Merge branch 'x86/asm' into x86/core, to pick up dependent commits

Signed-off-by: Ingo Molnar <[e-mail]>

Documentation/admin-guide/kdump/kdump.rst

···
 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

Documentation/admin-guide/kernel-parameters.txt

···
 			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 }
···
 				 8 - SIGSEGV faults
 				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:

Documentation/arch/x86/usb-legacy-support.rst

···
    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.
···
   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

arch/arm/include/asm/io.h

···
 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
 
 /*

arch/arm/mm/ioremap.c

···
 	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,

arch/arm/mm/nommu.c

···
 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;
 }

arch/riscv/include/asm/io.h

···
 #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
 

arch/x86/Kconfig

···
 	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
···
 	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
···
 	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
···
 	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
···
 	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
···
 	  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
···
 		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.
···
 	  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)"
···
 	  Enable support for the Goldfish virtual platform used primarily
 	  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"
···
 	  Select for the Intel CE media processor (CE4100) SOC.
 	  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"
···
 	  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():
···
 	# On 32-bit SPARSEMEM adds too big of SECTIONS_WIDTH:
 	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"
···
 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
···
 config NR_CPUS_DEFAULT
 	int
 	depends on X86_32
-	default   32 if  X86_BIGSMP
 	default    8 if  SMP
 	default    1 if !SMP
 
···
 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
···
 
 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
···
 	  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
···
 	  possible.
 
 	  If the machine has between 1 and 4 Gigabytes physical RAM, then
-	  answer "4GB" here.
+	  answer "Y" 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.
-
-endchoice
+	  If unsure, say N.
 
 choice
 	prompt "Memory split" if EXPERT
···
 	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
···
 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
···
 
 	  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 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
 
···
 	  they can be used for persistent storage.
 
 	  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"
···
 	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)

arch/x86/Kconfig.cpu

···
 # 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
···
 	  - "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.
···
 	  - "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"
···
 	  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"
···
 		-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"
···
 	  Select this for an AMD Athlon K7-family processor.  Enables use of
 	  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"
···
 	  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_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
 
···
 
 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

arch/x86/Makefile

···
         # temporary until string.h is fixed
         KBUILD_CFLAGS += -ffreestanding
 
-    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
···
 	# 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
 
 #

arch/x86/Makefile_32.cpu

···
 # 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)	+= $(call cc-option,-march=winchip-c6,-march=i586)
···
 cflags-$(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

arch/x86/boot/compressed/misc.c

···
 
 	/*
 	 * 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.
···
 	 * 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
 	 *
···
 		*(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;

arch/x86/configs/xen.config

···
 # 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

arch/x86/entry/entry.S

···
 
 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
···
  */
 #ifdef CONFIG_STACKPROTECTOR
 EXPORT_SYMBOL(__ref_stack_chk_guard);
-#endif
 #endif

arch/x86/entry/entry_64.S

···
 
 #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
 
 	/*

arch/x86/events/intel/core.c

···
 	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)
···
 
 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;
 
 	/*
···
 	 * 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
···
 		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];
 		}
 	}
···
 	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,

arch/x86/events/perf_event.h

···
 #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
···
 	hybrid_big_small	= hybrid_big   | hybrid_small,
 	hybrid_small_tiny	= hybrid_small | hybrid_tiny,
 	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 {
···
 	 */
 	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 {

arch/x86/hyperv/mmu.c

···
 
 	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;
 }

arch/x86/include/asm/alternative.h

···
  * 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.
···
  * 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__
 

arch/x86/include/asm/apic.h

···
 	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)

arch/x86/include/asm/asm-prototypes.h

···
 #include <asm/gsseg.h>
 #include <asm/nospec-branch.h>
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 extern void cmpxchg8b_emu(void);
 #endif
 

arch/x86/include/asm/asm.h

···
 
 /* 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

arch/x86/include/asm/atomic64_32.h

···
 	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)
···
 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);
···
 	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
···
 {
 	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
···
 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
···
 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
···
 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
···
 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
 
···
 	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
···
 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
···
 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

arch/x86/include/asm/cmpxchg_32.h

···
 	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 
 #define arch_cmpxchg64 __cmpxchg64
 
···
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8)	\
+		: ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	o.full;								\
 })
···
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     CC_SET(e)						\
-		     : ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
-				     "+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+		CC_SET(e)						\
+		: ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+				"+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	if (unlikely(!ret))						\
 		*(_oldp) = o.full;					\

arch/x86/include/asm/cpu.h

···
 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

arch/x86/include/asm/cpufeature.h

···
 	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))

arch/x86/include/asm/cpuid.h

···
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
+#include <linux/build_bug.h>
 #include <linux/types.h>
 
 #include <asm/string.h>

arch/x86/include/asm/desc.h

···
 } __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)

arch/x86/include/asm/elf.h

···
 #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 */

arch/x86/include/asm/intel-family.h

···
 
 #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) */
···
 #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) */
 
···
 #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 */
···
 /* 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 */

arch/x86/include/asm/io.h

···
 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

arch/x86/include/asm/mshyperv.h

···
 		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;
 	}
···
 	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);
···
 		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");
 	}

arch/x86/include/asm/nospec-branch.h

···
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
···
 #ifdef CONFIG_X86_64
 
 /*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
+/*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 

arch/x86/include/asm/page_32_types.h

···
  * 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

arch/x86/include/asm/page_64.h

···
 			   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);

arch/x86/include/asm/paravirt.h

···
 	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);

arch/x86/include/asm/paravirt_types.h

···
 	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);

arch/x86/include/asm/percpu.h

···
 
 #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>
···
 # 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: */
···
 #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).
  */
···
 #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)
···
 ({									\
 	__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)));				\
 									\
···
 		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)
···
 ({									\
 	__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)));					\
 									\
···
 
 #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)));				\
 })
 
···
 		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)
···
 ({									\
 	__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");					\
···
 	__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__)		\
···
 	__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__),				\
···
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
···
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
 									\
···
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
···
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
+									\
 	likely(success);						\
 })
 

arch/x86/include/asm/pgalloc.h

···
 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

arch/x86/include/asm/processor.h

···
 # 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.
···
 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 *);
 
···
 } __aligned(IRQ_STACK_SIZE);
 
 #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_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
-
 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;
 

arch/x86/include/asm/required-features.h

···
 # define NEED_PAE	0
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 # define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_CX8	0

arch/x86/include/asm/smp.h

···
 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);
···
 {
 	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

arch/x86/include/asm/sta2x11.h

···
-/* 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 */

arch/x86/include/asm/stackprotector.h

···
 /*
  * 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
···
 #include <asm/desc.h>
 
 #include <linux/sched.h>
+
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
 
 /*
  * Initialize the stackprotector canary value.
···
 {
 	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 */

arch/x86/include/asm/vermagic.h

···
 #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
···
 #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

arch/x86/kernel/Makefile

···
 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

arch/x86/kernel/acpi/cstate.c

···
 #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
···
 	return retval;
 }
 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)
 {

arch/x86/kernel/apic/Makefile

···
 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

arch/x86/kernel/apic/apic.c

···
 
 	x86_64_probe_apic();
 
-	x86_32_install_bigsmp();
-
 	if (x86_platform.apic_post_init)
 		x86_platform.apic_post_init();
 
···
 		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

arch/x86/kernel/apic/bigsmp_32.c

···
-// 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);

arch/x86/kernel/apic/local.h

···
 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

arch/x86/kernel/apic/probe_32.c

···
 }
 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) {

arch/x86/kernel/asm-offsets_64.c

···
 	BLANK();
 #undef ENTRY
 
-	BLANK();
-
-#ifdef CONFIG_STACKPROTECTOR
-	OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
-	BLANK();
-#endif
 	return 0;
 }

arch/x86/kernel/cpu/amd.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);
···
 
 	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
···
 
 	/* 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[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev amd_cpu_dev = {

arch/x86/kernel/cpu/cacheinfo.c

···
  *	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"
···
 #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);
···
 	{ 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 */
···
 			}
 		}
 	}
-	/*
-	 * 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;
···
 			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
+			for (j = 0 ; j < 4 ; j++)
 				if (regs[j] & (1 << 31))
 					regs[j] = 0;
 
···
 				/* 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;

arch/x86/kernel/cpu/common.c

···
 		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);
 	}
 }
 
···
 	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)
 {
···
 		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)
···
 
 	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),
···
 #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"))
···
 		setup_clear_cpu_cap(X86_FEATURE_FRED);
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, false);
 
-	pr_info("Clearing CPUID bits:");
+	arglen = cmdline_find_option(boot_command_line, "setcpuid", arg, sizeof(arg));
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, true);
 
-	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;
-
-			pr_cont(" %s", opt);
-			setup_clear_cpu_cap(bit);
-			taint++;
-			found = true;
-			break;
-		}
-
-		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);
+	}
 }
 
 /*
···
 	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();
···
 		update_gds_msr();
 
 	tsx_ap_init();
+	c->initialized = true;
 }
 
 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);
+
+static __init int setup_setcpuid(char *arg)
+{
+	return 1;
+}
+__setup("setcpuid=", setup_setcpuid);
 
 DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
···
 EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
 
 #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);
-
 static void wrmsrl_cstar(unsigned long val)
 {
 	/*
···
 	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);
···
 EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
 #endif
 #endif
-
-#endif	/* CONFIG_X86_64 */
 
 /*
  * Clear all 6 debug registers:

arch/x86/kernel/cpu/cpu.h

···
 #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") = \

arch/x86/kernel/cpu/debugfs.c

···
 	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);

arch/x86/kernel/cpu/hygon.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 = {

arch/x86/kernel/cpu/intel.c

···
 // 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 <asm/cpufeature.h>
-#include <asm/msr.h>
-#include <asm/bugs.h>
-#include <asm/cpu.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/numa.h>
-#include <asm/thermal.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 "cpu.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/msr.h>
+#include <asm/numa.h>
+#include <asm/resctrl.h>
+#include <asm/thermal.h>
+#include <asm/uaccess.h>
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#endif
+#include "cpu.h"
 
 /*
  * Processors which have self-snooping capability can handle conflicting
···
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
+#define TLB_INST_4K		0x01
+#define TLB_INST_4M		0x02
+#define TLB_INST_2M_4M		0x03
 
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
+#define TLB_INST_ALL		0x05
+#define TLB_INST_1G		0x06
 
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
+#define TLB_DATA_4K		0x11
+#define TLB_DATA_4M		0x12
+#define TLB_DATA_2M_4M		0x13
+#define TLB_DATA_4K_4M		0x14
 
-#define TLB_DATA_1G	0x16
+#define TLB_DATA_1G		0x16
+#define TLB_DATA_1G_2M_4M	0x17
 
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
+#define TLB_DATA0_4K		0x21
+#define TLB_DATA0_4M		0x22
+#define TLB_DATA0_2M_4M		0x23
 
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
+#define STLB_4K			0x41
+#define STLB_4K_2M		0x42
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of
+ * entries for their respective TLB types.  The 0x63 descriptor is an
+ * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
+ * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
+ * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
+ * intel_tlb_table[] mapping.
+ */
+#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,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
-	{ 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;
 
···
 	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:
+		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;
 	}
 }
···
 		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
+		for (j = 0 ; j < 4 ; j++)
 			if (regs[j] & (1 << 31))
 				regs[j] = 0;
 
···
 };
 
 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);
-}

arch/x86/kernel/cpu/mtrr/if.c

···
 	char *ptr;
 	char line[LINE_SIZE];
 	int length;
-	size_t linelen;
 
 	memset(line, 0, LINE_SIZE);
 
···
 	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)) {

arch/x86/kernel/head64.c

···
  */
 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 = {

arch/x86/kernel/head_64.S

···
 	/* 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
···
 	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

arch/x86/kernel/ioport.c

···
 	 * 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;
 }

arch/x86/kernel/irq_32.c

···
 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);
 }
···
 }
 
 #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
 
 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");
 }
 
···
 	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);
···
 	 * current stack (which is the irq stack already after all)
 	 */
 	if (unlikely(curstk == irqstk))
-		return 0;
+		return false;
 
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
···
 	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;
 }
 
 /*
···
 
 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))

arch/x86/kernel/irq_64.c

···
 #include <asm/apic.h>
 
 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
 /*

arch/x86/kernel/kvm.c

···
 #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");
 	}
 

arch/x86/kernel/module.c

···
 #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>
···
 				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;

arch/x86/kernel/paravirt.c

···
 		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;
 
···
 	.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,

arch/x86/kernel/setup_percpu.c

···
 #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_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(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);
 
 /*

arch/x86/kernel/signal_32.c

···
 #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
···
 	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);

arch/x86/kernel/smpboot.c

···
 	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
···
 {
 	/*
 	 * 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,
···
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 ANNOTATE_NOENDBR_SYM(start_secondary);
-
-/*
- * 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;
-}
 
 static bool
 topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
···
  * 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;
···
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
···
 	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 */

arch/x86/kernel/tsc_msr.c

···
 	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),
 	{}
 };

arch/x86/kernel/vmlinux.lds.S

···
 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);          /* ___ */
 }
 
···
 		__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
···
 		EXIT_DATA
 	}
 
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
 	PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
 
 	RUNTIME_CONST_VARIABLES
 	RUNTIME_CONST(ptr, USER_PTR_MAX)
···
 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");

arch/x86/kvm/vmx/vmx_ops.h

···
 
 #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"
 
···
 		      * @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 */

arch/x86/lib/Makefile

···
         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

arch/x86/lib/cmpxchg8b_emu.S

···
 
 .text
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 
 /*
  * Emulate 'cmpxchg8b (%esi)' on UP

arch/x86/mm/init_32.c

···
 	"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:
···
 #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 */
 }
 

arch/x86/mm/ioremap.c

···
 }
 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

arch/x86/mm/kaslr.c

···
 	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;
 
 	/*

arch/x86/mm/mmap.c

···
 {
 	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)
···
 	 * 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);
 }

arch/x86/mm/pat/set_memory.c

···
 	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
···
 				.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 };
 
 	/*
···
 		.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,
 	};
 
···
 		.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,
 	};
 

arch/x86/mm/pgtable.c

···
 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);
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
 }
-
-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;
-}
-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
···
 #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 */

arch/x86/pci/Makefile

···
 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

arch/x86/pci/sta2x11-fixup.c

···
-// 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 */

arch/x86/platform/pvh/head.S

···
 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 */
···
 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)

arch/x86/tools/relocs.c

···
 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
···
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-	"__per_cpu_load|"
-	"init_per_cpu__.*|"
 	"__end_rodata_hpage_align|"
 #endif
 	"_end)$"
···
 		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),
···
 		name = sec_name(sym_index(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
···
 	}
 }
 
-/*
- * 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)
···
 	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. */
···
 
 	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
···
 
 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)
···
 	/* Order the relocations for more efficient processing */
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
-	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
 #else
 	sort_relocs(&relocs16);
···
 		/* 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 */
···
 	read_strtabs(fp);
 	read_symtabs(fp);
 	read_relocs(fp);
-
-	if (ELF_BITS == 64)
-		percpu_init();
 
 	if (show_absolute_syms) {
 		print_absolute_symbols();

arch/x86/xen/Kconfig

···
 	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

arch/x86/xen/mmu_pv.c

···
 		.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,

arch/x86/xen/smp_pv.c

···
 		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();

arch/x86/xen/xen-head.S

···
 
 	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

drivers/acpi/processor_idle.c

···
 			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;
 	}

drivers/cpufreq/intel_pstate.c

···
 	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();
 	}
 

drivers/idle/intel_idle.c

···
 #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"
 
···
 	mwait_idle_with_hints(eax, ecx);
 
 	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);
 }
 
 /*
···
 			mark_tsc_unstable("TSC halts in idle");
 
 		state->enter = intel_idle;
+		state->enter_dead = intel_idle_enter_dead;
 		state->enter_s2idle = intel_idle_s2idle;
 	}
 }
···
 		if (!cpuidle_state_table[cstate].enter &&
 		    !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) {

drivers/misc/mei/Kconfig

···
 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.

drivers/pci/Kconfig

···
 	  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

drivers/powercap/intel_rapl_common.c

···
 	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),

drivers/staging/media/atomisp/include/linux/atomisp_platform.h

···
 #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_ */

drivers/thermal/intel/intel_tcc.c

···
 	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),

include/acpi/processor.h

···
 				    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
···
 						   *cstate)
 {
 	return;
+}
+static inline void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	BUG();
 }
 #endif
 

include/asm-generic/sections.h

···
 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[];

include/asm-generic/vmlinux.lds.h

···
  */
 #define PERCPU_INPUT(cacheline)						\
 	__per_cpu_start = .;						\
-	*(.data..percpu..first)						\
 	. = ALIGN(PAGE_SIZE);						\
 	*(.data..percpu..page_aligned)					\
 	. = ALIGN(cacheline);						\
···
 	__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)					\
 	}
 

include/linux/percpu-defs.h

···
 #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
 
···
 
 #define DEFINE_PER_CPU(type, name)					\
 	DEFINE_PER_CPU_SECTION(type, name, "")
-
-/*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
- */
-#define DECLARE_PER_CPU_FIRST(type, name)				\
-	DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
-#define DEFINE_PER_CPU_FIRST(type, name)				\
-	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
 
 /*
  * Declaration/definition used for per-CPU variables that must be cacheline

include/linux/sizes.h

···
 #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

init/Kconfig

···
 
 	  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

kernel/bpf/verifier.c

···
 			 * 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)&pcpu_hot.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;

kernel/iomem.c

···
 #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);
···
 		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);
 	}
 
 	/*

kernel/kallsyms.c

···
 
 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)

lib/atomic64_test.c

···
 	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+",

mm/percpu.c

···
 				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);
 		}
 	}
···
 		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 */

scripts/gcc-x86_32-has-stack-protector.sh

···
-#!/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"

scripts/gcc-x86_64-has-stack-protector.sh

···
-#!/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"

scripts/kallsyms.c

···
  * 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
···
 	unsigned long long addr;
 	unsigned int len;
 	unsigned int seq;
-	bool percpu_absolute;
 	unsigned char sym[];
 };
 
···
 #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];
 
···
 
 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);
 }
 
···
 		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 */
···
 	sym->len = len;
 	sym->sym[0] = type;
 	strcpy(sym_name(sym), name);
-	sym->percpu_absolute = false;
 
 	return sym;
 }
···
 	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;
···
 		 */
 
 		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);
 		}
···
 	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)
···
 	while (1) {
 		static const struct option long_options[] = {
 			{"all-symbols",     no_argument, &all_symbols,     1},
-			{"absolute-percpu", no_argument, &absolute_percpu, 1},
 			{},
 		};
 
···
 
 	read_map(argv[optind]);
 	shrink_table();
-	if (absolute_percpu)
-		make_percpus_absolute();
 	sort_symbols();
 	record_relative_base();
 	optimize_token_table();

scripts/link-vmlinux.sh

···
 		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"
 

scripts/min-tool-version.sh

···
 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

tools/arch/x86/include/asm/required-features.h

···
 # define NEED_PAE	0
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 # define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_CX8	0

tools/objtool/noreturns.h

···
 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)
···
 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)

tools/power/x86/turbostat/turbostat.c

···
 	 * Missing support for
 	 * INTEL_ICELAKE
 	 * INTEL_ATOM_SILVERMONT_MID
-	 * INTEL_ATOM_AIRMONT_MID
+	 * INTEL_ATOM_SILVERMONT_MID2
 	 * INTEL_ATOM_AIRMONT_NP
 	 */
 	{ 0, NULL },

tools/testing/selftests/x86/lam.c

···
 #include <stdlib.h>
 #include <string.h>
 #include <sys/syscall.h>
+#include <sys/ioctl.h>
 #include <time.h>
 #include <signal.h>
 #include <setjmp.h>
···
 #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)
···
 	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;
 
-	__cpuid_count(0x7, 0, cpuinfo[0], cpuinfo[1], cpuinfo[2], cpuinfo[3]);
+	p = mmap((void *)HIGH_ADDR, PAGE_SIZE, PROT_READ | PROT_WRITE,
+		 MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
 
-	return (cpuinfo[2] & (1 << 16));
+	ret = p == MAP_FAILED ? 0 : 1;
+
+	munmap(p, PAGE_SIZE);
+	return ret;
 }
 
 /*
···
 		   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;
 	}
···
 		if (set_lam(test->lam) != -1 && ret == 0)
 			ret = 1;
 
+	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;
 }
 
···
 	fi->file_fd = file_fd;
 
 	ring = malloc(sizeof(*ring));
-	if (!ring)
+	if (!ring) {
+		free(fi);
 		return 1;
+	}
 
 	memset(ring, 0, sizeof(struct io_ring));
 
···
 		.lam = LAM_U57_BITS,
 		.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",
 	},
 };
 
···
 
 	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) {