(struct task_struct *task,
 
 #endif /* CONFIG_X86_64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_FSGSBASE_H */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index f9cb4d07df58..93156ac4ffe0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -22,7 +22,7 @@
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern void __fentry__(void);
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
@@ -36,21 +36,9 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 
 static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
 {
-#ifdef CONFIG_X86_KERNEL_IBT
-	u32 instr;
-
-	/* We want to be extra safe in case entry ip is on the page edge,
-	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
-	 */
-	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
-		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
-			return fentry_ip;
-	} else {
-		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
-	}
-	if (is_endbr(instr))
+	if (is_endbr((void*)(fentry_ip - ENDBR_INSN_SIZE)))
 		fentry_ip -= ENDBR_INSN_SIZE;
-#endif
+
 	return fentry_ip;
 }
 #define ftrace_get_symaddr(fentry_ip)	arch_ftrace_get_symaddr(fentry_ip)
@@ -118,11 +106,11 @@ struct dyn_arch_ftrace {
 };
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer);
@@ -166,6 +154,6 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
 }
 #endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */
 #endif /* !COMPILE_OFFSETS */
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 6ffa8b75f4cd..f00c09ffe6a9 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
-#include <asm/current.h>
 
 typedef struct {
 #if IS_ENABLED(CONFIG_KVM_INTEL)
@@ -66,7 +65,8 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
-#define local_softirq_pending_ref       pcpu_hot.softirq_pending
+DECLARE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+#define local_softirq_pending_ref       __softirq_pending
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 /*
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index edebf1020e04..162ebd73a698 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,7 +16,7 @@
 
 #include <asm/irq_vectors.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/percpu.h>
 #include <linux/profile.h>
@@ -128,6 +128,6 @@ extern char spurious_entries_start[];
 typedef struct irq_desc* vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
 
-#endif /* !ASSEMBLY_ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_HW_IRQ_H */
diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h
index 1e59581d500c..28d845257303 100644
--- a/arch/x86/include/asm/ibt.h
+++ b/arch/x86/include/asm/ibt.h
@@ -21,7 +21,7 @@
 
 #define HAS_KERNEL_IBT	1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_X86_64
 #define ASM_ENDBR	"endbr64\n\t"
@@ -41,7 +41,7 @@
 	_ASM_PTR fname "\n\t"				\
 	".popsection\n\t"
 
-static inline __attribute_const__ u32 gen_endbr(void)
+static __always_inline __attribute_const__ u32 gen_endbr(void)
 {
 	u32 endbr;
 
@@ -56,7 +56,7 @@ static inline __attribute_const__ u32 gen_endbr(void)
 	return endbr;
 }
 
-static inline __attribute_const__ u32 gen_endbr_poison(void)
+static __always_inline __attribute_const__ u32 gen_endbr_poison(void)
 {
 	/*
 	 * 4 byte NOP that isn't NOP4 (in fact it is OSP NOP3), such that it
@@ -65,19 +65,24 @@ static inline __attribute_const__ u32 gen_endbr_poison(void)
 	return 0x001f0f66; /* osp nopl (%rax) */
 }
 
-static inline bool is_endbr(u32 val)
+static inline bool __is_endbr(u32 val)
 {
 	if (val == gen_endbr_poison())
 		return true;
 
+	/* See cfi_fineibt_bhi_preamble() */
+	if (IS_ENABLED(CONFIG_FINEIBT_BHI) && val == 0x001f0ff5)
+		return true;
+
 	val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */
 	return val == gen_endbr();
 }
 
+extern __noendbr bool is_endbr(u32 *val);
 extern __noendbr u64 ibt_save(bool disable);
 extern __noendbr void ibt_restore(u64 save);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #ifdef CONFIG_X86_64
 #define ENDBR	endbr64
@@ -85,29 +90,29 @@ extern __noendbr void ibt_restore(u64 save);
 #define ENDBR	endbr32
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #else /* !IBT */
 
 #define HAS_KERNEL_IBT	0
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define ASM_ENDBR
 #define IBT_NOSEAL(name)
 
 #define __noendbr
 
-static inline bool is_endbr(u32 val) { return false; }
+static inline bool is_endbr(u32 *val) { return false; }
 
 static inline u64 ibt_save(bool disable) { return 0; }
 static inline void ibt_restore(u64 save) { }
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define ENDBR
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* CONFIG_X86_KERNEL_IBT */
 
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index ad5c68f0509d..a4ec27c67988 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -7,7 +7,7 @@
 
 #define IDT_ALIGN	(8 * (1 + HAS_KERNEL_IBT))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/entry-common.h>
 #include <linux/hardirq.h>
 
@@ -474,7 +474,7 @@ static inline void fred_install_sysvec(unsigned int vector, const idtentry_t fun
 		idt_install_sysvec(vector, asm_##function);		\
 }
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 /*
  * The ASM variants for DECLARE_IDTENTRY*() which emit the ASM entry stubs.
@@ -579,7 +579,7 @@ SYM_CODE_START(spurious_entries_start)
 SYM_CODE_END(spurious_entries_start)
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * The actual entry points. Note that DECLARE_IDTENTRY*() serves two
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 0e82ebc5d1e1..8b1b1abcef15 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -2,7 +2,11 @@
 #ifndef _ASM_X86_INIT_H
 #define _ASM_X86_INIT_H
 
+#if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+#define __head	__section(".head.text") __no_sanitize_undefined __no_stack_protector
+#else
 #define __head	__section(".head.text") __no_sanitize_undefined
+#endif
 
 struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h
index 438ccd4f3cc4..e48a00b3311d 100644
--- a/arch/x86/include/asm/inst.h
+++ b/arch/x86/include/asm/inst.h
@@ -6,7 +6,7 @@
 #ifndef X86_ASM_INST_H
 #define X86_ASM_INST_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define REG_NUM_INVALID		100
 
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6d7b04ffc5fd..3a97a7eefb51 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -45,7 +45,18 @@
 /* Wildcard match so X86_MATCH_VFM(ANY) works */
 #define INTEL_ANY			IFM(X86_FAMILY_ANY, X86_MODEL_ANY)
 
+/* Family 5 */
+#define INTEL_FAM5_START		IFM(5, 0x00) /* Notational marker, also P5 A-step */
+#define INTEL_PENTIUM_75		IFM(5, 0x02) /* P54C */
+#define INTEL_PENTIUM_MMX		IFM(5, 0x04) /* P55C */
+#define INTEL_QUARK_X1000		IFM(5, 0x09) /* Quark X1000 SoC */
+
+/* Family 6 */
 #define INTEL_PENTIUM_PRO		IFM(6, 0x01)
+#define INTEL_PENTIUM_II_KLAMATH	IFM(6, 0x03)
+#define INTEL_PENTIUM_III_DESCHUTES	IFM(6, 0x05)
+#define INTEL_PENTIUM_III_TUALATIN	IFM(6, 0x0B)
+#define INTEL_PENTIUM_M_DOTHAN		IFM(6, 0x0D)
 
 #define INTEL_CORE_YONAH		IFM(6, 0x0E)
 
@@ -110,9 +121,9 @@
 
 #define INTEL_SAPPHIRERAPIDS_X		IFM(6, 0x8F) /* Golden Cove */
 
-#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF)
+#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF) /* Raptor Cove */
 
-#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD)
+#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD) /* Redwood Cove */
 #define INTEL_GRANITERAPIDS_D		IFM(6, 0xAE)
 
 /* "Hybrid" Processors (P-Core/E-Core) */
@@ -126,16 +137,16 @@
 #define INTEL_RAPTORLAKE_P		IFM(6, 0xBA)
 #define INTEL_RAPTORLAKE_S		IFM(6, 0xBF)
 
-#define INTEL_METEORLAKE		IFM(6, 0xAC)
+#define INTEL_METEORLAKE		IFM(6, 0xAC) /* Redwood Cove / Crestmont */
 #define INTEL_METEORLAKE_L		IFM(6, 0xAA)
 
-#define INTEL_ARROWLAKE_H		IFM(6, 0xC5)
+#define INTEL_ARROWLAKE_H		IFM(6, 0xC5) /* Lion Cove / Skymont */
 #define INTEL_ARROWLAKE			IFM(6, 0xC6)
 #define INTEL_ARROWLAKE_U		IFM(6, 0xB5)
 
-#define INTEL_LUNARLAKE_M		IFM(6, 0xBD)
+#define INTEL_LUNARLAKE_M		IFM(6, 0xBD) /* Lion Cove / Skymont */
 
-#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC)
+#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC) /* Cougar Cove / Crestmont */
 
 /* "Small Core" Processors (Atom/E-Core) */
 
@@ -149,9 +160,9 @@
 #define INTEL_ATOM_SILVERMONT		IFM(6, 0x37) /* Bay Trail, Valleyview */
 #define INTEL_ATOM_SILVERMONT_D		IFM(6, 0x4D) /* Avaton, Rangely */
 #define INTEL_ATOM_SILVERMONT_MID	IFM(6, 0x4A) /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID2	IFM(6, 0x5A) /* Anniedale */
 
 #define INTEL_ATOM_AIRMONT		IFM(6, 0x4C) /* Cherry Trail, Braswell */
-#define INTEL_ATOM_AIRMONT_MID		IFM(6, 0x5A) /* Moorefield */
 #define INTEL_ATOM_AIRMONT_NP		IFM(6, 0x75) /* Lightning Mountain */
 
 #define INTEL_ATOM_GOLDMONT		IFM(6, 0x5C) /* Apollo Lake */
@@ -176,16 +187,35 @@
 #define INTEL_XEON_PHI_KNL		IFM(6, 0x57) /* Knights Landing */
 #define INTEL_XEON_PHI_KNM		IFM(6, 0x85) /* Knights Mill */
 
-/* Family 5 */
-#define INTEL_QUARK_X1000		IFM(5, 0x09) /* Quark X1000 SoC */
+/* Notational marker denoting the last Family 6 model */
+#define INTEL_FAM6_LAST			IFM(6, 0xFF)
+
+/* Family 15 - NetBurst */
+#define INTEL_P4_WILLAMETTE		IFM(15, 0x01) /* Also Xeon Foster */
+#define INTEL_P4_PRESCOTT		IFM(15, 0x03)
+#define INTEL_P4_PRESCOTT_2M		IFM(15, 0x04)
+#define INTEL_P4_CEDARMILL		IFM(15, 0x06) /* Also Xeon Dempsey */
 
 /* Family 19 */
 #define INTEL_PANTHERCOVE_X		IFM(19, 0x01) /* Diamond Rapids */
 
-/* CPU core types */
+/*
+ * Intel CPU core types
+ *
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum intel_cpu_type {
+	INTEL_CPU_TYPE_UNKNOWN,
 	INTEL_CPU_TYPE_ATOM = 0x20,
 	INTEL_CPU_TYPE_CORE = 0x40,
 };
 
+enum intel_native_id {
+	INTEL_ATOM_CMT_NATIVE_ID = 0x2,  /* Crestmont */
+	INTEL_ATOM_SKT_NATIVE_ID = 0x3,  /* Skymont */
+};
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ed580c7f9d0a..1a0dc2b2bf5b 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -175,6 +175,9 @@ extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, un
 extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size);
 #define ioremap_encrypted ioremap_encrypted
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
+#define arch_memremap_wb arch_memremap_wb
+
 /**
  * ioremap     -   map bus memory into CPU space
  * @offset:    bus address of the memory
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 562a547c29a5..735c3a491f60 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -116,7 +116,7 @@
 	ASM_CALL_ARG2
 
 #define call_on_irqstack(func, asm_call, argconstr...)			\
-	call_on_stack(__this_cpu_read(pcpu_hot.hardirq_stack_ptr),	\
+	call_on_stack(__this_cpu_read(hardirq_stack_ptr),		\
 		      func, asm_call, argconstr)
 
 /* Macros to assert type correctness for run_*_on_irqstack macros */
@@ -135,7 +135,7 @@
 	 * User mode entry and interrupt on the irq stack do not	\
 	 * switch stacks. If from user mode the task stack is empty.	\
 	 */								\
-	if (user_mode(regs) || __this_cpu_read(pcpu_hot.hardirq_stack_inuse)) { \
+	if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) {	\
 		irq_enter_rcu();					\
 		func(c_args);						\
 		irq_exit_rcu();						\
@@ -146,9 +146,9 @@
 		 * places. Invoke the stack switch macro with the call	\
 		 * sequence which matches the above direct invocation.	\
 		 */							\
-		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);	\
+		__this_cpu_write(hardirq_stack_inuse, true);		\
 		call_on_irqstack(func, asm_call, constr);		\
-		__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);	\
+		__this_cpu_write(hardirq_stack_inuse, false);		\
 	}								\
 }
 
@@ -212,9 +212,9 @@
  */
 #define do_softirq_own_stack()						\
 {									\
-	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, true);		\
+	__this_cpu_write(hardirq_stack_inuse, true);			\
 	call_on_irqstack(__do_softirq, ASM_CALL_ARG0);			\
-	__this_cpu_write(pcpu_hot.hardirq_stack_inuse, false);		\
+	__this_cpu_write(hardirq_stack_inuse, false);			\
 }
 
 #endif
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index cf7fc2b8e3ce..abb8374c9ff7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -4,7 +4,7 @@
 
 #include <asm/processor-flags.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/nospec-branch.h>
 
@@ -79,7 +79,7 @@ static __always_inline void native_local_irq_restore(unsigned long flags)
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 static __always_inline unsigned long arch_local_save_flags(void)
@@ -133,10 +133,10 @@ static __always_inline unsigned long arch_local_irq_save(void)
 
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* CONFIG_PARAVIRT_XXL */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 static __always_inline int arch_irqs_disabled_flags(unsigned long flags)
 {
 	return !(flags & X86_EFLAGS_IF);
@@ -154,6 +154,6 @@ static __always_inline void arch_local_irq_restore(unsigned long flags)
 	if (!arch_irqs_disabled_flags(flags))
 		arch_local_irq_enable();
 }
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 3f1c1d6c0da1..61dd1dee7812 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -7,7 +7,7 @@
 #include <asm/asm.h>
 #include <asm/nops.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stringify.h>
 #include <linux/types.h>
@@ -55,6 +55,6 @@ l_yes:
 
 extern int arch_jump_entry_size(struct jump_entry *entry);
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index de75306b932e..d7e33c7f096b 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -23,7 +23,7 @@
 					(1ULL << (__VIRTUAL_MASK_SHIFT - \
 						  KASAN_SHADOW_SCALE_SHIFT)))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_KASAN
 void __init kasan_early_init(void);
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 8ad187462b68..5432457d2338 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -13,11 +13,12 @@
 # define KEXEC_CONTROL_PAGE_SIZE	4096
 # define KEXEC_CONTROL_CODE_MAX_SIZE	2048
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/string.h>
 #include <linux/kernel.h>
 
+#include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
 
@@ -71,41 +72,32 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 	if (oldregs) {
 		memcpy(newregs, oldregs, sizeof(*newregs));
 	} else {
+		asm volatile("mov %%" _ASM_BX ",%0" : "=m"(newregs->bx));
+		asm volatile("mov %%" _ASM_CX ",%0" : "=m"(newregs->cx));
+		asm volatile("mov %%" _ASM_DX ",%0" : "=m"(newregs->dx));
+		asm volatile("mov %%" _ASM_SI ",%0" : "=m"(newregs->si));
+		asm volatile("mov %%" _ASM_DI ",%0" : "=m"(newregs->di));
+		asm volatile("mov %%" _ASM_BP ",%0" : "=m"(newregs->bp));
+		asm volatile("mov %%" _ASM_AX ",%0" : "=m"(newregs->ax));
+		asm volatile("mov %%" _ASM_SP ",%0" : "=m"(newregs->sp));
+#ifdef CONFIG_X86_64
+		asm volatile("mov %%r8,%0" : "=m"(newregs->r8));
+		asm volatile("mov %%r9,%0" : "=m"(newregs->r9));
+		asm volatile("mov %%r10,%0" : "=m"(newregs->r10));
+		asm volatile("mov %%r11,%0" : "=m"(newregs->r11));
+		asm volatile("mov %%r12,%0" : "=m"(newregs->r12));
+		asm volatile("mov %%r13,%0" : "=m"(newregs->r13));
+		asm volatile("mov %%r14,%0" : "=m"(newregs->r14));
+		asm volatile("mov %%r15,%0" : "=m"(newregs->r15));
+#endif
+		asm volatile("mov %%ss,%k0" : "=a"(newregs->ss));
+		asm volatile("mov %%cs,%k0" : "=a"(newregs->cs));
 #ifdef CONFIG_X86_32
-		asm volatile("movl %%ebx,%0" : "=m"(newregs->bx));
-		asm volatile("movl %%ecx,%0" : "=m"(newregs->cx));
-		asm volatile("movl %%edx,%0" : "=m"(newregs->dx));
-		asm volatile("movl %%esi,%0" : "=m"(newregs->si));
-		asm volatile("movl %%edi,%0" : "=m"(newregs->di));
-		asm volatile("movl %%ebp,%0" : "=m"(newregs->bp));
-		asm volatile("movl %%eax,%0" : "=m"(newregs->ax));
-		asm volatile("movl %%esp,%0" : "=m"(newregs->sp));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("movl %%ds, %%eax;" :"=a"(newregs->ds));
-		asm volatile("movl %%es, %%eax;" :"=a"(newregs->es));
-		asm volatile("pushfl; popl %0" :"=m"(newregs->flags));
-#else
-		asm volatile("movq %%rbx,%0" : "=m"(newregs->bx));
-		asm volatile("movq %%rcx,%0" : "=m"(newregs->cx));
-		asm volatile("movq %%rdx,%0" : "=m"(newregs->dx));
-		asm volatile("movq %%rsi,%0" : "=m"(newregs->si));
-		asm volatile("movq %%rdi,%0" : "=m"(newregs->di));
-		asm volatile("movq %%rbp,%0" : "=m"(newregs->bp));
-		asm volatile("movq %%rax,%0" : "=m"(newregs->ax));
-		asm volatile("movq %%rsp,%0" : "=m"(newregs->sp));
-		asm volatile("movq %%r8,%0" : "=m"(newregs->r8));
-		asm volatile("movq %%r9,%0" : "=m"(newregs->r9));
-		asm volatile("movq %%r10,%0" : "=m"(newregs->r10));
-		asm volatile("movq %%r11,%0" : "=m"(newregs->r11));
-		asm volatile("movq %%r12,%0" : "=m"(newregs->r12));
-		asm volatile("movq %%r13,%0" : "=m"(newregs->r13));
-		asm volatile("movq %%r14,%0" : "=m"(newregs->r14));
-		asm volatile("movq %%r15,%0" : "=m"(newregs->r15));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("pushfq; popq %0" :"=m"(newregs->flags));
+		asm volatile("mov %%ds,%k0" : "=a"(newregs->ds));
+		asm volatile("mov %%es,%k0" : "=a"(newregs->es));
 #endif
+		asm volatile("pushf\n\t"
+			     "pop %0" : "=m"(newregs->flags));
 		newregs->ip = _THIS_IP_;
 	}
 }
@@ -225,6 +217,6 @@ unsigned int arch_crash_get_elfcorehdr_size(void);
 #define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index dc31b13b87a0..b51d8a4673f5 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -38,7 +38,7 @@
 #define ASM_FUNC_ALIGN		__stringify(__FUNC_ALIGN)
 #define SYM_F_ALIGN		__FUNC_ALIGN
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define RET	jmp __x86_return_thunk
@@ -50,7 +50,7 @@
 #endif
 #endif /* CONFIG_MITIGATION_RETPOLINE */
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 #define ASM_RET	"jmp __x86_return_thunk\n\t"
@@ -62,7 +62,7 @@
 #endif
 #endif /* CONFIG_MITIGATION_RETPOLINE */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the
@@ -119,33 +119,27 @@
 
 /* SYM_FUNC_START -- use for global functions */
 #define SYM_FUNC_START(name)				\
-	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */
 #define SYM_FUNC_START_NOALIGN(name)			\
-	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)	\
-	ENDBR
+	SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE)
 
 /* SYM_FUNC_START_LOCAL -- use for local functions */
 #define SYM_FUNC_START_LOCAL(name)			\
-	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */
 #define SYM_FUNC_START_LOCAL_NOALIGN(name)		\
-	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)	\
-	ENDBR
+	SYM_START(name, SYM_L_LOCAL, SYM_A_NONE)
 
 /* SYM_FUNC_START_WEAK -- use for weak functions */
 #define SYM_FUNC_START_WEAK(name)			\
-	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)	\
-	ENDBR
+	SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN)
 
 /* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */
 #define SYM_FUNC_START_WEAK_NOALIGN(name)		\
-	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
-	ENDBR
+	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
 
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index f922b682b9b4..1530ee301dfe 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -10,7 +10,7 @@
 #ifndef __X86_MEM_ENCRYPT_H__
 #define __X86_MEM_ENCRYPT_H__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/init.h>
 #include <linux/cc_platform.h>
@@ -114,6 +114,6 @@ void add_encrypt_protection_map(void);
 
 extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[];
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* __X86_MEM_ENCRYPT_H__ */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 3b496cdcb74b..8b8055a8eb9e 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -69,6 +69,18 @@ typedef struct {
 	u16 pkey_allocation_map;
 	s16 execute_only_pkey;
 #endif
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	/*
+	 * The global ASID will be a non-zero value when the process has
+	 * the same ASID across all CPUs, allowing it to make use of
+	 * hardware-assisted remote TLB invalidation like AMD INVLPGB.
+	 */
+	u16 global_asid;
+
+	/* The process is transitioning to a new global ASID number. */
+	bool asid_transition;
+#endif
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(mm)						\
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 795fdd53bd0a..2398058b6e83 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_MMU_CONTEXT_H
 #define _ASM_X86_MMU_CONTEXT_H
 
-#include <asm/desc.h>
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
 #include <linux/pkeys.h>
@@ -13,6 +12,7 @@
 #include <asm/paravirt.h>
 #include <asm/debugreg.h>
 #include <asm/gsseg.h>
+#include <asm/desc.h>
 
 extern atomic64_t last_mm_ctx_id;
 
@@ -139,6 +139,11 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 #define enter_lazy_tlb enter_lazy_tlb
 extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+#define mm_init_global_asid mm_init_global_asid
+extern void mm_init_global_asid(struct mm_struct *mm);
+
+extern void mm_free_global_asid(struct mm_struct *mm);
+
 /*
  * Init a new mm.  Used on mm copies, like at fork()
  * and on mm's that are brand-new, like at execve().
@@ -161,6 +166,8 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.execute_only_pkey = -1;
 	}
 #endif
+
+	mm_init_global_asid(mm);
 	mm_reset_untag_mask(mm);
 	init_new_context_ldt(mm);
 	return 0;
@@ -170,6 +177,7 @@ static inline int init_new_context(struct task_struct *tsk,
 static inline void destroy_context(struct mm_struct *mm)
 {
 	destroy_context_ldt(mm);
+	mm_free_global_asid(mm);
 }
 
 extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f91ab1e75f9f..5e6193dbc97e 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -77,11 +77,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return hv_tdx_hypercall(control, input_address, output_address);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[output_address], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input_address)
-				     :  "r" (output_address)
+				     : [output_address] "r" (output_address)
 				     : "cc", "memory", "r8", "r9", "r10", "r11");
 		return hv_status;
 	}
@@ -89,12 +89,12 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
-	__asm__ __volatile__("mov %4, %%r8\n"
+	__asm__ __volatile__("mov %[output_address], %%r8\n"
 			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address),
-				THUNK_TARGET(hv_hypercall_pg)
+			     : [output_address] "r" (output_address),
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -187,18 +187,18 @@ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 		return hv_tdx_hypercall(control, input1, input2);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2)
+				     : [input2] "r" (input2)
 				     : "cc", "r8", "r9", "r10", "r11");
 	} else {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2),
+				     : [input2] "r" (input2),
 				       THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 72765b2fe0d8..1aacd6b68fab 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_TCE		15 /* Enable Translation Cache Extensions */
 #define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
@@ -34,6 +35,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_TCE		(1<<_EFER_TCE)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /*
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 001853541f1e..9397a319d165 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -4,7 +4,7 @@
 
 #include "msr-index.h"
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/asm.h>
 #include <asm/errno.h>
@@ -397,5 +397,5 @@ static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
 	return wrmsr_safe_regs(regs);
 }
 #endif  /* CONFIG_SMP */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_MSR_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 41a0ebb699ec..f677382093f3 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -56,6 +56,8 @@ int __register_nmi_handler(unsigned int, struct nmiaction *);
 
 void unregister_nmi_handler(unsigned int, const char *);
 
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler);
+
 void stop_nmi(void);
 void restart_nmi(void);
 void local_touch_nmi(void);
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
index 1c1b7550fa55..cd94221d8335 100644
--- a/arch/x86/include/asm/nops.h
+++ b/arch/x86/include/asm/nops.h
@@ -82,7 +82,7 @@
 #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
 #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern const unsigned char * const x86_nops[];
 #endif
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index aee26bb8230f..804b66a7686a 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -12,7 +12,6 @@
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 /*
  * Call depth tracking for Intel SKL CPUs to address the RSB underflow
@@ -78,21 +77,21 @@
 #include <asm/asm-offsets.h>
 
 #define CREDIT_CALL_DEPTH					\
-	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	$-1, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH					\
 	xor	%eax, %eax;					\
 	bts	$63, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH_FROM_CALL				\
 	movb	$0xfc, %al;					\
 	shl	$56, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #define INCREMENT_CALL_DEPTH					\
-	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	sarq	$5, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #else
@@ -177,7 +176,7 @@
 	add	$(BITS_PER_LONG/8), %_ASM_SP;		\
 	lfence;
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /*
  * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions
@@ -335,7 +334,7 @@
 #define CLEAR_BRANCH_HISTORY_VMEXIT
 #endif
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
 extern retpoline_thunk_t __x86_indirect_thunk_array[];
@@ -387,6 +386,8 @@ extern void call_depth_return_thunk(void);
 		    __stringify(INCREMENT_CALL_DEPTH),		\
 		    X86_FEATURE_CALL_DEPTH)
 
+DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 DECLARE_PER_CPU(u64, __x86_call_count);
 DECLARE_PER_CPU(u64, __x86_ret_count);
@@ -602,6 +603,6 @@ static __always_inline void mds_idle_clear_cpu_buffers(void)
 		mds_clear_cpu_buffers();
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 46d7e06763c9..e0125afa53fb 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -45,7 +45,7 @@
 #define ORC_TYPE_REGS			3
 #define ORC_TYPE_REGS_PARTIAL		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/byteorder.h>
 
 /*
@@ -73,6 +73,6 @@ struct orc_entry {
 #endif
 } __packed;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index c9fe207916f4..9265f2fca99a 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -14,7 +14,7 @@
 #include <asm/page_32.h>
 #endif	/* CONFIG_X86_64 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct page;
 
@@ -84,7 +84,7 @@ static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits)
 	return __canonical_address(vaddr, vaddr_bits) == vaddr;
 }
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index 580d71aca65a..0c623706cb7e 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -4,7 +4,7 @@
 
 #include <asm/page_32_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define __phys_addr_nodebug(x)	((x) - PAGE_OFFSET)
 #ifdef CONFIG_DEBUG_VIRTUAL
@@ -26,6 +26,6 @@ static inline void copy_page(void *to, void *from)
 {
 	memcpy(to, from, PAGE_SIZE);
 }
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_PAGE_32_H */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index faf9cc1c14bb..a9b62e0e6f79 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -11,8 +11,8 @@
  * a virtual address space of one gigabyte, which limits the
  * amount of physical memory you can use to about 950MB.
  *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ * If you want more physical memory than this then see the CONFIG_VMSPLIT_2G
+ * and CONFIG_HIGHMEM4G options in the kernel configuration.
  */
 #define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
 #define __PAGE_OFFSET		__PAGE_OFFSET_BASE
@@ -63,7 +63,7 @@
  */
 #define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * This much address space is reserved for vmalloc() and iomap()
@@ -75,6 +75,6 @@ extern int sysctl_legacy_va_layout;
 extern void find_low_pfn_range(void);
 extern void setup_bootmem_allocator(void);
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_PAGE_32_DEFS_H */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d63576608ce7..d3aab6f4e59a 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -4,7 +4,7 @@
 
 #include <asm/page_64_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -55,11 +55,12 @@ static inline void clear_page(void *page)
 			   clear_page_rep, X86_FEATURE_REP_GOOD,
 			   clear_page_erms, X86_FEATURE_ERMS,
 			   "=D" (page),
-			   "D" (page)
-			   : "cc", "memory", "rax", "rcx");
+			   "D" (page),
+			   "cc", "memory", "rax", "rcx");
 }
 
 void copy_page(void *to, void *from);
+KCFI_REFERENCE(copy_page);
 
 #ifdef CONFIG_X86_5LEVEL
 /*
@@ -94,7 +95,7 @@ static __always_inline unsigned long task_size_max(void)
 }
 #endif	/* CONFIG_X86_5LEVEL */
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 # define __HAVE_ARCH_GATE_AREA 1
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 06ef25411d62..1faa8f88850a 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PAGE_64_DEFS_H
 #define _ASM_X86_PAGE_64_DEFS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/kaslr.h>
 #endif
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 974688973cf6..9f77bf03d747 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -43,7 +43,7 @@
 #define IOREMAP_MAX_ORDER       (PMD_SHIFT)
 #endif	/* CONFIG_X86_64 */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
 extern phys_addr_t physical_mask;
@@ -66,6 +66,6 @@ bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn);
 
 extern void initmem_init(void);
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif	/* _ASM_X86_PAGE_DEFS_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 041aff51eb50..bed346bfac89 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -6,7 +6,7 @@
 
 #include <asm/paravirt_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct mm_struct;
 #endif
 
@@ -15,7 +15,7 @@ struct mm_struct;
 #include <asm/asm.h>
 #include <asm/nospec-branch.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
@@ -91,11 +91,6 @@ static inline void __flush_tlb_multi(const struct cpumask *cpumask,
 	PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info);
 }
 
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
-}
-
 static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 	PVOP_VCALL1(mmu.exit_mmap, mm);
@@ -720,7 +715,7 @@ static __always_inline unsigned long arch_local_irq_save(void)
 extern void default_banner(void);
 void native_pv_lock_init(void) __init;
 
-#else  /* __ASSEMBLY__ */
+#else  /* __ASSEMBLER__ */
 
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_PARAVIRT_XXL
@@ -740,18 +735,18 @@ void native_pv_lock_init(void) __init;
 #endif /* CONFIG_PARAVIRT_XXL */
 #endif	/* CONFIG_X86_64 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #else  /* CONFIG_PARAVIRT */
 # define default_banner x86_init_noop
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 static inline void native_pv_lock_init(void)
 {
 }
 #endif
 #endif /* !CONFIG_PARAVIRT */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifndef CONFIG_PARAVIRT_XXL
 static inline void paravirt_enter_mmap(struct mm_struct *mm)
 {
@@ -769,5 +764,5 @@ static inline void paravirt_set_cap(void)
 {
 }
 #endif
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fea56b04f436..62912023b46f 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -4,7 +4,7 @@
 
 #ifdef CONFIG_PARAVIRT
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 #include <asm/desc_defs.h>
@@ -134,8 +134,6 @@ struct pv_mmu_ops {
 	void (*flush_tlb_multi)(const struct cpumask *cpus,
 				const struct flush_tlb_info *info);
 
-	void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
-
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
 	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
@@ -242,9 +240,17 @@ extern struct paravirt_patch_template pv_ops;
 
 #define paravirt_ptr(op)	[paravirt_opptr] "m" (pv_ops.op)
 
-int paravirt_disable_iospace(void);
-
-/* This generates an indirect call based on the operation type number. */
+/*
+ * This generates an indirect call based on the operation type number.
+ *
+ * Since alternatives run after enabling CET/IBT -- the latter setting/clearing
+ * capabilities and the former requiring all capabilities being finalized --
+ * these indirect calls are subject to IBT and the paravirt stubs should have
+ * ENDBR on.
+ *
+ * OTOH since this is effectively a __nocfi indirect call, the paravirt stubs
+ * don't need to bother with CFI prefixes.
+ */
 #define PARAVIRT_CALL					\
 	ANNOTATE_RETPOLINE_SAFE				\
 	"call *%[paravirt_opptr];"
@@ -519,7 +525,7 @@ unsigned long pv_native_read_cr2(void);
 
 #define paravirt_nop	((void *)nop_func)
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define ALT_NOT_XEN	ALT_NOT(X86_FEATURE_XENPV)
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 08f5f61690b7..105db2d33c7b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -10,7 +10,7 @@
 # define __percpu_rel
 #endif
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #ifdef CONFIG_SMP
 # define __percpu		%__percpu_seg:
@@ -20,14 +20,9 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#ifdef CONFIG_X86_64_SMP
-# define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
-#else
-# define INIT_PER_CPU_VAR(var)  var
-#endif
-
 #else /* !__ASSEMBLY__: */
 
+#include <linux/args.h>
 #include <linux/build_bug.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
@@ -41,12 +36,7 @@
 # define __seg_fs		__attribute__((address_space(__seg_fs)))
 #endif
 
-#ifdef CONFIG_X86_64
-# define __percpu_seg_override	__seg_gs
-#else
-# define __percpu_seg_override	__seg_fs
-#endif
-
+#define __percpu_seg_override	CONCATENATE(__seg_, __percpu_seg)
 #define __percpu_prefix		""
 
 #else /* !CONFIG_CC_HAS_NAMED_AS: */
@@ -98,22 +88,6 @@
 #define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
 /*
- * Initialized pointers to per-CPU variables needed for the boot
- * processor need to use these macros to get the proper address
- * offset from __per_cpu_load on SMP.
- *
- * There also must be an entry in vmlinux_64.lds.S
- */
-#define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(var) init_per_cpu_var(var)
-
-#ifdef CONFIG_X86_64_SMP
-# define init_per_cpu_var(var)  init_per_cpu__##var
-#else
-# define init_per_cpu_var(var)  var
-#endif
-
-/*
  * For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though).
  */
@@ -128,15 +102,10 @@
 #define __pcpu_cast_4(val)	((u32)(((unsigned long) val) & 0xffffffff))
 #define __pcpu_cast_8(val)	((u64)(val))
 
-#define __pcpu_op1_1(op, dst)	op "b " dst
-#define __pcpu_op1_2(op, dst)	op "w " dst
-#define __pcpu_op1_4(op, dst)	op "l " dst
-#define __pcpu_op1_8(op, dst)	op "q " dst
-
-#define __pcpu_op2_1(op, src, dst) op "b " src ", " dst
-#define __pcpu_op2_2(op, src, dst) op "w " src ", " dst
-#define __pcpu_op2_4(op, src, dst) op "l " src ", " dst
-#define __pcpu_op2_8(op, src, dst) op "q " src ", " dst
+#define __pcpu_op_1(op)		op "b "
+#define __pcpu_op_2(op)		op "w "
+#define __pcpu_op_4(op)		op "l "
+#define __pcpu_op_8(op)		op "q "
 
 #define __pcpu_reg_1(mod, x)	mod "q" (x)
 #define __pcpu_reg_2(mod, x)	mod "r" (x)
@@ -168,7 +137,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+	asm qual (__pcpu_op_##size("mov")				\
+		  __percpu_arg([var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "m" (__my_cpu_var(_var)));				\
 									\
@@ -184,7 +154,8 @@ do {									\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+	asm qual (__pcpu_op_##size("mov") "%[val], "			\
+		  __percpu_arg([var])					\
 	    : [var] "=m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -201,7 +172,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+	asm(__pcpu_op_##size("mov")					\
+	    __force_percpu_arg(a[var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "i" (&(_var)));					\
 									\
@@ -210,7 +182,7 @@ do {									\
 
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
-	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size(op) __percpu_arg([var])		\
 	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
@@ -223,7 +195,7 @@ do {									\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
+	asm qual (__pcpu_op_##size(op) "%[val], " __percpu_arg([var])	\
 	    : [var] "+m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -259,8 +231,8 @@ do {									\
 ({									\
 	__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val);	\
 									\
-	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
-				     __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("xadd") "%[tmp], "			\
+		  __percpu_arg([var])					\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : : "memory");					\
@@ -303,8 +275,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval);	\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  : [oval] "+a" (pco_old__),				\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
@@ -320,8 +292,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = *pco_oval__;			\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
 		    [oval] "+a" (pco_old__),				\
@@ -579,7 +551,7 @@ do {									\
  * it is accessed while this_cpu_read_stable() allows the value to be cached.
  * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across CPUs.  The current users include
- * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * current_task and cpu_current_top_of_stack, both of which are
  * actually per-thread variables implemented as per-CPU variables and
  * thus stable for the duration of the respective task.
  */
@@ -614,9 +586,9 @@ do {									\
 #include <asm-generic/percpu.h>
 
 /* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off);
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #ifdef CONFIG_SMP
 
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd4841231bb9..a33147520044 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -29,11 +29,6 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
 static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
-/*
- * Flags to use when allocating a user page table page.
- */
-extern gfp_t __userpte_alloc_gfp;
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 4a12c276b181..66425424ce91 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PGTABLE_2LEVEL_DEFS_H
 #define _ASM_X86_PGTABLE_2LEVEL_DEFS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 typedef unsigned long	pteval_t;
@@ -16,7 +16,7 @@ typedef union {
 	pteval_t pte;
 	pteval_t pte_low;
 } pte_t;
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #define SHARED_KERNEL_PMD	0
 
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 80911349519e..9d5b257d44e3 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_PGTABLE_3LEVEL_DEFS_H
 #define _ASM_X86_PGTABLE_3LEVEL_DEFS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 typedef u64	pteval_t;
@@ -25,7 +25,7 @@ typedef union {
 	};
 	pmdval_t pmd;
 } pmd_t;
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
 
diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
index a0c1525f1b6f..e12e52ae8083 100644
--- a/arch/x86/include/asm/pgtable-invert.h
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_PGTABLE_INVERT_H
 #define _ASM_PGTABLE_INVERT_H 1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * A clear pte value is special, and doesn't get inverted.
@@ -36,6 +36,6 @@ static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
 	return val;
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 593f10aabd45..7bd6bd6df4a1 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -15,7 +15,7 @@
 		     cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)))	\
 	 : (prot))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/spinlock.h>
 #include <asm/x86_init.h>
 #include <asm/pkru.h>
@@ -973,7 +973,7 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 }
 #endif  /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 
 #ifdef CONFIG_X86_32
@@ -982,7 +982,7 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 # include <asm/pgtable_64.h>
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/mm_types.h>
 #include <linux/mmdebug.h>
 #include <linux/log2.h>
@@ -1233,12 +1233,12 @@ static inline int pgd_none(pgd_t pgd)
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
 #define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern int direct_gbpages;
 void init_mem_mapping(void);
@@ -1812,6 +1812,6 @@ bool arch_is_platform_page(u64 paddr);
 	WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \
 	set_pgd(pgdp, pgd); \
 })
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 7d4ad8907297..b612cc57a4d3 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -13,7 +13,7 @@
  * This file contains the functions and defines necessary to modify and use
  * the i386 page table tree.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/processor.h>
 #include <linux/threads.h>
 #include <asm/paravirt.h>
@@ -45,7 +45,7 @@ do {						\
 	flush_tlb_one_kernel((vaddr));		\
 } while (0)
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * This is used to calculate the .brk reservation for initial pagetables.
diff --git a/arch/x86/include/asm/pgtable_32_areas.h b/arch/x86/include/asm/pgtable_32_areas.h
index b6355416a15a..921148b42967 100644
--- a/arch/x86/include/asm/pgtable_32_areas.h
+++ b/arch/x86/include/asm/pgtable_32_areas.h
@@ -13,7 +13,7 @@
  */
 #define VMALLOC_OFFSET	(8 * 1024 * 1024)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern bool __vmalloc_start_set; /* set once high_memory is set */
 #endif
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index d1426b64c1b9..b89f8f1194a9 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -5,7 +5,7 @@
 #include <linux/const.h>
 #include <asm/pgtable_64_types.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * This file contains the functions and defines necessary to modify and use
@@ -270,7 +270,7 @@ static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 
 #include <asm/pgtable-invert.h>
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define l4_index(x)	(((x) >> 39) & 511)
 #define pud_index(x)	(((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
@@ -291,5 +291,5 @@ L3_START_KERNEL = pud_index(__START_KERNEL_map)
 	i = i + 1 ;					\
 	.endr
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index ec68f8369bdc..5bb782d856f2 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -4,7 +4,7 @@
 
 #include <asm/sparsemem.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <asm/kaslr.h>
 
@@ -44,7 +44,7 @@ static inline bool pgtable_l5_enabled(void)
 extern unsigned int pgdir_shift;
 extern unsigned int ptrs_per_p4d;
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #define SHARED_KERNEL_PMD	0
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4b804531b03c..b2ed8198d5cd 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -33,6 +33,7 @@
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
+#define _PAGE_BIT_KERNEL_4K	_PAGE_BIT_SOFTW3 /* page must not be converted to large */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
@@ -64,6 +65,7 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_KERNEL_4K	(_AT(pteval_t, 1) << _PAGE_BIT_KERNEL_4K)
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 #define _PAGE_PKEY_BIT0	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0)
 #define _PAGE_PKEY_BIT1	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1)
@@ -164,7 +166,7 @@
  * to have the WB mode at index 0 (all bits clear). This is the default
  * right now and likely would break too much if changed.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 enum page_cache_mode {
 	_PAGE_CACHE_MODE_WB       = 0,
 	_PAGE_CACHE_MODE_WC       = 1,
@@ -239,7 +241,7 @@ enum page_cache_mode {
 #define __PAGE_KERNEL_IO_NOCACHE	__PAGE_KERNEL_NOCACHE
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define __PAGE_KERNEL_ENC	(__PAGE_KERNEL    | _ENC)
 #define __PAGE_KERNEL_ENC_WP	(__PAGE_KERNEL_WP | _ENC)
@@ -262,7 +264,7 @@ enum page_cache_mode {
 #define PAGE_KERNEL_IO		__pgprot_mask(__PAGE_KERNEL_IO)
 #define PAGE_KERNEL_IO_NOCACHE	__pgprot_mask(__PAGE_KERNEL_IO_NOCACHE)
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 /*
  * early identity mapping  pte attrib macros.
@@ -281,7 +283,7 @@ enum page_cache_mode {
 # include <asm/pgtable_64_types.h>
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -580,6 +582,6 @@ extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
 					  unsigned long page_flags);
 extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 					    unsigned long numpages);
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 919909d8cb77..578441db09f0 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -4,10 +4,11 @@
 
 #include <asm/rmwcc.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 #include <linux/static_call_types.h>
 
+DECLARE_PER_CPU_CACHE_HOT(int, __preempt_count);
+
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -23,18 +24,18 @@
  */
 static __always_inline int preempt_count(void)
 {
-	return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED;
+	return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void preempt_count_set(int pc)
 {
 	int old, new;
 
-	old = raw_cpu_read_4(pcpu_hot.preempt_count);
+	old = raw_cpu_read_4(__preempt_count);
 	do {
 		new = (old & PREEMPT_NEED_RESCHED) |
 			(pc & ~PREEMPT_NEED_RESCHED);
-	} while (!raw_cpu_try_cmpxchg_4(pcpu_hot.preempt_count, &old, new));
+	} while (!raw_cpu_try_cmpxchg_4(__preempt_count, &old, new));
 }
 
 /*
@@ -43,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
 #define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	per_cpu(pcpu_hot.preempt_count, (cpu)) = PREEMPT_DISABLED; \
+	per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
 } while (0)
 
 /*
@@ -57,17 +58,17 @@ static __always_inline void preempt_count_set(int pc)
 
 static __always_inline void set_preempt_need_resched(void)
 {
-	raw_cpu_and_4(pcpu_hot.preempt_count, ~PREEMPT_NEED_RESCHED);
+	raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	raw_cpu_or_4(pcpu_hot.preempt_count, PREEMPT_NEED_RESCHED);
+	raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(raw_cpu_read_4(pcpu_hot.preempt_count) & PREEMPT_NEED_RESCHED);
+	return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
 }
 
 /*
@@ -76,12 +77,12 @@ static __always_inline bool test_preempt_need_resched(void)
 
 static __always_inline void __preempt_count_add(int val)
 {
-	raw_cpu_add_4(pcpu_hot.preempt_count, val);
+	raw_cpu_add_4(__preempt_count, val);
 }
 
 static __always_inline void __preempt_count_sub(int val)
 {
-	raw_cpu_add_4(pcpu_hot.preempt_count, -val);
+	raw_cpu_add_4(__preempt_count, -val);
 }
 
 /*
@@ -91,7 +92,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
+	return GEN_UNARY_RMWcc("decl", __my_cpu_var(__preempt_count), e,
 			       __percpu_arg([var]));
 }
 
@@ -100,7 +101,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset);
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPTION
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c0cd10182e90..7a3918308a36 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -60,18 +60,13 @@ struct vm86;
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
-enum tlb_infos {
-	ENTRIES,
-	NR_INFO
-};
-
-extern u16 __read_mostly tlb_lli_4k[NR_INFO];
-extern u16 __read_mostly tlb_lli_2m[NR_INFO];
-extern u16 __read_mostly tlb_lli_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4k[NR_INFO];
-extern u16 __read_mostly tlb_lld_2m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_1g[NR_INFO];
+extern u16 __read_mostly tlb_lli_4k;
+extern u16 __read_mostly tlb_lli_2m;
+extern u16 __read_mostly tlb_lli_4m;
+extern u16 __read_mostly tlb_lld_4k;
+extern u16 __read_mostly tlb_lld_2m;
+extern u16 __read_mostly tlb_lld_4m;
+extern u16 __read_mostly tlb_lld_1g;
 
 /*
  * CPU type and hardware bug flags. Kept separately for each CPU.
@@ -234,7 +229,7 @@ static inline unsigned long long l1tf_pfn_limit(void)
 void init_cpu_devs(void);
 void get_cpu_vendor(struct cpuinfo_x86 *c);
 extern void early_cpu_init(void);
-extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void identify_secondary_cpu(unsigned int cpu);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 
@@ -420,37 +415,33 @@ struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
 } __aligned(IRQ_STACK_SIZE);
 
+DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
 #ifdef CONFIG_X86_64
-struct fixed_percpu_data {
-	/*
-	 * GCC hardcodes the stack canary as %gs:40.  Since the
-	 * irq_stack is the object at %gs:0, we reserve the bottom
-	 * 48 bytes of the irq stack for the canary.
-	 *
-	 * Once we are willing to require -mstack-protector-guard-symbol=
-	 * support for x86_64 stackprotector, we can get rid of this.
-	 */
-	char		gs_base[40];
-	unsigned long	stack_canary;
-};
+DECLARE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
+#else
+DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
+#endif
 
-DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack);
+/* const-qualified alias provided by the linker. */
+DECLARE_PER_CPU_CACHE_HOT(const unsigned long __percpu_seg_override,
+			  const_cpu_current_top_of_stack);
 
+#ifdef CONFIG_X86_64
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+	return per_cpu_offset(cpu);
+#else
+	return 0;
+#endif
 }
 
 extern asmlinkage void entry_SYSCALL32_ignore(void);
 
 /* Save actual FS/GS selectors and bases to current->thread */
 void current_save_fsgs(void);
-#else	/* X86_64 */
-#ifdef CONFIG_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
-#endif
-#endif	/* !X86_64 */
+#endif	/* X86_64 */
 
 struct perf_event;
 
@@ -561,9 +552,9 @@ static __always_inline unsigned long current_top_of_stack(void)
 	 *  entry trampoline.
 	 */
 	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
-		return this_cpu_read_const(const_pcpu_hot.top_of_stack);
+		return this_cpu_read_const(const_cpu_current_top_of_stack);
 
-	return this_cpu_read_stable(pcpu_hot.top_of_stack);
+	return this_cpu_read_stable(cpu_current_top_of_stack);
 }
 
 static __always_inline bool on_thread_stack(void)
@@ -668,8 +659,6 @@ static __always_inline void prefetchw(const void *x)
 	.sysenter_cs		= __KERNEL_CS,				  \
 }
 
-#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
-
 #else
 extern unsigned long __top_init_kernel_stack[];
 
@@ -677,8 +666,6 @@ extern unsigned long __top_init_kernel_stack[];
 	.sp	= (unsigned long)&__top_init_kernel_stack,		\
 }
 
-extern unsigned long KSTK_ESP(struct task_struct *task);
-
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -692,6 +679,7 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 #define TASK_UNMAPPED_BASE		__TASK_UNMAPPED_BASE(TASK_SIZE_LOW)
 
 #define KSTK_EIP(task)		(task_pt_regs(task)->ip)
+#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 /* Get/set a process' ability to use the timestamp counter instruction */
 #define GET_TSC_CTL(adr)	get_tsc_mode((adr))
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 365798cb4408..5d0dbab85264 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -8,7 +8,7 @@
 
 #ifndef _ASM_X86_PROM_H
 #define _ASM_X86_PROM_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/of.h>
 #include <linux/types.h>
@@ -33,5 +33,5 @@ static inline void x86_flattree_get_config(void) { }
 
 extern char cmd_line[COMMAND_LINE_SIZE];
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 484f4f0131a5..05224a695872 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -15,7 +15,6 @@ void entry_SYSCALL_64(void);
 void entry_SYSCALL_64_safe_stack(void);
 void entry_SYSRETQ_unsafe_stack(void);
 void entry_SYSRETQ_end(void);
-long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
 #ifdef CONFIG_X86_32
@@ -41,6 +40,6 @@ void x86_configure_nx(void);
 
 extern int reboot_force;
 
-long do_arch_prctl_common(int option, unsigned long arg2);
+long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index ab167c96b9ab..88d0a1ab1f77 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_PTI_H
 #define _ASM_X86_PTI_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
@@ -11,5 +11,5 @@ extern void pti_finalize(void);
 static inline void pti_check_boottime_disable(void) { }
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 5a83fbd9bc0b..50f75467f73d 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -6,7 +6,7 @@
 #include <asm/page_types.h>
 #include <uapi/asm/ptrace.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef __i386__
 
 struct pt_regs {
@@ -469,5 +469,5 @@ extern int do_set_thread_area(struct task_struct *p, int idx,
 # define do_set_thread_area_64(p, s, t)	(0)
 #endif
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_PTRACE_H */
diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h
index 5528e9325049..2fee5e9f1ccc 100644
--- a/arch/x86/include/asm/purgatory.h
+++ b/arch/x86/include/asm/purgatory.h
@@ -2,10 +2,10 @@
 #ifndef _ASM_X86_PURGATORY_H
 #define _ASM_X86_PURGATORY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/purgatory.h>
 
 extern void purgatory(void);
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif /* _ASM_PURGATORY_H */
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 1436226efe3e..b9fece5fc96d 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_PVCLOCK_ABI_H
 #define _ASM_X86_PVCLOCK_ABI_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * These structs MUST NOT be changed.
@@ -44,5 +44,5 @@ struct pvclock_wall_clock {
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
 /* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
 #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 87e5482acd0d..f607081a022a 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -9,7 +9,7 @@
 #define TH_FLAGS_SME_ACTIVE_BIT		0
 #define TH_FLAGS_SME_ACTIVE		BIT(TH_FLAGS_SME_ACTIVE_BIT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <asm/io.h>
@@ -95,6 +95,6 @@ void reserve_real_mode(void);
 void load_trampoline_pgtable(void);
 void init_real_mode(void);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ARCH_X86_REALMODE_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
deleted file mode 100644
index e9187ddd3d1f..000000000000
--- a/arch/x86/include/asm/required-features.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#define _ASM_X86_REQUIRED_FEATURES_H
-
-/* Define minimum CPUID feature set for kernel These bits are checked
-   really early to actually display a visible error message before the
-   kernel dies.  Make sure to assign features to the proper mask!
-
-   Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
-
-   The real information is in arch/x86/Kconfig.cpu, this just converts
-   the CONFIGs into a bitmask */
-
-#ifndef CONFIG_MATH_EMULATION
-# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
-#else
-# define NEED_FPU	0
-#endif
-
-#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-#else
-# define NEED_PAE	0
-#endif
-
-#ifdef CONFIG_X86_CMPXCHG64
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
-#else
-# define NEED_CX8	0
-#endif
-
-#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
-# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
-#else
-# define NEED_CMOV	0
-#endif
-
-# define NEED_3DNOW	0
-
-#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
-# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
-#else
-# define NEED_NOPL	0
-#endif
-
-#ifdef CONFIG_MATOM
-# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
-#else
-# define NEED_MOVBE	0
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
-/* Paravirtualized systems may not have PSE or PGE available */
-#define NEED_PSE	0
-#define NEED_PGE	0
-#else
-#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
-#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
-#endif
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
-#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
-#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
-#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
-#else
-#define NEED_PSE	0
-#define NEED_MSR	0
-#define NEED_PGE	0
-#define NEED_FXSR	0
-#define NEED_XMM	0
-#define NEED_XMM2	0
-#define NEED_LM		0
-#endif
-
-#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
-			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
-			 NEED_XMM|NEED_XMM2)
-#define SSE_MASK	(NEED_XMM|NEED_XMM2)
-
-#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
-
-#define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	(NEED_MOVBE)
-#define REQUIRED_MASK5	0
-#define REQUIRED_MASK6	0
-#define REQUIRED_MASK7	0
-#define REQUIRED_MASK8	0
-#define REQUIRED_MASK9	0
-#define REQUIRED_MASK10	0
-#define REQUIRED_MASK11	0
-#define REQUIRED_MASK12	0
-#define REQUIRED_MASK13	0
-#define REQUIRED_MASK14	0
-#define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
-#define REQUIRED_MASK17	0
-#define REQUIRED_MASK18	0
-#define REQUIRED_MASK19	0
-#define REQUIRED_MASK20	0
-#define REQUIRED_MASK21	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 363266cbcada..3821ee3fae35 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -29,7 +29,7 @@ cc_label:	c = true;						\
 #define __GEN_RMWcc(fullop, _var, cc, clobbers, ...)			\
 ({									\
 	bool c;								\
-	asm volatile (fullop CC_SET(cc)					\
+	asm_inline volatile (fullop CC_SET(cc)				\
 			: [var] "+m" (_var), CC_OUT(cc) (c)		\
 			: __VA_ARGS__ : clobbers);			\
 	c;								\
diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h
index 6652ebddfd02..8d983cfd06ea 100644
--- a/arch/x86/include/asm/runtime-const.h
+++ b/arch/x86/include/asm/runtime-const.h
@@ -2,6 +2,18 @@
 #ifndef _ASM_RUNTIME_CONST_H
 #define _ASM_RUNTIME_CONST_H
 
+#ifdef __ASSEMBLY__
+
+.macro RUNTIME_CONST_PTR sym reg
+	movq	$0x0123456789abcdef, %\reg
+	1:
+	.pushsection runtime_ptr_\sym, "a"
+	.long	1b - 8 - .
+	.popsection
+.endm
+
+#else /* __ASSEMBLY__ */
+
 #define runtime_const_ptr(sym) ({				\
 	typeof(sym) __ret;					\
 	asm_inline("mov %1,%0\n1:\n"				\
@@ -58,4 +70,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long),
 	}
 }
 
+#endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 9d6411c65920..77d8f49b92bd 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -233,7 +233,7 @@
 #define VDSO_CPUNODE_BITS		12
 #define VDSO_CPUNODE_MASK		0xfff
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* Helper functions to store/load CPU and node numbers */
 
@@ -265,7 +265,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
 		*node = (p >> VDSO_CPUNODE_BITS);
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #ifdef __KERNEL__
 
@@ -286,7 +286,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node)
  */
 #define XEN_EARLY_IDT_HANDLER_SIZE (8 + ENDBR_INSN_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 extern void early_ignore_irq(void);
@@ -350,7 +350,7 @@ static inline void __loadsegment_fs(unsigned short value)
 #define savesegment(seg, value)				\
 	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SEGMENT_H */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index cc62ef70ccc0..8d9f1c9aaa4c 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -2,7 +2,6 @@
 #ifndef _ASM_X86_SET_MEMORY_H
 #define _ASM_X86_SET_MEMORY_H
 
-#include <linux/mm.h>
 #include <asm/page.h>
 #include <asm-generic/set_memory.h>
 
@@ -38,7 +37,6 @@ int set_memory_rox(unsigned long addr, int numpages);
  * The caller is required to take care of these.
  */
 
-int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot);
 int _set_memory_uc(unsigned long addr, int numpages);
 int _set_memory_wc(unsigned long addr, int numpages);
 int _set_memory_wt(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 85f4fde3515c..ad9212df0ec0 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -27,7 +27,7 @@
 #define OLD_CL_ADDRESS		0x020	/* Relative to real mode data */
 #define NEW_CL_POINTER		0x228	/* Relative to real mode data */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cache.h>
 
 #include <asm/bootparam.h>
@@ -46,6 +46,7 @@ void setup_bios_corruption_check(void);
 void early_platform_quirks(void);
 
 extern unsigned long saved_video_mode;
+extern unsigned long acpi_realmode_flags;
 
 extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
@@ -141,7 +142,7 @@ extern bool builtin_cmdline_added __ro_after_init;
 #define builtin_cmdline_added 0
 #endif
 
-#else  /* __ASSEMBLY */
+#else  /* __ASSEMBLER__ */
 
 .macro __RESERVE_BRK name, size
 	.pushsection .bss..brk, "aw"
@@ -153,6 +154,6 @@ SYM_DATA_END(__brk_\name)
 
 #define RESERVE_BRK(name, size) __RESERVE_BRK name, size
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SETUP_H */
diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h
index 77c51111a893..7bb16f843c93 100644
--- a/arch/x86/include/asm/setup_data.h
+++ b/arch/x86/include/asm/setup_data.h
@@ -4,7 +4,7 @@
 
 #include <uapi/asm/setup_data.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct pci_setup_rom {
 	struct setup_data data;
@@ -27,6 +27,6 @@ struct efi_setup_data {
 	u64 reserved[8];
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index fcbbef484a78..a28ff6b14145 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -106,7 +106,7 @@
 #define TDX_PS_1G	2
 #define TDX_PS_NR	(TDX_PS_1G + 1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler_attributes.h>
 
@@ -177,5 +177,5 @@ static __always_inline u64 hcall_func(u64 exit_reason)
         return exit_reason;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_SHARED_TDX_H */
diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 4cb77e004615..ba6f2fe43848 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_SHSTK_H
 #define _ASM_X86_SHSTK_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 struct task_struct;
@@ -37,6 +37,6 @@ static inline int shstk_update_last_frame(unsigned long val) { return 0; }
 static inline bool shstk_is_enabled(void) { return false; }
 #endif /* CONFIG_X86_USER_SHADOW_STACK */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SHSTK_H */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 4a4043ca6493..c72d46175374 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_SIGNAL_H
 #define _ASM_X86_SIGNAL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/linkage.h>
 
 /* Most things should be clean enough to redefine this at will, if care
@@ -28,9 +28,9 @@ typedef struct {
 #define SA_IA32_ABI	0x02000000u
 #define SA_X32_ABI	0x01000000u
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #include <uapi/asm/signal.h>
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define __ARCH_HAS_SA_RESTORER
 
@@ -101,5 +101,5 @@ struct pt_regs;
 
 #endif /* !__i386__ */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_SIGNAL_H */
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index 2de1e5a75c57..daea94c2993c 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -13,7 +13,7 @@
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define ASM_CLAC \
 	ALTERNATIVE "", "clac", X86_FEATURE_SMAP
@@ -21,7 +21,7 @@
 #define ASM_STAC \
 	ALTERNATIVE "", "stac", X86_FEATURE_SMAP
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 static __always_inline void clac(void)
 {
@@ -61,6 +61,6 @@ static __always_inline void smap_restore(unsigned long flags)
 #define ASM_STAC \
 	ALTERNATIVE("", "stac", X86_FEATURE_SMAP)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_SMAP_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698f..0c1c68039d6f 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -1,12 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_SMP_H
 #define _ASM_X86_SMP_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 
 #include <asm/cpumask.h>
-#include <asm/current.h>
-#include <asm/thread_info.h>
+
+DECLARE_PER_CPU_CACHE_HOT(int, cpu_number);
 
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
@@ -114,13 +115,12 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
+void __noreturn mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-void smp_store_cpu_info(int id);
-
 asmlinkage __visible void smp_reboot_interrupt(void);
 __visible void smp_reschedule_interrupt(struct pt_regs *regs);
 __visible void smp_call_function_interrupt(struct pt_regs *regs);
@@ -133,14 +133,8 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
  * This function is needed by all SMP systems. It must _always_ be valid
  * from the initial startup.
  */
-#define raw_smp_processor_id()  this_cpu_read(pcpu_hot.cpu_number)
-#define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number)
-
-#ifdef CONFIG_X86_32
-extern int safe_smp_processor_id(void);
-#else
-# define safe_smp_processor_id()	smp_processor_id()
-#endif
+#define raw_smp_processor_id()  this_cpu_read(cpu_number)
+#define __smp_processor_id() __this_cpu_read(cpu_number)
 
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
@@ -164,6 +158,8 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);
 }
+
+static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
@@ -175,7 +171,7 @@ extern void nmi_selftest(void);
 extern unsigned int smpboot_control;
 extern unsigned long apic_mmio_base;
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /* Control bits for startup_64 */
 #define STARTUP_READ_APICID	0x80000000
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 03e7c2d49559..6266d6b9e0b8 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -42,14 +42,14 @@ static __always_inline void native_write_cr2(unsigned long val)
 	asm volatile("mov %0,%%cr2": : "r" (val) : "memory");
 }
 
-static inline unsigned long __native_read_cr3(void)
+static __always_inline unsigned long __native_read_cr3(void)
 {
 	unsigned long val;
 	asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
 	return val;
 }
 
-static inline void native_write_cr3(unsigned long val)
+static __always_inline void native_write_cr3(unsigned long val)
 {
 	asm volatile("mov %0,%%cr3": : "r" (val) : "memory");
 }
@@ -176,9 +176,8 @@ static __always_inline void clflush(volatile void *__p)
 
 static inline void clflushopt(volatile void *__p)
 {
-	alternative_io(".byte 0x3e; clflush %0",
-		       ".byte 0x66; clflush %0",
-		       X86_FEATURE_CLFLUSHOPT,
+	alternative_io("ds clflush %0",
+		       "clflushopt %0", X86_FEATURE_CLFLUSHOPT,
 		       "+m" (*(volatile char __force *)__p));
 }
 
@@ -186,14 +185,11 @@ static inline void clwb(volatile void *__p)
 {
 	volatile struct { char x[64]; } *p = __p;
 
-	asm volatile(ALTERNATIVE_2(
-		".byte 0x3e; clflush (%[pax])",
-		".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */
-		X86_FEATURE_CLFLUSHOPT,
-		".byte 0x66, 0x0f, 0xae, 0x30",  /* clwb (%%rax) */
-		X86_FEATURE_CLWB)
-		: [p] "+m" (*p)
-		: [pax] "a" (p));
+	asm_inline volatile(ALTERNATIVE_2(
+		"ds clflush %0",
+		"clflushopt %0", X86_FEATURE_CLFLUSHOPT,
+		"clwb %0", X86_FEATURE_CLWB)
+		: "+m" (*p));
 }
 
 #ifdef CONFIG_X86_USER_SHADOW_STACK
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
deleted file mode 100644
index e0975e9c4f47..000000000000
--- a/arch/x86/include/asm/sta2x11.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
- */
-#ifndef __ASM_STA2X11_H
-#define __ASM_STA2X11_H
-
-#include <linux/pci.h>
-
-/* This needs to be called from the MFD to configure its sub-devices */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
-
-#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 00473a650f51..cd761b14eb02 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -2,26 +2,10 @@
 /*
  * GCC stack protector support.
  *
- * Stack protector works by putting predefined pattern at the start of
+ * Stack protector works by putting a predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc historically required it to be at a fixed offset
- * from the percpu segment base.  On x86_64, the offset is 40 bytes.
- *
- * The same segment is shared by percpu area and stack canary.  On
- * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
- * base of percpu area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at the appropriate
- * offset.  On x86_32, the stack canary is just a regular percpu
- * variable.
- *
- * Putting percpu data in %fs on 32-bit is a minor optimization compared to
- * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
- * to load 0 into %fs on exit to usermode, whereas with percpu data in
- * %gs, we are likely to load a non-null %gs on return to user mode.
- *
- * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
- * support, we can remove some of this complexity.
+ * returning from the function.  The pattern is called the stack canary
+ * and is a unique value for each task.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -36,6 +20,8 @@
 
 #include <linux/sched.h>
 
+DECLARE_PER_CPU_CACHE_HOT(unsigned long, __stack_chk_guard);
+
 /*
  * Initialize the stackprotector canary value.
  *
@@ -51,25 +37,13 @@ static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary = get_random_canary();
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
-#endif
-
 	current->stack_canary = canary;
-#ifdef CONFIG_X86_64
-	this_cpu_write(fixed_percpu_data.stack_canary, canary);
-#else
 	this_cpu_write(__stack_chk_guard, canary);
-#endif
 }
 
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 {
-#ifdef CONFIG_X86_64
-	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
-#else
 	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
-#endif
 }
 
 #else	/* STACKPROTECTOR */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 9d0b324eab21..79e9695dc13e 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -21,6 +21,7 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
 void *__memset(void *s, int c, size_t n);
+KCFI_REFERENCE(__memset);
 
 /*
  * KMSAN needs to instrument as much code as possible. Use C versions of
@@ -70,6 +71,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t count);
 void *__memmove(void *dest, const void *src, size_t count);
+KCFI_REFERENCE(__memmove);
 
 int memcmp(const void *cs, const void *ct, size_t count);
 size_t strlen(const char *s);
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index b4b16dafd55e..65394aa9b49f 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -30,7 +30,7 @@
 #define TDX_SUCCESS		0ULL
 #define TDX_RND_NO_ENTROPY	0x8000020300000000ULL
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <uapi/asm/mce.h>
 
@@ -126,5 +126,5 @@ static inline int tdx_enable(void)  { return -ENODEV; }
 static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
 #endif	/* CONFIG_INTEL_TDX_HOST */
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_TDX_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a55c214f3ba6..9282465eea21 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -54,7 +54,7 @@
  * - this struct should fit entirely inside of one cache line
  * - this struct shares the supervisor stack pages
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct task_struct;
 #include <asm/cpufeature.h>
 #include <linux/atomic.h>
@@ -73,7 +73,7 @@ struct thread_info {
 	.flags		= 0,			\
 }
 
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
 
 #include <asm/asm-offsets.h>
 
@@ -161,7 +161,7 @@ struct thread_info {
  *
  * preempt_count needs to be 1 initially, until the scheduler is functional.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * Walks up the stack frames to make sure that the specified object is
@@ -213,7 +213,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #endif
 }
 
-#endif  /* !__ASSEMBLY__ */
+#endif  /* !__ASSEMBLER__ */
 
 /*
  * Thread-synchronous status.
@@ -224,7 +224,7 @@ static inline int arch_within_stack_frames(const void * const stack,
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
 
@@ -242,6 +242,6 @@ static inline int arch_within_stack_frames(const void * const stack,
 
 extern void arch_setup_new_exec(void);
 #define arch_setup_new_exec arch_setup_new_exec
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #endif /* _ASM_X86_THREAD_INFO_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 77f52bc1578a..866ea78ba156 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,9 @@
 static inline void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
+#include <linux/kernel.h>
+#include <vdso/bits.h>
+#include <vdso/page.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
@@ -25,4 +28,139 @@ static inline void invlpg(unsigned long addr)
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 }
 
+enum addr_stride {
+	PTE_STRIDE = 0,
+	PMD_STRIDE = 1
+};
+
+/*
+ * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination
+ * of the three. For example:
+ * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address
+ * - FLAG_PCID:			    invalidate all TLB entries matching the PCID
+ *
+ * The first is used to invalidate (kernel) mappings at a particular
+ * address across all processes.
+ *
+ * The latter invalidates all TLB entries matching a PCID.
+ */
+#define INVLPGB_FLAG_VA			BIT(0)
+#define INVLPGB_FLAG_PCID		BIT(1)
+#define INVLPGB_FLAG_ASID		BIT(2)
+#define INVLPGB_FLAG_INCLUDE_GLOBAL	BIT(3)
+#define INVLPGB_FLAG_FINAL_ONLY		BIT(4)
+#define INVLPGB_FLAG_INCLUDE_NESTED	BIT(5)
+
+/* The implied mode when all bits are clear: */
+#define INVLPGB_MODE_ALL_NONGLOBALS	0UL
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+/*
+ * INVLPGB does broadcast TLB invalidation across all the CPUs in the system.
+ *
+ * The INVLPGB instruction is weakly ordered, and a batch of invalidations can
+ * be done in a parallel fashion.
+ *
+ * The instruction takes the number of extra pages to invalidate, beyond the
+ * first page, while __invlpgb gets the more human readable number of pages to
+ * invalidate.
+ *
+ * The bits in rax[0:2] determine respectively which components of the address
+ * (VA, PCID, ASID) get compared when flushing. If neither bits are set, *any*
+ * address in the specified range matches.
+ *
+ * Since it is desired to only flush TLB entries for the ASID that is executing
+ * the instruction (a host/hypervisor or a guest), the ASID valid bit should
+ * always be set. On a host/hypervisor, the hardware will use the ASID value
+ * specified in EDX[15:0] (which should be 0). On a guest, the hardware will
+ * use the actual ASID value of the guest.
+ *
+ * TLBSYNC is used to ensure that pending INVLPGB invalidations initiated from
+ * this CPU have completed.
+ */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+			     unsigned long addr, u16 nr_pages,
+			     enum addr_stride stride, u8 flags)
+{
+	u64 rax = addr | flags | INVLPGB_FLAG_ASID;
+	u32 ecx = (stride << 31) | (nr_pages - 1);
+	u32 edx = (pcid << 16) | asid;
+
+	/* The low bits in rax are for flags. Verify addr is clean. */
+	VM_WARN_ON_ONCE(addr & ~PAGE_MASK);
+
+	/* INVLPGB; supported in binutils >= 2.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xfe" :: "a" (rax), "c" (ecx), "d" (edx));
+}
+
+static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags)
+{
+	__invlpgb(asid, pcid, 0, 1, 0, flags);
+}
+
+static inline void __tlbsync(void)
+{
+	/*
+	 * TLBSYNC waits for INVLPGB instructions originating on the same CPU
+	 * to have completed. Print a warning if the task has been migrated,
+	 * and might not be waiting on all the INVLPGBs issued during this TLB
+	 * invalidation sequence.
+	 */
+	cant_migrate();
+
+	/* TLBSYNC: supported in binutils >= 0.36. */
+	asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory");
+}
+#else
+/* Some compilers (I'm looking at you clang!) simply can't do DCE */
+static inline void __invlpgb(unsigned long asid, unsigned long pcid,
+			     unsigned long addr, u16 nr_pages,
+			     enum addr_stride s, u8 flags) { }
+static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags) { }
+static inline void __tlbsync(void) { }
+#endif
+
+static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
+						unsigned long addr,
+						u16 nr, bool stride)
+{
+	enum addr_stride str = stride ? PMD_STRIDE : PTE_STRIDE;
+	u8 flags = INVLPGB_FLAG_PCID | INVLPGB_FLAG_VA;
+
+	__invlpgb(0, pcid, addr, nr, str, flags);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid)
+{
+	__invlpgb_all(0, pcid, INVLPGB_FLAG_PCID);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invlpgb_flush_all(void)
+{
+	/*
+	 * TLBSYNC at the end needs to make sure all flushes done on the
+	 * current CPU have been executed system-wide. Therefore, make
+	 * sure nothing gets migrated in-between but disable preemption
+	 * as it is cheaper.
+	 */
+	guard(preempt)();
+	__invlpgb_all(0, 0, INVLPGB_FLAG_INCLUDE_GLOBAL);
+	__tlbsync();
+}
+
+/* Flush addr, including globals, for all PCIDs. */
+static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr)
+{
+	__invlpgb(0, 0, addr, nr, PTE_STRIDE, INVLPGB_FLAG_INCLUDE_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invlpgb_flush_all_nonglobals(void)
+{
+	guard(preempt)();
+	__invlpgb_all(0, 0, INVLPGB_MODE_ALL_NONGLOBALS);
+	__tlbsync();
+}
 #endif /* _ASM_X86_TLB_H */
diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h
index 1ad56eb3e8a8..80aaf64ff25f 100644
--- a/arch/x86/include/asm/tlbbatch.h
+++ b/arch/x86/include/asm/tlbbatch.h
@@ -10,6 +10,11 @@ struct arch_tlbflush_unmap_batch {
 	 * the PFNs being flushed..
 	 */
 	struct cpumask cpumask;
+	/*
+	 * Set if pages were unmapped from any MM, even one that does not
+	 * have active CPUs in its cpumask.
+	 */
+	bool unmapped_pages;
 };
 
 #endif /* _ARCH_X86_TLBBATCH_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 02fc2aa06e9e..a9af8759de34 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -6,6 +6,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/sched.h>
 
+#include <asm/barrier.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
@@ -183,6 +184,9 @@ static inline void cr4_init_shadow(void)
 extern unsigned long mmu_cr4_features;
 extern u32 *trampoline_cr4_features;
 
+/* How many pages can be invalidated with one INVLPGB. */
+extern u16 invlpgb_count_max;
+
 extern void initialize_tlbstate_and_flush(void);
 
 /*
@@ -231,6 +235,71 @@ void flush_tlb_one_kernel(unsigned long addr);
 void flush_tlb_multi(const struct cpumask *cpumask,
 		      const struct flush_tlb_info *info);
 
+static inline bool is_dyn_asid(u16 asid)
+{
+	return asid < TLB_NR_DYN_ASIDS;
+}
+
+static inline bool is_global_asid(u16 asid)
+{
+	return !is_dyn_asid(asid);
+}
+
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+static inline u16 mm_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return 0;
+
+	asid = smp_load_acquire(&mm->context.global_asid);
+
+	/* mm->context.global_asid is either 0, or a global ASID */
+	VM_WARN_ON_ONCE(asid && is_dyn_asid(asid));
+
+	return asid;
+}
+
+static inline void mm_init_global_asid(struct mm_struct *mm)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		mm->context.global_asid = 0;
+		mm->context.asid_transition = false;
+	}
+}
+
+static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid)
+{
+	/*
+	 * Notably flush_tlb_mm_range() -> broadcast_tlb_flush() ->
+	 * finish_asid_transition() needs to observe asid_transition = true
+	 * once it observes global_asid.
+	 */
+	mm->context.asid_transition = true;
+	smp_store_release(&mm->context.global_asid, asid);
+}
+
+static inline void mm_clear_asid_transition(struct mm_struct *mm)
+{
+	WRITE_ONCE(mm->context.asid_transition, false);
+}
+
+static inline bool mm_in_asid_transition(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	return mm && READ_ONCE(mm->context.asid_transition);
+}
+#else
+static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; }
+static inline void mm_init_global_asid(struct mm_struct *mm) { }
+static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { }
+static inline void mm_clear_asid_transition(struct mm_struct *mm) { }
+static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; }
+#endif /* CONFIG_BROADCAST_TLB_FLUSH */
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
@@ -242,7 +311,7 @@ void flush_tlb_multi(const struct cpumask *cpumask,
 	flush_tlb_mm_range((vma)->vm_mm, start, end,			\
 			   ((vma)->vm_flags & VM_HUGETLB)		\
 				? huge_page_shift(hstate_vma(vma))	\
-				: PAGE_SHIFT, false)
+				: PAGE_SHIFT, true)
 
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
@@ -284,6 +353,7 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 {
 	inc_mm_tlb_gen(mm);
 	cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
+	batch->unmapped_pages = true;
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1f1deaecd364..869b88061801 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -35,8 +35,6 @@ static inline int get_si_code(unsigned long condition)
 		return TRAP_BRKPT;
 }
 
-extern int panic_on_unrecovered_nmi;
-
 void math_emulate(struct math_emu_info *);
 
 bool fault_in_kernel_space(unsigned long address);
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index 85cc57cb6539..8f4579c5a6f8 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -5,7 +5,7 @@
 
 #include "orc_types.h"
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 .macro UNWIND_HINT_END_OF_STACK
 	UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK
@@ -88,6 +88,6 @@
 #define UNWIND_HINT_RESTORE \
 	UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_UNWIND_HINTS_H */
diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h
index 2bf9c0e970c3..785f8edcb9c9 100644
--- a/arch/x86/include/asm/vdso/getrandom.h
+++ b/arch/x86/include/asm/vdso/getrandom.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_GETRANDOM_H
 #define __ASM_VDSO_GETRANDOM_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 
@@ -37,6 +37,6 @@ static __always_inline const struct vdso_rng_data *__arch_get_vdso_rng_data(void
 	return &vdso_rng_data;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */
diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h
index 375a34b0f365..428f3f4c2235 100644
--- a/arch/x86/include/asm/vdso/gettimeofday.h
+++ b/arch/x86/include/asm/vdso/gettimeofday.h
@@ -10,7 +10,7 @@
 #ifndef __ASM_VDSO_GETTIMEOFDAY_H
 #define __ASM_VDSO_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <uapi/linux/time.h>
 #include <asm/vgtod.h>
@@ -350,6 +350,6 @@ static __always_inline u64 vdso_calc_ns(const struct vdso_data *vd, u64 cycles,
 }
 #define vdso_calc_ns vdso_calc_ns
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/x86/include/asm/vdso/processor.h b/arch/x86/include/asm/vdso/processor.h
index 2cbce97d29ea..c9b2ba7a9ec4 100644
--- a/arch/x86/include/asm/vdso/processor.h
+++ b/arch/x86/include/asm/vdso/processor.h
@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_PROCESSOR_H
 #define __ASM_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
 static __always_inline void rep_nop(void)
@@ -22,6 +22,6 @@ struct getcpu_cache;
 
 notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_PROCESSOR_H */
diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h
index 37b4a70559a8..72aedebb7648 100644
--- a/arch/x86/include/asm/vdso/vsyscall.h
+++ b/arch/x86/include/asm/vdso/vsyscall.h
@@ -9,7 +9,7 @@
 #define VDSO_PAGE_PVCLOCK_OFFSET	0
 #define VDSO_PAGE_HVCLOCK_OFFSET	1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <vdso/datapage.h>
 #include <asm/vgtod.h>
@@ -36,6 +36,6 @@ struct vdso_rng_data *__x86_get_k_vdso_rng_data(void)
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
index 75884d2cdec3..5d471253c755 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -15,8 +15,6 @@
 #define MODULE_PROC_FAMILY "586TSC "
 #elif defined CONFIG_M586MMX
 #define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -33,8 +31,6 @@
 #define MODULE_PROC_FAMILY "K6 "
 #elif defined CONFIG_MK7
 #define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index baca0b00ef76..a078a2b0f032 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -72,7 +72,7 @@
 #endif
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* Explicitly size integers that represent pfns in the public interface
  * with Xen so that on ARM we can have one ABI that works for 32 and 64
  * bit guests. */
@@ -137,7 +137,7 @@ DEFINE_GUEST_HANDLE(xen_ulong_t);
 #define TI_SET_DPL(_ti, _dpl)	((_ti)->flags |= (_dpl))
 #define TI_SET_IF(_ti, _if)	((_ti)->flags |= ((!!(_if))<<2))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct trap_info {
     uint8_t       vector;  /* exception vector                              */
     uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
@@ -186,7 +186,7 @@ struct arch_shared_info {
 	uint32_t wc_sec_hi;
 #endif
 };
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 #ifdef CONFIG_X86_32
 #include <asm/xen/interface_32.h>
@@ -196,7 +196,7 @@ struct arch_shared_info {
 
 #include <asm/pvclock-abi.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * The following is all CPU context. Note that the fpu_ctxt block is filled
  * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
@@ -376,7 +376,7 @@ struct xen_pmu_arch {
 	} c;
 };
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 
 /*
  * Prefix forces emulation of some non-trapping instructions.
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index dc40578abded..74d9768a9cf7 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -44,7 +44,7 @@
  */
 #define __HYPERVISOR_VIRT_START 0xF5800000
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct cpu_user_regs {
     uint32_t ebx;
@@ -85,7 +85,7 @@ typedef struct xen_callback xen_callback_t;
 
 #define XEN_CALLBACK(__cs, __eip)				\
 	((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 
 /*
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index c10f279aae93..38a19edb81a3 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -77,7 +77,7 @@
 #define VGCF_in_syscall  (1<<_VGCF_in_syscall)
 #define VGCF_IN_SYSCALL  VGCF_in_syscall
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct iret_context {
     /* Top of stack (%rsp at point of hypercall). */
@@ -143,7 +143,7 @@ typedef unsigned long xen_callback_t;
 #define XEN_CALLBACK(__cs, __rip)				\
 	((unsigned long)(__rip))
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 
 #endif /* _ASM_X86_XEN_INTERFACE_64_H */
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 9b82eebd7add..dafbf581c515 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -26,7 +26,7 @@
 #define XLF_5LEVEL_ENABLED		(1<<6)
 #define XLF_MEM_ENCRYPTION		(1<<7)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/screen_info.h>
@@ -210,6 +210,6 @@ enum x86_hardware_subarch {
 	X86_NR_SUBARCHS,
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_X86_BOOTPARAM_H */
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index 2f491efe3a12..55bc66867156 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -54,7 +54,7 @@
  */
 #define E820_RESERVED_KERN        128
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 struct e820entry {
 	__u64 addr;	/* start of memory segment */
@@ -76,7 +76,7 @@ struct e820map {
 #define BIOS_ROM_BASE		0xffe00000
 #define BIOS_ROM_END		0xffffffff
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #endif /* _UAPI_ASM_X86_E820_H */
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index d62ac5db093b..a82c039d8e6a 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -12,7 +12,7 @@
 /* The size of each LDT entry. */
 #define LDT_ENTRY_SIZE	8
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Note on 64bit base and limit is ignored and you cannot set DS/ES/CS
  * not to the default values if you still want to do syscalls. This
@@ -44,5 +44,5 @@ struct user_desc {
 #define MODIFY_LDT_CONTENTS_STACK	1
 #define MODIFY_LDT_CONTENTS_CODE	2
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_X86_LDT_H */
diff --git a/arch/x86/include/uapi/asm/msr.h b/arch/x86/include/uapi/asm/msr.h
index e7516b402a00..4b8917ca28fe 100644
--- a/arch/x86/include/uapi/asm/msr.h
+++ b/arch/x86/include/uapi/asm/msr.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_ASM_X86_MSR_H
 #define _UAPI_ASM_X86_MSR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
@@ -10,5 +10,5 @@
 #define X86_IOC_RDMSR_REGS	_IOWR('c', 0xA0, __u32[8])
 #define X86_IOC_WRMSR_REGS	_IOWR('c', 0xA1, __u32[8])
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _UAPI_ASM_X86_MSR_H */
diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h
index 16074b9c93bb..5823584dea13 100644
--- a/arch/x86/include/uapi/asm/ptrace-abi.h
+++ b/arch/x86/include/uapi/asm/ptrace-abi.h
@@ -25,7 +25,7 @@
 
 #else /* __i386__ */
 
-#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#if defined(__ASSEMBLER__) || defined(__FRAME_OFFSETS)
 /*
  * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
  * unless syscall needs a complete, fully filled "struct pt_regs".
@@ -57,7 +57,7 @@
 #define EFLAGS 144
 #define RSP 152
 #define SS 160
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /* top of stack page */
 #define FRAME_SIZE 168
@@ -87,7 +87,7 @@
 
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #endif
 
diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h
index 85165c0edafc..e0b5b4f6226b 100644
--- a/arch/x86/include/uapi/asm/ptrace.h
+++ b/arch/x86/include/uapi/asm/ptrace.h
@@ -7,7 +7,7 @@
 #include <asm/processor-flags.h>
 
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef __i386__
 /* this struct defines the way the registers are stored on the
@@ -81,6 +81,6 @@ struct pt_regs {
 
 
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_PTRACE_H */
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
index b111b0c18544..50c45ead4e7c 100644
--- a/arch/x86/include/uapi/asm/setup_data.h
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -18,7 +18,7 @@
 #define SETUP_INDIRECT			(1<<31)
 #define SETUP_TYPE_MAX			(SETUP_ENUM_MAX | SETUP_INDIRECT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -78,6 +78,6 @@ struct ima_setup_data {
 	__u64 size;
 } __attribute__((packed));
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h
index f777346450ec..1067efabf18b 100644
--- a/arch/x86/include/uapi/asm/signal.h
+++ b/arch/x86/include/uapi/asm/signal.h
@@ -2,7 +2,7 @@
 #ifndef _UAPI_ASM_X86_SIGNAL_H
 #define _UAPI_ASM_X86_SIGNAL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -16,7 +16,7 @@ struct siginfo;
 typedef unsigned long sigset_t;
 
 #endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 
 #define SIGHUP		 1
@@ -68,7 +68,7 @@ typedef unsigned long sigset_t;
 
 #include <asm-generic/signal-defs.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 
 # ifndef __KERNEL__
@@ -106,6 +106,6 @@ typedef struct sigaltstack {
 	__kernel_size_t ss_size;
 } stack_t;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _UAPI_ASM_X86_SIGNAL_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b43eb7e384eb..84cfa179802c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -44,6 +44,8 @@ KCOV_INSTRUMENT_unwind_orc.o				:= n
 KCOV_INSTRUMENT_unwind_frame.o				:= n
 KCOV_INSTRUMENT_unwind_guess.o				:= n
 
+CFLAGS_head32.o := -fno-stack-protector
+CFLAGS_head64.o := -fno-stack-protector
 CFLAGS_irq.o := -I $(src)/../include/asm/trace
 
 obj-y			+= head_$(BITS).o
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 5854f0b8f0f1..d5ac34186555 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -13,9 +13,11 @@
 #include <linux/sched.h>
 
 #include <acpi/processor.h>
+#include <asm/cpu_device_id.h>
 #include <asm/cpuid.h>
 #include <asm/mwait.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -47,12 +49,11 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 	/*
 	 * On all recent Intel platforms, ARB_DISABLE is a nop.
 	 * So, set bm_control to zero to indicate that ARB_DISABLE
-	 * is not required while entering C3 type state on
-	 * P4, Core and beyond CPUs
+	 * is not required while entering C3 type state.
 	 */
 	if (c->x86_vendor == X86_VENDOR_INTEL &&
-	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
-			flags->bm_control = 0;
+	    (c->x86 > 15 || (c->x86_vfm >= INTEL_CORE2_MEROM && c->x86_vfm <= INTEL_FAM6_LAST)))
+		flags->bm_control = 0;
 
 	if (c->x86_vendor == X86_VENDOR_CENTAUR) {
 		if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
@@ -205,6 +206,16 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_play_dead(percpu_entry->states[cx->index].eax);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_play_dead);
+
 void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S
index 4e498d28cdc8..aefb9cb583ad 100644
--- a/arch/x86/kernel/acpi/madt_playdead.S
+++ b/arch/x86/kernel/acpi/madt_playdead.S
@@ -14,6 +14,7 @@
  * rsi: PGD of the identity mapping
  */
 SYM_FUNC_START(asm_acpi_mp_play_dead)
+	ANNOTATE_NOENDBR
 	/* Turn off global entries. Following CR3 write will flush them. */
 	movq	%cr4, %rdx
 	andq	$~(X86_CR4_PGE), %rdx
diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
index d5ef6215583b..f36f28405dcc 100644
--- a/arch/x86/kernel/acpi/madt_wakeup.c
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -70,58 +70,6 @@ static void __init free_pgt_page(void *pgt, void *dummy)
 	return memblock_free(pgt, PAGE_SIZE);
 }
 
-/*
- * Make sure asm_acpi_mp_play_dead() is present in the identity mapping at
- * the same place as in the kernel page tables. asm_acpi_mp_play_dead() switches
- * to the identity mapping and the function has be present at the same spot in
- * the virtual address space before and after switching page tables.
- */
-static int __init init_transition_pgtable(pgd_t *pgd)
-{
-	pgprot_t prot = PAGE_KERNEL_EXEC_NOENC;
-	unsigned long vaddr, paddr;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	vaddr = (unsigned long)asm_acpi_mp_play_dead;
-	pgd += pgd_index(vaddr);
-	if (!pgd_present(*pgd)) {
-		p4d = (p4d_t *)alloc_pgt_page(NULL);
-		if (!p4d)
-			return -ENOMEM;
-		set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
-	}
-	p4d = p4d_offset(pgd, vaddr);
-	if (!p4d_present(*p4d)) {
-		pud = (pud_t *)alloc_pgt_page(NULL);
-		if (!pud)
-			return -ENOMEM;
-		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
-	}
-	pud = pud_offset(p4d, vaddr);
-	if (!pud_present(*pud)) {
-		pmd = (pmd_t *)alloc_pgt_page(NULL);
-		if (!pmd)
-			return -ENOMEM;
-		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
-	}
-	pmd = pmd_offset(pud, vaddr);
-	if (!pmd_present(*pmd)) {
-		pte = (pte_t *)alloc_pgt_page(NULL);
-		if (!pte)
-			return -ENOMEM;
-		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
-	}
-	pte = pte_offset_kernel(pmd, vaddr);
-
-	paddr = __pa(vaddr);
-	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, prot));
-
-	return 0;
-}
-
 static int __init acpi_mp_setup_reset(u64 reset_vector)
 {
 	struct x86_mapping_info info = {
@@ -130,6 +78,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		.page_flag      = __PAGE_KERNEL_LARGE_EXEC,
 		.kernpg_flag    = _KERNPG_TABLE_NOENC,
 	};
+	unsigned long mstart, mend;
 	pgd_t *pgd;
 
 	pgd = alloc_pgt_page(NULL);
@@ -137,8 +86,6 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		return -ENOMEM;
 
 	for (int i = 0; i < nr_pfn_mapped; i++) {
-		unsigned long mstart, mend;
-
 		mstart = pfn_mapped[i].start << PAGE_SHIFT;
 		mend   = pfn_mapped[i].end << PAGE_SHIFT;
 		if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
@@ -147,14 +94,24 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
 		}
 	}
 
-	if (kernel_ident_mapping_init(&info, pgd,
-				      PAGE_ALIGN_DOWN(reset_vector),
-				      PAGE_ALIGN(reset_vector + 1))) {
+	mstart = PAGE_ALIGN_DOWN(reset_vector);
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
 		kernel_ident_mapping_free(&info, pgd);
 		return -ENOMEM;
 	}
 
-	if (init_transition_pgtable(pgd)) {
+	/*
+	 * Make sure asm_acpi_mp_play_dead() is present in the identity mapping
+	 * at the same place as in the kernel page tables.
+	 * asm_acpi_mp_play_dead() switches to the identity mapping and the
+	 * function must be present at the same spot in the virtual address space
+	 * before and after switching page tables.
+	 */
+	info.offset = __START_KERNEL_map - phys_base;
+	mstart = PAGE_ALIGN_DOWN(__pa(asm_acpi_mp_play_dead));
+	mend = mstart + PAGE_SIZE;
+	if (kernel_ident_mapping_init(&info, pgd, mstart, mend)) {
 		kernel_ident_mapping_free(&info, pgd);
 		return -ENOMEM;
 	}
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index b200a193beeb..04f561f75e99 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -17,6 +17,7 @@
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
 SYM_FUNC_START(wakeup_long64)
+	ANNOTATE_NOENDBR
 	movq	saved_magic(%rip), %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c71b575bf229..bf82c6f7d690 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -392,10 +392,8 @@ EXPORT_SYMBOL(BUG_func);
  * Rewrite the "call BUG_func" replacement to point to the target of the
  * indirect pv_ops call "call *disp(%ip)".
  */
-static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
-			    struct module *mod)
+static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
 {
-	u8 *wr_instr = module_writable_address(mod, instr);
 	void *target, *bug = &BUG_func;
 	s32 disp;
 
@@ -405,14 +403,14 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
 	}
 
 	if (a->instrlen != 6 ||
-	    wr_instr[0] != CALL_RIP_REL_OPCODE ||
-	    wr_instr[1] != CALL_RIP_REL_MODRM) {
+	    instr[0] != CALL_RIP_REL_OPCODE ||
+	    instr[1] != CALL_RIP_REL_MODRM) {
 		pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
 		BUG();
 	}
 
 	/* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
-	disp = *(s32 *)(wr_instr + 2);
+	disp = *(s32 *)(instr + 2);
 #ifdef CONFIG_X86_64
 	/* ff 15 00 00 00 00   call   *0x0(%rip) */
 	/* target address is stored at "next instruction + disp". */
@@ -450,8 +448,7 @@ static inline u8 * instr_va(struct alt_instr *i)
  * to refetch changed I$ lines.
  */
 void __init_or_module noinline apply_alternatives(struct alt_instr *start,
-						  struct alt_instr *end,
-						  struct module *mod)
+						  struct alt_instr *end)
 {
 	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *instr, *replacement;
@@ -480,7 +477,6 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
-		u8 *wr_instr, *wr_replacement;
 
 		/*
 		 * In case of nested ALTERNATIVE()s the outer alternative might
@@ -494,11 +490,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		}
 
 		instr = instr_va(a);
-		wr_instr = module_writable_address(mod, instr);
-
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		wr_replacement = module_writable_address(mod, replacement);
-
 		BUG_ON(a->instrlen > sizeof(insn_buff));
 		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
 
@@ -509,9 +501,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		 *   patch if feature is *NOT* present.
 		 */
 		if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
-			memcpy(insn_buff, wr_instr, a->instrlen);
+			memcpy(insn_buff, instr, a->instrlen);
 			optimize_nops(instr, insn_buff, a->instrlen);
-			text_poke_early(wr_instr, insn_buff, a->instrlen);
+			text_poke_early(instr, insn_buff, a->instrlen);
 			continue;
 		}
 
@@ -521,12 +513,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->flags);
 
-		memcpy(insn_buff, wr_replacement, a->replacementlen);
+		memcpy(insn_buff, replacement, a->replacementlen);
 		insn_buff_sz = a->replacementlen;
 
 		if (a->flags & ALT_FLAG_DIRECT_CALL) {
-			insn_buff_sz = alt_replace_call(instr, insn_buff, a,
-							mod);
+			insn_buff_sz = alt_replace_call(instr, insn_buff, a);
 			if (insn_buff_sz < 0)
 				continue;
 		}
@@ -536,11 +527,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 
 		apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
 
-		DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px:   old_insn: ", instr);
+		DUMP_BYTES(ALT, instr, a->instrlen, "%px:   old_insn: ", instr);
 		DUMP_BYTES(ALT, replacement, a->replacementlen, "%px:   rpl_insn: ", replacement);
 		DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
 
-		text_poke_early(wr_instr, insn_buff, insn_buff_sz);
+		text_poke_early(instr, insn_buff, insn_buff_sz);
 	}
 
 	kasan_enable_current();
@@ -731,20 +722,18 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 /*
  * Generated by 'objtool --retpoline'.
  */
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod)
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op1, op2;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -752,6 +741,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
 		op2 = insn.opcode.bytes[1];
 
 		switch (op1) {
+		case 0x70 ... 0x7f:	/* Jcc.d8 */
+			/* See cfi_paranoid. */
+			WARN_ON_ONCE(cfi_mode != CFI_FINEIBT);
+			continue;
+
 		case CALL_INSN_OPCODE:
 		case JMP32_INSN_OPCODE:
 			break;
@@ -772,9 +766,9 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
 		len = patch_retpoline(addr, &insn, bytes);
 		if (len == insn.length) {
 			optimize_nops(addr, bytes, len);
-			DUMP_BYTES(RETPOLINE, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RETPOLINE, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
@@ -810,8 +804,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	return i;
 }
 
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod)
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
@@ -820,13 +813,12 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 	for (s = start; s < end; s++) {
 		void *dest = NULL, *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -846,41 +838,59 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 		len = patch_return(addr, &insn, bytes);
 		if (len == insn.length) {
-			DUMP_BYTES(RET, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RET, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
-#else
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
-#endif /* CONFIG_MITIGATION_RETHUNK */
+#else /* !CONFIG_MITIGATION_RETHUNK: */
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+#endif /* !CONFIG_MITIGATION_RETHUNK */
 
 #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod) { }
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
+#endif /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
-static void poison_cfi(void *addr, void *wr_addr);
+__noendbr bool is_endbr(u32 *val)
+{
+	u32 endbr;
+
+	__get_kernel_nofault(&endbr, val, u32, Efault);
+	return __is_endbr(endbr);
+
+Efault:
+	return false;
+}
 
-static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
+#ifdef CONFIG_FINEIBT
+
+static __noendbr bool exact_endbr(u32 *val)
 {
-	u32 endbr, poison = gen_endbr_poison();
+	u32 endbr;
 
-	if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr)))
-		return;
+	__get_kernel_nofault(&endbr, val, u32, Efault);
+	return endbr == gen_endbr();
+
+Efault:
+	return false;
+}
 
-	if (!is_endbr(endbr)) {
-		WARN_ON_ONCE(warn);
+#endif
+
+static void poison_cfi(void *addr);
+
+static void __init_or_module poison_endbr(void *addr)
+{
+	u32 poison = gen_endbr_poison();
+
+	if (WARN_ON_ONCE(!is_endbr(addr)))
 		return;
-	}
 
 	DPRINTK(ENDBR, "ENDBR at: %pS (%px)", addr, addr);
 
@@ -889,7 +899,7 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
 	 */
 	DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr);
 	DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr);
-	text_poke_early(wr_addr, &poison, 4);
+	text_poke_early(addr, &poison, 4);
 }
 
 /*
@@ -898,36 +908,39 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
  * Seal the functions for indirect calls by clobbering the ENDBR instructions
  * and the kCFI hash value.
  */
-void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr, wr_addr, true);
+		poison_endbr(addr);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_cfi(addr - 16, wr_addr - 16);
+			poison_cfi(addr - 16);
 	}
 }
 
-#else
+#else /* !CONFIG_X86_KERNEL_IBT: */
 
-void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { }
+void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 
-#endif /* CONFIG_X86_KERNEL_IBT */
+#endif /* !CONFIG_X86_KERNEL_IBT */
 
 #ifdef CONFIG_CFI_AUTO_DEFAULT
-#define __CFI_DEFAULT	CFI_AUTO
+# define __CFI_DEFAULT CFI_AUTO
 #elif defined(CONFIG_CFI_CLANG)
-#define __CFI_DEFAULT	CFI_KCFI
+# define __CFI_DEFAULT CFI_KCFI
 #else
-#define __CFI_DEFAULT	CFI_OFF
+# define __CFI_DEFAULT CFI_OFF
 #endif
 
 enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT;
 
+#ifdef CONFIG_FINEIBT_BHI
+bool cfi_bhi __ro_after_init = false;
+#endif
+
 #ifdef CONFIG_CFI_CLANG
 struct bpf_insn;
 
@@ -935,11 +948,7 @@ struct bpf_insn;
 extern unsigned int __bpf_prog_runX(const void *ctx,
 				    const struct bpf_insn *insn);
 
-/*
- * Force a reference to the external symbol so the compiler generates
- * __kcfi_typid.
- */
-__ADDRESSABLE(__bpf_prog_runX);
+KCFI_REFERENCE(__bpf_prog_runX);
 
 /* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
 asm (
@@ -956,7 +965,7 @@ asm (
 /* Must match bpf_callback_t */
 extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
 
-__ADDRESSABLE(__bpf_callback_fn);
+KCFI_REFERENCE(__bpf_callback_fn);
 
 /* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
 asm (
@@ -991,6 +1000,21 @@ u32 cfi_get_func_hash(void *func)
 
 	return hash;
 }
+
+int cfi_get_func_arity(void *func)
+{
+	bhi_thunk *target;
+	s32 disp;
+
+	if (cfi_mode != CFI_FINEIBT && !cfi_bhi)
+		return 0;
+
+	if (get_kernel_nofault(disp, func - 4))
+		return 0;
+
+	target = func + disp;
+	return target - __bhi_args;
+}
 #endif
 
 #ifdef CONFIG_FINEIBT
@@ -998,6 +1022,8 @@ u32 cfi_get_func_hash(void *func)
 static bool cfi_rand __ro_after_init = true;
 static u32  cfi_seed __ro_after_init;
 
+static bool cfi_paranoid __ro_after_init = false;
+
 /*
  * Re-hash the CFI hash with a boot-time seed while making sure the result is
  * not a valid ENDBR instruction.
@@ -1005,7 +1031,7 @@ static u32  cfi_seed __ro_after_init;
 static u32 cfi_rehash(u32 hash)
 {
 	hash ^= cfi_seed;
-	while (unlikely(is_endbr(hash) || is_endbr(-hash))) {
+	while (unlikely(__is_endbr(hash) || __is_endbr(-hash))) {
 		bool lsb = hash & 1;
 		hash >>= 1;
 		if (lsb)
@@ -1037,6 +1063,25 @@ static __init int cfi_parse_cmdline(char *str)
 			cfi_mode = CFI_FINEIBT;
 		} else if (!strcmp(str, "norand")) {
 			cfi_rand = false;
+		} else if (!strcmp(str, "warn")) {
+			pr_alert("CFI mismatch non-fatal!\n");
+			cfi_warn = true;
+		} else if (!strcmp(str, "paranoid")) {
+			if (cfi_mode == CFI_FINEIBT) {
+				cfi_paranoid = true;
+			} else {
+				pr_err("Ignoring paranoid; depends on fineibt.\n");
+			}
+		} else if (!strcmp(str, "bhi")) {
+#ifdef CONFIG_FINEIBT_BHI
+			if (cfi_mode == CFI_FINEIBT) {
+				cfi_bhi = true;
+			} else {
+				pr_err("Ignoring bhi; depends on fineibt.\n");
+			}
+#else
+			pr_err("Ignoring bhi; depends on FINEIBT_BHI=y.\n");
+#endif
 		} else {
 			pr_err("Ignoring unknown cfi option (%s).", str);
 		}
@@ -1054,9 +1099,9 @@ early_param("cfi", cfi_parse_cmdline);
  * __cfi_\func:					__cfi_\func:
  *	movl   $0x12345678,%eax		// 5	     endbr64			// 4
  *	nop					     subl   $0x12345678,%r10d   // 7
- *	nop					     jz     1f			// 2
- *	nop					     ud2			// 2
- *	nop					1:   nop			// 1
+ *	nop					     jne    __cfi_\func+6	// 2
+ *	nop					     nop3			// 3
+ *	nop
  *	nop
  *	nop
  *	nop
@@ -1068,34 +1113,53 @@ early_param("cfi", cfi_parse_cmdline);
  *
  * caller:					caller:
  *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%r10d	// 6
- *	addl	$-15(%r11),%r10d	 // 4	     sub    $16,%r11		// 4
+ *	addl	$-15(%r11),%r10d	 // 4	     lea    -0x10(%r11),%r11	// 4
  *	je	1f			 // 2	     nop4			// 4
  *	ud2				 // 2
- * 1:	call	__x86_indirect_thunk_r11 // 5	     call   *%r11; nop2;	// 5
+ * 1:	cs call	__x86_indirect_thunk_r11 // 6	     call   *%r11; nop3;	// 6
  *
  */
 
-asm(	".pushsection .rodata			\n"
-	"fineibt_preamble_start:		\n"
-	"	endbr64				\n"
-	"	subl	$0x12345678, %r10d	\n"
-	"	je	fineibt_preamble_end	\n"
-	"	ud2				\n"
-	"	nop				\n"
-	"fineibt_preamble_end:			\n"
+/*
+ * <fineibt_preamble_start>:
+ *  0:   f3 0f 1e fa             endbr64
+ *  4:   41 81 <ea> 78 56 34 12  sub    $0x12345678, %r10d
+ *  b:   75 f9                   jne    6 <fineibt_preamble_start+0x6>
+ *  d:   0f 1f 00                nopl   (%rax)
+ *
+ * Note that the JNE target is the 0xEA byte inside the SUB, this decodes as
+ * (bad) on x86_64 and raises #UD.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_preamble_start:			\n"
+	"	endbr64					\n"
+	"	subl	$0x12345678, %r10d		\n"
+	"fineibt_preamble_bhi:				\n"
+	"	jne	fineibt_preamble_start+6	\n"
+	ASM_NOP3
+	"fineibt_preamble_end:				\n"
 	".popsection\n"
 );
 
 extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_bhi[];
 extern u8 fineibt_preamble_end[];
 
 #define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_bhi  (fineibt_preamble_bhi - fineibt_preamble_start)
+#define fineibt_preamble_ud   6
 #define fineibt_preamble_hash 7
 
+/*
+ * <fineibt_caller_start>:
+ *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+ *  6:   4d 8d 5b f0             lea    -0x10(%r11), %r11
+ *  a:   0f 1f 40 00             nopl   0x0(%rax)
+ */
 asm(	".pushsection .rodata			\n"
 	"fineibt_caller_start:			\n"
 	"	movl	$0x12345678, %r10d	\n"
-	"	sub	$16, %r11		\n"
+	"	lea	-0x10(%r11), %r11	\n"
 	ASM_NOP4
 	"fineibt_caller_end:			\n"
 	".popsection				\n"
@@ -1109,13 +1173,62 @@ extern u8 fineibt_caller_end[];
 
 #define fineibt_caller_jmp (fineibt_caller_size - 2)
 
-static u32 decode_preamble_hash(void *addr)
+/*
+ * Since FineIBT does hash validation on the callee side it is prone to
+ * circumvention attacks where a 'naked' ENDBR instruction exists that
+ * is not part of the fineibt_preamble sequence.
+ *
+ * Notably the x86 entry points must be ENDBR and equally cannot be
+ * fineibt_preamble.
+ *
+ * The fineibt_paranoid caller sequence adds additional caller side
+ * hash validation. This stops such circumvention attacks dead, but at the cost
+ * of adding a load.
+ *
+ * <fineibt_paranoid_start>:
+ *  0:   41 ba 78 56 34 12       mov    $0x12345678, %r10d
+ *  6:   45 3b 53 f7             cmp    -0x9(%r11), %r10d
+ *  a:   4d 8d 5b <f0>           lea    -0x10(%r11), %r11
+ *  e:   75 fd                   jne    d <fineibt_paranoid_start+0xd>
+ * 10:   41 ff d3                call   *%r11
+ * 13:   90                      nop
+ *
+ * Notably LEA does not modify flags and can be reordered with the CMP,
+ * avoiding a dependency. Again, using a non-taken (backwards) branch
+ * for the failure case, abusing LEA's immediate 0xf0 as LOCK prefix for the
+ * Jcc.d8, causing #UD.
+ */
+asm(	".pushsection .rodata				\n"
+	"fineibt_paranoid_start:			\n"
+	"	movl	$0x12345678, %r10d		\n"
+	"	cmpl	-9(%r11), %r10d			\n"
+	"	lea	-0x10(%r11), %r11		\n"
+	"	jne	fineibt_paranoid_start+0xd	\n"
+	"fineibt_paranoid_ind:				\n"
+	"	call	*%r11				\n"
+	"	nop					\n"
+	"fineibt_paranoid_end:				\n"
+	".popsection					\n"
+);
+
+extern u8 fineibt_paranoid_start[];
+extern u8 fineibt_paranoid_ind[];
+extern u8 fineibt_paranoid_end[];
+
+#define fineibt_paranoid_size (fineibt_paranoid_end - fineibt_paranoid_start)
+#define fineibt_paranoid_ind  (fineibt_paranoid_ind - fineibt_paranoid_start)
+#define fineibt_paranoid_ud   0xd
+
+static u32 decode_preamble_hash(void *addr, int *reg)
 {
 	u8 *p = addr;
 
-	/* b8 78 56 34 12          mov    $0x12345678,%eax */
-	if (p[0] == 0xb8)
+	/* b8+reg 78 56 34 12          movl    $0x12345678,\reg */
+	if (p[0] >= 0xb8 && p[0] < 0xc0) {
+		if (reg)
+			*reg = p[0] - 0xb8;
 		return *(u32 *)(addr + 1);
+	}
 
 	return 0; /* invalid hash value */
 }
@@ -1124,11 +1237,11 @@ static u32 decode_caller_hash(void *addr)
 {
 	u8 *p = addr;
 
-	/* 41 ba 78 56 34 12       mov    $0x12345678,%r10d */
+	/* 41 ba 88 a9 cb ed       mov    $(-0x12345678),%r10d */
 	if (p[0] == 0x41 && p[1] == 0xba)
 		return -*(u32 *)(addr + 2);
 
-	/* e8 0c 78 56 34 12	   jmp.d8  +12 */
+	/* e8 0c 88 a9 cb ed	   jmp.d8  +12 */
 	if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
 		return -*(u32 *)(addr + 2);
 
@@ -1136,7 +1249,7 @@ static u32 decode_caller_hash(void *addr)
 }
 
 /* .retpoline_sites */
-static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_disable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
@@ -1148,23 +1261,20 @@ static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
-
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, jmp, 2);
+		text_poke_early(addr, jmp, 2);
 	}
 
 	return 0;
 }
 
-static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_enable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Re-enable kCFI, undo what cfi_disable_callers() did.
@@ -1174,126 +1284,212 @@ static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, mov, 2);
+		text_poke_early(addr, mov, 2);
 	}
 
 	return 0;
 }
 
 /* .cfi_sites */
-static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		hash = decode_preamble_hash(addr, NULL);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
 		hash = cfi_rehash(hash);
-		text_poke_early(wr_addr + 1, &hash, 4);
+		text_poke_early(addr + 1, &hash, 4);
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod)
+static void cfi_fineibt_bhi_preamble(void *addr, int arity)
+{
+	if (!arity)
+		return;
+
+	if (!cfi_warn && arity == 1) {
+		/*
+		 * Crazy scheme to allow arity-1 inline:
+		 *
+		 * __cfi_foo:
+		 *  0: f3 0f 1e fa             endbr64
+		 *  4: 41 81 <ea> 78 56 34 12  sub     0x12345678, %r10d
+		 *  b: 49 0f 45 fa             cmovne  %r10, %rdi
+		 *  f: 75 f5                   jne     __cfi_foo+6
+		 * 11: 0f 1f 00                nopl    (%rax)
+		 *
+		 * Code that direct calls to foo()+0, decodes the tail end as:
+		 *
+		 * foo:
+		 *  0: f5                      cmc
+		 *  1: 0f 1f 00                nopl    (%rax)
+		 *
+		 * which clobbers CF, but does not affect anything ABI
+		 * wise.
+		 *
+		 * Notably, this scheme is incompatible with permissive CFI
+		 * because the CMOVcc is unconditional and RDI will have been
+		 * clobbered.
+		 */
+		const u8 magic[9] = {
+			0x49, 0x0f, 0x45, 0xfa,
+			0x75, 0xf5,
+			BYTES_NOP3,
+		};
+
+		text_poke_early(addr + fineibt_preamble_bhi, magic, 9);
+
+		return;
+	}
+
+	text_poke_early(addr + fineibt_preamble_bhi,
+			text_gen_insn(CALL_INSN_OPCODE,
+				      addr + fineibt_preamble_bhi,
+				      __bhi_args[arity]),
+			CALL_INSN_SIZE);
+}
+
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
+		int arity;
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		/*
+		 * When the function doesn't start with ENDBR the compiler will
+		 * have determined there are no indirect calls to it and we
+		 * don't need no CFI either.
+		 */
+		if (!is_endbr(addr + 16))
+			continue;
+
+		hash = decode_preamble_hash(addr, &arity);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
-		text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size);
-		WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678);
-		text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4);
+		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
+
+		WARN_ONCE(!IS_ENABLED(CONFIG_FINEIBT_BHI) && arity,
+			  "kCFI preamble has wrong register at: %pS %*ph\n",
+			  addr, 5, addr);
+
+		if (cfi_bhi)
+			cfi_fineibt_bhi_preamble(addr, arity);
 	}
 
 	return 0;
 }
 
-static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod)
+static void cfi_rewrite_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr + 16, wr_addr + 16, false);
+		if (!exact_endbr(addr + 16))
+			continue;
+
+		poison_endbr(addr + 16);
 	}
 }
 
 /* .retpoline_sites */
-static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (hash) {
 			hash = -cfi_rehash(hash);
-			text_poke_early(wr_addr + 2, &hash, 4);
+			text_poke_early(addr + 2, &hash, 4);
 		}
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
+	BUG_ON(fineibt_paranoid_size != 20);
+
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
+		struct insn insn;
+		u8 bytes[20];
 		u32 hash;
+		int ret;
+		u8 op;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
-		if (hash) {
-			text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size);
-			WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678);
-			text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4);
+		hash = decode_caller_hash(addr);
+		if (!hash)
+			continue;
+
+		if (!cfi_paranoid) {
+			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
+			/* rely on apply_retpolines() */
+			continue;
+		}
+
+		/* cfi_paranoid */
+		ret = insn_decode_kernel(&insn, addr + fineibt_caller_size);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op = insn.opcode.bytes[0];
+		if (op != CALL_INSN_OPCODE && op != JMP32_INSN_OPCODE) {
+			WARN_ON_ONCE(1);
+			continue;
 		}
-		/* rely on apply_retpolines() */
+
+		memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size);
+		memcpy(bytes + fineibt_caller_hash, &hash, 4);
+
+		ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
+		if (WARN_ON_ONCE(ret != 3))
+			continue;
+
+		text_poke_early(addr, bytes, fineibt_paranoid_size);
 	}
 
 	return 0;
 }
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
-	bool builtin = mod ? false : true;
 	int ret;
 
 	if (WARN_ONCE(fineibt_preamble_size != 16,
@@ -1302,8 +1498,15 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	if (cfi_mode == CFI_AUTO) {
 		cfi_mode = CFI_KCFI;
-		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT))
+		if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) {
+			/*
+			 * FRED has much saner context on exception entry and
+			 * is less easy to take advantage of.
+			 */
+			if (!cpu_feature_enabled(X86_FEATURE_FRED))
+				cfi_paranoid = true;
 			cfi_mode = CFI_FINEIBT;
+		}
 	}
 
 	/*
@@ -1311,7 +1514,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	 * rewrite them. This disables all CFI. If this succeeds but any of the
 	 * later stages fails, we're without CFI.
 	 */
-	ret = cfi_disable_callers(start_retpoline, end_retpoline, mod);
+	ret = cfi_disable_callers(start_retpoline, end_retpoline);
 	if (ret)
 		goto err;
 
@@ -1322,11 +1525,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
 		}
 
-		ret = cfi_rand_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
-		ret = cfi_rand_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rand_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 	}
@@ -1338,7 +1541,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_KCFI:
-		ret = cfi_enable_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_enable_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
@@ -1348,20 +1551,23 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	case CFI_FINEIBT:
 		/* place the FineIBT preamble at func()-16 */
-		ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
 		/* rewrite the callers to target func()-16 */
-		ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
 		/* now that nobody targets func()+0, remove ENDBR there */
-		cfi_rewrite_endbr(start_cfi, end_cfi, mod);
+		cfi_rewrite_endbr(start_cfi, end_cfi);
 
-		if (builtin)
-			pr_info("Using FineIBT CFI\n");
+		if (builtin) {
+			pr_info("Using %sFineIBT%s CFI\n",
+				cfi_paranoid ? "paranoid " : "",
+				cfi_bhi ? "+BHI" : "");
+		}
 		return;
 
 	default:
@@ -1377,11 +1583,25 @@ static inline void poison_hash(void *addr)
 	*(u32 *)addr = 0;
 }
 
-static void poison_cfi(void *addr, void *wr_addr)
+static void poison_cfi(void *addr)
 {
+	/*
+	 * Compilers manage to be inconsistent with ENDBR vs __cfi prefixes,
+	 * some (static) functions for which they can determine the address
+	 * is never taken do not get a __cfi prefix, but *DO* get an ENDBR.
+	 *
+	 * As such, these functions will get sealed, but we need to be careful
+	 * to not unconditionally scribble the previous function.
+	 */
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
 		/*
+		 * FineIBT prefix should start with an ENDBR.
+		 */
+		if (!is_endbr(addr))
+			break;
+
+		/*
 		 * __cfi_\func:
 		 *	osp nopl (%rax)
 		 *	subl	$0, %r10d
@@ -1389,17 +1609,23 @@ static void poison_cfi(void *addr, void *wr_addr)
 		 *	ud2
 		 * 1:	nop
 		 */
-		poison_endbr(addr, wr_addr, false);
-		poison_hash(wr_addr + fineibt_preamble_hash);
+		poison_endbr(addr);
+		poison_hash(addr + fineibt_preamble_hash);
 		break;
 
 	case CFI_KCFI:
 		/*
+		 * kCFI prefix should start with a valid hash.
+		 */
+		if (!decode_preamble_hash(addr, NULL))
+			break;
+
+		/*
 		 * __cfi_\func:
 		 *	movl	$0, %eax
 		 *	.skip	11, 0x90
 		 */
-		poison_hash(wr_addr + 1);
+		poison_hash(addr + 1);
 		break;
 
 	default:
@@ -1407,24 +1633,135 @@ static void poison_cfi(void *addr, void *wr_addr)
 	}
 }
 
-#else
+/*
+ * When regs->ip points to a 0xEA byte in the FineIBT preamble,
+ * return true and fill out target and type.
+ *
+ * We check the preamble by checking for the ENDBR instruction relative to the
+ * 0xEA instruction.
+ */
+static bool decode_fineibt_preamble(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr = regs->ip - fineibt_preamble_ud;
+	u32 hash;
+
+	if (!exact_endbr((void *)addr))
+		return false;
+
+	*target = addr + fineibt_preamble_size;
+
+	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+	*type = (u32)regs->r10 + hash;
+
+	/*
+	 * Since regs->ip points to the middle of an instruction; it cannot
+	 * continue with the normal fixup.
+	 */
+	regs->ip = *target;
+
+	return true;
+
+Efault:
+	return false;
+}
+
+/*
+ * regs->ip points to one of the UD2 in __bhi_args[].
+ */
+static bool decode_fineibt_bhi(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr;
+	u32 hash;
+
+	if (!cfi_bhi)
+		return false;
+
+	if (regs->ip < (unsigned long)__bhi_args ||
+	    regs->ip >= (unsigned long)__bhi_args_end)
+		return false;
+
+	/*
+	 * Fetch the return address from the stack, this points to the
+	 * FineIBT preamble. Since the CALL instruction is in the 5 last
+	 * bytes of the preamble, the return address is in fact the target
+	 * address.
+	 */
+	__get_kernel_nofault(&addr, regs->sp, unsigned long, Efault);
+	*target = addr;
+
+	addr -= fineibt_preamble_size;
+	if (!exact_endbr((void *)addr))
+		return false;
+
+	__get_kernel_nofault(&hash, addr + fineibt_preamble_hash, u32, Efault);
+	*type = (u32)regs->r10 + hash;
+
+	/*
+	 * The UD2 sites are constructed with a RET immediately following,
+	 * as such the non-fatal case can use the regular fixup.
+	 */
+	return true;
+
+Efault:
+	return false;
+}
+
+/*
+ * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[]
+ * sequence.
+ */
+static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	unsigned long addr = regs->ip - fineibt_paranoid_ud;
+	u32 hash;
+
+	if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2))
+		return false;
+
+	__get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault);
+	*target = regs->r11 + fineibt_preamble_size;
+	*type = regs->r10;
+
+	/*
+	 * Since the trapping instruction is the exact, but LOCK prefixed,
+	 * Jcc.d8 that got us here, the normal fixup will work.
+	 */
+	return true;
+
+Efault:
+	return false;
+}
+
+bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type)
+{
+	if (decode_fineibt_paranoid(regs, target, type))
+		return true;
+
+	if (decode_fineibt_bhi(regs, target, type))
+		return true;
+
+	return decode_fineibt_preamble(regs, target, type);
+}
+
+#else /* !CONFIG_FINEIBT: */
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
 }
 
 #ifdef CONFIG_X86_KERNEL_IBT
-static void poison_cfi(void *addr, void *wr_addr) { }
+static void poison_cfi(void *addr) { }
 #endif
 
-#endif
+#endif /* !CONFIG_FINEIBT */
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 	return __apply_fineibt(start_retpoline, end_retpoline,
-			       start_cfi, end_cfi, mod);
+			       start_cfi, end_cfi,
+			       /* .builtin = */ false);
 }
 
 #ifdef CONFIG_SMP
@@ -1721,27 +2058,27 @@ void __init alternative_instructions(void)
 	paravirt_set_cap();
 
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
-			__cfi_sites, __cfi_sites_end, NULL);
+			__cfi_sites, __cfi_sites_end, true);
 
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since
 	 * those can rewrite the retpoline thunks.
 	 */
-	apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL);
-	apply_returns(__return_sites, __return_sites_end, NULL);
-
-	apply_alternatives(__alt_instructions, __alt_instructions_end, NULL);
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
 
 	/*
-	 * Now all calls are established. Apply the call thunks if
-	 * required.
+	 * Adjust all CALL instructions to point to func()-10, including
+	 * those in .altinstr_replacement.
 	 */
 	callthunks_patch_builtin_calls();
 
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
+
 	/*
 	 * Seal all functions that do not have their address taken.
 	 */
-	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL);
+	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
 
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 67e773744edb..6d12a9b69432 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -73,7 +73,6 @@ static int amd_cache_northbridges(void)
 	amd_northbridges.nb = nb;
 
 	for (i = 0; i < amd_northbridges.num; i++) {
-		node_to_amd_nb(i)->root = amd_node_get_root(i);
 		node_to_amd_nb(i)->misc = amd_node_get_func(i, 3);
 
 		/*
diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index d2ec7fd555c5..b670fa85c61b 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -8,6 +8,7 @@
  * Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
  */
 
+#include <linux/debugfs.h>
 #include <asm/amd_node.h>
 
 /*
@@ -93,10 +94,14 @@ static struct pci_dev **amd_roots;
 
 /* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
+static bool smn_exclusive;
 
 #define SMN_INDEX_OFFSET	0x60
 #define SMN_DATA_OFFSET		0x64
 
+#define HSMP_INDEX_OFFSET	0xc4
+#define HSMP_DATA_OFFSET	0xc8
+
 /*
  * SMN accesses may fail in ways that are difficult to detect here in the called
  * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do
@@ -146,6 +151,9 @@ static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, b
 	if (!root)
 		return err;
 
+	if (!smn_exclusive)
+		return err;
+
 	guard(mutex)(&smn_mutex);
 
 	err = pci_write_config_dword(root, i_off, address);
@@ -179,6 +187,93 @@ int __must_check amd_smn_write(u16 node, u32 address, u32 value)
 }
 EXPORT_SYMBOL_GPL(amd_smn_write);
 
+int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write)
+{
+	return __amd_smn_rw(HSMP_INDEX_OFFSET, HSMP_DATA_OFFSET, node, address, value, write);
+}
+EXPORT_SYMBOL_GPL(amd_smn_hsmp_rdwr);
+
+static struct dentry *debugfs_dir;
+static u16 debug_node;
+static u32 debug_address;
+
+static ssize_t smn_node_write(struct file *file, const char __user *userbuf,
+			      size_t count, loff_t *ppos)
+{
+	u16 node;
+	int ret;
+
+	ret = kstrtou16_from_user(userbuf, count, 0, &node);
+	if (ret)
+		return ret;
+
+	if (node >= amd_num_nodes())
+		return -ENODEV;
+
+	debug_node = node;
+	return count;
+}
+
+static int smn_node_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%08x\n", debug_node);
+	return 0;
+}
+
+static ssize_t smn_address_write(struct file *file, const char __user *userbuf,
+				 size_t count, loff_t *ppos)
+{
+	int ret;
+
+	ret = kstrtouint_from_user(userbuf, count, 0, &debug_address);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static int smn_address_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "0x%08x\n", debug_address);
+	return 0;
+}
+
+static int smn_value_show(struct seq_file *m, void *v)
+{
+	u32 val;
+	int ret;
+
+	ret = amd_smn_read(debug_node, debug_address, &val);
+	if (ret)
+		return ret;
+
+	seq_printf(m, "0x%08x\n", val);
+	return 0;
+}
+
+static ssize_t smn_value_write(struct file *file, const char __user *userbuf,
+			       size_t count, loff_t *ppos)
+{
+	u32 val;
+	int ret;
+
+	ret = kstrtouint_from_user(userbuf, count, 0, &val);
+	if (ret)
+		return ret;
+
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
+	ret = amd_smn_write(debug_node, debug_address, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_node);
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_address);
+DEFINE_SHOW_STORE_ATTRIBUTE(smn_value);
+
 static int amd_cache_roots(void)
 {
 	u16 node, num_nodes = amd_num_nodes();
@@ -193,6 +288,48 @@ static int amd_cache_roots(void)
 	return 0;
 }
 
+static int reserve_root_config_spaces(void)
+{
+	struct pci_dev *root = NULL;
+	struct pci_bus *bus = NULL;
+
+	while ((bus = pci_find_next_bus(bus))) {
+		/* Root device is Device 0 Function 0 on each Primary Bus. */
+		root = pci_get_slot(bus, 0);
+		if (!root)
+			continue;
+
+		if (root->vendor != PCI_VENDOR_ID_AMD &&
+		    root->vendor != PCI_VENDOR_ID_HYGON)
+			continue;
+
+		pci_dbg(root, "Reserving PCI config space\n");
+
+		/*
+		 * There are a few SMN index/data pairs and other registers
+		 * that shouldn't be accessed by user space.
+		 * So reserve the entire PCI config space for simplicity rather
+		 * than covering specific registers piecemeal.
+		 */
+		if (!pci_request_config_region_exclusive(root, 0, PCI_CFG_SPACE_SIZE, NULL)) {
+			pci_err(root, "Failed to reserve config space\n");
+			return -EEXIST;
+		}
+	}
+
+	smn_exclusive = true;
+	return 0;
+}
+
+static bool enable_dfs;
+
+static int __init amd_smn_enable_dfs(char *str)
+{
+	enable_dfs = true;
+	return 1;
+}
+__setup("amd_smn_debugfs_enable", amd_smn_enable_dfs);
+
 static int __init amd_smn_init(void)
 {
 	int err;
@@ -209,6 +346,18 @@ static int __init amd_smn_init(void)
 	if (err)
 		return err;
 
+	err = reserve_root_config_spaces();
+	if (err)
+		return err;
+
+	if (enable_dfs) {
+		debugfs_dir = debugfs_create_dir("amd_smn", arch_debugfs_dir);
+
+		debugfs_create_file("node",	0600, debugfs_dir, NULL, &smn_node_fops);
+		debugfs_create_file("address",	0600, debugfs_dir, NULL, &smn_address_fops);
+		debugfs_create_file("value",	0600, debugfs_dir, NULL, &smn_value_fops);
+	}
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 3bf0487cf3b7..52d1808ee360 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -23,8 +23,5 @@ obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o
 obj-y				+= apic_flat_64.o
 endif
 
-# APIC probe will depend on the listing order here
-obj-$(CONFIG_X86_BIGSMP)	+= bigsmp_32.o
-
 # For 32bit, probe_32 need to be listed last
 obj-$(CONFIG_X86_LOCAL_APIC)	+= probe_$(BITS).o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e893dc6f11c1..62584a347931 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1371,8 +1371,6 @@ void __init apic_intr_mode_init(void)
 
 	x86_64_probe_apic();
 
-	x86_32_install_bigsmp();
-
 	if (x86_platform.apic_post_init)
 		x86_platform.apic_post_init();
 
@@ -1674,7 +1672,6 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 	topology_register_boot_apic(boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
@@ -2014,8 +2011,8 @@ static bool __init detect_init_APIC(void)
 	case X86_VENDOR_HYGON:
 		break;
 	case X86_VENDOR_INTEL:
-		if (boot_cpu_data.x86 == 6 || boot_cpu_data.x86 == 15 ||
-		    (boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)))
+		if ((boot_cpu_data.x86 == 5 && boot_cpu_has(X86_FEATURE_APIC)) ||
+		    boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO)
 			break;
 		goto no_apic;
 	default:
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
deleted file mode 100644
index 9285d500d5b4..000000000000
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs.
- *
- * Drives the local APIC in "clustered mode".
- */
-#include <linux/cpumask.h>
-#include <linux/dmi.h>
-#include <linux/smp.h>
-
-#include <asm/apic.h>
-#include <asm/io_apic.h>
-
-#include "local.h"
-
-static u32 bigsmp_get_apic_id(u32 x)
-{
-	return (x >> 24) & 0xFF;
-}
-
-static void bigsmp_send_IPI_allbutself(int vector)
-{
-	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void bigsmp_send_IPI_all(int vector)
-{
-	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
-}
-
-static int dmi_bigsmp; /* can be set by dmi scanners */
-
-static int hp_ht_bigsmp(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
-	dmi_bigsmp = 1;
-
-	return 0;
-}
-
-
-static const struct dmi_system_id bigsmp_dmi_table[] = {
-	{ hp_ht_bigsmp, "HP ProLiant DL760 G2",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P44-"),
-		}
-	},
-
-	{ hp_ht_bigsmp, "HP ProLiant DL740",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P47-"),
-		}
-	},
-	{ } /* NULL entry stops DMI scanning */
-};
-
-static int probe_bigsmp(void)
-{
-	return dmi_check_system(bigsmp_dmi_table);
-}
-
-static struct apic apic_bigsmp __ro_after_init = {
-
-	.name				= "bigsmp",
-	.probe				= probe_bigsmp,
-
-	.dest_mode_logical		= false,
-
-	.disable_esr			= 1,
-
-	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-
-	.max_apic_id			= 0xFE,
-	.get_apic_id			= bigsmp_get_apic_id,
-
-	.calc_dest_apicid		= apic_default_calc_apicid,
-
-	.send_IPI			= default_send_IPI_single_phys,
-	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
-	.send_IPI_mask_allbutself	= NULL,
-	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
-	.send_IPI_all			= bigsmp_send_IPI_all,
-	.send_IPI_self			= default_send_IPI_self,
-
-	.read				= native_apic_mem_read,
-	.write				= native_apic_mem_write,
-	.eoi				= native_apic_mem_eoi,
-	.icr_read			= native_apic_icr_read,
-	.icr_write			= native_apic_icr_write,
-	.wait_icr_idle			= apic_mem_wait_icr_idle,
-	.safe_wait_icr_idle		= apic_mem_wait_icr_idle_timeout,
-};
-
-bool __init apic_bigsmp_possible(bool cmdline_override)
-{
-	return apic == &apic_bigsmp || !cmdline_override;
-}
-
-void __init apic_bigsmp_force(void)
-{
-	if (apic != &apic_bigsmp)
-		apic_install_driver(&apic_bigsmp);
-}
-
-apic_driver(apic_bigsmp);
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index 5da693d633b7..23025a3a1db4 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -287,34 +287,4 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
 	__default_send_IPI_dest_field(mask, vector, APIC_DEST_LOGICAL);
 	local_irq_restore(flags);
 }
-
-#ifdef CONFIG_SMP
-static int convert_apicid_to_cpu(u32 apic_id)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		if (per_cpu(x86_cpu_to_apicid, i) == apic_id)
-			return i;
-	}
-	return -1;
-}
-
-int safe_smp_processor_id(void)
-{
-	u32 apicid;
-	int cpuid;
-
-	if (!boot_cpu_has(X86_FEATURE_APIC))
-		return 0;
-
-	apicid = read_apic_id();
-	if (apicid == BAD_APICID)
-		return 0;
-
-	cpuid = convert_apicid_to_cpu(apicid);
-
-	return cpuid >= 0 ? cpuid : 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 842fe28496be..bdcf609eb283 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -65,17 +65,4 @@ void default_send_IPI_self(int vector);
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_logical(const struct cpumask *mask, int vector);
-void x86_32_probe_bigsmp_early(void);
-void x86_32_install_bigsmp(void);
-#else
-static inline void x86_32_probe_bigsmp_early(void) { }
-static inline void x86_32_install_bigsmp(void) { }
-#endif
-
-#ifdef CONFIG_X86_BIGSMP
-bool apic_bigsmp_possible(bool cmdline_selected);
-void apic_bigsmp_force(void);
-#else
-static inline bool apic_bigsmp_possible(bool cmdline_selected) { return false; };
-static inline void apic_bigsmp_force(void) { }
 #endif
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index f75ee345c02d..87bc9e7ca5d6 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -93,35 +93,6 @@ static int __init parse_apic(char *arg)
 }
 early_param("apic", parse_apic);
 
-void __init x86_32_probe_bigsmp_early(void)
-{
-	if (nr_cpu_ids <= 8 || xen_pv_domain())
-		return;
-
-	if (IS_ENABLED(CONFIG_X86_BIGSMP)) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(boot_cpu_apic_version))
-				break;
-			/* P4 and above */
-			fallthrough;
-		case X86_VENDOR_HYGON:
-		case X86_VENDOR_AMD:
-			if (apic_bigsmp_possible(cmdline_apic))
-				return;
-			break;
-		}
-	}
-	pr_info("Limiting to 8 possible CPUs\n");
-	set_nr_cpu_ids(8);
-}
-
-void __init x86_32_install_bigsmp(void)
-{
-	if (nr_cpu_ids > 8 && !xen_pv_domain())
-		apic_bigsmp_force();
-}
-
 void __init x86_32_probe_apic(void)
 {
 	if (!cmdline_apic) {
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index a98020bf31bb..ad4ea6fb3b6c 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -107,11 +107,6 @@ static void __used common(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
-	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
-	OFFSET(X86_current_task, pcpu_hot, current_task);
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-	OFFSET(X86_call_depth, pcpu_hot, call_depth);
-#endif
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
 	/* Offset for fields in aria_ctx */
 	BLANK();
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index bb65371ea9df..590b6cd0eac0 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -54,11 +54,5 @@ int main(void)
 	BLANK();
 #undef ENTRY
 
-	BLANK();
-
-#ifdef CONFIG_STACKPROTECTOR
-	OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
-	BLANK();
-#endif
 	return 0;
 }
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 8418a892d195..25ae54250112 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -240,21 +240,10 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct)
 }
 
 static __init_or_module void
-patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end,
-		     const struct core_text *ct)
-{
-	struct alt_instr *a;
-
-	for (a = start; a < end; a++)
-		patch_call((void *)&a->instr_offset + a->instr_offset, ct);
-}
-
-static __init_or_module void
 callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct)
 {
 	prdbg("Patching call sites %s\n", ct->name);
 	patch_call_sites(cs->call_start, cs->call_end, ct);
-	patch_alt_call_sites(cs->alt_start, cs->alt_end, ct);
 	prdbg("Patching call sites done%s\n", ct->name);
 }
 
@@ -263,8 +252,6 @@ void __init callthunks_patch_builtin_calls(void)
 	struct callthunk_sites cs = {
 		.call_start	= __call_sites,
 		.call_end	= __call_sites_end,
-		.alt_start	= __alt_instructions,
-		.alt_end	= __alt_instructions_end
 	};
 
 	if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH))
diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c
index e6bf78fac146..77086cf565ec 100644
--- a/arch/x86/kernel/cfi.c
+++ b/arch/x86/kernel/cfi.c
@@ -67,16 +67,30 @@ static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target,
  */
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
-	unsigned long target;
+	unsigned long target, addr = regs->ip;
 	u32 type;
 
-	if (!is_cfi_trap(regs->ip))
-		return BUG_TRAP_TYPE_NONE;
+	switch (cfi_mode) {
+	case CFI_KCFI:
+		if (!is_cfi_trap(addr))
+			return BUG_TRAP_TYPE_NONE;
+
+		if (!decode_cfi_insn(regs, &target, &type))
+			return report_cfi_failure_noaddr(regs, addr);
+
+		break;
 
-	if (!decode_cfi_insn(regs, &target, &type))
-		return report_cfi_failure_noaddr(regs, regs->ip);
+	case CFI_FINEIBT:
+		if (!decode_fineibt_insn(regs, &target, &type))
+			return BUG_TRAP_TYPE_NONE;
+
+		break;
+
+	default:
+		return BUG_TRAP_TYPE_NONE;
+	}
 
-	return report_cfi_failure(regs, regs->ip, &target, type);
+	return report_cfi_failure(regs, addr, &target, type);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 54194f5995de..79569f72b8ee 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -29,6 +29,8 @@
 
 #include "cpu.h"
 
+u16 invlpgb_count_max __ro_after_init;
+
 static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 {
 	u32 gprs[8] = { 0 };
@@ -632,7 +634,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 * (model = 0x14) and later actually support it.
 	 * (AMD Erratum #110, docId: 25759).
 	 */
-	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
 		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
 			value &= ~BIT_64(32);
@@ -1073,6 +1075,10 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	/* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */
 	clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE);
+
+	/* Enable Translation Cache Extension */
+	if (cpu_has(c, X86_FEATURE_TCE))
+		msr_set_bit(MSR_EFER, _EFER_TCE);
 }
 
 #ifdef CONFIG_X86_32
@@ -1105,8 +1111,8 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/*
 	 * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
@@ -1119,26 +1125,30 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		/* Erratum 658 */
 		if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
-			tlb_lli_2m[ENTRIES] = 1024;
+			tlb_lli_2m = 1024;
 		} else {
 			cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-			tlb_lli_2m[ENTRIES] = eax & 0xff;
+			tlb_lli_2m = eax & 0xff;
 		}
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
+
+	tlb_lli_4m = tlb_lli_2m >> 1;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	/* Max number of pages INVLPGB can invalidate in one shot */
+	if (cpu_has(c, X86_FEATURE_INVLPGB))
+		invlpgb_count_max = (cpuid_edx(0x80000008) & 0xffff) + 1;
 }
 
 static const struct cpu_dev amd_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index a6c6bccfa8b8..b3a520959b51 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -8,21 +8,19 @@
  *	Andi Kleen / Andreas Herrmann	: CPUID4 emulation on AMD.
  */
 
-#include <linux/slab.h>
 #include <linux/cacheinfo.h>
+#include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
-#include <linux/sched.h>
-#include <linux/capability.h>
-#include <linux/sysfs.h>
 #include <linux/pci.h>
 #include <linux/stop_machine.h>
+#include <linux/sysfs.h>
 
-#include <asm/cpufeature.h>
-#include <asm/cacheinfo.h>
 #include <asm/amd_nb.h>
-#include <asm/smp.h>
+#include <asm/cacheinfo.h>
+#include <asm/cpufeature.h>
 #include <asm/mtrr.h>
+#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 #include "cpu.h"
@@ -31,7 +29,6 @@
 #define LVL_1_DATA	2
 #define LVL_2		3
 #define LVL_3		4
-#define LVL_TRACE	5
 
 /* Shared last level cache maps */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
@@ -96,10 +93,6 @@ static const struct _cache_table cache_table[] =
 	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x68, LVL_1_DATA, 32 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x70, LVL_TRACE,  12 },	/* 8-way set assoc */
-	{ 0x71, LVL_TRACE,  16 },	/* 8-way set assoc */
-	{ 0x72, LVL_TRACE,  32 },	/* 8-way set assoc */
-	{ 0x73, LVL_TRACE,  64 },	/* 8-way set assoc */
 	{ 0x78, LVL_2,      MB(1) },	/* 4-way set assoc, 64 byte line size */
 	{ 0x79, LVL_2,      128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x7a, LVL_2,      256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -787,19 +780,13 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			}
 		}
 	}
-	/*
-	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
-	 * trace cache
-	 */
-	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
+
+	/* Don't use CPUID(2) if CPUID(4) is supported. */
+	if (!ci->num_leaves && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
-		int only_trace = 0;
-
-		if (ci->num_leaves && c->x86 == 15)
-			only_trace = 1;
 
 		/* Number of times to iterate */
 		n = cpuid_eax(2) & 0xFF;
@@ -820,8 +807,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 				/* look up this descriptor in the table */
 				while (cache_table[k].descriptor != 0) {
 					if (cache_table[k].descriptor == des) {
-						if (only_trace && cache_table[k].cache_type != LVL_TRACE)
-							break;
 						switch (cache_table[k].cache_type) {
 						case LVL_1_INST:
 							l1i += cache_table[k].size;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7cce91b19fb2..73565168fc19 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -667,8 +667,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
 		if (!warn)
 			continue;
 
-		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
-			x86_cap_flag(df->feature), df->level);
+		pr_warn("CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
+			x86_cap_flags[df->feature], df->level);
 	}
 }
 
@@ -846,13 +846,13 @@ void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 	c->x86_cache_size = l2size;
 }
 
-u16 __read_mostly tlb_lli_4k[NR_INFO];
-u16 __read_mostly tlb_lli_2m[NR_INFO];
-u16 __read_mostly tlb_lli_4m[NR_INFO];
-u16 __read_mostly tlb_lld_4k[NR_INFO];
-u16 __read_mostly tlb_lld_2m[NR_INFO];
-u16 __read_mostly tlb_lld_4m[NR_INFO];
-u16 __read_mostly tlb_lld_1g[NR_INFO];
+u16 __read_mostly tlb_lli_4k;
+u16 __read_mostly tlb_lli_2m;
+u16 __read_mostly tlb_lli_4m;
+u16 __read_mostly tlb_lld_4k;
+u16 __read_mostly tlb_lld_2m;
+u16 __read_mostly tlb_lld_4m;
+u16 __read_mostly tlb_lld_1g;
 
 static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 {
@@ -860,12 +860,10 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		this_cpu->c_detect_tlb(c);
 
 	pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
-		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
-		tlb_lli_4m[ENTRIES]);
+		tlb_lli_4k, tlb_lli_2m, tlb_lli_4m);
 
 	pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
-		tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
-		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
+		tlb_lld_4k, tlb_lld_2m, tlb_lld_4m, tlb_lld_1g);
 }
 
 void get_cpu_vendor(struct cpuinfo_x86 *c)
@@ -1164,7 +1162,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 
 	VULNWL_INTEL(INTEL_CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
+	VULNWL_INTEL(INTEL_ATOM_SILVERMONT_MID2,NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
 	VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	VULNWL_INTEL(INTEL_ATOM_GOLDMONT,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
@@ -1205,6 +1203,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define VULNBL_INTEL_STEPS(vfm, max_stepping, issues)		   \
 	X86_MATCH_VFM_STEPS(vfm, X86_STEP_MIN, max_stepping, issues)
 
+#define VULNBL_INTEL_TYPE(vfm, cpu_type, issues)	\
+	X86_MATCH_VFM_CPU_TYPE(vfm, INTEL_CPU_TYPE_##cpu_type, issues)
+
 #define VULNBL_AMD(family, blacklist)		\
 	VULNBL(AMD, family, X86_MODEL_ANY, blacklist)
 
@@ -1253,9 +1254,9 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_TIGERLAKE,	     X86_STEP_MAX,	GDS),
 	VULNBL_INTEL_STEPS(INTEL_LAKEFIELD,	     X86_STEP_MAX,	MMIO | MMIO_SBDS | RETBLEED),
 	VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE,	     X86_STEP_MAX,	MMIO | RETBLEED | GDS),
-	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE,	     X86_STEP_MAX,	RFDS),
+	VULNBL_INTEL_TYPE(INTEL_ALDERLAKE,		     ATOM,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L,	     X86_STEP_MAX,	RFDS),
-	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE,	     X86_STEP_MAX,	RFDS),
+	VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE,		     ATOM,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P,	     X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S,	     X86_STEP_MAX,	RFDS),
 	VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT,     X86_STEP_MAX,	RFDS),
@@ -1479,15 +1480,96 @@ static void detect_nopl(void)
 #endif
 }
 
+static inline bool parse_set_clear_cpuid(char *arg, bool set)
+{
+	char *opt;
+	int taint = 0;
+
+	while (arg) {
+		bool found __maybe_unused = false;
+		unsigned int bit;
+
+		opt = strsep(&arg, ",");
+
+		/*
+		 * Handle naked numbers first for feature flags which don't
+		 * have names. It doesn't make sense for a bug not to have a
+		 * name so don't handle bug flags here.
+		 */
+		if (!kstrtouint(opt, 10, &bit)) {
+			if (bit < NCAPINTS * 32) {
+
+				if (set) {
+					pr_warn("setcpuid: force-enabling CPU feature flag:");
+					setup_force_cpu_cap(bit);
+				} else {
+					pr_warn("clearcpuid: force-disabling CPU feature flag:");
+					setup_clear_cpu_cap(bit);
+				}
+				/* empty-string, i.e., ""-defined feature flags */
+				if (!x86_cap_flags[bit])
+					pr_cont(" %d:%d\n", bit >> 5, bit & 31);
+				else
+					pr_cont(" %s\n", x86_cap_flags[bit]);
+
+				taint++;
+			}
+			/*
+			 * The assumption is that there are no feature names with only
+			 * numbers in the name thus go to the next argument.
+			 */
+			continue;
+		}
+
+		for (bit = 0; bit < 32 * (NCAPINTS + NBUGINTS); bit++) {
+			const char *flag;
+			const char *kind;
+
+			if (bit < 32 * NCAPINTS) {
+				flag = x86_cap_flags[bit];
+				kind = "feature";
+			} else {
+				kind = "bug";
+				flag = x86_bug_flags[bit - (32 * NCAPINTS)];
+			}
+
+			if (!flag)
+				continue;
+
+			if (strcmp(flag, opt))
+				continue;
+
+			if (set) {
+				pr_warn("setcpuid: force-enabling CPU %s flag: %s\n",
+					kind, flag);
+				setup_force_cpu_cap(bit);
+			} else {
+				pr_warn("clearcpuid: force-disabling CPU %s flag: %s\n",
+					kind, flag);
+				setup_clear_cpu_cap(bit);
+			}
+			taint++;
+			found = true;
+			break;
+		}
+
+		if (!found)
+			pr_warn("%s: unknown CPU flag: %s", set ? "setcpuid" : "clearcpuid", opt);
+	}
+
+	return taint;
+}
+
+
 /*
  * We parse cpu parameters early because fpu__init_system() is executed
  * before parse_early_param().
  */
 static void __init cpu_parse_early_param(void)
 {
+	bool cpuid_taint = false;
 	char arg[128];
-	char *argptr = arg, *opt;
-	int arglen, taint = 0;
+	int arglen;
 
 #ifdef CONFIG_X86_32
 	if (cmdline_find_option_bool(boot_command_line, "no387"))
@@ -1519,61 +1601,17 @@ static void __init cpu_parse_early_param(void)
 		setup_clear_cpu_cap(X86_FEATURE_FRED);
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
-
-	pr_info("Clearing CPUID bits:");
-
-	while (argptr) {
-		bool found __maybe_unused = false;
-		unsigned int bit;
-
-		opt = strsep(&argptr, ",");
-
-		/*
-		 * Handle naked numbers first for feature flags which don't
-		 * have names.
-		 */
-		if (!kstrtouint(opt, 10, &bit)) {
-			if (bit < NCAPINTS * 32) {
-
-				/* empty-string, i.e., ""-defined feature flags */
-				if (!x86_cap_flags[bit])
-					pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit));
-				else
-					pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
-
-				setup_clear_cpu_cap(bit);
-				taint++;
-			}
-			/*
-			 * The assumption is that there are no feature names with only
-			 * numbers in the name thus go to the next argument.
-			 */
-			continue;
-		}
-
-		for (bit = 0; bit < 32 * NCAPINTS; bit++) {
-			if (!x86_cap_flag(bit))
-				continue;
-
-			if (strcmp(x86_cap_flag(bit), opt))
-				continue;
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, false);
 
-			pr_cont(" %s", opt);
-			setup_clear_cpu_cap(bit);
-			taint++;
-			found = true;
-			break;
-		}
+	arglen = cmdline_find_option(boot_command_line, "setcpuid", arg, sizeof(arg));
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, true);
 
-		if (!found)
-			pr_cont(" (unknown: %s)", opt);
-	}
-	pr_cont("\n");
-
-	if (taint)
+	if (cpuid_taint) {
+		pr_warn("!!! setcpuid=/clearcpuid= in use, this is for TESTING ONLY, may break things horribly. Tainting kernel.\n");
 		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	}
 }
 
 /*
@@ -1610,6 +1648,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 		c->cpu_index = 0;
 		filter_cpuid_features(c, false);
+		check_cpufeature_deps(c);
 
 		if (this_cpu->c_bsp_init)
 			this_cpu->c_bsp_init(c);
@@ -1870,6 +1909,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	/* Filter out anything that depends on CPUID levels we don't have */
 	filter_cpuid_features(c, true);
 
+	/* Check for unmet dependencies based on the CPUID dependency table */
+	check_cpufeature_deps(c);
+
 	/* If the model name is still unset, do table lookup. */
 	if (!c->x86_model_id[0]) {
 		const char *p;
@@ -1962,9 +2004,15 @@ static __init void identify_boot_cpu(void)
 	lkgs_init();
 }
 
-void identify_secondary_cpu(struct cpuinfo_x86 *c)
+void identify_secondary_cpu(unsigned int cpu)
 {
-	BUG_ON(c == &boot_cpu_data);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	/* Copy boot_cpu_data only on the first bringup */
+	if (!c->initialized)
+		*c = boot_cpu_data;
+	c->cpu_index = cpu;
+
 	identify_cpu(c);
 #ifdef CONFIG_X86_32
 	enable_sep_cpu();
@@ -1975,6 +2023,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 		update_gds_msr();
 
 	tsx_ap_init();
+	c->initialized = true;
 }
 
 void print_cpu_info(struct cpuinfo_x86 *c)
@@ -2005,27 +2054,40 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 }
 
 /*
- * clearcpuid= was already parsed in cpu_parse_early_param().  This dummy
- * function prevents it from becoming an environment variable for init.
+ * clearcpuid= and setcpuid= were already parsed in cpu_parse_early_param().
+ * These dummy functions prevent them from becoming an environment variable for
+ * init.
  */
+
 static __init int setup_clearcpuid(char *arg)
 {
 	return 1;
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
-DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
-	.current_task	= &init_task,
-	.preempt_count	= INIT_PREEMPT_COUNT,
-	.top_of_stack	= TOP_OF_INIT_STACK,
-};
-EXPORT_PER_CPU_SYMBOL(pcpu_hot);
-EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
+static __init int setup_setcpuid(char *arg)
+{
+	return 1;
+}
+__setup("setcpuid=", setup_setcpuid);
+
+DEFINE_PER_CPU_CACHE_HOT(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+EXPORT_PER_CPU_SYMBOL(const_current_task);
+
+DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
+
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
-		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
+/*
+ * Note: Do not make this dependant on CONFIG_MITIGATION_CALL_DEPTH_TRACKING
+ * so that this space is reserved in the hot cache section even when the
+ * mitigation is disabled.
+ */
+DEFINE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+EXPORT_PER_CPU_SYMBOL(__x86_call_depth);
 
 static void wrmsrl_cstar(unsigned long val)
 {
@@ -2089,18 +2151,15 @@ void syscall_init(void)
 	if (!cpu_feature_enabled(X86_FEATURE_FRED))
 		idt_syscall_init();
 }
-
-#else	/* CONFIG_X86_64 */
+#endif /* CONFIG_X86_64 */
 
 #ifdef CONFIG_STACKPROTECTOR
-DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, __stack_chk_guard);
 #ifndef CONFIG_SMP
 EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * Clear all 6 debug registers:
  */
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1beccefbaff9..51deb60a9d26 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -33,14 +33,6 @@ struct cpu_dev {
 #endif
 };
 
-struct _tlb_table {
-	unsigned char descriptor;
-	char tlb_type;
-	unsigned int entries;
-	/* unsigned int ways; */
-	char info[128];
-};
-
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
 	__section(".x86_cpu_dev.init") = \
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index df838e3bdbe0..a2fbea0be535 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -147,3 +147,38 @@ void setup_clear_cpu_cap(unsigned int feature)
 {
 	do_clear_cpu_cap(NULL, feature);
 }
+
+/*
+ * Return the feature "name" if available, otherwise return
+ * the X86_FEATURE_* numerals to make it easier to identify
+ * the feature.
+ */
+static const char *x86_feature_name(unsigned int feature, char *buf)
+{
+	if (x86_cap_flags[feature])
+		return x86_cap_flags[feature];
+
+	snprintf(buf, 16, "%d*32+%2d", feature / 32, feature % 32);
+
+	return buf;
+}
+
+void check_cpufeature_deps(struct cpuinfo_x86 *c)
+{
+	char feature_buf[16], depends_buf[16];
+	const struct cpuid_dep *d;
+
+	for (d = cpuid_deps; d->feature; d++) {
+		if (cpu_has(c, d->feature) && !cpu_has(c, d->depends)) {
+			/*
+			 * Only warn about the first unmet dependency on the
+			 * first CPU where it is encountered to avoid spamming
+			 * the kernel log.
+			 */
+			pr_warn_once("x86 CPU feature dependency check failure: CPU%d has '%s' enabled but '%s' disabled. Kernel might be fine, but no guarantees.\n",
+				     smp_processor_id(),
+				     x86_feature_name(d->feature, feature_buf),
+				     x86_feature_name(d->depends, depends_buf));
+		}
+	}
+}
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
index cacfd3f6abef..1976fef2dfe5 100644
--- a/arch/x86/kernel/cpu/debugfs.c
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -16,8 +16,8 @@ static int cpu_debug_show(struct seq_file *m, void *p)
 	if (!c->initialized)
 		return 0;
 
-	seq_printf(m, "initial_apicid:      %x\n", c->topo.initial_apicid);
-	seq_printf(m, "apicid:              %x\n", c->topo.apicid);
+	seq_printf(m, "initial_apicid:	    0x%x\n", c->topo.initial_apicid);
+	seq_printf(m, "apicid:		    0x%x\n", c->topo.apicid);
 	seq_printf(m, "pkg_id:              %u\n", c->topo.pkg_id);
 	seq_printf(m, "die_id:              %u\n", c->topo.die_id);
 	seq_printf(m, "cu_id:               %u\n", c->topo.cu_id);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index c5191b06f9f2..6af4a4a90a52 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -240,26 +240,26 @@ static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-		tlb_lli_2m[ENTRIES] = eax & 0xff;
+		tlb_lli_2m = eax & 0xff;
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev hygon_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 134368a3f4b1..4cbb2e69bea1 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1,40 +1,31 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/pgtable.h>
 
-#include <linux/string.h>
 #include <linux/bitops.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/thread_info.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/minmax.h>
+#include <linux/smp.h>
+#include <linux/string.h>
+
+#ifdef CONFIG_X86_64
+#include <linux/topology.h>
+#endif
 
-#include <asm/cpufeature.h>
-#include <asm/msr.h>
 #include <asm/bugs.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu.h>
+#include <asm/hwcap2.h>
 #include <asm/intel-family.h>
 #include <asm/microcode.h>
-#include <asm/hwcap2.h>
-#include <asm/elf.h>
-#include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
 #include <asm/numa.h>
+#include <asm/resctrl.h>
 #include <asm/thermal.h>
-
-#ifdef CONFIG_X86_64
-#include <linux/topology.h>
-#endif
+#include <asm/uaccess.h>
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#endif
-
 /*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
@@ -195,7 +186,7 @@ void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 		return;
 
-	if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd))
+	if (c->x86_vfm < INTEL_PENTIUM_M_DOTHAN)
 		return;
 
 	/*
@@ -210,10 +201,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
 
-	if ((c->x86 == 0xf && c->x86_model >= 0x03) ||
-		(c->x86 == 0x6 && c->x86_model >= 0x0e))
-		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
-
 	if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64))
 		c->microcode = intel_get_microcode_revision();
 
@@ -256,8 +243,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 #endif
 
 	/* CPUID workaround for 0F33/0F34 CPU */
-	if (c->x86 == 0xF && c->x86_model == 0x3
-	    && (c->x86_stepping == 0x3 || c->x86_stepping == 0x4))
+	if (c->x86_vfm == INTEL_P4_PRESCOTT &&
+	    (c->x86_stepping == 0x3 || c->x86_stepping == 0x4))
 		c->x86_phys_bits = 36;
 
 	/*
@@ -266,10 +253,16 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	 *
 	 * It is also reliable across cores and sockets. (but not across
 	 * cabinets - we turn it off in that case explicitly.)
+	 *
+	 * Use a model-specific check for some older CPUs that have invariant
+	 * TSC but may not report it architecturally via 8000_0007.
 	 */
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
+	} else if ((c->x86_vfm >= INTEL_P4_PRESCOTT && c->x86_vfm <= INTEL_P4_WILLAMETTE) ||
+		   (c->x86_vfm >= INTEL_CORE_YONAH  && c->x86_vfm <= INTEL_IVYBRIDGE)) {
+		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
@@ -298,12 +291,19 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 		clear_cpu_cap(c, X86_FEATURE_PAT);
 
 	/*
-	 * If fast string is not enabled in IA32_MISC_ENABLE for any reason,
-	 * clear the fast string and enhanced fast string CPU capabilities.
+	 * Modern CPUs are generally expected to have a sane fast string
+	 * implementation. However, BIOSes typically have a knob to tweak
+	 * the architectural MISC_ENABLE.FAST_STRING enable bit.
+	 *
+	 * Adhere to the preference and program the Linux-defined fast
+	 * string flag and enhanced fast string capabilities accordingly.
 	 */
-	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
+	if (c->x86_vfm >= INTEL_PENTIUM_M_DOTHAN) {
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-		if (!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) {
+		if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
+			/* X86_FEATURE_ERMS is set based on CPUID */
+			set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+		} else {
 			pr_info("Disabled fast string operations\n");
 			setup_clear_cpu_cap(X86_FEATURE_REP_GOOD);
 			setup_clear_cpu_cap(X86_FEATURE_ERMS);
@@ -350,9 +350,7 @@ static void bsp_init_intel(struct cpuinfo_x86 *c)
 int ppro_with_ram_bug(void)
 {
 	/* Uses data from early_cpu_detect now */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model == 1 &&
+	if (boot_cpu_data.x86_vfm == INTEL_PENTIUM_PRO &&
 	    boot_cpu_data.x86_stepping < 8) {
 		pr_info("Pentium Pro with Errata#50 detected. Taking evasive action.\n");
 		return 1;
@@ -369,9 +367,8 @@ static void intel_smp_check(struct cpuinfo_x86 *c)
 	/*
 	 * Mask B, Pentium, but not Pentium MMX
 	 */
-	if (c->x86 == 5 &&
-	    c->x86_stepping >= 1 && c->x86_stepping <= 4 &&
-	    c->x86_model <= 3) {
+	if (c->x86_vfm >= INTEL_FAM5_START && c->x86_vfm < INTEL_PENTIUM_MMX &&
+	    c->x86_stepping >= 1 && c->x86_stepping <= 4) {
 		/*
 		 * Remember we have B step Pentia with bugs
 		 */
@@ -398,7 +395,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * The Quark is also family 5, but does not have the same bug.
 	 */
 	clear_cpu_bug(c, X86_BUG_F00F);
-	if (c->x86 == 5 && c->x86_model < 9) {
+	if (c->x86_vfm >= INTEL_FAM5_START && c->x86_vfm < INTEL_QUARK_X1000) {
 		static int f00f_workaround_enabled;
 
 		set_cpu_bug(c, X86_BUG_F00F);
@@ -413,7 +410,8 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * SEP CPUID bug: Pentium Pro reports SEP but doesn't have it until
 	 * model 3 mask 3
 	 */
-	if ((c->x86<<8 | c->x86_model<<4 | c->x86_stepping) < 0x633)
+	if ((c->x86_vfm == INTEL_PENTIUM_II_KLAMATH && c->x86_stepping < 3) ||
+	    c->x86_vfm < INTEL_PENTIUM_II_KLAMATH)
 		clear_cpu_cap(c, X86_FEATURE_SEP);
 
 	/*
@@ -431,7 +429,7 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * P4 Xeon erratum 037 workaround.
 	 * Hardware prefetcher may cause stale data to be loaded into the cache.
 	 */
-	if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_stepping == 1)) {
+	if (c->x86_vfm == INTEL_P4_WILLAMETTE && c->x86_stepping == 1) {
 		if (msr_set_bit(MSR_IA32_MISC_ENABLE,
 				MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) > 0) {
 			pr_info("CPU: C0 stepping P4 Xeon detected.\n");
@@ -445,27 +443,20 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
 	 * integrated APIC (see 11AP erratum in "Pentium Processor
 	 * Specification Update").
 	 */
-	if (boot_cpu_has(X86_FEATURE_APIC) && (c->x86<<8 | c->x86_model<<4) == 0x520 &&
+	if (boot_cpu_has(X86_FEATURE_APIC) && c->x86_vfm == INTEL_PENTIUM_75 &&
 	    (c->x86_stepping < 0x6 || c->x86_stepping == 0xb))
 		set_cpu_bug(c, X86_BUG_11AP);
 
-
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	/*
-	 * Set up the preferred alignment for movsl bulk memory moves
+	 * MOVSL bulk memory moves can be slow when source and dest are not
+	 * both 8-byte aligned. PII/PIII only like MOVSL with 8-byte alignment.
+	 *
+	 * Set the preferred alignment for Pentium Pro and newer processors, as
+	 * it has only been tested on these.
 	 */
-	switch (c->x86) {
-	case 4:		/* 486: untested */
-		break;
-	case 5:		/* Old Pentia: untested */
-		break;
-	case 6:		/* PII/PIII only like movsl with 8-byte alignment */
+	if (c->x86_vfm >= INTEL_PENTIUM_PRO)
 		movsl_mask.mask = 7;
-		break;
-	case 15:	/* P4 is OK down to 8-byte alignment */
-		movsl_mask.mask = 7;
-		break;
-	}
 #endif
 
 	intel_smp_check(c);
@@ -563,8 +554,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;
-	if (c->x86 == 6)
-		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
 #else
 	/*
 	 * Names for the Pentium II/Celeron processors
@@ -622,14 +611,14 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 	 * to determine which, so we use a boottime override
 	 * for the 512kb model, and assume 256 otherwise.
 	 */
-	if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
+	if (c->x86_vfm == INTEL_PENTIUM_III_TUALATIN && size == 0)
 		size = 256;
 
 	/*
 	 * Intel Quark SoC X1000 contains a 4-way set associative
 	 * 16K cache with a 16 byte cache line and 256 lines per tag
 	 */
-	if ((c->x86 == 5) && (c->x86_model == 9))
+	if (c->x86_vfm == INTEL_QUARK_X1000)
 		size = 16;
 	return size;
 }
@@ -667,50 +656,58 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
  */
 #define TLB_0x63_2M_4M_ENTRIES	32
 
+struct _tlb_table {
+	unsigned char descriptor;
+	char tlb_type;
+	unsigned int entries;
+};
+
 static const struct _tlb_table intel_tlb_table[] = {
-	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
-	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
-	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages" },
-	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x55, TLB_INST_2M_4M,		7,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
-	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
-	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
-	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
-	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G_2M_4M,	4,	" TLB_DATA 1 GByte pages, 4-way set associative"
-						" (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here)" },
-	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
-	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
-	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
-	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
-	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
-	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
-	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
-	{ 0xc2, TLB_DATA_2M_4M,		16,	" TLB_DATA 2 MByte/4MByte pages, 4-way associative" },
-	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
+	{ 0x01, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages, 4-way set associative */
+	{ 0x02, TLB_INST_4M,		2},	/* TLB_INST 4 MByte pages, full associative */
+	{ 0x03, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	{ 0x04, TLB_DATA_4M,		8},	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	{ 0x05, TLB_DATA_4M,		32},	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	{ 0x0b, TLB_INST_4M,		4},	/* TLB_INST 4 MByte pages, 4-way set associative */
+	{ 0x4f, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages */
+	{ 0x50, TLB_INST_ALL,		64},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x51, TLB_INST_ALL,		128},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x52, TLB_INST_ALL,		256},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x55, TLB_INST_2M_4M,		7},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	{ 0x56, TLB_DATA0_4M,		16},	/* TLB_DATA0 4 MByte pages, 4-way set associative */
+	{ 0x57, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, 4-way associative */
+	{ 0x59, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, fully associative */
+	{ 0x5a, TLB_DATA0_2M_4M,	32},	/* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
+	{ 0x5b, TLB_DATA_4K_4M,		64},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x5c, TLB_DATA_4K_4M,		128},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x5d, TLB_DATA_4K_4M,		256},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x61, TLB_INST_4K,		48},	/* TLB_INST 4 KByte pages, full associative */
+	{ 0x63, TLB_DATA_1G_2M_4M,	4},	/* TLB_DATA 1 GByte pages, 4-way set associative
+						 * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
+	{ 0x6b, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 8-way associative */
+	{ 0x6c, TLB_DATA_2M_4M,		128},	/* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
+	{ 0x6d, TLB_DATA_1G,		16},	/* TLB_DATA 1 GByte pages, fully associative */
+	{ 0x76, TLB_INST_2M_4M,		8},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	{ 0xb0, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 4-way set associative */
+	{ 0xb1, TLB_INST_2M_4M,		4},	/* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
+	{ 0xb2, TLB_INST_4K,		64},	/* TLB_INST 4KByte pages, 4-way set associative */
+	{ 0xb3, TLB_DATA_4K,		128},	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	{ 0xb4, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 4-way associative */
+	{ 0xb5, TLB_INST_4K,		64},	/* TLB_INST 4 KByte pages, 8-way set associative */
+	{ 0xb6, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 8-way set associative */
+	{ 0xba, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way associative */
+	{ 0xc0, TLB_DATA_4K_4M,		8},	/* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
+	{ 0xc1, STLB_4K_2M,		1024},	/* STLB 4 KByte and 2 MByte pages, 8-way associative */
+	{ 0xc2, TLB_DATA_2M_4M,		16},	/* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
+	{ 0xca, STLB_4K,		512},	/* STLB 4 KByte pages, 4-way associative */
 	{ 0x00, 0, 0 }
 };
 
 static void intel_tlb_lookup(const unsigned char desc)
 {
+	unsigned int entries;
 	unsigned char k;
+
 	if (desc == 0)
 		return;
 
@@ -722,81 +719,58 @@ static void intel_tlb_lookup(const unsigned char desc)
 	if (intel_tlb_table[k].tlb_type == 0)
 		return;
 
+	entries = intel_tlb_table[k].entries;
 	switch (intel_tlb_table[k].tlb_type) {
 	case STLB_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case STLB_4K_2M:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_INST_ALL:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
 		break;
 	case TLB_INST_4M:
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_2M_4M:
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_DATA_4K:
 	case TLB_DATA0_4K:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case TLB_DATA_4M:
 	case TLB_DATA0_4M:
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_2M_4M:
 	case TLB_DATA0_2M_4M:
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_4K_4M:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_1G_2M_4M:
-		if (tlb_lld_2m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
-			tlb_lld_2m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
-		if (tlb_lld_4m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
-			tlb_lld_4m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		tlb_lld_2m = max(tlb_lld_2m, TLB_0x63_2M_4M_ENTRIES);
+		tlb_lld_4m = max(tlb_lld_4m, TLB_0x63_2M_4M_ENTRIES);
 		fallthrough;
 	case TLB_DATA_1G:
-		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_1g = max(tlb_lld_1g, entries);
 		break;
 	}
 }
@@ -891,34 +865,3 @@ static const struct cpu_dev intel_cpu_dev = {
 };
 
 cpu_dev_register(intel_cpu_dev);
-
-#define X86_HYBRID_CPU_TYPE_ID_SHIFT	24
-
-/**
- * get_this_hybrid_cpu_type() - Get the type of this hybrid CPU
- *
- * Returns the CPU type [31:24] (i.e., Atom or Core) of a CPU in
- * a hybrid processor. If the processor is not hybrid, returns 0.
- */
-u8 get_this_hybrid_cpu_type(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) >> X86_HYBRID_CPU_TYPE_ID_SHIFT;
-}
-
-/**
- * get_this_hybrid_cpu_native_id() - Get the native id of this hybrid CPU
- *
- * Returns the uarch native ID [23:0] of a CPU in a hybrid processor.
- * If the processor is not hybrid, returns 0.
- */
-u32 get_this_hybrid_cpu_native_id(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) &
-	       (BIT_ULL(X86_HYBRID_CPU_TYPE_ID_SHIFT) - 1);
-}
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 4f3c65429f82..6af1e8baeb0f 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -6,6 +6,34 @@
 #include <linux/slab.h>
 
 /**
+ * x86_match_vendor_cpu_type - helper function to match the hardware defined
+ *                             cpu-type for a single entry in the x86_cpu_id
+ *                             table. Note, this function does not match the
+ *                             generic cpu-types TOPO_CPU_TYPE_EFFICIENCY and
+ *                             TOPO_CPU_TYPE_PERFORMANCE.
+ * @c: Pointer to the cpuinfo_x86 structure of the CPU to match.
+ * @m: Pointer to the x86_cpu_id entry to match against.
+ *
+ * Return: true if the cpu-type matches, false otherwise.
+ */
+static bool x86_match_vendor_cpu_type(struct cpuinfo_x86 *c, const struct x86_cpu_id *m)
+{
+	if (m->type == X86_CPU_TYPE_ANY)
+		return true;
+
+	/* Hybrid CPUs are special, they are assumed to match all cpu-types */
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		return true;
+
+	if (c->x86_vendor == X86_VENDOR_INTEL)
+		return m->type == c->topo.intel_type;
+	if (c->x86_vendor == X86_VENDOR_AMD)
+		return m->type == c->topo.amd_type;
+
+	return false;
+}
+
+/**
  * x86_match_cpu - match current CPU against an array of x86_cpu_ids
  * @match: Pointer to array of x86_cpu_ids. Last entry terminated with
  *         {}.
@@ -50,6 +78,8 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 			continue;
 		if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature))
 			continue;
+		if (!x86_match_vendor_cpu_type(c, m))
+			continue;
 		return m;
 	}
 	return NULL;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index f3d534807d91..819199bc0119 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -74,7 +74,7 @@ void intel_collect_cpu_info(struct cpu_signature *sig)
 	sig->pf = 0;
 	sig->rev = intel_get_microcode_revision();
 
-	if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) {
+	if (IFM(x86_family(sig->sig), x86_model(sig->sig)) >= INTEL_PENTIUM_III_DESCHUTES) {
 		unsigned int val[2];
 
 		/* get processor flags from MSR 0x17 */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 2fdfda2b60e4..e2c6b471d230 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -9,9 +9,11 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/cc_platform.h>
+#include <linux/string_choices.h>
 #include <asm/processor-flags.h>
 #include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
 #include <asm/tlbflush.h>
@@ -646,10 +648,10 @@ static void __init print_mtrr_state(void)
 	pr_info("MTRR default type: %s\n",
 		mtrr_attrib_to_str(mtrr_state.def_type));
 	if (mtrr_state.have_fixed) {
-		pr_info("MTRR fixed ranges %sabled:\n",
-			((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
-			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ?
-			 "en" : "dis");
+		pr_info("MTRR fixed ranges %s:\n",
+			str_enabled_disabled(
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) &&
+			 (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)));
 		print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0);
 		for (i = 0; i < 2; ++i)
 			print_fixed(0x80000 + i * 0x20000, 0x04000,
@@ -661,8 +663,8 @@ static void __init print_mtrr_state(void)
 		/* tail */
 		print_fixed_last();
 	}
-	pr_info("MTRR variable ranges %sabled:\n",
-		mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis");
+	pr_info("MTRR variable ranges %s:\n",
+		str_enabled_disabled(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED));
 	high_width = (boot_cpu_data.x86_phys_bits - (32 - PAGE_SHIFT) + 3) / 4;
 
 	for (i = 0; i < num_var_ranges; ++i) {
@@ -1025,8 +1027,7 @@ int generic_validate_add_page(unsigned long base, unsigned long size,
 	 * For Intel PPro stepping <= 7
 	 * must be 4 MiB aligned and not touch 0x70000000 -> 0x7003FFFF
 	 */
-	if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model == 1 &&
+	if (mtrr_if == &generic_mtrr_ops && boot_cpu_data.x86_vfm == INTEL_PENTIUM_PRO &&
 	    boot_cpu_data.x86_stepping <= 7) {
 		if (base & ((1 << (22 - PAGE_SHIFT)) - 1)) {
 			pr_warn("mtrr: base(0x%lx000) is not 4 MiB aligned\n", base);
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index a5c506f6da7f..4049235b1bfe 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -99,7 +99,6 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	char *ptr;
 	char line[LINE_SIZE];
 	int length;
-	size_t linelen;
 
 	memset(line, 0, LINE_SIZE);
 
@@ -108,9 +107,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	if (length < 0)
 		return length;
 
-	linelen = strlen(line);
-	ptr = line + linelen - 1;
-	if (linelen && *ptr == '\n')
+	ptr = line + length - 1;
+	if (length && *ptr == '\n')
 		*ptr = '\0';
 
 	if (!strncmp(line, "disable=", 8)) {
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 340af8155658..0be61c45400c 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -140,7 +140,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	x86_platform.guest.enc_kexec_begin();
 	x86_platform.guest.enc_kexec_finish();
 
-	crash_save_cpu(regs, safe_smp_processor_id());
+	crash_save_cpu(regs, smp_processor_id());
 }
 
 #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG)
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index b4905d5173fd..722fd712e1cf 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -37,7 +37,7 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
@@ -62,7 +62,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.softirq_stack_ptr);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index f05339fee778..6c5defd6569a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -134,7 +134,7 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *begin;
 
 	/*
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 44f937015e1e..fc1714bad045 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -19,6 +19,7 @@
 #include <linux/usb/ehci_def.h>
 #include <linux/usb/xhci-dbgp.h>
 #include <asm/pci_x86.h>
+#include <linux/static_call.h>
 
 /* Simple VGA output */
 #define VGABASE		(__ISA_IO_base + 0xb8000)
@@ -94,26 +95,28 @@ static unsigned long early_serial_base = 0x3f8;  /* ttyS0 */
 #define DLL             0       /*  Divisor Latch Low         */
 #define DLH             1       /*  Divisor latch High        */
 
-static unsigned int io_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int io_serial_in(unsigned long addr, int offset)
 {
 	return inb(addr + offset);
 }
+ANNOTATE_NOENDBR_SYM(io_serial_in);
 
-static void io_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void io_serial_out(unsigned long addr, int offset, int value)
 {
 	outb(value, addr + offset);
 }
+ANNOTATE_NOENDBR_SYM(io_serial_out);
 
-static unsigned int (*serial_in)(unsigned long addr, int offset) = io_serial_in;
-static void (*serial_out)(unsigned long addr, int offset, int value) = io_serial_out;
+DEFINE_STATIC_CALL(serial_in, io_serial_in);
+DEFINE_STATIC_CALL(serial_out, io_serial_out);
 
 static int early_serial_putc(unsigned char ch)
 {
 	unsigned timeout = 0xffff;
 
-	while ((serial_in(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
+	while ((static_call(serial_in)(early_serial_base, LSR) & XMTRDY) == 0 && --timeout)
 		cpu_relax();
-	serial_out(early_serial_base, TXR, ch);
+	static_call(serial_out)(early_serial_base, TXR, ch);
 	return timeout ? 0 : -1;
 }
 
@@ -131,16 +134,16 @@ static __init void early_serial_hw_init(unsigned divisor)
 {
 	unsigned char c;
 
-	serial_out(early_serial_base, LCR, 0x3);	/* 8n1 */
-	serial_out(early_serial_base, IER, 0);	/* no interrupt */
-	serial_out(early_serial_base, FCR, 0);	/* no fifo */
-	serial_out(early_serial_base, MCR, 0x3);	/* DTR + RTS */
+	static_call(serial_out)(early_serial_base, LCR, 0x3);	/* 8n1 */
+	static_call(serial_out)(early_serial_base, IER, 0);	/* no interrupt */
+	static_call(serial_out)(early_serial_base, FCR, 0);	/* no fifo */
+	static_call(serial_out)(early_serial_base, MCR, 0x3);	/* DTR + RTS */
 
-	c = serial_in(early_serial_base, LCR);
-	serial_out(early_serial_base, LCR, c | DLAB);
-	serial_out(early_serial_base, DLL, divisor & 0xff);
-	serial_out(early_serial_base, DLH, (divisor >> 8) & 0xff);
-	serial_out(early_serial_base, LCR, c & ~DLAB);
+	c = static_call(serial_in)(early_serial_base, LCR);
+	static_call(serial_out)(early_serial_base, LCR, c | DLAB);
+	static_call(serial_out)(early_serial_base, DLL, divisor & 0xff);
+	static_call(serial_out)(early_serial_base, DLH, (divisor >> 8) & 0xff);
+	static_call(serial_out)(early_serial_base, LCR, c & ~DLAB);
 }
 
 #define DEFAULT_BAUD 9600
@@ -183,28 +186,26 @@ static __init void early_serial_init(char *s)
 	/* Convert from baud to divisor value */
 	divisor = 115200 / baud;
 
-	/* These will always be IO based ports */
-	serial_in = io_serial_in;
-	serial_out = io_serial_out;
-
 	/* Set up the HW */
 	early_serial_hw_init(divisor);
 }
 
 #ifdef CONFIG_PCI
-static void mem32_serial_out(unsigned long addr, int offset, int value)
+static __noendbr void mem32_serial_out(unsigned long addr, int offset, int value)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
 	/* shift implied by pointer type */
 	writel(value, vaddr + offset);
 }
+ANNOTATE_NOENDBR_SYM(mem32_serial_out);
 
-static unsigned int mem32_serial_in(unsigned long addr, int offset)
+static __noendbr unsigned int mem32_serial_in(unsigned long addr, int offset)
 {
 	u32 __iomem *vaddr = (u32 __iomem *)addr;
 	/* shift implied by pointer type */
 	return readl(vaddr + offset);
 }
+ANNOTATE_NOENDBR_SYM(mem32_serial_in);
 
 /*
  * early_pci_serial_init()
@@ -278,15 +279,13 @@ static __init void early_pci_serial_init(char *s)
 	 */
 	if ((bar0 & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
 		/* it is IO mapped */
-		serial_in = io_serial_in;
-		serial_out = io_serial_out;
 		early_serial_base = bar0 & PCI_BASE_ADDRESS_IO_MASK;
 		write_pci_config(bus, slot, func, PCI_COMMAND,
 				 cmdreg|PCI_COMMAND_IO);
 	} else {
 		/* It is memory mapped - assume 32-bit alignment */
-		serial_in = mem32_serial_in;
-		serial_out = mem32_serial_out;
+		static_call_update(serial_in, mem32_serial_in);
+		static_call_update(serial_out, mem32_serial_out);
 		/* WARNING! assuming the address is always in the first 4G */
 		early_serial_base =
 			(unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 166bc0ea3bdf..cace6e8d7cc7 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -118,13 +118,10 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
 		return ret;
 
 	/* replace the text with the new text */
-	if (ftrace_poke_late) {
+	if (ftrace_poke_late)
 		text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
-	} else {
-		mutex_lock(&text_mutex);
-		text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE);
-		mutex_unlock(&text_mutex);
-	}
+	else
+		text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
 	return 0;
 }
 
@@ -321,7 +318,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
 	union ftrace_op_code_union op_ptr;
-	void *ret;
+	int ret;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		start_offset = (unsigned long)ftrace_regs_caller;
@@ -352,15 +349,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = text_poke_copy(trampoline, (void *)start_offset, size);
-	if (WARN_ON(!ret))
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
+	if (WARN_ON(ret < 0))
 		goto fail;
 
 	ip = trampoline + size;
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
 		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
-		text_poke_copy(ip, retq, sizeof(retq));
+		memcpy(ip, retq, sizeof(retq));
 
 	/* No need to test direct calls on created trampolines */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
@@ -368,7 +365,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		ip = trampoline + (jmp_offset - start_offset);
 		if (WARN_ON(*(char *)ip != 0x75))
 			goto fail;
-		if (!text_poke_copy(ip, x86_nops[2], 2))
+		ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
+		if (ret < 0)
 			goto fail;
 	}
 
@@ -381,7 +379,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 */
 
 	ptr = (unsigned long *)(trampoline + size + RET_SIZE);
-	text_poke_copy(ptr, &ops, sizeof(unsigned long));
+	*ptr = (unsigned long)ops;
 
 	op_offset -= start_offset;
 	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
@@ -397,7 +395,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	op_ptr.offset = offset;
 
 	/* put in the new offset to the ftrace_ops */
-	text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
 
 	/* put in the call to the function */
 	mutex_lock(&text_mutex);
@@ -407,9 +405,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 * the depth accounting before the call already.
 	 */
 	dest = ftrace_ops_get_func(ops);
-	text_poke_copy_locked(trampoline + call_offset,
-	      text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
-	      CALL_INSN_SIZE, false);
+	memcpy(trampoline + call_offset,
+	       text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+	       CALL_INSN_SIZE);
 	mutex_unlock(&text_mutex);
 
 	/* ALLOC_TRAMP flags lets us know we created it */
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index d51647228596..367da3638167 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -146,12 +146,14 @@ SYM_FUNC_END(ftrace_stub_graph)
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
 
 SYM_FUNC_START(ftrace_caller)
+	ANNOTATE_NOENDBR
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
@@ -197,6 +199,7 @@ SYM_FUNC_END(ftrace_caller);
 STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
 
 SYM_FUNC_START(ftrace_regs_caller)
+	ANNOTATE_NOENDBR
 	/* Save the current flags before any operations that can change them */
 	pushfq
 
@@ -310,6 +313,7 @@ SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 
 SYM_FUNC_START(ftrace_stub_direct_tramp)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(ftrace_stub_direct_tramp)
@@ -317,6 +321,7 @@ SYM_FUNC_END(ftrace_stub_direct_tramp)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 SYM_FUNC_START(__fentry__)
+	ANNOTATE_NOENDBR
 	CALL_DEPTH_ACCOUNT
 
 	cmpq $ftrace_stub, ftrace_trace_function
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 368157a7f6d2..fa9b6339975f 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -565,7 +565,7 @@ void early_setup_idt(void)
  */
 void __head startup_64_setup_gdt_idt(void)
 {
-	struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt);
+	struct desc_struct *gdt = (void *)(__force unsigned long)gdt_page.gdt;
 	void *handler = NULL;
 
 	struct desc_ptr startup_gdt_descr = {
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 31345e0ba006..fefe2a25cf02 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -61,11 +61,14 @@ SYM_CODE_START_NOALIGN(startup_64)
 	/* Set up the stack for verify_cpu() */
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Setup GSBASE to allow stack canary access for C code */
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
 	movl	$MSR_GS_BASE, %ecx
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-	movl	%edx, %eax
-	shrq	$32,  %rdx
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	call	startup_64_setup_gdt_idt
@@ -319,7 +322,7 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	 *
 	 * RDX contains the per-cpu offset
 	 */
-	movq	pcpu_hot + X86_current_task(%rdx), %rax
+	movq	current_task(%rdx), %rax
 	movq	TASK_threadsp(%rax), %rsp
 
 	/*
@@ -359,17 +362,12 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
 	movl %eax,%fs
 	movl %eax,%gs
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data. If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-#ifndef CONFIG_SMP
-	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-#endif
 	movl	%edx, %eax
 	shrq	$32, %rdx
 	wrmsr
@@ -435,7 +433,7 @@ SYM_CODE_START(soft_restart_cpu)
 	UNWIND_HINT_END_OF_STACK
 
 	/* Find the idle task stack */
-	movq	PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx
+	movq	PER_CPU_VAR(current_task), %rcx
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index e2fab3ceb09f..6290dd120f5e 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -144,7 +144,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * Update the sequence number to force a TSS update on return to
 	 * user mode.
 	 */
-	iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
+	iobm->sequence = atomic64_inc_return(&io_bitmap_sequence);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index feca4f20b06a..81f9b78e0f7b 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -33,6 +33,11 @@
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
+DEFINE_PER_CPU_CACHE_HOT(u16, __softirq_pending);
+EXPORT_PER_CPU_SYMBOL(__softirq_pending);
+
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr);
+
 atomic_t irq_err_count;
 
 /*
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index dc1049c01f9b..c7a5d2960d57 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -29,12 +29,9 @@
 int sysctl_panic_on_stackoverflow __read_mostly;
 
 /* Debugging check for stack overflow: is there less than 1KB free? */
-static int check_stack_overflow(void)
+static bool check_stack_overflow(void)
 {
-	long sp;
-
-	__asm__ __volatile__("andl %%esp,%0" :
-			     "=r" (sp) : "0" (THREAD_SIZE - 1));
+	unsigned long sp = current_stack_pointer & (THREAD_SIZE - 1);
 
 	return sp < (sizeof(struct thread_info) + STACK_WARN);
 }
@@ -48,18 +45,19 @@ static void print_stack_overflow(void)
 }
 
 #else
-static inline int check_stack_overflow(void) { return 0; }
+static inline bool check_stack_overflow(void) { return false; }
 static inline void print_stack_overflow(void) { }
 #endif
 
+DEFINE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr);
+
 static void call_on_stack(void *func, void *stack)
 {
-	asm volatile("xchgl	%%ebx,%%esp	\n"
+	asm volatile("xchgl %[sp], %%esp\n"
 		     CALL_NOSPEC
-		     "movl	%%ebx,%%esp	\n"
-		     : "=b" (stack)
-		     : "0" (stack),
-		       [thunk_target] "D"(func)
+		     "movl %[sp], %%esp"
+		     : [sp] "+b" (stack)
+		     : [thunk_target] "D" (func)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
@@ -68,13 +66,13 @@ static inline void *current_stack(void)
 	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
 }
 
-static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
+static inline bool execute_on_irq_stack(bool overflow, struct irq_desc *desc)
 {
 	struct irq_stack *curstk, *irqstk;
-	u32 *isp, *prev_esp, arg1;
+	u32 *isp, *prev_esp;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr);
+	irqstk = __this_cpu_read(hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -83,7 +81,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	 * current stack (which is the irq stack already after all)
 	 */
 	if (unlikely(curstk == irqstk))
-		return 0;
+		return false;
 
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
@@ -94,14 +92,13 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
 
-	asm volatile("xchgl	%%ebx,%%esp	\n"
+	asm volatile("xchgl %[sp], %%esp\n"
 		     CALL_NOSPEC
-		     "movl	%%ebx,%%esp	\n"
-		     : "=a" (arg1), "=b" (isp)
-		     :  "0" (desc),   "1" (isp),
-			[thunk_target] "D" (desc->handle_irq)
-		     : "memory", "cc", "ecx");
-	return 1;
+		     "movl %[sp], %%esp"
+		     : "+a" (desc), [sp] "+b" (isp)
+		     : [thunk_target] "D" (desc->handle_irq)
+		     : "memory", "cc", "edx", "ecx");
+	return true;
 }
 
 /*
@@ -112,7 +109,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 	int node = cpu_to_node(cpu);
 	struct page *ph, *ps;
 
-	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
 		return 0;
 
 	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
@@ -124,8 +121,8 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 		return -ENOMEM;
 	}
 
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = page_address(ph);
-	per_cpu(pcpu_hot.softirq_stack_ptr, cpu) = page_address(ps);
+	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
+	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
 	return 0;
 }
 
@@ -135,7 +132,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(pcpu_hot.softirq_stack_ptr);
+	irqstk = __this_cpu_read(softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
@@ -150,7 +147,7 @@ void do_softirq_own_stack(void)
 
 void __handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	int overflow = check_stack_overflow();
+	bool overflow = check_stack_overflow();
 
 	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
 		if (unlikely(overflow))
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ade0043ce56e..ca78dce39361 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -26,8 +26,8 @@
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
+DEFINE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse);
 DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_backing_store);
 
 #ifdef CONFIG_VMAP_STACK
 /*
@@ -51,7 +51,7 @@ static int map_irq_stack(unsigned int cpu)
 		return -ENOMEM;
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -64,14 +64,14 @@ static int map_irq_stack(unsigned int cpu)
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
 	/* Store actual TOS to avoid adjustment in the hotpath */
-	per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif
 
 int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu))
+	if (per_cpu(hardirq_stack_ptr, cpu))
 		return 0;
 	return map_irq_stack(cpu);
 }
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index 7f542a7799cb..fdabd5dda154 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -9,6 +9,7 @@
  */
 .pushsection .noinstr.text, "ax"
 SYM_FUNC_START(native_save_fl)
+	ENDBR
 	pushf
 	pop %_ASM_AX
 	RET
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 72e6a45e7ec2..09608fd93687 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -373,16 +373,7 @@ out:
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	u32 insn;
-
-	/*
-	 * Since 'addr' is not guaranteed to be safe to access, use
-	 * copy_from_kernel_nofault() to read the instruction:
-	 */
-	if (copy_from_kernel_nofault(&insn, (void *)addr, sizeof(u32)))
-		return NULL;
-
-	if (is_endbr(insn)) {
+	if (is_endbr((u32 *)addr)) {
 		*on_func_entry = !offset || offset == 4;
 		if (*on_func_entry)
 			offset = 4;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7a422a6c5983..3be9b3342c67 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -838,7 +838,6 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	if (pv_tlb_flush_supported()) {
 		pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi;
-		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 8984abd91c00..a7998f351701 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -19,6 +19,7 @@
 #include <linux/jump_label.h>
 #include <linux/random.h>
 #include <linux/memory.h>
+#include <linux/stackprotector.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -130,6 +131,20 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 				goto overflow;
 			size = 4;
 			break;
+#if defined(CONFIG_STACKPROTECTOR) && \
+    defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+		case R_X86_64_REX_GOTPCRELX: {
+			static unsigned long __percpu *const addr = &__stack_chk_guard;
+
+			if (sym->st_value != (u64)addr) {
+				pr_err("%s: Unsupported GOTPCREL relocation\n", me->name);
+				return -ENOEXEC;
+			}
+
+			val = (u64)&addr + rel[i].r_addend;
+			fallthrough;
+		}
+#endif
 		case R_X86_64_PC32:
 		case R_X86_64_PLT32:
 			val -= (u64)loc;
@@ -146,21 +161,18 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 		}
 
 		if (apply) {
-			void *wr_loc = module_writable_address(me, loc);
-
-			if (memcmp(wr_loc, &zero, size)) {
+			if (memcmp(loc, &zero, size)) {
 				pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
 				       (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			write(wr_loc, &val, size);
+			write(loc, &val, size);
 		} else {
 			if (memcmp(loc, &val, size)) {
 				pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n",
 					(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			/* FIXME: needs care for ROX module allocations */
 			write(loc, &zero, size);
 		}
 	}
@@ -227,7 +239,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	const Elf_Shdr *s, *alt = NULL,
+	const Elf_Shdr *s, *alt = NULL, *locks = NULL,
 		*orc = NULL, *orc_ip = NULL,
 		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
 		*calls = NULL, *cfi = NULL;
@@ -236,6 +248,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
 		if (!strcmp(".altinstructions", secstrings + s->sh_name))
 			alt = s;
+		if (!strcmp(".smp_locks", secstrings + s->sh_name))
+			locks = s;
 		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -266,60 +280,33 @@ int module_finalize(const Elf_Ehdr *hdr,
 			csize = cfi->sh_size;
 		}
 
-		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me);
+		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
 	}
 	if (retpolines) {
 		void *rseg = (void *)retpolines->sh_addr;
-		apply_retpolines(rseg, rseg + retpolines->sh_size, me);
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
 	}
 	if (returns) {
 		void *rseg = (void *)returns->sh_addr;
-		apply_returns(rseg, rseg + returns->sh_size, me);
-	}
-	if (alt) {
-		/* patch .altinstructions */
-		void *aseg = (void *)alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size, me);
+		apply_returns(rseg, rseg + returns->sh_size);
 	}
-	if (calls || alt) {
+	if (calls) {
 		struct callthunk_sites cs = {};
 
-		if (calls) {
-			cs.call_start = (void *)calls->sh_addr;
-			cs.call_end = (void *)calls->sh_addr + calls->sh_size;
-		}
-
-		if (alt) {
-			cs.alt_start = (void *)alt->sh_addr;
-			cs.alt_end = (void *)alt->sh_addr + alt->sh_size;
-		}
+		cs.call_start = (void *)calls->sh_addr;
+		cs.call_end = (void *)calls->sh_addr + calls->sh_size;
 
 		callthunks_patch_module_calls(&cs, me);
 	}
+	if (alt) {
+		/* patch .altinstructions */
+		void *aseg = (void *)alt->sh_addr;
+		apply_alternatives(aseg, aseg + alt->sh_size);
+	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
-		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me);
+		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
 	}
-
-	if (orc && orc_ip)
-		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
-				   (void *)orc->sh_addr, orc->sh_size);
-
-	return 0;
-}
-
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *me)
-{
-	const Elf_Shdr *s, *locks = NULL;
-	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-
-	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
-		if (!strcmp(".smp_locks", secstrings + s->sh_name))
-			locks = s;
-	}
-
 	if (locks) {
 		void *lseg = (void *)locks->sh_addr;
 		void *text = me->mem[MOD_TEXT].base;
@@ -329,6 +316,10 @@ int module_post_finalize(const Elf_Ehdr *hdr,
 					    text, text_end);
 	}
 
+	if (orc && orc_ip)
+		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
+				   (void *)orc->sh_addr, orc->sh_size);
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ed163c8c8604..9a95d00f1423 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -40,8 +40,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
 
+/*
+ * An emergency handler can be set in any context including NMI
+ */
 struct nmi_desc {
 	raw_spinlock_t lock;
+	nmi_handler_t emerg_handler;
 	struct list_head head;
 };
 
@@ -132,9 +136,22 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration)
 static int nmi_handle(unsigned int type, struct pt_regs *regs)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
+	nmi_handler_t ehandler;
 	struct nmiaction *a;
 	int handled=0;
 
+	/*
+	 * Call the emergency handler, if set
+	 *
+	 * In the case of crash_nmi_callback() emergency handler, it will
+	 * return in the case of the crashing CPU to enable it to complete
+	 * other necessary crashing actions ASAP. Other handlers in the
+	 * linked list won't need to be run.
+	 */
+	ehandler = desc->emerg_handler;
+	if (ehandler)
+		return ehandler(type, regs);
+
 	rcu_read_lock();
 
 	/*
@@ -224,6 +241,31 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 }
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
+/**
+ * set_emergency_nmi_handler - Set emergency handler
+ * @type:    NMI type
+ * @handler: the emergency handler to be stored
+ *
+ * Set an emergency NMI handler which, if set, will preempt all the other
+ * handlers in the linked list. If a NULL handler is passed in, it will clear
+ * it. It is expected that concurrent calls to this function will not happen
+ * or the system is screwed beyond repair.
+ */
+void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+
+	if (WARN_ON_ONCE(desc->emerg_handler == handler))
+		return;
+	desc->emerg_handler = handler;
+
+	/*
+	 * Ensure the emergency handler is visible to other CPUs before
+	 * function return
+	 */
+	smp_wmb();
+}
+
 static void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccaa3397a67..97925632c28e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -59,21 +59,6 @@ void __init native_pv_lock_init(void)
 		static_branch_enable(&virt_spin_lock_key);
 }
 
-#ifndef CONFIG_PT_RECLAIM
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -90,30 +75,20 @@ void paravirt_set_sched_clock(u64 (*func)(void))
 	static_call_update(pv_sched_clock, func);
 }
 
-/* These are in entry.S */
-static struct resource reserve_ioports = {
-	.start = 0,
-	.end = IO_SPACE_LIMIT,
-	.name = "paravirt-ioport",
-	.flags = IORESOURCE_IO | IORESOURCE_BUSY,
-};
+#ifdef CONFIG_PARAVIRT_XXL
+static noinstr void pv_native_write_cr2(unsigned long val)
+{
+	native_write_cr2(val);
+}
 
-/*
- * Reserve the whole legacy IO space to prevent any legacy drivers
- * from wasting time probing for their hardware.  This is a fairly
- * brute-force approach to disabling all non-virtual drivers.
- *
- * Note that this must be called very early to have any effect.
- */
-int paravirt_disable_iospace(void)
+static noinstr unsigned long pv_native_read_cr3(void)
 {
-	return request_resource(&ioport_resource, &reserve_ioports);
+	return __native_read_cr3();
 }
 
-#ifdef CONFIG_PARAVIRT_XXL
-static noinstr void pv_native_write_cr2(unsigned long val)
+static noinstr void pv_native_write_cr3(unsigned long cr3)
 {
-	native_write_cr2(val);
+	native_write_cr3(cr3);
 }
 
 static noinstr unsigned long pv_native_get_debugreg(int regno)
@@ -195,7 +170,6 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
-	.mmu.tlb_remove_table	= native_tlb_remove_table,
 
 	.mmu.exit_mmap		= paravirt_nop,
 	.mmu.notify_page_enc_status_changed	= paravirt_nop,
@@ -203,8 +177,8 @@ struct paravirt_patch_template pv_ops = {
 #ifdef CONFIG_PARAVIRT_XXL
 	.mmu.read_cr2		= __PV_IS_CALLEE_SAVE(pv_native_read_cr2),
 	.mmu.write_cr2		= pv_native_write_cr2,
-	.mmu.read_cr3		= __native_read_cr3,
-	.mmu.write_cr3		= native_write_cr3,
+	.mmu.read_cr3		= pv_native_read_cr3,
+	.mmu.write_cr3		= pv_native_write_cr3,
 
 	.mmu.pgd_alloc		= __paravirt_pgd_alloc,
 	.mmu.pgd_free		= paravirt_nop,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6da6769d7254..5452237fabd4 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -1043,7 +1043,7 @@ unsigned long __get_wchan(struct task_struct *p)
 	return addr;
 }
 
-long do_arch_prctl_common(int option, unsigned long arg2)
+SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 {
 	switch (option) {
 	case ARCH_GET_CPUID:
@@ -1058,5 +1058,13 @@ long do_arch_prctl_common(int option, unsigned long arg2)
 		return fpu_xstate_prctl(option, arg2);
 	}
 
+	if (!in_ia32_syscall())
+		return do_arch_prctl_64(current, option, arg2);
+
 	return -EINVAL;
 }
+
+SYSCALL_DEFINE0(ni_syscall)
+{
+	return -ENOSYS;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0917c7f25720..4636ef359973 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -190,13 +190,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	arch_end_context_switch(next_p);
 
 	/*
-	 * Reload esp0 and pcpu_hot.top_of_stack.  This changes
+	 * Reload esp0 and cpu_current_top_of_stack.  This changes
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
 	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
-	this_cpu_write(pcpu_hot.top_of_stack,
+	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
 
@@ -206,7 +206,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	raw_cpu_write(pcpu_hot.current_task, next_p);
+	raw_cpu_write(current_task, next_p);
 
 	switch_fpu_finish(next_p);
 
@@ -215,8 +215,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	return prev_p;
 }
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	return do_arch_prctl_common(option, arg2);
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 226472332a70..7196ca7048be 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -614,7 +614,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
-		     this_cpu_read(pcpu_hot.hardirq_stack_inuse));
+		     this_cpu_read(hardirq_stack_inuse));
 
 	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
 		switch_fpu_prepare(prev_p, cpu);
@@ -668,8 +668,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	raw_cpu_write(pcpu_hot.current_task, next_p);
-	raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
+	raw_cpu_write(current_task, next_p);
+	raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	switch_fpu_finish(next_p);
 
@@ -942,7 +942,7 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 	case ARCH_MAP_VDSO_X32:
 		return prctl_map_vdso(&vdso_image_x32, arg2);
 # endif
-# if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+# ifdef CONFIG_IA32_EMULATION
 	case ARCH_MAP_VDSO_32:
 		return prctl_map_vdso(&vdso_image_32, arg2);
 # endif
@@ -979,26 +979,3 @@ long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2)
 
 	return ret;
 }
-
-SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	long ret;
-
-	ret = do_arch_prctl_64(current, option, arg2);
-	if (ret == -EINVAL)
-		ret = do_arch_prctl_common(option, arg2);
-
-	return ret;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-COMPAT_SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
-{
-	return do_arch_prctl_common(option, arg2);
-}
-#endif
-
-unsigned long KSTK_ESP(struct task_struct *task)
-{
-	return task_pt_regs(task)->sp;
-}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index dc1dd3f3e67f..964f6b0a3d68 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -921,20 +921,16 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 		return;
 
 	/* Make a note of crashing cpu. Will be used in NMI callback. */
-	crashing_cpu = safe_smp_processor_id();
+	crashing_cpu = smp_processor_id();
 
 	shootdown_callback = callback;
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	/* Would it be better to replace the trap vector here? */
-	if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
-				 NMI_FLAG_FIRST, "crash"))
-		return;		/* Return what? */
+
 	/*
-	 * Ensure the new callback function is set before sending
-	 * out the NMI
+	 * Set emergency handler to preempt other handlers.
 	 */
-	wmb();
+	set_emergency_nmi_handler(NMI_LOCAL, crash_nmi_callback);
 
 	apic_send_IPI_allbutself(NMI_VECTOR);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index cebee310e200..9f8ff3aad4f4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -56,6 +56,9 @@
 #include <asm/unwind.h>
 #include <asm/vsyscall.h>
 #include <linux/vmalloc.h>
+#if defined(CONFIG_X86_LOCAL_APIC)
+#include <asm/nmi.h>
+#endif
 
 /*
  * max_low_pfn_mapped: highest directly mapped pfn < 4 GB
@@ -146,6 +149,69 @@ static size_t ima_kexec_buffer_size;
 /* Boot loader ID and version as integers, for the benefit of proc_dointvec */
 int bootloader_type, bootloader_version;
 
+static const struct ctl_table x86_sysctl_table[] = {
+	{
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "panic_on_io_nmi",
+		.data		= &panic_on_io_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "bootloader_type",
+		.data		= &bootloader_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "bootloader_version",
+		.data		= &bootloader_version,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "io_delay_type",
+		.data		= &io_delay_type,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+#if defined(CONFIG_X86_LOCAL_APIC)
+	{
+		.procname       = "unknown_nmi_panic",
+		.data           = &unknown_nmi_panic,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#endif
+#if defined(CONFIG_ACPI_SLEEP)
+	{
+		.procname	= "acpi_video_flags",
+		.data		= &acpi_realmode_flags,
+		.maxlen		= sizeof(unsigned long),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+	},
+#endif
+};
+
+static int __init init_x86_sysctl(void)
+{
+	register_sysctl_init("kernel", x86_sysctl_table);
+	return 0;
+}
+arch_initcall(init_x86_sysctl);
+
 /*
  * Setup options
  */
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b30d6e180df7..bfa48e7a32a2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,18 +23,13 @@
 #include <asm/cpumask.h>
 #include <asm/cpu.h>
 
-#ifdef CONFIG_X86_64
-#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
-#else
-#define BOOT_PERCPU_OFFSET 0
-#endif
+DEFINE_PER_CPU_CACHE_HOT(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
 
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
-	[0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
 EXPORT_SYMBOL(__per_cpu_offset);
 
 /*
@@ -169,7 +164,7 @@ void __init setup_per_cpu_areas(void)
 	for_each_possible_cpu(cpu) {
 		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
-		per_cpu(pcpu_hot.cpu_number, cpu) = cpu;
+		per_cpu(cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
 		/*
 		 * Copy data used in early init routines from the
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index ef654530bf5a..98123ff10506 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -33,25 +33,55 @@
 #include <asm/smap.h>
 #include <asm/gsseg.h>
 
+/*
+ * The first GDT descriptor is reserved as 'NULL descriptor'.  As bits 0
+ * and 1 of a segment selector, i.e., the RPL bits, are NOT used to index
+ * GDT, selector values 0~3 all point to the NULL descriptor, thus values
+ * 0, 1, 2 and 3 are all valid NULL selector values.
+ *
+ * However IRET zeros ES, FS, GS, and DS segment registers if any of them
+ * is found to have any nonzero NULL selector value, which can be used by
+ * userspace in pre-FRED systems to spot any interrupt/exception by loading
+ * a nonzero NULL selector and waiting for it to become zero.  Before FRED
+ * there was nothing software could do to prevent such an information leak.
+ *
+ * ERETU, the only legit instruction to return to userspace from kernel
+ * under FRED, by design does NOT zero any segment register to avoid this
+ * problem behavior.
+ *
+ * As such, leave NULL selector values 0~3 unchanged.
+ */
+static inline u16 fixup_rpl(u16 sel)
+{
+	return sel <= 3 ? sel : sel | 3;
+}
+
 #ifdef CONFIG_IA32_EMULATION
 #include <asm/unistd_32_ia32.h>
 
 static inline void reload_segments(struct sigcontext_32 *sc)
 {
-	unsigned int cur;
+	u16 cur;
 
+	/*
+	 * Reload fs and gs if they have changed in the signal
+	 * handler.  This does not handle long fs/gs base changes in
+	 * the handler, but does not clobber them at least in the
+	 * normal case.
+	 */
 	savesegment(gs, cur);
-	if ((sc->gs | 0x03) != cur)
-		load_gs_index(sc->gs | 0x03);
+	if (fixup_rpl(sc->gs) != cur)
+		load_gs_index(fixup_rpl(sc->gs));
 	savesegment(fs, cur);
-	if ((sc->fs | 0x03) != cur)
-		loadsegment(fs, sc->fs | 0x03);
+	if (fixup_rpl(sc->fs) != cur)
+		loadsegment(fs, fixup_rpl(sc->fs));
+
 	savesegment(ds, cur);
-	if ((sc->ds | 0x03) != cur)
-		loadsegment(ds, sc->ds | 0x03);
+	if (fixup_rpl(sc->ds) != cur)
+		loadsegment(ds, fixup_rpl(sc->ds));
 	savesegment(es, cur);
-	if ((sc->es | 0x03) != cur)
-		loadsegment(es, sc->es | 0x03);
+	if (fixup_rpl(sc->es) != cur)
+		loadsegment(es, fixup_rpl(sc->es));
 }
 
 #define sigset32_t			compat_sigset_t
@@ -105,18 +135,12 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs,
 	regs->orig_ax = -1;
 
 #ifdef CONFIG_IA32_EMULATION
-	/*
-	 * Reload fs and gs if they have changed in the signal
-	 * handler.  This does not handle long fs/gs base changes in
-	 * the handler, but does not clobber them at least in the
-	 * normal case.
-	 */
 	reload_segments(&sc);
 #else
-	loadsegment(gs, sc.gs);
-	regs->fs = sc.fs;
-	regs->es = sc.es;
-	regs->ds = sc.ds;
+	loadsegment(gs, fixup_rpl(sc.gs));
+	regs->fs = fixup_rpl(sc.fs);
+	regs->es = fixup_rpl(sc.es);
+	regs->ds = fixup_rpl(sc.ds);
 #endif
 
 	return fpu__restore_sig(compat_ptr(sc.fpstate), 1);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c10850ae6f09..d6cf1e23c2a3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -190,7 +190,7 @@ static void ap_starting(void)
 	apic_ap_setup();
 
 	/* Save the processor parameters. */
-	smp_store_cpu_info(cpuid);
+	identify_secondary_cpu(cpuid);
 
 	/*
 	 * The topology information must be up to date before
@@ -215,7 +215,7 @@ static void ap_calibrate_delay(void)
 {
 	/*
 	 * Calibrate the delay loop and update loops_per_jiffy in cpu_data.
-	 * smp_store_cpu_info() stored a value that is close but not as
+	 * identify_secondary_cpu() stored a value that is close but not as
 	 * accurate as the value just calculated.
 	 *
 	 * As this is invoked after the TSC synchronization check,
@@ -229,7 +229,7 @@ static void ap_calibrate_delay(void)
 /*
  * Activate a secondary processor.
  */
-static void notrace start_secondary(void *unused)
+static void notrace __noendbr start_secondary(void *unused)
 {
 	/*
 	 * Don't put *anything* except direct CPU state initialization
@@ -314,26 +314,7 @@ static void notrace start_secondary(void *unused)
 	wmb();
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
-
-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
-void smp_store_cpu_info(int id)
-{
-	struct cpuinfo_x86 *c = &cpu_data(id);
-
-	/* Copy boot_cpu_data only on the first bringup */
-	if (!c->initialized)
-		*c = boot_cpu_data;
-	c->cpu_index = id;
-	/*
-	 * During boot time, CPU0 has this setup already. Save the info when
-	 * bringing up an AP.
-	 */
-	identify_secondary_cpu(c);
-	c->initialized = true;
-}
+ANNOTATE_NOENDBR_SYM(start_secondary);
 
 static bool
 topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
@@ -654,10 +635,9 @@ static void impress_friends(void)
  * But that slows boot and resume on modern processors, which include
  * many cores and don't require that delay.
  *
- * Cmdline "init_cpu_udelay=" is available to over-ride this delay.
- * Modern processor families are quirked to remove the delay entirely.
+ * Cmdline "cpu_init_udelay=" is available to override this delay.
  */
-#define UDELAY_10MS_DEFAULT 10000
+#define UDELAY_10MS_LEGACY 10000
 
 static unsigned int init_udelay = UINT_MAX;
 
@@ -669,21 +649,21 @@ static int __init cpu_init_udelay(char *str)
 }
 early_param("cpu_init_udelay", cpu_init_udelay);
 
-static void __init smp_quirk_init_udelay(void)
+static void __init smp_set_init_udelay(void)
 {
 	/* if cmdline changed it from default, leave it alone */
 	if (init_udelay != UINT_MAX)
 		return;
 
 	/* if modern processor, use no delay */
-	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) && (boot_cpu_data.x86 >= 0x18)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
+	if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86_vfm >= INTEL_PENTIUM_PRO) ||
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON && boot_cpu_data.x86 >= 0x18) ||
+	    (boot_cpu_data.x86_vendor == X86_VENDOR_AMD   && boot_cpu_data.x86 >= 0xF)) {
 		init_udelay = 0;
 		return;
 	}
 	/* else, use legacy delay */
-	init_udelay = UDELAY_10MS_DEFAULT;
+	init_udelay = UDELAY_10MS_LEGACY;
 }
 
 /*
@@ -841,7 +821,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
-	per_cpu(pcpu_hot.current_task, cpu) = idle;
+	per_cpu(current_task, cpu) = idle;
 	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */
@@ -851,7 +831,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
+	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #endif
 	return 0;
 }
@@ -1094,7 +1074,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 
 	uv_system_init();
 
-	smp_quirk_init_udelay();
+	smp_set_init_udelay();
 
 	speculative_store_bypass_ht_init();
 
@@ -1262,43 +1242,9 @@ void play_dead_common(void)
  * We need to flush the caches before going to sleep, lest we have
  * dirty data in our caches when we come back up.
  */
-static inline void mwait_play_dead(void)
+void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
 
 	/* Set up state for the kexec() hack below */
 	md->status = CPUDEAD_MWAIT_WAIT;
@@ -1319,7 +1265,7 @@ static inline void mwait_play_dead(void)
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
@@ -1391,9 +1337,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 5e3e036e6e53..9f88b8a78e50 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -94,10 +94,20 @@ __always_inline int is_valid_bugaddr(unsigned long addr)
 
 /*
  * Check for UD1 or UD2, accounting for Address Size Override Prefixes.
- * If it's a UD1, get the ModRM byte to pass along to UBSan.
+ * If it's a UD1, further decode to determine its use:
+ *
+ * FineIBT:      ea                      (bad)
+ * FineIBT:      f0 75 f9                lock jne . - 6
+ * UBSan{0}:     67 0f b9 00             ud1    (%eax),%eax
+ * UBSan{10}:    67 0f b9 40 10          ud1    0x10(%eax),%eax
+ * static_call:  0f b9 cc                ud1    %esp,%ecx
+ *
+ * Notably UBSAN uses EAX, static_call uses ECX.
  */
-__always_inline int decode_bug(unsigned long addr, u32 *imm)
+__always_inline int decode_bug(unsigned long addr, s32 *imm, int *len)
 {
+	unsigned long start = addr;
+	bool lock = false;
 	u8 v;
 
 	if (addr < TASK_SIZE_MAX)
@@ -106,28 +116,67 @@ __always_inline int decode_bug(unsigned long addr, u32 *imm)
 	v = *(u8 *)(addr++);
 	if (v == INSN_ASOP)
 		v = *(u8 *)(addr++);
-	if (v != OPCODE_ESCAPE)
+
+	if (v == INSN_LOCK) {
+		lock = true;
+		v = *(u8 *)(addr++);
+	}
+
+	switch (v) {
+	case 0x70 ... 0x7f: /* Jcc.d8 */
+		addr += 1; /* d8 */
+		*len = addr - start;
+		WARN_ON_ONCE(!lock);
+		return BUG_LOCK;
+
+	case 0xea:
+		*len = addr - start;
+		return BUG_EA;
+
+	case OPCODE_ESCAPE:
+		break;
+
+	default:
 		return BUG_NONE;
+	}
 
 	v = *(u8 *)(addr++);
-	if (v == SECOND_BYTE_OPCODE_UD2)
+	if (v == SECOND_BYTE_OPCODE_UD2) {
+		*len = addr - start;
 		return BUG_UD2;
+	}
 
-	if (!IS_ENABLED(CONFIG_UBSAN_TRAP) || v != SECOND_BYTE_OPCODE_UD1)
+	if (v != SECOND_BYTE_OPCODE_UD1)
 		return BUG_NONE;
 
-	/* Retrieve the immediate (type value) for the UBSAN UD1 */
-	v = *(u8 *)(addr++);
-	if (X86_MODRM_RM(v) == 4)
-		addr++;
-
 	*imm = 0;
-	if (X86_MODRM_MOD(v) == 1)
-		*imm = *(u8 *)addr;
-	else if (X86_MODRM_MOD(v) == 2)
-		*imm = *(u32 *)addr;
-	else
-		WARN_ONCE(1, "Unexpected MODRM_MOD: %u\n", X86_MODRM_MOD(v));
+	v = *(u8 *)(addr++);		/* ModRM */
+
+	if (X86_MODRM_MOD(v) != 3 && X86_MODRM_RM(v) == 4)
+		addr++;			/* SIB */
+
+	/* Decode immediate, if present */
+	switch (X86_MODRM_MOD(v)) {
+	case 0: if (X86_MODRM_RM(v) == 5)
+			addr += 4; /* RIP + disp32 */
+		break;
+
+	case 1: *imm = *(s8 *)addr;
+		addr += 1;
+		break;
+
+	case 2: *imm = *(s32 *)addr;
+		addr += 4;
+		break;
+
+	case 3: break;
+	}
+
+	/* record instruction length */
+	*len = addr - start;
+
+	if (X86_MODRM_REG(v) == 0)	/* EAX */
+		return BUG_UD1_UBSAN;
 
 	return BUG_UD1;
 }
@@ -257,11 +306,12 @@ static inline void handle_invalid_op(struct pt_regs *regs)
 
 static noinstr bool handle_bug(struct pt_regs *regs)
 {
+	unsigned long addr = regs->ip;
 	bool handled = false;
-	int ud_type;
-	u32 imm;
+	int ud_type, ud_len;
+	s32 ud_imm;
 
-	ud_type = decode_bug(regs->ip, &imm);
+	ud_type = decode_bug(addr, &ud_imm, &ud_len);
 	if (ud_type == BUG_NONE)
 		return handled;
 
@@ -281,15 +331,47 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 */
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_enable();
-	if (ud_type == BUG_UD2) {
-		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN ||
-		    handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
-			regs->ip += LEN_UD2;
+
+	switch (ud_type) {
+	case BUG_UD2:
+		if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
 			handled = true;
+			break;
 		}
-	} else if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
-		pr_crit("%s at %pS\n", report_ubsan_failure(regs, imm), (void *)regs->ip);
+		fallthrough;
+
+	case BUG_EA:
+	case BUG_LOCK:
+		if (handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) {
+			handled = true;
+			break;
+		}
+		break;
+
+	case BUG_UD1_UBSAN:
+		if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
+			pr_crit("%s at %pS\n",
+				report_ubsan_failure(regs, ud_imm),
+				(void *)regs->ip);
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	/*
+	 * When continuing, and regs->ip hasn't changed, move it to the next
+	 * instruction. When not continuing execution, restore the instruction
+	 * pointer.
+	 */
+	if (handled) {
+		if (regs->ip == addr)
+			regs->ip += ud_len;
+	} else {
+		regs->ip = addr;
 	}
+
 	if (regs->flags & X86_EFLAGS_IF)
 		raw_local_irq_disable();
 	instrumentation_end();
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index deeb02825670..48e6cc1cb017 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -152,7 +152,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	&freq_desc_byt),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID,	&freq_desc_tng),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	&freq_desc_cht),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,	&freq_desc_ann),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,	&freq_desc_ann),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP,	&freq_desc_lgm),
 	{}
 };
diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S
index 1258a5872d12..37ad43792452 100644
--- a/arch/x86/kernel/verify_cpu.S
+++ b/arch/x86/kernel/verify_cpu.S
@@ -29,8 +29,12 @@
  */
 
 #include <asm/cpufeatures.h>
+#include <asm/cpufeaturemasks.h>
 #include <asm/msr-index.h>
 
+#define SSE_MASK	\
+	(REQUIRED_MASK0 & ((1<<(X86_FEATURE_XMM & 31)) | (1<<(X86_FEATURE_XMM2 & 31))))
+
 SYM_FUNC_START_LOCAL(verify_cpu)
 	pushf				# Save caller passed flags
 	push	$0			# Kill any dangerous flags
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0deb4887d6e9..ccdc45e5b759 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -43,7 +43,8 @@ ENTRY(phys_startup_64)
 #endif
 
 jiffies = jiffies_64;
-const_pcpu_hot = pcpu_hot;
+const_current_task = current_task;
+const_cpu_current_top_of_stack = cpu_current_top_of_stack;
 
 #if defined(CONFIG_X86_64)
 /*
@@ -112,12 +113,6 @@ ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX
 PHDRS {
 	text PT_LOAD FLAGS(5);          /* R_E */
 	data PT_LOAD FLAGS(6);          /* RW_ */
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_SMP
-	percpu PT_LOAD FLAGS(6);        /* RW_ */
-#endif
-	init PT_LOAD FLAGS(7);          /* RWE */
-#endif
 	note PT_NOTE FLAGS(0);          /* ___ */
 }
 
@@ -193,6 +188,8 @@ SECTIONS
 
 		PAGE_ALIGNED_DATA(PAGE_SIZE)
 
+		CACHE_HOT_DATA(L1_CACHE_BYTES)
+
 		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 
 		DATA_DATA
@@ -216,21 +213,7 @@ SECTIONS
 		__init_begin = .; /* paired with __init_end */
 	}
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
-	/*
-	 * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
-	 * output PHDR, so the next output section - .init.text - should
-	 * start another segment - init.
-	 */
-	PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
-	ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
-	       "per-CPU data too large - increase CONFIG_PHYSICAL_START")
-#endif
-
 	INIT_TEXT_SECTION(PAGE_SIZE)
-#ifdef CONFIG_X86_64
-	:init
-#endif
 
 	/*
 	 * Section for code used exclusively before alternatives are run. All
@@ -347,9 +330,8 @@ SECTIONS
 		EXIT_DATA
 	}
 
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
-	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
+	PERCPU_SECTION(L1_CACHE_BYTES)
+	ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot data too large")
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)
@@ -493,19 +475,6 @@ SECTIONS
 PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
 
 #ifdef CONFIG_X86_64
-/*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(fixed_percpu_data);
-INIT_PER_CPU(irq_stack_backing_store);
-
-#ifdef CONFIG_SMP
-. = ASSERT((fixed_percpu_data == 0),
-           "fixed_percpu_data is not at start of per-cpu area");
-#endif
 
 #ifdef CONFIG_MITIGATION_UNRET_ENTRY
 . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index 633c87e2fd92..96677576c836 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -118,7 +118,7 @@ do_exception:
 
 #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
 
-	asm volatile("1: vmread %2, %1\n\t"
+	asm volatile("1: vmread %[field], %[output]\n\t"
 		     ".byte 0x3e\n\t" /* branch taken hint */
 		     "ja 3f\n\t"
 
@@ -127,24 +127,26 @@ do_exception:
 		      * @field, and bounce through the trampoline to preserve
 		      * volatile registers.
 		      */
-		     "xorl %k1, %k1\n\t"
+		     "xorl %k[output], %k[output]\n\t"
 		     "2:\n\t"
-		     "push %1\n\t"
-		     "push %2\n\t"
+		     "push %[output]\n\t"
+		     "push %[field]\n\t"
 		     "call vmread_error_trampoline\n\t"
 
 		     /*
 		      * Unwind the stack.  Note, the trampoline zeros out the
 		      * memory for @fault so that the result is '0' on error.
 		      */
-		     "pop %2\n\t"
-		     "pop %1\n\t"
+		     "pop %[field]\n\t"
+		     "pop %[output]\n\t"
 		     "3:\n\t"
 
 		     /* VMREAD faulted.  As above, except push '1' for @fault. */
-		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %1)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_ONE_REG, %[output])
 
-		     : ASM_CALL_CONSTRAINT, "=&r"(value) : "r"(field) : "cc");
+		     : ASM_CALL_CONSTRAINT, [output] "=&r" (value)
+		     : [field] "r" (field)
+		     : "cc");
 	return value;
 
 #endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8a59c61624c2..64ccecedc9f8 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -56,7 +56,7 @@ ifeq ($(CONFIG_X86_32),y)
         lib-y += string_32.o
         lib-y += memmove_32.o
         lib-y += cmpxchg8b_emu.o
-ifneq ($(CONFIG_X86_CMPXCHG64),y)
+ifneq ($(CONFIG_X86_CX8),y)
         lib-y += atomic64_386_32.o
 endif
 else
@@ -66,5 +66,6 @@ endif
         lib-y += clear_page_64.o copy_page_64.o
         lib-y += memmove_64.o memset_64.o
         lib-y += copy_user_64.o copy_user_uncached_64.o
-	lib-y += cmpxchg16b_emu.o
+        lib-y += cmpxchg16b_emu.o
+        lib-y += bhi.o
 endif
diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S
new file mode 100644
index 000000000000..58891681261b
--- /dev/null
+++ b/arch/x86/lib/bhi.S
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/unwind_hints.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * Notably, the FineIBT preamble calling these will have ZF set and r10 zero.
+ *
+ * The very last element is in fact larger than 32 bytes, but since its the
+ * last element, this does not matter,
+ *
+ * There are 2 #UD sites, located between 0,1-2,3 and 4,5-6,7 such that they
+ * can be reached using Jcc.d8, these elements (1 and 5) have sufficiently
+ * big alignment holes for this to not stagger the array.
+ */
+
+.pushsection .noinstr.text, "ax"
+
+	.align 32
+SYM_CODE_START(__bhi_args)
+
+#ifdef CONFIG_FINEIBT_BHI
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_0, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 8
+	ANNOTATE_REACHABLE
+.Lud_1:	ud2
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_1
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 8
+	ANNOTATE_REACHABLE
+.Lud_2:	ud2
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	cmovne %r10, %r9
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	jne .Lud_2
+	cmovne %r10, %rdi
+	cmovne %r10, %rsi
+	cmovne %r10, %rdx
+	cmovne %r10, %rcx
+	cmovne %r10, %r8
+	cmovne %r10, %r9
+	cmovne %r10, %rsp
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+
+#endif /* CONFIG_FINEIBT_BHI */
+
+	.align 32
+SYM_INNER_LABEL(__bhi_args_end, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	nop /* Work around toolchain+objtool quirk */
+SYM_CODE_END(__bhi_args)
+
+.popsection
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 2760a15fbc00..a508e4a8c66a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 #include <asm/asm.h>
 
 /*
@@ -14,7 +16,7 @@
  * Zero a page.
  * %rdi	- page
  */
-SYM_FUNC_START(clear_page_rep)
+SYM_TYPED_FUNC_START(clear_page_rep)
 	movl $4096/8,%ecx
 	xorl %eax,%eax
 	rep stosq
@@ -22,7 +24,7 @@ SYM_FUNC_START(clear_page_rep)
 SYM_FUNC_END(clear_page_rep)
 EXPORT_SYMBOL_GPL(clear_page_rep)
 
-SYM_FUNC_START(clear_page_orig)
+SYM_TYPED_FUNC_START(clear_page_orig)
 	xorl   %eax,%eax
 	movl   $4096/64,%ecx
 	.p2align 4
@@ -44,7 +46,7 @@ SYM_FUNC_START(clear_page_orig)
 SYM_FUNC_END(clear_page_orig)
 EXPORT_SYMBOL_GPL(clear_page_orig)
 
-SYM_FUNC_START(clear_page_erms)
+SYM_TYPED_FUNC_START(clear_page_erms)
 	movl $4096,%ecx
 	xorl %eax,%eax
 	rep stosb
@@ -63,6 +65,7 @@ EXPORT_SYMBOL_GPL(clear_page_erms)
  * rcx: uncleared bytes or 0 if successful.
  */
 SYM_FUNC_START(rep_stos_alternative)
+	ANNOTATE_NOENDBR
 	cmpq $64,%rcx
 	jae .Lunrolled
 
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 1c96be769adc..d4bb24347ff8 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,7 @@
 
 .text
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 
 /*
  * Emulate 'cmpxchg8b (%esi)' on UP
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index d6ae793d08fa..d8e87fedc20d 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -13,7 +14,7 @@
  * prefetch distance based on SMP/UP.
  */
 	ALIGN
-SYM_FUNC_START(copy_page)
+SYM_TYPED_FUNC_START(copy_page)
 	ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
 	movl	$4096/8, %ecx
 	rep	movsq
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fc9fb5d06174..aa8c341b2441 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -8,6 +8,8 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 #include <asm/asm.h>
@@ -30,6 +32,7 @@
  * it simpler for us, we can clobber rsi/rdi and rax freely.
  */
 SYM_FUNC_START(rep_movs_alternative)
+	ANNOTATE_NOENDBR
 	cmpq $64,%rcx
 	jae .Llarge
 
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 2918e36eece2..18350b343c2a 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -5,6 +5,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/asm.h>
 
 /*
@@ -27,6 +28,7 @@
  * rax uncopied bytes or 0 if successful.
  */
 SYM_FUNC_START(__copy_user_nocache)
+	ANNOTATE_NOENDBR
 	/* If destination is not 7-byte aligned, we'll have to align it */
 	testb $7,%dil
 	jne .Lalign
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 89ecd57c9d42..9d5654b8a72a 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,22 +28,20 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
+#include <asm/runtime-const.h>
 
 #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
 
 .macro check_range size:req
 .if IS_ENABLED(CONFIG_X86_64)
-	movq $0x0123456789abcdef,%rdx
-  1:
-  .pushsection runtime_ptr_USER_PTR_MAX,"a"
-	.long 1b - 8 - .
-  .popsection
+	RUNTIME_CONST_PTR USER_PTR_MAX, rdx
 	cmp %rdx, %rax
 	cmova %rdx, %rax
 .else
@@ -62,6 +60,7 @@
 
 	.text
 SYM_FUNC_START(__get_user_1)
+	ANNOTATE_NOENDBR
 	check_range size=1
 	ASM_STAC
 	UACCESS movzbl (%_ASM_AX),%edx
@@ -72,6 +71,7 @@ SYM_FUNC_END(__get_user_1)
 EXPORT_SYMBOL(__get_user_1)
 
 SYM_FUNC_START(__get_user_2)
+	ANNOTATE_NOENDBR
 	check_range size=2
 	ASM_STAC
 	UACCESS movzwl (%_ASM_AX),%edx
@@ -82,6 +82,7 @@ SYM_FUNC_END(__get_user_2)
 EXPORT_SYMBOL(__get_user_2)
 
 SYM_FUNC_START(__get_user_4)
+	ANNOTATE_NOENDBR
 	check_range size=4
 	ASM_STAC
 	UACCESS movl (%_ASM_AX),%edx
@@ -92,6 +93,7 @@ SYM_FUNC_END(__get_user_4)
 EXPORT_SYMBOL(__get_user_4)
 
 SYM_FUNC_START(__get_user_8)
+	ANNOTATE_NOENDBR
 #ifndef CONFIG_X86_64
 	xor %ecx,%ecx
 #endif
@@ -111,6 +113,7 @@ EXPORT_SYMBOL(__get_user_8)
 
 /* .. and the same for __get_user, just without the range checks */
 SYM_FUNC_START(__get_user_nocheck_1)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movzbl (%_ASM_AX),%edx
@@ -121,6 +124,7 @@ SYM_FUNC_END(__get_user_nocheck_1)
 EXPORT_SYMBOL(__get_user_nocheck_1)
 
 SYM_FUNC_START(__get_user_nocheck_2)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movzwl (%_ASM_AX),%edx
@@ -131,6 +135,7 @@ SYM_FUNC_END(__get_user_nocheck_2)
 EXPORT_SYMBOL(__get_user_nocheck_2)
 
 SYM_FUNC_START(__get_user_nocheck_4)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 	UACCESS movl (%_ASM_AX),%edx
@@ -141,6 +146,7 @@ SYM_FUNC_END(__get_user_nocheck_4)
 EXPORT_SYMBOL(__get_user_nocheck_4)
 
 SYM_FUNC_START(__get_user_nocheck_8)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 	ASM_BARRIER_NOSPEC
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 774bdf3e6f0a..edbeb3ecad38 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 
 #include <asm/asm.h>
 
@@ -9,6 +10,7 @@
  * %rdi: w
  */
 SYM_FUNC_START(__sw_hweight32)
+	ANNOTATE_NOENDBR
 
 #ifdef CONFIG_X86_64
 	movl %edi, %eax				# w
@@ -42,6 +44,7 @@ EXPORT_SYMBOL(__sw_hweight32)
  */
 #ifdef CONFIG_X86_64
 SYM_FUNC_START(__sw_hweight64)
+	ANNOTATE_NOENDBR
 	pushq   %rdi
 	pushq   %rdx
 
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 1b60ae81ecd8..aa1f92ee6b2e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
  */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -26,7 +27,7 @@
  * Output:
  * rax: dest
  */
-SYM_FUNC_START(__memmove)
+SYM_TYPED_FUNC_START(__memmove)
 
 	mov %rdi, %rax
 
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0199d56cb479..d66b710d628f 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
 
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
@@ -28,7 +29,7 @@
  * only for the return value that is the same as the source input,
  * which the compiler could/should do much better anyway.
  */
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
 	ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
 
 	movq %rdi,%r9
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ebd259f31496..5ef8494896e8 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/linkage.h>
 #include <linux/errno.h>
+#include <linux/cfi_types.h>
 #include <asm/asm.h>
 #include <asm/msr.h>
 
@@ -12,7 +13,7 @@
  *
  */
 .macro op_safe_regs op
-SYM_FUNC_START(\op\()_safe_regs)
+SYM_TYPED_FUNC_START(\op\()_safe_regs)
 	pushq %rbx
 	pushq %r12
 	movq	%rdi, %r10	/* Save pointer */
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 975c9c18263d..46d9e9b98a61 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -13,6 +13,7 @@
  */
 #include <linux/export.h>
 #include <linux/linkage.h>
+#include <linux/objtool.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
@@ -45,6 +46,7 @@
 
 .text
 SYM_FUNC_START(__put_user_1)
+	ANNOTATE_NOENDBR
 	check_range size=1
 	ASM_STAC
 1:	movb %al,(%_ASM_CX)
@@ -55,6 +57,7 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -64,6 +67,7 @@ SYM_FUNC_END(__put_user_nocheck_1)
 EXPORT_SYMBOL(__put_user_nocheck_1)
 
 SYM_FUNC_START(__put_user_2)
+	ANNOTATE_NOENDBR
 	check_range size=2
 	ASM_STAC
 3:	movw %ax,(%_ASM_CX)
@@ -74,6 +78,7 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -83,6 +88,7 @@ SYM_FUNC_END(__put_user_nocheck_2)
 EXPORT_SYMBOL(__put_user_nocheck_2)
 
 SYM_FUNC_START(__put_user_4)
+	ANNOTATE_NOENDBR
 	check_range size=4
 	ASM_STAC
 5:	movl %eax,(%_ASM_CX)
@@ -93,6 +99,7 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -102,6 +109,7 @@ SYM_FUNC_END(__put_user_nocheck_4)
 EXPORT_SYMBOL(__put_user_nocheck_4)
 
 SYM_FUNC_START(__put_user_8)
+	ANNOTATE_NOENDBR
 	check_range size=8
 	ASM_STAC
 7:	mov %_ASM_AX,(%_ASM_CX)
@@ -115,6 +123,7 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
+	ANNOTATE_NOENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 391059b2c6fb..a26c43abd47d 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -326,6 +326,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
 #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
+	ANNOTATE_NOENDBR
 	ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
@@ -342,7 +343,7 @@ SYM_FUNC_START(call_depth_return_thunk)
 	 * case.
 	 */
 	CALL_THUNKS_DEBUG_INC_RETS
-	shlq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+	shlq	$5, PER_CPU_VAR(__x86_call_depth)
 	jz	1f
 	ANNOTATE_UNRET_SAFE
 	ret
diff --git a/arch/x86/math-emu/control_w.h b/arch/x86/math-emu/control_w.h
index 60f4dcc5edc3..93cbc89b34e2 100644
--- a/arch/x86/math-emu/control_w.h
+++ b/arch/x86/math-emu/control_w.h
@@ -11,7 +11,7 @@
 #ifndef _CONTROLW_H_
 #define _CONTROLW_H_
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define	_Const_(x)	$##x
 #else
 #define	_Const_(x)	x
diff --git a/arch/x86/math-emu/exception.h b/arch/x86/math-emu/exception.h
index 75230b977577..59961d350bc4 100644
--- a/arch/x86/math-emu/exception.h
+++ b/arch/x86/math-emu/exception.h
@@ -10,7 +10,7 @@
 #ifndef _EXCEPTION_H_
 #define _EXCEPTION_H_
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define	Const_(x)	$##x
 #else
 #define	Const_(x)	x
@@ -37,7 +37,7 @@
 #define PRECISION_LOST_UP    Const_((EX_Precision | SW_C1))
 #define PRECISION_LOST_DOWN  Const_(EX_Precision)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #ifdef DEBUG
 #define	EXCEPTION(x)	{ printk("exception in %s at line %d\n", \
@@ -46,6 +46,6 @@
 #define	EXCEPTION(x)	FPU_exception(x)
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _EXCEPTION_H_ */
diff --git a/arch/x86/math-emu/fpu_emu.h b/arch/x86/math-emu/fpu_emu.h
index 0c122226ca56..def569c50b76 100644
--- a/arch/x86/math-emu/fpu_emu.h
+++ b/arch/x86/math-emu/fpu_emu.h
@@ -20,7 +20,7 @@
  */
 #define PECULIAR_486
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #include "fpu_asm.h"
 #define	Const(x)	$##x
 #else
@@ -68,7 +68,7 @@
 
 #define FPU_Exception   Const(0x80000000)	/* Added to tag returns. */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include "fpu_system.h"
 
@@ -213,6 +213,6 @@ asmlinkage int FPU_round(FPU_REG *arg, unsigned int extent, int dummy,
 #include "fpu_proto.h"
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _FPU_EMU_H_ */
diff --git a/arch/x86/math-emu/status_w.h b/arch/x86/math-emu/status_w.h
index b77bafec9526..f642957330ef 100644
--- a/arch/x86/math-emu/status_w.h
+++ b/arch/x86/math-emu/status_w.h
@@ -13,7 +13,7 @@
 
 #include "fpu_emu.h"		/* for definition of PECULIAR_486 */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define	Const__(x)	$##x
 #else
 #define	Const__(x)	x
@@ -37,7 +37,7 @@
 
 #define SW_Exc_Mask     Const__(0x27f)	/* Status word exception bit mask */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define COMP_A_gt_B	1
 #define COMP_A_eq_B	2
@@ -63,6 +63,6 @@ static inline void setcc(int cc)
 #  define clear_C1()
 #endif /* PECULIAR_486 */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _STATUS_H_ */
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 5ab7bd2f1983..bd5d101c5c37 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -101,9 +101,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 		pmd_t *pmd;
 		bool use_gbpage;
 
-		next = (addr & PUD_MASK) + PUD_SIZE;
-		if (next > end)
-			next = end;
+		next = pud_addr_end(addr, end);
 
 		/* if this is already a gbpage, this portion is already mapped */
 		if (pud_leaf(*pud))
@@ -154,10 +152,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
 		p4d_t *p4d = p4d_page + p4d_index(addr);
 		pud_t *pud;
 
-		next = (addr & P4D_MASK) + P4D_SIZE;
-		if (next > end)
-			next = end;
-
+		next = p4d_addr_end(addr, end);
 		if (p4d_present(*p4d)) {
 			pud = pud_offset(p4d, 0);
 			result = ident_pud_init(info, pud, addr, next);
@@ -199,10 +194,7 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
 		pgd_t *pgd = pgd_page + pgd_index(addr);
 		p4d_t *p4d;
 
-		next = (addr & PGDIR_MASK) + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-
+		next = pgd_addr_end(addr, end);
 		if (pgd_present(*pgd)) {
 			p4d = p4d_offset(pgd, 0);
 			result = ident_p4d_init(info, p4d, addr, next);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 62aa4d66a032..bfa444a7dbb0 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -645,8 +645,13 @@ static void __init memory_map_top_down(unsigned long map_start,
 	 */
 	addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
 					 map_end);
-	memblock_phys_free(addr, PMD_SIZE);
-	real_end = addr + PMD_SIZE;
+	if (!addr) {
+		pr_warn("Failed to release memory for alloc_low_pages()");
+		real_end = max(map_start, ALIGN_DOWN(map_end, PMD_SIZE));
+	} else {
+		memblock_phys_free(addr, PMD_SIZE);
+		real_end = addr + PMD_SIZE;
+	}
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
 	step_size = PMD_SIZE;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ac41b1e0940d..f288aad8dc74 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -582,7 +582,7 @@ static void __init lowmem_pfn_init(void)
 	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
 
 #define MSG_HIGHMEM_TRIMMED \
-	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+	"Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n"
 /*
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
@@ -606,18 +606,13 @@ static void __init highmem_pfn_init(void)
 #ifndef CONFIG_HIGHMEM
 	/* Maximum memory usable is what is directly addressable */
 	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
-	if (max_pfn > MAX_NONPAE_PFN)
-		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
-	else
-		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
 	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
-#ifndef CONFIG_HIGHMEM64G
 	if (max_pfn > MAX_NONPAE_PFN) {
 		max_pfn = MAX_NONPAE_PFN;
 		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
 	}
-#endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 38ff7791a9c7..42c90b420773 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -503,6 +503,14 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
+{
+	if ((flags & MEMREMAP_DEC) || cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return (void __force *)ioremap_cache(phys_addr, size);
+
+	return (void __force *)ioremap_encrypted(phys_addr, size);
+}
+
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 11a93542d198..3c306de52fd4 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -113,8 +113,14 @@ void __init kernel_randomize_memory(void)
 	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
 		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
 
-	/* Adapt physical memory region size based on available memory */
-	if (memory_tb < kaslr_regions[0].size_tb)
+	/*
+	 * Adapt physical memory region size based on available memory,
+	 * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the
+	 * device BAR space assuming the direct map space is large enough
+	 * for creating a ZONE_DEVICE mapping in the direct map corresponding
+	 * to the physical BAR address.
+	 */
+	if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb))
 		kaslr_regions[0].size_tb = memory_tb;
 
 	/*
diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S
index e25288ee33c2..f8a33b25ae86 100644
--- a/arch/x86/mm/mem_encrypt_boot.S
+++ b/arch/x86/mm/mem_encrypt_boot.S
@@ -72,6 +72,7 @@ SYM_FUNC_START(sme_encrypt_execute)
 SYM_FUNC_END(sme_encrypt_execute)
 
 SYM_FUNC_START(__enc_copy)
+	ANNOTATE_NOENDBR
 /*
  * Routine used to encrypt memory in place.
  *   This routine must be run outside of the kernel proper since
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index b8a6ffffb451..5ed2109211da 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -84,7 +84,6 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 {
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
-	unsigned long gap_min, gap_max;
 
 	/* Values close to RLIM_INFINITY can overflow. */
 	if (gap + pad > gap)
@@ -94,13 +93,7 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 	 * Top of mmap area (just below the process stack).
 	 * Leave an at least ~128 MB hole with possible stack randomization.
 	 */
-	gap_min = SIZE_128M;
-	gap_max = (task_size / 6) * 5;
-
-	if (gap < gap_min)
-		gap = gap_min;
-	else if (gap > gap_max)
-		gap = gap_max;
+	gap = clamp(gap, SIZE_128M, (task_size / 6) * 5);
 
 	return PAGE_ALIGN(task_size - gap - rnd);
 }
diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c
index 3d2f7f0a6ed1..ad3c1feec990 100644
--- a/arch/x86/mm/pat/cpa-test.c
+++ b/arch/x86/mm/pat/cpa-test.c
@@ -183,7 +183,7 @@ static int pageattr_test(void)
 			break;
 
 		case 1:
-			err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1);
+			err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
 			break;
 
 		case 2:
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index feb8cc6a12bf..e40861c9cb90 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -43,6 +43,7 @@
 #include <linux/fs.h>
 #include <linux/rbtree.h>
 
+#include <asm/cpu_device_id.h>
 #include <asm/cacheflush.h>
 #include <asm/cacheinfo.h>
 #include <asm/processor.h>
@@ -290,9 +291,8 @@ void __init pat_bp_init(void)
 		return;
 	}
 
-	if ((c->x86_vendor == X86_VENDOR_INTEL) &&
-	    (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
-	     ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+	if ((c->x86_vfm >= INTEL_PENTIUM_PRO   && c->x86_vfm <= INTEL_PENTIUM_M_DOTHAN) ||
+	    (c->x86_vfm >= INTEL_P4_WILLAMETTE && c->x86_vfm <= INTEL_P4_CEDARMILL)) {
 		/*
 		 * PAT support with the lower four entries. Intel Pentium 2,
 		 * 3, M, and 4 are affected by PAT errata, which makes the
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index ef4514d64c05..72405d315b41 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -73,6 +73,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
+#define CPA_COLLAPSE 16 /* try to collapse large pages */
 
 static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
 {
@@ -105,6 +106,18 @@ static void split_page_count(int level)
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
+static void collapse_page_count(int level)
+{
+	direct_pages_count[level]++;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE);
+	}
+	direct_pages_count[level - 1] -= PTRS_PER_PTE;
+}
+
 void arch_report_meminfo(struct seq_file *m)
 {
 	seq_printf(m, "DirectMap4k:    %8lu kB\n",
@@ -122,6 +135,7 @@ void arch_report_meminfo(struct seq_file *m)
 }
 #else
 static inline void split_page_count(int level) { }
+static inline void collapse_page_count(int level) { }
 #endif
 
 #ifdef CONFIG_X86_CPA_STATISTICS
@@ -211,14 +225,14 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
+#ifdef CONFIG_X86_64
+
 static inline int
 within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
 {
 	return addr >= start && addr <= end;
 }
 
-#ifdef CONFIG_X86_64
-
 /*
  * The kernel image is mapped into two places in the virtual address space
  * (addresses without KASLR, of course):
@@ -394,16 +408,49 @@ static void __cpa_flush_tlb(void *data)
 		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
-static void cpa_flush(struct cpa_data *data, int cache)
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables);
+
+static void cpa_collapse_large_pages(struct cpa_data *cpa)
+{
+	unsigned long start, addr, end;
+	struct ptdesc *ptdesc, *tmp;
+	LIST_HEAD(pgtables);
+	int collapsed = 0;
+	int i;
+
+	if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+		for (i = 0; i < cpa->numpages; i++)
+			collapsed += collapse_large_pages(__cpa_addr(cpa, i),
+							  &pgtables);
+	} else {
+		addr = __cpa_addr(cpa, 0);
+		start = addr & PMD_MASK;
+		end = addr + PAGE_SIZE * cpa->numpages;
+
+		for (addr = start; within(addr, start, end); addr += PMD_SIZE)
+			collapsed += collapse_large_pages(addr, &pgtables);
+	}
+
+	if (!collapsed)
+		return;
+
+	flush_tlb_all();
+
+	list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) {
+		list_del(&ptdesc->pt_list);
+		__free_page(ptdesc_page(ptdesc));
+	}
+}
+
+static void cpa_flush(struct cpa_data *cpa, int cache)
 {
-	struct cpa_data *cpa = data;
 	unsigned int i;
 
 	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
 
 	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
 		cpa_flush_all(cache);
-		return;
+		goto collapse_large_pages;
 	}
 
 	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
@@ -412,7 +459,7 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
-		return;
+		goto collapse_large_pages;
 
 	mb();
 	for (i = 0; i < cpa->numpages; i++) {
@@ -428,6 +475,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 			clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
 	}
 	mb();
+
+collapse_large_pages:
+	if (cpa->flags & CPA_COLLAPSE)
+		cpa_collapse_large_pages(cpa);
 }
 
 static bool overlaps(unsigned long r1_start, unsigned long r1_end,
@@ -1197,6 +1248,161 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
 	return 0;
 }
 
+static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	pmd_t _pmd, old_pmd;
+	pte_t *pte, first;
+	unsigned long pfn;
+	pgprot_t pgprot;
+	int i = 0;
+
+	addr &= PMD_MASK;
+	pte = pte_offset_kernel(pmd, addr);
+	first = *pte;
+	pfn = pte_pfn(first);
+
+	/* Make sure alignment is suitable */
+	if (PFN_PHYS(pfn) & ~PMD_MASK)
+		return 0;
+
+	/* The page is 4k intentionally */
+	if (pte_flags(first) & _PAGE_KERNEL_4K)
+		return 0;
+
+	/* Check that the rest of PTEs are compatible with the first one */
+	for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) {
+		pte_t entry = *pte;
+
+		if (!pte_present(entry))
+			return 0;
+		if (pte_flags(entry) != pte_flags(first))
+			return 0;
+		if (pte_pfn(entry) != pte_pfn(first) + i)
+			return 0;
+	}
+
+	old_pmd = *pmd;
+
+	/* Success: set up a large page */
+	pgprot = pgprot_4k_2_large(pte_pgprot(first));
+	pgprot_val(pgprot) |= _PAGE_PSE;
+	_pmd = pfn_pmd(pfn, pgprot);
+	set_pmd(pmd, _pmd);
+
+	/* Queue the page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
+
+	if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) {
+		struct page *page;
+
+		/* Update all PGD tables to use the same large page */
+		list_for_each_entry(page, &pgd_list, lru) {
+			pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+			p4d_t *p4d = p4d_offset(pgd, addr);
+			pud_t *pud = pud_offset(p4d, addr);
+			pmd_t *pmd = pmd_offset(pud, addr);
+			/* Something is wrong if entries doesn't match */
+			if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd)))
+				continue;
+			set_pmd(pmd, _pmd);
+		}
+	}
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_2M);
+
+	return 1;
+}
+
+static int collapse_pud_page(pud_t *pud, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	unsigned long pfn;
+	pmd_t *pmd, first;
+	int i;
+
+	if (!direct_gbpages)
+		return 0;
+
+	addr &= PUD_MASK;
+	pmd = pmd_offset(pud, addr);
+	first = *pmd;
+
+	/*
+	 * To restore PUD page all PMD entries must be large and
+	 * have suitable alignment
+	 */
+	pfn = pmd_pfn(first);
+	if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK))
+		return 0;
+
+	/*
+	 * To restore PUD page, all following PMDs must be compatible with the
+	 * first one.
+	 */
+	for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) {
+		pmd_t entry = *pmd;
+
+		if (!pmd_present(entry) || !pmd_leaf(entry))
+			return 0;
+		if (pmd_flags(entry) != pmd_flags(first))
+			return 0;
+		if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE)
+			return 0;
+	}
+
+	/* Restore PUD page and queue page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables);
+	set_pud(pud, pfn_pud(pfn, pmd_pgprot(first)));
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_1G);
+
+	return 1;
+}
+
+/*
+ * Collapse PMD and PUD pages in the kernel mapping around the address where
+ * possible.
+ *
+ * Caller must flush TLB and free page tables queued on the list before
+ * touching the new entries. CPU must not see TLB entries of different size
+ * with different attributes.
+ */
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables)
+{
+	int collapsed = 0;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	addr &= PMD_MASK;
+
+	spin_lock(&pgd_lock);
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		goto out;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		goto out;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud) || pud_leaf(*pud))
+		goto out;
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+		goto out;
+
+	collapsed = collapse_pmd_page(pmd, addr, pgtables);
+	if (collapsed)
+		collapsed += collapse_pud_page(pud, addr, pgtables);
+
+out:
+	spin_unlock(&pgd_lock);
+	return collapsed;
+}
+
 static bool try_to_free_pte_page(pte_t *pte)
 {
 	int i;
@@ -1942,19 +2148,6 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
 		CPA_PAGES_ARRAY, pages);
 }
 
-/*
- * __set_memory_prot is an internal helper for callers that have been passed
- * a pgprot_t value from upper layers and a reservation has already been taken.
- * If you want to set the pgprot to a specific page protocol, use the
- * set_memory_xx() functions.
- */
-int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot)
-{
-	return change_page_attr_set_clr(&addr, numpages, prot,
-					__pgprot(~pgprot_val(prot)), 0, 0,
-					NULL);
-}
-
 int _set_memory_uc(unsigned long addr, int numpages)
 {
 	/*
@@ -2120,7 +2313,8 @@ int set_memory_rox(unsigned long addr, int numpages)
 	if (__supported_pte_mask & _PAGE_NX)
 		clr.pgprot |= _PAGE_NX;
 
-	return change_page_attr_clear(&addr, numpages, clr, 0);
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0,
+					CPA_COLLAPSE, NULL);
 }
 
 int set_memory_rw(unsigned long addr, int numpages)
@@ -2147,7 +2341,8 @@ int set_memory_p(unsigned long addr, int numpages)
 
 int set_memory_4k(unsigned long addr, int numpages)
 {
-	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+	return change_page_attr_set_clr(&addr, numpages,
+					__pgprot(_PAGE_KERNEL_4K),
 					__pgprot(0), 1, 0, NULL);
 }
 
@@ -2420,7 +2615,7 @@ static int __set_pages_np(struct page *page, int numpages)
 				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
-				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 				.flags = CPA_NO_CHECK_ALIAS };
 
 	/*
@@ -2507,7 +2702,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.pgd = pgd,
 		.numpages = numpages,
 		.mask_set = __pgprot(0),
-		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)),
 		.flags = CPA_NO_CHECK_ALIAS,
 	};
 
@@ -2550,7 +2745,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 		.pgd		= pgd,
 		.numpages	= numpages,
 		.mask_set	= __pgprot(0),
-		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW),
+		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 		.flags		= CPA_NO_CHECK_ALIAS,
 	};
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 1fef5ad32d5a..cec321fb74f2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -12,59 +12,15 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
 EXPORT_SYMBOL(physical_mask);
 #endif
 
-#ifdef CONFIG_HIGHPTE
-#define PGTABLE_HIGHMEM __GFP_HIGHMEM
-#else
-#define PGTABLE_HIGHMEM 0
-#endif
-
-#ifndef CONFIG_PARAVIRT
-#ifndef CONFIG_PT_RECLAIM
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif /* !CONFIG_PT_RECLAIM */
-#endif /* !CONFIG_PARAVIRT */
-
-gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
-
 pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
-	return __pte_alloc_one(mm, __userpte_alloc_gfp);
-}
-
-static int __init setup_userpte(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	/*
-	 * "userpte=nohigh" disables allocation of user pagetables in
-	 * high memory.
-	 */
-	if (strcmp(arg, "nohigh") == 0)
-		__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-	else
-		return -EINVAL;
-	return 0;
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
 }
-early_param("userpte", setup_userpte);
 
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
 	paravirt_release_pte(page_to_pfn(pte));
-	paravirt_tlb_remove_table(tlb, page_ptdesc(pte));
+	tlb_remove_table(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
@@ -78,21 +34,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_table(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud));
+	tlb_remove_table(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d));
+	tlb_remove_table(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bb..0925768d00cb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -74,13 +74,15 @@
  * use different names for each of them:
  *
  * ASID  - [0, TLB_NR_DYN_ASIDS-1]
- *         the canonical identifier for an mm
+ *         the canonical identifier for an mm, dynamically allocated on each CPU
+ *         [TLB_NR_DYN_ASIDS, MAX_ASID_AVAILABLE-1]
+ *         the canonical, global identifier for an mm, identical across all CPUs
  *
- * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * kPCID - [1, MAX_ASID_AVAILABLE]
  *         the value we write into the PCID part of CR3; corresponds to the
  *         ASID+1, because PCID 0 is special.
  *
- * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * uPCID - [2048 + 1, 2048 + MAX_ASID_AVAILABLE]
  *         for KPTI each mm has two address spaces and thus needs two
  *         PCID values, but we can still do with a single ASID denomination
  *         for each mm. Corresponds to kPCID + 2048.
@@ -225,6 +227,20 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 		return;
 	}
 
+	/*
+	 * TLB consistency for global ASIDs is maintained with hardware assisted
+	 * remote TLB flushing. Global ASIDs are always up to date.
+	 */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+		u16 global_asid = mm_global_asid(next);
+
+		if (global_asid) {
+			*new_asid = global_asid;
+			*need_flush = false;
+			return;
+		}
+	}
+
 	if (this_cpu_read(cpu_tlbstate.invalidate_other))
 		clear_asid_other();
 
@@ -252,6 +268,268 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
 }
 
 /*
+ * Global ASIDs are allocated for multi-threaded processes that are
+ * active on multiple CPUs simultaneously, giving each of those
+ * processes the same PCID on every CPU, for use with hardware-assisted
+ * TLB shootdown on remote CPUs, like AMD INVLPGB or Intel RAR.
+ *
+ * These global ASIDs are held for the lifetime of the process.
+ */
+static DEFINE_RAW_SPINLOCK(global_asid_lock);
+static u16 last_global_asid = MAX_ASID_AVAILABLE;
+static DECLARE_BITMAP(global_asid_used, MAX_ASID_AVAILABLE);
+static DECLARE_BITMAP(global_asid_freed, MAX_ASID_AVAILABLE);
+static int global_asid_available = MAX_ASID_AVAILABLE - TLB_NR_DYN_ASIDS - 1;
+
+/*
+ * When the search for a free ASID in the global ASID space reaches
+ * MAX_ASID_AVAILABLE, a global TLB flush guarantees that previously
+ * freed global ASIDs are safe to re-use.
+ *
+ * This way the global flush only needs to happen at ASID rollover
+ * time, and not at ASID allocation time.
+ */
+static void reset_global_asid_space(void)
+{
+	lockdep_assert_held(&global_asid_lock);
+
+	invlpgb_flush_all_nonglobals();
+
+	/*
+	 * The TLB flush above makes it safe to re-use the previously
+	 * freed global ASIDs.
+	 */
+	bitmap_andnot(global_asid_used, global_asid_used,
+			global_asid_freed, MAX_ASID_AVAILABLE);
+	bitmap_clear(global_asid_freed, 0, MAX_ASID_AVAILABLE);
+
+	/* Restart the search from the start of global ASID space. */
+	last_global_asid = TLB_NR_DYN_ASIDS;
+}
+
+static u16 allocate_global_asid(void)
+{
+	u16 asid;
+
+	lockdep_assert_held(&global_asid_lock);
+
+	/* The previous allocation hit the edge of available address space */
+	if (last_global_asid >= MAX_ASID_AVAILABLE - 1)
+		reset_global_asid_space();
+
+	asid = find_next_zero_bit(global_asid_used, MAX_ASID_AVAILABLE, last_global_asid);
+
+	if (asid >= MAX_ASID_AVAILABLE && !global_asid_available) {
+		/* This should never happen. */
+		VM_WARN_ONCE(1, "Unable to allocate global ASID despite %d available\n",
+				global_asid_available);
+		return 0;
+	}
+
+	/* Claim this global ASID. */
+	__set_bit(asid, global_asid_used);
+	last_global_asid = asid;
+	global_asid_available--;
+	return asid;
+}
+
+/*
+ * Check whether a process is currently active on more than @threshold CPUs.
+ * This is a cheap estimation on whether or not it may make sense to assign
+ * a global ASID to this process, and use broadcast TLB invalidation.
+ */
+static bool mm_active_cpus_exceeds(struct mm_struct *mm, int threshold)
+{
+	int count = 0;
+	int cpu;
+
+	/* This quick check should eliminate most single threaded programs. */
+	if (cpumask_weight(mm_cpumask(mm)) <= threshold)
+		return false;
+
+	/* Slower check to make sure. */
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/* Skip the CPUs that aren't really running this process. */
+		if (per_cpu(cpu_tlbstate.loaded_mm, cpu) != mm)
+			continue;
+
+		if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+			continue;
+
+		if (++count > threshold)
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Assign a global ASID to the current process, protecting against
+ * races between multiple threads in the process.
+ */
+static void use_global_asid(struct mm_struct *mm)
+{
+	u16 asid;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* This process is already using broadcast TLB invalidation. */
+	if (mm_global_asid(mm))
+		return;
+
+	/*
+	 * The last global ASID was consumed while waiting for the lock.
+	 *
+	 * If this fires, a more aggressive ASID reuse scheme might be
+	 * needed.
+	 */
+	if (!global_asid_available) {
+		VM_WARN_ONCE(1, "Ran out of global ASIDs\n");
+		return;
+	}
+
+	asid = allocate_global_asid();
+	if (!asid)
+		return;
+
+	mm_assign_global_asid(mm, asid);
+}
+
+void mm_free_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	if (!mm_global_asid(mm))
+		return;
+
+	guard(raw_spinlock_irqsave)(&global_asid_lock);
+
+	/* The global ASID can be re-used only after flush at wrap-around. */
+#ifdef CONFIG_BROADCAST_TLB_FLUSH
+	__set_bit(mm->context.global_asid, global_asid_freed);
+
+	mm->context.global_asid = 0;
+	global_asid_available++;
+#endif
+}
+
+/*
+ * Is the mm transitioning from a CPU-local ASID to a global ASID?
+ */
+static bool mm_needs_global_asid(struct mm_struct *mm, u16 asid)
+{
+	u16 global_asid = mm_global_asid(mm);
+
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return false;
+
+	/* Process is transitioning to a global ASID */
+	if (global_asid && asid != global_asid)
+		return true;
+
+	return false;
+}
+
+/*
+ * x86 has 4k ASIDs (2k when compiled with KPTI), but the largest x86
+ * systems have over 8k CPUs. Because of this potential ASID shortage,
+ * global ASIDs are handed out to processes that have frequent TLB
+ * flushes and are active on 4 or more CPUs simultaneously.
+ */
+static void consider_global_asid(struct mm_struct *mm)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		return;
+
+	/* Check every once in a while. */
+	if ((current->pid & 0x1f) != (jiffies & 0x1f))
+		return;
+
+	/*
+	 * Assign a global ASID if the process is active on
+	 * 4 or more CPUs simultaneously.
+	 */
+	if (mm_active_cpus_exceeds(mm, 3))
+		use_global_asid(mm);
+}
+
+static void finish_asid_transition(struct flush_tlb_info *info)
+{
+	struct mm_struct *mm = info->mm;
+	int bc_asid = mm_global_asid(mm);
+	int cpu;
+
+	if (!mm_in_asid_transition(mm))
+		return;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		/*
+		 * The remote CPU is context switching. Wait for that to
+		 * finish, to catch the unlikely case of it switching to
+		 * the target mm with an out of date ASID.
+		 */
+		while (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) == LOADED_MM_SWITCHING)
+			cpu_relax();
+
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm, cpu)) != mm)
+			continue;
+
+		/*
+		 * If at least one CPU is not using the global ASID yet,
+		 * send a TLB flush IPI. The IPI should cause stragglers
+		 * to transition soon.
+		 *
+		 * This can race with the CPU switching to another task;
+		 * that results in a (harmless) extra IPI.
+		 */
+		if (READ_ONCE(per_cpu(cpu_tlbstate.loaded_mm_asid, cpu)) != bc_asid) {
+			flush_tlb_multi(mm_cpumask(info->mm), info);
+			return;
+		}
+	}
+
+	/* All the CPUs running this process are using the global ASID. */
+	mm_clear_asid_transition(mm);
+}
+
+static void broadcast_tlb_flush(struct flush_tlb_info *info)
+{
+	bool pmd = info->stride_shift == PMD_SHIFT;
+	unsigned long asid = mm_global_asid(info->mm);
+	unsigned long addr = info->start;
+
+	/*
+	 * TLB flushes with INVLPGB are kicked off asynchronously.
+	 * The inc_mm_tlb_gen() guarantees page table updates are done
+	 * before these TLB flushes happen.
+	 */
+	if (info->end == TLB_FLUSH_ALL) {
+		invlpgb_flush_single_pcid_nosync(kern_pcid(asid));
+		/* Do any CPUs supporting INVLPGB need PTI? */
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_single_pcid_nosync(user_pcid(asid));
+	} else do {
+		unsigned long nr = 1;
+
+		if (info->stride_shift <= PMD_SHIFT) {
+			nr = (info->end - addr) >> info->stride_shift;
+			nr = clamp_val(nr, 1, invlpgb_count_max);
+		}
+
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		if (cpu_feature_enabled(X86_FEATURE_PTI))
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+
+		addr += nr << info->stride_shift;
+	} while (addr < info->end);
+
+	finish_asid_transition(info);
+
+	/* Wait for the INVLPGBs kicked off above to finish. */
+	__tlbsync();
+}
+
+/*
  * Given an ASID, flush the corresponding user ASID.  We can delay this
  * until the next time we switch to it.
  *
@@ -556,7 +834,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	 */
 	if (prev == next) {
 		/* Not actually switching mm's */
-		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
+		VM_WARN_ON(is_dyn_asid(prev_asid) &&
+			   this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
 			   next->context.ctx_id);
 
 		/*
@@ -573,6 +852,20 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
+		/* Check if the current mm is transitioning to a global ASID */
+		if (mm_needs_global_asid(next, prev_asid)) {
+			next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+			choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+			goto reload_tlb;
+		}
+
+		/*
+		 * Broadcast TLB invalidation keeps this ASID up to date
+		 * all the time.
+		 */
+		if (is_global_asid(prev_asid))
+			return;
+
 		/*
 		 * If the CPU is not in lazy TLB mode, we are just switching
 		 * from one thread in a process to another thread in the same
@@ -607,6 +900,13 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		cond_mitigation(tsk);
 
 		/*
+		 * Let nmi_uaccess_okay() and finish_asid_transition()
+		 * know that CR3 is changing.
+		 */
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+		barrier();
+
+		/*
 		 * Leave this CPU in prev's mm_cpumask. Atomic writes to
 		 * mm_cpumask can be expensive under contention. The CPU
 		 * will be removed lazily at TLB flush time.
@@ -620,14 +920,12 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
-
-		/* Let nmi_uaccess_okay() know that we're changing CR3. */
-		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
-		barrier();
 	}
 
+reload_tlb:
 	new_lam = mm_lam_cr3_mask(next);
 	if (need_flush) {
+		VM_WARN_ON_ONCE(is_global_asid(new_asid));
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 		load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
@@ -746,7 +1044,7 @@ static void flush_tlb_func(void *info)
 	const struct flush_tlb_info *f = info;
 	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
-	u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+	u64 local_tlb_gen;
 	bool local = smp_processor_id() == f->initiating_cpu;
 	unsigned long nr_invalidate = 0;
 	u64 mm_tlb_gen;
@@ -769,6 +1067,16 @@ static void flush_tlb_func(void *info)
 	if (unlikely(loaded_mm == &init_mm))
 		return;
 
+	/* Reload the ASID if transitioning into or out of a global ASID */
+	if (mm_needs_global_asid(loaded_mm, loaded_mm_asid)) {
+		switch_mm_irqs_off(NULL, loaded_mm, NULL);
+		loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	}
+
+	/* Broadcast ASIDs are always kept up to date with INVLPGB. */
+	if (is_global_asid(loaded_mm_asid))
+		return;
+
 	VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].ctx_id) !=
 		   loaded_mm->context.ctx_id);
 
@@ -786,6 +1094,8 @@ static void flush_tlb_func(void *info)
 		return;
 	}
 
+	local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
+
 	if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
 		     f->new_tlb_gen <= local_tlb_gen)) {
 		/*
@@ -953,7 +1263,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	 * up on the new contents of what used to be page tables, while
 	 * doing a speculative memory access.
 	 */
-	if (info->freed_tables)
+	if (info->freed_tables || mm_in_asid_transition(info->mm))
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
 		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
@@ -1000,6 +1310,15 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
 #endif
 
+	/*
+	 * If the number of flushes is so large that a full flush
+	 * would be faster, do a full flush.
+	 */
+	if ((end - start) >> stride_shift > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
+	}
+
 	info->start		= start;
 	info->end		= end;
 	info->mm		= mm;
@@ -1026,17 +1345,8 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				bool freed_tables)
 {
 	struct flush_tlb_info *info;
+	int cpu = get_cpu();
 	u64 new_tlb_gen;
-	int cpu;
-
-	cpu = get_cpu();
-
-	/* Should we flush just the requested range? */
-	if ((end == TLB_FLUSH_ALL) ||
-	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
-		start = 0;
-		end = TLB_FLUSH_ALL;
-	}
 
 	/* This is also a barrier that synchronizes with switch_mm(). */
 	new_tlb_gen = inc_mm_tlb_gen(mm);
@@ -1049,9 +1359,12 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+	if (mm_global_asid(mm)) {
+		broadcast_tlb_flush(info);
+	} else if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
 		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
+		consider_global_asid(mm);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();
 		local_irq_disable();
@@ -1064,7 +1377,6 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
@@ -1074,7 +1386,32 @@ static void do_flush_tlb_all(void *info)
 void flush_tlb_all(void)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
-	on_each_cpu(do_flush_tlb_all, NULL, 1);
+
+	/* First try (faster) hardware-assisted TLB invalidation. */
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
+		/* Fall back to the IPI-based invalidation. */
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+}
+
+/* Flush an arbitrarily large range of memory with INVLPGB. */
+static void invlpgb_kernel_range_flush(struct flush_tlb_info *info)
+{
+	unsigned long addr, nr;
+
+	for (addr = info->start; addr < info->end; addr += nr << PAGE_SHIFT) {
+		nr = (info->end - addr) >> PAGE_SHIFT;
+
+		/*
+		 * INVLPGB has a limit on the size of ranges it can
+		 * flush. Break up large flushes.
+		 */
+		nr = clamp_val(nr, 1, invlpgb_count_max);
+
+		invlpgb_flush_addr_nosync(addr, nr);
+	}
+	__tlbsync();
 }
 
 static void do_kernel_range_flush(void *info)
@@ -1087,24 +1424,37 @@ static void do_kernel_range_flush(void *info)
 		flush_tlb_one_kernel(addr);
 }
 
-void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+static void kernel_tlb_flush_all(struct flush_tlb_info *info)
 {
-	/* Balance as user space task's flush, a bit conservative */
-	if (end == TLB_FLUSH_ALL ||
-	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_flush_all();
+	else
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
-	} else {
-		struct flush_tlb_info *info;
-
-		preempt_disable();
-		info = get_flush_tlb_info(NULL, start, end, 0, false,
-					  TLB_GENERATION_INVALID);
+}
 
+static void kernel_tlb_flush_range(struct flush_tlb_info *info)
+{
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB))
+		invlpgb_kernel_range_flush(info);
+	else
 		on_each_cpu(do_kernel_range_flush, info, 1);
+}
 
-		put_flush_tlb_info();
-		preempt_enable();
-	}
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	struct flush_tlb_info *info;
+
+	guard(preempt)();
+
+	info = get_flush_tlb_info(NULL, start, end, PAGE_SHIFT, false,
+				  TLB_GENERATION_INVALID);
+
+	if (info->end == TLB_FLUSH_ALL)
+		kernel_tlb_flush_all(info);
+	else
+		kernel_tlb_flush_range(info);
+
+	put_flush_tlb_info();
 }
 
 /*
@@ -1283,7 +1633,10 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 	 * a local TLB flush is needed. Optimize this use-case by calling
 	 * flush_tlb_func_local() directly in this case.
 	 */
-	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+	if (cpu_feature_enabled(X86_FEATURE_INVLPGB) && batch->unmapped_pages) {
+		invlpgb_flush_all_nonglobals();
+		batch->unmapped_pages = false;
+	} else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
 		flush_tlb_multi(&batch->cpumask, info);
 	} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
 		lockdep_assert_irqs_enabled();
@@ -1325,7 +1678,7 @@ bool nmi_uaccess_okay(void)
 	if (loaded_mm != current_mm)
 		return false;
 
-	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
 
 	return true;
 }
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a43fc5af973d..72776dcb75aa 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -410,16 +410,20 @@ static void emit_nops(u8 **pprog, int len)
  * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT
  * in arch/x86/kernel/alternative.c
  */
+static int emit_call(u8 **prog, void *func, void *ip);
 
-static void emit_fineibt(u8 **pprog, u32 hash)
+static void emit_fineibt(u8 **pprog, u8 *ip, u32 hash, int arity)
 {
 	u8 *prog = *pprog;
 
 	EMIT_ENDBR();
 	EMIT3_off32(0x41, 0x81, 0xea, hash);		/* subl $hash, %r10d	*/
-	EMIT2(0x74, 0x07);				/* jz.d8 +7		*/
-	EMIT2(0x0f, 0x0b);				/* ud2			*/
-	EMIT1(0x90);					/* nop			*/
+	if (cfi_bhi) {
+		emit_call(&prog, __bhi_args[arity], ip + 11);
+	} else {
+		EMIT2(0x75, 0xf9);			/* jne.d8 .-7		*/
+		EMIT3(0x0f, 0x1f, 0x00);		/* nop3			*/
+	}
 	EMIT_ENDBR_POISON();
 
 	*pprog = prog;
@@ -448,13 +452,13 @@ static void emit_kcfi(u8 **pprog, u32 hash)
 	*pprog = prog;
 }
 
-static void emit_cfi(u8 **pprog, u32 hash)
+static void emit_cfi(u8 **pprog, u8 *ip, u32 hash, int arity)
 {
 	u8 *prog = *pprog;
 
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
-		emit_fineibt(&prog, hash);
+		emit_fineibt(&prog, ip, hash, arity);
 		break;
 
 	case CFI_KCFI:
@@ -505,13 +509,17 @@ static void emit_prologue_tail_call(u8 **pprog, bool is_subprog)
  * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
  * while jumping to another program
  */
-static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+static void emit_prologue(u8 **pprog, u8 *ip, u32 stack_depth, bool ebpf_from_cbpf,
 			  bool tail_call_reachable, bool is_subprog,
 			  bool is_exception_cb)
 {
 	u8 *prog = *pprog;
 
-	emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash);
+	if (is_subprog) {
+		emit_cfi(&prog, ip, cfi_bpf_subprog_hash, 5);
+	} else {
+		emit_cfi(&prog, ip, cfi_bpf_hash, 1);
+	}
 	/* BPF trampoline can be made to work without these nops,
 	 * but let's waste 5 bytes for now and optimize later
 	 */
@@ -641,7 +649,7 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 	 * See emit_prologue(), for IBT builds the trampoline hook is preceded
 	 * with an ENDBR instruction.
 	 */
-	if (is_endbr(*(u32 *)ip))
+	if (is_endbr(ip))
 		ip += ENDBR_INSN_SIZE;
 
 	return __bpf_arch_text_poke(ip, t, old_addr, new_addr);
@@ -1480,7 +1488,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
 
 	detect_reg_usage(insn, insn_cnt, callee_regs_used);
 
-	emit_prologue(&prog, stack_depth,
+	emit_prologue(&prog, image, stack_depth,
 		      bpf_prog_was_classic(bpf_prog), tail_call_reachable,
 		      bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
 	/* Exception callback will clobber callee regs for its own use, and
@@ -3036,7 +3044,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
 		 */
-		if (is_endbr(*(u32 *)orig_call))
+		if (is_endbr(orig_call))
 			orig_call += ENDBR_INSN_SIZE;
 		orig_call += X86_PATCH_SIZE;
 	}
@@ -3047,7 +3055,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		/*
 		 * Indirect call for bpf_struct_ops
 		 */
-		emit_cfi(&prog, cfi_get_func_hash(func_addr));
+		emit_cfi(&prog, image,
+			 cfi_get_func_hash(func_addr),
+			 cfi_get_func_arity(func_addr));
 	} else {
 		/*
 		 * Direct-call fentry stub, as such it needs accounting for the
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 48bcada5cabe..4933fb337983 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -12,8 +12,6 @@ obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-y				+= legacy.o irq.o
 
-obj-$(CONFIG_STA2X11)           += sta2x11-fixup.o
-
 obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid_pci.o
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
deleted file mode 100644
index 8c8ddc4dcc08..000000000000
--- a/arch/x86/pci/sta2x11-fixup.c
+++ /dev/null
@@ -1,233 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * DMA translation between STA2x11 AMBA memory mapping and the x86 memory mapping
- *
- * ST Microelectronics ConneXt (STA2X11/STA2X10)
- *
- * Copyright (c) 2010-2011 Wind River Systems, Inc.
- */
-
-#include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/export.h>
-#include <linux/list.h>
-#include <linux/dma-map-ops.h>
-#include <linux/swiotlb.h>
-#include <asm/iommu.h>
-#include <asm/sta2x11.h>
-
-#define STA2X11_SWIOTLB_SIZE (4*1024*1024)
-
-/*
- * We build a list of bus numbers that are under the ConneXt. The
- * main bridge hosts 4 busses, which are the 4 endpoints, in order.
- */
-#define STA2X11_NR_EP		4	/* 0..3 included */
-#define STA2X11_NR_FUNCS	8	/* 0..7 included */
-#define STA2X11_AMBA_SIZE	(512 << 20)
-
-struct sta2x11_ahb_regs { /* saved during suspend */
-	u32 base, pexlbase, pexhbase, crw;
-};
-
-struct sta2x11_mapping {
-	int is_suspended;
-	struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS];
-};
-
-struct sta2x11_instance {
-	struct list_head list;
-	int bus0;
-	struct sta2x11_mapping map[STA2X11_NR_EP];
-};
-
-static LIST_HEAD(sta2x11_instance_list);
-
-/* At probe time, record new instances of this bridge (likely one only) */
-static void sta2x11_new_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = kzalloc(sizeof(*instance), GFP_ATOMIC);
-	if (!instance)
-		return;
-	/* This has a subordinate bridge, with 4 more-subordinate ones */
-	instance->bus0 = pdev->subordinate->number + 1;
-
-	if (list_empty(&sta2x11_instance_list)) {
-		int size = STA2X11_SWIOTLB_SIZE;
-		/* First instance: register your own swiotlb area */
-		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_init_late(size, GFP_DMA, NULL))
-			dev_emerg(&pdev->dev, "init swiotlb failed\n");
-	}
-	list_add(&instance->list, &sta2x11_instance_list);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, 0xcc17, sta2x11_new_instance);
-
-/*
- * Utility functions used in this file from below
- */
-static struct sta2x11_instance *sta2x11_pdev_to_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	list_for_each_entry(instance, &sta2x11_instance_list, list) {
-		ep = pdev->bus->number - instance->bus0;
-		if (ep >= 0 && ep < STA2X11_NR_EP)
-			return instance;
-	}
-	return NULL;
-}
-
-static int sta2x11_pdev_to_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return -1;
-
-	return pdev->bus->number - instance->bus0;
-}
-
-/* This is exported, as some devices need to access the MFD registers */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
-{
-	return sta2x11_pdev_to_instance(pdev);
-}
-EXPORT_SYMBOL(sta2x11_get_instance);
-
-/* At setup time, we use our own ops if the device is a ConneXt one */
-static void sta2x11_setup_pdev(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-
-	if (!instance) /* either a sta2x11 bridge or another ST device */
-		return;
-
-	/* We must enable all devices as master, for audio DMA to work */
-	pci_set_master(pdev);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev);
-
-/*
- * At boot we must set up the mappings for the pcie-to-amba bridge.
- * It involves device access, and the same happens at suspend/resume time
- */
-
-#define AHB_MAPB		0xCA4
-#define AHB_CRW(i)		(AHB_MAPB + 0  + (i) * 0x10)
-#define AHB_CRW_SZMASK			0xfffffc00UL
-#define AHB_CRW_ENABLE			(1 << 0)
-#define AHB_CRW_WTYPE_MEM		(2 << 1)
-#define AHB_CRW_ROE			(1UL << 3)	/* Relax Order Ena */
-#define AHB_CRW_NSE			(1UL << 4)	/* No Snoop Enable */
-#define AHB_BASE(i)		(AHB_MAPB + 4  + (i) * 0x10)
-#define AHB_PEXLBASE(i)		(AHB_MAPB + 8  + (i) * 0x10)
-#define AHB_PEXHBASE(i)		(AHB_MAPB + 12 + (i) * 0x10)
-
-/* At probe time, enable mapping for each endpoint, using the pdev */
-static void sta2x11_map_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-	struct device *dev = &pdev->dev;
-	u32 amba_base, max_amba_addr;
-	int i, ret;
-
-	if (!instance)
-		return;
-
-	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
-	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
-
-	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
-	if (ret)
-		dev_err(dev, "sta2x11: could not set DMA offset\n");
-
-	dev->bus_dma_limit = max_amba_addr;
-	dma_set_mask_and_coherent(&pdev->dev, max_amba_addr);
-
-	/* Configure AHB mapping */
-	pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_PEXHBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_CRW(0), STA2X11_AMBA_SIZE |
-			       AHB_CRW_WTYPE_MEM | AHB_CRW_ENABLE);
-
-	/* Disable all the other windows */
-	for (i = 1; i < STA2X11_NR_FUNCS; i++)
-		pci_write_config_dword(pdev, AHB_CRW(i), 0);
-
-	dev_info(&pdev->dev,
-		 "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n",
-		 sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep);
-
-#ifdef CONFIG_PM /* Some register values must be saved and restored */
-
-static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return NULL;
-	ep = sta2x11_pdev_to_ep(pdev);
-	return instance->map + ep;
-}
-
-static void suspend_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-	if (map->is_suspended)
-		return;
-	map->is_suspended = 1;
-
-	/* Save all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_read_config_dword(pdev, AHB_BASE(i), &regs->base);
-		pci_read_config_dword(pdev, AHB_PEXLBASE(i), &regs->pexlbase);
-		pci_read_config_dword(pdev, AHB_PEXHBASE(i), &regs->pexhbase);
-		pci_read_config_dword(pdev, AHB_CRW(i), &regs->crw);
-	}
-}
-DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, suspend_mapping);
-
-static void resume_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-
-	if (!map->is_suspended)
-		goto out;
-	map->is_suspended = 0;
-
-	/* Restore all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_write_config_dword(pdev, AHB_BASE(i), regs->base);
-		pci_write_config_dword(pdev, AHB_PEXLBASE(i), regs->pexlbase);
-		pci_write_config_dword(pdev, AHB_PEXHBASE(i), regs->pexhbase);
-		pci_write_config_dword(pdev, AHB_CRW(i), regs->crw);
-	}
-out:
-	pci_set_master(pdev); /* Like at boot, enable master on all devices */
-}
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, resume_mapping);
-
-#endif /* CONFIG_PM */
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 4733a5f467b8..cfa18ec7d55f 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -173,10 +173,14 @@ SYM_CODE_START(pvh_start_xen)
 1:
 	UNWIND_HINT_END_OF_STACK
 
-	/* Set base address in stack canary descriptor. */
-	mov $MSR_GS_BASE,%ecx
-	leal canary(%rip), %eax
-	xor %edx, %edx
+	/*
+	 * Set up GSBASE.
+	 * Note that on SMP the boot CPU uses the init data section until
+	 * the per-CPU areas are set up.
+	 */
+	movl $MSR_GS_BASE,%ecx
+	xorl %eax, %eax
+	xorl %edx, %edx
 	wrmsr
 
 	/* Call xen_prepare_pvh() via the kernel virtual mapping */
@@ -238,8 +242,6 @@ SYM_DATA_START_LOCAL(gdt_start)
 SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
 
 	.balign 16
-SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
-
 SYM_DATA_START_LOCAL(early_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
 SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 0a0539e1cc81..8c534c36adfa 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -26,6 +26,7 @@
 	 /* code below belongs to the image kernel */
 	.align PAGE_SIZE
 SYM_FUNC_START(restore_registers)
+	ANNOTATE_NOENDBR
 	/* go back to the original page tables */
 	movq    %r9, %cr3
 
@@ -119,6 +120,7 @@ SYM_FUNC_END(restore_image)
 
 	/* code below has been relocated to a safe page */
 SYM_FUNC_START(core_restore_code)
+	ANNOTATE_NOENDBR
 	/* switch to temporary page tables */
 	movq	%rax, %cr3
 	/* flush TLB */
diff --git a/arch/x86/realmode/rm/realmode.h b/arch/x86/realmode/rm/realmode.h
index c76041a35397..867e55f1d6af 100644
--- a/arch/x86/realmode/rm/realmode.h
+++ b/arch/x86/realmode/rm/realmode.h
@@ -2,7 +2,7 @@
 #ifndef ARCH_X86_REALMODE_RM_REALMODE_H
 #define ARCH_X86_REALMODE_RM_REALMODE_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 /*
  * 16-bit ljmpw to the real_mode_seg
@@ -12,7 +12,7 @@
  */
 #define LJMPW_RM(to)	.byte 0xea ; .word (to), real_mode_seg
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Signature at the end of the realmode region
diff --git a/arch/x86/realmode/rm/wakeup.h b/arch/x86/realmode/rm/wakeup.h
index 0e4fd08ae447..3b6d8fa82d3e 100644
--- a/arch/x86/realmode/rm/wakeup.h
+++ b/arch/x86/realmode/rm/wakeup.h
@@ -7,7 +7,7 @@
 #ifndef ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H
 #define ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 
 /* This must match data at wakeup.S */
diff --git a/arch/x86/tools/cpufeaturemasks.awk b/arch/x86/tools/cpufeaturemasks.awk
new file mode 100755
index 000000000000..173d5bf2d999
--- /dev/null
+++ b/arch/x86/tools/cpufeaturemasks.awk
@@ -0,0 +1,88 @@
+#!/usr/bin/awk
+#
+# Convert cpufeatures.h to a list of compile-time masks
+# Note: this blithely assumes that each word has at least one
+# feature defined in it; if not, something else is wrong!
+#
+
+BEGIN {
+	printf "#ifndef _ASM_X86_CPUFEATUREMASKS_H\n";
+	printf "#define _ASM_X86_CPUFEATUREMASKS_H\n\n";
+
+	file = 0
+}
+
+FNR == 1 {
+	++file;
+
+	# arch/x86/include/asm/cpufeatures.h
+	if (file == 1)
+		FS = "[ \t()*+]+";
+
+	# .config
+	if (file == 2)
+		FS = "=";
+}
+
+# Create a dictionary of sorts, containing all defined feature bits
+file == 1 && $1 ~ /^#define$/ && $2 ~ /^X86_FEATURE_/ {
+	nfeat = $3 * $4 + $5;
+	feat = $2;
+	sub(/^X86_FEATURE_/, "", feat);
+	feats[nfeat] = feat;
+}
+file == 1 && $1 ~ /^#define$/ && $2 == "NCAPINTS" {
+	ncapints = int($3);
+}
+
+# Create a dictionary featstat[REQUIRED|DISABLED, FEATURE_NAME] = on | off
+file == 2 && $1 ~ /^CONFIG_X86_(REQUIRED|DISABLED)_FEATURE_/ {
+	on = ($2 == "y");
+	if (split($1, fs, "CONFIG_X86_|_FEATURE_") == 3)
+		featstat[fs[2], fs[3]] = on;
+}
+
+END {
+	sets[1] = "REQUIRED";
+	sets[2] = "DISABLED";
+
+	for (ns in sets) {
+		s = sets[ns];
+
+		printf "/*\n";
+		printf " * %s features:\n", s;
+		printf " *\n";
+		fstr = "";
+		for (i = 0; i < ncapints; i++) {
+			mask = 0;
+			for (j = 0; j < 32; j++) {
+				feat = feats[i*32 + j];
+				if (featstat[s, feat]) {
+					nfstr = fstr " " feat;
+					if (length(nfstr) > 72) {
+						printf " *   %s\n", fstr;
+						nfstr = " " feat;
+					}
+					fstr = nfstr;
+					mask += (2 ^ j);
+				}
+			}
+			masks[i] = mask;
+		}
+		printf " *   %s\n */\n", fstr;
+
+		for (i = 0; i < ncapints; i++)
+			printf "#define %s_MASK%d\t0x%08xU\n", s, i, masks[i];
+
+		printf "\n#define %s_MASK_BIT_SET(x)\t\t\t\\\n", s;
+		printf "\t((\t\t\t\t\t";
+		for (i = 0; i < ncapints; i++) {
+			if (masks[i])
+				printf "\t\\\n\t\t((x) >> 5) == %2d ? %s_MASK%d :", i, s, i;
+		}
+		printf " 0\t\\\n";
+		printf "\t) & (1U << ((x) & 31)))\n\n";
+	}
+
+	printf "#endif /* _ASM_X86_CPUFEATUREMASKS_H */\n";
+}
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e937be979ec8..5778bc498415 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -29,9 +29,13 @@ static struct relocs		relocs16;
 static struct relocs		relocs32;
 
 #if ELF_BITS == 64
-static struct relocs		relocs32neg;
 static struct relocs		relocs64;
 # define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
 #else
 # define FMT PRIu32
 #endif
@@ -86,8 +90,6 @@ static const char * const	sym_regex_kernel[S_NSYMTYPES] = {
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"__per_cpu_load|"
-	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
 	"_end)$"
@@ -227,6 +229,7 @@ static const char *rel_type(unsigned type)
 		REL_TYPE(R_X86_64_PC16),
 		REL_TYPE(R_X86_64_8),
 		REL_TYPE(R_X86_64_PC8),
+		REL_TYPE(R_X86_64_REX_GOTPCRELX),
 #else
 		REL_TYPE(R_386_NONE),
 		REL_TYPE(R_386_32),
@@ -284,34 +287,6 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 	return name;
 }
 
-static Elf_Sym *sym_lookup(const char *symname)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		struct section *sec = &secs[i];
-		long nsyms;
-		char *strtab;
-		Elf_Sym *symtab;
-		Elf_Sym *sym;
-
-		if (sec->shdr.sh_type != SHT_SYMTAB)
-			continue;
-
-		nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
-		symtab = sec->symtab;
-		strtab = sec->link->strtab;
-
-		for (sym = symtab; --nsyms >= 0; sym++) {
-			if (!sym->st_name)
-				continue;
-			if (strcmp(symname, strtab + sym->st_name) == 0)
-				return sym;
-		}
-	}
-	return 0;
-}
-
 #if BYTE_ORDER == LITTLE_ENDIAN
 # define le16_to_cpu(val)	(val)
 # define le32_to_cpu(val)	(val)
@@ -760,84 +735,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 	}
 }
 
-/*
- * The .data..percpu section is a special case for x86_64 SMP kernels.
- * It is used to initialize the actual per_cpu areas and to provide
- * definitions for the per_cpu variables that correspond to their offsets
- * within the percpu area. Since the values of all of the symbols need
- * to be offsets from the start of the per_cpu area the virtual address
- * (sh_addr) of .data..percpu is 0 in SMP kernels.
- *
- * This means that:
- *
- *	Relocations that reference symbols in the per_cpu area do not
- *	need further relocation (since the value is an offset relative
- *	to the start of the per_cpu area that does not change).
- *
- *	Relocations that apply to the per_cpu area need to have their
- *	offset adjusted by by the value of __per_cpu_load to make them
- *	point to the correct place in the loaded image (because the
- *	virtual address of .data..percpu is 0).
- *
- * For non SMP kernels .data..percpu is linked as part of the normal
- * kernel data and does not require special treatment.
- *
- */
-static int per_cpu_shndx = -1;
-static Elf_Addr per_cpu_load_addr;
-
-static void percpu_init(void)
-{
-	int i;
-
-	for (i = 0; i < shnum; i++) {
-		ElfW(Sym) *sym;
-
-		if (strcmp(sec_name(i), ".data..percpu"))
-			continue;
-
-		if (secs[i].shdr.sh_addr != 0)	/* non SMP kernel */
-			return;
-
-		sym = sym_lookup("__per_cpu_load");
-		if (!sym)
-			die("can't find __per_cpu_load\n");
-
-		per_cpu_shndx = i;
-		per_cpu_load_addr = sym->st_value;
-
-		return;
-	}
-}
-
 #if ELF_BITS == 64
 
-/*
- * Check to see if a symbol lies in the .data..percpu section.
- *
- * The linker incorrectly associates some symbols with the
- * .data..percpu section so we also need to check the symbol
- * name to make sure that we classify the symbol correctly.
- *
- * The GNU linker incorrectly associates:
- *	__init_begin
- *	__per_cpu_load
- *
- * The "gold" linker incorrectly associates:
- *	init_per_cpu__fixed_percpu_data
- *	init_per_cpu__gdt_page
- */
-static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-{
-	int shndx = sym_index(sym);
-
-	return (shndx == per_cpu_shndx) &&
-		strcmp(symname, "__init_begin") &&
-		strcmp(symname, "__per_cpu_load") &&
-		strncmp(symname, "init_per_cpu_", 13);
-}
-
-
 static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 		      const char *symname)
 {
@@ -848,12 +747,6 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 	if (sym->st_shndx == SHN_UNDEF)
 		return 0;
 
-	/*
-	 * Adjust the offset if this reloc applies to the percpu section.
-	 */
-	if (sec->shdr.sh_info == per_cpu_shndx)
-		offset += per_cpu_load_addr;
-
 	switch (r_type) {
 	case R_X86_64_NONE:
 		/* NONE can be ignored. */
@@ -861,33 +754,23 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
 
 	case R_X86_64_PC32:
 	case R_X86_64_PLT32:
+	case R_X86_64_REX_GOTPCRELX:
 		/*
-		 * PC relative relocations don't need to be adjusted unless
-		 * referencing a percpu symbol.
+		 * PC relative relocations don't need to be adjusted.
 		 *
 		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
-		if (is_percpu_sym(sym, symname))
-			add_reloc(&relocs32neg, offset);
 		break;
 
 	case R_X86_64_PC64:
 		/*
 		 * Only used by jump labels
 		 */
-		if (is_percpu_sym(sym, symname))
-			die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
 		break;
 
 	case R_X86_64_32:
 	case R_X86_64_32S:
 	case R_X86_64_64:
-		/*
-		 * References to the percpu area don't need to be adjusted.
-		 */
-		if (is_percpu_sym(sym, symname))
-			break;
-
 		if (shn_abs) {
 			/*
 			 * Whitelisted absolute symbols do not require
@@ -1055,7 +938,8 @@ static int cmp_relocs(const void *va, const void *vb)
 
 static void sort_relocs(struct relocs *r)
 {
-	qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+	if (r->count)
+		qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
 }
 
 static int write32(uint32_t v, FILE *f)
@@ -1099,7 +983,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 	/* Order the relocations for more efficient processing */
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
-	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
 #else
 	sort_relocs(&relocs16);
@@ -1131,13 +1014,6 @@ static void emit_relocs(int as_text, int use_real_mode)
 		/* Now print each relocation */
 		for (i = 0; i < relocs64.count; i++)
 			write_reloc(relocs64.offset[i], stdout);
-
-		/* Print a stop */
-		write_reloc(0, stdout);
-
-		/* Now print each inverse 32-bit relocation */
-		for (i = 0; i < relocs32neg.count; i++)
-			write_reloc(relocs32neg.offset[i], stdout);
 #endif
 
 		/* Print a stop */
@@ -1190,9 +1066,6 @@ void process(FILE *fp, int use_real_mode, int as_text,
 	read_symtabs(fp);
 	read_relocs(fp);
 
-	if (ELF_BITS == 64)
-		percpu_init();
-
 	if (show_absolute_syms) {
 		print_absolute_symbols();
 		return;
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 77e788e928cd..98d8a50d2aed 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,7 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MATOM)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5e57835e999d..dcc2041f8e61 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -73,6 +73,7 @@
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/cpu.h>
+#include <asm/irq_stack.h>
 #ifdef CONFIG_X86_IOPL_IOPERM
 #include <asm/io_bitmap.h>
 #endif
@@ -94,6 +95,44 @@ void *xen_initial_gdt;
 static int xen_cpu_up_prepare_pv(unsigned int cpu);
 static int xen_cpu_dead_pv(unsigned int cpu);
 
+#ifndef CONFIG_PREEMPTION
+/*
+ * Some hypercalls issued by the toolstack can take many 10s of
+ * seconds. Allow tasks running hypercalls via the privcmd driver to
+ * be voluntarily preempted even if full kernel preemption is
+ * disabled.
+ *
+ * Such preemptible hypercalls are bracketed by
+ * xen_preemptible_hcall_begin() and xen_preemptible_hcall_end()
+ * calls.
+ */
+DEFINE_PER_CPU(bool, xen_in_preemptible_hcall);
+EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
+
+/*
+ * In case of scheduling the flag must be cleared and restored after
+ * returning from schedule as the task might move to a different CPU.
+ */
+static __always_inline bool get_and_clear_inhcall(void)
+{
+	bool inhcall = __this_cpu_read(xen_in_preemptible_hcall);
+
+	__this_cpu_write(xen_in_preemptible_hcall, false);
+	return inhcall;
+}
+
+static __always_inline void restore_inhcall(bool inhcall)
+{
+	__this_cpu_write(xen_in_preemptible_hcall, inhcall);
+}
+
+#else
+
+static __always_inline bool get_and_clear_inhcall(void) { return false; }
+static __always_inline void restore_inhcall(bool inhcall) { }
+
+#endif
+
 struct tls_descs {
 	struct desc_struct desc[3];
 };
@@ -687,6 +726,36 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_machine_check)
 }
 #endif
 
+static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	inc_irq_stat(irq_hv_callback_count);
+
+	xen_evtchn_do_upcall();
+
+	set_irq_regs(old_regs);
+}
+
+__visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs)
+{
+	irqentry_state_t state = irqentry_enter(regs);
+	bool inhcall;
+
+	instrumentation_begin();
+	run_sysvec_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs);
+
+	inhcall = get_and_clear_inhcall();
+	if (inhcall && !WARN_ON_ONCE(state.exit_rcu)) {
+		irqentry_exit_cond_resched();
+		instrumentation_end();
+		restore_inhcall(inhcall);
+	} else {
+		instrumentation_end();
+		irqentry_exit(regs, state);
+	}
+}
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index d078de2c952b..38971c6dcd4b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2189,7 +2189,6 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.flush_tlb_kernel = xen_flush_tlb,
 		.flush_tlb_one_user = xen_flush_tlb_one_user,
 		.flush_tlb_multi = xen_flush_tlb_multi,
-		.tlb_remove_table = tlb_remove_table,
 
 		.pgd_alloc = xen_pgd_alloc,
 		.pgd_free = xen_pgd_free,
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6863d3da7dec..688ff59318ae 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -70,7 +70,7 @@ static void cpu_bringup(void)
 		xen_enable_syscall();
 	}
 	cpu = smp_processor_id();
-	smp_store_cpu_info(cpu);
+	identify_secondary_cpu(cpu);
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index b518f36d1ca2..109af12f7647 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -51,6 +51,7 @@ SYM_FUNC_END(xen_hypercall_pv)
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
+	ENDBR
 	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
@@ -90,6 +91,7 @@ SYM_FUNC_END(check_events)
  * then enter the hypervisor to get them handled.
  */
 SYM_FUNC_START(xen_irq_enable_direct)
+	ENDBR
 	FRAME_BEGIN
 	/* Unmask events */
 	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
@@ -120,6 +122,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
+	ENDBR
 	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
@@ -127,6 +130,7 @@ SYM_FUNC_START(xen_save_fl_direct)
 SYM_FUNC_END(xen_save_fl_direct)
 
 SYM_FUNC_START(xen_read_cr2)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
 	_ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX
@@ -135,6 +139,7 @@ SYM_FUNC_START(xen_read_cr2)
 SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
+	ENDBR
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62..5dad6c51cdc3 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -31,16 +31,14 @@ SYM_CODE_START(startup_xen)
 
 	leaq	__top_init_kernel_stack(%rip), %rsp
 
-	/* Set up %gs.
-	 *
-	 * The base of %gs always points to fixed_percpu_data.  If the
-	 * stack protector canary is enabled, it is located at %gs:40.
+	/*
+	 * Set up GSBASE.
 	 * Note that, on SMP, the boot cpu uses init data section until
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
-	cdq
+	xorl	%eax, %eax
+	xorl	%edx, %edx
 	wrmsr
 
 	mov	%rsi, %rdi
@@ -133,11 +131,13 @@ SYM_FUNC_START(xen_hypercall_hvm)
 SYM_FUNC_END(xen_hypercall_hvm)
 
 SYM_FUNC_START(xen_hypercall_amd)
+	ANNOTATE_NOENDBR
 	vmmcall
 	RET
 SYM_FUNC_END(xen_hypercall_amd)
 
 SYM_FUNC_START(xen_hypercall_intel)
+	ANNOTATE_NOENDBR
 	vmcall
 	RET
 SYM_FUNC_END(xen_hypercall_intel)
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 698897b29de2..586cc7d1d8aa 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -590,6 +590,8 @@ static void acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			raw_safe_halt();
 		else if (cx->entry_method == ACPI_CSTATE_SYSTEMIO) {
 			io_idle(cx->address);
+		} else if (cx->entry_method == ACPI_CSTATE_FFH) {
+			acpi_processor_ffh_play_dead(cx);
 		} else
 			return;
 	}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9c4cc01fd51a..f06b9bc99945 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2200,28 +2200,20 @@ static int knl_get_turbo_pstate(int cpu)
 	return ret;
 }
 
-static void hybrid_get_type(void *data)
-{
-	u8 *cpu_type = data;
-
-	*cpu_type = get_this_hybrid_cpu_type();
-}
-
 static int hwp_get_cpu_scaling(int cpu)
 {
 	if (hybrid_scaling_factor) {
-		u8 cpu_type = 0;
-
-		smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
+		struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+		u8 cpu_type = c->topo.intel_type;
 
 		/*
 		 * Return the hybrid scaling factor for P-cores and use the
 		 * default core scaling for E-cores.
 		 */
-		if (cpu_type == 0x40)
+		if (cpu_type == INTEL_CPU_TYPE_CORE)
 			return hybrid_scaling_factor;
 
-		if (cpu_type == 0x20)
+		if (cpu_type == INTEL_CPU_TYPE_ATOM)
 			return core_get_scaling();
 	}
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 0fdb1d1316c4..5687089e406a 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -58,6 +58,7 @@
 #include <asm/spec-ctrl.h>
 #include <asm/tsc.h>
 #include <asm/fpu/api.h>
+#include <asm/smp.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
 
@@ -229,6 +230,15 @@ static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 	return 0;
 }
 
+static void intel_idle_enter_dead(struct cpuidle_device *dev, int index)
+{
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	struct cpuidle_state *state = &drv->states[index];
+	unsigned long eax = flg2MWAIT(state->flags);
+
+	mwait_play_dead(eax);
+}
+
 /*
  * States are indexed by the cstate number,
  * which is also the index into the MWAIT hint array.
@@ -1804,6 +1814,7 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 			mark_tsc_unstable("TSC halts in idle");
 
 		state->enter = intel_idle;
+		state->enter_dead = intel_idle_enter_dead;
 		state->enter_s2idle = intel_idle_s2idle;
 	}
 }
@@ -2153,6 +2164,9 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 		    !cpuidle_state_table[cstate].enter_s2idle)
 			break;
 
+		if (!cpuidle_state_table[cstate].enter_dead)
+			cpuidle_state_table[cstate].enter_dead = intel_idle_enter_dead;
+
 		/* If marked as unusable, skip this state. */
 		if (cpuidle_state_table[cstate].flags & CPUIDLE_FLAG_UNUSABLE) {
 			pr_debug("state %s is disabled\n",
diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig
index 67d9391f1855..7575fee96cc6 100644
--- a/drivers/misc/mei/Kconfig
+++ b/drivers/misc/mei/Kconfig
@@ -3,7 +3,7 @@
 config INTEL_MEI
 	tristate "Intel Management Engine Interface"
 	depends on X86 && PCI
-	default GENERIC_CPU || MCORE2 || MATOM || X86_GENERIC
+	default X86_64 || MATOM
 	help
 	  The Intel Management Engine (Intel ME) provides Manageability,
 	  Security and Media services for system containing Intel chipsets.
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 2fbd379923fd..5c3054aaec8c 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -203,6 +203,12 @@ config PCI_P2PDMA
 	  P2P DMA transactions must be between devices behind the same root
 	  port.
 
+	  Enabling this option will reduce the entropy of x86 KASLR memory
+	  regions. For example - on a 46 bit system, the entropy goes down
+	  from 16 bits to 15 bits. The actual reduction in entropy depends
+	  on the physical address bits, on processor features, kernel config
+	  (5 level page table) and physical memory present on the system.
+
 	  If unsure, say N.
 
 config PCI_LABEL
diff --git a/drivers/platform/x86/amd/hsmp/Kconfig b/drivers/platform/x86/amd/hsmp/Kconfig
index 7d10d4462a45..d6f7a62d55b5 100644
--- a/drivers/platform/x86/amd/hsmp/Kconfig
+++ b/drivers/platform/x86/amd/hsmp/Kconfig
@@ -7,7 +7,7 @@ config AMD_HSMP
 	tristate
 
 menu "AMD HSMP Driver"
-	depends on AMD_NB || COMPILE_TEST
+	depends on AMD_NODE || COMPILE_TEST
 
 config AMD_HSMP_ACPI
 	tristate "AMD HSMP ACPI device driver"
diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c
index 444b43be35a2..c1eccb3c80c5 100644
--- a/drivers/platform/x86/amd/hsmp/acpi.c
+++ b/drivers/platform/x86/amd/hsmp/acpi.c
@@ -10,7 +10,6 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <asm/amd_hsmp.h>
-#include <asm/amd_nb.h>
 
 #include <linux/acpi.h>
 #include <linux/device.h>
@@ -24,6 +23,8 @@
 
 #include <uapi/asm-generic/errno-base.h>
 
+#include <asm/amd_node.h>
+
 #include "hsmp.h"
 
 #define DRIVER_NAME		"amd_hsmp"
@@ -321,8 +322,8 @@ static int hsmp_acpi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	if (!hsmp_pdev->is_probed) {
-		hsmp_pdev->num_sockets = amd_nb_num();
-		if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_SOCKETS)
+		hsmp_pdev->num_sockets = amd_num_nodes();
+		if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_NUM_NODES)
 			return -ENODEV;
 
 		hsmp_pdev->sock = devm_kcalloc(&pdev->dev, hsmp_pdev->num_sockets,
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index 03164e30b3a5..a3ac09a90de4 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -8,7 +8,6 @@
  */
 
 #include <asm/amd_hsmp.h>
-#include <asm/amd_nb.h>
 
 #include <linux/acpi.h>
 #include <linux/delay.h>
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.h b/drivers/platform/x86/amd/hsmp/hsmp.h
index e852f0a947e4..af8b21f821d6 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.h
+++ b/drivers/platform/x86/amd/hsmp/hsmp.h
@@ -21,8 +21,6 @@
 
 #define HSMP_ATTR_GRP_NAME_SIZE	10
 
-#define MAX_AMD_SOCKETS 8
-
 #define HSMP_CDEV_NAME		"hsmp_cdev"
 #define HSMP_DEVNODE_NAME	"hsmp"
 
@@ -41,7 +39,6 @@ struct hsmp_socket {
 	void __iomem *virt_base_addr;
 	struct semaphore hsmp_sem;
 	char name[HSMP_ATTR_GRP_NAME_SIZE];
-	struct pci_dev *root;
 	struct device *dev;
 	u16 sock_ind;
 	int (*amd_hsmp_rdwr)(struct hsmp_socket *sock, u32 off, u32 *val, bool rw);
diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c
index 02ca85762b68..b9782a078dbd 100644
--- a/drivers/platform/x86/amd/hsmp/plat.c
+++ b/drivers/platform/x86/amd/hsmp/plat.c
@@ -10,14 +10,16 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <asm/amd_hsmp.h>
-#include <asm/amd_nb.h>
 
+#include <linux/build_bug.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/sysfs.h>
 
+#include <asm/amd_node.h>
+
 #include "hsmp.h"
 
 #define DRIVER_NAME		"amd_hsmp"
@@ -34,28 +36,12 @@
 #define SMN_HSMP_MSG_RESP	0x0010980
 #define SMN_HSMP_MSG_DATA	0x00109E0
 
-#define HSMP_INDEX_REG		0xc4
-#define HSMP_DATA_REG		0xc8
-
 static struct hsmp_plat_device *hsmp_pdev;
 
 static int amd_hsmp_pci_rdwr(struct hsmp_socket *sock, u32 offset,
 			     u32 *value, bool write)
 {
-	int ret;
-
-	if (!sock->root)
-		return -ENODEV;
-
-	ret = pci_write_config_dword(sock->root, HSMP_INDEX_REG,
-				     sock->mbinfo.base_addr + offset);
-	if (ret)
-		return ret;
-
-	ret = (write ? pci_write_config_dword(sock->root, HSMP_DATA_REG, *value)
-		     : pci_read_config_dword(sock->root, HSMP_DATA_REG, value));
-
-	return ret;
+	return amd_smn_hsmp_rdwr(sock->sock_ind, sock->mbinfo.base_addr + offset, value, write);
 }
 
 static ssize_t hsmp_metric_tbl_plat_read(struct file *filp, struct kobject *kobj,
@@ -95,7 +81,12 @@ static umode_t hsmp_is_sock_attr_visible(struct kobject *kobj,
  * Static array of 8 + 1(for NULL) elements is created below
  * to create sysfs groups for sockets.
  * is_bin_visible function is used to show / hide the necessary groups.
+ *
+ * Validate the maximum number against MAX_AMD_NUM_NODES. If this changes,
+ * then the attributes and groups below must be adjusted.
  */
+static_assert(MAX_AMD_NUM_NODES == 8);
+
 #define HSMP_BIN_ATTR(index, _list)					\
 static const struct bin_attribute attr##index = {			\
 	.attr = { .name = HSMP_METRICS_TABLE_NAME, .mode = 0444},	\
@@ -159,10 +150,7 @@ static int init_platform_device(struct device *dev)
 	int ret, i;
 
 	for (i = 0; i < hsmp_pdev->num_sockets; i++) {
-		if (!node_to_amd_nb(i))
-			return -ENODEV;
 		sock = &hsmp_pdev->sock[i];
-		sock->root			= node_to_amd_nb(i)->root;
 		sock->sock_ind			= i;
 		sock->dev			= dev;
 		sock->mbinfo.base_addr		= SMN_HSMP_BASE;
@@ -305,11 +293,11 @@ static int __init hsmp_plt_init(void)
 		return -ENOMEM;
 
 	/*
-	 * amd_nb_num() returns number of SMN/DF interfaces present in the system
+	 * amd_num_nodes() returns number of SMN/DF interfaces present in the system
 	 * if we have N SMN/DF interfaces that ideally means N sockets
 	 */
-	hsmp_pdev->num_sockets = amd_nb_num();
-	if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_SOCKETS)
+	hsmp_pdev->num_sockets = amd_num_nodes();
+	if (hsmp_pdev->num_sockets == 0 || hsmp_pdev->num_sockets > MAX_AMD_NUM_NODES)
 		return ret;
 
 	ret = platform_driver_register(&amd_hsmp_driver);
diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
index 77d75e1f14a9..5ccde3982314 100644
--- a/drivers/powercap/intel_rapl_common.c
+++ b/drivers/powercap/intel_rapl_common.c
@@ -1274,7 +1274,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	&rapl_defaults_byt),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	&rapl_defaults_cht),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID, &rapl_defaults_tng),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,	&rapl_defaults_ann),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,&rapl_defaults_ann),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS,	&rapl_defaults_core),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D,	&rapl_defaults_core),
diff --git a/drivers/staging/media/atomisp/include/linux/atomisp_platform.h b/drivers/staging/media/atomisp/include/linux/atomisp_platform.h
index 049246774ced..6146555fe9cf 100644
--- a/drivers/staging/media/atomisp/include/linux/atomisp_platform.h
+++ b/drivers/staging/media/atomisp/include/linux/atomisp_platform.h
@@ -172,10 +172,10 @@ void atomisp_unregister_subdev(struct v4l2_subdev *subdev);
 #define IS_BYT	__IS_SOC(INTEL_ATOM_SILVERMONT)
 #define IS_CHT	__IS_SOC(INTEL_ATOM_AIRMONT)
 #define IS_MRFD	__IS_SOC(INTEL_ATOM_SILVERMONT_MID)
-#define IS_MOFD	__IS_SOC(INTEL_ATOM_AIRMONT_MID)
+#define IS_MOFD	__IS_SOC(INTEL_ATOM_SILVERMONT_MID2)
 
 /* Both CHT and MOFD come with ISP2401 */
 #define IS_ISP2401 __IS_SOCS(INTEL_ATOM_AIRMONT, \
-			     INTEL_ATOM_AIRMONT_MID)
+			     INTEL_ATOM_SILVERMONT_MID2)
 
 #endif /* ATOMISP_PLATFORM_H_ */
diff --git a/drivers/thermal/intel/intel_tcc.c b/drivers/thermal/intel/intel_tcc.c
index 817421508d5c..b2a615aea7c1 100644
--- a/drivers/thermal/intel/intel_tcc.c
+++ b/drivers/thermal/intel/intel_tcc.c
@@ -106,7 +106,7 @@ static const struct x86_cpu_id intel_tcc_cpu_ids[] __initconst = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_D,		&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID,	&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,		&temp_broadwell),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,		&temp_broadwell),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,	&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP,		&temp_broadwell),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT,		&temp_goldmont),
 	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D,		&temp_goldmont),
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 70fbc9a3e703..cf3fb61f4d5b 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -23,6 +23,7 @@
 #include <linux/cleanup.h>
 #include <linux/uuid.h>
 #include <linux/configfs.h>
+#include <linux/mm.h>
 #include <uapi/linux/sev-guest.h>
 #include <uapi/linux/psp-sev.h>
 
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index a17e97e634a6..d0eccbd920e5 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -280,6 +280,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 				    struct acpi_processor_cx *cx,
 				    struct acpi_power_register *reg);
 void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cstate);
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx);
 #else
 static inline void acpi_processor_power_init_bm_check(struct
 						      acpi_processor_flags
@@ -300,6 +301,10 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 {
 	return;
 }
+static inline void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	BUG();
+}
 #endif
 
 static inline int call_on_cpu(int cpu, long (*fn)(void *), void *arg,
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c768de6f19a9..0755bc39b0d8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char __start_ro_after_init[], __end_ro_after_init[];
 extern char _end[];
-extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __entry_text_start[], __entry_text_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0d5b186abee8..4925441bc471 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -385,6 +385,11 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN(PAGE_SIZE);						\
 	__nosave_end = .;
 
+#define CACHE_HOT_DATA(align)						\
+	. = ALIGN(align);						\
+	*(SORT_BY_ALIGNMENT(.data..hot.*))				\
+	. = ALIGN(align);
+
 #define PAGE_ALIGNED_DATA(page_align)					\
 	. = ALIGN(page_align);						\
 	*(.data..page_aligned)						\
@@ -1062,10 +1067,13 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
  */
 #define PERCPU_INPUT(cacheline)						\
 	__per_cpu_start = .;						\
-	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
+	__per_cpu_hot_start = .;					\
+	*(SORT_BY_ALIGNMENT(.data..percpu..hot.*))			\
+	__per_cpu_hot_end = .;						\
+	. = ALIGN(cacheline);						\
 	*(.data..percpu..read_mostly)					\
 	. = ALIGN(cacheline);						\
 	*(.data..percpu)						\
@@ -1074,52 +1082,17 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	__per_cpu_end = .;
 
 /**
- * PERCPU_VADDR - define output section for percpu area
+ * PERCPU_SECTION - define output section for percpu area
  * @cacheline: cacheline size
- * @vaddr: explicit base address (optional)
- * @phdr: destination PHDR (optional)
  *
  * Macro which expands to output section for percpu area.
  *
  * @cacheline is used to align subsections to avoid false cacheline
  * sharing between subsections for different purposes.
- *
- * If @vaddr is not blank, it specifies explicit base address and all
- * percpu symbols will be offset from the given address.  If blank,
- * @vaddr always equals @laddr + LOAD_OFFSET.
- *
- * @phdr defines the output PHDR to use if not blank.  Be warned that
- * output PHDR is sticky.  If @phdr is specified, the next output
- * section in the linker script will go there too.  @phdr should have
- * a leading colon.
- *
- * Note that this macros defines __per_cpu_load as an absolute symbol.
- * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU_SECTION.
- */
-#define PERCPU_VADDR(cacheline, vaddr, phdr)				\
-	__per_cpu_load = .;						\
-	.data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) {	\
-		PERCPU_INPUT(cacheline)					\
-	} phdr								\
-	. = __per_cpu_load + SIZEOF(.data..percpu);
-
-/**
- * PERCPU_SECTION - define output section for percpu area, simple version
- * @cacheline: cacheline size
- *
- * Align to PAGE_SIZE and outputs output section for percpu area.  This
- * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
- * __per_cpu_start will be identical.
- *
- * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
- * except that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32 configuration.
  */
 #define PERCPU_SECTION(cacheline)					\
 	. = ALIGN(PAGE_SIZE);						\
 	.data..percpu	: AT(ADDR(.data..percpu) - LOAD_OFFSET) {	\
-		__per_cpu_load = .;					\
 		PERCPU_INPUT(cacheline)					\
 	}
 
@@ -1148,6 +1121,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 		INIT_TASK_DATA(inittask)				\
 		NOSAVE_DATA						\
 		PAGE_ALIGNED_DATA(pagealigned)				\
+		CACHE_HOT_DATA(cacheline)				\
 		CACHELINE_ALIGNED_DATA(cacheline)			\
 		READ_MOSTLY_DATA(cacheline)				\
 		DATA_DATA						\
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 4e495b29c640..a70e62d69dc7 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -330,7 +330,6 @@ static inline bool acpi_sci_irq_valid(void)
 }
 
 extern int sbf_port;
-extern unsigned long acpi_realmode_flags;
 
 int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index f0df518e11dd..1db17ecbb86c 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -11,6 +11,8 @@
 #include <linux/module.h>
 #include <asm/cfi.h>
 
+extern bool cfi_warn;
+
 #ifndef cfi_get_offset
 static inline int cfi_get_offset(void)
 {
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6db889c9efcc..9fc30b6b80c9 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -228,6 +228,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 #endif /* __KERNEL__ */
 
+#if defined(CONFIG_CFI_CLANG) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+/*
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
+ */
+#define KCFI_REFERENCE(sym) __ADDRESSABLE(sym)
+#else
+#define KCFI_REFERENCE(sym)
+#endif
+
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
  * @off:	the address of the 32-bit offset value
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 64130ae19690..65655a5d1be2 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -65,6 +65,37 @@ enum execmem_range_flags {
  * Architectures that use EXECMEM_ROX_CACHE must implement this.
  */
 void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
+
+/**
+ * execmem_make_temp_rw - temporarily remap region with read-write
+ *			  permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Remaps a part of the cached large page in the ROX cache in the range
+ * [@ptr, @ptr + @size) as writable and not executable. The caller must
+ * have exclusive ownership of this range and ensure nothing will try to
+ * execute code in this range.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_make_temp_rw(void *ptr, size_t size);
+
+/**
+ * execmem_restore_rox - restore read-only-execute permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Restores read-only-execute permissions on a range [@ptr, @ptr + @size)
+ * after it was temporarily remapped as writable. Relies on architecture
+ * implementation of set_memory_rox() to restore mapping using large pages.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_restore_rox(void *ptr, size_t size);
+#else
+static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
+static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
 #endif
 
 /**
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index d67614f7b7f1..bd7e60c0b72f 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -692,6 +692,7 @@ struct x86_cpu_id {
 	__u16 feature;	/* bit index */
 	/* Solely for kernel-internal use: DO NOT EXPORT to userspace! */
 	__u16 flags;
+	__u8  type;
 	kernel_ulong_t driver_data;
 };
 
@@ -703,6 +704,7 @@ struct x86_cpu_id {
 #define X86_STEP_MIN 0
 #define X86_STEP_MAX 0xf
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
+#define X86_CPU_TYPE_ANY 0
 
 /*
  * Generic table type for matching CPU features.
diff --git a/include/linux/module.h b/include/linux/module.h
index 30e5b19bafa9..9937e71a3b5b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -370,7 +370,6 @@ enum mod_mem_type {
 
 struct module_memory {
 	void *base;
-	void *rw_copy;
 	bool is_rox;
 	unsigned int size;
 
@@ -772,16 +771,6 @@ static inline bool is_livepatch_module(struct module *mod)
 
 void set_module_sig_enforced(void);
 
-void *__module_writable_address(struct module *mod, void *loc);
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) || !mod ||
-	    mod->state != MODULE_STATE_UNFORMED)
-		return loc;
-	return __module_writable_address(mod, loc);
-}
-
 #else /* !CONFIG_MODULES... */
 
 static inline struct module *__module_address(unsigned long addr)
@@ -889,11 +878,6 @@ static inline bool module_is_coming(struct module *mod)
 {
 	return false;
 }
-
-static inline void *module_writable_address(struct module *mod, void *loc)
-{
-	return loc;
-}
 #endif /* CONFIG_MODULES */
 
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 1f5507ba5a12..e395461d59e5 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -108,10 +108,6 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *mod);
 
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *mod);
-
 #ifdef CONFIG_MODULES
 void flush_module_init_free_work(void);
 #else
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index c722a921165b..3ca965a2ddc8 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -128,7 +128,7 @@
 #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
 #define STACK_FRAME_NON_STANDARD_FP(func)
-#define __ASM_ANNOTATE(label, type)
+#define __ASM_ANNOTATE(label, type) ""
 #define ASM_ANNOTATE(type)
 #else
 .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0
@@ -147,6 +147,8 @@
  * these relocations will never be used for indirect calls.
  */
 #define ANNOTATE_NOENDBR		ASM_ANNOTATE(ANNOTYPE_NOENDBR)
+#define ANNOTATE_NOENDBR_SYM(sym)	asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR))
+
 /*
  * This should be used immediately before an indirect jump/call. It tells
  * objtool the subsequent indirect jump/call is vouched safe for retpoline
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5b520fe86b60..0fcacb909778 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -26,13 +26,11 @@
 #define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
 #endif
-#define PER_CPU_FIRST_SECTION "..first"
 
 #else
 
 #define PER_CPU_SHARED_ALIGNED_SECTION ""
 #define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
 
 #endif
 
@@ -115,14 +113,17 @@
 	DEFINE_PER_CPU_SECTION(type, name, "")
 
 /*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
+ * Declaration/definition used for per-CPU variables that are frequently
+ * accessed and should be in a single cacheline.
+ *
+ * For use only by architecture and core code.  Only use scalar or pointer
+ * types to maximize density.
  */
-#define DECLARE_PER_CPU_FIRST(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+#define DECLARE_PER_CPU_CACHE_HOT(type, name)				\
+	DECLARE_PER_CPU_SECTION(type, name, "..hot.." #name)
 
-#define DEFINE_PER_CPU_FIRST(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
+#define DEFINE_PER_CPU_CACHE_HOT(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, "..hot.." #name)
 
 /*
  * Declaration/definition used for per-CPU variables that must be cacheline
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 3e9808f2b549..b0af8d4ef6e6 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -319,6 +319,7 @@ do { \
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
+struct task_struct;
 
 /**
  * preempt_ops - notifiers called when a task is preempted and rescheduled
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index c3a00b967d18..49039494076f 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -23,17 +23,25 @@
 #define SZ_4K				0x00001000
 #define SZ_8K				0x00002000
 #define SZ_16K				0x00004000
+#define SZ_24K				0x00006000
 #define SZ_32K				0x00008000
 #define SZ_64K				0x00010000
 #define SZ_128K				0x00020000
+#define SZ_192K				0x00030000
 #define SZ_256K				0x00040000
+#define SZ_384K				0x00060000
 #define SZ_512K				0x00080000
 
 #define SZ_1M				0x00100000
 #define SZ_2M				0x00200000
+#define SZ_3M				0x00300000
 #define SZ_4M				0x00400000
+#define SZ_6M				0x00600000
 #define SZ_8M				0x00800000
+#define SZ_12M				0x00c00000
 #define SZ_16M				0x01000000
+#define SZ_18M				0x01200000
+#define SZ_24M				0x01800000
 #define SZ_32M				0x02000000
 #define SZ_64M				0x04000000
 #define SZ_128M				0x08000000
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index f70d0958095c..5a37cb2b6f93 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -151,6 +151,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
 		DIRECT_MAP_LEVEL3_SPLIT,
+		DIRECT_MAP_LEVEL2_COLLAPSE,
+		DIRECT_MAP_LEVEL3_COLLAPSE,
 #endif
 #ifdef CONFIG_PER_VMA_LOCK_STATS
 		VMA_LOCK_SUCCESS,
diff --git a/init/Kconfig b/init/Kconfig
index aeea36d11dda..681f38ee68db 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1880,11 +1880,6 @@ config KALLSYMS_ALL
 
 	  Say N unless you really need all symbols, or kernel live patching.
 
-config KALLSYMS_ABSOLUTE_PERCPU
-	bool
-	depends on KALLSYMS
-	default X86_64 && SMP
-
 # end of the "standard kernel features (expert users)" menu
 
 config ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 60611df77957..6e604caa870c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21702,12 +21702,12 @@ patch_map_ops_generic:
 		if (insn->imm == BPF_FUNC_get_smp_processor_id &&
 		    verifier_inlines_helper_call(env, insn->imm)) {
 			/* BPF_FUNC_get_smp_processor_id inlining is an
-			 * optimization, so if pcpu_hot.cpu_number is ever
+			 * optimization, so if cpu_number is ever
 			 * changed in some incompatible and hard to support
 			 * way, it's fine to back out this inlining logic
 			 */
 #ifdef CONFIG_SMP
-			insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
+			insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&cpu_number);
 			insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
 			insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
 			cnt = 3;
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 08caad776717..19be79639542 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -7,6 +7,8 @@
 
 #include <linux/cfi.h>
 
+bool cfi_warn __ro_after_init = IS_ENABLED(CONFIG_CFI_PERMISSIVE);
+
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 				      unsigned long *target, u32 type)
 {
@@ -17,7 +19,7 @@ enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 		pr_err("CFI failure at %pS (no target information)\n",
 		       (void *)addr);
 
-	if (IS_ENABLED(CONFIG_CFI_PERMISSIVE)) {
+	if (cfi_warn) {
 		__warn(NULL, 0, (void *)addr, 0, regs, NULL);
 		return BUG_TRAP_TYPE_WARN;
 	}
diff --git a/kernel/iomem.c b/kernel/iomem.c
index dc2120776e1c..75e61c1c6bc0 100644
--- a/kernel/iomem.c
+++ b/kernel/iomem.c
@@ -6,7 +6,8 @@
 #include <linux/ioremap.h>
 
 #ifndef arch_memremap_wb
-static void *arch_memremap_wb(resource_size_t offset, unsigned long size)
+static void *arch_memremap_wb(resource_size_t offset, unsigned long size,
+			      unsigned long flags)
 {
 #ifdef ioremap_cache
 	return (__force void *)ioremap_cache(offset, size);
@@ -91,7 +92,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 		if (is_ram == REGION_INTERSECTS)
 			addr = try_ram_remap(offset, size, flags);
 		if (!addr)
-			addr = arch_memremap_wb(offset, size);
+			addr = arch_memremap_wb(offset, size, flags);
 	}
 
 	/*
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index a9a0ca605d4a..4198f30aac3c 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -148,16 +148,8 @@ static unsigned int get_symbol_offset(unsigned long pos)
 
 unsigned long kallsyms_sym_address(int idx)
 {
-	/* values are unsigned offsets if --absolute-percpu is not in effect */
-	if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
-		return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
-
-	/* ...otherwise, positive offsets are absolute values */
-	if (kallsyms_offsets[idx] >= 0)
-		return kallsyms_offsets[idx];
-
-	/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
-	return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+	/* values are unsigned offsets */
+	return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
 }
 
 static unsigned int get_symbol_seq(int index)
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 1fb9ad289a6f..a256cc919ad7 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1221,18 +1221,6 @@ void __weak module_arch_freeing_init(struct module *mod)
 {
 }
 
-void *__module_writable_address(struct module *mod, void *loc)
-{
-	for_class_mod_mem_type(type, text) {
-		struct module_memory *mem = &mod->mem[type];
-
-		if (loc >= mem->base && loc < mem->base + mem->size)
-			return loc + (mem->rw_copy - mem->base);
-	}
-
-	return loc;
-}
-
 static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 {
 	unsigned int size = PAGE_ALIGN(mod->mem[type].size);
@@ -1250,21 +1238,15 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	if (!ptr)
 		return -ENOMEM;
 
-	mod->mem[type].base = ptr;
-
 	if (execmem_is_rox(execmem_type)) {
-		ptr = vzalloc(size);
+		int err = execmem_make_temp_rw(ptr, size);
 
-		if (!ptr) {
-			execmem_free(mod->mem[type].base);
+		if (err) {
+			execmem_free(ptr);
 			return -ENOMEM;
 		}
 
-		mod->mem[type].rw_copy = ptr;
 		mod->mem[type].is_rox = true;
-	} else {
-		mod->mem[type].rw_copy = mod->mem[type].base;
-		memset(mod->mem[type].base, 0, size);
 	}
 
 	/*
@@ -1278,18 +1260,29 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	 * *do* eventually get freed, but let's just keep things simple
 	 * and avoid *any* false positives.
 	 */
-	kmemleak_not_leak(ptr);
+	if (!mod->mem[type].is_rox)
+		kmemleak_not_leak(ptr);
+
+	memset(ptr, 0, size);
+	mod->mem[type].base = ptr;
 
 	return 0;
 }
 
+static void module_memory_restore_rox(struct module *mod)
+{
+	for_class_mod_mem_type(type, text) {
+		struct module_memory *mem = &mod->mem[type];
+
+		if (mem->is_rox)
+			execmem_restore_rox(mem->base, mem->size);
+	}
+}
+
 static void module_memory_free(struct module *mod, enum mod_mem_type type)
 {
 	struct module_memory *mem = &mod->mem[type];
 
-	if (mem->is_rox)
-		vfree(mem->rw_copy);
-
 	execmem_free(mem->base);
 }
 
@@ -2642,7 +2635,6 @@ static int move_module(struct module *mod, struct load_info *info)
 	for_each_mod_mem_type(type) {
 		if (!mod->mem[type].size) {
 			mod->mem[type].base = NULL;
-			mod->mem[type].rw_copy = NULL;
 			continue;
 		}
 
@@ -2659,7 +2651,6 @@ static int move_module(struct module *mod, struct load_info *info)
 		void *dest;
 		Elf_Shdr *shdr = &info->sechdrs[i];
 		const char *sname;
-		unsigned long addr;
 
 		if (!(shdr->sh_flags & SHF_ALLOC))
 			continue;
@@ -2680,14 +2671,12 @@ static int move_module(struct module *mod, struct load_info *info)
 				ret = PTR_ERR(dest);
 				goto out_err;
 			}
-			addr = (unsigned long)dest;
 			codetag_section_found = true;
 		} else {
 			enum mod_mem_type type = shdr->sh_entsize >> SH_ENTSIZE_TYPE_SHIFT;
 			unsigned long offset = shdr->sh_entsize & SH_ENTSIZE_OFFSET_MASK;
 
-			addr = (unsigned long)mod->mem[type].base + offset;
-			dest = mod->mem[type].rw_copy + offset;
+			dest = mod->mem[type].base + offset;
 		}
 
 		if (shdr->sh_type != SHT_NOBITS) {
@@ -2710,13 +2699,14 @@ static int move_module(struct module *mod, struct load_info *info)
 		 * users of info can keep taking advantage and using the newly
 		 * minted official memory area.
 		 */
-		shdr->sh_addr = addr;
+		shdr->sh_addr = (unsigned long)dest;
 		pr_debug("\t0x%lx 0x%.8lx %s\n", (long)shdr->sh_addr,
 			 (long)shdr->sh_size, info->secstrings + shdr->sh_name);
 	}
 
 	return 0;
 out_err:
+	module_memory_restore_rox(mod);
 	for (t--; t >= 0; t--)
 		module_memory_free(mod, t);
 	if (codetag_section_found)
@@ -2863,17 +2853,8 @@ int __weak module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
-int __weak module_post_finalize(const Elf_Ehdr *hdr,
-				const Elf_Shdr *sechdrs,
-				struct module *me)
-{
-	return 0;
-}
-
 static int post_relocation(struct module *mod, const struct load_info *info)
 {
-	int ret;
-
 	/* Sort exception table now relocations are done. */
 	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
@@ -2885,24 +2866,7 @@ static int post_relocation(struct module *mod, const struct load_info *info)
 	add_kallsyms(mod, info);
 
 	/* Arch-specific module finalizing. */
-	ret = module_finalize(info->hdr, info->sechdrs, mod);
-	if (ret)
-		return ret;
-
-	for_each_mod_mem_type(type) {
-		struct module_memory *mem = &mod->mem[type];
-
-		if (mem->is_rox) {
-			if (!execmem_update_copy(mem->base, mem->rw_copy,
-						 mem->size))
-				return -ENOMEM;
-
-			vfree(mem->rw_copy);
-			mem->rw_copy = NULL;
-		}
-	}
-
-	return module_post_finalize(info->hdr, info->sechdrs, mod);
+	return module_finalize(info->hdr, info->sechdrs, mod);
 }
 
 /* Call module constructors. */
@@ -3499,6 +3463,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 				       mod->mem[type].size);
 	}
 
+	module_memory_restore_rox(mod);
 	module_deallocate(mod, info);
  free_copy:
 	/*
diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c
index 74834ba15615..03f4142cfbf4 100644
--- a/kernel/module/strict_rwx.c
+++ b/kernel/module/strict_rwx.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/set_memory.h>
+#include <linux/execmem.h>
 #include "internal.h"
 
 static int module_set_memory(const struct module *mod, enum mod_mem_type type,
@@ -32,12 +33,12 @@ static int module_set_memory(const struct module *mod, enum mod_mem_type type,
 int module_enable_text_rox(const struct module *mod)
 {
 	for_class_mod_mem_type(type, text) {
+		const struct module_memory *mem = &mod->mem[type];
 		int ret;
 
-		if (mod->mem[type].is_rox)
-			continue;
-
-		if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		if (mem->is_rox)
+			ret = execmem_restore_rox(mem->base, mem->size);
+		else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
 			ret = module_set_memory(mod, type, set_memory_rox);
 		else
 			ret = module_set_memory(mod, type, set_memory_x);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4484cdb504c7..4ebe6136b08d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1824,16 +1824,6 @@ static const struct ctl_table kern_table[] = {
 		.mode		= 0444,
 		.proc_handler	= proc_dointvec,
 	},
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
-	{
-		.procname       = "unknown_nmi_panic",
-		.data           = &unknown_nmi_panic,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
-		.proc_handler   = proc_dointvec,
-	},
-#endif
-
 #if (defined(CONFIG_X86_32) || defined(CONFIG_PARISC)) && \
 	defined(CONFIG_DEBUG_STACKOVERFLOW)
 	{
@@ -1844,43 +1834,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#if defined(CONFIG_X86)
-	{
-		.procname	= "panic_on_unrecovered_nmi",
-		.data		= &panic_on_unrecovered_nmi,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "panic_on_io_nmi",
-		.data		= &panic_on_io_nmi,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "bootloader_type",
-		.data		= &bootloader_type,
-		.maxlen		= sizeof (int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "bootloader_version",
-		.data		= &bootloader_version,
-		.maxlen		= sizeof (int),
-		.mode		= 0444,
-		.proc_handler	= proc_dointvec,
-	},
-	{
-		.procname	= "io_delay_type",
-		.data		= &io_delay_type,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #if defined(CONFIG_MMU)
 	{
 		.procname	= "randomize_va_space",
@@ -1899,15 +1852,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#if	defined(CONFIG_ACPI_SLEEP) && defined(CONFIG_X86)
-	{
-		.procname	= "acpi_video_flags",
-		.data		= &acpi_realmode_flags,
-		.maxlen		= sizeof (unsigned long),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax,
-	},
-#endif
 #ifdef CONFIG_SYSCTL_ARCH_UNALIGN_NO_WARN
 	{
 		.procname	= "ignore-unaligned-usertrap",
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index adc947587eb8..997fb2a47c92 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1038,27 +1038,14 @@ static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
-#ifdef CONFIG_X86_KERNEL_IBT
-static unsigned long get_entry_ip(unsigned long fentry_ip)
+static inline unsigned long get_entry_ip(unsigned long fentry_ip)
 {
-	u32 instr;
-
-	/* We want to be extra safe in case entry ip is on the page edge,
-	 * but otherwise we need to avoid get_kernel_nofault()'s overhead.
-	 */
-	if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
-		if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
-			return fentry_ip;
-	} else {
-		instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
-	}
-	if (is_endbr(instr))
+#ifdef CONFIG_X86_KERNEL_IBT
+	if (is_endbr((void *)(fentry_ip - ENDBR_INSN_SIZE)))
 		fentry_ip -= ENDBR_INSN_SIZE;
+#endif
 	return fentry_ip;
 }
-#else
-#define get_entry_ip(fentry_ip) fentry_ip
-#endif
 
 BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
 {
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 759ea1783cc5..d726068358c7 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -254,7 +254,7 @@ static __init int test_atomics_init(void)
 	pr_info("passed for %s platform %s CX8 and %s SSE\n",
 #ifdef CONFIG_X86_64
 		"x86-64",
-#elif defined(CONFIG_X86_CMPXCHG64)
+#elif defined(CONFIG_X86_CX8)
 		"i586+",
 #else
 		"i386+",
diff --git a/lib/zstd/common/portability_macros.h b/lib/zstd/common/portability_macros.h
index 0e3b2c0a527d..0dde8bf56595 100644
--- a/lib/zstd/common/portability_macros.h
+++ b/lib/zstd/common/portability_macros.h
@@ -55,7 +55,7 @@
 #ifndef DYNAMIC_BMI2
   #if ((defined(__clang__) && __has_attribute(__target__)) \
       || (defined(__GNUC__) \
-          && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
+          && (__GNUC__ >= 11))) \
       && (defined(__x86_64__) || defined(_M_X64)) \
       && !defined(__BMI2__)
   #  define DYNAMIC_BMI2 1
diff --git a/mm/execmem.c b/mm/execmem.c
index 317b6a8d35be..e6c4f5076ca8 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -257,7 +257,6 @@ out_unlock:
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
-	unsigned long start, end;
 	struct vm_struct *vm;
 	size_t alloc_size;
 	int err = -ENOMEM;
@@ -275,26 +274,18 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	start = (unsigned long)p;
-	end = start + alloc_size;
-
-	vunmap_range(start, end);
-
-	err = execmem_set_direct_map_valid(vm, false);
-	if (err)
-		goto err_free_mem;
-
-	err = vmap_pages_range_noflush(start, end, range->pgprot, vm->pages,
-				       PMD_SHIFT);
+	err = set_memory_rox((unsigned long)p, vm->nr_pages);
 	if (err)
 		goto err_free_mem;
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)
-		goto err_free_mem;
+		goto err_reset_direct_map;
 
 	return 0;
 
+err_reset_direct_map:
+	execmem_set_direct_map_valid(vm, true);
 err_free_mem:
 	vfree(p);
 	return err;
@@ -344,6 +335,28 @@ static bool execmem_cache_free(void *ptr)
 
 	return true;
 }
+
+int execmem_make_temp_rw(void *ptr, size_t size)
+{
+	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)ptr;
+	int ret;
+
+	ret = set_memory_nx(addr, nr);
+	if (ret)
+		return ret;
+
+	return set_memory_rw(addr, nr);
+}
+
+int execmem_restore_rox(void *ptr, size_t size)
+{
+	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)ptr;
+
+	return set_memory_rox(addr, nr);
+}
+
 #else /* CONFIG_ARCH_HAS_EXECMEM_ROX */
 static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
 {
diff --git a/mm/percpu.c b/mm/percpu.c
index ac61e3fc5f15..7b5835356d1e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3071,7 +3071,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 				continue;
 			}
 			/* copy and return the unused part */
-			memcpy(ptr, __per_cpu_load, ai->static_size);
+			memcpy(ptr, __per_cpu_start, ai->static_size);
 			pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
 		}
 	}
@@ -3240,7 +3240,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
-		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
+		memcpy((void *)unit_addr, __per_cpu_start, ai->static_size);
 	}
 
 	/* we're ready, commit */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 16bfe1c694dd..88998725f1c5 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1435,6 +1435,8 @@ const char * const vmstat_text[] = {
 #ifdef CONFIG_X86
 	"direct_map_level2_splits",
 	"direct_map_level3_splits",
+	"direct_map_level2_collapses",
+	"direct_map_level3_collapses",
 #endif
 #ifdef CONFIG_PER_VMA_LOCK_STATS
 	"vma_lock_success",
diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh
deleted file mode 100755
index 9459ca4f0f11..000000000000
--- a/scripts/gcc-x86_32-has-stack-protector.sh
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-# This requires GCC 8.1 or better.  Specifically, we require
-# -mstack-protector-guard-reg, added by
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
deleted file mode 100755
index f680bb01aeeb..000000000000
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ /dev/null
@@ -1,4 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py
index 13eb8b3901b8..8f7c4fb78c2c 100644
--- a/scripts/gdb/linux/cpus.py
+++ b/scripts/gdb/linux/cpus.py
@@ -164,7 +164,7 @@ def get_current_task(cpu):
             var_ptr = gdb.parse_and_eval("(struct task_struct *)cpu_tasks[0].task")
             return var_ptr.dereference()
         else:
-            var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task")
+            var_ptr = gdb.parse_and_eval("&current_task")
             return per_cpu(var_ptr, cpu).dereference()
     elif utils.is_target_arch("aarch64"):
         current_task_addr = gdb.parse_and_eval("(unsigned long)$SP_EL0")
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 03852da3d249..4b0234e4b12f 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -5,7 +5,7 @@
  * This software may be used and distributed according to the terms
  * of the GNU General Public License, incorporated herein by reference.
  *
- * Usage: kallsyms [--all-symbols] [--absolute-percpu]  in.map > out.S
+ * Usage: kallsyms [--all-symbols] in.map > out.S
  *
  *      Table compression uses all the unused char codes on the symbols and
  *  maps these to the most used substrings (tokens). For instance, it might
@@ -37,7 +37,6 @@ struct sym_entry {
 	unsigned long long addr;
 	unsigned int len;
 	unsigned int seq;
-	bool percpu_absolute;
 	unsigned char sym[];
 };
 
@@ -55,14 +54,9 @@ static struct addr_range text_ranges[] = {
 #define text_range_text     (&text_ranges[0])
 #define text_range_inittext (&text_ranges[1])
 
-static struct addr_range percpu_range = {
-	"__per_cpu_start", "__per_cpu_end", -1ULL, 0
-};
-
 static struct sym_entry **table;
 static unsigned int table_size, table_cnt;
 static int all_symbols;
-static int absolute_percpu;
 
 static int token_profit[0x10000];
 
@@ -73,7 +67,7 @@ static unsigned char best_table_len[256];
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n");
+	fprintf(stderr, "Usage: kallsyms [--all-symbols] in.map > out.S\n");
 	exit(1);
 }
 
@@ -164,7 +158,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 		return NULL;
 
 	check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges));
-	check_symbol_range(name, addr, &percpu_range, 1);
 
 	/* include the type field in the symbol name, so that it gets
 	 * compressed together */
@@ -175,7 +168,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
 	sym->len = len;
 	sym->sym[0] = type;
 	strcpy(sym_name(sym), name);
-	sym->percpu_absolute = false;
 
 	return sym;
 }
@@ -319,11 +311,6 @@ static int expand_symbol(const unsigned char *data, int len, char *result)
 	return total;
 }
 
-static bool symbol_absolute(const struct sym_entry *s)
-{
-	return s->percpu_absolute;
-}
-
 static int compare_names(const void *a, const void *b)
 {
 	int ret;
@@ -455,22 +442,11 @@ static void write_src(void)
 		 */
 
 		long long offset;
-		bool overflow;
-
-		if (!absolute_percpu) {
-			offset = table[i]->addr - relative_base;
-			overflow = offset < 0 || offset > UINT_MAX;
-		} else if (symbol_absolute(table[i])) {
-			offset = table[i]->addr;
-			overflow = offset < 0 || offset > INT_MAX;
-		} else {
-			offset = relative_base - table[i]->addr - 1;
-			overflow = offset < INT_MIN || offset >= 0;
-		}
-		if (overflow) {
+
+		offset = table[i]->addr - relative_base;
+		if (offset < 0 || offset > UINT_MAX) {
 			fprintf(stderr, "kallsyms failure: "
-				"%s symbol value %#llx out of range in relative mode\n",
-				symbol_absolute(table[i]) ? "absolute" : "relative",
+				"relative symbol value %#llx out of range\n",
 				table[i]->addr);
 			exit(EXIT_FAILURE);
 		}
@@ -725,36 +701,15 @@ static void sort_symbols(void)
 	qsort(table, table_cnt, sizeof(table[0]), compare_symbols);
 }
 
-static void make_percpus_absolute(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < table_cnt; i++)
-		if (symbol_in_range(table[i], &percpu_range, 1)) {
-			/*
-			 * Keep the 'A' override for percpu symbols to
-			 * ensure consistent behavior compared to older
-			 * versions of this tool.
-			 */
-			table[i]->sym[0] = 'A';
-			table[i]->percpu_absolute = true;
-		}
-}
-
 /* find the minimum non-absolute symbol address */
 static void record_relative_base(void)
 {
-	unsigned int i;
-
-	for (i = 0; i < table_cnt; i++)
-		if (!symbol_absolute(table[i])) {
-			/*
-			 * The table is sorted by address.
-			 * Take the first non-absolute symbol value.
-			 */
-			relative_base = table[i]->addr;
-			return;
-		}
+	/*
+	 * The table is sorted by address.
+	 * Take the first symbol value.
+	 */
+	if (table_cnt)
+		relative_base = table[0]->addr;
 }
 
 int main(int argc, char **argv)
@@ -762,7 +717,6 @@ int main(int argc, char **argv)
 	while (1) {
 		static const struct option long_options[] = {
 			{"all-symbols",     no_argument, &all_symbols,     1},
-			{"absolute-percpu", no_argument, &absolute_percpu, 1},
 			{},
 		};
 
@@ -779,8 +733,6 @@ int main(int argc, char **argv)
 
 	read_map(argv[optind]);
 	shrink_table();
-	if (absolute_percpu)
-		make_percpus_absolute();
 	sort_symbols();
 	record_relative_base();
 	optimize_token_table();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 56a077d204cf..67e66333bd2a 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -144,10 +144,6 @@ kallsyms()
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi
 
-	if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then
-		kallsymopt="${kallsymopt} --absolute-percpu"
-	fi
-
 	info KSYMS "${2}.S"
 	scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
 
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 91c91201212c..787868183b84 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -19,12 +19,14 @@ binutils)
 gcc)
 	if [ "$ARCH" = parisc64 ]; then
 		echo 12.0.0
+	elif [ "$SRCARCH" = x86 ]; then
+		echo 8.1.0
 	else
 		echo 5.1.0
 	fi
 	;;
 llvm)
-	if [ "$SRCARCH" = s390 ]; then
+	if [ "$SRCARCH" = s390 -o "$SRCARCH" = x86 ]; then
 		echo 15.0.0
 	elif [ "$SRCARCH" = loongarch ]; then
 		echo 18.0.0
diff --git a/tools/arch/x86/include/asm/asm.h b/tools/arch/x86/include/asm/asm.h
index 3ad3da9a7d97..dbe39b44256b 100644
--- a/tools/arch/x86/include/asm/asm.h
+++ b/tools/arch/x86/include/asm/asm.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ASM_H
 #define _ASM_X86_ASM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 # define __ASM_FORM(x, ...)		x,## __VA_ARGS__
 # define __ASM_FORM_RAW(x, ...)		x,## __VA_ARGS__
 # define __ASM_FORM_COMMA(x, ...)	x,## __VA_ARGS__,
@@ -123,7 +123,7 @@
 #ifdef __KERNEL__
 
 /* Exception table entry */
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	.pushsection "__ex_table","a" ;				\
 	.balign 4 ;						\
@@ -154,7 +154,7 @@
 #  define _ASM_NOKPROBE(entry)
 # endif
 
-#else /* ! __ASSEMBLY__ */
+#else /* ! __ASSEMBLER__ */
 # define _EXPAND_EXTABLE_HANDLE(x) #x
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
@@ -186,7 +186,7 @@
  */
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __KERNEL__ */
 
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 17b6590748c0..c691481d59ce 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -2,14 +2,6 @@
 #ifndef _ASM_X86_CPUFEATURES_H
 #define _ASM_X86_CPUFEATURES_H
 
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#include <asm/required-features.h>
-#endif
-
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#include <asm/disabled-features.h>
-#endif
-
 /*
  * Defines x86 CPU feature bits
  */
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
deleted file mode 100644
index c492bdc97b05..000000000000
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ /dev/null
@@ -1,161 +0,0 @@
-#ifndef _ASM_X86_DISABLED_FEATURES_H
-#define _ASM_X86_DISABLED_FEATURES_H
-
-/* These features, although they might be available in a CPU
- * will not be used because the compile options to support
- * them are not present.
- *
- * This code allows them to be checked and disabled at
- * compile time without an explicit #ifdef.  Use
- * cpu_feature_enabled().
- */
-
-#ifdef CONFIG_X86_UMIP
-# define DISABLE_UMIP	0
-#else
-# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
-#endif
-
-#ifdef CONFIG_X86_64
-# define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
-# define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
-# define DISABLE_CYRIX_ARR	(1<<(X86_FEATURE_CYRIX_ARR & 31))
-# define DISABLE_CENTAUR_MCR	(1<<(X86_FEATURE_CENTAUR_MCR & 31))
-# define DISABLE_PCID		0
-#else
-# define DISABLE_VME		0
-# define DISABLE_K6_MTRR	0
-# define DISABLE_CYRIX_ARR	0
-# define DISABLE_CENTAUR_MCR	0
-# define DISABLE_PCID		(1<<(X86_FEATURE_PCID & 31))
-#endif /* CONFIG_X86_64 */
-
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-# define DISABLE_PKU		0
-# define DISABLE_OSPKE		0
-#else
-# define DISABLE_PKU		(1<<(X86_FEATURE_PKU & 31))
-# define DISABLE_OSPKE		(1<<(X86_FEATURE_OSPKE & 31))
-#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
-
-#ifdef CONFIG_X86_5LEVEL
-# define DISABLE_LA57	0
-#else
-# define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
-# define DISABLE_PTI		0
-#else
-# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETPOLINE
-# define DISABLE_RETPOLINE	0
-#else
-# define DISABLE_RETPOLINE	((1 << (X86_FEATURE_RETPOLINE & 31)) | \
-				 (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31)))
-#endif
-
-#ifdef CONFIG_MITIGATION_RETHUNK
-# define DISABLE_RETHUNK	0
-#else
-# define DISABLE_RETHUNK	(1 << (X86_FEATURE_RETHUNK & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_UNRET_ENTRY
-# define DISABLE_UNRET		0
-#else
-# define DISABLE_UNRET		(1 << (X86_FEATURE_UNRET & 31))
-#endif
-
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-# define DISABLE_CALL_DEPTH_TRACKING	0
-#else
-# define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
-#endif
-
-#ifdef CONFIG_ADDRESS_MASKING
-# define DISABLE_LAM		0
-#else
-# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
-#endif
-
-#ifdef CONFIG_INTEL_IOMMU_SVM
-# define DISABLE_ENQCMD		0
-#else
-# define DISABLE_ENQCMD		(1 << (X86_FEATURE_ENQCMD & 31))
-#endif
-
-#ifdef CONFIG_X86_SGX
-# define DISABLE_SGX	0
-#else
-# define DISABLE_SGX	(1 << (X86_FEATURE_SGX & 31))
-#endif
-
-#ifdef CONFIG_XEN_PV
-# define DISABLE_XENPV		0
-#else
-# define DISABLE_XENPV		(1 << (X86_FEATURE_XENPV & 31))
-#endif
-
-#ifdef CONFIG_INTEL_TDX_GUEST
-# define DISABLE_TDX_GUEST	0
-#else
-# define DISABLE_TDX_GUEST	(1 << (X86_FEATURE_TDX_GUEST & 31))
-#endif
-
-#ifdef CONFIG_X86_USER_SHADOW_STACK
-#define DISABLE_USER_SHSTK	0
-#else
-#define DISABLE_USER_SHSTK	(1 << (X86_FEATURE_USER_SHSTK & 31))
-#endif
-
-#ifdef CONFIG_X86_KERNEL_IBT
-#define DISABLE_IBT	0
-#else
-#define DISABLE_IBT	(1 << (X86_FEATURE_IBT & 31))
-#endif
-
-#ifdef CONFIG_X86_FRED
-# define DISABLE_FRED	0
-#else
-# define DISABLE_FRED	(1 << (X86_FEATURE_FRED & 31))
-#endif
-
-#ifdef CONFIG_KVM_AMD_SEV
-#define DISABLE_SEV_SNP		0
-#else
-#define DISABLE_SEV_SNP		(1 << (X86_FEATURE_SEV_SNP & 31))
-#endif
-
-/*
- * Make sure to add features to the correct mask
- */
-#define DISABLED_MASK0	(DISABLE_VME)
-#define DISABLED_MASK1	0
-#define DISABLED_MASK2	0
-#define DISABLED_MASK3	(DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4	(DISABLE_PCID)
-#define DISABLED_MASK5	0
-#define DISABLED_MASK6	0
-#define DISABLED_MASK7	(DISABLE_PTI)
-#define DISABLED_MASK8	(DISABLE_XENPV|DISABLE_TDX_GUEST)
-#define DISABLED_MASK9	(DISABLE_SGX)
-#define DISABLED_MASK10	0
-#define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
-			 DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK)
-#define DISABLED_MASK12	(DISABLE_FRED|DISABLE_LAM)
-#define DISABLED_MASK13	0
-#define DISABLED_MASK14	0
-#define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
-			 DISABLE_ENQCMD)
-#define DISABLED_MASK17	0
-#define DISABLED_MASK18	(DISABLE_IBT)
-#define DISABLED_MASK19	(DISABLE_SEV_SNP)
-#define DISABLED_MASK20	0
-#define DISABLED_MASK21	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 3ae84c3b8e6d..dc1c1057f26e 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -25,6 +25,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_TCE		15 /* Enable Translation Cache Extensions */
 #define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
@@ -34,6 +35,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_TCE		(1<<_EFER_TCE)
 #define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /*
diff --git a/tools/arch/x86/include/asm/nops.h b/tools/arch/x86/include/asm/nops.h
index 1c1b7550fa55..cd94221d8335 100644
--- a/tools/arch/x86/include/asm/nops.h
+++ b/tools/arch/x86/include/asm/nops.h
@@ -82,7 +82,7 @@
 #define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
 #define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 extern const unsigned char * const x86_nops[];
 #endif
 
diff --git a/tools/arch/x86/include/asm/orc_types.h b/tools/arch/x86/include/asm/orc_types.h
index 46d7e06763c9..e0125afa53fb 100644
--- a/tools/arch/x86/include/asm/orc_types.h
+++ b/tools/arch/x86/include/asm/orc_types.h
@@ -45,7 +45,7 @@
 #define ORC_TYPE_REGS			3
 #define ORC_TYPE_REGS_PARTIAL		4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/byteorder.h>
 
 /*
@@ -73,6 +73,6 @@ struct orc_entry {
 #endif
 } __packed;
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ORC_TYPES_H */
diff --git a/tools/arch/x86/include/asm/pvclock-abi.h b/tools/arch/x86/include/asm/pvclock-abi.h
index 1436226efe3e..b9fece5fc96d 100644
--- a/tools/arch/x86/include/asm/pvclock-abi.h
+++ b/tools/arch/x86/include/asm/pvclock-abi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_X86_PVCLOCK_ABI_H
 #define _ASM_X86_PVCLOCK_ABI_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /*
  * These structs MUST NOT be changed.
@@ -44,5 +44,5 @@ struct pvclock_wall_clock {
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
 /* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
 #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h
deleted file mode 100644
index e9187ddd3d1f..000000000000
--- a/tools/arch/x86/include/asm/required-features.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef _ASM_X86_REQUIRED_FEATURES_H
-#define _ASM_X86_REQUIRED_FEATURES_H
-
-/* Define minimum CPUID feature set for kernel These bits are checked
-   really early to actually display a visible error message before the
-   kernel dies.  Make sure to assign features to the proper mask!
-
-   Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
-
-   The real information is in arch/x86/Kconfig.cpu, this just converts
-   the CONFIGs into a bitmask */
-
-#ifndef CONFIG_MATH_EMULATION
-# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
-#else
-# define NEED_FPU	0
-#endif
-
-#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-#else
-# define NEED_PAE	0
-#endif
-
-#ifdef CONFIG_X86_CMPXCHG64
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
-#else
-# define NEED_CX8	0
-#endif
-
-#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
-# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
-#else
-# define NEED_CMOV	0
-#endif
-
-# define NEED_3DNOW	0
-
-#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
-# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
-#else
-# define NEED_NOPL	0
-#endif
-
-#ifdef CONFIG_MATOM
-# define NEED_MOVBE	(1<<(X86_FEATURE_MOVBE & 31))
-#else
-# define NEED_MOVBE	0
-#endif
-
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
-/* Paravirtualized systems may not have PSE or PGE available */
-#define NEED_PSE	0
-#define NEED_PGE	0
-#else
-#define NEED_PSE	(1<<(X86_FEATURE_PSE) & 31)
-#define NEED_PGE	(1<<(X86_FEATURE_PGE) & 31)
-#endif
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
-#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
-#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
-#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
-#else
-#define NEED_PSE	0
-#define NEED_MSR	0
-#define NEED_PGE	0
-#define NEED_FXSR	0
-#define NEED_XMM	0
-#define NEED_XMM2	0
-#define NEED_LM		0
-#endif
-
-#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
-			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
-			 NEED_XMM|NEED_XMM2)
-#define SSE_MASK	(NEED_XMM|NEED_XMM2)
-
-#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
-
-#define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	(NEED_MOVBE)
-#define REQUIRED_MASK5	0
-#define REQUIRED_MASK6	0
-#define REQUIRED_MASK7	0
-#define REQUIRED_MASK8	0
-#define REQUIRED_MASK9	0
-#define REQUIRED_MASK10	0
-#define REQUIRED_MASK11	0
-#define REQUIRED_MASK12	0
-#define REQUIRED_MASK13	0
-#define REQUIRED_MASK14	0
-#define REQUIRED_MASK15	0
-#define REQUIRED_MASK16	0
-#define REQUIRED_MASK17	0
-#define REQUIRED_MASK18	0
-#define REQUIRED_MASK19	0
-#define REQUIRED_MASK20	0
-#define REQUIRED_MASK21	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
-
-#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index fb9691a34d92..7567c893f45e 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -850,6 +850,7 @@ bool arch_is_rethunk(struct symbol *sym)
 bool arch_is_embedded_insn(struct symbol *sym)
 {
 	return !strcmp(sym->name, "retbleed_return_thunk") ||
+	       !strcmp(sym->name, "srso_alias_safe_ret") ||
 	       !strcmp(sym->name, "srso_safe_ret");
 }
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 48d7bc5b4736..ca3435acc326 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1284,15 +1284,6 @@ static void annotate_call_site(struct objtool_file *file,
 	if (!sym)
 		sym = reloc->sym;
 
-	/*
-	 * Alternative replacement code is just template code which is
-	 * sometimes copied to the original instruction. For now, don't
-	 * annotate it. (In the future we might consider annotating the
-	 * original instruction if/when it ever makes sense to do so.)
-	 */
-	if (!strcmp(insn->sec->name, ".altinstr_replacement"))
-		return;
-
 	if (sym->static_call_tramp) {
 		list_add_tail(&insn->call_node, &file->static_call_list);
 		return;
@@ -1350,7 +1341,8 @@ static void annotate_call_site(struct objtool_file *file,
 		return;
 	}
 
-	if (insn->type == INSN_CALL && !insn->sec->init)
+	if (insn->type == INSN_CALL && !insn->sec->init &&
+	    !insn->_call_dest->embedded_insn)
 		list_add_tail(&insn->call_node, &file->call_list);
 
 	if (!sibling && dead_end_function(file, sym))
diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index 6bb7edda3094..eacfe3b0a8d1 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -16,6 +16,7 @@ NORETURN(__tdx_hypercall_failed)
 NORETURN(__ubsan_handle_builtin_unreachable)
 NORETURN(__x64_sys_exit)
 NORETURN(__x64_sys_exit_group)
+NORETURN(acpi_processor_ffh_play_dead)
 NORETURN(arch_cpu_idle_dead)
 NORETURN(bch2_trans_in_restart_error)
 NORETURN(bch2_trans_restart_error)
@@ -34,6 +35,7 @@ NORETURN(kunit_try_catch_throw)
 NORETURN(machine_real_restart)
 NORETURN(make_task_dead)
 NORETURN(mpt_halt_firmware)
+NORETURN(mwait_play_dead)
 NORETURN(nmi_panic_self_stop)
 NORETURN(panic)
 NORETURN(panic_smp_self_stop)
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index d3c6e10dce73..a4499e5a6f9c 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -26,8 +26,6 @@ FILES=(
   "include/linux/hash.h"
   "include/linux/list-sort.h"
   "include/uapi/linux/hw_breakpoint.h"
-  "arch/x86/include/asm/disabled-features.h"
-  "arch/x86/include/asm/required-features.h"
   "arch/x86/include/asm/cpufeatures.h"
   "arch/x86/include/asm/inat_types.h"
   "arch/x86/include/asm/emulate_prefix.h"
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 8d5011a0bf60..26057af6b5a1 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -1056,7 +1056,7 @@ static const struct platform_data turbostat_pdata[] = {
 	 * Missing support for
 	 * INTEL_ICELAKE
 	 * INTEL_ATOM_SILVERMONT_MID
-	 * INTEL_ATOM_AIRMONT_MID
+	 * INTEL_ATOM_SILVERMONT_MID2
 	 * INTEL_ATOM_AIRMONT_NP
 	 */
 	{ 0, NULL },
diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index 4d4a76532dc9..18d736640ece 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -4,6 +4,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/syscall.h>
+#include <sys/ioctl.h>
 #include <time.h>
 #include <signal.h>
 #include <setjmp.h>
@@ -43,7 +44,15 @@
 #define FUNC_INHERITE           0x20
 #define FUNC_PASID              0x40
 
+/* get_user() pointer test cases */
+#define GET_USER_USER           0
+#define GET_USER_KERNEL_TOP     1
+#define GET_USER_KERNEL_BOT     2
+#define GET_USER_KERNEL         3
+
 #define TEST_MASK               0x7f
+#define L5_SIGN_EXT_MASK        (0xFFUL << 56)
+#define L4_SIGN_EXT_MASK        (0x1FFFFUL << 47)
 
 #define LOW_ADDR                (0x1UL << 30)
 #define HIGH_ADDR               (0x3UL << 48)
@@ -115,23 +124,42 @@ static void segv_handler(int sig)
 	siglongjmp(segv_env, 1);
 }
 
-static inline int cpu_has_lam(void)
+static inline int lam_is_available(void)
 {
 	unsigned int cpuinfo[4];
+	unsigned long bits = 0;
+	int ret;
 
 	__cpuid_count(0x7, 1, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]);
 
-	return (cpuinfo[0] & (1 << 26));
+	/* Check if cpu supports LAM */
+	if (!(cpuinfo[0] & (1 << 26))) {
+		ksft_print_msg("LAM is not supported!\n");
+		return 0;
+	}
+
+	/* Return 0 if CONFIG_ADDRESS_MASKING is not set */
+	ret = syscall(SYS_arch_prctl, ARCH_GET_MAX_TAG_BITS, &bits);
+	if (ret) {
+		ksft_print_msg("LAM is disabled in the kernel!\n");
+		return 0;
+	}
+
+	return 1;
 }
 
-/* Check 5-level page table feature in CPUID.(EAX=07H, ECX=00H):ECX.[bit 16] */
-static inline int cpu_has_la57(void)
+static inline int la57_enabled(void)
 {
-	unsigned int cpuinfo[4];
+	int ret;
+	void *p;
+
+	p = mmap((void *)HIGH_ADDR, PAGE_SIZE, PROT_READ | PROT_WRITE,
+		 MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
 
-	__cpuid_count(0x7, 0, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]);
+	ret = p == MAP_FAILED ? 0 : 1;
 
-	return (cpuinfo[2] & (1 << 16));
+	munmap(p, PAGE_SIZE);
+	return ret;
 }
 
 /*
@@ -322,7 +350,7 @@ static int handle_mmap(struct testcases *test)
 		   flags, -1, 0);
 	if (ptr == MAP_FAILED) {
 		if (test->addr == HIGH_ADDR)
-			if (!cpu_has_la57())
+			if (!la57_enabled())
 				return 3; /* unsupport LA57 */
 		return 1;
 	}
@@ -370,6 +398,78 @@ static int handle_syscall(struct testcases *test)
 	return ret;
 }
 
+static int get_user_syscall(struct testcases *test)
+{
+	uint64_t ptr_address, bitmask;
+	int fd, ret = 0;
+	void *ptr;
+
+	if (la57_enabled()) {
+		bitmask = L5_SIGN_EXT_MASK;
+		ptr_address = HIGH_ADDR;
+	} else {
+		bitmask = L4_SIGN_EXT_MASK;
+		ptr_address = LOW_ADDR;
+	}
+
+	ptr = mmap((void *)ptr_address, PAGE_SIZE, PROT_READ | PROT_WRITE,
+		   MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+
+	if (ptr == MAP_FAILED) {
+		perror("failed to map byte to pass into get_user");
+		return 1;
+	}
+
+	if (set_lam(test->lam) != 0) {
+		ret = 2;
+		goto error;
+	}
+
+	fd = memfd_create("lam_ioctl", 0);
+	if (fd == -1) {
+		munmap(ptr, PAGE_SIZE);
+		exit(EXIT_FAILURE);
+	}
+
+	switch (test->later) {
+	case GET_USER_USER:
+		/* Control group - properly tagged user pointer */
+		ptr = (void *)set_metadata((uint64_t)ptr, test->lam);
+		break;
+	case GET_USER_KERNEL_TOP:
+		/* Kernel address with top bit cleared */
+		bitmask &= (bitmask >> 1);
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	case GET_USER_KERNEL_BOT:
+		/* Kernel address with bottom sign-extension bit cleared */
+		bitmask &= (bitmask << 1);
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	case GET_USER_KERNEL:
+		/* Try to pass a kernel address */
+		ptr = (void *)((uint64_t)ptr | bitmask);
+		break;
+	default:
+		printf("Invalid test case value passed!\n");
+		break;
+	}
+
+	/*
+	 * Use FIOASYNC ioctl because it utilizes get_user() internally and is
+	 * very non-invasive to the system. Pass differently tagged pointers to
+	 * get_user() in order to verify that valid user pointers are going
+	 * through and invalid kernel/non-canonical pointers are not.
+	 */
+	if (ioctl(fd, FIOASYNC, ptr) != 0)
+		ret = 1;
+
+	close(fd);
+error:
+	munmap(ptr, PAGE_SIZE);
+	return ret;
+}
+
 int sys_uring_setup(unsigned int entries, struct io_uring_params *p)
 {
 	return (int)syscall(__NR_io_uring_setup, entries, p);
@@ -596,8 +696,10 @@ int do_uring(unsigned long lam)
 	fi->file_fd = file_fd;
 
 	ring = malloc(sizeof(*ring));
-	if (!ring)
+	if (!ring) {
+		free(fi);
 		return 1;
+	}
 
 	memset(ring, 0, sizeof(struct io_ring));
 
@@ -883,6 +985,33 @@ static struct testcases syscall_cases[] = {
 		.test_func = handle_syscall,
 		.msg = "SYSCALL:[Negative] Disable LAM. Dereferencing pointer with metadata.\n",
 	},
+	{
+		.later = GET_USER_USER,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER: get_user() and pass a properly tagged user pointer.\n",
+	},
+	{
+		.later = GET_USER_KERNEL_TOP,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() with a kernel pointer and the top bit cleared.\n",
+	},
+	{
+		.later = GET_USER_KERNEL_BOT,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() with a kernel pointer and the bottom sign-extension bit cleared.\n",
+	},
+	{
+		.later = GET_USER_KERNEL,
+		.expected = 1,
+		.lam = LAM_U57_BITS,
+		.test_func = get_user_syscall,
+		.msg = "GET_USER:[Negative] get_user() and pass a kernel pointer.\n",
+	},
 };
 
 static struct testcases mmap_cases[] = {
@@ -1181,10 +1310,8 @@ int main(int argc, char **argv)
 
 	tests_cnt = 0;
 
-	if (!cpu_has_lam()) {
-		ksft_print_msg("Unsupported LAM feature!\n");
+	if (!lam_is_available())
 		return KSFT_SKIP;
-	}
 
 	while ((c = getopt(argc, argv, "ht:")) != -1) {
 		switch (c) {
author	Linus Torvalds <torvalds@linux-foundation.org>	2025-03-24 22:06:11 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2025-03-24 22:06:11 -0700
commit	e34c38057a131d14e47b4acb461564d9f351b9f7 (patch)
tree	b2a2b707c0c97927493cf85c0418594c06c76f19
parent	327ecdbc0fda28da3563a34426f63d80384062be (diff)
parent	1400c87e6cac47eb243f260352c854474d9a9073 (diff)