summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig127
-rw-r--r--arch/x86/Kconfig.cpu5
-rw-r--r--arch/x86/Makefile2
-rw-r--r--arch/x86/boot/Makefile4
-rw-r--r--arch/x86/boot/compressed/Makefile3
-rw-r--r--arch/x86/boot/compressed/eboot.c34
-rw-r--r--arch/x86/boot/compressed/eboot.h4
-rw-r--r--arch/x86/boot/header.S4
-rw-r--r--arch/x86/boot/mkcpustr.c2
-rw-r--r--arch/x86/configs/i386_defconfig23
-rw-r--r--arch/x86/configs/x86_64_defconfig23
-rw-r--r--arch/x86/crypto/Makefile4
-rw-r--r--arch/x86/crypto/aes_glue.c1
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c258
-rw-r--r--arch/x86/crypto/blowfish_glue.c4
-rw-r--r--arch/x86/crypto/camellia_glue.c1382
-rw-r--r--arch/x86/crypto/cast5-avx-x86_64-asm_64.S376
-rw-r--r--arch/x86/crypto/cast5_avx_glue.c530
-rw-r--r--arch/x86/crypto/cast6-avx-x86_64-asm_64.S383
-rw-r--r--arch/x86/crypto/cast6_avx_glue.c648
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_glue.c2
-rw-r--r--arch/x86/crypto/glue_helper.c2
-rw-r--r--arch/x86/crypto/salsa20_glue.c1
-rw-r--r--arch/x86/crypto/serpent_avx_glue.c10
-rw-r--r--arch/x86/crypto/serpent_sse2_glue.c10
-rw-r--r--arch/x86/crypto/twofish-avx-x86_64-asm_64.S227
-rw-r--r--arch/x86/crypto/twofish_avx_glue.c10
-rw-r--r--arch/x86/crypto/twofish_glue.c1
-rw-r--r--arch/x86/crypto/twofish_glue_3way.c5
-rw-r--r--arch/x86/ia32/ia32_signal.c31
-rw-r--r--arch/x86/ia32/ia32entry.S6
-rw-r--r--arch/x86/ia32/sys_ia32.c2
-rw-r--r--arch/x86/include/asm/Kbuild4
-rw-r--r--arch/x86/include/asm/alternative-asm.h9
-rw-r--r--arch/x86/include/asm/alternative.h36
-rw-r--r--arch/x86/include/asm/apic.h2
-rw-r--r--arch/x86/include/asm/atomic.h4
-rw-r--r--arch/x86/include/asm/bitops.h14
-rw-r--r--arch/x86/include/asm/calling.h50
-rw-r--r--arch/x86/include/asm/checksum.h4
-rw-r--r--arch/x86/include/asm/cmpxchg.h4
-rw-r--r--arch/x86/include/asm/compat.h74
-rw-r--r--arch/x86/include/asm/cpufeature.h6
-rw-r--r--arch/x86/include/asm/fpu-internal.h422
-rw-r--r--arch/x86/include/asm/ftrace.h56
-rw-r--r--arch/x86/include/asm/futex.h19
-rw-r--r--arch/x86/include/asm/hardirq.h4
-rw-r--r--arch/x86/include/asm/hpet.h2
-rw-r--r--arch/x86/include/asm/i387.h29
-rw-r--r--arch/x86/include/asm/ia32.h67
-rw-r--r--arch/x86/include/asm/iommu_table.h6
-rw-r--r--arch/x86/include/asm/kprobes.h1
-rw-r--r--arch/x86/include/asm/kvm.h17
-rw-r--r--arch/x86/include/asm/kvm_emulate.h48
-rw-r--r--arch/x86/include/asm/kvm_host.h52
-rw-r--r--arch/x86/include/asm/kvm_para.h6
-rw-r--r--arch/x86/include/asm/mce.h13
-rw-r--r--arch/x86/include/asm/microcode.h10
-rw-r--r--arch/x86/include/asm/mmzone.h4
-rw-r--r--arch/x86/include/asm/msr-index.h3
-rw-r--r--arch/x86/include/asm/mutex.h4
-rw-r--r--arch/x86/include/asm/numa.h4
-rw-r--r--arch/x86/include/asm/pci.h2
-rw-r--r--arch/x86/include/asm/perf_event.h2
-rw-r--r--arch/x86/include/asm/perf_regs.h33
-rw-r--r--arch/x86/include/asm/pgtable.h4
-rw-r--r--arch/x86/include/asm/pgtable_types.h10
-rw-r--r--arch/x86/include/asm/posix_types.h10
-rw-r--r--arch/x86/include/asm/processor-flags.h1
-rw-r--r--arch/x86/include/asm/processor.h3
-rw-r--r--arch/x86/include/asm/rcu.h32
-rw-r--r--arch/x86/include/asm/seccomp.h4
-rw-r--r--arch/x86/include/asm/signal.h4
-rw-r--r--arch/x86/include/asm/smap.h91
-rw-r--r--arch/x86/include/asm/string.h4
-rw-r--r--arch/x86/include/asm/suspend.h4
-rw-r--r--arch/x86/include/asm/svm.h205
-rw-r--r--arch/x86/include/asm/sys_ia32.h2
-rw-r--r--arch/x86/include/asm/thread_info.h10
-rw-r--r--arch/x86/include/asm/uaccess.h32
-rw-r--r--arch/x86/include/asm/uaccess_32.h3
-rw-r--r--arch/x86/include/asm/uaccess_64.h3
-rw-r--r--arch/x86/include/asm/uprobes.h3
-rw-r--r--arch/x86/include/asm/user.h4
-rw-r--r--arch/x86/include/asm/vdso.h3
-rw-r--r--arch/x86/include/asm/vmx.h127
-rw-r--r--arch/x86/include/asm/x86_init.h9
-rw-r--r--arch/x86/include/asm/xen/interface.h12
-rw-r--r--arch/x86/include/asm/xen/page.h3
-rw-r--r--arch/x86/include/asm/xen/swiotlb-xen.h2
-rw-r--r--arch/x86/include/asm/xor.h4
-rw-r--r--arch/x86/include/asm/xor_32.h58
-rw-r--r--arch/x86/include/asm/xor_64.h63
-rw-r--r--arch/x86/include/asm/xor_avx.h54
-rw-r--r--arch/x86/include/asm/xsave.h23
-rw-r--r--arch/x86/include/uapi/asm/Kbuild6
-rw-r--r--arch/x86/kernel/Makefile5
-rw-r--r--arch/x86/kernel/acpi/boot.c2
-rw-r--r--arch/x86/kernel/acpi/sleep.c15
-rw-r--r--arch/x86/kernel/alternative.c111
-rw-r--r--arch/x86/kernel/apic/apic.c2
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c4
-rw-r--r--arch/x86/kernel/cpu/amd.c67
-rw-r--r--arch/x86/kernel/cpu/bugs.c7
-rw-r--r--arch/x86/kernel/cpu/common.c63
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c8
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h12
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c94
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c168
-rw-r--r--arch/x86/kernel/cpu/mkcapflags.pl5
-rw-r--r--arch/x86/kernel/cpu/perf_event.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c25
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c14
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c36
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h6
-rw-r--r--arch/x86/kernel/cpu/proc.c5
-rw-r--r--arch/x86/kernel/cpuid.c5
-rw-r--r--arch/x86/kernel/devicetree.c51
-rw-r--r--arch/x86/kernel/entry_32.S100
-rw-r--r--arch/x86/kernel/entry_64.S172
-rw-r--r--arch/x86/kernel/ftrace.c73
-rw-r--r--arch/x86/kernel/head_32.S31
-rw-r--r--arch/x86/kernel/i387.c292
-rw-r--r--arch/x86/kernel/i8259.c2
-rw-r--r--arch/x86/kernel/irq.c4
-rw-r--r--arch/x86/kernel/kprobes.c67
-rw-r--r--arch/x86/kernel/kvm.c3
-rw-r--r--arch/x86/kernel/microcode_amd.c357
-rw-r--r--arch/x86/kernel/microcode_core.c70
-rw-r--r--arch/x86/kernel/microcode_intel.c3
-rw-r--r--arch/x86/kernel/msr.c5
-rw-r--r--arch/x86/kernel/perf_regs.c105
-rw-r--r--arch/x86/kernel/probe_roms.c2
-rw-r--r--arch/x86/kernel/process.c22
-rw-r--r--arch/x86/kernel/process_32.c4
-rw-r--r--arch/x86/kernel/process_64.c4
-rw-r--r--arch/x86/kernel/ptrace.c8
-rw-r--r--arch/x86/kernel/rtc.c2
-rw-r--r--arch/x86/kernel/setup.c6
-rw-r--r--arch/x86/kernel/signal.c231
-rw-r--r--arch/x86/kernel/smpboot.c20
-rw-r--r--arch/x86/kernel/step.c53
-rw-r--r--arch/x86/kernel/traps.c174
-rw-r--r--arch/x86/kernel/uprobes.c52
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c6
-rw-r--r--arch/x86/kernel/x86_init.c4
-rw-r--r--arch/x86/kernel/xsave.c517
-rw-r--r--arch/x86/kvm/Kconfig2
-rw-r--r--arch/x86/kvm/Makefile2
-rw-r--r--arch/x86/kvm/cpuid.c14
-rw-r--r--arch/x86/kvm/emulate.c538
-rw-r--r--arch/x86/kvm/i8254.c64
-rw-r--r--arch/x86/kvm/i8254.h6
-rw-r--r--arch/x86/kvm/i8259.c70
-rw-r--r--arch/x86/kvm/irq.h2
-rw-r--r--arch/x86/kvm/kvm_timer.h18
-rw-r--r--arch/x86/kvm/lapic.c484
-rw-r--r--arch/x86/kvm/lapic.h61
-rw-r--r--arch/x86/kvm/mmu.c240
-rw-r--r--arch/x86/kvm/mmu.h25
-rw-r--r--arch/x86/kvm/mmu_audit.c8
-rw-r--r--arch/x86/kvm/paging_tmpl.h199
-rw-r--r--arch/x86/kvm/pmu.c2
-rw-r--r--arch/x86/kvm/svm.c82
-rw-r--r--arch/x86/kvm/timer.c47
-rw-r--r--arch/x86/kvm/trace.h89
-rw-r--r--arch/x86/kvm/vmx.c268
-rw-r--r--arch/x86/kvm/x86.c400
-rw-r--r--arch/x86/kvm/x86.h1
-rw-r--r--arch/x86/lib/copy_user_64.S7
-rw-r--r--arch/x86/lib/copy_user_nocache_64.S3
-rw-r--r--arch/x86/lib/getuser.S10
-rw-r--r--arch/x86/lib/insn.c4
-rw-r--r--arch/x86/lib/putuser.S8
-rw-r--r--arch/x86/lib/usercopy_32.c13
-rw-r--r--arch/x86/lib/usercopy_64.c3
-rw-r--r--arch/x86/mm/fault.c31
-rw-r--r--arch/x86/mm/init.c2
-rw-r--r--arch/x86/mm/init_32.c13
-rw-r--r--arch/x86/mm/tlb.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c34
-rw-r--r--arch/x86/pci/acpi.c3
-rw-r--r--arch/x86/pci/mmconfig-shared.c2
-rw-r--r--arch/x86/pci/visws.c5
-rw-r--r--arch/x86/platform/efi/Makefile1
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c76
-rw-r--r--arch/x86/platform/efi/efi.c66
-rw-r--r--arch/x86/realmode/rm/wakeup.h2
-rw-r--r--arch/x86/realmode/rm/wakeup_asm.S29
-rw-r--r--arch/x86/syscalls/Makefile17
-rw-r--r--arch/x86/tools/Makefile2
-rw-r--r--arch/x86/um/Kconfig1
-rw-r--r--arch/x86/um/shared/sysdep/kernel-offsets.h3
-rw-r--r--arch/x86/um/shared/sysdep/syscalls.h2
-rw-r--r--arch/x86/um/signal.c6
-rw-r--r--arch/x86/um/sys_call_table_32.c2
-rw-r--r--arch/x86/um/syscalls_32.c27
-rw-r--r--arch/x86/um/syscalls_64.c23
-rw-r--r--arch/x86/xen/apic.c3
-rw-r--r--arch/x86/xen/enlighten.c20
-rw-r--r--arch/x86/xen/irq.c1
-rw-r--r--arch/x86/xen/mmu.c190
-rw-r--r--arch/x86/xen/p2m.c121
-rw-r--r--arch/x86/xen/pci-swiotlb-xen.c52
-rw-r--r--arch/x86/xen/platform-pci-unplug.c1
-rw-r--r--arch/x86/xen/setup.c22
-rw-r--r--arch/x86/xen/smp.c6
-rw-r--r--arch/x86/xen/vga.c7
-rw-r--r--arch/x86/xen/xen-head.S56
-rw-r--r--arch/x86/xen/xen-ops.h4
213 files changed, 8335 insertions, 4212 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ec3a1aa4ab..b72777ff32a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -7,11 +7,13 @@ config 64BIT
Say no to build a 32-bit kernel - formerly known as i386
config X86_32
- def_bool !64BIT
+ def_bool y
+ depends on !64BIT
select CLKSRC_I8253
config X86_64
- def_bool 64BIT
+ def_bool y
+ depends on 64BIT
select X86_DEV_DMA_OPS
### Arch settings
@@ -36,6 +38,7 @@ config X86
select HAVE_KRETPROBES
select HAVE_OPTPROBES
select HAVE_FTRACE_MCOUNT_RECORD
+ select HAVE_FENTRY if X86_64
select HAVE_C_RECORDMCOUNT
select HAVE_DYNAMIC_FTRACE
select HAVE_FUNCTION_TRACER
@@ -60,6 +63,8 @@ config X86
select HAVE_MIXED_BREAKPOINTS_REGS
select PERF_EVENTS
select HAVE_PERF_EVENTS_NMI
+ select HAVE_PERF_REGS
+ select HAVE_PERF_USER_STACK_DUMP
select ANON_INODES
select HAVE_ALIGNED_STRUCT_PAGE if SLUB && !M386
select HAVE_CMPXCHG_LOCAL if !M386
@@ -97,9 +102,12 @@ config X86
select KTIME_SCALAR if X86_32
select GENERIC_STRNCPY_FROM_USER
select GENERIC_STRNLEN_USER
+ select HAVE_RCU_USER_QS if X86_64
+ select HAVE_IRQ_TIME_ACCOUNTING
config INSTRUCTION_DECODER
- def_bool (KPROBES || PERF_EVENTS || UPROBES)
+ def_bool y
+ depends on KPROBES || PERF_EVENTS || UPROBES
config OUTPUT_FORMAT
string
@@ -127,13 +135,15 @@ config SBUS
bool
config NEED_DMA_MAP_STATE
- def_bool (X86_64 || INTEL_IOMMU || DMA_API_DEBUG)
+ def_bool y
+ depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG
config NEED_SG_DMA_LENGTH
def_bool y
config GENERIC_ISA_DMA
- def_bool ISA_DMA_API
+ def_bool y
+ depends on ISA_DMA_API
config GENERIC_BUG
def_bool y
@@ -150,13 +160,16 @@ config GENERIC_GPIO
bool
config ARCH_MAY_HAVE_PC_FDC
- def_bool ISA_DMA_API
+ def_bool y
+ depends on ISA_DMA_API
config RWSEM_GENERIC_SPINLOCK
- def_bool !X86_XADD
+ def_bool y
+ depends on !X86_XADD
config RWSEM_XCHGADD_ALGORITHM
- def_bool X86_XADD
+ def_bool y
+ depends on X86_XADD
config GENERIC_CALIBRATE_DELAY
def_bool y
@@ -573,23 +586,18 @@ config PARAVIRT_TIME_ACCOUNTING
source "arch/x86/xen/Kconfig"
-config KVM_CLOCK
- bool "KVM paravirtualized clock"
- select PARAVIRT
- select PARAVIRT_CLOCK
- ---help---
- Turning on this option will allow you to run a paravirtualized clock
- when running over the KVM hypervisor. Instead of relying on a PIT
- (or probably other) emulation by the underlying device model, the host
- provides the guest with timing infrastructure such as time of day, and
- system time
-
config KVM_GUEST
- bool "KVM Guest support"
+ bool "KVM Guest support (including kvmclock)"
+ select PARAVIRT
select PARAVIRT
+ select PARAVIRT_CLOCK
+ default y if PARAVIRT_GUEST
---help---
This option enables various optimizations for running under the KVM
- hypervisor.
+ hypervisor. It includes a paravirtualized clock, so that instead
+ of relying on a PIT (or probably other) emulation by the
+ underlying device model, the host provides the guest with
+ timing infrastructure such as time of day, and system time
source "arch/x86/lguest/Kconfig"
@@ -746,13 +754,14 @@ config SWIOTLB
def_bool y if X86_64
---help---
Support for software bounce buffers used on x86-64 systems
- which don't have a hardware IOMMU (e.g. the current generation
- of Intel's x86-64 CPUs). Using this PCI devices which can only
- access 32-bits of memory can be used on systems with more than
- 3 GB of memory. If unsure, say Y.
+ which don't have a hardware IOMMU. Using this PCI devices
+ which can only access 32-bits of memory can be used on systems
+ with more than 3 GB of memory.
+ If unsure, say Y.
config IOMMU_HELPER
- def_bool (CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU)
+ def_bool y
+ depends on CALGARY_IOMMU || GART_IOMMU || SWIOTLB || AMD_IOMMU
config MAXSMP
bool "Enable Maximum number of SMP Processors and NUMA Nodes"
@@ -796,17 +805,6 @@ config SCHED_MC
making when dealing with multi-core CPU chips at a cost of slightly
increased overhead in some places. If unsure say N here.
-config IRQ_TIME_ACCOUNTING
- bool "Fine granularity task level IRQ time accounting"
- default n
- ---help---
- Select this option to enable fine granularity task irq time
- accounting. This is done by reading a timestamp on each
- transitions between softirq and hardirq state, so there can be a
- small performance impact.
-
- If in doubt, say N here.
-
source "kernel/Kconfig.preempt"
config X86_UP_APIC
@@ -871,6 +869,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
config X86_MCE
bool "Machine Check / overheating reporting"
+ default y
---help---
Machine Check support allows the processor to notify the
kernel if it detects a problem (e.g. overheating, data corruption).
@@ -982,25 +981,25 @@ config X86_REBOOTFIXUPS
Say N otherwise.
config MICROCODE
- tristate "/dev/cpu/microcode - microcode support"
+ tristate "CPU microcode loading support"
select FW_LOADER
---help---
+
If you say Y here, you will be able to update the microcode on
certain Intel and AMD processors. The Intel support is for the
- IA32 family, e.g. Pentium Pro, Pentium II, Pentium III,
- Pentium 4, Xeon etc. The AMD support is for family 0x10 and
- 0x11 processors, e.g. Opteron, Phenom and Turion 64 Ultra.
- You will obviously need the actual microcode binary data itself
- which is not shipped with the Linux kernel.
+ IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4,
+ Xeon etc. The AMD support is for families 0x10 and later. You will
+ obviously need the actual microcode binary data itself which is not
+ shipped with the Linux kernel.
This option selects the general module only, you need to select
at least one vendor specific module as well.
- To compile this driver as a module, choose M here: the
- module will be called microcode.
+ To compile this driver as a module, choose M here: the module
+ will be called microcode.
config MICROCODE_INTEL
- bool "Intel microcode patch loading support"
+ bool "Intel microcode loading support"
depends on MICROCODE
default MICROCODE
select FW_LOADER
@@ -1013,7 +1012,7 @@ config MICROCODE_INTEL
<http://www.urbanmyth.org/microcode/>.
config MICROCODE_AMD
- bool "AMD microcode patch loading support"
+ bool "AMD microcode loading support"
depends on MICROCODE
select FW_LOADER
---help---
@@ -1159,10 +1158,12 @@ config X86_PAE
consumes more pagetable space per process.
config ARCH_PHYS_ADDR_T_64BIT
- def_bool X86_64 || X86_PAE
+ def_bool y
+ depends on X86_64 || X86_PAE
config ARCH_DMA_ADDR_T_64BIT
- def_bool X86_64 || HIGHMEM64G
+ def_bool y
+ depends on X86_64 || HIGHMEM64G
config DIRECT_GBPAGES
bool "Enable 1GB pages for kernel pagetables" if EXPERT
@@ -1285,8 +1286,8 @@ config ARCH_SELECT_MEMORY_MODEL
depends on ARCH_SPARSEMEM_ENABLE
config ARCH_MEMORY_PROBE
- def_bool X86_64
- depends on MEMORY_HOTPLUG
+ def_bool y
+ depends on X86_64 && MEMORY_HOTPLUG
config ARCH_PROC_KCORE_TEXT
def_bool y
@@ -1487,6 +1488,17 @@ config ARCH_RANDOM
If supported, this is a high bandwidth, cryptographically
secure hardware random number generator.
+config X86_SMAP
+ def_bool y
+ prompt "Supervisor Mode Access Prevention" if EXPERT
+ ---help---
+ Supervisor Mode Access Prevention (SMAP) is a security
+ feature in newer Intel processors. There is a small
+ performance cost if this enabled and turned on; there is
+ also a small increase in the kernel size if this is enabled.
+
+ If unsure, say Y.
+
config EFI
bool "EFI runtime service support"
depends on ACPI
@@ -1975,7 +1987,6 @@ config PCI_MMCONFIG
config PCI_CNB20LE_QUIRK
bool "Read CNB20LE Host Bridge Windows" if EXPERT
- default n
depends on PCI && EXPERIMENTAL
help
Read the PCI windows out of the CNB20LE host bridge. This allows
@@ -2186,18 +2197,18 @@ config COMPAT
depends on IA32_EMULATION || X86_X32
select ARCH_WANT_OLD_COMPAT_IPC
+if COMPAT
config COMPAT_FOR_U64_ALIGNMENT
- def_bool COMPAT
- depends on X86_64
+ def_bool y
config SYSVIPC_COMPAT
def_bool y
- depends on COMPAT && SYSVIPC
+ depends on SYSVIPC
config KEYS_COMPAT
- bool
- depends on COMPAT && KEYS
- default y
+ def_bool y
+ depends on KEYS
+endif
endmenu
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 706e12e9984..f3b86d0df44 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -306,7 +306,8 @@ config X86_INTERNODE_CACHE_SHIFT
default X86_L1_CACHE_SHIFT
config X86_CMPXCHG
- def_bool X86_64 || (X86_32 && !M386)
+ def_bool y
+ depends on X86_64 || (X86_32 && !M386)
config X86_L1_CACHE_SHIFT
int
@@ -317,7 +318,7 @@ config X86_L1_CACHE_SHIFT
config X86_XADD
def_bool y
- depends on X86_64 || !M386
+ depends on !M386
config X86_PPRO_FENCE
bool "PentiumPro memory ordering errata workaround"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 682e9c210ba..474ca35b1bc 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -142,7 +142,7 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
KBUILD_CFLAGS += $(mflags-y)
KBUILD_AFLAGS += $(mflags-y)
-archscripts:
+archscripts: scripts_basic
$(Q)$(MAKE) $(build)=arch/x86/tools relocs
###
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index f7535bedc33..ce03476d8c8 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -37,7 +37,7 @@ setup-y += video-bios.o
targets += $(setup-y)
hostprogs-y := mkcpustr tools/build
-HOST_EXTRACFLAGS += -I$(srctree)/tools/include $(LINUXINCLUDE) \
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include $(USERINCLUDE) \
-D__EXPORTED_HEADERS__
$(obj)/cpu.o: $(obj)/cpustr.h
@@ -52,7 +52,7 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
# 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.
-KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
+KBUILD_CFLAGS := $(USERINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
-DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes \
-march=i386 -mregparm=3 \
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index e398bb5d63b..8a84501acb1 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -28,6 +28,9 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
$(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
$(obj)/piggy.o
+$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
+$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone
+
ifeq ($(CONFIG_EFI_STUB), y)
VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
endif
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index b3e0227df2c..c760e073963 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -276,8 +276,9 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
nr_gops = size / sizeof(void *);
for (i = 0; i < nr_gops; i++) {
struct efi_graphics_output_mode_info *info;
- efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
- void *pciio;
+ efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+ bool conout_found = false;
+ void *dummy;
void *h = gop_handle[i];
status = efi_call_phys3(sys_table->boottime->handle_protocol,
@@ -285,19 +286,21 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
if (status != EFI_SUCCESS)
continue;
- efi_call_phys3(sys_table->boottime->handle_protocol,
- h, &pciio_proto, &pciio);
+ status = efi_call_phys3(sys_table->boottime->handle_protocol,
+ h, &conout_proto, &dummy);
+
+ if (status == EFI_SUCCESS)
+ conout_found = true;
status = efi_call_phys4(gop->query_mode, gop,
gop->mode->mode, &size, &info);
- if (status == EFI_SUCCESS && (!first_gop || pciio)) {
+ if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
/*
- * Apple provide GOPs that are not backed by
- * real hardware (they're used to handle
- * multiple displays). The workaround is to
- * search for a GOP implementing the PCIIO
- * protocol, and if one isn't found, to just
- * fallback to the first GOP.
+ * Systems that use the UEFI Console Splitter may
+ * provide multiple GOP devices, not all of which are
+ * backed by real hardware. The workaround is to search
+ * for a GOP implementing the ConOut protocol, and if
+ * one isn't found, to just fall back to the first GOP.
*/
width = info->horizontal_resolution;
height = info->vertical_resolution;
@@ -308,10 +311,10 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
pixels_per_scan_line = info->pixels_per_scan_line;
/*
- * Once we've found a GOP supporting PCIIO,
+ * Once we've found a GOP supporting ConOut,
* don't bother looking any further.
*/
- if (pciio)
+ if (conout_found)
break;
first_gop = gop;
@@ -328,7 +331,6 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
si->lfb_width = width;
si->lfb_height = height;
si->lfb_base = fb_base;
- si->lfb_size = fb_size;
si->pages = 1;
if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
@@ -376,6 +378,10 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
si->rsvd_pos = 0;
}
+ si->lfb_size = si->lfb_linelength * si->lfb_height;
+
+ si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+
free_handle:
efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
return status;
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index 3b6e15627c5..e5b0a8f91c5 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -14,6 +14,10 @@
#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT)
#define EFI_READ_CHUNK_SIZE (1024 * 1024)
+#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
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b4e15dd6786..2a017441b8b 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -32,10 +32,6 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
#define SVGA_MODE ASK_VGA
#endif
-#ifndef RAMDISK
-#define RAMDISK 0
-#endif
-
#ifndef ROOT_RDONLY
#define ROOT_RDONLY 1
#endif
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index 919257f526f..4579eff0ef4 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -15,6 +15,8 @@
#include <stdio.h>
+#include "../include/asm/required-features.h"
+#include "../include/asm/cpufeature.h"
#include "../kernel/cpu/capflags.c"
int main(void)
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 119db67dcb0..5598547281a 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -8,6 +8,8 @@ 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
@@ -34,8 +36,6 @@ CONFIG_SGI_PARTITION=y
CONFIG_SUN_PARTITION=y
CONFIG_KARMA_PARTITION=y
CONFIG_EFI_PARTITION=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
CONFIG_SMP=y
CONFIG_X86_GENERIC=y
CONFIG_HPET_TIMER=y
@@ -144,8 +144,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=16384
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
CONFIG_BLK_DEV_SR_VENDOR=y
@@ -231,8 +229,6 @@ CONFIG_SND_HRTIMER=y
CONFIG_SND_HDA_INTEL=y
CONFIG_SND_HDA_HWDEP=y
CONFIG_HIDRAW=y
-CONFIG_HID_PID=y
-CONFIG_USB_HIDDEV=y
CONFIG_HID_GYRATION=y
CONFIG_LOGITECH_FF=y
CONFIG_HID_NTRIG=y
@@ -243,11 +239,11 @@ 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_DEBUG=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_DEVICEFS=y
-# CONFIG_USB_DEVICE_CLASS is not set
CONFIG_USB_MON=y
CONFIG_USB_EHCI_HCD=y
# CONFIG_USB_EHCI_TT_NEWSCHED is not set
@@ -262,10 +258,9 @@ CONFIG_RTC_CLASS=y
CONFIG_DMADEVICES=y
CONFIG_EEEPC_LAPTOP=y
CONFIG_EFI_VARS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=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
@@ -280,7 +275,6 @@ CONFIG_PROC_KCORE=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_HUGETLBFS=y
CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
@@ -299,13 +293,11 @@ CONFIG_DEBUG_KERNEL=y
CONFIG_SCHEDSTATS=y
CONFIG_TIMER_STATS=y
CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_SYSCTL_SYSCALL_CHECK=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_NX_TEST=m
CONFIG_DEBUG_BOOT_PARAMS=y
CONFIG_OPTIMIZE_INLINING=y
CONFIG_KEYS_DEBUG_PROC_KEYS=y
@@ -316,4 +308,3 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_CRYPTO_AES_586=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 76eb2903809..671524d0f6c 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -8,6 +8,8 @@ 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
@@ -34,8 +36,6 @@ CONFIG_SGI_PARTITION=y
CONFIG_SUN_PARTITION=y
CONFIG_KARMA_PARTITION=y
CONFIG_EFI_PARTITION=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
CONFIG_SMP=y
CONFIG_CALGARY_IOMMU=y
CONFIG_NR_CPUS=64
@@ -144,8 +144,6 @@ CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
CONFIG_BLK_DEV_LOOP=y
-CONFIG_BLK_DEV_RAM=y
-CONFIG_BLK_DEV_RAM_SIZE=16384
CONFIG_BLK_DEV_SD=y
CONFIG_BLK_DEV_SR=y
CONFIG_BLK_DEV_SR_VENDOR=y
@@ -227,8 +225,6 @@ CONFIG_SND_HRTIMER=y
CONFIG_SND_HDA_INTEL=y
CONFIG_SND_HDA_HWDEP=y
CONFIG_HIDRAW=y
-CONFIG_HID_PID=y
-CONFIG_USB_HIDDEV=y
CONFIG_HID_GYRATION=y
CONFIG_LOGITECH_FF=y
CONFIG_HID_NTRIG=y
@@ -239,11 +235,11 @@ 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_DEBUG=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
-CONFIG_USB_DEVICEFS=y
-# CONFIG_USB_DEVICE_CLASS is not set
CONFIG_USB_MON=y
CONFIG_USB_EHCI_HCD=y
# CONFIG_USB_EHCI_TT_NEWSCHED is not set
@@ -262,10 +258,9 @@ CONFIG_AMD_IOMMU_STATS=y
CONFIG_INTEL_IOMMU=y
# CONFIG_INTEL_IOMMU_DEFAULT_ON is not set
CONFIG_EFI_VARS=y
-CONFIG_EXT3_FS=y
-# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
-CONFIG_EXT3_FS_POSIX_ACL=y
-CONFIG_EXT3_FS_SECURITY=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
@@ -280,7 +275,6 @@ CONFIG_PROC_KCORE=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_HUGETLBFS=y
CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
CONFIG_NFS_V3_ACL=y
CONFIG_NFS_V4=y
CONFIG_ROOT_NFS=y
@@ -298,13 +292,11 @@ CONFIG_DEBUG_KERNEL=y
CONFIG_SCHEDSTATS=y
CONFIG_TIMER_STATS=y
CONFIG_DEBUG_STACK_USAGE=y
-CONFIG_SYSCTL_SYSCALL_CHECK=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_NX_TEST=m
CONFIG_DEBUG_BOOT_PARAMS=y
CONFIG_OPTIMIZE_INLINING=y
CONFIG_KEYS_DEBUG_PROC_KEYS=y
@@ -314,4 +306,3 @@ CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_DISABLE=y
# CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC_T10DIF=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index e908e5de82d..5bacb4a226a 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -12,6 +12,8 @@ obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
+obj-$(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_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
@@ -32,6 +34,8 @@ 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
camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_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
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
diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c
index 59b37deb8c8..aafe8ce0d65 100644
--- a/arch/x86/crypto/aes_glue.c
+++ b/arch/x86/crypto/aes_glue.c
@@ -40,7 +40,6 @@ static struct crypto_alg aes_alg = {
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct crypto_aes_ctx),
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(aes_alg.cra_list),
.cra_u = {
.cipher = {
.cia_min_keysize = AES_MIN_KEY_SIZE,
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 34fdcff4d2c..7c04d0da709 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -28,6 +28,9 @@
#include <crypto/aes.h>
#include <crypto/cryptd.h>
#include <crypto/ctr.h>
+#include <crypto/b128ops.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
#include <asm/cpu_device_id.h>
#include <asm/i387.h>
#include <asm/crypto/aes.h>
@@ -41,18 +44,10 @@
#define HAS_CTR
#endif
-#if defined(CONFIG_CRYPTO_LRW) || defined(CONFIG_CRYPTO_LRW_MODULE)
-#define HAS_LRW
-#endif
-
#if defined(CONFIG_CRYPTO_PCBC) || defined(CONFIG_CRYPTO_PCBC_MODULE)
#define HAS_PCBC
#endif
-#if defined(CONFIG_CRYPTO_XTS) || defined(CONFIG_CRYPTO_XTS_MODULE)
-#define HAS_XTS
-#endif
-
/* This data is stored at the end of the crypto_tfm struct.
* It's a type of per "session" data storage location.
* This needs to be 16 byte aligned.
@@ -79,6 +74,16 @@ struct aesni_hash_subkey_req_data {
#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1))
#define RFC4106_HASH_SUBKEY_SIZE 16
+struct aesni_lrw_ctx {
+ struct lrw_table_ctx lrw_table;
+ u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
+};
+
+struct aesni_xts_ctx {
+ u8 raw_tweak_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
+ u8 raw_crypt_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1];
+};
+
asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
unsigned int key_len);
asmlinkage void aesni_enc(struct crypto_aes_ctx *ctx, u8 *out,
@@ -398,13 +403,6 @@ static int ablk_rfc3686_ctr_init(struct crypto_tfm *tfm)
#endif
#endif
-#ifdef HAS_LRW
-static int ablk_lrw_init(struct crypto_tfm *tfm)
-{
- return ablk_init_common(tfm, "fpu(lrw(__driver-aes-aesni))");
-}
-#endif
-
#ifdef HAS_PCBC
static int ablk_pcbc_init(struct crypto_tfm *tfm)
{
@@ -412,12 +410,160 @@ static int ablk_pcbc_init(struct crypto_tfm *tfm)
}
#endif
-#ifdef HAS_XTS
-static int ablk_xts_init(struct crypto_tfm *tfm)
+static void lrw_xts_encrypt_callback(void *ctx, u8 *blks, unsigned int nbytes)
{
- return ablk_init_common(tfm, "fpu(xts(__driver-aes-aesni))");
+ aesni_ecb_enc(ctx, blks, blks, nbytes);
+}
+
+static void lrw_xts_decrypt_callback(void *ctx, u8 *blks, unsigned int nbytes)
+{
+ aesni_ecb_dec(ctx, blks, blks, nbytes);
+}
+
+static int lrw_aesni_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct aesni_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+ int err;
+
+ err = aes_set_key_common(tfm, ctx->raw_aes_ctx, key,
+ keylen - AES_BLOCK_SIZE);
+ if (err)
+ return err;
+
+ return lrw_init_table(&ctx->lrw_table, key + keylen - AES_BLOCK_SIZE);
+}
+
+static void lrw_aesni_exit_tfm(struct crypto_tfm *tfm)
+{
+ struct aesni_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ lrw_free_table(&ctx->lrw_table);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesni_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[8];
+ struct lrw_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .table_ctx = &ctx->lrw_table,
+ .crypt_ctx = aes_ctx(ctx->raw_aes_ctx),
+ .crypt_fn = lrw_xts_encrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ kernel_fpu_begin();
+ ret = lrw_crypt(desc, dst, src, nbytes, &req);
+ kernel_fpu_end();
+
+ return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesni_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[8];
+ struct lrw_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .table_ctx = &ctx->lrw_table,
+ .crypt_ctx = aes_ctx(ctx->raw_aes_ctx),
+ .crypt_fn = lrw_xts_decrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ kernel_fpu_begin();
+ ret = lrw_crypt(desc, dst, src, nbytes, &req);
+ kernel_fpu_end();
+
+ return ret;
+}
+
+static int xts_aesni_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct aesni_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 = aes_set_key_common(tfm, ctx->raw_crypt_ctx, key, keylen / 2);
+ if (err)
+ return err;
+
+ /* second half of xts-key is for tweak */
+ return aes_set_key_common(tfm, ctx->raw_tweak_ctx, key + keylen / 2,
+ keylen / 2);
+}
+
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesni_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[8];
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = aes_ctx(ctx->raw_tweak_ctx),
+ .tweak_fn = XTS_TWEAK_CAST(aesni_enc),
+ .crypt_ctx = aes_ctx(ctx->raw_crypt_ctx),
+ .crypt_fn = lrw_xts_encrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ kernel_fpu_begin();
+ ret = xts_crypt(desc, dst, src, nbytes, &req);
+ kernel_fpu_end();
+
+ return ret;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes)
+{
+ struct aesni_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+ be128 buf[8];
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = aes_ctx(ctx->raw_tweak_ctx),
+ .tweak_fn = XTS_TWEAK_CAST(aesni_enc),
+ .crypt_ctx = aes_ctx(ctx->raw_crypt_ctx),
+ .crypt_fn = lrw_xts_decrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+ kernel_fpu_begin();
+ ret = xts_crypt(desc, dst, src, nbytes, &req);
+ kernel_fpu_end();
+
+ return ret;
}
-#endif
#ifdef CONFIG_X86_64
static int rfc4106_init(struct crypto_tfm *tfm)
@@ -1035,10 +1181,10 @@ static struct crypto_alg aesni_algs[] = { {
},
#endif
#endif
-#ifdef HAS_LRW
+#ifdef HAS_PCBC
}, {
- .cra_name = "lrw(aes)",
- .cra_driver_name = "lrw-aes-aesni",
+ .cra_name = "pcbc(aes)",
+ .cra_driver_name = "pcbc-aes-aesni",
.cra_priority = 400,
.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
.cra_blocksize = AES_BLOCK_SIZE,
@@ -1046,12 +1192,12 @@ static struct crypto_alg aesni_algs[] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_init = ablk_lrw_init,
+ .cra_init = ablk_pcbc_init,
.cra_exit = ablk_exit,
.cra_u = {
.ablkcipher = {
- .min_keysize = AES_MIN_KEY_SIZE + AES_BLOCK_SIZE,
- .max_keysize = AES_MAX_KEY_SIZE + AES_BLOCK_SIZE,
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = ablk_set_key,
.encrypt = ablk_encrypt,
@@ -1059,10 +1205,50 @@ static struct crypto_alg aesni_algs[] = { {
},
},
#endif
-#ifdef HAS_PCBC
}, {
- .cra_name = "pcbc(aes)",
- .cra_driver_name = "pcbc-aes-aesni",
+ .cra_name = "__lrw-aes-aesni",
+ .cra_driver_name = "__driver-lrw-aes-aesni",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct aesni_lrw_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_exit = lrw_aesni_exit_tfm,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = AES_MIN_KEY_SIZE + AES_BLOCK_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE + AES_BLOCK_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = lrw_aesni_setkey,
+ .encrypt = lrw_encrypt,
+ .decrypt = lrw_decrypt,
+ },
+ },
+}, {
+ .cra_name = "__xts-aes-aesni",
+ .cra_driver_name = "__driver-xts-aes-aesni",
+ .cra_priority = 0,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct aesni_xts_ctx),
+ .cra_alignmask = 0,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .setkey = xts_aesni_setkey,
+ .encrypt = xts_encrypt,
+ .decrypt = xts_decrypt,
+ },
+ },
+}, {
+ .cra_name = "lrw(aes)",
+ .cra_driver_name = "lrw-aes-aesni",
.cra_priority = 400,
.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
.cra_blocksize = AES_BLOCK_SIZE,
@@ -1070,20 +1256,18 @@ static struct crypto_alg aesni_algs[] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_init = ablk_pcbc_init,
+ .cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
.ablkcipher = {
- .min_keysize = AES_MIN_KEY_SIZE,
- .max_keysize = AES_MAX_KEY_SIZE,
+ .min_keysize = AES_MIN_KEY_SIZE + AES_BLOCK_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE + AES_BLOCK_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = ablk_set_key,
.encrypt = ablk_encrypt,
.decrypt = ablk_decrypt,
},
},
-#endif
-#ifdef HAS_XTS
}, {
.cra_name = "xts(aes)",
.cra_driver_name = "xts-aes-aesni",
@@ -1094,7 +1278,7 @@ static struct crypto_alg aesni_algs[] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_init = ablk_xts_init,
+ .cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
.ablkcipher = {
@@ -1106,7 +1290,6 @@ static struct crypto_alg aesni_algs[] = { {
.decrypt = ablk_decrypt,
},
},
-#endif
} };
@@ -1118,7 +1301,7 @@ MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
static int __init aesni_init(void)
{
- int err, i;
+ int err;
if (!x86_match_cpu(aesni_cpu_id))
return -ENODEV;
@@ -1127,9 +1310,6 @@ static int __init aesni_init(void)
if (err)
return err;
- for (i = 0; i < ARRAY_SIZE(aesni_algs); i++)
- INIT_LIST_HEAD(&aesni_algs[i].cra_list);
-
return crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
}
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 7967474de8f..50ec333b70e 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -367,7 +367,6 @@ static struct crypto_alg bf_algs[4] = { {
.cra_ctxsize = sizeof(struct bf_ctx),
.cra_alignmask = 0,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(bf_algs[0].cra_list),
.cra_u = {
.cipher = {
.cia_min_keysize = BF_MIN_KEY_SIZE,
@@ -387,7 +386,6 @@ static struct crypto_alg bf_algs[4] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(bf_algs[1].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = BF_MIN_KEY_SIZE,
@@ -407,7 +405,6 @@ static struct crypto_alg bf_algs[4] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(bf_algs[2].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = BF_MIN_KEY_SIZE,
@@ -428,7 +425,6 @@ static struct crypto_alg bf_algs[4] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(bf_algs[3].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = BF_MIN_KEY_SIZE,
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index eeb2b3b743e..42ffd2bbab5 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -92,715 +92,715 @@ static void camellia_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
/* camellia sboxes */
const u64 camellia_sp10011110[256] = {
- 0x7000007070707000, 0x8200008282828200, 0x2c00002c2c2c2c00,
- 0xec0000ecececec00, 0xb30000b3b3b3b300, 0x2700002727272700,
- 0xc00000c0c0c0c000, 0xe50000e5e5e5e500, 0xe40000e4e4e4e400,
- 0x8500008585858500, 0x5700005757575700, 0x3500003535353500,
- 0xea0000eaeaeaea00, 0x0c00000c0c0c0c00, 0xae0000aeaeaeae00,
- 0x4100004141414100, 0x2300002323232300, 0xef0000efefefef00,
- 0x6b00006b6b6b6b00, 0x9300009393939300, 0x4500004545454500,
- 0x1900001919191900, 0xa50000a5a5a5a500, 0x2100002121212100,
- 0xed0000edededed00, 0x0e00000e0e0e0e00, 0x4f00004f4f4f4f00,
- 0x4e00004e4e4e4e00, 0x1d00001d1d1d1d00, 0x6500006565656500,
- 0x9200009292929200, 0xbd0000bdbdbdbd00, 0x8600008686868600,
- 0xb80000b8b8b8b800, 0xaf0000afafafaf00, 0x8f00008f8f8f8f00,
- 0x7c00007c7c7c7c00, 0xeb0000ebebebeb00, 0x1f00001f1f1f1f00,
- 0xce0000cececece00, 0x3e00003e3e3e3e00, 0x3000003030303000,
- 0xdc0000dcdcdcdc00, 0x5f00005f5f5f5f00, 0x5e00005e5e5e5e00,
- 0xc50000c5c5c5c500, 0x0b00000b0b0b0b00, 0x1a00001a1a1a1a00,
- 0xa60000a6a6a6a600, 0xe10000e1e1e1e100, 0x3900003939393900,
- 0xca0000cacacaca00, 0xd50000d5d5d5d500, 0x4700004747474700,
- 0x5d00005d5d5d5d00, 0x3d00003d3d3d3d00, 0xd90000d9d9d9d900,
- 0x0100000101010100, 0x5a00005a5a5a5a00, 0xd60000d6d6d6d600,
- 0x5100005151515100, 0x5600005656565600, 0x6c00006c6c6c6c00,
- 0x4d00004d4d4d4d00, 0x8b00008b8b8b8b00, 0x0d00000d0d0d0d00,
- 0x9a00009a9a9a9a00, 0x6600006666666600, 0xfb0000fbfbfbfb00,
- 0xcc0000cccccccc00, 0xb00000b0b0b0b000, 0x2d00002d2d2d2d00,
- 0x7400007474747400, 0x1200001212121200, 0x2b00002b2b2b2b00,
- 0x2000002020202000, 0xf00000f0f0f0f000, 0xb10000b1b1b1b100,
- 0x8400008484848400, 0x9900009999999900, 0xdf0000dfdfdfdf00,
- 0x4c00004c4c4c4c00, 0xcb0000cbcbcbcb00, 0xc20000c2c2c2c200,
- 0x3400003434343400, 0x7e00007e7e7e7e00, 0x7600007676767600,
- 0x0500000505050500, 0x6d00006d6d6d6d00, 0xb70000b7b7b7b700,
- 0xa90000a9a9a9a900, 0x3100003131313100, 0xd10000d1d1d1d100,
- 0x1700001717171700, 0x0400000404040400, 0xd70000d7d7d7d700,
- 0x1400001414141400, 0x5800005858585800, 0x3a00003a3a3a3a00,
- 0x6100006161616100, 0xde0000dededede00, 0x1b00001b1b1b1b00,
- 0x1100001111111100, 0x1c00001c1c1c1c00, 0x3200003232323200,
- 0x0f00000f0f0f0f00, 0x9c00009c9c9c9c00, 0x1600001616161600,
- 0x5300005353535300, 0x1800001818181800, 0xf20000f2f2f2f200,
- 0x2200002222222200, 0xfe0000fefefefe00, 0x4400004444444400,
- 0xcf0000cfcfcfcf00, 0xb20000b2b2b2b200, 0xc30000c3c3c3c300,
- 0xb50000b5b5b5b500, 0x7a00007a7a7a7a00, 0x9100009191919100,
- 0x2400002424242400, 0x0800000808080800, 0xe80000e8e8e8e800,
- 0xa80000a8a8a8a800, 0x6000006060606000, 0xfc0000fcfcfcfc00,
- 0x6900006969696900, 0x5000005050505000, 0xaa0000aaaaaaaa00,
- 0xd00000d0d0d0d000, 0xa00000a0a0a0a000, 0x7d00007d7d7d7d00,
- 0xa10000a1a1a1a100, 0x8900008989898900, 0x6200006262626200,
- 0x9700009797979700, 0x5400005454545400, 0x5b00005b5b5b5b00,
- 0x1e00001e1e1e1e00, 0x9500009595959500, 0xe00000e0e0e0e000,
- 0xff0000ffffffff00, 0x6400006464646400, 0xd20000d2d2d2d200,
- 0x1000001010101000, 0xc40000c4c4c4c400, 0x0000000000000000,
- 0x4800004848484800, 0xa30000a3a3a3a300, 0xf70000f7f7f7f700,
- 0x7500007575757500, 0xdb0000dbdbdbdb00, 0x8a00008a8a8a8a00,
- 0x0300000303030300, 0xe60000e6e6e6e600, 0xda0000dadadada00,
- 0x0900000909090900, 0x3f00003f3f3f3f00, 0xdd0000dddddddd00,
- 0x9400009494949400, 0x8700008787878700, 0x5c00005c5c5c5c00,
- 0x8300008383838300, 0x0200000202020200, 0xcd0000cdcdcdcd00,
- 0x4a00004a4a4a4a00, 0x9000009090909000, 0x3300003333333300,
- 0x7300007373737300, 0x6700006767676700, 0xf60000f6f6f6f600,
- 0xf30000f3f3f3f300, 0x9d00009d9d9d9d00, 0x7f00007f7f7f7f00,
- 0xbf0000bfbfbfbf00, 0xe20000e2e2e2e200, 0x5200005252525200,
- 0x9b00009b9b9b9b00, 0xd80000d8d8d8d800, 0x2600002626262600,
- 0xc80000c8c8c8c800, 0x3700003737373700, 0xc60000c6c6c6c600,
- 0x3b00003b3b3b3b00, 0x8100008181818100, 0x9600009696969600,
- 0x6f00006f6f6f6f00, 0x4b00004b4b4b4b00, 0x1300001313131300,
- 0xbe0000bebebebe00, 0x6300006363636300, 0x2e00002e2e2e2e00,
- 0xe90000e9e9e9e900, 0x7900007979797900, 0xa70000a7a7a7a700,
- 0x8c00008c8c8c8c00, 0x9f00009f9f9f9f00, 0x6e00006e6e6e6e00,
- 0xbc0000bcbcbcbc00, 0x8e00008e8e8e8e00, 0x2900002929292900,
- 0xf50000f5f5f5f500, 0xf90000f9f9f9f900, 0xb60000b6b6b6b600,
- 0x2f00002f2f2f2f00, 0xfd0000fdfdfdfd00, 0xb40000b4b4b4b400,
- 0x5900005959595900, 0x7800007878787800, 0x9800009898989800,
- 0x0600000606060600, 0x6a00006a6a6a6a00, 0xe70000e7e7e7e700,
- 0x4600004646464600, 0x7100007171717100, 0xba0000babababa00,
- 0xd40000d4d4d4d400, 0x2500002525252500, 0xab0000abababab00,
- 0x4200004242424200, 0x8800008888888800, 0xa20000a2a2a2a200,
- 0x8d00008d8d8d8d00, 0xfa0000fafafafa00, 0x7200007272727200,
- 0x0700000707070700, 0xb90000b9b9b9b900, 0x5500005555555500,
- 0xf80000f8f8f8f800, 0xee0000eeeeeeee00, 0xac0000acacacac00,
- 0x0a00000a0a0a0a00, 0x3600003636363600, 0x4900004949494900,
- 0x2a00002a2a2a2a00, 0x6800006868686800, 0x3c00003c3c3c3c00,
- 0x3800003838383800, 0xf10000f1f1f1f100, 0xa40000a4a4a4a400,
- 0x4000004040404000, 0x2800002828282800, 0xd30000d3d3d3d300,
- 0x7b00007b7b7b7b00, 0xbb0000bbbbbbbb00, 0xc90000c9c9c9c900,
- 0x4300004343434300, 0xc10000c1c1c1c100, 0x1500001515151500,
- 0xe30000e3e3e3e300, 0xad0000adadadad00, 0xf40000f4f4f4f400,
- 0x7700007777777700, 0xc70000c7c7c7c700, 0x8000008080808000,
- 0x9e00009e9e9e9e00,
+ 0x7000007070707000ULL, 0x8200008282828200ULL, 0x2c00002c2c2c2c00ULL,
+ 0xec0000ecececec00ULL, 0xb30000b3b3b3b300ULL, 0x2700002727272700ULL,
+ 0xc00000c0c0c0c000ULL, 0xe50000e5e5e5e500ULL, 0xe40000e4e4e4e400ULL,
+ 0x8500008585858500ULL, 0x5700005757575700ULL, 0x3500003535353500ULL,
+ 0xea0000eaeaeaea00ULL, 0x0c00000c0c0c0c00ULL, 0xae0000aeaeaeae00ULL,
+ 0x4100004141414100ULL, 0x2300002323232300ULL, 0xef0000efefefef00ULL,
+ 0x6b00006b6b6b6b00ULL, 0x9300009393939300ULL, 0x4500004545454500ULL,
+ 0x1900001919191900ULL, 0xa50000a5a5a5a500ULL, 0x2100002121212100ULL,
+ 0xed0000edededed00ULL, 0x0e00000e0e0e0e00ULL, 0x4f00004f4f4f4f00ULL,
+ 0x4e00004e4e4e4e00ULL, 0x1d00001d1d1d1d00ULL, 0x6500006565656500ULL,
+ 0x9200009292929200ULL, 0xbd0000bdbdbdbd00ULL, 0x8600008686868600ULL,
+ 0xb80000b8b8b8b800ULL, 0xaf0000afafafaf00ULL, 0x8f00008f8f8f8f00ULL,
+ 0x7c00007c7c7c7c00ULL, 0xeb0000ebebebeb00ULL, 0x1f00001f1f1f1f00ULL,
+ 0xce0000cececece00ULL, 0x3e00003e3e3e3e00ULL, 0x3000003030303000ULL,
+ 0xdc0000dcdcdcdc00ULL, 0x5f00005f5f5f5f00ULL, 0x5e00005e5e5e5e00ULL,
+ 0xc50000c5c5c5c500ULL, 0x0b00000b0b0b0b00ULL, 0x1a00001a1a1a1a00ULL,
+ 0xa60000a6a6a6a600ULL, 0xe10000e1e1e1e100ULL, 0x3900003939393900ULL,
+ 0xca0000cacacaca00ULL, 0xd50000d5d5d5d500ULL, 0x4700004747474700ULL,
+ 0x5d00005d5d5d5d00ULL, 0x3d00003d3d3d3d00ULL, 0xd90000d9d9d9d900ULL,
+ 0x0100000101010100ULL, 0x5a00005a5a5a5a00ULL, 0xd60000d6d6d6d600ULL,
+ 0x5100005151515100ULL, 0x5600005656565600ULL, 0x6c00006c6c6c6c00ULL,
+ 0x4d00004d4d4d4d00ULL, 0x8b00008b8b8b8b00ULL, 0x0d00000d0d0d0d00ULL,
+ 0x9a00009a9a9a9a00ULL, 0x6600006666666600ULL, 0xfb0000fbfbfbfb00ULL,
+ 0xcc0000cccccccc00ULL, 0xb00000b0b0b0b000ULL, 0x2d00002d2d2d2d00ULL,
+ 0x7400007474747400ULL, 0x1200001212121200ULL, 0x2b00002b2b2b2b00ULL,
+ 0x2000002020202000ULL, 0xf00000f0f0f0f000ULL, 0xb10000b1b1b1b100ULL,
+ 0x8400008484848400ULL, 0x9900009999999900ULL, 0xdf0000dfdfdfdf00ULL,
+ 0x4c00004c4c4c4c00ULL, 0xcb0000cbcbcbcb00ULL, 0xc20000c2c2c2c200ULL,
+ 0x3400003434343400ULL, 0x7e00007e7e7e7e00ULL, 0x7600007676767600ULL,
+ 0x0500000505050500ULL, 0x6d00006d6d6d6d00ULL, 0xb70000b7b7b7b700ULL,
+ 0xa90000a9a9a9a900ULL, 0x3100003131313100ULL, 0xd10000d1d1d1d100ULL,
+ 0x1700001717171700ULL, 0x0400000404040400ULL, 0xd70000d7d7d7d700ULL,
+ 0x1400001414141400ULL, 0x5800005858585800ULL, 0x3a00003a3a3a3a00ULL,
+ 0x6100006161616100ULL, 0xde0000dededede00ULL, 0x1b00001b1b1b1b00ULL,
+ 0x1100001111111100ULL, 0x1c00001c1c1c1c00ULL, 0x3200003232323200ULL,
+ 0x0f00000f0f0f0f00ULL, 0x9c00009c9c9c9c00ULL, 0x1600001616161600ULL,
+ 0x5300005353535300ULL, 0x1800001818181800ULL, 0xf20000f2f2f2f200ULL,
+ 0x2200002222222200ULL, 0xfe0000fefefefe00ULL, 0x4400004444444400ULL,
+ 0xcf0000cfcfcfcf00ULL, 0xb20000b2b2b2b200ULL, 0xc30000c3c3c3c300ULL,
+ 0xb50000b5b5b5b500ULL, 0x7a00007a7a7a7a00ULL, 0x9100009191919100ULL,
+ 0x2400002424242400ULL, 0x0800000808080800ULL, 0xe80000e8e8e8e800ULL,
+ 0xa80000a8a8a8a800ULL, 0x6000006060606000ULL, 0xfc0000fcfcfcfc00ULL,
+ 0x6900006969696900ULL, 0x5000005050505000ULL, 0xaa0000aaaaaaaa00ULL,
+ 0xd00000d0d0d0d000ULL, 0xa00000a0a0a0a000ULL, 0x7d00007d7d7d7d00ULL,
+ 0xa10000a1a1a1a100ULL, 0x8900008989898900ULL, 0x6200006262626200ULL,
+ 0x9700009797979700ULL, 0x5400005454545400ULL, 0x5b00005b5b5b5b00ULL,
+ 0x1e00001e1e1e1e00ULL, 0x9500009595959500ULL, 0xe00000e0e0e0e000ULL,
+ 0xff0000ffffffff00ULL, 0x6400006464646400ULL, 0xd20000d2d2d2d200ULL,
+ 0x1000001010101000ULL, 0xc40000c4c4c4c400ULL, 0x0000000000000000ULL,
+ 0x4800004848484800ULL, 0xa30000a3a3a3a300ULL, 0xf70000f7f7f7f700ULL,
+ 0x7500007575757500ULL, 0xdb0000dbdbdbdb00ULL, 0x8a00008a8a8a8a00ULL,
+ 0x0300000303030300ULL, 0xe60000e6e6e6e600ULL, 0xda0000dadadada00ULL,
+ 0x0900000909090900ULL, 0x3f00003f3f3f3f00ULL, 0xdd0000dddddddd00ULL,
+ 0x9400009494949400ULL, 0x8700008787878700ULL, 0x5c00005c5c5c5c00ULL,
+ 0x8300008383838300ULL, 0x0200000202020200ULL, 0xcd0000cdcdcdcd00ULL,
+ 0x4a00004a4a4a4a00ULL, 0x9000009090909000ULL, 0x3300003333333300ULL,
+ 0x7300007373737300ULL, 0x6700006767676700ULL, 0xf60000f6f6f6f600ULL,
+ 0xf30000f3f3f3f300ULL, 0x9d00009d9d9d9d00ULL, 0x7f00007f7f7f7f00ULL,
+ 0xbf0000bfbfbfbf00ULL, 0xe20000e2e2e2e200ULL, 0x5200005252525200ULL,
+ 0x9b00009b9b9b9b00ULL, 0xd80000d8d8d8d800ULL, 0x2600002626262600ULL,
+ 0xc80000c8c8c8c800ULL, 0x3700003737373700ULL, 0xc60000c6c6c6c600ULL,
+ 0x3b00003b3b3b3b00ULL, 0x8100008181818100ULL, 0x9600009696969600ULL,
+ 0x6f00006f6f6f6f00ULL, 0x4b00004b4b4b4b00ULL, 0x1300001313131300ULL,
+ 0xbe0000bebebebe00ULL, 0x6300006363636300ULL, 0x2e00002e2e2e2e00ULL,
+ 0xe90000e9e9e9e900ULL, 0x7900007979797900ULL, 0xa70000a7a7a7a700ULL,
+ 0x8c00008c8c8c8c00ULL, 0x9f00009f9f9f9f00ULL, 0x6e00006e6e6e6e00ULL,
+ 0xbc0000bcbcbcbc00ULL, 0x8e00008e8e8e8e00ULL, 0x2900002929292900ULL,
+ 0xf50000f5f5f5f500ULL, 0xf90000f9f9f9f900ULL, 0xb60000b6b6b6b600ULL,
+ 0x2f00002f2f2f2f00ULL, 0xfd0000fdfdfdfd00ULL, 0xb40000b4b4b4b400ULL,
+ 0x5900005959595900ULL, 0x7800007878787800ULL, 0x9800009898989800ULL,
+ 0x0600000606060600ULL, 0x6a00006a6a6a6a00ULL, 0xe70000e7e7e7e700ULL,
+ 0x4600004646464600ULL, 0x7100007171717100ULL, 0xba0000babababa00ULL,
+ 0xd40000d4d4d4d400ULL, 0x2500002525252500ULL, 0xab0000abababab00ULL,
+ 0x4200004242424200ULL, 0x8800008888888800ULL, 0xa20000a2a2a2a200ULL,
+ 0x8d00008d8d8d8d00ULL, 0xfa0000fafafafa00ULL, 0x7200007272727200ULL,
+ 0x0700000707070700ULL, 0xb90000b9b9b9b900ULL, 0x5500005555555500ULL,
+ 0xf80000f8f8f8f800ULL, 0xee0000eeeeeeee00ULL, 0xac0000acacacac00ULL,
+ 0x0a00000a0a0a0a00ULL, 0x3600003636363600ULL, 0x4900004949494900ULL,
+ 0x2a00002a2a2a2a00ULL, 0x6800006868686800ULL, 0x3c00003c3c3c3c00ULL,
+ 0x3800003838383800ULL, 0xf10000f1f1f1f100ULL, 0xa40000a4a4a4a400ULL,
+ 0x4000004040404000ULL, 0x2800002828282800ULL, 0xd30000d3d3d3d300ULL,
+ 0x7b00007b7b7b7b00ULL, 0xbb0000bbbbbbbb00ULL, 0xc90000c9c9c9c900ULL,
+ 0x4300004343434300ULL, 0xc10000c1c1c1c100ULL, 0x1500001515151500ULL,
+ 0xe30000e3e3e3e300ULL, 0xad0000adadadad00ULL, 0xf40000f4f4f4f400ULL,
+ 0x7700007777777700ULL, 0xc70000c7c7c7c700ULL, 0x8000008080808000ULL,
+ 0x9e00009e9e9e9e00ULL,
};
const u64 camellia_sp22000222[256] = {
- 0xe0e0000000e0e0e0, 0x0505000000050505, 0x5858000000585858,
- 0xd9d9000000d9d9d9, 0x6767000000676767, 0x4e4e0000004e4e4e,
- 0x8181000000818181, 0xcbcb000000cbcbcb, 0xc9c9000000c9c9c9,
- 0x0b0b0000000b0b0b, 0xaeae000000aeaeae, 0x6a6a0000006a6a6a,
- 0xd5d5000000d5d5d5, 0x1818000000181818, 0x5d5d0000005d5d5d,
- 0x8282000000828282, 0x4646000000464646, 0xdfdf000000dfdfdf,
- 0xd6d6000000d6d6d6, 0x2727000000272727, 0x8a8a0000008a8a8a,
- 0x3232000000323232, 0x4b4b0000004b4b4b, 0x4242000000424242,
- 0xdbdb000000dbdbdb, 0x1c1c0000001c1c1c, 0x9e9e0000009e9e9e,
- 0x9c9c0000009c9c9c, 0x3a3a0000003a3a3a, 0xcaca000000cacaca,
- 0x2525000000252525, 0x7b7b0000007b7b7b, 0x0d0d0000000d0d0d,
- 0x7171000000717171, 0x5f5f0000005f5f5f, 0x1f1f0000001f1f1f,
- 0xf8f8000000f8f8f8, 0xd7d7000000d7d7d7, 0x3e3e0000003e3e3e,
- 0x9d9d0000009d9d9d, 0x7c7c0000007c7c7c, 0x6060000000606060,
- 0xb9b9000000b9b9b9, 0xbebe000000bebebe, 0xbcbc000000bcbcbc,
- 0x8b8b0000008b8b8b, 0x1616000000161616, 0x3434000000343434,
- 0x4d4d0000004d4d4d, 0xc3c3000000c3c3c3, 0x7272000000727272,
- 0x9595000000959595, 0xabab000000ababab, 0x8e8e0000008e8e8e,
- 0xbaba000000bababa, 0x7a7a0000007a7a7a, 0xb3b3000000b3b3b3,
- 0x0202000000020202, 0xb4b4000000b4b4b4, 0xadad000000adadad,
- 0xa2a2000000a2a2a2, 0xacac000000acacac, 0xd8d8000000d8d8d8,
- 0x9a9a0000009a9a9a, 0x1717000000171717, 0x1a1a0000001a1a1a,
- 0x3535000000353535, 0xcccc000000cccccc, 0xf7f7000000f7f7f7,
- 0x9999000000999999, 0x6161000000616161, 0x5a5a0000005a5a5a,
- 0xe8e8000000e8e8e8, 0x2424000000242424, 0x5656000000565656,
- 0x4040000000404040, 0xe1e1000000e1e1e1, 0x6363000000636363,
- 0x0909000000090909, 0x3333000000333333, 0xbfbf000000bfbfbf,
- 0x9898000000989898, 0x9797000000979797, 0x8585000000858585,
- 0x6868000000686868, 0xfcfc000000fcfcfc, 0xecec000000ececec,
- 0x0a0a0000000a0a0a, 0xdada000000dadada, 0x6f6f0000006f6f6f,
- 0x5353000000535353, 0x6262000000626262, 0xa3a3000000a3a3a3,
- 0x2e2e0000002e2e2e, 0x0808000000080808, 0xafaf000000afafaf,
- 0x2828000000282828, 0xb0b0000000b0b0b0, 0x7474000000747474,
- 0xc2c2000000c2c2c2, 0xbdbd000000bdbdbd, 0x3636000000363636,
- 0x2222000000222222, 0x3838000000383838, 0x6464000000646464,
- 0x1e1e0000001e1e1e, 0x3939000000393939, 0x2c2c0000002c2c2c,
- 0xa6a6000000a6a6a6, 0x3030000000303030, 0xe5e5000000e5e5e5,
- 0x4444000000444444, 0xfdfd000000fdfdfd, 0x8888000000888888,
- 0x9f9f0000009f9f9f, 0x6565000000656565, 0x8787000000878787,
- 0x6b6b0000006b6b6b, 0xf4f4000000f4f4f4, 0x2323000000232323,
- 0x4848000000484848, 0x1010000000101010, 0xd1d1000000d1d1d1,
- 0x5151000000515151, 0xc0c0000000c0c0c0, 0xf9f9000000f9f9f9,
- 0xd2d2000000d2d2d2, 0xa0a0000000a0a0a0, 0x5555000000555555,
- 0xa1a1000000a1a1a1, 0x4141000000414141, 0xfafa000000fafafa,
- 0x4343000000434343, 0x1313000000131313, 0xc4c4000000c4c4c4,
- 0x2f2f0000002f2f2f, 0xa8a8000000a8a8a8, 0xb6b6000000b6b6b6,
- 0x3c3c0000003c3c3c, 0x2b2b0000002b2b2b, 0xc1c1000000c1c1c1,
- 0xffff000000ffffff, 0xc8c8000000c8c8c8, 0xa5a5000000a5a5a5,
- 0x2020000000202020, 0x8989000000898989, 0x0000000000000000,
- 0x9090000000909090, 0x4747000000474747, 0xefef000000efefef,
- 0xeaea000000eaeaea, 0xb7b7000000b7b7b7, 0x1515000000151515,
- 0x0606000000060606, 0xcdcd000000cdcdcd, 0xb5b5000000b5b5b5,
- 0x1212000000121212, 0x7e7e0000007e7e7e, 0xbbbb000000bbbbbb,
- 0x2929000000292929, 0x0f0f0000000f0f0f, 0xb8b8000000b8b8b8,
- 0x0707000000070707, 0x0404000000040404, 0x9b9b0000009b9b9b,
- 0x9494000000949494, 0x2121000000212121, 0x6666000000666666,
- 0xe6e6000000e6e6e6, 0xcece000000cecece, 0xeded000000ededed,
- 0xe7e7000000e7e7e7, 0x3b3b0000003b3b3b, 0xfefe000000fefefe,
- 0x7f7f0000007f7f7f, 0xc5c5000000c5c5c5, 0xa4a4000000a4a4a4,
- 0x3737000000373737, 0xb1b1000000b1b1b1, 0x4c4c0000004c4c4c,
- 0x9191000000919191, 0x6e6e0000006e6e6e, 0x8d8d0000008d8d8d,
- 0x7676000000767676, 0x0303000000030303, 0x2d2d0000002d2d2d,
- 0xdede000000dedede, 0x9696000000969696, 0x2626000000262626,
- 0x7d7d0000007d7d7d, 0xc6c6000000c6c6c6, 0x5c5c0000005c5c5c,
- 0xd3d3000000d3d3d3, 0xf2f2000000f2f2f2, 0x4f4f0000004f4f4f,
- 0x1919000000191919, 0x3f3f0000003f3f3f, 0xdcdc000000dcdcdc,
- 0x7979000000797979, 0x1d1d0000001d1d1d, 0x5252000000525252,
- 0xebeb000000ebebeb, 0xf3f3000000f3f3f3, 0x6d6d0000006d6d6d,
- 0x5e5e0000005e5e5e, 0xfbfb000000fbfbfb, 0x6969000000696969,
- 0xb2b2000000b2b2b2, 0xf0f0000000f0f0f0, 0x3131000000313131,
- 0x0c0c0000000c0c0c, 0xd4d4000000d4d4d4, 0xcfcf000000cfcfcf,
- 0x8c8c0000008c8c8c, 0xe2e2000000e2e2e2, 0x7575000000757575,
- 0xa9a9000000a9a9a9, 0x4a4a0000004a4a4a, 0x5757000000575757,
- 0x8484000000848484, 0x1111000000111111, 0x4545000000454545,
- 0x1b1b0000001b1b1b, 0xf5f5000000f5f5f5, 0xe4e4000000e4e4e4,
- 0x0e0e0000000e0e0e, 0x7373000000737373, 0xaaaa000000aaaaaa,
- 0xf1f1000000f1f1f1, 0xdddd000000dddddd, 0x5959000000595959,
- 0x1414000000141414, 0x6c6c0000006c6c6c, 0x9292000000929292,
- 0x5454000000545454, 0xd0d0000000d0d0d0, 0x7878000000787878,
- 0x7070000000707070, 0xe3e3000000e3e3e3, 0x4949000000494949,
- 0x8080000000808080, 0x5050000000505050, 0xa7a7000000a7a7a7,
- 0xf6f6000000f6f6f6, 0x7777000000777777, 0x9393000000939393,
- 0x8686000000868686, 0x8383000000838383, 0x2a2a0000002a2a2a,
- 0xc7c7000000c7c7c7, 0x5b5b0000005b5b5b, 0xe9e9000000e9e9e9,
- 0xeeee000000eeeeee, 0x8f8f0000008f8f8f, 0x0101000000010101,
- 0x3d3d0000003d3d3d,
+ 0xe0e0000000e0e0e0ULL, 0x0505000000050505ULL, 0x5858000000585858ULL,
+ 0xd9d9000000d9d9d9ULL, 0x6767000000676767ULL, 0x4e4e0000004e4e4eULL,
+ 0x8181000000818181ULL, 0xcbcb000000cbcbcbULL, 0xc9c9000000c9c9c9ULL,
+ 0x0b0b0000000b0b0bULL, 0xaeae000000aeaeaeULL, 0x6a6a0000006a6a6aULL,
+ 0xd5d5000000d5d5d5ULL, 0x1818000000181818ULL, 0x5d5d0000005d5d5dULL,
+ 0x8282000000828282ULL, 0x4646000000464646ULL, 0xdfdf000000dfdfdfULL,
+ 0xd6d6000000d6d6d6ULL, 0x2727000000272727ULL, 0x8a8a0000008a8a8aULL,
+ 0x3232000000323232ULL, 0x4b4b0000004b4b4bULL, 0x4242000000424242ULL,
+ 0xdbdb000000dbdbdbULL, 0x1c1c0000001c1c1cULL, 0x9e9e0000009e9e9eULL,
+ 0x9c9c0000009c9c9cULL, 0x3a3a0000003a3a3aULL, 0xcaca000000cacacaULL,
+ 0x2525000000252525ULL, 0x7b7b0000007b7b7bULL, 0x0d0d0000000d0d0dULL,
+ 0x7171000000717171ULL, 0x5f5f0000005f5f5fULL, 0x1f1f0000001f1f1fULL,
+ 0xf8f8000000f8f8f8ULL, 0xd7d7000000d7d7d7ULL, 0x3e3e0000003e3e3eULL,
+ 0x9d9d0000009d9d9dULL, 0x7c7c0000007c7c7cULL, 0x6060000000606060ULL,
+ 0xb9b9000000b9b9b9ULL, 0xbebe000000bebebeULL, 0xbcbc000000bcbcbcULL,
+ 0x8b8b0000008b8b8bULL, 0x1616000000161616ULL, 0x3434000000343434ULL,
+ 0x4d4d0000004d4d4dULL, 0xc3c3000000c3c3c3ULL, 0x7272000000727272ULL,
+ 0x9595000000959595ULL, 0xabab000000abababULL, 0x8e8e0000008e8e8eULL,
+ 0xbaba000000bababaULL, 0x7a7a0000007a7a7aULL, 0xb3b3000000b3b3b3ULL,
+ 0x0202000000020202ULL, 0xb4b4000000b4b4b4ULL, 0xadad000000adadadULL,
+ 0xa2a2000000a2a2a2ULL, 0xacac000000acacacULL, 0xd8d8000000d8d8d8ULL,
+ 0x9a9a0000009a9a9aULL, 0x1717000000171717ULL, 0x1a1a0000001a1a1aULL,
+ 0x3535000000353535ULL, 0xcccc000000ccccccULL, 0xf7f7000000f7f7f7ULL,
+ 0x9999000000999999ULL, 0x6161000000616161ULL, 0x5a5a0000005a5a5aULL,
+ 0xe8e8000000e8e8e8ULL, 0x2424000000242424ULL, 0x5656000000565656ULL,
+ 0x4040000000404040ULL, 0xe1e1000000e1e1e1ULL, 0x6363000000636363ULL,
+ 0x0909000000090909ULL, 0x3333000000333333ULL, 0xbfbf000000bfbfbfULL,
+ 0x9898000000989898ULL, 0x9797000000979797ULL, 0x8585000000858585ULL,
+ 0x6868000000686868ULL, 0xfcfc000000fcfcfcULL, 0xecec000000ecececULL,
+ 0x0a0a0000000a0a0aULL, 0xdada000000dadadaULL, 0x6f6f0000006f6f6fULL,
+ 0x5353000000535353ULL, 0x6262000000626262ULL, 0xa3a3000000a3a3a3ULL,
+ 0x2e2e0000002e2e2eULL, 0x0808000000080808ULL, 0xafaf000000afafafULL,
+ 0x2828000000282828ULL, 0xb0b0000000b0b0b0ULL, 0x7474000000747474ULL,
+ 0xc2c2000000c2c2c2ULL, 0xbdbd000000bdbdbdULL, 0x3636000000363636ULL,
+ 0x2222000000222222ULL, 0x3838000000383838ULL, 0x6464000000646464ULL,
+ 0x1e1e0000001e1e1eULL, 0x3939000000393939ULL, 0x2c2c0000002c2c2cULL,
+ 0xa6a6000000a6a6a6ULL, 0x3030000000303030ULL, 0xe5e5000000e5e5e5ULL,
+ 0x4444000000444444ULL, 0xfdfd000000fdfdfdULL, 0x8888000000888888ULL,
+ 0x9f9f0000009f9f9fULL, 0x6565000000656565ULL, 0x8787000000878787ULL,
+ 0x6b6b0000006b6b6bULL, 0xf4f4000000f4f4f4ULL, 0x2323000000232323ULL,
+ 0x4848000000484848ULL, 0x1010000000101010ULL, 0xd1d1000000d1d1d1ULL,
+ 0x5151000000515151ULL, 0xc0c0000000c0c0c0ULL, 0xf9f9000000f9f9f9ULL,
+ 0xd2d2000000d2d2d2ULL, 0xa0a0000000a0a0a0ULL, 0x5555000000555555ULL,
+ 0xa1a1000000a1a1a1ULL, 0x4141000000414141ULL, 0xfafa000000fafafaULL,
+ 0x4343000000434343ULL, 0x1313000000131313ULL, 0xc4c4000000c4c4c4ULL,
+ 0x2f2f0000002f2f2fULL, 0xa8a8000000a8a8a8ULL, 0xb6b6000000b6b6b6ULL,
+ 0x3c3c0000003c3c3cULL, 0x2b2b0000002b2b2bULL, 0xc1c1000000c1c1c1ULL,
+ 0xffff000000ffffffULL, 0xc8c8000000c8c8c8ULL, 0xa5a5000000a5a5a5ULL,
+ 0x2020000000202020ULL, 0x8989000000898989ULL, 0x0000000000000000ULL,
+ 0x9090000000909090ULL, 0x4747000000474747ULL, 0xefef000000efefefULL,
+ 0xeaea000000eaeaeaULL, 0xb7b7000000b7b7b7ULL, 0x1515000000151515ULL,
+ 0x0606000000060606ULL, 0xcdcd000000cdcdcdULL, 0xb5b5000000b5b5b5ULL,
+ 0x1212000000121212ULL, 0x7e7e0000007e7e7eULL, 0xbbbb000000bbbbbbULL,
+ 0x2929000000292929ULL, 0x0f0f0000000f0f0fULL, 0xb8b8000000b8b8b8ULL,
+ 0x0707000000070707ULL, 0x0404000000040404ULL, 0x9b9b0000009b9b9bULL,
+ 0x9494000000949494ULL, 0x2121000000212121ULL, 0x6666000000666666ULL,
+ 0xe6e6000000e6e6e6ULL, 0xcece000000cececeULL, 0xeded000000edededULL,
+ 0xe7e7000000e7e7e7ULL, 0x3b3b0000003b3b3bULL, 0xfefe000000fefefeULL,
+ 0x7f7f0000007f7f7fULL, 0xc5c5000000c5c5c5ULL, 0xa4a4000000a4a4a4ULL,
+ 0x3737000000373737ULL, 0xb1b1000000b1b1b1ULL, 0x4c4c0000004c4c4cULL,
+ 0x9191000000919191ULL, 0x6e6e0000006e6e6eULL, 0x8d8d0000008d8d8dULL,
+ 0x7676000000767676ULL, 0x0303000000030303ULL, 0x2d2d0000002d2d2dULL,
+ 0xdede000000dededeULL, 0x9696000000969696ULL, 0x2626000000262626ULL,
+ 0x7d7d0000007d7d7dULL, 0xc6c6000000c6c6c6ULL, 0x5c5c0000005c5c5cULL,
+ 0xd3d3000000d3d3d3ULL, 0xf2f2000000f2f2f2ULL, 0x4f4f0000004f4f4fULL,
+ 0x1919000000191919ULL, 0x3f3f0000003f3f3fULL, 0xdcdc000000dcdcdcULL,
+ 0x7979000000797979ULL, 0x1d1d0000001d1d1dULL, 0x5252000000525252ULL,
+ 0xebeb000000ebebebULL, 0xf3f3000000f3f3f3ULL, 0x6d6d0000006d6d6dULL,
+ 0x5e5e0000005e5e5eULL, 0xfbfb000000fbfbfbULL, 0x6969000000696969ULL,
+ 0xb2b2000000b2b2b2ULL, 0xf0f0000000f0f0f0ULL, 0x3131000000313131ULL,
+ 0x0c0c0000000c0c0cULL, 0xd4d4000000d4d4d4ULL, 0xcfcf000000cfcfcfULL,
+ 0x8c8c0000008c8c8cULL, 0xe2e2000000e2e2e2ULL, 0x7575000000757575ULL,
+ 0xa9a9000000a9a9a9ULL, 0x4a4a0000004a4a4aULL, 0x5757000000575757ULL,
+ 0x8484000000848484ULL, 0x1111000000111111ULL, 0x4545000000454545ULL,
+ 0x1b1b0000001b1b1bULL, 0xf5f5000000f5f5f5ULL, 0xe4e4000000e4e4e4ULL,
+ 0x0e0e0000000e0e0eULL, 0x7373000000737373ULL, 0xaaaa000000aaaaaaULL,
+ 0xf1f1000000f1f1f1ULL, 0xdddd000000ddddddULL, 0x5959000000595959ULL,
+ 0x1414000000141414ULL, 0x6c6c0000006c6c6cULL, 0x9292000000929292ULL,
+ 0x5454000000545454ULL, 0xd0d0000000d0d0d0ULL, 0x7878000000787878ULL,
+ 0x7070000000707070ULL, 0xe3e3000000e3e3e3ULL, 0x4949000000494949ULL,
+ 0x8080000000808080ULL, 0x5050000000505050ULL, 0xa7a7000000a7a7a7ULL,
+ 0xf6f6000000f6f6f6ULL, 0x7777000000777777ULL, 0x9393000000939393ULL,
+ 0x8686000000868686ULL, 0x8383000000838383ULL, 0x2a2a0000002a2a2aULL,
+ 0xc7c7000000c7c7c7ULL, 0x5b5b0000005b5b5bULL, 0xe9e9000000e9e9e9ULL,
+ 0xeeee000000eeeeeeULL, 0x8f8f0000008f8f8fULL, 0x0101000000010101ULL,
+ 0x3d3d0000003d3d3dULL,
};
const u64 camellia_sp03303033[256] = {
- 0x0038380038003838, 0x0041410041004141, 0x0016160016001616,
- 0x0076760076007676, 0x00d9d900d900d9d9, 0x0093930093009393,
- 0x0060600060006060, 0x00f2f200f200f2f2, 0x0072720072007272,
- 0x00c2c200c200c2c2, 0x00abab00ab00abab, 0x009a9a009a009a9a,
- 0x0075750075007575, 0x0006060006000606, 0x0057570057005757,
- 0x00a0a000a000a0a0, 0x0091910091009191, 0x00f7f700f700f7f7,
- 0x00b5b500b500b5b5, 0x00c9c900c900c9c9, 0x00a2a200a200a2a2,
- 0x008c8c008c008c8c, 0x00d2d200d200d2d2, 0x0090900090009090,
- 0x00f6f600f600f6f6, 0x0007070007000707, 0x00a7a700a700a7a7,
- 0x0027270027002727, 0x008e8e008e008e8e, 0x00b2b200b200b2b2,
- 0x0049490049004949, 0x00dede00de00dede, 0x0043430043004343,
- 0x005c5c005c005c5c, 0x00d7d700d700d7d7, 0x00c7c700c700c7c7,
- 0x003e3e003e003e3e, 0x00f5f500f500f5f5, 0x008f8f008f008f8f,
- 0x0067670067006767, 0x001f1f001f001f1f, 0x0018180018001818,
- 0x006e6e006e006e6e, 0x00afaf00af00afaf, 0x002f2f002f002f2f,
- 0x00e2e200e200e2e2, 0x0085850085008585, 0x000d0d000d000d0d,
- 0x0053530053005353, 0x00f0f000f000f0f0, 0x009c9c009c009c9c,
- 0x0065650065006565, 0x00eaea00ea00eaea, 0x00a3a300a300a3a3,
- 0x00aeae00ae00aeae, 0x009e9e009e009e9e, 0x00ecec00ec00ecec,
- 0x0080800080008080, 0x002d2d002d002d2d, 0x006b6b006b006b6b,
- 0x00a8a800a800a8a8, 0x002b2b002b002b2b, 0x0036360036003636,
- 0x00a6a600a600a6a6, 0x00c5c500c500c5c5, 0x0086860086008686,
- 0x004d4d004d004d4d, 0x0033330033003333, 0x00fdfd00fd00fdfd,
- 0x0066660066006666, 0x0058580058005858, 0x0096960096009696,
- 0x003a3a003a003a3a, 0x0009090009000909, 0x0095950095009595,
- 0x0010100010001010, 0x0078780078007878, 0x00d8d800d800d8d8,
- 0x0042420042004242, 0x00cccc00cc00cccc, 0x00efef00ef00efef,
- 0x0026260026002626, 0x00e5e500e500e5e5, 0x0061610061006161,
- 0x001a1a001a001a1a, 0x003f3f003f003f3f, 0x003b3b003b003b3b,
- 0x0082820082008282, 0x00b6b600b600b6b6, 0x00dbdb00db00dbdb,
- 0x00d4d400d400d4d4, 0x0098980098009898, 0x00e8e800e800e8e8,
- 0x008b8b008b008b8b, 0x0002020002000202, 0x00ebeb00eb00ebeb,
- 0x000a0a000a000a0a, 0x002c2c002c002c2c, 0x001d1d001d001d1d,
- 0x00b0b000b000b0b0, 0x006f6f006f006f6f, 0x008d8d008d008d8d,
- 0x0088880088008888, 0x000e0e000e000e0e, 0x0019190019001919,
- 0x0087870087008787, 0x004e4e004e004e4e, 0x000b0b000b000b0b,
- 0x00a9a900a900a9a9, 0x000c0c000c000c0c, 0x0079790079007979,
- 0x0011110011001111, 0x007f7f007f007f7f, 0x0022220022002222,
- 0x00e7e700e700e7e7, 0x0059590059005959, 0x00e1e100e100e1e1,
- 0x00dada00da00dada, 0x003d3d003d003d3d, 0x00c8c800c800c8c8,
- 0x0012120012001212, 0x0004040004000404, 0x0074740074007474,
- 0x0054540054005454, 0x0030300030003030, 0x007e7e007e007e7e,
- 0x00b4b400b400b4b4, 0x0028280028002828, 0x0055550055005555,
- 0x0068680068006868, 0x0050500050005050, 0x00bebe00be00bebe,
- 0x00d0d000d000d0d0, 0x00c4c400c400c4c4, 0x0031310031003131,
- 0x00cbcb00cb00cbcb, 0x002a2a002a002a2a, 0x00adad00ad00adad,
- 0x000f0f000f000f0f, 0x00caca00ca00caca, 0x0070700070007070,
- 0x00ffff00ff00ffff, 0x0032320032003232, 0x0069690069006969,
- 0x0008080008000808, 0x0062620062006262, 0x0000000000000000,
- 0x0024240024002424, 0x00d1d100d100d1d1, 0x00fbfb00fb00fbfb,
- 0x00baba00ba00baba, 0x00eded00ed00eded, 0x0045450045004545,
- 0x0081810081008181, 0x0073730073007373, 0x006d6d006d006d6d,
- 0x0084840084008484, 0x009f9f009f009f9f, 0x00eeee00ee00eeee,
- 0x004a4a004a004a4a, 0x00c3c300c300c3c3, 0x002e2e002e002e2e,
- 0x00c1c100c100c1c1, 0x0001010001000101, 0x00e6e600e600e6e6,
- 0x0025250025002525, 0x0048480048004848, 0x0099990099009999,
- 0x00b9b900b900b9b9, 0x00b3b300b300b3b3, 0x007b7b007b007b7b,
- 0x00f9f900f900f9f9, 0x00cece00ce00cece, 0x00bfbf00bf00bfbf,
- 0x00dfdf00df00dfdf, 0x0071710071007171, 0x0029290029002929,
- 0x00cdcd00cd00cdcd, 0x006c6c006c006c6c, 0x0013130013001313,
- 0x0064640064006464, 0x009b9b009b009b9b, 0x0063630063006363,
- 0x009d9d009d009d9d, 0x00c0c000c000c0c0, 0x004b4b004b004b4b,
- 0x00b7b700b700b7b7, 0x00a5a500a500a5a5, 0x0089890089008989,
- 0x005f5f005f005f5f, 0x00b1b100b100b1b1, 0x0017170017001717,
- 0x00f4f400f400f4f4, 0x00bcbc00bc00bcbc, 0x00d3d300d300d3d3,
- 0x0046460046004646, 0x00cfcf00cf00cfcf, 0x0037370037003737,
- 0x005e5e005e005e5e, 0x0047470047004747, 0x0094940094009494,
- 0x00fafa00fa00fafa, 0x00fcfc00fc00fcfc, 0x005b5b005b005b5b,
- 0x0097970097009797, 0x00fefe00fe00fefe, 0x005a5a005a005a5a,
- 0x00acac00ac00acac, 0x003c3c003c003c3c, 0x004c4c004c004c4c,
- 0x0003030003000303, 0x0035350035003535, 0x00f3f300f300f3f3,
- 0x0023230023002323, 0x00b8b800b800b8b8, 0x005d5d005d005d5d,
- 0x006a6a006a006a6a, 0x0092920092009292, 0x00d5d500d500d5d5,
- 0x0021210021002121, 0x0044440044004444, 0x0051510051005151,
- 0x00c6c600c600c6c6, 0x007d7d007d007d7d, 0x0039390039003939,
- 0x0083830083008383, 0x00dcdc00dc00dcdc, 0x00aaaa00aa00aaaa,
- 0x007c7c007c007c7c, 0x0077770077007777, 0x0056560056005656,
- 0x0005050005000505, 0x001b1b001b001b1b, 0x00a4a400a400a4a4,
- 0x0015150015001515, 0x0034340034003434, 0x001e1e001e001e1e,
- 0x001c1c001c001c1c, 0x00f8f800f800f8f8, 0x0052520052005252,
- 0x0020200020002020, 0x0014140014001414, 0x00e9e900e900e9e9,
- 0x00bdbd00bd00bdbd, 0x00dddd00dd00dddd, 0x00e4e400e400e4e4,
- 0x00a1a100a100a1a1, 0x00e0e000e000e0e0, 0x008a8a008a008a8a,
- 0x00f1f100f100f1f1, 0x00d6d600d600d6d6, 0x007a7a007a007a7a,
- 0x00bbbb00bb00bbbb, 0x00e3e300e300e3e3, 0x0040400040004040,
- 0x004f4f004f004f4f,
+ 0x0038380038003838ULL, 0x0041410041004141ULL, 0x0016160016001616ULL,
+ 0x0076760076007676ULL, 0x00d9d900d900d9d9ULL, 0x0093930093009393ULL,
+ 0x0060600060006060ULL, 0x00f2f200f200f2f2ULL, 0x0072720072007272ULL,
+ 0x00c2c200c200c2c2ULL, 0x00abab00ab00ababULL, 0x009a9a009a009a9aULL,
+ 0x0075750075007575ULL, 0x0006060006000606ULL, 0x0057570057005757ULL,
+ 0x00a0a000a000a0a0ULL, 0x0091910091009191ULL, 0x00f7f700f700f7f7ULL,
+ 0x00b5b500b500b5b5ULL, 0x00c9c900c900c9c9ULL, 0x00a2a200a200a2a2ULL,
+ 0x008c8c008c008c8cULL, 0x00d2d200d200d2d2ULL, 0x0090900090009090ULL,
+ 0x00f6f600f600f6f6ULL, 0x0007070007000707ULL, 0x00a7a700a700a7a7ULL,
+ 0x0027270027002727ULL, 0x008e8e008e008e8eULL, 0x00b2b200b200b2b2ULL,
+ 0x0049490049004949ULL, 0x00dede00de00dedeULL, 0x0043430043004343ULL,
+ 0x005c5c005c005c5cULL, 0x00d7d700d700d7d7ULL, 0x00c7c700c700c7c7ULL,
+ 0x003e3e003e003e3eULL, 0x00f5f500f500f5f5ULL, 0x008f8f008f008f8fULL,
+ 0x0067670067006767ULL, 0x001f1f001f001f1fULL, 0x0018180018001818ULL,
+ 0x006e6e006e006e6eULL, 0x00afaf00af00afafULL, 0x002f2f002f002f2fULL,
+ 0x00e2e200e200e2e2ULL, 0x0085850085008585ULL, 0x000d0d000d000d0dULL,
+ 0x0053530053005353ULL, 0x00f0f000f000f0f0ULL, 0x009c9c009c009c9cULL,
+ 0x0065650065006565ULL, 0x00eaea00ea00eaeaULL, 0x00a3a300a300a3a3ULL,
+ 0x00aeae00ae00aeaeULL, 0x009e9e009e009e9eULL, 0x00ecec00ec00ececULL,
+ 0x0080800080008080ULL, 0x002d2d002d002d2dULL, 0x006b6b006b006b6bULL,
+ 0x00a8a800a800a8a8ULL, 0x002b2b002b002b2bULL, 0x0036360036003636ULL,
+ 0x00a6a600a600a6a6ULL, 0x00c5c500c500c5c5ULL, 0x0086860086008686ULL,
+ 0x004d4d004d004d4dULL, 0x0033330033003333ULL, 0x00fdfd00fd00fdfdULL,
+ 0x0066660066006666ULL, 0x0058580058005858ULL, 0x0096960096009696ULL,
+ 0x003a3a003a003a3aULL, 0x0009090009000909ULL, 0x0095950095009595ULL,
+ 0x0010100010001010ULL, 0x0078780078007878ULL, 0x00d8d800d800d8d8ULL,
+ 0x0042420042004242ULL, 0x00cccc00cc00ccccULL, 0x00efef00ef00efefULL,
+ 0x0026260026002626ULL, 0x00e5e500e500e5e5ULL, 0x0061610061006161ULL,
+ 0x001a1a001a001a1aULL, 0x003f3f003f003f3fULL, 0x003b3b003b003b3bULL,
+ 0x0082820082008282ULL, 0x00b6b600b600b6b6ULL, 0x00dbdb00db00dbdbULL,
+ 0x00d4d400d400d4d4ULL, 0x0098980098009898ULL, 0x00e8e800e800e8e8ULL,
+ 0x008b8b008b008b8bULL, 0x0002020002000202ULL, 0x00ebeb00eb00ebebULL,
+ 0x000a0a000a000a0aULL, 0x002c2c002c002c2cULL, 0x001d1d001d001d1dULL,
+ 0x00b0b000b000b0b0ULL, 0x006f6f006f006f6fULL, 0x008d8d008d008d8dULL,
+ 0x0088880088008888ULL, 0x000e0e000e000e0eULL, 0x0019190019001919ULL,
+ 0x0087870087008787ULL, 0x004e4e004e004e4eULL, 0x000b0b000b000b0bULL,
+ 0x00a9a900a900a9a9ULL, 0x000c0c000c000c0cULL, 0x0079790079007979ULL,
+ 0x0011110011001111ULL, 0x007f7f007f007f7fULL, 0x0022220022002222ULL,
+ 0x00e7e700e700e7e7ULL, 0x0059590059005959ULL, 0x00e1e100e100e1e1ULL,
+ 0x00dada00da00dadaULL, 0x003d3d003d003d3dULL, 0x00c8c800c800c8c8ULL,
+ 0x0012120012001212ULL, 0x0004040004000404ULL, 0x0074740074007474ULL,
+ 0x0054540054005454ULL, 0x0030300030003030ULL, 0x007e7e007e007e7eULL,
+ 0x00b4b400b400b4b4ULL, 0x0028280028002828ULL, 0x0055550055005555ULL,
+ 0x0068680068006868ULL, 0x0050500050005050ULL, 0x00bebe00be00bebeULL,
+ 0x00d0d000d000d0d0ULL, 0x00c4c400c400c4c4ULL, 0x0031310031003131ULL,
+ 0x00cbcb00cb00cbcbULL, 0x002a2a002a002a2aULL, 0x00adad00ad00adadULL,
+ 0x000f0f000f000f0fULL, 0x00caca00ca00cacaULL, 0x0070700070007070ULL,
+ 0x00ffff00ff00ffffULL, 0x0032320032003232ULL, 0x0069690069006969ULL,
+ 0x0008080008000808ULL, 0x0062620062006262ULL, 0x0000000000000000ULL,
+ 0x0024240024002424ULL, 0x00d1d100d100d1d1ULL, 0x00fbfb00fb00fbfbULL,
+ 0x00baba00ba00babaULL, 0x00eded00ed00ededULL, 0x0045450045004545ULL,
+ 0x0081810081008181ULL, 0x0073730073007373ULL, 0x006d6d006d006d6dULL,
+ 0x0084840084008484ULL, 0x009f9f009f009f9fULL, 0x00eeee00ee00eeeeULL,
+ 0x004a4a004a004a4aULL, 0x00c3c300c300c3c3ULL, 0x002e2e002e002e2eULL,
+ 0x00c1c100c100c1c1ULL, 0x0001010001000101ULL, 0x00e6e600e600e6e6ULL,
+ 0x0025250025002525ULL, 0x0048480048004848ULL, 0x0099990099009999ULL,
+ 0x00b9b900b900b9b9ULL, 0x00b3b300b300b3b3ULL, 0x007b7b007b007b7bULL,
+ 0x00f9f900f900f9f9ULL, 0x00cece00ce00ceceULL, 0x00bfbf00bf00bfbfULL,
+ 0x00dfdf00df00dfdfULL, 0x0071710071007171ULL, 0x0029290029002929ULL,
+ 0x00cdcd00cd00cdcdULL, 0x006c6c006c006c6cULL, 0x0013130013001313ULL,
+ 0x0064640064006464ULL, 0x009b9b009b009b9bULL, 0x0063630063006363ULL,
+ 0x009d9d009d009d9dULL, 0x00c0c000c000c0c0ULL, 0x004b4b004b004b4bULL,
+ 0x00b7b700b700b7b7ULL, 0x00a5a500a500a5a5ULL, 0x0089890089008989ULL,
+ 0x005f5f005f005f5fULL, 0x00b1b100b100b1b1ULL, 0x0017170017001717ULL,
+ 0x00f4f400f400f4f4ULL, 0x00bcbc00bc00bcbcULL, 0x00d3d300d300d3d3ULL,
+ 0x0046460046004646ULL, 0x00cfcf00cf00cfcfULL, 0x0037370037003737ULL,
+ 0x005e5e005e005e5eULL, 0x0047470047004747ULL, 0x0094940094009494ULL,
+ 0x00fafa00fa00fafaULL, 0x00fcfc00fc00fcfcULL, 0x005b5b005b005b5bULL,
+ 0x0097970097009797ULL, 0x00fefe00fe00fefeULL, 0x005a5a005a005a5aULL,
+ 0x00acac00ac00acacULL, 0x003c3c003c003c3cULL, 0x004c4c004c004c4cULL,
+ 0x0003030003000303ULL, 0x0035350035003535ULL, 0x00f3f300f300f3f3ULL,
+ 0x0023230023002323ULL, 0x00b8b800b800b8b8ULL, 0x005d5d005d005d5dULL,
+ 0x006a6a006a006a6aULL, 0x0092920092009292ULL, 0x00d5d500d500d5d5ULL,
+ 0x0021210021002121ULL, 0x0044440044004444ULL, 0x0051510051005151ULL,
+ 0x00c6c600c600c6c6ULL, 0x007d7d007d007d7dULL, 0x0039390039003939ULL,
+ 0x0083830083008383ULL, 0x00dcdc00dc00dcdcULL, 0x00aaaa00aa00aaaaULL,
+ 0x007c7c007c007c7cULL, 0x0077770077007777ULL, 0x0056560056005656ULL,
+ 0x0005050005000505ULL, 0x001b1b001b001b1bULL, 0x00a4a400a400a4a4ULL,
+ 0x0015150015001515ULL, 0x0034340034003434ULL, 0x001e1e001e001e1eULL,
+ 0x001c1c001c001c1cULL, 0x00f8f800f800f8f8ULL, 0x0052520052005252ULL,
+ 0x0020200020002020ULL, 0x0014140014001414ULL, 0x00e9e900e900e9e9ULL,
+ 0x00bdbd00bd00bdbdULL, 0x00dddd00dd00ddddULL, 0x00e4e400e400e4e4ULL,
+ 0x00a1a100a100a1a1ULL, 0x00e0e000e000e0e0ULL, 0x008a8a008a008a8aULL,
+ 0x00f1f100f100f1f1ULL, 0x00d6d600d600d6d6ULL, 0x007a7a007a007a7aULL,
+ 0x00bbbb00bb00bbbbULL, 0x00e3e300e300e3e3ULL, 0x0040400040004040ULL,
+ 0x004f4f004f004f4fULL,
};
const u64 camellia_sp00444404[256] = {
- 0x0000707070700070, 0x00002c2c2c2c002c, 0x0000b3b3b3b300b3,
- 0x0000c0c0c0c000c0, 0x0000e4e4e4e400e4, 0x0000575757570057,
- 0x0000eaeaeaea00ea, 0x0000aeaeaeae00ae, 0x0000232323230023,
- 0x00006b6b6b6b006b, 0x0000454545450045, 0x0000a5a5a5a500a5,
- 0x0000edededed00ed, 0x00004f4f4f4f004f, 0x00001d1d1d1d001d,
- 0x0000929292920092, 0x0000868686860086, 0x0000afafafaf00af,
- 0x00007c7c7c7c007c, 0x00001f1f1f1f001f, 0x00003e3e3e3e003e,
- 0x0000dcdcdcdc00dc, 0x00005e5e5e5e005e, 0x00000b0b0b0b000b,
- 0x0000a6a6a6a600a6, 0x0000393939390039, 0x0000d5d5d5d500d5,
- 0x00005d5d5d5d005d, 0x0000d9d9d9d900d9, 0x00005a5a5a5a005a,
- 0x0000515151510051, 0x00006c6c6c6c006c, 0x00008b8b8b8b008b,
- 0x00009a9a9a9a009a, 0x0000fbfbfbfb00fb, 0x0000b0b0b0b000b0,
- 0x0000747474740074, 0x00002b2b2b2b002b, 0x0000f0f0f0f000f0,
- 0x0000848484840084, 0x0000dfdfdfdf00df, 0x0000cbcbcbcb00cb,
- 0x0000343434340034, 0x0000767676760076, 0x00006d6d6d6d006d,
- 0x0000a9a9a9a900a9, 0x0000d1d1d1d100d1, 0x0000040404040004,
- 0x0000141414140014, 0x00003a3a3a3a003a, 0x0000dededede00de,
- 0x0000111111110011, 0x0000323232320032, 0x00009c9c9c9c009c,
- 0x0000535353530053, 0x0000f2f2f2f200f2, 0x0000fefefefe00fe,
- 0x0000cfcfcfcf00cf, 0x0000c3c3c3c300c3, 0x00007a7a7a7a007a,
- 0x0000242424240024, 0x0000e8e8e8e800e8, 0x0000606060600060,
- 0x0000696969690069, 0x0000aaaaaaaa00aa, 0x0000a0a0a0a000a0,
- 0x0000a1a1a1a100a1, 0x0000626262620062, 0x0000545454540054,
- 0x00001e1e1e1e001e, 0x0000e0e0e0e000e0, 0x0000646464640064,
- 0x0000101010100010, 0x0000000000000000, 0x0000a3a3a3a300a3,
- 0x0000757575750075, 0x00008a8a8a8a008a, 0x0000e6e6e6e600e6,
- 0x0000090909090009, 0x0000dddddddd00dd, 0x0000878787870087,
- 0x0000838383830083, 0x0000cdcdcdcd00cd, 0x0000909090900090,
- 0x0000737373730073, 0x0000f6f6f6f600f6, 0x00009d9d9d9d009d,
- 0x0000bfbfbfbf00bf, 0x0000525252520052, 0x0000d8d8d8d800d8,
- 0x0000c8c8c8c800c8, 0x0000c6c6c6c600c6, 0x0000818181810081,
- 0x00006f6f6f6f006f, 0x0000131313130013, 0x0000636363630063,
- 0x0000e9e9e9e900e9, 0x0000a7a7a7a700a7, 0x00009f9f9f9f009f,
- 0x0000bcbcbcbc00bc, 0x0000292929290029, 0x0000f9f9f9f900f9,
- 0x00002f2f2f2f002f, 0x0000b4b4b4b400b4, 0x0000787878780078,
- 0x0000060606060006, 0x0000e7e7e7e700e7, 0x0000717171710071,
- 0x0000d4d4d4d400d4, 0x0000abababab00ab, 0x0000888888880088,
- 0x00008d8d8d8d008d, 0x0000727272720072, 0x0000b9b9b9b900b9,
- 0x0000f8f8f8f800f8, 0x0000acacacac00ac, 0x0000363636360036,
- 0x00002a2a2a2a002a, 0x00003c3c3c3c003c, 0x0000f1f1f1f100f1,
- 0x0000404040400040, 0x0000d3d3d3d300d3, 0x0000bbbbbbbb00bb,
- 0x0000434343430043, 0x0000151515150015, 0x0000adadadad00ad,
- 0x0000777777770077, 0x0000808080800080, 0x0000828282820082,
- 0x0000ecececec00ec, 0x0000272727270027, 0x0000e5e5e5e500e5,
- 0x0000858585850085, 0x0000353535350035, 0x00000c0c0c0c000c,
- 0x0000414141410041, 0x0000efefefef00ef, 0x0000939393930093,
- 0x0000191919190019, 0x0000212121210021, 0x00000e0e0e0e000e,
- 0x00004e4e4e4e004e, 0x0000656565650065, 0x0000bdbdbdbd00bd,
- 0x0000b8b8b8b800b8, 0x00008f8f8f8f008f, 0x0000ebebebeb00eb,
- 0x0000cececece00ce, 0x0000303030300030, 0x00005f5f5f5f005f,
- 0x0000c5c5c5c500c5, 0x00001a1a1a1a001a, 0x0000e1e1e1e100e1,
- 0x0000cacacaca00ca, 0x0000474747470047, 0x00003d3d3d3d003d,
- 0x0000010101010001, 0x0000d6d6d6d600d6, 0x0000565656560056,
- 0x00004d4d4d4d004d, 0x00000d0d0d0d000d, 0x0000666666660066,
- 0x0000cccccccc00cc, 0x00002d2d2d2d002d, 0x0000121212120012,
- 0x0000202020200020, 0x0000b1b1b1b100b1, 0x0000999999990099,
- 0x00004c4c4c4c004c, 0x0000c2c2c2c200c2, 0x00007e7e7e7e007e,
- 0x0000050505050005, 0x0000b7b7b7b700b7, 0x0000313131310031,
- 0x0000171717170017, 0x0000d7d7d7d700d7, 0x0000585858580058,
- 0x0000616161610061, 0x00001b1b1b1b001b, 0x00001c1c1c1c001c,
- 0x00000f0f0f0f000f, 0x0000161616160016, 0x0000181818180018,
- 0x0000222222220022, 0x0000444444440044, 0x0000b2b2b2b200b2,
- 0x0000b5b5b5b500b5, 0x0000919191910091, 0x0000080808080008,
- 0x0000a8a8a8a800a8, 0x0000fcfcfcfc00fc, 0x0000505050500050,
- 0x0000d0d0d0d000d0, 0x00007d7d7d7d007d, 0x0000898989890089,
- 0x0000979797970097, 0x00005b5b5b5b005b, 0x0000959595950095,
- 0x0000ffffffff00ff, 0x0000d2d2d2d200d2, 0x0000c4c4c4c400c4,
- 0x0000484848480048, 0x0000f7f7f7f700f7, 0x0000dbdbdbdb00db,
- 0x0000030303030003, 0x0000dadadada00da, 0x00003f3f3f3f003f,
- 0x0000949494940094, 0x00005c5c5c5c005c, 0x0000020202020002,
- 0x00004a4a4a4a004a, 0x0000333333330033, 0x0000676767670067,
- 0x0000f3f3f3f300f3, 0x00007f7f7f7f007f, 0x0000e2e2e2e200e2,
- 0x00009b9b9b9b009b, 0x0000262626260026, 0x0000373737370037,
- 0x00003b3b3b3b003b, 0x0000969696960096, 0x00004b4b4b4b004b,
- 0x0000bebebebe00be, 0x00002e2e2e2e002e, 0x0000797979790079,
- 0x00008c8c8c8c008c, 0x00006e6e6e6e006e, 0x00008e8e8e8e008e,
- 0x0000f5f5f5f500f5, 0x0000b6b6b6b600b6, 0x0000fdfdfdfd00fd,
- 0x0000595959590059, 0x0000989898980098, 0x00006a6a6a6a006a,
- 0x0000464646460046, 0x0000babababa00ba, 0x0000252525250025,
- 0x0000424242420042, 0x0000a2a2a2a200a2, 0x0000fafafafa00fa,
- 0x0000070707070007, 0x0000555555550055, 0x0000eeeeeeee00ee,
- 0x00000a0a0a0a000a, 0x0000494949490049, 0x0000686868680068,
- 0x0000383838380038, 0x0000a4a4a4a400a4, 0x0000282828280028,
- 0x00007b7b7b7b007b, 0x0000c9c9c9c900c9, 0x0000c1c1c1c100c1,
- 0x0000e3e3e3e300e3, 0x0000f4f4f4f400f4, 0x0000c7c7c7c700c7,
- 0x00009e9e9e9e009e,
+ 0x0000707070700070ULL, 0x00002c2c2c2c002cULL, 0x0000b3b3b3b300b3ULL,
+ 0x0000c0c0c0c000c0ULL, 0x0000e4e4e4e400e4ULL, 0x0000575757570057ULL,
+ 0x0000eaeaeaea00eaULL, 0x0000aeaeaeae00aeULL, 0x0000232323230023ULL,
+ 0x00006b6b6b6b006bULL, 0x0000454545450045ULL, 0x0000a5a5a5a500a5ULL,
+ 0x0000edededed00edULL, 0x00004f4f4f4f004fULL, 0x00001d1d1d1d001dULL,
+ 0x0000929292920092ULL, 0x0000868686860086ULL, 0x0000afafafaf00afULL,
+ 0x00007c7c7c7c007cULL, 0x00001f1f1f1f001fULL, 0x00003e3e3e3e003eULL,
+ 0x0000dcdcdcdc00dcULL, 0x00005e5e5e5e005eULL, 0x00000b0b0b0b000bULL,
+ 0x0000a6a6a6a600a6ULL, 0x0000393939390039ULL, 0x0000d5d5d5d500d5ULL,
+ 0x00005d5d5d5d005dULL, 0x0000d9d9d9d900d9ULL, 0x00005a5a5a5a005aULL,
+ 0x0000515151510051ULL, 0x00006c6c6c6c006cULL, 0x00008b8b8b8b008bULL,
+ 0x00009a9a9a9a009aULL, 0x0000fbfbfbfb00fbULL, 0x0000b0b0b0b000b0ULL,
+ 0x0000747474740074ULL, 0x00002b2b2b2b002bULL, 0x0000f0f0f0f000f0ULL,
+ 0x0000848484840084ULL, 0x0000dfdfdfdf00dfULL, 0x0000cbcbcbcb00cbULL,
+ 0x0000343434340034ULL, 0x0000767676760076ULL, 0x00006d6d6d6d006dULL,
+ 0x0000a9a9a9a900a9ULL, 0x0000d1d1d1d100d1ULL, 0x0000040404040004ULL,
+ 0x0000141414140014ULL, 0x00003a3a3a3a003aULL, 0x0000dededede00deULL,
+ 0x0000111111110011ULL, 0x0000323232320032ULL, 0x00009c9c9c9c009cULL,
+ 0x0000535353530053ULL, 0x0000f2f2f2f200f2ULL, 0x0000fefefefe00feULL,
+ 0x0000cfcfcfcf00cfULL, 0x0000c3c3c3c300c3ULL, 0x00007a7a7a7a007aULL,
+ 0x0000242424240024ULL, 0x0000e8e8e8e800e8ULL, 0x0000606060600060ULL,
+ 0x0000696969690069ULL, 0x0000aaaaaaaa00aaULL, 0x0000a0a0a0a000a0ULL,
+ 0x0000a1a1a1a100a1ULL, 0x0000626262620062ULL, 0x0000545454540054ULL,
+ 0x00001e1e1e1e001eULL, 0x0000e0e0e0e000e0ULL, 0x0000646464640064ULL,
+ 0x0000101010100010ULL, 0x0000000000000000ULL, 0x0000a3a3a3a300a3ULL,
+ 0x0000757575750075ULL, 0x00008a8a8a8a008aULL, 0x0000e6e6e6e600e6ULL,
+ 0x0000090909090009ULL, 0x0000dddddddd00ddULL, 0x0000878787870087ULL,
+ 0x0000838383830083ULL, 0x0000cdcdcdcd00cdULL, 0x0000909090900090ULL,
+ 0x0000737373730073ULL, 0x0000f6f6f6f600f6ULL, 0x00009d9d9d9d009dULL,
+ 0x0000bfbfbfbf00bfULL, 0x0000525252520052ULL, 0x0000d8d8d8d800d8ULL,
+ 0x0000c8c8c8c800c8ULL, 0x0000c6c6c6c600c6ULL, 0x0000818181810081ULL,
+ 0x00006f6f6f6f006fULL, 0x0000131313130013ULL, 0x0000636363630063ULL,
+ 0x0000e9e9e9e900e9ULL, 0x0000a7a7a7a700a7ULL, 0x00009f9f9f9f009fULL,
+ 0x0000bcbcbcbc00bcULL, 0x0000292929290029ULL, 0x0000f9f9f9f900f9ULL,
+ 0x00002f2f2f2f002fULL, 0x0000b4b4b4b400b4ULL, 0x0000787878780078ULL,
+ 0x0000060606060006ULL, 0x0000e7e7e7e700e7ULL, 0x0000717171710071ULL,
+ 0x0000d4d4d4d400d4ULL, 0x0000abababab00abULL, 0x0000888888880088ULL,
+ 0x00008d8d8d8d008dULL, 0x0000727272720072ULL, 0x0000b9b9b9b900b9ULL,
+ 0x0000f8f8f8f800f8ULL, 0x0000acacacac00acULL, 0x0000363636360036ULL,
+ 0x00002a2a2a2a002aULL, 0x00003c3c3c3c003cULL, 0x0000f1f1f1f100f1ULL,
+ 0x0000404040400040ULL, 0x0000d3d3d3d300d3ULL, 0x0000bbbbbbbb00bbULL,
+ 0x0000434343430043ULL, 0x0000151515150015ULL, 0x0000adadadad00adULL,
+ 0x0000777777770077ULL, 0x0000808080800080ULL, 0x0000828282820082ULL,
+ 0x0000ecececec00ecULL, 0x0000272727270027ULL, 0x0000e5e5e5e500e5ULL,
+ 0x0000858585850085ULL, 0x0000353535350035ULL, 0x00000c0c0c0c000cULL,
+ 0x0000414141410041ULL, 0x0000efefefef00efULL, 0x0000939393930093ULL,
+ 0x0000191919190019ULL, 0x0000212121210021ULL, 0x00000e0e0e0e000eULL,
+ 0x00004e4e4e4e004eULL, 0x0000656565650065ULL, 0x0000bdbdbdbd00bdULL,
+ 0x0000b8b8b8b800b8ULL, 0x00008f8f8f8f008fULL, 0x0000ebebebeb00ebULL,
+ 0x0000cececece00ceULL, 0x0000303030300030ULL, 0x00005f5f5f5f005fULL,
+ 0x0000c5c5c5c500c5ULL, 0x00001a1a1a1a001aULL, 0x0000e1e1e1e100e1ULL,
+ 0x0000cacacaca00caULL, 0x0000474747470047ULL, 0x00003d3d3d3d003dULL,
+ 0x0000010101010001ULL, 0x0000d6d6d6d600d6ULL, 0x0000565656560056ULL,
+ 0x00004d4d4d4d004dULL, 0x00000d0d0d0d000dULL, 0x0000666666660066ULL,
+ 0x0000cccccccc00ccULL, 0x00002d2d2d2d002dULL, 0x0000121212120012ULL,
+ 0x0000202020200020ULL, 0x0000b1b1b1b100b1ULL, 0x0000999999990099ULL,
+ 0x00004c4c4c4c004cULL, 0x0000c2c2c2c200c2ULL, 0x00007e7e7e7e007eULL,
+ 0x0000050505050005ULL, 0x0000b7b7b7b700b7ULL, 0x0000313131310031ULL,
+ 0x0000171717170017ULL, 0x0000d7d7d7d700d7ULL, 0x0000585858580058ULL,
+ 0x0000616161610061ULL, 0x00001b1b1b1b001bULL, 0x00001c1c1c1c001cULL,
+ 0x00000f0f0f0f000fULL, 0x0000161616160016ULL, 0x0000181818180018ULL,
+ 0x0000222222220022ULL, 0x0000444444440044ULL, 0x0000b2b2b2b200b2ULL,
+ 0x0000b5b5b5b500b5ULL, 0x0000919191910091ULL, 0x0000080808080008ULL,
+ 0x0000a8a8a8a800a8ULL, 0x0000fcfcfcfc00fcULL, 0x0000505050500050ULL,
+ 0x0000d0d0d0d000d0ULL, 0x00007d7d7d7d007dULL, 0x0000898989890089ULL,
+ 0x0000979797970097ULL, 0x00005b5b5b5b005bULL, 0x0000959595950095ULL,
+ 0x0000ffffffff00ffULL, 0x0000d2d2d2d200d2ULL, 0x0000c4c4c4c400c4ULL,
+ 0x0000484848480048ULL, 0x0000f7f7f7f700f7ULL, 0x0000dbdbdbdb00dbULL,
+ 0x0000030303030003ULL, 0x0000dadadada00daULL, 0x00003f3f3f3f003fULL,
+ 0x0000949494940094ULL, 0x00005c5c5c5c005cULL, 0x0000020202020002ULL,
+ 0x00004a4a4a4a004aULL, 0x0000333333330033ULL, 0x0000676767670067ULL,
+ 0x0000f3f3f3f300f3ULL, 0x00007f7f7f7f007fULL, 0x0000e2e2e2e200e2ULL,
+ 0x00009b9b9b9b009bULL, 0x0000262626260026ULL, 0x0000373737370037ULL,
+ 0x00003b3b3b3b003bULL, 0x0000969696960096ULL, 0x00004b4b4b4b004bULL,
+ 0x0000bebebebe00beULL, 0x00002e2e2e2e002eULL, 0x0000797979790079ULL,
+ 0x00008c8c8c8c008cULL, 0x00006e6e6e6e006eULL, 0x00008e8e8e8e008eULL,
+ 0x0000f5f5f5f500f5ULL, 0x0000b6b6b6b600b6ULL, 0x0000fdfdfdfd00fdULL,
+ 0x0000595959590059ULL, 0x0000989898980098ULL, 0x00006a6a6a6a006aULL,
+ 0x0000464646460046ULL, 0x0000babababa00baULL, 0x0000252525250025ULL,
+ 0x0000424242420042ULL, 0x0000a2a2a2a200a2ULL, 0x0000fafafafa00faULL,
+ 0x0000070707070007ULL, 0x0000555555550055ULL, 0x0000eeeeeeee00eeULL,
+ 0x00000a0a0a0a000aULL, 0x0000494949490049ULL, 0x0000686868680068ULL,
+ 0x0000383838380038ULL, 0x0000a4a4a4a400a4ULL, 0x0000282828280028ULL,
+ 0x00007b7b7b7b007bULL, 0x0000c9c9c9c900c9ULL, 0x0000c1c1c1c100c1ULL,
+ 0x0000e3e3e3e300e3ULL, 0x0000f4f4f4f400f4ULL, 0x0000c7c7c7c700c7ULL,
+ 0x00009e9e9e9e009eULL,
};
const u64 camellia_sp02220222[256] = {
- 0x00e0e0e000e0e0e0, 0x0005050500050505, 0x0058585800585858,
- 0x00d9d9d900d9d9d9, 0x0067676700676767, 0x004e4e4e004e4e4e,
- 0x0081818100818181, 0x00cbcbcb00cbcbcb, 0x00c9c9c900c9c9c9,
- 0x000b0b0b000b0b0b, 0x00aeaeae00aeaeae, 0x006a6a6a006a6a6a,
- 0x00d5d5d500d5d5d5, 0x0018181800181818, 0x005d5d5d005d5d5d,
- 0x0082828200828282, 0x0046464600464646, 0x00dfdfdf00dfdfdf,
- 0x00d6d6d600d6d6d6, 0x0027272700272727, 0x008a8a8a008a8a8a,
- 0x0032323200323232, 0x004b4b4b004b4b4b, 0x0042424200424242,
- 0x00dbdbdb00dbdbdb, 0x001c1c1c001c1c1c, 0x009e9e9e009e9e9e,
- 0x009c9c9c009c9c9c, 0x003a3a3a003a3a3a, 0x00cacaca00cacaca,
- 0x0025252500252525, 0x007b7b7b007b7b7b, 0x000d0d0d000d0d0d,
- 0x0071717100717171, 0x005f5f5f005f5f5f, 0x001f1f1f001f1f1f,
- 0x00f8f8f800f8f8f8, 0x00d7d7d700d7d7d7, 0x003e3e3e003e3e3e,
- 0x009d9d9d009d9d9d, 0x007c7c7c007c7c7c, 0x0060606000606060,
- 0x00b9b9b900b9b9b9, 0x00bebebe00bebebe, 0x00bcbcbc00bcbcbc,
- 0x008b8b8b008b8b8b, 0x0016161600161616, 0x0034343400343434,
- 0x004d4d4d004d4d4d, 0x00c3c3c300c3c3c3, 0x0072727200727272,
- 0x0095959500959595, 0x00ababab00ababab, 0x008e8e8e008e8e8e,
- 0x00bababa00bababa, 0x007a7a7a007a7a7a, 0x00b3b3b300b3b3b3,
- 0x0002020200020202, 0x00b4b4b400b4b4b4, 0x00adadad00adadad,
- 0x00a2a2a200a2a2a2, 0x00acacac00acacac, 0x00d8d8d800d8d8d8,
- 0x009a9a9a009a9a9a, 0x0017171700171717, 0x001a1a1a001a1a1a,
- 0x0035353500353535, 0x00cccccc00cccccc, 0x00f7f7f700f7f7f7,
- 0x0099999900999999, 0x0061616100616161, 0x005a5a5a005a5a5a,
- 0x00e8e8e800e8e8e8, 0x0024242400242424, 0x0056565600565656,
- 0x0040404000404040, 0x00e1e1e100e1e1e1, 0x0063636300636363,
- 0x0009090900090909, 0x0033333300333333, 0x00bfbfbf00bfbfbf,
- 0x0098989800989898, 0x0097979700979797, 0x0085858500858585,
- 0x0068686800686868, 0x00fcfcfc00fcfcfc, 0x00ececec00ececec,
- 0x000a0a0a000a0a0a, 0x00dadada00dadada, 0x006f6f6f006f6f6f,
- 0x0053535300535353, 0x0062626200626262, 0x00a3a3a300a3a3a3,
- 0x002e2e2e002e2e2e, 0x0008080800080808, 0x00afafaf00afafaf,
- 0x0028282800282828, 0x00b0b0b000b0b0b0, 0x0074747400747474,
- 0x00c2c2c200c2c2c2, 0x00bdbdbd00bdbdbd, 0x0036363600363636,
- 0x0022222200222222, 0x0038383800383838, 0x0064646400646464,
- 0x001e1e1e001e1e1e, 0x0039393900393939, 0x002c2c2c002c2c2c,
- 0x00a6a6a600a6a6a6, 0x0030303000303030, 0x00e5e5e500e5e5e5,
- 0x0044444400444444, 0x00fdfdfd00fdfdfd, 0x0088888800888888,
- 0x009f9f9f009f9f9f, 0x0065656500656565, 0x0087878700878787,
- 0x006b6b6b006b6b6b, 0x00f4f4f400f4f4f4, 0x0023232300232323,
- 0x0048484800484848, 0x0010101000101010, 0x00d1d1d100d1d1d1,
- 0x0051515100515151, 0x00c0c0c000c0c0c0, 0x00f9f9f900f9f9f9,
- 0x00d2d2d200d2d2d2, 0x00a0a0a000a0a0a0, 0x0055555500555555,
- 0x00a1a1a100a1a1a1, 0x0041414100414141, 0x00fafafa00fafafa,
- 0x0043434300434343, 0x0013131300131313, 0x00c4c4c400c4c4c4,
- 0x002f2f2f002f2f2f, 0x00a8a8a800a8a8a8, 0x00b6b6b600b6b6b6,
- 0x003c3c3c003c3c3c, 0x002b2b2b002b2b2b, 0x00c1c1c100c1c1c1,
- 0x00ffffff00ffffff, 0x00c8c8c800c8c8c8, 0x00a5a5a500a5a5a5,
- 0x0020202000202020, 0x0089898900898989, 0x0000000000000000,
- 0x0090909000909090, 0x0047474700474747, 0x00efefef00efefef,
- 0x00eaeaea00eaeaea, 0x00b7b7b700b7b7b7, 0x0015151500151515,
- 0x0006060600060606, 0x00cdcdcd00cdcdcd, 0x00b5b5b500b5b5b5,
- 0x0012121200121212, 0x007e7e7e007e7e7e, 0x00bbbbbb00bbbbbb,
- 0x0029292900292929, 0x000f0f0f000f0f0f, 0x00b8b8b800b8b8b8,
- 0x0007070700070707, 0x0004040400040404, 0x009b9b9b009b9b9b,
- 0x0094949400949494, 0x0021212100212121, 0x0066666600666666,
- 0x00e6e6e600e6e6e6, 0x00cecece00cecece, 0x00ededed00ededed,
- 0x00e7e7e700e7e7e7, 0x003b3b3b003b3b3b, 0x00fefefe00fefefe,
- 0x007f7f7f007f7f7f, 0x00c5c5c500c5c5c5, 0x00a4a4a400a4a4a4,
- 0x0037373700373737, 0x00b1b1b100b1b1b1, 0x004c4c4c004c4c4c,
- 0x0091919100919191, 0x006e6e6e006e6e6e, 0x008d8d8d008d8d8d,
- 0x0076767600767676, 0x0003030300030303, 0x002d2d2d002d2d2d,
- 0x00dedede00dedede, 0x0096969600969696, 0x0026262600262626,
- 0x007d7d7d007d7d7d, 0x00c6c6c600c6c6c6, 0x005c5c5c005c5c5c,
- 0x00d3d3d300d3d3d3, 0x00f2f2f200f2f2f2, 0x004f4f4f004f4f4f,
- 0x0019191900191919, 0x003f3f3f003f3f3f, 0x00dcdcdc00dcdcdc,
- 0x0079797900797979, 0x001d1d1d001d1d1d, 0x0052525200525252,
- 0x00ebebeb00ebebeb, 0x00f3f3f300f3f3f3, 0x006d6d6d006d6d6d,
- 0x005e5e5e005e5e5e, 0x00fbfbfb00fbfbfb, 0x0069696900696969,
- 0x00b2b2b200b2b2b2, 0x00f0f0f000f0f0f0, 0x0031313100313131,
- 0x000c0c0c000c0c0c, 0x00d4d4d400d4d4d4, 0x00cfcfcf00cfcfcf,
- 0x008c8c8c008c8c8c, 0x00e2e2e200e2e2e2, 0x0075757500757575,
- 0x00a9a9a900a9a9a9, 0x004a4a4a004a4a4a, 0x0057575700575757,
- 0x0084848400848484, 0x0011111100111111, 0x0045454500454545,
- 0x001b1b1b001b1b1b, 0x00f5f5f500f5f5f5, 0x00e4e4e400e4e4e4,
- 0x000e0e0e000e0e0e, 0x0073737300737373, 0x00aaaaaa00aaaaaa,
- 0x00f1f1f100f1f1f1, 0x00dddddd00dddddd, 0x0059595900595959,
- 0x0014141400141414, 0x006c6c6c006c6c6c, 0x0092929200929292,
- 0x0054545400545454, 0x00d0d0d000d0d0d0, 0x0078787800787878,
- 0x0070707000707070, 0x00e3e3e300e3e3e3, 0x0049494900494949,
- 0x0080808000808080, 0x0050505000505050, 0x00a7a7a700a7a7a7,
- 0x00f6f6f600f6f6f6, 0x0077777700777777, 0x0093939300939393,
- 0x0086868600868686, 0x0083838300838383, 0x002a2a2a002a2a2a,
- 0x00c7c7c700c7c7c7, 0x005b5b5b005b5b5b, 0x00e9e9e900e9e9e9,
- 0x00eeeeee00eeeeee, 0x008f8f8f008f8f8f, 0x0001010100010101,
- 0x003d3d3d003d3d3d,
+ 0x00e0e0e000e0e0e0ULL, 0x0005050500050505ULL, 0x0058585800585858ULL,
+ 0x00d9d9d900d9d9d9ULL, 0x0067676700676767ULL, 0x004e4e4e004e4e4eULL,
+ 0x0081818100818181ULL, 0x00cbcbcb00cbcbcbULL, 0x00c9c9c900c9c9c9ULL,
+ 0x000b0b0b000b0b0bULL, 0x00aeaeae00aeaeaeULL, 0x006a6a6a006a6a6aULL,
+ 0x00d5d5d500d5d5d5ULL, 0x0018181800181818ULL, 0x005d5d5d005d5d5dULL,
+ 0x0082828200828282ULL, 0x0046464600464646ULL, 0x00dfdfdf00dfdfdfULL,
+ 0x00d6d6d600d6d6d6ULL, 0x0027272700272727ULL, 0x008a8a8a008a8a8aULL,
+ 0x0032323200323232ULL, 0x004b4b4b004b4b4bULL, 0x0042424200424242ULL,
+ 0x00dbdbdb00dbdbdbULL, 0x001c1c1c001c1c1cULL, 0x009e9e9e009e9e9eULL,
+ 0x009c9c9c009c9c9cULL, 0x003a3a3a003a3a3aULL, 0x00cacaca00cacacaULL,
+ 0x0025252500252525ULL, 0x007b7b7b007b7b7bULL, 0x000d0d0d000d0d0dULL,
+ 0x0071717100717171ULL, 0x005f5f5f005f5f5fULL, 0x001f1f1f001f1f1fULL,
+ 0x00f8f8f800f8f8f8ULL, 0x00d7d7d700d7d7d7ULL, 0x003e3e3e003e3e3eULL,
+ 0x009d9d9d009d9d9dULL, 0x007c7c7c007c7c7cULL, 0x0060606000606060ULL,
+ 0x00b9b9b900b9b9b9ULL, 0x00bebebe00bebebeULL, 0x00bcbcbc00bcbcbcULL,
+ 0x008b8b8b008b8b8bULL, 0x0016161600161616ULL, 0x0034343400343434ULL,
+ 0x004d4d4d004d4d4dULL, 0x00c3c3c300c3c3c3ULL, 0x0072727200727272ULL,
+ 0x0095959500959595ULL, 0x00ababab00abababULL, 0x008e8e8e008e8e8eULL,
+ 0x00bababa00bababaULL, 0x007a7a7a007a7a7aULL, 0x00b3b3b300b3b3b3ULL,
+ 0x0002020200020202ULL, 0x00b4b4b400b4b4b4ULL, 0x00adadad00adadadULL,
+ 0x00a2a2a200a2a2a2ULL, 0x00acacac00acacacULL, 0x00d8d8d800d8d8d8ULL,
+ 0x009a9a9a009a9a9aULL, 0x0017171700171717ULL, 0x001a1a1a001a1a1aULL,
+ 0x0035353500353535ULL, 0x00cccccc00ccccccULL, 0x00f7f7f700f7f7f7ULL,
+ 0x0099999900999999ULL, 0x0061616100616161ULL, 0x005a5a5a005a5a5aULL,
+ 0x00e8e8e800e8e8e8ULL, 0x0024242400242424ULL, 0x0056565600565656ULL,
+ 0x0040404000404040ULL, 0x00e1e1e100e1e1e1ULL, 0x0063636300636363ULL,
+ 0x0009090900090909ULL, 0x0033333300333333ULL, 0x00bfbfbf00bfbfbfULL,
+ 0x0098989800989898ULL, 0x0097979700979797ULL, 0x0085858500858585ULL,
+ 0x0068686800686868ULL, 0x00fcfcfc00fcfcfcULL, 0x00ececec00ecececULL,
+ 0x000a0a0a000a0a0aULL, 0x00dadada00dadadaULL, 0x006f6f6f006f6f6fULL,
+ 0x0053535300535353ULL, 0x0062626200626262ULL, 0x00a3a3a300a3a3a3ULL,
+ 0x002e2e2e002e2e2eULL, 0x0008080800080808ULL, 0x00afafaf00afafafULL,
+ 0x0028282800282828ULL, 0x00b0b0b000b0b0b0ULL, 0x0074747400747474ULL,
+ 0x00c2c2c200c2c2c2ULL, 0x00bdbdbd00bdbdbdULL, 0x0036363600363636ULL,
+ 0x0022222200222222ULL, 0x0038383800383838ULL, 0x0064646400646464ULL,
+ 0x001e1e1e001e1e1eULL, 0x0039393900393939ULL, 0x002c2c2c002c2c2cULL,
+ 0x00a6a6a600a6a6a6ULL, 0x0030303000303030ULL, 0x00e5e5e500e5e5e5ULL,
+ 0x0044444400444444ULL, 0x00fdfdfd00fdfdfdULL, 0x0088888800888888ULL,
+ 0x009f9f9f009f9f9fULL, 0x0065656500656565ULL, 0x0087878700878787ULL,
+ 0x006b6b6b006b6b6bULL, 0x00f4f4f400f4f4f4ULL, 0x0023232300232323ULL,
+ 0x0048484800484848ULL, 0x0010101000101010ULL, 0x00d1d1d100d1d1d1ULL,
+ 0x0051515100515151ULL, 0x00c0c0c000c0c0c0ULL, 0x00f9f9f900f9f9f9ULL,
+ 0x00d2d2d200d2d2d2ULL, 0x00a0a0a000a0a0a0ULL, 0x0055555500555555ULL,
+ 0x00a1a1a100a1a1a1ULL, 0x0041414100414141ULL, 0x00fafafa00fafafaULL,
+ 0x0043434300434343ULL, 0x0013131300131313ULL, 0x00c4c4c400c4c4c4ULL,
+ 0x002f2f2f002f2f2fULL, 0x00a8a8a800a8a8a8ULL, 0x00b6b6b600b6b6b6ULL,
+ 0x003c3c3c003c3c3cULL, 0x002b2b2b002b2b2bULL, 0x00c1c1c100c1c1c1ULL,
+ 0x00ffffff00ffffffULL, 0x00c8c8c800c8c8c8ULL, 0x00a5a5a500a5a5a5ULL,
+ 0x0020202000202020ULL, 0x0089898900898989ULL, 0x0000000000000000ULL,
+ 0x0090909000909090ULL, 0x0047474700474747ULL, 0x00efefef00efefefULL,
+ 0x00eaeaea00eaeaeaULL, 0x00b7b7b700b7b7b7ULL, 0x0015151500151515ULL,
+ 0x0006060600060606ULL, 0x00cdcdcd00cdcdcdULL, 0x00b5b5b500b5b5b5ULL,
+ 0x0012121200121212ULL, 0x007e7e7e007e7e7eULL, 0x00bbbbbb00bbbbbbULL,
+ 0x0029292900292929ULL, 0x000f0f0f000f0f0fULL, 0x00b8b8b800b8b8b8ULL,
+ 0x0007070700070707ULL, 0x0004040400040404ULL, 0x009b9b9b009b9b9bULL,
+ 0x0094949400949494ULL, 0x0021212100212121ULL, 0x0066666600666666ULL,
+ 0x00e6e6e600e6e6e6ULL, 0x00cecece00cececeULL, 0x00ededed00edededULL,
+ 0x00e7e7e700e7e7e7ULL, 0x003b3b3b003b3b3bULL, 0x00fefefe00fefefeULL,
+ 0x007f7f7f007f7f7fULL, 0x00c5c5c500c5c5c5ULL, 0x00a4a4a400a4a4a4ULL,
+ 0x0037373700373737ULL, 0x00b1b1b100b1b1b1ULL, 0x004c4c4c004c4c4cULL,
+ 0x0091919100919191ULL, 0x006e6e6e006e6e6eULL, 0x008d8d8d008d8d8dULL,
+ 0x0076767600767676ULL, 0x0003030300030303ULL, 0x002d2d2d002d2d2dULL,
+ 0x00dedede00dededeULL, 0x0096969600969696ULL, 0x0026262600262626ULL,
+ 0x007d7d7d007d7d7dULL, 0x00c6c6c600c6c6c6ULL, 0x005c5c5c005c5c5cULL,
+ 0x00d3d3d300d3d3d3ULL, 0x00f2f2f200f2f2f2ULL, 0x004f4f4f004f4f4fULL,
+ 0x0019191900191919ULL, 0x003f3f3f003f3f3fULL, 0x00dcdcdc00dcdcdcULL,
+ 0x0079797900797979ULL, 0x001d1d1d001d1d1dULL, 0x0052525200525252ULL,
+ 0x00ebebeb00ebebebULL, 0x00f3f3f300f3f3f3ULL, 0x006d6d6d006d6d6dULL,
+ 0x005e5e5e005e5e5eULL, 0x00fbfbfb00fbfbfbULL, 0x0069696900696969ULL,
+ 0x00b2b2b200b2b2b2ULL, 0x00f0f0f000f0f0f0ULL, 0x0031313100313131ULL,
+ 0x000c0c0c000c0c0cULL, 0x00d4d4d400d4d4d4ULL, 0x00cfcfcf00cfcfcfULL,
+ 0x008c8c8c008c8c8cULL, 0x00e2e2e200e2e2e2ULL, 0x0075757500757575ULL,
+ 0x00a9a9a900a9a9a9ULL, 0x004a4a4a004a4a4aULL, 0x0057575700575757ULL,
+ 0x0084848400848484ULL, 0x0011111100111111ULL, 0x0045454500454545ULL,
+ 0x001b1b1b001b1b1bULL, 0x00f5f5f500f5f5f5ULL, 0x00e4e4e400e4e4e4ULL,
+ 0x000e0e0e000e0e0eULL, 0x0073737300737373ULL, 0x00aaaaaa00aaaaaaULL,
+ 0x00f1f1f100f1f1f1ULL, 0x00dddddd00ddddddULL, 0x0059595900595959ULL,
+ 0x0014141400141414ULL, 0x006c6c6c006c6c6cULL, 0x0092929200929292ULL,
+ 0x0054545400545454ULL, 0x00d0d0d000d0d0d0ULL, 0x0078787800787878ULL,
+ 0x0070707000707070ULL, 0x00e3e3e300e3e3e3ULL, 0x0049494900494949ULL,
+ 0x0080808000808080ULL, 0x0050505000505050ULL, 0x00a7a7a700a7a7a7ULL,
+ 0x00f6f6f600f6f6f6ULL, 0x0077777700777777ULL, 0x0093939300939393ULL,
+ 0x0086868600868686ULL, 0x0083838300838383ULL, 0x002a2a2a002a2a2aULL,
+ 0x00c7c7c700c7c7c7ULL, 0x005b5b5b005b5b5bULL, 0x00e9e9e900e9e9e9ULL,
+ 0x00eeeeee00eeeeeeULL, 0x008f8f8f008f8f8fULL, 0x0001010100010101ULL,
+ 0x003d3d3d003d3d3dULL,
};
const u64 camellia_sp30333033[256] = {
- 0x3800383838003838, 0x4100414141004141, 0x1600161616001616,
- 0x7600767676007676, 0xd900d9d9d900d9d9, 0x9300939393009393,
- 0x6000606060006060, 0xf200f2f2f200f2f2, 0x7200727272007272,
- 0xc200c2c2c200c2c2, 0xab00ababab00abab, 0x9a009a9a9a009a9a,
- 0x7500757575007575, 0x0600060606000606, 0x5700575757005757,
- 0xa000a0a0a000a0a0, 0x9100919191009191, 0xf700f7f7f700f7f7,
- 0xb500b5b5b500b5b5, 0xc900c9c9c900c9c9, 0xa200a2a2a200a2a2,
- 0x8c008c8c8c008c8c, 0xd200d2d2d200d2d2, 0x9000909090009090,
- 0xf600f6f6f600f6f6, 0x0700070707000707, 0xa700a7a7a700a7a7,
- 0x2700272727002727, 0x8e008e8e8e008e8e, 0xb200b2b2b200b2b2,
- 0x4900494949004949, 0xde00dedede00dede, 0x4300434343004343,
- 0x5c005c5c5c005c5c, 0xd700d7d7d700d7d7, 0xc700c7c7c700c7c7,
- 0x3e003e3e3e003e3e, 0xf500f5f5f500f5f5, 0x8f008f8f8f008f8f,
- 0x6700676767006767, 0x1f001f1f1f001f1f, 0x1800181818001818,
- 0x6e006e6e6e006e6e, 0xaf00afafaf00afaf, 0x2f002f2f2f002f2f,
- 0xe200e2e2e200e2e2, 0x8500858585008585, 0x0d000d0d0d000d0d,
- 0x5300535353005353, 0xf000f0f0f000f0f0, 0x9c009c9c9c009c9c,
- 0x6500656565006565, 0xea00eaeaea00eaea, 0xa300a3a3a300a3a3,
- 0xae00aeaeae00aeae, 0x9e009e9e9e009e9e, 0xec00ececec00ecec,
- 0x8000808080008080, 0x2d002d2d2d002d2d, 0x6b006b6b6b006b6b,
- 0xa800a8a8a800a8a8, 0x2b002b2b2b002b2b, 0x3600363636003636,
- 0xa600a6a6a600a6a6, 0xc500c5c5c500c5c5, 0x8600868686008686,
- 0x4d004d4d4d004d4d, 0x3300333333003333, 0xfd00fdfdfd00fdfd,
- 0x6600666666006666, 0x5800585858005858, 0x9600969696009696,
- 0x3a003a3a3a003a3a, 0x0900090909000909, 0x9500959595009595,
- 0x1000101010001010, 0x7800787878007878, 0xd800d8d8d800d8d8,
- 0x4200424242004242, 0xcc00cccccc00cccc, 0xef00efefef00efef,
- 0x2600262626002626, 0xe500e5e5e500e5e5, 0x6100616161006161,
- 0x1a001a1a1a001a1a, 0x3f003f3f3f003f3f, 0x3b003b3b3b003b3b,
- 0x8200828282008282, 0xb600b6b6b600b6b6, 0xdb00dbdbdb00dbdb,
- 0xd400d4d4d400d4d4, 0x9800989898009898, 0xe800e8e8e800e8e8,
- 0x8b008b8b8b008b8b, 0x0200020202000202, 0xeb00ebebeb00ebeb,
- 0x0a000a0a0a000a0a, 0x2c002c2c2c002c2c, 0x1d001d1d1d001d1d,
- 0xb000b0b0b000b0b0, 0x6f006f6f6f006f6f, 0x8d008d8d8d008d8d,
- 0x8800888888008888, 0x0e000e0e0e000e0e, 0x1900191919001919,
- 0x8700878787008787, 0x4e004e4e4e004e4e, 0x0b000b0b0b000b0b,
- 0xa900a9a9a900a9a9, 0x0c000c0c0c000c0c, 0x7900797979007979,
- 0x1100111111001111, 0x7f007f7f7f007f7f, 0x2200222222002222,
- 0xe700e7e7e700e7e7, 0x5900595959005959, 0xe100e1e1e100e1e1,
- 0xda00dadada00dada, 0x3d003d3d3d003d3d, 0xc800c8c8c800c8c8,
- 0x1200121212001212, 0x0400040404000404, 0x7400747474007474,
- 0x5400545454005454, 0x3000303030003030, 0x7e007e7e7e007e7e,
- 0xb400b4b4b400b4b4, 0x2800282828002828, 0x5500555555005555,
- 0x6800686868006868, 0x5000505050005050, 0xbe00bebebe00bebe,
- 0xd000d0d0d000d0d0, 0xc400c4c4c400c4c4, 0x3100313131003131,
- 0xcb00cbcbcb00cbcb, 0x2a002a2a2a002a2a, 0xad00adadad00adad,
- 0x0f000f0f0f000f0f, 0xca00cacaca00caca, 0x7000707070007070,
- 0xff00ffffff00ffff, 0x3200323232003232, 0x6900696969006969,
- 0x0800080808000808, 0x6200626262006262, 0x0000000000000000,
- 0x2400242424002424, 0xd100d1d1d100d1d1, 0xfb00fbfbfb00fbfb,
- 0xba00bababa00baba, 0xed00ededed00eded, 0x4500454545004545,
- 0x8100818181008181, 0x7300737373007373, 0x6d006d6d6d006d6d,
- 0x8400848484008484, 0x9f009f9f9f009f9f, 0xee00eeeeee00eeee,
- 0x4a004a4a4a004a4a, 0xc300c3c3c300c3c3, 0x2e002e2e2e002e2e,
- 0xc100c1c1c100c1c1, 0x0100010101000101, 0xe600e6e6e600e6e6,
- 0x2500252525002525, 0x4800484848004848, 0x9900999999009999,
- 0xb900b9b9b900b9b9, 0xb300b3b3b300b3b3, 0x7b007b7b7b007b7b,
- 0xf900f9f9f900f9f9, 0xce00cecece00cece, 0xbf00bfbfbf00bfbf,
- 0xdf00dfdfdf00dfdf, 0x7100717171007171, 0x2900292929002929,
- 0xcd00cdcdcd00cdcd, 0x6c006c6c6c006c6c, 0x1300131313001313,
- 0x6400646464006464, 0x9b009b9b9b009b9b, 0x6300636363006363,
- 0x9d009d9d9d009d9d, 0xc000c0c0c000c0c0, 0x4b004b4b4b004b4b,
- 0xb700b7b7b700b7b7, 0xa500a5a5a500a5a5, 0x8900898989008989,
- 0x5f005f5f5f005f5f, 0xb100b1b1b100b1b1, 0x1700171717001717,
- 0xf400f4f4f400f4f4, 0xbc00bcbcbc00bcbc, 0xd300d3d3d300d3d3,
- 0x4600464646004646, 0xcf00cfcfcf00cfcf, 0x3700373737003737,
- 0x5e005e5e5e005e5e, 0x4700474747004747, 0x9400949494009494,
- 0xfa00fafafa00fafa, 0xfc00fcfcfc00fcfc, 0x5b005b5b5b005b5b,
- 0x9700979797009797, 0xfe00fefefe00fefe, 0x5a005a5a5a005a5a,
- 0xac00acacac00acac, 0x3c003c3c3c003c3c, 0x4c004c4c4c004c4c,
- 0x0300030303000303, 0x3500353535003535, 0xf300f3f3f300f3f3,
- 0x2300232323002323, 0xb800b8b8b800b8b8, 0x5d005d5d5d005d5d,
- 0x6a006a6a6a006a6a, 0x9200929292009292, 0xd500d5d5d500d5d5,
- 0x2100212121002121, 0x4400444444004444, 0x5100515151005151,
- 0xc600c6c6c600c6c6, 0x7d007d7d7d007d7d, 0x3900393939003939,
- 0x8300838383008383, 0xdc00dcdcdc00dcdc, 0xaa00aaaaaa00aaaa,
- 0x7c007c7c7c007c7c, 0x7700777777007777, 0x5600565656005656,
- 0x0500050505000505, 0x1b001b1b1b001b1b, 0xa400a4a4a400a4a4,
- 0x1500151515001515, 0x3400343434003434, 0x1e001e1e1e001e1e,
- 0x1c001c1c1c001c1c, 0xf800f8f8f800f8f8, 0x5200525252005252,
- 0x2000202020002020, 0x1400141414001414, 0xe900e9e9e900e9e9,
- 0xbd00bdbdbd00bdbd, 0xdd00dddddd00dddd, 0xe400e4e4e400e4e4,
- 0xa100a1a1a100a1a1, 0xe000e0e0e000e0e0, 0x8a008a8a8a008a8a,
- 0xf100f1f1f100f1f1, 0xd600d6d6d600d6d6, 0x7a007a7a7a007a7a,
- 0xbb00bbbbbb00bbbb, 0xe300e3e3e300e3e3, 0x4000404040004040,
- 0x4f004f4f4f004f4f,
+ 0x3800383838003838ULL, 0x4100414141004141ULL, 0x1600161616001616ULL,
+ 0x7600767676007676ULL, 0xd900d9d9d900d9d9ULL, 0x9300939393009393ULL,
+ 0x6000606060006060ULL, 0xf200f2f2f200f2f2ULL, 0x7200727272007272ULL,
+ 0xc200c2c2c200c2c2ULL, 0xab00ababab00ababULL, 0x9a009a9a9a009a9aULL,
+ 0x7500757575007575ULL, 0x0600060606000606ULL, 0x5700575757005757ULL,
+ 0xa000a0a0a000a0a0ULL, 0x9100919191009191ULL, 0xf700f7f7f700f7f7ULL,
+ 0xb500b5b5b500b5b5ULL, 0xc900c9c9c900c9c9ULL, 0xa200a2a2a200a2a2ULL,
+ 0x8c008c8c8c008c8cULL, 0xd200d2d2d200d2d2ULL, 0x9000909090009090ULL,
+ 0xf600f6f6f600f6f6ULL, 0x0700070707000707ULL, 0xa700a7a7a700a7a7ULL,
+ 0x2700272727002727ULL, 0x8e008e8e8e008e8eULL, 0xb200b2b2b200b2b2ULL,
+ 0x4900494949004949ULL, 0xde00dedede00dedeULL, 0x4300434343004343ULL,
+ 0x5c005c5c5c005c5cULL, 0xd700d7d7d700d7d7ULL, 0xc700c7c7c700c7c7ULL,
+ 0x3e003e3e3e003e3eULL, 0xf500f5f5f500f5f5ULL, 0x8f008f8f8f008f8fULL,
+ 0x6700676767006767ULL, 0x1f001f1f1f001f1fULL, 0x1800181818001818ULL,
+ 0x6e006e6e6e006e6eULL, 0xaf00afafaf00afafULL, 0x2f002f2f2f002f2fULL,
+ 0xe200e2e2e200e2e2ULL, 0x8500858585008585ULL, 0x0d000d0d0d000d0dULL,
+ 0x5300535353005353ULL, 0xf000f0f0f000f0f0ULL, 0x9c009c9c9c009c9cULL,
+ 0x6500656565006565ULL, 0xea00eaeaea00eaeaULL, 0xa300a3a3a300a3a3ULL,
+ 0xae00aeaeae00aeaeULL, 0x9e009e9e9e009e9eULL, 0xec00ececec00ececULL,
+ 0x8000808080008080ULL, 0x2d002d2d2d002d2dULL, 0x6b006b6b6b006b6bULL,
+ 0xa800a8a8a800a8a8ULL, 0x2b002b2b2b002b2bULL, 0x3600363636003636ULL,
+ 0xa600a6a6a600a6a6ULL, 0xc500c5c5c500c5c5ULL, 0x8600868686008686ULL,
+ 0x4d004d4d4d004d4dULL, 0x3300333333003333ULL, 0xfd00fdfdfd00fdfdULL,
+ 0x6600666666006666ULL, 0x5800585858005858ULL, 0x9600969696009696ULL,
+ 0x3a003a3a3a003a3aULL, 0x0900090909000909ULL, 0x9500959595009595ULL,
+ 0x1000101010001010ULL, 0x7800787878007878ULL, 0xd800d8d8d800d8d8ULL,
+ 0x4200424242004242ULL, 0xcc00cccccc00ccccULL, 0xef00efefef00efefULL,
+ 0x2600262626002626ULL, 0xe500e5e5e500e5e5ULL, 0x6100616161006161ULL,
+ 0x1a001a1a1a001a1aULL, 0x3f003f3f3f003f3fULL, 0x3b003b3b3b003b3bULL,
+ 0x8200828282008282ULL, 0xb600b6b6b600b6b6ULL, 0xdb00dbdbdb00dbdbULL,
+ 0xd400d4d4d400d4d4ULL, 0x9800989898009898ULL, 0xe800e8e8e800e8e8ULL,
+ 0x8b008b8b8b008b8bULL, 0x0200020202000202ULL, 0xeb00ebebeb00ebebULL,
+ 0x0a000a0a0a000a0aULL, 0x2c002c2c2c002c2cULL, 0x1d001d1d1d001d1dULL,
+ 0xb000b0b0b000b0b0ULL, 0x6f006f6f6f006f6fULL, 0x8d008d8d8d008d8dULL,
+ 0x8800888888008888ULL, 0x0e000e0e0e000e0eULL, 0x1900191919001919ULL,
+ 0x8700878787008787ULL, 0x4e004e4e4e004e4eULL, 0x0b000b0b0b000b0bULL,
+ 0xa900a9a9a900a9a9ULL, 0x0c000c0c0c000c0cULL, 0x7900797979007979ULL,
+ 0x1100111111001111ULL, 0x7f007f7f7f007f7fULL, 0x2200222222002222ULL,
+ 0xe700e7e7e700e7e7ULL, 0x5900595959005959ULL, 0xe100e1e1e100e1e1ULL,
+ 0xda00dadada00dadaULL, 0x3d003d3d3d003d3dULL, 0xc800c8c8c800c8c8ULL,
+ 0x1200121212001212ULL, 0x0400040404000404ULL, 0x7400747474007474ULL,
+ 0x5400545454005454ULL, 0x3000303030003030ULL, 0x7e007e7e7e007e7eULL,
+ 0xb400b4b4b400b4b4ULL, 0x2800282828002828ULL, 0x5500555555005555ULL,
+ 0x6800686868006868ULL, 0x5000505050005050ULL, 0xbe00bebebe00bebeULL,
+ 0xd000d0d0d000d0d0ULL, 0xc400c4c4c400c4c4ULL, 0x3100313131003131ULL,
+ 0xcb00cbcbcb00cbcbULL, 0x2a002a2a2a002a2aULL, 0xad00adadad00adadULL,
+ 0x0f000f0f0f000f0fULL, 0xca00cacaca00cacaULL, 0x7000707070007070ULL,
+ 0xff00ffffff00ffffULL, 0x3200323232003232ULL, 0x6900696969006969ULL,
+ 0x0800080808000808ULL, 0x6200626262006262ULL, 0x0000000000000000ULL,
+ 0x2400242424002424ULL, 0xd100d1d1d100d1d1ULL, 0xfb00fbfbfb00fbfbULL,
+ 0xba00bababa00babaULL, 0xed00ededed00ededULL, 0x4500454545004545ULL,
+ 0x8100818181008181ULL, 0x7300737373007373ULL, 0x6d006d6d6d006d6dULL,
+ 0x8400848484008484ULL, 0x9f009f9f9f009f9fULL, 0xee00eeeeee00eeeeULL,
+ 0x4a004a4a4a004a4aULL, 0xc300c3c3c300c3c3ULL, 0x2e002e2e2e002e2eULL,
+ 0xc100c1c1c100c1c1ULL, 0x0100010101000101ULL, 0xe600e6e6e600e6e6ULL,
+ 0x2500252525002525ULL, 0x4800484848004848ULL, 0x9900999999009999ULL,
+ 0xb900b9b9b900b9b9ULL, 0xb300b3b3b300b3b3ULL, 0x7b007b7b7b007b7bULL,
+ 0xf900f9f9f900f9f9ULL, 0xce00cecece00ceceULL, 0xbf00bfbfbf00bfbfULL,
+ 0xdf00dfdfdf00dfdfULL, 0x7100717171007171ULL, 0x2900292929002929ULL,
+ 0xcd00cdcdcd00cdcdULL, 0x6c006c6c6c006c6cULL, 0x1300131313001313ULL,
+ 0x6400646464006464ULL, 0x9b009b9b9b009b9bULL, 0x6300636363006363ULL,
+ 0x9d009d9d9d009d9dULL, 0xc000c0c0c000c0c0ULL, 0x4b004b4b4b004b4bULL,
+ 0xb700b7b7b700b7b7ULL, 0xa500a5a5a500a5a5ULL, 0x8900898989008989ULL,
+ 0x5f005f5f5f005f5fULL, 0xb100b1b1b100b1b1ULL, 0x1700171717001717ULL,
+ 0xf400f4f4f400f4f4ULL, 0xbc00bcbcbc00bcbcULL, 0xd300d3d3d300d3d3ULL,
+ 0x4600464646004646ULL, 0xcf00cfcfcf00cfcfULL, 0x3700373737003737ULL,
+ 0x5e005e5e5e005e5eULL, 0x4700474747004747ULL, 0x9400949494009494ULL,
+ 0xfa00fafafa00fafaULL, 0xfc00fcfcfc00fcfcULL, 0x5b005b5b5b005b5bULL,
+ 0x9700979797009797ULL, 0xfe00fefefe00fefeULL, 0x5a005a5a5a005a5aULL,
+ 0xac00acacac00acacULL, 0x3c003c3c3c003c3cULL, 0x4c004c4c4c004c4cULL,
+ 0x0300030303000303ULL, 0x3500353535003535ULL, 0xf300f3f3f300f3f3ULL,
+ 0x2300232323002323ULL, 0xb800b8b8b800b8b8ULL, 0x5d005d5d5d005d5dULL,
+ 0x6a006a6a6a006a6aULL, 0x9200929292009292ULL, 0xd500d5d5d500d5d5ULL,
+ 0x2100212121002121ULL, 0x4400444444004444ULL, 0x5100515151005151ULL,
+ 0xc600c6c6c600c6c6ULL, 0x7d007d7d7d007d7dULL, 0x3900393939003939ULL,
+ 0x8300838383008383ULL, 0xdc00dcdcdc00dcdcULL, 0xaa00aaaaaa00aaaaULL,
+ 0x7c007c7c7c007c7cULL, 0x7700777777007777ULL, 0x5600565656005656ULL,
+ 0x0500050505000505ULL, 0x1b001b1b1b001b1bULL, 0xa400a4a4a400a4a4ULL,
+ 0x1500151515001515ULL, 0x3400343434003434ULL, 0x1e001e1e1e001e1eULL,
+ 0x1c001c1c1c001c1cULL, 0xf800f8f8f800f8f8ULL, 0x5200525252005252ULL,
+ 0x2000202020002020ULL, 0x1400141414001414ULL, 0xe900e9e9e900e9e9ULL,
+ 0xbd00bdbdbd00bdbdULL, 0xdd00dddddd00ddddULL, 0xe400e4e4e400e4e4ULL,
+ 0xa100a1a1a100a1a1ULL, 0xe000e0e0e000e0e0ULL, 0x8a008a8a8a008a8aULL,
+ 0xf100f1f1f100f1f1ULL, 0xd600d6d6d600d6d6ULL, 0x7a007a7a7a007a7aULL,
+ 0xbb00bbbbbb00bbbbULL, 0xe300e3e3e300e3e3ULL, 0x4000404040004040ULL,
+ 0x4f004f4f4f004f4fULL,
};
const u64 camellia_sp44044404[256] = {
- 0x7070007070700070, 0x2c2c002c2c2c002c, 0xb3b300b3b3b300b3,
- 0xc0c000c0c0c000c0, 0xe4e400e4e4e400e4, 0x5757005757570057,
- 0xeaea00eaeaea00ea, 0xaeae00aeaeae00ae, 0x2323002323230023,
- 0x6b6b006b6b6b006b, 0x4545004545450045, 0xa5a500a5a5a500a5,
- 0xeded00ededed00ed, 0x4f4f004f4f4f004f, 0x1d1d001d1d1d001d,
- 0x9292009292920092, 0x8686008686860086, 0xafaf00afafaf00af,
- 0x7c7c007c7c7c007c, 0x1f1f001f1f1f001f, 0x3e3e003e3e3e003e,
- 0xdcdc00dcdcdc00dc, 0x5e5e005e5e5e005e, 0x0b0b000b0b0b000b,
- 0xa6a600a6a6a600a6, 0x3939003939390039, 0xd5d500d5d5d500d5,
- 0x5d5d005d5d5d005d, 0xd9d900d9d9d900d9, 0x5a5a005a5a5a005a,
- 0x5151005151510051, 0x6c6c006c6c6c006c, 0x8b8b008b8b8b008b,
- 0x9a9a009a9a9a009a, 0xfbfb00fbfbfb00fb, 0xb0b000b0b0b000b0,
- 0x7474007474740074, 0x2b2b002b2b2b002b, 0xf0f000f0f0f000f0,
- 0x8484008484840084, 0xdfdf00dfdfdf00df, 0xcbcb00cbcbcb00cb,
- 0x3434003434340034, 0x7676007676760076, 0x6d6d006d6d6d006d,
- 0xa9a900a9a9a900a9, 0xd1d100d1d1d100d1, 0x0404000404040004,
- 0x1414001414140014, 0x3a3a003a3a3a003a, 0xdede00dedede00de,
- 0x1111001111110011, 0x3232003232320032, 0x9c9c009c9c9c009c,
- 0x5353005353530053, 0xf2f200f2f2f200f2, 0xfefe00fefefe00fe,
- 0xcfcf00cfcfcf00cf, 0xc3c300c3c3c300c3, 0x7a7a007a7a7a007a,
- 0x2424002424240024, 0xe8e800e8e8e800e8, 0x6060006060600060,
- 0x6969006969690069, 0xaaaa00aaaaaa00aa, 0xa0a000a0a0a000a0,
- 0xa1a100a1a1a100a1, 0x6262006262620062, 0x5454005454540054,
- 0x1e1e001e1e1e001e, 0xe0e000e0e0e000e0, 0x6464006464640064,
- 0x1010001010100010, 0x0000000000000000, 0xa3a300a3a3a300a3,
- 0x7575007575750075, 0x8a8a008a8a8a008a, 0xe6e600e6e6e600e6,
- 0x0909000909090009, 0xdddd00dddddd00dd, 0x8787008787870087,
- 0x8383008383830083, 0xcdcd00cdcdcd00cd, 0x9090009090900090,
- 0x7373007373730073, 0xf6f600f6f6f600f6, 0x9d9d009d9d9d009d,
- 0xbfbf00bfbfbf00bf, 0x5252005252520052, 0xd8d800d8d8d800d8,
- 0xc8c800c8c8c800c8, 0xc6c600c6c6c600c6, 0x8181008181810081,
- 0x6f6f006f6f6f006f, 0x1313001313130013, 0x6363006363630063,
- 0xe9e900e9e9e900e9, 0xa7a700a7a7a700a7, 0x9f9f009f9f9f009f,
- 0xbcbc00bcbcbc00bc, 0x2929002929290029, 0xf9f900f9f9f900f9,
- 0x2f2f002f2f2f002f, 0xb4b400b4b4b400b4, 0x7878007878780078,
- 0x0606000606060006, 0xe7e700e7e7e700e7, 0x7171007171710071,
- 0xd4d400d4d4d400d4, 0xabab00ababab00ab, 0x8888008888880088,
- 0x8d8d008d8d8d008d, 0x7272007272720072, 0xb9b900b9b9b900b9,
- 0xf8f800f8f8f800f8, 0xacac00acacac00ac, 0x3636003636360036,
- 0x2a2a002a2a2a002a, 0x3c3c003c3c3c003c, 0xf1f100f1f1f100f1,
- 0x4040004040400040, 0xd3d300d3d3d300d3, 0xbbbb00bbbbbb00bb,
- 0x4343004343430043, 0x1515001515150015, 0xadad00adadad00ad,
- 0x7777007777770077, 0x8080008080800080, 0x8282008282820082,
- 0xecec00ececec00ec, 0x2727002727270027, 0xe5e500e5e5e500e5,
- 0x8585008585850085, 0x3535003535350035, 0x0c0c000c0c0c000c,
- 0x4141004141410041, 0xefef00efefef00ef, 0x9393009393930093,
- 0x1919001919190019, 0x2121002121210021, 0x0e0e000e0e0e000e,
- 0x4e4e004e4e4e004e, 0x6565006565650065, 0xbdbd00bdbdbd00bd,
- 0xb8b800b8b8b800b8, 0x8f8f008f8f8f008f, 0xebeb00ebebeb00eb,
- 0xcece00cecece00ce, 0x3030003030300030, 0x5f5f005f5f5f005f,
- 0xc5c500c5c5c500c5, 0x1a1a001a1a1a001a, 0xe1e100e1e1e100e1,
- 0xcaca00cacaca00ca, 0x4747004747470047, 0x3d3d003d3d3d003d,
- 0x0101000101010001, 0xd6d600d6d6d600d6, 0x5656005656560056,
- 0x4d4d004d4d4d004d, 0x0d0d000d0d0d000d, 0x6666006666660066,
- 0xcccc00cccccc00cc, 0x2d2d002d2d2d002d, 0x1212001212120012,
- 0x2020002020200020, 0xb1b100b1b1b100b1, 0x9999009999990099,
- 0x4c4c004c4c4c004c, 0xc2c200c2c2c200c2, 0x7e7e007e7e7e007e,
- 0x0505000505050005, 0xb7b700b7b7b700b7, 0x3131003131310031,
- 0x1717001717170017, 0xd7d700d7d7d700d7, 0x5858005858580058,
- 0x6161006161610061, 0x1b1b001b1b1b001b, 0x1c1c001c1c1c001c,
- 0x0f0f000f0f0f000f, 0x1616001616160016, 0x1818001818180018,
- 0x2222002222220022, 0x4444004444440044, 0xb2b200b2b2b200b2,
- 0xb5b500b5b5b500b5, 0x9191009191910091, 0x0808000808080008,
- 0xa8a800a8a8a800a8, 0xfcfc00fcfcfc00fc, 0x5050005050500050,
- 0xd0d000d0d0d000d0, 0x7d7d007d7d7d007d, 0x8989008989890089,
- 0x9797009797970097, 0x5b5b005b5b5b005b, 0x9595009595950095,
- 0xffff00ffffff00ff, 0xd2d200d2d2d200d2, 0xc4c400c4c4c400c4,
- 0x4848004848480048, 0xf7f700f7f7f700f7, 0xdbdb00dbdbdb00db,
- 0x0303000303030003, 0xdada00dadada00da, 0x3f3f003f3f3f003f,
- 0x9494009494940094, 0x5c5c005c5c5c005c, 0x0202000202020002,
- 0x4a4a004a4a4a004a, 0x3333003333330033, 0x6767006767670067,
- 0xf3f300f3f3f300f3, 0x7f7f007f7f7f007f, 0xe2e200e2e2e200e2,
- 0x9b9b009b9b9b009b, 0x2626002626260026, 0x3737003737370037,
- 0x3b3b003b3b3b003b, 0x9696009696960096, 0x4b4b004b4b4b004b,
- 0xbebe00bebebe00be, 0x2e2e002e2e2e002e, 0x7979007979790079,
- 0x8c8c008c8c8c008c, 0x6e6e006e6e6e006e, 0x8e8e008e8e8e008e,
- 0xf5f500f5f5f500f5, 0xb6b600b6b6b600b6, 0xfdfd00fdfdfd00fd,
- 0x5959005959590059, 0x9898009898980098, 0x6a6a006a6a6a006a,
- 0x4646004646460046, 0xbaba00bababa00ba, 0x2525002525250025,
- 0x4242004242420042, 0xa2a200a2a2a200a2, 0xfafa00fafafa00fa,
- 0x0707000707070007, 0x5555005555550055, 0xeeee00eeeeee00ee,
- 0x0a0a000a0a0a000a, 0x4949004949490049, 0x6868006868680068,
- 0x3838003838380038, 0xa4a400a4a4a400a4, 0x2828002828280028,
- 0x7b7b007b7b7b007b, 0xc9c900c9c9c900c9, 0xc1c100c1c1c100c1,
- 0xe3e300e3e3e300e3, 0xf4f400f4f4f400f4, 0xc7c700c7c7c700c7,
- 0x9e9e009e9e9e009e,
+ 0x7070007070700070ULL, 0x2c2c002c2c2c002cULL, 0xb3b300b3b3b300b3ULL,
+ 0xc0c000c0c0c000c0ULL, 0xe4e400e4e4e400e4ULL, 0x5757005757570057ULL,
+ 0xeaea00eaeaea00eaULL, 0xaeae00aeaeae00aeULL, 0x2323002323230023ULL,
+ 0x6b6b006b6b6b006bULL, 0x4545004545450045ULL, 0xa5a500a5a5a500a5ULL,
+ 0xeded00ededed00edULL, 0x4f4f004f4f4f004fULL, 0x1d1d001d1d1d001dULL,
+ 0x9292009292920092ULL, 0x8686008686860086ULL, 0xafaf00afafaf00afULL,
+ 0x7c7c007c7c7c007cULL, 0x1f1f001f1f1f001fULL, 0x3e3e003e3e3e003eULL,
+ 0xdcdc00dcdcdc00dcULL, 0x5e5e005e5e5e005eULL, 0x0b0b000b0b0b000bULL,
+ 0xa6a600a6a6a600a6ULL, 0x3939003939390039ULL, 0xd5d500d5d5d500d5ULL,
+ 0x5d5d005d5d5d005dULL, 0xd9d900d9d9d900d9ULL, 0x5a5a005a5a5a005aULL,
+ 0x5151005151510051ULL, 0x6c6c006c6c6c006cULL, 0x8b8b008b8b8b008bULL,
+ 0x9a9a009a9a9a009aULL, 0xfbfb00fbfbfb00fbULL, 0xb0b000b0b0b000b0ULL,
+ 0x7474007474740074ULL, 0x2b2b002b2b2b002bULL, 0xf0f000f0f0f000f0ULL,
+ 0x8484008484840084ULL, 0xdfdf00dfdfdf00dfULL, 0xcbcb00cbcbcb00cbULL,
+ 0x3434003434340034ULL, 0x7676007676760076ULL, 0x6d6d006d6d6d006dULL,
+ 0xa9a900a9a9a900a9ULL, 0xd1d100d1d1d100d1ULL, 0x0404000404040004ULL,
+ 0x1414001414140014ULL, 0x3a3a003a3a3a003aULL, 0xdede00dedede00deULL,
+ 0x1111001111110011ULL, 0x3232003232320032ULL, 0x9c9c009c9c9c009cULL,
+ 0x5353005353530053ULL, 0xf2f200f2f2f200f2ULL, 0xfefe00fefefe00feULL,
+ 0xcfcf00cfcfcf00cfULL, 0xc3c300c3c3c300c3ULL, 0x7a7a007a7a7a007aULL,
+ 0x2424002424240024ULL, 0xe8e800e8e8e800e8ULL, 0x6060006060600060ULL,
+ 0x6969006969690069ULL, 0xaaaa00aaaaaa00aaULL, 0xa0a000a0a0a000a0ULL,
+ 0xa1a100a1a1a100a1ULL, 0x6262006262620062ULL, 0x5454005454540054ULL,
+ 0x1e1e001e1e1e001eULL, 0xe0e000e0e0e000e0ULL, 0x6464006464640064ULL,
+ 0x1010001010100010ULL, 0x0000000000000000ULL, 0xa3a300a3a3a300a3ULL,
+ 0x7575007575750075ULL, 0x8a8a008a8a8a008aULL, 0xe6e600e6e6e600e6ULL,
+ 0x0909000909090009ULL, 0xdddd00dddddd00ddULL, 0x8787008787870087ULL,
+ 0x8383008383830083ULL, 0xcdcd00cdcdcd00cdULL, 0x9090009090900090ULL,
+ 0x7373007373730073ULL, 0xf6f600f6f6f600f6ULL, 0x9d9d009d9d9d009dULL,
+ 0xbfbf00bfbfbf00bfULL, 0x5252005252520052ULL, 0xd8d800d8d8d800d8ULL,
+ 0xc8c800c8c8c800c8ULL, 0xc6c600c6c6c600c6ULL, 0x8181008181810081ULL,
+ 0x6f6f006f6f6f006fULL, 0x1313001313130013ULL, 0x6363006363630063ULL,
+ 0xe9e900e9e9e900e9ULL, 0xa7a700a7a7a700a7ULL, 0x9f9f009f9f9f009fULL,
+ 0xbcbc00bcbcbc00bcULL, 0x2929002929290029ULL, 0xf9f900f9f9f900f9ULL,
+ 0x2f2f002f2f2f002fULL, 0xb4b400b4b4b400b4ULL, 0x7878007878780078ULL,
+ 0x0606000606060006ULL, 0xe7e700e7e7e700e7ULL, 0x7171007171710071ULL,
+ 0xd4d400d4d4d400d4ULL, 0xabab00ababab00abULL, 0x8888008888880088ULL,
+ 0x8d8d008d8d8d008dULL, 0x7272007272720072ULL, 0xb9b900b9b9b900b9ULL,
+ 0xf8f800f8f8f800f8ULL, 0xacac00acacac00acULL, 0x3636003636360036ULL,
+ 0x2a2a002a2a2a002aULL, 0x3c3c003c3c3c003cULL, 0xf1f100f1f1f100f1ULL,
+ 0x4040004040400040ULL, 0xd3d300d3d3d300d3ULL, 0xbbbb00bbbbbb00bbULL,
+ 0x4343004343430043ULL, 0x1515001515150015ULL, 0xadad00adadad00adULL,
+ 0x7777007777770077ULL, 0x8080008080800080ULL, 0x8282008282820082ULL,
+ 0xecec00ececec00ecULL, 0x2727002727270027ULL, 0xe5e500e5e5e500e5ULL,
+ 0x8585008585850085ULL, 0x3535003535350035ULL, 0x0c0c000c0c0c000cULL,
+ 0x4141004141410041ULL, 0xefef00efefef00efULL, 0x9393009393930093ULL,
+ 0x1919001919190019ULL, 0x2121002121210021ULL, 0x0e0e000e0e0e000eULL,
+ 0x4e4e004e4e4e004eULL, 0x6565006565650065ULL, 0xbdbd00bdbdbd00bdULL,
+ 0xb8b800b8b8b800b8ULL, 0x8f8f008f8f8f008fULL, 0xebeb00ebebeb00ebULL,
+ 0xcece00cecece00ceULL, 0x3030003030300030ULL, 0x5f5f005f5f5f005fULL,
+ 0xc5c500c5c5c500c5ULL, 0x1a1a001a1a1a001aULL, 0xe1e100e1e1e100e1ULL,
+ 0xcaca00cacaca00caULL, 0x4747004747470047ULL, 0x3d3d003d3d3d003dULL,
+ 0x0101000101010001ULL, 0xd6d600d6d6d600d6ULL, 0x5656005656560056ULL,
+ 0x4d4d004d4d4d004dULL, 0x0d0d000d0d0d000dULL, 0x6666006666660066ULL,
+ 0xcccc00cccccc00ccULL, 0x2d2d002d2d2d002dULL, 0x1212001212120012ULL,
+ 0x2020002020200020ULL, 0xb1b100b1b1b100b1ULL, 0x9999009999990099ULL,
+ 0x4c4c004c4c4c004cULL, 0xc2c200c2c2c200c2ULL, 0x7e7e007e7e7e007eULL,
+ 0x0505000505050005ULL, 0xb7b700b7b7b700b7ULL, 0x3131003131310031ULL,
+ 0x1717001717170017ULL, 0xd7d700d7d7d700d7ULL, 0x5858005858580058ULL,
+ 0x6161006161610061ULL, 0x1b1b001b1b1b001bULL, 0x1c1c001c1c1c001cULL,
+ 0x0f0f000f0f0f000fULL, 0x1616001616160016ULL, 0x1818001818180018ULL,
+ 0x2222002222220022ULL, 0x4444004444440044ULL, 0xb2b200b2b2b200b2ULL,
+ 0xb5b500b5b5b500b5ULL, 0x9191009191910091ULL, 0x0808000808080008ULL,
+ 0xa8a800a8a8a800a8ULL, 0xfcfc00fcfcfc00fcULL, 0x5050005050500050ULL,
+ 0xd0d000d0d0d000d0ULL, 0x7d7d007d7d7d007dULL, 0x8989008989890089ULL,
+ 0x9797009797970097ULL, 0x5b5b005b5b5b005bULL, 0x9595009595950095ULL,
+ 0xffff00ffffff00ffULL, 0xd2d200d2d2d200d2ULL, 0xc4c400c4c4c400c4ULL,
+ 0x4848004848480048ULL, 0xf7f700f7f7f700f7ULL, 0xdbdb00dbdbdb00dbULL,
+ 0x0303000303030003ULL, 0xdada00dadada00daULL, 0x3f3f003f3f3f003fULL,
+ 0x9494009494940094ULL, 0x5c5c005c5c5c005cULL, 0x0202000202020002ULL,
+ 0x4a4a004a4a4a004aULL, 0x3333003333330033ULL, 0x6767006767670067ULL,
+ 0xf3f300f3f3f300f3ULL, 0x7f7f007f7f7f007fULL, 0xe2e200e2e2e200e2ULL,
+ 0x9b9b009b9b9b009bULL, 0x2626002626260026ULL, 0x3737003737370037ULL,
+ 0x3b3b003b3b3b003bULL, 0x9696009696960096ULL, 0x4b4b004b4b4b004bULL,
+ 0xbebe00bebebe00beULL, 0x2e2e002e2e2e002eULL, 0x7979007979790079ULL,
+ 0x8c8c008c8c8c008cULL, 0x6e6e006e6e6e006eULL, 0x8e8e008e8e8e008eULL,
+ 0xf5f500f5f5f500f5ULL, 0xb6b600b6b6b600b6ULL, 0xfdfd00fdfdfd00fdULL,
+ 0x5959005959590059ULL, 0x9898009898980098ULL, 0x6a6a006a6a6a006aULL,
+ 0x4646004646460046ULL, 0xbaba00bababa00baULL, 0x2525002525250025ULL,
+ 0x4242004242420042ULL, 0xa2a200a2a2a200a2ULL, 0xfafa00fafafa00faULL,
+ 0x0707000707070007ULL, 0x5555005555550055ULL, 0xeeee00eeeeee00eeULL,
+ 0x0a0a000a0a0a000aULL, 0x4949004949490049ULL, 0x6868006868680068ULL,
+ 0x3838003838380038ULL, 0xa4a400a4a4a400a4ULL, 0x2828002828280028ULL,
+ 0x7b7b007b7b7b007bULL, 0xc9c900c9c9c900c9ULL, 0xc1c100c1c1c100c1ULL,
+ 0xe3e300e3e3e300e3ULL, 0xf4f400f4f4f400f4ULL, 0xc7c700c7c7c700c7ULL,
+ 0x9e9e009e9e9e009eULL,
};
const u64 camellia_sp11101110[256] = {
- 0x7070700070707000, 0x8282820082828200, 0x2c2c2c002c2c2c00,
- 0xececec00ececec00, 0xb3b3b300b3b3b300, 0x2727270027272700,
- 0xc0c0c000c0c0c000, 0xe5e5e500e5e5e500, 0xe4e4e400e4e4e400,
- 0x8585850085858500, 0x5757570057575700, 0x3535350035353500,
- 0xeaeaea00eaeaea00, 0x0c0c0c000c0c0c00, 0xaeaeae00aeaeae00,
- 0x4141410041414100, 0x2323230023232300, 0xefefef00efefef00,
- 0x6b6b6b006b6b6b00, 0x9393930093939300, 0x4545450045454500,
- 0x1919190019191900, 0xa5a5a500a5a5a500, 0x2121210021212100,
- 0xededed00ededed00, 0x0e0e0e000e0e0e00, 0x4f4f4f004f4f4f00,
- 0x4e4e4e004e4e4e00, 0x1d1d1d001d1d1d00, 0x6565650065656500,
- 0x9292920092929200, 0xbdbdbd00bdbdbd00, 0x8686860086868600,
- 0xb8b8b800b8b8b800, 0xafafaf00afafaf00, 0x8f8f8f008f8f8f00,
- 0x7c7c7c007c7c7c00, 0xebebeb00ebebeb00, 0x1f1f1f001f1f1f00,
- 0xcecece00cecece00, 0x3e3e3e003e3e3e00, 0x3030300030303000,
- 0xdcdcdc00dcdcdc00, 0x5f5f5f005f5f5f00, 0x5e5e5e005e5e5e00,
- 0xc5c5c500c5c5c500, 0x0b0b0b000b0b0b00, 0x1a1a1a001a1a1a00,
- 0xa6a6a600a6a6a600, 0xe1e1e100e1e1e100, 0x3939390039393900,
- 0xcacaca00cacaca00, 0xd5d5d500d5d5d500, 0x4747470047474700,
- 0x5d5d5d005d5d5d00, 0x3d3d3d003d3d3d00, 0xd9d9d900d9d9d900,
- 0x0101010001010100, 0x5a5a5a005a5a5a00, 0xd6d6d600d6d6d600,
- 0x5151510051515100, 0x5656560056565600, 0x6c6c6c006c6c6c00,
- 0x4d4d4d004d4d4d00, 0x8b8b8b008b8b8b00, 0x0d0d0d000d0d0d00,
- 0x9a9a9a009a9a9a00, 0x6666660066666600, 0xfbfbfb00fbfbfb00,
- 0xcccccc00cccccc00, 0xb0b0b000b0b0b000, 0x2d2d2d002d2d2d00,
- 0x7474740074747400, 0x1212120012121200, 0x2b2b2b002b2b2b00,
- 0x2020200020202000, 0xf0f0f000f0f0f000, 0xb1b1b100b1b1b100,
- 0x8484840084848400, 0x9999990099999900, 0xdfdfdf00dfdfdf00,
- 0x4c4c4c004c4c4c00, 0xcbcbcb00cbcbcb00, 0xc2c2c200c2c2c200,
- 0x3434340034343400, 0x7e7e7e007e7e7e00, 0x7676760076767600,
- 0x0505050005050500, 0x6d6d6d006d6d6d00, 0xb7b7b700b7b7b700,
- 0xa9a9a900a9a9a900, 0x3131310031313100, 0xd1d1d100d1d1d100,
- 0x1717170017171700, 0x0404040004040400, 0xd7d7d700d7d7d700,
- 0x1414140014141400, 0x5858580058585800, 0x3a3a3a003a3a3a00,
- 0x6161610061616100, 0xdedede00dedede00, 0x1b1b1b001b1b1b00,
- 0x1111110011111100, 0x1c1c1c001c1c1c00, 0x3232320032323200,
- 0x0f0f0f000f0f0f00, 0x9c9c9c009c9c9c00, 0x1616160016161600,
- 0x5353530053535300, 0x1818180018181800, 0xf2f2f200f2f2f200,
- 0x2222220022222200, 0xfefefe00fefefe00, 0x4444440044444400,
- 0xcfcfcf00cfcfcf00, 0xb2b2b200b2b2b200, 0xc3c3c300c3c3c300,
- 0xb5b5b500b5b5b500, 0x7a7a7a007a7a7a00, 0x9191910091919100,
- 0x2424240024242400, 0x0808080008080800, 0xe8e8e800e8e8e800,
- 0xa8a8a800a8a8a800, 0x6060600060606000, 0xfcfcfc00fcfcfc00,
- 0x6969690069696900, 0x5050500050505000, 0xaaaaaa00aaaaaa00,
- 0xd0d0d000d0d0d000, 0xa0a0a000a0a0a000, 0x7d7d7d007d7d7d00,
- 0xa1a1a100a1a1a100, 0x8989890089898900, 0x6262620062626200,
- 0x9797970097979700, 0x5454540054545400, 0x5b5b5b005b5b5b00,
- 0x1e1e1e001e1e1e00, 0x9595950095959500, 0xe0e0e000e0e0e000,
- 0xffffff00ffffff00, 0x6464640064646400, 0xd2d2d200d2d2d200,
- 0x1010100010101000, 0xc4c4c400c4c4c400, 0x0000000000000000,
- 0x4848480048484800, 0xa3a3a300a3a3a300, 0xf7f7f700f7f7f700,
- 0x7575750075757500, 0xdbdbdb00dbdbdb00, 0x8a8a8a008a8a8a00,
- 0x0303030003030300, 0xe6e6e600e6e6e600, 0xdadada00dadada00,
- 0x0909090009090900, 0x3f3f3f003f3f3f00, 0xdddddd00dddddd00,
- 0x9494940094949400, 0x8787870087878700, 0x5c5c5c005c5c5c00,
- 0x8383830083838300, 0x0202020002020200, 0xcdcdcd00cdcdcd00,
- 0x4a4a4a004a4a4a00, 0x9090900090909000, 0x3333330033333300,
- 0x7373730073737300, 0x6767670067676700, 0xf6f6f600f6f6f600,
- 0xf3f3f300f3f3f300, 0x9d9d9d009d9d9d00, 0x7f7f7f007f7f7f00,
- 0xbfbfbf00bfbfbf00, 0xe2e2e200e2e2e200, 0x5252520052525200,
- 0x9b9b9b009b9b9b00, 0xd8d8d800d8d8d800, 0x2626260026262600,
- 0xc8c8c800c8c8c800, 0x3737370037373700, 0xc6c6c600c6c6c600,
- 0x3b3b3b003b3b3b00, 0x8181810081818100, 0x9696960096969600,
- 0x6f6f6f006f6f6f00, 0x4b4b4b004b4b4b00, 0x1313130013131300,
- 0xbebebe00bebebe00, 0x6363630063636300, 0x2e2e2e002e2e2e00,
- 0xe9e9e900e9e9e900, 0x7979790079797900, 0xa7a7a700a7a7a700,
- 0x8c8c8c008c8c8c00, 0x9f9f9f009f9f9f00, 0x6e6e6e006e6e6e00,
- 0xbcbcbc00bcbcbc00, 0x8e8e8e008e8e8e00, 0x2929290029292900,
- 0xf5f5f500f5f5f500, 0xf9f9f900f9f9f900, 0xb6b6b600b6b6b600,
- 0x2f2f2f002f2f2f00, 0xfdfdfd00fdfdfd00, 0xb4b4b400b4b4b400,
- 0x5959590059595900, 0x7878780078787800, 0x9898980098989800,
- 0x0606060006060600, 0x6a6a6a006a6a6a00, 0xe7e7e700e7e7e700,
- 0x4646460046464600, 0x7171710071717100, 0xbababa00bababa00,
- 0xd4d4d400d4d4d400, 0x2525250025252500, 0xababab00ababab00,
- 0x4242420042424200, 0x8888880088888800, 0xa2a2a200a2a2a200,
- 0x8d8d8d008d8d8d00, 0xfafafa00fafafa00, 0x7272720072727200,
- 0x0707070007070700, 0xb9b9b900b9b9b900, 0x5555550055555500,
- 0xf8f8f800f8f8f800, 0xeeeeee00eeeeee00, 0xacacac00acacac00,
- 0x0a0a0a000a0a0a00, 0x3636360036363600, 0x4949490049494900,
- 0x2a2a2a002a2a2a00, 0x6868680068686800, 0x3c3c3c003c3c3c00,
- 0x3838380038383800, 0xf1f1f100f1f1f100, 0xa4a4a400a4a4a400,
- 0x4040400040404000, 0x2828280028282800, 0xd3d3d300d3d3d300,
- 0x7b7b7b007b7b7b00, 0xbbbbbb00bbbbbb00, 0xc9c9c900c9c9c900,
- 0x4343430043434300, 0xc1c1c100c1c1c100, 0x1515150015151500,
- 0xe3e3e300e3e3e300, 0xadadad00adadad00, 0xf4f4f400f4f4f400,
- 0x7777770077777700, 0xc7c7c700c7c7c700, 0x8080800080808000,
- 0x9e9e9e009e9e9e00,
+ 0x7070700070707000ULL, 0x8282820082828200ULL, 0x2c2c2c002c2c2c00ULL,
+ 0xececec00ececec00ULL, 0xb3b3b300b3b3b300ULL, 0x2727270027272700ULL,
+ 0xc0c0c000c0c0c000ULL, 0xe5e5e500e5e5e500ULL, 0xe4e4e400e4e4e400ULL,
+ 0x8585850085858500ULL, 0x5757570057575700ULL, 0x3535350035353500ULL,
+ 0xeaeaea00eaeaea00ULL, 0x0c0c0c000c0c0c00ULL, 0xaeaeae00aeaeae00ULL,
+ 0x4141410041414100ULL, 0x2323230023232300ULL, 0xefefef00efefef00ULL,
+ 0x6b6b6b006b6b6b00ULL, 0x9393930093939300ULL, 0x4545450045454500ULL,
+ 0x1919190019191900ULL, 0xa5a5a500a5a5a500ULL, 0x2121210021212100ULL,
+ 0xededed00ededed00ULL, 0x0e0e0e000e0e0e00ULL, 0x4f4f4f004f4f4f00ULL,
+ 0x4e4e4e004e4e4e00ULL, 0x1d1d1d001d1d1d00ULL, 0x6565650065656500ULL,
+ 0x9292920092929200ULL, 0xbdbdbd00bdbdbd00ULL, 0x8686860086868600ULL,
+ 0xb8b8b800b8b8b800ULL, 0xafafaf00afafaf00ULL, 0x8f8f8f008f8f8f00ULL,
+ 0x7c7c7c007c7c7c00ULL, 0xebebeb00ebebeb00ULL, 0x1f1f1f001f1f1f00ULL,
+ 0xcecece00cecece00ULL, 0x3e3e3e003e3e3e00ULL, 0x3030300030303000ULL,
+ 0xdcdcdc00dcdcdc00ULL, 0x5f5f5f005f5f5f00ULL, 0x5e5e5e005e5e5e00ULL,
+ 0xc5c5c500c5c5c500ULL, 0x0b0b0b000b0b0b00ULL, 0x1a1a1a001a1a1a00ULL,
+ 0xa6a6a600a6a6a600ULL, 0xe1e1e100e1e1e100ULL, 0x3939390039393900ULL,
+ 0xcacaca00cacaca00ULL, 0xd5d5d500d5d5d500ULL, 0x4747470047474700ULL,
+ 0x5d5d5d005d5d5d00ULL, 0x3d3d3d003d3d3d00ULL, 0xd9d9d900d9d9d900ULL,
+ 0x0101010001010100ULL, 0x5a5a5a005a5a5a00ULL, 0xd6d6d600d6d6d600ULL,
+ 0x5151510051515100ULL, 0x5656560056565600ULL, 0x6c6c6c006c6c6c00ULL,
+ 0x4d4d4d004d4d4d00ULL, 0x8b8b8b008b8b8b00ULL, 0x0d0d0d000d0d0d00ULL,
+ 0x9a9a9a009a9a9a00ULL, 0x6666660066666600ULL, 0xfbfbfb00fbfbfb00ULL,
+ 0xcccccc00cccccc00ULL, 0xb0b0b000b0b0b000ULL, 0x2d2d2d002d2d2d00ULL,
+ 0x7474740074747400ULL, 0x1212120012121200ULL, 0x2b2b2b002b2b2b00ULL,
+ 0x2020200020202000ULL, 0xf0f0f000f0f0f000ULL, 0xb1b1b100b1b1b100ULL,
+ 0x8484840084848400ULL, 0x9999990099999900ULL, 0xdfdfdf00dfdfdf00ULL,
+ 0x4c4c4c004c4c4c00ULL, 0xcbcbcb00cbcbcb00ULL, 0xc2c2c200c2c2c200ULL,
+ 0x3434340034343400ULL, 0x7e7e7e007e7e7e00ULL, 0x7676760076767600ULL,
+ 0x0505050005050500ULL, 0x6d6d6d006d6d6d00ULL, 0xb7b7b700b7b7b700ULL,
+ 0xa9a9a900a9a9a900ULL, 0x3131310031313100ULL, 0xd1d1d100d1d1d100ULL,
+ 0x1717170017171700ULL, 0x0404040004040400ULL, 0xd7d7d700d7d7d700ULL,
+ 0x1414140014141400ULL, 0x5858580058585800ULL, 0x3a3a3a003a3a3a00ULL,
+ 0x6161610061616100ULL, 0xdedede00dedede00ULL, 0x1b1b1b001b1b1b00ULL,
+ 0x1111110011111100ULL, 0x1c1c1c001c1c1c00ULL, 0x3232320032323200ULL,
+ 0x0f0f0f000f0f0f00ULL, 0x9c9c9c009c9c9c00ULL, 0x1616160016161600ULL,
+ 0x5353530053535300ULL, 0x1818180018181800ULL, 0xf2f2f200f2f2f200ULL,
+ 0x2222220022222200ULL, 0xfefefe00fefefe00ULL, 0x4444440044444400ULL,
+ 0xcfcfcf00cfcfcf00ULL, 0xb2b2b200b2b2b200ULL, 0xc3c3c300c3c3c300ULL,
+ 0xb5b5b500b5b5b500ULL, 0x7a7a7a007a7a7a00ULL, 0x9191910091919100ULL,
+ 0x2424240024242400ULL, 0x0808080008080800ULL, 0xe8e8e800e8e8e800ULL,
+ 0xa8a8a800a8a8a800ULL, 0x6060600060606000ULL, 0xfcfcfc00fcfcfc00ULL,
+ 0x6969690069696900ULL, 0x5050500050505000ULL, 0xaaaaaa00aaaaaa00ULL,
+ 0xd0d0d000d0d0d000ULL, 0xa0a0a000a0a0a000ULL, 0x7d7d7d007d7d7d00ULL,
+ 0xa1a1a100a1a1a100ULL, 0x8989890089898900ULL, 0x6262620062626200ULL,
+ 0x9797970097979700ULL, 0x5454540054545400ULL, 0x5b5b5b005b5b5b00ULL,
+ 0x1e1e1e001e1e1e00ULL, 0x9595950095959500ULL, 0xe0e0e000e0e0e000ULL,
+ 0xffffff00ffffff00ULL, 0x6464640064646400ULL, 0xd2d2d200d2d2d200ULL,
+ 0x1010100010101000ULL, 0xc4c4c400c4c4c400ULL, 0x0000000000000000ULL,
+ 0x4848480048484800ULL, 0xa3a3a300a3a3a300ULL, 0xf7f7f700f7f7f700ULL,
+ 0x7575750075757500ULL, 0xdbdbdb00dbdbdb00ULL, 0x8a8a8a008a8a8a00ULL,
+ 0x0303030003030300ULL, 0xe6e6e600e6e6e600ULL, 0xdadada00dadada00ULL,
+ 0x0909090009090900ULL, 0x3f3f3f003f3f3f00ULL, 0xdddddd00dddddd00ULL,
+ 0x9494940094949400ULL, 0x8787870087878700ULL, 0x5c5c5c005c5c5c00ULL,
+ 0x8383830083838300ULL, 0x0202020002020200ULL, 0xcdcdcd00cdcdcd00ULL,
+ 0x4a4a4a004a4a4a00ULL, 0x9090900090909000ULL, 0x3333330033333300ULL,
+ 0x7373730073737300ULL, 0x6767670067676700ULL, 0xf6f6f600f6f6f600ULL,
+ 0xf3f3f300f3f3f300ULL, 0x9d9d9d009d9d9d00ULL, 0x7f7f7f007f7f7f00ULL,
+ 0xbfbfbf00bfbfbf00ULL, 0xe2e2e200e2e2e200ULL, 0x5252520052525200ULL,
+ 0x9b9b9b009b9b9b00ULL, 0xd8d8d800d8d8d800ULL, 0x2626260026262600ULL,
+ 0xc8c8c800c8c8c800ULL, 0x3737370037373700ULL, 0xc6c6c600c6c6c600ULL,
+ 0x3b3b3b003b3b3b00ULL, 0x8181810081818100ULL, 0x9696960096969600ULL,
+ 0x6f6f6f006f6f6f00ULL, 0x4b4b4b004b4b4b00ULL, 0x1313130013131300ULL,
+ 0xbebebe00bebebe00ULL, 0x6363630063636300ULL, 0x2e2e2e002e2e2e00ULL,
+ 0xe9e9e900e9e9e900ULL, 0x7979790079797900ULL, 0xa7a7a700a7a7a700ULL,
+ 0x8c8c8c008c8c8c00ULL, 0x9f9f9f009f9f9f00ULL, 0x6e6e6e006e6e6e00ULL,
+ 0xbcbcbc00bcbcbc00ULL, 0x8e8e8e008e8e8e00ULL, 0x2929290029292900ULL,
+ 0xf5f5f500f5f5f500ULL, 0xf9f9f900f9f9f900ULL, 0xb6b6b600b6b6b600ULL,
+ 0x2f2f2f002f2f2f00ULL, 0xfdfdfd00fdfdfd00ULL, 0xb4b4b400b4b4b400ULL,
+ 0x5959590059595900ULL, 0x7878780078787800ULL, 0x9898980098989800ULL,
+ 0x0606060006060600ULL, 0x6a6a6a006a6a6a00ULL, 0xe7e7e700e7e7e700ULL,
+ 0x4646460046464600ULL, 0x7171710071717100ULL, 0xbababa00bababa00ULL,
+ 0xd4d4d400d4d4d400ULL, 0x2525250025252500ULL, 0xababab00ababab00ULL,
+ 0x4242420042424200ULL, 0x8888880088888800ULL, 0xa2a2a200a2a2a200ULL,
+ 0x8d8d8d008d8d8d00ULL, 0xfafafa00fafafa00ULL, 0x7272720072727200ULL,
+ 0x0707070007070700ULL, 0xb9b9b900b9b9b900ULL, 0x5555550055555500ULL,
+ 0xf8f8f800f8f8f800ULL, 0xeeeeee00eeeeee00ULL, 0xacacac00acacac00ULL,
+ 0x0a0a0a000a0a0a00ULL, 0x3636360036363600ULL, 0x4949490049494900ULL,
+ 0x2a2a2a002a2a2a00ULL, 0x6868680068686800ULL, 0x3c3c3c003c3c3c00ULL,
+ 0x3838380038383800ULL, 0xf1f1f100f1f1f100ULL, 0xa4a4a400a4a4a400ULL,
+ 0x4040400040404000ULL, 0x2828280028282800ULL, 0xd3d3d300d3d3d300ULL,
+ 0x7b7b7b007b7b7b00ULL, 0xbbbbbb00bbbbbb00ULL, 0xc9c9c900c9c9c900ULL,
+ 0x4343430043434300ULL, 0xc1c1c100c1c1c100ULL, 0x1515150015151500ULL,
+ 0xe3e3e300e3e3e300ULL, 0xadadad00adadad00ULL, 0xf4f4f400f4f4f400ULL,
+ 0x7777770077777700ULL, 0xc7c7c700c7c7c700ULL, 0x8080800080808000ULL,
+ 0x9e9e9e009e9e9e00ULL,
};
/* key constants */
@@ -1601,7 +1601,6 @@ static struct crypto_alg camellia_algs[6] = { {
.cra_ctxsize = sizeof(struct camellia_ctx),
.cra_alignmask = 0,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(camellia_algs[0].cra_list),
.cra_u = {
.cipher = {
.cia_min_keysize = CAMELLIA_MIN_KEY_SIZE,
@@ -1621,7 +1620,6 @@ static struct crypto_alg camellia_algs[6] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(camellia_algs[1].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = CAMELLIA_MIN_KEY_SIZE,
@@ -1641,7 +1639,6 @@ static struct crypto_alg camellia_algs[6] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(camellia_algs[2].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = CAMELLIA_MIN_KEY_SIZE,
@@ -1662,7 +1659,6 @@ static struct crypto_alg camellia_algs[6] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(camellia_algs[3].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = CAMELLIA_MIN_KEY_SIZE,
@@ -1683,7 +1679,6 @@ static struct crypto_alg camellia_algs[6] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(camellia_algs[4].cra_list),
.cra_exit = lrw_exit_tfm,
.cra_u = {
.blkcipher = {
@@ -1707,7 +1702,6 @@ static struct crypto_alg camellia_algs[6] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(camellia_algs[5].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = CAMELLIA_MIN_KEY_SIZE * 2,
diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
new file mode 100644
index 00000000000..a41a3aaba22
--- /dev/null
+++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S
@@ -0,0 +1,376 @@
+/*
+ * 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
+ *
+ */
+
+.file "cast5-avx-x86_64-asm_64.S"
+
+.extern cast5_s1
+.extern cast5_s2
+.extern cast5_s3
+.extern cast5_s4
+
+/* structure of crypto context */
+#define km 0
+#define kr (16*4)
+#define rr ((16*4)+16)
+
+/* s-boxes */
+#define s1 cast5_s1
+#define s2 cast5_s2
+#define s3 cast5_s3
+#define s4 cast5_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(in, x0, x1, t0, t1, rmask) \
+ vmovdqu (0*4*4)(in), x0; \
+ vmovdqu (1*4*4)(in), x1; \
+ vpshufb rmask, x0, x0; \
+ vpshufb rmask, x1, x1; \
+ \
+ transpose_2x4(x0, x1, t0, t1)
+
+#define outunpack_blocks(out, x0, x1, t0, t1, rmask) \
+ transpose_2x4(x0, x1, t0, t1) \
+ \
+ vpshufb rmask, x0, x0; \
+ vpshufb rmask, x1, x1; \
+ vmovdqu x0, (0*4*4)(out); \
+ vmovdqu x1, (1*4*4)(out);
+
+#define outunpack_xor_blocks(out, x0, x1, t0, t1, rmask) \
+ transpose_2x4(x0, x1, t0, t1) \
+ \
+ vpshufb rmask, x0, x0; \
+ vpshufb rmask, x1, x1; \
+ vpxor (0*4*4)(out), x0, x0; \
+ vmovdqu x0, (0*4*4)(out); \
+ vpxor (1*4*4)(out), x1, x1; \
+ vmovdqu x1, (1*4*4)(out);
+
+.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
+.L16_mask:
+ .byte 16, 16, 16, 16
+.L32_mask:
+ .byte 32, 0, 0, 0
+.Lfirst_mask:
+ .byte 0x1f, 0, 0, 0
+
+.text
+
+.align 16
+.global __cast5_enc_blk_16way
+.type __cast5_enc_blk_16way,@function;
+
+__cast5_enc_blk_16way:
+ /* input:
+ * %rdi: ctx, CTX
+ * %rsi: dst
+ * %rdx: src
+ * %rcx: bool, if true: xor output
+ */
+
+ pushq %rbp;
+ pushq %rbx;
+ pushq %rcx;
+
+ vmovdqa .Lbswap_mask, RKM;
+ vmovd .Lfirst_mask, R1ST;
+ vmovd .L32_mask, R32;
+ enc_preload_rkr();
+
+ leaq 1*(2*4*4)(%rdx), %rax;
+ inpack_blocks(%rdx, RL1, RR1, RTMP, RX, RKM);
+ inpack_blocks(%rax, RL2, RR2, RTMP, RX, RKM);
+ leaq 2*(2*4*4)(%rdx), %rax;
+ inpack_blocks(%rax, RL3, RR3, RTMP, RX, RKM);
+ leaq 3*(2*4*4)(%rdx), %rax;
+ inpack_blocks(%rax, RL4, RR4, RTMP, RX, RKM);
+
+ movq %rsi, %r11;
+
+ 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 __skip_enc;
+
+ round(RL, RR, 12, 1);
+ round(RR, RL, 13, 2);
+ round(RL, RR, 14, 3);
+ round(RR, RL, 15, 1);
+
+__skip_enc:
+ popq %rcx;
+ popq %rbx;
+ popq %rbp;
+
+ vmovdqa .Lbswap_mask, RKM;
+ leaq 1*(2*4*4)(%r11), %rax;
+
+ testb %cl, %cl;
+ jnz __enc_xor16;
+
+ outunpack_blocks(%r11, RR1, RL1, RTMP, RX, RKM);
+ outunpack_blocks(%rax, RR2, RL2, RTMP, RX, RKM);
+ leaq 2*(2*4*4)(%r11), %rax;
+ outunpack_blocks(%rax, RR3, RL3, RTMP, RX, RKM);
+ leaq 3*(2*4*4)(%r11), %rax;
+ outunpack_blocks(%rax, RR4, RL4, RTMP, RX, RKM);
+
+ ret;
+
+__enc_xor16:
+ outunpack_xor_blocks(%r11, RR1, RL1, RTMP, RX, RKM);
+ outunpack_xor_blocks(%rax, RR2, RL2, RTMP, RX, RKM);
+ leaq 2*(2*4*4)(%r11), %rax;
+ outunpack_xor_blocks(%rax, RR3, RL3, RTMP, RX, RKM);
+ leaq 3*(2*4*4)(%r11), %rax;
+ outunpack_xor_blocks(%rax, RR4, RL4, RTMP, RX, RKM);
+
+ ret;
+
+.align 16
+.global cast5_dec_blk_16way
+.type cast5_dec_blk_16way,@function;
+
+cast5_dec_blk_16way:
+ /* input:
+ * %rdi: ctx, CTX
+ * %rsi: dst
+ * %rdx: src
+ */
+
+ pushq %rbp;
+ pushq %rbx;
+
+ vmovdqa .Lbswap_mask, RKM;
+ vmovd .Lfirst_mask, R1ST;
+ vmovd .L32_mask, R32;
+ dec_preload_rkr();
+
+ leaq 1*(2*4*4)(%rdx), %rax;
+ inpack_blocks(%rdx, RL1, RR1, RTMP, RX, RKM);
+ inpack_blocks(%rax, RL2, RR2, RTMP, RX, RKM);
+ leaq 2*(2*4*4)(%rdx), %rax;
+ inpack_blocks(%rax, RL3, RR3, RTMP, RX, RKM);
+ leaq 3*(2*4*4)(%rdx), %rax;
+ inpack_blocks(%rax, RL4, RR4, RTMP, RX, RKM);
+
+ movq %rsi, %r11;
+
+ movzbl rr(CTX), %eax;
+ testl %eax, %eax;
+ jnz __skip_dec;
+
+ round(RL, RR, 15, 1);
+ round(RR, RL, 14, 3);
+ round(RL, RR, 13, 2);
+ round(RR, RL, 12, 1);
+
+__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;
+
+ leaq 1*(2*4*4)(%r11), %rax;
+ outunpack_blocks(%r11, RR1, RL1, RTMP, RX, RKM);
+ outunpack_blocks(%rax, RR2, RL2, RTMP, RX, RKM);
+ leaq 2*(2*4*4)(%r11), %rax;
+ outunpack_blocks(%rax, RR3, RL3, RTMP, RX, RKM);
+ leaq 3*(2*4*4)(%r11), %rax;
+ outunpack_blocks(%rax, RR4, RL4, RTMP, RX, RKM);
+
+ ret;
+
+__skip_dec:
+ vpsrldq $4, RKR, RKR;
+ jmp __dec_tail;
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
new file mode 100644
index 00000000000..e0ea14f9547
--- /dev/null
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -0,0 +1,530 @@
+/*
+ * 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/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/ablk_helper.h>
+#include <asm/crypto/glue_helper.h>
+
+#define CAST5_PARALLEL_BLOCKS 16
+
+asmlinkage void __cast5_enc_blk_16way(struct cast5_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void cast5_dec_blk_16way(struct cast5_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+static inline void cast5_enc_blk_xway(struct cast5_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __cast5_enc_blk_16way(ctx, dst, src, false);
+}
+
+static inline void cast5_enc_blk_xway_xor(struct cast5_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __cast5_enc_blk_16way(ctx, dst, src, true);
+}
+
+static inline void cast5_dec_blk_xway(struct cast5_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ cast5_dec_blk_16way(ctx, dst, src);
+}
+
+
+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;
+ int err;
+
+ 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 {
+ if (enc)
+ cast5_enc_blk_xway(ctx, wdst, wsrc);
+ else
+ cast5_dec_blk_xway(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;
+ }
+
+ /* Handle leftovers */
+ do {
+ if (enc)
+ __cast5_encrypt(ctx, wdst, wsrc);
+ else
+ __cast5_decrypt(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 ivs[CAST5_PARALLEL_BLOCKS - 1];
+ u64 last_iv;
+ int i;
+
+ /* 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;
+
+ for (i = 0; i < CAST5_PARALLEL_BLOCKS - 1; i++)
+ ivs[i] = src[i];
+
+ cast5_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
+
+ for (i = 0; i < CAST5_PARALLEL_BLOCKS - 1; i++)
+ *(dst + (i + 1)) ^= *(ivs + i);
+
+ nbytes -= bsize;
+ if (nbytes < bsize)
+ goto done;
+
+ *dst ^= *(src - 1);
+ src -= 1;
+ dst -= 1;
+ } while (nbytes >= bsize * CAST5_PARALLEL_BLOCKS);
+
+ if (nbytes < bsize)
+ goto done;
+ }
+
+ /* 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;
+ u64 ctrblk = be64_to_cpu(*(__be64 *)walk->iv);
+ __be64 ctrblocks[CAST5_PARALLEL_BLOCKS];
+ int i;
+
+ /* Process multi-block batch */
+ if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
+ do {
+ /* create ctrblks for parallel encrypt */
+ for (i = 0; i < CAST5_PARALLEL_BLOCKS; i++) {
+ if (dst != src)
+ dst[i] = src[i];
+
+ ctrblocks[i] = cpu_to_be64(ctrblk++);
+ }
+
+ cast5_enc_blk_xway_xor(ctx, (u8 *)dst,
+ (u8 *)ctrblocks);
+
+ 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 {
+ if (dst != src)
+ *dst = *src;
+
+ ctrblocks[0] = cpu_to_be64(ctrblk++);
+
+ __cast5_encrypt(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
+ *dst ^= ctrblocks[0];
+
+ src += 1;
+ dst += 1;
+ nbytes -= bsize;
+ } while (nbytes >= 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)
+{
+ 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("cast5");
diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
new file mode 100644
index 00000000000..218d283772f
--- /dev/null
+++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S
@@ -0,0 +1,383 @@
+/*
+ * Cast6 Cipher 8-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
+ *
+ */
+
+.file "cast6-avx-x86_64-asm_64.S"
+
+.extern cast6_s1
+.extern cast6_s2
+.extern cast6_s3
+.extern cast6_s4
+
+/* structure of crypto context */
+#define km 0
+#define kr (12*4*4)
+
+/* s-boxes */
+#define s1 cast6_s1
+#define s2 cast6_s2
+#define s3 cast6_s3
+#define s4 cast6_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(in, x0, x1, x2, x3, t0, t1, t2, rmask) \
+ vmovdqu (0*4*4)(in), x0; \
+ vmovdqu (1*4*4)(in), x1; \
+ vmovdqu (2*4*4)(in), x2; \
+ vmovdqu (3*4*4)(in), x3; \
+ 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(out, 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; \
+ vmovdqu x0, (0*4*4)(out); \
+ vmovdqu x1, (1*4*4)(out); \
+ vmovdqu x2, (2*4*4)(out); \
+ vmovdqu x3, (3*4*4)(out);
+
+#define outunpack_xor_blocks(out, 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; \
+ vpxor (0*4*4)(out), x0, x0; \
+ vmovdqu x0, (0*4*4)(out); \
+ vpxor (1*4*4)(out), x1, x1; \
+ vmovdqu x1, (1*4*4)(out); \
+ vpxor (2*4*4)(out), x2, x2; \
+ vmovdqu x2, (2*4*4)(out); \
+ vpxor (3*4*4)(out), x3, x3; \
+ vmovdqu x3, (3*4*4)(out);
+
+.data
+
+.align 16
+.Lbswap_mask:
+ .byte 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
+.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 16
+.global __cast6_enc_blk_8way
+.type __cast6_enc_blk_8way,@function;
+
+__cast6_enc_blk_8way:
+ /* input:
+ * %rdi: ctx, CTX
+ * %rsi: dst
+ * %rdx: src
+ * %rcx: bool, if true: xor output
+ */
+
+ pushq %rbp;
+ pushq %rbx;
+ pushq %rcx;
+
+ vmovdqa .Lbswap_mask, RKM;
+ vmovd .Lfirst_mask, R1ST;
+ vmovd .L32_mask, R32;
+
+ leaq (4*4*4)(%rdx), %rax;
+ inpack_blocks(%rdx, RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+ inpack_blocks(%rax, RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+ movq %rsi, %r11;
+
+ 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 %rcx;
+ popq %rbx;
+ popq %rbp;
+
+ vmovdqa .Lbswap_mask, RKM;
+ leaq (4*4*4)(%r11), %rax;
+
+ testb %cl, %cl;
+ jnz __enc_xor8;
+
+ outunpack_blocks(%r11, RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+ outunpack_blocks(%rax, RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+ ret;
+
+__enc_xor8:
+ outunpack_xor_blocks(%r11, RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+ outunpack_xor_blocks(%rax, RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+ ret;
+
+.align 16
+.global cast6_dec_blk_8way
+.type cast6_dec_blk_8way,@function;
+
+cast6_dec_blk_8way:
+ /* input:
+ * %rdi: ctx, CTX
+ * %rsi: dst
+ * %rdx: src
+ */
+
+ pushq %rbp;
+ pushq %rbx;
+
+ vmovdqa .Lbswap_mask, RKM;
+ vmovd .Lfirst_mask, R1ST;
+ vmovd .L32_mask, R32;
+
+ leaq (4*4*4)(%rdx), %rax;
+ inpack_blocks(%rdx, RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+ inpack_blocks(%rax, RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+ movq %rsi, %r11;
+
+ 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;
+ leaq (4*4*4)(%r11), %rax;
+ outunpack_blocks(%r11, RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
+ outunpack_blocks(%rax, RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);
+
+ ret;
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
new file mode 100644
index 00000000000..15e5f85a501
--- /dev/null
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -0,0 +1,648 @@
+/*
+ * Glue Code for the AVX assembler implemention of the Cast6 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/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/ablk_helper.h>
+#include <asm/crypto/glue_helper.h>
+
+#define CAST6_PARALLEL_BLOCKS 8
+
+asmlinkage void __cast6_enc_blk_8way(struct cast6_ctx *ctx, u8 *dst,
+ const u8 *src, bool xor);
+asmlinkage void cast6_dec_blk_8way(struct cast6_ctx *ctx, u8 *dst,
+ const u8 *src);
+
+static inline void cast6_enc_blk_xway(struct cast6_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __cast6_enc_blk_8way(ctx, dst, src, false);
+}
+
+static inline void cast6_enc_blk_xway_xor(struct cast6_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ __cast6_enc_blk_8way(ctx, dst, src, true);
+}
+
+static inline void cast6_dec_blk_xway(struct cast6_ctx *ctx, u8 *dst,
+ const u8 *src)
+{
+ cast6_dec_blk_8way(ctx, dst, src);
+}
+
+
+static void cast6_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src)
+{
+ u128 ivs[CAST6_PARALLEL_BLOCKS - 1];
+ unsigned int j;
+
+ for (j = 0; j < CAST6_PARALLEL_BLOCKS - 1; j++)
+ ivs[j] = src[j];
+
+ cast6_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
+
+ for (j = 0; j < CAST6_PARALLEL_BLOCKS - 1; j++)
+ u128_xor(dst + (j + 1), dst + (j + 1), ivs + j);
+}
+
+static void cast6_crypt_ctr(void *ctx, u128 *dst, const u128 *src, u128 *iv)
+{
+ be128 ctrblk;
+
+ u128_to_be128(&ctrblk, iv);
+ u128_inc(iv);
+
+ __cast6_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
+ u128_xor(dst, src, (u128 *)&ctrblk);
+}
+
+static void cast6_crypt_ctr_xway(void *ctx, u128 *dst, const u128 *src,
+ u128 *iv)
+{
+ be128 ctrblks[CAST6_PARALLEL_BLOCKS];
+ unsigned int i;
+
+ for (i = 0; i < CAST6_PARALLEL_BLOCKS; i++) {
+ if (dst != src)
+ dst[i] = src[i];
+
+ u128_to_be128(&ctrblks[i], iv);
+ u128_inc(iv);
+ }
+
+ cast6_enc_blk_xway_xor(ctx, (u8 *)dst, (u8 *)ctrblks);
+}
+
+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_enc_blk_xway) }
+ }, {
+ .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_crypt_ctr_xway) }
+ }, {
+ .num_blocks = 1,
+ .fn_u = { .ctr = GLUE_CTR_FUNC_CAST(cast6_crypt_ctr) }
+ } }
+};
+
+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_dec_blk_xway) }
+ }, {
+ .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_decrypt_cbc_xway) }
+ }, {
+ .num_blocks = 1,
+ .fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__cast6_decrypt) }
+ } }
+};
+
+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_enc_blk_xway(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_dec_blk_xway(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);
+ be128 buf[CAST6_PARALLEL_BLOCKS];
+ struct crypt_priv crypt_ctx = {
+ .ctx = &ctx->crypt_ctx,
+ .fpu_enabled = false,
+ };
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = &ctx->tweak_ctx,
+ .tweak_fn = XTS_TWEAK_CAST(__cast6_encrypt),
+ .crypt_ctx = &crypt_ctx,
+ .crypt_fn = encrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ ret = xts_crypt(desc, dst, src, nbytes, &req);
+ cast6_fpu_end(crypt_ctx.fpu_enabled);
+
+ return ret;
+}
+
+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);
+ be128 buf[CAST6_PARALLEL_BLOCKS];
+ struct crypt_priv crypt_ctx = {
+ .ctx = &ctx->crypt_ctx,
+ .fpu_enabled = false,
+ };
+ struct xts_crypt_req req = {
+ .tbuf = buf,
+ .tbuflen = sizeof(buf),
+
+ .tweak_ctx = &ctx->tweak_ctx,
+ .tweak_fn = XTS_TWEAK_CAST(__cast6_encrypt),
+ .crypt_ctx = &crypt_ctx,
+ .crypt_fn = decrypt_callback,
+ };
+ int ret;
+
+ desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+ ret = xts_crypt(desc, dst, src, nbytes, &req);
+ cast6_fpu_end(crypt_ctx.fpu_enabled);
+
+ return ret;
+}
+
+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("cast6");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index b4bf0a63b52..6759dd1135b 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -150,7 +150,6 @@ static struct shash_alg ghash_alg = {
.cra_blocksize = GHASH_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct ghash_ctx),
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(ghash_alg.base.cra_list),
},
};
@@ -288,7 +287,6 @@ static struct ahash_alg ghash_async_alg = {
.cra_blocksize = GHASH_BLOCK_SIZE,
.cra_type = &crypto_ahash_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(ghash_async_alg.halg.base.cra_list),
.cra_init = ghash_async_init_tfm,
.cra_exit = ghash_async_exit_tfm,
},
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index 4854f0f31e4..30b3927bd73 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -110,7 +110,7 @@ static unsigned int __glue_cbc_encrypt_128bit(const common_glue_func_t fn,
nbytes -= bsize;
} while (nbytes >= bsize);
- u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
+ *(u128 *)walk->iv = *iv;
return nbytes;
}
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index bccb76d8098..a3a3c0205c1 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -97,7 +97,6 @@ static struct crypto_alg alg = {
.cra_ctxsize = sizeof(struct salsa20_ctx),
.cra_alignmask = 3,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(alg.cra_list),
.cra_u = {
.blkcipher = {
.setkey = setkey,
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index b36bdac237e..3f543a04cf1 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -390,7 +390,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[0].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE,
@@ -410,7 +409,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[1].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE,
@@ -430,7 +428,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[2].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE,
@@ -451,7 +448,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[3].cra_list),
.cra_exit = lrw_exit_tfm,
.cra_u = {
.blkcipher = {
@@ -475,7 +471,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[4].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE * 2,
@@ -496,7 +491,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[5].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -518,7 +512,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[6].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -541,7 +534,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[7].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -565,7 +557,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[8].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -590,7 +581,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[9].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index d679c8675f4..9107a9908c4 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -393,7 +393,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[0].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE,
@@ -413,7 +412,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[1].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE,
@@ -433,7 +431,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[2].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE,
@@ -454,7 +451,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[3].cra_list),
.cra_exit = lrw_exit_tfm,
.cra_u = {
.blkcipher = {
@@ -478,7 +474,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[4].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = SERPENT_MIN_KEY_SIZE * 2,
@@ -499,7 +494,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[5].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -521,7 +515,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[6].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -544,7 +537,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[7].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -568,7 +560,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[8].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -593,7 +584,6 @@ static struct crypto_alg serpent_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(serpent_algs[9].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
index 35f45574390..1585abb13dd 100644
--- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -4,6 +4,8 @@
* 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
@@ -47,16 +49,22 @@
#define RC2 %xmm6
#define RD2 %xmm7
-#define RX %xmm8
-#define RY %xmm9
+#define RX0 %xmm8
+#define RY0 %xmm9
+
+#define RX1 %xmm10
+#define RY1 %xmm11
-#define RK1 %xmm10
-#define RK2 %xmm11
+#define RK1 %xmm12
+#define RK2 %xmm13
-#define RID1 %rax
-#define RID1b %al
-#define RID2 %rbx
-#define RID2b %bl
+#define RT %xmm14
+#define RR %xmm15
+
+#define RID1 %rbp
+#define RID1d %ebp
+#define RID2 %rsi
+#define RID2d %esi
#define RGI1 %rdx
#define RGI1bl %dl
@@ -65,6 +73,13 @@
#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 RGS1 %r8
#define RGS1d %r8d
#define RGS2 %r9
@@ -73,89 +88,123 @@
#define RGS3d %r10d
-#define lookup_32bit(t0, t1, t2, t3, src, dst) \
- movb src ## bl, RID1b; \
- movb src ## bh, RID2b; \
- movl t0(CTX, RID1, 4), dst ## d; \
- xorl t1(CTX, RID2, 4), dst ## d; \
+#define lookup_32bit(t0, t1, t2, t3, src, dst, interleave_op, il_reg) \
+ movzbl src ## bl, RID1d; \
+ movzbl src ## bh, RID2d; \
shrq $16, src; \
- movb src ## bl, RID1b; \
- movb src ## bh, RID2b; \
+ movl t0(CTX, RID1, 4), dst ## d; \
+ movl t1(CTX, RID2, 4), RID2d; \
+ movzbl src ## bl, RID1d; \
+ xorl RID2d, dst ## d; \
+ movzbl src ## bh, RID2d; \
+ interleave_op(il_reg); \
xorl t2(CTX, RID1, 4), dst ## d; \
xorl t3(CTX, RID2, 4), dst ## d;
-#define G(a, x, t0, t1, t2, t3) \
- vmovq a, RGI1; \
- vpsrldq $8, a, x; \
- vmovq x, RGI2; \
+#define dummy(d) /* do nothing */
+
+#define shr_next(reg) \
+ shrq $16, reg;
+
+#define G(gi1, gi2, x, t0, t1, t2, t3) \
+ lookup_32bit(t0, t1, t2, t3, ##gi1, RGS1, shr_next, ##gi1); \
+ lookup_32bit(t0, t1, t2, t3, ##gi2, RGS3, shr_next, ##gi2); \
+ \
+ lookup_32bit(t0, t1, t2, t3, ##gi1, RGS2, dummy, none); \
+ shlq $32, RGS2; \
+ orq RGS1, RGS2; \
+ lookup_32bit(t0, t1, t2, t3, ##gi2, RGS1, dummy, none); \
+ shlq $32, RGS1; \
+ orq RGS1, RGS3;
+
+#define round_head_2(a, b, x1, y1, x2, y2) \
+ vmovq b ## 1, RGI3; \
+ vpextrq $1, b ## 1, RGI4; \
\
- lookup_32bit(t0, t1, t2, t3, RGI1, RGS1); \
- shrq $16, RGI1; \
- lookup_32bit(t0, t1, t2, t3, RGI1, RGS2); \
- shlq $32, RGS2; \
- orq RGS1, RGS2; \
+ G(RGI1, RGI2, x1, s0, s1, s2, s3); \
+ vmovq a ## 2, RGI1; \
+ vpextrq $1, a ## 2, RGI2; \
+ vmovq RGS2, x1; \
+ vpinsrq $1, RGS3, x1, x1; \
\
- lookup_32bit(t0, t1, t2, t3, RGI2, RGS1); \
- shrq $16, RGI2; \
- lookup_32bit(t0, t1, t2, t3, RGI2, RGS3); \
- shlq $32, RGS3; \
- orq RGS1, RGS3; \
+ G(RGI3, RGI4, y1, s1, s2, s3, s0); \
+ vmovq b ## 2, RGI3; \
+ vpextrq $1, b ## 2, RGI4; \
+ vmovq RGS2, y1; \
+ vpinsrq $1, RGS3, y1, y1; \
\
- vmovq RGS2, x; \
- vpinsrq $1, RGS3, x, x;
+ G(RGI1, RGI2, x2, s0, s1, s2, s3); \
+ vmovq RGS2, x2; \
+ vpinsrq $1, RGS3, x2, x2; \
+ \
+ G(RGI3, RGI4, y2, s1, s2, s3, s0); \
+ vmovq RGS2, y2; \
+ vpinsrq $1, RGS3, y2, y2;
-#define encround(a, b, c, d, x, y) \
- G(a, x, s0, s1, s2, s3); \
- G(b, y, s1, s2, s3, s0); \
+#define encround_tail(a, b, c, d, x, y, prerotate) \
vpaddd x, y, x; \
+ vpaddd x, RK1, RT;\
+ prerotate(b); \
+ vpxor RT, c, c; \
vpaddd y, x, y; \
- vpaddd x, RK1, x; \
vpaddd y, RK2, y; \
- vpxor x, c, c; \
- vpsrld $1, c, x; \
+ vpsrld $1, c, RT; \
vpslld $(32 - 1), c, c; \
- vpor c, x, c; \
- vpslld $1, d, x; \
- vpsrld $(32 - 1), d, d; \
- vpor d, x, d; \
- vpxor d, y, d;
-
-#define decround(a, b, c, d, x, y) \
- G(a, x, s0, s1, s2, s3); \
- G(b, y, s1, s2, s3, s0); \
+ vpor c, RT, c; \
+ vpxor d, y, d; \
+
+#define decround_tail(a, b, c, d, x, y, prerotate) \
vpaddd x, y, x; \
+ vpaddd x, RK1, RT;\
+ prerotate(a); \
+ vpxor RT, c, c; \
vpaddd y, x, y; \
vpaddd y, RK2, y; \
vpxor d, y, d; \
vpsrld $1, d, y; \
vpslld $(32 - 1), d, d; \
vpor d, y, d; \
- vpslld $1, c, y; \
- vpsrld $(32 - 1), c, c; \
- vpor c, y, c; \
- vpaddd x, RK1, x; \
- vpxor x, c, c;
-
-#define encrypt_round(n, a, b, c, d) \
- vbroadcastss (k+4*(2*(n)))(CTX), RK1; \
- vbroadcastss (k+4*(2*(n)+1))(CTX), RK2; \
- encround(a ## 1, b ## 1, c ## 1, d ## 1, RX, RY); \
- encround(a ## 2, b ## 2, c ## 2, d ## 2, RX, RY);
-
-#define decrypt_round(n, a, b, c, d) \
- vbroadcastss (k+4*(2*(n)))(CTX), RK1; \
- vbroadcastss (k+4*(2*(n)+1))(CTX), RK2; \
- decround(a ## 1, b ## 1, c ## 1, d ## 1, RX, RY); \
- decround(a ## 2, b ## 2, c ## 2, d ## 2, RX, RY);
+
+#define rotate_1l(x) \
+ vpslld $1, x, RR; \
+ vpsrld $(32 - 1), x, x; \
+ vpor x, RR, x;
+
+#define preload_rgi(c) \
+ vmovq c, RGI1; \
+ vpextrq $1, c, RGI2;
+
+#define encrypt_round(n, a, b, c, d, preload, prerotate) \
+ vbroadcastss (k+4*(2*(n)))(CTX), RK1; \
+ vbroadcastss (k+4*(2*(n)+1))(CTX), RK2; \
+ round_head_2(a, b, RX0, RY0, RX1, RY1); \
+ encround_tail(a ## 1, b ## 1, c ## 1, d ## 1, RX0, RY0, prerotate); \
+ preload(c ## 1); \
+ encround_tail(a ## 2, b ## 2, c ## 2, d ## 2, RX1, RY1, prerotate);
+
+#define decrypt_round(n, a, b, c, d, preload, prerotate) \
+ vbroadcastss (k+4*(2*(n)))(CTX), RK1; \
+ vbroadcastss (k+4*(2*(n)+1))(CTX), RK2; \
+ round_head_2(a, b, RX0, RY0, RX1, RY1); \
+ decround_tail(a ## 1, b ## 1, c ## 1, d ## 1, RX0, RY0, prerotate); \
+ preload(c ## 1); \
+ decround_tail(a ## 2, b ## 2, c ## 2, d ## 2, RX1, RY1, prerotate);
#define encrypt_cycle(n) \
- encrypt_round((2*n), RA, RB, RC, RD); \
- encrypt_round(((2*n) + 1), RC, RD, RA, RB);
+ encrypt_round((2*n), RA, RB, RC, RD, preload_rgi, rotate_1l); \
+ encrypt_round(((2*n) + 1), RC, RD, RA, RB, preload_rgi, rotate_1l);
+
+#define encrypt_cycle_last(n) \
+ encrypt_round((2*n), RA, RB, RC, RD, preload_rgi, rotate_1l); \
+ encrypt_round(((2*n) + 1), RC, RD, RA, RB, dummy, dummy);
#define decrypt_cycle(n) \
- decrypt_round(((2*n) + 1), RC, RD, RA, RB); \
- decrypt_round((2*n), RA, RB, RC, RD);
+ decrypt_round(((2*n) + 1), RC, RD, RA, RB, preload_rgi, rotate_1l); \
+ decrypt_round((2*n), RA, RB, RC, RD, preload_rgi, rotate_1l);
+#define decrypt_cycle_last(n) \
+ decrypt_round(((2*n) + 1), RC, RD, RA, RB, preload_rgi, rotate_1l); \
+ decrypt_round((2*n), RA, RB, RC, RD, dummy, dummy);
#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
vpunpckldq x1, x0, t0; \
@@ -216,17 +265,20 @@ __twofish_enc_blk_8way:
* %rcx: bool, if true: xor output
*/
+ pushq %rbp;
pushq %rbx;
pushq %rcx;
vmovdqu w(CTX), RK1;
leaq (4*4*4)(%rdx), %rax;
- inpack_blocks(%rdx, RA1, RB1, RC1, RD1, RK1, RX, RY, RK2);
- inpack_blocks(%rax, RA2, RB2, RC2, RD2, RK1, RX, RY, RK2);
+ inpack_blocks(%rdx, RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
+ preload_rgi(RA1);
+ rotate_1l(RD1);
+ inpack_blocks(%rax, RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
+ rotate_1l(RD2);
- xorq RID1, RID1;
- xorq RID2, RID2;
+ movq %rsi, %r11;
encrypt_cycle(0);
encrypt_cycle(1);
@@ -235,26 +287,27 @@ __twofish_enc_blk_8way:
encrypt_cycle(4);
encrypt_cycle(5);
encrypt_cycle(6);
- encrypt_cycle(7);
+ encrypt_cycle_last(7);
vmovdqu (w+4*4)(CTX), RK1;
popq %rcx;
popq %rbx;
+ popq %rbp;
- leaq (4*4*4)(%rsi), %rax;
+ leaq (4*4*4)(%r11), %rax;
testb %cl, %cl;
jnz __enc_xor8;
- outunpack_blocks(%rsi, RC1, RD1, RA1, RB1, RK1, RX, RY, RK2);
- outunpack_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX, RY, RK2);
+ outunpack_blocks(%r11, RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
+ outunpack_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
ret;
__enc_xor8:
- outunpack_xor_blocks(%rsi, RC1, RD1, RA1, RB1, RK1, RX, RY, RK2);
- outunpack_xor_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX, RY, RK2);
+ outunpack_xor_blocks(%r11, RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
+ outunpack_xor_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
ret;
@@ -269,16 +322,19 @@ twofish_dec_blk_8way:
* %rdx: src
*/
+ pushq %rbp;
pushq %rbx;
vmovdqu (w+4*4)(CTX), RK1;
leaq (4*4*4)(%rdx), %rax;
- inpack_blocks(%rdx, RC1, RD1, RA1, RB1, RK1, RX, RY, RK2);
- inpack_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX, RY, RK2);
+ inpack_blocks(%rdx, RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
+ preload_rgi(RC1);
+ rotate_1l(RA1);
+ inpack_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
+ rotate_1l(RA2);
- xorq RID1, RID1;
- xorq RID2, RID2;
+ movq %rsi, %r11;
decrypt_cycle(7);
decrypt_cycle(6);
@@ -287,14 +343,15 @@ twofish_dec_blk_8way:
decrypt_cycle(3);
decrypt_cycle(2);
decrypt_cycle(1);
- decrypt_cycle(0);
+ decrypt_cycle_last(0);
vmovdqu (w)(CTX), RK1;
popq %rbx;
+ popq %rbp;
- leaq (4*4*4)(%rsi), %rax;
- outunpack_blocks(%rsi, RA1, RB1, RC1, RD1, RK1, RX, RY, RK2);
- outunpack_blocks(%rax, RA2, RB2, RC2, RD2, RK1, RX, RY, RK2);
+ leaq (4*4*4)(%r11), %rax;
+ outunpack_blocks(%r11, RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
+ outunpack_blocks(%rax, RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
ret;
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 782b67ddaf6..e7708b5442e 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -378,7 +378,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[0].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE,
@@ -398,7 +397,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[1].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE,
@@ -418,7 +416,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[2].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE,
@@ -439,7 +436,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[3].cra_list),
.cra_exit = lrw_twofish_exit_tfm,
.cra_u = {
.blkcipher = {
@@ -463,7 +459,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[4].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE * 2,
@@ -484,7 +479,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[5].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -506,7 +500,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[6].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -529,7 +522,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[7].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -553,7 +545,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[8].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
@@ -578,7 +569,6 @@ static struct crypto_alg twofish_algs[10] = { {
.cra_alignmask = 0,
.cra_type = &crypto_ablkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(twofish_algs[9].cra_list),
.cra_init = ablk_init,
.cra_exit = ablk_exit,
.cra_u = {
diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c
index 359ae084275..0a520230350 100644
--- a/arch/x86/crypto/twofish_glue.c
+++ b/arch/x86/crypto/twofish_glue.c
@@ -70,7 +70,6 @@ static struct crypto_alg alg = {
.cra_ctxsize = sizeof(struct twofish_ctx),
.cra_alignmask = 0,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(alg.cra_list),
.cra_u = {
.cipher = {
.cia_min_keysize = TF_MIN_KEY_SIZE,
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 15f9347316c..aa3eb358b7e 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -342,7 +342,6 @@ static struct crypto_alg tf_algs[5] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(tf_algs[0].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE,
@@ -362,7 +361,6 @@ static struct crypto_alg tf_algs[5] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(tf_algs[1].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE,
@@ -383,7 +381,6 @@ static struct crypto_alg tf_algs[5] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(tf_algs[2].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE,
@@ -404,7 +401,6 @@ static struct crypto_alg tf_algs[5] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(tf_algs[3].cra_list),
.cra_exit = lrw_twofish_exit_tfm,
.cra_u = {
.blkcipher = {
@@ -426,7 +422,6 @@ static struct crypto_alg tf_algs[5] = { {
.cra_alignmask = 0,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
- .cra_list = LIST_HEAD_INIT(tf_algs[4].cra_list),
.cra_u = {
.blkcipher = {
.min_keysize = TF_MIN_KEY_SIZE * 2,
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 673ac9b63d6..efc6a958b71 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -32,6 +32,7 @@
#include <asm/sigframe.h>
#include <asm/sighandling.h>
#include <asm/sys_ia32.h>
+#include <asm/smap.h>
#define FIX_EFLAGS __FIX_EFLAGS
@@ -162,7 +163,8 @@ asmlinkage long sys32_sigaltstack(const stack_ia32_t __user *uss_ptr,
}
seg = get_fs();
set_fs(KERNEL_DS);
- ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp);
+ ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL),
+ (stack_t __force __user *) &uoss, regs->sp);
set_fs(seg);
if (ret >= 0 && uoss_ptr) {
if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)))
@@ -250,11 +252,12 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
get_user_ex(tmp, &sc->fpstate);
buf = compat_ptr(tmp);
- err |= restore_i387_xstate_ia32(buf);
get_user_ex(*pax, &sc->ax);
} get_user_catch(err);
+ err |= restore_xstate_sig(buf, 1);
+
return err;
}
@@ -361,7 +364,7 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
*/
static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
size_t frame_size,
- void **fpstate)
+ void __user **fpstate)
{
unsigned long sp;
@@ -381,9 +384,12 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
sp = (unsigned long) ka->sa.sa_restorer;
if (used_math()) {
- sp = sp - sig_xstate_ia32_size;
- *fpstate = (struct _fpstate_ia32 *) sp;
- if (save_i387_xstate_ia32(*fpstate) < 0)
+ unsigned long fx_aligned, math_size;
+
+ sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+ *fpstate = (struct _fpstate_ia32 __user *) sp;
+ if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+ math_size) < 0)
return (void __user *) -1L;
}
@@ -448,7 +454,7 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
* These are actually not used anymore, but left because some
* gdb versions depend on them as a marker.
*/
- put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+ put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
} put_user_catch(err);
if (err)
@@ -502,7 +508,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
put_user_ex(sig, &frame->sig);
put_user_ex(ptr_to_compat(&frame->info), &frame->pinfo);
put_user_ex(ptr_to_compat(&frame->uc), &frame->puc);
- err |= copy_siginfo_to_user32(&frame->info, info);
/* Create the ucontext. */
if (cpu_has_xsave)
@@ -514,9 +519,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
put_user_ex(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (ka->sa.sa_flags & SA_RESTORER)
restorer = ka->sa.sa_restorer;
@@ -529,9 +531,14 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
* Not actually used anymore, but left because some gdb
* versions need it.
*/
- put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+ put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
} put_user_catch(err);
+ err |= copy_siginfo_to_user32(&frame->info, info);
+ err |= ia32_setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
if (err)
return -EFAULT;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 20e5f7ba0e6..9c289504e68 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -14,6 +14,7 @@
#include <asm/segment.h>
#include <asm/irqflags.h>
#include <asm/asm.h>
+#include <asm/smap.h>
#include <linux/linkage.h>
#include <linux/err.h>
@@ -146,8 +147,10 @@ ENTRY(ia32_sysenter_target)
SAVE_ARGS 0,1,0
/* no need to do an access_ok check here because rbp has been
32bit zero extended */
+ ASM_STAC
1: movl (%rbp),%ebp
_ASM_EXTABLE(1b,ia32_badarg)
+ ASM_CLAC
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
@@ -301,8 +304,10 @@ ENTRY(ia32_cstar_target)
/* no need to do an access_ok check here because r8 has been
32bit zero extended */
/* hardware stack frame is complete now */
+ ASM_STAC
1: movl (%r8),%r9d
_ASM_EXTABLE(1b,ia32_badarg)
+ ASM_CLAC
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
@@ -365,6 +370,7 @@ cstar_tracesys:
END(ia32_cstar_target)
ia32_badarg:
+ ASM_CLAC
movq $-EFAULT,%rax
jmp ia32_sysret
CFI_ENDPROC
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 4540bece094..c5b938d92ea 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -287,7 +287,7 @@ asmlinkage long sys32_sigaction(int sig, struct old_sigaction32 __user *act,
return ret;
}
-asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr,
+asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr,
int options)
{
return compat_sys_wait4(pid, stat_addr, options, NULL);
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index f9c0d3ba9e8..1595d681343 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -22,7 +22,3 @@ header-y += sigcontext32.h
header-y += ucontext.h
header-y += vm86.h
header-y += vsyscall.h
-
-genhdr-y += unistd_32.h
-genhdr-y += unistd_64.h
-genhdr-y += unistd_x32.h
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 952bd0100c5..372231c22a4 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -1,3 +1,6 @@
+#ifndef _ASM_X86_ALTERNATIVE_ASM_H
+#define _ASM_X86_ALTERNATIVE_ASM_H
+
#ifdef __ASSEMBLY__
#include <asm/asm.h>
@@ -5,10 +8,10 @@
#ifdef CONFIG_SMP
.macro LOCK_PREFIX
672: lock
- .section .smp_locks,"a"
+ .pushsection .smp_locks,"a"
.balign 4
.long 672b - .
- .previous
+ .popsection
.endm
#else
.macro LOCK_PREFIX
@@ -24,3 +27,5 @@
.endm
#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 70780689599..58ed6d96a6a 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -29,10 +29,10 @@
#ifdef CONFIG_SMP
#define LOCK_PREFIX_HERE \
- ".section .smp_locks,\"a\"\n" \
- ".balign 4\n" \
- ".long 671f - .\n" /* offset */ \
- ".previous\n" \
+ ".pushsection .smp_locks,\"a\"\n" \
+ ".balign 4\n" \
+ ".long 671f - .\n" /* offset */ \
+ ".popsection\n" \
"671:"
#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
@@ -60,7 +60,7 @@ extern void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end);
extern void alternatives_smp_module_del(struct module *mod);
-extern void alternatives_smp_switch(int smp);
+extern void alternatives_enable_smp(void);
extern int alternatives_text_reserved(void *start, void *end);
extern bool skip_smp_alternatives;
#else
@@ -68,7 +68,7 @@ static inline void alternatives_smp_module_add(struct module *mod, char *name,
void *locks, void *locks_end,
void *text, void *text_end) {}
static inline void alternatives_smp_module_del(struct module *mod) {}
-static inline void alternatives_smp_switch(int smp) {}
+static inline void alternatives_enable_smp(void) {}
static inline int alternatives_text_reserved(void *start, void *end)
{
return 0;
@@ -99,30 +99,30 @@ static inline int alternatives_text_reserved(void *start, void *end)
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
OLDINSTR(oldinstr) \
- ".section .altinstructions,\"a\"\n" \
+ ".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feature, 1) \
- ".previous\n" \
- ".section .discard,\"aw\",@progbits\n" \
+ ".popsection\n" \
+ ".pushsection .discard,\"aw\",@progbits\n" \
DISCARD_ENTRY(1) \
- ".previous\n" \
- ".section .altinstr_replacement, \"ax\"\n" \
+ ".popsection\n" \
+ ".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
- ".previous"
+ ".popsection"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
OLDINSTR(oldinstr) \
- ".section .altinstructions,\"a\"\n" \
+ ".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feature1, 1) \
ALTINSTR_ENTRY(feature2, 2) \
- ".previous\n" \
- ".section .discard,\"aw\",@progbits\n" \
+ ".popsection\n" \
+ ".pushsection .discard,\"aw\",@progbits\n" \
DISCARD_ENTRY(1) \
DISCARD_ENTRY(2) \
- ".previous\n" \
- ".section .altinstr_replacement, \"ax\"\n" \
+ ".popsection\n" \
+ ".pushsection .altinstr_replacement, \"ax\"\n" \
ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
- ".previous"
+ ".popsection"
/*
* This must be included *after* the definition of ALTERNATIVE due to
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f34261296ff..33880342223 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -409,7 +409,7 @@ extern struct apic *apic;
* to enforce the order with in them.
*/
#define apic_driver(sym) \
- static struct apic *__apicdrivers_##sym __used \
+ static const struct apic *__apicdrivers_##sym __used \
__aligned(sizeof(struct apic *)) \
__section(.apicdrivers) = { &sym }
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 58cb6d4085f..250b8774c15 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -309,9 +309,9 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
#define smp_mb__after_atomic_inc() barrier()
#ifdef CONFIG_X86_32
-# include "atomic64_32.h"
+# include <asm/atomic64_32.h>
#else
-# include "atomic64_64.h"
+# include <asm/atomic64_64.h>
#endif
#endif /* _ASM_X86_ATOMIC_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 72f5009deb5..6dfd0195bb5 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -355,7 +355,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
*/
static inline unsigned long __ffs(unsigned long word)
{
- asm("bsf %1,%0"
+ asm("rep; bsf %1,%0"
: "=r" (word)
: "rm" (word));
return word;
@@ -369,7 +369,7 @@ static inline unsigned long __ffs(unsigned long word)
*/
static inline unsigned long ffz(unsigned long word)
{
- asm("bsf %1,%0"
+ asm("rep; bsf %1,%0"
: "=r" (word)
: "r" (~word));
return word;
@@ -417,10 +417,9 @@ static inline int ffs(int x)
* We cannot do this on 32 bits because at the very least some
* 486 CPUs did not behave this way.
*/
- long tmp = -1;
asm("bsfl %1,%0"
: "=r" (r)
- : "rm" (x), "0" (tmp));
+ : "rm" (x), "0" (-1));
#elif defined(CONFIG_X86_CMOV)
asm("bsfl %1,%0\n\t"
"cmovzl %2,%0"
@@ -459,10 +458,9 @@ static inline int fls(int x)
* We cannot do this on 32 bits because at the very least some
* 486 CPUs did not behave this way.
*/
- long tmp = -1;
asm("bsrl %1,%0"
: "=r" (r)
- : "rm" (x), "0" (tmp));
+ : "rm" (x), "0" (-1));
#elif defined(CONFIG_X86_CMOV)
asm("bsrl %1,%0\n\t"
"cmovzl %2,%0"
@@ -490,13 +488,13 @@ static inline int fls(int x)
#ifdef CONFIG_X86_64
static __always_inline int fls64(__u64 x)
{
- long bitpos = -1;
+ int bitpos = -1;
/*
* AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
* dest reg is undefined if x==0, but their CPU architect says its
* value is written to set it to the same as before.
*/
- asm("bsrq %1,%0"
+ asm("bsrq %1,%q0"
: "+r" (bitpos)
: "rm" (x));
return bitpos + 1;
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index a9e3a740f69..0fa67503391 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -46,41 +46,39 @@ For 32-bit we have the following conventions - kernel is built with
*/
-#include "dwarf2.h"
+#include <asm/dwarf2.h>
/*
- * 64-bit system call stack frame layout defines and helpers, for
- * assembly code (note that the seemingly unnecessary parentheses
- * are to prevent cpp from inserting spaces in expressions that get
- * passed to macros):
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
*/
-#define R15 (0)
-#define R14 (8)
-#define R13 (16)
-#define R12 (24)
-#define RBP (32)
-#define RBX (40)
+#define R15 0
+#define R14 8
+#define R13 16
+#define R12 24
+#define RBP 32
+#define RBX 40
/* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11 (48)
-#define R10 (56)
-#define R9 (64)
-#define R8 (72)
-#define RAX (80)
-#define RCX (88)
-#define RDX (96)
-#define RSI (104)
-#define RDI (112)
-#define ORIG_RAX (120) /* + error_code */
+#define R11 48
+#define R10 56
+#define R9 64
+#define R8 72
+#define RAX 80
+#define RCX 88
+#define RDX 96
+#define RSI 104
+#define RDI 112
+#define ORIG_RAX 120 /* + error_code */
/* end of arguments */
/* cpu exception frame or undefined in case of fast syscall: */
-#define RIP (128)
-#define CS (136)
-#define EFLAGS (144)
-#define RSP (152)
-#define SS (160)
+#define RIP 128
+#define CS 136
+#define EFLAGS 144
+#define RSP 152
+#define SS 160
#define ARGOFFSET R11
#define SWFRAME ORIG_RAX
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index 848850fd7d6..5f5bb0f9736 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "checksum_32.h"
+# include <asm/checksum_32.h>
#else
-# include "checksum_64.h"
+# include <asm/checksum_64.h>
#endif
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 99480e55973..8d871eaddb6 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -138,9 +138,9 @@ extern void __add_wrong_size(void)
__raw_cmpxchg((ptr), (old), (new), (size), "")
#ifdef CONFIG_X86_32
-# include "cmpxchg_32.h"
+# include <asm/cmpxchg_32.h>
#else
-# include "cmpxchg_64.h"
+# include <asm/cmpxchg_64.h>
#endif
#ifdef __HAVE_ARCH_CMPXCHG
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index fedf32b73e6..59c6c401f79 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -41,6 +41,7 @@ typedef s64 __attribute__((aligned(4))) compat_s64;
typedef u32 compat_uint_t;
typedef u32 compat_ulong_t;
typedef u64 __attribute__((aligned(4))) compat_u64;
+typedef u32 compat_uptr_t;
struct compat_timespec {
compat_time_t tv_sec;
@@ -124,6 +125,78 @@ typedef u32 compat_old_sigset_t; /* at least 32 bits */
typedef u32 compat_sigset_word;
+typedef union compat_sigval {
+ compat_int_t sival_int;
+ compat_uptr_t sival_ptr;
+} compat_sigval_t;
+
+typedef struct compat_siginfo {
+ int si_signo;
+ int si_errno;
+ int si_code;
+
+ union {
+ int _pad[128/sizeof(int) - 3];
+
+ /* kill() */
+ struct {
+ unsigned int _pid; /* sender's pid */
+ unsigned int _uid; /* sender's uid */
+ } _kill;
+
+ /* POSIX.1b timers */
+ struct {
+ compat_timer_t _tid; /* timer id */
+ int _overrun; /* overrun count */
+ compat_sigval_t _sigval; /* same as below */
+ int _sys_private; /* not to be passed to user */
+ int _overrun_incr; /* amount to add to overrun */
+ } _timer;
+
+ /* POSIX.1b signals */
+ struct {
+ unsigned int _pid; /* sender's pid */
+ unsigned int _uid; /* sender's uid */
+ compat_sigval_t _sigval;
+ } _rt;
+
+ /* SIGCHLD */
+ struct {
+ unsigned int _pid; /* which child */
+ unsigned int _uid; /* sender's uid */
+ int _status; /* exit code */
+ compat_clock_t _utime;
+ compat_clock_t _stime;
+ } _sigchld;
+
+ /* SIGCHLD (x32 version) */
+ struct {
+ unsigned int _pid; /* which child */
+ unsigned int _uid; /* sender's uid */
+ int _status; /* exit code */
+ compat_s64 _utime;
+ compat_s64 _stime;
+ } _sigchld_x32;
+
+ /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+ struct {
+ unsigned int _addr; /* faulting insn/memory ref. */
+ } _sigfault;
+
+ /* SIGPOLL */
+ struct {
+ int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
+ int _fd;
+ } _sigpoll;
+
+ struct {
+ unsigned int _call_addr; /* calling insn */
+ int _syscall; /* triggering system call number */
+ unsigned int _arch; /* AUDIT_ARCH_* of syscall */
+ } _sigsys;
+ } _sifields;
+} compat_siginfo_t;
+
#define COMPAT_OFF_T_MAX 0x7fffffff
#define COMPAT_LOFF_T_MAX 0x7fffffffffffffffL
@@ -209,7 +282,6 @@ typedef struct user_regs_struct32 compat_elf_gregset_t;
* as pointers because the syscall entry code will have
* appropriately converted them already.
*/
-typedef u32 compat_uptr_t;
static inline void __user *compat_ptr(compat_uptr_t uptr)
{
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 6b7ee5ff682..8c297aa53ee 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -4,7 +4,9 @@
#ifndef _ASM_X86_CPUFEATURE_H
#define _ASM_X86_CPUFEATURE_H
+#ifndef _ASM_X86_REQUIRED_FEATURES_H
#include <asm/required-features.h>
+#endif
#define NCAPINTS 10 /* N 32-bit words worth of info */
@@ -97,6 +99,7 @@
#define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */
#define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */
#define X86_FEATURE_APERFMPERF (3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU (3*32+29) /* "eagerfpu" Non lazy FPU restore */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
@@ -209,6 +212,7 @@
#define X86_FEATURE_RTM (9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_RDSEED (9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX (9*32+19) /* The ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP (9*32+20) /* Supervisor Mode Access Prevention */
#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
@@ -299,12 +303,14 @@ extern const char * const x86_power_flags[32];
#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2)
#define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC)
#define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT)
#define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE)
#define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR)
#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ)
#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8)
#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16)
+#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU)
#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
# define cpu_has_invlpg 1
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 75f4c6d6a33..831dbb9c6c0 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -12,6 +12,7 @@
#include <linux/kernel_stat.h>
#include <linux/regset.h>
+#include <linux/compat.h>
#include <linux/slab.h>
#include <asm/asm.h>
#include <asm/cpufeature.h>
@@ -20,43 +21,76 @@
#include <asm/user.h>
#include <asm/uaccess.h>
#include <asm/xsave.h>
+#include <asm/smap.h>
-extern unsigned int sig_xstate_size;
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+ compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+ compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct user_i387_struct
+# define user32_fxsr_struct user_fxsr_struct
+# define ia32_setup_frame __setup_frame
+# define ia32_setup_rt_frame __setup_rt_frame
+#endif
+
+extern unsigned int mxcsr_feature_mask;
extern void fpu_init(void);
+extern void eager_fpu_init(void);
DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+ struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env);
+
extern user_regset_active_fn fpregs_active, xfpregs_active;
extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
xstateregs_get;
extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
xstateregs_set;
-
/*
* xstateregs_active == fpregs_active. Please refer to the comment
* at the definition of fpregs_active.
*/
#define xstateregs_active fpregs_active
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
#ifdef CONFIG_MATH_EMULATION
+# define HAVE_HWFP (boot_cpu_data.hard_math)
extern void finit_soft_fpu(struct i387_soft_struct *soft);
#else
+# define HAVE_HWFP 1
static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
#endif
+static inline int is_ia32_compat_frame(void)
+{
+ return config_enabled(CONFIG_IA32_EMULATION) &&
+ test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+ return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+ return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
#define X87_FSW_ES (1 << 7) /* Exception Summary */
+static __always_inline __pure bool use_eager_fpu(void)
+{
+ return static_cpu_has(X86_FEATURE_EAGER_FPU);
+}
+
static __always_inline __pure bool use_xsaveopt(void)
{
return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -72,6 +106,13 @@ static __always_inline __pure bool use_fxsr(void)
return static_cpu_has(X86_FEATURE_FXSR);
}
+static inline void fx_finit(struct i387_fxsave_struct *fx)
+{
+ memset(fx, 0, xstate_size);
+ fx->cwd = 0x37f;
+ fx->mxcsr = MXCSR_DEFAULT;
+}
+
extern void __sanitize_i387_state(struct task_struct *);
static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -81,131 +122,121 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
__sanitize_i387_state(tsk);
}
-#ifdef CONFIG_X86_64
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
- int err;
-
- /* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
- asm volatile("1: fxrstorq %[fx]\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : [fx] "m" (*fx), "0" (0));
-#else
- asm volatile("1: rex64/fxrstor (%[fx])\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err)
- : [fx] "R" (fx), "m" (*fx), "0" (0));
-#endif
- return err;
+#define user_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile(ASM_STAC "\n" \
+ "1:" #insn "\n\t" \
+ "2: " ASM_CLAC "\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+#define check_insn(insn, output, input...) \
+({ \
+ int err; \
+ asm volatile("1:" #insn "\n\t" \
+ "2:\n" \
+ ".section .fixup,\"ax\"\n" \
+ "3: movl $-1,%[err]\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE(1b, 3b) \
+ : [err] "=r" (err), output \
+ : "0"(0), input); \
+ err; \
+})
+
+static inline int fsave_user(struct i387_fsave_struct __user *fx)
+{
+ return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
}
static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
{
- int err;
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
- /*
- * Clear the bytes not touched by the fxsave and reserved
- * for the SW usage.
- */
- err = __clear_user(&fx->sw_reserved,
- sizeof(struct _fpx_sw_bytes));
- if (unlikely(err))
- return -EFAULT;
-
- /* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
- asm volatile("1: fxsaveq %[fx]\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), [fx] "=m" (*fx)
- : "0" (0));
-#else
- asm volatile("1: rex64/fxsave (%[fx])\n\t"
- "2:\n"
- ".section .fixup,\"ax\"\n"
- "3: movl $-1,%[err]\n"
- " jmp 2b\n"
- ".previous\n"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), "=m" (*fx)
- : [fx] "R" (fx), "0" (0));
-#endif
- if (unlikely(err) &&
- __clear_user(fx, sizeof(struct i387_fxsave_struct)))
- err = -EFAULT;
- /* No need to clear here because the caller clears USED_MATH */
- return err;
+ /* See comment in fpu_fxsave() below. */
+ return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
}
-static inline void fpu_fxsave(struct fpu *fpu)
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
{
- /* Using "rex64; fxsave %0" is broken because, if the memory operand
- uses any extended registers for addressing, a second REX prefix
- will be generated (to the assembler, rex64 followed by semicolon
- is a separate instruction), and hence the 64-bitness is lost. */
+ if (config_enabled(CONFIG_X86_32))
+ return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-#ifdef CONFIG_AS_FXSAVEQ
- /* Using "fxsaveq %0" would be the ideal choice, but is only supported
- starting with gas 2.16. */
- __asm__ __volatile__("fxsaveq %0"
- : "=m" (fpu->state->fxsave));
-#else
- /* Using, as a workaround, the properly prefixed form below isn't
- accepted by any binutils version so far released, complaining that
- the same type of prefix is used twice if an extended register is
- needed for addressing (fix submitted to mainline 2005-11-21).
- asm volatile("rex64/fxsave %0"
- : "=m" (fpu->state->fxsave));
- This, however, we can work around by forcing the compiler to select
- an addressing mode that doesn't require extended registers. */
- asm volatile("rex64/fxsave (%[fx])"
- : "=m" (fpu->state->fxsave)
- : [fx] "R" (&fpu->state->fxsave));
-#endif
+ /* See comment in fpu_fxsave() below. */
+ return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
}
-#else /* CONFIG_X86_32 */
+static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
+{
+ if (config_enabled(CONFIG_X86_32))
+ return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
-/* perform fxrstor iff the processor has extended states, otherwise frstor */
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+ /* See comment in fpu_fxsave() below. */
+ return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+ "m" (*fx));
+}
+
+static inline int frstor_checking(struct i387_fsave_struct *fx)
{
- /*
- * The "nop" is needed to make the instructions the same
- * length.
- */
- alternative_input(
- "nop ; frstor %1",
- "fxrstor %1",
- X86_FEATURE_FXSR,
- "m" (*fx));
+ return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+}
- return 0;
+static inline int frstor_user(struct i387_fsave_struct __user *fx)
+{
+ return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline void fpu_fxsave(struct fpu *fpu)
{
- asm volatile("fxsave %[fx]"
- : [fx] "=m" (fpu->state->fxsave));
+ if (config_enabled(CONFIG_X86_32))
+ asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
+ else if (config_enabled(CONFIG_AS_FXSAVEQ))
+ asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
+ else {
+ /* Using "rex64; fxsave %0" is broken because, if the memory
+ * operand uses any extended registers for addressing, a second
+ * REX prefix will be generated (to the assembler, rex64
+ * followed by semicolon is a separate instruction), and hence
+ * the 64-bitness is lost.
+ *
+ * Using "fxsaveq %0" would be the ideal choice, but is only
+ * supported starting with gas 2.16.
+ *
+ * Using, as a workaround, the properly prefixed form below
+ * isn't accepted by any binutils version so far released,
+ * complaining that the same type of prefix is used twice if
+ * an extended register is needed for addressing (fix submitted
+ * to mainline 2005-11-21).
+ *
+ * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
+ *
+ * This, however, we can work around by forcing the compiler to
+ * select an addressing mode that doesn't require extended
+ * registers.
+ */
+ asm volatile( "rex64/fxsave (%[fx])"
+ : "=m" (fpu->state->fxsave)
+ : [fx] "R" (&fpu->state->fxsave));
+ }
}
-#endif /* CONFIG_X86_64 */
-
/*
* These must be called with preempt disabled. Returns
* 'true' if the FPU state is still intact.
@@ -248,17 +279,14 @@ static inline int __save_init_fpu(struct task_struct *tsk)
return fpu_save_init(&tsk->thread.fpu);
}
-static inline int fpu_fxrstor_checking(struct fpu *fpu)
-{
- return fxrstor_checking(&fpu->state->fxsave);
-}
-
static inline int fpu_restore_checking(struct fpu *fpu)
{
if (use_xsave())
- return fpu_xrstor_checking(fpu);
+ return fpu_xrstor_checking(&fpu->state->xsave);
+ else if (use_fxsr())
+ return fxrstor_checking(&fpu->state->fxsave);
else
- return fpu_fxrstor_checking(fpu);
+ return frstor_checking(&fpu->state->fsave);
}
static inline int restore_fpu_checking(struct task_struct *tsk)
@@ -310,15 +338,52 @@ static inline void __thread_set_has_fpu(struct task_struct *tsk)
static inline void __thread_fpu_end(struct task_struct *tsk)
{
__thread_clear_has_fpu(tsk);
- stts();
+ if (!use_eager_fpu())
+ stts();
}
static inline void __thread_fpu_begin(struct task_struct *tsk)
{
- clts();
+ if (!use_eager_fpu())
+ clts();
__thread_set_has_fpu(tsk);
}
+static inline void __drop_fpu(struct task_struct *tsk)
+{
+ if (__thread_has_fpu(tsk)) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ __thread_fpu_end(tsk);
+ }
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+ /*
+ * Forget coprocessor state..
+ */
+ preempt_disable();
+ tsk->fpu_counter = 0;
+ __drop_fpu(tsk);
+ clear_used_math();
+ preempt_enable();
+}
+
+static inline void drop_init_fpu(struct task_struct *tsk)
+{
+ if (!use_eager_fpu())
+ drop_fpu(tsk);
+ else {
+ if (use_xsave())
+ xrstor_state(init_xstate_buf, -1);
+ else
+ fxrstor_checking(&init_xstate_buf->i387);
+ }
+}
+
/*
* FPU state switching for scheduling.
*
@@ -352,7 +417,12 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
{
fpu_switch_t fpu;
- fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+ /*
+ * If the task has used the math, pre-load the FPU on xsave processors
+ * or if the past 5 consecutive context-switches used math.
+ */
+ fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
+ new->fpu_counter > 5);
if (__thread_has_fpu(old)) {
if (!__save_init_fpu(old))
cpu = ~0;
@@ -364,14 +434,14 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
new->fpu_counter++;
__thread_set_has_fpu(new);
prefetch(new->thread.fpu.state);
- } else
+ } else if (!use_eager_fpu())
stts();
} else {
old->fpu_counter = 0;
old->thread.fpu.last_cpu = ~0;
if (fpu.preload) {
new->fpu_counter++;
- if (fpu_lazy_restore(new, cpu))
+ if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
fpu.preload = 0;
else
prefetch(new->thread.fpu.state);
@@ -391,44 +461,40 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
{
if (fpu.preload) {
if (unlikely(restore_fpu_checking(new)))
- __thread_fpu_end(new);
+ drop_init_fpu(new);
}
}
/*
* Signal frame handlers...
*/
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
+extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
-static inline void __clear_fpu(struct task_struct *tsk)
+static inline int xstate_sigframe_size(void)
{
- if (__thread_has_fpu(tsk)) {
- /* Ignore delayed exceptions from user space */
- asm volatile("1: fwait\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b));
- __thread_fpu_end(tsk);
+ return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
+{
+ void __user *buf_fx = buf;
+ int size = xstate_sigframe_size();
+
+ if (ia32_frame && use_fxsr()) {
+ buf_fx = buf + sizeof(struct i387_fsave_struct);
+ size += sizeof(struct i387_fsave_struct);
}
+
+ return __restore_xstate_sig(buf, buf_fx, size);
}
/*
- * The actual user_fpu_begin/end() functions
- * need to be preemption-safe.
+ * Need to be preemption-safe.
*
- * NOTE! user_fpu_end() must be used only after you
- * have saved the FP state, and user_fpu_begin() must
- * be used only immediately before restoring it.
- * These functions do not do any save/restore on
- * their own.
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * it. This function does not do any save/restore on their own.
*/
-static inline void user_fpu_end(void)
-{
- preempt_disable();
- __thread_fpu_end(current);
- preempt_enable();
-}
-
static inline void user_fpu_begin(void)
{
preempt_disable();
@@ -437,25 +503,32 @@ static inline void user_fpu_begin(void)
preempt_enable();
}
+static inline void __save_fpu(struct task_struct *tsk)
+{
+ if (use_xsave())
+ xsave_state(&tsk->thread.fpu.state->xsave, -1);
+ else
+ fpu_fxsave(&tsk->thread.fpu);
+}
+
/*
* These disable preemption on their own and are safe
*/
static inline void save_init_fpu(struct task_struct *tsk)
{
WARN_ON_ONCE(!__thread_has_fpu(tsk));
+
+ if (use_eager_fpu()) {
+ __save_fpu(tsk);
+ return;
+ }
+
preempt_disable();
__save_init_fpu(tsk);
__thread_fpu_end(tsk);
preempt_enable();
}
-static inline void clear_fpu(struct task_struct *tsk)
-{
- preempt_disable();
- __clear_fpu(tsk);
- preempt_enable();
-}
-
/*
* i387 state interaction
*/
@@ -510,11 +583,34 @@ static inline void fpu_free(struct fpu *fpu)
}
}
-static inline void fpu_copy(struct fpu *dst, struct fpu *src)
+static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
{
- memcpy(dst->state, src->state, xstate_size);
+ if (use_eager_fpu()) {
+ memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
+ __save_fpu(dst);
+ } else {
+ struct fpu *dfpu = &dst->thread.fpu;
+ struct fpu *sfpu = &src->thread.fpu;
+
+ unlazy_fpu(src);
+ memcpy(dfpu->state, sfpu->state, xstate_size);
+ }
}
-extern void fpu_finit(struct fpu *fpu);
+static inline unsigned long
+alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
+ unsigned long *size)
+{
+ unsigned long frame_size = xstate_sigframe_size();
+
+ *buf_fx = sp = round_down(sp - frame_size, 64);
+ if (ia32_frame && use_fxsr()) {
+ frame_size += sizeof(struct i387_fsave_struct);
+ sp -= sizeof(struct i387_fsave_struct);
+ }
+
+ *size = frame_size;
+ return sp;
+}
#endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b0767bc0874..9a25b522d37 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -3,38 +3,54 @@
#ifdef __ASSEMBLY__
- .macro MCOUNT_SAVE_FRAME
- /* taken from glibc */
- subq $0x38, %rsp
- movq %rax, (%rsp)
- movq %rcx, 8(%rsp)
- movq %rdx, 16(%rsp)
- movq %rsi, 24(%rsp)
- movq %rdi, 32(%rsp)
- movq %r8, 40(%rsp)
- movq %r9, 48(%rsp)
+ /* skip is set if the stack was already partially adjusted */
+ .macro MCOUNT_SAVE_FRAME skip=0
+ /*
+ * We add enough stack to save all regs.
+ */
+ subq $(SS+8-\skip), %rsp
+ movq %rax, RAX(%rsp)
+ movq %rcx, RCX(%rsp)
+ movq %rdx, RDX(%rsp)
+ movq %rsi, RSI(%rsp)
+ movq %rdi, RDI(%rsp)
+ movq %r8, R8(%rsp)
+ movq %r9, R9(%rsp)
+ /* Move RIP to its proper location */
+ movq SS+8(%rsp), %rdx
+ movq %rdx, RIP(%rsp)
.endm
- .macro MCOUNT_RESTORE_FRAME
- movq 48(%rsp), %r9
- movq 40(%rsp), %r8
- movq 32(%rsp), %rdi
- movq 24(%rsp), %rsi
- movq 16(%rsp), %rdx
- movq 8(%rsp), %rcx
- movq (%rsp), %rax
- addq $0x38, %rsp
+ .macro MCOUNT_RESTORE_FRAME skip=0
+ movq R9(%rsp), %r9
+ movq R8(%rsp), %r8
+ movq RDI(%rsp), %rdi
+ movq RSI(%rsp), %rsi
+ movq RDX(%rsp), %rdx
+ movq RCX(%rsp), %rcx
+ movq RAX(%rsp), %rax
+ addq $(SS+8-\skip), %rsp
.endm
#endif
#ifdef CONFIG_FUNCTION_TRACER
-#define MCOUNT_ADDR ((long)(mcount))
+#ifdef CC_USING_FENTRY
+# define MCOUNT_ADDR ((long)(__fentry__))
+#else
+# define MCOUNT_ADDR ((long)(mcount))
+#endif
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define ARCH_SUPPORTS_FTRACE_OPS 1
+#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#endif
+
#ifndef __ASSEMBLY__
extern void mcount(void);
extern atomic_t modifying_ftrace_code;
+extern void __fentry__(void);
static inline unsigned long ftrace_call_adjust(unsigned long addr)
{
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index 71ecbcba1a4..f373046e63e 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,10 +9,13 @@
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/processor.h>
+#include <asm/smap.h>
#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \
- asm volatile("1:\t" insn "\n" \
- "2:\t.section .fixup,\"ax\"\n" \
+ asm volatile("\t" ASM_STAC "\n" \
+ "1:\t" insn "\n" \
+ "2:\t" ASM_CLAC "\n" \
+ "\t.section .fixup,\"ax\"\n" \
"3:\tmov\t%3, %1\n" \
"\tjmp\t2b\n" \
"\t.previous\n" \
@@ -21,12 +24,14 @@
: "i" (-EFAULT), "0" (oparg), "1" (0))
#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \
- asm volatile("1:\tmovl %2, %0\n" \
+ asm volatile("\t" ASM_STAC "\n" \
+ "1:\tmovl %2, %0\n" \
"\tmovl\t%0, %3\n" \
"\t" insn "\n" \
"2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \
"\tjnz\t1b\n" \
- "3:\t.section .fixup,\"ax\"\n" \
+ "3:\t" ASM_CLAC "\n" \
+ "\t.section .fixup,\"ax\"\n" \
"4:\tmov\t%5, %1\n" \
"\tjmp\t3b\n" \
"\t.previous\n" \
@@ -122,8 +127,10 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
- asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
- "2:\t.section .fixup, \"ax\"\n"
+ asm volatile("\t" ASM_STAC "\n"
+ "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+ "2:\t" ASM_CLAC "\n"
+ "\t.section .fixup, \"ax\"\n"
"3:\tmov %3, %0\n"
"\tjmp 2b\n"
"\t.previous\n"
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index d3895dbf4dd..81f04cee5f7 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -18,6 +18,10 @@ typedef struct {
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
+ /*
+ * irq_tlb_count is double-counted in irq_call_count, so it must be
+ * subtracted from irq_call_count when displaying irq_call_count
+ */
unsigned int irq_tlb_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 2c392d663dc..434e2106cc8 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -35,8 +35,6 @@
#define HPET_ID_NUMBER_SHIFT 8
#define HPET_ID_VENDOR_SHIFT 16
-#define HPET_ID_VENDOR_8086 0x8086
-
#define HPET_CFG_ENABLE 0x001
#define HPET_CFG_LEGACY 0x002
#define HPET_LEGACY_8254 2
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 257d9cca214..ed8089d6909 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -19,12 +19,37 @@ struct pt_regs;
struct user_i387_struct;
extern int init_fpu(struct task_struct *child);
+extern void fpu_finit(struct fpu *fpu);
extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
extern void math_state_restore(void);
extern bool irq_fpu_usable(void);
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+
+static inline void kernel_fpu_begin(void)
+{
+ WARN_ON_ONCE(!irq_fpu_usable());
+ preempt_disable();
+ __kernel_fpu_begin();
+}
+
+static inline void kernel_fpu_end(void)
+{
+ __kernel_fpu_end();
+ preempt_enable();
+}
/*
* Some instructions like VIA's padlock instructions generate a spurious
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index b04cbdb138c..e6232773ce4 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -86,73 +86,6 @@ struct stat64 {
unsigned long long st_ino;
} __attribute__((packed));
-typedef struct compat_siginfo {
- int si_signo;
- int si_errno;
- int si_code;
-
- union {
- int _pad[((128 / sizeof(int)) - 3)];
-
- /* kill() */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- } _kill;
-
- /* POSIX.1b timers */
- struct {
- compat_timer_t _tid; /* timer id */
- int _overrun; /* overrun count */
- compat_sigval_t _sigval; /* same as below */
- int _sys_private; /* not to be passed to user */
- int _overrun_incr; /* amount to add to overrun */
- } _timer;
-
- /* POSIX.1b signals */
- struct {
- unsigned int _pid; /* sender's pid */
- unsigned int _uid; /* sender's uid */
- compat_sigval_t _sigval;
- } _rt;
-
- /* SIGCHLD */
- struct {
- unsigned int _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_clock_t _utime;
- compat_clock_t _stime;
- } _sigchld;
-
- /* SIGCHLD (x32 version) */
- struct {
- unsigned int _pid; /* which child */
- unsigned int _uid; /* sender's uid */
- int _status; /* exit code */
- compat_s64 _utime;
- compat_s64 _stime;
- } _sigchld_x32;
-
- /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
- struct {
- unsigned int _addr; /* faulting insn/memory ref. */
- } _sigfault;
-
- /* SIGPOLL */
- struct {
- int _band; /* POLL_IN, POLL_OUT, POLL_MSG */
- int _fd;
- } _sigpoll;
-
- struct {
- unsigned int _call_addr; /* calling insn */
- int _syscall; /* triggering system call number */
- unsigned int _arch; /* AUDIT_ARCH_* of syscall */
- } _sigsys;
- } _sifields;
-} compat_siginfo_t;
-
#define IA32_STACK_TOP IA32_PAGE_OFFSET
#ifdef __KERNEL__
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
index f229b13a5f3..f42a04735a0 100644
--- a/arch/x86/include/asm/iommu_table.h
+++ b/arch/x86/include/asm/iommu_table.h
@@ -48,7 +48,7 @@ struct iommu_table_entry {
#define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
- static const struct iommu_table_entry const \
+ static const struct iommu_table_entry \
__iommu_entry_##_detect __used \
__attribute__ ((unused, __section__(".iommu_table"), \
aligned((sizeof(void *))))) \
@@ -63,10 +63,10 @@ struct iommu_table_entry {
* to stop detecting the other IOMMUs after yours has been detected.
*/
#define IOMMU_INIT_POST(_detect) \
- __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, 0, 0, 0)
+ __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, NULL, NULL, 0)
#define IOMMU_INIT_POST_FINISH(detect) \
- __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, 0, 0, 1)
+ __IOMMU_INIT(_detect, pci_swiotlb_detect_4gb, NULL, NULL, 1)
/*
* A more sophisticated version of IOMMU_INIT. This variant requires:
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 54788253915..d3ddd17405d 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -27,6 +27,7 @@
#include <asm/insn.h>
#define __ARCH_WANT_KPROBES_INSN_SLOT
+#define ARCH_SUPPORTS_KPROBES_ON_FTRACE
struct pt_regs;
struct kprobe;
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 246617efd67..a65ec29e6ff 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -9,6 +9,22 @@
#include <linux/types.h>
#include <linux/ioctl.h>
+#define DE_VECTOR 0
+#define DB_VECTOR 1
+#define BP_VECTOR 3
+#define OF_VECTOR 4
+#define BR_VECTOR 5
+#define UD_VECTOR 6
+#define NM_VECTOR 7
+#define DF_VECTOR 8
+#define TS_VECTOR 10
+#define NP_VECTOR 11
+#define SS_VECTOR 12
+#define GP_VECTOR 13
+#define PF_VECTOR 14
+#define MF_VECTOR 16
+#define MC_VECTOR 18
+
/* Select x86 specific features in <linux/kvm.h> */
#define __KVM_HAVE_PIT
#define __KVM_HAVE_IOAPIC
@@ -25,6 +41,7 @@
#define __KVM_HAVE_DEBUGREGS
#define __KVM_HAVE_XSAVE
#define __KVM_HAVE_XCRS
+#define __KVM_HAVE_READONLY_MEM
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index c764f43b71c..15f960c06ff 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -86,6 +86,19 @@ struct x86_instruction_info {
struct x86_emulate_ops {
/*
+ * read_gpr: read a general purpose register (rax - r15)
+ *
+ * @reg: gpr number.
+ */
+ ulong (*read_gpr)(struct x86_emulate_ctxt *ctxt, unsigned reg);
+ /*
+ * write_gpr: write a general purpose register (rax - r15)
+ *
+ * @reg: gpr number.
+ * @val: value to write.
+ */
+ void (*write_gpr)(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val);
+ /*
* read_std: Read bytes of standard (non-emulated/special) memory.
* Used for descriptor reading.
* @addr: [IN ] Linear address from which to read.
@@ -200,8 +213,9 @@ typedef u32 __attribute__((vector_size(16))) sse128_t;
/* Type, address-of, and value of an instruction's operand. */
struct operand {
- enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
+ enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
unsigned int bytes;
+ unsigned int count;
union {
unsigned long orig_val;
u64 orig_val64;
@@ -221,6 +235,7 @@ struct operand {
char valptr[sizeof(unsigned long) + 2];
sse128_t vec_val;
u64 mm_val;
+ void *data;
};
};
@@ -236,14 +251,23 @@ struct read_cache {
unsigned long end;
};
+/* Execution mode, passed to the emulator. */
+enum x86emul_mode {
+ X86EMUL_MODE_REAL, /* Real mode. */
+ X86EMUL_MODE_VM86, /* Virtual 8086 mode. */
+ X86EMUL_MODE_PROT16, /* 16-bit protected mode. */
+ X86EMUL_MODE_PROT32, /* 32-bit protected mode. */
+ X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */
+};
+
struct x86_emulate_ctxt {
- struct x86_emulate_ops *ops;
+ const struct x86_emulate_ops *ops;
/* Register state before/after emulation. */
unsigned long eflags;
unsigned long eip; /* eip before instruction emulation */
/* Emulated execution mode, represented by an X86EMUL_MODE value. */
- int mode;
+ enum x86emul_mode mode;
/* interruptibility state, as a result of execution of STI or MOV SS */
int interruptibility;
@@ -281,8 +305,10 @@ struct x86_emulate_ctxt {
bool rip_relative;
unsigned long _eip;
struct operand memop;
+ u32 regs_valid; /* bitmaps of registers in _regs[] that can be read */
+ u32 regs_dirty; /* bitmaps of registers in _regs[] that have been written */
/* Fields above regs are cleared together. */
- unsigned long regs[NR_VCPU_REGS];
+ unsigned long _regs[NR_VCPU_REGS];
struct operand *memopp;
struct fetch_cache fetch;
struct read_cache io_read;
@@ -293,17 +319,6 @@ struct x86_emulate_ctxt {
#define REPE_PREFIX 0xf3
#define REPNE_PREFIX 0xf2
-/* Execution mode, passed to the emulator. */
-#define X86EMUL_MODE_REAL 0 /* Real mode. */
-#define X86EMUL_MODE_VM86 1 /* Virtual 8086 mode. */
-#define X86EMUL_MODE_PROT16 2 /* 16-bit protected mode. */
-#define X86EMUL_MODE_PROT32 4 /* 32-bit protected mode. */
-#define X86EMUL_MODE_PROT64 8 /* 64-bit (long) mode. */
-
-/* any protected mode */
-#define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
- X86EMUL_MODE_PROT64)
-
/* CPUID vendors */
#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
@@ -394,4 +409,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
u16 tss_selector, int idt_index, int reason,
bool has_error_code, u32 error_code);
int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
+void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
+void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
+
#endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 09155d64cf7..b2e11f45243 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -75,22 +75,6 @@
#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1))
#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
-#define DE_VECTOR 0
-#define DB_VECTOR 1
-#define BP_VECTOR 3
-#define OF_VECTOR 4
-#define BR_VECTOR 5
-#define UD_VECTOR 6
-#define NM_VECTOR 7
-#define DF_VECTOR 8
-#define TS_VECTOR 10
-#define NP_VECTOR 11
-#define SS_VECTOR 12
-#define GP_VECTOR 13
-#define PF_VECTOR 14
-#define MF_VECTOR 16
-#define MC_VECTOR 18
-
#define SELECTOR_TI_MASK (1 << 2)
#define SELECTOR_RPL_MASK 0x03
@@ -287,10 +271,24 @@ struct kvm_mmu {
union kvm_mmu_page_role base_role;
bool direct_map;
+ /*
+ * Bitmap; bit set = permission fault
+ * Byte index: page fault error code [4:1]
+ * Bit index: pte permissions in ACC_* format
+ */
+ u8 permissions[16];
+
u64 *pae_root;
u64 *lm_root;
u64 rsvd_bits_mask[2][4];
+ /*
+ * Bitmap: bit set = last pte in walk
+ * index[0:1]: level (zero-based)
+ * index[2]: pte.ps
+ */
+ u8 last_pte_bitmap;
+
bool nx;
u64 pdptrs[4]; /* pae */
@@ -414,12 +412,15 @@ struct kvm_vcpu_arch {
struct x86_emulate_ctxt emulate_ctxt;
bool emulate_regs_need_sync_to_vcpu;
bool emulate_regs_need_sync_from_vcpu;
+ int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
gpa_t time;
struct pvclock_vcpu_time_info hv_clock;
unsigned int hw_tsc_khz;
unsigned int time_offset;
struct page *time_page;
+ /* set guest stopped flag in pvclock flags field */
+ bool pvclock_set_guest_stopped_request;
struct {
u64 msr_val;
@@ -454,6 +455,7 @@ struct kvm_vcpu_arch {
unsigned long dr6;
unsigned long dr7;
unsigned long eff_db[KVM_NR_DB_REGS];
+ unsigned long guest_debug_dr7;
u64 mcg_cap;
u64 mcg_status;
@@ -500,14 +502,24 @@ struct kvm_vcpu_arch {
};
struct kvm_lpage_info {
- unsigned long rmap_pde;
int write_count;
};
struct kvm_arch_memory_slot {
+ unsigned long *rmap[KVM_NR_PAGE_SIZES];
struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
};
+struct kvm_apic_map {
+ struct rcu_head rcu;
+ u8 ldr_bits;
+ /* fields bellow are used to decode ldr values in different modes */
+ u32 cid_shift, cid_mask, lid_mask;
+ struct kvm_lapic *phys_map[256];
+ /* first index is cluster id second is cpu id in a cluster */
+ struct kvm_lapic *logical_map[16][16];
+};
+
struct kvm_arch {
unsigned int n_used_mmu_pages;
unsigned int n_requested_mmu_pages;
@@ -525,6 +537,8 @@ struct kvm_arch {
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
int vapics_in_nmi_mode;
+ struct mutex apic_map_lock;
+ struct kvm_apic_map *apic_map;
unsigned int tss_addr;
struct page *apic_access_page;
@@ -618,8 +632,7 @@ struct kvm_x86_ops {
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
- void (*set_guest_debug)(struct kvm_vcpu *vcpu,
- struct kvm_guest_debug *dbg);
+ void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -957,6 +970,7 @@ extern bool kvm_rebooting;
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_age_hva(struct kvm *kvm, unsigned long hva);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 2f7712e08b1..eb3e9d85e1f 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -102,21 +102,21 @@ struct kvm_vcpu_pv_apf_data {
extern void kvmclock_init(void);
extern int kvm_register_clock(char *txt);
-#ifdef CONFIG_KVM_CLOCK
+#ifdef CONFIG_KVM_GUEST
bool kvm_check_and_clear_guest_paused(void);
#else
static inline bool kvm_check_and_clear_guest_paused(void)
{
return false;
}
-#endif /* CONFIG_KVMCLOCK */
+#endif /* CONFIG_KVM_GUEST */
/* This instruction is vmcall. On non-VT architectures, it will generate a
* trap that we will then rewrite to the appropriate instruction.
*/
#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun
+/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
* instruction. The hypervisor may replace it with something else but only the
* instructions are guaranteed to be supported.
*
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index a3ac52b29cb..54d73b1f00a 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -116,19 +116,9 @@ struct mce_log {
/* Software defined banks */
#define MCE_EXTENDED_BANK 128
#define MCE_THERMAL_BANK MCE_EXTENDED_BANK + 0
-
-#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1) /* MCE_AMD */
-#define K8_MCE_THRESHOLD_BANK_0 (MCE_THRESHOLD_BASE + 0 * 9)
-#define K8_MCE_THRESHOLD_BANK_1 (MCE_THRESHOLD_BASE + 1 * 9)
-#define K8_MCE_THRESHOLD_BANK_2 (MCE_THRESHOLD_BASE + 2 * 9)
-#define K8_MCE_THRESHOLD_BANK_3 (MCE_THRESHOLD_BASE + 3 * 9)
-#define K8_MCE_THRESHOLD_BANK_4 (MCE_THRESHOLD_BASE + 4 * 9)
-#define K8_MCE_THRESHOLD_BANK_5 (MCE_THRESHOLD_BASE + 5 * 9)
-#define K8_MCE_THRESHOLD_DRAM_ECC (MCE_THRESHOLD_BANK_4 + 0)
-
+#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1)
#ifdef __KERNEL__
-
extern void mce_register_decode_chain(struct notifier_block *nb);
extern void mce_unregister_decode_chain(struct notifier_block *nb);
@@ -171,6 +161,7 @@ DECLARE_PER_CPU(struct device *, mce_device);
#ifdef CONFIG_X86_MCE_INTEL
extern int mce_cmci_disabled;
extern int mce_ignore_ce;
+extern int mce_bios_cmci_threshold;
void mce_intel_feature_init(struct cpuinfo_x86 *c);
void cmci_clear(void);
void cmci_reenable(void);
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 4ebe157bf73..43d921b4752 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -15,8 +15,8 @@ struct microcode_ops {
enum ucode_state (*request_microcode_user) (int cpu,
const void __user *buf, size_t size);
- enum ucode_state (*request_microcode_fw) (int cpu,
- struct device *device);
+ enum ucode_state (*request_microcode_fw) (int cpu, struct device *,
+ bool refresh_fw);
void (*microcode_fini_cpu) (int cpu);
@@ -49,12 +49,6 @@ static inline struct microcode_ops * __init init_intel_microcode(void)
#ifdef CONFIG_MICROCODE_AMD
extern struct microcode_ops * __init init_amd_microcode(void);
extern void __exit exit_amd_microcode(void);
-
-static inline void get_ucode_data(void *to, const u8 *from, size_t n)
-{
- memcpy(to, from, n);
-}
-
#else
static inline struct microcode_ops * __init init_amd_microcode(void)
{
diff --git a/arch/x86/include/asm/mmzone.h b/arch/x86/include/asm/mmzone.h
index 64217ea16a3..d497bc425ca 100644
--- a/arch/x86/include/asm/mmzone.h
+++ b/arch/x86/include/asm/mmzone.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "mmzone_32.h"
+# include <asm/mmzone_32.h>
#else
-# include "mmzone_64.h"
+# include <asm/mmzone_64.h>
#endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 957ec87385a..fbee9714d9a 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -248,6 +248,9 @@
#define MSR_IA32_PERF_STATUS 0x00000198
#define MSR_IA32_PERF_CTL 0x00000199
+#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064
+#define MSR_AMD_PERF_STATUS 0xc0010063
+#define MSR_AMD_PERF_CTL 0xc0010062
#define MSR_IA32_MPERF 0x000000e7
#define MSR_IA32_APERF 0x000000e8
diff --git a/arch/x86/include/asm/mutex.h b/arch/x86/include/asm/mutex.h
index a731b9c573a..7d3a4827539 100644
--- a/arch/x86/include/asm/mutex.h
+++ b/arch/x86/include/asm/mutex.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "mutex_32.h"
+# include <asm/mutex_32.h>
#else
-# include "mutex_64.h"
+# include <asm/mutex_64.h>
#endif
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index bfacd2ccf65..49119fcea2d 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -53,9 +53,9 @@ static inline int numa_cpu_node(int cpu)
#endif /* CONFIG_NUMA */
#ifdef CONFIG_X86_32
-# include "numa_32.h"
+# include <asm/numa_32.h>
#else
-# include "numa_64.h"
+# include <asm/numa_64.h>
#endif
#ifdef CONFIG_NUMA
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index df75d07571c..6e41b934392 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -141,7 +141,7 @@ void default_restore_msi_irqs(struct pci_dev *dev, int irq);
#endif /* __KERNEL__ */
#ifdef CONFIG_X86_64
-#include "pci_64.h"
+#include <asm/pci_64.h>
#endif
/* implement the pci_ DMA API in terms of the generic device dma_ one */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index cb4e43bce98..4fabcdf1cfa 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -262,4 +262,6 @@ static inline void perf_check_microcode(void) { }
static inline void amd_pmu_disable_virt(void) { }
#endif
+#define arch_perf_out_copy_user copy_from_user_nmi
+
#endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/arch/x86/include/asm/perf_regs.h b/arch/x86/include/asm/perf_regs.h
new file mode 100644
index 00000000000..3f2207bfd17
--- /dev/null
+++ b/arch/x86/include/asm/perf_regs.h
@@ -0,0 +1,33 @@
+#ifndef _ASM_X86_PERF_REGS_H
+#define _ASM_X86_PERF_REGS_H
+
+enum perf_event_x86_regs {
+ PERF_REG_X86_AX,
+ PERF_REG_X86_BX,
+ PERF_REG_X86_CX,
+ PERF_REG_X86_DX,
+ PERF_REG_X86_SI,
+ PERF_REG_X86_DI,
+ PERF_REG_X86_BP,
+ PERF_REG_X86_SP,
+ PERF_REG_X86_IP,
+ PERF_REG_X86_FLAGS,
+ PERF_REG_X86_CS,
+ PERF_REG_X86_SS,
+ PERF_REG_X86_DS,
+ PERF_REG_X86_ES,
+ PERF_REG_X86_FS,
+ PERF_REG_X86_GS,
+ PERF_REG_X86_R8,
+ PERF_REG_X86_R9,
+ PERF_REG_X86_R10,
+ PERF_REG_X86_R11,
+ PERF_REG_X86_R12,
+ PERF_REG_X86_R13,
+ PERF_REG_X86_R14,
+ PERF_REG_X86_R15,
+
+ PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
+ PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+};
+#endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 49afb3f41eb..fc994846529 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -384,9 +384,9 @@ pte_t *populate_extra_pte(unsigned long vaddr);
#endif /* __ASSEMBLY__ */
#ifdef CONFIG_X86_32
-# include "pgtable_32.h"
+# include <asm/pgtable_32.h>
#else
-# include "pgtable_64.h"
+# include <asm/pgtable_64.h>
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 013286a10c2..ec8a1fc9505 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -174,9 +174,9 @@
#endif
#ifdef CONFIG_X86_32
-# include "pgtable_32_types.h"
+# include <asm/pgtable_32_types.h>
#else
-# include "pgtable_64_types.h"
+# include <asm/pgtable_64_types.h>
#endif
#ifndef __ASSEMBLY__
@@ -303,11 +303,9 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte);
extern void native_pagetable_reserve(u64 start, u64 end);
#ifdef CONFIG_X86_32
-extern void native_pagetable_setup_start(pgd_t *base);
-extern void native_pagetable_setup_done(pgd_t *base);
+extern void native_pagetable_init(void);
#else
-#define native_pagetable_setup_start x86_init_pgd_noop
-#define native_pagetable_setup_done x86_init_pgd_noop
+#define native_pagetable_init paging_init
#endif
struct seq_file;
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index 7ef7c3020e5..bad3665c25f 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -1,15 +1,15 @@
#ifdef __KERNEL__
# ifdef CONFIG_X86_32
-# include "posix_types_32.h"
+# include <asm/posix_types_32.h>
# else
-# include "posix_types_64.h"
+# include <asm/posix_types_64.h>
# endif
#else
# ifdef __i386__
-# include "posix_types_32.h"
+# include <asm/posix_types_32.h>
# elif defined(__ILP32__)
-# include "posix_types_x32.h"
+# include <asm/posix_types_x32.h>
# else
-# include "posix_types_64.h"
+# include <asm/posix_types_64.h>
# endif
#endif
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index aea1d1d848c..680cf09ed10 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -65,6 +65,7 @@
#define X86_CR4_PCIDE 0x00020000 /* enable PCID support */
#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
#define X86_CR4_SMEP 0x00100000 /* enable SMEP support */
+#define X86_CR4_SMAP 0x00200000 /* enable SMAP support */
/*
* x86-64 Task Priority Register, CR8
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d048cad9bca..b98c0d958eb 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -423,7 +423,6 @@ DECLARE_INIT_PER_CPU(irq_stack_union);
DECLARE_PER_CPU(char *, irq_stack_ptr);
DECLARE_PER_CPU(unsigned int, irq_count);
-extern unsigned long kernel_eflags;
extern asmlinkage void ignore_sysret(void);
#else /* X86_64 */
#ifdef CONFIG_CC_STACKPROTECTOR
@@ -759,6 +758,8 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
}
+extern void set_task_blockstep(struct task_struct *task, bool on);
+
/*
* from system description table in BIOS. Mostly for MCA use, but
* others may find it useful:
diff --git a/arch/x86/include/asm/rcu.h b/arch/x86/include/asm/rcu.h
new file mode 100644
index 00000000000..d1ac07a2397
--- /dev/null
+++ b/arch/x86/include/asm/rcu.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_X86_RCU_H
+#define _ASM_X86_RCU_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/rcupdate.h>
+#include <asm/ptrace.h>
+
+static inline void exception_enter(struct pt_regs *regs)
+{
+ rcu_user_exit();
+}
+
+static inline void exception_exit(struct pt_regs *regs)
+{
+#ifdef CONFIG_RCU_USER_QS
+ if (user_mode(regs))
+ rcu_user_enter();
+#endif
+}
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_RCU_USER_QS
+# define SCHEDULE_USER call schedule_user
+#else
+# define SCHEDULE_USER call schedule
+#endif
+
+#endif /* !__ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h
index c62e58a5a90..0f3d7f09922 100644
--- a/arch/x86/include/asm/seccomp.h
+++ b/arch/x86/include/asm/seccomp.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "seccomp_32.h"
+# include <asm/seccomp_32.h>
#else
-# include "seccomp_64.h"
+# include <asm/seccomp_64.h>
#endif
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 598457cbd0f..323973f4abf 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -31,6 +31,10 @@ typedef struct {
unsigned long sig[_NSIG_WORDS];
} sigset_t;
+#ifndef CONFIG_COMPAT
+typedef sigset_t compat_sigset_t;
+#endif
+
#else
/* Here we must cater to libcs that poke about in kernel headers. */
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
new file mode 100644
index 00000000000..8d3120f4e27
--- /dev/null
+++ b/arch/x86/include/asm/smap.h
@@ -0,0 +1,91 @@
+/*
+ * Supervisor Mode Access Prevention support
+ *
+ * Copyright (C) 2012 Intel Corporation
+ * Author: H. Peter Anvin <hpa@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; version 2
+ * of the License.
+ */
+
+#ifndef _ASM_X86_SMAP_H
+#define _ASM_X86_SMAP_H
+
+#include <linux/stringify.h>
+#include <asm/nops.h>
+#include <asm/cpufeature.h>
+
+/* "Raw" instruction opcodes */
+#define __ASM_CLAC .byte 0x0f,0x01,0xca
+#define __ASM_STAC .byte 0x0f,0x01,0xcb
+
+#ifdef __ASSEMBLY__
+
+#include <asm/alternative-asm.h>
+
+#ifdef CONFIG_X86_SMAP
+
+#define ASM_CLAC \
+ 661: ASM_NOP3 ; \
+ .pushsection .altinstr_replacement, "ax" ; \
+ 662: __ASM_CLAC ; \
+ .popsection ; \
+ .pushsection .altinstructions, "a" ; \
+ altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ; \
+ .popsection
+
+#define ASM_STAC \
+ 661: ASM_NOP3 ; \
+ .pushsection .altinstr_replacement, "ax" ; \
+ 662: __ASM_STAC ; \
+ .popsection ; \
+ .pushsection .altinstructions, "a" ; \
+ altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ; \
+ .popsection
+
+#else /* CONFIG_X86_SMAP */
+
+#define ASM_CLAC
+#define ASM_STAC
+
+#endif /* CONFIG_X86_SMAP */
+
+#else /* __ASSEMBLY__ */
+
+#include <asm/alternative.h>
+
+#ifdef CONFIG_X86_SMAP
+
+static __always_inline void clac(void)
+{
+ /* Note: a barrier is implicit in alternative() */
+ alternative(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP);
+}
+
+static __always_inline void stac(void)
+{
+ /* Note: a barrier is implicit in alternative() */
+ alternative(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP);
+}
+
+/* These macros can be used in asm() statements */
+#define ASM_CLAC \
+ ALTERNATIVE(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP)
+#define ASM_STAC \
+ ALTERNATIVE(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP)
+
+#else /* CONFIG_X86_SMAP */
+
+static inline void clac(void) { }
+static inline void stac(void) { }
+
+#define ASM_CLAC
+#define ASM_STAC
+
+#endif /* CONFIG_X86_SMAP */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_SMAP_H */
diff --git a/arch/x86/include/asm/string.h b/arch/x86/include/asm/string.h
index 6dfd6d9373a..09224d7a586 100644
--- a/arch/x86/include/asm/string.h
+++ b/arch/x86/include/asm/string.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "string_32.h"
+# include <asm/string_32.h>
#else
-# include "string_64.h"
+# include <asm/string_64.h>
#endif
diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h
index 9bd521fe457..2fab6c2c357 100644
--- a/arch/x86/include/asm/suspend.h
+++ b/arch/x86/include/asm/suspend.h
@@ -1,5 +1,5 @@
#ifdef CONFIG_X86_32
-# include "suspend_32.h"
+# include <asm/suspend_32.h>
#else
-# include "suspend_64.h"
+# include <asm/suspend_64.h>
#endif
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index f2b83bc7d78..cdf5674dd23 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -1,6 +1,135 @@
#ifndef __SVM_H
#define __SVM_H
+#define SVM_EXIT_READ_CR0 0x000
+#define SVM_EXIT_READ_CR3 0x003
+#define SVM_EXIT_READ_CR4 0x004
+#define SVM_EXIT_READ_CR8 0x008
+#define SVM_EXIT_WRITE_CR0 0x010
+#define SVM_EXIT_WRITE_CR3 0x013
+#define SVM_EXIT_WRITE_CR4 0x014
+#define SVM_EXIT_WRITE_CR8 0x018
+#define SVM_EXIT_READ_DR0 0x020
+#define SVM_EXIT_READ_DR1 0x021
+#define SVM_EXIT_READ_DR2 0x022
+#define SVM_EXIT_READ_DR3 0x023
+#define SVM_EXIT_READ_DR4 0x024
+#define SVM_EXIT_READ_DR5 0x025
+#define SVM_EXIT_READ_DR6 0x026
+#define SVM_EXIT_READ_DR7 0x027
+#define SVM_EXIT_WRITE_DR0 0x030
+#define SVM_EXIT_WRITE_DR1 0x031
+#define SVM_EXIT_WRITE_DR2 0x032
+#define SVM_EXIT_WRITE_DR3 0x033
+#define SVM_EXIT_WRITE_DR4 0x034
+#define SVM_EXIT_WRITE_DR5 0x035
+#define SVM_EXIT_WRITE_DR6 0x036
+#define SVM_EXIT_WRITE_DR7 0x037
+#define SVM_EXIT_EXCP_BASE 0x040
+#define SVM_EXIT_INTR 0x060
+#define SVM_EXIT_NMI 0x061
+#define SVM_EXIT_SMI 0x062
+#define SVM_EXIT_INIT 0x063
+#define SVM_EXIT_VINTR 0x064
+#define SVM_EXIT_CR0_SEL_WRITE 0x065
+#define SVM_EXIT_IDTR_READ 0x066
+#define SVM_EXIT_GDTR_READ 0x067
+#define SVM_EXIT_LDTR_READ 0x068
+#define SVM_EXIT_TR_READ 0x069
+#define SVM_EXIT_IDTR_WRITE 0x06a
+#define SVM_EXIT_GDTR_WRITE 0x06b
+#define SVM_EXIT_LDTR_WRITE 0x06c
+#define SVM_EXIT_TR_WRITE 0x06d
+#define SVM_EXIT_RDTSC 0x06e
+#define SVM_EXIT_RDPMC 0x06f
+#define SVM_EXIT_PUSHF 0x070
+#define SVM_EXIT_POPF 0x071
+#define SVM_EXIT_CPUID 0x072
+#define SVM_EXIT_RSM 0x073
+#define SVM_EXIT_IRET 0x074
+#define SVM_EXIT_SWINT 0x075
+#define SVM_EXIT_INVD 0x076
+#define SVM_EXIT_PAUSE 0x077
+#define SVM_EXIT_HLT 0x078
+#define SVM_EXIT_INVLPG 0x079
+#define SVM_EXIT_INVLPGA 0x07a
+#define SVM_EXIT_IOIO 0x07b
+#define SVM_EXIT_MSR 0x07c
+#define SVM_EXIT_TASK_SWITCH 0x07d
+#define SVM_EXIT_FERR_FREEZE 0x07e
+#define SVM_EXIT_SHUTDOWN 0x07f
+#define SVM_EXIT_VMRUN 0x080
+#define SVM_EXIT_VMMCALL 0x081
+#define SVM_EXIT_VMLOAD 0x082
+#define SVM_EXIT_VMSAVE 0x083
+#define SVM_EXIT_STGI 0x084
+#define SVM_EXIT_CLGI 0x085
+#define SVM_EXIT_SKINIT 0x086
+#define SVM_EXIT_RDTSCP 0x087
+#define SVM_EXIT_ICEBP 0x088
+#define SVM_EXIT_WBINVD 0x089
+#define SVM_EXIT_MONITOR 0x08a
+#define SVM_EXIT_MWAIT 0x08b
+#define SVM_EXIT_MWAIT_COND 0x08c
+#define SVM_EXIT_XSETBV 0x08d
+#define SVM_EXIT_NPF 0x400
+
+#define SVM_EXIT_ERR -1
+
+#define SVM_EXIT_REASONS \
+ { SVM_EXIT_READ_CR0, "read_cr0" }, \
+ { SVM_EXIT_READ_CR3, "read_cr3" }, \
+ { SVM_EXIT_READ_CR4, "read_cr4" }, \
+ { SVM_EXIT_READ_CR8, "read_cr8" }, \
+ { SVM_EXIT_WRITE_CR0, "write_cr0" }, \
+ { SVM_EXIT_WRITE_CR3, "write_cr3" }, \
+ { SVM_EXIT_WRITE_CR4, "write_cr4" }, \
+ { SVM_EXIT_WRITE_CR8, "write_cr8" }, \
+ { SVM_EXIT_READ_DR0, "read_dr0" }, \
+ { SVM_EXIT_READ_DR1, "read_dr1" }, \
+ { SVM_EXIT_READ_DR2, "read_dr2" }, \
+ { SVM_EXIT_READ_DR3, "read_dr3" }, \
+ { SVM_EXIT_WRITE_DR0, "write_dr0" }, \
+ { SVM_EXIT_WRITE_DR1, "write_dr1" }, \
+ { SVM_EXIT_WRITE_DR2, "write_dr2" }, \
+ { SVM_EXIT_WRITE_DR3, "write_dr3" }, \
+ { SVM_EXIT_WRITE_DR5, "write_dr5" }, \
+ { SVM_EXIT_WRITE_DR7, "write_dr7" }, \
+ { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \
+ { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \
+ { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \
+ { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \
+ { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \
+ { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \
+ { SVM_EXIT_INTR, "interrupt" }, \
+ { SVM_EXIT_NMI, "nmi" }, \
+ { SVM_EXIT_SMI, "smi" }, \
+ { SVM_EXIT_INIT, "init" }, \
+ { SVM_EXIT_VINTR, "vintr" }, \
+ { SVM_EXIT_CPUID, "cpuid" }, \
+ { SVM_EXIT_INVD, "invd" }, \
+ { SVM_EXIT_HLT, "hlt" }, \
+ { SVM_EXIT_INVLPG, "invlpg" }, \
+ { SVM_EXIT_INVLPGA, "invlpga" }, \
+ { SVM_EXIT_IOIO, "io" }, \
+ { SVM_EXIT_MSR, "msr" }, \
+ { SVM_EXIT_TASK_SWITCH, "task_switch" }, \
+ { SVM_EXIT_SHUTDOWN, "shutdown" }, \
+ { SVM_EXIT_VMRUN, "vmrun" }, \
+ { SVM_EXIT_VMMCALL, "hypercall" }, \
+ { SVM_EXIT_VMLOAD, "vmload" }, \
+ { SVM_EXIT_VMSAVE, "vmsave" }, \
+ { SVM_EXIT_STGI, "stgi" }, \
+ { SVM_EXIT_CLGI, "clgi" }, \
+ { SVM_EXIT_SKINIT, "skinit" }, \
+ { SVM_EXIT_WBINVD, "wbinvd" }, \
+ { SVM_EXIT_MONITOR, "monitor" }, \
+ { SVM_EXIT_MWAIT, "mwait" }, \
+ { SVM_EXIT_XSETBV, "xsetbv" }, \
+ { SVM_EXIT_NPF, "npf" }
+
+#ifdef __KERNEL__
+
enum {
INTERCEPT_INTR,
INTERCEPT_NMI,
@@ -264,81 +393,6 @@ struct __attribute__ ((__packed__)) vmcb {
#define SVM_EXITINFO_REG_MASK 0x0F
-#define SVM_EXIT_READ_CR0 0x000
-#define SVM_EXIT_READ_CR3 0x003
-#define SVM_EXIT_READ_CR4 0x004
-#define SVM_EXIT_READ_CR8 0x008
-#define SVM_EXIT_WRITE_CR0 0x010
-#define SVM_EXIT_WRITE_CR3 0x013
-#define SVM_EXIT_WRITE_CR4 0x014
-#define SVM_EXIT_WRITE_CR8 0x018
-#define SVM_EXIT_READ_DR0 0x020
-#define SVM_EXIT_READ_DR1 0x021
-#define SVM_EXIT_READ_DR2 0x022
-#define SVM_EXIT_READ_DR3 0x023
-#define SVM_EXIT_READ_DR4 0x024
-#define SVM_EXIT_READ_DR5 0x025
-#define SVM_EXIT_READ_DR6 0x026
-#define SVM_EXIT_READ_DR7 0x027
-#define SVM_EXIT_WRITE_DR0 0x030
-#define SVM_EXIT_WRITE_DR1 0x031
-#define SVM_EXIT_WRITE_DR2 0x032
-#define SVM_EXIT_WRITE_DR3 0x033
-#define SVM_EXIT_WRITE_DR4 0x034
-#define SVM_EXIT_WRITE_DR5 0x035
-#define SVM_EXIT_WRITE_DR6 0x036
-#define SVM_EXIT_WRITE_DR7 0x037
-#define SVM_EXIT_EXCP_BASE 0x040
-#define SVM_EXIT_INTR 0x060
-#define SVM_EXIT_NMI 0x061
-#define SVM_EXIT_SMI 0x062
-#define SVM_EXIT_INIT 0x063
-#define SVM_EXIT_VINTR 0x064
-#define SVM_EXIT_CR0_SEL_WRITE 0x065
-#define SVM_EXIT_IDTR_READ 0x066
-#define SVM_EXIT_GDTR_READ 0x067
-#define SVM_EXIT_LDTR_READ 0x068
-#define SVM_EXIT_TR_READ 0x069
-#define SVM_EXIT_IDTR_WRITE 0x06a
-#define SVM_EXIT_GDTR_WRITE 0x06b
-#define SVM_EXIT_LDTR_WRITE 0x06c
-#define SVM_EXIT_TR_WRITE 0x06d
-#define SVM_EXIT_RDTSC 0x06e
-#define SVM_EXIT_RDPMC 0x06f
-#define SVM_EXIT_PUSHF 0x070
-#define SVM_EXIT_POPF 0x071
-#define SVM_EXIT_CPUID 0x072
-#define SVM_EXIT_RSM 0x073
-#define SVM_EXIT_IRET 0x074
-#define SVM_EXIT_SWINT 0x075
-#define SVM_EXIT_INVD 0x076
-#define SVM_EXIT_PAUSE 0x077
-#define SVM_EXIT_HLT 0x078
-#define SVM_EXIT_INVLPG 0x079
-#define SVM_EXIT_INVLPGA 0x07a
-#define SVM_EXIT_IOIO 0x07b
-#define SVM_EXIT_MSR 0x07c
-#define SVM_EXIT_TASK_SWITCH 0x07d
-#define SVM_EXIT_FERR_FREEZE 0x07e
-#define SVM_EXIT_SHUTDOWN 0x07f
-#define SVM_EXIT_VMRUN 0x080
-#define SVM_EXIT_VMMCALL 0x081
-#define SVM_EXIT_VMLOAD 0x082
-#define SVM_EXIT_VMSAVE 0x083
-#define SVM_EXIT_STGI 0x084
-#define SVM_EXIT_CLGI 0x085
-#define SVM_EXIT_SKINIT 0x086
-#define SVM_EXIT_RDTSCP 0x087
-#define SVM_EXIT_ICEBP 0x088
-#define SVM_EXIT_WBINVD 0x089
-#define SVM_EXIT_MONITOR 0x08a
-#define SVM_EXIT_MWAIT 0x08b
-#define SVM_EXIT_MWAIT_COND 0x08c
-#define SVM_EXIT_XSETBV 0x08d
-#define SVM_EXIT_NPF 0x400
-
-#define SVM_EXIT_ERR -1
-
#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
@@ -350,3 +404,4 @@ struct __attribute__ ((__packed__)) vmcb {
#endif
+#endif
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 3fda9db4881..4ca1c611b55 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -40,7 +40,7 @@ asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *,
struct old_sigaction32 __user *);
asmlinkage long sys32_alarm(unsigned int);
-asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
+asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int);
asmlinkage long sys32_sysfs(int, u32, u32);
asmlinkage long sys32_sched_rr_get_interval(compat_pid_t,
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89f794f007e..c535d847e3b 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -89,6 +89,7 @@ struct thread_info {
#define TIF_NOTSC 16 /* TSC is not accessible in userland */
#define TIF_IA32 17 /* IA32 compatibility process */
#define TIF_FORK 18 /* ret_from_fork */
+#define TIF_NOHZ 19 /* in adaptive nohz mode */
#define TIF_MEMDIE 20 /* is terminating due to OOM killer */
#define TIF_DEBUG 21 /* uses debug registers */
#define TIF_IO_BITMAP 22 /* uses I/O bitmap */
@@ -114,6 +115,7 @@ struct thread_info {
#define _TIF_NOTSC (1 << TIF_NOTSC)
#define _TIF_IA32 (1 << TIF_IA32)
#define _TIF_FORK (1 << TIF_FORK)
+#define _TIF_NOHZ (1 << TIF_NOHZ)
#define _TIF_DEBUG (1 << TIF_DEBUG)
#define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP)
#define _TIF_FORCED_TF (1 << TIF_FORCED_TF)
@@ -126,12 +128,13 @@ struct thread_info {
/* work to do in syscall_trace_enter() */
#define _TIF_WORK_SYSCALL_ENTRY \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT | \
- _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
+ _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \
+ _TIF_NOHZ)
/* work to do in syscall_trace_leave() */
#define _TIF_WORK_SYSCALL_EXIT \
(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \
- _TIF_SYSCALL_TRACEPOINT)
+ _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ)
/* work to do on interrupt/exception return */
#define _TIF_WORK_MASK \
@@ -141,7 +144,8 @@ struct thread_info {
/* work to do on any return to user space */
#define _TIF_ALLWORK_MASK \
- ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT)
+ ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \
+ _TIF_NOHZ)
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index e1f3a17034f..7ccf8d13153 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -9,6 +9,7 @@
#include <linux/string.h>
#include <asm/asm.h>
#include <asm/page.h>
+#include <asm/smap.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
@@ -192,9 +193,10 @@ extern int __get_user_bad(void);
#ifdef CONFIG_X86_32
#define __put_user_asm_u64(x, addr, err, errret) \
- asm volatile("1: movl %%eax,0(%2)\n" \
+ asm volatile(ASM_STAC "\n" \
+ "1: movl %%eax,0(%2)\n" \
"2: movl %%edx,4(%2)\n" \
- "3:\n" \
+ "3: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"4: movl %3,%0\n" \
" jmp 3b\n" \
@@ -205,9 +207,10 @@ extern int __get_user_bad(void);
: "A" (x), "r" (addr), "i" (errret), "0" (err))
#define __put_user_asm_ex_u64(x, addr) \
- asm volatile("1: movl %%eax,0(%1)\n" \
+ asm volatile(ASM_STAC "\n" \
+ "1: movl %%eax,0(%1)\n" \
"2: movl %%edx,4(%1)\n" \
- "3:\n" \
+ "3: " ASM_CLAC "\n" \
_ASM_EXTABLE_EX(1b, 2b) \
_ASM_EXTABLE_EX(2b, 3b) \
: : "A" (x), "r" (addr))
@@ -379,8 +382,9 @@ do { \
} while (0)
#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \
- asm volatile("1: mov"itype" %2,%"rtype"1\n" \
- "2:\n" \
+ asm volatile(ASM_STAC "\n" \
+ "1: mov"itype" %2,%"rtype"1\n" \
+ "2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"3: mov %3,%0\n" \
" xor"itype" %"rtype"1,%"rtype"1\n" \
@@ -443,8 +447,9 @@ struct __large_struct { unsigned long buf[100]; };
* aliasing issues.
*/
#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \
- asm volatile("1: mov"itype" %"rtype"1,%2\n" \
- "2:\n" \
+ asm volatile(ASM_STAC "\n" \
+ "1: mov"itype" %"rtype"1,%2\n" \
+ "2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"3: mov %3,%0\n" \
" jmp 2b\n" \
@@ -463,13 +468,13 @@ struct __large_struct { unsigned long buf[100]; };
* uaccess_try and catch
*/
#define uaccess_try do { \
- int prev_err = current_thread_info()->uaccess_err; \
current_thread_info()->uaccess_err = 0; \
+ stac(); \
barrier();
#define uaccess_catch(err) \
+ clac(); \
(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0); \
- current_thread_info()->uaccess_err = prev_err; \
} while (0)
/**
@@ -569,6 +574,9 @@ strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
+unsigned long __must_check clear_user(void __user *mem, unsigned long len);
+unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
+
/*
* movsl can be slow when source and dest are not both 8-byte aligned
*/
@@ -581,9 +589,9 @@ extern struct movsl_mask {
#define ARCH_HAS_NOCACHE_UACCESS 1
#ifdef CONFIG_X86_32
-# include "uaccess_32.h"
+# include <asm/uaccess_32.h>
#else
-# include "uaccess_64.h"
+# include <asm/uaccess_64.h>
#endif
#endif /* _ASM_X86_UACCESS_H */
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 576e39bca6a..7f760a9f1f6 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,7 +213,4 @@ static inline unsigned long __must_check copy_from_user(void *to,
return n;
}
-unsigned long __must_check clear_user(void __user *mem, unsigned long len);
-unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-
#endif /* _ASM_X86_UACCESS_32_H */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index d8def8b3dba..142810c457d 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -217,9 +217,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
}
}
-__must_check unsigned long clear_user(void __user *mem, unsigned long len);
-__must_check unsigned long __clear_user(void __user *mem, unsigned long len);
-
static __must_check __always_inline int
__copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
{
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index f3971bbcd1d..8ff8be7835a 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -42,10 +42,11 @@ struct arch_uprobe {
};
struct arch_uprobe_task {
- unsigned long saved_trap_nr;
#ifdef CONFIG_X86_64
unsigned long saved_scratch_register;
#endif
+ unsigned int saved_trap_nr;
+ unsigned int saved_tf;
};
extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
index 24532c7da3d..ccab4af1646 100644
--- a/arch/x86/include/asm/user.h
+++ b/arch/x86/include/asm/user.h
@@ -2,9 +2,9 @@
#define _ASM_X86_USER_H
#ifdef CONFIG_X86_32
-# include "user_32.h"
+# include <asm/user_32.h>
#else
-# include "user_64.h"
+# include <asm/user_64.h>
#endif
#include <asm/types.h>
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index bb0522850b7..fddb53d6391 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -11,7 +11,8 @@ extern const char VDSO32_PRELINK[];
#define VDSO32_SYMBOL(base, name) \
({ \
extern const char VDSO32_##name[]; \
- (void *)(VDSO32_##name - VDSO32_PRELINK + (unsigned long)(base)); \
+ (void __user *)(VDSO32_##name - VDSO32_PRELINK + \
+ (unsigned long)(base)); \
})
#endif
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 74fcb963595..36ec21c36d6 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -25,6 +25,88 @@
*
*/
+#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000
+
+#define EXIT_REASON_EXCEPTION_NMI 0
+#define EXIT_REASON_EXTERNAL_INTERRUPT 1
+#define EXIT_REASON_TRIPLE_FAULT 2
+
+#define EXIT_REASON_PENDING_INTERRUPT 7
+#define EXIT_REASON_NMI_WINDOW 8
+#define EXIT_REASON_TASK_SWITCH 9
+#define EXIT_REASON_CPUID 10
+#define EXIT_REASON_HLT 12
+#define EXIT_REASON_INVD 13
+#define EXIT_REASON_INVLPG 14
+#define EXIT_REASON_RDPMC 15
+#define EXIT_REASON_RDTSC 16
+#define EXIT_REASON_VMCALL 18
+#define EXIT_REASON_VMCLEAR 19
+#define EXIT_REASON_VMLAUNCH 20
+#define EXIT_REASON_VMPTRLD 21
+#define EXIT_REASON_VMPTRST 22
+#define EXIT_REASON_VMREAD 23
+#define EXIT_REASON_VMRESUME 24
+#define EXIT_REASON_VMWRITE 25
+#define EXIT_REASON_VMOFF 26
+#define EXIT_REASON_VMON 27
+#define EXIT_REASON_CR_ACCESS 28
+#define EXIT_REASON_DR_ACCESS 29
+#define EXIT_REASON_IO_INSTRUCTION 30
+#define EXIT_REASON_MSR_READ 31
+#define EXIT_REASON_MSR_WRITE 32
+#define EXIT_REASON_INVALID_STATE 33
+#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION 40
+#define EXIT_REASON_MCE_DURING_VMENTRY 41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS 44
+#define EXIT_REASON_EPT_VIOLATION 48
+#define EXIT_REASON_EPT_MISCONFIG 49
+#define EXIT_REASON_WBINVD 54
+#define EXIT_REASON_XSETBV 55
+#define EXIT_REASON_INVPCID 58
+
+#define VMX_EXIT_REASONS \
+ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
+ { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \
+ { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \
+ { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \
+ { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \
+ { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \
+ { EXIT_REASON_CPUID, "CPUID" }, \
+ { EXIT_REASON_HLT, "HLT" }, \
+ { EXIT_REASON_INVLPG, "INVLPG" }, \
+ { EXIT_REASON_RDPMC, "RDPMC" }, \
+ { EXIT_REASON_RDTSC, "RDTSC" }, \
+ { EXIT_REASON_VMCALL, "VMCALL" }, \
+ { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \
+ { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \
+ { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \
+ { EXIT_REASON_VMPTRST, "VMPTRST" }, \
+ { EXIT_REASON_VMREAD, "VMREAD" }, \
+ { EXIT_REASON_VMRESUME, "VMRESUME" }, \
+ { EXIT_REASON_VMWRITE, "VMWRITE" }, \
+ { EXIT_REASON_VMOFF, "VMOFF" }, \
+ { EXIT_REASON_VMON, "VMON" }, \
+ { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \
+ { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \
+ { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \
+ { EXIT_REASON_MSR_READ, "MSR_READ" }, \
+ { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \
+ { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \
+ { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \
+ { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \
+ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
+ { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
+ { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
+ { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
+ { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
+ { EXIT_REASON_WBINVD, "WBINVD" }
+
+#ifdef __KERNEL__
+
#include <linux/types.h>
/*
@@ -241,49 +323,6 @@ enum vmcs_field {
HOST_RIP = 0x00006c16,
};
-#define VMX_EXIT_REASONS_FAILED_VMENTRY 0x80000000
-
-#define EXIT_REASON_EXCEPTION_NMI 0
-#define EXIT_REASON_EXTERNAL_INTERRUPT 1
-#define EXIT_REASON_TRIPLE_FAULT 2
-
-#define EXIT_REASON_PENDING_INTERRUPT 7
-#define EXIT_REASON_NMI_WINDOW 8
-#define EXIT_REASON_TASK_SWITCH 9
-#define EXIT_REASON_CPUID 10
-#define EXIT_REASON_HLT 12
-#define EXIT_REASON_INVD 13
-#define EXIT_REASON_INVLPG 14
-#define EXIT_REASON_RDPMC 15
-#define EXIT_REASON_RDTSC 16
-#define EXIT_REASON_VMCALL 18
-#define EXIT_REASON_VMCLEAR 19
-#define EXIT_REASON_VMLAUNCH 20
-#define EXIT_REASON_VMPTRLD 21
-#define EXIT_REASON_VMPTRST 22
-#define EXIT_REASON_VMREAD 23
-#define EXIT_REASON_VMRESUME 24
-#define EXIT_REASON_VMWRITE 25
-#define EXIT_REASON_VMOFF 26
-#define EXIT_REASON_VMON 27
-#define EXIT_REASON_CR_ACCESS 28
-#define EXIT_REASON_DR_ACCESS 29
-#define EXIT_REASON_IO_INSTRUCTION 30
-#define EXIT_REASON_MSR_READ 31
-#define EXIT_REASON_MSR_WRITE 32
-#define EXIT_REASON_INVALID_STATE 33
-#define EXIT_REASON_MWAIT_INSTRUCTION 36
-#define EXIT_REASON_MONITOR_INSTRUCTION 39
-#define EXIT_REASON_PAUSE_INSTRUCTION 40
-#define EXIT_REASON_MCE_DURING_VMENTRY 41
-#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
-#define EXIT_REASON_APIC_ACCESS 44
-#define EXIT_REASON_EPT_VIOLATION 48
-#define EXIT_REASON_EPT_MISCONFIG 49
-#define EXIT_REASON_WBINVD 54
-#define EXIT_REASON_XSETBV 55
-#define EXIT_REASON_INVPCID 58
-
/*
* Interruption-information format
*/
@@ -488,3 +527,5 @@ enum vm_instruction_error_number {
};
#endif
+
+#endif
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 38155f66714..57693498519 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -81,12 +81,13 @@ struct x86_init_mapping {
/**
* struct x86_init_paging - platform specific paging functions
- * @pagetable_setup_start: platform specific pre paging_init() call
- * @pagetable_setup_done: platform specific post paging_init() call
+ * @pagetable_init: platform specific paging initialization call to setup
+ * the kernel pagetables and prepare accessors functions.
+ * Callback must call paging_init(). Called once after the
+ * direct mapping for phys memory is available.
*/
struct x86_init_paging {
- void (*pagetable_setup_start)(pgd_t *base);
- void (*pagetable_setup_done)(pgd_t *base);
+ void (*pagetable_init)(void);
};
/**
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index cbf0c9d50b9..6d2f75a82a1 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -47,6 +47,11 @@
#endif
#ifndef __ASSEMBLY__
+/* Explicitly size integers that represent pfns in the public interface
+ * with Xen so that on ARM we can have one ABI that works for 32 and 64
+ * bit guests. */
+typedef unsigned long xen_pfn_t;
+typedef unsigned long xen_ulong_t;
/* Guest handles for primitive C types. */
__DEFINE_GUEST_HANDLE(uchar, unsigned char);
__DEFINE_GUEST_HANDLE(uint, unsigned int);
@@ -57,6 +62,7 @@ DEFINE_GUEST_HANDLE(long);
DEFINE_GUEST_HANDLE(void);
DEFINE_GUEST_HANDLE(uint64_t);
DEFINE_GUEST_HANDLE(uint32_t);
+DEFINE_GUEST_HANDLE(xen_pfn_t);
#endif
#ifndef HYPERVISOR_VIRT_START
@@ -116,11 +122,13 @@ struct arch_shared_info {
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_X86_32
-#include "interface_32.h"
+#include <asm/xen/interface_32.h>
#else
-#include "interface_64.h"
+#include <asm/xen/interface_64.h>
#endif
+#include <asm/pvclock-abi.h>
+
#ifndef __ASSEMBLY__
/*
* The following is all CPU context. Note that the fpu_ctxt block is filled
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 93971e841dd..472b9b78301 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -51,7 +51,8 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
extern int m2p_add_override(unsigned long mfn, struct page *page,
struct gnttab_map_grant_ref *kmap_op);
-extern int m2p_remove_override(struct page *page, bool clear_pte);
+extern int m2p_remove_override(struct page *page,
+ struct gnttab_map_grant_ref *kmap_op);
extern struct page *m2p_find_override(unsigned long mfn);
extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h
index 1be1ab7d6a4..ee52fcac6f7 100644
--- a/arch/x86/include/asm/xen/swiotlb-xen.h
+++ b/arch/x86/include/asm/xen/swiotlb-xen.h
@@ -5,10 +5,12 @@
extern int xen_swiotlb;
extern int __init pci_xen_swiotlb_detect(void);
extern void __init pci_xen_swiotlb_init(void);
+extern int pci_xen_swiotlb_init_late(void);
#else
#define xen_swiotlb (0)
static inline int __init pci_xen_swiotlb_detect(void) { return 0; }
static inline void __init pci_xen_swiotlb_init(void) { }
+static inline int pci_xen_swiotlb_init_late(void) { return -ENXIO; }
#endif
#endif /* _ASM_X86_SWIOTLB_XEN_H */
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index 7fcf6f3dbcc..f8fde90bc45 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -3,8 +3,8 @@
# include <asm-generic/xor.h>
#else
#ifdef CONFIG_X86_32
-# include "xor_32.h"
+# include <asm/xor_32.h>
#else
-# include "xor_64.h"
+# include <asm/xor_64.h>
#endif
#endif
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index 454570891bd..f79cb7ec0e0 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -534,38 +534,6 @@ static struct xor_block_template xor_block_p5_mmx = {
* Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
*/
-#define XMMS_SAVE \
-do { \
- preempt_disable(); \
- cr0 = read_cr0(); \
- clts(); \
- asm volatile( \
- "movups %%xmm0,(%0) ;\n\t" \
- "movups %%xmm1,0x10(%0) ;\n\t" \
- "movups %%xmm2,0x20(%0) ;\n\t" \
- "movups %%xmm3,0x30(%0) ;\n\t" \
- : \
- : "r" (xmm_save) \
- : "memory"); \
-} while (0)
-
-#define XMMS_RESTORE \
-do { \
- asm volatile( \
- "sfence ;\n\t" \
- "movups (%0),%%xmm0 ;\n\t" \
- "movups 0x10(%0),%%xmm1 ;\n\t" \
- "movups 0x20(%0),%%xmm2 ;\n\t" \
- "movups 0x30(%0),%%xmm3 ;\n\t" \
- : \
- : "r" (xmm_save) \
- : "memory"); \
- write_cr0(cr0); \
- preempt_enable(); \
-} while (0)
-
-#define ALIGN16 __attribute__((aligned(16)))
-
#define OFFS(x) "16*("#x")"
#define PF_OFFS(x) "256+16*("#x")"
#define PF0(x) " prefetchnta "PF_OFFS(x)"(%1) ;\n"
@@ -587,10 +555,8 @@ static void
xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned long lines = bytes >> 8;
- char xmm_save[16*4] ALIGN16;
- int cr0;
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
@@ -633,7 +599,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
:
: "memory");
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static void
@@ -641,10 +607,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned long lines = bytes >> 8;
- char xmm_save[16*4] ALIGN16;
- int cr0;
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
@@ -694,7 +658,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
:
: "memory" );
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static void
@@ -702,10 +666,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned long lines = bytes >> 8;
- char xmm_save[16*4] ALIGN16;
- int cr0;
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
@@ -762,7 +724,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
:
: "memory" );
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static void
@@ -770,10 +732,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned long lines = bytes >> 8;
- char xmm_save[16*4] ALIGN16;
- int cr0;
- XMMS_SAVE;
+ kernel_fpu_begin();
/* Make sure GCC forgets anything it knows about p4 or p5,
such that it won't pass to the asm volatile below a
@@ -850,7 +810,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
like assuming they have some legal value. */
asm("" : "=r" (p4), "=r" (p5));
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static struct xor_block_template xor_block_pIII_sse = {
@@ -862,7 +822,7 @@ static struct xor_block_template xor_block_pIII_sse = {
};
/* Also try the AVX routines */
-#include "xor_avx.h"
+#include <asm/xor_avx.h>
/* Also try the generic routines. */
#include <asm-generic/xor.h>
diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h
index b9b2323e90f..87ac522c4af 100644
--- a/arch/x86/include/asm/xor_64.h
+++ b/arch/x86/include/asm/xor_64.h
@@ -34,41 +34,7 @@
* no advantages to be gotten from x86-64 here anyways.
*/
-typedef struct {
- unsigned long a, b;
-} __attribute__((aligned(16))) xmm_store_t;
-
-/* Doesn't use gcc to save the XMM registers, because there is no easy way to
- tell it to do a clts before the register saving. */
-#define XMMS_SAVE \
-do { \
- preempt_disable(); \
- asm volatile( \
- "movq %%cr0,%0 ;\n\t" \
- "clts ;\n\t" \
- "movups %%xmm0,(%1) ;\n\t" \
- "movups %%xmm1,0x10(%1) ;\n\t" \
- "movups %%xmm2,0x20(%1) ;\n\t" \
- "movups %%xmm3,0x30(%1) ;\n\t" \
- : "=&r" (cr0) \
- : "r" (xmm_save) \
- : "memory"); \
-} while (0)
-
-#define XMMS_RESTORE \
-do { \
- asm volatile( \
- "sfence ;\n\t" \
- "movups (%1),%%xmm0 ;\n\t" \
- "movups 0x10(%1),%%xmm1 ;\n\t" \
- "movups 0x20(%1),%%xmm2 ;\n\t" \
- "movups 0x30(%1),%%xmm3 ;\n\t" \
- "movq %0,%%cr0 ;\n\t" \
- : \
- : "r" (cr0), "r" (xmm_save) \
- : "memory"); \
- preempt_enable(); \
-} while (0)
+#include <asm/i387.h>
#define OFFS(x) "16*("#x")"
#define PF_OFFS(x) "256+16*("#x")"
@@ -91,10 +57,8 @@ static void
xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
{
unsigned int lines = bytes >> 8;
- unsigned long cr0;
- xmm_store_t xmm_save[4];
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
@@ -135,7 +99,7 @@ xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
: [inc] "r" (256UL)
: "memory");
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static void
@@ -143,11 +107,8 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3)
{
unsigned int lines = bytes >> 8;
- xmm_store_t xmm_save[4];
- unsigned long cr0;
-
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
#define BLOCK(i) \
@@ -194,7 +155,7 @@ xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
[p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
: [inc] "r" (256UL)
: "memory");
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static void
@@ -202,10 +163,8 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4)
{
unsigned int lines = bytes >> 8;
- xmm_store_t xmm_save[4];
- unsigned long cr0;
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
@@ -261,7 +220,7 @@ xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
: [inc] "r" (256UL)
: "memory" );
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static void
@@ -269,10 +228,8 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
unsigned long *p3, unsigned long *p4, unsigned long *p5)
{
unsigned int lines = bytes >> 8;
- xmm_store_t xmm_save[4];
- unsigned long cr0;
- XMMS_SAVE;
+ kernel_fpu_begin();
asm volatile(
#undef BLOCK
@@ -336,7 +293,7 @@ xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
: [inc] "r" (256UL)
: "memory");
- XMMS_RESTORE;
+ kernel_fpu_end();
}
static struct xor_block_template xor_block_sse = {
@@ -349,7 +306,7 @@ static struct xor_block_template xor_block_sse = {
/* Also try the AVX routines */
-#include "xor_avx.h"
+#include <asm/xor_avx.h>
#undef XOR_TRY_TEMPLATES
#define XOR_TRY_TEMPLATES \
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 2510d35f480..7ea79c5fa1f 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -20,32 +20,6 @@
#include <linux/compiler.h>
#include <asm/i387.h>
-#define ALIGN32 __aligned(32)
-
-#define YMM_SAVED_REGS 4
-
-#define YMMS_SAVE \
-do { \
- preempt_disable(); \
- cr0 = read_cr0(); \
- clts(); \
- asm volatile("vmovaps %%ymm0, %0" : "=m" (ymm_save[0]) : : "memory"); \
- asm volatile("vmovaps %%ymm1, %0" : "=m" (ymm_save[32]) : : "memory"); \
- asm volatile("vmovaps %%ymm2, %0" : "=m" (ymm_save[64]) : : "memory"); \
- asm volatile("vmovaps %%ymm3, %0" : "=m" (ymm_save[96]) : : "memory"); \
-} while (0);
-
-#define YMMS_RESTORE \
-do { \
- asm volatile("sfence" : : : "memory"); \
- asm volatile("vmovaps %0, %%ymm3" : : "m" (ymm_save[96])); \
- asm volatile("vmovaps %0, %%ymm2" : : "m" (ymm_save[64])); \
- asm volatile("vmovaps %0, %%ymm1" : : "m" (ymm_save[32])); \
- asm volatile("vmovaps %0, %%ymm0" : : "m" (ymm_save[0])); \
- write_cr0(cr0); \
- preempt_enable(); \
-} while (0);
-
#define BLOCK4(i) \
BLOCK(32 * i, 0) \
BLOCK(32 * (i + 1), 1) \
@@ -60,10 +34,9 @@ do { \
static void xor_avx_2(unsigned long bytes, unsigned long *p0, unsigned long *p1)
{
- unsigned long cr0, lines = bytes >> 9;
- char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+ unsigned long lines = bytes >> 9;
- YMMS_SAVE
+ kernel_fpu_begin();
while (lines--) {
#undef BLOCK
@@ -82,16 +55,15 @@ do { \
p1 = (unsigned long *)((uintptr_t)p1 + 512);
}
- YMMS_RESTORE
+ kernel_fpu_end();
}
static void xor_avx_3(unsigned long bytes, unsigned long *p0, unsigned long *p1,
unsigned long *p2)
{
- unsigned long cr0, lines = bytes >> 9;
- char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+ unsigned long lines = bytes >> 9;
- YMMS_SAVE
+ kernel_fpu_begin();
while (lines--) {
#undef BLOCK
@@ -113,16 +85,15 @@ do { \
p2 = (unsigned long *)((uintptr_t)p2 + 512);
}
- YMMS_RESTORE
+ kernel_fpu_end();
}
static void xor_avx_4(unsigned long bytes, unsigned long *p0, unsigned long *p1,
unsigned long *p2, unsigned long *p3)
{
- unsigned long cr0, lines = bytes >> 9;
- char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+ unsigned long lines = bytes >> 9;
- YMMS_SAVE
+ kernel_fpu_begin();
while (lines--) {
#undef BLOCK
@@ -147,16 +118,15 @@ do { \
p3 = (unsigned long *)((uintptr_t)p3 + 512);
}
- YMMS_RESTORE
+ kernel_fpu_end();
}
static void xor_avx_5(unsigned long bytes, unsigned long *p0, unsigned long *p1,
unsigned long *p2, unsigned long *p3, unsigned long *p4)
{
- unsigned long cr0, lines = bytes >> 9;
- char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+ unsigned long lines = bytes >> 9;
- YMMS_SAVE
+ kernel_fpu_begin();
while (lines--) {
#undef BLOCK
@@ -184,7 +154,7 @@ do { \
p4 = (unsigned long *)((uintptr_t)p4 + 512);
}
- YMMS_RESTORE
+ kernel_fpu_end();
}
static struct xor_block_template xor_block_avx = {
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 8a1b6f9b594..0415cdabb5a 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -34,17 +34,14 @@
extern unsigned int xstate_size;
extern u64 pcntxt_mask;
extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+extern struct xsave_struct *init_xstate_buf;
extern void xsave_init(void);
extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
extern int init_fpu(struct task_struct *child);
-extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
- void __user *fpstate,
- struct _fpx_sw_bytes *sw);
-static inline int fpu_xrstor_checking(struct fpu *fpu)
+static inline int fpu_xrstor_checking(struct xsave_struct *fx)
{
- struct xsave_struct *fx = &fpu->state->xsave;
int err;
asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
@@ -69,13 +66,13 @@ static inline int xsave_user(struct xsave_struct __user *buf)
* Clear the xsave header first, so that reserved fields are
* initialized to zero.
*/
- err = __clear_user(&buf->xsave_hdr,
- sizeof(struct xsave_hdr_struct));
+ err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
if (unlikely(err))
return -EFAULT;
- __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
- "2:\n"
+ __asm__ __volatile__(ASM_STAC "\n"
+ "1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+ "2: " ASM_CLAC "\n"
".section .fixup,\"ax\"\n"
"3: movl $-1,%[err]\n"
" jmp 2b\n"
@@ -84,9 +81,6 @@ static inline int xsave_user(struct xsave_struct __user *buf)
: [err] "=r" (err)
: "D" (buf), "a" (-1), "d" (-1), "0" (0)
: "memory");
- if (unlikely(err) && __clear_user(buf, xstate_size))
- err = -EFAULT;
- /* No need to clear here because the caller clears USED_MATH */
return err;
}
@@ -97,8 +91,9 @@ static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
u32 lmask = mask;
u32 hmask = mask >> 32;
- __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
- "2:\n"
+ __asm__ __volatile__(ASM_STAC "\n"
+ "1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+ "2: " ASM_CLAC "\n"
".section .fixup,\"ax\"\n"
"3: movl $-1,%[err]\n"
" jmp 2b\n"
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
new file mode 100644
index 00000000000..83b6e9a0dce
--- /dev/null
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -0,0 +1,6 @@
+# UAPI Header export list
+include include/uapi/asm-generic/Kbuild.asm
+
+genhdr-y += unistd_32.h
+genhdr-y += unistd_64.h
+genhdr-y += unistd_x32.h
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8215e5652d9..a48ea05157d 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -81,8 +81,7 @@ obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
obj-$(CONFIG_DEBUG_NX_TEST) += test_nx.o
obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
-obj-$(CONFIG_KVM_GUEST) += kvm.o
-obj-$(CONFIG_KVM_CLOCK) += kvmclock.o
+obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o
obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
@@ -100,6 +99,8 @@ obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
+
###
# 64 bit specific files
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b2297e58c6e..e651f7a589a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -656,7 +656,7 @@ static int __cpuinit _acpi_map_lsapic(acpi_handle handle, int *pcpu)
acpi_register_lapic(physid, ACPI_MADT_ENABLED);
/*
- * If mp_register_lapic successfully generates a new logical cpu
+ * If acpi_register_lapic successfully generates a new logical cpu
* number, then the following will get us exactly what was mapped
*/
cpumask_andnot(new_map, cpu_present_mask, tmp_map);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 1b8e5a03d94..11676cf65ae 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -43,17 +43,22 @@ int acpi_suspend_lowlevel(void)
header->video_mode = saved_video_mode;
+ header->pmode_behavior = 0;
+
#ifndef CONFIG_64BIT
store_gdt((struct desc_ptr *)&header->pmode_gdt);
- if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low,
- &header->pmode_efer_high))
- header->pmode_efer_low = header->pmode_efer_high = 0;
+ if (!rdmsr_safe(MSR_EFER,
+ &header->pmode_efer_low,
+ &header->pmode_efer_high))
+ header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER);
#endif /* !CONFIG_64BIT */
header->pmode_cr0 = read_cr0();
- header->pmode_cr4 = read_cr4_safe();
- header->pmode_behavior = 0;
+ if (__this_cpu_read(cpu_info.cpuid_level) >= 0) {
+ header->pmode_cr4 = read_cr4();
+ header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_CR4);
+ }
if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
&header->pmode_misc_en_low,
&header->pmode_misc_en_high))
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ced4534baed..ef5ccca79a6 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -23,19 +23,6 @@
#define MAX_PATCH_LEN (255-1)
-#ifdef CONFIG_HOTPLUG_CPU
-static int smp_alt_once;
-
-static int __init bootonly(char *str)
-{
- smp_alt_once = 1;
- return 1;
-}
-__setup("smp-alt-boot", bootonly);
-#else
-#define smp_alt_once 1
-#endif
-
static int __initdata_or_module debug_alternative;
static int __init debug_alt(char *str)
@@ -317,7 +304,7 @@ static void alternatives_smp_lock(const s32 *start, const s32 *end,
/* turn DS segment override prefix into lock prefix */
if (*ptr == 0x3e)
text_poke(ptr, ((unsigned char []){0xf0}), 1);
- };
+ }
mutex_unlock(&text_mutex);
}
@@ -326,9 +313,6 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end,
{
const s32 *poff;
- if (noreplace_smp)
- return;
-
mutex_lock(&text_mutex);
for (poff = start; poff < end; poff++) {
u8 *ptr = (u8 *)poff + *poff;
@@ -338,7 +322,7 @@ static void alternatives_smp_unlock(const s32 *start, const s32 *end,
/* turn lock prefix into DS segment override prefix */
if (*ptr == 0xf0)
text_poke(ptr, ((unsigned char []){0x3E}), 1);
- };
+ }
mutex_unlock(&text_mutex);
}
@@ -359,7 +343,7 @@ struct smp_alt_module {
};
static LIST_HEAD(smp_alt_modules);
static DEFINE_MUTEX(smp_alt);
-static int smp_mode = 1; /* protected by smp_alt */
+static bool uniproc_patched = false; /* protected by smp_alt */
void __init_or_module alternatives_smp_module_add(struct module *mod,
char *name,
@@ -368,19 +352,18 @@ void __init_or_module alternatives_smp_module_add(struct module *mod,
{
struct smp_alt_module *smp;
- if (noreplace_smp)
- return;
+ mutex_lock(&smp_alt);
+ if (!uniproc_patched)
+ goto unlock;
- if (smp_alt_once) {
- if (boot_cpu_has(X86_FEATURE_UP))
- alternatives_smp_unlock(locks, locks_end,
- text, text_end);
- return;
- }
+ if (num_possible_cpus() == 1)
+ /* Don't bother remembering, we'll never have to undo it. */
+ goto smp_unlock;
smp = kzalloc(sizeof(*smp), GFP_KERNEL);
if (NULL == smp)
- return; /* we'll run the (safe but slow) SMP code then ... */
+ /* we'll run the (safe but slow) SMP code then ... */
+ goto unlock;
smp->mod = mod;
smp->name = name;
@@ -392,11 +375,10 @@ void __init_or_module alternatives_smp_module_add(struct module *mod,
__func__, smp->locks, smp->locks_end,
smp->text, smp->text_end, smp->name);
- mutex_lock(&smp_alt);
list_add_tail(&smp->next, &smp_alt_modules);
- if (boot_cpu_has(X86_FEATURE_UP))
- alternatives_smp_unlock(smp->locks, smp->locks_end,
- smp->text, smp->text_end);
+smp_unlock:
+ alternatives_smp_unlock(locks, locks_end, text, text_end);
+unlock:
mutex_unlock(&smp_alt);
}
@@ -404,24 +386,18 @@ void __init_or_module alternatives_smp_module_del(struct module *mod)
{
struct smp_alt_module *item;
- if (smp_alt_once || noreplace_smp)
- return;
-
mutex_lock(&smp_alt);
list_for_each_entry(item, &smp_alt_modules, next) {
if (mod != item->mod)
continue;
list_del(&item->next);
- mutex_unlock(&smp_alt);
- DPRINTK("%s: %s\n", __func__, item->name);
kfree(item);
- return;
+ break;
}
mutex_unlock(&smp_alt);
}
-bool skip_smp_alternatives;
-void alternatives_smp_switch(int smp)
+void alternatives_enable_smp(void)
{
struct smp_alt_module *mod;
@@ -436,34 +412,21 @@ void alternatives_smp_switch(int smp)
pr_info("lockdep: fixing up alternatives\n");
#endif
- if (noreplace_smp || smp_alt_once || skip_smp_alternatives)
- return;
- BUG_ON(!smp && (num_online_cpus() > 1));
+ /* Why bother if there are no other CPUs? */
+ BUG_ON(num_possible_cpus() == 1);
mutex_lock(&smp_alt);
- /*
- * Avoid unnecessary switches because it forces JIT based VMs to
- * throw away all cached translations, which can be quite costly.
- */
- if (smp == smp_mode) {
- /* nothing */
- } else if (smp) {
+ if (uniproc_patched) {
pr_info("switching to SMP code\n");
+ BUG_ON(num_online_cpus() != 1);
clear_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
clear_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
list_for_each_entry(mod, &smp_alt_modules, next)
alternatives_smp_lock(mod->locks, mod->locks_end,
mod->text, mod->text_end);
- } else {
- pr_info("switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
- list_for_each_entry(mod, &smp_alt_modules, next)
- alternatives_smp_unlock(mod->locks, mod->locks_end,
- mod->text, mod->text_end);
+ uniproc_patched = false;
}
- smp_mode = smp;
mutex_unlock(&smp_alt);
}
@@ -540,40 +503,22 @@ void __init alternative_instructions(void)
apply_alternatives(__alt_instructions, __alt_instructions_end);
- /* switch to patch-once-at-boottime-only mode and free the
- * tables in case we know the number of CPUs will never ever
- * change */
-#ifdef CONFIG_HOTPLUG_CPU
- if (num_possible_cpus() < 2)
- smp_alt_once = 1;
-#endif
-
#ifdef CONFIG_SMP
- if (smp_alt_once) {
- if (1 == num_possible_cpus()) {
- pr_info("switching to UP code\n");
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_UP);
- set_cpu_cap(&cpu_data(0), X86_FEATURE_UP);
-
- alternatives_smp_unlock(__smp_locks, __smp_locks_end,
- _text, _etext);
- }
- } else {
+ /* Patch to UP if other cpus not imminent. */
+ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
+ uniproc_patched = true;
alternatives_smp_module_add(NULL, "core kernel",
__smp_locks, __smp_locks_end,
_text, _etext);
-
- /* Only switch to UP mode if we don't immediately boot others */
- if (num_present_cpus() == 1 || setup_max_cpus <= 1)
- alternatives_smp_switch(0);
}
-#endif
- apply_paravirt(__parainstructions, __parainstructions_end);
- if (smp_alt_once)
+ if (!uniproc_patched || num_possible_cpus() == 1)
free_init_pages("SMP alternatives",
(unsigned long)__smp_locks,
(unsigned long)__smp_locks_end);
+#endif
+
+ apply_paravirt(__parainstructions, __parainstructions_end);
restart_nmi();
}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 24deb308232..b17416e72fb 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1934,7 +1934,7 @@ void smp_error_interrupt(struct pt_regs *regs)
apic_printk(APIC_DEBUG, KERN_CONT " : %s", error_interrupt_reason[i]);
i++;
v1 >>= 1;
- };
+ }
apic_printk(APIC_DEBUG, KERN_CONT "\n");
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index bc552cff257..a65829ac2b9 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -30,7 +30,7 @@
static int numachip_system __read_mostly;
-static struct apic apic_numachip __read_mostly;
+static const struct apic apic_numachip __read_mostly;
static unsigned int get_apic_id(unsigned long x)
{
@@ -199,7 +199,7 @@ static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
return 0;
}
-static struct apic apic_numachip __refconst = {
+static const struct apic apic_numachip __refconst = {
.name = "NumaConnect system",
.probe = numachip_probe,
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9d92e19039f..f7e98a2c0d1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -737,6 +737,72 @@ static unsigned int __cpuinit amd_size_cache(struct cpuinfo_x86 *c,
}
#endif
+static void __cpuinit cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has_invlpg)
+ return;
+
+ tlb_flushall_shift = 5;
+
+ if (c->x86 <= 0x11)
+ tlb_flushall_shift = 4;
+}
+
+static void __cpuinit cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
+{
+ u32 ebx, eax, ecx, edx;
+ u16 mask = 0xfff;
+
+ if (c->x86 < 0xf)
+ return;
+
+ if (c->extended_cpuid_level < 0x80000006)
+ return;
+
+ cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
+
+ tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
+ tlb_lli_4k[ENTRIES] = ebx & mask;
+
+ /*
+ * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
+ * characteristics from the CPUID function 0x80000005 instead.
+ */
+ if (c->x86 == 0xf) {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ mask = 0xff;
+ }
+
+ /* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!((eax >> 16) & mask)) {
+ u32 a, b, c, d;
+
+ cpuid(0x80000005, &a, &b, &c, &d);
+ tlb_lld_2m[ENTRIES] = (a >> 16) & 0xff;
+ } else {
+ tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+ }
+
+ /* a 4M entry uses two 2M entries */
+ tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+
+ /* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
+ if (!(eax & mask)) {
+ /* Erratum 658 */
+ if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
+ tlb_lli_2m[ENTRIES] = 1024;
+ } else {
+ cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
+ tlb_lli_2m[ENTRIES] = eax & 0xff;
+ }
+ } else
+ tlb_lli_2m[ENTRIES] = eax & mask;
+
+ tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+
+ cpu_set_tlb_flushall_shift(c);
+}
+
static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
.c_vendor = "AMD",
.c_ident = { "AuthenticAMD" },
@@ -756,6 +822,7 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
.c_size_cache = amd_size_cache,
#endif
.c_early_init = early_init_amd,
+ .c_detect_tlb = cpu_detect_tlb_amd,
.c_bsp_init = bsp_init_amd,
.c_init = init_amd,
.c_x86_vendor = X86_VENDOR_AMD,
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c97bb7b5a9f..d0e910da16c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -165,10 +165,15 @@ void __init check_bugs(void)
print_cpu_info(&boot_cpu_data);
#endif
check_config();
- check_fpu();
check_hlt();
check_popad();
init_utsname()->machine[1] =
'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
alternative_instructions();
+
+ /*
+ * kernel_fpu_begin/end() in check_fpu() relies on the patched
+ * alternative instructions.
+ */
+ check_fpu();
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a5fbc3c5fcc..7505f7b13e7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -259,23 +259,36 @@ static inline void squash_the_stupid_serial_number(struct cpuinfo_x86 *c)
}
#endif
-static int disable_smep __cpuinitdata;
static __init int setup_disable_smep(char *arg)
{
- disable_smep = 1;
+ setup_clear_cpu_cap(X86_FEATURE_SMEP);
return 1;
}
__setup("nosmep", setup_disable_smep);
-static __cpuinit void setup_smep(struct cpuinfo_x86 *c)
+static __always_inline void setup_smep(struct cpuinfo_x86 *c)
{
- if (cpu_has(c, X86_FEATURE_SMEP)) {
- if (unlikely(disable_smep)) {
- setup_clear_cpu_cap(X86_FEATURE_SMEP);
- clear_in_cr4(X86_CR4_SMEP);
- } else
- set_in_cr4(X86_CR4_SMEP);
- }
+ if (cpu_has(c, X86_FEATURE_SMEP))
+ set_in_cr4(X86_CR4_SMEP);
+}
+
+static __init int setup_disable_smap(char *arg)
+{
+ setup_clear_cpu_cap(X86_FEATURE_SMAP);
+ return 1;
+}
+__setup("nosmap", setup_disable_smap);
+
+static __always_inline void setup_smap(struct cpuinfo_x86 *c)
+{
+ unsigned long eflags;
+
+ /* This should have been cleared long ago */
+ raw_local_save_flags(eflags);
+ BUG_ON(eflags & X86_EFLAGS_AC);
+
+ if (cpu_has(c, X86_FEATURE_SMAP))
+ set_in_cr4(X86_CR4_SMAP);
}
/*
@@ -476,7 +489,7 @@ void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c)
printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
- "tlb_flushall_shift is 0x%x\n",
+ "tlb_flushall_shift: %d\n",
tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
@@ -712,8 +725,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
c->cpu_index = 0;
filter_cpuid_features(c, false);
- setup_smep(c);
-
if (this_cpu->c_bsp_init)
this_cpu->c_bsp_init(c);
}
@@ -798,8 +809,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
c->phys_proc_id = c->initial_apicid;
}
- setup_smep(c);
-
get_model_name(c); /* Default name */
detect_nopl(c);
@@ -864,6 +873,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
/* Disable the PN if appropriate */
squash_the_stupid_serial_number(c);
+ /* Set up SMEP/SMAP */
+ setup_smep(c);
+ setup_smap(c);
+
/*
* The vendor-specific functions might have changed features.
* Now we do "generic changes."
@@ -942,8 +955,7 @@ void __init identify_boot_cpu(void)
#else
vgetcpu_set_mode();
#endif
- if (boot_cpu_data.cpuid_level >= 2)
- cpu_detect_tlb(&boot_cpu_data);
+ cpu_detect_tlb(&boot_cpu_data);
}
void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
@@ -1023,14 +1035,16 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c)
printk(KERN_CONT "%s ", vendor);
if (c->x86_model_id[0])
- printk(KERN_CONT "%s", c->x86_model_id);
+ printk(KERN_CONT "%s", strim(c->x86_model_id));
else
printk(KERN_CONT "%d86", c->x86);
+ printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model);
+
if (c->x86_mask || c->cpuid_level >= 0)
- printk(KERN_CONT " stepping %02x\n", c->x86_mask);
+ printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask);
else
- printk(KERN_CONT "\n");
+ printk(KERN_CONT ")\n");
print_cpu_msr(c);
}
@@ -1113,11 +1127,10 @@ void syscall_init(void)
/* Flags to clear on syscall */
wrmsrl(MSR_SYSCALL_MASK,
- X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
+ X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
+ X86_EFLAGS_IOPL|X86_EFLAGS_AC);
}
-unsigned long kernel_eflags;
-
/*
* Copies of the original ist values from the tss are only accessed during
* debugging, no special alignment required.
@@ -1297,9 +1310,6 @@ void __cpuinit cpu_init(void)
dbg_restore_debug_regs();
fpu_init();
- xsave_init();
-
- raw_local_save_flags(kernel_eflags);
if (is_uv_system())
uv_cpu_init();
@@ -1352,6 +1362,5 @@ void __cpuinit cpu_init(void)
dbg_restore_debug_regs();
fpu_init();
- xsave_init();
}
#endif
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 0a4ce2980a5..198e019a531 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -648,6 +648,10 @@ static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c)
int i, j, n;
unsigned int regs[4];
unsigned char *desc = (unsigned char *)regs;
+
+ if (c->cpuid_level < 2)
+ return;
+
/* Number of times to iterate */
n = cpuid_eax(2) & 0xFF;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index fc4beb39357..ddc72f83933 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -78,6 +78,7 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs)
}
static cpumask_var_t mce_inject_cpumask;
+static DEFINE_MUTEX(mce_inject_mutex);
static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
{
@@ -194,7 +195,11 @@ static void raise_mce(struct mce *m)
put_online_cpus();
} else
#endif
+ {
+ preempt_disable();
raise_local();
+ preempt_enable();
+ }
}
/* Error injection interface */
@@ -225,7 +230,10 @@ static ssize_t mce_write(struct file *filp, const char __user *ubuf,
* so do it a jiffie or two later everywhere.
*/
schedule_timeout(2);
+
+ mutex_lock(&mce_inject_mutex);
raise_mce(&m);
+ mutex_unlock(&mce_inject_mutex);
return usize;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index ed44c8a6585..6a05c1d327a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -28,6 +28,18 @@ extern int mce_ser;
extern struct mce_bank *mce_banks;
+#ifdef CONFIG_X86_MCE_INTEL
+unsigned long mce_intel_adjust_timer(unsigned long interval);
+void mce_intel_cmci_poll(void);
+void mce_intel_hcpu_update(unsigned long cpu);
+#else
+# define mce_intel_adjust_timer mce_adjust_timer_default
+static inline void mce_intel_cmci_poll(void) { }
+static inline void mce_intel_hcpu_update(unsigned long cpu) { }
+#endif
+
+void mce_timer_kick(unsigned long interval);
+
#ifdef CONFIG_ACPI_APEI
int apei_write_mce(struct mce *m);
ssize_t apei_read_mce(struct mce *m, u64 *record_id);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 292d0258311..29e87d3b284 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -83,6 +83,7 @@ static int mce_dont_log_ce __read_mostly;
int mce_cmci_disabled __read_mostly;
int mce_ignore_ce __read_mostly;
int mce_ser __read_mostly;
+int mce_bios_cmci_threshold __read_mostly;
struct mce_bank *mce_banks __read_mostly;
@@ -1266,6 +1267,14 @@ static unsigned long check_interval = 5 * 60; /* 5 minutes */
static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
+static unsigned long mce_adjust_timer_default(unsigned long interval)
+{
+ return interval;
+}
+
+static unsigned long (*mce_adjust_timer)(unsigned long interval) =
+ mce_adjust_timer_default;
+
static void mce_timer_fn(unsigned long data)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
@@ -1276,6 +1285,7 @@ static void mce_timer_fn(unsigned long data)
if (mce_available(__this_cpu_ptr(&cpu_info))) {
machine_check_poll(MCP_TIMESTAMP,
&__get_cpu_var(mce_poll_banks));
+ mce_intel_cmci_poll();
}
/*
@@ -1283,14 +1293,38 @@ static void mce_timer_fn(unsigned long data)
* polling interval, otherwise increase the polling interval.
*/
iv = __this_cpu_read(mce_next_interval);
- if (mce_notify_irq())
+ if (mce_notify_irq()) {
iv = max(iv / 2, (unsigned long) HZ/100);
- else
+ } else {
iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
+ iv = mce_adjust_timer(iv);
+ }
__this_cpu_write(mce_next_interval, iv);
+ /* Might have become 0 after CMCI storm subsided */
+ if (iv) {
+ t->expires = jiffies + iv;
+ add_timer_on(t, smp_processor_id());
+ }
+}
- t->expires = jiffies + iv;
- add_timer_on(t, smp_processor_id());
+/*
+ * Ensure that the timer is firing in @interval from now.
+ */
+void mce_timer_kick(unsigned long interval)
+{
+ struct timer_list *t = &__get_cpu_var(mce_timer);
+ unsigned long when = jiffies + interval;
+ unsigned long iv = __this_cpu_read(mce_next_interval);
+
+ if (timer_pending(t)) {
+ if (time_before(when, t->expires))
+ mod_timer_pinned(t, when);
+ } else {
+ t->expires = round_jiffies(when);
+ add_timer_on(t, smp_processor_id());
+ }
+ if (interval < iv)
+ __this_cpu_write(mce_next_interval, interval);
}
/* Must not be called in IRQ context where del_timer_sync() can deadlock */
@@ -1585,6 +1619,7 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
switch (c->x86_vendor) {
case X86_VENDOR_INTEL:
mce_intel_feature_init(c);
+ mce_adjust_timer = mce_intel_adjust_timer;
break;
case X86_VENDOR_AMD:
mce_amd_feature_init(c);
@@ -1594,23 +1629,28 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
}
}
-static void __mcheck_cpu_init_timer(void)
+static void mce_start_timer(unsigned int cpu, struct timer_list *t)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
- unsigned long iv = check_interval * HZ;
+ unsigned long iv = mce_adjust_timer(check_interval * HZ);
- setup_timer(t, mce_timer_fn, smp_processor_id());
+ __this_cpu_write(mce_next_interval, iv);
- if (mce_ignore_ce)
+ if (mce_ignore_ce || !iv)
return;
- __this_cpu_write(mce_next_interval, iv);
- if (!iv)
- return;
t->expires = round_jiffies(jiffies + iv);
add_timer_on(t, smp_processor_id());
}
+static void __mcheck_cpu_init_timer(void)
+{
+ struct timer_list *t = &__get_cpu_var(mce_timer);
+ unsigned int cpu = smp_processor_id();
+
+ setup_timer(t, mce_timer_fn, cpu);
+ mce_start_timer(cpu, t);
+}
+
/* Handle unconfigured int18 (should never happen) */
static void unexpected_machine_check(struct pt_regs *regs, long error_code)
{
@@ -1907,6 +1947,7 @@ static struct miscdevice mce_chrdev_device = {
* check, or 0 to not wait
* mce=bootlog Log MCEs from before booting. Disabled by default on AMD.
* mce=nobootlog Don't log MCEs from before booting.
+ * mce=bios_cmci_threshold Don't program the CMCI threshold
*/
static int __init mcheck_enable(char *str)
{
@@ -1926,6 +1967,8 @@ static int __init mcheck_enable(char *str)
mce_ignore_ce = 1;
else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog"))
mce_bootlog = (str[0] == 'b');
+ else if (!strcmp(str, "bios_cmci_threshold"))
+ mce_bios_cmci_threshold = 1;
else if (isdigit(str[0])) {
get_option(&str, &tolerant);
if (*str == ',') {
@@ -2166,6 +2209,11 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = {
&mce_cmci_disabled
};
+static struct dev_ext_attribute dev_attr_bios_cmci_threshold = {
+ __ATTR(bios_cmci_threshold, 0444, device_show_int, NULL),
+ &mce_bios_cmci_threshold
+};
+
static struct device_attribute *mce_device_attrs[] = {
&dev_attr_tolerant.attr,
&dev_attr_check_interval.attr,
@@ -2174,6 +2222,7 @@ static struct device_attribute *mce_device_attrs[] = {
&dev_attr_dont_log_ce.attr,
&dev_attr_ignore_ce.attr,
&dev_attr_cmci_disabled.attr,
+ &dev_attr_bios_cmci_threshold.attr,
NULL
};
@@ -2294,38 +2343,33 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
unsigned int cpu = (unsigned long)hcpu;
struct timer_list *t = &per_cpu(mce_timer, cpu);
- switch (action) {
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
mce_device_create(cpu);
if (threshold_cpu_callback)
threshold_cpu_callback(action, cpu);
break;
case CPU_DEAD:
- case CPU_DEAD_FROZEN:
if (threshold_cpu_callback)
threshold_cpu_callback(action, cpu);
mce_device_remove(cpu);
+ mce_intel_hcpu_update(cpu);
break;
case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
- del_timer_sync(t);
smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
+ del_timer_sync(t);
break;
case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
- if (!mce_ignore_ce && check_interval) {
- t->expires = round_jiffies(jiffies +
- per_cpu(mce_next_interval, cpu));
- add_timer_on(t, cpu);
- }
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
+ mce_start_timer(cpu, t);
break;
- case CPU_POST_DEAD:
+ }
+
+ if (action == CPU_POST_DEAD) {
/* intentionally ignoring frozen here */
cmci_rediscover(cpu);
- break;
}
+
return NOTIFY_OK;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 38e49bc95ff..5f88abf07e9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -15,6 +15,8 @@
#include <asm/msr.h>
#include <asm/mce.h>
+#include "mce-internal.h"
+
/*
* Support for Intel Correct Machine Check Interrupts. This allows
* the CPU to raise an interrupt when a corrected machine check happened.
@@ -30,7 +32,22 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
*/
static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
-#define CMCI_THRESHOLD 1
+#define CMCI_THRESHOLD 1
+#define CMCI_POLL_INTERVAL (30 * HZ)
+#define CMCI_STORM_INTERVAL (1 * HZ)
+#define CMCI_STORM_THRESHOLD 15
+
+static DEFINE_PER_CPU(unsigned long, cmci_time_stamp);
+static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt);
+static DEFINE_PER_CPU(unsigned int, cmci_storm_state);
+
+enum {
+ CMCI_STORM_NONE,
+ CMCI_STORM_ACTIVE,
+ CMCI_STORM_SUBSIDED,
+};
+
+static atomic_t cmci_storm_on_cpus;
static int cmci_supported(int *banks)
{
@@ -53,6 +70,93 @@ static int cmci_supported(int *banks)
return !!(cap & MCG_CMCI_P);
}
+void mce_intel_cmci_poll(void)
+{
+ if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
+ return;
+ machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+}
+
+void mce_intel_hcpu_update(unsigned long cpu)
+{
+ if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE)
+ atomic_dec(&cmci_storm_on_cpus);
+
+ per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE;
+}
+
+unsigned long mce_intel_adjust_timer(unsigned long interval)
+{
+ int r;
+
+ if (interval < CMCI_POLL_INTERVAL)
+ return interval;
+
+ switch (__this_cpu_read(cmci_storm_state)) {
+ case CMCI_STORM_ACTIVE:
+ /*
+ * We switch back to interrupt mode once the poll timer has
+ * silenced itself. That means no events recorded and the
+ * timer interval is back to our poll interval.
+ */
+ __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED);
+ r = atomic_sub_return(1, &cmci_storm_on_cpus);
+ if (r == 0)
+ pr_notice("CMCI storm subsided: switching to interrupt mode\n");
+ /* FALLTHROUGH */
+
+ case CMCI_STORM_SUBSIDED:
+ /*
+ * We wait for all cpus to go back to SUBSIDED
+ * state. When that happens we switch back to
+ * interrupt mode.
+ */
+ if (!atomic_read(&cmci_storm_on_cpus)) {
+ __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE);
+ cmci_reenable();
+ cmci_recheck();
+ }
+ return CMCI_POLL_INTERVAL;
+ default:
+ /*
+ * We have shiny weather. Let the poll do whatever it
+ * thinks.
+ */
+ return interval;
+ }
+}
+
+static bool cmci_storm_detect(void)
+{
+ unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
+ unsigned long ts = __this_cpu_read(cmci_time_stamp);
+ unsigned long now = jiffies;
+ int r;
+
+ if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE)
+ return true;
+
+ if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) {
+ cnt++;
+ } else {
+ cnt = 1;
+ __this_cpu_write(cmci_time_stamp, now);
+ }
+ __this_cpu_write(cmci_storm_cnt, cnt);
+
+ if (cnt <= CMCI_STORM_THRESHOLD)
+ return false;
+
+ cmci_clear();
+ __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
+ r = atomic_add_return(1, &cmci_storm_on_cpus);
+ mce_timer_kick(CMCI_POLL_INTERVAL);
+
+ if (r == 1)
+ pr_notice("CMCI storm detected: switching to poll mode\n");
+ return true;
+}
+
/*
* The interrupt handler. This is called on every event.
* Just call the poller directly to log any events.
@@ -61,33 +165,28 @@ static int cmci_supported(int *banks)
*/
static void intel_threshold_interrupt(void)
{
+ if (cmci_storm_detect())
+ return;
machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
mce_notify_irq();
}
-static void print_update(char *type, int *hdr, int num)
-{
- if (*hdr == 0)
- printk(KERN_INFO "CPU %d MCA banks", smp_processor_id());
- *hdr = 1;
- printk(KERN_CONT " %s:%d", type, num);
-}
-
/*
* Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
* on this CPU. Use the algorithm recommended in the SDM to discover shared
* banks.
*/
-static void cmci_discover(int banks, int boot)
+static void cmci_discover(int banks)
{
unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
unsigned long flags;
- int hdr = 0;
int i;
+ int bios_wrong_thresh = 0;
raw_spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
u64 val;
+ int bios_zero_thresh = 0;
if (test_bit(i, owned))
continue;
@@ -96,29 +195,52 @@ static void cmci_discover(int banks, int boot)
/* Already owned by someone else? */
if (val & MCI_CTL2_CMCI_EN) {
- if (test_and_clear_bit(i, owned) && !boot)
- print_update("SHD", &hdr, i);
+ clear_bit(i, owned);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
continue;
}
- val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
- val |= MCI_CTL2_CMCI_EN | CMCI_THRESHOLD;
+ if (!mce_bios_cmci_threshold) {
+ val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
+ val |= CMCI_THRESHOLD;
+ } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) {
+ /*
+ * If bios_cmci_threshold boot option was specified
+ * but the threshold is zero, we'll try to initialize
+ * it to 1.
+ */
+ bios_zero_thresh = 1;
+ val |= CMCI_THRESHOLD;
+ }
+
+ val |= MCI_CTL2_CMCI_EN;
wrmsrl(MSR_IA32_MCx_CTL2(i), val);
rdmsrl(MSR_IA32_MCx_CTL2(i), val);
/* Did the enable bit stick? -- the bank supports CMCI */
if (val & MCI_CTL2_CMCI_EN) {
- if (!test_and_set_bit(i, owned) && !boot)
- print_update("CMCI", &hdr, i);
+ set_bit(i, owned);
__clear_bit(i, __get_cpu_var(mce_poll_banks));
+ /*
+ * We are able to set thresholds for some banks that
+ * had a threshold of 0. This means the BIOS has not
+ * set the thresholds properly or does not work with
+ * this boot option. Note down now and report later.
+ */
+ if (mce_bios_cmci_threshold && bios_zero_thresh &&
+ (val & MCI_CTL2_CMCI_THRESHOLD_MASK))
+ bios_wrong_thresh = 1;
} else {
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
- if (hdr)
- printk(KERN_CONT "\n");
+ if (mce_bios_cmci_threshold && bios_wrong_thresh) {
+ pr_info_once(
+ "bios_cmci_threshold: Some banks do not have valid thresholds set\n");
+ pr_info_once(
+ "bios_cmci_threshold: Make sure your BIOS supports this boot option\n");
+ }
}
/*
@@ -156,7 +278,7 @@ void cmci_clear(void)
continue;
/* Disable CMCI */
rdmsrl(MSR_IA32_MCx_CTL2(i), val);
- val &= ~(MCI_CTL2_CMCI_EN|MCI_CTL2_CMCI_THRESHOLD_MASK);
+ val &= ~MCI_CTL2_CMCI_EN;
wrmsrl(MSR_IA32_MCx_CTL2(i), val);
__clear_bit(i, __get_cpu_var(mce_banks_owned));
}
@@ -186,7 +308,7 @@ void cmci_rediscover(int dying)
continue;
/* Recheck banks in case CPUs don't all have the same */
if (cmci_supported(&banks))
- cmci_discover(banks, 0);
+ cmci_discover(banks);
}
set_cpus_allowed_ptr(current, old);
@@ -200,7 +322,7 @@ void cmci_reenable(void)
{
int banks;
if (cmci_supported(&banks))
- cmci_discover(banks, 0);
+ cmci_discover(banks);
}
static void intel_init_cmci(void)
@@ -211,7 +333,7 @@ static void intel_init_cmci(void)
return;
mce_threshold_vector = intel_threshold_interrupt;
- cmci_discover(banks, 1);
+ cmci_discover(banks);
/*
* For CPU #0 this runs with still disabled APIC, but that's
* ok because only the vector is set up. We still do another
diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl
index c7b3fe2d72e..091972ef49d 100644
--- a/arch/x86/kernel/cpu/mkcapflags.pl
+++ b/arch/x86/kernel/cpu/mkcapflags.pl
@@ -8,7 +8,10 @@
open(IN, "< $in\0") or die "$0: cannot open: $in: $!\n";
open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n";
-print OUT "#include <asm/cpufeature.h>\n\n";
+print OUT "#ifndef _ASM_X86_CPUFEATURE_H\n";
+print OUT "#include <asm/cpufeature.h>\n";
+print OUT "#endif\n";
+print OUT "\n";
print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n";
%features = ();
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 6605a81ba33..8b6defe7eef 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -586,6 +586,8 @@ extern struct event_constraint intel_westmere_pebs_event_constraints[];
extern struct event_constraint intel_snb_pebs_event_constraints[];
+extern struct event_constraint intel_ivb_pebs_event_constraints[];
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 7bfb5bec863..eebd5ffe1bb 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -209,6 +209,15 @@ static int perf_ibs_precise_event(struct perf_event *event, u64 *config)
return -EOPNOTSUPP;
}
+static const struct perf_event_attr ibs_notsupp = {
+ .exclude_user = 1,
+ .exclude_kernel = 1,
+ .exclude_hv = 1,
+ .exclude_idle = 1,
+ .exclude_host = 1,
+ .exclude_guest = 1,
+};
+
static int perf_ibs_init(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -229,6 +238,9 @@ static int perf_ibs_init(struct perf_event *event)
if (event->pmu != &perf_ibs->pmu)
return -ENOENT;
+ if (perf_flags(&event->attr) & perf_flags(&ibs_notsupp))
+ return -EINVAL;
+
if (config & ~perf_ibs->config_mask)
return -EINVAL;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7f2739e03e7..6bca492b854 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
break;
case 28: /* Atom */
+ case 54: /* Cedariew */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2047,7 +2048,6 @@ __init int intel_pmu_init(void)
case 42: /* SandyBridge */
case 45: /* SandyBridge, "Romely-EP" */
x86_add_quirk(intel_sandybridge_quirk);
- case 58: /* IvyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
@@ -2072,6 +2072,29 @@ __init int intel_pmu_init(void)
pr_cont("SandyBridge events, ");
break;
+ case 58: /* IvyBridge */
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+
+ intel_pmu_lbr_init_snb();
+
+ x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+ x86_pmu.extra_regs = intel_snb_extra_regs;
+ /* all extra regs are per-cpu when HT is on */
+ x86_pmu.er_flags |= ERF_HAS_RSP_1;
+ x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+ /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
+ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+ X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
+
+ pr_cont("IvyBridge events, ");
+ break;
+
default:
switch (x86_pmu.version) {
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index e38d97bf425..826054a4f2e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -407,6 +407,20 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_ivb_pebs_event_constraints[] = {
+ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+ INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
+ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint *intel_pebs_constraints(struct perf_event *event)
{
struct event_constraint *c;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 520b4265fcd..da02e9cc375 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
* to have an operational LBR which can freeze
* on PMU interrupt
*/
- if (boot_cpu_data.x86_mask < 10) {
+ if (boot_cpu_data.x86_model == 28
+ && boot_cpu_data.x86_mask < 10) {
pr_cont("LBR disabled due to erratum");
return;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0a5571080e7..99d96a4978b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -661,6 +661,11 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
}
}
+static struct uncore_event_desc snb_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ { /* end: all zeroes */ },
+};
+
static struct attribute *snb_uncore_formats_attr[] = {
&format_attr_event.attr,
&format_attr_umask.attr,
@@ -704,6 +709,7 @@ static struct intel_uncore_type snb_uncore_cbox = {
.constraints = snb_uncore_cbox_constraints,
.ops = &snb_uncore_msr_ops,
.format_group = &snb_uncore_format_group,
+ .event_descs = snb_uncore_events,
};
static struct intel_uncore_type *snb_msr_uncores[] = {
@@ -1944,7 +1950,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp
static struct intel_uncore_box *
uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
- static struct intel_uncore_box *box;
+ struct intel_uncore_box *box;
box = *per_cpu_ptr(pmu->box, cpu);
if (box)
@@ -2341,6 +2347,27 @@ int uncore_pmu_event_init(struct perf_event *event)
return ret;
}
+static ssize_t uncore_get_attr_cpumask(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask);
+
+ buf[n++] = '\n';
+ buf[n] = '\0';
+ return n;
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
+
+static struct attribute *uncore_pmu_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL,
+};
+
+static struct attribute_group uncore_pmu_attr_group = {
+ .attrs = uncore_pmu_attrs,
+};
+
static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
{
int ret;
@@ -2378,8 +2405,8 @@ static void __init uncore_type_exit(struct intel_uncore_type *type)
free_percpu(type->pmus[i].box);
kfree(type->pmus);
type->pmus = NULL;
- kfree(type->attr_groups[1]);
- type->attr_groups[1] = NULL;
+ kfree(type->events_group);
+ type->events_group = NULL;
}
static void __init uncore_types_exit(struct intel_uncore_type **types)
@@ -2431,9 +2458,10 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
for (j = 0; j < i; j++)
attrs[j] = &type->event_descs[j].attr.attr;
- type->attr_groups[1] = events_group;
+ type->events_group = events_group;
}
+ type->pmu_group = &uncore_pmu_attr_group;
type->pmus = pmus;
return 0;
fail:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 5b81c1856aa..e68a4550e95 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -369,10 +369,12 @@ struct intel_uncore_type {
struct intel_uncore_pmu *pmus;
struct intel_uncore_ops *ops;
struct uncore_event_desc *event_descs;
- const struct attribute_group *attr_groups[3];
+ const struct attribute_group *attr_groups[4];
};
-#define format_group attr_groups[0]
+#define pmu_group attr_groups[0]
+#define format_group attr_groups[1]
+#define events_group attr_groups[2]
struct intel_uncore_ops {
void (*init_box)(struct intel_uncore_box *);
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 8022c668148..fbd89556229 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -140,10 +140,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
static void *c_start(struct seq_file *m, loff_t *pos)
{
- if (*pos == 0) /* just in case, cpu 0 is not the first */
- *pos = cpumask_first(cpu_online_mask);
- else
- *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
if ((*pos) < nr_cpu_ids)
return &cpu_data(*pos);
return NULL;
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 39472dd2323..60c78917190 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -199,12 +199,14 @@ static int __init cpuid_init(void)
goto out_chrdev;
}
cpuid_class->devnode = cpuid_devnode;
+ get_online_cpus();
for_each_online_cpu(i) {
err = cpuid_device_create(i);
if (err != 0)
goto out_class;
}
register_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ put_online_cpus();
err = 0;
goto out;
@@ -214,6 +216,7 @@ out_class:
for_each_online_cpu(i) {
cpuid_device_destroy(i);
}
+ put_online_cpus();
class_destroy(cpuid_class);
out_chrdev:
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
@@ -225,11 +228,13 @@ static void __exit cpuid_exit(void)
{
int cpu = 0;
+ get_online_cpus();
for_each_online_cpu(cpu)
cpuid_device_destroy(cpu);
class_destroy(cpuid_class);
__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
+ put_online_cpus();
}
module_init(cpuid_init);
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 3ae2ced4a87..b1581527a23 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -342,6 +342,47 @@ const struct irq_domain_ops ioapic_irq_domain_ops = {
.xlate = ioapic_xlate,
};
+static void dt_add_ioapic_domain(unsigned int ioapic_num,
+ struct device_node *np)
+{
+ struct irq_domain *id;
+ struct mp_ioapic_gsi *gsi_cfg;
+ int ret;
+ int num;
+
+ gsi_cfg = mp_ioapic_gsi_routing(ioapic_num);
+ num = gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1;
+
+ id = irq_domain_add_linear(np, num, &ioapic_irq_domain_ops,
+ (void *)ioapic_num);
+ BUG_ON(!id);
+ if (gsi_cfg->gsi_base == 0) {
+ /*
+ * The first NR_IRQS_LEGACY irq descs are allocated in
+ * early_irq_init() and need just a mapping. The
+ * remaining irqs need both. All of them are preallocated
+ * and assigned so we can keep the 1:1 mapping which the ioapic
+ * is having.
+ */
+ ret = irq_domain_associate_many(id, 0, 0, NR_IRQS_LEGACY);
+ if (ret)
+ pr_err("Error mapping legacy IRQs: %d\n", ret);
+
+ if (num > NR_IRQS_LEGACY) {
+ ret = irq_create_strict_mappings(id, NR_IRQS_LEGACY,
+ NR_IRQS_LEGACY, num - NR_IRQS_LEGACY);
+ if (ret)
+ pr_err("Error creating mapping for the "
+ "remaining IRQs: %d\n", ret);
+ }
+ irq_set_default_host(id);
+ } else {
+ ret = irq_create_strict_mappings(id, gsi_cfg->gsi_base, 0, num);
+ if (ret)
+ pr_err("Error creating IRQ mapping: %d\n", ret);
+ }
+}
+
static void __init ioapic_add_ofnode(struct device_node *np)
{
struct resource r;
@@ -356,15 +397,7 @@ static void __init ioapic_add_ofnode(struct device_node *np)
for (i = 0; i < nr_ioapics; i++) {
if (r.start == mpc_ioapic_addr(i)) {
- struct irq_domain *id;
- struct mp_ioapic_gsi *gsi_cfg;
-
- gsi_cfg = mp_ioapic_gsi_routing(i);
-
- id = irq_domain_add_legacy(np, 32, gsi_cfg->gsi_base, 0,
- &ioapic_irq_domain_ops,
- (void*)i);
- BUG_ON(!id);
+ dt_add_ioapic_domain(i, np);
return;
}
}
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 623f2883747..0750e3ba87c 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -57,6 +57,7 @@
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
+#include <asm/smap.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
@@ -407,7 +408,9 @@ sysenter_past_esp:
*/
cmpl $__PAGE_OFFSET-3,%ebp
jae syscall_fault
+ ASM_STAC
1: movl (%ebp),%ebp
+ ASM_CLAC
movl %ebp,PT_EBP(%esp)
_ASM_EXTABLE(1b,syscall_fault)
@@ -488,6 +491,7 @@ ENDPROC(ia32_sysenter_target)
# system call handler stub
ENTRY(system_call)
RING0_INT_FRAME # can't unwind into user space anyway
+ ASM_CLAC
pushl_cfi %eax # save orig_eax
SAVE_ALL
GET_THREAD_INFO(%ebp)
@@ -670,6 +674,7 @@ END(syscall_exit_work)
RING0_INT_FRAME # can't unwind into user space anyway
syscall_fault:
+ ASM_CLAC
GET_THREAD_INFO(%ebp)
movl $-EFAULT,PT_EAX(%esp)
jmp resume_userspace
@@ -825,6 +830,7 @@ END(interrupt)
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
+ ASM_CLAC
addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */
SAVE_ALL
TRACE_IRQS_OFF
@@ -841,6 +847,7 @@ ENDPROC(common_interrupt)
#define BUILD_INTERRUPT3(name, nr, fn) \
ENTRY(name) \
RING0_INT_FRAME; \
+ ASM_CLAC; \
pushl_cfi $~(nr); \
SAVE_ALL; \
TRACE_IRQS_OFF \
@@ -857,6 +864,7 @@ ENDPROC(name)
ENTRY(coprocessor_error)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi $do_coprocessor_error
jmp error_code
@@ -865,6 +873,7 @@ END(coprocessor_error)
ENTRY(simd_coprocessor_error)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
#ifdef CONFIG_X86_INVD_BUG
/* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
@@ -886,6 +895,7 @@ END(simd_coprocessor_error)
ENTRY(device_not_available)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $-1 # mark this as an int
pushl_cfi $do_device_not_available
jmp error_code
@@ -906,6 +916,7 @@ END(native_irq_enable_sysexit)
ENTRY(overflow)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi $do_overflow
jmp error_code
@@ -914,6 +925,7 @@ END(overflow)
ENTRY(bounds)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi $do_bounds
jmp error_code
@@ -922,6 +934,7 @@ END(bounds)
ENTRY(invalid_op)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi $do_invalid_op
jmp error_code
@@ -930,6 +943,7 @@ END(invalid_op)
ENTRY(coprocessor_segment_overrun)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi $do_coprocessor_segment_overrun
jmp error_code
@@ -938,6 +952,7 @@ END(coprocessor_segment_overrun)
ENTRY(invalid_TSS)
RING0_EC_FRAME
+ ASM_CLAC
pushl_cfi $do_invalid_TSS
jmp error_code
CFI_ENDPROC
@@ -945,6 +960,7 @@ END(invalid_TSS)
ENTRY(segment_not_present)
RING0_EC_FRAME
+ ASM_CLAC
pushl_cfi $do_segment_not_present
jmp error_code
CFI_ENDPROC
@@ -952,6 +968,7 @@ END(segment_not_present)
ENTRY(stack_segment)
RING0_EC_FRAME
+ ASM_CLAC
pushl_cfi $do_stack_segment
jmp error_code
CFI_ENDPROC
@@ -959,6 +976,7 @@ END(stack_segment)
ENTRY(alignment_check)
RING0_EC_FRAME
+ ASM_CLAC
pushl_cfi $do_alignment_check
jmp error_code
CFI_ENDPROC
@@ -966,6 +984,7 @@ END(alignment_check)
ENTRY(divide_error)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0 # no error code
pushl_cfi $do_divide_error
jmp error_code
@@ -975,6 +994,7 @@ END(divide_error)
#ifdef CONFIG_X86_MCE
ENTRY(machine_check)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi machine_check_vector
jmp error_code
@@ -984,6 +1004,7 @@ END(machine_check)
ENTRY(spurious_interrupt_bug)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $0
pushl_cfi $do_spurious_interrupt_bug
jmp error_code
@@ -1109,17 +1130,21 @@ ENTRY(ftrace_caller)
pushl %eax
pushl %ecx
pushl %edx
- movl 0xc(%esp), %eax
+ pushl $0 /* Pass NULL as regs pointer */
+ movl 4*4(%esp), %eax
movl 0x4(%ebp), %edx
+ leal function_trace_op, %ecx
subl $MCOUNT_INSN_SIZE, %eax
.globl ftrace_call
ftrace_call:
call ftrace_stub
+ addl $4,%esp /* skip NULL pointer */
popl %edx
popl %ecx
popl %eax
+ftrace_ret:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
.globl ftrace_graph_call
ftrace_graph_call:
@@ -1131,6 +1156,71 @@ ftrace_stub:
ret
END(ftrace_caller)
+ENTRY(ftrace_regs_caller)
+ pushf /* push flags before compare (in cs location) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /*
+ * i386 does not save SS and ESP when coming from kernel.
+ * Instead, to get sp, &regs->sp is used (see ptrace.h).
+ * Unfortunately, that means eflags must be at the same location
+ * as the current return ip is. We move the return ip into the
+ * ip location, and move flags into the return ip location.
+ */
+ pushl 4(%esp) /* save return ip into ip slot */
+
+ pushl $0 /* Load 0 into orig_ax */
+ pushl %gs
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+
+ movl 13*4(%esp), %eax /* Get the saved flags */
+ movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */
+ /* clobbering return ip */
+ movl $__KERNEL_CS,13*4(%esp)
+
+ movl 12*4(%esp), %eax /* Load ip (1st parameter) */
+ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */
+ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */
+ leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */
+ pushl %esp /* Save pt_regs as 4th parameter */
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ addl $4, %esp /* Skip pt_regs */
+ movl 14*4(%esp), %eax /* Move flags back into cs */
+ movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */
+ movl 12*4(%esp), %eax /* Get return ip from regs->ip */
+ movl %eax, 14*4(%esp) /* Put return ip back for ret */
+
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+ popl %ds
+ popl %es
+ popl %fs
+ popl %gs
+ addl $8, %esp /* Skip orig_ax and ip */
+ popf /* Pop flags at end (no addl to corrupt flags) */
+ jmp ftrace_ret
+
+ftrace_restore_flags:
+ popf
+ jmp ftrace_stub
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(mcount)
@@ -1171,9 +1261,6 @@ END(mcount)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
pushl %eax
pushl %ecx
pushl %edx
@@ -1207,6 +1294,7 @@ return_to_handler:
ENTRY(page_fault)
RING0_EC_FRAME
+ ASM_CLAC
pushl_cfi $do_page_fault
ALIGN
error_code:
@@ -1279,6 +1367,7 @@ END(page_fault)
ENTRY(debug)
RING0_INT_FRAME
+ ASM_CLAC
cmpl $ia32_sysenter_target,(%esp)
jne debug_stack_correct
FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
@@ -1303,6 +1392,7 @@ END(debug)
*/
ENTRY(nmi)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi %eax
movl %ss, %eax
cmpw $__ESPFIX_SS, %ax
@@ -1373,6 +1463,7 @@ END(nmi)
ENTRY(int3)
RING0_INT_FRAME
+ ASM_CLAC
pushl_cfi $-1 # mark this as an int
SAVE_ALL
TRACE_IRQS_OFF
@@ -1393,6 +1484,7 @@ END(general_protection)
#ifdef CONFIG_KVM_GUEST
ENTRY(async_page_fault)
RING0_EC_FRAME
+ ASM_CLAC
pushl_cfi $do_async_page_fault
jmp error_code
CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 69babd8c834..44531acd9a8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -56,6 +56,8 @@
#include <asm/ftrace.h>
#include <asm/percpu.h>
#include <asm/asm.h>
+#include <asm/rcu.h>
+#include <asm/smap.h>
#include <linux/err.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
@@ -68,25 +70,51 @@
.section .entry.text, "ax"
#ifdef CONFIG_FUNCTION_TRACER
+
+#ifdef CC_USING_FENTRY
+# define function_hook __fentry__
+#else
+# define function_hook mcount
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
-ENTRY(mcount)
+
+ENTRY(function_hook)
retq
-END(mcount)
+END(function_hook)
+
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+ MCOUNT_SAVE_FRAME \skip
+
+ /* Load the ftrace_ops into the 3rd parameter */
+ leaq function_trace_op, %rdx
+
+ /* Load ip into the first parameter */
+ movq RIP(%rsp), %rdi
+ subq $MCOUNT_INSN_SIZE, %rdi
+ /* Load the parent_ip into the second parameter */
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
+ movq 8(%rbp), %rsi
+#endif
+.endm
ENTRY(ftrace_caller)
+ /* Check if tracing was disabled (quick check) */
cmpl $0, function_trace_stop
jne ftrace_stub
- MCOUNT_SAVE_FRAME
-
- movq 0x38(%rsp), %rdi
- movq 8(%rbp), %rsi
- subq $MCOUNT_INSN_SIZE, %rdi
+ ftrace_caller_setup
+ /* regs go into 4th parameter (but make it NULL) */
+ movq $0, %rcx
GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
+ftrace_return:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
GLOBAL(ftrace_graph_call)
@@ -97,8 +125,78 @@ GLOBAL(ftrace_stub)
retq
END(ftrace_caller)
+ENTRY(ftrace_regs_caller)
+ /* Save the current flags before compare (in SS location)*/
+ pushfq
+
+ /* Check if tracing was disabled (quick check) */
+ cmpl $0, function_trace_stop
+ jne ftrace_restore_flags
+
+ /* skip=8 to skip flags saved in SS */
+ ftrace_caller_setup 8
+
+ /* Save the rest of pt_regs */
+ movq %r15, R15(%rsp)
+ movq %r14, R14(%rsp)
+ movq %r13, R13(%rsp)
+ movq %r12, R12(%rsp)
+ movq %r11, R11(%rsp)
+ movq %r10, R10(%rsp)
+ movq %rbp, RBP(%rsp)
+ movq %rbx, RBX(%rsp)
+ /* Copy saved flags */
+ movq SS(%rsp), %rcx
+ movq %rcx, EFLAGS(%rsp)
+ /* Kernel segments */
+ movq $__KERNEL_DS, %rcx
+ movq %rcx, SS(%rsp)
+ movq $__KERNEL_CS, %rcx
+ movq %rcx, CS(%rsp)
+ /* Stack - skipping return address */
+ leaq SS+16(%rsp), %rcx
+ movq %rcx, RSP(%rsp)
+
+ /* regs go into 4th parameter */
+ leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+ call ftrace_stub
+
+ /* Copy flags back to SS, to restore them */
+ movq EFLAGS(%rsp), %rax
+ movq %rax, SS(%rsp)
+
+ /* Handlers can change the RIP */
+ movq RIP(%rsp), %rax
+ movq %rax, SS+8(%rsp)
+
+ /* restore the rest of pt_regs */
+ movq R15(%rsp), %r15
+ movq R14(%rsp), %r14
+ movq R13(%rsp), %r13
+ movq R12(%rsp), %r12
+ movq R10(%rsp), %r10
+ movq RBP(%rsp), %rbp
+ movq RBX(%rsp), %rbx
+
+ /* skip=8 to skip flags saved in SS */
+ MCOUNT_RESTORE_FRAME 8
+
+ /* Restore flags */
+ popfq
+
+ jmp ftrace_return
+ftrace_restore_flags:
+ popfq
+ jmp ftrace_stub
+
+END(ftrace_regs_caller)
+
+
#else /* ! CONFIG_DYNAMIC_FTRACE */
-ENTRY(mcount)
+
+ENTRY(function_hook)
cmpl $0, function_trace_stop
jne ftrace_stub
@@ -119,8 +217,12 @@ GLOBAL(ftrace_stub)
trace:
MCOUNT_SAVE_FRAME
- movq 0x38(%rsp), %rdi
+ movq RIP(%rsp), %rdi
+#ifdef CC_USING_FENTRY
+ movq SS+16(%rsp), %rsi
+#else
movq 8(%rbp), %rsi
+#endif
subq $MCOUNT_INSN_SIZE, %rdi
call *ftrace_trace_function
@@ -128,20 +230,22 @@ trace:
MCOUNT_RESTORE_FRAME
jmp ftrace_stub
-END(mcount)
+END(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- cmpl $0, function_trace_stop
- jne ftrace_stub
-
MCOUNT_SAVE_FRAME
+#ifdef CC_USING_FENTRY
+ leaq SS+16(%rsp), %rdi
+ movq $0, %rdx /* No framepointers needed */
+#else
leaq 8(%rbp), %rdi
- movq 0x38(%rsp), %rsi
movq (%rbp), %rdx
+#endif
+ movq RIP(%rsp), %rsi
subq $MCOUNT_INSN_SIZE, %rsi
call prepare_ftrace_return
@@ -342,15 +446,15 @@ ENDPROC(native_usergs_sysret64)
.macro SAVE_ARGS_IRQ
cld
/* start from rbp in pt_regs and jump over */
- movq_cfi rdi, RDI-RBP
- movq_cfi rsi, RSI-RBP
- movq_cfi rdx, RDX-RBP
- movq_cfi rcx, RCX-RBP
- movq_cfi rax, RAX-RBP
- movq_cfi r8, R8-RBP
- movq_cfi r9, R9-RBP
- movq_cfi r10, R10-RBP
- movq_cfi r11, R11-RBP
+ movq_cfi rdi, (RDI-RBP)
+ movq_cfi rsi, (RSI-RBP)
+ movq_cfi rdx, (RDX-RBP)
+ movq_cfi rcx, (RCX-RBP)
+ movq_cfi rax, (RAX-RBP)
+ movq_cfi r8, (R8-RBP)
+ movq_cfi r9, (R9-RBP)
+ movq_cfi r10, (R10-RBP)
+ movq_cfi r11, (R11-RBP)
/* Save rbp so that we can unwind from get_irq_regs() */
movq_cfi rbp, 0
@@ -384,7 +488,7 @@ ENDPROC(native_usergs_sysret64)
.endm
ENTRY(save_rest)
- PARTIAL_FRAME 1 REST_SKIP+8
+ PARTIAL_FRAME 1 (REST_SKIP+8)
movq 5*8+16(%rsp), %r11 /* save return address */
movq_cfi rbx, RBX+16
movq_cfi rbp, RBP+16
@@ -440,7 +544,7 @@ ENTRY(ret_from_fork)
LOCK ; btr $TIF_FORK,TI_flags(%r8)
- pushq_cfi kernel_eflags(%rip)
+ pushq_cfi $0x0002
popfq_cfi # reset kernel eflags
call schedule_tail # rdi: 'prev' task parameter
@@ -465,7 +569,8 @@ END(ret_from_fork)
* System call entry. Up to 6 arguments in registers are supported.
*
* SYSCALL does not save anything on the stack and does not change the
- * stack pointer.
+ * stack pointer. However, it does mask the flags register for us, so
+ * CLD and CLAC are not needed.
*/
/*
@@ -565,7 +670,7 @@ sysret_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
jmp sysret_check
@@ -678,7 +783,7 @@ int_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
@@ -884,6 +989,7 @@ END(interrupt)
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
+ ASM_CLAC
XCPT_FRAME
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
@@ -974,7 +1080,7 @@ retint_careful:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_NONE)
pushq_cfi %rdi
- call schedule
+ SCHEDULE_USER
popq_cfi %rdi
GET_THREAD_INFO(%rcx)
DISABLE_INTERRUPTS(CLBR_NONE)
@@ -1023,6 +1129,7 @@ END(common_interrupt)
*/
.macro apicinterrupt num sym do_sym
ENTRY(\sym)
+ ASM_CLAC
INTR_FRAME
pushq_cfi $~(\num)
.Lcommon_\sym:
@@ -1077,6 +1184,7 @@ apicinterrupt IRQ_WORK_VECTOR \
*/
.macro zeroentry sym do_sym
ENTRY(\sym)
+ ASM_CLAC
INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
@@ -1094,6 +1202,7 @@ END(\sym)
.macro paranoidzeroentry sym do_sym
ENTRY(\sym)
+ ASM_CLAC
INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
@@ -1112,6 +1221,7 @@ END(\sym)
#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
.macro paranoidzeroentry_ist sym do_sym ist
ENTRY(\sym)
+ ASM_CLAC
INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
@@ -1131,6 +1241,7 @@ END(\sym)
.macro errorentry sym do_sym
ENTRY(\sym)
+ ASM_CLAC
XCPT_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $ORIG_RAX-R15, %rsp
@@ -1149,6 +1260,7 @@ END(\sym)
/* error code is on the stack already */
.macro paranoiderrorentry sym do_sym
ENTRY(\sym)
+ ASM_CLAC
XCPT_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $ORIG_RAX-R15, %rsp
@@ -1449,7 +1561,7 @@ paranoid_userspace:
paranoid_schedule:
TRACE_IRQS_ON
ENABLE_INTERRUPTS(CLBR_ANY)
- call schedule
+ SCHEDULE_USER
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
jmp paranoid_userspace
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c3a7cb4bf6e..1d414029f1d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -206,6 +206,21 @@ static int
ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
unsigned const char *new_code);
+/*
+ * Should never be called:
+ * As it is only called by __ftrace_replace_code() which is called by
+ * ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
+ * which is called to turn mcount into nops or nops into function calls
+ * but not to convert a function from not using regs to one that uses
+ * regs, which ftrace_modify_call() is for.
+ */
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+ unsigned long addr)
+{
+ WARN_ON(1);
+ return -EINVAL;
+}
+
int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
@@ -220,6 +235,14 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
ret = ftrace_modify_code(ip, old, new);
+ /* Also update the regs callback function */
+ if (!ret) {
+ ip = (unsigned long)(&ftrace_regs_call);
+ memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = ftrace_modify_code(ip, old, new);
+ }
+
atomic_dec(&modifying_ftrace_code);
return ret;
@@ -299,6 +322,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
return add_break(rec->ip, old);
}
+/*
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ */
+static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_REGS)
+ return (unsigned long)FTRACE_REGS_ADDR;
+ else
+ return (unsigned long)FTRACE_ADDR;
+}
+
+/*
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ */
+static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
+{
+ if (rec->flags & FTRACE_FL_REGS_EN)
+ return (unsigned long)FTRACE_REGS_ADDR;
+ else
+ return (unsigned long)FTRACE_ADDR;
+}
+
static int add_breakpoints(struct dyn_ftrace *rec, int enable)
{
unsigned long ftrace_addr;
@@ -306,7 +355,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
ret = ftrace_test_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
@@ -316,6 +365,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
/* converting nop to call */
return add_brk_on_nop(rec);
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
+ ftrace_addr = get_ftrace_old_addr(rec);
+ /* fall through */
case FTRACE_UPDATE_MAKE_NOP:
/* converting a call to a nop */
return add_brk_on_call(rec, ftrace_addr);
@@ -360,13 +413,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
* If not, don't touch the breakpoint, we make just create
* a disaster.
*/
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
+ nop = ftrace_call_replace(ip, ftrace_addr);
+
+ if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
+ goto update;
+
+ /* Check both ftrace_addr and ftrace_old_addr */
+ ftrace_addr = get_ftrace_old_addr(rec);
nop = ftrace_call_replace(ip, ftrace_addr);
if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
return -EINVAL;
}
+ update:
return probe_kernel_write((void *)ip, &nop[0], 1);
}
@@ -405,12 +466,14 @@ static int add_update(struct dyn_ftrace *rec, int enable)
ret = ftrace_test_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
return add_update_call(rec, ftrace_addr);
@@ -455,12 +518,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable)
ret = ftrace_update_record(rec, enable);
- ftrace_addr = (unsigned long)FTRACE_ADDR;
+ ftrace_addr = get_ftrace_addr(rec);
switch (ret) {
case FTRACE_UPDATE_IGNORE:
return 0;
+ case FTRACE_UPDATE_MODIFY_CALL_REGS:
+ case FTRACE_UPDATE_MODIFY_CALL:
case FTRACE_UPDATE_MAKE_CALL:
/* converting nop to call */
return finish_update_call(rec, ftrace_addr);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index d42ab17b739..957a47aec64 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -287,27 +287,28 @@ ENTRY(startup_32_smp)
leal -__PAGE_OFFSET(%ecx),%esp
default_entry:
-
/*
* New page tables may be in 4Mbyte page mode and may
* be using the global pages.
*
* NOTE! If we are on a 486 we may have no cr4 at all!
- * So we do not try to touch it unless we really have
- * some bits in it to set. This won't work if the BSP
- * implements cr4 but this AP does not -- very unlikely
- * but be warned! The same applies to the pse feature
- * if not equally supported. --macro
- *
- * NOTE! We have to correct for the fact that we're
- * not yet offset PAGE_OFFSET..
+ * Specifically, cr4 exists if and only if CPUID exists,
+ * which in turn exists if and only if EFLAGS.ID exists.
*/
-#define cr4_bits pa(mmu_cr4_features)
- movl cr4_bits,%edx
- andl %edx,%edx
- jz 6f
- movl %cr4,%eax # Turn on paging options (PSE,PAE,..)
- orl %edx,%eax
+ movl $X86_EFLAGS_ID,%ecx
+ pushl %ecx
+ popfl
+ pushfl
+ popl %eax
+ pushl $0
+ popfl
+ pushfl
+ popl %edx
+ xorl %edx,%eax
+ testl %ecx,%eax
+ jz 6f # No ID flag = no CPUID = no CR4
+
+ movl pa(mmu_cr4_features),%eax
movl %eax,%cr4
testb $X86_CR4_PAE, %al # check if PAE is enabled
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f250431fb50..675a0501244 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -19,24 +19,17 @@
#include <asm/fpu-internal.h>
#include <asm/user.h>
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-#else
-# define save_i387_xstate_ia32 save_i387_xstate
-# define restore_i387_xstate_ia32 restore_i387_xstate
-# define _fpstate_ia32 _fpstate
-# define _xstate_ia32 _xstate
-# define sig_xstate_ia32_size sig_xstate_size
-# define fx_sw_reserved_ia32 fx_sw_reserved
-# define user_i387_ia32_struct user_i387_struct
-# define user32_fxsr_struct user_fxsr_struct
-#endif
-
/*
* Were we in an interrupt that interrupted kernel mode?
*
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * For now, with eagerfpu we will return interrupted kernel FPU
+ * state as not-idle. TBD: Ideally we can change the return value
+ * to something like __thread_has_fpu(current). But we need to
+ * be careful of doing __thread_clear_has_fpu() before saving
+ * the FPU etc for supporting nested uses etc. For now, take
+ * the simple route!
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
* pair does nothing at all: the thread must not have fpu (so
* that we don't try to save the FPU state), and TS must
* be set (so that the clts/stts pair does nothing that is
@@ -44,6 +37,9 @@
*/
static inline bool interrupted_kernel_fpu_idle(void)
{
+ if (use_eager_fpu())
+ return 0;
+
return !__thread_has_fpu(current) &&
(read_cr0() & X86_CR0_TS);
}
@@ -77,29 +73,29 @@ bool irq_fpu_usable(void)
}
EXPORT_SYMBOL(irq_fpu_usable);
-void kernel_fpu_begin(void)
+void __kernel_fpu_begin(void)
{
struct task_struct *me = current;
- WARN_ON_ONCE(!irq_fpu_usable());
- preempt_disable();
if (__thread_has_fpu(me)) {
__save_init_fpu(me);
__thread_clear_has_fpu(me);
- /* We do 'stts()' in kernel_fpu_end() */
- } else {
+ /* We do 'stts()' in __kernel_fpu_end() */
+ } else if (!use_eager_fpu()) {
this_cpu_write(fpu_owner_task, NULL);
clts();
}
}
-EXPORT_SYMBOL(kernel_fpu_begin);
+EXPORT_SYMBOL(__kernel_fpu_begin);
-void kernel_fpu_end(void)
+void __kernel_fpu_end(void)
{
- stts();
- preempt_enable();
+ if (use_eager_fpu())
+ math_state_restore();
+ else
+ stts();
}
-EXPORT_SYMBOL(kernel_fpu_end);
+EXPORT_SYMBOL(__kernel_fpu_end);
void unlazy_fpu(struct task_struct *tsk)
{
@@ -113,23 +109,15 @@ void unlazy_fpu(struct task_struct *tsk)
}
EXPORT_SYMBOL(unlazy_fpu);
-#ifdef CONFIG_MATH_EMULATION
-# define HAVE_HWFP (boot_cpu_data.hard_math)
-#else
-# define HAVE_HWFP 1
-#endif
-
-static unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
unsigned int xstate_size;
EXPORT_SYMBOL_GPL(xstate_size);
-unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
static struct i387_fxsave_struct fx_scratch __cpuinitdata;
static void __cpuinit mxcsr_feature_mask_init(void)
{
unsigned long mask = 0;
- clts();
if (cpu_has_fxsr) {
memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
asm volatile("fxsave %0" : : "m" (fx_scratch));
@@ -138,7 +126,6 @@ static void __cpuinit mxcsr_feature_mask_init(void)
mask = 0x0000ffbf;
}
mxcsr_feature_mask &= mask;
- stts();
}
static void __cpuinit init_thread_xstate(void)
@@ -192,9 +179,8 @@ void __cpuinit fpu_init(void)
init_thread_xstate();
mxcsr_feature_mask_init();
- /* clean state in init */
- current_thread_info()->status = 0;
- clear_used_math();
+ xsave_init();
+ eager_fpu_init();
}
void fpu_finit(struct fpu *fpu)
@@ -205,12 +191,7 @@ void fpu_finit(struct fpu *fpu)
}
if (cpu_has_fxsr) {
- struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
- memset(fx, 0, xstate_size);
- fx->cwd = 0x37f;
- if (cpu_has_xmm)
- fx->mxcsr = MXCSR_DEFAULT;
+ fx_finit(&fpu->state->fxsave);
} else {
struct i387_fsave_struct *fp = &fpu->state->fsave;
memset(fp, 0, xstate_size);
@@ -454,7 +435,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
* FXSR floating point environment conversions.
*/
-static void
+void
convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
{
struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -491,8 +472,8 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
memcpy(&to[i], &from[i], sizeof(to[0]));
}
-static void convert_to_fxsr(struct task_struct *tsk,
- const struct user_i387_ia32_struct *env)
+void convert_to_fxsr(struct task_struct *tsk,
+ const struct user_i387_ia32_struct *env)
{
struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -589,223 +570,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
}
/*
- * Signal frame handlers.
- */
-
-static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
- struct task_struct *tsk = current;
- struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave;
-
- fp->status = fp->swd;
- if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct)))
- return -1;
- return 1;
-}
-
-static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
-{
- struct task_struct *tsk = current;
- struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
- struct user_i387_ia32_struct env;
- int err = 0;
-
- convert_from_fxsr(&env, tsk);
- if (__copy_to_user(buf, &env, sizeof(env)))
- return -1;
-
- err |= __put_user(fx->swd, &buf->status);
- err |= __put_user(X86_FXSR_MAGIC, &buf->magic);
- if (err)
- return -1;
-
- if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size))
- return -1;
- return 1;
-}
-
-static int save_i387_xsave(void __user *buf)
-{
- struct task_struct *tsk = current;
- struct _fpstate_ia32 __user *fx = buf;
- int err = 0;
-
-
- sanitize_i387_state(tsk);
-
- /*
- * For legacy compatible, we always set FP/SSE bits in the bit
- * vector while saving the state to the user context.
- * This will enable us capturing any changes(during sigreturn) to
- * the FP/SSE bits by the legacy applications which don't touch
- * xstate_bv in the xsave header.
- *
- * xsave aware applications can change the xstate_bv in the xsave
- * header as well as change any contents in the memory layout.
- * xrestore as part of sigreturn will capture all the changes.
- */
- tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
- if (save_i387_fxsave(fx) < 0)
- return -1;
-
- err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32,
- sizeof(struct _fpx_sw_bytes));
- err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *) (buf + sig_xstate_ia32_size
- - FP_XSTATE_MAGIC2_SIZE));
- if (err)
- return -1;
-
- return 1;
-}
-
-int save_i387_xstate_ia32(void __user *buf)
-{
- struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
- struct task_struct *tsk = current;
-
- if (!used_math())
- return 0;
-
- if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size))
- return -EACCES;
- /*
- * This will cause a "finit" to be triggered by the next
- * attempted FPU operation by the 'current' process.
- */
- clear_used_math();
-
- if (!HAVE_HWFP) {
- return fpregs_soft_get(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, fp) ? -1 : 1;
- }
-
- unlazy_fpu(tsk);
-
- if (cpu_has_xsave)
- return save_i387_xsave(fp);
- if (cpu_has_fxsr)
- return save_i387_fxsave(fp);
- else
- return save_i387_fsave(fp);
-}
-
-static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
- struct task_struct *tsk = current;
-
- return __copy_from_user(&tsk->thread.fpu.state->fsave, buf,
- sizeof(struct i387_fsave_struct));
-}
-
-static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf,
- unsigned int size)
-{
- struct task_struct *tsk = current;
- struct user_i387_ia32_struct env;
- int err;
-
- err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0],
- size);
- /* mxcsr reserved bits must be masked to zero for security reasons */
- tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
- if (err || __copy_from_user(&env, buf, sizeof(env)))
- return 1;
- convert_to_fxsr(tsk, &env);
-
- return 0;
-}
-
-static int restore_i387_xsave(void __user *buf)
-{
- struct _fpx_sw_bytes fx_sw_user;
- struct _fpstate_ia32 __user *fx_user =
- ((struct _fpstate_ia32 __user *) buf);
- struct i387_fxsave_struct __user *fx =
- (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0];
- struct xsave_hdr_struct *xsave_hdr =
- &current->thread.fpu.state->xsave.xsave_hdr;
- u64 mask;
- int err;
-
- if (check_for_xstate(fx, buf, &fx_sw_user))
- goto fx_only;
-
- mask = fx_sw_user.xstate_bv;
-
- err = restore_i387_fxsave(buf, fx_sw_user.xstate_size);
-
- xsave_hdr->xstate_bv &= pcntxt_mask;
- /*
- * These bits must be zero.
- */
- xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
-
- /*
- * Init the state that is not present in the memory layout
- * and enabled by the OS.
- */
- mask = ~(pcntxt_mask & ~mask);
- xsave_hdr->xstate_bv &= mask;
-
- return err;
-fx_only:
- /*
- * Couldn't find the extended state information in the memory
- * layout. Restore the FP/SSE and init the other extended state
- * enabled by the OS.
- */
- xsave_hdr->xstate_bv = XSTATE_FPSSE;
- return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct));
-}
-
-int restore_i387_xstate_ia32(void __user *buf)
-{
- int err;
- struct task_struct *tsk = current;
- struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
-
- if (HAVE_HWFP)
- clear_fpu(tsk);
-
- if (!buf) {
- if (used_math()) {
- clear_fpu(tsk);
- clear_used_math();
- }
-
- return 0;
- } else
- if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size))
- return -EACCES;
-
- if (!used_math()) {
- err = init_fpu(tsk);
- if (err)
- return err;
- }
-
- if (HAVE_HWFP) {
- if (cpu_has_xsave)
- err = restore_i387_xsave(buf);
- else if (cpu_has_fxsr)
- err = restore_i387_fxsave(fp, sizeof(struct
- i387_fxsave_struct));
- else
- err = restore_i387_fsave(fp);
- } else {
- err = fpregs_soft_set(current, NULL,
- 0, sizeof(struct user_i387_ia32_struct),
- NULL, fp) != 0;
- }
- set_used_math();
-
- return err;
-}
-
-/*
* FPU state for core dumps.
* This is only used for a.out dumps now.
* It is declared generically using elf_fpregset_t (which is
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 36d1853e91a..9a5c460404d 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -263,7 +263,7 @@ static void i8259A_shutdown(void)
* out of.
*/
outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */
- outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-1 */
+ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */
}
static struct syscore_ops i8259_syscore_ops = {
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index d44f7829968..e4595f10591 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -92,7 +92,8 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, " Rescheduling interrupts\n");
seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
+ seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
+ irq_stats(j)->irq_tlb_count);
seq_printf(p, " Function call interrupts\n");
seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
@@ -147,7 +148,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
#ifdef CONFIG_SMP
sum += irq_stats(cpu)->irq_resched_count;
sum += irq_stats(cpu)->irq_call_count;
- sum += irq_stats(cpu)->irq_tlb_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
sum += irq_stats(cpu)->irq_thermal_count;
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index e2f751efb7b..57916c0d3cf 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -541,6 +541,23 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb
return 1;
}
+#ifdef KPROBES_CAN_USE_FTRACE
+static void __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ /*
+ * Emulate singlestep (and also recover regs->ip)
+ * as if there is a 5byte nop
+ */
+ regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+ if (unlikely(p->post_handler)) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ p->post_handler(p, regs, 0);
+ }
+ __this_cpu_write(current_kprobe, NULL);
+}
+#endif
+
/*
* Interrupts are disabled on entry as trap3 is an interrupt gate and they
* remain disabled throughout this function.
@@ -599,6 +616,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
} else if (kprobe_running()) {
p = __this_cpu_read(current_kprobe);
if (p->break_handler && p->break_handler(p, regs)) {
+#ifdef KPROBES_CAN_USE_FTRACE
+ if (kprobe_ftrace(p)) {
+ skip_singlestep(p, regs, kcb);
+ return 1;
+ }
+#endif
setup_singlestep(p, regs, kcb, 0);
return 1;
}
@@ -1052,6 +1075,50 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
return 0;
}
+#ifdef KPROBES_CAN_USE_FTRACE
+/* Ftrace callback handler for kprobes */
+void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *ops, struct pt_regs *regs)
+{
+ struct kprobe *p;
+ struct kprobe_ctlblk *kcb;
+ unsigned long flags;
+
+ /* Disable irq for emulating a breakpoint and avoiding preempt */
+ local_irq_save(flags);
+
+ p = get_kprobe((kprobe_opcode_t *)ip);
+ if (unlikely(!p) || kprobe_disabled(p))
+ goto end;
+
+ kcb = get_kprobe_ctlblk();
+ if (kprobe_running()) {
+ kprobes_inc_nmissed_count(p);
+ } else {
+ /* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
+ regs->ip = ip + sizeof(kprobe_opcode_t);
+
+ __this_cpu_write(current_kprobe, p);
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+ if (!p->pre_handler || !p->pre_handler(p, regs))
+ skip_singlestep(p, regs, kcb);
+ /*
+ * If pre_handler returns !0, it sets regs->ip and
+ * resets current kprobe.
+ */
+ }
+end:
+ local_irq_restore(flags);
+}
+
+int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p)
+{
+ p->ainsn.insn = NULL;
+ p->ainsn.boostable = -1;
+ return 0;
+}
+#endif
+
int __init arch_init_kprobes(void)
{
return arch_init_optprobes();
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index c1d61ee4b4f..b3e5e51bc90 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -354,6 +354,7 @@ static void kvm_pv_guest_cpu_reboot(void *unused)
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
wrmsrl(MSR_KVM_PV_EOI_EN, 0);
kvm_pv_disable_apf();
+ kvm_disable_steal_time();
}
static int kvm_pv_reboot_notify(struct notifier_block *nb,
@@ -396,9 +397,7 @@ void kvm_disable_steal_time(void)
#ifdef CONFIG_SMP
static void __init kvm_smp_prepare_boot_cpu(void)
{
-#ifdef CONFIG_KVM_CLOCK
WARN_ON(kvm_register_clock("primary cpu clock"));
-#endif
kvm_guest_cpu_init();
native_smp_prepare_boot_cpu();
}
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 82746f942cd..7720ff5a9ee 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -75,20 +75,113 @@ struct microcode_amd {
static struct equiv_cpu_entry *equiv_cpu_table;
-/* page-sized ucode patch buffer */
-void *patch;
+struct ucode_patch {
+ struct list_head plist;
+ void *data;
+ u32 patch_id;
+ u16 equiv_cpu;
+};
+
+static LIST_HEAD(pcache);
+
+static u16 find_equiv_id(unsigned int cpu)
+{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ int i = 0;
+
+ if (!equiv_cpu_table)
+ return 0;
+
+ while (equiv_cpu_table[i].installed_cpu != 0) {
+ if (uci->cpu_sig.sig == equiv_cpu_table[i].installed_cpu)
+ return equiv_cpu_table[i].equiv_cpu;
+
+ i++;
+ }
+ return 0;
+}
+
+static u32 find_cpu_family_by_equiv_cpu(u16 equiv_cpu)
+{
+ int i = 0;
+
+ BUG_ON(!equiv_cpu_table);
+
+ while (equiv_cpu_table[i].equiv_cpu != 0) {
+ if (equiv_cpu == equiv_cpu_table[i].equiv_cpu)
+ return equiv_cpu_table[i].installed_cpu;
+ i++;
+ }
+ return 0;
+}
+
+/*
+ * a small, trivial cache of per-family ucode patches
+ */
+static struct ucode_patch *cache_find_patch(u16 equiv_cpu)
+{
+ struct ucode_patch *p;
+
+ list_for_each_entry(p, &pcache, plist)
+ if (p->equiv_cpu == equiv_cpu)
+ return p;
+ return NULL;
+}
+
+static void update_cache(struct ucode_patch *new_patch)
+{
+ struct ucode_patch *p;
+
+ list_for_each_entry(p, &pcache, plist) {
+ if (p->equiv_cpu == new_patch->equiv_cpu) {
+ if (p->patch_id >= new_patch->patch_id)
+ /* we already have the latest patch */
+ return;
+
+ list_replace(&p->plist, &new_patch->plist);
+ kfree(p->data);
+ kfree(p);
+ return;
+ }
+ }
+ /* no patch found, add it */
+ list_add_tail(&new_patch->plist, &pcache);
+}
+
+static void free_cache(void)
+{
+ struct ucode_patch *p, *tmp;
+
+ list_for_each_entry_safe(p, tmp, &pcache, plist) {
+ __list_del(p->plist.prev, p->plist.next);
+ kfree(p->data);
+ kfree(p);
+ }
+}
+
+static struct ucode_patch *find_patch(unsigned int cpu)
+{
+ u16 equiv_id;
+
+ equiv_id = find_equiv_id(cpu);
+ if (!equiv_id)
+ return NULL;
+
+ return cache_find_patch(equiv_id);
+}
static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ csig->sig = cpuid_eax(0x00000001);
csig->rev = c->microcode;
pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
return 0;
}
-static unsigned int verify_ucode_size(int cpu, u32 patch_size,
+static unsigned int verify_patch_size(int cpu, u32 patch_size,
unsigned int size)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -118,95 +211,37 @@ static unsigned int verify_ucode_size(int cpu, u32 patch_size,
return patch_size;
}
-static u16 find_equiv_id(void)
+static int apply_microcode_amd(int cpu)
{
- unsigned int current_cpu_id, i = 0;
-
- BUG_ON(equiv_cpu_table == NULL);
-
- current_cpu_id = cpuid_eax(0x00000001);
-
- while (equiv_cpu_table[i].installed_cpu != 0) {
- if (current_cpu_id == equiv_cpu_table[i].installed_cpu)
- return equiv_cpu_table[i].equiv_cpu;
-
- i++;
- }
- return 0;
-}
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct microcode_amd *mc_amd;
+ struct ucode_cpu_info *uci;
+ struct ucode_patch *p;
+ u32 rev, dummy;
-/*
- * we signal a good patch is found by returning its size > 0
- */
-static int get_matching_microcode(int cpu, const u8 *ucode_ptr,
- unsigned int leftover_size, int rev,
- unsigned int *current_size)
-{
- struct microcode_header_amd *mc_hdr;
- unsigned int actual_size, patch_size;
- u16 equiv_cpu_id;
+ BUG_ON(raw_smp_processor_id() != cpu);
- /* size of the current patch we're staring at */
- patch_size = *(u32 *)(ucode_ptr + 4);
- *current_size = patch_size + SECTION_HDR_SIZE;
+ uci = ucode_cpu_info + cpu;
- equiv_cpu_id = find_equiv_id();
- if (!equiv_cpu_id)
+ p = find_patch(cpu);
+ if (!p)
return 0;
- /*
- * let's look at the patch header itself now
- */
- mc_hdr = (struct microcode_header_amd *)(ucode_ptr + SECTION_HDR_SIZE);
+ mc_amd = p->data;
+ uci->mc = p->data;
- if (mc_hdr->processor_rev_id != equiv_cpu_id)
- return 0;
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- /* ucode might be chipset specific -- currently we don't support this */
- if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
- pr_err("CPU%d: chipset specific code not yet supported\n",
- cpu);
+ /* need to apply patch? */
+ if (rev >= mc_amd->hdr.patch_id) {
+ c->microcode = rev;
return 0;
}
- if (mc_hdr->patch_id <= rev)
- return 0;
-
- /*
- * now that the header looks sane, verify its size
- */
- actual_size = verify_ucode_size(cpu, patch_size, leftover_size);
- if (!actual_size)
- return 0;
-
- /* clear the patch buffer */
- memset(patch, 0, PAGE_SIZE);
-
- /* all looks ok, get the binary patch */
- get_ucode_data(patch, ucode_ptr + SECTION_HDR_SIZE, actual_size);
-
- return actual_size;
-}
-
-static int apply_microcode_amd(int cpu)
-{
- u32 rev, dummy;
- int cpu_num = raw_smp_processor_id();
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num;
- struct microcode_amd *mc_amd = uci->mc;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-
- /* We should bind the task to the CPU */
- BUG_ON(cpu_num != cpu);
-
- if (mc_amd == NULL)
- return 0;
-
wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
- /* get patch id after patching */
- rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
- /* check current patch id and patch's id for match */
+ /* verify patch application was successful */
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
if (rev != mc_amd->hdr.patch_id) {
pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
@@ -238,7 +273,7 @@ static int install_equiv_cpu_table(const u8 *buf)
return -ENOMEM;
}
- get_ucode_data(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
+ memcpy(equiv_cpu_table, buf + CONTAINER_HDR_SZ, size);
/* add header length */
return size + CONTAINER_HDR_SZ;
@@ -250,61 +285,113 @@ static void free_equiv_cpu_table(void)
equiv_cpu_table = NULL;
}
-static enum ucode_state
-generic_load_microcode(int cpu, const u8 *data, size_t size)
+static void cleanup(void)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- struct microcode_header_amd *mc_hdr = NULL;
- unsigned int mc_size, leftover, current_size = 0;
+ free_equiv_cpu_table();
+ free_cache();
+}
+
+/*
+ * We return the current size even if some of the checks failed so that
+ * we can skip over the next patch. If we return a negative value, we
+ * signal a grave error like a memory allocation has failed and the
+ * driver cannot continue functioning normally. In such cases, we tear
+ * down everything we've used up so far and exit.
+ */
+static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover)
+{
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct microcode_header_amd *mc_hdr;
+ struct ucode_patch *patch;
+ unsigned int patch_size, crnt_size, ret;
+ u32 proc_fam;
+ u16 proc_id;
+
+ patch_size = *(u32 *)(fw + 4);
+ crnt_size = patch_size + SECTION_HDR_SIZE;
+ mc_hdr = (struct microcode_header_amd *)(fw + SECTION_HDR_SIZE);
+ proc_id = mc_hdr->processor_rev_id;
+
+ proc_fam = find_cpu_family_by_equiv_cpu(proc_id);
+ if (!proc_fam) {
+ pr_err("No patch family for equiv ID: 0x%04x\n", proc_id);
+ return crnt_size;
+ }
+
+ /* check if patch is for the current family */
+ proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff);
+ if (proc_fam != c->x86)
+ return crnt_size;
+
+ if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) {
+ pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n",
+ mc_hdr->patch_id);
+ return crnt_size;
+ }
+
+ ret = verify_patch_size(cpu, patch_size, leftover);
+ if (!ret) {
+ pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id);
+ return crnt_size;
+ }
+
+ patch = kzalloc(sizeof(*patch), GFP_KERNEL);
+ if (!patch) {
+ pr_err("Patch allocation failure.\n");
+ return -EINVAL;
+ }
+
+ patch->data = kzalloc(patch_size, GFP_KERNEL);
+ if (!patch->data) {
+ pr_err("Patch data allocation failure.\n");
+ kfree(patch);
+ return -EINVAL;
+ }
+
+ /* All looks ok, copy patch... */
+ memcpy(patch->data, fw + SECTION_HDR_SIZE, patch_size);
+ INIT_LIST_HEAD(&patch->plist);
+ patch->patch_id = mc_hdr->patch_id;
+ patch->equiv_cpu = proc_id;
+
+ /* ... and add to cache. */
+ update_cache(patch);
+
+ return crnt_size;
+}
+
+static enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size)
+{
+ enum ucode_state ret = UCODE_ERROR;
+ unsigned int leftover;
+ u8 *fw = (u8 *)data;
+ int crnt_size = 0;
int offset;
- const u8 *ucode_ptr = data;
- void *new_mc = NULL;
- unsigned int new_rev = uci->cpu_sig.rev;
- enum ucode_state state = UCODE_ERROR;
- offset = install_equiv_cpu_table(ucode_ptr);
+ offset = install_equiv_cpu_table(data);
if (offset < 0) {
pr_err("failed to create equivalent cpu table\n");
- goto out;
+ return ret;
}
- ucode_ptr += offset;
+ fw += offset;
leftover = size - offset;
- if (*(u32 *)ucode_ptr != UCODE_UCODE_TYPE) {
+ if (*(u32 *)fw != UCODE_UCODE_TYPE) {
pr_err("invalid type field in container file section header\n");
- goto free_table;
+ free_equiv_cpu_table();
+ return ret;
}
while (leftover) {
- mc_size = get_matching_microcode(cpu, ucode_ptr, leftover,
- new_rev, &current_size);
- if (mc_size) {
- mc_hdr = patch;
- new_mc = patch;
- new_rev = mc_hdr->patch_id;
- goto out_ok;
- }
-
- ucode_ptr += current_size;
- leftover -= current_size;
- }
+ crnt_size = verify_and_add_patch(cpu, fw, leftover);
+ if (crnt_size < 0)
+ return ret;
- if (!new_mc) {
- state = UCODE_NFOUND;
- goto free_table;
+ fw += crnt_size;
+ leftover -= crnt_size;
}
-out_ok:
- uci->mc = new_mc;
- state = UCODE_OK;
- pr_debug("CPU%d update ucode (0x%08x -> 0x%08x)\n",
- cpu, uci->cpu_sig.rev, new_rev);
-
-free_table:
- free_equiv_cpu_table();
-
-out:
- return state;
+ return UCODE_OK;
}
/*
@@ -315,7 +402,7 @@ out:
*
* This legacy file is always smaller than 2K in size.
*
- * Starting at family 15h they are in family specific firmware files:
+ * Beginning with family 15h, they are in family-specific firmware files:
*
* amd-ucode/microcode_amd_fam15h.bin
* amd-ucode/microcode_amd_fam16h.bin
@@ -323,12 +410,17 @@ out:
*
* These might be larger than 2K.
*/
-static enum ucode_state request_microcode_amd(int cpu, struct device *device)
+static enum ucode_state request_microcode_amd(int cpu, struct device *device,
+ bool refresh_fw)
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
- const struct firmware *fw;
- enum ucode_state ret = UCODE_NFOUND;
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ enum ucode_state ret = UCODE_NFOUND;
+ const struct firmware *fw;
+
+ /* reload ucode container only on the boot cpu */
+ if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+ return UCODE_OK;
if (c->x86 >= 0x15)
snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
@@ -344,12 +436,17 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device)
goto fw_release;
}
- ret = generic_load_microcode(cpu, fw->data, fw->size);
+ /* free old equiv table */
+ free_equiv_cpu_table();
+
+ ret = load_microcode_amd(cpu, fw->data, fw->size);
+ if (ret != UCODE_OK)
+ cleanup();
-fw_release:
+ fw_release:
release_firmware(fw);
-out:
+ out:
return ret;
}
@@ -383,14 +480,10 @@ struct microcode_ops * __init init_amd_microcode(void)
return NULL;
}
- patch = (void *)get_zeroed_page(GFP_KERNEL);
- if (!patch)
- return NULL;
-
return &microcode_amd_ops;
}
void __exit exit_amd_microcode(void)
{
- free_page((unsigned long)patch);
+ cleanup();
}
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 4873e62db6a..3a04b224d0c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -225,6 +225,9 @@ static ssize_t microcode_write(struct file *file, const char __user *buf,
if (do_microcode_update(buf, len) == 0)
ret = (ssize_t)len;
+ if (ret > 0)
+ perf_check_microcode();
+
mutex_unlock(&microcode_mutex);
put_online_cpus();
@@ -276,19 +279,18 @@ static struct platform_device *microcode_pdev;
static int reload_for_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ enum ucode_state ustate;
int err = 0;
- if (uci->valid) {
- enum ucode_state ustate;
-
- ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
- if (ustate == UCODE_OK)
- apply_microcode_on_target(cpu);
- else
- if (ustate == UCODE_ERROR)
- err = -EINVAL;
- }
+ if (!uci->valid)
+ return err;
+ ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
+ if (ustate == UCODE_OK)
+ apply_microcode_on_target(cpu);
+ else
+ if (ustate == UCODE_ERROR)
+ err = -EINVAL;
return err;
}
@@ -370,18 +372,15 @@ static void microcode_fini_cpu(int cpu)
static enum ucode_state microcode_resume_cpu(int cpu)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-
- if (!uci->mc)
- return UCODE_NFOUND;
-
pr_debug("CPU%d updated upon resume\n", cpu);
- apply_microcode_on_target(cpu);
+
+ if (apply_microcode_on_target(cpu))
+ return UCODE_ERROR;
return UCODE_OK;
}
-static enum ucode_state microcode_init_cpu(int cpu)
+static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
{
enum ucode_state ustate;
@@ -392,7 +391,8 @@ static enum ucode_state microcode_init_cpu(int cpu)
if (system_state != SYSTEM_RUNNING)
return UCODE_NFOUND;
- ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev);
+ ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
+ refresh_fw);
if (ustate == UCODE_OK) {
pr_debug("CPU%d updated upon init\n", cpu);
@@ -405,14 +405,11 @@ static enum ucode_state microcode_init_cpu(int cpu)
static enum ucode_state microcode_update_cpu(int cpu)
{
struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- enum ucode_state ustate;
if (uci->valid)
- ustate = microcode_resume_cpu(cpu);
- else
- ustate = microcode_init_cpu(cpu);
+ return microcode_resume_cpu(cpu);
- return ustate;
+ return microcode_init_cpu(cpu, false);
}
static int mc_device_add(struct device *dev, struct subsys_interface *sif)
@@ -428,7 +425,7 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif)
if (err)
return err;
- if (microcode_init_cpu(cpu) == UCODE_ERROR)
+ if (microcode_init_cpu(cpu, true) == UCODE_ERROR)
return -EINVAL;
return err;
@@ -477,34 +474,41 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
struct device *dev;
dev = get_cpu_device(cpu);
- switch (action) {
+
+ switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
microcode_update_cpu(cpu);
- case CPU_DOWN_FAILED:
- case CPU_DOWN_FAILED_FROZEN:
pr_debug("CPU%d added\n", cpu);
+ /*
+ * "break" is missing on purpose here because we want to fall
+ * through in order to create the sysfs group.
+ */
+
+ case CPU_DOWN_FAILED:
if (sysfs_create_group(&dev->kobj, &mc_attr_group))
pr_err("Failed to create group for CPU%d\n", cpu);
break;
+
case CPU_DOWN_PREPARE:
- case CPU_DOWN_PREPARE_FROZEN:
/* Suspend is in progress, only remove the interface */
sysfs_remove_group(&dev->kobj, &mc_attr_group);
pr_debug("CPU%d removed\n", cpu);
break;
/*
+ * case CPU_DEAD:
+ *
* When a CPU goes offline, don't free up or invalidate the copy of
* the microcode in kernel memory, so that we can reuse it when the
* CPU comes back online without unnecessarily requesting the userspace
* for it again.
*/
- case CPU_UP_CANCELED_FROZEN:
- /* The CPU refused to come up during a system resume */
- microcode_fini_cpu(cpu);
- break;
}
+
+ /* The CPU refused to come up during a system resume */
+ if (action == CPU_UP_CANCELED_FROZEN)
+ microcode_fini_cpu(cpu);
+
return NOTIFY_OK;
}
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 0327e2b3c40..3544aed3933 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -405,7 +405,8 @@ static int get_ucode_fw(void *to, const void *from, size_t n)
return 0;
}
-static enum ucode_state request_microcode_fw(int cpu, struct device *device)
+static enum ucode_state request_microcode_fw(int cpu, struct device *device,
+ bool refresh_fw)
{
char name[30];
struct cpuinfo_x86 *c = &cpu_data(cpu);
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index eb113693f04..a7c5661f849 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -257,12 +257,14 @@ static int __init msr_init(void)
goto out_chrdev;
}
msr_class->devnode = msr_devnode;
+ get_online_cpus();
for_each_online_cpu(i) {
err = msr_device_create(i);
if (err != 0)
goto out_class;
}
register_hotcpu_notifier(&msr_class_cpu_notifier);
+ put_online_cpus();
err = 0;
goto out;
@@ -271,6 +273,7 @@ out_class:
i = 0;
for_each_online_cpu(i)
msr_device_destroy(i);
+ put_online_cpus();
class_destroy(msr_class);
out_chrdev:
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
@@ -281,11 +284,13 @@ out:
static void __exit msr_exit(void)
{
int cpu = 0;
+ get_online_cpus();
for_each_online_cpu(cpu)
msr_device_destroy(cpu);
class_destroy(msr_class);
__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
unregister_hotcpu_notifier(&msr_class_cpu_notifier);
+ put_online_cpus();
}
module_init(msr_init);
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
new file mode 100644
index 00000000000..e309cc5c276
--- /dev/null
+++ b/arch/x86/kernel/perf_regs.c
@@ -0,0 +1,105 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <linux/stddef.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_X86_32
+#define PERF_REG_X86_MAX PERF_REG_X86_32_MAX
+#else
+#define PERF_REG_X86_MAX PERF_REG_X86_64_MAX
+#endif
+
+#define PT_REGS_OFFSET(id, r) [id] = offsetof(struct pt_regs, r)
+
+static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
+ PT_REGS_OFFSET(PERF_REG_X86_AX, ax),
+ PT_REGS_OFFSET(PERF_REG_X86_BX, bx),
+ PT_REGS_OFFSET(PERF_REG_X86_CX, cx),
+ PT_REGS_OFFSET(PERF_REG_X86_DX, dx),
+ PT_REGS_OFFSET(PERF_REG_X86_SI, si),
+ PT_REGS_OFFSET(PERF_REG_X86_DI, di),
+ PT_REGS_OFFSET(PERF_REG_X86_BP, bp),
+ PT_REGS_OFFSET(PERF_REG_X86_SP, sp),
+ PT_REGS_OFFSET(PERF_REG_X86_IP, ip),
+ PT_REGS_OFFSET(PERF_REG_X86_FLAGS, flags),
+ PT_REGS_OFFSET(PERF_REG_X86_CS, cs),
+ PT_REGS_OFFSET(PERF_REG_X86_SS, ss),
+#ifdef CONFIG_X86_32
+ PT_REGS_OFFSET(PERF_REG_X86_DS, ds),
+ PT_REGS_OFFSET(PERF_REG_X86_ES, es),
+ PT_REGS_OFFSET(PERF_REG_X86_FS, fs),
+ PT_REGS_OFFSET(PERF_REG_X86_GS, gs),
+#else
+ /*
+ * The pt_regs struct does not store
+ * ds, es, fs, gs in 64 bit mode.
+ */
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+ (unsigned int) -1,
+#endif
+#ifdef CONFIG_X86_64
+ PT_REGS_OFFSET(PERF_REG_X86_R8, r8),
+ PT_REGS_OFFSET(PERF_REG_X86_R9, r9),
+ PT_REGS_OFFSET(PERF_REG_X86_R10, r10),
+ PT_REGS_OFFSET(PERF_REG_X86_R11, r11),
+ PT_REGS_OFFSET(PERF_REG_X86_R12, r12),
+ PT_REGS_OFFSET(PERF_REG_X86_R13, r13),
+ PT_REGS_OFFSET(PERF_REG_X86_R14, r14),
+ PT_REGS_OFFSET(PERF_REG_X86_R15, r15),
+#endif
+};
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+ if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
+ return 0;
+
+ return regs_get_register(regs, pt_regs_offset[idx]);
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
+
+#ifdef CONFIG_X86_32
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ return PERF_SAMPLE_REGS_ABI_32;
+}
+#else /* CONFIG_X86_64 */
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
+ (1ULL << PERF_REG_X86_ES) | \
+ (1ULL << PERF_REG_X86_FS) | \
+ (1ULL << PERF_REG_X86_GS))
+
+int perf_reg_validate(u64 mask)
+{
+ if (!mask || mask & REG_RESERVED)
+ return -EINVAL;
+
+ if (mask & REG_NOSUPPORT)
+ return -EINVAL;
+
+ return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+ if (test_tsk_thread_flag(task, TIF_IA32))
+ return PERF_SAMPLE_REGS_ABI_32;
+ else
+ return PERF_SAMPLE_REGS_ABI_64;
+}
+#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 0bc72e2069e..d5f15c3f7b2 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -150,7 +150,7 @@ static struct resource *find_oprom(struct pci_dev *pdev)
return oprom;
}
-void *pci_map_biosrom(struct pci_dev *pdev)
+void __iomem *pci_map_biosrom(struct pci_dev *pdev)
{
struct resource *oprom = find_oprom(pdev);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ef6a8456f71..dc3567e083f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -66,15 +66,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
int ret;
- unlazy_fpu(src);
-
*dst = *src;
if (fpu_allocated(&src->thread.fpu)) {
memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
ret = fpu_alloc(&dst->thread.fpu);
if (ret)
return ret;
- fpu_copy(&dst->thread.fpu, &src->thread.fpu);
+ fpu_copy(dst, src);
}
return 0;
}
@@ -97,16 +95,6 @@ void arch_task_cache_init(void)
SLAB_PANIC | SLAB_NOTRACK, NULL);
}
-static inline void drop_fpu(struct task_struct *tsk)
-{
- /*
- * Forget coprocessor state..
- */
- tsk->fpu_counter = 0;
- clear_fpu(tsk);
- clear_used_math();
-}
-
/*
* Free current thread data structures etc..
*/
@@ -163,7 +151,13 @@ void flush_thread(void)
flush_ptrace_hw_breakpoint(tsk);
memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
- drop_fpu(tsk);
+ drop_init_fpu(tsk);
+ /*
+ * Free the FPU state for non xsave platforms. They get reallocated
+ * lazily at the first use.
+ */
+ if (!use_eager_fpu())
+ free_thread_xstate(tsk);
}
static void hard_disable_TSC(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 516fa186121..b9ff83c7135 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -190,10 +190,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
regs->cs = __USER_CS;
regs->ip = new_ip;
regs->sp = new_sp;
- /*
- * Free the old FP and other extended state
- */
- free_thread_xstate(current);
}
EXPORT_SYMBOL_GPL(start_thread);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 0a980c9d7cb..8a6d20ce197 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -232,10 +232,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
regs->cs = _cs;
regs->ss = _ss;
regs->flags = X86_EFLAGS_IF;
- /*
- * Free the old FP and other extended state
- */
- free_thread_xstate(current);
}
void
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c2bf0..b00b33a1839 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -21,6 +21,7 @@
#include <linux/signal.h>
#include <linux/perf_event.h>
#include <linux/hw_breakpoint.h>
+#include <linux/rcupdate.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
@@ -1332,9 +1333,6 @@ static const struct user_regset_view user_x86_64_view = {
#define genregs32_get genregs_get
#define genregs32_set genregs_set
-#define user_i387_ia32_struct user_i387_struct
-#define user32_fxsr_struct user_fxsr_struct
-
#endif /* CONFIG_X86_64 */
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
@@ -1463,6 +1461,8 @@ long syscall_trace_enter(struct pt_regs *regs)
{
long ret = 0;
+ rcu_user_exit();
+
/*
* If we stepped into a sysenter/syscall insn, it trapped in
* kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP.
@@ -1526,4 +1526,6 @@ void syscall_trace_leave(struct pt_regs *regs)
!test_thread_flag(TIF_SYSCALL_EMU);
if (step || test_thread_flag(TIF_SYSCALL_TRACE))
tracehook_report_syscall_exit(regs, step);
+
+ rcu_user_enter();
}
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index af6db6ec5b2..4929c1be0ac 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -225,7 +225,7 @@ static struct platform_device rtc_device = {
static __init int add_rtc_cmos(void)
{
#ifdef CONFIG_PNP
- static const char *ids[] __initconst =
+ static const char * const const ids[] __initconst =
{ "PNP0b00", "PNP0b01", "PNP0b02", };
struct pnp_dev *dev;
struct pnp_id *id;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f4b9b80e1b9..d609be046b5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -957,13 +957,11 @@ void __init setup_arch(char **cmdline_p)
initmem_init();
memblock_find_dma_reserve();
-#ifdef CONFIG_KVM_CLOCK
+#ifdef CONFIG_KVM_GUEST
kvmclock_init();
#endif
- x86_init.paging.pagetable_setup_start(swapper_pg_dir);
- paging_init();
- x86_init.paging.pagetable_setup_done(swapper_pg_dir);
+ x86_init.paging.pagetable_init();
if (boot_cpu_data.cpuid_level >= 0) {
/* A CPU has %cr4 if and only if it has CPUID */
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b280908a376..b33144c8b30 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -114,11 +114,12 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
regs->orig_ax = -1; /* disable syscall checks */
get_user_ex(buf, &sc->fpstate);
- err |= restore_i387_xstate(buf);
get_user_ex(*pax, &sc->ax);
} get_user_catch(err);
+ err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
+
return err;
}
@@ -206,35 +207,32 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
void __user **fpstate)
{
/* Default to using normal stack */
+ unsigned long math_size = 0;
unsigned long sp = regs->sp;
+ unsigned long buf_fx = 0;
int onsigstack = on_sig_stack(sp);
-#ifdef CONFIG_X86_64
/* redzone */
- sp -= 128;
-#endif /* CONFIG_X86_64 */
+ if (config_enabled(CONFIG_X86_64))
+ sp -= 128;
if (!onsigstack) {
/* This is the X/Open sanctioned signal stack switching. */
if (ka->sa.sa_flags & SA_ONSTACK) {
if (current->sas_ss_size)
sp = current->sas_ss_sp + current->sas_ss_size;
- } else {
-#ifdef CONFIG_X86_32
- /* This is the legacy signal stack switching. */
- if ((regs->ss & 0xffff) != __USER_DS &&
- !(ka->sa.sa_flags & SA_RESTORER) &&
- ka->sa.sa_restorer)
+ } else if (config_enabled(CONFIG_X86_32) &&
+ (regs->ss & 0xffff) != __USER_DS &&
+ !(ka->sa.sa_flags & SA_RESTORER) &&
+ ka->sa.sa_restorer) {
+ /* This is the legacy signal stack switching. */
sp = (unsigned long) ka->sa.sa_restorer;
-#endif /* CONFIG_X86_32 */
}
}
if (used_math()) {
- sp -= sig_xstate_size;
-#ifdef CONFIG_X86_64
- sp = round_down(sp, 64);
-#endif /* CONFIG_X86_64 */
+ sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+ &buf_fx, &math_size);
*fpstate = (void __user *)sp;
}
@@ -247,8 +245,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
if (onsigstack && !likely(on_sig_stack(sp)))
return (void __user *)-1L;
- /* save i387 state */
- if (used_math() && save_i387_xstate(*fpstate) < 0)
+ /* save i387 and extended state */
+ if (used_math() &&
+ save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
return (void __user *)-1L;
return (void __user *)sp;
@@ -357,7 +356,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
put_user_ex(sig, &frame->sig);
put_user_ex(&frame->info, &frame->pinfo);
put_user_ex(&frame->uc, &frame->puc);
- err |= copy_siginfo_to_user(&frame->info, info);
/* Create the ucontext. */
if (cpu_has_xsave)
@@ -369,9 +367,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
put_user_ex(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
/* Set up to return from userspace. */
restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -388,6 +383,11 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
*/
put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
} put_user_catch(err);
+
+ err |= copy_siginfo_to_user(&frame->info, info);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
if (err)
return -EFAULT;
@@ -436,8 +436,6 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
put_user_ex(sas_ss_flags(regs->sp),
&frame->uc.uc_stack.ss_flags);
put_user_ex(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
@@ -450,6 +448,9 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
}
} put_user_catch(err);
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
if (err)
return -EFAULT;
@@ -474,6 +475,75 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
}
#endif /* CONFIG_X86_32 */
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+ siginfo_t *info, compat_sigset_t *set,
+ struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_X32_ABI
+ struct rt_sigframe_x32 __user *frame;
+ void __user *restorer;
+ int err = 0;
+ void __user *fpstate = NULL;
+
+ frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+ if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+ return -EFAULT;
+
+ if (ka->sa.sa_flags & SA_SIGINFO) {
+ if (copy_siginfo_to_user32(&frame->info, info))
+ return -EFAULT;
+ }
+
+ put_user_try {
+ /* Create the ucontext. */
+ if (cpu_has_xsave)
+ put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+ else
+ put_user_ex(0, &frame->uc.uc_flags);
+ put_user_ex(0, &frame->uc.uc_link);
+ put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+ put_user_ex(sas_ss_flags(regs->sp),
+ &frame->uc.uc_stack.ss_flags);
+ put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+ put_user_ex(0, &frame->uc.uc__pad0);
+
+ if (ka->sa.sa_flags & SA_RESTORER) {
+ restorer = ka->sa.sa_restorer;
+ } else {
+ /* could use a vstub here */
+ restorer = NULL;
+ err |= -EFAULT;
+ }
+ put_user_ex(restorer, &frame->pretcode);
+ } put_user_catch(err);
+
+ err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+ regs, set->sig[0]);
+ err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+ if (err)
+ return -EFAULT;
+
+ /* Set up registers for signal handler */
+ regs->sp = (unsigned long) frame;
+ regs->ip = (unsigned long) ka->sa.sa_handler;
+
+ /* We use the x32 calling convention here... */
+ regs->di = sig;
+ regs->si = (unsigned long) &frame->info;
+ regs->dx = (unsigned long) &frame->uc;
+
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+
+ regs->cs = __USER_CS;
+ regs->ss = __USER_DS;
+#endif /* CONFIG_X86_X32_ABI */
+
+ return 0;
+}
+
#ifdef CONFIG_X86_32
/*
* Atomically swap in the new signal mask, and wait for a signal.
@@ -612,55 +682,22 @@ static int signr_convert(int sig)
return sig;
}
-#ifdef CONFIG_X86_32
-
-#define is_ia32 1
-#define ia32_setup_frame __setup_frame
-#define ia32_setup_rt_frame __setup_rt_frame
-
-#else /* !CONFIG_X86_32 */
-
-#ifdef CONFIG_IA32_EMULATION
-#define is_ia32 test_thread_flag(TIF_IA32)
-#else /* !CONFIG_IA32_EMULATION */
-#define is_ia32 0
-#endif /* CONFIG_IA32_EMULATION */
-
-#ifdef CONFIG_X86_X32_ABI
-#define is_x32 test_thread_flag(TIF_X32)
-
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
- siginfo_t *info, compat_sigset_t *set,
- struct pt_regs *regs);
-#else /* !CONFIG_X86_X32_ABI */
-#define is_x32 0
-#endif /* CONFIG_X86_X32_ABI */
-
-int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
- sigset_t *set, struct pt_regs *regs);
-int ia32_setup_frame(int sig, struct k_sigaction *ka,
- sigset_t *set, struct pt_regs *regs);
-
-#endif /* CONFIG_X86_32 */
-
static int
setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
struct pt_regs *regs)
{
int usig = signr_convert(sig);
sigset_t *set = sigmask_to_save();
+ compat_sigset_t *cset = (compat_sigset_t *) set;
/* Set up the stack frame */
- if (is_ia32) {
+ if (is_ia32_frame()) {
if (ka->sa.sa_flags & SA_SIGINFO)
- return ia32_setup_rt_frame(usig, ka, info, set, regs);
+ return ia32_setup_rt_frame(usig, ka, info, cset, regs);
else
- return ia32_setup_frame(usig, ka, set, regs);
-#ifdef CONFIG_X86_X32_ABI
- } else if (is_x32) {
- return x32_setup_rt_frame(usig, ka, info,
- (compat_sigset_t *)set, regs);
-#endif
+ return ia32_setup_frame(usig, ka, cset, regs);
+ } else if (is_x32_frame()) {
+ return x32_setup_rt_frame(usig, ka, info, cset, regs);
} else {
return __setup_rt_frame(sig, ka, info, set, regs);
}
@@ -779,6 +816,8 @@ static void do_signal(struct pt_regs *regs)
void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
+ rcu_user_exit();
+
#ifdef CONFIG_X86_MCE
/* notify userspace of pending MCEs */
if (thread_info_flags & _TIF_MCE_NOTIFY)
@@ -804,6 +843,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
#ifdef CONFIG_X86_32
clear_thread_flag(TIF_IRET);
#endif /* CONFIG_X86_32 */
+
+ rcu_user_enter();
}
void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
@@ -824,72 +865,6 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
}
#ifdef CONFIG_X86_X32_ABI
-static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
- siginfo_t *info, compat_sigset_t *set,
- struct pt_regs *regs)
-{
- struct rt_sigframe_x32 __user *frame;
- void __user *restorer;
- int err = 0;
- void __user *fpstate = NULL;
-
- frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
-
- if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
- return -EFAULT;
-
- if (ka->sa.sa_flags & SA_SIGINFO) {
- if (copy_siginfo_to_user32(&frame->info, info))
- return -EFAULT;
- }
-
- put_user_try {
- /* Create the ucontext. */
- if (cpu_has_xsave)
- put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
- else
- put_user_ex(0, &frame->uc.uc_flags);
- put_user_ex(0, &frame->uc.uc_link);
- put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
- put_user_ex(sas_ss_flags(regs->sp),
- &frame->uc.uc_stack.ss_flags);
- put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
- put_user_ex(0, &frame->uc.uc__pad0);
- err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
- regs, set->sig[0]);
- err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
- if (ka->sa.sa_flags & SA_RESTORER) {
- restorer = ka->sa.sa_restorer;
- } else {
- /* could use a vstub here */
- restorer = NULL;
- err |= -EFAULT;
- }
- put_user_ex(restorer, &frame->pretcode);
- } put_user_catch(err);
-
- if (err)
- return -EFAULT;
-
- /* Set up registers for signal handler */
- regs->sp = (unsigned long) frame;
- regs->ip = (unsigned long) ka->sa.sa_handler;
-
- /* We use the x32 calling convention here... */
- regs->di = sig;
- regs->si = (unsigned long) &frame->info;
- regs->dx = (unsigned long) &frame->uc;
-
- loadsegment(ds, __USER_DS);
- loadsegment(es, __USER_DS);
-
- regs->cs = __USER_CS;
- regs->ss = __USER_DS;
-
- return 0;
-}
-
asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
{
struct rt_sigframe_x32 __user *frame;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7c5a8c314c0..c80a33bc528 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -665,7 +665,8 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
unsigned long boot_error = 0;
int timeout;
- alternatives_smp_switch(1);
+ /* Just in case we booted with a single CPU. */
+ alternatives_enable_smp();
idle->thread.sp = (unsigned long) (((struct pt_regs *)
(THREAD_SIZE + task_stack_page(idle))) - 1);
@@ -1053,20 +1054,6 @@ out:
preempt_enable();
}
-void arch_disable_nonboot_cpus_begin(void)
-{
- /*
- * Avoid the smp alternatives switch during the disable_nonboot_cpus().
- * In the suspend path, we will be back in the SMP mode shortly anyways.
- */
- skip_smp_alternatives = true;
-}
-
-void arch_disable_nonboot_cpus_end(void)
-{
- skip_smp_alternatives = false;
-}
-
void arch_enable_nonboot_cpus_begin(void)
{
set_mtrr_aps_delayed_init();
@@ -1256,9 +1243,6 @@ void native_cpu_die(unsigned int cpu)
if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
if (system_state == SYSTEM_RUNNING)
pr_info("CPU %u is now offline\n", cpu);
-
- if (1 == num_online_cpus())
- alternatives_smp_switch(0);
return;
}
msleep(100);
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index c346d116148..cd3b2438a98 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -157,6 +157,33 @@ static int enable_single_step(struct task_struct *child)
return 1;
}
+void set_task_blockstep(struct task_struct *task, bool on)
+{
+ unsigned long debugctl;
+
+ /*
+ * Ensure irq/preemption can't change debugctl in between.
+ * Note also that both TIF_BLOCKSTEP and debugctl should
+ * be changed atomically wrt preemption.
+ * FIXME: this means that set/clear TIF_BLOCKSTEP is simply
+ * wrong if task != current, SIGKILL can wakeup the stopped
+ * tracee and set/clear can play with the running task, this
+ * can confuse the next __switch_to_xtra().
+ */
+ local_irq_disable();
+ debugctl = get_debugctlmsr();
+ if (on) {
+ debugctl |= DEBUGCTLMSR_BTF;
+ set_tsk_thread_flag(task, TIF_BLOCKSTEP);
+ } else {
+ debugctl &= ~DEBUGCTLMSR_BTF;
+ clear_tsk_thread_flag(task, TIF_BLOCKSTEP);
+ }
+ if (task == current)
+ update_debugctlmsr(debugctl);
+ local_irq_enable();
+}
+
/*
* Enable single or block step.
*/
@@ -169,19 +196,10 @@ static void enable_step(struct task_struct *child, bool block)
* So no one should try to use debugger block stepping in a program
* that uses user-mode single stepping itself.
*/
- if (enable_single_step(child) && block) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl |= DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- set_tsk_thread_flag(child, TIF_BLOCKSTEP);
- } else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl &= ~DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
- }
+ if (enable_single_step(child) && block)
+ set_task_blockstep(child, true);
+ else if (test_tsk_thread_flag(child, TIF_BLOCKSTEP))
+ set_task_blockstep(child, false);
}
void user_enable_single_step(struct task_struct *child)
@@ -199,13 +217,8 @@ void user_disable_single_step(struct task_struct *child)
/*
* Make sure block stepping (BTF) is disabled.
*/
- if (test_tsk_thread_flag(child, TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl &= ~DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- clear_tsk_thread_flag(child, TIF_BLOCKSTEP);
- }
+ if (test_tsk_thread_flag(child, TIF_BLOCKSTEP))
+ set_task_blockstep(child, false);
/* Always clear TIF_SINGLESTEP... */
clear_tsk_thread_flag(child, TIF_SINGLESTEP);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b481341c936..8276dc6794c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -55,6 +55,7 @@
#include <asm/i387.h>
#include <asm/fpu-internal.h>
#include <asm/mce.h>
+#include <asm/rcu.h>
#include <asm/mach_traps.h>
@@ -107,30 +108,45 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
dec_preempt_count();
}
-static void __kprobes
-do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
- long error_code, siginfo_t *info)
+static int __kprobes
+do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
+ struct pt_regs *regs, long error_code)
{
- struct task_struct *tsk = current;
-
#ifdef CONFIG_X86_32
if (regs->flags & X86_VM_MASK) {
/*
- * traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
+ * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
* On nmi (interrupt 2), do_trap should not be called.
*/
- if (trapnr < X86_TRAP_UD)
- goto vm86_trap;
- goto trap_signal;
+ if (trapnr < X86_TRAP_UD) {
+ if (!handle_vm86_trap((struct kernel_vm86_regs *) regs,
+ error_code, trapnr))
+ return 0;
+ }
+ return -1;
}
#endif
+ if (!user_mode(regs)) {
+ if (!fixup_exception(regs)) {
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_nr = trapnr;
+ die(str, regs, error_code);
+ }
+ return 0;
+ }
- if (!user_mode(regs))
- goto kernel_trap;
+ return -1;
+}
-#ifdef CONFIG_X86_32
-trap_signal:
-#endif
+static void __kprobes
+do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
+ long error_code, siginfo_t *info)
+{
+ struct task_struct *tsk = current;
+
+
+ if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
+ return;
/*
* We want error_code and trap_nr set for userspace faults and
* kernelspace faults which result in die(), but not
@@ -158,33 +174,20 @@ trap_signal:
force_sig_info(signr, info, tsk);
else
force_sig(signr, tsk);
- return;
-
-kernel_trap:
- if (!fixup_exception(regs)) {
- tsk->thread.error_code = error_code;
- tsk->thread.trap_nr = trapnr;
- die(str, regs, error_code);
- }
- return;
-
-#ifdef CONFIG_X86_32
-vm86_trap:
- if (handle_vm86_trap((struct kernel_vm86_regs *) regs,
- error_code, trapnr))
- goto trap_signal;
- return;
-#endif
}
#define DO_ERROR(trapnr, signr, str, name) \
dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
{ \
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
- == NOTIFY_STOP) \
+ exception_enter(regs); \
+ if (notify_die(DIE_TRAP, str, regs, error_code, \
+ trapnr, signr) == NOTIFY_STOP) { \
+ exception_exit(regs); \
return; \
+ } \
conditional_sti(regs); \
do_trap(trapnr, signr, str, regs, error_code, NULL); \
+ exception_exit(regs); \
}
#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \
@@ -195,11 +198,15 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
info.si_errno = 0; \
info.si_code = sicode; \
info.si_addr = (void __user *)siaddr; \
- if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \
- == NOTIFY_STOP) \
+ exception_enter(regs); \
+ if (notify_die(DIE_TRAP, str, regs, error_code, \
+ trapnr, signr) == NOTIFY_STOP) { \
+ exception_exit(regs); \
return; \
+ } \
conditional_sti(regs); \
do_trap(trapnr, signr, str, regs, error_code, &info); \
+ exception_exit(regs); \
}
DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
@@ -222,12 +229,14 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
/* Runs on IST stack */
dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
{
+ exception_enter(regs);
if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
- X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
- return;
- preempt_conditional_sti(regs);
- do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
- preempt_conditional_cli(regs);
+ X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
+ preempt_conditional_sti(regs);
+ do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
+ preempt_conditional_cli(regs);
+ }
+ exception_exit(regs);
}
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
@@ -235,6 +244,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
static const char str[] = "double fault";
struct task_struct *tsk = current;
+ exception_enter(regs);
/* Return not checked because double check cannot be ignored */
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -255,16 +265,29 @@ do_general_protection(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk;
+ exception_enter(regs);
conditional_sti(regs);
#ifdef CONFIG_X86_32
- if (regs->flags & X86_VM_MASK)
- goto gp_in_vm86;
+ if (regs->flags & X86_VM_MASK) {
+ local_irq_enable();
+ handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
+ goto exit;
+ }
#endif
tsk = current;
- if (!user_mode(regs))
- goto gp_in_kernel;
+ if (!user_mode(regs)) {
+ if (fixup_exception(regs))
+ goto exit;
+
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_nr = X86_TRAP_GP;
+ if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+ X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
+ die("general protection fault", regs, error_code);
+ goto exit;
+ }
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
@@ -279,25 +302,8 @@ do_general_protection(struct pt_regs *regs, long error_code)
}
force_sig(SIGSEGV, tsk);
- return;
-
-#ifdef CONFIG_X86_32
-gp_in_vm86:
- local_irq_enable();
- handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code);
- return;
-#endif
-
-gp_in_kernel:
- if (fixup_exception(regs))
- return;
-
- tsk->thread.error_code = error_code;
- tsk->thread.trap_nr = X86_TRAP_GP;
- if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
- X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
- return;
- die("general protection fault", regs, error_code);
+exit:
+ exception_exit(regs);
}
/* May run on IST stack. */
@@ -312,15 +318,16 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
ftrace_int3_handler(regs))
return;
#endif
+ exception_enter(regs);
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
#endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
/*
* Let others (NMI) know that the debug stack is in use
@@ -331,6 +338,8 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
+exit:
+ exception_exit(regs);
}
#ifdef CONFIG_X86_64
@@ -391,6 +400,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
unsigned long dr6;
int si_code;
+ exception_enter(regs);
+
get_debugreg(dr6, 6);
/* Filter out all the reserved bits which are preset to 1 */
@@ -406,7 +417,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
- return;
+ goto exit;
/* DR6 may or may not be cleared by the CPU */
set_debugreg(0, 6);
@@ -421,7 +432,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
if (notify_die(DIE_DEBUG, "debug", regs, PTR_ERR(&dr6), error_code,
SIGTRAP) == NOTIFY_STOP)
- return;
+ goto exit;
/*
* Let others (NMI) know that the debug stack is in use
@@ -437,7 +448,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
X86_TRAP_DB);
preempt_conditional_cli(regs);
debug_stack_usage_dec();
- return;
+ goto exit;
}
/*
@@ -458,7 +469,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
preempt_conditional_cli(regs);
debug_stack_usage_dec();
- return;
+exit:
+ exception_exit(regs);
}
/*
@@ -555,14 +567,17 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
#ifdef CONFIG_X86_32
ignore_fpu_irq = 1;
#endif
-
+ exception_enter(regs);
math_error(regs, error_code, X86_TRAP_MF);
+ exception_exit(regs);
}
dotraplinkage void
do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
{
+ exception_enter(regs);
math_error(regs, error_code, X86_TRAP_XF);
+ exception_exit(regs);
}
dotraplinkage void
@@ -613,11 +628,12 @@ void math_state_restore(void)
}
__thread_fpu_begin(tsk);
+
/*
* Paranoid restore. send a SIGSEGV if we fail to restore the state.
*/
if (unlikely(restore_fpu_checking(tsk))) {
- __thread_fpu_end(tsk);
+ drop_init_fpu(tsk);
force_sig(SIGSEGV, tsk);
return;
}
@@ -629,6 +645,9 @@ EXPORT_SYMBOL_GPL(math_state_restore);
dotraplinkage void __kprobes
do_device_not_available(struct pt_regs *regs, long error_code)
{
+ exception_enter(regs);
+ BUG_ON(use_eager_fpu());
+
#ifdef CONFIG_MATH_EMULATION
if (read_cr0() & X86_CR0_EM) {
struct math_emu_info info = { };
@@ -637,6 +656,7 @@ do_device_not_available(struct pt_regs *regs, long error_code)
info.regs = regs;
math_emulate(&info);
+ exception_exit(regs);
return;
}
#endif
@@ -644,12 +664,15 @@ do_device_not_available(struct pt_regs *regs, long error_code)
#ifdef CONFIG_X86_32
conditional_sti(regs);
#endif
+ exception_exit(regs);
}
#ifdef CONFIG_X86_32
dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
{
siginfo_t info;
+
+ exception_enter(regs);
local_irq_enable();
info.si_signo = SIGILL;
@@ -657,10 +680,11 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
info.si_code = ILL_BADSTK;
info.si_addr = NULL;
if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
- X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
- return;
- do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
- &info);
+ X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) {
+ do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+ &info);
+ }
+ exception_exit(regs);
}
#endif
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 36fd42091fa..9538f00827a 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -41,6 +41,9 @@
/* Adjust the return address of a call insn */
#define UPROBE_FIX_CALL 0x2
+/* Instruction will modify TF, don't change it */
+#define UPROBE_FIX_SETF 0x4
+
#define UPROBE_FIX_RIP_AX 0x8000
#define UPROBE_FIX_RIP_CX 0x4000
@@ -239,6 +242,10 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn)
insn_get_opcode(insn); /* should be a nop */
switch (OPCODE1(insn)) {
+ case 0x9d:
+ /* popf */
+ auprobe->fixups |= UPROBE_FIX_SETF;
+ break;
case 0xc3: /* ret/lret */
case 0xcb:
case 0xc2:
@@ -646,7 +653,7 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
* Skip these instructions as per the currently known x86 ISA.
* 0x66* { 0x90 | 0x0f 0x1f | 0x0f 0x19 | 0x87 0xc0 }
*/
-bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
int i;
@@ -673,3 +680,46 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
}
return false;
}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+ bool ret = __skip_sstep(auprobe, regs);
+ if (ret && (regs->flags & X86_EFLAGS_TF))
+ send_sig(SIGTRAP, current, 0);
+ return ret;
+}
+
+void arch_uprobe_enable_step(struct arch_uprobe *auprobe)
+{
+ struct task_struct *task = current;
+ struct arch_uprobe_task *autask = &task->utask->autask;
+ struct pt_regs *regs = task_pt_regs(task);
+
+ autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
+
+ regs->flags |= X86_EFLAGS_TF;
+ if (test_tsk_thread_flag(task, TIF_BLOCKSTEP))
+ set_task_blockstep(task, false);
+}
+
+void arch_uprobe_disable_step(struct arch_uprobe *auprobe)
+{
+ struct task_struct *task = current;
+ struct arch_uprobe_task *autask = &task->utask->autask;
+ bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED);
+ struct pt_regs *regs = task_pt_regs(task);
+ /*
+ * The state of TIF_BLOCKSTEP was not saved so we can get an extra
+ * SIGTRAP if we do not clear TF. We need to examine the opcode to
+ * make it right.
+ */
+ if (unlikely(trapped)) {
+ if (!autask->saved_tf)
+ regs->flags &= ~X86_EFLAGS_TF;
+ } else {
+ if (autask->saved_tf)
+ send_sig(SIGTRAP, task, 0);
+ else if (!(auprobe->fixups & UPROBE_FIX_SETF))
+ regs->flags &= ~X86_EFLAGS_TF;
+ }
+}
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index 6020f6f5927..1330dd10295 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -13,9 +13,13 @@
#include <asm/ftrace.h>
#ifdef CONFIG_FUNCTION_TRACER
-/* mcount is defined in assembly */
+/* mcount and __fentry__ are defined in assembly */
+#ifdef CC_USING_FENTRY
+EXPORT_SYMBOL(__fentry__);
+#else
EXPORT_SYMBOL(mcount);
#endif
+#endif
EXPORT_SYMBOL(__get_user_1);
EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 9f3167e891e..7a3d075a814 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -26,7 +26,6 @@
void __cpuinit x86_init_noop(void) { }
void __init x86_init_uint_noop(unsigned int unused) { }
-void __init x86_init_pgd_noop(pgd_t *unused) { }
int __init iommu_init_noop(void) { return 0; }
void iommu_shutdown_noop(void) { }
@@ -68,8 +67,7 @@ struct x86_init_ops x86_init __initdata = {
},
.paging = {
- .pagetable_setup_start = native_pagetable_setup_start,
- .pagetable_setup_done = native_pagetable_setup_done,
+ .pagetable_init = native_pagetable_init,
},
.timers = {
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 3d3e2070911..ada87a329ed 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -10,9 +10,7 @@
#include <linux/compat.h>
#include <asm/i387.h>
#include <asm/fpu-internal.h>
-#ifdef CONFIG_IA32_EMULATION
-#include <asm/sigcontext32.h>
-#endif
+#include <asm/sigframe.h>
#include <asm/xcr.h>
/*
@@ -23,13 +21,9 @@ u64 pcntxt_mask;
/*
* Represents init state for the supported extended state.
*/
-static struct xsave_struct *init_xstate_buf;
-
-struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-struct _fpx_sw_bytes fx_sw_reserved_ia32;
-#endif
+struct xsave_struct *init_xstate_buf;
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
/*
@@ -44,9 +38,9 @@ static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
*/
void __sanitize_i387_state(struct task_struct *tsk)
{
- u64 xstate_bv;
- int feature_bit = 0x2;
struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
+ int feature_bit = 0x2;
+ u64 xstate_bv;
if (!fx)
return;
@@ -104,213 +98,326 @@ void __sanitize_i387_state(struct task_struct *tsk)
* Check for the presence of extended state information in the
* user fpstate pointer in the sigcontext.
*/
-int check_for_xstate(struct i387_fxsave_struct __user *buf,
- void __user *fpstate,
- struct _fpx_sw_bytes *fx_sw_user)
+static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
+ void __user *fpstate,
+ struct _fpx_sw_bytes *fx_sw)
{
int min_xstate_size = sizeof(struct i387_fxsave_struct) +
sizeof(struct xsave_hdr_struct);
unsigned int magic2;
- int err;
- err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
- sizeof(struct _fpx_sw_bytes));
- if (err)
- return -EFAULT;
+ if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+ return -1;
- /*
- * First Magic check failed.
- */
- if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
- return -EINVAL;
+ /* Check for the first magic field and other error scenarios. */
+ if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+ fx_sw->xstate_size < min_xstate_size ||
+ fx_sw->xstate_size > xstate_size ||
+ fx_sw->xstate_size > fx_sw->extended_size)
+ return -1;
/*
- * Check for error scenarios.
- */
- if (fx_sw_user->xstate_size < min_xstate_size ||
- fx_sw_user->xstate_size > xstate_size ||
- fx_sw_user->xstate_size > fx_sw_user->extended_size)
- return -EINVAL;
-
- err = __get_user(magic2, (__u32 *) (((void *)fpstate) +
- fx_sw_user->extended_size -
- FP_XSTATE_MAGIC2_SIZE));
- if (err)
- return err;
- /*
* Check for the presence of second magic word at the end of memory
* layout. This detects the case where the user just copied the legacy
* fpstate layout with out copying the extended state information
* in the memory layout.
*/
- if (magic2 != FP_XSTATE_MAGIC2)
- return -EFAULT;
+ if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+ || magic2 != FP_XSTATE_MAGIC2)
+ return -1;
return 0;
}
-#ifdef CONFIG_X86_64
/*
* Signal frame handlers.
*/
-
-int save_i387_xstate(void __user *buf)
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
{
- struct task_struct *tsk = current;
- int err = 0;
-
- if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
- return -EACCES;
+ if (use_fxsr()) {
+ struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct user_i387_ia32_struct env;
+ struct _fpstate_ia32 __user *fp = buf;
- BUG_ON(sig_xstate_size < xstate_size);
+ convert_from_fxsr(&env, tsk);
- if ((unsigned long)buf % 64)
- pr_err("%s: bad fpstate %p\n", __func__, buf);
-
- if (!used_math())
- return 0;
-
- if (user_has_fpu()) {
- if (use_xsave())
- err = xsave_user(buf);
- else
- err = fxsave_user(buf);
-
- if (err)
- return err;
- user_fpu_end();
+ if (__copy_to_user(buf, &env, sizeof(env)) ||
+ __put_user(xsave->i387.swd, &fp->status) ||
+ __put_user(X86_FXSR_MAGIC, &fp->magic))
+ return -1;
} else {
- sanitize_i387_state(tsk);
- if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
- xstate_size))
+ struct i387_fsave_struct __user *fp = buf;
+ u32 swd;
+ if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
return -1;
}
- clear_used_math(); /* trigger finit */
+ return 0;
+}
- if (use_xsave()) {
- struct _fpstate __user *fx = buf;
- struct _xstate __user *x = buf;
- u64 xstate_bv;
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
+{
+ struct xsave_struct __user *x = buf;
+ struct _fpx_sw_bytes *sw_bytes;
+ u32 xstate_bv;
+ int err;
- err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
- sizeof(struct _fpx_sw_bytes));
+ /* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+ sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+ err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
- err |= __put_user(FP_XSTATE_MAGIC2,
- (__u32 __user *) (buf + sig_xstate_size
- - FP_XSTATE_MAGIC2_SIZE));
+ if (!use_xsave())
+ return err;
- /*
- * Read the xstate_bv which we copied (directly from the cpu or
- * from the state in task struct) to the user buffers and
- * set the FP/SSE bits.
- */
- err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+ err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
- /*
- * For legacy compatible, we always set FP/SSE bits in the bit
- * vector while saving the state to the user context. This will
- * enable us capturing any changes(during sigreturn) to
- * the FP/SSE bits by the legacy applications which don't touch
- * xstate_bv in the xsave header.
- *
- * xsave aware apps can change the xstate_bv in the xsave
- * header as well as change any contents in the memory layout.
- * xrestore as part of sigreturn will capture all the changes.
- */
- xstate_bv |= XSTATE_FPSSE;
+ /*
+ * Read the xstate_bv which we copied (directly from the cpu or
+ * from the state in task struct) to the user buffers.
+ */
+ err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
- err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv);
+ /*
+ * For legacy compatible, we always set FP/SSE bits in the bit
+ * vector while saving the state to the user context. This will
+ * enable us capturing any changes(during sigreturn) to
+ * the FP/SSE bits by the legacy applications which don't touch
+ * xstate_bv in the xsave header.
+ *
+ * xsave aware apps can change the xstate_bv in the xsave
+ * header as well as change any contents in the memory layout.
+ * xrestore as part of sigreturn will capture all the changes.
+ */
+ xstate_bv |= XSTATE_FPSSE;
- if (err)
- return err;
- }
+ err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
- return 1;
+ return err;
+}
+
+static inline int save_user_xstate(struct xsave_struct __user *buf)
+{
+ int err;
+
+ if (use_xsave())
+ err = xsave_user(buf);
+ else if (use_fxsr())
+ err = fxsave_user((struct i387_fxsave_struct __user *) buf);
+ else
+ err = fsave_user((struct i387_fsave_struct __user *) buf);
+
+ if (unlikely(err) && __clear_user(buf, xstate_size))
+ err = -EFAULT;
+ return err;
}
/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE
- * state.
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ * state is copied.
+ * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ * buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ * buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
*/
-static int restore_user_xstate(void __user *buf)
+int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
{
- struct _fpx_sw_bytes fx_sw_user;
- u64 mask;
- int err;
+ struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
+ struct task_struct *tsk = current;
+ int ia32_fxstate = (buf != buf_fx);
- if (((unsigned long)buf % 64) ||
- check_for_xstate(buf, buf, &fx_sw_user))
- goto fx_only;
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
- mask = fx_sw_user.xstate_bv;
+ if (!access_ok(VERIFY_WRITE, buf, size))
+ return -EACCES;
- /*
- * restore the state passed by the user.
- */
- err = xrestore_user(buf, mask);
- if (err)
- return err;
+ if (!HAVE_HWFP)
+ return fpregs_soft_get(current, NULL, 0,
+ sizeof(struct user_i387_ia32_struct), NULL,
+ (struct _fpstate_ia32 __user *) buf) ? -1 : 1;
- /*
- * init the state skipped by the user.
- */
- mask = pcntxt_mask & ~mask;
- if (unlikely(mask))
- xrstor_state(init_xstate_buf, mask);
+ if (user_has_fpu()) {
+ /* Save the live register state to the user directly. */
+ if (save_user_xstate(buf_fx))
+ return -1;
+ /* Update the thread's fxstate to save the fsave header. */
+ if (ia32_fxstate)
+ fpu_fxsave(&tsk->thread.fpu);
+ } else {
+ sanitize_i387_state(tsk);
+ if (__copy_to_user(buf_fx, xsave, xstate_size))
+ return -1;
+ }
+
+ /* Save the fsave header for the 32-bit frames. */
+ if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+ return -1;
+
+ if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+ return -1;
+
+ drop_init_fpu(tsk); /* trigger finit */
return 0;
+}
-fx_only:
- /*
- * couldn't find the extended state information in the
- * memory layout. Restore just the FP/SSE and init all
- * the other extended state.
- */
- xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE);
- return fxrstor_checking((__force struct i387_fxsave_struct *)buf);
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+ struct user_i387_ia32_struct *ia32_env,
+ u64 xstate_bv, int fx_only)
+{
+ struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
+
+ if (use_xsave()) {
+ /* These bits must be zero. */
+ xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+
+ /*
+ * Init the state that is not present in the memory
+ * layout and not enabled by the OS.
+ */
+ if (fx_only)
+ xsave_hdr->xstate_bv = XSTATE_FPSSE;
+ else
+ xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
+ }
+
+ if (use_fxsr()) {
+ /*
+ * mscsr reserved bits must be masked to zero for security
+ * reasons.
+ */
+ xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+ convert_to_fxsr(tsk, ia32_env);
+ }
}
/*
- * This restores directly out of user space. Exceptions are handled.
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
*/
-int restore_i387_xstate(void __user *buf)
+static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
{
+ if (use_xsave()) {
+ if ((unsigned long)buf % 64 || fx_only) {
+ u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
+ xrstor_state(init_xstate_buf, init_bv);
+ return fxrstor_user(buf);
+ } else {
+ u64 init_bv = pcntxt_mask & ~xbv;
+ if (unlikely(init_bv))
+ xrstor_state(init_xstate_buf, init_bv);
+ return xrestore_user(buf, xbv);
+ }
+ } else if (use_fxsr()) {
+ return fxrstor_user(buf);
+ } else
+ return frstor_user(buf);
+}
+
+int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
+{
+ int ia32_fxstate = (buf != buf_fx);
struct task_struct *tsk = current;
- int err = 0;
+ int state_size = xstate_size;
+ u64 xstate_bv = 0;
+ int fx_only = 0;
+
+ ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+ config_enabled(CONFIG_IA32_EMULATION));
if (!buf) {
- if (used_math())
- goto clear;
+ drop_init_fpu(tsk);
return 0;
- } else
- if (!access_ok(VERIFY_READ, buf, sig_xstate_size))
- return -EACCES;
+ }
- if (!used_math()) {
- err = init_fpu(tsk);
- if (err)
- return err;
+ if (!access_ok(VERIFY_READ, buf, size))
+ return -EACCES;
+
+ if (!used_math() && init_fpu(tsk))
+ return -1;
+
+ if (!HAVE_HWFP) {
+ return fpregs_soft_set(current, NULL,
+ 0, sizeof(struct user_i387_ia32_struct),
+ NULL, buf) != 0;
}
- user_fpu_begin();
- if (use_xsave())
- err = restore_user_xstate(buf);
- else
- err = fxrstor_checking((__force struct i387_fxsave_struct *)
- buf);
- if (unlikely(err)) {
+ if (use_xsave()) {
+ struct _fpx_sw_bytes fx_sw_user;
+ if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+ /*
+ * Couldn't find the extended state information in the
+ * memory layout. Restore just the FP/SSE and init all
+ * the other extended state.
+ */
+ state_size = sizeof(struct i387_fxsave_struct);
+ fx_only = 1;
+ } else {
+ state_size = fx_sw_user.xstate_size;
+ xstate_bv = fx_sw_user.xstate_bv;
+ }
+ }
+
+ if (ia32_fxstate) {
+ /*
+ * For 32-bit frames with fxstate, copy the user state to the
+ * thread's fpu state, reconstruct fxstate from the fsave
+ * header. Sanitize the copied state etc.
+ */
+ struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+ struct user_i387_ia32_struct env;
+ int err = 0;
+
+ /*
+ * Drop the current fpu which clears used_math(). This ensures
+ * that any context-switch during the copy of the new state,
+ * avoids the intermediate state from getting restored/saved.
+ * Thus avoiding the new restored state from getting corrupted.
+ * We will be ready to restore/save the state only after
+ * set_used_math() is again set.
+ */
+ drop_fpu(tsk);
+
+ if (__copy_from_user(xsave, buf_fx, state_size) ||
+ __copy_from_user(&env, buf, sizeof(env))) {
+ err = -1;
+ } else {
+ sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
+ set_used_math();
+ }
+
+ if (use_eager_fpu())
+ math_state_restore();
+
+ return err;
+ } else {
/*
- * Encountered an error while doing the restore from the
- * user buffer, clear the fpu state.
+ * For 64-bit frames and 32-bit fsave frames, restore the user
+ * state to the registers directly (with exceptions handled).
*/
-clear:
- clear_fpu(tsk);
- clear_used_math();
+ user_fpu_begin();
+ if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
+ drop_init_fpu(tsk);
+ return -1;
+ }
}
- return err;
+
+ return 0;
}
-#endif
/*
* Prepare the SW reserved portion of the fxsave memory layout, indicating
@@ -321,31 +428,22 @@ clear:
*/
static void prepare_fx_sw_frame(void)
{
- int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) +
- FP_XSTATE_MAGIC2_SIZE;
+ int fsave_header_size = sizeof(struct i387_fsave_struct);
+ int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
- sig_xstate_size = sizeof(struct _fpstate) + size_extended;
-
-#ifdef CONFIG_IA32_EMULATION
- sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended;
-#endif
-
- memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved));
+ if (config_enabled(CONFIG_X86_32))
+ size += fsave_header_size;
fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
- fx_sw_reserved.extended_size = sig_xstate_size;
+ fx_sw_reserved.extended_size = size;
fx_sw_reserved.xstate_bv = pcntxt_mask;
fx_sw_reserved.xstate_size = xstate_size;
-#ifdef CONFIG_IA32_EMULATION
- memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved,
- sizeof(struct _fpx_sw_bytes));
- fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size;
-#endif
-}
-#ifdef CONFIG_X86_64
-unsigned int sig_xstate_size = sizeof(struct _fpstate);
-#endif
+ if (config_enabled(CONFIG_IA32_EMULATION)) {
+ fx_sw_reserved_ia32 = fx_sw_reserved;
+ fx_sw_reserved_ia32.extended_size += fsave_header_size;
+ }
+}
/*
* Enable the extended processor state save/restore feature
@@ -384,19 +482,21 @@ static void __init setup_xstate_features(void)
/*
* setup the xstate image representing the init state
*/
-static void __init setup_xstate_init(void)
+static void __init setup_init_fpu_buf(void)
{
- setup_xstate_features();
-
/*
* Setup init_xstate_buf to represent the init state of
* all the features managed by the xsave
*/
init_xstate_buf = alloc_bootmem_align(xstate_size,
__alignof__(struct xsave_struct));
- init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
+ fx_finit(&init_xstate_buf->i387);
+
+ if (!cpu_has_xsave)
+ return;
+
+ setup_xstate_features();
- clts();
/*
* Init all the features state with header_bv being 0x0
*/
@@ -406,9 +506,21 @@ static void __init setup_xstate_init(void)
* of any feature which is not represented by all zero's.
*/
xsave_state(init_xstate_buf, -1);
- stts();
}
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static int __init eager_fpu_setup(char *s)
+{
+ if (!strcmp(s, "on"))
+ eagerfpu = ENABLE;
+ else if (!strcmp(s, "off"))
+ eagerfpu = DISABLE;
+ else if (!strcmp(s, "auto"))
+ eagerfpu = AUTO;
+ return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
/*
* Enable and initialize the xsave feature.
*/
@@ -445,8 +557,11 @@ static void __init xstate_enable_boot_cpu(void)
update_regset_xstate_info(xstate_size, pcntxt_mask);
prepare_fx_sw_frame();
+ setup_init_fpu_buf();
- setup_xstate_init();
+ /* Auto enable eagerfpu for xsaveopt */
+ if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+ eagerfpu = ENABLE;
pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
pcntxt_mask, xstate_size);
@@ -471,3 +586,43 @@ void __cpuinit xsave_init(void)
next_func = xstate_enable;
this_func();
}
+
+static inline void __init eager_fpu_init_bp(void)
+{
+ current->thread.fpu.state =
+ alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct));
+ if (!init_xstate_buf)
+ setup_init_fpu_buf();
+}
+
+void __cpuinit eager_fpu_init(void)
+{
+ static __refdata void (*boot_func)(void) = eager_fpu_init_bp;
+
+ clear_used_math();
+ current_thread_info()->status = 0;
+
+ if (eagerfpu == ENABLE)
+ setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+ if (!cpu_has_eager_fpu) {
+ stts();
+ return;
+ }
+
+ if (boot_func) {
+ boot_func();
+ boot_func = NULL;
+ }
+
+ /*
+ * This is same as math_state_restore(). But use_xsave() is
+ * not yet patched to use math_state_restore().
+ */
+ init_fpu(current);
+ __thread_fpu_begin(current);
+ if (cpu_has_xsave)
+ xrstor_state(init_xstate_buf, -1);
+ else
+ fxrstor_checking(&init_xstate_buf->i387);
+}
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a28f338843e..586f0005980 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -20,6 +20,7 @@ if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM
+ depends on HIGH_RES_TIMERS
# for device assignment:
depends on PCI
# for TASKSTATS/TASK_DELAY_ACCT:
@@ -37,6 +38,7 @@ config KVM
select TASK_DELAY_ACCT
select PERF_EVENTS
select HAVE_KVM_MSI
+ select HAVE_KVM_CPU_RELAX_INTERCEPT
---help---
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 4f579e8dcac..04d30401c5c 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o)
kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o)
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
- i8254.o timer.o cpuid.o pmu.o
+ i8254.o cpuid.o pmu.o
kvm-intel-y += vmx.o
kvm-amd-y += svm.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0595f1397b7..ec79e773342 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -316,7 +316,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
}
case 7: {
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- /* Mask ebx against host capbability word 9 */
+ /* Mask ebx against host capability word 9 */
if (index == 0) {
entry->ebx &= kvm_supported_word9_x86_features;
cpuid_mask(&entry->ebx, 9);
@@ -397,8 +397,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
break;
}
case KVM_CPUID_SIGNATURE: {
- char signature[12] = "KVMKVMKVM\0\0";
- u32 *sigptr = (u32 *)signature;
+ static const char signature[12] = "KVMKVMKVM\0\0";
+ const u32 *sigptr = (const u32 *)signature;
entry->eax = KVM_CPUID_FEATURES;
entry->ebx = sigptr[0];
entry->ecx = sigptr[1];
@@ -484,10 +484,10 @@ struct kvm_cpuid_param {
u32 func;
u32 idx;
bool has_leaf_count;
- bool (*qualifier)(struct kvm_cpuid_param *param);
+ bool (*qualifier)(const struct kvm_cpuid_param *param);
};
-static bool is_centaur_cpu(struct kvm_cpuid_param *param)
+static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
{
return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
}
@@ -498,7 +498,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 *cpuid_entries;
int limit, nent = 0, r = -E2BIG, i;
u32 func;
- static struct kvm_cpuid_param param[] = {
+ static const struct kvm_cpuid_param param[] = {
{ .func = 0, .has_leaf_count = true },
{ .func = 0x80000000, .has_leaf_count = true },
{ .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true },
@@ -517,7 +517,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
r = 0;
for (i = 0; i < ARRAY_SIZE(param); i++) {
- struct kvm_cpuid_param *ent = &param[i];
+ const struct kvm_cpuid_param *ent = &param[i];
if (ent->qualifier && !ent->qualifier(ent))
continue;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a3b57a27be8..39171cb307e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -161,9 +161,9 @@ struct opcode {
u64 intercept : 8;
union {
int (*execute)(struct x86_emulate_ctxt *ctxt);
- struct opcode *group;
- struct group_dual *gdual;
- struct gprefix *gprefix;
+ const struct opcode *group;
+ const struct group_dual *gdual;
+ const struct gprefix *gprefix;
} u;
int (*check_perm)(struct x86_emulate_ctxt *ctxt);
};
@@ -202,6 +202,42 @@ struct gprefix {
#define EFLG_RESERVED_ZEROS_MASK 0xffc0802a
#define EFLG_RESERVED_ONE_MASK 2
+static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ if (!(ctxt->regs_valid & (1 << nr))) {
+ ctxt->regs_valid |= 1 << nr;
+ ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr);
+ }
+ return ctxt->_regs[nr];
+}
+
+static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ ctxt->regs_valid |= 1 << nr;
+ ctxt->regs_dirty |= 1 << nr;
+ return &ctxt->_regs[nr];
+}
+
+static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ reg_read(ctxt, nr);
+ return reg_write(ctxt, nr);
+}
+
+static void writeback_registers(struct x86_emulate_ctxt *ctxt)
+{
+ unsigned reg;
+
+ for_each_set_bit(reg, (ulong *)&ctxt->regs_dirty, 16)
+ ctxt->ops->write_gpr(ctxt, reg, ctxt->_regs[reg]);
+}
+
+static void invalidate_registers(struct x86_emulate_ctxt *ctxt)
+{
+ ctxt->regs_dirty = 0;
+ ctxt->regs_valid = 0;
+}
+
/*
* Instruction emulation:
* Most instructions are emulated directly via a fragment of inline assembly
@@ -374,8 +410,8 @@ struct gprefix {
#define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex) \
do { \
unsigned long _tmp; \
- ulong *rax = &(ctxt)->regs[VCPU_REGS_RAX]; \
- ulong *rdx = &(ctxt)->regs[VCPU_REGS_RDX]; \
+ ulong *rax = reg_rmw((ctxt), VCPU_REGS_RAX); \
+ ulong *rdx = reg_rmw((ctxt), VCPU_REGS_RDX); \
\
__asm__ __volatile__ ( \
_PRE_EFLAGS("0", "5", "1") \
@@ -494,7 +530,7 @@ register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, in
static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
{
- masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc);
+ masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
}
static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -632,8 +668,6 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
la = seg_base(ctxt, addr.seg) + addr.ea;
switch (ctxt->mode) {
- case X86EMUL_MODE_REAL:
- break;
case X86EMUL_MODE_PROT64:
if (((signed long)la << 16) >> 16 != la)
return emulate_gp(ctxt, 0);
@@ -655,7 +689,7 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
goto bad;
} else {
- /* exapand-down segment */
+ /* expand-down segment */
if (addr.ea <= lim || (u32)(addr.ea + size - 1) <= lim)
goto bad;
lim = desc.d ? 0xffffffff : 0xffff;
@@ -663,7 +697,10 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
goto bad;
}
cpl = ctxt->ops->cpl(ctxt);
- rpl = sel & 3;
+ if (ctxt->mode == X86EMUL_MODE_REAL)
+ rpl = 0;
+ else
+ rpl = sel & 3;
cpl = max(cpl, rpl);
if (!(desc.type & 8)) {
/* data segment */
@@ -688,9 +725,9 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
return X86EMUL_CONTINUE;
bad:
if (addr.seg == VCPU_SREG_SS)
- return emulate_ss(ctxt, addr.seg);
+ return emulate_ss(ctxt, sel);
else
- return emulate_gp(ctxt, addr.seg);
+ return emulate_gp(ctxt, sel);
}
static int linearize(struct x86_emulate_ctxt *ctxt,
@@ -786,14 +823,15 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
* pointer into the block that addresses the relevant register.
* @highbyte_regs specifies whether to decode AH,CH,DH,BH.
*/
-static void *decode_register(u8 modrm_reg, unsigned long *regs,
+static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg,
int highbyte_regs)
{
void *p;
- p = &regs[modrm_reg];
if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8)
- p = (unsigned char *)&regs[modrm_reg & 3] + 1;
+ p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1;
+ else
+ p = reg_rmw(ctxt, modrm_reg);
return p;
}
@@ -871,23 +909,23 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
{
ctxt->ops->get_fpu(ctxt);
switch (reg) {
- case 0: asm("movdqu %%xmm0, %0" : "=m"(*data)); break;
- case 1: asm("movdqu %%xmm1, %0" : "=m"(*data)); break;
- case 2: asm("movdqu %%xmm2, %0" : "=m"(*data)); break;
- case 3: asm("movdqu %%xmm3, %0" : "=m"(*data)); break;
- case 4: asm("movdqu %%xmm4, %0" : "=m"(*data)); break;
- case 5: asm("movdqu %%xmm5, %0" : "=m"(*data)); break;
- case 6: asm("movdqu %%xmm6, %0" : "=m"(*data)); break;
- case 7: asm("movdqu %%xmm7, %0" : "=m"(*data)); break;
+ case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
+ case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
+ case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break;
+ case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break;
+ case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break;
+ case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break;
+ case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break;
+ case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break;
#ifdef CONFIG_X86_64
- case 8: asm("movdqu %%xmm8, %0" : "=m"(*data)); break;
- case 9: asm("movdqu %%xmm9, %0" : "=m"(*data)); break;
- case 10: asm("movdqu %%xmm10, %0" : "=m"(*data)); break;
- case 11: asm("movdqu %%xmm11, %0" : "=m"(*data)); break;
- case 12: asm("movdqu %%xmm12, %0" : "=m"(*data)); break;
- case 13: asm("movdqu %%xmm13, %0" : "=m"(*data)); break;
- case 14: asm("movdqu %%xmm14, %0" : "=m"(*data)); break;
- case 15: asm("movdqu %%xmm15, %0" : "=m"(*data)); break;
+ case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break;
+ case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break;
+ case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break;
+ case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break;
+ case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break;
+ case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break;
+ case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break;
+ case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break;
#endif
default: BUG();
}
@@ -899,23 +937,23 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
{
ctxt->ops->get_fpu(ctxt);
switch (reg) {
- case 0: asm("movdqu %0, %%xmm0" : : "m"(*data)); break;
- case 1: asm("movdqu %0, %%xmm1" : : "m"(*data)); break;
- case 2: asm("movdqu %0, %%xmm2" : : "m"(*data)); break;
- case 3: asm("movdqu %0, %%xmm3" : : "m"(*data)); break;
- case 4: asm("movdqu %0, %%xmm4" : : "m"(*data)); break;
- case 5: asm("movdqu %0, %%xmm5" : : "m"(*data)); break;
- case 6: asm("movdqu %0, %%xmm6" : : "m"(*data)); break;
- case 7: asm("movdqu %0, %%xmm7" : : "m"(*data)); break;
+ case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
+ case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
+ case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break;
+ case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break;
+ case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break;
+ case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break;
+ case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break;
+ case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break;
#ifdef CONFIG_X86_64
- case 8: asm("movdqu %0, %%xmm8" : : "m"(*data)); break;
- case 9: asm("movdqu %0, %%xmm9" : : "m"(*data)); break;
- case 10: asm("movdqu %0, %%xmm10" : : "m"(*data)); break;
- case 11: asm("movdqu %0, %%xmm11" : : "m"(*data)); break;
- case 12: asm("movdqu %0, %%xmm12" : : "m"(*data)); break;
- case 13: asm("movdqu %0, %%xmm13" : : "m"(*data)); break;
- case 14: asm("movdqu %0, %%xmm14" : : "m"(*data)); break;
- case 15: asm("movdqu %0, %%xmm15" : : "m"(*data)); break;
+ case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break;
+ case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break;
+ case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break;
+ case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break;
+ case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break;
+ case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break;
+ case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break;
+ case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break;
#endif
default: BUG();
}
@@ -982,10 +1020,10 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
op->type = OP_REG;
if (ctxt->d & ByteOp) {
- op->addr.reg = decode_register(reg, ctxt->regs, highbyte_regs);
+ op->addr.reg = decode_register(ctxt, reg, highbyte_regs);
op->bytes = 1;
} else {
- op->addr.reg = decode_register(reg, ctxt->regs, 0);
+ op->addr.reg = decode_register(ctxt, reg, 0);
op->bytes = ctxt->op_bytes;
}
fetch_register_operand(op);
@@ -1020,8 +1058,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
if (ctxt->modrm_mod == 3) {
op->type = OP_REG;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
- op->addr.reg = decode_register(ctxt->modrm_rm,
- ctxt->regs, ctxt->d & ByteOp);
+ op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp);
if (ctxt->d & Sse) {
op->type = OP_XMM;
op->bytes = 16;
@@ -1042,10 +1079,10 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
op->type = OP_MEM;
if (ctxt->ad_bytes == 2) {
- unsigned bx = ctxt->regs[VCPU_REGS_RBX];
- unsigned bp = ctxt->regs[VCPU_REGS_RBP];
- unsigned si = ctxt->regs[VCPU_REGS_RSI];
- unsigned di = ctxt->regs[VCPU_REGS_RDI];
+ unsigned bx = reg_read(ctxt, VCPU_REGS_RBX);
+ unsigned bp = reg_read(ctxt, VCPU_REGS_RBP);
+ unsigned si = reg_read(ctxt, VCPU_REGS_RSI);
+ unsigned di = reg_read(ctxt, VCPU_REGS_RDI);
/* 16-bit ModR/M decode. */
switch (ctxt->modrm_mod) {
@@ -1102,17 +1139,17 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0)
modrm_ea += insn_fetch(s32, ctxt);
else {
- modrm_ea += ctxt->regs[base_reg];
+ modrm_ea += reg_read(ctxt, base_reg);
adjust_modrm_seg(ctxt, base_reg);
}
if (index_reg != 4)
- modrm_ea += ctxt->regs[index_reg] << scale;
+ modrm_ea += reg_read(ctxt, index_reg) << scale;
} else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) {
if (ctxt->mode == X86EMUL_MODE_PROT64)
ctxt->rip_relative = 1;
} else {
base_reg = ctxt->modrm_rm;
- modrm_ea += ctxt->regs[base_reg];
+ modrm_ea += reg_read(ctxt, base_reg);
adjust_modrm_seg(ctxt, base_reg);
}
switch (ctxt->modrm_mod) {
@@ -1179,24 +1216,21 @@ static int read_emulated(struct x86_emulate_ctxt *ctxt,
int rc;
struct read_cache *mc = &ctxt->mem_read;
- while (size) {
- int n = min(size, 8u);
- size -= n;
- if (mc->pos < mc->end)
- goto read_cached;
+ if (mc->pos < mc->end)
+ goto read_cached;
- rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, n,
- &ctxt->exception);
- if (rc != X86EMUL_CONTINUE)
- return rc;
- mc->end += n;
+ WARN_ON((mc->end + size) >= sizeof(mc->data));
- read_cached:
- memcpy(dest, mc->data + mc->pos, n);
- mc->pos += n;
- dest += n;
- addr += n;
- }
+ rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, size,
+ &ctxt->exception);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ mc->end += size;
+
+read_cached:
+ memcpy(dest, mc->data + mc->pos, size);
+ mc->pos += size;
return X86EMUL_CONTINUE;
}
@@ -1253,10 +1287,10 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
if (rc->pos == rc->end) { /* refill pio read ahead */
unsigned int in_page, n;
unsigned int count = ctxt->rep_prefix ?
- address_mask(ctxt, ctxt->regs[VCPU_REGS_RCX]) : 1;
+ address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1;
in_page = (ctxt->eflags & EFLG_DF) ?
- offset_in_page(ctxt->regs[VCPU_REGS_RDI]) :
- PAGE_SIZE - offset_in_page(ctxt->regs[VCPU_REGS_RDI]);
+ offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) :
+ PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI));
n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size,
count);
if (n == 0)
@@ -1267,8 +1301,15 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
rc->end = n * size;
}
- memcpy(dest, rc->data + rc->pos, size);
- rc->pos += size;
+ if (ctxt->rep_prefix && !(ctxt->eflags & EFLG_DF)) {
+ ctxt->dst.data = rc->data + rc->pos;
+ ctxt->dst.type = OP_MEM_STR;
+ ctxt->dst.count = (rc->end - rc->pos) / size;
+ rc->pos = rc->end;
+ } else {
+ memcpy(dest, rc->data + rc->pos, size);
+ rc->pos += size;
+ }
return 1;
}
@@ -1291,7 +1332,7 @@ static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt,
static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
u16 selector, struct desc_ptr *dt)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
if (selector & 1 << 2) {
struct desc_struct desc;
@@ -1355,19 +1396,15 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
ulong desc_addr;
int ret;
+ u16 dummy;
memset(&seg_desc, 0, sizeof seg_desc);
if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86)
|| ctxt->mode == X86EMUL_MODE_REAL) {
/* set real mode segment descriptor */
+ ctxt->ops->get_segment(ctxt, &dummy, &seg_desc, NULL, seg);
set_desc_base(&seg_desc, selector << 4);
- set_desc_limit(&seg_desc, 0xffff);
- seg_desc.type = 3;
- seg_desc.p = 1;
- seg_desc.s = 1;
- if (ctxt->mode == X86EMUL_MODE_VM86)
- seg_desc.dpl = 3;
goto load;
}
@@ -1396,7 +1433,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
err_code = selector & 0xfffc;
err_vec = GP_VECTOR;
- /* can't load system descriptor into segment selecor */
+ /* can't load system descriptor into segment selector */
if (seg <= VCPU_SREG_GS && !seg_desc.s)
goto exception;
@@ -1516,6 +1553,14 @@ static int writeback(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
break;
+ case OP_MEM_STR:
+ rc = segmented_write(ctxt,
+ ctxt->dst.addr.mem,
+ ctxt->dst.data,
+ ctxt->dst.bytes * ctxt->dst.count);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ break;
case OP_XMM:
write_sse_reg(ctxt, &ctxt->dst.vec_val, ctxt->dst.addr.xmm);
break;
@@ -1536,7 +1581,7 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes)
struct segmented_address addr;
rsp_increment(ctxt, -bytes);
- addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
+ addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt);
addr.seg = VCPU_SREG_SS;
return segmented_write(ctxt, addr, data, bytes);
@@ -1555,7 +1600,7 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt,
int rc;
struct segmented_address addr;
- addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt);
+ addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt);
addr.seg = VCPU_SREG_SS;
rc = segmented_read(ctxt, addr, dest, len);
if (rc != X86EMUL_CONTINUE)
@@ -1623,26 +1668,28 @@ static int em_enter(struct x86_emulate_ctxt *ctxt)
int rc;
unsigned frame_size = ctxt->src.val;
unsigned nesting_level = ctxt->src2.val & 31;
+ ulong rbp;
if (nesting_level)
return X86EMUL_UNHANDLEABLE;
- rc = push(ctxt, &ctxt->regs[VCPU_REGS_RBP], stack_size(ctxt));
+ rbp = reg_read(ctxt, VCPU_REGS_RBP);
+ rc = push(ctxt, &rbp, stack_size(ctxt));
if (rc != X86EMUL_CONTINUE)
return rc;
- assign_masked(&ctxt->regs[VCPU_REGS_RBP], ctxt->regs[VCPU_REGS_RSP],
+ assign_masked(reg_rmw(ctxt, VCPU_REGS_RBP), reg_read(ctxt, VCPU_REGS_RSP),
stack_mask(ctxt));
- assign_masked(&ctxt->regs[VCPU_REGS_RSP],
- ctxt->regs[VCPU_REGS_RSP] - frame_size,
+ assign_masked(reg_rmw(ctxt, VCPU_REGS_RSP),
+ reg_read(ctxt, VCPU_REGS_RSP) - frame_size,
stack_mask(ctxt));
return X86EMUL_CONTINUE;
}
static int em_leave(struct x86_emulate_ctxt *ctxt)
{
- assign_masked(&ctxt->regs[VCPU_REGS_RSP], ctxt->regs[VCPU_REGS_RBP],
+ assign_masked(reg_rmw(ctxt, VCPU_REGS_RSP), reg_read(ctxt, VCPU_REGS_RBP),
stack_mask(ctxt));
- return emulate_pop(ctxt, &ctxt->regs[VCPU_REGS_RBP], ctxt->op_bytes);
+ return emulate_pop(ctxt, reg_rmw(ctxt, VCPU_REGS_RBP), ctxt->op_bytes);
}
static int em_push_sreg(struct x86_emulate_ctxt *ctxt)
@@ -1670,13 +1717,13 @@ static int em_pop_sreg(struct x86_emulate_ctxt *ctxt)
static int em_pusha(struct x86_emulate_ctxt *ctxt)
{
- unsigned long old_esp = ctxt->regs[VCPU_REGS_RSP];
+ unsigned long old_esp = reg_read(ctxt, VCPU_REGS_RSP);
int rc = X86EMUL_CONTINUE;
int reg = VCPU_REGS_RAX;
while (reg <= VCPU_REGS_RDI) {
(reg == VCPU_REGS_RSP) ?
- (ctxt->src.val = old_esp) : (ctxt->src.val = ctxt->regs[reg]);
+ (ctxt->src.val = old_esp) : (ctxt->src.val = reg_read(ctxt, reg));
rc = em_push(ctxt);
if (rc != X86EMUL_CONTINUE)
@@ -1705,7 +1752,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
--reg;
}
- rc = emulate_pop(ctxt, &ctxt->regs[reg], ctxt->op_bytes);
+ rc = emulate_pop(ctxt, reg_rmw(ctxt, reg), ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
break;
--reg;
@@ -1713,9 +1760,9 @@ static int em_popa(struct x86_emulate_ctxt *ctxt)
return rc;
}
-int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
+static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
int rc;
struct desc_ptr dt;
gva_t cs_addr;
@@ -1762,11 +1809,22 @@ int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
return rc;
}
+int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq)
+{
+ int rc;
+
+ invalidate_registers(ctxt);
+ rc = __emulate_int_real(ctxt, irq);
+ if (rc == X86EMUL_CONTINUE)
+ writeback_registers(ctxt);
+ return rc;
+}
+
static int emulate_int(struct x86_emulate_ctxt *ctxt, int irq)
{
switch(ctxt->mode) {
case X86EMUL_MODE_REAL:
- return emulate_int_real(ctxt, irq);
+ return __emulate_int_real(ctxt, irq);
case X86EMUL_MODE_VM86:
case X86EMUL_MODE_PROT16:
case X86EMUL_MODE_PROT32:
@@ -1973,14 +2031,14 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
{
u64 old = ctxt->dst.orig_val64;
- if (((u32) (old >> 0) != (u32) ctxt->regs[VCPU_REGS_RAX]) ||
- ((u32) (old >> 32) != (u32) ctxt->regs[VCPU_REGS_RDX])) {
- ctxt->regs[VCPU_REGS_RAX] = (u32) (old >> 0);
- ctxt->regs[VCPU_REGS_RDX] = (u32) (old >> 32);
+ if (((u32) (old >> 0) != (u32) reg_read(ctxt, VCPU_REGS_RAX)) ||
+ ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) {
+ *reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0);
+ *reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32);
ctxt->eflags &= ~EFLG_ZF;
} else {
- ctxt->dst.val64 = ((u64)ctxt->regs[VCPU_REGS_RCX] << 32) |
- (u32) ctxt->regs[VCPU_REGS_RBX];
+ ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) |
+ (u32) reg_read(ctxt, VCPU_REGS_RBX);
ctxt->eflags |= EFLG_ZF;
}
@@ -2016,7 +2074,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
{
/* Save real source value, then compare EAX against destination. */
ctxt->src.orig_val = ctxt->src.val;
- ctxt->src.val = ctxt->regs[VCPU_REGS_RAX];
+ ctxt->src.val = reg_read(ctxt, VCPU_REGS_RAX);
emulate_2op_SrcV(ctxt, "cmp");
if (ctxt->eflags & EFLG_ZF) {
@@ -2025,7 +2083,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
} else {
/* Failure: write the value we saw to EAX. */
ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX];
+ ctxt->dst.addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX);
}
return X86EMUL_CONTINUE;
}
@@ -2050,12 +2108,6 @@ static void
setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
struct desc_struct *cs, struct desc_struct *ss)
{
- u16 selector;
-
- memset(cs, 0, sizeof(struct desc_struct));
- ctxt->ops->get_segment(ctxt, &selector, cs, NULL, VCPU_SREG_CS);
- memset(ss, 0, sizeof(struct desc_struct));
-
cs->l = 0; /* will be adjusted later */
set_desc_base(cs, 0); /* flat segment */
cs->g = 1; /* 4kb granularity */
@@ -2065,6 +2117,7 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
cs->dpl = 0; /* will be adjusted later */
cs->p = 1;
cs->d = 1;
+ cs->avl = 0;
set_desc_base(ss, 0); /* flat segment */
set_desc_limit(ss, 0xfffff); /* 4GB limit */
@@ -2074,6 +2127,8 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
ss->d = 1; /* 32bit stack segment */
ss->dpl = 0;
ss->p = 1;
+ ss->l = 0;
+ ss->avl = 0;
}
static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
@@ -2089,7 +2144,7 @@ static bool vendor_intel(struct x86_emulate_ctxt *ctxt)
static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
u32 eax, ebx, ecx, edx;
/*
@@ -2133,7 +2188,7 @@ static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
static int em_syscall(struct x86_emulate_ctxt *ctxt)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
u64 msr_data;
u16 cs_sel, ss_sel;
@@ -2165,10 +2220,10 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
- ctxt->regs[VCPU_REGS_RCX] = ctxt->_eip;
+ *reg_write(ctxt, VCPU_REGS_RCX) = ctxt->_eip;
if (efer & EFER_LMA) {
#ifdef CONFIG_X86_64
- ctxt->regs[VCPU_REGS_R11] = ctxt->eflags & ~EFLG_RF;
+ *reg_write(ctxt, VCPU_REGS_R11) = ctxt->eflags & ~EFLG_RF;
ops->get_msr(ctxt,
ctxt->mode == X86EMUL_MODE_PROT64 ?
@@ -2191,7 +2246,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
static int em_sysenter(struct x86_emulate_ctxt *ctxt)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
u64 msr_data;
u16 cs_sel, ss_sel;
@@ -2228,6 +2283,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
if (msr_data == 0x0)
return emulate_gp(ctxt, 0);
break;
+ default:
+ break;
}
ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
@@ -2247,14 +2304,14 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
ctxt->_eip = msr_data;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
- ctxt->regs[VCPU_REGS_RSP] = msr_data;
+ *reg_write(ctxt, VCPU_REGS_RSP) = msr_data;
return X86EMUL_CONTINUE;
}
static int em_sysexit(struct x86_emulate_ctxt *ctxt)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
u64 msr_data;
int usermode;
@@ -2297,8 +2354,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
- ctxt->_eip = ctxt->regs[VCPU_REGS_RDX];
- ctxt->regs[VCPU_REGS_RSP] = ctxt->regs[VCPU_REGS_RCX];
+ ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX);
+ *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX);
return X86EMUL_CONTINUE;
}
@@ -2317,7 +2374,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
u16 port, u16 len)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct tr_seg;
u32 base3;
int r;
@@ -2367,14 +2424,14 @@ static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
{
tss->ip = ctxt->_eip;
tss->flag = ctxt->eflags;
- tss->ax = ctxt->regs[VCPU_REGS_RAX];
- tss->cx = ctxt->regs[VCPU_REGS_RCX];
- tss->dx = ctxt->regs[VCPU_REGS_RDX];
- tss->bx = ctxt->regs[VCPU_REGS_RBX];
- tss->sp = ctxt->regs[VCPU_REGS_RSP];
- tss->bp = ctxt->regs[VCPU_REGS_RBP];
- tss->si = ctxt->regs[VCPU_REGS_RSI];
- tss->di = ctxt->regs[VCPU_REGS_RDI];
+ tss->ax = reg_read(ctxt, VCPU_REGS_RAX);
+ tss->cx = reg_read(ctxt, VCPU_REGS_RCX);
+ tss->dx = reg_read(ctxt, VCPU_REGS_RDX);
+ tss->bx = reg_read(ctxt, VCPU_REGS_RBX);
+ tss->sp = reg_read(ctxt, VCPU_REGS_RSP);
+ tss->bp = reg_read(ctxt, VCPU_REGS_RBP);
+ tss->si = reg_read(ctxt, VCPU_REGS_RSI);
+ tss->di = reg_read(ctxt, VCPU_REGS_RDI);
tss->es = get_segment_selector(ctxt, VCPU_SREG_ES);
tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS);
@@ -2390,14 +2447,14 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
ctxt->_eip = tss->ip;
ctxt->eflags = tss->flag | 2;
- ctxt->regs[VCPU_REGS_RAX] = tss->ax;
- ctxt->regs[VCPU_REGS_RCX] = tss->cx;
- ctxt->regs[VCPU_REGS_RDX] = tss->dx;
- ctxt->regs[VCPU_REGS_RBX] = tss->bx;
- ctxt->regs[VCPU_REGS_RSP] = tss->sp;
- ctxt->regs[VCPU_REGS_RBP] = tss->bp;
- ctxt->regs[VCPU_REGS_RSI] = tss->si;
- ctxt->regs[VCPU_REGS_RDI] = tss->di;
+ *reg_write(ctxt, VCPU_REGS_RAX) = tss->ax;
+ *reg_write(ctxt, VCPU_REGS_RCX) = tss->cx;
+ *reg_write(ctxt, VCPU_REGS_RDX) = tss->dx;
+ *reg_write(ctxt, VCPU_REGS_RBX) = tss->bx;
+ *reg_write(ctxt, VCPU_REGS_RSP) = tss->sp;
+ *reg_write(ctxt, VCPU_REGS_RBP) = tss->bp;
+ *reg_write(ctxt, VCPU_REGS_RSI) = tss->si;
+ *reg_write(ctxt, VCPU_REGS_RDI) = tss->di;
/*
* SDM says that segment selectors are loaded before segment
@@ -2410,7 +2467,7 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS);
/*
- * Now load segment descriptors. If fault happenes at this stage
+ * Now load segment descriptors. If fault happens at this stage
* it is handled in a context of new task
*/
ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR);
@@ -2436,7 +2493,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
u16 tss_selector, u16 old_tss_sel,
ulong old_tss_base, struct desc_struct *new_desc)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct tss_segment_16 tss_seg;
int ret;
u32 new_tss_base = get_desc_base(new_desc);
@@ -2482,14 +2539,14 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
tss->cr3 = ctxt->ops->get_cr(ctxt, 3);
tss->eip = ctxt->_eip;
tss->eflags = ctxt->eflags;
- tss->eax = ctxt->regs[VCPU_REGS_RAX];
- tss->ecx = ctxt->regs[VCPU_REGS_RCX];
- tss->edx = ctxt->regs[VCPU_REGS_RDX];
- tss->ebx = ctxt->regs[VCPU_REGS_RBX];
- tss->esp = ctxt->regs[VCPU_REGS_RSP];
- tss->ebp = ctxt->regs[VCPU_REGS_RBP];
- tss->esi = ctxt->regs[VCPU_REGS_RSI];
- tss->edi = ctxt->regs[VCPU_REGS_RDI];
+ tss->eax = reg_read(ctxt, VCPU_REGS_RAX);
+ tss->ecx = reg_read(ctxt, VCPU_REGS_RCX);
+ tss->edx = reg_read(ctxt, VCPU_REGS_RDX);
+ tss->ebx = reg_read(ctxt, VCPU_REGS_RBX);
+ tss->esp = reg_read(ctxt, VCPU_REGS_RSP);
+ tss->ebp = reg_read(ctxt, VCPU_REGS_RBP);
+ tss->esi = reg_read(ctxt, VCPU_REGS_RSI);
+ tss->edi = reg_read(ctxt, VCPU_REGS_RDI);
tss->es = get_segment_selector(ctxt, VCPU_SREG_ES);
tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS);
@@ -2511,14 +2568,14 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
ctxt->eflags = tss->eflags | 2;
/* General purpose registers */
- ctxt->regs[VCPU_REGS_RAX] = tss->eax;
- ctxt->regs[VCPU_REGS_RCX] = tss->ecx;
- ctxt->regs[VCPU_REGS_RDX] = tss->edx;
- ctxt->regs[VCPU_REGS_RBX] = tss->ebx;
- ctxt->regs[VCPU_REGS_RSP] = tss->esp;
- ctxt->regs[VCPU_REGS_RBP] = tss->ebp;
- ctxt->regs[VCPU_REGS_RSI] = tss->esi;
- ctxt->regs[VCPU_REGS_RDI] = tss->edi;
+ *reg_write(ctxt, VCPU_REGS_RAX) = tss->eax;
+ *reg_write(ctxt, VCPU_REGS_RCX) = tss->ecx;
+ *reg_write(ctxt, VCPU_REGS_RDX) = tss->edx;
+ *reg_write(ctxt, VCPU_REGS_RBX) = tss->ebx;
+ *reg_write(ctxt, VCPU_REGS_RSP) = tss->esp;
+ *reg_write(ctxt, VCPU_REGS_RBP) = tss->ebp;
+ *reg_write(ctxt, VCPU_REGS_RSI) = tss->esi;
+ *reg_write(ctxt, VCPU_REGS_RDI) = tss->edi;
/*
* SDM says that segment selectors are loaded before segment
@@ -2583,7 +2640,7 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
u16 tss_selector, u16 old_tss_sel,
ulong old_tss_base, struct desc_struct *new_desc)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct tss_segment_32 tss_seg;
int ret;
u32 new_tss_base = get_desc_base(new_desc);
@@ -2627,7 +2684,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
u16 tss_selector, int idt_index, int reason,
bool has_error_code, u32 error_code)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct curr_tss_desc, next_tss_desc;
int ret;
u16 old_tss_sel = get_segment_selector(ctxt, VCPU_SREG_TR);
@@ -2652,7 +2709,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
*
* 1. jmp/call/int to task gate: Check against DPL of the task gate
* 2. Exception/IRQ/iret: No check is performed
- * 3. jmp/call to TSS: Check agains DPL of the TSS
+ * 3. jmp/call to TSS: Check against DPL of the TSS
*/
if (reason == TASK_SWITCH_GATE) {
if (idt_index != -1) {
@@ -2693,7 +2750,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT;
/* set back link to prev task only if NT bit is set in eflags
- note that old_tss_sel is not used afetr this point */
+ note that old_tss_sel is not used after this point */
if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
old_tss_sel = 0xffff;
@@ -2733,26 +2790,28 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
{
int rc;
+ invalidate_registers(ctxt);
ctxt->_eip = ctxt->eip;
ctxt->dst.type = OP_NONE;
rc = emulator_do_task_switch(ctxt, tss_selector, idt_index, reason,
has_error_code, error_code);
- if (rc == X86EMUL_CONTINUE)
+ if (rc == X86EMUL_CONTINUE) {
ctxt->eip = ctxt->_eip;
+ writeback_registers(ctxt);
+ }
return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK;
}
-static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned seg,
- int reg, struct operand *op)
+static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg,
+ struct operand *op)
{
- int df = (ctxt->eflags & EFLG_DF) ? -1 : 1;
+ int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count;
- register_address_increment(ctxt, &ctxt->regs[reg], df * op->bytes);
- op->addr.mem.ea = register_address(ctxt, ctxt->regs[reg]);
- op->addr.mem.seg = seg;
+ register_address_increment(ctxt, reg_rmw(ctxt, reg), df * op->bytes);
+ op->addr.mem.ea = register_address(ctxt, reg_read(ctxt, reg));
}
static int em_das(struct x86_emulate_ctxt *ctxt)
@@ -2927,7 +2986,7 @@ static int em_cwd(struct x86_emulate_ctxt *ctxt)
{
ctxt->dst.type = OP_REG;
ctxt->dst.bytes = ctxt->src.bytes;
- ctxt->dst.addr.reg = &ctxt->regs[VCPU_REGS_RDX];
+ ctxt->dst.addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX);
ctxt->dst.val = ~((ctxt->src.val >> (ctxt->src.bytes * 8 - 1)) - 1);
return X86EMUL_CONTINUE;
@@ -2938,8 +2997,8 @@ static int em_rdtsc(struct x86_emulate_ctxt *ctxt)
u64 tsc = 0;
ctxt->ops->get_msr(ctxt, MSR_IA32_TSC, &tsc);
- ctxt->regs[VCPU_REGS_RAX] = (u32)tsc;
- ctxt->regs[VCPU_REGS_RDX] = tsc >> 32;
+ *reg_write(ctxt, VCPU_REGS_RAX) = (u32)tsc;
+ *reg_write(ctxt, VCPU_REGS_RDX) = tsc >> 32;
return X86EMUL_CONTINUE;
}
@@ -2947,10 +3006,10 @@ static int em_rdpmc(struct x86_emulate_ctxt *ctxt)
{
u64 pmc;
- if (ctxt->ops->read_pmc(ctxt, ctxt->regs[VCPU_REGS_RCX], &pmc))
+ if (ctxt->ops->read_pmc(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &pmc))
return emulate_gp(ctxt, 0);
- ctxt->regs[VCPU_REGS_RAX] = (u32)pmc;
- ctxt->regs[VCPU_REGS_RDX] = pmc >> 32;
+ *reg_write(ctxt, VCPU_REGS_RAX) = (u32)pmc;
+ *reg_write(ctxt, VCPU_REGS_RDX) = pmc >> 32;
return X86EMUL_CONTINUE;
}
@@ -2992,9 +3051,9 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
{
u64 msr_data;
- msr_data = (u32)ctxt->regs[VCPU_REGS_RAX]
- | ((u64)ctxt->regs[VCPU_REGS_RDX] << 32);
- if (ctxt->ops->set_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], msr_data))
+ msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX)
+ | ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32);
+ if (ctxt->ops->set_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), msr_data))
return emulate_gp(ctxt, 0);
return X86EMUL_CONTINUE;
@@ -3004,11 +3063,11 @@ static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
{
u64 msr_data;
- if (ctxt->ops->get_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], &msr_data))
+ if (ctxt->ops->get_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &msr_data))
return emulate_gp(ctxt, 0);
- ctxt->regs[VCPU_REGS_RAX] = (u32)msr_data;
- ctxt->regs[VCPU_REGS_RDX] = msr_data >> 32;
+ *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data;
+ *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32;
return X86EMUL_CONTINUE;
}
@@ -3188,8 +3247,8 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt)
static int em_loop(struct x86_emulate_ctxt *ctxt)
{
- register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RCX], -1);
- if ((address_mask(ctxt, ctxt->regs[VCPU_REGS_RCX]) != 0) &&
+ register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
+ if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
(ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
jmp_rel(ctxt, ctxt->src.val);
@@ -3198,7 +3257,7 @@ static int em_loop(struct x86_emulate_ctxt *ctxt)
static int em_jcxz(struct x86_emulate_ctxt *ctxt)
{
- if (address_mask(ctxt, ctxt->regs[VCPU_REGS_RCX]) == 0)
+ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
jmp_rel(ctxt, ctxt->src.val);
return X86EMUL_CONTINUE;
@@ -3286,20 +3345,20 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt)
{
u32 eax, ebx, ecx, edx;
- eax = ctxt->regs[VCPU_REGS_RAX];
- ecx = ctxt->regs[VCPU_REGS_RCX];
+ eax = reg_read(ctxt, VCPU_REGS_RAX);
+ ecx = reg_read(ctxt, VCPU_REGS_RCX);
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
- ctxt->regs[VCPU_REGS_RAX] = eax;
- ctxt->regs[VCPU_REGS_RBX] = ebx;
- ctxt->regs[VCPU_REGS_RCX] = ecx;
- ctxt->regs[VCPU_REGS_RDX] = edx;
+ *reg_write(ctxt, VCPU_REGS_RAX) = eax;
+ *reg_write(ctxt, VCPU_REGS_RBX) = ebx;
+ *reg_write(ctxt, VCPU_REGS_RCX) = ecx;
+ *reg_write(ctxt, VCPU_REGS_RDX) = edx;
return X86EMUL_CONTINUE;
}
static int em_lahf(struct x86_emulate_ctxt *ctxt)
{
- ctxt->regs[VCPU_REGS_RAX] &= ~0xff00UL;
- ctxt->regs[VCPU_REGS_RAX] |= (ctxt->eflags & 0xff) << 8;
+ *reg_rmw(ctxt, VCPU_REGS_RAX) &= ~0xff00UL;
+ *reg_rmw(ctxt, VCPU_REGS_RAX) |= (ctxt->eflags & 0xff) << 8;
return X86EMUL_CONTINUE;
}
@@ -3456,7 +3515,7 @@ static int check_svme(struct x86_emulate_ctxt *ctxt)
static int check_svme_pa(struct x86_emulate_ctxt *ctxt)
{
- u64 rax = ctxt->regs[VCPU_REGS_RAX];
+ u64 rax = reg_read(ctxt, VCPU_REGS_RAX);
/* Valid physical address? */
if (rax & 0xffff000000000000ULL)
@@ -3478,7 +3537,7 @@ static int check_rdtsc(struct x86_emulate_ctxt *ctxt)
static int check_rdpmc(struct x86_emulate_ctxt *ctxt)
{
u64 cr4 = ctxt->ops->get_cr(ctxt, 4);
- u64 rcx = ctxt->regs[VCPU_REGS_RCX];
+ u64 rcx = reg_read(ctxt, VCPU_REGS_RCX);
if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) ||
(rcx > 3))
@@ -3531,13 +3590,13 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \
I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
-static struct opcode group7_rm1[] = {
+static const struct opcode group7_rm1[] = {
DI(SrcNone | Priv, monitor),
DI(SrcNone | Priv, mwait),
N, N, N, N, N, N,
};
-static struct opcode group7_rm3[] = {
+static const struct opcode group7_rm3[] = {
DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa),
II(SrcNone | Prot | VendorSpecific, em_vmmcall, vmmcall),
DIP(SrcNone | Prot | Priv, vmload, check_svme_pa),
@@ -3548,13 +3607,13 @@ static struct opcode group7_rm3[] = {
DIP(SrcNone | Prot | Priv, invlpga, check_svme),
};
-static struct opcode group7_rm7[] = {
+static const struct opcode group7_rm7[] = {
N,
DIP(SrcNone, rdtscp, check_rdtsc),
N, N, N, N, N, N,
};
-static struct opcode group1[] = {
+static const struct opcode group1[] = {
I(Lock, em_add),
I(Lock | PageTable, em_or),
I(Lock, em_adc),
@@ -3565,11 +3624,11 @@ static struct opcode group1[] = {
I(0, em_cmp),
};
-static struct opcode group1A[] = {
+static const struct opcode group1A[] = {
I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N,
};
-static struct opcode group3[] = {
+static const struct opcode group3[] = {
I(DstMem | SrcImm, em_test),
I(DstMem | SrcImm, em_test),
I(DstMem | SrcNone | Lock, em_not),
@@ -3580,13 +3639,13 @@ static struct opcode group3[] = {
I(SrcMem, em_idiv_ex),
};
-static struct opcode group4[] = {
+static const struct opcode group4[] = {
I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
N, N, N, N, N, N,
};
-static struct opcode group5[] = {
+static const struct opcode group5[] = {
I(DstMem | SrcNone | Lock, em_grp45),
I(DstMem | SrcNone | Lock, em_grp45),
I(SrcMem | Stack, em_grp45),
@@ -3596,7 +3655,7 @@ static struct opcode group5[] = {
I(SrcMem | Stack, em_grp45), N,
};
-static struct opcode group6[] = {
+static const struct opcode group6[] = {
DI(Prot, sldt),
DI(Prot, str),
II(Prot | Priv | SrcMem16, em_lldt, lldt),
@@ -3604,7 +3663,7 @@ static struct opcode group6[] = {
N, N, N, N,
};
-static struct group_dual group7 = { {
+static const struct group_dual group7 = { {
II(Mov | DstMem | Priv, em_sgdt, sgdt),
II(Mov | DstMem | Priv, em_sidt, sidt),
II(SrcMem | Priv, em_lgdt, lgdt),
@@ -3621,7 +3680,7 @@ static struct group_dual group7 = { {
EXT(0, group7_rm7),
} };
-static struct opcode group8[] = {
+static const struct opcode group8[] = {
N, N, N, N,
I(DstMem | SrcImmByte, em_bt),
I(DstMem | SrcImmByte | Lock | PageTable, em_bts),
@@ -3629,26 +3688,26 @@ static struct opcode group8[] = {
I(DstMem | SrcImmByte | Lock | PageTable, em_btc),
};
-static struct group_dual group9 = { {
+static const struct group_dual group9 = { {
N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N,
}, {
N, N, N, N, N, N, N, N,
} };
-static struct opcode group11[] = {
+static const struct opcode group11[] = {
I(DstMem | SrcImm | Mov | PageTable, em_mov),
X7(D(Undefined)),
};
-static struct gprefix pfx_0f_6f_0f_7f = {
+static const struct gprefix pfx_0f_6f_0f_7f = {
I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
};
-static struct gprefix pfx_vmovntpx = {
+static const struct gprefix pfx_vmovntpx = {
I(0, em_mov), N, N, N,
};
-static struct opcode opcode_table[256] = {
+static const struct opcode opcode_table[256] = {
/* 0x00 - 0x07 */
I6ALU(Lock, em_add),
I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg),
@@ -3689,7 +3748,7 @@ static struct opcode opcode_table[256] = {
I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op),
I(SrcImmByte | Mov | Stack, em_push),
I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op),
- I2bvIP(DstDI | SrcDX | Mov | String, em_in, ins, check_perm_in), /* insb, insw/insd */
+ I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */
I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */
/* 0x70 - 0x7F */
X16(D(SrcImmByte)),
@@ -3765,7 +3824,7 @@ static struct opcode opcode_table[256] = {
D(ImplicitOps), D(ImplicitOps), G(0, group4), G(0, group5),
};
-static struct opcode twobyte_table[256] = {
+static const struct opcode twobyte_table[256] = {
/* 0x00 - 0x0F */
G(0, group6), GD(0, &group7), N, N,
N, I(ImplicitOps | VendorSpecific, em_syscall),
@@ -3936,7 +3995,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
case OpAcc:
op->type = OP_REG;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
- op->addr.reg = &ctxt->regs[VCPU_REGS_RAX];
+ op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX);
fetch_register_operand(op);
op->orig_val = op->val;
break;
@@ -3944,19 +4003,20 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt, ctxt->regs[VCPU_REGS_RDI]);
+ register_address(ctxt, reg_read(ctxt, VCPU_REGS_RDI));
op->addr.mem.seg = VCPU_SREG_ES;
op->val = 0;
+ op->count = 1;
break;
case OpDX:
op->type = OP_REG;
op->bytes = 2;
- op->addr.reg = &ctxt->regs[VCPU_REGS_RDX];
+ op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX);
fetch_register_operand(op);
break;
case OpCL:
op->bytes = 1;
- op->val = ctxt->regs[VCPU_REGS_RCX] & 0xff;
+ op->val = reg_read(ctxt, VCPU_REGS_RCX) & 0xff;
break;
case OpImmByte:
rc = decode_imm(ctxt, op, 1, true);
@@ -3987,9 +4047,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt, ctxt->regs[VCPU_REGS_RSI]);
+ register_address(ctxt, reg_read(ctxt, VCPU_REGS_RSI));
op->addr.mem.seg = seg_override(ctxt);
op->val = 0;
+ op->count = 1;
break;
case OpImmFAddr:
op->type = OP_IMM;
@@ -4293,9 +4354,10 @@ static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
}
+
int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
{
- struct x86_emulate_ops *ops = ctxt->ops;
+ const struct x86_emulate_ops *ops = ctxt->ops;
int rc = X86EMUL_CONTINUE;
int saved_dst_type = ctxt->dst.type;
@@ -4356,7 +4418,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
}
/* Instruction can only be executed in protected mode */
- if ((ctxt->d & Prot) && !(ctxt->mode & X86EMUL_MODE_PROT)) {
+ if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
rc = emulate_ud(ctxt);
goto done;
}
@@ -4377,7 +4439,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
if (ctxt->rep_prefix && (ctxt->d & String)) {
/* All REP prefixes have the same first termination condition */
- if (address_mask(ctxt, ctxt->regs[VCPU_REGS_RCX]) == 0) {
+ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
ctxt->eip = ctxt->_eip;
goto done;
}
@@ -4450,7 +4512,7 @@ special_insn:
ctxt->dst.val = ctxt->src.addr.mem.ea;
break;
case 0x90 ... 0x97: /* nop / xchg reg, rax */
- if (ctxt->dst.addr.reg == &ctxt->regs[VCPU_REGS_RAX])
+ if (ctxt->dst.addr.reg == reg_rmw(ctxt, VCPU_REGS_RAX))
break;
rc = em_xchg(ctxt);
break;
@@ -4478,7 +4540,7 @@ special_insn:
rc = em_grp2(ctxt);
break;
case 0xd2 ... 0xd3: /* Grp2 */
- ctxt->src.val = ctxt->regs[VCPU_REGS_RCX];
+ ctxt->src.val = reg_read(ctxt, VCPU_REGS_RCX);
rc = em_grp2(ctxt);
break;
case 0xe9: /* jmp rel */
@@ -4524,23 +4586,27 @@ writeback:
ctxt->dst.type = saved_dst_type;
if ((ctxt->d & SrcMask) == SrcSI)
- string_addr_inc(ctxt, seg_override(ctxt),
- VCPU_REGS_RSI, &ctxt->src);
+ string_addr_inc(ctxt, VCPU_REGS_RSI, &ctxt->src);
if ((ctxt->d & DstMask) == DstDI)
- string_addr_inc(ctxt, VCPU_SREG_ES, VCPU_REGS_RDI,
- &ctxt->dst);
+ string_addr_inc(ctxt, VCPU_REGS_RDI, &ctxt->dst);
if (ctxt->rep_prefix && (ctxt->d & String)) {
+ unsigned int count;
struct read_cache *r = &ctxt->io_read;
- register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RCX], -1);
+ if ((ctxt->d & SrcMask) == SrcSI)
+ count = ctxt->src.count;
+ else
+ count = ctxt->dst.count;
+ register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX),
+ -count);
if (!string_insn_completed(ctxt)) {
/*
* Re-enter guest when pio read ahead buffer is empty
* or, if it is not used, after each 1024 iteration.
*/
- if ((r->end != 0 || ctxt->regs[VCPU_REGS_RCX] & 0x3ff) &&
+ if ((r->end != 0 || reg_read(ctxt, VCPU_REGS_RCX) & 0x3ff) &&
(r->end == 0 || r->end != r->pos)) {
/*
* Reset read cache. Usually happens before
@@ -4548,6 +4614,7 @@ writeback:
* we have to do it here.
*/
ctxt->mem_read.end = 0;
+ writeback_registers(ctxt);
return EMULATION_RESTART;
}
goto done; /* skip rip writeback */
@@ -4562,6 +4629,9 @@ done:
if (rc == X86EMUL_INTERCEPTED)
return EMULATION_INTERCEPTED;
+ if (rc == X86EMUL_CONTINUE)
+ writeback_registers(ctxt);
+
return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK;
twobyte_insn:
@@ -4634,3 +4704,13 @@ twobyte_insn:
cannot_emulate:
return EMULATION_FAILED;
}
+
+void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt)
+{
+ invalidate_registers(ctxt);
+}
+
+void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt)
+{
+ writeback_registers(ctxt);
+}
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index adba28f88d1..11300d2fa71 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -108,7 +108,7 @@ static s64 __kpit_elapsed(struct kvm *kvm)
ktime_t remaining;
struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
- if (!ps->pit_timer.period)
+ if (!ps->period)
return 0;
/*
@@ -120,9 +120,9 @@ static s64 __kpit_elapsed(struct kvm *kvm)
* itself with the initial count and continues counting
* from there.
*/
- remaining = hrtimer_get_remaining(&ps->pit_timer.timer);
- elapsed = ps->pit_timer.period - ktime_to_ns(remaining);
- elapsed = mod_64(elapsed, ps->pit_timer.period);
+ remaining = hrtimer_get_remaining(&ps->timer);
+ elapsed = ps->period - ktime_to_ns(remaining);
+ elapsed = mod_64(elapsed, ps->period);
return elapsed;
}
@@ -238,12 +238,12 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
int value;
spin_lock(&ps->inject_lock);
- value = atomic_dec_return(&ps->pit_timer.pending);
+ value = atomic_dec_return(&ps->pending);
if (value < 0)
/* spurious acks can be generated if, for example, the
* PIC is being reset. Handle it gracefully here
*/
- atomic_inc(&ps->pit_timer.pending);
+ atomic_inc(&ps->pending);
else if (value > 0)
/* in this case, we had multiple outstanding pit interrupts
* that we needed to inject. Reinject
@@ -261,28 +261,17 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
if (!kvm_vcpu_is_bsp(vcpu) || !pit)
return;
- timer = &pit->pit_state.pit_timer.timer;
+ timer = &pit->pit_state.timer;
if (hrtimer_cancel(timer))
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
static void destroy_pit_timer(struct kvm_pit *pit)
{
- hrtimer_cancel(&pit->pit_state.pit_timer.timer);
+ hrtimer_cancel(&pit->pit_state.timer);
flush_kthread_work(&pit->expired);
}
-static bool kpit_is_periodic(struct kvm_timer *ktimer)
-{
- struct kvm_kpit_state *ps = container_of(ktimer, struct kvm_kpit_state,
- pit_timer);
- return ps->is_periodic;
-}
-
-static struct kvm_timer_ops kpit_ops = {
- .is_periodic = kpit_is_periodic,
-};
-
static void pit_do_work(struct kthread_work *work)
{
struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
@@ -322,16 +311,16 @@ static void pit_do_work(struct kthread_work *work)
static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
{
- struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
- struct kvm_pit *pt = ktimer->kvm->arch.vpit;
+ struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
+ struct kvm_pit *pt = ps->kvm->arch.vpit;
- if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
- atomic_inc(&ktimer->pending);
+ if (ps->reinject || !atomic_read(&ps->pending)) {
+ atomic_inc(&ps->pending);
queue_kthread_work(&pt->worker, &pt->expired);
}
- if (ktimer->t_ops->is_periodic(ktimer)) {
- hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+ if (ps->is_periodic) {
+ hrtimer_add_expires_ns(&ps->timer, ps->period);
return HRTIMER_RESTART;
} else
return HRTIMER_NORESTART;
@@ -340,7 +329,6 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
{
struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
- struct kvm_timer *pt = &ps->pit_timer;
s64 interval;
if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
@@ -351,19 +339,18 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
pr_debug("create pit timer, interval is %llu nsec\n", interval);
/* TODO The new value only affected after the retriggered */
- hrtimer_cancel(&pt->timer);
+ hrtimer_cancel(&ps->timer);
flush_kthread_work(&ps->pit->expired);
- pt->period = interval;
+ ps->period = interval;
ps->is_periodic = is_period;
- pt->timer.function = pit_timer_fn;
- pt->t_ops = &kpit_ops;
- pt->kvm = ps->pit->kvm;
+ ps->timer.function = pit_timer_fn;
+ ps->kvm = ps->pit->kvm;
- atomic_set(&pt->pending, 0);
+ atomic_set(&ps->pending, 0);
ps->irq_ack = 1;
- hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval),
+ hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
HRTIMER_MODE_ABS);
}
@@ -639,7 +626,7 @@ void kvm_pit_reset(struct kvm_pit *pit)
}
mutex_unlock(&pit->pit_state.lock);
- atomic_set(&pit->pit_state.pit_timer.pending, 0);
+ atomic_set(&pit->pit_state.pending, 0);
pit->pit_state.irq_ack = 1;
}
@@ -648,7 +635,7 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
if (!mask) {
- atomic_set(&pit->pit_state.pit_timer.pending, 0);
+ atomic_set(&pit->pit_state.pending, 0);
pit->pit_state.irq_ack = 1;
}
}
@@ -706,12 +693,11 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
pit_state = &pit->pit_state;
pit_state->pit = pit;
- hrtimer_init(&pit_state->pit_timer.timer,
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
pit_state->irq_ack_notifier.gsi = 0;
pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
- pit_state->pit_timer.reinject = true;
+ pit_state->reinject = true;
mutex_unlock(&pit->pit_state.lock);
kvm_pit_reset(pit);
@@ -761,7 +747,7 @@ void kvm_free_pit(struct kvm *kvm)
kvm_unregister_irq_ack_notifier(kvm,
&kvm->arch.vpit->pit_state.irq_ack_notifier);
mutex_lock(&kvm->arch.vpit->pit_state.lock);
- timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
+ timer = &kvm->arch.vpit->pit_state.timer;
hrtimer_cancel(timer);
flush_kthread_work(&kvm->arch.vpit->expired);
kthread_stop(kvm->arch.vpit->worker_task);
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index fdf40425ea1..dd1b16b611b 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -24,8 +24,12 @@ struct kvm_kpit_channel_state {
struct kvm_kpit_state {
struct kvm_kpit_channel_state channels[3];
u32 flags;
- struct kvm_timer pit_timer;
bool is_periodic;
+ s64 period; /* unit: ns */
+ struct hrtimer timer;
+ atomic_t pending; /* accumulated triggered timers */
+ bool reinject;
+ struct kvm *kvm;
u32 speaker_data_on;
struct mutex lock;
struct kvm_pit *pit;
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index e498b18f010..848206df096 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -190,17 +190,17 @@ void kvm_pic_update_irq(struct kvm_pic *s)
int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level)
{
- int ret = -1;
+ int ret, irq_level;
+
+ BUG_ON(irq < 0 || irq >= PIC_NUM_PINS);
pic_lock(s);
- if (irq >= 0 && irq < PIC_NUM_PINS) {
- int irq_level = __kvm_irq_line_state(&s->irq_states[irq],
- irq_source_id, level);
- ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, irq_level);
- pic_update_irq(s);
- trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
- s->pics[irq >> 3].imr, ret == 0);
- }
+ irq_level = __kvm_irq_line_state(&s->irq_states[irq],
+ irq_source_id, level);
+ ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, irq_level);
+ pic_update_irq(s);
+ trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
+ s->pics[irq >> 3].imr, ret == 0);
pic_unlock(s);
return ret;
@@ -275,23 +275,20 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
{
int irq, i;
struct kvm_vcpu *vcpu;
- u8 irr = s->irr, isr = s->imr;
+ u8 edge_irr = s->irr & ~s->elcr;
bool found = false;
s->last_irr = 0;
- s->irr = 0;
+ s->irr &= s->elcr;
s->imr = 0;
- s->isr = 0;
s->priority_add = 0;
- s->irq_base = 0;
- s->read_reg_select = 0;
- s->poll = 0;
s->special_mask = 0;
- s->init_state = 0;
- s->auto_eoi = 0;
- s->rotate_on_auto_eoi = 0;
- s->special_fully_nested_mode = 0;
- s->init4 = 0;
+ s->read_reg_select = 0;
+ if (!s->init4) {
+ s->special_fully_nested_mode = 0;
+ s->auto_eoi = 0;
+ }
+ s->init_state = 1;
kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
if (kvm_apic_accept_pic_intr(vcpu)) {
@@ -304,7 +301,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
return;
for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
- if (irr & (1 << irq) || isr & (1 << irq))
+ if (edge_irr & (1 << irq))
pic_clear_isr(s, irq);
}
@@ -316,40 +313,13 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
addr &= 1;
if (addr == 0) {
if (val & 0x10) {
- u8 edge_irr = s->irr & ~s->elcr;
- int i;
- bool found;
- struct kvm_vcpu *vcpu;
-
s->init4 = val & 1;
- s->last_irr = 0;
- s->irr &= s->elcr;
- s->imr = 0;
- s->priority_add = 0;
- s->special_mask = 0;
- s->read_reg_select = 0;
- if (!s->init4) {
- s->special_fully_nested_mode = 0;
- s->auto_eoi = 0;
- }
- s->init_state = 1;
if (val & 0x02)
pr_pic_unimpl("single mode not supported");
if (val & 0x08)
pr_pic_unimpl(
- "level sensitive irq not supported");
-
- kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
- if (kvm_apic_accept_pic_intr(vcpu)) {
- found = true;
- break;
- }
-
-
- if (found)
- for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
- if (edge_irr & (1 << irq))
- pic_clear_isr(s, irq);
+ "level sensitive irq not supported");
+ kvm_pic_reset(s);
} else if (val & 0x08) {
if (val & 0x04)
s->poll = 1;
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2086f2bfba3..2d03568e949 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -70,7 +70,7 @@ struct kvm_pic {
struct kvm_io_device dev_slave;
struct kvm_io_device dev_eclr;
void (*ack_notifier)(void *opaque, int irq);
- unsigned long irq_states[16];
+ unsigned long irq_states[PIC_NUM_PINS];
};
struct kvm_pic *kvm_create_pic(struct kvm *kvm);
diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h
deleted file mode 100644
index 497dbaa366d..00000000000
--- a/arch/x86/kvm/kvm_timer.h
+++ /dev/null
@@ -1,18 +0,0 @@
-
-struct kvm_timer {
- struct hrtimer timer;
- s64 period; /* unit: ns */
- u32 timer_mode_mask;
- u64 tscdeadline;
- atomic_t pending; /* accumulated triggered timers */
- bool reinject;
- struct kvm_timer_ops *t_ops;
- struct kvm *kvm;
- struct kvm_vcpu *vcpu;
-};
-
-struct kvm_timer_ops {
- bool (*is_periodic)(struct kvm_timer *);
-};
-
-enum hrtimer_restart kvm_timer_fn(struct hrtimer *data);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index ce878788a39..c6e6b721b6e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -34,6 +34,7 @@
#include <asm/current.h>
#include <asm/apicdef.h>
#include <linux/atomic.h>
+#include <linux/jump_label.h>
#include "kvm_cache_regs.h"
#include "irq.h"
#include "trace.h"
@@ -65,6 +66,7 @@
#define APIC_DEST_NOSHORT 0x0
#define APIC_DEST_MASK 0x800
#define MAX_APIC_VECTOR 256
+#define APIC_VECTORS_PER_REG 32
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
@@ -72,11 +74,6 @@
static unsigned int min_timer_period_us = 500;
module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
-static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off)
-{
- return *((u32 *) (apic->regs + reg_off));
-}
-
static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
*((u32 *) (apic->regs + reg_off)) = val;
@@ -117,19 +114,23 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}
-static inline int apic_hw_enabled(struct kvm_lapic *apic)
-{
- return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
-}
+struct static_key_deferred apic_hw_disabled __read_mostly;
+struct static_key_deferred apic_sw_disabled __read_mostly;
-static inline int apic_sw_enabled(struct kvm_lapic *apic)
+static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
{
- return apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
+ if ((kvm_apic_get_reg(apic, APIC_SPIV) ^ val) & APIC_SPIV_APIC_ENABLED) {
+ if (val & APIC_SPIV_APIC_ENABLED)
+ static_key_slow_dec_deferred(&apic_sw_disabled);
+ else
+ static_key_slow_inc(&apic_sw_disabled.key);
+ }
+ apic_set_reg(apic, APIC_SPIV, val);
}
static inline int apic_enabled(struct kvm_lapic *apic)
{
- return apic_sw_enabled(apic) && apic_hw_enabled(apic);
+ return kvm_apic_sw_enabled(apic) && kvm_apic_hw_enabled(apic);
}
#define LVT_MASK \
@@ -139,36 +140,135 @@ static inline int apic_enabled(struct kvm_lapic *apic)
(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
+static inline int apic_x2apic_mode(struct kvm_lapic *apic)
+{
+ return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
+}
+
static inline int kvm_apic_id(struct kvm_lapic *apic)
{
- return (apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+ return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+}
+
+static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
+{
+ u16 cid;
+ ldr >>= 32 - map->ldr_bits;
+ cid = (ldr >> map->cid_shift) & map->cid_mask;
+
+ BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
+
+ return cid;
+}
+
+static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
+{
+ ldr >>= (32 - map->ldr_bits);
+ return ldr & map->lid_mask;
+}
+
+static void recalculate_apic_map(struct kvm *kvm)
+{
+ struct kvm_apic_map *new, *old = NULL;
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL);
+
+ mutex_lock(&kvm->arch.apic_map_lock);
+
+ if (!new)
+ goto out;
+
+ new->ldr_bits = 8;
+ /* flat mode is default */
+ new->cid_shift = 8;
+ new->cid_mask = 0;
+ new->lid_mask = 0xff;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u16 cid, lid;
+ u32 ldr;
+
+ if (!kvm_apic_present(vcpu))
+ continue;
+
+ /*
+ * All APICs have to be configured in the same mode by an OS.
+ * We take advatage of this while building logical id loockup
+ * table. After reset APICs are in xapic/flat mode, so if we
+ * find apic with different setting we assume this is the mode
+ * OS wants all apics to be in; build lookup table accordingly.
+ */
+ if (apic_x2apic_mode(apic)) {
+ new->ldr_bits = 32;
+ new->cid_shift = 16;
+ new->cid_mask = new->lid_mask = 0xffff;
+ } else if (kvm_apic_sw_enabled(apic) &&
+ !new->cid_mask /* flat mode */ &&
+ kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
+ new->cid_shift = 4;
+ new->cid_mask = 0xf;
+ new->lid_mask = 0xf;
+ }
+
+ new->phys_map[kvm_apic_id(apic)] = apic;
+
+ ldr = kvm_apic_get_reg(apic, APIC_LDR);
+ cid = apic_cluster_id(new, ldr);
+ lid = apic_logical_id(new, ldr);
+
+ if (lid)
+ new->logical_map[cid][ffs(lid) - 1] = apic;
+ }
+out:
+ old = rcu_dereference_protected(kvm->arch.apic_map,
+ lockdep_is_held(&kvm->arch.apic_map_lock));
+ rcu_assign_pointer(kvm->arch.apic_map, new);
+ mutex_unlock(&kvm->arch.apic_map_lock);
+
+ if (old)
+ kfree_rcu(old, rcu);
+}
+
+static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
+{
+ apic_set_reg(apic, APIC_ID, id << 24);
+ recalculate_apic_map(apic->vcpu->kvm);
+}
+
+static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
+{
+ apic_set_reg(apic, APIC_LDR, id);
+ recalculate_apic_map(apic->vcpu->kvm);
}
static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
{
- return !(apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
+ return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
}
static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type)
{
- return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
+ return kvm_apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
}
static inline int apic_lvtt_oneshot(struct kvm_lapic *apic)
{
- return ((apic_get_reg(apic, APIC_LVTT) &
+ return ((kvm_apic_get_reg(apic, APIC_LVTT) &
apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT);
}
static inline int apic_lvtt_period(struct kvm_lapic *apic)
{
- return ((apic_get_reg(apic, APIC_LVTT) &
+ return ((kvm_apic_get_reg(apic, APIC_LVTT) &
apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC);
}
static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic)
{
- return ((apic_get_reg(apic, APIC_LVTT) &
+ return ((kvm_apic_get_reg(apic, APIC_LVTT) &
apic->lapic_timer.timer_mode_mask) ==
APIC_LVT_TIMER_TSCDEADLINE);
}
@@ -184,7 +284,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
struct kvm_cpuid_entry2 *feat;
u32 v = APIC_VERSION;
- if (!irqchip_in_kernel(vcpu->kvm))
+ if (!kvm_vcpu_has_lapic(vcpu))
return;
feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
@@ -193,12 +293,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
apic_set_reg(apic, APIC_LVR, v);
}
-static inline int apic_x2apic_mode(struct kvm_lapic *apic)
-{
- return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
-}
-
-static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
+static const unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
LVT_MASK , /* part LVTT mask, timer mode mask added at runtime */
LVT_MASK | APIC_MODE_MASK, /* LVTTHMR */
LVT_MASK | APIC_MODE_MASK, /* LVTPC */
@@ -208,25 +303,30 @@ static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
static int find_highest_vector(void *bitmap)
{
- u32 *word = bitmap;
- int word_offset = MAX_APIC_VECTOR >> 5;
+ int vec;
+ u32 *reg;
- while ((word_offset != 0) && (word[(--word_offset) << 2] == 0))
- continue;
+ for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
+ vec >= 0; vec -= APIC_VECTORS_PER_REG) {
+ reg = bitmap + REG_POS(vec);
+ if (*reg)
+ return fls(*reg) - 1 + vec;
+ }
- if (likely(!word_offset && !word[0]))
- return -1;
- else
- return fls(word[word_offset << 2]) - 1 + (word_offset << 5);
+ return -1;
}
static u8 count_vectors(void *bitmap)
{
- u32 *word = bitmap;
- int word_offset;
+ int vec;
+ u32 *reg;
u8 count = 0;
- for (word_offset = 0; word_offset < MAX_APIC_VECTOR >> 5; ++word_offset)
- count += hweight32(word[word_offset << 2]);
+
+ for (vec = 0; vec < MAX_APIC_VECTOR; vec += APIC_VECTORS_PER_REG) {
+ reg = bitmap + REG_POS(vec);
+ count += hweight32(*reg);
+ }
+
return count;
}
@@ -285,7 +385,6 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
- struct kvm_lapic *apic = vcpu->arch.apic;
int highest_irr;
/* This may race with setting of irr in __apic_accept_irq() and
@@ -293,9 +392,9 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
* will cause vmexit immediately and the value will be recalculated
* on the next vmentry.
*/
- if (!apic)
+ if (!kvm_vcpu_has_lapic(vcpu))
return 0;
- highest_irr = apic_find_highest_irr(apic);
+ highest_irr = apic_find_highest_irr(vcpu->arch.apic);
return highest_irr;
}
@@ -378,8 +477,8 @@ static void apic_update_ppr(struct kvm_lapic *apic)
u32 tpr, isrv, ppr, old_ppr;
int isr;
- old_ppr = apic_get_reg(apic, APIC_PROCPRI);
- tpr = apic_get_reg(apic, APIC_TASKPRI);
+ old_ppr = kvm_apic_get_reg(apic, APIC_PROCPRI);
+ tpr = kvm_apic_get_reg(apic, APIC_TASKPRI);
isr = apic_find_highest_isr(apic);
isrv = (isr != -1) ? isr : 0;
@@ -415,13 +514,13 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
u32 logical_id;
if (apic_x2apic_mode(apic)) {
- logical_id = apic_get_reg(apic, APIC_LDR);
+ logical_id = kvm_apic_get_reg(apic, APIC_LDR);
return logical_id & mda;
}
- logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR));
+ logical_id = GET_APIC_LOGICAL_ID(kvm_apic_get_reg(apic, APIC_LDR));
- switch (apic_get_reg(apic, APIC_DFR)) {
+ switch (kvm_apic_get_reg(apic, APIC_DFR)) {
case APIC_DFR_FLAT:
if (logical_id & mda)
result = 1;
@@ -433,7 +532,7 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
break;
default:
apic_debug("Bad DFR vcpu %d: %08x\n",
- apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR));
+ apic->vcpu->vcpu_id, kvm_apic_get_reg(apic, APIC_DFR));
break;
}
@@ -478,6 +577,72 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
return result;
}
+bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq, int *r)
+{
+ struct kvm_apic_map *map;
+ unsigned long bitmap = 1;
+ struct kvm_lapic **dst;
+ int i;
+ bool ret = false;
+
+ *r = -1;
+
+ if (irq->shorthand == APIC_DEST_SELF) {
+ *r = kvm_apic_set_irq(src->vcpu, irq);
+ return true;
+ }
+
+ if (irq->shorthand)
+ return false;
+
+ rcu_read_lock();
+ map = rcu_dereference(kvm->arch.apic_map);
+
+ if (!map)
+ goto out;
+
+ if (irq->dest_mode == 0) { /* physical mode */
+ if (irq->delivery_mode == APIC_DM_LOWEST ||
+ irq->dest_id == 0xff)
+ goto out;
+ dst = &map->phys_map[irq->dest_id & 0xff];
+ } else {
+ u32 mda = irq->dest_id << (32 - map->ldr_bits);
+
+ dst = map->logical_map[apic_cluster_id(map, mda)];
+
+ bitmap = apic_logical_id(map, mda);
+
+ if (irq->delivery_mode == APIC_DM_LOWEST) {
+ int l = -1;
+ for_each_set_bit(i, &bitmap, 16) {
+ if (!dst[i])
+ continue;
+ if (l < 0)
+ l = i;
+ else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+ l = i;
+ }
+
+ bitmap = (l >= 0) ? 1 << l : 0;
+ }
+ }
+
+ for_each_set_bit(i, &bitmap, 16) {
+ if (!dst[i])
+ continue;
+ if (*r < 0)
+ *r = 0;
+ *r += kvm_apic_set_irq(dst[i]->vcpu, irq);
+ }
+
+ ret = true;
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
/*
* Add a pending IRQ into lapic.
* Return 1 if successfully added and 0 if discarded.
@@ -591,7 +756,7 @@ static int apic_set_eoi(struct kvm_lapic *apic)
apic_clear_isr(vector, apic);
apic_update_ppr(apic);
- if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+ if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
int trigger_mode;
if (apic_test_vector(vector, apic->regs + APIC_TMR))
@@ -606,8 +771,8 @@ static int apic_set_eoi(struct kvm_lapic *apic)
static void apic_send_ipi(struct kvm_lapic *apic)
{
- u32 icr_low = apic_get_reg(apic, APIC_ICR);
- u32 icr_high = apic_get_reg(apic, APIC_ICR2);
+ u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR);
+ u32 icr_high = kvm_apic_get_reg(apic, APIC_ICR2);
struct kvm_lapic_irq irq;
irq.vector = icr_low & APIC_VECTOR_MASK;
@@ -642,7 +807,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
ASSERT(apic != NULL);
/* if initial count is 0, current count should also be 0 */
- if (apic_get_reg(apic, APIC_TMICT) == 0)
+ if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
return 0;
remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -696,13 +861,15 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
val = apic_get_tmcct(apic);
break;
-
+ case APIC_PROCPRI:
+ apic_update_ppr(apic);
+ val = kvm_apic_get_reg(apic, offset);
+ break;
case APIC_TASKPRI:
report_tpr_access(apic, false);
/* fall thru */
default:
- apic_update_ppr(apic);
- val = apic_get_reg(apic, offset);
+ val = kvm_apic_get_reg(apic, offset);
break;
}
@@ -719,7 +886,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
{
unsigned char alignment = offset & 0xf;
u32 result;
- /* this bitmask has a bit cleared for each reserver register */
+ /* this bitmask has a bit cleared for each reserved register */
static const u64 rmask = 0x43ff01ffffffe70cULL;
if ((alignment + len) > 4) {
@@ -754,7 +921,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
{
- return apic_hw_enabled(apic) &&
+ return kvm_apic_hw_enabled(apic) &&
addr >= apic->base_address &&
addr < apic->base_address + LAPIC_MMIO_LENGTH;
}
@@ -777,7 +944,7 @@ static void update_divide_count(struct kvm_lapic *apic)
{
u32 tmp1, tmp2, tdcr;
- tdcr = apic_get_reg(apic, APIC_TDCR);
+ tdcr = kvm_apic_get_reg(apic, APIC_TDCR);
tmp1 = tdcr & 0xf;
tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
apic->divide_count = 0x1 << (tmp2 & 0x7);
@@ -792,9 +959,9 @@ static void start_apic_timer(struct kvm_lapic *apic)
atomic_set(&apic->lapic_timer.pending, 0);
if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
- /* lapic timer in oneshot or peroidic mode */
+ /* lapic timer in oneshot or periodic mode */
now = apic->lapic_timer.timer.base->get_time();
- apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT)
+ apic->lapic_timer.period = (u64)kvm_apic_get_reg(apic, APIC_TMICT)
* APIC_BUS_CYCLE_NS * apic->divide_count;
if (!apic->lapic_timer.period)
@@ -826,7 +993,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
"timer initial count 0x%x, period %lldns, "
"expire @ 0x%016" PRIx64 ".\n", __func__,
APIC_BUS_CYCLE_NS, ktime_to_ns(now),
- apic_get_reg(apic, APIC_TMICT),
+ kvm_apic_get_reg(apic, APIC_TMICT),
apic->lapic_timer.period,
ktime_to_ns(ktime_add_ns(now,
apic->lapic_timer.period)));
@@ -858,7 +1025,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
{
- int nmi_wd_enabled = apic_lvt_nmi_mode(apic_get_reg(apic, APIC_LVT0));
+ int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0));
if (apic_lvt_nmi_mode(lvt0_val)) {
if (!nmi_wd_enabled) {
@@ -879,7 +1046,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
switch (reg) {
case APIC_ID: /* Local APIC ID */
if (!apic_x2apic_mode(apic))
- apic_set_reg(apic, APIC_ID, val);
+ kvm_apic_set_id(apic, val >> 24);
else
ret = 1;
break;
@@ -895,29 +1062,30 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
case APIC_LDR:
if (!apic_x2apic_mode(apic))
- apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK);
+ kvm_apic_set_ldr(apic, val & APIC_LDR_MASK);
else
ret = 1;
break;
case APIC_DFR:
- if (!apic_x2apic_mode(apic))
+ if (!apic_x2apic_mode(apic)) {
apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
- else
+ recalculate_apic_map(apic->vcpu->kvm);
+ } else
ret = 1;
break;
case APIC_SPIV: {
u32 mask = 0x3ff;
- if (apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
+ if (kvm_apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
mask |= APIC_SPIV_DIRECTED_EOI;
- apic_set_reg(apic, APIC_SPIV, val & mask);
+ apic_set_spiv(apic, val & mask);
if (!(val & APIC_SPIV_APIC_ENABLED)) {
int i;
u32 lvt_val;
for (i = 0; i < APIC_LVT_NUM; i++) {
- lvt_val = apic_get_reg(apic,
+ lvt_val = kvm_apic_get_reg(apic,
APIC_LVTT + 0x10 * i);
apic_set_reg(apic, APIC_LVTT + 0x10 * i,
lvt_val | APIC_LVT_MASKED);
@@ -946,7 +1114,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
case APIC_LVT1:
case APIC_LVTERR:
/* TODO: Check vector */
- if (!apic_sw_enabled(apic))
+ if (!kvm_apic_sw_enabled(apic))
val |= APIC_LVT_MASKED;
val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
@@ -955,12 +1123,12 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
break;
case APIC_LVTT:
- if ((apic_get_reg(apic, APIC_LVTT) &
+ if ((kvm_apic_get_reg(apic, APIC_LVTT) &
apic->lapic_timer.timer_mode_mask) !=
(val & apic->lapic_timer.timer_mode_mask))
hrtimer_cancel(&apic->lapic_timer.timer);
- if (!apic_sw_enabled(apic))
+ if (!kvm_apic_sw_enabled(apic))
val |= APIC_LVT_MASKED;
val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
apic_set_reg(apic, APIC_LVTT, val);
@@ -1039,24 +1207,30 @@ static int apic_mmio_write(struct kvm_io_device *this,
void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
{
- struct kvm_lapic *apic = vcpu->arch.apic;
-
- if (apic)
+ if (kvm_vcpu_has_lapic(vcpu))
apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
}
EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
void kvm_free_lapic(struct kvm_vcpu *vcpu)
{
+ struct kvm_lapic *apic = vcpu->arch.apic;
+
if (!vcpu->arch.apic)
return;
- hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer);
+ hrtimer_cancel(&apic->lapic_timer.timer);
+
+ if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE))
+ static_key_slow_dec_deferred(&apic_hw_disabled);
+
+ if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED))
+ static_key_slow_dec_deferred(&apic_sw_disabled);
- if (vcpu->arch.apic->regs)
- free_page((unsigned long)vcpu->arch.apic->regs);
+ if (apic->regs)
+ free_page((unsigned long)apic->regs);
- kfree(vcpu->arch.apic);
+ kfree(apic);
}
/*
@@ -1068,10 +1242,9 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!apic)
- return 0;
- if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic))
+ if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+ apic_lvtt_period(apic))
return 0;
return apic->lapic_timer.tscdeadline;
@@ -1080,10 +1253,9 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!apic)
- return;
- if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic))
+ if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+ apic_lvtt_period(apic))
return;
hrtimer_cancel(&apic->lapic_timer.timer);
@@ -1095,20 +1267,21 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!apic)
+ if (!kvm_vcpu_has_lapic(vcpu))
return;
+
apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
- | (apic_get_reg(apic, APIC_TASKPRI) & 4));
+ | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
}
u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
{
- struct kvm_lapic *apic = vcpu->arch.apic;
u64 tpr;
- if (!apic)
+ if (!kvm_vcpu_has_lapic(vcpu))
return 0;
- tpr = (u64) apic_get_reg(apic, APIC_TASKPRI);
+
+ tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
return (tpr & 0xf0) >> 4;
}
@@ -1123,6 +1296,15 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
return;
}
+ /* update jump label if enable bit changes */
+ if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+ if (value & MSR_IA32_APICBASE_ENABLE)
+ static_key_slow_dec_deferred(&apic_hw_disabled);
+ else
+ static_key_slow_inc(&apic_hw_disabled.key);
+ recalculate_apic_map(vcpu->kvm);
+ }
+
if (!kvm_vcpu_is_bsp(apic->vcpu))
value &= ~MSR_IA32_APICBASE_BSP;
@@ -1130,7 +1312,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
if (apic_x2apic_mode(apic)) {
u32 id = kvm_apic_id(apic);
u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf));
- apic_set_reg(apic, APIC_LDR, ldr);
+ kvm_apic_set_ldr(apic, ldr);
}
apic->base_address = apic->vcpu->arch.apic_base &
MSR_IA32_APICBASE_BASE;
@@ -1155,7 +1337,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
- apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24);
+ kvm_apic_set_id(apic, vcpu->vcpu_id);
kvm_apic_set_version(apic->vcpu);
for (i = 0; i < APIC_LVT_NUM; i++)
@@ -1164,9 +1346,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_set_reg(apic, APIC_DFR, 0xffffffffU);
- apic_set_reg(apic, APIC_SPIV, 0xff);
+ apic_set_spiv(apic, 0xff);
apic_set_reg(apic, APIC_TASKPRI, 0);
- apic_set_reg(apic, APIC_LDR, 0);
+ kvm_apic_set_ldr(apic, 0);
apic_set_reg(apic, APIC_ESR, 0);
apic_set_reg(apic, APIC_ICR, 0);
apic_set_reg(apic, APIC_ICR2, 0);
@@ -1183,7 +1365,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
update_divide_count(apic);
atomic_set(&apic->lapic_timer.pending, 0);
if (kvm_vcpu_is_bsp(vcpu))
- vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ kvm_lapic_set_base(vcpu,
+ vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP);
vcpu->arch.pv_eoi.msr_val = 0;
apic_update_ppr(apic);
@@ -1196,45 +1379,34 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
vcpu->arch.apic_base, apic->base_address);
}
-bool kvm_apic_present(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic);
-}
-
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
-{
- return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
-}
-
/*
*----------------------------------------------------------------------
* timer interface
*----------------------------------------------------------------------
*/
-static bool lapic_is_periodic(struct kvm_timer *ktimer)
+static bool lapic_is_periodic(struct kvm_lapic *apic)
{
- struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
- lapic_timer);
return apic_lvtt_period(apic);
}
int apic_has_pending_timer(struct kvm_vcpu *vcpu)
{
- struct kvm_lapic *lapic = vcpu->arch.apic;
+ struct kvm_lapic *apic = vcpu->arch.apic;
- if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
- return atomic_read(&lapic->lapic_timer.pending);
+ if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) &&
+ apic_lvt_enabled(apic, APIC_LVTT))
+ return atomic_read(&apic->lapic_timer.pending);
return 0;
}
int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
{
- u32 reg = apic_get_reg(apic, lvt_type);
+ u32 reg = kvm_apic_get_reg(apic, lvt_type);
int vector, mode, trig_mode;
- if (apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
+ if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
vector = reg & APIC_VECTOR_MASK;
mode = reg & APIC_MODE_MASK;
trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
@@ -1251,15 +1423,40 @@ void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
kvm_apic_local_deliver(apic, APIC_LVT0);
}
-static struct kvm_timer_ops lapic_timer_ops = {
- .is_periodic = lapic_is_periodic,
-};
-
static const struct kvm_io_device_ops apic_mmio_ops = {
.read = apic_mmio_read,
.write = apic_mmio_write,
};
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
+{
+ struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+ struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
+ struct kvm_vcpu *vcpu = apic->vcpu;
+ wait_queue_head_t *q = &vcpu->wq;
+
+ /*
+ * There is a race window between reading and incrementing, but we do
+ * not care about potentially losing timer events in the !reinject
+ * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
+ * in vcpu_enter_guest.
+ */
+ if (!atomic_read(&ktimer->pending)) {
+ atomic_inc(&ktimer->pending);
+ /* FIXME: this code should not know anything about vcpus */
+ kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+ }
+
+ if (waitqueue_active(q))
+ wake_up_interruptible(q);
+
+ if (lapic_is_periodic(apic)) {
+ hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+ return HRTIMER_RESTART;
+ } else
+ return HRTIMER_NORESTART;
+}
+
int kvm_create_lapic(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic;
@@ -1283,14 +1480,17 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
HRTIMER_MODE_ABS);
- apic->lapic_timer.timer.function = kvm_timer_fn;
- apic->lapic_timer.t_ops = &lapic_timer_ops;
- apic->lapic_timer.kvm = vcpu->kvm;
- apic->lapic_timer.vcpu = vcpu;
+ apic->lapic_timer.timer.function = apic_timer_fn;
- apic->base_address = APIC_DEFAULT_PHYS_BASE;
- vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
+ /*
+ * APIC is created enabled. This will prevent kvm_lapic_set_base from
+ * thinking that APIC satet has changed.
+ */
+ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
+ kvm_lapic_set_base(vcpu,
+ APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
+ static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
kvm_lapic_reset(vcpu);
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
@@ -1306,23 +1506,23 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
struct kvm_lapic *apic = vcpu->arch.apic;
int highest_irr;
- if (!apic || !apic_enabled(apic))
+ if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic))
return -1;
apic_update_ppr(apic);
highest_irr = apic_find_highest_irr(apic);
if ((highest_irr == -1) ||
- ((highest_irr & 0xF0) <= apic_get_reg(apic, APIC_PROCPRI)))
+ ((highest_irr & 0xF0) <= kvm_apic_get_reg(apic, APIC_PROCPRI)))
return -1;
return highest_irr;
}
int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
{
- u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0);
+ u32 lvt0 = kvm_apic_get_reg(vcpu->arch.apic, APIC_LVT0);
int r = 0;
- if (!apic_hw_enabled(vcpu->arch.apic))
+ if (!kvm_apic_hw_enabled(vcpu->arch.apic))
r = 1;
if ((lvt0 & APIC_LVT_MASKED) == 0 &&
GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT)
@@ -1334,7 +1534,10 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (apic && atomic_read(&apic->lapic_timer.pending) > 0) {
+ if (!kvm_vcpu_has_lapic(vcpu))
+ return;
+
+ if (atomic_read(&apic->lapic_timer.pending) > 0) {
if (kvm_apic_local_deliver(apic, APIC_LVTT))
atomic_dec(&apic->lapic_timer.pending);
}
@@ -1354,12 +1557,17 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
return vector;
}
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
+void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
+ struct kvm_lapic_state *s)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- apic->base_address = vcpu->arch.apic_base &
- MSR_IA32_APICBASE_BASE;
+ kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
+ /* set SPIV separately to get count of SW disabled APICs right */
+ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));
+ memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
+ /* call kvm_apic_set_id() to put apic into apic_map */
+ kvm_apic_set_id(apic, kvm_apic_id(apic));
kvm_apic_set_version(vcpu);
apic_update_ppr(apic);
@@ -1374,13 +1582,12 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
{
- struct kvm_lapic *apic = vcpu->arch.apic;
struct hrtimer *timer;
- if (!apic)
+ if (!kvm_vcpu_has_lapic(vcpu))
return;
- timer = &apic->lapic_timer.timer;
+ timer = &vcpu->arch.apic->lapic_timer.timer;
if (hrtimer_cancel(timer))
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}
@@ -1478,7 +1685,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
return;
- tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff;
+ tpr = kvm_apic_get_reg(apic, APIC_TASKPRI) & 0xff;
max_irr = apic_find_highest_irr(apic);
if (max_irr < 0)
max_irr = 0;
@@ -1537,7 +1744,7 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- if (!irqchip_in_kernel(vcpu->kvm))
+ if (!kvm_vcpu_has_lapic(vcpu))
return 1;
/* if this is ICR write vector before command */
@@ -1551,7 +1758,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
struct kvm_lapic *apic = vcpu->arch.apic;
u32 low, high = 0;
- if (!irqchip_in_kernel(vcpu->kvm))
+ if (!kvm_vcpu_has_lapic(vcpu))
return 1;
if (apic_reg_read(apic, reg, 4, &low))
@@ -1576,3 +1783,10 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
addr);
}
+
+void kvm_lapic_init(void)
+{
+ /* do not patch jump label more than once per second */
+ jump_label_rate_limit(&apic_hw_disabled, HZ);
+ jump_label_rate_limit(&apic_sw_disabled, HZ);
+}
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 4af5405ae1e..e5ebf9f3571 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -2,10 +2,17 @@
#define __KVM_X86_LAPIC_H
#include "iodev.h"
-#include "kvm_timer.h"
#include <linux/kvm_host.h>
+struct kvm_timer {
+ struct hrtimer timer;
+ s64 period; /* unit: ns */
+ u32 timer_mode_mask;
+ u64 tscdeadline;
+ atomic_t pending; /* accumulated triggered timers */
+};
+
struct kvm_lapic {
unsigned long base_address;
struct kvm_io_device dev;
@@ -45,11 +52,13 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
+bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq, int *r);
+
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
-bool kvm_apic_present(struct kvm_vcpu *vcpu);
+void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
+ struct kvm_lapic_state *s);
int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
@@ -71,4 +80,48 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
}
int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
+void kvm_lapic_init(void);
+
+static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
+{
+ return *((u32 *) (apic->regs + reg_off));
+}
+
+extern struct static_key kvm_no_apic_vcpu;
+
+static inline bool kvm_vcpu_has_lapic(struct kvm_vcpu *vcpu)
+{
+ if (static_key_false(&kvm_no_apic_vcpu))
+ return vcpu->arch.apic;
+ return true;
+}
+
+extern struct static_key_deferred apic_hw_disabled;
+
+static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
+{
+ if (static_key_false(&apic_hw_disabled.key))
+ return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
+ return MSR_IA32_APICBASE_ENABLE;
+}
+
+extern struct static_key_deferred apic_sw_disabled;
+
+static inline int kvm_apic_sw_enabled(struct kvm_lapic *apic)
+{
+ if (static_key_false(&apic_sw_disabled.key))
+ return kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
+ return APIC_SPIV_APIC_ENABLED;
+}
+
+static inline bool kvm_apic_present(struct kvm_vcpu *vcpu)
+{
+ return kvm_vcpu_has_lapic(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic);
+}
+
+static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
+{
+ return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
+}
+
#endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7fbd0d273ea..d289fee1ffb 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -556,6 +556,14 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
return 0;
pfn = spte_to_pfn(old_spte);
+
+ /*
+ * KVM does not hold the refcount of the page used by
+ * kvm mmu, before reclaiming the page, we should
+ * unmap it from mmu first.
+ */
+ WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+
if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
kvm_set_pfn_accessed(pfn);
if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
@@ -960,13 +968,10 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
struct kvm_memory_slot *slot)
{
- struct kvm_lpage_info *linfo;
-
- if (likely(level == PT_PAGE_TABLE_LEVEL))
- return &slot->rmap[gfn - slot->base_gfn];
+ unsigned long idx;
- linfo = lpage_info_slot(gfn, slot, level);
- return &linfo->rmap_pde;
+ idx = gfn_to_index(gfn, slot->base_gfn, level);
+ return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx];
}
/*
@@ -1173,7 +1178,8 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
unsigned long *rmapp;
while (mask) {
- rmapp = &slot->rmap[gfn_offset + __ffs(mask)];
+ rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
+ PT_PAGE_TABLE_LEVEL, slot);
__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false);
/* clear the first set bit */
@@ -1200,7 +1206,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
}
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
- unsigned long data)
+ struct kvm_memory_slot *slot, unsigned long data)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1218,7 +1224,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
}
static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
- unsigned long data)
+ struct kvm_memory_slot *slot, unsigned long data)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1259,43 +1265,67 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
return 0;
}
-static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
- unsigned long data,
- int (*handler)(struct kvm *kvm, unsigned long *rmapp,
- unsigned long data))
+static int kvm_handle_hva_range(struct kvm *kvm,
+ unsigned long start,
+ unsigned long end,
+ unsigned long data,
+ int (*handler)(struct kvm *kvm,
+ unsigned long *rmapp,
+ struct kvm_memory_slot *slot,
+ unsigned long data))
{
int j;
- int ret;
- int retval = 0;
+ int ret = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
slots = kvm_memslots(kvm);
kvm_for_each_memslot(memslot, slots) {
- unsigned long start = memslot->userspace_addr;
- unsigned long end;
+ unsigned long hva_start, hva_end;
+ gfn_t gfn_start, gfn_end;
- end = start + (memslot->npages << PAGE_SHIFT);
- if (hva >= start && hva < end) {
- gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
- gfn_t gfn = memslot->base_gfn + gfn_offset;
+ hva_start = max(start, memslot->userspace_addr);
+ hva_end = min(end, memslot->userspace_addr +
+ (memslot->npages << PAGE_SHIFT));
+ if (hva_start >= hva_end)
+ continue;
+ /*
+ * {gfn(page) | page intersects with [hva_start, hva_end)} =
+ * {gfn_start, gfn_start+1, ..., gfn_end-1}.
+ */
+ gfn_start = hva_to_gfn_memslot(hva_start, memslot);
+ gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
- ret = handler(kvm, &memslot->rmap[gfn_offset], data);
+ for (j = PT_PAGE_TABLE_LEVEL;
+ j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
+ unsigned long idx, idx_end;
+ unsigned long *rmapp;
- for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
- struct kvm_lpage_info *linfo;
+ /*
+ * {idx(page_j) | page_j intersects with
+ * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
+ */
+ idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
+ idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
- linfo = lpage_info_slot(gfn, memslot,
- PT_DIRECTORY_LEVEL + j);
- ret |= handler(kvm, &linfo->rmap_pde, data);
- }
- trace_kvm_age_page(hva, memslot, ret);
- retval |= ret;
+ rmapp = __gfn_to_rmap(gfn_start, j, memslot);
+
+ for (; idx <= idx_end; ++idx)
+ ret |= handler(kvm, rmapp++, memslot, data);
}
}
- return retval;
+ return ret;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+ unsigned long data,
+ int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+ struct kvm_memory_slot *slot,
+ unsigned long data))
+{
+ return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
}
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
@@ -1303,13 +1333,18 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
}
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+ return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
+}
+
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
{
kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
}
static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
- unsigned long data)
+ struct kvm_memory_slot *slot, unsigned long data)
{
u64 *sptep;
struct rmap_iterator uninitialized_var(iter);
@@ -1323,8 +1358,10 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
* This has some overhead, but not as much as the cost of swapping
* out actively used pages or breaking up actively used hugepages.
*/
- if (!shadow_accessed_mask)
- return kvm_unmap_rmapp(kvm, rmapp, data);
+ if (!shadow_accessed_mask) {
+ young = kvm_unmap_rmapp(kvm, rmapp, slot, data);
+ goto out;
+ }
for (sptep = rmap_get_first(*rmapp, &iter); sptep;
sptep = rmap_get_next(&iter)) {
@@ -1336,12 +1373,14 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
(unsigned long *)sptep);
}
}
-
+out:
+ /* @data has hva passed to kvm_age_hva(). */
+ trace_kvm_age_page(data, slot, young);
return young;
}
static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
- unsigned long data)
+ struct kvm_memory_slot *slot, unsigned long data)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1379,13 +1418,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
- kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
+ kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0);
kvm_flush_remote_tlbs(vcpu->kvm);
}
int kvm_age_hva(struct kvm *kvm, unsigned long hva)
{
- return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
+ return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp);
}
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
@@ -2457,7 +2496,9 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
rmap_recycle(vcpu, sptep, gfn);
}
}
- kvm_release_pfn_clean(pfn);
+
+ if (!is_error_pfn(pfn))
+ kvm_release_pfn_clean(pfn);
}
static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
@@ -2469,17 +2510,12 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
bool no_dirty_log)
{
struct kvm_memory_slot *slot;
- unsigned long hva;
slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
- if (!slot) {
- get_page(fault_page);
- return page_to_pfn(fault_page);
- }
+ if (!slot)
+ return KVM_PFN_ERR_FAULT;
- hva = gfn_to_hva_memslot(slot, gfn);
-
- return hva_to_pfn_atomic(vcpu->kvm, hva);
+ return gfn_to_pfn_memslot_atomic(slot, gfn);
}
static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
@@ -2580,11 +2616,6 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
iterator.level - 1,
1, ACC_ALL, iterator.sptep);
- if (!sp) {
- pgprintk("nonpaging_map: ENOMEM\n");
- kvm_release_pfn_clean(pfn);
- return -ENOMEM;
- }
mmu_spte_set(iterator.sptep,
__pa(sp->spt)
@@ -2611,8 +2642,16 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn)
{
- kvm_release_pfn_clean(pfn);
- if (is_hwpoison_pfn(pfn)) {
+ /*
+ * Do not cache the mmio info caused by writing the readonly gfn
+ * into the spte otherwise read access on readonly gfn also can
+ * caused mmio page fault and treat it as mmio access.
+ * Return 1 to tell kvm to emulate it.
+ */
+ if (pfn == KVM_PFN_ERR_RO_FAULT)
+ return 1;
+
+ if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current);
return 0;
}
@@ -3236,8 +3275,6 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
if (!async)
return false; /* *pfn has correct page already */
- put_page(pfn_to_page(*pfn));
-
if (!prefault && can_do_async_pf(vcpu)) {
trace_kvm_try_async_get_page(gva, gfn);
if (kvm_find_async_pf_gfn(vcpu, gfn)) {
@@ -3371,6 +3408,18 @@ static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
}
+static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
+{
+ unsigned mask;
+
+ BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+ mask = (unsigned)~ACC_WRITE_MASK;
+ /* Allow write access to dirty gptes */
+ mask |= (gpte >> (PT_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & PT_WRITABLE_MASK;
+ *access &= mask;
+}
+
static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
int *nr_present)
{
@@ -3388,6 +3437,25 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
return false;
}
+static inline unsigned gpte_access(struct kvm_vcpu *vcpu, u64 gpte)
+{
+ unsigned access;
+
+ access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+ access &= ~(gpte >> PT64_NX_SHIFT);
+
+ return access;
+}
+
+static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
+{
+ unsigned index;
+
+ index = level - 1;
+ index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
+ return mmu->last_pte_bitmap & (1 << index);
+}
+
#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE
@@ -3457,6 +3525,56 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
}
}
+static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+ unsigned bit, byte, pfec;
+ u8 map;
+ bool fault, x, w, u, wf, uf, ff, smep;
+
+ smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+ for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
+ pfec = byte << 1;
+ map = 0;
+ wf = pfec & PFERR_WRITE_MASK;
+ uf = pfec & PFERR_USER_MASK;
+ ff = pfec & PFERR_FETCH_MASK;
+ for (bit = 0; bit < 8; ++bit) {
+ x = bit & ACC_EXEC_MASK;
+ w = bit & ACC_WRITE_MASK;
+ u = bit & ACC_USER_MASK;
+
+ /* Not really needed: !nx will cause pte.nx to fault */
+ x |= !mmu->nx;
+ /* Allow supervisor writes if !cr0.wp */
+ w |= !is_write_protection(vcpu) && !uf;
+ /* Disallow supervisor fetches of user code if cr4.smep */
+ x &= !(smep && u && !uf);
+
+ fault = (ff && !x) || (uf && !u) || (wf && !w);
+ map |= fault << bit;
+ }
+ mmu->permissions[byte] = map;
+ }
+}
+
+static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+ u8 map;
+ unsigned level, root_level = mmu->root_level;
+ const unsigned ps_set_index = 1 << 2; /* bit 2 of index: ps */
+
+ if (root_level == PT32E_ROOT_LEVEL)
+ --root_level;
+ /* PT_PAGE_TABLE_LEVEL always terminates */
+ map = 1 | (1 << ps_set_index);
+ for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
+ if (level <= PT_PDPE_LEVEL
+ && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
+ map |= 1 << (ps_set_index | (level - 1));
+ }
+ mmu->last_pte_bitmap = map;
+}
+
static int paging64_init_context_common(struct kvm_vcpu *vcpu,
struct kvm_mmu *context,
int level)
@@ -3465,6 +3583,8 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
context->root_level = level;
reset_rsvds_bits_mask(vcpu, context);
+ update_permission_bitmask(vcpu, context);
+ update_last_pte_bitmap(vcpu, context);
ASSERT(is_pae(vcpu));
context->new_cr3 = paging_new_cr3;
@@ -3493,6 +3613,8 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
context->root_level = PT32_ROOT_LEVEL;
reset_rsvds_bits_mask(vcpu, context);
+ update_permission_bitmask(vcpu, context);
+ update_last_pte_bitmap(vcpu, context);
context->new_cr3 = paging_new_cr3;
context->page_fault = paging32_page_fault;
@@ -3553,6 +3675,9 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
context->gva_to_gpa = paging32_gva_to_gpa;
}
+ update_permission_bitmask(vcpu, context);
+ update_last_pte_bitmap(vcpu, context);
+
return 0;
}
@@ -3628,6 +3753,9 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
}
+ update_permission_bitmask(vcpu, g_context);
+ update_last_pte_bitmap(vcpu, g_context);
+
return 0;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index e374db9af02..69871080e86 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -18,8 +18,10 @@
#define PT_PCD_MASK (1ULL << 4)
#define PT_ACCESSED_SHIFT 5
#define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
-#define PT_DIRTY_MASK (1ULL << 6)
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
+#define PT_DIRTY_SHIFT 6
+#define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT)
+#define PT_PAGE_SIZE_SHIFT 7
+#define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
#define PT_PAT_MASK (1ULL << 7)
#define PT_GLOBAL_MASK (1ULL << 8)
#define PT64_NX_SHIFT 63
@@ -88,17 +90,14 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
}
-static inline bool check_write_user_access(struct kvm_vcpu *vcpu,
- bool write_fault, bool user_fault,
- unsigned long pte)
+/*
+ * Will a fault with a given page-fault error code (pfec) cause a permission
+ * fault with the given access (in ACC_* format)?
+ */
+static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
+ unsigned pfec)
{
- if (unlikely(write_fault && !is_writable_pte(pte)
- && (user_fault || is_write_protection(vcpu))))
- return false;
-
- if (unlikely(user_fault && !(pte & PT_USER_MASK)))
- return false;
-
- return true;
+ return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
}
+
#endif
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 7d7d0b9e23e..daff69e2115 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -116,10 +116,8 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
- if (is_error_pfn(pfn)) {
- kvm_release_pfn_clean(pfn);
+ if (is_error_pfn(pfn))
return;
- }
hpa = pfn << PAGE_SHIFT;
if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
@@ -190,7 +188,6 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp)
static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
{
- struct kvm_memory_slot *slot;
unsigned long *rmapp;
u64 *sptep;
struct rmap_iterator iter;
@@ -198,8 +195,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
if (sp->role.direct || sp->unsync || sp->role.invalid)
return;
- slot = gfn_to_memslot(kvm, sp->gfn);
- rmapp = &slot->rmap[sp->gfn - slot->base_gfn];
+ rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL);
for (sptep = rmap_get_first(*rmapp, &iter); sptep;
sptep = rmap_get_next(&iter)) {
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index bb7cf01cae7..714e2c01a6f 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -63,10 +63,12 @@
*/
struct guest_walker {
int level;
+ unsigned max_level;
gfn_t table_gfn[PT_MAX_FULL_LEVELS];
pt_element_t ptes[PT_MAX_FULL_LEVELS];
pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
+ pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -101,38 +103,41 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
return (ret != orig_pte);
}
-static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte,
- bool last)
+static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu,
+ struct guest_walker *walker,
+ int write_fault)
{
- unsigned access;
-
- access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
- if (last && !is_dirty_gpte(gpte))
- access &= ~ACC_WRITE_MASK;
-
-#if PTTYPE == 64
- if (vcpu->arch.mmu.nx)
- access &= ~(gpte >> PT64_NX_SHIFT);
-#endif
- return access;
-}
-
-static bool FNAME(is_last_gpte)(struct guest_walker *walker,
- struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- pt_element_t gpte)
-{
- if (walker->level == PT_PAGE_TABLE_LEVEL)
- return true;
-
- if ((walker->level == PT_DIRECTORY_LEVEL) && is_large_pte(gpte) &&
- (PTTYPE == 64 || is_pse(vcpu)))
- return true;
+ unsigned level, index;
+ pt_element_t pte, orig_pte;
+ pt_element_t __user *ptep_user;
+ gfn_t table_gfn;
+ int ret;
+
+ for (level = walker->max_level; level >= walker->level; --level) {
+ pte = orig_pte = walker->ptes[level - 1];
+ table_gfn = walker->table_gfn[level - 1];
+ ptep_user = walker->ptep_user[level - 1];
+ index = offset_in_page(ptep_user) / sizeof(pt_element_t);
+ if (!(pte & PT_ACCESSED_MASK)) {
+ trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
+ pte |= PT_ACCESSED_MASK;
+ }
+ if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+ trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+ pte |= PT_DIRTY_MASK;
+ }
+ if (pte == orig_pte)
+ continue;
- if ((walker->level == PT_PDPE_LEVEL) && is_large_pte(gpte) &&
- (mmu->root_level == PT64_ROOT_LEVEL))
- return true;
+ ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
+ if (ret)
+ return ret;
- return false;
+ mark_page_dirty(vcpu->kvm, table_gfn);
+ walker->ptes[level] = pte;
+ }
+ return 0;
}
/*
@@ -142,21 +147,22 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gva_t addr, u32 access)
{
+ int ret;
pt_element_t pte;
pt_element_t __user *uninitialized_var(ptep_user);
gfn_t table_gfn;
- unsigned index, pt_access, uninitialized_var(pte_access);
+ unsigned index, pt_access, pte_access, accessed_dirty, shift;
gpa_t pte_gpa;
- bool eperm, last_gpte;
int offset;
const int write_fault = access & PFERR_WRITE_MASK;
const int user_fault = access & PFERR_USER_MASK;
const int fetch_fault = access & PFERR_FETCH_MASK;
u16 errcode = 0;
+ gpa_t real_gpa;
+ gfn_t gfn;
trace_kvm_mmu_pagetable_walk(addr, access);
retry_walk:
- eperm = false;
walker->level = mmu->root_level;
pte = mmu->get_cr3(vcpu);
@@ -169,15 +175,21 @@ retry_walk:
--walker->level;
}
#endif
+ walker->max_level = walker->level;
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
(mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
- pt_access = ACC_ALL;
+ accessed_dirty = PT_ACCESSED_MASK;
+ pt_access = pte_access = ACC_ALL;
+ ++walker->level;
- for (;;) {
+ do {
gfn_t real_gfn;
unsigned long host_addr;
+ pt_access &= pte_access;
+ --walker->level;
+
index = PT_INDEX(addr, walker->level);
table_gfn = gpte_to_gfn(pte);
@@ -199,6 +211,7 @@ retry_walk:
ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte))))
goto error;
+ walker->ptep_user[walker->level - 1] = ptep_user;
trace_kvm_mmu_paging_element(pte, walker->level);
@@ -211,92 +224,48 @@ retry_walk:
goto error;
}
- if (!check_write_user_access(vcpu, write_fault, user_fault,
- pte))
- eperm = true;
-
-#if PTTYPE == 64
- if (unlikely(fetch_fault && (pte & PT64_NX_MASK)))
- eperm = true;
-#endif
-
- last_gpte = FNAME(is_last_gpte)(walker, vcpu, mmu, pte);
- if (last_gpte) {
- pte_access = pt_access &
- FNAME(gpte_access)(vcpu, pte, true);
- /* check if the kernel is fetching from user page */
- if (unlikely(pte_access & PT_USER_MASK) &&
- kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
- if (fetch_fault && !user_fault)
- eperm = true;
- }
-
- if (!eperm && unlikely(!(pte & PT_ACCESSED_MASK))) {
- int ret;
- trace_kvm_mmu_set_accessed_bit(table_gfn, index,
- sizeof(pte));
- ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
- pte, pte|PT_ACCESSED_MASK);
- if (unlikely(ret < 0))
- goto error;
- else if (ret)
- goto retry_walk;
-
- mark_page_dirty(vcpu->kvm, table_gfn);
- pte |= PT_ACCESSED_MASK;
- }
+ accessed_dirty &= pte;
+ pte_access = pt_access & gpte_access(vcpu, pte);
walker->ptes[walker->level - 1] = pte;
+ } while (!is_last_gpte(mmu, walker->level, pte));
- if (last_gpte) {
- int lvl = walker->level;
- gpa_t real_gpa;
- gfn_t gfn;
- u32 ac;
-
- gfn = gpte_to_gfn_lvl(pte, lvl);
- gfn += (addr & PT_LVL_OFFSET_MASK(lvl)) >> PAGE_SHIFT;
-
- if (PTTYPE == 32 &&
- walker->level == PT_DIRECTORY_LEVEL &&
- is_cpuid_PSE36())
- gfn += pse36_gfn_delta(pte);
-
- ac = write_fault | fetch_fault | user_fault;
+ if (unlikely(permission_fault(mmu, pte_access, access))) {
+ errcode |= PFERR_PRESENT_MASK;
+ goto error;
+ }
- real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn),
- ac);
- if (real_gpa == UNMAPPED_GVA)
- return 0;
+ gfn = gpte_to_gfn_lvl(pte, walker->level);
+ gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;
- walker->gfn = real_gpa >> PAGE_SHIFT;
+ if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
+ gfn += pse36_gfn_delta(pte);
- break;
- }
+ real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
+ if (real_gpa == UNMAPPED_GVA)
+ return 0;
- pt_access &= FNAME(gpte_access)(vcpu, pte, false);
- --walker->level;
- }
+ walker->gfn = real_gpa >> PAGE_SHIFT;
- if (unlikely(eperm)) {
- errcode |= PFERR_PRESENT_MASK;
- goto error;
- }
+ if (!write_fault)
+ protect_clean_gpte(&pte_access, pte);
- if (write_fault && unlikely(!is_dirty_gpte(pte))) {
- int ret;
+ /*
+ * On a write fault, fold the dirty bit into accessed_dirty by shifting it one
+ * place right.
+ *
+ * On a read fault, do nothing.
+ */
+ shift = write_fault >> ilog2(PFERR_WRITE_MASK);
+ shift *= PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT;
+ accessed_dirty &= pte >> shift;
- trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
- ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
- pte, pte|PT_DIRTY_MASK);
+ if (unlikely(!accessed_dirty)) {
+ ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
if (unlikely(ret < 0))
goto error;
else if (ret)
goto retry_walk;
-
- mark_page_dirty(vcpu->kvm, table_gfn);
- pte |= PT_DIRTY_MASK;
- walker->ptes[walker->level - 1] = pte;
}
walker->pt_access = pt_access;
@@ -368,12 +337,11 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
return;
pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
- pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte, true);
+ pte_access = sp->role.access & gpte_access(vcpu, gpte);
+ protect_clean_gpte(&pte_access, gpte);
pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte));
- if (mmu_invalid_pfn(pfn)) {
- kvm_release_pfn_clean(pfn);
+ if (mmu_invalid_pfn(pfn))
return;
- }
/*
* we call mmu_set_spte() with host_writable = true because that
@@ -443,15 +411,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
continue;
- pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte,
- true);
+ pte_access = sp->role.access & gpte_access(vcpu, gpte);
+ protect_clean_gpte(&pte_access, gpte);
gfn = gpte_to_gfn(gpte);
pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
pte_access & ACC_WRITE_MASK);
- if (mmu_invalid_pfn(pfn)) {
- kvm_release_pfn_clean(pfn);
+ if (mmu_invalid_pfn(pfn))
break;
- }
mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
NULL, PT_PAGE_TABLE_LEVEL, gfn,
@@ -798,7 +764,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access;
- pte_access &= FNAME(gpte_access)(vcpu, gpte, true);
+ pte_access &= gpte_access(vcpu, gpte);
+ protect_clean_gpte(&pte_access, gpte);
if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present))
continue;
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 9b7ec1150ab..cfc258a6bf9 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -1,5 +1,5 @@
/*
- * Kernel-based Virtual Machine -- Performane Monitoring Unit support
+ * Kernel-based Virtual Machine -- Performance Monitoring Unit support
*
* Copyright 2011 Red Hat, Inc. and/or its affiliates.
*
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index baead950d6c..d017df3899e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -163,7 +163,7 @@ static DEFINE_PER_CPU(u64, current_tsc_ratio);
#define MSR_INVALID 0xffffffffU
-static struct svm_direct_access_msrs {
+static const struct svm_direct_access_msrs {
u32 index; /* Index of the MSR */
bool always; /* True if intercept is always on */
} direct_access_msrs[] = {
@@ -400,7 +400,7 @@ struct svm_init_data {
int r;
};
-static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
+static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
#define MSRS_RANGE_SIZE 2048
@@ -1146,7 +1146,6 @@ static void init_vmcb(struct vcpu_svm *svm)
svm_set_efer(&svm->vcpu, 0);
save->dr6 = 0xffff0ff0;
- save->dr7 = 0x400;
kvm_set_rflags(&svm->vcpu, 2);
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
@@ -1643,7 +1642,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
mark_dirty(svm->vmcb, VMCB_SEG);
}
-static void update_db_intercept(struct kvm_vcpu *vcpu)
+static void update_db_bp_intercept(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1663,20 +1662,6 @@ static void update_db_intercept(struct kvm_vcpu *vcpu)
vcpu->guest_debug = 0;
}
-static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
- else
- svm->vmcb->save.dr7 = vcpu->arch.dr7;
-
- mark_dirty(svm->vmcb, VMCB_DR);
-
- update_db_intercept(vcpu);
-}
-
static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
{
if (sd->next_asid > sd->max_asid) {
@@ -1748,7 +1733,7 @@ static int db_interception(struct vcpu_svm *svm)
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
svm->vmcb->save.rflags &=
~(X86_EFLAGS_TF | X86_EFLAGS_RF);
- update_db_intercept(&svm->vcpu);
+ update_db_bp_intercept(&svm->vcpu);
}
if (svm->vcpu.guest_debug &
@@ -2063,7 +2048,7 @@ static inline bool nested_svm_intr(struct vcpu_svm *svm)
if (svm->nested.intercept & 1ULL) {
/*
* The #vmexit can't be emulated here directly because this
- * code path runs with irqs and preemtion disabled. A
+ * code path runs with irqs and preemption disabled. A
* #vmexit emulation might sleep. Only signal request for
* the #vmexit here.
*/
@@ -2105,7 +2090,6 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
return kmap(page);
error:
- kvm_release_page_clean(page);
kvm_inject_gp(&svm->vcpu, 0);
return NULL;
@@ -2409,7 +2393,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
/*
* This function merges the msr permission bitmaps of kvm and the
- * nested vmcb. It is omptimized in that it only merges the parts where
+ * nested vmcb. It is optimized in that it only merges the parts where
* the kvm msr permission bitmap may contain zero bits
*/
int i;
@@ -3268,7 +3252,7 @@ static int pause_interception(struct vcpu_svm *svm)
return 1;
}
-static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
+static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_READ_CR0] = cr_interception,
[SVM_EXIT_READ_CR3] = cr_interception,
[SVM_EXIT_READ_CR4] = cr_interception,
@@ -3660,7 +3644,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
*/
svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
- update_db_intercept(vcpu);
+ update_db_bp_intercept(vcpu);
}
static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
@@ -3783,12 +3767,6 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
svm_complete_interrupts(svm);
}
-#ifdef CONFIG_X86_64
-#define R "r"
-#else
-#define R "e"
-#endif
-
static void svm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -3815,13 +3793,13 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
local_irq_enable();
asm volatile (
- "push %%"R"bp; \n\t"
- "mov %c[rbx](%[svm]), %%"R"bx \n\t"
- "mov %c[rcx](%[svm]), %%"R"cx \n\t"
- "mov %c[rdx](%[svm]), %%"R"dx \n\t"
- "mov %c[rsi](%[svm]), %%"R"si \n\t"
- "mov %c[rdi](%[svm]), %%"R"di \n\t"
- "mov %c[rbp](%[svm]), %%"R"bp \n\t"
+ "push %%" _ASM_BP "; \n\t"
+ "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t"
+ "mov %c[rcx](%[svm]), %%" _ASM_CX " \n\t"
+ "mov %c[rdx](%[svm]), %%" _ASM_DX " \n\t"
+ "mov %c[rsi](%[svm]), %%" _ASM_SI " \n\t"
+ "mov %c[rdi](%[svm]), %%" _ASM_DI " \n\t"
+ "mov %c[rbp](%[svm]), %%" _ASM_BP " \n\t"
#ifdef CONFIG_X86_64
"mov %c[r8](%[svm]), %%r8 \n\t"
"mov %c[r9](%[svm]), %%r9 \n\t"
@@ -3834,20 +3812,20 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
#endif
/* Enter guest mode */
- "push %%"R"ax \n\t"
- "mov %c[vmcb](%[svm]), %%"R"ax \n\t"
+ "push %%" _ASM_AX " \n\t"
+ "mov %c[vmcb](%[svm]), %%" _ASM_AX " \n\t"
__ex(SVM_VMLOAD) "\n\t"
__ex(SVM_VMRUN) "\n\t"
__ex(SVM_VMSAVE) "\n\t"
- "pop %%"R"ax \n\t"
+ "pop %%" _ASM_AX " \n\t"
/* Save guest registers, load host registers */
- "mov %%"R"bx, %c[rbx](%[svm]) \n\t"
- "mov %%"R"cx, %c[rcx](%[svm]) \n\t"
- "mov %%"R"dx, %c[rdx](%[svm]) \n\t"
- "mov %%"R"si, %c[rsi](%[svm]) \n\t"
- "mov %%"R"di, %c[rdi](%[svm]) \n\t"
- "mov %%"R"bp, %c[rbp](%[svm]) \n\t"
+ "mov %%" _ASM_BX ", %c[rbx](%[svm]) \n\t"
+ "mov %%" _ASM_CX ", %c[rcx](%[svm]) \n\t"
+ "mov %%" _ASM_DX ", %c[rdx](%[svm]) \n\t"
+ "mov %%" _ASM_SI ", %c[rsi](%[svm]) \n\t"
+ "mov %%" _ASM_DI ", %c[rdi](%[svm]) \n\t"
+ "mov %%" _ASM_BP ", %c[rbp](%[svm]) \n\t"
#ifdef CONFIG_X86_64
"mov %%r8, %c[r8](%[svm]) \n\t"
"mov %%r9, %c[r9](%[svm]) \n\t"
@@ -3858,7 +3836,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r14, %c[r14](%[svm]) \n\t"
"mov %%r15, %c[r15](%[svm]) \n\t"
#endif
- "pop %%"R"bp"
+ "pop %%" _ASM_BP
:
: [svm]"a"(svm),
[vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)),
@@ -3879,9 +3857,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
[r15]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R15]))
#endif
: "cc", "memory"
- , R"bx", R"cx", R"dx", R"si", R"di"
#ifdef CONFIG_X86_64
+ , "rbx", "rcx", "rdx", "rsi", "rdi"
, "r8", "r9", "r10", "r11" , "r12", "r13", "r14", "r15"
+#else
+ , "ebx", "ecx", "edx", "esi", "edi"
#endif
);
@@ -3941,8 +3921,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
mark_all_clean(svm->vmcb);
}
-#undef R
-
static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -4069,7 +4047,7 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
#define POST_MEM(exit) { .exit_code = (exit), \
.stage = X86_ICPT_POST_MEMACCESS, }
-static struct __x86_intercept {
+static const struct __x86_intercept {
u32 exit_code;
enum x86_intercept_stage stage;
} x86_intercept_map[] = {
@@ -4260,7 +4238,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.vcpu_load = svm_vcpu_load,
.vcpu_put = svm_vcpu_put,
- .set_guest_debug = svm_guest_debug,
+ .update_db_bp_intercept = update_db_bp_intercept,
.get_msr = svm_get_msr,
.set_msr = svm_set_msr,
.get_segment_base = svm_get_segment_base,
diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c
deleted file mode 100644
index 6b85cc647f3..00000000000
--- a/arch/x86/kvm/timer.c
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Kernel-based Virtual Machine driver for Linux
- *
- * This module enables machines with Intel VT-x extensions to run virtual
- * machines without emulation or binary translation.
- *
- * timer support
- *
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- * This work is licensed under the terms of the GNU GPL, version 2. See
- * the COPYING file in the top-level directory.
- */
-
-#include <linux/kvm_host.h>
-#include <linux/kvm.h>
-#include <linux/hrtimer.h>
-#include <linux/atomic.h>
-#include "kvm_timer.h"
-
-enum hrtimer_restart kvm_timer_fn(struct hrtimer *data)
-{
- struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
- struct kvm_vcpu *vcpu = ktimer->vcpu;
- wait_queue_head_t *q = &vcpu->wq;
-
- /*
- * There is a race window between reading and incrementing, but we do
- * not care about potentially losing timer events in the !reinject
- * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
- * in vcpu_enter_guest.
- */
- if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
- atomic_inc(&ktimer->pending);
- /* FIXME: this code should not know anything about vcpus */
- kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
- }
-
- if (waitqueue_active(q))
- wake_up_interruptible(q);
-
- if (ktimer->t_ops->is_periodic(ktimer)) {
- hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
- return HRTIMER_RESTART;
- } else
- return HRTIMER_NORESTART;
-}
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index a71faf727ff..bca63f04dcc 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -183,95 +183,6 @@ TRACE_EVENT(kvm_apic,
#define KVM_ISA_VMX 1
#define KVM_ISA_SVM 2
-#define VMX_EXIT_REASONS \
- { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
- { EXIT_REASON_EXTERNAL_INTERRUPT, "EXTERNAL_INTERRUPT" }, \
- { EXIT_REASON_TRIPLE_FAULT, "TRIPLE_FAULT" }, \
- { EXIT_REASON_PENDING_INTERRUPT, "PENDING_INTERRUPT" }, \
- { EXIT_REASON_NMI_WINDOW, "NMI_WINDOW" }, \
- { EXIT_REASON_TASK_SWITCH, "TASK_SWITCH" }, \
- { EXIT_REASON_CPUID, "CPUID" }, \
- { EXIT_REASON_HLT, "HLT" }, \
- { EXIT_REASON_INVLPG, "INVLPG" }, \
- { EXIT_REASON_RDPMC, "RDPMC" }, \
- { EXIT_REASON_RDTSC, "RDTSC" }, \
- { EXIT_REASON_VMCALL, "VMCALL" }, \
- { EXIT_REASON_VMCLEAR, "VMCLEAR" }, \
- { EXIT_REASON_VMLAUNCH, "VMLAUNCH" }, \
- { EXIT_REASON_VMPTRLD, "VMPTRLD" }, \
- { EXIT_REASON_VMPTRST, "VMPTRST" }, \
- { EXIT_REASON_VMREAD, "VMREAD" }, \
- { EXIT_REASON_VMRESUME, "VMRESUME" }, \
- { EXIT_REASON_VMWRITE, "VMWRITE" }, \
- { EXIT_REASON_VMOFF, "VMOFF" }, \
- { EXIT_REASON_VMON, "VMON" }, \
- { EXIT_REASON_CR_ACCESS, "CR_ACCESS" }, \
- { EXIT_REASON_DR_ACCESS, "DR_ACCESS" }, \
- { EXIT_REASON_IO_INSTRUCTION, "IO_INSTRUCTION" }, \
- { EXIT_REASON_MSR_READ, "MSR_READ" }, \
- { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \
- { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \
- { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \
- { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \
- { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
- { EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
- { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
- { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
- { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
- { EXIT_REASON_WBINVD, "WBINVD" }
-
-#define SVM_EXIT_REASONS \
- { SVM_EXIT_READ_CR0, "read_cr0" }, \
- { SVM_EXIT_READ_CR3, "read_cr3" }, \
- { SVM_EXIT_READ_CR4, "read_cr4" }, \
- { SVM_EXIT_READ_CR8, "read_cr8" }, \
- { SVM_EXIT_WRITE_CR0, "write_cr0" }, \
- { SVM_EXIT_WRITE_CR3, "write_cr3" }, \
- { SVM_EXIT_WRITE_CR4, "write_cr4" }, \
- { SVM_EXIT_WRITE_CR8, "write_cr8" }, \
- { SVM_EXIT_READ_DR0, "read_dr0" }, \
- { SVM_EXIT_READ_DR1, "read_dr1" }, \
- { SVM_EXIT_READ_DR2, "read_dr2" }, \
- { SVM_EXIT_READ_DR3, "read_dr3" }, \
- { SVM_EXIT_WRITE_DR0, "write_dr0" }, \
- { SVM_EXIT_WRITE_DR1, "write_dr1" }, \
- { SVM_EXIT_WRITE_DR2, "write_dr2" }, \
- { SVM_EXIT_WRITE_DR3, "write_dr3" }, \
- { SVM_EXIT_WRITE_DR5, "write_dr5" }, \
- { SVM_EXIT_WRITE_DR7, "write_dr7" }, \
- { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, \
- { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, \
- { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \
- { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \
- { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \
- { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \
- { SVM_EXIT_INTR, "interrupt" }, \
- { SVM_EXIT_NMI, "nmi" }, \
- { SVM_EXIT_SMI, "smi" }, \
- { SVM_EXIT_INIT, "init" }, \
- { SVM_EXIT_VINTR, "vintr" }, \
- { SVM_EXIT_CPUID, "cpuid" }, \
- { SVM_EXIT_INVD, "invd" }, \
- { SVM_EXIT_HLT, "hlt" }, \
- { SVM_EXIT_INVLPG, "invlpg" }, \
- { SVM_EXIT_INVLPGA, "invlpga" }, \
- { SVM_EXIT_IOIO, "io" }, \
- { SVM_EXIT_MSR, "msr" }, \
- { SVM_EXIT_TASK_SWITCH, "task_switch" }, \
- { SVM_EXIT_SHUTDOWN, "shutdown" }, \
- { SVM_EXIT_VMRUN, "vmrun" }, \
- { SVM_EXIT_VMMCALL, "hypercall" }, \
- { SVM_EXIT_VMLOAD, "vmload" }, \
- { SVM_EXIT_VMSAVE, "vmsave" }, \
- { SVM_EXIT_STGI, "stgi" }, \
- { SVM_EXIT_CLGI, "clgi" }, \
- { SVM_EXIT_SKINIT, "skinit" }, \
- { SVM_EXIT_WBINVD, "wbinvd" }, \
- { SVM_EXIT_MONITOR, "monitor" }, \
- { SVM_EXIT_MWAIT, "mwait" }, \
- { SVM_EXIT_XSETBV, "xsetbv" }, \
- { SVM_EXIT_NPF, "npf" }
-
/*
* Tracepoint for kvm guest exit:
*/
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03de1b7..ad6b1dd06f8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -127,6 +127,8 @@ module_param(ple_gap, int, S_IRUGO);
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
+extern const ulong vmx_return;
+
#define NR_AUTOLOAD_MSRS 8
#define VMCS02_POOL_SIZE 1
@@ -405,16 +407,16 @@ struct vcpu_vmx {
struct {
int vm86_active;
ulong save_rflags;
+ struct kvm_segment segs[8];
+ } rmode;
+ struct {
+ u32 bitmask; /* 4 bits per segment (1 bit per field) */
struct kvm_save_segment {
u16 selector;
unsigned long base;
u32 limit;
u32 ar;
- } tr, es, ds, fs, gs;
- } rmode;
- struct {
- u32 bitmask; /* 4 bits per segment (1 bit per field) */
- struct kvm_save_segment seg[8];
+ } seg[8];
} segment_cache;
int vpid;
bool emulation_required;
@@ -450,7 +452,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
#define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \
[number##_HIGH] = VMCS12_OFFSET(name)+4
-static unsigned short vmcs_field_to_offset_table[] = {
+static const unsigned short vmcs_field_to_offset_table[] = {
FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
FIELD(GUEST_ES_SELECTOR, guest_es_selector),
FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
@@ -596,10 +598,9 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
{
struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT);
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
+ if (is_error_page(page))
return NULL;
- }
+
return page;
}
@@ -667,7 +668,7 @@ static struct vmx_capability {
.ar_bytes = GUEST_##seg##_AR_BYTES, \
}
-static struct kvm_vmx_segment_field {
+static const struct kvm_vmx_segment_field {
unsigned selector;
unsigned base;
unsigned limit;
@@ -1343,7 +1344,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
guest_efer = vmx->vcpu.arch.efer;
/*
- * NX is emulated; LMA and LME handled by hardware; SCE meaninless
+ * NX is emulated; LMA and LME handled by hardware; SCE meaningless
* outside long mode
*/
ignore_bits = EFER_NX | EFER_SCE;
@@ -1493,8 +1494,12 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
#ifdef CONFIG_X86_64
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
#endif
- if (user_has_fpu())
- clts();
+ /*
+ * If the FPU is not active (through the host task or
+ * the guest vcpu), then restore the cr0.TS bit.
+ */
+ if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+ stts();
load_gdt(&__get_cpu_var(host_gdt));
}
@@ -1991,7 +1996,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
#endif
CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
- CPU_BASED_RDPMC_EXITING |
+ CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
/*
* We can allow some features even when not supported by the
@@ -2287,16 +2292,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
}
}
-static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
-{
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
- else
- vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
-
- update_exception_bitmap(vcpu);
-}
-
static __init int cpu_has_kvm_support(void)
{
return cpu_has_vmx();
@@ -2694,20 +2689,17 @@ static __exit void hardware_unsetup(void)
free_kvm_area();
}
-static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save)
+static void fix_pmode_dataseg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save)
{
- struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ struct kvm_segment tmp = *save;
- if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) {
- vmcs_write16(sf->selector, save->selector);
- vmcs_writel(sf->base, save->base);
- vmcs_write32(sf->limit, save->limit);
- vmcs_write32(sf->ar_bytes, save->ar);
- } else {
- u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK)
- << AR_DPL_SHIFT;
- vmcs_write32(sf->ar_bytes, 0x93 | dpl);
+ if (!(vmcs_readl(sf->base) == tmp.base && tmp.s)) {
+ tmp.base = vmcs_readl(sf->base);
+ tmp.selector = vmcs_read16(sf->selector);
+ tmp.s = 1;
}
+ vmx_set_segment(vcpu, &tmp, seg);
}
static void enter_pmode(struct kvm_vcpu *vcpu)
@@ -2720,10 +2712,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
vmx_segment_cache_clear(vmx);
- vmcs_write16(GUEST_TR_SELECTOR, vmx->rmode.tr.selector);
- vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base);
- vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit);
- vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
+ vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
flags = vmcs_readl(GUEST_RFLAGS);
flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
@@ -2738,10 +2727,10 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
if (emulate_invalid_guest_state)
return;
- fix_pmode_dataseg(VCPU_SREG_ES, &vmx->rmode.es);
- fix_pmode_dataseg(VCPU_SREG_DS, &vmx->rmode.ds);
- fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs);
- fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs);
+ fix_pmode_dataseg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
+ fix_pmode_dataseg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
+ fix_pmode_dataseg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
+ fix_pmode_dataseg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
vmx_segment_cache_clear(vmx);
@@ -2769,14 +2758,10 @@ static gva_t rmode_tss_base(struct kvm *kvm)
return kvm->arch.tss_addr;
}
-static void fix_rmode_seg(int seg, struct kvm_save_segment *save)
+static void fix_rmode_seg(int seg, struct kvm_segment *save)
{
- struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
- save->selector = vmcs_read16(sf->selector);
- save->base = vmcs_readl(sf->base);
- save->limit = vmcs_read32(sf->limit);
- save->ar = vmcs_read32(sf->ar_bytes);
vmcs_write16(sf->selector, save->base >> 4);
vmcs_write32(sf->base, save->base & 0xffff0);
vmcs_write32(sf->limit, 0xffff);
@@ -2796,9 +2781,16 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
if (enable_unrestricted_guest)
return;
+ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
+ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
+ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
+ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
+ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+
vmx->emulation_required = 1;
vmx->rmode.vm86_active = 1;
+
/*
* Very old userspace does not call KVM_SET_TSS_ADDR before entering
* vcpu. Call it here with phys address pointing 16M below 4G.
@@ -2813,14 +2805,8 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
vmx_segment_cache_clear(vmx);
- vmx->rmode.tr.selector = vmcs_read16(GUEST_TR_SELECTOR);
- vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
-
- vmx->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
-
- vmx->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
flags = vmcs_readl(GUEST_RFLAGS);
@@ -3113,35 +3099,24 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct kvm_save_segment *save;
u32 ar;
if (vmx->rmode.vm86_active
&& (seg == VCPU_SREG_TR || seg == VCPU_SREG_ES
|| seg == VCPU_SREG_DS || seg == VCPU_SREG_FS
- || seg == VCPU_SREG_GS)
- && !emulate_invalid_guest_state) {
- switch (seg) {
- case VCPU_SREG_TR: save = &vmx->rmode.tr; break;
- case VCPU_SREG_ES: save = &vmx->rmode.es; break;
- case VCPU_SREG_DS: save = &vmx->rmode.ds; break;
- case VCPU_SREG_FS: save = &vmx->rmode.fs; break;
- case VCPU_SREG_GS: save = &vmx->rmode.gs; break;
- default: BUG();
- }
- var->selector = save->selector;
- var->base = save->base;
- var->limit = save->limit;
- ar = save->ar;
+ || seg == VCPU_SREG_GS)) {
+ *var = vmx->rmode.segs[seg];
if (seg == VCPU_SREG_TR
|| var->selector == vmx_read_guest_seg_selector(vmx, seg))
- goto use_saved_rmode_seg;
+ return;
+ var->base = vmx_read_guest_seg_base(vmx, seg);
+ var->selector = vmx_read_guest_seg_selector(vmx, seg);
+ return;
}
var->base = vmx_read_guest_seg_base(vmx, seg);
var->limit = vmx_read_guest_seg_limit(vmx, seg);
var->selector = vmx_read_guest_seg_selector(vmx, seg);
ar = vmx_read_guest_seg_ar(vmx, seg);
-use_saved_rmode_seg:
if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
ar = 0;
var->type = ar & 15;
@@ -3223,23 +3198,21 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
u32 ar;
vmx_segment_cache_clear(vmx);
if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
vmcs_write16(sf->selector, var->selector);
- vmx->rmode.tr.selector = var->selector;
- vmx->rmode.tr.base = var->base;
- vmx->rmode.tr.limit = var->limit;
- vmx->rmode.tr.ar = vmx_segment_access_rights(var);
+ vmx->rmode.segs[VCPU_SREG_TR] = *var;
return;
}
vmcs_writel(sf->base, var->base);
vmcs_write32(sf->limit, var->limit);
vmcs_write16(sf->selector, var->selector);
if (vmx->rmode.vm86_active && var->s) {
+ vmx->rmode.segs[seg] = *var;
/*
* Hack real-mode segments into vm86 compatibility.
*/
@@ -3254,7 +3227,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
* qemu binaries.
* IA32 arch specifies that at the time of processor reset the
* "Accessed" bit in the AR field of segment registers is 1. And qemu
- * is setting it to 0 in the usedland code. This causes invalid guest
+ * is setting it to 0 in the userland code. This causes invalid guest
* state vmexit when "unrestricted guest" mode is turned on.
* Fix for this setup issue in cpu_reset is being pushed in the qemu
* tree. Newer qemu binaries with that qemu fix would not need this
@@ -3284,16 +3257,10 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
vmcs_readl(GUEST_CS_BASE) >> 4);
break;
case VCPU_SREG_ES:
- fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
- break;
case VCPU_SREG_DS:
- fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
- break;
case VCPU_SREG_GS:
- fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
- break;
case VCPU_SREG_FS:
- fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
+ fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
break;
case VCPU_SREG_SS:
vmcs_write16(GUEST_SS_SELECTOR,
@@ -3347,9 +3314,9 @@ static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
if (var.base != (var.selector << 4))
return false;
- if (var.limit != 0xffff)
+ if (var.limit < 0xffff)
return false;
- if (ar != 0xf3)
+ if (((ar | (3 << AR_DPL_SHIFT)) & ~(AR_G_MASK | AR_DB_MASK)) != 0xf3)
return false;
return true;
@@ -3601,7 +3568,7 @@ out:
static void seg_setup(int seg)
{
- struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+ const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
unsigned int ar;
vmcs_write16(sf->selector, 0);
@@ -3619,6 +3586,7 @@ static void seg_setup(int seg)
static int alloc_apic_access_page(struct kvm *kvm)
{
+ struct page *page;
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
@@ -3633,7 +3601,13 @@ static int alloc_apic_access_page(struct kvm *kvm)
if (r)
goto out;
- kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
+ page = gfn_to_page(kvm, 0xfee00);
+ if (is_error_page(page)) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ kvm->arch.apic_access_page = page;
out:
mutex_unlock(&kvm->slots_lock);
return r;
@@ -3641,6 +3615,7 @@ out:
static int alloc_identity_pagetable(struct kvm *kvm)
{
+ struct page *page;
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
@@ -3656,8 +3631,13 @@ static int alloc_identity_pagetable(struct kvm *kvm)
if (r)
goto out;
- kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
- kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+ page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
+ if (is_error_page(page)) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ kvm->arch.ept_identity_pagetable = page;
out:
mutex_unlock(&kvm->slots_lock);
return r;
@@ -3730,7 +3710,7 @@ static void vmx_set_constant_host_state(void)
unsigned long tmpl;
struct desc_ptr dt;
- vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS); /* 22.2.3 */
+ vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */
vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
@@ -3753,8 +3733,7 @@ static void vmx_set_constant_host_state(void)
native_store_idt(&dt);
vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
- asm("mov $.Lkvm_vmx_return, %0" : "=r"(tmpl));
- vmcs_writel(HOST_RIP, tmpl); /* 22.2.5 */
+ vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */
rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
@@ -3988,8 +3967,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
kvm_rip_write(vcpu, 0);
kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
- vmcs_writel(GUEST_DR7, 0x400);
-
vmcs_writel(GUEST_GDTR_BASE, 0);
vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
@@ -4439,7 +4416,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
hypercall[2] = 0xc1;
}
-/* called to set cr0 as approriate for a mov-to-cr0 exit. */
+/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
{
if (to_vmx(vcpu)->nested.vmxon &&
@@ -4530,7 +4507,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
vcpu->run->exit_reason = KVM_EXIT_SET_TPR;
return 0;
}
- };
+ }
break;
case 2: /* clts */
handle_clts(vcpu);
@@ -5684,7 +5661,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
* to be done to userspace and return 0.
*/
-static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
+static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_EXCEPTION_NMI] = handle_exception,
[EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt,
[EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault,
@@ -6212,17 +6189,10 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
msrs[i].host);
}
-#ifdef CONFIG_X86_64
-#define R "r"
-#define Q "q"
-#else
-#define R "e"
-#define Q "l"
-#endif
-
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ unsigned long debugctlmsr;
if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) {
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -6262,34 +6232,35 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmx_set_interrupt_shadow(vcpu, 0);
atomic_switch_perf_msrs(vmx);
+ debugctlmsr = get_debugctlmsr();
vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
- "push %%"R"dx; push %%"R"bp;"
- "push %%"R"cx \n\t" /* placeholder for guest rcx */
- "push %%"R"cx \n\t"
- "cmp %%"R"sp, %c[host_rsp](%0) \n\t"
+ "push %%" _ASM_DX "; push %%" _ASM_BP ";"
+ "push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */
+ "push %%" _ASM_CX " \n\t"
+ "cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
"je 1f \n\t"
- "mov %%"R"sp, %c[host_rsp](%0) \n\t"
+ "mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
"1: \n\t"
/* Reload cr2 if changed */
- "mov %c[cr2](%0), %%"R"ax \n\t"
- "mov %%cr2, %%"R"dx \n\t"
- "cmp %%"R"ax, %%"R"dx \n\t"
+ "mov %c[cr2](%0), %%" _ASM_AX " \n\t"
+ "mov %%cr2, %%" _ASM_DX " \n\t"
+ "cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t"
"je 2f \n\t"
- "mov %%"R"ax, %%cr2 \n\t"
+ "mov %%" _ASM_AX", %%cr2 \n\t"
"2: \n\t"
/* Check if vmlaunch of vmresume is needed */
"cmpl $0, %c[launched](%0) \n\t"
/* Load guest registers. Don't clobber flags. */
- "mov %c[rax](%0), %%"R"ax \n\t"
- "mov %c[rbx](%0), %%"R"bx \n\t"
- "mov %c[rdx](%0), %%"R"dx \n\t"
- "mov %c[rsi](%0), %%"R"si \n\t"
- "mov %c[rdi](%0), %%"R"di \n\t"
- "mov %c[rbp](%0), %%"R"bp \n\t"
+ "mov %c[rax](%0), %%" _ASM_AX " \n\t"
+ "mov %c[rbx](%0), %%" _ASM_BX " \n\t"
+ "mov %c[rdx](%0), %%" _ASM_DX " \n\t"
+ "mov %c[rsi](%0), %%" _ASM_SI " \n\t"
+ "mov %c[rdi](%0), %%" _ASM_DI " \n\t"
+ "mov %c[rbp](%0), %%" _ASM_BP " \n\t"
#ifdef CONFIG_X86_64
"mov %c[r8](%0), %%r8 \n\t"
"mov %c[r9](%0), %%r9 \n\t"
@@ -6300,24 +6271,24 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %c[r14](%0), %%r14 \n\t"
"mov %c[r15](%0), %%r15 \n\t"
#endif
- "mov %c[rcx](%0), %%"R"cx \n\t" /* kills %0 (ecx) */
+ "mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */
/* Enter guest mode */
- "jne .Llaunched \n\t"
+ "jne 1f \n\t"
__ex(ASM_VMX_VMLAUNCH) "\n\t"
- "jmp .Lkvm_vmx_return \n\t"
- ".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t"
- ".Lkvm_vmx_return: "
+ "jmp 2f \n\t"
+ "1: " __ex(ASM_VMX_VMRESUME) "\n\t"
+ "2: "
/* Save guest registers, load host registers, keep flags */
- "mov %0, %c[wordsize](%%"R"sp) \n\t"
+ "mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
"pop %0 \n\t"
- "mov %%"R"ax, %c[rax](%0) \n\t"
- "mov %%"R"bx, %c[rbx](%0) \n\t"
- "pop"Q" %c[rcx](%0) \n\t"
- "mov %%"R"dx, %c[rdx](%0) \n\t"
- "mov %%"R"si, %c[rsi](%0) \n\t"
- "mov %%"R"di, %c[rdi](%0) \n\t"
- "mov %%"R"bp, %c[rbp](%0) \n\t"
+ "mov %%" _ASM_AX ", %c[rax](%0) \n\t"
+ "mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
+ __ASM_SIZE(pop) " %c[rcx](%0) \n\t"
+ "mov %%" _ASM_DX ", %c[rdx](%0) \n\t"
+ "mov %%" _ASM_SI ", %c[rsi](%0) \n\t"
+ "mov %%" _ASM_DI ", %c[rdi](%0) \n\t"
+ "mov %%" _ASM_BP ", %c[rbp](%0) \n\t"
#ifdef CONFIG_X86_64
"mov %%r8, %c[r8](%0) \n\t"
"mov %%r9, %c[r9](%0) \n\t"
@@ -6328,11 +6299,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
"mov %%r14, %c[r14](%0) \n\t"
"mov %%r15, %c[r15](%0) \n\t"
#endif
- "mov %%cr2, %%"R"ax \n\t"
- "mov %%"R"ax, %c[cr2](%0) \n\t"
+ "mov %%cr2, %%" _ASM_AX " \n\t"
+ "mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
- "pop %%"R"bp; pop %%"R"dx \n\t"
+ "pop %%" _ASM_BP "; pop %%" _ASM_DX " \n\t"
"setbe %c[fail](%0) \n\t"
+ ".pushsection .rodata \n\t"
+ ".global vmx_return \n\t"
+ "vmx_return: " _ASM_PTR " 2b \n\t"
+ ".popsection"
: : "c"(vmx), "d"((unsigned long)HOST_RSP),
[launched]"i"(offsetof(struct vcpu_vmx, __launched)),
[fail]"i"(offsetof(struct vcpu_vmx, fail)),
@@ -6357,12 +6332,18 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
[wordsize]"i"(sizeof(ulong))
: "cc", "memory"
- , R"ax", R"bx", R"di", R"si"
#ifdef CONFIG_X86_64
+ , "rax", "rbx", "rdi", "rsi"
, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
+#else
+ , "eax", "ebx", "edi", "esi"
#endif
);
+ /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
+ if (debugctlmsr)
+ update_debugctlmsr(debugctlmsr);
+
#ifndef CONFIG_X86_64
/*
* The sysexit path does not restore ds/es, so we must set them to
@@ -6407,9 +6388,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmx_complete_interrupts(vmx);
}
-#undef R
-#undef Q
-
static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6575,7 +6553,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
/* Exposing INVPCID only when PCID is exposed */
best = kvm_find_cpuid_entry(vcpu, 0x7, 0);
if (vmx_invpcid_supported() &&
- best && (best->ecx & bit(X86_FEATURE_INVPCID)) &&
+ best && (best->ebx & bit(X86_FEATURE_INVPCID)) &&
guest_cpuid_has_pcid(vcpu)) {
exec_control |= SECONDARY_EXEC_ENABLE_INVPCID;
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
@@ -6585,7 +6563,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
vmcs_write32(SECONDARY_VM_EXEC_CONTROL,
exec_control);
if (best)
- best->ecx &= ~bit(X86_FEATURE_INVPCID);
+ best->ebx &= ~bit(X86_FEATURE_INVPCID);
}
}
@@ -7264,7 +7242,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.vcpu_load = vmx_vcpu_load,
.vcpu_put = vmx_vcpu_put,
- .set_guest_debug = set_guest_debug,
+ .update_db_bp_intercept = update_exception_bitmap,
.get_msr = vmx_get_msr,
.set_msr = vmx_set_msr,
.get_segment_base = vmx_get_segment_base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 148ed666e31..1eefebe5d72 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,20 +246,14 @@ static void drop_user_return_notifiers(void *ignore)
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
- if (irqchip_in_kernel(vcpu->kvm))
- return vcpu->arch.apic_base;
- else
- return vcpu->arch.apic_base;
+ return vcpu->arch.apic_base;
}
EXPORT_SYMBOL_GPL(kvm_get_apic_base);
void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
{
/* TODO: reserve bits check */
- if (irqchip_in_kernel(vcpu->kvm))
- kvm_lapic_set_base(vcpu, data);
- else
- vcpu->arch.apic_base = data;
+ kvm_lapic_set_base(vcpu, data);
}
EXPORT_SYMBOL_GPL(kvm_set_apic_base);
@@ -698,6 +692,18 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);
+static void kvm_update_dr7(struct kvm_vcpu *vcpu)
+{
+ unsigned long dr7;
+
+ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+ dr7 = vcpu->arch.guest_debug_dr7;
+ else
+ dr7 = vcpu->arch.dr7;
+ kvm_x86_ops->set_dr7(vcpu, dr7);
+ vcpu->arch.switch_db_regs = (dr7 & DR7_BP_EN_MASK);
+}
+
static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
switch (dr) {
@@ -723,10 +729,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
if (val & 0xffffffff00000000ULL)
return -1; /* #GP */
vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
- vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
- }
+ kvm_update_dr7(vcpu);
break;
}
@@ -823,7 +826,7 @@ static u32 msrs_to_save[] = {
static unsigned num_msrs_to_save;
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs[] = {
MSR_IA32_TSCDEADLINE,
MSR_IA32_MISC_ENABLE,
MSR_IA32_MCG_STATUS,
@@ -1097,7 +1100,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
* For each generation, we track the original measured
* nanosecond time, offset, and write, so if TSCs are in
* sync, we can match exact offset, and if not, we can match
- * exact software computaion in compute_guest_tsc()
+ * exact software computation in compute_guest_tsc()
*
* These values are tracked in kvm->arch.cur_xxx variables.
*/
@@ -1140,6 +1143,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
unsigned long this_tsc_khz;
s64 kernel_ns, max_kernel_ns;
u64 tsc_timestamp;
+ u8 pvclock_flags;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
@@ -1221,7 +1225,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
vcpu->last_kernel_ns = kernel_ns;
vcpu->last_guest_tsc = tsc_timestamp;
- vcpu->hv_clock.flags = 0;
+
+ pvclock_flags = 0;
+ if (vcpu->pvclock_set_guest_stopped_request) {
+ pvclock_flags |= PVCLOCK_GUEST_STOPPED;
+ vcpu->pvclock_set_guest_stopped_request = false;
+ }
+
+ vcpu->hv_clock.flags = pvclock_flags;
/*
* The interface expects us to write an even number signaling that the
@@ -1504,7 +1515,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
{
gpa_t gpa = data & ~0x3f;
- /* Bits 2:5 are resrved, Should be zero */
+ /* Bits 2:5 are reserved, Should be zero */
if (data & 0x3c)
return 1;
@@ -1639,10 +1650,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
vcpu->arch.time_page =
gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
- if (is_error_page(vcpu->arch.time_page)) {
- kvm_release_page_clean(vcpu->arch.time_page);
+ if (is_error_page(vcpu->arch.time_page))
vcpu->arch.time_page = NULL;
- }
+
break;
}
case MSR_KVM_ASYNC_PF_EN:
@@ -1727,7 +1737,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
* Ignore all writes to this no longer documented MSR.
* Writes are only relevant for old K7 processors,
* all pre-dating SVM, but a recommended workaround from
- * AMD for these chips. It is possible to speicify the
+ * AMD for these chips. It is possible to specify the
* affected processor models on the command line, hence
* the need to ignore the workaround.
*/
@@ -2177,6 +2187,8 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_GET_TSC_KHZ:
case KVM_CAP_PCI_2_3:
case KVM_CAP_KVMCLOCK_CTRL:
+ case KVM_CAP_READONLY_MEM:
+ case KVM_CAP_IRQFD_RESAMPLE:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -2358,8 +2370,7 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
- memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
- kvm_apic_post_state_restore(vcpu);
+ kvm_apic_post_state_restore(vcpu, s);
update_cr8_intercept(vcpu);
return 0;
@@ -2368,7 +2379,7 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
struct kvm_interrupt *irq)
{
- if (irq->irq < 0 || irq->irq >= 256)
+ if (irq->irq < 0 || irq->irq >= KVM_NR_INTERRUPTS)
return -EINVAL;
if (irqchip_in_kernel(vcpu->kvm))
return -ENXIO;
@@ -2635,11 +2646,9 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
*/
static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
{
- struct pvclock_vcpu_time_info *src = &vcpu->arch.hv_clock;
if (!vcpu->arch.time_page)
return -EINVAL;
- src->flags |= PVCLOCK_GUEST_STOPPED;
- mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
+ vcpu->arch.pvclock_set_guest_stopped_request = true;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
return 0;
}
@@ -3090,7 +3099,7 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
if (!kvm->arch.vpit)
return -ENXIO;
mutex_lock(&kvm->arch.vpit->pit_state.lock);
- kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
+ kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
mutex_unlock(&kvm->arch.vpit->pit_state.lock);
return 0;
}
@@ -3173,6 +3182,16 @@ out:
return r;
}
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event)
+{
+ if (!irqchip_in_kernel(kvm))
+ return -ENXIO;
+
+ irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+ irq_event->irq, irq_event->level);
+ return 0;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -3279,29 +3298,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
create_pit_unlock:
mutex_unlock(&kvm->slots_lock);
break;
- case KVM_IRQ_LINE_STATUS:
- case KVM_IRQ_LINE: {
- struct kvm_irq_level irq_event;
-
- r = -EFAULT;
- if (copy_from_user(&irq_event, argp, sizeof irq_event))
- goto out;
- r = -ENXIO;
- if (irqchip_in_kernel(kvm)) {
- __s32 status;
- status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
- irq_event.irq, irq_event.level);
- if (ioctl == KVM_IRQ_LINE_STATUS) {
- r = -EFAULT;
- irq_event.status = status;
- if (copy_to_user(argp, &irq_event,
- sizeof irq_event))
- goto out;
- }
- r = 0;
- }
- break;
- }
case KVM_GET_IRQCHIP: {
/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
struct kvm_irqchip *chip;
@@ -3689,20 +3685,17 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
gpa_t *gpa, struct x86_exception *exception,
bool write)
{
- u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0)
+ | (write ? PFERR_WRITE_MASK : 0);
- if (vcpu_match_mmio_gva(vcpu, gva) &&
- check_write_user_access(vcpu, write, access,
- vcpu->arch.access)) {
+ if (vcpu_match_mmio_gva(vcpu, gva)
+ && !permission_fault(vcpu->arch.walk_mmu, vcpu->arch.access, access)) {
*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
(gva & (PAGE_SIZE - 1));
trace_vcpu_match_mmio(gva, *gpa, write, false);
return 1;
}
- if (write)
- access |= PFERR_WRITE_MASK;
-
*gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
if (*gpa == UNMAPPED_GVA)
@@ -3790,14 +3783,14 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
return X86EMUL_CONTINUE;
}
-static struct read_write_emulator_ops read_emultor = {
+static const struct read_write_emulator_ops read_emultor = {
.read_write_prepare = read_prepare,
.read_write_emulate = read_emulate,
.read_write_mmio = vcpu_mmio_read,
.read_write_exit_mmio = read_exit_mmio,
};
-static struct read_write_emulator_ops write_emultor = {
+static const struct read_write_emulator_ops write_emultor = {
.read_write_emulate = write_emulate,
.read_write_mmio = write_mmio,
.read_write_exit_mmio = write_exit_mmio,
@@ -3808,7 +3801,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
unsigned int bytes,
struct x86_exception *exception,
struct kvm_vcpu *vcpu,
- struct read_write_emulator_ops *ops)
+ const struct read_write_emulator_ops *ops)
{
gpa_t gpa;
int handled, ret;
@@ -3857,7 +3850,7 @@ mmio:
int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
void *val, unsigned int bytes,
struct x86_exception *exception,
- struct read_write_emulator_ops *ops)
+ const struct read_write_emulator_ops *ops)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
gpa_t gpa;
@@ -3962,10 +3955,8 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
goto emul_write;
page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
- if (is_error_page(page)) {
- kvm_release_page_clean(page);
+ if (is_error_page(page))
goto emul_write;
- }
kaddr = kmap_atomic(page);
kaddr += offset_in_page(gpa);
@@ -4332,7 +4323,19 @@ static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx);
}
-static struct x86_emulate_ops emulate_ops = {
+static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
+{
+ return kvm_register_read(emul_to_vcpu(ctxt), reg);
+}
+
+static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val)
+{
+ kvm_register_write(emul_to_vcpu(ctxt), reg, val);
+}
+
+static const struct x86_emulate_ops emulate_ops = {
+ .read_gpr = emulator_read_gpr,
+ .write_gpr = emulator_write_gpr,
.read_std = kvm_read_guest_virt_system,
.write_std = kvm_write_guest_virt_system,
.fetch = kvm_fetch_guest_virt,
@@ -4367,14 +4370,6 @@ static struct x86_emulate_ops emulate_ops = {
.get_cpuid = emulator_get_cpuid,
};
-static void cache_all_regs(struct kvm_vcpu *vcpu)
-{
- kvm_register_read(vcpu, VCPU_REGS_RAX);
- kvm_register_read(vcpu, VCPU_REGS_RSP);
- kvm_register_read(vcpu, VCPU_REGS_RIP);
- vcpu->arch.regs_dirty = ~0;
-}
-
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
{
u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu, mask);
@@ -4401,12 +4396,10 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
kvm_queue_exception(vcpu, ctxt->exception.vector);
}
-static void init_decode_cache(struct x86_emulate_ctxt *ctxt,
- const unsigned long *regs)
+static void init_decode_cache(struct x86_emulate_ctxt *ctxt)
{
memset(&ctxt->twobyte, 0,
- (void *)&ctxt->regs - (void *)&ctxt->twobyte);
- memcpy(ctxt->regs, regs, sizeof(ctxt->regs));
+ (void *)&ctxt->_regs - (void *)&ctxt->twobyte);
ctxt->fetch.start = 0;
ctxt->fetch.end = 0;
@@ -4421,14 +4414,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
int cs_db, cs_l;
- /*
- * TODO: fix emulate.c to use guest_read/write_register
- * instead of direct ->regs accesses, can save hundred cycles
- * on Intel for instructions that don't read/change RSP, for
- * for example.
- */
- cache_all_regs(vcpu);
-
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
ctxt->eflags = kvm_get_rflags(vcpu);
@@ -4440,7 +4425,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
X86EMUL_MODE_PROT16;
ctxt->guest_mode = is_guest_mode(vcpu);
- init_decode_cache(ctxt, vcpu->arch.regs);
+ init_decode_cache(ctxt);
vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
}
@@ -4460,7 +4445,6 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
return EMULATE_FAIL;
ctxt->eip = ctxt->_eip;
- memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
kvm_rip_write(vcpu, ctxt->eip);
kvm_set_rflags(vcpu, ctxt->eflags);
@@ -4493,13 +4477,14 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
{
gpa_t gpa;
+ pfn_t pfn;
if (tdp_enabled)
return false;
/*
* if emulation was due to access to shadowed page table
- * and it failed try to unshadow page and re-entetr the
+ * and it failed try to unshadow page and re-enter the
* guest to let CPU execute the instruction.
*/
if (kvm_mmu_unprotect_page_virt(vcpu, gva))
@@ -4510,8 +4495,17 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
if (gpa == UNMAPPED_GVA)
return true; /* let cpu generate fault */
- if (!kvm_is_error_hva(gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT)))
+ /*
+ * Do not retry the unhandleable instruction if it faults on the
+ * readonly host memory, otherwise it will goto a infinite loop:
+ * retry instruction -> write #PF -> emulation fail -> retry
+ * instruction -> ...
+ */
+ pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
+ if (!is_error_pfn(pfn)) {
+ kvm_release_pfn_clean(pfn);
return true;
+ }
return false;
}
@@ -4560,6 +4554,9 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
return true;
}
+static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
+static int complete_emulated_pio(struct kvm_vcpu *vcpu);
+
int x86_emulate_instruction(struct kvm_vcpu *vcpu,
unsigned long cr2,
int emulation_type,
@@ -4608,7 +4605,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
changes registers values during IO operation */
if (vcpu->arch.emulate_regs_need_sync_from_vcpu) {
vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
- memcpy(ctxt->regs, vcpu->arch.regs, sizeof ctxt->regs);
+ emulator_invalidate_register_cache(ctxt);
}
restart:
@@ -4630,13 +4627,16 @@ restart:
} else if (vcpu->arch.pio.count) {
if (!vcpu->arch.pio.in)
vcpu->arch.pio.count = 0;
- else
+ else {
writeback = false;
+ vcpu->arch.complete_userspace_io = complete_emulated_pio;
+ }
r = EMULATE_DO_MMIO;
} else if (vcpu->mmio_needed) {
if (!vcpu->mmio_is_write)
writeback = false;
r = EMULATE_DO_MMIO;
+ vcpu->arch.complete_userspace_io = complete_emulated_mmio;
} else if (r == EMULATION_RESTART)
goto restart;
else
@@ -4646,7 +4646,6 @@ restart:
toggle_interruptibility(vcpu, ctxt->interruptibility);
kvm_set_rflags(vcpu, ctxt->eflags);
kvm_make_request(KVM_REQ_EVENT, vcpu);
- memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
kvm_rip_write(vcpu, ctxt->eip);
} else
@@ -4929,6 +4928,7 @@ int kvm_arch_init(void *opaque)
if (cpu_has_xsave)
host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+ kvm_lapic_init();
return 0;
out:
@@ -5113,17 +5113,20 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
!kvm_event_needs_reinjection(vcpu);
}
-static void vapic_enter(struct kvm_vcpu *vcpu)
+static int vapic_enter(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
struct page *page;
if (!apic || !apic->vapic_addr)
- return;
+ return 0;
page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
+ if (is_error_page(page))
+ return -EFAULT;
vcpu->arch.apic->vapic_page = page;
+ return 0;
}
static void vapic_exit(struct kvm_vcpu *vcpu)
@@ -5430,7 +5433,11 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
}
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- vapic_enter(vcpu);
+ r = vapic_enter(vcpu);
+ if (r) {
+ srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
+ return r;
+ }
r = 1;
while (r > 0) {
@@ -5492,6 +5499,24 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
return r;
}
+static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
+{
+ int r;
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+ if (r != EMULATE_DONE)
+ return 0;
+ return 1;
+}
+
+static int complete_emulated_pio(struct kvm_vcpu *vcpu)
+{
+ BUG_ON(!vcpu->arch.pio.count);
+
+ return complete_emulated_io(vcpu);
+}
+
/*
* Implements the following, as a state machine:
*
@@ -5508,47 +5533,37 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
* copy data
* exit
*/
-static int complete_mmio(struct kvm_vcpu *vcpu)
+static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
struct kvm_mmio_fragment *frag;
- int r;
- if (!(vcpu->arch.pio.count || vcpu->mmio_needed))
- return 1;
+ BUG_ON(!vcpu->mmio_needed);
- if (vcpu->mmio_needed) {
- /* Complete previous fragment */
- frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
- if (!vcpu->mmio_is_write)
- memcpy(frag->data, run->mmio.data, frag->len);
- if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
- vcpu->mmio_needed = 0;
- if (vcpu->mmio_is_write)
- return 1;
- vcpu->mmio_read_completed = 1;
- goto done;
- }
- /* Initiate next fragment */
- ++frag;
- run->exit_reason = KVM_EXIT_MMIO;
- run->mmio.phys_addr = frag->gpa;
+ /* Complete previous fragment */
+ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
+ if (!vcpu->mmio_is_write)
+ memcpy(frag->data, run->mmio.data, frag->len);
+ if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+ vcpu->mmio_needed = 0;
if (vcpu->mmio_is_write)
- memcpy(run->mmio.data, frag->data, frag->len);
- run->mmio.len = frag->len;
- run->mmio.is_write = vcpu->mmio_is_write;
- return 0;
-
- }
-done:
- vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
- srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- if (r != EMULATE_DONE)
- return 0;
- return 1;
+ return 1;
+ vcpu->mmio_read_completed = 1;
+ return complete_emulated_io(vcpu);
+ }
+ /* Initiate next fragment */
+ ++frag;
+ run->exit_reason = KVM_EXIT_MMIO;
+ run->mmio.phys_addr = frag->gpa;
+ if (vcpu->mmio_is_write)
+ memcpy(run->mmio.data, frag->data, frag->len);
+ run->mmio.len = frag->len;
+ run->mmio.is_write = vcpu->mmio_is_write;
+ vcpu->arch.complete_userspace_io = complete_emulated_mmio;
+ return 0;
}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
int r;
@@ -5575,9 +5590,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
}
}
- r = complete_mmio(vcpu);
- if (r <= 0)
- goto out;
+ if (unlikely(vcpu->arch.complete_userspace_io)) {
+ int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
+ vcpu->arch.complete_userspace_io = NULL;
+ r = cui(vcpu);
+ if (r <= 0)
+ goto out;
+ } else
+ WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
r = __vcpu_run(vcpu);
@@ -5595,12 +5615,11 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
/*
* We are here if userspace calls get_regs() in the middle of
* instruction emulation. Registers state needs to be copied
- * back from emulation context to vcpu. Usrapace shouldn't do
+ * back from emulation context to vcpu. Userspace shouldn't do
* that usually, but some bad designed PV devices (vmware
* backdoor interface) need this to work
*/
- struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
- memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
+ emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
}
regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
@@ -5740,7 +5759,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
if (ret)
return EMULATE_FAIL;
- memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
kvm_rip_write(vcpu, ctxt->eip);
kvm_set_rflags(vcpu, ctxt->eflags);
kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -5792,7 +5810,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
if (mmu_reset_needed)
kvm_mmu_reset_context(vcpu);
- max_bits = (sizeof sregs->interrupt_bitmap) << 3;
+ max_bits = KVM_NR_INTERRUPTS;
pending_vec = find_first_bit(
(const unsigned long *)sregs->interrupt_bitmap, max_bits);
if (pending_vec < max_bits) {
@@ -5852,13 +5870,12 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
for (i = 0; i < KVM_NR_DB_REGS; ++i)
vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
- vcpu->arch.switch_db_regs =
- (dbg->arch.debugreg[7] & DR7_BP_EN_MASK);
+ vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7];
} else {
for (i = 0; i < KVM_NR_DB_REGS; i++)
vcpu->arch.eff_db[i] = vcpu->arch.db[i];
- vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
}
+ kvm_update_dr7(vcpu);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
@@ -5870,7 +5887,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
*/
kvm_set_rflags(vcpu, rflags);
- kvm_x86_ops->set_guest_debug(vcpu, dbg);
+ kvm_x86_ops->update_db_bp_intercept(vcpu);
r = 0;
@@ -5972,7 +5989,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
*/
kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
- unlazy_fpu(current);
+ __kernel_fpu_begin();
fpu_restore_checking(&vcpu->arch.guest_fpu);
trace_kvm_fpu(1);
}
@@ -5986,6 +6003,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
vcpu->guest_fpu_loaded = 0;
fpu_save_init(&vcpu->arch.guest_fpu);
+ __kernel_fpu_end();
++vcpu->stat.fpu_reload;
kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
trace_kvm_fpu(0);
@@ -6015,7 +6033,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
int r;
vcpu->arch.mtrr_state.have_fixed = 1;
- vcpu_load(vcpu);
+ r = vcpu_load(vcpu);
+ if (r)
+ return r;
r = kvm_arch_vcpu_reset(vcpu);
if (r == 0)
r = kvm_mmu_setup(vcpu);
@@ -6026,9 +6046,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
+ int r;
vcpu->arch.apf.msr_val = 0;
- vcpu_load(vcpu);
+ r = vcpu_load(vcpu);
+ BUG_ON(r);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
@@ -6042,10 +6064,10 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
- vcpu->arch.switch_db_regs = 0;
memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
vcpu->arch.dr6 = DR6_FIXED_1;
vcpu->arch.dr7 = DR7_FIXED_1;
+ kvm_update_dr7(vcpu);
kvm_make_request(KVM_REQ_EVENT, vcpu);
vcpu->arch.apf.msr_val = 0;
@@ -6124,7 +6146,7 @@ int kvm_arch_hardware_enable(void *garbage)
* as we reset last_host_tsc on all VCPUs to stop this from being
* called multiple times (one for each physical CPU bringup).
*
- * Platforms with unnreliable TSCs don't have to deal with this, they
+ * Platforms with unreliable TSCs don't have to deal with this, they
* will be compensated by the logic in vcpu_load, which sets the TSC to
* catchup mode. This will catchup all VCPUs to real time, but cannot
* guarantee that they stay in perfect synchronization.
@@ -6177,6 +6199,8 @@ bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
}
+struct static_key kvm_no_apic_vcpu __read_mostly;
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
struct page *page;
@@ -6209,7 +6233,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
r = kvm_create_lapic(vcpu);
if (r < 0)
goto fail_mmu_destroy;
- }
+ } else
+ static_key_slow_inc(&kvm_no_apic_vcpu);
vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4,
GFP_KERNEL);
@@ -6249,6 +6274,8 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
kvm_mmu_destroy(vcpu);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
free_page((unsigned long)vcpu->arch.pio_data);
+ if (!irqchip_in_kernel(vcpu->kvm))
+ static_key_slow_dec(&kvm_no_apic_vcpu);
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
@@ -6261,15 +6288,21 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
+ /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */
+ set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+ &kvm->arch.irq_sources_bitmap);
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
+ mutex_init(&kvm->arch.apic_map_lock);
return 0;
}
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
- vcpu_load(vcpu);
+ int r;
+ r = vcpu_load(vcpu);
+ BUG_ON(r);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
}
@@ -6313,6 +6346,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
put_page(kvm->arch.apic_access_page);
if (kvm->arch.ept_identity_pagetable)
put_page(kvm->arch.ept_identity_pagetable);
+ kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
}
void kvm_arch_free_memslot(struct kvm_memory_slot *free,
@@ -6320,10 +6354,18 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
{
int i;
- for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
- if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
- kvm_kvfree(free->arch.lpage_info[i]);
- free->arch.lpage_info[i] = NULL;
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) {
+ kvm_kvfree(free->arch.rmap[i]);
+ free->arch.rmap[i] = NULL;
+ }
+ if (i == 0)
+ continue;
+
+ if (!dont || free->arch.lpage_info[i - 1] !=
+ dont->arch.lpage_info[i - 1]) {
+ kvm_kvfree(free->arch.lpage_info[i - 1]);
+ free->arch.lpage_info[i - 1] = NULL;
}
}
}
@@ -6332,23 +6374,30 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
{
int i;
- for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
unsigned long ugfn;
int lpages;
- int level = i + 2;
+ int level = i + 1;
lpages = gfn_to_index(slot->base_gfn + npages - 1,
slot->base_gfn, level) + 1;
- slot->arch.lpage_info[i] =
- kvm_kvzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
- if (!slot->arch.lpage_info[i])
+ slot->arch.rmap[i] =
+ kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i]));
+ if (!slot->arch.rmap[i])
+ goto out_free;
+ if (i == 0)
+ continue;
+
+ slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
+ sizeof(*slot->arch.lpage_info[i - 1]));
+ if (!slot->arch.lpage_info[i - 1])
goto out_free;
if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i][0].write_count = 1;
+ slot->arch.lpage_info[i - 1][0].write_count = 1;
if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
- slot->arch.lpage_info[i][lpages - 1].write_count = 1;
+ slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
ugfn = slot->userspace_addr >> PAGE_SHIFT;
/*
* If the gfn and userspace address are not aligned wrt each
@@ -6360,16 +6409,21 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
unsigned long j;
for (j = 0; j < lpages; ++j)
- slot->arch.lpage_info[i][j].write_count = 1;
+ slot->arch.lpage_info[i - 1][j].write_count = 1;
}
}
return 0;
out_free:
- for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
- kvm_kvfree(slot->arch.lpage_info[i]);
- slot->arch.lpage_info[i] = NULL;
+ for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
+ kvm_kvfree(slot->arch.rmap[i]);
+ slot->arch.rmap[i] = NULL;
+ if (i == 0)
+ continue;
+
+ kvm_kvfree(slot->arch.lpage_info[i - 1]);
+ slot->arch.lpage_info[i - 1] = NULL;
}
return -ENOMEM;
}
@@ -6388,10 +6442,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
map_flags = MAP_SHARED | MAP_ANONYMOUS;
/*To keep backward compatibility with older userspace,
- *x86 needs to hanlde !user_alloc case.
+ *x86 needs to handle !user_alloc case.
*/
if (!user_alloc) {
- if (npages && !old.rmap) {
+ if (npages && !old.npages) {
unsigned long userspace_addr;
userspace_addr = vm_mmap(NULL, 0,
@@ -6419,7 +6473,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
- if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
+ if (!user_alloc && !old.user_alloc && old.npages && !npages) {
int ret;
ret = vm_munmap(old.userspace_addr,
@@ -6438,14 +6492,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
kvm_mmu_slot_remove_write_access(kvm, mem->slot);
spin_unlock(&kvm->mmu_lock);
+ /*
+ * If memory slot is created, or moved, we need to clear all
+ * mmio sptes.
+ */
+ if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT) {
+ kvm_mmu_zap_all(kvm);
+ kvm_reload_remote_mmus(kvm);
+ }
}
-void kvm_arch_flush_shadow(struct kvm *kvm)
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
kvm_mmu_zap_all(kvm);
kvm_reload_remote_mmus(kvm);
}
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *slot)
+{
+ kvm_arch_flush_shadow_all(kvm);
+}
+
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 3d1134ddb88..2b5219c12ac 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -124,4 +124,5 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
extern u64 host_xcr0;
+extern struct static_key kvm_no_apic_vcpu;
#endif
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 5b2995f4557..a30ca15be21 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -17,6 +17,7 @@
#include <asm/cpufeature.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
+#include <asm/smap.h>
/*
* By placing feature2 after feature1 in altinstructions section, we logically
@@ -130,6 +131,7 @@ ENDPROC(bad_from_user)
*/
ENTRY(copy_user_generic_unrolled)
CFI_STARTPROC
+ ASM_STAC
cmpl $8,%edx
jb 20f /* less then 8 bytes, go to byte copy loop */
ALIGN_DESTINATION
@@ -177,6 +179,7 @@ ENTRY(copy_user_generic_unrolled)
decl %ecx
jnz 21b
23: xor %eax,%eax
+ ASM_CLAC
ret
.section .fixup,"ax"
@@ -232,6 +235,7 @@ ENDPROC(copy_user_generic_unrolled)
*/
ENTRY(copy_user_generic_string)
CFI_STARTPROC
+ ASM_STAC
andl %edx,%edx
jz 4f
cmpl $8,%edx
@@ -246,6 +250,7 @@ ENTRY(copy_user_generic_string)
3: rep
movsb
4: xorl %eax,%eax
+ ASM_CLAC
ret
.section .fixup,"ax"
@@ -273,12 +278,14 @@ ENDPROC(copy_user_generic_string)
*/
ENTRY(copy_user_enhanced_fast_string)
CFI_STARTPROC
+ ASM_STAC
andl %edx,%edx
jz 2f
movl %edx,%ecx
1: rep
movsb
2: xorl %eax,%eax
+ ASM_CLAC
ret
.section .fixup,"ax"
diff --git a/arch/x86/lib/copy_user_nocache_64.S b/arch/x86/lib/copy_user_nocache_64.S
index cacddc7163e..6a4f43c2d9e 100644
--- a/arch/x86/lib/copy_user_nocache_64.S
+++ b/arch/x86/lib/copy_user_nocache_64.S
@@ -15,6 +15,7 @@
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/asm.h>
+#include <asm/smap.h>
.macro ALIGN_DESTINATION
#ifdef FIX_ALIGNMENT
@@ -48,6 +49,7 @@
*/
ENTRY(__copy_user_nocache)
CFI_STARTPROC
+ ASM_STAC
cmpl $8,%edx
jb 20f /* less then 8 bytes, go to byte copy loop */
ALIGN_DESTINATION
@@ -95,6 +97,7 @@ ENTRY(__copy_user_nocache)
decl %ecx
jnz 21b
23: xorl %eax,%eax
+ ASM_CLAC
sfence
ret
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index b33b1fb1e6d..156b9c80467 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -33,6 +33,7 @@
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/asm.h>
+#include <asm/smap.h>
.text
ENTRY(__get_user_1)
@@ -40,8 +41,10 @@ ENTRY(__get_user_1)
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
+ ASM_STAC
1: movzb (%_ASM_AX),%edx
xor %eax,%eax
+ ASM_CLAC
ret
CFI_ENDPROC
ENDPROC(__get_user_1)
@@ -53,8 +56,10 @@ ENTRY(__get_user_2)
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
+ ASM_STAC
2: movzwl -1(%_ASM_AX),%edx
xor %eax,%eax
+ ASM_CLAC
ret
CFI_ENDPROC
ENDPROC(__get_user_2)
@@ -66,8 +71,10 @@ ENTRY(__get_user_4)
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
+ ASM_STAC
3: mov -3(%_ASM_AX),%edx
xor %eax,%eax
+ ASM_CLAC
ret
CFI_ENDPROC
ENDPROC(__get_user_4)
@@ -80,8 +87,10 @@ ENTRY(__get_user_8)
GET_THREAD_INFO(%_ASM_DX)
cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
jae bad_get_user
+ ASM_STAC
4: movq -7(%_ASM_AX),%_ASM_DX
xor %eax,%eax
+ ASM_CLAC
ret
CFI_ENDPROC
ENDPROC(__get_user_8)
@@ -91,6 +100,7 @@ bad_get_user:
CFI_STARTPROC
xor %edx,%edx
mov $(-EFAULT),%_ASM_AX
+ ASM_CLAC
ret
CFI_ENDPROC
END(bad_get_user)
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index b1e6c4b2e8e..54fcffed28e 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -18,7 +18,11 @@
* Copyright (C) IBM Corporation, 2002, 2004, 2009
*/
+#ifdef __KERNEL__
#include <linux/string.h>
+#else
+#include <string.h>
+#endif
#include <asm/inat.h>
#include <asm/insn.h>
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 7f951c8f76c..fc6ba17a7ee 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -15,6 +15,7 @@
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
+#include <asm/smap.h>
/*
@@ -31,7 +32,8 @@
#define ENTER CFI_STARTPROC ; \
GET_THREAD_INFO(%_ASM_BX)
-#define EXIT ret ; \
+#define EXIT ASM_CLAC ; \
+ ret ; \
CFI_ENDPROC
.text
@@ -39,6 +41,7 @@ ENTRY(__put_user_1)
ENTER
cmp TI_addr_limit(%_ASM_BX),%_ASM_CX
jae bad_put_user
+ ASM_STAC
1: movb %al,(%_ASM_CX)
xor %eax,%eax
EXIT
@@ -50,6 +53,7 @@ ENTRY(__put_user_2)
sub $1,%_ASM_BX
cmp %_ASM_BX,%_ASM_CX
jae bad_put_user
+ ASM_STAC
2: movw %ax,(%_ASM_CX)
xor %eax,%eax
EXIT
@@ -61,6 +65,7 @@ ENTRY(__put_user_4)
sub $3,%_ASM_BX
cmp %_ASM_BX,%_ASM_CX
jae bad_put_user
+ ASM_STAC
3: movl %eax,(%_ASM_CX)
xor %eax,%eax
EXIT
@@ -72,6 +77,7 @@ ENTRY(__put_user_8)
sub $7,%_ASM_BX
cmp %_ASM_BX,%_ASM_CX
jae bad_put_user
+ ASM_STAC
4: mov %_ASM_AX,(%_ASM_CX)
#ifdef CONFIG_X86_32
5: movl %edx,4(%_ASM_CX)
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 1781b2f950e..98f6d6b68f5 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -42,10 +42,11 @@ do { \
int __d0; \
might_fault(); \
__asm__ __volatile__( \
+ ASM_STAC "\n" \
"0: rep; stosl\n" \
" movl %2,%0\n" \
"1: rep; stosb\n" \
- "2:\n" \
+ "2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"3: lea 0(%2,%0,4),%0\n" \
" jmp 2b\n" \
@@ -626,10 +627,12 @@ survive:
return n;
}
#endif
+ stac();
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel(to, from, n);
+ clac();
return n;
}
EXPORT_SYMBOL(__copy_to_user_ll);
@@ -637,10 +640,12 @@ EXPORT_SYMBOL(__copy_to_user_ll);
unsigned long __copy_from_user_ll(void *to, const void __user *from,
unsigned long n)
{
+ stac();
if (movsl_is_ok(to, from, n))
__copy_user_zeroing(to, from, n);
else
n = __copy_user_zeroing_intel(to, from, n);
+ clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll);
@@ -648,11 +653,13 @@ EXPORT_SYMBOL(__copy_from_user_ll);
unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
unsigned long n)
{
+ stac();
if (movsl_is_ok(to, from, n))
__copy_user(to, from, n);
else
n = __copy_user_intel((void __user *)to,
(const void *)from, n);
+ clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nozero);
@@ -660,6 +667,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero);
unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
unsigned long n)
{
+ stac();
#ifdef CONFIG_X86_INTEL_USERCOPY
if (n > 64 && cpu_has_xmm2)
n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -668,6 +676,7 @@ unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
#else
__copy_user_zeroing(to, from, n);
#endif
+ clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nocache);
@@ -675,6 +684,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache);
unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
unsigned long n)
{
+ stac();
#ifdef CONFIG_X86_INTEL_USERCOPY
if (n > 64 && cpu_has_xmm2)
n = __copy_user_intel_nocache(to, from, n);
@@ -683,6 +693,7 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr
#else
__copy_user(to, from, n);
#endif
+ clac();
return n;
}
EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e5b130bc2d0..05928aae911 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -18,6 +18,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
might_fault();
/* no memory constraint because it doesn't change any memory gcc knows
about */
+ stac();
asm volatile(
" testq %[size8],%[size8]\n"
" jz 4f\n"
@@ -40,6 +41,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
: [size8] "=&c"(size), [dst] "=&D" (__d0)
: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr),
[zero] "r" (0UL), [eight] "r" (8UL));
+ clac();
return size;
}
EXPORT_SYMBOL(__clear_user);
@@ -82,5 +84,6 @@ copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
for (c = 0, zero_len = len; zerorest && zero_len; --zero_len)
if (__put_user_nocheck(c, to++, sizeof(char)))
break;
+ clac();
return len;
}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 76dcd9d8e0b..a530b230e7d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -18,6 +18,7 @@
#include <asm/pgalloc.h> /* pgd_*(), ... */
#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
#include <asm/fixmap.h> /* VSYSCALL_START */
+#include <asm/rcu.h> /* exception_enter(), ... */
/*
* Page fault error code bits:
@@ -995,13 +996,24 @@ static int fault_in_kernel_space(unsigned long address)
return address >= TASK_SIZE_MAX;
}
+static inline bool smap_violation(int error_code, struct pt_regs *regs)
+{
+ if (error_code & PF_USER)
+ return false;
+
+ if (!user_mode_vm(regs) && (regs->flags & X86_EFLAGS_AC))
+ return false;
+
+ return true;
+}
+
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
-dotraplinkage void __kprobes
-do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes
+__do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
@@ -1088,6 +1100,13 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
+ if (static_cpu_has(X86_FEATURE_SMAP)) {
+ if (unlikely(smap_violation(error_code, regs))) {
+ bad_area_nosemaphore(regs, error_code, address);
+ return;
+ }
+ }
+
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
/*
@@ -1209,3 +1228,11 @@ good_area:
up_read(&mm->mmap_sem);
}
+
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
+{
+ exception_enter(regs);
+ __do_page_fault(regs, error_code);
+ exception_exit(regs);
+}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index e0e6990723e..ab1f6a93b52 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -319,7 +319,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
*/
int devmem_is_allowed(unsigned long pagenr)
{
- if (pagenr <= 256)
+ if (pagenr < 256)
return 1;
if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
return 0;
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 575d86f85ce..11a58001b4c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -445,10 +445,10 @@ static inline void permanent_kmaps_init(pgd_t *pgd_base)
}
#endif /* CONFIG_HIGHMEM */
-void __init native_pagetable_setup_start(pgd_t *base)
+void __init native_pagetable_init(void)
{
unsigned long pfn, va;
- pgd_t *pgd;
+ pgd_t *pgd, *base = swapper_pg_dir;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -475,10 +475,7 @@ void __init native_pagetable_setup_start(pgd_t *base)
pte_clear(NULL, va, pte);
}
paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
-}
-
-void __init native_pagetable_setup_done(pgd_t *base)
-{
+ paging_init();
}
/*
@@ -493,7 +490,7 @@ void __init native_pagetable_setup_done(pgd_t *base)
* If we're booting paravirtualized under a hypervisor, then there are
* more options: we may already be running PAE, and the pagetable may
* or may not be based in swapper_pg_dir. In any case,
- * paravirt_pagetable_setup_start() will set up swapper_pg_dir
+ * paravirt_pagetable_init() will set up swapper_pg_dir
* appropriately for the rest of the initialization to work.
*
* In general, pagetable_init() assumes that the pagetable may already
@@ -712,7 +709,7 @@ static void __init test_wp_bit(void)
"Checking if this processor honours the WP bit even in supervisor mode...");
/* Any page-aligned address will do, the test is non-destructive */
- __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
+ __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_KERNEL_RO);
boot_cpu_data.wp_works_ok = do_test_wp_bit();
clear_fixmap(FIX_WP_TEST);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 613cd83e8c0..0777f042e40 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -98,6 +98,8 @@ static void flush_tlb_func(void *info)
{
struct flush_tlb_info *f = info;
+ inc_irq_stat(irq_tlb_count);
+
if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
return;
@@ -320,7 +322,7 @@ static ssize_t tlbflush_write_file(struct file *file,
if (kstrtos8(buf, 0, &shift))
return -EINVAL;
- if (shift > 64)
+ if (shift < -1 || shift >= BITS_PER_LONG)
return -EINVAL;
tlb_flushall_shift = shift;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 33643a8bcbb..520d2bd0b9c 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -280,6 +280,31 @@ void bpf_jit_compile(struct sk_filter *fp)
}
EMIT4(0x31, 0xd2, 0xf7, 0xf3); /* xor %edx,%edx; div %ebx */
break;
+ case BPF_S_ALU_MOD_X: /* A %= X; */
+ seen |= SEEN_XREG;
+ EMIT2(0x85, 0xdb); /* test %ebx,%ebx */
+ if (pc_ret0 > 0) {
+ /* addrs[pc_ret0 - 1] is start address of target
+ * (addrs[i] - 6) is the address following this jmp
+ * ("xor %edx,%edx; div %ebx;mov %edx,%eax" being 6 bytes long)
+ */
+ EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
+ (addrs[i] - 6));
+ } else {
+ EMIT_COND_JMP(X86_JNE, 2 + 5);
+ CLEAR_A();
+ EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 6)); /* jmp .+off32 */
+ }
+ EMIT2(0x31, 0xd2); /* xor %edx,%edx */
+ EMIT2(0xf7, 0xf3); /* div %ebx */
+ EMIT2(0x89, 0xd0); /* mov %edx,%eax */
+ break;
+ case BPF_S_ALU_MOD_K: /* A %= K; */
+ EMIT2(0x31, 0xd2); /* xor %edx,%edx */
+ EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */
+ EMIT2(0xf7, 0xf1); /* div %ecx */
+ EMIT2(0x89, 0xd0); /* mov %edx,%eax */
+ break;
case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */
EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */
EMIT(K, 4);
@@ -310,9 +335,18 @@ void bpf_jit_compile(struct sk_filter *fp)
EMIT1_off32(0x0d, K); /* or imm32,%eax */
break;
case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */
+ case BPF_S_ALU_XOR_X:
seen |= SEEN_XREG;
EMIT2(0x31, 0xd8); /* xor %ebx,%eax */
break;
+ case BPF_S_ALU_XOR_K: /* A ^= K; */
+ if (K == 0)
+ break;
+ if (is_imm8(K))
+ EMIT3(0x83, 0xf0, K); /* xor imm8,%eax */
+ else
+ EMIT1_off32(0x35, K); /* xor imm32,%eax */
+ break;
case BPF_S_ALU_LSH_X: /* A <<= X; */
seen |= SEEN_XREG;
EMIT4(0x89, 0xd9, 0xd3, 0xe0); /* mov %ebx,%ecx; shl %cl,%eax */
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 505acdd6d60..192397c9860 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -305,7 +305,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
res->flags = flags;
res->start = start;
res->end = end;
- res->child = NULL;
if (!pci_use_crs) {
dev_printk(KERN_DEBUG, &info->bridge->dev,
@@ -434,7 +433,7 @@ probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device,
size = sizeof(*info->res) * info->res_num;
info->res_num = 0;
- info->res = kmalloc(size, GFP_KERNEL);
+ info->res = kzalloc(size, GFP_KERNEL);
if (!info->res)
return;
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 937bcece700..704b9ec043d 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -585,7 +585,7 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header)
while (i >= sizeof(struct acpi_mcfg_allocation)) {
entries++;
i -= sizeof(struct acpi_mcfg_allocation);
- };
+ }
if (entries == 0) {
pr_err(PREFIX "MMCONFIG has no entries\n");
return -ENODEV;
diff --git a/arch/x86/pci/visws.c b/arch/x86/pci/visws.c
index 6f2f8eeed17..3e6d2a6db86 100644
--- a/arch/x86/pci/visws.c
+++ b/arch/x86/pci/visws.c
@@ -62,11 +62,6 @@ out:
return irq;
}
-void __init pcibios_update_irq(struct pci_dev *dev, int irq)
-{
- pci_write_config_byte(dev, PCI_INTERRUPT_LINE, irq);
-}
-
int __init pci_visws_init(void)
{
pcibios_enable_irq = &pci_visws_enable_irq;
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index 73b8be0f367..6db1cc4c753 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1 +1,2 @@
obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o
+obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
new file mode 100644
index 00000000000..f6a0c1b8e51
--- /dev/null
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2012 Intel Corporation
+ * Author: Josh Triplett <josh@joshtriplett.org>
+ *
+ * Based on the bgrt driver:
+ * Copyright 2012 Red Hat, Inc <mjg@redhat.com>
+ * Author: Matthew Garrett
+ *
+ * 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/kernel.h>
+#include <linux/acpi.h>
+#include <linux/efi.h>
+#include <linux/efi-bgrt.h>
+
+struct acpi_table_bgrt *bgrt_tab;
+void *bgrt_image;
+size_t bgrt_image_size;
+
+struct bmp_header {
+ u16 id;
+ u32 size;
+} __packed;
+
+void efi_bgrt_init(void)
+{
+ acpi_status status;
+ void __iomem *image;
+ bool ioremapped = false;
+ struct bmp_header bmp_header;
+
+ if (acpi_disabled)
+ return;
+
+ status = acpi_get_table("BGRT", 0,
+ (struct acpi_table_header **)&bgrt_tab);
+ if (ACPI_FAILURE(status))
+ return;
+
+ if (bgrt_tab->version != 1)
+ return;
+ if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
+ return;
+
+ image = efi_lookup_mapped_addr(bgrt_tab->image_address);
+ if (!image) {
+ image = ioremap(bgrt_tab->image_address, sizeof(bmp_header));
+ ioremapped = true;
+ if (!image)
+ return;
+ }
+
+ memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
+ if (ioremapped)
+ iounmap(image);
+ bgrt_image_size = bmp_header.size;
+
+ bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL);
+ if (!bgrt_image)
+ return;
+
+ if (ioremapped) {
+ image = ioremap(bgrt_tab->image_address, bmp_header.size);
+ if (!image) {
+ kfree(bgrt_image);
+ bgrt_image = NULL;
+ return;
+ }
+ }
+
+ memcpy_fromio(bgrt_image, image, bgrt_image_size);
+ if (ioremapped)
+ iounmap(image);
+}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 92660edaa1e..aded2a91162 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -31,6 +31,7 @@
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/efi.h>
+#include <linux/efi-bgrt.h>
#include <linux/export.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
@@ -419,10 +420,21 @@ void __init efi_reserve_boot_services(void)
}
}
-static void __init efi_free_boot_services(void)
+static void __init efi_unmap_memmap(void)
+{
+ if (memmap.map) {
+ early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
+ memmap.map = NULL;
+ }
+}
+
+void __init efi_free_boot_services(void)
{
void *p;
+ if (!efi_native)
+ return;
+
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
efi_memory_desc_t *md = p;
unsigned long long start = md->phys_addr;
@@ -438,6 +450,8 @@ static void __init efi_free_boot_services(void)
free_bootmem_late(start, size);
}
+
+ efi_unmap_memmap();
}
static int __init efi_systab_init(void *phys)
@@ -732,6 +746,11 @@ void __init efi_init(void)
#endif
}
+void __init efi_late_init(void)
+{
+ efi_bgrt_init();
+}
+
void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
{
u64 addr, npages;
@@ -764,6 +783,34 @@ static void __init runtime_code_page_mkexec(void)
}
/*
+ * We can't ioremap data in EFI boot services RAM, because we've already mapped
+ * it as RAM. So, look it up in the existing EFI memory map instead. Only
+ * callable after efi_enter_virtual_mode and before efi_free_boot_services.
+ */
+void __iomem *efi_lookup_mapped_addr(u64 phys_addr)
+{
+ void *p;
+ if (WARN_ON(!memmap.map))
+ return NULL;
+ for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+ efi_memory_desc_t *md = p;
+ u64 size = md->num_pages << EFI_PAGE_SHIFT;
+ u64 end = md->phys_addr + size;
+ if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+ md->type != EFI_BOOT_SERVICES_CODE &&
+ md->type != EFI_BOOT_SERVICES_DATA)
+ continue;
+ if (!md->virt_addr)
+ continue;
+ if (phys_addr >= md->phys_addr && phys_addr < end) {
+ phys_addr += md->virt_addr - md->phys_addr;
+ return (__force void __iomem *)(unsigned long)phys_addr;
+ }
+ }
+ return NULL;
+}
+
+/*
* This function will switch the EFI runtime services to virtual mode.
* Essentially, look through the EFI memmap and map every region that
* has the runtime attribute bit set in its memory descriptor and update
@@ -787,8 +834,10 @@ void __init efi_enter_virtual_mode(void)
* non-native EFI
*/
- if (!efi_native)
- goto out;
+ if (!efi_native) {
+ efi_unmap_memmap();
+ return;
+ }
/* Merge contiguous regions of the same type and attribute */
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
@@ -878,18 +927,12 @@ void __init efi_enter_virtual_mode(void)
}
/*
- * Thankfully, it does seem that no runtime services other than
- * SetVirtualAddressMap() will touch boot services code, so we can
- * get rid of it all at this point
- */
- efi_free_boot_services();
-
- /*
* Now that EFI is in virtual mode, update the function
* pointers in the runtime service table to the new virtual addresses.
*
* Call EFI services through wrapper functions.
*/
+ efi.runtime_version = efi_systab.fw_revision;
efi.get_time = virt_efi_get_time;
efi.set_time = virt_efi_set_time;
efi.get_wakeup_time = virt_efi_get_wakeup_time;
@@ -906,9 +949,6 @@ void __init efi_enter_virtual_mode(void)
if (__supported_pte_mask & _PAGE_NX)
runtime_code_page_mkexec();
-out:
- early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
- memmap.map = NULL;
kfree(new_memmap);
}
diff --git a/arch/x86/realmode/rm/wakeup.h b/arch/x86/realmode/rm/wakeup.h
index 9317e0042f2..7dd86a419f5 100644
--- a/arch/x86/realmode/rm/wakeup.h
+++ b/arch/x86/realmode/rm/wakeup.h
@@ -36,5 +36,7 @@ extern struct wakeup_header wakeup_header;
/* Wakeup behavior bits */
#define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE 0
+#define WAKEUP_BEHAVIOR_RESTORE_CR4 1
+#define WAKEUP_BEHAVIOR_RESTORE_EFER 2
#endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */
diff --git a/arch/x86/realmode/rm/wakeup_asm.S b/arch/x86/realmode/rm/wakeup_asm.S
index 8905166b0bb..e56479e5805 100644
--- a/arch/x86/realmode/rm/wakeup_asm.S
+++ b/arch/x86/realmode/rm/wakeup_asm.S
@@ -74,9 +74,18 @@ ENTRY(wakeup_start)
lidtl wakeup_idt
- /* Clear the EFLAGS */
- pushl $0
+ /* Clear the EFLAGS but remember if we have EFLAGS.ID */
+ movl $X86_EFLAGS_ID, %ecx
+ pushl %ecx
popfl
+ pushfl
+ popl %edi
+ pushl $0
+ popfl
+ pushfl
+ popl %edx
+ xorl %edx, %edi
+ andl %ecx, %edi /* %edi is zero iff CPUID & %cr4 are missing */
/* Check header signature... */
movl signature, %eax
@@ -93,8 +102,8 @@ ENTRY(wakeup_start)
/* Restore MISC_ENABLE before entering protected mode, in case
BIOS decided to clear XD_DISABLE during S3. */
- movl pmode_behavior, %eax
- btl $WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %eax
+ movl pmode_behavior, %edi
+ btl $WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %edi
jnc 1f
movl pmode_misc_en, %eax
@@ -110,15 +119,15 @@ ENTRY(wakeup_start)
movl pmode_cr3, %eax
movl %eax, %cr3
- movl pmode_cr4, %ecx
- jecxz 1f
- movl %ecx, %cr4
+ btl $WAKEUP_BEHAVIOR_RESTORE_CR4, %edi
+ jz 1f
+ movl pmode_cr4, %eax
+ movl %eax, %cr4
1:
+ btl $WAKEUP_BEHAVIOR_RESTORE_EFER, %edi
+ jz 1f
movl pmode_efer, %eax
movl pmode_efer + 4, %edx
- movl %eax, %ecx
- orl %edx, %ecx
- jz 1f
movl $MSR_EFER, %ecx
wrmsr
1:
diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile
index 3236aebc828..f325af26107 100644
--- a/arch/x86/syscalls/Makefile
+++ b/arch/x86/syscalls/Makefile
@@ -1,7 +1,9 @@
out := $(obj)/../include/generated/asm
+uapi := $(obj)/../include/generated/uapi/asm
# Create output directory if not already present
-_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
+ $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)')
syscall32 := $(srctree)/$(src)/syscall_32.tbl
syscall64 := $(srctree)/$(src)/syscall_64.tbl
@@ -18,7 +20,7 @@ quiet_cmd_systbl = SYSTBL $@
cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
syshdr_abi_unistd_32 := i386
-$(out)/unistd_32.h: $(syscall32) $(syshdr)
+$(uapi)/unistd_32.h: $(syscall32) $(syshdr)
$(call if_changed,syshdr)
syshdr_abi_unistd_32_ia32 := i386
@@ -28,11 +30,11 @@ $(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
syshdr_abi_unistd_x32 := common,x32
syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
-$(out)/unistd_x32.h: $(syscall64) $(syshdr)
+$(uapi)/unistd_x32.h: $(syscall64) $(syshdr)
$(call if_changed,syshdr)
syshdr_abi_unistd_64 := common,64
-$(out)/unistd_64.h: $(syscall64) $(syshdr)
+$(uapi)/unistd_64.h: $(syscall64) $(syshdr)
$(call if_changed,syshdr)
syshdr_abi_unistd_64_x32 := x32
@@ -45,11 +47,12 @@ $(out)/syscalls_32.h: $(syscall32) $(systbl)
$(out)/syscalls_64.h: $(syscall64) $(systbl)
$(call if_changed,systbl)
-syshdr-y += unistd_32.h unistd_64.h unistd_x32.h
+uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h
syshdr-y += syscalls_32.h
syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h
syshdr-$(CONFIG_X86_64) += syscalls_64.h
-targets += $(syshdr-y)
+targets += $(uapisyshdr-y) $(syshdr-y)
-all: $(addprefix $(out)/,$(targets))
+all: $(addprefix $(uapi)/,$(uapisyshdr-y))
+all: $(addprefix $(out)/,$(syshdr-y))
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index 733057b435b..bae601f900e 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -28,7 +28,7 @@ posttest: $(obj)/test_get_len vmlinux $(obj)/insn_sanity
hostprogs-y += test_get_len insn_sanity
# -I needed for generated C source and C source which in the kernel tree.
-HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
+HOSTCFLAGS_test_get_len.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/uapi/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/uapi/
HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x86/include/ -I$(srctree)/arch/x86/lib/ -I$(srctree)/include/
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 9926e11a772..aeaff8bef2f 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -21,6 +21,7 @@ config 64BIT
config X86_32
def_bool !64BIT
select HAVE_AOUT
+ select ARCH_WANT_IPC_PARSE_VERSION
config X86_64
def_bool 64BIT
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index 5868526b5ee..46a9df99f3c 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -7,9 +7,6 @@
#define DEFINE(sym, val) \
asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-#define STR(x) #x
-#define DEFINE_STR(sym, val) asm volatile("\n->" #sym " " STR(val) " " #val: : )
-
#define BLANK() asm volatile("\n->" : : )
#define OFFSET(sym, str, mem) \
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
index bd9a89b67e4..ca255a805ed 100644
--- a/arch/x86/um/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -1,3 +1,5 @@
+extern long sys_clone(unsigned long clone_flags, unsigned long newsp,
+ void __user *parent_tid, void __user *child_tid);
#ifdef __i386__
#include "syscalls_32.h"
#else
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index a508cea1350..ba7363ecf89 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -416,9 +416,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
PT_REGS_AX(regs) = (unsigned long) sig;
PT_REGS_DX(regs) = (unsigned long) 0;
PT_REGS_CX(regs) = (unsigned long) 0;
-
- if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
- ptrace_notify(SIGTRAP);
return 0;
}
@@ -466,9 +463,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
PT_REGS_AX(regs) = (unsigned long) sig;
PT_REGS_DX(regs) = (unsigned long) &frame->info;
PT_REGS_CX(regs) = (unsigned long) &frame->uc;
-
- if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
- ptrace_notify(SIGTRAP);
return 0;
}
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 68d1dc91b37..b5408cecac6 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -28,7 +28,7 @@
#define ptregs_execve sys_execve
#define ptregs_iopl sys_iopl
#define ptregs_vm86old sys_vm86old
-#define ptregs_clone sys_clone
+#define ptregs_clone i386_clone
#define ptregs_vm86 sys_vm86
#define ptregs_sigaltstack sys_sigaltstack
#define ptregs_vfork sys_vfork
diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c
index b853e8600b9..db444c7218f 100644
--- a/arch/x86/um/syscalls_32.c
+++ b/arch/x86/um/syscalls_32.c
@@ -3,37 +3,24 @@
* Licensed under the GPL
*/
-#include "linux/sched.h"
-#include "linux/shm.h"
-#include "linux/ipc.h"
-#include "linux/syscalls.h"
-#include "asm/mman.h"
-#include "asm/uaccess.h"
-#include "asm/unistd.h"
+#include <linux/syscalls.h>
+#include <sysdep/syscalls.h>
/*
* The prototype on i386 is:
*
- * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls, int * child_tidptr)
+ * int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls
*
* and the "newtls" arg. on i386 is read by copy_thread directly from the
* register saved on the stack.
*/
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
- int __user *parent_tid, void *newtls, int __user *child_tid)
+long i386_clone(unsigned long clone_flags, unsigned long newsp,
+ int __user *parent_tid, void *newtls, int __user *child_tid)
{
- long ret;
-
- if (!newsp)
- newsp = UPT_SP(&current->thread.regs.regs);
-
- current->thread.forking = 1;
- ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
- child_tid);
- current->thread.forking = 0;
- return ret;
+ return sys_clone(clone_flags, newsp, parent_tid, child_tid);
}
+
long sys_sigaction(int sig, const struct old_sigaction __user *act,
struct old_sigaction __user *oact)
{
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index f3d82bb6e15..adb08eb5c22 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -5,12 +5,9 @@
* Licensed under the GPL
*/
-#include "linux/linkage.h"
-#include "linux/personality.h"
-#include "linux/utsname.h"
-#include "asm/prctl.h" /* XXX This should get the constants from libc */
-#include "asm/uaccess.h"
-#include "os.h"
+#include <linux/sched.h>
+#include <asm/prctl.h> /* XXX This should get the constants from libc */
+#include <os.h>
long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
{
@@ -79,20 +76,6 @@ long sys_arch_prctl(int code, unsigned long addr)
return arch_prctl(current, code, (unsigned long __user *) addr);
}
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
- void __user *parent_tid, void __user *child_tid)
-{
- long ret;
-
- if (!newsp)
- newsp = UPT_SP(&current->thread.regs.regs);
- current->thread.forking = 1;
- ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
- child_tid);
- current->thread.forking = 0;
- return ret;
-}
-
void arch_switch_to(struct task_struct *to)
{
if ((to->thread.arch.fs == 0) || (to->mm == NULL))
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index ec57bd3818a..7005ced5d1a 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -6,8 +6,9 @@
#include <xen/xen.h>
#include <xen/interface/physdev.h>
+#include "xen-ops.h"
-unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
+static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
{
struct physdev_apic apic_op;
int ret;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 9642d4a3860..bf788d34530 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,7 @@
#include <linux/memblock.h>
#include <xen/xen.h>
+#include <xen/events.h>
#include <xen/interface/xen.h>
#include <xen/interface/version.h>
#include <xen/interface/physdev.h>
@@ -80,6 +81,8 @@
#include "smp.h"
#include "multicalls.h"
+#include <xen/events.h>
+
EXPORT_SYMBOL_GPL(hypercall_page);
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
@@ -1288,7 +1291,6 @@ asmlinkage void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
int rc;
- pgd_t *pgd;
if (!xen_start_info)
return;
@@ -1380,8 +1382,6 @@ asmlinkage void __init xen_start_kernel(void)
acpi_numa = -1;
#endif
- pgd = (pgd_t *)xen_start_info->pt_base;
-
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
@@ -1390,7 +1390,7 @@ asmlinkage void __init xen_start_kernel(void)
early_boot_irqs_disabled = true;
xen_raw_console_write("mapping kernel into physical memory\n");
- pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
+ xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
/* Allocate and initialize top and mid mfn levels for p2m structure */
xen_build_mfn_list_list();
@@ -1441,17 +1441,29 @@ asmlinkage void __init xen_start_kernel(void)
const struct dom0_vga_console_info *info =
(void *)((char *)xen_start_info +
xen_start_info->console.dom0.info_off);
+ struct xen_platform_op op = {
+ .cmd = XENPF_firmware_info,
+ .interface_version = XENPF_INTERFACE_VERSION,
+ .u.firmware_info.type = XEN_FW_KBD_SHIFT_FLAGS,
+ };
xen_init_vga(info, xen_start_info->console.dom0.info_size);
xen_start_info->console.domU.mfn = 0;
xen_start_info->console.domU.evtchn = 0;
+ if (HYPERVISOR_dom0_op(&op) == 0)
+ boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags;
+
xen_init_apic();
/* Make sure ACS will be enabled */
pci_request_acs();
xen_acpi_sleep_register();
+
+ /* Avoid searching for BIOS MP tables */
+ x86_init.mpparse.find_smp_config = x86_init_noop;
+ x86_init.mpparse.get_smp_config = x86_init_uint_noop;
}
#ifdef CONFIG_PCI
/* PCI BIOS service won't work from a PV guest. */
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 15733765797..01a4dc015ae 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -5,6 +5,7 @@
#include <xen/interface/xen.h>
#include <xen/interface/sched.h>
#include <xen/interface/vcpu.h>
+#include <xen/events.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index b65a76133f4..5a16824cc2b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -84,6 +84,7 @@
*/
DEFINE_SPINLOCK(xen_reservation_lock);
+#ifdef CONFIG_X86_32
/*
* Identity map, in addition to plain kernel map. This needs to be
* large enough to allocate page table pages to allocate the rest.
@@ -91,7 +92,7 @@ DEFINE_SPINLOCK(xen_reservation_lock);
*/
#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4)
static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES);
-
+#endif
#ifdef CONFIG_X86_64
/* l3 pud for userspace vsyscall mapping */
static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
@@ -1174,9 +1175,7 @@ static void xen_exit_mmap(struct mm_struct *mm)
spin_unlock(&mm->page_table_lock);
}
-static void __init xen_pagetable_setup_start(pgd_t *base)
-{
-}
+static void xen_post_allocator_init(void);
static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
{
@@ -1192,14 +1191,87 @@ static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
}
}
-static void xen_post_allocator_init(void);
+#ifdef CONFIG_X86_64
+static void __init xen_cleanhighmap(unsigned long vaddr,
+ unsigned long vaddr_end)
+{
+ unsigned long kernel_end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
+ pmd_t *pmd = level2_kernel_pgt + pmd_index(vaddr);
-static void __init xen_pagetable_setup_done(pgd_t *base)
+ /* NOTE: The loop is more greedy than the cleanup_highmap variant.
+ * We include the PMD passed in on _both_ boundaries. */
+ for (; vaddr <= vaddr_end && (pmd < (level2_kernel_pgt + PAGE_SIZE));
+ pmd++, vaddr += PMD_SIZE) {
+ if (pmd_none(*pmd))
+ continue;
+ if (vaddr < (unsigned long) _text || vaddr > kernel_end)
+ set_pmd(pmd, __pmd(0));
+ }
+ /* In case we did something silly, we should crash in this function
+ * instead of somewhere later and be confusing. */
+ xen_mc_flush();
+}
+#endif
+static void __init xen_pagetable_init(void)
{
+#ifdef CONFIG_X86_64
+ unsigned long size;
+ unsigned long addr;
+#endif
+ paging_init();
xen_setup_shared_info();
+#ifdef CONFIG_X86_64
+ if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ unsigned long new_mfn_list;
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+
+ /* On 32-bit, we get zero so this never gets executed. */
+ new_mfn_list = xen_revector_p2m_tree();
+ if (new_mfn_list && new_mfn_list != xen_start_info->mfn_list) {
+ /* using __ka address and sticking INVALID_P2M_ENTRY! */
+ memset((void *)xen_start_info->mfn_list, 0xff, size);
+
+ /* We should be in __ka space. */
+ BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map);
+ addr = xen_start_info->mfn_list;
+ /* We roundup to the PMD, which means that if anybody at this stage is
+ * using the __ka address of xen_start_info or xen_start_info->shared_info
+ * they are in going to crash. Fortunatly we have already revectored
+ * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */
+ size = roundup(size, PMD_SIZE);
+ xen_cleanhighmap(addr, addr + size);
+
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+ memblock_free(__pa(xen_start_info->mfn_list), size);
+ /* And revector! Bye bye old array */
+ xen_start_info->mfn_list = new_mfn_list;
+ } else
+ goto skip;
+ }
+ /* At this stage, cleanup_highmap has already cleaned __ka space
+ * from _brk_limit way up to the max_pfn_mapped (which is the end of
+ * the ramdisk). We continue on, erasing PMD entries that point to page
+ * tables - do note that they are accessible at this stage via __va.
+ * For good measure we also round up to the PMD - which means that if
+ * anybody is using __ka address to the initial boot-stack - and try
+ * to use it - they are going to crash. The xen_start_info has been
+ * taken care of already in xen_setup_kernel_pagetable. */
+ addr = xen_start_info->pt_base;
+ size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+
+ xen_cleanhighmap(addr, addr + size);
+ xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
+#ifdef DEBUG
+ /* This is superflous and is not neccessary, but you know what
+ * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
+ * anything at this stage. */
+ xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
+#endif
+skip:
+#endif
xen_post_allocator_init();
}
-
static void xen_write_cr2(unsigned long cr2)
{
this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
@@ -1283,7 +1355,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
- if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
+ if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
args->op.cmd = MMUEXT_INVLPG_MULTI;
args->op.arg1.linear_addr = start;
}
@@ -1655,7 +1727,7 @@ static void set_page_prot(void *addr, pgprot_t prot)
if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
BUG();
}
-
+#ifdef CONFIG_X86_32
static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
{
unsigned pmdidx, pteidx;
@@ -1706,7 +1778,7 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
set_page_prot(pmd, PAGE_KERNEL_RO);
}
-
+#endif
void __init xen_setup_machphys_mapping(void)
{
struct xen_machphys_mapping mapping;
@@ -1734,7 +1806,20 @@ static void convert_pfn_mfn(void *v)
for (i = 0; i < PTRS_PER_PTE; i++)
pte[i] = xen_make_pte(pte[i].pte);
}
-
+static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
+ unsigned long addr)
+{
+ if (*pt_base == PFN_DOWN(__pa(addr))) {
+ set_page_prot((void *)addr, PAGE_KERNEL);
+ clear_page((void *)addr);
+ (*pt_base)++;
+ }
+ if (*pt_end == PFN_DOWN(__pa(addr))) {
+ set_page_prot((void *)addr, PAGE_KERNEL);
+ clear_page((void *)addr);
+ (*pt_end)--;
+ }
+}
/*
* Set up the initial kernel pagetable.
*
@@ -1746,11 +1831,13 @@ static void convert_pfn_mfn(void *v)
* of the physical mapping once some sort of allocator has been set
* up.
*/
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
pud_t *l3;
pmd_t *l2;
+ unsigned long addr[3];
+ unsigned long pt_base, pt_end;
+ unsigned i;
/* max_pfn_mapped is the last pfn mapped in the initial memory
* mappings. Considering that on Xen after the kernel mappings we
@@ -1758,32 +1845,53 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
* set max_pfn_mapped to the last real pfn mapped. */
max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+ pt_base = PFN_DOWN(__pa(xen_start_info->pt_base));
+ pt_end = pt_base + xen_start_info->nr_pt_frames;
+
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
/* Pre-constructed entries are in pfn, so convert to mfn */
+ /* L4[272] -> level3_ident_pgt
+ * L4[511] -> level3_kernel_pgt */
convert_pfn_mfn(init_level4_pgt);
+
+ /* L3_i[0] -> level2_ident_pgt */
convert_pfn_mfn(level3_ident_pgt);
+ /* L3_k[510] -> level2_kernel_pgt
+ * L3_i[511] -> level2_fixmap_pgt */
convert_pfn_mfn(level3_kernel_pgt);
+ /* We get [511][511] and have Xen's version of level2_kernel_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
- memcpy(level2_ident_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
- memcpy(level2_kernel_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
+ addr[0] = (unsigned long)pgd;
+ addr[1] = (unsigned long)l3;
+ addr[2] = (unsigned long)l2;
+ /* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
+ * Both L4[272][0] and L4[511][511] have entries that point to the same
+ * L2 (PMD) tables. Meaning that if you modify it in __va space
+ * it will be also modified in the __ka space! (But if you just
+ * modify the PMD table to point to other PTE's or none, then you
+ * are OK - which is what cleanup_highmap does) */
+ copy_page(level2_ident_pgt, l2);
+ /* Graft it onto L4[511][511] */
+ copy_page(level2_kernel_pgt, l2);
+
+ /* Get [511][510] and graft that in level2_fixmap_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
- memcpy(level2_fixmap_pgt, l2, sizeof(pmd_t) * PTRS_PER_PMD);
-
- /* Set up identity map */
- xen_map_identity_early(level2_ident_pgt, max_pfn);
+ copy_page(level2_fixmap_pgt, l2);
+ /* Note that we don't do anything with level1_fixmap_pgt which
+ * we don't need. */
/* Make pagetable pieces RO */
set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
@@ -1794,22 +1902,28 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
/* Unpin Xen-provided one */
pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- /* Switch over */
- pgd = init_level4_pgt;
-
/*
* At this stage there can be no user pgd, and no page
* structure to attach it to, so make sure we just set kernel
* pgd.
*/
xen_mc_batch();
- __xen_write_cr3(true, __pa(pgd));
+ __xen_write_cr3(true, __pa(init_level4_pgt));
xen_mc_issue(PARAVIRT_LAZY_CPU);
- memblock_reserve(__pa(xen_start_info->pt_base),
- xen_start_info->nr_pt_frames * PAGE_SIZE);
+ /* We can't that easily rip out L3 and L2, as the Xen pagetables are
+ * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for
+ * the initial domain. For guests using the toolstack, they are in:
+ * [L4], [L3], [L2], [L1], [L1], order .. So for dom0 we can only
+ * rip out the [L4] (pgd), but for guests we shave off three pages.
+ */
+ for (i = 0; i < ARRAY_SIZE(addr); i++)
+ check_pt_base(&pt_base, &pt_end, addr[i]);
- return pgd;
+ /* Our (by three pages) smaller Xen pagetable that we are using */
+ memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE);
+ /* Revector the xen_start_info */
+ xen_start_info = (struct start_info *)__va(__pa(xen_start_info));
}
#else /* !CONFIG_X86_64 */
static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
@@ -1834,8 +1948,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
*/
swapper_kernel_pmd =
extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
- memcpy(swapper_kernel_pmd, initial_kernel_pmd,
- sizeof(pmd_t) * PTRS_PER_PMD);
+ copy_page(swapper_kernel_pmd, initial_kernel_pmd);
swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
__pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
@@ -1852,8 +1965,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
pv_mmu_ops.write_cr3 = &xen_write_cr3;
}
-pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
- unsigned long max_pfn)
+void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
{
pmd_t *kernel_pmd;
@@ -1865,11 +1977,11 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
512*1024);
kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
- memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+ copy_page(initial_kernel_pmd, kernel_pmd);
xen_map_identity_early(initial_kernel_pmd, max_pfn);
- memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+ copy_page(initial_page_table, pgd);
initial_page_table[KERNEL_PGD_BOUNDARY] =
__pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
@@ -1885,8 +1997,6 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
memblock_reserve(__pa(xen_start_info->pt_base),
xen_start_info->nr_pt_frames * PAGE_SIZE);
-
- return initial_page_table;
}
#endif /* CONFIG_X86_64 */
@@ -2068,8 +2178,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
void __init xen_init_mmu_ops(void)
{
x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
- x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
- x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
+ x86_init.paging.pagetable_init = xen_pagetable_init;
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
@@ -2337,6 +2446,9 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
unsigned long range;
int err = 0;
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return -EINVAL;
+
prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
@@ -2355,8 +2467,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
if (err)
goto out;
- err = -EFAULT;
- if (HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid) < 0)
+ err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid);
+ if (err < 0)
goto out;
nr -= batch;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index d4b25546325..95fb2aa5927 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -22,7 +22,7 @@
*
* P2M_PER_PAGE depends on the architecture, as a mfn is always
* unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
- * 512 and 1024 entries respectively.
+ * 512 and 1024 entries respectively.
*
* In short, these structures contain the Machine Frame Number (MFN) of the PFN.
*
@@ -139,11 +139,11 @@
* / | ~0, ~0, .... |
* | \---------------/
* |
- * p2m_missing p2m_missing
- * /------------------\ /------------\
- * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
- * | [p2m_mid_missing]+---->| ..., ~0 |
- * \------------------/ \------------/
+ * p2m_mid_missing p2m_missing
+ * /-----------------\ /------------\
+ * | [p2m_missing] +---->| ~0, ~0, ~0 |
+ * | [p2m_missing] +---->| ..., ~0 |
+ * \-----------------/ \------------/
*
* where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
*/
@@ -396,7 +396,85 @@ void __init xen_build_dynamic_phys_to_machine(void)
m2p_override_init();
}
+#ifdef CONFIG_X86_64
+#include <linux/bootmem.h>
+unsigned long __init xen_revector_p2m_tree(void)
+{
+ unsigned long va_start;
+ unsigned long va_end;
+ unsigned long pfn;
+ unsigned long pfn_free = 0;
+ unsigned long *mfn_list = NULL;
+ unsigned long size;
+
+ va_start = xen_start_info->mfn_list;
+ /*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long),
+ * so make sure it is rounded up to that */
+ size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
+ va_end = va_start + size;
+
+ /* If we were revectored already, don't do it again. */
+ if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET)
+ return 0;
+
+ mfn_list = alloc_bootmem_align(size, PAGE_SIZE);
+ if (!mfn_list) {
+ pr_warn("Could not allocate space for a new P2M tree!\n");
+ return xen_start_info->mfn_list;
+ }
+ /* Fill it out with INVALID_P2M_ENTRY value */
+ memset(mfn_list, 0xFF, size);
+
+ for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) {
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx;
+ unsigned long *mid_p;
+
+ if (!p2m_top[topidx])
+ continue;
+ if (p2m_top[topidx] == p2m_mid_missing)
+ continue;
+
+ mididx = p2m_mid_index(pfn);
+ mid_p = p2m_top[topidx][mididx];
+ if (!mid_p)
+ continue;
+ if ((mid_p == p2m_missing) || (mid_p == p2m_identity))
+ continue;
+
+ if ((unsigned long)mid_p == INVALID_P2M_ENTRY)
+ continue;
+
+ /* The old va. Rebase it on mfn_list */
+ if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) {
+ unsigned long *new;
+
+ if (pfn_free > (size / sizeof(unsigned long))) {
+ WARN(1, "Only allocated for %ld pages, but we want %ld!\n",
+ size / sizeof(unsigned long), pfn_free);
+ return 0;
+ }
+ new = &mfn_list[pfn_free];
+
+ copy_page(new, mid_p);
+ p2m_top[topidx][mididx] = &mfn_list[pfn_free];
+ p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn_free]);
+
+ pfn_free += P2M_PER_PAGE;
+
+ }
+ /* This should be the leafs allocated for identity from _brk. */
+ }
+ return (unsigned long)mfn_list;
+
+}
+#else
+unsigned long __init xen_revector_p2m_tree(void)
+{
+ return 0;
+}
+#endif
unsigned long get_phys_to_machine(unsigned long pfn)
{
unsigned topidx, mididx, idx;
@@ -430,7 +508,7 @@ static void free_p2m_page(void *p)
free_page((unsigned long)p);
}
-/*
+/*
* Fully allocate the p2m structure for a given pfn. We need to check
* that both the top and mid levels are allocated, and make sure the
* parallel mfn tree is kept in sync. We may race with other cpus, so
@@ -599,7 +677,7 @@ bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_
if (p2m_index(set_pfn))
return false;
- for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
+ for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
topidx = p2m_top_index(pfn);
if (!p2m_top[topidx])
@@ -828,9 +906,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
xen_mc_issue(PARAVIRT_LAZY_MMU);
}
- /* let's use dev_bus_addr to record the old mfn instead */
- kmap_op->dev_bus_addr = page->index;
- page->index = (unsigned long) kmap_op;
}
spin_lock_irqsave(&m2p_override_lock, flags);
list_add(&page->lru, &m2p_overrides[mfn_hash(mfn)]);
@@ -857,7 +932,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
return 0;
}
EXPORT_SYMBOL_GPL(m2p_add_override);
-int m2p_remove_override(struct page *page, bool clear_pte)
+int m2p_remove_override(struct page *page,
+ struct gnttab_map_grant_ref *kmap_op)
{
unsigned long flags;
unsigned long mfn;
@@ -887,10 +963,8 @@ int m2p_remove_override(struct page *page, bool clear_pte)
WARN_ON(!PagePrivate(page));
ClearPagePrivate(page);
- if (clear_pte) {
- struct gnttab_map_grant_ref *map_op =
- (struct gnttab_map_grant_ref *) page->index;
- set_phys_to_machine(pfn, map_op->dev_bus_addr);
+ set_phys_to_machine(pfn, page->index);
+ if (kmap_op != NULL) {
if (!PageHighMem(page)) {
struct multicall_space mcs;
struct gnttab_unmap_grant_ref *unmap_op;
@@ -902,13 +976,13 @@ int m2p_remove_override(struct page *page, bool clear_pte)
* issued. In this case handle is going to -1 because
* it hasn't been modified yet.
*/
- if (map_op->handle == -1)
+ if (kmap_op->handle == -1)
xen_mc_flush();
/*
- * Now if map_op->handle is negative it means that the
+ * Now if kmap_op->handle is negative it means that the
* hypercall actually returned an error.
*/
- if (map_op->handle == GNTST_general_error) {
+ if (kmap_op->handle == GNTST_general_error) {
printk(KERN_WARNING "m2p_remove_override: "
"pfn %lx mfn %lx, failed to modify kernel mappings",
pfn, mfn);
@@ -918,8 +992,8 @@ int m2p_remove_override(struct page *page, bool clear_pte)
mcs = xen_mc_entry(
sizeof(struct gnttab_unmap_grant_ref));
unmap_op = mcs.args;
- unmap_op->host_addr = map_op->host_addr;
- unmap_op->handle = map_op->handle;
+ unmap_op->host_addr = kmap_op->host_addr;
+ unmap_op->handle = kmap_op->handle;
unmap_op->dev_bus_addr = 0;
MULTI_grant_table_op(mcs.mc,
@@ -930,10 +1004,9 @@ int m2p_remove_override(struct page *page, bool clear_pte)
set_pte_at(&init_mm, address, ptep,
pfn_pte(pfn, PAGE_KERNEL));
__flush_tlb_single(address);
- map_op->host_addr = 0;
+ kmap_op->host_addr = 0;
}
- } else
- set_phys_to_machine(pfn, page->index);
+ }
/* p2m(m2p(mfn)) == FOREIGN_FRAME(mfn): the mfn is already present
* somewhere in this domain, even before being added to the
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index 967633ad98c..969570491c3 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -8,6 +8,14 @@
#include <xen/xen.h>
#include <asm/iommu_table.h>
+
+#include <asm/xen/swiotlb-xen.h>
+#ifdef CONFIG_X86_64
+#include <asm/iommu.h>
+#include <asm/dma.h>
+#endif
+#include <linux/export.h>
+
int xen_swiotlb __read_mostly;
static struct dma_map_ops xen_swiotlb_dma_ops = {
@@ -34,34 +42,64 @@ static struct dma_map_ops xen_swiotlb_dma_ops = {
int __init pci_xen_swiotlb_detect(void)
{
+ if (!xen_pv_domain())
+ return 0;
+
/* If running as PV guest, either iommu=soft, or swiotlb=force will
* activate this IOMMU. If running as PV privileged, activate it
* irregardless.
*/
- if ((xen_initial_domain() || swiotlb || swiotlb_force) &&
- (xen_pv_domain()))
+ if ((xen_initial_domain() || swiotlb || swiotlb_force))
xen_swiotlb = 1;
/* If we are running under Xen, we MUST disable the native SWIOTLB.
* Don't worry about swiotlb_force flag activating the native, as
* the 'swiotlb' flag is the only one turning it on. */
- if (xen_pv_domain())
- swiotlb = 0;
+ swiotlb = 0;
+#ifdef CONFIG_X86_64
+ /* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0
+ * (so no iommu=X command line over-writes).
+ * Considering that PV guests do not want the *native SWIOTLB* but
+ * only Xen SWIOTLB it is not useful to us so set no_iommu=1 here.
+ */
+ if (max_pfn > MAX_DMA32_PFN)
+ no_iommu = 1;
+#endif
return xen_swiotlb;
}
void __init pci_xen_swiotlb_init(void)
{
if (xen_swiotlb) {
- xen_swiotlb_init(1);
+ xen_swiotlb_init(1, true /* early */);
dma_ops = &xen_swiotlb_dma_ops;
/* Make sure ACS will be enabled */
pci_request_acs();
}
}
+
+int pci_xen_swiotlb_init_late(void)
+{
+ int rc;
+
+ if (xen_swiotlb)
+ return 0;
+
+ rc = xen_swiotlb_init(1, false /* late */);
+ if (rc)
+ return rc;
+
+ dma_ops = &xen_swiotlb_dma_ops;
+ /* Make sure ACS will be enabled */
+ pci_request_acs();
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pci_xen_swiotlb_init_late);
+
IOMMU_INIT_FINISH(pci_xen_swiotlb_detect,
- 0,
+ NULL,
pci_xen_swiotlb_init,
- 0);
+ NULL);
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index ffcf2615640..0a7852483ff 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -24,6 +24,7 @@
#include <linux/module.h>
#include <xen/platform_pci.h>
+#include "xen-ops.h"
#define XEN_PLATFORM_ERR_MAGIC -1
#define XEN_PLATFORM_ERR_PROTOCOL -2
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index d11ca11d14f..8971a26d21a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -17,6 +17,7 @@
#include <asm/e820.h>
#include <asm/setup.h>
#include <asm/acpi.h>
+#include <asm/numa.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
@@ -431,6 +432,24 @@ char * __init xen_memory_setup(void)
* - mfn_list
* - xen_start_info
* See comment above "struct start_info" in <xen/interface/xen.h>
+ * We tried to make the the memblock_reserve more selective so
+ * that it would be clear what region is reserved. Sadly we ran
+ * in the problem wherein on a 64-bit hypervisor with a 32-bit
+ * initial domain, the pt_base has the cr3 value which is not
+ * neccessarily where the pagetable starts! As Jan put it: "
+ * Actually, the adjustment turns out to be correct: The page
+ * tables for a 32-on-64 dom0 get allocated in the order "first L1",
+ * "first L2", "first L3", so the offset to the page table base is
+ * indeed 2. When reading xen/include/public/xen.h's comment
+ * very strictly, this is not a violation (since there nothing is said
+ * that the first thing in the page table space is pointed to by
+ * pt_base; I admit that this seems to be implied though, namely
+ * do I think that it is implied that the page table space is the
+ * range [pt_base, pt_base + nt_pt_frames), whereas that
+ * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames),
+ * which - without a priori knowledge - the kernel would have
+ * difficulty to figure out)." - so lets just fall back to the
+ * easy way and reserve the whole region.
*/
memblock_reserve(__pa(xen_start_info->mfn_list),
xen_start_info->pt_base - xen_start_info->mfn_list);
@@ -544,4 +563,7 @@ void __init xen_arch_setup(void)
disable_cpufreq();
WARN_ON(set_pm_idle_to_default());
fiddle_vdso();
+#ifdef CONFIG_NUMA
+ numa_off = 1;
+#endif
}
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index f58dca7a6e5..353c50f1870 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -377,7 +377,8 @@ static int __cpuinit xen_cpu_up(unsigned int cpu, struct task_struct *idle)
return rc;
if (num_online_cpus() == 1)
- alternatives_smp_switch(1);
+ /* Just in case we booted with a single CPU. */
+ alternatives_enable_smp();
rc = xen_smp_intr_init(cpu);
if (rc)
@@ -424,9 +425,6 @@ static void xen_cpu_die(unsigned int cpu)
unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
-
- if (num_online_cpus() == 1)
- alternatives_smp_switch(0);
}
static void __cpuinit xen_play_dead(void) /* used only with HOTPLUG_CPU */
diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c
index 1cd7f4d11e2..6722e3733f0 100644
--- a/arch/x86/xen/vga.c
+++ b/arch/x86/xen/vga.c
@@ -35,6 +35,7 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
info->u.text_mode_3.font_height;
break;
+ case XEN_VGATYPE_EFI_LFB:
case XEN_VGATYPE_VESA_LFB:
if (size < offsetof(struct dom0_vga_console_info,
u.vesa_lfb.gbl_caps))
@@ -54,6 +55,12 @@ void __init xen_init_vga(const struct dom0_vga_console_info *info, size_t size)
screen_info->blue_pos = info->u.vesa_lfb.blue_pos;
screen_info->rsvd_size = info->u.vesa_lfb.rsvd_size;
screen_info->rsvd_pos = info->u.vesa_lfb.rsvd_pos;
+
+ if (info->video_type == XEN_VGATYPE_EFI_LFB) {
+ screen_info->orig_video_isVGA = VIDEO_TYPE_EFI;
+ break;
+ }
+
if (size >= offsetof(struct dom0_vga_console_info,
u.vesa_lfb.gbl_caps)
+ sizeof(info->u.vesa_lfb.gbl_caps))
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index aaa7291c925..7faed5869e5 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -28,9 +28,61 @@ ENTRY(startup_xen)
__FINIT
.pushsection .text
- .align PAGE_SIZE
+ .balign PAGE_SIZE
ENTRY(hypercall_page)
- .skip PAGE_SIZE
+#define NEXT_HYPERCALL(x) \
+ ENTRY(xen_hypercall_##x) \
+ .skip 32
+
+NEXT_HYPERCALL(set_trap_table)
+NEXT_HYPERCALL(mmu_update)
+NEXT_HYPERCALL(set_gdt)
+NEXT_HYPERCALL(stack_switch)
+NEXT_HYPERCALL(set_callbacks)
+NEXT_HYPERCALL(fpu_taskswitch)
+NEXT_HYPERCALL(sched_op_compat)
+NEXT_HYPERCALL(platform_op)
+NEXT_HYPERCALL(set_debugreg)
+NEXT_HYPERCALL(get_debugreg)
+NEXT_HYPERCALL(update_descriptor)
+NEXT_HYPERCALL(ni)
+NEXT_HYPERCALL(memory_op)
+NEXT_HYPERCALL(multicall)
+NEXT_HYPERCALL(update_va_mapping)
+NEXT_HYPERCALL(set_timer_op)
+NEXT_HYPERCALL(event_channel_op_compat)
+NEXT_HYPERCALL(xen_version)
+NEXT_HYPERCALL(console_io)
+NEXT_HYPERCALL(physdev_op_compat)
+NEXT_HYPERCALL(grant_table_op)
+NEXT_HYPERCALL(vm_assist)
+NEXT_HYPERCALL(update_va_mapping_otherdomain)
+NEXT_HYPERCALL(iret)
+NEXT_HYPERCALL(vcpu_op)
+NEXT_HYPERCALL(set_segment_base)
+NEXT_HYPERCALL(mmuext_op)
+NEXT_HYPERCALL(xsm_op)
+NEXT_HYPERCALL(nmi_op)
+NEXT_HYPERCALL(sched_op)
+NEXT_HYPERCALL(callback_op)
+NEXT_HYPERCALL(xenoprof_op)
+NEXT_HYPERCALL(event_channel_op)
+NEXT_HYPERCALL(physdev_op)
+NEXT_HYPERCALL(hvm_op)
+NEXT_HYPERCALL(sysctl)
+NEXT_HYPERCALL(domctl)
+NEXT_HYPERCALL(kexec_op)
+NEXT_HYPERCALL(tmem_op) /* 38 */
+ENTRY(xen_hypercall_rsvr)
+ .skip 320
+NEXT_HYPERCALL(mca) /* 48 */
+NEXT_HYPERCALL(arch_1)
+NEXT_HYPERCALL(arch_2)
+NEXT_HYPERCALL(arch_3)
+NEXT_HYPERCALL(arch_4)
+NEXT_HYPERCALL(arch_5)
+NEXT_HYPERCALL(arch_6)
+ .balign PAGE_SIZE
.popsection
ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux")
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 202d4c15015..a95b41744ad 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -27,7 +27,7 @@ void xen_setup_mfn_list_list(void);
void xen_setup_shared_info(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
-pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
+void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
void xen_reserve_top(void);
extern unsigned long xen_max_p2m_pfn;
@@ -35,7 +35,6 @@ void xen_set_pat(u64);
char * __init xen_memory_setup(void);
void __init xen_arch_setup(void);
-void __init xen_init_IRQ(void);
void xen_enable_sysenter(void);
void xen_enable_syscall(void);
void xen_vcpu_restore(void);
@@ -45,6 +44,7 @@ void xen_hvm_init_shared_info(void);
void xen_unplug_emulated_devices(void);
void __init xen_build_dynamic_phys_to_machine(void);
+unsigned long __init xen_revector_p2m_tree(void);
void xen_init_irq_ops(void);
void xen_setup_timer(int cpu);