Fixed MTP to work with TWRP

arch/x86/Kbuild

@@ -0,0 +1,20 @@
+obj-$(CONFIG_KVM) += kvm/
+
+# Xen paravirtualization support
+obj-$(CONFIG_XEN) += xen/
+
+# lguest paravirtualization support
+obj-$(CONFIG_LGUEST_GUEST) += lguest/
+
+obj-y += realmode/
+obj-y += kernel/
+obj-y += mm/
+
+obj-y += crypto/
+obj-y += vdso/
+obj-$(CONFIG_IA32_EMULATION) += ia32/
+
+obj-y += platform/
+obj-y += net/
+
+obj-$(CONFIG_KEXEC_FILE) += purgatory/

arch/x86/Kconfig.cpu

@@ -0,0 +1,470 @@
+# Put here option for CPU selection and depending optimization
+choice
+	prompt "Processor family"
+	default M686 if X86_32
+	default GENERIC_CPU if X86_64
+
+config M486
+	bool "486"
+	depends on X86_32
+	---help---
+	  This is the processor type of your CPU. This information is
+	  used for optimizing purposes. In order to compile a kernel
+	  that can run on all supported x86 CPU types (albeit not
+	  optimally fast), you can specify "486" here.
+
+	  Note that the 386 is no longer supported, this includes
+	  AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI 486DLC/DLC2,
+	  UMC 486SX-S and the NexGen Nx586.
+
+	  The kernel will not necessarily run on earlier architectures than
+	  the one you have chosen, e.g. a Pentium optimized kernel will run on
+	  a PPro, but not necessarily on a i486.
+
+	  Here are the settings recommended for greatest speed:
+	  - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or
+	  SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S.
+	  - "586" for generic Pentium CPUs lacking the TSC
+	  (time stamp counter) register.
+	  - "Pentium-Classic" for the Intel Pentium.
+	  - "Pentium-MMX" for the Intel Pentium MMX.
+	  - "Pentium-Pro" for the Intel Pentium Pro.
+	  - "Pentium-II" for the Intel Pentium II or pre-Coppermine Celeron.
+	  - "Pentium-III" for the Intel Pentium III or Coppermine Celeron.
+	  - "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).
+	  - "Crusoe" for the Transmeta Crusoe series.
+	  - "Efficeon" for the Transmeta Efficeon series.
+	  - "Winchip-C6" for original IDT Winchip.
+	  - "Winchip-2" for IDT Winchips with 3dNow! capabilities.
+	  - "GeodeGX1" for Geode GX1 (Cyrix MediaGX).
+	  - "Geode GX/LX" For AMD Geode GX and LX processors.
+	  - "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.
+
+	  If you don't know what to do, choose "486".
+
+config M586
+	bool "586/K5/5x86/6x86/6x86MX"
+	depends on X86_32
+	---help---
+	  Select this for an 586 or 686 series processor such as the AMD K5,
+	  the Cyrix 5x86, 6x86 and 6x86MX.  This choice does not
+	  assume the RDTSC (Read Time Stamp Counter) instruction.
+
+config M586TSC
+	bool "Pentium-Classic"
+	depends on X86_32
+	---help---
+	  Select this for a Pentium Classic processor with the RDTSC (Read
+	  Time Stamp Counter) instruction for benchmarking.
+
+config M586MMX
+	bool "Pentium-MMX"
+	depends on X86_32
+	---help---
+	  Select this for a Pentium with the MMX graphics/multimedia
+	  extended instructions.
+
+config M686
+	bool "Pentium-Pro"
+	depends on X86_32
+	---help---
+	  Select this for Intel Pentium Pro chips.  This enables the use of
+	  Pentium Pro extended instructions, and disables the init-time guard
+	  against the f00f bug found in earlier Pentiums.
+
+config MPENTIUMII
+	bool "Pentium-II/Celeron(pre-Coppermine)"
+	depends on X86_32
+	---help---
+	  Select this for Intel chips based on the Pentium-II and
+	  pre-Coppermine Celeron core.  This option enables an unaligned
+	  copy optimization, compiles the kernel with optimization flags
+	  tailored for the chip, and applies any applicable Pentium Pro
+	  optimizations.
+
+config MPENTIUMIII
+	bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon"
+	depends on X86_32
+	---help---
+	  Select this for Intel chips based on the Pentium-III and
+	  Celeron-Coppermine core.  This option enables use of some
+	  extended prefetch instructions in addition to the Pentium II
+	  extensions.
+
+config MPENTIUMM
+	bool "Pentium M"
+	depends on X86_32
+	---help---
+	  Select this for Intel Pentium M (not Pentium-4 M)
+	  notebook chips.
+
+config MPENTIUM4
+	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
+	depends on X86_32
+	---help---
+	  Select this for Intel Pentium 4 chips.  This includes the
+	  Pentium 4, Pentium D, P4-based Celeron and Xeon, and
+	  Pentium-4 M (not Pentium M) chips.  This option enables compile
+	  flags optimized for the chip, uses the correct cache line size, and
+	  applies any applicable optimizations.
+
+	  CPUIDs: F[0-6][1-A] (in /proc/cpuinfo show = cpu family : 15 )
+
+	  Select this for:
+	    Pentiums (Pentium 4, Pentium D, Celeron, Celeron D) corename:
+		-Willamette
+		-Northwood
+		-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"
+	depends on X86_32
+	---help---
+	  Select this for an AMD K6-family processor.  Enables use of
+	  some extended instructions, and passes appropriate optimization
+	  flags to GCC.
+
+config MK7
+	bool "Athlon/Duron/K7"
+	depends on X86_32
+	---help---
+	  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"
+	depends on X86_32
+	---help---
+	  Select this for a Transmeta Crusoe processor.  Treats the processor
+	  like a 586 with TSC, and sets some GCC optimization flags (like a
+	  Pentium Pro with no alignment requirements).
+
+config MEFFICEON
+	bool "Efficeon"
+	depends on X86_32
+	---help---
+	  Select this for a Transmeta Efficeon processor.
+
+config MWINCHIPC6
+	bool "Winchip-C6"
+	depends on X86_32
+	---help---
+	  Select this for an IDT Winchip C6 chip.  Linux and GCC
+	  treat this chip as a 586TSC with some extended instructions
+	  and alignment requirements.
+
+config MWINCHIP3D
+	bool "Winchip-2/Winchip-2A/Winchip-3"
+	depends on X86_32
+	---help---
+	  Select this for an IDT Winchip-2, 2A or 3.  Linux and GCC
+	  treat this chip as a 586TSC with some extended instructions
+	  and alignment requirements.  Also enable out of order memory
+	  stores for this CPU, which can increase performance of some
+	  operations.
+
+config MELAN
+	bool "AMD Elan"
+	depends on X86_32
+	---help---
+	  Select this for an AMD Elan processor.
+
+	  Do not use this option for K6/Athlon/Opteron processors!
+
+config MGEODEGX1
+	bool "GeodeGX1"
+	depends on X86_32
+	---help---
+	  Select this for a Geode GX1 (Cyrix MediaGX) chip.
+
+config MGEODE_LX
+	bool "Geode GX/LX"
+	depends on X86_32
+	---help---
+	  Select this for AMD Geode GX and LX processors.
+
+config MCYRIXIII
+	bool "CyrixIII/VIA-C3"
+	depends on X86_32
+	---help---
+	  Select this for a Cyrix III or C3 chip.  Presently Linux and GCC
+	  treat this chip as a generic 586. Whilst the CPU is 686 class,
+	  it lacks the cmov extension which gcc assumes is present when
+	  generating 686 code.
+	  Note that Nehemiah (Model 9) and above will not boot with this
+	  kernel due to them lacking the 3DNow! instructions used in earlier
+	  incarnations of the CPU.
+
+config MVIAC3_2
+	bool "VIA C3-2 (Nehemiah)"
+	depends on X86_32
+	---help---
+	  Select this for a VIA C3 "Nehemiah". Selecting this enables usage
+	  of SSE and tells gcc to treat the CPU as a 686.
+	  Note, this kernel will not boot on older (pre model 9) C3s.
+
+config MVIAC7
+	bool "VIA C7"
+	depends on X86_32
+	---help---
+	  Select this for a VIA C7.  Selecting this uses the correct cache
+	  shift and tells gcc to treat the CPU as a 686.
+
+config MPSC
+	bool "Intel P4 / older Netburst based Xeon"
+	depends on X86_64
+	---help---
+	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
+	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
+	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
+	  Netburst core and shouldn't use this option. You can distinguish them
+	  using the cpu family field
+	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
+
+config MCORE2
+	bool "Core 2/newer Xeon"
+	---help---
+
+	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
+	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
+	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
+	  (not a typo)
+
+config MATOM
+	bool "Intel Atom"
+	---help---
+
+	  Select this for the Intel Atom platform. Intel Atom CPUs have an
+	  in-order pipelining architecture and thus can benefit from
+	  accordingly optimized code. Use a recent GCC with specific Atom
+	  support in order to fully benefit from selecting this option.
+
+config GENERIC_CPU
+	bool "Generic-x86-64"
+	depends on X86_64
+	---help---
+	  Generic x86-64 CPU.
+	  Run equally well on all x86-64 CPUs.
+
+endchoice
+
+config X86_GENERIC
+	bool "Generic x86 support"
+	depends on X86_32
+	---help---
+	  Instead of just including optimizations for the selected
+	  x86 variant (e.g. PII, Crusoe or Athlon), include some more
+	  generic optimizations as well. This will make the kernel
+	  perform better on x86 CPUs other than that selected.
+
+	  This is really intended for distributors who need more
+	  generic optimizations.
+
+#
+# Define implied options from the CPU selection here
+config X86_INTERNODE_CACHE_SHIFT
+	int
+	default "12" if X86_VSMP
+	default X86_L1_CACHE_SHIFT
+
+config X86_L1_CACHE_SHIFT
+	int
+	default "7" if MPENTIUM4 || MPSC
+	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "4" if MELAN || M486 || MGEODEGX1
+	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
+
+config X86_PPRO_FENCE
+	bool "PentiumPro memory ordering errata workaround"
+	depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1
+	---help---
+	  Old PentiumPro multiprocessor systems had errata that could cause
+	  memory operations to violate the x86 ordering standard in rare cases.
+	  Enabling this option will attempt to work around some (but not all)
+	  occurrences of this problem, at the cost of much heavier spinlock and
+	  memory barrier operations.
+
+	  If unsure, say n here. Even distro kernels should think twice before
+	  enabling this: there are few systems, and an unlikely bug.
+
+config X86_F00F_BUG
+	def_bool y
+	depends on M586MMX || M586TSC || M586 || M486
+
+config X86_INVD_BUG
+	def_bool y
+	depends on M486
+
+config X86_ALIGNMENT_16
+	def_bool y
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1
+
+config X86_INTEL_USERCOPY
+	def_bool y
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+
+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
+
+config X86_USE_3DNOW
+	def_bool y
+	depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
+
+#
+# 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)
+
+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
+
+config X86_CMPXCHG64
+	def_bool y
+	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
+
+# 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)
+
+config X86_MINIMUM_CPU_FAMILY
+	int
+	default "64" if X86_64
+	default "6" if X86_32 && X86_P6_NOP
+	default "5" if X86_32 && X86_CMPXCHG64
+	default "4"
+
+config X86_DEBUGCTLMSR
+	def_bool y
+	depends on !(MK6 || MWINCHIPC6 || MWINCHIP3D || MCYRIXIII || M586MMX || M586TSC || M586 || M486) && !UML
+
+menuconfig PROCESSOR_SELECT
+	bool "Supported processor vendors" if EXPERT
+	---help---
+	  This lets you choose what x86 vendor support code your kernel
+	  will include.
+
+config CPU_SUP_INTEL
+	default y
+	bool "Support Intel processors" if PROCESSOR_SELECT
+	---help---
+	  This enables detection, tunings and quirks for Intel processors
+
+	  You need this enabled if you want your kernel to run on an
+	  Intel CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on an Intel
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
+
+config CPU_SUP_CYRIX_32
+	default y
+	bool "Support Cyrix processors" if PROCESSOR_SELECT
+	depends on M486 || M586 || M586TSC || M586MMX || (EXPERT && !64BIT)
+	---help---
+	  This enables detection, tunings and quirks for Cyrix processors
+
+	  You need this enabled if you want your kernel to run on a
+	  Cyrix CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on a Cyrix
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
+
+config CPU_SUP_AMD
+	default y
+	bool "Support AMD processors" if PROCESSOR_SELECT
+	---help---
+	  This enables detection, tunings and quirks for AMD processors
+
+	  You need this enabled if you want your kernel to run on an
+	  AMD CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on an AMD
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
+
+config CPU_SUP_CENTAUR
+	default y
+	bool "Support Centaur processors" if PROCESSOR_SELECT
+	---help---
+	  This enables detection, tunings and quirks for Centaur processors
+
+	  You need this enabled if you want your kernel to run on a
+	  Centaur CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on a Centaur
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
+
+config CPU_SUP_TRANSMETA_32
+	default y
+	bool "Support Transmeta processors" if PROCESSOR_SELECT
+	depends on !64BIT
+	---help---
+	  This enables detection, tunings and quirks for Transmeta processors
+
+	  You need this enabled if you want your kernel to run on a
+	  Transmeta CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on a Transmeta
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
+
+config CPU_SUP_UMC_32
+	default y
+	bool "Support UMC processors" if PROCESSOR_SELECT
+	depends on M486 || (EXPERT && !64BIT)
+	---help---
+	  This enables detection, tunings and quirks for UMC processors
+
+	  You need this enabled if you want your kernel to run on a
+	  UMC CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on a UMC
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.

arch/x86/Kconfig.debug

@@ -0,0 +1,326 @@
+menu "Kernel hacking"
+
+config TRACE_IRQFLAGS_SUPPORT
+	def_bool y
+
+source "lib/Kconfig.debug"
+
+config STRICT_DEVMEM
+	bool "Filter access to /dev/mem"
+	---help---
+	  If this option is disabled, you allow userspace (root) access to all
+	  of memory, including kernel and userspace memory. Accidental
+	  access to this is obviously disastrous, but specific access can
+	  be used by people debugging the kernel. Note that with PAT support
+	  enabled, even in this case there are restrictions on /dev/mem
+	  use due to the cache aliasing requirements.
+
+	  If this option is switched on, the /dev/mem file only allows
+	  userspace access to PCI space and the BIOS code and data regions.
+	  This is sufficient for dosemu and X and all common users of
+	  /dev/mem.
+
+	  If in doubt, say Y.
+
+config X86_VERBOSE_BOOTUP
+	bool "Enable verbose x86 bootup info messages"
+	default y
+	---help---
+	  Enables the informational output from the decompression stage
+	  (e.g. bzImage) of the boot. If you disable this you will still
+	  see errors. Disable this if you want silent bootup.
+
+config EARLY_PRINTK
+	bool "Early printk" if EXPERT
+	default y
+	---help---
+	  Write kernel log output directly into the VGA buffer or to a serial
+	  port.
+
+	  This is useful for kernel debugging when your machine crashes very
+	  early before the console code is initialized. For normal operation
+	  it is not recommended because it looks ugly and doesn't cooperate
+	  with klogd/syslogd or the X server. You should normally N here,
+	  unless you want to debug such a crash.
+
+config EARLY_PRINTK_INTEL_MID
+	bool "Early printk for Intel MID platform support"
+	depends on EARLY_PRINTK && X86_INTEL_MID
+
+config EARLY_PRINTK_DBGP
+	bool "Early printk via EHCI debug port"
+	depends on EARLY_PRINTK && PCI
+	---help---
+	  Write kernel log output directly into the EHCI debug port.
+
+	  This is useful for kernel debugging when your machine crashes very
+	  early before the console code is initialized. For normal operation
+	  it is not recommended because it looks ugly and doesn't cooperate
+	  with klogd/syslogd or the X server. You should normally N here,
+	  unless you want to debug such a crash. You need usb debug device.
+
+config EARLY_PRINTK_EFI
+	bool "Early printk via the EFI framebuffer"
+	depends on EFI && EARLY_PRINTK
+	select FONT_SUPPORT
+	---help---
+	  Write kernel log output directly into the EFI framebuffer.
+
+	  This is useful for kernel debugging when your machine crashes very
+	  early before the console code is initialized.
+
+config X86_PTDUMP
+	bool "Export kernel pagetable layout to userspace via debugfs"
+	depends on DEBUG_KERNEL
+	select DEBUG_FS
+	---help---
+	  Say Y here if you want to show the kernel pagetable layout in a
+	  debugfs file. This information is only useful for kernel developers
+	  who are working in architecture specific areas of the kernel.
+	  It is probably not a good idea to enable this feature in a production
+	  kernel.
+	  If in doubt, say "N"
+
+config EFI_PGT_DUMP
+	bool "Dump the EFI pagetable"
+	depends on EFI && X86_PTDUMP
+	---help---
+	  Enable this if you want to dump the EFI page table before
+	  enabling virtual mode. This can be used to debug miscellaneous
+	  issues with the mapping of the EFI runtime regions into that
+	  table.
+
+config DEBUG_RODATA
+	bool "Write protect kernel read-only data structures"
+	default y
+	depends on DEBUG_KERNEL
+	---help---
+	  Mark the kernel read-only data as write-protected in the pagetables,
+	  in order to catch accidental (and incorrect) writes to such const
+	  data. This is recommended so that we can catch kernel bugs sooner.
+	  If in doubt, say "Y".
+
+config DEBUG_RODATA_TEST
+	bool "Testcase for the DEBUG_RODATA feature"
+	depends on DEBUG_RODATA
+	default y
+	---help---
+	  This option enables a testcase for the DEBUG_RODATA
+	  feature as well as for the change_page_attr() infrastructure.
+	  If in doubt, say "N"
+
+config DEBUG_SET_MODULE_RONX
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	---help---
+	  This option helps catch unintended modifications to loadable
+	  kernel module's text and read-only data. It also prevents execution
+	  of module data. Such protection may interfere with run-time code
+	  patching and dynamic kernel tracing - and they might also protect
+	  against certain classes of kernel exploits.
+	  If in doubt, say "N".
+
+config DEBUG_NX_TEST
+	tristate "Testcase for the NX non-executable stack feature"
+	depends on DEBUG_KERNEL && m
+	---help---
+	  This option enables a testcase for the CPU NX capability
+	  and the software setup of this feature.
+	  If in doubt, say "N"
+
+config DOUBLEFAULT
+	default y
+	bool "Enable doublefault exception handler" if EXPERT
+	---help---
+	  This option allows trapping of rare doublefault exceptions that
+	  would otherwise cause a system to silently reboot. Disabling this
+	  option saves about 4k and might cause you much additional grey
+	  hair.
+
+config DEBUG_TLBFLUSH
+	bool "Set upper limit of TLB entries to flush one-by-one"
+	depends on DEBUG_KERNEL
+	---help---
+
+	X86-only for now.
+
+	This option allows the user to tune the amount of TLB entries the
+	kernel flushes one-by-one instead of doing a full TLB flush. In
+	certain situations, the former is cheaper. This is controlled by the
+	tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it
+	to -1, the code flushes the whole TLB unconditionally. Otherwise,
+	for positive values of it, the kernel will use single TLB entry
+	invalidating instructions according to the following formula:
+
+	flush_entries <= active_tlb_entries / 2^tlb_flushall_shift
+
+	If in doubt, say "N".
+
+config IOMMU_DEBUG
+	bool "Enable IOMMU debugging"
+	depends on GART_IOMMU && DEBUG_KERNEL
+	depends on X86_64
+	---help---
+	  Force the IOMMU to on even when you have less than 4GB of
+	  memory and add debugging code. On overflow always panic. And
+	  allow to enable IOMMU leak tracing. Can be disabled at boot
+	  time with iommu=noforce. This will also enable scatter gather
+	  list merging.  Currently not recommended for production
+	  code. When you use it make sure you have a big enough
+	  IOMMU/AGP aperture.  Most of the options enabled by this can
+	  be set more finegrained using the iommu= command line
+	  options. See Documentation/x86/x86_64/boot-options.txt for more
+	  details.
+
+config IOMMU_STRESS
+	bool "Enable IOMMU stress-test mode"
+	---help---
+	  This option disables various optimizations in IOMMU related
+	  code to do real stress testing of the IOMMU code. This option
+	  will cause a performance drop and should only be enabled for
+	  testing.
+
+config IOMMU_LEAK
+	bool "IOMMU leak tracing"
+	depends on IOMMU_DEBUG && DMA_API_DEBUG
+	---help---
+	  Add a simple leak tracer to the IOMMU code. This is useful when you
+	  are debugging a buggy device driver that leaks IOMMU mappings.
+
+config HAVE_MMIOTRACE_SUPPORT
+	def_bool y
+
+config X86_DECODER_SELFTEST
+	bool "x86 instruction decoder selftest"
+	depends on DEBUG_KERNEL && KPROBES
+	depends on !COMPILE_TEST
+	---help---
+	 Perform x86 instruction decoder selftests at build time.
+	 This option is useful for checking the sanity of x86 instruction
+	 decoder code.
+	 If unsure, say "N".
+
+#
+# IO delay types:
+#
+
+config IO_DELAY_TYPE_0X80
+	int
+	default "0"
+
+config IO_DELAY_TYPE_0XED
+	int
+	default "1"
+
+config IO_DELAY_TYPE_UDELAY
+	int
+	default "2"
+
+config IO_DELAY_TYPE_NONE
+	int
+	default "3"
+
+choice
+	prompt "IO delay type"
+	default IO_DELAY_0X80
+
+config IO_DELAY_0X80
+	bool "port 0x80 based port-IO delay [recommended]"
+	---help---
+	  This is the traditional Linux IO delay used for in/out_p.
+	  It is the most tested hence safest selection here.
+
+config IO_DELAY_0XED
+	bool "port 0xed based port-IO delay"
+	---help---
+	  Use port 0xed as the IO delay. This frees up port 0x80 which is
+	  often used as a hardware-debug port.
+
+config IO_DELAY_UDELAY
+	bool "udelay based port-IO delay"
+	---help---
+	  Use udelay(2) as the IO delay method. This provides the delay
+	  while not having any side-effect on the IO port space.
+
+config IO_DELAY_NONE
+	bool "no port-IO delay"
+	---help---
+	  No port-IO delay. Will break on old boxes that require port-IO
+	  delay for certain operations. Should work on most new machines.
+
+endchoice
+
+if IO_DELAY_0X80
+config DEFAULT_IO_DELAY_TYPE
+	int
+	default IO_DELAY_TYPE_0X80
+endif
+
+if IO_DELAY_0XED
+config DEFAULT_IO_DELAY_TYPE
+	int
+	default IO_DELAY_TYPE_0XED
+endif
+
+if IO_DELAY_UDELAY
+config DEFAULT_IO_DELAY_TYPE
+	int
+	default IO_DELAY_TYPE_UDELAY
+endif
+
+if IO_DELAY_NONE
+config DEFAULT_IO_DELAY_TYPE
+	int
+	default IO_DELAY_TYPE_NONE
+endif
+
+config DEBUG_BOOT_PARAMS
+	bool "Debug boot parameters"
+	depends on DEBUG_KERNEL
+	depends on DEBUG_FS
+	---help---
+	  This option will cause struct boot_params to be exported via debugfs.
+
+config CPA_DEBUG
+	bool "CPA self-test code"
+	depends on DEBUG_KERNEL
+	---help---
+	  Do change_page_attr() self-tests every 30 seconds.
+
+config OPTIMIZE_INLINING
+	bool "Allow gcc to uninline functions marked 'inline'"
+	---help---
+	  This option determines if the kernel forces gcc to inline the functions
+	  developers have marked 'inline'. Doing so takes away freedom from gcc to
+	  do what it thinks is best, which is desirable for the gcc 3.x series of
+	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
+	  enabling this option will generate a smaller kernel there. Hopefully
+	  this algorithm is so good that allowing gcc 4.x and above to make the
+	  decision will become the default in the future. Until then this option
+	  is there to test gcc for this.
+
+	  If unsure, say N.
+
+config DEBUG_NMI_SELFTEST
+	bool "NMI Selftest"
+	depends on DEBUG_KERNEL && X86_LOCAL_APIC
+	---help---
+	  Enabling this option turns on a quick NMI selftest to verify
+	  that the NMI behaves correctly.
+
+	  This might help diagnose strange hangs that rely on NMI to
+	  function properly.
+
+	  If unsure, say N.
+
+config X86_DEBUG_STATIC_CPU_HAS
+	bool "Debug alternatives"
+	depends on DEBUG_KERNEL
+	---help---
+	  This option causes additional code to be generated which
+	  fails if static_cpu_has() is used before alternatives have
+	  run.
+
+	  If unsure, say N.
+
+endmenu

arch/x86/Makefile

@@ -0,0 +1,265 @@
+# Unified Makefile for i386 and x86_64
+
+# select defconfig based on actual architecture
+ifeq ($(ARCH),x86)
+  ifeq ($(shell uname -m),x86_64)
+        KBUILD_DEFCONFIG := x86_64_defconfig
+  else
+        KBUILD_DEFCONFIG := i386_defconfig
+  endif
+else
+        KBUILD_DEFCONFIG := $(ARCH)_defconfig
+endif
+
+# How to compile the 16-bit code.  Note we always compile for -march=i386;
+# that way we can complain to the user if the CPU is insufficient.
+#
+# The -m16 option is supported by GCC >= 4.9 and clang >= 3.5. For
+# older versions of GCC, include an *assembly* header to make sure that
+# gcc doesn't play any games behind our back.
+CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h
+M16_CFLAGS	 := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))
+
+REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -D__KERNEL__ \
+		   -DDISABLE_BRANCH_PROFILING \
+		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
+		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
+		   -mno-mmx -mno-sse \
+		   $(call cc-option, -ffreestanding) \
+		   $(call cc-option, -fno-stack-protector) \
+		   $(call cc-option, -mpreferred-stack-boundary=2)
+export REALMODE_CFLAGS
+
+# BITS is used as extension for files which are available in a 32 bit
+# and a 64 bit version to simplify shared Makefiles.
+# e.g.: obj-y += foo_$(BITS).o
+export BITS
+
+ifdef CONFIG_X86_NEED_RELOCS
+        LDFLAGS_vmlinux := --emit-relocs
+endif
+
+ifeq ($(CONFIG_X86_32),y)
+        BITS := 32
+        UTS_MACHINE := i386
+        CHECKFLAGS += -D__i386__
+
+        biarch := $(call cc-option,-m32)
+        KBUILD_AFLAGS += $(biarch)
+        KBUILD_CFLAGS += $(biarch)
+
+        KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
+
+        # Never want PIC in a 32-bit kernel, prevent breakage with GCC built
+        # with nonstandard options
+        KBUILD_CFLAGS += -fno-pic
+
+        # prevent gcc from keeping the stack 16 byte aligned
+        KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2)
+
+        # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
+        # a lot more stack due to the lack of sharing of stacklots:
+        KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \
+				$(call cc-option,-fno-unit-at-a-time))
+
+        # CPU-specific tuning. Anything which can be shared with UML should go here.
+        include $(srctree)/arch/x86/Makefile_32.cpu
+        KBUILD_CFLAGS += $(cflags-y)
+
+        # temporary until string.h is fixed
+        KBUILD_CFLAGS += -ffreestanding
+else
+        BITS := 64
+        UTS_MACHINE := x86_64
+        CHECKFLAGS += -D__x86_64__ -m64
+
+        biarch := -m64
+        KBUILD_AFLAGS += -m64
+        KBUILD_CFLAGS += -m64
+
+        # Don't autogenerate traditional x87 instructions
+        KBUILD_CFLAGS += $(call cc-option,-mno-80387)
+        KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
+
+	# Use -mpreferred-stack-boundary=3 if supported.
+	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
+
+        # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
+        cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
+        cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
+
+        cflags-$(CONFIG_MCORE2) += \
+                $(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
+	cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
+		$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
+        cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
+        KBUILD_CFLAGS += $(cflags-y)
+
+        KBUILD_CFLAGS += -mno-red-zone
+        KBUILD_CFLAGS += -mcmodel=kernel
+
+        # -funit-at-a-time shrinks the kernel .text considerably
+        # unfortunately it makes reading oopses harder.
+        KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
+
+        # this works around some issues with generating unwind tables in older gccs
+        # newer gccs do it by default
+        KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args)
+endif
+
+# Make sure compiler does not have buggy stack-protector support.
+ifdef CONFIG_CC_STACKPROTECTOR
+	cc_has_sp := $(srctree)/scripts/gcc-x86_$(BITS)-has-stack-protector.sh
+        ifneq ($(shell $(CONFIG_SHELL) $(cc_has_sp) $(CC) $(KBUILD_CPPFLAGS) $(biarch)),y)
+                $(warning stack-protector enabled but compiler support broken)
+        endif
+endif
+
+ifdef CONFIG_X86_X32
+	x32_ld_ok := $(call try-run,\
+			/bin/echo -e '1: .quad 1b' | \
+			$(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" - && \
+			$(OBJCOPY) -O elf32-x86-64 "$$TMP" "$$TMPO" && \
+			$(LD) -m elf32_x86_64 "$$TMPO" -o "$$TMP",y,n)
+        ifeq ($(x32_ld_ok),y)
+                CONFIG_X86_X32_ABI := y
+                KBUILD_AFLAGS += -DCONFIG_X86_X32_ABI
+                KBUILD_CFLAGS += -DCONFIG_X86_X32_ABI
+        else
+                $(warning CONFIG_X86_X32 enabled but no binutils support)
+        endif
+endif
+export CONFIG_X86_X32_ABI
+
+# Don't unroll struct assignments with kmemcheck enabled
+ifeq ($(CONFIG_KMEMCHECK),y)
+	KBUILD_CFLAGS += $(call cc-option,-fno-builtin-memcpy)
+endif
+
+# Stackpointer is addressed different for 32 bit and 64 bit x86
+sp-$(CONFIG_X86_32) := esp
+sp-$(CONFIG_X86_64) := rsp
+
+# do binutils support CFI?
+cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
+# is .cfi_signal_frame supported too?
+cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
+cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
+
+# does binutils support specific instructions?
+asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
+avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
+avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
+
+KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+
+LDFLAGS := -m elf_$(UTS_MACHINE)
+
+# Speed up the build
+KBUILD_CFLAGS += -pipe
+# Workaround for a gcc prelease that unfortunately was shipped in a suse release
+KBUILD_CFLAGS += -Wno-sign-compare
+#
+KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
+# prevent gcc from generating any FP code by mistake
+KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
+
+KBUILD_CFLAGS += $(mflags-y)
+KBUILD_AFLAGS += $(mflags-y)
+
+archscripts: scripts_basic
+	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
+
+###
+# Syscall table generation
+
+archheaders:
+	$(Q)$(MAKE) $(build)=arch/x86/syscalls all
+
+archprepare:
+ifeq ($(CONFIG_KEXEC_FILE),y)
+	$(Q)$(MAKE) $(build)=arch/x86/purgatory arch/x86/purgatory/kexec-purgatory.c
+endif
+
+###
+# Kernel objects
+
+head-y := arch/x86/kernel/head_$(BITS).o
+head-y += arch/x86/kernel/head$(BITS).o
+head-y += arch/x86/kernel/head.o
+
+libs-y  += arch/x86/lib/
+
+# See arch/x86/Kbuild for content of core part of the kernel
+core-y += arch/x86/
+
+# drivers-y are linked after core-y
+drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
+drivers-$(CONFIG_PCI)            += arch/x86/pci/
+
+# must be linked after kernel/
+drivers-$(CONFIG_OPROFILE) += arch/x86/oprofile/
+
+# suspend and hibernation support
+drivers-$(CONFIG_PM) += arch/x86/power/
+
+drivers-$(CONFIG_FB) += arch/x86/video/
+
+####
+# boot loader support. Several targets are kept for legacy purposes
+
+boot := arch/x86/boot
+
+BOOT_TARGETS = bzlilo bzdisk fdimage fdimage144 fdimage288 isoimage
+
+PHONY += bzImage $(BOOT_TARGETS)
+
+# Default kernel to build
+all: bzImage
+
+# KBUILD_IMAGE specify target image being built
+KBUILD_IMAGE := $(boot)/bzImage
+
+bzImage: vmlinux
+ifeq ($(CONFIG_X86_DECODER_SELFTEST),y)
+	$(Q)$(MAKE) $(build)=arch/x86/tools posttest
+endif
+	$(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE)
+	$(Q)mkdir -p $(objtree)/arch/$(UTS_MACHINE)/boot
+	$(Q)ln -fsn ../../x86/boot/bzImage $(objtree)/arch/$(UTS_MACHINE)/boot/$@
+
+$(BOOT_TARGETS): vmlinux
+	$(Q)$(MAKE) $(build)=$(boot) $@
+
+PHONY += install
+install:
+	$(Q)$(MAKE) $(build)=$(boot) $@
+
+PHONY += vdso_install
+vdso_install:
+	$(Q)$(MAKE) $(build)=arch/x86/vdso $@
+
+archclean:
+	$(Q)rm -rf $(objtree)/arch/i386
+	$(Q)rm -rf $(objtree)/arch/x86_64
+	$(Q)$(MAKE) $(clean)=$(boot)
+	$(Q)$(MAKE) $(clean)=arch/x86/tools
+	$(Q)$(MAKE) $(clean)=arch/x86/purgatory
+
+define archhelp
+  echo  '* bzImage      - Compressed kernel image (arch/x86/boot/bzImage)'
+  echo  '  install      - Install kernel using'
+  echo  '                  (your) ~/bin/$(INSTALLKERNEL) or'
+  echo  '                  (distribution) /sbin/$(INSTALLKERNEL) or'
+  echo  '                  install to $$(INSTALL_PATH) and run lilo'
+  echo  '  fdimage      - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
+  echo  '  fdimage144   - Create 1.4MB boot floppy image (arch/x86/boot/fdimage)'
+  echo  '  fdimage288   - Create 2.8MB boot floppy image (arch/x86/boot/fdimage)'
+  echo  '  isoimage     - Create a boot CD-ROM image (arch/x86/boot/image.iso)'
+  echo  '                  bzdisk/fdimage*/isoimage also accept:'
+  echo  '                  FDARGS="..."  arguments for the booted kernel'
+  echo  '                  FDINITRD=file initrd for the booted kernel'
+endef

arch/x86/Makefile.um

@@ -0,0 +1,60 @@
+core-y += arch/x86/crypto/
+
+ifeq ($(CONFIG_X86_32),y)
+START := 0x8048000
+
+LDFLAGS			+= -m elf_i386
+ELF_ARCH		:= i386
+ELF_FORMAT 		:= elf32-i386
+CHECKFLAGS	+= -D__i386__
+
+KBUILD_CFLAGS		+= $(call cc-option,-m32)
+KBUILD_AFLAGS		+= $(call cc-option,-m32)
+LINK-y			+= $(call cc-option,-m32)
+
+export LDFLAGS
+
+LDS_EXTRA		:= -Ui386
+export LDS_EXTRA
+
+# First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y.
+include $(srctree)/arch/x86/Makefile_32.cpu
+
+# prevent gcc from keeping the stack 16 byte aligned. Taken from i386.
+cflags-y += $(call cc-option,-mpreferred-stack-boundary=2)
+
+# Prevent sprintf in nfsd from being converted to strcpy and resulting in
+# an unresolved reference.
+cflags-y += -ffreestanding
+
+# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
+# a lot more stack due to the lack of sharing of stacklots.  Also, gcc
+# 4.3.0 needs -funit-at-a-time for extern inline functions.
+KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then \
+			echo $(call cc-option,-fno-unit-at-a-time); \
+			else echo $(call cc-option,-funit-at-a-time); fi ;)
+
+KBUILD_CFLAGS += $(cflags-y)
+
+else
+
+START := 0x60000000
+
+KBUILD_CFLAGS += -fno-builtin -m64 
+
+CHECKFLAGS  += -m64 -D__x86_64__
+KBUILD_AFLAGS += -m64
+LDFLAGS += -m elf_x86_64
+KBUILD_CPPFLAGS += -m64
+
+ELF_ARCH := i386:x86-64
+ELF_FORMAT := elf64-x86-64
+
+# Not on all 64-bit distros /lib is a symlink to /lib64. PLD is an example.
+
+LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
+LINK-y += -m64
+
+# Do unit-at-a-time unconditionally on x86_64, following the host
+KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)
+endif

arch/x86/Makefile_32.cpu

@@ -0,0 +1,70 @@
+# CPU tuning section - shared with UML.
+# Must change only cflags-y (or [yn]), not CFLAGS! That makes a difference for UML.
+
+#-mtune exists since gcc 3.4
+HAS_MTUNE	:= $(call cc-option-yn, -mtune=i386)
+ifeq ($(HAS_MTUNE),y)
+tune		= $(call cc-option,-mtune=$(1),$(2))
+else
+tune		= $(call cc-option,-mcpu=$(1),$(2))
+endif
+
+align := $(cc-option-align)
+cflags-$(CONFIG_M486)		+= -march=i486
+cflags-$(CONFIG_M586)		+= -march=i586
+cflags-$(CONFIG_M586TSC)	+= -march=i586
+cflags-$(CONFIG_M586MMX)	+= -march=pentium-mmx
+cflags-$(CONFIG_M686)		+= -march=i686
+cflags-$(CONFIG_MPENTIUMII)	+= -march=i686 $(call tune,pentium2)
+cflags-$(CONFIG_MPENTIUMIII)	+= -march=i686 $(call tune,pentium3)
+cflags-$(CONFIG_MPENTIUMM)	+= -march=i686 $(call tune,pentium3)
+cflags-$(CONFIG_MPENTIUM4)	+= -march=i686 $(call tune,pentium4)
+cflags-$(CONFIG_MK6)		+= -march=k6
+# Please note, that patches that add -march=athlon-xp and friends are pointless.
+# They make zero difference whatsosever to performance at this time.
+cflags-$(CONFIG_MK7)		+= -march=athlon
+cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
+cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
+cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
+cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
+cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
+cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
+cflags-$(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))
+
+# AMD Elan support
+cflags-$(CONFIG_MELAN)		+= -march=i486
+
+# Geode GX1 support
+cflags-$(CONFIG_MGEODEGX1)	+= -march=pentium-mmx
+cflags-$(CONFIG_MGEODE_LX)	+= $(call cc-option,-march=geode,-march=pentium-mmx)
+# add at the end to overwrite eventual tuning options from earlier
+# cpu entries
+cflags-$(CONFIG_X86_GENERIC) 	+= $(call tune,generic,$(call tune,i686))
+
+# Work around the pentium-mmx code generator madness of gcc4.4.x which
+# does stack alignment by generating horrible code _before_ the mcount
+# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph
+# tracer assumptions. For i686, generic, core2 this is set by the
+# compiler anyway
+ifeq ($(CONFIG_FUNCTION_GRAPH_TRACER), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+# Work around to a bug with asm goto with first implementations of it
+# in gcc causing gcc to mess up the push and pop of the stack in some
+# uses of asm goto.
+ifeq ($(CONFIG_JUMP_LABEL), y)
+ADD_ACCUMULATE_OUTGOING_ARGS := y
+endif
+
+cflags-$(ADD_ACCUMULATE_OUTGOING_ARGS) += $(call cc-option,-maccumulate-outgoing-args)
+
+# Bug fix for binutils: this option is required in order to keep
+# binutils from generating NOPL instructions against our will.
+ifneq ($(CONFIG_X86_P6_NOP),y)
+cflags-y			+= $(call cc-option,-Wa$(comma)-mtune=generic32,)
+endif

arch/x86/boot/Makefile

@@ -0,0 +1,187 @@
+#
+# arch/x86/boot/Makefile
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1994 by Linus Torvalds
+# Changed by many, many contributors over the years.
+#
+
+# If you want to preset the SVGA mode, uncomment the next line and
+# set SVGA_MODE to whatever number you want.
+# Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode.
+# The number is the same as you would ordinarily press at bootup.
+
+SVGA_MODE	:= -DSVGA_MODE=NORMAL_VGA
+
+targets		:= vmlinux.bin setup.bin setup.elf bzImage
+targets		+= fdimage fdimage144 fdimage288 image.iso mtools.conf
+subdir-		:= compressed
+
+setup-y		+= a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o
+setup-y		+= early_serial_console.o edd.o header.o main.o mca.o memory.o
+setup-y		+= pm.o pmjump.o printf.o regs.o string.o tty.o video.o
+setup-y		+= video-mode.o version.o
+setup-$(CONFIG_X86_APM_BOOT) += apm.o
+
+# The link order of the video-*.o modules can matter.  In particular,
+# video-vga.o *must* be listed first, followed by video-vesa.o.
+# Hardware-specific drivers should follow in the order they should be
+# probed, and video-bios.o should typically be last.
+setup-y		+= video-vga.o
+setup-y		+= video-vesa.o
+setup-y		+= video-bios.o
+
+targets		+= $(setup-y)
+hostprogs-y	:= tools/build
+hostprogs-$(CONFIG_X86_FEATURE_NAMES) += mkcpustr
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include \
+		    -include include/generated/autoconf.h \
+	            -D__EXPORTED_HEADERS__
+
+ifdef CONFIG_X86_FEATURE_NAMES
+$(obj)/cpu.o: $(obj)/cpustr.h
+
+quiet_cmd_cpustr = CPUSTR  $@
+      cmd_cpustr = $(obj)/mkcpustr > $@
+targets += cpustr.h
+$(obj)/cpustr.h: $(obj)/mkcpustr FORCE
+	$(call if_changed,cpustr)
+endif
+clean-files += cpustr.h
+
+# ---------------------------------------------------------------------------
+
+KBUILD_CFLAGS	:= $(USERINCLUDE) $(REALMODE_CFLAGS) -D_SETUP
+KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
+GCOV_PROFILE := n
+
+$(obj)/bzImage: asflags-y  := $(SVGA_MODE)
+
+quiet_cmd_image = BUILD   $@
+cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
+			       $(obj)/zoffset.h $@
+
+$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
+	$(call if_changed,image)
+	@echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
+
+OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S
+$(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,objcopy)
+
+SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
+
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
+
+quiet_cmd_voffset = VOFFSET $@
+      cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
+
+targets += voffset.h
+$(obj)/voffset.h: vmlinux FORCE
+	$(call if_changed,voffset)
+
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+
+quiet_cmd_zoffset = ZOFFSET $@
+      cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
+
+targets += zoffset.h
+$(obj)/zoffset.h: $(obj)/compressed/vmlinux FORCE
+	$(call if_changed,zoffset)
+
+
+AFLAGS_header.o += -I$(obj)
+$(obj)/header.o: $(obj)/voffset.h $(obj)/zoffset.h
+
+LDFLAGS_setup.elf	:= -T
+$(obj)/setup.elf: $(src)/setup.ld $(SETUP_OBJS) FORCE
+	$(call if_changed,ld)
+
+OBJCOPYFLAGS_setup.bin	:= -O binary
+$(obj)/setup.bin: $(obj)/setup.elf FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/compressed/vmlinux: FORCE
+	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
+
+# Set this if you want to pass append arguments to the
+# bzdisk/fdimage/isoimage kernel
+FDARGS =
+# Set this if you want an initrd included with the
+# bzdisk/fdimage/isoimage kernel
+FDINITRD =
+
+image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,)
+
+$(obj)/mtools.conf: $(src)/mtools.conf.in
+	sed -e 's|@OBJ@|$(obj)|g' < $< > $@
+
+# This requires write access to /dev/fd0
+bzdisk: $(obj)/bzImage $(obj)/mtools.conf
+	MTOOLSRC=$(obj)/mtools.conf mformat a:			; sync
+	syslinux /dev/fd0					; sync
+	echo '$(image_cmdline)' | \
+		MTOOLSRC=$(src)/mtools.conf mcopy - a:syslinux.cfg
+	if [ -f '$(FDINITRD)' ] ; then \
+		MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \
+	fi
+	MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage a:linux	; sync
+
+# These require being root or having syslinux 2.02 or higher installed
+fdimage fdimage144: $(obj)/bzImage $(obj)/mtools.conf
+	dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440
+	MTOOLSRC=$(obj)/mtools.conf mformat v:			; sync
+	syslinux $(obj)/fdimage					; sync
+	echo '$(image_cmdline)' | \
+		MTOOLSRC=$(obj)/mtools.conf mcopy - v:syslinux.cfg
+	if [ -f '$(FDINITRD)' ] ; then \
+		MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \
+	fi
+	MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage v:linux	; sync
+
+fdimage288: $(obj)/bzImage $(obj)/mtools.conf
+	dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880
+	MTOOLSRC=$(obj)/mtools.conf mformat w:			; sync
+	syslinux $(obj)/fdimage					; sync
+	echo '$(image_cmdline)' | \
+		MTOOLSRC=$(obj)/mtools.conf mcopy - w:syslinux.cfg
+	if [ -f '$(FDINITRD)' ] ; then \
+		MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \
+	fi
+	MTOOLSRC=$(obj)/mtools.conf mcopy $(obj)/bzImage w:linux	; sync
+
+isoimage: $(obj)/bzImage
+	-rm -rf $(obj)/isoimage
+	mkdir $(obj)/isoimage
+	for i in lib lib64 share end ; do \
+		if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \
+			cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \
+			break ; \
+		fi ; \
+		if [ $$i = end ] ; then exit 1 ; fi ; \
+	done
+	cp $(obj)/bzImage $(obj)/isoimage/linux
+	echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg
+	if [ -f '$(FDINITRD)' ] ; then \
+		cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \
+	fi
+	mkisofs -J -r -o $(obj)/image.iso -b isolinux.bin -c boot.cat \
+		-no-emul-boot -boot-load-size 4 -boot-info-table \
+		$(obj)/isoimage
+	isohybrid $(obj)/image.iso 2>/dev/null || true
+	rm -rf $(obj)/isoimage
+
+bzlilo: $(obj)/bzImage
+	if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi
+	if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi
+	cat $(obj)/bzImage > $(INSTALL_PATH)/vmlinuz
+	cp System.map $(INSTALL_PATH)/
+	if [ -x /sbin/lilo ]; then /sbin/lilo; else /etc/lilo/install; fi
+
+install:
+	sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
+		System.map "$(INSTALL_PATH)"

arch/x86/boot/a20.c

@@ -0,0 +1,165 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Enable A20 gate (return -1 on failure)
+ */
+
+#include "boot.h"
+
+#define MAX_8042_LOOPS	100000
+#define MAX_8042_FF	32
+
+static int empty_8042(void)
+{
+	u8 status;
+	int loops = MAX_8042_LOOPS;
+	int ffs   = MAX_8042_FF;
+
+	while (loops--) {
+		io_delay();
+
+		status = inb(0x64);
+		if (status == 0xff) {
+			/* FF is a plausible, but very unlikely status */
+			if (!--ffs)
+				return -1; /* Assume no KBC present */
+		}
+		if (status & 1) {
+			/* Read and discard input data */
+			io_delay();
+			(void)inb(0x60);
+		} else if (!(status & 2)) {
+			/* Buffers empty, finished! */
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+/* Returns nonzero if the A20 line is enabled.  The memory address
+   used as a test is the int $0x80 vector, which should be safe. */
+
+#define A20_TEST_ADDR	(4*0x80)
+#define A20_TEST_SHORT  32
+#define A20_TEST_LONG	2097152	/* 2^21 */
+
+static int a20_test(int loops)
+{
+	int ok = 0;
+	int saved, ctr;
+
+	set_fs(0x0000);
+	set_gs(0xffff);
+
+	saved = ctr = rdfs32(A20_TEST_ADDR);
+
+	while (loops--) {
+		wrfs32(++ctr, A20_TEST_ADDR);
+		io_delay();	/* Serialize and make delay constant */
+		ok = rdgs32(A20_TEST_ADDR+0x10) ^ ctr;
+		if (ok)
+			break;
+	}
+
+	wrfs32(saved, A20_TEST_ADDR);
+	return ok;
+}
+
+/* Quick test to see if A20 is already enabled */
+static int a20_test_short(void)
+{
+	return a20_test(A20_TEST_SHORT);
+}
+
+/* Longer test that actually waits for A20 to come on line; this
+   is useful when dealing with the KBC or other slow external circuitry. */
+static int a20_test_long(void)
+{
+	return a20_test(A20_TEST_LONG);
+}
+
+static void enable_a20_bios(void)
+{
+	struct biosregs ireg;
+
+	initregs(&ireg);
+	ireg.ax = 0x2401;
+	intcall(0x15, &ireg, NULL);
+}
+
+static void enable_a20_kbc(void)
+{
+	empty_8042();
+
+	outb(0xd1, 0x64);	/* Command write */
+	empty_8042();
+
+	outb(0xdf, 0x60);	/* A20 on */
+	empty_8042();
+
+	outb(0xff, 0x64);	/* Null command, but UHCI wants it */
+	empty_8042();
+}
+
+static void enable_a20_fast(void)
+{
+	u8 port_a;
+
+	port_a = inb(0x92);	/* Configuration port A */
+	port_a |=  0x02;	/* Enable A20 */
+	port_a &= ~0x01;	/* Do not reset machine */
+	outb(port_a, 0x92);
+}
+
+/*
+ * Actual routine to enable A20; return 0 on ok, -1 on failure
+ */
+
+#define A20_ENABLE_LOOPS 255	/* Number of times to try */
+
+int enable_a20(void)
+{
+       int loops = A20_ENABLE_LOOPS;
+       int kbc_err;
+
+       while (loops--) {
+	       /* First, check to see if A20 is already enabled
+		  (legacy free, etc.) */
+	       if (a20_test_short())
+		       return 0;
+	       
+	       /* Next, try the BIOS (INT 0x15, AX=0x2401) */
+	       enable_a20_bios();
+	       if (a20_test_short())
+		       return 0;
+	       
+	       /* Try enabling A20 through the keyboard controller */
+	       kbc_err = empty_8042();
+
+	       if (a20_test_short())
+		       return 0; /* BIOS worked, but with delayed reaction */
+	
+	       if (!kbc_err) {
+		       enable_a20_kbc();
+		       if (a20_test_long())
+			       return 0;
+	       }
+	       
+	       /* Finally, try enabling the "fast A20 gate" */
+	       enable_a20_fast();
+	       if (a20_test_long())
+		       return 0;
+       }
+       
+       return -1;
+}

arch/x86/boot/apm.c

@@ -0,0 +1,75 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   Original APM BIOS checking by Stephen Rothwell, May 1994
+ *   (sfr@canb.auug.org.au)
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Get APM BIOS information
+ */
+
+#include "boot.h"
+
+int query_apm_bios(void)
+{
+	struct biosregs ireg, oreg;
+
+	/* APM BIOS installation check */
+	initregs(&ireg);
+	ireg.ah = 0x53;
+	intcall(0x15, &ireg, &oreg);
+
+	if (oreg.flags & X86_EFLAGS_CF)
+		return -1;		/* No APM BIOS */
+
+	if (oreg.bx != 0x504d)		/* "PM" signature */
+		return -1;
+
+	if (!(oreg.cx & 0x02))		/* 32 bits supported? */
+		return -1;
+
+	/* Disconnect first, just in case */
+	ireg.al = 0x04;
+	intcall(0x15, &ireg, NULL);
+
+	/* 32-bit connect */
+	ireg.al = 0x03;
+	intcall(0x15, &ireg, &oreg);
+
+	boot_params.apm_bios_info.cseg        = oreg.ax;
+	boot_params.apm_bios_info.offset      = oreg.ebx;
+	boot_params.apm_bios_info.cseg_16     = oreg.cx;
+	boot_params.apm_bios_info.dseg        = oreg.dx;
+	boot_params.apm_bios_info.cseg_len    = oreg.si;
+	boot_params.apm_bios_info.cseg_16_len = oreg.hsi;
+	boot_params.apm_bios_info.dseg_len    = oreg.di;
+
+	if (oreg.flags & X86_EFLAGS_CF)
+		return -1;
+
+	/* Redo the installation check as the 32-bit connect;
+	   some BIOSes return different flags this way... */
+
+	ireg.al = 0x00;
+	intcall(0x15, &ireg, &oreg);
+
+	if ((oreg.eflags & X86_EFLAGS_CF) || oreg.bx != 0x504d) {
+		/* Failure with 32-bit connect, try to disconect and ignore */
+		ireg.al = 0x04;
+		intcall(0x15, &ireg, NULL);
+		return -1;
+	}
+
+	boot_params.apm_bios_info.version = oreg.ax;
+	boot_params.apm_bios_info.flags   = oreg.cx;
+	return 0;
+}
+

arch/x86/boot/bioscall.S

@@ -0,0 +1,82 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2009-2014 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * "Glove box" for BIOS calls.  Avoids the constant problems with BIOSes
+ * touching registers they shouldn't be.
+ */
+
+	.code16
+	.section ".inittext","ax"
+	.globl	intcall
+	.type	intcall, @function
+intcall:
+	/* Self-modify the INT instruction.  Ugly, but works. */
+	cmpb	%al, 3f
+	je	1f
+	movb	%al, 3f
+	jmp	1f		/* Synchronize pipeline */
+1:
+	/* Save state */
+	pushfl
+	pushw	%fs
+	pushw	%gs
+	pushal
+
+	/* Copy input state to stack frame */
+	subw	$44, %sp
+	movw	%dx, %si
+	movw	%sp, %di
+	movw	$11, %cx
+	rep; movsd
+
+	/* Pop full state from the stack */
+	popal
+	popw	%gs
+	popw	%fs
+	popw	%es
+	popw	%ds
+	popfl
+
+	/* Actual INT */
+	.byte	0xcd		/* INT opcode */
+3:	.byte	0
+
+	/* Push full state to the stack */
+	pushfl
+	pushw	%ds
+	pushw	%es
+	pushw	%fs
+	pushw	%gs
+	pushal
+
+	/* Re-establish C environment invariants */
+	cld
+	movzwl	%sp, %esp
+	movw	%cs, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+
+	/* Copy output state from stack frame */
+	movw	68(%esp), %di	/* Original %cx == 3rd argument */
+	andw	%di, %di
+	jz	4f
+	movw	%sp, %si
+	movw	$11, %cx
+	rep; movsd
+4:	addw	$44, %sp
+
+	/* Restore state and return */
+	popal
+	popw	%gs
+	popw	%fs
+	popfl
+	retl
+	.size	intcall, .-intcall

arch/x86/boot/bitops.h

@@ -0,0 +1,43 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Very simple bitops for the boot code.
+ */
+
+#ifndef BOOT_BITOPS_H
+#define BOOT_BITOPS_H
+#define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
+
+static inline int constant_test_bit(int nr, const void *addr)
+{
+	const u32 *p = (const u32 *)addr;
+	return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0;
+}
+static inline int variable_test_bit(int nr, const void *addr)
+{
+	u8 v;
+	const u32 *p = (const u32 *)addr;
+
+	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
+	return v;
+}
+
+#define test_bit(nr,addr) \
+(__builtin_constant_p(nr) ? \
+ constant_test_bit((nr),(addr)) : \
+ variable_test_bit((nr),(addr)))
+
+static inline void set_bit(int nr, void *addr)
+{
+	asm("btsl %1,%0" : "+m" (*(u32 *)addr) : "Ir" (nr));
+}
+
+#endif /* BOOT_BITOPS_H */

arch/x86/boot/boot.h

@@ -0,0 +1,359 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Header file for the real-mode kernel code
+ */
+
+#ifndef BOOT_BOOT_H
+#define BOOT_BOOT_H
+
+#define STACK_SIZE	512	/* Minimum number of bytes for stack */
+
+#ifndef __ASSEMBLY__
+
+#include <stdarg.h>
+#include <linux/types.h>
+#include <linux/edd.h>
+#include <asm/boot.h>
+#include <asm/setup.h>
+#include "bitops.h"
+#include "ctype.h"
+#include "cpuflags.h"
+
+/* Useful macros */
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
+
+extern struct setup_header hdr;
+extern struct boot_params boot_params;
+
+#define cpu_relax()	asm volatile("rep; nop")
+
+/* Basic port I/O */
+static inline void outb(u8 v, u16 port)
+{
+	asm volatile("outb %0,%1" : : "a" (v), "dN" (port));
+}
+static inline u8 inb(u16 port)
+{
+	u8 v;
+	asm volatile("inb %1,%0" : "=a" (v) : "dN" (port));
+	return v;
+}
+
+static inline void outw(u16 v, u16 port)
+{
+	asm volatile("outw %0,%1" : : "a" (v), "dN" (port));
+}
+static inline u16 inw(u16 port)
+{
+	u16 v;
+	asm volatile("inw %1,%0" : "=a" (v) : "dN" (port));
+	return v;
+}
+
+static inline void outl(u32 v, u16 port)
+{
+	asm volatile("outl %0,%1" : : "a" (v), "dN" (port));
+}
+static inline u32 inl(u16 port)
+{
+	u32 v;
+	asm volatile("inl %1,%0" : "=a" (v) : "dN" (port));
+	return v;
+}
+
+static inline void io_delay(void)
+{
+	const u16 DELAY_PORT = 0x80;
+	asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT));
+}
+
+/* These functions are used to reference data in other segments. */
+
+static inline u16 ds(void)
+{
+	u16 seg;
+	asm("movw %%ds,%0" : "=rm" (seg));
+	return seg;
+}
+
+static inline void set_fs(u16 seg)
+{
+	asm volatile("movw %0,%%fs" : : "rm" (seg));
+}
+static inline u16 fs(void)
+{
+	u16 seg;
+	asm volatile("movw %%fs,%0" : "=rm" (seg));
+	return seg;
+}
+
+static inline void set_gs(u16 seg)
+{
+	asm volatile("movw %0,%%gs" : : "rm" (seg));
+}
+static inline u16 gs(void)
+{
+	u16 seg;
+	asm volatile("movw %%gs,%0" : "=rm" (seg));
+	return seg;
+}
+
+typedef unsigned int addr_t;
+
+static inline u8 rdfs8(addr_t addr)
+{
+	u8 v;
+	asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+	return v;
+}
+static inline u16 rdfs16(addr_t addr)
+{
+	u16 v;
+	asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr));
+	return v;
+}
+static inline u32 rdfs32(addr_t addr)
+{
+	u32 v;
+	asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr));
+	return v;
+}
+
+static inline void wrfs8(u8 v, addr_t addr)
+{
+	asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
+}
+static inline void wrfs16(u16 v, addr_t addr)
+{
+	asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
+}
+static inline void wrfs32(u32 v, addr_t addr)
+{
+	asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
+}
+
+static inline u8 rdgs8(addr_t addr)
+{
+	u8 v;
+	asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
+	return v;
+}
+static inline u16 rdgs16(addr_t addr)
+{
+	u16 v;
+	asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr));
+	return v;
+}
+static inline u32 rdgs32(addr_t addr)
+{
+	u32 v;
+	asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr));
+	return v;
+}
+
+static inline void wrgs8(u8 v, addr_t addr)
+{
+	asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
+}
+static inline void wrgs16(u16 v, addr_t addr)
+{
+	asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
+}
+static inline void wrgs32(u32 v, addr_t addr)
+{
+	asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
+}
+
+/* Note: these only return true/false, not a signed return value! */
+static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
+{
+	u8 diff;
+	asm volatile("fs; repe; cmpsb; setnz %0"
+		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	return diff;
+}
+static inline int memcmp_gs(const void *s1, addr_t s2, size_t len)
+{
+	u8 diff;
+	asm volatile("gs; repe; cmpsb; setnz %0"
+		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	return diff;
+}
+
+/* Heap -- available for dynamic lists. */
+extern char _end[];
+extern char *HEAP;
+extern char *heap_end;
+#define RESET_HEAP() ((void *)( HEAP = _end ))
+static inline char *__get_heap(size_t s, size_t a, size_t n)
+{
+	char *tmp;
+
+	HEAP = (char *)(((size_t)HEAP+(a-1)) & ~(a-1));
+	tmp = HEAP;
+	HEAP += s*n;
+	return tmp;
+}
+#define GET_HEAP(type, n) \
+	((type *)__get_heap(sizeof(type),__alignof__(type),(n)))
+
+static inline bool heap_free(size_t n)
+{
+	return (int)(heap_end-HEAP) >= (int)n;
+}
+
+/* copy.S */
+
+void copy_to_fs(addr_t dst, void *src, size_t len);
+void *copy_from_fs(void *dst, addr_t src, size_t len);
+void copy_to_gs(addr_t dst, void *src, size_t len);
+void *copy_from_gs(void *dst, addr_t src, size_t len);
+
+/* a20.c */
+int enable_a20(void);
+
+/* apm.c */
+int query_apm_bios(void);
+
+/* bioscall.c */
+struct biosregs {
+	union {
+		struct {
+			u32 edi;
+			u32 esi;
+			u32 ebp;
+			u32 _esp;
+			u32 ebx;
+			u32 edx;
+			u32 ecx;
+			u32 eax;
+			u32 _fsgs;
+			u32 _dses;
+			u32 eflags;
+		};
+		struct {
+			u16 di, hdi;
+			u16 si, hsi;
+			u16 bp, hbp;
+			u16 _sp, _hsp;
+			u16 bx, hbx;
+			u16 dx, hdx;
+			u16 cx, hcx;
+			u16 ax, hax;
+			u16 gs, fs;
+			u16 es, ds;
+			u16 flags, hflags;
+		};
+		struct {
+			u8 dil, dih, edi2, edi3;
+			u8 sil, sih, esi2, esi3;
+			u8 bpl, bph, ebp2, ebp3;
+			u8 _spl, _sph, _esp2, _esp3;
+			u8 bl, bh, ebx2, ebx3;
+			u8 dl, dh, edx2, edx3;
+			u8 cl, ch, ecx2, ecx3;
+			u8 al, ah, eax2, eax3;
+		};
+	};
+};
+void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg);
+
+/* cmdline.c */
+int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *buffer, int bufsize);
+int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option);
+static inline int cmdline_find_option(const char *option, char *buffer, int bufsize)
+{
+	unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
+
+	if (cmd_line_ptr >= 0x100000)
+		return -1;      /* inaccessible */
+
+	return __cmdline_find_option(cmd_line_ptr, option, buffer, bufsize);
+}
+
+static inline int cmdline_find_option_bool(const char *option)
+{
+	unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
+
+	if (cmd_line_ptr >= 0x100000)
+		return -1;      /* inaccessible */
+
+	return __cmdline_find_option_bool(cmd_line_ptr, option);
+}
+
+/* cpu.c, cpucheck.c */
+int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
+int validate_cpu(void);
+
+/* early_serial_console.c */
+extern int early_serial_base;
+void console_init(void);
+
+/* edd.c */
+void query_edd(void);
+
+/* header.S */
+void __attribute__((noreturn)) die(void);
+
+/* mca.c */
+int query_mca(void);
+
+/* memory.c */
+int detect_memory(void);
+
+/* pm.c */
+void __attribute__((noreturn)) go_to_protected_mode(void);
+
+/* pmjump.S */
+void __attribute__((noreturn))
+	protected_mode_jump(u32 entrypoint, u32 bootparams);
+
+/* printf.c */
+int sprintf(char *buf, const char *fmt, ...);
+int vsprintf(char *buf, const char *fmt, va_list args);
+int printf(const char *fmt, ...);
+
+/* regs.c */
+void initregs(struct biosregs *regs);
+
+/* string.c */
+int strcmp(const char *str1, const char *str2);
+int strncmp(const char *cs, const char *ct, size_t count);
+size_t strnlen(const char *s, size_t maxlen);
+unsigned int atou(const char *s);
+unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
+size_t strlen(const char *s);
+
+/* tty.c */
+void puts(const char *);
+void putchar(int);
+int getchar(void);
+void kbd_flush(void);
+int getchar_timeout(void);
+
+/* video.c */
+void set_video(void);
+
+/* video-mode.c */
+int set_mode(u16 mode);
+int mode_defined(u16 mode);
+void probe_cards(int unsafe);
+
+/* video-vesa.c */
+void vesa_store_edid(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* BOOT_BOOT_H */

arch/x86/boot/cmdline.c

@@ -0,0 +1,158 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Simple command-line parser for early boot.
+ */
+
+#include "boot.h"
+
+static inline int myisspace(u8 c)
+{
+	return c <= ' ';	/* Close enough approximation */
+}
+
+/*
+ * Find a non-boolean option, that is, "option=argument".  In accordance
+ * with standard Linux practice, if this option is repeated, this returns
+ * the last instance on the command line.
+ *
+ * Returns the length of the argument (regardless of if it was
+ * truncated to fit in the buffer), or -1 on not found.
+ */
+int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *buffer, int bufsize)
+{
+	addr_t cptr;
+	char c;
+	int len = -1;
+	const char *opptr = NULL;
+	char *bufptr = buffer;
+	enum {
+		st_wordstart,	/* Start of word/after whitespace */
+		st_wordcmp,	/* Comparing this word */
+		st_wordskip,	/* Miscompare, skip */
+		st_bufcpy	/* Copying this to buffer */
+	} state = st_wordstart;
+
+	if (!cmdline_ptr)
+		return -1;      /* No command line */
+
+	cptr = cmdline_ptr & 0xf;
+	set_fs(cmdline_ptr >> 4);
+
+	while (cptr < 0x10000 && (c = rdfs8(cptr++))) {
+		switch (state) {
+		case st_wordstart:
+			if (myisspace(c))
+				break;
+
+			/* else */
+			state = st_wordcmp;
+			opptr = option;
+			/* fall through */
+
+		case st_wordcmp:
+			if (c == '=' && !*opptr) {
+				len = 0;
+				bufptr = buffer;
+				state = st_bufcpy;
+			} else if (myisspace(c)) {
+				state = st_wordstart;
+			} else if (c != *opptr++) {
+				state = st_wordskip;
+			}
+			break;
+
+		case st_wordskip:
+			if (myisspace(c))
+				state = st_wordstart;
+			break;
+
+		case st_bufcpy:
+			if (myisspace(c)) {
+				state = st_wordstart;
+			} else {
+				if (len < bufsize-1)
+					*bufptr++ = c;
+				len++;
+			}
+			break;
+		}
+	}
+
+	if (bufsize)
+		*bufptr = '\0';
+
+	return len;
+}
+
+/*
+ * Find a boolean option (like quiet,noapic,nosmp....)
+ *
+ * Returns the position of that option (starts counting with 1)
+ * or 0 on not found
+ */
+int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option)
+{
+	addr_t cptr;
+	char c;
+	int pos = 0, wstart = 0;
+	const char *opptr = NULL;
+	enum {
+		st_wordstart,	/* Start of word/after whitespace */
+		st_wordcmp,	/* Comparing this word */
+		st_wordskip,	/* Miscompare, skip */
+	} state = st_wordstart;
+
+	if (!cmdline_ptr)
+		return -1;      /* No command line */
+
+	cptr = cmdline_ptr & 0xf;
+	set_fs(cmdline_ptr >> 4);
+
+	while (cptr < 0x10000) {
+		c = rdfs8(cptr++);
+		pos++;
+
+		switch (state) {
+		case st_wordstart:
+			if (!c)
+				return 0;
+			else if (myisspace(c))
+				break;
+
+			state = st_wordcmp;
+			opptr = option;
+			wstart = pos;
+			/* fall through */
+
+		case st_wordcmp:
+			if (!*opptr)
+				if (!c || myisspace(c))
+					return wstart;
+				else
+					state = st_wordskip;
+			else if (!c)
+				return 0;
+			else if (c != *opptr++)
+				state = st_wordskip;
+			break;
+
+		case st_wordskip:
+			if (!c)
+				return 0;
+			else if (myisspace(c))
+				state = st_wordstart;
+			break;
+		}
+	}
+
+	return 0;	/* Buffer overrun */
+}

arch/x86/boot/code16gcc.h

@@ -0,0 +1,11 @@
+#
+# code16gcc.h
+#
+# This file is added to the assembler via -Wa when compiling 16-bit C code.
+# This is done this way instead via asm() to make sure gcc does not reorder
+# things around us.
+#
+# gcc 4.9+ has a real -m16 option so we can drop this hack long term.
+#
+
+	.code16gcc

arch/x86/boot/compressed/Makefile

@@ -0,0 +1,87 @@
+#
+# linux/arch/x86/boot/compressed/Makefile
+#
+# create a compressed vmlinux image from the original vmlinux
+#
+
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
+	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
+
+KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
+KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+cflags-$(CONFIG_X86_32) := -march=i386
+cflags-$(CONFIG_X86_64) := -mcmodel=small
+KBUILD_CFLAGS += $(cflags-y)
+KBUILD_CFLAGS += -mno-mmx -mno-sse
+KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
+
+KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
+GCOV_PROFILE := n
+
+LDFLAGS := -m elf_$(UTS_MACHINE)
+LDFLAGS_vmlinux := -T
+
+hostprogs-y	:= mkpiggy
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include
+
+vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
+	$(obj)/string.o $(obj)/cmdline.o \
+	$(obj)/piggy.o $(obj)/cpuflags.o
+
+vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
+vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o
+
+$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
+
+vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
+
+$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+	$(call if_changed,ld)
+	@:
+
+OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objcopy)
+
+targets += $(patsubst $(obj)/%,%,$(vmlinux-objs-y)) vmlinux.bin.all vmlinux.relocs
+
+CMD_RELOCS = arch/x86/tools/relocs
+quiet_cmd_relocs = RELOCS  $@
+      cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $<
+$(obj)/vmlinux.relocs: vmlinux FORCE
+	$(call if_changed,relocs)
+
+vmlinux.bin.all-y := $(obj)/vmlinux.bin
+vmlinux.bin.all-$(CONFIG_X86_NEED_RELOCS) += $(obj)/vmlinux.relocs
+
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,gzip)
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,bzip2)
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,lzma)
+$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,xzkern)
+$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,lzo)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,lz4)
+
+suffix-$(CONFIG_KERNEL_GZIP)	:= gz
+suffix-$(CONFIG_KERNEL_BZIP2)	:= bz2
+suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
+suffix-$(CONFIG_KERNEL_XZ)	:= xz
+suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
+suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
+
+RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
+	     $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh)
+quiet_cmd_mkpiggy = MKPIGGY $@
+      cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
+
+targets += piggy.S
+$(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
+	$(call if_changed,mkpiggy)

arch/x86/boot/compressed/aslr.c

@@ -0,0 +1,336 @@
+#include "misc.h"
+
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+#include <asm/e820.h>
+
+#include <generated/compile.h>
+#include <linux/module.h>
+#include <linux/uts.h>
+#include <linux/utsname.h>
+#include <generated/utsrelease.h>
+
+/* Simplified build-specific string for starting entropy. */
+static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
+		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+
+#define I8254_PORT_CONTROL	0x43
+#define I8254_PORT_COUNTER0	0x40
+#define I8254_CMD_READBACK	0xC0
+#define I8254_SELECT_COUNTER0	0x02
+#define I8254_STATUS_NOTREADY	0x40
+static inline u16 i8254(void)
+{
+	u16 status, timer;
+
+	do {
+		outb(I8254_PORT_CONTROL,
+		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		status = inb(I8254_PORT_COUNTER0);
+		timer  = inb(I8254_PORT_COUNTER0);
+		timer |= inb(I8254_PORT_COUNTER0) << 8;
+	} while (status & I8254_STATUS_NOTREADY);
+
+	return timer;
+}
+
+static unsigned long rotate_xor(unsigned long hash, const void *area,
+				size_t size)
+{
+	size_t i;
+	unsigned long *ptr = (unsigned long *)area;
+
+	for (i = 0; i < size / sizeof(hash); i++) {
+		/* Rotate by odd number of bits and XOR. */
+		hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7);
+		hash ^= ptr[i];
+	}
+
+	return hash;
+}
+
+/* Attempt to create a simple but unpredictable starting entropy. */
+static unsigned long get_random_boot(void)
+{
+	unsigned long hash = 0;
+
+	hash = rotate_xor(hash, build_str, sizeof(build_str));
+	hash = rotate_xor(hash, real_mode, sizeof(*real_mode));
+
+	return hash;
+}
+
+static unsigned long get_random_long(void)
+{
+#ifdef CONFIG_X86_64
+	const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+	const unsigned long mix_const = 0x3f39e593UL;
+#endif
+	unsigned long raw, random = get_random_boot();
+	bool use_i8254 = true;
+
+	debug_putstr("KASLR using");
+
+	if (has_cpuflag(X86_FEATURE_RDRAND)) {
+		debug_putstr(" RDRAND");
+		if (rdrand_long(&raw)) {
+			random ^= raw;
+			use_i8254 = false;
+		}
+	}
+
+	if (has_cpuflag(X86_FEATURE_TSC)) {
+		debug_putstr(" RDTSC");
+		rdtscll(raw);
+
+		random ^= raw;
+		use_i8254 = false;
+	}
+
+	if (use_i8254) {
+		debug_putstr(" i8254");
+		random ^= i8254();
+	}
+
+	/* Circular multiply for better bit diffusion */
+	asm("mul %3"
+	    : "=a" (random), "=d" (raw)
+	    : "a" (random), "rm" (mix_const));
+	random += raw;
+
+	debug_putstr("...\n");
+
+	return random;
+}
+
+struct mem_vector {
+	unsigned long start;
+	unsigned long size;
+};
+
+#define MEM_AVOID_MAX 5
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
+
+static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
+{
+	/* Item at least partially before region. */
+	if (item->start < region->start)
+		return false;
+	/* Item at least partially after region. */
+	if (item->start + item->size > region->start + region->size)
+		return false;
+	return true;
+}
+
+static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
+{
+	/* Item one is entirely before item two. */
+	if (one->start + one->size <= two->start)
+		return false;
+	/* Item one is entirely after item two. */
+	if (one->start >= two->start + two->size)
+		return false;
+	return true;
+}
+
+static void mem_avoid_init(unsigned long input, unsigned long input_size,
+			   unsigned long output, unsigned long output_size)
+{
+	u64 initrd_start, initrd_size;
+	u64 cmd_line, cmd_line_size;
+	unsigned long unsafe, unsafe_len;
+	char *ptr;
+
+	/*
+	 * Avoid the region that is unsafe to overlap during
+	 * decompression (see calculations at top of misc.c).
+	 */
+	unsafe_len = (output_size >> 12) + 32768 + 18;
+	unsafe = (unsigned long)input + input_size - unsafe_len;
+	mem_avoid[0].start = unsafe;
+	mem_avoid[0].size = unsafe_len;
+
+	/* Avoid initrd. */
+	initrd_start  = (u64)real_mode->ext_ramdisk_image << 32;
+	initrd_start |= real_mode->hdr.ramdisk_image;
+	initrd_size  = (u64)real_mode->ext_ramdisk_size << 32;
+	initrd_size |= real_mode->hdr.ramdisk_size;
+	mem_avoid[1].start = initrd_start;
+	mem_avoid[1].size = initrd_size;
+
+	/* Avoid kernel command line. */
+	cmd_line  = (u64)real_mode->ext_cmd_line_ptr << 32;
+	cmd_line |= real_mode->hdr.cmd_line_ptr;
+	/* Calculate size of cmd_line. */
+	ptr = (char *)(unsigned long)cmd_line;
+	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+		;
+	mem_avoid[2].start = cmd_line;
+	mem_avoid[2].size = cmd_line_size;
+
+	/* Avoid heap memory. */
+	mem_avoid[3].start = (unsigned long)free_mem_ptr;
+	mem_avoid[3].size = BOOT_HEAP_SIZE;
+
+	/* Avoid stack memory. */
+	mem_avoid[4].start = (unsigned long)free_mem_end_ptr;
+	mem_avoid[4].size = BOOT_STACK_SIZE;
+}
+
+/* Does this memory vector overlap a known avoided area? */
+static bool mem_avoid_overlap(struct mem_vector *img)
+{
+	int i;
+	struct setup_data *ptr;
+
+	for (i = 0; i < MEM_AVOID_MAX; i++) {
+		if (mem_overlaps(img, &mem_avoid[i]))
+			return true;
+	}
+
+	/* Avoid all entries in the setup_data linked list. */
+	ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data;
+	while (ptr) {
+		struct mem_vector avoid;
+
+		avoid.start = (unsigned long)ptr;
+		avoid.size = sizeof(*ptr) + ptr->len;
+
+		if (mem_overlaps(img, &avoid))
+			return true;
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
+	return false;
+}
+
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			   CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
+
+static void slots_append(unsigned long addr)
+{
+	/* Overflowing the slots list should be impossible. */
+	if (slot_max >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			CONFIG_PHYSICAL_ALIGN)
+		return;
+
+	slots[slot_max++] = addr;
+}
+
+static unsigned long slots_fetch_random(void)
+{
+	/* Handle case of no slots stored. */
+	if (slot_max == 0)
+		return 0;
+
+	return slots[get_random_long() % slot_max];
+}
+
+static void process_e820_entry(struct e820entry *entry,
+			       unsigned long minimum,
+			       unsigned long image_size)
+{
+	struct mem_vector region, img;
+
+	/* Skip non-RAM entries. */
+	if (entry->type != E820_RAM)
+		return;
+
+	/* Ignore entries entirely above our maximum. */
+	if (entry->addr >= CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		return;
+
+	/* Ignore entries entirely below our minimum. */
+	if (entry->addr + entry->size < minimum)
+		return;
+
+	region.start = entry->addr;
+	region.size = entry->size;
+
+	/* Potentially raise address to minimum location. */
+	if (region.start < minimum)
+		region.start = minimum;
+
+	/* Potentially raise address to meet alignment requirements. */
+	region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
+
+	/* Did we raise the address above the bounds of this e820 region? */
+	if (region.start > entry->addr + entry->size)
+		return;
+
+	/* Reduce size by any delta from the original address. */
+	region.size -= region.start - entry->addr;
+
+	/* Reduce maximum size to fit end of image within maximum limit. */
+	if (region.start + region.size > CONFIG_RANDOMIZE_BASE_MAX_OFFSET)
+		region.size = CONFIG_RANDOMIZE_BASE_MAX_OFFSET - region.start;
+
+	/* Walk each aligned slot and check for avoided areas. */
+	for (img.start = region.start, img.size = image_size ;
+	     mem_contains(&region, &img) ;
+	     img.start += CONFIG_PHYSICAL_ALIGN) {
+		if (mem_avoid_overlap(&img))
+			continue;
+		slots_append(img.start);
+	}
+}
+
+static unsigned long find_random_addr(unsigned long minimum,
+				      unsigned long size)
+{
+	int i;
+	unsigned long addr;
+
+	/* Make sure minimum is aligned. */
+	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+
+	/* Verify potential e820 positions, appending to slots list. */
+	for (i = 0; i < real_mode->e820_entries; i++) {
+		process_e820_entry(&real_mode->e820_map[i], minimum, size);
+	}
+
+	return slots_fetch_random();
+}
+
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	unsigned long choice = (unsigned long)output;
+	unsigned long random;
+
+#ifdef CONFIG_HIBERNATION
+	if (!cmdline_find_option_bool("kaslr")) {
+		debug_putstr("KASLR disabled by default...\n");
+		goto out;
+	}
+#else
+	if (cmdline_find_option_bool("nokaslr")) {
+		debug_putstr("KASLR disabled by cmdline...\n");
+		goto out;
+	}
+#endif
+
+	/* Record the various known unsafe memory ranges. */
+	mem_avoid_init((unsigned long)input, input_size,
+		       (unsigned long)output, output_size);
+
+	/* Walk e820 and find a random address. */
+	random = find_random_addr(choice, output_size);
+	if (!random) {
+		debug_putstr("KASLR could not find suitable E820 region...\n");
+		goto out;
+	}
+
+	/* Always enforce the minimum. */
+	if (random < choice)
+		goto out;
+
+	choice = random;
+out:
+	return (unsigned char *)choice;
+}

arch/x86/boot/compressed/cmdline.c

@@ -0,0 +1,33 @@
+#include "misc.h"
+
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
+
+static unsigned long fs;
+static inline void set_fs(unsigned long seg)
+{
+	fs = seg << 4;  /* shift it back */
+}
+typedef unsigned long addr_t;
+static inline char rdfs8(addr_t addr)
+{
+	return *((char *)(fs + addr));
+}
+#include "../cmdline.c"
+static unsigned long get_cmd_line_ptr(void)
+{
+	unsigned long cmd_line_ptr = real_mode->hdr.cmd_line_ptr;
+
+	cmd_line_ptr |= (u64)real_mode->ext_cmd_line_ptr << 32;
+
+	return cmd_line_ptr;
+}
+int cmdline_find_option(const char *option, char *buffer, int bufsize)
+{
+	return __cmdline_find_option(get_cmd_line_ptr(), option, buffer, bufsize);
+}
+int cmdline_find_option_bool(const char *option)
+{
+	return __cmdline_find_option_bool(get_cmd_line_ptr(), option);
+}
+
+#endif

arch/x86/boot/compressed/cpuflags.c

@@ -0,0 +1,12 @@
+#ifdef CONFIG_RANDOMIZE_BASE
+
+#include "../cpuflags.c"
+
+bool has_cpuflag(int flag)
+{
+	get_cpuflags();
+
+	return test_bit(flag, cpu.flags);
+}
+
+#endif

arch/x86/boot/compressed/early_serial_console.c

@@ -0,0 +1,5 @@
+#include "misc.h"
+
+int early_serial_base;
+
+#include "../early_serial_console.c"

arch/x86/boot/compressed/eboot.h

@@ -0,0 +1,122 @@
+#ifndef BOOT_COMPRESSED_EBOOT_H
+#define BOOT_COMPRESSED_EBOOT_H
+
+#define SEG_TYPE_DATA		(0 << 3)
+#define SEG_TYPE_READ_WRITE	(1 << 1)
+#define SEG_TYPE_CODE		(1 << 3)
+#define SEG_TYPE_EXEC_READ	(1 << 1)
+#define SEG_TYPE_TSS		((1 << 3) | (1 << 0))
+#define SEG_OP_SIZE_32BIT	(1 << 0)
+#define SEG_GRANULARITY_4KB	(1 << 0)
+
+#define DESC_TYPE_CODE_DATA	(1 << 0)
+
+#define EFI_CONSOLE_OUT_DEVICE_GUID    \
+	EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \
+		  0x3f, 0xc1, 0x4d)
+
+#define PIXEL_RGB_RESERVED_8BIT_PER_COLOR		0
+#define PIXEL_BGR_RESERVED_8BIT_PER_COLOR		1
+#define PIXEL_BIT_MASK					2
+#define PIXEL_BLT_ONLY					3
+#define PIXEL_FORMAT_MAX				4
+
+struct efi_pixel_bitmask {
+	u32 red_mask;
+	u32 green_mask;
+	u32 blue_mask;
+	u32 reserved_mask;
+};
+
+struct efi_graphics_output_mode_info {
+	u32 version;
+	u32 horizontal_resolution;
+	u32 vertical_resolution;
+	int pixel_format;
+	struct efi_pixel_bitmask pixel_information;
+	u32 pixels_per_scan_line;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_32 {
+	u32 max_mode;
+	u32 mode;
+	u32 info;
+	u32 size_of_info;
+	u64 frame_buffer_base;
+	u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+	u32 max_mode;
+	u32 mode;
+	u64 info;
+	u64 size_of_info;
+	u64 frame_buffer_base;
+	u64 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode {
+	u32 max_mode;
+	u32 mode;
+	unsigned long info;
+	unsigned long size_of_info;
+	u64 frame_buffer_base;
+	unsigned long frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_32 {
+	u32 query_mode;
+	u32 set_mode;
+	u32 blt;
+	u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+	u64 query_mode;
+	u64 set_mode;
+	u64 blt;
+	u64 mode;
+};
+
+struct efi_graphics_output_protocol {
+	void *query_mode;
+	unsigned long set_mode;
+	unsigned long blt;
+	struct efi_graphics_output_protocol_mode *mode;
+};
+
+struct efi_uga_draw_protocol_32 {
+	u32 get_mode;
+	u32 set_mode;
+	u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+	u64 get_mode;
+	u64 set_mode;
+	u64 blt;
+};
+
+struct efi_uga_draw_protocol {
+	void *get_mode;
+	void *set_mode;
+	void *blt;
+};
+
+struct efi_config {
+	u64 image_handle;
+	u64 table;
+	u64 allocate_pool;
+	u64 allocate_pages;
+	u64 get_memory_map;
+	u64 free_pool;
+	u64 free_pages;
+	u64 locate_handle;
+	u64 handle_protocol;
+	u64 exit_boot_services;
+	u64 text_output;
+	efi_status_t (*call)(unsigned long, ...);
+	bool is64;
+} __packed;
+
+#endif /* BOOT_COMPRESSED_EBOOT_H */

arch/x86/boot/compressed/efi_stub_32.S

@@ -0,0 +1,86 @@
+/*
+ * EFI call stub for IA32.
+ *
+ * This stub allows us to make EFI calls in physical mode with interrupts
+ * turned off. Note that this implementation is different from the one in
+ * arch/x86/platform/efi/efi_stub_32.S because we're _already_ in physical
+ * mode at this point.
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+/*
+ * efi_call_phys(void *, ...) is a function with variable parameters.
+ * All the callers of this function assure that all the parameters are 4-bytes.
+ */
+
+/*
+ * In gcc calling convention, EBX, ESP, EBP, ESI and EDI are all callee save.
+ * So we'd better save all of them at the beginning of this function and restore
+ * at the end no matter how many we use, because we can not assure EFI runtime
+ * service functions will comply with gcc calling convention, too.
+ */
+
+.text
+ENTRY(efi_call_phys)
+	/*
+	 * 0. The function can only be called in Linux kernel. So CS has been
+	 * set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
+	 * the values of these registers are the same. And, the corresponding
+	 * GDT entries are identical. So I will do nothing about segment reg
+	 * and GDT, but change GDT base register in prelog and epilog.
+	 */
+
+	/*
+	 * 1. Because we haven't been relocated by this point we need to
+	 * use relative addressing.
+	 */
+	call	1f
+1:	popl	%edx
+	subl	$1b, %edx
+
+	/*
+	 * 2. Now on the top of stack is the return
+	 * address in the caller of efi_call_phys(), then parameter 1,
+	 * parameter 2, ..., param n. To make things easy, we save the return
+	 * address of efi_call_phys in a global variable.
+	 */
+	popl	%ecx
+	movl	%ecx, saved_return_addr(%edx)
+	/* get the function pointer into ECX*/
+	popl	%ecx
+	movl	%ecx, efi_rt_function_ptr(%edx)
+
+	/*
+	 * 3. Call the physical function.
+	 */
+	call	*%ecx
+
+	/*
+	 * 4. Balance the stack. And because EAX contain the return value,
+	 * we'd better not clobber it. We need to calculate our address
+	 * again because %ecx and %edx are not preserved across EFI function
+	 * calls.
+	 */
+	call	1f
+1:	popl	%edx
+	subl	$1b, %edx
+
+	movl	efi_rt_function_ptr(%edx), %ecx
+	pushl	%ecx
+
+	/*
+	 * 10. Push the saved return address onto the stack and return.
+	 */
+	movl	saved_return_addr(%edx), %ecx
+	pushl	%ecx
+	ret
+ENDPROC(efi_call_phys)
+.previous
+
+.data
+saved_return_addr:
+	.long 0
+efi_rt_function_ptr:
+	.long 0

arch/x86/boot/compressed/efi_stub_64.S

@@ -0,0 +1,5 @@
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+
+#include "../../platform/efi/efi_stub_64.S"

arch/x86/boot/compressed/efi_thunk_64.S

@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT before we make EFI serivce calls,
+ * since the firmware's 32-bit IDT is still currently installed and it
+ * needs to be able to service interrupts.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identify
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+	.code64
+	.text
+ENTRY(efi64_thunk)
+	push	%rbp
+	push	%rbx
+
+	subq	$8, %rsp
+	leaq	efi_exit32(%rip), %rax
+	movl	%eax, 4(%rsp)
+	leaq	efi_gdt64(%rip), %rax
+	movl	%eax, (%rsp)
+	movl	%eax, 2(%rax)		/* Fixup the gdt base address */
+
+	movl	%ds, %eax
+	push	%rax
+	movl	%es, %eax
+	push	%rax
+	movl	%ss, %eax
+	push	%rax
+
+	/*
+	 * Convert x86-64 ABI params to i386 ABI
+	 */
+	subq	$32, %rsp
+	movl	%esi, 0x0(%rsp)
+	movl	%edx, 0x4(%rsp)
+	movl	%ecx, 0x8(%rsp)
+	movq	%r8, %rsi
+	movl	%esi, 0xc(%rsp)
+	movq	%r9, %rsi
+	movl	%esi,  0x10(%rsp)
+
+	sgdt	save_gdt(%rip)
+
+	leaq	1f(%rip), %rbx
+	movq	%rbx, func_rt_ptr(%rip)
+
+	/*
+	 * Switch to gdt with 32-bit segments. This is the firmware GDT
+	 * that was installed when the kernel started executing. This
+	 * pointer was saved at the EFI stub entry point in head_64.S.
+	 */
+	leaq	efi32_boot_gdt(%rip), %rax
+	lgdt	(%rax)
+
+	pushq	$__KERNEL_CS
+	leaq	efi_enter32(%rip), %rax
+	pushq	%rax
+	lretq
+
+1:	addq	$32, %rsp
+
+	lgdt	save_gdt(%rip)
+
+	pop	%rbx
+	movl	%ebx, %ss
+	pop	%rbx
+	movl	%ebx, %es
+	pop	%rbx
+	movl	%ebx, %ds
+
+	/*
+	 * Convert 32-bit status code into 64-bit.
+	 */
+	test	%rax, %rax
+	jz	1f
+	movl	%eax, %ecx
+	andl	$0x0fffffff, %ecx
+	andl	$0xf0000000, %eax
+	shl	$32, %rax
+	or	%rcx, %rax
+1:
+	addq	$8, %rsp
+	pop	%rbx
+	pop	%rbp
+	ret
+ENDPROC(efi64_thunk)
+
+ENTRY(efi_exit32)
+	movq	func_rt_ptr(%rip), %rax
+	push	%rax
+	mov	%rdi, %rax
+	ret
+ENDPROC(efi_exit32)
+
+	.code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+	movl	$__KERNEL_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+
+	/* Reload pgtables */
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	/* Disable paging */
+	movl	%cr0, %eax
+	btrl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+
+	/* Disable long mode via EFER */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btrl	$_EFER_LME, %eax
+	wrmsr
+
+	call	*%edi
+
+	/* We must preserve return value */
+	movl	%eax, %edi
+
+	/*
+	 * Some firmware will return with interrupts enabled. Be sure to
+	 * disable them before we switch GDTs.
+	 */
+	cli
+
+	movl	56(%esp), %eax
+	movl	%eax, 2(%eax)
+	lgdtl	(%eax)
+
+	movl	%cr4, %eax
+	btsl	$(X86_CR4_PAE_BIT), %eax
+	movl	%eax, %cr4
+
+	movl	%cr3, %eax
+	movl	%eax, %cr3
+
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	xorl	%eax, %eax
+	lldt	%ax
+
+	movl	60(%esp), %eax
+	pushl	$__KERNEL_CS
+	pushl	%eax
+
+	/* Enable paging */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
+	movl	%eax, %cr0
+	lret
+ENDPROC(efi_enter32)
+
+	.data
+	.balign	8
+	.global	efi32_boot_gdt
+efi32_boot_gdt:	.word	0
+		.quad	0
+
+save_gdt:	.word	0
+		.quad	0
+func_rt_ptr:	.quad	0
+
+	.global efi_gdt64
+efi_gdt64:
+	.word	efi_gdt64_end - efi_gdt64
+	.long	0			/* Filled out by user */
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+	.quad	0x0080890000000000	/* TS descriptor */
+	.quad   0x0000000000000000	/* TS continued */
+efi_gdt64_end:

arch/x86/boot/compressed/head_32.S

@@ -0,0 +1,247 @@
+/*
+ *  linux/boot/head.S
+ *
+ *  Copyright (C) 1991, 1992, 1993  Linus Torvalds
+ */
+
+/*
+ *  head.S contains the 32-bit startup code.
+ *
+ * NOTE!!! Startup happens at absolute address 0x00001000, which is also where
+ * the page directory will exist. The startup code will be overwritten by
+ * the page directory. [According to comments etc elsewhere on a compressed
+ * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
+ *
+ * Page 0 is deliberately kept safe, since System Management Mode code in
+ * laptops may need to access the BIOS data stored there.  This is also
+ * useful for future device drivers that either access the BIOS via VM86
+ * mode.
+ */
+
+/*
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+	.text
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/page_types.h>
+#include <asm/boot.h>
+#include <asm/asm-offsets.h>
+
+	__HEAD
+ENTRY(startup_32)
+#ifdef CONFIG_EFI_STUB
+	jmp	preferred_addr
+
+	/*
+	 * We don't need the return address, so set up the stack so
+	 * efi_main() can find its arguments.
+	 */
+ENTRY(efi_pe_entry)
+	add	$0x4, %esp
+
+	call	1f
+1:	popl	%esi
+	subl	$1b, %esi
+
+	popl	%ecx
+	movl	%ecx, efi32_config(%esi)	/* Handle */
+	popl	%ecx
+	movl	%ecx, efi32_config+8(%esi)	/* EFI System table pointer */
+
+	/* Relocate efi_config->call() */
+	leal	efi32_config(%esi), %eax
+	add	%esi, 88(%eax)
+	pushl	%eax
+
+	call	make_boot_params
+	cmpl	$0, %eax
+	je	fail
+	movl	%esi, BP_code32_start(%eax)
+	popl	%ecx
+	pushl	%eax
+	pushl	%ecx
+	jmp	2f		/* Skip efi_config initialization */
+
+ENTRY(efi32_stub_entry)
+	add	$0x4, %esp
+	popl	%ecx
+	popl	%edx
+
+	call	1f
+1:	popl	%esi
+	subl	$1b, %esi
+
+	movl	%ecx, efi32_config(%esi)	/* Handle */
+	movl	%edx, efi32_config+8(%esi)	/* EFI System table pointer */
+
+	/* Relocate efi_config->call() */
+	leal	efi32_config(%esi), %eax
+	add	%esi, 88(%eax)
+	pushl	%eax
+2:
+	call	efi_main
+	cmpl	$0, %eax
+	movl	%eax, %esi
+	jne	2f
+fail:
+	/* EFI init failed, so hang. */
+	hlt
+	jmp	fail
+2:
+	movl	BP_code32_start(%esi), %eax
+	leal	preferred_addr(%eax), %eax
+	jmp	*%eax
+
+preferred_addr:
+#endif
+	cld
+	/*
+	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+	 * us to not reload segments
+	 */
+	testb	$(1<<6), BP_loadflags(%esi)
+	jnz	1f
+
+	cli
+	movl	$__BOOT_DS, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %fs
+	movl	%eax, %gs
+	movl	%eax, %ss
+1:
+
+/*
+ * Calculate the delta between where we were compiled to run
+ * at and where we were actually loaded at.  This can only be done
+ * with a short local call on x86.  Nothing  else will tell us what
+ * address we are running at.  The reserved chunk of the real-mode
+ * data at 0x1e4 (defined as a scratch field) are used as the stack
+ * for this calculation. Only 4 bytes are needed.
+ */
+	leal	(BP_scratch+4)(%esi), %esp
+	call	1f
+1:	popl	%ebp
+	subl	$1b, %ebp
+
+/*
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
+ * contains the address where we should move the kernel image temporarily
+ * for safe in-place decompression.
+ */
+
+#ifdef CONFIG_RELOCATABLE
+	movl	%ebp, %ebx
+	movl	BP_kernel_alignment(%esi), %eax
+	decl	%eax
+	addl    %eax, %ebx
+	notl	%eax
+	andl    %eax, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
+#endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
+
+	/* Target address to relocate to for decompression */
+	addl	$z_extract_offset, %ebx
+
+	/* Set up the stack */
+	leal	boot_stack_end(%ebx), %esp
+
+	/* Zero EFLAGS */
+	pushl	$0
+	popfl
+
+/*
+ * Copy the compressed kernel to the end of our buffer
+ * where decompression in place becomes safe.
+ */
+	pushl	%esi
+	leal	(_bss-4)(%ebp), %esi
+	leal	(_bss-4)(%ebx), %edi
+	movl	$(_bss - startup_32), %ecx
+	shrl	$2, %ecx
+	std
+	rep	movsl
+	cld
+	popl	%esi
+
+/*
+ * Jump to the relocated address.
+ */
+	leal	relocated(%ebx), %eax
+	jmp	*%eax
+ENDPROC(startup_32)
+
+	.text
+relocated:
+
+/*
+ * Clear BSS (stack is currently empty)
+ */
+	xorl	%eax, %eax
+	leal	_bss(%ebx), %edi
+	leal	_ebss(%ebx), %ecx
+	subl	%edi, %ecx
+	shrl	$2, %ecx
+	rep	stosl
+
+/*
+ * Adjust our own GOT
+ */
+	leal	_got(%ebx), %edx
+	leal	_egot(%ebx), %ecx
+1:
+	cmpl	%ecx, %edx
+	jae	2f
+	addl	%ebx, (%edx)
+	addl	$4, %edx
+	jmp	1b
+2:
+
+/*
+ * Do the decompression, and jump to the new kernel..
+ */
+				/* push arguments for decompress_kernel: */
+	pushl	$z_run_size	/* size of kernel with .bss and .brk */
+	pushl	$z_output_len	/* decompressed length, end of relocs */
+	leal	z_extract_offset_negative(%ebx), %ebp
+	pushl	%ebp		/* output address */
+	pushl	$z_input_len	/* input_len */
+	leal	input_data(%ebx), %eax
+	pushl	%eax		/* input_data */
+	leal	boot_heap(%ebx), %eax
+	pushl	%eax		/* heap area */
+	pushl	%esi		/* real mode pointer */
+	call	decompress_kernel /* returns kernel location in %eax */
+	addl	$28, %esp
+
+/*
+ * Jump to the decompressed kernel.
+ */
+	xorl	%ebx, %ebx
+	jmp	*%eax
+
+#ifdef CONFIG_EFI_STUB
+	.data
+efi32_config:
+	.fill 11,8,0
+	.long efi_call_phys
+	.long 0
+	.byte 0
+#endif
+
+/*
+ * Stack and heap for uncompression
+ */
+	.bss
+	.balign 4
+boot_heap:
+	.fill BOOT_HEAP_SIZE, 1, 0
+boot_stack:
+	.fill BOOT_STACK_SIZE, 1, 0
+boot_stack_end:

arch/x86/boot/compressed/head_64.S

@@ -0,0 +1,479 @@
+/*
+ *  linux/boot/head.S
+ *
+ *  Copyright (C) 1991, 1992, 1993  Linus Torvalds
+ */
+
+/*
+ *  head.S contains the 32-bit startup code.
+ *
+ * NOTE!!! Startup happens at absolute address 0x00001000, which is also where
+ * the page directory will exist. The startup code will be overwritten by
+ * the page directory. [According to comments etc elsewhere on a compressed
+ * kernel it will end up at 0x1000 + 1Mb I hope so as I assume this. - AC]
+ *
+ * Page 0 is deliberately kept safe, since System Management Mode code in 
+ * laptops may need to access the BIOS data stored there.  This is also
+ * useful for future device drivers that either access the BIOS via VM86 
+ * mode.
+ */
+
+/*
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+	.code32
+	.text
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/boot.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+#include <asm/asm-offsets.h>
+
+	__HEAD
+	.code32
+ENTRY(startup_32)
+	/*
+	 * 32bit entry is 0 and it is ABI so immutable!
+	 * If we come here directly from a bootloader,
+	 * kernel(text+data+bss+brk) ramdisk, zero_page, command line
+	 * all need to be under the 4G limit.
+	 */
+	cld
+	/*
+	 * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+	 * us to not reload segments
+	 */
+	testb $(1<<6), BP_loadflags(%esi)
+	jnz 1f
+
+	cli
+	movl	$(__BOOT_DS), %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+1:
+
+/*
+ * Calculate the delta between where we were compiled to run
+ * at and where we were actually loaded at.  This can only be done
+ * with a short local call on x86.  Nothing  else will tell us what
+ * address we are running at.  The reserved chunk of the real-mode
+ * data at 0x1e4 (defined as a scratch field) are used as the stack
+ * for this calculation. Only 4 bytes are needed.
+ */
+	leal	(BP_scratch+4)(%esi), %esp
+	call	1f
+1:	popl	%ebp
+	subl	$1b, %ebp
+
+/* setup a stack and make sure cpu supports long mode. */
+	movl	$boot_stack_end, %eax
+	addl	%ebp, %eax
+	movl	%eax, %esp
+
+	call	verify_cpu
+	testl	%eax, %eax
+	jnz	no_longmode
+
+/*
+ * Compute the delta between where we were compiled to run at
+ * and where the code will actually run at.
+ *
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
+ * contains the address where we should move the kernel image temporarily
+ * for safe in-place decompression.
+ */
+
+#ifdef CONFIG_RELOCATABLE
+	movl	%ebp, %ebx
+	movl	BP_kernel_alignment(%esi), %eax
+	decl	%eax
+	addl	%eax, %ebx
+	notl	%eax
+	andl	%eax, %ebx
+	cmpl	$LOAD_PHYSICAL_ADDR, %ebx
+	jge	1f
+#endif
+	movl	$LOAD_PHYSICAL_ADDR, %ebx
+1:
+
+	/* Target address to relocate to for decompression */
+	addl	$z_extract_offset, %ebx
+
+/*
+ * Prepare for entering 64 bit mode
+ */
+
+	/* Load new GDT with the 64bit segments using 32bit descriptor */
+	leal	gdt(%ebp), %eax
+	movl	%eax, gdt+2(%ebp)
+	lgdt	gdt(%ebp)
+
+	/* Enable PAE mode */
+	movl	%cr4, %eax
+	orl	$X86_CR4_PAE, %eax
+	movl	%eax, %cr4
+
+ /*
+  * Build early 4G boot pagetable
+  */
+	/* Initialize Page tables to 0 */
+	leal	pgtable(%ebx), %edi
+	xorl	%eax, %eax
+	movl	$((4096*6)/4), %ecx
+	rep	stosl
+
+	/* Build Level 4 */
+	leal	pgtable + 0(%ebx), %edi
+	leal	0x1007 (%edi), %eax
+	movl	%eax, 0(%edi)
+
+	/* Build Level 3 */
+	leal	pgtable + 0x1000(%ebx), %edi
+	leal	0x1007(%edi), %eax
+	movl	$4, %ecx
+1:	movl	%eax, 0x00(%edi)
+	addl	$0x00001000, %eax
+	addl	$8, %edi
+	decl	%ecx
+	jnz	1b
+
+	/* Build Level 2 */
+	leal	pgtable + 0x2000(%ebx), %edi
+	movl	$0x00000183, %eax
+	movl	$2048, %ecx
+1:	movl	%eax, 0(%edi)
+	addl	$0x00200000, %eax
+	addl	$8, %edi
+	decl	%ecx
+	jnz	1b
+
+	/* Enable the boot page tables */
+	leal	pgtable(%ebx), %eax
+	movl	%eax, %cr3
+
+	/* Enable Long mode in EFER (Extended Feature Enable Register) */
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+
+	/* After gdt is loaded */
+	xorl	%eax, %eax
+	lldt	%ax
+	movl    $0x20, %eax
+	ltr	%ax
+
+	/*
+	 * Setup for the jump to 64bit mode
+	 *
+	 * When the jump is performend we will be in long mode but
+	 * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
+	 * (and in turn EFER.LMA = 1).	To jump into 64bit mode we use
+	 * the new gdt/idt that has __KERNEL_CS with CS.L = 1.
+	 * We place all of the values on our mini stack so lret can
+	 * used to perform that far jump.
+	 */
+	pushl	$__KERNEL_CS
+	leal	startup_64(%ebp), %eax
+#ifdef CONFIG_EFI_MIXED
+	movl	efi32_config(%ebp), %ebx
+	cmp	$0, %ebx
+	jz	1f
+	leal	handover_entry(%ebp), %eax
+1:
+#endif
+	pushl	%eax
+
+	/* Enter paged protected Mode, activating Long Mode */
+	movl	$(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
+	movl	%eax, %cr0
+
+	/* Jump from 32bit compatibility mode into 64bit mode. */
+	lret
+ENDPROC(startup_32)
+
+#ifdef CONFIG_EFI_MIXED
+	.org 0x190
+ENTRY(efi32_stub_entry)
+	add	$0x4, %esp		/* Discard return address */
+	popl	%ecx
+	popl	%edx
+	popl	%esi
+
+	leal	(BP_scratch+4)(%esi), %esp
+	call	1f
+1:	pop	%ebp
+	subl	$1b, %ebp
+
+	movl	%ecx, efi32_config(%ebp)
+	movl	%edx, efi32_config+8(%ebp)
+	sgdtl	efi32_boot_gdt(%ebp)
+
+	leal	efi32_config(%ebp), %eax
+	movl	%eax, efi_config(%ebp)
+
+	jmp	startup_32
+ENDPROC(efi32_stub_entry)
+#endif
+
+	.code64
+	.org 0x200
+ENTRY(startup_64)
+	/*
+	 * 64bit entry is 0x200 and it is ABI so immutable!
+	 * We come here either from startup_32 or directly from a
+	 * 64bit bootloader.
+	 * If we come here from a bootloader, kernel(text+data+bss+brk),
+	 * ramdisk, zero_page, command line could be above 4G.
+	 * We depend on an identity mapped page table being provided
+	 * that maps our entire kernel(text+data+bss+brk), zero page
+	 * and command line.
+	 */
+#ifdef CONFIG_EFI_STUB
+	/*
+	 * The entry point for the PE/COFF executable is efi_pe_entry, so
+	 * only legacy boot loaders will execute this jmp.
+	 */
+	jmp	preferred_addr
+
+ENTRY(efi_pe_entry)
+	movq	%rcx, efi64_config(%rip)	/* Handle */
+	movq	%rdx, efi64_config+8(%rip) /* EFI System table pointer */
+
+	leaq	efi64_config(%rip), %rax
+	movq	%rax, efi_config(%rip)
+
+	call	1f
+1:	popq	%rbp
+	subq	$1b, %rbp
+
+	/*
+	 * Relocate efi_config->call().
+	 */
+	addq	%rbp, efi64_config+88(%rip)
+
+	movq	%rax, %rdi
+	call	make_boot_params
+	cmpq	$0,%rax
+	je	fail
+	mov	%rax, %rsi
+	leaq	startup_32(%rip), %rax
+	movl	%eax, BP_code32_start(%rsi)
+	jmp	2f		/* Skip the relocation */
+
+handover_entry:
+	call	1f
+1:	popq	%rbp
+	subq	$1b, %rbp
+
+	/*
+	 * Relocate efi_config->call().
+	 */
+	movq	efi_config(%rip), %rax
+	addq	%rbp, 88(%rax)
+2:
+	movq	efi_config(%rip), %rdi
+	call	efi_main
+	movq	%rax,%rsi
+	cmpq	$0,%rax
+	jne	2f
+fail:
+	/* EFI init failed, so hang. */
+	hlt
+	jmp	fail
+2:
+	movl	BP_code32_start(%esi), %eax
+	leaq	preferred_addr(%rax), %rax
+	jmp	*%rax
+
+preferred_addr:
+#endif
+
+	/* Setup data segments. */
+	xorl	%eax, %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	%eax, %ss
+	movl	%eax, %fs
+	movl	%eax, %gs
+
+	/*
+	 * Compute the decompressed kernel start address.  It is where
+	 * we were loaded at aligned to a 2M boundary. %rbp contains the
+	 * decompressed kernel start address.
+	 *
+	 * If it is a relocatable kernel then decompress and run the kernel
+	 * from load address aligned to 2MB addr, otherwise decompress and
+	 * run the kernel from LOAD_PHYSICAL_ADDR
+	 *
+	 * We cannot rely on the calculation done in 32-bit mode, since we
+	 * may have been invoked via the 64-bit entry point.
+	 */
+
+	/* Start with the delta to where the kernel will run at. */
+#ifdef CONFIG_RELOCATABLE
+	leaq	startup_32(%rip) /* - $startup_32 */, %rbp
+	movl	BP_kernel_alignment(%rsi), %eax
+	decl	%eax
+	addq	%rax, %rbp
+	notq	%rax
+	andq	%rax, %rbp
+	cmpq	$LOAD_PHYSICAL_ADDR, %rbp
+	jge	1f
+#endif
+	movq	$LOAD_PHYSICAL_ADDR, %rbp
+1:
+
+	/* Target address to relocate to for decompression */
+	leaq	z_extract_offset(%rbp), %rbx
+
+	/* Set up the stack */
+	leaq	boot_stack_end(%rbx), %rsp
+
+	/* Zero EFLAGS */
+	pushq	$0
+	popfq
+
+/*
+ * Copy the compressed kernel to the end of our buffer
+ * where decompression in place becomes safe.
+ */
+	pushq	%rsi
+	leaq	(_bss-8)(%rip), %rsi
+	leaq	(_bss-8)(%rbx), %rdi
+	movq	$_bss /* - $startup_32 */, %rcx
+	shrq	$3, %rcx
+	std
+	rep	movsq
+	cld
+	popq	%rsi
+
+/*
+ * Jump to the relocated address.
+ */
+	leaq	relocated(%rbx), %rax
+	jmp	*%rax
+
+#ifdef CONFIG_EFI_STUB
+	.org 0x390
+ENTRY(efi64_stub_entry)
+	movq	%rdi, efi64_config(%rip)	/* Handle */
+	movq	%rsi, efi64_config+8(%rip) /* EFI System table pointer */
+
+	leaq	efi64_config(%rip), %rax
+	movq	%rax, efi_config(%rip)
+
+	movq	%rdx, %rsi
+	jmp	handover_entry
+ENDPROC(efi64_stub_entry)
+#endif
+
+	.text
+relocated:
+
+/*
+ * Clear BSS (stack is currently empty)
+ */
+	xorl	%eax, %eax
+	leaq    _bss(%rip), %rdi
+	leaq    _ebss(%rip), %rcx
+	subq	%rdi, %rcx
+	shrq	$3, %rcx
+	rep	stosq
+
+/*
+ * Adjust our own GOT
+ */
+	leaq	_got(%rip), %rdx
+	leaq	_egot(%rip), %rcx
+1:
+	cmpq	%rcx, %rdx
+	jae	2f
+	addq	%rbx, (%rdx)
+	addq	$8, %rdx
+	jmp	1b
+2:
+	
+/*
+ * Do the decompression, and jump to the new kernel..
+ */
+	pushq	%rsi			/* Save the real mode argument */
+	movq	$z_run_size, %r9	/* size of kernel with .bss and .brk */
+	pushq	%r9
+	movq	%rsi, %rdi		/* real mode address */
+	leaq	boot_heap(%rip), %rsi	/* malloc area for uncompression */
+	leaq	input_data(%rip), %rdx  /* input_data */
+	movl	$z_input_len, %ecx	/* input_len */
+	movq	%rbp, %r8		/* output target address */
+	movq	$z_output_len, %r9	/* decompressed length, end of relocs */
+	call	decompress_kernel	/* returns kernel location in %rax */
+	popq	%r9
+	popq	%rsi
+
+/*
+ * Jump to the decompressed kernel.
+ */
+	jmp	*%rax
+
+	.code32
+no_longmode:
+	/* This isn't an x86-64 CPU so hang */
+1:
+	hlt
+	jmp     1b
+
+#include "../../kernel/verify_cpu.S"
+
+	.data
+gdt:
+	.word	gdt_end - gdt
+	.long	gdt
+	.word	0
+	.quad	0x0000000000000000	/* NULL descriptor */
+	.quad	0x00af9a000000ffff	/* __KERNEL_CS */
+	.quad	0x00cf92000000ffff	/* __KERNEL_DS */
+	.quad	0x0080890000000000	/* TS descriptor */
+	.quad   0x0000000000000000	/* TS continued */
+gdt_end:
+
+#ifdef CONFIG_EFI_STUB
+efi_config:
+	.quad	0
+
+#ifdef CONFIG_EFI_MIXED
+	.global efi32_config
+efi32_config:
+	.fill	11,8,0
+	.quad	efi64_thunk
+	.byte	0
+#endif
+
+	.global efi64_config
+efi64_config:
+	.fill	11,8,0
+	.quad	efi_call
+	.byte	1
+#endif /* CONFIG_EFI_STUB */
+
+/*
+ * Stack and heap for uncompression
+ */
+	.bss
+	.balign 4
+boot_heap:
+	.fill BOOT_HEAP_SIZE, 1, 0
+boot_stack:
+	.fill BOOT_STACK_SIZE, 1, 0
+boot_stack_end:
+
+/*
+ * Space for page tables (not in .bss so not zeroed)
+ */
+	.section ".pgtable","a",@nobits
+	.balign 4096
+pgtable:
+	.fill 6*4096, 1, 0

arch/x86/boot/compressed/misc.c

@@ -0,0 +1,422 @@
+/*
+ * misc.c
+ *
+ * This is a collection of several routines from gzip-1.0.3
+ * adapted for Linux.
+ *
+ * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ * puts by Nick Holloway 1993, better puts by Martin Mares 1995
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ */
+
+#include "misc.h"
+#include "../string.h"
+
+/* WARNING!!
+ * This code is compiled with -fPIC and it is relocated dynamically
+ * at run time, but no relocation processing is performed.
+ * This means that it is not safe to place pointers in static structures.
+ */
+
+/*
+ * Getting to provable safe in place decompression is hard.
+ * Worst case behaviours need to be analyzed.
+ * Background information:
+ *
+ * The file layout is:
+ *    magic[2]
+ *    method[1]
+ *    flags[1]
+ *    timestamp[4]
+ *    extraflags[1]
+ *    os[1]
+ *    compressed data blocks[N]
+ *    crc[4] orig_len[4]
+ *
+ * resulting in 18 bytes of non compressed data overhead.
+ *
+ * Files divided into blocks
+ * 1 bit (last block flag)
+ * 2 bits (block type)
+ *
+ * 1 block occurs every 32K -1 bytes or when there 50% compression
+ * has been achieved. The smallest block type encoding is always used.
+ *
+ * stored:
+ *    32 bits length in bytes.
+ *
+ * fixed:
+ *    magic fixed tree.
+ *    symbols.
+ *
+ * dynamic:
+ *    dynamic tree encoding.
+ *    symbols.
+ *
+ *
+ * The buffer for decompression in place is the length of the
+ * uncompressed data, plus a small amount extra to keep the algorithm safe.
+ * The compressed data is placed at the end of the buffer.  The output
+ * pointer is placed at the start of the buffer and the input pointer
+ * is placed where the compressed data starts.  Problems will occur
+ * when the output pointer overruns the input pointer.
+ *
+ * The output pointer can only overrun the input pointer if the input
+ * pointer is moving faster than the output pointer.  A condition only
+ * triggered by data whose compressed form is larger than the uncompressed
+ * form.
+ *
+ * The worst case at the block level is a growth of the compressed data
+ * of 5 bytes per 32767 bytes.
+ *
+ * The worst case internal to a compressed block is very hard to figure.
+ * The worst case can at least be boundined by having one bit that represents
+ * 32764 bytes and then all of the rest of the bytes representing the very
+ * very last byte.
+ *
+ * All of which is enough to compute an amount of extra data that is required
+ * to be safe.  To avoid problems at the block level allocating 5 extra bytes
+ * per 32767 bytes of data is sufficient.  To avoind problems internal to a
+ * block adding an extra 32767 bytes (the worst case uncompressed block size)
+ * is sufficient, to ensure that in the worst case the decompressed data for
+ * block will stop the byte before the compressed data for a block begins.
+ * To avoid problems with the compressed data's meta information an extra 18
+ * bytes are needed.  Leading to the formula:
+ *
+ * extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
+ *
+ * Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
+ * Adding 32768 instead of 32767 just makes for round numbers.
+ * Adding the decompressor_size is necessary as it musht live after all
+ * of the data as well.  Last I measured the decompressor is about 14K.
+ * 10K of actual data and 4K of bss.
+ *
+ */
+
+/*
+ * gzip declarations
+ */
+#define STATIC		static
+
+#undef memcpy
+
+/*
+ * Use a normal definition of memset() from string.c. There are already
+ * included header files which expect a definition of memset() and by
+ * the time we define memset macro, it is too late.
+ */
+#undef memset
+#define memzero(s, n)	memset((s), 0, (n))
+
+
+static void error(char *m);
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+struct boot_params *real_mode;		/* Pointer to real-mode data */
+
+memptr free_mem_ptr;
+memptr free_mem_end_ptr;
+
+static char *vidmem;
+static int vidport;
+static int lines, cols;
+
+#ifdef CONFIG_KERNEL_GZIP
+#include "../../../../lib/decompress_inflate.c"
+#endif
+
+#ifdef CONFIG_KERNEL_BZIP2
+#include "../../../../lib/decompress_bunzip2.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZMA
+#include "../../../../lib/decompress_unlzma.c"
+#endif
+
+#ifdef CONFIG_KERNEL_XZ
+#include "../../../../lib/decompress_unxz.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZO
+#include "../../../../lib/decompress_unlzo.c"
+#endif
+
+#ifdef CONFIG_KERNEL_LZ4
+#include "../../../../lib/decompress_unlz4.c"
+#endif
+
+static void scroll(void)
+{
+	int i;
+
+	memcpy(vidmem, vidmem + cols * 2, (lines - 1) * cols * 2);
+	for (i = (lines - 1) * cols * 2; i < lines * cols * 2; i += 2)
+		vidmem[i] = ' ';
+}
+
+#define XMTRDY          0x20
+
+#define TXR             0       /*  Transmit register (WRITE) */
+#define LSR             5       /*  Line Status               */
+static void serial_putchar(int ch)
+{
+	unsigned timeout = 0xffff;
+
+	while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout)
+		cpu_relax();
+
+	outb(ch, early_serial_base + TXR);
+}
+
+void __putstr(const char *s)
+{
+	int x, y, pos;
+	char c;
+
+	if (early_serial_base) {
+		const char *str = s;
+		while (*str) {
+			if (*str == '\n')
+				serial_putchar('\r');
+			serial_putchar(*str++);
+		}
+	}
+
+	if (real_mode->screen_info.orig_video_mode == 0 &&
+	    lines == 0 && cols == 0)
+		return;
+
+	x = real_mode->screen_info.orig_x;
+	y = real_mode->screen_info.orig_y;
+
+	while ((c = *s++) != '\0') {
+		if (c == '\n') {
+			x = 0;
+			if (++y >= lines) {
+				scroll();
+				y--;
+			}
+		} else {
+			vidmem[(x + cols * y) * 2] = c;
+			if (++x >= cols) {
+				x = 0;
+				if (++y >= lines) {
+					scroll();
+					y--;
+				}
+			}
+		}
+	}
+
+	real_mode->screen_info.orig_x = x;
+	real_mode->screen_info.orig_y = y;
+
+	pos = (x + cols * y) * 2;	/* Update cursor position */
+	outb(14, vidport);
+	outb(0xff & (pos >> 9), vidport+1);
+	outb(15, vidport);
+	outb(0xff & (pos >> 1), vidport+1);
+}
+
+static void error(char *x)
+{
+	error_putstr("\n\n");
+	error_putstr(x);
+	error_putstr("\n\n -- System halted");
+
+	while (1)
+		asm("hlt");
+}
+
+#if CONFIG_X86_NEED_RELOCS
+static void handle_relocations(void *output, unsigned long output_len)
+{
+	int *reloc;
+	unsigned long delta, map, ptr;
+	unsigned long min_addr = (unsigned long)output;
+	unsigned long max_addr = min_addr + output_len;
+
+	/*
+	 * Calculate the delta between where vmlinux was linked to load
+	 * and where it was actually loaded.
+	 */
+	delta = min_addr - LOAD_PHYSICAL_ADDR;
+	if (!delta) {
+		debug_putstr("No relocation needed... ");
+		return;
+	}
+	debug_putstr("Performing relocations... ");
+
+	/*
+	 * The kernel contains a table of relocation addresses. Those
+	 * addresses have the final load address of the kernel in virtual
+	 * memory. We are currently working in the self map. So we need to
+	 * create an adjustment for kernel memory addresses to the self map.
+	 * This will involve subtracting out the base address of the kernel.
+	 */
+	map = delta - __START_KERNEL_map;
+
+	/*
+	 * Process relocations: 32 bit relocations first then 64 bit after.
+	 * 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.
+	 *
+	 * Format is:
+	 *
+	 * kernel bits...
+	 * 0 - zero terminator for 64 bit relocations
+	 * 64 bit relocation repeated
+	 * 0 - zero terminator for 32 bit relocations
+	 * 32 bit relocation repeated
+	 *
+	 * So we work backwards from the end of the decompressed image.
+	 */
+	for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
+		int extended = *reloc;
+		extended += map;
+
+		ptr = (unsigned long)extended;
+		if (ptr < min_addr || ptr > max_addr)
+			error("32-bit relocation outside of kernel!\n");
+
+		*(uint32_t *)ptr += delta;
+	}
+#ifdef CONFIG_X86_64
+	for (reloc--; *reloc; reloc--) {
+		long extended = *reloc;
+		extended += map;
+
+		ptr = (unsigned long)extended;
+		if (ptr < min_addr || ptr > max_addr)
+			error("64-bit relocation outside of kernel!\n");
+
+		*(uint64_t *)ptr += delta;
+	}
+#endif
+}
+#else
+static inline void handle_relocations(void *output, unsigned long output_len)
+{ }
+#endif
+
+static void parse_elf(void *output)
+{
+#ifdef CONFIG_X86_64
+	Elf64_Ehdr ehdr;
+	Elf64_Phdr *phdrs, *phdr;
+#else
+	Elf32_Ehdr ehdr;
+	Elf32_Phdr *phdrs, *phdr;
+#endif
+	void *dest;
+	int i;
+
+	memcpy(&ehdr, output, sizeof(ehdr));
+	if (ehdr.e_ident[EI_MAG0] != ELFMAG0 ||
+	   ehdr.e_ident[EI_MAG1] != ELFMAG1 ||
+	   ehdr.e_ident[EI_MAG2] != ELFMAG2 ||
+	   ehdr.e_ident[EI_MAG3] != ELFMAG3) {
+		error("Kernel is not a valid ELF file");
+		return;
+	}
+
+	debug_putstr("Parsing ELF... ");
+
+	phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum);
+	if (!phdrs)
+		error("Failed to allocate space for phdrs");
+
+	memcpy(phdrs, output + ehdr.e_phoff, sizeof(*phdrs) * ehdr.e_phnum);
+
+	for (i = 0; i < ehdr.e_phnum; i++) {
+		phdr = &phdrs[i];
+
+		switch (phdr->p_type) {
+		case PT_LOAD:
+#ifdef CONFIG_RELOCATABLE
+			dest = output;
+			dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR);
+#else
+			dest = (void *)(phdr->p_paddr);
+#endif
+			memcpy(dest,
+			       output + phdr->p_offset,
+			       phdr->p_filesz);
+			break;
+		default: /* Ignore other PT_* */ break;
+		}
+	}
+
+	free(phdrs);
+}
+
+asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
+				  unsigned char *input_data,
+				  unsigned long input_len,
+				  unsigned char *output,
+				  unsigned long output_len,
+				  unsigned long run_size)
+{
+	unsigned char *output_orig = output;
+
+	real_mode = rmode;
+
+	sanitize_boot_params(real_mode);
+
+	if (real_mode->screen_info.orig_video_mode == 7) {
+		vidmem = (char *) 0xb0000;
+		vidport = 0x3b4;
+	} else {
+		vidmem = (char *) 0xb8000;
+		vidport = 0x3d4;
+	}
+
+	lines = real_mode->screen_info.orig_video_lines;
+	cols = real_mode->screen_info.orig_video_cols;
+
+	console_init();
+	debug_putstr("early console in decompress_kernel\n");
+
+	free_mem_ptr     = heap;	/* Heap */
+	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
+
+	/*
+	 * The memory hole needed for the kernel is the larger of either
+	 * the entire decompressed kernel plus relocation table, or the
+	 * entire decompressed kernel plus .bss and .brk sections.
+	 */
+	output = choose_kernel_location(input_data, input_len, output,
+					output_len > run_size ? output_len
+							      : run_size);
+
+	/* Validate memory location choices. */
+	if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
+		error("Destination address inappropriately aligned");
+#ifdef CONFIG_X86_64
+	if (heap > 0x3fffffffffffUL)
+		error("Destination address too large");
+#else
+	if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff))
+		error("Destination address too large");
+#endif
+#ifndef CONFIG_RELOCATABLE
+	if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
+		error("Wrong destination address");
+#endif
+
+	debug_putstr("\nDecompressing Linux... ");
+	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
+	parse_elf(output);
+	/*
+	 * 32-bit always performs relocations. 64-bit relocations are only
+	 * needed if kASLR has chosen a different load address.
+	 */
+	if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig)
+		handle_relocations(output, output_len);
+	debug_putstr("done.\nBooting the kernel.\n");
+	return output;
+}

arch/x86/boot/compressed/misc.h

@@ -0,0 +1,86 @@
+#ifndef BOOT_COMPRESSED_MISC_H
+#define BOOT_COMPRESSED_MISC_H
+
+/*
+ * we have to be careful, because no indirections are allowed here, and
+ * paravirt_ops is a kind of one. As it will only run in baremetal anyway,
+ * we just keep it from happening
+ */
+#undef CONFIG_PARAVIRT
+#ifdef CONFIG_X86_32
+#define _ASM_X86_DESC_H 1
+#endif
+
+#include <linux/linkage.h>
+#include <linux/screen_info.h>
+#include <linux/elf.h>
+#include <linux/io.h>
+#include <asm/page.h>
+#include <asm/boot.h>
+#include <asm/bootparam.h>
+#include <asm/bootparam_utils.h>
+
+#define BOOT_BOOT_H
+#include "../ctype.h"
+
+#ifdef CONFIG_X86_64
+#define memptr long
+#else
+#define memptr unsigned
+#endif
+
+/* misc.c */
+extern memptr free_mem_ptr;
+extern memptr free_mem_end_ptr;
+extern struct boot_params *real_mode;		/* Pointer to real-mode data */
+void __putstr(const char *s);
+#define error_putstr(__x)  __putstr(__x)
+
+#ifdef CONFIG_X86_VERBOSE_BOOTUP
+
+#define debug_putstr(__x)  __putstr(__x)
+
+#else
+
+static inline void debug_putstr(const char *s)
+{ }
+
+#endif
+
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
+/* cmdline.c */
+int cmdline_find_option(const char *option, char *buffer, int bufsize);
+int cmdline_find_option_bool(const char *option);
+#endif
+
+
+#if CONFIG_RANDOMIZE_BASE
+/* aslr.c */
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size);
+/* cpuflags.c */
+bool has_cpuflag(int flag);
+#else
+static inline
+unsigned char *choose_kernel_location(unsigned char *input,
+				      unsigned long input_size,
+				      unsigned char *output,
+				      unsigned long output_size)
+{
+	return output;
+}
+#endif
+
+#ifdef CONFIG_EARLY_PRINTK
+/* early_serial_console.c */
+extern int early_serial_base;
+void console_init(void);
+#else
+static const int early_serial_base;
+static inline void console_init(void)
+{ }
+#endif
+
+#endif

arch/x86/boot/compressed/mkpiggy.c

@@ -0,0 +1,104 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *  Copyright (C) 2009 Intel Corporation. All rights reserved.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License version
+ *  2 as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ *  02110-1301, USA.
+ *
+ *  H. Peter Anvin <hpa@linux.intel.com>
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Compute the desired load offset from a compressed program; outputs
+ * a small assembly wrapper with the appropriate symbols defined.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <tools/le_byteshift.h>
+
+int main(int argc, char *argv[])
+{
+	uint32_t olen;
+	long ilen;
+	unsigned long offs;
+	unsigned long run_size;
+	FILE *f = NULL;
+	int retval = 1;
+
+	if (argc < 3) {
+		fprintf(stderr, "Usage: %s compressed_file run_size\n",
+				argv[0]);
+		goto bail;
+	}
+
+	/* Get the information for the compressed kernel image first */
+
+	f = fopen(argv[1], "r");
+	if (!f) {
+		perror(argv[1]);
+		goto bail;
+	}
+
+
+	if (fseek(f, -4L, SEEK_END)) {
+		perror(argv[1]);
+	}
+
+	if (fread(&olen, sizeof(olen), 1, f) != 1) {
+		perror(argv[1]);
+		goto bail;
+	}
+
+	ilen = ftell(f);
+	olen = get_unaligned_le32(&olen);
+
+	/*
+	 * Now we have the input (compressed) and output (uncompressed)
+	 * sizes, compute the necessary decompression offset...
+	 */
+
+	offs = (olen > ilen) ? olen - ilen : 0;
+	offs += olen >> 12;	/* Add 8 bytes for each 32K block */
+	offs += 64*1024 + 128;	/* Add 64K + 128 bytes slack */
+	offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+	run_size = atoi(argv[2]);
+
+	printf(".section \".rodata..compressed\",\"a\",@progbits\n");
+	printf(".globl z_input_len\n");
+	printf("z_input_len = %lu\n", ilen);
+	printf(".globl z_output_len\n");
+	printf("z_output_len = %lu\n", (unsigned long)olen);
+	printf(".globl z_extract_offset\n");
+	printf("z_extract_offset = 0x%lx\n", offs);
+	/* z_extract_offset_negative allows simplification of head_32.S */
+	printf(".globl z_extract_offset_negative\n");
+	printf("z_extract_offset_negative = -0x%lx\n", offs);
+	printf(".globl z_run_size\n");
+	printf("z_run_size = %lu\n", run_size);
+
+	printf(".globl input_data, input_data_end\n");
+	printf("input_data:\n");
+	printf(".incbin \"%s\"\n", argv[1]);
+	printf("input_data_end:\n");
+
+	retval = 0;
+bail:
+	if (f)
+		fclose(f);
+	return retval;
+}

arch/x86/boot/compressed/string.c

@@ -0,0 +1,41 @@
+#include "../string.c"
+
+#ifdef CONFIG_X86_32
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	int d0, d1, d2;
+	asm volatile(
+		"rep ; movsl\n\t"
+		"movl %4,%%ecx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
+		: "memory");
+
+	return dest;
+}
+#else
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	long d0, d1, d2;
+	asm volatile(
+		"rep ; movsq\n\t"
+		"movq %4,%%rcx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
+		: "memory");
+
+	return dest;
+}
+#endif
+
+void *memset(void *s, int c, size_t n)
+{
+	int i;
+	char *ss = s;
+
+	for (i = 0; i < n; i++)
+		ss[i] = c;
+	return s;
+}

arch/x86/boot/compressed/vmlinux.lds.S

@@ -0,0 +1,74 @@
+#include <asm-generic/vmlinux.lds.h>
+
+OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT)
+
+#undef i386
+
+#include <asm/cache.h>
+#include <asm/page_types.h>
+
+#ifdef CONFIG_X86_64
+OUTPUT_ARCH(i386:x86-64)
+ENTRY(startup_64)
+#else
+OUTPUT_ARCH(i386)
+ENTRY(startup_32)
+#endif
+
+SECTIONS
+{
+	/* Be careful parts of head_64.S assume startup_32 is at
+	 * address 0.
+	 */
+	. = 0;
+	.head.text : {
+		_head = . ;
+		HEAD_TEXT
+		_ehead = . ;
+	}
+	.rodata..compressed : {
+		*(.rodata..compressed)
+	}
+	.text :	{
+		_text = .; 	/* Text */
+		*(.text)
+		*(.text.*)
+		_etext = . ;
+	}
+	.rodata : {
+		_rodata = . ;
+		*(.rodata)	 /* read-only data */
+		*(.rodata.*)
+		_erodata = . ;
+	}
+	.got : {
+		_got = .;
+		KEEP(*(.got.plt))
+		KEEP(*(.got))
+		_egot = .;
+	}
+	.data :	{
+		_data = . ;
+		*(.data)
+		*(.data.*)
+		_edata = . ;
+	}
+	. = ALIGN(L1_CACHE_BYTES);
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		. = ALIGN(8);	/* For convenience during zeroing */
+		_ebss = .;
+	}
+#ifdef CONFIG_X86_64
+       . = ALIGN(PAGE_SIZE);
+       .pgtable : {
+		_pgtable = . ;
+		*(.pgtable)
+		_epgtable = . ;
+	}
+#endif
+	_end = .;
+}

arch/x86/boot/copy.S

@@ -0,0 +1,87 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+#include <linux/linkage.h>
+
+/*
+ * Memory copy routines
+ */
+
+	.code16
+	.text
+
+GLOBAL(memcpy)
+	pushw	%si
+	pushw	%di
+	movw	%ax, %di
+	movw	%dx, %si
+	pushw	%cx
+	shrw	$2, %cx
+	rep; movsl
+	popw	%cx
+	andw	$3, %cx
+	rep; movsb
+	popw	%di
+	popw	%si
+	retl
+ENDPROC(memcpy)
+
+GLOBAL(memset)
+	pushw	%di
+	movw	%ax, %di
+	movzbl	%dl, %eax
+	imull	$0x01010101,%eax
+	pushw	%cx
+	shrw	$2, %cx
+	rep; stosl
+	popw	%cx
+	andw	$3, %cx
+	rep; stosb
+	popw	%di
+	retl
+ENDPROC(memset)
+
+GLOBAL(copy_from_fs)
+	pushw	%ds
+	pushw	%fs
+	popw	%ds
+	calll	memcpy
+	popw	%ds
+	retl
+ENDPROC(copy_from_fs)
+
+GLOBAL(copy_to_fs)
+	pushw	%es
+	pushw	%fs
+	popw	%es
+	calll	memcpy
+	popw	%es
+	retl
+ENDPROC(copy_to_fs)
+
+#if 0 /* Not currently used, but can be enabled as needed */
+GLOBAL(copy_from_gs)
+	pushw	%ds
+	pushw	%gs
+	popw	%ds
+	calll	memcpy
+	popw	%ds
+	retl
+ENDPROC(copy_from_gs)
+
+GLOBAL(copy_to_gs)
+	pushw	%es
+	pushw	%gs
+	popw	%es
+	calll	memcpy
+	popw	%es
+	retl
+ENDPROC(copy_to_gs)
+#endif

arch/x86/boot/cpu.c

@@ -0,0 +1,99 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * arch/x86/boot/cpu.c
+ *
+ * Check for obligatory CPU features and abort if the features are not
+ * present.
+ */
+
+#include "boot.h"
+#ifdef CONFIG_X86_FEATURE_NAMES
+#include "cpustr.h"
+#endif
+
+static char *cpu_name(int level)
+{
+	static char buf[6];
+
+	if (level == 64) {
+		return "x86-64";
+	} else {
+		if (level == 15)
+			level = 6;
+		sprintf(buf, "i%d86", level);
+		return buf;
+	}
+}
+
+static void show_cap_strs(u32 *err_flags)
+{
+	int i, j;
+#ifdef CONFIG_X86_FEATURE_NAMES
+	const unsigned char *msg_strs = (const unsigned char *)x86_cap_strs;
+	for (i = 0; i < NCAPINTS; i++) {
+		u32 e = err_flags[i];
+		for (j = 0; j < 32; j++) {
+			if (msg_strs[0] < i ||
+			    (msg_strs[0] == i && msg_strs[1] < j)) {
+				/* Skip to the next string */
+				msg_strs += 2;
+				while (*msg_strs++)
+					;
+			}
+			if (e & 1) {
+				if (msg_strs[0] == i &&
+				    msg_strs[1] == j &&
+				    msg_strs[2])
+					printf("%s ", msg_strs+2);
+				else
+					printf("%d:%d ", i, j);
+			}
+			e >>= 1;
+		}
+	}
+#else
+	for (i = 0; i < NCAPINTS; i++) {
+		u32 e = err_flags[i];
+		for (j = 0; j < 32; j++) {
+			if (e & 1)
+				printf("%d:%d ", i, j);
+			e >>= 1;
+		}
+	}
+#endif
+}
+
+int validate_cpu(void)
+{
+	u32 *err_flags;
+	int cpu_level, req_level;
+
+	check_cpu(&cpu_level, &req_level, &err_flags);
+
+	if (cpu_level < req_level) {
+		printf("This kernel requires an %s CPU, ",
+		       cpu_name(req_level));
+		printf("but only detected an %s CPU.\n",
+		       cpu_name(cpu_level));
+		return -1;
+	}
+
+	if (err_flags) {
+		puts("This kernel requires the following features "
+		     "not present on the CPU:\n");
+		show_cap_strs(err_flags);
+		putchar('\n');
+		return -1;
+	} else {
+		return 0;
+	}
+}

arch/x86/boot/cpucheck.c

@@ -0,0 +1,187 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Check for obligatory CPU features and abort if the features are not
+ * present.  This code should be compilable as 16-, 32- or 64-bit
+ * code, so be very careful with types and inline assembly.
+ *
+ * This code should not contain any messages; that requires an
+ * additional wrapper.
+ *
+ * As written, this code is not safe for inclusion into the kernel
+ * proper (after FPU initialization, in particular).
+ */
+
+#ifdef _SETUP
+# include "boot.h"
+#endif
+#include <linux/types.h>
+#include <asm/processor-flags.h>
+#include <asm/required-features.h>
+#include <asm/msr-index.h>
+#include "string.h"
+
+static u32 err_flags[NCAPINTS];
+
+static const int req_level = CONFIG_X86_MINIMUM_CPU_FAMILY;
+
+static const u32 req_flags[NCAPINTS] =
+{
+	REQUIRED_MASK0,
+	REQUIRED_MASK1,
+	0, /* REQUIRED_MASK2 not implemented in this file */
+	0, /* REQUIRED_MASK3 not implemented in this file */
+	REQUIRED_MASK4,
+	0, /* REQUIRED_MASK5 not implemented in this file */
+	REQUIRED_MASK6,
+	0, /* REQUIRED_MASK7 not implemented in this file */
+};
+
+#define A32(a, b, c, d) (((d) << 24)+((c) << 16)+((b) << 8)+(a))
+
+static int is_amd(void)
+{
+	return cpu_vendor[0] == A32('A', 'u', 't', 'h') &&
+	       cpu_vendor[1] == A32('e', 'n', 't', 'i') &&
+	       cpu_vendor[2] == A32('c', 'A', 'M', 'D');
+}
+
+static int is_centaur(void)
+{
+	return cpu_vendor[0] == A32('C', 'e', 'n', 't') &&
+	       cpu_vendor[1] == A32('a', 'u', 'r', 'H') &&
+	       cpu_vendor[2] == A32('a', 'u', 'l', 's');
+}
+
+static int is_transmeta(void)
+{
+	return cpu_vendor[0] == A32('G', 'e', 'n', 'u') &&
+	       cpu_vendor[1] == A32('i', 'n', 'e', 'T') &&
+	       cpu_vendor[2] == A32('M', 'x', '8', '6');
+}
+
+static int is_intel(void)
+{
+	return cpu_vendor[0] == A32('G', 'e', 'n', 'u') &&
+	       cpu_vendor[1] == A32('i', 'n', 'e', 'I') &&
+	       cpu_vendor[2] == A32('n', 't', 'e', 'l');
+}
+
+/* Returns a bitmask of which words we have error bits in */
+static int check_cpuflags(void)
+{
+	u32 err;
+	int i;
+
+	err = 0;
+	for (i = 0; i < NCAPINTS; i++) {
+		err_flags[i] = req_flags[i] & ~cpu.flags[i];
+		if (err_flags[i])
+			err |= 1 << i;
+	}
+
+	return err;
+}
+
+/*
+ * Returns -1 on error.
+ *
+ * *cpu_level is set to the current CPU level; *req_level to the required
+ * level.  x86-64 is considered level 64 for this purpose.
+ *
+ * *err_flags_ptr is set to the flags error array if there are flags missing.
+ */
+int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
+{
+	int err;
+
+	memset(&cpu.flags, 0, sizeof cpu.flags);
+	cpu.level = 3;
+
+	if (has_eflag(X86_EFLAGS_AC))
+		cpu.level = 4;
+
+	get_cpuflags();
+	err = check_cpuflags();
+
+	if (test_bit(X86_FEATURE_LM, cpu.flags))
+		cpu.level = 64;
+
+	if (err == 0x01 &&
+	    !(err_flags[0] &
+	      ~((1 << X86_FEATURE_XMM)|(1 << X86_FEATURE_XMM2))) &&
+	    is_amd()) {
+		/* If this is an AMD and we're only missing SSE+SSE2, try to
+		   turn them on */
+
+		u32 ecx = MSR_K7_HWCR;
+		u32 eax, edx;
+
+		asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx));
+		eax &= ~(1 << 15);
+		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
+
+		get_cpuflags();	/* Make sure it really did something */
+		err = check_cpuflags();
+	} else if (err == 0x01 &&
+		   !(err_flags[0] & ~(1 << X86_FEATURE_CX8)) &&
+		   is_centaur() && cpu.model >= 6) {
+		/* If this is a VIA C3, we might have to enable CX8
+		   explicitly */
+
+		u32 ecx = MSR_VIA_FCR;
+		u32 eax, edx;
+
+		asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx));
+		eax |= (1<<1)|(1<<7);
+		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
+
+		set_bit(X86_FEATURE_CX8, cpu.flags);
+		err = check_cpuflags();
+	} else if (err == 0x01 && is_transmeta()) {
+		/* Transmeta might have masked feature bits in word 0 */
+
+		u32 ecx = 0x80860004;
+		u32 eax, edx;
+		u32 level = 1;
+
+		asm("rdmsr" : "=a" (eax), "=d" (edx) : "c" (ecx));
+		asm("wrmsr" : : "a" (~0), "d" (edx), "c" (ecx));
+		asm("cpuid"
+		    : "+a" (level), "=d" (cpu.flags[0])
+		    : : "ecx", "ebx");
+		asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
+
+		err = check_cpuflags();
+	} else if (err == 0x01 &&
+		   !(err_flags[0] & ~(1 << X86_FEATURE_PAE)) &&
+		   is_intel() && cpu.level == 6 &&
+		   (cpu.model == 9 || cpu.model == 13)) {
+		/* PAE is disabled on this Pentium M but can be forced */
+		if (cmdline_find_option_bool("forcepae")) {
+			puts("WARNING: Forcing PAE in CPU flags\n");
+			set_bit(X86_FEATURE_PAE, cpu.flags);
+			err = check_cpuflags();
+		}
+		else {
+			puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n");
+		}
+	}
+
+	if (err_flags_ptr)
+		*err_flags_ptr = err ? err_flags : NULL;
+	if (cpu_level_ptr)
+		*cpu_level_ptr = cpu.level;
+	if (req_level_ptr)
+		*req_level_ptr = req_level;
+
+	return (cpu.level < req_level || err) ? -1 : 0;
+}

arch/x86/boot/cpuflags.c

@@ -0,0 +1,119 @@
+#include <linux/types.h>
+#include "bitops.h"
+
+#include <asm/processor-flags.h>
+#include <asm/required-features.h>
+#include <asm/msr-index.h>
+#include "cpuflags.h"
+
+struct cpu_features cpu;
+u32 cpu_vendor[3];
+
+static bool loaded_flags;
+
+static int has_fpu(void)
+{
+	u16 fcw = -1, fsw = -1;
+	unsigned long cr0;
+
+	asm volatile("mov %%cr0,%0" : "=r" (cr0));
+	if (cr0 & (X86_CR0_EM|X86_CR0_TS)) {
+		cr0 &= ~(X86_CR0_EM|X86_CR0_TS);
+		asm volatile("mov %0,%%cr0" : : "r" (cr0));
+	}
+
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
+		     : "+m" (fsw), "+m" (fcw));
+
+	return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+/*
+ * For building the 16-bit code we want to explicitly specify 32-bit
+ * push/pop operations, rather than just saying 'pushf' or 'popf' and
+ * letting the compiler choose. But this is also included from the
+ * compressed/ directory where it may be 64-bit code, and thus needs
+ * to be 'pushfq' or 'popfq' in that case.
+ */
+#ifdef __x86_64__
+#define PUSHF "pushfq"
+#define POPF "popfq"
+#else
+#define PUSHF "pushfl"
+#define POPF "popfl"
+#endif
+
+int has_eflag(unsigned long mask)
+{
+	unsigned long f0, f1;
+
+	asm volatile(PUSHF "	\n\t"
+		     PUSHF "	\n\t"
+		     "pop %0	\n\t"
+		     "mov %0,%1	\n\t"
+		     "xor %2,%1	\n\t"
+		     "push %1	\n\t"
+		     POPF "	\n\t"
+		     PUSHF "	\n\t"
+		     "pop %1	\n\t"
+		     POPF
+		     : "=&r" (f0), "=&r" (f1)
+		     : "ri" (mask));
+
+	return !!((f0^f1) & mask);
+}
+
+/* Handle x86_32 PIC using ebx. */
+#if defined(__i386__) && defined(__PIC__)
+# define EBX_REG "=r"
+#else
+# define EBX_REG "=b"
+#endif
+
+static inline void cpuid(u32 id, u32 *a, u32 *b, u32 *c, u32 *d)
+{
+	asm volatile(".ifnc %%ebx,%3 ; movl  %%ebx,%3 ; .endif	\n\t"
+		     "cpuid					\n\t"
+		     ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif	\n\t"
+		    : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b)
+		    : "a" (id)
+	);
+}
+
+void get_cpuflags(void)
+{
+	u32 max_intel_level, max_amd_level;
+	u32 tfms;
+	u32 ignored;
+
+	if (loaded_flags)
+		return;
+	loaded_flags = true;
+
+	if (has_fpu())
+		set_bit(X86_FEATURE_FPU, cpu.flags);
+
+	if (has_eflag(X86_EFLAGS_ID)) {
+		cpuid(0x0, &max_intel_level, &cpu_vendor[0], &cpu_vendor[2],
+		      &cpu_vendor[1]);
+
+		if (max_intel_level >= 0x00000001 &&
+		    max_intel_level <= 0x0000ffff) {
+			cpuid(0x1, &tfms, &ignored, &cpu.flags[4],
+			      &cpu.flags[0]);
+			cpu.level = (tfms >> 8) & 15;
+			cpu.model = (tfms >> 4) & 15;
+			if (cpu.level >= 6)
+				cpu.model += ((tfms >> 16) & 0xf) << 4;
+		}
+
+		cpuid(0x80000000, &max_amd_level, &ignored, &ignored,
+		      &ignored);
+
+		if (max_amd_level >= 0x80000001 &&
+		    max_amd_level <= 0x8000ffff) {
+			cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6],
+			      &cpu.flags[1]);
+		}
+	}
+}

arch/x86/boot/cpuflags.h

@@ -0,0 +1,19 @@
+#ifndef BOOT_CPUFLAGS_H
+#define BOOT_CPUFLAGS_H
+
+#include <asm/cpufeature.h>
+#include <asm/processor-flags.h>
+
+struct cpu_features {
+	int level;		/* Family, or 64 for x86-64 */
+	int model;
+	u32 flags[NCAPINTS];
+};
+
+extern struct cpu_features cpu;
+extern u32 cpu_vendor[3];
+
+int has_eflag(unsigned long mask);
+void get_cpuflags(void);
+
+#endif

arch/x86/boot/ctype.h

@@ -0,0 +1,21 @@
+#ifndef BOOT_ISDIGIT_H
+
+#define BOOT_ISDIGIT_H
+
+static inline int isdigit(int ch)
+{
+	return (ch >= '0') && (ch <= '9');
+}
+
+static inline int isxdigit(int ch)
+{
+	if (isdigit(ch))
+		return true;
+
+	if ((ch >= 'a') && (ch <= 'f'))
+		return true;
+
+	return (ch >= 'A') && (ch <= 'F');
+}
+
+#endif

arch/x86/boot/early_serial_console.c

@@ -0,0 +1,151 @@
+#include "boot.h"
+
+#define DEFAULT_SERIAL_PORT 0x3f8 /* ttyS0 */
+
+#define XMTRDY          0x20
+
+#define DLAB		0x80
+
+#define TXR             0       /*  Transmit register (WRITE) */
+#define RXR             0       /*  Receive register  (READ)  */
+#define IER             1       /*  Interrupt Enable          */
+#define IIR             2       /*  Interrupt ID              */
+#define FCR             2       /*  FIFO control              */
+#define LCR             3       /*  Line control              */
+#define MCR             4       /*  Modem control             */
+#define LSR             5       /*  Line Status               */
+#define MSR             6       /*  Modem Status              */
+#define DLL             0       /*  Divisor Latch Low         */
+#define DLH             1       /*  Divisor latch High        */
+
+#define DEFAULT_BAUD 9600
+
+static void early_serial_init(int port, int baud)
+{
+	unsigned char c;
+	unsigned divisor;
+
+	outb(0x3, port + LCR);	/* 8n1 */
+	outb(0, port + IER);	/* no interrupt */
+	outb(0, port + FCR);	/* no fifo */
+	outb(0x3, port + MCR);	/* DTR + RTS */
+
+	divisor	= 115200 / baud;
+	c = inb(port + LCR);
+	outb(c | DLAB, port + LCR);
+	outb(divisor & 0xff, port + DLL);
+	outb((divisor >> 8) & 0xff, port + DLH);
+	outb(c & ~DLAB, port + LCR);
+
+	early_serial_base = port;
+}
+
+static void parse_earlyprintk(void)
+{
+	int baud = DEFAULT_BAUD;
+	char arg[32];
+	int pos = 0;
+	int port = 0;
+
+	if (cmdline_find_option("earlyprintk", arg, sizeof arg) > 0) {
+		char *e;
+
+		if (!strncmp(arg, "serial", 6)) {
+			port = DEFAULT_SERIAL_PORT;
+			pos += 6;
+		}
+
+		if (arg[pos] == ',')
+			pos++;
+
+		/*
+		 * make sure we have
+		 *	"serial,0x3f8,115200"
+		 *	"serial,ttyS0,115200"
+		 *	"ttyS0,115200"
+		 */
+		if (pos == 7 && !strncmp(arg + pos, "0x", 2)) {
+			port = simple_strtoull(arg + pos, &e, 16);
+			if (port == 0 || arg + pos == e)
+				port = DEFAULT_SERIAL_PORT;
+			else
+				pos = e - arg;
+		} else if (!strncmp(arg + pos, "ttyS", 4)) {
+			static const int bases[] = { 0x3f8, 0x2f8 };
+			int idx = 0;
+
+			if (!strncmp(arg + pos, "ttyS", 4))
+				pos += 4;
+
+			if (arg[pos++] == '1')
+				idx = 1;
+
+			port = bases[idx];
+		}
+
+		if (arg[pos] == ',')
+			pos++;
+
+		baud = simple_strtoull(arg + pos, &e, 0);
+		if (baud == 0 || arg + pos == e)
+			baud = DEFAULT_BAUD;
+	}
+
+	if (port)
+		early_serial_init(port, baud);
+}
+
+#define BASE_BAUD (1843200/16)
+static unsigned int probe_baud(int port)
+{
+	unsigned char lcr, dll, dlh;
+	unsigned int quot;
+
+	lcr = inb(port + LCR);
+	outb(lcr | DLAB, port + LCR);
+	dll = inb(port + DLL);
+	dlh = inb(port + DLH);
+	outb(lcr, port + LCR);
+	quot = (dlh << 8) | dll;
+
+	return BASE_BAUD / quot;
+}
+
+static void parse_console_uart8250(void)
+{
+	char optstr[64], *options;
+	int baud = DEFAULT_BAUD;
+	int port = 0;
+
+	/*
+	 * console=uart8250,io,0x3f8,115200n8
+	 * need to make sure it is last one console !
+	 */
+	if (cmdline_find_option("console", optstr, sizeof optstr) <= 0)
+		return;
+
+	options = optstr;
+
+	if (!strncmp(options, "uart8250,io,", 12))
+		port = simple_strtoull(options + 12, &options, 0);
+	else if (!strncmp(options, "uart,io,", 8))
+		port = simple_strtoull(options + 8, &options, 0);
+	else
+		return;
+
+	if (options && (options[0] == ','))
+		baud = simple_strtoull(options + 1, &options, 0);
+	else
+		baud = probe_baud(port);
+
+	if (port)
+		early_serial_init(port, baud);
+}
+
+void console_init(void)
+{
+	parse_earlyprintk();
+
+	if (!early_serial_base)
+		parse_console_uart8250();
+}

arch/x86/boot/edd.c

@@ -0,0 +1,182 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Get EDD BIOS disk information
+ */
+
+#include "boot.h"
+#include <linux/edd.h>
+#include "string.h"
+
+#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+
+/*
+ * Read the MBR (first sector) from a specific device.
+ */
+static int read_mbr(u8 devno, void *buf)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ax = 0x0201;		/* Legacy Read, one sector */
+	ireg.cx = 0x0001;		/* Sector 0-0-1 */
+	ireg.dl = devno;
+	ireg.bx = (size_t)buf;
+
+	intcall(0x13, &ireg, &oreg);
+
+	return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
+}
+
+static u32 read_mbr_sig(u8 devno, struct edd_info *ei, u32 *mbrsig)
+{
+	int sector_size;
+	char *mbrbuf_ptr, *mbrbuf_end;
+	u32 buf_base, mbr_base;
+	extern char _end[];
+	u16 mbr_magic;
+
+	sector_size = ei->params.bytes_per_sector;
+	if (!sector_size)
+		sector_size = 512; /* Best available guess */
+
+	/* Produce a naturally aligned buffer on the heap */
+	buf_base = (ds() << 4) + (u32)&_end;
+	mbr_base = (buf_base+sector_size-1) & ~(sector_size-1);
+	mbrbuf_ptr = _end + (mbr_base-buf_base);
+	mbrbuf_end = mbrbuf_ptr + sector_size;
+
+	/* Make sure we actually have space on the heap... */
+	if (!(boot_params.hdr.loadflags & CAN_USE_HEAP))
+		return -1;
+	if (mbrbuf_end > (char *)(size_t)boot_params.hdr.heap_end_ptr)
+		return -1;
+
+	memset(mbrbuf_ptr, 0, sector_size);
+	if (read_mbr(devno, mbrbuf_ptr))
+		return -1;
+
+	*mbrsig = *(u32 *)&mbrbuf_ptr[EDD_MBR_SIG_OFFSET];
+	mbr_magic = *(u16 *)&mbrbuf_ptr[510];
+
+	/* check for valid MBR magic */
+	return mbr_magic == 0xAA55 ? 0 : -1;
+}
+
+static int get_edd_info(u8 devno, struct edd_info *ei)
+{
+	struct biosregs ireg, oreg;
+
+	memset(ei, 0, sizeof *ei);
+
+	/* Check Extensions Present */
+
+	initregs(&ireg);
+	ireg.ah = 0x41;
+	ireg.bx = EDDMAGIC1;
+	ireg.dl = devno;
+	intcall(0x13, &ireg, &oreg);
+
+	if (oreg.eflags & X86_EFLAGS_CF)
+		return -1;	/* No extended information */
+
+	if (oreg.bx != EDDMAGIC2)
+		return -1;
+
+	ei->device  = devno;
+	ei->version = oreg.ah;		 /* EDD version number */
+	ei->interface_support = oreg.cx; /* EDD functionality subsets */
+
+	/* Extended Get Device Parameters */
+
+	ei->params.length = sizeof(ei->params);
+	ireg.ah = 0x48;
+	ireg.si = (size_t)&ei->params;
+	intcall(0x13, &ireg, &oreg);
+
+	/* Get legacy CHS parameters */
+
+	/* Ralf Brown recommends setting ES:DI to 0:0 */
+	ireg.ah = 0x08;
+	ireg.es = 0;
+	intcall(0x13, &ireg, &oreg);
+
+	if (!(oreg.eflags & X86_EFLAGS_CF)) {
+		ei->legacy_max_cylinder = oreg.ch + ((oreg.cl & 0xc0) << 2);
+		ei->legacy_max_head = oreg.dh;
+		ei->legacy_sectors_per_track = oreg.cl & 0x3f;
+	}
+
+	return 0;
+}
+
+void query_edd(void)
+{
+	char eddarg[8];
+	int do_mbr = 1;
+#ifdef CONFIG_EDD_OFF
+	int do_edd = 0;
+#else
+	int do_edd = 1;
+#endif
+	int be_quiet;
+	int devno;
+	struct edd_info ei, *edp;
+	u32 *mbrptr;
+
+	if (cmdline_find_option("edd", eddarg, sizeof eddarg) > 0) {
+		if (!strcmp(eddarg, "skipmbr") || !strcmp(eddarg, "skip")) {
+			do_edd = 1;
+			do_mbr = 0;
+		}
+		else if (!strcmp(eddarg, "off"))
+			do_edd = 0;
+		else if (!strcmp(eddarg, "on"))
+			do_edd = 1;
+	}
+
+	be_quiet = cmdline_find_option_bool("quiet");
+
+	edp    = boot_params.eddbuf;
+	mbrptr = boot_params.edd_mbr_sig_buffer;
+
+	if (!do_edd)
+		return;
+
+	/* Bugs in OnBoard or AddOnCards Bios may hang the EDD probe,
+	 * so give a hint if this happens.
+	 */
+
+	if (!be_quiet)
+		printf("Probing EDD (edd=off to disable)... ");
+
+	for (devno = 0x80; devno < 0x80+EDD_MBR_SIG_MAX; devno++) {
+		/*
+		 * Scan the BIOS-supported hard disks and query EDD
+		 * information...
+		 */
+		if (!get_edd_info(devno, &ei)
+		    && boot_params.eddbuf_entries < EDDMAXNR) {
+			memcpy(edp, &ei, sizeof ei);
+			edp++;
+			boot_params.eddbuf_entries++;
+		}
+
+		if (do_mbr && !read_mbr_sig(devno, &ei, mbrptr++))
+			boot_params.edd_mbr_sig_buf_entries = devno-0x80+1;
+	}
+
+	if (!be_quiet)
+		printf("ok\n");
+}
+
+#endif

arch/x86/boot/header.S

@@ -0,0 +1,528 @@
+/*
+ *	header.S
+ *
+ *	Copyright (C) 1991, 1992 Linus Torvalds
+ *
+ *	Based on bootsect.S and setup.S
+ *	modified by more people than can be counted
+ *
+ *	Rewritten as a common file by H. Peter Anvin (Apr 2007)
+ *
+ * BIG FAT NOTE: We're in real mode using 64k segments.  Therefore segment
+ * addresses must be multiplied by 16 to obtain their respective linear
+ * addresses. To avoid confusion, linear addresses are written using leading
+ * hex while segment addresses are written as segment:offset.
+ *
+ */
+
+#include <asm/segment.h>
+#include <generated/utsrelease.h>
+#include <asm/boot.h>
+#include <asm/e820.h>
+#include <asm/page_types.h>
+#include <asm/setup.h>
+#include <asm/bootparam.h>
+#include "boot.h"
+#include "voffset.h"
+#include "zoffset.h"
+
+BOOTSEG		= 0x07C0		/* original address of boot-sector */
+SYSSEG		= 0x1000		/* historical load address >> 4 */
+
+#ifndef SVGA_MODE
+#define SVGA_MODE ASK_VGA
+#endif
+
+#ifndef ROOT_RDONLY
+#define ROOT_RDONLY 1
+#endif
+
+	.code16
+	.section ".bstext", "ax"
+
+	.global bootsect_start
+bootsect_start:
+#ifdef CONFIG_EFI_STUB
+	# "MZ", MS-DOS header
+	.byte 0x4d
+	.byte 0x5a
+#endif
+
+	# Normalize the start address
+	ljmp	$BOOTSEG, $start2
+
+start2:
+	movw	%cs, %ax
+	movw	%ax, %ds
+	movw	%ax, %es
+	movw	%ax, %ss
+	xorw	%sp, %sp
+	sti
+	cld
+
+	movw	$bugger_off_msg, %si
+
+msg_loop:
+	lodsb
+	andb	%al, %al
+	jz	bs_die
+	movb	$0xe, %ah
+	movw	$7, %bx
+	int	$0x10
+	jmp	msg_loop
+
+bs_die:
+	# Allow the user to press a key, then reboot
+	xorw	%ax, %ax
+	int	$0x16
+	int	$0x19
+
+	# int 0x19 should never return.  In case it does anyway,
+	# invoke the BIOS reset code...
+	ljmp	$0xf000,$0xfff0
+
+#ifdef CONFIG_EFI_STUB
+	.org	0x3c
+	#
+	# Offset to the PE header.
+	#
+	.long	pe_header
+#endif /* CONFIG_EFI_STUB */
+
+	.section ".bsdata", "a"
+bugger_off_msg:
+	.ascii	"Use a boot loader.\r\n"
+	.ascii	"\n"
+	.ascii	"Remove disk and press any key to reboot...\r\n"
+	.byte	0
+
+#ifdef CONFIG_EFI_STUB
+pe_header:
+	.ascii	"PE"
+	.word 	0
+
+coff_header:
+#ifdef CONFIG_X86_32
+	.word	0x14c				# i386
+#else
+	.word	0x8664				# x86-64
+#endif
+	.word	4				# nr_sections
+	.long	0 				# TimeDateStamp
+	.long	0				# PointerToSymbolTable
+	.long	1				# NumberOfSymbols
+	.word	section_table - optional_header	# SizeOfOptionalHeader
+#ifdef CONFIG_X86_32
+	.word	0x306				# Characteristics.
+						# IMAGE_FILE_32BIT_MACHINE |
+						# IMAGE_FILE_DEBUG_STRIPPED |
+						# IMAGE_FILE_EXECUTABLE_IMAGE |
+						# IMAGE_FILE_LINE_NUMS_STRIPPED
+#else
+	.word	0x206				# Characteristics
+						# IMAGE_FILE_DEBUG_STRIPPED |
+						# IMAGE_FILE_EXECUTABLE_IMAGE |
+						# IMAGE_FILE_LINE_NUMS_STRIPPED
+#endif
+
+optional_header:
+#ifdef CONFIG_X86_32
+	.word	0x10b				# PE32 format
+#else
+	.word	0x20b 				# PE32+ format
+#endif
+	.byte	0x02				# MajorLinkerVersion
+	.byte	0x14				# MinorLinkerVersion
+
+	# Filled in by build.c
+	.long	0				# SizeOfCode
+
+	.long	0				# SizeOfInitializedData
+	.long	0				# SizeOfUninitializedData
+
+	# Filled in by build.c
+	.long	0x0000				# AddressOfEntryPoint
+
+	.long	0x0200				# BaseOfCode
+#ifdef CONFIG_X86_32
+	.long	0				# data
+#endif
+
+extra_header_fields:
+#ifdef CONFIG_X86_32
+	.long	0				# ImageBase
+#else
+	.quad	0				# ImageBase
+#endif
+	.long	CONFIG_PHYSICAL_ALIGN		# SectionAlignment
+	.long	0x20				# FileAlignment
+	.word	0				# MajorOperatingSystemVersion
+	.word	0				# MinorOperatingSystemVersion
+	.word	0				# MajorImageVersion
+	.word	0				# MinorImageVersion
+	.word	0				# MajorSubsystemVersion
+	.word	0				# MinorSubsystemVersion
+	.long	0				# Win32VersionValue
+
+	#
+	# The size of the bzImage is written in tools/build.c
+	#
+	.long	0				# SizeOfImage
+
+	.long	0x200				# SizeOfHeaders
+	.long	0				# CheckSum
+	.word	0xa				# Subsystem (EFI application)
+	.word	0				# DllCharacteristics
+#ifdef CONFIG_X86_32
+	.long	0				# SizeOfStackReserve
+	.long	0				# SizeOfStackCommit
+	.long	0				# SizeOfHeapReserve
+	.long	0				# SizeOfHeapCommit
+#else
+	.quad	0				# SizeOfStackReserve
+	.quad	0				# SizeOfStackCommit
+	.quad	0				# SizeOfHeapReserve
+	.quad	0				# SizeOfHeapCommit
+#endif
+	.long	0				# LoaderFlags
+	.long	0x6				# NumberOfRvaAndSizes
+
+	.quad	0				# ExportTable
+	.quad	0				# ImportTable
+	.quad	0				# ResourceTable
+	.quad	0				# ExceptionTable
+	.quad	0				# CertificationTable
+	.quad	0				# BaseRelocationTable
+
+	# Section table
+section_table:
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".setup"
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0				# startup_{32,64}
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0				# startup_{32,64}
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0x60500020			# Characteristics (section flags)
+
+	#
+	# The EFI application loader requires a relocation section
+	# because EFI applications must be relocatable. The .reloc
+	# offset & size fields are filled in by build.c.
+	#
+	.ascii	".reloc"
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0
+	.long	0				# SizeOfRawData
+	.long	0				# PointerToRawData
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0x42100040			# Characteristics (section flags)
+
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".text"
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0				# startup_{32,64}
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0				# startup_{32,64}
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0x60500020			# Characteristics (section flags)
+
+	#
+	# The offset & size fields are filled in by build.c.
+	#
+	.ascii	".bss"
+	.byte	0
+	.byte	0
+	.byte	0
+	.byte	0
+	.long	0
+	.long	0x0
+	.long	0				# Size of initialized data
+						# on disk
+	.long	0x0
+	.long	0				# PointerToRelocations
+	.long	0				# PointerToLineNumbers
+	.word	0				# NumberOfRelocations
+	.word	0				# NumberOfLineNumbers
+	.long	0xc8000080			# Characteristics (section flags)
+
+#endif /* CONFIG_EFI_STUB */
+
+	# Kernel attributes; used by setup.  This is part 1 of the
+	# header, from the old boot sector.
+
+	.section ".header", "a"
+	.globl	sentinel
+sentinel:	.byte 0xff, 0xff        /* Used to detect broken loaders */
+
+	.globl	hdr
+hdr:
+setup_sects:	.byte 0			/* Filled in by build.c */
+root_flags:	.word ROOT_RDONLY
+syssize:	.long 0			/* Filled in by build.c */
+ram_size:	.word 0			/* Obsolete */
+vid_mode:	.word SVGA_MODE
+root_dev:	.word 0			/* Filled in by build.c */
+boot_flag:	.word 0xAA55
+
+	# offset 512, entry point
+
+	.globl	_start
+_start:
+		# Explicitly enter this as bytes, or the assembler
+		# tries to generate a 3-byte jump here, which causes
+		# everything else to push off to the wrong offset.
+		.byte	0xeb		# short (2-byte) jump
+		.byte	start_of_setup-1f
+1:
+
+	# Part 2 of the header, from the old setup.S
+
+		.ascii	"HdrS"		# header signature
+		.word	0x020d		# header version number (>= 0x0105)
+					# or else old loadlin-1.5 will fail)
+		.globl realmode_swtch
+realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
+start_sys_seg:	.word	SYSSEG		# obsolete and meaningless, but just
+					# in case something decided to "use" it
+		.word	kernel_version-512 # pointing to kernel version string
+					# above section of header is compatible
+					# with loadlin-1.5 (header v1.5). Don't
+					# change it.
+
+type_of_loader:	.byte	0		# 0 means ancient bootloader, newer
+					# bootloaders know to change this.
+					# See Documentation/x86/boot.txt for
+					# assigned ids
+
+# flags, unused bits must be zero (RFU) bit within loadflags
+loadflags:
+		.byte	LOADED_HIGH	# The kernel is to be loaded high
+
+setup_move_size: .word  0x8000		# size to move, when setup is not
+					# loaded at 0x90000. We will move setup
+					# to 0x90000 then just before jumping
+					# into the kernel. However, only the
+					# loader knows how much data behind
+					# us also needs to be loaded.
+
+code32_start:				# here loaders can put a different
+					# start address for 32-bit code.
+		.long	0x100000	# 0x100000 = default for big kernel
+
+ramdisk_image:	.long	0		# address of loaded ramdisk image
+					# Here the loader puts the 32-bit
+					# address where it loaded the image.
+					# This only will be read by the kernel.
+
+ramdisk_size:	.long	0		# its size in bytes
+
+bootsect_kludge:
+		.long	0		# obsolete
+
+heap_end_ptr:	.word	_end+STACK_SIZE-512
+					# (Header version 0x0201 or later)
+					# space from here (exclusive) down to
+					# end of setup code can be used by setup
+					# for local heap purposes.
+
+ext_loader_ver:
+		.byte	0		# Extended boot loader version
+ext_loader_type:
+		.byte	0		# Extended boot loader type
+
+cmd_line_ptr:	.long	0		# (Header version 0x0202 or later)
+					# If nonzero, a 32-bit pointer
+					# to the kernel command line.
+					# The command line should be
+					# located between the start of
+					# setup and the end of low
+					# memory (0xa0000), or it may
+					# get overwritten before it
+					# gets read.  If this field is
+					# used, there is no longer
+					# anything magical about the
+					# 0x90000 segment; the setup
+					# can be located anywhere in
+					# low memory 0x10000 or higher.
+
+initrd_addr_max: .long 0x7fffffff
+					# (Header version 0x0203 or later)
+					# The highest safe address for
+					# the contents of an initrd
+					# The current kernel allows up to 4 GB,
+					# but leave it at 2 GB to avoid
+					# possible bootloader bugs.
+
+kernel_alignment:  .long CONFIG_PHYSICAL_ALIGN	#physical addr alignment
+						#required for protected mode
+						#kernel
+#ifdef CONFIG_RELOCATABLE
+relocatable_kernel:    .byte 1
+#else
+relocatable_kernel:    .byte 0
+#endif
+min_alignment:		.byte MIN_KERNEL_ALIGN_LG2	# minimum alignment
+
+xloadflags:
+#ifdef CONFIG_X86_64
+# define XLF0 XLF_KERNEL_64			/* 64-bit kernel */
+#else
+# define XLF0 0
+#endif
+
+#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64)
+   /* kernel/boot_param/ramdisk could be loaded above 4g */
+# define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G
+#else
+# define XLF1 0
+#endif
+
+#ifdef CONFIG_EFI_STUB
+# ifdef CONFIG_EFI_MIXED
+#  define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64)
+# else
+#  ifdef CONFIG_X86_64
+#   define XLF23 XLF_EFI_HANDOVER_64		/* 64-bit EFI handover ok */
+#  else
+#   define XLF23 XLF_EFI_HANDOVER_32		/* 32-bit EFI handover ok */
+#  endif
+# endif
+#else
+# define XLF23 0
+#endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC)
+# define XLF4 XLF_EFI_KEXEC
+#else
+# define XLF4 0
+#endif
+
+			.word XLF0 | XLF1 | XLF23 | XLF4
+
+cmdline_size:   .long   COMMAND_LINE_SIZE-1     #length of the command line,
+                                                #added with boot protocol
+                                                #version 2.06
+
+hardware_subarch:	.long 0			# subarchitecture, added with 2.07
+						# default to 0 for normal x86 PC
+
+hardware_subarch_data:	.quad 0
+
+payload_offset:		.long ZO_input_data
+payload_length:		.long ZO_z_input_len
+
+setup_data:		.quad 0			# 64-bit physical pointer to
+						# single linked list of
+						# struct setup_data
+
+pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
+
+#define ZO_INIT_SIZE	(ZO__end - ZO_startup_32 + ZO_z_extract_offset)
+#define VO_INIT_SIZE	(VO__end - VO__text)
+#if ZO_INIT_SIZE > VO_INIT_SIZE
+#define INIT_SIZE ZO_INIT_SIZE
+#else
+#define INIT_SIZE VO_INIT_SIZE
+#endif
+init_size:		.long INIT_SIZE		# kernel initialization size
+handover_offset:	.long 0			# Filled in by build.c
+
+# End of setup header #####################################################
+
+	.section ".entrytext", "ax"
+start_of_setup:
+# Force %es = %ds
+	movw	%ds, %ax
+	movw	%ax, %es
+	cld
+
+# Apparently some ancient versions of LILO invoked the kernel with %ss != %ds,
+# which happened to work by accident for the old code.  Recalculate the stack
+# pointer if %ss is invalid.  Otherwise leave it alone, LOADLIN sets up the
+# stack behind its own code, so we can't blindly put it directly past the heap.
+
+	movw	%ss, %dx
+	cmpw	%ax, %dx	# %ds == %ss?
+	movw	%sp, %dx
+	je	2f		# -> assume %sp is reasonably set
+
+	# Invalid %ss, make up a new stack
+	movw	$_end, %dx
+	testb	$CAN_USE_HEAP, loadflags
+	jz	1f
+	movw	heap_end_ptr, %dx
+1:	addw	$STACK_SIZE, %dx
+	jnc	2f
+	xorw	%dx, %dx	# Prevent wraparound
+
+2:	# Now %dx should point to the end of our stack space
+	andw	$~3, %dx	# dword align (might as well...)
+	jnz	3f
+	movw	$0xfffc, %dx	# Make sure we're not zero
+3:	movw	%ax, %ss
+	movzwl	%dx, %esp	# Clear upper half of %esp
+	sti			# Now we should have a working stack
+
+# We will have entered with %cs = %ds+0x20, normalize %cs so
+# it is on par with the other segments.
+	pushw	%ds
+	pushw	$6f
+	lretw
+6:
+
+# Check signature at end of setup
+	cmpl	$0x5a5aaa55, setup_sig
+	jne	setup_bad
+
+# Zero the bss
+	movw	$__bss_start, %di
+	movw	$_end+3, %cx
+	xorl	%eax, %eax
+	subw	%di, %cx
+	shrw	$2, %cx
+	rep; stosl
+
+# Jump to C code (should not return)
+	calll	main
+
+# Setup corrupt somehow...
+setup_bad:
+	movl	$setup_corrupt, %eax
+	calll	puts
+	# Fall through...
+
+	.globl	die
+	.type	die, @function
+die:
+	hlt
+	jmp	die
+
+	.size	die, .-die
+
+	.section ".initdata", "a"
+setup_corrupt:
+	.byte	7
+	.string	"No setup signature found...\n"

arch/x86/boot/install.sh

@@ -0,0 +1,59 @@
+#!/bin/sh
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License.  See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+# Copyright (C) 1995 by Linus Torvalds
+#
+# Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin
+#
+# "make install" script for i386 architecture
+#
+# Arguments:
+#   $1 - kernel version
+#   $2 - kernel image file
+#   $3 - kernel map file
+#   $4 - default install path (blank if root directory)
+#
+
+verify () {
+	if [ ! -f "$1" ]; then
+		echo ""                                                   1>&2
+		echo " *** Missing file: $1"                              1>&2
+		echo ' *** You need to run "make" before "make install".' 1>&2
+		echo ""                                                   1>&2
+		exit 1
+ 	fi
+}
+
+# Make sure the files actually exist
+verify "$2"
+verify "$3"
+
+# User may have a custom install script
+
+if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi
+if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi
+
+# Default install - same as make zlilo
+
+if [ -f $4/vmlinuz ]; then
+	mv $4/vmlinuz $4/vmlinuz.old
+fi
+
+if [ -f $4/System.map ]; then
+	mv $4/System.map $4/System.old
+fi
+
+cat $2 > $4/vmlinuz
+cp $3 $4/System.map
+
+if [ -x /sbin/lilo ]; then
+       /sbin/lilo
+elif [ -x /etc/lilo/install ]; then
+       /etc/lilo/install
+else
+       sync
+       echo "Cannot find LILO."
+fi

arch/x86/boot/main.c

@@ -0,0 +1,185 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Main module for the real-mode kernel code
+ */
+
+#include "boot.h"
+#include "string.h"
+
+struct boot_params boot_params __attribute__((aligned(16)));
+
+char *HEAP = _end;
+char *heap_end = _end;		/* Default end of heap = no heap */
+
+/*
+ * Copy the header into the boot parameter block.  Since this
+ * screws up the old-style command line protocol, adjust by
+ * filling in the new-style command line pointer instead.
+ */
+
+static void copy_boot_params(void)
+{
+	struct old_cmdline {
+		u16 cl_magic;
+		u16 cl_offset;
+	};
+	const struct old_cmdline * const oldcmd =
+		(const struct old_cmdline *)OLD_CL_ADDRESS;
+
+	BUILD_BUG_ON(sizeof boot_params != 4096);
+	memcpy(&boot_params.hdr, &hdr, sizeof hdr);
+
+	if (!boot_params.hdr.cmd_line_ptr &&
+	    oldcmd->cl_magic == OLD_CL_MAGIC) {
+		/* Old-style command line protocol. */
+		u16 cmdline_seg;
+
+		/* Figure out if the command line falls in the region
+		   of memory that an old kernel would have copied up
+		   to 0x90000... */
+		if (oldcmd->cl_offset < boot_params.hdr.setup_move_size)
+			cmdline_seg = ds();
+		else
+			cmdline_seg = 0x9000;
+
+		boot_params.hdr.cmd_line_ptr =
+			(cmdline_seg << 4) + oldcmd->cl_offset;
+	}
+}
+
+/*
+ * Query the keyboard lock status as given by the BIOS, and
+ * set the keyboard repeat rate to maximum.  Unclear why the latter
+ * is done here; this might be possible to kill off as stale code.
+ */
+static void keyboard_init(void)
+{
+	struct biosregs ireg, oreg;
+	initregs(&ireg);
+
+	ireg.ah = 0x02;		/* Get keyboard status */
+	intcall(0x16, &ireg, &oreg);
+	boot_params.kbd_status = oreg.al;
+
+	ireg.ax = 0x0305;	/* Set keyboard repeat rate */
+	intcall(0x16, &ireg, NULL);
+}
+
+/*
+ * Get Intel SpeedStep (IST) information.
+ */
+static void query_ist(void)
+{
+	struct biosregs ireg, oreg;
+
+	/* Some older BIOSes apparently crash on this call, so filter
+	   it from machines too old to have SpeedStep at all. */
+	if (cpu.level < 6)
+		return;
+
+	initregs(&ireg);
+	ireg.ax  = 0xe980;	 /* IST Support */
+	ireg.edx = 0x47534943;	 /* Request value */
+	intcall(0x15, &ireg, &oreg);
+
+	boot_params.ist_info.signature  = oreg.eax;
+	boot_params.ist_info.command    = oreg.ebx;
+	boot_params.ist_info.event      = oreg.ecx;
+	boot_params.ist_info.perf_level = oreg.edx;
+}
+
+/*
+ * Tell the BIOS what CPU mode we intend to run in.
+ */
+static void set_bios_mode(void)
+{
+#ifdef CONFIG_X86_64
+	struct biosregs ireg;
+
+	initregs(&ireg);
+	ireg.ax = 0xec00;
+	ireg.bx = 2;
+	intcall(0x15, &ireg, NULL);
+#endif
+}
+
+static void init_heap(void)
+{
+	char *stack_end;
+
+	if (boot_params.hdr.loadflags & CAN_USE_HEAP) {
+		asm("leal %P1(%%esp),%0"
+		    : "=r" (stack_end) : "i" (-STACK_SIZE));
+
+		heap_end = (char *)
+			((size_t)boot_params.hdr.heap_end_ptr + 0x200);
+		if (heap_end > stack_end)
+			heap_end = stack_end;
+	} else {
+		/* Boot protocol 2.00 only, no heap available */
+		puts("WARNING: Ancient bootloader, some functionality "
+		     "may be limited!\n");
+	}
+}
+
+void main(void)
+{
+	/* First, copy the boot header into the "zeropage" */
+	copy_boot_params();
+
+	/* Initialize the early-boot console */
+	console_init();
+	if (cmdline_find_option_bool("debug"))
+		puts("early console in setup code\n");
+
+	/* End of heap check */
+	init_heap();
+
+	/* Make sure we have all the proper CPU support */
+	if (validate_cpu()) {
+		puts("Unable to boot - please use a kernel appropriate "
+		     "for your CPU.\n");
+		die();
+	}
+
+	/* Tell the BIOS what CPU mode we intend to run in. */
+	set_bios_mode();
+
+	/* Detect memory layout */
+	detect_memory();
+
+	/* Set keyboard repeat rate (why?) and query the lock flags */
+	keyboard_init();
+
+	/* Query MCA information */
+	query_mca();
+
+	/* Query Intel SpeedStep (IST) information */
+	query_ist();
+
+	/* Query APM information */
+#if defined(CONFIG_APM) || defined(CONFIG_APM_MODULE)
+	query_apm_bios();
+#endif
+
+	/* Query EDD information */
+#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE)
+	query_edd();
+#endif
+
+	/* Set the video mode */
+	set_video();
+
+	/* Do the last things and invoke protected mode */
+	go_to_protected_mode();
+}

arch/x86/boot/mca.c

@@ -0,0 +1,38 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Get the MCA system description table
+ */
+
+#include "boot.h"
+
+int query_mca(void)
+{
+	struct biosregs ireg, oreg;
+	u16 len;
+
+	initregs(&ireg);
+	ireg.ah = 0xc0;
+	intcall(0x15, &ireg, &oreg);
+
+	if (oreg.eflags & X86_EFLAGS_CF)
+		return -1;	/* No MCA present */
+
+	set_fs(oreg.es);
+	len = rdfs16(oreg.bx);
+
+	if (len > sizeof(boot_params.sys_desc_table))
+		len = sizeof(boot_params.sys_desc_table);
+
+	copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len);
+	return 0;
+}

arch/x86/boot/memory.c

@@ -0,0 +1,136 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Memory detection code
+ */
+
+#include "boot.h"
+
+#define SMAP	0x534d4150	/* ASCII "SMAP" */
+
+static int detect_memory_e820(void)
+{
+	int count = 0;
+	struct biosregs ireg, oreg;
+	struct e820entry *desc = boot_params.e820_map;
+	static struct e820entry buf; /* static so it is zeroed */
+
+	initregs(&ireg);
+	ireg.ax  = 0xe820;
+	ireg.cx  = sizeof buf;
+	ireg.edx = SMAP;
+	ireg.di  = (size_t)&buf;
+
+	/*
+	 * Note: at least one BIOS is known which assumes that the
+	 * buffer pointed to by one e820 call is the same one as
+	 * the previous call, and only changes modified fields.  Therefore,
+	 * we use a temporary buffer and copy the results entry by entry.
+	 *
+	 * This routine deliberately does not try to account for
+	 * ACPI 3+ extended attributes.  This is because there are
+	 * BIOSes in the field which report zero for the valid bit for
+	 * all ranges, and we don't currently make any use of the
+	 * other attribute bits.  Revisit this if we see the extended
+	 * attribute bits deployed in a meaningful way in the future.
+	 */
+
+	do {
+		intcall(0x15, &ireg, &oreg);
+		ireg.ebx = oreg.ebx; /* for next iteration... */
+
+		/* BIOSes which terminate the chain with CF = 1 as opposed
+		   to %ebx = 0 don't always report the SMAP signature on
+		   the final, failing, probe. */
+		if (oreg.eflags & X86_EFLAGS_CF)
+			break;
+
+		/* Some BIOSes stop returning SMAP in the middle of
+		   the search loop.  We don't know exactly how the BIOS
+		   screwed up the map at that point, we might have a
+		   partial map, the full map, or complete garbage, so
+		   just return failure. */
+		if (oreg.eax != SMAP) {
+			count = 0;
+			break;
+		}
+
+		*desc++ = buf;
+		count++;
+	} while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map));
+
+	return boot_params.e820_entries = count;
+}
+
+static int detect_memory_e801(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ax = 0xe801;
+	intcall(0x15, &ireg, &oreg);
+
+	if (oreg.eflags & X86_EFLAGS_CF)
+		return -1;
+
+	/* Do we really need to do this? */
+	if (oreg.cx || oreg.dx) {
+		oreg.ax = oreg.cx;
+		oreg.bx = oreg.dx;
+	}
+
+	if (oreg.ax > 15*1024) {
+		return -1;	/* Bogus! */
+	} else if (oreg.ax == 15*1024) {
+		boot_params.alt_mem_k = (oreg.bx << 6) + oreg.ax;
+	} else {
+		/*
+		 * This ignores memory above 16MB if we have a memory
+		 * hole there.  If someone actually finds a machine
+		 * with a memory hole at 16MB and no support for
+		 * 0E820h they should probably generate a fake e820
+		 * map.
+		 */
+		boot_params.alt_mem_k = oreg.ax;
+	}
+
+	return 0;
+}
+
+static int detect_memory_88(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x88;
+	intcall(0x15, &ireg, &oreg);
+
+	boot_params.screen_info.ext_mem_k = oreg.ax;
+
+	return -(oreg.eflags & X86_EFLAGS_CF); /* 0 or -1 */
+}
+
+int detect_memory(void)
+{
+	int err = -1;
+
+	if (detect_memory_e820() > 0)
+		err = 0;
+
+	if (!detect_memory_e801())
+		err = 0;
+
+	if (!detect_memory_88())
+		err = 0;
+
+	return err;
+}

arch/x86/boot/mkcpustr.c

@@ -0,0 +1,52 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2008 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * This is a host program to preprocess the CPU strings into a
+ * compact format suitable for the setup code.
+ */
+
+#include <stdio.h>
+
+#include "../include/asm/required-features.h"
+#include "../include/asm/disabled-features.h"
+#include "../include/asm/cpufeature.h"
+#include "../kernel/cpu/capflags.c"
+
+int main(void)
+{
+	int i, j;
+	const char *str;
+
+	printf("static const char x86_cap_strs[] =\n");
+
+	for (i = 0; i < NCAPINTS; i++) {
+		for (j = 0; j < 32; j++) {
+			str = x86_cap_flags[i*32+j];
+
+			if (i == NCAPINTS-1 && j == 31) {
+				/* The last entry must be unconditional; this
+				   also consumes the compiler-added null
+				   character */
+				if (!str)
+					str = "";
+				printf("\t\"\\x%02x\\x%02x\"\"%s\"\n",
+				       i, j, str);
+			} else if (str) {
+				printf("#if REQUIRED_MASK%d & (1 << %d)\n"
+				       "\t\"\\x%02x\\x%02x\"\"%s\\0\"\n"
+				       "#endif\n",
+				       i, j, i, j, str);
+			}
+		}
+	}
+	printf("\t;\n");
+	return 0;
+}

arch/x86/boot/mtools.conf.in

@@ -0,0 +1,17 @@
+#
+# mtools configuration file for "make (b)zdisk"
+#
+
+# Actual floppy drive
+drive a:
+  file="/dev/fd0"
+
+# 1.44 MB floppy disk image
+drive v:
+  file="@OBJ@/fdimage" cylinders=80 heads=2 sectors=18 filter
+
+# 2.88 MB floppy disk image (mostly for virtual uses)
+drive w:
+  file="@OBJ@/fdimage" cylinders=80 heads=2 sectors=36 filter
+
+

arch/x86/boot/pm.c

@@ -0,0 +1,126 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Prepare the machine for transition to protected mode.
+ */
+
+#include "boot.h"
+#include <asm/segment.h>
+
+/*
+ * Invoke the realmode switch hook if present; otherwise
+ * disable all interrupts.
+ */
+static void realmode_switch_hook(void)
+{
+	if (boot_params.hdr.realmode_swtch) {
+		asm volatile("lcallw *%0"
+			     : : "m" (boot_params.hdr.realmode_swtch)
+			     : "eax", "ebx", "ecx", "edx");
+	} else {
+		asm volatile("cli");
+		outb(0x80, 0x70); /* Disable NMI */
+		io_delay();
+	}
+}
+
+/*
+ * Disable all interrupts at the legacy PIC.
+ */
+static void mask_all_interrupts(void)
+{
+	outb(0xff, 0xa1);	/* Mask all interrupts on the secondary PIC */
+	io_delay();
+	outb(0xfb, 0x21);	/* Mask all but cascade on the primary PIC */
+	io_delay();
+}
+
+/*
+ * Reset IGNNE# if asserted in the FPU.
+ */
+static void reset_coprocessor(void)
+{
+	outb(0, 0xf0);
+	io_delay();
+	outb(0, 0xf1);
+	io_delay();
+}
+
+/*
+ * Set up the GDT
+ */
+
+struct gdt_ptr {
+	u16 len;
+	u32 ptr;
+} __attribute__((packed));
+
+static void setup_gdt(void)
+{
+	/* There are machines which are known to not boot with the GDT
+	   being 8-byte unaligned.  Intel recommends 16 byte alignment. */
+	static const u64 boot_gdt[] __attribute__((aligned(16))) = {
+		/* CS: code, read/execute, 4 GB, base 0 */
+		[GDT_ENTRY_BOOT_CS] = GDT_ENTRY(0xc09b, 0, 0xfffff),
+		/* DS: data, read/write, 4 GB, base 0 */
+		[GDT_ENTRY_BOOT_DS] = GDT_ENTRY(0xc093, 0, 0xfffff),
+		/* TSS: 32-bit tss, 104 bytes, base 4096 */
+		/* We only have a TSS here to keep Intel VT happy;
+		   we don't actually use it for anything. */
+		[GDT_ENTRY_BOOT_TSS] = GDT_ENTRY(0x0089, 4096, 103),
+	};
+	/* Xen HVM incorrectly stores a pointer to the gdt_ptr, instead
+	   of the gdt_ptr contents.  Thus, make it static so it will
+	   stay in memory, at least long enough that we switch to the
+	   proper kernel GDT. */
+	static struct gdt_ptr gdt;
+
+	gdt.len = sizeof(boot_gdt)-1;
+	gdt.ptr = (u32)&boot_gdt + (ds() << 4);
+
+	asm volatile("lgdtl %0" : : "m" (gdt));
+}
+
+/*
+ * Set up the IDT
+ */
+static void setup_idt(void)
+{
+	static const struct gdt_ptr null_idt = {0, 0};
+	asm volatile("lidtl %0" : : "m" (null_idt));
+}
+
+/*
+ * Actual invocation sequence
+ */
+void go_to_protected_mode(void)
+{
+	/* Hook before leaving real mode, also disables interrupts */
+	realmode_switch_hook();
+
+	/* Enable the A20 gate */
+	if (enable_a20()) {
+		puts("A20 gate not responding, unable to boot...\n");
+		die();
+	}
+
+	/* Reset coprocessor (IGNNE#) */
+	reset_coprocessor();
+
+	/* Mask all interrupts in the PIC */
+	mask_all_interrupts();
+
+	/* Actual transition to protected mode... */
+	setup_idt();
+	setup_gdt();
+	protected_mode_jump(boot_params.hdr.code32_start,
+			    (u32)&boot_params + (ds() << 4));
+}

arch/x86/boot/pmjump.S

@@ -0,0 +1,77 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * The actual transition into protected mode
+ */
+
+#include <asm/boot.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+#include <linux/linkage.h>
+
+	.text
+	.code16
+
+/*
+ * void protected_mode_jump(u32 entrypoint, u32 bootparams);
+ */
+GLOBAL(protected_mode_jump)
+	movl	%edx, %esi		# Pointer to boot_params table
+
+	xorl	%ebx, %ebx
+	movw	%cs, %bx
+	shll	$4, %ebx
+	addl	%ebx, 2f
+	jmp	1f			# Short jump to serialize on 386/486
+1:
+
+	movw	$__BOOT_DS, %cx
+	movw	$__BOOT_TSS, %di
+
+	movl	%cr0, %edx
+	orb	$X86_CR0_PE, %dl	# Protected mode
+	movl	%edx, %cr0
+
+	# Transition to 32-bit mode
+	.byte	0x66, 0xea		# ljmpl opcode
+2:	.long	in_pm32			# offset
+	.word	__BOOT_CS		# segment
+ENDPROC(protected_mode_jump)
+
+	.code32
+	.section ".text32","ax"
+GLOBAL(in_pm32)
+	# Set up data segments for flat 32-bit mode
+	movl	%ecx, %ds
+	movl	%ecx, %es
+	movl	%ecx, %fs
+	movl	%ecx, %gs
+	movl	%ecx, %ss
+	# The 32-bit code sets up its own stack, but this way we do have
+	# a valid stack if some debugging hack wants to use it.
+	addl	%ebx, %esp
+
+	# Set up TR to make Intel VT happy
+	ltr	%di
+
+	# Clear registers to allow for future extensions to the
+	# 32-bit boot protocol
+	xorl	%ecx, %ecx
+	xorl	%edx, %edx
+	xorl	%ebx, %ebx
+	xorl	%ebp, %ebp
+	xorl	%edi, %edi
+
+	# Set up LDTR to make Intel VT happy
+	lldt	%cx
+
+	jmpl	*%eax			# Jump to the 32-bit entrypoint
+ENDPROC(in_pm32)

arch/x86/boot/printf.c

@@ -0,0 +1,309 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Oh, it's a waste of space, but oh-so-yummy for debugging.  This
+ * version of printf() does not include 64-bit support.  "Live with
+ * it."
+ *
+ */
+
+#include "boot.h"
+
+static int skip_atoi(const char **s)
+{
+	int i = 0;
+
+	while (isdigit(**s))
+		i = i * 10 + *((*s)++) - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SMALL	32		/* Must be 32 == 0x20 */
+#define SPECIAL	64		/* 0x */
+
+#define __do_div(n, base) ({ \
+int __res; \
+__res = ((unsigned long) n) % (unsigned) base; \
+n = ((unsigned long) n) / (unsigned) base; \
+__res; })
+
+static char *number(char *str, long num, int base, int size, int precision,
+		    int type)
+{
+	/* we are called with base 8, 10 or 16, only, thus don't need "G..."  */
+	static const char digits[16] = "0123456789ABCDEF"; /* "GHIJKLMNOPQRSTUVWXYZ"; */
+
+	char tmp[66];
+	char c, sign, locase;
+	int i;
+
+	/* locase = 0 or 0x20. ORing digits or letters with 'locase'
+	 * produces same digits or (maybe lowercased) letters */
+	locase = (type & SMALL);
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 16)
+		return NULL;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if (num < 0) {
+			sign = '-';
+			num = -num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++] = '0';
+	else
+		while (num != 0)
+			tmp[i++] = (digits[__do_div(num, base)] | locase);
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type & (ZEROPAD + LEFT)))
+		while (size-- > 0)
+			*str++ = ' ';
+	if (sign)
+		*str++ = sign;
+	if (type & SPECIAL) {
+		if (base == 8)
+			*str++ = '0';
+		else if (base == 16) {
+			*str++ = '0';
+			*str++ = ('X' | locase);
+		}
+	}
+	if (!(type & LEFT))
+		while (size-- > 0)
+			*str++ = c;
+	while (i < precision--)
+		*str++ = '0';
+	while (i-- > 0)
+		*str++ = tmp[i];
+	while (size-- > 0)
+		*str++ = ' ';
+	return str;
+}
+
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+	int len;
+	unsigned long num;
+	int i, base;
+	char *str;
+	const char *s;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+
+	for (str = buf; *fmt; ++fmt) {
+		if (*fmt != '%') {
+			*str++ = *fmt;
+			continue;
+		}
+
+		/* process flags */
+		flags = 0;
+	      repeat:
+		++fmt;		/* this also skips first '%' */
+		switch (*fmt) {
+		case '-':
+			flags |= LEFT;
+			goto repeat;
+		case '+':
+			flags |= PLUS;
+			goto repeat;
+		case ' ':
+			flags |= SPACE;
+			goto repeat;
+		case '#':
+			flags |= SPECIAL;
+			goto repeat;
+		case '0':
+			flags |= ZEROPAD;
+			goto repeat;
+		}
+
+		/* get field width */
+		field_width = -1;
+		if (isdigit(*fmt))
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;
+			if (isdigit(*fmt))
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L') {
+			qualifier = *fmt;
+			++fmt;
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+		case 'c':
+			if (!(flags & LEFT))
+				while (--field_width > 0)
+					*str++ = ' ';
+			*str++ = (unsigned char)va_arg(args, int);
+			while (--field_width > 0)
+				*str++ = ' ';
+			continue;
+
+		case 's':
+			s = va_arg(args, char *);
+			len = strnlen(s, precision);
+
+			if (!(flags & LEFT))
+				while (len < field_width--)
+					*str++ = ' ';
+			for (i = 0; i < len; ++i)
+				*str++ = *s++;
+			while (len < field_width--)
+				*str++ = ' ';
+			continue;
+
+		case 'p':
+			if (field_width == -1) {
+				field_width = 2 * sizeof(void *);
+				flags |= ZEROPAD;
+			}
+			str = number(str,
+				     (unsigned long)va_arg(args, void *), 16,
+				     field_width, precision, flags);
+			continue;
+
+		case 'n':
+			if (qualifier == 'l') {
+				long *ip = va_arg(args, long *);
+				*ip = (str - buf);
+			} else {
+				int *ip = va_arg(args, int *);
+				*ip = (str - buf);
+			}
+			continue;
+
+		case '%':
+			*str++ = '%';
+			continue;
+
+			/* integer number formats - set up the flags and "break" */
+		case 'o':
+			base = 8;
+			break;
+
+		case 'x':
+			flags |= SMALL;
+		case 'X':
+			base = 16;
+			break;
+
+		case 'd':
+		case 'i':
+			flags |= SIGN;
+		case 'u':
+			break;
+
+		default:
+			*str++ = '%';
+			if (*fmt)
+				*str++ = *fmt;
+			else
+				--fmt;
+			continue;
+		}
+		if (qualifier == 'l')
+			num = va_arg(args, unsigned long);
+		else if (qualifier == 'h') {
+			num = (unsigned short)va_arg(args, int);
+			if (flags & SIGN)
+				num = (short)num;
+		} else if (flags & SIGN)
+			num = va_arg(args, int);
+		else
+			num = va_arg(args, unsigned int);
+		str = number(str, num, base, field_width, precision, flags);
+	}
+	*str = '\0';
+	return str - buf;
+}
+
+int sprintf(char *buf, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i = vsprintf(buf, fmt, args);
+	va_end(args);
+	return i;
+}
+
+int printf(const char *fmt, ...)
+{
+	char printf_buf[1024];
+	va_list args;
+	int printed;
+
+	va_start(args, fmt);
+	printed = vsprintf(printf_buf, fmt, args);
+	va_end(args);
+
+	puts(printf_buf);
+
+	return printed;
+}

arch/x86/boot/regs.c

@@ -0,0 +1,30 @@
+/* -----------------------------------------------------------------------
+ *
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Simple helper function for initializing a register set.
+ *
+ * Note that this sets EFLAGS_CF in the input register set; this
+ * makes it easier to catch functions which do nothing but don't
+ * explicitly set CF.
+ */
+
+#include "boot.h"
+#include "string.h"
+
+void initregs(struct biosregs *reg)
+{
+	memset(reg, 0, sizeof *reg);
+	reg->eflags |= X86_EFLAGS_CF;
+	reg->ds = ds();
+	reg->es = ds();
+	reg->fs = fs();
+	reg->gs = gs();
+}

arch/x86/boot/setup.ld

@@ -0,0 +1,64 @@
+/*
+ * setup.ld
+ *
+ * Linker script for the i386 setup code
+ */
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+ENTRY(_start)
+
+SECTIONS
+{
+	. = 0;
+	.bstext		: { *(.bstext) }
+	.bsdata		: { *(.bsdata) }
+
+	. = 495;
+	.header		: { *(.header) }
+	.entrytext	: { *(.entrytext) }
+	.inittext	: { *(.inittext) }
+	.initdata	: { *(.initdata) }
+	__end_init = .;
+
+	.text		: { *(.text) }
+	.text32		: { *(.text32) }
+
+	. = ALIGN(16);
+	.rodata		: { *(.rodata*) }
+
+	.videocards	: {
+		video_cards = .;
+		*(.videocards)
+		video_cards_end = .;
+	}
+
+	. = ALIGN(16);
+	.data		: { *(.data*) }
+
+	.signature	: {
+		setup_sig = .;
+		LONG(0x5a5aaa55)
+	}
+
+
+	. = ALIGN(16);
+	.bss		:
+	{
+		__bss_start = .;
+		*(.bss)
+		__bss_end = .;
+	}
+	. = ALIGN(16);
+	_end = .;
+
+	/DISCARD/ : { *(.note*) }
+
+	/*
+	 * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+	 */
+	. = ASSERT(_end <= 0x8000, "Setup too big!");
+	. = ASSERT(hdr == 0x1f1, "The setup header has the wrong offset!");
+	/* Necessary for the very-old-loader check to work... */
+	. = ASSERT(__end_init <= 5*512, "init sections too big!");
+
+}

arch/x86/boot/string.c

@@ -0,0 +1,157 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Very basic string functions
+ */
+
+#include <linux/types.h>
+#include "ctype.h"
+
+int memcmp(const void *s1, const void *s2, size_t len)
+{
+	u8 diff;
+	asm("repe; cmpsb; setnz %0"
+	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	return diff;
+}
+
+int strcmp(const char *str1, const char *str2)
+{
+	const unsigned char *s1 = (const unsigned char *)str1;
+	const unsigned char *s2 = (const unsigned char *)str2;
+	int delta = 0;
+
+	while (*s1 || *s2) {
+		delta = *s2 - *s1;
+		if (delta)
+			return delta;
+		s1++;
+		s2++;
+	}
+	return 0;
+}
+
+int strncmp(const char *cs, const char *ct, size_t count)
+{
+	unsigned char c1, c2;
+
+	while (count) {
+		c1 = *cs++;
+		c2 = *ct++;
+		if (c1 != c2)
+			return c1 < c2 ? -1 : 1;
+		if (!c1)
+			break;
+		count--;
+	}
+	return 0;
+}
+
+size_t strnlen(const char *s, size_t maxlen)
+{
+	const char *es = s;
+	while (*es && maxlen) {
+		es++;
+		maxlen--;
+	}
+
+	return (es - s);
+}
+
+unsigned int atou(const char *s)
+{
+	unsigned int i = 0;
+	while (isdigit(*s))
+		i = i * 10 + (*s++ - '0');
+	return i;
+}
+
+/* Works only for digits and letters, but small and fast */
+#define TOLOWER(x) ((x) | 0x20)
+
+static unsigned int simple_guess_base(const char *cp)
+{
+	if (cp[0] == '0') {
+		if (TOLOWER(cp[1]) == 'x' && isxdigit(cp[2]))
+			return 16;
+		else
+			return 8;
+	} else {
+		return 10;
+	}
+}
+
+/**
+ * simple_strtoull - convert a string to an unsigned long long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ */
+
+unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
+{
+	unsigned long long result = 0;
+
+	if (!base)
+		base = simple_guess_base(cp);
+
+	if (base == 16 && cp[0] == '0' && TOLOWER(cp[1]) == 'x')
+		cp += 2;
+
+	while (isxdigit(*cp)) {
+		unsigned int value;
+
+		value = isdigit(*cp) ? *cp - '0' : TOLOWER(*cp) - 'a' + 10;
+		if (value >= base)
+			break;
+		result = result * base + value;
+		cp++;
+	}
+	if (endp)
+		*endp = (char *)cp;
+
+	return result;
+}
+
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t strlen(const char *s)
+{
+	const char *sc;
+
+	for (sc = s; *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+
+/**
+ * strstr - Find the first substring in a %NUL terminated string
+ * @s1: The string to be searched
+ * @s2: The string to search for
+ */
+char *strstr(const char *s1, const char *s2)
+{
+	size_t l1, l2;
+
+	l2 = strlen(s2);
+	if (!l2)
+		return (char *)s1;
+	l1 = strlen(s1);
+	while (l1 >= l2) {
+		l1--;
+		if (!memcmp(s1, s2, l2))
+			return (char *)s1;
+		s1++;
+	}
+	return NULL;
+}

arch/x86/boot/string.h

@@ -0,0 +1,21 @@
+#ifndef BOOT_STRING_H
+#define BOOT_STRING_H
+
+/* Undef any of these macros coming from string_32.h. */
+#undef memcpy
+#undef memset
+#undef memcmp
+
+void *memcpy(void *dst, const void *src, size_t len);
+void *memset(void *dst, int c, size_t len);
+int memcmp(const void *s1, const void *s2, size_t len);
+
+/*
+ * Access builtin version by default. If one needs to use optimized version,
+ * do "undef memcpy" in .c file and link against right string.c
+ */
+#define memcpy(d,s,l) __builtin_memcpy(d,s,l)
+#define memset(d,c,l) __builtin_memset(d,c,l)
+#define memcmp	__builtin_memcmp
+
+#endif /* BOOT_STRING_H */

arch/x86/boot/tools/build.c

@@ -0,0 +1,435 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 1997 Martin Mares
+ *  Copyright (C) 2007 H. Peter Anvin
+ */
+
+/*
+ * This file builds a disk-image from three different files:
+ *
+ * - setup: 8086 machine code, sets up system parm
+ * - system: 80386 code for actual system
+ * - zoffset.h: header with ZO_* defines
+ *
+ * It does some checking that all files are of the correct type, and writes
+ * the result to the specified destination, removing headers and padding to
+ * the right amount. It also writes some system data to stdout.
+ */
+
+/*
+ * Changes by tytso to allow root device specification
+ * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
+ * Cross compiling fixes by Gertjan van Wingerde, July 1996
+ * Rewritten by Martin Mares, April 1997
+ * Substantially overhauled by H. Peter Anvin, April 2007
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include <tools/le_byteshift.h>
+
+typedef unsigned char  u8;
+typedef unsigned short u16;
+typedef unsigned int   u32;
+
+#define DEFAULT_MAJOR_ROOT 0
+#define DEFAULT_MINOR_ROOT 0
+#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT)
+
+/* Minimal number of setup sectors */
+#define SETUP_SECT_MIN 5
+#define SETUP_SECT_MAX 64
+
+/* This must be large enough to hold the entire setup */
+u8 buf[SETUP_SECT_MAX*512];
+int is_big_kernel;
+
+#define PECOFF_RELOC_RESERVE 0x20
+
+unsigned long efi32_stub_entry;
+unsigned long efi64_stub_entry;
+unsigned long efi_pe_entry;
+unsigned long startup_64;
+
+/*----------------------------------------------------------------------*/
+
+static const u32 crctab32[] = {
+	0x00000000, 0x77073096, 0xee0e612c, 0x990951ba, 0x076dc419,
+	0x706af48f, 0xe963a535, 0x9e6495a3, 0x0edb8832, 0x79dcb8a4,
+	0xe0d5e91e, 0x97d2d988, 0x09b64c2b, 0x7eb17cbd, 0xe7b82d07,
+	0x90bf1d91, 0x1db71064, 0x6ab020f2, 0xf3b97148, 0x84be41de,
+	0x1adad47d, 0x6ddde4eb, 0xf4d4b551, 0x83d385c7, 0x136c9856,
+	0x646ba8c0, 0xfd62f97a, 0x8a65c9ec, 0x14015c4f, 0x63066cd9,
+	0xfa0f3d63, 0x8d080df5, 0x3b6e20c8, 0x4c69105e, 0xd56041e4,
+	0xa2677172, 0x3c03e4d1, 0x4b04d447, 0xd20d85fd, 0xa50ab56b,
+	0x35b5a8fa, 0x42b2986c, 0xdbbbc9d6, 0xacbcf940, 0x32d86ce3,
+	0x45df5c75, 0xdcd60dcf, 0xabd13d59, 0x26d930ac, 0x51de003a,
+	0xc8d75180, 0xbfd06116, 0x21b4f4b5, 0x56b3c423, 0xcfba9599,
+	0xb8bda50f, 0x2802b89e, 0x5f058808, 0xc60cd9b2, 0xb10be924,
+	0x2f6f7c87, 0x58684c11, 0xc1611dab, 0xb6662d3d, 0x76dc4190,
+	0x01db7106, 0x98d220bc, 0xefd5102a, 0x71b18589, 0x06b6b51f,
+	0x9fbfe4a5, 0xe8b8d433, 0x7807c9a2, 0x0f00f934, 0x9609a88e,
+	0xe10e9818, 0x7f6a0dbb, 0x086d3d2d, 0x91646c97, 0xe6635c01,
+	0x6b6b51f4, 0x1c6c6162, 0x856530d8, 0xf262004e, 0x6c0695ed,
+	0x1b01a57b, 0x8208f4c1, 0xf50fc457, 0x65b0d9c6, 0x12b7e950,
+	0x8bbeb8ea, 0xfcb9887c, 0x62dd1ddf, 0x15da2d49, 0x8cd37cf3,
+	0xfbd44c65, 0x4db26158, 0x3ab551ce, 0xa3bc0074, 0xd4bb30e2,
+	0x4adfa541, 0x3dd895d7, 0xa4d1c46d, 0xd3d6f4fb, 0x4369e96a,
+	0x346ed9fc, 0xad678846, 0xda60b8d0, 0x44042d73, 0x33031de5,
+	0xaa0a4c5f, 0xdd0d7cc9, 0x5005713c, 0x270241aa, 0xbe0b1010,
+	0xc90c2086, 0x5768b525, 0x206f85b3, 0xb966d409, 0xce61e49f,
+	0x5edef90e, 0x29d9c998, 0xb0d09822, 0xc7d7a8b4, 0x59b33d17,
+	0x2eb40d81, 0xb7bd5c3b, 0xc0ba6cad, 0xedb88320, 0x9abfb3b6,
+	0x03b6e20c, 0x74b1d29a, 0xead54739, 0x9dd277af, 0x04db2615,
+	0x73dc1683, 0xe3630b12, 0x94643b84, 0x0d6d6a3e, 0x7a6a5aa8,
+	0xe40ecf0b, 0x9309ff9d, 0x0a00ae27, 0x7d079eb1, 0xf00f9344,
+	0x8708a3d2, 0x1e01f268, 0x6906c2fe, 0xf762575d, 0x806567cb,
+	0x196c3671, 0x6e6b06e7, 0xfed41b76, 0x89d32be0, 0x10da7a5a,
+	0x67dd4acc, 0xf9b9df6f, 0x8ebeeff9, 0x17b7be43, 0x60b08ed5,
+	0xd6d6a3e8, 0xa1d1937e, 0x38d8c2c4, 0x4fdff252, 0xd1bb67f1,
+	0xa6bc5767, 0x3fb506dd, 0x48b2364b, 0xd80d2bda, 0xaf0a1b4c,
+	0x36034af6, 0x41047a60, 0xdf60efc3, 0xa867df55, 0x316e8eef,
+	0x4669be79, 0xcb61b38c, 0xbc66831a, 0x256fd2a0, 0x5268e236,
+	0xcc0c7795, 0xbb0b4703, 0x220216b9, 0x5505262f, 0xc5ba3bbe,
+	0xb2bd0b28, 0x2bb45a92, 0x5cb36a04, 0xc2d7ffa7, 0xb5d0cf31,
+	0x2cd99e8b, 0x5bdeae1d, 0x9b64c2b0, 0xec63f226, 0x756aa39c,
+	0x026d930a, 0x9c0906a9, 0xeb0e363f, 0x72076785, 0x05005713,
+	0x95bf4a82, 0xe2b87a14, 0x7bb12bae, 0x0cb61b38, 0x92d28e9b,
+	0xe5d5be0d, 0x7cdcefb7, 0x0bdbdf21, 0x86d3d2d4, 0xf1d4e242,
+	0x68ddb3f8, 0x1fda836e, 0x81be16cd, 0xf6b9265b, 0x6fb077e1,
+	0x18b74777, 0x88085ae6, 0xff0f6a70, 0x66063bca, 0x11010b5c,
+	0x8f659eff, 0xf862ae69, 0x616bffd3, 0x166ccf45, 0xa00ae278,
+	0xd70dd2ee, 0x4e048354, 0x3903b3c2, 0xa7672661, 0xd06016f7,
+	0x4969474d, 0x3e6e77db, 0xaed16a4a, 0xd9d65adc, 0x40df0b66,
+	0x37d83bf0, 0xa9bcae53, 0xdebb9ec5, 0x47b2cf7f, 0x30b5ffe9,
+	0xbdbdf21c, 0xcabac28a, 0x53b39330, 0x24b4a3a6, 0xbad03605,
+	0xcdd70693, 0x54de5729, 0x23d967bf, 0xb3667a2e, 0xc4614ab8,
+	0x5d681b02, 0x2a6f2b94, 0xb40bbe37, 0xc30c8ea1, 0x5a05df1b,
+	0x2d02ef8d
+};
+
+static u32 partial_crc32_one(u8 c, u32 crc)
+{
+	return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8);
+}
+
+static u32 partial_crc32(const u8 *s, int len, u32 crc)
+{
+	while (len--)
+		crc = partial_crc32_one(*s++, crc);
+	return crc;
+}
+
+static void die(const char * str, ...)
+{
+	va_list args;
+	va_start(args, str);
+	vfprintf(stderr, str, args);
+	fputc('\n', stderr);
+	exit(1);
+}
+
+static void usage(void)
+{
+	die("Usage: build setup system zoffset.h image");
+}
+
+#ifdef CONFIG_EFI_STUB
+
+static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
+{
+	unsigned int pe_header;
+	unsigned short num_sections;
+	u8 *section;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+	num_sections = get_unaligned_le16(&buf[pe_header + 6]);
+
+#ifdef CONFIG_X86_32
+	section = &buf[pe_header + 0xa8];
+#else
+	section = &buf[pe_header + 0xb8];
+#endif
+
+	while (num_sections > 0) {
+		if (strncmp((char*)section, section_name, 8) == 0) {
+			/* section header size field */
+			put_unaligned_le32(size, section + 0x8);
+
+			/* section header vma field */
+			put_unaligned_le32(vma, section + 0xc);
+
+			/* section header 'size of initialised data' field */
+			put_unaligned_le32(datasz, section + 0x10);
+
+			/* section header 'file offset' field */
+			put_unaligned_le32(offset, section + 0x14);
+
+			break;
+		}
+		section += 0x28;
+		num_sections--;
+	}
+}
+
+static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
+{
+	update_pecoff_section_header_fields(section_name, offset, size, size, offset);
+}
+
+static void update_pecoff_setup_and_reloc(unsigned int size)
+{
+	u32 setup_offset = 0x200;
+	u32 reloc_offset = size - PECOFF_RELOC_RESERVE;
+	u32 setup_size = reloc_offset - setup_offset;
+
+	update_pecoff_section_header(".setup", setup_offset, setup_size);
+	update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
+
+	/*
+	 * Modify .reloc section contents with a single entry. The
+	 * relocation is applied to offset 10 of the relocation section.
+	 */
+	put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
+	put_unaligned_le32(10, &buf[reloc_offset + 4]);
+}
+
+static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
+{
+	unsigned int pe_header;
+	unsigned int text_sz = file_sz - text_start;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/*
+	 * Size of code: Subtract the size of the first sector (512 bytes)
+	 * which includes the header.
+	 */
+	put_unaligned_le32(file_sz - 512, &buf[pe_header + 0x1c]);
+
+	/*
+	 * Address of entry point for PE/COFF executable
+	 */
+	put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]);
+
+	update_pecoff_section_header(".text", text_start, text_sz);
+}
+
+static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz)
+{
+	unsigned int pe_header;
+	unsigned int bss_sz = init_sz - file_sz;
+
+	pe_header = get_unaligned_le32(&buf[0x3c]);
+
+	/* Size of uninitialized data */
+	put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]);
+
+	/* Size of image */
+	put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
+
+	update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0);
+}
+
+static int reserve_pecoff_reloc_section(int c)
+{
+	/* Reserve 0x20 bytes for .reloc section */
+	memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+	return PECOFF_RELOC_RESERVE;
+}
+
+static void efi_stub_defaults(void)
+{
+	/* Defaults for old kernel */
+#ifdef CONFIG_X86_32
+	efi_pe_entry = 0x10;
+#else
+	efi_pe_entry = 0x210;
+	startup_64 = 0x200;
+#endif
+}
+
+static void efi_stub_entry_update(void)
+{
+	unsigned long addr = efi32_stub_entry;
+
+#ifdef CONFIG_X86_64
+	/* Yes, this is really how we defined it :( */
+	addr = efi64_stub_entry - 0x200;
+#endif
+
+#ifdef CONFIG_EFI_MIXED
+	if (efi32_stub_entry != addr)
+		die("32-bit and 64-bit EFI entry points do not match\n");
+#endif
+	put_unaligned_le32(addr, &buf[0x264]);
+}
+
+#else
+
+static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
+static inline void update_pecoff_text(unsigned int text_start,
+				      unsigned int file_sz) {}
+static inline void update_pecoff_bss(unsigned int file_sz,
+				     unsigned int init_sz) {}
+static inline void efi_stub_defaults(void) {}
+static inline void efi_stub_entry_update(void) {}
+
+static inline int reserve_pecoff_reloc_section(int c)
+{
+	return 0;
+}
+#endif /* CONFIG_EFI_STUB */
+
+
+/*
+ * Parse zoffset.h and find the entry points. We could just #include zoffset.h
+ * but that would mean tools/build would have to be rebuilt every time. It's
+ * not as if parsing it is hard...
+ */
+#define PARSE_ZOFS(p, sym) do { \
+	if (!strncmp(p, "#define ZO_" #sym " ", 11+sizeof(#sym)))	\
+		sym = strtoul(p + 11 + sizeof(#sym), NULL, 16);		\
+} while (0)
+
+static void parse_zoffset(char *fname)
+{
+	FILE *file;
+	char *p;
+	int c;
+
+	file = fopen(fname, "r");
+	if (!file)
+		die("Unable to open `%s': %m", fname);
+	c = fread(buf, 1, sizeof(buf) - 1, file);
+	if (ferror(file))
+		die("read-error on `zoffset.h'");
+	fclose(file);
+	buf[c] = 0;
+
+	p = (char *)buf;
+
+	while (p && *p) {
+		PARSE_ZOFS(p, efi32_stub_entry);
+		PARSE_ZOFS(p, efi64_stub_entry);
+		PARSE_ZOFS(p, efi_pe_entry);
+		PARSE_ZOFS(p, startup_64);
+
+		p = strchr(p, '\n');
+		while (p && (*p == '\r' || *p == '\n'))
+			p++;
+	}
+}
+
+int main(int argc, char ** argv)
+{
+	unsigned int i, sz, setup_sectors, init_sz;
+	int c;
+	u32 sys_size;
+	struct stat sb;
+	FILE *file, *dest;
+	int fd;
+	void *kernel;
+	u32 crc = 0xffffffffUL;
+
+	efi_stub_defaults();
+
+	if (argc != 5)
+		usage();
+	parse_zoffset(argv[3]);
+
+	dest = fopen(argv[4], "w");
+	if (!dest)
+		die("Unable to write `%s': %m", argv[4]);
+
+	/* Copy the setup code */
+	file = fopen(argv[1], "r");
+	if (!file)
+		die("Unable to open `%s': %m", argv[1]);
+	c = fread(buf, 1, sizeof(buf), file);
+	if (ferror(file))
+		die("read-error on `setup'");
+	if (c < 1024)
+		die("The setup must be at least 1024 bytes");
+	if (get_unaligned_le16(&buf[510]) != 0xAA55)
+		die("Boot block hasn't got boot flag (0xAA55)");
+	fclose(file);
+
+	c += reserve_pecoff_reloc_section(c);
+
+	/* Pad unused space with zeros */
+	setup_sectors = (c + 511) / 512;
+	if (setup_sectors < SETUP_SECT_MIN)
+		setup_sectors = SETUP_SECT_MIN;
+	i = setup_sectors*512;
+	memset(buf+c, 0, i-c);
+
+	update_pecoff_setup_and_reloc(i);
+
+	/* Set the default root device */
+	put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
+
+	printf("Setup is %d bytes (padded to %d bytes).\n", c, i);
+
+	/* Open and stat the kernel file */
+	fd = open(argv[2], O_RDONLY);
+	if (fd < 0)
+		die("Unable to open `%s': %m", argv[2]);
+	if (fstat(fd, &sb))
+		die("Unable to stat `%s': %m", argv[2]);
+	sz = sb.st_size;
+	printf("System is %d kB\n", (sz+1023)/1024);
+	kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
+	if (kernel == MAP_FAILED)
+		die("Unable to mmap '%s': %m", argv[2]);
+	/* Number of 16-byte paragraphs, including space for a 4-byte CRC */
+	sys_size = (sz + 15 + 4) / 16;
+
+	/* Patch the setup code with the appropriate size parameters */
+	buf[0x1f1] = setup_sectors-1;
+	put_unaligned_le32(sys_size, &buf[0x1f4]);
+
+	update_pecoff_text(setup_sectors * 512, i + (sys_size * 16));
+	init_sz = get_unaligned_le32(&buf[0x260]);
+	update_pecoff_bss(i + (sys_size * 16), init_sz);
+
+	efi_stub_entry_update();
+
+	crc = partial_crc32(buf, i, crc);
+	if (fwrite(buf, 1, i, dest) != i)
+		die("Writing setup failed");
+
+	/* Copy the kernel code */
+	crc = partial_crc32(kernel, sz, crc);
+	if (fwrite(kernel, 1, sz, dest) != sz)
+		die("Writing kernel failed");
+
+	/* Add padding leaving 4 bytes for the checksum */
+	while (sz++ < (sys_size*16) - 4) {
+		crc = partial_crc32_one('\0', crc);
+		if (fwrite("\0", 1, 1, dest) != 1)
+			die("Writing padding failed");
+	}
+
+	/* Write the CRC */
+	printf("CRC %x\n", crc);
+	put_unaligned_le32(crc, buf);
+	if (fwrite(buf, 1, 4, dest) != 4)
+		die("Writing CRC failed");
+
+	/* Catch any delayed write failures */
+	if (fclose(dest))
+		die("Writing image failed");
+
+	close(fd);
+
+	/* Everything is OK */
+	return 0;
+}

arch/x86/boot/tty.c

@@ -0,0 +1,139 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Very simple screen and serial I/O
+ */
+
+#include "boot.h"
+
+int early_serial_base;
+
+#define XMTRDY          0x20
+
+#define TXR             0       /*  Transmit register (WRITE) */
+#define LSR             5       /*  Line Status               */
+
+/*
+ * These functions are in .inittext so they can be used to signal
+ * error during initialization.
+ */
+
+static void __attribute__((section(".inittext"))) serial_putchar(int ch)
+{
+	unsigned timeout = 0xffff;
+
+	while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout)
+		cpu_relax();
+
+	outb(ch, early_serial_base + TXR);
+}
+
+static void __attribute__((section(".inittext"))) bios_putchar(int ch)
+{
+	struct biosregs ireg;
+
+	initregs(&ireg);
+	ireg.bx = 0x0007;
+	ireg.cx = 0x0001;
+	ireg.ah = 0x0e;
+	ireg.al = ch;
+	intcall(0x10, &ireg, NULL);
+}
+
+void __attribute__((section(".inittext"))) putchar(int ch)
+{
+	if (ch == '\n')
+		putchar('\r');	/* \n -> \r\n */
+
+	bios_putchar(ch);
+
+	if (early_serial_base != 0)
+		serial_putchar(ch);
+}
+
+void __attribute__((section(".inittext"))) puts(const char *str)
+{
+	while (*str)
+		putchar(*str++);
+}
+
+/*
+ * Read the CMOS clock through the BIOS, and return the
+ * seconds in BCD.
+ */
+
+static u8 gettime(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x02;
+	intcall(0x1a, &ireg, &oreg);
+
+	return oreg.dh;
+}
+
+/*
+ * Read from the keyboard
+ */
+int getchar(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	/* ireg.ah = 0x00; */
+	intcall(0x16, &ireg, &oreg);
+
+	return oreg.al;
+}
+
+static int kbd_pending(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x01;
+	intcall(0x16, &ireg, &oreg);
+
+	return !(oreg.eflags & X86_EFLAGS_ZF);
+}
+
+void kbd_flush(void)
+{
+	for (;;) {
+		if (!kbd_pending())
+			break;
+		getchar();
+	}
+}
+
+int getchar_timeout(void)
+{
+	int cnt = 30;
+	int t0, t1;
+
+	t0 = gettime();
+
+	while (cnt) {
+		if (kbd_pending())
+			return getchar();
+
+		t1 = gettime();
+		if (t0 != t1) {
+			cnt--;
+			t0 = t1;
+		}
+	}
+
+	return 0;		/* Timeout! */
+}
+

arch/x86/boot/version.c

@@ -0,0 +1,21 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Kernel version string
+ */
+
+#include "boot.h"
+#include <generated/utsrelease.h>
+#include <generated/compile.h>
+
+const char kernel_version[] =
+	UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") "
+	UTS_VERSION;

arch/x86/boot/vesa.h

@@ -0,0 +1,72 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 1999-2007 H. Peter Anvin - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+#ifndef BOOT_VESA_H
+#define BOOT_VESA_H
+
+typedef struct {
+	u16 off, seg;
+} far_ptr;
+
+/* VESA General Information table */
+struct vesa_general_info {
+	u32 signature;		/* 0 Magic number = "VESA" */
+	u16 version;		/* 4 */
+	far_ptr vendor_string;	/* 6 */
+	u32 capabilities;	/* 10 */
+	far_ptr video_mode_ptr;	/* 14 */
+	u16 total_memory;	/* 18 */
+
+	u8 reserved[236];	/* 20 */
+} __attribute__ ((packed));
+
+#define VESA_MAGIC ('V' + ('E' << 8) + ('S' << 16) + ('A' << 24))
+
+struct vesa_mode_info {
+	u16 mode_attr;		/* 0 */
+	u8 win_attr[2];		/* 2 */
+	u16 win_grain;		/* 4 */
+	u16 win_size;		/* 6 */
+	u16 win_seg[2];		/* 8 */
+	far_ptr win_scheme;	/* 12 */
+	u16 logical_scan;	/* 16 */
+
+	u16 h_res;		/* 18 */
+	u16 v_res;		/* 20 */
+	u8 char_width;		/* 22 */
+	u8 char_height;		/* 23 */
+	u8 memory_planes;	/* 24 */
+	u8 bpp;			/* 25 */
+	u8 banks;		/* 26 */
+	u8 memory_layout;	/* 27 */
+	u8 bank_size;		/* 28 */
+	u8 image_planes;	/* 29 */
+	u8 page_function;	/* 30 */
+
+	u8 rmask;		/* 31 */
+	u8 rpos;		/* 32 */
+	u8 gmask;		/* 33 */
+	u8 gpos;		/* 34 */
+	u8 bmask;		/* 35 */
+	u8 bpos;		/* 36 */
+	u8 resv_mask;		/* 37 */
+	u8 resv_pos;		/* 38 */
+	u8 dcm_info;		/* 39 */
+
+	u32 lfb_ptr;		/* 40 Linear frame buffer address */
+	u32 offscreen_ptr;	/* 44 Offscreen memory address */
+	u16 offscreen_size;	/* 48 */
+
+	u8 reserved[206];	/* 50 */
+} __attribute__ ((packed));
+
+#endif				/* LIB_SYS_VESA_H */

arch/x86/boot/video-bios.c

@@ -0,0 +1,128 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Standard video BIOS modes
+ *
+ * We have two options for this; silent and scanned.
+ */
+
+#include "boot.h"
+#include "video.h"
+
+static __videocard video_bios;
+
+/* Set a conventional BIOS mode */
+static int set_bios_mode(u8 mode);
+
+static int bios_set_mode(struct mode_info *mi)
+{
+	return set_bios_mode(mi->mode - VIDEO_FIRST_BIOS);
+}
+
+static int set_bios_mode(u8 mode)
+{
+	struct biosregs ireg, oreg;
+	u8 new_mode;
+
+	initregs(&ireg);
+	ireg.al = mode;		/* AH=0x00 Set Video Mode */
+	intcall(0x10, &ireg, NULL);
+
+	ireg.ah = 0x0f;		/* Get Current Video Mode */
+	intcall(0x10, &ireg, &oreg);
+
+	do_restore = 1;		/* Assume video contents were lost */
+
+	/* Not all BIOSes are clean with the top bit */
+	new_mode = oreg.al & 0x7f;
+
+	if (new_mode == mode)
+		return 0;	/* Mode change OK */
+
+#ifndef _WAKEUP
+	if (new_mode != boot_params.screen_info.orig_video_mode) {
+		/* Mode setting failed, but we didn't end up where we
+		   started.  That's bad.  Try to revert to the original
+		   video mode. */
+		ireg.ax = boot_params.screen_info.orig_video_mode;
+		intcall(0x10, &ireg, NULL);
+	}
+#endif
+	return -1;
+}
+
+static int bios_probe(void)
+{
+	u8 mode;
+#ifdef _WAKEUP
+	u8 saved_mode = 0x03;
+#else
+	u8 saved_mode = boot_params.screen_info.orig_video_mode;
+#endif
+	u16 crtc;
+	struct mode_info *mi;
+	int nmodes = 0;
+
+	if (adapter != ADAPTER_EGA && adapter != ADAPTER_VGA)
+		return 0;
+
+	set_fs(0);
+	crtc = vga_crtc();
+
+	video_bios.modes = GET_HEAP(struct mode_info, 0);
+
+	for (mode = 0x14; mode <= 0x7f; mode++) {
+		if (!heap_free(sizeof(struct mode_info)))
+			break;
+
+		if (mode_defined(VIDEO_FIRST_BIOS+mode))
+			continue;
+
+		if (set_bios_mode(mode))
+			continue;
+
+		/* Try to verify that it's a text mode. */
+
+		/* Attribute Controller: make graphics controller disabled */
+		if (in_idx(0x3c0, 0x10) & 0x01)
+			continue;
+
+		/* Graphics Controller: verify Alpha addressing enabled */
+		if (in_idx(0x3ce, 0x06) & 0x01)
+			continue;
+
+		/* CRTC cursor location low should be zero(?) */
+		if (in_idx(crtc, 0x0f))
+			continue;
+
+		mi = GET_HEAP(struct mode_info, 1);
+		mi->mode = VIDEO_FIRST_BIOS+mode;
+		mi->depth = 0;	/* text */
+		mi->x = rdfs16(0x44a);
+		mi->y = rdfs8(0x484)+1;
+		nmodes++;
+	}
+
+	set_bios_mode(saved_mode);
+
+	return nmodes;
+}
+
+static __videocard video_bios =
+{
+	.card_name	= "BIOS",
+	.probe		= bios_probe,
+	.set_mode	= bios_set_mode,
+	.unsafe		= 1,
+	.xmode_first	= VIDEO_FIRST_BIOS,
+	.xmode_n	= 0x80,
+};

arch/x86/boot/video-mode.c

@@ -0,0 +1,173 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007-2008 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * arch/i386/boot/video-mode.c
+ *
+ * Set the video mode.  This is separated out into a different
+ * file in order to be shared with the ACPI wakeup code.
+ */
+
+#include "boot.h"
+#include "video.h"
+#include "vesa.h"
+
+/*
+ * Common variables
+ */
+int adapter;			/* 0=CGA/MDA/HGC, 1=EGA, 2=VGA+ */
+u16 video_segment;
+int force_x, force_y;	/* Don't query the BIOS for cols/rows */
+
+int do_restore;		/* Screen contents changed during mode flip */
+int graphic_mode;	/* Graphic mode with linear frame buffer */
+
+/* Probe the video drivers and have them generate their mode lists. */
+void probe_cards(int unsafe)
+{
+	struct card_info *card;
+	static u8 probed[2];
+
+	if (probed[unsafe])
+		return;
+
+	probed[unsafe] = 1;
+
+	for (card = video_cards; card < video_cards_end; card++) {
+		if (card->unsafe == unsafe) {
+			if (card->probe)
+				card->nmodes = card->probe();
+			else
+				card->nmodes = 0;
+		}
+	}
+}
+
+/* Test if a mode is defined */
+int mode_defined(u16 mode)
+{
+	struct card_info *card;
+	struct mode_info *mi;
+	int i;
+
+	for (card = video_cards; card < video_cards_end; card++) {
+		mi = card->modes;
+		for (i = 0; i < card->nmodes; i++, mi++) {
+			if (mi->mode == mode)
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+/* Set mode (without recalc) */
+static int raw_set_mode(u16 mode, u16 *real_mode)
+{
+	int nmode, i;
+	struct card_info *card;
+	struct mode_info *mi;
+
+	/* Drop the recalc bit if set */
+	mode &= ~VIDEO_RECALC;
+
+	/* Scan for mode based on fixed ID, position, or resolution */
+	nmode = 0;
+	for (card = video_cards; card < video_cards_end; card++) {
+		mi = card->modes;
+		for (i = 0; i < card->nmodes; i++, mi++) {
+			int visible = mi->x || mi->y;
+
+			if ((mode == nmode && visible) ||
+			    mode == mi->mode ||
+			    mode == (mi->y << 8)+mi->x) {
+				*real_mode = mi->mode;
+				return card->set_mode(mi);
+			}
+
+			if (visible)
+				nmode++;
+		}
+	}
+
+	/* Nothing found?  Is it an "exceptional" (unprobed) mode? */
+	for (card = video_cards; card < video_cards_end; card++) {
+		if (mode >= card->xmode_first &&
+		    mode < card->xmode_first+card->xmode_n) {
+			struct mode_info mix;
+			*real_mode = mix.mode = mode;
+			mix.x = mix.y = 0;
+			return card->set_mode(&mix);
+		}
+	}
+
+	/* Otherwise, failure... */
+	return -1;
+}
+
+/*
+ * Recalculate the vertical video cutoff (hack!)
+ */
+static void vga_recalc_vertical(void)
+{
+	unsigned int font_size, rows;
+	u16 crtc;
+	u8 pt, ov;
+
+	set_fs(0);
+	font_size = rdfs8(0x485); /* BIOS: font size (pixels) */
+	rows = force_y ? force_y : rdfs8(0x484)+1; /* Text rows */
+
+	rows *= font_size;	/* Visible scan lines */
+	rows--;			/* ... minus one */
+
+	crtc = vga_crtc();
+
+	pt = in_idx(crtc, 0x11);
+	pt &= ~0x80;		/* Unlock CR0-7 */
+	out_idx(pt, crtc, 0x11);
+
+	out_idx((u8)rows, crtc, 0x12); /* Lower height register */
+
+	ov = in_idx(crtc, 0x07); /* Overflow register */
+	ov &= 0xbd;
+	ov |= (rows >> (8-1)) & 0x02;
+	ov |= (rows >> (9-6)) & 0x40;
+	out_idx(ov, crtc, 0x07);
+}
+
+/* Set mode (with recalc if specified) */
+int set_mode(u16 mode)
+{
+	int rv;
+	u16 real_mode;
+
+	/* Very special mode numbers... */
+	if (mode == VIDEO_CURRENT_MODE)
+		return 0;	/* Nothing to do... */
+	else if (mode == NORMAL_VGA)
+		mode = VIDEO_80x25;
+	else if (mode == EXTENDED_VGA)
+		mode = VIDEO_8POINT;
+
+	rv = raw_set_mode(mode, &real_mode);
+	if (rv)
+		return rv;
+
+	if (mode & VIDEO_RECALC)
+		vga_recalc_vertical();
+
+	/* Save the canonical mode number for the kernel, not
+	   an alias, size specification or menu position */
+#ifndef _WAKEUP
+	boot_params.hdr.vid_mode = real_mode;
+#endif
+	return 0;
+}

arch/x86/boot/video-vesa.c

@@ -0,0 +1,281 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * VESA text modes
+ */
+
+#include "boot.h"
+#include "video.h"
+#include "vesa.h"
+#include "string.h"
+
+/* VESA information */
+static struct vesa_general_info vginfo;
+static struct vesa_mode_info vminfo;
+
+static __videocard video_vesa;
+
+#ifndef _WAKEUP
+static void vesa_store_mode_params_graphics(void);
+#else /* _WAKEUP */
+static inline void vesa_store_mode_params_graphics(void) {}
+#endif /* _WAKEUP */
+
+static int vesa_probe(void)
+{
+	struct biosregs ireg, oreg;
+	u16 mode;
+	addr_t mode_ptr;
+	struct mode_info *mi;
+	int nmodes = 0;
+
+	video_vesa.modes = GET_HEAP(struct mode_info, 0);
+
+	initregs(&ireg);
+	ireg.ax = 0x4f00;
+	ireg.di = (size_t)&vginfo;
+	intcall(0x10, &ireg, &oreg);
+
+	if (oreg.ax != 0x004f ||
+	    vginfo.signature != VESA_MAGIC ||
+	    vginfo.version < 0x0102)
+		return 0;	/* Not present */
+
+	set_fs(vginfo.video_mode_ptr.seg);
+	mode_ptr = vginfo.video_mode_ptr.off;
+
+	while ((mode = rdfs16(mode_ptr)) != 0xffff) {
+		mode_ptr += 2;
+
+		if (!heap_free(sizeof(struct mode_info)))
+			break;	/* Heap full, can't save mode info */
+
+		if (mode & ~0x1ff)
+			continue;
+
+		memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
+
+		ireg.ax = 0x4f01;
+		ireg.cx = mode;
+		ireg.di = (size_t)&vminfo;
+		intcall(0x10, &ireg, &oreg);
+
+		if (oreg.ax != 0x004f)
+			continue;
+
+		if ((vminfo.mode_attr & 0x15) == 0x05) {
+			/* Text Mode, TTY BIOS supported,
+			   supported by hardware */
+			mi = GET_HEAP(struct mode_info, 1);
+			mi->mode  = mode + VIDEO_FIRST_VESA;
+			mi->depth = 0; /* text */
+			mi->x     = vminfo.h_res;
+			mi->y     = vminfo.v_res;
+			nmodes++;
+		} else if ((vminfo.mode_attr & 0x99) == 0x99 &&
+			   (vminfo.memory_layout == 4 ||
+			    vminfo.memory_layout == 6) &&
+			   vminfo.memory_planes == 1) {
+#ifdef CONFIG_FB_BOOT_VESA_SUPPORT
+			/* Graphics mode, color, linear frame buffer
+			   supported.  Only register the mode if
+			   if framebuffer is configured, however,
+			   otherwise the user will be left without a screen. */
+			mi = GET_HEAP(struct mode_info, 1);
+			mi->mode = mode + VIDEO_FIRST_VESA;
+			mi->depth = vminfo.bpp;
+			mi->x = vminfo.h_res;
+			mi->y = vminfo.v_res;
+			nmodes++;
+#endif
+		}
+	}
+
+	return nmodes;
+}
+
+static int vesa_set_mode(struct mode_info *mode)
+{
+	struct biosregs ireg, oreg;
+	int is_graphic;
+	u16 vesa_mode = mode->mode - VIDEO_FIRST_VESA;
+
+	memset(&vminfo, 0, sizeof vminfo); /* Just in case... */
+
+	initregs(&ireg);
+	ireg.ax = 0x4f01;
+	ireg.cx = vesa_mode;
+	ireg.di = (size_t)&vminfo;
+	intcall(0x10, &ireg, &oreg);
+
+	if (oreg.ax != 0x004f)
+		return -1;
+
+	if ((vminfo.mode_attr & 0x15) == 0x05) {
+		/* It's a supported text mode */
+		is_graphic = 0;
+#ifdef CONFIG_FB_BOOT_VESA_SUPPORT
+	} else if ((vminfo.mode_attr & 0x99) == 0x99) {
+		/* It's a graphics mode with linear frame buffer */
+		is_graphic = 1;
+		vesa_mode |= 0x4000; /* Request linear frame buffer */
+#endif
+	} else {
+		return -1;	/* Invalid mode */
+	}
+
+
+	initregs(&ireg);
+	ireg.ax = 0x4f02;
+	ireg.bx = vesa_mode;
+	intcall(0x10, &ireg, &oreg);
+
+	if (oreg.ax != 0x004f)
+		return -1;
+
+	graphic_mode = is_graphic;
+	if (!is_graphic) {
+		/* Text mode */
+		force_x = mode->x;
+		force_y = mode->y;
+		do_restore = 1;
+	} else {
+		/* Graphics mode */
+		vesa_store_mode_params_graphics();
+	}
+
+	return 0;
+}
+
+
+#ifndef _WAKEUP
+
+/* Switch DAC to 8-bit mode */
+static void vesa_dac_set_8bits(void)
+{
+	struct biosregs ireg, oreg;
+	u8 dac_size = 6;
+
+	/* If possible, switch the DAC to 8-bit mode */
+	if (vginfo.capabilities & 1) {
+		initregs(&ireg);
+		ireg.ax = 0x4f08;
+		ireg.bh = 0x08;
+		intcall(0x10, &ireg, &oreg);
+		if (oreg.ax == 0x004f)
+			dac_size = oreg.bh;
+	}
+
+	/* Set the color sizes to the DAC size, and offsets to 0 */
+	boot_params.screen_info.red_size   = dac_size;
+	boot_params.screen_info.green_size = dac_size;
+	boot_params.screen_info.blue_size  = dac_size;
+	boot_params.screen_info.rsvd_size  = dac_size;
+
+	boot_params.screen_info.red_pos    = 0;
+	boot_params.screen_info.green_pos  = 0;
+	boot_params.screen_info.blue_pos   = 0;
+	boot_params.screen_info.rsvd_pos   = 0;
+}
+
+/* Save the VESA protected mode info */
+static void vesa_store_pm_info(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ax = 0x4f0a;
+	intcall(0x10, &ireg, &oreg);
+
+	if (oreg.ax != 0x004f)
+		return;
+
+	boot_params.screen_info.vesapm_seg = oreg.es;
+	boot_params.screen_info.vesapm_off = oreg.di;
+}
+
+/*
+ * Save video mode parameters for graphics mode
+ */
+static void vesa_store_mode_params_graphics(void)
+{
+	/* Tell the kernel we're in VESA graphics mode */
+	boot_params.screen_info.orig_video_isVGA = VIDEO_TYPE_VLFB;
+
+	/* Mode parameters */
+	boot_params.screen_info.vesa_attributes = vminfo.mode_attr;
+	boot_params.screen_info.lfb_linelength = vminfo.logical_scan;
+	boot_params.screen_info.lfb_width = vminfo.h_res;
+	boot_params.screen_info.lfb_height = vminfo.v_res;
+	boot_params.screen_info.lfb_depth = vminfo.bpp;
+	boot_params.screen_info.pages = vminfo.image_planes;
+	boot_params.screen_info.lfb_base = vminfo.lfb_ptr;
+	memcpy(&boot_params.screen_info.red_size,
+	       &vminfo.rmask, 8);
+
+	/* General parameters */
+	boot_params.screen_info.lfb_size = vginfo.total_memory;
+
+	if (vminfo.bpp <= 8)
+		vesa_dac_set_8bits();
+
+	vesa_store_pm_info();
+}
+
+/*
+ * Save EDID information for the kernel; this is invoked, separately,
+ * after mode-setting.
+ */
+void vesa_store_edid(void)
+{
+#ifdef CONFIG_FIRMWARE_EDID
+	struct biosregs ireg, oreg;
+
+	/* Apparently used as a nonsense token... */
+	memset(&boot_params.edid_info, 0x13, sizeof boot_params.edid_info);
+
+	if (vginfo.version < 0x0200)
+		return;		/* EDID requires VBE 2.0+ */
+
+	initregs(&ireg);
+	ireg.ax = 0x4f15;		/* VBE DDC */
+	/* ireg.bx = 0x0000; */		/* Report DDC capabilities */
+	/* ireg.cx = 0;	*/		/* Controller 0 */
+	ireg.es = 0;			/* ES:DI must be 0 by spec */
+	intcall(0x10, &ireg, &oreg);
+
+	if (oreg.ax != 0x004f)
+		return;		/* No EDID */
+
+	/* BH = time in seconds to transfer EDD information */
+	/* BL = DDC level supported */
+
+	ireg.ax = 0x4f15;		/* VBE DDC */
+	ireg.bx = 0x0001;		/* Read EDID */
+	/* ireg.cx = 0; */		/* Controller 0 */
+	/* ireg.dx = 0;	*/		/* EDID block number */
+	ireg.es = ds();
+	ireg.di =(size_t)&boot_params.edid_info; /* (ES:)Pointer to block */
+	intcall(0x10, &ireg, &oreg);
+#endif /* CONFIG_FIRMWARE_EDID */
+}
+
+#endif /* not _WAKEUP */
+
+static __videocard video_vesa =
+{
+	.card_name	= "VESA",
+	.probe		= vesa_probe,
+	.set_mode	= vesa_set_mode,
+	.xmode_first	= VIDEO_FIRST_VESA,
+	.xmode_n	= 0x200,
+};

arch/x86/boot/video-vga.c

@@ -0,0 +1,288 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Common all-VGA modes
+ */
+
+#include "boot.h"
+#include "video.h"
+
+static struct mode_info vga_modes[] = {
+	{ VIDEO_80x25,  80, 25, 0 },
+	{ VIDEO_8POINT, 80, 50, 0 },
+	{ VIDEO_80x43,  80, 43, 0 },
+	{ VIDEO_80x28,  80, 28, 0 },
+	{ VIDEO_80x30,  80, 30, 0 },
+	{ VIDEO_80x34,  80, 34, 0 },
+	{ VIDEO_80x60,  80, 60, 0 },
+};
+
+static struct mode_info ega_modes[] = {
+	{ VIDEO_80x25,  80, 25, 0 },
+	{ VIDEO_8POINT, 80, 43, 0 },
+};
+
+static struct mode_info cga_modes[] = {
+	{ VIDEO_80x25,  80, 25, 0 },
+};
+
+static __videocard video_vga;
+
+/* Set basic 80x25 mode */
+static u8 vga_set_basic_mode(void)
+{
+	struct biosregs ireg, oreg;
+	u8 mode;
+
+	initregs(&ireg);
+
+	/* Query current mode */
+	ireg.ax = 0x0f00;
+	intcall(0x10, &ireg, &oreg);
+	mode = oreg.al;
+
+	if (mode != 3 && mode != 7)
+		mode = 3;
+
+	/* Set the mode */
+	ireg.ax = mode;		/* AH=0: set mode */
+	intcall(0x10, &ireg, NULL);
+	do_restore = 1;
+	return mode;
+}
+
+static void vga_set_8font(void)
+{
+	/* Set 8x8 font - 80x43 on EGA, 80x50 on VGA */
+	struct biosregs ireg;
+
+	initregs(&ireg);
+
+	/* Set 8x8 font */
+	ireg.ax = 0x1112;
+	/* ireg.bl = 0; */
+	intcall(0x10, &ireg, NULL);
+
+	/* Use alternate print screen */
+	ireg.ax = 0x1200;
+	ireg.bl = 0x20;
+	intcall(0x10, &ireg, NULL);
+
+	/* Turn off cursor emulation */
+	ireg.ax = 0x1201;
+	ireg.bl = 0x34;
+	intcall(0x10, &ireg, NULL);
+
+	/* Cursor is scan lines 6-7 */
+	ireg.ax = 0x0100;
+	ireg.cx = 0x0607;
+	intcall(0x10, &ireg, NULL);
+}
+
+static void vga_set_14font(void)
+{
+	/* Set 9x14 font - 80x28 on VGA */
+	struct biosregs ireg;
+
+	initregs(&ireg);
+
+	/* Set 9x14 font */
+	ireg.ax = 0x1111;
+	/* ireg.bl = 0; */
+	intcall(0x10, &ireg, NULL);
+
+	/* Turn off cursor emulation */
+	ireg.ax = 0x1201;
+	ireg.bl = 0x34;
+	intcall(0x10, &ireg, NULL);
+
+	/* Cursor is scan lines 11-12 */
+	ireg.ax = 0x0100;
+	ireg.cx = 0x0b0c;
+	intcall(0x10, &ireg, NULL);
+}
+
+static void vga_set_80x43(void)
+{
+	/* Set 80x43 mode on VGA (not EGA) */
+	struct biosregs ireg;
+
+	initregs(&ireg);
+
+	/* Set 350 scans */
+	ireg.ax = 0x1201;
+	ireg.bl = 0x30;
+	intcall(0x10, &ireg, NULL);
+
+	/* Reset video mode */
+	ireg.ax = 0x0003;
+	intcall(0x10, &ireg, NULL);
+
+	vga_set_8font();
+}
+
+/* I/O address of the VGA CRTC */
+u16 vga_crtc(void)
+{
+	return (inb(0x3cc) & 1) ? 0x3d4 : 0x3b4;
+}
+
+static void vga_set_480_scanlines(void)
+{
+	u16 crtc;		/* CRTC base address */
+	u8  csel;		/* CRTC miscellaneous output register */
+
+	crtc = vga_crtc();
+
+	out_idx(0x0c, crtc, 0x11); /* Vertical sync end, unlock CR0-7 */
+	out_idx(0x0b, crtc, 0x06); /* Vertical total */
+	out_idx(0x3e, crtc, 0x07); /* Vertical overflow */
+	out_idx(0xea, crtc, 0x10); /* Vertical sync start */
+	out_idx(0xdf, crtc, 0x12); /* Vertical display end */
+	out_idx(0xe7, crtc, 0x15); /* Vertical blank start */
+	out_idx(0x04, crtc, 0x16); /* Vertical blank end */
+	csel = inb(0x3cc);
+	csel &= 0x0d;
+	csel |= 0xe2;
+	outb(csel, 0x3c2);
+}
+
+static void vga_set_vertical_end(int lines)
+{
+	u16 crtc;		/* CRTC base address */
+	u8  ovfw;		/* CRTC overflow register */
+	int end = lines-1;
+
+	crtc = vga_crtc();
+
+	ovfw = 0x3c | ((end >> (8-1)) & 0x02) | ((end >> (9-6)) & 0x40);
+
+	out_idx(ovfw, crtc, 0x07); /* Vertical overflow */
+	out_idx(end,  crtc, 0x12); /* Vertical display end */
+}
+
+static void vga_set_80x30(void)
+{
+	vga_set_480_scanlines();
+	vga_set_vertical_end(30*16);
+}
+
+static void vga_set_80x34(void)
+{
+	vga_set_480_scanlines();
+	vga_set_14font();
+	vga_set_vertical_end(34*14);
+}
+
+static void vga_set_80x60(void)
+{
+	vga_set_480_scanlines();
+	vga_set_8font();
+	vga_set_vertical_end(60*8);
+}
+
+static int vga_set_mode(struct mode_info *mode)
+{
+	/* Set the basic mode */
+	vga_set_basic_mode();
+
+	/* Override a possibly broken BIOS */
+	force_x = mode->x;
+	force_y = mode->y;
+
+	switch (mode->mode) {
+	case VIDEO_80x25:
+		break;
+	case VIDEO_8POINT:
+		vga_set_8font();
+		break;
+	case VIDEO_80x43:
+		vga_set_80x43();
+		break;
+	case VIDEO_80x28:
+		vga_set_14font();
+		break;
+	case VIDEO_80x30:
+		vga_set_80x30();
+		break;
+	case VIDEO_80x34:
+		vga_set_80x34();
+		break;
+	case VIDEO_80x60:
+		vga_set_80x60();
+		break;
+	}
+
+	return 0;
+}
+
+/*
+ * Note: this probe includes basic information required by all
+ * systems.  It should be executed first, by making sure
+ * video-vga.c is listed first in the Makefile.
+ */
+static int vga_probe(void)
+{
+	static const char *card_name[] = {
+		"CGA/MDA/HGC", "EGA", "VGA"
+	};
+	static struct mode_info *mode_lists[] = {
+		cga_modes,
+		ega_modes,
+		vga_modes,
+	};
+	static int mode_count[] = {
+		sizeof(cga_modes)/sizeof(struct mode_info),
+		sizeof(ega_modes)/sizeof(struct mode_info),
+		sizeof(vga_modes)/sizeof(struct mode_info),
+	};
+
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+
+	ireg.ax = 0x1200;
+	ireg.bl = 0x10;		/* Check EGA/VGA */
+	intcall(0x10, &ireg, &oreg);
+
+#ifndef _WAKEUP
+	boot_params.screen_info.orig_video_ega_bx = oreg.bx;
+#endif
+
+	/* If we have MDA/CGA/HGC then BL will be unchanged at 0x10 */
+	if (oreg.bl != 0x10) {
+		/* EGA/VGA */
+		ireg.ax = 0x1a00;
+		intcall(0x10, &ireg, &oreg);
+
+		if (oreg.al == 0x1a) {
+			adapter = ADAPTER_VGA;
+#ifndef _WAKEUP
+			boot_params.screen_info.orig_video_isVGA = 1;
+#endif
+		} else {
+			adapter = ADAPTER_EGA;
+		}
+	} else {
+		adapter = ADAPTER_CGA;
+	}
+
+	video_vga.modes = mode_lists[adapter];
+	video_vga.card_name = card_name[adapter];
+	return mode_count[adapter];
+}
+
+static __videocard video_vga = {
+	.card_name	= "VGA",
+	.probe		= vga_probe,
+	.set_mode	= vga_set_mode,
+};

arch/x86/boot/video.c

@@ -0,0 +1,341 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Select video mode
+ */
+
+#include "boot.h"
+#include "video.h"
+#include "vesa.h"
+
+static void store_cursor_position(void)
+{
+	struct biosregs ireg, oreg;
+
+	initregs(&ireg);
+	ireg.ah = 0x03;
+	intcall(0x10, &ireg, &oreg);
+
+	boot_params.screen_info.orig_x = oreg.dl;
+	boot_params.screen_info.orig_y = oreg.dh;
+
+	if (oreg.ch & 0x20)
+		boot_params.screen_info.flags |= VIDEO_FLAGS_NOCURSOR;
+
+	if ((oreg.ch & 0x1f) > (oreg.cl & 0x1f))
+		boot_params.screen_info.flags |= VIDEO_FLAGS_NOCURSOR;
+}
+
+static void store_video_mode(void)
+{
+	struct biosregs ireg, oreg;
+
+	/* N.B.: the saving of the video page here is a bit silly,
+	   since we pretty much assume page 0 everywhere. */
+	initregs(&ireg);
+	ireg.ah = 0x0f;
+	intcall(0x10, &ireg, &oreg);
+
+	/* Not all BIOSes are clean with respect to the top bit */
+	boot_params.screen_info.orig_video_mode = oreg.al & 0x7f;
+	boot_params.screen_info.orig_video_page = oreg.bh;
+}
+
+/*
+ * Store the video mode parameters for later usage by the kernel.
+ * This is done by asking the BIOS except for the rows/columns
+ * parameters in the default 80x25 mode -- these are set directly,
+ * because some very obscure BIOSes supply insane values.
+ */
+static void store_mode_params(void)
+{
+	u16 font_size;
+	int x, y;
+
+	/* For graphics mode, it is up to the mode-setting driver
+	   (currently only video-vesa.c) to store the parameters */
+	if (graphic_mode)
+		return;
+
+	store_cursor_position();
+	store_video_mode();
+
+	if (boot_params.screen_info.orig_video_mode == 0x07) {
+		/* MDA, HGC, or VGA in monochrome mode */
+		video_segment = 0xb000;
+	} else {
+		/* CGA, EGA, VGA and so forth */
+		video_segment = 0xb800;
+	}
+
+	set_fs(0);
+	font_size = rdfs16(0x485); /* Font size, BIOS area */
+	boot_params.screen_info.orig_video_points = font_size;
+
+	x = rdfs16(0x44a);
+	y = (adapter == ADAPTER_CGA) ? 25 : rdfs8(0x484)+1;
+
+	if (force_x)
+		x = force_x;
+	if (force_y)
+		y = force_y;
+
+	boot_params.screen_info.orig_video_cols  = x;
+	boot_params.screen_info.orig_video_lines = y;
+}
+
+static unsigned int get_entry(void)
+{
+	char entry_buf[4];
+	int i, len = 0;
+	int key;
+	unsigned int v;
+
+	do {
+		key = getchar();
+
+		if (key == '\b') {
+			if (len > 0) {
+				puts("\b \b");
+				len--;
+			}
+		} else if ((key >= '0' && key <= '9') ||
+			   (key >= 'A' && key <= 'Z') ||
+			   (key >= 'a' && key <= 'z')) {
+			if (len < sizeof entry_buf) {
+				entry_buf[len++] = key;
+				putchar(key);
+			}
+		}
+	} while (key != '\r');
+	putchar('\n');
+
+	if (len == 0)
+		return VIDEO_CURRENT_MODE; /* Default */
+
+	v = 0;
+	for (i = 0; i < len; i++) {
+		v <<= 4;
+		key = entry_buf[i] | 0x20;
+		v += (key > '9') ? key-'a'+10 : key-'0';
+	}
+
+	return v;
+}
+
+static void display_menu(void)
+{
+	struct card_info *card;
+	struct mode_info *mi;
+	char ch;
+	int i;
+	int nmodes;
+	int modes_per_line;
+	int col;
+
+	nmodes = 0;
+	for (card = video_cards; card < video_cards_end; card++)
+		nmodes += card->nmodes;
+
+	modes_per_line = 1;
+	if (nmodes >= 20)
+		modes_per_line = 3;
+
+	for (col = 0; col < modes_per_line; col++)
+		puts("Mode: Resolution:  Type: ");
+	putchar('\n');
+
+	col = 0;
+	ch = '0';
+	for (card = video_cards; card < video_cards_end; card++) {
+		mi = card->modes;
+		for (i = 0; i < card->nmodes; i++, mi++) {
+			char resbuf[32];
+			int visible = mi->x && mi->y;
+			u16 mode_id = mi->mode ? mi->mode :
+				(mi->y << 8)+mi->x;
+
+			if (!visible)
+				continue; /* Hidden mode */
+
+			if (mi->depth)
+				sprintf(resbuf, "%dx%d", mi->y, mi->depth);
+			else
+				sprintf(resbuf, "%d", mi->y);
+
+			printf("%c %03X %4dx%-7s %-6s",
+			       ch, mode_id, mi->x, resbuf, card->card_name);
+			col++;
+			if (col >= modes_per_line) {
+				putchar('\n');
+				col = 0;
+			}
+
+			if (ch == '9')
+				ch = 'a';
+			else if (ch == 'z' || ch == ' ')
+				ch = ' '; /* Out of keys... */
+			else
+				ch++;
+		}
+	}
+	if (col)
+		putchar('\n');
+}
+
+#define H(x)	((x)-'a'+10)
+#define SCAN	((H('s')<<12)+(H('c')<<8)+(H('a')<<4)+H('n'))
+
+static unsigned int mode_menu(void)
+{
+	int key;
+	unsigned int sel;
+
+	puts("Press <ENTER> to see video modes available, "
+	     "<SPACE> to continue, or wait 30 sec\n");
+
+	kbd_flush();
+	while (1) {
+		key = getchar_timeout();
+		if (key == ' ' || key == 0)
+			return VIDEO_CURRENT_MODE; /* Default */
+		if (key == '\r')
+			break;
+		putchar('\a');	/* Beep! */
+	}
+
+
+	for (;;) {
+		display_menu();
+
+		puts("Enter a video mode or \"scan\" to scan for "
+		     "additional modes: ");
+		sel = get_entry();
+		if (sel != SCAN)
+			return sel;
+
+		probe_cards(1);
+	}
+}
+
+/* Save screen content to the heap */
+static struct saved_screen {
+	int x, y;
+	int curx, cury;
+	u16 *data;
+} saved;
+
+static void save_screen(void)
+{
+	/* Should be called after store_mode_params() */
+	saved.x = boot_params.screen_info.orig_video_cols;
+	saved.y = boot_params.screen_info.orig_video_lines;
+	saved.curx = boot_params.screen_info.orig_x;
+	saved.cury = boot_params.screen_info.orig_y;
+
+	if (!heap_free(saved.x*saved.y*sizeof(u16)+512))
+		return;		/* Not enough heap to save the screen */
+
+	saved.data = GET_HEAP(u16, saved.x*saved.y);
+
+	set_fs(video_segment);
+	copy_from_fs(saved.data, 0, saved.x*saved.y*sizeof(u16));
+}
+
+static void restore_screen(void)
+{
+	/* Should be called after store_mode_params() */
+	int xs = boot_params.screen_info.orig_video_cols;
+	int ys = boot_params.screen_info.orig_video_lines;
+	int y;
+	addr_t dst = 0;
+	u16 *src = saved.data;
+	struct biosregs ireg;
+
+	if (graphic_mode)
+		return;		/* Can't restore onto a graphic mode */
+
+	if (!src)
+		return;		/* No saved screen contents */
+
+	/* Restore screen contents */
+
+	set_fs(video_segment);
+	for (y = 0; y < ys; y++) {
+		int npad;
+
+		if (y < saved.y) {
+			int copy = (xs < saved.x) ? xs : saved.x;
+			copy_to_fs(dst, src, copy*sizeof(u16));
+			dst += copy*sizeof(u16);
+			src += saved.x;
+			npad = (xs < saved.x) ? 0 : xs-saved.x;
+		} else {
+			npad = xs;
+		}
+
+		/* Writes "npad" blank characters to
+		   video_segment:dst and advances dst */
+		asm volatile("pushw %%es ; "
+			     "movw %2,%%es ; "
+			     "shrw %%cx ; "
+			     "jnc 1f ; "
+			     "stosw \n\t"
+			     "1: rep;stosl ; "
+			     "popw %%es"
+			     : "+D" (dst), "+c" (npad)
+			     : "bdS" (video_segment),
+			       "a" (0x07200720));
+	}
+
+	/* Restore cursor position */
+	if (saved.curx >= xs)
+		saved.curx = xs-1;
+	if (saved.cury >= ys)
+		saved.cury = ys-1;
+
+	initregs(&ireg);
+	ireg.ah = 0x02;		/* Set cursor position */
+	ireg.dh = saved.cury;
+	ireg.dl = saved.curx;
+	intcall(0x10, &ireg, NULL);
+
+	store_cursor_position();
+}
+
+void set_video(void)
+{
+	u16 mode = boot_params.hdr.vid_mode;
+
+	RESET_HEAP();
+
+	store_mode_params();
+	save_screen();
+	probe_cards(0);
+
+	for (;;) {
+		if (mode == ASK_VGA)
+			mode = mode_menu();
+
+		if (!set_mode(mode))
+			break;
+
+		printf("Undefined video mode number: %x\n", mode);
+		mode = ASK_VGA;
+	}
+	boot_params.hdr.vid_mode = mode;
+	vesa_store_edid();
+	store_mode_params();
+
+	if (do_restore)
+		restore_screen();
+}

arch/x86/boot/video.h

@@ -0,0 +1,121 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright (C) 1991, 1992 Linus Torvalds
+ *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * Header file for the real-mode video probing code
+ */
+
+#ifndef BOOT_VIDEO_H
+#define BOOT_VIDEO_H
+
+#include <linux/types.h>
+
+/*
+ * This code uses an extended set of video mode numbers. These include:
+ * Aliases for standard modes
+ *      NORMAL_VGA (-1)
+ *      EXTENDED_VGA (-2)
+ *      ASK_VGA (-3)
+ * Video modes numbered by menu position -- NOT RECOMMENDED because of lack
+ * of compatibility when extending the table. These are between 0x00 and 0xff.
+ */
+#define VIDEO_FIRST_MENU 0x0000
+
+/* Standard BIOS video modes (BIOS number + 0x0100) */
+#define VIDEO_FIRST_BIOS 0x0100
+
+/* VESA BIOS video modes (VESA number + 0x0200) */
+#define VIDEO_FIRST_VESA 0x0200
+
+/* Video7 special modes (BIOS number + 0x0900) */
+#define VIDEO_FIRST_V7 0x0900
+
+/* Special video modes */
+#define VIDEO_FIRST_SPECIAL 0x0f00
+#define VIDEO_80x25 0x0f00
+#define VIDEO_8POINT 0x0f01
+#define VIDEO_80x43 0x0f02
+#define VIDEO_80x28 0x0f03
+#define VIDEO_CURRENT_MODE 0x0f04
+#define VIDEO_80x30 0x0f05
+#define VIDEO_80x34 0x0f06
+#define VIDEO_80x60 0x0f07
+#define VIDEO_GFX_HACK 0x0f08
+#define VIDEO_LAST_SPECIAL 0x0f09
+
+/* Video modes given by resolution */
+#define VIDEO_FIRST_RESOLUTION 0x1000
+
+/* The "recalculate timings" flag */
+#define VIDEO_RECALC 0x8000
+
+void store_screen(void);
+#define DO_STORE() store_screen()
+
+/*
+ * Mode table structures
+ */
+
+struct mode_info {
+	u16 mode;		/* Mode number (vga= style) */
+	u16 x, y;		/* Width, height */
+	u16 depth;		/* Bits per pixel, 0 for text mode */
+};
+
+struct card_info {
+	const char *card_name;
+	int (*set_mode)(struct mode_info *mode);
+	int (*probe)(void);
+	struct mode_info *modes;
+	int nmodes;		/* Number of probed modes so far */
+	int unsafe;		/* Probing is unsafe, only do after "scan" */
+	u16 xmode_first;	/* Unprobed modes to try to call anyway */
+	u16 xmode_n;		/* Size of unprobed mode range */
+};
+
+#define __videocard struct card_info __attribute__((used,section(".videocards")))
+extern struct card_info video_cards[], video_cards_end[];
+
+int mode_defined(u16 mode);	/* video.c */
+
+/* Basic video information */
+#define ADAPTER_CGA	0	/* CGA/MDA/HGC */
+#define ADAPTER_EGA	1
+#define ADAPTER_VGA	2
+
+extern int adapter;
+extern u16 video_segment;
+extern int force_x, force_y;	/* Don't query the BIOS for cols/rows */
+extern int do_restore;		/* Restore screen contents */
+extern int graphic_mode;	/* Graphics mode with linear frame buffer */
+
+/* Accessing VGA indexed registers */
+static inline u8 in_idx(u16 port, u8 index)
+{
+	outb(index, port);
+	return inb(port+1);
+}
+
+static inline void out_idx(u8 v, u16 port, u8 index)
+{
+	outw(index+(v << 8), port);
+}
+
+/* Writes a value to an indexed port and then reads the port again */
+static inline u8 tst_idx(u8 v, u16 port, u8 index)
+{
+	out_idx(port, index, v);
+	return in_idx(port, index);
+}
+
+/* Get the I/O port of the VGA CRTC */
+u16 vga_crtc(void);		/* video-vga.c */
+
+#endif /* BOOT_VIDEO_H */

arch/x86/configs/i386_defconfig

@@ -0,0 +1,311 @@
+# CONFIG_64BIT is not set
+CONFIG_EXPERIMENTAL=y
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_LOG_BUF_SHIFT=18
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PROFILING=y
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
+CONFIG_SMP=y
+CONFIG_X86_GENERIC=y
+CONFIG_HPET_TIMER=y
+CONFIG_SCHED_SMT=y
+CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
+CONFIG_X86_MCE=y
+CONFIG_X86_REBOOTFIXUPS=y
+CONFIG_MICROCODE=y
+CONFIG_MICROCODE_AMD=y
+CONFIG_X86_MSR=y
+CONFIG_X86_CPUID=y
+CONFIG_HIGHPTE=y
+CONFIG_X86_CHECK_BIOS_CORRUPTION=y
+# CONFIG_MTRR_SANITIZER is not set
+CONFIG_EFI=y
+CONFIG_HZ_1000=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
+# CONFIG_COMPAT_VDSO is not set
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_TRACE_RTC=y
+CONFIG_ACPI_DOCK=y
+CONFIG_CPU_FREQ=y
+# CONFIG_CPU_FREQ_STAT is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_X86_ACPI_CPUFREQ=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_MSI=y
+CONFIG_PCCARD=y
+CONFIG_YENTA=y
+CONFIG_HOTPLUG_PCI=y
+CONFIG_BINFMT_MISC=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+CONFIG_TCP_MD5SIG=y
+CONFIG_IPV6=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_NETLABEL=y
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_ADVANCED is not set
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_SIP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_ULOG=y
+CONFIG_NF_NAT=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_HAMRADIO=y
+CONFIG_CFG80211=y
+CONFIG_MAC80211=y
+CONFIG_MAC80211_LEDS=y
+CONFIG_RFKILL=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DEBUG_DEVRES=y
+CONFIG_CONNECTOR=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_SPI_ATTRS=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_ATA_PIIX=y
+CONFIG_PATA_AMD=y
+CONFIG_PATA_OLDPIIX=y
+CONFIG_PATA_SCH=y
+CONFIG_PATA_MPIIX=y
+CONFIG_ATA_GENERIC=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
+CONFIG_MACINTOSH_DRIVERS=y
+CONFIG_MAC_EMUMOUSEBTN=y
+CONFIG_NETDEVICES=y
+CONFIG_NETCONSOLE=y
+CONFIG_BNX2=y
+CONFIG_TIGON3=y
+CONFIG_NET_TULIP=y
+CONFIG_E100=y
+CONFIG_E1000=y
+CONFIG_E1000E=y
+CONFIG_SKY2=y
+CONFIG_NE2K_PCI=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
+# CONFIG_8139TOO_PIO is not set
+CONFIG_R8169=y
+CONFIG_FDDI=y
+CONFIG_INPUT_POLLDEV=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_INPUT_MISC=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_NONSTANDARD=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_HW_RANDOM=y
+CONFIG_NVRAM=y
+CONFIG_HPET=y
+# CONFIG_HPET_MMAP is not set
+CONFIG_I2C_I801=y
+CONFIG_WATCHDOG=y
+CONFIG_AGP=y
+CONFIG_AGP_AMD64=y
+CONFIG_AGP_INTEL=y
+CONFIG_DRM=y
+CONFIG_DRM_I915=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_FB_EFI=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_VGACON_SOFT_SCROLLBACK=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQ_DUMMY=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_HRTIMER=y
+CONFIG_SND_HDA_INTEL=y
+CONFIG_SND_HDA_HWDEP=y
+CONFIG_HIDRAW=y
+CONFIG_HID_GYRATION=y
+CONFIG_LOGITECH_FF=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_PID=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_UHCI_HCD=y
+CONFIG_USB_PRINTER=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_LIBUSUAL=y
+CONFIG_EDAC=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_HCTOSYS is not set
+CONFIG_DMADEVICES=y
+CONFIG_EEEPC_LAPTOP=y
+CONFIG_EFI_VARS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_QFMT_V2=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+CONFIG_FRAME_WARN=2048
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
+CONFIG_EARLY_PRINTK_DBGP=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_DEBUG_RODATA_TEST is not set
+CONFIG_DEBUG_BOOT_PARAMS=y
+CONFIG_OPTIMIZE_INLINING=y
+CONFIG_KEYS_DEBUG_PROC_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_CRYPTO_AES_586=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set

arch/x86/configs/kvm_guest.config

@@ -0,0 +1,28 @@
+CONFIG_NET=y
+CONFIG_NET_CORE=y
+CONFIG_NETDEVICES=y
+CONFIG_BLOCK=y
+CONFIG_BLK_DEV=y
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_INET=y
+CONFIG_TTY=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_BINFMT_ELF=y
+CONFIG_PCI=y
+CONFIG_PCI_MSI=y
+CONFIG_DEBUG_KERNEL=y
+CONFIG_VIRTUALIZATION=y
+CONFIG_HYPERVISOR_GUEST=y
+CONFIG_PARAVIRT=y
+CONFIG_KVM_GUEST=y
+CONFIG_VIRTIO=y
+CONFIG_VIRTIO_PCI=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_VIRTIO_NET=y
+CONFIG_9P_FS=y
+CONFIG_NET_9P=y
+CONFIG_NET_9P_VIRTIO=y

arch/x86/configs/tiny.config

@@ -0,0 +1 @@
+CONFIG_NOHIGHMEM=y

arch/x86/configs/x86_64_defconfig

@@ -0,0 +1,308 @@
+CONFIG_EXPERIMENTAL=y
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_TASKSTATS=y
+CONFIG_TASK_DELAY_ACCT=y
+CONFIG_TASK_XACCT=y
+CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_LOG_BUF_SHIFT=18
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_RESOURCE_COUNTERS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_BLK_DEV_INITRD=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_PROFILING=y
+CONFIG_KPROBES=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_OSF_PARTITION=y
+CONFIG_AMIGA_PARTITION=y
+CONFIG_MAC_PARTITION=y
+CONFIG_BSD_DISKLABEL=y
+CONFIG_MINIX_SUBPARTITION=y
+CONFIG_SOLARIS_X86_PARTITION=y
+CONFIG_UNIXWARE_DISKLABEL=y
+CONFIG_SGI_PARTITION=y
+CONFIG_SUN_PARTITION=y
+CONFIG_KARMA_PARTITION=y
+CONFIG_EFI_PARTITION=y
+CONFIG_SMP=y
+CONFIG_CALGARY_IOMMU=y
+CONFIG_NR_CPUS=64
+CONFIG_SCHED_SMT=y
+CONFIG_PREEMPT_VOLUNTARY=y
+CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
+CONFIG_X86_MCE=y
+CONFIG_MICROCODE=y
+CONFIG_MICROCODE_AMD=y
+CONFIG_X86_MSR=y
+CONFIG_X86_CPUID=y
+CONFIG_NUMA=y
+CONFIG_X86_CHECK_BIOS_CORRUPTION=y
+# CONFIG_MTRR_SANITIZER is not set
+CONFIG_EFI=y
+CONFIG_HZ_1000=y
+CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
+# CONFIG_COMPAT_VDSO is not set
+CONFIG_HIBERNATION=y
+CONFIG_PM_DEBUG=y
+CONFIG_PM_TRACE_RTC=y
+CONFIG_ACPI_DOCK=y
+CONFIG_CPU_FREQ=y
+# CONFIG_CPU_FREQ_STAT is not set
+CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_X86_ACPI_CPUFREQ=y
+CONFIG_PCI_MMCONFIG=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCCARD=y
+CONFIG_YENTA=y
+CONFIG_HOTPLUG_PCI=y
+CONFIG_BINFMT_MISC=y
+CONFIG_IA32_EMULATION=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+CONFIG_TCP_CONG_ADVANCED=y
+# CONFIG_TCP_CONG_BIC is not set
+# CONFIG_TCP_CONG_WESTWOOD is not set
+# CONFIG_TCP_CONG_HTCP is not set
+CONFIG_TCP_MD5SIG=y
+CONFIG_IPV6=y
+CONFIG_INET6_AH=y
+CONFIG_INET6_ESP=y
+CONFIG_NETLABEL=y
+CONFIG_NETFILTER=y
+# CONFIG_NETFILTER_ADVANCED is not set
+CONFIG_NF_CONNTRACK=y
+CONFIG_NF_CONNTRACK_FTP=y
+CONFIG_NF_CONNTRACK_IRC=y
+CONFIG_NF_CONNTRACK_SIP=y
+CONFIG_NF_CT_NETLINK=y
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=y
+CONFIG_NETFILTER_XT_TARGET_NFLOG=y
+CONFIG_NETFILTER_XT_TARGET_SECMARK=y
+CONFIG_NETFILTER_XT_TARGET_TCPMSS=y
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=y
+CONFIG_NETFILTER_XT_MATCH_POLICY=y
+CONFIG_NETFILTER_XT_MATCH_STATE=y
+CONFIG_NF_CONNTRACK_IPV4=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP_NF_FILTER=y
+CONFIG_IP_NF_TARGET_REJECT=y
+CONFIG_IP_NF_TARGET_ULOG=y
+CONFIG_NF_NAT=y
+CONFIG_IP_NF_TARGET_MASQUERADE=y
+CONFIG_IP_NF_MANGLE=y
+CONFIG_NF_CONNTRACK_IPV6=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_MATCH_IPV6HEADER=y
+CONFIG_IP6_NF_FILTER=y
+CONFIG_IP6_NF_TARGET_REJECT=y
+CONFIG_IP6_NF_MANGLE=y
+CONFIG_NET_SCHED=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_HAMRADIO=y
+CONFIG_CFG80211=y
+CONFIG_MAC80211=y
+CONFIG_MAC80211_LEDS=y
+CONFIG_RFKILL=y
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DEBUG_DEVRES=y
+CONFIG_CONNECTOR=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_BLK_DEV_SR_VENDOR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_CONSTANTS=y
+CONFIG_SCSI_SPI_ATTRS=y
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_ATA_PIIX=y
+CONFIG_PATA_AMD=y
+CONFIG_PATA_OLDPIIX=y
+CONFIG_PATA_SCH=y
+CONFIG_MD=y
+CONFIG_BLK_DEV_MD=y
+CONFIG_BLK_DEV_DM=y
+CONFIG_DM_MIRROR=y
+CONFIG_DM_ZERO=y
+CONFIG_MACINTOSH_DRIVERS=y
+CONFIG_MAC_EMUMOUSEBTN=y
+CONFIG_NETDEVICES=y
+CONFIG_NETCONSOLE=y
+CONFIG_TIGON3=y
+CONFIG_NET_TULIP=y
+CONFIG_E100=y
+CONFIG_E1000=y
+CONFIG_SKY2=y
+CONFIG_FORCEDETH=y
+CONFIG_8139TOO=y
+CONFIG_FDDI=y
+CONFIG_INPUT_POLLDEV=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_EVDEV=y
+CONFIG_INPUT_JOYSTICK=y
+CONFIG_INPUT_TABLET=y
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_INPUT_MISC=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_SERIAL_NONSTANDARD=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_SHARE_IRQ=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_INTEL is not set
+# CONFIG_HW_RANDOM_AMD is not set
+CONFIG_NVRAM=y
+CONFIG_HPET=y
+# CONFIG_HPET_MMAP is not set
+CONFIG_I2C_I801=y
+CONFIG_WATCHDOG=y
+CONFIG_AGP=y
+CONFIG_AGP_AMD64=y
+CONFIG_AGP_INTEL=y
+CONFIG_DRM=y
+CONFIG_DRM_I915=y
+CONFIG_DRM_I915_KMS=y
+CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB_TILEBLITTING=y
+CONFIG_FB_EFI=y
+# CONFIG_LCD_CLASS_DEVICE is not set
+CONFIG_VGACON_SOFT_SCROLLBACK=y
+CONFIG_LOGO=y
+# CONFIG_LOGO_LINUX_MONO is not set
+# CONFIG_LOGO_LINUX_VGA16 is not set
+CONFIG_SOUND=y
+CONFIG_SND=y
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQ_DUMMY=y
+CONFIG_SND_MIXER_OSS=y
+CONFIG_SND_PCM_OSS=y
+CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_HRTIMER=y
+CONFIG_SND_HDA_INTEL=y
+CONFIG_SND_HDA_HWDEP=y
+CONFIG_HIDRAW=y
+CONFIG_HID_GYRATION=y
+CONFIG_LOGITECH_FF=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_PANTHERLORD=y
+CONFIG_PANTHERLORD_FF=y
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_PID=y
+CONFIG_USB_HIDDEV=y
+CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_UHCI_HCD=y
+CONFIG_USB_PRINTER=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_LIBUSUAL=y
+CONFIG_EDAC=y
+CONFIG_RTC_CLASS=y
+# CONFIG_RTC_HCTOSYS is not set
+CONFIG_DMADEVICES=y
+CONFIG_EEEPC_LAPTOP=y
+CONFIG_AMD_IOMMU=y
+CONFIG_AMD_IOMMU_STATS=y
+CONFIG_INTEL_IOMMU=y
+# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
+CONFIG_EFI_VARS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
+CONFIG_QFMT_V2=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_ISO9660_FS=y
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_HUGETLBFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3_ACL=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_DEFAULT="utf8"
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ASCII=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_SCHED_DEBUG is not set
+CONFIG_SCHEDSTATS=y
+CONFIG_TIMER_STATS=y
+CONFIG_DEBUG_STACK_USAGE=y
+CONFIG_BLK_DEV_IO_TRACE=y
+CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
+CONFIG_EARLY_PRINTK_DBGP=y
+CONFIG_DEBUG_STACKOVERFLOW=y
+# CONFIG_DEBUG_RODATA_TEST is not set
+CONFIG_DEBUG_BOOT_PARAMS=y
+CONFIG_OPTIMIZE_INLINING=y
+CONFIG_KEYS_DEBUG_PROC_KEYS=y
+CONFIG_SECURITY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SECURITY_SELINUX=y
+CONFIG_SECURITY_SELINUX_BOOTPARAM=y
+CONFIG_SECURITY_SELINUX_DISABLE=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set

arch/x86/crypto/Makefile

@@ -0,0 +1,93 @@
+#
+# Arch-specific CryptoAPI modules.
+#
+
+avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no)
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+				$(comma)4)$(comma)%ymm2,yes,no)
+
+obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
+
+obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
+obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
+obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
+obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
+
+obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
+obj-$(CONFIG_CRYPTO_DES3_EDE_X86_64) += des3_ede-x86_64.o
+obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
+obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
+obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
+obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
+obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
+obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
+obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
+obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
+
+obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o
+obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
+obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
+obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
+obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
+
+# These modules require assembler to support AVX.
+ifeq ($(avx_supported),yes)
+	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \
+						camellia-aesni-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_CAST5_AVX_X86_64) += cast5-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_CAST6_AVX_X86_64) += cast6-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
+	obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
+endif
+
+# These modules require assembler to support AVX2.
+ifeq ($(avx2_supported),yes)
+	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
+	obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+	obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
+endif
+
+aes-i586-y := aes-i586-asm_32.o aes_glue.o
+twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
+salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
+serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
+
+aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
+des3_ede-x86_64-y := des3_ede-asm_64.o des3_ede_glue.o
+camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
+blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
+twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
+twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
+salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
+serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
+
+ifeq ($(avx_supported),yes)
+	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
+					camellia_aesni_avx_glue.o
+	cast5-avx-x86_64-y := cast5-avx-x86_64-asm_64.o cast5_avx_glue.o
+	cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
+	twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o \
+				twofish_avx_glue.o
+	serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o \
+				serpent_avx_glue.o
+endif
+
+ifeq ($(avx2_supported),yes)
+	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
+	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
+endif
+
+aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
+aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o
+ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
+sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
+ifeq ($(avx2_supported),yes)
+sha1-ssse3-y += sha1_avx2_x86_64_asm.o
+endif
+crc32c-intel-y := crc32c-intel_glue.o
+crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
+crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
+sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
+sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
+crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o

arch/x86/crypto/aes-i586-asm_32.S

@@ -0,0 +1,362 @@
+// -------------------------------------------------------------------------
+// Copyright (c) 2001, Dr Brian Gladman <                 >, Worcester, UK.
+// All rights reserved.
+//
+// LICENSE TERMS
+//
+// The free distribution and use of this software in both source and binary 
+// form is allowed (with or without changes) provided that:
+//
+//   1. distributions of this source code include the above copyright 
+//      notice, this list of conditions and the following disclaimer//
+//
+//   2. distributions in binary form include the above copyright
+//      notice, this list of conditions and the following disclaimer
+//      in the documentation and/or other associated materials//
+//
+//   3. the copyright holder's name is not used to endorse products 
+//      built using this software without specific written permission.
+//
+//
+// ALTERNATIVELY, provided that this notice is retained in full, this product
+// may be distributed under the terms of the GNU General Public License (GPL),
+// in which case the provisions of the GPL apply INSTEAD OF those given above.
+//
+// Copyright (c) 2004 Linus Torvalds <torvalds@osdl.org>
+// Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
+
+// DISCLAIMER
+//
+// This software is provided 'as is' with no explicit or implied warranties
+// in respect of its properties including, but not limited to, correctness 
+// and fitness for purpose.
+// -------------------------------------------------------------------------
+// Issue Date: 29/07/2002
+
+.file "aes-i586-asm.S"
+.text
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+
+#define tlen 1024   // length of each of 4 'xor' arrays (256 32-bit words)
+
+/* offsets to parameters with one register pushed onto stack */
+#define ctx 8
+#define out_blk 12
+#define in_blk 16
+
+/* offsets in crypto_aes_ctx structure */
+#define klen (480)
+#define ekey (0)
+#define dkey (240)
+
+// register mapping for encrypt and decrypt subroutines
+
+#define r0  eax
+#define r1  ebx
+#define r2  ecx
+#define r3  edx
+#define r4  esi
+#define r5  edi
+
+#define eaxl  al
+#define eaxh  ah
+#define ebxl  bl
+#define ebxh  bh
+#define ecxl  cl
+#define ecxh  ch
+#define edxl  dl
+#define edxh  dh
+
+#define _h(reg) reg##h
+#define h(reg) _h(reg)
+
+#define _l(reg) reg##l
+#define l(reg) _l(reg)
+
+// This macro takes a 32-bit word representing a column and uses
+// each of its four bytes to index into four tables of 256 32-bit
+// words to obtain values that are then xored into the appropriate
+// output registers r0, r1, r4 or r5.  
+
+// Parameters:
+// table table base address
+//   %1  out_state[0]
+//   %2  out_state[1]
+//   %3  out_state[2]
+//   %4  out_state[3]
+//   idx input register for the round (destroyed)
+//   tmp scratch register for the round
+// sched key schedule
+
+#define do_col(table, a1,a2,a3,a4, idx, tmp)	\
+	movzx   %l(idx),%tmp;			\
+	xor     table(,%tmp,4),%a1;		\
+	movzx   %h(idx),%tmp;			\
+	shr     $16,%idx;			\
+	xor     table+tlen(,%tmp,4),%a2;	\
+	movzx   %l(idx),%tmp;			\
+	movzx   %h(idx),%idx;			\
+	xor     table+2*tlen(,%tmp,4),%a3;	\
+	xor     table+3*tlen(,%idx,4),%a4;
+
+// initialise output registers from the key schedule
+// NB1: original value of a3 is in idx on exit
+// NB2: original values of a1,a2,a4 aren't used
+#define do_fcol(table, a1,a2,a3,a4, idx, tmp, sched) \
+	mov     0 sched,%a1;			\
+	movzx   %l(idx),%tmp;			\
+	mov     12 sched,%a2;			\
+	xor     table(,%tmp,4),%a1;		\
+	mov     4 sched,%a4;			\
+	movzx   %h(idx),%tmp;			\
+	shr     $16,%idx;			\
+	xor     table+tlen(,%tmp,4),%a2;	\
+	movzx   %l(idx),%tmp;			\
+	movzx   %h(idx),%idx;			\
+	xor     table+3*tlen(,%idx,4),%a4;	\
+	mov     %a3,%idx;			\
+	mov     8 sched,%a3;			\
+	xor     table+2*tlen(,%tmp,4),%a3;
+
+// initialise output registers from the key schedule
+// NB1: original value of a3 is in idx on exit
+// NB2: original values of a1,a2,a4 aren't used
+#define do_icol(table, a1,a2,a3,a4, idx, tmp, sched) \
+	mov     0 sched,%a1;			\
+	movzx   %l(idx),%tmp;			\
+	mov     4 sched,%a2;			\
+	xor     table(,%tmp,4),%a1;		\
+	mov     12 sched,%a4;			\
+	movzx   %h(idx),%tmp;			\
+	shr     $16,%idx;			\
+	xor     table+tlen(,%tmp,4),%a2;	\
+	movzx   %l(idx),%tmp;			\
+	movzx   %h(idx),%idx;			\
+	xor     table+3*tlen(,%idx,4),%a4;	\
+	mov     %a3,%idx;			\
+	mov     8 sched,%a3;			\
+	xor     table+2*tlen(,%tmp,4),%a3;
+
+
+// original Gladman had conditional saves to MMX regs.
+#define save(a1, a2)		\
+	mov     %a2,4*a1(%esp)
+
+#define restore(a1, a2)		\
+	mov     4*a2(%esp),%a1
+
+// These macros perform a forward encryption cycle. They are entered with
+// the first previous round column values in r0,r1,r4,r5 and
+// exit with the final values in the same registers, using stack
+// for temporary storage.
+
+// round column values
+// on entry: r0,r1,r4,r5
+// on exit:  r2,r1,r4,r5
+#define fwd_rnd1(arg, table)						\
+	save   (0,r1);							\
+	save   (1,r5);							\
+									\
+	/* compute new column values */					\
+	do_fcol(table, r2,r5,r4,r1, r0,r3, arg);	/* idx=r0 */	\
+	do_col (table, r4,r1,r2,r5, r0,r3);		/* idx=r4 */	\
+	restore(r0,0);							\
+	do_col (table, r1,r2,r5,r4, r0,r3);		/* idx=r1 */	\
+	restore(r0,1);							\
+	do_col (table, r5,r4,r1,r2, r0,r3);		/* idx=r5 */
+
+// round column values
+// on entry: r2,r1,r4,r5
+// on exit:  r0,r1,r4,r5
+#define fwd_rnd2(arg, table)						\
+	save   (0,r1);							\
+	save   (1,r5);							\
+									\
+	/* compute new column values */					\
+	do_fcol(table, r0,r5,r4,r1, r2,r3, arg);	/* idx=r2 */	\
+	do_col (table, r4,r1,r0,r5, r2,r3);		/* idx=r4 */	\
+	restore(r2,0);							\
+	do_col (table, r1,r0,r5,r4, r2,r3);		/* idx=r1 */	\
+	restore(r2,1);							\
+	do_col (table, r5,r4,r1,r0, r2,r3);		/* idx=r5 */
+
+// These macros performs an inverse encryption cycle. They are entered with
+// the first previous round column values in r0,r1,r4,r5 and
+// exit with the final values in the same registers, using stack
+// for temporary storage
+
+// round column values
+// on entry: r0,r1,r4,r5
+// on exit:  r2,r1,r4,r5
+#define inv_rnd1(arg, table)						\
+	save    (0,r1);							\
+	save    (1,r5);							\
+									\
+	/* compute new column values */					\
+	do_icol(table, r2,r1,r4,r5, r0,r3, arg);	/* idx=r0 */	\
+	do_col (table, r4,r5,r2,r1, r0,r3);		/* idx=r4 */	\
+	restore(r0,0);							\
+	do_col (table, r1,r4,r5,r2, r0,r3);		/* idx=r1 */	\
+	restore(r0,1);							\
+	do_col (table, r5,r2,r1,r4, r0,r3);		/* idx=r5 */
+
+// round column values
+// on entry: r2,r1,r4,r5
+// on exit:  r0,r1,r4,r5
+#define inv_rnd2(arg, table)						\
+	save    (0,r1);							\
+	save    (1,r5);							\
+									\
+	/* compute new column values */					\
+	do_icol(table, r0,r1,r4,r5, r2,r3, arg);	/* idx=r2 */	\
+	do_col (table, r4,r5,r0,r1, r2,r3);		/* idx=r4 */	\
+	restore(r2,0);							\
+	do_col (table, r1,r4,r5,r0, r2,r3);		/* idx=r1 */	\
+	restore(r2,1);							\
+	do_col (table, r5,r0,r1,r4, r2,r3);		/* idx=r5 */
+
+// AES (Rijndael) Encryption Subroutine
+/* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */
+
+.extern  crypto_ft_tab
+.extern  crypto_fl_tab
+
+ENTRY(aes_enc_blk)
+	push    %ebp
+	mov     ctx(%esp),%ebp
+
+// CAUTION: the order and the values used in these assigns 
+// rely on the register mappings
+
+1:	push    %ebx
+	mov     in_blk+4(%esp),%r2
+	push    %esi
+	mov     klen(%ebp),%r3   // key size
+	push    %edi
+#if ekey != 0
+	lea     ekey(%ebp),%ebp  // key pointer
+#endif
+
+// input four columns and xor in first round key
+
+	mov     (%r2),%r0
+	mov     4(%r2),%r1
+	mov     8(%r2),%r4
+	mov     12(%r2),%r5
+	xor     (%ebp),%r0
+	xor     4(%ebp),%r1
+	xor     8(%ebp),%r4
+	xor     12(%ebp),%r5
+
+	sub     $8,%esp		// space for register saves on stack
+	add     $16,%ebp	// increment to next round key
+	cmp     $24,%r3
+	jb      4f		// 10 rounds for 128-bit key
+	lea     32(%ebp),%ebp
+	je      3f		// 12 rounds for 192-bit key
+	lea     32(%ebp),%ebp
+
+2:	fwd_rnd1( -64(%ebp), crypto_ft_tab)	// 14 rounds for 256-bit key
+	fwd_rnd2( -48(%ebp), crypto_ft_tab)
+3:	fwd_rnd1( -32(%ebp), crypto_ft_tab)	// 12 rounds for 192-bit key
+	fwd_rnd2( -16(%ebp), crypto_ft_tab)
+4:	fwd_rnd1(    (%ebp), crypto_ft_tab)	// 10 rounds for 128-bit key
+	fwd_rnd2( +16(%ebp), crypto_ft_tab)
+	fwd_rnd1( +32(%ebp), crypto_ft_tab)
+	fwd_rnd2( +48(%ebp), crypto_ft_tab)
+	fwd_rnd1( +64(%ebp), crypto_ft_tab)
+	fwd_rnd2( +80(%ebp), crypto_ft_tab)
+	fwd_rnd1( +96(%ebp), crypto_ft_tab)
+	fwd_rnd2(+112(%ebp), crypto_ft_tab)
+	fwd_rnd1(+128(%ebp), crypto_ft_tab)
+	fwd_rnd2(+144(%ebp), crypto_fl_tab)	// last round uses a different table
+
+// move final values to the output array.  CAUTION: the 
+// order of these assigns rely on the register mappings
+
+	add     $8,%esp
+	mov     out_blk+12(%esp),%ebp
+	mov     %r5,12(%ebp)
+	pop     %edi
+	mov     %r4,8(%ebp)
+	pop     %esi
+	mov     %r1,4(%ebp)
+	pop     %ebx
+	mov     %r0,(%ebp)
+	pop     %ebp
+	ret
+ENDPROC(aes_enc_blk)
+
+// AES (Rijndael) Decryption Subroutine
+/* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */
+
+.extern  crypto_it_tab
+.extern  crypto_il_tab
+
+ENTRY(aes_dec_blk)
+	push    %ebp
+	mov     ctx(%esp),%ebp
+
+// CAUTION: the order and the values used in these assigns 
+// rely on the register mappings
+
+1:	push    %ebx
+	mov     in_blk+4(%esp),%r2
+	push    %esi
+	mov     klen(%ebp),%r3   // key size
+	push    %edi
+#if dkey != 0
+	lea     dkey(%ebp),%ebp  // key pointer
+#endif
+	
+// input four columns and xor in first round key
+
+	mov     (%r2),%r0
+	mov     4(%r2),%r1
+	mov     8(%r2),%r4
+	mov     12(%r2),%r5
+	xor     (%ebp),%r0
+	xor     4(%ebp),%r1
+	xor     8(%ebp),%r4
+	xor     12(%ebp),%r5
+
+	sub     $8,%esp		// space for register saves on stack
+	add     $16,%ebp	// increment to next round key
+	cmp     $24,%r3
+	jb      4f		// 10 rounds for 128-bit key
+	lea     32(%ebp),%ebp
+	je      3f		// 12 rounds for 192-bit key
+	lea     32(%ebp),%ebp
+
+2:	inv_rnd1( -64(%ebp), crypto_it_tab)	// 14 rounds for 256-bit key
+	inv_rnd2( -48(%ebp), crypto_it_tab)
+3:	inv_rnd1( -32(%ebp), crypto_it_tab)	// 12 rounds for 192-bit key
+	inv_rnd2( -16(%ebp), crypto_it_tab)
+4:	inv_rnd1(    (%ebp), crypto_it_tab)	// 10 rounds for 128-bit key
+	inv_rnd2( +16(%ebp), crypto_it_tab)
+	inv_rnd1( +32(%ebp), crypto_it_tab)
+	inv_rnd2( +48(%ebp), crypto_it_tab)
+	inv_rnd1( +64(%ebp), crypto_it_tab)
+	inv_rnd2( +80(%ebp), crypto_it_tab)
+	inv_rnd1( +96(%ebp), crypto_it_tab)
+	inv_rnd2(+112(%ebp), crypto_it_tab)
+	inv_rnd1(+128(%ebp), crypto_it_tab)
+	inv_rnd2(+144(%ebp), crypto_il_tab)	// last round uses a different table
+
+// move final values to the output array.  CAUTION: the 
+// order of these assigns rely on the register mappings
+
+	add     $8,%esp
+	mov     out_blk+12(%esp),%ebp
+	mov     %r5,12(%ebp)
+	pop     %edi
+	mov     %r4,8(%ebp)
+	pop     %esi
+	mov     %r1,4(%ebp)
+	pop     %ebx
+	mov     %r0,(%ebp)
+	pop     %ebp
+	ret
+ENDPROC(aes_dec_blk)

arch/x86/crypto/aes-x86_64-asm_64.S

@@ -0,0 +1,188 @@
+/* AES (Rijndael) implementation (FIPS PUB 197) for x86_64
+ *
+ * Copyright (C) 2005 Andreas Steinmetz, <ast@domdv.de>
+ *
+ * License:
+ * This code can be distributed under the terms of the GNU General Public
+ * License (GPL) Version 2 provided that the above header down to and
+ * including this sentence is retained in full.
+ */
+
+.extern crypto_ft_tab
+.extern crypto_it_tab
+.extern crypto_fl_tab
+.extern crypto_il_tab
+
+.text
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+
+#define R1	%rax
+#define R1E	%eax
+#define R1X	%ax
+#define R1H	%ah
+#define R1L	%al
+#define R2	%rbx
+#define R2E	%ebx
+#define R2X	%bx
+#define R2H	%bh
+#define R2L	%bl
+#define R3	%rcx
+#define R3E	%ecx
+#define R3X	%cx
+#define R3H	%ch
+#define R3L	%cl
+#define R4	%rdx
+#define R4E	%edx
+#define R4X	%dx
+#define R4H	%dh
+#define R4L	%dl
+#define R5	%rsi
+#define R5E	%esi
+#define R6	%rdi
+#define R6E	%edi
+#define R7	%rbp
+#define R7E	%ebp
+#define R8	%r8
+#define R9	%r9
+#define R10	%r10
+#define R11	%r11
+
+#define prologue(FUNC,KEY,B128,B192,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11) \
+	ENTRY(FUNC);			\
+	movq	r1,r2;			\
+	movq	r3,r4;			\
+	leaq	KEY+48(r8),r9;		\
+	movq	r10,r11;		\
+	movl	(r7),r5 ## E;		\
+	movl	4(r7),r1 ## E;		\
+	movl	8(r7),r6 ## E;		\
+	movl	12(r7),r7 ## E;		\
+	movl	480(r8),r10 ## E;	\
+	xorl	-48(r9),r5 ## E;	\
+	xorl	-44(r9),r1 ## E;	\
+	xorl	-40(r9),r6 ## E;	\
+	xorl	-36(r9),r7 ## E;	\
+	cmpl	$24,r10 ## E;		\
+	jb	B128;			\
+	leaq	32(r9),r9;		\
+	je	B192;			\
+	leaq	32(r9),r9;
+
+#define epilogue(FUNC,r1,r2,r3,r4,r5,r6,r7,r8,r9) \
+	movq	r1,r2;			\
+	movq	r3,r4;			\
+	movl	r5 ## E,(r9);		\
+	movl	r6 ## E,4(r9);		\
+	movl	r7 ## E,8(r9);		\
+	movl	r8 ## E,12(r9);		\
+	ret;				\
+	ENDPROC(FUNC);
+
+#define round(TAB,OFFSET,r1,r2,r3,r4,r5,r6,r7,r8,ra,rb,rc,rd) \
+	movzbl	r2 ## H,r5 ## E;	\
+	movzbl	r2 ## L,r6 ## E;	\
+	movl	TAB+1024(,r5,4),r5 ## E;\
+	movw	r4 ## X,r2 ## X;	\
+	movl	TAB(,r6,4),r6 ## E;	\
+	roll	$16,r2 ## E;		\
+	shrl	$16,r4 ## E;		\
+	movzbl	r4 ## H,r7 ## E;	\
+	movzbl	r4 ## L,r4 ## E;	\
+	xorl	OFFSET(r8),ra ## E;	\
+	xorl	OFFSET+4(r8),rb ## E;	\
+	xorl	TAB+3072(,r7,4),r5 ## E;\
+	xorl	TAB+2048(,r4,4),r6 ## E;\
+	movzbl	r1 ## L,r7 ## E;	\
+	movzbl	r1 ## H,r4 ## E;	\
+	movl	TAB+1024(,r4,4),r4 ## E;\
+	movw	r3 ## X,r1 ## X;	\
+	roll	$16,r1 ## E;		\
+	shrl	$16,r3 ## E;		\
+	xorl	TAB(,r7,4),r5 ## E;	\
+	movzbl	r3 ## H,r7 ## E;	\
+	movzbl	r3 ## L,r3 ## E;	\
+	xorl	TAB+3072(,r7,4),r4 ## E;\
+	xorl	TAB+2048(,r3,4),r5 ## E;\
+	movzbl	r1 ## H,r7 ## E;	\
+	movzbl	r1 ## L,r3 ## E;	\
+	shrl	$16,r1 ## E;		\
+	xorl	TAB+3072(,r7,4),r6 ## E;\
+	movl	TAB+2048(,r3,4),r3 ## E;\
+	movzbl	r1 ## H,r7 ## E;	\
+	movzbl	r1 ## L,r1 ## E;	\
+	xorl	TAB+1024(,r7,4),r6 ## E;\
+	xorl	TAB(,r1,4),r3 ## E;	\
+	movzbl	r2 ## H,r1 ## E;	\
+	movzbl	r2 ## L,r7 ## E;	\
+	shrl	$16,r2 ## E;		\
+	xorl	TAB+3072(,r1,4),r3 ## E;\
+	xorl	TAB+2048(,r7,4),r4 ## E;\
+	movzbl	r2 ## H,r1 ## E;	\
+	movzbl	r2 ## L,r2 ## E;	\
+	xorl	OFFSET+8(r8),rc ## E;	\
+	xorl	OFFSET+12(r8),rd ## E;	\
+	xorl	TAB+1024(,r1,4),r3 ## E;\
+	xorl	TAB(,r2,4),r4 ## E;
+
+#define move_regs(r1,r2,r3,r4) \
+	movl	r3 ## E,r1 ## E;	\
+	movl	r4 ## E,r2 ## E;
+
+#define entry(FUNC,KEY,B128,B192) \
+	prologue(FUNC,KEY,B128,B192,R2,R8,R7,R9,R1,R3,R4,R6,R10,R5,R11)
+
+#define return(FUNC) epilogue(FUNC,R8,R2,R9,R7,R5,R6,R3,R4,R11)
+
+#define encrypt_round(TAB,OFFSET) \
+	round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \
+	move_regs(R1,R2,R5,R6)
+
+#define encrypt_final(TAB,OFFSET) \
+	round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4)
+
+#define decrypt_round(TAB,OFFSET) \
+	round(TAB,OFFSET,R2,R1,R4,R3,R6,R5,R7,R10,R5,R6,R3,R4) \
+	move_regs(R1,R2,R5,R6)
+
+#define decrypt_final(TAB,OFFSET) \
+	round(TAB,OFFSET,R2,R1,R4,R3,R6,R5,R7,R10,R5,R6,R3,R4)
+
+/* void aes_enc_blk(stuct crypto_tfm *tfm, u8 *out, const u8 *in) */
+
+	entry(aes_enc_blk,0,.Le128,.Le192)
+	encrypt_round(crypto_ft_tab,-96)
+	encrypt_round(crypto_ft_tab,-80)
+.Le192:	encrypt_round(crypto_ft_tab,-64)
+	encrypt_round(crypto_ft_tab,-48)
+.Le128:	encrypt_round(crypto_ft_tab,-32)
+	encrypt_round(crypto_ft_tab,-16)
+	encrypt_round(crypto_ft_tab,  0)
+	encrypt_round(crypto_ft_tab, 16)
+	encrypt_round(crypto_ft_tab, 32)
+	encrypt_round(crypto_ft_tab, 48)
+	encrypt_round(crypto_ft_tab, 64)
+	encrypt_round(crypto_ft_tab, 80)
+	encrypt_round(crypto_ft_tab, 96)
+	encrypt_final(crypto_fl_tab,112)
+	return(aes_enc_blk)
+
+/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in) */
+
+	entry(aes_dec_blk,240,.Ld128,.Ld192)
+	decrypt_round(crypto_it_tab,-96)
+	decrypt_round(crypto_it_tab,-80)
+.Ld192:	decrypt_round(crypto_it_tab,-64)
+	decrypt_round(crypto_it_tab,-48)
+.Ld128:	decrypt_round(crypto_it_tab,-32)
+	decrypt_round(crypto_it_tab,-16)
+	decrypt_round(crypto_it_tab,  0)
+	decrypt_round(crypto_it_tab, 16)
+	decrypt_round(crypto_it_tab, 32)
+	decrypt_round(crypto_it_tab, 48)
+	decrypt_round(crypto_it_tab, 64)
+	decrypt_round(crypto_it_tab, 80)
+	decrypt_round(crypto_it_tab, 96)
+	decrypt_final(crypto_il_tab,112)
+	return(aes_dec_blk)

arch/x86/crypto/aes_ctrby8_avx-x86_64.S

@@ -0,0 +1,580 @@
+/*
+ *	Implement AES CTR mode by8 optimization with AVX instructions. (x86_64)
+ *
+ * This is AES128/192/256 CTR mode optimization implementation. It requires
+ * the support of Intel(R) AESNI and AVX instructions.
+ *
+ * This work was inspired by the AES CTR mode optimization published
+ * in Intel Optimized IPSEC Cryptograhpic library.
+ * Additional information on it can be found at:
+ *    http://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=22972
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Sean Gulley <sean.m.gulley@intel.com>
+ * Chandramouli Narayanan <mouli@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+#define CONCAT(a,b)	a##b
+#define VMOVDQ		vmovdqu
+
+#define xdata0		%xmm0
+#define xdata1		%xmm1
+#define xdata2		%xmm2
+#define xdata3		%xmm3
+#define xdata4		%xmm4
+#define xdata5		%xmm5
+#define xdata6		%xmm6
+#define xdata7		%xmm7
+#define xcounter	%xmm8
+#define xbyteswap	%xmm9
+#define xkey0		%xmm10
+#define xkey4		%xmm11
+#define xkey8		%xmm12
+#define xkey12		%xmm13
+#define xkeyA		%xmm14
+#define xkeyB		%xmm15
+
+#define p_in		%rdi
+#define p_iv		%rsi
+#define p_keys		%rdx
+#define p_out		%rcx
+#define num_bytes	%r8
+
+#define tmp		%r10
+#define	DDQ(i)		CONCAT(ddq_add_,i)
+#define	XMM(i)		CONCAT(%xmm, i)
+#define	DDQ_DATA	0
+#define	XDATA		1
+#define KEY_128		1
+#define KEY_192		2
+#define KEY_256		3
+
+.section .rodata
+.align 16
+
+byteswap_const:
+	.octa 0x000102030405060708090A0B0C0D0E0F
+ddq_low_msk:
+	.octa 0x0000000000000000FFFFFFFFFFFFFFFF
+ddq_high_add_1:
+	.octa 0x00000000000000010000000000000000
+ddq_add_1:
+	.octa 0x00000000000000000000000000000001
+ddq_add_2:
+	.octa 0x00000000000000000000000000000002
+ddq_add_3:
+	.octa 0x00000000000000000000000000000003
+ddq_add_4:
+	.octa 0x00000000000000000000000000000004
+ddq_add_5:
+	.octa 0x00000000000000000000000000000005
+ddq_add_6:
+	.octa 0x00000000000000000000000000000006
+ddq_add_7:
+	.octa 0x00000000000000000000000000000007
+ddq_add_8:
+	.octa 0x00000000000000000000000000000008
+
+.text
+
+/* generate a unique variable for ddq_add_x */
+
+.macro setddq n
+	var_ddq_add = DDQ(\n)
+.endm
+
+/* generate a unique variable for xmm register */
+.macro setxdata n
+	var_xdata = XMM(\n)
+.endm
+
+/* club the numeric 'id' to the symbol 'name' */
+
+.macro club name, id
+.altmacro
+	.if \name == DDQ_DATA
+		setddq %\id
+	.elseif \name == XDATA
+		setxdata %\id
+	.endif
+.noaltmacro
+.endm
+
+/*
+ * do_aes num_in_par load_keys key_len
+ * This increments p_in, but not p_out
+ */
+.macro do_aes b, k, key_len
+	.set by, \b
+	.set load_keys, \k
+	.set klen, \key_len
+
+	.if (load_keys)
+		vmovdqa	0*16(p_keys), xkey0
+	.endif
+
+	vpshufb	xbyteswap, xcounter, xdata0
+
+	.set i, 1
+	.rept (by - 1)
+		club DDQ_DATA, i
+		club XDATA, i
+		vpaddq	var_ddq_add(%rip), xcounter, var_xdata
+		vptest	ddq_low_msk(%rip), var_xdata
+		jnz 1f
+		vpaddq	ddq_high_add_1(%rip), var_xdata, var_xdata
+		vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
+		1:
+		vpshufb	xbyteswap, var_xdata, var_xdata
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	1*16(p_keys), xkeyA
+
+	vpxor	xkey0, xdata0, xdata0
+	club DDQ_DATA, by
+	vpaddq	var_ddq_add(%rip), xcounter, xcounter
+	vptest	ddq_low_msk(%rip), xcounter
+	jnz	1f
+	vpaddq	ddq_high_add_1(%rip), xcounter, xcounter
+	1:
+
+	.set i, 1
+	.rept (by - 1)
+		club XDATA, i
+		vpxor	xkey0, var_xdata, var_xdata
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	2*16(p_keys), xkeyB
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 1 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		.if (load_keys)
+			vmovdqa	3*16(p_keys), xkey4
+		.endif
+	.else
+		vmovdqa	3*16(p_keys), xkeyA
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyB, var_xdata, var_xdata		/* key 2 */
+		.set i, (i +1)
+	.endr
+
+	add	$(16*by), p_in
+
+	.if (klen == KEY_128)
+		vmovdqa	4*16(p_keys), xkeyB
+	.else
+		.if (load_keys)
+			vmovdqa	4*16(p_keys), xkey4
+		.endif
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 3 */
+		.if (klen == KEY_128)
+			vaesenc	xkey4, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	5*16(p_keys), xkeyA
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 4 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey4, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		.if (load_keys)
+			vmovdqa	6*16(p_keys), xkey8
+		.endif
+	.else
+		vmovdqa	6*16(p_keys), xkeyB
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 5 */
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	7*16(p_keys), xkeyA
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 6 */
+		.if (klen == KEY_128)
+			vaesenc	xkey8, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		vmovdqa	8*16(p_keys), xkeyB
+	.else
+		.if (load_keys)
+			vmovdqa	8*16(p_keys), xkey8
+		.endif
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		vaesenc	xkeyA, var_xdata, var_xdata		/* key 7 */
+		.set i, (i +1)
+	.endr
+
+	.if (klen == KEY_128)
+		.if (load_keys)
+			vmovdqa	9*16(p_keys), xkey12
+		.endif
+	.else
+		vmovdqa	9*16(p_keys), xkeyA
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 8 */
+		.if (klen == KEY_128)
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkey8, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	vmovdqa	10*16(p_keys), xkeyB
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 9 */
+		.if (klen == KEY_128)
+			vaesenc	xkey12, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyA, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	.if (klen != KEY_128)
+		vmovdqa	11*16(p_keys), xkeyA
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		/* key 10 */
+		.if (klen == KEY_128)
+			vaesenclast	xkeyB, var_xdata, var_xdata
+		.else
+			vaesenc	xkeyB, var_xdata, var_xdata
+		.endif
+		.set i, (i +1)
+	.endr
+
+	.if (klen != KEY_128)
+		.if (load_keys)
+			vmovdqa	12*16(p_keys), xkey12
+		.endif
+
+		.set i, 0
+		.rept by
+			club XDATA, i
+			vaesenc	xkeyA, var_xdata, var_xdata	/* key 11 */
+			.set i, (i +1)
+		.endr
+
+		.if (klen == KEY_256)
+			vmovdqa	13*16(p_keys), xkeyA
+		.endif
+
+		.set i, 0
+		.rept by
+			club XDATA, i
+			.if (klen == KEY_256)
+				/* key 12 */
+				vaesenc	xkey12, var_xdata, var_xdata
+			.else
+				vaesenclast xkey12, var_xdata, var_xdata
+			.endif
+			.set i, (i +1)
+		.endr
+
+		.if (klen == KEY_256)
+			vmovdqa	14*16(p_keys), xkeyB
+
+			.set i, 0
+			.rept by
+				club XDATA, i
+				/* key 13 */
+				vaesenc	xkeyA, var_xdata, var_xdata
+				.set i, (i +1)
+			.endr
+
+			.set i, 0
+			.rept by
+				club XDATA, i
+				/* key 14 */
+				vaesenclast	xkeyB, var_xdata, var_xdata
+				.set i, (i +1)
+			.endr
+		.endif
+	.endif
+
+	.set i, 0
+	.rept (by / 2)
+		.set j, (i+1)
+		VMOVDQ	(i*16 - 16*by)(p_in), xkeyA
+		VMOVDQ	(j*16 - 16*by)(p_in), xkeyB
+		club XDATA, i
+		vpxor	xkeyA, var_xdata, var_xdata
+		club XDATA, j
+		vpxor	xkeyB, var_xdata, var_xdata
+		.set i, (i+2)
+	.endr
+
+	.if (i < by)
+		VMOVDQ	(i*16 - 16*by)(p_in), xkeyA
+		club XDATA, i
+		vpxor	xkeyA, var_xdata, var_xdata
+	.endif
+
+	.set i, 0
+	.rept by
+		club XDATA, i
+		VMOVDQ	var_xdata, i*16(p_out)
+		.set i, (i+1)
+	.endr
+.endm
+
+.macro do_aes_load val, key_len
+	do_aes \val, 1, \key_len
+.endm
+
+.macro do_aes_noload val, key_len
+	do_aes \val, 0, \key_len
+.endm
+
+/* main body of aes ctr load */
+
+.macro do_aes_ctrmain key_len
+	cmp	$16, num_bytes
+	jb	.Ldo_return2\key_len
+
+	vmovdqa	byteswap_const(%rip), xbyteswap
+	vmovdqu	(p_iv), xcounter
+	vpshufb	xbyteswap, xcounter, xcounter
+
+	mov	num_bytes, tmp
+	and	$(7*16), tmp
+	jz	.Lmult_of_8_blks\key_len
+
+	/* 1 <= tmp <= 7 */
+	cmp	$(4*16), tmp
+	jg	.Lgt4\key_len
+	je	.Leq4\key_len
+
+.Llt4\key_len:
+	cmp	$(2*16), tmp
+	jg	.Leq3\key_len
+	je	.Leq2\key_len
+
+.Leq1\key_len:
+	do_aes_load	1, \key_len
+	add	$(1*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq2\key_len:
+	do_aes_load	2, \key_len
+	add	$(2*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+
+.Leq3\key_len:
+	do_aes_load	3, \key_len
+	add	$(3*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq4\key_len:
+	do_aes_load	4, \key_len
+	add	$(4*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Lgt4\key_len:
+	cmp	$(6*16), tmp
+	jg	.Leq7\key_len
+	je	.Leq6\key_len
+
+.Leq5\key_len:
+	do_aes_load	5, \key_len
+	add	$(5*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq6\key_len:
+	do_aes_load	6, \key_len
+	add	$(6*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Leq7\key_len:
+	do_aes_load	7, \key_len
+	add	$(7*16), p_out
+	and	$(~7*16), num_bytes
+	jz	.Ldo_return2\key_len
+	jmp	.Lmain_loop2\key_len
+
+.Lmult_of_8_blks\key_len:
+	.if (\key_len != KEY_128)
+		vmovdqa	0*16(p_keys), xkey0
+		vmovdqa	4*16(p_keys), xkey4
+		vmovdqa	8*16(p_keys), xkey8
+		vmovdqa	12*16(p_keys), xkey12
+	.else
+		vmovdqa	0*16(p_keys), xkey0
+		vmovdqa	3*16(p_keys), xkey4
+		vmovdqa	6*16(p_keys), xkey8
+		vmovdqa	9*16(p_keys), xkey12
+	.endif
+.align 16
+.Lmain_loop2\key_len:
+	/* num_bytes is a multiple of 8 and >0 */
+	do_aes_noload	8, \key_len
+	add	$(8*16), p_out
+	sub	$(8*16), num_bytes
+	jne	.Lmain_loop2\key_len
+
+.Ldo_return2\key_len:
+	/* return updated IV */
+	vpshufb	xbyteswap, xcounter, xcounter
+	vmovdqu	xcounter, (p_iv)
+	ret
+.endm
+
+/*
+ * routine to do AES128 CTR enc/decrypt "by8"
+ * XMM registers are clobbered.
+ * Saving/restoring must be done at a higher level
+ * aes_ctr_enc_128_avx_by8(void *in, void *iv, void *keys, void *out,
+ *			unsigned int num_bytes)
+ */
+ENTRY(aes_ctr_enc_128_avx_by8)
+	/* call the aes main loop */
+	do_aes_ctrmain KEY_128
+
+ENDPROC(aes_ctr_enc_128_avx_by8)
+
+/*
+ * routine to do AES192 CTR enc/decrypt "by8"
+ * XMM registers are clobbered.
+ * Saving/restoring must be done at a higher level
+ * aes_ctr_enc_192_avx_by8(void *in, void *iv, void *keys, void *out,
+ *			unsigned int num_bytes)
+ */
+ENTRY(aes_ctr_enc_192_avx_by8)
+	/* call the aes main loop */
+	do_aes_ctrmain KEY_192
+
+ENDPROC(aes_ctr_enc_192_avx_by8)
+
+/*
+ * routine to do AES256 CTR enc/decrypt "by8"
+ * XMM registers are clobbered.
+ * Saving/restoring must be done at a higher level
+ * aes_ctr_enc_256_avx_by8(void *in, void *iv, void *keys, void *out,
+ *			unsigned int num_bytes)
+ */
+ENTRY(aes_ctr_enc_256_avx_by8)
+	/* call the aes main loop */
+	do_aes_ctrmain KEY_256
+
+ENDPROC(aes_ctr_enc_256_avx_by8)

arch/x86/crypto/aes_glue.c

@@ -0,0 +1,70 @@
+/*
+ * Glue Code for the asm optimized version of the AES Cipher Algorithm
+ *
+ */
+
+#include <linux/module.h>
+#include <crypto/aes.h>
+#include <asm/crypto/aes.h>
+
+asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in);
+asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in);
+
+void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
+{
+	aes_enc_blk(ctx, dst, src);
+}
+EXPORT_SYMBOL_GPL(crypto_aes_encrypt_x86);
+
+void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
+{
+	aes_dec_blk(ctx, dst, src);
+}
+EXPORT_SYMBOL_GPL(crypto_aes_decrypt_x86);
+
+static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	aes_enc_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	aes_dec_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static struct crypto_alg aes_alg = {
+	.cra_name		= "aes",
+	.cra_driver_name	= "aes-asm",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= AES_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
+	.cra_module		= THIS_MODULE,
+	.cra_u	= {
+		.cipher	= {
+			.cia_min_keysize	= AES_MIN_KEY_SIZE,
+			.cia_max_keysize	= AES_MAX_KEY_SIZE,
+			.cia_setkey		= crypto_aes_set_key,
+			.cia_encrypt		= aes_encrypt,
+			.cia_decrypt		= aes_decrypt
+		}
+	}
+};
+
+static int __init aes_init(void)
+{
+	return crypto_register_alg(&aes_alg);
+}
+
+static void __exit aes_fini(void)
+{
+	crypto_unregister_alg(&aes_alg);
+}
+
+module_init(aes_init);
+module_exit(aes_fini);
+
+MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");

arch/x86/crypto/blowfish-x86_64-asm_64.S

@@ -0,0 +1,379 @@
+/*
+ * Blowfish Cipher Algorithm (x86_64)
+ *
+ * Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/linkage.h>
+
+.file "blowfish-x86_64-asm.S"
+.text
+
+/* structure of crypto context */
+#define p	0
+#define s0	((16 + 2) * 4)
+#define s1	((16 + 2 + (1 * 256)) * 4)
+#define s2	((16 + 2 + (2 * 256)) * 4)
+#define s3	((16 + 2 + (3 * 256)) * 4)
+
+/* register macros */
+#define CTX %rdi
+#define RIO %rsi
+
+#define RX0 %rax
+#define RX1 %rbx
+#define RX2 %rcx
+#define RX3 %rdx
+
+#define RX0d %eax
+#define RX1d %ebx
+#define RX2d %ecx
+#define RX3d %edx
+
+#define RX0bl %al
+#define RX1bl %bl
+#define RX2bl %cl
+#define RX3bl %dl
+
+#define RX0bh %ah
+#define RX1bh %bh
+#define RX2bh %ch
+#define RX3bh %dh
+
+#define RT0 %rbp
+#define RT1 %rsi
+#define RT2 %r8
+#define RT3 %r9
+
+#define RT0d %ebp
+#define RT1d %esi
+#define RT2d %r8d
+#define RT3d %r9d
+
+#define RKEY %r10
+
+/***********************************************************************
+ * 1-way blowfish
+ ***********************************************************************/
+#define F() \
+	rorq $16,		RX0; \
+	movzbl RX0bh,		RT0d; \
+	movzbl RX0bl,		RT1d; \
+	rolq $16,		RX0; \
+	movl s0(CTX,RT0,4),	RT0d; \
+	addl s1(CTX,RT1,4),	RT0d; \
+	movzbl RX0bh,		RT1d; \
+	movzbl RX0bl,		RT2d; \
+	rolq $32,		RX0; \
+	xorl s2(CTX,RT1,4),	RT0d; \
+	addl s3(CTX,RT2,4),	RT0d; \
+	xorq RT0,		RX0;
+
+#define add_roundkey_enc(n) \
+	xorq p+4*(n)(CTX), 	RX0;
+
+#define round_enc(n) \
+	add_roundkey_enc(n); \
+	\
+	F(); \
+	F();
+
+#define add_roundkey_dec(n) \
+	movq p+4*(n-1)(CTX),	RT0; \
+	rorq $32,		RT0; \
+	xorq RT0,		RX0;
+
+#define round_dec(n) \
+	add_roundkey_dec(n); \
+	\
+	F(); \
+	F(); \
+
+#define read_block() \
+	movq (RIO), 		RX0; \
+	rorq $32, 		RX0; \
+	bswapq 			RX0;
+
+#define write_block() \
+	bswapq 			RX0; \
+	movq RX0, 		(RIO);
+
+#define xor_block() \
+	bswapq 			RX0; \
+	xorq RX0, 		(RIO);
+
+ENTRY(__blowfish_enc_blk)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool, if true: xor output
+	 */
+	movq %rbp, %r11;
+
+	movq %rsi, %r10;
+	movq %rdx, RIO;
+
+	read_block();
+
+	round_enc(0);
+	round_enc(2);
+	round_enc(4);
+	round_enc(6);
+	round_enc(8);
+	round_enc(10);
+	round_enc(12);
+	round_enc(14);
+	add_roundkey_enc(16);
+
+	movq %r11, %rbp;
+
+	movq %r10, RIO;
+	test %cl, %cl;
+	jnz .L__enc_xor;
+
+	write_block();
+	ret;
+.L__enc_xor:
+	xor_block();
+	ret;
+ENDPROC(__blowfish_enc_blk)
+
+ENTRY(blowfish_dec_blk)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+	movq %rbp, %r11;
+
+	movq %rsi, %r10;
+	movq %rdx, RIO;
+
+	read_block();
+
+	round_dec(17);
+	round_dec(15);
+	round_dec(13);
+	round_dec(11);
+	round_dec(9);
+	round_dec(7);
+	round_dec(5);
+	round_dec(3);
+	add_roundkey_dec(1);
+
+	movq %r10, RIO;
+	write_block();
+
+	movq %r11, %rbp;
+
+	ret;
+ENDPROC(blowfish_dec_blk)
+
+/**********************************************************************
+  4-way blowfish, four blocks parallel
+ **********************************************************************/
+
+/* F() for 4-way. Slower when used alone/1-way, but faster when used
+ * parallel/4-way (tested on AMD Phenom II & Intel Xeon E7330).
+ */
+#define F4(x) \
+	movzbl x ## bh,		RT1d; \
+	movzbl x ## bl,		RT3d; \
+	rorq $16,		x; \
+	movzbl x ## bh,		RT0d; \
+	movzbl x ## bl,		RT2d; \
+	rorq $16,		x; \
+	movl s0(CTX,RT0,4),	RT0d; \
+	addl s1(CTX,RT2,4),	RT0d; \
+	xorl s2(CTX,RT1,4),	RT0d; \
+	addl s3(CTX,RT3,4),	RT0d; \
+	xorq RT0,		x;
+
+#define add_preloaded_roundkey4() \
+	xorq RKEY,		RX0; \
+	xorq RKEY,		RX1; \
+	xorq RKEY,		RX2; \
+	xorq RKEY,		RX3;
+
+#define preload_roundkey_enc(n) \
+	movq p+4*(n)(CTX),	RKEY;
+
+#define add_roundkey_enc4(n) \
+	add_preloaded_roundkey4(); \
+	preload_roundkey_enc(n + 2);
+
+#define round_enc4(n) \
+	add_roundkey_enc4(n); \
+	\
+	F4(RX0); \
+	F4(RX1); \
+	F4(RX2); \
+	F4(RX3); \
+	\
+	F4(RX0); \
+	F4(RX1); \
+	F4(RX2); \
+	F4(RX3);
+
+#define preload_roundkey_dec(n) \
+	movq p+4*((n)-1)(CTX),	RKEY; \
+	rorq $32,		RKEY;
+
+#define add_roundkey_dec4(n) \
+	add_preloaded_roundkey4(); \
+	preload_roundkey_dec(n - 2);
+
+#define round_dec4(n) \
+	add_roundkey_dec4(n); \
+	\
+	F4(RX0); \
+	F4(RX1); \
+	F4(RX2); \
+	F4(RX3); \
+	\
+	F4(RX0); \
+	F4(RX1); \
+	F4(RX2); \
+	F4(RX3);
+
+#define read_block4() \
+	movq (RIO),		RX0; \
+	rorq $32,		RX0; \
+	bswapq 			RX0; \
+	\
+	movq 8(RIO),		RX1; \
+	rorq $32,		RX1; \
+	bswapq 			RX1; \
+	\
+	movq 16(RIO),		RX2; \
+	rorq $32,		RX2; \
+	bswapq 			RX2; \
+	\
+	movq 24(RIO),		RX3; \
+	rorq $32,		RX3; \
+	bswapq 			RX3;
+
+#define write_block4() \
+	bswapq 			RX0; \
+	movq RX0,		(RIO); \
+	\
+	bswapq 			RX1; \
+	movq RX1,		8(RIO); \
+	\
+	bswapq 			RX2; \
+	movq RX2,		16(RIO); \
+	\
+	bswapq 			RX3; \
+	movq RX3,		24(RIO);
+
+#define xor_block4() \
+	bswapq 			RX0; \
+	xorq RX0,		(RIO); \
+	\
+	bswapq 			RX1; \
+	xorq RX1,		8(RIO); \
+	\
+	bswapq 			RX2; \
+	xorq RX2,		16(RIO); \
+	\
+	bswapq 			RX3; \
+	xorq RX3,		24(RIO);
+
+ENTRY(__blowfish_enc_blk_4way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool, if true: xor output
+	 */
+	pushq %rbp;
+	pushq %rbx;
+	pushq %rcx;
+
+	preload_roundkey_enc(0);
+
+	movq %rsi, %r11;
+	movq %rdx, RIO;
+
+	read_block4();
+
+	round_enc4(0);
+	round_enc4(2);
+	round_enc4(4);
+	round_enc4(6);
+	round_enc4(8);
+	round_enc4(10);
+	round_enc4(12);
+	round_enc4(14);
+	add_preloaded_roundkey4();
+
+	popq %rbp;
+	movq %r11, RIO;
+
+	test %bpl, %bpl;
+	jnz .L__enc_xor4;
+
+	write_block4();
+
+	popq %rbx;
+	popq %rbp;
+	ret;
+
+.L__enc_xor4:
+	xor_block4();
+
+	popq %rbx;
+	popq %rbp;
+	ret;
+ENDPROC(__blowfish_enc_blk_4way)
+
+ENTRY(blowfish_dec_blk_4way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+	pushq %rbp;
+	pushq %rbx;
+	preload_roundkey_dec(17);
+
+	movq %rsi, %r11;
+	movq %rdx, RIO;
+
+	read_block4();
+
+	round_dec4(17);
+	round_dec4(15);
+	round_dec4(13);
+	round_dec4(11);
+	round_dec4(9);
+	round_dec4(7);
+	round_dec4(5);
+	round_dec4(3);
+	add_preloaded_roundkey4();
+
+	movq %r11, RIO;
+	write_block4();
+
+	popq %rbx;
+	popq %rbp;
+
+	ret;
+ENDPROC(blowfish_dec_blk_4way)

arch/x86/crypto/blowfish_glue.c

@@ -0,0 +1,482 @@
+/*
+ * Glue Code for assembler optimized version of Blowfish
+ *
+ * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ * CTR part based on code (crypto/ctr.c) by:
+ *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <asm/processor.h>
+#include <crypto/blowfish.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/algapi.h>
+
+/* regular block cipher functions */
+asmlinkage void __blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src,
+				   bool xor);
+asmlinkage void blowfish_dec_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src);
+
+/* 4-way parallel cipher functions */
+asmlinkage void __blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst,
+					const u8 *src, bool xor);
+asmlinkage void blowfish_dec_blk_4way(struct bf_ctx *ctx, u8 *dst,
+				      const u8 *src);
+
+static inline void blowfish_enc_blk(struct bf_ctx *ctx, u8 *dst, const u8 *src)
+{
+	__blowfish_enc_blk(ctx, dst, src, false);
+}
+
+static inline void blowfish_enc_blk_xor(struct bf_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	__blowfish_enc_blk(ctx, dst, src, true);
+}
+
+static inline void blowfish_enc_blk_4way(struct bf_ctx *ctx, u8 *dst,
+					 const u8 *src)
+{
+	__blowfish_enc_blk_4way(ctx, dst, src, false);
+}
+
+static inline void blowfish_enc_blk_xor_4way(struct bf_ctx *ctx, u8 *dst,
+				      const u8 *src)
+{
+	__blowfish_enc_blk_4way(ctx, dst, src, true);
+}
+
+static void blowfish_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	blowfish_enc_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static void blowfish_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	blowfish_dec_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
+		     void (*fn)(struct bf_ctx *, u8 *, const u8 *),
+		     void (*fn_4way)(struct bf_ctx *, u8 *, const u8 *))
+{
+	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = BF_BLOCK_SIZE;
+	unsigned int nbytes;
+	int err;
+
+	err = blkcipher_walk_virt(desc, walk);
+
+	while ((nbytes = walk->nbytes)) {
+		u8 *wsrc = walk->src.virt.addr;
+		u8 *wdst = walk->dst.virt.addr;
+
+		/* Process four block batch */
+		if (nbytes >= bsize * 4) {
+			do {
+				fn_4way(ctx, wdst, wsrc);
+
+				wsrc += bsize * 4;
+				wdst += bsize * 4;
+				nbytes -= bsize * 4;
+			} while (nbytes >= bsize * 4);
+
+			if (nbytes < bsize)
+				goto done;
+		}
+
+		/* Handle leftovers */
+		do {
+			fn(ctx, wdst, wsrc);
+
+			wsrc += bsize;
+			wdst += bsize;
+			nbytes -= bsize;
+		} while (nbytes >= bsize);
+
+done:
+		err = blkcipher_walk_done(desc, walk, nbytes);
+	}
+
+	return err;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, blowfish_enc_blk, blowfish_enc_blk_4way);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, blowfish_dec_blk, blowfish_dec_blk_4way);
+}
+
+static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = BF_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 *iv = (u64 *)walk->iv;
+
+	do {
+		*dst = *src ^ *iv;
+		blowfish_enc_blk(ctx, (u8 *)dst, (u8 *)dst);
+		iv = dst;
+
+		src += 1;
+		dst += 1;
+		nbytes -= bsize;
+	} while (nbytes >= bsize);
+
+	*(u64 *)walk->iv = *iv;
+	return nbytes;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_encrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = BF_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 ivs[4 - 1];
+	u64 last_iv;
+
+	/* Start of the last block. */
+	src += nbytes / bsize - 1;
+	dst += nbytes / bsize - 1;
+
+	last_iv = *src;
+
+	/* Process four block batch */
+	if (nbytes >= bsize * 4) {
+		do {
+			nbytes -= bsize * 4 - bsize;
+			src -= 4 - 1;
+			dst -= 4 - 1;
+
+			ivs[0] = src[0];
+			ivs[1] = src[1];
+			ivs[2] = src[2];
+
+			blowfish_dec_blk_4way(ctx, (u8 *)dst, (u8 *)src);
+
+			dst[1] ^= ivs[0];
+			dst[2] ^= ivs[1];
+			dst[3] ^= ivs[2];
+
+			nbytes -= bsize;
+			if (nbytes < bsize)
+				goto done;
+
+			*dst ^= *(src - 1);
+			src -= 1;
+			dst -= 1;
+		} while (nbytes >= bsize * 4);
+	}
+
+	/* Handle leftovers */
+	for (;;) {
+		blowfish_dec_blk(ctx, (u8 *)dst, (u8 *)src);
+
+		nbytes -= bsize;
+		if (nbytes < bsize)
+			break;
+
+		*dst ^= *(src - 1);
+		src -= 1;
+		dst -= 1;
+	}
+
+done:
+	*dst ^= *(u64 *)walk->iv;
+	*(u64 *)walk->iv = last_iv;
+
+	return nbytes;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_decrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static void ctr_crypt_final(struct bf_ctx *ctx, struct blkcipher_walk *walk)
+{
+	u8 *ctrblk = walk->iv;
+	u8 keystream[BF_BLOCK_SIZE];
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	blowfish_enc_blk(ctx, keystream, ctrblk);
+	crypto_xor(keystream, src, nbytes);
+	memcpy(dst, keystream, nbytes);
+
+	crypto_inc(ctrblk, BF_BLOCK_SIZE);
+}
+
+static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
+				struct blkcipher_walk *walk)
+{
+	struct bf_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = BF_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv);
+	__be64 ctrblocks[4];
+
+	/* Process four block batch */
+	if (nbytes >= bsize * 4) {
+		do {
+			if (dst != src) {
+				dst[0] = src[0];
+				dst[1] = src[1];
+				dst[2] = src[2];
+				dst[3] = src[3];
+			}
+
+			/* create ctrblks for parallel encrypt */
+			ctrblocks[0] = cpu_to_be64(ctrblk++);
+			ctrblocks[1] = cpu_to_be64(ctrblk++);
+			ctrblocks[2] = cpu_to_be64(ctrblk++);
+			ctrblocks[3] = cpu_to_be64(ctrblk++);
+
+			blowfish_enc_blk_xor_4way(ctx, (u8 *)dst,
+						  (u8 *)ctrblocks);
+
+			src += 4;
+			dst += 4;
+		} while ((nbytes -= bsize * 4) >= bsize * 4);
+
+		if (nbytes < bsize)
+			goto done;
+	}
+
+	/* Handle leftovers */
+	do {
+		if (dst != src)
+			*dst = *src;
+
+		ctrblocks[0] = cpu_to_be64(ctrblk++);
+
+		blowfish_enc_blk_xor(ctx, (u8 *)dst, (u8 *)ctrblocks);
+
+		src += 1;
+		dst += 1;
+	} while ((nbytes -= bsize) >= bsize);
+
+done:
+	*(__be64 *)walk->iv = cpu_to_be64(ctrblk);
+	return nbytes;
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, BF_BLOCK_SIZE);
+
+	while ((nbytes = walk.nbytes) >= BF_BLOCK_SIZE) {
+		nbytes = __ctr_crypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	if (walk.nbytes) {
+		ctr_crypt_final(crypto_blkcipher_ctx(desc->tfm), &walk);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+
+static struct crypto_alg bf_algs[4] = { {
+	.cra_name		= "blowfish",
+	.cra_driver_name	= "blowfish-asm",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= BF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct bf_ctx),
+	.cra_alignmask		= 0,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.cipher = {
+			.cia_min_keysize	= BF_MIN_KEY_SIZE,
+			.cia_max_keysize	= BF_MAX_KEY_SIZE,
+			.cia_setkey		= blowfish_setkey,
+			.cia_encrypt		= blowfish_encrypt,
+			.cia_decrypt		= blowfish_decrypt,
+		}
+	}
+}, {
+	.cra_name		= "ecb(blowfish)",
+	.cra_driver_name	= "ecb-blowfish-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= BF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct bf_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= BF_MIN_KEY_SIZE,
+			.max_keysize	= BF_MAX_KEY_SIZE,
+			.setkey		= blowfish_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(blowfish)",
+	.cra_driver_name	= "cbc-blowfish-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= BF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct bf_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= BF_MIN_KEY_SIZE,
+			.max_keysize	= BF_MAX_KEY_SIZE,
+			.ivsize		= BF_BLOCK_SIZE,
+			.setkey		= blowfish_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(blowfish)",
+	.cra_driver_name	= "ctr-blowfish-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct bf_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= BF_MIN_KEY_SIZE,
+			.max_keysize	= BF_MAX_KEY_SIZE,
+			.ivsize		= BF_BLOCK_SIZE,
+			.setkey		= blowfish_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+} };
+
+static bool is_blacklisted_cpu(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (boot_cpu_data.x86 == 0x0f) {
+		/*
+		 * On Pentium 4, blowfish-x86_64 is slower than generic C
+		 * implementation because use of 64bit rotates (which are really
+		 * slow on P4). Therefore blacklist P4s.
+		 */
+		return true;
+	}
+
+	return false;
+}
+
+static int force;
+module_param(force, int, 0);
+MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+
+static int __init init(void)
+{
+	if (!force && is_blacklisted_cpu()) {
+		printk(KERN_INFO
+			"blowfish-x86_64: performance on this CPU "
+			"would be suboptimal: disabling "
+			"blowfish-x86_64.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(bf_algs, ARRAY_SIZE(bf_algs));
+}
+
+static void __exit fini(void)
+{
+	crypto_unregister_algs(bf_algs, ARRAY_SIZE(bf_algs));
+}
+
+module_init(init);
+module_exit(fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");

arch/x86/crypto/camellia-x86_64-asm_64.S

@@ -0,0 +1,514 @@
+/*
+ * Camellia Cipher Algorithm (x86_64)
+ *
+ * Copyright (C) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/linkage.h>
+
+.file "camellia-x86_64-asm_64.S"
+.text
+
+.extern camellia_sp10011110;
+.extern camellia_sp22000222;
+.extern camellia_sp03303033;
+.extern camellia_sp00444404;
+.extern camellia_sp02220222;
+.extern camellia_sp30333033;
+.extern camellia_sp44044404;
+.extern camellia_sp11101110;
+
+#define sp10011110 camellia_sp10011110
+#define sp22000222 camellia_sp22000222
+#define sp03303033 camellia_sp03303033
+#define sp00444404 camellia_sp00444404
+#define sp02220222 camellia_sp02220222
+#define sp30333033 camellia_sp30333033
+#define sp44044404 camellia_sp44044404
+#define sp11101110 camellia_sp11101110
+
+#define CAMELLIA_TABLE_BYTE_LEN 272
+
+/* struct camellia_ctx: */
+#define key_table 0
+#define key_length CAMELLIA_TABLE_BYTE_LEN
+
+/* register macros */
+#define CTX %rdi
+#define RIO %rsi
+#define RIOd %esi
+
+#define RAB0 %rax
+#define RCD0 %rcx
+#define RAB1 %rbx
+#define RCD1 %rdx
+
+#define RAB0d %eax
+#define RCD0d %ecx
+#define RAB1d %ebx
+#define RCD1d %edx
+
+#define RAB0bl %al
+#define RCD0bl %cl
+#define RAB1bl %bl
+#define RCD1bl %dl
+
+#define RAB0bh %ah
+#define RCD0bh %ch
+#define RAB1bh %bh
+#define RCD1bh %dh
+
+#define RT0 %rsi
+#define RT1 %rbp
+#define RT2 %r8
+
+#define RT0d %esi
+#define RT1d %ebp
+#define RT2d %r8d
+
+#define RT2bl %r8b
+
+#define RXOR %r9
+#define RRBP %r10
+#define RDST %r11
+
+#define RXORd %r9d
+#define RXORbl %r9b
+
+#define xor2ror16(T0, T1, tmp1, tmp2, ab, dst) \
+	movzbl ab ## bl,		tmp2 ## d; \
+	movzbl ab ## bh,		tmp1 ## d; \
+	rorq $16,			ab; \
+	xorq T0(, tmp2, 8),		dst; \
+	xorq T1(, tmp1, 8),		dst;
+
+/**********************************************************************
+  1-way camellia
+ **********************************************************************/
+#define roundsm(ab, subkey, cd) \
+	movq (key_table + ((subkey) * 2) * 4)(CTX),	RT2; \
+	\
+	xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 0, cd ## 0); \
+	xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 0, RT2); \
+	xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 0, cd ## 0); \
+	xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 0, RT2); \
+	\
+	xorq RT2,					cd ## 0;
+
+#define fls(l, r, kl, kr) \
+	movl (key_table + ((kl) * 2) * 4)(CTX),		RT0d; \
+	andl l ## 0d,					RT0d; \
+	roll $1,					RT0d; \
+	shlq $32,					RT0; \
+	xorq RT0,					l ## 0; \
+	movq (key_table + ((kr) * 2) * 4)(CTX),		RT1; \
+	orq r ## 0,					RT1; \
+	shrq $32,					RT1; \
+	xorq RT1,					r ## 0; \
+	\
+	movq (key_table + ((kl) * 2) * 4)(CTX),		RT2; \
+	orq l ## 0,					RT2; \
+	shrq $32,					RT2; \
+	xorq RT2,					l ## 0; \
+	movl (key_table + ((kr) * 2) * 4)(CTX),		RT0d; \
+	andl r ## 0d,					RT0d; \
+	roll $1,					RT0d; \
+	shlq $32,					RT0; \
+	xorq RT0,					r ## 0;
+
+#define enc_rounds(i) \
+	roundsm(RAB, i + 2, RCD); \
+	roundsm(RCD, i + 3, RAB); \
+	roundsm(RAB, i + 4, RCD); \
+	roundsm(RCD, i + 5, RAB); \
+	roundsm(RAB, i + 6, RCD); \
+	roundsm(RCD, i + 7, RAB);
+
+#define enc_fls(i) \
+	fls(RAB, RCD, i + 0, i + 1);
+
+#define enc_inpack() \
+	movq (RIO),			RAB0; \
+	bswapq				RAB0; \
+	rolq $32,			RAB0; \
+	movq 4*2(RIO),			RCD0; \
+	bswapq				RCD0; \
+	rorq $32,			RCD0; \
+	xorq key_table(CTX),		RAB0;
+
+#define enc_outunpack(op, max) \
+	xorq key_table(CTX, max, 8),	RCD0; \
+	rorq $32,			RCD0; \
+	bswapq				RCD0; \
+	op ## q RCD0,			(RIO); \
+	rolq $32,			RAB0; \
+	bswapq				RAB0; \
+	op ## q RAB0,			4*2(RIO);
+
+#define dec_rounds(i) \
+	roundsm(RAB, i + 7, RCD); \
+	roundsm(RCD, i + 6, RAB); \
+	roundsm(RAB, i + 5, RCD); \
+	roundsm(RCD, i + 4, RAB); \
+	roundsm(RAB, i + 3, RCD); \
+	roundsm(RCD, i + 2, RAB);
+
+#define dec_fls(i) \
+	fls(RAB, RCD, i + 1, i + 0);
+
+#define dec_inpack(max) \
+	movq (RIO),			RAB0; \
+	bswapq				RAB0; \
+	rolq $32,			RAB0; \
+	movq 4*2(RIO),			RCD0; \
+	bswapq				RCD0; \
+	rorq $32,			RCD0; \
+	xorq key_table(CTX, max, 8),	RAB0;
+
+#define dec_outunpack() \
+	xorq key_table(CTX),		RCD0; \
+	rorq $32,			RCD0; \
+	bswapq				RCD0; \
+	movq RCD0,			(RIO); \
+	rolq $32,			RAB0; \
+	bswapq				RAB0; \
+	movq RAB0,			4*2(RIO);
+
+ENTRY(__camellia_enc_blk)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool xor
+	 */
+	movq %rbp, RRBP;
+
+	movq %rcx, RXOR;
+	movq %rsi, RDST;
+	movq %rdx, RIO;
+
+	enc_inpack();
+
+	enc_rounds(0);
+	enc_fls(8);
+	enc_rounds(8);
+	enc_fls(16);
+	enc_rounds(16);
+	movl $24, RT1d; /* max */
+
+	cmpb $16, key_length(CTX);
+	je .L__enc_done;
+
+	enc_fls(24);
+	enc_rounds(24);
+	movl $32, RT1d; /* max */
+
+.L__enc_done:
+	testb RXORbl, RXORbl;
+	movq RDST, RIO;
+
+	jnz .L__enc_xor;
+
+	enc_outunpack(mov, RT1);
+
+	movq RRBP, %rbp;
+	ret;
+
+.L__enc_xor:
+	enc_outunpack(xor, RT1);
+
+	movq RRBP, %rbp;
+	ret;
+ENDPROC(__camellia_enc_blk)
+
+ENTRY(camellia_dec_blk)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+	cmpl $16, key_length(CTX);
+	movl $32, RT2d;
+	movl $24, RXORd;
+	cmovel RXORd, RT2d; /* max */
+
+	movq %rbp, RRBP;
+	movq %rsi, RDST;
+	movq %rdx, RIO;
+
+	dec_inpack(RT2);
+
+	cmpb $24, RT2bl;
+	je .L__dec_rounds16;
+
+	dec_rounds(24);
+	dec_fls(24);
+
+.L__dec_rounds16:
+	dec_rounds(16);
+	dec_fls(16);
+	dec_rounds(8);
+	dec_fls(8);
+	dec_rounds(0);
+
+	movq RDST, RIO;
+
+	dec_outunpack();
+
+	movq RRBP, %rbp;
+	ret;
+ENDPROC(camellia_dec_blk)
+
+/**********************************************************************
+  2-way camellia
+ **********************************************************************/
+#define roundsm2(ab, subkey, cd) \
+	movq (key_table + ((subkey) * 2) * 4)(CTX),	RT2; \
+	xorq RT2,					cd ## 1; \
+	\
+	xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 0, cd ## 0); \
+	xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 0, RT2); \
+	xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 0, cd ## 0); \
+	xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 0, RT2); \
+	\
+		xor2ror16(sp00444404, sp03303033, RT0, RT1, ab ## 1, cd ## 1); \
+		xorq RT2,					cd ## 0; \
+		xor2ror16(sp22000222, sp10011110, RT0, RT1, ab ## 1, cd ## 1); \
+		xor2ror16(sp11101110, sp44044404, RT0, RT1, ab ## 1, cd ## 1); \
+		xor2ror16(sp30333033, sp02220222, RT0, RT1, ab ## 1, cd ## 1);
+
+#define fls2(l, r, kl, kr) \
+	movl (key_table + ((kl) * 2) * 4)(CTX),		RT0d; \
+	andl l ## 0d,					RT0d; \
+	roll $1,					RT0d; \
+	shlq $32,					RT0; \
+	xorq RT0,					l ## 0; \
+	movq (key_table + ((kr) * 2) * 4)(CTX),		RT1; \
+	orq r ## 0,					RT1; \
+	shrq $32,					RT1; \
+	xorq RT1,					r ## 0; \
+	\
+		movl (key_table + ((kl) * 2) * 4)(CTX),		RT2d; \
+		andl l ## 1d,					RT2d; \
+		roll $1,					RT2d; \
+		shlq $32,					RT2; \
+		xorq RT2,					l ## 1; \
+		movq (key_table + ((kr) * 2) * 4)(CTX),		RT0; \
+		orq r ## 1,					RT0; \
+		shrq $32,					RT0; \
+		xorq RT0,					r ## 1; \
+	\
+	movq (key_table + ((kl) * 2) * 4)(CTX),		RT1; \
+	orq l ## 0,					RT1; \
+	shrq $32,					RT1; \
+	xorq RT1,					l ## 0; \
+	movl (key_table + ((kr) * 2) * 4)(CTX),		RT2d; \
+	andl r ## 0d,					RT2d; \
+	roll $1,					RT2d; \
+	shlq $32,					RT2; \
+	xorq RT2,					r ## 0; \
+	\
+		movq (key_table + ((kl) * 2) * 4)(CTX),		RT0; \
+		orq l ## 1,					RT0; \
+		shrq $32,					RT0; \
+		xorq RT0,					l ## 1; \
+		movl (key_table + ((kr) * 2) * 4)(CTX),		RT1d; \
+		andl r ## 1d,					RT1d; \
+		roll $1,					RT1d; \
+		shlq $32,					RT1; \
+		xorq RT1,					r ## 1;
+
+#define enc_rounds2(i) \
+	roundsm2(RAB, i + 2, RCD); \
+	roundsm2(RCD, i + 3, RAB); \
+	roundsm2(RAB, i + 4, RCD); \
+	roundsm2(RCD, i + 5, RAB); \
+	roundsm2(RAB, i + 6, RCD); \
+	roundsm2(RCD, i + 7, RAB);
+
+#define enc_fls2(i) \
+	fls2(RAB, RCD, i + 0, i + 1);
+
+#define enc_inpack2() \
+	movq (RIO),			RAB0; \
+	bswapq				RAB0; \
+	rorq $32,			RAB0; \
+	movq 4*2(RIO),			RCD0; \
+	bswapq				RCD0; \
+	rolq $32,			RCD0; \
+	xorq key_table(CTX),		RAB0; \
+	\
+		movq 8*2(RIO),			RAB1; \
+		bswapq				RAB1; \
+		rorq $32,			RAB1; \
+		movq 12*2(RIO),			RCD1; \
+		bswapq				RCD1; \
+		rolq $32,			RCD1; \
+		xorq key_table(CTX),		RAB1;
+
+#define enc_outunpack2(op, max) \
+	xorq key_table(CTX, max, 8),	RCD0; \
+	rolq $32,			RCD0; \
+	bswapq				RCD0; \
+	op ## q RCD0,			(RIO); \
+	rorq $32,			RAB0; \
+	bswapq				RAB0; \
+	op ## q RAB0,			4*2(RIO); \
+	\
+		xorq key_table(CTX, max, 8),	RCD1; \
+		rolq $32,			RCD1; \
+		bswapq				RCD1; \
+		op ## q RCD1,			8*2(RIO); \
+		rorq $32,			RAB1; \
+		bswapq				RAB1; \
+		op ## q RAB1,			12*2(RIO);
+
+#define dec_rounds2(i) \
+	roundsm2(RAB, i + 7, RCD); \
+	roundsm2(RCD, i + 6, RAB); \
+	roundsm2(RAB, i + 5, RCD); \
+	roundsm2(RCD, i + 4, RAB); \
+	roundsm2(RAB, i + 3, RCD); \
+	roundsm2(RCD, i + 2, RAB);
+
+#define dec_fls2(i) \
+	fls2(RAB, RCD, i + 1, i + 0);
+
+#define dec_inpack2(max) \
+	movq (RIO),			RAB0; \
+	bswapq				RAB0; \
+	rorq $32,			RAB0; \
+	movq 4*2(RIO),			RCD0; \
+	bswapq				RCD0; \
+	rolq $32,			RCD0; \
+	xorq key_table(CTX, max, 8),	RAB0; \
+	\
+		movq 8*2(RIO),			RAB1; \
+		bswapq				RAB1; \
+		rorq $32,			RAB1; \
+		movq 12*2(RIO),			RCD1; \
+		bswapq				RCD1; \
+		rolq $32,			RCD1; \
+		xorq key_table(CTX, max, 8),	RAB1;
+
+#define dec_outunpack2() \
+	xorq key_table(CTX),		RCD0; \
+	rolq $32,			RCD0; \
+	bswapq				RCD0; \
+	movq RCD0,			(RIO); \
+	rorq $32,			RAB0; \
+	bswapq				RAB0; \
+	movq RAB0,			4*2(RIO); \
+	\
+		xorq key_table(CTX),		RCD1; \
+		rolq $32,			RCD1; \
+		bswapq				RCD1; \
+		movq RCD1,			8*2(RIO); \
+		rorq $32,			RAB1; \
+		bswapq				RAB1; \
+		movq RAB1,			12*2(RIO);
+
+ENTRY(__camellia_enc_blk_2way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool xor
+	 */
+	pushq %rbx;
+
+	movq %rbp, RRBP;
+	movq %rcx, RXOR;
+	movq %rsi, RDST;
+	movq %rdx, RIO;
+
+	enc_inpack2();
+
+	enc_rounds2(0);
+	enc_fls2(8);
+	enc_rounds2(8);
+	enc_fls2(16);
+	enc_rounds2(16);
+	movl $24, RT2d; /* max */
+
+	cmpb $16, key_length(CTX);
+	je .L__enc2_done;
+
+	enc_fls2(24);
+	enc_rounds2(24);
+	movl $32, RT2d; /* max */
+
+.L__enc2_done:
+	test RXORbl, RXORbl;
+	movq RDST, RIO;
+	jnz .L__enc2_xor;
+
+	enc_outunpack2(mov, RT2);
+
+	movq RRBP, %rbp;
+	popq %rbx;
+	ret;
+
+.L__enc2_xor:
+	enc_outunpack2(xor, RT2);
+
+	movq RRBP, %rbp;
+	popq %rbx;
+	ret;
+ENDPROC(__camellia_enc_blk_2way)
+
+ENTRY(camellia_dec_blk_2way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+	cmpl $16, key_length(CTX);
+	movl $32, RT2d;
+	movl $24, RXORd;
+	cmovel RXORd, RT2d; /* max */
+
+	movq %rbx, RXOR;
+	movq %rbp, RRBP;
+	movq %rsi, RDST;
+	movq %rdx, RIO;
+
+	dec_inpack2(RT2);
+
+	cmpb $24, RT2bl;
+	je .L__dec2_rounds16;
+
+	dec_rounds2(24);
+	dec_fls2(24);
+
+.L__dec2_rounds16:
+	dec_rounds2(16);
+	dec_fls2(16);
+	dec_rounds2(8);
+	dec_fls2(8);
+	dec_rounds2(0);
+
+	movq RDST, RIO;
+
+	dec_outunpack2();
+
+	movq RRBP, %rbp;
+	movq RXOR, %rbx;
+	ret;
+ENDPROC(camellia_dec_blk_2way)

arch/x86/crypto/camellia_aesni_avx2_glue.c

@@ -0,0 +1,586 @@
+/*
+ * Glue Code for x86_64/AVX2/AES-NI assembler optimized version of Camellia
+ *
+ * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <crypto/ctr.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <asm/crypto/camellia.h>
+#include <asm/crypto/glue_helper.h>
+
+#define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
+#define CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS 32
+
+/* 32-way AVX2/AES-NI parallel cipher functions */
+asmlinkage void camellia_ecb_enc_32way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src);
+asmlinkage void camellia_ecb_dec_32way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src);
+
+asmlinkage void camellia_cbc_dec_32way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src);
+asmlinkage void camellia_ctr_32way(struct camellia_ctx *ctx, u8 *dst,
+				   const u8 *src, le128 *iv);
+
+asmlinkage void camellia_xts_enc_32way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src, le128 *iv);
+asmlinkage void camellia_xts_dec_32way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src, le128 *iv);
+
+static const struct common_glue_ctx camellia_enc = {
+	.num_funcs = 4,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_enc_32way) }
+	}, {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_enc_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_ctr = {
+	.num_funcs = 4,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_ctr_32way) }
+	}, {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_ctr_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_enc_xts = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc_32way) }
+	}, {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc_16way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_dec = {
+	.num_funcs = 4,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_dec_32way) }
+	}, {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_dec_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_dec_cbc = {
+	.num_funcs = 4,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_cbc_dec_32way) }
+	}, {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_cbc_dec_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_decrypt_cbc_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_dec_blk) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_dec_xts = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec_32way) }
+	}, {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec_16way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec) }
+	} }
+};
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&camellia_enc, desc, dst, src, nbytes);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&camellia_dec, desc, dst, src, nbytes);
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(camellia_enc_blk), desc,
+				       dst, src, nbytes);
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_decrypt_128bit(&camellia_dec_cbc, desc, dst, src,
+				       nbytes);
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ctr_crypt_128bit(&camellia_ctr, desc, dst, src, nbytes);
+}
+
+static inline bool camellia_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+	return glue_fpu_begin(CAMELLIA_BLOCK_SIZE,
+			      CAMELLIA_AESNI_PARALLEL_BLOCKS, NULL, fpu_enabled,
+			      nbytes);
+}
+
+static inline void camellia_fpu_end(bool fpu_enabled)
+{
+	glue_fpu_end(fpu_enabled);
+}
+
+static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+			   unsigned int key_len)
+{
+	return __camellia_setkey(crypto_tfm_ctx(tfm), in_key, key_len,
+				 &tfm->crt_flags);
+}
+
+struct crypt_priv {
+	struct camellia_ctx *ctx;
+	bool fpu_enabled;
+};
+
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes >= CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS * bsize) {
+		camellia_ecb_enc_32way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
+	}
+
+	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+		camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+	}
+
+	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		camellia_enc_blk(ctx->ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes >= CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS * bsize) {
+		camellia_ecb_dec_32way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS;
+	}
+
+	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+		camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+	}
+
+	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		camellia_dec_blk(ctx->ctx, srcdst, srcdst);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->camellia_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	camellia_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[CAMELLIA_AESNI_AVX2_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->camellia_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	camellia_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+
+	return glue_xts_crypt_128bit(&camellia_enc_xts, desc, dst, src, nbytes,
+				     XTS_TWEAK_CAST(camellia_enc_blk),
+				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+
+	return glue_xts_crypt_128bit(&camellia_dec_xts, desc, dst, src, nbytes,
+				     XTS_TWEAK_CAST(camellia_enc_blk),
+				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+}
+
+static struct crypto_alg cmll_algs[10] = { {
+	.cra_name		= "__ecb-camellia-aesni-avx2",
+	.cra_driver_name	= "__driver-ecb-camellia-aesni-avx2",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.setkey		= camellia_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__cbc-camellia-aesni-avx2",
+	.cra_driver_name	= "__driver-cbc-camellia-aesni-avx2",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.setkey		= camellia_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__ctr-camellia-aesni-avx2",
+	.cra_driver_name	= "__driver-ctr-camellia-aesni-avx2",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct camellia_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= camellia_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+}, {
+	.cra_name		= "__lrw-camellia-aesni-avx2",
+	.cra_driver_name	= "__driver-lrw-camellia-aesni-avx2",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_lrw_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_exit		= lrw_camellia_exit_tfm,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= lrw_camellia_setkey,
+			.encrypt	= lrw_encrypt,
+			.decrypt	= lrw_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__xts-camellia-aesni-avx2",
+	.cra_driver_name	= "__driver-xts-camellia-aesni-avx2",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_xts_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= xts_camellia_setkey,
+			.encrypt	= xts_encrypt,
+			.decrypt	= xts_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ecb(camellia)",
+	.cra_driver_name	= "ecb-camellia-aesni-avx2",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(camellia)",
+	.cra_driver_name	= "cbc-camellia-aesni-avx2",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= __ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(camellia)",
+	.cra_driver_name	= "ctr-camellia-aesni-avx2",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_encrypt,
+			.geniv		= "chainiv",
+		},
+	},
+}, {
+	.cra_name		= "lrw(camellia)",
+	.cra_driver_name	= "lrw-camellia-aesni-avx2",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "xts(camellia)",
+	.cra_driver_name	= "xts-camellia-aesni-avx2",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+} };
+
+static int __init camellia_aesni_init(void)
+{
+	u64 xcr0;
+
+	if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+		pr_info("AVX2 or AES-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
+		pr_info("AVX2 detected but unusable.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+}
+
+static void __exit camellia_aesni_fini(void)
+{
+	crypto_unregister_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+}
+
+module_init(camellia_aesni_init);
+module_exit(camellia_aesni_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");

arch/x86/crypto/camellia_aesni_avx_glue.c

@@ -0,0 +1,578 @@
+/*
+ * Glue Code for x86_64/AVX/AES-NI assembler optimized version of Camellia
+ *
+ * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <crypto/ctr.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <asm/crypto/camellia.h>
+#include <asm/crypto/glue_helper.h>
+
+#define CAMELLIA_AESNI_PARALLEL_BLOCKS 16
+
+/* 16-way parallel cipher functions (avx/aes-ni) */
+asmlinkage void camellia_ecb_enc_16way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src);
+EXPORT_SYMBOL_GPL(camellia_ecb_enc_16way);
+
+asmlinkage void camellia_ecb_dec_16way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src);
+EXPORT_SYMBOL_GPL(camellia_ecb_dec_16way);
+
+asmlinkage void camellia_cbc_dec_16way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src);
+EXPORT_SYMBOL_GPL(camellia_cbc_dec_16way);
+
+asmlinkage void camellia_ctr_16way(struct camellia_ctx *ctx, u8 *dst,
+				   const u8 *src, le128 *iv);
+EXPORT_SYMBOL_GPL(camellia_ctr_16way);
+
+asmlinkage void camellia_xts_enc_16way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src, le128 *iv);
+EXPORT_SYMBOL_GPL(camellia_xts_enc_16way);
+
+asmlinkage void camellia_xts_dec_16way(struct camellia_ctx *ctx, u8 *dst,
+				       const u8 *src, le128 *iv);
+EXPORT_SYMBOL_GPL(camellia_xts_dec_16way);
+
+void camellia_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv)
+{
+	glue_xts_crypt_128bit_one(ctx, dst, src, iv,
+				  GLUE_FUNC_CAST(camellia_enc_blk));
+}
+EXPORT_SYMBOL_GPL(camellia_xts_enc);
+
+void camellia_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv)
+{
+	glue_xts_crypt_128bit_one(ctx, dst, src, iv,
+				  GLUE_FUNC_CAST(camellia_dec_blk));
+}
+EXPORT_SYMBOL_GPL(camellia_xts_dec);
+
+static const struct common_glue_ctx camellia_enc = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_enc_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_ctr = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_ctr_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_enc_xts = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc_16way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_enc) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_dec = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_ecb_dec_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_dec_cbc = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_cbc_dec_16way) }
+	}, {
+		.num_blocks = 2,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_decrypt_cbc_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_dec_blk) }
+	} }
+};
+
+static const struct common_glue_ctx camellia_dec_xts = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAMELLIA_AESNI_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec_16way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(camellia_xts_dec) }
+	} }
+};
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&camellia_enc, desc, dst, src, nbytes);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&camellia_dec, desc, dst, src, nbytes);
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(camellia_enc_blk), desc,
+				       dst, src, nbytes);
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_decrypt_128bit(&camellia_dec_cbc, desc, dst, src,
+				       nbytes);
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ctr_crypt_128bit(&camellia_ctr, desc, dst, src, nbytes);
+}
+
+static inline bool camellia_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+	return glue_fpu_begin(CAMELLIA_BLOCK_SIZE,
+			      CAMELLIA_AESNI_PARALLEL_BLOCKS, NULL, fpu_enabled,
+			      nbytes);
+}
+
+static inline void camellia_fpu_end(bool fpu_enabled)
+{
+	glue_fpu_end(fpu_enabled);
+}
+
+static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key,
+			   unsigned int key_len)
+{
+	return __camellia_setkey(crypto_tfm_ctx(tfm), in_key, key_len,
+				 &tfm->crt_flags);
+}
+
+struct crypt_priv {
+	struct camellia_ctx *ctx;
+	bool fpu_enabled;
+};
+
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+		camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+	}
+
+	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		camellia_enc_blk(ctx->ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = camellia_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+		camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
+	}
+
+	while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+		camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
+		srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
+		nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		camellia_dec_blk(ctx->ctx, srcdst, srcdst);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[CAMELLIA_AESNI_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->camellia_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	camellia_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[CAMELLIA_AESNI_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->camellia_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	camellia_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+
+	return glue_xts_crypt_128bit(&camellia_enc_xts, desc, dst, src, nbytes,
+				     XTS_TWEAK_CAST(camellia_enc_blk),
+				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct camellia_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+
+	return glue_xts_crypt_128bit(&camellia_dec_xts, desc, dst, src, nbytes,
+				     XTS_TWEAK_CAST(camellia_enc_blk),
+				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+}
+
+static struct crypto_alg cmll_algs[10] = { {
+	.cra_name		= "__ecb-camellia-aesni",
+	.cra_driver_name	= "__driver-ecb-camellia-aesni",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.setkey		= camellia_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__cbc-camellia-aesni",
+	.cra_driver_name	= "__driver-cbc-camellia-aesni",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.setkey		= camellia_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__ctr-camellia-aesni",
+	.cra_driver_name	= "__driver-ctr-camellia-aesni",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct camellia_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= camellia_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+}, {
+	.cra_name		= "__lrw-camellia-aesni",
+	.cra_driver_name	= "__driver-lrw-camellia-aesni",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_lrw_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_exit		= lrw_camellia_exit_tfm,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= lrw_camellia_setkey,
+			.encrypt	= lrw_encrypt,
+			.decrypt	= lrw_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__xts-camellia-aesni",
+	.cra_driver_name	= "__driver-xts-camellia-aesni",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct camellia_xts_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= xts_camellia_setkey,
+			.encrypt	= xts_encrypt,
+			.decrypt	= xts_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ecb(camellia)",
+	.cra_driver_name	= "ecb-camellia-aesni",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(camellia)",
+	.cra_driver_name	= "cbc-camellia-aesni",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= __ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(camellia)",
+	.cra_driver_name	= "ctr-camellia-aesni",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_encrypt,
+			.geniv		= "chainiv",
+		},
+	},
+}, {
+	.cra_name		= "lrw(camellia)",
+	.cra_driver_name	= "lrw-camellia-aesni",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE +
+					  CAMELLIA_BLOCK_SIZE,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "xts(camellia)",
+	.cra_driver_name	= "xts-camellia-aesni",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAMELLIA_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAMELLIA_MIN_KEY_SIZE * 2,
+			.max_keysize	= CAMELLIA_MAX_KEY_SIZE * 2,
+			.ivsize		= CAMELLIA_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+} };
+
+static int __init camellia_aesni_init(void)
+{
+	u64 xcr0;
+
+	if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) {
+		pr_info("AVX or AES-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
+		pr_info("AVX detected but unusable.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+}
+
+static void __exit camellia_aesni_fini(void)
+{
+	crypto_unregister_algs(cmll_algs, ARRAY_SIZE(cmll_algs));
+}
+
+module_init(camellia_aesni_init);
+module_exit(camellia_aesni_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");

arch/x86/crypto/cast5-avx-x86_64-asm_64.S

@@ -0,0 +1,546 @@
+/*
+ * Cast5 Cipher 16-way parallel algorithm (AVX/x86_64)
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * Copyright © 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/linkage.h>
+
+.file "cast5-avx-x86_64-asm_64.S"
+
+.extern cast_s1
+.extern cast_s2
+.extern cast_s3
+.extern cast_s4
+
+/* structure of crypto context */
+#define km	0
+#define kr	(16*4)
+#define rr	((16*4)+16)
+
+/* s-boxes */
+#define s1	cast_s1
+#define s2	cast_s2
+#define s3	cast_s3
+#define s4	cast_s4
+
+/**********************************************************************
+  16-way AVX cast5
+ **********************************************************************/
+#define CTX %rdi
+
+#define RL1 %xmm0
+#define RR1 %xmm1
+#define RL2 %xmm2
+#define RR2 %xmm3
+#define RL3 %xmm4
+#define RR3 %xmm5
+#define RL4 %xmm6
+#define RR4 %xmm7
+
+#define RX %xmm8
+
+#define RKM  %xmm9
+#define RKR  %xmm10
+#define RKRF %xmm11
+#define RKRR %xmm12
+
+#define R32  %xmm13
+#define R1ST %xmm14
+
+#define RTMP %xmm15
+
+#define RID1  %rbp
+#define RID1d %ebp
+#define RID2  %rsi
+#define RID2d %esi
+
+#define RGI1   %rdx
+#define RGI1bl %dl
+#define RGI1bh %dh
+#define RGI2   %rcx
+#define RGI2bl %cl
+#define RGI2bh %ch
+
+#define RGI3   %rax
+#define RGI3bl %al
+#define RGI3bh %ah
+#define RGI4   %rbx
+#define RGI4bl %bl
+#define RGI4bh %bh
+
+#define RFS1  %r8
+#define RFS1d %r8d
+#define RFS2  %r9
+#define RFS2d %r9d
+#define RFS3  %r10
+#define RFS3d %r10d
+
+
+#define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
+	movzbl		src ## bh,     RID1d;    \
+	movzbl		src ## bl,     RID2d;    \
+	shrq $16,	src;                     \
+	movl		s1(, RID1, 4), dst ## d; \
+	op1		s2(, RID2, 4), dst ## d; \
+	movzbl		src ## bh,     RID1d;    \
+	movzbl		src ## bl,     RID2d;    \
+	interleave_op(il_reg);			 \
+	op2		s3(, RID1, 4), dst ## d; \
+	op3		s4(, RID2, 4), dst ## d;
+
+#define dummy(d) /* do nothing */
+
+#define shr_next(reg) \
+	shrq $16,	reg;
+
+#define F_head(a, x, gi1, gi2, op0) \
+	op0	a,	RKM,  x;                 \
+	vpslld	RKRF,	x,    RTMP;              \
+	vpsrld	RKRR,	x,    x;                 \
+	vpor	RTMP,	x,    x;                 \
+	\
+	vmovq		x,    gi1;               \
+	vpextrq $1,	x,    gi2;
+
+#define F_tail(a, x, gi1, gi2, op1, op2, op3) \
+	lookup_32bit(##gi1, RFS1, op1, op2, op3, shr_next, ##gi1); \
+	lookup_32bit(##gi2, RFS3, op1, op2, op3, shr_next, ##gi2); \
+	\
+	lookup_32bit(##gi1, RFS2, op1, op2, op3, dummy, none);     \
+	shlq $32,	RFS2;                                      \
+	orq		RFS1, RFS2;                                \
+	lookup_32bit(##gi2, RFS1, op1, op2, op3, dummy, none);     \
+	shlq $32,	RFS1;                                      \
+	orq		RFS1, RFS3;                                \
+	\
+	vmovq		RFS2, x;                                   \
+	vpinsrq $1,	RFS3, x, x;
+
+#define F_2(a1, b1, a2, b2, op0, op1, op2, op3) \
+	F_head(b1, RX, RGI1, RGI2, op0);              \
+	F_head(b2, RX, RGI3, RGI4, op0);              \
+	\
+	F_tail(b1, RX, RGI1, RGI2, op1, op2, op3);    \
+	F_tail(b2, RTMP, RGI3, RGI4, op1, op2, op3);  \
+	\
+	vpxor		a1, RX,   a1;                 \
+	vpxor		a2, RTMP, a2;
+
+#define F1_2(a1, b1, a2, b2) \
+	F_2(a1, b1, a2, b2, vpaddd, xorl, subl, addl)
+#define F2_2(a1, b1, a2, b2) \
+	F_2(a1, b1, a2, b2, vpxor, subl, addl, xorl)
+#define F3_2(a1, b1, a2, b2) \
+	F_2(a1, b1, a2, b2, vpsubd, addl, xorl, subl)
+
+#define subround(a1, b1, a2, b2, f) \
+	F ## f ## _2(a1, b1, a2, b2);
+
+#define round(l, r, n, f) \
+	vbroadcastss 	(km+(4*n))(CTX), RKM;        \
+	vpand		R1ST,            RKR,  RKRF; \
+	vpsubq		RKRF,            R32,  RKRR; \
+	vpsrldq $1,	RKR,             RKR;        \
+	subround(l ## 1, r ## 1, l ## 2, r ## 2, f); \
+	subround(l ## 3, r ## 3, l ## 4, r ## 4, f);
+
+#define enc_preload_rkr() \
+	vbroadcastss	.L16_mask,                RKR;      \
+	/* add 16-bit rotation to key rotations (mod 32) */ \
+	vpxor		kr(CTX),                  RKR, RKR;
+
+#define dec_preload_rkr() \
+	vbroadcastss	.L16_mask,                RKR;      \
+	/* add 16-bit rotation to key rotations (mod 32) */ \
+	vpxor		kr(CTX),                  RKR, RKR; \
+	vpshufb		.Lbswap128_mask,          RKR, RKR;
+
+#define transpose_2x4(x0, x1, t0, t1) \
+	vpunpckldq		x1, x0, t0; \
+	vpunpckhdq		x1, x0, t1; \
+	\
+	vpunpcklqdq		t1, t0, x0; \
+	vpunpckhqdq		t1, t0, x1;
+
+#define inpack_blocks(x0, x1, t0, t1, rmask) \
+	vpshufb rmask, 	x0,	x0; \
+	vpshufb rmask, 	x1,	x1; \
+	\
+	transpose_2x4(x0, x1, t0, t1)
+
+#define outunpack_blocks(x0, x1, t0, t1, rmask) \
+	transpose_2x4(x0, x1, t0, t1) \
+	\
+	vpshufb rmask,	x0, x0;           \
+	vpshufb rmask,	x1, x1;
+
+.data
+
+.align 16
+.Lbswap_mask:
+	.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+.Lbswap128_mask:
+	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+.Lbswap_iv_mask:
+	.byte 7, 6, 5, 4, 3, 2, 1, 0, 7, 6, 5, 4, 3, 2, 1, 0
+.L16_mask:
+	.byte 16, 16, 16, 16
+.L32_mask:
+	.byte 32, 0, 0, 0
+.Lfirst_mask:
+	.byte 0x1f, 0, 0, 0
+
+.text
+
+.align 16
+__cast5_enc_blk16:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	RL1: blocks 1 and 2
+	 *	RR1: blocks 3 and 4
+	 *	RL2: blocks 5 and 6
+	 *	RR2: blocks 7 and 8
+	 *	RL3: blocks 9 and 10
+	 *	RR3: blocks 11 and 12
+	 *	RL4: blocks 13 and 14
+	 *	RR4: blocks 15 and 16
+	 * output:
+	 *	RL1: encrypted blocks 1 and 2
+	 *	RR1: encrypted blocks 3 and 4
+	 *	RL2: encrypted blocks 5 and 6
+	 *	RR2: encrypted blocks 7 and 8
+	 *	RL3: encrypted blocks 9 and 10
+	 *	RR3: encrypted blocks 11 and 12
+	 *	RL4: encrypted blocks 13 and 14
+	 *	RR4: encrypted blocks 15 and 16
+	 */
+
+	pushq %rbp;
+	pushq %rbx;
+
+	vmovdqa .Lbswap_mask, RKM;
+	vmovd .Lfirst_mask, R1ST;
+	vmovd .L32_mask, R32;
+	enc_preload_rkr();
+
+	inpack_blocks(RL1, RR1, RTMP, RX, RKM);
+	inpack_blocks(RL2, RR2, RTMP, RX, RKM);
+	inpack_blocks(RL3, RR3, RTMP, RX, RKM);
+	inpack_blocks(RL4, RR4, RTMP, RX, RKM);
+
+	round(RL, RR, 0, 1);
+	round(RR, RL, 1, 2);
+	round(RL, RR, 2, 3);
+	round(RR, RL, 3, 1);
+	round(RL, RR, 4, 2);
+	round(RR, RL, 5, 3);
+	round(RL, RR, 6, 1);
+	round(RR, RL, 7, 2);
+	round(RL, RR, 8, 3);
+	round(RR, RL, 9, 1);
+	round(RL, RR, 10, 2);
+	round(RR, RL, 11, 3);
+
+	movzbl rr(CTX), %eax;
+	testl %eax, %eax;
+	jnz .L__skip_enc;
+
+	round(RL, RR, 12, 1);
+	round(RR, RL, 13, 2);
+	round(RL, RR, 14, 3);
+	round(RR, RL, 15, 1);
+
+.L__skip_enc:
+	popq %rbx;
+	popq %rbp;
+
+	vmovdqa .Lbswap_mask, RKM;
+
+	outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
+	outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
+	outunpack_blocks(RR3, RL3, RTMP, RX, RKM);
+	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
+
+	ret;
+ENDPROC(__cast5_enc_blk16)
+
+.align 16
+__cast5_dec_blk16:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	RL1: encrypted blocks 1 and 2
+	 *	RR1: encrypted blocks 3 and 4
+	 *	RL2: encrypted blocks 5 and 6
+	 *	RR2: encrypted blocks 7 and 8
+	 *	RL3: encrypted blocks 9 and 10
+	 *	RR3: encrypted blocks 11 and 12
+	 *	RL4: encrypted blocks 13 and 14
+	 *	RR4: encrypted blocks 15 and 16
+	 * output:
+	 *	RL1: decrypted blocks 1 and 2
+	 *	RR1: decrypted blocks 3 and 4
+	 *	RL2: decrypted blocks 5 and 6
+	 *	RR2: decrypted blocks 7 and 8
+	 *	RL3: decrypted blocks 9 and 10
+	 *	RR3: decrypted blocks 11 and 12
+	 *	RL4: decrypted blocks 13 and 14
+	 *	RR4: decrypted blocks 15 and 16
+	 */
+
+	pushq %rbp;
+	pushq %rbx;
+
+	vmovdqa .Lbswap_mask, RKM;
+	vmovd .Lfirst_mask, R1ST;
+	vmovd .L32_mask, R32;
+	dec_preload_rkr();
+
+	inpack_blocks(RL1, RR1, RTMP, RX, RKM);
+	inpack_blocks(RL2, RR2, RTMP, RX, RKM);
+	inpack_blocks(RL3, RR3, RTMP, RX, RKM);
+	inpack_blocks(RL4, RR4, RTMP, RX, RKM);
+
+	movzbl rr(CTX), %eax;
+	testl %eax, %eax;
+	jnz .L__skip_dec;
+
+	round(RL, RR, 15, 1);
+	round(RR, RL, 14, 3);
+	round(RL, RR, 13, 2);
+	round(RR, RL, 12, 1);
+
+.L__dec_tail:
+	round(RL, RR, 11, 3);
+	round(RR, RL, 10, 2);
+	round(RL, RR, 9, 1);
+	round(RR, RL, 8, 3);
+	round(RL, RR, 7, 2);
+	round(RR, RL, 6, 1);
+	round(RL, RR, 5, 3);
+	round(RR, RL, 4, 2);
+	round(RL, RR, 3, 1);
+	round(RR, RL, 2, 3);
+	round(RL, RR, 1, 2);
+	round(RR, RL, 0, 1);
+
+	vmovdqa .Lbswap_mask, RKM;
+	popq %rbx;
+	popq %rbp;
+
+	outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
+	outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
+	outunpack_blocks(RR3, RL3, RTMP, RX, RKM);
+	outunpack_blocks(RR4, RL4, RTMP, RX, RKM);
+
+	ret;
+
+.L__skip_dec:
+	vpsrldq $4, RKR, RKR;
+	jmp .L__dec_tail;
+ENDPROC(__cast5_dec_blk16)
+
+ENTRY(cast5_ecb_enc_16way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	movq %rsi, %r11;
+
+	vmovdqu (0*4*4)(%rdx), RL1;
+	vmovdqu (1*4*4)(%rdx), RR1;
+	vmovdqu (2*4*4)(%rdx), RL2;
+	vmovdqu (3*4*4)(%rdx), RR2;
+	vmovdqu (4*4*4)(%rdx), RL3;
+	vmovdqu (5*4*4)(%rdx), RR3;
+	vmovdqu (6*4*4)(%rdx), RL4;
+	vmovdqu (7*4*4)(%rdx), RR4;
+
+	call __cast5_enc_blk16;
+
+	vmovdqu RR1, (0*4*4)(%r11);
+	vmovdqu RL1, (1*4*4)(%r11);
+	vmovdqu RR2, (2*4*4)(%r11);
+	vmovdqu RL2, (3*4*4)(%r11);
+	vmovdqu RR3, (4*4*4)(%r11);
+	vmovdqu RL3, (5*4*4)(%r11);
+	vmovdqu RR4, (6*4*4)(%r11);
+	vmovdqu RL4, (7*4*4)(%r11);
+
+	ret;
+ENDPROC(cast5_ecb_enc_16way)
+
+ENTRY(cast5_ecb_dec_16way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	movq %rsi, %r11;
+
+	vmovdqu (0*4*4)(%rdx), RL1;
+	vmovdqu (1*4*4)(%rdx), RR1;
+	vmovdqu (2*4*4)(%rdx), RL2;
+	vmovdqu (3*4*4)(%rdx), RR2;
+	vmovdqu (4*4*4)(%rdx), RL3;
+	vmovdqu (5*4*4)(%rdx), RR3;
+	vmovdqu (6*4*4)(%rdx), RL4;
+	vmovdqu (7*4*4)(%rdx), RR4;
+
+	call __cast5_dec_blk16;
+
+	vmovdqu RR1, (0*4*4)(%r11);
+	vmovdqu RL1, (1*4*4)(%r11);
+	vmovdqu RR2, (2*4*4)(%r11);
+	vmovdqu RL2, (3*4*4)(%r11);
+	vmovdqu RR3, (4*4*4)(%r11);
+	vmovdqu RL3, (5*4*4)(%r11);
+	vmovdqu RR4, (6*4*4)(%r11);
+	vmovdqu RL4, (7*4*4)(%r11);
+
+	ret;
+ENDPROC(cast5_ecb_dec_16way)
+
+ENTRY(cast5_cbc_dec_16way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	pushq %r12;
+
+	movq %rsi, %r11;
+	movq %rdx, %r12;
+
+	vmovdqu (0*16)(%rdx), RL1;
+	vmovdqu (1*16)(%rdx), RR1;
+	vmovdqu (2*16)(%rdx), RL2;
+	vmovdqu (3*16)(%rdx), RR2;
+	vmovdqu (4*16)(%rdx), RL3;
+	vmovdqu (5*16)(%rdx), RR3;
+	vmovdqu (6*16)(%rdx), RL4;
+	vmovdqu (7*16)(%rdx), RR4;
+
+	call __cast5_dec_blk16;
+
+	/* xor with src */
+	vmovq (%r12), RX;
+	vpshufd $0x4f, RX, RX;
+	vpxor RX, RR1, RR1;
+	vpxor 0*16+8(%r12), RL1, RL1;
+	vpxor 1*16+8(%r12), RR2, RR2;
+	vpxor 2*16+8(%r12), RL2, RL2;
+	vpxor 3*16+8(%r12), RR3, RR3;
+	vpxor 4*16+8(%r12), RL3, RL3;
+	vpxor 5*16+8(%r12), RR4, RR4;
+	vpxor 6*16+8(%r12), RL4, RL4;
+
+	vmovdqu RR1, (0*16)(%r11);
+	vmovdqu RL1, (1*16)(%r11);
+	vmovdqu RR2, (2*16)(%r11);
+	vmovdqu RL2, (3*16)(%r11);
+	vmovdqu RR3, (4*16)(%r11);
+	vmovdqu RL3, (5*16)(%r11);
+	vmovdqu RR4, (6*16)(%r11);
+	vmovdqu RL4, (7*16)(%r11);
+
+	popq %r12;
+
+	ret;
+ENDPROC(cast5_cbc_dec_16way)
+
+ENTRY(cast5_ctr_16way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: iv (big endian, 64bit)
+	 */
+
+	pushq %r12;
+
+	movq %rsi, %r11;
+	movq %rdx, %r12;
+
+	vpcmpeqd RTMP, RTMP, RTMP;
+	vpsrldq $8, RTMP, RTMP; /* low: -1, high: 0 */
+
+	vpcmpeqd RKR, RKR, RKR;
+	vpaddq RKR, RKR, RKR; /* low: -2, high: -2 */
+	vmovdqa .Lbswap_iv_mask, R1ST;
+	vmovdqa .Lbswap128_mask, RKM;
+
+	/* load IV and byteswap */
+	vmovq (%rcx), RX;
+	vpshufb R1ST, RX, RX;
+
+	/* construct IVs */
+	vpsubq RTMP, RX, RX;  /* le: IV1, IV0 */
+	vpshufb RKM, RX, RL1; /* be: IV0, IV1 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RR1; /* be: IV2, IV3 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RL2; /* be: IV4, IV5 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RR2; /* be: IV6, IV7 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RL3; /* be: IV8, IV9 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RR3; /* be: IV10, IV11 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RL4; /* be: IV12, IV13 */
+	vpsubq RKR, RX, RX;
+	vpshufb RKM, RX, RR4; /* be: IV14, IV15 */
+
+	/* store last IV */
+	vpsubq RTMP, RX, RX; /* le: IV16, IV14 */
+	vpshufb R1ST, RX, RX; /* be: IV16, IV16 */
+	vmovq RX, (%rcx);
+
+	call __cast5_enc_blk16;
+
+	/* dst = src ^ iv */
+	vpxor (0*16)(%r12), RR1, RR1;
+	vpxor (1*16)(%r12), RL1, RL1;
+	vpxor (2*16)(%r12), RR2, RR2;
+	vpxor (3*16)(%r12), RL2, RL2;
+	vpxor (4*16)(%r12), RR3, RR3;
+	vpxor (5*16)(%r12), RL3, RL3;
+	vpxor (6*16)(%r12), RR4, RR4;
+	vpxor (7*16)(%r12), RL4, RL4;
+	vmovdqu RR1, (0*16)(%r11);
+	vmovdqu RL1, (1*16)(%r11);
+	vmovdqu RR2, (2*16)(%r11);
+	vmovdqu RL2, (3*16)(%r11);
+	vmovdqu RR3, (4*16)(%r11);
+	vmovdqu RL3, (5*16)(%r11);
+	vmovdqu RR4, (6*16)(%r11);
+	vmovdqu RL4, (7*16)(%r11);
+
+	popq %r12;
+
+	ret;
+ENDPROC(cast5_ctr_16way)

arch/x86/crypto/cast5_avx_glue.c

@@ -0,0 +1,494 @@
+/*
+ * Glue Code for the AVX assembler implemention of the Cast5 Cipher
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <crypto/cast5.h>
+#include <crypto/cryptd.h>
+#include <crypto/ctr.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <asm/crypto/glue_helper.h>
+
+#define CAST5_PARALLEL_BLOCKS 16
+
+asmlinkage void cast5_ecb_enc_16way(struct cast5_ctx *ctx, u8 *dst,
+				    const u8 *src);
+asmlinkage void cast5_ecb_dec_16way(struct cast5_ctx *ctx, u8 *dst,
+				    const u8 *src);
+asmlinkage void cast5_cbc_dec_16way(struct cast5_ctx *ctx, u8 *dst,
+				    const u8 *src);
+asmlinkage void cast5_ctr_16way(struct cast5_ctx *ctx, u8 *dst, const u8 *src,
+				__be64 *iv);
+
+static inline bool cast5_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+	return glue_fpu_begin(CAST5_BLOCK_SIZE, CAST5_PARALLEL_BLOCKS,
+			      NULL, fpu_enabled, nbytes);
+}
+
+static inline void cast5_fpu_end(bool fpu_enabled)
+{
+	return glue_fpu_end(fpu_enabled);
+}
+
+static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
+		     bool enc)
+{
+	bool fpu_enabled = false;
+	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = CAST5_BLOCK_SIZE;
+	unsigned int nbytes;
+	void (*fn)(struct cast5_ctx *ctx, u8 *dst, const u8 *src);
+	int err;
+
+	fn = (enc) ? cast5_ecb_enc_16way : cast5_ecb_dec_16way;
+
+	err = blkcipher_walk_virt(desc, walk);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	while ((nbytes = walk->nbytes)) {
+		u8 *wsrc = walk->src.virt.addr;
+		u8 *wdst = walk->dst.virt.addr;
+
+		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+
+		/* Process multi-block batch */
+		if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
+			do {
+				fn(ctx, wdst, wsrc);
+
+				wsrc += bsize * CAST5_PARALLEL_BLOCKS;
+				wdst += bsize * CAST5_PARALLEL_BLOCKS;
+				nbytes -= bsize * CAST5_PARALLEL_BLOCKS;
+			} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
+
+			if (nbytes < bsize)
+				goto done;
+		}
+
+		fn = (enc) ? __cast5_encrypt : __cast5_decrypt;
+
+		/* Handle leftovers */
+		do {
+			fn(ctx, wdst, wsrc);
+
+			wsrc += bsize;
+			wdst += bsize;
+			nbytes -= bsize;
+		} while (nbytes >= bsize);
+
+done:
+		err = blkcipher_walk_done(desc, walk, nbytes);
+	}
+
+	cast5_fpu_end(fpu_enabled);
+	return err;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, true);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, false);
+}
+
+static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = CAST5_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 *iv = (u64 *)walk->iv;
+
+	do {
+		*dst = *src ^ *iv;
+		__cast5_encrypt(ctx, (u8 *)dst, (u8 *)dst);
+		iv = dst;
+
+		src += 1;
+		dst += 1;
+		nbytes -= bsize;
+	} while (nbytes >= bsize);
+
+	*(u64 *)walk->iv = *iv;
+	return nbytes;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_encrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = CAST5_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 last_iv;
+
+	/* Start of the last block. */
+	src += nbytes / bsize - 1;
+	dst += nbytes / bsize - 1;
+
+	last_iv = *src;
+
+	/* Process multi-block batch */
+	if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
+		do {
+			nbytes -= bsize * (CAST5_PARALLEL_BLOCKS - 1);
+			src -= CAST5_PARALLEL_BLOCKS - 1;
+			dst -= CAST5_PARALLEL_BLOCKS - 1;
+
+			cast5_cbc_dec_16way(ctx, (u8 *)dst, (u8 *)src);
+
+			nbytes -= bsize;
+			if (nbytes < bsize)
+				goto done;
+
+			*dst ^= *(src - 1);
+			src -= 1;
+			dst -= 1;
+		} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
+	}
+
+	/* Handle leftovers */
+	for (;;) {
+		__cast5_decrypt(ctx, (u8 *)dst, (u8 *)src);
+
+		nbytes -= bsize;
+		if (nbytes < bsize)
+			break;
+
+		*dst ^= *(src - 1);
+		src -= 1;
+		dst -= 1;
+	}
+
+done:
+	*dst ^= *(u64 *)walk->iv;
+	*(u64 *)walk->iv = last_iv;
+
+	return nbytes;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	bool fpu_enabled = false;
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	while ((nbytes = walk.nbytes)) {
+		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+		nbytes = __cbc_decrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	cast5_fpu_end(fpu_enabled);
+	return err;
+}
+
+static void ctr_crypt_final(struct blkcipher_desc *desc,
+			    struct blkcipher_walk *walk)
+{
+	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	u8 *ctrblk = walk->iv;
+	u8 keystream[CAST5_BLOCK_SIZE];
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	__cast5_encrypt(ctx, keystream, ctrblk);
+	crypto_xor(keystream, src, nbytes);
+	memcpy(dst, keystream, nbytes);
+
+	crypto_inc(ctrblk, CAST5_BLOCK_SIZE);
+}
+
+static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
+				struct blkcipher_walk *walk)
+{
+	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = CAST5_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+
+	/* Process multi-block batch */
+	if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
+		do {
+			cast5_ctr_16way(ctx, (u8 *)dst, (u8 *)src,
+					(__be64 *)walk->iv);
+
+			src += CAST5_PARALLEL_BLOCKS;
+			dst += CAST5_PARALLEL_BLOCKS;
+			nbytes -= bsize * CAST5_PARALLEL_BLOCKS;
+		} while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
+
+		if (nbytes < bsize)
+			goto done;
+	}
+
+	/* Handle leftovers */
+	do {
+		u64 ctrblk;
+
+		if (dst != src)
+			*dst = *src;
+
+		ctrblk = *(u64 *)walk->iv;
+		be64_add_cpu((__be64 *)walk->iv, 1);
+
+		__cast5_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
+		*dst ^= ctrblk;
+
+		src += 1;
+		dst += 1;
+		nbytes -= bsize;
+	} while (nbytes >= bsize);
+
+done:
+	return nbytes;
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	bool fpu_enabled = false;
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, CAST5_BLOCK_SIZE);
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
+		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+		nbytes = __ctr_crypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	cast5_fpu_end(fpu_enabled);
+
+	if (walk.nbytes) {
+		ctr_crypt_final(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+
+
+static struct crypto_alg cast5_algs[6] = { {
+	.cra_name		= "__ecb-cast5-avx",
+	.cra_driver_name	= "__driver-ecb-cast5-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAST5_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct cast5_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST5_MIN_KEY_SIZE,
+			.max_keysize	= CAST5_MAX_KEY_SIZE,
+			.setkey		= cast5_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__cbc-cast5-avx",
+	.cra_driver_name	= "__driver-cbc-cast5-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAST5_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct cast5_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST5_MIN_KEY_SIZE,
+			.max_keysize	= CAST5_MAX_KEY_SIZE,
+			.setkey		= cast5_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__ctr-cast5-avx",
+	.cra_driver_name	= "__driver-ctr-cast5-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct cast5_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST5_MIN_KEY_SIZE,
+			.max_keysize	= CAST5_MAX_KEY_SIZE,
+			.ivsize		= CAST5_BLOCK_SIZE,
+			.setkey		= cast5_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+}, {
+	.cra_name		= "ecb(cast5)",
+	.cra_driver_name	= "ecb-cast5-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAST5_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST5_MIN_KEY_SIZE,
+			.max_keysize	= CAST5_MAX_KEY_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(cast5)",
+	.cra_driver_name	= "cbc-cast5-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAST5_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST5_MIN_KEY_SIZE,
+			.max_keysize	= CAST5_MAX_KEY_SIZE,
+			.ivsize		= CAST5_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= __ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(cast5)",
+	.cra_driver_name	= "ctr-cast5-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST5_MIN_KEY_SIZE,
+			.max_keysize	= CAST5_MAX_KEY_SIZE,
+			.ivsize		= CAST5_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_encrypt,
+			.geniv		= "chainiv",
+		},
+	},
+} };
+
+static int __init cast5_init(void)
+{
+	u64 xcr0;
+
+	if (!cpu_has_avx || !cpu_has_osxsave) {
+		pr_info("AVX instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
+		pr_info("AVX detected but unusable.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(cast5_algs, ARRAY_SIZE(cast5_algs));
+}
+
+static void __exit cast5_exit(void)
+{
+	crypto_unregister_algs(cast5_algs, ARRAY_SIZE(cast5_algs));
+}
+
+module_init(cast5_init);
+module_exit(cast5_exit);
+
+MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("cast5");

arch/x86/crypto/cast6-avx-x86_64-asm_64.S

@@ -0,0 +1,472 @@
+/*
+ * Cast6 Cipher 8-way parallel algorithm (AVX/x86_64)
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/linkage.h>
+#include "glue_helper-asm-avx.S"
+
+.file "cast6-avx-x86_64-asm_64.S"
+
+.extern cast_s1
+.extern cast_s2
+.extern cast_s3
+.extern cast_s4
+
+/* structure of crypto context */
+#define km	0
+#define kr	(12*4*4)
+
+/* s-boxes */
+#define s1	cast_s1
+#define s2	cast_s2
+#define s3	cast_s3
+#define s4	cast_s4
+
+/**********************************************************************
+  8-way AVX cast6
+ **********************************************************************/
+#define CTX %rdi
+
+#define RA1 %xmm0
+#define RB1 %xmm1
+#define RC1 %xmm2
+#define RD1 %xmm3
+
+#define RA2 %xmm4
+#define RB2 %xmm5
+#define RC2 %xmm6
+#define RD2 %xmm7
+
+#define RX  %xmm8
+
+#define RKM  %xmm9
+#define RKR  %xmm10
+#define RKRF %xmm11
+#define RKRR %xmm12
+#define R32  %xmm13
+#define R1ST %xmm14
+
+#define RTMP %xmm15
+
+#define RID1  %rbp
+#define RID1d %ebp
+#define RID2  %rsi
+#define RID2d %esi
+
+#define RGI1   %rdx
+#define RGI1bl %dl
+#define RGI1bh %dh
+#define RGI2   %rcx
+#define RGI2bl %cl
+#define RGI2bh %ch
+
+#define RGI3   %rax
+#define RGI3bl %al
+#define RGI3bh %ah
+#define RGI4   %rbx
+#define RGI4bl %bl
+#define RGI4bh %bh
+
+#define RFS1  %r8
+#define RFS1d %r8d
+#define RFS2  %r9
+#define RFS2d %r9d
+#define RFS3  %r10
+#define RFS3d %r10d
+
+
+#define lookup_32bit(src, dst, op1, op2, op3, interleave_op, il_reg) \
+	movzbl		src ## bh,     RID1d;    \
+	movzbl		src ## bl,     RID2d;    \
+	shrq $16,	src;                     \
+	movl		s1(, RID1, 4), dst ## d; \
+	op1		s2(, RID2, 4), dst ## d; \
+	movzbl		src ## bh,     RID1d;    \
+	movzbl		src ## bl,     RID2d;    \
+	interleave_op(il_reg);			 \
+	op2		s3(, RID1, 4), dst ## d; \
+	op3		s4(, RID2, 4), dst ## d;
+
+#define dummy(d) /* do nothing */
+
+#define shr_next(reg) \
+	shrq $16,	reg;
+
+#define F_head(a, x, gi1, gi2, op0) \
+	op0	a,	RKM,  x;                 \
+	vpslld	RKRF,	x,    RTMP;              \
+	vpsrld	RKRR,	x,    x;                 \
+	vpor	RTMP,	x,    x;                 \
+	\
+	vmovq		x,    gi1;               \
+	vpextrq $1,	x,    gi2;
+
+#define F_tail(a, x, gi1, gi2, op1, op2, op3) \
+	lookup_32bit(##gi1, RFS1, op1, op2, op3, shr_next, ##gi1); \
+	lookup_32bit(##gi2, RFS3, op1, op2, op3, shr_next, ##gi2); \
+	\
+	lookup_32bit(##gi1, RFS2, op1, op2, op3, dummy, none);     \
+	shlq $32,	RFS2;                                      \
+	orq		RFS1, RFS2;                                \
+	lookup_32bit(##gi2, RFS1, op1, op2, op3, dummy, none);     \
+	shlq $32,	RFS1;                                      \
+	orq		RFS1, RFS3;                                \
+	\
+	vmovq		RFS2, x;                                   \
+	vpinsrq $1,	RFS3, x, x;
+
+#define F_2(a1, b1, a2, b2, op0, op1, op2, op3) \
+	F_head(b1, RX, RGI1, RGI2, op0);              \
+	F_head(b2, RX, RGI3, RGI4, op0);              \
+	\
+	F_tail(b1, RX, RGI1, RGI2, op1, op2, op3);    \
+	F_tail(b2, RTMP, RGI3, RGI4, op1, op2, op3);  \
+	\
+	vpxor		a1, RX,   a1;                 \
+	vpxor		a2, RTMP, a2;
+
+#define F1_2(a1, b1, a2, b2) \
+	F_2(a1, b1, a2, b2, vpaddd, xorl, subl, addl)
+#define F2_2(a1, b1, a2, b2) \
+	F_2(a1, b1, a2, b2, vpxor, subl, addl, xorl)
+#define F3_2(a1, b1, a2, b2) \
+	F_2(a1, b1, a2, b2, vpsubd, addl, xorl, subl)
+
+#define qop(in, out, f) \
+	F ## f ## _2(out ## 1, in ## 1, out ## 2, in ## 2);
+
+#define get_round_keys(nn) \
+	vbroadcastss	(km+(4*(nn)))(CTX), RKM;        \
+	vpand		R1ST,               RKR,  RKRF; \
+	vpsubq		RKRF,               R32,  RKRR; \
+	vpsrldq $1,	RKR,                RKR;
+
+#define Q(n) \
+	get_round_keys(4*n+0); \
+	qop(RD, RC, 1);        \
+	\
+	get_round_keys(4*n+1); \
+	qop(RC, RB, 2);        \
+	\
+	get_round_keys(4*n+2); \
+	qop(RB, RA, 3);        \
+	\
+	get_round_keys(4*n+3); \
+	qop(RA, RD, 1);
+
+#define QBAR(n) \
+	get_round_keys(4*n+3); \
+	qop(RA, RD, 1);        \
+	\
+	get_round_keys(4*n+2); \
+	qop(RB, RA, 3);        \
+	\
+	get_round_keys(4*n+1); \
+	qop(RC, RB, 2);        \
+	\
+	get_round_keys(4*n+0); \
+	qop(RD, RC, 1);
+
+#define shuffle(mask) \
+	vpshufb		mask,            RKR, RKR;
+
+#define preload_rkr(n, do_mask, mask) \
+	vbroadcastss	.L16_mask,                RKR;      \
+	/* add 16-bit rotation to key rotations (mod 32) */ \
+	vpxor		(kr+n*16)(CTX),           RKR, RKR; \
+	do_mask(mask);
+
+#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	vpunpckldq		x1, x0, t0; \
+	vpunpckhdq		x1, x0, t2; \
+	vpunpckldq		x3, x2, t1; \
+	vpunpckhdq		x3, x2, x3; \
+	\
+	vpunpcklqdq		t1, t0, x0; \
+	vpunpckhqdq		t1, t0, x1; \
+	vpunpcklqdq		x3, t2, x2; \
+	vpunpckhqdq		x3, t2, x3;
+
+#define inpack_blocks(x0, x1, x2, x3, t0, t1, t2, rmask) \
+	vpshufb rmask, x0,	x0; \
+	vpshufb rmask, x1,	x1; \
+	vpshufb rmask, x2,	x2; \
+	vpshufb rmask, x3,	x3; \
+	\
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define outunpack_blocks(x0, x1, x2, x3, t0, t1, t2, rmask) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	vpshufb rmask,		x0, x0;       \
+	vpshufb rmask,		x1, x1;       \
+	vpshufb rmask,		x2, x2;       \
+	vpshufb rmask,		x3, x3;
+
+.data
+
+.align 16
+.Lxts_gf128mul_and_shl1_mask:
+	.byte 0x87, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0
+.Lbswap_mask:
+	.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+.Lbswap128_mask:
+	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+.Lrkr_enc_Q_Q_QBAR_QBAR:
+	.byte 0, 1, 2, 3, 4, 5, 6, 7, 11, 10, 9, 8, 15, 14, 13, 12
+.Lrkr_enc_QBAR_QBAR_QBAR_QBAR:
+	.byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+.Lrkr_dec_Q_Q_Q_Q:
+	.byte 12, 13, 14, 15, 8, 9, 10, 11, 4, 5, 6, 7, 0, 1, 2, 3
+.Lrkr_dec_Q_Q_QBAR_QBAR:
+	.byte 12, 13, 14, 15, 8, 9, 10, 11, 7, 6, 5, 4, 3, 2, 1, 0
+.Lrkr_dec_QBAR_QBAR_QBAR_QBAR:
+	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
+.L16_mask:
+	.byte 16, 16, 16, 16
+.L32_mask:
+	.byte 32, 0, 0, 0
+.Lfirst_mask:
+	.byte 0x1f, 0, 0, 0
+
+.text
+
+.align 8
+__cast6_enc_blk8:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
+	 * output:
+	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
+	 */
+
+	pushq %rbp;
+	pushq %rbx;
+
+	vmovdqa .Lbswap_mask, RKM;
+	vmovd .Lfirst_mask, R1ST;
+	vmovd .L32_mask, R32;
+
+	inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+	inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+	preload_rkr(0, dummy, none);
+	Q(0);
+	Q(1);
+	Q(2);
+	Q(3);
+	preload_rkr(1, shuffle, .Lrkr_enc_Q_Q_QBAR_QBAR);
+	Q(4);
+	Q(5);
+	QBAR(6);
+	QBAR(7);
+	preload_rkr(2, shuffle, .Lrkr_enc_QBAR_QBAR_QBAR_QBAR);
+	QBAR(8);
+	QBAR(9);
+	QBAR(10);
+	QBAR(11);
+
+	popq %rbx;
+	popq %rbp;
+
+	vmovdqa .Lbswap_mask, RKM;
+
+	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+	ret;
+ENDPROC(__cast6_enc_blk8)
+
+.align 8
+__cast6_dec_blk8:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
+	 * output:
+	 *	RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks
+	 */
+
+	pushq %rbp;
+	pushq %rbx;
+
+	vmovdqa .Lbswap_mask, RKM;
+	vmovd .Lfirst_mask, R1ST;
+	vmovd .L32_mask, R32;
+
+	inpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+	inpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+	preload_rkr(2, shuffle, .Lrkr_dec_Q_Q_Q_Q);
+	Q(11);
+	Q(10);
+	Q(9);
+	Q(8);
+	preload_rkr(1, shuffle, .Lrkr_dec_Q_Q_QBAR_QBAR);
+	Q(7);
+	Q(6);
+	QBAR(5);
+	QBAR(4);
+	preload_rkr(0, shuffle, .Lrkr_dec_QBAR_QBAR_QBAR_QBAR);
+	QBAR(3);
+	QBAR(2);
+	QBAR(1);
+	QBAR(0);
+
+	popq %rbx;
+	popq %rbp;
+
+	vmovdqa .Lbswap_mask, RKM;
+	outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+	outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+	ret;
+ENDPROC(__cast6_dec_blk8)
+
+ENTRY(cast6_ecb_enc_8way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	movq %rsi, %r11;
+
+	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	call __cast6_enc_blk8;
+
+	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	ret;
+ENDPROC(cast6_ecb_enc_8way)
+
+ENTRY(cast6_ecb_dec_8way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	movq %rsi, %r11;
+
+	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	call __cast6_dec_blk8;
+
+	store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	ret;
+ENDPROC(cast6_ecb_dec_8way)
+
+ENTRY(cast6_cbc_dec_8way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	pushq %r12;
+
+	movq %rsi, %r11;
+	movq %rdx, %r12;
+
+	load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	call __cast6_dec_blk8;
+
+	store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	popq %r12;
+
+	ret;
+ENDPROC(cast6_cbc_dec_8way)
+
+ENTRY(cast6_ctr_8way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: iv (little endian, 128bit)
+	 */
+
+	pushq %r12;
+
+	movq %rsi, %r11;
+	movq %rdx, %r12;
+
+	load_ctr_8way(%rcx, .Lbswap128_mask, RA1, RB1, RC1, RD1, RA2, RB2, RC2,
+		      RD2, RX, RKR, RKM);
+
+	call __cast6_enc_blk8;
+
+	store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	popq %r12;
+
+	ret;
+ENDPROC(cast6_ctr_8way)
+
+ENTRY(cast6_xts_enc_8way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
+	 */
+
+	movq %rsi, %r11;
+
+	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
+	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
+		      RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask);
+
+	call __cast6_enc_blk8;
+
+	/* dst <= regs xor IVs(in dst) */
+	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	ret;
+ENDPROC(cast6_xts_enc_8way)
+
+ENTRY(cast6_xts_dec_8way)
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
+	 */
+
+	movq %rsi, %r11;
+
+	/* regs <= src, dst <= IVs, regs <= regs xor IVs */
+	load_xts_8way(%rcx, %rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2,
+		      RX, RKR, RKM, .Lxts_gf128mul_and_shl1_mask);
+
+	call __cast6_dec_blk8;
+
+	/* dst <= regs xor IVs(in dst) */
+	store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+
+	ret;
+ENDPROC(cast6_xts_dec_8way)

arch/x86/crypto/cast6_avx_glue.c

@@ -0,0 +1,614 @@
+/*
+ * Glue Code for the AVX assembler implemention of the Cast6 Cipher
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/ablk_helper.h>
+#include <crypto/algapi.h>
+#include <crypto/cast6.h>
+#include <crypto/cryptd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ctr.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <asm/crypto/glue_helper.h>
+
+#define CAST6_PARALLEL_BLOCKS 8
+
+asmlinkage void cast6_ecb_enc_8way(struct cast6_ctx *ctx, u8 *dst,
+				   const u8 *src);
+asmlinkage void cast6_ecb_dec_8way(struct cast6_ctx *ctx, u8 *dst,
+				   const u8 *src);
+
+asmlinkage void cast6_cbc_dec_8way(struct cast6_ctx *ctx, u8 *dst,
+				   const u8 *src);
+asmlinkage void cast6_ctr_8way(struct cast6_ctx *ctx, u8 *dst, const u8 *src,
+			       le128 *iv);
+
+asmlinkage void cast6_xts_enc_8way(struct cast6_ctx *ctx, u8 *dst,
+				   const u8 *src, le128 *iv);
+asmlinkage void cast6_xts_dec_8way(struct cast6_ctx *ctx, u8 *dst,
+				   const u8 *src, le128 *iv);
+
+static void cast6_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv)
+{
+	glue_xts_crypt_128bit_one(ctx, dst, src, iv,
+				  GLUE_FUNC_CAST(__cast6_encrypt));
+}
+
+static void cast6_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv)
+{
+	glue_xts_crypt_128bit_one(ctx, dst, src, iv,
+				  GLUE_FUNC_CAST(__cast6_decrypt));
+}
+
+static void cast6_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv)
+{
+	be128 ctrblk;
+
+	le128_to_be128(&ctrblk, iv);
+	le128_inc(iv);
+
+	__cast6_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
+	u128_xor(dst, src, (u128 *)&ctrblk);
+}
+
+static const struct common_glue_ctx cast6_enc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAST6_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(cast6_ecb_enc_8way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(__cast6_encrypt) }
+	} }
+};
+
+static const struct common_glue_ctx cast6_ctr = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAST6_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(cast6_ctr_8way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(cast6_crypt_ctr) }
+	} }
+};
+
+static const struct common_glue_ctx cast6_enc_xts = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAST6_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_enc_8way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_enc) }
+	} }
+};
+
+static const struct common_glue_ctx cast6_dec = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAST6_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(cast6_ecb_dec_8way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(__cast6_decrypt) }
+	} }
+};
+
+static const struct common_glue_ctx cast6_dec_cbc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAST6_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(cast6_cbc_dec_8way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__cast6_decrypt) }
+	} }
+};
+
+static const struct common_glue_ctx cast6_dec_xts = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = CAST6_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = CAST6_PARALLEL_BLOCKS,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_dec_8way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .xts = GLUE_XTS_FUNC_CAST(cast6_xts_dec) }
+	} }
+};
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&cast6_enc, desc, dst, src, nbytes);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&cast6_dec, desc, dst, src, nbytes);
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__cast6_encrypt), desc,
+				       dst, src, nbytes);
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_decrypt_128bit(&cast6_dec_cbc, desc, dst, src,
+				       nbytes);
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ctr_crypt_128bit(&cast6_ctr, desc, dst, src, nbytes);
+}
+
+static inline bool cast6_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+	return glue_fpu_begin(CAST6_BLOCK_SIZE, CAST6_PARALLEL_BLOCKS,
+			      NULL, fpu_enabled, nbytes);
+}
+
+static inline void cast6_fpu_end(bool fpu_enabled)
+{
+	glue_fpu_end(fpu_enabled);
+}
+
+struct crypt_priv {
+	struct cast6_ctx *ctx;
+	bool fpu_enabled;
+};
+
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = CAST6_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+		cast6_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		__cast6_encrypt(ctx->ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = CAST6_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+		cast6_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		__cast6_decrypt(ctx->ctx, srcdst, srcdst);
+}
+
+struct cast6_lrw_ctx {
+	struct lrw_table_ctx lrw_table;
+	struct cast6_ctx cast6_ctx;
+};
+
+static int lrw_cast6_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct cast6_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+	int err;
+
+	err = __cast6_setkey(&ctx->cast6_ctx, key, keylen - CAST6_BLOCK_SIZE,
+			     &tfm->crt_flags);
+	if (err)
+		return err;
+
+	return lrw_init_table(&ctx->lrw_table, key + keylen - CAST6_BLOCK_SIZE);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct cast6_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[CAST6_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->cast6_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	cast6_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct cast6_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[CAST6_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->cast6_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	cast6_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static void lrw_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct cast6_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	lrw_free_table(&ctx->lrw_table);
+}
+
+struct cast6_xts_ctx {
+	struct cast6_ctx tweak_ctx;
+	struct cast6_ctx crypt_ctx;
+};
+
+static int xts_cast6_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct cast6_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 *flags = &tfm->crt_flags;
+	int err;
+
+	/* key consists of keys of equal size concatenated, therefore
+	 * the length must be even
+	 */
+	if (keylen % 2) {
+		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+
+	/* first half of xts-key is for crypt */
+	err = __cast6_setkey(&ctx->crypt_ctx, key, keylen / 2, flags);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return __cast6_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
+			      flags);
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct cast6_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+
+	return glue_xts_crypt_128bit(&cast6_enc_xts, desc, dst, src, nbytes,
+				     XTS_TWEAK_CAST(__cast6_encrypt),
+				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct cast6_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+
+	return glue_xts_crypt_128bit(&cast6_dec_xts, desc, dst, src, nbytes,
+				     XTS_TWEAK_CAST(__cast6_encrypt),
+				     &ctx->tweak_ctx, &ctx->crypt_ctx);
+}
+
+static struct crypto_alg cast6_algs[10] = { {
+	.cra_name		= "__ecb-cast6-avx",
+	.cra_driver_name	= "__driver-ecb-cast6-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct cast6_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE,
+			.setkey		= cast6_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__cbc-cast6-avx",
+	.cra_driver_name	= "__driver-cbc-cast6-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct cast6_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE,
+			.setkey		= cast6_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__ctr-cast6-avx",
+	.cra_driver_name	= "__driver-ctr-cast6-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct cast6_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= cast6_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+}, {
+	.cra_name		= "__lrw-cast6-avx",
+	.cra_driver_name	= "__driver-lrw-cast6-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct cast6_lrw_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_exit		= lrw_exit_tfm,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE +
+					  CAST6_BLOCK_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE +
+					  CAST6_BLOCK_SIZE,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= lrw_cast6_setkey,
+			.encrypt	= lrw_encrypt,
+			.decrypt	= lrw_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__xts-cast6-avx",
+	.cra_driver_name	= "__driver-xts-cast6-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct cast6_xts_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE * 2,
+			.max_keysize	= CAST6_MAX_KEY_SIZE * 2,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= xts_cast6_setkey,
+			.encrypt	= xts_encrypt,
+			.decrypt	= xts_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ecb(cast6)",
+	.cra_driver_name	= "ecb-cast6-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(cast6)",
+	.cra_driver_name	= "cbc-cast6-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= __ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(cast6)",
+	.cra_driver_name	= "ctr-cast6-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_encrypt,
+			.geniv		= "chainiv",
+		},
+	},
+}, {
+	.cra_name		= "lrw(cast6)",
+	.cra_driver_name	= "lrw-cast6-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE +
+					  CAST6_BLOCK_SIZE,
+			.max_keysize	= CAST6_MAX_KEY_SIZE +
+					  CAST6_BLOCK_SIZE,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "xts(cast6)",
+	.cra_driver_name	= "xts-cast6-avx",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= CAST6_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= CAST6_MIN_KEY_SIZE * 2,
+			.max_keysize	= CAST6_MAX_KEY_SIZE * 2,
+			.ivsize		= CAST6_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+} };
+
+static int __init cast6_init(void)
+{
+	u64 xcr0;
+
+	if (!cpu_has_avx || !cpu_has_osxsave) {
+		pr_info("AVX instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
+		pr_info("AVX detected but unusable.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(cast6_algs, ARRAY_SIZE(cast6_algs));
+}
+
+static void __exit cast6_exit(void)
+{
+	crypto_unregister_algs(cast6_algs, ARRAY_SIZE(cast6_algs));
+}
+
+module_init(cast6_init);
+module_exit(cast6_exit);
+
+MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_CRYPTO("cast6");

arch/x86/crypto/crc32-pclmul_asm.S

@@ -0,0 +1,246 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please  visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
+ * calculation.
+ * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
+ * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
+ * at:
+ * http://www.intel.com/products/processor/manuals/
+ * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
+ * Volume 2B: Instruction Set Reference, N-Z
+ *
+ * Authors:   Gregory Prestas <Gregory_Prestas@us.xyratex.com>
+ *	      Alexander Boyko <Alexander_Boyko@xyratex.com>
+ */
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+
+.align 16
+/*
+ * [x4*128+32 mod P(x) << 32)]'  << 1   = 0x154442bd4
+ * #define CONSTANT_R1  0x154442bd4LL
+ *
+ * [(x4*128-32 mod P(x) << 32)]' << 1   = 0x1c6e41596
+ * #define CONSTANT_R2  0x1c6e41596LL
+ */
+.Lconstant_R2R1:
+	.octa 0x00000001c6e415960000000154442bd4
+/*
+ * [(x128+32 mod P(x) << 32)]'   << 1   = 0x1751997d0
+ * #define CONSTANT_R3  0x1751997d0LL
+ *
+ * [(x128-32 mod P(x) << 32)]'   << 1   = 0x0ccaa009e
+ * #define CONSTANT_R4  0x0ccaa009eLL
+ */
+.Lconstant_R4R3:
+	.octa 0x00000000ccaa009e00000001751997d0
+/*
+ * [(x64 mod P(x) << 32)]'       << 1   = 0x163cd6124
+ * #define CONSTANT_R5  0x163cd6124LL
+ */
+.Lconstant_R5:
+	.octa 0x00000000000000000000000163cd6124
+.Lconstant_mask32:
+	.octa 0x000000000000000000000000FFFFFFFF
+/*
+ * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
+ *
+ * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))` = 0x1F7011641LL
+ * #define CONSTANT_RU  0x1F7011641LL
+ */
+.Lconstant_RUpoly:
+	.octa 0x00000001F701164100000001DB710641
+
+#define CONSTANT %xmm0
+
+#ifdef __x86_64__
+#define BUF     %rdi
+#define LEN     %rsi
+#define CRC     %edx
+#else
+#define BUF     %eax
+#define LEN     %edx
+#define CRC     %ecx
+#endif
+
+
+
+.text
+/**
+ *      Calculate crc32
+ *      BUF - buffer (16 bytes aligned)
+ *      LEN - sizeof buffer (16 bytes aligned), LEN should be grater than 63
+ *      CRC - initial crc32
+ *      return %eax crc32
+ *      uint crc32_pclmul_le_16(unsigned char const *buffer,
+ *	                     size_t len, uint crc32)
+ */
+
+ENTRY(crc32_pclmul_le_16) /* buffer and buffer size are 16 bytes aligned */
+	movdqa  (BUF), %xmm1
+	movdqa  0x10(BUF), %xmm2
+	movdqa  0x20(BUF), %xmm3
+	movdqa  0x30(BUF), %xmm4
+	movd    CRC, CONSTANT
+	pxor    CONSTANT, %xmm1
+	sub     $0x40, LEN
+	add     $0x40, BUF
+#ifndef __x86_64__
+	/* This is for position independent code(-fPIC) support for 32bit */
+	call    delta
+delta:
+	pop     %ecx
+#endif
+	cmp     $0x40, LEN
+	jb      less_64
+
+#ifdef __x86_64__
+	movdqa .Lconstant_R2R1(%rip), CONSTANT
+#else
+	movdqa .Lconstant_R2R1 - delta(%ecx), CONSTANT
+#endif
+
+loop_64:/*  64 bytes Full cache line folding */
+	prefetchnta    0x40(BUF)
+	movdqa  %xmm1, %xmm5
+	movdqa  %xmm2, %xmm6
+	movdqa  %xmm3, %xmm7
+#ifdef __x86_64__
+	movdqa  %xmm4, %xmm8
+#endif
+	PCLMULQDQ 00, CONSTANT, %xmm1
+	PCLMULQDQ 00, CONSTANT, %xmm2
+	PCLMULQDQ 00, CONSTANT, %xmm3
+#ifdef __x86_64__
+	PCLMULQDQ 00, CONSTANT, %xmm4
+#endif
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	PCLMULQDQ 0x11, CONSTANT, %xmm6
+	PCLMULQDQ 0x11, CONSTANT, %xmm7
+#ifdef __x86_64__
+	PCLMULQDQ 0x11, CONSTANT, %xmm8
+#endif
+	pxor    %xmm5, %xmm1
+	pxor    %xmm6, %xmm2
+	pxor    %xmm7, %xmm3
+#ifdef __x86_64__
+	pxor    %xmm8, %xmm4
+#else
+	/* xmm8 unsupported for x32 */
+	movdqa  %xmm4, %xmm5
+	PCLMULQDQ 00, CONSTANT, %xmm4
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm4
+#endif
+
+	pxor    (BUF), %xmm1
+	pxor    0x10(BUF), %xmm2
+	pxor    0x20(BUF), %xmm3
+	pxor    0x30(BUF), %xmm4
+
+	sub     $0x40, LEN
+	add     $0x40, BUF
+	cmp     $0x40, LEN
+	jge     loop_64
+less_64:/*  Folding cache line into 128bit */
+#ifdef __x86_64__
+	movdqa  .Lconstant_R4R3(%rip), CONSTANT
+#else
+	movdqa  .Lconstant_R4R3 - delta(%ecx), CONSTANT
+#endif
+	prefetchnta     (BUF)
+
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    %xmm2, %xmm1
+
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    %xmm3, %xmm1
+
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    %xmm4, %xmm1
+
+	cmp     $0x10, LEN
+	jb      fold_64
+loop_16:/* Folding rest buffer into 128bit */
+	movdqa  %xmm1, %xmm5
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	PCLMULQDQ 0x11, CONSTANT, %xmm5
+	pxor    %xmm5, %xmm1
+	pxor    (BUF), %xmm1
+	sub     $0x10, LEN
+	add     $0x10, BUF
+	cmp     $0x10, LEN
+	jge     loop_16
+
+fold_64:
+	/* perform the last 64 bit fold, also adds 32 zeroes
+	 * to the input stream */
+	PCLMULQDQ 0x01, %xmm1, CONSTANT /* R4 * xmm1.low */
+	psrldq  $0x08, %xmm1
+	pxor    CONSTANT, %xmm1
+
+	/* final 32-bit fold */
+	movdqa  %xmm1, %xmm2
+#ifdef __x86_64__
+	movdqa  .Lconstant_R5(%rip), CONSTANT
+	movdqa  .Lconstant_mask32(%rip), %xmm3
+#else
+	movdqa  .Lconstant_R5 - delta(%ecx), CONSTANT
+	movdqa  .Lconstant_mask32 - delta(%ecx), %xmm3
+#endif
+	psrldq  $0x04, %xmm2
+	pand    %xmm3, %xmm1
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	pxor    %xmm2, %xmm1
+
+	/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
+#ifdef __x86_64__
+	movdqa  .Lconstant_RUpoly(%rip), CONSTANT
+#else
+	movdqa  .Lconstant_RUpoly - delta(%ecx), CONSTANT
+#endif
+	movdqa  %xmm1, %xmm2
+	pand    %xmm3, %xmm1
+	PCLMULQDQ 0x10, CONSTANT, %xmm1
+	pand    %xmm3, %xmm1
+	PCLMULQDQ 0x00, CONSTANT, %xmm1
+	pxor    %xmm2, %xmm1
+	PEXTRD  0x01, %xmm1, %eax
+
+	ret
+ENDPROC(crc32_pclmul_le_16)

arch/x86/crypto/crc32-pclmul_glue.c

@@ -0,0 +1,201 @@
+/* GPL HEADER START
+ *
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 only,
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License version 2 for more details (a copy is included
+ * in the LICENSE file that accompanied this code).
+ *
+ * You should have received a copy of the GNU General Public License
+ * version 2 along with this program; If not, see http://www.gnu.org/licenses
+ *
+ * Please  visit http://www.xyratex.com/contact if you need additional
+ * information or have any questions.
+ *
+ * GPL HEADER END
+ */
+
+/*
+ * Copyright 2012 Xyratex Technology Limited
+ *
+ * Wrappers for kernel crypto shash api to pclmulqdq crc32 imlementation.
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <linux/crc32.h>
+#include <crypto/internal/hash.h>
+
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+#include <asm/i387.h>
+
+#define CHKSUM_BLOCK_SIZE	1
+#define CHKSUM_DIGEST_SIZE	4
+
+#define PCLMUL_MIN_LEN		64L     /* minimum size of buffer
+					 * for crc32_pclmul_le_16 */
+#define SCALE_F			16L	/* size of xmm register */
+#define SCALE_F_MASK		(SCALE_F - 1)
+
+u32 crc32_pclmul_le_16(unsigned char const *buffer, size_t len, u32 crc32);
+
+static u32 __attribute__((pure))
+	crc32_pclmul_le(u32 crc, unsigned char const *p, size_t len)
+{
+	unsigned int iquotient;
+	unsigned int iremainder;
+	unsigned int prealign;
+
+	if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !irq_fpu_usable())
+		return crc32_le(crc, p, len);
+
+	if ((long)p & SCALE_F_MASK) {
+		/* align p to 16 byte */
+		prealign = SCALE_F - ((long)p & SCALE_F_MASK);
+
+		crc = crc32_le(crc, p, prealign);
+		len -= prealign;
+		p = (unsigned char *)(((unsigned long)p + SCALE_F_MASK) &
+				     ~SCALE_F_MASK);
+	}
+	iquotient = len & (~SCALE_F_MASK);
+	iremainder = len & SCALE_F_MASK;
+
+	kernel_fpu_begin();
+	crc = crc32_pclmul_le_16(p, iquotient, crc);
+	kernel_fpu_end();
+
+	if (iremainder)
+		crc = crc32_le(crc, p + iquotient, iremainder);
+
+	return crc;
+}
+
+static int crc32_pclmul_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = 0;
+
+	return 0;
+}
+
+static int crc32_pclmul_setkey(struct crypto_shash *hash, const u8 *key,
+			unsigned int keylen)
+{
+	u32 *mctx = crypto_shash_ctx(hash);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	*mctx = le32_to_cpup((__le32 *)key);
+	return 0;
+}
+
+static int crc32_pclmul_init(struct shash_desc *desc)
+{
+	u32 *mctx = crypto_shash_ctx(desc->tfm);
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = *mctx;
+
+	return 0;
+}
+
+static int crc32_pclmul_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = crc32_pclmul_le(*crcp, data, len);
+	return 0;
+}
+
+/* No final XOR 0xFFFFFFFF, like crc32_le */
+static int __crc32_pclmul_finup(u32 *crcp, const u8 *data, unsigned int len,
+				u8 *out)
+{
+	*(__le32 *)out = cpu_to_le32(crc32_pclmul_le(*crcp, data, len));
+	return 0;
+}
+
+static int crc32_pclmul_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return __crc32_pclmul_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32_pclmul_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*(__le32 *)out = cpu_to_le32p(crcp);
+	return 0;
+}
+
+static int crc32_pclmul_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
+{
+	return __crc32_pclmul_finup(crypto_shash_ctx(desc->tfm), data, len,
+				    out);
+}
+
+static struct shash_alg alg = {
+	.setkey		= crc32_pclmul_setkey,
+	.init		= crc32_pclmul_init,
+	.update		= crc32_pclmul_update,
+	.final		= crc32_pclmul_final,
+	.finup		= crc32_pclmul_finup,
+	.digest		= crc32_pclmul_digest,
+	.descsize	= sizeof(u32),
+	.digestsize	= CHKSUM_DIGEST_SIZE,
+	.base		= {
+			.cra_name		= "crc32",
+			.cra_driver_name	= "crc32-pclmul",
+			.cra_priority		= 200,
+			.cra_blocksize		= CHKSUM_BLOCK_SIZE,
+			.cra_ctxsize		= sizeof(u32),
+			.cra_module		= THIS_MODULE,
+			.cra_init		= crc32_pclmul_cra_init,
+	}
+};
+
+static const struct x86_cpu_id crc32pclmul_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, crc32pclmul_cpu_id);
+
+
+static int __init crc32_pclmul_mod_init(void)
+{
+
+	if (!x86_match_cpu(crc32pclmul_cpu_id)) {
+		pr_info("PCLMULQDQ-NI instructions are not detected.\n");
+		return -ENODEV;
+	}
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crc32_pclmul_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crc32_pclmul_mod_init);
+module_exit(crc32_pclmul_mod_fini);
+
+MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-pclmul");

arch/x86/crypto/crc32c-intel_glue.c

@@ -0,0 +1,284 @@
+/*
+ * Using hardware provided CRC32 instruction to accelerate the CRC32 disposal.
+ * CRC32C polynomial:0x1EDC6F41(BE)/0x82F63B78(LE)
+ * CRC32 is a new instruction in Intel SSE4.2, the reference can be found at:
+ * http://www.intel.com/products/processor/manuals/
+ * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
+ * Volume 2A: Instruction Set Reference, A-M
+ *
+ * Copyright (C) 2008 Intel Corporation
+ * Authors: Austin Zhang <austin_zhang@linux.intel.com>
+ *          Kent Liu <kent.liu@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <crypto/internal/hash.h>
+
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+#include <asm/i387.h>
+#include <asm/fpu-internal.h>
+
+#define CHKSUM_BLOCK_SIZE	1
+#define CHKSUM_DIGEST_SIZE	4
+
+#define SCALE_F	sizeof(unsigned long)
+
+#ifdef CONFIG_X86_64
+#define REX_PRE "0x48, "
+#else
+#define REX_PRE
+#endif
+
+#ifdef CONFIG_X86_64
+/*
+ * use carryless multiply version of crc32c when buffer
+ * size is >= 512 (when eager fpu is enabled) or
+ * >= 1024 (when eager fpu is disabled) to account
+ * for fpu state save/restore overhead.
+ */
+#define CRC32C_PCL_BREAKEVEN_EAGERFPU	512
+#define CRC32C_PCL_BREAKEVEN_NOEAGERFPU	1024
+
+asmlinkage unsigned int crc_pcl(const u8 *buffer, int len,
+				unsigned int crc_init);
+static int crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_EAGERFPU;
+#if defined(X86_FEATURE_EAGER_FPU)
+#define set_pcl_breakeven_point()					\
+do {									\
+	if (!use_eager_fpu())						\
+		crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU;	\
+} while (0)
+#else
+#define set_pcl_breakeven_point()					\
+	(crc32c_pcl_breakeven = CRC32C_PCL_BREAKEVEN_NOEAGERFPU)
+#endif
+#endif /* CONFIG_X86_64 */
+
+static u32 crc32c_intel_le_hw_byte(u32 crc, unsigned char const *data, size_t length)
+{
+	while (length--) {
+		__asm__ __volatile__(
+			".byte 0xf2, 0xf, 0x38, 0xf0, 0xf1"
+			:"=S"(crc)
+			:"0"(crc), "c"(*data)
+		);
+		data++;
+	}
+
+	return crc;
+}
+
+static u32 __pure crc32c_intel_le_hw(u32 crc, unsigned char const *p, size_t len)
+{
+	unsigned int iquotient = len / SCALE_F;
+	unsigned int iremainder = len % SCALE_F;
+	unsigned long *ptmp = (unsigned long *)p;
+
+	while (iquotient--) {
+		__asm__ __volatile__(
+			".byte 0xf2, " REX_PRE "0xf, 0x38, 0xf1, 0xf1;"
+			:"=S"(crc)
+			:"0"(crc), "c"(*ptmp)
+		);
+		ptmp++;
+	}
+
+	if (iremainder)
+		crc = crc32c_intel_le_hw_byte(crc, (unsigned char *)ptmp,
+				 iremainder);
+
+	return crc;
+}
+
+/*
+ * Setting the seed allows arbitrary accumulators and flexible XOR policy
+ * If your algorithm starts with ~0, then XOR with ~0 before you set
+ * the seed.
+ */
+static int crc32c_intel_setkey(struct crypto_shash *hash, const u8 *key,
+			unsigned int keylen)
+{
+	u32 *mctx = crypto_shash_ctx(hash);
+
+	if (keylen != sizeof(u32)) {
+		crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+	*mctx = le32_to_cpup((__le32 *)key);
+	return 0;
+}
+
+static int crc32c_intel_init(struct shash_desc *desc)
+{
+	u32 *mctx = crypto_shash_ctx(desc->tfm);
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = *mctx;
+
+	return 0;
+}
+
+static int crc32c_intel_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*crcp = crc32c_intel_le_hw(*crcp, data, len);
+	return 0;
+}
+
+static int __crc32c_intel_finup(u32 *crcp, const u8 *data, unsigned int len,
+				u8 *out)
+{
+	*(__le32 *)out = ~cpu_to_le32(crc32c_intel_le_hw(*crcp, data, len));
+	return 0;
+}
+
+static int crc32c_intel_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return __crc32c_intel_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32c_intel_final(struct shash_desc *desc, u8 *out)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	*(__le32 *)out = ~cpu_to_le32p(crcp);
+	return 0;
+}
+
+static int crc32c_intel_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
+{
+	return __crc32c_intel_finup(crypto_shash_ctx(desc->tfm), data, len,
+				    out);
+}
+
+static int crc32c_intel_cra_init(struct crypto_tfm *tfm)
+{
+	u32 *key = crypto_tfm_ctx(tfm);
+
+	*key = ~0;
+
+	return 0;
+}
+
+#ifdef CONFIG_X86_64
+static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
+			       unsigned int len)
+{
+	u32 *crcp = shash_desc_ctx(desc);
+
+	/*
+	 * use faster PCL version if datasize is large enough to
+	 * overcome kernel fpu state save/restore overhead
+	 */
+	if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) {
+		kernel_fpu_begin();
+		*crcp = crc_pcl(data, len, *crcp);
+		kernel_fpu_end();
+	} else
+		*crcp = crc32c_intel_le_hw(*crcp, data, len);
+	return 0;
+}
+
+static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len,
+				u8 *out)
+{
+	if (len >= crc32c_pcl_breakeven && irq_fpu_usable()) {
+		kernel_fpu_begin();
+		*(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp));
+		kernel_fpu_end();
+	} else
+		*(__le32 *)out =
+			~cpu_to_le32(crc32c_intel_le_hw(*crcp, data, len));
+	return 0;
+}
+
+static int crc32c_pcl_intel_finup(struct shash_desc *desc, const u8 *data,
+			      unsigned int len, u8 *out)
+{
+	return __crc32c_pcl_intel_finup(shash_desc_ctx(desc), data, len, out);
+}
+
+static int crc32c_pcl_intel_digest(struct shash_desc *desc, const u8 *data,
+			       unsigned int len, u8 *out)
+{
+	return __crc32c_pcl_intel_finup(crypto_shash_ctx(desc->tfm), data, len,
+				    out);
+}
+#endif /* CONFIG_X86_64 */
+
+static struct shash_alg alg = {
+	.setkey			=	crc32c_intel_setkey,
+	.init			=	crc32c_intel_init,
+	.update			=	crc32c_intel_update,
+	.final			=	crc32c_intel_final,
+	.finup			=	crc32c_intel_finup,
+	.digest			=	crc32c_intel_digest,
+	.descsize		=	sizeof(u32),
+	.digestsize		=	CHKSUM_DIGEST_SIZE,
+	.base			=	{
+		.cra_name		=	"crc32c",
+		.cra_driver_name	=	"crc32c-intel",
+		.cra_priority		=	200,
+		.cra_blocksize		=	CHKSUM_BLOCK_SIZE,
+		.cra_ctxsize		=	sizeof(u32),
+		.cra_module		=	THIS_MODULE,
+		.cra_init		=	crc32c_intel_cra_init,
+	}
+};
+
+static const struct x86_cpu_id crc32c_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_XMM4_2),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, crc32c_cpu_id);
+
+static int __init crc32c_intel_mod_init(void)
+{
+	if (!x86_match_cpu(crc32c_cpu_id))
+		return -ENODEV;
+#ifdef CONFIG_X86_64
+	if (cpu_has_pclmulqdq) {
+		alg.update = crc32c_pcl_intel_update;
+		alg.finup = crc32c_pcl_intel_finup;
+		alg.digest = crc32c_pcl_intel_digest;
+		set_pcl_breakeven_point();
+	}
+#endif
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crc32c_intel_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crc32c_intel_mod_init);
+module_exit(crc32c_intel_mod_fini);
+
+MODULE_AUTHOR("Austin Zhang <austin.zhang@intel.com>, Kent Liu <kent.liu@intel.com>");
+MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware.");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-intel");

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

@@ -0,0 +1,463 @@
+/*
+ * Implement fast CRC32C with PCLMULQDQ instructions. (x86_64)
+ *
+ * The white papers on CRC32C calculations with PCLMULQDQ instruction can be
+ * downloaded from:
+ * http://www.intel.com/content/dam/www/public/us/en/documents/white-papers/crc-iscsi-polynomial-crc32-instruction-paper.pdf
+ * http://www.intel.com/content/dam/www/public/us/en/documents/white-papers/fast-crc-computation-paper.pdf
+ *
+ * Copyright (C) 2012 Intel Corporation.
+ *
+ * Authors:
+ *	Wajdi Feghali <wajdi.k.feghali@intel.com>
+ *	James Guilford <james.guilford@intel.com>
+ *	David Cote <david.m.cote@intel.com>
+ *	Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <asm/inst.h>
+#include <linux/linkage.h>
+
+## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
+
+.macro LABEL prefix n
+\prefix\n\():
+.endm
+
+.macro JMPTBL_ENTRY i
+.word crc_\i - crc_array
+.endm
+
+.macro JNC_LESS_THAN j
+	jnc less_than_\j
+.endm
+
+# Define threshold where buffers are considered "small" and routed to more
+# efficient "by-1" code. This "by-1" code only handles up to 255 bytes, so
+# SMALL_SIZE can be no larger than 255.
+
+#define SMALL_SIZE 200
+
+.if (SMALL_SIZE > 255)
+.error "SMALL_ SIZE must be < 256"
+.endif
+
+# unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init);
+
+.text
+ENTRY(crc_pcl)
+#define    bufp		%rdi
+#define    bufp_dw	%edi
+#define    bufp_w	%di
+#define    bufp_b	%dil
+#define    bufptmp	%rcx
+#define    block_0	%rcx
+#define    block_1	%rdx
+#define    block_2	%r11
+#define    len		%rsi
+#define    len_dw	%esi
+#define    len_w	%si
+#define    len_b	%sil
+#define    crc_init_arg %rdx
+#define    tmp		%rbx
+#define    crc_init	%r8
+#define    crc_init_dw	%r8d
+#define    crc1		%r9
+#define    crc2		%r10
+
+	pushq   %rbx
+	pushq   %rdi
+	pushq   %rsi
+
+	## Move crc_init for Linux to a different
+	mov     crc_init_arg, crc_init
+
+	################################################################
+	## 1) ALIGN:
+	################################################################
+
+	mov     bufp, bufptmp		# rdi = *buf
+	neg     bufp
+	and     $7, bufp		# calculate the unalignment amount of
+					# the address
+	je      proc_block		# Skip if aligned
+
+	## If len is less than 8 and we're unaligned, we need to jump
+	## to special code to avoid reading beyond the end of the buffer
+	cmp     $8, len
+	jae     do_align
+	# less_than_8 expects length in upper 3 bits of len_dw
+	# less_than_8_post_shl1 expects length = carryflag * 8 + len_dw[31:30]
+	shl     $32-3+1, len_dw
+	jmp     less_than_8_post_shl1
+
+do_align:
+	#### Calculate CRC of unaligned bytes of the buffer (if any)
+	movq    (bufptmp), tmp		# load a quadward from the buffer
+	add     bufp, bufptmp		# align buffer pointer for quadword
+					# processing
+	sub     bufp, len		# update buffer length
+align_loop:
+	crc32b  %bl, crc_init_dw 	# compute crc32 of 1-byte
+	shr     $8, tmp			# get next byte
+	dec     bufp
+	jne     align_loop
+
+proc_block:
+
+	################################################################
+	## 2) PROCESS  BLOCKS:
+	################################################################
+
+	## compute num of bytes to be processed
+	movq    len, tmp		# save num bytes in tmp
+
+	cmpq    $128*24, len
+	jae     full_block
+
+continue_block:
+	cmpq    $SMALL_SIZE, len
+	jb      small
+
+	## len < 128*24
+	movq    $2731, %rax		# 2731 = ceil(2^16 / 24)
+	mul     len_dw
+	shrq    $16, %rax
+
+	## eax contains floor(bytes / 24) = num 24-byte chunks to do
+
+	## process rax 24-byte chunks (128 >= rax >= 0)
+
+	## compute end address of each block
+	## block 0 (base addr + RAX * 8)
+	## block 1 (base addr + RAX * 16)
+	## block 2 (base addr + RAX * 24)
+	lea     (bufptmp, %rax, 8), block_0
+	lea     (block_0, %rax, 8), block_1
+	lea     (block_1, %rax, 8), block_2
+
+	xor     crc1, crc1
+	xor     crc2, crc2
+
+	## branch into array
+	lea	jump_table(%rip), bufp
+	movzxw  (bufp, %rax, 2), len
+	offset=crc_array-jump_table
+	lea     offset(bufp, len, 1), bufp
+	jmp     *bufp
+
+	################################################################
+	## 2a) PROCESS FULL BLOCKS:
+	################################################################
+full_block:
+	movq    $128,%rax
+	lea     128*8*2(block_0), block_1
+	lea     128*8*3(block_0), block_2
+	add     $128*8*1, block_0
+
+	xor     crc1,crc1
+	xor     crc2,crc2
+
+	# Fall thruogh into top of crc array (crc_128)
+
+	################################################################
+	## 3) CRC Array:
+	################################################################
+
+crc_array:
+	i=128
+.rept 128-1
+.altmacro
+LABEL crc_ %i
+.noaltmacro
+	crc32q   -i*8(block_0), crc_init
+	crc32q   -i*8(block_1), crc1
+	crc32q   -i*8(block_2), crc2
+	i=(i-1)
+.endr
+
+.altmacro
+LABEL crc_ %i
+.noaltmacro
+	crc32q   -i*8(block_0), crc_init
+	crc32q   -i*8(block_1), crc1
+# SKIP  crc32  -i*8(block_2), crc2 ; Don't do this one yet
+
+	mov     block_2, block_0
+
+	################################################################
+	## 4) Combine three results:
+	################################################################
+
+	lea	(K_table-8)(%rip), bufp		# first entry is for idx 1
+	shlq    $3, %rax			# rax *= 8
+	pmovzxdq (bufp,%rax), %xmm0		# 2 consts: K1:K2
+	leal	(%eax,%eax,2), %eax		# rax *= 3 (total *24)
+	subq    %rax, tmp			# tmp -= rax*24
+
+	movq    crc_init, %xmm1			# CRC for block 1
+	PCLMULQDQ 0x00,%xmm0,%xmm1		# Multiply by K2
+
+	movq    crc1, %xmm2			# CRC for block 2
+	PCLMULQDQ 0x10, %xmm0, %xmm2		# Multiply by K1
+
+	pxor    %xmm2,%xmm1
+	movq    %xmm1, %rax
+	xor     -i*8(block_2), %rax
+	mov     crc2, crc_init
+	crc32   %rax, crc_init
+
+	################################################################
+	## 5) Check for end:
+	################################################################
+
+LABEL crc_ 0
+	mov     tmp, len
+	cmp     $128*24, tmp
+	jae     full_block
+	cmp     $24, tmp
+	jae     continue_block
+
+less_than_24:
+	shl     $32-4, len_dw			# less_than_16 expects length
+						# in upper 4 bits of len_dw
+	jnc     less_than_16
+	crc32q  (bufptmp), crc_init
+	crc32q  8(bufptmp), crc_init
+	jz      do_return
+	add     $16, bufptmp
+	# len is less than 8 if we got here
+	# less_than_8 expects length in upper 3 bits of len_dw
+	# less_than_8_post_shl1 expects length = carryflag * 8 + len_dw[31:30]
+	shl     $2, len_dw
+	jmp     less_than_8_post_shl1
+
+	#######################################################################
+	## 6) LESS THAN 256-bytes REMAIN AT THIS POINT (8-bits of len are full)
+	#######################################################################
+small:
+	shl $32-8, len_dw		# Prepare len_dw for less_than_256
+	j=256
+.rept 5					# j = {256, 128, 64, 32, 16}
+.altmacro
+LABEL less_than_ %j			# less_than_j: Length should be in
+					# upper lg(j) bits of len_dw
+	j=(j/2)
+	shl     $1, len_dw		# Get next MSB
+	JNC_LESS_THAN %j
+.noaltmacro
+	i=0
+.rept (j/8)
+	crc32q  i(bufptmp), crc_init	# Compute crc32 of 8-byte data
+	i=i+8
+.endr
+	jz      do_return		# Return if remaining length is zero
+	add     $j, bufptmp		# Advance buf
+.endr
+
+less_than_8:				# Length should be stored in
+					# upper 3 bits of len_dw
+	shl     $1, len_dw
+less_than_8_post_shl1:
+	jnc     less_than_4
+	crc32l  (bufptmp), crc_init_dw	# CRC of 4 bytes
+	jz      do_return		# return if remaining data is zero
+	add     $4, bufptmp
+less_than_4:				# Length should be stored in
+					# upper 2 bits of len_dw
+	shl     $1, len_dw
+	jnc     less_than_2
+	crc32w  (bufptmp), crc_init_dw	# CRC of 2 bytes
+	jz      do_return		# return if remaining data is zero
+	add     $2, bufptmp
+less_than_2:				# Length should be stored in the MSB
+					# of len_dw
+	shl     $1, len_dw
+	jnc     less_than_1
+	crc32b  (bufptmp), crc_init_dw	# CRC of 1 byte
+less_than_1:				# Length should be zero
+do_return:
+	movq    crc_init, %rax
+	popq    %rsi
+	popq    %rdi
+	popq    %rbx
+        ret
+
+        ################################################################
+        ## jump table        Table is 129 entries x 2 bytes each
+        ################################################################
+.align 4
+jump_table:
+	i=0
+.rept 129
+.altmacro
+JMPTBL_ENTRY %i
+.noaltmacro
+	i=i+1
+.endr
+
+ENDPROC(crc_pcl)
+
+	################################################################
+	## PCLMULQDQ tables
+	## Table is 128 entries x 2 words (8 bytes) each
+	################################################################
+.section	.rotata, "a", %progbits
+.align 8
+K_table:
+	.long 0x493c7d27, 0x00000001
+	.long 0xba4fc28e, 0x493c7d27
+	.long 0xddc0152b, 0xf20c0dfe
+	.long 0x9e4addf8, 0xba4fc28e
+	.long 0x39d3b296, 0x3da6d0cb
+	.long 0x0715ce53, 0xddc0152b
+	.long 0x47db8317, 0x1c291d04
+	.long 0x0d3b6092, 0x9e4addf8
+	.long 0xc96cfdc0, 0x740eef02
+	.long 0x878a92a7, 0x39d3b296
+	.long 0xdaece73e, 0x083a6eec
+	.long 0xab7aff2a, 0x0715ce53
+	.long 0x2162d385, 0xc49f4f67
+	.long 0x83348832, 0x47db8317
+	.long 0x299847d5, 0x2ad91c30
+	.long 0xb9e02b86, 0x0d3b6092
+	.long 0x18b33a4e, 0x6992cea2
+	.long 0xb6dd949b, 0xc96cfdc0
+	.long 0x78d9ccb7, 0x7e908048
+	.long 0xbac2fd7b, 0x878a92a7
+	.long 0xa60ce07b, 0x1b3d8f29
+	.long 0xce7f39f4, 0xdaece73e
+	.long 0x61d82e56, 0xf1d0f55e
+	.long 0xd270f1a2, 0xab7aff2a
+	.long 0xc619809d, 0xa87ab8a8
+	.long 0x2b3cac5d, 0x2162d385
+	.long 0x65863b64, 0x8462d800
+	.long 0x1b03397f, 0x83348832
+	.long 0xebb883bd, 0x71d111a8
+	.long 0xb3e32c28, 0x299847d5
+	.long 0x064f7f26, 0xffd852c6
+	.long 0xdd7e3b0c, 0xb9e02b86
+	.long 0xf285651c, 0xdcb17aa4
+	.long 0x10746f3c, 0x18b33a4e
+	.long 0xc7a68855, 0xf37c5aee
+	.long 0x271d9844, 0xb6dd949b
+	.long 0x8e766a0c, 0x6051d5a2
+	.long 0x93a5f730, 0x78d9ccb7
+	.long 0x6cb08e5c, 0x18b0d4ff
+	.long 0x6b749fb2, 0xbac2fd7b
+	.long 0x1393e203, 0x21f3d99c
+	.long 0xcec3662e, 0xa60ce07b
+	.long 0x96c515bb, 0x8f158014
+	.long 0xe6fc4e6a, 0xce7f39f4
+	.long 0x8227bb8a, 0xa00457f7
+	.long 0xb0cd4768, 0x61d82e56
+	.long 0x39c7ff35, 0x8d6d2c43
+	.long 0xd7a4825c, 0xd270f1a2
+	.long 0x0ab3844b, 0x00ac29cf
+	.long 0x0167d312, 0xc619809d
+	.long 0xf6076544, 0xe9adf796
+	.long 0x26f6a60a, 0x2b3cac5d
+	.long 0xa741c1bf, 0x96638b34
+	.long 0x98d8d9cb, 0x65863b64
+	.long 0x49c3cc9c, 0xe0e9f351
+	.long 0x68bce87a, 0x1b03397f
+	.long 0x57a3d037, 0x9af01f2d
+	.long 0x6956fc3b, 0xebb883bd
+	.long 0x42d98888, 0x2cff42cf
+	.long 0x3771e98f, 0xb3e32c28
+	.long 0xb42ae3d9, 0x88f25a3a
+	.long 0x2178513a, 0x064f7f26
+	.long 0xe0ac139e, 0x4e36f0b0
+	.long 0x170076fa, 0xdd7e3b0c
+	.long 0x444dd413, 0xbd6f81f8
+	.long 0x6f345e45, 0xf285651c
+	.long 0x41d17b64, 0x91c9bd4b
+	.long 0xff0dba97, 0x10746f3c
+	.long 0xa2b73df1, 0x885f087b
+	.long 0xf872e54c, 0xc7a68855
+	.long 0x1e41e9fc, 0x4c144932
+	.long 0x86d8e4d2, 0x271d9844
+	.long 0x651bd98b, 0x52148f02
+	.long 0x5bb8f1bc, 0x8e766a0c
+	.long 0xa90fd27a, 0xa3c6f37a
+	.long 0xb3af077a, 0x93a5f730
+	.long 0x4984d782, 0xd7c0557f
+	.long 0xca6ef3ac, 0x6cb08e5c
+	.long 0x234e0b26, 0x63ded06a
+	.long 0xdd66cbbb, 0x6b749fb2
+	.long 0x4597456a, 0x4d56973c
+	.long 0xe9e28eb4, 0x1393e203
+	.long 0x7b3ff57a, 0x9669c9df
+	.long 0xc9c8b782, 0xcec3662e
+	.long 0x3f70cc6f, 0xe417f38a
+	.long 0x93e106a4, 0x96c515bb
+	.long 0x62ec6c6d, 0x4b9e0f71
+	.long 0xd813b325, 0xe6fc4e6a
+	.long 0x0df04680, 0xd104b8fc
+	.long 0x2342001e, 0x8227bb8a
+	.long 0x0a2a8d7e, 0x5b397730
+	.long 0x6d9a4957, 0xb0cd4768
+	.long 0xe8b6368b, 0xe78eb416
+	.long 0xd2c3ed1a, 0x39c7ff35
+	.long 0x995a5724, 0x61ff0e01
+	.long 0x9ef68d35, 0xd7a4825c
+	.long 0x0c139b31, 0x8d96551c
+	.long 0xf2271e60, 0x0ab3844b
+	.long 0x0b0bf8ca, 0x0bf80dd2
+	.long 0x2664fd8b, 0x0167d312
+	.long 0xed64812d, 0x8821abed
+	.long 0x02ee03b2, 0xf6076544
+	.long 0x8604ae0f, 0x6a45d2b2
+	.long 0x363bd6b3, 0x26f6a60a
+	.long 0x135c83fd, 0xd8d26619
+	.long 0x5fabe670, 0xa741c1bf
+	.long 0x35ec3279, 0xde87806c
+	.long 0x00bcf5f6, 0x98d8d9cb
+	.long 0x8ae00689, 0x14338754
+	.long 0x17f27698, 0x49c3cc9c
+	.long 0x58ca5f00, 0x5bd2011f
+	.long 0xaa7c7ad5, 0x68bce87a
+	.long 0xb5cfca28, 0xdd07448e
+	.long 0xded288f8, 0x57a3d037
+	.long 0x59f229bc, 0xdde8f5b9
+	.long 0x6d390dec, 0x6956fc3b
+	.long 0x37170390, 0xa3e3e02c
+	.long 0x6353c1cc, 0x42d98888
+	.long 0xc4584f5c, 0xd73c7bea
+	.long 0xf48642e9, 0x3771e98f
+	.long 0x531377e2, 0x80ff0093
+	.long 0xdd35bc8d, 0xb42ae3d9
+	.long 0xb25b29f2, 0x8fe4c34d
+	.long 0x9a5ede41, 0x2178513a
+	.long 0xa563905d, 0xdf99fc11
+	.long 0x45cddf4e, 0xe0ac139e
+	.long 0xacfa3103, 0x6c23e841
+	.long 0xa51b6135, 0x170076fa

arch/x86/crypto/crct10dif-pcl-asm_64.S

@@ -0,0 +1,643 @@
+########################################################################
+# Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
+#
+# Copyright (c) 2013, Intel Corporation
+#
+# Authors:
+#     Erdinc Ozturk <erdinc.ozturk@intel.com>
+#     Vinodh Gopal <vinodh.gopal@intel.com>
+#     James Guilford <james.guilford@intel.com>
+#     Tim Chen <tim.c.chen@linux.intel.com>
+#
+# This software is available to you under a choice of one of two
+# licenses.  You may choose to be licensed under the terms of the GNU
+# General Public License (GPL) Version 2, available from the file
+# COPYING in the main directory of this source tree, or the
+# OpenIB.org BSD license below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+# * Redistributions of source code must retain the above copyright
+#   notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+#   notice, this list of conditions and the following disclaimer in the
+#   documentation and/or other materials provided with the
+#   distribution.
+#
+# * Neither the name of the Intel Corporation nor the names of its
+#   contributors may be used to endorse or promote products derived from
+#   this software without specific prior written permission.
+#
+#
+# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+########################################################################
+#       Function API:
+#       UINT16 crc_t10dif_pcl(
+#               UINT16 init_crc, //initial CRC value, 16 bits
+#               const unsigned char *buf, //buffer pointer to calculate CRC on
+#               UINT64 len //buffer length in bytes (64-bit data)
+#       );
+#
+#       Reference paper titled "Fast CRC Computation for Generic
+#	Polynomials Using PCLMULQDQ Instruction"
+#       URL: http://www.intel.com/content/dam/www/public/us/en/documents
+#  /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
+#
+#
+
+#include <linux/linkage.h>
+
+.text
+
+#define        arg1 %rdi
+#define        arg2 %rsi
+#define        arg3 %rdx
+
+#define        arg1_low32 %edi
+
+ENTRY(crc_t10dif_pcl)
+.align 16
+
+	# adjust the 16-bit initial_crc value, scale it to 32 bits
+	shl	$16, arg1_low32
+
+	# Allocate Stack Space
+	mov     %rsp, %rcx
+	sub	$16*2, %rsp
+	# align stack to 16 byte boundary
+	and     $~(0x10 - 1), %rsp
+
+	# check if smaller than 256
+	cmp	$256, arg3
+
+	# for sizes less than 128, we can't fold 64B at a time...
+	jl	_less_than_128
+
+
+	# load the initial crc value
+	movd	arg1_low32, %xmm10	# initial crc
+
+	# crc value does not need to be byte-reflected, but it needs
+	# to be moved to the high part of the register.
+	# because data will be byte-reflected and will align with
+	# initial crc at correct place.
+	pslldq	$12, %xmm10
+
+	movdqa  SHUF_MASK(%rip), %xmm11
+	# receive the initial 64B data, xor the initial crc value
+	movdqu	16*0(arg2), %xmm0
+	movdqu	16*1(arg2), %xmm1
+	movdqu	16*2(arg2), %xmm2
+	movdqu	16*3(arg2), %xmm3
+	movdqu	16*4(arg2), %xmm4
+	movdqu	16*5(arg2), %xmm5
+	movdqu	16*6(arg2), %xmm6
+	movdqu	16*7(arg2), %xmm7
+
+	pshufb	%xmm11, %xmm0
+	# XOR the initial_crc value
+	pxor	%xmm10, %xmm0
+	pshufb	%xmm11, %xmm1
+	pshufb	%xmm11, %xmm2
+	pshufb	%xmm11, %xmm3
+	pshufb	%xmm11, %xmm4
+	pshufb	%xmm11, %xmm5
+	pshufb	%xmm11, %xmm6
+	pshufb	%xmm11, %xmm7
+
+	movdqa	rk3(%rip), %xmm10	#xmm10 has rk3 and rk4
+					#imm value of pclmulqdq instruction
+					#will determine which constant to use
+
+	#################################################################
+	# we subtract 256 instead of 128 to save one instruction from the loop
+	sub	$256, arg3
+
+	# at this section of the code, there is 64*x+y (0<=y<64) bytes of
+	# buffer. The _fold_64_B_loop will fold 64B at a time
+	# until we have 64+y Bytes of buffer
+
+
+	# fold 64B at a time. This section of the code folds 4 xmm
+	# registers in parallel
+_fold_64_B_loop:
+
+	# update the buffer pointer
+	add	$128, arg2		#    buf += 64#
+
+	movdqu	16*0(arg2), %xmm9
+	movdqu	16*1(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm0, %xmm8
+	movdqa	%xmm1, %xmm13
+	pclmulqdq	$0x0 , %xmm10, %xmm0
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0 , %xmm10, %xmm1
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 , %xmm0
+	xorps	%xmm8 , %xmm0
+	pxor	%xmm12, %xmm1
+	xorps	%xmm13, %xmm1
+
+	movdqu	16*2(arg2), %xmm9
+	movdqu	16*3(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm2, %xmm8
+	movdqa	%xmm3, %xmm13
+	pclmulqdq	$0x0, %xmm10, %xmm2
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0, %xmm10, %xmm3
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 , %xmm2
+	xorps	%xmm8 , %xmm2
+	pxor	%xmm12, %xmm3
+	xorps	%xmm13, %xmm3
+
+	movdqu	16*4(arg2), %xmm9
+	movdqu	16*5(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm4, %xmm8
+	movdqa	%xmm5, %xmm13
+	pclmulqdq	$0x0,  %xmm10, %xmm4
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0,  %xmm10, %xmm5
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 ,  %xmm4
+	xorps	%xmm8 ,  %xmm4
+	pxor	%xmm12,  %xmm5
+	xorps	%xmm13,  %xmm5
+
+	movdqu	16*6(arg2), %xmm9
+	movdqu	16*7(arg2), %xmm12
+	pshufb	%xmm11, %xmm9
+	pshufb	%xmm11, %xmm12
+	movdqa	%xmm6 , %xmm8
+	movdqa	%xmm7 , %xmm13
+	pclmulqdq	$0x0 , %xmm10, %xmm6
+	pclmulqdq	$0x11, %xmm10, %xmm8
+	pclmulqdq	$0x0 , %xmm10, %xmm7
+	pclmulqdq	$0x11, %xmm10, %xmm13
+	pxor	%xmm9 , %xmm6
+	xorps	%xmm8 , %xmm6
+	pxor	%xmm12, %xmm7
+	xorps	%xmm13, %xmm7
+
+	sub	$128, arg3
+
+	# check if there is another 64B in the buffer to be able to fold
+	jge	_fold_64_B_loop
+	##################################################################
+
+
+	add	$128, arg2
+	# at this point, the buffer pointer is pointing at the last y Bytes
+	# of the buffer the 64B of folded data is in 4 of the xmm
+	# registers: xmm0, xmm1, xmm2, xmm3
+
+
+	# fold the 8 xmm registers to 1 xmm register with different constants
+
+	movdqa	rk9(%rip), %xmm10
+	movdqa	%xmm0, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm0
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm0, %xmm7
+
+	movdqa	rk11(%rip), %xmm10
+	movdqa	%xmm1, %xmm8
+	pclmulqdq	 $0x11, %xmm10, %xmm1
+	pclmulqdq	 $0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm1, %xmm7
+
+	movdqa	rk13(%rip), %xmm10
+	movdqa	%xmm2, %xmm8
+	pclmulqdq	 $0x11, %xmm10, %xmm2
+	pclmulqdq	 $0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm2, %xmm7
+
+	movdqa	rk15(%rip), %xmm10
+	movdqa	%xmm3, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm3
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm3, %xmm7
+
+	movdqa	rk17(%rip), %xmm10
+	movdqa	%xmm4, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm4
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm4, %xmm7
+
+	movdqa	rk19(%rip), %xmm10
+	movdqa	%xmm5, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm5
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	xorps	%xmm5, %xmm7
+
+	movdqa	rk1(%rip), %xmm10	#xmm10 has rk1 and rk2
+					#imm value of pclmulqdq instruction
+					#will determine which constant to use
+	movdqa	%xmm6, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm6
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm6, %xmm7
+
+
+	# instead of 64, we add 48 to the loop counter to save 1 instruction
+	# from the loop instead of a cmp instruction, we use the negative
+	# flag with the jl instruction
+	add	$128-16, arg3
+	jl	_final_reduction_for_128
+
+	# now we have 16+y bytes left to reduce. 16 Bytes is in register xmm7
+	# and the rest is in memory. We can fold 16 bytes at a time if y>=16
+	# continue folding 16B at a time
+
+_16B_reduction_loop:
+	movdqa	%xmm7, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm7
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	movdqu	(arg2), %xmm0
+	pshufb	%xmm11, %xmm0
+	pxor	%xmm0 , %xmm7
+	add	$16, arg2
+	sub	$16, arg3
+	# instead of a cmp instruction, we utilize the flags with the
+	# jge instruction equivalent of: cmp arg3, 16-16
+	# check if there is any more 16B in the buffer to be able to fold
+	jge	_16B_reduction_loop
+
+	#now we have 16+z bytes left to reduce, where 0<= z < 16.
+	#first, we reduce the data in the xmm7 register
+
+
+_final_reduction_for_128:
+	# check if any more data to fold. If not, compute the CRC of
+	# the final 128 bits
+	add	$16, arg3
+	je	_128_done
+
+	# here we are getting data that is less than 16 bytes.
+	# since we know that there was data before the pointer, we can
+	# offset the input pointer before the actual point, to receive
+	# exactly 16 bytes. after that the registers need to be adjusted.
+_get_last_two_xmms:
+	movdqa	%xmm7, %xmm2
+
+	movdqu	-16(arg2, arg3), %xmm1
+	pshufb	%xmm11, %xmm1
+
+	# get rid of the extra data that was loaded before
+	# load the shift constant
+	lea	pshufb_shf_table+16(%rip), %rax
+	sub	arg3, %rax
+	movdqu	(%rax), %xmm0
+
+	# shift xmm2 to the left by arg3 bytes
+	pshufb	%xmm0, %xmm2
+
+	# shift xmm7 to the right by 16-arg3 bytes
+	pxor	mask1(%rip), %xmm0
+	pshufb	%xmm0, %xmm7
+	pblendvb	%xmm2, %xmm1	#xmm0 is implicit
+
+	# fold 16 Bytes
+	movdqa	%xmm1, %xmm2
+	movdqa	%xmm7, %xmm8
+	pclmulqdq	$0x11, %xmm10, %xmm7
+	pclmulqdq	$0x0 , %xmm10, %xmm8
+	pxor	%xmm8, %xmm7
+	pxor	%xmm2, %xmm7
+
+_128_done:
+	# compute crc of a 128-bit value
+	movdqa	rk5(%rip), %xmm10	# rk5 and rk6 in xmm10
+	movdqa	%xmm7, %xmm0
+
+	#64b fold
+	pclmulqdq	$0x1, %xmm10, %xmm7
+	pslldq	$8   ,  %xmm0
+	pxor	%xmm0,  %xmm7
+
+	#32b fold
+	movdqa	%xmm7, %xmm0
+
+	pand	mask2(%rip), %xmm0
+
+	psrldq	$12, %xmm7
+	pclmulqdq	$0x10, %xmm10, %xmm7
+	pxor	%xmm0, %xmm7
+
+	#barrett reduction
+_barrett:
+	movdqa	rk7(%rip), %xmm10	# rk7 and rk8 in xmm10
+	movdqa	%xmm7, %xmm0
+	pclmulqdq	$0x01, %xmm10, %xmm7
+	pslldq	$4, %xmm7
+	pclmulqdq	$0x11, %xmm10, %xmm7
+
+	pslldq	$4, %xmm7
+	pxor	%xmm0, %xmm7
+	pextrd	$1, %xmm7, %eax
+
+_cleanup:
+	# scale the result back to 16 bits
+	shr	$16, %eax
+	mov     %rcx, %rsp
+	ret
+
+########################################################################
+
+.align 16
+_less_than_128:
+
+	# check if there is enough buffer to be able to fold 16B at a time
+	cmp	$32, arg3
+	jl	_less_than_32
+	movdqa  SHUF_MASK(%rip), %xmm11
+
+	# now if there is, load the constants
+	movdqa	rk1(%rip), %xmm10	# rk1 and rk2 in xmm10
+
+	movd	arg1_low32, %xmm0	# get the initial crc value
+	pslldq	$12, %xmm0	# align it to its correct place
+	movdqu	(arg2), %xmm7	# load the plaintext
+	pshufb	%xmm11, %xmm7	# byte-reflect the plaintext
+	pxor	%xmm0, %xmm7
+
+
+	# update the buffer pointer
+	add	$16, arg2
+
+	# update the counter. subtract 32 instead of 16 to save one
+	# instruction from the loop
+	sub	$32, arg3
+
+	jmp	_16B_reduction_loop
+
+
+.align 16
+_less_than_32:
+	# mov initial crc to the return value. this is necessary for
+	# zero-length buffers.
+	mov	arg1_low32, %eax
+	test	arg3, arg3
+	je	_cleanup
+
+	movdqa  SHUF_MASK(%rip), %xmm11
+
+	movd	arg1_low32, %xmm0	# get the initial crc value
+	pslldq	$12, %xmm0	# align it to its correct place
+
+	cmp	$16, arg3
+	je	_exact_16_left
+	jl	_less_than_16_left
+
+	movdqu	(arg2), %xmm7	# load the plaintext
+	pshufb	%xmm11, %xmm7	# byte-reflect the plaintext
+	pxor	%xmm0 , %xmm7	# xor the initial crc value
+	add	$16, arg2
+	sub	$16, arg3
+	movdqa	rk1(%rip), %xmm10	# rk1 and rk2 in xmm10
+	jmp	_get_last_two_xmms
+
+
+.align 16
+_less_than_16_left:
+	# use stack space to load data less than 16 bytes, zero-out
+	# the 16B in memory first.
+
+	pxor	%xmm1, %xmm1
+	mov	%rsp, %r11
+	movdqa	%xmm1, (%r11)
+
+	cmp	$4, arg3
+	jl	_only_less_than_4
+
+	# backup the counter value
+	mov	arg3, %r9
+	cmp	$8, arg3
+	jl	_less_than_8_left
+
+	# load 8 Bytes
+	mov	(arg2), %rax
+	mov	%rax, (%r11)
+	add	$8, %r11
+	sub	$8, arg3
+	add	$8, arg2
+_less_than_8_left:
+
+	cmp	$4, arg3
+	jl	_less_than_4_left
+
+	# load 4 Bytes
+	mov	(arg2), %eax
+	mov	%eax, (%r11)
+	add	$4, %r11
+	sub	$4, arg3
+	add	$4, arg2
+_less_than_4_left:
+
+	cmp	$2, arg3
+	jl	_less_than_2_left
+
+	# load 2 Bytes
+	mov	(arg2), %ax
+	mov	%ax, (%r11)
+	add	$2, %r11
+	sub	$2, arg3
+	add	$2, arg2
+_less_than_2_left:
+	cmp     $1, arg3
+        jl      _zero_left
+
+	# load 1 Byte
+	mov	(arg2), %al
+	mov	%al, (%r11)
+_zero_left:
+	movdqa	(%rsp), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7	# xor the initial crc value
+
+	# shl r9, 4
+	lea	pshufb_shf_table+16(%rip), %rax
+	sub	%r9, %rax
+	movdqu	(%rax), %xmm0
+	pxor	mask1(%rip), %xmm0
+
+	pshufb	%xmm0, %xmm7
+	jmp	_128_done
+
+.align 16
+_exact_16_left:
+	movdqu	(arg2), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7   # xor the initial crc value
+
+	jmp	_128_done
+
+_only_less_than_4:
+	cmp	$3, arg3
+	jl	_only_less_than_3
+
+	# load 3 Bytes
+	mov	(arg2), %al
+	mov	%al, (%r11)
+
+	mov	1(arg2), %al
+	mov	%al, 1(%r11)
+
+	mov	2(arg2), %al
+	mov	%al, 2(%r11)
+
+	movdqa	 (%rsp), %xmm7
+	pshufb	 %xmm11, %xmm7
+	pxor	 %xmm0 , %xmm7  # xor the initial crc value
+
+	psrldq	$5, %xmm7
+
+	jmp	_barrett
+_only_less_than_3:
+	cmp	$2, arg3
+	jl	_only_less_than_2
+
+	# load 2 Bytes
+	mov	(arg2), %al
+	mov	%al, (%r11)
+
+	mov	1(arg2), %al
+	mov	%al, 1(%r11)
+
+	movdqa	(%rsp), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7   # xor the initial crc value
+
+	psrldq	$6, %xmm7
+
+	jmp	_barrett
+_only_less_than_2:
+
+	# load 1 Byte
+	mov	(arg2), %al
+	mov	%al, (%r11)
+
+	movdqa	(%rsp), %xmm7
+	pshufb	%xmm11, %xmm7
+	pxor	%xmm0 , %xmm7   # xor the initial crc value
+
+	psrldq	$7, %xmm7
+
+	jmp	_barrett
+
+ENDPROC(crc_t10dif_pcl)
+
+.data
+
+# precomputed constants
+# these constants are precomputed from the poly:
+# 0x8bb70000 (0x8bb7 scaled to 32 bits)
+.align 16
+# Q = 0x18BB70000
+# rk1 = 2^(32*3) mod Q << 32
+# rk2 = 2^(32*5) mod Q << 32
+# rk3 = 2^(32*15) mod Q << 32
+# rk4 = 2^(32*17) mod Q << 32
+# rk5 = 2^(32*3) mod Q << 32
+# rk6 = 2^(32*2) mod Q << 32
+# rk7 = floor(2^64/Q)
+# rk8 = Q
+rk1:
+.quad 0x2d56000000000000
+rk2:
+.quad 0x06df000000000000
+rk3:
+.quad 0x9d9d000000000000
+rk4:
+.quad 0x7cf5000000000000
+rk5:
+.quad 0x2d56000000000000
+rk6:
+.quad 0x1368000000000000
+rk7:
+.quad 0x00000001f65a57f8
+rk8:
+.quad 0x000000018bb70000
+
+rk9:
+.quad 0xceae000000000000
+rk10:
+.quad 0xbfd6000000000000
+rk11:
+.quad 0x1e16000000000000
+rk12:
+.quad 0x713c000000000000
+rk13:
+.quad 0xf7f9000000000000
+rk14:
+.quad 0x80a6000000000000
+rk15:
+.quad 0x044c000000000000
+rk16:
+.quad 0xe658000000000000
+rk17:
+.quad 0xad18000000000000
+rk18:
+.quad 0xa497000000000000
+rk19:
+.quad 0x6ee3000000000000
+rk20:
+.quad 0xe7b5000000000000
+
+
+
+mask1:
+.octa 0x80808080808080808080808080808080
+mask2:
+.octa 0x00000000FFFFFFFFFFFFFFFFFFFFFFFF
+
+SHUF_MASK:
+.octa 0x000102030405060708090A0B0C0D0E0F
+
+pshufb_shf_table:
+# use these values for shift constants for the pshufb instruction
+# different alignments result in values as shown:
+#	DDQ 0x008f8e8d8c8b8a898887868584838281 # shl 15 (16-1) / shr1
+#	DDQ 0x01008f8e8d8c8b8a8988878685848382 # shl 14 (16-3) / shr2
+#	DDQ 0x0201008f8e8d8c8b8a89888786858483 # shl 13 (16-4) / shr3
+#	DDQ 0x030201008f8e8d8c8b8a898887868584 # shl 12 (16-4) / shr4
+#	DDQ 0x04030201008f8e8d8c8b8a8988878685 # shl 11 (16-5) / shr5
+#	DDQ 0x0504030201008f8e8d8c8b8a89888786 # shl 10 (16-6) / shr6
+#	DDQ 0x060504030201008f8e8d8c8b8a898887 # shl 9  (16-7) / shr7
+#	DDQ 0x07060504030201008f8e8d8c8b8a8988 # shl 8  (16-8) / shr8
+#	DDQ 0x0807060504030201008f8e8d8c8b8a89 # shl 7  (16-9) / shr9
+#	DDQ 0x090807060504030201008f8e8d8c8b8a # shl 6  (16-10) / shr10
+#	DDQ 0x0a090807060504030201008f8e8d8c8b # shl 5  (16-11) / shr11
+#	DDQ 0x0b0a090807060504030201008f8e8d8c # shl 4  (16-12) / shr12
+#	DDQ 0x0c0b0a090807060504030201008f8e8d # shl 3  (16-13) / shr13
+#	DDQ 0x0d0c0b0a090807060504030201008f8e # shl 2  (16-14) / shr14
+#	DDQ 0x0e0d0c0b0a090807060504030201008f # shl 1  (16-15) / shr15
+.octa 0x8f8e8d8c8b8a89888786858483828100
+.octa 0x000e0d0c0b0a09080706050403020100

arch/x86/crypto/crct10dif-pclmul_glue.c

@@ -0,0 +1,151 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform using PCLMULQDQ Instructions
+ *
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <asm/i387.h>
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+
+asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,
+				size_t len);
+
+struct chksum_desc_ctx {
+	__u16 crc;
+};
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected
+ * crc using table.
+ */
+
+static int chksum_init(struct shash_desc *desc)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = 0;
+
+	return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int length)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	if (irq_fpu_usable()) {
+		kernel_fpu_begin();
+		ctx->crc = crc_t10dif_pcl(ctx->crc, data, length);
+		kernel_fpu_end();
+	} else
+		ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
+	return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*(__u16 *)out = ctx->crc;
+	return 0;
+}
+
+static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+			u8 *out)
+{
+	if (irq_fpu_usable()) {
+		kernel_fpu_begin();
+		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+		kernel_fpu_end();
+	} else
+		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+	return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data,
+			 unsigned int length, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, length, out);
+}
+
+static struct shash_alg alg = {
+	.digestsize		=	CRC_T10DIF_DIGEST_SIZE,
+	.init		=	chksum_init,
+	.update		=	chksum_update,
+	.final		=	chksum_final,
+	.finup		=	chksum_finup,
+	.digest		=	chksum_digest,
+	.descsize		=	sizeof(struct chksum_desc_ctx),
+	.base			=	{
+		.cra_name		=	"crct10dif",
+		.cra_driver_name	=	"crct10dif-pclmul",
+		.cra_priority		=	200,
+		.cra_blocksize		=	CRC_T10DIF_BLOCK_SIZE,
+		.cra_module		=	THIS_MODULE,
+	}
+};
+
+static const struct x86_cpu_id crct10dif_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id);
+
+static int __init crct10dif_intel_mod_init(void)
+{
+	if (!x86_match_cpu(crct10dif_cpu_id))
+		return -ENODEV;
+
+	return crypto_register_shash(&alg);
+}
+
+static void __exit crct10dif_intel_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crct10dif_intel_mod_init);
+module_exit(crct10dif_intel_mod_fini);
+
+MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
+MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-pclmul");

arch/x86/crypto/des3_ede-asm_64.S

@@ -0,0 +1,805 @@
+/*
+ * des3_ede-asm_64.S  -  x86-64 assembly implementation of 3DES cipher
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/linkage.h>
+
+.file "des3_ede-asm_64.S"
+.text
+
+#define s1 .L_s1
+#define s2 ((s1) + (64*8))
+#define s3 ((s2) + (64*8))
+#define s4 ((s3) + (64*8))
+#define s5 ((s4) + (64*8))
+#define s6 ((s5) + (64*8))
+#define s7 ((s6) + (64*8))
+#define s8 ((s7) + (64*8))
+
+/* register macros */
+#define CTX %rdi
+
+#define RL0 %r8
+#define RL1 %r9
+#define RL2 %r10
+
+#define RL0d %r8d
+#define RL1d %r9d
+#define RL2d %r10d
+
+#define RR0 %r11
+#define RR1 %r12
+#define RR2 %r13
+
+#define RR0d %r11d
+#define RR1d %r12d
+#define RR2d %r13d
+
+#define RW0 %rax
+#define RW1 %rbx
+#define RW2 %rcx
+
+#define RW0d %eax
+#define RW1d %ebx
+#define RW2d %ecx
+
+#define RW0bl %al
+#define RW1bl %bl
+#define RW2bl %cl
+
+#define RW0bh %ah
+#define RW1bh %bh
+#define RW2bh %ch
+
+#define RT0 %r15
+#define RT1 %rbp
+#define RT2 %r14
+#define RT3 %rdx
+
+#define RT0d %r15d
+#define RT1d %ebp
+#define RT2d %r14d
+#define RT3d %edx
+
+/***********************************************************************
+ * 1-way 3DES
+ ***********************************************************************/
+#define do_permutation(a, b, offset, mask) \
+	movl a, RT0d; \
+	shrl $(offset), RT0d; \
+	xorl b, RT0d; \
+	andl $(mask), RT0d; \
+	xorl RT0d, b; \
+	shll $(offset), RT0d; \
+	xorl RT0d, a;
+
+#define expand_to_64bits(val, mask) \
+	movl val##d, RT0d; \
+	rorl $4, RT0d; \
+	shlq $32, RT0; \
+	orq RT0, val; \
+	andq mask, val;
+
+#define compress_to_64bits(val) \
+	movq val, RT0; \
+	shrq $32, RT0; \
+	roll $4, RT0d; \
+	orl RT0d, val##d;
+
+#define initial_permutation(left, right) \
+	do_permutation(left##d, right##d,  4, 0x0f0f0f0f); \
+	do_permutation(left##d, right##d, 16, 0x0000ffff); \
+	do_permutation(right##d, left##d,  2, 0x33333333); \
+	do_permutation(right##d, left##d,  8, 0x00ff00ff); \
+	movabs $0x3f3f3f3f3f3f3f3f, RT3; \
+	movl left##d, RW0d; \
+	roll $1, right##d; \
+	xorl right##d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, left##d; \
+	xorl RW0d, right##d; \
+	roll $1, left##d; \
+	expand_to_64bits(right, RT3); \
+	expand_to_64bits(left, RT3);
+
+#define final_permutation(left, right) \
+	compress_to_64bits(right); \
+	compress_to_64bits(left); \
+	movl right##d, RW0d; \
+	rorl $1, left##d; \
+	xorl left##d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, right##d; \
+	xorl RW0d, left##d; \
+	rorl $1, right##d; \
+	do_permutation(right##d, left##d,  8, 0x00ff00ff); \
+	do_permutation(right##d, left##d,  2, 0x33333333); \
+	do_permutation(left##d, right##d, 16, 0x0000ffff); \
+	do_permutation(left##d, right##d,  4, 0x0f0f0f0f);
+
+#define round1(n, from, to, load_next_key) \
+	xorq from, RW0; \
+	\
+	movzbl RW0bl, RT0d; \
+	movzbl RW0bh, RT1d; \
+	shrq $16, RW0; \
+	movzbl RW0bl, RT2d; \
+	movzbl RW0bh, RT3d; \
+	shrq $16, RW0; \
+	movq s8(, RT0, 8), RT0; \
+	xorq s6(, RT1, 8), to; \
+	movzbl RW0bl, RL1d; \
+	movzbl RW0bh, RT1d; \
+	shrl $16, RW0d; \
+	xorq s4(, RT2, 8), RT0; \
+	xorq s2(, RT3, 8), to; \
+	movzbl RW0bl, RT2d; \
+	movzbl RW0bh, RT3d; \
+	xorq s7(, RL1, 8), RT0; \
+	xorq s5(, RT1, 8), to; \
+	xorq s3(, RT2, 8), RT0; \
+	load_next_key(n, RW0); \
+	xorq RT0, to; \
+	xorq s1(, RT3, 8), to; \
+
+#define load_next_key(n, RWx) \
+	movq (((n) + 1) * 8)(CTX), RWx;
+
+#define dummy2(a, b) /*_*/
+
+#define read_block(io, left, right) \
+	movl    (io), left##d; \
+	movl   4(io), right##d; \
+	bswapl left##d; \
+	bswapl right##d;
+
+#define write_block(io, left, right) \
+	bswapl left##d; \
+	bswapl right##d; \
+	movl   left##d,   (io); \
+	movl   right##d, 4(io);
+
+ENTRY(des3_ede_x86_64_crypt_blk)
+	/* input:
+	 *	%rdi: round keys, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+	pushq %rbp;
+	pushq %rbx;
+	pushq %r12;
+	pushq %r13;
+	pushq %r14;
+	pushq %r15;
+
+	read_block(%rdx, RL0, RR0);
+	initial_permutation(RL0, RR0);
+
+	movq (CTX), RW0;
+
+	round1(0, RR0, RL0, load_next_key);
+	round1(1, RL0, RR0, load_next_key);
+	round1(2, RR0, RL0, load_next_key);
+	round1(3, RL0, RR0, load_next_key);
+	round1(4, RR0, RL0, load_next_key);
+	round1(5, RL0, RR0, load_next_key);
+	round1(6, RR0, RL0, load_next_key);
+	round1(7, RL0, RR0, load_next_key);
+	round1(8, RR0, RL0, load_next_key);
+	round1(9, RL0, RR0, load_next_key);
+	round1(10, RR0, RL0, load_next_key);
+	round1(11, RL0, RR0, load_next_key);
+	round1(12, RR0, RL0, load_next_key);
+	round1(13, RL0, RR0, load_next_key);
+	round1(14, RR0, RL0, load_next_key);
+	round1(15, RL0, RR0, load_next_key);
+
+	round1(16+0, RL0, RR0, load_next_key);
+	round1(16+1, RR0, RL0, load_next_key);
+	round1(16+2, RL0, RR0, load_next_key);
+	round1(16+3, RR0, RL0, load_next_key);
+	round1(16+4, RL0, RR0, load_next_key);
+	round1(16+5, RR0, RL0, load_next_key);
+	round1(16+6, RL0, RR0, load_next_key);
+	round1(16+7, RR0, RL0, load_next_key);
+	round1(16+8, RL0, RR0, load_next_key);
+	round1(16+9, RR0, RL0, load_next_key);
+	round1(16+10, RL0, RR0, load_next_key);
+	round1(16+11, RR0, RL0, load_next_key);
+	round1(16+12, RL0, RR0, load_next_key);
+	round1(16+13, RR0, RL0, load_next_key);
+	round1(16+14, RL0, RR0, load_next_key);
+	round1(16+15, RR0, RL0, load_next_key);
+
+	round1(32+0, RR0, RL0, load_next_key);
+	round1(32+1, RL0, RR0, load_next_key);
+	round1(32+2, RR0, RL0, load_next_key);
+	round1(32+3, RL0, RR0, load_next_key);
+	round1(32+4, RR0, RL0, load_next_key);
+	round1(32+5, RL0, RR0, load_next_key);
+	round1(32+6, RR0, RL0, load_next_key);
+	round1(32+7, RL0, RR0, load_next_key);
+	round1(32+8, RR0, RL0, load_next_key);
+	round1(32+9, RL0, RR0, load_next_key);
+	round1(32+10, RR0, RL0, load_next_key);
+	round1(32+11, RL0, RR0, load_next_key);
+	round1(32+12, RR0, RL0, load_next_key);
+	round1(32+13, RL0, RR0, load_next_key);
+	round1(32+14, RR0, RL0, load_next_key);
+	round1(32+15, RL0, RR0, dummy2);
+
+	final_permutation(RR0, RL0);
+	write_block(%rsi, RR0, RL0);
+
+	popq %r15;
+	popq %r14;
+	popq %r13;
+	popq %r12;
+	popq %rbx;
+	popq %rbp;
+
+	ret;
+ENDPROC(des3_ede_x86_64_crypt_blk)
+
+/***********************************************************************
+ * 3-way 3DES
+ ***********************************************************************/
+#define expand_to_64bits(val, mask) \
+	movl val##d, RT0d; \
+	rorl $4, RT0d; \
+	shlq $32, RT0; \
+	orq RT0, val; \
+	andq mask, val;
+
+#define compress_to_64bits(val) \
+	movq val, RT0; \
+	shrq $32, RT0; \
+	roll $4, RT0d; \
+	orl RT0d, val##d;
+
+#define initial_permutation3(left, right) \
+	do_permutation(left##0d, right##0d,  4, 0x0f0f0f0f); \
+	do_permutation(left##0d, right##0d, 16, 0x0000ffff); \
+	  do_permutation(left##1d, right##1d,  4, 0x0f0f0f0f); \
+	  do_permutation(left##1d, right##1d, 16, 0x0000ffff); \
+	    do_permutation(left##2d, right##2d,  4, 0x0f0f0f0f); \
+	    do_permutation(left##2d, right##2d, 16, 0x0000ffff); \
+	    \
+	do_permutation(right##0d, left##0d,  2, 0x33333333); \
+	do_permutation(right##0d, left##0d,  8, 0x00ff00ff); \
+	  do_permutation(right##1d, left##1d,  2, 0x33333333); \
+	  do_permutation(right##1d, left##1d,  8, 0x00ff00ff); \
+	    do_permutation(right##2d, left##2d,  2, 0x33333333); \
+	    do_permutation(right##2d, left##2d,  8, 0x00ff00ff); \
+	    \
+	movabs $0x3f3f3f3f3f3f3f3f, RT3; \
+	    \
+	movl left##0d, RW0d; \
+	roll $1, right##0d; \
+	xorl right##0d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, left##0d; \
+	xorl RW0d, right##0d; \
+	roll $1, left##0d; \
+	expand_to_64bits(right##0, RT3); \
+	expand_to_64bits(left##0, RT3); \
+	  movl left##1d, RW1d; \
+	  roll $1, right##1d; \
+	  xorl right##1d, RW1d; \
+	  andl $0xaaaaaaaa, RW1d; \
+	  xorl RW1d, left##1d; \
+	  xorl RW1d, right##1d; \
+	  roll $1, left##1d; \
+	  expand_to_64bits(right##1, RT3); \
+	  expand_to_64bits(left##1, RT3); \
+	    movl left##2d, RW2d; \
+	    roll $1, right##2d; \
+	    xorl right##2d, RW2d; \
+	    andl $0xaaaaaaaa, RW2d; \
+	    xorl RW2d, left##2d; \
+	    xorl RW2d, right##2d; \
+	    roll $1, left##2d; \
+	    expand_to_64bits(right##2, RT3); \
+	    expand_to_64bits(left##2, RT3);
+
+#define final_permutation3(left, right) \
+	compress_to_64bits(right##0); \
+	compress_to_64bits(left##0); \
+	movl right##0d, RW0d; \
+	rorl $1, left##0d; \
+	xorl left##0d, RW0d; \
+	andl $0xaaaaaaaa, RW0d; \
+	xorl RW0d, right##0d; \
+	xorl RW0d, left##0d; \
+	rorl $1, right##0d; \
+	  compress_to_64bits(right##1); \
+	  compress_to_64bits(left##1); \
+	  movl right##1d, RW1d; \
+	  rorl $1, left##1d; \
+	  xorl left##1d, RW1d; \
+	  andl $0xaaaaaaaa, RW1d; \
+	  xorl RW1d, right##1d; \
+	  xorl RW1d, left##1d; \
+	  rorl $1, right##1d; \
+	    compress_to_64bits(right##2); \
+	    compress_to_64bits(left##2); \
+	    movl right##2d, RW2d; \
+	    rorl $1, left##2d; \
+	    xorl left##2d, RW2d; \
+	    andl $0xaaaaaaaa, RW2d; \
+	    xorl RW2d, right##2d; \
+	    xorl RW2d, left##2d; \
+	    rorl $1, right##2d; \
+	    \
+	do_permutation(right##0d, left##0d,  8, 0x00ff00ff); \
+	do_permutation(right##0d, left##0d,  2, 0x33333333); \
+	  do_permutation(right##1d, left##1d,  8, 0x00ff00ff); \
+	  do_permutation(right##1d, left##1d,  2, 0x33333333); \
+	    do_permutation(right##2d, left##2d,  8, 0x00ff00ff); \
+	    do_permutation(right##2d, left##2d,  2, 0x33333333); \
+	    \
+	do_permutation(left##0d, right##0d, 16, 0x0000ffff); \
+	do_permutation(left##0d, right##0d,  4, 0x0f0f0f0f); \
+	  do_permutation(left##1d, right##1d, 16, 0x0000ffff); \
+	  do_permutation(left##1d, right##1d,  4, 0x0f0f0f0f); \
+	    do_permutation(left##2d, right##2d, 16, 0x0000ffff); \
+	    do_permutation(left##2d, right##2d,  4, 0x0f0f0f0f);
+
+#define round3(n, from, to, load_next_key, do_movq) \
+	xorq from##0, RW0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	shrq $16, RW0; \
+	xorq s8(, RT3, 8), to##0; \
+	xorq s6(, RT1, 8), to##0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	shrq $16, RW0; \
+	xorq s4(, RT3, 8), to##0; \
+	xorq s2(, RT1, 8), to##0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	shrl $16, RW0d; \
+	xorq s7(, RT3, 8), to##0; \
+	xorq s5(, RT1, 8), to##0; \
+	movzbl RW0bl, RT3d; \
+	movzbl RW0bh, RT1d; \
+	load_next_key(n, RW0); \
+	xorq s3(, RT3, 8), to##0; \
+	xorq s1(, RT1, 8), to##0; \
+		xorq from##1, RW1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		shrq $16, RW1; \
+		xorq s8(, RT3, 8), to##1; \
+		xorq s6(, RT1, 8), to##1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		shrq $16, RW1; \
+		xorq s4(, RT3, 8), to##1; \
+		xorq s2(, RT1, 8), to##1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		shrl $16, RW1d; \
+		xorq s7(, RT3, 8), to##1; \
+		xorq s5(, RT1, 8), to##1; \
+		movzbl RW1bl, RT3d; \
+		movzbl RW1bh, RT1d; \
+		do_movq(RW0, RW1); \
+		xorq s3(, RT3, 8), to##1; \
+		xorq s1(, RT1, 8), to##1; \
+			xorq from##2, RW2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			shrq $16, RW2; \
+			xorq s8(, RT3, 8), to##2; \
+			xorq s6(, RT1, 8), to##2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			shrq $16, RW2; \
+			xorq s4(, RT3, 8), to##2; \
+			xorq s2(, RT1, 8), to##2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			shrl $16, RW2d; \
+			xorq s7(, RT3, 8), to##2; \
+			xorq s5(, RT1, 8), to##2; \
+			movzbl RW2bl, RT3d; \
+			movzbl RW2bh, RT1d; \
+			do_movq(RW0, RW2); \
+			xorq s3(, RT3, 8), to##2; \
+			xorq s1(, RT1, 8), to##2;
+
+#define __movq(src, dst) \
+	movq src, dst;
+
+ENTRY(des3_ede_x86_64_crypt_blk_3way)
+	/* input:
+	 *	%rdi: ctx, round keys
+	 *	%rsi: dst (3 blocks)
+	 *	%rdx: src (3 blocks)
+	 */
+
+	pushq %rbp;
+	pushq %rbx;
+	pushq %r12;
+	pushq %r13;
+	pushq %r14;
+	pushq %r15;
+
+	/* load input */
+	movl 0 * 4(%rdx), RL0d;
+	movl 1 * 4(%rdx), RR0d;
+	movl 2 * 4(%rdx), RL1d;
+	movl 3 * 4(%rdx), RR1d;
+	movl 4 * 4(%rdx), RL2d;
+	movl 5 * 4(%rdx), RR2d;
+
+	bswapl RL0d;
+	bswapl RR0d;
+	bswapl RL1d;
+	bswapl RR1d;
+	bswapl RL2d;
+	bswapl RR2d;
+
+	initial_permutation3(RL, RR);
+
+	movq 0(CTX), RW0;
+	movq RW0, RW1;
+	movq RW0, RW2;
+
+	round3(0, RR, RL, load_next_key, __movq);
+	round3(1, RL, RR, load_next_key, __movq);
+	round3(2, RR, RL, load_next_key, __movq);
+	round3(3, RL, RR, load_next_key, __movq);
+	round3(4, RR, RL, load_next_key, __movq);
+	round3(5, RL, RR, load_next_key, __movq);
+	round3(6, RR, RL, load_next_key, __movq);
+	round3(7, RL, RR, load_next_key, __movq);
+	round3(8, RR, RL, load_next_key, __movq);
+	round3(9, RL, RR, load_next_key, __movq);
+	round3(10, RR, RL, load_next_key, __movq);
+	round3(11, RL, RR, load_next_key, __movq);
+	round3(12, RR, RL, load_next_key, __movq);
+	round3(13, RL, RR, load_next_key, __movq);
+	round3(14, RR, RL, load_next_key, __movq);
+	round3(15, RL, RR, load_next_key, __movq);
+
+	round3(16+0, RL, RR, load_next_key, __movq);
+	round3(16+1, RR, RL, load_next_key, __movq);
+	round3(16+2, RL, RR, load_next_key, __movq);
+	round3(16+3, RR, RL, load_next_key, __movq);
+	round3(16+4, RL, RR, load_next_key, __movq);
+	round3(16+5, RR, RL, load_next_key, __movq);
+	round3(16+6, RL, RR, load_next_key, __movq);
+	round3(16+7, RR, RL, load_next_key, __movq);
+	round3(16+8, RL, RR, load_next_key, __movq);
+	round3(16+9, RR, RL, load_next_key, __movq);
+	round3(16+10, RL, RR, load_next_key, __movq);
+	round3(16+11, RR, RL, load_next_key, __movq);
+	round3(16+12, RL, RR, load_next_key, __movq);
+	round3(16+13, RR, RL, load_next_key, __movq);
+	round3(16+14, RL, RR, load_next_key, __movq);
+	round3(16+15, RR, RL, load_next_key, __movq);
+
+	round3(32+0, RR, RL, load_next_key, __movq);
+	round3(32+1, RL, RR, load_next_key, __movq);
+	round3(32+2, RR, RL, load_next_key, __movq);
+	round3(32+3, RL, RR, load_next_key, __movq);
+	round3(32+4, RR, RL, load_next_key, __movq);
+	round3(32+5, RL, RR, load_next_key, __movq);
+	round3(32+6, RR, RL, load_next_key, __movq);
+	round3(32+7, RL, RR, load_next_key, __movq);
+	round3(32+8, RR, RL, load_next_key, __movq);
+	round3(32+9, RL, RR, load_next_key, __movq);
+	round3(32+10, RR, RL, load_next_key, __movq);
+	round3(32+11, RL, RR, load_next_key, __movq);
+	round3(32+12, RR, RL, load_next_key, __movq);
+	round3(32+13, RL, RR, load_next_key, __movq);
+	round3(32+14, RR, RL, load_next_key, __movq);
+	round3(32+15, RL, RR, dummy2, dummy2);
+
+	final_permutation3(RR, RL);
+
+	bswapl RR0d;
+	bswapl RL0d;
+	bswapl RR1d;
+	bswapl RL1d;
+	bswapl RR2d;
+	bswapl RL2d;
+
+	movl RR0d, 0 * 4(%rsi);
+	movl RL0d, 1 * 4(%rsi);
+	movl RR1d, 2 * 4(%rsi);
+	movl RL1d, 3 * 4(%rsi);
+	movl RR2d, 4 * 4(%rsi);
+	movl RL2d, 5 * 4(%rsi);
+
+	popq %r15;
+	popq %r14;
+	popq %r13;
+	popq %r12;
+	popq %rbx;
+	popq %rbp;
+
+	ret;
+ENDPROC(des3_ede_x86_64_crypt_blk_3way)
+
+.data
+.align 16
+.L_s1:
+	.quad 0x0010100001010400, 0x0000000000000000
+	.quad 0x0000100000010000, 0x0010100001010404
+	.quad 0x0010100001010004, 0x0000100000010404
+	.quad 0x0000000000000004, 0x0000100000010000
+	.quad 0x0000000000000400, 0x0010100001010400
+	.quad 0x0010100001010404, 0x0000000000000400
+	.quad 0x0010000001000404, 0x0010100001010004
+	.quad 0x0010000001000000, 0x0000000000000004
+	.quad 0x0000000000000404, 0x0010000001000400
+	.quad 0x0010000001000400, 0x0000100000010400
+	.quad 0x0000100000010400, 0x0010100001010000
+	.quad 0x0010100001010000, 0x0010000001000404
+	.quad 0x0000100000010004, 0x0010000001000004
+	.quad 0x0010000001000004, 0x0000100000010004
+	.quad 0x0000000000000000, 0x0000000000000404
+	.quad 0x0000100000010404, 0x0010000001000000
+	.quad 0x0000100000010000, 0x0010100001010404
+	.quad 0x0000000000000004, 0x0010100001010000
+	.quad 0x0010100001010400, 0x0010000001000000
+	.quad 0x0010000001000000, 0x0000000000000400
+	.quad 0x0010100001010004, 0x0000100000010000
+	.quad 0x0000100000010400, 0x0010000001000004
+	.quad 0x0000000000000400, 0x0000000000000004
+	.quad 0x0010000001000404, 0x0000100000010404
+	.quad 0x0010100001010404, 0x0000100000010004
+	.quad 0x0010100001010000, 0x0010000001000404
+	.quad 0x0010000001000004, 0x0000000000000404
+	.quad 0x0000100000010404, 0x0010100001010400
+	.quad 0x0000000000000404, 0x0010000001000400
+	.quad 0x0010000001000400, 0x0000000000000000
+	.quad 0x0000100000010004, 0x0000100000010400
+	.quad 0x0000000000000000, 0x0010100001010004
+.L_s2:
+	.quad 0x0801080200100020, 0x0800080000000000
+	.quad 0x0000080000000000, 0x0001080200100020
+	.quad 0x0001000000100000, 0x0000000200000020
+	.quad 0x0801000200100020, 0x0800080200000020
+	.quad 0x0800000200000020, 0x0801080200100020
+	.quad 0x0801080000100000, 0x0800000000000000
+	.quad 0x0800080000000000, 0x0001000000100000
+	.quad 0x0000000200000020, 0x0801000200100020
+	.quad 0x0001080000100000, 0x0001000200100020
+	.quad 0x0800080200000020, 0x0000000000000000
+	.quad 0x0800000000000000, 0x0000080000000000
+	.quad 0x0001080200100020, 0x0801000000100000
+	.quad 0x0001000200100020, 0x0800000200000020
+	.quad 0x0000000000000000, 0x0001080000100000
+	.quad 0x0000080200000020, 0x0801080000100000
+	.quad 0x0801000000100000, 0x0000080200000020
+	.quad 0x0000000000000000, 0x0001080200100020
+	.quad 0x0801000200100020, 0x0001000000100000
+	.quad 0x0800080200000020, 0x0801000000100000
+	.quad 0x0801080000100000, 0x0000080000000000
+	.quad 0x0801000000100000, 0x0800080000000000
+	.quad 0x0000000200000020, 0x0801080200100020
+	.quad 0x0001080200100020, 0x0000000200000020
+	.quad 0x0000080000000000, 0x0800000000000000
+	.quad 0x0000080200000020, 0x0801080000100000
+	.quad 0x0001000000100000, 0x0800000200000020
+	.quad 0x0001000200100020, 0x0800080200000020
+	.quad 0x0800000200000020, 0x0001000200100020
+	.quad 0x0001080000100000, 0x0000000000000000
+	.quad 0x0800080000000000, 0x0000080200000020
+	.quad 0x0800000000000000, 0x0801000200100020
+	.quad 0x0801080200100020, 0x0001080000100000
+.L_s3:
+	.quad 0x0000002000000208, 0x0000202008020200
+	.quad 0x0000000000000000, 0x0000200008020008
+	.quad 0x0000002008000200, 0x0000000000000000
+	.quad 0x0000202000020208, 0x0000002008000200
+	.quad 0x0000200000020008, 0x0000000008000008
+	.quad 0x0000000008000008, 0x0000200000020000
+	.quad 0x0000202008020208, 0x0000200000020008
+	.quad 0x0000200008020000, 0x0000002000000208
+	.quad 0x0000000008000000, 0x0000000000000008
+	.quad 0x0000202008020200, 0x0000002000000200
+	.quad 0x0000202000020200, 0x0000200008020000
+	.quad 0x0000200008020008, 0x0000202000020208
+	.quad 0x0000002008000208, 0x0000202000020200
+	.quad 0x0000200000020000, 0x0000002008000208
+	.quad 0x0000000000000008, 0x0000202008020208
+	.quad 0x0000002000000200, 0x0000000008000000
+	.quad 0x0000202008020200, 0x0000000008000000
+	.quad 0x0000200000020008, 0x0000002000000208
+	.quad 0x0000200000020000, 0x0000202008020200
+	.quad 0x0000002008000200, 0x0000000000000000
+	.quad 0x0000002000000200, 0x0000200000020008
+	.quad 0x0000202008020208, 0x0000002008000200
+	.quad 0x0000000008000008, 0x0000002000000200
+	.quad 0x0000000000000000, 0x0000200008020008
+	.quad 0x0000002008000208, 0x0000200000020000
+	.quad 0x0000000008000000, 0x0000202008020208
+	.quad 0x0000000000000008, 0x0000202000020208
+	.quad 0x0000202000020200, 0x0000000008000008
+	.quad 0x0000200008020000, 0x0000002008000208
+	.quad 0x0000002000000208, 0x0000200008020000
+	.quad 0x0000202000020208, 0x0000000000000008
+	.quad 0x0000200008020008, 0x0000202000020200
+.L_s4:
+	.quad 0x1008020000002001, 0x1000020800002001
+	.quad 0x1000020800002001, 0x0000000800000000
+	.quad 0x0008020800002000, 0x1008000800000001
+	.quad 0x1008000000000001, 0x1000020000002001
+	.quad 0x0000000000000000, 0x0008020000002000
+	.quad 0x0008020000002000, 0x1008020800002001
+	.quad 0x1000000800000001, 0x0000000000000000
+	.quad 0x0008000800000000, 0x1008000000000001
+	.quad 0x1000000000000001, 0x0000020000002000
+	.quad 0x0008000000000000, 0x1008020000002001
+	.quad 0x0000000800000000, 0x0008000000000000
+	.quad 0x1000020000002001, 0x0000020800002000
+	.quad 0x1008000800000001, 0x1000000000000001
+	.quad 0x0000020800002000, 0x0008000800000000
+	.quad 0x0000020000002000, 0x0008020800002000
+	.quad 0x1008020800002001, 0x1000000800000001
+	.quad 0x0008000800000000, 0x1008000000000001
+	.quad 0x0008020000002000, 0x1008020800002001
+	.quad 0x1000000800000001, 0x0000000000000000
+	.quad 0x0000000000000000, 0x0008020000002000
+	.quad 0x0000020800002000, 0x0008000800000000
+	.quad 0x1008000800000001, 0x1000000000000001
+	.quad 0x1008020000002001, 0x1000020800002001
+	.quad 0x1000020800002001, 0x0000000800000000
+	.quad 0x1008020800002001, 0x1000000800000001
+	.quad 0x1000000000000001, 0x0000020000002000
+	.quad 0x1008000000000001, 0x1000020000002001
+	.quad 0x0008020800002000, 0x1008000800000001
+	.quad 0x1000020000002001, 0x0000020800002000
+	.quad 0x0008000000000000, 0x1008020000002001
+	.quad 0x0000000800000000, 0x0008000000000000
+	.quad 0x0000020000002000, 0x0008020800002000
+.L_s5:
+	.quad 0x0000001000000100, 0x0020001002080100
+	.quad 0x0020000002080000, 0x0420001002000100
+	.quad 0x0000000000080000, 0x0000001000000100
+	.quad 0x0400000000000000, 0x0020000002080000
+	.quad 0x0400001000080100, 0x0000000000080000
+	.quad 0x0020001002000100, 0x0400001000080100
+	.quad 0x0420001002000100, 0x0420000002080000
+	.quad 0x0000001000080100, 0x0400000000000000
+	.quad 0x0020000002000000, 0x0400000000080000
+	.quad 0x0400000000080000, 0x0000000000000000
+	.quad 0x0400001000000100, 0x0420001002080100
+	.quad 0x0420001002080100, 0x0020001002000100
+	.quad 0x0420000002080000, 0x0400001000000100
+	.quad 0x0000000000000000, 0x0420000002000000
+	.quad 0x0020001002080100, 0x0020000002000000
+	.quad 0x0420000002000000, 0x0000001000080100
+	.quad 0x0000000000080000, 0x0420001002000100
+	.quad 0x0000001000000100, 0x0020000002000000
+	.quad 0x0400000000000000, 0x0020000002080000
+	.quad 0x0420001002000100, 0x0400001000080100
+	.quad 0x0020001002000100, 0x0400000000000000
+	.quad 0x0420000002080000, 0x0020001002080100
+	.quad 0x0400001000080100, 0x0000001000000100
+	.quad 0x0020000002000000, 0x0420000002080000
+	.quad 0x0420001002080100, 0x0000001000080100
+	.quad 0x0420000002000000, 0x0420001002080100
+	.quad 0x0020000002080000, 0x0000000000000000
+	.quad 0x0400000000080000, 0x0420000002000000
+	.quad 0x0000001000080100, 0x0020001002000100
+	.quad 0x0400001000000100, 0x0000000000080000
+	.quad 0x0000000000000000, 0x0400000000080000
+	.quad 0x0020001002080100, 0x0400001000000100
+.L_s6:
+	.quad 0x0200000120000010, 0x0204000020000000
+	.quad 0x0000040000000000, 0x0204040120000010
+	.quad 0x0204000020000000, 0x0000000100000010
+	.quad 0x0204040120000010, 0x0004000000000000
+	.quad 0x0200040020000000, 0x0004040100000010
+	.quad 0x0004000000000000, 0x0200000120000010
+	.quad 0x0004000100000010, 0x0200040020000000
+	.quad 0x0200000020000000, 0x0000040100000010
+	.quad 0x0000000000000000, 0x0004000100000010
+	.quad 0x0200040120000010, 0x0000040000000000
+	.quad 0x0004040000000000, 0x0200040120000010
+	.quad 0x0000000100000010, 0x0204000120000010
+	.quad 0x0204000120000010, 0x0000000000000000
+	.quad 0x0004040100000010, 0x0204040020000000
+	.quad 0x0000040100000010, 0x0004040000000000
+	.quad 0x0204040020000000, 0x0200000020000000
+	.quad 0x0200040020000000, 0x0000000100000010
+	.quad 0x0204000120000010, 0x0004040000000000
+	.quad 0x0204040120000010, 0x0004000000000000
+	.quad 0x0000040100000010, 0x0200000120000010
+	.quad 0x0004000000000000, 0x0200040020000000
+	.quad 0x0200000020000000, 0x0000040100000010
+	.quad 0x0200000120000010, 0x0204040120000010
+	.quad 0x0004040000000000, 0x0204000020000000
+	.quad 0x0004040100000010, 0x0204040020000000
+	.quad 0x0000000000000000, 0x0204000120000010
+	.quad 0x0000000100000010, 0x0000040000000000
+	.quad 0x0204000020000000, 0x0004040100000010
+	.quad 0x0000040000000000, 0x0004000100000010
+	.quad 0x0200040120000010, 0x0000000000000000
+	.quad 0x0204040020000000, 0x0200000020000000
+	.quad 0x0004000100000010, 0x0200040120000010
+.L_s7:
+	.quad 0x0002000000200000, 0x2002000004200002
+	.quad 0x2000000004000802, 0x0000000000000000
+	.quad 0x0000000000000800, 0x2000000004000802
+	.quad 0x2002000000200802, 0x0002000004200800
+	.quad 0x2002000004200802, 0x0002000000200000
+	.quad 0x0000000000000000, 0x2000000004000002
+	.quad 0x2000000000000002, 0x0000000004000000
+	.quad 0x2002000004200002, 0x2000000000000802
+	.quad 0x0000000004000800, 0x2002000000200802
+	.quad 0x2002000000200002, 0x0000000004000800
+	.quad 0x2000000004000002, 0x0002000004200000
+	.quad 0x0002000004200800, 0x2002000000200002
+	.quad 0x0002000004200000, 0x0000000000000800
+	.quad 0x2000000000000802, 0x2002000004200802
+	.quad 0x0002000000200800, 0x2000000000000002
+	.quad 0x0000000004000000, 0x0002000000200800
+	.quad 0x0000000004000000, 0x0002000000200800
+	.quad 0x0002000000200000, 0x2000000004000802
+	.quad 0x2000000004000802, 0x2002000004200002
+	.quad 0x2002000004200002, 0x2000000000000002
+	.quad 0x2002000000200002, 0x0000000004000000
+	.quad 0x0000000004000800, 0x0002000000200000
+	.quad 0x0002000004200800, 0x2000000000000802
+	.quad 0x2002000000200802, 0x0002000004200800
+	.quad 0x2000000000000802, 0x2000000004000002
+	.quad 0x2002000004200802, 0x0002000004200000
+	.quad 0x0002000000200800, 0x0000000000000000
+	.quad 0x2000000000000002, 0x2002000004200802
+	.quad 0x0000000000000000, 0x2002000000200802
+	.quad 0x0002000004200000, 0x0000000000000800
+	.quad 0x2000000004000002, 0x0000000004000800
+	.quad 0x0000000000000800, 0x2002000000200002
+.L_s8:
+	.quad 0x0100010410001000, 0x0000010000001000
+	.quad 0x0000000000040000, 0x0100010410041000
+	.quad 0x0100000010000000, 0x0100010410001000
+	.quad 0x0000000400000000, 0x0100000010000000
+	.quad 0x0000000400040000, 0x0100000010040000
+	.quad 0x0100010410041000, 0x0000010000041000
+	.quad 0x0100010010041000, 0x0000010400041000
+	.quad 0x0000010000001000, 0x0000000400000000
+	.quad 0x0100000010040000, 0x0100000410000000
+	.quad 0x0100010010001000, 0x0000010400001000
+	.quad 0x0000010000041000, 0x0000000400040000
+	.quad 0x0100000410040000, 0x0100010010041000
+	.quad 0x0000010400001000, 0x0000000000000000
+	.quad 0x0000000000000000, 0x0100000410040000
+	.quad 0x0100000410000000, 0x0100010010001000
+	.quad 0x0000010400041000, 0x0000000000040000
+	.quad 0x0000010400041000, 0x0000000000040000
+	.quad 0x0100010010041000, 0x0000010000001000
+	.quad 0x0000000400000000, 0x0100000410040000
+	.quad 0x0000010000001000, 0x0000010400041000
+	.quad 0x0100010010001000, 0x0000000400000000
+	.quad 0x0100000410000000, 0x0100000010040000
+	.quad 0x0100000410040000, 0x0100000010000000
+	.quad 0x0000000000040000, 0x0100010410001000
+	.quad 0x0000000000000000, 0x0100010410041000
+	.quad 0x0000000400040000, 0x0100000410000000
+	.quad 0x0100000010040000, 0x0100010010001000
+	.quad 0x0100010410001000, 0x0000000000000000
+	.quad 0x0100010410041000, 0x0000010000041000
+	.quad 0x0000010000041000, 0x0000010400001000
+	.quad 0x0000010400001000, 0x0000000400040000
+	.quad 0x0100000010000000, 0x0100010010041000

arch/x86/crypto/des3_ede_glue.c

@@ -0,0 +1,509 @@
+/*
+ * Glue Code for assembler optimized version of 3DES
+ *
+ * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ * CTR part based on code (crypto/ctr.c) by:
+ *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <asm/processor.h>
+#include <crypto/des.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <crypto/algapi.h>
+
+struct des3_ede_x86_ctx {
+	u32 enc_expkey[DES3_EDE_EXPKEY_WORDS];
+	u32 dec_expkey[DES3_EDE_EXPKEY_WORDS];
+};
+
+/* regular block cipher functions */
+asmlinkage void des3_ede_x86_64_crypt_blk(const u32 *expkey, u8 *dst,
+					  const u8 *src);
+
+/* 3-way parallel cipher functions */
+asmlinkage void des3_ede_x86_64_crypt_blk_3way(const u32 *expkey, u8 *dst,
+					       const u8 *src);
+
+static inline void des3_ede_enc_blk(struct des3_ede_x86_ctx *ctx, u8 *dst,
+				    const u8 *src)
+{
+	u32 *enc_ctx = ctx->enc_expkey;
+
+	des3_ede_x86_64_crypt_blk(enc_ctx, dst, src);
+}
+
+static inline void des3_ede_dec_blk(struct des3_ede_x86_ctx *ctx, u8 *dst,
+				    const u8 *src)
+{
+	u32 *dec_ctx = ctx->dec_expkey;
+
+	des3_ede_x86_64_crypt_blk(dec_ctx, dst, src);
+}
+
+static inline void des3_ede_enc_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst,
+					 const u8 *src)
+{
+	u32 *enc_ctx = ctx->enc_expkey;
+
+	des3_ede_x86_64_crypt_blk_3way(enc_ctx, dst, src);
+}
+
+static inline void des3_ede_dec_blk_3way(struct des3_ede_x86_ctx *ctx, u8 *dst,
+					 const u8 *src)
+{
+	u32 *dec_ctx = ctx->dec_expkey;
+
+	des3_ede_x86_64_crypt_blk_3way(dec_ctx, dst, src);
+}
+
+static void des3_ede_x86_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	des3_ede_enc_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static void des3_ede_x86_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
+{
+	des3_ede_dec_blk(crypto_tfm_ctx(tfm), dst, src);
+}
+
+static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
+		     const u32 *expkey)
+{
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes;
+	int err;
+
+	err = blkcipher_walk_virt(desc, walk);
+
+	while ((nbytes = walk->nbytes)) {
+		u8 *wsrc = walk->src.virt.addr;
+		u8 *wdst = walk->dst.virt.addr;
+
+		/* Process four block batch */
+		if (nbytes >= bsize * 3) {
+			do {
+				des3_ede_x86_64_crypt_blk_3way(expkey, wdst,
+							       wsrc);
+
+				wsrc += bsize * 3;
+				wdst += bsize * 3;
+				nbytes -= bsize * 3;
+			} while (nbytes >= bsize * 3);
+
+			if (nbytes < bsize)
+				goto done;
+		}
+
+		/* Handle leftovers */
+		do {
+			des3_ede_x86_64_crypt_blk(expkey, wdst, wsrc);
+
+			wsrc += bsize;
+			wdst += bsize;
+			nbytes -= bsize;
+		} while (nbytes >= bsize);
+
+done:
+		err = blkcipher_walk_done(desc, walk, nbytes);
+	}
+
+	return err;
+}
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, ctx->enc_expkey);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return ecb_crypt(desc, &walk, ctx->dec_expkey);
+}
+
+static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 *iv = (u64 *)walk->iv;
+
+	do {
+		*dst = *src ^ *iv;
+		des3_ede_enc_blk(ctx, (u8 *)dst, (u8 *)dst);
+		iv = dst;
+
+		src += 1;
+		dst += 1;
+		nbytes -= bsize;
+	} while (nbytes >= bsize);
+
+	*(u64 *)walk->iv = *iv;
+	return nbytes;
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_encrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
+				  struct blkcipher_walk *walk)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	u64 *src = (u64 *)walk->src.virt.addr;
+	u64 *dst = (u64 *)walk->dst.virt.addr;
+	u64 ivs[3 - 1];
+	u64 last_iv;
+
+	/* Start of the last block. */
+	src += nbytes / bsize - 1;
+	dst += nbytes / bsize - 1;
+
+	last_iv = *src;
+
+	/* Process four block batch */
+	if (nbytes >= bsize * 3) {
+		do {
+			nbytes -= bsize * 3 - bsize;
+			src -= 3 - 1;
+			dst -= 3 - 1;
+
+			ivs[0] = src[0];
+			ivs[1] = src[1];
+
+			des3_ede_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src);
+
+			dst[1] ^= ivs[0];
+			dst[2] ^= ivs[1];
+
+			nbytes -= bsize;
+			if (nbytes < bsize)
+				goto done;
+
+			*dst ^= *(src - 1);
+			src -= 1;
+			dst -= 1;
+		} while (nbytes >= bsize * 3);
+	}
+
+	/* Handle leftovers */
+	for (;;) {
+		des3_ede_dec_blk(ctx, (u8 *)dst, (u8 *)src);
+
+		nbytes -= bsize;
+		if (nbytes < bsize)
+			break;
+
+		*dst ^= *(src - 1);
+		src -= 1;
+		dst -= 1;
+	}
+
+done:
+	*dst ^= *(u64 *)walk->iv;
+	*(u64 *)walk->iv = last_iv;
+
+	return nbytes;
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __cbc_decrypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+
+static void ctr_crypt_final(struct des3_ede_x86_ctx *ctx,
+			    struct blkcipher_walk *walk)
+{
+	u8 *ctrblk = walk->iv;
+	u8 keystream[DES3_EDE_BLOCK_SIZE];
+	u8 *src = walk->src.virt.addr;
+	u8 *dst = walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+
+	des3_ede_enc_blk(ctx, keystream, ctrblk);
+	crypto_xor(keystream, src, nbytes);
+	memcpy(dst, keystream, nbytes);
+
+	crypto_inc(ctrblk, DES3_EDE_BLOCK_SIZE);
+}
+
+static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
+				struct blkcipher_walk *walk)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int bsize = DES3_EDE_BLOCK_SIZE;
+	unsigned int nbytes = walk->nbytes;
+	__be64 *src = (__be64 *)walk->src.virt.addr;
+	__be64 *dst = (__be64 *)walk->dst.virt.addr;
+	u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv);
+	__be64 ctrblocks[3];
+
+	/* Process four block batch */
+	if (nbytes >= bsize * 3) {
+		do {
+			/* create ctrblks for parallel encrypt */
+			ctrblocks[0] = cpu_to_be64(ctrblk++);
+			ctrblocks[1] = cpu_to_be64(ctrblk++);
+			ctrblocks[2] = cpu_to_be64(ctrblk++);
+
+			des3_ede_enc_blk_3way(ctx, (u8 *)ctrblocks,
+					      (u8 *)ctrblocks);
+
+			dst[0] = src[0] ^ ctrblocks[0];
+			dst[1] = src[1] ^ ctrblocks[1];
+			dst[2] = src[2] ^ ctrblocks[2];
+
+			src += 3;
+			dst += 3;
+		} while ((nbytes -= bsize * 3) >= bsize * 3);
+
+		if (nbytes < bsize)
+			goto done;
+	}
+
+	/* Handle leftovers */
+	do {
+		ctrblocks[0] = cpu_to_be64(ctrblk++);
+
+		des3_ede_enc_blk(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
+
+		dst[0] = src[0] ^ ctrblocks[0];
+
+		src += 1;
+		dst += 1;
+	} while ((nbytes -= bsize) >= bsize);
+
+done:
+	*(__be64 *)walk->iv = cpu_to_be64(ctrblk);
+	return nbytes;
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, DES3_EDE_BLOCK_SIZE);
+
+	while ((nbytes = walk.nbytes) >= DES3_EDE_BLOCK_SIZE) {
+		nbytes = __ctr_crypt(desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	if (walk.nbytes) {
+		ctr_crypt_final(crypto_blkcipher_ctx(desc->tfm), &walk);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+
+static int des3_ede_x86_setkey(struct crypto_tfm *tfm, const u8 *key,
+			       unsigned int keylen)
+{
+	struct des3_ede_x86_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 i, j, tmp;
+	int err;
+
+	/* Generate encryption context using generic implementation. */
+	err = __des3_ede_setkey(ctx->enc_expkey, &tfm->crt_flags, key, keylen);
+	if (err < 0)
+		return err;
+
+	/* Fix encryption context for this implementation and form decryption
+	 * context. */
+	j = DES3_EDE_EXPKEY_WORDS - 2;
+	for (i = 0; i < DES3_EDE_EXPKEY_WORDS; i += 2, j -= 2) {
+		tmp = ror32(ctx->enc_expkey[i + 1], 4);
+		ctx->enc_expkey[i + 1] = tmp;
+
+		ctx->dec_expkey[j + 0] = ctx->enc_expkey[i + 0];
+		ctx->dec_expkey[j + 1] = tmp;
+	}
+
+	return 0;
+}
+
+static struct crypto_alg des3_ede_algs[4] = { {
+	.cra_name		= "des3_ede",
+	.cra_driver_name	= "des3_ede-asm",
+	.cra_priority		= 200,
+	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
+	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.cipher = {
+			.cia_min_keysize	= DES3_EDE_KEY_SIZE,
+			.cia_max_keysize	= DES3_EDE_KEY_SIZE,
+			.cia_setkey		= des3_ede_x86_setkey,
+			.cia_encrypt		= des3_ede_x86_encrypt,
+			.cia_decrypt		= des3_ede_x86_decrypt,
+		}
+	}
+}, {
+	.cra_name		= "ecb(des3_ede)",
+	.cra_driver_name	= "ecb-des3_ede-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.setkey		= des3_ede_x86_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(des3_ede)",
+	.cra_driver_name	= "cbc-des3_ede-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= DES3_EDE_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES3_EDE_BLOCK_SIZE,
+			.setkey		= des3_ede_x86_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(des3_ede)",
+	.cra_driver_name	= "ctr-des3_ede-asm",
+	.cra_priority		= 300,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct des3_ede_x86_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= DES3_EDE_KEY_SIZE,
+			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.ivsize		= DES3_EDE_BLOCK_SIZE,
+			.setkey		= des3_ede_x86_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+} };
+
+static bool is_blacklisted_cpu(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (boot_cpu_data.x86 == 0x0f) {
+		/*
+		 * On Pentium 4, des3_ede-x86_64 is slower than generic C
+		 * implementation because use of 64bit rotates (which are really
+		 * slow on P4). Therefore blacklist P4s.
+		 */
+		return true;
+	}
+
+	return false;
+}
+
+static int force;
+module_param(force, int, 0);
+MODULE_PARM_DESC(force, "Force module load, ignore CPU blacklist");
+
+static int __init des3_ede_x86_init(void)
+{
+	if (!force && is_blacklisted_cpu()) {
+		pr_info("des3_ede-x86_64: performance on this CPU would be suboptimal: disabling des3_ede-x86_64.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(des3_ede_algs, ARRAY_SIZE(des3_ede_algs));
+}
+
+static void __exit des3_ede_x86_fini(void)
+{
+	crypto_unregister_algs(des3_ede_algs, ARRAY_SIZE(des3_ede_algs));
+}
+
+module_init(des3_ede_x86_init);
+module_exit(des3_ede_x86_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-asm");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-asm");
+MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");

arch/x86/crypto/fpu.c

@@ -0,0 +1,164 @@
+/*
+ * FPU: Wrapper for blkcipher touching fpu
+ *
+ * Copyright (c) Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/algapi.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/crypto.h>
+#include <asm/i387.h>
+
+struct crypto_fpu_ctx {
+	struct crypto_blkcipher *child;
+};
+
+static int crypto_fpu_setkey(struct crypto_tfm *parent, const u8 *key,
+			     unsigned int keylen)
+{
+	struct crypto_fpu_ctx *ctx = crypto_tfm_ctx(parent);
+	struct crypto_blkcipher *child = ctx->child;
+	int err;
+
+	crypto_blkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_blkcipher_set_flags(child, crypto_tfm_get_flags(parent) &
+				   CRYPTO_TFM_REQ_MASK);
+	err = crypto_blkcipher_setkey(child, key, keylen);
+	crypto_tfm_set_flags(parent, crypto_blkcipher_get_flags(child) &
+				     CRYPTO_TFM_RES_MASK);
+	return err;
+}
+
+static int crypto_fpu_encrypt(struct blkcipher_desc *desc_in,
+			      struct scatterlist *dst, struct scatterlist *src,
+			      unsigned int nbytes)
+{
+	int err;
+	struct crypto_fpu_ctx *ctx = crypto_blkcipher_ctx(desc_in->tfm);
+	struct crypto_blkcipher *child = ctx->child;
+	struct blkcipher_desc desc = {
+		.tfm = child,
+		.info = desc_in->info,
+		.flags = desc_in->flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
+	};
+
+	kernel_fpu_begin();
+	err = crypto_blkcipher_crt(desc.tfm)->encrypt(&desc, dst, src, nbytes);
+	kernel_fpu_end();
+	return err;
+}
+
+static int crypto_fpu_decrypt(struct blkcipher_desc *desc_in,
+			      struct scatterlist *dst, struct scatterlist *src,
+			      unsigned int nbytes)
+{
+	int err;
+	struct crypto_fpu_ctx *ctx = crypto_blkcipher_ctx(desc_in->tfm);
+	struct crypto_blkcipher *child = ctx->child;
+	struct blkcipher_desc desc = {
+		.tfm = child,
+		.info = desc_in->info,
+		.flags = desc_in->flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
+	};
+
+	kernel_fpu_begin();
+	err = crypto_blkcipher_crt(desc.tfm)->decrypt(&desc, dst, src, nbytes);
+	kernel_fpu_end();
+	return err;
+}
+
+static int crypto_fpu_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
+	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
+	struct crypto_fpu_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_blkcipher *cipher;
+
+	cipher = crypto_spawn_blkcipher(spawn);
+	if (IS_ERR(cipher))
+		return PTR_ERR(cipher);
+
+	ctx->child = cipher;
+	return 0;
+}
+
+static void crypto_fpu_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_fpu_ctx *ctx = crypto_tfm_ctx(tfm);
+	crypto_free_blkcipher(ctx->child);
+}
+
+static struct crypto_instance *crypto_fpu_alloc(struct rtattr **tb)
+{
+	struct crypto_instance *inst;
+	struct crypto_alg *alg;
+	int err;
+
+	err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_BLKCIPHER);
+	if (err)
+		return ERR_PTR(err);
+
+	alg = crypto_get_attr_alg(tb, CRYPTO_ALG_TYPE_BLKCIPHER,
+				  CRYPTO_ALG_TYPE_MASK);
+	if (IS_ERR(alg))
+		return ERR_CAST(alg);
+
+	inst = crypto_alloc_instance("fpu", alg);
+	if (IS_ERR(inst))
+		goto out_put_alg;
+
+	inst->alg.cra_flags = alg->cra_flags;
+	inst->alg.cra_priority = alg->cra_priority;
+	inst->alg.cra_blocksize = alg->cra_blocksize;
+	inst->alg.cra_alignmask = alg->cra_alignmask;
+	inst->alg.cra_type = alg->cra_type;
+	inst->alg.cra_blkcipher.ivsize = alg->cra_blkcipher.ivsize;
+	inst->alg.cra_blkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
+	inst->alg.cra_blkcipher.max_keysize = alg->cra_blkcipher.max_keysize;
+	inst->alg.cra_ctxsize = sizeof(struct crypto_fpu_ctx);
+	inst->alg.cra_init = crypto_fpu_init_tfm;
+	inst->alg.cra_exit = crypto_fpu_exit_tfm;
+	inst->alg.cra_blkcipher.setkey = crypto_fpu_setkey;
+	inst->alg.cra_blkcipher.encrypt = crypto_fpu_encrypt;
+	inst->alg.cra_blkcipher.decrypt = crypto_fpu_decrypt;
+
+out_put_alg:
+	crypto_mod_put(alg);
+	return inst;
+}
+
+static void crypto_fpu_free(struct crypto_instance *inst)
+{
+	crypto_drop_spawn(crypto_instance_ctx(inst));
+	kfree(inst);
+}
+
+static struct crypto_template crypto_fpu_tmpl = {
+	.name = "fpu",
+	.alloc = crypto_fpu_alloc,
+	.free = crypto_fpu_free,
+	.module = THIS_MODULE,
+};
+
+int __init crypto_fpu_init(void)
+{
+	return crypto_register_template(&crypto_fpu_tmpl);
+}
+
+void __exit crypto_fpu_exit(void)
+{
+	crypto_unregister_template(&crypto_fpu_tmpl);
+}
+
+MODULE_ALIAS_CRYPTO("fpu");

arch/x86/crypto/ghash-clmulni-intel_asm.S

@@ -0,0 +1,132 @@
+/*
+ * Accelerated GHASH implementation with Intel PCLMULQDQ-NI
+ * instructions. This file contains accelerated part of ghash
+ * implementation. More information about PCLMULQDQ can be found at:
+ *
+ * http://software.intel.com/en-us/articles/carry-less-multiplication-and-its-usage-for-computing-the-gcm-mode/
+ *
+ * Copyright (c) 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *	     Vinodh Gopal
+ *	     Erdinc Ozturk
+ *	     Deniz Karakoyunlu
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/inst.h>
+
+.data
+
+.align 16
+.Lbswap_mask:
+	.octa 0x000102030405060708090a0b0c0d0e0f
+
+#define DATA	%xmm0
+#define SHASH	%xmm1
+#define T1	%xmm2
+#define T2	%xmm3
+#define T3	%xmm4
+#define BSWAP	%xmm5
+#define IN1	%xmm6
+
+.text
+
+/*
+ * __clmul_gf128mul_ble:	internal ABI
+ * input:
+ *	DATA:			operand1
+ *	SHASH:			operand2, hash_key << 1 mod poly
+ * output:
+ *	DATA:			operand1 * operand2 mod poly
+ * changed:
+ *	T1
+ *	T2
+ *	T3
+ */
+__clmul_gf128mul_ble:
+	movaps DATA, T1
+	pshufd $0b01001110, DATA, T2
+	pshufd $0b01001110, SHASH, T3
+	pxor DATA, T2
+	pxor SHASH, T3
+
+	PCLMULQDQ 0x00 SHASH DATA	# DATA = a0 * b0
+	PCLMULQDQ 0x11 SHASH T1		# T1 = a1 * b1
+	PCLMULQDQ 0x00 T3 T2		# T2 = (a1 + a0) * (b1 + b0)
+	pxor DATA, T2
+	pxor T1, T2			# T2 = a0 * b1 + a1 * b0
+
+	movaps T2, T3
+	pslldq $8, T3
+	psrldq $8, T2
+	pxor T3, DATA
+	pxor T2, T1			# <T1:DATA> is result of
+					# carry-less multiplication
+
+	# first phase of the reduction
+	movaps DATA, T3
+	psllq $1, T3
+	pxor DATA, T3
+	psllq $5, T3
+	pxor DATA, T3
+	psllq $57, T3
+	movaps T3, T2
+	pslldq $8, T2
+	psrldq $8, T3
+	pxor T2, DATA
+	pxor T3, T1
+
+	# second phase of the reduction
+	movaps DATA, T2
+	psrlq $5, T2
+	pxor DATA, T2
+	psrlq $1, T2
+	pxor DATA, T2
+	psrlq $1, T2
+	pxor T2, T1
+	pxor T1, DATA
+	ret
+ENDPROC(__clmul_gf128mul_ble)
+
+/* void clmul_ghash_mul(char *dst, const u128 *shash) */
+ENTRY(clmul_ghash_mul)
+	movups (%rdi), DATA
+	movups (%rsi), SHASH
+	movaps .Lbswap_mask, BSWAP
+	PSHUFB_XMM BSWAP DATA
+	call __clmul_gf128mul_ble
+	PSHUFB_XMM BSWAP DATA
+	movups DATA, (%rdi)
+	ret
+ENDPROC(clmul_ghash_mul)
+
+/*
+ * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
+ *			   const u128 *shash);
+ */
+ENTRY(clmul_ghash_update)
+	cmp $16, %rdx
+	jb .Lupdate_just_ret	# check length
+	movaps .Lbswap_mask, BSWAP
+	movups (%rdi), DATA
+	movups (%rcx), SHASH
+	PSHUFB_XMM BSWAP DATA
+.align 4
+.Lupdate_loop:
+	movups (%rsi), IN1
+	PSHUFB_XMM BSWAP IN1
+	pxor IN1, DATA
+	call __clmul_gf128mul_ble
+	sub $16, %rdx
+	add $16, %rsi
+	cmp $16, %rdx
+	jge .Lupdate_loop
+	PSHUFB_XMM BSWAP DATA
+	movups DATA, (%rdi)
+.Lupdate_just_ret:
+	ret
+ENDPROC(clmul_ghash_update)

arch/x86/crypto/ghash-clmulni-intel_glue.c

@@ -0,0 +1,344 @@
+/*
+ * Accelerated GHASH implementation with Intel PCLMULQDQ-NI
+ * instructions. This file contains glue code.
+ *
+ * Copyright (c) 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
+#include <crypto/cryptd.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/hash.h>
+#include <asm/i387.h>
+#include <asm/cpu_device_id.h>
+
+#define GHASH_BLOCK_SIZE	16
+#define GHASH_DIGEST_SIZE	16
+
+void clmul_ghash_mul(char *dst, const u128 *shash);
+
+void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
+			const u128 *shash);
+
+struct ghash_async_ctx {
+	struct cryptd_ahash *cryptd_tfm;
+};
+
+struct ghash_ctx {
+	u128 shash;
+};
+
+struct ghash_desc_ctx {
+	u8 buffer[GHASH_BLOCK_SIZE];
+	u32 bytes;
+};
+
+static int ghash_init(struct shash_desc *desc)
+{
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	memset(dctx, 0, sizeof(*dctx));
+
+	return 0;
+}
+
+static int ghash_setkey(struct crypto_shash *tfm,
+			const u8 *key, unsigned int keylen)
+{
+	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+	be128 *x = (be128 *)key;
+	u64 a, b;
+
+	if (keylen != GHASH_BLOCK_SIZE) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	/* perform multiplication by 'x' in GF(2^128) */
+	a = be64_to_cpu(x->a);
+	b = be64_to_cpu(x->b);
+
+	ctx->shash.a = (b << 1) | (a >> 63);
+	ctx->shash.b = (a << 1) | (b >> 63);
+
+	if (a >> 63)
+		ctx->shash.b ^= ((u64)0xc2) << 56;
+
+	return 0;
+}
+
+static int ghash_update(struct shash_desc *desc,
+			 const u8 *src, unsigned int srclen)
+{
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	u8 *dst = dctx->buffer;
+
+	kernel_fpu_begin();
+	if (dctx->bytes) {
+		int n = min(srclen, dctx->bytes);
+		u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
+
+		dctx->bytes -= n;
+		srclen -= n;
+
+		while (n--)
+			*pos++ ^= *src++;
+
+		if (!dctx->bytes)
+			clmul_ghash_mul(dst, &ctx->shash);
+	}
+
+	clmul_ghash_update(dst, src, srclen, &ctx->shash);
+	kernel_fpu_end();
+
+	if (srclen & 0xf) {
+		src += srclen - (srclen & 0xf);
+		srclen &= 0xf;
+		dctx->bytes = GHASH_BLOCK_SIZE - srclen;
+		while (srclen--)
+			*dst++ ^= *src++;
+	}
+
+	return 0;
+}
+
+static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+{
+	u8 *dst = dctx->buffer;
+
+	if (dctx->bytes) {
+		u8 *tmp = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
+
+		while (dctx->bytes--)
+			*tmp++ ^= 0;
+
+		kernel_fpu_begin();
+		clmul_ghash_mul(dst, &ctx->shash);
+		kernel_fpu_end();
+	}
+
+	dctx->bytes = 0;
+}
+
+static int ghash_final(struct shash_desc *desc, u8 *dst)
+{
+	struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
+	struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
+	u8 *buf = dctx->buffer;
+
+	ghash_flush(ctx, dctx);
+	memcpy(dst, buf, GHASH_BLOCK_SIZE);
+
+	return 0;
+}
+
+static struct shash_alg ghash_alg = {
+	.digestsize	= GHASH_DIGEST_SIZE,
+	.init		= ghash_init,
+	.update		= ghash_update,
+	.final		= ghash_final,
+	.setkey		= ghash_setkey,
+	.descsize	= sizeof(struct ghash_desc_ctx),
+	.base		= {
+		.cra_name		= "__ghash",
+		.cra_driver_name	= "__ghash-pclmulqdqni",
+		.cra_priority		= 0,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= GHASH_BLOCK_SIZE,
+		.cra_ctxsize		= sizeof(struct ghash_ctx),
+		.cra_module		= THIS_MODULE,
+	},
+};
+
+static int ghash_async_init(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!irq_fpu_usable()) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_init(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+		desc->tfm = child;
+		desc->flags = req->base.flags;
+		return crypto_shash_init(desc);
+	}
+}
+
+static int ghash_async_update(struct ahash_request *req)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+
+	if (!irq_fpu_usable()) {
+		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_update(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		return shash_ahash_update(req, desc);
+	}
+}
+
+static int ghash_async_final(struct ahash_request *req)
+{
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+
+	if (!irq_fpu_usable()) {
+		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_final(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		return crypto_shash_final(desc, req->result);
+	}
+}
+
+static int ghash_async_digest(struct ahash_request *req)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+
+	if (!irq_fpu_usable()) {
+		memcpy(cryptd_req, req, sizeof(*req));
+		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
+		return crypto_ahash_digest(cryptd_req);
+	} else {
+		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
+
+		desc->tfm = child;
+		desc->flags = req->base.flags;
+		return shash_ahash_digest(req, desc);
+	}
+}
+
+static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct crypto_ahash *child = &ctx->cryptd_tfm->base;
+	int err;
+
+	crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
+			       & CRYPTO_TFM_REQ_MASK);
+	err = crypto_ahash_setkey(child, key, keylen);
+	crypto_ahash_set_flags(tfm, crypto_ahash_get_flags(child)
+			       & CRYPTO_TFM_RES_MASK);
+
+	return err;
+}
+
+static int ghash_async_init_tfm(struct crypto_tfm *tfm)
+{
+	struct cryptd_ahash *cryptd_tfm;
+	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_tfm = cryptd_alloc_ahash("__ghash-pclmulqdqni", 0, 0);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+	ctx->cryptd_tfm = cryptd_tfm;
+	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+				 sizeof(struct ahash_request) +
+				 crypto_ahash_reqsize(&cryptd_tfm->base));
+
+	return 0;
+}
+
+static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_free_ahash(ctx->cryptd_tfm);
+}
+
+static struct ahash_alg ghash_async_alg = {
+	.init		= ghash_async_init,
+	.update		= ghash_async_update,
+	.final		= ghash_async_final,
+	.setkey		= ghash_async_setkey,
+	.digest		= ghash_async_digest,
+	.halg = {
+		.digestsize	= GHASH_DIGEST_SIZE,
+		.base = {
+			.cra_name		= "ghash",
+			.cra_driver_name	= "ghash-clmulni",
+			.cra_priority		= 400,
+			.cra_flags		= CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_blocksize		= GHASH_BLOCK_SIZE,
+			.cra_type		= &crypto_ahash_type,
+			.cra_module		= THIS_MODULE,
+			.cra_init		= ghash_async_init_tfm,
+			.cra_exit		= ghash_async_exit_tfm,
+		},
+	},
+};
+
+static const struct x86_cpu_id pcmul_cpu_id[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ), /* Pickle-Mickle-Duck */
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id);
+
+static int __init ghash_pclmulqdqni_mod_init(void)
+{
+	int err;
+
+	if (!x86_match_cpu(pcmul_cpu_id))
+		return -ENODEV;
+
+	err = crypto_register_shash(&ghash_alg);
+	if (err)
+		goto err_out;
+	err = crypto_register_ahash(&ghash_async_alg);
+	if (err)
+		goto err_shash;
+
+	return 0;
+
+err_shash:
+	crypto_unregister_shash(&ghash_alg);
+err_out:
+	return err;
+}
+
+static void __exit ghash_pclmulqdqni_mod_exit(void)
+{
+	crypto_unregister_ahash(&ghash_async_alg);
+	crypto_unregister_shash(&ghash_alg);
+}
+
+module_init(ghash_pclmulqdqni_mod_init);
+module_exit(ghash_pclmulqdqni_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
+		   "acclerated by PCLMULQDQ-NI");
+MODULE_ALIAS_CRYPTO("ghash");

arch/x86/crypto/glue_helper-asm-avx.S

@@ -0,0 +1,150 @@
+/*
+ * Shared glue code for 128bit block ciphers, AVX assembler macros
+ *
+ * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define load_8way(src, x0, x1, x2, x3, x4, x5, x6, x7) \
+	vmovdqu (0*16)(src), x0; \
+	vmovdqu (1*16)(src), x1; \
+	vmovdqu (2*16)(src), x2; \
+	vmovdqu (3*16)(src), x3; \
+	vmovdqu (4*16)(src), x4; \
+	vmovdqu (5*16)(src), x5; \
+	vmovdqu (6*16)(src), x6; \
+	vmovdqu (7*16)(src), x7;
+
+#define store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \
+	vmovdqu x0, (0*16)(dst); \
+	vmovdqu x1, (1*16)(dst); \
+	vmovdqu x2, (2*16)(dst); \
+	vmovdqu x3, (3*16)(dst); \
+	vmovdqu x4, (4*16)(dst); \
+	vmovdqu x5, (5*16)(dst); \
+	vmovdqu x6, (6*16)(dst); \
+	vmovdqu x7, (7*16)(dst);
+
+#define store_cbc_8way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \
+	vpxor (0*16)(src), x1, x1; \
+	vpxor (1*16)(src), x2, x2; \
+	vpxor (2*16)(src), x3, x3; \
+	vpxor (3*16)(src), x4, x4; \
+	vpxor (4*16)(src), x5, x5; \
+	vpxor (5*16)(src), x6, x6; \
+	vpxor (6*16)(src), x7, x7; \
+	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
+
+#define inc_le128(x, minus_one, tmp) \
+	vpcmpeqq minus_one, x, tmp; \
+	vpsubq minus_one, x, x; \
+	vpslldq $8, tmp, tmp; \
+	vpsubq tmp, x, x;
+
+#define load_ctr_8way(iv, bswap, x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2) \
+	vpcmpeqd t0, t0, t0; \
+	vpsrldq $8, t0, t0; /* low: -1, high: 0 */ \
+	vmovdqa bswap, t1; \
+	\
+	/* load IV and byteswap */ \
+	vmovdqu (iv), x7; \
+	vpshufb t1, x7, x0; \
+	\
+	/* construct IVs */ \
+	inc_le128(x7, t0, t2); \
+	vpshufb t1, x7, x1; \
+	inc_le128(x7, t0, t2); \
+	vpshufb t1, x7, x2; \
+	inc_le128(x7, t0, t2); \
+	vpshufb t1, x7, x3; \
+	inc_le128(x7, t0, t2); \
+	vpshufb t1, x7, x4; \
+	inc_le128(x7, t0, t2); \
+	vpshufb t1, x7, x5; \
+	inc_le128(x7, t0, t2); \
+	vpshufb t1, x7, x6; \
+	inc_le128(x7, t0, t2); \
+	vmovdqa x7, t2; \
+	vpshufb t1, x7, x7; \
+	inc_le128(t2, t0, t1); \
+	vmovdqu t2, (iv);
+
+#define store_ctr_8way(src, dst, x0, x1, x2, x3, x4, x5, x6, x7) \
+	vpxor (0*16)(src), x0, x0; \
+	vpxor (1*16)(src), x1, x1; \
+	vpxor (2*16)(src), x2, x2; \
+	vpxor (3*16)(src), x3, x3; \
+	vpxor (4*16)(src), x4, x4; \
+	vpxor (5*16)(src), x5, x5; \
+	vpxor (6*16)(src), x6, x6; \
+	vpxor (7*16)(src), x7, x7; \
+	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);
+
+#define gf128mul_x_ble(iv, mask, tmp) \
+	vpsrad $31, iv, tmp; \
+	vpaddq iv, iv, iv; \
+	vpshufd $0x13, tmp, tmp; \
+	vpand mask, tmp, tmp; \
+	vpxor tmp, iv, iv;
+
+#define load_xts_8way(iv, src, dst, x0, x1, x2, x3, x4, x5, x6, x7, tiv, t0, \
+		      t1, xts_gf128mul_and_shl1_mask) \
+	vmovdqa xts_gf128mul_and_shl1_mask, t0; \
+	\
+	/* load IV */ \
+	vmovdqu (iv), tiv; \
+	vpxor (0*16)(src), tiv, x0; \
+	vmovdqu tiv, (0*16)(dst); \
+	\
+	/* construct and store IVs, also xor with source */ \
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (1*16)(src), tiv, x1; \
+	vmovdqu tiv, (1*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (2*16)(src), tiv, x2; \
+	vmovdqu tiv, (2*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (3*16)(src), tiv, x3; \
+	vmovdqu tiv, (3*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (4*16)(src), tiv, x4; \
+	vmovdqu tiv, (4*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (5*16)(src), tiv, x5; \
+	vmovdqu tiv, (5*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (6*16)(src), tiv, x6; \
+	vmovdqu tiv, (6*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vpxor (7*16)(src), tiv, x7; \
+	vmovdqu tiv, (7*16)(dst); \
+	\
+	gf128mul_x_ble(tiv, t0, t1); \
+	vmovdqu tiv, (iv);
+
+#define store_xts_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7) \
+	vpxor (0*16)(dst), x0, x0; \
+	vpxor (1*16)(dst), x1, x1; \
+	vpxor (2*16)(dst), x2, x2; \
+	vpxor (3*16)(dst), x3, x3; \
+	vpxor (4*16)(dst), x4, x4; \
+	vpxor (5*16)(dst), x5, x5; \
+	vpxor (6*16)(dst), x6, x6; \
+	vpxor (7*16)(dst), x7, x7; \
+	store_8way(dst, x0, x1, x2, x3, x4, x5, x6, x7);